{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 504693, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.9442076668390486e-05, "grad_norm": 12.547857284545898, "learning_rate": 3.566475133742818e-08, "loss": 4.593567657470703, "step": 10 }, { "epoch": 0.00011888415333678097, "grad_norm": 13.390036582946777, "learning_rate": 7.529225282345949e-08, "loss": 4.458981704711914, "step": 20 }, { "epoch": 0.00017832623000517146, "grad_norm": 17.37639617919922, "learning_rate": 1.1491975430949078e-07, "loss": 4.652117156982422, "step": 30 }, { "epoch": 0.00023776830667356194, "grad_norm": 11.95329761505127, "learning_rate": 1.5454725579552208e-07, "loss": 4.3567253112792965, "step": 40 }, { "epoch": 0.00029721038334195243, "grad_norm": 11.665525436401367, "learning_rate": 1.941747572815534e-07, "loss": 4.507932662963867, "step": 50 }, { "epoch": 0.0003566524600103429, "grad_norm": 13.051751136779785, "learning_rate": 2.3380225876758473e-07, "loss": 4.218190002441406, "step": 60 }, { "epoch": 0.0004160945366787334, "grad_norm": 13.08608341217041, "learning_rate": 2.73429760253616e-07, "loss": 4.346537017822266, "step": 70 }, { "epoch": 0.0004755366133471239, "grad_norm": 10.560647964477539, "learning_rate": 3.130572617396473e-07, "loss": 4.193457412719726, "step": 80 }, { "epoch": 0.0005349786900155144, "grad_norm": 13.427597999572754, "learning_rate": 3.526847632256786e-07, "loss": 4.260939025878907, "step": 90 }, { "epoch": 0.0005944207666839049, "grad_norm": 12.506022453308105, "learning_rate": 3.923122647117099e-07, "loss": 4.29034194946289, "step": 100 }, { "epoch": 0.0006538628433522954, "grad_norm": 12.120749473571777, "learning_rate": 4.3193976619774126e-07, "loss": 4.3617706298828125, "step": 110 }, { "epoch": 0.0007133049200206858, "grad_norm": 9.279792785644531, "learning_rate": 4.7156726768377255e-07, "loss": 4.151397705078125, "step": 120 }, { "epoch": 0.0007727469966890764, "grad_norm": 9.696342468261719, "learning_rate": 5.111947691698039e-07, "loss": 3.9262859344482424, "step": 130 }, { "epoch": 0.0008321890733574668, "grad_norm": 6.447898864746094, "learning_rate": 5.508222706558353e-07, "loss": 3.891461944580078, "step": 140 }, { "epoch": 0.0008916311500258573, "grad_norm": 7.808491230010986, "learning_rate": 5.904497721418665e-07, "loss": 4.081196594238281, "step": 150 }, { "epoch": 0.0009510732266942478, "grad_norm": 8.199882507324219, "learning_rate": 6.300772736278977e-07, "loss": 3.7815555572509765, "step": 160 }, { "epoch": 0.0010105153033626382, "grad_norm": 6.786199569702148, "learning_rate": 6.697047751139291e-07, "loss": 3.752734375, "step": 170 }, { "epoch": 0.0010699573800310289, "grad_norm": 6.380858898162842, "learning_rate": 7.093322765999604e-07, "loss": 3.6628391265869142, "step": 180 }, { "epoch": 0.0011293994566994193, "grad_norm": 7.138105869293213, "learning_rate": 7.489597780859917e-07, "loss": 3.681249237060547, "step": 190 }, { "epoch": 0.0011888415333678097, "grad_norm": 6.539507865905762, "learning_rate": 7.88587279572023e-07, "loss": 3.3965290069580076, "step": 200 }, { "epoch": 0.0012482836100362001, "grad_norm": 5.700268745422363, "learning_rate": 8.282147810580543e-07, "loss": 3.352864074707031, "step": 210 }, { "epoch": 0.0013077256867045908, "grad_norm": 5.3058342933654785, "learning_rate": 8.678422825440856e-07, "loss": 3.2862625122070312, "step": 220 }, { "epoch": 0.0013671677633729812, "grad_norm": 5.600744247436523, "learning_rate": 9.074697840301169e-07, "loss": 3.2194133758544923, "step": 230 }, { "epoch": 0.0014266098400413717, "grad_norm": 5.093986988067627, "learning_rate": 9.470972855161483e-07, "loss": 3.15503044128418, "step": 240 }, { "epoch": 0.001486051916709762, "grad_norm": 5.055179119110107, "learning_rate": 9.867247870021795e-07, "loss": 3.085689163208008, "step": 250 }, { "epoch": 0.0015454939933781527, "grad_norm": 4.466731548309326, "learning_rate": 1.0263522884882107e-06, "loss": 3.0236684799194338, "step": 260 }, { "epoch": 0.0016049360700465432, "grad_norm": 5.0164642333984375, "learning_rate": 1.0659797899742422e-06, "loss": 2.7900053024291993, "step": 270 }, { "epoch": 0.0016643781467149336, "grad_norm": 5.193600177764893, "learning_rate": 1.1056072914602734e-06, "loss": 3.0033697128295898, "step": 280 }, { "epoch": 0.001723820223383324, "grad_norm": 4.373141765594482, "learning_rate": 1.1452347929463048e-06, "loss": 2.7500289916992187, "step": 290 }, { "epoch": 0.0017832623000517147, "grad_norm": 4.745594501495361, "learning_rate": 1.184862294432336e-06, "loss": 2.7729488372802735, "step": 300 }, { "epoch": 0.0018427043767201051, "grad_norm": 4.587249755859375, "learning_rate": 1.2244897959183673e-06, "loss": 2.7224273681640625, "step": 310 }, { "epoch": 0.0019021464533884955, "grad_norm": 3.7488768100738525, "learning_rate": 1.2641172974043988e-06, "loss": 2.6072879791259767, "step": 320 }, { "epoch": 0.001961588530056886, "grad_norm": 4.392887592315674, "learning_rate": 1.30374479889043e-06, "loss": 2.6210964202880858, "step": 330 }, { "epoch": 0.0020210306067252764, "grad_norm": 3.2508153915405273, "learning_rate": 1.3433723003764615e-06, "loss": 2.5716989517211912, "step": 340 }, { "epoch": 0.002080472683393667, "grad_norm": 4.4272966384887695, "learning_rate": 1.3829998018624927e-06, "loss": 2.5584270477294924, "step": 350 }, { "epoch": 0.0021399147600620577, "grad_norm": 3.770786762237549, "learning_rate": 1.422627303348524e-06, "loss": 2.503190803527832, "step": 360 }, { "epoch": 0.002199356836730448, "grad_norm": 3.240497589111328, "learning_rate": 1.4622548048345552e-06, "loss": 2.4690616607666014, "step": 370 }, { "epoch": 0.0022587989133988386, "grad_norm": 3.9229037761688232, "learning_rate": 1.5018823063205865e-06, "loss": 2.3468517303466796, "step": 380 }, { "epoch": 0.0023182409900672288, "grad_norm": 2.6868956089019775, "learning_rate": 1.5415098078066177e-06, "loss": 2.1173656463623045, "step": 390 }, { "epoch": 0.0023776830667356194, "grad_norm": 3.0260398387908936, "learning_rate": 1.581137309292649e-06, "loss": 2.3103336334228515, "step": 400 }, { "epoch": 0.00243712514340401, "grad_norm": 2.6161420345306396, "learning_rate": 1.6207648107786806e-06, "loss": 2.2241397857666017, "step": 410 }, { "epoch": 0.0024965672200724003, "grad_norm": 2.758397102355957, "learning_rate": 1.6603923122647119e-06, "loss": 2.1461421966552736, "step": 420 }, { "epoch": 0.002556009296740791, "grad_norm": 2.8277618885040283, "learning_rate": 1.700019813750743e-06, "loss": 2.1255718231201173, "step": 430 }, { "epoch": 0.0026154513734091816, "grad_norm": 2.8993077278137207, "learning_rate": 1.7396473152367743e-06, "loss": 2.0189846038818358, "step": 440 }, { "epoch": 0.002674893450077572, "grad_norm": 2.6321985721588135, "learning_rate": 1.7792748167228056e-06, "loss": 1.9078250885009767, "step": 450 }, { "epoch": 0.0027343355267459625, "grad_norm": 2.8338325023651123, "learning_rate": 1.8189023182088372e-06, "loss": 1.949160385131836, "step": 460 }, { "epoch": 0.002793777603414353, "grad_norm": 2.798154830932617, "learning_rate": 1.8585298196948685e-06, "loss": 1.8362945556640624, "step": 470 }, { "epoch": 0.0028532196800827433, "grad_norm": 3.180044651031494, "learning_rate": 1.8981573211808997e-06, "loss": 1.893651580810547, "step": 480 }, { "epoch": 0.002912661756751134, "grad_norm": 2.6773173809051514, "learning_rate": 1.937784822666931e-06, "loss": 1.6419696807861328, "step": 490 }, { "epoch": 0.002972103833419524, "grad_norm": 2.247689962387085, "learning_rate": 1.977412324152962e-06, "loss": 1.6620677947998046, "step": 500 }, { "epoch": 0.003031545910087915, "grad_norm": 2.8047218322753906, "learning_rate": 2.017039825638994e-06, "loss": 1.5621123313903809, "step": 510 }, { "epoch": 0.0030909879867563055, "grad_norm": 2.463456869125366, "learning_rate": 2.056667327125025e-06, "loss": 1.629021453857422, "step": 520 }, { "epoch": 0.0031504300634246957, "grad_norm": 1.9175200462341309, "learning_rate": 2.0962948286110564e-06, "loss": 1.5331878662109375, "step": 530 }, { "epoch": 0.0032098721400930863, "grad_norm": 2.1260855197906494, "learning_rate": 2.1359223300970874e-06, "loss": 1.393486213684082, "step": 540 }, { "epoch": 0.003269314216761477, "grad_norm": 2.1019532680511475, "learning_rate": 2.175549831583119e-06, "loss": 1.4848221778869628, "step": 550 }, { "epoch": 0.003328756293429867, "grad_norm": 1.71958589553833, "learning_rate": 2.2151773330691503e-06, "loss": 1.4835708618164063, "step": 560 }, { "epoch": 0.003388198370098258, "grad_norm": 2.308586835861206, "learning_rate": 2.2548048345551813e-06, "loss": 1.5013245582580566, "step": 570 }, { "epoch": 0.003447640446766648, "grad_norm": 1.6300153732299805, "learning_rate": 2.294432336041213e-06, "loss": 1.3628653526306151, "step": 580 }, { "epoch": 0.0035070825234350387, "grad_norm": 2.2373781204223633, "learning_rate": 2.334059837527244e-06, "loss": 1.375466537475586, "step": 590 }, { "epoch": 0.0035665246001034294, "grad_norm": 1.69536292552948, "learning_rate": 2.3736873390132753e-06, "loss": 1.32600679397583, "step": 600 }, { "epoch": 0.0036259666767718196, "grad_norm": 2.0573527812957764, "learning_rate": 2.4133148404993063e-06, "loss": 1.3495954513549804, "step": 610 }, { "epoch": 0.0036854087534402102, "grad_norm": 2.4061810970306396, "learning_rate": 2.452942341985338e-06, "loss": 1.3859505653381348, "step": 620 }, { "epoch": 0.003744850830108601, "grad_norm": 2.1660585403442383, "learning_rate": 2.4925698434713692e-06, "loss": 1.344762420654297, "step": 630 }, { "epoch": 0.003804292906776991, "grad_norm": 1.763530969619751, "learning_rate": 2.5321973449574007e-06, "loss": 1.2871136665344238, "step": 640 }, { "epoch": 0.0038637349834453817, "grad_norm": 2.0715761184692383, "learning_rate": 2.5718248464434317e-06, "loss": 1.4374876022338867, "step": 650 }, { "epoch": 0.003923177060113772, "grad_norm": 2.574467897415161, "learning_rate": 2.611452347929463e-06, "loss": 1.1907476425170898, "step": 660 }, { "epoch": 0.003982619136782163, "grad_norm": 1.709761142730713, "learning_rate": 2.6510798494154946e-06, "loss": 1.282036018371582, "step": 670 }, { "epoch": 0.004042061213450553, "grad_norm": 1.3968201875686646, "learning_rate": 2.6907073509015257e-06, "loss": 1.335802936553955, "step": 680 }, { "epoch": 0.004101503290118944, "grad_norm": 1.806082844734192, "learning_rate": 2.730334852387557e-06, "loss": 1.3502662658691407, "step": 690 }, { "epoch": 0.004160945366787334, "grad_norm": 1.7691642045974731, "learning_rate": 2.769962353873588e-06, "loss": 1.291712188720703, "step": 700 }, { "epoch": 0.004220387443455724, "grad_norm": 1.9481371641159058, "learning_rate": 2.8095898553596196e-06, "loss": 1.3376205444335938, "step": 710 }, { "epoch": 0.004279829520124115, "grad_norm": 2.260634660720825, "learning_rate": 2.849217356845651e-06, "loss": 1.3174555778503418, "step": 720 }, { "epoch": 0.004339271596792506, "grad_norm": 1.963916301727295, "learning_rate": 2.8888448583316825e-06, "loss": 1.2784785270690917, "step": 730 }, { "epoch": 0.004398713673460896, "grad_norm": 1.7624757289886475, "learning_rate": 2.9284723598177135e-06, "loss": 1.3198506355285644, "step": 740 }, { "epoch": 0.004458155750129287, "grad_norm": 1.6008046865463257, "learning_rate": 2.968099861303745e-06, "loss": 1.3102123260498046, "step": 750 }, { "epoch": 0.004517597826797677, "grad_norm": 2.4310779571533203, "learning_rate": 3.007727362789776e-06, "loss": 1.3348793029785155, "step": 760 }, { "epoch": 0.004577039903466067, "grad_norm": 1.673010230064392, "learning_rate": 3.047354864275808e-06, "loss": 1.3767840385437011, "step": 770 }, { "epoch": 0.0046364819801344576, "grad_norm": 2.0611326694488525, "learning_rate": 3.086982365761839e-06, "loss": 1.2513769149780274, "step": 780 }, { "epoch": 0.004695924056802849, "grad_norm": 2.389101505279541, "learning_rate": 3.12660986724787e-06, "loss": 1.2997237205505372, "step": 790 }, { "epoch": 0.004755366133471239, "grad_norm": 1.9435030221939087, "learning_rate": 3.1662373687339014e-06, "loss": 1.3431902885437013, "step": 800 }, { "epoch": 0.004814808210139629, "grad_norm": 1.748296856880188, "learning_rate": 3.205864870219933e-06, "loss": 1.2593418121337892, "step": 810 }, { "epoch": 0.00487425028680802, "grad_norm": 1.9578890800476074, "learning_rate": 3.245492371705964e-06, "loss": 1.323433017730713, "step": 820 }, { "epoch": 0.00493369236347641, "grad_norm": 1.9602340459823608, "learning_rate": 3.2851198731919954e-06, "loss": 1.3645051956176757, "step": 830 }, { "epoch": 0.004993134440144801, "grad_norm": 2.1934309005737305, "learning_rate": 3.3247473746780264e-06, "loss": 1.3661352157592774, "step": 840 }, { "epoch": 0.005052576516813192, "grad_norm": 2.2002031803131104, "learning_rate": 3.364374876164058e-06, "loss": 1.2709478378295898, "step": 850 }, { "epoch": 0.005112018593481582, "grad_norm": 2.3395707607269287, "learning_rate": 3.4040023776500897e-06, "loss": 1.299694538116455, "step": 860 }, { "epoch": 0.005171460670149972, "grad_norm": 1.984652042388916, "learning_rate": 3.4436298791361203e-06, "loss": 1.2347120285034179, "step": 870 }, { "epoch": 0.005230902746818363, "grad_norm": 1.7387125492095947, "learning_rate": 3.483257380622152e-06, "loss": 1.246932029724121, "step": 880 }, { "epoch": 0.005290344823486753, "grad_norm": 2.0051047801971436, "learning_rate": 3.522884882108183e-06, "loss": 1.2306982040405274, "step": 890 }, { "epoch": 0.005349786900155144, "grad_norm": 2.587726354598999, "learning_rate": 3.5625123835942147e-06, "loss": 1.307435894012451, "step": 900 }, { "epoch": 0.005409228976823535, "grad_norm": 1.8891011476516724, "learning_rate": 3.602139885080246e-06, "loss": 1.3991640090942383, "step": 910 }, { "epoch": 0.005468671053491925, "grad_norm": 1.8450735807418823, "learning_rate": 3.641767386566277e-06, "loss": 1.3072214126586914, "step": 920 }, { "epoch": 0.005528113130160315, "grad_norm": 1.9044897556304932, "learning_rate": 3.6813948880523086e-06, "loss": 1.239403247833252, "step": 930 }, { "epoch": 0.005587555206828706, "grad_norm": 1.9165176153182983, "learning_rate": 3.7210223895383397e-06, "loss": 1.2351875305175781, "step": 940 }, { "epoch": 0.005646997283497096, "grad_norm": 2.3276760578155518, "learning_rate": 3.760649891024371e-06, "loss": 1.2725488662719726, "step": 950 }, { "epoch": 0.005706439360165487, "grad_norm": 1.906380295753479, "learning_rate": 3.8002773925104026e-06, "loss": 1.1973480224609374, "step": 960 }, { "epoch": 0.005765881436833877, "grad_norm": 1.6747221946716309, "learning_rate": 3.839904893996434e-06, "loss": 1.3003731727600099, "step": 970 }, { "epoch": 0.005825323513502268, "grad_norm": 1.8639378547668457, "learning_rate": 3.8795323954824655e-06, "loss": 1.2489897727966308, "step": 980 }, { "epoch": 0.005884765590170658, "grad_norm": 1.9814112186431885, "learning_rate": 3.919159896968496e-06, "loss": 1.1962033271789552, "step": 990 }, { "epoch": 0.005944207666839048, "grad_norm": 2.0583078861236572, "learning_rate": 3.9587873984545275e-06, "loss": 1.2737028121948242, "step": 1000 }, { "epoch": 0.0060036497435074394, "grad_norm": 1.9879194498062134, "learning_rate": 3.9984148999405594e-06, "loss": 1.2790397644042968, "step": 1010 }, { "epoch": 0.00606309182017583, "grad_norm": 2.328688383102417, "learning_rate": 4.0380424014265905e-06, "loss": 1.2361578941345215, "step": 1020 }, { "epoch": 0.00612253389684422, "grad_norm": 1.5993541479110718, "learning_rate": 4.0776699029126215e-06, "loss": 1.2101224899291991, "step": 1030 }, { "epoch": 0.006181975973512611, "grad_norm": 2.091947317123413, "learning_rate": 4.1172974043986525e-06, "loss": 1.299319076538086, "step": 1040 }, { "epoch": 0.006241418050181001, "grad_norm": 1.810735821723938, "learning_rate": 4.156924905884684e-06, "loss": 1.2130346298217773, "step": 1050 }, { "epoch": 0.006300860126849391, "grad_norm": 2.107279062271118, "learning_rate": 4.1965524073707154e-06, "loss": 1.213459587097168, "step": 1060 }, { "epoch": 0.0063603022035177825, "grad_norm": 2.053896427154541, "learning_rate": 4.2361799088567465e-06, "loss": 1.21963472366333, "step": 1070 }, { "epoch": 0.006419744280186173, "grad_norm": 1.873337984085083, "learning_rate": 4.275807410342778e-06, "loss": 1.2330387115478516, "step": 1080 }, { "epoch": 0.006479186356854563, "grad_norm": 2.53079891204834, "learning_rate": 4.315434911828809e-06, "loss": 1.2646854400634766, "step": 1090 }, { "epoch": 0.006538628433522954, "grad_norm": 1.9511581659317017, "learning_rate": 4.35506241331484e-06, "loss": 1.1843045234680176, "step": 1100 }, { "epoch": 0.006598070510191344, "grad_norm": 2.2843620777130127, "learning_rate": 4.394689914800872e-06, "loss": 1.2307806015014648, "step": 1110 }, { "epoch": 0.006657512586859734, "grad_norm": 2.4147608280181885, "learning_rate": 4.434317416286903e-06, "loss": 1.2074855804443358, "step": 1120 }, { "epoch": 0.006716954663528125, "grad_norm": 2.0611631870269775, "learning_rate": 4.473944917772935e-06, "loss": 1.234516716003418, "step": 1130 }, { "epoch": 0.006776396740196516, "grad_norm": 2.0567374229431152, "learning_rate": 4.513572419258965e-06, "loss": 1.2284512519836426, "step": 1140 }, { "epoch": 0.006835838816864906, "grad_norm": 1.9027187824249268, "learning_rate": 4.553199920744997e-06, "loss": 1.2136104583740235, "step": 1150 }, { "epoch": 0.006895280893533296, "grad_norm": 1.7528672218322754, "learning_rate": 4.592827422231029e-06, "loss": 1.2564477920532227, "step": 1160 }, { "epoch": 0.006954722970201687, "grad_norm": 2.0895466804504395, "learning_rate": 4.63245492371706e-06, "loss": 1.143053150177002, "step": 1170 }, { "epoch": 0.007014165046870077, "grad_norm": 2.2818169593811035, "learning_rate": 4.672082425203091e-06, "loss": 1.1990953445434571, "step": 1180 }, { "epoch": 0.007073607123538468, "grad_norm": 2.2058358192443848, "learning_rate": 4.711709926689122e-06, "loss": 1.3032346725463868, "step": 1190 }, { "epoch": 0.007133049200206859, "grad_norm": 2.143037796020508, "learning_rate": 4.751337428175154e-06, "loss": 1.328993320465088, "step": 1200 }, { "epoch": 0.007192491276875249, "grad_norm": 1.8957995176315308, "learning_rate": 4.790964929661185e-06, "loss": 1.2429760932922362, "step": 1210 }, { "epoch": 0.007251933353543639, "grad_norm": 2.0447726249694824, "learning_rate": 4.830592431147216e-06, "loss": 1.1873894691467286, "step": 1220 }, { "epoch": 0.00731137543021203, "grad_norm": 2.4045450687408447, "learning_rate": 4.870219932633248e-06, "loss": 1.1858000755310059, "step": 1230 }, { "epoch": 0.0073708175068804204, "grad_norm": 2.3375132083892822, "learning_rate": 4.909847434119279e-06, "loss": 1.1078206062316895, "step": 1240 }, { "epoch": 0.007430259583548811, "grad_norm": 2.313182830810547, "learning_rate": 4.94947493560531e-06, "loss": 1.216137981414795, "step": 1250 }, { "epoch": 0.007489701660217202, "grad_norm": 2.4107511043548584, "learning_rate": 4.989102437091342e-06, "loss": 1.235244369506836, "step": 1260 }, { "epoch": 0.007549143736885592, "grad_norm": 2.237708330154419, "learning_rate": 5.028729938577373e-06, "loss": 1.216409397125244, "step": 1270 }, { "epoch": 0.007608585813553982, "grad_norm": 1.918287992477417, "learning_rate": 5.068357440063404e-06, "loss": 1.2212602615356445, "step": 1280 }, { "epoch": 0.007668027890222372, "grad_norm": 2.4054017066955566, "learning_rate": 5.107984941549435e-06, "loss": 1.2169641494750976, "step": 1290 }, { "epoch": 0.0077274699668907635, "grad_norm": 2.2550241947174072, "learning_rate": 5.147612443035467e-06, "loss": 1.255579376220703, "step": 1300 }, { "epoch": 0.007786912043559154, "grad_norm": 1.7707178592681885, "learning_rate": 5.187239944521499e-06, "loss": 1.180374526977539, "step": 1310 }, { "epoch": 0.007846354120227545, "grad_norm": 2.18697190284729, "learning_rate": 5.226867446007529e-06, "loss": 1.168604278564453, "step": 1320 }, { "epoch": 0.007905796196895935, "grad_norm": 2.4077091217041016, "learning_rate": 5.266494947493561e-06, "loss": 1.226307487487793, "step": 1330 }, { "epoch": 0.007965238273564325, "grad_norm": 2.6251964569091797, "learning_rate": 5.306122448979592e-06, "loss": 1.2102428436279298, "step": 1340 }, { "epoch": 0.008024680350232715, "grad_norm": 1.643373727798462, "learning_rate": 5.345749950465624e-06, "loss": 1.21323881149292, "step": 1350 }, { "epoch": 0.008084122426901106, "grad_norm": 1.9502496719360352, "learning_rate": 5.385377451951655e-06, "loss": 1.1784034729003907, "step": 1360 }, { "epoch": 0.008143564503569498, "grad_norm": 2.1169586181640625, "learning_rate": 5.425004953437686e-06, "loss": 1.280207061767578, "step": 1370 }, { "epoch": 0.008203006580237888, "grad_norm": 2.305999994277954, "learning_rate": 5.464632454923718e-06, "loss": 1.1457304954528809, "step": 1380 }, { "epoch": 0.008262448656906278, "grad_norm": 2.452604293823242, "learning_rate": 5.504259956409749e-06, "loss": 1.1907512664794921, "step": 1390 }, { "epoch": 0.008321890733574668, "grad_norm": 1.954841136932373, "learning_rate": 5.54388745789578e-06, "loss": 1.1228721618652344, "step": 1400 }, { "epoch": 0.008381332810243058, "grad_norm": 2.204413890838623, "learning_rate": 5.583514959381811e-06, "loss": 1.2708133697509765, "step": 1410 }, { "epoch": 0.008440774886911449, "grad_norm": 2.2230191230773926, "learning_rate": 5.623142460867843e-06, "loss": 1.2312725067138672, "step": 1420 }, { "epoch": 0.008500216963579839, "grad_norm": 2.2446510791778564, "learning_rate": 5.662769962353874e-06, "loss": 1.1774065017700195, "step": 1430 }, { "epoch": 0.00855965904024823, "grad_norm": 2.30896258354187, "learning_rate": 5.702397463839905e-06, "loss": 1.1464827537536622, "step": 1440 }, { "epoch": 0.008619101116916621, "grad_norm": 2.2817347049713135, "learning_rate": 5.742024965325937e-06, "loss": 1.1700960159301759, "step": 1450 }, { "epoch": 0.008678543193585011, "grad_norm": 2.2345309257507324, "learning_rate": 5.781652466811968e-06, "loss": 1.2030136108398437, "step": 1460 }, { "epoch": 0.008737985270253401, "grad_norm": 1.963736653327942, "learning_rate": 5.821279968297999e-06, "loss": 1.14189453125, "step": 1470 }, { "epoch": 0.008797427346921792, "grad_norm": 2.1969823837280273, "learning_rate": 5.860907469784031e-06, "loss": 1.1796487808227538, "step": 1480 }, { "epoch": 0.008856869423590182, "grad_norm": 2.4443254470825195, "learning_rate": 5.900534971270062e-06, "loss": 1.236405372619629, "step": 1490 }, { "epoch": 0.008916311500258574, "grad_norm": 1.9693498611450195, "learning_rate": 5.9401624727560935e-06, "loss": 1.1837812423706056, "step": 1500 }, { "epoch": 0.008975753576926964, "grad_norm": 2.625309944152832, "learning_rate": 5.979789974242124e-06, "loss": 1.1340676307678224, "step": 1510 }, { "epoch": 0.009035195653595354, "grad_norm": 2.448151111602783, "learning_rate": 6.0194174757281556e-06, "loss": 1.2029471397399902, "step": 1520 }, { "epoch": 0.009094637730263744, "grad_norm": 2.926598072052002, "learning_rate": 6.0590449772141874e-06, "loss": 1.1327415466308595, "step": 1530 }, { "epoch": 0.009154079806932135, "grad_norm": 2.4744486808776855, "learning_rate": 6.0986724787002185e-06, "loss": 1.1769068717956543, "step": 1540 }, { "epoch": 0.009213521883600525, "grad_norm": 2.1945319175720215, "learning_rate": 6.1382999801862495e-06, "loss": 1.1526355743408203, "step": 1550 }, { "epoch": 0.009272963960268915, "grad_norm": 2.4360945224761963, "learning_rate": 6.1779274816722805e-06, "loss": 1.1731508255004883, "step": 1560 }, { "epoch": 0.009332406036937307, "grad_norm": 2.2409543991088867, "learning_rate": 6.217554983158312e-06, "loss": 1.1609942436218261, "step": 1570 }, { "epoch": 0.009391848113605697, "grad_norm": 2.792401075363159, "learning_rate": 6.2571824846443435e-06, "loss": 1.1614652633666993, "step": 1580 }, { "epoch": 0.009451290190274087, "grad_norm": 2.6160776615142822, "learning_rate": 6.296809986130375e-06, "loss": 1.1823518753051758, "step": 1590 }, { "epoch": 0.009510732266942478, "grad_norm": 1.999354600906372, "learning_rate": 6.336437487616406e-06, "loss": 1.075180435180664, "step": 1600 }, { "epoch": 0.009570174343610868, "grad_norm": 3.7162833213806152, "learning_rate": 6.376064989102437e-06, "loss": 1.1140410423278808, "step": 1610 }, { "epoch": 0.009629616420279258, "grad_norm": 2.1494338512420654, "learning_rate": 6.415692490588469e-06, "loss": 1.116223430633545, "step": 1620 }, { "epoch": 0.00968905849694765, "grad_norm": 3.063095808029175, "learning_rate": 6.4553199920745e-06, "loss": 1.1473505020141601, "step": 1630 }, { "epoch": 0.00974850057361604, "grad_norm": 2.4404566287994385, "learning_rate": 6.494947493560531e-06, "loss": 1.0853916168212892, "step": 1640 }, { "epoch": 0.00980794265028443, "grad_norm": 2.074312210083008, "learning_rate": 6.534574995046562e-06, "loss": 1.156757640838623, "step": 1650 }, { "epoch": 0.00986738472695282, "grad_norm": 2.0145957469940186, "learning_rate": 6.574202496532594e-06, "loss": 1.176304817199707, "step": 1660 }, { "epoch": 0.009926826803621211, "grad_norm": 2.204904317855835, "learning_rate": 6.613829998018625e-06, "loss": 1.1426580429077149, "step": 1670 }, { "epoch": 0.009986268880289601, "grad_norm": 3.487076997756958, "learning_rate": 6.653457499504656e-06, "loss": 1.1557583808898926, "step": 1680 }, { "epoch": 0.010045710956957993, "grad_norm": 3.027869939804077, "learning_rate": 6.693085000990688e-06, "loss": 1.2003070831298828, "step": 1690 }, { "epoch": 0.010105153033626383, "grad_norm": 2.3687381744384766, "learning_rate": 6.732712502476719e-06, "loss": 1.1285768508911134, "step": 1700 }, { "epoch": 0.010164595110294774, "grad_norm": 2.732112169265747, "learning_rate": 6.77234000396275e-06, "loss": 1.1232206344604492, "step": 1710 }, { "epoch": 0.010224037186963164, "grad_norm": 2.327561855316162, "learning_rate": 6.811967505448781e-06, "loss": 1.1719533920288085, "step": 1720 }, { "epoch": 0.010283479263631554, "grad_norm": 2.838085412979126, "learning_rate": 6.851595006934813e-06, "loss": 1.1724976539611816, "step": 1730 }, { "epoch": 0.010342921340299944, "grad_norm": 2.3860652446746826, "learning_rate": 6.891222508420844e-06, "loss": 1.1320985794067382, "step": 1740 }, { "epoch": 0.010402363416968334, "grad_norm": 3.0965116024017334, "learning_rate": 6.930850009906875e-06, "loss": 1.2318195343017577, "step": 1750 }, { "epoch": 0.010461805493636726, "grad_norm": 2.329529047012329, "learning_rate": 6.970477511392907e-06, "loss": 1.1748472213745118, "step": 1760 }, { "epoch": 0.010521247570305117, "grad_norm": 2.4055938720703125, "learning_rate": 7.010105012878938e-06, "loss": 1.1327917098999023, "step": 1770 }, { "epoch": 0.010580689646973507, "grad_norm": 2.23246693611145, "learning_rate": 7.049732514364969e-06, "loss": 1.1629220962524414, "step": 1780 }, { "epoch": 0.010640131723641897, "grad_norm": 2.6222259998321533, "learning_rate": 7.089360015851002e-06, "loss": 1.1144948959350587, "step": 1790 }, { "epoch": 0.010699573800310287, "grad_norm": 2.897196054458618, "learning_rate": 7.128987517337032e-06, "loss": 1.2093457221984862, "step": 1800 }, { "epoch": 0.010759015876978677, "grad_norm": 2.386474847793579, "learning_rate": 7.168615018823063e-06, "loss": 1.1796555519104004, "step": 1810 }, { "epoch": 0.01081845795364707, "grad_norm": 2.6788275241851807, "learning_rate": 7.208242520309094e-06, "loss": 1.0926705360412599, "step": 1820 }, { "epoch": 0.01087790003031546, "grad_norm": 2.4888904094696045, "learning_rate": 7.247870021795127e-06, "loss": 1.1100961685180664, "step": 1830 }, { "epoch": 0.01093734210698385, "grad_norm": 2.0864386558532715, "learning_rate": 7.287497523281157e-06, "loss": 1.074325180053711, "step": 1840 }, { "epoch": 0.01099678418365224, "grad_norm": 2.697584390640259, "learning_rate": 7.327125024767188e-06, "loss": 1.1688157081604005, "step": 1850 }, { "epoch": 0.01105622626032063, "grad_norm": 2.1800992488861084, "learning_rate": 7.366752526253221e-06, "loss": 1.1088838577270508, "step": 1860 }, { "epoch": 0.01111566833698902, "grad_norm": 2.750476837158203, "learning_rate": 7.406380027739252e-06, "loss": 1.1783902168273925, "step": 1870 }, { "epoch": 0.011175110413657412, "grad_norm": 2.6890718936920166, "learning_rate": 7.446007529225282e-06, "loss": 1.1886281967163086, "step": 1880 }, { "epoch": 0.011234552490325803, "grad_norm": 2.336315155029297, "learning_rate": 7.485635030711315e-06, "loss": 1.0898530960083008, "step": 1890 }, { "epoch": 0.011293994566994193, "grad_norm": 3.138195037841797, "learning_rate": 7.525262532197346e-06, "loss": 1.1946697235107422, "step": 1900 }, { "epoch": 0.011353436643662583, "grad_norm": 2.7784969806671143, "learning_rate": 7.564890033683377e-06, "loss": 1.1116214752197267, "step": 1910 }, { "epoch": 0.011412878720330973, "grad_norm": 2.139389753341675, "learning_rate": 7.604517535169407e-06, "loss": 1.13125638961792, "step": 1920 }, { "epoch": 0.011472320796999363, "grad_norm": 2.2753732204437256, "learning_rate": 7.644145036655439e-06, "loss": 1.1186139106750488, "step": 1930 }, { "epoch": 0.011531762873667754, "grad_norm": 3.0402023792266846, "learning_rate": 7.68377253814147e-06, "loss": 1.132275390625, "step": 1940 }, { "epoch": 0.011591204950336146, "grad_norm": 3.066875457763672, "learning_rate": 7.723400039627501e-06, "loss": 1.1463637351989746, "step": 1950 }, { "epoch": 0.011650647027004536, "grad_norm": 2.5215790271759033, "learning_rate": 7.763027541113533e-06, "loss": 1.124018096923828, "step": 1960 }, { "epoch": 0.011710089103672926, "grad_norm": 2.6521077156066895, "learning_rate": 7.802655042599565e-06, "loss": 1.1345460891723633, "step": 1970 }, { "epoch": 0.011769531180341316, "grad_norm": 2.4002010822296143, "learning_rate": 7.842282544085595e-06, "loss": 1.1267440795898438, "step": 1980 }, { "epoch": 0.011828973257009706, "grad_norm": 2.5411932468414307, "learning_rate": 7.881910045571628e-06, "loss": 1.1534425735473632, "step": 1990 }, { "epoch": 0.011888415333678097, "grad_norm": 2.991877317428589, "learning_rate": 7.921537547057659e-06, "loss": 1.149061107635498, "step": 2000 }, { "epoch": 0.011947857410346489, "grad_norm": 2.579836368560791, "learning_rate": 7.961165048543689e-06, "loss": 1.1695026397705077, "step": 2010 }, { "epoch": 0.012007299487014879, "grad_norm": 3.3950610160827637, "learning_rate": 8.00079255002972e-06, "loss": 1.0977840423583984, "step": 2020 }, { "epoch": 0.012066741563683269, "grad_norm": 2.8179705142974854, "learning_rate": 8.040420051515753e-06, "loss": 1.06568603515625, "step": 2030 }, { "epoch": 0.01212618364035166, "grad_norm": 2.5454673767089844, "learning_rate": 8.080047553001783e-06, "loss": 1.124931526184082, "step": 2040 }, { "epoch": 0.01218562571702005, "grad_norm": 2.3182077407836914, "learning_rate": 8.119675054487815e-06, "loss": 1.0756017684936523, "step": 2050 }, { "epoch": 0.01224506779368844, "grad_norm": 2.1686971187591553, "learning_rate": 8.159302555973847e-06, "loss": 1.147867774963379, "step": 2060 }, { "epoch": 0.01230450987035683, "grad_norm": 2.4642159938812256, "learning_rate": 8.198930057459878e-06, "loss": 1.1706170082092284, "step": 2070 }, { "epoch": 0.012363951947025222, "grad_norm": 2.960771322250366, "learning_rate": 8.238557558945909e-06, "loss": 1.1041367530822754, "step": 2080 }, { "epoch": 0.012423394023693612, "grad_norm": 2.280226707458496, "learning_rate": 8.27818506043194e-06, "loss": 1.058744239807129, "step": 2090 }, { "epoch": 0.012482836100362002, "grad_norm": 2.9791882038116455, "learning_rate": 8.317812561917972e-06, "loss": 1.1829851150512696, "step": 2100 }, { "epoch": 0.012542278177030393, "grad_norm": 2.2622737884521484, "learning_rate": 8.357440063404003e-06, "loss": 1.1260725021362306, "step": 2110 }, { "epoch": 0.012601720253698783, "grad_norm": 2.7931017875671387, "learning_rate": 8.397067564890033e-06, "loss": 1.1981283187866212, "step": 2120 }, { "epoch": 0.012661162330367173, "grad_norm": 2.3789730072021484, "learning_rate": 8.436695066376066e-06, "loss": 1.1251598358154298, "step": 2130 }, { "epoch": 0.012720604407035565, "grad_norm": 2.388362407684326, "learning_rate": 8.476322567862096e-06, "loss": 1.0857366561889648, "step": 2140 }, { "epoch": 0.012780046483703955, "grad_norm": 2.5775094032287598, "learning_rate": 8.515950069348128e-06, "loss": 1.1451295852661132, "step": 2150 }, { "epoch": 0.012839488560372345, "grad_norm": 2.6352620124816895, "learning_rate": 8.55557757083416e-06, "loss": 1.1334507942199707, "step": 2160 }, { "epoch": 0.012898930637040736, "grad_norm": 3.3737733364105225, "learning_rate": 8.59520507232019e-06, "loss": 1.0817638397216798, "step": 2170 }, { "epoch": 0.012958372713709126, "grad_norm": 2.7400460243225098, "learning_rate": 8.634832573806222e-06, "loss": 1.1399642944335937, "step": 2180 }, { "epoch": 0.013017814790377516, "grad_norm": 2.46077561378479, "learning_rate": 8.674460075292254e-06, "loss": 1.1708087921142578, "step": 2190 }, { "epoch": 0.013077256867045908, "grad_norm": 2.1939289569854736, "learning_rate": 8.714087576778284e-06, "loss": 1.1019025802612306, "step": 2200 }, { "epoch": 0.013136698943714298, "grad_norm": 2.851583480834961, "learning_rate": 8.753715078264316e-06, "loss": 1.1099397659301757, "step": 2210 }, { "epoch": 0.013196141020382688, "grad_norm": 3.192246198654175, "learning_rate": 8.793342579750346e-06, "loss": 1.0613826751708983, "step": 2220 }, { "epoch": 0.013255583097051079, "grad_norm": 2.3167572021484375, "learning_rate": 8.832970081236378e-06, "loss": 1.1036313056945801, "step": 2230 }, { "epoch": 0.013315025173719469, "grad_norm": 2.658378839492798, "learning_rate": 8.87259758272241e-06, "loss": 1.1025026321411133, "step": 2240 }, { "epoch": 0.013374467250387859, "grad_norm": 2.9232583045959473, "learning_rate": 8.91222508420844e-06, "loss": 1.088669776916504, "step": 2250 }, { "epoch": 0.01343390932705625, "grad_norm": 2.633831739425659, "learning_rate": 8.951852585694472e-06, "loss": 1.0776128768920898, "step": 2260 }, { "epoch": 0.013493351403724641, "grad_norm": 2.5803635120391846, "learning_rate": 8.991480087180504e-06, "loss": 1.0655977249145507, "step": 2270 }, { "epoch": 0.013552793480393031, "grad_norm": 2.808781385421753, "learning_rate": 9.031107588666534e-06, "loss": 1.2104772567749023, "step": 2280 }, { "epoch": 0.013612235557061422, "grad_norm": 2.719482421875, "learning_rate": 9.070735090152568e-06, "loss": 1.156565284729004, "step": 2290 }, { "epoch": 0.013671677633729812, "grad_norm": 2.632603406906128, "learning_rate": 9.110362591638598e-06, "loss": 1.0710504531860352, "step": 2300 }, { "epoch": 0.013731119710398202, "grad_norm": 2.934152603149414, "learning_rate": 9.149990093124628e-06, "loss": 1.051969051361084, "step": 2310 }, { "epoch": 0.013790561787066592, "grad_norm": 3.0428597927093506, "learning_rate": 9.18961759461066e-06, "loss": 1.1583470344543456, "step": 2320 }, { "epoch": 0.013850003863734984, "grad_norm": 2.7461130619049072, "learning_rate": 9.229245096096692e-06, "loss": 1.1272522926330566, "step": 2330 }, { "epoch": 0.013909445940403374, "grad_norm": 2.600639820098877, "learning_rate": 9.268872597582722e-06, "loss": 1.0762279510498047, "step": 2340 }, { "epoch": 0.013968888017071765, "grad_norm": 2.6275057792663574, "learning_rate": 9.308500099068754e-06, "loss": 1.0853189468383788, "step": 2350 }, { "epoch": 0.014028330093740155, "grad_norm": 2.295419216156006, "learning_rate": 9.348127600554786e-06, "loss": 1.0955564498901367, "step": 2360 }, { "epoch": 0.014087772170408545, "grad_norm": 3.1521596908569336, "learning_rate": 9.387755102040816e-06, "loss": 1.0594755172729493, "step": 2370 }, { "epoch": 0.014147214247076935, "grad_norm": 2.8861918449401855, "learning_rate": 9.427382603526848e-06, "loss": 1.0485488891601562, "step": 2380 }, { "epoch": 0.014206656323745327, "grad_norm": 2.752868413925171, "learning_rate": 9.467010105012878e-06, "loss": 1.1358774185180665, "step": 2390 }, { "epoch": 0.014266098400413717, "grad_norm": 3.0123989582061768, "learning_rate": 9.506637606498912e-06, "loss": 1.1321675300598144, "step": 2400 }, { "epoch": 0.014325540477082108, "grad_norm": 2.3944449424743652, "learning_rate": 9.546265107984942e-06, "loss": 1.1701950073242187, "step": 2410 }, { "epoch": 0.014384982553750498, "grad_norm": 2.5606679916381836, "learning_rate": 9.585892609470972e-06, "loss": 1.1136165618896485, "step": 2420 }, { "epoch": 0.014444424630418888, "grad_norm": 2.832149028778076, "learning_rate": 9.625520110957006e-06, "loss": 1.1603885650634767, "step": 2430 }, { "epoch": 0.014503866707087278, "grad_norm": 3.4068431854248047, "learning_rate": 9.665147612443036e-06, "loss": 1.0799873352050782, "step": 2440 }, { "epoch": 0.014563308783755669, "grad_norm": 2.5312881469726562, "learning_rate": 9.704775113929066e-06, "loss": 1.091214942932129, "step": 2450 }, { "epoch": 0.01462275086042406, "grad_norm": 2.6654818058013916, "learning_rate": 9.7444026154151e-06, "loss": 1.0392655372619628, "step": 2460 }, { "epoch": 0.01468219293709245, "grad_norm": 2.991870403289795, "learning_rate": 9.78403011690113e-06, "loss": 1.0528094291687011, "step": 2470 }, { "epoch": 0.014741635013760841, "grad_norm": 3.388942003250122, "learning_rate": 9.823657618387162e-06, "loss": 1.0679155349731446, "step": 2480 }, { "epoch": 0.014801077090429231, "grad_norm": 3.384600877761841, "learning_rate": 9.863285119873192e-06, "loss": 1.1786652565002442, "step": 2490 }, { "epoch": 0.014860519167097621, "grad_norm": 2.150491714477539, "learning_rate": 9.902912621359224e-06, "loss": 1.1230929374694825, "step": 2500 }, { "epoch": 0.014919961243766012, "grad_norm": 2.9772236347198486, "learning_rate": 9.942540122845256e-06, "loss": 1.1129039764404296, "step": 2510 }, { "epoch": 0.014979403320434403, "grad_norm": 2.667565107345581, "learning_rate": 9.982167624331286e-06, "loss": 1.0921356201171875, "step": 2520 }, { "epoch": 0.015038845397102794, "grad_norm": 2.512458324432373, "learning_rate": 1.0021795125817318e-05, "loss": 1.044052791595459, "step": 2530 }, { "epoch": 0.015098287473771184, "grad_norm": 2.8898749351501465, "learning_rate": 1.006142262730335e-05, "loss": 1.0683382034301758, "step": 2540 }, { "epoch": 0.015157729550439574, "grad_norm": 3.1172938346862793, "learning_rate": 1.010105012878938e-05, "loss": 1.135575294494629, "step": 2550 }, { "epoch": 0.015217171627107964, "grad_norm": 2.9342074394226074, "learning_rate": 1.0140677630275412e-05, "loss": 1.134829616546631, "step": 2560 }, { "epoch": 0.015276613703776355, "grad_norm": 2.431706428527832, "learning_rate": 1.0180305131761443e-05, "loss": 1.048694133758545, "step": 2570 }, { "epoch": 0.015336055780444745, "grad_norm": 2.74483323097229, "learning_rate": 1.0219932633247474e-05, "loss": 1.1166807174682618, "step": 2580 }, { "epoch": 0.015395497857113137, "grad_norm": 3.2426891326904297, "learning_rate": 1.0259560134733506e-05, "loss": 1.0309626579284668, "step": 2590 }, { "epoch": 0.015454939933781527, "grad_norm": 2.8197848796844482, "learning_rate": 1.0299187636219537e-05, "loss": 1.0826733589172364, "step": 2600 }, { "epoch": 0.015514382010449917, "grad_norm": 2.7901976108551025, "learning_rate": 1.0338815137705568e-05, "loss": 1.081258773803711, "step": 2610 }, { "epoch": 0.015573824087118307, "grad_norm": 2.3711116313934326, "learning_rate": 1.03784426391916e-05, "loss": 1.0387006759643556, "step": 2620 }, { "epoch": 0.0156332661637867, "grad_norm": 3.1218721866607666, "learning_rate": 1.0418070140677631e-05, "loss": 1.059881591796875, "step": 2630 }, { "epoch": 0.01569270824045509, "grad_norm": 3.0373523235321045, "learning_rate": 1.0457697642163662e-05, "loss": 1.088663673400879, "step": 2640 }, { "epoch": 0.01575215031712348, "grad_norm": 3.2448976039886475, "learning_rate": 1.0497325143649693e-05, "loss": 1.1217853546142578, "step": 2650 }, { "epoch": 0.01581159239379187, "grad_norm": 2.4848532676696777, "learning_rate": 1.0536952645135725e-05, "loss": 1.0774925231933594, "step": 2660 }, { "epoch": 0.01587103447046026, "grad_norm": 2.818042039871216, "learning_rate": 1.0576580146621755e-05, "loss": 1.0564698219299316, "step": 2670 }, { "epoch": 0.01593047654712865, "grad_norm": 2.587076187133789, "learning_rate": 1.0616207648107787e-05, "loss": 1.1240666389465332, "step": 2680 }, { "epoch": 0.01598991862379704, "grad_norm": 2.831686496734619, "learning_rate": 1.0655835149593818e-05, "loss": 1.0129985809326172, "step": 2690 }, { "epoch": 0.01604936070046543, "grad_norm": 3.0822455883026123, "learning_rate": 1.0695462651079851e-05, "loss": 1.086693000793457, "step": 2700 }, { "epoch": 0.01610880277713382, "grad_norm": 2.5993242263793945, "learning_rate": 1.0735090152565881e-05, "loss": 1.0239160537719727, "step": 2710 }, { "epoch": 0.01616824485380221, "grad_norm": 2.8075599670410156, "learning_rate": 1.0774717654051912e-05, "loss": 1.162445068359375, "step": 2720 }, { "epoch": 0.0162276869304706, "grad_norm": 2.6301000118255615, "learning_rate": 1.0814345155537945e-05, "loss": 1.0503362655639648, "step": 2730 }, { "epoch": 0.016287129007138995, "grad_norm": 2.820186138153076, "learning_rate": 1.0853972657023975e-05, "loss": 1.0419328689575196, "step": 2740 }, { "epoch": 0.016346571083807385, "grad_norm": 2.826709270477295, "learning_rate": 1.0893600158510005e-05, "loss": 1.0633440971374513, "step": 2750 }, { "epoch": 0.016406013160475776, "grad_norm": 3.1880807876586914, "learning_rate": 1.0933227659996039e-05, "loss": 1.0543249130249024, "step": 2760 }, { "epoch": 0.016465455237144166, "grad_norm": 2.860334634780884, "learning_rate": 1.097285516148207e-05, "loss": 1.088575553894043, "step": 2770 }, { "epoch": 0.016524897313812556, "grad_norm": 2.8909249305725098, "learning_rate": 1.10124826629681e-05, "loss": 1.0479619026184082, "step": 2780 }, { "epoch": 0.016584339390480946, "grad_norm": 2.617856979370117, "learning_rate": 1.1052110164454131e-05, "loss": 1.06396541595459, "step": 2790 }, { "epoch": 0.016643781467149336, "grad_norm": 3.0122458934783936, "learning_rate": 1.1091737665940163e-05, "loss": 1.1310035705566406, "step": 2800 }, { "epoch": 0.016703223543817727, "grad_norm": 2.8299777507781982, "learning_rate": 1.1131365167426195e-05, "loss": 1.0238353729248046, "step": 2810 }, { "epoch": 0.016762665620486117, "grad_norm": 2.921931028366089, "learning_rate": 1.1170992668912225e-05, "loss": 0.9949205398559571, "step": 2820 }, { "epoch": 0.016822107697154507, "grad_norm": 2.9195125102996826, "learning_rate": 1.1210620170398257e-05, "loss": 1.1345674514770507, "step": 2830 }, { "epoch": 0.016881549773822897, "grad_norm": 3.1423416137695312, "learning_rate": 1.1250247671884289e-05, "loss": 1.0793044090270996, "step": 2840 }, { "epoch": 0.016940991850491288, "grad_norm": 2.9288511276245117, "learning_rate": 1.1289875173370319e-05, "loss": 1.0424314498901368, "step": 2850 }, { "epoch": 0.017000433927159678, "grad_norm": 2.9130568504333496, "learning_rate": 1.1329502674856351e-05, "loss": 1.0707736968994142, "step": 2860 }, { "epoch": 0.01705987600382807, "grad_norm": 2.897390365600586, "learning_rate": 1.1369130176342383e-05, "loss": 1.102492618560791, "step": 2870 }, { "epoch": 0.01711931808049646, "grad_norm": 2.684596538543701, "learning_rate": 1.1408757677828413e-05, "loss": 0.9902538299560547, "step": 2880 }, { "epoch": 0.017178760157164852, "grad_norm": 2.6585843563079834, "learning_rate": 1.1448385179314445e-05, "loss": 1.038355827331543, "step": 2890 }, { "epoch": 0.017238202233833242, "grad_norm": 3.144430160522461, "learning_rate": 1.1488012680800477e-05, "loss": 1.0218464851379394, "step": 2900 }, { "epoch": 0.017297644310501632, "grad_norm": 3.3306596279144287, "learning_rate": 1.1527640182286507e-05, "loss": 1.0409871101379395, "step": 2910 }, { "epoch": 0.017357086387170022, "grad_norm": 2.789966106414795, "learning_rate": 1.1567267683772539e-05, "loss": 1.0463931083679199, "step": 2920 }, { "epoch": 0.017416528463838413, "grad_norm": 2.862757682800293, "learning_rate": 1.160689518525857e-05, "loss": 1.0191295623779297, "step": 2930 }, { "epoch": 0.017475970540506803, "grad_norm": 2.3394508361816406, "learning_rate": 1.1646522686744601e-05, "loss": 1.0761890411376953, "step": 2940 }, { "epoch": 0.017535412617175193, "grad_norm": 3.010528564453125, "learning_rate": 1.1686150188230633e-05, "loss": 1.0440214157104493, "step": 2950 }, { "epoch": 0.017594854693843583, "grad_norm": 2.661450147628784, "learning_rate": 1.1725777689716663e-05, "loss": 1.015333080291748, "step": 2960 }, { "epoch": 0.017654296770511974, "grad_norm": 2.783783435821533, "learning_rate": 1.1765405191202695e-05, "loss": 1.0565531730651856, "step": 2970 }, { "epoch": 0.017713738847180364, "grad_norm": 2.7765543460845947, "learning_rate": 1.1805032692688727e-05, "loss": 1.094081974029541, "step": 2980 }, { "epoch": 0.017773180923848754, "grad_norm": 3.29577898979187, "learning_rate": 1.1844660194174757e-05, "loss": 1.0977417945861816, "step": 2990 }, { "epoch": 0.017832623000517148, "grad_norm": 2.191226005554199, "learning_rate": 1.1884287695660789e-05, "loss": 1.031494140625, "step": 3000 }, { "epoch": 0.017892065077185538, "grad_norm": 2.8093929290771484, "learning_rate": 1.192391519714682e-05, "loss": 1.0205134391784667, "step": 3010 }, { "epoch": 0.017951507153853928, "grad_norm": 2.6199564933776855, "learning_rate": 1.1963542698632851e-05, "loss": 1.0220168113708497, "step": 3020 }, { "epoch": 0.01801094923052232, "grad_norm": 2.665914535522461, "learning_rate": 1.2003170200118884e-05, "loss": 1.0711756706237794, "step": 3030 }, { "epoch": 0.01807039130719071, "grad_norm": 2.9336512088775635, "learning_rate": 1.2042797701604915e-05, "loss": 1.074765968322754, "step": 3040 }, { "epoch": 0.0181298333838591, "grad_norm": 3.1254653930664062, "learning_rate": 1.2082425203090945e-05, "loss": 1.0426667213439942, "step": 3050 }, { "epoch": 0.01818927546052749, "grad_norm": 2.9918882846832275, "learning_rate": 1.2122052704576977e-05, "loss": 1.013319206237793, "step": 3060 }, { "epoch": 0.01824871753719588, "grad_norm": 2.635427236557007, "learning_rate": 1.2161680206063009e-05, "loss": 1.0910725593566895, "step": 3070 }, { "epoch": 0.01830815961386427, "grad_norm": 2.8819031715393066, "learning_rate": 1.2201307707549039e-05, "loss": 1.0928114891052245, "step": 3080 }, { "epoch": 0.01836760169053266, "grad_norm": 3.438498020172119, "learning_rate": 1.224093520903507e-05, "loss": 1.034033203125, "step": 3090 }, { "epoch": 0.01842704376720105, "grad_norm": 2.639962911605835, "learning_rate": 1.2280562710521103e-05, "loss": 0.9935920715332032, "step": 3100 }, { "epoch": 0.01848648584386944, "grad_norm": 3.528904676437378, "learning_rate": 1.2320190212007134e-05, "loss": 1.0006217002868651, "step": 3110 }, { "epoch": 0.01854592792053783, "grad_norm": 2.572547197341919, "learning_rate": 1.2359817713493165e-05, "loss": 1.0364171981811523, "step": 3120 }, { "epoch": 0.018605369997206224, "grad_norm": 2.65523624420166, "learning_rate": 1.2399445214979196e-05, "loss": 1.0518617630004883, "step": 3130 }, { "epoch": 0.018664812073874614, "grad_norm": 3.030632734298706, "learning_rate": 1.2439072716465228e-05, "loss": 1.0706637382507325, "step": 3140 }, { "epoch": 0.018724254150543004, "grad_norm": 2.9260523319244385, "learning_rate": 1.2478700217951259e-05, "loss": 0.9555800437927247, "step": 3150 }, { "epoch": 0.018783696227211395, "grad_norm": 3.258599042892456, "learning_rate": 1.2518327719437289e-05, "loss": 1.0134279251098632, "step": 3160 }, { "epoch": 0.018843138303879785, "grad_norm": 2.933544874191284, "learning_rate": 1.255795522092332e-05, "loss": 1.0294720649719238, "step": 3170 }, { "epoch": 0.018902580380548175, "grad_norm": 3.069129228591919, "learning_rate": 1.2597582722409354e-05, "loss": 1.0758390426635742, "step": 3180 }, { "epoch": 0.018962022457216565, "grad_norm": 2.6624274253845215, "learning_rate": 1.2637210223895384e-05, "loss": 1.034881591796875, "step": 3190 }, { "epoch": 0.019021464533884955, "grad_norm": 2.5980215072631836, "learning_rate": 1.2676837725381416e-05, "loss": 0.9902961730957032, "step": 3200 }, { "epoch": 0.019080906610553346, "grad_norm": 2.8727619647979736, "learning_rate": 1.2716465226867446e-05, "loss": 0.9885358810424805, "step": 3210 }, { "epoch": 0.019140348687221736, "grad_norm": 2.831845760345459, "learning_rate": 1.2756092728353478e-05, "loss": 1.0133216857910157, "step": 3220 }, { "epoch": 0.019199790763890126, "grad_norm": 2.6663355827331543, "learning_rate": 1.2795720229839508e-05, "loss": 1.035550308227539, "step": 3230 }, { "epoch": 0.019259232840558516, "grad_norm": 3.2075414657592773, "learning_rate": 1.2835347731325539e-05, "loss": 1.0822105407714844, "step": 3240 }, { "epoch": 0.01931867491722691, "grad_norm": 2.6095070838928223, "learning_rate": 1.2874975232811572e-05, "loss": 1.0789838790893556, "step": 3250 }, { "epoch": 0.0193781169938953, "grad_norm": 2.6239309310913086, "learning_rate": 1.2914602734297604e-05, "loss": 1.0686413764953613, "step": 3260 }, { "epoch": 0.01943755907056369, "grad_norm": 2.7684412002563477, "learning_rate": 1.2954230235783634e-05, "loss": 1.0304858207702636, "step": 3270 }, { "epoch": 0.01949700114723208, "grad_norm": 2.606886148452759, "learning_rate": 1.2993857737269666e-05, "loss": 1.1174272537231444, "step": 3280 }, { "epoch": 0.01955644322390047, "grad_norm": 3.352457284927368, "learning_rate": 1.3033485238755696e-05, "loss": 1.0574405670166016, "step": 3290 }, { "epoch": 0.01961588530056886, "grad_norm": 3.0328853130340576, "learning_rate": 1.3073112740241728e-05, "loss": 1.0674656867980956, "step": 3300 }, { "epoch": 0.01967532737723725, "grad_norm": 2.903394937515259, "learning_rate": 1.3112740241727758e-05, "loss": 0.9977883338928223, "step": 3310 }, { "epoch": 0.01973476945390564, "grad_norm": 3.06278133392334, "learning_rate": 1.3152367743213792e-05, "loss": 1.0349114418029786, "step": 3320 }, { "epoch": 0.01979421153057403, "grad_norm": 3.493330240249634, "learning_rate": 1.3191995244699822e-05, "loss": 1.0038965225219727, "step": 3330 }, { "epoch": 0.019853653607242422, "grad_norm": 2.7876861095428467, "learning_rate": 1.3231622746185854e-05, "loss": 0.9920130729675293, "step": 3340 }, { "epoch": 0.019913095683910812, "grad_norm": 3.055598258972168, "learning_rate": 1.3271250247671884e-05, "loss": 0.9875605583190918, "step": 3350 }, { "epoch": 0.019972537760579202, "grad_norm": 3.1773738861083984, "learning_rate": 1.3310877749157916e-05, "loss": 1.0315120697021485, "step": 3360 }, { "epoch": 0.020031979837247593, "grad_norm": 3.0752172470092773, "learning_rate": 1.3350505250643946e-05, "loss": 1.0554183959960937, "step": 3370 }, { "epoch": 0.020091421913915986, "grad_norm": 2.849682569503784, "learning_rate": 1.339013275212998e-05, "loss": 1.056320571899414, "step": 3380 }, { "epoch": 0.020150863990584376, "grad_norm": 2.7090160846710205, "learning_rate": 1.3429760253616012e-05, "loss": 0.9959712028503418, "step": 3390 }, { "epoch": 0.020210306067252767, "grad_norm": 2.9832651615142822, "learning_rate": 1.3469387755102042e-05, "loss": 1.0103390693664551, "step": 3400 }, { "epoch": 0.020269748143921157, "grad_norm": 2.7732722759246826, "learning_rate": 1.3509015256588072e-05, "loss": 0.9754732131958008, "step": 3410 }, { "epoch": 0.020329190220589547, "grad_norm": 2.6673777103424072, "learning_rate": 1.3548642758074104e-05, "loss": 1.0084495544433594, "step": 3420 }, { "epoch": 0.020388632297257937, "grad_norm": 3.2580690383911133, "learning_rate": 1.3588270259560134e-05, "loss": 1.0273767471313477, "step": 3430 }, { "epoch": 0.020448074373926328, "grad_norm": 3.729673147201538, "learning_rate": 1.3627897761046166e-05, "loss": 1.047391414642334, "step": 3440 }, { "epoch": 0.020507516450594718, "grad_norm": 3.2036871910095215, "learning_rate": 1.36675252625322e-05, "loss": 1.0756839752197265, "step": 3450 }, { "epoch": 0.020566958527263108, "grad_norm": 3.142963409423828, "learning_rate": 1.370715276401823e-05, "loss": 1.0173199653625489, "step": 3460 }, { "epoch": 0.020626400603931498, "grad_norm": 2.67449951171875, "learning_rate": 1.3746780265504262e-05, "loss": 1.076723003387451, "step": 3470 }, { "epoch": 0.02068584268059989, "grad_norm": 3.07979416847229, "learning_rate": 1.3786407766990292e-05, "loss": 1.0171944618225097, "step": 3480 }, { "epoch": 0.02074528475726828, "grad_norm": 2.928541660308838, "learning_rate": 1.3826035268476322e-05, "loss": 0.9547465324401856, "step": 3490 }, { "epoch": 0.02080472683393667, "grad_norm": 2.979016065597534, "learning_rate": 1.3865662769962354e-05, "loss": 1.0421573638916015, "step": 3500 }, { "epoch": 0.020864168910605062, "grad_norm": 3.694147825241089, "learning_rate": 1.3905290271448384e-05, "loss": 1.0298528671264648, "step": 3510 }, { "epoch": 0.020923610987273453, "grad_norm": 3.8566653728485107, "learning_rate": 1.3944917772934418e-05, "loss": 0.9985663414001464, "step": 3520 }, { "epoch": 0.020983053063941843, "grad_norm": 2.375837802886963, "learning_rate": 1.398454527442045e-05, "loss": 1.0110177993774414, "step": 3530 }, { "epoch": 0.021042495140610233, "grad_norm": 3.3624866008758545, "learning_rate": 1.402417277590648e-05, "loss": 0.9713631629943847, "step": 3540 }, { "epoch": 0.021101937217278623, "grad_norm": 3.153515577316284, "learning_rate": 1.4063800277392512e-05, "loss": 0.9880214691162109, "step": 3550 }, { "epoch": 0.021161379293947014, "grad_norm": 2.708179235458374, "learning_rate": 1.4103427778878542e-05, "loss": 1.0347131729125976, "step": 3560 }, { "epoch": 0.021220821370615404, "grad_norm": 2.7287814617156982, "learning_rate": 1.4143055280364572e-05, "loss": 1.0696893692016602, "step": 3570 }, { "epoch": 0.021280263447283794, "grad_norm": 3.112689971923828, "learning_rate": 1.4182682781850604e-05, "loss": 1.0633815765380858, "step": 3580 }, { "epoch": 0.021339705523952184, "grad_norm": 2.480747938156128, "learning_rate": 1.4222310283336637e-05, "loss": 0.9989197731018067, "step": 3590 }, { "epoch": 0.021399147600620574, "grad_norm": 2.9658761024475098, "learning_rate": 1.4261937784822668e-05, "loss": 1.0420213699340821, "step": 3600 }, { "epoch": 0.021458589677288965, "grad_norm": 2.473940849304199, "learning_rate": 1.43015652863087e-05, "loss": 0.9896361351013183, "step": 3610 }, { "epoch": 0.021518031753957355, "grad_norm": 2.8237192630767822, "learning_rate": 1.434119278779473e-05, "loss": 1.0564609527587892, "step": 3620 }, { "epoch": 0.021577473830625745, "grad_norm": 2.952888011932373, "learning_rate": 1.4380820289280762e-05, "loss": 0.995815658569336, "step": 3630 }, { "epoch": 0.02163691590729414, "grad_norm": 2.9373977184295654, "learning_rate": 1.4420447790766792e-05, "loss": 0.9834968566894531, "step": 3640 }, { "epoch": 0.02169635798396253, "grad_norm": 3.2665836811065674, "learning_rate": 1.4460075292252825e-05, "loss": 1.0236804962158204, "step": 3650 }, { "epoch": 0.02175580006063092, "grad_norm": 3.4184329509735107, "learning_rate": 1.4499702793738856e-05, "loss": 0.9725728988647461, "step": 3660 }, { "epoch": 0.02181524213729931, "grad_norm": 3.178544759750366, "learning_rate": 1.4539330295224887e-05, "loss": 1.0354841232299805, "step": 3670 }, { "epoch": 0.0218746842139677, "grad_norm": 2.980584144592285, "learning_rate": 1.4578957796710918e-05, "loss": 1.070418930053711, "step": 3680 }, { "epoch": 0.02193412629063609, "grad_norm": 2.4186477661132812, "learning_rate": 1.461858529819695e-05, "loss": 0.9777576446533203, "step": 3690 }, { "epoch": 0.02199356836730448, "grad_norm": 2.7892796993255615, "learning_rate": 1.465821279968298e-05, "loss": 0.9503032684326171, "step": 3700 }, { "epoch": 0.02205301044397287, "grad_norm": 3.6202142238616943, "learning_rate": 1.4697840301169012e-05, "loss": 1.0649415969848632, "step": 3710 }, { "epoch": 0.02211245252064126, "grad_norm": 3.0156421661376953, "learning_rate": 1.4737467802655045e-05, "loss": 1.0514812469482422, "step": 3720 }, { "epoch": 0.02217189459730965, "grad_norm": 2.788867473602295, "learning_rate": 1.4777095304141075e-05, "loss": 0.9974440574645996, "step": 3730 }, { "epoch": 0.02223133667397804, "grad_norm": 2.8395438194274902, "learning_rate": 1.4816722805627105e-05, "loss": 0.9822397232055664, "step": 3740 }, { "epoch": 0.02229077875064643, "grad_norm": 2.6084091663360596, "learning_rate": 1.4856350307113137e-05, "loss": 1.0125028610229492, "step": 3750 }, { "epoch": 0.022350220827314825, "grad_norm": 2.7655751705169678, "learning_rate": 1.4895977808599168e-05, "loss": 0.9981590270996094, "step": 3760 }, { "epoch": 0.022409662903983215, "grad_norm": 3.3422935009002686, "learning_rate": 1.49356053100852e-05, "loss": 0.9670103073120118, "step": 3770 }, { "epoch": 0.022469104980651605, "grad_norm": 3.2193171977996826, "learning_rate": 1.497523281157123e-05, "loss": 1.1062384605407716, "step": 3780 }, { "epoch": 0.022528547057319995, "grad_norm": 2.9199061393737793, "learning_rate": 1.5014860313057263e-05, "loss": 0.9687848091125488, "step": 3790 }, { "epoch": 0.022587989133988386, "grad_norm": 3.0747132301330566, "learning_rate": 1.5054487814543295e-05, "loss": 1.0079854011535645, "step": 3800 }, { "epoch": 0.022647431210656776, "grad_norm": 3.4126102924346924, "learning_rate": 1.5094115316029325e-05, "loss": 0.9956210136413575, "step": 3810 }, { "epoch": 0.022706873287325166, "grad_norm": 2.9258992671966553, "learning_rate": 1.5133742817515355e-05, "loss": 0.9552427291870117, "step": 3820 }, { "epoch": 0.022766315363993556, "grad_norm": 3.5490665435791016, "learning_rate": 1.5173370319001387e-05, "loss": 0.9924581527709961, "step": 3830 }, { "epoch": 0.022825757440661947, "grad_norm": 2.676469564437866, "learning_rate": 1.5212997820487417e-05, "loss": 1.0160232543945313, "step": 3840 }, { "epoch": 0.022885199517330337, "grad_norm": 3.593956708908081, "learning_rate": 1.5252625321973451e-05, "loss": 1.0537419319152832, "step": 3850 }, { "epoch": 0.022944641593998727, "grad_norm": 2.986189126968384, "learning_rate": 1.5292252823459483e-05, "loss": 0.9864952087402343, "step": 3860 }, { "epoch": 0.023004083670667117, "grad_norm": 3.5045180320739746, "learning_rate": 1.5331880324945515e-05, "loss": 1.0192244529724122, "step": 3870 }, { "epoch": 0.023063525747335507, "grad_norm": 3.543687582015991, "learning_rate": 1.5371507826431543e-05, "loss": 1.0211500167846679, "step": 3880 }, { "epoch": 0.0231229678240039, "grad_norm": 3.163264513015747, "learning_rate": 1.5411135327917575e-05, "loss": 0.9646158218383789, "step": 3890 }, { "epoch": 0.02318240990067229, "grad_norm": 3.098557472229004, "learning_rate": 1.5450762829403607e-05, "loss": 1.0479816436767577, "step": 3900 }, { "epoch": 0.02324185197734068, "grad_norm": 3.2522051334381104, "learning_rate": 1.5490390330889636e-05, "loss": 0.9982215881347656, "step": 3910 }, { "epoch": 0.02330129405400907, "grad_norm": 3.5375471115112305, "learning_rate": 1.553001783237567e-05, "loss": 0.9546760559082031, "step": 3920 }, { "epoch": 0.023360736130677462, "grad_norm": 2.8604133129119873, "learning_rate": 1.5569645333861703e-05, "loss": 1.067555046081543, "step": 3930 }, { "epoch": 0.023420178207345852, "grad_norm": 3.4755165576934814, "learning_rate": 1.560927283534773e-05, "loss": 1.0203363418579101, "step": 3940 }, { "epoch": 0.023479620284014242, "grad_norm": 2.987330913543701, "learning_rate": 1.5648900336833763e-05, "loss": 1.024933433532715, "step": 3950 }, { "epoch": 0.023539062360682633, "grad_norm": 3.1441144943237305, "learning_rate": 1.5688527838319795e-05, "loss": 0.985911750793457, "step": 3960 }, { "epoch": 0.023598504437351023, "grad_norm": 2.8672640323638916, "learning_rate": 1.5728155339805823e-05, "loss": 0.9977823257446289, "step": 3970 }, { "epoch": 0.023657946514019413, "grad_norm": 2.5891473293304443, "learning_rate": 1.5767782841291855e-05, "loss": 0.9766096115112305, "step": 3980 }, { "epoch": 0.023717388590687803, "grad_norm": 2.695896863937378, "learning_rate": 1.580741034277789e-05, "loss": 1.0187286376953124, "step": 3990 }, { "epoch": 0.023776830667356193, "grad_norm": 3.1503820419311523, "learning_rate": 1.584703784426392e-05, "loss": 0.9702949523925781, "step": 4000 }, { "epoch": 0.023836272744024584, "grad_norm": 3.3108904361724854, "learning_rate": 1.588666534574995e-05, "loss": 0.9580820083618165, "step": 4010 }, { "epoch": 0.023895714820692977, "grad_norm": 3.16352915763855, "learning_rate": 1.5926292847235983e-05, "loss": 0.9815861701965332, "step": 4020 }, { "epoch": 0.023955156897361368, "grad_norm": 2.646819829940796, "learning_rate": 1.5965920348722015e-05, "loss": 1.0097745895385741, "step": 4030 }, { "epoch": 0.024014598974029758, "grad_norm": 2.8126111030578613, "learning_rate": 1.6005547850208043e-05, "loss": 0.9113503456115722, "step": 4040 }, { "epoch": 0.024074041050698148, "grad_norm": 3.3496081829071045, "learning_rate": 1.604517535169408e-05, "loss": 1.0042816162109376, "step": 4050 }, { "epoch": 0.024133483127366538, "grad_norm": 3.41977596282959, "learning_rate": 1.608480285318011e-05, "loss": 1.0281959533691407, "step": 4060 }, { "epoch": 0.02419292520403493, "grad_norm": 2.961754560470581, "learning_rate": 1.612443035466614e-05, "loss": 0.9321132659912109, "step": 4070 }, { "epoch": 0.02425236728070332, "grad_norm": 3.053215980529785, "learning_rate": 1.616405785615217e-05, "loss": 0.9960269927978516, "step": 4080 }, { "epoch": 0.02431180935737171, "grad_norm": 3.3953804969787598, "learning_rate": 1.6203685357638203e-05, "loss": 1.017312717437744, "step": 4090 }, { "epoch": 0.0243712514340401, "grad_norm": 2.6540064811706543, "learning_rate": 1.624331285912423e-05, "loss": 0.9300251960754394, "step": 4100 }, { "epoch": 0.02443069351070849, "grad_norm": 3.0675153732299805, "learning_rate": 1.6282940360610263e-05, "loss": 0.9426742553710937, "step": 4110 }, { "epoch": 0.02449013558737688, "grad_norm": 2.5861706733703613, "learning_rate": 1.6322567862096298e-05, "loss": 0.9381536483764649, "step": 4120 }, { "epoch": 0.02454957766404527, "grad_norm": 2.3893625736236572, "learning_rate": 1.6362195363582327e-05, "loss": 0.8814033508300781, "step": 4130 }, { "epoch": 0.02460901974071366, "grad_norm": 3.0587339401245117, "learning_rate": 1.640182286506836e-05, "loss": 0.9735208511352539, "step": 4140 }, { "epoch": 0.024668461817382054, "grad_norm": 2.815401315689087, "learning_rate": 1.644145036655439e-05, "loss": 1.0049110412597657, "step": 4150 }, { "epoch": 0.024727903894050444, "grad_norm": 2.9926037788391113, "learning_rate": 1.648107786804042e-05, "loss": 0.9496475219726562, "step": 4160 }, { "epoch": 0.024787345970718834, "grad_norm": 3.093923568725586, "learning_rate": 1.652070536952645e-05, "loss": 1.014931869506836, "step": 4170 }, { "epoch": 0.024846788047387224, "grad_norm": 2.237654447555542, "learning_rate": 1.6560332871012483e-05, "loss": 0.9465804100036621, "step": 4180 }, { "epoch": 0.024906230124055614, "grad_norm": 2.9581568241119385, "learning_rate": 1.6599960372498515e-05, "loss": 0.9947265625, "step": 4190 }, { "epoch": 0.024965672200724005, "grad_norm": 2.8938591480255127, "learning_rate": 1.6639587873984546e-05, "loss": 0.98709135055542, "step": 4200 }, { "epoch": 0.025025114277392395, "grad_norm": 2.324577569961548, "learning_rate": 1.667921537547058e-05, "loss": 0.9626176834106446, "step": 4210 }, { "epoch": 0.025084556354060785, "grad_norm": 3.048462152481079, "learning_rate": 1.671884287695661e-05, "loss": 0.9668209075927734, "step": 4220 }, { "epoch": 0.025143998430729175, "grad_norm": 3.2034928798675537, "learning_rate": 1.675847037844264e-05, "loss": 0.8959949493408204, "step": 4230 }, { "epoch": 0.025203440507397566, "grad_norm": 2.1758127212524414, "learning_rate": 1.679809787992867e-05, "loss": 0.9850991249084473, "step": 4240 }, { "epoch": 0.025262882584065956, "grad_norm": 3.398202419281006, "learning_rate": 1.6837725381414702e-05, "loss": 0.9628340721130371, "step": 4250 }, { "epoch": 0.025322324660734346, "grad_norm": 3.0033249855041504, "learning_rate": 1.6877352882900734e-05, "loss": 0.968243408203125, "step": 4260 }, { "epoch": 0.02538176673740274, "grad_norm": 3.1433496475219727, "learning_rate": 1.6916980384386766e-05, "loss": 1.0090147018432618, "step": 4270 }, { "epoch": 0.02544120881407113, "grad_norm": 3.0092835426330566, "learning_rate": 1.6956607885872798e-05, "loss": 1.045884132385254, "step": 4280 }, { "epoch": 0.02550065089073952, "grad_norm": 3.218778133392334, "learning_rate": 1.6996235387358827e-05, "loss": 1.0113259315490724, "step": 4290 }, { "epoch": 0.02556009296740791, "grad_norm": 3.321870803833008, "learning_rate": 1.703586288884486e-05, "loss": 0.9728466987609863, "step": 4300 }, { "epoch": 0.0256195350440763, "grad_norm": 2.9158315658569336, "learning_rate": 1.707549039033089e-05, "loss": 1.0196418762207031, "step": 4310 }, { "epoch": 0.02567897712074469, "grad_norm": 2.9127321243286133, "learning_rate": 1.7115117891816922e-05, "loss": 0.9837656021118164, "step": 4320 }, { "epoch": 0.02573841919741308, "grad_norm": 2.9974284172058105, "learning_rate": 1.7154745393302954e-05, "loss": 0.9986040115356445, "step": 4330 }, { "epoch": 0.02579786127408147, "grad_norm": 2.8259761333465576, "learning_rate": 1.7194372894788986e-05, "loss": 0.8754289627075196, "step": 4340 }, { "epoch": 0.02585730335074986, "grad_norm": 3.7209248542785645, "learning_rate": 1.7234000396275014e-05, "loss": 1.017233657836914, "step": 4350 }, { "epoch": 0.02591674542741825, "grad_norm": 2.954108476638794, "learning_rate": 1.7273627897761046e-05, "loss": 0.9727465629577636, "step": 4360 }, { "epoch": 0.025976187504086642, "grad_norm": 2.484142541885376, "learning_rate": 1.7313255399247078e-05, "loss": 0.9607023239135742, "step": 4370 }, { "epoch": 0.026035629580755032, "grad_norm": 3.215695381164551, "learning_rate": 1.7352882900733107e-05, "loss": 0.9469696044921875, "step": 4380 }, { "epoch": 0.026095071657423422, "grad_norm": 3.376332998275757, "learning_rate": 1.7392510402219142e-05, "loss": 1.0369213104248047, "step": 4390 }, { "epoch": 0.026154513734091816, "grad_norm": 3.1263675689697266, "learning_rate": 1.7432137903705174e-05, "loss": 0.965329933166504, "step": 4400 }, { "epoch": 0.026213955810760206, "grad_norm": 3.7477333545684814, "learning_rate": 1.7471765405191202e-05, "loss": 1.0227818489074707, "step": 4410 }, { "epoch": 0.026273397887428596, "grad_norm": 2.6073102951049805, "learning_rate": 1.7511392906677234e-05, "loss": 0.8817893028259277, "step": 4420 }, { "epoch": 0.026332839964096987, "grad_norm": 2.864250421524048, "learning_rate": 1.7551020408163266e-05, "loss": 1.0137647628784179, "step": 4430 }, { "epoch": 0.026392282040765377, "grad_norm": 3.0239384174346924, "learning_rate": 1.7590647909649298e-05, "loss": 0.8916999816894531, "step": 4440 }, { "epoch": 0.026451724117433767, "grad_norm": 2.4304795265197754, "learning_rate": 1.7630275411135326e-05, "loss": 0.9640094757080078, "step": 4450 }, { "epoch": 0.026511166194102157, "grad_norm": 3.2925195693969727, "learning_rate": 1.7669902912621362e-05, "loss": 0.9332464218139649, "step": 4460 }, { "epoch": 0.026570608270770547, "grad_norm": 2.6196389198303223, "learning_rate": 1.7709530414107394e-05, "loss": 0.9536845207214355, "step": 4470 }, { "epoch": 0.026630050347438938, "grad_norm": 2.813647747039795, "learning_rate": 1.7749157915593422e-05, "loss": 0.9596769332885742, "step": 4480 }, { "epoch": 0.026689492424107328, "grad_norm": 3.865609645843506, "learning_rate": 1.7788785417079454e-05, "loss": 0.9358712196350097, "step": 4490 }, { "epoch": 0.026748934500775718, "grad_norm": 3.2069263458251953, "learning_rate": 1.7828412918565486e-05, "loss": 0.9448985099792481, "step": 4500 }, { "epoch": 0.026808376577444108, "grad_norm": 3.0074710845947266, "learning_rate": 1.7868040420051514e-05, "loss": 0.9800752639770508, "step": 4510 }, { "epoch": 0.0268678186541125, "grad_norm": 2.7051846981048584, "learning_rate": 1.790766792153755e-05, "loss": 0.9401438713073731, "step": 4520 }, { "epoch": 0.026927260730780892, "grad_norm": 2.9535210132598877, "learning_rate": 1.794729542302358e-05, "loss": 0.9638334274291992, "step": 4530 }, { "epoch": 0.026986702807449282, "grad_norm": 2.4937055110931396, "learning_rate": 1.798692292450961e-05, "loss": 0.9423070907592773, "step": 4540 }, { "epoch": 0.027046144884117673, "grad_norm": 3.0662717819213867, "learning_rate": 1.8026550425995642e-05, "loss": 0.9308942794799805, "step": 4550 }, { "epoch": 0.027105586960786063, "grad_norm": 3.5955090522766113, "learning_rate": 1.8066177927481674e-05, "loss": 0.9526849746704101, "step": 4560 }, { "epoch": 0.027165029037454453, "grad_norm": 2.9596900939941406, "learning_rate": 1.8105805428967702e-05, "loss": 1.0556884765625, "step": 4570 }, { "epoch": 0.027224471114122843, "grad_norm": 2.8181517124176025, "learning_rate": 1.8145432930453734e-05, "loss": 0.9534155845642089, "step": 4580 }, { "epoch": 0.027283913190791233, "grad_norm": 2.673431873321533, "learning_rate": 1.818506043193977e-05, "loss": 0.9906101226806641, "step": 4590 }, { "epoch": 0.027343355267459624, "grad_norm": 3.084174633026123, "learning_rate": 1.8224687933425798e-05, "loss": 0.9598299026489258, "step": 4600 }, { "epoch": 0.027402797344128014, "grad_norm": 3.2601687908172607, "learning_rate": 1.826431543491183e-05, "loss": 1.0764469146728515, "step": 4610 }, { "epoch": 0.027462239420796404, "grad_norm": 2.751856565475464, "learning_rate": 1.830394293639786e-05, "loss": 0.9780899047851562, "step": 4620 }, { "epoch": 0.027521681497464794, "grad_norm": 3.725220203399658, "learning_rate": 1.8343570437883894e-05, "loss": 0.9169855117797852, "step": 4630 }, { "epoch": 0.027581123574133184, "grad_norm": 3.3693742752075195, "learning_rate": 1.8383197939369922e-05, "loss": 0.948613452911377, "step": 4640 }, { "epoch": 0.027640565650801575, "grad_norm": 2.7197930812835693, "learning_rate": 1.8422825440855954e-05, "loss": 0.9407907485961914, "step": 4650 }, { "epoch": 0.02770000772746997, "grad_norm": 3.4868173599243164, "learning_rate": 1.8462452942341986e-05, "loss": 1.0131364822387696, "step": 4660 }, { "epoch": 0.02775944980413836, "grad_norm": 2.96767258644104, "learning_rate": 1.8502080443828018e-05, "loss": 1.0201663017272948, "step": 4670 }, { "epoch": 0.02781889188080675, "grad_norm": 3.045664072036743, "learning_rate": 1.854170794531405e-05, "loss": 0.9888156890869141, "step": 4680 }, { "epoch": 0.02787833395747514, "grad_norm": 2.8663973808288574, "learning_rate": 1.858133544680008e-05, "loss": 0.9396116256713867, "step": 4690 }, { "epoch": 0.02793777603414353, "grad_norm": 2.4522011280059814, "learning_rate": 1.862096294828611e-05, "loss": 0.9161691665649414, "step": 4700 }, { "epoch": 0.02799721811081192, "grad_norm": 2.501009464263916, "learning_rate": 1.8660590449772142e-05, "loss": 0.9328290939331054, "step": 4710 }, { "epoch": 0.02805666018748031, "grad_norm": 2.4529006481170654, "learning_rate": 1.8700217951258177e-05, "loss": 0.8393545150756836, "step": 4720 }, { "epoch": 0.0281161022641487, "grad_norm": 3.391587257385254, "learning_rate": 1.8739845452744206e-05, "loss": 1.0271577835083008, "step": 4730 }, { "epoch": 0.02817554434081709, "grad_norm": 3.324859380722046, "learning_rate": 1.8779472954230237e-05, "loss": 0.8787607192993164, "step": 4740 }, { "epoch": 0.02823498641748548, "grad_norm": 3.2569894790649414, "learning_rate": 1.881910045571627e-05, "loss": 0.9404687881469727, "step": 4750 }, { "epoch": 0.02829442849415387, "grad_norm": 2.3653478622436523, "learning_rate": 1.8858727957202298e-05, "loss": 0.9066884040832519, "step": 4760 }, { "epoch": 0.02835387057082226, "grad_norm": 3.3838720321655273, "learning_rate": 1.889835545868833e-05, "loss": 0.9448785781860352, "step": 4770 }, { "epoch": 0.028413312647490654, "grad_norm": 2.335038185119629, "learning_rate": 1.893798296017436e-05, "loss": 0.8997000694274903, "step": 4780 }, { "epoch": 0.028472754724159045, "grad_norm": 3.003020763397217, "learning_rate": 1.8977610461660393e-05, "loss": 0.957003402709961, "step": 4790 }, { "epoch": 0.028532196800827435, "grad_norm": 2.8803093433380127, "learning_rate": 1.9017237963146425e-05, "loss": 0.9069509506225586, "step": 4800 }, { "epoch": 0.028591638877495825, "grad_norm": 2.777956008911133, "learning_rate": 1.9056865464632457e-05, "loss": 0.9279718399047852, "step": 4810 }, { "epoch": 0.028651080954164215, "grad_norm": 3.0639872550964355, "learning_rate": 1.9096492966118486e-05, "loss": 0.9523209571838379, "step": 4820 }, { "epoch": 0.028710523030832606, "grad_norm": 3.0635533332824707, "learning_rate": 1.9136120467604518e-05, "loss": 0.9257299423217773, "step": 4830 }, { "epoch": 0.028769965107500996, "grad_norm": 2.8611838817596436, "learning_rate": 1.917574796909055e-05, "loss": 0.8804914474487304, "step": 4840 }, { "epoch": 0.028829407184169386, "grad_norm": 3.018570899963379, "learning_rate": 1.921537547057658e-05, "loss": 0.910906982421875, "step": 4850 }, { "epoch": 0.028888849260837776, "grad_norm": 2.7042834758758545, "learning_rate": 1.9255002972062613e-05, "loss": 0.9754165649414063, "step": 4860 }, { "epoch": 0.028948291337506166, "grad_norm": 2.387810707092285, "learning_rate": 1.9294630473548645e-05, "loss": 0.9289260864257812, "step": 4870 }, { "epoch": 0.029007733414174557, "grad_norm": 2.650336980819702, "learning_rate": 1.9334257975034677e-05, "loss": 0.9006792068481445, "step": 4880 }, { "epoch": 0.029067175490842947, "grad_norm": 3.025372266769409, "learning_rate": 1.9373885476520705e-05, "loss": 1.034602737426758, "step": 4890 }, { "epoch": 0.029126617567511337, "grad_norm": 2.6558003425598145, "learning_rate": 1.9413512978006737e-05, "loss": 0.9461427688598633, "step": 4900 }, { "epoch": 0.02918605964417973, "grad_norm": 2.913576126098633, "learning_rate": 1.945314047949277e-05, "loss": 0.9500835418701172, "step": 4910 }, { "epoch": 0.02924550172084812, "grad_norm": 3.170200824737549, "learning_rate": 1.9492767980978798e-05, "loss": 0.8839879035949707, "step": 4920 }, { "epoch": 0.02930494379751651, "grad_norm": 2.415130138397217, "learning_rate": 1.9532395482464833e-05, "loss": 0.9441818237304688, "step": 4930 }, { "epoch": 0.0293643858741849, "grad_norm": 2.4703478813171387, "learning_rate": 1.9572022983950865e-05, "loss": 0.9665049552917481, "step": 4940 }, { "epoch": 0.02942382795085329, "grad_norm": 2.581455945968628, "learning_rate": 1.9611650485436893e-05, "loss": 0.8770780563354492, "step": 4950 }, { "epoch": 0.029483270027521682, "grad_norm": 2.420039653778076, "learning_rate": 1.9651277986922925e-05, "loss": 0.8856571197509766, "step": 4960 }, { "epoch": 0.029542712104190072, "grad_norm": 2.7733314037323, "learning_rate": 1.9690905488408957e-05, "loss": 0.8918987274169922, "step": 4970 }, { "epoch": 0.029602154180858462, "grad_norm": 3.138762950897217, "learning_rate": 1.9730532989894986e-05, "loss": 0.9622640609741211, "step": 4980 }, { "epoch": 0.029661596257526852, "grad_norm": 2.835994005203247, "learning_rate": 1.977016049138102e-05, "loss": 0.9829300880432129, "step": 4990 }, { "epoch": 0.029721038334195243, "grad_norm": 2.47890567779541, "learning_rate": 1.9809787992867053e-05, "loss": 0.9173810958862305, "step": 5000 }, { "epoch": 0.029780480410863633, "grad_norm": 2.6958441734313965, "learning_rate": 1.984941549435308e-05, "loss": 0.9090386390686035, "step": 5010 }, { "epoch": 0.029839922487532023, "grad_norm": 2.620558977127075, "learning_rate": 1.9889042995839113e-05, "loss": 0.8966389656066894, "step": 5020 }, { "epoch": 0.029899364564200413, "grad_norm": 3.0196497440338135, "learning_rate": 1.9928670497325145e-05, "loss": 0.8349458694458007, "step": 5030 }, { "epoch": 0.029958806640868807, "grad_norm": 2.676588296890259, "learning_rate": 1.9968297998811177e-05, "loss": 0.9615718841552734, "step": 5040 }, { "epoch": 0.030018248717537197, "grad_norm": 2.9387848377227783, "learning_rate": 2.0007925500297205e-05, "loss": 0.9531806945800781, "step": 5050 }, { "epoch": 0.030077690794205587, "grad_norm": 4.009819507598877, "learning_rate": 2.004755300178324e-05, "loss": 0.9653018951416016, "step": 5060 }, { "epoch": 0.030137132870873978, "grad_norm": 2.9162235260009766, "learning_rate": 2.008718050326927e-05, "loss": 0.9447144508361817, "step": 5070 }, { "epoch": 0.030196574947542368, "grad_norm": 2.7530620098114014, "learning_rate": 2.01268080047553e-05, "loss": 0.8448934555053711, "step": 5080 }, { "epoch": 0.030256017024210758, "grad_norm": 3.3561954498291016, "learning_rate": 2.0166435506241333e-05, "loss": 0.950253677368164, "step": 5090 }, { "epoch": 0.030315459100879148, "grad_norm": 2.7180745601654053, "learning_rate": 2.0206063007727365e-05, "loss": 0.9167647361755371, "step": 5100 }, { "epoch": 0.03037490117754754, "grad_norm": 2.987527847290039, "learning_rate": 2.0245690509213393e-05, "loss": 0.9601247787475586, "step": 5110 }, { "epoch": 0.03043434325421593, "grad_norm": 2.8013594150543213, "learning_rate": 2.0285318010699425e-05, "loss": 1.0045852661132812, "step": 5120 }, { "epoch": 0.03049378533088432, "grad_norm": 3.4244701862335205, "learning_rate": 2.032494551218546e-05, "loss": 0.9473334312438965, "step": 5130 }, { "epoch": 0.03055322740755271, "grad_norm": 2.8962788581848145, "learning_rate": 2.036457301367149e-05, "loss": 0.8948871612548828, "step": 5140 }, { "epoch": 0.0306126694842211, "grad_norm": 2.4062042236328125, "learning_rate": 2.040420051515752e-05, "loss": 0.9386625289916992, "step": 5150 }, { "epoch": 0.03067211156088949, "grad_norm": 2.5923750400543213, "learning_rate": 2.0443828016643553e-05, "loss": 0.8885410308837891, "step": 5160 }, { "epoch": 0.030731553637557883, "grad_norm": 3.093161106109619, "learning_rate": 2.048345551812958e-05, "loss": 1.0058931350708007, "step": 5170 }, { "epoch": 0.030790995714226273, "grad_norm": 2.9481277465820312, "learning_rate": 2.0523083019615613e-05, "loss": 0.9530448913574219, "step": 5180 }, { "epoch": 0.030850437790894664, "grad_norm": 3.4080820083618164, "learning_rate": 2.0562710521101648e-05, "loss": 0.931705379486084, "step": 5190 }, { "epoch": 0.030909879867563054, "grad_norm": 2.666696071624756, "learning_rate": 2.0602338022587677e-05, "loss": 0.8770763397216796, "step": 5200 }, { "epoch": 0.030969321944231444, "grad_norm": 2.81117582321167, "learning_rate": 2.064196552407371e-05, "loss": 0.9029839515686036, "step": 5210 }, { "epoch": 0.031028764020899834, "grad_norm": 2.6140260696411133, "learning_rate": 2.068159302555974e-05, "loss": 0.9222320556640625, "step": 5220 }, { "epoch": 0.031088206097568225, "grad_norm": 2.7414653301239014, "learning_rate": 2.072122052704577e-05, "loss": 0.9217964172363281, "step": 5230 }, { "epoch": 0.031147648174236615, "grad_norm": 3.088160514831543, "learning_rate": 2.07608480285318e-05, "loss": 0.9423885345458984, "step": 5240 }, { "epoch": 0.031207090250905005, "grad_norm": 2.1126818656921387, "learning_rate": 2.0800475530017833e-05, "loss": 0.908842658996582, "step": 5250 }, { "epoch": 0.0312665323275734, "grad_norm": 2.8796207904815674, "learning_rate": 2.0840103031503865e-05, "loss": 0.8452016830444335, "step": 5260 }, { "epoch": 0.031325974404241785, "grad_norm": 3.1657838821411133, "learning_rate": 2.0879730532989896e-05, "loss": 0.9277463912963867, "step": 5270 }, { "epoch": 0.03138541648091018, "grad_norm": 2.5184710025787354, "learning_rate": 2.091935803447593e-05, "loss": 0.8961844444274902, "step": 5280 }, { "epoch": 0.031444858557578566, "grad_norm": 2.545380115509033, "learning_rate": 2.095898553596196e-05, "loss": 0.9297532081604004, "step": 5290 }, { "epoch": 0.03150430063424696, "grad_norm": 2.318607807159424, "learning_rate": 2.099861303744799e-05, "loss": 0.9288763999938965, "step": 5300 }, { "epoch": 0.031563742710915346, "grad_norm": 2.7338335514068604, "learning_rate": 2.103824053893402e-05, "loss": 0.9345544815063477, "step": 5310 }, { "epoch": 0.03162318478758374, "grad_norm": 3.0035386085510254, "learning_rate": 2.1077868040420052e-05, "loss": 0.9662408828735352, "step": 5320 }, { "epoch": 0.03168262686425213, "grad_norm": 3.108424186706543, "learning_rate": 2.1117495541906084e-05, "loss": 0.9190208435058593, "step": 5330 }, { "epoch": 0.03174206894092052, "grad_norm": 2.4765470027923584, "learning_rate": 2.1157123043392116e-05, "loss": 0.9222660064697266, "step": 5340 }, { "epoch": 0.03180151101758891, "grad_norm": 2.73634934425354, "learning_rate": 2.1196750544878148e-05, "loss": 0.868468189239502, "step": 5350 }, { "epoch": 0.0318609530942573, "grad_norm": 2.417205572128296, "learning_rate": 2.1236378046364177e-05, "loss": 1.0040753364562989, "step": 5360 }, { "epoch": 0.031920395170925694, "grad_norm": 2.3479316234588623, "learning_rate": 2.127600554785021e-05, "loss": 0.9262178421020508, "step": 5370 }, { "epoch": 0.03197983724759408, "grad_norm": 2.8118553161621094, "learning_rate": 2.131563304933624e-05, "loss": 0.9349292755126953, "step": 5380 }, { "epoch": 0.032039279324262475, "grad_norm": 3.04375958442688, "learning_rate": 2.1355260550822272e-05, "loss": 0.9168002128601074, "step": 5390 }, { "epoch": 0.03209872140093086, "grad_norm": 2.9377059936523438, "learning_rate": 2.1394888052308304e-05, "loss": 0.9615909576416015, "step": 5400 }, { "epoch": 0.032158163477599255, "grad_norm": 2.3374924659729004, "learning_rate": 2.1434515553794336e-05, "loss": 0.882204818725586, "step": 5410 }, { "epoch": 0.03221760555426764, "grad_norm": 2.1564643383026123, "learning_rate": 2.1474143055280364e-05, "loss": 0.9824613571166992, "step": 5420 }, { "epoch": 0.032277047630936036, "grad_norm": 3.161036491394043, "learning_rate": 2.1513770556766396e-05, "loss": 0.8890127182006836, "step": 5430 }, { "epoch": 0.03233648970760442, "grad_norm": 2.904855251312256, "learning_rate": 2.1553398058252428e-05, "loss": 0.9519600868225098, "step": 5440 }, { "epoch": 0.032395931784272816, "grad_norm": 2.0854504108428955, "learning_rate": 2.159302555973846e-05, "loss": 0.9125760078430176, "step": 5450 }, { "epoch": 0.0324553738609412, "grad_norm": 3.063018321990967, "learning_rate": 2.1632653061224492e-05, "loss": 0.8623395919799804, "step": 5460 }, { "epoch": 0.0325148159376096, "grad_norm": 2.7935352325439453, "learning_rate": 2.1672280562710524e-05, "loss": 0.873776912689209, "step": 5470 }, { "epoch": 0.03257425801427799, "grad_norm": 2.841179847717285, "learning_rate": 2.1711908064196552e-05, "loss": 0.9795008659362793, "step": 5480 }, { "epoch": 0.03263370009094638, "grad_norm": 2.816272258758545, "learning_rate": 2.1751535565682584e-05, "loss": 0.9371305465698242, "step": 5490 }, { "epoch": 0.03269314216761477, "grad_norm": 2.5354764461517334, "learning_rate": 2.1791163067168616e-05, "loss": 0.8662063598632812, "step": 5500 }, { "epoch": 0.03275258424428316, "grad_norm": 3.159834623336792, "learning_rate": 2.1830790568654648e-05, "loss": 0.855487060546875, "step": 5510 }, { "epoch": 0.03281202632095155, "grad_norm": 2.7978098392486572, "learning_rate": 2.1870418070140676e-05, "loss": 0.8876998901367188, "step": 5520 }, { "epoch": 0.03287146839761994, "grad_norm": 2.932246685028076, "learning_rate": 2.1910045571626712e-05, "loss": 0.8966188430786133, "step": 5530 }, { "epoch": 0.03293091047428833, "grad_norm": 2.780815839767456, "learning_rate": 2.1949673073112744e-05, "loss": 0.8916084289550781, "step": 5540 }, { "epoch": 0.03299035255095672, "grad_norm": 2.573654890060425, "learning_rate": 2.1989300574598772e-05, "loss": 0.9297924041748047, "step": 5550 }, { "epoch": 0.03304979462762511, "grad_norm": 2.5983431339263916, "learning_rate": 2.2028928076084804e-05, "loss": 0.9563896179199218, "step": 5560 }, { "epoch": 0.0331092367042935, "grad_norm": 2.35685658454895, "learning_rate": 2.2068555577570836e-05, "loss": 0.9103824615478515, "step": 5570 }, { "epoch": 0.03316867878096189, "grad_norm": 3.162708282470703, "learning_rate": 2.2108183079056864e-05, "loss": 0.8690174102783204, "step": 5580 }, { "epoch": 0.03322812085763028, "grad_norm": 3.116472005844116, "learning_rate": 2.2147810580542896e-05, "loss": 0.9157417297363282, "step": 5590 }, { "epoch": 0.03328756293429867, "grad_norm": 2.257890224456787, "learning_rate": 2.218743808202893e-05, "loss": 0.9027931213378906, "step": 5600 }, { "epoch": 0.03334700501096707, "grad_norm": 2.94757080078125, "learning_rate": 2.222706558351496e-05, "loss": 0.8575244903564453, "step": 5610 }, { "epoch": 0.03340644708763545, "grad_norm": 2.3968422412872314, "learning_rate": 2.2266693085000992e-05, "loss": 0.8936684608459473, "step": 5620 }, { "epoch": 0.03346588916430385, "grad_norm": 2.9925696849823, "learning_rate": 2.2306320586487024e-05, "loss": 0.9200151443481446, "step": 5630 }, { "epoch": 0.033525331240972234, "grad_norm": 3.4382543563842773, "learning_rate": 2.2345948087973052e-05, "loss": 0.867798137664795, "step": 5640 }, { "epoch": 0.03358477331764063, "grad_norm": 2.3416213989257812, "learning_rate": 2.2385575589459084e-05, "loss": 0.9725597381591797, "step": 5650 }, { "epoch": 0.033644215394309014, "grad_norm": 3.0791382789611816, "learning_rate": 2.242520309094512e-05, "loss": 0.9273576736450195, "step": 5660 }, { "epoch": 0.03370365747097741, "grad_norm": 3.0693273544311523, "learning_rate": 2.2464830592431148e-05, "loss": 0.9189577102661133, "step": 5670 }, { "epoch": 0.033763099547645795, "grad_norm": 3.289592742919922, "learning_rate": 2.250445809391718e-05, "loss": 0.899449348449707, "step": 5680 }, { "epoch": 0.03382254162431419, "grad_norm": 2.2621119022369385, "learning_rate": 2.254408559540321e-05, "loss": 1.0003168106079101, "step": 5690 }, { "epoch": 0.033881983700982575, "grad_norm": 3.034879684448242, "learning_rate": 2.2583713096889244e-05, "loss": 0.8929978370666504, "step": 5700 }, { "epoch": 0.03394142577765097, "grad_norm": 2.6121621131896973, "learning_rate": 2.2623340598375272e-05, "loss": 0.905037784576416, "step": 5710 }, { "epoch": 0.034000867854319355, "grad_norm": 3.4470081329345703, "learning_rate": 2.2662968099861304e-05, "loss": 0.9521738052368164, "step": 5720 }, { "epoch": 0.03406030993098775, "grad_norm": 2.809431314468384, "learning_rate": 2.2702595601347336e-05, "loss": 0.9223876953125, "step": 5730 }, { "epoch": 0.03411975200765614, "grad_norm": 2.905404567718506, "learning_rate": 2.2742223102833368e-05, "loss": 0.8106907844543457, "step": 5740 }, { "epoch": 0.03417919408432453, "grad_norm": 2.5888845920562744, "learning_rate": 2.27818506043194e-05, "loss": 0.9112408638000489, "step": 5750 }, { "epoch": 0.03423863616099292, "grad_norm": 2.6788930892944336, "learning_rate": 2.282147810580543e-05, "loss": 0.9266034126281738, "step": 5760 }, { "epoch": 0.03429807823766131, "grad_norm": 3.4754624366760254, "learning_rate": 2.286110560729146e-05, "loss": 1.0035078048706054, "step": 5770 }, { "epoch": 0.034357520314329704, "grad_norm": 2.4248204231262207, "learning_rate": 2.2900733108777492e-05, "loss": 0.8816068649291993, "step": 5780 }, { "epoch": 0.03441696239099809, "grad_norm": 2.615086317062378, "learning_rate": 2.2940360610263524e-05, "loss": 0.8242943763732911, "step": 5790 }, { "epoch": 0.034476404467666484, "grad_norm": 2.617062568664551, "learning_rate": 2.2979988111749556e-05, "loss": 0.8442831993103027, "step": 5800 }, { "epoch": 0.03453584654433487, "grad_norm": 3.050285816192627, "learning_rate": 2.3019615613235587e-05, "loss": 0.9235431671142578, "step": 5810 }, { "epoch": 0.034595288621003265, "grad_norm": 2.2410695552825928, "learning_rate": 2.305924311472162e-05, "loss": 0.8109147071838378, "step": 5820 }, { "epoch": 0.03465473069767165, "grad_norm": 2.847064256668091, "learning_rate": 2.3098870616207648e-05, "loss": 0.9258049011230469, "step": 5830 }, { "epoch": 0.034714172774340045, "grad_norm": 2.533586025238037, "learning_rate": 2.313849811769368e-05, "loss": 0.9265259742736817, "step": 5840 }, { "epoch": 0.03477361485100843, "grad_norm": 2.6847476959228516, "learning_rate": 2.317812561917971e-05, "loss": 0.9046340942382812, "step": 5850 }, { "epoch": 0.034833056927676825, "grad_norm": 2.2515106201171875, "learning_rate": 2.3217753120665743e-05, "loss": 0.9089527130126953, "step": 5860 }, { "epoch": 0.03489249900434522, "grad_norm": 2.4845736026763916, "learning_rate": 2.3257380622151775e-05, "loss": 0.8985818862915039, "step": 5870 }, { "epoch": 0.034951941081013606, "grad_norm": 2.3573970794677734, "learning_rate": 2.3297008123637807e-05, "loss": 0.9331266403198242, "step": 5880 }, { "epoch": 0.035011383157682, "grad_norm": 2.8347086906433105, "learning_rate": 2.3336635625123836e-05, "loss": 0.8860992431640625, "step": 5890 }, { "epoch": 0.035070825234350386, "grad_norm": 3.0314106941223145, "learning_rate": 2.3376263126609868e-05, "loss": 0.947608757019043, "step": 5900 }, { "epoch": 0.03513026731101878, "grad_norm": 3.0521674156188965, "learning_rate": 2.34158906280959e-05, "loss": 0.8462265014648438, "step": 5910 }, { "epoch": 0.03518970938768717, "grad_norm": 2.767821788787842, "learning_rate": 2.345551812958193e-05, "loss": 0.9142335891723633, "step": 5920 }, { "epoch": 0.03524915146435556, "grad_norm": 2.424729347229004, "learning_rate": 2.3495145631067963e-05, "loss": 0.9342098236083984, "step": 5930 }, { "epoch": 0.03530859354102395, "grad_norm": 2.4645261764526367, "learning_rate": 2.3534773132553995e-05, "loss": 0.8813352584838867, "step": 5940 }, { "epoch": 0.03536803561769234, "grad_norm": 2.6407132148742676, "learning_rate": 2.3574400634040027e-05, "loss": 0.869696044921875, "step": 5950 }, { "epoch": 0.03542747769436073, "grad_norm": 3.1391313076019287, "learning_rate": 2.3614028135526055e-05, "loss": 0.9317840576171875, "step": 5960 }, { "epoch": 0.03548691977102912, "grad_norm": 2.226388454437256, "learning_rate": 2.3653655637012087e-05, "loss": 0.9083395004272461, "step": 5970 }, { "epoch": 0.03554636184769751, "grad_norm": 2.4697413444519043, "learning_rate": 2.369328313849812e-05, "loss": 0.8585241317749024, "step": 5980 }, { "epoch": 0.0356058039243659, "grad_norm": 2.5455434322357178, "learning_rate": 2.3732910639984148e-05, "loss": 0.9741205215454102, "step": 5990 }, { "epoch": 0.035665246001034295, "grad_norm": 2.4282286167144775, "learning_rate": 2.3772538141470183e-05, "loss": 0.9222089767456054, "step": 6000 }, { "epoch": 0.03572468807770268, "grad_norm": 2.609372854232788, "learning_rate": 2.3812165642956215e-05, "loss": 0.8899099349975585, "step": 6010 }, { "epoch": 0.035784130154371076, "grad_norm": 2.4395253658294678, "learning_rate": 2.3851793144442243e-05, "loss": 0.8135545730590821, "step": 6020 }, { "epoch": 0.03584357223103946, "grad_norm": 2.943509340286255, "learning_rate": 2.3891420645928275e-05, "loss": 0.9005171775817871, "step": 6030 }, { "epoch": 0.035903014307707856, "grad_norm": 3.14396595954895, "learning_rate": 2.3931048147414307e-05, "loss": 0.9757545471191407, "step": 6040 }, { "epoch": 0.03596245638437624, "grad_norm": 2.9701545238494873, "learning_rate": 2.3970675648900336e-05, "loss": 0.8566795349121094, "step": 6050 }, { "epoch": 0.03602189846104464, "grad_norm": 2.1600489616394043, "learning_rate": 2.4010303150386367e-05, "loss": 0.8583416938781738, "step": 6060 }, { "epoch": 0.03608134053771302, "grad_norm": 2.833268404006958, "learning_rate": 2.4049930651872403e-05, "loss": 0.8949755668640137, "step": 6070 }, { "epoch": 0.03614078261438142, "grad_norm": 2.3900558948516846, "learning_rate": 2.408955815335843e-05, "loss": 0.9013092041015625, "step": 6080 }, { "epoch": 0.036200224691049804, "grad_norm": 1.9495874643325806, "learning_rate": 2.4129185654844463e-05, "loss": 0.9431028366088867, "step": 6090 }, { "epoch": 0.0362596667677182, "grad_norm": 2.9818549156188965, "learning_rate": 2.4168813156330495e-05, "loss": 0.8838360786437989, "step": 6100 }, { "epoch": 0.036319108844386584, "grad_norm": 2.3269829750061035, "learning_rate": 2.4208440657816527e-05, "loss": 0.9106047630310059, "step": 6110 }, { "epoch": 0.03637855092105498, "grad_norm": 2.498410940170288, "learning_rate": 2.4248068159302555e-05, "loss": 0.9023134231567382, "step": 6120 }, { "epoch": 0.03643799299772337, "grad_norm": 2.9516003131866455, "learning_rate": 2.428769566078859e-05, "loss": 0.8631854057312012, "step": 6130 }, { "epoch": 0.03649743507439176, "grad_norm": 3.1008198261260986, "learning_rate": 2.432732316227462e-05, "loss": 0.9287908554077149, "step": 6140 }, { "epoch": 0.03655687715106015, "grad_norm": 2.4507811069488525, "learning_rate": 2.436695066376065e-05, "loss": 0.7547933101654053, "step": 6150 }, { "epoch": 0.03661631922772854, "grad_norm": 2.630974531173706, "learning_rate": 2.4406578165246683e-05, "loss": 0.8667783737182617, "step": 6160 }, { "epoch": 0.03667576130439693, "grad_norm": 2.3138082027435303, "learning_rate": 2.4446205666732715e-05, "loss": 0.8886359214782715, "step": 6170 }, { "epoch": 0.03673520338106532, "grad_norm": 3.1711835861206055, "learning_rate": 2.4485833168218743e-05, "loss": 0.929353904724121, "step": 6180 }, { "epoch": 0.03679464545773371, "grad_norm": 3.493867874145508, "learning_rate": 2.4525460669704775e-05, "loss": 0.8928555488586426, "step": 6190 }, { "epoch": 0.0368540875344021, "grad_norm": 1.7628499269485474, "learning_rate": 2.456508817119081e-05, "loss": 0.8539106369018554, "step": 6200 }, { "epoch": 0.03691352961107049, "grad_norm": 2.504826545715332, "learning_rate": 2.460471567267684e-05, "loss": 0.939208984375, "step": 6210 }, { "epoch": 0.03697297168773888, "grad_norm": 2.5208640098571777, "learning_rate": 2.464434317416287e-05, "loss": 0.8736295700073242, "step": 6220 }, { "epoch": 0.037032413764407274, "grad_norm": 2.5166635513305664, "learning_rate": 2.4683970675648903e-05, "loss": 0.8799285888671875, "step": 6230 }, { "epoch": 0.03709185584107566, "grad_norm": 2.2628560066223145, "learning_rate": 2.472359817713493e-05, "loss": 0.89227294921875, "step": 6240 }, { "epoch": 0.037151297917744054, "grad_norm": 2.6206142902374268, "learning_rate": 2.4763225678620963e-05, "loss": 0.8816762924194336, "step": 6250 }, { "epoch": 0.03721073999441245, "grad_norm": 1.9576410055160522, "learning_rate": 2.4802853180106995e-05, "loss": 0.8899982452392579, "step": 6260 }, { "epoch": 0.037270182071080835, "grad_norm": 2.454043388366699, "learning_rate": 2.4842480681593027e-05, "loss": 0.9367635726928711, "step": 6270 }, { "epoch": 0.03732962414774923, "grad_norm": 2.721562385559082, "learning_rate": 2.488210818307906e-05, "loss": 0.8675838470458984, "step": 6280 }, { "epoch": 0.037389066224417615, "grad_norm": 2.582026481628418, "learning_rate": 2.492173568456509e-05, "loss": 0.864421272277832, "step": 6290 }, { "epoch": 0.03744850830108601, "grad_norm": 2.473580837249756, "learning_rate": 2.496136318605112e-05, "loss": 0.8527591705322266, "step": 6300 }, { "epoch": 0.037507950377754395, "grad_norm": 2.6933369636535645, "learning_rate": 2.500099068753715e-05, "loss": 0.8928985595703125, "step": 6310 }, { "epoch": 0.03756739245442279, "grad_norm": 2.561436891555786, "learning_rate": 2.5040618189023186e-05, "loss": 0.8967732429504395, "step": 6320 }, { "epoch": 0.037626834531091176, "grad_norm": 2.648637533187866, "learning_rate": 2.5080245690509215e-05, "loss": 0.8618123054504394, "step": 6330 }, { "epoch": 0.03768627660775957, "grad_norm": 2.7563047409057617, "learning_rate": 2.5119873191995246e-05, "loss": 0.8589032173156739, "step": 6340 }, { "epoch": 0.037745718684427956, "grad_norm": 2.2126412391662598, "learning_rate": 2.5159500693481275e-05, "loss": 0.9194178581237793, "step": 6350 }, { "epoch": 0.03780516076109635, "grad_norm": 3.0751914978027344, "learning_rate": 2.519912819496731e-05, "loss": 0.8991554260253907, "step": 6360 }, { "epoch": 0.03786460283776474, "grad_norm": 2.2223613262176514, "learning_rate": 2.5238755696453342e-05, "loss": 0.918914794921875, "step": 6370 }, { "epoch": 0.03792404491443313, "grad_norm": 2.019076347351074, "learning_rate": 2.527838319793937e-05, "loss": 0.9005353927612305, "step": 6380 }, { "epoch": 0.037983486991101524, "grad_norm": 2.603895425796509, "learning_rate": 2.5318010699425402e-05, "loss": 0.8970386505126953, "step": 6390 }, { "epoch": 0.03804292906776991, "grad_norm": 2.6431779861450195, "learning_rate": 2.535763820091143e-05, "loss": 0.8300168991088868, "step": 6400 }, { "epoch": 0.038102371144438305, "grad_norm": 2.391792058944702, "learning_rate": 2.5397265702397466e-05, "loss": 0.8446109771728516, "step": 6410 }, { "epoch": 0.03816181322110669, "grad_norm": 2.72017240524292, "learning_rate": 2.5436893203883495e-05, "loss": 0.8898948669433594, "step": 6420 }, { "epoch": 0.038221255297775085, "grad_norm": 2.8419110774993896, "learning_rate": 2.5476520705369527e-05, "loss": 0.9007057189941406, "step": 6430 }, { "epoch": 0.03828069737444347, "grad_norm": 2.5889804363250732, "learning_rate": 2.5516148206855562e-05, "loss": 0.8862222671508789, "step": 6440 }, { "epoch": 0.038340139451111865, "grad_norm": 2.945495367050171, "learning_rate": 2.555577570834159e-05, "loss": 0.9159539222717286, "step": 6450 }, { "epoch": 0.03839958152778025, "grad_norm": 2.3216981887817383, "learning_rate": 2.5595403209827622e-05, "loss": 0.8442692756652832, "step": 6460 }, { "epoch": 0.038459023604448646, "grad_norm": 2.607597589492798, "learning_rate": 2.563503071131365e-05, "loss": 0.8539608955383301, "step": 6470 }, { "epoch": 0.03851846568111703, "grad_norm": 2.4344494342803955, "learning_rate": 2.5674658212799686e-05, "loss": 0.8927309036254882, "step": 6480 }, { "epoch": 0.038577907757785426, "grad_norm": 2.413058042526245, "learning_rate": 2.5714285714285714e-05, "loss": 0.8173547744750976, "step": 6490 }, { "epoch": 0.03863734983445382, "grad_norm": 2.123419761657715, "learning_rate": 2.5753913215771746e-05, "loss": 0.8912481307983399, "step": 6500 }, { "epoch": 0.03869679191112221, "grad_norm": 2.948533058166504, "learning_rate": 2.579354071725778e-05, "loss": 0.9099753379821778, "step": 6510 }, { "epoch": 0.0387562339877906, "grad_norm": 2.2829229831695557, "learning_rate": 2.583316821874381e-05, "loss": 0.8855247497558594, "step": 6520 }, { "epoch": 0.03881567606445899, "grad_norm": 2.28347110748291, "learning_rate": 2.5872795720229842e-05, "loss": 0.8660335540771484, "step": 6530 }, { "epoch": 0.03887511814112738, "grad_norm": 2.791036367416382, "learning_rate": 2.591242322171587e-05, "loss": 0.8383049964904785, "step": 6540 }, { "epoch": 0.03893456021779577, "grad_norm": 3.489001989364624, "learning_rate": 2.5952050723201902e-05, "loss": 0.8435766220092773, "step": 6550 }, { "epoch": 0.03899400229446416, "grad_norm": 2.939663887023926, "learning_rate": 2.599167822468793e-05, "loss": 0.8423980712890625, "step": 6560 }, { "epoch": 0.03905344437113255, "grad_norm": 2.751161575317383, "learning_rate": 2.6031305726173966e-05, "loss": 0.9655380249023438, "step": 6570 }, { "epoch": 0.03911288644780094, "grad_norm": 2.3537824153900146, "learning_rate": 2.6070933227659998e-05, "loss": 0.8705463409423828, "step": 6580 }, { "epoch": 0.03917232852446933, "grad_norm": 2.399657726287842, "learning_rate": 2.6110560729146026e-05, "loss": 0.9045382499694824, "step": 6590 }, { "epoch": 0.03923177060113772, "grad_norm": 2.2861979007720947, "learning_rate": 2.6150188230632062e-05, "loss": 0.8643861770629883, "step": 6600 }, { "epoch": 0.03929121267780611, "grad_norm": 3.1074342727661133, "learning_rate": 2.618981573211809e-05, "loss": 0.8573295593261718, "step": 6610 }, { "epoch": 0.0393506547544745, "grad_norm": 2.90919828414917, "learning_rate": 2.6229443233604122e-05, "loss": 0.8930130004882812, "step": 6620 }, { "epoch": 0.039410096831142896, "grad_norm": 2.3129749298095703, "learning_rate": 2.6269070735090157e-05, "loss": 0.8920749664306641, "step": 6630 }, { "epoch": 0.03946953890781128, "grad_norm": 2.565349578857422, "learning_rate": 2.6308698236576186e-05, "loss": 0.8885994911193847, "step": 6640 }, { "epoch": 0.03952898098447968, "grad_norm": 2.1871423721313477, "learning_rate": 2.6348325738062218e-05, "loss": 0.8566898345947266, "step": 6650 }, { "epoch": 0.03958842306114806, "grad_norm": 2.137547492980957, "learning_rate": 2.6387953239548246e-05, "loss": 0.886318588256836, "step": 6660 }, { "epoch": 0.03964786513781646, "grad_norm": 2.991398811340332, "learning_rate": 2.642758074103428e-05, "loss": 0.8500954627990722, "step": 6670 }, { "epoch": 0.039707307214484844, "grad_norm": 2.41426944732666, "learning_rate": 2.646720824252031e-05, "loss": 0.8544618606567382, "step": 6680 }, { "epoch": 0.03976674929115324, "grad_norm": 2.2862067222595215, "learning_rate": 2.6506835744006342e-05, "loss": 0.8422863006591796, "step": 6690 }, { "epoch": 0.039826191367821624, "grad_norm": 2.0662777423858643, "learning_rate": 2.6546463245492377e-05, "loss": 0.8366716384887696, "step": 6700 }, { "epoch": 0.03988563344449002, "grad_norm": 3.200453042984009, "learning_rate": 2.6586090746978402e-05, "loss": 0.8667165756225585, "step": 6710 }, { "epoch": 0.039945075521158405, "grad_norm": 2.0809974670410156, "learning_rate": 2.6625718248464437e-05, "loss": 0.9390596389770508, "step": 6720 }, { "epoch": 0.0400045175978268, "grad_norm": 2.942026376724243, "learning_rate": 2.6665345749950466e-05, "loss": 0.9135062217712402, "step": 6730 }, { "epoch": 0.040063959674495185, "grad_norm": 2.1937193870544434, "learning_rate": 2.6704973251436498e-05, "loss": 0.8463022232055664, "step": 6740 }, { "epoch": 0.04012340175116358, "grad_norm": 1.707700252532959, "learning_rate": 2.6744600752922526e-05, "loss": 0.8378320693969726, "step": 6750 }, { "epoch": 0.04018284382783197, "grad_norm": 2.2628400325775146, "learning_rate": 2.678422825440856e-05, "loss": 0.8373445510864258, "step": 6760 }, { "epoch": 0.04024228590450036, "grad_norm": 2.6187515258789062, "learning_rate": 2.6823855755894593e-05, "loss": 0.9101374626159668, "step": 6770 }, { "epoch": 0.04030172798116875, "grad_norm": 2.7933361530303955, "learning_rate": 2.6863483257380622e-05, "loss": 0.8114681243896484, "step": 6780 }, { "epoch": 0.04036117005783714, "grad_norm": 2.6565370559692383, "learning_rate": 2.6903110758866657e-05, "loss": 0.9189868927001953, "step": 6790 }, { "epoch": 0.04042061213450553, "grad_norm": 2.8292396068573, "learning_rate": 2.6942738260352686e-05, "loss": 0.896082878112793, "step": 6800 }, { "epoch": 0.04048005421117392, "grad_norm": 2.6979055404663086, "learning_rate": 2.6982365761838718e-05, "loss": 0.8438510894775391, "step": 6810 }, { "epoch": 0.040539496287842314, "grad_norm": 2.7305479049682617, "learning_rate": 2.7021993263324746e-05, "loss": 0.9047172546386719, "step": 6820 }, { "epoch": 0.0405989383645107, "grad_norm": 2.1351044178009033, "learning_rate": 2.706162076481078e-05, "loss": 0.8959020614624024, "step": 6830 }, { "epoch": 0.040658380441179094, "grad_norm": 2.4725801944732666, "learning_rate": 2.7101248266296813e-05, "loss": 0.9228705406188965, "step": 6840 }, { "epoch": 0.04071782251784748, "grad_norm": 1.8903037309646606, "learning_rate": 2.7140875767782842e-05, "loss": 0.8593582153320313, "step": 6850 }, { "epoch": 0.040777264594515875, "grad_norm": 2.6583666801452637, "learning_rate": 2.7180503269268877e-05, "loss": 0.8269550323486328, "step": 6860 }, { "epoch": 0.04083670667118426, "grad_norm": 2.2481651306152344, "learning_rate": 2.7220130770754902e-05, "loss": 0.8501821517944336, "step": 6870 }, { "epoch": 0.040896148747852655, "grad_norm": 1.645256519317627, "learning_rate": 2.7259758272240937e-05, "loss": 0.8567663192749023, "step": 6880 }, { "epoch": 0.04095559082452105, "grad_norm": 2.382469892501831, "learning_rate": 2.7299385773726966e-05, "loss": 0.8543848037719727, "step": 6890 }, { "epoch": 0.041015032901189435, "grad_norm": 3.0283660888671875, "learning_rate": 2.7339013275212998e-05, "loss": 0.8262954711914062, "step": 6900 }, { "epoch": 0.04107447497785783, "grad_norm": 2.842172622680664, "learning_rate": 2.7378640776699033e-05, "loss": 0.8745876312255859, "step": 6910 }, { "epoch": 0.041133917054526216, "grad_norm": 2.4109604358673096, "learning_rate": 2.741826827818506e-05, "loss": 0.8487018585205078, "step": 6920 }, { "epoch": 0.04119335913119461, "grad_norm": 2.692497491836548, "learning_rate": 2.7457895779671093e-05, "loss": 0.9181900024414062, "step": 6930 }, { "epoch": 0.041252801207862996, "grad_norm": 2.0876429080963135, "learning_rate": 2.7497523281157122e-05, "loss": 0.8533716201782227, "step": 6940 }, { "epoch": 0.04131224328453139, "grad_norm": 2.706296920776367, "learning_rate": 2.7537150782643157e-05, "loss": 0.8708853721618652, "step": 6950 }, { "epoch": 0.04137168536119978, "grad_norm": 2.491074562072754, "learning_rate": 2.7576778284129186e-05, "loss": 0.8536435127258301, "step": 6960 }, { "epoch": 0.04143112743786817, "grad_norm": 2.5473010540008545, "learning_rate": 2.7616405785615218e-05, "loss": 0.9357307434082032, "step": 6970 }, { "epoch": 0.04149056951453656, "grad_norm": 3.1550705432891846, "learning_rate": 2.7656033287101253e-05, "loss": 0.8833330154418946, "step": 6980 }, { "epoch": 0.04155001159120495, "grad_norm": 2.6084892749786377, "learning_rate": 2.769566078858728e-05, "loss": 0.8856158256530762, "step": 6990 }, { "epoch": 0.04160945366787334, "grad_norm": 3.1801788806915283, "learning_rate": 2.7735288290073313e-05, "loss": 0.9022920608520508, "step": 7000 }, { "epoch": 0.04166889574454173, "grad_norm": 2.8862457275390625, "learning_rate": 2.777491579155934e-05, "loss": 0.8235340118408203, "step": 7010 }, { "epoch": 0.041728337821210125, "grad_norm": 2.4473347663879395, "learning_rate": 2.7814543293045377e-05, "loss": 0.8119122505187988, "step": 7020 }, { "epoch": 0.04178777989787851, "grad_norm": 2.4911601543426514, "learning_rate": 2.7854170794531402e-05, "loss": 0.7120901584625244, "step": 7030 }, { "epoch": 0.041847221974546905, "grad_norm": 2.299898862838745, "learning_rate": 2.7893798296017437e-05, "loss": 0.881137466430664, "step": 7040 }, { "epoch": 0.04190666405121529, "grad_norm": 2.759242534637451, "learning_rate": 2.793342579750347e-05, "loss": 0.8874788284301758, "step": 7050 }, { "epoch": 0.041966106127883686, "grad_norm": 2.4070708751678467, "learning_rate": 2.7973053298989498e-05, "loss": 0.8960918426513672, "step": 7060 }, { "epoch": 0.04202554820455207, "grad_norm": 2.2625255584716797, "learning_rate": 2.8012680800475533e-05, "loss": 0.847445011138916, "step": 7070 }, { "epoch": 0.042084990281220466, "grad_norm": 2.3954122066497803, "learning_rate": 2.805230830196156e-05, "loss": 0.859988021850586, "step": 7080 }, { "epoch": 0.04214443235788885, "grad_norm": 2.2268810272216797, "learning_rate": 2.8091935803447593e-05, "loss": 0.7559028625488281, "step": 7090 }, { "epoch": 0.04220387443455725, "grad_norm": 2.4307351112365723, "learning_rate": 2.813156330493363e-05, "loss": 0.8014708518981933, "step": 7100 }, { "epoch": 0.04226331651122563, "grad_norm": 2.2977869510650635, "learning_rate": 2.8171190806419657e-05, "loss": 0.8820513725280762, "step": 7110 }, { "epoch": 0.04232275858789403, "grad_norm": 2.7738723754882812, "learning_rate": 2.821081830790569e-05, "loss": 0.8650708198547363, "step": 7120 }, { "epoch": 0.042382200664562414, "grad_norm": 2.380762815475464, "learning_rate": 2.8250445809391717e-05, "loss": 0.836263370513916, "step": 7130 }, { "epoch": 0.04244164274123081, "grad_norm": 2.3765363693237305, "learning_rate": 2.8290073310877753e-05, "loss": 0.8465463638305664, "step": 7140 }, { "epoch": 0.0425010848178992, "grad_norm": 2.901519536972046, "learning_rate": 2.832970081236378e-05, "loss": 0.9207441329956054, "step": 7150 }, { "epoch": 0.04256052689456759, "grad_norm": 2.2890796661376953, "learning_rate": 2.8369328313849813e-05, "loss": 0.818946647644043, "step": 7160 }, { "epoch": 0.04261996897123598, "grad_norm": 2.1736199855804443, "learning_rate": 2.8408955815335848e-05, "loss": 0.9062065124511719, "step": 7170 }, { "epoch": 0.04267941104790437, "grad_norm": 2.582415819168091, "learning_rate": 2.8448583316821877e-05, "loss": 0.8037662506103516, "step": 7180 }, { "epoch": 0.04273885312457276, "grad_norm": 2.416703939437866, "learning_rate": 2.848821081830791e-05, "loss": 0.900633716583252, "step": 7190 }, { "epoch": 0.04279829520124115, "grad_norm": 1.8174948692321777, "learning_rate": 2.8527838319793937e-05, "loss": 0.8249164581298828, "step": 7200 }, { "epoch": 0.04285773727790954, "grad_norm": 2.363618850708008, "learning_rate": 2.856746582127997e-05, "loss": 0.8411616325378418, "step": 7210 }, { "epoch": 0.04291717935457793, "grad_norm": 2.381556510925293, "learning_rate": 2.8607093322765998e-05, "loss": 0.7797861099243164, "step": 7220 }, { "epoch": 0.04297662143124632, "grad_norm": 2.4790220260620117, "learning_rate": 2.8646720824252033e-05, "loss": 0.8480628967285156, "step": 7230 }, { "epoch": 0.04303606350791471, "grad_norm": 2.429152011871338, "learning_rate": 2.8686348325738065e-05, "loss": 0.8416999816894531, "step": 7240 }, { "epoch": 0.0430955055845831, "grad_norm": 2.006866693496704, "learning_rate": 2.8725975827224093e-05, "loss": 0.822285270690918, "step": 7250 }, { "epoch": 0.04315494766125149, "grad_norm": 3.1201260089874268, "learning_rate": 2.876560332871013e-05, "loss": 0.868037223815918, "step": 7260 }, { "epoch": 0.043214389737919884, "grad_norm": 3.3438823223114014, "learning_rate": 2.8805230830196157e-05, "loss": 0.8094942092895507, "step": 7270 }, { "epoch": 0.04327383181458828, "grad_norm": 2.255361557006836, "learning_rate": 2.884485833168219e-05, "loss": 0.8466083526611328, "step": 7280 }, { "epoch": 0.043333273891256664, "grad_norm": 2.2679827213287354, "learning_rate": 2.8884485833168217e-05, "loss": 0.9113251686096191, "step": 7290 }, { "epoch": 0.04339271596792506, "grad_norm": 1.9157863855361938, "learning_rate": 2.8924113334654253e-05, "loss": 0.827910327911377, "step": 7300 }, { "epoch": 0.043452158044593445, "grad_norm": 2.2366726398468018, "learning_rate": 2.8963740836140284e-05, "loss": 0.8795893669128418, "step": 7310 }, { "epoch": 0.04351160012126184, "grad_norm": 2.572432518005371, "learning_rate": 2.9003368337626313e-05, "loss": 0.838416576385498, "step": 7320 }, { "epoch": 0.043571042197930225, "grad_norm": 2.4587836265563965, "learning_rate": 2.9042995839112348e-05, "loss": 0.8375473022460938, "step": 7330 }, { "epoch": 0.04363048427459862, "grad_norm": 2.1537606716156006, "learning_rate": 2.9082623340598377e-05, "loss": 0.7467400550842285, "step": 7340 }, { "epoch": 0.043689926351267006, "grad_norm": 2.2333316802978516, "learning_rate": 2.912225084208441e-05, "loss": 0.9171389579772949, "step": 7350 }, { "epoch": 0.0437493684279354, "grad_norm": 2.355799913406372, "learning_rate": 2.9161878343570437e-05, "loss": 0.8257577896118165, "step": 7360 }, { "epoch": 0.043808810504603786, "grad_norm": 2.271091938018799, "learning_rate": 2.920150584505647e-05, "loss": 0.8195761680603028, "step": 7370 }, { "epoch": 0.04386825258127218, "grad_norm": 2.2398841381073, "learning_rate": 2.9241133346542504e-05, "loss": 0.8173789978027344, "step": 7380 }, { "epoch": 0.043927694657940566, "grad_norm": 2.340890407562256, "learning_rate": 2.9280760848028533e-05, "loss": 0.7977207660675049, "step": 7390 }, { "epoch": 0.04398713673460896, "grad_norm": 2.6581008434295654, "learning_rate": 2.9320388349514565e-05, "loss": 0.8216086387634277, "step": 7400 }, { "epoch": 0.044046578811277354, "grad_norm": 2.2298383712768555, "learning_rate": 2.9360015851000593e-05, "loss": 0.8540983200073242, "step": 7410 }, { "epoch": 0.04410602088794574, "grad_norm": 1.9755901098251343, "learning_rate": 2.939964335248663e-05, "loss": 0.8255231857299805, "step": 7420 }, { "epoch": 0.044165462964614134, "grad_norm": 2.6724090576171875, "learning_rate": 2.9439270853972657e-05, "loss": 0.8872657775878906, "step": 7430 }, { "epoch": 0.04422490504128252, "grad_norm": 2.2983994483947754, "learning_rate": 2.947889835545869e-05, "loss": 0.8241701126098633, "step": 7440 }, { "epoch": 0.044284347117950915, "grad_norm": 2.958468198776245, "learning_rate": 2.9518525856944724e-05, "loss": 0.8827537536621094, "step": 7450 }, { "epoch": 0.0443437891946193, "grad_norm": 2.188829183578491, "learning_rate": 2.9558153358430752e-05, "loss": 0.8283015251159668, "step": 7460 }, { "epoch": 0.044403231271287695, "grad_norm": 2.672907590866089, "learning_rate": 2.9597780859916784e-05, "loss": 0.8548653602600098, "step": 7470 }, { "epoch": 0.04446267334795608, "grad_norm": 2.445390224456787, "learning_rate": 2.9637408361402813e-05, "loss": 0.8153247833251953, "step": 7480 }, { "epoch": 0.044522115424624475, "grad_norm": 1.9737049341201782, "learning_rate": 2.9677035862888848e-05, "loss": 0.8029470443725586, "step": 7490 }, { "epoch": 0.04458155750129286, "grad_norm": 1.9906415939331055, "learning_rate": 2.9716663364374873e-05, "loss": 0.7985050201416015, "step": 7500 }, { "epoch": 0.044640999577961256, "grad_norm": 2.396765947341919, "learning_rate": 2.975629086586091e-05, "loss": 0.858734130859375, "step": 7510 }, { "epoch": 0.04470044165462965, "grad_norm": 2.554494857788086, "learning_rate": 2.9795918367346944e-05, "loss": 0.9438014984130859, "step": 7520 }, { "epoch": 0.044759883731298036, "grad_norm": 2.8463263511657715, "learning_rate": 2.983554586883297e-05, "loss": 0.8351326942443847, "step": 7530 }, { "epoch": 0.04481932580796643, "grad_norm": 2.494338274002075, "learning_rate": 2.9875173370319004e-05, "loss": 0.8910692214965821, "step": 7540 }, { "epoch": 0.04487876788463482, "grad_norm": 2.2952444553375244, "learning_rate": 2.9914800871805033e-05, "loss": 0.9128508567810059, "step": 7550 }, { "epoch": 0.04493820996130321, "grad_norm": 2.5112195014953613, "learning_rate": 2.9954428373291064e-05, "loss": 0.8244457244873047, "step": 7560 }, { "epoch": 0.0449976520379716, "grad_norm": 2.56756591796875, "learning_rate": 2.99940558747771e-05, "loss": 0.7431815147399903, "step": 7570 }, { "epoch": 0.04505709411463999, "grad_norm": 2.4342050552368164, "learning_rate": 3.0033683376263128e-05, "loss": 0.8477396011352539, "step": 7580 }, { "epoch": 0.04511653619130838, "grad_norm": 2.0966413021087646, "learning_rate": 3.007331087774916e-05, "loss": 0.8707691192626953, "step": 7590 }, { "epoch": 0.04517597826797677, "grad_norm": 2.2666592597961426, "learning_rate": 3.011293837923519e-05, "loss": 0.8578849792480469, "step": 7600 }, { "epoch": 0.04523542034464516, "grad_norm": 2.6428418159484863, "learning_rate": 3.0152565880721224e-05, "loss": 0.8733333587646485, "step": 7610 }, { "epoch": 0.04529486242131355, "grad_norm": 2.6627843379974365, "learning_rate": 3.0192193382207252e-05, "loss": 0.8247271537780761, "step": 7620 }, { "epoch": 0.04535430449798194, "grad_norm": 2.110978841781616, "learning_rate": 3.0231820883693284e-05, "loss": 0.7823429107666016, "step": 7630 }, { "epoch": 0.04541374657465033, "grad_norm": 2.03733229637146, "learning_rate": 3.027144838517932e-05, "loss": 0.8759113311767578, "step": 7640 }, { "epoch": 0.045473188651318726, "grad_norm": 2.0494747161865234, "learning_rate": 3.0311075886665348e-05, "loss": 0.8790026664733886, "step": 7650 }, { "epoch": 0.04553263072798711, "grad_norm": 2.349430799484253, "learning_rate": 3.035070338815138e-05, "loss": 0.9313935279846192, "step": 7660 }, { "epoch": 0.045592072804655506, "grad_norm": 2.4847354888916016, "learning_rate": 3.039033088963741e-05, "loss": 0.9138903617858887, "step": 7670 }, { "epoch": 0.04565151488132389, "grad_norm": 2.6202809810638428, "learning_rate": 3.0429958391123444e-05, "loss": 0.8974069595336914, "step": 7680 }, { "epoch": 0.04571095695799229, "grad_norm": 2.502565860748291, "learning_rate": 3.046958589260947e-05, "loss": 0.7886274337768555, "step": 7690 }, { "epoch": 0.04577039903466067, "grad_norm": 2.2646279335021973, "learning_rate": 3.0509213394095504e-05, "loss": 0.841916847229004, "step": 7700 }, { "epoch": 0.04582984111132907, "grad_norm": 2.8095004558563232, "learning_rate": 3.054884089558154e-05, "loss": 0.8235467910766602, "step": 7710 }, { "epoch": 0.045889283187997454, "grad_norm": 2.2068638801574707, "learning_rate": 3.0588468397067564e-05, "loss": 0.903449821472168, "step": 7720 }, { "epoch": 0.04594872526466585, "grad_norm": 2.687516212463379, "learning_rate": 3.0628095898553596e-05, "loss": 0.8179925918579102, "step": 7730 }, { "epoch": 0.046008167341334234, "grad_norm": 2.3034074306488037, "learning_rate": 3.066772340003963e-05, "loss": 0.8892745971679688, "step": 7740 }, { "epoch": 0.04606760941800263, "grad_norm": 2.4141805171966553, "learning_rate": 3.070735090152566e-05, "loss": 0.912289047241211, "step": 7750 }, { "epoch": 0.046127051494671015, "grad_norm": 2.1882035732269287, "learning_rate": 3.074697840301169e-05, "loss": 0.8460779190063477, "step": 7760 }, { "epoch": 0.04618649357133941, "grad_norm": 2.330009937286377, "learning_rate": 3.0786605904497724e-05, "loss": 0.7984859943389893, "step": 7770 }, { "epoch": 0.0462459356480078, "grad_norm": 2.163058042526245, "learning_rate": 3.0826233405983756e-05, "loss": 0.8404458045959473, "step": 7780 }, { "epoch": 0.04630537772467619, "grad_norm": 2.022968053817749, "learning_rate": 3.086586090746979e-05, "loss": 0.8514385223388672, "step": 7790 }, { "epoch": 0.04636481980134458, "grad_norm": 2.372804641723633, "learning_rate": 3.090548840895582e-05, "loss": 0.8373701095581054, "step": 7800 }, { "epoch": 0.04642426187801297, "grad_norm": 1.5946124792099, "learning_rate": 3.0945115910441844e-05, "loss": 0.8187052726745605, "step": 7810 }, { "epoch": 0.04648370395468136, "grad_norm": 1.6850001811981201, "learning_rate": 3.098474341192788e-05, "loss": 0.8559708595275879, "step": 7820 }, { "epoch": 0.04654314603134975, "grad_norm": 3.168462038040161, "learning_rate": 3.102437091341391e-05, "loss": 0.8251455307006836, "step": 7830 }, { "epoch": 0.04660258810801814, "grad_norm": 1.8630527257919312, "learning_rate": 3.106399841489994e-05, "loss": 0.8648454666137695, "step": 7840 }, { "epoch": 0.04666203018468653, "grad_norm": 2.2593955993652344, "learning_rate": 3.110362591638598e-05, "loss": 0.8409863471984863, "step": 7850 }, { "epoch": 0.046721472261354924, "grad_norm": 2.3776419162750244, "learning_rate": 3.1143253417872004e-05, "loss": 0.8108213424682618, "step": 7860 }, { "epoch": 0.04678091433802331, "grad_norm": 1.9842902421951294, "learning_rate": 3.1182880919358036e-05, "loss": 0.8627094268798828, "step": 7870 }, { "epoch": 0.046840356414691704, "grad_norm": 2.4831104278564453, "learning_rate": 3.122250842084407e-05, "loss": 0.850309181213379, "step": 7880 }, { "epoch": 0.04689979849136009, "grad_norm": 2.8117740154266357, "learning_rate": 3.12621359223301e-05, "loss": 0.8460719108581543, "step": 7890 }, { "epoch": 0.046959240568028485, "grad_norm": 2.9206619262695312, "learning_rate": 3.1301763423816125e-05, "loss": 0.9401147842407227, "step": 7900 }, { "epoch": 0.04701868264469688, "grad_norm": 2.175710439682007, "learning_rate": 3.134139092530216e-05, "loss": 0.8622190475463867, "step": 7910 }, { "epoch": 0.047078124721365265, "grad_norm": 2.165743589401245, "learning_rate": 3.1381018426788195e-05, "loss": 0.8256694793701171, "step": 7920 }, { "epoch": 0.04713756679803366, "grad_norm": 2.582792043685913, "learning_rate": 3.142064592827422e-05, "loss": 0.8234624862670898, "step": 7930 }, { "epoch": 0.047197008874702046, "grad_norm": 1.7321507930755615, "learning_rate": 3.146027342976026e-05, "loss": 0.83597412109375, "step": 7940 }, { "epoch": 0.04725645095137044, "grad_norm": 1.8613771200180054, "learning_rate": 3.1499900931246284e-05, "loss": 0.8113222122192383, "step": 7950 }, { "epoch": 0.047315893028038826, "grad_norm": 2.5226283073425293, "learning_rate": 3.1539528432732316e-05, "loss": 0.8504307746887207, "step": 7960 }, { "epoch": 0.04737533510470722, "grad_norm": 2.2059414386749268, "learning_rate": 3.157915593421835e-05, "loss": 0.8643497467041016, "step": 7970 }, { "epoch": 0.047434777181375606, "grad_norm": 2.2192485332489014, "learning_rate": 3.161878343570438e-05, "loss": 0.8096782684326171, "step": 7980 }, { "epoch": 0.047494219258044, "grad_norm": 2.6256072521209717, "learning_rate": 3.165841093719041e-05, "loss": 0.8288504600524902, "step": 7990 }, { "epoch": 0.04755366133471239, "grad_norm": 2.0612194538116455, "learning_rate": 3.169803843867644e-05, "loss": 0.8374496459960937, "step": 8000 }, { "epoch": 0.04761310341138078, "grad_norm": 2.3568217754364014, "learning_rate": 3.1737665940162475e-05, "loss": 0.8560046195983887, "step": 8010 }, { "epoch": 0.04767254548804917, "grad_norm": 2.167827606201172, "learning_rate": 3.17772934416485e-05, "loss": 0.7839701652526856, "step": 8020 }, { "epoch": 0.04773198756471756, "grad_norm": 2.9503023624420166, "learning_rate": 3.181692094313454e-05, "loss": 0.7937836647033691, "step": 8030 }, { "epoch": 0.047791429641385955, "grad_norm": 2.3959801197052, "learning_rate": 3.185654844462057e-05, "loss": 0.803561019897461, "step": 8040 }, { "epoch": 0.04785087171805434, "grad_norm": 2.5037055015563965, "learning_rate": 3.1896175946106596e-05, "loss": 0.8909032821655274, "step": 8050 }, { "epoch": 0.047910313794722735, "grad_norm": 2.462777853012085, "learning_rate": 3.1935803447592635e-05, "loss": 0.8442728996276856, "step": 8060 }, { "epoch": 0.04796975587139112, "grad_norm": 2.309532880783081, "learning_rate": 3.197543094907866e-05, "loss": 0.8231357574462891, "step": 8070 }, { "epoch": 0.048029197948059515, "grad_norm": 2.0208072662353516, "learning_rate": 3.201505845056469e-05, "loss": 0.8250961303710938, "step": 8080 }, { "epoch": 0.0480886400247279, "grad_norm": 2.576625108718872, "learning_rate": 3.2054685952050723e-05, "loss": 0.850190544128418, "step": 8090 }, { "epoch": 0.048148082101396296, "grad_norm": 2.2382824420928955, "learning_rate": 3.2094313453536755e-05, "loss": 0.845743465423584, "step": 8100 }, { "epoch": 0.04820752417806468, "grad_norm": 2.3495852947235107, "learning_rate": 3.213394095502279e-05, "loss": 0.8400651931762695, "step": 8110 }, { "epoch": 0.048266966254733076, "grad_norm": 2.514516830444336, "learning_rate": 3.217356845650882e-05, "loss": 0.8924468994140625, "step": 8120 }, { "epoch": 0.04832640833140146, "grad_norm": 2.3678860664367676, "learning_rate": 3.221319595799485e-05, "loss": 0.8803386688232422, "step": 8130 }, { "epoch": 0.04838585040806986, "grad_norm": 2.467193603515625, "learning_rate": 3.225282345948088e-05, "loss": 0.8299662590026855, "step": 8140 }, { "epoch": 0.048445292484738244, "grad_norm": 2.6843199729919434, "learning_rate": 3.2292450960966915e-05, "loss": 0.8722331047058105, "step": 8150 }, { "epoch": 0.04850473456140664, "grad_norm": 2.434828758239746, "learning_rate": 3.233207846245294e-05, "loss": 0.8165388107299805, "step": 8160 }, { "epoch": 0.04856417663807503, "grad_norm": 2.4789552688598633, "learning_rate": 3.237170596393898e-05, "loss": 0.8528359413146973, "step": 8170 }, { "epoch": 0.04862361871474342, "grad_norm": 2.217005491256714, "learning_rate": 3.241133346542501e-05, "loss": 0.8845063209533691, "step": 8180 }, { "epoch": 0.04868306079141181, "grad_norm": 2.54945969581604, "learning_rate": 3.2450960966911035e-05, "loss": 0.7936611175537109, "step": 8190 }, { "epoch": 0.0487425028680802, "grad_norm": 2.0664069652557373, "learning_rate": 3.249058846839707e-05, "loss": 0.8577552795410156, "step": 8200 }, { "epoch": 0.04880194494474859, "grad_norm": 2.154677629470825, "learning_rate": 3.25302159698831e-05, "loss": 0.8027254104614258, "step": 8210 }, { "epoch": 0.04886138702141698, "grad_norm": 2.3434269428253174, "learning_rate": 3.256984347136913e-05, "loss": 0.8345741271972656, "step": 8220 }, { "epoch": 0.04892082909808537, "grad_norm": 2.199082851409912, "learning_rate": 3.260947097285516e-05, "loss": 0.7962605476379394, "step": 8230 }, { "epoch": 0.04898027117475376, "grad_norm": 2.1870615482330322, "learning_rate": 3.2649098474341195e-05, "loss": 0.8035263061523438, "step": 8240 }, { "epoch": 0.04903971325142215, "grad_norm": 2.065504789352417, "learning_rate": 3.268872597582723e-05, "loss": 0.7896615982055664, "step": 8250 }, { "epoch": 0.04909915532809054, "grad_norm": 2.5236241817474365, "learning_rate": 3.272835347731326e-05, "loss": 0.7974404335021973, "step": 8260 }, { "epoch": 0.04915859740475893, "grad_norm": 2.3556902408599854, "learning_rate": 3.276798097879929e-05, "loss": 0.818639087677002, "step": 8270 }, { "epoch": 0.04921803948142732, "grad_norm": 2.417612075805664, "learning_rate": 3.2807608480285316e-05, "loss": 0.8579410552978516, "step": 8280 }, { "epoch": 0.04927748155809571, "grad_norm": 2.460688352584839, "learning_rate": 3.2847235981771354e-05, "loss": 0.7888341903686523, "step": 8290 }, { "epoch": 0.04933692363476411, "grad_norm": 2.3304080963134766, "learning_rate": 3.288686348325738e-05, "loss": 0.8892608642578125, "step": 8300 }, { "epoch": 0.049396365711432494, "grad_norm": 2.5048227310180664, "learning_rate": 3.292649098474341e-05, "loss": 0.7731578350067139, "step": 8310 }, { "epoch": 0.04945580778810089, "grad_norm": 1.9801480770111084, "learning_rate": 3.296611848622945e-05, "loss": 0.8052642822265625, "step": 8320 }, { "epoch": 0.049515249864769274, "grad_norm": 3.070676803588867, "learning_rate": 3.3005745987715475e-05, "loss": 0.8305624961853028, "step": 8330 }, { "epoch": 0.04957469194143767, "grad_norm": 2.1503701210021973, "learning_rate": 3.304537348920151e-05, "loss": 0.8821045875549316, "step": 8340 }, { "epoch": 0.049634134018106055, "grad_norm": 2.7638802528381348, "learning_rate": 3.308500099068754e-05, "loss": 0.8060686111450195, "step": 8350 }, { "epoch": 0.04969357609477445, "grad_norm": 2.0857317447662354, "learning_rate": 3.312462849217357e-05, "loss": 0.788905143737793, "step": 8360 }, { "epoch": 0.049753018171442835, "grad_norm": 2.311312675476074, "learning_rate": 3.3164255993659596e-05, "loss": 0.8670324325561524, "step": 8370 }, { "epoch": 0.04981246024811123, "grad_norm": 2.286269426345825, "learning_rate": 3.3203883495145634e-05, "loss": 0.8057217597961426, "step": 8380 }, { "epoch": 0.049871902324779616, "grad_norm": 2.8104066848754883, "learning_rate": 3.3243510996631666e-05, "loss": 0.7989500999450684, "step": 8390 }, { "epoch": 0.04993134440144801, "grad_norm": 2.100839138031006, "learning_rate": 3.328313849811769e-05, "loss": 0.8472771644592285, "step": 8400 }, { "epoch": 0.049990786478116396, "grad_norm": 2.30839204788208, "learning_rate": 3.332276599960373e-05, "loss": 0.7975100517272949, "step": 8410 }, { "epoch": 0.05005022855478479, "grad_norm": 2.032046318054199, "learning_rate": 3.3362393501089755e-05, "loss": 0.8432445526123047, "step": 8420 }, { "epoch": 0.05010967063145318, "grad_norm": 1.9886795282363892, "learning_rate": 3.340202100257579e-05, "loss": 0.7663759708404541, "step": 8430 }, { "epoch": 0.05016911270812157, "grad_norm": 2.6227118968963623, "learning_rate": 3.3441648504061826e-05, "loss": 0.9256757736206055, "step": 8440 }, { "epoch": 0.050228554784789964, "grad_norm": 2.1574134826660156, "learning_rate": 3.348127600554785e-05, "loss": 0.8036592483520508, "step": 8450 }, { "epoch": 0.05028799686145835, "grad_norm": 2.2821109294891357, "learning_rate": 3.352090350703388e-05, "loss": 0.754214859008789, "step": 8460 }, { "epoch": 0.050347438938126744, "grad_norm": 2.3952901363372803, "learning_rate": 3.3560531008519915e-05, "loss": 0.8060170173645019, "step": 8470 }, { "epoch": 0.05040688101479513, "grad_norm": 2.7743890285491943, "learning_rate": 3.3600158510005946e-05, "loss": 0.8687347412109375, "step": 8480 }, { "epoch": 0.050466323091463525, "grad_norm": 1.6771502494812012, "learning_rate": 3.363978601149198e-05, "loss": 0.8132439613342285, "step": 8490 }, { "epoch": 0.05052576516813191, "grad_norm": 2.4702398777008057, "learning_rate": 3.367941351297801e-05, "loss": 0.8363434791564941, "step": 8500 }, { "epoch": 0.050585207244800305, "grad_norm": 2.0867931842803955, "learning_rate": 3.371904101446404e-05, "loss": 0.8459024429321289, "step": 8510 }, { "epoch": 0.05064464932146869, "grad_norm": 2.0297482013702393, "learning_rate": 3.375866851595007e-05, "loss": 0.8247262954711914, "step": 8520 }, { "epoch": 0.050704091398137086, "grad_norm": 2.2150349617004395, "learning_rate": 3.3798296017436106e-05, "loss": 0.7894363403320312, "step": 8530 }, { "epoch": 0.05076353347480548, "grad_norm": 2.295748710632324, "learning_rate": 3.383792351892213e-05, "loss": 0.7986562252044678, "step": 8540 }, { "epoch": 0.050822975551473866, "grad_norm": 2.173401117324829, "learning_rate": 3.387755102040816e-05, "loss": 0.8795857429504395, "step": 8550 }, { "epoch": 0.05088241762814226, "grad_norm": 2.3461711406707764, "learning_rate": 3.3917178521894195e-05, "loss": 0.8286123275756836, "step": 8560 }, { "epoch": 0.050941859704810646, "grad_norm": 2.129833221435547, "learning_rate": 3.3956806023380227e-05, "loss": 0.8471275329589844, "step": 8570 }, { "epoch": 0.05100130178147904, "grad_norm": 1.8018525838851929, "learning_rate": 3.399643352486626e-05, "loss": 0.7490943908691406, "step": 8580 }, { "epoch": 0.05106074385814743, "grad_norm": 2.589627504348755, "learning_rate": 3.403606102635229e-05, "loss": 0.7968174934387207, "step": 8590 }, { "epoch": 0.05112018593481582, "grad_norm": 2.253772735595703, "learning_rate": 3.407568852783832e-05, "loss": 0.8254171371459961, "step": 8600 }, { "epoch": 0.05117962801148421, "grad_norm": 1.8131986856460571, "learning_rate": 3.4115316029324354e-05, "loss": 0.7884232521057128, "step": 8610 }, { "epoch": 0.0512390700881526, "grad_norm": 1.9568270444869995, "learning_rate": 3.4154943530810386e-05, "loss": 0.8176311492919922, "step": 8620 }, { "epoch": 0.05129851216482099, "grad_norm": 2.262089252471924, "learning_rate": 3.419457103229641e-05, "loss": 0.8104110717773437, "step": 8630 }, { "epoch": 0.05135795424148938, "grad_norm": 2.208216905593872, "learning_rate": 3.423419853378245e-05, "loss": 0.7790939331054687, "step": 8640 }, { "epoch": 0.05141739631815777, "grad_norm": 2.09516978263855, "learning_rate": 3.427382603526848e-05, "loss": 0.8266637802124024, "step": 8650 }, { "epoch": 0.05147683839482616, "grad_norm": 2.1639773845672607, "learning_rate": 3.431345353675451e-05, "loss": 0.8309232711791992, "step": 8660 }, { "epoch": 0.051536280471494555, "grad_norm": 2.0470640659332275, "learning_rate": 3.4353081038240545e-05, "loss": 0.7920202255249024, "step": 8670 }, { "epoch": 0.05159572254816294, "grad_norm": 2.0151431560516357, "learning_rate": 3.439270853972657e-05, "loss": 0.894329833984375, "step": 8680 }, { "epoch": 0.051655164624831336, "grad_norm": 1.9124245643615723, "learning_rate": 3.44323360412126e-05, "loss": 0.8285940170288086, "step": 8690 }, { "epoch": 0.05171460670149972, "grad_norm": 2.131251811981201, "learning_rate": 3.4471963542698634e-05, "loss": 0.8022396087646484, "step": 8700 }, { "epoch": 0.051774048778168116, "grad_norm": 2.2455224990844727, "learning_rate": 3.4511591044184666e-05, "loss": 0.765594482421875, "step": 8710 }, { "epoch": 0.0518334908548365, "grad_norm": 1.9210455417633057, "learning_rate": 3.45512185456707e-05, "loss": 0.8162729263305664, "step": 8720 }, { "epoch": 0.0518929329315049, "grad_norm": 2.6809704303741455, "learning_rate": 3.459084604715673e-05, "loss": 0.8127819061279297, "step": 8730 }, { "epoch": 0.051952375008173284, "grad_norm": 2.245365619659424, "learning_rate": 3.463047354864276e-05, "loss": 0.7805811405181885, "step": 8740 }, { "epoch": 0.05201181708484168, "grad_norm": 2.118856191635132, "learning_rate": 3.467010105012879e-05, "loss": 0.8214988708496094, "step": 8750 }, { "epoch": 0.052071259161510064, "grad_norm": 2.7243080139160156, "learning_rate": 3.4709728551614825e-05, "loss": 0.7958688259124755, "step": 8760 }, { "epoch": 0.05213070123817846, "grad_norm": 1.5810284614562988, "learning_rate": 3.474935605310085e-05, "loss": 0.8121060371398926, "step": 8770 }, { "epoch": 0.052190143314846844, "grad_norm": 2.19279146194458, "learning_rate": 3.478898355458688e-05, "loss": 0.8920408248901367, "step": 8780 }, { "epoch": 0.05224958539151524, "grad_norm": 1.858223795890808, "learning_rate": 3.482861105607292e-05, "loss": 0.8672460556030274, "step": 8790 }, { "epoch": 0.05230902746818363, "grad_norm": 2.31296706199646, "learning_rate": 3.4868238557558946e-05, "loss": 0.8197626113891602, "step": 8800 }, { "epoch": 0.05236846954485202, "grad_norm": 2.1339707374572754, "learning_rate": 3.490786605904498e-05, "loss": 0.808871841430664, "step": 8810 }, { "epoch": 0.05242791162152041, "grad_norm": 1.978423833847046, "learning_rate": 3.494749356053101e-05, "loss": 0.8010960578918457, "step": 8820 }, { "epoch": 0.0524873536981888, "grad_norm": 1.872570276260376, "learning_rate": 3.498712106201704e-05, "loss": 0.7674485206604004, "step": 8830 }, { "epoch": 0.05254679577485719, "grad_norm": 1.778077244758606, "learning_rate": 3.502674856350307e-05, "loss": 0.8765375137329101, "step": 8840 }, { "epoch": 0.05260623785152558, "grad_norm": 1.9402872323989868, "learning_rate": 3.5066376064989106e-05, "loss": 0.8272735595703125, "step": 8850 }, { "epoch": 0.05266567992819397, "grad_norm": 2.4782583713531494, "learning_rate": 3.510600356647514e-05, "loss": 0.7597359657287598, "step": 8860 }, { "epoch": 0.05272512200486236, "grad_norm": 2.2332634925842285, "learning_rate": 3.514563106796116e-05, "loss": 0.8015815734863281, "step": 8870 }, { "epoch": 0.05278456408153075, "grad_norm": 3.1229445934295654, "learning_rate": 3.51852585694472e-05, "loss": 0.755367660522461, "step": 8880 }, { "epoch": 0.05284400615819914, "grad_norm": 2.4211859703063965, "learning_rate": 3.5224886070933226e-05, "loss": 0.835692024230957, "step": 8890 }, { "epoch": 0.052903448234867534, "grad_norm": 3.3085362911224365, "learning_rate": 3.526451357241926e-05, "loss": 0.8290204048156739, "step": 8900 }, { "epoch": 0.05296289031153592, "grad_norm": 2.2306365966796875, "learning_rate": 3.53041410739053e-05, "loss": 0.7882390022277832, "step": 8910 }, { "epoch": 0.053022332388204314, "grad_norm": 2.1512510776519775, "learning_rate": 3.534376857539132e-05, "loss": 0.8406828880310059, "step": 8920 }, { "epoch": 0.05308177446487271, "grad_norm": 2.164964199066162, "learning_rate": 3.5383396076877354e-05, "loss": 0.830943489074707, "step": 8930 }, { "epoch": 0.053141216541541095, "grad_norm": 2.2011091709136963, "learning_rate": 3.5423023578363386e-05, "loss": 0.8813798904418946, "step": 8940 }, { "epoch": 0.05320065861820949, "grad_norm": 2.288215398788452, "learning_rate": 3.546265107984942e-05, "loss": 0.8091482162475586, "step": 8950 }, { "epoch": 0.053260100694877875, "grad_norm": 2.3592307567596436, "learning_rate": 3.550227858133545e-05, "loss": 0.8272436141967774, "step": 8960 }, { "epoch": 0.05331954277154627, "grad_norm": 1.9415868520736694, "learning_rate": 3.554190608282148e-05, "loss": 0.8488582611083985, "step": 8970 }, { "epoch": 0.053378984848214656, "grad_norm": 1.8592984676361084, "learning_rate": 3.558153358430751e-05, "loss": 0.7783755779266357, "step": 8980 }, { "epoch": 0.05343842692488305, "grad_norm": 2.5238213539123535, "learning_rate": 3.5621161085793545e-05, "loss": 0.7970305919647217, "step": 8990 }, { "epoch": 0.053497869001551436, "grad_norm": 1.5856863260269165, "learning_rate": 3.566078858727958e-05, "loss": 0.8045047760009766, "step": 9000 }, { "epoch": 0.05355731107821983, "grad_norm": 2.2180581092834473, "learning_rate": 3.57004160887656e-05, "loss": 0.8367576599121094, "step": 9010 }, { "epoch": 0.053616753154888216, "grad_norm": 2.190129518508911, "learning_rate": 3.5740043590251634e-05, "loss": 0.7990867137908936, "step": 9020 }, { "epoch": 0.05367619523155661, "grad_norm": 2.014354944229126, "learning_rate": 3.5779671091737666e-05, "loss": 0.7720830917358399, "step": 9030 }, { "epoch": 0.053735637308225, "grad_norm": 3.2216057777404785, "learning_rate": 3.58192985932237e-05, "loss": 0.808527946472168, "step": 9040 }, { "epoch": 0.05379507938489339, "grad_norm": 1.9456850290298462, "learning_rate": 3.585892609470973e-05, "loss": 0.7960816383361816, "step": 9050 }, { "epoch": 0.053854521461561784, "grad_norm": 2.1343190670013428, "learning_rate": 3.589855359619576e-05, "loss": 0.7426846027374268, "step": 9060 }, { "epoch": 0.05391396353823017, "grad_norm": 2.020512580871582, "learning_rate": 3.593818109768179e-05, "loss": 0.7814121246337891, "step": 9070 }, { "epoch": 0.053973405614898565, "grad_norm": 2.639756917953491, "learning_rate": 3.5977808599167825e-05, "loss": 0.8086147308349609, "step": 9080 }, { "epoch": 0.05403284769156695, "grad_norm": 1.90325129032135, "learning_rate": 3.601743610065386e-05, "loss": 0.795461893081665, "step": 9090 }, { "epoch": 0.054092289768235345, "grad_norm": 2.445897340774536, "learning_rate": 3.605706360213988e-05, "loss": 0.8592632293701172, "step": 9100 }, { "epoch": 0.05415173184490373, "grad_norm": 1.892653226852417, "learning_rate": 3.609669110362592e-05, "loss": 0.7746563911437988, "step": 9110 }, { "epoch": 0.054211173921572126, "grad_norm": 1.7882938385009766, "learning_rate": 3.613631860511195e-05, "loss": 0.7939251899719239, "step": 9120 }, { "epoch": 0.05427061599824051, "grad_norm": 2.538271903991699, "learning_rate": 3.617594610659798e-05, "loss": 0.8137212753295898, "step": 9130 }, { "epoch": 0.054330058074908906, "grad_norm": 2.6321072578430176, "learning_rate": 3.6215573608084016e-05, "loss": 0.7732799530029297, "step": 9140 }, { "epoch": 0.05438950015157729, "grad_norm": 1.9167027473449707, "learning_rate": 3.625520110957004e-05, "loss": 0.7773810386657715, "step": 9150 }, { "epoch": 0.054448942228245686, "grad_norm": 2.0798404216766357, "learning_rate": 3.6294828611056073e-05, "loss": 0.8509928703308105, "step": 9160 }, { "epoch": 0.05450838430491407, "grad_norm": 2.23801589012146, "learning_rate": 3.6334456112542105e-05, "loss": 0.7488588333129883, "step": 9170 }, { "epoch": 0.05456782638158247, "grad_norm": 2.184680461883545, "learning_rate": 3.637408361402814e-05, "loss": 0.8007472038269043, "step": 9180 }, { "epoch": 0.05462726845825086, "grad_norm": 2.2238881587982178, "learning_rate": 3.641371111551417e-05, "loss": 0.7927509307861328, "step": 9190 }, { "epoch": 0.05468671053491925, "grad_norm": 1.8585526943206787, "learning_rate": 3.64533386170002e-05, "loss": 0.7918123245239258, "step": 9200 }, { "epoch": 0.05474615261158764, "grad_norm": 1.9443362951278687, "learning_rate": 3.649296611848623e-05, "loss": 0.6947365760803222, "step": 9210 }, { "epoch": 0.05480559468825603, "grad_norm": 1.971941590309143, "learning_rate": 3.653259361997226e-05, "loss": 0.7544161319732666, "step": 9220 }, { "epoch": 0.05486503676492442, "grad_norm": 2.0358612537384033, "learning_rate": 3.65722211214583e-05, "loss": 0.8597997665405274, "step": 9230 }, { "epoch": 0.05492447884159281, "grad_norm": 2.5307581424713135, "learning_rate": 3.661184862294432e-05, "loss": 0.82723388671875, "step": 9240 }, { "epoch": 0.0549839209182612, "grad_norm": 2.7395174503326416, "learning_rate": 3.6651476124430354e-05, "loss": 0.8034393310546875, "step": 9250 }, { "epoch": 0.05504336299492959, "grad_norm": 2.035911798477173, "learning_rate": 3.669110362591639e-05, "loss": 0.8294706344604492, "step": 9260 }, { "epoch": 0.05510280507159798, "grad_norm": 2.0401127338409424, "learning_rate": 3.673073112740242e-05, "loss": 0.7972446918487549, "step": 9270 }, { "epoch": 0.05516224714826637, "grad_norm": 2.19640851020813, "learning_rate": 3.677035862888845e-05, "loss": 0.792475414276123, "step": 9280 }, { "epoch": 0.05522168922493476, "grad_norm": 2.490128993988037, "learning_rate": 3.680998613037448e-05, "loss": 0.7946589469909668, "step": 9290 }, { "epoch": 0.05528113130160315, "grad_norm": 2.230046272277832, "learning_rate": 3.684961363186051e-05, "loss": 0.8057407379150391, "step": 9300 }, { "epoch": 0.05534057337827154, "grad_norm": 2.736154556274414, "learning_rate": 3.6889241133346545e-05, "loss": 0.7634969234466553, "step": 9310 }, { "epoch": 0.05540001545493994, "grad_norm": 2.300002098083496, "learning_rate": 3.692886863483258e-05, "loss": 0.7639658451080322, "step": 9320 }, { "epoch": 0.055459457531608324, "grad_norm": 2.2411715984344482, "learning_rate": 3.696849613631861e-05, "loss": 0.752061128616333, "step": 9330 }, { "epoch": 0.05551889960827672, "grad_norm": 1.90608549118042, "learning_rate": 3.7008123637804634e-05, "loss": 0.787424373626709, "step": 9340 }, { "epoch": 0.055578341684945104, "grad_norm": 1.7522066831588745, "learning_rate": 3.704775113929067e-05, "loss": 0.7930339813232422, "step": 9350 }, { "epoch": 0.0556377837616135, "grad_norm": 1.9154884815216064, "learning_rate": 3.70873786407767e-05, "loss": 0.8608761787414551, "step": 9360 }, { "epoch": 0.055697225838281884, "grad_norm": 1.9330869913101196, "learning_rate": 3.712700614226273e-05, "loss": 0.7960577964782715, "step": 9370 }, { "epoch": 0.05575666791495028, "grad_norm": 1.8452030420303345, "learning_rate": 3.716663364374877e-05, "loss": 0.7960087776184082, "step": 9380 }, { "epoch": 0.055816109991618665, "grad_norm": 1.7990975379943848, "learning_rate": 3.720626114523479e-05, "loss": 0.8253472328186036, "step": 9390 }, { "epoch": 0.05587555206828706, "grad_norm": 2.191464424133301, "learning_rate": 3.7245888646720825e-05, "loss": 0.8223559379577636, "step": 9400 }, { "epoch": 0.055934994144955445, "grad_norm": 2.0980494022369385, "learning_rate": 3.728551614820686e-05, "loss": 0.8030781745910645, "step": 9410 }, { "epoch": 0.05599443622162384, "grad_norm": 1.963430643081665, "learning_rate": 3.732514364969289e-05, "loss": 0.8140099525451661, "step": 9420 }, { "epoch": 0.056053878298292226, "grad_norm": 1.7564350366592407, "learning_rate": 3.736477115117892e-05, "loss": 0.7930108070373535, "step": 9430 }, { "epoch": 0.05611332037496062, "grad_norm": 2.0897934436798096, "learning_rate": 3.740439865266495e-05, "loss": 0.7948759078979493, "step": 9440 }, { "epoch": 0.05617276245162901, "grad_norm": 1.8900041580200195, "learning_rate": 3.7444026154150984e-05, "loss": 0.8222232818603515, "step": 9450 }, { "epoch": 0.0562322045282974, "grad_norm": 2.139652967453003, "learning_rate": 3.7483653655637016e-05, "loss": 0.8154020309448242, "step": 9460 }, { "epoch": 0.056291646604965793, "grad_norm": 2.5679636001586914, "learning_rate": 3.752328115712305e-05, "loss": 0.7902478218078614, "step": 9470 }, { "epoch": 0.05635108868163418, "grad_norm": 2.4179773330688477, "learning_rate": 3.756290865860907e-05, "loss": 0.7768736839294433, "step": 9480 }, { "epoch": 0.056410530758302574, "grad_norm": 1.8027682304382324, "learning_rate": 3.760253616009511e-05, "loss": 0.8117448806762695, "step": 9490 }, { "epoch": 0.05646997283497096, "grad_norm": 1.892169713973999, "learning_rate": 3.764216366158114e-05, "loss": 0.7667028427124023, "step": 9500 }, { "epoch": 0.056529414911639354, "grad_norm": 2.0028653144836426, "learning_rate": 3.768179116306717e-05, "loss": 0.7692992210388183, "step": 9510 }, { "epoch": 0.05658885698830774, "grad_norm": 2.151376247406006, "learning_rate": 3.772141866455321e-05, "loss": 0.803765869140625, "step": 9520 }, { "epoch": 0.056648299064976135, "grad_norm": 2.454162120819092, "learning_rate": 3.776104616603923e-05, "loss": 0.8305131912231445, "step": 9530 }, { "epoch": 0.05670774114164452, "grad_norm": 2.1603121757507324, "learning_rate": 3.7800673667525265e-05, "loss": 0.8166924476623535, "step": 9540 }, { "epoch": 0.056767183218312915, "grad_norm": 2.4636476039886475, "learning_rate": 3.7840301169011296e-05, "loss": 0.8275274276733399, "step": 9550 }, { "epoch": 0.05682662529498131, "grad_norm": 2.4002978801727295, "learning_rate": 3.787992867049733e-05, "loss": 0.8505912780761719, "step": 9560 }, { "epoch": 0.056886067371649696, "grad_norm": 2.432659149169922, "learning_rate": 3.791955617198335e-05, "loss": 0.7953312873840332, "step": 9570 }, { "epoch": 0.05694550944831809, "grad_norm": 3.085247755050659, "learning_rate": 3.795918367346939e-05, "loss": 0.7908003807067872, "step": 9580 }, { "epoch": 0.057004951524986476, "grad_norm": 2.255117177963257, "learning_rate": 3.7998811174955424e-05, "loss": 0.7627317428588867, "step": 9590 }, { "epoch": 0.05706439360165487, "grad_norm": 1.8368648290634155, "learning_rate": 3.803843867644145e-05, "loss": 0.8666852951049805, "step": 9600 }, { "epoch": 0.057123835678323256, "grad_norm": 2.766737461090088, "learning_rate": 3.807806617792749e-05, "loss": 0.7734378814697266, "step": 9610 }, { "epoch": 0.05718327775499165, "grad_norm": 1.659193515777588, "learning_rate": 3.811769367941351e-05, "loss": 0.8126800537109375, "step": 9620 }, { "epoch": 0.05724271983166004, "grad_norm": 2.1059510707855225, "learning_rate": 3.8157321180899545e-05, "loss": 0.8048717498779296, "step": 9630 }, { "epoch": 0.05730216190832843, "grad_norm": 1.9174211025238037, "learning_rate": 3.8196948682385577e-05, "loss": 0.7775933265686035, "step": 9640 }, { "epoch": 0.05736160398499682, "grad_norm": 1.9537209272384644, "learning_rate": 3.823657618387161e-05, "loss": 0.8663790702819825, "step": 9650 }, { "epoch": 0.05742104606166521, "grad_norm": 2.2500128746032715, "learning_rate": 3.827620368535764e-05, "loss": 0.7342833518981934, "step": 9660 }, { "epoch": 0.0574804881383336, "grad_norm": 1.8875188827514648, "learning_rate": 3.831583118684367e-05, "loss": 0.7822003364562988, "step": 9670 }, { "epoch": 0.05753993021500199, "grad_norm": 2.145298957824707, "learning_rate": 3.8355458688329704e-05, "loss": 0.8414735794067383, "step": 9680 }, { "epoch": 0.057599372291670385, "grad_norm": 1.88186776638031, "learning_rate": 3.839508618981573e-05, "loss": 0.8021456718444824, "step": 9690 }, { "epoch": 0.05765881436833877, "grad_norm": 2.410574197769165, "learning_rate": 3.843471369130177e-05, "loss": 0.7743597030639648, "step": 9700 }, { "epoch": 0.057718256445007166, "grad_norm": 2.5423965454101562, "learning_rate": 3.847434119278779e-05, "loss": 0.7970564842224122, "step": 9710 }, { "epoch": 0.05777769852167555, "grad_norm": 2.31833815574646, "learning_rate": 3.8513968694273825e-05, "loss": 0.7566370487213134, "step": 9720 }, { "epoch": 0.057837140598343946, "grad_norm": 2.1191511154174805, "learning_rate": 3.8553596195759863e-05, "loss": 0.8137832641601562, "step": 9730 }, { "epoch": 0.05789658267501233, "grad_norm": 2.4858386516571045, "learning_rate": 3.859322369724589e-05, "loss": 0.8171991348266602, "step": 9740 }, { "epoch": 0.057956024751680726, "grad_norm": 2.1249735355377197, "learning_rate": 3.863285119873192e-05, "loss": 0.7664790153503418, "step": 9750 }, { "epoch": 0.05801546682834911, "grad_norm": 2.081223964691162, "learning_rate": 3.867247870021795e-05, "loss": 0.7761886119842529, "step": 9760 }, { "epoch": 0.05807490890501751, "grad_norm": 1.8839787244796753, "learning_rate": 3.8712106201703984e-05, "loss": 0.8215126037597656, "step": 9770 }, { "epoch": 0.058134350981685894, "grad_norm": 1.8149899244308472, "learning_rate": 3.8751733703190016e-05, "loss": 0.7960074424743653, "step": 9780 }, { "epoch": 0.05819379305835429, "grad_norm": 2.5601706504821777, "learning_rate": 3.879136120467605e-05, "loss": 0.8106776237487793, "step": 9790 }, { "epoch": 0.058253235135022674, "grad_norm": 1.8505167961120605, "learning_rate": 3.883098870616208e-05, "loss": 0.8250505447387695, "step": 9800 }, { "epoch": 0.05831267721169107, "grad_norm": 2.4853515625, "learning_rate": 3.887061620764811e-05, "loss": 0.7466120719909668, "step": 9810 }, { "epoch": 0.05837211928835946, "grad_norm": 1.660042405128479, "learning_rate": 3.8910243709134144e-05, "loss": 0.8019586563110351, "step": 9820 }, { "epoch": 0.05843156136502785, "grad_norm": 1.867023229598999, "learning_rate": 3.894987121062017e-05, "loss": 0.7503938198089599, "step": 9830 }, { "epoch": 0.05849100344169624, "grad_norm": 2.648576259613037, "learning_rate": 3.89894987121062e-05, "loss": 0.8204843521118164, "step": 9840 }, { "epoch": 0.05855044551836463, "grad_norm": 1.9068810939788818, "learning_rate": 3.902912621359224e-05, "loss": 0.7549623012542724, "step": 9850 }, { "epoch": 0.05860988759503302, "grad_norm": 2.3365681171417236, "learning_rate": 3.9068753715078264e-05, "loss": 0.8249256134033203, "step": 9860 }, { "epoch": 0.05866932967170141, "grad_norm": 1.8137754201889038, "learning_rate": 3.9108381216564296e-05, "loss": 0.7860006332397461, "step": 9870 }, { "epoch": 0.0587287717483698, "grad_norm": 1.7472237348556519, "learning_rate": 3.914800871805033e-05, "loss": 0.7542441368103028, "step": 9880 }, { "epoch": 0.05878821382503819, "grad_norm": 2.385698080062866, "learning_rate": 3.918763621953636e-05, "loss": 0.7542121887207032, "step": 9890 }, { "epoch": 0.05884765590170658, "grad_norm": 2.0043177604675293, "learning_rate": 3.922726372102239e-05, "loss": 0.8080476760864258, "step": 9900 }, { "epoch": 0.05890709797837497, "grad_norm": 1.9217445850372314, "learning_rate": 3.9266891222508424e-05, "loss": 0.7775925636291504, "step": 9910 }, { "epoch": 0.058966540055043364, "grad_norm": 1.7865021228790283, "learning_rate": 3.9306518723994456e-05, "loss": 0.7728493213653564, "step": 9920 }, { "epoch": 0.05902598213171175, "grad_norm": 1.9900784492492676, "learning_rate": 3.934614622548049e-05, "loss": 0.8053345680236816, "step": 9930 }, { "epoch": 0.059085424208380144, "grad_norm": 2.04819917678833, "learning_rate": 3.938577372696652e-05, "loss": 0.8045506477355957, "step": 9940 }, { "epoch": 0.05914486628504854, "grad_norm": 2.43019962310791, "learning_rate": 3.9425401228452544e-05, "loss": 0.7323720455169678, "step": 9950 }, { "epoch": 0.059204308361716924, "grad_norm": 2.7107994556427, "learning_rate": 3.946502872993858e-05, "loss": 0.8583857536315918, "step": 9960 }, { "epoch": 0.05926375043838532, "grad_norm": 2.038356065750122, "learning_rate": 3.950465623142461e-05, "loss": 0.8179611206054688, "step": 9970 }, { "epoch": 0.059323192515053705, "grad_norm": 2.491206645965576, "learning_rate": 3.954428373291064e-05, "loss": 0.8130640029907227, "step": 9980 }, { "epoch": 0.0593826345917221, "grad_norm": 1.9406867027282715, "learning_rate": 3.958391123439668e-05, "loss": 0.8075465202331543, "step": 9990 }, { "epoch": 0.059442076668390485, "grad_norm": 1.8715038299560547, "learning_rate": 3.9623538735882704e-05, "loss": 0.7584451675415039, "step": 10000 }, { "epoch": 0.05950151874505888, "grad_norm": 2.021850347518921, "learning_rate": 3.9663166237368736e-05, "loss": 0.8005473136901855, "step": 10010 }, { "epoch": 0.059560960821727266, "grad_norm": 2.527195692062378, "learning_rate": 3.970279373885477e-05, "loss": 0.7442173957824707, "step": 10020 }, { "epoch": 0.05962040289839566, "grad_norm": 1.8386272192001343, "learning_rate": 3.97424212403408e-05, "loss": 0.7666257381439209, "step": 10030 }, { "epoch": 0.059679844975064046, "grad_norm": 2.4321682453155518, "learning_rate": 3.9782048741826825e-05, "loss": 0.7459395885467529, "step": 10040 }, { "epoch": 0.05973928705173244, "grad_norm": 1.8466547727584839, "learning_rate": 3.982167624331286e-05, "loss": 0.7787026405334473, "step": 10050 }, { "epoch": 0.05979872912840083, "grad_norm": 2.5694899559020996, "learning_rate": 3.9861303744798895e-05, "loss": 0.7967969417572022, "step": 10060 }, { "epoch": 0.05985817120506922, "grad_norm": 2.2905092239379883, "learning_rate": 3.990093124628492e-05, "loss": 0.7520534992218018, "step": 10070 }, { "epoch": 0.059917613281737614, "grad_norm": 1.8822046518325806, "learning_rate": 3.994055874777096e-05, "loss": 0.8004810333251953, "step": 10080 }, { "epoch": 0.059977055358406, "grad_norm": 1.9626967906951904, "learning_rate": 3.9980186249256984e-05, "loss": 0.7717457771301269, "step": 10090 }, { "epoch": 0.060036497435074394, "grad_norm": 2.818145751953125, "learning_rate": 4.0019813750743016e-05, "loss": 0.7859837055206299, "step": 10100 }, { "epoch": 0.06009593951174278, "grad_norm": 2.231839179992676, "learning_rate": 4.005944125222905e-05, "loss": 0.7841832637786865, "step": 10110 }, { "epoch": 0.060155381588411175, "grad_norm": 1.7564789056777954, "learning_rate": 4.009906875371508e-05, "loss": 0.7457822799682617, "step": 10120 }, { "epoch": 0.06021482366507956, "grad_norm": 1.930267572402954, "learning_rate": 4.013869625520111e-05, "loss": 0.7586069583892823, "step": 10130 }, { "epoch": 0.060274265741747955, "grad_norm": 2.3227241039276123, "learning_rate": 4.017832375668714e-05, "loss": 0.7632997512817383, "step": 10140 }, { "epoch": 0.06033370781841634, "grad_norm": 2.613210678100586, "learning_rate": 4.0217951258173175e-05, "loss": 0.7967523574829102, "step": 10150 }, { "epoch": 0.060393149895084736, "grad_norm": 2.397965669631958, "learning_rate": 4.02575787596592e-05, "loss": 0.7498530387878418, "step": 10160 }, { "epoch": 0.06045259197175312, "grad_norm": 2.3110244274139404, "learning_rate": 4.029720626114524e-05, "loss": 0.8517715454101562, "step": 10170 }, { "epoch": 0.060512034048421516, "grad_norm": 1.4862802028656006, "learning_rate": 4.0336833762631264e-05, "loss": 0.8049888610839844, "step": 10180 }, { "epoch": 0.0605714761250899, "grad_norm": 1.888127088546753, "learning_rate": 4.0376461264117296e-05, "loss": 0.8265035629272461, "step": 10190 }, { "epoch": 0.060630918201758296, "grad_norm": 2.261396884918213, "learning_rate": 4.0416088765603335e-05, "loss": 0.7858775615692138, "step": 10200 }, { "epoch": 0.06069036027842669, "grad_norm": 2.428339719772339, "learning_rate": 4.045571626708936e-05, "loss": 0.7686689376831055, "step": 10210 }, { "epoch": 0.06074980235509508, "grad_norm": 2.5860629081726074, "learning_rate": 4.049534376857539e-05, "loss": 0.7696518421173095, "step": 10220 }, { "epoch": 0.06080924443176347, "grad_norm": 1.9033526182174683, "learning_rate": 4.0534971270061423e-05, "loss": 0.7695536613464355, "step": 10230 }, { "epoch": 0.06086868650843186, "grad_norm": 2.1865975856781006, "learning_rate": 4.0574598771547455e-05, "loss": 0.7743953227996826, "step": 10240 }, { "epoch": 0.06092812858510025, "grad_norm": 1.6899940967559814, "learning_rate": 4.061422627303349e-05, "loss": 0.7616009712219238, "step": 10250 }, { "epoch": 0.06098757066176864, "grad_norm": 2.3729546070098877, "learning_rate": 4.065385377451952e-05, "loss": 0.777348518371582, "step": 10260 }, { "epoch": 0.06104701273843703, "grad_norm": 1.9685430526733398, "learning_rate": 4.069348127600555e-05, "loss": 0.7866290092468262, "step": 10270 }, { "epoch": 0.06110645481510542, "grad_norm": 1.8119839429855347, "learning_rate": 4.073310877749158e-05, "loss": 0.7565505504608154, "step": 10280 }, { "epoch": 0.06116589689177381, "grad_norm": 2.3161027431488037, "learning_rate": 4.0772736278977615e-05, "loss": 0.7858049392700195, "step": 10290 }, { "epoch": 0.0612253389684422, "grad_norm": 2.431126117706299, "learning_rate": 4.081236378046364e-05, "loss": 0.81158447265625, "step": 10300 }, { "epoch": 0.06128478104511059, "grad_norm": 2.5076351165771484, "learning_rate": 4.085199128194968e-05, "loss": 0.8119806289672852, "step": 10310 }, { "epoch": 0.06134422312177898, "grad_norm": 1.8901035785675049, "learning_rate": 4.089161878343571e-05, "loss": 0.8285930633544922, "step": 10320 }, { "epoch": 0.06140366519844737, "grad_norm": 1.6333494186401367, "learning_rate": 4.0931246284921735e-05, "loss": 0.7837195873260498, "step": 10330 }, { "epoch": 0.061463107275115766, "grad_norm": 1.899565577507019, "learning_rate": 4.0970873786407774e-05, "loss": 0.7986676216125488, "step": 10340 }, { "epoch": 0.06152254935178415, "grad_norm": 2.8793859481811523, "learning_rate": 4.10105012878938e-05, "loss": 0.8177925109863281, "step": 10350 }, { "epoch": 0.06158199142845255, "grad_norm": 2.2380709648132324, "learning_rate": 4.105012878937983e-05, "loss": 0.8209882736206054, "step": 10360 }, { "epoch": 0.061641433505120934, "grad_norm": 1.9055101871490479, "learning_rate": 4.108975629086586e-05, "loss": 0.7815726280212403, "step": 10370 }, { "epoch": 0.06170087558178933, "grad_norm": 1.5616052150726318, "learning_rate": 4.1129383792351895e-05, "loss": 0.8085775375366211, "step": 10380 }, { "epoch": 0.061760317658457714, "grad_norm": 2.1309804916381836, "learning_rate": 4.116901129383793e-05, "loss": 0.7478067398071289, "step": 10390 }, { "epoch": 0.06181975973512611, "grad_norm": 1.8634169101715088, "learning_rate": 4.120863879532396e-05, "loss": 0.7928237915039062, "step": 10400 }, { "epoch": 0.061879201811794494, "grad_norm": 1.6797822713851929, "learning_rate": 4.124826629680999e-05, "loss": 0.7530370712280273, "step": 10410 }, { "epoch": 0.06193864388846289, "grad_norm": 1.849411964416504, "learning_rate": 4.1287893798296016e-05, "loss": 0.7245992183685303, "step": 10420 }, { "epoch": 0.061998085965131275, "grad_norm": 2.0173089504241943, "learning_rate": 4.1327521299782054e-05, "loss": 0.7578129291534423, "step": 10430 }, { "epoch": 0.06205752804179967, "grad_norm": 1.6227415800094604, "learning_rate": 4.136714880126808e-05, "loss": 0.8249763488769531, "step": 10440 }, { "epoch": 0.06211697011846806, "grad_norm": 3.096104621887207, "learning_rate": 4.140677630275411e-05, "loss": 0.7993824005126953, "step": 10450 }, { "epoch": 0.06217641219513645, "grad_norm": 2.6670072078704834, "learning_rate": 4.144640380424015e-05, "loss": 0.7671741962432861, "step": 10460 }, { "epoch": 0.06223585427180484, "grad_norm": 2.4365384578704834, "learning_rate": 4.1486031305726175e-05, "loss": 0.8165450096130371, "step": 10470 }, { "epoch": 0.06229529634847323, "grad_norm": 2.110776901245117, "learning_rate": 4.152565880721221e-05, "loss": 0.7829062461853027, "step": 10480 }, { "epoch": 0.06235473842514162, "grad_norm": 1.8183528184890747, "learning_rate": 4.156528630869824e-05, "loss": 0.7392535209655762, "step": 10490 }, { "epoch": 0.06241418050181001, "grad_norm": 2.356611967086792, "learning_rate": 4.160491381018427e-05, "loss": 0.7501761436462402, "step": 10500 }, { "epoch": 0.062473622578478404, "grad_norm": 1.9651708602905273, "learning_rate": 4.1644541311670296e-05, "loss": 0.8059526443481445, "step": 10510 }, { "epoch": 0.0625330646551468, "grad_norm": 2.3008902072906494, "learning_rate": 4.1684168813156334e-05, "loss": 0.8104698181152343, "step": 10520 }, { "epoch": 0.06259250673181518, "grad_norm": 1.497682809829712, "learning_rate": 4.1723796314642366e-05, "loss": 0.7529148578643798, "step": 10530 }, { "epoch": 0.06265194880848357, "grad_norm": 1.917698621749878, "learning_rate": 4.176342381612839e-05, "loss": 0.7712183952331543, "step": 10540 }, { "epoch": 0.06271139088515196, "grad_norm": 2.7902708053588867, "learning_rate": 4.180305131761443e-05, "loss": 0.7803462028503418, "step": 10550 }, { "epoch": 0.06277083296182036, "grad_norm": 2.1342413425445557, "learning_rate": 4.1842678819100455e-05, "loss": 0.792595911026001, "step": 10560 }, { "epoch": 0.06283027503848874, "grad_norm": 1.8698668479919434, "learning_rate": 4.188230632058649e-05, "loss": 0.8107328414916992, "step": 10570 }, { "epoch": 0.06288971711515713, "grad_norm": 2.226228713989258, "learning_rate": 4.192193382207252e-05, "loss": 0.800957202911377, "step": 10580 }, { "epoch": 0.06294915919182553, "grad_norm": 2.0258166790008545, "learning_rate": 4.196156132355855e-05, "loss": 0.7127317905426025, "step": 10590 }, { "epoch": 0.06300860126849392, "grad_norm": 1.7136651277542114, "learning_rate": 4.200118882504458e-05, "loss": 0.7257904052734375, "step": 10600 }, { "epoch": 0.0630680433451623, "grad_norm": 1.7188351154327393, "learning_rate": 4.2040816326530615e-05, "loss": 0.7263135433197021, "step": 10610 }, { "epoch": 0.06312748542183069, "grad_norm": 2.296322822570801, "learning_rate": 4.2080443828016646e-05, "loss": 0.8479440689086915, "step": 10620 }, { "epoch": 0.0631869274984991, "grad_norm": 2.5424885749816895, "learning_rate": 4.212007132950268e-05, "loss": 0.8253590583801269, "step": 10630 }, { "epoch": 0.06324636957516748, "grad_norm": 2.535547971725464, "learning_rate": 4.215969883098871e-05, "loss": 0.8401487350463868, "step": 10640 }, { "epoch": 0.06330581165183587, "grad_norm": 1.7349944114685059, "learning_rate": 4.2199326332474735e-05, "loss": 0.7655887603759766, "step": 10650 }, { "epoch": 0.06336525372850425, "grad_norm": 1.6857738494873047, "learning_rate": 4.223895383396077e-05, "loss": 0.7981964588165283, "step": 10660 }, { "epoch": 0.06342469580517265, "grad_norm": 2.190992593765259, "learning_rate": 4.2278581335446806e-05, "loss": 0.736996078491211, "step": 10670 }, { "epoch": 0.06348413788184104, "grad_norm": 2.8073015213012695, "learning_rate": 4.231820883693283e-05, "loss": 0.8163686752319336, "step": 10680 }, { "epoch": 0.06354357995850943, "grad_norm": 1.8177375793457031, "learning_rate": 4.235783633841886e-05, "loss": 0.770834493637085, "step": 10690 }, { "epoch": 0.06360302203517781, "grad_norm": 2.0141348838806152, "learning_rate": 4.2397463839904895e-05, "loss": 0.7607241630554199, "step": 10700 }, { "epoch": 0.06366246411184621, "grad_norm": 2.1663901805877686, "learning_rate": 4.2437091341390927e-05, "loss": 0.7670946598052979, "step": 10710 }, { "epoch": 0.0637219061885146, "grad_norm": 1.8752493858337402, "learning_rate": 4.247671884287696e-05, "loss": 0.8051006317138671, "step": 10720 }, { "epoch": 0.06378134826518299, "grad_norm": 1.6187771558761597, "learning_rate": 4.251634634436299e-05, "loss": 0.8275385856628418, "step": 10730 }, { "epoch": 0.06384079034185139, "grad_norm": 2.504987955093384, "learning_rate": 4.255597384584902e-05, "loss": 0.7816970825195313, "step": 10740 }, { "epoch": 0.06390023241851978, "grad_norm": 1.8194266557693481, "learning_rate": 4.2595601347335054e-05, "loss": 0.7458542823791504, "step": 10750 }, { "epoch": 0.06395967449518816, "grad_norm": 1.8863842487335205, "learning_rate": 4.2635228848821086e-05, "loss": 0.7797158241271973, "step": 10760 }, { "epoch": 0.06401911657185655, "grad_norm": 2.0257480144500732, "learning_rate": 4.267485635030711e-05, "loss": 0.7919107437133789, "step": 10770 }, { "epoch": 0.06407855864852495, "grad_norm": 1.7007803916931152, "learning_rate": 4.271448385179315e-05, "loss": 0.7828829288482666, "step": 10780 }, { "epoch": 0.06413800072519334, "grad_norm": 1.8579250574111938, "learning_rate": 4.275411135327918e-05, "loss": 0.8200061798095704, "step": 10790 }, { "epoch": 0.06419744280186172, "grad_norm": 2.255380392074585, "learning_rate": 4.279373885476521e-05, "loss": 0.727209997177124, "step": 10800 }, { "epoch": 0.06425688487853011, "grad_norm": 2.003891706466675, "learning_rate": 4.2833366356251245e-05, "loss": 0.7945352554321289, "step": 10810 }, { "epoch": 0.06431632695519851, "grad_norm": 2.176279306411743, "learning_rate": 4.287299385773727e-05, "loss": 0.8186429977416992, "step": 10820 }, { "epoch": 0.0643757690318669, "grad_norm": 2.1820642948150635, "learning_rate": 4.29126213592233e-05, "loss": 0.7868987083435058, "step": 10830 }, { "epoch": 0.06443521110853528, "grad_norm": 2.035346746444702, "learning_rate": 4.2952248860709334e-05, "loss": 0.6865426063537597, "step": 10840 }, { "epoch": 0.06449465318520368, "grad_norm": 2.2926626205444336, "learning_rate": 4.2991876362195366e-05, "loss": 0.856688404083252, "step": 10850 }, { "epoch": 0.06455409526187207, "grad_norm": 1.4087644815444946, "learning_rate": 4.30315038636814e-05, "loss": 0.7570231437683106, "step": 10860 }, { "epoch": 0.06461353733854046, "grad_norm": 2.1894094944000244, "learning_rate": 4.307113136516743e-05, "loss": 0.8261978149414062, "step": 10870 }, { "epoch": 0.06467297941520884, "grad_norm": 1.89310884475708, "learning_rate": 4.311075886665346e-05, "loss": 0.8085952758789062, "step": 10880 }, { "epoch": 0.06473242149187725, "grad_norm": 1.9159384965896606, "learning_rate": 4.315038636813949e-05, "loss": 0.7436460494995117, "step": 10890 }, { "epoch": 0.06479186356854563, "grad_norm": 2.034281015396118, "learning_rate": 4.3190013869625525e-05, "loss": 0.7806227684020997, "step": 10900 }, { "epoch": 0.06485130564521402, "grad_norm": 2.0684452056884766, "learning_rate": 4.322964137111155e-05, "loss": 0.8187889099121094, "step": 10910 }, { "epoch": 0.0649107477218824, "grad_norm": 2.233201026916504, "learning_rate": 4.326926887259758e-05, "loss": 0.7824729919433594, "step": 10920 }, { "epoch": 0.0649701897985508, "grad_norm": 1.731066346168518, "learning_rate": 4.330889637408362e-05, "loss": 0.7374770641326904, "step": 10930 }, { "epoch": 0.0650296318752192, "grad_norm": 2.0233235359191895, "learning_rate": 4.3348523875569646e-05, "loss": 0.6923511981964111, "step": 10940 }, { "epoch": 0.06508907395188758, "grad_norm": 2.1222755908966064, "learning_rate": 4.338815137705568e-05, "loss": 0.7513619422912597, "step": 10950 }, { "epoch": 0.06514851602855598, "grad_norm": 1.6162183284759521, "learning_rate": 4.342777887854171e-05, "loss": 0.7377578735351562, "step": 10960 }, { "epoch": 0.06520795810522437, "grad_norm": 1.8949811458587646, "learning_rate": 4.346740638002774e-05, "loss": 0.7972115516662598, "step": 10970 }, { "epoch": 0.06526740018189275, "grad_norm": 1.7551194429397583, "learning_rate": 4.350703388151377e-05, "loss": 0.759462547302246, "step": 10980 }, { "epoch": 0.06532684225856114, "grad_norm": 1.7709401845932007, "learning_rate": 4.3546661382999806e-05, "loss": 0.7659529209136963, "step": 10990 }, { "epoch": 0.06538628433522954, "grad_norm": 1.7408487796783447, "learning_rate": 4.358628888448584e-05, "loss": 0.7175873756408692, "step": 11000 }, { "epoch": 0.06544572641189793, "grad_norm": 2.1747984886169434, "learning_rate": 4.362591638597186e-05, "loss": 0.7621094226837158, "step": 11010 }, { "epoch": 0.06550516848856631, "grad_norm": 1.5364227294921875, "learning_rate": 4.36655438874579e-05, "loss": 0.7860033512115479, "step": 11020 }, { "epoch": 0.0655646105652347, "grad_norm": 1.8908472061157227, "learning_rate": 4.3705171388943926e-05, "loss": 0.724673080444336, "step": 11030 }, { "epoch": 0.0656240526419031, "grad_norm": 2.084718942642212, "learning_rate": 4.374479889042996e-05, "loss": 0.7713590145111084, "step": 11040 }, { "epoch": 0.06568349471857149, "grad_norm": 1.804496169090271, "learning_rate": 4.378442639191599e-05, "loss": 0.827060317993164, "step": 11050 }, { "epoch": 0.06574293679523988, "grad_norm": 1.858986735343933, "learning_rate": 4.382405389340202e-05, "loss": 0.7588452816009521, "step": 11060 }, { "epoch": 0.06580237887190826, "grad_norm": 2.091806411743164, "learning_rate": 4.3863681394888054e-05, "loss": 0.7626741409301758, "step": 11070 }, { "epoch": 0.06586182094857666, "grad_norm": 1.7638301849365234, "learning_rate": 4.3903308896374086e-05, "loss": 0.7615194320678711, "step": 11080 }, { "epoch": 0.06592126302524505, "grad_norm": 2.092144012451172, "learning_rate": 4.394293639786012e-05, "loss": 0.7879887580871582, "step": 11090 }, { "epoch": 0.06598070510191344, "grad_norm": 1.8171120882034302, "learning_rate": 4.398256389934615e-05, "loss": 0.7815712451934814, "step": 11100 }, { "epoch": 0.06604014717858184, "grad_norm": 1.9663158655166626, "learning_rate": 4.402219140083218e-05, "loss": 0.744879150390625, "step": 11110 }, { "epoch": 0.06609958925525022, "grad_norm": 2.2812094688415527, "learning_rate": 4.4061818902318206e-05, "loss": 0.7738349914550782, "step": 11120 }, { "epoch": 0.06615903133191861, "grad_norm": 2.0371408462524414, "learning_rate": 4.4101446403804245e-05, "loss": 0.783884334564209, "step": 11130 }, { "epoch": 0.066218473408587, "grad_norm": 1.6595934629440308, "learning_rate": 4.414107390529028e-05, "loss": 0.762656831741333, "step": 11140 }, { "epoch": 0.0662779154852554, "grad_norm": 1.7808114290237427, "learning_rate": 4.41807014067763e-05, "loss": 0.7889718532562255, "step": 11150 }, { "epoch": 0.06633735756192378, "grad_norm": 1.6914963722229004, "learning_rate": 4.4220328908262334e-05, "loss": 0.7482167243957519, "step": 11160 }, { "epoch": 0.06639679963859217, "grad_norm": 1.6996382474899292, "learning_rate": 4.4259956409748366e-05, "loss": 0.7834161758422852, "step": 11170 }, { "epoch": 0.06645624171526056, "grad_norm": 2.337939500808716, "learning_rate": 4.42995839112344e-05, "loss": 0.787309980392456, "step": 11180 }, { "epoch": 0.06651568379192896, "grad_norm": 2.074803352355957, "learning_rate": 4.433921141272043e-05, "loss": 0.7048240661621094, "step": 11190 }, { "epoch": 0.06657512586859735, "grad_norm": 1.654076337814331, "learning_rate": 4.437883891420646e-05, "loss": 0.7781742095947266, "step": 11200 }, { "epoch": 0.06663456794526573, "grad_norm": 2.0733015537261963, "learning_rate": 4.441846641569249e-05, "loss": 0.7960451126098633, "step": 11210 }, { "epoch": 0.06669401002193413, "grad_norm": 1.6999244689941406, "learning_rate": 4.4458093917178525e-05, "loss": 0.7534549713134766, "step": 11220 }, { "epoch": 0.06675345209860252, "grad_norm": 1.4404159784317017, "learning_rate": 4.449772141866456e-05, "loss": 0.7338471412658691, "step": 11230 }, { "epoch": 0.0668128941752709, "grad_norm": 2.178867816925049, "learning_rate": 4.453734892015058e-05, "loss": 0.7561613082885742, "step": 11240 }, { "epoch": 0.0668723362519393, "grad_norm": 2.5382301807403564, "learning_rate": 4.457697642163662e-05, "loss": 0.7673120021820068, "step": 11250 }, { "epoch": 0.0669317783286077, "grad_norm": 1.9006990194320679, "learning_rate": 4.461660392312265e-05, "loss": 0.8796741485595703, "step": 11260 }, { "epoch": 0.06699122040527608, "grad_norm": 2.1511728763580322, "learning_rate": 4.465623142460868e-05, "loss": 0.757834529876709, "step": 11270 }, { "epoch": 0.06705066248194447, "grad_norm": 1.7956478595733643, "learning_rate": 4.4695858926094716e-05, "loss": 0.7700052261352539, "step": 11280 }, { "epoch": 0.06711010455861285, "grad_norm": 1.9827414751052856, "learning_rate": 4.473548642758074e-05, "loss": 0.7610762119293213, "step": 11290 }, { "epoch": 0.06716954663528125, "grad_norm": 1.7702186107635498, "learning_rate": 4.4775113929066773e-05, "loss": 0.7996929168701172, "step": 11300 }, { "epoch": 0.06722898871194964, "grad_norm": 1.626855492591858, "learning_rate": 4.4814741430552805e-05, "loss": 0.7512520790100098, "step": 11310 }, { "epoch": 0.06728843078861803, "grad_norm": 2.150512456893921, "learning_rate": 4.485436893203884e-05, "loss": 0.743096113204956, "step": 11320 }, { "epoch": 0.06734787286528642, "grad_norm": 1.6999857425689697, "learning_rate": 4.489399643352487e-05, "loss": 0.7476368427276612, "step": 11330 }, { "epoch": 0.06740731494195482, "grad_norm": 2.0980587005615234, "learning_rate": 4.49336239350109e-05, "loss": 0.8315375328063965, "step": 11340 }, { "epoch": 0.0674667570186232, "grad_norm": 2.2465059757232666, "learning_rate": 4.497325143649693e-05, "loss": 0.7733850479125977, "step": 11350 }, { "epoch": 0.06752619909529159, "grad_norm": 2.2038047313690186, "learning_rate": 4.501287893798296e-05, "loss": 0.7279383659362793, "step": 11360 }, { "epoch": 0.06758564117195999, "grad_norm": 1.5037540197372437, "learning_rate": 4.5052506439468997e-05, "loss": 0.7122469425201416, "step": 11370 }, { "epoch": 0.06764508324862838, "grad_norm": 1.883854627609253, "learning_rate": 4.509213394095502e-05, "loss": 0.7909923553466797, "step": 11380 }, { "epoch": 0.06770452532529676, "grad_norm": 2.1725289821624756, "learning_rate": 4.5131761442441054e-05, "loss": 0.8200660705566406, "step": 11390 }, { "epoch": 0.06776396740196515, "grad_norm": 2.0984950065612793, "learning_rate": 4.517138894392709e-05, "loss": 0.7405002593994141, "step": 11400 }, { "epoch": 0.06782340947863355, "grad_norm": 2.0113871097564697, "learning_rate": 4.521101644541312e-05, "loss": 0.7742910385131836, "step": 11410 }, { "epoch": 0.06788285155530194, "grad_norm": 1.7745280265808105, "learning_rate": 4.525064394689915e-05, "loss": 0.7077221870422363, "step": 11420 }, { "epoch": 0.06794229363197032, "grad_norm": 2.286611795425415, "learning_rate": 4.529027144838518e-05, "loss": 0.755678367614746, "step": 11430 }, { "epoch": 0.06800173570863871, "grad_norm": 2.231706380844116, "learning_rate": 4.532989894987121e-05, "loss": 0.8161741256713867, "step": 11440 }, { "epoch": 0.06806117778530711, "grad_norm": 1.894303560256958, "learning_rate": 4.5369526451357245e-05, "loss": 0.7601288795471192, "step": 11450 }, { "epoch": 0.0681206198619755, "grad_norm": 1.8050650358200073, "learning_rate": 4.540915395284328e-05, "loss": 0.762788200378418, "step": 11460 }, { "epoch": 0.06818006193864388, "grad_norm": 1.6869405508041382, "learning_rate": 4.544878145432931e-05, "loss": 0.7419410228729248, "step": 11470 }, { "epoch": 0.06823950401531229, "grad_norm": 1.9587047100067139, "learning_rate": 4.5488408955815334e-05, "loss": 0.7522367477416992, "step": 11480 }, { "epoch": 0.06829894609198067, "grad_norm": 2.025790214538574, "learning_rate": 4.552803645730137e-05, "loss": 0.8159683227539063, "step": 11490 }, { "epoch": 0.06835838816864906, "grad_norm": 1.4194433689117432, "learning_rate": 4.55676639587874e-05, "loss": 0.8491127014160156, "step": 11500 }, { "epoch": 0.06841783024531745, "grad_norm": 1.8718986511230469, "learning_rate": 4.560729146027343e-05, "loss": 0.762817668914795, "step": 11510 }, { "epoch": 0.06847727232198585, "grad_norm": 2.056654453277588, "learning_rate": 4.564691896175946e-05, "loss": 0.7102396965026856, "step": 11520 }, { "epoch": 0.06853671439865423, "grad_norm": 1.7158033847808838, "learning_rate": 4.568654646324549e-05, "loss": 0.7784239768981933, "step": 11530 }, { "epoch": 0.06859615647532262, "grad_norm": 1.7447000741958618, "learning_rate": 4.5726173964731525e-05, "loss": 0.7154545783996582, "step": 11540 }, { "epoch": 0.068655598551991, "grad_norm": 2.2071962356567383, "learning_rate": 4.576580146621756e-05, "loss": 0.8013553619384766, "step": 11550 }, { "epoch": 0.06871504062865941, "grad_norm": 1.6697381734848022, "learning_rate": 4.580542896770359e-05, "loss": 0.7432242393493652, "step": 11560 }, { "epoch": 0.0687744827053278, "grad_norm": 2.4306907653808594, "learning_rate": 4.584505646918962e-05, "loss": 0.7902722358703613, "step": 11570 }, { "epoch": 0.06883392478199618, "grad_norm": 1.637377381324768, "learning_rate": 4.588468397067565e-05, "loss": 0.7705307960510254, "step": 11580 }, { "epoch": 0.06889336685866457, "grad_norm": 1.922166347503662, "learning_rate": 4.5924311472161684e-05, "loss": 0.7799635410308838, "step": 11590 }, { "epoch": 0.06895280893533297, "grad_norm": 1.6985112428665161, "learning_rate": 4.5963938973647716e-05, "loss": 0.7732516288757324, "step": 11600 }, { "epoch": 0.06901225101200135, "grad_norm": 1.6999073028564453, "learning_rate": 4.600356647513375e-05, "loss": 0.7361010551452637, "step": 11610 }, { "epoch": 0.06907169308866974, "grad_norm": 1.6110039949417114, "learning_rate": 4.604319397661977e-05, "loss": 0.7368323326110839, "step": 11620 }, { "epoch": 0.06913113516533814, "grad_norm": 1.6280817985534668, "learning_rate": 4.608282147810581e-05, "loss": 0.7910887718200683, "step": 11630 }, { "epoch": 0.06919057724200653, "grad_norm": 1.605568528175354, "learning_rate": 4.612244897959184e-05, "loss": 0.7975391864776611, "step": 11640 }, { "epoch": 0.06925001931867492, "grad_norm": 1.739087700843811, "learning_rate": 4.616207648107787e-05, "loss": 0.7567547798156739, "step": 11650 }, { "epoch": 0.0693094613953433, "grad_norm": 2.5626962184906006, "learning_rate": 4.620170398256391e-05, "loss": 0.7507541656494141, "step": 11660 }, { "epoch": 0.0693689034720117, "grad_norm": 1.8480148315429688, "learning_rate": 4.624133148404993e-05, "loss": 0.7506566524505616, "step": 11670 }, { "epoch": 0.06942834554868009, "grad_norm": 1.8901571035385132, "learning_rate": 4.6280958985535964e-05, "loss": 0.6903628826141357, "step": 11680 }, { "epoch": 0.06948778762534848, "grad_norm": 2.082335948944092, "learning_rate": 4.6320586487021996e-05, "loss": 0.7302294731140136, "step": 11690 }, { "epoch": 0.06954722970201686, "grad_norm": 1.578386664390564, "learning_rate": 4.636021398850803e-05, "loss": 0.7054285049438477, "step": 11700 }, { "epoch": 0.06960667177868526, "grad_norm": 1.9052382707595825, "learning_rate": 4.639984148999405e-05, "loss": 0.7405589103698731, "step": 11710 }, { "epoch": 0.06966611385535365, "grad_norm": 1.9473443031311035, "learning_rate": 4.643946899148009e-05, "loss": 0.7802489280700684, "step": 11720 }, { "epoch": 0.06972555593202204, "grad_norm": 1.9169350862503052, "learning_rate": 4.6479096492966124e-05, "loss": 0.7352911949157714, "step": 11730 }, { "epoch": 0.06978499800869044, "grad_norm": 1.7437987327575684, "learning_rate": 4.651872399445215e-05, "loss": 0.7523050308227539, "step": 11740 }, { "epoch": 0.06984444008535882, "grad_norm": 1.7672405242919922, "learning_rate": 4.655835149593819e-05, "loss": 0.7003849506378174, "step": 11750 }, { "epoch": 0.06990388216202721, "grad_norm": 1.886311411857605, "learning_rate": 4.659797899742421e-05, "loss": 0.707469367980957, "step": 11760 }, { "epoch": 0.0699633242386956, "grad_norm": 1.7467894554138184, "learning_rate": 4.6637606498910245e-05, "loss": 0.8034017562866211, "step": 11770 }, { "epoch": 0.070022766315364, "grad_norm": 1.7319185733795166, "learning_rate": 4.6677234000396277e-05, "loss": 0.7288936614990235, "step": 11780 }, { "epoch": 0.07008220839203239, "grad_norm": 2.004997730255127, "learning_rate": 4.671686150188231e-05, "loss": 0.721247673034668, "step": 11790 }, { "epoch": 0.07014165046870077, "grad_norm": 2.224052906036377, "learning_rate": 4.675648900336834e-05, "loss": 0.7672470569610595, "step": 11800 }, { "epoch": 0.07020109254536916, "grad_norm": 1.858971118927002, "learning_rate": 4.679611650485437e-05, "loss": 0.8128589630126953, "step": 11810 }, { "epoch": 0.07026053462203756, "grad_norm": 1.7278801202774048, "learning_rate": 4.6835744006340404e-05, "loss": 0.7845324516296387, "step": 11820 }, { "epoch": 0.07031997669870595, "grad_norm": 1.666724681854248, "learning_rate": 4.687537150782643e-05, "loss": 0.7659775733947753, "step": 11830 }, { "epoch": 0.07037941877537433, "grad_norm": 1.9068435430526733, "learning_rate": 4.691499900931247e-05, "loss": 0.7488805770874023, "step": 11840 }, { "epoch": 0.07043886085204272, "grad_norm": 1.9813271760940552, "learning_rate": 4.695462651079849e-05, "loss": 0.7035204887390136, "step": 11850 }, { "epoch": 0.07049830292871112, "grad_norm": 2.125410795211792, "learning_rate": 4.6994254012284525e-05, "loss": 0.8449800491333008, "step": 11860 }, { "epoch": 0.07055774500537951, "grad_norm": 2.126146078109741, "learning_rate": 4.7033881513770563e-05, "loss": 0.7767008781433106, "step": 11870 }, { "epoch": 0.0706171870820479, "grad_norm": 2.0058062076568604, "learning_rate": 4.707350901525659e-05, "loss": 0.7697982788085938, "step": 11880 }, { "epoch": 0.0706766291587163, "grad_norm": 1.5447242259979248, "learning_rate": 4.711313651674262e-05, "loss": 0.7592144012451172, "step": 11890 }, { "epoch": 0.07073607123538468, "grad_norm": 1.8903883695602417, "learning_rate": 4.715276401822865e-05, "loss": 0.7711937904357911, "step": 11900 }, { "epoch": 0.07079551331205307, "grad_norm": 2.168144941329956, "learning_rate": 4.7192391519714684e-05, "loss": 0.7715524196624756, "step": 11910 }, { "epoch": 0.07085495538872146, "grad_norm": 2.341736316680908, "learning_rate": 4.7232019021200716e-05, "loss": 0.777921199798584, "step": 11920 }, { "epoch": 0.07091439746538986, "grad_norm": 2.011796474456787, "learning_rate": 4.727164652268675e-05, "loss": 0.7625879764556884, "step": 11930 }, { "epoch": 0.07097383954205824, "grad_norm": 1.9000060558319092, "learning_rate": 4.731127402417278e-05, "loss": 0.7432737350463867, "step": 11940 }, { "epoch": 0.07103328161872663, "grad_norm": 1.897180438041687, "learning_rate": 4.735090152565881e-05, "loss": 0.7750022888183594, "step": 11950 }, { "epoch": 0.07109272369539502, "grad_norm": 2.0224382877349854, "learning_rate": 4.7390529027144844e-05, "loss": 0.7434975624084472, "step": 11960 }, { "epoch": 0.07115216577206342, "grad_norm": 1.7877819538116455, "learning_rate": 4.743015652863087e-05, "loss": 0.794793701171875, "step": 11970 }, { "epoch": 0.0712116078487318, "grad_norm": 1.741819977760315, "learning_rate": 4.74697840301169e-05, "loss": 0.7511537551879883, "step": 11980 }, { "epoch": 0.07127104992540019, "grad_norm": 1.7834043502807617, "learning_rate": 4.750941153160293e-05, "loss": 0.7249523162841797, "step": 11990 }, { "epoch": 0.07133049200206859, "grad_norm": 1.948365330696106, "learning_rate": 4.7549039033088964e-05, "loss": 0.8060928344726562, "step": 12000 }, { "epoch": 0.07138993407873698, "grad_norm": 1.9425441026687622, "learning_rate": 4.7588666534574996e-05, "loss": 0.7979259967803956, "step": 12010 }, { "epoch": 0.07144937615540536, "grad_norm": 2.460416555404663, "learning_rate": 4.762829403606103e-05, "loss": 0.8164573669433594, "step": 12020 }, { "epoch": 0.07150881823207375, "grad_norm": 2.3309361934661865, "learning_rate": 4.766792153754706e-05, "loss": 0.8243914604187011, "step": 12030 }, { "epoch": 0.07156826030874215, "grad_norm": 1.894812822341919, "learning_rate": 4.770754903903309e-05, "loss": 0.767764663696289, "step": 12040 }, { "epoch": 0.07162770238541054, "grad_norm": 1.5051918029785156, "learning_rate": 4.7747176540519124e-05, "loss": 0.756324291229248, "step": 12050 }, { "epoch": 0.07168714446207892, "grad_norm": 2.3549506664276123, "learning_rate": 4.7786804042005156e-05, "loss": 0.7476404666900635, "step": 12060 }, { "epoch": 0.07174658653874731, "grad_norm": 1.7423361539840698, "learning_rate": 4.782643154349119e-05, "loss": 0.7665542602539063, "step": 12070 }, { "epoch": 0.07180602861541571, "grad_norm": 1.9535703659057617, "learning_rate": 4.786605904497722e-05, "loss": 0.7273152351379395, "step": 12080 }, { "epoch": 0.0718654706920841, "grad_norm": 2.9326727390289307, "learning_rate": 4.7905686546463244e-05, "loss": 0.7967974185943604, "step": 12090 }, { "epoch": 0.07192491276875249, "grad_norm": 2.0446956157684326, "learning_rate": 4.794531404794928e-05, "loss": 0.7595488548278808, "step": 12100 }, { "epoch": 0.07198435484542089, "grad_norm": 1.8668652772903442, "learning_rate": 4.798494154943531e-05, "loss": 0.7853874206542969, "step": 12110 }, { "epoch": 0.07204379692208927, "grad_norm": 1.808027982711792, "learning_rate": 4.802456905092134e-05, "loss": 0.7548314571380615, "step": 12120 }, { "epoch": 0.07210323899875766, "grad_norm": 2.0528297424316406, "learning_rate": 4.806419655240738e-05, "loss": 0.8070634841918946, "step": 12130 }, { "epoch": 0.07216268107542605, "grad_norm": 2.4949052333831787, "learning_rate": 4.8103824053893404e-05, "loss": 0.7199114322662353, "step": 12140 }, { "epoch": 0.07222212315209445, "grad_norm": 2.0505282878875732, "learning_rate": 4.8143451555379436e-05, "loss": 0.7649671554565429, "step": 12150 }, { "epoch": 0.07228156522876283, "grad_norm": 1.7056546211242676, "learning_rate": 4.818307905686547e-05, "loss": 0.7846960544586181, "step": 12160 }, { "epoch": 0.07234100730543122, "grad_norm": 2.3866539001464844, "learning_rate": 4.82227065583515e-05, "loss": 0.7563089370727539, "step": 12170 }, { "epoch": 0.07240044938209961, "grad_norm": 1.7583516836166382, "learning_rate": 4.8262334059837525e-05, "loss": 0.7081761360168457, "step": 12180 }, { "epoch": 0.07245989145876801, "grad_norm": 2.41768741607666, "learning_rate": 4.830196156132356e-05, "loss": 0.7687793731689453, "step": 12190 }, { "epoch": 0.0725193335354364, "grad_norm": 1.713492751121521, "learning_rate": 4.8341589062809595e-05, "loss": 0.8587762832641601, "step": 12200 }, { "epoch": 0.07257877561210478, "grad_norm": 1.9062732458114624, "learning_rate": 4.838121656429562e-05, "loss": 0.7524570465087891, "step": 12210 }, { "epoch": 0.07263821768877317, "grad_norm": 1.7860264778137207, "learning_rate": 4.842084406578166e-05, "loss": 0.7449508666992187, "step": 12220 }, { "epoch": 0.07269765976544157, "grad_norm": 1.9847571849822998, "learning_rate": 4.8460471567267684e-05, "loss": 0.7517153739929199, "step": 12230 }, { "epoch": 0.07275710184210996, "grad_norm": 2.1540331840515137, "learning_rate": 4.8500099068753716e-05, "loss": 0.7749515533447265, "step": 12240 }, { "epoch": 0.07281654391877834, "grad_norm": 1.694516897201538, "learning_rate": 4.853972657023975e-05, "loss": 0.7237906455993652, "step": 12250 }, { "epoch": 0.07287598599544674, "grad_norm": 1.8711007833480835, "learning_rate": 4.857935407172578e-05, "loss": 0.7555063247680665, "step": 12260 }, { "epoch": 0.07293542807211513, "grad_norm": 2.305654525756836, "learning_rate": 4.861898157321181e-05, "loss": 0.7368327140808105, "step": 12270 }, { "epoch": 0.07299487014878352, "grad_norm": 1.9088202714920044, "learning_rate": 4.865860907469784e-05, "loss": 0.7597278118133545, "step": 12280 }, { "epoch": 0.0730543122254519, "grad_norm": 1.9698234796524048, "learning_rate": 4.8698236576183875e-05, "loss": 0.7756118774414062, "step": 12290 }, { "epoch": 0.0731137543021203, "grad_norm": 2.0749704837799072, "learning_rate": 4.87378640776699e-05, "loss": 0.7484983921051025, "step": 12300 }, { "epoch": 0.07317319637878869, "grad_norm": 1.9817079305648804, "learning_rate": 4.877749157915594e-05, "loss": 0.7579218864440918, "step": 12310 }, { "epoch": 0.07323263845545708, "grad_norm": 1.7947455644607544, "learning_rate": 4.8817119080641964e-05, "loss": 0.7256756782531738, "step": 12320 }, { "epoch": 0.07329208053212546, "grad_norm": 2.062316417694092, "learning_rate": 4.8856746582127996e-05, "loss": 0.8000778198242188, "step": 12330 }, { "epoch": 0.07335152260879386, "grad_norm": 1.4720901250839233, "learning_rate": 4.8896374083614035e-05, "loss": 0.7084379196166992, "step": 12340 }, { "epoch": 0.07341096468546225, "grad_norm": 1.943877100944519, "learning_rate": 4.893600158510006e-05, "loss": 0.7723113059997558, "step": 12350 }, { "epoch": 0.07347040676213064, "grad_norm": 1.8126050233840942, "learning_rate": 4.897562908658609e-05, "loss": 0.7919564247131348, "step": 12360 }, { "epoch": 0.07352984883879904, "grad_norm": 1.6562087535858154, "learning_rate": 4.9015256588072123e-05, "loss": 0.7743941307067871, "step": 12370 }, { "epoch": 0.07358929091546743, "grad_norm": 1.8278231620788574, "learning_rate": 4.9054884089558155e-05, "loss": 0.7647137641906738, "step": 12380 }, { "epoch": 0.07364873299213581, "grad_norm": 1.8374406099319458, "learning_rate": 4.909451159104419e-05, "loss": 0.75897216796875, "step": 12390 }, { "epoch": 0.0737081750688042, "grad_norm": 2.0256235599517822, "learning_rate": 4.913413909253022e-05, "loss": 0.7790558815002442, "step": 12400 }, { "epoch": 0.0737676171454726, "grad_norm": 1.95879065990448, "learning_rate": 4.917376659401625e-05, "loss": 0.701657485961914, "step": 12410 }, { "epoch": 0.07382705922214099, "grad_norm": 1.8450764417648315, "learning_rate": 4.921339409550228e-05, "loss": 0.721400260925293, "step": 12420 }, { "epoch": 0.07388650129880937, "grad_norm": 1.9984610080718994, "learning_rate": 4.9253021596988315e-05, "loss": 0.7757413864135743, "step": 12430 }, { "epoch": 0.07394594337547776, "grad_norm": 1.789397954940796, "learning_rate": 4.929264909847434e-05, "loss": 0.7461295127868652, "step": 12440 }, { "epoch": 0.07400538545214616, "grad_norm": 1.6155974864959717, "learning_rate": 4.933227659996038e-05, "loss": 0.77379150390625, "step": 12450 }, { "epoch": 0.07406482752881455, "grad_norm": 2.028087854385376, "learning_rate": 4.9371904101446404e-05, "loss": 0.7391781330108642, "step": 12460 }, { "epoch": 0.07412426960548293, "grad_norm": 1.8566173315048218, "learning_rate": 4.9411531602932435e-05, "loss": 0.7763550758361817, "step": 12470 }, { "epoch": 0.07418371168215132, "grad_norm": 1.7497589588165283, "learning_rate": 4.9451159104418474e-05, "loss": 0.7756733417510986, "step": 12480 }, { "epoch": 0.07424315375881972, "grad_norm": 1.5988645553588867, "learning_rate": 4.94907866059045e-05, "loss": 0.7764763832092285, "step": 12490 }, { "epoch": 0.07430259583548811, "grad_norm": 1.533514380455017, "learning_rate": 4.953041410739053e-05, "loss": 0.6851993560791015, "step": 12500 }, { "epoch": 0.0743620379121565, "grad_norm": 1.6026073694229126, "learning_rate": 4.957004160887656e-05, "loss": 0.6764481544494629, "step": 12510 }, { "epoch": 0.0744214799888249, "grad_norm": 2.160858392715454, "learning_rate": 4.9609669110362595e-05, "loss": 0.7759204864501953, "step": 12520 }, { "epoch": 0.07448092206549328, "grad_norm": 2.067023992538452, "learning_rate": 4.964929661184863e-05, "loss": 0.8134973526000977, "step": 12530 }, { "epoch": 0.07454036414216167, "grad_norm": 1.3362632989883423, "learning_rate": 4.968892411333466e-05, "loss": 0.7678648948669433, "step": 12540 }, { "epoch": 0.07459980621883006, "grad_norm": 1.6981761455535889, "learning_rate": 4.972855161482069e-05, "loss": 0.7878582000732421, "step": 12550 }, { "epoch": 0.07465924829549846, "grad_norm": 1.2296316623687744, "learning_rate": 4.9768179116306716e-05, "loss": 0.6835249900817871, "step": 12560 }, { "epoch": 0.07471869037216684, "grad_norm": 1.72939932346344, "learning_rate": 4.9807806617792754e-05, "loss": 0.7907584190368653, "step": 12570 }, { "epoch": 0.07477813244883523, "grad_norm": 1.4900072813034058, "learning_rate": 4.984743411927878e-05, "loss": 0.7169134140014648, "step": 12580 }, { "epoch": 0.07483757452550362, "grad_norm": 1.9964429140090942, "learning_rate": 4.988706162076481e-05, "loss": 0.7098263740539551, "step": 12590 }, { "epoch": 0.07489701660217202, "grad_norm": 1.5439587831497192, "learning_rate": 4.992668912225085e-05, "loss": 0.7833086967468261, "step": 12600 }, { "epoch": 0.0749564586788404, "grad_norm": 1.5188815593719482, "learning_rate": 4.9966316623736875e-05, "loss": 0.7465610504150391, "step": 12610 }, { "epoch": 0.07501590075550879, "grad_norm": 1.8277441263198853, "learning_rate": 5.00059441252229e-05, "loss": 0.7484480857849121, "step": 12620 }, { "epoch": 0.07507534283217719, "grad_norm": 2.1974539756774902, "learning_rate": 5.0045571626708945e-05, "loss": 0.7301953315734864, "step": 12630 }, { "epoch": 0.07513478490884558, "grad_norm": 1.9069231748580933, "learning_rate": 5.008519912819497e-05, "loss": 0.7897327423095704, "step": 12640 }, { "epoch": 0.07519422698551397, "grad_norm": 1.9342536926269531, "learning_rate": 5.0124826629680996e-05, "loss": 0.7704401969909668, "step": 12650 }, { "epoch": 0.07525366906218235, "grad_norm": 1.5427275896072388, "learning_rate": 5.016445413116703e-05, "loss": 0.6518256187438964, "step": 12660 }, { "epoch": 0.07531311113885075, "grad_norm": 1.8501853942871094, "learning_rate": 5.0204081632653066e-05, "loss": 0.7862525939941406, "step": 12670 }, { "epoch": 0.07537255321551914, "grad_norm": 1.709009051322937, "learning_rate": 5.024370913413909e-05, "loss": 0.7771993637084961, "step": 12680 }, { "epoch": 0.07543199529218753, "grad_norm": 1.731865406036377, "learning_rate": 5.028333663562512e-05, "loss": 0.7635815620422364, "step": 12690 }, { "epoch": 0.07549143736885591, "grad_norm": 1.6791315078735352, "learning_rate": 5.032296413711116e-05, "loss": 0.7607529163360596, "step": 12700 }, { "epoch": 0.07555087944552431, "grad_norm": 2.10191011428833, "learning_rate": 5.036259163859719e-05, "loss": 0.7616758346557617, "step": 12710 }, { "epoch": 0.0756103215221927, "grad_norm": 1.9811795949935913, "learning_rate": 5.040221914008322e-05, "loss": 0.697888994216919, "step": 12720 }, { "epoch": 0.07566976359886109, "grad_norm": 1.9474867582321167, "learning_rate": 5.044184664156926e-05, "loss": 0.7027359485626221, "step": 12730 }, { "epoch": 0.07572920567552947, "grad_norm": 1.726241946220398, "learning_rate": 5.048147414305528e-05, "loss": 0.71298246383667, "step": 12740 }, { "epoch": 0.07578864775219787, "grad_norm": 1.8256970643997192, "learning_rate": 5.0521101644541314e-05, "loss": 0.7737951755523682, "step": 12750 }, { "epoch": 0.07584808982886626, "grad_norm": 1.8377941846847534, "learning_rate": 5.056072914602734e-05, "loss": 0.7373708724975586, "step": 12760 }, { "epoch": 0.07590753190553465, "grad_norm": 2.0349512100219727, "learning_rate": 5.060035664751338e-05, "loss": 0.7304406642913819, "step": 12770 }, { "epoch": 0.07596697398220305, "grad_norm": 2.1376595497131348, "learning_rate": 5.063998414899941e-05, "loss": 0.7762221336364746, "step": 12780 }, { "epoch": 0.07602641605887143, "grad_norm": 1.9678685665130615, "learning_rate": 5.0679611650485435e-05, "loss": 0.7455921649932862, "step": 12790 }, { "epoch": 0.07608585813553982, "grad_norm": 2.5447335243225098, "learning_rate": 5.0719239151971474e-05, "loss": 0.7380998611450196, "step": 12800 }, { "epoch": 0.07614530021220821, "grad_norm": 1.6709414720535278, "learning_rate": 5.0758866653457506e-05, "loss": 0.7108884811401367, "step": 12810 }, { "epoch": 0.07620474228887661, "grad_norm": 1.83082914352417, "learning_rate": 5.079849415494353e-05, "loss": 0.7528270244598388, "step": 12820 }, { "epoch": 0.076264184365545, "grad_norm": 1.6962119340896606, "learning_rate": 5.083812165642956e-05, "loss": 0.7583561420440674, "step": 12830 }, { "epoch": 0.07632362644221338, "grad_norm": 1.9547573328018188, "learning_rate": 5.08777491579156e-05, "loss": 0.7603615760803223, "step": 12840 }, { "epoch": 0.07638306851888177, "grad_norm": 1.7291665077209473, "learning_rate": 5.0917376659401626e-05, "loss": 0.6942861557006836, "step": 12850 }, { "epoch": 0.07644251059555017, "grad_norm": 1.7299489974975586, "learning_rate": 5.095700416088766e-05, "loss": 0.7544121265411377, "step": 12860 }, { "epoch": 0.07650195267221856, "grad_norm": 2.108759880065918, "learning_rate": 5.09966316623737e-05, "loss": 0.7422896385192871, "step": 12870 }, { "epoch": 0.07656139474888694, "grad_norm": 1.9149401187896729, "learning_rate": 5.103625916385972e-05, "loss": 0.6886657238006592, "step": 12880 }, { "epoch": 0.07662083682555534, "grad_norm": 1.7547595500946045, "learning_rate": 5.1075886665345754e-05, "loss": 0.7918397903442382, "step": 12890 }, { "epoch": 0.07668027890222373, "grad_norm": 2.150094747543335, "learning_rate": 5.111551416683178e-05, "loss": 0.8199825286865234, "step": 12900 }, { "epoch": 0.07673972097889212, "grad_norm": 1.9033746719360352, "learning_rate": 5.115514166831782e-05, "loss": 0.8043605804443359, "step": 12910 }, { "epoch": 0.0767991630555605, "grad_norm": 1.9296988248825073, "learning_rate": 5.119476916980385e-05, "loss": 0.7820693969726562, "step": 12920 }, { "epoch": 0.0768586051322289, "grad_norm": 2.194770336151123, "learning_rate": 5.1234396671289875e-05, "loss": 0.7655407905578613, "step": 12930 }, { "epoch": 0.07691804720889729, "grad_norm": 1.7787662744522095, "learning_rate": 5.1274024172775913e-05, "loss": 0.7931571483612061, "step": 12940 }, { "epoch": 0.07697748928556568, "grad_norm": 1.6001380681991577, "learning_rate": 5.1313651674261945e-05, "loss": 0.7269608497619628, "step": 12950 }, { "epoch": 0.07703693136223407, "grad_norm": 1.9885202646255493, "learning_rate": 5.135327917574797e-05, "loss": 0.7295247077941894, "step": 12960 }, { "epoch": 0.07709637343890247, "grad_norm": 1.9704594612121582, "learning_rate": 5.1392906677233995e-05, "loss": 0.7096014499664307, "step": 12970 }, { "epoch": 0.07715581551557085, "grad_norm": 1.9056222438812256, "learning_rate": 5.143253417872004e-05, "loss": 0.7267992496490479, "step": 12980 }, { "epoch": 0.07721525759223924, "grad_norm": 1.96868896484375, "learning_rate": 5.1472161680206066e-05, "loss": 0.7380166530609131, "step": 12990 }, { "epoch": 0.07727469966890764, "grad_norm": 2.306502103805542, "learning_rate": 5.151178918169209e-05, "loss": 0.7786079406738281, "step": 13000 }, { "epoch": 0.07733414174557603, "grad_norm": 1.740817666053772, "learning_rate": 5.155141668317813e-05, "loss": 0.760749626159668, "step": 13010 }, { "epoch": 0.07739358382224441, "grad_norm": 1.6956782341003418, "learning_rate": 5.159104418466416e-05, "loss": 0.7601191520690918, "step": 13020 }, { "epoch": 0.0774530258989128, "grad_norm": 1.9429811239242554, "learning_rate": 5.163067168615019e-05, "loss": 0.760743236541748, "step": 13030 }, { "epoch": 0.0775124679755812, "grad_norm": 1.9819434881210327, "learning_rate": 5.167029918763622e-05, "loss": 0.7224529266357422, "step": 13040 }, { "epoch": 0.07757191005224959, "grad_norm": 1.7436072826385498, "learning_rate": 5.170992668912226e-05, "loss": 0.7671323299407959, "step": 13050 }, { "epoch": 0.07763135212891797, "grad_norm": 1.9476573467254639, "learning_rate": 5.174955419060828e-05, "loss": 0.6967949867248535, "step": 13060 }, { "epoch": 0.07769079420558636, "grad_norm": 2.2671217918395996, "learning_rate": 5.1789181692094314e-05, "loss": 0.7164202690124511, "step": 13070 }, { "epoch": 0.07775023628225476, "grad_norm": 1.6698368787765503, "learning_rate": 5.182880919358035e-05, "loss": 0.732274341583252, "step": 13080 }, { "epoch": 0.07780967835892315, "grad_norm": 2.1240806579589844, "learning_rate": 5.186843669506638e-05, "loss": 0.7711035728454589, "step": 13090 }, { "epoch": 0.07786912043559154, "grad_norm": 2.116055965423584, "learning_rate": 5.190806419655241e-05, "loss": 0.7540058135986328, "step": 13100 }, { "epoch": 0.07792856251225992, "grad_norm": 1.8164669275283813, "learning_rate": 5.1947691698038435e-05, "loss": 0.7254556655883789, "step": 13110 }, { "epoch": 0.07798800458892832, "grad_norm": 1.9016529321670532, "learning_rate": 5.1987319199524474e-05, "loss": 0.7481221199035645, "step": 13120 }, { "epoch": 0.07804744666559671, "grad_norm": 2.991933584213257, "learning_rate": 5.2026946701010506e-05, "loss": 0.7983148574829102, "step": 13130 }, { "epoch": 0.0781068887422651, "grad_norm": 2.052671194076538, "learning_rate": 5.206657420249653e-05, "loss": 0.7854779243469239, "step": 13140 }, { "epoch": 0.0781663308189335, "grad_norm": 1.6533021926879883, "learning_rate": 5.210620170398257e-05, "loss": 0.783759069442749, "step": 13150 }, { "epoch": 0.07822577289560188, "grad_norm": 2.144247531890869, "learning_rate": 5.21458292054686e-05, "loss": 0.698056411743164, "step": 13160 }, { "epoch": 0.07828521497227027, "grad_norm": 1.6969558000564575, "learning_rate": 5.2185456706954626e-05, "loss": 0.711659288406372, "step": 13170 }, { "epoch": 0.07834465704893866, "grad_norm": 2.093207836151123, "learning_rate": 5.222508420844066e-05, "loss": 0.74471116065979, "step": 13180 }, { "epoch": 0.07840409912560706, "grad_norm": 1.7158546447753906, "learning_rate": 5.22647117099267e-05, "loss": 0.7142293930053711, "step": 13190 }, { "epoch": 0.07846354120227544, "grad_norm": 1.4864823818206787, "learning_rate": 5.230433921141272e-05, "loss": 0.7573016166687012, "step": 13200 }, { "epoch": 0.07852298327894383, "grad_norm": 2.1127545833587646, "learning_rate": 5.2343966712898754e-05, "loss": 0.731055212020874, "step": 13210 }, { "epoch": 0.07858242535561222, "grad_norm": 1.9042664766311646, "learning_rate": 5.238359421438479e-05, "loss": 0.7131036758422852, "step": 13220 }, { "epoch": 0.07864186743228062, "grad_norm": 2.2632408142089844, "learning_rate": 5.242322171587082e-05, "loss": 0.7597596168518066, "step": 13230 }, { "epoch": 0.078701309508949, "grad_norm": 1.6850236654281616, "learning_rate": 5.246284921735685e-05, "loss": 0.7690637588500977, "step": 13240 }, { "epoch": 0.07876075158561739, "grad_norm": 2.1517748832702637, "learning_rate": 5.2502476718842875e-05, "loss": 0.7657297134399415, "step": 13250 }, { "epoch": 0.07882019366228579, "grad_norm": 2.0800869464874268, "learning_rate": 5.254210422032891e-05, "loss": 0.777793025970459, "step": 13260 }, { "epoch": 0.07887963573895418, "grad_norm": 1.7494480609893799, "learning_rate": 5.2581731721814945e-05, "loss": 0.6750072002410888, "step": 13270 }, { "epoch": 0.07893907781562257, "grad_norm": 1.8920153379440308, "learning_rate": 5.262135922330097e-05, "loss": 0.7625130176544189, "step": 13280 }, { "epoch": 0.07899851989229095, "grad_norm": 1.9621764421463013, "learning_rate": 5.266098672478701e-05, "loss": 0.7741819381713867, "step": 13290 }, { "epoch": 0.07905796196895935, "grad_norm": 1.6732487678527832, "learning_rate": 5.270061422627304e-05, "loss": 0.738668155670166, "step": 13300 }, { "epoch": 0.07911740404562774, "grad_norm": 2.0996224880218506, "learning_rate": 5.2740241727759066e-05, "loss": 0.7413345813751221, "step": 13310 }, { "epoch": 0.07917684612229613, "grad_norm": 2.2564690113067627, "learning_rate": 5.277986922924509e-05, "loss": 0.7398759841918945, "step": 13320 }, { "epoch": 0.07923628819896451, "grad_norm": 1.8585916757583618, "learning_rate": 5.281949673073113e-05, "loss": 0.7732464790344238, "step": 13330 }, { "epoch": 0.07929573027563291, "grad_norm": 1.7578147649765015, "learning_rate": 5.285912423221716e-05, "loss": 0.7178997039794922, "step": 13340 }, { "epoch": 0.0793551723523013, "grad_norm": 1.809056282043457, "learning_rate": 5.2898751733703187e-05, "loss": 0.7287446975708007, "step": 13350 }, { "epoch": 0.07941461442896969, "grad_norm": 1.7687791585922241, "learning_rate": 5.2938379235189225e-05, "loss": 0.7281707763671875, "step": 13360 }, { "epoch": 0.07947405650563807, "grad_norm": 1.7363715171813965, "learning_rate": 5.297800673667526e-05, "loss": 0.7479783058166504, "step": 13370 }, { "epoch": 0.07953349858230647, "grad_norm": 2.224048614501953, "learning_rate": 5.301763423816128e-05, "loss": 0.7361090183258057, "step": 13380 }, { "epoch": 0.07959294065897486, "grad_norm": 1.1888676881790161, "learning_rate": 5.3057261739647314e-05, "loss": 0.725606632232666, "step": 13390 }, { "epoch": 0.07965238273564325, "grad_norm": 1.7944895029067993, "learning_rate": 5.309688924113335e-05, "loss": 0.6966663360595703, "step": 13400 }, { "epoch": 0.07971182481231165, "grad_norm": 1.9284213781356812, "learning_rate": 5.313651674261938e-05, "loss": 0.6685633659362793, "step": 13410 }, { "epoch": 0.07977126688898004, "grad_norm": 1.7866549491882324, "learning_rate": 5.317614424410541e-05, "loss": 0.7221850395202637, "step": 13420 }, { "epoch": 0.07983070896564842, "grad_norm": 1.8181984424591064, "learning_rate": 5.321577174559145e-05, "loss": 0.6770725250244141, "step": 13430 }, { "epoch": 0.07989015104231681, "grad_norm": 2.204087257385254, "learning_rate": 5.3255399247077473e-05, "loss": 0.7459104061126709, "step": 13440 }, { "epoch": 0.07994959311898521, "grad_norm": 1.69638192653656, "learning_rate": 5.3295026748563505e-05, "loss": 0.7346232414245606, "step": 13450 }, { "epoch": 0.0800090351956536, "grad_norm": 1.6791017055511475, "learning_rate": 5.333465425004953e-05, "loss": 0.666838550567627, "step": 13460 }, { "epoch": 0.08006847727232198, "grad_norm": 1.5122333765029907, "learning_rate": 5.337428175153557e-05, "loss": 0.7228143692016602, "step": 13470 }, { "epoch": 0.08012791934899037, "grad_norm": 1.7842930555343628, "learning_rate": 5.34139092530216e-05, "loss": 0.678102445602417, "step": 13480 }, { "epoch": 0.08018736142565877, "grad_norm": 1.8828624486923218, "learning_rate": 5.3453536754507626e-05, "loss": 0.7169583320617676, "step": 13490 }, { "epoch": 0.08024680350232716, "grad_norm": 2.027406930923462, "learning_rate": 5.3493164255993665e-05, "loss": 0.7595384597778321, "step": 13500 }, { "epoch": 0.08030624557899554, "grad_norm": 2.1201860904693604, "learning_rate": 5.3532791757479697e-05, "loss": 0.7614253044128418, "step": 13510 }, { "epoch": 0.08036568765566394, "grad_norm": 1.5739556550979614, "learning_rate": 5.357241925896572e-05, "loss": 0.7461452960968018, "step": 13520 }, { "epoch": 0.08042512973233233, "grad_norm": 1.3155680894851685, "learning_rate": 5.3612046760451754e-05, "loss": 0.6917315483093261, "step": 13530 }, { "epoch": 0.08048457180900072, "grad_norm": 2.0112180709838867, "learning_rate": 5.365167426193779e-05, "loss": 0.7144902229309082, "step": 13540 }, { "epoch": 0.0805440138856691, "grad_norm": 2.2270212173461914, "learning_rate": 5.369130176342382e-05, "loss": 0.7620285987854004, "step": 13550 }, { "epoch": 0.0806034559623375, "grad_norm": 2.004117488861084, "learning_rate": 5.373092926490985e-05, "loss": 0.733305549621582, "step": 13560 }, { "epoch": 0.08066289803900589, "grad_norm": 2.1649675369262695, "learning_rate": 5.377055676639589e-05, "loss": 0.7882651329040528, "step": 13570 }, { "epoch": 0.08072234011567428, "grad_norm": 1.8579833507537842, "learning_rate": 5.381018426788191e-05, "loss": 0.722348403930664, "step": 13580 }, { "epoch": 0.08078178219234267, "grad_norm": 2.002772569656372, "learning_rate": 5.3849811769367945e-05, "loss": 0.7697652816772461, "step": 13590 }, { "epoch": 0.08084122426901107, "grad_norm": 1.8306620121002197, "learning_rate": 5.388943927085397e-05, "loss": 0.693144416809082, "step": 13600 }, { "epoch": 0.08090066634567945, "grad_norm": 1.6277811527252197, "learning_rate": 5.392906677234001e-05, "loss": 0.7168471336364746, "step": 13610 }, { "epoch": 0.08096010842234784, "grad_norm": 1.440793752670288, "learning_rate": 5.3968694273826034e-05, "loss": 0.725618553161621, "step": 13620 }, { "epoch": 0.08101955049901623, "grad_norm": 1.7698044776916504, "learning_rate": 5.4008321775312066e-05, "loss": 0.734759521484375, "step": 13630 }, { "epoch": 0.08107899257568463, "grad_norm": 1.7632330656051636, "learning_rate": 5.4047949276798104e-05, "loss": 0.7393426895141602, "step": 13640 }, { "epoch": 0.08113843465235301, "grad_norm": 1.954063892364502, "learning_rate": 5.408757677828413e-05, "loss": 0.745356559753418, "step": 13650 }, { "epoch": 0.0811978767290214, "grad_norm": 2.0554749965667725, "learning_rate": 5.412720427977016e-05, "loss": 0.7794188976287841, "step": 13660 }, { "epoch": 0.0812573188056898, "grad_norm": 1.9946560859680176, "learning_rate": 5.41668317812562e-05, "loss": 0.7971362113952637, "step": 13670 }, { "epoch": 0.08131676088235819, "grad_norm": 1.7896058559417725, "learning_rate": 5.4206459282742225e-05, "loss": 0.7152839660644531, "step": 13680 }, { "epoch": 0.08137620295902658, "grad_norm": 1.951519250869751, "learning_rate": 5.424608678422826e-05, "loss": 0.7768816947937012, "step": 13690 }, { "epoch": 0.08143564503569496, "grad_norm": 1.4000341892242432, "learning_rate": 5.428571428571428e-05, "loss": 0.7460376739501953, "step": 13700 }, { "epoch": 0.08149508711236336, "grad_norm": 1.8364591598510742, "learning_rate": 5.432534178720032e-05, "loss": 0.703072452545166, "step": 13710 }, { "epoch": 0.08155452918903175, "grad_norm": 2.0908286571502686, "learning_rate": 5.436496928868635e-05, "loss": 0.7438355445861816, "step": 13720 }, { "epoch": 0.08161397126570014, "grad_norm": 1.450256586074829, "learning_rate": 5.440459679017238e-05, "loss": 0.772938871383667, "step": 13730 }, { "epoch": 0.08167341334236852, "grad_norm": 1.9332873821258545, "learning_rate": 5.4444224291658416e-05, "loss": 0.7237353324890137, "step": 13740 }, { "epoch": 0.08173285541903692, "grad_norm": 2.0302422046661377, "learning_rate": 5.448385179314445e-05, "loss": 0.6965244293212891, "step": 13750 }, { "epoch": 0.08179229749570531, "grad_norm": 1.7494381666183472, "learning_rate": 5.452347929463047e-05, "loss": 0.7345974922180176, "step": 13760 }, { "epoch": 0.0818517395723737, "grad_norm": 1.883255124092102, "learning_rate": 5.4563106796116505e-05, "loss": 0.7220257759094239, "step": 13770 }, { "epoch": 0.0819111816490421, "grad_norm": 1.9348558187484741, "learning_rate": 5.4602734297602544e-05, "loss": 0.7818012237548828, "step": 13780 }, { "epoch": 0.08197062372571048, "grad_norm": 1.9511419534683228, "learning_rate": 5.464236179908857e-05, "loss": 0.8133659362792969, "step": 13790 }, { "epoch": 0.08203006580237887, "grad_norm": 1.96164071559906, "learning_rate": 5.46819893005746e-05, "loss": 0.7396489143371582, "step": 13800 }, { "epoch": 0.08208950787904726, "grad_norm": 1.6928292512893677, "learning_rate": 5.472161680206064e-05, "loss": 0.71871018409729, "step": 13810 }, { "epoch": 0.08214894995571566, "grad_norm": 1.9464954137802124, "learning_rate": 5.4761244303546664e-05, "loss": 0.8069210052490234, "step": 13820 }, { "epoch": 0.08220839203238405, "grad_norm": 1.739649772644043, "learning_rate": 5.4800871805032696e-05, "loss": 0.6872031211853027, "step": 13830 }, { "epoch": 0.08226783410905243, "grad_norm": 2.295006513595581, "learning_rate": 5.484049930651872e-05, "loss": 0.7831465721130371, "step": 13840 }, { "epoch": 0.08232727618572082, "grad_norm": 1.8228281736373901, "learning_rate": 5.488012680800476e-05, "loss": 0.758791446685791, "step": 13850 }, { "epoch": 0.08238671826238922, "grad_norm": 1.6968374252319336, "learning_rate": 5.491975430949079e-05, "loss": 0.7629763603210449, "step": 13860 }, { "epoch": 0.0824461603390576, "grad_norm": 1.7077996730804443, "learning_rate": 5.495938181097682e-05, "loss": 0.7277846813201905, "step": 13870 }, { "epoch": 0.08250560241572599, "grad_norm": 1.6797974109649658, "learning_rate": 5.4999009312462856e-05, "loss": 0.7530631065368653, "step": 13880 }, { "epoch": 0.08256504449239438, "grad_norm": 1.5436978340148926, "learning_rate": 5.503863681394889e-05, "loss": 0.7555433750152588, "step": 13890 }, { "epoch": 0.08262448656906278, "grad_norm": 1.9448552131652832, "learning_rate": 5.507826431543491e-05, "loss": 0.7528864860534668, "step": 13900 }, { "epoch": 0.08268392864573117, "grad_norm": 1.969490647315979, "learning_rate": 5.5117891816920945e-05, "loss": 0.6904889583587647, "step": 13910 }, { "epoch": 0.08274337072239955, "grad_norm": 1.6597115993499756, "learning_rate": 5.515751931840698e-05, "loss": 0.7571073532104492, "step": 13920 }, { "epoch": 0.08280281279906795, "grad_norm": 1.8661776781082153, "learning_rate": 5.519714681989301e-05, "loss": 0.738125991821289, "step": 13930 }, { "epoch": 0.08286225487573634, "grad_norm": 1.9421190023422241, "learning_rate": 5.5236774321379033e-05, "loss": 0.7384019374847413, "step": 13940 }, { "epoch": 0.08292169695240473, "grad_norm": 1.9250718355178833, "learning_rate": 5.527640182286508e-05, "loss": 0.7855253219604492, "step": 13950 }, { "epoch": 0.08298113902907311, "grad_norm": 1.9171150922775269, "learning_rate": 5.5316029324351104e-05, "loss": 0.7110194206237793, "step": 13960 }, { "epoch": 0.08304058110574151, "grad_norm": 1.6904860734939575, "learning_rate": 5.535565682583713e-05, "loss": 0.7197908878326416, "step": 13970 }, { "epoch": 0.0831000231824099, "grad_norm": 1.9171335697174072, "learning_rate": 5.539528432732316e-05, "loss": 0.7009248733520508, "step": 13980 }, { "epoch": 0.08315946525907829, "grad_norm": 1.9056867361068726, "learning_rate": 5.54349118288092e-05, "loss": 0.7408702850341797, "step": 13990 }, { "epoch": 0.08321890733574668, "grad_norm": 1.8002197742462158, "learning_rate": 5.5474539330295225e-05, "loss": 0.7630980491638184, "step": 14000 }, { "epoch": 0.08327834941241508, "grad_norm": 1.9387805461883545, "learning_rate": 5.5514166831781257e-05, "loss": 0.7460893630981446, "step": 14010 }, { "epoch": 0.08333779148908346, "grad_norm": 1.8044579029083252, "learning_rate": 5.5553794333267295e-05, "loss": 0.6933078765869141, "step": 14020 }, { "epoch": 0.08339723356575185, "grad_norm": 1.7773021459579468, "learning_rate": 5.559342183475332e-05, "loss": 0.7517476558685303, "step": 14030 }, { "epoch": 0.08345667564242025, "grad_norm": 2.464014768600464, "learning_rate": 5.563304933623935e-05, "loss": 0.7683785438537598, "step": 14040 }, { "epoch": 0.08351611771908864, "grad_norm": 2.0087203979492188, "learning_rate": 5.567267683772538e-05, "loss": 0.6938858032226562, "step": 14050 }, { "epoch": 0.08357555979575702, "grad_norm": 1.7814334630966187, "learning_rate": 5.5712304339211416e-05, "loss": 0.694088077545166, "step": 14060 }, { "epoch": 0.08363500187242541, "grad_norm": 1.8683193922042847, "learning_rate": 5.575193184069745e-05, "loss": 0.7472912788391113, "step": 14070 }, { "epoch": 0.08369444394909381, "grad_norm": 1.6886159181594849, "learning_rate": 5.579155934218347e-05, "loss": 0.7568608283996582, "step": 14080 }, { "epoch": 0.0837538860257622, "grad_norm": 1.7805982828140259, "learning_rate": 5.583118684366951e-05, "loss": 0.7576628684997558, "step": 14090 }, { "epoch": 0.08381332810243058, "grad_norm": 1.9730825424194336, "learning_rate": 5.5870814345155544e-05, "loss": 0.7859005928039551, "step": 14100 }, { "epoch": 0.08387277017909897, "grad_norm": 1.4590065479278564, "learning_rate": 5.591044184664157e-05, "loss": 0.707786750793457, "step": 14110 }, { "epoch": 0.08393221225576737, "grad_norm": 1.7679392099380493, "learning_rate": 5.59500693481276e-05, "loss": 0.7237558364868164, "step": 14120 }, { "epoch": 0.08399165433243576, "grad_norm": 2.119126081466675, "learning_rate": 5.598969684961364e-05, "loss": 0.6880438804626465, "step": 14130 }, { "epoch": 0.08405109640910415, "grad_norm": 1.8155887126922607, "learning_rate": 5.6029324351099664e-05, "loss": 0.6848752975463868, "step": 14140 }, { "epoch": 0.08411053848577255, "grad_norm": 1.6400476694107056, "learning_rate": 5.6068951852585696e-05, "loss": 0.6980358123779297, "step": 14150 }, { "epoch": 0.08416998056244093, "grad_norm": 1.9084826707839966, "learning_rate": 5.6108579354071735e-05, "loss": 0.7440567016601562, "step": 14160 }, { "epoch": 0.08422942263910932, "grad_norm": 1.6787159442901611, "learning_rate": 5.614820685555776e-05, "loss": 0.7059807777404785, "step": 14170 }, { "epoch": 0.0842888647157777, "grad_norm": 1.9858641624450684, "learning_rate": 5.618783435704379e-05, "loss": 0.7422533988952636, "step": 14180 }, { "epoch": 0.0843483067924461, "grad_norm": 1.8642244338989258, "learning_rate": 5.622746185852982e-05, "loss": 0.705600357055664, "step": 14190 }, { "epoch": 0.0844077488691145, "grad_norm": 1.4308803081512451, "learning_rate": 5.6267089360015856e-05, "loss": 0.6873650074005127, "step": 14200 }, { "epoch": 0.08446719094578288, "grad_norm": 1.921087622642517, "learning_rate": 5.630671686150189e-05, "loss": 0.7307559967041015, "step": 14210 }, { "epoch": 0.08452663302245127, "grad_norm": 2.2095601558685303, "learning_rate": 5.634634436298791e-05, "loss": 0.7578412055969238, "step": 14220 }, { "epoch": 0.08458607509911967, "grad_norm": 1.9398030042648315, "learning_rate": 5.638597186447395e-05, "loss": 0.7836482524871826, "step": 14230 }, { "epoch": 0.08464551717578805, "grad_norm": 1.7432196140289307, "learning_rate": 5.642559936595998e-05, "loss": 0.766664695739746, "step": 14240 }, { "epoch": 0.08470495925245644, "grad_norm": 1.5228726863861084, "learning_rate": 5.646522686744601e-05, "loss": 0.7361852645874023, "step": 14250 }, { "epoch": 0.08476440132912483, "grad_norm": 1.512611746788025, "learning_rate": 5.650485436893203e-05, "loss": 0.7297506332397461, "step": 14260 }, { "epoch": 0.08482384340579323, "grad_norm": 1.8267549276351929, "learning_rate": 5.654448187041808e-05, "loss": 0.7260559558868408, "step": 14270 }, { "epoch": 0.08488328548246162, "grad_norm": 1.6950677633285522, "learning_rate": 5.6584109371904104e-05, "loss": 0.8024630546569824, "step": 14280 }, { "epoch": 0.08494272755913, "grad_norm": 1.6091792583465576, "learning_rate": 5.662373687339013e-05, "loss": 0.7129621505737305, "step": 14290 }, { "epoch": 0.0850021696357984, "grad_norm": 1.8301801681518555, "learning_rate": 5.6663364374876174e-05, "loss": 0.733591365814209, "step": 14300 }, { "epoch": 0.08506161171246679, "grad_norm": 1.8792668581008911, "learning_rate": 5.67029918763622e-05, "loss": 0.7277876377105713, "step": 14310 }, { "epoch": 0.08512105378913518, "grad_norm": 1.7948801517486572, "learning_rate": 5.6742619377848224e-05, "loss": 0.7341976642608643, "step": 14320 }, { "epoch": 0.08518049586580356, "grad_norm": 1.5710067749023438, "learning_rate": 5.6782246879334256e-05, "loss": 0.7627803325653076, "step": 14330 }, { "epoch": 0.08523993794247196, "grad_norm": 1.2168498039245605, "learning_rate": 5.6821874380820295e-05, "loss": 0.6970799446105957, "step": 14340 }, { "epoch": 0.08529938001914035, "grad_norm": 1.6971243619918823, "learning_rate": 5.686150188230632e-05, "loss": 0.7079246044158936, "step": 14350 }, { "epoch": 0.08535882209580874, "grad_norm": 1.638309121131897, "learning_rate": 5.690112938379235e-05, "loss": 0.7424732685089112, "step": 14360 }, { "epoch": 0.08541826417247712, "grad_norm": 2.086395502090454, "learning_rate": 5.694075688527839e-05, "loss": 0.7448743343353271, "step": 14370 }, { "epoch": 0.08547770624914552, "grad_norm": 1.6021615266799927, "learning_rate": 5.6980384386764416e-05, "loss": 0.7321120262145996, "step": 14380 }, { "epoch": 0.08553714832581391, "grad_norm": 1.885122299194336, "learning_rate": 5.702001188825045e-05, "loss": 0.7209537506103516, "step": 14390 }, { "epoch": 0.0855965904024823, "grad_norm": 1.8602467775344849, "learning_rate": 5.705963938973647e-05, "loss": 0.749121904373169, "step": 14400 }, { "epoch": 0.0856560324791507, "grad_norm": 1.8772274255752563, "learning_rate": 5.709926689122251e-05, "loss": 0.7999490737915039, "step": 14410 }, { "epoch": 0.08571547455581909, "grad_norm": 1.5452860593795776, "learning_rate": 5.713889439270854e-05, "loss": 0.7373411178588867, "step": 14420 }, { "epoch": 0.08577491663248747, "grad_norm": 2.2204248905181885, "learning_rate": 5.717852189419457e-05, "loss": 0.7149980545043946, "step": 14430 }, { "epoch": 0.08583435870915586, "grad_norm": 2.2043497562408447, "learning_rate": 5.721814939568061e-05, "loss": 0.7328161239624024, "step": 14440 }, { "epoch": 0.08589380078582426, "grad_norm": 1.5841838121414185, "learning_rate": 5.725777689716664e-05, "loss": 0.6728322505950928, "step": 14450 }, { "epoch": 0.08595324286249265, "grad_norm": 1.682177186012268, "learning_rate": 5.7297404398652664e-05, "loss": 0.6881122589111328, "step": 14460 }, { "epoch": 0.08601268493916103, "grad_norm": 1.4799765348434448, "learning_rate": 5.7337031900138696e-05, "loss": 0.7311532020568847, "step": 14470 }, { "epoch": 0.08607212701582942, "grad_norm": 2.6569769382476807, "learning_rate": 5.7376659401624735e-05, "loss": 0.7166273117065429, "step": 14480 }, { "epoch": 0.08613156909249782, "grad_norm": 1.9514590501785278, "learning_rate": 5.741628690311076e-05, "loss": 0.7740116596221924, "step": 14490 }, { "epoch": 0.0861910111691662, "grad_norm": 1.4834178686141968, "learning_rate": 5.745591440459679e-05, "loss": 0.7654538154602051, "step": 14500 }, { "epoch": 0.0862504532458346, "grad_norm": 1.6913447380065918, "learning_rate": 5.749554190608283e-05, "loss": 0.7968939304351806, "step": 14510 }, { "epoch": 0.08630989532250298, "grad_norm": 1.9634840488433838, "learning_rate": 5.7535169407568855e-05, "loss": 0.6953314304351806, "step": 14520 }, { "epoch": 0.08636933739917138, "grad_norm": 1.5079381465911865, "learning_rate": 5.757479690905489e-05, "loss": 0.7685259819030762, "step": 14530 }, { "epoch": 0.08642877947583977, "grad_norm": 1.888542890548706, "learning_rate": 5.7614424410540926e-05, "loss": 0.7304391384124755, "step": 14540 }, { "epoch": 0.08648822155250815, "grad_norm": 1.6169490814208984, "learning_rate": 5.765405191202695e-05, "loss": 0.6716536045074463, "step": 14550 }, { "epoch": 0.08654766362917655, "grad_norm": 1.3745396137237549, "learning_rate": 5.769367941351298e-05, "loss": 0.7612923622131348, "step": 14560 }, { "epoch": 0.08660710570584494, "grad_norm": 2.0284197330474854, "learning_rate": 5.773330691499901e-05, "loss": 0.7227534770965576, "step": 14570 }, { "epoch": 0.08666654778251333, "grad_norm": 1.722328782081604, "learning_rate": 5.7772934416485047e-05, "loss": 0.719056510925293, "step": 14580 }, { "epoch": 0.08672598985918172, "grad_norm": 2.0792386531829834, "learning_rate": 5.781256191797108e-05, "loss": 0.7093693733215332, "step": 14590 }, { "epoch": 0.08678543193585012, "grad_norm": 1.8271363973617554, "learning_rate": 5.7852189419457104e-05, "loss": 0.7452042579650879, "step": 14600 }, { "epoch": 0.0868448740125185, "grad_norm": 1.6138237714767456, "learning_rate": 5.789181692094314e-05, "loss": 0.736368465423584, "step": 14610 }, { "epoch": 0.08690431608918689, "grad_norm": 1.795030951499939, "learning_rate": 5.7931444422429174e-05, "loss": 0.7213022232055664, "step": 14620 }, { "epoch": 0.08696375816585528, "grad_norm": 1.7647888660430908, "learning_rate": 5.79710719239152e-05, "loss": 0.7310266494750977, "step": 14630 }, { "epoch": 0.08702320024252368, "grad_norm": 1.7260303497314453, "learning_rate": 5.8010699425401224e-05, "loss": 0.7108648300170899, "step": 14640 }, { "epoch": 0.08708264231919206, "grad_norm": 1.7952651977539062, "learning_rate": 5.805032692688726e-05, "loss": 0.7067082405090332, "step": 14650 }, { "epoch": 0.08714208439586045, "grad_norm": 1.33447265625, "learning_rate": 5.8089954428373295e-05, "loss": 0.6933538913726807, "step": 14660 }, { "epoch": 0.08720152647252885, "grad_norm": 2.030564069747925, "learning_rate": 5.812958192985932e-05, "loss": 0.7053693294525146, "step": 14670 }, { "epoch": 0.08726096854919724, "grad_norm": 1.4771804809570312, "learning_rate": 5.816920943134536e-05, "loss": 0.7164829730987549, "step": 14680 }, { "epoch": 0.08732041062586562, "grad_norm": 1.5552579164505005, "learning_rate": 5.820883693283139e-05, "loss": 0.7440321922302247, "step": 14690 }, { "epoch": 0.08737985270253401, "grad_norm": 1.5693451166152954, "learning_rate": 5.8248464434317416e-05, "loss": 0.6501808166503906, "step": 14700 }, { "epoch": 0.08743929477920241, "grad_norm": 1.1812338829040527, "learning_rate": 5.828809193580345e-05, "loss": 0.7215877056121827, "step": 14710 }, { "epoch": 0.0874987368558708, "grad_norm": 1.8963141441345215, "learning_rate": 5.8327719437289486e-05, "loss": 0.7272257804870605, "step": 14720 }, { "epoch": 0.08755817893253919, "grad_norm": 1.766113042831421, "learning_rate": 5.836734693877551e-05, "loss": 0.7429004192352295, "step": 14730 }, { "epoch": 0.08761762100920757, "grad_norm": 1.3633766174316406, "learning_rate": 5.840697444026154e-05, "loss": 0.7750779151916504, "step": 14740 }, { "epoch": 0.08767706308587597, "grad_norm": 1.396079659461975, "learning_rate": 5.844660194174758e-05, "loss": 0.7392534255981446, "step": 14750 }, { "epoch": 0.08773650516254436, "grad_norm": 1.3511879444122314, "learning_rate": 5.848622944323361e-05, "loss": 0.7325668334960938, "step": 14760 }, { "epoch": 0.08779594723921275, "grad_norm": 2.20002818107605, "learning_rate": 5.852585694471964e-05, "loss": 0.7340982913970947, "step": 14770 }, { "epoch": 0.08785538931588113, "grad_norm": 1.6054301261901855, "learning_rate": 5.8565484446205664e-05, "loss": 0.7327771186828613, "step": 14780 }, { "epoch": 0.08791483139254953, "grad_norm": 1.9445476531982422, "learning_rate": 5.86051119476917e-05, "loss": 0.7616429805755616, "step": 14790 }, { "epoch": 0.08797427346921792, "grad_norm": 1.8518569469451904, "learning_rate": 5.8644739449177734e-05, "loss": 0.7022212982177735, "step": 14800 }, { "epoch": 0.0880337155458863, "grad_norm": 1.8570258617401123, "learning_rate": 5.868436695066376e-05, "loss": 0.7535385131835938, "step": 14810 }, { "epoch": 0.08809315762255471, "grad_norm": 1.9161810874938965, "learning_rate": 5.87239944521498e-05, "loss": 0.6967504501342774, "step": 14820 }, { "epoch": 0.0881525996992231, "grad_norm": 1.4875636100769043, "learning_rate": 5.876362195363583e-05, "loss": 0.7340666770935058, "step": 14830 }, { "epoch": 0.08821204177589148, "grad_norm": 1.5736911296844482, "learning_rate": 5.8803249455121855e-05, "loss": 0.7250921726226807, "step": 14840 }, { "epoch": 0.08827148385255987, "grad_norm": 2.8362438678741455, "learning_rate": 5.884287695660789e-05, "loss": 0.7953130722045898, "step": 14850 }, { "epoch": 0.08833092592922827, "grad_norm": 1.6799564361572266, "learning_rate": 5.8882504458093926e-05, "loss": 0.6785358428955078, "step": 14860 }, { "epoch": 0.08839036800589666, "grad_norm": 2.076301336288452, "learning_rate": 5.892213195957995e-05, "loss": 0.7696330070495605, "step": 14870 }, { "epoch": 0.08844981008256504, "grad_norm": 1.9901622533798218, "learning_rate": 5.896175946106598e-05, "loss": 0.7665416717529296, "step": 14880 }, { "epoch": 0.08850925215923343, "grad_norm": 1.6735806465148926, "learning_rate": 5.900138696255202e-05, "loss": 0.735377025604248, "step": 14890 }, { "epoch": 0.08856869423590183, "grad_norm": 1.5744701623916626, "learning_rate": 5.9041014464038046e-05, "loss": 0.6846429824829101, "step": 14900 }, { "epoch": 0.08862813631257022, "grad_norm": 1.4604860544204712, "learning_rate": 5.908064196552408e-05, "loss": 0.7152245998382568, "step": 14910 }, { "epoch": 0.0886875783892386, "grad_norm": 1.8455482721328735, "learning_rate": 5.91202694670101e-05, "loss": 0.7246079444885254, "step": 14920 }, { "epoch": 0.088747020465907, "grad_norm": 1.9249811172485352, "learning_rate": 5.915989696849614e-05, "loss": 0.6873729705810547, "step": 14930 }, { "epoch": 0.08880646254257539, "grad_norm": 1.8519808053970337, "learning_rate": 5.9199524469982174e-05, "loss": 0.7296516418457031, "step": 14940 }, { "epoch": 0.08886590461924378, "grad_norm": 2.8329999446868896, "learning_rate": 5.92391519714682e-05, "loss": 0.7209862232208252, "step": 14950 }, { "epoch": 0.08892534669591216, "grad_norm": 2.116190195083618, "learning_rate": 5.927877947295424e-05, "loss": 0.7330191612243653, "step": 14960 }, { "epoch": 0.08898478877258056, "grad_norm": 1.8537951707839966, "learning_rate": 5.931840697444026e-05, "loss": 0.6800366401672363, "step": 14970 }, { "epoch": 0.08904423084924895, "grad_norm": 1.4881685972213745, "learning_rate": 5.9358034475926295e-05, "loss": 0.7005069255828857, "step": 14980 }, { "epoch": 0.08910367292591734, "grad_norm": 2.5787887573242188, "learning_rate": 5.939766197741232e-05, "loss": 0.7824063777923584, "step": 14990 }, { "epoch": 0.08916311500258572, "grad_norm": 1.5432186126708984, "learning_rate": 5.943728947889836e-05, "loss": 0.7484192371368408, "step": 15000 }, { "epoch": 0.08922255707925413, "grad_norm": 1.8947601318359375, "learning_rate": 5.947691698038439e-05, "loss": 0.7231041431427002, "step": 15010 }, { "epoch": 0.08928199915592251, "grad_norm": 1.525472640991211, "learning_rate": 5.9516544481870415e-05, "loss": 0.7422499656677246, "step": 15020 }, { "epoch": 0.0893414412325909, "grad_norm": 1.4776947498321533, "learning_rate": 5.9556171983356454e-05, "loss": 0.7161260604858398, "step": 15030 }, { "epoch": 0.0894008833092593, "grad_norm": 1.748137354850769, "learning_rate": 5.9595799484842486e-05, "loss": 0.6786980628967285, "step": 15040 }, { "epoch": 0.08946032538592769, "grad_norm": 2.068650960922241, "learning_rate": 5.963542698632851e-05, "loss": 0.7262779235839844, "step": 15050 }, { "epoch": 0.08951976746259607, "grad_norm": 1.7247239351272583, "learning_rate": 5.967505448781454e-05, "loss": 0.7485985279083252, "step": 15060 }, { "epoch": 0.08957920953926446, "grad_norm": 1.713286280632019, "learning_rate": 5.971468198930058e-05, "loss": 0.6955438613891601, "step": 15070 }, { "epoch": 0.08963865161593286, "grad_norm": 1.5336002111434937, "learning_rate": 5.9754309490786607e-05, "loss": 0.7120311260223389, "step": 15080 }, { "epoch": 0.08969809369260125, "grad_norm": 1.682748556137085, "learning_rate": 5.979393699227264e-05, "loss": 0.7065784454345703, "step": 15090 }, { "epoch": 0.08975753576926963, "grad_norm": 1.7124086618423462, "learning_rate": 5.983356449375868e-05, "loss": 0.7266753196716309, "step": 15100 }, { "epoch": 0.08981697784593802, "grad_norm": 2.018482208251953, "learning_rate": 5.98731919952447e-05, "loss": 0.7050704002380371, "step": 15110 }, { "epoch": 0.08987641992260642, "grad_norm": 1.4904738664627075, "learning_rate": 5.9912819496730734e-05, "loss": 0.7449185371398925, "step": 15120 }, { "epoch": 0.08993586199927481, "grad_norm": 1.4538447856903076, "learning_rate": 5.995244699821676e-05, "loss": 0.6981564998626709, "step": 15130 }, { "epoch": 0.0899953040759432, "grad_norm": 2.1652557849884033, "learning_rate": 5.99920744997028e-05, "loss": 0.6717513561248779, "step": 15140 }, { "epoch": 0.09005474615261158, "grad_norm": 1.533021330833435, "learning_rate": 6.003170200118883e-05, "loss": 0.6747695922851562, "step": 15150 }, { "epoch": 0.09011418822927998, "grad_norm": 2.1553308963775635, "learning_rate": 6.0071329502674855e-05, "loss": 0.6862672805786133, "step": 15160 }, { "epoch": 0.09017363030594837, "grad_norm": 1.6133750677108765, "learning_rate": 6.0110957004160893e-05, "loss": 0.7311831951141358, "step": 15170 }, { "epoch": 0.09023307238261676, "grad_norm": 1.5675824880599976, "learning_rate": 6.0150584505646925e-05, "loss": 0.6516722679138184, "step": 15180 }, { "epoch": 0.09029251445928516, "grad_norm": 1.7523760795593262, "learning_rate": 6.019021200713295e-05, "loss": 0.7315805435180665, "step": 15190 }, { "epoch": 0.09035195653595354, "grad_norm": 1.4583263397216797, "learning_rate": 6.022983950861898e-05, "loss": 0.596828556060791, "step": 15200 }, { "epoch": 0.09041139861262193, "grad_norm": 1.7809313535690308, "learning_rate": 6.026946701010502e-05, "loss": 0.696898078918457, "step": 15210 }, { "epoch": 0.09047084068929032, "grad_norm": 1.7706433534622192, "learning_rate": 6.0309094511591046e-05, "loss": 0.7227609634399415, "step": 15220 }, { "epoch": 0.09053028276595872, "grad_norm": 1.6407467126846313, "learning_rate": 6.034872201307708e-05, "loss": 0.7076058864593506, "step": 15230 }, { "epoch": 0.0905897248426271, "grad_norm": 1.8093926906585693, "learning_rate": 6.038834951456312e-05, "loss": 0.728696870803833, "step": 15240 }, { "epoch": 0.09064916691929549, "grad_norm": 1.900300145149231, "learning_rate": 6.042797701604914e-05, "loss": 0.7369925498962402, "step": 15250 }, { "epoch": 0.09070860899596388, "grad_norm": 1.5030690431594849, "learning_rate": 6.046760451753517e-05, "loss": 0.6776715278625488, "step": 15260 }, { "epoch": 0.09076805107263228, "grad_norm": 2.214369058609009, "learning_rate": 6.05072320190212e-05, "loss": 0.6951948165893554, "step": 15270 }, { "epoch": 0.09082749314930066, "grad_norm": 1.4070402383804321, "learning_rate": 6.054685952050724e-05, "loss": 0.7244596481323242, "step": 15280 }, { "epoch": 0.09088693522596905, "grad_norm": 2.0088770389556885, "learning_rate": 6.058648702199326e-05, "loss": 0.7712067604064942, "step": 15290 }, { "epoch": 0.09094637730263745, "grad_norm": 1.579006552696228, "learning_rate": 6.0626114523479294e-05, "loss": 0.7583718299865723, "step": 15300 }, { "epoch": 0.09100581937930584, "grad_norm": 1.3627246618270874, "learning_rate": 6.066574202496533e-05, "loss": 0.7512590408325195, "step": 15310 }, { "epoch": 0.09106526145597423, "grad_norm": 1.8729578256607056, "learning_rate": 6.070536952645136e-05, "loss": 0.7313468933105469, "step": 15320 }, { "epoch": 0.09112470353264261, "grad_norm": 2.153221368789673, "learning_rate": 6.074499702793739e-05, "loss": 0.6708431243896484, "step": 15330 }, { "epoch": 0.09118414560931101, "grad_norm": 1.7322158813476562, "learning_rate": 6.0784624529423415e-05, "loss": 0.759760570526123, "step": 15340 }, { "epoch": 0.0912435876859794, "grad_norm": 1.524327278137207, "learning_rate": 6.0824252030909454e-05, "loss": 0.7040907859802246, "step": 15350 }, { "epoch": 0.09130302976264779, "grad_norm": 1.7150639295578003, "learning_rate": 6.0863879532395486e-05, "loss": 0.7866357803344727, "step": 15360 }, { "epoch": 0.09136247183931617, "grad_norm": 2.332310914993286, "learning_rate": 6.090350703388151e-05, "loss": 0.7826395988464355, "step": 15370 }, { "epoch": 0.09142191391598457, "grad_norm": 1.3948785066604614, "learning_rate": 6.094313453536755e-05, "loss": 0.6874540328979493, "step": 15380 }, { "epoch": 0.09148135599265296, "grad_norm": 1.6143922805786133, "learning_rate": 6.098276203685358e-05, "loss": 0.6937433242797851, "step": 15390 }, { "epoch": 0.09154079806932135, "grad_norm": 1.457518219947815, "learning_rate": 6.1022389538339606e-05, "loss": 0.6944561004638672, "step": 15400 }, { "epoch": 0.09160024014598973, "grad_norm": 2.0437276363372803, "learning_rate": 6.106201703982564e-05, "loss": 0.7045280456542968, "step": 15410 }, { "epoch": 0.09165968222265813, "grad_norm": 1.7841633558273315, "learning_rate": 6.110164454131168e-05, "loss": 0.7135002136230468, "step": 15420 }, { "epoch": 0.09171912429932652, "grad_norm": 1.5130664110183716, "learning_rate": 6.11412720427977e-05, "loss": 0.6701872825622559, "step": 15430 }, { "epoch": 0.09177856637599491, "grad_norm": 1.6175998449325562, "learning_rate": 6.118089954428373e-05, "loss": 0.7334275245666504, "step": 15440 }, { "epoch": 0.09183800845266331, "grad_norm": 1.50566828250885, "learning_rate": 6.122052704576977e-05, "loss": 0.6830679893493652, "step": 15450 }, { "epoch": 0.0918974505293317, "grad_norm": 1.5948489904403687, "learning_rate": 6.12601545472558e-05, "loss": 0.7445611000061035, "step": 15460 }, { "epoch": 0.09195689260600008, "grad_norm": 1.9490848779678345, "learning_rate": 6.129978204874183e-05, "loss": 0.7054551124572754, "step": 15470 }, { "epoch": 0.09201633468266847, "grad_norm": 1.2714840173721313, "learning_rate": 6.133940955022787e-05, "loss": 0.7434883117675781, "step": 15480 }, { "epoch": 0.09207577675933687, "grad_norm": 1.8921780586242676, "learning_rate": 6.13790370517139e-05, "loss": 0.7151803970336914, "step": 15490 }, { "epoch": 0.09213521883600526, "grad_norm": 2.0910799503326416, "learning_rate": 6.141866455319992e-05, "loss": 0.7396996021270752, "step": 15500 }, { "epoch": 0.09219466091267364, "grad_norm": 1.6452244520187378, "learning_rate": 6.145829205468596e-05, "loss": 0.7255769729614258, "step": 15510 }, { "epoch": 0.09225410298934203, "grad_norm": 1.5740591287612915, "learning_rate": 6.1497919556172e-05, "loss": 0.7007770538330078, "step": 15520 }, { "epoch": 0.09231354506601043, "grad_norm": 1.632840633392334, "learning_rate": 6.153754705765802e-05, "loss": 0.7397689819335938, "step": 15530 }, { "epoch": 0.09237298714267882, "grad_norm": 1.538310170173645, "learning_rate": 6.157717455914405e-05, "loss": 0.6670351982116699, "step": 15540 }, { "epoch": 0.0924324292193472, "grad_norm": 1.8492738008499146, "learning_rate": 6.161680206063008e-05, "loss": 0.6835104942321777, "step": 15550 }, { "epoch": 0.0924918712960156, "grad_norm": 1.8130439519882202, "learning_rate": 6.165642956211611e-05, "loss": 0.6695481300354004, "step": 15560 }, { "epoch": 0.09255131337268399, "grad_norm": 1.665363073348999, "learning_rate": 6.169605706360215e-05, "loss": 0.7683393478393554, "step": 15570 }, { "epoch": 0.09261075544935238, "grad_norm": 2.1559641361236572, "learning_rate": 6.173568456508817e-05, "loss": 0.7325561046600342, "step": 15580 }, { "epoch": 0.09267019752602076, "grad_norm": 1.4803075790405273, "learning_rate": 6.177531206657421e-05, "loss": 0.7120468139648437, "step": 15590 }, { "epoch": 0.09272963960268917, "grad_norm": 4.109151840209961, "learning_rate": 6.181493956806024e-05, "loss": 0.6736915588378907, "step": 15600 }, { "epoch": 0.09278908167935755, "grad_norm": 1.3065134286880493, "learning_rate": 6.185456706954626e-05, "loss": 0.7279890060424805, "step": 15610 }, { "epoch": 0.09284852375602594, "grad_norm": 1.8635112047195435, "learning_rate": 6.18941945710323e-05, "loss": 0.7275603771209717, "step": 15620 }, { "epoch": 0.09290796583269433, "grad_norm": 1.9627878665924072, "learning_rate": 6.193382207251833e-05, "loss": 0.7755270957946777, "step": 15630 }, { "epoch": 0.09296740790936273, "grad_norm": 1.6024940013885498, "learning_rate": 6.197344957400436e-05, "loss": 0.7086980819702149, "step": 15640 }, { "epoch": 0.09302684998603111, "grad_norm": 1.5012258291244507, "learning_rate": 6.201307707549039e-05, "loss": 0.7074000358581543, "step": 15650 }, { "epoch": 0.0930862920626995, "grad_norm": 1.5752090215682983, "learning_rate": 6.205270457697643e-05, "loss": 0.7233011722564697, "step": 15660 }, { "epoch": 0.09314573413936789, "grad_norm": 1.3866609334945679, "learning_rate": 6.209233207846245e-05, "loss": 0.6811361312866211, "step": 15670 }, { "epoch": 0.09320517621603629, "grad_norm": 1.918784499168396, "learning_rate": 6.213195957994848e-05, "loss": 0.6865851402282714, "step": 15680 }, { "epoch": 0.09326461829270467, "grad_norm": 1.8337754011154175, "learning_rate": 6.217158708143452e-05, "loss": 0.6801094055175781, "step": 15690 }, { "epoch": 0.09332406036937306, "grad_norm": 1.6778584718704224, "learning_rate": 6.221121458292056e-05, "loss": 0.6799785614013671, "step": 15700 }, { "epoch": 0.09338350244604146, "grad_norm": 1.4272090196609497, "learning_rate": 6.225084208440658e-05, "loss": 0.7197154998779297, "step": 15710 }, { "epoch": 0.09344294452270985, "grad_norm": 1.4795764684677124, "learning_rate": 6.22904695858926e-05, "loss": 0.6341075897216797, "step": 15720 }, { "epoch": 0.09350238659937823, "grad_norm": 1.8594691753387451, "learning_rate": 6.233009708737864e-05, "loss": 0.7193895816802979, "step": 15730 }, { "epoch": 0.09356182867604662, "grad_norm": 1.759678602218628, "learning_rate": 6.236972458886467e-05, "loss": 0.7273081302642822, "step": 15740 }, { "epoch": 0.09362127075271502, "grad_norm": 1.5678787231445312, "learning_rate": 6.240935209035071e-05, "loss": 0.6943951606750488, "step": 15750 }, { "epoch": 0.09368071282938341, "grad_norm": 1.6845322847366333, "learning_rate": 6.244897959183675e-05, "loss": 0.7079980850219727, "step": 15760 }, { "epoch": 0.0937401549060518, "grad_norm": 1.4374115467071533, "learning_rate": 6.248860709332277e-05, "loss": 0.6797304630279541, "step": 15770 }, { "epoch": 0.09379959698272018, "grad_norm": 1.7190089225769043, "learning_rate": 6.25282345948088e-05, "loss": 0.7317852020263672, "step": 15780 }, { "epoch": 0.09385903905938858, "grad_norm": 1.6924856901168823, "learning_rate": 6.256786209629482e-05, "loss": 0.7266695499420166, "step": 15790 }, { "epoch": 0.09391848113605697, "grad_norm": 1.901313066482544, "learning_rate": 6.260748959778086e-05, "loss": 0.7043012142181396, "step": 15800 }, { "epoch": 0.09397792321272536, "grad_norm": 2.119347333908081, "learning_rate": 6.26471170992669e-05, "loss": 0.7543966770172119, "step": 15810 }, { "epoch": 0.09403736528939376, "grad_norm": 1.6902786493301392, "learning_rate": 6.268674460075292e-05, "loss": 0.6948487758636475, "step": 15820 }, { "epoch": 0.09409680736606214, "grad_norm": 1.943078875541687, "learning_rate": 6.272637210223896e-05, "loss": 0.6599225521087646, "step": 15830 }, { "epoch": 0.09415624944273053, "grad_norm": 1.9941262006759644, "learning_rate": 6.276599960372499e-05, "loss": 0.6909358024597168, "step": 15840 }, { "epoch": 0.09421569151939892, "grad_norm": 1.615144968032837, "learning_rate": 6.280562710521101e-05, "loss": 0.7041247367858887, "step": 15850 }, { "epoch": 0.09427513359606732, "grad_norm": 1.5907472372055054, "learning_rate": 6.284525460669705e-05, "loss": 0.7587398529052735, "step": 15860 }, { "epoch": 0.0943345756727357, "grad_norm": 2.448423385620117, "learning_rate": 6.288488210818309e-05, "loss": 0.6331651210784912, "step": 15870 }, { "epoch": 0.09439401774940409, "grad_norm": 1.8100451231002808, "learning_rate": 6.292450960966912e-05, "loss": 0.6559524059295654, "step": 15880 }, { "epoch": 0.09445345982607248, "grad_norm": 1.8692643642425537, "learning_rate": 6.296413711115514e-05, "loss": 0.7107820510864258, "step": 15890 }, { "epoch": 0.09451290190274088, "grad_norm": 1.91883385181427, "learning_rate": 6.300376461264118e-05, "loss": 0.698900842666626, "step": 15900 }, { "epoch": 0.09457234397940927, "grad_norm": 1.8094367980957031, "learning_rate": 6.30433921141272e-05, "loss": 0.7374825477600098, "step": 15910 }, { "epoch": 0.09463178605607765, "grad_norm": 1.649275302886963, "learning_rate": 6.308301961561323e-05, "loss": 0.7609164714813232, "step": 15920 }, { "epoch": 0.09469122813274605, "grad_norm": 1.651183843612671, "learning_rate": 6.312264711709927e-05, "loss": 0.657985782623291, "step": 15930 }, { "epoch": 0.09475067020941444, "grad_norm": 1.7593201398849487, "learning_rate": 6.316227461858531e-05, "loss": 0.7471687316894531, "step": 15940 }, { "epoch": 0.09481011228608283, "grad_norm": 1.4657526016235352, "learning_rate": 6.320190212007133e-05, "loss": 0.6859705924987793, "step": 15950 }, { "epoch": 0.09486955436275121, "grad_norm": 1.5005214214324951, "learning_rate": 6.324152962155736e-05, "loss": 0.701115608215332, "step": 15960 }, { "epoch": 0.09492899643941961, "grad_norm": 1.993727684020996, "learning_rate": 6.32811571230434e-05, "loss": 0.7147175788879394, "step": 15970 }, { "epoch": 0.094988438516088, "grad_norm": 1.670088291168213, "learning_rate": 6.332078462452942e-05, "loss": 0.6890007019042969, "step": 15980 }, { "epoch": 0.09504788059275639, "grad_norm": 1.8105412721633911, "learning_rate": 6.336041212601546e-05, "loss": 0.6990325927734375, "step": 15990 }, { "epoch": 0.09510732266942477, "grad_norm": 1.6299444437026978, "learning_rate": 6.340003962750149e-05, "loss": 0.6831436157226562, "step": 16000 }, { "epoch": 0.09516676474609317, "grad_norm": 2.388732433319092, "learning_rate": 6.343966712898752e-05, "loss": 0.777467155456543, "step": 16010 }, { "epoch": 0.09522620682276156, "grad_norm": 2.6007766723632812, "learning_rate": 6.347929463047355e-05, "loss": 0.7396860122680664, "step": 16020 }, { "epoch": 0.09528564889942995, "grad_norm": 1.5708986520767212, "learning_rate": 6.351892213195957e-05, "loss": 0.660502815246582, "step": 16030 }, { "epoch": 0.09534509097609833, "grad_norm": 1.5607621669769287, "learning_rate": 6.355854963344561e-05, "loss": 0.7140337467193604, "step": 16040 }, { "epoch": 0.09540453305276674, "grad_norm": 1.7346744537353516, "learning_rate": 6.359817713493165e-05, "loss": 0.7135092735290527, "step": 16050 }, { "epoch": 0.09546397512943512, "grad_norm": 1.8491624593734741, "learning_rate": 6.363780463641768e-05, "loss": 0.6533503532409668, "step": 16060 }, { "epoch": 0.09552341720610351, "grad_norm": 2.143756151199341, "learning_rate": 6.36774321379037e-05, "loss": 0.6467413425445556, "step": 16070 }, { "epoch": 0.09558285928277191, "grad_norm": 1.8159770965576172, "learning_rate": 6.371705963938974e-05, "loss": 0.700867748260498, "step": 16080 }, { "epoch": 0.0956423013594403, "grad_norm": 1.7115627527236938, "learning_rate": 6.375668714087577e-05, "loss": 0.6797921657562256, "step": 16090 }, { "epoch": 0.09570174343610868, "grad_norm": 1.8679028749465942, "learning_rate": 6.37963146423618e-05, "loss": 0.6977671623229981, "step": 16100 }, { "epoch": 0.09576118551277707, "grad_norm": 1.6437110900878906, "learning_rate": 6.383594214384784e-05, "loss": 0.7889039039611816, "step": 16110 }, { "epoch": 0.09582062758944547, "grad_norm": 1.4542717933654785, "learning_rate": 6.387556964533387e-05, "loss": 0.6846884727478028, "step": 16120 }, { "epoch": 0.09588006966611386, "grad_norm": 1.7900121212005615, "learning_rate": 6.391519714681989e-05, "loss": 0.7360495567321778, "step": 16130 }, { "epoch": 0.09593951174278224, "grad_norm": 1.6665470600128174, "learning_rate": 6.395482464830592e-05, "loss": 0.6875755310058593, "step": 16140 }, { "epoch": 0.09599895381945063, "grad_norm": 2.061640977859497, "learning_rate": 6.399445214979196e-05, "loss": 0.8299962043762207, "step": 16150 }, { "epoch": 0.09605839589611903, "grad_norm": 1.6222445964813232, "learning_rate": 6.4034079651278e-05, "loss": 0.7063436031341552, "step": 16160 }, { "epoch": 0.09611783797278742, "grad_norm": 1.7574958801269531, "learning_rate": 6.407370715276402e-05, "loss": 0.6660161972045898, "step": 16170 }, { "epoch": 0.0961772800494558, "grad_norm": 1.724119782447815, "learning_rate": 6.411333465425006e-05, "loss": 0.642866849899292, "step": 16180 }, { "epoch": 0.0962367221261242, "grad_norm": 1.8751554489135742, "learning_rate": 6.415296215573608e-05, "loss": 0.7248832702636718, "step": 16190 }, { "epoch": 0.09629616420279259, "grad_norm": 1.3561972379684448, "learning_rate": 6.419258965722211e-05, "loss": 0.6859522819519043, "step": 16200 }, { "epoch": 0.09635560627946098, "grad_norm": 1.5776437520980835, "learning_rate": 6.423221715870815e-05, "loss": 0.7518596649169922, "step": 16210 }, { "epoch": 0.09641504835612937, "grad_norm": 1.8927878141403198, "learning_rate": 6.427184466019419e-05, "loss": 0.7500032424926758, "step": 16220 }, { "epoch": 0.09647449043279777, "grad_norm": 1.8674721717834473, "learning_rate": 6.431147216168021e-05, "loss": 0.6808150768280029, "step": 16230 }, { "epoch": 0.09653393250946615, "grad_norm": 1.732752799987793, "learning_rate": 6.435109966316624e-05, "loss": 0.7047711372375488, "step": 16240 }, { "epoch": 0.09659337458613454, "grad_norm": 1.5185996294021606, "learning_rate": 6.439072716465228e-05, "loss": 0.7437406539916992, "step": 16250 }, { "epoch": 0.09665281666280293, "grad_norm": 1.8043115139007568, "learning_rate": 6.44303546661383e-05, "loss": 0.7532196521759034, "step": 16260 }, { "epoch": 0.09671225873947133, "grad_norm": 1.1892204284667969, "learning_rate": 6.446998216762433e-05, "loss": 0.6944334506988525, "step": 16270 }, { "epoch": 0.09677170081613971, "grad_norm": 1.4986717700958252, "learning_rate": 6.450960966911036e-05, "loss": 0.651393985748291, "step": 16280 }, { "epoch": 0.0968311428928081, "grad_norm": 1.5514763593673706, "learning_rate": 6.45492371705964e-05, "loss": 0.7558810710906982, "step": 16290 }, { "epoch": 0.09689058496947649, "grad_norm": 1.6022491455078125, "learning_rate": 6.458886467208243e-05, "loss": 0.7421372413635254, "step": 16300 }, { "epoch": 0.09695002704614489, "grad_norm": 1.4717395305633545, "learning_rate": 6.462849217356845e-05, "loss": 0.7156507015228272, "step": 16310 }, { "epoch": 0.09700946912281327, "grad_norm": 1.4115197658538818, "learning_rate": 6.466811967505449e-05, "loss": 0.6508089065551758, "step": 16320 }, { "epoch": 0.09706891119948166, "grad_norm": 1.758362054824829, "learning_rate": 6.470774717654052e-05, "loss": 0.7038816928863525, "step": 16330 }, { "epoch": 0.09712835327615006, "grad_norm": 1.4216035604476929, "learning_rate": 6.474737467802656e-05, "loss": 0.7037358283996582, "step": 16340 }, { "epoch": 0.09718779535281845, "grad_norm": 1.564639925956726, "learning_rate": 6.47870021795126e-05, "loss": 0.7556975364685059, "step": 16350 }, { "epoch": 0.09724723742948684, "grad_norm": 1.8641459941864014, "learning_rate": 6.482662968099862e-05, "loss": 0.7214137554168701, "step": 16360 }, { "epoch": 0.09730667950615522, "grad_norm": 1.8622212409973145, "learning_rate": 6.486625718248464e-05, "loss": 0.6997238636016846, "step": 16370 }, { "epoch": 0.09736612158282362, "grad_norm": 1.5973185300827026, "learning_rate": 6.490588468397067e-05, "loss": 0.6520251750946044, "step": 16380 }, { "epoch": 0.09742556365949201, "grad_norm": 1.6380826234817505, "learning_rate": 6.494551218545671e-05, "loss": 0.7293555259704589, "step": 16390 }, { "epoch": 0.0974850057361604, "grad_norm": 1.7015670537948608, "learning_rate": 6.498513968694275e-05, "loss": 0.7522706985473633, "step": 16400 }, { "epoch": 0.09754444781282878, "grad_norm": 1.6203144788742065, "learning_rate": 6.502476718842877e-05, "loss": 0.7418473720550537, "step": 16410 }, { "epoch": 0.09760388988949718, "grad_norm": 1.7681543827056885, "learning_rate": 6.506439468991481e-05, "loss": 0.6928352355957031, "step": 16420 }, { "epoch": 0.09766333196616557, "grad_norm": 1.5241643190383911, "learning_rate": 6.510402219140084e-05, "loss": 0.7057276248931885, "step": 16430 }, { "epoch": 0.09772277404283396, "grad_norm": 1.6119059324264526, "learning_rate": 6.514364969288686e-05, "loss": 0.7090188503265381, "step": 16440 }, { "epoch": 0.09778221611950236, "grad_norm": 1.7358224391937256, "learning_rate": 6.51832771943729e-05, "loss": 0.7234081268310547, "step": 16450 }, { "epoch": 0.09784165819617074, "grad_norm": 1.7180614471435547, "learning_rate": 6.522290469585894e-05, "loss": 0.7085479259490967, "step": 16460 }, { "epoch": 0.09790110027283913, "grad_norm": 1.726173758506775, "learning_rate": 6.526253219734496e-05, "loss": 0.7134411811828614, "step": 16470 }, { "epoch": 0.09796054234950752, "grad_norm": 1.644991159439087, "learning_rate": 6.530215969883099e-05, "loss": 0.7042584896087647, "step": 16480 }, { "epoch": 0.09801998442617592, "grad_norm": 1.698448657989502, "learning_rate": 6.534178720031703e-05, "loss": 0.676615047454834, "step": 16490 }, { "epoch": 0.0980794265028443, "grad_norm": 1.7863895893096924, "learning_rate": 6.538141470180305e-05, "loss": 0.7006631851196289, "step": 16500 }, { "epoch": 0.09813886857951269, "grad_norm": 1.2055492401123047, "learning_rate": 6.542104220328909e-05, "loss": 0.6881674766540528, "step": 16510 }, { "epoch": 0.09819831065618108, "grad_norm": 1.4084866046905518, "learning_rate": 6.546066970477512e-05, "loss": 0.7189772129058838, "step": 16520 }, { "epoch": 0.09825775273284948, "grad_norm": 1.5109496116638184, "learning_rate": 6.550029720626115e-05, "loss": 0.6827248573303223, "step": 16530 }, { "epoch": 0.09831719480951787, "grad_norm": 1.8998701572418213, "learning_rate": 6.553992470774718e-05, "loss": 0.7882650375366211, "step": 16540 }, { "epoch": 0.09837663688618625, "grad_norm": 1.5011229515075684, "learning_rate": 6.55795522092332e-05, "loss": 0.7422322273254395, "step": 16550 }, { "epoch": 0.09843607896285464, "grad_norm": 1.2004598379135132, "learning_rate": 6.561917971071924e-05, "loss": 0.6816115379333496, "step": 16560 }, { "epoch": 0.09849552103952304, "grad_norm": 1.3592466115951538, "learning_rate": 6.565880721220528e-05, "loss": 0.6365335941314697, "step": 16570 }, { "epoch": 0.09855496311619143, "grad_norm": 1.5730834007263184, "learning_rate": 6.569843471369131e-05, "loss": 0.7164838790893555, "step": 16580 }, { "epoch": 0.09861440519285981, "grad_norm": 1.44269597530365, "learning_rate": 6.573806221517733e-05, "loss": 0.6900529861450195, "step": 16590 }, { "epoch": 0.09867384726952821, "grad_norm": 1.6603468656539917, "learning_rate": 6.577768971666337e-05, "loss": 0.7559622287750244, "step": 16600 }, { "epoch": 0.0987332893461966, "grad_norm": 1.6107438802719116, "learning_rate": 6.58173172181494e-05, "loss": 0.6942702293395996, "step": 16610 }, { "epoch": 0.09879273142286499, "grad_norm": 1.225885272026062, "learning_rate": 6.585694471963542e-05, "loss": 0.7157155990600585, "step": 16620 }, { "epoch": 0.09885217349953337, "grad_norm": 1.5594532489776611, "learning_rate": 6.589657222112147e-05, "loss": 0.7601263999938965, "step": 16630 }, { "epoch": 0.09891161557620178, "grad_norm": 1.3719109296798706, "learning_rate": 6.59361997226075e-05, "loss": 0.7337074279785156, "step": 16640 }, { "epoch": 0.09897105765287016, "grad_norm": 1.32200026512146, "learning_rate": 6.597582722409352e-05, "loss": 0.6912988662719727, "step": 16650 }, { "epoch": 0.09903049972953855, "grad_norm": 1.5411269664764404, "learning_rate": 6.601545472557955e-05, "loss": 0.7253127574920655, "step": 16660 }, { "epoch": 0.09908994180620694, "grad_norm": 1.4151825904846191, "learning_rate": 6.605508222706559e-05, "loss": 0.6521742820739747, "step": 16670 }, { "epoch": 0.09914938388287534, "grad_norm": 1.738136649131775, "learning_rate": 6.609470972855161e-05, "loss": 0.658449363708496, "step": 16680 }, { "epoch": 0.09920882595954372, "grad_norm": 1.4400347471237183, "learning_rate": 6.613433723003765e-05, "loss": 0.6421197891235352, "step": 16690 }, { "epoch": 0.09926826803621211, "grad_norm": 1.4543336629867554, "learning_rate": 6.617396473152369e-05, "loss": 0.68808012008667, "step": 16700 }, { "epoch": 0.09932771011288051, "grad_norm": 3.664555072784424, "learning_rate": 6.621359223300971e-05, "loss": 0.7503412246704102, "step": 16710 }, { "epoch": 0.0993871521895489, "grad_norm": 1.6346865892410278, "learning_rate": 6.625321973449574e-05, "loss": 0.7395191669464112, "step": 16720 }, { "epoch": 0.09944659426621728, "grad_norm": 1.6661694049835205, "learning_rate": 6.629284723598176e-05, "loss": 0.7188557624816895, "step": 16730 }, { "epoch": 0.09950603634288567, "grad_norm": 2.0756986141204834, "learning_rate": 6.63324747374678e-05, "loss": 0.7589842796325683, "step": 16740 }, { "epoch": 0.09956547841955407, "grad_norm": 1.9887129068374634, "learning_rate": 6.637210223895384e-05, "loss": 0.6725711345672607, "step": 16750 }, { "epoch": 0.09962492049622246, "grad_norm": 1.685405969619751, "learning_rate": 6.641172974043987e-05, "loss": 0.756993293762207, "step": 16760 }, { "epoch": 0.09968436257289084, "grad_norm": 1.7415409088134766, "learning_rate": 6.64513572419259e-05, "loss": 0.7202177047729492, "step": 16770 }, { "epoch": 0.09974380464955923, "grad_norm": 1.8484965562820435, "learning_rate": 6.649098474341193e-05, "loss": 0.6995764255523682, "step": 16780 }, { "epoch": 0.09980324672622763, "grad_norm": 1.542739987373352, "learning_rate": 6.653061224489796e-05, "loss": 0.6836113929748535, "step": 16790 }, { "epoch": 0.09986268880289602, "grad_norm": 1.5504488945007324, "learning_rate": 6.6570239746384e-05, "loss": 0.6660830020904541, "step": 16800 }, { "epoch": 0.0999221308795644, "grad_norm": 1.7439930438995361, "learning_rate": 6.660986724787003e-05, "loss": 0.7240962982177734, "step": 16810 }, { "epoch": 0.09998157295623279, "grad_norm": 1.9344160556793213, "learning_rate": 6.664949474935606e-05, "loss": 0.6886816024780273, "step": 16820 }, { "epoch": 0.10004101503290119, "grad_norm": 1.706525444984436, "learning_rate": 6.668912225084208e-05, "loss": 0.7190671443939209, "step": 16830 }, { "epoch": 0.10010045710956958, "grad_norm": 1.69204580783844, "learning_rate": 6.672874975232812e-05, "loss": 0.7541735649108887, "step": 16840 }, { "epoch": 0.10015989918623797, "grad_norm": 1.5173038244247437, "learning_rate": 6.676837725381415e-05, "loss": 0.6856198310852051, "step": 16850 }, { "epoch": 0.10021934126290637, "grad_norm": 1.7328581809997559, "learning_rate": 6.680800475530019e-05, "loss": 0.7341518402099609, "step": 16860 }, { "epoch": 0.10027878333957475, "grad_norm": 1.5988349914550781, "learning_rate": 6.684763225678621e-05, "loss": 0.7458541870117188, "step": 16870 }, { "epoch": 0.10033822541624314, "grad_norm": 1.8814359903335571, "learning_rate": 6.688725975827225e-05, "loss": 0.7414980411529541, "step": 16880 }, { "epoch": 0.10039766749291153, "grad_norm": 1.7861125469207764, "learning_rate": 6.692688725975827e-05, "loss": 0.7946866989135742, "step": 16890 }, { "epoch": 0.10045710956957993, "grad_norm": 1.6046326160430908, "learning_rate": 6.69665147612443e-05, "loss": 0.6869937419891358, "step": 16900 }, { "epoch": 0.10051655164624831, "grad_norm": 1.7289035320281982, "learning_rate": 6.700614226273034e-05, "loss": 0.6798139095306397, "step": 16910 }, { "epoch": 0.1005759937229167, "grad_norm": 1.5792144536972046, "learning_rate": 6.704576976421638e-05, "loss": 0.7176982879638671, "step": 16920 }, { "epoch": 0.10063543579958509, "grad_norm": 1.5312587022781372, "learning_rate": 6.70853972657024e-05, "loss": 0.6667826652526856, "step": 16930 }, { "epoch": 0.10069487787625349, "grad_norm": 1.4072542190551758, "learning_rate": 6.712502476718843e-05, "loss": 0.6775052547454834, "step": 16940 }, { "epoch": 0.10075431995292188, "grad_norm": 1.4756073951721191, "learning_rate": 6.716465226867447e-05, "loss": 0.6516561508178711, "step": 16950 }, { "epoch": 0.10081376202959026, "grad_norm": 1.7087408304214478, "learning_rate": 6.720427977016049e-05, "loss": 0.7226776599884033, "step": 16960 }, { "epoch": 0.10087320410625866, "grad_norm": 1.975490689277649, "learning_rate": 6.724390727164652e-05, "loss": 0.7298770904541015, "step": 16970 }, { "epoch": 0.10093264618292705, "grad_norm": 1.5847951173782349, "learning_rate": 6.728353477313256e-05, "loss": 0.704246997833252, "step": 16980 }, { "epoch": 0.10099208825959544, "grad_norm": 1.7697943449020386, "learning_rate": 6.73231622746186e-05, "loss": 0.7219916820526123, "step": 16990 }, { "epoch": 0.10105153033626382, "grad_norm": 1.450270414352417, "learning_rate": 6.736278977610462e-05, "loss": 0.6618513107299805, "step": 17000 }, { "epoch": 0.10111097241293222, "grad_norm": 1.6661105155944824, "learning_rate": 6.740241727759064e-05, "loss": 0.7322173118591309, "step": 17010 }, { "epoch": 0.10117041448960061, "grad_norm": 1.693818211555481, "learning_rate": 6.744204477907668e-05, "loss": 0.7075785636901856, "step": 17020 }, { "epoch": 0.101229856566269, "grad_norm": 1.4500712156295776, "learning_rate": 6.748167228056271e-05, "loss": 0.6986178398132324, "step": 17030 }, { "epoch": 0.10128929864293738, "grad_norm": 1.6574653387069702, "learning_rate": 6.752129978204875e-05, "loss": 0.7350696563720703, "step": 17040 }, { "epoch": 0.10134874071960578, "grad_norm": 1.7686738967895508, "learning_rate": 6.756092728353478e-05, "loss": 0.6648402214050293, "step": 17050 }, { "epoch": 0.10140818279627417, "grad_norm": 1.7707427740097046, "learning_rate": 6.760055478502081e-05, "loss": 0.7570142269134521, "step": 17060 }, { "epoch": 0.10146762487294256, "grad_norm": 1.7787976264953613, "learning_rate": 6.764018228650684e-05, "loss": 0.6822936058044433, "step": 17070 }, { "epoch": 0.10152706694961096, "grad_norm": 1.6032849550247192, "learning_rate": 6.767980978799286e-05, "loss": 0.7020768165588379, "step": 17080 }, { "epoch": 0.10158650902627935, "grad_norm": 1.628947138786316, "learning_rate": 6.77194372894789e-05, "loss": 0.6437324523925781, "step": 17090 }, { "epoch": 0.10164595110294773, "grad_norm": 1.609648585319519, "learning_rate": 6.775906479096494e-05, "loss": 0.7333159446716309, "step": 17100 }, { "epoch": 0.10170539317961612, "grad_norm": 1.428541660308838, "learning_rate": 6.779869229245096e-05, "loss": 0.7232214927673339, "step": 17110 }, { "epoch": 0.10176483525628452, "grad_norm": 1.4101622104644775, "learning_rate": 6.7838319793937e-05, "loss": 0.6727132797241211, "step": 17120 }, { "epoch": 0.1018242773329529, "grad_norm": 1.979219675064087, "learning_rate": 6.787794729542303e-05, "loss": 0.7343820571899414, "step": 17130 }, { "epoch": 0.10188371940962129, "grad_norm": 1.4261304140090942, "learning_rate": 6.791757479690905e-05, "loss": 0.7029624462127686, "step": 17140 }, { "epoch": 0.10194316148628968, "grad_norm": 1.339126706123352, "learning_rate": 6.795720229839509e-05, "loss": 0.6578073501586914, "step": 17150 }, { "epoch": 0.10200260356295808, "grad_norm": 1.2662361860275269, "learning_rate": 6.799682979988113e-05, "loss": 0.6501790046691894, "step": 17160 }, { "epoch": 0.10206204563962647, "grad_norm": 1.3915923833847046, "learning_rate": 6.803645730136715e-05, "loss": 0.7538990020751953, "step": 17170 }, { "epoch": 0.10212148771629485, "grad_norm": 1.6382008790969849, "learning_rate": 6.807608480285318e-05, "loss": 0.7258347034454345, "step": 17180 }, { "epoch": 0.10218092979296324, "grad_norm": 1.5369658470153809, "learning_rate": 6.811571230433922e-05, "loss": 0.7117903709411622, "step": 17190 }, { "epoch": 0.10224037186963164, "grad_norm": 1.2505959272384644, "learning_rate": 6.815533980582524e-05, "loss": 0.667765998840332, "step": 17200 }, { "epoch": 0.10229981394630003, "grad_norm": 2.2484190464019775, "learning_rate": 6.819496730731128e-05, "loss": 0.6824183464050293, "step": 17210 }, { "epoch": 0.10235925602296841, "grad_norm": 1.3083773851394653, "learning_rate": 6.823459480879732e-05, "loss": 0.7711653232574462, "step": 17220 }, { "epoch": 0.10241869809963682, "grad_norm": 1.9262118339538574, "learning_rate": 6.827422231028335e-05, "loss": 0.6873745918273926, "step": 17230 }, { "epoch": 0.1024781401763052, "grad_norm": 1.5944513082504272, "learning_rate": 6.831384981176937e-05, "loss": 0.7350177764892578, "step": 17240 }, { "epoch": 0.10253758225297359, "grad_norm": 1.5603634119033813, "learning_rate": 6.83534773132554e-05, "loss": 0.7259055137634277, "step": 17250 }, { "epoch": 0.10259702432964198, "grad_norm": 1.4630383253097534, "learning_rate": 6.839310481474143e-05, "loss": 0.7231840133666992, "step": 17260 }, { "epoch": 0.10265646640631038, "grad_norm": 1.5269060134887695, "learning_rate": 6.843273231622746e-05, "loss": 0.7317699909210205, "step": 17270 }, { "epoch": 0.10271590848297876, "grad_norm": 1.6821846961975098, "learning_rate": 6.84723598177135e-05, "loss": 0.7049837112426758, "step": 17280 }, { "epoch": 0.10277535055964715, "grad_norm": 1.7123008966445923, "learning_rate": 6.851198731919954e-05, "loss": 0.7206304550170899, "step": 17290 }, { "epoch": 0.10283479263631554, "grad_norm": 1.2670232057571411, "learning_rate": 6.855161482068556e-05, "loss": 0.6438730239868165, "step": 17300 }, { "epoch": 0.10289423471298394, "grad_norm": 1.7239503860473633, "learning_rate": 6.859124232217159e-05, "loss": 0.6745787620544433, "step": 17310 }, { "epoch": 0.10295367678965232, "grad_norm": 1.478253960609436, "learning_rate": 6.863086982365761e-05, "loss": 0.7067014217376709, "step": 17320 }, { "epoch": 0.10301311886632071, "grad_norm": 1.4348150491714478, "learning_rate": 6.867049732514365e-05, "loss": 0.6555452346801758, "step": 17330 }, { "epoch": 0.10307256094298911, "grad_norm": 1.598923921585083, "learning_rate": 6.871012482662969e-05, "loss": 0.7086836814880371, "step": 17340 }, { "epoch": 0.1031320030196575, "grad_norm": 1.4491493701934814, "learning_rate": 6.874975232811571e-05, "loss": 0.6980886459350586, "step": 17350 }, { "epoch": 0.10319144509632588, "grad_norm": 1.8832095861434937, "learning_rate": 6.878937982960175e-05, "loss": 0.6861403465270997, "step": 17360 }, { "epoch": 0.10325088717299427, "grad_norm": 1.441741943359375, "learning_rate": 6.882900733108778e-05, "loss": 0.6383812904357911, "step": 17370 }, { "epoch": 0.10331032924966267, "grad_norm": 1.4196196794509888, "learning_rate": 6.88686348325738e-05, "loss": 0.7226063251495362, "step": 17380 }, { "epoch": 0.10336977132633106, "grad_norm": 1.903537631034851, "learning_rate": 6.890826233405984e-05, "loss": 0.7203210830688477, "step": 17390 }, { "epoch": 0.10342921340299945, "grad_norm": 1.772778868675232, "learning_rate": 6.894788983554588e-05, "loss": 0.7631679534912109, "step": 17400 }, { "epoch": 0.10348865547966783, "grad_norm": 1.5635825395584106, "learning_rate": 6.89875173370319e-05, "loss": 0.7388660430908203, "step": 17410 }, { "epoch": 0.10354809755633623, "grad_norm": 1.338199257850647, "learning_rate": 6.902714483851793e-05, "loss": 0.6792194366455078, "step": 17420 }, { "epoch": 0.10360753963300462, "grad_norm": 1.3650254011154175, "learning_rate": 6.906677234000397e-05, "loss": 0.7107223510742188, "step": 17430 }, { "epoch": 0.103666981709673, "grad_norm": 1.8211004734039307, "learning_rate": 6.910639984149e-05, "loss": 0.7738454818725586, "step": 17440 }, { "epoch": 0.10372642378634139, "grad_norm": 1.4427053928375244, "learning_rate": 6.914602734297603e-05, "loss": 0.7124999523162842, "step": 17450 }, { "epoch": 0.1037858658630098, "grad_norm": 1.6190390586853027, "learning_rate": 6.918565484446206e-05, "loss": 0.7139138221740723, "step": 17460 }, { "epoch": 0.10384530793967818, "grad_norm": 1.9146393537521362, "learning_rate": 6.92252823459481e-05, "loss": 0.7320779800415039, "step": 17470 }, { "epoch": 0.10390475001634657, "grad_norm": 1.5605326890945435, "learning_rate": 6.926490984743412e-05, "loss": 0.7230198860168457, "step": 17480 }, { "epoch": 0.10396419209301497, "grad_norm": 1.6354033946990967, "learning_rate": 6.930453734892015e-05, "loss": 0.6726067066192627, "step": 17490 }, { "epoch": 0.10402363416968335, "grad_norm": 1.206161618232727, "learning_rate": 6.934416485040619e-05, "loss": 0.7458469867706299, "step": 17500 }, { "epoch": 0.10408307624635174, "grad_norm": 1.7268773317337036, "learning_rate": 6.938379235189222e-05, "loss": 0.6696142196655274, "step": 17510 }, { "epoch": 0.10414251832302013, "grad_norm": 1.5000075101852417, "learning_rate": 6.942341985337825e-05, "loss": 0.7257611751556396, "step": 17520 }, { "epoch": 0.10420196039968853, "grad_norm": 2.1040239334106445, "learning_rate": 6.946304735486427e-05, "loss": 0.778196382522583, "step": 17530 }, { "epoch": 0.10426140247635692, "grad_norm": 1.7652955055236816, "learning_rate": 6.950267485635031e-05, "loss": 0.738511610031128, "step": 17540 }, { "epoch": 0.1043208445530253, "grad_norm": 1.5395286083221436, "learning_rate": 6.954230235783634e-05, "loss": 0.7857234954833985, "step": 17550 }, { "epoch": 0.10438028662969369, "grad_norm": 1.5724745988845825, "learning_rate": 6.958192985932236e-05, "loss": 0.7491714954376221, "step": 17560 }, { "epoch": 0.10443972870636209, "grad_norm": 1.9178787469863892, "learning_rate": 6.962155736080842e-05, "loss": 0.6962545394897461, "step": 17570 }, { "epoch": 0.10449917078303048, "grad_norm": 2.0012590885162354, "learning_rate": 6.966118486229444e-05, "loss": 0.6853448867797851, "step": 17580 }, { "epoch": 0.10455861285969886, "grad_norm": 1.343247413635254, "learning_rate": 6.970081236378047e-05, "loss": 0.6833686828613281, "step": 17590 }, { "epoch": 0.10461805493636726, "grad_norm": 1.8702099323272705, "learning_rate": 6.974043986526649e-05, "loss": 0.6948769569396973, "step": 17600 }, { "epoch": 0.10467749701303565, "grad_norm": 1.580968976020813, "learning_rate": 6.978006736675253e-05, "loss": 0.6902650833129883, "step": 17610 }, { "epoch": 0.10473693908970404, "grad_norm": 1.6497085094451904, "learning_rate": 6.981969486823855e-05, "loss": 0.6782565116882324, "step": 17620 }, { "epoch": 0.10479638116637242, "grad_norm": 1.8961493968963623, "learning_rate": 6.98593223697246e-05, "loss": 0.642571210861206, "step": 17630 }, { "epoch": 0.10485582324304082, "grad_norm": 1.6481214761734009, "learning_rate": 6.989894987121063e-05, "loss": 0.6885931015014648, "step": 17640 }, { "epoch": 0.10491526531970921, "grad_norm": 1.5191386938095093, "learning_rate": 6.993857737269666e-05, "loss": 0.7734432220458984, "step": 17650 }, { "epoch": 0.1049747073963776, "grad_norm": 1.5618442296981812, "learning_rate": 6.997820487418268e-05, "loss": 0.6379929065704346, "step": 17660 }, { "epoch": 0.10503414947304598, "grad_norm": 1.7839069366455078, "learning_rate": 7.001783237566871e-05, "loss": 0.7524025917053223, "step": 17670 }, { "epoch": 0.10509359154971439, "grad_norm": 1.4638334512710571, "learning_rate": 7.005745987715475e-05, "loss": 0.7050505638122558, "step": 17680 }, { "epoch": 0.10515303362638277, "grad_norm": 1.6295584440231323, "learning_rate": 7.009708737864078e-05, "loss": 0.6203771591186523, "step": 17690 }, { "epoch": 0.10521247570305116, "grad_norm": 1.9933327436447144, "learning_rate": 7.013671488012681e-05, "loss": 0.675936508178711, "step": 17700 }, { "epoch": 0.10527191777971955, "grad_norm": 1.9854310750961304, "learning_rate": 7.017634238161285e-05, "loss": 0.7381853103637696, "step": 17710 }, { "epoch": 0.10533135985638795, "grad_norm": 1.423058032989502, "learning_rate": 7.021596988309887e-05, "loss": 0.7154651641845703, "step": 17720 }, { "epoch": 0.10539080193305633, "grad_norm": 1.9511114358901978, "learning_rate": 7.02555973845849e-05, "loss": 0.6957616806030273, "step": 17730 }, { "epoch": 0.10545024400972472, "grad_norm": 1.2806302309036255, "learning_rate": 7.029522488607094e-05, "loss": 0.6584025859832764, "step": 17740 }, { "epoch": 0.10550968608639312, "grad_norm": 1.6906428337097168, "learning_rate": 7.033485238755698e-05, "loss": 0.6708545207977294, "step": 17750 }, { "epoch": 0.1055691281630615, "grad_norm": 1.1568756103515625, "learning_rate": 7.0374479889043e-05, "loss": 0.7233322143554688, "step": 17760 }, { "epoch": 0.1056285702397299, "grad_norm": 1.619712471961975, "learning_rate": 7.041410739052903e-05, "loss": 0.7594078063964844, "step": 17770 }, { "epoch": 0.10568801231639828, "grad_norm": 1.5352452993392944, "learning_rate": 7.045373489201506e-05, "loss": 0.6545253753662109, "step": 17780 }, { "epoch": 0.10574745439306668, "grad_norm": 1.5232197046279907, "learning_rate": 7.049336239350109e-05, "loss": 0.7091272354125977, "step": 17790 }, { "epoch": 0.10580689646973507, "grad_norm": 1.5416783094406128, "learning_rate": 7.053298989498713e-05, "loss": 0.7423151016235352, "step": 17800 }, { "epoch": 0.10586633854640345, "grad_norm": 1.8424326181411743, "learning_rate": 7.057261739647315e-05, "loss": 0.7354015350341797, "step": 17810 }, { "epoch": 0.10592578062307184, "grad_norm": 1.605089545249939, "learning_rate": 7.061224489795919e-05, "loss": 0.640697431564331, "step": 17820 }, { "epoch": 0.10598522269974024, "grad_norm": 1.657938838005066, "learning_rate": 7.065187239944522e-05, "loss": 0.6543495655059814, "step": 17830 }, { "epoch": 0.10604466477640863, "grad_norm": 1.6436883211135864, "learning_rate": 7.069149990093124e-05, "loss": 0.6973817825317383, "step": 17840 }, { "epoch": 0.10610410685307702, "grad_norm": 1.7241642475128174, "learning_rate": 7.073112740241728e-05, "loss": 0.7195716857910156, "step": 17850 }, { "epoch": 0.10616354892974542, "grad_norm": 1.4986066818237305, "learning_rate": 7.077075490390332e-05, "loss": 0.7208251953125, "step": 17860 }, { "epoch": 0.1062229910064138, "grad_norm": 1.5098916292190552, "learning_rate": 7.081038240538934e-05, "loss": 0.7147454261779785, "step": 17870 }, { "epoch": 0.10628243308308219, "grad_norm": 1.489816427230835, "learning_rate": 7.085000990687537e-05, "loss": 0.68856840133667, "step": 17880 }, { "epoch": 0.10634187515975058, "grad_norm": 1.662302017211914, "learning_rate": 7.088963740836141e-05, "loss": 0.7677824974060059, "step": 17890 }, { "epoch": 0.10640131723641898, "grad_norm": 1.8159687519073486, "learning_rate": 7.092926490984743e-05, "loss": 0.7232883930206299, "step": 17900 }, { "epoch": 0.10646075931308736, "grad_norm": 1.7022786140441895, "learning_rate": 7.096889241133346e-05, "loss": 0.706417179107666, "step": 17910 }, { "epoch": 0.10652020138975575, "grad_norm": 1.8550773859024048, "learning_rate": 7.100851991281951e-05, "loss": 0.7106013774871827, "step": 17920 }, { "epoch": 0.10657964346642414, "grad_norm": 1.5616856813430786, "learning_rate": 7.104814741430554e-05, "loss": 0.66239013671875, "step": 17930 }, { "epoch": 0.10663908554309254, "grad_norm": 1.7755073308944702, "learning_rate": 7.108777491579156e-05, "loss": 0.7398879051208496, "step": 17940 }, { "epoch": 0.10669852761976092, "grad_norm": 1.572067141532898, "learning_rate": 7.112740241727759e-05, "loss": 0.6845314025878906, "step": 17950 }, { "epoch": 0.10675796969642931, "grad_norm": 1.7119715213775635, "learning_rate": 7.116702991876362e-05, "loss": 0.7202382564544678, "step": 17960 }, { "epoch": 0.10681741177309771, "grad_norm": 1.6339690685272217, "learning_rate": 7.120665742024965e-05, "loss": 0.6967203140258789, "step": 17970 }, { "epoch": 0.1068768538497661, "grad_norm": 1.8390655517578125, "learning_rate": 7.124628492173569e-05, "loss": 0.7838476181030274, "step": 17980 }, { "epoch": 0.10693629592643449, "grad_norm": 1.7717530727386475, "learning_rate": 7.128591242322173e-05, "loss": 0.7636804580688477, "step": 17990 }, { "epoch": 0.10699573800310287, "grad_norm": 1.5774463415145874, "learning_rate": 7.132553992470775e-05, "loss": 0.68956298828125, "step": 18000 }, { "epoch": 0.10705518007977127, "grad_norm": 1.851232886314392, "learning_rate": 7.136516742619378e-05, "loss": 0.709386157989502, "step": 18010 }, { "epoch": 0.10711462215643966, "grad_norm": 1.2726998329162598, "learning_rate": 7.14047949276798e-05, "loss": 0.6821889400482177, "step": 18020 }, { "epoch": 0.10717406423310805, "grad_norm": 1.5054457187652588, "learning_rate": 7.144442242916584e-05, "loss": 0.6691884517669677, "step": 18030 }, { "epoch": 0.10723350630977643, "grad_norm": 1.1617639064788818, "learning_rate": 7.148404993065188e-05, "loss": 0.6721649169921875, "step": 18040 }, { "epoch": 0.10729294838644483, "grad_norm": 1.6693661212921143, "learning_rate": 7.15236774321379e-05, "loss": 0.7111573219299316, "step": 18050 }, { "epoch": 0.10735239046311322, "grad_norm": 1.3066051006317139, "learning_rate": 7.156330493362394e-05, "loss": 0.7350843906402588, "step": 18060 }, { "epoch": 0.10741183253978161, "grad_norm": 1.189837098121643, "learning_rate": 7.160293243510997e-05, "loss": 0.7073513984680175, "step": 18070 }, { "epoch": 0.10747127461645, "grad_norm": 1.8984854221343994, "learning_rate": 7.1642559936596e-05, "loss": 0.6791913032531738, "step": 18080 }, { "epoch": 0.1075307166931184, "grad_norm": 1.8826348781585693, "learning_rate": 7.168218743808203e-05, "loss": 0.7243504524230957, "step": 18090 }, { "epoch": 0.10759015876978678, "grad_norm": 1.1849614381790161, "learning_rate": 7.172181493956807e-05, "loss": 0.7013833522796631, "step": 18100 }, { "epoch": 0.10764960084645517, "grad_norm": 1.4732717275619507, "learning_rate": 7.17614424410541e-05, "loss": 0.692864179611206, "step": 18110 }, { "epoch": 0.10770904292312357, "grad_norm": 1.7762644290924072, "learning_rate": 7.180106994254012e-05, "loss": 0.7148419380187988, "step": 18120 }, { "epoch": 0.10776848499979196, "grad_norm": 1.6993595361709595, "learning_rate": 7.184069744402616e-05, "loss": 0.6451028823852539, "step": 18130 }, { "epoch": 0.10782792707646034, "grad_norm": 1.3608139753341675, "learning_rate": 7.188032494551219e-05, "loss": 0.68624267578125, "step": 18140 }, { "epoch": 0.10788736915312873, "grad_norm": 1.7480982542037964, "learning_rate": 7.191995244699822e-05, "loss": 0.6800624370574951, "step": 18150 }, { "epoch": 0.10794681122979713, "grad_norm": 1.74312162399292, "learning_rate": 7.195957994848426e-05, "loss": 0.6669378280639648, "step": 18160 }, { "epoch": 0.10800625330646552, "grad_norm": 2.1638424396514893, "learning_rate": 7.199920744997029e-05, "loss": 0.7182034492492676, "step": 18170 }, { "epoch": 0.1080656953831339, "grad_norm": 1.6275554895401, "learning_rate": 7.203883495145631e-05, "loss": 0.667055082321167, "step": 18180 }, { "epoch": 0.10812513745980229, "grad_norm": 1.6901522874832153, "learning_rate": 7.207846245294234e-05, "loss": 0.666960620880127, "step": 18190 }, { "epoch": 0.10818457953647069, "grad_norm": 1.5563746690750122, "learning_rate": 7.211808995442838e-05, "loss": 0.6402399063110351, "step": 18200 }, { "epoch": 0.10824402161313908, "grad_norm": 1.5600850582122803, "learning_rate": 7.215771745591442e-05, "loss": 0.681905460357666, "step": 18210 }, { "epoch": 0.10830346368980746, "grad_norm": 1.859184980392456, "learning_rate": 7.219734495740044e-05, "loss": 0.6890907764434815, "step": 18220 }, { "epoch": 0.10836290576647586, "grad_norm": 1.6310157775878906, "learning_rate": 7.223697245888648e-05, "loss": 0.6780760765075684, "step": 18230 }, { "epoch": 0.10842234784314425, "grad_norm": 1.3362754583358765, "learning_rate": 7.22765999603725e-05, "loss": 0.6677000045776367, "step": 18240 }, { "epoch": 0.10848178991981264, "grad_norm": 1.2362428903579712, "learning_rate": 7.231622746185853e-05, "loss": 0.6659589767456054, "step": 18250 }, { "epoch": 0.10854123199648102, "grad_norm": 1.5221366882324219, "learning_rate": 7.235585496334455e-05, "loss": 0.6973299026489258, "step": 18260 }, { "epoch": 0.10860067407314943, "grad_norm": 1.4731758832931519, "learning_rate": 7.23954824648306e-05, "loss": 0.7128734588623047, "step": 18270 }, { "epoch": 0.10866011614981781, "grad_norm": 1.7610138654708862, "learning_rate": 7.243510996631663e-05, "loss": 0.7432205200195312, "step": 18280 }, { "epoch": 0.1087195582264862, "grad_norm": 1.5138664245605469, "learning_rate": 7.247473746780266e-05, "loss": 0.7026814460754395, "step": 18290 }, { "epoch": 0.10877900030315459, "grad_norm": 1.7363641262054443, "learning_rate": 7.25143649692887e-05, "loss": 0.6554804801940918, "step": 18300 }, { "epoch": 0.10883844237982299, "grad_norm": 1.898739218711853, "learning_rate": 7.255399247077472e-05, "loss": 0.7372564315795899, "step": 18310 }, { "epoch": 0.10889788445649137, "grad_norm": 1.9501405954360962, "learning_rate": 7.259361997226075e-05, "loss": 0.7019474983215332, "step": 18320 }, { "epoch": 0.10895732653315976, "grad_norm": 1.9820055961608887, "learning_rate": 7.263324747374678e-05, "loss": 0.6811045169830322, "step": 18330 }, { "epoch": 0.10901676860982815, "grad_norm": 1.4731378555297852, "learning_rate": 7.267287497523282e-05, "loss": 0.6883533954620361, "step": 18340 }, { "epoch": 0.10907621068649655, "grad_norm": 1.6233409643173218, "learning_rate": 7.271250247671885e-05, "loss": 0.68355712890625, "step": 18350 }, { "epoch": 0.10913565276316493, "grad_norm": 1.906233549118042, "learning_rate": 7.275212997820487e-05, "loss": 0.6937214851379394, "step": 18360 }, { "epoch": 0.10919509483983332, "grad_norm": 1.7480686902999878, "learning_rate": 7.279175747969091e-05, "loss": 0.6706338882446289, "step": 18370 }, { "epoch": 0.10925453691650172, "grad_norm": 1.5154212713241577, "learning_rate": 7.283138498117694e-05, "loss": 0.6879408836364747, "step": 18380 }, { "epoch": 0.10931397899317011, "grad_norm": 1.5990891456604004, "learning_rate": 7.287101248266298e-05, "loss": 0.6800670623779297, "step": 18390 }, { "epoch": 0.1093734210698385, "grad_norm": 2.022592067718506, "learning_rate": 7.2910639984149e-05, "loss": 0.6949936866760253, "step": 18400 }, { "epoch": 0.10943286314650688, "grad_norm": 2.145132303237915, "learning_rate": 7.295026748563504e-05, "loss": 0.759153413772583, "step": 18410 }, { "epoch": 0.10949230522317528, "grad_norm": 1.4533734321594238, "learning_rate": 7.298989498712106e-05, "loss": 0.6437179565429687, "step": 18420 }, { "epoch": 0.10955174729984367, "grad_norm": 1.743064045906067, "learning_rate": 7.302952248860709e-05, "loss": 0.6813261032104492, "step": 18430 }, { "epoch": 0.10961118937651206, "grad_norm": 1.79888916015625, "learning_rate": 7.306914999009313e-05, "loss": 0.7078973770141601, "step": 18440 }, { "epoch": 0.10967063145318044, "grad_norm": 1.6492829322814941, "learning_rate": 7.310877749157917e-05, "loss": 0.6742603302001953, "step": 18450 }, { "epoch": 0.10973007352984884, "grad_norm": 1.6592777967453003, "learning_rate": 7.314840499306519e-05, "loss": 0.6839121818542481, "step": 18460 }, { "epoch": 0.10978951560651723, "grad_norm": 1.2461624145507812, "learning_rate": 7.318803249455122e-05, "loss": 0.7039244651794434, "step": 18470 }, { "epoch": 0.10984895768318562, "grad_norm": 1.9265000820159912, "learning_rate": 7.322765999603726e-05, "loss": 0.7094773292541504, "step": 18480 }, { "epoch": 0.10990839975985402, "grad_norm": 1.7095402479171753, "learning_rate": 7.326728749752328e-05, "loss": 0.6769428253173828, "step": 18490 }, { "epoch": 0.1099678418365224, "grad_norm": 1.9785536527633667, "learning_rate": 7.330691499900932e-05, "loss": 0.7139298439025878, "step": 18500 }, { "epoch": 0.11002728391319079, "grad_norm": 1.67681884765625, "learning_rate": 7.334654250049536e-05, "loss": 0.7654060840606689, "step": 18510 }, { "epoch": 0.11008672598985918, "grad_norm": 1.6705394983291626, "learning_rate": 7.338617000198138e-05, "loss": 0.783259391784668, "step": 18520 }, { "epoch": 0.11014616806652758, "grad_norm": 1.6490917205810547, "learning_rate": 7.342579750346741e-05, "loss": 0.6367456436157226, "step": 18530 }, { "epoch": 0.11020561014319596, "grad_norm": 1.667710781097412, "learning_rate": 7.346542500495343e-05, "loss": 0.7108772277832032, "step": 18540 }, { "epoch": 0.11026505221986435, "grad_norm": 2.2003254890441895, "learning_rate": 7.350505250643947e-05, "loss": 0.7544644832611084, "step": 18550 }, { "epoch": 0.11032449429653274, "grad_norm": 1.6934146881103516, "learning_rate": 7.354468000792551e-05, "loss": 0.6807459831237793, "step": 18560 }, { "epoch": 0.11038393637320114, "grad_norm": 2.1403379440307617, "learning_rate": 7.358430750941154e-05, "loss": 0.6933891773223877, "step": 18570 }, { "epoch": 0.11044337844986953, "grad_norm": 1.7585728168487549, "learning_rate": 7.362393501089757e-05, "loss": 0.6785189628601074, "step": 18580 }, { "epoch": 0.11050282052653791, "grad_norm": 1.698752760887146, "learning_rate": 7.36635625123836e-05, "loss": 0.7020448684692383, "step": 18590 }, { "epoch": 0.1105622626032063, "grad_norm": 1.9782118797302246, "learning_rate": 7.370319001386962e-05, "loss": 0.6751125812530517, "step": 18600 }, { "epoch": 0.1106217046798747, "grad_norm": 1.3448536396026611, "learning_rate": 7.374281751535565e-05, "loss": 0.6572076797485351, "step": 18610 }, { "epoch": 0.11068114675654309, "grad_norm": 1.1754227876663208, "learning_rate": 7.378244501684169e-05, "loss": 0.6544675827026367, "step": 18620 }, { "epoch": 0.11074058883321147, "grad_norm": 2.3665637969970703, "learning_rate": 7.382207251832773e-05, "loss": 0.714081859588623, "step": 18630 }, { "epoch": 0.11080003090987987, "grad_norm": 1.4952064752578735, "learning_rate": 7.386170001981375e-05, "loss": 0.6712511062622071, "step": 18640 }, { "epoch": 0.11085947298654826, "grad_norm": 2.160412549972534, "learning_rate": 7.390132752129979e-05, "loss": 0.6681021690368653, "step": 18650 }, { "epoch": 0.11091891506321665, "grad_norm": 1.581864595413208, "learning_rate": 7.394095502278582e-05, "loss": 0.6827354431152344, "step": 18660 }, { "epoch": 0.11097835713988503, "grad_norm": 1.7995774745941162, "learning_rate": 7.398058252427184e-05, "loss": 0.731594467163086, "step": 18670 }, { "epoch": 0.11103779921655343, "grad_norm": 1.292484164237976, "learning_rate": 7.402021002575788e-05, "loss": 0.689417552947998, "step": 18680 }, { "epoch": 0.11109724129322182, "grad_norm": 1.6426455974578857, "learning_rate": 7.405983752724392e-05, "loss": 0.7294621467590332, "step": 18690 }, { "epoch": 0.11115668336989021, "grad_norm": 2.4265823364257812, "learning_rate": 7.409946502872994e-05, "loss": 0.6673375129699707, "step": 18700 }, { "epoch": 0.1112161254465586, "grad_norm": 1.7335546016693115, "learning_rate": 7.413909253021597e-05, "loss": 0.7290917873382569, "step": 18710 }, { "epoch": 0.111275567523227, "grad_norm": 1.7679238319396973, "learning_rate": 7.417872003170201e-05, "loss": 0.679274034500122, "step": 18720 }, { "epoch": 0.11133500959989538, "grad_norm": 1.462945580482483, "learning_rate": 7.421834753318803e-05, "loss": 0.6798571586608887, "step": 18730 }, { "epoch": 0.11139445167656377, "grad_norm": 1.6653913259506226, "learning_rate": 7.425797503467407e-05, "loss": 0.667649507522583, "step": 18740 }, { "epoch": 0.11145389375323217, "grad_norm": 1.5819344520568848, "learning_rate": 7.42976025361601e-05, "loss": 0.6997103214263916, "step": 18750 }, { "epoch": 0.11151333582990056, "grad_norm": 1.9004374742507935, "learning_rate": 7.433723003764613e-05, "loss": 0.7037561893463135, "step": 18760 }, { "epoch": 0.11157277790656894, "grad_norm": 1.785493016242981, "learning_rate": 7.437685753913216e-05, "loss": 0.6796097755432129, "step": 18770 }, { "epoch": 0.11163221998323733, "grad_norm": 1.5307817459106445, "learning_rate": 7.441648504061818e-05, "loss": 0.699904203414917, "step": 18780 }, { "epoch": 0.11169166205990573, "grad_norm": 1.7228022813796997, "learning_rate": 7.445611254210422e-05, "loss": 0.6530188083648681, "step": 18790 }, { "epoch": 0.11175110413657412, "grad_norm": 1.542271375656128, "learning_rate": 7.449574004359026e-05, "loss": 0.7305127620697022, "step": 18800 }, { "epoch": 0.1118105462132425, "grad_norm": 1.6461107730865479, "learning_rate": 7.453536754507629e-05, "loss": 0.6698721885681153, "step": 18810 }, { "epoch": 0.11186998828991089, "grad_norm": 1.526880145072937, "learning_rate": 7.457499504656231e-05, "loss": 0.6460637092590332, "step": 18820 }, { "epoch": 0.11192943036657929, "grad_norm": 1.4003558158874512, "learning_rate": 7.461462254804835e-05, "loss": 0.6978078365325928, "step": 18830 }, { "epoch": 0.11198887244324768, "grad_norm": 1.4548149108886719, "learning_rate": 7.465425004953438e-05, "loss": 0.7180220127105713, "step": 18840 }, { "epoch": 0.11204831451991606, "grad_norm": 1.8216744661331177, "learning_rate": 7.469387755102041e-05, "loss": 0.7143498420715332, "step": 18850 }, { "epoch": 0.11210775659658445, "grad_norm": 1.6022955179214478, "learning_rate": 7.473350505250645e-05, "loss": 0.7014809131622315, "step": 18860 }, { "epoch": 0.11216719867325285, "grad_norm": 1.6724693775177002, "learning_rate": 7.477313255399248e-05, "loss": 0.7470557689666748, "step": 18870 }, { "epoch": 0.11222664074992124, "grad_norm": 1.2523608207702637, "learning_rate": 7.48127600554785e-05, "loss": 0.6773149013519287, "step": 18880 }, { "epoch": 0.11228608282658963, "grad_norm": 1.6161432266235352, "learning_rate": 7.485238755696453e-05, "loss": 0.6806532859802246, "step": 18890 }, { "epoch": 0.11234552490325803, "grad_norm": 1.6834149360656738, "learning_rate": 7.489201505845057e-05, "loss": 0.6254517555236816, "step": 18900 }, { "epoch": 0.11240496697992641, "grad_norm": 1.9559763669967651, "learning_rate": 7.493164255993659e-05, "loss": 0.7406659126281738, "step": 18910 }, { "epoch": 0.1124644090565948, "grad_norm": 1.6313139200210571, "learning_rate": 7.497127006142263e-05, "loss": 0.7463837623596191, "step": 18920 }, { "epoch": 0.11252385113326319, "grad_norm": 1.7697783708572388, "learning_rate": 7.501089756290867e-05, "loss": 0.704396390914917, "step": 18930 }, { "epoch": 0.11258329320993159, "grad_norm": 1.3678741455078125, "learning_rate": 7.50505250643947e-05, "loss": 0.6523615837097168, "step": 18940 }, { "epoch": 0.11264273528659997, "grad_norm": 1.438401699066162, "learning_rate": 7.509015256588072e-05, "loss": 0.686162281036377, "step": 18950 }, { "epoch": 0.11270217736326836, "grad_norm": 2.062220335006714, "learning_rate": 7.512978006736674e-05, "loss": 0.6693315029144287, "step": 18960 }, { "epoch": 0.11276161943993675, "grad_norm": 1.5290800333023071, "learning_rate": 7.516940756885278e-05, "loss": 0.6915990829467773, "step": 18970 }, { "epoch": 0.11282106151660515, "grad_norm": 1.4163779020309448, "learning_rate": 7.520903507033882e-05, "loss": 0.6914485454559326, "step": 18980 }, { "epoch": 0.11288050359327353, "grad_norm": 1.3392677307128906, "learning_rate": 7.524866257182485e-05, "loss": 0.6636894226074219, "step": 18990 }, { "epoch": 0.11293994566994192, "grad_norm": 1.6179521083831787, "learning_rate": 7.528829007331089e-05, "loss": 0.6745885848999024, "step": 19000 }, { "epoch": 0.11299938774661032, "grad_norm": 1.3297628164291382, "learning_rate": 7.532791757479691e-05, "loss": 0.6660337924957276, "step": 19010 }, { "epoch": 0.11305882982327871, "grad_norm": 1.4399195909500122, "learning_rate": 7.536754507628294e-05, "loss": 0.6841739654541016, "step": 19020 }, { "epoch": 0.1131182718999471, "grad_norm": 1.634184718132019, "learning_rate": 7.540717257776897e-05, "loss": 0.6984862327575684, "step": 19030 }, { "epoch": 0.11317771397661548, "grad_norm": 1.6345946788787842, "learning_rate": 7.544680007925501e-05, "loss": 0.717534065246582, "step": 19040 }, { "epoch": 0.11323715605328388, "grad_norm": 1.706506609916687, "learning_rate": 7.548642758074104e-05, "loss": 0.726803207397461, "step": 19050 }, { "epoch": 0.11329659812995227, "grad_norm": 1.285360336303711, "learning_rate": 7.552605508222706e-05, "loss": 0.6602738857269287, "step": 19060 }, { "epoch": 0.11335604020662066, "grad_norm": 1.4802275896072388, "learning_rate": 7.55656825837131e-05, "loss": 0.6896098136901856, "step": 19070 }, { "epoch": 0.11341548228328904, "grad_norm": 1.4594742059707642, "learning_rate": 7.560531008519913e-05, "loss": 0.7183405876159668, "step": 19080 }, { "epoch": 0.11347492435995744, "grad_norm": 1.2865660190582275, "learning_rate": 7.564493758668517e-05, "loss": 0.6413644790649414, "step": 19090 }, { "epoch": 0.11353436643662583, "grad_norm": 1.9214909076690674, "learning_rate": 7.56845650881712e-05, "loss": 0.7060256481170655, "step": 19100 }, { "epoch": 0.11359380851329422, "grad_norm": 1.7630884647369385, "learning_rate": 7.572419258965723e-05, "loss": 0.7331543922424316, "step": 19110 }, { "epoch": 0.11365325058996262, "grad_norm": 2.1126606464385986, "learning_rate": 7.576382009114326e-05, "loss": 0.6738169670104981, "step": 19120 }, { "epoch": 0.113712692666631, "grad_norm": 1.4664143323898315, "learning_rate": 7.580344759262928e-05, "loss": 0.6402613162994385, "step": 19130 }, { "epoch": 0.11377213474329939, "grad_norm": 1.2430133819580078, "learning_rate": 7.584307509411532e-05, "loss": 0.6505527973175049, "step": 19140 }, { "epoch": 0.11383157681996778, "grad_norm": 1.5041707754135132, "learning_rate": 7.588270259560136e-05, "loss": 0.7225695610046386, "step": 19150 }, { "epoch": 0.11389101889663618, "grad_norm": 1.588963270187378, "learning_rate": 7.592233009708738e-05, "loss": 0.7030835151672363, "step": 19160 }, { "epoch": 0.11395046097330457, "grad_norm": 1.743264079093933, "learning_rate": 7.596195759857342e-05, "loss": 0.711176872253418, "step": 19170 }, { "epoch": 0.11400990304997295, "grad_norm": 1.8073689937591553, "learning_rate": 7.600158510005945e-05, "loss": 0.7170936584472656, "step": 19180 }, { "epoch": 0.11406934512664134, "grad_norm": 1.3138564825057983, "learning_rate": 7.604121260154547e-05, "loss": 0.6499594688415528, "step": 19190 }, { "epoch": 0.11412878720330974, "grad_norm": 1.8787086009979248, "learning_rate": 7.60808401030315e-05, "loss": 0.7036333560943604, "step": 19200 }, { "epoch": 0.11418822927997813, "grad_norm": 1.9638274908065796, "learning_rate": 7.612046760451755e-05, "loss": 0.767055892944336, "step": 19210 }, { "epoch": 0.11424767135664651, "grad_norm": 1.671607494354248, "learning_rate": 7.616009510600357e-05, "loss": 0.6973381996154785, "step": 19220 }, { "epoch": 0.1143071134333149, "grad_norm": 1.7948758602142334, "learning_rate": 7.61997226074896e-05, "loss": 0.7553133010864258, "step": 19230 }, { "epoch": 0.1143665555099833, "grad_norm": 1.4301221370697021, "learning_rate": 7.623935010897564e-05, "loss": 0.7271127700805664, "step": 19240 }, { "epoch": 0.11442599758665169, "grad_norm": 1.8395204544067383, "learning_rate": 7.627897761046166e-05, "loss": 0.6967666149139404, "step": 19250 }, { "epoch": 0.11448543966332007, "grad_norm": 1.3183919191360474, "learning_rate": 7.631860511194769e-05, "loss": 0.7102421760559082, "step": 19260 }, { "epoch": 0.11454488173998847, "grad_norm": 1.6292463541030884, "learning_rate": 7.635823261343373e-05, "loss": 0.6847664833068847, "step": 19270 }, { "epoch": 0.11460432381665686, "grad_norm": 2.152984857559204, "learning_rate": 7.639786011491977e-05, "loss": 0.7104727268218994, "step": 19280 }, { "epoch": 0.11466376589332525, "grad_norm": 1.3714888095855713, "learning_rate": 7.643748761640579e-05, "loss": 0.6978235244750977, "step": 19290 }, { "epoch": 0.11472320796999363, "grad_norm": 1.7400336265563965, "learning_rate": 7.647711511789182e-05, "loss": 0.7751877784729004, "step": 19300 }, { "epoch": 0.11478265004666204, "grad_norm": 1.6986700296401978, "learning_rate": 7.651674261937785e-05, "loss": 0.6731086254119873, "step": 19310 }, { "epoch": 0.11484209212333042, "grad_norm": 1.4326975345611572, "learning_rate": 7.655637012086388e-05, "loss": 0.7360897064208984, "step": 19320 }, { "epoch": 0.11490153419999881, "grad_norm": 1.4878759384155273, "learning_rate": 7.659599762234992e-05, "loss": 0.6619146347045899, "step": 19330 }, { "epoch": 0.1149609762766672, "grad_norm": 1.717349886894226, "learning_rate": 7.663562512383594e-05, "loss": 0.6624289512634277, "step": 19340 }, { "epoch": 0.1150204183533356, "grad_norm": 1.4521135091781616, "learning_rate": 7.667525262532198e-05, "loss": 0.7289776802062988, "step": 19350 }, { "epoch": 0.11507986043000398, "grad_norm": 1.7085012197494507, "learning_rate": 7.6714880126808e-05, "loss": 0.6874620914459229, "step": 19360 }, { "epoch": 0.11513930250667237, "grad_norm": 1.3979263305664062, "learning_rate": 7.675450762829403e-05, "loss": 0.6885210037231445, "step": 19370 }, { "epoch": 0.11519874458334077, "grad_norm": 1.4838900566101074, "learning_rate": 7.679413512978007e-05, "loss": 0.7570419311523438, "step": 19380 }, { "epoch": 0.11525818666000916, "grad_norm": 1.4217615127563477, "learning_rate": 7.683376263126611e-05, "loss": 0.7022191524505615, "step": 19390 }, { "epoch": 0.11531762873667754, "grad_norm": 1.8573198318481445, "learning_rate": 7.687339013275213e-05, "loss": 0.7226626396179199, "step": 19400 }, { "epoch": 0.11537707081334593, "grad_norm": 1.627770185470581, "learning_rate": 7.691301763423816e-05, "loss": 0.6455634593963623, "step": 19410 }, { "epoch": 0.11543651289001433, "grad_norm": 1.6292868852615356, "learning_rate": 7.69526451357242e-05, "loss": 0.7434494972229004, "step": 19420 }, { "epoch": 0.11549595496668272, "grad_norm": 1.6862844228744507, "learning_rate": 7.699227263721022e-05, "loss": 0.7198020935058593, "step": 19430 }, { "epoch": 0.1155553970433511, "grad_norm": 2.0547261238098145, "learning_rate": 7.703190013869626e-05, "loss": 0.7011220932006836, "step": 19440 }, { "epoch": 0.11561483912001949, "grad_norm": 1.9184340238571167, "learning_rate": 7.70715276401823e-05, "loss": 0.6848791122436524, "step": 19450 }, { "epoch": 0.11567428119668789, "grad_norm": 1.0939323902130127, "learning_rate": 7.711115514166833e-05, "loss": 0.6926980495452881, "step": 19460 }, { "epoch": 0.11573372327335628, "grad_norm": 1.206598162651062, "learning_rate": 7.715078264315435e-05, "loss": 0.6893205642700195, "step": 19470 }, { "epoch": 0.11579316535002467, "grad_norm": 1.8170708417892456, "learning_rate": 7.719041014464038e-05, "loss": 0.7415889739990235, "step": 19480 }, { "epoch": 0.11585260742669305, "grad_norm": 1.6327329874038696, "learning_rate": 7.723003764612641e-05, "loss": 0.7253291130065918, "step": 19490 }, { "epoch": 0.11591204950336145, "grad_norm": 1.5854640007019043, "learning_rate": 7.726966514761245e-05, "loss": 0.6898463726043701, "step": 19500 }, { "epoch": 0.11597149158002984, "grad_norm": 1.9334794282913208, "learning_rate": 7.730929264909848e-05, "loss": 0.6920759677886963, "step": 19510 }, { "epoch": 0.11603093365669823, "grad_norm": 1.5439033508300781, "learning_rate": 7.734892015058452e-05, "loss": 0.6684377670288086, "step": 19520 }, { "epoch": 0.11609037573336663, "grad_norm": 1.5138180255889893, "learning_rate": 7.738854765207054e-05, "loss": 0.7297675132751464, "step": 19530 }, { "epoch": 0.11614981781003501, "grad_norm": 1.3517961502075195, "learning_rate": 7.742817515355657e-05, "loss": 0.7399797439575195, "step": 19540 }, { "epoch": 0.1162092598867034, "grad_norm": 2.28759503364563, "learning_rate": 7.746780265504259e-05, "loss": 0.7452907562255859, "step": 19550 }, { "epoch": 0.11626870196337179, "grad_norm": 1.4173974990844727, "learning_rate": 7.750743015652864e-05, "loss": 0.7099874496459961, "step": 19560 }, { "epoch": 0.11632814404004019, "grad_norm": 1.7674113512039185, "learning_rate": 7.754705765801467e-05, "loss": 0.7160808563232421, "step": 19570 }, { "epoch": 0.11638758611670857, "grad_norm": 1.6314632892608643, "learning_rate": 7.75866851595007e-05, "loss": 0.6812207221984863, "step": 19580 }, { "epoch": 0.11644702819337696, "grad_norm": 1.354195475578308, "learning_rate": 7.762631266098673e-05, "loss": 0.6660345077514649, "step": 19590 }, { "epoch": 0.11650647027004535, "grad_norm": 1.6806598901748657, "learning_rate": 7.766594016247276e-05, "loss": 0.6921625137329102, "step": 19600 }, { "epoch": 0.11656591234671375, "grad_norm": 1.5688860416412354, "learning_rate": 7.770556766395878e-05, "loss": 0.753870677947998, "step": 19610 }, { "epoch": 0.11662535442338214, "grad_norm": 1.2644262313842773, "learning_rate": 7.774519516544482e-05, "loss": 0.6779991626739502, "step": 19620 }, { "epoch": 0.11668479650005052, "grad_norm": 1.4968678951263428, "learning_rate": 7.778482266693086e-05, "loss": 0.7149919509887696, "step": 19630 }, { "epoch": 0.11674423857671892, "grad_norm": 1.278548240661621, "learning_rate": 7.782445016841689e-05, "loss": 0.7149276256561279, "step": 19640 }, { "epoch": 0.11680368065338731, "grad_norm": 1.4261046648025513, "learning_rate": 7.786407766990291e-05, "loss": 0.6641533851623536, "step": 19650 }, { "epoch": 0.1168631227300557, "grad_norm": 1.884772777557373, "learning_rate": 7.790370517138895e-05, "loss": 0.7231784343719483, "step": 19660 }, { "epoch": 0.11692256480672408, "grad_norm": 1.8431215286254883, "learning_rate": 7.794333267287497e-05, "loss": 0.6252174377441406, "step": 19670 }, { "epoch": 0.11698200688339248, "grad_norm": 1.7854528427124023, "learning_rate": 7.798296017436101e-05, "loss": 0.6695273399353028, "step": 19680 }, { "epoch": 0.11704144896006087, "grad_norm": 2.0140445232391357, "learning_rate": 7.802258767584704e-05, "loss": 0.6719334602355957, "step": 19690 }, { "epoch": 0.11710089103672926, "grad_norm": 1.578757643699646, "learning_rate": 7.806221517733308e-05, "loss": 0.723176908493042, "step": 19700 }, { "epoch": 0.11716033311339764, "grad_norm": 1.5220189094543457, "learning_rate": 7.81018426788191e-05, "loss": 0.6417096614837646, "step": 19710 }, { "epoch": 0.11721977519006604, "grad_norm": 1.7479474544525146, "learning_rate": 7.814147018030513e-05, "loss": 0.7295805931091308, "step": 19720 }, { "epoch": 0.11727921726673443, "grad_norm": 1.9120161533355713, "learning_rate": 7.818109768179117e-05, "loss": 0.7177667617797852, "step": 19730 }, { "epoch": 0.11733865934340282, "grad_norm": 1.4523987770080566, "learning_rate": 7.82207251832772e-05, "loss": 0.6642816543579102, "step": 19740 }, { "epoch": 0.1173981014200712, "grad_norm": 1.5806244611740112, "learning_rate": 7.826035268476323e-05, "loss": 0.6870527267456055, "step": 19750 }, { "epoch": 0.1174575434967396, "grad_norm": 1.6191363334655762, "learning_rate": 7.829998018624925e-05, "loss": 0.6691308498382569, "step": 19760 }, { "epoch": 0.11751698557340799, "grad_norm": 1.895420789718628, "learning_rate": 7.833960768773529e-05, "loss": 0.6712601661682129, "step": 19770 }, { "epoch": 0.11757642765007638, "grad_norm": 1.4611074924468994, "learning_rate": 7.837923518922132e-05, "loss": 0.7550529479980469, "step": 19780 }, { "epoch": 0.11763586972674478, "grad_norm": 1.5156008005142212, "learning_rate": 7.841886269070736e-05, "loss": 0.6807256698608398, "step": 19790 }, { "epoch": 0.11769531180341317, "grad_norm": 1.5144685506820679, "learning_rate": 7.84584901921934e-05, "loss": 0.6809573173522949, "step": 19800 }, { "epoch": 0.11775475388008155, "grad_norm": 1.5529003143310547, "learning_rate": 7.849811769367942e-05, "loss": 0.6657332897186279, "step": 19810 }, { "epoch": 0.11781419595674994, "grad_norm": 1.338283658027649, "learning_rate": 7.853774519516545e-05, "loss": 0.6907132148742676, "step": 19820 }, { "epoch": 0.11787363803341834, "grad_norm": 1.5759645700454712, "learning_rate": 7.857737269665147e-05, "loss": 0.742620849609375, "step": 19830 }, { "epoch": 0.11793308011008673, "grad_norm": 1.557286262512207, "learning_rate": 7.861700019813751e-05, "loss": 0.6699271202087402, "step": 19840 }, { "epoch": 0.11799252218675511, "grad_norm": 1.5799999237060547, "learning_rate": 7.865662769962355e-05, "loss": 0.6866578102111817, "step": 19850 }, { "epoch": 0.1180519642634235, "grad_norm": 1.6533232927322388, "learning_rate": 7.869625520110957e-05, "loss": 0.6852150917053222, "step": 19860 }, { "epoch": 0.1181114063400919, "grad_norm": 1.8392655849456787, "learning_rate": 7.873588270259561e-05, "loss": 0.6963041305541993, "step": 19870 }, { "epoch": 0.11817084841676029, "grad_norm": 1.3999311923980713, "learning_rate": 7.877551020408164e-05, "loss": 0.7030943870544434, "step": 19880 }, { "epoch": 0.11823029049342867, "grad_norm": 1.6817662715911865, "learning_rate": 7.881513770556766e-05, "loss": 0.6965778827667236, "step": 19890 }, { "epoch": 0.11828973257009708, "grad_norm": 2.0011391639709473, "learning_rate": 7.885476520705369e-05, "loss": 0.7202026844024658, "step": 19900 }, { "epoch": 0.11834917464676546, "grad_norm": 1.7965025901794434, "learning_rate": 7.889439270853974e-05, "loss": 0.6742256164550782, "step": 19910 }, { "epoch": 0.11840861672343385, "grad_norm": 1.9551349878311157, "learning_rate": 7.893402021002576e-05, "loss": 0.7017959117889404, "step": 19920 }, { "epoch": 0.11846805880010224, "grad_norm": 1.6274827718734741, "learning_rate": 7.897364771151179e-05, "loss": 0.7149442195892334, "step": 19930 }, { "epoch": 0.11852750087677064, "grad_norm": 1.316847324371338, "learning_rate": 7.901327521299783e-05, "loss": 0.6623453140258789, "step": 19940 }, { "epoch": 0.11858694295343902, "grad_norm": 1.499531865119934, "learning_rate": 7.905290271448385e-05, "loss": 0.7841850757598877, "step": 19950 }, { "epoch": 0.11864638503010741, "grad_norm": 1.7119256258010864, "learning_rate": 7.909253021596988e-05, "loss": 0.7439012050628662, "step": 19960 }, { "epoch": 0.1187058271067758, "grad_norm": 1.2355756759643555, "learning_rate": 7.913215771745592e-05, "loss": 0.6707966804504395, "step": 19970 }, { "epoch": 0.1187652691834442, "grad_norm": 1.4015061855316162, "learning_rate": 7.917178521894196e-05, "loss": 0.696384048461914, "step": 19980 }, { "epoch": 0.11882471126011258, "grad_norm": 1.9467239379882812, "learning_rate": 7.921141272042798e-05, "loss": 0.7295132160186768, "step": 19990 }, { "epoch": 0.11888415333678097, "grad_norm": 1.7306091785430908, "learning_rate": 7.9251040221914e-05, "loss": 0.6714009284973145, "step": 20000 }, { "epoch": 0.11894359541344937, "grad_norm": 1.4182894229888916, "learning_rate": 7.929066772340004e-05, "loss": 0.7421850204467774, "step": 20010 }, { "epoch": 0.11900303749011776, "grad_norm": 1.5643994808197021, "learning_rate": 7.933029522488607e-05, "loss": 0.7556916236877441, "step": 20020 }, { "epoch": 0.11906247956678614, "grad_norm": 1.5502959489822388, "learning_rate": 7.936992272637211e-05, "loss": 0.7070655345916748, "step": 20030 }, { "epoch": 0.11912192164345453, "grad_norm": 1.5820181369781494, "learning_rate": 7.940955022785815e-05, "loss": 0.6592965126037598, "step": 20040 }, { "epoch": 0.11918136372012293, "grad_norm": 1.9268720149993896, "learning_rate": 7.944917772934417e-05, "loss": 0.6836339950561523, "step": 20050 }, { "epoch": 0.11924080579679132, "grad_norm": 1.6407395601272583, "learning_rate": 7.94888052308302e-05, "loss": 0.7106021881103516, "step": 20060 }, { "epoch": 0.1193002478734597, "grad_norm": 1.6262603998184204, "learning_rate": 7.952843273231622e-05, "loss": 0.7359624862670898, "step": 20070 }, { "epoch": 0.11935968995012809, "grad_norm": 1.2971975803375244, "learning_rate": 7.956806023380226e-05, "loss": 0.6732316970825195, "step": 20080 }, { "epoch": 0.11941913202679649, "grad_norm": 1.9562829732894897, "learning_rate": 7.96076877352883e-05, "loss": 0.6904911041259766, "step": 20090 }, { "epoch": 0.11947857410346488, "grad_norm": 2.138232707977295, "learning_rate": 7.964731523677432e-05, "loss": 0.7115649223327637, "step": 20100 }, { "epoch": 0.11953801618013327, "grad_norm": 1.520361065864563, "learning_rate": 7.968694273826036e-05, "loss": 0.6181325912475586, "step": 20110 }, { "epoch": 0.11959745825680165, "grad_norm": 1.9660964012145996, "learning_rate": 7.972657023974639e-05, "loss": 0.7509985446929932, "step": 20120 }, { "epoch": 0.11965690033347005, "grad_norm": 1.4123538732528687, "learning_rate": 7.976619774123241e-05, "loss": 0.7509958267211914, "step": 20130 }, { "epoch": 0.11971634241013844, "grad_norm": 1.4357744455337524, "learning_rate": 7.980582524271845e-05, "loss": 0.750177526473999, "step": 20140 }, { "epoch": 0.11977578448680683, "grad_norm": 2.0444939136505127, "learning_rate": 7.984545274420449e-05, "loss": 0.6314738273620606, "step": 20150 }, { "epoch": 0.11983522656347523, "grad_norm": 1.7276829481124878, "learning_rate": 7.988508024569052e-05, "loss": 0.6052627563476562, "step": 20160 }, { "epoch": 0.11989466864014361, "grad_norm": 1.444877028465271, "learning_rate": 7.992470774717654e-05, "loss": 0.6860577583312988, "step": 20170 }, { "epoch": 0.119954110716812, "grad_norm": 1.7593895196914673, "learning_rate": 7.996433524866258e-05, "loss": 0.7335009574890137, "step": 20180 }, { "epoch": 0.12001355279348039, "grad_norm": 1.8683933019638062, "learning_rate": 8.00039627501486e-05, "loss": 0.6933974266052246, "step": 20190 }, { "epoch": 0.12007299487014879, "grad_norm": 1.7995022535324097, "learning_rate": 8.004359025163464e-05, "loss": 0.6100439071655274, "step": 20200 }, { "epoch": 0.12013243694681718, "grad_norm": 1.3861355781555176, "learning_rate": 8.008321775312067e-05, "loss": 0.6985944747924805, "step": 20210 }, { "epoch": 0.12019187902348556, "grad_norm": 1.5385557413101196, "learning_rate": 8.012284525460671e-05, "loss": 0.6683403015136719, "step": 20220 }, { "epoch": 0.12025132110015395, "grad_norm": 1.8901346921920776, "learning_rate": 8.016247275609273e-05, "loss": 0.7087832450866699, "step": 20230 }, { "epoch": 0.12031076317682235, "grad_norm": 1.6602014303207397, "learning_rate": 8.020210025757876e-05, "loss": 0.6453777313232422, "step": 20240 }, { "epoch": 0.12037020525349074, "grad_norm": 1.8034545183181763, "learning_rate": 8.02417277590648e-05, "loss": 0.7111492156982422, "step": 20250 }, { "epoch": 0.12042964733015912, "grad_norm": 1.4944125413894653, "learning_rate": 8.028135526055082e-05, "loss": 0.670306396484375, "step": 20260 }, { "epoch": 0.12048908940682752, "grad_norm": 1.3558697700500488, "learning_rate": 8.032098276203686e-05, "loss": 0.6890753269195556, "step": 20270 }, { "epoch": 0.12054853148349591, "grad_norm": 1.3092472553253174, "learning_rate": 8.036061026352289e-05, "loss": 0.680025863647461, "step": 20280 }, { "epoch": 0.1206079735601643, "grad_norm": 1.5767803192138672, "learning_rate": 8.040023776500892e-05, "loss": 0.6888736724853516, "step": 20290 }, { "epoch": 0.12066741563683268, "grad_norm": 1.5839734077453613, "learning_rate": 8.043986526649495e-05, "loss": 0.6846317291259766, "step": 20300 }, { "epoch": 0.12072685771350108, "grad_norm": 2.020421028137207, "learning_rate": 8.047949276798097e-05, "loss": 0.7693452835083008, "step": 20310 }, { "epoch": 0.12078629979016947, "grad_norm": 1.6161869764328003, "learning_rate": 8.051912026946701e-05, "loss": 0.7546308994293213, "step": 20320 }, { "epoch": 0.12084574186683786, "grad_norm": 1.6907185316085815, "learning_rate": 8.055874777095305e-05, "loss": 0.6633964061737061, "step": 20330 }, { "epoch": 0.12090518394350624, "grad_norm": 1.3412724733352661, "learning_rate": 8.059837527243908e-05, "loss": 0.7023690700531006, "step": 20340 }, { "epoch": 0.12096462602017465, "grad_norm": 1.8223631381988525, "learning_rate": 8.06380027739251e-05, "loss": 0.7182563781738281, "step": 20350 }, { "epoch": 0.12102406809684303, "grad_norm": 1.9727603197097778, "learning_rate": 8.067763027541114e-05, "loss": 0.6943470954895019, "step": 20360 }, { "epoch": 0.12108351017351142, "grad_norm": 1.347663402557373, "learning_rate": 8.071725777689717e-05, "loss": 0.7079653739929199, "step": 20370 }, { "epoch": 0.1211429522501798, "grad_norm": 1.5325981378555298, "learning_rate": 8.07568852783832e-05, "loss": 0.6751474857330322, "step": 20380 }, { "epoch": 0.1212023943268482, "grad_norm": 1.5527124404907227, "learning_rate": 8.079651277986924e-05, "loss": 0.6610418319702148, "step": 20390 }, { "epoch": 0.12126183640351659, "grad_norm": 1.7512727975845337, "learning_rate": 8.083614028135527e-05, "loss": 0.6290669441223145, "step": 20400 }, { "epoch": 0.12132127848018498, "grad_norm": 1.4270634651184082, "learning_rate": 8.087576778284129e-05, "loss": 0.7163418769836426, "step": 20410 }, { "epoch": 0.12138072055685338, "grad_norm": 1.697096824645996, "learning_rate": 8.091539528432732e-05, "loss": 0.6460165977478027, "step": 20420 }, { "epoch": 0.12144016263352177, "grad_norm": 1.6586329936981201, "learning_rate": 8.095502278581336e-05, "loss": 0.6995726585388183, "step": 20430 }, { "epoch": 0.12149960471019015, "grad_norm": 1.3738656044006348, "learning_rate": 8.09946502872994e-05, "loss": 0.7160534858703613, "step": 20440 }, { "epoch": 0.12155904678685854, "grad_norm": 1.7828847169876099, "learning_rate": 8.103427778878542e-05, "loss": 0.6514388084411621, "step": 20450 }, { "epoch": 0.12161848886352694, "grad_norm": 2.1167562007904053, "learning_rate": 8.107390529027146e-05, "loss": 0.6921899318695068, "step": 20460 }, { "epoch": 0.12167793094019533, "grad_norm": 1.8957420587539673, "learning_rate": 8.111353279175748e-05, "loss": 0.6899625778198242, "step": 20470 }, { "epoch": 0.12173737301686371, "grad_norm": 1.935753345489502, "learning_rate": 8.115316029324351e-05, "loss": 0.6441155433654785, "step": 20480 }, { "epoch": 0.1217968150935321, "grad_norm": 1.5711547136306763, "learning_rate": 8.119278779472955e-05, "loss": 0.7085219383239746, "step": 20490 }, { "epoch": 0.1218562571702005, "grad_norm": 1.6928247213363647, "learning_rate": 8.123241529621559e-05, "loss": 0.7081686973571777, "step": 20500 }, { "epoch": 0.12191569924686889, "grad_norm": 1.7666853666305542, "learning_rate": 8.127204279770161e-05, "loss": 0.6222784996032715, "step": 20510 }, { "epoch": 0.12197514132353728, "grad_norm": 1.5436104536056519, "learning_rate": 8.131167029918764e-05, "loss": 0.6312267303466796, "step": 20520 }, { "epoch": 0.12203458340020568, "grad_norm": 2.2385919094085693, "learning_rate": 8.135129780067368e-05, "loss": 0.7319260597229004, "step": 20530 }, { "epoch": 0.12209402547687406, "grad_norm": 1.9692715406417847, "learning_rate": 8.13909253021597e-05, "loss": 0.7235179901123047, "step": 20540 }, { "epoch": 0.12215346755354245, "grad_norm": 1.872132658958435, "learning_rate": 8.143055280364573e-05, "loss": 0.6868391990661621, "step": 20550 }, { "epoch": 0.12221290963021084, "grad_norm": 1.3251785039901733, "learning_rate": 8.147018030513176e-05, "loss": 0.6876416206359863, "step": 20560 }, { "epoch": 0.12227235170687924, "grad_norm": 1.4199705123901367, "learning_rate": 8.15098078066178e-05, "loss": 0.7319912910461426, "step": 20570 }, { "epoch": 0.12233179378354762, "grad_norm": 1.5298492908477783, "learning_rate": 8.154943530810383e-05, "loss": 0.6790917873382568, "step": 20580 }, { "epoch": 0.12239123586021601, "grad_norm": 1.6801167726516724, "learning_rate": 8.158906280958985e-05, "loss": 0.6698470115661621, "step": 20590 }, { "epoch": 0.1224506779368844, "grad_norm": 1.6926510334014893, "learning_rate": 8.162869031107589e-05, "loss": 0.7351755142211914, "step": 20600 }, { "epoch": 0.1225101200135528, "grad_norm": 1.463314175605774, "learning_rate": 8.166831781256192e-05, "loss": 0.6858229637145996, "step": 20610 }, { "epoch": 0.12256956209022118, "grad_norm": 1.4727897644042969, "learning_rate": 8.170794531404796e-05, "loss": 0.8067009925842286, "step": 20620 }, { "epoch": 0.12262900416688957, "grad_norm": 1.292328119277954, "learning_rate": 8.174757281553398e-05, "loss": 0.726964282989502, "step": 20630 }, { "epoch": 0.12268844624355796, "grad_norm": 1.5747919082641602, "learning_rate": 8.178720031702002e-05, "loss": 0.7218531131744385, "step": 20640 }, { "epoch": 0.12274788832022636, "grad_norm": 1.7172203063964844, "learning_rate": 8.182682781850604e-05, "loss": 0.6927241325378418, "step": 20650 }, { "epoch": 0.12280733039689475, "grad_norm": 1.5432944297790527, "learning_rate": 8.186645531999207e-05, "loss": 0.6940365791320801, "step": 20660 }, { "epoch": 0.12286677247356313, "grad_norm": 1.7307056188583374, "learning_rate": 8.190608282147811e-05, "loss": 0.6692593574523926, "step": 20670 }, { "epoch": 0.12292621455023153, "grad_norm": 1.6776148080825806, "learning_rate": 8.194571032296415e-05, "loss": 0.6567704200744628, "step": 20680 }, { "epoch": 0.12298565662689992, "grad_norm": 1.6641918420791626, "learning_rate": 8.198533782445017e-05, "loss": 0.7557052612304688, "step": 20690 }, { "epoch": 0.1230450987035683, "grad_norm": 1.7480905055999756, "learning_rate": 8.20249653259362e-05, "loss": 0.7176596641540527, "step": 20700 }, { "epoch": 0.1231045407802367, "grad_norm": 1.6986875534057617, "learning_rate": 8.206459282742224e-05, "loss": 0.664430046081543, "step": 20710 }, { "epoch": 0.1231639828569051, "grad_norm": 1.7499642372131348, "learning_rate": 8.210422032890826e-05, "loss": 0.6640974521636963, "step": 20720 }, { "epoch": 0.12322342493357348, "grad_norm": 1.592477798461914, "learning_rate": 8.21438478303943e-05, "loss": 0.7376665115356446, "step": 20730 }, { "epoch": 0.12328286701024187, "grad_norm": 1.5420349836349487, "learning_rate": 8.218347533188034e-05, "loss": 0.6475068092346191, "step": 20740 }, { "epoch": 0.12334230908691025, "grad_norm": 1.7440228462219238, "learning_rate": 8.222310283336636e-05, "loss": 0.7305968284606934, "step": 20750 }, { "epoch": 0.12340175116357865, "grad_norm": 1.2519123554229736, "learning_rate": 8.226273033485239e-05, "loss": 0.6592780590057373, "step": 20760 }, { "epoch": 0.12346119324024704, "grad_norm": 1.5805556774139404, "learning_rate": 8.230235783633841e-05, "loss": 0.6407304763793945, "step": 20770 }, { "epoch": 0.12352063531691543, "grad_norm": 1.5647313594818115, "learning_rate": 8.234198533782445e-05, "loss": 0.693827486038208, "step": 20780 }, { "epoch": 0.12358007739358383, "grad_norm": 1.9394375085830688, "learning_rate": 8.238161283931049e-05, "loss": 0.6818790435791016, "step": 20790 }, { "epoch": 0.12363951947025222, "grad_norm": 1.7840288877487183, "learning_rate": 8.242124034079652e-05, "loss": 0.6961039066314697, "step": 20800 }, { "epoch": 0.1236989615469206, "grad_norm": 1.6551719903945923, "learning_rate": 8.246086784228255e-05, "loss": 0.7257832050323486, "step": 20810 }, { "epoch": 0.12375840362358899, "grad_norm": 1.5285307168960571, "learning_rate": 8.250049534376858e-05, "loss": 0.6824718475341797, "step": 20820 }, { "epoch": 0.12381784570025739, "grad_norm": 1.4497016668319702, "learning_rate": 8.25401228452546e-05, "loss": 0.6763738632202149, "step": 20830 }, { "epoch": 0.12387728777692578, "grad_norm": 1.7226154804229736, "learning_rate": 8.257975034674064e-05, "loss": 0.7323456764221191, "step": 20840 }, { "epoch": 0.12393672985359416, "grad_norm": 1.6206210851669312, "learning_rate": 8.261937784822668e-05, "loss": 0.7139366149902344, "step": 20850 }, { "epoch": 0.12399617193026255, "grad_norm": 1.4967035055160522, "learning_rate": 8.265900534971271e-05, "loss": 0.6651695728302002, "step": 20860 }, { "epoch": 0.12405561400693095, "grad_norm": 1.5644892454147339, "learning_rate": 8.269863285119873e-05, "loss": 0.7061789989471435, "step": 20870 }, { "epoch": 0.12411505608359934, "grad_norm": 1.4959741830825806, "learning_rate": 8.273826035268477e-05, "loss": 0.6305007934570312, "step": 20880 }, { "epoch": 0.12417449816026772, "grad_norm": 1.3092354536056519, "learning_rate": 8.27778878541708e-05, "loss": 0.7425667762756347, "step": 20890 }, { "epoch": 0.12423394023693612, "grad_norm": 1.2698341608047485, "learning_rate": 8.281751535565682e-05, "loss": 0.6613472938537598, "step": 20900 }, { "epoch": 0.12429338231360451, "grad_norm": 1.9204399585723877, "learning_rate": 8.285714285714287e-05, "loss": 0.6332625389099121, "step": 20910 }, { "epoch": 0.1243528243902729, "grad_norm": 1.1511794328689575, "learning_rate": 8.28967703586289e-05, "loss": 0.6958065509796143, "step": 20920 }, { "epoch": 0.12441226646694128, "grad_norm": 1.6372177600860596, "learning_rate": 8.293639786011492e-05, "loss": 0.742064094543457, "step": 20930 }, { "epoch": 0.12447170854360969, "grad_norm": 1.2867670059204102, "learning_rate": 8.297602536160095e-05, "loss": 0.6755956649780274, "step": 20940 }, { "epoch": 0.12453115062027807, "grad_norm": 1.514513611793518, "learning_rate": 8.301565286308699e-05, "loss": 0.7231130123138427, "step": 20950 }, { "epoch": 0.12459059269694646, "grad_norm": 1.7757103443145752, "learning_rate": 8.305528036457301e-05, "loss": 0.7033167839050293, "step": 20960 }, { "epoch": 0.12465003477361485, "grad_norm": 1.4442418813705444, "learning_rate": 8.309490786605905e-05, "loss": 0.6901519775390625, "step": 20970 }, { "epoch": 0.12470947685028325, "grad_norm": 1.7857615947723389, "learning_rate": 8.313453536754509e-05, "loss": 0.7216506004333496, "step": 20980 }, { "epoch": 0.12476891892695163, "grad_norm": 1.7841267585754395, "learning_rate": 8.317416286903111e-05, "loss": 0.6943285942077637, "step": 20990 }, { "epoch": 0.12482836100362002, "grad_norm": 1.166738748550415, "learning_rate": 8.321379037051714e-05, "loss": 0.6736732482910156, "step": 21000 }, { "epoch": 0.1248878030802884, "grad_norm": 1.673041820526123, "learning_rate": 8.325341787200316e-05, "loss": 0.7001142024993896, "step": 21010 }, { "epoch": 0.12494724515695681, "grad_norm": 1.5771220922470093, "learning_rate": 8.32930453734892e-05, "loss": 0.6845324516296387, "step": 21020 }, { "epoch": 0.1250066872336252, "grad_norm": 1.7039649486541748, "learning_rate": 8.333267287497524e-05, "loss": 0.6009902000427246, "step": 21030 }, { "epoch": 0.1250661293102936, "grad_norm": 1.647943377494812, "learning_rate": 8.337230037646127e-05, "loss": 0.6742319583892822, "step": 21040 }, { "epoch": 0.12512557138696198, "grad_norm": 1.9813858270645142, "learning_rate": 8.34119278779473e-05, "loss": 0.6520347595214844, "step": 21050 }, { "epoch": 0.12518501346363037, "grad_norm": 1.8038849830627441, "learning_rate": 8.345155537943333e-05, "loss": 0.6827279567718506, "step": 21060 }, { "epoch": 0.12524445554029875, "grad_norm": 1.782427430152893, "learning_rate": 8.349118288091936e-05, "loss": 0.6810853004455566, "step": 21070 }, { "epoch": 0.12530389761696714, "grad_norm": 1.7120716571807861, "learning_rate": 8.35308103824054e-05, "loss": 0.6821477890014649, "step": 21080 }, { "epoch": 0.12536333969363553, "grad_norm": 1.4956369400024414, "learning_rate": 8.357043788389143e-05, "loss": 0.7084407806396484, "step": 21090 }, { "epoch": 0.12542278177030391, "grad_norm": 1.4883763790130615, "learning_rate": 8.361006538537746e-05, "loss": 0.6481813430786133, "step": 21100 }, { "epoch": 0.12548222384697233, "grad_norm": 1.5207924842834473, "learning_rate": 8.364969288686348e-05, "loss": 0.7025812149047852, "step": 21110 }, { "epoch": 0.12554166592364072, "grad_norm": 1.4106913805007935, "learning_rate": 8.368932038834952e-05, "loss": 0.6760416984558105, "step": 21120 }, { "epoch": 0.1256011080003091, "grad_norm": 1.284112811088562, "learning_rate": 8.372894788983555e-05, "loss": 0.7126921653747559, "step": 21130 }, { "epoch": 0.1256605500769775, "grad_norm": 1.6159098148345947, "learning_rate": 8.376857539132159e-05, "loss": 0.7347303867340088, "step": 21140 }, { "epoch": 0.12571999215364588, "grad_norm": 1.773199439048767, "learning_rate": 8.380820289280761e-05, "loss": 0.6807798385620117, "step": 21150 }, { "epoch": 0.12577943423031426, "grad_norm": 1.5096461772918701, "learning_rate": 8.384783039429365e-05, "loss": 0.6420772075653076, "step": 21160 }, { "epoch": 0.12583887630698265, "grad_norm": 1.534076452255249, "learning_rate": 8.388745789577967e-05, "loss": 0.697293758392334, "step": 21170 }, { "epoch": 0.12589831838365106, "grad_norm": 1.7511885166168213, "learning_rate": 8.39270853972657e-05, "loss": 0.6683384895324707, "step": 21180 }, { "epoch": 0.12595776046031945, "grad_norm": 1.5181448459625244, "learning_rate": 8.396671289875174e-05, "loss": 0.688110065460205, "step": 21190 }, { "epoch": 0.12601720253698784, "grad_norm": 1.534111499786377, "learning_rate": 8.400634040023778e-05, "loss": 0.6824119091033936, "step": 21200 }, { "epoch": 0.12607664461365622, "grad_norm": 1.45177161693573, "learning_rate": 8.40459679017238e-05, "loss": 0.6863185882568359, "step": 21210 }, { "epoch": 0.1261360866903246, "grad_norm": 1.476804256439209, "learning_rate": 8.408559540320983e-05, "loss": 0.6877810478210449, "step": 21220 }, { "epoch": 0.126195528766993, "grad_norm": 1.8839547634124756, "learning_rate": 8.412522290469587e-05, "loss": 0.6383206844329834, "step": 21230 }, { "epoch": 0.12625497084366138, "grad_norm": 1.6204025745391846, "learning_rate": 8.416485040618189e-05, "loss": 0.7306410789489746, "step": 21240 }, { "epoch": 0.12631441292032977, "grad_norm": 1.1534843444824219, "learning_rate": 8.420447790766792e-05, "loss": 0.683238172531128, "step": 21250 }, { "epoch": 0.1263738549969982, "grad_norm": 1.4224001169204712, "learning_rate": 8.424410540915395e-05, "loss": 0.6875169754028321, "step": 21260 }, { "epoch": 0.12643329707366657, "grad_norm": 1.9071141481399536, "learning_rate": 8.428373291064e-05, "loss": 0.6976414680480957, "step": 21270 }, { "epoch": 0.12649273915033496, "grad_norm": 1.829271674156189, "learning_rate": 8.432336041212602e-05, "loss": 0.7084464073181153, "step": 21280 }, { "epoch": 0.12655218122700335, "grad_norm": 3.798923969268799, "learning_rate": 8.436298791361204e-05, "loss": 0.6858411312103272, "step": 21290 }, { "epoch": 0.12661162330367173, "grad_norm": 1.6801546812057495, "learning_rate": 8.440261541509808e-05, "loss": 0.6420807838439941, "step": 21300 }, { "epoch": 0.12667106538034012, "grad_norm": 1.438066840171814, "learning_rate": 8.444224291658411e-05, "loss": 0.7427953243255615, "step": 21310 }, { "epoch": 0.1267305074570085, "grad_norm": 1.6331385374069214, "learning_rate": 8.448187041807015e-05, "loss": 0.6831989288330078, "step": 21320 }, { "epoch": 0.12678994953367692, "grad_norm": 1.8047165870666504, "learning_rate": 8.452149791955618e-05, "loss": 0.6466970443725586, "step": 21330 }, { "epoch": 0.1268493916103453, "grad_norm": 1.7349042892456055, "learning_rate": 8.456112542104221e-05, "loss": 0.7092213153839111, "step": 21340 }, { "epoch": 0.1269088336870137, "grad_norm": 1.6233972311019897, "learning_rate": 8.460075292252824e-05, "loss": 0.7221212387084961, "step": 21350 }, { "epoch": 0.12696827576368208, "grad_norm": 2.2421746253967285, "learning_rate": 8.464038042401426e-05, "loss": 0.6839670181274414, "step": 21360 }, { "epoch": 0.12702771784035047, "grad_norm": 1.917149305343628, "learning_rate": 8.46800079255003e-05, "loss": 0.6807567119598389, "step": 21370 }, { "epoch": 0.12708715991701885, "grad_norm": 1.4227112531661987, "learning_rate": 8.471963542698634e-05, "loss": 0.6828875541687012, "step": 21380 }, { "epoch": 0.12714660199368724, "grad_norm": 1.8742876052856445, "learning_rate": 8.475926292847236e-05, "loss": 0.716903829574585, "step": 21390 }, { "epoch": 0.12720604407035563, "grad_norm": 1.5391379594802856, "learning_rate": 8.47988904299584e-05, "loss": 0.6505924224853515, "step": 21400 }, { "epoch": 0.12726548614702404, "grad_norm": 1.3148870468139648, "learning_rate": 8.483851793144443e-05, "loss": 0.6041444778442383, "step": 21410 }, { "epoch": 0.12732492822369243, "grad_norm": 2.1679913997650146, "learning_rate": 8.487814543293045e-05, "loss": 0.7198968410491944, "step": 21420 }, { "epoch": 0.12738437030036082, "grad_norm": 1.7940186262130737, "learning_rate": 8.491777293441649e-05, "loss": 0.6615568161010742, "step": 21430 }, { "epoch": 0.1274438123770292, "grad_norm": 1.507265329360962, "learning_rate": 8.495740043590253e-05, "loss": 0.6913631916046142, "step": 21440 }, { "epoch": 0.1275032544536976, "grad_norm": 1.3824665546417236, "learning_rate": 8.499702793738855e-05, "loss": 0.7221256256103515, "step": 21450 }, { "epoch": 0.12756269653036598, "grad_norm": 1.6348977088928223, "learning_rate": 8.503665543887458e-05, "loss": 0.7092211723327637, "step": 21460 }, { "epoch": 0.12762213860703436, "grad_norm": 1.7939115762710571, "learning_rate": 8.507628294036062e-05, "loss": 0.7062996387481689, "step": 21470 }, { "epoch": 0.12768158068370278, "grad_norm": 1.480149507522583, "learning_rate": 8.511591044184664e-05, "loss": 0.6866673469543457, "step": 21480 }, { "epoch": 0.12774102276037116, "grad_norm": 1.7144769430160522, "learning_rate": 8.515553794333268e-05, "loss": 0.7325294017791748, "step": 21490 }, { "epoch": 0.12780046483703955, "grad_norm": 1.6865651607513428, "learning_rate": 8.51951654448187e-05, "loss": 0.7374458312988281, "step": 21500 }, { "epoch": 0.12785990691370794, "grad_norm": 1.5241409540176392, "learning_rate": 8.523479294630475e-05, "loss": 0.6822548389434815, "step": 21510 }, { "epoch": 0.12791934899037632, "grad_norm": 1.6023656129837036, "learning_rate": 8.527442044779077e-05, "loss": 0.7155809879302979, "step": 21520 }, { "epoch": 0.1279787910670447, "grad_norm": 1.7327451705932617, "learning_rate": 8.53140479492768e-05, "loss": 0.6681100368499756, "step": 21530 }, { "epoch": 0.1280382331437131, "grad_norm": 0.9818239808082581, "learning_rate": 8.535367545076283e-05, "loss": 0.591638708114624, "step": 21540 }, { "epoch": 0.1280976752203815, "grad_norm": 1.9960830211639404, "learning_rate": 8.539330295224887e-05, "loss": 0.7010058403015137, "step": 21550 }, { "epoch": 0.1281571172970499, "grad_norm": 1.673025131225586, "learning_rate": 8.54329304537349e-05, "loss": 0.6995496273040771, "step": 21560 }, { "epoch": 0.1282165593737183, "grad_norm": 1.3621522188186646, "learning_rate": 8.547255795522092e-05, "loss": 0.7366863250732422, "step": 21570 }, { "epoch": 0.12827600145038667, "grad_norm": 1.4076610803604126, "learning_rate": 8.551218545670696e-05, "loss": 0.6678424835205078, "step": 21580 }, { "epoch": 0.12833544352705506, "grad_norm": 1.5413990020751953, "learning_rate": 8.555181295819299e-05, "loss": 0.6461180210113525, "step": 21590 }, { "epoch": 0.12839488560372345, "grad_norm": 1.6172430515289307, "learning_rate": 8.559144045967901e-05, "loss": 0.6978494644165039, "step": 21600 }, { "epoch": 0.12845432768039183, "grad_norm": 1.7548798322677612, "learning_rate": 8.563106796116505e-05, "loss": 0.6938830375671386, "step": 21610 }, { "epoch": 0.12851376975706022, "grad_norm": 1.81904935836792, "learning_rate": 8.567069546265109e-05, "loss": 0.7341244220733643, "step": 21620 }, { "epoch": 0.12857321183372863, "grad_norm": 1.6195429563522339, "learning_rate": 8.571032296413711e-05, "loss": 0.7297401428222656, "step": 21630 }, { "epoch": 0.12863265391039702, "grad_norm": 1.7713662385940552, "learning_rate": 8.574995046562314e-05, "loss": 0.6178825378417969, "step": 21640 }, { "epoch": 0.1286920959870654, "grad_norm": 1.5155930519104004, "learning_rate": 8.578957796710918e-05, "loss": 0.643104362487793, "step": 21650 }, { "epoch": 0.1287515380637338, "grad_norm": 1.502308964729309, "learning_rate": 8.58292054685952e-05, "loss": 0.6335973262786865, "step": 21660 }, { "epoch": 0.12881098014040218, "grad_norm": 1.4047211408615112, "learning_rate": 8.586883297008124e-05, "loss": 0.7046274185180664, "step": 21670 }, { "epoch": 0.12887042221707057, "grad_norm": 1.4400951862335205, "learning_rate": 8.590846047156728e-05, "loss": 0.6280336380004883, "step": 21680 }, { "epoch": 0.12892986429373895, "grad_norm": 1.4228897094726562, "learning_rate": 8.59480879730533e-05, "loss": 0.6796706199645997, "step": 21690 }, { "epoch": 0.12898930637040737, "grad_norm": 1.378861665725708, "learning_rate": 8.598771547453933e-05, "loss": 0.6099263668060303, "step": 21700 }, { "epoch": 0.12904874844707576, "grad_norm": 1.5005176067352295, "learning_rate": 8.602734297602536e-05, "loss": 0.678607177734375, "step": 21710 }, { "epoch": 0.12910819052374414, "grad_norm": 1.6824864149093628, "learning_rate": 8.60669704775114e-05, "loss": 0.6421503067016602, "step": 21720 }, { "epoch": 0.12916763260041253, "grad_norm": 1.6597449779510498, "learning_rate": 8.610659797899743e-05, "loss": 0.6295423984527588, "step": 21730 }, { "epoch": 0.12922707467708092, "grad_norm": 1.339015245437622, "learning_rate": 8.614622548048346e-05, "loss": 0.6577629089355469, "step": 21740 }, { "epoch": 0.1292865167537493, "grad_norm": 1.6356643438339233, "learning_rate": 8.61858529819695e-05, "loss": 0.7204117774963379, "step": 21750 }, { "epoch": 0.1293459588304177, "grad_norm": 1.5888715982437134, "learning_rate": 8.622548048345552e-05, "loss": 0.7277634620666504, "step": 21760 }, { "epoch": 0.12940540090708608, "grad_norm": 1.4468729496002197, "learning_rate": 8.626510798494155e-05, "loss": 0.7302186489105225, "step": 21770 }, { "epoch": 0.1294648429837545, "grad_norm": 1.6998262405395508, "learning_rate": 8.630473548642759e-05, "loss": 0.7148172378540039, "step": 21780 }, { "epoch": 0.12952428506042288, "grad_norm": 1.5315338373184204, "learning_rate": 8.634436298791362e-05, "loss": 0.6871417045593262, "step": 21790 }, { "epoch": 0.12958372713709126, "grad_norm": 1.569047212600708, "learning_rate": 8.638399048939965e-05, "loss": 0.6807504177093506, "step": 21800 }, { "epoch": 0.12964316921375965, "grad_norm": 1.4107239246368408, "learning_rate": 8.642361799088567e-05, "loss": 0.6465951919555664, "step": 21810 }, { "epoch": 0.12970261129042804, "grad_norm": 1.9000040292739868, "learning_rate": 8.646324549237171e-05, "loss": 0.6160655975341797, "step": 21820 }, { "epoch": 0.12976205336709642, "grad_norm": 2.196946382522583, "learning_rate": 8.650287299385774e-05, "loss": 0.7404903411865235, "step": 21830 }, { "epoch": 0.1298214954437648, "grad_norm": 1.3238605260849, "learning_rate": 8.654250049534378e-05, "loss": 0.6799576282501221, "step": 21840 }, { "epoch": 0.12988093752043323, "grad_norm": 1.287215232849121, "learning_rate": 8.658212799682982e-05, "loss": 0.6790916442871093, "step": 21850 }, { "epoch": 0.1299403795971016, "grad_norm": 1.7384268045425415, "learning_rate": 8.662175549831584e-05, "loss": 0.7024404048919678, "step": 21860 }, { "epoch": 0.12999982167377, "grad_norm": 1.890415072441101, "learning_rate": 8.666138299980187e-05, "loss": 0.6064100742340088, "step": 21870 }, { "epoch": 0.1300592637504384, "grad_norm": 1.6764472723007202, "learning_rate": 8.670101050128789e-05, "loss": 0.6875456809997559, "step": 21880 }, { "epoch": 0.13011870582710677, "grad_norm": 1.2645692825317383, "learning_rate": 8.674063800277393e-05, "loss": 0.6897801399230957, "step": 21890 }, { "epoch": 0.13017814790377516, "grad_norm": 1.7152920961380005, "learning_rate": 8.678026550425995e-05, "loss": 0.6830826282501221, "step": 21900 }, { "epoch": 0.13023758998044355, "grad_norm": 1.478635549545288, "learning_rate": 8.681989300574599e-05, "loss": 0.6875678062438965, "step": 21910 }, { "epoch": 0.13029703205711196, "grad_norm": 1.460345983505249, "learning_rate": 8.685952050723203e-05, "loss": 0.6615975379943848, "step": 21920 }, { "epoch": 0.13035647413378035, "grad_norm": 1.7870519161224365, "learning_rate": 8.689914800871806e-05, "loss": 0.7070230484008789, "step": 21930 }, { "epoch": 0.13041591621044873, "grad_norm": 1.613037347793579, "learning_rate": 8.693877551020408e-05, "loss": 0.6927414894104004, "step": 21940 }, { "epoch": 0.13047535828711712, "grad_norm": 1.4561405181884766, "learning_rate": 8.697840301169011e-05, "loss": 0.6539937019348144, "step": 21950 }, { "epoch": 0.1305348003637855, "grad_norm": 1.1696571111679077, "learning_rate": 8.701803051317615e-05, "loss": 0.6747819900512695, "step": 21960 }, { "epoch": 0.1305942424404539, "grad_norm": 1.2874846458435059, "learning_rate": 8.705765801466218e-05, "loss": 0.6415006637573242, "step": 21970 }, { "epoch": 0.13065368451712228, "grad_norm": 1.6783146858215332, "learning_rate": 8.709728551614821e-05, "loss": 0.6948111534118653, "step": 21980 }, { "epoch": 0.13071312659379067, "grad_norm": 1.4721782207489014, "learning_rate": 8.713691301763425e-05, "loss": 0.7006255149841308, "step": 21990 }, { "epoch": 0.13077256867045908, "grad_norm": 1.7828853130340576, "learning_rate": 8.717654051912027e-05, "loss": 0.7368133544921875, "step": 22000 }, { "epoch": 0.13083201074712747, "grad_norm": 1.6087013483047485, "learning_rate": 8.72161680206063e-05, "loss": 0.6817740440368653, "step": 22010 }, { "epoch": 0.13089145282379586, "grad_norm": 1.3530220985412598, "learning_rate": 8.725579552209234e-05, "loss": 0.6647112369537354, "step": 22020 }, { "epoch": 0.13095089490046424, "grad_norm": 1.6641709804534912, "learning_rate": 8.729542302357838e-05, "loss": 0.7276406288146973, "step": 22030 }, { "epoch": 0.13101033697713263, "grad_norm": 1.2824310064315796, "learning_rate": 8.73350505250644e-05, "loss": 0.6480076789855957, "step": 22040 }, { "epoch": 0.13106977905380102, "grad_norm": 1.799246907234192, "learning_rate": 8.737467802655043e-05, "loss": 0.7488762378692627, "step": 22050 }, { "epoch": 0.1311292211304694, "grad_norm": 1.7183765172958374, "learning_rate": 8.741430552803646e-05, "loss": 0.6521009922027587, "step": 22060 }, { "epoch": 0.13118866320713782, "grad_norm": 1.6761999130249023, "learning_rate": 8.745393302952249e-05, "loss": 0.6810362339019775, "step": 22070 }, { "epoch": 0.1312481052838062, "grad_norm": 1.5617612600326538, "learning_rate": 8.749356053100853e-05, "loss": 0.6688961982727051, "step": 22080 }, { "epoch": 0.1313075473604746, "grad_norm": 1.34565269947052, "learning_rate": 8.753318803249455e-05, "loss": 0.6829273700714111, "step": 22090 }, { "epoch": 0.13136698943714298, "grad_norm": 1.496733546257019, "learning_rate": 8.757281553398059e-05, "loss": 0.718566608428955, "step": 22100 }, { "epoch": 0.13142643151381136, "grad_norm": 1.6273314952850342, "learning_rate": 8.761244303546662e-05, "loss": 0.6703326225280761, "step": 22110 }, { "epoch": 0.13148587359047975, "grad_norm": 1.6055759191513062, "learning_rate": 8.765207053695264e-05, "loss": 0.6827625274658203, "step": 22120 }, { "epoch": 0.13154531566714814, "grad_norm": 1.6654762029647827, "learning_rate": 8.769169803843868e-05, "loss": 0.7367052555084228, "step": 22130 }, { "epoch": 0.13160475774381653, "grad_norm": 1.6150985956192017, "learning_rate": 8.773132553992472e-05, "loss": 0.7267957210540772, "step": 22140 }, { "epoch": 0.13166419982048494, "grad_norm": 1.4450725317001343, "learning_rate": 8.777095304141074e-05, "loss": 0.662015151977539, "step": 22150 }, { "epoch": 0.13172364189715333, "grad_norm": 1.4711415767669678, "learning_rate": 8.781058054289677e-05, "loss": 0.649857759475708, "step": 22160 }, { "epoch": 0.1317830839738217, "grad_norm": 1.5169305801391602, "learning_rate": 8.785020804438281e-05, "loss": 0.662403678894043, "step": 22170 }, { "epoch": 0.1318425260504901, "grad_norm": 1.4819003343582153, "learning_rate": 8.788983554586883e-05, "loss": 0.6445390701293945, "step": 22180 }, { "epoch": 0.1319019681271585, "grad_norm": 1.3878872394561768, "learning_rate": 8.792946304735486e-05, "loss": 0.6464136123657227, "step": 22190 }, { "epoch": 0.13196141020382687, "grad_norm": 1.5403894186019897, "learning_rate": 8.796909054884091e-05, "loss": 0.7085058212280273, "step": 22200 }, { "epoch": 0.13202085228049526, "grad_norm": 1.4666261672973633, "learning_rate": 8.800871805032694e-05, "loss": 0.6860109806060791, "step": 22210 }, { "epoch": 0.13208029435716367, "grad_norm": 1.8205734491348267, "learning_rate": 8.804834555181296e-05, "loss": 0.7112030982971191, "step": 22220 }, { "epoch": 0.13213973643383206, "grad_norm": 1.957763910293579, "learning_rate": 8.808797305329899e-05, "loss": 0.7187738418579102, "step": 22230 }, { "epoch": 0.13219917851050045, "grad_norm": 1.329811453819275, "learning_rate": 8.812760055478502e-05, "loss": 0.6595998764038086, "step": 22240 }, { "epoch": 0.13225862058716883, "grad_norm": 1.3219767808914185, "learning_rate": 8.816722805627105e-05, "loss": 0.6716895580291748, "step": 22250 }, { "epoch": 0.13231806266383722, "grad_norm": 1.2883636951446533, "learning_rate": 8.820685555775709e-05, "loss": 0.6586114883422851, "step": 22260 }, { "epoch": 0.1323775047405056, "grad_norm": 1.692539095878601, "learning_rate": 8.824648305924313e-05, "loss": 0.6747384071350098, "step": 22270 }, { "epoch": 0.132436946817174, "grad_norm": 1.5134721994400024, "learning_rate": 8.828611056072915e-05, "loss": 0.6534433364868164, "step": 22280 }, { "epoch": 0.13249638889384238, "grad_norm": 1.4781466722488403, "learning_rate": 8.832573806221518e-05, "loss": 0.6601239204406738, "step": 22290 }, { "epoch": 0.1325558309705108, "grad_norm": 1.7444487810134888, "learning_rate": 8.83653655637012e-05, "loss": 0.6540407657623291, "step": 22300 }, { "epoch": 0.13261527304717918, "grad_norm": 1.3823926448822021, "learning_rate": 8.840499306518724e-05, "loss": 0.6040654182434082, "step": 22310 }, { "epoch": 0.13267471512384757, "grad_norm": 1.5501844882965088, "learning_rate": 8.844462056667328e-05, "loss": 0.6255311965942383, "step": 22320 }, { "epoch": 0.13273415720051596, "grad_norm": 1.6846569776535034, "learning_rate": 8.84842480681593e-05, "loss": 0.6663444995880127, "step": 22330 }, { "epoch": 0.13279359927718434, "grad_norm": 1.5496246814727783, "learning_rate": 8.852387556964534e-05, "loss": 0.737816047668457, "step": 22340 }, { "epoch": 0.13285304135385273, "grad_norm": 1.9311970472335815, "learning_rate": 8.856350307113137e-05, "loss": 0.6695323944091797, "step": 22350 }, { "epoch": 0.13291248343052112, "grad_norm": 1.7347739934921265, "learning_rate": 8.86031305726174e-05, "loss": 0.6322771072387695, "step": 22360 }, { "epoch": 0.13297192550718953, "grad_norm": 1.926051139831543, "learning_rate": 8.864275807410343e-05, "loss": 0.6904955863952636, "step": 22370 }, { "epoch": 0.13303136758385792, "grad_norm": 1.579463243484497, "learning_rate": 8.868238557558947e-05, "loss": 0.6373051166534424, "step": 22380 }, { "epoch": 0.1330908096605263, "grad_norm": 1.4048823118209839, "learning_rate": 8.87220130770755e-05, "loss": 0.6422138214111328, "step": 22390 }, { "epoch": 0.1331502517371947, "grad_norm": 1.714167833328247, "learning_rate": 8.876164057856152e-05, "loss": 0.7226762771606445, "step": 22400 }, { "epoch": 0.13320969381386308, "grad_norm": 1.6238553524017334, "learning_rate": 8.880126808004756e-05, "loss": 0.6759088516235352, "step": 22410 }, { "epoch": 0.13326913589053146, "grad_norm": 1.775992512702942, "learning_rate": 8.884089558153359e-05, "loss": 0.6459846019744873, "step": 22420 }, { "epoch": 0.13332857796719985, "grad_norm": 1.7994701862335205, "learning_rate": 8.888052308301962e-05, "loss": 0.6506903648376465, "step": 22430 }, { "epoch": 0.13338802004386827, "grad_norm": 1.416523814201355, "learning_rate": 8.892015058450565e-05, "loss": 0.6080383777618408, "step": 22440 }, { "epoch": 0.13344746212053665, "grad_norm": 1.5862390995025635, "learning_rate": 8.895977808599169e-05, "loss": 0.7153586387634278, "step": 22450 }, { "epoch": 0.13350690419720504, "grad_norm": 1.5998445749282837, "learning_rate": 8.899940558747771e-05, "loss": 0.7080839157104493, "step": 22460 }, { "epoch": 0.13356634627387343, "grad_norm": 2.1211156845092773, "learning_rate": 8.903903308896374e-05, "loss": 0.6907943248748779, "step": 22470 }, { "epoch": 0.1336257883505418, "grad_norm": 1.6835891008377075, "learning_rate": 8.907866059044978e-05, "loss": 0.6201964855194092, "step": 22480 }, { "epoch": 0.1336852304272102, "grad_norm": 1.5884664058685303, "learning_rate": 8.911828809193582e-05, "loss": 0.7736836433410644, "step": 22490 }, { "epoch": 0.1337446725038786, "grad_norm": 1.5350958108901978, "learning_rate": 8.915791559342184e-05, "loss": 0.6214091777801514, "step": 22500 }, { "epoch": 0.13380411458054697, "grad_norm": 1.7449500560760498, "learning_rate": 8.919754309490787e-05, "loss": 0.6945363998413085, "step": 22510 }, { "epoch": 0.1338635566572154, "grad_norm": 1.2873668670654297, "learning_rate": 8.92371705963939e-05, "loss": 0.739850664138794, "step": 22520 }, { "epoch": 0.13392299873388377, "grad_norm": 1.7688723802566528, "learning_rate": 8.927679809787993e-05, "loss": 0.6150761127471924, "step": 22530 }, { "epoch": 0.13398244081055216, "grad_norm": 1.8342902660369873, "learning_rate": 8.931642559936595e-05, "loss": 0.7216455459594726, "step": 22540 }, { "epoch": 0.13404188288722055, "grad_norm": 1.6671767234802246, "learning_rate": 8.9356053100852e-05, "loss": 0.687594985961914, "step": 22550 }, { "epoch": 0.13410132496388893, "grad_norm": 1.2810646295547485, "learning_rate": 8.939568060233803e-05, "loss": 0.6357198715209961, "step": 22560 }, { "epoch": 0.13416076704055732, "grad_norm": 1.4413399696350098, "learning_rate": 8.943530810382406e-05, "loss": 0.6784326553344726, "step": 22570 }, { "epoch": 0.1342202091172257, "grad_norm": 1.1565449237823486, "learning_rate": 8.947493560531008e-05, "loss": 0.6761880397796631, "step": 22580 }, { "epoch": 0.13427965119389412, "grad_norm": 1.502262830734253, "learning_rate": 8.951456310679612e-05, "loss": 0.7142024993896484, "step": 22590 }, { "epoch": 0.1343390932705625, "grad_norm": 1.6660085916519165, "learning_rate": 8.955419060828215e-05, "loss": 0.6583219528198242, "step": 22600 }, { "epoch": 0.1343985353472309, "grad_norm": 1.4413305521011353, "learning_rate": 8.959381810976818e-05, "loss": 0.6649471282958984, "step": 22610 }, { "epoch": 0.13445797742389928, "grad_norm": 1.686589002609253, "learning_rate": 8.963344561125422e-05, "loss": 0.6894227981567382, "step": 22620 }, { "epoch": 0.13451741950056767, "grad_norm": 1.6050938367843628, "learning_rate": 8.967307311274025e-05, "loss": 0.6269500732421875, "step": 22630 }, { "epoch": 0.13457686157723606, "grad_norm": 1.3485486507415771, "learning_rate": 8.971270061422627e-05, "loss": 0.660768985748291, "step": 22640 }, { "epoch": 0.13463630365390444, "grad_norm": 1.4160189628601074, "learning_rate": 8.975232811571231e-05, "loss": 0.6992058753967285, "step": 22650 }, { "epoch": 0.13469574573057283, "grad_norm": 1.6916823387145996, "learning_rate": 8.979195561719834e-05, "loss": 0.6435736656188965, "step": 22660 }, { "epoch": 0.13475518780724124, "grad_norm": 1.5105422735214233, "learning_rate": 8.983158311868438e-05, "loss": 0.7317740440368652, "step": 22670 }, { "epoch": 0.13481462988390963, "grad_norm": 1.7950843572616577, "learning_rate": 8.98712106201704e-05, "loss": 0.7367418289184571, "step": 22680 }, { "epoch": 0.13487407196057802, "grad_norm": 1.4337342977523804, "learning_rate": 8.991083812165644e-05, "loss": 0.6515811443328857, "step": 22690 }, { "epoch": 0.1349335140372464, "grad_norm": 1.2479907274246216, "learning_rate": 8.995046562314246e-05, "loss": 0.6778416156768798, "step": 22700 }, { "epoch": 0.1349929561139148, "grad_norm": 1.8963618278503418, "learning_rate": 8.999009312462849e-05, "loss": 0.6706124305725097, "step": 22710 }, { "epoch": 0.13505239819058318, "grad_norm": 1.3863391876220703, "learning_rate": 9.002972062611453e-05, "loss": 0.6678085327148438, "step": 22720 }, { "epoch": 0.13511184026725157, "grad_norm": 1.447581171989441, "learning_rate": 9.006934812760057e-05, "loss": 0.6980408668518067, "step": 22730 }, { "epoch": 0.13517128234391998, "grad_norm": 1.3585516214370728, "learning_rate": 9.010897562908659e-05, "loss": 0.6555740356445312, "step": 22740 }, { "epoch": 0.13523072442058837, "grad_norm": 1.8428760766983032, "learning_rate": 9.014860313057262e-05, "loss": 0.6432295799255371, "step": 22750 }, { "epoch": 0.13529016649725675, "grad_norm": 1.3022143840789795, "learning_rate": 9.018823063205866e-05, "loss": 0.6785510063171387, "step": 22760 }, { "epoch": 0.13534960857392514, "grad_norm": 1.5388686656951904, "learning_rate": 9.022785813354468e-05, "loss": 0.6738354206085205, "step": 22770 }, { "epoch": 0.13540905065059353, "grad_norm": 1.3197057247161865, "learning_rate": 9.026748563503072e-05, "loss": 0.6222348213195801, "step": 22780 }, { "epoch": 0.1354684927272619, "grad_norm": 1.5919935703277588, "learning_rate": 9.030711313651676e-05, "loss": 0.6603370666503906, "step": 22790 }, { "epoch": 0.1355279348039303, "grad_norm": 1.654435396194458, "learning_rate": 9.034674063800278e-05, "loss": 0.7433196067810058, "step": 22800 }, { "epoch": 0.1355873768805987, "grad_norm": 1.4683948755264282, "learning_rate": 9.038636813948881e-05, "loss": 0.7271876335144043, "step": 22810 }, { "epoch": 0.1356468189572671, "grad_norm": 1.54644775390625, "learning_rate": 9.042599564097483e-05, "loss": 0.6588253974914551, "step": 22820 }, { "epoch": 0.1357062610339355, "grad_norm": 1.596110224723816, "learning_rate": 9.046562314246087e-05, "loss": 0.6918825149536133, "step": 22830 }, { "epoch": 0.13576570311060387, "grad_norm": 1.1647191047668457, "learning_rate": 9.050525064394691e-05, "loss": 0.6832963466644287, "step": 22840 }, { "epoch": 0.13582514518727226, "grad_norm": 1.5650615692138672, "learning_rate": 9.054487814543294e-05, "loss": 0.6248585224151612, "step": 22850 }, { "epoch": 0.13588458726394065, "grad_norm": 1.8775157928466797, "learning_rate": 9.058450564691897e-05, "loss": 0.6643957138061524, "step": 22860 }, { "epoch": 0.13594402934060903, "grad_norm": 1.4292070865631104, "learning_rate": 9.0624133148405e-05, "loss": 0.6709583759307861, "step": 22870 }, { "epoch": 0.13600347141727742, "grad_norm": 1.493744969367981, "learning_rate": 9.066376064989102e-05, "loss": 0.6455458641052246, "step": 22880 }, { "epoch": 0.13606291349394584, "grad_norm": 1.2682493925094604, "learning_rate": 9.070338815137705e-05, "loss": 0.6722549438476563, "step": 22890 }, { "epoch": 0.13612235557061422, "grad_norm": 1.340142011642456, "learning_rate": 9.074301565286309e-05, "loss": 0.6693305969238281, "step": 22900 }, { "epoch": 0.1361817976472826, "grad_norm": 1.413222074508667, "learning_rate": 9.078264315434913e-05, "loss": 0.7108263492584228, "step": 22910 }, { "epoch": 0.136241239723951, "grad_norm": 1.9580413103103638, "learning_rate": 9.082227065583515e-05, "loss": 0.700701093673706, "step": 22920 }, { "epoch": 0.13630068180061938, "grad_norm": 1.7432582378387451, "learning_rate": 9.086189815732119e-05, "loss": 0.7424869537353516, "step": 22930 }, { "epoch": 0.13636012387728777, "grad_norm": 1.5802682638168335, "learning_rate": 9.090152565880722e-05, "loss": 0.7129180908203125, "step": 22940 }, { "epoch": 0.13641956595395616, "grad_norm": 1.8055601119995117, "learning_rate": 9.094115316029324e-05, "loss": 0.7000280380249023, "step": 22950 }, { "epoch": 0.13647900803062457, "grad_norm": 1.180925965309143, "learning_rate": 9.098078066177928e-05, "loss": 0.7051392555236816, "step": 22960 }, { "epoch": 0.13653845010729296, "grad_norm": 1.5146806240081787, "learning_rate": 9.102040816326532e-05, "loss": 0.6704654693603516, "step": 22970 }, { "epoch": 0.13659789218396134, "grad_norm": 1.4849032163619995, "learning_rate": 9.106003566475134e-05, "loss": 0.7298219680786133, "step": 22980 }, { "epoch": 0.13665733426062973, "grad_norm": 1.5454128980636597, "learning_rate": 9.109966316623737e-05, "loss": 0.6095915794372558, "step": 22990 }, { "epoch": 0.13671677633729812, "grad_norm": 1.8627827167510986, "learning_rate": 9.113929066772341e-05, "loss": 0.6650213241577149, "step": 23000 }, { "epoch": 0.1367762184139665, "grad_norm": 1.6977804899215698, "learning_rate": 9.117891816920943e-05, "loss": 0.6447139739990234, "step": 23010 }, { "epoch": 0.1368356604906349, "grad_norm": 1.792479395866394, "learning_rate": 9.121854567069547e-05, "loss": 0.6989271163940429, "step": 23020 }, { "epoch": 0.13689510256730328, "grad_norm": 1.5110505819320679, "learning_rate": 9.12581731721815e-05, "loss": 0.6200662612915039, "step": 23030 }, { "epoch": 0.1369545446439717, "grad_norm": 1.552736520767212, "learning_rate": 9.129780067366753e-05, "loss": 0.6711291313171387, "step": 23040 }, { "epoch": 0.13701398672064008, "grad_norm": 1.302115797996521, "learning_rate": 9.133742817515356e-05, "loss": 0.6392436981201172, "step": 23050 }, { "epoch": 0.13707342879730847, "grad_norm": 1.3656436204910278, "learning_rate": 9.137705567663958e-05, "loss": 0.7292123317718506, "step": 23060 }, { "epoch": 0.13713287087397685, "grad_norm": 1.5431528091430664, "learning_rate": 9.141668317812562e-05, "loss": 0.7138402938842774, "step": 23070 }, { "epoch": 0.13719231295064524, "grad_norm": 1.6062431335449219, "learning_rate": 9.145631067961166e-05, "loss": 0.6463310241699218, "step": 23080 }, { "epoch": 0.13725175502731363, "grad_norm": 1.4366456270217896, "learning_rate": 9.149593818109769e-05, "loss": 0.6934885025024414, "step": 23090 }, { "epoch": 0.137311197103982, "grad_norm": 1.4738523960113525, "learning_rate": 9.153556568258371e-05, "loss": 0.6484643936157226, "step": 23100 }, { "epoch": 0.13737063918065043, "grad_norm": 1.4784873723983765, "learning_rate": 9.157519318406975e-05, "loss": 0.6657576560974121, "step": 23110 }, { "epoch": 0.13743008125731881, "grad_norm": 1.7842247486114502, "learning_rate": 9.161482068555578e-05, "loss": 0.7117067337036133, "step": 23120 }, { "epoch": 0.1374895233339872, "grad_norm": 1.272251009941101, "learning_rate": 9.165444818704181e-05, "loss": 0.6910497188568115, "step": 23130 }, { "epoch": 0.1375489654106556, "grad_norm": 1.7841145992279053, "learning_rate": 9.169407568852785e-05, "loss": 0.714700174331665, "step": 23140 }, { "epoch": 0.13760840748732397, "grad_norm": 1.2744206190109253, "learning_rate": 9.173370319001388e-05, "loss": 0.6787005424499511, "step": 23150 }, { "epoch": 0.13766784956399236, "grad_norm": 1.5087491273880005, "learning_rate": 9.17733306914999e-05, "loss": 0.6952691078186035, "step": 23160 }, { "epoch": 0.13772729164066075, "grad_norm": 1.5583449602127075, "learning_rate": 9.181295819298593e-05, "loss": 0.6788583755493164, "step": 23170 }, { "epoch": 0.13778673371732914, "grad_norm": 1.709152102470398, "learning_rate": 9.185258569447197e-05, "loss": 0.6467827796936035, "step": 23180 }, { "epoch": 0.13784617579399755, "grad_norm": 2.75624418258667, "learning_rate": 9.189221319595799e-05, "loss": 0.66744384765625, "step": 23190 }, { "epoch": 0.13790561787066594, "grad_norm": 1.3400295972824097, "learning_rate": 9.193184069744403e-05, "loss": 0.635882043838501, "step": 23200 }, { "epoch": 0.13796505994733432, "grad_norm": 1.7410264015197754, "learning_rate": 9.197146819893007e-05, "loss": 0.6277451992034913, "step": 23210 }, { "epoch": 0.1380245020240027, "grad_norm": 1.4033136367797852, "learning_rate": 9.20110957004161e-05, "loss": 0.6892106533050537, "step": 23220 }, { "epoch": 0.1380839441006711, "grad_norm": 1.75624680519104, "learning_rate": 9.205072320190212e-05, "loss": 0.666701078414917, "step": 23230 }, { "epoch": 0.13814338617733948, "grad_norm": 1.4759360551834106, "learning_rate": 9.209035070338814e-05, "loss": 0.6513251304626465, "step": 23240 }, { "epoch": 0.13820282825400787, "grad_norm": 1.4217463731765747, "learning_rate": 9.212997820487418e-05, "loss": 0.677138376235962, "step": 23250 }, { "epoch": 0.13826227033067628, "grad_norm": 1.6278067827224731, "learning_rate": 9.216960570636022e-05, "loss": 0.6716855049133301, "step": 23260 }, { "epoch": 0.13832171240734467, "grad_norm": 1.966701865196228, "learning_rate": 9.220923320784625e-05, "loss": 0.6697910308837891, "step": 23270 }, { "epoch": 0.13838115448401306, "grad_norm": 1.8217499256134033, "learning_rate": 9.224886070933229e-05, "loss": 0.6992684364318847, "step": 23280 }, { "epoch": 0.13844059656068144, "grad_norm": 1.3899425268173218, "learning_rate": 9.228848821081831e-05, "loss": 0.7016522407531738, "step": 23290 }, { "epoch": 0.13850003863734983, "grad_norm": 1.5442062616348267, "learning_rate": 9.232811571230434e-05, "loss": 0.7068727493286133, "step": 23300 }, { "epoch": 0.13855948071401822, "grad_norm": 2.130244731903076, "learning_rate": 9.236774321379037e-05, "loss": 0.7202357292175293, "step": 23310 }, { "epoch": 0.1386189227906866, "grad_norm": 1.3273078203201294, "learning_rate": 9.240737071527641e-05, "loss": 0.6337714195251465, "step": 23320 }, { "epoch": 0.13867836486735502, "grad_norm": 1.6287778615951538, "learning_rate": 9.244699821676244e-05, "loss": 0.7332880020141601, "step": 23330 }, { "epoch": 0.1387378069440234, "grad_norm": 1.1751967668533325, "learning_rate": 9.248662571824846e-05, "loss": 0.6699749946594238, "step": 23340 }, { "epoch": 0.1387972490206918, "grad_norm": 1.5606791973114014, "learning_rate": 9.25262532197345e-05, "loss": 0.6570118427276611, "step": 23350 }, { "epoch": 0.13885669109736018, "grad_norm": 1.4614719152450562, "learning_rate": 9.256588072122053e-05, "loss": 0.6972215652465821, "step": 23360 }, { "epoch": 0.13891613317402857, "grad_norm": 1.5957266092300415, "learning_rate": 9.260550822270657e-05, "loss": 0.6795605659484864, "step": 23370 }, { "epoch": 0.13897557525069695, "grad_norm": 1.4272489547729492, "learning_rate": 9.264513572419259e-05, "loss": 0.7118478775024414, "step": 23380 }, { "epoch": 0.13903501732736534, "grad_norm": 1.799774408340454, "learning_rate": 9.268476322567863e-05, "loss": 0.7756362438201905, "step": 23390 }, { "epoch": 0.13909445940403373, "grad_norm": 1.3471688032150269, "learning_rate": 9.272439072716465e-05, "loss": 0.6791042804718017, "step": 23400 }, { "epoch": 0.13915390148070214, "grad_norm": 1.9647198915481567, "learning_rate": 9.276401822865068e-05, "loss": 0.686758279800415, "step": 23410 }, { "epoch": 0.13921334355737053, "grad_norm": 1.0792099237442017, "learning_rate": 9.280364573013672e-05, "loss": 0.666943883895874, "step": 23420 }, { "epoch": 0.13927278563403891, "grad_norm": 1.4082545042037964, "learning_rate": 9.284327323162276e-05, "loss": 0.7061716556549072, "step": 23430 }, { "epoch": 0.1393322277107073, "grad_norm": 1.4463915824890137, "learning_rate": 9.288290073310878e-05, "loss": 0.6196876525878906, "step": 23440 }, { "epoch": 0.1393916697873757, "grad_norm": 1.5894087553024292, "learning_rate": 9.292252823459481e-05, "loss": 0.7097285270690918, "step": 23450 }, { "epoch": 0.13945111186404407, "grad_norm": 1.5146150588989258, "learning_rate": 9.296215573608085e-05, "loss": 0.7181629180908203, "step": 23460 }, { "epoch": 0.13951055394071246, "grad_norm": 1.5023475885391235, "learning_rate": 9.300178323756687e-05, "loss": 0.6367462158203125, "step": 23470 }, { "epoch": 0.13956999601738088, "grad_norm": 1.4857499599456787, "learning_rate": 9.304141073905291e-05, "loss": 0.7042599201202393, "step": 23480 }, { "epoch": 0.13962943809404926, "grad_norm": 1.6822015047073364, "learning_rate": 9.308103824053895e-05, "loss": 0.7652186393737793, "step": 23490 }, { "epoch": 0.13968888017071765, "grad_norm": 1.5760741233825684, "learning_rate": 9.312066574202497e-05, "loss": 0.6855565071105957, "step": 23500 }, { "epoch": 0.13974832224738604, "grad_norm": 1.6273587942123413, "learning_rate": 9.3160293243511e-05, "loss": 0.7001286506652832, "step": 23510 }, { "epoch": 0.13980776432405442, "grad_norm": 1.5637093782424927, "learning_rate": 9.319992074499702e-05, "loss": 0.6843839645385742, "step": 23520 }, { "epoch": 0.1398672064007228, "grad_norm": 1.6814210414886475, "learning_rate": 9.323954824648306e-05, "loss": 0.6878750801086426, "step": 23530 }, { "epoch": 0.1399266484773912, "grad_norm": 1.6587159633636475, "learning_rate": 9.327917574796909e-05, "loss": 0.6906249523162842, "step": 23540 }, { "epoch": 0.13998609055405958, "grad_norm": 1.167691946029663, "learning_rate": 9.331880324945513e-05, "loss": 0.6795547485351563, "step": 23550 }, { "epoch": 0.140045532630728, "grad_norm": 1.3238929510116577, "learning_rate": 9.335843075094116e-05, "loss": 0.6498281478881835, "step": 23560 }, { "epoch": 0.14010497470739638, "grad_norm": 1.3585375547409058, "learning_rate": 9.339805825242719e-05, "loss": 0.6408620834350586, "step": 23570 }, { "epoch": 0.14016441678406477, "grad_norm": 1.3493036031723022, "learning_rate": 9.343768575391322e-05, "loss": 0.7077983856201172, "step": 23580 }, { "epoch": 0.14022385886073316, "grad_norm": 1.6542625427246094, "learning_rate": 9.347731325539925e-05, "loss": 0.6667759895324707, "step": 23590 }, { "epoch": 0.14028330093740154, "grad_norm": 1.435185432434082, "learning_rate": 9.351694075688528e-05, "loss": 0.6781134605407715, "step": 23600 }, { "epoch": 0.14034274301406993, "grad_norm": 1.5948396921157837, "learning_rate": 9.355656825837132e-05, "loss": 0.7239944458007812, "step": 23610 }, { "epoch": 0.14040218509073832, "grad_norm": 1.6228358745574951, "learning_rate": 9.359619575985734e-05, "loss": 0.645404577255249, "step": 23620 }, { "epoch": 0.14046162716740673, "grad_norm": 1.5780894756317139, "learning_rate": 9.363582326134338e-05, "loss": 0.6534253120422363, "step": 23630 }, { "epoch": 0.14052106924407512, "grad_norm": 1.5605920553207397, "learning_rate": 9.36754507628294e-05, "loss": 0.6758529663085937, "step": 23640 }, { "epoch": 0.1405805113207435, "grad_norm": 1.6526601314544678, "learning_rate": 9.371507826431543e-05, "loss": 0.7096070289611817, "step": 23650 }, { "epoch": 0.1406399533974119, "grad_norm": 1.4811784029006958, "learning_rate": 9.375470576580147e-05, "loss": 0.6596128463745117, "step": 23660 }, { "epoch": 0.14069939547408028, "grad_norm": 1.748533844947815, "learning_rate": 9.379433326728751e-05, "loss": 0.6703426837921143, "step": 23670 }, { "epoch": 0.14075883755074867, "grad_norm": 1.4372875690460205, "learning_rate": 9.383396076877353e-05, "loss": 0.6763474464416503, "step": 23680 }, { "epoch": 0.14081827962741705, "grad_norm": 2.0216755867004395, "learning_rate": 9.387358827025956e-05, "loss": 0.7288232803344726, "step": 23690 }, { "epoch": 0.14087772170408544, "grad_norm": 1.545739769935608, "learning_rate": 9.39132157717456e-05, "loss": 0.6794417858123779, "step": 23700 }, { "epoch": 0.14093716378075385, "grad_norm": 1.4961423873901367, "learning_rate": 9.395284327323162e-05, "loss": 0.6794502258300781, "step": 23710 }, { "epoch": 0.14099660585742224, "grad_norm": 1.5426479578018188, "learning_rate": 9.399247077471766e-05, "loss": 0.6871635437011718, "step": 23720 }, { "epoch": 0.14105604793409063, "grad_norm": 1.4180530309677124, "learning_rate": 9.40320982762037e-05, "loss": 0.6820847511291503, "step": 23730 }, { "epoch": 0.14111549001075901, "grad_norm": 1.4946589469909668, "learning_rate": 9.407172577768973e-05, "loss": 0.7222921848297119, "step": 23740 }, { "epoch": 0.1411749320874274, "grad_norm": 1.6408733129501343, "learning_rate": 9.411135327917575e-05, "loss": 0.7158643722534179, "step": 23750 }, { "epoch": 0.1412343741640958, "grad_norm": 1.5968199968338013, "learning_rate": 9.415098078066178e-05, "loss": 0.6780793190002441, "step": 23760 }, { "epoch": 0.14129381624076418, "grad_norm": 1.6533528566360474, "learning_rate": 9.419060828214781e-05, "loss": 0.6854883193969726, "step": 23770 }, { "epoch": 0.1413532583174326, "grad_norm": 1.6564689874649048, "learning_rate": 9.423023578363385e-05, "loss": 0.6867640495300293, "step": 23780 }, { "epoch": 0.14141270039410098, "grad_norm": 1.3022923469543457, "learning_rate": 9.426986328511988e-05, "loss": 0.6787199020385742, "step": 23790 }, { "epoch": 0.14147214247076936, "grad_norm": 1.7143309116363525, "learning_rate": 9.430949078660592e-05, "loss": 0.6767579555511475, "step": 23800 }, { "epoch": 0.14153158454743775, "grad_norm": 1.385382890701294, "learning_rate": 9.434911828809194e-05, "loss": 0.7046177864074707, "step": 23810 }, { "epoch": 0.14159102662410614, "grad_norm": 2.002519369125366, "learning_rate": 9.438874578957797e-05, "loss": 0.7149288177490234, "step": 23820 }, { "epoch": 0.14165046870077452, "grad_norm": 1.3408480882644653, "learning_rate": 9.442837329106399e-05, "loss": 0.661596155166626, "step": 23830 }, { "epoch": 0.1417099107774429, "grad_norm": 1.598802924156189, "learning_rate": 9.446800079255004e-05, "loss": 0.7005719184875489, "step": 23840 }, { "epoch": 0.14176935285411132, "grad_norm": 1.8417986631393433, "learning_rate": 9.450762829403607e-05, "loss": 0.7188939094543457, "step": 23850 }, { "epoch": 0.1418287949307797, "grad_norm": 1.6309144496917725, "learning_rate": 9.45472557955221e-05, "loss": 0.6198280811309814, "step": 23860 }, { "epoch": 0.1418882370074481, "grad_norm": 1.4170258045196533, "learning_rate": 9.458688329700813e-05, "loss": 0.6607338905334472, "step": 23870 }, { "epoch": 0.14194767908411648, "grad_norm": 1.4839037656784058, "learning_rate": 9.462651079849416e-05, "loss": 0.7191334247589112, "step": 23880 }, { "epoch": 0.14200712116078487, "grad_norm": 1.4127165079116821, "learning_rate": 9.466613829998018e-05, "loss": 0.6691612243652344, "step": 23890 }, { "epoch": 0.14206656323745326, "grad_norm": 1.4860093593597412, "learning_rate": 9.470576580146622e-05, "loss": 0.6809754371643066, "step": 23900 }, { "epoch": 0.14212600531412165, "grad_norm": 1.39707350730896, "learning_rate": 9.474539330295226e-05, "loss": 0.6568688869476318, "step": 23910 }, { "epoch": 0.14218544739079003, "grad_norm": 1.324562907218933, "learning_rate": 9.478502080443829e-05, "loss": 0.6569668292999268, "step": 23920 }, { "epoch": 0.14224488946745845, "grad_norm": 1.8638105392456055, "learning_rate": 9.482464830592431e-05, "loss": 0.6511167526245117, "step": 23930 }, { "epoch": 0.14230433154412683, "grad_norm": 1.6091281175613403, "learning_rate": 9.486427580741035e-05, "loss": 0.6749666213989258, "step": 23940 }, { "epoch": 0.14236377362079522, "grad_norm": 2.086076498031616, "learning_rate": 9.490390330889637e-05, "loss": 0.7196837425231933, "step": 23950 }, { "epoch": 0.1424232156974636, "grad_norm": 1.3495960235595703, "learning_rate": 9.494353081038241e-05, "loss": 0.6896409511566162, "step": 23960 }, { "epoch": 0.142482657774132, "grad_norm": 1.770957350730896, "learning_rate": 9.498315831186844e-05, "loss": 0.63279128074646, "step": 23970 }, { "epoch": 0.14254209985080038, "grad_norm": 1.68500816822052, "learning_rate": 9.502278581335448e-05, "loss": 0.6875768661499023, "step": 23980 }, { "epoch": 0.14260154192746877, "grad_norm": 1.4673385620117188, "learning_rate": 9.50624133148405e-05, "loss": 0.7107004165649414, "step": 23990 }, { "epoch": 0.14266098400413718, "grad_norm": 1.099636197090149, "learning_rate": 9.510204081632653e-05, "loss": 0.6307018756866455, "step": 24000 }, { "epoch": 0.14272042608080557, "grad_norm": 1.9142942428588867, "learning_rate": 9.514166831781257e-05, "loss": 0.7310429573059082, "step": 24010 }, { "epoch": 0.14277986815747395, "grad_norm": 1.4678257703781128, "learning_rate": 9.51812958192986e-05, "loss": 0.666484260559082, "step": 24020 }, { "epoch": 0.14283931023414234, "grad_norm": 1.3429540395736694, "learning_rate": 9.522092332078463e-05, "loss": 0.6294547080993652, "step": 24030 }, { "epoch": 0.14289875231081073, "grad_norm": 1.6371078491210938, "learning_rate": 9.526055082227065e-05, "loss": 0.7134583473205567, "step": 24040 }, { "epoch": 0.14295819438747912, "grad_norm": 2.0368781089782715, "learning_rate": 9.530017832375669e-05, "loss": 0.6310841083526612, "step": 24050 }, { "epoch": 0.1430176364641475, "grad_norm": 1.5765454769134521, "learning_rate": 9.533980582524272e-05, "loss": 0.6965339660644532, "step": 24060 }, { "epoch": 0.1430770785408159, "grad_norm": 1.735313057899475, "learning_rate": 9.537943332672876e-05, "loss": 0.7996318817138672, "step": 24070 }, { "epoch": 0.1431365206174843, "grad_norm": 1.349758267402649, "learning_rate": 9.54190608282148e-05, "loss": 0.6887154579162598, "step": 24080 }, { "epoch": 0.1431959626941527, "grad_norm": 1.8983794450759888, "learning_rate": 9.545868832970082e-05, "loss": 0.6689794540405274, "step": 24090 }, { "epoch": 0.14325540477082108, "grad_norm": 1.5852093696594238, "learning_rate": 9.549831583118685e-05, "loss": 0.6627001762390137, "step": 24100 }, { "epoch": 0.14331484684748946, "grad_norm": 1.5251290798187256, "learning_rate": 9.553794333267287e-05, "loss": 0.683983564376831, "step": 24110 }, { "epoch": 0.14337428892415785, "grad_norm": 1.628511905670166, "learning_rate": 9.557757083415891e-05, "loss": 0.7062881469726563, "step": 24120 }, { "epoch": 0.14343373100082624, "grad_norm": 1.7084722518920898, "learning_rate": 9.561719833564495e-05, "loss": 0.7601483821868896, "step": 24130 }, { "epoch": 0.14349317307749462, "grad_norm": 1.8157927989959717, "learning_rate": 9.565682583713097e-05, "loss": 0.6775504589080811, "step": 24140 }, { "epoch": 0.14355261515416304, "grad_norm": 1.4999197721481323, "learning_rate": 9.569645333861701e-05, "loss": 0.6447939872741699, "step": 24150 }, { "epoch": 0.14361205723083142, "grad_norm": 1.7311012744903564, "learning_rate": 9.573608084010304e-05, "loss": 0.6654245376586914, "step": 24160 }, { "epoch": 0.1436714993074998, "grad_norm": 1.4606072902679443, "learning_rate": 9.577570834158906e-05, "loss": 0.6875820159912109, "step": 24170 }, { "epoch": 0.1437309413841682, "grad_norm": 1.4346492290496826, "learning_rate": 9.581533584307509e-05, "loss": 0.676560926437378, "step": 24180 }, { "epoch": 0.14379038346083658, "grad_norm": 1.4235187768936157, "learning_rate": 9.585496334456114e-05, "loss": 0.6508090019226074, "step": 24190 }, { "epoch": 0.14384982553750497, "grad_norm": 1.511033296585083, "learning_rate": 9.589459084604716e-05, "loss": 0.7200244903564453, "step": 24200 }, { "epoch": 0.14390926761417336, "grad_norm": 1.571616291999817, "learning_rate": 9.593421834753319e-05, "loss": 0.6608282089233398, "step": 24210 }, { "epoch": 0.14396870969084177, "grad_norm": 1.4046661853790283, "learning_rate": 9.597384584901923e-05, "loss": 0.6361823081970215, "step": 24220 }, { "epoch": 0.14402815176751016, "grad_norm": 1.8171180486679077, "learning_rate": 9.601347335050525e-05, "loss": 0.6548283576965332, "step": 24230 }, { "epoch": 0.14408759384417855, "grad_norm": 1.750059962272644, "learning_rate": 9.605310085199128e-05, "loss": 0.6295370101928711, "step": 24240 }, { "epoch": 0.14414703592084693, "grad_norm": 1.6451900005340576, "learning_rate": 9.609272835347732e-05, "loss": 0.7390161514282226, "step": 24250 }, { "epoch": 0.14420647799751532, "grad_norm": 1.122376799583435, "learning_rate": 9.613235585496336e-05, "loss": 0.7070116996765137, "step": 24260 }, { "epoch": 0.1442659200741837, "grad_norm": 1.863954782485962, "learning_rate": 9.617198335644938e-05, "loss": 0.7257822036743165, "step": 24270 }, { "epoch": 0.1443253621508521, "grad_norm": 1.6158294677734375, "learning_rate": 9.62116108579354e-05, "loss": 0.6490708351135254, "step": 24280 }, { "epoch": 0.14438480422752048, "grad_norm": 1.3381584882736206, "learning_rate": 9.625123835942144e-05, "loss": 0.6611382484436035, "step": 24290 }, { "epoch": 0.1444442463041889, "grad_norm": 1.6293898820877075, "learning_rate": 9.629086586090747e-05, "loss": 0.7204608917236328, "step": 24300 }, { "epoch": 0.14450368838085728, "grad_norm": 1.550769567489624, "learning_rate": 9.633049336239351e-05, "loss": 0.6490175724029541, "step": 24310 }, { "epoch": 0.14456313045752567, "grad_norm": 1.6966966390609741, "learning_rate": 9.637012086387953e-05, "loss": 0.6075523376464844, "step": 24320 }, { "epoch": 0.14462257253419405, "grad_norm": 1.176073670387268, "learning_rate": 9.640974836536557e-05, "loss": 0.6807410240173339, "step": 24330 }, { "epoch": 0.14468201461086244, "grad_norm": 1.6311413049697876, "learning_rate": 9.64493758668516e-05, "loss": 0.6909899711608887, "step": 24340 }, { "epoch": 0.14474145668753083, "grad_norm": 1.346261739730835, "learning_rate": 9.648900336833762e-05, "loss": 0.6005393028259277, "step": 24350 }, { "epoch": 0.14480089876419922, "grad_norm": 1.4853739738464355, "learning_rate": 9.652863086982366e-05, "loss": 0.7175538063049316, "step": 24360 }, { "epoch": 0.14486034084086763, "grad_norm": 1.9654279947280884, "learning_rate": 9.65682583713097e-05, "loss": 0.672826099395752, "step": 24370 }, { "epoch": 0.14491978291753602, "grad_norm": 2.0183849334716797, "learning_rate": 9.660788587279572e-05, "loss": 0.7320969581604004, "step": 24380 }, { "epoch": 0.1449792249942044, "grad_norm": 1.5570032596588135, "learning_rate": 9.664751337428175e-05, "loss": 0.6985483169555664, "step": 24390 }, { "epoch": 0.1450386670708728, "grad_norm": 1.5599040985107422, "learning_rate": 9.668714087576779e-05, "loss": 0.7084734916687012, "step": 24400 }, { "epoch": 0.14509810914754118, "grad_norm": 1.5165064334869385, "learning_rate": 9.672676837725381e-05, "loss": 0.6713546752929688, "step": 24410 }, { "epoch": 0.14515755122420956, "grad_norm": 1.5708272457122803, "learning_rate": 9.676639587873985e-05, "loss": 0.6442351341247559, "step": 24420 }, { "epoch": 0.14521699330087795, "grad_norm": 1.508594036102295, "learning_rate": 9.680602338022589e-05, "loss": 0.6615742683410645, "step": 24430 }, { "epoch": 0.14527643537754634, "grad_norm": 2.1130380630493164, "learning_rate": 9.684565088171192e-05, "loss": 0.6900983810424804, "step": 24440 }, { "epoch": 0.14533587745421475, "grad_norm": 1.2384026050567627, "learning_rate": 9.688527838319794e-05, "loss": 0.6320268154144287, "step": 24450 }, { "epoch": 0.14539531953088314, "grad_norm": 1.4651784896850586, "learning_rate": 9.692490588468398e-05, "loss": 0.7173846244812012, "step": 24460 }, { "epoch": 0.14545476160755152, "grad_norm": 1.2665983438491821, "learning_rate": 9.696453338617e-05, "loss": 0.720029878616333, "step": 24470 }, { "epoch": 0.1455142036842199, "grad_norm": 1.6031218767166138, "learning_rate": 9.700416088765604e-05, "loss": 0.6956970691680908, "step": 24480 }, { "epoch": 0.1455736457608883, "grad_norm": 1.4023725986480713, "learning_rate": 9.704378838914207e-05, "loss": 0.6588396072387696, "step": 24490 }, { "epoch": 0.14563308783755669, "grad_norm": 2.1878745555877686, "learning_rate": 9.708341589062811e-05, "loss": 0.7212558269500733, "step": 24500 }, { "epoch": 0.14569252991422507, "grad_norm": 1.4451693296432495, "learning_rate": 9.712304339211413e-05, "loss": 0.6170883655548096, "step": 24510 }, { "epoch": 0.1457519719908935, "grad_norm": 1.7336859703063965, "learning_rate": 9.716267089360016e-05, "loss": 0.626621150970459, "step": 24520 }, { "epoch": 0.14581141406756187, "grad_norm": 1.2765148878097534, "learning_rate": 9.72022983950862e-05, "loss": 0.6370861530303955, "step": 24530 }, { "epoch": 0.14587085614423026, "grad_norm": 1.3323920965194702, "learning_rate": 9.724192589657222e-05, "loss": 0.6976622581481934, "step": 24540 }, { "epoch": 0.14593029822089865, "grad_norm": 1.7972640991210938, "learning_rate": 9.728155339805826e-05, "loss": 0.7129847526550293, "step": 24550 }, { "epoch": 0.14598974029756703, "grad_norm": 1.6041836738586426, "learning_rate": 9.732118089954429e-05, "loss": 0.6637007713317871, "step": 24560 }, { "epoch": 0.14604918237423542, "grad_norm": 1.5103464126586914, "learning_rate": 9.736080840103032e-05, "loss": 0.6433368682861328, "step": 24570 }, { "epoch": 0.1461086244509038, "grad_norm": 1.5212105512619019, "learning_rate": 9.740043590251635e-05, "loss": 0.6780147552490234, "step": 24580 }, { "epoch": 0.1461680665275722, "grad_norm": 1.6287378072738647, "learning_rate": 9.744006340400237e-05, "loss": 0.685680627822876, "step": 24590 }, { "epoch": 0.1462275086042406, "grad_norm": 1.5088472366333008, "learning_rate": 9.747969090548841e-05, "loss": 0.6995673179626465, "step": 24600 }, { "epoch": 0.146286950680909, "grad_norm": 1.996270775794983, "learning_rate": 9.751931840697445e-05, "loss": 0.6885295391082764, "step": 24610 }, { "epoch": 0.14634639275757738, "grad_norm": 1.5679641962051392, "learning_rate": 9.755894590846048e-05, "loss": 0.731282901763916, "step": 24620 }, { "epoch": 0.14640583483424577, "grad_norm": 1.714396595954895, "learning_rate": 9.75985734099465e-05, "loss": 0.6591212272644043, "step": 24630 }, { "epoch": 0.14646527691091416, "grad_norm": 1.4258941411972046, "learning_rate": 9.763820091143254e-05, "loss": 0.6265488624572754, "step": 24640 }, { "epoch": 0.14652471898758254, "grad_norm": 1.2082977294921875, "learning_rate": 9.767782841291857e-05, "loss": 0.6423269271850586, "step": 24650 }, { "epoch": 0.14658416106425093, "grad_norm": 1.4502754211425781, "learning_rate": 9.77174559144046e-05, "loss": 0.6988568782806397, "step": 24660 }, { "epoch": 0.14664360314091934, "grad_norm": 1.2910361289978027, "learning_rate": 9.775708341589064e-05, "loss": 0.6670978546142579, "step": 24670 }, { "epoch": 0.14670304521758773, "grad_norm": 1.6340875625610352, "learning_rate": 9.779671091737667e-05, "loss": 0.684707498550415, "step": 24680 }, { "epoch": 0.14676248729425612, "grad_norm": 1.548158884048462, "learning_rate": 9.783633841886269e-05, "loss": 0.6811115264892578, "step": 24690 }, { "epoch": 0.1468219293709245, "grad_norm": 1.8119431734085083, "learning_rate": 9.787596592034872e-05, "loss": 0.6232398986816406, "step": 24700 }, { "epoch": 0.1468813714475929, "grad_norm": 1.3537362813949585, "learning_rate": 9.791559342183476e-05, "loss": 0.6423518657684326, "step": 24710 }, { "epoch": 0.14694081352426128, "grad_norm": 1.2491397857666016, "learning_rate": 9.79552209233208e-05, "loss": 0.6810463905334473, "step": 24720 }, { "epoch": 0.14700025560092966, "grad_norm": 1.3782665729522705, "learning_rate": 9.799484842480682e-05, "loss": 0.734256649017334, "step": 24730 }, { "epoch": 0.14705969767759808, "grad_norm": 1.5763300657272339, "learning_rate": 9.803447592629286e-05, "loss": 0.6345488071441651, "step": 24740 }, { "epoch": 0.14711913975426646, "grad_norm": 1.510636806488037, "learning_rate": 9.807410342777888e-05, "loss": 0.6522861003875733, "step": 24750 }, { "epoch": 0.14717858183093485, "grad_norm": 1.431473970413208, "learning_rate": 9.811373092926491e-05, "loss": 0.625719690322876, "step": 24760 }, { "epoch": 0.14723802390760324, "grad_norm": 1.0469647645950317, "learning_rate": 9.815335843075095e-05, "loss": 0.6855528831481934, "step": 24770 }, { "epoch": 0.14729746598427162, "grad_norm": 1.278212070465088, "learning_rate": 9.819298593223699e-05, "loss": 0.6225350379943848, "step": 24780 }, { "epoch": 0.14735690806094, "grad_norm": 1.3699092864990234, "learning_rate": 9.823261343372301e-05, "loss": 0.6437355041503906, "step": 24790 }, { "epoch": 0.1474163501376084, "grad_norm": 1.5570799112319946, "learning_rate": 9.827224093520904e-05, "loss": 0.6867121696472168, "step": 24800 }, { "epoch": 0.14747579221427679, "grad_norm": 1.4160171747207642, "learning_rate": 9.831186843669508e-05, "loss": 0.7482597351074218, "step": 24810 }, { "epoch": 0.1475352342909452, "grad_norm": 1.902217984199524, "learning_rate": 9.83514959381811e-05, "loss": 0.6738725185394288, "step": 24820 }, { "epoch": 0.1475946763676136, "grad_norm": 1.4390383958816528, "learning_rate": 9.839112343966713e-05, "loss": 0.697600269317627, "step": 24830 }, { "epoch": 0.14765411844428197, "grad_norm": 1.4883761405944824, "learning_rate": 9.843075094115316e-05, "loss": 0.6694149494171142, "step": 24840 }, { "epoch": 0.14771356052095036, "grad_norm": 1.7171883583068848, "learning_rate": 9.84703784426392e-05, "loss": 0.6939966201782226, "step": 24850 }, { "epoch": 0.14777300259761875, "grad_norm": 1.5193949937820435, "learning_rate": 9.851000594412523e-05, "loss": 0.6938184261322021, "step": 24860 }, { "epoch": 0.14783244467428713, "grad_norm": 1.3827992677688599, "learning_rate": 9.854963344561125e-05, "loss": 0.6084902286529541, "step": 24870 }, { "epoch": 0.14789188675095552, "grad_norm": 1.5062997341156006, "learning_rate": 9.858926094709729e-05, "loss": 0.7037506580352784, "step": 24880 }, { "epoch": 0.14795132882762393, "grad_norm": 1.7488516569137573, "learning_rate": 9.862888844858332e-05, "loss": 0.701390266418457, "step": 24890 }, { "epoch": 0.14801077090429232, "grad_norm": 1.6776317358016968, "learning_rate": 9.866851595006936e-05, "loss": 0.7073238849639892, "step": 24900 }, { "epoch": 0.1480702129809607, "grad_norm": 1.7437200546264648, "learning_rate": 9.870814345155538e-05, "loss": 0.6844031333923339, "step": 24910 }, { "epoch": 0.1481296550576291, "grad_norm": 1.8594001531600952, "learning_rate": 9.874777095304142e-05, "loss": 0.6802104949951172, "step": 24920 }, { "epoch": 0.14818909713429748, "grad_norm": 1.8289527893066406, "learning_rate": 9.878739845452744e-05, "loss": 0.6955326557159424, "step": 24930 }, { "epoch": 0.14824853921096587, "grad_norm": 1.406571626663208, "learning_rate": 9.882702595601347e-05, "loss": 0.6771713733673096, "step": 24940 }, { "epoch": 0.14830798128763426, "grad_norm": 1.592951774597168, "learning_rate": 9.886665345749951e-05, "loss": 0.6558717250823974, "step": 24950 }, { "epoch": 0.14836742336430264, "grad_norm": 1.5574400424957275, "learning_rate": 9.890628095898555e-05, "loss": 0.6301994800567627, "step": 24960 }, { "epoch": 0.14842686544097106, "grad_norm": 1.5795878171920776, "learning_rate": 9.894590846047157e-05, "loss": 0.600214672088623, "step": 24970 }, { "epoch": 0.14848630751763944, "grad_norm": 1.6581833362579346, "learning_rate": 9.89855359619576e-05, "loss": 0.6928647518157959, "step": 24980 }, { "epoch": 0.14854574959430783, "grad_norm": 1.632201910018921, "learning_rate": 9.902516346344364e-05, "loss": 0.6483086585998535, "step": 24990 }, { "epoch": 0.14860519167097622, "grad_norm": 1.482265591621399, "learning_rate": 9.906479096492966e-05, "loss": 0.6760848999023438, "step": 25000 }, { "epoch": 0.1486646337476446, "grad_norm": 1.7574725151062012, "learning_rate": 9.91044184664157e-05, "loss": 0.6794424533843995, "step": 25010 }, { "epoch": 0.148724075824313, "grad_norm": 1.5641337633132935, "learning_rate": 9.914404596790174e-05, "loss": 0.6514882564544677, "step": 25020 }, { "epoch": 0.14878351790098138, "grad_norm": 1.8630766868591309, "learning_rate": 9.918367346938776e-05, "loss": 0.7198468208312988, "step": 25030 }, { "epoch": 0.1488429599776498, "grad_norm": 1.3466076850891113, "learning_rate": 9.922330097087379e-05, "loss": 0.6436790466308594, "step": 25040 }, { "epoch": 0.14890240205431818, "grad_norm": 1.5383840799331665, "learning_rate": 9.926292847235981e-05, "loss": 0.7077815055847168, "step": 25050 }, { "epoch": 0.14896184413098656, "grad_norm": 1.8008538484573364, "learning_rate": 9.930255597384585e-05, "loss": 0.6494342803955078, "step": 25060 }, { "epoch": 0.14902128620765495, "grad_norm": 1.6117103099822998, "learning_rate": 9.934218347533189e-05, "loss": 0.717888355255127, "step": 25070 }, { "epoch": 0.14908072828432334, "grad_norm": 1.8343088626861572, "learning_rate": 9.938181097681792e-05, "loss": 0.6386991500854492, "step": 25080 }, { "epoch": 0.14914017036099173, "grad_norm": 1.4391882419586182, "learning_rate": 9.942143847830395e-05, "loss": 0.6576433181762695, "step": 25090 }, { "epoch": 0.1491996124376601, "grad_norm": 1.7312926054000854, "learning_rate": 9.946106597978998e-05, "loss": 0.6378665924072265, "step": 25100 }, { "epoch": 0.14925905451432853, "grad_norm": 1.5697665214538574, "learning_rate": 9.9500693481276e-05, "loss": 0.6813720703125, "step": 25110 }, { "epoch": 0.1493184965909969, "grad_norm": 1.719376564025879, "learning_rate": 9.954032098276204e-05, "loss": 0.6310784339904785, "step": 25120 }, { "epoch": 0.1493779386676653, "grad_norm": 1.9285727739334106, "learning_rate": 9.957994848424808e-05, "loss": 0.6822811126708984, "step": 25130 }, { "epoch": 0.1494373807443337, "grad_norm": 1.5300590991973877, "learning_rate": 9.961957598573411e-05, "loss": 0.721076774597168, "step": 25140 }, { "epoch": 0.14949682282100207, "grad_norm": 1.6552950143814087, "learning_rate": 9.965920348722013e-05, "loss": 0.6739099502563477, "step": 25150 }, { "epoch": 0.14955626489767046, "grad_norm": 1.5467678308486938, "learning_rate": 9.969883098870617e-05, "loss": 0.6872426986694335, "step": 25160 }, { "epoch": 0.14961570697433885, "grad_norm": 1.3919734954833984, "learning_rate": 9.97384584901922e-05, "loss": 0.6963441848754883, "step": 25170 }, { "epoch": 0.14967514905100723, "grad_norm": 1.5165597200393677, "learning_rate": 9.977808599167822e-05, "loss": 0.6574442863464356, "step": 25180 }, { "epoch": 0.14973459112767565, "grad_norm": 1.3122007846832275, "learning_rate": 9.981771349316426e-05, "loss": 0.6261669158935547, "step": 25190 }, { "epoch": 0.14979403320434403, "grad_norm": 1.5104016065597534, "learning_rate": 9.98573409946503e-05, "loss": 0.6896506309509277, "step": 25200 }, { "epoch": 0.14985347528101242, "grad_norm": 1.8960363864898682, "learning_rate": 9.989696849613632e-05, "loss": 0.6733073711395263, "step": 25210 }, { "epoch": 0.1499129173576808, "grad_norm": 1.5684432983398438, "learning_rate": 9.993659599762235e-05, "loss": 0.6400120258331299, "step": 25220 }, { "epoch": 0.1499723594343492, "grad_norm": 1.520148515701294, "learning_rate": 9.997622349910839e-05, "loss": 0.6305000305175781, "step": 25230 }, { "epoch": 0.15003180151101758, "grad_norm": 1.470051884651184, "learning_rate": 0.00010001585100059441, "loss": 0.6860846519470215, "step": 25240 }, { "epoch": 0.15009124358768597, "grad_norm": 1.4716918468475342, "learning_rate": 0.00010005547850208045, "loss": 0.6792492866516113, "step": 25250 }, { "epoch": 0.15015068566435438, "grad_norm": 1.6697688102722168, "learning_rate": 0.00010009510600356649, "loss": 0.7050006866455079, "step": 25260 }, { "epoch": 0.15021012774102277, "grad_norm": 1.5169960260391235, "learning_rate": 0.00010013473350505251, "loss": 0.6754641532897949, "step": 25270 }, { "epoch": 0.15026956981769116, "grad_norm": 1.3852617740631104, "learning_rate": 0.00010017436100653854, "loss": 0.6614995956420898, "step": 25280 }, { "epoch": 0.15032901189435954, "grad_norm": 1.5665093660354614, "learning_rate": 0.00010021398850802456, "loss": 0.735594367980957, "step": 25290 }, { "epoch": 0.15038845397102793, "grad_norm": 1.8852444887161255, "learning_rate": 0.0001002536160095106, "loss": 0.7284150123596191, "step": 25300 }, { "epoch": 0.15044789604769632, "grad_norm": 1.6273728609085083, "learning_rate": 0.00010029324351099663, "loss": 0.6489899635314942, "step": 25310 }, { "epoch": 0.1505073381243647, "grad_norm": 1.6821017265319824, "learning_rate": 0.00010033287101248268, "loss": 0.6556129455566406, "step": 25320 }, { "epoch": 0.1505667802010331, "grad_norm": 1.3912014961242676, "learning_rate": 0.0001003724985139687, "loss": 0.6999045372009277, "step": 25330 }, { "epoch": 0.1506262222777015, "grad_norm": 1.5629339218139648, "learning_rate": 0.00010041212601545473, "loss": 0.6532205581665039, "step": 25340 }, { "epoch": 0.1506856643543699, "grad_norm": 1.3830137252807617, "learning_rate": 0.00010045175351694076, "loss": 0.6414086818695068, "step": 25350 }, { "epoch": 0.15074510643103828, "grad_norm": 1.5469005107879639, "learning_rate": 0.0001004913810184268, "loss": 0.6559749603271484, "step": 25360 }, { "epoch": 0.15080454850770666, "grad_norm": 1.7803066968917847, "learning_rate": 0.00010053100851991282, "loss": 0.7142186641693116, "step": 25370 }, { "epoch": 0.15086399058437505, "grad_norm": 1.6872755289077759, "learning_rate": 0.00010057063602139884, "loss": 0.6855039119720459, "step": 25380 }, { "epoch": 0.15092343266104344, "grad_norm": 1.4683300256729126, "learning_rate": 0.0001006102635228849, "loss": 0.6667971134185791, "step": 25390 }, { "epoch": 0.15098287473771183, "grad_norm": 1.8629463911056519, "learning_rate": 0.00010064989102437092, "loss": 0.6510100364685059, "step": 25400 }, { "epoch": 0.15104231681438024, "grad_norm": 1.7571635246276855, "learning_rate": 0.00010068951852585695, "loss": 0.7159753322601319, "step": 25410 }, { "epoch": 0.15110175889104863, "grad_norm": 1.4192010164260864, "learning_rate": 0.00010072914602734299, "loss": 0.6693416595458984, "step": 25420 }, { "epoch": 0.151161200967717, "grad_norm": 1.57724928855896, "learning_rate": 0.00010076877352882901, "loss": 0.657728624343872, "step": 25430 }, { "epoch": 0.1512206430443854, "grad_norm": 1.2341381311416626, "learning_rate": 0.00010080840103031504, "loss": 0.6173001289367676, "step": 25440 }, { "epoch": 0.1512800851210538, "grad_norm": 1.457751750946045, "learning_rate": 0.00010084802853180106, "loss": 0.6368605136871338, "step": 25450 }, { "epoch": 0.15133952719772217, "grad_norm": 1.4489418268203735, "learning_rate": 0.00010088765603328711, "loss": 0.6739086627960205, "step": 25460 }, { "epoch": 0.15139896927439056, "grad_norm": 1.4327514171600342, "learning_rate": 0.00010092728353477314, "loss": 0.7038040161132812, "step": 25470 }, { "epoch": 0.15145841135105895, "grad_norm": 1.424136757850647, "learning_rate": 0.00010096691103625918, "loss": 0.6394245147705078, "step": 25480 }, { "epoch": 0.15151785342772736, "grad_norm": 1.5801347494125366, "learning_rate": 0.0001010065385377452, "loss": 0.6267473697662354, "step": 25490 }, { "epoch": 0.15157729550439575, "grad_norm": 1.5433650016784668, "learning_rate": 0.00010104616603923123, "loss": 0.7000247955322265, "step": 25500 }, { "epoch": 0.15163673758106413, "grad_norm": 1.6204158067703247, "learning_rate": 0.00010108579354071725, "loss": 0.6526555061340332, "step": 25510 }, { "epoch": 0.15169617965773252, "grad_norm": 1.4780246019363403, "learning_rate": 0.00010112542104220328, "loss": 0.659878921508789, "step": 25520 }, { "epoch": 0.1517556217344009, "grad_norm": 1.8445535898208618, "learning_rate": 0.00010116504854368933, "loss": 0.6787822723388672, "step": 25530 }, { "epoch": 0.1518150638110693, "grad_norm": 1.26786208152771, "learning_rate": 0.00010120467604517537, "loss": 0.6293602466583252, "step": 25540 }, { "epoch": 0.15187450588773768, "grad_norm": 1.4501299858093262, "learning_rate": 0.0001012443035466614, "loss": 0.6221545219421387, "step": 25550 }, { "epoch": 0.1519339479644061, "grad_norm": 1.5071616172790527, "learning_rate": 0.00010128393104814742, "loss": 0.6132748603820801, "step": 25560 }, { "epoch": 0.15199339004107448, "grad_norm": 1.6584676504135132, "learning_rate": 0.00010132355854963344, "loss": 0.6963592529296875, "step": 25570 }, { "epoch": 0.15205283211774287, "grad_norm": 1.412856936454773, "learning_rate": 0.00010136318605111947, "loss": 0.6832738399505616, "step": 25580 }, { "epoch": 0.15211227419441126, "grad_norm": 1.6308894157409668, "learning_rate": 0.00010140281355260551, "loss": 0.6546996116638184, "step": 25590 }, { "epoch": 0.15217171627107964, "grad_norm": 1.7720756530761719, "learning_rate": 0.00010144244105409155, "loss": 0.7025726318359375, "step": 25600 }, { "epoch": 0.15223115834774803, "grad_norm": 1.3120946884155273, "learning_rate": 0.00010148206855557758, "loss": 0.6124505996704102, "step": 25610 }, { "epoch": 0.15229060042441642, "grad_norm": 1.5461649894714355, "learning_rate": 0.00010152169605706361, "loss": 0.700412654876709, "step": 25620 }, { "epoch": 0.15235004250108483, "grad_norm": 1.5238778591156006, "learning_rate": 0.00010156132355854964, "loss": 0.6775717258453369, "step": 25630 }, { "epoch": 0.15240948457775322, "grad_norm": 1.7028566598892212, "learning_rate": 0.00010160095106003566, "loss": 0.7181831359863281, "step": 25640 }, { "epoch": 0.1524689266544216, "grad_norm": 1.5760992765426636, "learning_rate": 0.0001016405785615217, "loss": 0.679987096786499, "step": 25650 }, { "epoch": 0.15252836873109, "grad_norm": 1.6494183540344238, "learning_rate": 0.00010168020606300772, "loss": 0.6540932178497314, "step": 25660 }, { "epoch": 0.15258781080775838, "grad_norm": 1.9232734441757202, "learning_rate": 0.00010171983356449378, "loss": 0.6981735229492188, "step": 25670 }, { "epoch": 0.15264725288442677, "grad_norm": 1.764491319656372, "learning_rate": 0.0001017594610659798, "loss": 0.6652544021606446, "step": 25680 }, { "epoch": 0.15270669496109515, "grad_norm": 1.6585948467254639, "learning_rate": 0.00010179908856746583, "loss": 0.7028010845184326, "step": 25690 }, { "epoch": 0.15276613703776354, "grad_norm": 1.7725948095321655, "learning_rate": 0.00010183871606895185, "loss": 0.6630623817443848, "step": 25700 }, { "epoch": 0.15282557911443195, "grad_norm": 1.5746917724609375, "learning_rate": 0.00010187834357043789, "loss": 0.6649256706237793, "step": 25710 }, { "epoch": 0.15288502119110034, "grad_norm": 1.8146014213562012, "learning_rate": 0.00010191797107192392, "loss": 0.6880005359649658, "step": 25720 }, { "epoch": 0.15294446326776873, "grad_norm": 1.2191587686538696, "learning_rate": 0.00010195759857340994, "loss": 0.6466599464416504, "step": 25730 }, { "epoch": 0.1530039053444371, "grad_norm": 1.5959793329238892, "learning_rate": 0.00010199722607489599, "loss": 0.6296820640563965, "step": 25740 }, { "epoch": 0.1530633474211055, "grad_norm": 1.4876140356063843, "learning_rate": 0.00010203685357638202, "loss": 0.6615988731384277, "step": 25750 }, { "epoch": 0.1531227894977739, "grad_norm": 1.5801922082901, "learning_rate": 0.00010207648107786804, "loss": 0.6565549373626709, "step": 25760 }, { "epoch": 0.15318223157444227, "grad_norm": 1.401249647140503, "learning_rate": 0.00010211610857935408, "loss": 0.6705129146575928, "step": 25770 }, { "epoch": 0.1532416736511107, "grad_norm": 1.2848083972930908, "learning_rate": 0.0001021557360808401, "loss": 0.6873021602630616, "step": 25780 }, { "epoch": 0.15330111572777907, "grad_norm": 1.9947474002838135, "learning_rate": 0.00010219536358232613, "loss": 0.6787957668304443, "step": 25790 }, { "epoch": 0.15336055780444746, "grad_norm": 1.6429243087768555, "learning_rate": 0.00010223499108381218, "loss": 0.6560875415802002, "step": 25800 }, { "epoch": 0.15341999988111585, "grad_norm": 1.5383501052856445, "learning_rate": 0.00010227461858529821, "loss": 0.7107302665710449, "step": 25810 }, { "epoch": 0.15347944195778424, "grad_norm": 1.7351107597351074, "learning_rate": 0.00010231424608678423, "loss": 0.6666899681091308, "step": 25820 }, { "epoch": 0.15353888403445262, "grad_norm": 1.440940260887146, "learning_rate": 0.00010235387358827027, "loss": 0.6744039535522461, "step": 25830 }, { "epoch": 0.153598326111121, "grad_norm": 1.7646721601486206, "learning_rate": 0.0001023935010897563, "loss": 0.6325150966644287, "step": 25840 }, { "epoch": 0.1536577681877894, "grad_norm": 1.6038024425506592, "learning_rate": 0.00010243312859124232, "loss": 0.7431978225708008, "step": 25850 }, { "epoch": 0.1537172102644578, "grad_norm": 2.010678291320801, "learning_rate": 0.00010247275609272835, "loss": 0.7009430885314941, "step": 25860 }, { "epoch": 0.1537766523411262, "grad_norm": 1.2977702617645264, "learning_rate": 0.0001025123835942144, "loss": 0.6589704513549804, "step": 25870 }, { "epoch": 0.15383609441779458, "grad_norm": 1.5794364213943481, "learning_rate": 0.00010255201109570043, "loss": 0.7232560157775879, "step": 25880 }, { "epoch": 0.15389553649446297, "grad_norm": 1.791867971420288, "learning_rate": 0.00010259163859718645, "loss": 0.6615280151367188, "step": 25890 }, { "epoch": 0.15395497857113136, "grad_norm": 1.8947432041168213, "learning_rate": 0.00010263126609867249, "loss": 0.6622223377227783, "step": 25900 }, { "epoch": 0.15401442064779974, "grad_norm": 1.754065990447998, "learning_rate": 0.00010267089360015851, "loss": 0.7003966331481933, "step": 25910 }, { "epoch": 0.15407386272446813, "grad_norm": 1.4732521772384644, "learning_rate": 0.00010271052110164454, "loss": 0.6585618019104004, "step": 25920 }, { "epoch": 0.15413330480113654, "grad_norm": 1.5831027030944824, "learning_rate": 0.00010275014860313056, "loss": 0.6488225936889649, "step": 25930 }, { "epoch": 0.15419274687780493, "grad_norm": 1.699364185333252, "learning_rate": 0.00010278977610461662, "loss": 0.648351526260376, "step": 25940 }, { "epoch": 0.15425218895447332, "grad_norm": 1.380461573600769, "learning_rate": 0.00010282940360610264, "loss": 0.6859241962432862, "step": 25950 }, { "epoch": 0.1543116310311417, "grad_norm": 1.692077398300171, "learning_rate": 0.00010286903110758868, "loss": 0.7182584762573242, "step": 25960 }, { "epoch": 0.1543710731078101, "grad_norm": 1.4361125230789185, "learning_rate": 0.0001029086586090747, "loss": 0.6923154830932617, "step": 25970 }, { "epoch": 0.15443051518447848, "grad_norm": 1.3990484476089478, "learning_rate": 0.00010294828611056073, "loss": 0.7092558383941651, "step": 25980 }, { "epoch": 0.15448995726114687, "grad_norm": 1.6129003763198853, "learning_rate": 0.00010298791361204676, "loss": 0.7033276081085205, "step": 25990 }, { "epoch": 0.15454939933781528, "grad_norm": 1.409204363822937, "learning_rate": 0.0001030275411135328, "loss": 0.6808440208435058, "step": 26000 }, { "epoch": 0.15460884141448367, "grad_norm": 1.5661628246307373, "learning_rate": 0.00010306716861501883, "loss": 0.6656715393066406, "step": 26010 }, { "epoch": 0.15466828349115205, "grad_norm": 1.5406631231307983, "learning_rate": 0.00010310679611650487, "loss": 0.6785815238952637, "step": 26020 }, { "epoch": 0.15472772556782044, "grad_norm": 1.764413595199585, "learning_rate": 0.0001031464236179909, "loss": 0.6657841205596924, "step": 26030 }, { "epoch": 0.15478716764448883, "grad_norm": 1.4665952920913696, "learning_rate": 0.00010318605111947692, "loss": 0.683842945098877, "step": 26040 }, { "epoch": 0.1548466097211572, "grad_norm": 1.6374577283859253, "learning_rate": 0.00010322567862096295, "loss": 0.6560330390930176, "step": 26050 }, { "epoch": 0.1549060517978256, "grad_norm": 1.0692541599273682, "learning_rate": 0.00010326530612244899, "loss": 0.5978898048400879, "step": 26060 }, { "epoch": 0.154965493874494, "grad_norm": 1.7065235376358032, "learning_rate": 0.00010330493362393501, "loss": 0.6643329620361328, "step": 26070 }, { "epoch": 0.1550249359511624, "grad_norm": 1.3607673645019531, "learning_rate": 0.00010334456112542106, "loss": 0.6881466865539551, "step": 26080 }, { "epoch": 0.1550843780278308, "grad_norm": 1.4581776857376099, "learning_rate": 0.00010338418862690709, "loss": 0.720337200164795, "step": 26090 }, { "epoch": 0.15514382010449917, "grad_norm": 1.2966405153274536, "learning_rate": 0.00010342381612839311, "loss": 0.7136681556701661, "step": 26100 }, { "epoch": 0.15520326218116756, "grad_norm": 1.4847478866577148, "learning_rate": 0.00010346344362987914, "loss": 0.6505632400512695, "step": 26110 }, { "epoch": 0.15526270425783595, "grad_norm": 1.788224458694458, "learning_rate": 0.00010350307113136518, "loss": 0.6306481838226319, "step": 26120 }, { "epoch": 0.15532214633450434, "grad_norm": 1.4282498359680176, "learning_rate": 0.0001035426986328512, "loss": 0.6907378196716308, "step": 26130 }, { "epoch": 0.15538158841117272, "grad_norm": 1.5887395143508911, "learning_rate": 0.00010358232613433723, "loss": 0.6407978057861328, "step": 26140 }, { "epoch": 0.15544103048784114, "grad_norm": 1.5623701810836792, "learning_rate": 0.00010362195363582328, "loss": 0.7086030006408691, "step": 26150 }, { "epoch": 0.15550047256450952, "grad_norm": 1.213371753692627, "learning_rate": 0.0001036615811373093, "loss": 0.6008195877075195, "step": 26160 }, { "epoch": 0.1555599146411779, "grad_norm": 1.6840652227401733, "learning_rate": 0.00010370120863879533, "loss": 0.716981029510498, "step": 26170 }, { "epoch": 0.1556193567178463, "grad_norm": 1.5753355026245117, "learning_rate": 0.00010374083614028135, "loss": 0.6424388408660888, "step": 26180 }, { "epoch": 0.15567879879451468, "grad_norm": 1.6547737121582031, "learning_rate": 0.00010378046364176739, "loss": 0.5995200157165528, "step": 26190 }, { "epoch": 0.15573824087118307, "grad_norm": 1.4464272260665894, "learning_rate": 0.00010382009114325342, "loss": 0.6466503620147706, "step": 26200 }, { "epoch": 0.15579768294785146, "grad_norm": 1.131466269493103, "learning_rate": 0.00010385971864473944, "loss": 0.6632493495941162, "step": 26210 }, { "epoch": 0.15585712502451984, "grad_norm": 1.1756113767623901, "learning_rate": 0.0001038993461462255, "loss": 0.6369861602783203, "step": 26220 }, { "epoch": 0.15591656710118826, "grad_norm": 1.7170521020889282, "learning_rate": 0.00010393897364771152, "loss": 0.6633009433746337, "step": 26230 }, { "epoch": 0.15597600917785664, "grad_norm": 1.3617197275161743, "learning_rate": 0.00010397860114919755, "loss": 0.6556342124938965, "step": 26240 }, { "epoch": 0.15603545125452503, "grad_norm": 1.5985107421875, "learning_rate": 0.00010401822865068358, "loss": 0.6667756557464599, "step": 26250 }, { "epoch": 0.15609489333119342, "grad_norm": 1.7975175380706787, "learning_rate": 0.00010405785615216961, "loss": 0.6814405441284179, "step": 26260 }, { "epoch": 0.1561543354078618, "grad_norm": 1.3387844562530518, "learning_rate": 0.00010409748365365563, "loss": 0.6406063079833985, "step": 26270 }, { "epoch": 0.1562137774845302, "grad_norm": 1.4298793077468872, "learning_rate": 0.00010413711115514166, "loss": 0.6731290817260742, "step": 26280 }, { "epoch": 0.15627321956119858, "grad_norm": 1.139905571937561, "learning_rate": 0.00010417673865662771, "loss": 0.6412912368774414, "step": 26290 }, { "epoch": 0.156332661637867, "grad_norm": 1.10331130027771, "learning_rate": 0.00010421636615811374, "loss": 0.5987249374389648, "step": 26300 }, { "epoch": 0.15639210371453538, "grad_norm": 1.9310615062713623, "learning_rate": 0.00010425599365959978, "loss": 0.6420038223266602, "step": 26310 }, { "epoch": 0.15645154579120377, "grad_norm": 1.530091643333435, "learning_rate": 0.0001042956211610858, "loss": 0.7114033222198486, "step": 26320 }, { "epoch": 0.15651098786787215, "grad_norm": 1.8068567514419556, "learning_rate": 0.00010433524866257183, "loss": 0.6389133930206299, "step": 26330 }, { "epoch": 0.15657042994454054, "grad_norm": 1.758211612701416, "learning_rate": 0.00010437487616405785, "loss": 0.6661172866821289, "step": 26340 }, { "epoch": 0.15662987202120893, "grad_norm": 1.4444929361343384, "learning_rate": 0.00010441450366554389, "loss": 0.6589246273040772, "step": 26350 }, { "epoch": 0.1566893140978773, "grad_norm": 1.5608108043670654, "learning_rate": 0.00010445413116702993, "loss": 0.6887687683105469, "step": 26360 }, { "epoch": 0.1567487561745457, "grad_norm": 1.6365123987197876, "learning_rate": 0.00010449375866851597, "loss": 0.6534592151641846, "step": 26370 }, { "epoch": 0.15680819825121411, "grad_norm": 1.565121054649353, "learning_rate": 0.00010453338617000199, "loss": 0.7012464523315429, "step": 26380 }, { "epoch": 0.1568676403278825, "grad_norm": 1.3554168939590454, "learning_rate": 0.00010457301367148802, "loss": 0.665647029876709, "step": 26390 }, { "epoch": 0.1569270824045509, "grad_norm": 1.1938233375549316, "learning_rate": 0.00010461264117297404, "loss": 0.6035852432250977, "step": 26400 }, { "epoch": 0.15698652448121928, "grad_norm": 1.5415781736373901, "learning_rate": 0.00010465226867446008, "loss": 0.6360642433166503, "step": 26410 }, { "epoch": 0.15704596655788766, "grad_norm": 1.4368445873260498, "learning_rate": 0.0001046918961759461, "loss": 0.666500473022461, "step": 26420 }, { "epoch": 0.15710540863455605, "grad_norm": 1.4635792970657349, "learning_rate": 0.00010473152367743216, "loss": 0.6793757438659668, "step": 26430 }, { "epoch": 0.15716485071122444, "grad_norm": 1.5673727989196777, "learning_rate": 0.00010477115117891818, "loss": 0.6684005260467529, "step": 26440 }, { "epoch": 0.15722429278789285, "grad_norm": 1.397736668586731, "learning_rate": 0.00010481077868040421, "loss": 0.641343641281128, "step": 26450 }, { "epoch": 0.15728373486456124, "grad_norm": 1.6421713829040527, "learning_rate": 0.00010485040618189023, "loss": 0.7243122100830078, "step": 26460 }, { "epoch": 0.15734317694122962, "grad_norm": 1.3580149412155151, "learning_rate": 0.00010489003368337626, "loss": 0.739538049697876, "step": 26470 }, { "epoch": 0.157402619017898, "grad_norm": 1.3744324445724487, "learning_rate": 0.0001049296611848623, "loss": 0.6781434059143067, "step": 26480 }, { "epoch": 0.1574620610945664, "grad_norm": 1.5862457752227783, "learning_rate": 0.00010496928868634832, "loss": 0.7066837787628174, "step": 26490 }, { "epoch": 0.15752150317123478, "grad_norm": 1.8575152158737183, "learning_rate": 0.00010500891618783437, "loss": 0.6722366333007812, "step": 26500 }, { "epoch": 0.15758094524790317, "grad_norm": 1.6416997909545898, "learning_rate": 0.0001050485436893204, "loss": 0.6655776023864746, "step": 26510 }, { "epoch": 0.15764038732457158, "grad_norm": 1.4944778680801392, "learning_rate": 0.00010508817119080642, "loss": 0.6811212062835693, "step": 26520 }, { "epoch": 0.15769982940123997, "grad_norm": 1.2489275932312012, "learning_rate": 0.00010512779869229245, "loss": 0.7077618598937988, "step": 26530 }, { "epoch": 0.15775927147790836, "grad_norm": 1.5498555898666382, "learning_rate": 0.00010516742619377849, "loss": 0.6187386035919189, "step": 26540 }, { "epoch": 0.15781871355457674, "grad_norm": 1.7785873413085938, "learning_rate": 0.00010520705369526451, "loss": 0.6549516201019288, "step": 26550 }, { "epoch": 0.15787815563124513, "grad_norm": 1.618162751197815, "learning_rate": 0.00010524668119675054, "loss": 0.6671503067016602, "step": 26560 }, { "epoch": 0.15793759770791352, "grad_norm": 1.6723638772964478, "learning_rate": 0.00010528630869823659, "loss": 0.6776298999786377, "step": 26570 }, { "epoch": 0.1579970397845819, "grad_norm": 1.4891387224197388, "learning_rate": 0.00010532593619972262, "loss": 0.691068458557129, "step": 26580 }, { "epoch": 0.1580564818612503, "grad_norm": 1.6541353464126587, "learning_rate": 0.00010536556370120864, "loss": 0.6666555881500245, "step": 26590 }, { "epoch": 0.1581159239379187, "grad_norm": 2.0158638954162598, "learning_rate": 0.00010540519120269468, "loss": 0.6370395660400391, "step": 26600 }, { "epoch": 0.1581753660145871, "grad_norm": 1.0499773025512695, "learning_rate": 0.0001054448187041807, "loss": 0.703823471069336, "step": 26610 }, { "epoch": 0.15823480809125548, "grad_norm": 1.8118970394134521, "learning_rate": 0.00010548444620566673, "loss": 0.660579252243042, "step": 26620 }, { "epoch": 0.15829425016792387, "grad_norm": 1.5493961572647095, "learning_rate": 0.00010552407370715276, "loss": 0.6858902931213379, "step": 26630 }, { "epoch": 0.15835369224459225, "grad_norm": 1.2887699604034424, "learning_rate": 0.00010556370120863881, "loss": 0.6852808952331543, "step": 26640 }, { "epoch": 0.15841313432126064, "grad_norm": 1.246475100517273, "learning_rate": 0.00010560332871012483, "loss": 0.6825331687927246, "step": 26650 }, { "epoch": 0.15847257639792903, "grad_norm": 1.8348956108093262, "learning_rate": 0.00010564295621161087, "loss": 0.607537031173706, "step": 26660 }, { "epoch": 0.15853201847459744, "grad_norm": 1.1828325986862183, "learning_rate": 0.0001056825837130969, "loss": 0.6192299842834472, "step": 26670 }, { "epoch": 0.15859146055126583, "grad_norm": 1.3552906513214111, "learning_rate": 0.00010572221121458292, "loss": 0.6797271728515625, "step": 26680 }, { "epoch": 0.15865090262793421, "grad_norm": 1.472719430923462, "learning_rate": 0.00010576183871606895, "loss": 0.6805574417114257, "step": 26690 }, { "epoch": 0.1587103447046026, "grad_norm": 1.44444739818573, "learning_rate": 0.00010580146621755499, "loss": 0.7225037097930909, "step": 26700 }, { "epoch": 0.158769786781271, "grad_norm": 1.7650470733642578, "learning_rate": 0.00010584109371904102, "loss": 0.7385237216949463, "step": 26710 }, { "epoch": 0.15882922885793938, "grad_norm": 1.368475079536438, "learning_rate": 0.00010588072122052706, "loss": 0.7104208946228028, "step": 26720 }, { "epoch": 0.15888867093460776, "grad_norm": 1.5173099040985107, "learning_rate": 0.00010592034872201309, "loss": 0.7119575500488281, "step": 26730 }, { "epoch": 0.15894811301127615, "grad_norm": 1.3684923648834229, "learning_rate": 0.00010595997622349911, "loss": 0.6679120063781738, "step": 26740 }, { "epoch": 0.15900755508794456, "grad_norm": 1.434020757675171, "learning_rate": 0.00010599960372498514, "loss": 0.6680230617523193, "step": 26750 }, { "epoch": 0.15906699716461295, "grad_norm": 1.5110347270965576, "learning_rate": 0.00010603923122647118, "loss": 0.722963809967041, "step": 26760 }, { "epoch": 0.15912643924128134, "grad_norm": 1.5527904033660889, "learning_rate": 0.0001060788587279572, "loss": 0.6815190315246582, "step": 26770 }, { "epoch": 0.15918588131794972, "grad_norm": 1.6767939329147339, "learning_rate": 0.00010611848622944325, "loss": 0.6479043960571289, "step": 26780 }, { "epoch": 0.1592453233946181, "grad_norm": 1.5801671743392944, "learning_rate": 0.00010615811373092928, "loss": 0.7130183219909668, "step": 26790 }, { "epoch": 0.1593047654712865, "grad_norm": 1.5637575387954712, "learning_rate": 0.0001061977412324153, "loss": 0.7324445724487305, "step": 26800 }, { "epoch": 0.15936420754795488, "grad_norm": 1.3395699262619019, "learning_rate": 0.00010623736873390133, "loss": 0.6621654033660889, "step": 26810 }, { "epoch": 0.1594236496246233, "grad_norm": 1.592418909072876, "learning_rate": 0.00010627699623538735, "loss": 0.6025288581848145, "step": 26820 }, { "epoch": 0.15948309170129168, "grad_norm": 1.7470781803131104, "learning_rate": 0.00010631662373687339, "loss": 0.6630834579467774, "step": 26830 }, { "epoch": 0.15954253377796007, "grad_norm": 1.192508578300476, "learning_rate": 0.00010635625123835942, "loss": 0.6378756523132324, "step": 26840 }, { "epoch": 0.15960197585462846, "grad_norm": 1.6707080602645874, "learning_rate": 0.00010639587873984547, "loss": 0.670826530456543, "step": 26850 }, { "epoch": 0.15966141793129685, "grad_norm": 1.7236907482147217, "learning_rate": 0.0001064355062413315, "loss": 0.673743724822998, "step": 26860 }, { "epoch": 0.15972086000796523, "grad_norm": 1.4533356428146362, "learning_rate": 0.00010647513374281752, "loss": 0.656863021850586, "step": 26870 }, { "epoch": 0.15978030208463362, "grad_norm": 1.3143935203552246, "learning_rate": 0.00010651476124430355, "loss": 0.6952449798583984, "step": 26880 }, { "epoch": 0.15983974416130203, "grad_norm": 1.2956639528274536, "learning_rate": 0.00010655438874578958, "loss": 0.6601478576660156, "step": 26890 }, { "epoch": 0.15989918623797042, "grad_norm": 1.954944133758545, "learning_rate": 0.00010659401624727561, "loss": 0.6622121810913086, "step": 26900 }, { "epoch": 0.1599586283146388, "grad_norm": 1.5244883298873901, "learning_rate": 0.00010663364374876163, "loss": 0.6943190097808838, "step": 26910 }, { "epoch": 0.1600180703913072, "grad_norm": 1.527786374092102, "learning_rate": 0.00010667327125024769, "loss": 0.7073846817016601, "step": 26920 }, { "epoch": 0.16007751246797558, "grad_norm": 1.6796250343322754, "learning_rate": 0.00010671289875173371, "loss": 0.6684191703796387, "step": 26930 }, { "epoch": 0.16013695454464397, "grad_norm": 1.4408341646194458, "learning_rate": 0.00010675252625321974, "loss": 0.6634552001953125, "step": 26940 }, { "epoch": 0.16019639662131235, "grad_norm": 1.643743634223938, "learning_rate": 0.00010679215375470578, "loss": 0.6918177604675293, "step": 26950 }, { "epoch": 0.16025583869798074, "grad_norm": 1.6613376140594482, "learning_rate": 0.0001068317812561918, "loss": 0.6617030143737793, "step": 26960 }, { "epoch": 0.16031528077464915, "grad_norm": 1.3549554347991943, "learning_rate": 0.00010687140875767783, "loss": 0.710216760635376, "step": 26970 }, { "epoch": 0.16037472285131754, "grad_norm": 1.5573856830596924, "learning_rate": 0.00010691103625916385, "loss": 0.6705908298492431, "step": 26980 }, { "epoch": 0.16043416492798593, "grad_norm": 1.6349939107894897, "learning_rate": 0.0001069506637606499, "loss": 0.6864619255065918, "step": 26990 }, { "epoch": 0.16049360700465432, "grad_norm": 1.723523736000061, "learning_rate": 0.00010699029126213593, "loss": 0.6549175262451172, "step": 27000 }, { "epoch": 0.1605530490813227, "grad_norm": 1.6740880012512207, "learning_rate": 0.00010702991876362197, "loss": 0.606386137008667, "step": 27010 }, { "epoch": 0.1606124911579911, "grad_norm": 1.4167158603668213, "learning_rate": 0.00010706954626510799, "loss": 0.6322078704833984, "step": 27020 }, { "epoch": 0.16067193323465948, "grad_norm": 1.6762211322784424, "learning_rate": 0.00010710917376659402, "loss": 0.7381430625915527, "step": 27030 }, { "epoch": 0.1607313753113279, "grad_norm": 1.3604965209960938, "learning_rate": 0.00010714880126808004, "loss": 0.6118831634521484, "step": 27040 }, { "epoch": 0.16079081738799628, "grad_norm": 1.6493208408355713, "learning_rate": 0.00010718842876956608, "loss": 0.6682812690734863, "step": 27050 }, { "epoch": 0.16085025946466466, "grad_norm": 1.6107007265090942, "learning_rate": 0.00010722805627105212, "loss": 0.6239445686340332, "step": 27060 }, { "epoch": 0.16090970154133305, "grad_norm": 1.3299778699874878, "learning_rate": 0.00010726768377253816, "loss": 0.6318258285522461, "step": 27070 }, { "epoch": 0.16096914361800144, "grad_norm": 1.5582876205444336, "learning_rate": 0.00010730731127402418, "loss": 0.6182017803192139, "step": 27080 }, { "epoch": 0.16102858569466982, "grad_norm": 1.4538294076919556, "learning_rate": 0.00010734693877551021, "loss": 0.7504373073577881, "step": 27090 }, { "epoch": 0.1610880277713382, "grad_norm": 1.9343806505203247, "learning_rate": 0.00010738656627699623, "loss": 0.6830157279968262, "step": 27100 }, { "epoch": 0.1611474698480066, "grad_norm": 1.5015305280685425, "learning_rate": 0.00010742619377848226, "loss": 0.5754756927490234, "step": 27110 }, { "epoch": 0.161206911924675, "grad_norm": 1.3725906610488892, "learning_rate": 0.0001074658212799683, "loss": 0.6946669578552246, "step": 27120 }, { "epoch": 0.1612663540013434, "grad_norm": 1.9177427291870117, "learning_rate": 0.00010750544878145435, "loss": 0.6871200561523437, "step": 27130 }, { "epoch": 0.16132579607801179, "grad_norm": 1.4163371324539185, "learning_rate": 0.00010754507628294037, "loss": 0.7024959087371826, "step": 27140 }, { "epoch": 0.16138523815468017, "grad_norm": 1.5782703161239624, "learning_rate": 0.0001075847037844264, "loss": 0.680514144897461, "step": 27150 }, { "epoch": 0.16144468023134856, "grad_norm": 1.3073346614837646, "learning_rate": 0.00010762433128591242, "loss": 0.620321798324585, "step": 27160 }, { "epoch": 0.16150412230801695, "grad_norm": 1.36668860912323, "learning_rate": 0.00010766395878739845, "loss": 0.7367382526397706, "step": 27170 }, { "epoch": 0.16156356438468533, "grad_norm": 1.529406189918518, "learning_rate": 0.00010770358628888449, "loss": 0.624084758758545, "step": 27180 }, { "epoch": 0.16162300646135375, "grad_norm": 1.3263975381851196, "learning_rate": 0.00010774321379037051, "loss": 0.6644384384155273, "step": 27190 }, { "epoch": 0.16168244853802213, "grad_norm": 1.6424059867858887, "learning_rate": 0.00010778284129185657, "loss": 0.6577324390411377, "step": 27200 }, { "epoch": 0.16174189061469052, "grad_norm": 1.7927871942520142, "learning_rate": 0.00010782246879334259, "loss": 0.646108865737915, "step": 27210 }, { "epoch": 0.1618013326913589, "grad_norm": 1.7100183963775635, "learning_rate": 0.00010786209629482862, "loss": 0.6546892166137696, "step": 27220 }, { "epoch": 0.1618607747680273, "grad_norm": 1.7697261571884155, "learning_rate": 0.00010790172379631464, "loss": 0.6025490760803223, "step": 27230 }, { "epoch": 0.16192021684469568, "grad_norm": 1.2930456399917603, "learning_rate": 0.00010794135129780068, "loss": 0.6769284248352051, "step": 27240 }, { "epoch": 0.16197965892136407, "grad_norm": 1.645639419555664, "learning_rate": 0.0001079809787992867, "loss": 0.6750670433044433, "step": 27250 }, { "epoch": 0.16203910099803245, "grad_norm": 1.605161428451538, "learning_rate": 0.00010802060630077273, "loss": 0.6505309104919433, "step": 27260 }, { "epoch": 0.16209854307470087, "grad_norm": 1.3015555143356323, "learning_rate": 0.00010806023380225878, "loss": 0.6779378414154053, "step": 27270 }, { "epoch": 0.16215798515136925, "grad_norm": 1.7081471681594849, "learning_rate": 0.00010809986130374481, "loss": 0.638089370727539, "step": 27280 }, { "epoch": 0.16221742722803764, "grad_norm": 1.403728723526001, "learning_rate": 0.00010813948880523083, "loss": 0.7125152587890625, "step": 27290 }, { "epoch": 0.16227686930470603, "grad_norm": 1.898748755455017, "learning_rate": 0.00010817911630671687, "loss": 0.6476491451263428, "step": 27300 }, { "epoch": 0.16233631138137442, "grad_norm": 1.1307079792022705, "learning_rate": 0.0001082187438082029, "loss": 0.6452552795410156, "step": 27310 }, { "epoch": 0.1623957534580428, "grad_norm": 1.2564501762390137, "learning_rate": 0.00010825837130968892, "loss": 0.6600217819213867, "step": 27320 }, { "epoch": 0.1624551955347112, "grad_norm": 1.463286280632019, "learning_rate": 0.00010829799881117495, "loss": 0.6385416507720947, "step": 27330 }, { "epoch": 0.1625146376113796, "grad_norm": 1.0877954959869385, "learning_rate": 0.000108337626312661, "loss": 0.6076377391815185, "step": 27340 }, { "epoch": 0.162574079688048, "grad_norm": 1.8312764167785645, "learning_rate": 0.00010837725381414702, "loss": 0.6607974529266357, "step": 27350 }, { "epoch": 0.16263352176471638, "grad_norm": 1.5076875686645508, "learning_rate": 0.00010841688131563306, "loss": 0.6444465637207031, "step": 27360 }, { "epoch": 0.16269296384138476, "grad_norm": 1.3597720861434937, "learning_rate": 0.00010845650881711909, "loss": 0.6110710144042969, "step": 27370 }, { "epoch": 0.16275240591805315, "grad_norm": 1.51143479347229, "learning_rate": 0.00010849613631860511, "loss": 0.6252418518066406, "step": 27380 }, { "epoch": 0.16281184799472154, "grad_norm": 1.5238847732543945, "learning_rate": 0.00010853576382009114, "loss": 0.6900504112243653, "step": 27390 }, { "epoch": 0.16287129007138992, "grad_norm": 1.5119643211364746, "learning_rate": 0.00010857539132157716, "loss": 0.6279918670654296, "step": 27400 }, { "epoch": 0.16293073214805834, "grad_norm": 1.256873369216919, "learning_rate": 0.00010861501882306321, "loss": 0.6653348922729492, "step": 27410 }, { "epoch": 0.16299017422472672, "grad_norm": 1.5612468719482422, "learning_rate": 0.00010865464632454925, "loss": 0.6624818801879883, "step": 27420 }, { "epoch": 0.1630496163013951, "grad_norm": 1.398674488067627, "learning_rate": 0.00010869427382603528, "loss": 0.6255153179168701, "step": 27430 }, { "epoch": 0.1631090583780635, "grad_norm": 1.3752280473709106, "learning_rate": 0.0001087339013275213, "loss": 0.6776413917541504, "step": 27440 }, { "epoch": 0.16316850045473189, "grad_norm": 2.136631965637207, "learning_rate": 0.00010877352882900733, "loss": 0.6211498260498047, "step": 27450 }, { "epoch": 0.16322794253140027, "grad_norm": 1.5602304935455322, "learning_rate": 0.00010881315633049335, "loss": 0.6734613418579102, "step": 27460 }, { "epoch": 0.16328738460806866, "grad_norm": 1.7698041200637817, "learning_rate": 0.00010885278383197939, "loss": 0.6438465118408203, "step": 27470 }, { "epoch": 0.16334682668473705, "grad_norm": 1.4317378997802734, "learning_rate": 0.00010889241133346544, "loss": 0.6704948425292969, "step": 27480 }, { "epoch": 0.16340626876140546, "grad_norm": 1.6942344903945923, "learning_rate": 0.00010893203883495147, "loss": 0.6937390327453613, "step": 27490 }, { "epoch": 0.16346571083807385, "grad_norm": 1.5190467834472656, "learning_rate": 0.0001089716663364375, "loss": 0.6902214050292969, "step": 27500 }, { "epoch": 0.16352515291474223, "grad_norm": 1.3943935632705688, "learning_rate": 0.00010901129383792352, "loss": 0.6739818572998046, "step": 27510 }, { "epoch": 0.16358459499141062, "grad_norm": 1.4560363292694092, "learning_rate": 0.00010905092133940954, "loss": 0.626361608505249, "step": 27520 }, { "epoch": 0.163644037068079, "grad_norm": 1.6744097471237183, "learning_rate": 0.00010909054884089558, "loss": 0.6762257099151612, "step": 27530 }, { "epoch": 0.1637034791447474, "grad_norm": 1.2312759160995483, "learning_rate": 0.00010913017634238161, "loss": 0.67061448097229, "step": 27540 }, { "epoch": 0.16376292122141578, "grad_norm": 1.5716969966888428, "learning_rate": 0.00010916980384386766, "loss": 0.6498763084411621, "step": 27550 }, { "epoch": 0.1638223632980842, "grad_norm": 1.5870615243911743, "learning_rate": 0.00010920943134535369, "loss": 0.6997078895568848, "step": 27560 }, { "epoch": 0.16388180537475258, "grad_norm": 1.3676832914352417, "learning_rate": 0.00010924905884683971, "loss": 0.6496586799621582, "step": 27570 }, { "epoch": 0.16394124745142097, "grad_norm": 1.6244466304779053, "learning_rate": 0.00010928868634832574, "loss": 0.7100008010864258, "step": 27580 }, { "epoch": 0.16400068952808936, "grad_norm": 1.5388883352279663, "learning_rate": 0.00010932831384981177, "loss": 0.6607054710388184, "step": 27590 }, { "epoch": 0.16406013160475774, "grad_norm": 1.4334450960159302, "learning_rate": 0.0001093679413512978, "loss": 0.7070531845092773, "step": 27600 }, { "epoch": 0.16411957368142613, "grad_norm": 1.5909931659698486, "learning_rate": 0.00010940756885278385, "loss": 0.6524131774902344, "step": 27610 }, { "epoch": 0.16417901575809452, "grad_norm": 1.2969930171966553, "learning_rate": 0.00010944719635426988, "loss": 0.645272159576416, "step": 27620 }, { "epoch": 0.1642384578347629, "grad_norm": 1.2710909843444824, "learning_rate": 0.0001094868238557559, "loss": 0.6765249252319336, "step": 27630 }, { "epoch": 0.16429789991143132, "grad_norm": 1.626267910003662, "learning_rate": 0.00010952645135724193, "loss": 0.6130327224731446, "step": 27640 }, { "epoch": 0.1643573419880997, "grad_norm": 1.3191430568695068, "learning_rate": 0.00010956607885872797, "loss": 0.6296508312225342, "step": 27650 }, { "epoch": 0.1644167840647681, "grad_norm": 1.5070267915725708, "learning_rate": 0.00010960570636021399, "loss": 0.6665688514709472, "step": 27660 }, { "epoch": 0.16447622614143648, "grad_norm": 1.399124264717102, "learning_rate": 0.00010964533386170002, "loss": 0.6663955211639404, "step": 27670 }, { "epoch": 0.16453566821810486, "grad_norm": 1.210229754447937, "learning_rate": 0.00010968496136318607, "loss": 0.6381182670593262, "step": 27680 }, { "epoch": 0.16459511029477325, "grad_norm": 1.244207501411438, "learning_rate": 0.0001097245888646721, "loss": 0.6465604305267334, "step": 27690 }, { "epoch": 0.16465455237144164, "grad_norm": 1.2999824285507202, "learning_rate": 0.00010976421636615812, "loss": 0.6884385108947754, "step": 27700 }, { "epoch": 0.16471399444811005, "grad_norm": 1.0718055963516235, "learning_rate": 0.00010980384386764416, "loss": 0.7085290908813476, "step": 27710 }, { "epoch": 0.16477343652477844, "grad_norm": 1.6089859008789062, "learning_rate": 0.00010984347136913018, "loss": 0.6237377166748047, "step": 27720 }, { "epoch": 0.16483287860144683, "grad_norm": 1.540348768234253, "learning_rate": 0.00010988309887061621, "loss": 0.6779135704040528, "step": 27730 }, { "epoch": 0.1648923206781152, "grad_norm": 1.5712007284164429, "learning_rate": 0.00010992272637210223, "loss": 0.6935259342193604, "step": 27740 }, { "epoch": 0.1649517627547836, "grad_norm": 1.415016531944275, "learning_rate": 0.00010996235387358828, "loss": 0.6470712184906006, "step": 27750 }, { "epoch": 0.16501120483145199, "grad_norm": 1.282618761062622, "learning_rate": 0.00011000198137507431, "loss": 0.7343628883361817, "step": 27760 }, { "epoch": 0.16507064690812037, "grad_norm": 1.4378119707107544, "learning_rate": 0.00011004160887656035, "loss": 0.6791201591491699, "step": 27770 }, { "epoch": 0.16513008898478876, "grad_norm": 1.8263897895812988, "learning_rate": 0.00011008123637804637, "loss": 0.6602918624877929, "step": 27780 }, { "epoch": 0.16518953106145717, "grad_norm": 1.5363346338272095, "learning_rate": 0.0001101208638795324, "loss": 0.6997128963470459, "step": 27790 }, { "epoch": 0.16524897313812556, "grad_norm": 1.1524338722229004, "learning_rate": 0.00011016049138101842, "loss": 0.6929692268371582, "step": 27800 }, { "epoch": 0.16530841521479395, "grad_norm": 1.4631677865982056, "learning_rate": 0.00011020011888250445, "loss": 0.6728673458099366, "step": 27810 }, { "epoch": 0.16536785729146233, "grad_norm": 1.1724801063537598, "learning_rate": 0.0001102397463839905, "loss": 0.6388644218444824, "step": 27820 }, { "epoch": 0.16542729936813072, "grad_norm": 1.5481871366500854, "learning_rate": 0.00011027937388547654, "loss": 0.7208722114562989, "step": 27830 }, { "epoch": 0.1654867414447991, "grad_norm": 1.4264863729476929, "learning_rate": 0.00011031900138696256, "loss": 0.6291721343994141, "step": 27840 }, { "epoch": 0.1655461835214675, "grad_norm": 1.5777828693389893, "learning_rate": 0.00011035862888844859, "loss": 0.650539779663086, "step": 27850 }, { "epoch": 0.1656056255981359, "grad_norm": 1.5450053215026855, "learning_rate": 0.00011039825638993462, "loss": 0.6930152893066406, "step": 27860 }, { "epoch": 0.1656650676748043, "grad_norm": 1.436668872833252, "learning_rate": 0.00011043788389142064, "loss": 0.6581556320190429, "step": 27870 }, { "epoch": 0.16572450975147268, "grad_norm": 1.644614577293396, "learning_rate": 0.00011047751139290668, "loss": 0.6324079036712646, "step": 27880 }, { "epoch": 0.16578395182814107, "grad_norm": 1.4725652933120728, "learning_rate": 0.00011051713889439273, "loss": 0.6498815536499023, "step": 27890 }, { "epoch": 0.16584339390480946, "grad_norm": 1.7084712982177734, "learning_rate": 0.00011055676639587876, "loss": 0.6973822593688965, "step": 27900 }, { "epoch": 0.16590283598147784, "grad_norm": 1.382980227470398, "learning_rate": 0.00011059639389736478, "loss": 0.6711615562438965, "step": 27910 }, { "epoch": 0.16596227805814623, "grad_norm": 1.287433385848999, "learning_rate": 0.0001106360213988508, "loss": 0.6879005432128906, "step": 27920 }, { "epoch": 0.16602172013481464, "grad_norm": 1.4552828073501587, "learning_rate": 0.00011067564890033683, "loss": 0.6943643093109131, "step": 27930 }, { "epoch": 0.16608116221148303, "grad_norm": 1.482171654701233, "learning_rate": 0.00011071527640182287, "loss": 0.6608962535858154, "step": 27940 }, { "epoch": 0.16614060428815142, "grad_norm": 1.356416940689087, "learning_rate": 0.0001107549039033089, "loss": 0.6691339492797852, "step": 27950 }, { "epoch": 0.1662000463648198, "grad_norm": 1.093409776687622, "learning_rate": 0.00011079453140479495, "loss": 0.646058177947998, "step": 27960 }, { "epoch": 0.1662594884414882, "grad_norm": 1.8560768365859985, "learning_rate": 0.00011083415890628097, "loss": 0.6977152347564697, "step": 27970 }, { "epoch": 0.16631893051815658, "grad_norm": 1.4321997165679932, "learning_rate": 0.000110873786407767, "loss": 0.6693769454956054, "step": 27980 }, { "epoch": 0.16637837259482496, "grad_norm": 1.5574253797531128, "learning_rate": 0.00011091341390925302, "loss": 0.7200736045837403, "step": 27990 }, { "epoch": 0.16643781467149335, "grad_norm": 1.406036615371704, "learning_rate": 0.00011095304141073906, "loss": 0.6934197425842286, "step": 28000 }, { "epoch": 0.16649725674816176, "grad_norm": 1.594867467880249, "learning_rate": 0.00011099266891222509, "loss": 0.7275474548339844, "step": 28010 }, { "epoch": 0.16655669882483015, "grad_norm": 1.9521267414093018, "learning_rate": 0.00011103229641371111, "loss": 0.7015302658081055, "step": 28020 }, { "epoch": 0.16661614090149854, "grad_norm": 1.4478119611740112, "learning_rate": 0.00011107192391519716, "loss": 0.7035904407501221, "step": 28030 }, { "epoch": 0.16667558297816693, "grad_norm": 1.6245663166046143, "learning_rate": 0.00011111155141668319, "loss": 0.6492774963378907, "step": 28040 }, { "epoch": 0.1667350250548353, "grad_norm": 1.4687165021896362, "learning_rate": 0.00011115117891816921, "loss": 0.6445101737976074, "step": 28050 }, { "epoch": 0.1667944671315037, "grad_norm": 1.407626748085022, "learning_rate": 0.00011119080641965525, "loss": 0.7359204292297363, "step": 28060 }, { "epoch": 0.16685390920817209, "grad_norm": 1.3396666049957275, "learning_rate": 0.00011123043392114128, "loss": 0.6022469520568847, "step": 28070 }, { "epoch": 0.1669133512848405, "grad_norm": 1.798272728919983, "learning_rate": 0.0001112700614226273, "loss": 0.690447998046875, "step": 28080 }, { "epoch": 0.1669727933615089, "grad_norm": 1.1795796155929565, "learning_rate": 0.00011130968892411333, "loss": 0.665518045425415, "step": 28090 }, { "epoch": 0.16703223543817727, "grad_norm": 1.5483720302581787, "learning_rate": 0.00011134931642559938, "loss": 0.73440580368042, "step": 28100 }, { "epoch": 0.16709167751484566, "grad_norm": 1.4453003406524658, "learning_rate": 0.0001113889439270854, "loss": 0.7137951850891113, "step": 28110 }, { "epoch": 0.16715111959151405, "grad_norm": 1.4494428634643555, "learning_rate": 0.00011142857142857144, "loss": 0.5967056274414062, "step": 28120 }, { "epoch": 0.16721056166818243, "grad_norm": 1.492806077003479, "learning_rate": 0.00011146819893005747, "loss": 0.6286416053771973, "step": 28130 }, { "epoch": 0.16727000374485082, "grad_norm": 1.8649324178695679, "learning_rate": 0.0001115078264315435, "loss": 0.6860939502716065, "step": 28140 }, { "epoch": 0.1673294458215192, "grad_norm": 1.3625354766845703, "learning_rate": 0.00011154745393302952, "loss": 0.7021075248718261, "step": 28150 }, { "epoch": 0.16738888789818762, "grad_norm": 1.5446239709854126, "learning_rate": 0.00011158708143451554, "loss": 0.7274449348449707, "step": 28160 }, { "epoch": 0.167448329974856, "grad_norm": 1.199082851409912, "learning_rate": 0.0001116267089360016, "loss": 0.6314595222473145, "step": 28170 }, { "epoch": 0.1675077720515244, "grad_norm": 1.4380701780319214, "learning_rate": 0.00011166633643748764, "loss": 0.6650717735290528, "step": 28180 }, { "epoch": 0.16756721412819278, "grad_norm": 1.687833309173584, "learning_rate": 0.00011170596393897366, "loss": 0.6263734817504882, "step": 28190 }, { "epoch": 0.16762665620486117, "grad_norm": 1.2589187622070312, "learning_rate": 0.00011174559144045969, "loss": 0.6613595485687256, "step": 28200 }, { "epoch": 0.16768609828152956, "grad_norm": 2.059803009033203, "learning_rate": 0.00011178521894194571, "loss": 0.6532832622528076, "step": 28210 }, { "epoch": 0.16774554035819794, "grad_norm": 1.69284987449646, "learning_rate": 0.00011182484644343174, "loss": 0.6953289985656739, "step": 28220 }, { "epoch": 0.16780498243486636, "grad_norm": 1.269714593887329, "learning_rate": 0.00011186447394491777, "loss": 0.6593293666839599, "step": 28230 }, { "epoch": 0.16786442451153474, "grad_norm": 1.353971004486084, "learning_rate": 0.00011190410144640381, "loss": 0.6611225128173828, "step": 28240 }, { "epoch": 0.16792386658820313, "grad_norm": 1.4372564554214478, "learning_rate": 0.00011194372894788985, "loss": 0.675552225112915, "step": 28250 }, { "epoch": 0.16798330866487152, "grad_norm": 1.363660216331482, "learning_rate": 0.00011198335644937588, "loss": 0.6825888633728028, "step": 28260 }, { "epoch": 0.1680427507415399, "grad_norm": 1.3123869895935059, "learning_rate": 0.0001120229839508619, "loss": 0.646838903427124, "step": 28270 }, { "epoch": 0.1681021928182083, "grad_norm": 1.708767294883728, "learning_rate": 0.00011206261145234793, "loss": 0.6837228775024414, "step": 28280 }, { "epoch": 0.16816163489487668, "grad_norm": 1.1529221534729004, "learning_rate": 0.00011210223895383397, "loss": 0.6684105873107911, "step": 28290 }, { "epoch": 0.1682210769715451, "grad_norm": 1.3648582696914673, "learning_rate": 0.00011214186645531999, "loss": 0.6384323120117188, "step": 28300 }, { "epoch": 0.16828051904821348, "grad_norm": 1.4131566286087036, "learning_rate": 0.00011218149395680604, "loss": 0.6439292430877686, "step": 28310 }, { "epoch": 0.16833996112488187, "grad_norm": 1.8428380489349365, "learning_rate": 0.00011222112145829207, "loss": 0.6555744171142578, "step": 28320 }, { "epoch": 0.16839940320155025, "grad_norm": 2.0236082077026367, "learning_rate": 0.00011226074895977809, "loss": 0.6478117942810059, "step": 28330 }, { "epoch": 0.16845884527821864, "grad_norm": 2.1218068599700928, "learning_rate": 0.00011230037646126412, "loss": 0.6874072074890136, "step": 28340 }, { "epoch": 0.16851828735488703, "grad_norm": 1.3601149320602417, "learning_rate": 0.00011234000396275016, "loss": 0.7163598537445068, "step": 28350 }, { "epoch": 0.1685777294315554, "grad_norm": 1.4092421531677246, "learning_rate": 0.00011237963146423618, "loss": 0.6289789199829101, "step": 28360 }, { "epoch": 0.1686371715082238, "grad_norm": 1.4508593082427979, "learning_rate": 0.00011241925896572221, "loss": 0.6957047462463379, "step": 28370 }, { "epoch": 0.1686966135848922, "grad_norm": 1.368335247039795, "learning_rate": 0.00011245888646720826, "loss": 0.6612538814544677, "step": 28380 }, { "epoch": 0.1687560556615606, "grad_norm": 1.620999813079834, "learning_rate": 0.00011249851396869428, "loss": 0.721973466873169, "step": 28390 }, { "epoch": 0.168815497738229, "grad_norm": 1.5046560764312744, "learning_rate": 0.00011253814147018031, "loss": 0.6596670150756836, "step": 28400 }, { "epoch": 0.16887493981489737, "grad_norm": 2.0960090160369873, "learning_rate": 0.00011257776897166635, "loss": 0.6620057106018067, "step": 28410 }, { "epoch": 0.16893438189156576, "grad_norm": 1.489967942237854, "learning_rate": 0.00011261739647315237, "loss": 0.6739622116088867, "step": 28420 }, { "epoch": 0.16899382396823415, "grad_norm": 1.1919281482696533, "learning_rate": 0.0001126570239746384, "loss": 0.6556572914123535, "step": 28430 }, { "epoch": 0.16905326604490253, "grad_norm": 2.1307754516601562, "learning_rate": 0.00011269665147612442, "loss": 0.6649372100830078, "step": 28440 }, { "epoch": 0.16911270812157095, "grad_norm": 1.5311387777328491, "learning_rate": 0.00011273627897761048, "loss": 0.678199577331543, "step": 28450 }, { "epoch": 0.16917215019823933, "grad_norm": 1.426119089126587, "learning_rate": 0.0001127759064790965, "loss": 0.6929396629333496, "step": 28460 }, { "epoch": 0.16923159227490772, "grad_norm": 1.5915201902389526, "learning_rate": 0.00011281553398058254, "loss": 0.6231417655944824, "step": 28470 }, { "epoch": 0.1692910343515761, "grad_norm": 2.561579704284668, "learning_rate": 0.00011285516148206856, "loss": 0.6665474891662597, "step": 28480 }, { "epoch": 0.1693504764282445, "grad_norm": 1.5939114093780518, "learning_rate": 0.00011289478898355459, "loss": 0.7231511116027832, "step": 28490 }, { "epoch": 0.16940991850491288, "grad_norm": 1.422904133796692, "learning_rate": 0.00011293441648504061, "loss": 0.6737591743469238, "step": 28500 }, { "epoch": 0.16946936058158127, "grad_norm": 1.4130845069885254, "learning_rate": 0.00011297404398652664, "loss": 0.6603398799896241, "step": 28510 }, { "epoch": 0.16952880265824966, "grad_norm": 1.4857796430587769, "learning_rate": 0.00011301367148801269, "loss": 0.7113092422485352, "step": 28520 }, { "epoch": 0.16958824473491807, "grad_norm": 1.4843357801437378, "learning_rate": 0.00011305329898949872, "loss": 0.6751676559448242, "step": 28530 }, { "epoch": 0.16964768681158646, "grad_norm": 1.5772788524627686, "learning_rate": 0.00011309292649098476, "loss": 0.6657628059387207, "step": 28540 }, { "epoch": 0.16970712888825484, "grad_norm": 1.7329235076904297, "learning_rate": 0.00011313255399247078, "loss": 0.6817787647247314, "step": 28550 }, { "epoch": 0.16976657096492323, "grad_norm": 1.5455191135406494, "learning_rate": 0.0001131721814939568, "loss": 0.7143467903137207, "step": 28560 }, { "epoch": 0.16982601304159162, "grad_norm": 1.2494746446609497, "learning_rate": 0.00011321180899544283, "loss": 0.6383099555969238, "step": 28570 }, { "epoch": 0.16988545511826, "grad_norm": 1.2728615999221802, "learning_rate": 0.00011325143649692887, "loss": 0.6595283508300781, "step": 28580 }, { "epoch": 0.1699448971949284, "grad_norm": 1.5733517408370972, "learning_rate": 0.00011329106399841491, "loss": 0.7300590515136719, "step": 28590 }, { "epoch": 0.1700043392715968, "grad_norm": 1.3379746675491333, "learning_rate": 0.00011333069149990095, "loss": 0.6894954681396485, "step": 28600 }, { "epoch": 0.1700637813482652, "grad_norm": 1.4239521026611328, "learning_rate": 0.00011337031900138697, "loss": 0.6577448844909668, "step": 28610 }, { "epoch": 0.17012322342493358, "grad_norm": 1.562578797340393, "learning_rate": 0.000113409946502873, "loss": 0.6999078750610351, "step": 28620 }, { "epoch": 0.17018266550160197, "grad_norm": 1.6748090982437134, "learning_rate": 0.00011344957400435902, "loss": 0.67637619972229, "step": 28630 }, { "epoch": 0.17024210757827035, "grad_norm": 1.5205798149108887, "learning_rate": 0.00011348920150584506, "loss": 0.7031056404113769, "step": 28640 }, { "epoch": 0.17030154965493874, "grad_norm": 1.4477958679199219, "learning_rate": 0.00011352882900733109, "loss": 0.7100790500640869, "step": 28650 }, { "epoch": 0.17036099173160713, "grad_norm": 1.7344263792037964, "learning_rate": 0.00011356845650881714, "loss": 0.6595396995544434, "step": 28660 }, { "epoch": 0.1704204338082755, "grad_norm": 1.852612018585205, "learning_rate": 0.00011360808401030316, "loss": 0.6488523483276367, "step": 28670 }, { "epoch": 0.17047987588494393, "grad_norm": 1.2815483808517456, "learning_rate": 0.00011364771151178919, "loss": 0.689639949798584, "step": 28680 }, { "epoch": 0.1705393179616123, "grad_norm": 1.5173285007476807, "learning_rate": 0.00011368733901327521, "loss": 0.6405400276184082, "step": 28690 }, { "epoch": 0.1705987600382807, "grad_norm": 1.2476072311401367, "learning_rate": 0.00011372696651476125, "loss": 0.5952719211578369, "step": 28700 }, { "epoch": 0.1706582021149491, "grad_norm": 1.391011357307434, "learning_rate": 0.00011376659401624728, "loss": 0.69229097366333, "step": 28710 }, { "epoch": 0.17071764419161747, "grad_norm": 1.1037517786026, "learning_rate": 0.0001138062215177333, "loss": 0.6869038105010986, "step": 28720 }, { "epoch": 0.17077708626828586, "grad_norm": 1.529930830001831, "learning_rate": 0.00011384584901921935, "loss": 0.671150016784668, "step": 28730 }, { "epoch": 0.17083652834495425, "grad_norm": 0.8552169799804688, "learning_rate": 0.00011388547652070538, "loss": 0.60186767578125, "step": 28740 }, { "epoch": 0.17089597042162266, "grad_norm": 1.4495172500610352, "learning_rate": 0.0001139251040221914, "loss": 0.7069303512573242, "step": 28750 }, { "epoch": 0.17095541249829105, "grad_norm": 1.1715788841247559, "learning_rate": 0.00011396473152367744, "loss": 0.6790699005126953, "step": 28760 }, { "epoch": 0.17101485457495944, "grad_norm": 1.4595547914505005, "learning_rate": 0.00011400435902516347, "loss": 0.629314661026001, "step": 28770 }, { "epoch": 0.17107429665162782, "grad_norm": 1.2634638547897339, "learning_rate": 0.0001140439865266495, "loss": 0.6836535453796386, "step": 28780 }, { "epoch": 0.1711337387282962, "grad_norm": 1.335235595703125, "learning_rate": 0.00011408361402813552, "loss": 0.7356934547424316, "step": 28790 }, { "epoch": 0.1711931808049646, "grad_norm": 1.4917774200439453, "learning_rate": 0.00011412324152962157, "loss": 0.7075772762298584, "step": 28800 }, { "epoch": 0.17125262288163298, "grad_norm": 1.7645399570465088, "learning_rate": 0.0001141628690311076, "loss": 0.7520384311676025, "step": 28810 }, { "epoch": 0.1713120649583014, "grad_norm": 1.7225418090820312, "learning_rate": 0.00011420249653259362, "loss": 0.6697252273559571, "step": 28820 }, { "epoch": 0.17137150703496978, "grad_norm": 1.7207424640655518, "learning_rate": 0.00011424212403407966, "loss": 0.7091679573059082, "step": 28830 }, { "epoch": 0.17143094911163817, "grad_norm": 1.4470018148422241, "learning_rate": 0.00011428175153556569, "loss": 0.658001708984375, "step": 28840 }, { "epoch": 0.17149039118830656, "grad_norm": 1.262916922569275, "learning_rate": 0.00011432137903705171, "loss": 0.6762107849121094, "step": 28850 }, { "epoch": 0.17154983326497494, "grad_norm": 1.3285622596740723, "learning_rate": 0.00011436100653853774, "loss": 0.6999341964721679, "step": 28860 }, { "epoch": 0.17160927534164333, "grad_norm": 1.3079079389572144, "learning_rate": 0.00011440063404002379, "loss": 0.609159278869629, "step": 28870 }, { "epoch": 0.17166871741831172, "grad_norm": 1.4105520248413086, "learning_rate": 0.00011444026154150981, "loss": 0.6990399837493897, "step": 28880 }, { "epoch": 0.1717281594949801, "grad_norm": 1.5775948762893677, "learning_rate": 0.00011447988904299585, "loss": 0.7044528007507325, "step": 28890 }, { "epoch": 0.17178760157164852, "grad_norm": 1.5320900678634644, "learning_rate": 0.00011451951654448188, "loss": 0.7049650192260742, "step": 28900 }, { "epoch": 0.1718470436483169, "grad_norm": 1.4133574962615967, "learning_rate": 0.0001145591440459679, "loss": 0.7376061916351319, "step": 28910 }, { "epoch": 0.1719064857249853, "grad_norm": 1.427926778793335, "learning_rate": 0.00011459877154745393, "loss": 0.6968253135681153, "step": 28920 }, { "epoch": 0.17196592780165368, "grad_norm": 1.4408767223358154, "learning_rate": 0.00011463839904893997, "loss": 0.7027411460876465, "step": 28930 }, { "epoch": 0.17202536987832207, "grad_norm": 1.538130760192871, "learning_rate": 0.000114678026550426, "loss": 0.6859467506408692, "step": 28940 }, { "epoch": 0.17208481195499045, "grad_norm": 1.5039606094360352, "learning_rate": 0.00011471765405191204, "loss": 0.6837775230407714, "step": 28950 }, { "epoch": 0.17214425403165884, "grad_norm": 1.5021567344665527, "learning_rate": 0.00011475728155339807, "loss": 0.7126679420471191, "step": 28960 }, { "epoch": 0.17220369610832725, "grad_norm": 1.58664071559906, "learning_rate": 0.00011479690905488409, "loss": 0.683342170715332, "step": 28970 }, { "epoch": 0.17226313818499564, "grad_norm": 1.493621826171875, "learning_rate": 0.00011483653655637012, "loss": 0.7416317939758301, "step": 28980 }, { "epoch": 0.17232258026166403, "grad_norm": 1.3172786235809326, "learning_rate": 0.00011487616405785616, "loss": 0.6783996105194092, "step": 28990 }, { "epoch": 0.1723820223383324, "grad_norm": 1.748799204826355, "learning_rate": 0.00011491579155934218, "loss": 0.6138044357299804, "step": 29000 }, { "epoch": 0.1724414644150008, "grad_norm": 1.9369165897369385, "learning_rate": 0.00011495541906082823, "loss": 0.6743250846862793, "step": 29010 }, { "epoch": 0.1725009064916692, "grad_norm": 1.6703219413757324, "learning_rate": 0.00011499504656231426, "loss": 0.6620607376098633, "step": 29020 }, { "epoch": 0.17256034856833757, "grad_norm": 1.193562626838684, "learning_rate": 0.00011503467406380028, "loss": 0.6295544624328613, "step": 29030 }, { "epoch": 0.17261979064500596, "grad_norm": 1.9962854385375977, "learning_rate": 0.00011507430156528631, "loss": 0.639328908920288, "step": 29040 }, { "epoch": 0.17267923272167437, "grad_norm": 1.1608299016952515, "learning_rate": 0.00011511392906677235, "loss": 0.6060475826263427, "step": 29050 }, { "epoch": 0.17273867479834276, "grad_norm": 1.6035007238388062, "learning_rate": 0.00011515355656825837, "loss": 0.6549980640411377, "step": 29060 }, { "epoch": 0.17279811687501115, "grad_norm": 1.8139305114746094, "learning_rate": 0.0001151931840697444, "loss": 0.6594440460205078, "step": 29070 }, { "epoch": 0.17285755895167954, "grad_norm": 1.2691622972488403, "learning_rate": 0.00011523281157123045, "loss": 0.7117889881134033, "step": 29080 }, { "epoch": 0.17291700102834792, "grad_norm": 1.6484544277191162, "learning_rate": 0.00011527243907271648, "loss": 0.7071385383605957, "step": 29090 }, { "epoch": 0.1729764431050163, "grad_norm": 1.5312303304672241, "learning_rate": 0.0001153120665742025, "loss": 0.6136029243469239, "step": 29100 }, { "epoch": 0.1730358851816847, "grad_norm": 1.5774481296539307, "learning_rate": 0.00011535169407568854, "loss": 0.6387234210968018, "step": 29110 }, { "epoch": 0.1730953272583531, "grad_norm": 1.3588916063308716, "learning_rate": 0.00011539132157717456, "loss": 0.5968206405639649, "step": 29120 }, { "epoch": 0.1731547693350215, "grad_norm": 1.5922590494155884, "learning_rate": 0.00011543094907866059, "loss": 0.7056298732757569, "step": 29130 }, { "epoch": 0.17321421141168988, "grad_norm": 1.549951434135437, "learning_rate": 0.00011547057658014661, "loss": 0.662109088897705, "step": 29140 }, { "epoch": 0.17327365348835827, "grad_norm": 1.6258695125579834, "learning_rate": 0.00011551020408163267, "loss": 0.6504735946655273, "step": 29150 }, { "epoch": 0.17333309556502666, "grad_norm": 1.6317068338394165, "learning_rate": 0.00011554983158311869, "loss": 0.6114564895629883, "step": 29160 }, { "epoch": 0.17339253764169504, "grad_norm": 1.4542717933654785, "learning_rate": 0.00011558945908460472, "loss": 0.6646116733551025, "step": 29170 }, { "epoch": 0.17345197971836343, "grad_norm": 1.8406959772109985, "learning_rate": 0.00011562908658609076, "loss": 0.7247468948364257, "step": 29180 }, { "epoch": 0.17351142179503184, "grad_norm": 1.5563091039657593, "learning_rate": 0.00011566871408757678, "loss": 0.666012191772461, "step": 29190 }, { "epoch": 0.17357086387170023, "grad_norm": 2.359581708908081, "learning_rate": 0.0001157083415890628, "loss": 0.6066003322601319, "step": 29200 }, { "epoch": 0.17363030594836862, "grad_norm": 1.4178818464279175, "learning_rate": 0.00011574796909054883, "loss": 0.6140038967132568, "step": 29210 }, { "epoch": 0.173689748025037, "grad_norm": 1.389364242553711, "learning_rate": 0.00011578759659203488, "loss": 0.6763210773468018, "step": 29220 }, { "epoch": 0.1737491901017054, "grad_norm": 1.4724270105361938, "learning_rate": 0.00011582722409352091, "loss": 0.6492150306701661, "step": 29230 }, { "epoch": 0.17380863217837378, "grad_norm": 1.5552058219909668, "learning_rate": 0.00011586685159500695, "loss": 0.6507887840270996, "step": 29240 }, { "epoch": 0.17386807425504217, "grad_norm": 1.8033121824264526, "learning_rate": 0.00011590647909649297, "loss": 0.656791877746582, "step": 29250 }, { "epoch": 0.17392751633171055, "grad_norm": 1.5060484409332275, "learning_rate": 0.000115946106597979, "loss": 0.6609257698059082, "step": 29260 }, { "epoch": 0.17398695840837897, "grad_norm": 1.8153765201568604, "learning_rate": 0.00011598573409946502, "loss": 0.638492488861084, "step": 29270 }, { "epoch": 0.17404640048504735, "grad_norm": 1.6279538869857788, "learning_rate": 0.00011602536160095106, "loss": 0.7157602310180664, "step": 29280 }, { "epoch": 0.17410584256171574, "grad_norm": 1.1549831628799438, "learning_rate": 0.0001160649891024371, "loss": 0.6408705711364746, "step": 29290 }, { "epoch": 0.17416528463838413, "grad_norm": 1.5275055170059204, "learning_rate": 0.00011610461660392314, "loss": 0.6965507507324219, "step": 29300 }, { "epoch": 0.1742247267150525, "grad_norm": 2.072470188140869, "learning_rate": 0.00011614424410540916, "loss": 0.6791495323181153, "step": 29310 }, { "epoch": 0.1742841687917209, "grad_norm": 1.4791852235794067, "learning_rate": 0.00011618387160689519, "loss": 0.6932684898376464, "step": 29320 }, { "epoch": 0.1743436108683893, "grad_norm": 1.4970873594284058, "learning_rate": 0.00011622349910838121, "loss": 0.6349082946777344, "step": 29330 }, { "epoch": 0.1744030529450577, "grad_norm": 1.1349481344223022, "learning_rate": 0.00011626312660986725, "loss": 0.6682257652282715, "step": 29340 }, { "epoch": 0.1744624950217261, "grad_norm": 1.7864011526107788, "learning_rate": 0.00011630275411135328, "loss": 0.6455212116241456, "step": 29350 }, { "epoch": 0.17452193709839448, "grad_norm": 2.0210890769958496, "learning_rate": 0.00011634238161283933, "loss": 0.7294182777404785, "step": 29360 }, { "epoch": 0.17458137917506286, "grad_norm": 1.4305847883224487, "learning_rate": 0.00011638200911432535, "loss": 0.6459338665008545, "step": 29370 }, { "epoch": 0.17464082125173125, "grad_norm": 1.4251925945281982, "learning_rate": 0.00011642163661581138, "loss": 0.6657840728759765, "step": 29380 }, { "epoch": 0.17470026332839964, "grad_norm": 1.2401760816574097, "learning_rate": 0.0001164612641172974, "loss": 0.6303231239318847, "step": 29390 }, { "epoch": 0.17475970540506802, "grad_norm": 1.4536871910095215, "learning_rate": 0.00011650089161878344, "loss": 0.6381364822387695, "step": 29400 }, { "epoch": 0.1748191474817364, "grad_norm": 1.3546820878982544, "learning_rate": 0.00011654051912026947, "loss": 0.6549807548522949, "step": 29410 }, { "epoch": 0.17487858955840482, "grad_norm": 1.1936930418014526, "learning_rate": 0.00011658014662175552, "loss": 0.6943359375, "step": 29420 }, { "epoch": 0.1749380316350732, "grad_norm": 1.2151317596435547, "learning_rate": 0.00011661977412324155, "loss": 0.6580106735229492, "step": 29430 }, { "epoch": 0.1749974737117416, "grad_norm": 1.8773410320281982, "learning_rate": 0.00011665940162472757, "loss": 0.6398515701293945, "step": 29440 }, { "epoch": 0.17505691578840998, "grad_norm": 1.408907175064087, "learning_rate": 0.0001166990291262136, "loss": 0.6562140464782715, "step": 29450 }, { "epoch": 0.17511635786507837, "grad_norm": 1.4772688150405884, "learning_rate": 0.00011673865662769962, "loss": 0.6939606666564941, "step": 29460 }, { "epoch": 0.17517579994174676, "grad_norm": 1.6124626398086548, "learning_rate": 0.00011677828412918566, "loss": 0.6780758380889893, "step": 29470 }, { "epoch": 0.17523524201841514, "grad_norm": 1.8116929531097412, "learning_rate": 0.00011681791163067168, "loss": 0.6904648780822754, "step": 29480 }, { "epoch": 0.17529468409508356, "grad_norm": 1.9342544078826904, "learning_rate": 0.00011685753913215774, "loss": 0.7086153507232666, "step": 29490 }, { "epoch": 0.17535412617175195, "grad_norm": 1.3760528564453125, "learning_rate": 0.00011689716663364376, "loss": 0.6781368255615234, "step": 29500 }, { "epoch": 0.17541356824842033, "grad_norm": 1.568631887435913, "learning_rate": 0.00011693679413512979, "loss": 0.6987418174743653, "step": 29510 }, { "epoch": 0.17547301032508872, "grad_norm": 1.6571825742721558, "learning_rate": 0.00011697642163661581, "loss": 0.6736040592193604, "step": 29520 }, { "epoch": 0.1755324524017571, "grad_norm": 1.2328764200210571, "learning_rate": 0.00011701604913810185, "loss": 0.6664210796356201, "step": 29530 }, { "epoch": 0.1755918944784255, "grad_norm": 1.469258189201355, "learning_rate": 0.00011705567663958788, "loss": 0.6428884506225586, "step": 29540 }, { "epoch": 0.17565133655509388, "grad_norm": 1.1539082527160645, "learning_rate": 0.0001170953041410739, "loss": 0.6689333915710449, "step": 29550 }, { "epoch": 0.17571077863176227, "grad_norm": 1.5517147779464722, "learning_rate": 0.00011713493164255995, "loss": 0.7013904094696045, "step": 29560 }, { "epoch": 0.17577022070843068, "grad_norm": 1.2945754528045654, "learning_rate": 0.00011717455914404598, "loss": 0.6623192310333252, "step": 29570 }, { "epoch": 0.17582966278509907, "grad_norm": 1.6252360343933105, "learning_rate": 0.000117214186645532, "loss": 0.6782722473144531, "step": 29580 }, { "epoch": 0.17588910486176745, "grad_norm": 1.6242008209228516, "learning_rate": 0.00011725381414701804, "loss": 0.7125933170318604, "step": 29590 }, { "epoch": 0.17594854693843584, "grad_norm": 1.4490184783935547, "learning_rate": 0.00011729344164850407, "loss": 0.6598342895507813, "step": 29600 }, { "epoch": 0.17600798901510423, "grad_norm": 1.5001691579818726, "learning_rate": 0.00011733306914999009, "loss": 0.6547446250915527, "step": 29610 }, { "epoch": 0.1760674310917726, "grad_norm": 1.6054472923278809, "learning_rate": 0.00011737269665147612, "loss": 0.6640482902526855, "step": 29620 }, { "epoch": 0.176126873168441, "grad_norm": 1.3440358638763428, "learning_rate": 0.00011741232415296217, "loss": 0.694120454788208, "step": 29630 }, { "epoch": 0.17618631524510941, "grad_norm": 1.3746310472488403, "learning_rate": 0.0001174519516544482, "loss": 0.6973852634429931, "step": 29640 }, { "epoch": 0.1762457573217778, "grad_norm": 1.336690068244934, "learning_rate": 0.00011749157915593423, "loss": 0.6512240886688232, "step": 29650 }, { "epoch": 0.1763051993984462, "grad_norm": 1.3745841979980469, "learning_rate": 0.00011753120665742026, "loss": 0.6225883483886718, "step": 29660 }, { "epoch": 0.17636464147511458, "grad_norm": 1.4629545211791992, "learning_rate": 0.00011757083415890628, "loss": 0.7160204887390137, "step": 29670 }, { "epoch": 0.17642408355178296, "grad_norm": 2.044630289077759, "learning_rate": 0.00011761046166039231, "loss": 0.6821905612945557, "step": 29680 }, { "epoch": 0.17648352562845135, "grad_norm": 1.4625346660614014, "learning_rate": 0.00011765008916187835, "loss": 0.6805853843688965, "step": 29690 }, { "epoch": 0.17654296770511974, "grad_norm": 1.7147740125656128, "learning_rate": 0.00011768971666336439, "loss": 0.6068115234375, "step": 29700 }, { "epoch": 0.17660240978178815, "grad_norm": 1.6322928667068481, "learning_rate": 0.00011772934416485042, "loss": 0.674779224395752, "step": 29710 }, { "epoch": 0.17666185185845654, "grad_norm": 1.5788966417312622, "learning_rate": 0.00011776897166633645, "loss": 0.6355792999267578, "step": 29720 }, { "epoch": 0.17672129393512492, "grad_norm": 1.437644600868225, "learning_rate": 0.00011780859916782247, "loss": 0.669329833984375, "step": 29730 }, { "epoch": 0.1767807360117933, "grad_norm": 1.4324837923049927, "learning_rate": 0.0001178482266693085, "loss": 0.7345038890838623, "step": 29740 }, { "epoch": 0.1768401780884617, "grad_norm": 1.3368339538574219, "learning_rate": 0.00011788785417079452, "loss": 0.6677089691162109, "step": 29750 }, { "epoch": 0.17689962016513008, "grad_norm": 1.404863953590393, "learning_rate": 0.00011792748167228056, "loss": 0.653348445892334, "step": 29760 }, { "epoch": 0.17695906224179847, "grad_norm": 1.58566153049469, "learning_rate": 0.00011796710917376662, "loss": 0.6799668312072754, "step": 29770 }, { "epoch": 0.17701850431846686, "grad_norm": 1.6526124477386475, "learning_rate": 0.00011800673667525264, "loss": 0.6135120391845703, "step": 29780 }, { "epoch": 0.17707794639513527, "grad_norm": 2.293344736099243, "learning_rate": 0.00011804636417673867, "loss": 0.6935583591461182, "step": 29790 }, { "epoch": 0.17713738847180366, "grad_norm": 1.397233486175537, "learning_rate": 0.00011808599167822469, "loss": 0.690317440032959, "step": 29800 }, { "epoch": 0.17719683054847205, "grad_norm": 1.4058605432510376, "learning_rate": 0.00011812561917971072, "loss": 0.6797543048858643, "step": 29810 }, { "epoch": 0.17725627262514043, "grad_norm": 1.8798813819885254, "learning_rate": 0.00011816524668119675, "loss": 0.7423221111297608, "step": 29820 }, { "epoch": 0.17731571470180882, "grad_norm": 1.5965086221694946, "learning_rate": 0.00011820487418268278, "loss": 0.6681221008300782, "step": 29830 }, { "epoch": 0.1773751567784772, "grad_norm": 1.581555724143982, "learning_rate": 0.00011824450168416883, "loss": 0.6197362899780273, "step": 29840 }, { "epoch": 0.1774345988551456, "grad_norm": 1.506266713142395, "learning_rate": 0.00011828412918565486, "loss": 0.6279854774475098, "step": 29850 }, { "epoch": 0.177494040931814, "grad_norm": 1.8388034105300903, "learning_rate": 0.00011832375668714088, "loss": 0.7146681785583496, "step": 29860 }, { "epoch": 0.1775534830084824, "grad_norm": 1.3901214599609375, "learning_rate": 0.00011836338418862691, "loss": 0.6557488918304444, "step": 29870 }, { "epoch": 0.17761292508515078, "grad_norm": 1.4037117958068848, "learning_rate": 0.00011840301169011295, "loss": 0.6686690330505372, "step": 29880 }, { "epoch": 0.17767236716181917, "grad_norm": 1.5531920194625854, "learning_rate": 0.00011844263919159897, "loss": 0.6802406311035156, "step": 29890 }, { "epoch": 0.17773180923848755, "grad_norm": 1.6167230606079102, "learning_rate": 0.000118482266693085, "loss": 0.6569484233856201, "step": 29900 }, { "epoch": 0.17779125131515594, "grad_norm": 1.5949499607086182, "learning_rate": 0.00011852189419457105, "loss": 0.6154006958007813, "step": 29910 }, { "epoch": 0.17785069339182433, "grad_norm": 1.8400508165359497, "learning_rate": 0.00011856152169605707, "loss": 0.6937238693237304, "step": 29920 }, { "epoch": 0.1779101354684927, "grad_norm": 1.1628187894821167, "learning_rate": 0.0001186011491975431, "loss": 0.6464168071746826, "step": 29930 }, { "epoch": 0.17796957754516113, "grad_norm": 1.2566123008728027, "learning_rate": 0.00011864077669902914, "loss": 0.7032037734985351, "step": 29940 }, { "epoch": 0.17802901962182952, "grad_norm": 1.4862433671951294, "learning_rate": 0.00011868040420051516, "loss": 0.6960731983184815, "step": 29950 }, { "epoch": 0.1780884616984979, "grad_norm": 1.7007131576538086, "learning_rate": 0.00011872003170200119, "loss": 0.6294290542602539, "step": 29960 }, { "epoch": 0.1781479037751663, "grad_norm": 1.635088324546814, "learning_rate": 0.00011875965920348721, "loss": 0.6335720539093017, "step": 29970 }, { "epoch": 0.17820734585183468, "grad_norm": 1.2969167232513428, "learning_rate": 0.00011879928670497326, "loss": 0.7335664749145507, "step": 29980 }, { "epoch": 0.17826678792850306, "grad_norm": 1.6849420070648193, "learning_rate": 0.00011883891420645929, "loss": 0.6863603591918945, "step": 29990 }, { "epoch": 0.17832623000517145, "grad_norm": 1.4658833742141724, "learning_rate": 0.00011887854170794533, "loss": 0.6954124450683594, "step": 30000 }, { "epoch": 0.17838567208183986, "grad_norm": 1.2648893594741821, "learning_rate": 0.00011891816920943135, "loss": 0.669189739227295, "step": 30010 }, { "epoch": 0.17844511415850825, "grad_norm": 1.3992102146148682, "learning_rate": 0.00011895779671091738, "loss": 0.6638231754302979, "step": 30020 }, { "epoch": 0.17850455623517664, "grad_norm": 1.3408823013305664, "learning_rate": 0.0001189974242124034, "loss": 0.6612166404724121, "step": 30030 }, { "epoch": 0.17856399831184502, "grad_norm": 1.4058526754379272, "learning_rate": 0.00011903705171388944, "loss": 0.6767981052398682, "step": 30040 }, { "epoch": 0.1786234403885134, "grad_norm": 1.4278161525726318, "learning_rate": 0.00011907667921537548, "loss": 0.6339051723480225, "step": 30050 }, { "epoch": 0.1786828824651818, "grad_norm": 1.6103930473327637, "learning_rate": 0.00011911630671686152, "loss": 0.6366127014160157, "step": 30060 }, { "epoch": 0.17874232454185018, "grad_norm": 1.5983046293258667, "learning_rate": 0.00011915593421834755, "loss": 0.6734556198120117, "step": 30070 }, { "epoch": 0.1788017666185186, "grad_norm": 1.7769020795822144, "learning_rate": 0.00011919556171983357, "loss": 0.6479047775268555, "step": 30080 }, { "epoch": 0.17886120869518699, "grad_norm": 1.6469664573669434, "learning_rate": 0.0001192351892213196, "loss": 0.6810583114624024, "step": 30090 }, { "epoch": 0.17892065077185537, "grad_norm": 1.5667508840560913, "learning_rate": 0.00011927481672280562, "loss": 0.6687159061431884, "step": 30100 }, { "epoch": 0.17898009284852376, "grad_norm": 1.6330792903900146, "learning_rate": 0.00011931444422429166, "loss": 0.6454999923706055, "step": 30110 }, { "epoch": 0.17903953492519215, "grad_norm": 1.663957953453064, "learning_rate": 0.00011935407172577771, "loss": 0.6229316711425781, "step": 30120 }, { "epoch": 0.17909897700186053, "grad_norm": 1.4370192289352417, "learning_rate": 0.00011939369922726374, "loss": 0.6242106437683106, "step": 30130 }, { "epoch": 0.17915841907852892, "grad_norm": 1.3301323652267456, "learning_rate": 0.00011943332672874976, "loss": 0.5980748176574707, "step": 30140 }, { "epoch": 0.1792178611551973, "grad_norm": 1.5548993349075317, "learning_rate": 0.00011947295423023579, "loss": 0.6629638671875, "step": 30150 }, { "epoch": 0.17927730323186572, "grad_norm": 1.4276623725891113, "learning_rate": 0.00011951258173172181, "loss": 0.649269962310791, "step": 30160 }, { "epoch": 0.1793367453085341, "grad_norm": 2.092754364013672, "learning_rate": 0.00011955220923320785, "loss": 0.6757325172424317, "step": 30170 }, { "epoch": 0.1793961873852025, "grad_norm": 1.637745976448059, "learning_rate": 0.00011959183673469388, "loss": 0.6563238143920899, "step": 30180 }, { "epoch": 0.17945562946187088, "grad_norm": 1.6169105768203735, "learning_rate": 0.00011963146423617993, "loss": 0.652214527130127, "step": 30190 }, { "epoch": 0.17951507153853927, "grad_norm": 1.6901490688323975, "learning_rate": 0.00011967109173766595, "loss": 0.6453524589538574, "step": 30200 }, { "epoch": 0.17957451361520765, "grad_norm": 1.3831641674041748, "learning_rate": 0.00011971071923915198, "loss": 0.6610171318054199, "step": 30210 }, { "epoch": 0.17963395569187604, "grad_norm": 1.3684526681900024, "learning_rate": 0.000119750346740638, "loss": 0.6615612983703614, "step": 30220 }, { "epoch": 0.17969339776854446, "grad_norm": 1.430519938468933, "learning_rate": 0.00011978997424212404, "loss": 0.7162887573242187, "step": 30230 }, { "epoch": 0.17975283984521284, "grad_norm": 1.317206621170044, "learning_rate": 0.00011982960174361007, "loss": 0.6366286277770996, "step": 30240 }, { "epoch": 0.17981228192188123, "grad_norm": 1.584722638130188, "learning_rate": 0.00011986922924509609, "loss": 0.6165594100952149, "step": 30250 }, { "epoch": 0.17987172399854962, "grad_norm": 1.2283028364181519, "learning_rate": 0.00011990885674658214, "loss": 0.6375278949737548, "step": 30260 }, { "epoch": 0.179931166075218, "grad_norm": 1.6148574352264404, "learning_rate": 0.00011994848424806817, "loss": 0.6405478477478027, "step": 30270 }, { "epoch": 0.1799906081518864, "grad_norm": 1.3029030561447144, "learning_rate": 0.0001199881117495542, "loss": 0.6521941184997558, "step": 30280 }, { "epoch": 0.18005005022855478, "grad_norm": 1.201983094215393, "learning_rate": 0.00012002773925104023, "loss": 0.7093276023864746, "step": 30290 }, { "epoch": 0.18010949230522316, "grad_norm": 1.3969988822937012, "learning_rate": 0.00012006736675252626, "loss": 0.6459318637847901, "step": 30300 }, { "epoch": 0.18016893438189158, "grad_norm": 1.6718432903289795, "learning_rate": 0.00012010699425401228, "loss": 0.6854230880737304, "step": 30310 }, { "epoch": 0.18022837645855996, "grad_norm": 1.4567002058029175, "learning_rate": 0.00012014662175549831, "loss": 0.6633442401885986, "step": 30320 }, { "epoch": 0.18028781853522835, "grad_norm": 1.5522996187210083, "learning_rate": 0.00012018624925698436, "loss": 0.6755495071411133, "step": 30330 }, { "epoch": 0.18034726061189674, "grad_norm": 1.5062416791915894, "learning_rate": 0.00012022587675847039, "loss": 0.7070281028747558, "step": 30340 }, { "epoch": 0.18040670268856512, "grad_norm": 1.5095911026000977, "learning_rate": 0.00012026550425995642, "loss": 0.6606842994689941, "step": 30350 }, { "epoch": 0.1804661447652335, "grad_norm": 1.2785698175430298, "learning_rate": 0.00012030513176144245, "loss": 0.6821740150451661, "step": 30360 }, { "epoch": 0.1805255868419019, "grad_norm": 1.2011319398880005, "learning_rate": 0.00012034475926292847, "loss": 0.6727432250976563, "step": 30370 }, { "epoch": 0.1805850289185703, "grad_norm": 1.4261460304260254, "learning_rate": 0.0001203843867644145, "loss": 0.5921133518218994, "step": 30380 }, { "epoch": 0.1806444709952387, "grad_norm": 1.3643591403961182, "learning_rate": 0.00012042401426590052, "loss": 0.6524919033050537, "step": 30390 }, { "epoch": 0.18070391307190709, "grad_norm": 1.3815937042236328, "learning_rate": 0.00012046364176738658, "loss": 0.6688868522644043, "step": 30400 }, { "epoch": 0.18076335514857547, "grad_norm": 2.2322473526000977, "learning_rate": 0.00012050326926887262, "loss": 0.6571937561035156, "step": 30410 }, { "epoch": 0.18082279722524386, "grad_norm": 1.7600449323654175, "learning_rate": 0.00012054289677035864, "loss": 0.6960638523101806, "step": 30420 }, { "epoch": 0.18088223930191225, "grad_norm": 1.3742451667785645, "learning_rate": 0.00012058252427184467, "loss": 0.6550190448760986, "step": 30430 }, { "epoch": 0.18094168137858063, "grad_norm": 1.455163836479187, "learning_rate": 0.00012062215177333069, "loss": 0.684942626953125, "step": 30440 }, { "epoch": 0.18100112345524902, "grad_norm": 1.421826720237732, "learning_rate": 0.00012066177927481672, "loss": 0.6167601585388184, "step": 30450 }, { "epoch": 0.18106056553191743, "grad_norm": 1.3384262323379517, "learning_rate": 0.00012070140677630275, "loss": 0.648032808303833, "step": 30460 }, { "epoch": 0.18112000760858582, "grad_norm": 1.8304387331008911, "learning_rate": 0.0001207410342777888, "loss": 0.6717251777648926, "step": 30470 }, { "epoch": 0.1811794496852542, "grad_norm": 1.585443377494812, "learning_rate": 0.00012078066177927483, "loss": 0.6707037925720215, "step": 30480 }, { "epoch": 0.1812388917619226, "grad_norm": 1.747726559638977, "learning_rate": 0.00012082028928076086, "loss": 0.6855700016021729, "step": 30490 }, { "epoch": 0.18129833383859098, "grad_norm": 1.5637649297714233, "learning_rate": 0.00012085991678224688, "loss": 0.6631102561950684, "step": 30500 }, { "epoch": 0.18135777591525937, "grad_norm": 1.1994050741195679, "learning_rate": 0.00012089954428373291, "loss": 0.702135705947876, "step": 30510 }, { "epoch": 0.18141721799192775, "grad_norm": 1.6411306858062744, "learning_rate": 0.00012093917178521895, "loss": 0.6351099491119385, "step": 30520 }, { "epoch": 0.18147666006859617, "grad_norm": 1.4636567831039429, "learning_rate": 0.00012097879928670497, "loss": 0.653618574142456, "step": 30530 }, { "epoch": 0.18153610214526456, "grad_norm": 1.2744430303573608, "learning_rate": 0.00012101842678819102, "loss": 0.5719606876373291, "step": 30540 }, { "epoch": 0.18159554422193294, "grad_norm": 1.528724193572998, "learning_rate": 0.00012105805428967705, "loss": 0.714429235458374, "step": 30550 }, { "epoch": 0.18165498629860133, "grad_norm": 1.7009822130203247, "learning_rate": 0.00012109768179116307, "loss": 0.6712443351745605, "step": 30560 }, { "epoch": 0.18171442837526972, "grad_norm": 1.7657543420791626, "learning_rate": 0.0001211373092926491, "loss": 0.6895012855529785, "step": 30570 }, { "epoch": 0.1817738704519381, "grad_norm": 1.9839760065078735, "learning_rate": 0.00012117693679413514, "loss": 0.6733694076538086, "step": 30580 }, { "epoch": 0.1818333125286065, "grad_norm": 1.4140783548355103, "learning_rate": 0.00012121656429562116, "loss": 0.6479113101959229, "step": 30590 }, { "epoch": 0.1818927546052749, "grad_norm": 1.53532874584198, "learning_rate": 0.00012125619179710719, "loss": 0.7000610828399658, "step": 30600 }, { "epoch": 0.1819521966819433, "grad_norm": 1.657346487045288, "learning_rate": 0.00012129581929859324, "loss": 0.6265616416931152, "step": 30610 }, { "epoch": 0.18201163875861168, "grad_norm": 1.541685700416565, "learning_rate": 0.00012133544680007926, "loss": 0.6823726654052734, "step": 30620 }, { "epoch": 0.18207108083528006, "grad_norm": 1.3474805355072021, "learning_rate": 0.00012137507430156529, "loss": 0.6343745231628418, "step": 30630 }, { "epoch": 0.18213052291194845, "grad_norm": 1.581547737121582, "learning_rate": 0.00012141470180305133, "loss": 0.6622182846069335, "step": 30640 }, { "epoch": 0.18218996498861684, "grad_norm": 1.538087248802185, "learning_rate": 0.00012145432930453735, "loss": 0.7105870723724366, "step": 30650 }, { "epoch": 0.18224940706528522, "grad_norm": 1.7692736387252808, "learning_rate": 0.00012149395680602338, "loss": 0.7276561737060547, "step": 30660 }, { "epoch": 0.1823088491419536, "grad_norm": 1.5725144147872925, "learning_rate": 0.0001215335843075094, "loss": 0.6388077735900879, "step": 30670 }, { "epoch": 0.18236829121862203, "grad_norm": 1.6946765184402466, "learning_rate": 0.00012157321180899546, "loss": 0.6282460212707519, "step": 30680 }, { "epoch": 0.1824277332952904, "grad_norm": 1.541175127029419, "learning_rate": 0.00012161283931048148, "loss": 0.6971580505371093, "step": 30690 }, { "epoch": 0.1824871753719588, "grad_norm": 1.6069940328598022, "learning_rate": 0.00012165246681196752, "loss": 0.6588431835174561, "step": 30700 }, { "epoch": 0.18254661744862719, "grad_norm": 1.506313681602478, "learning_rate": 0.00012169209431345354, "loss": 0.6070270538330078, "step": 30710 }, { "epoch": 0.18260605952529557, "grad_norm": 1.3509786128997803, "learning_rate": 0.00012173172181493957, "loss": 0.6374363899230957, "step": 30720 }, { "epoch": 0.18266550160196396, "grad_norm": 1.2609491348266602, "learning_rate": 0.0001217713493164256, "loss": 0.6466045379638672, "step": 30730 }, { "epoch": 0.18272494367863235, "grad_norm": 1.575838565826416, "learning_rate": 0.00012181097681791162, "loss": 0.7036982536315918, "step": 30740 }, { "epoch": 0.18278438575530076, "grad_norm": 1.6373209953308105, "learning_rate": 0.00012185060431939767, "loss": 0.6831032752990722, "step": 30750 }, { "epoch": 0.18284382783196915, "grad_norm": 1.730141043663025, "learning_rate": 0.00012189023182088371, "loss": 0.7310273170471191, "step": 30760 }, { "epoch": 0.18290326990863753, "grad_norm": 1.8777525424957275, "learning_rate": 0.00012192985932236974, "loss": 0.6996362209320068, "step": 30770 }, { "epoch": 0.18296271198530592, "grad_norm": 1.476985216140747, "learning_rate": 0.00012196948682385576, "loss": 0.6901968479156494, "step": 30780 }, { "epoch": 0.1830221540619743, "grad_norm": 1.3182793855667114, "learning_rate": 0.00012200911432534179, "loss": 0.7344383716583252, "step": 30790 }, { "epoch": 0.1830815961386427, "grad_norm": 1.527045726776123, "learning_rate": 0.00012204874182682781, "loss": 0.6788651466369628, "step": 30800 }, { "epoch": 0.18314103821531108, "grad_norm": 1.5453071594238281, "learning_rate": 0.00012208836932831385, "loss": 0.6798878669738769, "step": 30810 }, { "epoch": 0.18320048029197947, "grad_norm": 1.215171217918396, "learning_rate": 0.0001221279968297999, "loss": 0.6752212524414063, "step": 30820 }, { "epoch": 0.18325992236864788, "grad_norm": 1.5058640241622925, "learning_rate": 0.00012216762433128593, "loss": 0.6757655620574952, "step": 30830 }, { "epoch": 0.18331936444531627, "grad_norm": 1.5443779230117798, "learning_rate": 0.00012220725183277194, "loss": 0.6734638690948487, "step": 30840 }, { "epoch": 0.18337880652198466, "grad_norm": 1.8523571491241455, "learning_rate": 0.00012224687933425798, "loss": 0.6728116035461426, "step": 30850 }, { "epoch": 0.18343824859865304, "grad_norm": 1.5137048959732056, "learning_rate": 0.00012228650683574402, "loss": 0.6951900482177734, "step": 30860 }, { "epoch": 0.18349769067532143, "grad_norm": 1.2725822925567627, "learning_rate": 0.00012232613433723003, "loss": 0.6473577499389649, "step": 30870 }, { "epoch": 0.18355713275198982, "grad_norm": 1.585368275642395, "learning_rate": 0.00012236576183871607, "loss": 0.5972864627838135, "step": 30880 }, { "epoch": 0.1836165748286582, "grad_norm": 2.35489559173584, "learning_rate": 0.0001224053893402021, "loss": 0.6655355453491211, "step": 30890 }, { "epoch": 0.18367601690532662, "grad_norm": 1.706279993057251, "learning_rate": 0.00012244501684168814, "loss": 0.6381211757659913, "step": 30900 }, { "epoch": 0.183735458981995, "grad_norm": 1.5865325927734375, "learning_rate": 0.00012248464434317418, "loss": 0.723486852645874, "step": 30910 }, { "epoch": 0.1837949010586634, "grad_norm": 1.6282583475112915, "learning_rate": 0.0001225242718446602, "loss": 0.6991991996765137, "step": 30920 }, { "epoch": 0.18385434313533178, "grad_norm": 1.6415293216705322, "learning_rate": 0.00012256389934614623, "loss": 0.6978261947631836, "step": 30930 }, { "epoch": 0.18391378521200016, "grad_norm": 1.721173644065857, "learning_rate": 0.00012260352684763224, "loss": 0.6449216842651367, "step": 30940 }, { "epoch": 0.18397322728866855, "grad_norm": 1.4857115745544434, "learning_rate": 0.00012264315434911828, "loss": 0.671265983581543, "step": 30950 }, { "epoch": 0.18403266936533694, "grad_norm": 1.754980444908142, "learning_rate": 0.00012268278185060432, "loss": 0.626704740524292, "step": 30960 }, { "epoch": 0.18409211144200535, "grad_norm": 1.3893991708755493, "learning_rate": 0.00012272240935209036, "loss": 0.6687309265136718, "step": 30970 }, { "epoch": 0.18415155351867374, "grad_norm": 2.573361396789551, "learning_rate": 0.0001227620368535764, "loss": 0.6201773643493652, "step": 30980 }, { "epoch": 0.18421099559534213, "grad_norm": 1.5346230268478394, "learning_rate": 0.0001228016643550624, "loss": 0.6876473903656006, "step": 30990 }, { "epoch": 0.1842704376720105, "grad_norm": 1.6835806369781494, "learning_rate": 0.00012284129185654845, "loss": 0.6402092933654785, "step": 31000 }, { "epoch": 0.1843298797486789, "grad_norm": 1.4872157573699951, "learning_rate": 0.0001228809193580345, "loss": 0.6539370536804199, "step": 31010 }, { "epoch": 0.18438932182534729, "grad_norm": 1.9415377378463745, "learning_rate": 0.0001229205468595205, "loss": 0.6653793811798095, "step": 31020 }, { "epoch": 0.18444876390201567, "grad_norm": 1.2101753950119019, "learning_rate": 0.00012296017436100656, "loss": 0.6068943977355957, "step": 31030 }, { "epoch": 0.18450820597868406, "grad_norm": 1.753644585609436, "learning_rate": 0.00012299980186249258, "loss": 0.7022874832153321, "step": 31040 }, { "epoch": 0.18456764805535247, "grad_norm": 1.956419825553894, "learning_rate": 0.00012303942936397861, "loss": 0.6425631523132325, "step": 31050 }, { "epoch": 0.18462709013202086, "grad_norm": 1.58622407913208, "learning_rate": 0.00012307905686546463, "loss": 0.6264450073242187, "step": 31060 }, { "epoch": 0.18468653220868925, "grad_norm": 1.9124847650527954, "learning_rate": 0.00012311868436695067, "loss": 0.7475243091583252, "step": 31070 }, { "epoch": 0.18474597428535763, "grad_norm": 1.4739006757736206, "learning_rate": 0.0001231583118684367, "loss": 0.689294958114624, "step": 31080 }, { "epoch": 0.18480541636202602, "grad_norm": 1.1060527563095093, "learning_rate": 0.00012319793936992272, "loss": 0.7015924453735352, "step": 31090 }, { "epoch": 0.1848648584386944, "grad_norm": 1.4715969562530518, "learning_rate": 0.00012323756687140878, "loss": 0.6848660469055176, "step": 31100 }, { "epoch": 0.1849243005153628, "grad_norm": 1.6064784526824951, "learning_rate": 0.0001232771943728948, "loss": 0.6216695785522461, "step": 31110 }, { "epoch": 0.1849837425920312, "grad_norm": 1.4884237051010132, "learning_rate": 0.00012331682187438083, "loss": 0.6700490951538086, "step": 31120 }, { "epoch": 0.1850431846686996, "grad_norm": 1.9644215106964111, "learning_rate": 0.00012335644937586684, "loss": 0.663074541091919, "step": 31130 }, { "epoch": 0.18510262674536798, "grad_norm": 1.9532973766326904, "learning_rate": 0.00012339607687735288, "loss": 0.6909761905670166, "step": 31140 }, { "epoch": 0.18516206882203637, "grad_norm": 1.5555362701416016, "learning_rate": 0.00012343570437883892, "loss": 0.6409054279327393, "step": 31150 }, { "epoch": 0.18522151089870476, "grad_norm": 1.5157763957977295, "learning_rate": 0.00012347533188032493, "loss": 0.6418585777282715, "step": 31160 }, { "epoch": 0.18528095297537314, "grad_norm": 1.6726198196411133, "learning_rate": 0.000123514959381811, "loss": 0.6355489730834961, "step": 31170 }, { "epoch": 0.18534039505204153, "grad_norm": 1.3132035732269287, "learning_rate": 0.000123554586883297, "loss": 0.6834154605865479, "step": 31180 }, { "epoch": 0.18539983712870992, "grad_norm": 1.5343369245529175, "learning_rate": 0.00012359421438478305, "loss": 0.6849573135375977, "step": 31190 }, { "epoch": 0.18545927920537833, "grad_norm": 1.4166268110275269, "learning_rate": 0.00012363384188626909, "loss": 0.6876266956329345, "step": 31200 }, { "epoch": 0.18551872128204672, "grad_norm": 1.7576521635055542, "learning_rate": 0.0001236734693877551, "loss": 0.6589216232299805, "step": 31210 }, { "epoch": 0.1855781633587151, "grad_norm": 1.5480482578277588, "learning_rate": 0.00012371309688924114, "loss": 0.7672400951385498, "step": 31220 }, { "epoch": 0.1856376054353835, "grad_norm": 1.757014274597168, "learning_rate": 0.00012375272439072718, "loss": 0.6942944049835205, "step": 31230 }, { "epoch": 0.18569704751205188, "grad_norm": 2.11446475982666, "learning_rate": 0.00012379235189221321, "loss": 0.6829409599304199, "step": 31240 }, { "epoch": 0.18575648958872026, "grad_norm": 1.492130160331726, "learning_rate": 0.00012383197939369923, "loss": 0.6698146820068359, "step": 31250 }, { "epoch": 0.18581593166538865, "grad_norm": 1.7835018634796143, "learning_rate": 0.00012387160689518526, "loss": 0.7224652290344238, "step": 31260 }, { "epoch": 0.18587537374205707, "grad_norm": 1.8539055585861206, "learning_rate": 0.0001239112343966713, "loss": 0.6565216064453125, "step": 31270 }, { "epoch": 0.18593481581872545, "grad_norm": 1.2616881132125854, "learning_rate": 0.00012395086189815731, "loss": 0.6494094371795655, "step": 31280 }, { "epoch": 0.18599425789539384, "grad_norm": 1.315807580947876, "learning_rate": 0.00012399048939964335, "loss": 0.6406244277954102, "step": 31290 }, { "epoch": 0.18605369997206223, "grad_norm": 1.2492649555206299, "learning_rate": 0.0001240301169011294, "loss": 0.6437868118286133, "step": 31300 }, { "epoch": 0.1861131420487306, "grad_norm": 1.4524818658828735, "learning_rate": 0.00012406974440261543, "loss": 0.6820610046386719, "step": 31310 }, { "epoch": 0.186172584125399, "grad_norm": 1.698407530784607, "learning_rate": 0.00012410937190410147, "loss": 0.7090397834777832, "step": 31320 }, { "epoch": 0.18623202620206739, "grad_norm": 1.3024061918258667, "learning_rate": 0.00012414899940558748, "loss": 0.7570835590362549, "step": 31330 }, { "epoch": 0.18629146827873577, "grad_norm": 1.5183206796646118, "learning_rate": 0.00012418862690707352, "loss": 0.6726849555969239, "step": 31340 }, { "epoch": 0.1863509103554042, "grad_norm": 1.4795156717300415, "learning_rate": 0.00012422825440855953, "loss": 0.7037851333618164, "step": 31350 }, { "epoch": 0.18641035243207257, "grad_norm": 1.4970630407333374, "learning_rate": 0.00012426788191004557, "loss": 0.6747420787811279, "step": 31360 }, { "epoch": 0.18646979450874096, "grad_norm": 1.553102970123291, "learning_rate": 0.0001243075094115316, "loss": 0.7095033645629882, "step": 31370 }, { "epoch": 0.18652923658540935, "grad_norm": 1.3985514640808105, "learning_rate": 0.00012434713691301765, "loss": 0.5968671798706054, "step": 31380 }, { "epoch": 0.18658867866207773, "grad_norm": 1.071797490119934, "learning_rate": 0.00012438676441450369, "loss": 0.662658977508545, "step": 31390 }, { "epoch": 0.18664812073874612, "grad_norm": 1.3073376417160034, "learning_rate": 0.0001244263919159897, "loss": 0.6922569274902344, "step": 31400 }, { "epoch": 0.1867075628154145, "grad_norm": 1.5616008043289185, "learning_rate": 0.00012446601941747574, "loss": 0.6805954933166504, "step": 31410 }, { "epoch": 0.18676700489208292, "grad_norm": 1.4955450296401978, "learning_rate": 0.00012450564691896175, "loss": 0.6971171379089356, "step": 31420 }, { "epoch": 0.1868264469687513, "grad_norm": 1.5329645872116089, "learning_rate": 0.00012454527442044779, "loss": 0.7144129276275635, "step": 31430 }, { "epoch": 0.1868858890454197, "grad_norm": 1.62962806224823, "learning_rate": 0.00012458490192193385, "loss": 0.6872927188873291, "step": 31440 }, { "epoch": 0.18694533112208808, "grad_norm": 1.3554097414016724, "learning_rate": 0.00012462452942341986, "loss": 0.6357366561889648, "step": 31450 }, { "epoch": 0.18700477319875647, "grad_norm": 1.3998918533325195, "learning_rate": 0.0001246641569249059, "loss": 0.6228814601898194, "step": 31460 }, { "epoch": 0.18706421527542486, "grad_norm": 1.4071966409683228, "learning_rate": 0.0001247037844263919, "loss": 0.6306485176086426, "step": 31470 }, { "epoch": 0.18712365735209324, "grad_norm": 2.263540744781494, "learning_rate": 0.00012474341192787795, "loss": 0.6273569583892822, "step": 31480 }, { "epoch": 0.18718309942876166, "grad_norm": 2.0218164920806885, "learning_rate": 0.000124783039429364, "loss": 0.6590466976165772, "step": 31490 }, { "epoch": 0.18724254150543004, "grad_norm": 1.5520285367965698, "learning_rate": 0.00012482266693085, "loss": 0.704296350479126, "step": 31500 }, { "epoch": 0.18730198358209843, "grad_norm": 1.6632353067398071, "learning_rate": 0.00012486229443233607, "loss": 0.6349076271057129, "step": 31510 }, { "epoch": 0.18736142565876682, "grad_norm": 1.6588515043258667, "learning_rate": 0.00012490192193382208, "loss": 0.6803860664367676, "step": 31520 }, { "epoch": 0.1874208677354352, "grad_norm": 1.615531086921692, "learning_rate": 0.00012494154943530812, "loss": 0.6672558784484863, "step": 31530 }, { "epoch": 0.1874803098121036, "grad_norm": 1.5602571964263916, "learning_rate": 0.00012498117693679413, "loss": 0.6823396682739258, "step": 31540 }, { "epoch": 0.18753975188877198, "grad_norm": 1.4351370334625244, "learning_rate": 0.00012502080443828017, "loss": 0.6638879776000977, "step": 31550 }, { "epoch": 0.18759919396544036, "grad_norm": 1.3793057203292847, "learning_rate": 0.0001250604319397662, "loss": 0.6909931182861329, "step": 31560 }, { "epoch": 0.18765863604210878, "grad_norm": 1.55753493309021, "learning_rate": 0.00012510005944125222, "loss": 0.6348968505859375, "step": 31570 }, { "epoch": 0.18771807811877717, "grad_norm": 1.7119802236557007, "learning_rate": 0.00012513968694273828, "loss": 0.6710705757141113, "step": 31580 }, { "epoch": 0.18777752019544555, "grad_norm": 1.2961745262145996, "learning_rate": 0.0001251793144442243, "loss": 0.7244355201721191, "step": 31590 }, { "epoch": 0.18783696227211394, "grad_norm": 1.4951363801956177, "learning_rate": 0.00012521894194571033, "loss": 0.610067081451416, "step": 31600 }, { "epoch": 0.18789640434878233, "grad_norm": 1.475677251815796, "learning_rate": 0.00012525856944719637, "loss": 0.6440874099731445, "step": 31610 }, { "epoch": 0.1879558464254507, "grad_norm": 1.3111534118652344, "learning_rate": 0.00012529819694868238, "loss": 0.6724244117736816, "step": 31620 }, { "epoch": 0.1880152885021191, "grad_norm": 1.312006950378418, "learning_rate": 0.00012533782445016842, "loss": 0.6250114917755127, "step": 31630 }, { "epoch": 0.1880747305787875, "grad_norm": 1.8249754905700684, "learning_rate": 0.00012537745195165443, "loss": 0.7372100353240967, "step": 31640 }, { "epoch": 0.1881341726554559, "grad_norm": 1.5048470497131348, "learning_rate": 0.0001254170794531405, "loss": 0.7245893478393555, "step": 31650 }, { "epoch": 0.1881936147321243, "grad_norm": 1.6791268587112427, "learning_rate": 0.0001254567069546265, "loss": 0.6454702854156494, "step": 31660 }, { "epoch": 0.18825305680879267, "grad_norm": 1.2571567296981812, "learning_rate": 0.00012549633445611255, "loss": 0.6614981651306152, "step": 31670 }, { "epoch": 0.18831249888546106, "grad_norm": 1.668666124343872, "learning_rate": 0.0001255359619575986, "loss": 0.6725986480712891, "step": 31680 }, { "epoch": 0.18837194096212945, "grad_norm": 1.6617287397384644, "learning_rate": 0.0001255755894590846, "loss": 0.6562388420104981, "step": 31690 }, { "epoch": 0.18843138303879783, "grad_norm": 1.2989219427108765, "learning_rate": 0.00012561521696057064, "loss": 0.6842564582824707, "step": 31700 }, { "epoch": 0.18849082511546622, "grad_norm": 1.6888453960418701, "learning_rate": 0.00012565484446205665, "loss": 0.671230411529541, "step": 31710 }, { "epoch": 0.18855026719213464, "grad_norm": 1.7395200729370117, "learning_rate": 0.00012569447196354272, "loss": 0.6707943916320801, "step": 31720 }, { "epoch": 0.18860970926880302, "grad_norm": 1.9132813215255737, "learning_rate": 0.00012573409946502876, "loss": 0.6520673751831054, "step": 31730 }, { "epoch": 0.1886691513454714, "grad_norm": 1.929099678993225, "learning_rate": 0.00012577372696651477, "loss": 0.6857344627380371, "step": 31740 }, { "epoch": 0.1887285934221398, "grad_norm": 1.410468578338623, "learning_rate": 0.0001258133544680008, "loss": 0.6632529258728027, "step": 31750 }, { "epoch": 0.18878803549880818, "grad_norm": 1.4327809810638428, "learning_rate": 0.00012585298196948682, "loss": 0.6780589103698731, "step": 31760 }, { "epoch": 0.18884747757547657, "grad_norm": 1.375320315361023, "learning_rate": 0.00012589260947097286, "loss": 0.676021671295166, "step": 31770 }, { "epoch": 0.18890691965214496, "grad_norm": 1.257367491722107, "learning_rate": 0.0001259322369724589, "loss": 0.6093991756439209, "step": 31780 }, { "epoch": 0.18896636172881337, "grad_norm": 1.4787626266479492, "learning_rate": 0.00012597186447394493, "loss": 0.703392505645752, "step": 31790 }, { "epoch": 0.18902580380548176, "grad_norm": 1.6456414461135864, "learning_rate": 0.00012601149197543097, "loss": 0.6230351448059082, "step": 31800 }, { "epoch": 0.18908524588215014, "grad_norm": 1.1836198568344116, "learning_rate": 0.00012605111947691698, "loss": 0.6162423133850098, "step": 31810 }, { "epoch": 0.18914468795881853, "grad_norm": 1.7448393106460571, "learning_rate": 0.00012609074697840302, "loss": 0.6705265998840332, "step": 31820 }, { "epoch": 0.18920413003548692, "grad_norm": 1.7937817573547363, "learning_rate": 0.00012613037447988903, "loss": 0.6667966365814209, "step": 31830 }, { "epoch": 0.1892635721121553, "grad_norm": 1.782576560974121, "learning_rate": 0.00012617000198137507, "loss": 0.6493927955627441, "step": 31840 }, { "epoch": 0.1893230141888237, "grad_norm": 1.2375386953353882, "learning_rate": 0.0001262096294828611, "loss": 0.6512017250061035, "step": 31850 }, { "epoch": 0.1893824562654921, "grad_norm": 1.369104266166687, "learning_rate": 0.00012624925698434715, "loss": 0.63657546043396, "step": 31860 }, { "epoch": 0.1894418983421605, "grad_norm": 1.6587496995925903, "learning_rate": 0.0001262888844858332, "loss": 0.6331612586975097, "step": 31870 }, { "epoch": 0.18950134041882888, "grad_norm": 1.606520652770996, "learning_rate": 0.0001263285119873192, "loss": 0.6716269969940185, "step": 31880 }, { "epoch": 0.18956078249549727, "grad_norm": 1.637307047843933, "learning_rate": 0.00012636813948880524, "loss": 0.6900959491729737, "step": 31890 }, { "epoch": 0.18962022457216565, "grad_norm": 1.4560320377349854, "learning_rate": 0.00012640776699029128, "loss": 0.6554590225219726, "step": 31900 }, { "epoch": 0.18967966664883404, "grad_norm": 1.187612533569336, "learning_rate": 0.0001264473944917773, "loss": 0.7304558277130127, "step": 31910 }, { "epoch": 0.18973910872550243, "grad_norm": 1.339938998222351, "learning_rate": 0.00012648702199326333, "loss": 0.6602528095245361, "step": 31920 }, { "epoch": 0.1897985508021708, "grad_norm": 1.4978611469268799, "learning_rate": 0.00012652664949474937, "loss": 0.7174296379089355, "step": 31930 }, { "epoch": 0.18985799287883923, "grad_norm": 2.1510794162750244, "learning_rate": 0.0001265662769962354, "loss": 0.6842199325561523, "step": 31940 }, { "epoch": 0.1899174349555076, "grad_norm": 1.1719039678573608, "learning_rate": 0.00012660590449772142, "loss": 0.6343956470489502, "step": 31950 }, { "epoch": 0.189976877032176, "grad_norm": 1.1738920211791992, "learning_rate": 0.00012664553199920745, "loss": 0.5807811737060546, "step": 31960 }, { "epoch": 0.1900363191088444, "grad_norm": 1.5630358457565308, "learning_rate": 0.0001266851595006935, "loss": 0.6653204917907715, "step": 31970 }, { "epoch": 0.19009576118551277, "grad_norm": 1.6120089292526245, "learning_rate": 0.0001267247870021795, "loss": 0.6607693672180176, "step": 31980 }, { "epoch": 0.19015520326218116, "grad_norm": 1.5826706886291504, "learning_rate": 0.00012676441450366554, "loss": 0.6251534461975098, "step": 31990 }, { "epoch": 0.19021464533884955, "grad_norm": 1.721191167831421, "learning_rate": 0.00012680404200515158, "loss": 0.693143367767334, "step": 32000 }, { "epoch": 0.19027408741551796, "grad_norm": 1.4950759410858154, "learning_rate": 0.00012684366950663762, "loss": 0.7010100364685059, "step": 32010 }, { "epoch": 0.19033352949218635, "grad_norm": 1.793123722076416, "learning_rate": 0.00012688329700812366, "loss": 0.7133652687072753, "step": 32020 }, { "epoch": 0.19039297156885474, "grad_norm": 1.8656221628189087, "learning_rate": 0.00012692292450960967, "loss": 0.6490038871765137, "step": 32030 }, { "epoch": 0.19045241364552312, "grad_norm": 1.5068697929382324, "learning_rate": 0.0001269625520110957, "loss": 0.6209395408630372, "step": 32040 }, { "epoch": 0.1905118557221915, "grad_norm": 1.4476910829544067, "learning_rate": 0.00012700217951258172, "loss": 0.6915627956390381, "step": 32050 }, { "epoch": 0.1905712977988599, "grad_norm": 1.6887996196746826, "learning_rate": 0.00012704180701406776, "loss": 0.651613998413086, "step": 32060 }, { "epoch": 0.19063073987552828, "grad_norm": 1.9012748003005981, "learning_rate": 0.0001270814345155538, "loss": 0.579593563079834, "step": 32070 }, { "epoch": 0.19069018195219667, "grad_norm": 1.4442397356033325, "learning_rate": 0.00012712106201703984, "loss": 0.6649312019348145, "step": 32080 }, { "epoch": 0.19074962402886508, "grad_norm": 1.306061029434204, "learning_rate": 0.00012716068951852588, "loss": 0.6620803833007812, "step": 32090 }, { "epoch": 0.19080906610553347, "grad_norm": 1.2580682039260864, "learning_rate": 0.0001272003170200119, "loss": 0.6969296932220459, "step": 32100 }, { "epoch": 0.19086850818220186, "grad_norm": 1.345077633857727, "learning_rate": 0.00012723994452149793, "loss": 0.7244478702545166, "step": 32110 }, { "epoch": 0.19092795025887024, "grad_norm": 1.3731203079223633, "learning_rate": 0.00012727957202298394, "loss": 0.6701080799102783, "step": 32120 }, { "epoch": 0.19098739233553863, "grad_norm": 1.6346877813339233, "learning_rate": 0.00012731919952446998, "loss": 0.6913780212402344, "step": 32130 }, { "epoch": 0.19104683441220702, "grad_norm": 1.6746773719787598, "learning_rate": 0.00012735882702595604, "loss": 0.6363065719604493, "step": 32140 }, { "epoch": 0.1911062764888754, "grad_norm": 1.4926135540008545, "learning_rate": 0.00012739845452744205, "loss": 0.6683358192443848, "step": 32150 }, { "epoch": 0.19116571856554382, "grad_norm": 1.5599020719528198, "learning_rate": 0.0001274380820289281, "loss": 0.6373640537261963, "step": 32160 }, { "epoch": 0.1912251606422122, "grad_norm": 1.4517452716827393, "learning_rate": 0.0001274777095304141, "loss": 0.6128240585327148, "step": 32170 }, { "epoch": 0.1912846027188806, "grad_norm": 1.2208476066589355, "learning_rate": 0.00012751733703190014, "loss": 0.6250836372375488, "step": 32180 }, { "epoch": 0.19134404479554898, "grad_norm": 1.476422667503357, "learning_rate": 0.00012755696453338618, "loss": 0.7184345245361328, "step": 32190 }, { "epoch": 0.19140348687221737, "grad_norm": 1.293984055519104, "learning_rate": 0.0001275965920348722, "loss": 0.6720053672790527, "step": 32200 }, { "epoch": 0.19146292894888575, "grad_norm": 1.6812947988510132, "learning_rate": 0.00012763621953635826, "loss": 0.7036820411682129, "step": 32210 }, { "epoch": 0.19152237102555414, "grad_norm": 1.7328381538391113, "learning_rate": 0.00012767584703784427, "loss": 0.7043734550476074, "step": 32220 }, { "epoch": 0.19158181310222253, "grad_norm": 1.4034706354141235, "learning_rate": 0.0001277154745393303, "loss": 0.6509029865264893, "step": 32230 }, { "epoch": 0.19164125517889094, "grad_norm": 1.3981724977493286, "learning_rate": 0.00012775510204081632, "loss": 0.6670558452606201, "step": 32240 }, { "epoch": 0.19170069725555933, "grad_norm": 1.537173867225647, "learning_rate": 0.00012779472954230236, "loss": 0.6471818447113037, "step": 32250 }, { "epoch": 0.1917601393322277, "grad_norm": 1.5749467611312866, "learning_rate": 0.0001278343570437884, "loss": 0.6851375579833985, "step": 32260 }, { "epoch": 0.1918195814088961, "grad_norm": 1.5833148956298828, "learning_rate": 0.0001278739845452744, "loss": 0.650082778930664, "step": 32270 }, { "epoch": 0.1918790234855645, "grad_norm": 1.9387445449829102, "learning_rate": 0.00012791361204676047, "loss": 0.7364837646484375, "step": 32280 }, { "epoch": 0.19193846556223287, "grad_norm": 1.3949118852615356, "learning_rate": 0.0001279532395482465, "loss": 0.6294162750244141, "step": 32290 }, { "epoch": 0.19199790763890126, "grad_norm": 1.5249778032302856, "learning_rate": 0.00012799286704973253, "loss": 0.7166201591491699, "step": 32300 }, { "epoch": 0.19205734971556968, "grad_norm": 1.493222713470459, "learning_rate": 0.00012803249455121856, "loss": 0.6357817649841309, "step": 32310 }, { "epoch": 0.19211679179223806, "grad_norm": 2.110262870788574, "learning_rate": 0.00012807212205270458, "loss": 0.7510412216186524, "step": 32320 }, { "epoch": 0.19217623386890645, "grad_norm": 1.2206252813339233, "learning_rate": 0.00012811174955419061, "loss": 0.6591828346252442, "step": 32330 }, { "epoch": 0.19223567594557484, "grad_norm": 1.4105548858642578, "learning_rate": 0.00012815137705567663, "loss": 0.6534120559692382, "step": 32340 }, { "epoch": 0.19229511802224322, "grad_norm": 1.3499860763549805, "learning_rate": 0.0001281910045571627, "loss": 0.6347020149230957, "step": 32350 }, { "epoch": 0.1923545600989116, "grad_norm": 1.6608728170394897, "learning_rate": 0.0001282306320586487, "loss": 0.6798591136932373, "step": 32360 }, { "epoch": 0.19241400217558, "grad_norm": 1.3861925601959229, "learning_rate": 0.00012827025956013474, "loss": 0.7344057083129882, "step": 32370 }, { "epoch": 0.1924734442522484, "grad_norm": 1.3919072151184082, "learning_rate": 0.00012830988706162078, "loss": 0.6283857822418213, "step": 32380 }, { "epoch": 0.1925328863289168, "grad_norm": 1.5640603303909302, "learning_rate": 0.0001283495145631068, "loss": 0.6662880897521972, "step": 32390 }, { "epoch": 0.19259232840558518, "grad_norm": 1.6500911712646484, "learning_rate": 0.00012838914206459283, "loss": 0.664217758178711, "step": 32400 }, { "epoch": 0.19265177048225357, "grad_norm": 1.5790356397628784, "learning_rate": 0.00012842876956607884, "loss": 0.66685471534729, "step": 32410 }, { "epoch": 0.19271121255892196, "grad_norm": 1.6524386405944824, "learning_rate": 0.0001284683970675649, "loss": 0.6899738311767578, "step": 32420 }, { "epoch": 0.19277065463559034, "grad_norm": 1.3656795024871826, "learning_rate": 0.00012850802456905095, "loss": 0.6816770553588867, "step": 32430 }, { "epoch": 0.19283009671225873, "grad_norm": 1.4976707696914673, "learning_rate": 0.00012854765207053696, "loss": 0.7080150604248047, "step": 32440 }, { "epoch": 0.19288953878892712, "grad_norm": 1.5222114324569702, "learning_rate": 0.000128587279572023, "loss": 0.68492431640625, "step": 32450 }, { "epoch": 0.19294898086559553, "grad_norm": 1.6767497062683105, "learning_rate": 0.000128626907073509, "loss": 0.7704771041870118, "step": 32460 }, { "epoch": 0.19300842294226392, "grad_norm": 1.5815995931625366, "learning_rate": 0.00012866653457499505, "loss": 0.6887946128845215, "step": 32470 }, { "epoch": 0.1930678650189323, "grad_norm": 1.5945687294006348, "learning_rate": 0.00012870616207648109, "loss": 0.6950507164001465, "step": 32480 }, { "epoch": 0.1931273070956007, "grad_norm": 1.563644289970398, "learning_rate": 0.00012874578957796712, "loss": 0.6723613262176513, "step": 32490 }, { "epoch": 0.19318674917226908, "grad_norm": 1.6650910377502441, "learning_rate": 0.00012878541707945316, "loss": 0.6510299205780029, "step": 32500 }, { "epoch": 0.19324619124893747, "grad_norm": 1.3540023565292358, "learning_rate": 0.00012882504458093917, "loss": 0.6723286628723144, "step": 32510 }, { "epoch": 0.19330563332560585, "grad_norm": 1.785231351852417, "learning_rate": 0.0001288646720824252, "loss": 0.6792725563049317, "step": 32520 }, { "epoch": 0.19336507540227427, "grad_norm": 1.8860595226287842, "learning_rate": 0.00012890429958391122, "loss": 0.6455717086791992, "step": 32530 }, { "epoch": 0.19342451747894265, "grad_norm": 2.04111385345459, "learning_rate": 0.00012894392708539726, "loss": 0.6572193145751953, "step": 32540 }, { "epoch": 0.19348395955561104, "grad_norm": 1.2355022430419922, "learning_rate": 0.0001289835545868833, "loss": 0.5907163619995117, "step": 32550 }, { "epoch": 0.19354340163227943, "grad_norm": 1.4877018928527832, "learning_rate": 0.00012902318208836934, "loss": 0.662333345413208, "step": 32560 }, { "epoch": 0.1936028437089478, "grad_norm": 1.34009850025177, "learning_rate": 0.00012906280958985538, "loss": 0.6965825080871582, "step": 32570 }, { "epoch": 0.1936622857856162, "grad_norm": 1.4152101278305054, "learning_rate": 0.0001291024370913414, "loss": 0.6895664691925049, "step": 32580 }, { "epoch": 0.1937217278622846, "grad_norm": 1.8221768140792847, "learning_rate": 0.00012914206459282743, "loss": 0.6718737125396729, "step": 32590 }, { "epoch": 0.19378116993895297, "grad_norm": 1.5450814962387085, "learning_rate": 0.00012918169209431347, "loss": 0.6952317237854004, "step": 32600 }, { "epoch": 0.1938406120156214, "grad_norm": 1.3633407354354858, "learning_rate": 0.00012922131959579948, "loss": 0.6525407791137695, "step": 32610 }, { "epoch": 0.19390005409228978, "grad_norm": 1.5691019296646118, "learning_rate": 0.00012926094709728552, "loss": 0.658781623840332, "step": 32620 }, { "epoch": 0.19395949616895816, "grad_norm": 1.6146191358566284, "learning_rate": 0.00012930057459877156, "loss": 0.710045337677002, "step": 32630 }, { "epoch": 0.19401893824562655, "grad_norm": 1.460707426071167, "learning_rate": 0.0001293402021002576, "loss": 0.6925318241119385, "step": 32640 }, { "epoch": 0.19407838032229494, "grad_norm": 2.231177568435669, "learning_rate": 0.0001293798296017436, "loss": 0.7075016021728515, "step": 32650 }, { "epoch": 0.19413782239896332, "grad_norm": 1.4972095489501953, "learning_rate": 0.00012941945710322965, "loss": 0.6784323692321778, "step": 32660 }, { "epoch": 0.1941972644756317, "grad_norm": 1.902004599571228, "learning_rate": 0.00012945908460471568, "loss": 0.6535993576049804, "step": 32670 }, { "epoch": 0.19425670655230012, "grad_norm": 1.5970659255981445, "learning_rate": 0.0001294987121062017, "loss": 0.6872962951660156, "step": 32680 }, { "epoch": 0.1943161486289685, "grad_norm": 1.180930256843567, "learning_rate": 0.00012953833960768773, "loss": 0.6608198642730713, "step": 32690 }, { "epoch": 0.1943755907056369, "grad_norm": 1.3480298519134521, "learning_rate": 0.00012957796710917377, "loss": 0.6680614471435546, "step": 32700 }, { "epoch": 0.19443503278230528, "grad_norm": 1.546238660812378, "learning_rate": 0.0001296175946106598, "loss": 0.6098106384277344, "step": 32710 }, { "epoch": 0.19449447485897367, "grad_norm": 1.5242222547531128, "learning_rate": 0.00012965722211214585, "loss": 0.6056036472320556, "step": 32720 }, { "epoch": 0.19455391693564206, "grad_norm": 1.7998641729354858, "learning_rate": 0.00012969684961363186, "loss": 0.7262217044830322, "step": 32730 }, { "epoch": 0.19461335901231044, "grad_norm": 1.533828616142273, "learning_rate": 0.0001297364771151179, "loss": 0.6730599403381348, "step": 32740 }, { "epoch": 0.19467280108897883, "grad_norm": 1.3505030870437622, "learning_rate": 0.0001297761046166039, "loss": 0.7212818622589111, "step": 32750 }, { "epoch": 0.19473224316564725, "grad_norm": 1.6297216415405273, "learning_rate": 0.00012981573211808995, "loss": 0.6247133255004883, "step": 32760 }, { "epoch": 0.19479168524231563, "grad_norm": 1.503118872642517, "learning_rate": 0.000129855359619576, "loss": 0.6508925437927247, "step": 32770 }, { "epoch": 0.19485112731898402, "grad_norm": 1.708880066871643, "learning_rate": 0.00012989498712106203, "loss": 0.6973659992218018, "step": 32780 }, { "epoch": 0.1949105693956524, "grad_norm": 1.4388872385025024, "learning_rate": 0.00012993461462254807, "loss": 0.7162645339965821, "step": 32790 }, { "epoch": 0.1949700114723208, "grad_norm": 1.6549255847930908, "learning_rate": 0.00012997424212403408, "loss": 0.724808931350708, "step": 32800 }, { "epoch": 0.19502945354898918, "grad_norm": 1.6299574375152588, "learning_rate": 0.00013001386962552012, "loss": 0.5907262802124024, "step": 32810 }, { "epoch": 0.19508889562565757, "grad_norm": 1.6002010107040405, "learning_rate": 0.00013005349712700613, "loss": 0.646359920501709, "step": 32820 }, { "epoch": 0.19514833770232598, "grad_norm": 1.5498530864715576, "learning_rate": 0.00013009312462849217, "loss": 0.633427906036377, "step": 32830 }, { "epoch": 0.19520777977899437, "grad_norm": 1.3331323862075806, "learning_rate": 0.0001301327521299782, "loss": 0.6470742225646973, "step": 32840 }, { "epoch": 0.19526722185566275, "grad_norm": 1.4137986898422241, "learning_rate": 0.00013017237963146424, "loss": 0.6679174423217773, "step": 32850 }, { "epoch": 0.19532666393233114, "grad_norm": 1.3271467685699463, "learning_rate": 0.00013021200713295028, "loss": 0.6489577770233155, "step": 32860 }, { "epoch": 0.19538610600899953, "grad_norm": 1.7705113887786865, "learning_rate": 0.0001302516346344363, "loss": 0.7282005310058594, "step": 32870 }, { "epoch": 0.19544554808566791, "grad_norm": 1.7249720096588135, "learning_rate": 0.00013029126213592233, "loss": 0.6569888591766357, "step": 32880 }, { "epoch": 0.1955049901623363, "grad_norm": 1.7294154167175293, "learning_rate": 0.00013033088963740837, "loss": 0.6812602519989014, "step": 32890 }, { "epoch": 0.19556443223900472, "grad_norm": 1.7830182313919067, "learning_rate": 0.00013037051713889438, "loss": 0.6513143539428711, "step": 32900 }, { "epoch": 0.1956238743156731, "grad_norm": 1.5694174766540527, "learning_rate": 0.00013041014464038045, "loss": 0.6771435737609863, "step": 32910 }, { "epoch": 0.1956833163923415, "grad_norm": 1.9405606985092163, "learning_rate": 0.00013044977214186646, "loss": 0.7978428363800049, "step": 32920 }, { "epoch": 0.19574275846900988, "grad_norm": 1.8768041133880615, "learning_rate": 0.0001304893996433525, "loss": 0.7129260063171386, "step": 32930 }, { "epoch": 0.19580220054567826, "grad_norm": 2.036137342453003, "learning_rate": 0.0001305290271448385, "loss": 0.6604759216308593, "step": 32940 }, { "epoch": 0.19586164262234665, "grad_norm": 1.4048458337783813, "learning_rate": 0.00013056865464632455, "loss": 0.6296424865722656, "step": 32950 }, { "epoch": 0.19592108469901504, "grad_norm": 2.0644166469573975, "learning_rate": 0.0001306082821478106, "loss": 0.6968323707580566, "step": 32960 }, { "epoch": 0.19598052677568342, "grad_norm": 1.6749629974365234, "learning_rate": 0.0001306479096492966, "loss": 0.6707577228546142, "step": 32970 }, { "epoch": 0.19603996885235184, "grad_norm": 1.421578288078308, "learning_rate": 0.00013068753715078267, "loss": 0.6783321380615235, "step": 32980 }, { "epoch": 0.19609941092902022, "grad_norm": 1.6199911832809448, "learning_rate": 0.00013072716465226868, "loss": 0.7075898170471191, "step": 32990 }, { "epoch": 0.1961588530056886, "grad_norm": 1.5710794925689697, "learning_rate": 0.00013076679215375472, "loss": 0.6331979274749756, "step": 33000 }, { "epoch": 0.196218295082357, "grad_norm": 1.8834600448608398, "learning_rate": 0.00013080641965524075, "loss": 0.6736392974853516, "step": 33010 }, { "epoch": 0.19627773715902538, "grad_norm": 1.9674683809280396, "learning_rate": 0.00013084604715672677, "loss": 0.7243889808654785, "step": 33020 }, { "epoch": 0.19633717923569377, "grad_norm": 1.4712154865264893, "learning_rate": 0.0001308856746582128, "loss": 0.6792673587799072, "step": 33030 }, { "epoch": 0.19639662131236216, "grad_norm": 1.45130455493927, "learning_rate": 0.00013092530215969884, "loss": 0.670084285736084, "step": 33040 }, { "epoch": 0.19645606338903057, "grad_norm": 1.5866175889968872, "learning_rate": 0.00013096492966118488, "loss": 0.7301108360290527, "step": 33050 }, { "epoch": 0.19651550546569896, "grad_norm": 1.898620367050171, "learning_rate": 0.0001310045571626709, "loss": 0.7256566524505615, "step": 33060 }, { "epoch": 0.19657494754236735, "grad_norm": 1.5160490274429321, "learning_rate": 0.00013104418466415693, "loss": 0.679743766784668, "step": 33070 }, { "epoch": 0.19663438961903573, "grad_norm": 1.5127975940704346, "learning_rate": 0.00013108381216564297, "loss": 0.6926057815551758, "step": 33080 }, { "epoch": 0.19669383169570412, "grad_norm": 1.446132779121399, "learning_rate": 0.00013112343966712898, "loss": 0.6554901123046875, "step": 33090 }, { "epoch": 0.1967532737723725, "grad_norm": 1.4563183784484863, "learning_rate": 0.00013116306716861502, "loss": 0.6572194576263428, "step": 33100 }, { "epoch": 0.1968127158490409, "grad_norm": 1.6044718027114868, "learning_rate": 0.00013120269467010106, "loss": 0.5930264472961426, "step": 33110 }, { "epoch": 0.19687215792570928, "grad_norm": 1.9028236865997314, "learning_rate": 0.0001312423221715871, "loss": 0.6767724990844727, "step": 33120 }, { "epoch": 0.1969316000023777, "grad_norm": 1.6937649250030518, "learning_rate": 0.0001312819496730731, "loss": 0.6842187881469727, "step": 33130 }, { "epoch": 0.19699104207904608, "grad_norm": 1.5966615676879883, "learning_rate": 0.00013132157717455915, "loss": 0.7389891624450684, "step": 33140 }, { "epoch": 0.19705048415571447, "grad_norm": 1.6822208166122437, "learning_rate": 0.0001313612046760452, "loss": 0.6866913318634034, "step": 33150 }, { "epoch": 0.19710992623238285, "grad_norm": 1.4468048810958862, "learning_rate": 0.0001314008321775312, "loss": 0.6757082939147949, "step": 33160 }, { "epoch": 0.19716936830905124, "grad_norm": 1.5699613094329834, "learning_rate": 0.00013144045967901724, "loss": 0.6600894927978516, "step": 33170 }, { "epoch": 0.19722881038571963, "grad_norm": 1.7559069395065308, "learning_rate": 0.00013148008718050328, "loss": 0.6959346294403076, "step": 33180 }, { "epoch": 0.19728825246238801, "grad_norm": 1.7287487983703613, "learning_rate": 0.00013151971468198931, "loss": 0.6835122108459473, "step": 33190 }, { "epoch": 0.19734769453905643, "grad_norm": 1.4906445741653442, "learning_rate": 0.00013155934218347535, "loss": 0.6941572189331054, "step": 33200 }, { "epoch": 0.19740713661572482, "grad_norm": 2.0005154609680176, "learning_rate": 0.00013159896968496137, "loss": 0.6365188598632813, "step": 33210 }, { "epoch": 0.1974665786923932, "grad_norm": 1.3284443616867065, "learning_rate": 0.0001316385971864474, "loss": 0.6719932079315185, "step": 33220 }, { "epoch": 0.1975260207690616, "grad_norm": 1.2969383001327515, "learning_rate": 0.00013167822468793342, "loss": 0.6866492748260498, "step": 33230 }, { "epoch": 0.19758546284572998, "grad_norm": 1.7413543462753296, "learning_rate": 0.00013171785218941945, "loss": 0.6688212871551513, "step": 33240 }, { "epoch": 0.19764490492239836, "grad_norm": 1.9483543634414673, "learning_rate": 0.0001317574796909055, "loss": 0.6638367652893067, "step": 33250 }, { "epoch": 0.19770434699906675, "grad_norm": 1.1820194721221924, "learning_rate": 0.00013179710719239153, "loss": 0.6402328014373779, "step": 33260 }, { "epoch": 0.19776378907573516, "grad_norm": 1.5250754356384277, "learning_rate": 0.00013183673469387757, "loss": 0.6593257904052734, "step": 33270 }, { "epoch": 0.19782323115240355, "grad_norm": 1.9685888290405273, "learning_rate": 0.00013187636219536358, "loss": 0.7113095760345459, "step": 33280 }, { "epoch": 0.19788267322907194, "grad_norm": 1.4306976795196533, "learning_rate": 0.00013191598969684962, "loss": 0.654411506652832, "step": 33290 }, { "epoch": 0.19794211530574032, "grad_norm": 1.73549222946167, "learning_rate": 0.00013195561719833566, "loss": 0.658540153503418, "step": 33300 }, { "epoch": 0.1980015573824087, "grad_norm": 1.4796758890151978, "learning_rate": 0.00013199524469982167, "loss": 0.6720176696777344, "step": 33310 }, { "epoch": 0.1980609994590771, "grad_norm": 1.4571468830108643, "learning_rate": 0.00013203487220130774, "loss": 0.6605660438537597, "step": 33320 }, { "epoch": 0.19812044153574548, "grad_norm": 1.7657127380371094, "learning_rate": 0.00013207449970279375, "loss": 0.6457975387573243, "step": 33330 }, { "epoch": 0.19817988361241387, "grad_norm": 1.5024056434631348, "learning_rate": 0.00013211412720427979, "loss": 0.6304069042205811, "step": 33340 }, { "epoch": 0.19823932568908229, "grad_norm": 1.5343292951583862, "learning_rate": 0.0001321537547057658, "loss": 0.6380528450012207, "step": 33350 }, { "epoch": 0.19829876776575067, "grad_norm": 1.6044282913208008, "learning_rate": 0.00013219338220725184, "loss": 0.6902829170227051, "step": 33360 }, { "epoch": 0.19835820984241906, "grad_norm": 1.663824200630188, "learning_rate": 0.00013223300970873788, "loss": 0.6152248382568359, "step": 33370 }, { "epoch": 0.19841765191908745, "grad_norm": 1.533509612083435, "learning_rate": 0.0001322726372102239, "loss": 0.6214929580688476, "step": 33380 }, { "epoch": 0.19847709399575583, "grad_norm": 1.4697010517120361, "learning_rate": 0.00013231226471170995, "loss": 0.679319190979004, "step": 33390 }, { "epoch": 0.19853653607242422, "grad_norm": 1.6221015453338623, "learning_rate": 0.00013235189221319596, "loss": 0.6414934635162354, "step": 33400 }, { "epoch": 0.1985959781490926, "grad_norm": 1.7220509052276611, "learning_rate": 0.000132391519714682, "loss": 0.6456231117248535, "step": 33410 }, { "epoch": 0.19865542022576102, "grad_norm": 1.52481210231781, "learning_rate": 0.00013243114721616804, "loss": 0.674609899520874, "step": 33420 }, { "epoch": 0.1987148623024294, "grad_norm": 1.4952375888824463, "learning_rate": 0.00013247077471765405, "loss": 0.6808967113494873, "step": 33430 }, { "epoch": 0.1987743043790978, "grad_norm": 1.387006402015686, "learning_rate": 0.0001325104022191401, "loss": 0.6621977806091308, "step": 33440 }, { "epoch": 0.19883374645576618, "grad_norm": 1.5897868871688843, "learning_rate": 0.0001325500297206261, "loss": 0.6682275772094727, "step": 33450 }, { "epoch": 0.19889318853243457, "grad_norm": 1.469743251800537, "learning_rate": 0.00013258965722211217, "loss": 0.6431571006774902, "step": 33460 }, { "epoch": 0.19895263060910295, "grad_norm": 1.2100169658660889, "learning_rate": 0.00013262928472359818, "loss": 0.687798023223877, "step": 33470 }, { "epoch": 0.19901207268577134, "grad_norm": 1.712225317955017, "learning_rate": 0.00013266891222508422, "loss": 0.6694517135620117, "step": 33480 }, { "epoch": 0.19907151476243973, "grad_norm": 1.6311873197555542, "learning_rate": 0.00013270853972657026, "loss": 0.670224666595459, "step": 33490 }, { "epoch": 0.19913095683910814, "grad_norm": 1.3590192794799805, "learning_rate": 0.00013274816722805627, "loss": 0.7249398231506348, "step": 33500 }, { "epoch": 0.19919039891577653, "grad_norm": 1.962059497833252, "learning_rate": 0.0001327877947295423, "loss": 0.7017580032348633, "step": 33510 }, { "epoch": 0.19924984099244492, "grad_norm": 1.744218111038208, "learning_rate": 0.00013282742223102832, "loss": 0.6714373111724854, "step": 33520 }, { "epoch": 0.1993092830691133, "grad_norm": 1.5624771118164062, "learning_rate": 0.00013286704973251439, "loss": 0.6730123519897461, "step": 33530 }, { "epoch": 0.1993687251457817, "grad_norm": 1.335839867591858, "learning_rate": 0.0001329066772340004, "loss": 0.6645246505737304, "step": 33540 }, { "epoch": 0.19942816722245008, "grad_norm": 1.7539507150650024, "learning_rate": 0.00013294630473548644, "loss": 0.701376485824585, "step": 33550 }, { "epoch": 0.19948760929911846, "grad_norm": 1.9473068714141846, "learning_rate": 0.00013298593223697247, "loss": 0.7045090675354004, "step": 33560 }, { "epoch": 0.19954705137578688, "grad_norm": 1.5223286151885986, "learning_rate": 0.00013302555973845849, "loss": 0.7023972511291504, "step": 33570 }, { "epoch": 0.19960649345245526, "grad_norm": 1.6016217470169067, "learning_rate": 0.00013306518723994452, "loss": 0.6704488754272461, "step": 33580 }, { "epoch": 0.19966593552912365, "grad_norm": 2.300490140914917, "learning_rate": 0.00013310481474143056, "loss": 0.7337589263916016, "step": 33590 }, { "epoch": 0.19972537760579204, "grad_norm": 1.4075297117233276, "learning_rate": 0.0001331444422429166, "loss": 0.6752371788024902, "step": 33600 }, { "epoch": 0.19978481968246042, "grad_norm": 1.2390156984329224, "learning_rate": 0.00013318406974440264, "loss": 0.657977294921875, "step": 33610 }, { "epoch": 0.1998442617591288, "grad_norm": 1.2205450534820557, "learning_rate": 0.00013322369724588865, "loss": 0.6717826843261718, "step": 33620 }, { "epoch": 0.1999037038357972, "grad_norm": 1.2987349033355713, "learning_rate": 0.0001332633247473747, "loss": 0.635239839553833, "step": 33630 }, { "epoch": 0.19996314591246558, "grad_norm": 1.4970897436141968, "learning_rate": 0.0001333029522488607, "loss": 0.6691913604736328, "step": 33640 }, { "epoch": 0.200022587989134, "grad_norm": 1.7000092267990112, "learning_rate": 0.00013334257975034674, "loss": 0.6537732601165771, "step": 33650 }, { "epoch": 0.20008203006580239, "grad_norm": 1.8658992052078247, "learning_rate": 0.00013338220725183278, "loss": 0.7355597019195557, "step": 33660 }, { "epoch": 0.20014147214247077, "grad_norm": 1.3546442985534668, "learning_rate": 0.00013342183475331882, "loss": 0.6634241104125976, "step": 33670 }, { "epoch": 0.20020091421913916, "grad_norm": 1.645703673362732, "learning_rate": 0.00013346146225480486, "loss": 0.6738658905029297, "step": 33680 }, { "epoch": 0.20026035629580755, "grad_norm": 1.3710646629333496, "learning_rate": 0.00013350108975629087, "loss": 0.6385476112365722, "step": 33690 }, { "epoch": 0.20031979837247593, "grad_norm": 1.4320727586746216, "learning_rate": 0.0001335407172577769, "loss": 0.6870837211608887, "step": 33700 }, { "epoch": 0.20037924044914432, "grad_norm": 1.805908203125, "learning_rate": 0.00013358034475926295, "loss": 0.6646661758422852, "step": 33710 }, { "epoch": 0.20043868252581273, "grad_norm": 1.3024979829788208, "learning_rate": 0.00013361997226074896, "loss": 0.6482019901275635, "step": 33720 }, { "epoch": 0.20049812460248112, "grad_norm": 1.443922519683838, "learning_rate": 0.000133659599762235, "loss": 0.7047224044799805, "step": 33730 }, { "epoch": 0.2005575666791495, "grad_norm": 1.3896386623382568, "learning_rate": 0.00013369922726372103, "loss": 0.6825218200683594, "step": 33740 }, { "epoch": 0.2006170087558179, "grad_norm": 1.4914110898971558, "learning_rate": 0.00013373885476520707, "loss": 0.6764864921569824, "step": 33750 }, { "epoch": 0.20067645083248628, "grad_norm": 1.299866795539856, "learning_rate": 0.00013377848226669308, "loss": 0.7063909530639648, "step": 33760 }, { "epoch": 0.20073589290915467, "grad_norm": 2.037445068359375, "learning_rate": 0.00013381810976817912, "loss": 0.6320880889892578, "step": 33770 }, { "epoch": 0.20079533498582305, "grad_norm": 1.3722152709960938, "learning_rate": 0.00013385773726966516, "loss": 0.6349240303039551, "step": 33780 }, { "epoch": 0.20085477706249147, "grad_norm": 1.5167373418807983, "learning_rate": 0.00013389736477115117, "loss": 0.6598892211914062, "step": 33790 }, { "epoch": 0.20091421913915986, "grad_norm": 1.5544060468673706, "learning_rate": 0.0001339369922726372, "loss": 0.6722335338592529, "step": 33800 }, { "epoch": 0.20097366121582824, "grad_norm": 1.6421186923980713, "learning_rate": 0.00013397661977412325, "loss": 0.711320161819458, "step": 33810 }, { "epoch": 0.20103310329249663, "grad_norm": 1.8498698472976685, "learning_rate": 0.0001340162472756093, "loss": 0.6497827529907226, "step": 33820 }, { "epoch": 0.20109254536916502, "grad_norm": 1.6692413091659546, "learning_rate": 0.0001340558747770953, "loss": 0.7035720825195313, "step": 33830 }, { "epoch": 0.2011519874458334, "grad_norm": 1.6532979011535645, "learning_rate": 0.00013409550227858134, "loss": 0.6548005104064941, "step": 33840 }, { "epoch": 0.2012114295225018, "grad_norm": 1.4104353189468384, "learning_rate": 0.00013413512978006738, "loss": 0.6027317047119141, "step": 33850 }, { "epoch": 0.20127087159917018, "grad_norm": 1.522038221359253, "learning_rate": 0.0001341747572815534, "loss": 0.6483329772949219, "step": 33860 }, { "epoch": 0.2013303136758386, "grad_norm": 1.5848579406738281, "learning_rate": 0.00013421438478303943, "loss": 0.7041259765625, "step": 33870 }, { "epoch": 0.20138975575250698, "grad_norm": 1.5717638731002808, "learning_rate": 0.00013425401228452547, "loss": 0.6223745346069336, "step": 33880 }, { "epoch": 0.20144919782917536, "grad_norm": 1.651597261428833, "learning_rate": 0.0001342936397860115, "loss": 0.6647310256958008, "step": 33890 }, { "epoch": 0.20150863990584375, "grad_norm": 1.454801082611084, "learning_rate": 0.00013433326728749754, "loss": 0.6938895225524903, "step": 33900 }, { "epoch": 0.20156808198251214, "grad_norm": 2.308678150177002, "learning_rate": 0.00013437289478898356, "loss": 0.6766459465026855, "step": 33910 }, { "epoch": 0.20162752405918052, "grad_norm": 1.5996088981628418, "learning_rate": 0.0001344125222904696, "loss": 0.636716079711914, "step": 33920 }, { "epoch": 0.2016869661358489, "grad_norm": 2.324023485183716, "learning_rate": 0.0001344521497919556, "loss": 0.6435635566711426, "step": 33930 }, { "epoch": 0.20174640821251733, "grad_norm": 1.4174270629882812, "learning_rate": 0.00013449177729344164, "loss": 0.6466828346252441, "step": 33940 }, { "epoch": 0.2018058502891857, "grad_norm": 1.3580846786499023, "learning_rate": 0.00013453140479492768, "loss": 0.6381455421447754, "step": 33950 }, { "epoch": 0.2018652923658541, "grad_norm": 1.7483084201812744, "learning_rate": 0.00013457103229641372, "loss": 0.7015160083770752, "step": 33960 }, { "epoch": 0.20192473444252249, "grad_norm": 1.5551018714904785, "learning_rate": 0.00013461065979789976, "loss": 0.7320729255676269, "step": 33970 }, { "epoch": 0.20198417651919087, "grad_norm": 1.7138431072235107, "learning_rate": 0.00013465028729938577, "loss": 0.6233397483825683, "step": 33980 }, { "epoch": 0.20204361859585926, "grad_norm": 1.2107585668563843, "learning_rate": 0.0001346899148008718, "loss": 0.5883656501770019, "step": 33990 }, { "epoch": 0.20210306067252765, "grad_norm": 1.539772391319275, "learning_rate": 0.00013472954230235785, "loss": 0.6279361248016357, "step": 34000 }, { "epoch": 0.20216250274919603, "grad_norm": 1.3757450580596924, "learning_rate": 0.00013476916980384386, "loss": 0.6530739784240722, "step": 34010 }, { "epoch": 0.20222194482586445, "grad_norm": 1.2074795961380005, "learning_rate": 0.00013480879730532993, "loss": 0.6348868370056152, "step": 34020 }, { "epoch": 0.20228138690253283, "grad_norm": 1.4647022485733032, "learning_rate": 0.00013484842480681594, "loss": 0.6241957664489746, "step": 34030 }, { "epoch": 0.20234082897920122, "grad_norm": 1.672848105430603, "learning_rate": 0.00013488805230830198, "loss": 0.7207340717315673, "step": 34040 }, { "epoch": 0.2024002710558696, "grad_norm": 1.5872288942337036, "learning_rate": 0.000134927679809788, "loss": 0.6864212036132813, "step": 34050 }, { "epoch": 0.202459713132538, "grad_norm": 1.4448846578598022, "learning_rate": 0.00013496730731127403, "loss": 0.7372829914093018, "step": 34060 }, { "epoch": 0.20251915520920638, "grad_norm": 1.2492365837097168, "learning_rate": 0.00013500693481276007, "loss": 0.5799766540527344, "step": 34070 }, { "epoch": 0.20257859728587477, "grad_norm": 1.3760590553283691, "learning_rate": 0.00013504656231424608, "loss": 0.6553221702575683, "step": 34080 }, { "epoch": 0.20263803936254318, "grad_norm": 1.1466461420059204, "learning_rate": 0.00013508618981573214, "loss": 0.7026060104370118, "step": 34090 }, { "epoch": 0.20269748143921157, "grad_norm": 1.584941029548645, "learning_rate": 0.00013512581731721815, "loss": 0.6197077751159668, "step": 34100 }, { "epoch": 0.20275692351587996, "grad_norm": 1.532157063484192, "learning_rate": 0.0001351654448187042, "loss": 0.6431497097015381, "step": 34110 }, { "epoch": 0.20281636559254834, "grad_norm": 1.6606465578079224, "learning_rate": 0.0001352050723201902, "loss": 0.6387322902679443, "step": 34120 }, { "epoch": 0.20287580766921673, "grad_norm": 1.7983657121658325, "learning_rate": 0.00013524469982167624, "loss": 0.7416115760803222, "step": 34130 }, { "epoch": 0.20293524974588512, "grad_norm": 1.8940799236297607, "learning_rate": 0.00013528432732316228, "loss": 0.740573787689209, "step": 34140 }, { "epoch": 0.2029946918225535, "grad_norm": 1.2859818935394287, "learning_rate": 0.0001353239548246483, "loss": 0.6865847110748291, "step": 34150 }, { "epoch": 0.20305413389922192, "grad_norm": 1.4518227577209473, "learning_rate": 0.00013536358232613436, "loss": 0.6888031959533691, "step": 34160 }, { "epoch": 0.2031135759758903, "grad_norm": 1.540804147720337, "learning_rate": 0.00013540320982762037, "loss": 0.6823810577392578, "step": 34170 }, { "epoch": 0.2031730180525587, "grad_norm": 1.3697161674499512, "learning_rate": 0.0001354428373291064, "loss": 0.630715799331665, "step": 34180 }, { "epoch": 0.20323246012922708, "grad_norm": 1.5706558227539062, "learning_rate": 0.00013548246483059245, "loss": 0.6805649757385254, "step": 34190 }, { "epoch": 0.20329190220589546, "grad_norm": 1.4210178852081299, "learning_rate": 0.00013552209233207846, "loss": 0.7283383369445801, "step": 34200 }, { "epoch": 0.20335134428256385, "grad_norm": 1.3508613109588623, "learning_rate": 0.0001355617198335645, "loss": 0.5976983070373535, "step": 34210 }, { "epoch": 0.20341078635923224, "grad_norm": 1.5996607542037964, "learning_rate": 0.0001356013473350505, "loss": 0.6841959953308105, "step": 34220 }, { "epoch": 0.20347022843590062, "grad_norm": 1.4659168720245361, "learning_rate": 0.00013564097483653658, "loss": 0.7084555625915527, "step": 34230 }, { "epoch": 0.20352967051256904, "grad_norm": 2.3059678077697754, "learning_rate": 0.0001356806023380226, "loss": 0.6825963973999023, "step": 34240 }, { "epoch": 0.20358911258923743, "grad_norm": 1.4965763092041016, "learning_rate": 0.00013572022983950863, "loss": 0.6514997482299805, "step": 34250 }, { "epoch": 0.2036485546659058, "grad_norm": 1.5910792350769043, "learning_rate": 0.00013575985734099466, "loss": 0.7537527561187745, "step": 34260 }, { "epoch": 0.2037079967425742, "grad_norm": 1.4908891916275024, "learning_rate": 0.00013579948484248068, "loss": 0.6137795925140381, "step": 34270 }, { "epoch": 0.20376743881924259, "grad_norm": 1.5690350532531738, "learning_rate": 0.00013583911234396672, "loss": 0.7048004627227783, "step": 34280 }, { "epoch": 0.20382688089591097, "grad_norm": 1.4252874851226807, "learning_rate": 0.00013587873984545275, "loss": 0.6062368392944336, "step": 34290 }, { "epoch": 0.20388632297257936, "grad_norm": 1.3589931726455688, "learning_rate": 0.0001359183673469388, "loss": 0.6652096271514892, "step": 34300 }, { "epoch": 0.20394576504924777, "grad_norm": 1.3632330894470215, "learning_rate": 0.00013595799484842483, "loss": 0.6052927017211914, "step": 34310 }, { "epoch": 0.20400520712591616, "grad_norm": 1.4657632112503052, "learning_rate": 0.00013599762234991084, "loss": 0.6269514560699463, "step": 34320 }, { "epoch": 0.20406464920258455, "grad_norm": 1.4865480661392212, "learning_rate": 0.00013603724985139688, "loss": 0.6301060676574707, "step": 34330 }, { "epoch": 0.20412409127925293, "grad_norm": 2.096289873123169, "learning_rate": 0.0001360768773528829, "loss": 0.6824936866760254, "step": 34340 }, { "epoch": 0.20418353335592132, "grad_norm": 1.7960351705551147, "learning_rate": 0.00013611650485436893, "loss": 0.6328961372375488, "step": 34350 }, { "epoch": 0.2042429754325897, "grad_norm": 1.4332507848739624, "learning_rate": 0.00013615613235585497, "loss": 0.6857345581054688, "step": 34360 }, { "epoch": 0.2043024175092581, "grad_norm": 1.4154468774795532, "learning_rate": 0.000136195759857341, "loss": 0.6715039253234864, "step": 34370 }, { "epoch": 0.20436185958592648, "grad_norm": 1.3400473594665527, "learning_rate": 0.00013623538735882705, "loss": 0.6066624641418457, "step": 34380 }, { "epoch": 0.2044213016625949, "grad_norm": 2.0942811965942383, "learning_rate": 0.00013627501486031306, "loss": 0.6538093090057373, "step": 34390 }, { "epoch": 0.20448074373926328, "grad_norm": 1.63585364818573, "learning_rate": 0.0001363146423617991, "loss": 0.6573755264282226, "step": 34400 }, { "epoch": 0.20454018581593167, "grad_norm": 1.4823077917099, "learning_rate": 0.0001363542698632851, "loss": 0.6111468315124512, "step": 34410 }, { "epoch": 0.20459962789260006, "grad_norm": 1.3599659204483032, "learning_rate": 0.00013639389736477115, "loss": 0.6759627342224122, "step": 34420 }, { "epoch": 0.20465906996926844, "grad_norm": 1.6469202041625977, "learning_rate": 0.0001364335248662572, "loss": 0.6892155647277832, "step": 34430 }, { "epoch": 0.20471851204593683, "grad_norm": 1.4333627223968506, "learning_rate": 0.00013647315236774323, "loss": 0.6816149711608886, "step": 34440 }, { "epoch": 0.20477795412260522, "grad_norm": 1.2079828977584839, "learning_rate": 0.00013651277986922926, "loss": 0.6434701442718506, "step": 34450 }, { "epoch": 0.20483739619927363, "grad_norm": 1.6861573457717896, "learning_rate": 0.00013655240737071528, "loss": 0.6965407371520996, "step": 34460 }, { "epoch": 0.20489683827594202, "grad_norm": 1.6369986534118652, "learning_rate": 0.00013659203487220131, "loss": 0.6826669692993164, "step": 34470 }, { "epoch": 0.2049562803526104, "grad_norm": 1.6173224449157715, "learning_rate": 0.00013663166237368735, "loss": 0.698484992980957, "step": 34480 }, { "epoch": 0.2050157224292788, "grad_norm": 1.953643798828125, "learning_rate": 0.00013667128987517336, "loss": 0.6777672290802002, "step": 34490 }, { "epoch": 0.20507516450594718, "grad_norm": 1.529505729675293, "learning_rate": 0.0001367109173766594, "loss": 0.6287541866302491, "step": 34500 }, { "epoch": 0.20513460658261556, "grad_norm": 1.5623228549957275, "learning_rate": 0.00013675054487814544, "loss": 0.6530440330505372, "step": 34510 }, { "epoch": 0.20519404865928395, "grad_norm": 1.8538432121276855, "learning_rate": 0.00013679017237963148, "loss": 0.6934139251708984, "step": 34520 }, { "epoch": 0.20525349073595234, "grad_norm": 1.6654462814331055, "learning_rate": 0.0001368297998811175, "loss": 0.7091836929321289, "step": 34530 }, { "epoch": 0.20531293281262075, "grad_norm": 1.8304345607757568, "learning_rate": 0.00013686942738260353, "loss": 0.6963799476623536, "step": 34540 }, { "epoch": 0.20537237488928914, "grad_norm": 1.779624104499817, "learning_rate": 0.00013690905488408957, "loss": 0.7471982002258301, "step": 34550 }, { "epoch": 0.20543181696595753, "grad_norm": 1.3199812173843384, "learning_rate": 0.00013694868238557558, "loss": 0.6207855224609375, "step": 34560 }, { "epoch": 0.2054912590426259, "grad_norm": 1.459194302558899, "learning_rate": 0.00013698830988706162, "loss": 0.6648332595825195, "step": 34570 }, { "epoch": 0.2055507011192943, "grad_norm": 1.6953330039978027, "learning_rate": 0.00013702793738854766, "loss": 0.6984540939331054, "step": 34580 }, { "epoch": 0.20561014319596269, "grad_norm": 1.2286324501037598, "learning_rate": 0.0001370675648900337, "loss": 0.6601926326751709, "step": 34590 }, { "epoch": 0.20566958527263107, "grad_norm": 1.4489612579345703, "learning_rate": 0.00013710719239151974, "loss": 0.66227707862854, "step": 34600 }, { "epoch": 0.2057290273492995, "grad_norm": 1.7712688446044922, "learning_rate": 0.00013714681989300575, "loss": 0.6743124961853028, "step": 34610 }, { "epoch": 0.20578846942596787, "grad_norm": 1.266631007194519, "learning_rate": 0.00013718644739449179, "loss": 0.6544119358062744, "step": 34620 }, { "epoch": 0.20584791150263626, "grad_norm": 1.3917397260665894, "learning_rate": 0.0001372260748959778, "loss": 0.6886741161346436, "step": 34630 }, { "epoch": 0.20590735357930465, "grad_norm": 1.8691893815994263, "learning_rate": 0.00013726570239746384, "loss": 0.6675710678100586, "step": 34640 }, { "epoch": 0.20596679565597303, "grad_norm": 1.8101277351379395, "learning_rate": 0.00013730532989894987, "loss": 0.6166973114013672, "step": 34650 }, { "epoch": 0.20602623773264142, "grad_norm": 1.5770304203033447, "learning_rate": 0.0001373449574004359, "loss": 0.6445485591888428, "step": 34660 }, { "epoch": 0.2060856798093098, "grad_norm": 1.1261464357376099, "learning_rate": 0.00013738458490192195, "loss": 0.6482596397399902, "step": 34670 }, { "epoch": 0.20614512188597822, "grad_norm": 1.5032933950424194, "learning_rate": 0.00013742421240340796, "loss": 0.6658190727233887, "step": 34680 }, { "epoch": 0.2062045639626466, "grad_norm": 1.6821165084838867, "learning_rate": 0.000137463839904894, "loss": 0.6660151481628418, "step": 34690 }, { "epoch": 0.206264006039315, "grad_norm": 1.557669758796692, "learning_rate": 0.00013750346740638, "loss": 0.7519540786743164, "step": 34700 }, { "epoch": 0.20632344811598338, "grad_norm": 1.7187697887420654, "learning_rate": 0.00013754309490786605, "loss": 0.6233093738555908, "step": 34710 }, { "epoch": 0.20638289019265177, "grad_norm": 1.595458984375, "learning_rate": 0.00013758272240935212, "loss": 0.653738260269165, "step": 34720 }, { "epoch": 0.20644233226932016, "grad_norm": 1.4801806211471558, "learning_rate": 0.00013762234991083813, "loss": 0.7049917221069336, "step": 34730 }, { "epoch": 0.20650177434598854, "grad_norm": 1.6025885343551636, "learning_rate": 0.00013766197741232417, "loss": 0.6252079963684082, "step": 34740 }, { "epoch": 0.20656121642265693, "grad_norm": 1.5300889015197754, "learning_rate": 0.00013770160491381018, "loss": 0.691946268081665, "step": 34750 }, { "epoch": 0.20662065849932534, "grad_norm": 1.5735321044921875, "learning_rate": 0.00013774123241529622, "loss": 0.6229016304016113, "step": 34760 }, { "epoch": 0.20668010057599373, "grad_norm": 1.6315348148345947, "learning_rate": 0.00013778085991678226, "loss": 0.6854280471801758, "step": 34770 }, { "epoch": 0.20673954265266212, "grad_norm": 1.67704439163208, "learning_rate": 0.00013782048741826827, "loss": 0.7527604103088379, "step": 34780 }, { "epoch": 0.2067989847293305, "grad_norm": 1.2307698726654053, "learning_rate": 0.00013786011491975433, "loss": 0.6426029682159424, "step": 34790 }, { "epoch": 0.2068584268059989, "grad_norm": 1.8686400651931763, "learning_rate": 0.00013789974242124035, "loss": 0.6816141605377197, "step": 34800 }, { "epoch": 0.20691786888266728, "grad_norm": 1.2987531423568726, "learning_rate": 0.00013793936992272638, "loss": 0.722067928314209, "step": 34810 }, { "epoch": 0.20697731095933566, "grad_norm": 1.4076098203659058, "learning_rate": 0.0001379789974242124, "loss": 0.6307746410369873, "step": 34820 }, { "epoch": 0.20703675303600408, "grad_norm": 1.2813177108764648, "learning_rate": 0.00013801862492569843, "loss": 0.6556979179382324, "step": 34830 }, { "epoch": 0.20709619511267247, "grad_norm": 1.498439908027649, "learning_rate": 0.00013805825242718447, "loss": 0.6852580547332764, "step": 34840 }, { "epoch": 0.20715563718934085, "grad_norm": 1.7209441661834717, "learning_rate": 0.0001380978799286705, "loss": 0.6694221496582031, "step": 34850 }, { "epoch": 0.20721507926600924, "grad_norm": 1.7019928693771362, "learning_rate": 0.00013813750743015655, "loss": 0.6709713459014892, "step": 34860 }, { "epoch": 0.20727452134267763, "grad_norm": 1.9304147958755493, "learning_rate": 0.00013817713493164256, "loss": 0.662770128250122, "step": 34870 }, { "epoch": 0.207333963419346, "grad_norm": 1.5052926540374756, "learning_rate": 0.0001382167624331286, "loss": 0.6653234958648682, "step": 34880 }, { "epoch": 0.2073934054960144, "grad_norm": 1.4921449422836304, "learning_rate": 0.00013825638993461464, "loss": 0.6254354476928711, "step": 34890 }, { "epoch": 0.20745284757268279, "grad_norm": 1.4648895263671875, "learning_rate": 0.00013829601743610065, "loss": 0.6374969482421875, "step": 34900 }, { "epoch": 0.2075122896493512, "grad_norm": 1.3119072914123535, "learning_rate": 0.0001383356449375867, "loss": 0.7040084838867188, "step": 34910 }, { "epoch": 0.2075717317260196, "grad_norm": 1.6193389892578125, "learning_rate": 0.00013837527243907273, "loss": 0.6406119346618653, "step": 34920 }, { "epoch": 0.20763117380268797, "grad_norm": 1.4559297561645508, "learning_rate": 0.00013841489994055877, "loss": 0.6542937278747558, "step": 34930 }, { "epoch": 0.20769061587935636, "grad_norm": 1.9367159605026245, "learning_rate": 0.00013845452744204478, "loss": 0.671109390258789, "step": 34940 }, { "epoch": 0.20775005795602475, "grad_norm": 1.7344595193862915, "learning_rate": 0.00013849415494353082, "loss": 0.662920331954956, "step": 34950 }, { "epoch": 0.20780950003269313, "grad_norm": 1.5485265254974365, "learning_rate": 0.00013853378244501686, "loss": 0.6524621486663819, "step": 34960 }, { "epoch": 0.20786894210936152, "grad_norm": 1.6006884574890137, "learning_rate": 0.00013857340994650287, "loss": 0.6210076332092285, "step": 34970 }, { "epoch": 0.20792838418602994, "grad_norm": 1.691447377204895, "learning_rate": 0.0001386130374479889, "loss": 0.677949047088623, "step": 34980 }, { "epoch": 0.20798782626269832, "grad_norm": 1.4712458848953247, "learning_rate": 0.00013865266494947494, "loss": 0.6528845310211182, "step": 34990 }, { "epoch": 0.2080472683393667, "grad_norm": 1.5295639038085938, "learning_rate": 0.00013869229245096098, "loss": 0.7287227630615234, "step": 35000 }, { "epoch": 0.2081067104160351, "grad_norm": 1.4644614458084106, "learning_rate": 0.00013873191995244702, "loss": 0.6184924125671387, "step": 35010 }, { "epoch": 0.20816615249270348, "grad_norm": 1.4373526573181152, "learning_rate": 0.00013877154745393303, "loss": 0.6898457527160644, "step": 35020 }, { "epoch": 0.20822559456937187, "grad_norm": 1.3798013925552368, "learning_rate": 0.00013881117495541907, "loss": 0.6422907829284668, "step": 35030 }, { "epoch": 0.20828503664604026, "grad_norm": 1.4090150594711304, "learning_rate": 0.00013885080245690508, "loss": 0.6785470008850097, "step": 35040 }, { "epoch": 0.20834447872270867, "grad_norm": 1.5558098554611206, "learning_rate": 0.00013889042995839112, "loss": 0.655238676071167, "step": 35050 }, { "epoch": 0.20840392079937706, "grad_norm": 1.2696353197097778, "learning_rate": 0.00013893005745987716, "loss": 0.6763358592987061, "step": 35060 }, { "epoch": 0.20846336287604544, "grad_norm": 1.4599372148513794, "learning_rate": 0.0001389696849613632, "loss": 0.6345656394958497, "step": 35070 }, { "epoch": 0.20852280495271383, "grad_norm": 1.5602984428405762, "learning_rate": 0.00013900931246284924, "loss": 0.6506887435913086, "step": 35080 }, { "epoch": 0.20858224702938222, "grad_norm": 1.216001033782959, "learning_rate": 0.00013904893996433525, "loss": 0.6790610790252686, "step": 35090 }, { "epoch": 0.2086416891060506, "grad_norm": 1.3667151927947998, "learning_rate": 0.0001390885674658213, "loss": 0.651059627532959, "step": 35100 }, { "epoch": 0.208701131182719, "grad_norm": 1.4163992404937744, "learning_rate": 0.0001391281949673073, "loss": 0.6894515991210938, "step": 35110 }, { "epoch": 0.20876057325938738, "grad_norm": 1.3962814807891846, "learning_rate": 0.00013916782246879334, "loss": 0.7298442840576171, "step": 35120 }, { "epoch": 0.2088200153360558, "grad_norm": 1.9443312883377075, "learning_rate": 0.0001392074499702794, "loss": 0.6419558525085449, "step": 35130 }, { "epoch": 0.20887945741272418, "grad_norm": 1.443570613861084, "learning_rate": 0.00013924707747176542, "loss": 0.6060216903686524, "step": 35140 }, { "epoch": 0.20893889948939257, "grad_norm": 1.4722564220428467, "learning_rate": 0.00013928670497325145, "loss": 0.7500503540039063, "step": 35150 }, { "epoch": 0.20899834156606095, "grad_norm": 1.2337466478347778, "learning_rate": 0.00013932633247473747, "loss": 0.6781518936157227, "step": 35160 }, { "epoch": 0.20905778364272934, "grad_norm": 1.608292579650879, "learning_rate": 0.0001393659599762235, "loss": 0.6729920864105224, "step": 35170 }, { "epoch": 0.20911722571939773, "grad_norm": 1.9414857625961304, "learning_rate": 0.00013940558747770954, "loss": 0.689944076538086, "step": 35180 }, { "epoch": 0.2091766677960661, "grad_norm": 1.3558071851730347, "learning_rate": 0.00013944521497919555, "loss": 0.6562099456787109, "step": 35190 }, { "epoch": 0.20923610987273453, "grad_norm": 1.6754831075668335, "learning_rate": 0.00013948484248068162, "loss": 0.6691378116607666, "step": 35200 }, { "epoch": 0.2092955519494029, "grad_norm": 1.7243400812149048, "learning_rate": 0.00013952446998216763, "loss": 0.6908507347106934, "step": 35210 }, { "epoch": 0.2093549940260713, "grad_norm": 1.4971064329147339, "learning_rate": 0.00013956409748365367, "loss": 0.6697784423828125, "step": 35220 }, { "epoch": 0.2094144361027397, "grad_norm": 1.444949984550476, "learning_rate": 0.00013960372498513968, "loss": 0.663782262802124, "step": 35230 }, { "epoch": 0.20947387817940807, "grad_norm": 1.5377784967422485, "learning_rate": 0.00013964335248662572, "loss": 0.7174779891967773, "step": 35240 }, { "epoch": 0.20953332025607646, "grad_norm": 1.048758864402771, "learning_rate": 0.00013968297998811176, "loss": 0.6284040451049805, "step": 35250 }, { "epoch": 0.20959276233274485, "grad_norm": 1.623915195465088, "learning_rate": 0.00013972260748959777, "loss": 0.6468649864196777, "step": 35260 }, { "epoch": 0.20965220440941323, "grad_norm": 1.4444864988327026, "learning_rate": 0.00013976223499108384, "loss": 0.7116138458251953, "step": 35270 }, { "epoch": 0.20971164648608165, "grad_norm": 1.2315489053726196, "learning_rate": 0.00013980186249256985, "loss": 0.6573347091674805, "step": 35280 }, { "epoch": 0.20977108856275004, "grad_norm": 1.2678580284118652, "learning_rate": 0.0001398414899940559, "loss": 0.6326146125793457, "step": 35290 }, { "epoch": 0.20983053063941842, "grad_norm": 1.40505850315094, "learning_rate": 0.00013988111749554193, "loss": 0.626302433013916, "step": 35300 }, { "epoch": 0.2098899727160868, "grad_norm": 1.3958728313446045, "learning_rate": 0.00013992074499702794, "loss": 0.6220649719238281, "step": 35310 }, { "epoch": 0.2099494147927552, "grad_norm": 1.6544008255004883, "learning_rate": 0.00013996037249851398, "loss": 0.6900286674499512, "step": 35320 }, { "epoch": 0.21000885686942358, "grad_norm": 1.456594467163086, "learning_rate": 0.00014, "loss": 0.6867722988128662, "step": 35330 }, { "epoch": 0.21006829894609197, "grad_norm": 1.2263864278793335, "learning_rate": 0.00014003962750148605, "loss": 0.6299347400665283, "step": 35340 }, { "epoch": 0.21012774102276038, "grad_norm": 1.472733497619629, "learning_rate": 0.00014007925500297207, "loss": 0.6933622837066651, "step": 35350 }, { "epoch": 0.21018718309942877, "grad_norm": 1.6332021951675415, "learning_rate": 0.0001401188825044581, "loss": 0.6842013359069824, "step": 35360 }, { "epoch": 0.21024662517609716, "grad_norm": 1.5647097826004028, "learning_rate": 0.00014015851000594414, "loss": 0.667575454711914, "step": 35370 }, { "epoch": 0.21030606725276554, "grad_norm": 1.577253818511963, "learning_rate": 0.00014019813750743015, "loss": 0.6924954414367676, "step": 35380 }, { "epoch": 0.21036550932943393, "grad_norm": 1.3456422090530396, "learning_rate": 0.0001402377650089162, "loss": 0.6072073459625245, "step": 35390 }, { "epoch": 0.21042495140610232, "grad_norm": 1.555553913116455, "learning_rate": 0.0001402773925104022, "loss": 0.7066069602966308, "step": 35400 }, { "epoch": 0.2104843934827707, "grad_norm": 1.7676985263824463, "learning_rate": 0.00014031702001188827, "loss": 0.749715518951416, "step": 35410 }, { "epoch": 0.2105438355594391, "grad_norm": 1.4879765510559082, "learning_rate": 0.0001403566475133743, "loss": 0.6919678688049317, "step": 35420 }, { "epoch": 0.2106032776361075, "grad_norm": 1.4539679288864136, "learning_rate": 0.00014039627501486032, "loss": 0.6541427135467529, "step": 35430 }, { "epoch": 0.2106627197127759, "grad_norm": 1.519407033920288, "learning_rate": 0.00014043590251634636, "loss": 0.6865122795104981, "step": 35440 }, { "epoch": 0.21072216178944428, "grad_norm": 1.4677317142486572, "learning_rate": 0.00014047553001783237, "loss": 0.6110833168029786, "step": 35450 }, { "epoch": 0.21078160386611267, "grad_norm": 1.898474097251892, "learning_rate": 0.0001405151575193184, "loss": 0.6441009044647217, "step": 35460 }, { "epoch": 0.21084104594278105, "grad_norm": 1.2797366380691528, "learning_rate": 0.00014055478502080445, "loss": 0.6866630554199219, "step": 35470 }, { "epoch": 0.21090048801944944, "grad_norm": 1.6512476205825806, "learning_rate": 0.00014059441252229049, "loss": 0.645416259765625, "step": 35480 }, { "epoch": 0.21095993009611783, "grad_norm": 1.6584157943725586, "learning_rate": 0.00014063404002377652, "loss": 0.6433721065521241, "step": 35490 }, { "epoch": 0.21101937217278624, "grad_norm": 1.6075716018676758, "learning_rate": 0.00014067366752526254, "loss": 0.647875452041626, "step": 35500 }, { "epoch": 0.21107881424945463, "grad_norm": 1.2686419486999512, "learning_rate": 0.00014071329502674858, "loss": 0.609724760055542, "step": 35510 }, { "epoch": 0.211138256326123, "grad_norm": 1.7215834856033325, "learning_rate": 0.0001407529225282346, "loss": 0.6608442783355712, "step": 35520 }, { "epoch": 0.2111976984027914, "grad_norm": 1.9344336986541748, "learning_rate": 0.00014079255002972063, "loss": 0.6339517116546631, "step": 35530 }, { "epoch": 0.2112571404794598, "grad_norm": 1.4728895425796509, "learning_rate": 0.00014083217753120666, "loss": 0.6849555969238281, "step": 35540 }, { "epoch": 0.21131658255612817, "grad_norm": 1.4902132749557495, "learning_rate": 0.0001408718050326927, "loss": 0.6334126949310303, "step": 35550 }, { "epoch": 0.21137602463279656, "grad_norm": 1.4869892597198486, "learning_rate": 0.00014091143253417874, "loss": 0.6783316612243653, "step": 35560 }, { "epoch": 0.21143546670946498, "grad_norm": 1.4044336080551147, "learning_rate": 0.00014095106003566475, "loss": 0.6608009338378906, "step": 35570 }, { "epoch": 0.21149490878613336, "grad_norm": 1.5699117183685303, "learning_rate": 0.0001409906875371508, "loss": 0.694695234298706, "step": 35580 }, { "epoch": 0.21155435086280175, "grad_norm": 1.4805197715759277, "learning_rate": 0.00014103031503863683, "loss": 0.6470167160034179, "step": 35590 }, { "epoch": 0.21161379293947014, "grad_norm": 1.3564091920852661, "learning_rate": 0.00014106994254012284, "loss": 0.6519467830657959, "step": 35600 }, { "epoch": 0.21167323501613852, "grad_norm": 1.6972469091415405, "learning_rate": 0.00014110957004160888, "loss": 0.6512598037719727, "step": 35610 }, { "epoch": 0.2117326770928069, "grad_norm": 1.588733434677124, "learning_rate": 0.00014114919754309492, "loss": 0.6153100967407227, "step": 35620 }, { "epoch": 0.2117921191694753, "grad_norm": 1.867995262145996, "learning_rate": 0.00014118882504458096, "loss": 0.6593540191650391, "step": 35630 }, { "epoch": 0.21185156124614368, "grad_norm": 1.786234974861145, "learning_rate": 0.00014122845254606697, "loss": 0.6804090023040772, "step": 35640 }, { "epoch": 0.2119110033228121, "grad_norm": 1.4189329147338867, "learning_rate": 0.000141268080047553, "loss": 0.6486646175384522, "step": 35650 }, { "epoch": 0.21197044539948048, "grad_norm": 1.43250572681427, "learning_rate": 0.00014130770754903905, "loss": 0.6856493473052978, "step": 35660 }, { "epoch": 0.21202988747614887, "grad_norm": 1.7309411764144897, "learning_rate": 0.00014134733505052506, "loss": 0.7359768867492675, "step": 35670 }, { "epoch": 0.21208932955281726, "grad_norm": 1.428430199623108, "learning_rate": 0.0001413869625520111, "loss": 0.6319273948669434, "step": 35680 }, { "epoch": 0.21214877162948564, "grad_norm": 1.475783348083496, "learning_rate": 0.00014142659005349714, "loss": 0.7087301254272461, "step": 35690 }, { "epoch": 0.21220821370615403, "grad_norm": 1.5614923238754272, "learning_rate": 0.00014146621755498317, "loss": 0.6571001052856446, "step": 35700 }, { "epoch": 0.21226765578282242, "grad_norm": 1.5890847444534302, "learning_rate": 0.0001415058450564692, "loss": 0.5995429039001465, "step": 35710 }, { "epoch": 0.21232709785949083, "grad_norm": 1.8923816680908203, "learning_rate": 0.00014154547255795522, "loss": 0.6662478923797608, "step": 35720 }, { "epoch": 0.21238653993615922, "grad_norm": 1.4548417329788208, "learning_rate": 0.00014158510005944126, "loss": 0.7141609191894531, "step": 35730 }, { "epoch": 0.2124459820128276, "grad_norm": 1.2468957901000977, "learning_rate": 0.00014162472756092727, "loss": 0.6364013671875, "step": 35740 }, { "epoch": 0.212505424089496, "grad_norm": 1.6354917287826538, "learning_rate": 0.0001416643550624133, "loss": 0.6216460227966308, "step": 35750 }, { "epoch": 0.21256486616616438, "grad_norm": 1.5902204513549805, "learning_rate": 0.00014170398256389935, "loss": 0.6683573722839355, "step": 35760 }, { "epoch": 0.21262430824283277, "grad_norm": 1.5201046466827393, "learning_rate": 0.0001417436100653854, "loss": 0.6573208808898926, "step": 35770 }, { "epoch": 0.21268375031950115, "grad_norm": 1.7342357635498047, "learning_rate": 0.00014178323756687143, "loss": 0.6201070308685303, "step": 35780 }, { "epoch": 0.21274319239616954, "grad_norm": 1.812090516090393, "learning_rate": 0.00014182286506835744, "loss": 0.7040818214416504, "step": 35790 }, { "epoch": 0.21280263447283795, "grad_norm": 2.192261219024658, "learning_rate": 0.00014186249256984348, "loss": 0.6457201957702636, "step": 35800 }, { "epoch": 0.21286207654950634, "grad_norm": 1.2326326370239258, "learning_rate": 0.0001419021200713295, "loss": 0.5985552787780761, "step": 35810 }, { "epoch": 0.21292151862617473, "grad_norm": 1.2788844108581543, "learning_rate": 0.00014194174757281553, "loss": 0.6723233222961426, "step": 35820 }, { "epoch": 0.21298096070284311, "grad_norm": 1.906594157218933, "learning_rate": 0.00014198137507430157, "loss": 0.7112442016601562, "step": 35830 }, { "epoch": 0.2130404027795115, "grad_norm": 1.687997817993164, "learning_rate": 0.0001420210025757876, "loss": 0.6775355339050293, "step": 35840 }, { "epoch": 0.2130998448561799, "grad_norm": 1.482546329498291, "learning_rate": 0.00014206063007727365, "loss": 0.6417715072631835, "step": 35850 }, { "epoch": 0.21315928693284827, "grad_norm": 1.685119867324829, "learning_rate": 0.00014210025757875966, "loss": 0.677794075012207, "step": 35860 }, { "epoch": 0.2132187290095167, "grad_norm": 1.7379869222640991, "learning_rate": 0.0001421398850802457, "loss": 0.7077239513397217, "step": 35870 }, { "epoch": 0.21327817108618508, "grad_norm": 1.6506251096725464, "learning_rate": 0.00014217951258173173, "loss": 0.6971589088439941, "step": 35880 }, { "epoch": 0.21333761316285346, "grad_norm": 1.9080232381820679, "learning_rate": 0.00014221914008321775, "loss": 0.7136987686157227, "step": 35890 }, { "epoch": 0.21339705523952185, "grad_norm": 1.830965518951416, "learning_rate": 0.0001422587675847038, "loss": 0.6415364265441894, "step": 35900 }, { "epoch": 0.21345649731619024, "grad_norm": 1.6109733581542969, "learning_rate": 0.00014229839508618982, "loss": 0.6624754905700684, "step": 35910 }, { "epoch": 0.21351593939285862, "grad_norm": 1.4972680807113647, "learning_rate": 0.00014233802258767586, "loss": 0.6019227027893066, "step": 35920 }, { "epoch": 0.213575381469527, "grad_norm": 1.4412437677383423, "learning_rate": 0.00014237765008916187, "loss": 0.6752408981323242, "step": 35930 }, { "epoch": 0.21363482354619542, "grad_norm": 1.7739402055740356, "learning_rate": 0.0001424172775906479, "loss": 0.6481739044189453, "step": 35940 }, { "epoch": 0.2136942656228638, "grad_norm": 1.6338683366775513, "learning_rate": 0.00014245690509213395, "loss": 0.6967579841613769, "step": 35950 }, { "epoch": 0.2137537076995322, "grad_norm": 1.4240384101867676, "learning_rate": 0.00014249653259361996, "loss": 0.6542322158813476, "step": 35960 }, { "epoch": 0.21381314977620058, "grad_norm": 1.3720157146453857, "learning_rate": 0.00014253616009510603, "loss": 0.7279911518096924, "step": 35970 }, { "epoch": 0.21387259185286897, "grad_norm": 1.5754410028457642, "learning_rate": 0.00014257578759659204, "loss": 0.6409669876098633, "step": 35980 }, { "epoch": 0.21393203392953736, "grad_norm": 1.4294523000717163, "learning_rate": 0.00014261541509807808, "loss": 0.675666618347168, "step": 35990 }, { "epoch": 0.21399147600620574, "grad_norm": 1.5164408683776855, "learning_rate": 0.00014265504259956412, "loss": 0.6677800178527832, "step": 36000 }, { "epoch": 0.21405091808287413, "grad_norm": 1.4192793369293213, "learning_rate": 0.00014269467010105013, "loss": 0.664326810836792, "step": 36010 }, { "epoch": 0.21411036015954255, "grad_norm": 1.5577666759490967, "learning_rate": 0.00014273429760253617, "loss": 0.6297317504882812, "step": 36020 }, { "epoch": 0.21416980223621093, "grad_norm": 1.469834566116333, "learning_rate": 0.00014277392510402218, "loss": 0.6664265155792236, "step": 36030 }, { "epoch": 0.21422924431287932, "grad_norm": 1.4577940702438354, "learning_rate": 0.00014281355260550824, "loss": 0.6182143688201904, "step": 36040 }, { "epoch": 0.2142886863895477, "grad_norm": 1.2681488990783691, "learning_rate": 0.00014285318010699426, "loss": 0.6799506664276123, "step": 36050 }, { "epoch": 0.2143481284662161, "grad_norm": 1.6998032331466675, "learning_rate": 0.0001428928076084803, "loss": 0.6950844764709473, "step": 36060 }, { "epoch": 0.21440757054288448, "grad_norm": 1.4236737489700317, "learning_rate": 0.00014293243510996633, "loss": 0.677796459197998, "step": 36070 }, { "epoch": 0.21446701261955287, "grad_norm": 1.6595053672790527, "learning_rate": 0.00014297206261145234, "loss": 0.6598602294921875, "step": 36080 }, { "epoch": 0.21452645469622128, "grad_norm": 1.3838251829147339, "learning_rate": 0.00014301169011293838, "loss": 0.6568495273590088, "step": 36090 }, { "epoch": 0.21458589677288967, "grad_norm": 1.7993828058242798, "learning_rate": 0.0001430513176144244, "loss": 0.6394913673400879, "step": 36100 }, { "epoch": 0.21464533884955805, "grad_norm": 1.9834619760513306, "learning_rate": 0.00014309094511591046, "loss": 0.7599699020385742, "step": 36110 }, { "epoch": 0.21470478092622644, "grad_norm": 1.480847716331482, "learning_rate": 0.00014313057261739647, "loss": 0.6983212471008301, "step": 36120 }, { "epoch": 0.21476422300289483, "grad_norm": 1.3964999914169312, "learning_rate": 0.0001431702001188825, "loss": 0.6793712139129638, "step": 36130 }, { "epoch": 0.21482366507956321, "grad_norm": 1.3863136768341064, "learning_rate": 0.00014320982762036855, "loss": 0.6110954284667969, "step": 36140 }, { "epoch": 0.2148831071562316, "grad_norm": 1.3155685663223267, "learning_rate": 0.00014324945512185456, "loss": 0.6996256351470947, "step": 36150 }, { "epoch": 0.2149425492329, "grad_norm": 1.7006012201309204, "learning_rate": 0.0001432890826233406, "loss": 0.652976131439209, "step": 36160 }, { "epoch": 0.2150019913095684, "grad_norm": 1.364140510559082, "learning_rate": 0.00014332871012482664, "loss": 0.6874216079711915, "step": 36170 }, { "epoch": 0.2150614333862368, "grad_norm": 1.5323090553283691, "learning_rate": 0.00014336833762631268, "loss": 0.6502556324005127, "step": 36180 }, { "epoch": 0.21512087546290518, "grad_norm": 1.5000461339950562, "learning_rate": 0.00014340796512779872, "loss": 0.6787855148315429, "step": 36190 }, { "epoch": 0.21518031753957356, "grad_norm": 1.6271229982376099, "learning_rate": 0.00014344759262928473, "loss": 0.6313555717468262, "step": 36200 }, { "epoch": 0.21523975961624195, "grad_norm": 1.4619672298431396, "learning_rate": 0.00014348722013077077, "loss": 0.6818068981170654, "step": 36210 }, { "epoch": 0.21529920169291034, "grad_norm": 1.492629885673523, "learning_rate": 0.00014352684763225678, "loss": 0.6466750621795654, "step": 36220 }, { "epoch": 0.21535864376957872, "grad_norm": 1.33133864402771, "learning_rate": 0.00014356647513374282, "loss": 0.6537785053253173, "step": 36230 }, { "epoch": 0.21541808584624714, "grad_norm": 1.8307667970657349, "learning_rate": 0.00014360610263522885, "loss": 0.6406757354736328, "step": 36240 }, { "epoch": 0.21547752792291552, "grad_norm": 1.4598636627197266, "learning_rate": 0.0001436457301367149, "loss": 0.6399173259735107, "step": 36250 }, { "epoch": 0.2155369699995839, "grad_norm": 1.6333733797073364, "learning_rate": 0.00014368535763820093, "loss": 0.6543745994567871, "step": 36260 }, { "epoch": 0.2155964120762523, "grad_norm": 1.6098028421401978, "learning_rate": 0.00014372498513968694, "loss": 0.6757334709167481, "step": 36270 }, { "epoch": 0.21565585415292068, "grad_norm": 1.6843762397766113, "learning_rate": 0.00014376461264117298, "loss": 0.6885466575622559, "step": 36280 }, { "epoch": 0.21571529622958907, "grad_norm": 1.3394466638565063, "learning_rate": 0.00014380424014265902, "loss": 0.6558760643005371, "step": 36290 }, { "epoch": 0.21577473830625746, "grad_norm": 1.4947518110275269, "learning_rate": 0.00014384386764414503, "loss": 0.6835753440856933, "step": 36300 }, { "epoch": 0.21583418038292584, "grad_norm": 1.4557983875274658, "learning_rate": 0.00014388349514563107, "loss": 0.6671810150146484, "step": 36310 }, { "epoch": 0.21589362245959426, "grad_norm": 1.723526954650879, "learning_rate": 0.0001439231226471171, "loss": 0.7212611198425293, "step": 36320 }, { "epoch": 0.21595306453626265, "grad_norm": 1.4935063123703003, "learning_rate": 0.00014396275014860315, "loss": 0.7039785385131836, "step": 36330 }, { "epoch": 0.21601250661293103, "grad_norm": 1.6877505779266357, "learning_rate": 0.00014400237765008916, "loss": 0.6517587661743164, "step": 36340 }, { "epoch": 0.21607194868959942, "grad_norm": 1.577370524406433, "learning_rate": 0.0001440420051515752, "loss": 0.6840348243713379, "step": 36350 }, { "epoch": 0.2161313907662678, "grad_norm": 1.44657301902771, "learning_rate": 0.00014408163265306124, "loss": 0.6642170906066894, "step": 36360 }, { "epoch": 0.2161908328429362, "grad_norm": 1.345176339149475, "learning_rate": 0.00014412126015454725, "loss": 0.6675479888916016, "step": 36370 }, { "epoch": 0.21625027491960458, "grad_norm": 1.457267165184021, "learning_rate": 0.0001441608876560333, "loss": 0.6745000362396241, "step": 36380 }, { "epoch": 0.216309716996273, "grad_norm": 1.7897783517837524, "learning_rate": 0.00014420051515751933, "loss": 0.6222676277160645, "step": 36390 }, { "epoch": 0.21636915907294138, "grad_norm": 1.8320683240890503, "learning_rate": 0.00014424014265900536, "loss": 0.7085086822509765, "step": 36400 }, { "epoch": 0.21642860114960977, "grad_norm": 1.4768019914627075, "learning_rate": 0.00014427977016049138, "loss": 0.7101585388183593, "step": 36410 }, { "epoch": 0.21648804322627815, "grad_norm": 1.908959984779358, "learning_rate": 0.00014431939766197742, "loss": 0.6657592296600342, "step": 36420 }, { "epoch": 0.21654748530294654, "grad_norm": 1.1781384944915771, "learning_rate": 0.00014435902516346345, "loss": 0.6699389457702637, "step": 36430 }, { "epoch": 0.21660692737961493, "grad_norm": 1.261493444442749, "learning_rate": 0.00014439865266494947, "loss": 0.6747193336486816, "step": 36440 }, { "epoch": 0.21666636945628331, "grad_norm": 1.9333453178405762, "learning_rate": 0.0001444382801664355, "loss": 0.6872812271118164, "step": 36450 }, { "epoch": 0.21672581153295173, "grad_norm": 1.731394648551941, "learning_rate": 0.00014447790766792154, "loss": 0.6793460845947266, "step": 36460 }, { "epoch": 0.21678525360962012, "grad_norm": 1.6198712587356567, "learning_rate": 0.00014451753516940758, "loss": 0.6196921348571778, "step": 36470 }, { "epoch": 0.2168446956862885, "grad_norm": 1.3863787651062012, "learning_rate": 0.00014455716267089362, "loss": 0.694405460357666, "step": 36480 }, { "epoch": 0.2169041377629569, "grad_norm": 1.4471274614334106, "learning_rate": 0.00014459679017237963, "loss": 0.7388469696044921, "step": 36490 }, { "epoch": 0.21696357983962528, "grad_norm": 1.6838207244873047, "learning_rate": 0.00014463641767386567, "loss": 0.7101585388183593, "step": 36500 }, { "epoch": 0.21702302191629366, "grad_norm": 1.4625707864761353, "learning_rate": 0.00014467604517535168, "loss": 0.6806539535522461, "step": 36510 }, { "epoch": 0.21708246399296205, "grad_norm": 1.463187336921692, "learning_rate": 0.00014471567267683772, "loss": 0.6018112659454345, "step": 36520 }, { "epoch": 0.21714190606963044, "grad_norm": 1.6336338520050049, "learning_rate": 0.00014475530017832376, "loss": 0.6376298904418946, "step": 36530 }, { "epoch": 0.21720134814629885, "grad_norm": 1.7317049503326416, "learning_rate": 0.0001447949276798098, "loss": 0.6514825820922852, "step": 36540 }, { "epoch": 0.21726079022296724, "grad_norm": 1.5290131568908691, "learning_rate": 0.00014483455518129584, "loss": 0.7146520614624023, "step": 36550 }, { "epoch": 0.21732023229963562, "grad_norm": 1.782766342163086, "learning_rate": 0.00014487418268278185, "loss": 0.6742453575134277, "step": 36560 }, { "epoch": 0.217379674376304, "grad_norm": 1.357536792755127, "learning_rate": 0.00014491381018426789, "loss": 0.6988467216491699, "step": 36570 }, { "epoch": 0.2174391164529724, "grad_norm": 1.642913579940796, "learning_rate": 0.00014495343768575393, "loss": 0.6428268909454345, "step": 36580 }, { "epoch": 0.21749855852964078, "grad_norm": 1.6883991956710815, "learning_rate": 0.00014499306518723994, "loss": 0.6863170146942139, "step": 36590 }, { "epoch": 0.21755800060630917, "grad_norm": 1.489848256111145, "learning_rate": 0.000145032692688726, "loss": 0.733034896850586, "step": 36600 }, { "epoch": 0.21761744268297759, "grad_norm": 1.4097028970718384, "learning_rate": 0.00014507232019021201, "loss": 0.6849372386932373, "step": 36610 }, { "epoch": 0.21767688475964597, "grad_norm": 1.8217105865478516, "learning_rate": 0.00014511194769169805, "loss": 0.6343606948852539, "step": 36620 }, { "epoch": 0.21773632683631436, "grad_norm": 1.4175751209259033, "learning_rate": 0.00014515157519318406, "loss": 0.667177963256836, "step": 36630 }, { "epoch": 0.21779576891298275, "grad_norm": 1.4802650213241577, "learning_rate": 0.0001451912026946701, "loss": 0.7073911190032959, "step": 36640 }, { "epoch": 0.21785521098965113, "grad_norm": 1.385864496231079, "learning_rate": 0.00014523083019615614, "loss": 0.6855290412902832, "step": 36650 }, { "epoch": 0.21791465306631952, "grad_norm": 1.9918845891952515, "learning_rate": 0.00014527045769764218, "loss": 0.6926260948181152, "step": 36660 }, { "epoch": 0.2179740951429879, "grad_norm": 1.7384579181671143, "learning_rate": 0.00014531008519912822, "loss": 0.7143351554870605, "step": 36670 }, { "epoch": 0.2180335372196563, "grad_norm": 1.8008863925933838, "learning_rate": 0.00014534971270061423, "loss": 0.7522966384887695, "step": 36680 }, { "epoch": 0.2180929792963247, "grad_norm": 1.4606925249099731, "learning_rate": 0.00014538934020210027, "loss": 0.6646228790283203, "step": 36690 }, { "epoch": 0.2181524213729931, "grad_norm": 1.4664756059646606, "learning_rate": 0.0001454289677035863, "loss": 0.656130599975586, "step": 36700 }, { "epoch": 0.21821186344966148, "grad_norm": 1.3598350286483765, "learning_rate": 0.00014546859520507232, "loss": 0.6822375297546387, "step": 36710 }, { "epoch": 0.21827130552632987, "grad_norm": 1.7098404169082642, "learning_rate": 0.00014550822270655836, "loss": 0.7016615867614746, "step": 36720 }, { "epoch": 0.21833074760299825, "grad_norm": 1.5321587324142456, "learning_rate": 0.0001455478502080444, "loss": 0.6006672859191895, "step": 36730 }, { "epoch": 0.21839018967966664, "grad_norm": 1.4350963830947876, "learning_rate": 0.00014558747770953044, "loss": 0.6890401363372802, "step": 36740 }, { "epoch": 0.21844963175633503, "grad_norm": 1.4165537357330322, "learning_rate": 0.00014562710521101645, "loss": 0.6662033081054688, "step": 36750 }, { "epoch": 0.21850907383300344, "grad_norm": 1.5768731832504272, "learning_rate": 0.00014566673271250249, "loss": 0.6576522350311279, "step": 36760 }, { "epoch": 0.21856851590967183, "grad_norm": 1.8519864082336426, "learning_rate": 0.00014570636021398852, "loss": 0.6580967903137207, "step": 36770 }, { "epoch": 0.21862795798634022, "grad_norm": 1.7215096950531006, "learning_rate": 0.00014574598771547454, "loss": 0.6915621757507324, "step": 36780 }, { "epoch": 0.2186874000630086, "grad_norm": 1.9065889120101929, "learning_rate": 0.00014578561521696057, "loss": 0.5956060409545898, "step": 36790 }, { "epoch": 0.218746842139677, "grad_norm": 1.4944710731506348, "learning_rate": 0.0001458252427184466, "loss": 0.6788215637207031, "step": 36800 }, { "epoch": 0.21880628421634538, "grad_norm": 1.5496896505355835, "learning_rate": 0.00014586487021993265, "loss": 0.7091371536254882, "step": 36810 }, { "epoch": 0.21886572629301376, "grad_norm": 1.5613821744918823, "learning_rate": 0.00014590449772141866, "loss": 0.6804537773132324, "step": 36820 }, { "epoch": 0.21892516836968218, "grad_norm": 1.7662757635116577, "learning_rate": 0.0001459441252229047, "loss": 0.6895618438720703, "step": 36830 }, { "epoch": 0.21898461044635056, "grad_norm": 1.461382269859314, "learning_rate": 0.00014598375272439074, "loss": 0.6411566734313965, "step": 36840 }, { "epoch": 0.21904405252301895, "grad_norm": 1.587158203125, "learning_rate": 0.00014602338022587675, "loss": 0.6606593132019043, "step": 36850 }, { "epoch": 0.21910349459968734, "grad_norm": 1.4347583055496216, "learning_rate": 0.0001460630077273628, "loss": 0.7010118961334229, "step": 36860 }, { "epoch": 0.21916293667635572, "grad_norm": 1.6447808742523193, "learning_rate": 0.00014610263522884883, "loss": 0.6368882656097412, "step": 36870 }, { "epoch": 0.2192223787530241, "grad_norm": 1.800669550895691, "learning_rate": 0.00014614226273033487, "loss": 0.6654469490051269, "step": 36880 }, { "epoch": 0.2192818208296925, "grad_norm": 1.6938914060592651, "learning_rate": 0.0001461818902318209, "loss": 0.6829202175140381, "step": 36890 }, { "epoch": 0.21934126290636088, "grad_norm": 2.1352858543395996, "learning_rate": 0.00014622151773330692, "loss": 0.6906692504882812, "step": 36900 }, { "epoch": 0.2194007049830293, "grad_norm": 1.3158780336380005, "learning_rate": 0.00014626114523479296, "loss": 0.6645002841949463, "step": 36910 }, { "epoch": 0.21946014705969769, "grad_norm": 1.6465867757797241, "learning_rate": 0.00014630077273627897, "loss": 0.6601101398468018, "step": 36920 }, { "epoch": 0.21951958913636607, "grad_norm": 1.7160691022872925, "learning_rate": 0.000146340400237765, "loss": 0.6390798568725586, "step": 36930 }, { "epoch": 0.21957903121303446, "grad_norm": 1.5521355867385864, "learning_rate": 0.00014638002773925105, "loss": 0.6353696346282959, "step": 36940 }, { "epoch": 0.21963847328970285, "grad_norm": 1.4708061218261719, "learning_rate": 0.00014641965524073708, "loss": 0.6415601253509522, "step": 36950 }, { "epoch": 0.21969791536637123, "grad_norm": 1.4854214191436768, "learning_rate": 0.00014645928274222312, "loss": 0.6490708827972412, "step": 36960 }, { "epoch": 0.21975735744303962, "grad_norm": 1.8321856260299683, "learning_rate": 0.00014649891024370913, "loss": 0.6361157894134521, "step": 36970 }, { "epoch": 0.21981679951970803, "grad_norm": 1.4426190853118896, "learning_rate": 0.00014653853774519517, "loss": 0.6130015850067139, "step": 36980 }, { "epoch": 0.21987624159637642, "grad_norm": 1.8061065673828125, "learning_rate": 0.0001465781652466812, "loss": 0.6734183311462403, "step": 36990 }, { "epoch": 0.2199356836730448, "grad_norm": 1.6969572305679321, "learning_rate": 0.00014661779274816722, "loss": 0.7355701446533203, "step": 37000 }, { "epoch": 0.2199951257497132, "grad_norm": 1.563952922821045, "learning_rate": 0.0001466574202496533, "loss": 0.7067251682281495, "step": 37010 }, { "epoch": 0.22005456782638158, "grad_norm": 2.1532654762268066, "learning_rate": 0.0001466970477511393, "loss": 0.6886187076568604, "step": 37020 }, { "epoch": 0.22011400990304997, "grad_norm": 1.6605170965194702, "learning_rate": 0.00014673667525262534, "loss": 0.6786626815795899, "step": 37030 }, { "epoch": 0.22017345197971835, "grad_norm": 1.803204894065857, "learning_rate": 0.00014677630275411135, "loss": 0.6151965618133545, "step": 37040 }, { "epoch": 0.22023289405638674, "grad_norm": 1.6305848360061646, "learning_rate": 0.0001468159302555974, "loss": 0.6457369804382325, "step": 37050 }, { "epoch": 0.22029233613305516, "grad_norm": 1.4768985509872437, "learning_rate": 0.00014685555775708343, "loss": 0.6562589168548584, "step": 37060 }, { "epoch": 0.22035177820972354, "grad_norm": 1.2903248071670532, "learning_rate": 0.00014689518525856944, "loss": 0.6347977638244628, "step": 37070 }, { "epoch": 0.22041122028639193, "grad_norm": 1.6312236785888672, "learning_rate": 0.0001469348127600555, "loss": 0.6903066635131836, "step": 37080 }, { "epoch": 0.22047066236306032, "grad_norm": 1.572497010231018, "learning_rate": 0.00014697444026154152, "loss": 0.6892114639282226, "step": 37090 }, { "epoch": 0.2205301044397287, "grad_norm": 1.5967988967895508, "learning_rate": 0.00014701406776302756, "loss": 0.664889144897461, "step": 37100 }, { "epoch": 0.2205895465163971, "grad_norm": 1.9496800899505615, "learning_rate": 0.00014705369526451357, "loss": 0.6660676002502441, "step": 37110 }, { "epoch": 0.22064898859306548, "grad_norm": 1.750059962272644, "learning_rate": 0.0001470933227659996, "loss": 0.6249685287475586, "step": 37120 }, { "epoch": 0.2207084306697339, "grad_norm": 1.5762203931808472, "learning_rate": 0.00014713295026748564, "loss": 0.6370333671569824, "step": 37130 }, { "epoch": 0.22076787274640228, "grad_norm": 1.4430525302886963, "learning_rate": 0.00014717257776897166, "loss": 0.7347354888916016, "step": 37140 }, { "epoch": 0.22082731482307066, "grad_norm": 1.6877325773239136, "learning_rate": 0.00014721220527045772, "loss": 0.6770526885986328, "step": 37150 }, { "epoch": 0.22088675689973905, "grad_norm": 1.8204656839370728, "learning_rate": 0.00014725183277194373, "loss": 0.6589102745056152, "step": 37160 }, { "epoch": 0.22094619897640744, "grad_norm": 1.6224321126937866, "learning_rate": 0.00014729146027342977, "loss": 0.6250736236572265, "step": 37170 }, { "epoch": 0.22100564105307582, "grad_norm": 1.653974175453186, "learning_rate": 0.0001473310877749158, "loss": 0.6801835060119629, "step": 37180 }, { "epoch": 0.2210650831297442, "grad_norm": 1.192893147468567, "learning_rate": 0.00014737071527640182, "loss": 0.6640882968902588, "step": 37190 }, { "epoch": 0.2211245252064126, "grad_norm": 1.5753828287124634, "learning_rate": 0.00014741034277788786, "loss": 0.6891857624053955, "step": 37200 }, { "epoch": 0.221183967283081, "grad_norm": 1.338059425354004, "learning_rate": 0.00014744997027937387, "loss": 0.7105945587158203, "step": 37210 }, { "epoch": 0.2212434093597494, "grad_norm": 1.5255212783813477, "learning_rate": 0.00014748959778085994, "loss": 0.6412143707275391, "step": 37220 }, { "epoch": 0.22130285143641779, "grad_norm": 1.5513243675231934, "learning_rate": 0.00014752922528234595, "loss": 0.6768990516662597, "step": 37230 }, { "epoch": 0.22136229351308617, "grad_norm": 1.5881372690200806, "learning_rate": 0.000147568852783832, "loss": 0.7305578231811524, "step": 37240 }, { "epoch": 0.22142173558975456, "grad_norm": 1.5507382154464722, "learning_rate": 0.00014760848028531803, "loss": 0.6219381332397461, "step": 37250 }, { "epoch": 0.22148117766642295, "grad_norm": 1.75978422164917, "learning_rate": 0.00014764810778680404, "loss": 0.7765556335449219, "step": 37260 }, { "epoch": 0.22154061974309133, "grad_norm": 1.5087738037109375, "learning_rate": 0.00014768773528829008, "loss": 0.6398252964019775, "step": 37270 }, { "epoch": 0.22160006181975975, "grad_norm": 1.308467984199524, "learning_rate": 0.00014772736278977612, "loss": 0.6197863578796386, "step": 37280 }, { "epoch": 0.22165950389642813, "grad_norm": 2.5305519104003906, "learning_rate": 0.00014776699029126215, "loss": 0.6742228507995606, "step": 37290 }, { "epoch": 0.22171894597309652, "grad_norm": 1.3511677980422974, "learning_rate": 0.0001478066177927482, "loss": 0.6213901519775391, "step": 37300 }, { "epoch": 0.2217783880497649, "grad_norm": 1.7402727603912354, "learning_rate": 0.0001478462452942342, "loss": 0.709979248046875, "step": 37310 }, { "epoch": 0.2218378301264333, "grad_norm": 1.3502169847488403, "learning_rate": 0.00014788587279572024, "loss": 0.668798828125, "step": 37320 }, { "epoch": 0.22189727220310168, "grad_norm": 1.5791988372802734, "learning_rate": 0.00014792550029720625, "loss": 0.615750789642334, "step": 37330 }, { "epoch": 0.22195671427977007, "grad_norm": 1.5442298650741577, "learning_rate": 0.0001479651277986923, "loss": 0.687094783782959, "step": 37340 }, { "epoch": 0.22201615635643848, "grad_norm": 1.645839810371399, "learning_rate": 0.00014800475530017833, "loss": 0.6901976585388183, "step": 37350 }, { "epoch": 0.22207559843310687, "grad_norm": 1.358639121055603, "learning_rate": 0.00014804438280166437, "loss": 0.7010281562805176, "step": 37360 }, { "epoch": 0.22213504050977526, "grad_norm": 1.5926412343978882, "learning_rate": 0.0001480840103031504, "loss": 0.6835317611694336, "step": 37370 }, { "epoch": 0.22219448258644364, "grad_norm": 1.4527626037597656, "learning_rate": 0.00014812363780463642, "loss": 0.7368188381195069, "step": 37380 }, { "epoch": 0.22225392466311203, "grad_norm": 1.9566973447799683, "learning_rate": 0.00014816326530612246, "loss": 0.6932677745819091, "step": 37390 }, { "epoch": 0.22231336673978042, "grad_norm": 1.8851128816604614, "learning_rate": 0.00014820289280760847, "loss": 0.6729813575744629, "step": 37400 }, { "epoch": 0.2223728088164488, "grad_norm": 1.4806069135665894, "learning_rate": 0.0001482425203090945, "loss": 0.6328399658203125, "step": 37410 }, { "epoch": 0.2224322508931172, "grad_norm": 1.839089035987854, "learning_rate": 0.00014828214781058055, "loss": 0.6505178451538086, "step": 37420 }, { "epoch": 0.2224916929697856, "grad_norm": 1.8272511959075928, "learning_rate": 0.0001483217753120666, "loss": 0.7160781860351563, "step": 37430 }, { "epoch": 0.222551135046454, "grad_norm": 1.4553557634353638, "learning_rate": 0.00014836140281355263, "loss": 0.6306935310363769, "step": 37440 }, { "epoch": 0.22261057712312238, "grad_norm": 1.295028805732727, "learning_rate": 0.00014840103031503864, "loss": 0.6812994003295898, "step": 37450 }, { "epoch": 0.22267001919979076, "grad_norm": 1.6940945386886597, "learning_rate": 0.00014844065781652468, "loss": 0.7173133850097656, "step": 37460 }, { "epoch": 0.22272946127645915, "grad_norm": 1.7650028467178345, "learning_rate": 0.00014848028531801071, "loss": 0.7280593872070312, "step": 37470 }, { "epoch": 0.22278890335312754, "grad_norm": 1.5177407264709473, "learning_rate": 0.00014851991281949673, "loss": 0.6802216529846191, "step": 37480 }, { "epoch": 0.22284834542979592, "grad_norm": 1.7139949798583984, "learning_rate": 0.00014855954032098277, "loss": 0.5953296184539795, "step": 37490 }, { "epoch": 0.22290778750646434, "grad_norm": 1.7004671096801758, "learning_rate": 0.0001485991678224688, "loss": 0.653584098815918, "step": 37500 }, { "epoch": 0.22296722958313273, "grad_norm": 1.3332947492599487, "learning_rate": 0.00014863879532395484, "loss": 0.6711219310760498, "step": 37510 }, { "epoch": 0.2230266716598011, "grad_norm": 1.426655650138855, "learning_rate": 0.00014867842282544085, "loss": 0.7169287204742432, "step": 37520 }, { "epoch": 0.2230861137364695, "grad_norm": 1.6237404346466064, "learning_rate": 0.0001487180503269269, "loss": 0.6791540145874023, "step": 37530 }, { "epoch": 0.22314555581313789, "grad_norm": 1.5183265209197998, "learning_rate": 0.00014875767782841293, "loss": 0.728396987915039, "step": 37540 }, { "epoch": 0.22320499788980627, "grad_norm": 1.465804100036621, "learning_rate": 0.00014879730532989894, "loss": 0.6670393943786621, "step": 37550 }, { "epoch": 0.22326443996647466, "grad_norm": 2.179409980773926, "learning_rate": 0.00014883693283138498, "loss": 0.6344407081604004, "step": 37560 }, { "epoch": 0.22332388204314305, "grad_norm": 1.3051317930221558, "learning_rate": 0.00014887656033287102, "loss": 0.7380099296569824, "step": 37570 }, { "epoch": 0.22338332411981146, "grad_norm": 1.6212754249572754, "learning_rate": 0.00014891618783435706, "loss": 0.6600900650024414, "step": 37580 }, { "epoch": 0.22344276619647985, "grad_norm": 1.4804844856262207, "learning_rate": 0.0001489558153358431, "loss": 0.6825152397155761, "step": 37590 }, { "epoch": 0.22350220827314823, "grad_norm": 1.7947043180465698, "learning_rate": 0.0001489954428373291, "loss": 0.6740998268127442, "step": 37600 }, { "epoch": 0.22356165034981662, "grad_norm": 1.5513285398483276, "learning_rate": 0.00014903507033881515, "loss": 0.748861026763916, "step": 37610 }, { "epoch": 0.223621092426485, "grad_norm": 1.4994745254516602, "learning_rate": 0.00014907469784030116, "loss": 0.6821901321411132, "step": 37620 }, { "epoch": 0.2236805345031534, "grad_norm": 1.4761937856674194, "learning_rate": 0.0001491143253417872, "loss": 0.7175972938537598, "step": 37630 }, { "epoch": 0.22373997657982178, "grad_norm": 1.3746551275253296, "learning_rate": 0.00014915395284327324, "loss": 0.6454115867614746, "step": 37640 }, { "epoch": 0.2237994186564902, "grad_norm": 1.5382601022720337, "learning_rate": 0.00014919358034475928, "loss": 0.7229322910308837, "step": 37650 }, { "epoch": 0.22385886073315858, "grad_norm": 1.8546801805496216, "learning_rate": 0.00014923320784624531, "loss": 0.6979408264160156, "step": 37660 }, { "epoch": 0.22391830280982697, "grad_norm": 1.389683723449707, "learning_rate": 0.00014927283534773133, "loss": 0.6510893821716308, "step": 37670 }, { "epoch": 0.22397774488649536, "grad_norm": 1.9905937910079956, "learning_rate": 0.00014931246284921736, "loss": 0.6913351058959961, "step": 37680 }, { "epoch": 0.22403718696316374, "grad_norm": 1.1669217348098755, "learning_rate": 0.00014935209035070338, "loss": 0.6443522453308106, "step": 37690 }, { "epoch": 0.22409662903983213, "grad_norm": 1.686829924583435, "learning_rate": 0.00014939171785218941, "loss": 0.6969172954559326, "step": 37700 }, { "epoch": 0.22415607111650052, "grad_norm": 2.474358081817627, "learning_rate": 0.00014943134535367548, "loss": 0.6719741821289062, "step": 37710 }, { "epoch": 0.2242155131931689, "grad_norm": 1.4263912439346313, "learning_rate": 0.0001494709728551615, "loss": 0.6520044803619385, "step": 37720 }, { "epoch": 0.22427495526983732, "grad_norm": 1.660598874092102, "learning_rate": 0.00014951060035664753, "loss": 0.7329761505126953, "step": 37730 }, { "epoch": 0.2243343973465057, "grad_norm": 1.9343960285186768, "learning_rate": 0.00014955022785813354, "loss": 0.6966112136840821, "step": 37740 }, { "epoch": 0.2243938394231741, "grad_norm": 1.6381398439407349, "learning_rate": 0.00014958985535961958, "loss": 0.7385366439819336, "step": 37750 }, { "epoch": 0.22445328149984248, "grad_norm": 1.9725013971328735, "learning_rate": 0.00014962948286110562, "loss": 0.718361759185791, "step": 37760 }, { "epoch": 0.22451272357651086, "grad_norm": 1.856218934059143, "learning_rate": 0.00014966911036259163, "loss": 0.6593082427978516, "step": 37770 }, { "epoch": 0.22457216565317925, "grad_norm": 1.6738317012786865, "learning_rate": 0.0001497087378640777, "loss": 0.6629117012023926, "step": 37780 }, { "epoch": 0.22463160772984764, "grad_norm": 1.304073452949524, "learning_rate": 0.0001497483653655637, "loss": 0.6687235355377197, "step": 37790 }, { "epoch": 0.22469104980651605, "grad_norm": 1.5076426267623901, "learning_rate": 0.00014978799286704975, "loss": 0.6455477237701416, "step": 37800 }, { "epoch": 0.22475049188318444, "grad_norm": 1.5216282606124878, "learning_rate": 0.00014982762036853576, "loss": 0.6615736961364747, "step": 37810 }, { "epoch": 0.22480993395985283, "grad_norm": 1.473132610321045, "learning_rate": 0.0001498672478700218, "loss": 0.6116308689117431, "step": 37820 }, { "epoch": 0.2248693760365212, "grad_norm": 1.8690965175628662, "learning_rate": 0.00014990687537150784, "loss": 0.6786859512329102, "step": 37830 }, { "epoch": 0.2249288181131896, "grad_norm": 1.8125343322753906, "learning_rate": 0.00014994650287299385, "loss": 0.6768482685089111, "step": 37840 }, { "epoch": 0.22498826018985799, "grad_norm": 1.5641437768936157, "learning_rate": 0.0001499861303744799, "loss": 0.6771528244018554, "step": 37850 }, { "epoch": 0.22504770226652637, "grad_norm": 1.6628552675247192, "learning_rate": 0.00015002575787596592, "loss": 0.6624777793884278, "step": 37860 }, { "epoch": 0.2251071443431948, "grad_norm": 1.6478272676467896, "learning_rate": 0.00015006538537745196, "loss": 0.7093654632568359, "step": 37870 }, { "epoch": 0.22516658641986317, "grad_norm": 1.536096215248108, "learning_rate": 0.000150105012878938, "loss": 0.6468539714813233, "step": 37880 }, { "epoch": 0.22522602849653156, "grad_norm": 1.6188294887542725, "learning_rate": 0.000150144640380424, "loss": 0.6900421142578125, "step": 37890 }, { "epoch": 0.22528547057319995, "grad_norm": 2.089458703994751, "learning_rate": 0.00015018426788191005, "loss": 0.7280259132385254, "step": 37900 }, { "epoch": 0.22534491264986833, "grad_norm": 1.357682704925537, "learning_rate": 0.00015022389538339606, "loss": 0.6580936431884765, "step": 37910 }, { "epoch": 0.22540435472653672, "grad_norm": 1.4035166501998901, "learning_rate": 0.00015026352288488213, "loss": 0.6258116722106933, "step": 37920 }, { "epoch": 0.2254637968032051, "grad_norm": 1.472935676574707, "learning_rate": 0.00015030315038636814, "loss": 0.6448787689208985, "step": 37930 }, { "epoch": 0.2255232388798735, "grad_norm": 1.3020009994506836, "learning_rate": 0.00015034277788785418, "loss": 0.6649380683898926, "step": 37940 }, { "epoch": 0.2255826809565419, "grad_norm": 1.5247514247894287, "learning_rate": 0.00015038240538934022, "loss": 0.7125326156616211, "step": 37950 }, { "epoch": 0.2256421230332103, "grad_norm": 1.672127366065979, "learning_rate": 0.00015042203289082623, "loss": 0.6372371673583984, "step": 37960 }, { "epoch": 0.22570156510987868, "grad_norm": 1.6005654335021973, "learning_rate": 0.00015046166039231227, "loss": 0.6583389282226563, "step": 37970 }, { "epoch": 0.22576100718654707, "grad_norm": 1.5704374313354492, "learning_rate": 0.00015050128789379828, "loss": 0.6719916343688965, "step": 37980 }, { "epoch": 0.22582044926321546, "grad_norm": 1.5402840375900269, "learning_rate": 0.00015054091539528435, "loss": 0.6037700176239014, "step": 37990 }, { "epoch": 0.22587989133988384, "grad_norm": 1.451625943183899, "learning_rate": 0.00015058054289677038, "loss": 0.6659879684448242, "step": 38000 }, { "epoch": 0.22593933341655223, "grad_norm": 1.9842286109924316, "learning_rate": 0.0001506201703982564, "loss": 0.6569616317749023, "step": 38010 }, { "epoch": 0.22599877549322064, "grad_norm": 1.6217414140701294, "learning_rate": 0.00015065979789974243, "loss": 0.7270676136016846, "step": 38020 }, { "epoch": 0.22605821756988903, "grad_norm": 1.7645584344863892, "learning_rate": 0.00015069942540122845, "loss": 0.6865657806396485, "step": 38030 }, { "epoch": 0.22611765964655742, "grad_norm": 1.3355292081832886, "learning_rate": 0.00015073905290271448, "loss": 0.6824997425079345, "step": 38040 }, { "epoch": 0.2261771017232258, "grad_norm": 1.3906269073486328, "learning_rate": 0.00015077868040420052, "loss": 0.6566072940826416, "step": 38050 }, { "epoch": 0.2262365437998942, "grad_norm": 1.7048004865646362, "learning_rate": 0.00015081830790568656, "loss": 0.7214820861816407, "step": 38060 }, { "epoch": 0.22629598587656258, "grad_norm": 1.502895712852478, "learning_rate": 0.0001508579354071726, "loss": 0.7441408157348632, "step": 38070 }, { "epoch": 0.22635542795323096, "grad_norm": 1.5982375144958496, "learning_rate": 0.0001508975629086586, "loss": 0.6689726829528808, "step": 38080 }, { "epoch": 0.22641487002989935, "grad_norm": 1.4695799350738525, "learning_rate": 0.00015093719041014465, "loss": 0.6791655063629151, "step": 38090 }, { "epoch": 0.22647431210656777, "grad_norm": 1.5026780366897583, "learning_rate": 0.00015097681791163066, "loss": 0.696117353439331, "step": 38100 }, { "epoch": 0.22653375418323615, "grad_norm": 1.6454750299453735, "learning_rate": 0.0001510164454131167, "loss": 0.665866470336914, "step": 38110 }, { "epoch": 0.22659319625990454, "grad_norm": 1.2221475839614868, "learning_rate": 0.00015105607291460274, "loss": 0.6883141040802002, "step": 38120 }, { "epoch": 0.22665263833657293, "grad_norm": 1.497984528541565, "learning_rate": 0.00015109570041608878, "loss": 0.6957264900207519, "step": 38130 }, { "epoch": 0.2267120804132413, "grad_norm": 1.3289040327072144, "learning_rate": 0.00015113532791757482, "loss": 0.6314079284667968, "step": 38140 }, { "epoch": 0.2267715224899097, "grad_norm": 1.3393465280532837, "learning_rate": 0.00015117495541906083, "loss": 0.6545961380004883, "step": 38150 }, { "epoch": 0.22683096456657809, "grad_norm": 1.5894861221313477, "learning_rate": 0.00015121458292054687, "loss": 0.6693684577941894, "step": 38160 }, { "epoch": 0.2268904066432465, "grad_norm": 1.6628823280334473, "learning_rate": 0.0001512542104220329, "loss": 0.6351138114929199, "step": 38170 }, { "epoch": 0.2269498487199149, "grad_norm": 1.5051038265228271, "learning_rate": 0.00015129383792351892, "loss": 0.6883157253265381, "step": 38180 }, { "epoch": 0.22700929079658327, "grad_norm": 1.6302635669708252, "learning_rate": 0.00015133346542500496, "loss": 0.6663541793823242, "step": 38190 }, { "epoch": 0.22706873287325166, "grad_norm": 1.3057502508163452, "learning_rate": 0.000151373092926491, "loss": 0.6697423934936524, "step": 38200 }, { "epoch": 0.22712817494992005, "grad_norm": 1.7745507955551147, "learning_rate": 0.00015141272042797703, "loss": 0.6429577827453613, "step": 38210 }, { "epoch": 0.22718761702658843, "grad_norm": 1.6493315696716309, "learning_rate": 0.00015145234792946304, "loss": 0.6685976028442383, "step": 38220 }, { "epoch": 0.22724705910325682, "grad_norm": 1.9128707647323608, "learning_rate": 0.00015149197543094908, "loss": 0.7161437034606933, "step": 38230 }, { "epoch": 0.22730650117992524, "grad_norm": 1.3450024127960205, "learning_rate": 0.00015153160293243512, "loss": 0.6405267715454102, "step": 38240 }, { "epoch": 0.22736594325659362, "grad_norm": 1.481974482536316, "learning_rate": 0.00015157123043392113, "loss": 0.7181758403778076, "step": 38250 }, { "epoch": 0.227425385333262, "grad_norm": 1.6216081380844116, "learning_rate": 0.00015161085793540717, "loss": 0.6834629535675049, "step": 38260 }, { "epoch": 0.2274848274099304, "grad_norm": 1.587910771369934, "learning_rate": 0.0001516504854368932, "loss": 0.6710782051086426, "step": 38270 }, { "epoch": 0.22754426948659878, "grad_norm": 1.3854061365127563, "learning_rate": 0.00015169011293837925, "loss": 0.6665787696838379, "step": 38280 }, { "epoch": 0.22760371156326717, "grad_norm": 1.7279075384140015, "learning_rate": 0.0001517297404398653, "loss": 0.6924398422241211, "step": 38290 }, { "epoch": 0.22766315363993556, "grad_norm": 1.3271409273147583, "learning_rate": 0.0001517693679413513, "loss": 0.7126784324645996, "step": 38300 }, { "epoch": 0.22772259571660394, "grad_norm": 1.5024056434631348, "learning_rate": 0.00015180899544283734, "loss": 0.6805161476135254, "step": 38310 }, { "epoch": 0.22778203779327236, "grad_norm": 1.5262024402618408, "learning_rate": 0.00015184862294432335, "loss": 0.65906982421875, "step": 38320 }, { "epoch": 0.22784147986994074, "grad_norm": 1.5826388597488403, "learning_rate": 0.0001518882504458094, "loss": 0.6782437324523926, "step": 38330 }, { "epoch": 0.22790092194660913, "grad_norm": 1.5928360223770142, "learning_rate": 0.00015192787794729543, "loss": 0.6819852352142334, "step": 38340 }, { "epoch": 0.22796036402327752, "grad_norm": 1.6456594467163086, "learning_rate": 0.00015196750544878147, "loss": 0.6984564781188964, "step": 38350 }, { "epoch": 0.2280198060999459, "grad_norm": 1.3396207094192505, "learning_rate": 0.0001520071329502675, "loss": 0.6569963455200195, "step": 38360 }, { "epoch": 0.2280792481766143, "grad_norm": 1.6704264879226685, "learning_rate": 0.00015204676045175352, "loss": 0.6852879524230957, "step": 38370 }, { "epoch": 0.22813869025328268, "grad_norm": 1.8786003589630127, "learning_rate": 0.00015208638795323955, "loss": 0.672475528717041, "step": 38380 }, { "epoch": 0.2281981323299511, "grad_norm": 1.3569767475128174, "learning_rate": 0.00015212601545472557, "loss": 0.6668231010437011, "step": 38390 }, { "epoch": 0.22825757440661948, "grad_norm": 1.7328404188156128, "learning_rate": 0.00015216564295621163, "loss": 0.6209471702575684, "step": 38400 }, { "epoch": 0.22831701648328787, "grad_norm": 1.556528091430664, "learning_rate": 0.00015220527045769767, "loss": 0.6354327201843262, "step": 38410 }, { "epoch": 0.22837645855995625, "grad_norm": 1.6351372003555298, "learning_rate": 0.00015224489795918368, "loss": 0.6832485198974609, "step": 38420 }, { "epoch": 0.22843590063662464, "grad_norm": 1.5631343126296997, "learning_rate": 0.00015228452546066972, "loss": 0.6482029914855957, "step": 38430 }, { "epoch": 0.22849534271329303, "grad_norm": 1.9210317134857178, "learning_rate": 0.00015232415296215573, "loss": 0.718500804901123, "step": 38440 }, { "epoch": 0.2285547847899614, "grad_norm": 1.3062257766723633, "learning_rate": 0.00015236378046364177, "loss": 0.7055724143981934, "step": 38450 }, { "epoch": 0.2286142268666298, "grad_norm": 1.4110852479934692, "learning_rate": 0.0001524034079651278, "loss": 0.6372306823730469, "step": 38460 }, { "epoch": 0.22867366894329821, "grad_norm": 1.3723617792129517, "learning_rate": 0.00015244303546661385, "loss": 0.6409308433532714, "step": 38470 }, { "epoch": 0.2287331110199666, "grad_norm": 1.5271503925323486, "learning_rate": 0.0001524826629680999, "loss": 0.7339484214782714, "step": 38480 }, { "epoch": 0.228792553096635, "grad_norm": 1.6312901973724365, "learning_rate": 0.0001525222904695859, "loss": 0.7139074325561523, "step": 38490 }, { "epoch": 0.22885199517330337, "grad_norm": 1.650865912437439, "learning_rate": 0.00015256191797107194, "loss": 0.6922972202301025, "step": 38500 }, { "epoch": 0.22891143724997176, "grad_norm": 1.929707646369934, "learning_rate": 0.00015260154547255795, "loss": 0.6846067428588867, "step": 38510 }, { "epoch": 0.22897087932664015, "grad_norm": 1.4652745723724365, "learning_rate": 0.000152641172974044, "loss": 0.7115134716033935, "step": 38520 }, { "epoch": 0.22903032140330853, "grad_norm": 1.6657555103302002, "learning_rate": 0.00015268080047553003, "loss": 0.664608383178711, "step": 38530 }, { "epoch": 0.22908976347997695, "grad_norm": 1.3820381164550781, "learning_rate": 0.00015272042797701606, "loss": 0.6606718063354492, "step": 38540 }, { "epoch": 0.22914920555664534, "grad_norm": 1.3057454824447632, "learning_rate": 0.0001527600554785021, "loss": 0.650663948059082, "step": 38550 }, { "epoch": 0.22920864763331372, "grad_norm": 1.7018260955810547, "learning_rate": 0.00015279968297998812, "loss": 0.6565551280975341, "step": 38560 }, { "epoch": 0.2292680897099821, "grad_norm": 1.8781840801239014, "learning_rate": 0.00015283931048147415, "loss": 0.6829882144927979, "step": 38570 }, { "epoch": 0.2293275317866505, "grad_norm": 1.5278584957122803, "learning_rate": 0.0001528789379829602, "loss": 0.6591748237609864, "step": 38580 }, { "epoch": 0.22938697386331888, "grad_norm": 1.6205990314483643, "learning_rate": 0.0001529185654844462, "loss": 0.6720058441162109, "step": 38590 }, { "epoch": 0.22944641593998727, "grad_norm": 1.5868146419525146, "learning_rate": 0.00015295819298593224, "loss": 0.7617998123168945, "step": 38600 }, { "epoch": 0.22950585801665566, "grad_norm": 1.4525607824325562, "learning_rate": 0.00015299782048741828, "loss": 0.6597613334655762, "step": 38610 }, { "epoch": 0.22956530009332407, "grad_norm": 1.6251300573349, "learning_rate": 0.00015303744798890432, "loss": 0.6770209312438965, "step": 38620 }, { "epoch": 0.22962474216999246, "grad_norm": 1.52426278591156, "learning_rate": 0.00015307707549039033, "loss": 0.7470513343811035, "step": 38630 }, { "epoch": 0.22968418424666084, "grad_norm": 1.6292400360107422, "learning_rate": 0.00015311670299187637, "loss": 0.6587396144866944, "step": 38640 }, { "epoch": 0.22974362632332923, "grad_norm": 1.5158928632736206, "learning_rate": 0.0001531563304933624, "loss": 0.6981064796447753, "step": 38650 }, { "epoch": 0.22980306839999762, "grad_norm": 1.221300721168518, "learning_rate": 0.00015319595799484842, "loss": 0.6248347282409668, "step": 38660 }, { "epoch": 0.229862510476666, "grad_norm": 1.310874342918396, "learning_rate": 0.00015323558549633446, "loss": 0.6680130004882813, "step": 38670 }, { "epoch": 0.2299219525533344, "grad_norm": 1.4587377309799194, "learning_rate": 0.0001532752129978205, "loss": 0.6128517150878906, "step": 38680 }, { "epoch": 0.2299813946300028, "grad_norm": 1.7835049629211426, "learning_rate": 0.00015331484049930654, "loss": 0.6635103225708008, "step": 38690 }, { "epoch": 0.2300408367066712, "grad_norm": 1.705039620399475, "learning_rate": 0.00015335446800079257, "loss": 0.688844871520996, "step": 38700 }, { "epoch": 0.23010027878333958, "grad_norm": 1.9439362287521362, "learning_rate": 0.00015339409550227859, "loss": 0.6368844985961915, "step": 38710 }, { "epoch": 0.23015972086000797, "grad_norm": 1.4517822265625, "learning_rate": 0.00015343372300376463, "loss": 0.6977235794067382, "step": 38720 }, { "epoch": 0.23021916293667635, "grad_norm": 1.5706467628479004, "learning_rate": 0.00015347335050525064, "loss": 0.7141051292419434, "step": 38730 }, { "epoch": 0.23027860501334474, "grad_norm": 1.5194658041000366, "learning_rate": 0.00015351297800673668, "loss": 0.6194881916046142, "step": 38740 }, { "epoch": 0.23033804709001313, "grad_norm": 1.8122762441635132, "learning_rate": 0.00015355260550822271, "loss": 0.6899414539337159, "step": 38750 }, { "epoch": 0.23039748916668154, "grad_norm": 1.66018545627594, "learning_rate": 0.00015359223300970875, "loss": 0.6546745777130127, "step": 38760 }, { "epoch": 0.23045693124334993, "grad_norm": 1.7128429412841797, "learning_rate": 0.0001536318605111948, "loss": 0.6254630565643311, "step": 38770 }, { "epoch": 0.23051637332001831, "grad_norm": 1.5969581604003906, "learning_rate": 0.0001536714880126808, "loss": 0.6526697158813477, "step": 38780 }, { "epoch": 0.2305758153966867, "grad_norm": 1.4321140050888062, "learning_rate": 0.00015371111551416684, "loss": 0.7255626201629639, "step": 38790 }, { "epoch": 0.2306352574733551, "grad_norm": 1.6149260997772217, "learning_rate": 0.00015375074301565285, "loss": 0.6856755256652832, "step": 38800 }, { "epoch": 0.23069469955002347, "grad_norm": 1.856549859046936, "learning_rate": 0.0001537903705171389, "loss": 0.6402744293212891, "step": 38810 }, { "epoch": 0.23075414162669186, "grad_norm": 1.2377657890319824, "learning_rate": 0.00015382999801862493, "loss": 0.6490148544311524, "step": 38820 }, { "epoch": 0.23081358370336025, "grad_norm": 1.435945749282837, "learning_rate": 0.00015386962552011097, "loss": 0.6350676536560058, "step": 38830 }, { "epoch": 0.23087302578002866, "grad_norm": 1.3515814542770386, "learning_rate": 0.000153909253021597, "loss": 0.6604746818542481, "step": 38840 }, { "epoch": 0.23093246785669705, "grad_norm": 1.861426591873169, "learning_rate": 0.00015394888052308302, "loss": 0.7063170433044433, "step": 38850 }, { "epoch": 0.23099190993336544, "grad_norm": 1.4759467840194702, "learning_rate": 0.00015398850802456906, "loss": 0.6553950309753418, "step": 38860 }, { "epoch": 0.23105135201003382, "grad_norm": 1.5572305917739868, "learning_rate": 0.0001540281355260551, "loss": 0.672206974029541, "step": 38870 }, { "epoch": 0.2311107940867022, "grad_norm": 1.5070430040359497, "learning_rate": 0.0001540677630275411, "loss": 0.6295660018920899, "step": 38880 }, { "epoch": 0.2311702361633706, "grad_norm": 1.6178687810897827, "learning_rate": 0.00015410739052902717, "loss": 0.7013258934020996, "step": 38890 }, { "epoch": 0.23122967824003898, "grad_norm": 1.6407870054244995, "learning_rate": 0.00015414701803051319, "loss": 0.7375505924224853, "step": 38900 }, { "epoch": 0.2312891203167074, "grad_norm": 1.6108514070510864, "learning_rate": 0.00015418664553199922, "loss": 0.6131411552429199, "step": 38910 }, { "epoch": 0.23134856239337578, "grad_norm": 1.5349550247192383, "learning_rate": 0.00015422627303348524, "loss": 0.601150369644165, "step": 38920 }, { "epoch": 0.23140800447004417, "grad_norm": 1.594921350479126, "learning_rate": 0.00015426590053497127, "loss": 0.6732031822204589, "step": 38930 }, { "epoch": 0.23146744654671256, "grad_norm": 1.7811002731323242, "learning_rate": 0.0001543055280364573, "loss": 0.6233182430267334, "step": 38940 }, { "epoch": 0.23152688862338094, "grad_norm": 1.3191640377044678, "learning_rate": 0.00015434515553794332, "loss": 0.7035004615783691, "step": 38950 }, { "epoch": 0.23158633070004933, "grad_norm": 1.445573329925537, "learning_rate": 0.0001543847830394294, "loss": 0.6010564804077149, "step": 38960 }, { "epoch": 0.23164577277671772, "grad_norm": 1.5469931364059448, "learning_rate": 0.0001544244105409154, "loss": 0.7099512577056885, "step": 38970 }, { "epoch": 0.2317052148533861, "grad_norm": 1.9457709789276123, "learning_rate": 0.00015446403804240144, "loss": 0.7057023048400879, "step": 38980 }, { "epoch": 0.23176465693005452, "grad_norm": 1.712019920349121, "learning_rate": 0.00015450366554388748, "loss": 0.6970641136169433, "step": 38990 }, { "epoch": 0.2318240990067229, "grad_norm": 1.5307388305664062, "learning_rate": 0.0001545432930453735, "loss": 0.66915283203125, "step": 39000 }, { "epoch": 0.2318835410833913, "grad_norm": 1.8701053857803345, "learning_rate": 0.00015458292054685953, "loss": 0.6672899723052979, "step": 39010 }, { "epoch": 0.23194298316005968, "grad_norm": 2.0296168327331543, "learning_rate": 0.00015462254804834554, "loss": 0.6954081535339356, "step": 39020 }, { "epoch": 0.23200242523672807, "grad_norm": 1.403920292854309, "learning_rate": 0.0001546621755498316, "loss": 0.7161200523376465, "step": 39030 }, { "epoch": 0.23206186731339645, "grad_norm": 1.4690961837768555, "learning_rate": 0.00015470180305131762, "loss": 0.7341811180114746, "step": 39040 }, { "epoch": 0.23212130939006484, "grad_norm": 1.581666350364685, "learning_rate": 0.00015474143055280366, "loss": 0.7170108318328857, "step": 39050 }, { "epoch": 0.23218075146673325, "grad_norm": 1.6655610799789429, "learning_rate": 0.0001547810580542897, "loss": 0.6328907012939453, "step": 39060 }, { "epoch": 0.23224019354340164, "grad_norm": 1.3748835325241089, "learning_rate": 0.0001548206855557757, "loss": 0.6832528591156006, "step": 39070 }, { "epoch": 0.23229963562007003, "grad_norm": 1.6689281463623047, "learning_rate": 0.00015486031305726175, "loss": 0.695280647277832, "step": 39080 }, { "epoch": 0.23235907769673841, "grad_norm": 1.5176597833633423, "learning_rate": 0.00015489994055874776, "loss": 0.7179611682891845, "step": 39090 }, { "epoch": 0.2324185197734068, "grad_norm": 1.409416913986206, "learning_rate": 0.00015493956806023382, "loss": 0.6061365127563476, "step": 39100 }, { "epoch": 0.2324779618500752, "grad_norm": 1.7674633264541626, "learning_rate": 0.00015497919556171983, "loss": 0.6992634296417236, "step": 39110 }, { "epoch": 0.23253740392674357, "grad_norm": 1.2992966175079346, "learning_rate": 0.00015501882306320587, "loss": 0.6864993572235107, "step": 39120 }, { "epoch": 0.232596846003412, "grad_norm": 1.505839228630066, "learning_rate": 0.0001550584505646919, "loss": 0.681544017791748, "step": 39130 }, { "epoch": 0.23265628808008038, "grad_norm": 1.4345093965530396, "learning_rate": 0.00015509807806617792, "loss": 0.6309903621673584, "step": 39140 }, { "epoch": 0.23271573015674876, "grad_norm": 2.0476789474487305, "learning_rate": 0.00015513770556766396, "loss": 0.6906303405761719, "step": 39150 }, { "epoch": 0.23277517223341715, "grad_norm": 1.2095736265182495, "learning_rate": 0.00015517733306915, "loss": 0.6435821533203125, "step": 39160 }, { "epoch": 0.23283461431008554, "grad_norm": 1.5373759269714355, "learning_rate": 0.00015521696057063604, "loss": 0.6930880546569824, "step": 39170 }, { "epoch": 0.23289405638675392, "grad_norm": 1.6353758573532104, "learning_rate": 0.00015525658807212208, "loss": 0.6704794883728027, "step": 39180 }, { "epoch": 0.2329534984634223, "grad_norm": 1.9185044765472412, "learning_rate": 0.0001552962155736081, "loss": 0.6185712337493896, "step": 39190 }, { "epoch": 0.2330129405400907, "grad_norm": 1.3798818588256836, "learning_rate": 0.00015533584307509413, "loss": 0.6436296463012695, "step": 39200 }, { "epoch": 0.2330723826167591, "grad_norm": 1.395084261894226, "learning_rate": 0.00015537547057658014, "loss": 0.6901183128356934, "step": 39210 }, { "epoch": 0.2331318246934275, "grad_norm": 2.2221174240112305, "learning_rate": 0.00015541509807806618, "loss": 0.7323767662048339, "step": 39220 }, { "epoch": 0.23319126677009588, "grad_norm": 1.4861587285995483, "learning_rate": 0.00015545472557955222, "loss": 0.6911212921142578, "step": 39230 }, { "epoch": 0.23325070884676427, "grad_norm": 1.6633692979812622, "learning_rate": 0.00015549435308103826, "loss": 0.673424768447876, "step": 39240 }, { "epoch": 0.23331015092343266, "grad_norm": 1.7616897821426392, "learning_rate": 0.0001555339805825243, "loss": 0.7112258434295654, "step": 39250 }, { "epoch": 0.23336959300010104, "grad_norm": 1.6165452003479004, "learning_rate": 0.0001555736080840103, "loss": 0.6778579711914062, "step": 39260 }, { "epoch": 0.23342903507676943, "grad_norm": 1.5704073905944824, "learning_rate": 0.00015561323558549634, "loss": 0.6942387580871582, "step": 39270 }, { "epoch": 0.23348847715343785, "grad_norm": 2.188713550567627, "learning_rate": 0.00015565286308698238, "loss": 0.6866367816925049, "step": 39280 }, { "epoch": 0.23354791923010623, "grad_norm": 1.8629785776138306, "learning_rate": 0.0001556924905884684, "loss": 0.6869722366333008, "step": 39290 }, { "epoch": 0.23360736130677462, "grad_norm": 1.4308913946151733, "learning_rate": 0.00015573211808995443, "loss": 0.6706880569458008, "step": 39300 }, { "epoch": 0.233666803383443, "grad_norm": 1.7674788236618042, "learning_rate": 0.00015577174559144047, "loss": 0.657941198348999, "step": 39310 }, { "epoch": 0.2337262454601114, "grad_norm": 1.247889757156372, "learning_rate": 0.0001558113730929265, "loss": 0.669381856918335, "step": 39320 }, { "epoch": 0.23378568753677978, "grad_norm": 1.8930569887161255, "learning_rate": 0.00015585100059441252, "loss": 0.6794369697570801, "step": 39330 }, { "epoch": 0.23384512961344817, "grad_norm": 1.6220768690109253, "learning_rate": 0.00015589062809589856, "loss": 0.664754581451416, "step": 39340 }, { "epoch": 0.23390457169011655, "grad_norm": 2.0397822856903076, "learning_rate": 0.0001559302555973846, "loss": 0.7505016803741456, "step": 39350 }, { "epoch": 0.23396401376678497, "grad_norm": 1.71175217628479, "learning_rate": 0.0001559698830988706, "loss": 0.6390087127685546, "step": 39360 }, { "epoch": 0.23402345584345335, "grad_norm": 1.505540132522583, "learning_rate": 0.00015600951060035665, "loss": 0.6876034736633301, "step": 39370 }, { "epoch": 0.23408289792012174, "grad_norm": 1.5027384757995605, "learning_rate": 0.0001560491381018427, "loss": 0.6537727355957031, "step": 39380 }, { "epoch": 0.23414233999679013, "grad_norm": 1.7113523483276367, "learning_rate": 0.00015608876560332873, "loss": 0.7315763473510742, "step": 39390 }, { "epoch": 0.23420178207345851, "grad_norm": 1.8147895336151123, "learning_rate": 0.00015612839310481474, "loss": 0.6604602813720704, "step": 39400 }, { "epoch": 0.2342612241501269, "grad_norm": 1.3125754594802856, "learning_rate": 0.00015616802060630078, "loss": 0.6166815757751465, "step": 39410 }, { "epoch": 0.2343206662267953, "grad_norm": 1.4575697183609009, "learning_rate": 0.00015620764810778682, "loss": 0.6460515975952148, "step": 39420 }, { "epoch": 0.2343801083034637, "grad_norm": 1.5563212633132935, "learning_rate": 0.00015624727560927283, "loss": 0.6717259407043457, "step": 39430 }, { "epoch": 0.2344395503801321, "grad_norm": 1.6954481601715088, "learning_rate": 0.00015628690311075887, "loss": 0.697575569152832, "step": 39440 }, { "epoch": 0.23449899245680048, "grad_norm": 1.605630874633789, "learning_rate": 0.0001563265306122449, "loss": 0.7116083145141602, "step": 39450 }, { "epoch": 0.23455843453346886, "grad_norm": 1.4100433588027954, "learning_rate": 0.00015636615811373094, "loss": 0.6898627281188965, "step": 39460 }, { "epoch": 0.23461787661013725, "grad_norm": 1.561804175376892, "learning_rate": 0.00015640578561521698, "loss": 0.6787949562072754, "step": 39470 }, { "epoch": 0.23467731868680564, "grad_norm": 1.6050512790679932, "learning_rate": 0.000156445413116703, "loss": 0.6903696060180664, "step": 39480 }, { "epoch": 0.23473676076347402, "grad_norm": 1.653929352760315, "learning_rate": 0.00015648504061818903, "loss": 0.625316047668457, "step": 39490 }, { "epoch": 0.2347962028401424, "grad_norm": 1.2193996906280518, "learning_rate": 0.00015652466811967504, "loss": 0.6609185218811036, "step": 39500 }, { "epoch": 0.23485564491681082, "grad_norm": 1.425227165222168, "learning_rate": 0.00015656429562116108, "loss": 0.6593976974487304, "step": 39510 }, { "epoch": 0.2349150869934792, "grad_norm": 1.7269480228424072, "learning_rate": 0.00015660392312264712, "loss": 0.6715658187866211, "step": 39520 }, { "epoch": 0.2349745290701476, "grad_norm": 1.7021417617797852, "learning_rate": 0.00015664355062413316, "loss": 0.6818897247314453, "step": 39530 }, { "epoch": 0.23503397114681598, "grad_norm": 1.5297824144363403, "learning_rate": 0.0001566831781256192, "loss": 0.7003639221191407, "step": 39540 }, { "epoch": 0.23509341322348437, "grad_norm": 1.5971482992172241, "learning_rate": 0.0001567228056271052, "loss": 0.6643218994140625, "step": 39550 }, { "epoch": 0.23515285530015276, "grad_norm": 1.3702062368392944, "learning_rate": 0.00015676243312859125, "loss": 0.7012148857116699, "step": 39560 }, { "epoch": 0.23521229737682114, "grad_norm": 1.646850347518921, "learning_rate": 0.0001568020606300773, "loss": 0.6992447376251221, "step": 39570 }, { "epoch": 0.23527173945348956, "grad_norm": 1.5845947265625, "learning_rate": 0.0001568416881315633, "loss": 0.7041491508483887, "step": 39580 }, { "epoch": 0.23533118153015795, "grad_norm": 1.9886412620544434, "learning_rate": 0.00015688131563304936, "loss": 0.7032835960388184, "step": 39590 }, { "epoch": 0.23539062360682633, "grad_norm": 1.5738587379455566, "learning_rate": 0.00015692094313453538, "loss": 0.683778715133667, "step": 39600 }, { "epoch": 0.23545006568349472, "grad_norm": 1.416417121887207, "learning_rate": 0.00015696057063602141, "loss": 0.6327310562133789, "step": 39610 }, { "epoch": 0.2355095077601631, "grad_norm": 1.4892895221710205, "learning_rate": 0.00015700019813750743, "loss": 0.7187392234802246, "step": 39620 }, { "epoch": 0.2355689498368315, "grad_norm": 1.5581127405166626, "learning_rate": 0.00015703982563899346, "loss": 0.6697898864746094, "step": 39630 }, { "epoch": 0.23562839191349988, "grad_norm": 1.5791871547698975, "learning_rate": 0.0001570794531404795, "loss": 0.6986635208129883, "step": 39640 }, { "epoch": 0.2356878339901683, "grad_norm": 1.6625511646270752, "learning_rate": 0.00015711908064196552, "loss": 0.6516802310943604, "step": 39650 }, { "epoch": 0.23574727606683668, "grad_norm": 1.5945566892623901, "learning_rate": 0.00015715870814345158, "loss": 0.6797699451446533, "step": 39660 }, { "epoch": 0.23580671814350507, "grad_norm": 1.5332238674163818, "learning_rate": 0.0001571983356449376, "loss": 0.6296527862548829, "step": 39670 }, { "epoch": 0.23586616022017345, "grad_norm": 1.4298559427261353, "learning_rate": 0.00015723796314642363, "loss": 0.6651180267333985, "step": 39680 }, { "epoch": 0.23592560229684184, "grad_norm": 2.022371292114258, "learning_rate": 0.00015727759064790964, "loss": 0.7635261535644531, "step": 39690 }, { "epoch": 0.23598504437351023, "grad_norm": 1.648273229598999, "learning_rate": 0.00015731721814939568, "loss": 0.6819944858551026, "step": 39700 }, { "epoch": 0.23604448645017861, "grad_norm": 1.6287565231323242, "learning_rate": 0.00015735684565088172, "loss": 0.6906696796417237, "step": 39710 }, { "epoch": 0.236103928526847, "grad_norm": 1.8200522661209106, "learning_rate": 0.00015739647315236773, "loss": 0.707090950012207, "step": 39720 }, { "epoch": 0.23616337060351542, "grad_norm": 1.611659049987793, "learning_rate": 0.0001574361006538538, "loss": 0.6486243724822998, "step": 39730 }, { "epoch": 0.2362228126801838, "grad_norm": 1.7939608097076416, "learning_rate": 0.0001574757281553398, "loss": 0.6689130783081054, "step": 39740 }, { "epoch": 0.2362822547568522, "grad_norm": 1.619262933731079, "learning_rate": 0.00015751535565682585, "loss": 0.6177031040191651, "step": 39750 }, { "epoch": 0.23634169683352058, "grad_norm": 1.4037328958511353, "learning_rate": 0.00015755498315831189, "loss": 0.6944563388824463, "step": 39760 }, { "epoch": 0.23640113891018896, "grad_norm": 1.9102712869644165, "learning_rate": 0.0001575946106597979, "loss": 0.6553598403930664, "step": 39770 }, { "epoch": 0.23646058098685735, "grad_norm": 2.0107452869415283, "learning_rate": 0.00015763423816128394, "loss": 0.6499786376953125, "step": 39780 }, { "epoch": 0.23652002306352574, "grad_norm": 1.4544020891189575, "learning_rate": 0.00015767386566276995, "loss": 0.6384374618530273, "step": 39790 }, { "epoch": 0.23657946514019415, "grad_norm": 1.882082223892212, "learning_rate": 0.00015771349316425601, "loss": 0.6834965229034424, "step": 39800 }, { "epoch": 0.23663890721686254, "grad_norm": 1.432786226272583, "learning_rate": 0.00015775312066574203, "loss": 0.6577715873718262, "step": 39810 }, { "epoch": 0.23669834929353092, "grad_norm": 1.4417555332183838, "learning_rate": 0.00015779274816722806, "loss": 0.6936501026153564, "step": 39820 }, { "epoch": 0.2367577913701993, "grad_norm": 1.4659672975540161, "learning_rate": 0.0001578323756687141, "loss": 0.6930965900421142, "step": 39830 }, { "epoch": 0.2368172334468677, "grad_norm": 1.3149685859680176, "learning_rate": 0.00015787200317020011, "loss": 0.6785439491271973, "step": 39840 }, { "epoch": 0.23687667552353608, "grad_norm": 1.8032853603363037, "learning_rate": 0.00015791163067168615, "loss": 0.7526850700378418, "step": 39850 }, { "epoch": 0.23693611760020447, "grad_norm": 2.082705497741699, "learning_rate": 0.0001579512581731722, "loss": 0.6985031127929687, "step": 39860 }, { "epoch": 0.23699555967687286, "grad_norm": 1.8936883211135864, "learning_rate": 0.00015799088567465823, "loss": 0.6637249946594238, "step": 39870 }, { "epoch": 0.23705500175354127, "grad_norm": 1.623420000076294, "learning_rate": 0.00015803051317614427, "loss": 0.7091871738433838, "step": 39880 }, { "epoch": 0.23711444383020966, "grad_norm": 1.2654565572738647, "learning_rate": 0.00015807014067763028, "loss": 0.6458116054534913, "step": 39890 }, { "epoch": 0.23717388590687805, "grad_norm": 1.6408933401107788, "learning_rate": 0.00015810976817911632, "loss": 0.6199362754821778, "step": 39900 }, { "epoch": 0.23723332798354643, "grad_norm": 1.8911421298980713, "learning_rate": 0.00015814939568060233, "loss": 0.740762996673584, "step": 39910 }, { "epoch": 0.23729277006021482, "grad_norm": 1.4693069458007812, "learning_rate": 0.00015818902318208837, "loss": 0.6110015869140625, "step": 39920 }, { "epoch": 0.2373522121368832, "grad_norm": 1.7869552373886108, "learning_rate": 0.0001582286506835744, "loss": 0.6675580978393555, "step": 39930 }, { "epoch": 0.2374116542135516, "grad_norm": 1.4692250490188599, "learning_rate": 0.00015826827818506045, "loss": 0.6540817260742188, "step": 39940 }, { "epoch": 0.23747109629022, "grad_norm": 1.57044517993927, "learning_rate": 0.00015830790568654649, "loss": 0.6098968029022217, "step": 39950 }, { "epoch": 0.2375305383668884, "grad_norm": 1.5780808925628662, "learning_rate": 0.0001583475331880325, "loss": 0.7044313907623291, "step": 39960 }, { "epoch": 0.23758998044355678, "grad_norm": 1.8811451196670532, "learning_rate": 0.00015838716068951854, "loss": 0.7198540210723877, "step": 39970 }, { "epoch": 0.23764942252022517, "grad_norm": 1.6514068841934204, "learning_rate": 0.00015842678819100455, "loss": 0.6905970573425293, "step": 39980 }, { "epoch": 0.23770886459689355, "grad_norm": 1.4919631481170654, "learning_rate": 0.00015846641569249059, "loss": 0.7095765113830567, "step": 39990 }, { "epoch": 0.23776830667356194, "grad_norm": 1.304131031036377, "learning_rate": 0.00015850604319397662, "loss": 0.667618989944458, "step": 40000 }, { "epoch": 0.23782774875023033, "grad_norm": 1.5312438011169434, "learning_rate": 0.00015854567069546266, "loss": 0.6238177299499512, "step": 40010 }, { "epoch": 0.23788719082689874, "grad_norm": 1.626333475112915, "learning_rate": 0.0001585852981969487, "loss": 0.7287935256958008, "step": 40020 }, { "epoch": 0.23794663290356713, "grad_norm": 1.4387849569320679, "learning_rate": 0.0001586249256984347, "loss": 0.645806074142456, "step": 40030 }, { "epoch": 0.23800607498023552, "grad_norm": 1.9820775985717773, "learning_rate": 0.00015866455319992075, "loss": 0.6460247993469238, "step": 40040 }, { "epoch": 0.2380655170569039, "grad_norm": 1.6697512865066528, "learning_rate": 0.0001587041807014068, "loss": 0.6323999881744384, "step": 40050 }, { "epoch": 0.2381249591335723, "grad_norm": 1.9370265007019043, "learning_rate": 0.0001587438082028928, "loss": 0.6664704322814942, "step": 40060 }, { "epoch": 0.23818440121024068, "grad_norm": 1.6691954135894775, "learning_rate": 0.00015878343570437884, "loss": 0.6795830726623535, "step": 40070 }, { "epoch": 0.23824384328690906, "grad_norm": 1.927019476890564, "learning_rate": 0.00015882306320586488, "loss": 0.6583178997039795, "step": 40080 }, { "epoch": 0.23830328536357745, "grad_norm": 1.4549275636672974, "learning_rate": 0.00015886269070735092, "loss": 0.6689316749572753, "step": 40090 }, { "epoch": 0.23836272744024586, "grad_norm": 1.4991894960403442, "learning_rate": 0.00015890231820883693, "loss": 0.6747591018676757, "step": 40100 }, { "epoch": 0.23842216951691425, "grad_norm": 1.6770268678665161, "learning_rate": 0.00015894194571032297, "loss": 0.6116420745849609, "step": 40110 }, { "epoch": 0.23848161159358264, "grad_norm": 1.8062442541122437, "learning_rate": 0.000158981573211809, "loss": 0.5895156860351562, "step": 40120 }, { "epoch": 0.23854105367025102, "grad_norm": 1.7628438472747803, "learning_rate": 0.00015902120071329502, "loss": 0.694127368927002, "step": 40130 }, { "epoch": 0.2386004957469194, "grad_norm": 1.8608134984970093, "learning_rate": 0.00015906082821478106, "loss": 0.7016088485717773, "step": 40140 }, { "epoch": 0.2386599378235878, "grad_norm": 1.5030789375305176, "learning_rate": 0.0001591004557162671, "loss": 0.6811469078063965, "step": 40150 }, { "epoch": 0.23871937990025618, "grad_norm": 1.2490205764770508, "learning_rate": 0.00015914008321775313, "loss": 0.6324467658996582, "step": 40160 }, { "epoch": 0.2387788219769246, "grad_norm": 1.3726261854171753, "learning_rate": 0.00015917971071923917, "loss": 0.6487534523010254, "step": 40170 }, { "epoch": 0.23883826405359299, "grad_norm": 1.5691555738449097, "learning_rate": 0.00015921933822072518, "loss": 0.65811185836792, "step": 40180 }, { "epoch": 0.23889770613026137, "grad_norm": 1.8680654764175415, "learning_rate": 0.00015925896572221122, "loss": 0.7520692825317383, "step": 40190 }, { "epoch": 0.23895714820692976, "grad_norm": 2.131197214126587, "learning_rate": 0.00015929859322369723, "loss": 0.6171497344970703, "step": 40200 }, { "epoch": 0.23901659028359815, "grad_norm": 1.4047131538391113, "learning_rate": 0.0001593382207251833, "loss": 0.652992057800293, "step": 40210 }, { "epoch": 0.23907603236026653, "grad_norm": 1.2233073711395264, "learning_rate": 0.0001593778482266693, "loss": 0.6870738983154296, "step": 40220 }, { "epoch": 0.23913547443693492, "grad_norm": 1.4620274305343628, "learning_rate": 0.00015941747572815535, "loss": 0.6764164924621582, "step": 40230 }, { "epoch": 0.2391949165136033, "grad_norm": 1.879560947418213, "learning_rate": 0.0001594571032296414, "loss": 0.6581961631774902, "step": 40240 }, { "epoch": 0.23925435859027172, "grad_norm": 1.893103003501892, "learning_rate": 0.0001594967307311274, "loss": 0.6735259056091308, "step": 40250 }, { "epoch": 0.2393138006669401, "grad_norm": 1.3571592569351196, "learning_rate": 0.00015953635823261344, "loss": 0.6103536128997803, "step": 40260 }, { "epoch": 0.2393732427436085, "grad_norm": 1.7199196815490723, "learning_rate": 0.00015957598573409948, "loss": 0.6355384349822998, "step": 40270 }, { "epoch": 0.23943268482027688, "grad_norm": 1.3968487977981567, "learning_rate": 0.00015961561323558552, "loss": 0.6600364208221435, "step": 40280 }, { "epoch": 0.23949212689694527, "grad_norm": 1.7377679347991943, "learning_rate": 0.00015965524073707156, "loss": 0.6286239624023438, "step": 40290 }, { "epoch": 0.23955156897361365, "grad_norm": 1.641327977180481, "learning_rate": 0.00015969486823855757, "loss": 0.6807528495788574, "step": 40300 }, { "epoch": 0.23961101105028204, "grad_norm": 1.4633218050003052, "learning_rate": 0.0001597344957400436, "loss": 0.6860513687133789, "step": 40310 }, { "epoch": 0.23967045312695046, "grad_norm": 1.1407912969589233, "learning_rate": 0.00015977412324152962, "loss": 0.692341661453247, "step": 40320 }, { "epoch": 0.23972989520361884, "grad_norm": 1.622741937637329, "learning_rate": 0.00015981375074301566, "loss": 0.6909862518310547, "step": 40330 }, { "epoch": 0.23978933728028723, "grad_norm": 1.4544124603271484, "learning_rate": 0.0001598533782445017, "loss": 0.6989912033081055, "step": 40340 }, { "epoch": 0.23984877935695562, "grad_norm": 1.906678318977356, "learning_rate": 0.00015989300574598773, "loss": 0.6259340286254883, "step": 40350 }, { "epoch": 0.239908221433624, "grad_norm": 1.796365737915039, "learning_rate": 0.00015993263324747377, "loss": 0.6445921897888184, "step": 40360 }, { "epoch": 0.2399676635102924, "grad_norm": 1.4331607818603516, "learning_rate": 0.00015997226074895978, "loss": 0.6834857940673829, "step": 40370 }, { "epoch": 0.24002710558696078, "grad_norm": 1.1824095249176025, "learning_rate": 0.00016001188825044582, "loss": 0.6548418998718262, "step": 40380 }, { "epoch": 0.24008654766362916, "grad_norm": 1.5689449310302734, "learning_rate": 0.00016005151575193183, "loss": 0.6981189727783204, "step": 40390 }, { "epoch": 0.24014598974029758, "grad_norm": 1.6965101957321167, "learning_rate": 0.00016009114325341787, "loss": 0.703673267364502, "step": 40400 }, { "epoch": 0.24020543181696596, "grad_norm": 1.7283666133880615, "learning_rate": 0.0001601307707549039, "loss": 0.6757970809936523, "step": 40410 }, { "epoch": 0.24026487389363435, "grad_norm": 1.691754937171936, "learning_rate": 0.00016017039825638995, "loss": 0.6833659172058105, "step": 40420 }, { "epoch": 0.24032431597030274, "grad_norm": 1.7012653350830078, "learning_rate": 0.000160210025757876, "loss": 0.6483166694641114, "step": 40430 }, { "epoch": 0.24038375804697112, "grad_norm": 1.5667108297348022, "learning_rate": 0.000160249653259362, "loss": 0.6221180915832519, "step": 40440 }, { "epoch": 0.2404432001236395, "grad_norm": 1.3371576070785522, "learning_rate": 0.00016028928076084804, "loss": 0.647407341003418, "step": 40450 }, { "epoch": 0.2405026422003079, "grad_norm": 1.615709662437439, "learning_rate": 0.00016032890826233408, "loss": 0.6487547874450683, "step": 40460 }, { "epoch": 0.2405620842769763, "grad_norm": 1.6000641584396362, "learning_rate": 0.0001603685357638201, "loss": 0.6370726585388183, "step": 40470 }, { "epoch": 0.2406215263536447, "grad_norm": 1.223723292350769, "learning_rate": 0.00016040816326530613, "loss": 0.7037858963012695, "step": 40480 }, { "epoch": 0.24068096843031309, "grad_norm": 1.56288743019104, "learning_rate": 0.00016044779076679217, "loss": 0.7309988021850586, "step": 40490 }, { "epoch": 0.24074041050698147, "grad_norm": 1.483327865600586, "learning_rate": 0.0001604874182682782, "loss": 0.6894060134887695, "step": 40500 }, { "epoch": 0.24079985258364986, "grad_norm": 1.5227277278900146, "learning_rate": 0.00016052704576976422, "loss": 0.6961113929748535, "step": 40510 }, { "epoch": 0.24085929466031825, "grad_norm": 1.678962230682373, "learning_rate": 0.00016056667327125025, "loss": 0.6920573234558105, "step": 40520 }, { "epoch": 0.24091873673698663, "grad_norm": 2.1310489177703857, "learning_rate": 0.0001606063007727363, "loss": 0.6651420593261719, "step": 40530 }, { "epoch": 0.24097817881365505, "grad_norm": 1.8347814083099365, "learning_rate": 0.0001606459282742223, "loss": 0.6542804718017579, "step": 40540 }, { "epoch": 0.24103762089032343, "grad_norm": 1.8035904169082642, "learning_rate": 0.00016068555577570834, "loss": 0.677517318725586, "step": 40550 }, { "epoch": 0.24109706296699182, "grad_norm": 1.7717037200927734, "learning_rate": 0.00016072518327719438, "loss": 0.7049003601074219, "step": 40560 }, { "epoch": 0.2411565050436602, "grad_norm": 1.4935119152069092, "learning_rate": 0.00016076481077868042, "loss": 0.6399362564086915, "step": 40570 }, { "epoch": 0.2412159471203286, "grad_norm": 1.3513104915618896, "learning_rate": 0.00016080443828016646, "loss": 0.711646318435669, "step": 40580 }, { "epoch": 0.24127538919699698, "grad_norm": 1.2308671474456787, "learning_rate": 0.00016084406578165247, "loss": 0.6479909420013428, "step": 40590 }, { "epoch": 0.24133483127366537, "grad_norm": 1.3231159448623657, "learning_rate": 0.0001608836932831385, "loss": 0.612083101272583, "step": 40600 }, { "epoch": 0.24139427335033375, "grad_norm": 1.3626247644424438, "learning_rate": 0.00016092332078462452, "loss": 0.670776081085205, "step": 40610 }, { "epoch": 0.24145371542700217, "grad_norm": 1.7963600158691406, "learning_rate": 0.00016096294828611056, "loss": 0.6595791816711426, "step": 40620 }, { "epoch": 0.24151315750367056, "grad_norm": 1.9431474208831787, "learning_rate": 0.0001610025757875966, "loss": 0.6290439605712891, "step": 40630 }, { "epoch": 0.24157259958033894, "grad_norm": 1.6077628135681152, "learning_rate": 0.00016104220328908264, "loss": 0.6747737884521484, "step": 40640 }, { "epoch": 0.24163204165700733, "grad_norm": 1.6801196336746216, "learning_rate": 0.00016108183079056868, "loss": 0.7435812950134277, "step": 40650 }, { "epoch": 0.24169148373367572, "grad_norm": 1.6654891967773438, "learning_rate": 0.0001611214582920547, "loss": 0.6660977840423584, "step": 40660 }, { "epoch": 0.2417509258103441, "grad_norm": 1.8211417198181152, "learning_rate": 0.00016116108579354073, "loss": 0.7312870502471924, "step": 40670 }, { "epoch": 0.2418103678870125, "grad_norm": 1.653820514678955, "learning_rate": 0.00016120071329502674, "loss": 0.6675552368164063, "step": 40680 }, { "epoch": 0.2418698099636809, "grad_norm": 2.077345848083496, "learning_rate": 0.00016124034079651278, "loss": 0.6697470664978027, "step": 40690 }, { "epoch": 0.2419292520403493, "grad_norm": 1.6681671142578125, "learning_rate": 0.00016127996829799884, "loss": 0.6582822799682617, "step": 40700 }, { "epoch": 0.24198869411701768, "grad_norm": 1.732301950454712, "learning_rate": 0.00016131959579948485, "loss": 0.7351043701171875, "step": 40710 }, { "epoch": 0.24204813619368606, "grad_norm": 1.598472237586975, "learning_rate": 0.0001613592233009709, "loss": 0.6381748199462891, "step": 40720 }, { "epoch": 0.24210757827035445, "grad_norm": 1.463857889175415, "learning_rate": 0.0001613988508024569, "loss": 0.66970796585083, "step": 40730 }, { "epoch": 0.24216702034702284, "grad_norm": 1.3227871656417847, "learning_rate": 0.00016143847830394294, "loss": 0.6646751403808594, "step": 40740 }, { "epoch": 0.24222646242369122, "grad_norm": 1.8731343746185303, "learning_rate": 0.00016147810580542898, "loss": 0.674470043182373, "step": 40750 }, { "epoch": 0.2422859045003596, "grad_norm": 1.4012523889541626, "learning_rate": 0.000161517733306915, "loss": 0.6367850303649902, "step": 40760 }, { "epoch": 0.24234534657702803, "grad_norm": 1.7656296491622925, "learning_rate": 0.00016155736080840106, "loss": 0.6845845222473145, "step": 40770 }, { "epoch": 0.2424047886536964, "grad_norm": 1.612736701965332, "learning_rate": 0.00016159698830988707, "loss": 0.6562628269195556, "step": 40780 }, { "epoch": 0.2424642307303648, "grad_norm": 1.463875651359558, "learning_rate": 0.0001616366158113731, "loss": 0.6941015720367432, "step": 40790 }, { "epoch": 0.24252367280703319, "grad_norm": 1.5788562297821045, "learning_rate": 0.00016167624331285912, "loss": 0.6830503940582275, "step": 40800 }, { "epoch": 0.24258311488370157, "grad_norm": 1.728770136833191, "learning_rate": 0.00016171587081434516, "loss": 0.6859941005706787, "step": 40810 }, { "epoch": 0.24264255696036996, "grad_norm": 1.4215036630630493, "learning_rate": 0.0001617554983158312, "loss": 0.6922409057617187, "step": 40820 }, { "epoch": 0.24270199903703835, "grad_norm": 1.3888534307479858, "learning_rate": 0.0001617951258173172, "loss": 0.6517919540405274, "step": 40830 }, { "epoch": 0.24276144111370676, "grad_norm": 1.3304694890975952, "learning_rate": 0.00016183475331880327, "loss": 0.6833292961120605, "step": 40840 }, { "epoch": 0.24282088319037515, "grad_norm": 1.8035684823989868, "learning_rate": 0.00016187438082028929, "loss": 0.6469512939453125, "step": 40850 }, { "epoch": 0.24288032526704353, "grad_norm": 1.6079696416854858, "learning_rate": 0.00016191400832177533, "loss": 0.7036733627319336, "step": 40860 }, { "epoch": 0.24293976734371192, "grad_norm": 1.6818783283233643, "learning_rate": 0.00016195363582326136, "loss": 0.6628180980682373, "step": 40870 }, { "epoch": 0.2429992094203803, "grad_norm": 1.5923917293548584, "learning_rate": 0.00016199326332474738, "loss": 0.6693262100219727, "step": 40880 }, { "epoch": 0.2430586514970487, "grad_norm": 1.7480840682983398, "learning_rate": 0.00016203289082623341, "loss": 0.6699935913085937, "step": 40890 }, { "epoch": 0.24311809357371708, "grad_norm": 1.851324439048767, "learning_rate": 0.00016207251832771943, "loss": 0.6861649990081787, "step": 40900 }, { "epoch": 0.2431775356503855, "grad_norm": 1.4406611919403076, "learning_rate": 0.0001621121458292055, "loss": 0.736432695388794, "step": 40910 }, { "epoch": 0.24323697772705388, "grad_norm": 1.8378406763076782, "learning_rate": 0.0001621517733306915, "loss": 0.6599106788635254, "step": 40920 }, { "epoch": 0.24329641980372227, "grad_norm": 1.7251180410385132, "learning_rate": 0.00016219140083217754, "loss": 0.6732661724090576, "step": 40930 }, { "epoch": 0.24335586188039066, "grad_norm": 1.9052976369857788, "learning_rate": 0.00016223102833366358, "loss": 0.6432515621185303, "step": 40940 }, { "epoch": 0.24341530395705904, "grad_norm": 1.51438307762146, "learning_rate": 0.0001622706558351496, "loss": 0.6380278587341308, "step": 40950 }, { "epoch": 0.24347474603372743, "grad_norm": 1.5862783193588257, "learning_rate": 0.00016231028333663563, "loss": 0.67610182762146, "step": 40960 }, { "epoch": 0.24353418811039582, "grad_norm": 1.8614850044250488, "learning_rate": 0.00016234991083812164, "loss": 0.6656064033508301, "step": 40970 }, { "epoch": 0.2435936301870642, "grad_norm": 1.9124863147735596, "learning_rate": 0.0001623895383396077, "loss": 0.7333134651184082, "step": 40980 }, { "epoch": 0.24365307226373262, "grad_norm": 1.9127475023269653, "learning_rate": 0.00016242916584109375, "loss": 0.7179203987121582, "step": 40990 }, { "epoch": 0.243712514340401, "grad_norm": 1.4387141466140747, "learning_rate": 0.00016246879334257976, "loss": 0.6379157543182373, "step": 41000 }, { "epoch": 0.2437719564170694, "grad_norm": 2.591048240661621, "learning_rate": 0.0001625084208440658, "loss": 0.6865398406982421, "step": 41010 }, { "epoch": 0.24383139849373778, "grad_norm": 1.5997122526168823, "learning_rate": 0.0001625480483455518, "loss": 0.6871333599090577, "step": 41020 }, { "epoch": 0.24389084057040616, "grad_norm": 1.5215444564819336, "learning_rate": 0.00016258767584703785, "loss": 0.7038451194763183, "step": 41030 }, { "epoch": 0.24395028264707455, "grad_norm": 1.5036380290985107, "learning_rate": 0.00016262730334852389, "loss": 0.639606523513794, "step": 41040 }, { "epoch": 0.24400972472374294, "grad_norm": 2.023210048675537, "learning_rate": 0.00016266693085000992, "loss": 0.7007499217987061, "step": 41050 }, { "epoch": 0.24406916680041135, "grad_norm": 1.8324254751205444, "learning_rate": 0.00016270655835149596, "loss": 0.6276179313659668, "step": 41060 }, { "epoch": 0.24412860887707974, "grad_norm": 1.3540949821472168, "learning_rate": 0.00016274618585298197, "loss": 0.6231176853179932, "step": 41070 }, { "epoch": 0.24418805095374813, "grad_norm": 1.4846199750900269, "learning_rate": 0.000162785813354468, "loss": 0.678046703338623, "step": 41080 }, { "epoch": 0.2442474930304165, "grad_norm": 1.505397915840149, "learning_rate": 0.00016282544085595402, "loss": 0.6794496536254883, "step": 41090 }, { "epoch": 0.2443069351070849, "grad_norm": 1.3486322164535522, "learning_rate": 0.00016286506835744006, "loss": 0.6585762023925781, "step": 41100 }, { "epoch": 0.24436637718375329, "grad_norm": 1.8309929370880127, "learning_rate": 0.0001629046958589261, "loss": 0.657569408416748, "step": 41110 }, { "epoch": 0.24442581926042167, "grad_norm": 1.438234567642212, "learning_rate": 0.00016294432336041214, "loss": 0.6728520870208741, "step": 41120 }, { "epoch": 0.24448526133709006, "grad_norm": 1.5836046934127808, "learning_rate": 0.00016298395086189818, "loss": 0.707191276550293, "step": 41130 }, { "epoch": 0.24454470341375847, "grad_norm": 1.6165663003921509, "learning_rate": 0.0001630235783633842, "loss": 0.6360228538513184, "step": 41140 }, { "epoch": 0.24460414549042686, "grad_norm": 1.634158730506897, "learning_rate": 0.00016306320586487023, "loss": 0.6694785118103027, "step": 41150 }, { "epoch": 0.24466358756709525, "grad_norm": 1.6608401536941528, "learning_rate": 0.00016310283336635627, "loss": 0.7133777618408204, "step": 41160 }, { "epoch": 0.24472302964376363, "grad_norm": 1.3120180368423462, "learning_rate": 0.00016314246086784228, "loss": 0.6513284683227539, "step": 41170 }, { "epoch": 0.24478247172043202, "grad_norm": 1.4785207509994507, "learning_rate": 0.00016318208836932832, "loss": 0.66775541305542, "step": 41180 }, { "epoch": 0.2448419137971004, "grad_norm": 1.7561053037643433, "learning_rate": 0.00016322171587081436, "loss": 0.7137593269348145, "step": 41190 }, { "epoch": 0.2449013558737688, "grad_norm": 1.4361807107925415, "learning_rate": 0.0001632613433723004, "loss": 0.6781128883361817, "step": 41200 }, { "epoch": 0.2449607979504372, "grad_norm": 1.6964714527130127, "learning_rate": 0.0001633009708737864, "loss": 0.6934805393218995, "step": 41210 }, { "epoch": 0.2450202400271056, "grad_norm": 2.2587034702301025, "learning_rate": 0.00016334059837527245, "loss": 0.6907707691192627, "step": 41220 }, { "epoch": 0.24507968210377398, "grad_norm": 1.481201410293579, "learning_rate": 0.00016338022587675848, "loss": 0.6390320777893066, "step": 41230 }, { "epoch": 0.24513912418044237, "grad_norm": 1.4277558326721191, "learning_rate": 0.0001634198533782445, "loss": 0.6604814529418945, "step": 41240 }, { "epoch": 0.24519856625711076, "grad_norm": 1.8327809572219849, "learning_rate": 0.00016345948087973053, "loss": 0.687226390838623, "step": 41250 }, { "epoch": 0.24525800833377914, "grad_norm": 1.3509820699691772, "learning_rate": 0.00016349910838121657, "loss": 0.6753727912902832, "step": 41260 }, { "epoch": 0.24531745041044753, "grad_norm": 1.8305275440216064, "learning_rate": 0.0001635387358827026, "loss": 0.7394688129425049, "step": 41270 }, { "epoch": 0.24537689248711592, "grad_norm": 1.8548160791397095, "learning_rate": 0.00016357836338418865, "loss": 0.6837615013122559, "step": 41280 }, { "epoch": 0.24543633456378433, "grad_norm": 1.390554666519165, "learning_rate": 0.00016361799088567466, "loss": 0.6468981742858887, "step": 41290 }, { "epoch": 0.24549577664045272, "grad_norm": 1.527472734451294, "learning_rate": 0.0001636576183871607, "loss": 0.6647745609283447, "step": 41300 }, { "epoch": 0.2455552187171211, "grad_norm": 1.6849466562271118, "learning_rate": 0.0001636972458886467, "loss": 0.688726282119751, "step": 41310 }, { "epoch": 0.2456146607937895, "grad_norm": 1.662673830986023, "learning_rate": 0.00016373687339013275, "loss": 0.7273617744445801, "step": 41320 }, { "epoch": 0.24567410287045788, "grad_norm": 1.6035155057907104, "learning_rate": 0.0001637765008916188, "loss": 0.6451304435729981, "step": 41330 }, { "epoch": 0.24573354494712626, "grad_norm": 1.8532586097717285, "learning_rate": 0.00016381612839310483, "loss": 0.7062790393829346, "step": 41340 }, { "epoch": 0.24579298702379465, "grad_norm": 1.513115644454956, "learning_rate": 0.00016385575589459087, "loss": 0.6570498466491699, "step": 41350 }, { "epoch": 0.24585242910046307, "grad_norm": 1.9672132730484009, "learning_rate": 0.00016389538339607688, "loss": 0.6968809127807617, "step": 41360 }, { "epoch": 0.24591187117713145, "grad_norm": 1.7084801197052002, "learning_rate": 0.00016393501089756292, "loss": 0.650014591217041, "step": 41370 }, { "epoch": 0.24597131325379984, "grad_norm": 1.6654340028762817, "learning_rate": 0.00016397463839904893, "loss": 0.6748062133789062, "step": 41380 }, { "epoch": 0.24603075533046823, "grad_norm": 1.5307860374450684, "learning_rate": 0.00016401426590053497, "loss": 0.6453879833221435, "step": 41390 }, { "epoch": 0.2460901974071366, "grad_norm": 1.3886982202529907, "learning_rate": 0.00016405389340202103, "loss": 0.677060317993164, "step": 41400 }, { "epoch": 0.246149639483805, "grad_norm": 1.4902948141098022, "learning_rate": 0.00016409352090350704, "loss": 0.7092998027801514, "step": 41410 }, { "epoch": 0.2462090815604734, "grad_norm": 1.6350854635238647, "learning_rate": 0.00016413314840499308, "loss": 0.6624611854553223, "step": 41420 }, { "epoch": 0.2462685236371418, "grad_norm": 1.1987279653549194, "learning_rate": 0.0001641727759064791, "loss": 0.6231515884399415, "step": 41430 }, { "epoch": 0.2463279657138102, "grad_norm": 1.6053811311721802, "learning_rate": 0.00016421240340796513, "loss": 0.6690289497375488, "step": 41440 }, { "epoch": 0.24638740779047857, "grad_norm": 1.5539134740829468, "learning_rate": 0.00016425203090945117, "loss": 0.7018853187561035, "step": 41450 }, { "epoch": 0.24644684986714696, "grad_norm": 1.7230796813964844, "learning_rate": 0.00016429165841093718, "loss": 0.6405631542205811, "step": 41460 }, { "epoch": 0.24650629194381535, "grad_norm": 1.7183072566986084, "learning_rate": 0.00016433128591242325, "loss": 0.6592141628265381, "step": 41470 }, { "epoch": 0.24656573402048373, "grad_norm": 1.5321053266525269, "learning_rate": 0.00016437091341390926, "loss": 0.6778384208679199, "step": 41480 }, { "epoch": 0.24662517609715212, "grad_norm": 1.3359967470169067, "learning_rate": 0.0001644105409153953, "loss": 0.6709466934204101, "step": 41490 }, { "epoch": 0.2466846181738205, "grad_norm": 1.5850121974945068, "learning_rate": 0.0001644501684168813, "loss": 0.6168638229370117, "step": 41500 }, { "epoch": 0.24674406025048892, "grad_norm": 2.2172532081604004, "learning_rate": 0.00016448979591836735, "loss": 0.7102424621582031, "step": 41510 }, { "epoch": 0.2468035023271573, "grad_norm": 1.5416561365127563, "learning_rate": 0.0001645294234198534, "loss": 0.6680141448974609, "step": 41520 }, { "epoch": 0.2468629444038257, "grad_norm": 1.4485867023468018, "learning_rate": 0.0001645690509213394, "loss": 0.6537991523742676, "step": 41530 }, { "epoch": 0.24692238648049408, "grad_norm": 1.6049115657806396, "learning_rate": 0.00016460867842282547, "loss": 0.6955125808715821, "step": 41540 }, { "epoch": 0.24698182855716247, "grad_norm": 1.4510825872421265, "learning_rate": 0.00016464830592431148, "loss": 0.6673496246337891, "step": 41550 }, { "epoch": 0.24704127063383086, "grad_norm": 1.417639970779419, "learning_rate": 0.00016468793342579752, "loss": 0.7529040813446045, "step": 41560 }, { "epoch": 0.24710071271049924, "grad_norm": 1.6080458164215088, "learning_rate": 0.00016472756092728355, "loss": 0.654871654510498, "step": 41570 }, { "epoch": 0.24716015478716766, "grad_norm": 1.4853302240371704, "learning_rate": 0.00016476718842876957, "loss": 0.6653138160705566, "step": 41580 }, { "epoch": 0.24721959686383604, "grad_norm": 1.3675004243850708, "learning_rate": 0.0001648068159302556, "loss": 0.6252612590789794, "step": 41590 }, { "epoch": 0.24727903894050443, "grad_norm": 1.852649450302124, "learning_rate": 0.00016484644343174162, "loss": 0.725999402999878, "step": 41600 }, { "epoch": 0.24733848101717282, "grad_norm": 1.5117347240447998, "learning_rate": 0.00016488607093322768, "loss": 0.6489463329315186, "step": 41610 }, { "epoch": 0.2473979230938412, "grad_norm": 1.526953101158142, "learning_rate": 0.0001649256984347137, "loss": 0.6696306705474854, "step": 41620 }, { "epoch": 0.2474573651705096, "grad_norm": 1.3542238473892212, "learning_rate": 0.00016496532593619973, "loss": 0.678587818145752, "step": 41630 }, { "epoch": 0.24751680724717798, "grad_norm": 1.5034666061401367, "learning_rate": 0.00016500495343768577, "loss": 0.6803324699401856, "step": 41640 }, { "epoch": 0.24757624932384636, "grad_norm": 1.7441331148147583, "learning_rate": 0.00016504458093917178, "loss": 0.6799917221069336, "step": 41650 }, { "epoch": 0.24763569140051478, "grad_norm": 1.3775304555892944, "learning_rate": 0.00016508420844065782, "loss": 0.6266517639160156, "step": 41660 }, { "epoch": 0.24769513347718317, "grad_norm": 1.7090178728103638, "learning_rate": 0.00016512383594214383, "loss": 0.7188297271728515, "step": 41670 }, { "epoch": 0.24775457555385155, "grad_norm": 1.614902377128601, "learning_rate": 0.0001651634634436299, "loss": 0.6042159080505372, "step": 41680 }, { "epoch": 0.24781401763051994, "grad_norm": 1.4433780908584595, "learning_rate": 0.00016520309094511594, "loss": 0.6533171176910401, "step": 41690 }, { "epoch": 0.24787345970718833, "grad_norm": 1.6926766633987427, "learning_rate": 0.00016524271844660195, "loss": 0.6765787124633789, "step": 41700 }, { "epoch": 0.2479329017838567, "grad_norm": 1.6004905700683594, "learning_rate": 0.000165282345948088, "loss": 0.703615379333496, "step": 41710 }, { "epoch": 0.2479923438605251, "grad_norm": 1.4778467416763306, "learning_rate": 0.000165321973449574, "loss": 0.6618134498596191, "step": 41720 }, { "epoch": 0.24805178593719351, "grad_norm": 1.7796504497528076, "learning_rate": 0.00016536160095106004, "loss": 0.6732564926147461, "step": 41730 }, { "epoch": 0.2481112280138619, "grad_norm": 1.5648715496063232, "learning_rate": 0.00016540122845254608, "loss": 0.6674368381500244, "step": 41740 }, { "epoch": 0.2481706700905303, "grad_norm": 1.6301120519638062, "learning_rate": 0.00016544085595403211, "loss": 0.671888780593872, "step": 41750 }, { "epoch": 0.24823011216719867, "grad_norm": 1.6803313493728638, "learning_rate": 0.00016548048345551815, "loss": 0.6053466796875, "step": 41760 }, { "epoch": 0.24828955424386706, "grad_norm": 1.277104377746582, "learning_rate": 0.00016552011095700416, "loss": 0.6424649238586426, "step": 41770 }, { "epoch": 0.24834899632053545, "grad_norm": 1.4405964612960815, "learning_rate": 0.0001655597384584902, "loss": 0.6274245262145997, "step": 41780 }, { "epoch": 0.24840843839720383, "grad_norm": 1.5779881477355957, "learning_rate": 0.00016559936595997622, "loss": 0.7275341987609864, "step": 41790 }, { "epoch": 0.24846788047387225, "grad_norm": 1.5752514600753784, "learning_rate": 0.00016563899346146225, "loss": 0.6794118881225586, "step": 41800 }, { "epoch": 0.24852732255054064, "grad_norm": 2.145470142364502, "learning_rate": 0.0001656786209629483, "loss": 0.7073912143707275, "step": 41810 }, { "epoch": 0.24858676462720902, "grad_norm": 1.7635948657989502, "learning_rate": 0.00016571824846443433, "loss": 0.6752388000488281, "step": 41820 }, { "epoch": 0.2486462067038774, "grad_norm": 1.9942386150360107, "learning_rate": 0.00016575787596592037, "loss": 0.7274550914764404, "step": 41830 }, { "epoch": 0.2487056487805458, "grad_norm": 1.7262418270111084, "learning_rate": 0.00016579750346740638, "loss": 0.714457893371582, "step": 41840 }, { "epoch": 0.24876509085721418, "grad_norm": 1.717665195465088, "learning_rate": 0.00016583713096889242, "loss": 0.7623664855957031, "step": 41850 }, { "epoch": 0.24882453293388257, "grad_norm": 1.683089017868042, "learning_rate": 0.00016587675847037846, "loss": 0.6052308559417725, "step": 41860 }, { "epoch": 0.24888397501055096, "grad_norm": 1.9174973964691162, "learning_rate": 0.00016591638597186447, "loss": 0.6680517196655273, "step": 41870 }, { "epoch": 0.24894341708721937, "grad_norm": 1.6091437339782715, "learning_rate": 0.0001659560134733505, "loss": 0.6278635025024414, "step": 41880 }, { "epoch": 0.24900285916388776, "grad_norm": 1.7914776802062988, "learning_rate": 0.00016599564097483655, "loss": 0.68153977394104, "step": 41890 }, { "epoch": 0.24906230124055614, "grad_norm": 1.8528634309768677, "learning_rate": 0.00016603526847632259, "loss": 0.6710105895996094, "step": 41900 }, { "epoch": 0.24912174331722453, "grad_norm": 1.4966621398925781, "learning_rate": 0.0001660748959778086, "loss": 0.7032964706420899, "step": 41910 }, { "epoch": 0.24918118539389292, "grad_norm": 1.347360610961914, "learning_rate": 0.00016611452347929464, "loss": 0.7085318565368652, "step": 41920 }, { "epoch": 0.2492406274705613, "grad_norm": 1.54646897315979, "learning_rate": 0.00016615415098078068, "loss": 0.6459529399871826, "step": 41930 }, { "epoch": 0.2493000695472297, "grad_norm": 1.7132796049118042, "learning_rate": 0.0001661937784822667, "loss": 0.6881353855133057, "step": 41940 }, { "epoch": 0.2493595116238981, "grad_norm": 1.4748752117156982, "learning_rate": 0.00016623340598375273, "loss": 0.6094849586486817, "step": 41950 }, { "epoch": 0.2494189537005665, "grad_norm": 1.5062307119369507, "learning_rate": 0.00016627303348523876, "loss": 0.7186432838439941, "step": 41960 }, { "epoch": 0.24947839577723488, "grad_norm": 1.7761069536209106, "learning_rate": 0.0001663126609867248, "loss": 0.6730260848999023, "step": 41970 }, { "epoch": 0.24953783785390327, "grad_norm": 1.7000858783721924, "learning_rate": 0.00016635228848821084, "loss": 0.7017573356628418, "step": 41980 }, { "epoch": 0.24959727993057165, "grad_norm": 2.05265474319458, "learning_rate": 0.00016639191598969685, "loss": 0.7181148529052734, "step": 41990 }, { "epoch": 0.24965672200724004, "grad_norm": 1.696763277053833, "learning_rate": 0.0001664315434911829, "loss": 0.6642961502075195, "step": 42000 }, { "epoch": 0.24971616408390843, "grad_norm": 1.5805190801620483, "learning_rate": 0.0001664711709926689, "loss": 0.7256345748901367, "step": 42010 }, { "epoch": 0.2497756061605768, "grad_norm": 1.8086234331130981, "learning_rate": 0.00016651079849415497, "loss": 0.7330124855041504, "step": 42020 }, { "epoch": 0.24983504823724523, "grad_norm": 1.7231547832489014, "learning_rate": 0.00016655042599564098, "loss": 0.64628586769104, "step": 42030 }, { "epoch": 0.24989449031391361, "grad_norm": 1.948980450630188, "learning_rate": 0.00016659005349712702, "loss": 0.6703188419342041, "step": 42040 }, { "epoch": 0.249953932390582, "grad_norm": 1.7130049467086792, "learning_rate": 0.00016662968099861306, "loss": 0.6624903202056884, "step": 42050 }, { "epoch": 0.2500133744672504, "grad_norm": 1.380564570426941, "learning_rate": 0.00016666930850009907, "loss": 0.6320401191711426, "step": 42060 }, { "epoch": 0.2500728165439188, "grad_norm": 1.7567076683044434, "learning_rate": 0.0001667089360015851, "loss": 0.7074016094207763, "step": 42070 }, { "epoch": 0.2501322586205872, "grad_norm": 1.2507747411727905, "learning_rate": 0.00016674856350307112, "loss": 0.708835506439209, "step": 42080 }, { "epoch": 0.25019170069725555, "grad_norm": 1.4683384895324707, "learning_rate": 0.00016678819100455719, "loss": 0.6570475101470947, "step": 42090 }, { "epoch": 0.25025114277392396, "grad_norm": 1.1595340967178345, "learning_rate": 0.0001668278185060432, "loss": 0.6608040809631348, "step": 42100 }, { "epoch": 0.2503105848505923, "grad_norm": 1.9012119770050049, "learning_rate": 0.00016686744600752924, "loss": 0.6586977005004883, "step": 42110 }, { "epoch": 0.25037002692726074, "grad_norm": 1.3990862369537354, "learning_rate": 0.00016690707350901527, "loss": 0.6409474372863769, "step": 42120 }, { "epoch": 0.2504294690039291, "grad_norm": 1.4892315864562988, "learning_rate": 0.00016694670101050129, "loss": 0.6669241428375244, "step": 42130 }, { "epoch": 0.2504889110805975, "grad_norm": 1.694350242614746, "learning_rate": 0.00016698632851198732, "loss": 0.6941840648651123, "step": 42140 }, { "epoch": 0.2505483531572659, "grad_norm": 1.8831621408462524, "learning_rate": 0.00016702595601347336, "loss": 0.7316416740417481, "step": 42150 }, { "epoch": 0.2506077952339343, "grad_norm": 1.6024925708770752, "learning_rate": 0.0001670655835149594, "loss": 0.6169574737548829, "step": 42160 }, { "epoch": 0.2506672373106027, "grad_norm": 1.440489649772644, "learning_rate": 0.00016710521101644544, "loss": 0.6856017112731934, "step": 42170 }, { "epoch": 0.25072667938727106, "grad_norm": 1.860660433769226, "learning_rate": 0.00016714483851793145, "loss": 0.7582269191741944, "step": 42180 }, { "epoch": 0.25078612146393947, "grad_norm": 1.5770394802093506, "learning_rate": 0.0001671844660194175, "loss": 0.654604721069336, "step": 42190 }, { "epoch": 0.25084556354060783, "grad_norm": 1.619884729385376, "learning_rate": 0.0001672240935209035, "loss": 0.7282025337219238, "step": 42200 }, { "epoch": 0.25090500561727624, "grad_norm": 1.8452427387237549, "learning_rate": 0.00016726372102238954, "loss": 0.679985523223877, "step": 42210 }, { "epoch": 0.25096444769394466, "grad_norm": 1.6688202619552612, "learning_rate": 0.00016730334852387558, "loss": 0.6842077255249024, "step": 42220 }, { "epoch": 0.251023889770613, "grad_norm": 1.8712584972381592, "learning_rate": 0.00016734297602536162, "loss": 0.7111624717712403, "step": 42230 }, { "epoch": 0.25108333184728143, "grad_norm": 1.3912134170532227, "learning_rate": 0.00016738260352684766, "loss": 0.7003750801086426, "step": 42240 }, { "epoch": 0.2511427739239498, "grad_norm": 1.663275122642517, "learning_rate": 0.00016742223102833367, "loss": 0.6412817001342773, "step": 42250 }, { "epoch": 0.2512022160006182, "grad_norm": 1.2765657901763916, "learning_rate": 0.0001674618585298197, "loss": 0.6663915634155273, "step": 42260 }, { "epoch": 0.25126165807728656, "grad_norm": 1.600143313407898, "learning_rate": 0.00016750148603130575, "loss": 0.679557991027832, "step": 42270 }, { "epoch": 0.251321100153955, "grad_norm": 1.7118034362792969, "learning_rate": 0.00016754111353279176, "loss": 0.675913143157959, "step": 42280 }, { "epoch": 0.2513805422306234, "grad_norm": 1.6820915937423706, "learning_rate": 0.0001675807410342778, "loss": 0.6804870128631592, "step": 42290 }, { "epoch": 0.25143998430729175, "grad_norm": 1.7144145965576172, "learning_rate": 0.00016762036853576383, "loss": 0.703830337524414, "step": 42300 }, { "epoch": 0.25149942638396017, "grad_norm": 1.8613237142562866, "learning_rate": 0.00016765999603724987, "loss": 0.6533102989196777, "step": 42310 }, { "epoch": 0.2515588684606285, "grad_norm": 1.5377126932144165, "learning_rate": 0.00016769962353873588, "loss": 0.6482923984527588, "step": 42320 }, { "epoch": 0.25161831053729694, "grad_norm": 1.5932000875473022, "learning_rate": 0.00016773925104022192, "loss": 0.6913919448852539, "step": 42330 }, { "epoch": 0.2516777526139653, "grad_norm": 1.3237969875335693, "learning_rate": 0.00016777887854170796, "loss": 0.6553433418273926, "step": 42340 }, { "epoch": 0.2517371946906337, "grad_norm": 1.658313512802124, "learning_rate": 0.00016781850604319397, "loss": 0.6797930717468261, "step": 42350 }, { "epoch": 0.25179663676730213, "grad_norm": 1.6286019086837769, "learning_rate": 0.00016785813354468, "loss": 0.6394891738891602, "step": 42360 }, { "epoch": 0.2518560788439705, "grad_norm": 1.6176422834396362, "learning_rate": 0.00016789776104616605, "loss": 0.6975006103515625, "step": 42370 }, { "epoch": 0.2519155209206389, "grad_norm": 1.4586509466171265, "learning_rate": 0.0001679373885476521, "loss": 0.7005992889404297, "step": 42380 }, { "epoch": 0.25197496299730726, "grad_norm": 1.7143954038619995, "learning_rate": 0.0001679770160491381, "loss": 0.6948164939880371, "step": 42390 }, { "epoch": 0.2520344050739757, "grad_norm": 1.445737600326538, "learning_rate": 0.00016801664355062414, "loss": 0.7157296657562255, "step": 42400 }, { "epoch": 0.25209384715064403, "grad_norm": 1.370279312133789, "learning_rate": 0.00016805627105211018, "loss": 0.6759572982788086, "step": 42410 }, { "epoch": 0.25215328922731245, "grad_norm": 1.4466625452041626, "learning_rate": 0.0001680958985535962, "loss": 0.6875252723693848, "step": 42420 }, { "epoch": 0.2522127313039808, "grad_norm": 1.5332965850830078, "learning_rate": 0.00016813552605508223, "loss": 0.6833765983581543, "step": 42430 }, { "epoch": 0.2522721733806492, "grad_norm": 2.041203022003174, "learning_rate": 0.00016817515355656827, "loss": 0.6326137542724609, "step": 42440 }, { "epoch": 0.25233161545731764, "grad_norm": 1.6932549476623535, "learning_rate": 0.0001682147810580543, "loss": 0.6253972053527832, "step": 42450 }, { "epoch": 0.252391057533986, "grad_norm": 1.5243865251541138, "learning_rate": 0.00016825440855954034, "loss": 0.6397648334503174, "step": 42460 }, { "epoch": 0.2524504996106544, "grad_norm": 1.6211230754852295, "learning_rate": 0.00016829403606102636, "loss": 0.6844632625579834, "step": 42470 }, { "epoch": 0.25250994168732277, "grad_norm": 1.9144238233566284, "learning_rate": 0.0001683336635625124, "loss": 0.6134156227111817, "step": 42480 }, { "epoch": 0.2525693837639912, "grad_norm": 1.6040685176849365, "learning_rate": 0.0001683732910639984, "loss": 0.6690558433532715, "step": 42490 }, { "epoch": 0.25262882584065954, "grad_norm": 1.7477169036865234, "learning_rate": 0.00016841291856548444, "loss": 0.7115755081176758, "step": 42500 }, { "epoch": 0.25268826791732796, "grad_norm": 1.4266042709350586, "learning_rate": 0.00016845254606697048, "loss": 0.6371426582336426, "step": 42510 }, { "epoch": 0.2527477099939964, "grad_norm": 1.608704924583435, "learning_rate": 0.00016849217356845652, "loss": 0.6785165786743164, "step": 42520 }, { "epoch": 0.25280715207066473, "grad_norm": 1.744666576385498, "learning_rate": 0.00016853180106994256, "loss": 0.617929220199585, "step": 42530 }, { "epoch": 0.25286659414733315, "grad_norm": 1.3888911008834839, "learning_rate": 0.00016857142857142857, "loss": 0.6426566123962403, "step": 42540 }, { "epoch": 0.2529260362240015, "grad_norm": 1.4844106435775757, "learning_rate": 0.0001686110560729146, "loss": 0.6959778785705566, "step": 42550 }, { "epoch": 0.2529854783006699, "grad_norm": 1.3374983072280884, "learning_rate": 0.00016865068357440065, "loss": 0.6800782203674316, "step": 42560 }, { "epoch": 0.2530449203773383, "grad_norm": 1.8347989320755005, "learning_rate": 0.00016869031107588666, "loss": 0.7070806503295899, "step": 42570 }, { "epoch": 0.2531043624540067, "grad_norm": 1.6314764022827148, "learning_rate": 0.00016872993857737273, "loss": 0.7067140579223633, "step": 42580 }, { "epoch": 0.2531638045306751, "grad_norm": 1.8724702596664429, "learning_rate": 0.00016876956607885874, "loss": 0.7001371860504151, "step": 42590 }, { "epoch": 0.25322324660734347, "grad_norm": 1.5241518020629883, "learning_rate": 0.00016880919358034478, "loss": 0.6461695671081543, "step": 42600 }, { "epoch": 0.2532826886840119, "grad_norm": 1.6923187971115112, "learning_rate": 0.0001688488210818308, "loss": 0.6863224029541015, "step": 42610 }, { "epoch": 0.25334213076068024, "grad_norm": 1.5455056428909302, "learning_rate": 0.00016888844858331683, "loss": 0.6632142066955566, "step": 42620 }, { "epoch": 0.25340157283734865, "grad_norm": 1.5636048316955566, "learning_rate": 0.00016892807608480287, "loss": 0.6435593128204345, "step": 42630 }, { "epoch": 0.253461014914017, "grad_norm": 1.4229159355163574, "learning_rate": 0.00016896770358628888, "loss": 0.6973326206207275, "step": 42640 }, { "epoch": 0.2535204569906854, "grad_norm": 1.5069341659545898, "learning_rate": 0.00016900733108777494, "loss": 0.6533061027526855, "step": 42650 }, { "epoch": 0.25357989906735384, "grad_norm": 1.6062207221984863, "learning_rate": 0.00016904695858926095, "loss": 0.6244892597198486, "step": 42660 }, { "epoch": 0.2536393411440222, "grad_norm": 1.8300305604934692, "learning_rate": 0.000169086586090747, "loss": 0.6653450489044189, "step": 42670 }, { "epoch": 0.2536987832206906, "grad_norm": 1.793589472770691, "learning_rate": 0.000169126213592233, "loss": 0.6226290702819824, "step": 42680 }, { "epoch": 0.253758225297359, "grad_norm": 1.5358387231826782, "learning_rate": 0.00016916584109371904, "loss": 0.6610243797302247, "step": 42690 }, { "epoch": 0.2538176673740274, "grad_norm": 2.1989731788635254, "learning_rate": 0.00016920546859520508, "loss": 0.6689672946929932, "step": 42700 }, { "epoch": 0.25387710945069575, "grad_norm": 2.0318603515625, "learning_rate": 0.0001692450960966911, "loss": 0.6797260284423828, "step": 42710 }, { "epoch": 0.25393655152736416, "grad_norm": 1.7337939739227295, "learning_rate": 0.00016928472359817716, "loss": 0.6619452476501465, "step": 42720 }, { "epoch": 0.2539959936040326, "grad_norm": 1.8564609289169312, "learning_rate": 0.00016932435109966317, "loss": 0.6678915977478027, "step": 42730 }, { "epoch": 0.25405543568070094, "grad_norm": 1.8138822317123413, "learning_rate": 0.0001693639786011492, "loss": 0.7036484718322754, "step": 42740 }, { "epoch": 0.25411487775736935, "grad_norm": 1.368473768234253, "learning_rate": 0.00016940360610263525, "loss": 0.6201753616333008, "step": 42750 }, { "epoch": 0.2541743198340377, "grad_norm": 1.6864533424377441, "learning_rate": 0.00016944323360412126, "loss": 0.727239990234375, "step": 42760 }, { "epoch": 0.2542337619107061, "grad_norm": 1.7714955806732178, "learning_rate": 0.0001694828611056073, "loss": 0.6267007827758789, "step": 42770 }, { "epoch": 0.2542932039873745, "grad_norm": 1.6710282564163208, "learning_rate": 0.0001695224886070933, "loss": 0.6698170661926269, "step": 42780 }, { "epoch": 0.2543526460640429, "grad_norm": 1.5812454223632812, "learning_rate": 0.00016956211610857938, "loss": 0.6722210884094239, "step": 42790 }, { "epoch": 0.25441208814071126, "grad_norm": 1.5146405696868896, "learning_rate": 0.0001696017436100654, "loss": 0.7065868377685547, "step": 42800 }, { "epoch": 0.25447153021737967, "grad_norm": 1.433303713798523, "learning_rate": 0.00016964137111155143, "loss": 0.6648705959320068, "step": 42810 }, { "epoch": 0.2545309722940481, "grad_norm": 1.8485543727874756, "learning_rate": 0.00016968099861303746, "loss": 0.7543204307556153, "step": 42820 }, { "epoch": 0.25459041437071644, "grad_norm": 1.3457481861114502, "learning_rate": 0.00016972062611452348, "loss": 0.6046220779418945, "step": 42830 }, { "epoch": 0.25464985644738486, "grad_norm": 1.7111468315124512, "learning_rate": 0.00016976025361600951, "loss": 0.6757069587707519, "step": 42840 }, { "epoch": 0.2547092985240532, "grad_norm": 1.4098645448684692, "learning_rate": 0.00016979988111749555, "loss": 0.6707325935363769, "step": 42850 }, { "epoch": 0.25476874060072163, "grad_norm": 1.716747522354126, "learning_rate": 0.0001698395086189816, "loss": 0.6766513824462891, "step": 42860 }, { "epoch": 0.25482818267739, "grad_norm": 1.8970415592193604, "learning_rate": 0.00016987913612046763, "loss": 0.6984676361083985, "step": 42870 }, { "epoch": 0.2548876247540584, "grad_norm": 1.7620786428451538, "learning_rate": 0.00016991876362195364, "loss": 0.6724756240844727, "step": 42880 }, { "epoch": 0.2549470668307268, "grad_norm": 1.9054865837097168, "learning_rate": 0.00016995839112343968, "loss": 0.6421789169311524, "step": 42890 }, { "epoch": 0.2550065089073952, "grad_norm": 1.6404836177825928, "learning_rate": 0.0001699980186249257, "loss": 0.6831934928894043, "step": 42900 }, { "epoch": 0.2550659509840636, "grad_norm": 1.6763192415237427, "learning_rate": 0.00017003764612641173, "loss": 0.689204216003418, "step": 42910 }, { "epoch": 0.25512539306073195, "grad_norm": 1.7598859071731567, "learning_rate": 0.00017007727362789777, "loss": 0.7005744934082031, "step": 42920 }, { "epoch": 0.25518483513740037, "grad_norm": 1.7094519138336182, "learning_rate": 0.0001701169011293838, "loss": 0.6935214042663574, "step": 42930 }, { "epoch": 0.2552442772140687, "grad_norm": 1.56015145778656, "learning_rate": 0.00017015652863086985, "loss": 0.6667814731597901, "step": 42940 }, { "epoch": 0.25530371929073714, "grad_norm": 1.5936594009399414, "learning_rate": 0.00017019615613235586, "loss": 0.7231799125671386, "step": 42950 }, { "epoch": 0.25536316136740556, "grad_norm": 1.6695791482925415, "learning_rate": 0.0001702357836338419, "loss": 0.6668821334838867, "step": 42960 }, { "epoch": 0.2554226034440739, "grad_norm": 1.5740106105804443, "learning_rate": 0.0001702754111353279, "loss": 0.6516548156738281, "step": 42970 }, { "epoch": 0.25548204552074233, "grad_norm": 2.0586867332458496, "learning_rate": 0.00017031503863681395, "loss": 0.7257155895233154, "step": 42980 }, { "epoch": 0.2555414875974107, "grad_norm": 1.6087005138397217, "learning_rate": 0.00017035466613829999, "loss": 0.6407800674438476, "step": 42990 }, { "epoch": 0.2556009296740791, "grad_norm": 1.6623245477676392, "learning_rate": 0.00017039429363978602, "loss": 0.6746361732482911, "step": 43000 }, { "epoch": 0.25566037175074746, "grad_norm": 1.4279464483261108, "learning_rate": 0.00017043392114127206, "loss": 0.6997458457946777, "step": 43010 }, { "epoch": 0.2557198138274159, "grad_norm": 1.7252297401428223, "learning_rate": 0.00017047354864275808, "loss": 0.6680850982666016, "step": 43020 }, { "epoch": 0.2557792559040843, "grad_norm": 1.8704171180725098, "learning_rate": 0.00017051317614424411, "loss": 0.7087646007537842, "step": 43030 }, { "epoch": 0.25583869798075265, "grad_norm": 1.6102725267410278, "learning_rate": 0.00017055280364573015, "loss": 0.6579148292541503, "step": 43040 }, { "epoch": 0.25589814005742106, "grad_norm": 1.6526286602020264, "learning_rate": 0.00017059243114721616, "loss": 0.652140474319458, "step": 43050 }, { "epoch": 0.2559575821340894, "grad_norm": 1.6806328296661377, "learning_rate": 0.0001706320586487022, "loss": 0.6773016452789307, "step": 43060 }, { "epoch": 0.25601702421075784, "grad_norm": 1.8397973775863647, "learning_rate": 0.00017067168615018824, "loss": 0.6771805286407471, "step": 43070 }, { "epoch": 0.2560764662874262, "grad_norm": 1.7202693223953247, "learning_rate": 0.00017071131365167428, "loss": 0.7057302474975586, "step": 43080 }, { "epoch": 0.2561359083640946, "grad_norm": 1.3118324279785156, "learning_rate": 0.0001707509411531603, "loss": 0.6963249206542969, "step": 43090 }, { "epoch": 0.256195350440763, "grad_norm": 1.5444570779800415, "learning_rate": 0.00017079056865464633, "loss": 0.7219285011291504, "step": 43100 }, { "epoch": 0.2562547925174314, "grad_norm": 1.4848078489303589, "learning_rate": 0.00017083019615613237, "loss": 0.6574841499328613, "step": 43110 }, { "epoch": 0.2563142345940998, "grad_norm": 1.4200241565704346, "learning_rate": 0.00017086982365761838, "loss": 0.7534778594970704, "step": 43120 }, { "epoch": 0.25637367667076816, "grad_norm": 1.8876466751098633, "learning_rate": 0.00017090945115910442, "loss": 0.6863667488098144, "step": 43130 }, { "epoch": 0.2564331187474366, "grad_norm": 1.8590307235717773, "learning_rate": 0.00017094907866059046, "loss": 0.6959959983825683, "step": 43140 }, { "epoch": 0.25649256082410493, "grad_norm": 1.7288877964019775, "learning_rate": 0.0001709887061620765, "loss": 0.6786369800567627, "step": 43150 }, { "epoch": 0.25655200290077335, "grad_norm": 1.6569393873214722, "learning_rate": 0.00017102833366356254, "loss": 0.6301254272460938, "step": 43160 }, { "epoch": 0.2566114449774417, "grad_norm": 1.5389671325683594, "learning_rate": 0.00017106796116504855, "loss": 0.7003580093383789, "step": 43170 }, { "epoch": 0.2566708870541101, "grad_norm": 1.785797119140625, "learning_rate": 0.00017110758866653459, "loss": 0.6632946491241455, "step": 43180 }, { "epoch": 0.25673032913077853, "grad_norm": 2.15087890625, "learning_rate": 0.0001711472161680206, "loss": 0.6835914134979248, "step": 43190 }, { "epoch": 0.2567897712074469, "grad_norm": 1.5070881843566895, "learning_rate": 0.00017118684366950664, "loss": 0.6265841960906983, "step": 43200 }, { "epoch": 0.2568492132841153, "grad_norm": 1.6932263374328613, "learning_rate": 0.00017122647117099267, "loss": 0.7037185668945313, "step": 43210 }, { "epoch": 0.25690865536078367, "grad_norm": 1.4717881679534912, "learning_rate": 0.0001712660986724787, "loss": 0.6216569423675538, "step": 43220 }, { "epoch": 0.2569680974374521, "grad_norm": 1.796910047531128, "learning_rate": 0.00017130572617396475, "loss": 0.6333617687225341, "step": 43230 }, { "epoch": 0.25702753951412044, "grad_norm": 1.942474365234375, "learning_rate": 0.00017134535367545076, "loss": 0.6586222648620605, "step": 43240 }, { "epoch": 0.25708698159078885, "grad_norm": 1.418445348739624, "learning_rate": 0.0001713849811769368, "loss": 0.6717475891113281, "step": 43250 }, { "epoch": 0.25714642366745727, "grad_norm": 1.812204122543335, "learning_rate": 0.0001714246086784228, "loss": 0.7065245628356933, "step": 43260 }, { "epoch": 0.25720586574412563, "grad_norm": 1.5838359594345093, "learning_rate": 0.00017146423617990885, "loss": 0.7016184806823731, "step": 43270 }, { "epoch": 0.25726530782079404, "grad_norm": 1.821060299873352, "learning_rate": 0.00017150386368139492, "loss": 0.7177506446838379, "step": 43280 }, { "epoch": 0.2573247498974624, "grad_norm": 1.7958134412765503, "learning_rate": 0.00017154349118288093, "loss": 0.6675433158874512, "step": 43290 }, { "epoch": 0.2573841919741308, "grad_norm": 1.531692385673523, "learning_rate": 0.00017158311868436697, "loss": 0.7008181571960449, "step": 43300 }, { "epoch": 0.2574436340507992, "grad_norm": 1.790552020072937, "learning_rate": 0.00017162274618585298, "loss": 0.6792095184326172, "step": 43310 }, { "epoch": 0.2575030761274676, "grad_norm": 1.733575463294983, "learning_rate": 0.00017166237368733902, "loss": 0.6951607704162598, "step": 43320 }, { "epoch": 0.257562518204136, "grad_norm": 1.8656121492385864, "learning_rate": 0.00017170200118882506, "loss": 0.712978744506836, "step": 43330 }, { "epoch": 0.25762196028080436, "grad_norm": 1.3377844095230103, "learning_rate": 0.00017174162869031107, "loss": 0.6258925437927246, "step": 43340 }, { "epoch": 0.2576814023574728, "grad_norm": 1.5494039058685303, "learning_rate": 0.00017178125619179713, "loss": 0.647825050354004, "step": 43350 }, { "epoch": 0.25774084443414114, "grad_norm": 1.554369568824768, "learning_rate": 0.00017182088369328315, "loss": 0.6610496520996094, "step": 43360 }, { "epoch": 0.25780028651080955, "grad_norm": 1.397868275642395, "learning_rate": 0.00017186051119476918, "loss": 0.6721375465393067, "step": 43370 }, { "epoch": 0.2578597285874779, "grad_norm": 1.824618935585022, "learning_rate": 0.0001719001386962552, "loss": 0.6996889114379883, "step": 43380 }, { "epoch": 0.2579191706641463, "grad_norm": 2.131807804107666, "learning_rate": 0.00017193976619774123, "loss": 0.6770180702209473, "step": 43390 }, { "epoch": 0.25797861274081474, "grad_norm": 1.720390796661377, "learning_rate": 0.00017197939369922727, "loss": 0.7155091285705566, "step": 43400 }, { "epoch": 0.2580380548174831, "grad_norm": 1.3847020864486694, "learning_rate": 0.00017201902120071328, "loss": 0.7191506862640381, "step": 43410 }, { "epoch": 0.2580974968941515, "grad_norm": 1.5728576183319092, "learning_rate": 0.00017205864870219935, "loss": 0.6949105262756348, "step": 43420 }, { "epoch": 0.25815693897081987, "grad_norm": 1.6114444732666016, "learning_rate": 0.00017209827620368536, "loss": 0.6297209739685059, "step": 43430 }, { "epoch": 0.2582163810474883, "grad_norm": 1.4841835498809814, "learning_rate": 0.0001721379037051714, "loss": 0.7067585945129394, "step": 43440 }, { "epoch": 0.25827582312415664, "grad_norm": 1.5987650156021118, "learning_rate": 0.00017217753120665744, "loss": 0.6554841518402099, "step": 43450 }, { "epoch": 0.25833526520082506, "grad_norm": 1.682669997215271, "learning_rate": 0.00017221715870814345, "loss": 0.7161943435668945, "step": 43460 }, { "epoch": 0.2583947072774935, "grad_norm": 1.9078490734100342, "learning_rate": 0.0001722567862096295, "loss": 0.6504025459289551, "step": 43470 }, { "epoch": 0.25845414935416183, "grad_norm": 1.9348351955413818, "learning_rate": 0.0001722964137111155, "loss": 0.6652641296386719, "step": 43480 }, { "epoch": 0.25851359143083025, "grad_norm": 1.4791250228881836, "learning_rate": 0.00017233604121260157, "loss": 0.6438240528106689, "step": 43490 }, { "epoch": 0.2585730335074986, "grad_norm": 1.4803545475006104, "learning_rate": 0.00017237566871408758, "loss": 0.7465383529663085, "step": 43500 }, { "epoch": 0.258632475584167, "grad_norm": 1.7665971517562866, "learning_rate": 0.00017241529621557362, "loss": 0.6724594116210938, "step": 43510 }, { "epoch": 0.2586919176608354, "grad_norm": 1.4605588912963867, "learning_rate": 0.00017245492371705966, "loss": 0.7077961921691894, "step": 43520 }, { "epoch": 0.2587513597375038, "grad_norm": 1.3798706531524658, "learning_rate": 0.00017249455121854567, "loss": 0.6810657978057861, "step": 43530 }, { "epoch": 0.25881080181417215, "grad_norm": 1.6568529605865479, "learning_rate": 0.0001725341787200317, "loss": 0.7257966518402099, "step": 43540 }, { "epoch": 0.25887024389084057, "grad_norm": 1.6041752099990845, "learning_rate": 0.00017257380622151774, "loss": 0.7183911323547363, "step": 43550 }, { "epoch": 0.258929685967509, "grad_norm": 1.8971542119979858, "learning_rate": 0.00017261343372300378, "loss": 0.6730572700500488, "step": 43560 }, { "epoch": 0.25898912804417734, "grad_norm": 1.734854817390442, "learning_rate": 0.00017265306122448982, "loss": 0.7399263381958008, "step": 43570 }, { "epoch": 0.25904857012084576, "grad_norm": 1.8178867101669312, "learning_rate": 0.00017269268872597583, "loss": 0.6808276176452637, "step": 43580 }, { "epoch": 0.2591080121975141, "grad_norm": 1.3582379817962646, "learning_rate": 0.00017273231622746187, "loss": 0.7166576385498047, "step": 43590 }, { "epoch": 0.25916745427418253, "grad_norm": 1.681523323059082, "learning_rate": 0.00017277194372894788, "loss": 0.6953486442565918, "step": 43600 }, { "epoch": 0.2592268963508509, "grad_norm": 2.2852213382720947, "learning_rate": 0.00017281157123043392, "loss": 0.6883116245269776, "step": 43610 }, { "epoch": 0.2592863384275193, "grad_norm": 1.5138109922409058, "learning_rate": 0.00017285119873191996, "loss": 0.6546177387237548, "step": 43620 }, { "epoch": 0.2593457805041877, "grad_norm": 1.645675539970398, "learning_rate": 0.000172890826233406, "loss": 0.6459781646728515, "step": 43630 }, { "epoch": 0.2594052225808561, "grad_norm": 1.8163537979125977, "learning_rate": 0.00017293045373489204, "loss": 0.6373971939086914, "step": 43640 }, { "epoch": 0.2594646646575245, "grad_norm": 1.4438531398773193, "learning_rate": 0.00017297008123637805, "loss": 0.6688271522521972, "step": 43650 }, { "epoch": 0.25952410673419285, "grad_norm": 1.689539909362793, "learning_rate": 0.0001730097087378641, "loss": 0.7010747909545898, "step": 43660 }, { "epoch": 0.25958354881086126, "grad_norm": 1.7665934562683105, "learning_rate": 0.0001730493362393501, "loss": 0.7307144165039062, "step": 43670 }, { "epoch": 0.2596429908875296, "grad_norm": 1.6792852878570557, "learning_rate": 0.00017308896374083614, "loss": 0.6748661041259766, "step": 43680 }, { "epoch": 0.25970243296419804, "grad_norm": 1.766830325126648, "learning_rate": 0.00017312859124232218, "loss": 0.6696946144104003, "step": 43690 }, { "epoch": 0.25976187504086645, "grad_norm": 1.260967493057251, "learning_rate": 0.00017316821874380822, "loss": 0.7618003845214844, "step": 43700 }, { "epoch": 0.2598213171175348, "grad_norm": 1.943136215209961, "learning_rate": 0.00017320784624529425, "loss": 0.7027029991149902, "step": 43710 }, { "epoch": 0.2598807591942032, "grad_norm": 1.6887842416763306, "learning_rate": 0.00017324747374678027, "loss": 0.7260231018066406, "step": 43720 }, { "epoch": 0.2599402012708716, "grad_norm": 1.5830731391906738, "learning_rate": 0.0001732871012482663, "loss": 0.6792078018188477, "step": 43730 }, { "epoch": 0.25999964334754, "grad_norm": 1.5768159627914429, "learning_rate": 0.00017332672874975234, "loss": 0.6601292610168457, "step": 43740 }, { "epoch": 0.26005908542420836, "grad_norm": 1.8184740543365479, "learning_rate": 0.00017336635625123835, "loss": 0.7091912269592285, "step": 43750 }, { "epoch": 0.2601185275008768, "grad_norm": 1.5996845960617065, "learning_rate": 0.0001734059837527244, "loss": 0.6761879920959473, "step": 43760 }, { "epoch": 0.2601779695775452, "grad_norm": 1.435779094696045, "learning_rate": 0.00017344561125421043, "loss": 0.6416355609893799, "step": 43770 }, { "epoch": 0.26023741165421355, "grad_norm": 2.258634090423584, "learning_rate": 0.00017348523875569647, "loss": 0.7307579994201661, "step": 43780 }, { "epoch": 0.26029685373088196, "grad_norm": 1.6179418563842773, "learning_rate": 0.00017352486625718248, "loss": 0.6967043399810791, "step": 43790 }, { "epoch": 0.2603562958075503, "grad_norm": 1.5564868450164795, "learning_rate": 0.00017356449375866852, "loss": 0.6390670776367188, "step": 43800 }, { "epoch": 0.26041573788421873, "grad_norm": 1.5681252479553223, "learning_rate": 0.00017360412126015456, "loss": 0.6944990158081055, "step": 43810 }, { "epoch": 0.2604751799608871, "grad_norm": 1.8807748556137085, "learning_rate": 0.00017364374876164057, "loss": 0.6788723468780518, "step": 43820 }, { "epoch": 0.2605346220375555, "grad_norm": 1.2429263591766357, "learning_rate": 0.00017368337626312664, "loss": 0.703464126586914, "step": 43830 }, { "epoch": 0.2605940641142239, "grad_norm": 1.3462738990783691, "learning_rate": 0.00017372300376461265, "loss": 0.6591498374938964, "step": 43840 }, { "epoch": 0.2606535061908923, "grad_norm": 1.7866078615188599, "learning_rate": 0.0001737626312660987, "loss": 0.6895014762878418, "step": 43850 }, { "epoch": 0.2607129482675607, "grad_norm": 1.6171131134033203, "learning_rate": 0.00017380225876758473, "loss": 0.6963481426239013, "step": 43860 }, { "epoch": 0.26077239034422905, "grad_norm": 2.142115592956543, "learning_rate": 0.00017384188626907074, "loss": 0.7057286262512207, "step": 43870 }, { "epoch": 0.26083183242089747, "grad_norm": 2.132951498031616, "learning_rate": 0.00017388151377055678, "loss": 0.7091974735260009, "step": 43880 }, { "epoch": 0.26089127449756583, "grad_norm": 2.14340877532959, "learning_rate": 0.0001739211412720428, "loss": 0.6633824825286865, "step": 43890 }, { "epoch": 0.26095071657423424, "grad_norm": 1.3125289678573608, "learning_rate": 0.00017396076877352885, "loss": 0.686750841140747, "step": 43900 }, { "epoch": 0.2610101586509026, "grad_norm": 1.5237841606140137, "learning_rate": 0.00017400039627501486, "loss": 0.7040223121643067, "step": 43910 }, { "epoch": 0.261069600727571, "grad_norm": 1.585389256477356, "learning_rate": 0.0001740400237765009, "loss": 0.6796354293823242, "step": 43920 }, { "epoch": 0.26112904280423943, "grad_norm": 1.7332289218902588, "learning_rate": 0.00017407965127798694, "loss": 0.6825404167175293, "step": 43930 }, { "epoch": 0.2611884848809078, "grad_norm": 1.6290827989578247, "learning_rate": 0.00017411927877947295, "loss": 0.7007014274597168, "step": 43940 }, { "epoch": 0.2612479269575762, "grad_norm": 1.3331478834152222, "learning_rate": 0.000174158906280959, "loss": 0.620260763168335, "step": 43950 }, { "epoch": 0.26130736903424456, "grad_norm": 1.832231879234314, "learning_rate": 0.000174198533782445, "loss": 0.7012538909912109, "step": 43960 }, { "epoch": 0.261366811110913, "grad_norm": 1.3734182119369507, "learning_rate": 0.00017423816128393107, "loss": 0.6135433197021485, "step": 43970 }, { "epoch": 0.26142625318758134, "grad_norm": 1.7394696474075317, "learning_rate": 0.0001742777887854171, "loss": 0.6625207901000977, "step": 43980 }, { "epoch": 0.26148569526424975, "grad_norm": 1.465998888015747, "learning_rate": 0.00017431741628690312, "loss": 0.6771646499633789, "step": 43990 }, { "epoch": 0.26154513734091817, "grad_norm": 1.2976990938186646, "learning_rate": 0.00017435704378838916, "loss": 0.6532225608825684, "step": 44000 }, { "epoch": 0.2616045794175865, "grad_norm": 1.5106786489486694, "learning_rate": 0.00017439667128987517, "loss": 0.6559336662292481, "step": 44010 }, { "epoch": 0.26166402149425494, "grad_norm": 1.7342329025268555, "learning_rate": 0.0001744362987913612, "loss": 0.6364203453063965, "step": 44020 }, { "epoch": 0.2617234635709233, "grad_norm": 1.7377253770828247, "learning_rate": 0.00017447592629284725, "loss": 0.7106954097747803, "step": 44030 }, { "epoch": 0.2617829056475917, "grad_norm": 1.48970627784729, "learning_rate": 0.00017451555379433329, "loss": 0.6620267391204834, "step": 44040 }, { "epoch": 0.26184234772426007, "grad_norm": 1.9401657581329346, "learning_rate": 0.00017455518129581932, "loss": 0.6725837230682373, "step": 44050 }, { "epoch": 0.2619017898009285, "grad_norm": 1.9076802730560303, "learning_rate": 0.00017459480879730534, "loss": 0.7254128456115723, "step": 44060 }, { "epoch": 0.2619612318775969, "grad_norm": 1.6919342279434204, "learning_rate": 0.00017463443629879137, "loss": 0.6990614891052246, "step": 44070 }, { "epoch": 0.26202067395426526, "grad_norm": 1.3199251890182495, "learning_rate": 0.0001746740638002774, "loss": 0.650147819519043, "step": 44080 }, { "epoch": 0.2620801160309337, "grad_norm": 1.8283690214157104, "learning_rate": 0.00017471369130176343, "loss": 0.6818939208984375, "step": 44090 }, { "epoch": 0.26213955810760203, "grad_norm": 1.7036877870559692, "learning_rate": 0.00017475331880324946, "loss": 0.6743514060974121, "step": 44100 }, { "epoch": 0.26219900018427045, "grad_norm": 2.427074432373047, "learning_rate": 0.0001747929463047355, "loss": 0.670587682723999, "step": 44110 }, { "epoch": 0.2622584422609388, "grad_norm": 1.5871549844741821, "learning_rate": 0.00017483257380622154, "loss": 0.6784718990325928, "step": 44120 }, { "epoch": 0.2623178843376072, "grad_norm": 1.43380606174469, "learning_rate": 0.00017487220130770755, "loss": 0.6786977767944335, "step": 44130 }, { "epoch": 0.26237732641427564, "grad_norm": 1.6713132858276367, "learning_rate": 0.0001749118288091936, "loss": 0.7309797763824463, "step": 44140 }, { "epoch": 0.262436768490944, "grad_norm": 1.794357419013977, "learning_rate": 0.00017495145631067963, "loss": 0.6843687057495117, "step": 44150 }, { "epoch": 0.2624962105676124, "grad_norm": 1.7057106494903564, "learning_rate": 0.00017499108381216564, "loss": 0.8029508590698242, "step": 44160 }, { "epoch": 0.26255565264428077, "grad_norm": 1.908294439315796, "learning_rate": 0.00017503071131365168, "loss": 0.6593233108520508, "step": 44170 }, { "epoch": 0.2626150947209492, "grad_norm": 1.5009074211120605, "learning_rate": 0.00017507033881513772, "loss": 0.6376275062561035, "step": 44180 }, { "epoch": 0.26267453679761754, "grad_norm": 1.8616998195648193, "learning_rate": 0.00017510996631662376, "loss": 0.6379258155822753, "step": 44190 }, { "epoch": 0.26273397887428596, "grad_norm": 1.6224335432052612, "learning_rate": 0.00017514959381810977, "loss": 0.6975480079650879, "step": 44200 }, { "epoch": 0.2627934209509543, "grad_norm": 1.6904305219650269, "learning_rate": 0.0001751892213195958, "loss": 0.7350803852081299, "step": 44210 }, { "epoch": 0.26285286302762273, "grad_norm": 1.6406868696212769, "learning_rate": 0.00017522884882108185, "loss": 0.6866169929504394, "step": 44220 }, { "epoch": 0.26291230510429114, "grad_norm": 1.7266572713851929, "learning_rate": 0.00017526847632256786, "loss": 0.6867237091064453, "step": 44230 }, { "epoch": 0.2629717471809595, "grad_norm": 1.882046103477478, "learning_rate": 0.0001753081038240539, "loss": 0.6740601539611817, "step": 44240 }, { "epoch": 0.2630311892576279, "grad_norm": 1.4645349979400635, "learning_rate": 0.00017534773132553994, "loss": 0.6612850189208984, "step": 44250 }, { "epoch": 0.2630906313342963, "grad_norm": 1.3417176008224487, "learning_rate": 0.00017538735882702597, "loss": 0.6405043601989746, "step": 44260 }, { "epoch": 0.2631500734109647, "grad_norm": 1.4910922050476074, "learning_rate": 0.000175426986328512, "loss": 0.6523818969726562, "step": 44270 }, { "epoch": 0.26320951548763305, "grad_norm": 1.7570977210998535, "learning_rate": 0.00017546661382999802, "loss": 0.6694059371948242, "step": 44280 }, { "epoch": 0.26326895756430146, "grad_norm": 1.7351969480514526, "learning_rate": 0.00017550624133148406, "loss": 0.6368839740753174, "step": 44290 }, { "epoch": 0.2633283996409699, "grad_norm": 1.6123601198196411, "learning_rate": 0.00017554586883297007, "loss": 0.6820608139038086, "step": 44300 }, { "epoch": 0.26338784171763824, "grad_norm": 1.7792209386825562, "learning_rate": 0.0001755854963344561, "loss": 0.6379776477813721, "step": 44310 }, { "epoch": 0.26344728379430665, "grad_norm": 1.3944685459136963, "learning_rate": 0.00017562512383594215, "loss": 0.6335087299346924, "step": 44320 }, { "epoch": 0.263506725870975, "grad_norm": 1.780159831047058, "learning_rate": 0.0001756647513374282, "loss": 0.6067484378814697, "step": 44330 }, { "epoch": 0.2635661679476434, "grad_norm": 1.6532323360443115, "learning_rate": 0.00017570437883891423, "loss": 0.6748688220977783, "step": 44340 }, { "epoch": 0.2636256100243118, "grad_norm": 1.5233838558197021, "learning_rate": 0.00017574400634040024, "loss": 0.668212604522705, "step": 44350 }, { "epoch": 0.2636850521009802, "grad_norm": 1.5105414390563965, "learning_rate": 0.00017578363384188628, "loss": 0.6857816696166992, "step": 44360 }, { "epoch": 0.2637444941776486, "grad_norm": 1.5267322063446045, "learning_rate": 0.0001758232613433723, "loss": 0.7105189323425293, "step": 44370 }, { "epoch": 0.263803936254317, "grad_norm": 1.2866172790527344, "learning_rate": 0.00017586288884485833, "loss": 0.6402660369873047, "step": 44380 }, { "epoch": 0.2638633783309854, "grad_norm": 1.6401386260986328, "learning_rate": 0.00017590251634634437, "loss": 0.6410065650939941, "step": 44390 }, { "epoch": 0.26392282040765375, "grad_norm": 1.2651158571243286, "learning_rate": 0.0001759421438478304, "loss": 0.6043635845184326, "step": 44400 }, { "epoch": 0.26398226248432216, "grad_norm": 1.6103922128677368, "learning_rate": 0.00017598177134931645, "loss": 0.6767284393310546, "step": 44410 }, { "epoch": 0.2640417045609905, "grad_norm": 1.416869878768921, "learning_rate": 0.00017602139885080246, "loss": 0.6758392333984375, "step": 44420 }, { "epoch": 0.26410114663765893, "grad_norm": 1.5750155448913574, "learning_rate": 0.0001760610263522885, "loss": 0.6993577480316162, "step": 44430 }, { "epoch": 0.26416058871432735, "grad_norm": 1.3940544128417969, "learning_rate": 0.00017610065385377453, "loss": 0.6673359870910645, "step": 44440 }, { "epoch": 0.2642200307909957, "grad_norm": 1.2334874868392944, "learning_rate": 0.00017614028135526055, "loss": 0.6678733825683594, "step": 44450 }, { "epoch": 0.2642794728676641, "grad_norm": 1.8620086908340454, "learning_rate": 0.0001761799088567466, "loss": 0.6547172546386719, "step": 44460 }, { "epoch": 0.2643389149443325, "grad_norm": 1.4573864936828613, "learning_rate": 0.00017621953635823262, "loss": 0.7092129707336425, "step": 44470 }, { "epoch": 0.2643983570210009, "grad_norm": 1.642229437828064, "learning_rate": 0.00017625916385971866, "loss": 0.7653286933898926, "step": 44480 }, { "epoch": 0.26445779909766925, "grad_norm": 1.495424509048462, "learning_rate": 0.00017629879136120467, "loss": 0.6651876449584961, "step": 44490 }, { "epoch": 0.26451724117433767, "grad_norm": 2.255751371383667, "learning_rate": 0.0001763384188626907, "loss": 0.7077821254730224, "step": 44500 }, { "epoch": 0.2645766832510061, "grad_norm": 1.8634083271026611, "learning_rate": 0.00017637804636417675, "loss": 0.6995741844177246, "step": 44510 }, { "epoch": 0.26463612532767444, "grad_norm": 2.030658483505249, "learning_rate": 0.00017641767386566276, "loss": 0.7285444736480713, "step": 44520 }, { "epoch": 0.26469556740434286, "grad_norm": 1.7073310613632202, "learning_rate": 0.00017645730136714883, "loss": 0.6292506694793701, "step": 44530 }, { "epoch": 0.2647550094810112, "grad_norm": 1.9457197189331055, "learning_rate": 0.00017649692886863484, "loss": 0.7042448043823242, "step": 44540 }, { "epoch": 0.26481445155767963, "grad_norm": 1.5924904346466064, "learning_rate": 0.00017653655637012088, "loss": 0.692723274230957, "step": 44550 }, { "epoch": 0.264873893634348, "grad_norm": 1.6596349477767944, "learning_rate": 0.00017657618387160692, "loss": 0.6382593154907227, "step": 44560 }, { "epoch": 0.2649333357110164, "grad_norm": 1.4442499876022339, "learning_rate": 0.00017661581137309293, "loss": 0.6469290733337403, "step": 44570 }, { "epoch": 0.26499277778768476, "grad_norm": 1.795135259628296, "learning_rate": 0.00017665543887457897, "loss": 0.7015356540679931, "step": 44580 }, { "epoch": 0.2650522198643532, "grad_norm": 1.5607962608337402, "learning_rate": 0.00017669506637606498, "loss": 0.6368267059326171, "step": 44590 }, { "epoch": 0.2651116619410216, "grad_norm": 1.5823032855987549, "learning_rate": 0.00017673469387755104, "loss": 0.6436245441436768, "step": 44600 }, { "epoch": 0.26517110401768995, "grad_norm": 1.8640351295471191, "learning_rate": 0.00017677432137903706, "loss": 0.6841367721557617, "step": 44610 }, { "epoch": 0.26523054609435837, "grad_norm": 1.6815201044082642, "learning_rate": 0.0001768139488805231, "loss": 0.6323231220245361, "step": 44620 }, { "epoch": 0.2652899881710267, "grad_norm": 1.5620484352111816, "learning_rate": 0.00017685357638200913, "loss": 0.6839352607727051, "step": 44630 }, { "epoch": 0.26534943024769514, "grad_norm": 1.8199933767318726, "learning_rate": 0.00017689320388349514, "loss": 0.7504298210144043, "step": 44640 }, { "epoch": 0.2654088723243635, "grad_norm": 1.5308576822280884, "learning_rate": 0.00017693283138498118, "loss": 0.7083394527435303, "step": 44650 }, { "epoch": 0.2654683144010319, "grad_norm": 1.4885791540145874, "learning_rate": 0.0001769724588864672, "loss": 0.6613232612609863, "step": 44660 }, { "epoch": 0.2655277564777003, "grad_norm": 1.573891282081604, "learning_rate": 0.00017701208638795326, "loss": 0.6531096935272217, "step": 44670 }, { "epoch": 0.2655871985543687, "grad_norm": 1.724194049835205, "learning_rate": 0.0001770517138894393, "loss": 0.7146762847900391, "step": 44680 }, { "epoch": 0.2656466406310371, "grad_norm": 2.0048797130584717, "learning_rate": 0.0001770913413909253, "loss": 0.713097333908081, "step": 44690 }, { "epoch": 0.26570608270770546, "grad_norm": 1.3686587810516357, "learning_rate": 0.00017713096889241135, "loss": 0.6406694412231445, "step": 44700 }, { "epoch": 0.2657655247843739, "grad_norm": 1.9537087678909302, "learning_rate": 0.00017717059639389736, "loss": 0.7121966361999512, "step": 44710 }, { "epoch": 0.26582496686104223, "grad_norm": 2.0156149864196777, "learning_rate": 0.0001772102238953834, "loss": 0.6397005558013916, "step": 44720 }, { "epoch": 0.26588440893771065, "grad_norm": 1.5382306575775146, "learning_rate": 0.00017724985139686944, "loss": 0.672181224822998, "step": 44730 }, { "epoch": 0.26594385101437906, "grad_norm": 1.5656089782714844, "learning_rate": 0.00017728947889835548, "loss": 0.6616038322448731, "step": 44740 }, { "epoch": 0.2660032930910474, "grad_norm": 1.721047043800354, "learning_rate": 0.00017732910639984152, "loss": 0.6334449768066406, "step": 44750 }, { "epoch": 0.26606273516771584, "grad_norm": 1.286484956741333, "learning_rate": 0.00017736873390132753, "loss": 0.673501443862915, "step": 44760 }, { "epoch": 0.2661221772443842, "grad_norm": 1.3296661376953125, "learning_rate": 0.00017740836140281357, "loss": 0.6873237609863281, "step": 44770 }, { "epoch": 0.2661816193210526, "grad_norm": 1.8622080087661743, "learning_rate": 0.00017744798890429958, "loss": 0.6409115791320801, "step": 44780 }, { "epoch": 0.26624106139772097, "grad_norm": 1.484366774559021, "learning_rate": 0.00017748761640578562, "loss": 0.6834981918334961, "step": 44790 }, { "epoch": 0.2663005034743894, "grad_norm": 1.380495548248291, "learning_rate": 0.00017752724390727165, "loss": 0.6712949752807618, "step": 44800 }, { "epoch": 0.2663599455510578, "grad_norm": 1.7589266300201416, "learning_rate": 0.0001775668714087577, "loss": 0.6391345024108886, "step": 44810 }, { "epoch": 0.26641938762772616, "grad_norm": 1.4657883644104004, "learning_rate": 0.00017760649891024373, "loss": 0.709836769104004, "step": 44820 }, { "epoch": 0.26647882970439457, "grad_norm": 1.47996985912323, "learning_rate": 0.00017764612641172974, "loss": 0.6675857543945313, "step": 44830 }, { "epoch": 0.26653827178106293, "grad_norm": 1.6556248664855957, "learning_rate": 0.00017768575391321578, "loss": 0.6410647392272949, "step": 44840 }, { "epoch": 0.26659771385773134, "grad_norm": 1.8873772621154785, "learning_rate": 0.00017772538141470182, "loss": 0.6818993568420411, "step": 44850 }, { "epoch": 0.2666571559343997, "grad_norm": 1.4436408281326294, "learning_rate": 0.00017776500891618783, "loss": 0.6152698040008545, "step": 44860 }, { "epoch": 0.2667165980110681, "grad_norm": 1.806889533996582, "learning_rate": 0.00017780463641767387, "loss": 0.690050458908081, "step": 44870 }, { "epoch": 0.26677604008773653, "grad_norm": 1.419196367263794, "learning_rate": 0.0001778442639191599, "loss": 0.6848961353302002, "step": 44880 }, { "epoch": 0.2668354821644049, "grad_norm": 1.649772047996521, "learning_rate": 0.00017788389142064595, "loss": 0.7354805946350098, "step": 44890 }, { "epoch": 0.2668949242410733, "grad_norm": 1.5349162817001343, "learning_rate": 0.00017792351892213196, "loss": 0.7049520492553711, "step": 44900 }, { "epoch": 0.26695436631774166, "grad_norm": 1.639111042022705, "learning_rate": 0.000177963146423618, "loss": 0.679495096206665, "step": 44910 }, { "epoch": 0.2670138083944101, "grad_norm": 1.5785083770751953, "learning_rate": 0.00017800277392510404, "loss": 0.6098024368286132, "step": 44920 }, { "epoch": 0.26707325047107844, "grad_norm": 1.9256486892700195, "learning_rate": 0.00017804240142659005, "loss": 0.7529251575469971, "step": 44930 }, { "epoch": 0.26713269254774685, "grad_norm": 1.729777216911316, "learning_rate": 0.0001780820289280761, "loss": 0.6535490036010743, "step": 44940 }, { "epoch": 0.2671921346244152, "grad_norm": 1.2860655784606934, "learning_rate": 0.00017812165642956213, "loss": 0.6617034912109375, "step": 44950 }, { "epoch": 0.2672515767010836, "grad_norm": 1.903426170349121, "learning_rate": 0.00017816128393104816, "loss": 0.7148236274719239, "step": 44960 }, { "epoch": 0.26731101877775204, "grad_norm": 1.488219141960144, "learning_rate": 0.0001782009114325342, "loss": 0.640458345413208, "step": 44970 }, { "epoch": 0.2673704608544204, "grad_norm": 1.920985460281372, "learning_rate": 0.00017824053893402021, "loss": 0.6454455375671386, "step": 44980 }, { "epoch": 0.2674299029310888, "grad_norm": 1.7870607376098633, "learning_rate": 0.00017828016643550625, "loss": 0.7415300369262695, "step": 44990 }, { "epoch": 0.2674893450077572, "grad_norm": 1.6360658407211304, "learning_rate": 0.00017831979393699227, "loss": 0.6517132759094239, "step": 45000 }, { "epoch": 0.2675487870844256, "grad_norm": 2.3133180141448975, "learning_rate": 0.0001783594214384783, "loss": 0.6394517898559571, "step": 45010 }, { "epoch": 0.26760822916109395, "grad_norm": 1.6065893173217773, "learning_rate": 0.00017839904893996434, "loss": 0.7302979469299317, "step": 45020 }, { "epoch": 0.26766767123776236, "grad_norm": 1.8751627206802368, "learning_rate": 0.00017843867644145038, "loss": 0.6965548992156982, "step": 45030 }, { "epoch": 0.2677271133144308, "grad_norm": 1.6958978176116943, "learning_rate": 0.00017847830394293642, "loss": 0.6863544464111329, "step": 45040 }, { "epoch": 0.26778655539109913, "grad_norm": 1.598374366760254, "learning_rate": 0.00017851793144442243, "loss": 0.6689961433410645, "step": 45050 }, { "epoch": 0.26784599746776755, "grad_norm": 1.429880976676941, "learning_rate": 0.00017855755894590847, "loss": 0.6816423892974853, "step": 45060 }, { "epoch": 0.2679054395444359, "grad_norm": 1.6961679458618164, "learning_rate": 0.00017859718644739448, "loss": 0.6106842041015625, "step": 45070 }, { "epoch": 0.2679648816211043, "grad_norm": 1.6613402366638184, "learning_rate": 0.00017863681394888052, "loss": 0.6546212196350097, "step": 45080 }, { "epoch": 0.2680243236977727, "grad_norm": 1.8187130689620972, "learning_rate": 0.00017867644145036656, "loss": 0.7154145240783691, "step": 45090 }, { "epoch": 0.2680837657744411, "grad_norm": 1.4041674137115479, "learning_rate": 0.0001787160689518526, "loss": 0.6901562690734864, "step": 45100 }, { "epoch": 0.2681432078511095, "grad_norm": 1.6033645868301392, "learning_rate": 0.00017875569645333864, "loss": 0.7104109764099121, "step": 45110 }, { "epoch": 0.26820264992777787, "grad_norm": 1.9664961099624634, "learning_rate": 0.00017879532395482465, "loss": 0.7292256832122803, "step": 45120 }, { "epoch": 0.2682620920044463, "grad_norm": 1.5466052293777466, "learning_rate": 0.00017883495145631069, "loss": 0.7182971954345703, "step": 45130 }, { "epoch": 0.26832153408111464, "grad_norm": 1.8953982591629028, "learning_rate": 0.00017887457895779672, "loss": 0.6980198860168457, "step": 45140 }, { "epoch": 0.26838097615778306, "grad_norm": 1.7612982988357544, "learning_rate": 0.00017891420645928274, "loss": 0.6821296691894532, "step": 45150 }, { "epoch": 0.2684404182344514, "grad_norm": 1.8474689722061157, "learning_rate": 0.0001789538339607688, "loss": 0.7139549732208252, "step": 45160 }, { "epoch": 0.26849986031111983, "grad_norm": 1.8254833221435547, "learning_rate": 0.00017899346146225481, "loss": 0.7143022537231445, "step": 45170 }, { "epoch": 0.26855930238778825, "grad_norm": 1.6421873569488525, "learning_rate": 0.00017903308896374085, "loss": 0.6832636833190918, "step": 45180 }, { "epoch": 0.2686187444644566, "grad_norm": 1.6427913904190063, "learning_rate": 0.00017907271646522686, "loss": 0.6887903213500977, "step": 45190 }, { "epoch": 0.268678186541125, "grad_norm": 1.639077067375183, "learning_rate": 0.0001791123439667129, "loss": 0.6526169300079345, "step": 45200 }, { "epoch": 0.2687376286177934, "grad_norm": 1.7302113771438599, "learning_rate": 0.00017915197146819894, "loss": 0.6871823310852051, "step": 45210 }, { "epoch": 0.2687970706944618, "grad_norm": 1.8170782327651978, "learning_rate": 0.00017919159896968495, "loss": 0.6706300735473633, "step": 45220 }, { "epoch": 0.26885651277113015, "grad_norm": 1.5295532941818237, "learning_rate": 0.00017923122647117102, "loss": 0.7015283584594727, "step": 45230 }, { "epoch": 0.26891595484779857, "grad_norm": 1.746461033821106, "learning_rate": 0.00017927085397265703, "loss": 0.7051330089569092, "step": 45240 }, { "epoch": 0.268975396924467, "grad_norm": 1.6809462308883667, "learning_rate": 0.00017931048147414307, "loss": 0.6034305572509766, "step": 45250 }, { "epoch": 0.26903483900113534, "grad_norm": 2.0850424766540527, "learning_rate": 0.0001793501089756291, "loss": 0.6845114231109619, "step": 45260 }, { "epoch": 0.26909428107780375, "grad_norm": 1.4926989078521729, "learning_rate": 0.00017938973647711512, "loss": 0.6684677124023437, "step": 45270 }, { "epoch": 0.2691537231544721, "grad_norm": 1.6234488487243652, "learning_rate": 0.00017942936397860116, "loss": 0.7178246021270752, "step": 45280 }, { "epoch": 0.2692131652311405, "grad_norm": 1.952557921409607, "learning_rate": 0.00017946899148008717, "loss": 0.6556378364562988, "step": 45290 }, { "epoch": 0.2692726073078089, "grad_norm": 2.2386391162872314, "learning_rate": 0.00017950861898157324, "loss": 0.6893474578857421, "step": 45300 }, { "epoch": 0.2693320493844773, "grad_norm": 1.6587042808532715, "learning_rate": 0.00017954824648305925, "loss": 0.6478386878967285, "step": 45310 }, { "epoch": 0.26939149146114566, "grad_norm": 1.5218926668167114, "learning_rate": 0.00017958787398454529, "loss": 0.6649754524230957, "step": 45320 }, { "epoch": 0.2694509335378141, "grad_norm": 2.2528975009918213, "learning_rate": 0.00017962750148603132, "loss": 0.7127462387084961, "step": 45330 }, { "epoch": 0.2695103756144825, "grad_norm": 1.896543025970459, "learning_rate": 0.00017966712898751734, "loss": 0.7034032821655274, "step": 45340 }, { "epoch": 0.26956981769115085, "grad_norm": 1.586990237236023, "learning_rate": 0.00017970675648900337, "loss": 0.6637934684753418, "step": 45350 }, { "epoch": 0.26962925976781926, "grad_norm": 1.9333314895629883, "learning_rate": 0.00017974638399048939, "loss": 0.7226504325866699, "step": 45360 }, { "epoch": 0.2696887018444876, "grad_norm": 1.667158603668213, "learning_rate": 0.00017978601149197545, "loss": 0.6399940490722656, "step": 45370 }, { "epoch": 0.26974814392115604, "grad_norm": 2.0931949615478516, "learning_rate": 0.00017982563899346146, "loss": 0.725970983505249, "step": 45380 }, { "epoch": 0.2698075859978244, "grad_norm": 1.9265573024749756, "learning_rate": 0.0001798652664949475, "loss": 0.6682363510131836, "step": 45390 }, { "epoch": 0.2698670280744928, "grad_norm": 1.3915327787399292, "learning_rate": 0.00017990489399643354, "loss": 0.7710960865020752, "step": 45400 }, { "epoch": 0.2699264701511612, "grad_norm": 1.6040878295898438, "learning_rate": 0.00017994452149791955, "loss": 0.7196861267089844, "step": 45410 }, { "epoch": 0.2699859122278296, "grad_norm": 1.430437684059143, "learning_rate": 0.0001799841489994056, "loss": 0.6455793857574463, "step": 45420 }, { "epoch": 0.270045354304498, "grad_norm": 2.0642144680023193, "learning_rate": 0.00018002377650089163, "loss": 0.6413435935974121, "step": 45430 }, { "epoch": 0.27010479638116636, "grad_norm": 1.5018091201782227, "learning_rate": 0.00018006340400237767, "loss": 0.660731315612793, "step": 45440 }, { "epoch": 0.27016423845783477, "grad_norm": 1.615808129310608, "learning_rate": 0.0001801030315038637, "loss": 0.6889615058898926, "step": 45450 }, { "epoch": 0.27022368053450313, "grad_norm": 1.8380683660507202, "learning_rate": 0.00018014265900534972, "loss": 0.6987479209899903, "step": 45460 }, { "epoch": 0.27028312261117154, "grad_norm": 1.839967966079712, "learning_rate": 0.00018018228650683576, "loss": 0.7236094951629639, "step": 45470 }, { "epoch": 0.27034256468783996, "grad_norm": 1.9007970094680786, "learning_rate": 0.00018022191400832177, "loss": 0.6964512825012207, "step": 45480 }, { "epoch": 0.2704020067645083, "grad_norm": 2.0350828170776367, "learning_rate": 0.0001802615415098078, "loss": 0.6343555450439453, "step": 45490 }, { "epoch": 0.27046144884117673, "grad_norm": 1.395678162574768, "learning_rate": 0.00018030116901129385, "loss": 0.6853574752807617, "step": 45500 }, { "epoch": 0.2705208909178451, "grad_norm": 1.4378119707107544, "learning_rate": 0.00018034079651277988, "loss": 0.6680552959442139, "step": 45510 }, { "epoch": 0.2705803329945135, "grad_norm": 1.6208966970443726, "learning_rate": 0.00018038042401426592, "loss": 0.7034520149230957, "step": 45520 }, { "epoch": 0.27063977507118187, "grad_norm": 1.639066457748413, "learning_rate": 0.00018042005151575193, "loss": 0.7114397048950195, "step": 45530 }, { "epoch": 0.2706992171478503, "grad_norm": 1.8994722366333008, "learning_rate": 0.00018045967901723797, "loss": 0.7046480178833008, "step": 45540 }, { "epoch": 0.2707586592245187, "grad_norm": 1.5541713237762451, "learning_rate": 0.000180499306518724, "loss": 0.7288019180297851, "step": 45550 }, { "epoch": 0.27081810130118705, "grad_norm": 1.7961440086364746, "learning_rate": 0.00018053893402021002, "loss": 0.6739158630371094, "step": 45560 }, { "epoch": 0.27087754337785547, "grad_norm": 1.5343623161315918, "learning_rate": 0.00018057856152169606, "loss": 0.7078831672668457, "step": 45570 }, { "epoch": 0.2709369854545238, "grad_norm": 1.6218496561050415, "learning_rate": 0.0001806181890231821, "loss": 0.6531959533691406, "step": 45580 }, { "epoch": 0.27099642753119224, "grad_norm": 1.8480310440063477, "learning_rate": 0.00018065781652466814, "loss": 0.6881828784942627, "step": 45590 }, { "epoch": 0.2710558696078606, "grad_norm": 2.033541679382324, "learning_rate": 0.00018069744402615415, "loss": 0.7069508552551269, "step": 45600 }, { "epoch": 0.271115311684529, "grad_norm": 1.401229977607727, "learning_rate": 0.0001807370715276402, "loss": 0.723999309539795, "step": 45610 }, { "epoch": 0.2711747537611974, "grad_norm": 1.6746399402618408, "learning_rate": 0.00018077669902912623, "loss": 0.7080901145935059, "step": 45620 }, { "epoch": 0.2712341958378658, "grad_norm": 2.099458932876587, "learning_rate": 0.00018081632653061224, "loss": 0.69760160446167, "step": 45630 }, { "epoch": 0.2712936379145342, "grad_norm": 1.3998693227767944, "learning_rate": 0.0001808559540320983, "loss": 0.6995781421661377, "step": 45640 }, { "epoch": 0.27135307999120256, "grad_norm": 1.7667242288589478, "learning_rate": 0.00018089558153358432, "loss": 0.7718389511108399, "step": 45650 }, { "epoch": 0.271412522067871, "grad_norm": 1.531394600868225, "learning_rate": 0.00018093520903507036, "loss": 0.6639490604400635, "step": 45660 }, { "epoch": 0.27147196414453933, "grad_norm": 1.5297598838806152, "learning_rate": 0.00018097483653655637, "loss": 0.7245744705200196, "step": 45670 }, { "epoch": 0.27153140622120775, "grad_norm": 1.7944700717926025, "learning_rate": 0.0001810144640380424, "loss": 0.6846575736999512, "step": 45680 }, { "epoch": 0.2715908482978761, "grad_norm": 1.9740206003189087, "learning_rate": 0.00018105409153952844, "loss": 0.6665095329284668, "step": 45690 }, { "epoch": 0.2716502903745445, "grad_norm": 1.951966404914856, "learning_rate": 0.00018109371904101446, "loss": 0.6642853736877441, "step": 45700 }, { "epoch": 0.27170973245121294, "grad_norm": 1.7441502809524536, "learning_rate": 0.00018113334654250052, "loss": 0.6812773704528808, "step": 45710 }, { "epoch": 0.2717691745278813, "grad_norm": 1.599260926246643, "learning_rate": 0.00018117297404398653, "loss": 0.6795085430145263, "step": 45720 }, { "epoch": 0.2718286166045497, "grad_norm": 1.6989495754241943, "learning_rate": 0.00018121260154547257, "loss": 0.7414886474609375, "step": 45730 }, { "epoch": 0.27188805868121807, "grad_norm": 1.6277450323104858, "learning_rate": 0.0001812522290469586, "loss": 0.6849237442016601, "step": 45740 }, { "epoch": 0.2719475007578865, "grad_norm": 1.9149943590164185, "learning_rate": 0.00018129185654844462, "loss": 0.722679328918457, "step": 45750 }, { "epoch": 0.27200694283455484, "grad_norm": 1.4504482746124268, "learning_rate": 0.00018133148404993066, "loss": 0.7003472328186036, "step": 45760 }, { "epoch": 0.27206638491122326, "grad_norm": 1.6640738248825073, "learning_rate": 0.00018137111155141667, "loss": 0.6908511161804199, "step": 45770 }, { "epoch": 0.2721258269878917, "grad_norm": 2.9797911643981934, "learning_rate": 0.00018141073905290274, "loss": 0.6743400573730469, "step": 45780 }, { "epoch": 0.27218526906456003, "grad_norm": 1.6828199625015259, "learning_rate": 0.00018145036655438875, "loss": 0.7228084087371827, "step": 45790 }, { "epoch": 0.27224471114122845, "grad_norm": 1.9527419805526733, "learning_rate": 0.0001814899940558748, "loss": 0.6862998008728027, "step": 45800 }, { "epoch": 0.2723041532178968, "grad_norm": 2.0017497539520264, "learning_rate": 0.00018152962155736083, "loss": 0.6785545349121094, "step": 45810 }, { "epoch": 0.2723635952945652, "grad_norm": 1.6765859127044678, "learning_rate": 0.00018156924905884684, "loss": 0.6886938095092774, "step": 45820 }, { "epoch": 0.2724230373712336, "grad_norm": 1.4140371084213257, "learning_rate": 0.00018160887656033288, "loss": 0.6498805046081543, "step": 45830 }, { "epoch": 0.272482479447902, "grad_norm": 1.7854735851287842, "learning_rate": 0.00018164850406181892, "loss": 0.6758304119110108, "step": 45840 }, { "epoch": 0.2725419215245704, "grad_norm": 2.018597364425659, "learning_rate": 0.00018168813156330495, "loss": 0.7091087341308594, "step": 45850 }, { "epoch": 0.27260136360123877, "grad_norm": 1.7028334140777588, "learning_rate": 0.000181727759064791, "loss": 0.6784739017486572, "step": 45860 }, { "epoch": 0.2726608056779072, "grad_norm": 1.8125466108322144, "learning_rate": 0.000181767386566277, "loss": 0.7090652465820313, "step": 45870 }, { "epoch": 0.27272024775457554, "grad_norm": 1.6382955312728882, "learning_rate": 0.00018180701406776304, "loss": 0.6452745914459228, "step": 45880 }, { "epoch": 0.27277968983124395, "grad_norm": 2.1350467205047607, "learning_rate": 0.00018184664156924905, "loss": 0.675609827041626, "step": 45890 }, { "epoch": 0.2728391319079123, "grad_norm": 1.6574410200119019, "learning_rate": 0.0001818862690707351, "loss": 0.6751903533935547, "step": 45900 }, { "epoch": 0.27289857398458073, "grad_norm": 1.813553810119629, "learning_rate": 0.00018192589657222113, "loss": 0.6440119743347168, "step": 45910 }, { "epoch": 0.27295801606124914, "grad_norm": 1.481092929840088, "learning_rate": 0.00018196552407370717, "loss": 0.6796642303466797, "step": 45920 }, { "epoch": 0.2730174581379175, "grad_norm": 1.5889508724212646, "learning_rate": 0.0001820051515751932, "loss": 0.6724479675292969, "step": 45930 }, { "epoch": 0.2730769002145859, "grad_norm": 1.98104989528656, "learning_rate": 0.00018204477907667922, "loss": 0.7413867473602295, "step": 45940 }, { "epoch": 0.2731363422912543, "grad_norm": 1.4128189086914062, "learning_rate": 0.00018208440657816526, "loss": 0.6646874427795411, "step": 45950 }, { "epoch": 0.2731957843679227, "grad_norm": 1.1891025304794312, "learning_rate": 0.00018212403407965127, "loss": 0.674417781829834, "step": 45960 }, { "epoch": 0.27325522644459105, "grad_norm": 1.356789469718933, "learning_rate": 0.0001821636615811373, "loss": 0.6132829666137696, "step": 45970 }, { "epoch": 0.27331466852125946, "grad_norm": 1.7723205089569092, "learning_rate": 0.00018220328908262335, "loss": 0.6868800163269043, "step": 45980 }, { "epoch": 0.2733741105979278, "grad_norm": 1.698989748954773, "learning_rate": 0.0001822429165841094, "loss": 0.6361957550048828, "step": 45990 }, { "epoch": 0.27343355267459624, "grad_norm": 1.5124467611312866, "learning_rate": 0.00018228254408559543, "loss": 0.7483770847320557, "step": 46000 }, { "epoch": 0.27349299475126465, "grad_norm": 1.6817011833190918, "learning_rate": 0.00018232217158708144, "loss": 0.6542195796966552, "step": 46010 }, { "epoch": 0.273552436827933, "grad_norm": 1.777065634727478, "learning_rate": 0.00018236179908856748, "loss": 0.7485612869262696, "step": 46020 }, { "epoch": 0.2736118789046014, "grad_norm": 1.7319293022155762, "learning_rate": 0.00018240142659005351, "loss": 0.6504128456115723, "step": 46030 }, { "epoch": 0.2736713209812698, "grad_norm": 1.5422418117523193, "learning_rate": 0.00018244105409153953, "loss": 0.6542033195495606, "step": 46040 }, { "epoch": 0.2737307630579382, "grad_norm": 1.7481647729873657, "learning_rate": 0.00018248068159302556, "loss": 0.6052531242370606, "step": 46050 }, { "epoch": 0.27379020513460656, "grad_norm": 1.4832435846328735, "learning_rate": 0.0001825203090945116, "loss": 0.7267690181732178, "step": 46060 }, { "epoch": 0.27384964721127497, "grad_norm": 1.6237590312957764, "learning_rate": 0.00018255993659599764, "loss": 0.6846916198730468, "step": 46070 }, { "epoch": 0.2739090892879434, "grad_norm": 1.6850924491882324, "learning_rate": 0.00018259956409748365, "loss": 0.6431808471679688, "step": 46080 }, { "epoch": 0.27396853136461174, "grad_norm": 1.6358975172042847, "learning_rate": 0.0001826391915989697, "loss": 0.6766202926635743, "step": 46090 }, { "epoch": 0.27402797344128016, "grad_norm": 1.5829806327819824, "learning_rate": 0.00018267881910045573, "loss": 0.6593898296356201, "step": 46100 }, { "epoch": 0.2740874155179485, "grad_norm": 1.4878582954406738, "learning_rate": 0.00018271844660194174, "loss": 0.7037747383117676, "step": 46110 }, { "epoch": 0.27414685759461693, "grad_norm": 1.831925392150879, "learning_rate": 0.00018275807410342778, "loss": 0.738526439666748, "step": 46120 }, { "epoch": 0.2742062996712853, "grad_norm": 2.12949538230896, "learning_rate": 0.00018279770160491382, "loss": 0.7187346458435059, "step": 46130 }, { "epoch": 0.2742657417479537, "grad_norm": 1.4905385971069336, "learning_rate": 0.00018283732910639986, "loss": 0.6758945465087891, "step": 46140 }, { "epoch": 0.2743251838246221, "grad_norm": 2.3838791847229004, "learning_rate": 0.0001828769566078859, "loss": 0.6794441699981689, "step": 46150 }, { "epoch": 0.2743846259012905, "grad_norm": 1.7711316347122192, "learning_rate": 0.0001829165841093719, "loss": 0.7328142166137696, "step": 46160 }, { "epoch": 0.2744440679779589, "grad_norm": 1.9057074785232544, "learning_rate": 0.00018295621161085795, "loss": 0.678456974029541, "step": 46170 }, { "epoch": 0.27450351005462725, "grad_norm": 1.3385881185531616, "learning_rate": 0.00018299583911234396, "loss": 0.6507643222808838, "step": 46180 }, { "epoch": 0.27456295213129567, "grad_norm": 1.7785606384277344, "learning_rate": 0.00018303546661383, "loss": 0.6584291458129883, "step": 46190 }, { "epoch": 0.274622394207964, "grad_norm": 1.698536992073059, "learning_rate": 0.00018307509411531604, "loss": 0.679865837097168, "step": 46200 }, { "epoch": 0.27468183628463244, "grad_norm": 1.3838683366775513, "learning_rate": 0.00018311472161680207, "loss": 0.6236191749572754, "step": 46210 }, { "epoch": 0.27474127836130086, "grad_norm": 1.3073111772537231, "learning_rate": 0.00018315434911828811, "loss": 0.716590690612793, "step": 46220 }, { "epoch": 0.2748007204379692, "grad_norm": 1.560079574584961, "learning_rate": 0.00018319397661977413, "loss": 0.6505993366241455, "step": 46230 }, { "epoch": 0.27486016251463763, "grad_norm": 1.7104910612106323, "learning_rate": 0.00018323360412126016, "loss": 0.644225788116455, "step": 46240 }, { "epoch": 0.274919604591306, "grad_norm": 1.6152584552764893, "learning_rate": 0.00018327323162274618, "loss": 0.6858384132385253, "step": 46250 }, { "epoch": 0.2749790466679744, "grad_norm": 1.7593460083007812, "learning_rate": 0.00018331285912423221, "loss": 0.6706832885742188, "step": 46260 }, { "epoch": 0.27503848874464276, "grad_norm": 1.6818779706954956, "learning_rate": 0.00018335248662571828, "loss": 0.6961601257324219, "step": 46270 }, { "epoch": 0.2750979308213112, "grad_norm": 1.4745395183563232, "learning_rate": 0.0001833921141272043, "loss": 0.7527563571929932, "step": 46280 }, { "epoch": 0.2751573728979796, "grad_norm": 1.5553181171417236, "learning_rate": 0.00018343174162869033, "loss": 0.6521703720092773, "step": 46290 }, { "epoch": 0.27521681497464795, "grad_norm": 1.9638956785202026, "learning_rate": 0.00018347136913017634, "loss": 0.7541406631469727, "step": 46300 }, { "epoch": 0.27527625705131636, "grad_norm": 2.0394744873046875, "learning_rate": 0.00018351099663166238, "loss": 0.7393042564392089, "step": 46310 }, { "epoch": 0.2753356991279847, "grad_norm": 1.9740086793899536, "learning_rate": 0.00018355062413314842, "loss": 0.6632367134094238, "step": 46320 }, { "epoch": 0.27539514120465314, "grad_norm": 3.5532500743865967, "learning_rate": 0.00018359025163463443, "loss": 0.7117892742156983, "step": 46330 }, { "epoch": 0.2754545832813215, "grad_norm": 1.4395110607147217, "learning_rate": 0.0001836298791361205, "loss": 0.6380420684814453, "step": 46340 }, { "epoch": 0.2755140253579899, "grad_norm": 1.7662863731384277, "learning_rate": 0.0001836695066376065, "loss": 0.6975914001464844, "step": 46350 }, { "epoch": 0.27557346743465827, "grad_norm": 1.548424243927002, "learning_rate": 0.00018370913413909255, "loss": 0.6297954082489013, "step": 46360 }, { "epoch": 0.2756329095113267, "grad_norm": 1.667819619178772, "learning_rate": 0.00018374876164057856, "loss": 0.6316068649291993, "step": 46370 }, { "epoch": 0.2756923515879951, "grad_norm": 1.65142822265625, "learning_rate": 0.0001837883891420646, "loss": 0.6678711891174316, "step": 46380 }, { "epoch": 0.27575179366466346, "grad_norm": 1.680033564567566, "learning_rate": 0.00018382801664355064, "loss": 0.684437370300293, "step": 46390 }, { "epoch": 0.2758112357413319, "grad_norm": 1.806997537612915, "learning_rate": 0.00018386764414503665, "loss": 0.664309310913086, "step": 46400 }, { "epoch": 0.27587067781800023, "grad_norm": 1.6458446979522705, "learning_rate": 0.0001839072716465227, "loss": 0.6734579563140869, "step": 46410 }, { "epoch": 0.27593011989466865, "grad_norm": 2.004190683364868, "learning_rate": 0.00018394689914800872, "loss": 0.7096341133117676, "step": 46420 }, { "epoch": 0.275989561971337, "grad_norm": 1.833250880241394, "learning_rate": 0.00018398652664949476, "loss": 0.6647989749908447, "step": 46430 }, { "epoch": 0.2760490040480054, "grad_norm": 1.826094150543213, "learning_rate": 0.0001840261541509808, "loss": 0.6399285316467285, "step": 46440 }, { "epoch": 0.27610844612467383, "grad_norm": 1.5330924987792969, "learning_rate": 0.0001840657816524668, "loss": 0.7217536926269531, "step": 46450 }, { "epoch": 0.2761678882013422, "grad_norm": 1.5506024360656738, "learning_rate": 0.00018410540915395285, "loss": 0.695633840560913, "step": 46460 }, { "epoch": 0.2762273302780106, "grad_norm": 1.828292727470398, "learning_rate": 0.00018414503665543886, "loss": 0.6664977073669434, "step": 46470 }, { "epoch": 0.27628677235467897, "grad_norm": 1.4024872779846191, "learning_rate": 0.00018418466415692493, "loss": 0.6258605003356934, "step": 46480 }, { "epoch": 0.2763462144313474, "grad_norm": 1.7308300733566284, "learning_rate": 0.00018422429165841094, "loss": 0.7013322830200195, "step": 46490 }, { "epoch": 0.27640565650801574, "grad_norm": 1.3372058868408203, "learning_rate": 0.00018426391915989698, "loss": 0.6269161224365234, "step": 46500 }, { "epoch": 0.27646509858468415, "grad_norm": 1.6956970691680908, "learning_rate": 0.00018430354666138302, "loss": 0.6888992309570312, "step": 46510 }, { "epoch": 0.27652454066135257, "grad_norm": 1.7811026573181152, "learning_rate": 0.00018434317416286903, "loss": 0.7083878517150879, "step": 46520 }, { "epoch": 0.27658398273802093, "grad_norm": 1.8069684505462646, "learning_rate": 0.00018438280166435507, "loss": 0.6865620613098145, "step": 46530 }, { "epoch": 0.27664342481468934, "grad_norm": 1.6857050657272339, "learning_rate": 0.00018442242916584108, "loss": 0.692444896697998, "step": 46540 }, { "epoch": 0.2767028668913577, "grad_norm": 1.514432430267334, "learning_rate": 0.00018446205666732715, "loss": 0.7559982776641846, "step": 46550 }, { "epoch": 0.2767623089680261, "grad_norm": 1.572277307510376, "learning_rate": 0.00018450168416881318, "loss": 0.7158325672149658, "step": 46560 }, { "epoch": 0.2768217510446945, "grad_norm": 1.6072944402694702, "learning_rate": 0.0001845413116702992, "loss": 0.6753684520721436, "step": 46570 }, { "epoch": 0.2768811931213629, "grad_norm": 1.640386700630188, "learning_rate": 0.00018458093917178523, "loss": 0.7166173934936524, "step": 46580 }, { "epoch": 0.2769406351980313, "grad_norm": 1.5385311841964722, "learning_rate": 0.00018462056667327125, "loss": 0.7146337509155274, "step": 46590 }, { "epoch": 0.27700007727469966, "grad_norm": 1.6270313262939453, "learning_rate": 0.00018466019417475728, "loss": 0.664652681350708, "step": 46600 }, { "epoch": 0.2770595193513681, "grad_norm": 1.732274055480957, "learning_rate": 0.00018469982167624332, "loss": 0.6524818420410157, "step": 46610 }, { "epoch": 0.27711896142803644, "grad_norm": 1.7041844129562378, "learning_rate": 0.00018473944917772936, "loss": 0.6868609428405762, "step": 46620 }, { "epoch": 0.27717840350470485, "grad_norm": 1.9318275451660156, "learning_rate": 0.0001847790766792154, "loss": 0.6885326385498047, "step": 46630 }, { "epoch": 0.2772378455813732, "grad_norm": 1.833639144897461, "learning_rate": 0.0001848187041807014, "loss": 0.6836797714233398, "step": 46640 }, { "epoch": 0.2772972876580416, "grad_norm": 1.941678524017334, "learning_rate": 0.00018485833168218745, "loss": 0.6678263664245605, "step": 46650 }, { "epoch": 0.27735672973471004, "grad_norm": 1.506534457206726, "learning_rate": 0.00018489795918367346, "loss": 0.6664978981018066, "step": 46660 }, { "epoch": 0.2774161718113784, "grad_norm": 1.7348783016204834, "learning_rate": 0.0001849375866851595, "loss": 0.6983765602111817, "step": 46670 }, { "epoch": 0.2774756138880468, "grad_norm": 1.5823853015899658, "learning_rate": 0.00018497721418664554, "loss": 0.6997953891754151, "step": 46680 }, { "epoch": 0.27753505596471517, "grad_norm": 1.9504727125167847, "learning_rate": 0.00018501684168813158, "loss": 0.639309024810791, "step": 46690 }, { "epoch": 0.2775944980413836, "grad_norm": 1.547128438949585, "learning_rate": 0.00018505646918961762, "loss": 0.7280341148376465, "step": 46700 }, { "epoch": 0.27765394011805195, "grad_norm": 2.397627115249634, "learning_rate": 0.00018509609669110363, "loss": 0.6322658061981201, "step": 46710 }, { "epoch": 0.27771338219472036, "grad_norm": 1.5031262636184692, "learning_rate": 0.00018513572419258967, "loss": 0.6711640357971191, "step": 46720 }, { "epoch": 0.2777728242713887, "grad_norm": 1.8617721796035767, "learning_rate": 0.0001851753516940757, "loss": 0.6748255729675293, "step": 46730 }, { "epoch": 0.27783226634805713, "grad_norm": 1.64765465259552, "learning_rate": 0.00018521497919556172, "loss": 0.69111647605896, "step": 46740 }, { "epoch": 0.27789170842472555, "grad_norm": 1.8695472478866577, "learning_rate": 0.00018525460669704776, "loss": 0.6489445686340332, "step": 46750 }, { "epoch": 0.2779511505013939, "grad_norm": 2.0001449584960938, "learning_rate": 0.0001852942341985338, "loss": 0.6496541976928711, "step": 46760 }, { "epoch": 0.2780105925780623, "grad_norm": 1.7324031591415405, "learning_rate": 0.00018533386170001983, "loss": 0.730840015411377, "step": 46770 }, { "epoch": 0.2780700346547307, "grad_norm": 1.4022653102874756, "learning_rate": 0.00018537348920150584, "loss": 0.6431443691253662, "step": 46780 }, { "epoch": 0.2781294767313991, "grad_norm": 1.2675172090530396, "learning_rate": 0.00018541311670299188, "loss": 0.708594799041748, "step": 46790 }, { "epoch": 0.27818891880806745, "grad_norm": 1.7744694948196411, "learning_rate": 0.00018545274420447792, "loss": 0.6800099372863769, "step": 46800 }, { "epoch": 0.27824836088473587, "grad_norm": 1.4386460781097412, "learning_rate": 0.00018549237170596393, "loss": 0.6702807903289795, "step": 46810 }, { "epoch": 0.2783078029614043, "grad_norm": 1.3462755680084229, "learning_rate": 0.00018553199920744997, "loss": 0.6345503807067872, "step": 46820 }, { "epoch": 0.27836724503807264, "grad_norm": 1.5073260068893433, "learning_rate": 0.000185571626708936, "loss": 0.6913407802581787, "step": 46830 }, { "epoch": 0.27842668711474106, "grad_norm": 1.5781581401824951, "learning_rate": 0.00018561125421042205, "loss": 0.6451304435729981, "step": 46840 }, { "epoch": 0.2784861291914094, "grad_norm": 1.594535231590271, "learning_rate": 0.0001856508817119081, "loss": 0.6426199436187744, "step": 46850 }, { "epoch": 0.27854557126807783, "grad_norm": 1.5879065990447998, "learning_rate": 0.0001856905092133941, "loss": 0.6583640098571777, "step": 46860 }, { "epoch": 0.2786050133447462, "grad_norm": 1.5818127393722534, "learning_rate": 0.00018573013671488014, "loss": 0.6812963962554932, "step": 46870 }, { "epoch": 0.2786644554214146, "grad_norm": 1.561328411102295, "learning_rate": 0.00018576976421636615, "loss": 0.7472137451171875, "step": 46880 }, { "epoch": 0.278723897498083, "grad_norm": 1.9438860416412354, "learning_rate": 0.0001858093917178522, "loss": 0.6396354675292969, "step": 46890 }, { "epoch": 0.2787833395747514, "grad_norm": 1.7884066104888916, "learning_rate": 0.00018584901921933823, "loss": 0.7146231651306152, "step": 46900 }, { "epoch": 0.2788427816514198, "grad_norm": 1.5390206575393677, "learning_rate": 0.00018588864672082427, "loss": 0.7052614212036132, "step": 46910 }, { "epoch": 0.27890222372808815, "grad_norm": 1.5853853225708008, "learning_rate": 0.0001859282742223103, "loss": 0.6584673881530761, "step": 46920 }, { "epoch": 0.27896166580475656, "grad_norm": 1.6837605237960815, "learning_rate": 0.00018596790172379632, "loss": 0.6735322952270508, "step": 46930 }, { "epoch": 0.2790211078814249, "grad_norm": 1.8161530494689941, "learning_rate": 0.00018600752922528235, "loss": 0.7107518672943115, "step": 46940 }, { "epoch": 0.27908054995809334, "grad_norm": 1.7339963912963867, "learning_rate": 0.00018604715672676837, "loss": 0.6456759452819825, "step": 46950 }, { "epoch": 0.27913999203476175, "grad_norm": 1.7656348943710327, "learning_rate": 0.0001860867842282544, "loss": 0.7026282787322998, "step": 46960 }, { "epoch": 0.2791994341114301, "grad_norm": 1.6872133016586304, "learning_rate": 0.00018612641172974047, "loss": 0.6188354015350341, "step": 46970 }, { "epoch": 0.2792588761880985, "grad_norm": 1.7181146144866943, "learning_rate": 0.00018616603923122648, "loss": 0.6971401691436767, "step": 46980 }, { "epoch": 0.2793183182647669, "grad_norm": 1.7918890714645386, "learning_rate": 0.00018620566673271252, "loss": 0.7039870262145996, "step": 46990 }, { "epoch": 0.2793777603414353, "grad_norm": 1.9922188520431519, "learning_rate": 0.00018624529423419853, "loss": 0.6379752159118652, "step": 47000 }, { "epoch": 0.27943720241810366, "grad_norm": 2.3455958366394043, "learning_rate": 0.00018628492173568457, "loss": 0.6507220268249512, "step": 47010 }, { "epoch": 0.2794966444947721, "grad_norm": 1.8384495973587036, "learning_rate": 0.0001863245492371706, "loss": 0.679536247253418, "step": 47020 }, { "epoch": 0.2795560865714405, "grad_norm": 1.6988774538040161, "learning_rate": 0.00018636417673865662, "loss": 0.7377337455749512, "step": 47030 }, { "epoch": 0.27961552864810885, "grad_norm": 1.8904248476028442, "learning_rate": 0.0001864038042401427, "loss": 0.6904245376586914, "step": 47040 }, { "epoch": 0.27967497072477726, "grad_norm": 1.4650769233703613, "learning_rate": 0.0001864434317416287, "loss": 0.6366236209869385, "step": 47050 }, { "epoch": 0.2797344128014456, "grad_norm": 1.8554350137710571, "learning_rate": 0.00018648305924311474, "loss": 0.7037135124206543, "step": 47060 }, { "epoch": 0.27979385487811403, "grad_norm": 1.2986801862716675, "learning_rate": 0.00018652268674460075, "loss": 0.7198032379150391, "step": 47070 }, { "epoch": 0.2798532969547824, "grad_norm": 1.4924966096878052, "learning_rate": 0.0001865623142460868, "loss": 0.6566354274749756, "step": 47080 }, { "epoch": 0.2799127390314508, "grad_norm": 1.4052106142044067, "learning_rate": 0.00018660194174757283, "loss": 0.6888169288635254, "step": 47090 }, { "epoch": 0.27997218110811917, "grad_norm": 1.3419278860092163, "learning_rate": 0.00018664156924905884, "loss": 0.6235755920410156, "step": 47100 }, { "epoch": 0.2800316231847876, "grad_norm": 1.9078288078308105, "learning_rate": 0.0001866811967505449, "loss": 0.7197055816650391, "step": 47110 }, { "epoch": 0.280091065261456, "grad_norm": 1.6247555017471313, "learning_rate": 0.00018672082425203091, "loss": 0.6383624076843262, "step": 47120 }, { "epoch": 0.28015050733812435, "grad_norm": 1.714056134223938, "learning_rate": 0.00018676045175351695, "loss": 0.6763832092285156, "step": 47130 }, { "epoch": 0.28020994941479277, "grad_norm": 1.9917701482772827, "learning_rate": 0.000186800079255003, "loss": 0.6897756576538085, "step": 47140 }, { "epoch": 0.28026939149146113, "grad_norm": 1.3781152963638306, "learning_rate": 0.000186839706756489, "loss": 0.7462030410766601, "step": 47150 }, { "epoch": 0.28032883356812954, "grad_norm": 1.6624661684036255, "learning_rate": 0.00018687933425797504, "loss": 0.7060948848724365, "step": 47160 }, { "epoch": 0.2803882756447979, "grad_norm": 1.825675368309021, "learning_rate": 0.00018691896175946105, "loss": 0.6920224666595459, "step": 47170 }, { "epoch": 0.2804477177214663, "grad_norm": 1.713962197303772, "learning_rate": 0.00018695858926094712, "loss": 0.698537540435791, "step": 47180 }, { "epoch": 0.28050715979813473, "grad_norm": 1.8814482688903809, "learning_rate": 0.00018699821676243313, "loss": 0.6623807907104492, "step": 47190 }, { "epoch": 0.2805666018748031, "grad_norm": 1.8343020677566528, "learning_rate": 0.00018703784426391917, "loss": 0.6350467681884766, "step": 47200 }, { "epoch": 0.2806260439514715, "grad_norm": 1.786256194114685, "learning_rate": 0.0001870774717654052, "loss": 0.690423583984375, "step": 47210 }, { "epoch": 0.28068548602813986, "grad_norm": 1.34086275100708, "learning_rate": 0.00018711709926689122, "loss": 0.6450126647949219, "step": 47220 }, { "epoch": 0.2807449281048083, "grad_norm": 1.5491774082183838, "learning_rate": 0.00018715672676837726, "loss": 0.7935891151428223, "step": 47230 }, { "epoch": 0.28080437018147664, "grad_norm": 1.7115235328674316, "learning_rate": 0.00018719635426986327, "loss": 0.7288510799407959, "step": 47240 }, { "epoch": 0.28086381225814505, "grad_norm": 1.5867618322372437, "learning_rate": 0.00018723598177134934, "loss": 0.7113553524017334, "step": 47250 }, { "epoch": 0.28092325433481347, "grad_norm": 1.6377439498901367, "learning_rate": 0.00018727560927283537, "loss": 0.6508296012878418, "step": 47260 }, { "epoch": 0.2809826964114818, "grad_norm": 1.4742205142974854, "learning_rate": 0.00018731523677432139, "loss": 0.7152940273284912, "step": 47270 }, { "epoch": 0.28104213848815024, "grad_norm": 1.7882368564605713, "learning_rate": 0.00018735486427580742, "loss": 0.7055698871612549, "step": 47280 }, { "epoch": 0.2811015805648186, "grad_norm": 1.7531930208206177, "learning_rate": 0.00018739449177729344, "loss": 0.7060685157775879, "step": 47290 }, { "epoch": 0.281161022641487, "grad_norm": 1.987402081489563, "learning_rate": 0.00018743411927877948, "loss": 0.6857690811157227, "step": 47300 }, { "epoch": 0.28122046471815537, "grad_norm": 1.7487080097198486, "learning_rate": 0.00018747374678026551, "loss": 0.7488895416259765, "step": 47310 }, { "epoch": 0.2812799067948238, "grad_norm": 1.4493563175201416, "learning_rate": 0.00018751337428175155, "loss": 0.6703484535217286, "step": 47320 }, { "epoch": 0.2813393488714922, "grad_norm": 2.0183420181274414, "learning_rate": 0.0001875530017832376, "loss": 0.7042205810546875, "step": 47330 }, { "epoch": 0.28139879094816056, "grad_norm": 1.6783474683761597, "learning_rate": 0.0001875926292847236, "loss": 0.622805118560791, "step": 47340 }, { "epoch": 0.281458233024829, "grad_norm": 1.9536511898040771, "learning_rate": 0.00018763225678620964, "loss": 0.6564841270446777, "step": 47350 }, { "epoch": 0.28151767510149733, "grad_norm": 1.307612657546997, "learning_rate": 0.00018767188428769565, "loss": 0.6313369750976563, "step": 47360 }, { "epoch": 0.28157711717816575, "grad_norm": 1.3874270915985107, "learning_rate": 0.0001877115117891817, "loss": 0.656975507736206, "step": 47370 }, { "epoch": 0.2816365592548341, "grad_norm": 1.6914725303649902, "learning_rate": 0.00018775113929066773, "loss": 0.6223737716674804, "step": 47380 }, { "epoch": 0.2816960013315025, "grad_norm": 2.0756170749664307, "learning_rate": 0.00018779076679215377, "loss": 0.6554330825805664, "step": 47390 }, { "epoch": 0.2817554434081709, "grad_norm": 1.433400273323059, "learning_rate": 0.0001878303942936398, "loss": 0.6364834308624268, "step": 47400 }, { "epoch": 0.2818148854848393, "grad_norm": 1.7004555463790894, "learning_rate": 0.00018787002179512582, "loss": 0.6623809337615967, "step": 47410 }, { "epoch": 0.2818743275615077, "grad_norm": 1.8995177745819092, "learning_rate": 0.00018790964929661186, "loss": 0.6469023704528809, "step": 47420 }, { "epoch": 0.28193376963817607, "grad_norm": 1.6487120389938354, "learning_rate": 0.0001879492767980979, "loss": 0.6399418830871582, "step": 47430 }, { "epoch": 0.2819932117148445, "grad_norm": 1.5965492725372314, "learning_rate": 0.0001879889042995839, "loss": 0.6789798736572266, "step": 47440 }, { "epoch": 0.28205265379151284, "grad_norm": 1.7130892276763916, "learning_rate": 0.00018802853180106997, "loss": 0.7382890701293945, "step": 47450 }, { "epoch": 0.28211209586818126, "grad_norm": 1.595154047012329, "learning_rate": 0.00018806815930255599, "loss": 0.6885890007019043, "step": 47460 }, { "epoch": 0.2821715379448496, "grad_norm": 1.8891161680221558, "learning_rate": 0.00018810778680404202, "loss": 0.6486140251159668, "step": 47470 }, { "epoch": 0.28223098002151803, "grad_norm": 1.3397157192230225, "learning_rate": 0.00018814741430552804, "loss": 0.7383446216583252, "step": 47480 }, { "epoch": 0.28229042209818644, "grad_norm": 1.773754358291626, "learning_rate": 0.00018818704180701407, "loss": 0.7710799217224121, "step": 47490 }, { "epoch": 0.2823498641748548, "grad_norm": 1.6291667222976685, "learning_rate": 0.0001882266693085001, "loss": 0.7252575397491455, "step": 47500 }, { "epoch": 0.2824093062515232, "grad_norm": 1.632124900817871, "learning_rate": 0.00018826629680998612, "loss": 0.729675006866455, "step": 47510 }, { "epoch": 0.2824687483281916, "grad_norm": 1.6344897747039795, "learning_rate": 0.0001883059243114722, "loss": 0.6843575954437255, "step": 47520 }, { "epoch": 0.28252819040486, "grad_norm": 1.957794189453125, "learning_rate": 0.0001883455518129582, "loss": 0.6479741096496582, "step": 47530 }, { "epoch": 0.28258763248152835, "grad_norm": 1.6199842691421509, "learning_rate": 0.00018838517931444424, "loss": 0.7522449970245362, "step": 47540 }, { "epoch": 0.28264707455819676, "grad_norm": 1.8397079706192017, "learning_rate": 0.00018842480681593028, "loss": 0.6981810569763184, "step": 47550 }, { "epoch": 0.2827065166348652, "grad_norm": 1.8312122821807861, "learning_rate": 0.0001884644343174163, "loss": 0.7258194923400879, "step": 47560 }, { "epoch": 0.28276595871153354, "grad_norm": 1.3790372610092163, "learning_rate": 0.00018850406181890233, "loss": 0.7064344406127929, "step": 47570 }, { "epoch": 0.28282540078820195, "grad_norm": 1.718675136566162, "learning_rate": 0.00018854368932038834, "loss": 0.6527190685272217, "step": 47580 }, { "epoch": 0.2828848428648703, "grad_norm": 2.1700193881988525, "learning_rate": 0.0001885833168218744, "loss": 0.6872784614562988, "step": 47590 }, { "epoch": 0.2829442849415387, "grad_norm": 1.6324576139450073, "learning_rate": 0.00018862294432336042, "loss": 0.6981465339660644, "step": 47600 }, { "epoch": 0.2830037270182071, "grad_norm": 1.3950495719909668, "learning_rate": 0.00018866257182484646, "loss": 0.7126584053039551, "step": 47610 }, { "epoch": 0.2830631690948755, "grad_norm": 1.4181368350982666, "learning_rate": 0.0001887021993263325, "loss": 0.6824772834777832, "step": 47620 }, { "epoch": 0.2831226111715439, "grad_norm": 1.639984369277954, "learning_rate": 0.0001887418268278185, "loss": 0.7301749229431153, "step": 47630 }, { "epoch": 0.2831820532482123, "grad_norm": 2.0987608432769775, "learning_rate": 0.00018878145432930455, "loss": 0.7436568260192871, "step": 47640 }, { "epoch": 0.2832414953248807, "grad_norm": 1.6449477672576904, "learning_rate": 0.00018882108183079056, "loss": 0.6770801544189453, "step": 47650 }, { "epoch": 0.28330093740154905, "grad_norm": 1.7739386558532715, "learning_rate": 0.00018886070933227662, "loss": 0.704875898361206, "step": 47660 }, { "epoch": 0.28336037947821746, "grad_norm": 1.847794532775879, "learning_rate": 0.00018890033683376263, "loss": 0.665095043182373, "step": 47670 }, { "epoch": 0.2834198215548858, "grad_norm": 1.6735060214996338, "learning_rate": 0.00018893996433524867, "loss": 0.6970410346984863, "step": 47680 }, { "epoch": 0.28347926363155423, "grad_norm": 1.8001500368118286, "learning_rate": 0.0001889795918367347, "loss": 0.703178071975708, "step": 47690 }, { "epoch": 0.28353870570822265, "grad_norm": 1.518491268157959, "learning_rate": 0.00018901921933822072, "loss": 0.6603629112243652, "step": 47700 }, { "epoch": 0.283598147784891, "grad_norm": 1.5153732299804688, "learning_rate": 0.00018905884683970676, "loss": 0.8034790992736817, "step": 47710 }, { "epoch": 0.2836575898615594, "grad_norm": 2.148519515991211, "learning_rate": 0.0001890984743411928, "loss": 0.7056181907653809, "step": 47720 }, { "epoch": 0.2837170319382278, "grad_norm": 2.2537572383880615, "learning_rate": 0.00018913810184267884, "loss": 0.6839791297912597, "step": 47730 }, { "epoch": 0.2837764740148962, "grad_norm": 1.2395904064178467, "learning_rate": 0.00018917772934416488, "loss": 0.6453059196472168, "step": 47740 }, { "epoch": 0.28383591609156456, "grad_norm": 1.7177343368530273, "learning_rate": 0.0001892173568456509, "loss": 0.7025140762329102, "step": 47750 }, { "epoch": 0.28389535816823297, "grad_norm": 1.4005069732666016, "learning_rate": 0.00018925698434713693, "loss": 0.6404204368591309, "step": 47760 }, { "epoch": 0.28395480024490133, "grad_norm": 2.1224606037139893, "learning_rate": 0.00018929661184862294, "loss": 0.6759281635284424, "step": 47770 }, { "epoch": 0.28401424232156974, "grad_norm": 1.4192179441452026, "learning_rate": 0.00018933623935010898, "loss": 0.7321127891540528, "step": 47780 }, { "epoch": 0.28407368439823816, "grad_norm": 2.032707929611206, "learning_rate": 0.00018937586685159502, "loss": 0.702731990814209, "step": 47790 }, { "epoch": 0.2841331264749065, "grad_norm": 1.704365849494934, "learning_rate": 0.00018941549435308106, "loss": 0.6439066886901855, "step": 47800 }, { "epoch": 0.28419256855157493, "grad_norm": 1.7609426975250244, "learning_rate": 0.0001894551218545671, "loss": 0.7057046890258789, "step": 47810 }, { "epoch": 0.2842520106282433, "grad_norm": 1.766609787940979, "learning_rate": 0.0001894947493560531, "loss": 0.6531321048736572, "step": 47820 }, { "epoch": 0.2843114527049117, "grad_norm": 1.4152060747146606, "learning_rate": 0.00018953437685753914, "loss": 0.6821561813354492, "step": 47830 }, { "epoch": 0.28437089478158006, "grad_norm": 1.9877216815948486, "learning_rate": 0.00018957400435902518, "loss": 0.7426969528198242, "step": 47840 }, { "epoch": 0.2844303368582485, "grad_norm": 1.3469765186309814, "learning_rate": 0.0001896136318605112, "loss": 0.7579179286956788, "step": 47850 }, { "epoch": 0.2844897789349169, "grad_norm": 1.6789038181304932, "learning_rate": 0.00018965325936199723, "loss": 0.6867675304412841, "step": 47860 }, { "epoch": 0.28454922101158525, "grad_norm": 1.4849661588668823, "learning_rate": 0.00018969288686348327, "loss": 0.6614347457885742, "step": 47870 }, { "epoch": 0.28460866308825367, "grad_norm": 1.2715013027191162, "learning_rate": 0.0001897325143649693, "loss": 0.6414683341979981, "step": 47880 }, { "epoch": 0.284668105164922, "grad_norm": 1.5847545862197876, "learning_rate": 0.00018977214186645532, "loss": 0.690641975402832, "step": 47890 }, { "epoch": 0.28472754724159044, "grad_norm": 1.60243821144104, "learning_rate": 0.00018981176936794136, "loss": 0.7143939018249512, "step": 47900 }, { "epoch": 0.2847869893182588, "grad_norm": 1.7896243333816528, "learning_rate": 0.0001898513968694274, "loss": 0.6814345359802246, "step": 47910 }, { "epoch": 0.2848464313949272, "grad_norm": 1.6296887397766113, "learning_rate": 0.0001898910243709134, "loss": 0.6743089199066162, "step": 47920 }, { "epoch": 0.2849058734715956, "grad_norm": 1.2792820930480957, "learning_rate": 0.00018993065187239945, "loss": 0.7086298942565918, "step": 47930 }, { "epoch": 0.284965315548264, "grad_norm": 1.6642076969146729, "learning_rate": 0.0001899702793738855, "loss": 0.664576244354248, "step": 47940 }, { "epoch": 0.2850247576249324, "grad_norm": 1.597350001335144, "learning_rate": 0.00019000990687537153, "loss": 0.742679214477539, "step": 47950 }, { "epoch": 0.28508419970160076, "grad_norm": 1.7801793813705444, "learning_rate": 0.00019004953437685757, "loss": 0.710801362991333, "step": 47960 }, { "epoch": 0.2851436417782692, "grad_norm": 1.8307602405548096, "learning_rate": 0.00019008916187834358, "loss": 0.7575780868530273, "step": 47970 }, { "epoch": 0.28520308385493753, "grad_norm": 1.7698659896850586, "learning_rate": 0.00019012878937982962, "loss": 0.6464375019073486, "step": 47980 }, { "epoch": 0.28526252593160595, "grad_norm": 1.1716060638427734, "learning_rate": 0.00019016841688131563, "loss": 0.7310670852661133, "step": 47990 }, { "epoch": 0.28532196800827436, "grad_norm": 1.5063741207122803, "learning_rate": 0.00019020804438280167, "loss": 0.6777411460876465, "step": 48000 }, { "epoch": 0.2853814100849427, "grad_norm": 2.021252393722534, "learning_rate": 0.0001902476718842877, "loss": 0.6413517951965332, "step": 48010 }, { "epoch": 0.28544085216161114, "grad_norm": 1.9143812656402588, "learning_rate": 0.00019028729938577374, "loss": 0.7192986011505127, "step": 48020 }, { "epoch": 0.2855002942382795, "grad_norm": 1.6526527404785156, "learning_rate": 0.00019032692688725978, "loss": 0.6985908508300781, "step": 48030 }, { "epoch": 0.2855597363149479, "grad_norm": 1.8114110231399536, "learning_rate": 0.0001903665543887458, "loss": 0.7102019786834717, "step": 48040 }, { "epoch": 0.28561917839161627, "grad_norm": 1.8075531721115112, "learning_rate": 0.00019040618189023183, "loss": 0.6749106407165527, "step": 48050 }, { "epoch": 0.2856786204682847, "grad_norm": 1.568385362625122, "learning_rate": 0.00019044580939171784, "loss": 0.6640201568603515, "step": 48060 }, { "epoch": 0.2857380625449531, "grad_norm": 1.732079267501831, "learning_rate": 0.00019048543689320388, "loss": 0.7603131771087647, "step": 48070 }, { "epoch": 0.28579750462162146, "grad_norm": 1.6825178861618042, "learning_rate": 0.00019052506439468992, "loss": 0.6451542377471924, "step": 48080 }, { "epoch": 0.28585694669828987, "grad_norm": 1.2398675680160522, "learning_rate": 0.00019056469189617596, "loss": 0.6260095596313476, "step": 48090 }, { "epoch": 0.28591638877495823, "grad_norm": 1.585032343864441, "learning_rate": 0.000190604319397662, "loss": 0.7266083717346191, "step": 48100 }, { "epoch": 0.28597583085162664, "grad_norm": 2.059734582901001, "learning_rate": 0.000190643946899148, "loss": 0.7304985046386718, "step": 48110 }, { "epoch": 0.286035272928295, "grad_norm": 1.8962557315826416, "learning_rate": 0.00019068357440063405, "loss": 0.7060382843017579, "step": 48120 }, { "epoch": 0.2860947150049634, "grad_norm": 2.0111544132232666, "learning_rate": 0.0001907232019021201, "loss": 0.7031878471374512, "step": 48130 }, { "epoch": 0.2861541570816318, "grad_norm": 1.9479119777679443, "learning_rate": 0.0001907628294036061, "loss": 0.7574013233184814, "step": 48140 }, { "epoch": 0.2862135991583002, "grad_norm": 1.7683757543563843, "learning_rate": 0.00019080245690509216, "loss": 0.6352285861968994, "step": 48150 }, { "epoch": 0.2862730412349686, "grad_norm": 1.6990818977355957, "learning_rate": 0.00019084208440657818, "loss": 0.6383560180664063, "step": 48160 }, { "epoch": 0.28633248331163696, "grad_norm": 1.9208295345306396, "learning_rate": 0.00019088171190806421, "loss": 0.764866304397583, "step": 48170 }, { "epoch": 0.2863919253883054, "grad_norm": 1.6856505870819092, "learning_rate": 0.00019092133940955023, "loss": 0.7027997493743896, "step": 48180 }, { "epoch": 0.28645136746497374, "grad_norm": 1.8321226835250854, "learning_rate": 0.00019096096691103626, "loss": 0.7299065113067627, "step": 48190 }, { "epoch": 0.28651080954164215, "grad_norm": 1.710754632949829, "learning_rate": 0.0001910005944125223, "loss": 0.7353265762329102, "step": 48200 }, { "epoch": 0.2865702516183105, "grad_norm": 1.815401315689087, "learning_rate": 0.00019104022191400832, "loss": 0.6506733894348145, "step": 48210 }, { "epoch": 0.2866296936949789, "grad_norm": 1.8814836740493774, "learning_rate": 0.00019107984941549438, "loss": 0.7047560214996338, "step": 48220 }, { "epoch": 0.28668913577164734, "grad_norm": 1.5688812732696533, "learning_rate": 0.0001911194769169804, "loss": 0.7274821281433106, "step": 48230 }, { "epoch": 0.2867485778483157, "grad_norm": 1.7031075954437256, "learning_rate": 0.00019115910441846643, "loss": 0.6434665203094483, "step": 48240 }, { "epoch": 0.2868080199249841, "grad_norm": 1.8982247114181519, "learning_rate": 0.00019119873191995247, "loss": 0.669527244567871, "step": 48250 }, { "epoch": 0.2868674620016525, "grad_norm": 2.2316110134124756, "learning_rate": 0.00019123835942143848, "loss": 0.7303579330444336, "step": 48260 }, { "epoch": 0.2869269040783209, "grad_norm": 1.737776279449463, "learning_rate": 0.00019127798692292452, "loss": 0.7093986511230469, "step": 48270 }, { "epoch": 0.28698634615498925, "grad_norm": 1.5759364366531372, "learning_rate": 0.00019131761442441053, "loss": 0.7469856262207031, "step": 48280 }, { "epoch": 0.28704578823165766, "grad_norm": 1.7478172779083252, "learning_rate": 0.0001913572419258966, "loss": 0.6444502830505371, "step": 48290 }, { "epoch": 0.2871052303083261, "grad_norm": 1.4908678531646729, "learning_rate": 0.0001913968694273826, "loss": 0.6922008514404296, "step": 48300 }, { "epoch": 0.28716467238499443, "grad_norm": 1.4171358346939087, "learning_rate": 0.00019143649692886865, "loss": 0.6511502742767334, "step": 48310 }, { "epoch": 0.28722411446166285, "grad_norm": 2.1173017024993896, "learning_rate": 0.00019147612443035469, "loss": 0.650717830657959, "step": 48320 }, { "epoch": 0.2872835565383312, "grad_norm": 2.0390965938568115, "learning_rate": 0.0001915157519318407, "loss": 0.6776584148406982, "step": 48330 }, { "epoch": 0.2873429986149996, "grad_norm": 1.4612421989440918, "learning_rate": 0.00019155537943332674, "loss": 0.6776539802551269, "step": 48340 }, { "epoch": 0.287402440691668, "grad_norm": 2.034574031829834, "learning_rate": 0.00019159500693481275, "loss": 0.6854265213012696, "step": 48350 }, { "epoch": 0.2874618827683364, "grad_norm": 1.48708975315094, "learning_rate": 0.00019163463443629881, "loss": 0.6377358436584473, "step": 48360 }, { "epoch": 0.2875213248450048, "grad_norm": 1.9110621213912964, "learning_rate": 0.00019167426193778483, "loss": 0.7413890838623047, "step": 48370 }, { "epoch": 0.28758076692167317, "grad_norm": 1.6461457014083862, "learning_rate": 0.00019171388943927086, "loss": 0.6630536556243897, "step": 48380 }, { "epoch": 0.2876402089983416, "grad_norm": 1.723331332206726, "learning_rate": 0.0001917535169407569, "loss": 0.6690503120422363, "step": 48390 }, { "epoch": 0.28769965107500994, "grad_norm": 1.671102523803711, "learning_rate": 0.00019179314444224291, "loss": 0.645281982421875, "step": 48400 }, { "epoch": 0.28775909315167836, "grad_norm": 1.503537654876709, "learning_rate": 0.00019183277194372895, "loss": 0.6915502548217773, "step": 48410 }, { "epoch": 0.2878185352283467, "grad_norm": 1.4529474973678589, "learning_rate": 0.000191872399445215, "loss": 0.6824623107910156, "step": 48420 }, { "epoch": 0.28787797730501513, "grad_norm": 1.5851399898529053, "learning_rate": 0.00019191202694670103, "loss": 0.6786980152130127, "step": 48430 }, { "epoch": 0.28793741938168355, "grad_norm": 1.8204673528671265, "learning_rate": 0.00019195165444818707, "loss": 0.6602819442749024, "step": 48440 }, { "epoch": 0.2879968614583519, "grad_norm": 1.7047183513641357, "learning_rate": 0.00019199128194967308, "loss": 0.7245528221130371, "step": 48450 }, { "epoch": 0.2880563035350203, "grad_norm": 1.7439781427383423, "learning_rate": 0.00019203090945115912, "loss": 0.759213924407959, "step": 48460 }, { "epoch": 0.2881157456116887, "grad_norm": 1.3401604890823364, "learning_rate": 0.00019207053695264513, "loss": 0.6709782123565674, "step": 48470 }, { "epoch": 0.2881751876883571, "grad_norm": 2.089263677597046, "learning_rate": 0.00019211016445413117, "loss": 0.6867817878723145, "step": 48480 }, { "epoch": 0.28823462976502545, "grad_norm": 1.4529601335525513, "learning_rate": 0.0001921497919556172, "loss": 0.6382549285888672, "step": 48490 }, { "epoch": 0.28829407184169387, "grad_norm": 1.909018874168396, "learning_rate": 0.00019218941945710325, "loss": 0.7015417575836181, "step": 48500 }, { "epoch": 0.2883535139183622, "grad_norm": 1.9454731941223145, "learning_rate": 0.00019222904695858928, "loss": 0.74227294921875, "step": 48510 }, { "epoch": 0.28841295599503064, "grad_norm": 1.4890936613082886, "learning_rate": 0.0001922686744600753, "loss": 0.6972230434417724, "step": 48520 }, { "epoch": 0.28847239807169905, "grad_norm": 1.8953707218170166, "learning_rate": 0.00019230830196156134, "loss": 0.6206676006317139, "step": 48530 }, { "epoch": 0.2885318401483674, "grad_norm": 1.7672628164291382, "learning_rate": 0.00019234792946304737, "loss": 0.695332145690918, "step": 48540 }, { "epoch": 0.28859128222503583, "grad_norm": 2.38374662399292, "learning_rate": 0.00019238755696453339, "loss": 0.7211843490600586, "step": 48550 }, { "epoch": 0.2886507243017042, "grad_norm": 1.5115795135498047, "learning_rate": 0.00019242718446601942, "loss": 0.6776049613952637, "step": 48560 }, { "epoch": 0.2887101663783726, "grad_norm": 1.7085700035095215, "learning_rate": 0.00019246681196750546, "loss": 0.6730385780334472, "step": 48570 }, { "epoch": 0.28876960845504096, "grad_norm": 1.7541284561157227, "learning_rate": 0.0001925064394689915, "loss": 0.7111745834350586, "step": 48580 }, { "epoch": 0.2888290505317094, "grad_norm": 2.427833080291748, "learning_rate": 0.0001925460669704775, "loss": 0.7151873588562012, "step": 48590 }, { "epoch": 0.2888884926083778, "grad_norm": 1.7019742727279663, "learning_rate": 0.00019258569447196355, "loss": 0.7674942016601562, "step": 48600 }, { "epoch": 0.28894793468504615, "grad_norm": 1.6069316864013672, "learning_rate": 0.0001926253219734496, "loss": 0.673582649230957, "step": 48610 }, { "epoch": 0.28900737676171456, "grad_norm": 2.1135246753692627, "learning_rate": 0.0001926649494749356, "loss": 0.667420482635498, "step": 48620 }, { "epoch": 0.2890668188383829, "grad_norm": 1.6108421087265015, "learning_rate": 0.00019270457697642164, "loss": 0.7068828582763672, "step": 48630 }, { "epoch": 0.28912626091505134, "grad_norm": 1.5401586294174194, "learning_rate": 0.00019274420447790768, "loss": 0.7486019611358643, "step": 48640 }, { "epoch": 0.2891857029917197, "grad_norm": 1.538822889328003, "learning_rate": 0.00019278383197939372, "loss": 0.658708143234253, "step": 48650 }, { "epoch": 0.2892451450683881, "grad_norm": 1.3225685358047485, "learning_rate": 0.00019282345948087973, "loss": 0.6580960273742675, "step": 48660 }, { "epoch": 0.2893045871450565, "grad_norm": 2.2157540321350098, "learning_rate": 0.00019286308698236577, "loss": 0.7112582206726075, "step": 48670 }, { "epoch": 0.2893640292217249, "grad_norm": 1.8569737672805786, "learning_rate": 0.0001929027144838518, "loss": 0.684381103515625, "step": 48680 }, { "epoch": 0.2894234712983933, "grad_norm": 1.3878304958343506, "learning_rate": 0.00019294234198533782, "loss": 0.6389158248901368, "step": 48690 }, { "epoch": 0.28948291337506166, "grad_norm": 1.724829077720642, "learning_rate": 0.00019298196948682386, "loss": 0.705353832244873, "step": 48700 }, { "epoch": 0.28954235545173007, "grad_norm": 1.1993707418441772, "learning_rate": 0.0001930215969883099, "loss": 0.7628102779388428, "step": 48710 }, { "epoch": 0.28960179752839843, "grad_norm": 2.051565647125244, "learning_rate": 0.00019306122448979593, "loss": 0.7163163661956787, "step": 48720 }, { "epoch": 0.28966123960506684, "grad_norm": 1.7913702726364136, "learning_rate": 0.00019310085199128197, "loss": 0.7125946998596191, "step": 48730 }, { "epoch": 0.28972068168173526, "grad_norm": 1.8353850841522217, "learning_rate": 0.00019314047949276798, "loss": 0.6900745868682862, "step": 48740 }, { "epoch": 0.2897801237584036, "grad_norm": 1.909277319908142, "learning_rate": 0.00019318010699425402, "loss": 0.6800741195678711, "step": 48750 }, { "epoch": 0.28983956583507203, "grad_norm": 1.4481805562973022, "learning_rate": 0.00019321973449574003, "loss": 0.6271799087524415, "step": 48760 }, { "epoch": 0.2898990079117404, "grad_norm": 2.333122968673706, "learning_rate": 0.00019325936199722607, "loss": 0.7300032615661621, "step": 48770 }, { "epoch": 0.2899584499884088, "grad_norm": 1.5416395664215088, "learning_rate": 0.0001932989894987121, "loss": 0.6646777629852295, "step": 48780 }, { "epoch": 0.29001789206507717, "grad_norm": 1.5269197225570679, "learning_rate": 0.00019333861700019815, "loss": 0.724449348449707, "step": 48790 }, { "epoch": 0.2900773341417456, "grad_norm": 1.9607775211334229, "learning_rate": 0.0001933782445016842, "loss": 0.7070672988891602, "step": 48800 }, { "epoch": 0.290136776218414, "grad_norm": 1.5276672840118408, "learning_rate": 0.0001934178720031702, "loss": 0.707745361328125, "step": 48810 }, { "epoch": 0.29019621829508235, "grad_norm": 1.9169542789459229, "learning_rate": 0.00019345749950465624, "loss": 0.6744617462158203, "step": 48820 }, { "epoch": 0.29025566037175077, "grad_norm": 1.7589443922042847, "learning_rate": 0.00019349712700614228, "loss": 0.6758980274200439, "step": 48830 }, { "epoch": 0.2903151024484191, "grad_norm": 1.4229779243469238, "learning_rate": 0.0001935367545076283, "loss": 0.681651258468628, "step": 48840 }, { "epoch": 0.29037454452508754, "grad_norm": 1.3838953971862793, "learning_rate": 0.00019357638200911436, "loss": 0.6785056114196777, "step": 48850 }, { "epoch": 0.2904339866017559, "grad_norm": 1.6785403490066528, "learning_rate": 0.00019361600951060037, "loss": 0.7782604217529296, "step": 48860 }, { "epoch": 0.2904934286784243, "grad_norm": 2.013432502746582, "learning_rate": 0.0001936556370120864, "loss": 0.7103988647460937, "step": 48870 }, { "epoch": 0.2905528707550927, "grad_norm": 1.626067042350769, "learning_rate": 0.00019369526451357242, "loss": 0.6874613761901855, "step": 48880 }, { "epoch": 0.2906123128317611, "grad_norm": 2.184272289276123, "learning_rate": 0.00019373489201505846, "loss": 0.7557723999023438, "step": 48890 }, { "epoch": 0.2906717549084295, "grad_norm": 1.5820308923721313, "learning_rate": 0.0001937745195165445, "loss": 0.6261175155639649, "step": 48900 }, { "epoch": 0.29073119698509786, "grad_norm": 1.6252344846725464, "learning_rate": 0.0001938141470180305, "loss": 0.6623785495758057, "step": 48910 }, { "epoch": 0.2907906390617663, "grad_norm": 1.4113267660140991, "learning_rate": 0.00019385377451951657, "loss": 0.7059126853942871, "step": 48920 }, { "epoch": 0.29085008113843464, "grad_norm": 1.709499478340149, "learning_rate": 0.00019389340202100258, "loss": 0.6980922222137451, "step": 48930 }, { "epoch": 0.29090952321510305, "grad_norm": 1.6739705801010132, "learning_rate": 0.00019393302952248862, "loss": 0.6627499103546143, "step": 48940 }, { "epoch": 0.2909689652917714, "grad_norm": 2.0075979232788086, "learning_rate": 0.00019397265702397463, "loss": 0.7006636142730713, "step": 48950 }, { "epoch": 0.2910284073684398, "grad_norm": 1.5604116916656494, "learning_rate": 0.00019401228452546067, "loss": 0.7004680633544922, "step": 48960 }, { "epoch": 0.29108784944510824, "grad_norm": 1.8806864023208618, "learning_rate": 0.0001940519120269467, "loss": 0.6872617721557617, "step": 48970 }, { "epoch": 0.2911472915217766, "grad_norm": 1.8473395109176636, "learning_rate": 0.00019409153952843272, "loss": 0.6973759651184082, "step": 48980 }, { "epoch": 0.291206733598445, "grad_norm": 1.556380033493042, "learning_rate": 0.0001941311670299188, "loss": 0.6740268707275391, "step": 48990 }, { "epoch": 0.29126617567511337, "grad_norm": 1.6689386367797852, "learning_rate": 0.0001941707945314048, "loss": 0.6702999114990235, "step": 49000 }, { "epoch": 0.2913256177517818, "grad_norm": 1.551978588104248, "learning_rate": 0.00019421042203289084, "loss": 0.7068024635314941, "step": 49010 }, { "epoch": 0.29138505982845014, "grad_norm": 1.5653660297393799, "learning_rate": 0.00019425004953437688, "loss": 0.741205883026123, "step": 49020 }, { "epoch": 0.29144450190511856, "grad_norm": 1.5355585813522339, "learning_rate": 0.0001942896770358629, "loss": 0.6666193008422852, "step": 49030 }, { "epoch": 0.291503943981787, "grad_norm": 1.6482281684875488, "learning_rate": 0.00019432930453734893, "loss": 0.7723151683807373, "step": 49040 }, { "epoch": 0.29156338605845533, "grad_norm": 2.076338768005371, "learning_rate": 0.00019436893203883494, "loss": 0.6625430107116699, "step": 49050 }, { "epoch": 0.29162282813512375, "grad_norm": 1.5783517360687256, "learning_rate": 0.000194408559540321, "loss": 0.7314714908599853, "step": 49060 }, { "epoch": 0.2916822702117921, "grad_norm": 1.473517656326294, "learning_rate": 0.00019444818704180702, "loss": 0.6667265892028809, "step": 49070 }, { "epoch": 0.2917417122884605, "grad_norm": 1.8450847864151, "learning_rate": 0.00019448781454329305, "loss": 0.7058794975280762, "step": 49080 }, { "epoch": 0.2918011543651289, "grad_norm": 1.585281252861023, "learning_rate": 0.0001945274420447791, "loss": 0.7055896282196045, "step": 49090 }, { "epoch": 0.2918605964417973, "grad_norm": 1.8517686128616333, "learning_rate": 0.0001945670695462651, "loss": 0.6761744976043701, "step": 49100 }, { "epoch": 0.2919200385184657, "grad_norm": 1.7446619272232056, "learning_rate": 0.00019460669704775114, "loss": 0.6619263648986816, "step": 49110 }, { "epoch": 0.29197948059513407, "grad_norm": 1.7425276041030884, "learning_rate": 0.00019464632454923718, "loss": 0.6596889972686768, "step": 49120 }, { "epoch": 0.2920389226718025, "grad_norm": 1.6792829036712646, "learning_rate": 0.00019468595205072322, "loss": 0.7079023838043212, "step": 49130 }, { "epoch": 0.29209836474847084, "grad_norm": 1.770285725593567, "learning_rate": 0.00019472557955220926, "loss": 0.6827218055725097, "step": 49140 }, { "epoch": 0.29215780682513925, "grad_norm": 1.7158552408218384, "learning_rate": 0.00019476520705369527, "loss": 0.7104431629180908, "step": 49150 }, { "epoch": 0.2922172489018076, "grad_norm": 1.4721264839172363, "learning_rate": 0.0001948048345551813, "loss": 0.725278091430664, "step": 49160 }, { "epoch": 0.29227669097847603, "grad_norm": 1.6697784662246704, "learning_rate": 0.00019484446205666732, "loss": 0.6481553077697754, "step": 49170 }, { "epoch": 0.2923361330551444, "grad_norm": 1.9347538948059082, "learning_rate": 0.00019488408955815336, "loss": 0.7785493850708007, "step": 49180 }, { "epoch": 0.2923955751318128, "grad_norm": 1.7685877084732056, "learning_rate": 0.0001949237170596394, "loss": 0.7410964965820312, "step": 49190 }, { "epoch": 0.2924550172084812, "grad_norm": 1.7867802381515503, "learning_rate": 0.00019496334456112544, "loss": 0.7481122493743897, "step": 49200 }, { "epoch": 0.2925144592851496, "grad_norm": 1.8103998899459839, "learning_rate": 0.00019500297206261148, "loss": 0.7198687076568604, "step": 49210 }, { "epoch": 0.292573901361818, "grad_norm": 1.6167540550231934, "learning_rate": 0.0001950425995640975, "loss": 0.6770156860351563, "step": 49220 }, { "epoch": 0.29263334343848635, "grad_norm": 2.0206615924835205, "learning_rate": 0.00019508222706558353, "loss": 0.7341130256652832, "step": 49230 }, { "epoch": 0.29269278551515476, "grad_norm": 2.368419647216797, "learning_rate": 0.00019512185456706954, "loss": 0.6277474403381348, "step": 49240 }, { "epoch": 0.2927522275918231, "grad_norm": 1.5352818965911865, "learning_rate": 0.00019516148206855558, "loss": 0.6290568351745606, "step": 49250 }, { "epoch": 0.29281166966849154, "grad_norm": 1.6650086641311646, "learning_rate": 0.00019520110957004164, "loss": 0.6888961791992188, "step": 49260 }, { "epoch": 0.29287111174515995, "grad_norm": 1.9414243698120117, "learning_rate": 0.00019524073707152765, "loss": 0.7218879699707031, "step": 49270 }, { "epoch": 0.2929305538218283, "grad_norm": 1.926801323890686, "learning_rate": 0.0001952803645730137, "loss": 0.7009387016296387, "step": 49280 }, { "epoch": 0.2929899958984967, "grad_norm": 1.4461098909378052, "learning_rate": 0.0001953199920744997, "loss": 0.6818903923034668, "step": 49290 }, { "epoch": 0.2930494379751651, "grad_norm": 1.9559450149536133, "learning_rate": 0.00019535961957598574, "loss": 0.7536057472229004, "step": 49300 }, { "epoch": 0.2931088800518335, "grad_norm": 1.557722806930542, "learning_rate": 0.00019539924707747178, "loss": 0.6487031936645508, "step": 49310 }, { "epoch": 0.29316832212850186, "grad_norm": 1.720194935798645, "learning_rate": 0.0001954388745789578, "loss": 0.7502249240875244, "step": 49320 }, { "epoch": 0.29322776420517027, "grad_norm": 1.7010643482208252, "learning_rate": 0.00019547850208044386, "loss": 0.693420124053955, "step": 49330 }, { "epoch": 0.2932872062818387, "grad_norm": 2.0143723487854004, "learning_rate": 0.00019551812958192987, "loss": 0.6813072204589844, "step": 49340 }, { "epoch": 0.29334664835850705, "grad_norm": 1.5468729734420776, "learning_rate": 0.0001955577570834159, "loss": 0.6592838287353515, "step": 49350 }, { "epoch": 0.29340609043517546, "grad_norm": 1.426659345626831, "learning_rate": 0.00019559738458490192, "loss": 0.7072247982025146, "step": 49360 }, { "epoch": 0.2934655325118438, "grad_norm": 1.9123247861862183, "learning_rate": 0.00019563701208638796, "loss": 0.6958245277404785, "step": 49370 }, { "epoch": 0.29352497458851223, "grad_norm": 1.654369831085205, "learning_rate": 0.000195676639587874, "loss": 0.7769193649291992, "step": 49380 }, { "epoch": 0.2935844166651806, "grad_norm": 1.6508835554122925, "learning_rate": 0.00019571626708936, "loss": 0.6922200202941895, "step": 49390 }, { "epoch": 0.293643858741849, "grad_norm": 2.3524203300476074, "learning_rate": 0.00019575589459084607, "loss": 0.6645060539245605, "step": 49400 }, { "epoch": 0.2937033008185174, "grad_norm": 1.8956260681152344, "learning_rate": 0.00019579552209233209, "loss": 0.7228740692138672, "step": 49410 }, { "epoch": 0.2937627428951858, "grad_norm": 1.6365145444869995, "learning_rate": 0.00019583514959381812, "loss": 0.7695142745971679, "step": 49420 }, { "epoch": 0.2938221849718542, "grad_norm": 2.1699514389038086, "learning_rate": 0.00019587477709530416, "loss": 0.6038793563842774, "step": 49430 }, { "epoch": 0.29388162704852255, "grad_norm": 1.4171277284622192, "learning_rate": 0.00019591440459679018, "loss": 0.651178503036499, "step": 49440 }, { "epoch": 0.29394106912519097, "grad_norm": 1.5341438055038452, "learning_rate": 0.00019595403209827621, "loss": 0.6087442398071289, "step": 49450 }, { "epoch": 0.2940005112018593, "grad_norm": 1.6238218545913696, "learning_rate": 0.00019599365959976223, "loss": 0.7155411720275879, "step": 49460 }, { "epoch": 0.29405995327852774, "grad_norm": 1.7840065956115723, "learning_rate": 0.0001960332871012483, "loss": 0.7491075992584229, "step": 49470 }, { "epoch": 0.29411939535519616, "grad_norm": 1.644991397857666, "learning_rate": 0.0001960729146027343, "loss": 0.7040335655212402, "step": 49480 }, { "epoch": 0.2941788374318645, "grad_norm": 2.0451788902282715, "learning_rate": 0.00019611254210422034, "loss": 0.7217905998229981, "step": 49490 }, { "epoch": 0.29423827950853293, "grad_norm": 1.455575704574585, "learning_rate": 0.00019615216960570638, "loss": 0.6849404335021972, "step": 49500 }, { "epoch": 0.2942977215852013, "grad_norm": 1.8632105588912964, "learning_rate": 0.0001961917971071924, "loss": 0.7185763359069824, "step": 49510 }, { "epoch": 0.2943571636618697, "grad_norm": 1.6535449028015137, "learning_rate": 0.00019623142460867843, "loss": 0.6925217151641846, "step": 49520 }, { "epoch": 0.29441660573853806, "grad_norm": 2.2250890731811523, "learning_rate": 0.00019627105211016444, "loss": 0.7501680850982666, "step": 49530 }, { "epoch": 0.2944760478152065, "grad_norm": 1.5019605159759521, "learning_rate": 0.0001963106796116505, "loss": 0.6950196743011474, "step": 49540 }, { "epoch": 0.29453548989187484, "grad_norm": 1.7725822925567627, "learning_rate": 0.00019635030711313655, "loss": 0.691956901550293, "step": 49550 }, { "epoch": 0.29459493196854325, "grad_norm": 2.05267333984375, "learning_rate": 0.00019638993461462256, "loss": 0.739510440826416, "step": 49560 }, { "epoch": 0.29465437404521166, "grad_norm": 1.2848163843154907, "learning_rate": 0.0001964295621161086, "loss": 0.6594025135040283, "step": 49570 }, { "epoch": 0.29471381612188, "grad_norm": 1.7671747207641602, "learning_rate": 0.0001964691896175946, "loss": 0.6682142734527587, "step": 49580 }, { "epoch": 0.29477325819854844, "grad_norm": 1.6978709697723389, "learning_rate": 0.00019650881711908065, "loss": 0.6732125282287598, "step": 49590 }, { "epoch": 0.2948327002752168, "grad_norm": 2.144383192062378, "learning_rate": 0.00019654844462056669, "loss": 0.7228781700134277, "step": 49600 }, { "epoch": 0.2948921423518852, "grad_norm": 1.7063798904418945, "learning_rate": 0.00019658807212205272, "loss": 0.7008060455322266, "step": 49610 }, { "epoch": 0.29495158442855357, "grad_norm": 1.7824127674102783, "learning_rate": 0.00019662769962353876, "loss": 0.6750507354736328, "step": 49620 }, { "epoch": 0.295011026505222, "grad_norm": 1.7487891912460327, "learning_rate": 0.00019666732712502477, "loss": 0.6945492267608643, "step": 49630 }, { "epoch": 0.2950704685818904, "grad_norm": 1.6104382276535034, "learning_rate": 0.0001967069546265108, "loss": 0.7138665676116943, "step": 49640 }, { "epoch": 0.29512991065855876, "grad_norm": 1.9597033262252808, "learning_rate": 0.00019674658212799682, "loss": 0.6742196083068848, "step": 49650 }, { "epoch": 0.2951893527352272, "grad_norm": 1.7644718885421753, "learning_rate": 0.00019678620962948286, "loss": 0.724347448348999, "step": 49660 }, { "epoch": 0.29524879481189553, "grad_norm": 2.4239134788513184, "learning_rate": 0.0001968258371309689, "loss": 0.6994441032409668, "step": 49670 }, { "epoch": 0.29530823688856395, "grad_norm": 1.5865815877914429, "learning_rate": 0.00019686546463245494, "loss": 0.6802265167236328, "step": 49680 }, { "epoch": 0.2953676789652323, "grad_norm": 2.0772109031677246, "learning_rate": 0.00019690509213394098, "loss": 0.6792362213134766, "step": 49690 }, { "epoch": 0.2954271210419007, "grad_norm": 1.830549716949463, "learning_rate": 0.000196944719635427, "loss": 0.7169669151306153, "step": 49700 }, { "epoch": 0.29548656311856913, "grad_norm": 2.1602203845977783, "learning_rate": 0.00019698434713691303, "loss": 0.6924139976501464, "step": 49710 }, { "epoch": 0.2955460051952375, "grad_norm": 1.6988881826400757, "learning_rate": 0.00019702397463839907, "loss": 0.7261430740356445, "step": 49720 }, { "epoch": 0.2956054472719059, "grad_norm": 1.7562333345413208, "learning_rate": 0.00019706360213988508, "loss": 0.6680427551269531, "step": 49730 }, { "epoch": 0.29566488934857427, "grad_norm": 1.8043076992034912, "learning_rate": 0.00019710322964137112, "loss": 0.6988729476928711, "step": 49740 }, { "epoch": 0.2957243314252427, "grad_norm": 1.6640937328338623, "learning_rate": 0.00019714285714285716, "loss": 0.672775411605835, "step": 49750 }, { "epoch": 0.29578377350191104, "grad_norm": 1.425132155418396, "learning_rate": 0.0001971824846443432, "loss": 0.6737427711486816, "step": 49760 }, { "epoch": 0.29584321557857945, "grad_norm": 1.6204876899719238, "learning_rate": 0.0001972221121458292, "loss": 0.7493748188018798, "step": 49770 }, { "epoch": 0.29590265765524787, "grad_norm": 1.59686279296875, "learning_rate": 0.00019726173964731525, "loss": 0.6507853507995606, "step": 49780 }, { "epoch": 0.29596209973191623, "grad_norm": 1.5756806135177612, "learning_rate": 0.00019730136714880128, "loss": 0.7293689250946045, "step": 49790 }, { "epoch": 0.29602154180858464, "grad_norm": 2.030601739883423, "learning_rate": 0.0001973409946502873, "loss": 0.7107817649841308, "step": 49800 }, { "epoch": 0.296080983885253, "grad_norm": 1.6795623302459717, "learning_rate": 0.00019738062215177333, "loss": 0.7097079277038574, "step": 49810 }, { "epoch": 0.2961404259619214, "grad_norm": 1.6684776544570923, "learning_rate": 0.00019742024965325937, "loss": 0.7342201232910156, "step": 49820 }, { "epoch": 0.2961998680385898, "grad_norm": 1.898082971572876, "learning_rate": 0.0001974598771547454, "loss": 0.6827750682830811, "step": 49830 }, { "epoch": 0.2962593101152582, "grad_norm": 1.887345790863037, "learning_rate": 0.00019749950465623145, "loss": 0.6240623474121094, "step": 49840 }, { "epoch": 0.2963187521919266, "grad_norm": 1.5916175842285156, "learning_rate": 0.00019753913215771746, "loss": 0.6695693016052247, "step": 49850 }, { "epoch": 0.29637819426859496, "grad_norm": 1.617063045501709, "learning_rate": 0.0001975787596592035, "loss": 0.7101715087890625, "step": 49860 }, { "epoch": 0.2964376363452634, "grad_norm": 1.8111212253570557, "learning_rate": 0.0001976183871606895, "loss": 0.7142922401428222, "step": 49870 }, { "epoch": 0.29649707842193174, "grad_norm": 2.0965325832366943, "learning_rate": 0.00019765801466217555, "loss": 0.7246270179748535, "step": 49880 }, { "epoch": 0.29655652049860015, "grad_norm": 1.7323516607284546, "learning_rate": 0.0001976976421636616, "loss": 0.714589786529541, "step": 49890 }, { "epoch": 0.2966159625752685, "grad_norm": 1.8042677640914917, "learning_rate": 0.00019773726966514763, "loss": 0.660371208190918, "step": 49900 }, { "epoch": 0.2966754046519369, "grad_norm": 1.7353596687316895, "learning_rate": 0.00019777689716663367, "loss": 0.7355391979217529, "step": 49910 }, { "epoch": 0.2967348467286053, "grad_norm": 1.9243414402008057, "learning_rate": 0.00019781652466811968, "loss": 0.7431266784667969, "step": 49920 }, { "epoch": 0.2967942888052737, "grad_norm": 1.9485803842544556, "learning_rate": 0.00019785615216960572, "loss": 0.7388820648193359, "step": 49930 }, { "epoch": 0.2968537308819421, "grad_norm": 1.7812905311584473, "learning_rate": 0.00019789577967109173, "loss": 0.6501158714294434, "step": 49940 }, { "epoch": 0.29691317295861047, "grad_norm": 1.8624582290649414, "learning_rate": 0.00019793540717257777, "loss": 0.6815829277038574, "step": 49950 }, { "epoch": 0.2969726150352789, "grad_norm": 1.738628625869751, "learning_rate": 0.00019797503467406383, "loss": 0.6787497520446777, "step": 49960 }, { "epoch": 0.29703205711194725, "grad_norm": 2.2715282440185547, "learning_rate": 0.00019801466217554984, "loss": 0.7009382247924805, "step": 49970 }, { "epoch": 0.29709149918861566, "grad_norm": 1.633265495300293, "learning_rate": 0.00019805428967703588, "loss": 0.7004540920257568, "step": 49980 }, { "epoch": 0.297150941265284, "grad_norm": 1.6656030416488647, "learning_rate": 0.0001980939171785219, "loss": 0.6612516403198242, "step": 49990 }, { "epoch": 0.29721038334195243, "grad_norm": 2.0530855655670166, "learning_rate": 0.00019813354468000793, "loss": 0.6883889198303222, "step": 50000 }, { "epoch": 0.29726982541862085, "grad_norm": 1.4135942459106445, "learning_rate": 0.00019817317218149397, "loss": 0.659427261352539, "step": 50010 }, { "epoch": 0.2973292674952892, "grad_norm": 1.6590067148208618, "learning_rate": 0.00019821279968297998, "loss": 0.7495773792266845, "step": 50020 }, { "epoch": 0.2973887095719576, "grad_norm": 1.5115646123886108, "learning_rate": 0.00019825242718446605, "loss": 0.6462380886077881, "step": 50030 }, { "epoch": 0.297448151648626, "grad_norm": 1.586195945739746, "learning_rate": 0.00019829205468595206, "loss": 0.691756296157837, "step": 50040 }, { "epoch": 0.2975075937252944, "grad_norm": 1.4220173358917236, "learning_rate": 0.0001983316821874381, "loss": 0.6817449569702149, "step": 50050 }, { "epoch": 0.29756703580196275, "grad_norm": 1.680593729019165, "learning_rate": 0.0001983713096889241, "loss": 0.6763222694396973, "step": 50060 }, { "epoch": 0.29762647787863117, "grad_norm": 1.768674612045288, "learning_rate": 0.00019841093719041015, "loss": 0.694786548614502, "step": 50070 }, { "epoch": 0.2976859199552996, "grad_norm": 1.8992165327072144, "learning_rate": 0.0001984505646918962, "loss": 0.6826753616333008, "step": 50080 }, { "epoch": 0.29774536203196794, "grad_norm": 1.779624104499817, "learning_rate": 0.0001984901921933822, "loss": 0.6663032531738281, "step": 50090 }, { "epoch": 0.29780480410863636, "grad_norm": 1.427635908126831, "learning_rate": 0.00019852981969486827, "loss": 0.6905242443084717, "step": 50100 }, { "epoch": 0.2978642461853047, "grad_norm": 1.821982979774475, "learning_rate": 0.00019856944719635428, "loss": 0.681124210357666, "step": 50110 }, { "epoch": 0.29792368826197313, "grad_norm": 1.9873441457748413, "learning_rate": 0.00019860907469784032, "loss": 0.7043239116668701, "step": 50120 }, { "epoch": 0.2979831303386415, "grad_norm": 2.1437454223632812, "learning_rate": 0.00019864870219932635, "loss": 0.7696401119232178, "step": 50130 }, { "epoch": 0.2980425724153099, "grad_norm": 1.6943708658218384, "learning_rate": 0.00019868832970081237, "loss": 0.7843869686126709, "step": 50140 }, { "epoch": 0.2981020144919783, "grad_norm": 1.5024868249893188, "learning_rate": 0.0001987279572022984, "loss": 0.717256736755371, "step": 50150 }, { "epoch": 0.2981614565686467, "grad_norm": 1.6056164503097534, "learning_rate": 0.00019876758470378442, "loss": 0.6739222049713135, "step": 50160 }, { "epoch": 0.2982208986453151, "grad_norm": 2.0442841053009033, "learning_rate": 0.00019880721220527048, "loss": 0.7385945320129395, "step": 50170 }, { "epoch": 0.29828034072198345, "grad_norm": 1.6415258646011353, "learning_rate": 0.0001988468397067565, "loss": 0.7382038116455079, "step": 50180 }, { "epoch": 0.29833978279865186, "grad_norm": 1.8109992742538452, "learning_rate": 0.00019888646720824253, "loss": 0.7063825130462646, "step": 50190 }, { "epoch": 0.2983992248753202, "grad_norm": 2.338120937347412, "learning_rate": 0.00019892609470972857, "loss": 0.6713316440582275, "step": 50200 }, { "epoch": 0.29845866695198864, "grad_norm": 2.0026092529296875, "learning_rate": 0.00019896572221121458, "loss": 0.6521175384521485, "step": 50210 }, { "epoch": 0.29851810902865705, "grad_norm": 1.345005989074707, "learning_rate": 0.00019900534971270062, "loss": 0.635247802734375, "step": 50220 }, { "epoch": 0.2985775511053254, "grad_norm": 1.7791646718978882, "learning_rate": 0.00019904497721418663, "loss": 0.6875581741333008, "step": 50230 }, { "epoch": 0.2986369931819938, "grad_norm": 1.813259482383728, "learning_rate": 0.0001990846047156727, "loss": 0.6581868648529052, "step": 50240 }, { "epoch": 0.2986964352586622, "grad_norm": 1.4422988891601562, "learning_rate": 0.00019912423221715874, "loss": 0.6740331649780273, "step": 50250 }, { "epoch": 0.2987558773353306, "grad_norm": 1.8883235454559326, "learning_rate": 0.00019916385971864475, "loss": 0.6861428260803223, "step": 50260 }, { "epoch": 0.29881531941199896, "grad_norm": 1.39031982421875, "learning_rate": 0.0001992034872201308, "loss": 0.7016839027404785, "step": 50270 }, { "epoch": 0.2988747614886674, "grad_norm": 2.0665905475616455, "learning_rate": 0.0001992431147216168, "loss": 0.7126128673553467, "step": 50280 }, { "epoch": 0.29893420356533573, "grad_norm": 1.6415122747421265, "learning_rate": 0.00019928274222310284, "loss": 0.7203169822692871, "step": 50290 }, { "epoch": 0.29899364564200415, "grad_norm": 1.5800118446350098, "learning_rate": 0.00019932236972458888, "loss": 0.6645450592041016, "step": 50300 }, { "epoch": 0.29905308771867256, "grad_norm": 2.203589916229248, "learning_rate": 0.00019936199722607491, "loss": 0.6882546424865723, "step": 50310 }, { "epoch": 0.2991125297953409, "grad_norm": 1.5696812868118286, "learning_rate": 0.00019940162472756095, "loss": 0.6653067588806152, "step": 50320 }, { "epoch": 0.29917197187200933, "grad_norm": 1.6936795711517334, "learning_rate": 0.00019944125222904696, "loss": 0.6874100685119628, "step": 50330 }, { "epoch": 0.2992314139486777, "grad_norm": 1.7642884254455566, "learning_rate": 0.000199480879730533, "loss": 0.6701135635375977, "step": 50340 }, { "epoch": 0.2992908560253461, "grad_norm": 1.4489107131958008, "learning_rate": 0.00019952050723201902, "loss": 0.7221609115600586, "step": 50350 }, { "epoch": 0.29935029810201447, "grad_norm": 2.0842785835266113, "learning_rate": 0.00019956013473350505, "loss": 0.6927023887634277, "step": 50360 }, { "epoch": 0.2994097401786829, "grad_norm": 1.8994656801223755, "learning_rate": 0.0001995997622349911, "loss": 0.7025599479675293, "step": 50370 }, { "epoch": 0.2994691822553513, "grad_norm": 1.8909412622451782, "learning_rate": 0.00019963938973647713, "loss": 0.724979019165039, "step": 50380 }, { "epoch": 0.29952862433201966, "grad_norm": 1.8105494976043701, "learning_rate": 0.00019967901723796317, "loss": 0.6636269569396973, "step": 50390 }, { "epoch": 0.29958806640868807, "grad_norm": 1.4590564966201782, "learning_rate": 0.00019971864473944918, "loss": 0.6524813175201416, "step": 50400 }, { "epoch": 0.29964750848535643, "grad_norm": 1.61411714553833, "learning_rate": 0.00019975827224093522, "loss": 0.7067809104919434, "step": 50410 }, { "epoch": 0.29970695056202484, "grad_norm": 1.850650429725647, "learning_rate": 0.00019979789974242126, "loss": 0.6616540431976319, "step": 50420 }, { "epoch": 0.2997663926386932, "grad_norm": 1.6996631622314453, "learning_rate": 0.00019983752724390727, "loss": 0.7038271427154541, "step": 50430 }, { "epoch": 0.2998258347153616, "grad_norm": 1.7611578702926636, "learning_rate": 0.0001998771547453933, "loss": 0.6830703735351562, "step": 50440 }, { "epoch": 0.29988527679203003, "grad_norm": 1.7674858570098877, "learning_rate": 0.00019991678224687935, "loss": 0.7460942268371582, "step": 50450 }, { "epoch": 0.2999447188686984, "grad_norm": 2.2155354022979736, "learning_rate": 0.00019995640974836539, "loss": 0.6493790626525879, "step": 50460 }, { "epoch": 0.3000041609453668, "grad_norm": 1.75800359249115, "learning_rate": 0.0001999960372498514, "loss": 0.66549711227417, "step": 50470 }, { "epoch": 0.30006360302203516, "grad_norm": 1.6758633852005005, "learning_rate": 0.00019999999982563512, "loss": 0.6587043285369873, "step": 50480 }, { "epoch": 0.3001230450987036, "grad_norm": 1.5873212814331055, "learning_rate": 0.00019999999922289233, "loss": 0.7257075309753418, "step": 50490 }, { "epoch": 0.30018248717537194, "grad_norm": 1.966292142868042, "learning_rate": 0.00019999999818961887, "loss": 0.7428311347961426, "step": 50500 }, { "epoch": 0.30024192925204035, "grad_norm": 1.65130615234375, "learning_rate": 0.00019999999672581491, "loss": 0.6973207473754883, "step": 50510 }, { "epoch": 0.30030137132870877, "grad_norm": 1.6338777542114258, "learning_rate": 0.00019999999483148034, "loss": 0.6623695850372314, "step": 50520 }, { "epoch": 0.3003608134053771, "grad_norm": 1.4713257551193237, "learning_rate": 0.00019999999250661522, "loss": 0.7161155700683594, "step": 50530 }, { "epoch": 0.30042025548204554, "grad_norm": 1.717118501663208, "learning_rate": 0.00019999998975121956, "loss": 0.7098333835601807, "step": 50540 }, { "epoch": 0.3004796975587139, "grad_norm": 1.8350754976272583, "learning_rate": 0.00019999998656529335, "loss": 0.7369086742401123, "step": 50550 }, { "epoch": 0.3005391396353823, "grad_norm": 1.4950637817382812, "learning_rate": 0.0001999999829488366, "loss": 0.6994259834289551, "step": 50560 }, { "epoch": 0.30059858171205067, "grad_norm": 1.7386454343795776, "learning_rate": 0.00019999997890184939, "loss": 0.6713947296142578, "step": 50570 }, { "epoch": 0.3006580237887191, "grad_norm": 1.8200119733810425, "learning_rate": 0.00019999997442433164, "loss": 0.6754142761230468, "step": 50580 }, { "epoch": 0.30071746586538745, "grad_norm": 1.6222331523895264, "learning_rate": 0.00019999996951628347, "loss": 0.6845356941223144, "step": 50590 }, { "epoch": 0.30077690794205586, "grad_norm": 1.5985106229782104, "learning_rate": 0.00019999996417770482, "loss": 0.7036702156066894, "step": 50600 }, { "epoch": 0.3008363500187243, "grad_norm": 1.9159578084945679, "learning_rate": 0.00019999995840859578, "loss": 0.6936814308166503, "step": 50610 }, { "epoch": 0.30089579209539263, "grad_norm": 1.979634404182434, "learning_rate": 0.00019999995220895634, "loss": 0.7178810119628907, "step": 50620 }, { "epoch": 0.30095523417206105, "grad_norm": 1.6301487684249878, "learning_rate": 0.00019999994557878654, "loss": 0.7347780704498291, "step": 50630 }, { "epoch": 0.3010146762487294, "grad_norm": 1.5750281810760498, "learning_rate": 0.0001999999385180864, "loss": 0.7683308601379395, "step": 50640 }, { "epoch": 0.3010741183253978, "grad_norm": 1.676130771636963, "learning_rate": 0.000199999931026856, "loss": 0.6578267097473145, "step": 50650 }, { "epoch": 0.3011335604020662, "grad_norm": 2.1107254028320312, "learning_rate": 0.0001999999231050953, "loss": 0.6559926033020019, "step": 50660 }, { "epoch": 0.3011930024787346, "grad_norm": 1.1828126907348633, "learning_rate": 0.00019999991475280442, "loss": 0.7376805782318115, "step": 50670 }, { "epoch": 0.301252444555403, "grad_norm": 1.7804312705993652, "learning_rate": 0.00019999990596998335, "loss": 0.6947402000427246, "step": 50680 }, { "epoch": 0.30131188663207137, "grad_norm": 1.505358338356018, "learning_rate": 0.00019999989675663213, "loss": 0.737179183959961, "step": 50690 }, { "epoch": 0.3013713287087398, "grad_norm": 1.6520105600357056, "learning_rate": 0.00019999988711275082, "loss": 0.7104733943939209, "step": 50700 }, { "epoch": 0.30143077078540814, "grad_norm": 1.8052902221679688, "learning_rate": 0.00019999987703833946, "loss": 0.7150388240814209, "step": 50710 }, { "epoch": 0.30149021286207656, "grad_norm": 2.177931547164917, "learning_rate": 0.00019999986653339812, "loss": 0.7708693504333496, "step": 50720 }, { "epoch": 0.3015496549387449, "grad_norm": 1.4634885787963867, "learning_rate": 0.0001999998555979268, "loss": 0.6578948020935058, "step": 50730 }, { "epoch": 0.30160909701541333, "grad_norm": 2.085298538208008, "learning_rate": 0.00019999984423192563, "loss": 0.7243633270263672, "step": 50740 }, { "epoch": 0.30166853909208174, "grad_norm": 1.9753419160842896, "learning_rate": 0.00019999983243539456, "loss": 0.6925868034362793, "step": 50750 }, { "epoch": 0.3017279811687501, "grad_norm": 1.9291839599609375, "learning_rate": 0.00019999982020833375, "loss": 0.7187341690063477, "step": 50760 }, { "epoch": 0.3017874232454185, "grad_norm": 1.705704927444458, "learning_rate": 0.00019999980755074318, "loss": 0.6752307891845704, "step": 50770 }, { "epoch": 0.3018468653220869, "grad_norm": 2.782693386077881, "learning_rate": 0.00019999979446262296, "loss": 0.668839979171753, "step": 50780 }, { "epoch": 0.3019063073987553, "grad_norm": 2.1953437328338623, "learning_rate": 0.00019999978094397314, "loss": 0.6154732704162598, "step": 50790 }, { "epoch": 0.30196574947542365, "grad_norm": 1.825256586074829, "learning_rate": 0.00019999976699479376, "loss": 0.703797721862793, "step": 50800 }, { "epoch": 0.30202519155209206, "grad_norm": 1.8464950323104858, "learning_rate": 0.0001999997526150849, "loss": 0.7750667095184326, "step": 50810 }, { "epoch": 0.3020846336287605, "grad_norm": 1.2797894477844238, "learning_rate": 0.00019999973780484667, "loss": 0.7004805564880371, "step": 50820 }, { "epoch": 0.30214407570542884, "grad_norm": 1.3384844064712524, "learning_rate": 0.0001999997225640791, "loss": 0.6937238693237304, "step": 50830 }, { "epoch": 0.30220351778209725, "grad_norm": 1.3853946924209595, "learning_rate": 0.00019999970689278223, "loss": 0.7443911075592041, "step": 50840 }, { "epoch": 0.3022629598587656, "grad_norm": 1.6267341375350952, "learning_rate": 0.00019999969079095622, "loss": 0.6642082214355469, "step": 50850 }, { "epoch": 0.302322401935434, "grad_norm": 1.8474953174591064, "learning_rate": 0.00019999967425860107, "loss": 0.675766897201538, "step": 50860 }, { "epoch": 0.3023818440121024, "grad_norm": 1.4183080196380615, "learning_rate": 0.00019999965729571695, "loss": 0.7232781887054444, "step": 50870 }, { "epoch": 0.3024412860887708, "grad_norm": 1.4113247394561768, "learning_rate": 0.00019999963990230383, "loss": 0.6705416679382324, "step": 50880 }, { "epoch": 0.3025007281654392, "grad_norm": 1.5908050537109375, "learning_rate": 0.00019999962207836183, "loss": 0.6316706657409668, "step": 50890 }, { "epoch": 0.3025601702421076, "grad_norm": 1.592395305633545, "learning_rate": 0.00019999960382389108, "loss": 0.6695714950561523, "step": 50900 }, { "epoch": 0.302619612318776, "grad_norm": 1.5562924146652222, "learning_rate": 0.00019999958513889163, "loss": 0.6895445346832275, "step": 50910 }, { "epoch": 0.30267905439544435, "grad_norm": 2.401668071746826, "learning_rate": 0.0001999995660233636, "loss": 0.6657169342041016, "step": 50920 }, { "epoch": 0.30273849647211276, "grad_norm": 1.7959377765655518, "learning_rate": 0.000199999546477307, "loss": 0.7895051956176757, "step": 50930 }, { "epoch": 0.3027979385487811, "grad_norm": 1.9927729368209839, "learning_rate": 0.00019999952650072203, "loss": 0.7022140502929688, "step": 50940 }, { "epoch": 0.30285738062544953, "grad_norm": 1.9870069026947021, "learning_rate": 0.00019999950609360872, "loss": 0.6980654716491699, "step": 50950 }, { "epoch": 0.3029168227021179, "grad_norm": 1.789917230606079, "learning_rate": 0.0001999994852559672, "loss": 0.7048959255218505, "step": 50960 }, { "epoch": 0.3029762647787863, "grad_norm": 1.741859793663025, "learning_rate": 0.00019999946398779753, "loss": 0.7345775127410888, "step": 50970 }, { "epoch": 0.3030357068554547, "grad_norm": 2.6016664505004883, "learning_rate": 0.00019999944228909987, "loss": 0.7295015335083008, "step": 50980 }, { "epoch": 0.3030951489321231, "grad_norm": 1.7055572271347046, "learning_rate": 0.00019999942015987425, "loss": 0.7231490135192871, "step": 50990 }, { "epoch": 0.3031545910087915, "grad_norm": 1.533709168434143, "learning_rate": 0.00019999939760012084, "loss": 0.6818443775177002, "step": 51000 }, { "epoch": 0.30321403308545986, "grad_norm": 1.7923752069473267, "learning_rate": 0.00019999937460983975, "loss": 0.6899938583374023, "step": 51010 }, { "epoch": 0.30327347516212827, "grad_norm": 1.668391227722168, "learning_rate": 0.000199999351189031, "loss": 0.673342227935791, "step": 51020 }, { "epoch": 0.30333291723879663, "grad_norm": 1.9066994190216064, "learning_rate": 0.00019999932733769484, "loss": 0.7101531982421875, "step": 51030 }, { "epoch": 0.30339235931546504, "grad_norm": 2.269578456878662, "learning_rate": 0.00019999930305583126, "loss": 0.6853354454040528, "step": 51040 }, { "epoch": 0.30345180139213346, "grad_norm": 1.3743888139724731, "learning_rate": 0.00019999927834344044, "loss": 0.6682356834411621, "step": 51050 }, { "epoch": 0.3035112434688018, "grad_norm": 1.8065903186798096, "learning_rate": 0.00019999925320052247, "loss": 0.6144695281982422, "step": 51060 }, { "epoch": 0.30357068554547023, "grad_norm": 1.7869747877120972, "learning_rate": 0.0001999992276270775, "loss": 0.7099122047424317, "step": 51070 }, { "epoch": 0.3036301276221386, "grad_norm": 1.9788535833358765, "learning_rate": 0.00019999920162310566, "loss": 0.749225664138794, "step": 51080 }, { "epoch": 0.303689569698807, "grad_norm": 1.750057339668274, "learning_rate": 0.000199999175188607, "loss": 0.7400309085845947, "step": 51090 }, { "epoch": 0.30374901177547536, "grad_norm": 1.9266157150268555, "learning_rate": 0.00019999914832358174, "loss": 0.6751261711120605, "step": 51100 }, { "epoch": 0.3038084538521438, "grad_norm": 1.9735898971557617, "learning_rate": 0.00019999912102802993, "loss": 0.6858086585998535, "step": 51110 }, { "epoch": 0.3038678959288122, "grad_norm": 1.884308934211731, "learning_rate": 0.00019999909330195177, "loss": 0.6912939071655273, "step": 51120 }, { "epoch": 0.30392733800548055, "grad_norm": 1.7337909936904907, "learning_rate": 0.00019999906514534736, "loss": 0.6266424655914307, "step": 51130 }, { "epoch": 0.30398678008214897, "grad_norm": 2.002669334411621, "learning_rate": 0.00019999903655821682, "loss": 0.6832708835601806, "step": 51140 }, { "epoch": 0.3040462221588173, "grad_norm": 2.2836852073669434, "learning_rate": 0.0001999990075405603, "loss": 0.6959393978118896, "step": 51150 }, { "epoch": 0.30410566423548574, "grad_norm": 1.903662085533142, "learning_rate": 0.00019999897809237793, "loss": 0.6959205150604248, "step": 51160 }, { "epoch": 0.3041651063121541, "grad_norm": 1.5659664869308472, "learning_rate": 0.00019999894821366986, "loss": 0.7090581893920899, "step": 51170 }, { "epoch": 0.3042245483888225, "grad_norm": 1.991896152496338, "learning_rate": 0.00019999891790443625, "loss": 0.7352554798126221, "step": 51180 }, { "epoch": 0.30428399046549093, "grad_norm": 2.0546340942382812, "learning_rate": 0.00019999888716467723, "loss": 0.687968397140503, "step": 51190 }, { "epoch": 0.3043434325421593, "grad_norm": 1.9230189323425293, "learning_rate": 0.00019999885599439297, "loss": 0.7183806419372558, "step": 51200 }, { "epoch": 0.3044028746188277, "grad_norm": 1.7886457443237305, "learning_rate": 0.00019999882439358354, "loss": 0.7267765998840332, "step": 51210 }, { "epoch": 0.30446231669549606, "grad_norm": 1.8759074211120605, "learning_rate": 0.00019999879236224917, "loss": 0.6828104019165039, "step": 51220 }, { "epoch": 0.3045217587721645, "grad_norm": 1.3303381204605103, "learning_rate": 0.00019999875990039001, "loss": 0.7293292045593261, "step": 51230 }, { "epoch": 0.30458120084883283, "grad_norm": 1.5732662677764893, "learning_rate": 0.00019999872700800618, "loss": 0.6591920852661133, "step": 51240 }, { "epoch": 0.30464064292550125, "grad_norm": 2.067039728164673, "learning_rate": 0.00019999869368509784, "loss": 0.6893464088439941, "step": 51250 }, { "epoch": 0.30470008500216966, "grad_norm": 1.8223575353622437, "learning_rate": 0.00019999865993166515, "loss": 0.7399222373962402, "step": 51260 }, { "epoch": 0.304759527078838, "grad_norm": 1.7440063953399658, "learning_rate": 0.00019999862574770835, "loss": 0.7310730934143066, "step": 51270 }, { "epoch": 0.30481896915550644, "grad_norm": 1.666857361793518, "learning_rate": 0.00019999859113322744, "loss": 0.7049406051635743, "step": 51280 }, { "epoch": 0.3048784112321748, "grad_norm": 1.6961311101913452, "learning_rate": 0.00019999855608822276, "loss": 0.7646964073181153, "step": 51290 }, { "epoch": 0.3049378533088432, "grad_norm": 1.9015636444091797, "learning_rate": 0.00019999852061269434, "loss": 0.720643424987793, "step": 51300 }, { "epoch": 0.30499729538551157, "grad_norm": 2.467702627182007, "learning_rate": 0.00019999848470664248, "loss": 0.6907981872558594, "step": 51310 }, { "epoch": 0.30505673746218, "grad_norm": 1.999926209449768, "learning_rate": 0.00019999844837006723, "loss": 0.6832322120666504, "step": 51320 }, { "epoch": 0.30511617953884834, "grad_norm": 1.832701563835144, "learning_rate": 0.0001999984116029688, "loss": 0.7441417217254639, "step": 51330 }, { "epoch": 0.30517562161551676, "grad_norm": 1.6175172328948975, "learning_rate": 0.00019999837440534742, "loss": 0.6758084297180176, "step": 51340 }, { "epoch": 0.30523506369218517, "grad_norm": 2.0834567546844482, "learning_rate": 0.00019999833677720322, "loss": 0.7045432090759277, "step": 51350 }, { "epoch": 0.30529450576885353, "grad_norm": 1.344174861907959, "learning_rate": 0.0001999982987185364, "loss": 0.7164155960083007, "step": 51360 }, { "epoch": 0.30535394784552194, "grad_norm": 1.8196864128112793, "learning_rate": 0.00019999826022934708, "loss": 0.7102686405181885, "step": 51370 }, { "epoch": 0.3054133899221903, "grad_norm": 1.6564489603042603, "learning_rate": 0.00019999822130963553, "loss": 0.6984230041503906, "step": 51380 }, { "epoch": 0.3054728319988587, "grad_norm": 1.5842342376708984, "learning_rate": 0.0001999981819594019, "loss": 0.7303370475769043, "step": 51390 }, { "epoch": 0.3055322740755271, "grad_norm": 1.6626546382904053, "learning_rate": 0.00019999814217864636, "loss": 0.6667554378509521, "step": 51400 }, { "epoch": 0.3055917161521955, "grad_norm": 1.4198685884475708, "learning_rate": 0.00019999810196736918, "loss": 0.6664159774780274, "step": 51410 }, { "epoch": 0.3056511582288639, "grad_norm": 1.7999733686447144, "learning_rate": 0.00019999806132557044, "loss": 0.7529605388641357, "step": 51420 }, { "epoch": 0.30571060030553227, "grad_norm": 1.803404688835144, "learning_rate": 0.0001999980202532504, "loss": 0.6859247207641601, "step": 51430 }, { "epoch": 0.3057700423822007, "grad_norm": 1.7340868711471558, "learning_rate": 0.00019999797875040921, "loss": 0.691689395904541, "step": 51440 }, { "epoch": 0.30582948445886904, "grad_norm": 1.5463565587997437, "learning_rate": 0.00019999793681704718, "loss": 0.7005374908447266, "step": 51450 }, { "epoch": 0.30588892653553745, "grad_norm": 1.66612708568573, "learning_rate": 0.00019999789445316436, "loss": 0.7209695339202881, "step": 51460 }, { "epoch": 0.3059483686122058, "grad_norm": 2.069734573364258, "learning_rate": 0.00019999785165876103, "loss": 0.7182962417602539, "step": 51470 }, { "epoch": 0.3060078106888742, "grad_norm": 1.9574089050292969, "learning_rate": 0.00019999780843383741, "loss": 0.7241603374481201, "step": 51480 }, { "epoch": 0.30606725276554264, "grad_norm": 1.339417815208435, "learning_rate": 0.00019999776477839368, "loss": 0.6200407028198243, "step": 51490 }, { "epoch": 0.306126694842211, "grad_norm": 1.3186222314834595, "learning_rate": 0.00019999772069243007, "loss": 0.7442728519439697, "step": 51500 }, { "epoch": 0.3061861369188794, "grad_norm": 1.4400880336761475, "learning_rate": 0.00019999767617594677, "loss": 0.7529935836791992, "step": 51510 }, { "epoch": 0.3062455789955478, "grad_norm": 1.9736510515213013, "learning_rate": 0.000199997631228944, "loss": 0.6651953220367431, "step": 51520 }, { "epoch": 0.3063050210722162, "grad_norm": 1.9576613903045654, "learning_rate": 0.00019999758585142197, "loss": 0.6990339279174804, "step": 51530 }, { "epoch": 0.30636446314888455, "grad_norm": 1.3283367156982422, "learning_rate": 0.00019999754004338088, "loss": 0.6929240226745605, "step": 51540 }, { "epoch": 0.30642390522555296, "grad_norm": 1.651340365409851, "learning_rate": 0.00019999749380482097, "loss": 0.6624299049377441, "step": 51550 }, { "epoch": 0.3064833473022214, "grad_norm": 1.7699167728424072, "learning_rate": 0.0001999974471357425, "loss": 0.6855792045593262, "step": 51560 }, { "epoch": 0.30654278937888974, "grad_norm": 1.7094380855560303, "learning_rate": 0.0001999974000361456, "loss": 0.6596755981445312, "step": 51570 }, { "epoch": 0.30660223145555815, "grad_norm": 1.823441743850708, "learning_rate": 0.0001999973525060306, "loss": 0.7357009410858154, "step": 51580 }, { "epoch": 0.3066616735322265, "grad_norm": 1.2645676136016846, "learning_rate": 0.00019999730454539765, "loss": 0.7163690567016602, "step": 51590 }, { "epoch": 0.3067211156088949, "grad_norm": 1.9252651929855347, "learning_rate": 0.00019999725615424705, "loss": 0.7595208644866943, "step": 51600 }, { "epoch": 0.3067805576855633, "grad_norm": 2.13346529006958, "learning_rate": 0.00019999720733257894, "loss": 0.7230700969696044, "step": 51610 }, { "epoch": 0.3068399997622317, "grad_norm": 1.682433843612671, "learning_rate": 0.0001999971580803936, "loss": 0.7146956443786621, "step": 51620 }, { "epoch": 0.3068994418389001, "grad_norm": 1.9731312990188599, "learning_rate": 0.0001999971083976913, "loss": 0.7183049201965332, "step": 51630 }, { "epoch": 0.30695888391556847, "grad_norm": 2.3390331268310547, "learning_rate": 0.0001999970582844722, "loss": 0.7206561088562011, "step": 51640 }, { "epoch": 0.3070183259922369, "grad_norm": 1.9227321147918701, "learning_rate": 0.00019999700774073664, "loss": 0.7202089786529541, "step": 51650 }, { "epoch": 0.30707776806890524, "grad_norm": 1.5876429080963135, "learning_rate": 0.00019999695676648475, "loss": 0.707413625717163, "step": 51660 }, { "epoch": 0.30713721014557366, "grad_norm": 2.0268754959106445, "learning_rate": 0.00019999690536171686, "loss": 0.6459890365600586, "step": 51670 }, { "epoch": 0.307196652222242, "grad_norm": 1.9408016204833984, "learning_rate": 0.0001999968535264332, "loss": 0.7557703971862793, "step": 51680 }, { "epoch": 0.30725609429891043, "grad_norm": 1.4584695100784302, "learning_rate": 0.000199996801260634, "loss": 0.6490480422973632, "step": 51690 }, { "epoch": 0.3073155363755788, "grad_norm": 1.631709098815918, "learning_rate": 0.00019999674856431947, "loss": 0.7452613830566406, "step": 51700 }, { "epoch": 0.3073749784522472, "grad_norm": 1.4200375080108643, "learning_rate": 0.00019999669543748996, "loss": 0.6668783187866211, "step": 51710 }, { "epoch": 0.3074344205289156, "grad_norm": 1.701309323310852, "learning_rate": 0.00019999664188014566, "loss": 0.6847671508789063, "step": 51720 }, { "epoch": 0.307493862605584, "grad_norm": 1.6643004417419434, "learning_rate": 0.0001999965878922868, "loss": 0.7502806663513184, "step": 51730 }, { "epoch": 0.3075533046822524, "grad_norm": 1.5179400444030762, "learning_rate": 0.00019999653347391373, "loss": 0.7306855678558349, "step": 51740 }, { "epoch": 0.30761274675892075, "grad_norm": 1.875972032546997, "learning_rate": 0.0001999964786250266, "loss": 0.6593226432800293, "step": 51750 }, { "epoch": 0.30767218883558917, "grad_norm": 1.5997291803359985, "learning_rate": 0.00019999642334562575, "loss": 0.7007988452911377, "step": 51760 }, { "epoch": 0.3077316309122575, "grad_norm": 1.8987696170806885, "learning_rate": 0.00019999636763571143, "loss": 0.6192511081695556, "step": 51770 }, { "epoch": 0.30779107298892594, "grad_norm": 1.97127103805542, "learning_rate": 0.00019999631149528389, "loss": 0.6727732181549072, "step": 51780 }, { "epoch": 0.30785051506559435, "grad_norm": 1.523274540901184, "learning_rate": 0.0001999962549243434, "loss": 0.6850958824157715, "step": 51790 }, { "epoch": 0.3079099571422627, "grad_norm": 1.7774391174316406, "learning_rate": 0.00019999619792289026, "loss": 0.7247566223144531, "step": 51800 }, { "epoch": 0.30796939921893113, "grad_norm": 2.218332529067993, "learning_rate": 0.00019999614049092472, "loss": 0.7432941436767578, "step": 51810 }, { "epoch": 0.3080288412955995, "grad_norm": 2.087207078933716, "learning_rate": 0.00019999608262844703, "loss": 0.7026299476623535, "step": 51820 }, { "epoch": 0.3080882833722679, "grad_norm": 1.5624691247940063, "learning_rate": 0.00019999602433545753, "loss": 0.6854682922363281, "step": 51830 }, { "epoch": 0.30814772544893626, "grad_norm": 2.0304274559020996, "learning_rate": 0.00019999596561195643, "loss": 0.7197221279144287, "step": 51840 }, { "epoch": 0.3082071675256047, "grad_norm": 1.9309943914413452, "learning_rate": 0.000199995906457944, "loss": 0.6648520469665528, "step": 51850 }, { "epoch": 0.3082666096022731, "grad_norm": 1.9023703336715698, "learning_rate": 0.00019999584687342063, "loss": 0.6589920520782471, "step": 51860 }, { "epoch": 0.30832605167894145, "grad_norm": 2.1135072708129883, "learning_rate": 0.0001999957868583865, "loss": 0.6411567687988281, "step": 51870 }, { "epoch": 0.30838549375560986, "grad_norm": 1.6508708000183105, "learning_rate": 0.00019999572641284197, "loss": 0.7483520984649659, "step": 51880 }, { "epoch": 0.3084449358322782, "grad_norm": 1.5014821290969849, "learning_rate": 0.00019999566553678731, "loss": 0.7258820533752441, "step": 51890 }, { "epoch": 0.30850437790894664, "grad_norm": 2.013014554977417, "learning_rate": 0.00019999560423022275, "loss": 0.7201627731323242, "step": 51900 }, { "epoch": 0.308563819985615, "grad_norm": 1.5854249000549316, "learning_rate": 0.00019999554249314867, "loss": 0.7010573387145996, "step": 51910 }, { "epoch": 0.3086232620622834, "grad_norm": 2.068899154663086, "learning_rate": 0.00019999548032556528, "loss": 0.6908162117004395, "step": 51920 }, { "epoch": 0.3086827041389518, "grad_norm": 1.3680258989334106, "learning_rate": 0.00019999541772747293, "loss": 0.661573839187622, "step": 51930 }, { "epoch": 0.3087421462156202, "grad_norm": 1.5813385248184204, "learning_rate": 0.00019999535469887193, "loss": 0.6265462398529053, "step": 51940 }, { "epoch": 0.3088015882922886, "grad_norm": 1.6408445835113525, "learning_rate": 0.00019999529123976257, "loss": 0.6904171943664551, "step": 51950 }, { "epoch": 0.30886103036895696, "grad_norm": 1.9554619789123535, "learning_rate": 0.00019999522735014518, "loss": 0.6488215446472168, "step": 51960 }, { "epoch": 0.30892047244562537, "grad_norm": 1.821799874305725, "learning_rate": 0.00019999516303001997, "loss": 0.7124804496765137, "step": 51970 }, { "epoch": 0.30897991452229373, "grad_norm": 1.6812235116958618, "learning_rate": 0.00019999509827938733, "loss": 0.7272041797637939, "step": 51980 }, { "epoch": 0.30903935659896214, "grad_norm": 2.1042988300323486, "learning_rate": 0.00019999503309824757, "loss": 0.7506083488464356, "step": 51990 }, { "epoch": 0.30909879867563056, "grad_norm": 1.6585819721221924, "learning_rate": 0.00019999496748660095, "loss": 0.713779878616333, "step": 52000 }, { "epoch": 0.3091582407522989, "grad_norm": 1.5970474481582642, "learning_rate": 0.00019999490144444787, "loss": 0.6944212913513184, "step": 52010 }, { "epoch": 0.30921768282896733, "grad_norm": 1.3820346593856812, "learning_rate": 0.00019999483497178854, "loss": 0.6775743961334229, "step": 52020 }, { "epoch": 0.3092771249056357, "grad_norm": 1.6108630895614624, "learning_rate": 0.00019999476806862337, "loss": 0.6848551750183105, "step": 52030 }, { "epoch": 0.3093365669823041, "grad_norm": 1.932173252105713, "learning_rate": 0.0001999947007349526, "loss": 0.7330033302307128, "step": 52040 }, { "epoch": 0.30939600905897247, "grad_norm": 2.017897367477417, "learning_rate": 0.00019999463297077662, "loss": 0.7510890960693359, "step": 52050 }, { "epoch": 0.3094554511356409, "grad_norm": 1.5028353929519653, "learning_rate": 0.0001999945647760957, "loss": 0.676007080078125, "step": 52060 }, { "epoch": 0.30951489321230924, "grad_norm": 2.9887166023254395, "learning_rate": 0.0001999944961509102, "loss": 0.7169640064239502, "step": 52070 }, { "epoch": 0.30957433528897765, "grad_norm": 1.9117746353149414, "learning_rate": 0.00019999442709522046, "loss": 0.6651123046875, "step": 52080 }, { "epoch": 0.30963377736564607, "grad_norm": 1.538097620010376, "learning_rate": 0.00019999435760902678, "loss": 0.6627926826477051, "step": 52090 }, { "epoch": 0.3096932194423144, "grad_norm": 2.097325563430786, "learning_rate": 0.00019999428769232948, "loss": 0.7041426181793213, "step": 52100 }, { "epoch": 0.30975266151898284, "grad_norm": 1.8851529359817505, "learning_rate": 0.00019999421734512895, "loss": 0.6467723369598388, "step": 52110 }, { "epoch": 0.3098121035956512, "grad_norm": 2.1479592323303223, "learning_rate": 0.00019999414656742548, "loss": 0.6872787475585938, "step": 52120 }, { "epoch": 0.3098715456723196, "grad_norm": 1.5070700645446777, "learning_rate": 0.00019999407535921946, "loss": 0.6781601905822754, "step": 52130 }, { "epoch": 0.309930987748988, "grad_norm": 1.9988282918930054, "learning_rate": 0.00019999400372051115, "loss": 0.7118853092193603, "step": 52140 }, { "epoch": 0.3099904298256564, "grad_norm": 1.7024822235107422, "learning_rate": 0.00019999393165130095, "loss": 0.6851869583129883, "step": 52150 }, { "epoch": 0.3100498719023248, "grad_norm": 1.6856915950775146, "learning_rate": 0.00019999385915158918, "loss": 0.6798144340515136, "step": 52160 }, { "epoch": 0.31010931397899316, "grad_norm": 1.4688072204589844, "learning_rate": 0.00019999378622137623, "loss": 0.669558334350586, "step": 52170 }, { "epoch": 0.3101687560556616, "grad_norm": 1.5393600463867188, "learning_rate": 0.0001999937128606624, "loss": 0.7217799663543701, "step": 52180 }, { "epoch": 0.31022819813232994, "grad_norm": 1.3853166103363037, "learning_rate": 0.00019999363906944803, "loss": 0.6918119430541992, "step": 52190 }, { "epoch": 0.31028764020899835, "grad_norm": 2.4386954307556152, "learning_rate": 0.00019999356484773356, "loss": 0.7032127857208252, "step": 52200 }, { "epoch": 0.3103470822856667, "grad_norm": 1.668277621269226, "learning_rate": 0.00019999349019551922, "loss": 0.7002727508544921, "step": 52210 }, { "epoch": 0.3104065243623351, "grad_norm": 2.136645555496216, "learning_rate": 0.0001999934151128055, "loss": 0.6893247604370117, "step": 52220 }, { "epoch": 0.31046596643900354, "grad_norm": 1.9075685739517212, "learning_rate": 0.00019999333959959265, "loss": 0.7210886001586914, "step": 52230 }, { "epoch": 0.3105254085156719, "grad_norm": 1.452200174331665, "learning_rate": 0.0001999932636558811, "loss": 0.7381556034088135, "step": 52240 }, { "epoch": 0.3105848505923403, "grad_norm": 1.7919678688049316, "learning_rate": 0.00019999318728167114, "loss": 0.7231268405914306, "step": 52250 }, { "epoch": 0.31064429266900867, "grad_norm": 1.7588071823120117, "learning_rate": 0.00019999311047696322, "loss": 0.6908655643463135, "step": 52260 }, { "epoch": 0.3107037347456771, "grad_norm": 1.7703417539596558, "learning_rate": 0.00019999303324175766, "loss": 0.7290994644165039, "step": 52270 }, { "epoch": 0.31076317682234544, "grad_norm": 1.8781754970550537, "learning_rate": 0.00019999295557605485, "loss": 0.7060531139373779, "step": 52280 }, { "epoch": 0.31082261889901386, "grad_norm": 1.5200496912002563, "learning_rate": 0.00019999287747985513, "loss": 0.7247383117675781, "step": 52290 }, { "epoch": 0.3108820609756823, "grad_norm": 1.3092858791351318, "learning_rate": 0.0001999927989531589, "loss": 0.6670916557312012, "step": 52300 }, { "epoch": 0.31094150305235063, "grad_norm": 1.1709181070327759, "learning_rate": 0.0001999927199959665, "loss": 0.7029263019561768, "step": 52310 }, { "epoch": 0.31100094512901905, "grad_norm": 1.43668794631958, "learning_rate": 0.0001999926406082784, "loss": 0.7800847053527832, "step": 52320 }, { "epoch": 0.3110603872056874, "grad_norm": 1.8203425407409668, "learning_rate": 0.00019999256079009488, "loss": 0.6941357612609863, "step": 52330 }, { "epoch": 0.3111198292823558, "grad_norm": 2.2232515811920166, "learning_rate": 0.00019999248054141638, "loss": 0.714579725265503, "step": 52340 }, { "epoch": 0.3111792713590242, "grad_norm": 1.908376932144165, "learning_rate": 0.00019999239986224324, "loss": 0.7487339973449707, "step": 52350 }, { "epoch": 0.3112387134356926, "grad_norm": 1.7116916179656982, "learning_rate": 0.0001999923187525759, "loss": 0.6747395992279053, "step": 52360 }, { "epoch": 0.31129815551236095, "grad_norm": 1.8524075746536255, "learning_rate": 0.0001999922372124147, "loss": 0.6939596176147461, "step": 52370 }, { "epoch": 0.31135759758902937, "grad_norm": 2.0929455757141113, "learning_rate": 0.00019999215524176003, "loss": 0.6616413593292236, "step": 52380 }, { "epoch": 0.3114170396656978, "grad_norm": 1.80059814453125, "learning_rate": 0.0001999920728406123, "loss": 0.7308916091918946, "step": 52390 }, { "epoch": 0.31147648174236614, "grad_norm": 1.756359338760376, "learning_rate": 0.0001999919900089719, "loss": 0.6358818054199219, "step": 52400 }, { "epoch": 0.31153592381903455, "grad_norm": 1.726513385772705, "learning_rate": 0.00019999190674683926, "loss": 0.675658130645752, "step": 52410 }, { "epoch": 0.3115953658957029, "grad_norm": 1.5457653999328613, "learning_rate": 0.00019999182305421474, "loss": 0.7340257644653321, "step": 52420 }, { "epoch": 0.31165480797237133, "grad_norm": 1.8179676532745361, "learning_rate": 0.00019999173893109874, "loss": 0.6969169616699219, "step": 52430 }, { "epoch": 0.3117142500490397, "grad_norm": 1.7458209991455078, "learning_rate": 0.00019999165437749165, "loss": 0.7165410995483399, "step": 52440 }, { "epoch": 0.3117736921257081, "grad_norm": 1.7543702125549316, "learning_rate": 0.00019999156939339393, "loss": 0.7036920547485351, "step": 52450 }, { "epoch": 0.3118331342023765, "grad_norm": 2.521470546722412, "learning_rate": 0.00019999148397880593, "loss": 0.6988101959228515, "step": 52460 }, { "epoch": 0.3118925762790449, "grad_norm": 1.6895439624786377, "learning_rate": 0.00019999139813372808, "loss": 0.7450314044952393, "step": 52470 }, { "epoch": 0.3119520183557133, "grad_norm": 1.7397834062576294, "learning_rate": 0.00019999131185816083, "loss": 0.6882230281829834, "step": 52480 }, { "epoch": 0.31201146043238165, "grad_norm": 1.801742434501648, "learning_rate": 0.0001999912251521045, "loss": 0.6737530708312989, "step": 52490 }, { "epoch": 0.31207090250905006, "grad_norm": 2.3167216777801514, "learning_rate": 0.00019999113801555962, "loss": 0.7158307075500489, "step": 52500 }, { "epoch": 0.3121303445857184, "grad_norm": 1.6980109214782715, "learning_rate": 0.0001999910504485265, "loss": 0.7410003662109375, "step": 52510 }, { "epoch": 0.31218978666238684, "grad_norm": 1.5658541917800903, "learning_rate": 0.0001999909624510056, "loss": 0.6954279899597168, "step": 52520 }, { "epoch": 0.31224922873905525, "grad_norm": 2.0544850826263428, "learning_rate": 0.00019999087402299736, "loss": 0.7036890029907227, "step": 52530 }, { "epoch": 0.3123086708157236, "grad_norm": 1.9021022319793701, "learning_rate": 0.00019999078516450217, "loss": 0.7094541549682617, "step": 52540 }, { "epoch": 0.312368112892392, "grad_norm": 1.3722103834152222, "learning_rate": 0.0001999906958755205, "loss": 0.657472801208496, "step": 52550 }, { "epoch": 0.3124275549690604, "grad_norm": 2.005568027496338, "learning_rate": 0.00019999060615605275, "loss": 0.709428358078003, "step": 52560 }, { "epoch": 0.3124869970457288, "grad_norm": 2.0556092262268066, "learning_rate": 0.0001999905160060993, "loss": 0.7206625461578369, "step": 52570 }, { "epoch": 0.31254643912239716, "grad_norm": 1.633439064025879, "learning_rate": 0.0001999904254256607, "loss": 0.6285821914672851, "step": 52580 }, { "epoch": 0.31260588119906557, "grad_norm": 1.945418119430542, "learning_rate": 0.00019999033441473724, "loss": 0.7320771217346191, "step": 52590 }, { "epoch": 0.312665323275734, "grad_norm": 2.1491072177886963, "learning_rate": 0.00019999024297332949, "loss": 0.7437421798706054, "step": 52600 }, { "epoch": 0.31272476535240235, "grad_norm": 1.5833226442337036, "learning_rate": 0.0001999901511014378, "loss": 0.7673581600189209, "step": 52610 }, { "epoch": 0.31278420742907076, "grad_norm": 1.7389894723892212, "learning_rate": 0.00019999005879906264, "loss": 0.7197609424591065, "step": 52620 }, { "epoch": 0.3128436495057391, "grad_norm": 1.9079511165618896, "learning_rate": 0.00019998996606620446, "loss": 0.689579963684082, "step": 52630 }, { "epoch": 0.31290309158240753, "grad_norm": 1.7459964752197266, "learning_rate": 0.00019998987290286368, "loss": 0.6793051719665527, "step": 52640 }, { "epoch": 0.3129625336590759, "grad_norm": 1.6587108373641968, "learning_rate": 0.00019998977930904075, "loss": 0.6613896369934082, "step": 52650 }, { "epoch": 0.3130219757357443, "grad_norm": 1.954160213470459, "learning_rate": 0.00019998968528473613, "loss": 0.698304271697998, "step": 52660 }, { "epoch": 0.3130814178124127, "grad_norm": 1.516385555267334, "learning_rate": 0.00019998959082995028, "loss": 0.7458293914794922, "step": 52670 }, { "epoch": 0.3131408598890811, "grad_norm": 1.7689504623413086, "learning_rate": 0.00019998949594468362, "loss": 0.7198667049407959, "step": 52680 }, { "epoch": 0.3132003019657495, "grad_norm": 1.6356524229049683, "learning_rate": 0.00019998940062893665, "loss": 0.6073582649230957, "step": 52690 }, { "epoch": 0.31325974404241785, "grad_norm": 1.7345685958862305, "learning_rate": 0.00019998930488270976, "loss": 0.7107558250427246, "step": 52700 }, { "epoch": 0.31331918611908627, "grad_norm": 1.948778748512268, "learning_rate": 0.00019998920870600346, "loss": 0.6664801597595215, "step": 52710 }, { "epoch": 0.3133786281957546, "grad_norm": 1.6194570064544678, "learning_rate": 0.00019998911209881816, "loss": 0.6805292129516601, "step": 52720 }, { "epoch": 0.31343807027242304, "grad_norm": 3.239266872406006, "learning_rate": 0.0001999890150611544, "loss": 0.7222425460815429, "step": 52730 }, { "epoch": 0.3134975123490914, "grad_norm": 1.5317968130111694, "learning_rate": 0.0001999889175930126, "loss": 0.7011957168579102, "step": 52740 }, { "epoch": 0.3135569544257598, "grad_norm": 1.612266182899475, "learning_rate": 0.0001999888196943932, "loss": 0.665268850326538, "step": 52750 }, { "epoch": 0.31361639650242823, "grad_norm": 1.3894307613372803, "learning_rate": 0.00019998872136529672, "loss": 0.7243749618530273, "step": 52760 }, { "epoch": 0.3136758385790966, "grad_norm": 1.9586949348449707, "learning_rate": 0.0001999886226057236, "loss": 0.7296347618103027, "step": 52770 }, { "epoch": 0.313735280655765, "grad_norm": 1.5691196918487549, "learning_rate": 0.00019998852341567428, "loss": 0.7462793827056885, "step": 52780 }, { "epoch": 0.31379472273243336, "grad_norm": 1.7596535682678223, "learning_rate": 0.00019998842379514932, "loss": 0.6600042343139648, "step": 52790 }, { "epoch": 0.3138541648091018, "grad_norm": 1.7844268083572388, "learning_rate": 0.00019998832374414912, "loss": 0.730091667175293, "step": 52800 }, { "epoch": 0.31391360688577014, "grad_norm": 1.900085687637329, "learning_rate": 0.00019998822326267423, "loss": 0.7257950782775879, "step": 52810 }, { "epoch": 0.31397304896243855, "grad_norm": 1.353192925453186, "learning_rate": 0.00019998812235072505, "loss": 0.7008524417877198, "step": 52820 }, { "epoch": 0.31403249103910696, "grad_norm": 1.8312203884124756, "learning_rate": 0.00019998802100830212, "loss": 0.6779332160949707, "step": 52830 }, { "epoch": 0.3140919331157753, "grad_norm": 1.8849292993545532, "learning_rate": 0.0001999879192354059, "loss": 0.72244234085083, "step": 52840 }, { "epoch": 0.31415137519244374, "grad_norm": 2.085273265838623, "learning_rate": 0.00019998781703203686, "loss": 0.7224464416503906, "step": 52850 }, { "epoch": 0.3142108172691121, "grad_norm": 1.6428825855255127, "learning_rate": 0.00019998771439819554, "loss": 0.6870308876037597, "step": 52860 }, { "epoch": 0.3142702593457805, "grad_norm": 1.7224355936050415, "learning_rate": 0.0001999876113338824, "loss": 0.709242296218872, "step": 52870 }, { "epoch": 0.31432970142244887, "grad_norm": 1.696883201599121, "learning_rate": 0.00019998750783909794, "loss": 0.701932144165039, "step": 52880 }, { "epoch": 0.3143891434991173, "grad_norm": 1.7624422311782837, "learning_rate": 0.00019998740391384263, "loss": 0.6749853134155274, "step": 52890 }, { "epoch": 0.3144485855757857, "grad_norm": 2.1443753242492676, "learning_rate": 0.000199987299558117, "loss": 0.6665547370910645, "step": 52900 }, { "epoch": 0.31450802765245406, "grad_norm": 1.5095906257629395, "learning_rate": 0.00019998719477192154, "loss": 0.716922378540039, "step": 52910 }, { "epoch": 0.3145674697291225, "grad_norm": 1.6975429058074951, "learning_rate": 0.00019998708955525673, "loss": 0.7457222938537598, "step": 52920 }, { "epoch": 0.31462691180579083, "grad_norm": 2.4596850872039795, "learning_rate": 0.00019998698390812314, "loss": 0.6499382972717285, "step": 52930 }, { "epoch": 0.31468635388245925, "grad_norm": 2.149254560470581, "learning_rate": 0.00019998687783052117, "loss": 0.7266529083251954, "step": 52940 }, { "epoch": 0.3147457959591276, "grad_norm": 1.4860632419586182, "learning_rate": 0.00019998677132245142, "loss": 0.7150585174560546, "step": 52950 }, { "epoch": 0.314805238035796, "grad_norm": 1.5616694688796997, "learning_rate": 0.00019998666438391434, "loss": 0.730107593536377, "step": 52960 }, { "epoch": 0.31486468011246443, "grad_norm": 1.746174693107605, "learning_rate": 0.00019998655701491047, "loss": 0.7006203651428222, "step": 52970 }, { "epoch": 0.3149241221891328, "grad_norm": 2.406203508377075, "learning_rate": 0.00019998644921544032, "loss": 0.7290843486785888, "step": 52980 }, { "epoch": 0.3149835642658012, "grad_norm": 1.3146190643310547, "learning_rate": 0.00019998634098550443, "loss": 0.6196742534637452, "step": 52990 }, { "epoch": 0.31504300634246957, "grad_norm": 1.8645144701004028, "learning_rate": 0.00019998623232510328, "loss": 0.7432582378387451, "step": 53000 }, { "epoch": 0.315102448419138, "grad_norm": 1.3025307655334473, "learning_rate": 0.0001999861232342374, "loss": 0.6261834144592285, "step": 53010 }, { "epoch": 0.31516189049580634, "grad_norm": 1.6982073783874512, "learning_rate": 0.00019998601371290728, "loss": 0.7660222053527832, "step": 53020 }, { "epoch": 0.31522133257247476, "grad_norm": 1.9226244688034058, "learning_rate": 0.00019998590376111354, "loss": 0.6722899436950683, "step": 53030 }, { "epoch": 0.31528077464914317, "grad_norm": 1.6544182300567627, "learning_rate": 0.0001999857933788566, "loss": 0.6339139938354492, "step": 53040 }, { "epoch": 0.31534021672581153, "grad_norm": 1.6483876705169678, "learning_rate": 0.00019998568256613704, "loss": 0.6798050880432129, "step": 53050 }, { "epoch": 0.31539965880247994, "grad_norm": 1.8862721920013428, "learning_rate": 0.00019998557132295538, "loss": 0.6955927848815918, "step": 53060 }, { "epoch": 0.3154591008791483, "grad_norm": 1.804304599761963, "learning_rate": 0.00019998545964931217, "loss": 0.6911074638366699, "step": 53070 }, { "epoch": 0.3155185429558167, "grad_norm": 1.8371278047561646, "learning_rate": 0.00019998534754520793, "loss": 0.7114070892333985, "step": 53080 }, { "epoch": 0.3155779850324851, "grad_norm": 1.6530191898345947, "learning_rate": 0.00019998523501064318, "loss": 0.6867004871368408, "step": 53090 }, { "epoch": 0.3156374271091535, "grad_norm": 1.4602960348129272, "learning_rate": 0.00019998512204561847, "loss": 0.7783935070037842, "step": 53100 }, { "epoch": 0.31569686918582185, "grad_norm": 1.5465482473373413, "learning_rate": 0.00019998500865013436, "loss": 0.7082081794738769, "step": 53110 }, { "epoch": 0.31575631126249026, "grad_norm": 1.9671498537063599, "learning_rate": 0.00019998489482419136, "loss": 0.703037166595459, "step": 53120 }, { "epoch": 0.3158157533391587, "grad_norm": 1.82272469997406, "learning_rate": 0.00019998478056779004, "loss": 0.680413007736206, "step": 53130 }, { "epoch": 0.31587519541582704, "grad_norm": 1.415285587310791, "learning_rate": 0.00019998466588093094, "loss": 0.7402707099914551, "step": 53140 }, { "epoch": 0.31593463749249545, "grad_norm": 1.5261564254760742, "learning_rate": 0.0001999845507636146, "loss": 0.7027874946594238, "step": 53150 }, { "epoch": 0.3159940795691638, "grad_norm": 1.7445173263549805, "learning_rate": 0.00019998443521584158, "loss": 0.7284863471984864, "step": 53160 }, { "epoch": 0.3160535216458322, "grad_norm": 1.8268868923187256, "learning_rate": 0.00019998431923761242, "loss": 0.6921724796295166, "step": 53170 }, { "epoch": 0.3161129637225006, "grad_norm": 1.5122698545455933, "learning_rate": 0.0001999842028289277, "loss": 0.6682779312133789, "step": 53180 }, { "epoch": 0.316172405799169, "grad_norm": 1.7306139469146729, "learning_rate": 0.00019998408598978794, "loss": 0.6659479141235352, "step": 53190 }, { "epoch": 0.3162318478758374, "grad_norm": 1.2180620431900024, "learning_rate": 0.00019998396872019373, "loss": 0.6322637557983398, "step": 53200 }, { "epoch": 0.31629128995250577, "grad_norm": 1.4181642532348633, "learning_rate": 0.00019998385102014564, "loss": 0.6940054416656494, "step": 53210 }, { "epoch": 0.3163507320291742, "grad_norm": 1.8842368125915527, "learning_rate": 0.0001999837328896442, "loss": 0.6964953422546387, "step": 53220 }, { "epoch": 0.31641017410584255, "grad_norm": 1.4895997047424316, "learning_rate": 0.00019998361432868998, "loss": 0.6858966827392579, "step": 53230 }, { "epoch": 0.31646961618251096, "grad_norm": 1.682454228401184, "learning_rate": 0.00019998349533728357, "loss": 0.6872202396392822, "step": 53240 }, { "epoch": 0.3165290582591793, "grad_norm": 2.1364150047302246, "learning_rate": 0.0001999833759154255, "loss": 0.7489002227783204, "step": 53250 }, { "epoch": 0.31658850033584773, "grad_norm": 1.371227502822876, "learning_rate": 0.0001999832560631164, "loss": 0.6946270942687989, "step": 53260 }, { "epoch": 0.31664794241251615, "grad_norm": 1.5339601039886475, "learning_rate": 0.00019998313578035678, "loss": 0.6558034420013428, "step": 53270 }, { "epoch": 0.3167073844891845, "grad_norm": 1.8494738340377808, "learning_rate": 0.00019998301506714728, "loss": 0.6745740890502929, "step": 53280 }, { "epoch": 0.3167668265658529, "grad_norm": 1.715431809425354, "learning_rate": 0.00019998289392348842, "loss": 0.6704477310180664, "step": 53290 }, { "epoch": 0.3168262686425213, "grad_norm": 1.5907272100448608, "learning_rate": 0.0001999827723493808, "loss": 0.7132795810699463, "step": 53300 }, { "epoch": 0.3168857107191897, "grad_norm": 2.0264809131622314, "learning_rate": 0.00019998265034482497, "loss": 0.6712553977966309, "step": 53310 }, { "epoch": 0.31694515279585805, "grad_norm": 1.9364656209945679, "learning_rate": 0.0001999825279098216, "loss": 0.6994941234588623, "step": 53320 }, { "epoch": 0.31700459487252647, "grad_norm": 1.3916395902633667, "learning_rate": 0.00019998240504437122, "loss": 0.6333229064941406, "step": 53330 }, { "epoch": 0.3170640369491949, "grad_norm": 1.819219946861267, "learning_rate": 0.0001999822817484744, "loss": 0.6343683242797852, "step": 53340 }, { "epoch": 0.31712347902586324, "grad_norm": 1.7168177366256714, "learning_rate": 0.00019998215802213175, "loss": 0.7313007354736328, "step": 53350 }, { "epoch": 0.31718292110253166, "grad_norm": 1.9582010507583618, "learning_rate": 0.00019998203386534388, "loss": 0.6761816501617431, "step": 53360 }, { "epoch": 0.3172423631792, "grad_norm": 1.9102250337600708, "learning_rate": 0.00019998190927811136, "loss": 0.7061142921447754, "step": 53370 }, { "epoch": 0.31730180525586843, "grad_norm": 1.9150588512420654, "learning_rate": 0.00019998178426043476, "loss": 0.7150667667388916, "step": 53380 }, { "epoch": 0.3173612473325368, "grad_norm": 2.1529557704925537, "learning_rate": 0.00019998165881231474, "loss": 0.6894720077514649, "step": 53390 }, { "epoch": 0.3174206894092052, "grad_norm": 1.490788459777832, "learning_rate": 0.0001999815329337519, "loss": 0.7507984161376953, "step": 53400 }, { "epoch": 0.3174801314858736, "grad_norm": 1.6504924297332764, "learning_rate": 0.00019998140662474677, "loss": 0.6764982223510743, "step": 53410 }, { "epoch": 0.317539573562542, "grad_norm": 1.9589771032333374, "learning_rate": 0.00019998127988530003, "loss": 0.7046197414398193, "step": 53420 }, { "epoch": 0.3175990156392104, "grad_norm": 1.786973237991333, "learning_rate": 0.0001999811527154122, "loss": 0.6404340267181396, "step": 53430 }, { "epoch": 0.31765845771587875, "grad_norm": 2.1746020317077637, "learning_rate": 0.00019998102511508398, "loss": 0.7167875289916992, "step": 53440 }, { "epoch": 0.31771789979254716, "grad_norm": 1.8857783079147339, "learning_rate": 0.00019998089708431595, "loss": 0.720851993560791, "step": 53450 }, { "epoch": 0.3177773418692155, "grad_norm": 1.5518648624420166, "learning_rate": 0.0001999807686231087, "loss": 0.6586337566375733, "step": 53460 }, { "epoch": 0.31783678394588394, "grad_norm": 1.596412181854248, "learning_rate": 0.00019998063973146286, "loss": 0.6798912048339844, "step": 53470 }, { "epoch": 0.3178962260225523, "grad_norm": 1.6286717653274536, "learning_rate": 0.00019998051040937903, "loss": 0.7393359184265137, "step": 53480 }, { "epoch": 0.3179556680992207, "grad_norm": 1.449489951133728, "learning_rate": 0.00019998038065685786, "loss": 0.7037327289581299, "step": 53490 }, { "epoch": 0.3180151101758891, "grad_norm": 1.4742084741592407, "learning_rate": 0.0001999802504739, "loss": 0.7341341495513916, "step": 53500 }, { "epoch": 0.3180745522525575, "grad_norm": 1.6949939727783203, "learning_rate": 0.00019998011986050595, "loss": 0.6857570171356201, "step": 53510 }, { "epoch": 0.3181339943292259, "grad_norm": 2.0026462078094482, "learning_rate": 0.00019997998881667647, "loss": 0.6517858982086182, "step": 53520 }, { "epoch": 0.31819343640589426, "grad_norm": 1.7461605072021484, "learning_rate": 0.0001999798573424121, "loss": 0.6508070945739746, "step": 53530 }, { "epoch": 0.3182528784825627, "grad_norm": 1.6456323862075806, "learning_rate": 0.00019997972543771349, "loss": 0.6894524574279786, "step": 53540 }, { "epoch": 0.31831232055923103, "grad_norm": 1.5699853897094727, "learning_rate": 0.00019997959310258127, "loss": 0.6849810600280761, "step": 53550 }, { "epoch": 0.31837176263589945, "grad_norm": 1.4862533807754517, "learning_rate": 0.00019997946033701612, "loss": 0.6588689804077148, "step": 53560 }, { "epoch": 0.31843120471256786, "grad_norm": 1.6701078414916992, "learning_rate": 0.00019997932714101862, "loss": 0.7008550643920899, "step": 53570 }, { "epoch": 0.3184906467892362, "grad_norm": 1.8350825309753418, "learning_rate": 0.00019997919351458942, "loss": 0.7311874866485596, "step": 53580 }, { "epoch": 0.31855008886590463, "grad_norm": 1.880335807800293, "learning_rate": 0.00019997905945772916, "loss": 0.6756443977355957, "step": 53590 }, { "epoch": 0.318609530942573, "grad_norm": 1.6814115047454834, "learning_rate": 0.0001999789249704385, "loss": 0.6408855438232421, "step": 53600 }, { "epoch": 0.3186689730192414, "grad_norm": 1.349255084991455, "learning_rate": 0.00019997879005271806, "loss": 0.7364543914794922, "step": 53610 }, { "epoch": 0.31872841509590977, "grad_norm": 1.882434606552124, "learning_rate": 0.00019997865470456852, "loss": 0.6480870723724366, "step": 53620 }, { "epoch": 0.3187878571725782, "grad_norm": 2.0620200634002686, "learning_rate": 0.0001999785189259905, "loss": 0.7270046234130859, "step": 53630 }, { "epoch": 0.3188472992492466, "grad_norm": 1.817097544670105, "learning_rate": 0.0001999783827169846, "loss": 0.679072380065918, "step": 53640 }, { "epoch": 0.31890674132591496, "grad_norm": 1.7174888849258423, "learning_rate": 0.00019997824607755155, "loss": 0.7171375751495361, "step": 53650 }, { "epoch": 0.31896618340258337, "grad_norm": 1.7550663948059082, "learning_rate": 0.000199978109007692, "loss": 0.6669451713562011, "step": 53660 }, { "epoch": 0.31902562547925173, "grad_norm": 1.8673776388168335, "learning_rate": 0.00019997797150740653, "loss": 0.7381699562072754, "step": 53670 }, { "epoch": 0.31908506755592014, "grad_norm": 1.71013605594635, "learning_rate": 0.0001999778335766959, "loss": 0.6482716560363769, "step": 53680 }, { "epoch": 0.3191445096325885, "grad_norm": 1.6626397371292114, "learning_rate": 0.00019997769521556068, "loss": 0.6810420036315918, "step": 53690 }, { "epoch": 0.3192039517092569, "grad_norm": 1.4966198205947876, "learning_rate": 0.00019997755642400163, "loss": 0.7201791763305664, "step": 53700 }, { "epoch": 0.31926339378592533, "grad_norm": 1.977563500404358, "learning_rate": 0.00019997741720201927, "loss": 0.6607783794403076, "step": 53710 }, { "epoch": 0.3193228358625937, "grad_norm": 1.6298967599868774, "learning_rate": 0.00019997727754961442, "loss": 0.6926442146301269, "step": 53720 }, { "epoch": 0.3193822779392621, "grad_norm": 1.8625686168670654, "learning_rate": 0.00019997713746678765, "loss": 0.6719278335571289, "step": 53730 }, { "epoch": 0.31944172001593046, "grad_norm": 1.8284876346588135, "learning_rate": 0.00019997699695353967, "loss": 0.6698593139648438, "step": 53740 }, { "epoch": 0.3195011620925989, "grad_norm": 1.4682426452636719, "learning_rate": 0.00019997685600987112, "loss": 0.6982778549194336, "step": 53750 }, { "epoch": 0.31956060416926724, "grad_norm": 1.6428248882293701, "learning_rate": 0.00019997671463578272, "loss": 0.6837363719940186, "step": 53760 }, { "epoch": 0.31962004624593565, "grad_norm": 2.3594460487365723, "learning_rate": 0.0001999765728312751, "loss": 0.6980222702026367, "step": 53770 }, { "epoch": 0.31967948832260407, "grad_norm": 1.6694422960281372, "learning_rate": 0.00019997643059634898, "loss": 0.6735031127929687, "step": 53780 }, { "epoch": 0.3197389303992724, "grad_norm": 1.5600717067718506, "learning_rate": 0.000199976287931005, "loss": 0.6774130821228027, "step": 53790 }, { "epoch": 0.31979837247594084, "grad_norm": 1.9349299669265747, "learning_rate": 0.0001999761448352439, "loss": 0.6819520950317383, "step": 53800 }, { "epoch": 0.3198578145526092, "grad_norm": 1.5837324857711792, "learning_rate": 0.00019997600130906628, "loss": 0.6753064155578613, "step": 53810 }, { "epoch": 0.3199172566292776, "grad_norm": 1.750319004058838, "learning_rate": 0.0001999758573524729, "loss": 0.6724387645721436, "step": 53820 }, { "epoch": 0.31997669870594597, "grad_norm": 1.8610259294509888, "learning_rate": 0.0001999757129654644, "loss": 0.7518935203552246, "step": 53830 }, { "epoch": 0.3200361407826144, "grad_norm": 1.7949802875518799, "learning_rate": 0.00019997556814804155, "loss": 0.7240765571594239, "step": 53840 }, { "epoch": 0.32009558285928275, "grad_norm": 2.070297956466675, "learning_rate": 0.00019997542290020495, "loss": 0.7679276943206788, "step": 53850 }, { "epoch": 0.32015502493595116, "grad_norm": 1.7394481897354126, "learning_rate": 0.00019997527722195532, "loss": 0.7015044212341308, "step": 53860 }, { "epoch": 0.3202144670126196, "grad_norm": 1.7024961709976196, "learning_rate": 0.00019997513111329337, "loss": 0.6698468208312989, "step": 53870 }, { "epoch": 0.32027390908928793, "grad_norm": 1.7938082218170166, "learning_rate": 0.00019997498457421985, "loss": 0.6679431915283203, "step": 53880 }, { "epoch": 0.32033335116595635, "grad_norm": 1.8311305046081543, "learning_rate": 0.00019997483760473533, "loss": 0.7639322757720948, "step": 53890 }, { "epoch": 0.3203927932426247, "grad_norm": 1.6745141744613647, "learning_rate": 0.00019997469020484063, "loss": 0.7404159545898438, "step": 53900 }, { "epoch": 0.3204522353192931, "grad_norm": 1.547920823097229, "learning_rate": 0.0001999745423745364, "loss": 0.7263503074645996, "step": 53910 }, { "epoch": 0.3205116773959615, "grad_norm": 1.7225342988967896, "learning_rate": 0.00019997439411382337, "loss": 0.7562912940979004, "step": 53920 }, { "epoch": 0.3205711194726299, "grad_norm": 1.4748046398162842, "learning_rate": 0.0001999742454227023, "loss": 0.6718812942504883, "step": 53930 }, { "epoch": 0.3206305615492983, "grad_norm": 2.039071798324585, "learning_rate": 0.00019997409630117377, "loss": 0.6594924926757812, "step": 53940 }, { "epoch": 0.32069000362596667, "grad_norm": 1.5259768962860107, "learning_rate": 0.00019997394674923857, "loss": 0.760850477218628, "step": 53950 }, { "epoch": 0.3207494457026351, "grad_norm": 1.7794245481491089, "learning_rate": 0.00019997379676689746, "loss": 0.7054713726043701, "step": 53960 }, { "epoch": 0.32080888777930344, "grad_norm": 1.6465786695480347, "learning_rate": 0.00019997364635415107, "loss": 0.675565528869629, "step": 53970 }, { "epoch": 0.32086832985597186, "grad_norm": 1.5489494800567627, "learning_rate": 0.00019997349551100014, "loss": 0.658564567565918, "step": 53980 }, { "epoch": 0.3209277719326402, "grad_norm": 1.6400997638702393, "learning_rate": 0.00019997334423744548, "loss": 0.731249475479126, "step": 53990 }, { "epoch": 0.32098721400930863, "grad_norm": 2.038287878036499, "learning_rate": 0.0001999731925334877, "loss": 0.6921232223510743, "step": 54000 }, { "epoch": 0.32104665608597704, "grad_norm": 1.6829047203063965, "learning_rate": 0.00019997304039912756, "loss": 0.7189025402069091, "step": 54010 }, { "epoch": 0.3211060981626454, "grad_norm": 2.049072265625, "learning_rate": 0.00019997288783436582, "loss": 0.7095699310302734, "step": 54020 }, { "epoch": 0.3211655402393138, "grad_norm": 2.065579652786255, "learning_rate": 0.0001999727348392032, "loss": 0.7612899303436279, "step": 54030 }, { "epoch": 0.3212249823159822, "grad_norm": 1.8033525943756104, "learning_rate": 0.00019997258141364038, "loss": 0.6877772331237793, "step": 54040 }, { "epoch": 0.3212844243926506, "grad_norm": 1.659134030342102, "learning_rate": 0.00019997242755767818, "loss": 0.7118932723999023, "step": 54050 }, { "epoch": 0.32134386646931895, "grad_norm": 1.7943130731582642, "learning_rate": 0.00019997227327131725, "loss": 0.7143675804138183, "step": 54060 }, { "epoch": 0.32140330854598737, "grad_norm": 2.1757569313049316, "learning_rate": 0.0001999721185545584, "loss": 0.7293465614318848, "step": 54070 }, { "epoch": 0.3214627506226558, "grad_norm": 1.7975029945373535, "learning_rate": 0.00019997196340740232, "loss": 0.6832552909851074, "step": 54080 }, { "epoch": 0.32152219269932414, "grad_norm": 1.9428242444992065, "learning_rate": 0.00019997180782984974, "loss": 0.636537742614746, "step": 54090 }, { "epoch": 0.32158163477599255, "grad_norm": 1.857420802116394, "learning_rate": 0.0001999716518219015, "loss": 0.7270736694335938, "step": 54100 }, { "epoch": 0.3216410768526609, "grad_norm": 1.6773825883865356, "learning_rate": 0.00019997149538355824, "loss": 0.6796849250793457, "step": 54110 }, { "epoch": 0.3217005189293293, "grad_norm": 1.876146674156189, "learning_rate": 0.00019997133851482076, "loss": 0.6737292766571045, "step": 54120 }, { "epoch": 0.3217599610059977, "grad_norm": 2.0284945964813232, "learning_rate": 0.0001999711812156898, "loss": 0.6979694843292237, "step": 54130 }, { "epoch": 0.3218194030826661, "grad_norm": 1.8757483959197998, "learning_rate": 0.00019997102348616612, "loss": 0.713629150390625, "step": 54140 }, { "epoch": 0.32187884515933446, "grad_norm": 2.01857328414917, "learning_rate": 0.00019997086532625046, "loss": 0.7402803421020507, "step": 54150 }, { "epoch": 0.3219382872360029, "grad_norm": 1.6707780361175537, "learning_rate": 0.00019997070673594356, "loss": 0.611914873123169, "step": 54160 }, { "epoch": 0.3219977293126713, "grad_norm": 1.7698501348495483, "learning_rate": 0.0001999705477152462, "loss": 0.6883715629577637, "step": 54170 }, { "epoch": 0.32205717138933965, "grad_norm": 2.104614496231079, "learning_rate": 0.00019997038826415918, "loss": 0.7177040100097656, "step": 54180 }, { "epoch": 0.32211661346600806, "grad_norm": 2.128509521484375, "learning_rate": 0.00019997022838268323, "loss": 0.7249288558959961, "step": 54190 }, { "epoch": 0.3221760555426764, "grad_norm": 1.736808180809021, "learning_rate": 0.00019997006807081908, "loss": 0.6897433280944825, "step": 54200 }, { "epoch": 0.32223549761934484, "grad_norm": 2.0160350799560547, "learning_rate": 0.00019996990732856754, "loss": 0.6862137317657471, "step": 54210 }, { "epoch": 0.3222949396960132, "grad_norm": 2.0747714042663574, "learning_rate": 0.00019996974615592934, "loss": 0.7109604835510254, "step": 54220 }, { "epoch": 0.3223543817726816, "grad_norm": 1.7323799133300781, "learning_rate": 0.0001999695845529053, "loss": 0.7162636756896973, "step": 54230 }, { "epoch": 0.32241382384935, "grad_norm": 1.9081376791000366, "learning_rate": 0.00019996942251949618, "loss": 0.6426451683044434, "step": 54240 }, { "epoch": 0.3224732659260184, "grad_norm": 1.613227128982544, "learning_rate": 0.00019996926005570273, "loss": 0.6634174346923828, "step": 54250 }, { "epoch": 0.3225327080026868, "grad_norm": 1.5201506614685059, "learning_rate": 0.00019996909716152574, "loss": 0.6919990539550781, "step": 54260 }, { "epoch": 0.32259215007935516, "grad_norm": 1.3458219766616821, "learning_rate": 0.000199968933836966, "loss": 0.6567068099975586, "step": 54270 }, { "epoch": 0.32265159215602357, "grad_norm": 2.266270399093628, "learning_rate": 0.00019996877008202427, "loss": 0.7186493873596191, "step": 54280 }, { "epoch": 0.32271103423269193, "grad_norm": 2.143160104751587, "learning_rate": 0.00019996860589670138, "loss": 0.6563308715820313, "step": 54290 }, { "epoch": 0.32277047630936034, "grad_norm": 1.8567752838134766, "learning_rate": 0.00019996844128099804, "loss": 0.7100537776947021, "step": 54300 }, { "epoch": 0.32282991838602876, "grad_norm": 2.0761451721191406, "learning_rate": 0.0001999682762349151, "loss": 0.7034743785858154, "step": 54310 }, { "epoch": 0.3228893604626971, "grad_norm": 1.675884485244751, "learning_rate": 0.00019996811075845332, "loss": 0.7540754318237305, "step": 54320 }, { "epoch": 0.32294880253936553, "grad_norm": 1.4678293466567993, "learning_rate": 0.00019996794485161349, "loss": 0.6314423561096192, "step": 54330 }, { "epoch": 0.3230082446160339, "grad_norm": 3.483696937561035, "learning_rate": 0.00019996777851439643, "loss": 0.7137313842773437, "step": 54340 }, { "epoch": 0.3230676866927023, "grad_norm": 1.655919075012207, "learning_rate": 0.00019996761174680293, "loss": 0.6519026756286621, "step": 54350 }, { "epoch": 0.32312712876937066, "grad_norm": 2.0373361110687256, "learning_rate": 0.00019996744454883376, "loss": 0.7436599731445312, "step": 54360 }, { "epoch": 0.3231865708460391, "grad_norm": 1.9878181219100952, "learning_rate": 0.00019996727692048974, "loss": 0.6369076728820801, "step": 54370 }, { "epoch": 0.3232460129227075, "grad_norm": 2.0520997047424316, "learning_rate": 0.00019996710886177168, "loss": 0.6835112571716309, "step": 54380 }, { "epoch": 0.32330545499937585, "grad_norm": 1.7766919136047363, "learning_rate": 0.00019996694037268035, "loss": 0.6816304206848145, "step": 54390 }, { "epoch": 0.32336489707604427, "grad_norm": 1.7757174968719482, "learning_rate": 0.0001999667714532166, "loss": 0.6585603713989258, "step": 54400 }, { "epoch": 0.3234243391527126, "grad_norm": 2.0217902660369873, "learning_rate": 0.0001999666021033812, "loss": 0.717679786682129, "step": 54410 }, { "epoch": 0.32348378122938104, "grad_norm": 1.6973854303359985, "learning_rate": 0.00019996643232317497, "loss": 0.7167343139648438, "step": 54420 }, { "epoch": 0.3235432233060494, "grad_norm": 1.531774878501892, "learning_rate": 0.00019996626211259876, "loss": 0.6949169635772705, "step": 54430 }, { "epoch": 0.3236026653827178, "grad_norm": 1.8064533472061157, "learning_rate": 0.00019996609147165332, "loss": 0.6878658294677734, "step": 54440 }, { "epoch": 0.32366210745938623, "grad_norm": 1.6498793363571167, "learning_rate": 0.00019996592040033955, "loss": 0.7044102191925049, "step": 54450 }, { "epoch": 0.3237215495360546, "grad_norm": 2.226121664047241, "learning_rate": 0.00019996574889865818, "loss": 0.741031551361084, "step": 54460 }, { "epoch": 0.323780991612723, "grad_norm": 2.0416109561920166, "learning_rate": 0.00019996557696661007, "loss": 0.7196696281433106, "step": 54470 }, { "epoch": 0.32384043368939136, "grad_norm": 1.8183668851852417, "learning_rate": 0.00019996540460419604, "loss": 0.6849706649780274, "step": 54480 }, { "epoch": 0.3238998757660598, "grad_norm": 1.834509253501892, "learning_rate": 0.00019996523181141693, "loss": 0.6431634902954102, "step": 54490 }, { "epoch": 0.32395931784272813, "grad_norm": 2.7678098678588867, "learning_rate": 0.00019996505858827353, "loss": 0.7271015644073486, "step": 54500 }, { "epoch": 0.32401875991939655, "grad_norm": 1.4372706413269043, "learning_rate": 0.00019996488493476673, "loss": 0.7299146175384521, "step": 54510 }, { "epoch": 0.3240782019960649, "grad_norm": 1.828857183456421, "learning_rate": 0.00019996471085089728, "loss": 0.7267567634582519, "step": 54520 }, { "epoch": 0.3241376440727333, "grad_norm": 2.0262975692749023, "learning_rate": 0.00019996453633666606, "loss": 0.7211625099182128, "step": 54530 }, { "epoch": 0.32419708614940174, "grad_norm": 2.059688091278076, "learning_rate": 0.00019996436139207394, "loss": 0.7113178253173829, "step": 54540 }, { "epoch": 0.3242565282260701, "grad_norm": 1.700425386428833, "learning_rate": 0.00019996418601712164, "loss": 0.702210807800293, "step": 54550 }, { "epoch": 0.3243159703027385, "grad_norm": 1.7560639381408691, "learning_rate": 0.00019996401021181011, "loss": 0.701198959350586, "step": 54560 }, { "epoch": 0.32437541237940687, "grad_norm": 1.2183047533035278, "learning_rate": 0.0001999638339761402, "loss": 0.6707064628601074, "step": 54570 }, { "epoch": 0.3244348544560753, "grad_norm": 2.047276735305786, "learning_rate": 0.00019996365731011267, "loss": 0.7676961898803711, "step": 54580 }, { "epoch": 0.32449429653274364, "grad_norm": 1.8143686056137085, "learning_rate": 0.0001999634802137284, "loss": 0.6943471908569336, "step": 54590 }, { "epoch": 0.32455373860941206, "grad_norm": 1.8882107734680176, "learning_rate": 0.00019996330268698824, "loss": 0.6790363788604736, "step": 54600 }, { "epoch": 0.32461318068608047, "grad_norm": 1.8774887323379517, "learning_rate": 0.00019996312472989305, "loss": 0.7142498970031739, "step": 54610 }, { "epoch": 0.32467262276274883, "grad_norm": 1.2744743824005127, "learning_rate": 0.00019996294634244365, "loss": 0.6841259002685547, "step": 54620 }, { "epoch": 0.32473206483941724, "grad_norm": 1.6851673126220703, "learning_rate": 0.00019996276752464094, "loss": 0.7177474021911621, "step": 54630 }, { "epoch": 0.3247915069160856, "grad_norm": 1.7030671834945679, "learning_rate": 0.00019996258827648575, "loss": 0.7389655113220215, "step": 54640 }, { "epoch": 0.324850948992754, "grad_norm": 1.9457725286483765, "learning_rate": 0.00019996240859797892, "loss": 0.7198446273803711, "step": 54650 }, { "epoch": 0.3249103910694224, "grad_norm": 1.6233539581298828, "learning_rate": 0.00019996222848912135, "loss": 0.7178207874298096, "step": 54660 }, { "epoch": 0.3249698331460908, "grad_norm": 1.6450929641723633, "learning_rate": 0.00019996204794991388, "loss": 0.6808614253997802, "step": 54670 }, { "epoch": 0.3250292752227592, "grad_norm": 1.9658230543136597, "learning_rate": 0.00019996186698035734, "loss": 0.7082130432128906, "step": 54680 }, { "epoch": 0.32508871729942757, "grad_norm": 1.8816580772399902, "learning_rate": 0.00019996168558045264, "loss": 0.6783509254455566, "step": 54690 }, { "epoch": 0.325148159376096, "grad_norm": 1.9841254949569702, "learning_rate": 0.00019996150375020067, "loss": 0.7398535251617432, "step": 54700 }, { "epoch": 0.32520760145276434, "grad_norm": 1.78174889087677, "learning_rate": 0.00019996132148960224, "loss": 0.7266346931457519, "step": 54710 }, { "epoch": 0.32526704352943275, "grad_norm": 1.405072808265686, "learning_rate": 0.00019996113879865824, "loss": 0.6687356472015381, "step": 54720 }, { "epoch": 0.3253264856061011, "grad_norm": 2.060145854949951, "learning_rate": 0.00019996095567736955, "loss": 0.7055771827697754, "step": 54730 }, { "epoch": 0.3253859276827695, "grad_norm": 1.6437017917633057, "learning_rate": 0.00019996077212573705, "loss": 0.7063991546630859, "step": 54740 }, { "epoch": 0.32544536975943794, "grad_norm": 1.6637532711029053, "learning_rate": 0.00019996058814376164, "loss": 0.6450447082519531, "step": 54750 }, { "epoch": 0.3255048118361063, "grad_norm": 1.8424838781356812, "learning_rate": 0.00019996040373144414, "loss": 0.6471617698669434, "step": 54760 }, { "epoch": 0.3255642539127747, "grad_norm": 1.9058257341384888, "learning_rate": 0.00019996021888878552, "loss": 0.6663699150085449, "step": 54770 }, { "epoch": 0.3256236959894431, "grad_norm": 1.7371727228164673, "learning_rate": 0.00019996003361578656, "loss": 0.7048281669616699, "step": 54780 }, { "epoch": 0.3256831380661115, "grad_norm": 1.8609187602996826, "learning_rate": 0.00019995984791244825, "loss": 0.6844698905944824, "step": 54790 }, { "epoch": 0.32574258014277985, "grad_norm": 1.8283706903457642, "learning_rate": 0.00019995966177877136, "loss": 0.7070446968078613, "step": 54800 }, { "epoch": 0.32580202221944826, "grad_norm": 1.8235769271850586, "learning_rate": 0.00019995947521475688, "loss": 0.6692949771881104, "step": 54810 }, { "epoch": 0.3258614642961167, "grad_norm": 1.9475269317626953, "learning_rate": 0.00019995928822040567, "loss": 0.7412710189819336, "step": 54820 }, { "epoch": 0.32592090637278504, "grad_norm": 2.061452627182007, "learning_rate": 0.00019995910079571863, "loss": 0.7208343505859375, "step": 54830 }, { "epoch": 0.32598034844945345, "grad_norm": 1.6832479238510132, "learning_rate": 0.00019995891294069667, "loss": 0.6892554283142089, "step": 54840 }, { "epoch": 0.3260397905261218, "grad_norm": 1.6582971811294556, "learning_rate": 0.00019995872465534062, "loss": 0.7847572803497315, "step": 54850 }, { "epoch": 0.3260992326027902, "grad_norm": 1.6193214654922485, "learning_rate": 0.0001999585359396515, "loss": 0.701838493347168, "step": 54860 }, { "epoch": 0.3261586746794586, "grad_norm": 1.41523277759552, "learning_rate": 0.00019995834679363005, "loss": 0.6255855083465576, "step": 54870 }, { "epoch": 0.326218116756127, "grad_norm": 1.7834837436676025, "learning_rate": 0.00019995815721727734, "loss": 0.7035200119018554, "step": 54880 }, { "epoch": 0.32627755883279536, "grad_norm": 1.4996142387390137, "learning_rate": 0.00019995796721059418, "loss": 0.6817874908447266, "step": 54890 }, { "epoch": 0.32633700090946377, "grad_norm": 1.4981154203414917, "learning_rate": 0.00019995777677358147, "loss": 0.6927059650421142, "step": 54900 }, { "epoch": 0.3263964429861322, "grad_norm": 1.6383514404296875, "learning_rate": 0.0001999575859062402, "loss": 0.6879481792449951, "step": 54910 }, { "epoch": 0.32645588506280054, "grad_norm": 1.5818278789520264, "learning_rate": 0.00019995739460857123, "loss": 0.6375346660614014, "step": 54920 }, { "epoch": 0.32651532713946896, "grad_norm": 1.4753823280334473, "learning_rate": 0.00019995720288057547, "loss": 0.6894145965576172, "step": 54930 }, { "epoch": 0.3265747692161373, "grad_norm": 1.8305253982543945, "learning_rate": 0.00019995701072225385, "loss": 0.6473195075988769, "step": 54940 }, { "epoch": 0.32663421129280573, "grad_norm": 1.6337804794311523, "learning_rate": 0.0001999568181336073, "loss": 0.6516558647155761, "step": 54950 }, { "epoch": 0.3266936533694741, "grad_norm": 1.8492305278778076, "learning_rate": 0.00019995662511463673, "loss": 0.7235064506530762, "step": 54960 }, { "epoch": 0.3267530954461425, "grad_norm": 1.615116000175476, "learning_rate": 0.00019995643166534309, "loss": 0.6449501037597656, "step": 54970 }, { "epoch": 0.3268125375228109, "grad_norm": 2.242929697036743, "learning_rate": 0.00019995623778572722, "loss": 0.7482322692871094, "step": 54980 }, { "epoch": 0.3268719795994793, "grad_norm": 1.5265611410140991, "learning_rate": 0.00019995604347579016, "loss": 0.7134758949279785, "step": 54990 }, { "epoch": 0.3269314216761477, "grad_norm": 1.702807068824768, "learning_rate": 0.00019995584873553273, "loss": 0.7037149429321289, "step": 55000 }, { "epoch": 0.32699086375281605, "grad_norm": 1.8212878704071045, "learning_rate": 0.00019995565356495596, "loss": 0.71201171875, "step": 55010 }, { "epoch": 0.32705030582948447, "grad_norm": 2.2490901947021484, "learning_rate": 0.00019995545796406075, "loss": 0.6771245956420898, "step": 55020 }, { "epoch": 0.3271097479061528, "grad_norm": 1.6520615816116333, "learning_rate": 0.000199955261932848, "loss": 0.6937475681304932, "step": 55030 }, { "epoch": 0.32716918998282124, "grad_norm": 1.376452922821045, "learning_rate": 0.0001999550654713187, "loss": 0.6439916133880615, "step": 55040 }, { "epoch": 0.32722863205948965, "grad_norm": 1.5183683633804321, "learning_rate": 0.00019995486857947374, "loss": 0.7023503303527832, "step": 55050 }, { "epoch": 0.327288074136158, "grad_norm": 1.0435223579406738, "learning_rate": 0.00019995467125731407, "loss": 0.6987231731414795, "step": 55060 }, { "epoch": 0.32734751621282643, "grad_norm": 1.464574933052063, "learning_rate": 0.0001999544735048407, "loss": 0.6643386840820312, "step": 55070 }, { "epoch": 0.3274069582894948, "grad_norm": 2.0242536067962646, "learning_rate": 0.00019995427532205448, "loss": 0.7448533058166504, "step": 55080 }, { "epoch": 0.3274664003661632, "grad_norm": 1.9064885377883911, "learning_rate": 0.00019995407670895642, "loss": 0.7026591777801514, "step": 55090 }, { "epoch": 0.32752584244283156, "grad_norm": 1.7397605180740356, "learning_rate": 0.00019995387766554744, "loss": 0.7003807067871094, "step": 55100 }, { "epoch": 0.3275852845195, "grad_norm": 1.5997962951660156, "learning_rate": 0.00019995367819182854, "loss": 0.6383294105529785, "step": 55110 }, { "epoch": 0.3276447265961684, "grad_norm": 2.136486053466797, "learning_rate": 0.00019995347828780062, "loss": 0.7141690254211426, "step": 55120 }, { "epoch": 0.32770416867283675, "grad_norm": 1.4681954383850098, "learning_rate": 0.0001999532779534647, "loss": 0.6910307884216309, "step": 55130 }, { "epoch": 0.32776361074950516, "grad_norm": 1.802888035774231, "learning_rate": 0.00019995307718882163, "loss": 0.732978343963623, "step": 55140 }, { "epoch": 0.3278230528261735, "grad_norm": 1.554772973060608, "learning_rate": 0.00019995287599387248, "loss": 0.6994967460632324, "step": 55150 }, { "epoch": 0.32788249490284194, "grad_norm": 1.8033852577209473, "learning_rate": 0.00019995267436861814, "loss": 0.749073600769043, "step": 55160 }, { "epoch": 0.3279419369795103, "grad_norm": 1.4540719985961914, "learning_rate": 0.00019995247231305963, "loss": 0.7013561248779296, "step": 55170 }, { "epoch": 0.3280013790561787, "grad_norm": 1.732635259628296, "learning_rate": 0.00019995226982719787, "loss": 0.6587891578674316, "step": 55180 }, { "epoch": 0.3280608211328471, "grad_norm": 1.6269336938858032, "learning_rate": 0.00019995206691103386, "loss": 0.7097957134246826, "step": 55190 }, { "epoch": 0.3281202632095155, "grad_norm": 1.5995752811431885, "learning_rate": 0.00019995186356456854, "loss": 0.7159371852874756, "step": 55200 }, { "epoch": 0.3281797052861839, "grad_norm": 2.004310131072998, "learning_rate": 0.00019995165978780292, "loss": 0.722376012802124, "step": 55210 }, { "epoch": 0.32823914736285226, "grad_norm": 1.721862554550171, "learning_rate": 0.00019995145558073793, "loss": 0.64266939163208, "step": 55220 }, { "epoch": 0.32829858943952067, "grad_norm": 1.7323957681655884, "learning_rate": 0.0001999512509433746, "loss": 0.7104215621948242, "step": 55230 }, { "epoch": 0.32835803151618903, "grad_norm": 1.8947539329528809, "learning_rate": 0.00019995104587571387, "loss": 0.6564817428588867, "step": 55240 }, { "epoch": 0.32841747359285745, "grad_norm": 1.418912410736084, "learning_rate": 0.00019995084037775676, "loss": 0.7379932403564453, "step": 55250 }, { "epoch": 0.3284769156695258, "grad_norm": 1.887702226638794, "learning_rate": 0.00019995063444950417, "loss": 0.7312817573547363, "step": 55260 }, { "epoch": 0.3285363577461942, "grad_norm": 2.0305919647216797, "learning_rate": 0.00019995042809095717, "loss": 0.7333172798156739, "step": 55270 }, { "epoch": 0.32859579982286263, "grad_norm": 2.0120644569396973, "learning_rate": 0.00019995022130211672, "loss": 0.6785286426544189, "step": 55280 }, { "epoch": 0.328655241899531, "grad_norm": 1.4972738027572632, "learning_rate": 0.0001999500140829838, "loss": 0.6836143493652344, "step": 55290 }, { "epoch": 0.3287146839761994, "grad_norm": 1.8891671895980835, "learning_rate": 0.00019994980643355944, "loss": 0.7390511512756348, "step": 55300 }, { "epoch": 0.32877412605286777, "grad_norm": 1.4363375902175903, "learning_rate": 0.00019994959835384457, "loss": 0.644227409362793, "step": 55310 }, { "epoch": 0.3288335681295362, "grad_norm": 1.735851764678955, "learning_rate": 0.00019994938984384023, "loss": 0.7110679626464844, "step": 55320 }, { "epoch": 0.32889301020620454, "grad_norm": 2.0683462619781494, "learning_rate": 0.0001999491809035474, "loss": 0.724038028717041, "step": 55330 }, { "epoch": 0.32895245228287295, "grad_norm": 1.786290168762207, "learning_rate": 0.00019994897153296706, "loss": 0.7129065513610839, "step": 55340 }, { "epoch": 0.32901189435954137, "grad_norm": 1.984062910079956, "learning_rate": 0.00019994876173210025, "loss": 0.6860584259033203, "step": 55350 }, { "epoch": 0.3290713364362097, "grad_norm": 1.7953307628631592, "learning_rate": 0.000199948551500948, "loss": 0.7279940605163574, "step": 55360 }, { "epoch": 0.32913077851287814, "grad_norm": 1.4151345491409302, "learning_rate": 0.00019994834083951124, "loss": 0.6509696960449218, "step": 55370 }, { "epoch": 0.3291902205895465, "grad_norm": 1.7341303825378418, "learning_rate": 0.00019994812974779102, "loss": 0.7460495948791503, "step": 55380 }, { "epoch": 0.3292496626662149, "grad_norm": 1.83796226978302, "learning_rate": 0.00019994791822578836, "loss": 0.7500335216522217, "step": 55390 }, { "epoch": 0.3293091047428833, "grad_norm": 1.4437400102615356, "learning_rate": 0.00019994770627350424, "loss": 0.636776065826416, "step": 55400 }, { "epoch": 0.3293685468195517, "grad_norm": 1.8039228916168213, "learning_rate": 0.00019994749389093966, "loss": 0.6712106704711914, "step": 55410 }, { "epoch": 0.3294279888962201, "grad_norm": 1.9976210594177246, "learning_rate": 0.0001999472810780957, "loss": 0.6843944549560547, "step": 55420 }, { "epoch": 0.32948743097288846, "grad_norm": 1.9798333644866943, "learning_rate": 0.00019994706783497333, "loss": 0.7359257698059082, "step": 55430 }, { "epoch": 0.3295468730495569, "grad_norm": 1.4166958332061768, "learning_rate": 0.00019994685416157358, "loss": 0.7023770809173584, "step": 55440 }, { "epoch": 0.32960631512622524, "grad_norm": 1.7749667167663574, "learning_rate": 0.00019994664005789744, "loss": 0.703664493560791, "step": 55450 }, { "epoch": 0.32966575720289365, "grad_norm": 1.6895818710327148, "learning_rate": 0.00019994642552394602, "loss": 0.7180852890014648, "step": 55460 }, { "epoch": 0.329725199279562, "grad_norm": 1.6472926139831543, "learning_rate": 0.0001999462105597203, "loss": 0.6933043479919434, "step": 55470 }, { "epoch": 0.3297846413562304, "grad_norm": 2.196551561355591, "learning_rate": 0.0001999459951652213, "loss": 0.7514177799224854, "step": 55480 }, { "epoch": 0.32984408343289884, "grad_norm": 1.585482120513916, "learning_rate": 0.00019994577934045001, "loss": 0.6927252769470215, "step": 55490 }, { "epoch": 0.3299035255095672, "grad_norm": 2.0727124214172363, "learning_rate": 0.00019994556308540755, "loss": 0.6925975322723389, "step": 55500 }, { "epoch": 0.3299629675862356, "grad_norm": 1.674506664276123, "learning_rate": 0.0001999453464000949, "loss": 0.6985951423645019, "step": 55510 }, { "epoch": 0.33002240966290397, "grad_norm": 1.71348237991333, "learning_rate": 0.0001999451292845131, "loss": 0.703676414489746, "step": 55520 }, { "epoch": 0.3300818517395724, "grad_norm": 1.9574273824691772, "learning_rate": 0.0001999449117386632, "loss": 0.6627267837524414, "step": 55530 }, { "epoch": 0.33014129381624074, "grad_norm": 1.7729781866073608, "learning_rate": 0.0001999446937625462, "loss": 0.6915796279907227, "step": 55540 }, { "epoch": 0.33020073589290916, "grad_norm": 2.0586416721343994, "learning_rate": 0.00019994447535616323, "loss": 0.6880468368530274, "step": 55550 }, { "epoch": 0.3302601779695775, "grad_norm": 2.354484796524048, "learning_rate": 0.00019994425651951526, "loss": 0.726639986038208, "step": 55560 }, { "epoch": 0.33031962004624593, "grad_norm": 2.0535550117492676, "learning_rate": 0.00019994403725260337, "loss": 0.6608963489532471, "step": 55570 }, { "epoch": 0.33037906212291435, "grad_norm": 1.6772959232330322, "learning_rate": 0.00019994381755542864, "loss": 0.7142518043518067, "step": 55580 }, { "epoch": 0.3304385041995827, "grad_norm": 2.044846296310425, "learning_rate": 0.000199943597427992, "loss": 0.7414342403411865, "step": 55590 }, { "epoch": 0.3304979462762511, "grad_norm": 1.891924500465393, "learning_rate": 0.00019994337687029466, "loss": 0.7048761367797851, "step": 55600 }, { "epoch": 0.3305573883529195, "grad_norm": 1.5773786306381226, "learning_rate": 0.00019994315588233756, "loss": 0.696761178970337, "step": 55610 }, { "epoch": 0.3306168304295879, "grad_norm": 1.771237850189209, "learning_rate": 0.0001999429344641218, "loss": 0.7543212890625, "step": 55620 }, { "epoch": 0.33067627250625625, "grad_norm": 1.254392147064209, "learning_rate": 0.00019994271261564842, "loss": 0.7445137977600098, "step": 55630 }, { "epoch": 0.33073571458292467, "grad_norm": 1.7334858179092407, "learning_rate": 0.0001999424903369185, "loss": 0.6860342025756836, "step": 55640 }, { "epoch": 0.3307951566595931, "grad_norm": 1.7157225608825684, "learning_rate": 0.00019994226762793312, "loss": 0.7075961112976075, "step": 55650 }, { "epoch": 0.33085459873626144, "grad_norm": 1.6285974979400635, "learning_rate": 0.00019994204448869332, "loss": 0.7700872421264648, "step": 55660 }, { "epoch": 0.33091404081292985, "grad_norm": 1.7175012826919556, "learning_rate": 0.00019994182091920016, "loss": 0.7166945457458496, "step": 55670 }, { "epoch": 0.3309734828895982, "grad_norm": 1.4753767251968384, "learning_rate": 0.00019994159691945473, "loss": 0.6968374252319336, "step": 55680 }, { "epoch": 0.33103292496626663, "grad_norm": 1.93147611618042, "learning_rate": 0.0001999413724894581, "loss": 0.666502857208252, "step": 55690 }, { "epoch": 0.331092367042935, "grad_norm": 1.394207239151001, "learning_rate": 0.00019994114762921132, "loss": 0.6840189933776856, "step": 55700 }, { "epoch": 0.3311518091196034, "grad_norm": 2.1211514472961426, "learning_rate": 0.0001999409223387155, "loss": 0.7036625862121582, "step": 55710 }, { "epoch": 0.3312112511962718, "grad_norm": 1.7719804048538208, "learning_rate": 0.00019994069661797168, "loss": 0.6839725494384765, "step": 55720 }, { "epoch": 0.3312706932729402, "grad_norm": 1.5493850708007812, "learning_rate": 0.00019994047046698098, "loss": 0.6967226028442383, "step": 55730 }, { "epoch": 0.3313301353496086, "grad_norm": 1.7017508745193481, "learning_rate": 0.00019994024388574446, "loss": 0.6557155609130859, "step": 55740 }, { "epoch": 0.33138957742627695, "grad_norm": 1.9280622005462646, "learning_rate": 0.0001999400168742632, "loss": 0.703480577468872, "step": 55750 }, { "epoch": 0.33144901950294536, "grad_norm": 1.650862693786621, "learning_rate": 0.0001999397894325383, "loss": 0.6759389400482178, "step": 55760 }, { "epoch": 0.3315084615796137, "grad_norm": 1.7521729469299316, "learning_rate": 0.00019993956156057083, "loss": 0.7004308700561523, "step": 55770 }, { "epoch": 0.33156790365628214, "grad_norm": 1.5967131853103638, "learning_rate": 0.0001999393332583619, "loss": 0.7266307830810547, "step": 55780 }, { "epoch": 0.33162734573295055, "grad_norm": 1.5187361240386963, "learning_rate": 0.00019993910452591258, "loss": 0.6771790504455566, "step": 55790 }, { "epoch": 0.3316867878096189, "grad_norm": 2.0693225860595703, "learning_rate": 0.000199938875363224, "loss": 0.7723348140716553, "step": 55800 }, { "epoch": 0.3317462298862873, "grad_norm": 1.6049911975860596, "learning_rate": 0.0001999386457702972, "loss": 0.7363841533660889, "step": 55810 }, { "epoch": 0.3318056719629557, "grad_norm": 2.043649196624756, "learning_rate": 0.00019993841574713332, "loss": 0.7388016700744628, "step": 55820 }, { "epoch": 0.3318651140396241, "grad_norm": 1.7746329307556152, "learning_rate": 0.00019993818529373346, "loss": 0.719712495803833, "step": 55830 }, { "epoch": 0.33192455611629246, "grad_norm": 2.278057336807251, "learning_rate": 0.00019993795441009872, "loss": 0.7129825115203857, "step": 55840 }, { "epoch": 0.33198399819296087, "grad_norm": 1.6284183263778687, "learning_rate": 0.00019993772309623018, "loss": 0.7124987602233886, "step": 55850 }, { "epoch": 0.3320434402696293, "grad_norm": 1.721274495124817, "learning_rate": 0.00019993749135212898, "loss": 0.6988723754882813, "step": 55860 }, { "epoch": 0.33210288234629765, "grad_norm": 1.796507716178894, "learning_rate": 0.00019993725917779622, "loss": 0.6575476169586182, "step": 55870 }, { "epoch": 0.33216232442296606, "grad_norm": 1.766049861907959, "learning_rate": 0.000199937026573233, "loss": 0.7351811408996582, "step": 55880 }, { "epoch": 0.3322217664996344, "grad_norm": 2.085184335708618, "learning_rate": 0.00019993679353844045, "loss": 0.7059134483337403, "step": 55890 }, { "epoch": 0.33228120857630283, "grad_norm": 1.7637156248092651, "learning_rate": 0.0001999365600734196, "loss": 0.7441253662109375, "step": 55900 }, { "epoch": 0.3323406506529712, "grad_norm": 1.7260738611221313, "learning_rate": 0.00019993632617817172, "loss": 0.6081738471984863, "step": 55910 }, { "epoch": 0.3324000927296396, "grad_norm": 1.5282200574874878, "learning_rate": 0.0001999360918526978, "loss": 0.7169168949127197, "step": 55920 }, { "epoch": 0.33245953480630797, "grad_norm": 1.5424221754074097, "learning_rate": 0.00019993585709699905, "loss": 0.7897208213806153, "step": 55930 }, { "epoch": 0.3325189768829764, "grad_norm": 1.9797347784042358, "learning_rate": 0.0001999356219110765, "loss": 0.654279088973999, "step": 55940 }, { "epoch": 0.3325784189596448, "grad_norm": 1.316580057144165, "learning_rate": 0.00019993538629493133, "loss": 0.7382814407348632, "step": 55950 }, { "epoch": 0.33263786103631315, "grad_norm": 1.835219144821167, "learning_rate": 0.0001999351502485647, "loss": 0.6732919216156006, "step": 55960 }, { "epoch": 0.33269730311298157, "grad_norm": 1.8176558017730713, "learning_rate": 0.0001999349137719777, "loss": 0.7270134449005127, "step": 55970 }, { "epoch": 0.3327567451896499, "grad_norm": 1.8105829954147339, "learning_rate": 0.00019993467686517144, "loss": 0.7119657516479492, "step": 55980 }, { "epoch": 0.33281618726631834, "grad_norm": 1.9158389568328857, "learning_rate": 0.0001999344395281471, "loss": 0.7044049263000488, "step": 55990 }, { "epoch": 0.3328756293429867, "grad_norm": 1.6293312311172485, "learning_rate": 0.00019993420176090575, "loss": 0.6662217140197754, "step": 56000 }, { "epoch": 0.3329350714196551, "grad_norm": 1.5143728256225586, "learning_rate": 0.0001999339635634486, "loss": 0.6519811153411865, "step": 56010 }, { "epoch": 0.33299451349632353, "grad_norm": 1.6684569120407104, "learning_rate": 0.00019993372493577678, "loss": 0.6856963157653808, "step": 56020 }, { "epoch": 0.3330539555729919, "grad_norm": 1.8650068044662476, "learning_rate": 0.00019993348587789137, "loss": 0.7219738483428955, "step": 56030 }, { "epoch": 0.3331133976496603, "grad_norm": 1.7309726476669312, "learning_rate": 0.0001999332463897936, "loss": 0.6869508266448975, "step": 56040 }, { "epoch": 0.33317283972632866, "grad_norm": 1.4940210580825806, "learning_rate": 0.00019993300647148452, "loss": 0.6724638938903809, "step": 56050 }, { "epoch": 0.3332322818029971, "grad_norm": 2.062713861465454, "learning_rate": 0.00019993276612296533, "loss": 0.6710480213165283, "step": 56060 }, { "epoch": 0.33329172387966544, "grad_norm": 1.6891520023345947, "learning_rate": 0.00019993252534423718, "loss": 0.6930178642272949, "step": 56070 }, { "epoch": 0.33335116595633385, "grad_norm": 1.4183706045150757, "learning_rate": 0.00019993228413530125, "loss": 0.7184609413146973, "step": 56080 }, { "epoch": 0.33341060803300226, "grad_norm": 1.7431583404541016, "learning_rate": 0.00019993204249615866, "loss": 0.6048845291137696, "step": 56090 }, { "epoch": 0.3334700501096706, "grad_norm": 1.6083794832229614, "learning_rate": 0.00019993180042681053, "loss": 0.6875763416290284, "step": 56100 }, { "epoch": 0.33352949218633904, "grad_norm": 1.5335029363632202, "learning_rate": 0.0001999315579272581, "loss": 0.674256420135498, "step": 56110 }, { "epoch": 0.3335889342630074, "grad_norm": 1.8139290809631348, "learning_rate": 0.00019993131499750248, "loss": 0.6860599517822266, "step": 56120 }, { "epoch": 0.3336483763396758, "grad_norm": 1.9143043756484985, "learning_rate": 0.00019993107163754483, "loss": 0.6571300983428955, "step": 56130 }, { "epoch": 0.33370781841634417, "grad_norm": 1.8781296014785767, "learning_rate": 0.0001999308278473863, "loss": 0.679265308380127, "step": 56140 }, { "epoch": 0.3337672604930126, "grad_norm": 1.7904895544052124, "learning_rate": 0.00019993058362702815, "loss": 0.6794212341308594, "step": 56150 }, { "epoch": 0.333826702569681, "grad_norm": 1.8179423809051514, "learning_rate": 0.0001999303389764714, "loss": 0.676552677154541, "step": 56160 }, { "epoch": 0.33388614464634936, "grad_norm": 1.5879164934158325, "learning_rate": 0.00019993009389571734, "loss": 0.707176399230957, "step": 56170 }, { "epoch": 0.3339455867230178, "grad_norm": 1.9778881072998047, "learning_rate": 0.00019992984838476706, "loss": 0.713578462600708, "step": 56180 }, { "epoch": 0.33400502879968613, "grad_norm": 1.8639025688171387, "learning_rate": 0.00019992960244362182, "loss": 0.7481829643249511, "step": 56190 }, { "epoch": 0.33406447087635455, "grad_norm": 1.7057360410690308, "learning_rate": 0.00019992935607228275, "loss": 0.6617277145385743, "step": 56200 }, { "epoch": 0.3341239129530229, "grad_norm": 1.585323452949524, "learning_rate": 0.00019992910927075098, "loss": 0.6805950164794922, "step": 56210 }, { "epoch": 0.3341833550296913, "grad_norm": 1.9067310094833374, "learning_rate": 0.0001999288620390278, "loss": 0.7162078857421875, "step": 56220 }, { "epoch": 0.33424279710635973, "grad_norm": 1.6401790380477905, "learning_rate": 0.0001999286143771143, "loss": 0.7241159439086914, "step": 56230 }, { "epoch": 0.3343022391830281, "grad_norm": 1.3541737794876099, "learning_rate": 0.0001999283662850117, "loss": 0.6851946830749511, "step": 56240 }, { "epoch": 0.3343616812596965, "grad_norm": 1.6944252252578735, "learning_rate": 0.0001999281177627212, "loss": 0.6804962158203125, "step": 56250 }, { "epoch": 0.33442112333636487, "grad_norm": 1.5018631219863892, "learning_rate": 0.00019992786881024396, "loss": 0.7498833656311035, "step": 56260 }, { "epoch": 0.3344805654130333, "grad_norm": 1.8861855268478394, "learning_rate": 0.0001999276194275812, "loss": 0.7499279975891113, "step": 56270 }, { "epoch": 0.33454000748970164, "grad_norm": 1.6770048141479492, "learning_rate": 0.00019992736961473405, "loss": 0.6881246089935302, "step": 56280 }, { "epoch": 0.33459944956637006, "grad_norm": 1.491219162940979, "learning_rate": 0.00019992711937170382, "loss": 0.6967143058776856, "step": 56290 }, { "epoch": 0.3346588916430384, "grad_norm": 1.482120394706726, "learning_rate": 0.00019992686869849157, "loss": 0.6786351203918457, "step": 56300 }, { "epoch": 0.33471833371970683, "grad_norm": 2.2255923748016357, "learning_rate": 0.00019992661759509863, "loss": 0.7052289962768554, "step": 56310 }, { "epoch": 0.33477777579637524, "grad_norm": 1.8137646913528442, "learning_rate": 0.0001999263660615261, "loss": 0.7602273464202881, "step": 56320 }, { "epoch": 0.3348372178730436, "grad_norm": 1.620311975479126, "learning_rate": 0.00019992611409777524, "loss": 0.6838942527770996, "step": 56330 }, { "epoch": 0.334896659949712, "grad_norm": 1.7688612937927246, "learning_rate": 0.00019992586170384724, "loss": 0.6697701454162598, "step": 56340 }, { "epoch": 0.3349561020263804, "grad_norm": 2.049855947494507, "learning_rate": 0.0001999256088797433, "loss": 0.7710680961608887, "step": 56350 }, { "epoch": 0.3350155441030488, "grad_norm": 1.8631486892700195, "learning_rate": 0.00019992535562546464, "loss": 0.6874510765075683, "step": 56360 }, { "epoch": 0.33507498617971715, "grad_norm": 1.7256953716278076, "learning_rate": 0.00019992510194101246, "loss": 0.7192838191986084, "step": 56370 }, { "epoch": 0.33513442825638556, "grad_norm": 1.575482964515686, "learning_rate": 0.000199924847826388, "loss": 0.6472608566284179, "step": 56380 }, { "epoch": 0.335193870333054, "grad_norm": 1.583616018295288, "learning_rate": 0.00019992459328159245, "loss": 0.7175150871276855, "step": 56390 }, { "epoch": 0.33525331240972234, "grad_norm": 1.796525001525879, "learning_rate": 0.000199924338306627, "loss": 0.6751889228820801, "step": 56400 }, { "epoch": 0.33531275448639075, "grad_norm": 1.8998085260391235, "learning_rate": 0.00019992408290149294, "loss": 0.693284559249878, "step": 56410 }, { "epoch": 0.3353721965630591, "grad_norm": 1.9425104856491089, "learning_rate": 0.00019992382706619143, "loss": 0.6908675193786621, "step": 56420 }, { "epoch": 0.3354316386397275, "grad_norm": 1.4690860509872437, "learning_rate": 0.00019992357080072373, "loss": 0.7161746978759765, "step": 56430 }, { "epoch": 0.3354910807163959, "grad_norm": 1.766098141670227, "learning_rate": 0.00019992331410509105, "loss": 0.7078165531158447, "step": 56440 }, { "epoch": 0.3355505227930643, "grad_norm": 1.6673274040222168, "learning_rate": 0.00019992305697929464, "loss": 0.6537364959716797, "step": 56450 }, { "epoch": 0.3356099648697327, "grad_norm": 1.5226836204528809, "learning_rate": 0.0001999227994233357, "loss": 0.6582602024078369, "step": 56460 }, { "epoch": 0.33566940694640107, "grad_norm": 1.63326096534729, "learning_rate": 0.00019992254143721546, "loss": 0.6588973522186279, "step": 56470 }, { "epoch": 0.3357288490230695, "grad_norm": 1.8645198345184326, "learning_rate": 0.0001999222830209352, "loss": 0.7340549468994141, "step": 56480 }, { "epoch": 0.33578829109973785, "grad_norm": 2.1028122901916504, "learning_rate": 0.0001999220241744961, "loss": 0.7597524642944335, "step": 56490 }, { "epoch": 0.33584773317640626, "grad_norm": 1.8157408237457275, "learning_rate": 0.00019992176489789943, "loss": 0.6985279083251953, "step": 56500 }, { "epoch": 0.3359071752530746, "grad_norm": 2.2447144985198975, "learning_rate": 0.00019992150519114642, "loss": 0.7100961208343506, "step": 56510 }, { "epoch": 0.33596661732974303, "grad_norm": 2.0921826362609863, "learning_rate": 0.0001999212450542383, "loss": 0.7029587745666503, "step": 56520 }, { "epoch": 0.33602605940641145, "grad_norm": 1.6921534538269043, "learning_rate": 0.00019992098448717635, "loss": 0.6413596153259278, "step": 56530 }, { "epoch": 0.3360855014830798, "grad_norm": 1.4698814153671265, "learning_rate": 0.0001999207234899618, "loss": 0.6437472343444824, "step": 56540 }, { "epoch": 0.3361449435597482, "grad_norm": 1.3742700815200806, "learning_rate": 0.00019992046206259592, "loss": 0.6656634330749511, "step": 56550 }, { "epoch": 0.3362043856364166, "grad_norm": 1.8114657402038574, "learning_rate": 0.0001999202002050799, "loss": 0.6734271049499512, "step": 56560 }, { "epoch": 0.336263827713085, "grad_norm": 1.6552846431732178, "learning_rate": 0.00019991993791741505, "loss": 0.7052432060241699, "step": 56570 }, { "epoch": 0.33632326978975335, "grad_norm": 1.5796072483062744, "learning_rate": 0.0001999196751996026, "loss": 0.7038755893707276, "step": 56580 }, { "epoch": 0.33638271186642177, "grad_norm": 2.0179691314697266, "learning_rate": 0.00019991941205164376, "loss": 0.68251051902771, "step": 56590 }, { "epoch": 0.3364421539430902, "grad_norm": 2.112253427505493, "learning_rate": 0.0001999191484735399, "loss": 0.6379875659942627, "step": 56600 }, { "epoch": 0.33650159601975854, "grad_norm": 1.9439414739608765, "learning_rate": 0.00019991888446529218, "loss": 0.7530172824859619, "step": 56610 }, { "epoch": 0.33656103809642696, "grad_norm": 1.3763725757598877, "learning_rate": 0.00019991862002690194, "loss": 0.6313677787780761, "step": 56620 }, { "epoch": 0.3366204801730953, "grad_norm": 1.7996433973312378, "learning_rate": 0.0001999183551583704, "loss": 0.6942716598510742, "step": 56630 }, { "epoch": 0.33667992224976373, "grad_norm": 1.644507646560669, "learning_rate": 0.0001999180898596988, "loss": 0.7617524147033692, "step": 56640 }, { "epoch": 0.3367393643264321, "grad_norm": 1.694220781326294, "learning_rate": 0.00019991782413088848, "loss": 0.7432996749877929, "step": 56650 }, { "epoch": 0.3367988064031005, "grad_norm": 1.5261561870574951, "learning_rate": 0.00019991755797194063, "loss": 0.6375659942626953, "step": 56660 }, { "epoch": 0.33685824847976886, "grad_norm": 1.8517764806747437, "learning_rate": 0.00019991729138285662, "loss": 0.7066095352172852, "step": 56670 }, { "epoch": 0.3369176905564373, "grad_norm": 1.5567728281021118, "learning_rate": 0.00019991702436363766, "loss": 0.7144447326660156, "step": 56680 }, { "epoch": 0.3369771326331057, "grad_norm": 2.074505090713501, "learning_rate": 0.000199916756914285, "loss": 0.6530375480651855, "step": 56690 }, { "epoch": 0.33703657470977405, "grad_norm": 2.031881809234619, "learning_rate": 0.00019991648903480003, "loss": 0.7083245754241944, "step": 56700 }, { "epoch": 0.33709601678644247, "grad_norm": 2.3121120929718018, "learning_rate": 0.00019991622072518391, "loss": 0.7591127395629883, "step": 56710 }, { "epoch": 0.3371554588631108, "grad_norm": 1.4756768941879272, "learning_rate": 0.000199915951985438, "loss": 0.7580607414245606, "step": 56720 }, { "epoch": 0.33721490093977924, "grad_norm": 2.2841718196868896, "learning_rate": 0.00019991568281556353, "loss": 0.738742446899414, "step": 56730 }, { "epoch": 0.3372743430164476, "grad_norm": 1.4369982481002808, "learning_rate": 0.00019991541321556186, "loss": 0.6970608711242676, "step": 56740 }, { "epoch": 0.337333785093116, "grad_norm": 1.5868487358093262, "learning_rate": 0.0001999151431854342, "loss": 0.7011621475219727, "step": 56750 }, { "epoch": 0.3373932271697844, "grad_norm": 1.3407621383666992, "learning_rate": 0.0001999148727251819, "loss": 0.6037239074707031, "step": 56760 }, { "epoch": 0.3374526692464528, "grad_norm": 2.075805902481079, "learning_rate": 0.00019991460183480623, "loss": 0.6671803951263428, "step": 56770 }, { "epoch": 0.3375121113231212, "grad_norm": 1.6300482749938965, "learning_rate": 0.00019991433051430848, "loss": 0.6339962005615234, "step": 56780 }, { "epoch": 0.33757155339978956, "grad_norm": 1.8995379209518433, "learning_rate": 0.00019991405876368997, "loss": 0.6763385772705078, "step": 56790 }, { "epoch": 0.337630995476458, "grad_norm": 1.9204317331314087, "learning_rate": 0.00019991378658295198, "loss": 0.5591437339782714, "step": 56800 }, { "epoch": 0.33769043755312633, "grad_norm": 2.014455795288086, "learning_rate": 0.00019991351397209584, "loss": 0.6848421573638916, "step": 56810 }, { "epoch": 0.33774987962979475, "grad_norm": 1.5119991302490234, "learning_rate": 0.0001999132409311228, "loss": 0.6870867252349854, "step": 56820 }, { "epoch": 0.33780932170646316, "grad_norm": 1.8516758680343628, "learning_rate": 0.00019991296746003424, "loss": 0.6336938858032226, "step": 56830 }, { "epoch": 0.3378687637831315, "grad_norm": 1.7031385898590088, "learning_rate": 0.0001999126935588314, "loss": 0.6605491638183594, "step": 56840 }, { "epoch": 0.33792820585979993, "grad_norm": 1.5983277559280396, "learning_rate": 0.00019991241922751564, "loss": 0.7374351978302002, "step": 56850 }, { "epoch": 0.3379876479364683, "grad_norm": 1.968632698059082, "learning_rate": 0.00019991214446608821, "loss": 0.7039785861968995, "step": 56860 }, { "epoch": 0.3380470900131367, "grad_norm": 1.7569057941436768, "learning_rate": 0.00019991186927455044, "loss": 0.7340636253356934, "step": 56870 }, { "epoch": 0.33810653208980507, "grad_norm": 2.316131353378296, "learning_rate": 0.00019991159365290376, "loss": 0.7151530265808106, "step": 56880 }, { "epoch": 0.3381659741664735, "grad_norm": 1.6607290506362915, "learning_rate": 0.00019991131760114934, "loss": 0.7097595691680908, "step": 56890 }, { "epoch": 0.3382254162431419, "grad_norm": 1.715834617614746, "learning_rate": 0.00019991104111928857, "loss": 0.6722547531127929, "step": 56900 }, { "epoch": 0.33828485831981026, "grad_norm": 1.6422388553619385, "learning_rate": 0.00019991076420732275, "loss": 0.7718435764312744, "step": 56910 }, { "epoch": 0.33834430039647867, "grad_norm": 2.0406506061553955, "learning_rate": 0.00019991048686525325, "loss": 0.7419639587402344, "step": 56920 }, { "epoch": 0.33840374247314703, "grad_norm": 1.705295205116272, "learning_rate": 0.00019991020909308137, "loss": 0.5939669609069824, "step": 56930 }, { "epoch": 0.33846318454981544, "grad_norm": 1.3972480297088623, "learning_rate": 0.0001999099308908084, "loss": 0.7236207962036133, "step": 56940 }, { "epoch": 0.3385226266264838, "grad_norm": 1.7992932796478271, "learning_rate": 0.00019990965225843573, "loss": 0.7017840385437012, "step": 56950 }, { "epoch": 0.3385820687031522, "grad_norm": 1.5880285501480103, "learning_rate": 0.00019990937319596462, "loss": 0.6617416858673095, "step": 56960 }, { "epoch": 0.33864151077982063, "grad_norm": 1.7995346784591675, "learning_rate": 0.0001999090937033965, "loss": 0.678168773651123, "step": 56970 }, { "epoch": 0.338700952856489, "grad_norm": 1.4868013858795166, "learning_rate": 0.00019990881378073266, "loss": 0.6321782112121582, "step": 56980 }, { "epoch": 0.3387603949331574, "grad_norm": 1.6923973560333252, "learning_rate": 0.0001999085334279744, "loss": 0.7013605117797852, "step": 56990 }, { "epoch": 0.33881983700982576, "grad_norm": 1.5158427953720093, "learning_rate": 0.0001999082526451231, "loss": 0.7279587745666504, "step": 57000 }, { "epoch": 0.3388792790864942, "grad_norm": 1.7014799118041992, "learning_rate": 0.00019990797143218015, "loss": 0.7064042568206788, "step": 57010 }, { "epoch": 0.33893872116316254, "grad_norm": 1.676038146018982, "learning_rate": 0.0001999076897891468, "loss": 0.6916939735412597, "step": 57020 }, { "epoch": 0.33899816323983095, "grad_norm": 1.516209602355957, "learning_rate": 0.00019990740771602444, "loss": 0.715878963470459, "step": 57030 }, { "epoch": 0.3390576053164993, "grad_norm": 2.0643224716186523, "learning_rate": 0.00019990712521281444, "loss": 0.7544415473937989, "step": 57040 }, { "epoch": 0.3391170473931677, "grad_norm": 1.8446588516235352, "learning_rate": 0.00019990684227951818, "loss": 0.7439886093139648, "step": 57050 }, { "epoch": 0.33917648946983614, "grad_norm": 1.413683533668518, "learning_rate": 0.0001999065589161369, "loss": 0.6972513198852539, "step": 57060 }, { "epoch": 0.3392359315465045, "grad_norm": 1.5745646953582764, "learning_rate": 0.00019990627512267206, "loss": 0.6675477027893066, "step": 57070 }, { "epoch": 0.3392953736231729, "grad_norm": 2.17240571975708, "learning_rate": 0.000199905990899125, "loss": 0.691783332824707, "step": 57080 }, { "epoch": 0.3393548156998413, "grad_norm": 1.8453789949417114, "learning_rate": 0.00019990570624549698, "loss": 0.6949188232421875, "step": 57090 }, { "epoch": 0.3394142577765097, "grad_norm": 1.8822376728057861, "learning_rate": 0.00019990542116178953, "loss": 0.6940611362457275, "step": 57100 }, { "epoch": 0.33947369985317805, "grad_norm": 1.7671586275100708, "learning_rate": 0.00019990513564800387, "loss": 0.6410301208496094, "step": 57110 }, { "epoch": 0.33953314192984646, "grad_norm": 1.7279971837997437, "learning_rate": 0.00019990484970414146, "loss": 0.6882591247558594, "step": 57120 }, { "epoch": 0.3395925840065149, "grad_norm": 1.6348583698272705, "learning_rate": 0.0001999045633302036, "loss": 0.6988963127136231, "step": 57130 }, { "epoch": 0.33965202608318323, "grad_norm": 1.6361900568008423, "learning_rate": 0.00019990427652619172, "loss": 0.6508916854858399, "step": 57140 }, { "epoch": 0.33971146815985165, "grad_norm": 1.5995737314224243, "learning_rate": 0.0001999039892921071, "loss": 0.6803592681884766, "step": 57150 }, { "epoch": 0.33977091023652, "grad_norm": 1.7915676832199097, "learning_rate": 0.00019990370162795127, "loss": 0.725853443145752, "step": 57160 }, { "epoch": 0.3398303523131884, "grad_norm": 1.977523684501648, "learning_rate": 0.00019990341353372547, "loss": 0.688053035736084, "step": 57170 }, { "epoch": 0.3398897943898568, "grad_norm": 1.677600622177124, "learning_rate": 0.00019990312500943108, "loss": 0.6449886798858643, "step": 57180 }, { "epoch": 0.3399492364665252, "grad_norm": 1.6235296726226807, "learning_rate": 0.0001999028360550696, "loss": 0.7188712120056152, "step": 57190 }, { "epoch": 0.3400086785431936, "grad_norm": 1.760308861732483, "learning_rate": 0.00019990254667064228, "loss": 0.6825801849365234, "step": 57200 }, { "epoch": 0.34006812061986197, "grad_norm": 1.7840967178344727, "learning_rate": 0.00019990225685615056, "loss": 0.6855744361877442, "step": 57210 }, { "epoch": 0.3401275626965304, "grad_norm": 2.082261562347412, "learning_rate": 0.0001999019666115958, "loss": 0.7399152755737305, "step": 57220 }, { "epoch": 0.34018700477319874, "grad_norm": 1.615639090538025, "learning_rate": 0.00019990167593697945, "loss": 0.6663753032684326, "step": 57230 }, { "epoch": 0.34024644684986716, "grad_norm": 1.6070351600646973, "learning_rate": 0.00019990138483230287, "loss": 0.7278504371643066, "step": 57240 }, { "epoch": 0.3403058889265355, "grad_norm": 1.7741459608078003, "learning_rate": 0.00019990109329756742, "loss": 0.7126655101776123, "step": 57250 }, { "epoch": 0.34036533100320393, "grad_norm": 1.6881484985351562, "learning_rate": 0.00019990080133277456, "loss": 0.6653340339660645, "step": 57260 }, { "epoch": 0.34042477307987234, "grad_norm": 2.24423885345459, "learning_rate": 0.0001999005089379256, "loss": 0.7819567680358886, "step": 57270 }, { "epoch": 0.3404842151565407, "grad_norm": 1.5857775211334229, "learning_rate": 0.000199900216113022, "loss": 0.6962753295898437, "step": 57280 }, { "epoch": 0.3405436572332091, "grad_norm": 2.1193056106567383, "learning_rate": 0.00019989992285806516, "loss": 0.7202249526977539, "step": 57290 }, { "epoch": 0.3406030993098775, "grad_norm": 1.9355379343032837, "learning_rate": 0.00019989962917305645, "loss": 0.6578370094299316, "step": 57300 }, { "epoch": 0.3406625413865459, "grad_norm": 1.6889790296554565, "learning_rate": 0.0001998993350579973, "loss": 0.7243198871612548, "step": 57310 }, { "epoch": 0.34072198346321425, "grad_norm": 1.7833821773529053, "learning_rate": 0.0001998990405128891, "loss": 0.6680784225463867, "step": 57320 }, { "epoch": 0.34078142553988267, "grad_norm": 1.9441301822662354, "learning_rate": 0.00019989874553773328, "loss": 0.7029732704162598, "step": 57330 }, { "epoch": 0.340840867616551, "grad_norm": 1.780642032623291, "learning_rate": 0.00019989845013253124, "loss": 0.6948105812072753, "step": 57340 }, { "epoch": 0.34090030969321944, "grad_norm": 1.861809253692627, "learning_rate": 0.0001998981542972844, "loss": 0.7149626731872558, "step": 57350 }, { "epoch": 0.34095975176988785, "grad_norm": 1.4814672470092773, "learning_rate": 0.00019989785803199416, "loss": 0.6950117111206054, "step": 57360 }, { "epoch": 0.3410191938465562, "grad_norm": 2.0889973640441895, "learning_rate": 0.00019989756133666195, "loss": 0.727471113204956, "step": 57370 }, { "epoch": 0.3410786359232246, "grad_norm": 1.6470783948898315, "learning_rate": 0.00019989726421128917, "loss": 0.6779036521911621, "step": 57380 }, { "epoch": 0.341138077999893, "grad_norm": 1.9854848384857178, "learning_rate": 0.00019989696665587728, "loss": 0.6459804534912109, "step": 57390 }, { "epoch": 0.3411975200765614, "grad_norm": 2.1693010330200195, "learning_rate": 0.00019989666867042767, "loss": 0.7504549980163574, "step": 57400 }, { "epoch": 0.34125696215322976, "grad_norm": 2.129509925842285, "learning_rate": 0.00019989637025494178, "loss": 0.7586718082427979, "step": 57410 }, { "epoch": 0.3413164042298982, "grad_norm": 1.7232950925827026, "learning_rate": 0.00019989607140942102, "loss": 0.7266968727111817, "step": 57420 }, { "epoch": 0.3413758463065666, "grad_norm": 1.6779823303222656, "learning_rate": 0.00019989577213386686, "loss": 0.6932479858398437, "step": 57430 }, { "epoch": 0.34143528838323495, "grad_norm": 1.6537244319915771, "learning_rate": 0.0001998954724282807, "loss": 0.6966622352600098, "step": 57440 }, { "epoch": 0.34149473045990336, "grad_norm": 1.689376711845398, "learning_rate": 0.00019989517229266395, "loss": 0.6510629653930664, "step": 57450 }, { "epoch": 0.3415541725365717, "grad_norm": 1.546985149383545, "learning_rate": 0.0001998948717270181, "loss": 0.6890370368957519, "step": 57460 }, { "epoch": 0.34161361461324014, "grad_norm": 1.6735107898712158, "learning_rate": 0.00019989457073134456, "loss": 0.6837339401245117, "step": 57470 }, { "epoch": 0.3416730566899085, "grad_norm": 1.7597907781600952, "learning_rate": 0.00019989426930564475, "loss": 0.739918327331543, "step": 57480 }, { "epoch": 0.3417324987665769, "grad_norm": 1.3288686275482178, "learning_rate": 0.00019989396744992012, "loss": 0.6450176239013672, "step": 57490 }, { "epoch": 0.3417919408432453, "grad_norm": 1.934822916984558, "learning_rate": 0.00019989366516417217, "loss": 0.6500952243804932, "step": 57500 }, { "epoch": 0.3418513829199137, "grad_norm": 1.5304217338562012, "learning_rate": 0.0001998933624484023, "loss": 0.7031773567199707, "step": 57510 }, { "epoch": 0.3419108249965821, "grad_norm": 1.7035858631134033, "learning_rate": 0.00019989305930261193, "loss": 0.7092203617095947, "step": 57520 }, { "epoch": 0.34197026707325046, "grad_norm": 1.5687344074249268, "learning_rate": 0.00019989275572680255, "loss": 0.6896684646606446, "step": 57530 }, { "epoch": 0.34202970914991887, "grad_norm": 1.645602822303772, "learning_rate": 0.0001998924517209756, "loss": 0.6864498138427735, "step": 57540 }, { "epoch": 0.34208915122658723, "grad_norm": 1.5810754299163818, "learning_rate": 0.00019989214728513257, "loss": 0.7312118530273437, "step": 57550 }, { "epoch": 0.34214859330325564, "grad_norm": 1.9686667919158936, "learning_rate": 0.00019989184241927488, "loss": 0.6700699806213379, "step": 57560 }, { "epoch": 0.34220803537992406, "grad_norm": 1.8245497941970825, "learning_rate": 0.00019989153712340397, "loss": 0.7434341430664062, "step": 57570 }, { "epoch": 0.3422674774565924, "grad_norm": 1.2970201969146729, "learning_rate": 0.00019989123139752132, "loss": 0.7281056404113769, "step": 57580 }, { "epoch": 0.34232691953326083, "grad_norm": 1.829761028289795, "learning_rate": 0.0001998909252416284, "loss": 0.6713549613952636, "step": 57590 }, { "epoch": 0.3423863616099292, "grad_norm": 1.6544947624206543, "learning_rate": 0.0001998906186557267, "loss": 0.6282856941223145, "step": 57600 }, { "epoch": 0.3424458036865976, "grad_norm": 1.3816674947738647, "learning_rate": 0.00019989031163981764, "loss": 0.7676749229431152, "step": 57610 }, { "epoch": 0.34250524576326596, "grad_norm": 1.6672433614730835, "learning_rate": 0.00019989000419390267, "loss": 0.6554036617279053, "step": 57620 }, { "epoch": 0.3425646878399344, "grad_norm": 1.601475715637207, "learning_rate": 0.00019988969631798336, "loss": 0.7035849094390869, "step": 57630 }, { "epoch": 0.3426241299166028, "grad_norm": 2.0607705116271973, "learning_rate": 0.00019988938801206106, "loss": 0.6555541038513184, "step": 57640 }, { "epoch": 0.34268357199327115, "grad_norm": 1.6905781030654907, "learning_rate": 0.00019988907927613733, "loss": 0.6744308471679688, "step": 57650 }, { "epoch": 0.34274301406993957, "grad_norm": 1.9344227313995361, "learning_rate": 0.00019988877011021362, "loss": 0.7014346122741699, "step": 57660 }, { "epoch": 0.3428024561466079, "grad_norm": 1.5923371315002441, "learning_rate": 0.00019988846051429142, "loss": 0.6994527816772461, "step": 57670 }, { "epoch": 0.34286189822327634, "grad_norm": 2.337952136993408, "learning_rate": 0.0001998881504883722, "loss": 0.7157859802246094, "step": 57680 }, { "epoch": 0.3429213402999447, "grad_norm": 1.5180383920669556, "learning_rate": 0.00019988784003245743, "loss": 0.6508642673492432, "step": 57690 }, { "epoch": 0.3429807823766131, "grad_norm": 1.695783019065857, "learning_rate": 0.0001998875291465486, "loss": 0.7414652824401855, "step": 57700 }, { "epoch": 0.3430402244532815, "grad_norm": 1.799857497215271, "learning_rate": 0.00019988721783064723, "loss": 0.6300642013549804, "step": 57710 }, { "epoch": 0.3430996665299499, "grad_norm": 1.963304877281189, "learning_rate": 0.00019988690608475478, "loss": 0.6762604713439941, "step": 57720 }, { "epoch": 0.3431591086066183, "grad_norm": 1.6691087484359741, "learning_rate": 0.00019988659390887274, "loss": 0.7100094795227051, "step": 57730 }, { "epoch": 0.34321855068328666, "grad_norm": 1.6407281160354614, "learning_rate": 0.00019988628130300262, "loss": 0.7067074775695801, "step": 57740 }, { "epoch": 0.3432779927599551, "grad_norm": 1.7692512273788452, "learning_rate": 0.00019988596826714587, "loss": 0.6565031051635742, "step": 57750 }, { "epoch": 0.34333743483662343, "grad_norm": 1.6968326568603516, "learning_rate": 0.00019988565480130407, "loss": 0.6734514236450195, "step": 57760 }, { "epoch": 0.34339687691329185, "grad_norm": 1.5380383729934692, "learning_rate": 0.00019988534090547867, "loss": 0.6987273216247558, "step": 57770 }, { "epoch": 0.3434563189899602, "grad_norm": 1.7853695154190063, "learning_rate": 0.00019988502657967115, "loss": 0.7019667625427246, "step": 57780 }, { "epoch": 0.3435157610666286, "grad_norm": 1.9030627012252808, "learning_rate": 0.00019988471182388304, "loss": 0.713268518447876, "step": 57790 }, { "epoch": 0.34357520314329704, "grad_norm": 1.8125437498092651, "learning_rate": 0.00019988439663811585, "loss": 0.6964657783508301, "step": 57800 }, { "epoch": 0.3436346452199654, "grad_norm": 1.4044855833053589, "learning_rate": 0.00019988408102237105, "loss": 0.7111390113830567, "step": 57810 }, { "epoch": 0.3436940872966338, "grad_norm": 1.4557324647903442, "learning_rate": 0.00019988376497665023, "loss": 0.6805236339569092, "step": 57820 }, { "epoch": 0.34375352937330217, "grad_norm": 1.806791067123413, "learning_rate": 0.0001998834485009548, "loss": 0.6637775421142578, "step": 57830 }, { "epoch": 0.3438129714499706, "grad_norm": 2.0709898471832275, "learning_rate": 0.0001998831315952864, "loss": 0.6997622013092041, "step": 57840 }, { "epoch": 0.34387241352663894, "grad_norm": 1.7504650354385376, "learning_rate": 0.00019988281425964644, "loss": 0.6320788383483886, "step": 57850 }, { "epoch": 0.34393185560330736, "grad_norm": 2.127782106399536, "learning_rate": 0.00019988249649403644, "loss": 0.6946910381317138, "step": 57860 }, { "epoch": 0.34399129767997577, "grad_norm": 1.3900749683380127, "learning_rate": 0.00019988217829845797, "loss": 0.6292036056518555, "step": 57870 }, { "epoch": 0.34405073975664413, "grad_norm": 1.776450514793396, "learning_rate": 0.00019988185967291256, "loss": 0.7288964271545411, "step": 57880 }, { "epoch": 0.34411018183331255, "grad_norm": 1.7585760354995728, "learning_rate": 0.00019988154061740168, "loss": 0.6965590476989746, "step": 57890 }, { "epoch": 0.3441696239099809, "grad_norm": 1.635402798652649, "learning_rate": 0.00019988122113192688, "loss": 0.6890995979309082, "step": 57900 }, { "epoch": 0.3442290659866493, "grad_norm": 1.6518571376800537, "learning_rate": 0.0001998809012164897, "loss": 0.6296340942382812, "step": 57910 }, { "epoch": 0.3442885080633177, "grad_norm": 1.856203556060791, "learning_rate": 0.00019988058087109164, "loss": 0.6776283264160157, "step": 57920 }, { "epoch": 0.3443479501399861, "grad_norm": 1.9748661518096924, "learning_rate": 0.00019988026009573427, "loss": 0.6349379062652588, "step": 57930 }, { "epoch": 0.3444073922166545, "grad_norm": 1.59888756275177, "learning_rate": 0.0001998799388904191, "loss": 0.7241197109222413, "step": 57940 }, { "epoch": 0.34446683429332287, "grad_norm": 2.162447452545166, "learning_rate": 0.0001998796172551477, "loss": 0.7814231872558594, "step": 57950 }, { "epoch": 0.3445262763699913, "grad_norm": 1.4932215213775635, "learning_rate": 0.00019987929518992158, "loss": 0.6482070922851563, "step": 57960 }, { "epoch": 0.34458571844665964, "grad_norm": 1.6980637311935425, "learning_rate": 0.00019987897269474228, "loss": 0.6846010684967041, "step": 57970 }, { "epoch": 0.34464516052332805, "grad_norm": 2.176424264907837, "learning_rate": 0.00019987864976961134, "loss": 0.7072325706481933, "step": 57980 }, { "epoch": 0.3447046025999964, "grad_norm": 1.175757646560669, "learning_rate": 0.00019987832641453032, "loss": 0.715015459060669, "step": 57990 }, { "epoch": 0.3447640446766648, "grad_norm": 1.8104687929153442, "learning_rate": 0.00019987800262950074, "loss": 0.7102258682250977, "step": 58000 }, { "epoch": 0.34482348675333324, "grad_norm": 1.7271654605865479, "learning_rate": 0.0001998776784145242, "loss": 0.6516987800598144, "step": 58010 }, { "epoch": 0.3448829288300016, "grad_norm": 1.3937947750091553, "learning_rate": 0.0001998773537696022, "loss": 0.6731671333312989, "step": 58020 }, { "epoch": 0.34494237090667, "grad_norm": 1.8375637531280518, "learning_rate": 0.0001998770286947363, "loss": 0.6917158126831054, "step": 58030 }, { "epoch": 0.3450018129833384, "grad_norm": 2.5279619693756104, "learning_rate": 0.00019987670318992812, "loss": 0.6880737781524658, "step": 58040 }, { "epoch": 0.3450612550600068, "grad_norm": 1.637123942375183, "learning_rate": 0.0001998763772551791, "loss": 0.7252495288848877, "step": 58050 }, { "epoch": 0.34512069713667515, "grad_norm": 1.7746492624282837, "learning_rate": 0.0001998760508904909, "loss": 0.682379150390625, "step": 58060 }, { "epoch": 0.34518013921334356, "grad_norm": 1.7558728456497192, "learning_rate": 0.00019987572409586502, "loss": 0.6682815551757812, "step": 58070 }, { "epoch": 0.3452395812900119, "grad_norm": 1.641645073890686, "learning_rate": 0.00019987539687130307, "loss": 0.7211038112640381, "step": 58080 }, { "epoch": 0.34529902336668034, "grad_norm": 2.2597763538360596, "learning_rate": 0.00019987506921680657, "loss": 0.6693331718444824, "step": 58090 }, { "epoch": 0.34535846544334875, "grad_norm": 2.030938148498535, "learning_rate": 0.00019987474113237715, "loss": 0.6758618354797363, "step": 58100 }, { "epoch": 0.3454179075200171, "grad_norm": 1.9490047693252563, "learning_rate": 0.00019987441261801628, "loss": 0.7185752391815186, "step": 58110 }, { "epoch": 0.3454773495966855, "grad_norm": 1.5628807544708252, "learning_rate": 0.00019987408367372564, "loss": 0.760448694229126, "step": 58120 }, { "epoch": 0.3455367916733539, "grad_norm": 1.4046918153762817, "learning_rate": 0.00019987375429950671, "loss": 0.7059288024902344, "step": 58130 }, { "epoch": 0.3455962337500223, "grad_norm": 1.8798328638076782, "learning_rate": 0.00019987342449536116, "loss": 0.734820556640625, "step": 58140 }, { "epoch": 0.34565567582669066, "grad_norm": 1.623617172241211, "learning_rate": 0.0001998730942612905, "loss": 0.6684548854827881, "step": 58150 }, { "epoch": 0.34571511790335907, "grad_norm": 1.7666152715682983, "learning_rate": 0.00019987276359729632, "loss": 0.679616641998291, "step": 58160 }, { "epoch": 0.3457745599800275, "grad_norm": 2.0474634170532227, "learning_rate": 0.00019987243250338022, "loss": 0.7374738693237305, "step": 58170 }, { "epoch": 0.34583400205669584, "grad_norm": 1.6743237972259521, "learning_rate": 0.0001998721009795438, "loss": 0.6175783634185791, "step": 58180 }, { "epoch": 0.34589344413336426, "grad_norm": 1.9501948356628418, "learning_rate": 0.00019987176902578856, "loss": 0.6482242107391357, "step": 58190 }, { "epoch": 0.3459528862100326, "grad_norm": 1.8839383125305176, "learning_rate": 0.0001998714366421162, "loss": 0.7134223937988281, "step": 58200 }, { "epoch": 0.34601232828670103, "grad_norm": 1.7001501321792603, "learning_rate": 0.00019987110382852822, "loss": 0.6986270904541015, "step": 58210 }, { "epoch": 0.3460717703633694, "grad_norm": 1.8499715328216553, "learning_rate": 0.00019987077058502626, "loss": 0.6660611152648925, "step": 58220 }, { "epoch": 0.3461312124400378, "grad_norm": 1.784502387046814, "learning_rate": 0.00019987043691161192, "loss": 0.7169114112854004, "step": 58230 }, { "epoch": 0.3461906545167062, "grad_norm": 1.5990511178970337, "learning_rate": 0.00019987010280828675, "loss": 0.708941650390625, "step": 58240 }, { "epoch": 0.3462500965933746, "grad_norm": 1.9282546043395996, "learning_rate": 0.00019986976827505242, "loss": 0.6991191864013672, "step": 58250 }, { "epoch": 0.346309538670043, "grad_norm": 1.9650359153747559, "learning_rate": 0.00019986943331191042, "loss": 0.6873116970062256, "step": 58260 }, { "epoch": 0.34636898074671135, "grad_norm": 2.564180850982666, "learning_rate": 0.00019986909791886248, "loss": 0.6703432559967041, "step": 58270 }, { "epoch": 0.34642842282337977, "grad_norm": 1.6274477243423462, "learning_rate": 0.00019986876209591013, "loss": 0.7311300754547119, "step": 58280 }, { "epoch": 0.3464878649000481, "grad_norm": 1.93486750125885, "learning_rate": 0.000199868425843055, "loss": 0.7135820388793945, "step": 58290 }, { "epoch": 0.34654730697671654, "grad_norm": 1.777366042137146, "learning_rate": 0.00019986808916029866, "loss": 0.7690094470977783, "step": 58300 }, { "epoch": 0.34660674905338495, "grad_norm": 1.8146073818206787, "learning_rate": 0.00019986775204764278, "loss": 0.6800081253051757, "step": 58310 }, { "epoch": 0.3466661911300533, "grad_norm": 1.6290972232818604, "learning_rate": 0.00019986741450508892, "loss": 0.6681652069091797, "step": 58320 }, { "epoch": 0.34672563320672173, "grad_norm": 1.6279890537261963, "learning_rate": 0.00019986707653263874, "loss": 0.7715714454650879, "step": 58330 }, { "epoch": 0.3467850752833901, "grad_norm": 1.4824576377868652, "learning_rate": 0.00019986673813029383, "loss": 0.7200821876525879, "step": 58340 }, { "epoch": 0.3468445173600585, "grad_norm": 2.0719754695892334, "learning_rate": 0.00019986639929805582, "loss": 0.7212123870849609, "step": 58350 }, { "epoch": 0.34690395943672686, "grad_norm": 1.9427926540374756, "learning_rate": 0.0001998660600359263, "loss": 0.7349133491516113, "step": 58360 }, { "epoch": 0.3469634015133953, "grad_norm": 1.7065194845199585, "learning_rate": 0.00019986572034390694, "loss": 0.7192389488220214, "step": 58370 }, { "epoch": 0.3470228435900637, "grad_norm": 1.6415690183639526, "learning_rate": 0.0001998653802219993, "loss": 0.7298783302307129, "step": 58380 }, { "epoch": 0.34708228566673205, "grad_norm": 1.7673802375793457, "learning_rate": 0.00019986503967020513, "loss": 0.7435856819152832, "step": 58390 }, { "epoch": 0.34714172774340046, "grad_norm": 1.7071611881256104, "learning_rate": 0.0001998646986885259, "loss": 0.7540193557739258, "step": 58400 }, { "epoch": 0.3472011698200688, "grad_norm": 1.8951101303100586, "learning_rate": 0.00019986435727696337, "loss": 0.7011963367462158, "step": 58410 }, { "epoch": 0.34726061189673724, "grad_norm": 1.9803171157836914, "learning_rate": 0.00019986401543551908, "loss": 0.7056052207946777, "step": 58420 }, { "epoch": 0.3473200539734056, "grad_norm": 1.535308599472046, "learning_rate": 0.00019986367316419476, "loss": 0.7363105773925781, "step": 58430 }, { "epoch": 0.347379496050074, "grad_norm": 1.5157760381698608, "learning_rate": 0.00019986333046299198, "loss": 0.679639482498169, "step": 58440 }, { "epoch": 0.34743893812674237, "grad_norm": 1.9207884073257446, "learning_rate": 0.00019986298733191239, "loss": 0.6904975891113281, "step": 58450 }, { "epoch": 0.3474983802034108, "grad_norm": 2.218282461166382, "learning_rate": 0.0001998626437709576, "loss": 0.6242362976074218, "step": 58460 }, { "epoch": 0.3475578222800792, "grad_norm": 1.7609626054763794, "learning_rate": 0.0001998622997801293, "loss": 0.5968029975891114, "step": 58470 }, { "epoch": 0.34761726435674756, "grad_norm": 1.8715192079544067, "learning_rate": 0.00019986195535942917, "loss": 0.6094581604003906, "step": 58480 }, { "epoch": 0.34767670643341597, "grad_norm": 1.9024392366409302, "learning_rate": 0.0001998616105088588, "loss": 0.6302324771881104, "step": 58490 }, { "epoch": 0.34773614851008433, "grad_norm": 2.493752956390381, "learning_rate": 0.0001998612652284198, "loss": 0.7320955276489258, "step": 58500 }, { "epoch": 0.34779559058675275, "grad_norm": 1.9631575345993042, "learning_rate": 0.00019986091951811394, "loss": 0.7231216430664062, "step": 58510 }, { "epoch": 0.3478550326634211, "grad_norm": 2.2039668560028076, "learning_rate": 0.00019986057337794278, "loss": 0.6867122650146484, "step": 58520 }, { "epoch": 0.3479144747400895, "grad_norm": 1.710945963859558, "learning_rate": 0.000199860226807908, "loss": 0.6896276950836182, "step": 58530 }, { "epoch": 0.34797391681675793, "grad_norm": 1.5583748817443848, "learning_rate": 0.00019985987980801126, "loss": 0.6932909965515137, "step": 58540 }, { "epoch": 0.3480333588934263, "grad_norm": 2.1345672607421875, "learning_rate": 0.00019985953237825426, "loss": 0.6823853969573974, "step": 58550 }, { "epoch": 0.3480928009700947, "grad_norm": 1.6642109155654907, "learning_rate": 0.00019985918451863855, "loss": 0.6689933776855469, "step": 58560 }, { "epoch": 0.34815224304676307, "grad_norm": 1.5963433980941772, "learning_rate": 0.00019985883622916593, "loss": 0.7182178497314453, "step": 58570 }, { "epoch": 0.3482116851234315, "grad_norm": 1.8431941270828247, "learning_rate": 0.00019985848750983797, "loss": 0.6797638893127441, "step": 58580 }, { "epoch": 0.34827112720009984, "grad_norm": 2.035733699798584, "learning_rate": 0.0001998581383606564, "loss": 0.6655954360961914, "step": 58590 }, { "epoch": 0.34833056927676825, "grad_norm": 2.0148441791534424, "learning_rate": 0.00019985778878162284, "loss": 0.7121756076812744, "step": 58600 }, { "epoch": 0.34839001135343667, "grad_norm": 1.5046641826629639, "learning_rate": 0.000199857438772739, "loss": 0.6418984413146973, "step": 58610 }, { "epoch": 0.348449453430105, "grad_norm": 1.9215271472930908, "learning_rate": 0.0001998570883340065, "loss": 0.6779999256134033, "step": 58620 }, { "epoch": 0.34850889550677344, "grad_norm": 1.8716464042663574, "learning_rate": 0.0001998567374654271, "loss": 0.6741658210754394, "step": 58630 }, { "epoch": 0.3485683375834418, "grad_norm": 1.6525377035140991, "learning_rate": 0.00019985638616700245, "loss": 0.7006961822509765, "step": 58640 }, { "epoch": 0.3486277796601102, "grad_norm": 1.7918674945831299, "learning_rate": 0.00019985603443873416, "loss": 0.6874522209167481, "step": 58650 }, { "epoch": 0.3486872217367786, "grad_norm": 1.9825180768966675, "learning_rate": 0.00019985568228062396, "loss": 0.7142819404602051, "step": 58660 }, { "epoch": 0.348746663813447, "grad_norm": 1.6879551410675049, "learning_rate": 0.0001998553296926736, "loss": 0.6720131874084473, "step": 58670 }, { "epoch": 0.3488061058901154, "grad_norm": 1.8115545511245728, "learning_rate": 0.0001998549766748847, "loss": 0.6937376976013183, "step": 58680 }, { "epoch": 0.34886554796678376, "grad_norm": 2.0235486030578613, "learning_rate": 0.00019985462322725893, "loss": 0.7168136596679687, "step": 58690 }, { "epoch": 0.3489249900434522, "grad_norm": 1.4674773216247559, "learning_rate": 0.00019985426934979801, "loss": 0.7090548038482666, "step": 58700 }, { "epoch": 0.34898443212012054, "grad_norm": 1.996199607849121, "learning_rate": 0.00019985391504250363, "loss": 0.6895717144012451, "step": 58710 }, { "epoch": 0.34904387419678895, "grad_norm": 1.5241655111312866, "learning_rate": 0.00019985356030537745, "loss": 0.6974434852600098, "step": 58720 }, { "epoch": 0.3491033162734573, "grad_norm": 1.5979548692703247, "learning_rate": 0.00019985320513842125, "loss": 0.712668514251709, "step": 58730 }, { "epoch": 0.3491627583501257, "grad_norm": 1.8699802160263062, "learning_rate": 0.00019985284954163667, "loss": 0.687256145477295, "step": 58740 }, { "epoch": 0.34922220042679414, "grad_norm": 1.5115841627120972, "learning_rate": 0.0001998524935150254, "loss": 0.6912722587585449, "step": 58750 }, { "epoch": 0.3492816425034625, "grad_norm": 1.7573884725570679, "learning_rate": 0.0001998521370585892, "loss": 0.7054656028747559, "step": 58760 }, { "epoch": 0.3493410845801309, "grad_norm": 1.798363208770752, "learning_rate": 0.00019985178017232973, "loss": 0.6777982711791992, "step": 58770 }, { "epoch": 0.34940052665679927, "grad_norm": 2.181763172149658, "learning_rate": 0.00019985142285624874, "loss": 0.7340534210205079, "step": 58780 }, { "epoch": 0.3494599687334677, "grad_norm": 2.2346622943878174, "learning_rate": 0.00019985106511034783, "loss": 0.7489175796508789, "step": 58790 }, { "epoch": 0.34951941081013604, "grad_norm": 1.8525588512420654, "learning_rate": 0.00019985070693462884, "loss": 0.7318507194519043, "step": 58800 }, { "epoch": 0.34957885288680446, "grad_norm": 1.7203900814056396, "learning_rate": 0.00019985034832909344, "loss": 0.7124220371246338, "step": 58810 }, { "epoch": 0.3496382949634728, "grad_norm": 1.8639384508132935, "learning_rate": 0.0001998499892937433, "loss": 0.6874269008636474, "step": 58820 }, { "epoch": 0.34969773704014123, "grad_norm": 1.6828054189682007, "learning_rate": 0.0001998496298285802, "loss": 0.7191133499145508, "step": 58830 }, { "epoch": 0.34975717911680965, "grad_norm": 2.0879390239715576, "learning_rate": 0.0001998492699336058, "loss": 0.6658875465393066, "step": 58840 }, { "epoch": 0.349816621193478, "grad_norm": 1.9697474241256714, "learning_rate": 0.00019984890960882191, "loss": 0.6705708503723145, "step": 58850 }, { "epoch": 0.3498760632701464, "grad_norm": 1.7442210912704468, "learning_rate": 0.00019984854885423016, "loss": 0.7034029960632324, "step": 58860 }, { "epoch": 0.3499355053468148, "grad_norm": 1.5227835178375244, "learning_rate": 0.00019984818766983234, "loss": 0.730736255645752, "step": 58870 }, { "epoch": 0.3499949474234832, "grad_norm": 1.859800100326538, "learning_rate": 0.00019984782605563016, "loss": 0.7247995376586914, "step": 58880 }, { "epoch": 0.35005438950015155, "grad_norm": 2.2875168323516846, "learning_rate": 0.00019984746401162528, "loss": 0.7003984451293945, "step": 58890 }, { "epoch": 0.35011383157681997, "grad_norm": 1.9313664436340332, "learning_rate": 0.00019984710153781956, "loss": 0.7058017730712891, "step": 58900 }, { "epoch": 0.3501732736534884, "grad_norm": 2.196922540664673, "learning_rate": 0.00019984673863421463, "loss": 0.7563362121582031, "step": 58910 }, { "epoch": 0.35023271573015674, "grad_norm": 1.366317868232727, "learning_rate": 0.0001998463753008123, "loss": 0.6338049888610839, "step": 58920 }, { "epoch": 0.35029215780682516, "grad_norm": 1.5977070331573486, "learning_rate": 0.00019984601153761423, "loss": 0.6616421699523926, "step": 58930 }, { "epoch": 0.3503515998834935, "grad_norm": 1.4802172183990479, "learning_rate": 0.00019984564734462222, "loss": 0.6782577514648438, "step": 58940 }, { "epoch": 0.35041104196016193, "grad_norm": 1.7294775247573853, "learning_rate": 0.00019984528272183803, "loss": 0.7269365787506104, "step": 58950 }, { "epoch": 0.3504704840368303, "grad_norm": 1.8291724920272827, "learning_rate": 0.00019984491766926333, "loss": 0.6795160293579101, "step": 58960 }, { "epoch": 0.3505299261134987, "grad_norm": 1.6705800294876099, "learning_rate": 0.0001998445521868999, "loss": 0.633292293548584, "step": 58970 }, { "epoch": 0.3505893681901671, "grad_norm": 1.8970162868499756, "learning_rate": 0.00019984418627474952, "loss": 0.6866819381713867, "step": 58980 }, { "epoch": 0.3506488102668355, "grad_norm": 1.562596082687378, "learning_rate": 0.00019984381993281392, "loss": 0.685846471786499, "step": 58990 }, { "epoch": 0.3507082523435039, "grad_norm": 1.7488521337509155, "learning_rate": 0.00019984345316109483, "loss": 0.6806657314300537, "step": 59000 }, { "epoch": 0.35076769442017225, "grad_norm": 1.7392339706420898, "learning_rate": 0.000199843085959594, "loss": 0.6616197109222413, "step": 59010 }, { "epoch": 0.35082713649684066, "grad_norm": 1.3743011951446533, "learning_rate": 0.00019984271832831324, "loss": 0.7007696151733398, "step": 59020 }, { "epoch": 0.350886578573509, "grad_norm": 1.504882574081421, "learning_rate": 0.00019984235026725426, "loss": 0.6524890899658203, "step": 59030 }, { "epoch": 0.35094602065017744, "grad_norm": 1.9054189920425415, "learning_rate": 0.00019984198177641884, "loss": 0.7137168884277344, "step": 59040 }, { "epoch": 0.35100546272684585, "grad_norm": 1.7124325037002563, "learning_rate": 0.00019984161285580874, "loss": 0.7129183769226074, "step": 59050 }, { "epoch": 0.3510649048035142, "grad_norm": 1.8539669513702393, "learning_rate": 0.00019984124350542576, "loss": 0.6905465602874756, "step": 59060 }, { "epoch": 0.3511243468801826, "grad_norm": 2.061142921447754, "learning_rate": 0.0001998408737252716, "loss": 0.7035579681396484, "step": 59070 }, { "epoch": 0.351183788956851, "grad_norm": 1.785823106765747, "learning_rate": 0.00019984050351534805, "loss": 0.7014391422271729, "step": 59080 }, { "epoch": 0.3512432310335194, "grad_norm": 1.6826943159103394, "learning_rate": 0.00019984013287565689, "loss": 0.7143899917602539, "step": 59090 }, { "epoch": 0.35130267311018776, "grad_norm": 1.833876371383667, "learning_rate": 0.0001998397618061999, "loss": 0.6531163692474365, "step": 59100 }, { "epoch": 0.35136211518685617, "grad_norm": 1.4089629650115967, "learning_rate": 0.00019983939030697884, "loss": 0.6365090847015381, "step": 59110 }, { "epoch": 0.35142155726352453, "grad_norm": 2.3720972537994385, "learning_rate": 0.00019983901837799552, "loss": 0.6813956737518311, "step": 59120 }, { "epoch": 0.35148099934019295, "grad_norm": 1.7438373565673828, "learning_rate": 0.0001998386460192517, "loss": 0.7139286041259766, "step": 59130 }, { "epoch": 0.35154044141686136, "grad_norm": 1.6385598182678223, "learning_rate": 0.00019983827323074912, "loss": 0.6864934921264648, "step": 59140 }, { "epoch": 0.3515998834935297, "grad_norm": 1.8383538722991943, "learning_rate": 0.00019983790001248963, "loss": 0.7031393051147461, "step": 59150 }, { "epoch": 0.35165932557019813, "grad_norm": 1.9889618158340454, "learning_rate": 0.000199837526364475, "loss": 0.6739312171936035, "step": 59160 }, { "epoch": 0.3517187676468665, "grad_norm": 1.815245509147644, "learning_rate": 0.000199837152286707, "loss": 0.7255095958709716, "step": 59170 }, { "epoch": 0.3517782097235349, "grad_norm": 1.357126235961914, "learning_rate": 0.00019983677777918738, "loss": 0.7245865821838379, "step": 59180 }, { "epoch": 0.35183765180020327, "grad_norm": 2.0215494632720947, "learning_rate": 0.000199836402841918, "loss": 0.6809262752532959, "step": 59190 }, { "epoch": 0.3518970938768717, "grad_norm": 1.5669829845428467, "learning_rate": 0.0001998360274749006, "loss": 0.6692520141601562, "step": 59200 }, { "epoch": 0.3519565359535401, "grad_norm": 1.6509277820587158, "learning_rate": 0.00019983565167813706, "loss": 0.6979117393493652, "step": 59210 }, { "epoch": 0.35201597803020845, "grad_norm": 1.5299009084701538, "learning_rate": 0.0001998352754516291, "loss": 0.719419288635254, "step": 59220 }, { "epoch": 0.35207542010687687, "grad_norm": 1.4099040031433105, "learning_rate": 0.00019983489879537853, "loss": 0.7466119766235352, "step": 59230 }, { "epoch": 0.3521348621835452, "grad_norm": 1.9080796241760254, "learning_rate": 0.00019983452170938717, "loss": 0.7296740055084229, "step": 59240 }, { "epoch": 0.35219430426021364, "grad_norm": 1.598516583442688, "learning_rate": 0.0001998341441936568, "loss": 0.7316960334777832, "step": 59250 }, { "epoch": 0.352253746336882, "grad_norm": 1.6213090419769287, "learning_rate": 0.00019983376624818926, "loss": 0.6786271572113037, "step": 59260 }, { "epoch": 0.3523131884135504, "grad_norm": 1.482738733291626, "learning_rate": 0.00019983338787298634, "loss": 0.6933561801910401, "step": 59270 }, { "epoch": 0.35237263049021883, "grad_norm": 1.491730809211731, "learning_rate": 0.00019983300906804981, "loss": 0.6859516143798828, "step": 59280 }, { "epoch": 0.3524320725668872, "grad_norm": 1.8697731494903564, "learning_rate": 0.00019983262983338157, "loss": 0.7030176639556884, "step": 59290 }, { "epoch": 0.3524915146435556, "grad_norm": 1.8524601459503174, "learning_rate": 0.0001998322501689834, "loss": 0.708725881576538, "step": 59300 }, { "epoch": 0.35255095672022396, "grad_norm": 1.82118558883667, "learning_rate": 0.00019983187007485706, "loss": 0.7241817474365234, "step": 59310 }, { "epoch": 0.3526103987968924, "grad_norm": 1.8141283988952637, "learning_rate": 0.00019983148955100445, "loss": 0.7234519481658935, "step": 59320 }, { "epoch": 0.35266984087356074, "grad_norm": 1.8645046949386597, "learning_rate": 0.0001998311085974273, "loss": 0.7044636249542237, "step": 59330 }, { "epoch": 0.35272928295022915, "grad_norm": 1.714349627494812, "learning_rate": 0.0001998307272141275, "loss": 0.6402399063110351, "step": 59340 }, { "epoch": 0.35278872502689756, "grad_norm": 1.845447301864624, "learning_rate": 0.0001998303454011069, "loss": 0.7283754348754883, "step": 59350 }, { "epoch": 0.3528481671035659, "grad_norm": 1.9133278131484985, "learning_rate": 0.00019982996315836724, "loss": 0.7029333114624023, "step": 59360 }, { "epoch": 0.35290760918023434, "grad_norm": 1.725781798362732, "learning_rate": 0.0001998295804859104, "loss": 0.6818492889404297, "step": 59370 }, { "epoch": 0.3529670512569027, "grad_norm": 1.9475477933883667, "learning_rate": 0.0001998291973837382, "loss": 0.6234065055847168, "step": 59380 }, { "epoch": 0.3530264933335711, "grad_norm": 1.5227893590927124, "learning_rate": 0.0001998288138518525, "loss": 0.6511808395385742, "step": 59390 }, { "epoch": 0.35308593541023947, "grad_norm": 1.6320875883102417, "learning_rate": 0.00019982842989025513, "loss": 0.7018706798553467, "step": 59400 }, { "epoch": 0.3531453774869079, "grad_norm": 1.9104931354522705, "learning_rate": 0.00019982804549894786, "loss": 0.737092399597168, "step": 59410 }, { "epoch": 0.3532048195635763, "grad_norm": 1.9308974742889404, "learning_rate": 0.00019982766067793258, "loss": 0.6942170143127442, "step": 59420 }, { "epoch": 0.35326426164024466, "grad_norm": 1.6863468885421753, "learning_rate": 0.00019982727542721115, "loss": 0.6601485252380371, "step": 59430 }, { "epoch": 0.3533237037169131, "grad_norm": 1.694746971130371, "learning_rate": 0.00019982688974678537, "loss": 0.7172941207885742, "step": 59440 }, { "epoch": 0.35338314579358143, "grad_norm": 1.4529049396514893, "learning_rate": 0.00019982650363665713, "loss": 0.655379056930542, "step": 59450 }, { "epoch": 0.35344258787024985, "grad_norm": 1.7184635400772095, "learning_rate": 0.00019982611709682823, "loss": 0.7351507186889649, "step": 59460 }, { "epoch": 0.3535020299469182, "grad_norm": 1.2562536001205444, "learning_rate": 0.00019982573012730054, "loss": 0.7180607318878174, "step": 59470 }, { "epoch": 0.3535614720235866, "grad_norm": 2.1490187644958496, "learning_rate": 0.00019982534272807592, "loss": 0.6826967239379883, "step": 59480 }, { "epoch": 0.353620914100255, "grad_norm": 1.624768853187561, "learning_rate": 0.0001998249548991562, "loss": 0.7035542488098144, "step": 59490 }, { "epoch": 0.3536803561769234, "grad_norm": 1.8092436790466309, "learning_rate": 0.00019982456664054327, "loss": 0.7039532661437988, "step": 59500 }, { "epoch": 0.3537397982535918, "grad_norm": 1.884696125984192, "learning_rate": 0.00019982417795223897, "loss": 0.6888181686401367, "step": 59510 }, { "epoch": 0.35379924033026017, "grad_norm": 1.32362961769104, "learning_rate": 0.00019982378883424517, "loss": 0.6810163497924805, "step": 59520 }, { "epoch": 0.3538586824069286, "grad_norm": 1.7379324436187744, "learning_rate": 0.0001998233992865637, "loss": 0.7351160049438477, "step": 59530 }, { "epoch": 0.35391812448359694, "grad_norm": 1.8426891565322876, "learning_rate": 0.00019982300930919644, "loss": 0.6351161956787109, "step": 59540 }, { "epoch": 0.35397756656026536, "grad_norm": 1.7216554880142212, "learning_rate": 0.00019982261890214527, "loss": 0.7110436439514161, "step": 59550 }, { "epoch": 0.3540370086369337, "grad_norm": 1.662746787071228, "learning_rate": 0.00019982222806541204, "loss": 0.7140671730041503, "step": 59560 }, { "epoch": 0.35409645071360213, "grad_norm": 2.099238395690918, "learning_rate": 0.00019982183679899862, "loss": 0.7438568115234375, "step": 59570 }, { "epoch": 0.35415589279027054, "grad_norm": 1.6461546421051025, "learning_rate": 0.00019982144510290688, "loss": 0.6977343559265137, "step": 59580 }, { "epoch": 0.3542153348669389, "grad_norm": 1.6495434045791626, "learning_rate": 0.00019982105297713872, "loss": 0.7436851978302002, "step": 59590 }, { "epoch": 0.3542747769436073, "grad_norm": 1.328034520149231, "learning_rate": 0.00019982066042169598, "loss": 0.6376755714416504, "step": 59600 }, { "epoch": 0.3543342190202757, "grad_norm": 1.9553812742233276, "learning_rate": 0.00019982026743658055, "loss": 0.6532560348510742, "step": 59610 }, { "epoch": 0.3543936610969441, "grad_norm": 2.081932544708252, "learning_rate": 0.00019981987402179432, "loss": 0.6820529460906982, "step": 59620 }, { "epoch": 0.35445310317361245, "grad_norm": 1.9055736064910889, "learning_rate": 0.0001998194801773392, "loss": 0.6650042533874512, "step": 59630 }, { "epoch": 0.35451254525028086, "grad_norm": 2.1168270111083984, "learning_rate": 0.000199819085903217, "loss": 0.7195497512817383, "step": 59640 }, { "epoch": 0.3545719873269493, "grad_norm": 2.024786949157715, "learning_rate": 0.00019981869119942966, "loss": 0.6671690940856934, "step": 59650 }, { "epoch": 0.35463142940361764, "grad_norm": 1.6274163722991943, "learning_rate": 0.00019981829606597904, "loss": 0.7022234916687011, "step": 59660 }, { "epoch": 0.35469087148028605, "grad_norm": 1.2993102073669434, "learning_rate": 0.00019981790050286707, "loss": 0.652066707611084, "step": 59670 }, { "epoch": 0.3547503135569544, "grad_norm": 1.6656957864761353, "learning_rate": 0.0001998175045100956, "loss": 0.6492174625396728, "step": 59680 }, { "epoch": 0.3548097556336228, "grad_norm": 2.1202285289764404, "learning_rate": 0.00019981710808766653, "loss": 0.7191273212432862, "step": 59690 }, { "epoch": 0.3548691977102912, "grad_norm": 1.7567124366760254, "learning_rate": 0.00019981671123558178, "loss": 0.6695502281188965, "step": 59700 }, { "epoch": 0.3549286397869596, "grad_norm": 1.3584219217300415, "learning_rate": 0.00019981631395384324, "loss": 0.677041482925415, "step": 59710 }, { "epoch": 0.354988081863628, "grad_norm": 1.6044878959655762, "learning_rate": 0.0001998159162424528, "loss": 0.6719814300537109, "step": 59720 }, { "epoch": 0.3550475239402964, "grad_norm": 1.6040679216384888, "learning_rate": 0.00019981551810141238, "loss": 0.6881763935089111, "step": 59730 }, { "epoch": 0.3551069660169648, "grad_norm": 1.234537124633789, "learning_rate": 0.00019981511953072388, "loss": 0.6844452857971192, "step": 59740 }, { "epoch": 0.35516640809363315, "grad_norm": 1.6480536460876465, "learning_rate": 0.0001998147205303892, "loss": 0.720258092880249, "step": 59750 }, { "epoch": 0.35522585017030156, "grad_norm": 1.6548631191253662, "learning_rate": 0.0001998143211004102, "loss": 0.7296946525573731, "step": 59760 }, { "epoch": 0.3552852922469699, "grad_norm": 1.8478409051895142, "learning_rate": 0.00019981392124078891, "loss": 0.655628776550293, "step": 59770 }, { "epoch": 0.35534473432363833, "grad_norm": 1.3546479940414429, "learning_rate": 0.00019981352095152713, "loss": 0.6632904052734375, "step": 59780 }, { "epoch": 0.35540417640030675, "grad_norm": 1.600364089012146, "learning_rate": 0.00019981312023262683, "loss": 0.6813808441162109, "step": 59790 }, { "epoch": 0.3554636184769751, "grad_norm": 1.648285150527954, "learning_rate": 0.00019981271908408988, "loss": 0.6793548583984375, "step": 59800 }, { "epoch": 0.3555230605536435, "grad_norm": 1.4298418760299683, "learning_rate": 0.0001998123175059183, "loss": 0.673093318939209, "step": 59810 }, { "epoch": 0.3555825026303119, "grad_norm": 1.7362650632858276, "learning_rate": 0.00019981191549811388, "loss": 0.7162879467010498, "step": 59820 }, { "epoch": 0.3556419447069803, "grad_norm": 1.4424831867218018, "learning_rate": 0.00019981151306067862, "loss": 0.6801679134368896, "step": 59830 }, { "epoch": 0.35570138678364865, "grad_norm": 2.1962039470672607, "learning_rate": 0.00019981111019361448, "loss": 0.7007017612457276, "step": 59840 }, { "epoch": 0.35576082886031707, "grad_norm": 1.6664891242980957, "learning_rate": 0.00019981070689692327, "loss": 0.6967162132263184, "step": 59850 }, { "epoch": 0.3558202709369854, "grad_norm": 1.7426940202713013, "learning_rate": 0.00019981030317060705, "loss": 0.6807207107543946, "step": 59860 }, { "epoch": 0.35587971301365384, "grad_norm": 2.0513529777526855, "learning_rate": 0.00019980989901466768, "loss": 0.7102994918823242, "step": 59870 }, { "epoch": 0.35593915509032226, "grad_norm": 1.6465858221054077, "learning_rate": 0.00019980949442910707, "loss": 0.7118277072906494, "step": 59880 }, { "epoch": 0.3559985971669906, "grad_norm": 1.7094695568084717, "learning_rate": 0.0001998090894139272, "loss": 0.6404781341552734, "step": 59890 }, { "epoch": 0.35605803924365903, "grad_norm": 1.800427794456482, "learning_rate": 0.00019980868396913, "loss": 0.7085377693176269, "step": 59900 }, { "epoch": 0.3561174813203274, "grad_norm": 1.9525026082992554, "learning_rate": 0.00019980827809471742, "loss": 0.7467152595520019, "step": 59910 }, { "epoch": 0.3561769233969958, "grad_norm": 1.6807314157485962, "learning_rate": 0.00019980787179069135, "loss": 0.7319722652435303, "step": 59920 }, { "epoch": 0.35623636547366416, "grad_norm": 1.8992043733596802, "learning_rate": 0.0001998074650570538, "loss": 0.7011854171752929, "step": 59930 }, { "epoch": 0.3562958075503326, "grad_norm": 1.7712424993515015, "learning_rate": 0.0001998070578938067, "loss": 0.6648953437805176, "step": 59940 }, { "epoch": 0.356355249627001, "grad_norm": 1.4898037910461426, "learning_rate": 0.00019980665030095194, "loss": 0.717844820022583, "step": 59950 }, { "epoch": 0.35641469170366935, "grad_norm": 1.8160717487335205, "learning_rate": 0.00019980624227849153, "loss": 0.7441972732543946, "step": 59960 }, { "epoch": 0.35647413378033777, "grad_norm": 1.853320837020874, "learning_rate": 0.00019980583382642745, "loss": 0.7102956771850586, "step": 59970 }, { "epoch": 0.3565335758570061, "grad_norm": 1.935583233833313, "learning_rate": 0.00019980542494476156, "loss": 0.6530454158782959, "step": 59980 }, { "epoch": 0.35659301793367454, "grad_norm": 1.635306715965271, "learning_rate": 0.00019980501563349588, "loss": 0.7835353374481201, "step": 59990 }, { "epoch": 0.3566524600103429, "grad_norm": 1.7727444171905518, "learning_rate": 0.00019980460589263236, "loss": 0.6957390785217286, "step": 60000 }, { "epoch": 0.3567119020870113, "grad_norm": 1.7386378049850464, "learning_rate": 0.00019980419572217294, "loss": 0.7123428344726562, "step": 60010 }, { "epoch": 0.3567713441636797, "grad_norm": 2.1387205123901367, "learning_rate": 0.0001998037851221196, "loss": 0.6924668312072754, "step": 60020 }, { "epoch": 0.3568307862403481, "grad_norm": 1.7241915464401245, "learning_rate": 0.0001998033740924743, "loss": 0.7139989852905273, "step": 60030 }, { "epoch": 0.3568902283170165, "grad_norm": 1.5781739950180054, "learning_rate": 0.00019980296263323903, "loss": 0.7022741317749024, "step": 60040 }, { "epoch": 0.35694967039368486, "grad_norm": 1.9225562810897827, "learning_rate": 0.0001998025507444157, "loss": 0.6835339546203614, "step": 60050 }, { "epoch": 0.3570091124703533, "grad_norm": 1.644114375114441, "learning_rate": 0.00019980213842600634, "loss": 0.6634268283843994, "step": 60060 }, { "epoch": 0.35706855454702163, "grad_norm": 2.0758731365203857, "learning_rate": 0.0001998017256780129, "loss": 0.715152359008789, "step": 60070 }, { "epoch": 0.35712799662369005, "grad_norm": 1.792547583580017, "learning_rate": 0.00019980131250043733, "loss": 0.6797457218170166, "step": 60080 }, { "epoch": 0.35718743870035846, "grad_norm": 1.6217637062072754, "learning_rate": 0.00019980089889328165, "loss": 0.7133332252502441, "step": 60090 }, { "epoch": 0.3572468807770268, "grad_norm": 1.516489028930664, "learning_rate": 0.00019980048485654782, "loss": 0.6959602355957031, "step": 60100 }, { "epoch": 0.35730632285369524, "grad_norm": 1.7384915351867676, "learning_rate": 0.00019980007039023778, "loss": 0.7022024154663086, "step": 60110 }, { "epoch": 0.3573657649303636, "grad_norm": 1.4177885055541992, "learning_rate": 0.00019979965549435358, "loss": 0.6711737632751464, "step": 60120 }, { "epoch": 0.357425207007032, "grad_norm": 2.0356783866882324, "learning_rate": 0.00019979924016889718, "loss": 0.6801632881164551, "step": 60130 }, { "epoch": 0.35748464908370037, "grad_norm": 1.6458020210266113, "learning_rate": 0.00019979882441387053, "loss": 0.7037968158721923, "step": 60140 }, { "epoch": 0.3575440911603688, "grad_norm": 2.2725367546081543, "learning_rate": 0.0001997984082292757, "loss": 0.6844282627105713, "step": 60150 }, { "epoch": 0.3576035332370372, "grad_norm": 1.7725807428359985, "learning_rate": 0.00019979799161511458, "loss": 0.6860574722290039, "step": 60160 }, { "epoch": 0.35766297531370556, "grad_norm": 1.3463021516799927, "learning_rate": 0.00019979757457138923, "loss": 0.6800743103027344, "step": 60170 }, { "epoch": 0.35772241739037397, "grad_norm": 1.7769945859909058, "learning_rate": 0.00019979715709810166, "loss": 0.7304466247558594, "step": 60180 }, { "epoch": 0.35778185946704233, "grad_norm": 1.7553596496582031, "learning_rate": 0.00019979673919525378, "loss": 0.7225401878356934, "step": 60190 }, { "epoch": 0.35784130154371074, "grad_norm": 1.7605847120285034, "learning_rate": 0.0001997963208628477, "loss": 0.7794362545013428, "step": 60200 }, { "epoch": 0.3579007436203791, "grad_norm": 1.6492692232131958, "learning_rate": 0.00019979590210088535, "loss": 0.6866914749145507, "step": 60210 }, { "epoch": 0.3579601856970475, "grad_norm": 1.7032970190048218, "learning_rate": 0.00019979548290936875, "loss": 0.7342868328094483, "step": 60220 }, { "epoch": 0.3580196277737159, "grad_norm": 1.776860237121582, "learning_rate": 0.0001997950632882999, "loss": 0.7235825538635254, "step": 60230 }, { "epoch": 0.3580790698503843, "grad_norm": 1.6070431470870972, "learning_rate": 0.00019979464323768083, "loss": 0.6291347503662109, "step": 60240 }, { "epoch": 0.3581385119270527, "grad_norm": 1.5963196754455566, "learning_rate": 0.0001997942227575135, "loss": 0.7017431259155273, "step": 60250 }, { "epoch": 0.35819795400372106, "grad_norm": 1.5432804822921753, "learning_rate": 0.00019979380184779997, "loss": 0.7062376022338868, "step": 60260 }, { "epoch": 0.3582573960803895, "grad_norm": 1.5612361431121826, "learning_rate": 0.00019979338050854224, "loss": 0.7257232189178466, "step": 60270 }, { "epoch": 0.35831683815705784, "grad_norm": 2.0333712100982666, "learning_rate": 0.00019979295873974234, "loss": 0.7445805072784424, "step": 60280 }, { "epoch": 0.35837628023372625, "grad_norm": 1.574449062347412, "learning_rate": 0.00019979253654140225, "loss": 0.68594970703125, "step": 60290 }, { "epoch": 0.3584357223103946, "grad_norm": 1.4495575428009033, "learning_rate": 0.00019979211391352397, "loss": 0.6792004585266114, "step": 60300 }, { "epoch": 0.358495164387063, "grad_norm": 1.6701058149337769, "learning_rate": 0.0001997916908561096, "loss": 0.7041201591491699, "step": 60310 }, { "epoch": 0.35855460646373144, "grad_norm": 1.407344102859497, "learning_rate": 0.00019979126736916115, "loss": 0.6975620269775391, "step": 60320 }, { "epoch": 0.3586140485403998, "grad_norm": 1.446690559387207, "learning_rate": 0.00019979084345268057, "loss": 0.6948708534240723, "step": 60330 }, { "epoch": 0.3586734906170682, "grad_norm": 1.6636043787002563, "learning_rate": 0.00019979041910666995, "loss": 0.6616485118865967, "step": 60340 }, { "epoch": 0.3587329326937366, "grad_norm": 1.6461646556854248, "learning_rate": 0.00019978999433113134, "loss": 0.655792236328125, "step": 60350 }, { "epoch": 0.358792374770405, "grad_norm": 1.5863102674484253, "learning_rate": 0.00019978956912606674, "loss": 0.6812061786651611, "step": 60360 }, { "epoch": 0.35885181684707335, "grad_norm": 1.8092617988586426, "learning_rate": 0.00019978914349147816, "loss": 0.7192231178283691, "step": 60370 }, { "epoch": 0.35891125892374176, "grad_norm": 1.5035289525985718, "learning_rate": 0.00019978871742736765, "loss": 0.7274251461029053, "step": 60380 }, { "epoch": 0.3589707010004102, "grad_norm": 2.125729560852051, "learning_rate": 0.0001997882909337373, "loss": 0.7083567619323731, "step": 60390 }, { "epoch": 0.35903014307707853, "grad_norm": 1.5217362642288208, "learning_rate": 0.00019978786401058908, "loss": 0.6489438056945801, "step": 60400 }, { "epoch": 0.35908958515374695, "grad_norm": 1.5687439441680908, "learning_rate": 0.00019978743665792509, "loss": 0.7143103599548339, "step": 60410 }, { "epoch": 0.3591490272304153, "grad_norm": 1.5078368186950684, "learning_rate": 0.0001997870088757473, "loss": 0.6522539138793946, "step": 60420 }, { "epoch": 0.3592084693070837, "grad_norm": 1.682913899421692, "learning_rate": 0.00019978658066405785, "loss": 0.6911290168762207, "step": 60430 }, { "epoch": 0.3592679113837521, "grad_norm": 1.8456175327301025, "learning_rate": 0.0001997861520228587, "loss": 0.6580193519592286, "step": 60440 }, { "epoch": 0.3593273534604205, "grad_norm": 1.446535348892212, "learning_rate": 0.00019978572295215196, "loss": 0.6804872035980225, "step": 60450 }, { "epoch": 0.3593867955370889, "grad_norm": 1.7046643495559692, "learning_rate": 0.00019978529345193965, "loss": 0.6613917827606202, "step": 60460 }, { "epoch": 0.35944623761375727, "grad_norm": 1.4816174507141113, "learning_rate": 0.00019978486352222388, "loss": 0.7396352767944336, "step": 60470 }, { "epoch": 0.3595056796904257, "grad_norm": 2.0116121768951416, "learning_rate": 0.0001997844331630066, "loss": 0.7030426979064941, "step": 60480 }, { "epoch": 0.35956512176709404, "grad_norm": 1.5424104928970337, "learning_rate": 0.00019978400237429, "loss": 0.6738699913024903, "step": 60490 }, { "epoch": 0.35962456384376246, "grad_norm": 1.809678554534912, "learning_rate": 0.00019978357115607606, "loss": 0.6795842170715332, "step": 60500 }, { "epoch": 0.3596840059204308, "grad_norm": 1.4469690322875977, "learning_rate": 0.00019978313950836684, "loss": 0.6650561332702637, "step": 60510 }, { "epoch": 0.35974344799709923, "grad_norm": 2.2035164833068848, "learning_rate": 0.0001997827074311644, "loss": 0.749547290802002, "step": 60520 }, { "epoch": 0.3598028900737676, "grad_norm": 1.6125949621200562, "learning_rate": 0.00019978227492447085, "loss": 0.6990048885345459, "step": 60530 }, { "epoch": 0.359862332150436, "grad_norm": 1.7038443088531494, "learning_rate": 0.00019978184198828826, "loss": 0.7299538612365722, "step": 60540 }, { "epoch": 0.3599217742271044, "grad_norm": 1.5365557670593262, "learning_rate": 0.00019978140862261866, "loss": 0.6738224983215332, "step": 60550 }, { "epoch": 0.3599812163037728, "grad_norm": 1.8362360000610352, "learning_rate": 0.00019978097482746413, "loss": 0.7645692825317383, "step": 60560 }, { "epoch": 0.3600406583804412, "grad_norm": 1.5800248384475708, "learning_rate": 0.0001997805406028268, "loss": 0.7277621269226074, "step": 60570 }, { "epoch": 0.36010010045710955, "grad_norm": 1.807474970817566, "learning_rate": 0.00019978010594870867, "loss": 0.7215195655822754, "step": 60580 }, { "epoch": 0.36015954253377797, "grad_norm": 1.748934030532837, "learning_rate": 0.00019977967086511183, "loss": 0.724320363998413, "step": 60590 }, { "epoch": 0.3602189846104463, "grad_norm": 1.8082109689712524, "learning_rate": 0.00019977923535203842, "loss": 0.6810701370239258, "step": 60600 }, { "epoch": 0.36027842668711474, "grad_norm": 1.6290208101272583, "learning_rate": 0.00019977879940949046, "loss": 0.6733053684234619, "step": 60610 }, { "epoch": 0.36033786876378315, "grad_norm": 1.6346526145935059, "learning_rate": 0.0001997783630374701, "loss": 0.6777590751647949, "step": 60620 }, { "epoch": 0.3603973108404515, "grad_norm": 2.1238276958465576, "learning_rate": 0.00019977792623597938, "loss": 0.7030363082885742, "step": 60630 }, { "epoch": 0.3604567529171199, "grad_norm": 1.5483713150024414, "learning_rate": 0.0001997774890050204, "loss": 0.7095569610595703, "step": 60640 }, { "epoch": 0.3605161949937883, "grad_norm": 1.591946005821228, "learning_rate": 0.00019977705134459524, "loss": 0.6919459342956543, "step": 60650 }, { "epoch": 0.3605756370704567, "grad_norm": 1.298514723777771, "learning_rate": 0.00019977661325470603, "loss": 0.6483250617980957, "step": 60660 }, { "epoch": 0.36063507914712506, "grad_norm": 1.6259286403656006, "learning_rate": 0.00019977617473535483, "loss": 0.7060620307922363, "step": 60670 }, { "epoch": 0.3606945212237935, "grad_norm": 2.0138723850250244, "learning_rate": 0.00019977573578654372, "loss": 0.7375548839569092, "step": 60680 }, { "epoch": 0.3607539633004619, "grad_norm": 1.6229287385940552, "learning_rate": 0.00019977529640827487, "loss": 0.732399845123291, "step": 60690 }, { "epoch": 0.36081340537713025, "grad_norm": 2.303609609603882, "learning_rate": 0.00019977485660055031, "loss": 0.7431624889373779, "step": 60700 }, { "epoch": 0.36087284745379866, "grad_norm": 1.81524658203125, "learning_rate": 0.0001997744163633722, "loss": 0.6912967681884765, "step": 60710 }, { "epoch": 0.360932289530467, "grad_norm": 1.536676049232483, "learning_rate": 0.0001997739756967426, "loss": 0.5991087913513183, "step": 60720 }, { "epoch": 0.36099173160713544, "grad_norm": 2.0651612281799316, "learning_rate": 0.00019977353460066366, "loss": 0.6783011436462403, "step": 60730 }, { "epoch": 0.3610511736838038, "grad_norm": 1.7500455379486084, "learning_rate": 0.00019977309307513743, "loss": 0.6515349388122559, "step": 60740 }, { "epoch": 0.3611106157604722, "grad_norm": 1.1706547737121582, "learning_rate": 0.0001997726511201661, "loss": 0.6167591571807861, "step": 60750 }, { "epoch": 0.3611700578371406, "grad_norm": 2.0206449031829834, "learning_rate": 0.00019977220873575174, "loss": 0.728969955444336, "step": 60760 }, { "epoch": 0.361229499913809, "grad_norm": 1.733901858329773, "learning_rate": 0.00019977176592189647, "loss": 0.6705748558044433, "step": 60770 }, { "epoch": 0.3612889419904774, "grad_norm": 1.5962752103805542, "learning_rate": 0.00019977132267860238, "loss": 0.6740942001342773, "step": 60780 }, { "epoch": 0.36134838406714576, "grad_norm": 1.3100155591964722, "learning_rate": 0.0001997708790058717, "loss": 0.6748569965362549, "step": 60790 }, { "epoch": 0.36140782614381417, "grad_norm": 1.7277727127075195, "learning_rate": 0.00019977043490370638, "loss": 0.6983396530151367, "step": 60800 }, { "epoch": 0.36146726822048253, "grad_norm": 1.7328225374221802, "learning_rate": 0.00019976999037210868, "loss": 0.6374560832977295, "step": 60810 }, { "epoch": 0.36152671029715094, "grad_norm": 1.6529672145843506, "learning_rate": 0.00019976954541108067, "loss": 0.7097318649291993, "step": 60820 }, { "epoch": 0.36158615237381936, "grad_norm": 2.0469980239868164, "learning_rate": 0.0001997691000206245, "loss": 0.713815450668335, "step": 60830 }, { "epoch": 0.3616455944504877, "grad_norm": 1.859628438949585, "learning_rate": 0.0001997686542007423, "loss": 0.7089085578918457, "step": 60840 }, { "epoch": 0.36170503652715613, "grad_norm": 1.4217394590377808, "learning_rate": 0.00019976820795143617, "loss": 0.7103249549865722, "step": 60850 }, { "epoch": 0.3617644786038245, "grad_norm": 1.680533528327942, "learning_rate": 0.00019976776127270828, "loss": 0.6894359111785888, "step": 60860 }, { "epoch": 0.3618239206804929, "grad_norm": 1.9171677827835083, "learning_rate": 0.00019976731416456077, "loss": 0.6733160972595215, "step": 60870 }, { "epoch": 0.36188336275716126, "grad_norm": 1.871544599533081, "learning_rate": 0.00019976686662699576, "loss": 0.7042304039001465, "step": 60880 }, { "epoch": 0.3619428048338297, "grad_norm": 1.6959577798843384, "learning_rate": 0.00019976641866001539, "loss": 0.6795129299163818, "step": 60890 }, { "epoch": 0.36200224691049804, "grad_norm": 1.521336555480957, "learning_rate": 0.0001997659702636218, "loss": 0.6673981666564941, "step": 60900 }, { "epoch": 0.36206168898716645, "grad_norm": 1.6889396905899048, "learning_rate": 0.00019976552143781718, "loss": 0.7257678031921386, "step": 60910 }, { "epoch": 0.36212113106383487, "grad_norm": 1.3218570947647095, "learning_rate": 0.0001997650721826036, "loss": 0.651371955871582, "step": 60920 }, { "epoch": 0.3621805731405032, "grad_norm": 1.5541402101516724, "learning_rate": 0.00019976462249798326, "loss": 0.7507365226745606, "step": 60930 }, { "epoch": 0.36224001521717164, "grad_norm": 2.3909451961517334, "learning_rate": 0.00019976417238395832, "loss": 0.7394299507141113, "step": 60940 }, { "epoch": 0.36229945729384, "grad_norm": 1.6653943061828613, "learning_rate": 0.0001997637218405309, "loss": 0.6425566673278809, "step": 60950 }, { "epoch": 0.3623588993705084, "grad_norm": 1.8434336185455322, "learning_rate": 0.00019976327086770318, "loss": 0.7479284286499024, "step": 60960 }, { "epoch": 0.3624183414471768, "grad_norm": 1.835404872894287, "learning_rate": 0.0001997628194654773, "loss": 0.752554178237915, "step": 60970 }, { "epoch": 0.3624777835238452, "grad_norm": 1.5585694313049316, "learning_rate": 0.00019976236763385544, "loss": 0.6757954597473145, "step": 60980 }, { "epoch": 0.3625372256005136, "grad_norm": 1.8138983249664307, "learning_rate": 0.00019976191537283972, "loss": 0.7837859153747558, "step": 60990 }, { "epoch": 0.36259666767718196, "grad_norm": 1.4798980951309204, "learning_rate": 0.00019976146268243234, "loss": 0.6569931030273437, "step": 61000 }, { "epoch": 0.3626561097538504, "grad_norm": 2.2331578731536865, "learning_rate": 0.00019976100956263547, "loss": 0.6583796977996826, "step": 61010 }, { "epoch": 0.36271555183051873, "grad_norm": 1.6409602165222168, "learning_rate": 0.00019976055601345126, "loss": 0.6662280559539795, "step": 61020 }, { "epoch": 0.36277499390718715, "grad_norm": 1.7004956007003784, "learning_rate": 0.0001997601020348819, "loss": 0.7715317726135253, "step": 61030 }, { "epoch": 0.3628344359838555, "grad_norm": 1.3155475854873657, "learning_rate": 0.00019975964762692952, "loss": 0.6440342903137207, "step": 61040 }, { "epoch": 0.3628938780605239, "grad_norm": 1.8248140811920166, "learning_rate": 0.0001997591927895963, "loss": 0.6396561622619629, "step": 61050 }, { "epoch": 0.36295332013719234, "grad_norm": 1.8025881052017212, "learning_rate": 0.00019975873752288447, "loss": 0.7560142517089844, "step": 61060 }, { "epoch": 0.3630127622138607, "grad_norm": 1.8360888957977295, "learning_rate": 0.0001997582818267962, "loss": 0.6591153621673584, "step": 61070 }, { "epoch": 0.3630722042905291, "grad_norm": 1.765034556388855, "learning_rate": 0.0001997578257013336, "loss": 0.6742057800292969, "step": 61080 }, { "epoch": 0.36313164636719747, "grad_norm": 1.514523983001709, "learning_rate": 0.00019975736914649888, "loss": 0.6788823127746582, "step": 61090 }, { "epoch": 0.3631910884438659, "grad_norm": 1.4812673330307007, "learning_rate": 0.00019975691216229425, "loss": 0.7492002487182617, "step": 61100 }, { "epoch": 0.36325053052053424, "grad_norm": 1.9252583980560303, "learning_rate": 0.00019975645474872193, "loss": 0.6912355422973633, "step": 61110 }, { "epoch": 0.36330997259720266, "grad_norm": 2.086449384689331, "learning_rate": 0.00019975599690578403, "loss": 0.7130432605743409, "step": 61120 }, { "epoch": 0.36336941467387107, "grad_norm": 2.0100340843200684, "learning_rate": 0.0001997555386334828, "loss": 0.7035342216491699, "step": 61130 }, { "epoch": 0.36342885675053943, "grad_norm": 1.8194856643676758, "learning_rate": 0.00019975507993182033, "loss": 0.6672362327575684, "step": 61140 }, { "epoch": 0.36348829882720785, "grad_norm": 2.239663600921631, "learning_rate": 0.00019975462080079896, "loss": 0.6978329658508301, "step": 61150 }, { "epoch": 0.3635477409038762, "grad_norm": 2.011847972869873, "learning_rate": 0.0001997541612404208, "loss": 0.7010546684265136, "step": 61160 }, { "epoch": 0.3636071829805446, "grad_norm": 2.239011287689209, "learning_rate": 0.00019975370125068808, "loss": 0.6299660682678223, "step": 61170 }, { "epoch": 0.363666625057213, "grad_norm": 1.6411375999450684, "learning_rate": 0.00019975324083160295, "loss": 0.6916932106018067, "step": 61180 }, { "epoch": 0.3637260671338814, "grad_norm": 1.9440901279449463, "learning_rate": 0.00019975277998316766, "loss": 0.7506142616271972, "step": 61190 }, { "epoch": 0.3637855092105498, "grad_norm": 1.900726079940796, "learning_rate": 0.00019975231870538438, "loss": 0.7073695182800293, "step": 61200 }, { "epoch": 0.36384495128721817, "grad_norm": 1.600393295288086, "learning_rate": 0.0001997518569982554, "loss": 0.6710264682769775, "step": 61210 }, { "epoch": 0.3639043933638866, "grad_norm": 1.5118802785873413, "learning_rate": 0.0001997513948617828, "loss": 0.7217975616455078, "step": 61220 }, { "epoch": 0.36396383544055494, "grad_norm": 1.6097153425216675, "learning_rate": 0.00019975093229596892, "loss": 0.7534433364868164, "step": 61230 }, { "epoch": 0.36402327751722335, "grad_norm": 1.8910267353057861, "learning_rate": 0.00019975046930081588, "loss": 0.7266236305236816, "step": 61240 }, { "epoch": 0.3640827195938917, "grad_norm": 1.5952762365341187, "learning_rate": 0.0001997500058763259, "loss": 0.6411478042602539, "step": 61250 }, { "epoch": 0.3641421616705601, "grad_norm": 1.627125859260559, "learning_rate": 0.00019974954202250128, "loss": 0.6948518276214599, "step": 61260 }, { "epoch": 0.3642016037472285, "grad_norm": 1.5985896587371826, "learning_rate": 0.00019974907773934414, "loss": 0.7096689701080322, "step": 61270 }, { "epoch": 0.3642610458238969, "grad_norm": 1.6637194156646729, "learning_rate": 0.00019974861302685673, "loss": 0.7044756412506104, "step": 61280 }, { "epoch": 0.3643204879005653, "grad_norm": 1.511237382888794, "learning_rate": 0.00019974814788504132, "loss": 0.7177659034729004, "step": 61290 }, { "epoch": 0.3643799299772337, "grad_norm": 1.6380740404129028, "learning_rate": 0.00019974768231390008, "loss": 0.6745600223541259, "step": 61300 }, { "epoch": 0.3644393720539021, "grad_norm": 1.5275182723999023, "learning_rate": 0.00019974721631343527, "loss": 0.7272407531738281, "step": 61310 }, { "epoch": 0.36449881413057045, "grad_norm": 1.4434698820114136, "learning_rate": 0.00019974674988364912, "loss": 0.6934822082519532, "step": 61320 }, { "epoch": 0.36455825620723886, "grad_norm": 2.265841245651245, "learning_rate": 0.00019974628302454385, "loss": 0.7008661270141602, "step": 61330 }, { "epoch": 0.3646176982839072, "grad_norm": 1.3422231674194336, "learning_rate": 0.00019974581573612164, "loss": 0.6656861305236816, "step": 61340 }, { "epoch": 0.36467714036057564, "grad_norm": 1.6153342723846436, "learning_rate": 0.00019974534801838481, "loss": 0.6638421058654785, "step": 61350 }, { "epoch": 0.36473658243724405, "grad_norm": 1.7107055187225342, "learning_rate": 0.00019974487987133556, "loss": 0.6985599517822265, "step": 61360 }, { "epoch": 0.3647960245139124, "grad_norm": 2.3345324993133545, "learning_rate": 0.00019974441129497615, "loss": 0.6976466178894043, "step": 61370 }, { "epoch": 0.3648554665905808, "grad_norm": 1.5168192386627197, "learning_rate": 0.00019974394228930878, "loss": 0.6556812286376953, "step": 61380 }, { "epoch": 0.3649149086672492, "grad_norm": 1.7507082223892212, "learning_rate": 0.0001997434728543357, "loss": 0.6979930877685547, "step": 61390 }, { "epoch": 0.3649743507439176, "grad_norm": 1.7281405925750732, "learning_rate": 0.00019974300299005924, "loss": 0.6944322109222412, "step": 61400 }, { "epoch": 0.36503379282058596, "grad_norm": 1.7779721021652222, "learning_rate": 0.00019974253269648156, "loss": 0.6473734855651856, "step": 61410 }, { "epoch": 0.36509323489725437, "grad_norm": 2.2019596099853516, "learning_rate": 0.00019974206197360492, "loss": 0.6610103607177734, "step": 61420 }, { "epoch": 0.3651526769739228, "grad_norm": 1.431780219078064, "learning_rate": 0.00019974159082143157, "loss": 0.7416062355041504, "step": 61430 }, { "epoch": 0.36521211905059114, "grad_norm": 1.4612581729888916, "learning_rate": 0.0001997411192399638, "loss": 0.6709086418151855, "step": 61440 }, { "epoch": 0.36527156112725956, "grad_norm": 1.0051718950271606, "learning_rate": 0.00019974064722920383, "loss": 0.6824808597564698, "step": 61450 }, { "epoch": 0.3653310032039279, "grad_norm": 1.9348393678665161, "learning_rate": 0.00019974017478915394, "loss": 0.6729562282562256, "step": 61460 }, { "epoch": 0.36539044528059633, "grad_norm": 1.384648323059082, "learning_rate": 0.00019973970191981637, "loss": 0.6647126197814941, "step": 61470 }, { "epoch": 0.3654498873572647, "grad_norm": 1.374955177307129, "learning_rate": 0.0001997392286211934, "loss": 0.7084073066711426, "step": 61480 }, { "epoch": 0.3655093294339331, "grad_norm": 1.750972867012024, "learning_rate": 0.0001997387548932873, "loss": 0.6740675926208496, "step": 61490 }, { "epoch": 0.3655687715106015, "grad_norm": 1.6837915182113647, "learning_rate": 0.0001997382807361003, "loss": 0.6967741489410401, "step": 61500 }, { "epoch": 0.3656282135872699, "grad_norm": 1.6709682941436768, "learning_rate": 0.0001997378061496347, "loss": 0.6435904979705811, "step": 61510 }, { "epoch": 0.3656876556639383, "grad_norm": 1.485779881477356, "learning_rate": 0.00019973733113389276, "loss": 0.6787967681884766, "step": 61520 }, { "epoch": 0.36574709774060665, "grad_norm": 1.9694747924804688, "learning_rate": 0.00019973685568887674, "loss": 0.6771230220794677, "step": 61530 }, { "epoch": 0.36580653981727507, "grad_norm": 2.0823819637298584, "learning_rate": 0.00019973637981458896, "loss": 0.7158881664276123, "step": 61540 }, { "epoch": 0.3658659818939434, "grad_norm": 1.6539196968078613, "learning_rate": 0.00019973590351103165, "loss": 0.6761195182800293, "step": 61550 }, { "epoch": 0.36592542397061184, "grad_norm": 1.448853850364685, "learning_rate": 0.00019973542677820713, "loss": 0.6906716346740722, "step": 61560 }, { "epoch": 0.36598486604728026, "grad_norm": 1.4245833158493042, "learning_rate": 0.00019973494961611762, "loss": 0.6980271339416504, "step": 61570 }, { "epoch": 0.3660443081239486, "grad_norm": 1.5796645879745483, "learning_rate": 0.00019973447202476543, "loss": 0.65110182762146, "step": 61580 }, { "epoch": 0.36610375020061703, "grad_norm": 1.9003525972366333, "learning_rate": 0.0001997339940041529, "loss": 0.6888967514038086, "step": 61590 }, { "epoch": 0.3661631922772854, "grad_norm": 1.8961259126663208, "learning_rate": 0.00019973351555428222, "loss": 0.6962116241455079, "step": 61600 }, { "epoch": 0.3662226343539538, "grad_norm": 1.5163524150848389, "learning_rate": 0.00019973303667515573, "loss": 0.6763210296630859, "step": 61610 }, { "epoch": 0.36628207643062216, "grad_norm": 1.8448364734649658, "learning_rate": 0.00019973255736677574, "loss": 0.688755989074707, "step": 61620 }, { "epoch": 0.3663415185072906, "grad_norm": 1.6353485584259033, "learning_rate": 0.00019973207762914453, "loss": 0.689772081375122, "step": 61630 }, { "epoch": 0.36640096058395893, "grad_norm": 1.9994148015975952, "learning_rate": 0.00019973159746226434, "loss": 0.6627715110778809, "step": 61640 }, { "epoch": 0.36646040266062735, "grad_norm": 1.9908381700515747, "learning_rate": 0.00019973111686613754, "loss": 0.7027157306671142, "step": 61650 }, { "epoch": 0.36651984473729576, "grad_norm": 1.5444021224975586, "learning_rate": 0.0001997306358407664, "loss": 0.6804385185241699, "step": 61660 }, { "epoch": 0.3665792868139641, "grad_norm": 1.726616621017456, "learning_rate": 0.0001997301543861532, "loss": 0.7118904113769531, "step": 61670 }, { "epoch": 0.36663872889063254, "grad_norm": 1.3987241983413696, "learning_rate": 0.00019972967250230032, "loss": 0.7011579990386962, "step": 61680 }, { "epoch": 0.3666981709673009, "grad_norm": 1.6186912059783936, "learning_rate": 0.00019972919018920997, "loss": 0.6675704956054688, "step": 61690 }, { "epoch": 0.3667576130439693, "grad_norm": 1.71880304813385, "learning_rate": 0.00019972870744688453, "loss": 0.676072072982788, "step": 61700 }, { "epoch": 0.36681705512063767, "grad_norm": 1.2855528593063354, "learning_rate": 0.00019972822427532624, "loss": 0.6999807834625245, "step": 61710 }, { "epoch": 0.3668764971973061, "grad_norm": 2.0955891609191895, "learning_rate": 0.00019972774067453746, "loss": 0.6212400436401367, "step": 61720 }, { "epoch": 0.3669359392739745, "grad_norm": 1.7224197387695312, "learning_rate": 0.0001997272566445205, "loss": 0.732081413269043, "step": 61730 }, { "epoch": 0.36699538135064286, "grad_norm": 1.6315609216690063, "learning_rate": 0.00019972677218527764, "loss": 0.7434513092041015, "step": 61740 }, { "epoch": 0.36705482342731127, "grad_norm": 1.6133861541748047, "learning_rate": 0.00019972628729681126, "loss": 0.6350156784057617, "step": 61750 }, { "epoch": 0.36711426550397963, "grad_norm": 1.6001174449920654, "learning_rate": 0.00019972580197912362, "loss": 0.6993905544281006, "step": 61760 }, { "epoch": 0.36717370758064805, "grad_norm": 1.7609671354293823, "learning_rate": 0.0001997253162322171, "loss": 0.6943482875823974, "step": 61770 }, { "epoch": 0.3672331496573164, "grad_norm": 1.6460120677947998, "learning_rate": 0.00019972483005609396, "loss": 0.7194986343383789, "step": 61780 }, { "epoch": 0.3672925917339848, "grad_norm": 1.4594403505325317, "learning_rate": 0.00019972434345075655, "loss": 0.6781061172485352, "step": 61790 }, { "epoch": 0.36735203381065323, "grad_norm": 1.7744113206863403, "learning_rate": 0.00019972385641620722, "loss": 0.7118089199066162, "step": 61800 }, { "epoch": 0.3674114758873216, "grad_norm": 1.7182387113571167, "learning_rate": 0.00019972336895244828, "loss": 0.6759722709655762, "step": 61810 }, { "epoch": 0.36747091796399, "grad_norm": 2.086469888687134, "learning_rate": 0.00019972288105948207, "loss": 0.6875753402709961, "step": 61820 }, { "epoch": 0.36753036004065837, "grad_norm": 1.5840474367141724, "learning_rate": 0.00019972239273731093, "loss": 0.6627098083496094, "step": 61830 }, { "epoch": 0.3675898021173268, "grad_norm": 1.5945696830749512, "learning_rate": 0.00019972190398593717, "loss": 0.7242193222045898, "step": 61840 }, { "epoch": 0.36764924419399514, "grad_norm": 1.7983568906784058, "learning_rate": 0.00019972141480536313, "loss": 0.7015552997589112, "step": 61850 }, { "epoch": 0.36770868627066355, "grad_norm": 1.7020517587661743, "learning_rate": 0.00019972092519559117, "loss": 0.6998116493225097, "step": 61860 }, { "epoch": 0.36776812834733197, "grad_norm": 2.073626756668091, "learning_rate": 0.00019972043515662362, "loss": 0.7137404441833496, "step": 61870 }, { "epoch": 0.3678275704240003, "grad_norm": 1.7036153078079224, "learning_rate": 0.00019971994468846285, "loss": 0.7319119930267334, "step": 61880 }, { "epoch": 0.36788701250066874, "grad_norm": 1.801773190498352, "learning_rate": 0.00019971945379111116, "loss": 0.673799705505371, "step": 61890 }, { "epoch": 0.3679464545773371, "grad_norm": 1.7125617265701294, "learning_rate": 0.00019971896246457095, "loss": 0.7346949577331543, "step": 61900 }, { "epoch": 0.3680058966540055, "grad_norm": 1.7757929563522339, "learning_rate": 0.00019971847070884453, "loss": 0.6453509330749512, "step": 61910 }, { "epoch": 0.3680653387306739, "grad_norm": 1.554063081741333, "learning_rate": 0.00019971797852393427, "loss": 0.7053179740905762, "step": 61920 }, { "epoch": 0.3681247808073423, "grad_norm": 1.9873826503753662, "learning_rate": 0.00019971748590984253, "loss": 0.7169812202453614, "step": 61930 }, { "epoch": 0.3681842228840107, "grad_norm": 2.0190980434417725, "learning_rate": 0.00019971699286657163, "loss": 0.7057165622711181, "step": 61940 }, { "epoch": 0.36824366496067906, "grad_norm": 2.039571762084961, "learning_rate": 0.00019971649939412396, "loss": 0.6917969703674316, "step": 61950 }, { "epoch": 0.3683031070373475, "grad_norm": 1.638147234916687, "learning_rate": 0.0001997160054925019, "loss": 0.6505790710449219, "step": 61960 }, { "epoch": 0.36836254911401584, "grad_norm": 2.4202170372009277, "learning_rate": 0.00019971551116170776, "loss": 0.7157408714294433, "step": 61970 }, { "epoch": 0.36842199119068425, "grad_norm": 1.4139881134033203, "learning_rate": 0.00019971501640174394, "loss": 0.6936065673828125, "step": 61980 }, { "epoch": 0.3684814332673526, "grad_norm": 1.8862618207931519, "learning_rate": 0.00019971452121261282, "loss": 0.7417250633239746, "step": 61990 }, { "epoch": 0.368540875344021, "grad_norm": 1.7197105884552002, "learning_rate": 0.00019971402559431677, "loss": 0.6990926742553711, "step": 62000 }, { "epoch": 0.3686003174206894, "grad_norm": 1.7023152112960815, "learning_rate": 0.0001997135295468581, "loss": 0.7170560836791993, "step": 62010 }, { "epoch": 0.3686597594973578, "grad_norm": 1.6921753883361816, "learning_rate": 0.00019971303307023922, "loss": 0.707404613494873, "step": 62020 }, { "epoch": 0.3687192015740262, "grad_norm": 1.4450238943099976, "learning_rate": 0.00019971253616446252, "loss": 0.6810608863830566, "step": 62030 }, { "epoch": 0.36877864365069457, "grad_norm": 1.7101777791976929, "learning_rate": 0.00019971203882953039, "loss": 0.6658106803894043, "step": 62040 }, { "epoch": 0.368838085727363, "grad_norm": 2.387690305709839, "learning_rate": 0.00019971154106544515, "loss": 0.7097156047821045, "step": 62050 }, { "epoch": 0.36889752780403134, "grad_norm": 1.6276986598968506, "learning_rate": 0.00019971104287220921, "loss": 0.6851402759552002, "step": 62060 }, { "epoch": 0.36895696988069976, "grad_norm": 1.961549162864685, "learning_rate": 0.000199710544249825, "loss": 0.7099821090698242, "step": 62070 }, { "epoch": 0.3690164119573681, "grad_norm": 1.6553945541381836, "learning_rate": 0.00019971004519829484, "loss": 0.7712077140808106, "step": 62080 }, { "epoch": 0.36907585403403653, "grad_norm": 1.605698585510254, "learning_rate": 0.00019970954571762114, "loss": 0.6601093292236329, "step": 62090 }, { "epoch": 0.36913529611070495, "grad_norm": 2.020764112472534, "learning_rate": 0.0001997090458078063, "loss": 0.6137429237365722, "step": 62100 }, { "epoch": 0.3691947381873733, "grad_norm": 2.1309995651245117, "learning_rate": 0.00019970854546885267, "loss": 0.6597514152526855, "step": 62110 }, { "epoch": 0.3692541802640417, "grad_norm": 1.4734026193618774, "learning_rate": 0.0001997080447007627, "loss": 0.7197447776794433, "step": 62120 }, { "epoch": 0.3693136223407101, "grad_norm": 1.530280351638794, "learning_rate": 0.00019970754350353878, "loss": 0.6448897361755371, "step": 62130 }, { "epoch": 0.3693730644173785, "grad_norm": 1.7397462129592896, "learning_rate": 0.00019970704187718328, "loss": 0.6349791049957275, "step": 62140 }, { "epoch": 0.36943250649404685, "grad_norm": 1.6243159770965576, "learning_rate": 0.0001997065398216986, "loss": 0.708098030090332, "step": 62150 }, { "epoch": 0.36949194857071527, "grad_norm": 1.6551493406295776, "learning_rate": 0.00019970603733708716, "loss": 0.7116414070129394, "step": 62160 }, { "epoch": 0.3695513906473837, "grad_norm": 1.603873610496521, "learning_rate": 0.00019970553442335133, "loss": 0.6736937522888183, "step": 62170 }, { "epoch": 0.36961083272405204, "grad_norm": 1.595481038093567, "learning_rate": 0.00019970503108049354, "loss": 0.6623373985290527, "step": 62180 }, { "epoch": 0.36967027480072046, "grad_norm": 1.598983645439148, "learning_rate": 0.0001997045273085162, "loss": 0.6392831325531005, "step": 62190 }, { "epoch": 0.3697297168773888, "grad_norm": 1.7162226438522339, "learning_rate": 0.00019970402310742172, "loss": 0.6812395095825196, "step": 62200 }, { "epoch": 0.36978915895405723, "grad_norm": 1.545601725578308, "learning_rate": 0.00019970351847721255, "loss": 0.7238896369934082, "step": 62210 }, { "epoch": 0.3698486010307256, "grad_norm": 2.0157480239868164, "learning_rate": 0.000199703013417891, "loss": 0.6242643356323242, "step": 62220 }, { "epoch": 0.369908043107394, "grad_norm": 1.4840046167373657, "learning_rate": 0.0001997025079294596, "loss": 0.674782657623291, "step": 62230 }, { "epoch": 0.3699674851840624, "grad_norm": 2.0289111137390137, "learning_rate": 0.0001997020020119207, "loss": 0.7344814300537109, "step": 62240 }, { "epoch": 0.3700269272607308, "grad_norm": 1.7818113565444946, "learning_rate": 0.00019970149566527672, "loss": 0.727292823791504, "step": 62250 }, { "epoch": 0.3700863693373992, "grad_norm": 1.6774358749389648, "learning_rate": 0.0001997009888895301, "loss": 0.7169845581054688, "step": 62260 }, { "epoch": 0.37014581141406755, "grad_norm": 2.303814649581909, "learning_rate": 0.00019970048168468327, "loss": 0.646452522277832, "step": 62270 }, { "epoch": 0.37020525349073596, "grad_norm": 1.5816900730133057, "learning_rate": 0.00019969997405073865, "loss": 0.631997013092041, "step": 62280 }, { "epoch": 0.3702646955674043, "grad_norm": 2.1058578491210938, "learning_rate": 0.0001996994659876987, "loss": 0.7193540573120117, "step": 62290 }, { "epoch": 0.37032413764407274, "grad_norm": 1.6290377378463745, "learning_rate": 0.00019969895749556577, "loss": 0.7412985324859619, "step": 62300 }, { "epoch": 0.3703835797207411, "grad_norm": 2.077275037765503, "learning_rate": 0.00019969844857434238, "loss": 0.711552095413208, "step": 62310 }, { "epoch": 0.3704430217974095, "grad_norm": 1.5131131410598755, "learning_rate": 0.0001996979392240309, "loss": 0.7277741432189941, "step": 62320 }, { "epoch": 0.3705024638740779, "grad_norm": 1.6172614097595215, "learning_rate": 0.00019969742944463378, "loss": 0.6643445014953613, "step": 62330 }, { "epoch": 0.3705619059507463, "grad_norm": 1.7546451091766357, "learning_rate": 0.00019969691923615353, "loss": 0.6703731536865234, "step": 62340 }, { "epoch": 0.3706213480274147, "grad_norm": 1.9964557886123657, "learning_rate": 0.00019969640859859248, "loss": 0.6139588356018066, "step": 62350 }, { "epoch": 0.37068079010408306, "grad_norm": 1.9822801351547241, "learning_rate": 0.00019969589753195312, "loss": 0.6843849182128906, "step": 62360 }, { "epoch": 0.37074023218075147, "grad_norm": 1.457794427871704, "learning_rate": 0.00019969538603623795, "loss": 0.6855079174041748, "step": 62370 }, { "epoch": 0.37079967425741983, "grad_norm": 1.6264843940734863, "learning_rate": 0.0001996948741114493, "loss": 0.7468720436096191, "step": 62380 }, { "epoch": 0.37085911633408825, "grad_norm": 1.854577898979187, "learning_rate": 0.00019969436175758975, "loss": 0.6986120223999024, "step": 62390 }, { "epoch": 0.37091855841075666, "grad_norm": 1.3808423280715942, "learning_rate": 0.00019969384897466165, "loss": 0.7081506729125977, "step": 62400 }, { "epoch": 0.370978000487425, "grad_norm": 1.7580456733703613, "learning_rate": 0.0001996933357626675, "loss": 0.6541203498840332, "step": 62410 }, { "epoch": 0.37103744256409343, "grad_norm": 1.498624563217163, "learning_rate": 0.00019969282212160973, "loss": 0.6735468864440918, "step": 62420 }, { "epoch": 0.3710968846407618, "grad_norm": 1.5495362281799316, "learning_rate": 0.00019969230805149082, "loss": 0.7559614658355713, "step": 62430 }, { "epoch": 0.3711563267174302, "grad_norm": 1.6295427083969116, "learning_rate": 0.0001996917935523132, "loss": 0.7352779388427735, "step": 62440 }, { "epoch": 0.37121576879409857, "grad_norm": 2.0260121822357178, "learning_rate": 0.0001996912786240794, "loss": 0.673878288269043, "step": 62450 }, { "epoch": 0.371275210870767, "grad_norm": 1.6125637292861938, "learning_rate": 0.0001996907632667918, "loss": 0.6934963226318359, "step": 62460 }, { "epoch": 0.3713346529474354, "grad_norm": 1.8805863857269287, "learning_rate": 0.00019969024748045289, "loss": 0.6763069152832031, "step": 62470 }, { "epoch": 0.37139409502410375, "grad_norm": 1.8880290985107422, "learning_rate": 0.00019968973126506515, "loss": 0.6473128318786621, "step": 62480 }, { "epoch": 0.37145353710077217, "grad_norm": 1.8387802839279175, "learning_rate": 0.00019968921462063107, "loss": 0.6830962181091309, "step": 62490 }, { "epoch": 0.3715129791774405, "grad_norm": 2.0661420822143555, "learning_rate": 0.0001996886975471531, "loss": 0.6769375801086426, "step": 62500 }, { "epoch": 0.37157242125410894, "grad_norm": 1.898975133895874, "learning_rate": 0.00019968818004463366, "loss": 0.7383899688720703, "step": 62510 }, { "epoch": 0.3716318633307773, "grad_norm": 1.7116726636886597, "learning_rate": 0.00019968766211307532, "loss": 0.6922760963439941, "step": 62520 }, { "epoch": 0.3716913054074457, "grad_norm": 1.4966386556625366, "learning_rate": 0.00019968714375248053, "loss": 0.635605001449585, "step": 62530 }, { "epoch": 0.37175074748411413, "grad_norm": 1.465057134628296, "learning_rate": 0.00019968662496285173, "loss": 0.682574462890625, "step": 62540 }, { "epoch": 0.3718101895607825, "grad_norm": 1.5520260334014893, "learning_rate": 0.00019968610574419145, "loss": 0.6485562324523926, "step": 62550 }, { "epoch": 0.3718696316374509, "grad_norm": 1.7898837327957153, "learning_rate": 0.00019968558609650212, "loss": 0.6920854568481445, "step": 62560 }, { "epoch": 0.37192907371411926, "grad_norm": 1.8020843267440796, "learning_rate": 0.00019968506601978627, "loss": 0.7170676231384278, "step": 62570 }, { "epoch": 0.3719885157907877, "grad_norm": 1.797627329826355, "learning_rate": 0.00019968454551404636, "loss": 0.634966230392456, "step": 62580 }, { "epoch": 0.37204795786745604, "grad_norm": 1.7242423295974731, "learning_rate": 0.0001996840245792849, "loss": 0.7048195838928223, "step": 62590 }, { "epoch": 0.37210739994412445, "grad_norm": 1.6654129028320312, "learning_rate": 0.00019968350321550435, "loss": 0.7218607902526856, "step": 62600 }, { "epoch": 0.37216684202079287, "grad_norm": 1.1990662813186646, "learning_rate": 0.00019968298142270728, "loss": 0.6562827110290528, "step": 62610 }, { "epoch": 0.3722262840974612, "grad_norm": 1.556074857711792, "learning_rate": 0.00019968245920089613, "loss": 0.6977426528930664, "step": 62620 }, { "epoch": 0.37228572617412964, "grad_norm": 1.681140661239624, "learning_rate": 0.00019968193655007336, "loss": 0.6966331481933594, "step": 62630 }, { "epoch": 0.372345168250798, "grad_norm": 1.6445270776748657, "learning_rate": 0.00019968141347024155, "loss": 0.716864013671875, "step": 62640 }, { "epoch": 0.3724046103274664, "grad_norm": 2.016723155975342, "learning_rate": 0.00019968088996140317, "loss": 0.7129031181335449, "step": 62650 }, { "epoch": 0.37246405240413477, "grad_norm": 1.8227533102035522, "learning_rate": 0.00019968036602356068, "loss": 0.6436280727386474, "step": 62660 }, { "epoch": 0.3725234944808032, "grad_norm": 1.5854412317276, "learning_rate": 0.00019967984165671668, "loss": 0.6721142292022705, "step": 62670 }, { "epoch": 0.37258293655747154, "grad_norm": 1.5651737451553345, "learning_rate": 0.00019967931686087358, "loss": 0.6349685668945313, "step": 62680 }, { "epoch": 0.37264237863413996, "grad_norm": 1.6303547620773315, "learning_rate": 0.00019967879163603394, "loss": 0.6831293106079102, "step": 62690 }, { "epoch": 0.3727018207108084, "grad_norm": 1.3903088569641113, "learning_rate": 0.0001996782659822003, "loss": 0.6721620559692383, "step": 62700 }, { "epoch": 0.37276126278747673, "grad_norm": 1.6725835800170898, "learning_rate": 0.00019967773989937513, "loss": 0.7244921207427979, "step": 62710 }, { "epoch": 0.37282070486414515, "grad_norm": 1.673779010772705, "learning_rate": 0.00019967721338756095, "loss": 0.7048465728759765, "step": 62720 }, { "epoch": 0.3728801469408135, "grad_norm": 2.137049436569214, "learning_rate": 0.00019967668644676028, "loss": 0.6855072498321533, "step": 62730 }, { "epoch": 0.3729395890174819, "grad_norm": 1.9209710359573364, "learning_rate": 0.0001996761590769757, "loss": 0.7093610763549805, "step": 62740 }, { "epoch": 0.3729990310941503, "grad_norm": 1.6124387979507446, "learning_rate": 0.00019967563127820963, "loss": 0.6958943367004394, "step": 62750 }, { "epoch": 0.3730584731708187, "grad_norm": 2.006619691848755, "learning_rate": 0.00019967510305046463, "loss": 0.7114603996276856, "step": 62760 }, { "epoch": 0.3731179152474871, "grad_norm": 1.7893660068511963, "learning_rate": 0.0001996745743937433, "loss": 0.6369516372680664, "step": 62770 }, { "epoch": 0.37317735732415547, "grad_norm": 1.684007167816162, "learning_rate": 0.00019967404530804808, "loss": 0.735510778427124, "step": 62780 }, { "epoch": 0.3732367994008239, "grad_norm": 1.3646610975265503, "learning_rate": 0.00019967351579338154, "loss": 0.6785409927368165, "step": 62790 }, { "epoch": 0.37329624147749224, "grad_norm": 2.3391215801239014, "learning_rate": 0.00019967298584974618, "loss": 0.7336398124694824, "step": 62800 }, { "epoch": 0.37335568355416066, "grad_norm": 1.2721779346466064, "learning_rate": 0.0001996724554771446, "loss": 0.6897687435150146, "step": 62810 }, { "epoch": 0.373415125630829, "grad_norm": 1.6232526302337646, "learning_rate": 0.00019967192467557928, "loss": 0.7036816120147705, "step": 62820 }, { "epoch": 0.37347456770749743, "grad_norm": 2.1014978885650635, "learning_rate": 0.0001996713934450528, "loss": 0.6686837196350097, "step": 62830 }, { "epoch": 0.37353400978416584, "grad_norm": 1.7844136953353882, "learning_rate": 0.00019967086178556765, "loss": 0.6706341743469239, "step": 62840 }, { "epoch": 0.3735934518608342, "grad_norm": 1.409380316734314, "learning_rate": 0.0001996703296971264, "loss": 0.6668420791625976, "step": 62850 }, { "epoch": 0.3736528939375026, "grad_norm": 1.742460012435913, "learning_rate": 0.0001996697971797316, "loss": 0.7526705741882325, "step": 62860 }, { "epoch": 0.373712336014171, "grad_norm": 1.7473101615905762, "learning_rate": 0.0001996692642333858, "loss": 0.7372249603271485, "step": 62870 }, { "epoch": 0.3737717780908394, "grad_norm": 1.9476107358932495, "learning_rate": 0.00019966873085809156, "loss": 0.6751850605010986, "step": 62880 }, { "epoch": 0.37383122016750775, "grad_norm": 1.6552512645721436, "learning_rate": 0.00019966819705385139, "loss": 0.6628406524658204, "step": 62890 }, { "epoch": 0.37389066224417616, "grad_norm": 2.1582624912261963, "learning_rate": 0.0001996676628206679, "loss": 0.6930146217346191, "step": 62900 }, { "epoch": 0.3739501043208446, "grad_norm": 1.41120183467865, "learning_rate": 0.00019966712815854362, "loss": 0.6405929565429688, "step": 62910 }, { "epoch": 0.37400954639751294, "grad_norm": 1.7374598979949951, "learning_rate": 0.00019966659306748107, "loss": 0.762264347076416, "step": 62920 }, { "epoch": 0.37406898847418135, "grad_norm": 2.1226189136505127, "learning_rate": 0.00019966605754748285, "loss": 0.724344539642334, "step": 62930 }, { "epoch": 0.3741284305508497, "grad_norm": 2.293146848678589, "learning_rate": 0.00019966552159855148, "loss": 0.7389481544494629, "step": 62940 }, { "epoch": 0.3741878726275181, "grad_norm": 1.7145178318023682, "learning_rate": 0.0001996649852206896, "loss": 0.6641220092773438, "step": 62950 }, { "epoch": 0.3742473147041865, "grad_norm": 1.7455780506134033, "learning_rate": 0.00019966444841389974, "loss": 0.671107292175293, "step": 62960 }, { "epoch": 0.3743067567808549, "grad_norm": 1.933675765991211, "learning_rate": 0.00019966391117818443, "loss": 0.6896013736724853, "step": 62970 }, { "epoch": 0.3743661988575233, "grad_norm": 1.8249114751815796, "learning_rate": 0.00019966337351354628, "loss": 0.6571364402770996, "step": 62980 }, { "epoch": 0.3744256409341917, "grad_norm": 1.5362598896026611, "learning_rate": 0.00019966283541998788, "loss": 0.7179609298706054, "step": 62990 }, { "epoch": 0.3744850830108601, "grad_norm": 1.528950810432434, "learning_rate": 0.00019966229689751176, "loss": 0.6958662033081054, "step": 63000 }, { "epoch": 0.37454452508752845, "grad_norm": 1.999681830406189, "learning_rate": 0.00019966175794612054, "loss": 0.7120011329650879, "step": 63010 }, { "epoch": 0.37460396716419686, "grad_norm": 1.7410625219345093, "learning_rate": 0.00019966121856581672, "loss": 0.7206039428710938, "step": 63020 }, { "epoch": 0.3746634092408652, "grad_norm": 1.759198546409607, "learning_rate": 0.00019966067875660298, "loss": 0.714201831817627, "step": 63030 }, { "epoch": 0.37472285131753363, "grad_norm": 2.0611937046051025, "learning_rate": 0.0001996601385184818, "loss": 0.6413047790527344, "step": 63040 }, { "epoch": 0.374782293394202, "grad_norm": 1.68044912815094, "learning_rate": 0.00019965959785145588, "loss": 0.67794189453125, "step": 63050 }, { "epoch": 0.3748417354708704, "grad_norm": 1.8003098964691162, "learning_rate": 0.0001996590567555277, "loss": 0.7007124900817872, "step": 63060 }, { "epoch": 0.3749011775475388, "grad_norm": 1.83678138256073, "learning_rate": 0.00019965851523069992, "loss": 0.738320779800415, "step": 63070 }, { "epoch": 0.3749606196242072, "grad_norm": 2.060873031616211, "learning_rate": 0.00019965797327697508, "loss": 0.6491576194763183, "step": 63080 }, { "epoch": 0.3750200617008756, "grad_norm": 1.4743069410324097, "learning_rate": 0.00019965743089435582, "loss": 0.7000597953796387, "step": 63090 }, { "epoch": 0.37507950377754395, "grad_norm": 1.138588547706604, "learning_rate": 0.00019965688808284472, "loss": 0.6699186801910401, "step": 63100 }, { "epoch": 0.37513894585421237, "grad_norm": 1.3480772972106934, "learning_rate": 0.0001996563448424443, "loss": 0.6984694004058838, "step": 63110 }, { "epoch": 0.37519838793088073, "grad_norm": 1.755760908126831, "learning_rate": 0.00019965580117315727, "loss": 0.6477713584899902, "step": 63120 }, { "epoch": 0.37525783000754914, "grad_norm": 1.4536066055297852, "learning_rate": 0.0001996552570749862, "loss": 0.6615150451660157, "step": 63130 }, { "epoch": 0.37531727208421756, "grad_norm": 1.6614353656768799, "learning_rate": 0.0001996547125479337, "loss": 0.7107233047485352, "step": 63140 }, { "epoch": 0.3753767141608859, "grad_norm": 1.7666747570037842, "learning_rate": 0.0001996541675920023, "loss": 0.6501254081726074, "step": 63150 }, { "epoch": 0.37543615623755433, "grad_norm": 1.5137768983840942, "learning_rate": 0.0001996536222071947, "loss": 0.7856486320495606, "step": 63160 }, { "epoch": 0.3754955983142227, "grad_norm": 1.190868854522705, "learning_rate": 0.00019965307639351344, "loss": 0.7153406143188477, "step": 63170 }, { "epoch": 0.3755550403908911, "grad_norm": 1.6562654972076416, "learning_rate": 0.0001996525301509612, "loss": 0.7443497180938721, "step": 63180 }, { "epoch": 0.37561448246755946, "grad_norm": 1.8408077955245972, "learning_rate": 0.00019965198347954053, "loss": 0.7140614986419678, "step": 63190 }, { "epoch": 0.3756739245442279, "grad_norm": 1.6575969457626343, "learning_rate": 0.00019965143637925406, "loss": 0.6662539482116699, "step": 63200 }, { "epoch": 0.3757333666208963, "grad_norm": 1.019063949584961, "learning_rate": 0.00019965088885010444, "loss": 0.6169176578521729, "step": 63210 }, { "epoch": 0.37579280869756465, "grad_norm": 1.7119386196136475, "learning_rate": 0.00019965034089209426, "loss": 0.6475695610046387, "step": 63220 }, { "epoch": 0.37585225077423307, "grad_norm": 2.1251332759857178, "learning_rate": 0.00019964979250522614, "loss": 0.7306755065917969, "step": 63230 }, { "epoch": 0.3759116928509014, "grad_norm": 1.6038621664047241, "learning_rate": 0.00019964924368950273, "loss": 0.7046903610229492, "step": 63240 }, { "epoch": 0.37597113492756984, "grad_norm": 2.085998773574829, "learning_rate": 0.0001996486944449266, "loss": 0.7233211040496826, "step": 63250 }, { "epoch": 0.3760305770042382, "grad_norm": 1.363129734992981, "learning_rate": 0.00019964814477150045, "loss": 0.6258139610290527, "step": 63260 }, { "epoch": 0.3760900190809066, "grad_norm": 1.2956984043121338, "learning_rate": 0.00019964759466922685, "loss": 0.7294986724853516, "step": 63270 }, { "epoch": 0.376149461157575, "grad_norm": 1.6795531511306763, "learning_rate": 0.00019964704413810846, "loss": 0.6704278945922851, "step": 63280 }, { "epoch": 0.3762089032342434, "grad_norm": 1.9091562032699585, "learning_rate": 0.0001996464931781479, "loss": 0.7073932647705078, "step": 63290 }, { "epoch": 0.3762683453109118, "grad_norm": 1.6484763622283936, "learning_rate": 0.00019964594178934785, "loss": 0.6576850414276123, "step": 63300 }, { "epoch": 0.37632778738758016, "grad_norm": 1.795901894569397, "learning_rate": 0.00019964538997171085, "loss": 0.7402537345886231, "step": 63310 }, { "epoch": 0.3763872294642486, "grad_norm": 1.6765668392181396, "learning_rate": 0.00019964483772523964, "loss": 0.6978165626525878, "step": 63320 }, { "epoch": 0.37644667154091693, "grad_norm": 1.6214845180511475, "learning_rate": 0.00019964428504993682, "loss": 0.6970805644989013, "step": 63330 }, { "epoch": 0.37650611361758535, "grad_norm": 1.9335888624191284, "learning_rate": 0.00019964373194580504, "loss": 0.7108963966369629, "step": 63340 }, { "epoch": 0.37656555569425376, "grad_norm": 1.7246589660644531, "learning_rate": 0.00019964317841284691, "loss": 0.6967610359191895, "step": 63350 }, { "epoch": 0.3766249977709221, "grad_norm": 1.4622187614440918, "learning_rate": 0.00019964262445106517, "loss": 0.741835641860962, "step": 63360 }, { "epoch": 0.37668443984759054, "grad_norm": 1.3906880617141724, "learning_rate": 0.00019964207006046235, "loss": 0.6672450542449951, "step": 63370 }, { "epoch": 0.3767438819242589, "grad_norm": 2.2850279808044434, "learning_rate": 0.00019964151524104118, "loss": 0.7137210845947266, "step": 63380 }, { "epoch": 0.3768033240009273, "grad_norm": 1.4388831853866577, "learning_rate": 0.0001996409599928043, "loss": 0.7206804275512695, "step": 63390 }, { "epoch": 0.37686276607759567, "grad_norm": 1.6969940662384033, "learning_rate": 0.00019964040431575436, "loss": 0.7134987831115722, "step": 63400 }, { "epoch": 0.3769222081542641, "grad_norm": 1.828587293624878, "learning_rate": 0.00019963984820989405, "loss": 0.7002185821533203, "step": 63410 }, { "epoch": 0.37698165023093244, "grad_norm": 2.0124895572662354, "learning_rate": 0.00019963929167522598, "loss": 0.7091124534606934, "step": 63420 }, { "epoch": 0.37704109230760086, "grad_norm": 1.7584656476974487, "learning_rate": 0.00019963873471175284, "loss": 0.7285623550415039, "step": 63430 }, { "epoch": 0.37710053438426927, "grad_norm": 1.958340048789978, "learning_rate": 0.00019963817731947725, "loss": 0.7041932106018066, "step": 63440 }, { "epoch": 0.37715997646093763, "grad_norm": 1.482928991317749, "learning_rate": 0.00019963761949840194, "loss": 0.6587844371795655, "step": 63450 }, { "epoch": 0.37721941853760604, "grad_norm": 1.5649662017822266, "learning_rate": 0.00019963706124852956, "loss": 0.6744482040405273, "step": 63460 }, { "epoch": 0.3772788606142744, "grad_norm": 1.8301146030426025, "learning_rate": 0.00019963650256986276, "loss": 0.7422657966613769, "step": 63470 }, { "epoch": 0.3773383026909428, "grad_norm": 1.3860853910446167, "learning_rate": 0.00019963594346240424, "loss": 0.6834152698516845, "step": 63480 }, { "epoch": 0.3773977447676112, "grad_norm": 1.591214895248413, "learning_rate": 0.00019963538392615664, "loss": 0.7477717876434327, "step": 63490 }, { "epoch": 0.3774571868442796, "grad_norm": 1.7081373929977417, "learning_rate": 0.00019963482396112266, "loss": 0.6991302490234375, "step": 63500 }, { "epoch": 0.377516628920948, "grad_norm": 1.5681040287017822, "learning_rate": 0.000199634263567305, "loss": 0.646595573425293, "step": 63510 }, { "epoch": 0.37757607099761636, "grad_norm": 1.8180352449417114, "learning_rate": 0.00019963370274470632, "loss": 0.6587484359741211, "step": 63520 }, { "epoch": 0.3776355130742848, "grad_norm": 1.4984996318817139, "learning_rate": 0.00019963314149332926, "loss": 0.7087770462036133, "step": 63530 }, { "epoch": 0.37769495515095314, "grad_norm": 1.6730875968933105, "learning_rate": 0.00019963257981317655, "loss": 0.684565544128418, "step": 63540 }, { "epoch": 0.37775439722762155, "grad_norm": 1.6576690673828125, "learning_rate": 0.0001996320177042509, "loss": 0.6962155342102051, "step": 63550 }, { "epoch": 0.3778138393042899, "grad_norm": 1.6538114547729492, "learning_rate": 0.00019963145516655492, "loss": 0.699155044555664, "step": 63560 }, { "epoch": 0.3778732813809583, "grad_norm": 1.6798112392425537, "learning_rate": 0.00019963089220009138, "loss": 0.676198673248291, "step": 63570 }, { "epoch": 0.37793272345762674, "grad_norm": 2.092305898666382, "learning_rate": 0.00019963032880486296, "loss": 0.6466767311096191, "step": 63580 }, { "epoch": 0.3779921655342951, "grad_norm": 1.8119279146194458, "learning_rate": 0.00019962976498087232, "loss": 0.7047818183898926, "step": 63590 }, { "epoch": 0.3780516076109635, "grad_norm": 1.9021408557891846, "learning_rate": 0.0001996292007281222, "loss": 0.6868955612182617, "step": 63600 }, { "epoch": 0.3781110496876319, "grad_norm": 1.9028878211975098, "learning_rate": 0.00019962863604661523, "loss": 0.7021621704101563, "step": 63610 }, { "epoch": 0.3781704917643003, "grad_norm": 2.0523645877838135, "learning_rate": 0.0001996280709363542, "loss": 0.6974411010742188, "step": 63620 }, { "epoch": 0.37822993384096865, "grad_norm": 1.8060286045074463, "learning_rate": 0.00019962750539734175, "loss": 0.7203017234802246, "step": 63630 }, { "epoch": 0.37828937591763706, "grad_norm": 1.4617600440979004, "learning_rate": 0.0001996269394295806, "loss": 0.6601973533630371, "step": 63640 }, { "epoch": 0.3783488179943055, "grad_norm": 1.5196653604507446, "learning_rate": 0.00019962637303307348, "loss": 0.6531493663787842, "step": 63650 }, { "epoch": 0.37840826007097383, "grad_norm": 1.8485525846481323, "learning_rate": 0.00019962580620782306, "loss": 0.6735730648040772, "step": 63660 }, { "epoch": 0.37846770214764225, "grad_norm": 1.4422110319137573, "learning_rate": 0.00019962523895383208, "loss": 0.6887744903564453, "step": 63670 }, { "epoch": 0.3785271442243106, "grad_norm": 1.8243870735168457, "learning_rate": 0.00019962467127110324, "loss": 0.6530919075012207, "step": 63680 }, { "epoch": 0.378586586300979, "grad_norm": 1.6326371431350708, "learning_rate": 0.00019962410315963928, "loss": 0.7487557411193848, "step": 63690 }, { "epoch": 0.3786460283776474, "grad_norm": 2.2010300159454346, "learning_rate": 0.00019962353461944288, "loss": 0.6776656150817871, "step": 63700 }, { "epoch": 0.3787054704543158, "grad_norm": 1.545501470565796, "learning_rate": 0.00019962296565051676, "loss": 0.7144620895385743, "step": 63710 }, { "epoch": 0.3787649125309842, "grad_norm": 2.0432417392730713, "learning_rate": 0.0001996223962528637, "loss": 0.6888699531555176, "step": 63720 }, { "epoch": 0.37882435460765257, "grad_norm": 1.7169238328933716, "learning_rate": 0.00019962182642648639, "loss": 0.6915305614471435, "step": 63730 }, { "epoch": 0.378883796684321, "grad_norm": 1.4224618673324585, "learning_rate": 0.00019962125617138755, "loss": 0.6863215446472168, "step": 63740 }, { "epoch": 0.37894323876098934, "grad_norm": 2.1955389976501465, "learning_rate": 0.00019962068548756988, "loss": 0.6744222164154052, "step": 63750 }, { "epoch": 0.37900268083765776, "grad_norm": 1.5073561668395996, "learning_rate": 0.00019962011437503615, "loss": 0.737548828125, "step": 63760 }, { "epoch": 0.3790621229143261, "grad_norm": 1.6352322101593018, "learning_rate": 0.0001996195428337891, "loss": 0.7311126232147217, "step": 63770 }, { "epoch": 0.37912156499099453, "grad_norm": 1.1566002368927002, "learning_rate": 0.00019961897086383143, "loss": 0.690406608581543, "step": 63780 }, { "epoch": 0.3791810070676629, "grad_norm": 1.5961098670959473, "learning_rate": 0.00019961839846516588, "loss": 0.7182193756103515, "step": 63790 }, { "epoch": 0.3792404491443313, "grad_norm": 1.9550492763519287, "learning_rate": 0.00019961782563779524, "loss": 0.6786387443542481, "step": 63800 }, { "epoch": 0.3792998912209997, "grad_norm": 1.7080156803131104, "learning_rate": 0.00019961725238172215, "loss": 0.6437296867370605, "step": 63810 }, { "epoch": 0.3793593332976681, "grad_norm": 1.6767582893371582, "learning_rate": 0.00019961667869694945, "loss": 0.7105939865112305, "step": 63820 }, { "epoch": 0.3794187753743365, "grad_norm": 1.7751786708831787, "learning_rate": 0.00019961610458347985, "loss": 0.7116581916809082, "step": 63830 }, { "epoch": 0.37947821745100485, "grad_norm": 1.5481858253479004, "learning_rate": 0.0001996155300413161, "loss": 0.7387776374816895, "step": 63840 }, { "epoch": 0.37953765952767327, "grad_norm": 1.7654142379760742, "learning_rate": 0.00019961495507046087, "loss": 0.7820283889770507, "step": 63850 }, { "epoch": 0.3795971016043416, "grad_norm": 1.934622883796692, "learning_rate": 0.00019961437967091708, "loss": 0.7160032749176025, "step": 63860 }, { "epoch": 0.37965654368101004, "grad_norm": 1.6821473836898804, "learning_rate": 0.00019961380384268733, "loss": 0.7419964790344238, "step": 63870 }, { "epoch": 0.37971598575767845, "grad_norm": 1.8962444067001343, "learning_rate": 0.0001996132275857744, "loss": 0.7420340061187745, "step": 63880 }, { "epoch": 0.3797754278343468, "grad_norm": 1.664497971534729, "learning_rate": 0.00019961265090018114, "loss": 0.7156275749206543, "step": 63890 }, { "epoch": 0.3798348699110152, "grad_norm": 1.5882774591445923, "learning_rate": 0.00019961207378591022, "loss": 0.7133403778076172, "step": 63900 }, { "epoch": 0.3798943119876836, "grad_norm": 1.6789528131484985, "learning_rate": 0.00019961149624296443, "loss": 0.6886167526245117, "step": 63910 }, { "epoch": 0.379953754064352, "grad_norm": 1.8847990036010742, "learning_rate": 0.00019961091827134652, "loss": 0.7286252021789551, "step": 63920 }, { "epoch": 0.38001319614102036, "grad_norm": 1.5309860706329346, "learning_rate": 0.00019961033987105924, "loss": 0.7436599731445312, "step": 63930 }, { "epoch": 0.3800726382176888, "grad_norm": 1.7780206203460693, "learning_rate": 0.0001996097610421054, "loss": 0.6455436706542969, "step": 63940 }, { "epoch": 0.3801320802943572, "grad_norm": 1.516395092010498, "learning_rate": 0.00019960918178448775, "loss": 0.6741610527038574, "step": 63950 }, { "epoch": 0.38019152237102555, "grad_norm": 1.6639127731323242, "learning_rate": 0.00019960860209820904, "loss": 0.6534235000610351, "step": 63960 }, { "epoch": 0.38025096444769396, "grad_norm": 1.506899356842041, "learning_rate": 0.0001996080219832721, "loss": 0.724740743637085, "step": 63970 }, { "epoch": 0.3803104065243623, "grad_norm": 1.6446967124938965, "learning_rate": 0.00019960744143967965, "loss": 0.6521121978759765, "step": 63980 }, { "epoch": 0.38036984860103074, "grad_norm": 1.493262767791748, "learning_rate": 0.00019960686046743443, "loss": 0.7465306282043457, "step": 63990 }, { "epoch": 0.3804292906776991, "grad_norm": 1.8465098142623901, "learning_rate": 0.00019960627906653934, "loss": 0.6774495601654053, "step": 64000 }, { "epoch": 0.3804887327543675, "grad_norm": 1.335325837135315, "learning_rate": 0.00019960569723699709, "loss": 0.6644105911254883, "step": 64010 }, { "epoch": 0.3805481748310359, "grad_norm": 1.5516093969345093, "learning_rate": 0.00019960511497881046, "loss": 0.6536425113677978, "step": 64020 }, { "epoch": 0.3806076169077043, "grad_norm": 1.6881484985351562, "learning_rate": 0.00019960453229198223, "loss": 0.6882211685180664, "step": 64030 }, { "epoch": 0.3806670589843727, "grad_norm": 1.6028465032577515, "learning_rate": 0.0001996039491765152, "loss": 0.6583712100982666, "step": 64040 }, { "epoch": 0.38072650106104106, "grad_norm": 1.8053942918777466, "learning_rate": 0.0001996033656324122, "loss": 0.6567865371704101, "step": 64050 }, { "epoch": 0.38078594313770947, "grad_norm": 1.6447639465332031, "learning_rate": 0.00019960278165967595, "loss": 0.6970550537109375, "step": 64060 }, { "epoch": 0.38084538521437783, "grad_norm": 1.6625322103500366, "learning_rate": 0.00019960219725830925, "loss": 0.6730254173278809, "step": 64070 }, { "epoch": 0.38090482729104624, "grad_norm": 1.7808096408843994, "learning_rate": 0.00019960161242831495, "loss": 0.6778135299682617, "step": 64080 }, { "epoch": 0.3809642693677146, "grad_norm": 1.4686503410339355, "learning_rate": 0.0001996010271696958, "loss": 0.6477823257446289, "step": 64090 }, { "epoch": 0.381023711444383, "grad_norm": 1.5092135667800903, "learning_rate": 0.00019960044148245468, "loss": 0.7286459922790527, "step": 64100 }, { "epoch": 0.38108315352105143, "grad_norm": 1.6294515132904053, "learning_rate": 0.00019959985536659424, "loss": 0.6853439331054687, "step": 64110 }, { "epoch": 0.3811425955977198, "grad_norm": 1.9267075061798096, "learning_rate": 0.00019959926882211744, "loss": 0.7152525901794433, "step": 64120 }, { "epoch": 0.3812020376743882, "grad_norm": 1.8805383443832397, "learning_rate": 0.00019959868184902697, "loss": 0.7321965217590332, "step": 64130 }, { "epoch": 0.38126147975105656, "grad_norm": 1.554753303527832, "learning_rate": 0.00019959809444732574, "loss": 0.7165816307067872, "step": 64140 }, { "epoch": 0.381320921827725, "grad_norm": 1.822816252708435, "learning_rate": 0.00019959750661701647, "loss": 0.7066990852355957, "step": 64150 }, { "epoch": 0.38138036390439334, "grad_norm": 2.4637129306793213, "learning_rate": 0.000199596918358102, "loss": 0.6703338623046875, "step": 64160 }, { "epoch": 0.38143980598106175, "grad_norm": 1.6539167165756226, "learning_rate": 0.0001995963296705852, "loss": 0.7122076034545899, "step": 64170 }, { "epoch": 0.38149924805773017, "grad_norm": 3.12884259223938, "learning_rate": 0.0001995957405544688, "loss": 0.708721399307251, "step": 64180 }, { "epoch": 0.3815586901343985, "grad_norm": 1.492138147354126, "learning_rate": 0.00019959515100975565, "loss": 0.6745333671569824, "step": 64190 }, { "epoch": 0.38161813221106694, "grad_norm": 1.7436572313308716, "learning_rate": 0.0001995945610364486, "loss": 0.728178882598877, "step": 64200 }, { "epoch": 0.3816775742877353, "grad_norm": 1.5311241149902344, "learning_rate": 0.00019959397063455046, "loss": 0.6970208168029786, "step": 64210 }, { "epoch": 0.3817370163644037, "grad_norm": 1.8479869365692139, "learning_rate": 0.00019959337980406404, "loss": 0.7403038024902344, "step": 64220 }, { "epoch": 0.3817964584410721, "grad_norm": 1.7281405925750732, "learning_rate": 0.00019959278854499214, "loss": 0.7189093589782715, "step": 64230 }, { "epoch": 0.3818559005177405, "grad_norm": 1.3484007120132446, "learning_rate": 0.00019959219685733765, "loss": 0.7482848644256592, "step": 64240 }, { "epoch": 0.3819153425944089, "grad_norm": 2.137819528579712, "learning_rate": 0.00019959160474110338, "loss": 0.6695063591003418, "step": 64250 }, { "epoch": 0.38197478467107726, "grad_norm": 1.4529869556427002, "learning_rate": 0.0001995910121962921, "loss": 0.6904003620147705, "step": 64260 }, { "epoch": 0.3820342267477457, "grad_norm": 1.9837616682052612, "learning_rate": 0.00019959041922290672, "loss": 0.6487000465393067, "step": 64270 }, { "epoch": 0.38209366882441403, "grad_norm": 1.8377903699874878, "learning_rate": 0.00019958982582095005, "loss": 0.7319953918457032, "step": 64280 }, { "epoch": 0.38215311090108245, "grad_norm": 1.64003324508667, "learning_rate": 0.00019958923199042493, "loss": 0.6813891410827637, "step": 64290 }, { "epoch": 0.3822125529777508, "grad_norm": 1.6963940858840942, "learning_rate": 0.00019958863773133424, "loss": 0.6734375953674316, "step": 64300 }, { "epoch": 0.3822719950544192, "grad_norm": 1.712999939918518, "learning_rate": 0.00019958804304368076, "loss": 0.6777482032775879, "step": 64310 }, { "epoch": 0.38233143713108764, "grad_norm": 1.9828640222549438, "learning_rate": 0.00019958744792746735, "loss": 0.6522984981536866, "step": 64320 }, { "epoch": 0.382390879207756, "grad_norm": 1.6927136182785034, "learning_rate": 0.00019958685238269687, "loss": 0.7667430877685547, "step": 64330 }, { "epoch": 0.3824503212844244, "grad_norm": 1.4839645624160767, "learning_rate": 0.0001995862564093722, "loss": 0.7663281440734864, "step": 64340 }, { "epoch": 0.38250976336109277, "grad_norm": 1.6156569719314575, "learning_rate": 0.0001995856600074961, "loss": 0.7319656372070312, "step": 64350 }, { "epoch": 0.3825692054377612, "grad_norm": 1.4281212091445923, "learning_rate": 0.00019958506317707152, "loss": 0.6702351093292236, "step": 64360 }, { "epoch": 0.38262864751442954, "grad_norm": 1.9096183776855469, "learning_rate": 0.00019958446591810127, "loss": 0.6612543106079102, "step": 64370 }, { "epoch": 0.38268808959109796, "grad_norm": 2.5721750259399414, "learning_rate": 0.00019958386823058818, "loss": 0.7272845268249511, "step": 64380 }, { "epoch": 0.38274753166776637, "grad_norm": 1.7396336793899536, "learning_rate": 0.00019958327011453518, "loss": 0.70191650390625, "step": 64390 }, { "epoch": 0.38280697374443473, "grad_norm": 1.6440109014511108, "learning_rate": 0.00019958267156994507, "loss": 0.690235948562622, "step": 64400 }, { "epoch": 0.38286641582110315, "grad_norm": 2.2176778316497803, "learning_rate": 0.00019958207259682074, "loss": 0.6965858936309814, "step": 64410 }, { "epoch": 0.3829258578977715, "grad_norm": 2.0741384029388428, "learning_rate": 0.00019958147319516502, "loss": 0.6763149261474609, "step": 64420 }, { "epoch": 0.3829852999744399, "grad_norm": 1.8531078100204468, "learning_rate": 0.00019958087336498088, "loss": 0.6413147449493408, "step": 64430 }, { "epoch": 0.3830447420511083, "grad_norm": 1.6982612609863281, "learning_rate": 0.00019958027310627106, "loss": 0.716768455505371, "step": 64440 }, { "epoch": 0.3831041841277767, "grad_norm": 1.3324942588806152, "learning_rate": 0.0001995796724190385, "loss": 0.6762720108032226, "step": 64450 }, { "epoch": 0.38316362620444505, "grad_norm": 1.7761675119400024, "learning_rate": 0.00019957907130328605, "loss": 0.6984084129333497, "step": 64460 }, { "epoch": 0.38322306828111347, "grad_norm": 2.340592384338379, "learning_rate": 0.00019957846975901663, "loss": 0.7059703350067139, "step": 64470 }, { "epoch": 0.3832825103577819, "grad_norm": 1.747917652130127, "learning_rate": 0.00019957786778623305, "loss": 0.5976469039916992, "step": 64480 }, { "epoch": 0.38334195243445024, "grad_norm": 1.741171956062317, "learning_rate": 0.00019957726538493827, "loss": 0.6734438896179199, "step": 64490 }, { "epoch": 0.38340139451111865, "grad_norm": 1.4882932901382446, "learning_rate": 0.00019957666255513508, "loss": 0.6760475158691406, "step": 64500 }, { "epoch": 0.383460836587787, "grad_norm": 1.8657374382019043, "learning_rate": 0.00019957605929682643, "loss": 0.6990170001983642, "step": 64510 }, { "epoch": 0.3835202786644554, "grad_norm": 1.9865484237670898, "learning_rate": 0.0001995754556100152, "loss": 0.7264721870422364, "step": 64520 }, { "epoch": 0.3835797207411238, "grad_norm": 1.3729240894317627, "learning_rate": 0.00019957485149470425, "loss": 0.6444864273071289, "step": 64530 }, { "epoch": 0.3836391628177922, "grad_norm": 2.0134503841400146, "learning_rate": 0.00019957424695089647, "loss": 0.7117913246154786, "step": 64540 }, { "epoch": 0.3836986048944606, "grad_norm": 1.6028029918670654, "learning_rate": 0.00019957364197859478, "loss": 0.687550687789917, "step": 64550 }, { "epoch": 0.383758046971129, "grad_norm": 2.0326550006866455, "learning_rate": 0.00019957303657780207, "loss": 0.7194499015808106, "step": 64560 }, { "epoch": 0.3838174890477974, "grad_norm": 1.759832501411438, "learning_rate": 0.0001995724307485212, "loss": 0.71864333152771, "step": 64570 }, { "epoch": 0.38387693112446575, "grad_norm": 1.8052583932876587, "learning_rate": 0.00019957182449075513, "loss": 0.6995900630950928, "step": 64580 }, { "epoch": 0.38393637320113416, "grad_norm": 1.909293532371521, "learning_rate": 0.00019957121780450672, "loss": 0.7186933517456054, "step": 64590 }, { "epoch": 0.3839958152778025, "grad_norm": 1.873377799987793, "learning_rate": 0.00019957061068977882, "loss": 0.6921292304992676, "step": 64600 }, { "epoch": 0.38405525735447094, "grad_norm": 1.8697497844696045, "learning_rate": 0.00019957000314657446, "loss": 0.6579504013061523, "step": 64610 }, { "epoch": 0.38411469943113935, "grad_norm": 1.6784251928329468, "learning_rate": 0.00019956939517489644, "loss": 0.7379002571105957, "step": 64620 }, { "epoch": 0.3841741415078077, "grad_norm": 1.732728362083435, "learning_rate": 0.0001995687867747477, "loss": 0.7059825897216797, "step": 64630 }, { "epoch": 0.3842335835844761, "grad_norm": 1.6015177965164185, "learning_rate": 0.00019956817794613118, "loss": 0.686442756652832, "step": 64640 }, { "epoch": 0.3842930256611445, "grad_norm": 1.5533701181411743, "learning_rate": 0.00019956756868904973, "loss": 0.7218070983886719, "step": 64650 }, { "epoch": 0.3843524677378129, "grad_norm": 2.1825363636016846, "learning_rate": 0.00019956695900350636, "loss": 0.6295477867126464, "step": 64660 }, { "epoch": 0.38441190981448126, "grad_norm": 1.5147665739059448, "learning_rate": 0.00019956634888950388, "loss": 0.6445881843566894, "step": 64670 }, { "epoch": 0.38447135189114967, "grad_norm": 1.8077577352523804, "learning_rate": 0.00019956573834704528, "loss": 0.7407486915588379, "step": 64680 }, { "epoch": 0.3845307939678181, "grad_norm": 1.8572635650634766, "learning_rate": 0.00019956512737613345, "loss": 0.7267580986022949, "step": 64690 }, { "epoch": 0.38459023604448644, "grad_norm": 2.096848726272583, "learning_rate": 0.00019956451597677135, "loss": 0.6808936119079589, "step": 64700 }, { "epoch": 0.38464967812115486, "grad_norm": 2.208266258239746, "learning_rate": 0.00019956390414896182, "loss": 0.7350209712982178, "step": 64710 }, { "epoch": 0.3847091201978232, "grad_norm": 1.332452654838562, "learning_rate": 0.00019956329189270785, "loss": 0.6939471244812012, "step": 64720 }, { "epoch": 0.38476856227449163, "grad_norm": 1.8106170892715454, "learning_rate": 0.00019956267920801242, "loss": 0.6822765827178955, "step": 64730 }, { "epoch": 0.38482800435116, "grad_norm": 2.0957212448120117, "learning_rate": 0.00019956206609487835, "loss": 0.6741630554199218, "step": 64740 }, { "epoch": 0.3848874464278284, "grad_norm": 1.763401985168457, "learning_rate": 0.00019956145255330864, "loss": 0.750058364868164, "step": 64750 }, { "epoch": 0.3849468885044968, "grad_norm": 2.073139190673828, "learning_rate": 0.0001995608385833062, "loss": 0.7544548988342286, "step": 64760 }, { "epoch": 0.3850063305811652, "grad_norm": 1.560675024986267, "learning_rate": 0.000199560224184874, "loss": 0.707139253616333, "step": 64770 }, { "epoch": 0.3850657726578336, "grad_norm": 1.7355111837387085, "learning_rate": 0.00019955960935801495, "loss": 0.6753432750701904, "step": 64780 }, { "epoch": 0.38512521473450195, "grad_norm": 1.640620231628418, "learning_rate": 0.00019955899410273198, "loss": 0.7451277732849121, "step": 64790 }, { "epoch": 0.38518465681117037, "grad_norm": 2.9105658531188965, "learning_rate": 0.00019955837841902806, "loss": 0.7054261207580567, "step": 64800 }, { "epoch": 0.3852440988878387, "grad_norm": 2.0217771530151367, "learning_rate": 0.00019955776230690613, "loss": 0.6858798027038574, "step": 64810 }, { "epoch": 0.38530354096450714, "grad_norm": 1.4221124649047852, "learning_rate": 0.00019955714576636914, "loss": 0.602104902267456, "step": 64820 }, { "epoch": 0.3853629830411755, "grad_norm": 1.6954959630966187, "learning_rate": 0.00019955652879742, "loss": 0.729481315612793, "step": 64830 }, { "epoch": 0.3854224251178439, "grad_norm": 2.0906169414520264, "learning_rate": 0.0001995559114000617, "loss": 0.7023733139038086, "step": 64840 }, { "epoch": 0.38548186719451233, "grad_norm": 1.524245023727417, "learning_rate": 0.00019955529357429722, "loss": 0.7624634742736817, "step": 64850 }, { "epoch": 0.3855413092711807, "grad_norm": 1.953032374382019, "learning_rate": 0.00019955467532012947, "loss": 0.6716491222381592, "step": 64860 }, { "epoch": 0.3856007513478491, "grad_norm": 1.9344913959503174, "learning_rate": 0.0001995540566375614, "loss": 0.7482355117797852, "step": 64870 }, { "epoch": 0.38566019342451746, "grad_norm": 1.660943865776062, "learning_rate": 0.000199553437526596, "loss": 0.7323017120361328, "step": 64880 }, { "epoch": 0.3857196355011859, "grad_norm": 2.368389368057251, "learning_rate": 0.00019955281798723624, "loss": 0.668199872970581, "step": 64890 }, { "epoch": 0.38577907757785423, "grad_norm": 1.657361388206482, "learning_rate": 0.00019955219801948504, "loss": 0.7393317222595215, "step": 64900 }, { "epoch": 0.38583851965452265, "grad_norm": 1.1644914150238037, "learning_rate": 0.0001995515776233454, "loss": 0.6915624141693115, "step": 64910 }, { "epoch": 0.38589796173119106, "grad_norm": 1.7509851455688477, "learning_rate": 0.0001995509567988203, "loss": 0.7661212921142578, "step": 64920 }, { "epoch": 0.3859574038078594, "grad_norm": 2.220461368560791, "learning_rate": 0.00019955033554591267, "loss": 0.7538969993591309, "step": 64930 }, { "epoch": 0.38601684588452784, "grad_norm": 2.134965181350708, "learning_rate": 0.0001995497138646255, "loss": 0.6237539768218994, "step": 64940 }, { "epoch": 0.3860762879611962, "grad_norm": 1.655098557472229, "learning_rate": 0.00019954909175496177, "loss": 0.8026070594787598, "step": 64950 }, { "epoch": 0.3861357300378646, "grad_norm": 1.8736621141433716, "learning_rate": 0.00019954846921692442, "loss": 0.769220495223999, "step": 64960 }, { "epoch": 0.38619517211453297, "grad_norm": 1.8679624795913696, "learning_rate": 0.00019954784625051647, "loss": 0.6754090309143066, "step": 64970 }, { "epoch": 0.3862546141912014, "grad_norm": 1.973091721534729, "learning_rate": 0.0001995472228557409, "loss": 0.7464083671569824, "step": 64980 }, { "epoch": 0.3863140562678698, "grad_norm": 1.6114048957824707, "learning_rate": 0.00019954659903260067, "loss": 0.6632410049438476, "step": 64990 }, { "epoch": 0.38637349834453816, "grad_norm": 1.702515959739685, "learning_rate": 0.00019954597478109878, "loss": 0.6890763282775879, "step": 65000 }, { "epoch": 0.38643294042120657, "grad_norm": 2.1125662326812744, "learning_rate": 0.00019954535010123823, "loss": 0.6764213562011718, "step": 65010 }, { "epoch": 0.38649238249787493, "grad_norm": 1.6301217079162598, "learning_rate": 0.00019954472499302198, "loss": 0.6879745960235596, "step": 65020 }, { "epoch": 0.38655182457454335, "grad_norm": 1.7383958101272583, "learning_rate": 0.00019954409945645301, "loss": 0.682497787475586, "step": 65030 }, { "epoch": 0.3866112666512117, "grad_norm": 2.2303626537323, "learning_rate": 0.00019954347349153436, "loss": 0.7144833564758301, "step": 65040 }, { "epoch": 0.3866707087278801, "grad_norm": 1.6862636804580688, "learning_rate": 0.00019954284709826898, "loss": 0.7131600379943848, "step": 65050 }, { "epoch": 0.38673015080454853, "grad_norm": 1.916646957397461, "learning_rate": 0.00019954222027665988, "loss": 0.6962896347045898, "step": 65060 }, { "epoch": 0.3867895928812169, "grad_norm": 1.7293497323989868, "learning_rate": 0.00019954159302671006, "loss": 0.711960744857788, "step": 65070 }, { "epoch": 0.3868490349578853, "grad_norm": 1.2389838695526123, "learning_rate": 0.00019954096534842251, "loss": 0.6772331237792969, "step": 65080 }, { "epoch": 0.38690847703455367, "grad_norm": 1.8919427394866943, "learning_rate": 0.00019954033724180024, "loss": 0.6674736976623535, "step": 65090 }, { "epoch": 0.3869679191112221, "grad_norm": 1.7548153400421143, "learning_rate": 0.0001995397087068463, "loss": 0.744717025756836, "step": 65100 }, { "epoch": 0.38702736118789044, "grad_norm": 1.5358573198318481, "learning_rate": 0.00019953907974356363, "loss": 0.6520495414733887, "step": 65110 }, { "epoch": 0.38708680326455885, "grad_norm": 1.8105595111846924, "learning_rate": 0.00019953845035195527, "loss": 0.7600845336914063, "step": 65120 }, { "epoch": 0.38714624534122727, "grad_norm": 1.7827503681182861, "learning_rate": 0.0001995378205320242, "loss": 0.7380393028259278, "step": 65130 }, { "epoch": 0.3872056874178956, "grad_norm": 1.517757534980774, "learning_rate": 0.00019953719028377348, "loss": 0.6990550041198731, "step": 65140 }, { "epoch": 0.38726512949456404, "grad_norm": 1.5978126525878906, "learning_rate": 0.0001995365596072061, "loss": 0.710568904876709, "step": 65150 }, { "epoch": 0.3873245715712324, "grad_norm": 3.702385187149048, "learning_rate": 0.0001995359285023251, "loss": 0.6490189552307128, "step": 65160 }, { "epoch": 0.3873840136479008, "grad_norm": 1.6878716945648193, "learning_rate": 0.00019953529696913345, "loss": 0.6607697486877442, "step": 65170 }, { "epoch": 0.3874434557245692, "grad_norm": 1.7703360319137573, "learning_rate": 0.0001995346650076342, "loss": 0.6939688205718995, "step": 65180 }, { "epoch": 0.3875028978012376, "grad_norm": 1.5834258794784546, "learning_rate": 0.00019953403261783038, "loss": 0.6662032127380371, "step": 65190 }, { "epoch": 0.38756233987790595, "grad_norm": 1.806127905845642, "learning_rate": 0.00019953339979972504, "loss": 0.6904889583587647, "step": 65200 }, { "epoch": 0.38762178195457436, "grad_norm": 1.8996012210845947, "learning_rate": 0.0001995327665533211, "loss": 0.7550056457519532, "step": 65210 }, { "epoch": 0.3876812240312428, "grad_norm": 1.4682018756866455, "learning_rate": 0.00019953213287862175, "loss": 0.6862273216247559, "step": 65220 }, { "epoch": 0.38774066610791114, "grad_norm": 1.752314805984497, "learning_rate": 0.0001995314987756299, "loss": 0.6716113090515137, "step": 65230 }, { "epoch": 0.38780010818457955, "grad_norm": 1.3818962574005127, "learning_rate": 0.00019953086424434862, "loss": 0.698981237411499, "step": 65240 }, { "epoch": 0.3878595502612479, "grad_norm": 1.6703420877456665, "learning_rate": 0.00019953022928478092, "loss": 0.6776710510253906, "step": 65250 }, { "epoch": 0.3879189923379163, "grad_norm": 1.580456018447876, "learning_rate": 0.00019952959389692986, "loss": 0.6629307746887207, "step": 65260 }, { "epoch": 0.3879784344145847, "grad_norm": 1.6460514068603516, "learning_rate": 0.0001995289580807985, "loss": 0.6738590240478516, "step": 65270 }, { "epoch": 0.3880378764912531, "grad_norm": 1.6800214052200317, "learning_rate": 0.0001995283218363899, "loss": 0.6515921115875244, "step": 65280 }, { "epoch": 0.3880973185679215, "grad_norm": 1.509191870689392, "learning_rate": 0.00019952768516370704, "loss": 0.7056188583374023, "step": 65290 }, { "epoch": 0.38815676064458987, "grad_norm": 1.5791009664535522, "learning_rate": 0.00019952704806275299, "loss": 0.70953369140625, "step": 65300 }, { "epoch": 0.3882162027212583, "grad_norm": 1.6584175825119019, "learning_rate": 0.00019952641053353075, "loss": 0.6317987442016602, "step": 65310 }, { "epoch": 0.38827564479792664, "grad_norm": 1.5439469814300537, "learning_rate": 0.0001995257725760435, "loss": 0.6679729461669922, "step": 65320 }, { "epoch": 0.38833508687459506, "grad_norm": 2.096418857574463, "learning_rate": 0.00019952513419029417, "loss": 0.7723702907562255, "step": 65330 }, { "epoch": 0.3883945289512634, "grad_norm": 1.7583565711975098, "learning_rate": 0.00019952449537628583, "loss": 0.6944877147674561, "step": 65340 }, { "epoch": 0.38845397102793183, "grad_norm": 1.6505836248397827, "learning_rate": 0.00019952385613402162, "loss": 0.6559981346130371, "step": 65350 }, { "epoch": 0.38851341310460025, "grad_norm": 1.2876317501068115, "learning_rate": 0.0001995232164635045, "loss": 0.6572076797485351, "step": 65360 }, { "epoch": 0.3885728551812686, "grad_norm": 1.8986883163452148, "learning_rate": 0.00019952257636473756, "loss": 0.6770967483520508, "step": 65370 }, { "epoch": 0.388632297257937, "grad_norm": 1.7509382963180542, "learning_rate": 0.00019952193583772389, "loss": 0.7086244106292725, "step": 65380 }, { "epoch": 0.3886917393346054, "grad_norm": 2.048309564590454, "learning_rate": 0.00019952129488246657, "loss": 0.6642643928527832, "step": 65390 }, { "epoch": 0.3887511814112738, "grad_norm": 1.7249820232391357, "learning_rate": 0.00019952065349896858, "loss": 0.6941184520721435, "step": 65400 }, { "epoch": 0.38881062348794215, "grad_norm": 1.5682297945022583, "learning_rate": 0.00019952001168723306, "loss": 0.683827543258667, "step": 65410 }, { "epoch": 0.38887006556461057, "grad_norm": 1.782725214958191, "learning_rate": 0.00019951936944726306, "loss": 0.7092089653015137, "step": 65420 }, { "epoch": 0.388929507641279, "grad_norm": 1.5880597829818726, "learning_rate": 0.00019951872677906164, "loss": 0.6414956092834473, "step": 65430 }, { "epoch": 0.38898894971794734, "grad_norm": 1.7830713987350464, "learning_rate": 0.0001995180836826319, "loss": 0.7296354293823242, "step": 65440 }, { "epoch": 0.38904839179461576, "grad_norm": 1.8681774139404297, "learning_rate": 0.00019951744015797687, "loss": 0.7377835750579834, "step": 65450 }, { "epoch": 0.3891078338712841, "grad_norm": 1.6326009035110474, "learning_rate": 0.00019951679620509971, "loss": 0.6637416839599609, "step": 65460 }, { "epoch": 0.38916727594795253, "grad_norm": 1.598022222518921, "learning_rate": 0.00019951615182400343, "loss": 0.7193143844604493, "step": 65470 }, { "epoch": 0.3892267180246209, "grad_norm": 1.2209222316741943, "learning_rate": 0.00019951550701469115, "loss": 0.6718876838684082, "step": 65480 }, { "epoch": 0.3892861601012893, "grad_norm": 1.2576282024383545, "learning_rate": 0.0001995148617771659, "loss": 0.687205457687378, "step": 65490 }, { "epoch": 0.38934560217795766, "grad_norm": 1.7591564655303955, "learning_rate": 0.0001995142161114308, "loss": 0.7309814453125, "step": 65500 }, { "epoch": 0.3894050442546261, "grad_norm": 1.8742064237594604, "learning_rate": 0.00019951357001748898, "loss": 0.6694709300994873, "step": 65510 }, { "epoch": 0.3894644863312945, "grad_norm": 2.1326816082000732, "learning_rate": 0.0001995129234953435, "loss": 0.7421957969665527, "step": 65520 }, { "epoch": 0.38952392840796285, "grad_norm": 1.5725406408309937, "learning_rate": 0.00019951227654499743, "loss": 0.7017546653747558, "step": 65530 }, { "epoch": 0.38958337048463126, "grad_norm": 1.6485625505447388, "learning_rate": 0.00019951162916645386, "loss": 0.7197862148284913, "step": 65540 }, { "epoch": 0.3896428125612996, "grad_norm": 1.6353017091751099, "learning_rate": 0.00019951098135971598, "loss": 0.7163830757141113, "step": 65550 }, { "epoch": 0.38970225463796804, "grad_norm": 1.60709810256958, "learning_rate": 0.00019951033312478675, "loss": 0.7307255268096924, "step": 65560 }, { "epoch": 0.3897616967146364, "grad_norm": 1.6307868957519531, "learning_rate": 0.00019950968446166937, "loss": 0.6800230979919434, "step": 65570 }, { "epoch": 0.3898211387913048, "grad_norm": 1.9981193542480469, "learning_rate": 0.00019950903537036688, "loss": 0.6977209091186524, "step": 65580 }, { "epoch": 0.3898805808679732, "grad_norm": 1.9066938161849976, "learning_rate": 0.00019950838585088243, "loss": 0.7352346420288086, "step": 65590 }, { "epoch": 0.3899400229446416, "grad_norm": 2.282128095626831, "learning_rate": 0.0001995077359032191, "loss": 0.6708132266998291, "step": 65600 }, { "epoch": 0.38999946502131, "grad_norm": 1.608796238899231, "learning_rate": 0.00019950708552738005, "loss": 0.7442547798156738, "step": 65610 }, { "epoch": 0.39005890709797836, "grad_norm": 2.3333070278167725, "learning_rate": 0.00019950643472336837, "loss": 0.7249269485473633, "step": 65620 }, { "epoch": 0.3901183491746468, "grad_norm": 1.5990203619003296, "learning_rate": 0.0001995057834911871, "loss": 0.7995199680328369, "step": 65630 }, { "epoch": 0.39017779125131513, "grad_norm": 1.7105926275253296, "learning_rate": 0.00019950513183083943, "loss": 0.690202283859253, "step": 65640 }, { "epoch": 0.39023723332798355, "grad_norm": 1.6576536893844604, "learning_rate": 0.00019950447974232847, "loss": 0.6997118473052979, "step": 65650 }, { "epoch": 0.39029667540465196, "grad_norm": 1.9588896036148071, "learning_rate": 0.00019950382722565732, "loss": 0.6948881626129151, "step": 65660 }, { "epoch": 0.3903561174813203, "grad_norm": 1.991999864578247, "learning_rate": 0.00019950317428082913, "loss": 0.7182047367095947, "step": 65670 }, { "epoch": 0.39041555955798873, "grad_norm": 1.4399034976959229, "learning_rate": 0.00019950252090784697, "loss": 0.6871001720428467, "step": 65680 }, { "epoch": 0.3904750016346571, "grad_norm": 1.7138456106185913, "learning_rate": 0.00019950186710671403, "loss": 0.6806119918823242, "step": 65690 }, { "epoch": 0.3905344437113255, "grad_norm": 1.7250443696975708, "learning_rate": 0.00019950121287743339, "loss": 0.6479268074035645, "step": 65700 }, { "epoch": 0.39059388578799387, "grad_norm": 3.0893712043762207, "learning_rate": 0.00019950055822000825, "loss": 0.7055497169494629, "step": 65710 }, { "epoch": 0.3906533278646623, "grad_norm": 1.586309552192688, "learning_rate": 0.0001994999031344416, "loss": 0.6771054744720459, "step": 65720 }, { "epoch": 0.3907127699413307, "grad_norm": 1.6788922548294067, "learning_rate": 0.00019949924762073672, "loss": 0.6335363864898682, "step": 65730 }, { "epoch": 0.39077221201799905, "grad_norm": 1.5365607738494873, "learning_rate": 0.00019949859167889668, "loss": 0.7072541236877441, "step": 65740 }, { "epoch": 0.39083165409466747, "grad_norm": 1.3683267831802368, "learning_rate": 0.00019949793530892463, "loss": 0.6872946739196777, "step": 65750 }, { "epoch": 0.39089109617133583, "grad_norm": 1.897680401802063, "learning_rate": 0.00019949727851082367, "loss": 0.6745636940002442, "step": 65760 }, { "epoch": 0.39095053824800424, "grad_norm": 1.9071455001831055, "learning_rate": 0.00019949662128459697, "loss": 0.697634506225586, "step": 65770 }, { "epoch": 0.3910099803246726, "grad_norm": 1.5668679475784302, "learning_rate": 0.00019949596363024773, "loss": 0.6502202987670899, "step": 65780 }, { "epoch": 0.391069422401341, "grad_norm": 1.7476129531860352, "learning_rate": 0.00019949530554777905, "loss": 0.6788819313049317, "step": 65790 }, { "epoch": 0.39112886447800943, "grad_norm": 1.6855261325836182, "learning_rate": 0.00019949464703719404, "loss": 0.6360837936401367, "step": 65800 }, { "epoch": 0.3911883065546778, "grad_norm": 2.074084520339966, "learning_rate": 0.0001994939880984959, "loss": 0.6952112197875977, "step": 65810 }, { "epoch": 0.3912477486313462, "grad_norm": 1.7567641735076904, "learning_rate": 0.0001994933287316878, "loss": 0.6166691780090332, "step": 65820 }, { "epoch": 0.39130719070801456, "grad_norm": 1.4560805559158325, "learning_rate": 0.00019949266893677282, "loss": 0.6703331470489502, "step": 65830 }, { "epoch": 0.391366632784683, "grad_norm": 2.700868844985962, "learning_rate": 0.00019949200871375417, "loss": 0.6910903453826904, "step": 65840 }, { "epoch": 0.39142607486135134, "grad_norm": 1.6695228815078735, "learning_rate": 0.00019949134806263502, "loss": 0.6622378349304199, "step": 65850 }, { "epoch": 0.39148551693801975, "grad_norm": 1.6999813318252563, "learning_rate": 0.00019949068698341848, "loss": 0.7081543445587158, "step": 65860 }, { "epoch": 0.3915449590146881, "grad_norm": 1.696933388710022, "learning_rate": 0.00019949002547610774, "loss": 0.7403446674346924, "step": 65870 }, { "epoch": 0.3916044010913565, "grad_norm": 1.430483341217041, "learning_rate": 0.00019948936354070596, "loss": 0.6996264457702637, "step": 65880 }, { "epoch": 0.39166384316802494, "grad_norm": 1.599283218383789, "learning_rate": 0.00019948870117721633, "loss": 0.6703888893127441, "step": 65890 }, { "epoch": 0.3917232852446933, "grad_norm": 1.3342111110687256, "learning_rate": 0.000199488038385642, "loss": 0.6261160373687744, "step": 65900 }, { "epoch": 0.3917827273213617, "grad_norm": 1.7015026807785034, "learning_rate": 0.00019948737516598612, "loss": 0.6856660842895508, "step": 65910 }, { "epoch": 0.39184216939803007, "grad_norm": 1.8862972259521484, "learning_rate": 0.00019948671151825186, "loss": 0.6305600166320801, "step": 65920 }, { "epoch": 0.3919016114746985, "grad_norm": 1.8694664239883423, "learning_rate": 0.00019948604744244247, "loss": 0.6744968891143799, "step": 65930 }, { "epoch": 0.39196105355136684, "grad_norm": 1.615513801574707, "learning_rate": 0.00019948538293856105, "loss": 0.7139352321624756, "step": 65940 }, { "epoch": 0.39202049562803526, "grad_norm": 1.3461039066314697, "learning_rate": 0.00019948471800661078, "loss": 0.657561206817627, "step": 65950 }, { "epoch": 0.3920799377047037, "grad_norm": 1.707016110420227, "learning_rate": 0.00019948405264659492, "loss": 0.6513078689575196, "step": 65960 }, { "epoch": 0.39213937978137203, "grad_norm": 1.986045002937317, "learning_rate": 0.00019948338685851652, "loss": 0.7570724487304688, "step": 65970 }, { "epoch": 0.39219882185804045, "grad_norm": 1.8399001359939575, "learning_rate": 0.0001994827206423789, "loss": 0.6361473083496094, "step": 65980 }, { "epoch": 0.3922582639347088, "grad_norm": 1.6689187288284302, "learning_rate": 0.0001994820539981852, "loss": 0.6562509536743164, "step": 65990 }, { "epoch": 0.3923177060113772, "grad_norm": 1.8568916320800781, "learning_rate": 0.00019948138692593855, "loss": 0.6849184036254883, "step": 66000 }, { "epoch": 0.3923771480880456, "grad_norm": 1.9400041103363037, "learning_rate": 0.00019948071942564217, "loss": 0.68739013671875, "step": 66010 }, { "epoch": 0.392436590164714, "grad_norm": 1.9292970895767212, "learning_rate": 0.00019948005149729933, "loss": 0.6720841407775879, "step": 66020 }, { "epoch": 0.3924960322413824, "grad_norm": 1.6615042686462402, "learning_rate": 0.0001994793831409131, "loss": 0.7304876327514649, "step": 66030 }, { "epoch": 0.39255547431805077, "grad_norm": 1.52157723903656, "learning_rate": 0.0001994787143564868, "loss": 0.6971402168273926, "step": 66040 }, { "epoch": 0.3926149163947192, "grad_norm": 1.9177404642105103, "learning_rate": 0.00019947804514402356, "loss": 0.7424870014190674, "step": 66050 }, { "epoch": 0.39267435847138754, "grad_norm": 1.716871976852417, "learning_rate": 0.0001994773755035266, "loss": 0.6841750144958496, "step": 66060 }, { "epoch": 0.39273380054805596, "grad_norm": 1.6962016820907593, "learning_rate": 0.0001994767054349991, "loss": 0.6712775230407715, "step": 66070 }, { "epoch": 0.3927932426247243, "grad_norm": 1.9007545709609985, "learning_rate": 0.00019947603493844428, "loss": 0.6979959011077881, "step": 66080 }, { "epoch": 0.39285268470139273, "grad_norm": 1.4994651079177856, "learning_rate": 0.00019947536401386537, "loss": 0.6615341186523438, "step": 66090 }, { "epoch": 0.39291212677806114, "grad_norm": 2.032104969024658, "learning_rate": 0.00019947469266126555, "loss": 0.7227169036865234, "step": 66100 }, { "epoch": 0.3929715688547295, "grad_norm": 1.6703697443008423, "learning_rate": 0.00019947402088064806, "loss": 0.7070719718933105, "step": 66110 }, { "epoch": 0.3930310109313979, "grad_norm": 2.4032883644104004, "learning_rate": 0.00019947334867201607, "loss": 0.6918091773986816, "step": 66120 }, { "epoch": 0.3930904530080663, "grad_norm": 1.7453144788742065, "learning_rate": 0.0001994726760353728, "loss": 0.6504475593566894, "step": 66130 }, { "epoch": 0.3931498950847347, "grad_norm": 1.6114619970321655, "learning_rate": 0.0001994720029707215, "loss": 0.731486177444458, "step": 66140 }, { "epoch": 0.39320933716140305, "grad_norm": 2.0668070316314697, "learning_rate": 0.0001994713294780654, "loss": 0.6976473808288575, "step": 66150 }, { "epoch": 0.39326877923807146, "grad_norm": 1.7276455163955688, "learning_rate": 0.0001994706555574077, "loss": 0.6831431865692139, "step": 66160 }, { "epoch": 0.3933282213147399, "grad_norm": 1.8251488208770752, "learning_rate": 0.00019946998120875162, "loss": 0.6457240104675293, "step": 66170 }, { "epoch": 0.39338766339140824, "grad_norm": 1.546732783317566, "learning_rate": 0.00019946930643210037, "loss": 0.7052833557128906, "step": 66180 }, { "epoch": 0.39344710546807665, "grad_norm": 1.9401576519012451, "learning_rate": 0.0001994686312274572, "loss": 0.69742431640625, "step": 66190 }, { "epoch": 0.393506547544745, "grad_norm": 1.8795713186264038, "learning_rate": 0.00019946795559482535, "loss": 0.7026110172271729, "step": 66200 }, { "epoch": 0.3935659896214134, "grad_norm": 1.9619123935699463, "learning_rate": 0.00019946727953420803, "loss": 0.6985588073730469, "step": 66210 }, { "epoch": 0.3936254316980818, "grad_norm": 1.3327199220657349, "learning_rate": 0.0001994666030456085, "loss": 0.7199788570404053, "step": 66220 }, { "epoch": 0.3936848737747502, "grad_norm": 1.978417158126831, "learning_rate": 0.00019946592612902998, "loss": 0.7106932640075684, "step": 66230 }, { "epoch": 0.39374431585141856, "grad_norm": 1.6130529642105103, "learning_rate": 0.00019946524878447567, "loss": 0.6928305625915527, "step": 66240 }, { "epoch": 0.393803757928087, "grad_norm": 1.5358339548110962, "learning_rate": 0.00019946457101194885, "loss": 0.632631778717041, "step": 66250 }, { "epoch": 0.3938632000047554, "grad_norm": 1.6425373554229736, "learning_rate": 0.00019946389281145282, "loss": 0.6610629081726074, "step": 66260 }, { "epoch": 0.39392264208142375, "grad_norm": 2.1261215209960938, "learning_rate": 0.00019946321418299072, "loss": 0.6723674774169922, "step": 66270 }, { "epoch": 0.39398208415809216, "grad_norm": 2.045476198196411, "learning_rate": 0.00019946253512656583, "loss": 0.6604060173034668, "step": 66280 }, { "epoch": 0.3940415262347605, "grad_norm": 1.8003582954406738, "learning_rate": 0.00019946185564218144, "loss": 0.6783098220825196, "step": 66290 }, { "epoch": 0.39410096831142893, "grad_norm": 1.8057197332382202, "learning_rate": 0.00019946117572984073, "loss": 0.7232184410095215, "step": 66300 }, { "epoch": 0.3941604103880973, "grad_norm": 1.954648733139038, "learning_rate": 0.000199460495389547, "loss": 0.675203800201416, "step": 66310 }, { "epoch": 0.3942198524647657, "grad_norm": 1.7885503768920898, "learning_rate": 0.00019945981462130352, "loss": 0.6858013153076172, "step": 66320 }, { "epoch": 0.3942792945414341, "grad_norm": 1.7554755210876465, "learning_rate": 0.00019945913342511352, "loss": 0.7406038761138916, "step": 66330 }, { "epoch": 0.3943387366181025, "grad_norm": 1.7623716592788696, "learning_rate": 0.00019945845180098024, "loss": 0.7363703727722168, "step": 66340 }, { "epoch": 0.3943981786947709, "grad_norm": 1.2791780233383179, "learning_rate": 0.00019945776974890697, "loss": 0.6893930435180664, "step": 66350 }, { "epoch": 0.39445762077143925, "grad_norm": 2.0812320709228516, "learning_rate": 0.000199457087268897, "loss": 0.6901299953460693, "step": 66360 }, { "epoch": 0.39451706284810767, "grad_norm": 2.3043532371520996, "learning_rate": 0.00019945640436095353, "loss": 0.7179162979125977, "step": 66370 }, { "epoch": 0.39457650492477603, "grad_norm": 1.8064671754837036, "learning_rate": 0.00019945572102507983, "loss": 0.7347990989685058, "step": 66380 }, { "epoch": 0.39463594700144444, "grad_norm": 1.8559926748275757, "learning_rate": 0.00019945503726127923, "loss": 0.6474820613861084, "step": 66390 }, { "epoch": 0.39469538907811286, "grad_norm": 1.7057627439498901, "learning_rate": 0.00019945435306955496, "loss": 0.6706602096557617, "step": 66400 }, { "epoch": 0.3947548311547812, "grad_norm": 1.849409818649292, "learning_rate": 0.0001994536684499103, "loss": 0.6945438861846924, "step": 66410 }, { "epoch": 0.39481427323144963, "grad_norm": 1.526241421699524, "learning_rate": 0.0001994529834023485, "loss": 0.6614214897155761, "step": 66420 }, { "epoch": 0.394873715308118, "grad_norm": 1.8680423498153687, "learning_rate": 0.0001994522979268729, "loss": 0.7253200054168701, "step": 66430 }, { "epoch": 0.3949331573847864, "grad_norm": 1.6043648719787598, "learning_rate": 0.00019945161202348673, "loss": 0.7227263450622559, "step": 66440 }, { "epoch": 0.39499259946145476, "grad_norm": 1.7216910123825073, "learning_rate": 0.00019945092569219325, "loss": 0.702854061126709, "step": 66450 }, { "epoch": 0.3950520415381232, "grad_norm": 1.5584272146224976, "learning_rate": 0.00019945023893299578, "loss": 0.6778756141662597, "step": 66460 }, { "epoch": 0.3951114836147916, "grad_norm": 2.000448226928711, "learning_rate": 0.00019944955174589765, "loss": 0.7407962799072265, "step": 66470 }, { "epoch": 0.39517092569145995, "grad_norm": 1.4600163698196411, "learning_rate": 0.00019944886413090208, "loss": 0.7414121627807617, "step": 66480 }, { "epoch": 0.39523036776812837, "grad_norm": 1.8214898109436035, "learning_rate": 0.00019944817608801233, "loss": 0.7322946548461914, "step": 66490 }, { "epoch": 0.3952898098447967, "grad_norm": 1.6508148908615112, "learning_rate": 0.00019944748761723178, "loss": 0.753032112121582, "step": 66500 }, { "epoch": 0.39534925192146514, "grad_norm": 2.0360465049743652, "learning_rate": 0.00019944679871856366, "loss": 0.7441139221191406, "step": 66510 }, { "epoch": 0.3954086939981335, "grad_norm": 1.4109126329421997, "learning_rate": 0.0001994461093920113, "loss": 0.7140334129333497, "step": 66520 }, { "epoch": 0.3954681360748019, "grad_norm": 3.2466065883636475, "learning_rate": 0.00019944541963757797, "loss": 0.7403457641601563, "step": 66530 }, { "epoch": 0.3955275781514703, "grad_norm": 1.700913429260254, "learning_rate": 0.000199444729455267, "loss": 0.7007652759552002, "step": 66540 }, { "epoch": 0.3955870202281387, "grad_norm": 1.4941797256469727, "learning_rate": 0.00019944403884508165, "loss": 0.7180958747863769, "step": 66550 }, { "epoch": 0.3956464623048071, "grad_norm": 1.8413100242614746, "learning_rate": 0.00019944334780702525, "loss": 0.7245165824890136, "step": 66560 }, { "epoch": 0.39570590438147546, "grad_norm": 1.9758870601654053, "learning_rate": 0.00019944265634110113, "loss": 0.6878519058227539, "step": 66570 }, { "epoch": 0.3957653464581439, "grad_norm": 1.4860312938690186, "learning_rate": 0.00019944196444731256, "loss": 0.7447872161865234, "step": 66580 }, { "epoch": 0.39582478853481223, "grad_norm": 1.8021231889724731, "learning_rate": 0.00019944127212566287, "loss": 0.6383648872375488, "step": 66590 }, { "epoch": 0.39588423061148065, "grad_norm": 1.704011082649231, "learning_rate": 0.00019944057937615534, "loss": 0.6670961380004883, "step": 66600 }, { "epoch": 0.395943672688149, "grad_norm": 2.0994057655334473, "learning_rate": 0.00019943988619879337, "loss": 0.6889895439147949, "step": 66610 }, { "epoch": 0.3960031147648174, "grad_norm": 1.4693679809570312, "learning_rate": 0.00019943919259358012, "loss": 0.6418837070465088, "step": 66620 }, { "epoch": 0.39606255684148584, "grad_norm": 1.6431022882461548, "learning_rate": 0.0001994384985605191, "loss": 0.6805311679840088, "step": 66630 }, { "epoch": 0.3961219989181542, "grad_norm": 1.8829184770584106, "learning_rate": 0.00019943780409961345, "loss": 0.6898926734924317, "step": 66640 }, { "epoch": 0.3961814409948226, "grad_norm": 1.4996992349624634, "learning_rate": 0.00019943710921086662, "loss": 0.6427838325500488, "step": 66650 }, { "epoch": 0.39624088307149097, "grad_norm": 2.12288236618042, "learning_rate": 0.00019943641389428188, "loss": 0.6947166442871093, "step": 66660 }, { "epoch": 0.3963003251481594, "grad_norm": 1.4233771562576294, "learning_rate": 0.00019943571814986258, "loss": 0.6424132347106933, "step": 66670 }, { "epoch": 0.39635976722482774, "grad_norm": 1.938294768333435, "learning_rate": 0.00019943502197761198, "loss": 0.6707683563232422, "step": 66680 }, { "epoch": 0.39641920930149616, "grad_norm": 1.38737952709198, "learning_rate": 0.0001994343253775335, "loss": 0.7144562721252441, "step": 66690 }, { "epoch": 0.39647865137816457, "grad_norm": 2.161083698272705, "learning_rate": 0.0001994336283496304, "loss": 0.6940652370452881, "step": 66700 }, { "epoch": 0.39653809345483293, "grad_norm": 1.767340898513794, "learning_rate": 0.00019943293089390608, "loss": 0.7172839641571045, "step": 66710 }, { "epoch": 0.39659753553150134, "grad_norm": 1.5531686544418335, "learning_rate": 0.00019943223301036384, "loss": 0.7119640827178955, "step": 66720 }, { "epoch": 0.3966569776081697, "grad_norm": 1.5417298078536987, "learning_rate": 0.00019943153469900704, "loss": 0.7613700866699219, "step": 66730 }, { "epoch": 0.3967164196848381, "grad_norm": 1.9551588296890259, "learning_rate": 0.000199430835959839, "loss": 0.6638846397399902, "step": 66740 }, { "epoch": 0.3967758617615065, "grad_norm": 1.8031134605407715, "learning_rate": 0.00019943013679286307, "loss": 0.7507706642150879, "step": 66750 }, { "epoch": 0.3968353038381749, "grad_norm": 1.6690330505371094, "learning_rate": 0.00019942943719808255, "loss": 0.6632400989532471, "step": 66760 }, { "epoch": 0.3968947459148433, "grad_norm": 2.0104904174804688, "learning_rate": 0.00019942873717550087, "loss": 0.6587494850158692, "step": 66770 }, { "epoch": 0.39695418799151166, "grad_norm": 1.5476137399673462, "learning_rate": 0.00019942803672512132, "loss": 0.6473172187805176, "step": 66780 }, { "epoch": 0.3970136300681801, "grad_norm": 1.452139973640442, "learning_rate": 0.00019942733584694727, "loss": 0.6955291748046875, "step": 66790 }, { "epoch": 0.39707307214484844, "grad_norm": 1.5081024169921875, "learning_rate": 0.0001994266345409821, "loss": 0.6980170249938965, "step": 66800 }, { "epoch": 0.39713251422151685, "grad_norm": 1.5587725639343262, "learning_rate": 0.0001994259328072291, "loss": 0.7182927131652832, "step": 66810 }, { "epoch": 0.3971919562981852, "grad_norm": 1.5597642660140991, "learning_rate": 0.00019942523064569168, "loss": 0.661495304107666, "step": 66820 }, { "epoch": 0.3972513983748536, "grad_norm": 1.920731782913208, "learning_rate": 0.00019942452805637314, "loss": 0.7080678462982177, "step": 66830 }, { "epoch": 0.39731084045152204, "grad_norm": 1.709220290184021, "learning_rate": 0.00019942382503927692, "loss": 0.6917498588562012, "step": 66840 }, { "epoch": 0.3973702825281904, "grad_norm": 1.569123387336731, "learning_rate": 0.00019942312159440637, "loss": 0.7092861652374267, "step": 66850 }, { "epoch": 0.3974297246048588, "grad_norm": 1.8691610097885132, "learning_rate": 0.0001994224177217648, "loss": 0.6339394569396972, "step": 66860 }, { "epoch": 0.3974891666815272, "grad_norm": 1.7592836618423462, "learning_rate": 0.0001994217134213556, "loss": 0.7663500308990479, "step": 66870 }, { "epoch": 0.3975486087581956, "grad_norm": 2.035031795501709, "learning_rate": 0.00019942100869318213, "loss": 0.714727783203125, "step": 66880 }, { "epoch": 0.39760805083486395, "grad_norm": 2.2150230407714844, "learning_rate": 0.00019942030353724784, "loss": 0.6693394660949707, "step": 66890 }, { "epoch": 0.39766749291153236, "grad_norm": 2.2016375064849854, "learning_rate": 0.00019941959795355597, "loss": 0.6823408126831054, "step": 66900 }, { "epoch": 0.3977269349882008, "grad_norm": 1.3595423698425293, "learning_rate": 0.00019941889194211002, "loss": 0.7196648597717286, "step": 66910 }, { "epoch": 0.39778637706486913, "grad_norm": 1.827473759651184, "learning_rate": 0.00019941818550291328, "loss": 0.7258564949035644, "step": 66920 }, { "epoch": 0.39784581914153755, "grad_norm": 1.885546326637268, "learning_rate": 0.00019941747863596915, "loss": 0.6735611915588379, "step": 66930 }, { "epoch": 0.3979052612182059, "grad_norm": 1.545878291130066, "learning_rate": 0.00019941677134128108, "loss": 0.6735701560974121, "step": 66940 }, { "epoch": 0.3979647032948743, "grad_norm": 2.4352712631225586, "learning_rate": 0.00019941606361885238, "loss": 0.7040517807006836, "step": 66950 }, { "epoch": 0.3980241453715427, "grad_norm": 1.5988152027130127, "learning_rate": 0.00019941535546868643, "loss": 0.6615699768066406, "step": 66960 }, { "epoch": 0.3980835874482111, "grad_norm": 1.6050443649291992, "learning_rate": 0.00019941464689078662, "loss": 0.7059239387512207, "step": 66970 }, { "epoch": 0.39814302952487945, "grad_norm": 1.4788777828216553, "learning_rate": 0.00019941393788515638, "loss": 0.7040739059448242, "step": 66980 }, { "epoch": 0.39820247160154787, "grad_norm": 1.5723984241485596, "learning_rate": 0.00019941322845179913, "loss": 0.7396260738372803, "step": 66990 }, { "epoch": 0.3982619136782163, "grad_norm": 1.695717215538025, "learning_rate": 0.00019941251859071816, "loss": 0.6925202369689941, "step": 67000 }, { "epoch": 0.39832135575488464, "grad_norm": 1.4487866163253784, "learning_rate": 0.00019941180830191694, "loss": 0.6501960754394531, "step": 67010 }, { "epoch": 0.39838079783155306, "grad_norm": 2.0096137523651123, "learning_rate": 0.00019941109758539883, "loss": 0.6884290695190429, "step": 67020 }, { "epoch": 0.3984402399082214, "grad_norm": 1.6808483600616455, "learning_rate": 0.0001994103864411673, "loss": 0.6485541343688965, "step": 67030 }, { "epoch": 0.39849968198488983, "grad_norm": 1.6551536321640015, "learning_rate": 0.00019940967486922564, "loss": 0.7088194847106933, "step": 67040 }, { "epoch": 0.3985591240615582, "grad_norm": 1.8471373319625854, "learning_rate": 0.00019940896286957735, "loss": 0.6760054111480713, "step": 67050 }, { "epoch": 0.3986185661382266, "grad_norm": 1.7988320589065552, "learning_rate": 0.0001994082504422258, "loss": 0.6856563091278076, "step": 67060 }, { "epoch": 0.398678008214895, "grad_norm": 2.1686835289001465, "learning_rate": 0.0001994075375871744, "loss": 0.6259615421295166, "step": 67070 }, { "epoch": 0.3987374502915634, "grad_norm": 1.6877044439315796, "learning_rate": 0.00019940682430442654, "loss": 0.6479076385498047, "step": 67080 }, { "epoch": 0.3987968923682318, "grad_norm": 1.9171593189239502, "learning_rate": 0.00019940611059398564, "loss": 0.7100530624389648, "step": 67090 }, { "epoch": 0.39885633444490015, "grad_norm": 1.8369956016540527, "learning_rate": 0.00019940539645585517, "loss": 0.7109979629516602, "step": 67100 }, { "epoch": 0.39891577652156857, "grad_norm": 1.758373737335205, "learning_rate": 0.00019940468189003847, "loss": 0.7097258567810059, "step": 67110 }, { "epoch": 0.3989752185982369, "grad_norm": 1.5621076822280884, "learning_rate": 0.000199403966896539, "loss": 0.7311155319213867, "step": 67120 }, { "epoch": 0.39903466067490534, "grad_norm": 1.7210553884506226, "learning_rate": 0.00019940325147536016, "loss": 0.67837495803833, "step": 67130 }, { "epoch": 0.39909410275157375, "grad_norm": 1.6947901248931885, "learning_rate": 0.0001994025356265054, "loss": 0.6709794044494629, "step": 67140 }, { "epoch": 0.3991535448282421, "grad_norm": 1.4705851078033447, "learning_rate": 0.0001994018193499781, "loss": 0.6727256774902344, "step": 67150 }, { "epoch": 0.3992129869049105, "grad_norm": 1.926596760749817, "learning_rate": 0.00019940110264578175, "loss": 0.6494449615478516, "step": 67160 }, { "epoch": 0.3992724289815789, "grad_norm": 1.8081530332565308, "learning_rate": 0.00019940038551391972, "loss": 0.6625981330871582, "step": 67170 }, { "epoch": 0.3993318710582473, "grad_norm": 1.739139199256897, "learning_rate": 0.00019939966795439547, "loss": 0.7095789432525634, "step": 67180 }, { "epoch": 0.39939131313491566, "grad_norm": 1.7064166069030762, "learning_rate": 0.0001993989499672124, "loss": 0.6584457397460938, "step": 67190 }, { "epoch": 0.3994507552115841, "grad_norm": 1.3881542682647705, "learning_rate": 0.000199398231552374, "loss": 0.6627434730529785, "step": 67200 }, { "epoch": 0.3995101972882525, "grad_norm": 2.055696964263916, "learning_rate": 0.00019939751270988367, "loss": 0.7039466381072998, "step": 67210 }, { "epoch": 0.39956963936492085, "grad_norm": 1.373346209526062, "learning_rate": 0.00019939679343974485, "loss": 0.713214921951294, "step": 67220 }, { "epoch": 0.39962908144158926, "grad_norm": 1.7146856784820557, "learning_rate": 0.00019939607374196098, "loss": 0.6945335388183593, "step": 67230 }, { "epoch": 0.3996885235182576, "grad_norm": 1.5864518880844116, "learning_rate": 0.0001993953536165355, "loss": 0.7254159450531006, "step": 67240 }, { "epoch": 0.39974796559492604, "grad_norm": 1.548848032951355, "learning_rate": 0.00019939463306347188, "loss": 0.6355718612670899, "step": 67250 }, { "epoch": 0.3998074076715944, "grad_norm": 1.5136287212371826, "learning_rate": 0.00019939391208277353, "loss": 0.7169608116149903, "step": 67260 }, { "epoch": 0.3998668497482628, "grad_norm": 1.7900148630142212, "learning_rate": 0.00019939319067444395, "loss": 0.653503704071045, "step": 67270 }, { "epoch": 0.39992629182493117, "grad_norm": 2.0921833515167236, "learning_rate": 0.00019939246883848654, "loss": 0.7309167861938477, "step": 67280 }, { "epoch": 0.3999857339015996, "grad_norm": 1.689884066581726, "learning_rate": 0.00019939174657490478, "loss": 0.6646222114562989, "step": 67290 }, { "epoch": 0.400045175978268, "grad_norm": 1.88619863986969, "learning_rate": 0.00019939102388370213, "loss": 0.7485777854919433, "step": 67300 }, { "epoch": 0.40010461805493636, "grad_norm": 1.784059762954712, "learning_rate": 0.00019939030076488202, "loss": 0.7093802452087402, "step": 67310 }, { "epoch": 0.40016406013160477, "grad_norm": 1.7928106784820557, "learning_rate": 0.0001993895772184479, "loss": 0.6747223854064941, "step": 67320 }, { "epoch": 0.40022350220827313, "grad_norm": 1.7883810997009277, "learning_rate": 0.0001993888532444033, "loss": 0.6806139945983887, "step": 67330 }, { "epoch": 0.40028294428494154, "grad_norm": 1.928360939025879, "learning_rate": 0.00019938812884275157, "loss": 0.6917176246643066, "step": 67340 }, { "epoch": 0.4003423863616099, "grad_norm": 1.8535641431808472, "learning_rate": 0.00019938740401349633, "loss": 0.6913335800170899, "step": 67350 }, { "epoch": 0.4004018284382783, "grad_norm": 1.3995448350906372, "learning_rate": 0.00019938667875664092, "loss": 0.6727135658264161, "step": 67360 }, { "epoch": 0.40046127051494673, "grad_norm": 1.4030685424804688, "learning_rate": 0.00019938595307218883, "loss": 0.6992118835449219, "step": 67370 }, { "epoch": 0.4005207125916151, "grad_norm": 2.251784086227417, "learning_rate": 0.00019938522696014358, "loss": 0.6994130611419678, "step": 67380 }, { "epoch": 0.4005801546682835, "grad_norm": 1.727491855621338, "learning_rate": 0.00019938450042050862, "loss": 0.6704360961914062, "step": 67390 }, { "epoch": 0.40063959674495186, "grad_norm": 1.483297348022461, "learning_rate": 0.00019938377345328742, "loss": 0.7294423103332519, "step": 67400 }, { "epoch": 0.4006990388216203, "grad_norm": 1.555530071258545, "learning_rate": 0.00019938304605848344, "loss": 0.6879263401031495, "step": 67410 }, { "epoch": 0.40075848089828864, "grad_norm": 1.551784873008728, "learning_rate": 0.0001993823182361002, "loss": 0.6821396827697754, "step": 67420 }, { "epoch": 0.40081792297495705, "grad_norm": 1.5181770324707031, "learning_rate": 0.00019938158998614113, "loss": 0.7304794311523437, "step": 67430 }, { "epoch": 0.40087736505162547, "grad_norm": 1.440852403640747, "learning_rate": 0.00019938086130860978, "loss": 0.6530575752258301, "step": 67440 }, { "epoch": 0.4009368071282938, "grad_norm": 1.4549294710159302, "learning_rate": 0.00019938013220350957, "loss": 0.6592973232269287, "step": 67450 }, { "epoch": 0.40099624920496224, "grad_norm": 2.5471229553222656, "learning_rate": 0.00019937940267084406, "loss": 0.7189562797546387, "step": 67460 }, { "epoch": 0.4010556912816306, "grad_norm": 1.9380559921264648, "learning_rate": 0.00019937867271061662, "loss": 0.7354538917541504, "step": 67470 }, { "epoch": 0.401115133358299, "grad_norm": 1.5366796255111694, "learning_rate": 0.0001993779423228309, "loss": 0.7407680511474609, "step": 67480 }, { "epoch": 0.4011745754349674, "grad_norm": 1.7886499166488647, "learning_rate": 0.0001993772115074903, "loss": 0.6522284507751465, "step": 67490 }, { "epoch": 0.4012340175116358, "grad_norm": 1.501666784286499, "learning_rate": 0.0001993764802645983, "loss": 0.6255769729614258, "step": 67500 }, { "epoch": 0.4012934595883042, "grad_norm": 1.5428661108016968, "learning_rate": 0.00019937574859415843, "loss": 0.7747417449951172, "step": 67510 }, { "epoch": 0.40135290166497256, "grad_norm": 1.63376784324646, "learning_rate": 0.00019937501649617417, "loss": 0.6795441150665283, "step": 67520 }, { "epoch": 0.401412343741641, "grad_norm": 1.8988522291183472, "learning_rate": 0.00019937428397064904, "loss": 0.6698089122772217, "step": 67530 }, { "epoch": 0.40147178581830933, "grad_norm": 1.559913992881775, "learning_rate": 0.0001993735510175866, "loss": 0.67068510055542, "step": 67540 }, { "epoch": 0.40153122789497775, "grad_norm": 2.206293821334839, "learning_rate": 0.00019937281763699025, "loss": 0.7023167610168457, "step": 67550 }, { "epoch": 0.4015906699716461, "grad_norm": 1.5632708072662354, "learning_rate": 0.0001993720838288636, "loss": 0.7049321174621582, "step": 67560 }, { "epoch": 0.4016501120483145, "grad_norm": 1.869079351425171, "learning_rate": 0.00019937134959321, "loss": 0.6963753700256348, "step": 67570 }, { "epoch": 0.40170955412498294, "grad_norm": 1.697129249572754, "learning_rate": 0.00019937061493003317, "loss": 0.6327366828918457, "step": 67580 }, { "epoch": 0.4017689962016513, "grad_norm": 1.6157593727111816, "learning_rate": 0.0001993698798393365, "loss": 0.6981550216674804, "step": 67590 }, { "epoch": 0.4018284382783197, "grad_norm": 1.7146497964859009, "learning_rate": 0.00019936914432112351, "loss": 0.7122174739837647, "step": 67600 }, { "epoch": 0.40188788035498807, "grad_norm": 1.7504690885543823, "learning_rate": 0.00019936840837539777, "loss": 0.6572826385498047, "step": 67610 }, { "epoch": 0.4019473224316565, "grad_norm": 1.466226577758789, "learning_rate": 0.00019936767200216278, "loss": 0.6798311233520508, "step": 67620 }, { "epoch": 0.40200676450832484, "grad_norm": 1.5230560302734375, "learning_rate": 0.00019936693520142203, "loss": 0.6512587547302247, "step": 67630 }, { "epoch": 0.40206620658499326, "grad_norm": 1.562406301498413, "learning_rate": 0.00019936619797317906, "loss": 0.7007927894592285, "step": 67640 }, { "epoch": 0.4021256486616616, "grad_norm": 1.7559891939163208, "learning_rate": 0.00019936546031743742, "loss": 0.674866008758545, "step": 67650 }, { "epoch": 0.40218509073833003, "grad_norm": 1.5674138069152832, "learning_rate": 0.00019936472223420058, "loss": 0.6759099960327148, "step": 67660 }, { "epoch": 0.40224453281499845, "grad_norm": 1.6170916557312012, "learning_rate": 0.00019936398372347216, "loss": 0.6909611701965332, "step": 67670 }, { "epoch": 0.4023039748916668, "grad_norm": 1.7217470407485962, "learning_rate": 0.0001993632447852556, "loss": 0.6948366165161133, "step": 67680 }, { "epoch": 0.4023634169683352, "grad_norm": 1.6027191877365112, "learning_rate": 0.00019936250541955454, "loss": 0.6886330604553222, "step": 67690 }, { "epoch": 0.4024228590450036, "grad_norm": 2.0118772983551025, "learning_rate": 0.00019936176562637245, "loss": 0.713712501525879, "step": 67700 }, { "epoch": 0.402482301121672, "grad_norm": 1.872092604637146, "learning_rate": 0.00019936102540571283, "loss": 0.6539149284362793, "step": 67710 }, { "epoch": 0.40254174319834035, "grad_norm": 1.947218656539917, "learning_rate": 0.00019936028475757932, "loss": 0.6697634696960449, "step": 67720 }, { "epoch": 0.40260118527500877, "grad_norm": 1.5769380331039429, "learning_rate": 0.0001993595436819754, "loss": 0.7041633605957032, "step": 67730 }, { "epoch": 0.4026606273516772, "grad_norm": 1.898738145828247, "learning_rate": 0.00019935880217890459, "loss": 0.6687769889831543, "step": 67740 }, { "epoch": 0.40272006942834554, "grad_norm": 1.6566054821014404, "learning_rate": 0.0001993580602483705, "loss": 0.6249815940856933, "step": 67750 }, { "epoch": 0.40277951150501395, "grad_norm": 2.0628082752227783, "learning_rate": 0.00019935731789037667, "loss": 0.7385626792907715, "step": 67760 }, { "epoch": 0.4028389535816823, "grad_norm": 1.9659701585769653, "learning_rate": 0.00019935657510492658, "loss": 0.6709165573120117, "step": 67770 }, { "epoch": 0.4028983956583507, "grad_norm": 2.077890157699585, "learning_rate": 0.0001993558318920239, "loss": 0.6442866325378418, "step": 67780 }, { "epoch": 0.4029578377350191, "grad_norm": 2.047388792037964, "learning_rate": 0.00019935508825167207, "loss": 0.699045467376709, "step": 67790 }, { "epoch": 0.4030172798116875, "grad_norm": 2.2665183544158936, "learning_rate": 0.00019935434418387474, "loss": 0.6840810775756836, "step": 67800 }, { "epoch": 0.4030767218883559, "grad_norm": 1.7287341356277466, "learning_rate": 0.0001993535996886354, "loss": 0.7090095520019531, "step": 67810 }, { "epoch": 0.4031361639650243, "grad_norm": 1.786972999572754, "learning_rate": 0.00019935285476595767, "loss": 0.7504543781280517, "step": 67820 }, { "epoch": 0.4031956060416927, "grad_norm": 1.775547981262207, "learning_rate": 0.00019935210941584506, "loss": 0.6829162120819092, "step": 67830 }, { "epoch": 0.40325504811836105, "grad_norm": 1.6265863180160522, "learning_rate": 0.00019935136363830115, "loss": 0.743585205078125, "step": 67840 }, { "epoch": 0.40331449019502946, "grad_norm": 1.6686277389526367, "learning_rate": 0.00019935061743332953, "loss": 0.6947502136230469, "step": 67850 }, { "epoch": 0.4033739322716978, "grad_norm": 1.6448971033096313, "learning_rate": 0.00019934987080093378, "loss": 0.693599796295166, "step": 67860 }, { "epoch": 0.40343337434836624, "grad_norm": 2.0724804401397705, "learning_rate": 0.0001993491237411174, "loss": 0.6857847690582275, "step": 67870 }, { "epoch": 0.40349281642503465, "grad_norm": 1.6524769067764282, "learning_rate": 0.00019934837625388405, "loss": 0.7402688026428222, "step": 67880 }, { "epoch": 0.403552258501703, "grad_norm": 2.3477213382720947, "learning_rate": 0.00019934762833923725, "loss": 0.6902489185333252, "step": 67890 }, { "epoch": 0.4036117005783714, "grad_norm": 2.0704855918884277, "learning_rate": 0.0001993468799971806, "loss": 0.7104395389556885, "step": 67900 }, { "epoch": 0.4036711426550398, "grad_norm": 2.1775083541870117, "learning_rate": 0.00019934613122771767, "loss": 0.7117015838623046, "step": 67910 }, { "epoch": 0.4037305847317082, "grad_norm": 1.5114169120788574, "learning_rate": 0.00019934538203085204, "loss": 0.6827725410461426, "step": 67920 }, { "epoch": 0.40379002680837656, "grad_norm": 1.5874730348587036, "learning_rate": 0.0001993446324065873, "loss": 0.6960035800933838, "step": 67930 }, { "epoch": 0.40384946888504497, "grad_norm": 1.3649238348007202, "learning_rate": 0.00019934388235492707, "loss": 0.6507594108581543, "step": 67940 }, { "epoch": 0.4039089109617134, "grad_norm": 1.6019542217254639, "learning_rate": 0.00019934313187587488, "loss": 0.705439567565918, "step": 67950 }, { "epoch": 0.40396835303838174, "grad_norm": 1.5748260021209717, "learning_rate": 0.00019934238096943433, "loss": 0.6759421348571777, "step": 67960 }, { "epoch": 0.40402779511505016, "grad_norm": 1.8359222412109375, "learning_rate": 0.00019934162963560905, "loss": 0.6750613689422608, "step": 67970 }, { "epoch": 0.4040872371917185, "grad_norm": 1.9786375761032104, "learning_rate": 0.00019934087787440262, "loss": 0.6760032176971436, "step": 67980 }, { "epoch": 0.40414667926838693, "grad_norm": 1.4883140325546265, "learning_rate": 0.0001993401256858186, "loss": 0.6989823341369629, "step": 67990 }, { "epoch": 0.4042061213450553, "grad_norm": 1.4224133491516113, "learning_rate": 0.00019933937306986063, "loss": 0.6839905738830566, "step": 68000 }, { "epoch": 0.4042655634217237, "grad_norm": 2.0237460136413574, "learning_rate": 0.0001993386200265323, "loss": 0.6573441505432129, "step": 68010 }, { "epoch": 0.40432500549839206, "grad_norm": 1.5477091073989868, "learning_rate": 0.00019933786655583718, "loss": 0.7046961784362793, "step": 68020 }, { "epoch": 0.4043844475750605, "grad_norm": 1.9673954248428345, "learning_rate": 0.00019933711265777894, "loss": 0.6100283622741699, "step": 68030 }, { "epoch": 0.4044438896517289, "grad_norm": 1.076795220375061, "learning_rate": 0.00019933635833236112, "loss": 0.6258794784545898, "step": 68040 }, { "epoch": 0.40450333172839725, "grad_norm": 2.068842649459839, "learning_rate": 0.0001993356035795874, "loss": 0.6077112197875977, "step": 68050 }, { "epoch": 0.40456277380506567, "grad_norm": 2.228977680206299, "learning_rate": 0.0001993348483994613, "loss": 0.6584255218505859, "step": 68060 }, { "epoch": 0.404622215881734, "grad_norm": 1.8674181699752808, "learning_rate": 0.00019933409279198648, "loss": 0.6727166652679444, "step": 68070 }, { "epoch": 0.40468165795840244, "grad_norm": 1.870297908782959, "learning_rate": 0.00019933333675716658, "loss": 0.6814001560211181, "step": 68080 }, { "epoch": 0.4047411000350708, "grad_norm": 1.6524094343185425, "learning_rate": 0.0001993325802950052, "loss": 0.7840973854064941, "step": 68090 }, { "epoch": 0.4048005421117392, "grad_norm": 1.8236528635025024, "learning_rate": 0.0001993318234055059, "loss": 0.7485058307647705, "step": 68100 }, { "epoch": 0.40485998418840763, "grad_norm": 1.6905946731567383, "learning_rate": 0.00019933106608867242, "loss": 0.672696876525879, "step": 68110 }, { "epoch": 0.404919426265076, "grad_norm": 1.5895636081695557, "learning_rate": 0.00019933030834450824, "loss": 0.7012598991394043, "step": 68120 }, { "epoch": 0.4049788683417444, "grad_norm": 1.4602683782577515, "learning_rate": 0.00019932955017301713, "loss": 0.7144523143768311, "step": 68130 }, { "epoch": 0.40503831041841276, "grad_norm": 1.5204957723617554, "learning_rate": 0.00019932879157420264, "loss": 0.681260061264038, "step": 68140 }, { "epoch": 0.4050977524950812, "grad_norm": 1.5943289995193481, "learning_rate": 0.00019932803254806835, "loss": 0.704231071472168, "step": 68150 }, { "epoch": 0.40515719457174953, "grad_norm": 1.859476089477539, "learning_rate": 0.00019932727309461795, "loss": 0.6827305793762207, "step": 68160 }, { "epoch": 0.40521663664841795, "grad_norm": 1.9628137350082397, "learning_rate": 0.00019932651321385512, "loss": 0.7074186325073242, "step": 68170 }, { "epoch": 0.40527607872508636, "grad_norm": 1.490701675415039, "learning_rate": 0.00019932575290578338, "loss": 0.7124980926513672, "step": 68180 }, { "epoch": 0.4053355208017547, "grad_norm": 2.0107526779174805, "learning_rate": 0.0001993249921704065, "loss": 0.7296325206756592, "step": 68190 }, { "epoch": 0.40539496287842314, "grad_norm": 1.5763689279556274, "learning_rate": 0.00019932423100772802, "loss": 0.7591276168823242, "step": 68200 }, { "epoch": 0.4054544049550915, "grad_norm": 1.5030804872512817, "learning_rate": 0.00019932346941775158, "loss": 0.7454526424407959, "step": 68210 }, { "epoch": 0.4055138470317599, "grad_norm": 1.9271570444107056, "learning_rate": 0.00019932270740048087, "loss": 0.7116974353790283, "step": 68220 }, { "epoch": 0.40557328910842827, "grad_norm": 1.9788262844085693, "learning_rate": 0.00019932194495591953, "loss": 0.667030668258667, "step": 68230 }, { "epoch": 0.4056327311850967, "grad_norm": 1.4311589002609253, "learning_rate": 0.00019932118208407118, "loss": 0.6849053382873536, "step": 68240 }, { "epoch": 0.4056921732617651, "grad_norm": 1.6088742017745972, "learning_rate": 0.0001993204187849395, "loss": 0.6680580139160156, "step": 68250 }, { "epoch": 0.40575161533843346, "grad_norm": 1.3553022146224976, "learning_rate": 0.0001993196550585281, "loss": 0.6048122406005859, "step": 68260 }, { "epoch": 0.4058110574151019, "grad_norm": 1.7291184663772583, "learning_rate": 0.00019931889090484074, "loss": 0.724129581451416, "step": 68270 }, { "epoch": 0.40587049949177023, "grad_norm": 1.5814989805221558, "learning_rate": 0.00019931812632388089, "loss": 0.6792407035827637, "step": 68280 }, { "epoch": 0.40592994156843865, "grad_norm": 1.575229525566101, "learning_rate": 0.00019931736131565238, "loss": 0.6732130527496338, "step": 68290 }, { "epoch": 0.405989383645107, "grad_norm": 1.6840769052505493, "learning_rate": 0.00019931659588015877, "loss": 0.6854591369628906, "step": 68300 }, { "epoch": 0.4060488257217754, "grad_norm": 1.9244942665100098, "learning_rate": 0.00019931583001740378, "loss": 0.6345966815948486, "step": 68310 }, { "epoch": 0.40610826779844383, "grad_norm": 1.7709935903549194, "learning_rate": 0.00019931506372739102, "loss": 0.6793361663818359, "step": 68320 }, { "epoch": 0.4061677098751122, "grad_norm": 1.5571264028549194, "learning_rate": 0.0001993142970101242, "loss": 0.6802309989929199, "step": 68330 }, { "epoch": 0.4062271519517806, "grad_norm": 1.4684206247329712, "learning_rate": 0.000199313529865607, "loss": 0.6251847267150878, "step": 68340 }, { "epoch": 0.40628659402844897, "grad_norm": 1.8392356634140015, "learning_rate": 0.00019931276229384303, "loss": 0.7233383178710937, "step": 68350 }, { "epoch": 0.4063460361051174, "grad_norm": 2.060814142227173, "learning_rate": 0.00019931199429483598, "loss": 0.7067643165588379, "step": 68360 }, { "epoch": 0.40640547818178574, "grad_norm": 1.8576385974884033, "learning_rate": 0.00019931122586858957, "loss": 0.7050436973571778, "step": 68370 }, { "epoch": 0.40646492025845415, "grad_norm": 1.3877296447753906, "learning_rate": 0.00019931045701510739, "loss": 0.7465417861938477, "step": 68380 }, { "epoch": 0.4065243623351225, "grad_norm": 1.716907024383545, "learning_rate": 0.00019930968773439322, "loss": 0.6929431915283203, "step": 68390 }, { "epoch": 0.40658380441179093, "grad_norm": 1.5971075296401978, "learning_rate": 0.00019930891802645066, "loss": 0.7504317283630371, "step": 68400 }, { "epoch": 0.40664324648845934, "grad_norm": 1.7744636535644531, "learning_rate": 0.00019930814789128346, "loss": 0.7104533195495606, "step": 68410 }, { "epoch": 0.4067026885651277, "grad_norm": 1.9254224300384521, "learning_rate": 0.00019930737732889523, "loss": 0.7009706020355224, "step": 68420 }, { "epoch": 0.4067621306417961, "grad_norm": 1.5561740398406982, "learning_rate": 0.00019930660633928974, "loss": 0.6803793907165527, "step": 68430 }, { "epoch": 0.4068215727184645, "grad_norm": 1.5217225551605225, "learning_rate": 0.00019930583492247056, "loss": 0.6233882427215576, "step": 68440 }, { "epoch": 0.4068810147951329, "grad_norm": 1.7367873191833496, "learning_rate": 0.0001993050630784415, "loss": 0.6788017749786377, "step": 68450 }, { "epoch": 0.40694045687180125, "grad_norm": 2.000213623046875, "learning_rate": 0.0001993042908072062, "loss": 0.7106916904449463, "step": 68460 }, { "epoch": 0.40699989894846966, "grad_norm": 1.2613095045089722, "learning_rate": 0.00019930351810876836, "loss": 0.7146707534790039, "step": 68470 }, { "epoch": 0.4070593410251381, "grad_norm": 1.9926031827926636, "learning_rate": 0.00019930274498313166, "loss": 0.6722444057464599, "step": 68480 }, { "epoch": 0.40711878310180644, "grad_norm": 1.6743351221084595, "learning_rate": 0.00019930197143029982, "loss": 0.6826341152191162, "step": 68490 }, { "epoch": 0.40717822517847485, "grad_norm": 1.9268549680709839, "learning_rate": 0.00019930119745027651, "loss": 0.673072099685669, "step": 68500 }, { "epoch": 0.4072376672551432, "grad_norm": 1.865322470664978, "learning_rate": 0.0001993004230430655, "loss": 0.6605243682861328, "step": 68510 }, { "epoch": 0.4072971093318116, "grad_norm": 2.0112781524658203, "learning_rate": 0.00019929964820867042, "loss": 0.6705222129821777, "step": 68520 }, { "epoch": 0.40735655140848, "grad_norm": 1.6013649702072144, "learning_rate": 0.00019929887294709502, "loss": 0.7358140468597412, "step": 68530 }, { "epoch": 0.4074159934851484, "grad_norm": 1.903947353363037, "learning_rate": 0.000199298097258343, "loss": 0.6431691169738769, "step": 68540 }, { "epoch": 0.4074754355618168, "grad_norm": 1.4877623319625854, "learning_rate": 0.00019929732114241802, "loss": 0.6698770523071289, "step": 68550 }, { "epoch": 0.40753487763848517, "grad_norm": 1.5577647686004639, "learning_rate": 0.00019929654459932387, "loss": 0.6246487140655518, "step": 68560 }, { "epoch": 0.4075943197151536, "grad_norm": 1.6965744495391846, "learning_rate": 0.00019929576762906423, "loss": 0.7502890586853027, "step": 68570 }, { "epoch": 0.40765376179182194, "grad_norm": 1.5601277351379395, "learning_rate": 0.0001992949902316428, "loss": 0.6583743095397949, "step": 68580 }, { "epoch": 0.40771320386849036, "grad_norm": 1.894752025604248, "learning_rate": 0.00019929421240706338, "loss": 0.6622007369995118, "step": 68590 }, { "epoch": 0.4077726459451587, "grad_norm": 1.8530911207199097, "learning_rate": 0.00019929343415532957, "loss": 0.7066480159759522, "step": 68600 }, { "epoch": 0.40783208802182713, "grad_norm": 1.4423645734786987, "learning_rate": 0.0001992926554764452, "loss": 0.6917802810668945, "step": 68610 }, { "epoch": 0.40789153009849555, "grad_norm": 2.1433236598968506, "learning_rate": 0.00019929187637041391, "loss": 0.6965706825256348, "step": 68620 }, { "epoch": 0.4079509721751639, "grad_norm": 1.6225500106811523, "learning_rate": 0.00019929109683723947, "loss": 0.6629937171936036, "step": 68630 }, { "epoch": 0.4080104142518323, "grad_norm": 1.9431897401809692, "learning_rate": 0.0001992903168769256, "loss": 0.6796904087066651, "step": 68640 }, { "epoch": 0.4080698563285007, "grad_norm": 1.5779763460159302, "learning_rate": 0.0001992895364894761, "loss": 0.6360104084014893, "step": 68650 }, { "epoch": 0.4081292984051691, "grad_norm": 1.7556465864181519, "learning_rate": 0.00019928875567489456, "loss": 0.6671528816223145, "step": 68660 }, { "epoch": 0.40818874048183745, "grad_norm": 1.811055064201355, "learning_rate": 0.00019928797443318478, "loss": 0.6835412979125977, "step": 68670 }, { "epoch": 0.40824818255850587, "grad_norm": 2.1065444946289062, "learning_rate": 0.00019928719276435057, "loss": 0.6476019382476806, "step": 68680 }, { "epoch": 0.4083076246351743, "grad_norm": 1.7805579900741577, "learning_rate": 0.00019928641066839557, "loss": 0.695869255065918, "step": 68690 }, { "epoch": 0.40836706671184264, "grad_norm": 2.0926623344421387, "learning_rate": 0.0001992856281453236, "loss": 0.6722957611083984, "step": 68700 }, { "epoch": 0.40842650878851106, "grad_norm": 1.5753825902938843, "learning_rate": 0.0001992848451951383, "loss": 0.6953318595886231, "step": 68710 }, { "epoch": 0.4084859508651794, "grad_norm": 1.7269684076309204, "learning_rate": 0.00019928406181784353, "loss": 0.684386157989502, "step": 68720 }, { "epoch": 0.40854539294184783, "grad_norm": 2.623112678527832, "learning_rate": 0.00019928327801344296, "loss": 0.7226910591125488, "step": 68730 }, { "epoch": 0.4086048350185162, "grad_norm": 1.7689385414123535, "learning_rate": 0.0001992824937819404, "loss": 0.6783529758453369, "step": 68740 }, { "epoch": 0.4086642770951846, "grad_norm": 1.6771045923233032, "learning_rate": 0.00019928170912333955, "loss": 0.6800647735595703, "step": 68750 }, { "epoch": 0.40872371917185296, "grad_norm": 1.7946586608886719, "learning_rate": 0.00019928092403764417, "loss": 0.675541353225708, "step": 68760 }, { "epoch": 0.4087831612485214, "grad_norm": 1.473144769668579, "learning_rate": 0.00019928013852485804, "loss": 0.6432461261749267, "step": 68770 }, { "epoch": 0.4088426033251898, "grad_norm": 2.6048338413238525, "learning_rate": 0.0001992793525849849, "loss": 0.6857377052307129, "step": 68780 }, { "epoch": 0.40890204540185815, "grad_norm": 2.167280912399292, "learning_rate": 0.00019927856621802852, "loss": 0.7077935218811036, "step": 68790 }, { "epoch": 0.40896148747852656, "grad_norm": 1.5420948266983032, "learning_rate": 0.00019927777942399267, "loss": 0.6638960838317871, "step": 68800 }, { "epoch": 0.4090209295551949, "grad_norm": 1.7122942209243774, "learning_rate": 0.00019927699220288105, "loss": 0.7059762954711915, "step": 68810 }, { "epoch": 0.40908037163186334, "grad_norm": 1.9155315160751343, "learning_rate": 0.00019927620455469753, "loss": 0.7090269088745117, "step": 68820 }, { "epoch": 0.4091398137085317, "grad_norm": 1.50751531124115, "learning_rate": 0.0001992754164794458, "loss": 0.6423211097717285, "step": 68830 }, { "epoch": 0.4091992557852001, "grad_norm": 1.9922078847885132, "learning_rate": 0.00019927462797712962, "loss": 0.7041263580322266, "step": 68840 }, { "epoch": 0.4092586978618685, "grad_norm": 1.7321069240570068, "learning_rate": 0.00019927383904775283, "loss": 0.7401261806488038, "step": 68850 }, { "epoch": 0.4093181399385369, "grad_norm": 1.6030628681182861, "learning_rate": 0.0001992730496913192, "loss": 0.7071198463439942, "step": 68860 }, { "epoch": 0.4093775820152053, "grad_norm": 1.8777357339859009, "learning_rate": 0.0001992722599078324, "loss": 0.7124814033508301, "step": 68870 }, { "epoch": 0.40943702409187366, "grad_norm": 2.084402084350586, "learning_rate": 0.00019927146969729633, "loss": 0.6864894390106201, "step": 68880 }, { "epoch": 0.4094964661685421, "grad_norm": 1.626580834388733, "learning_rate": 0.00019927067905971472, "loss": 0.6543234825134278, "step": 68890 }, { "epoch": 0.40955590824521043, "grad_norm": 1.837965488433838, "learning_rate": 0.00019926988799509138, "loss": 0.6256250381469727, "step": 68900 }, { "epoch": 0.40961535032187885, "grad_norm": 2.026843309402466, "learning_rate": 0.00019926909650343002, "loss": 0.7417030334472656, "step": 68910 }, { "epoch": 0.40967479239854726, "grad_norm": 2.0283849239349365, "learning_rate": 0.0001992683045847345, "loss": 0.7245398044586182, "step": 68920 }, { "epoch": 0.4097342344752156, "grad_norm": 1.8569931983947754, "learning_rate": 0.00019926751223900858, "loss": 0.6763035774230957, "step": 68930 }, { "epoch": 0.40979367655188403, "grad_norm": 1.9456769227981567, "learning_rate": 0.00019926671946625605, "loss": 0.6206477165222168, "step": 68940 }, { "epoch": 0.4098531186285524, "grad_norm": 1.7099277973175049, "learning_rate": 0.0001992659262664807, "loss": 0.728476095199585, "step": 68950 }, { "epoch": 0.4099125607052208, "grad_norm": 1.9479162693023682, "learning_rate": 0.00019926513263968633, "loss": 0.7322992324829102, "step": 68960 }, { "epoch": 0.40997200278188917, "grad_norm": 1.5647335052490234, "learning_rate": 0.00019926433858587678, "loss": 0.6773448944091797, "step": 68970 }, { "epoch": 0.4100314448585576, "grad_norm": 1.8169382810592651, "learning_rate": 0.00019926354410505578, "loss": 0.6577003002166748, "step": 68980 }, { "epoch": 0.410090886935226, "grad_norm": 1.5658100843429565, "learning_rate": 0.00019926274919722714, "loss": 0.654087495803833, "step": 68990 }, { "epoch": 0.41015032901189435, "grad_norm": 1.9886976480484009, "learning_rate": 0.0001992619538623947, "loss": 0.7588970184326171, "step": 69000 }, { "epoch": 0.41020977108856277, "grad_norm": 2.5231659412384033, "learning_rate": 0.00019926115810056224, "loss": 0.6955338001251221, "step": 69010 }, { "epoch": 0.41026921316523113, "grad_norm": 1.4559438228607178, "learning_rate": 0.00019926036191173356, "loss": 0.6727645874023438, "step": 69020 }, { "epoch": 0.41032865524189954, "grad_norm": 1.9191828966140747, "learning_rate": 0.0001992595652959125, "loss": 0.6866119384765625, "step": 69030 }, { "epoch": 0.4103880973185679, "grad_norm": 1.4280883073806763, "learning_rate": 0.00019925876825310283, "loss": 0.6952939033508301, "step": 69040 }, { "epoch": 0.4104475393952363, "grad_norm": 1.7245632410049438, "learning_rate": 0.0001992579707833084, "loss": 0.6710461616516114, "step": 69050 }, { "epoch": 0.4105069814719047, "grad_norm": 1.6513758897781372, "learning_rate": 0.000199257172886533, "loss": 0.7065372467041016, "step": 69060 }, { "epoch": 0.4105664235485731, "grad_norm": 1.5668550729751587, "learning_rate": 0.00019925637456278043, "loss": 0.6910633563995361, "step": 69070 }, { "epoch": 0.4106258656252415, "grad_norm": 1.8348816633224487, "learning_rate": 0.00019925557581205457, "loss": 0.646995735168457, "step": 69080 }, { "epoch": 0.41068530770190986, "grad_norm": 1.5710911750793457, "learning_rate": 0.0001992547766343592, "loss": 0.699926233291626, "step": 69090 }, { "epoch": 0.4107447497785783, "grad_norm": 1.9139968156814575, "learning_rate": 0.00019925397702969812, "loss": 0.6873764038085938, "step": 69100 }, { "epoch": 0.41080419185524664, "grad_norm": 1.779632806777954, "learning_rate": 0.0001992531769980752, "loss": 0.6992101669311523, "step": 69110 }, { "epoch": 0.41086363393191505, "grad_norm": 1.586076259613037, "learning_rate": 0.00019925237653949424, "loss": 0.6927565574645996, "step": 69120 }, { "epoch": 0.4109230760085834, "grad_norm": 1.9261761903762817, "learning_rate": 0.00019925157565395908, "loss": 0.7684125423431396, "step": 69130 }, { "epoch": 0.4109825180852518, "grad_norm": 1.6881797313690186, "learning_rate": 0.00019925077434147356, "loss": 0.7443177223205566, "step": 69140 }, { "epoch": 0.41104196016192024, "grad_norm": 1.8731857538223267, "learning_rate": 0.0001992499726020415, "loss": 0.7322818279266358, "step": 69150 }, { "epoch": 0.4111014022385886, "grad_norm": 1.2832006216049194, "learning_rate": 0.00019924917043566675, "loss": 0.7442850112915039, "step": 69160 }, { "epoch": 0.411160844315257, "grad_norm": 1.7827945947647095, "learning_rate": 0.00019924836784235314, "loss": 0.6947246551513672, "step": 69170 }, { "epoch": 0.41122028639192537, "grad_norm": 1.4562209844589233, "learning_rate": 0.00019924756482210445, "loss": 0.7278169631958008, "step": 69180 }, { "epoch": 0.4112797284685938, "grad_norm": 1.8685837984085083, "learning_rate": 0.00019924676137492465, "loss": 0.7062220573425293, "step": 69190 }, { "epoch": 0.41133917054526214, "grad_norm": 1.9606517553329468, "learning_rate": 0.00019924595750081745, "loss": 0.6979479789733887, "step": 69200 }, { "epoch": 0.41139861262193056, "grad_norm": 2.156679391860962, "learning_rate": 0.0001992451531997868, "loss": 0.7252824783325196, "step": 69210 }, { "epoch": 0.411458054698599, "grad_norm": 1.7617543935775757, "learning_rate": 0.0001992443484718365, "loss": 0.7213976860046387, "step": 69220 }, { "epoch": 0.41151749677526733, "grad_norm": 1.9312121868133545, "learning_rate": 0.00019924354331697034, "loss": 0.752730417251587, "step": 69230 }, { "epoch": 0.41157693885193575, "grad_norm": 1.8807662725448608, "learning_rate": 0.0001992427377351923, "loss": 0.7519011497497559, "step": 69240 }, { "epoch": 0.4116363809286041, "grad_norm": 1.7747738361358643, "learning_rate": 0.00019924193172650613, "loss": 0.6902637958526612, "step": 69250 }, { "epoch": 0.4116958230052725, "grad_norm": 1.4734797477722168, "learning_rate": 0.00019924112529091576, "loss": 0.6863491058349609, "step": 69260 }, { "epoch": 0.4117552650819409, "grad_norm": 1.8237032890319824, "learning_rate": 0.00019924031842842495, "loss": 0.652100944519043, "step": 69270 }, { "epoch": 0.4118147071586093, "grad_norm": 1.7854596376419067, "learning_rate": 0.00019923951113903768, "loss": 0.6912219524383545, "step": 69280 }, { "epoch": 0.4118741492352777, "grad_norm": 1.7681926488876343, "learning_rate": 0.00019923870342275775, "loss": 0.7180964469909668, "step": 69290 }, { "epoch": 0.41193359131194607, "grad_norm": 1.9533274173736572, "learning_rate": 0.000199237895279589, "loss": 0.7322779178619385, "step": 69300 }, { "epoch": 0.4119930333886145, "grad_norm": 1.7463375329971313, "learning_rate": 0.0001992370867095353, "loss": 0.7554691314697266, "step": 69310 }, { "epoch": 0.41205247546528284, "grad_norm": 2.0183064937591553, "learning_rate": 0.0001992362777126006, "loss": 0.6449472904205322, "step": 69320 }, { "epoch": 0.41211191754195126, "grad_norm": 1.707541823387146, "learning_rate": 0.00019923546828878869, "loss": 0.7168548583984375, "step": 69330 }, { "epoch": 0.4121713596186196, "grad_norm": 1.4334467649459839, "learning_rate": 0.00019923465843810348, "loss": 0.7560265541076661, "step": 69340 }, { "epoch": 0.41223080169528803, "grad_norm": 1.8809188604354858, "learning_rate": 0.0001992338481605488, "loss": 0.6733423709869385, "step": 69350 }, { "epoch": 0.41229024377195644, "grad_norm": 1.6305279731750488, "learning_rate": 0.00019923303745612853, "loss": 0.6298681735992432, "step": 69360 }, { "epoch": 0.4123496858486248, "grad_norm": 1.994628667831421, "learning_rate": 0.0001992322263248466, "loss": 0.6543976783752441, "step": 69370 }, { "epoch": 0.4124091279252932, "grad_norm": 1.613100528717041, "learning_rate": 0.00019923141476670684, "loss": 0.6091336250305176, "step": 69380 }, { "epoch": 0.4124685700019616, "grad_norm": 1.4725042581558228, "learning_rate": 0.0001992306027817132, "loss": 0.720966911315918, "step": 69390 }, { "epoch": 0.41252801207863, "grad_norm": 1.5984845161437988, "learning_rate": 0.00019922979036986947, "loss": 0.6951247215270996, "step": 69400 }, { "epoch": 0.41258745415529835, "grad_norm": 1.5385534763336182, "learning_rate": 0.0001992289775311796, "loss": 0.6913926124572753, "step": 69410 }, { "epoch": 0.41264689623196676, "grad_norm": 2.061786651611328, "learning_rate": 0.00019922816426564744, "loss": 0.7248006820678711, "step": 69420 }, { "epoch": 0.4127063383086351, "grad_norm": 1.782856822013855, "learning_rate": 0.00019922735057327693, "loss": 0.7265495300292969, "step": 69430 }, { "epoch": 0.41276578038530354, "grad_norm": 2.1732029914855957, "learning_rate": 0.00019922653645407194, "loss": 0.7593217849731445, "step": 69440 }, { "epoch": 0.41282522246197195, "grad_norm": 1.910408854484558, "learning_rate": 0.0001992257219080363, "loss": 0.6931259155273437, "step": 69450 }, { "epoch": 0.4128846645386403, "grad_norm": 1.6238088607788086, "learning_rate": 0.00019922490693517403, "loss": 0.6815299987792969, "step": 69460 }, { "epoch": 0.4129441066153087, "grad_norm": 1.860592007637024, "learning_rate": 0.00019922409153548895, "loss": 0.715465784072876, "step": 69470 }, { "epoch": 0.4130035486919771, "grad_norm": 1.444488286972046, "learning_rate": 0.00019922327570898497, "loss": 0.6437462329864502, "step": 69480 }, { "epoch": 0.4130629907686455, "grad_norm": 1.849613904953003, "learning_rate": 0.00019922245945566602, "loss": 0.7514683723449707, "step": 69490 }, { "epoch": 0.41312243284531386, "grad_norm": 1.4766124486923218, "learning_rate": 0.00019922164277553594, "loss": 0.7386775970458984, "step": 69500 }, { "epoch": 0.4131818749219823, "grad_norm": 1.6266674995422363, "learning_rate": 0.0001992208256685987, "loss": 0.7070189476013183, "step": 69510 }, { "epoch": 0.4132413169986507, "grad_norm": 1.8609979152679443, "learning_rate": 0.0001992200081348582, "loss": 0.7068861484527588, "step": 69520 }, { "epoch": 0.41330075907531905, "grad_norm": 1.5542432069778442, "learning_rate": 0.00019921919017431831, "loss": 0.6364622116088867, "step": 69530 }, { "epoch": 0.41336020115198746, "grad_norm": 1.821845293045044, "learning_rate": 0.00019921837178698298, "loss": 0.7068791389465332, "step": 69540 }, { "epoch": 0.4134196432286558, "grad_norm": 2.597032308578491, "learning_rate": 0.00019921755297285613, "loss": 0.6261730194091797, "step": 69550 }, { "epoch": 0.41347908530532423, "grad_norm": 1.5354454517364502, "learning_rate": 0.00019921673373194168, "loss": 0.661994457244873, "step": 69560 }, { "epoch": 0.4135385273819926, "grad_norm": 1.9014310836791992, "learning_rate": 0.0001992159140642435, "loss": 0.6737027645111084, "step": 69570 }, { "epoch": 0.413597969458661, "grad_norm": 1.8549538850784302, "learning_rate": 0.00019921509396976554, "loss": 0.7077022075653077, "step": 69580 }, { "epoch": 0.4136574115353294, "grad_norm": 2.2187678813934326, "learning_rate": 0.00019921427344851177, "loss": 0.7427265644073486, "step": 69590 }, { "epoch": 0.4137168536119978, "grad_norm": 1.626852035522461, "learning_rate": 0.000199213452500486, "loss": 0.7337126731872559, "step": 69600 }, { "epoch": 0.4137762956886662, "grad_norm": 1.453894019126892, "learning_rate": 0.00019921263112569225, "loss": 0.686796760559082, "step": 69610 }, { "epoch": 0.41383573776533455, "grad_norm": 1.4203203916549683, "learning_rate": 0.00019921180932413446, "loss": 0.677436351776123, "step": 69620 }, { "epoch": 0.41389517984200297, "grad_norm": 1.9180128574371338, "learning_rate": 0.00019921098709581653, "loss": 0.698056411743164, "step": 69630 }, { "epoch": 0.41395462191867133, "grad_norm": 1.5745199918746948, "learning_rate": 0.00019921016444074237, "loss": 0.6752185821533203, "step": 69640 }, { "epoch": 0.41401406399533974, "grad_norm": 2.0992562770843506, "learning_rate": 0.00019920934135891596, "loss": 0.7185938835144043, "step": 69650 }, { "epoch": 0.41407350607200816, "grad_norm": 1.5982121229171753, "learning_rate": 0.00019920851785034118, "loss": 0.6884510040283203, "step": 69660 }, { "epoch": 0.4141329481486765, "grad_norm": 1.7674672603607178, "learning_rate": 0.00019920769391502203, "loss": 0.779230260848999, "step": 69670 }, { "epoch": 0.41419239022534493, "grad_norm": 1.9781436920166016, "learning_rate": 0.00019920686955296243, "loss": 0.6594128131866455, "step": 69680 }, { "epoch": 0.4142518323020133, "grad_norm": 1.597602128982544, "learning_rate": 0.00019920604476416628, "loss": 0.6491636753082275, "step": 69690 }, { "epoch": 0.4143112743786817, "grad_norm": 2.069404125213623, "learning_rate": 0.0001992052195486376, "loss": 0.7144988536834717, "step": 69700 }, { "epoch": 0.41437071645535006, "grad_norm": 1.5083335638046265, "learning_rate": 0.0001992043939063803, "loss": 0.7275373935699463, "step": 69710 }, { "epoch": 0.4144301585320185, "grad_norm": 1.977080225944519, "learning_rate": 0.00019920356783739834, "loss": 0.6903014183044434, "step": 69720 }, { "epoch": 0.4144896006086869, "grad_norm": 1.836953043937683, "learning_rate": 0.00019920274134169565, "loss": 0.7196494102478027, "step": 69730 }, { "epoch": 0.41454904268535525, "grad_norm": 1.9237440824508667, "learning_rate": 0.00019920191441927617, "loss": 0.707216453552246, "step": 69740 }, { "epoch": 0.41460848476202367, "grad_norm": 1.3368619680404663, "learning_rate": 0.00019920108707014396, "loss": 0.6257566928863525, "step": 69750 }, { "epoch": 0.414667926838692, "grad_norm": 1.9819424152374268, "learning_rate": 0.00019920025929430284, "loss": 0.691632080078125, "step": 69760 }, { "epoch": 0.41472736891536044, "grad_norm": 1.5739177465438843, "learning_rate": 0.00019919943109175683, "loss": 0.6861935615539551, "step": 69770 }, { "epoch": 0.4147868109920288, "grad_norm": 2.2611708641052246, "learning_rate": 0.00019919860246250993, "loss": 0.7218860626220703, "step": 69780 }, { "epoch": 0.4148462530686972, "grad_norm": 1.571146011352539, "learning_rate": 0.00019919777340656603, "loss": 0.7011167526245117, "step": 69790 }, { "epoch": 0.41490569514536557, "grad_norm": 1.5067082643508911, "learning_rate": 0.00019919694392392913, "loss": 0.6765957832336426, "step": 69800 }, { "epoch": 0.414965137222034, "grad_norm": 1.8784594535827637, "learning_rate": 0.00019919611401460321, "loss": 0.6759877681732178, "step": 69810 }, { "epoch": 0.4150245792987024, "grad_norm": 2.3088114261627197, "learning_rate": 0.00019919528367859225, "loss": 0.7158492565155029, "step": 69820 }, { "epoch": 0.41508402137537076, "grad_norm": 1.6091408729553223, "learning_rate": 0.00019919445291590018, "loss": 0.7388017177581787, "step": 69830 }, { "epoch": 0.4151434634520392, "grad_norm": 1.6480729579925537, "learning_rate": 0.000199193621726531, "loss": 0.6438721656799317, "step": 69840 }, { "epoch": 0.41520290552870753, "grad_norm": 1.5768033266067505, "learning_rate": 0.00019919279011048865, "loss": 0.6992629528045654, "step": 69850 }, { "epoch": 0.41526234760537595, "grad_norm": 1.4675995111465454, "learning_rate": 0.00019919195806777722, "loss": 0.6309235572814942, "step": 69860 }, { "epoch": 0.4153217896820443, "grad_norm": 1.4758586883544922, "learning_rate": 0.00019919112559840053, "loss": 0.6643165588378906, "step": 69870 }, { "epoch": 0.4153812317587127, "grad_norm": 1.411458134651184, "learning_rate": 0.0001991902927023627, "loss": 0.688874626159668, "step": 69880 }, { "epoch": 0.41544067383538114, "grad_norm": 2.026071310043335, "learning_rate": 0.00019918945937966764, "loss": 0.7296799659729004, "step": 69890 }, { "epoch": 0.4155001159120495, "grad_norm": 1.7130030393600464, "learning_rate": 0.00019918862563031935, "loss": 0.6842130184173584, "step": 69900 }, { "epoch": 0.4155595579887179, "grad_norm": 1.4669190645217896, "learning_rate": 0.00019918779145432181, "loss": 0.7140884876251221, "step": 69910 }, { "epoch": 0.41561900006538627, "grad_norm": 1.8337557315826416, "learning_rate": 0.00019918695685167904, "loss": 0.6890271186828614, "step": 69920 }, { "epoch": 0.4156784421420547, "grad_norm": 1.4950889348983765, "learning_rate": 0.000199186121822395, "loss": 0.5965609550476074, "step": 69930 }, { "epoch": 0.41573788421872304, "grad_norm": 1.4365081787109375, "learning_rate": 0.00019918528636647372, "loss": 0.7110811233520508, "step": 69940 }, { "epoch": 0.41579732629539146, "grad_norm": 1.7537201642990112, "learning_rate": 0.00019918445048391917, "loss": 0.6952078819274903, "step": 69950 }, { "epoch": 0.41585676837205987, "grad_norm": 1.5391113758087158, "learning_rate": 0.00019918361417473534, "loss": 0.700588321685791, "step": 69960 }, { "epoch": 0.41591621044872823, "grad_norm": 1.7209100723266602, "learning_rate": 0.00019918277743892626, "loss": 0.7165402412414551, "step": 69970 }, { "epoch": 0.41597565252539664, "grad_norm": 1.725449800491333, "learning_rate": 0.0001991819402764959, "loss": 0.7615751266479492, "step": 69980 }, { "epoch": 0.416035094602065, "grad_norm": 1.8396941423416138, "learning_rate": 0.0001991811026874483, "loss": 0.7008355140686036, "step": 69990 }, { "epoch": 0.4160945366787334, "grad_norm": 1.3878422975540161, "learning_rate": 0.00019918026467178744, "loss": 0.621880292892456, "step": 70000 }, { "epoch": 0.4161539787554018, "grad_norm": 1.5555552244186401, "learning_rate": 0.00019917942622951735, "loss": 0.6787976741790771, "step": 70010 }, { "epoch": 0.4162134208320702, "grad_norm": 1.695159912109375, "learning_rate": 0.00019917858736064203, "loss": 0.6247465133666992, "step": 70020 }, { "epoch": 0.4162728629087386, "grad_norm": 1.4522250890731812, "learning_rate": 0.00019917774806516548, "loss": 0.6728908538818359, "step": 70030 }, { "epoch": 0.41633230498540696, "grad_norm": 1.524418592453003, "learning_rate": 0.00019917690834309176, "loss": 0.6835016250610352, "step": 70040 }, { "epoch": 0.4163917470620754, "grad_norm": 1.922700047492981, "learning_rate": 0.0001991760681944248, "loss": 0.7068465232849122, "step": 70050 }, { "epoch": 0.41645118913874374, "grad_norm": 1.61784827709198, "learning_rate": 0.00019917522761916872, "loss": 0.6543037414550781, "step": 70060 }, { "epoch": 0.41651063121541215, "grad_norm": 1.5761786699295044, "learning_rate": 0.00019917438661732747, "loss": 0.6693753719329834, "step": 70070 }, { "epoch": 0.4165700732920805, "grad_norm": 1.846144199371338, "learning_rate": 0.0001991735451889051, "loss": 0.6437677860260009, "step": 70080 }, { "epoch": 0.4166295153687489, "grad_norm": 2.019867420196533, "learning_rate": 0.0001991727033339056, "loss": 0.6923163414001465, "step": 70090 }, { "epoch": 0.41668895744541734, "grad_norm": 1.64949631690979, "learning_rate": 0.0001991718610523331, "loss": 0.7091480255126953, "step": 70100 }, { "epoch": 0.4167483995220857, "grad_norm": 1.3515260219573975, "learning_rate": 0.0001991710183441915, "loss": 0.6578986167907714, "step": 70110 }, { "epoch": 0.4168078415987541, "grad_norm": 1.6626218557357788, "learning_rate": 0.0001991701752094849, "loss": 0.7004599094390869, "step": 70120 }, { "epoch": 0.4168672836754225, "grad_norm": 1.3019341230392456, "learning_rate": 0.00019916933164821734, "loss": 0.647423267364502, "step": 70130 }, { "epoch": 0.4169267257520909, "grad_norm": 1.9063246250152588, "learning_rate": 0.0001991684876603928, "loss": 0.7309110641479493, "step": 70140 }, { "epoch": 0.41698616782875925, "grad_norm": 1.460684895515442, "learning_rate": 0.0001991676432460154, "loss": 0.6858298778533936, "step": 70150 }, { "epoch": 0.41704560990542766, "grad_norm": 1.92473566532135, "learning_rate": 0.00019916679840508914, "loss": 0.7169441699981689, "step": 70160 }, { "epoch": 0.417105051982096, "grad_norm": 1.4103320837020874, "learning_rate": 0.00019916595313761802, "loss": 0.6309376716613769, "step": 70170 }, { "epoch": 0.41716449405876443, "grad_norm": 1.6680041551589966, "learning_rate": 0.00019916510744360616, "loss": 0.6818570613861084, "step": 70180 }, { "epoch": 0.41722393613543285, "grad_norm": 2.01633358001709, "learning_rate": 0.00019916426132305753, "loss": 0.6866499900817871, "step": 70190 }, { "epoch": 0.4172833782121012, "grad_norm": 1.9759554862976074, "learning_rate": 0.0001991634147759762, "loss": 0.7129559516906738, "step": 70200 }, { "epoch": 0.4173428202887696, "grad_norm": 1.8342342376708984, "learning_rate": 0.00019916256780236628, "loss": 0.6503175258636474, "step": 70210 }, { "epoch": 0.417402262365438, "grad_norm": 1.8489817380905151, "learning_rate": 0.00019916172040223174, "loss": 0.6892032623291016, "step": 70220 }, { "epoch": 0.4174617044421064, "grad_norm": 1.9215072393417358, "learning_rate": 0.0001991608725755767, "loss": 0.7020468711853027, "step": 70230 }, { "epoch": 0.41752114651877476, "grad_norm": 1.2578891515731812, "learning_rate": 0.00019916002432240516, "loss": 0.6255395889282227, "step": 70240 }, { "epoch": 0.41758058859544317, "grad_norm": 1.6102489233016968, "learning_rate": 0.0001991591756427212, "loss": 0.70614595413208, "step": 70250 }, { "epoch": 0.4176400306721116, "grad_norm": 1.9021555185317993, "learning_rate": 0.0001991583265365289, "loss": 0.6797257423400879, "step": 70260 }, { "epoch": 0.41769947274877994, "grad_norm": 1.5368069410324097, "learning_rate": 0.00019915747700383228, "loss": 0.6169323921203613, "step": 70270 }, { "epoch": 0.41775891482544836, "grad_norm": 1.8092288970947266, "learning_rate": 0.00019915662704463543, "loss": 0.6812646865844727, "step": 70280 }, { "epoch": 0.4178183569021167, "grad_norm": 1.7868496179580688, "learning_rate": 0.00019915577665894244, "loss": 0.7191277980804444, "step": 70290 }, { "epoch": 0.41787779897878513, "grad_norm": 2.3514769077301025, "learning_rate": 0.00019915492584675733, "loss": 0.7153270721435547, "step": 70300 }, { "epoch": 0.4179372410554535, "grad_norm": 1.6071381568908691, "learning_rate": 0.00019915407460808417, "loss": 0.7134456634521484, "step": 70310 }, { "epoch": 0.4179966831321219, "grad_norm": 1.77906334400177, "learning_rate": 0.00019915322294292707, "loss": 0.7293560981750489, "step": 70320 }, { "epoch": 0.4180561252087903, "grad_norm": 2.0788774490356445, "learning_rate": 0.00019915237085129007, "loss": 0.7075117588043213, "step": 70330 }, { "epoch": 0.4181155672854587, "grad_norm": 1.5157461166381836, "learning_rate": 0.0001991515183331773, "loss": 0.7005411148071289, "step": 70340 }, { "epoch": 0.4181750093621271, "grad_norm": 1.7514393329620361, "learning_rate": 0.0001991506653885928, "loss": 0.6330276012420655, "step": 70350 }, { "epoch": 0.41823445143879545, "grad_norm": 1.6159390211105347, "learning_rate": 0.00019914981201754064, "loss": 0.6755341053009033, "step": 70360 }, { "epoch": 0.41829389351546387, "grad_norm": 1.540709376335144, "learning_rate": 0.0001991489582200249, "loss": 0.7086426734924316, "step": 70370 }, { "epoch": 0.4183533355921322, "grad_norm": 1.7034069299697876, "learning_rate": 0.00019914810399604968, "loss": 0.67415771484375, "step": 70380 }, { "epoch": 0.41841277766880064, "grad_norm": 1.912648320198059, "learning_rate": 0.00019914724934561907, "loss": 0.7456254005432129, "step": 70390 }, { "epoch": 0.41847221974546905, "grad_norm": 1.9215445518493652, "learning_rate": 0.00019914639426873719, "loss": 0.6502665519714356, "step": 70400 }, { "epoch": 0.4185316618221374, "grad_norm": 1.9275954961776733, "learning_rate": 0.00019914553876540804, "loss": 0.6740998744964599, "step": 70410 }, { "epoch": 0.4185911038988058, "grad_norm": 1.406133770942688, "learning_rate": 0.00019914468283563578, "loss": 0.6700634479522705, "step": 70420 }, { "epoch": 0.4186505459754742, "grad_norm": 1.8379217386245728, "learning_rate": 0.00019914382647942452, "loss": 0.7241558074951172, "step": 70430 }, { "epoch": 0.4187099880521426, "grad_norm": 1.5309611558914185, "learning_rate": 0.0001991429696967783, "loss": 0.6856077671051025, "step": 70440 }, { "epoch": 0.41876943012881096, "grad_norm": 1.626815915107727, "learning_rate": 0.00019914211248770123, "loss": 0.6963715553283691, "step": 70450 }, { "epoch": 0.4188288722054794, "grad_norm": 1.7653366327285767, "learning_rate": 0.00019914125485219743, "loss": 0.6747378349304199, "step": 70460 }, { "epoch": 0.41888831428214773, "grad_norm": 1.8400373458862305, "learning_rate": 0.00019914039679027104, "loss": 0.6882769584655761, "step": 70470 }, { "epoch": 0.41894775635881615, "grad_norm": 1.9234939813613892, "learning_rate": 0.0001991395383019261, "loss": 0.699687147140503, "step": 70480 }, { "epoch": 0.41900719843548456, "grad_norm": 1.4692835807800293, "learning_rate": 0.00019913867938716674, "loss": 0.6668617248535156, "step": 70490 }, { "epoch": 0.4190666405121529, "grad_norm": 1.7572109699249268, "learning_rate": 0.00019913782004599704, "loss": 0.6518222332000733, "step": 70500 }, { "epoch": 0.41912608258882134, "grad_norm": 1.5438483953475952, "learning_rate": 0.00019913696027842116, "loss": 0.6478567123413086, "step": 70510 }, { "epoch": 0.4191855246654897, "grad_norm": 2.1595680713653564, "learning_rate": 0.0001991361000844432, "loss": 0.7161357879638672, "step": 70520 }, { "epoch": 0.4192449667421581, "grad_norm": 1.5602750778198242, "learning_rate": 0.00019913523946406728, "loss": 0.7046394348144531, "step": 70530 }, { "epoch": 0.41930440881882647, "grad_norm": 1.8159316778182983, "learning_rate": 0.00019913437841729748, "loss": 0.698239803314209, "step": 70540 }, { "epoch": 0.4193638508954949, "grad_norm": 2.273066997528076, "learning_rate": 0.00019913351694413793, "loss": 0.7105367660522461, "step": 70550 }, { "epoch": 0.4194232929721633, "grad_norm": 1.8619158267974854, "learning_rate": 0.00019913265504459276, "loss": 0.6898192405700684, "step": 70560 }, { "epoch": 0.41948273504883166, "grad_norm": 2.051084518432617, "learning_rate": 0.00019913179271866614, "loss": 0.680998420715332, "step": 70570 }, { "epoch": 0.41954217712550007, "grad_norm": 2.13211989402771, "learning_rate": 0.00019913092996636214, "loss": 0.6634660720825195, "step": 70580 }, { "epoch": 0.41960161920216843, "grad_norm": 1.3667550086975098, "learning_rate": 0.0001991300667876849, "loss": 0.6623634338378906, "step": 70590 }, { "epoch": 0.41966106127883684, "grad_norm": 1.9777662754058838, "learning_rate": 0.00019912920318263853, "loss": 0.6864388942718506, "step": 70600 }, { "epoch": 0.4197205033555052, "grad_norm": 1.7632635831832886, "learning_rate": 0.0001991283391512272, "loss": 0.7034273147583008, "step": 70610 }, { "epoch": 0.4197799454321736, "grad_norm": 1.6712828874588013, "learning_rate": 0.00019912747469345501, "loss": 0.7131067276000976, "step": 70620 }, { "epoch": 0.41983938750884203, "grad_norm": 1.713683843612671, "learning_rate": 0.00019912660980932613, "loss": 0.7295936584472656, "step": 70630 }, { "epoch": 0.4198988295855104, "grad_norm": 1.6589385271072388, "learning_rate": 0.00019912574449884466, "loss": 0.6505185127258301, "step": 70640 }, { "epoch": 0.4199582716621788, "grad_norm": 1.5098373889923096, "learning_rate": 0.00019912487876201472, "loss": 0.6495736122131348, "step": 70650 }, { "epoch": 0.42001771373884716, "grad_norm": 2.202130079269409, "learning_rate": 0.00019912401259884052, "loss": 0.6759631633758545, "step": 70660 }, { "epoch": 0.4200771558155156, "grad_norm": 1.5845624208450317, "learning_rate": 0.00019912314600932618, "loss": 0.6806286334991455, "step": 70670 }, { "epoch": 0.42013659789218394, "grad_norm": 1.6065806150436401, "learning_rate": 0.00019912227899347582, "loss": 0.715425682067871, "step": 70680 }, { "epoch": 0.42019603996885235, "grad_norm": 1.6900765895843506, "learning_rate": 0.0001991214115512936, "loss": 0.7400321006774903, "step": 70690 }, { "epoch": 0.42025548204552077, "grad_norm": 1.7202807664871216, "learning_rate": 0.00019912054368278367, "loss": 0.7567084312438965, "step": 70700 }, { "epoch": 0.4203149241221891, "grad_norm": 1.6649712324142456, "learning_rate": 0.0001991196753879502, "loss": 0.6629073619842529, "step": 70710 }, { "epoch": 0.42037436619885754, "grad_norm": 1.9220675230026245, "learning_rate": 0.00019911880666679732, "loss": 0.6407248497009277, "step": 70720 }, { "epoch": 0.4204338082755259, "grad_norm": 1.7857201099395752, "learning_rate": 0.0001991179375193292, "loss": 0.6741605281829834, "step": 70730 }, { "epoch": 0.4204932503521943, "grad_norm": 1.6316884756088257, "learning_rate": 0.00019911706794555, "loss": 0.6628389358520508, "step": 70740 }, { "epoch": 0.4205526924288627, "grad_norm": 1.8592743873596191, "learning_rate": 0.00019911619794546384, "loss": 0.6803777694702149, "step": 70750 }, { "epoch": 0.4206121345055311, "grad_norm": 1.8762279748916626, "learning_rate": 0.00019911532751907494, "loss": 0.6942091941833496, "step": 70760 }, { "epoch": 0.4206715765821995, "grad_norm": 1.6571221351623535, "learning_rate": 0.00019911445666638742, "loss": 0.7025818824768066, "step": 70770 }, { "epoch": 0.42073101865886786, "grad_norm": 1.6363378763198853, "learning_rate": 0.00019911358538740546, "loss": 0.6784448623657227, "step": 70780 }, { "epoch": 0.4207904607355363, "grad_norm": 1.8205742835998535, "learning_rate": 0.00019911271368213323, "loss": 0.6997820854187011, "step": 70790 }, { "epoch": 0.42084990281220463, "grad_norm": 1.8778184652328491, "learning_rate": 0.0001991118415505749, "loss": 0.666838550567627, "step": 70800 }, { "epoch": 0.42090934488887305, "grad_norm": 1.7026002407073975, "learning_rate": 0.00019911096899273467, "loss": 0.7299405574798584, "step": 70810 }, { "epoch": 0.4209687869655414, "grad_norm": 1.900363564491272, "learning_rate": 0.00019911009600861668, "loss": 0.7167323112487793, "step": 70820 }, { "epoch": 0.4210282290422098, "grad_norm": 1.7920795679092407, "learning_rate": 0.00019910922259822506, "loss": 0.7049113750457764, "step": 70830 }, { "epoch": 0.4210876711188782, "grad_norm": 2.057119369506836, "learning_rate": 0.00019910834876156407, "loss": 0.637766170501709, "step": 70840 }, { "epoch": 0.4211471131955466, "grad_norm": 1.6436206102371216, "learning_rate": 0.00019910747449863788, "loss": 0.6458162784576416, "step": 70850 }, { "epoch": 0.421206555272215, "grad_norm": 1.9225016832351685, "learning_rate": 0.00019910659980945064, "loss": 0.6592058181762696, "step": 70860 }, { "epoch": 0.42126599734888337, "grad_norm": 2.047887086868286, "learning_rate": 0.00019910572469400656, "loss": 0.6906208038330078, "step": 70870 }, { "epoch": 0.4213254394255518, "grad_norm": 1.813110589981079, "learning_rate": 0.0001991048491523098, "loss": 0.6744214057922363, "step": 70880 }, { "epoch": 0.42138488150222014, "grad_norm": 1.2936409711837769, "learning_rate": 0.00019910397318436456, "loss": 0.7079368591308594, "step": 70890 }, { "epoch": 0.42144432357888856, "grad_norm": 1.6781134605407715, "learning_rate": 0.00019910309679017506, "loss": 0.650725269317627, "step": 70900 }, { "epoch": 0.4215037656555569, "grad_norm": 1.4496837854385376, "learning_rate": 0.00019910221996974543, "loss": 0.6917782783508301, "step": 70910 }, { "epoch": 0.42156320773222533, "grad_norm": 1.4569483995437622, "learning_rate": 0.00019910134272307987, "loss": 0.7156787395477295, "step": 70920 }, { "epoch": 0.42162264980889375, "grad_norm": 2.1791722774505615, "learning_rate": 0.00019910046505018265, "loss": 0.7236970901489258, "step": 70930 }, { "epoch": 0.4216820918855621, "grad_norm": 2.0323400497436523, "learning_rate": 0.00019909958695105793, "loss": 0.7024976730346679, "step": 70940 }, { "epoch": 0.4217415339622305, "grad_norm": 2.007206439971924, "learning_rate": 0.00019909870842570987, "loss": 0.7046722888946533, "step": 70950 }, { "epoch": 0.4218009760388989, "grad_norm": 2.4419198036193848, "learning_rate": 0.00019909782947414274, "loss": 0.7463639259338379, "step": 70960 }, { "epoch": 0.4218604181155673, "grad_norm": 1.6000921726226807, "learning_rate": 0.0001990969500963607, "loss": 0.6814385414123535, "step": 70970 }, { "epoch": 0.42191986019223565, "grad_norm": 1.8807508945465088, "learning_rate": 0.00019909607029236796, "loss": 0.7249972343444824, "step": 70980 }, { "epoch": 0.42197930226890407, "grad_norm": 1.7327675819396973, "learning_rate": 0.00019909519006216874, "loss": 0.6491021633148193, "step": 70990 }, { "epoch": 0.4220387443455725, "grad_norm": 1.6172155141830444, "learning_rate": 0.00019909430940576723, "loss": 0.6808414459228516, "step": 71000 }, { "epoch": 0.42209818642224084, "grad_norm": 2.010741710662842, "learning_rate": 0.0001990934283231677, "loss": 0.6848474502563476, "step": 71010 }, { "epoch": 0.42215762849890925, "grad_norm": 1.5493927001953125, "learning_rate": 0.0001990925468143743, "loss": 0.7335605621337891, "step": 71020 }, { "epoch": 0.4222170705755776, "grad_norm": 2.1348586082458496, "learning_rate": 0.00019909166487939127, "loss": 0.7537974834442138, "step": 71030 }, { "epoch": 0.422276512652246, "grad_norm": 1.711187720298767, "learning_rate": 0.00019909078251822285, "loss": 0.680592155456543, "step": 71040 }, { "epoch": 0.4223359547289144, "grad_norm": 1.5776413679122925, "learning_rate": 0.00019908989973087322, "loss": 0.6881200313568115, "step": 71050 }, { "epoch": 0.4223953968055828, "grad_norm": 1.946651577949524, "learning_rate": 0.00019908901651734663, "loss": 0.7293943881988525, "step": 71060 }, { "epoch": 0.4224548388822512, "grad_norm": 1.5381712913513184, "learning_rate": 0.00019908813287764732, "loss": 0.6389118194580078, "step": 71070 }, { "epoch": 0.4225142809589196, "grad_norm": 2.474985361099243, "learning_rate": 0.00019908724881177947, "loss": 0.7775126934051514, "step": 71080 }, { "epoch": 0.422573723035588, "grad_norm": 1.666572093963623, "learning_rate": 0.00019908636431974734, "loss": 0.7080138206481934, "step": 71090 }, { "epoch": 0.42263316511225635, "grad_norm": 1.6650944948196411, "learning_rate": 0.00019908547940155515, "loss": 0.6560789108276367, "step": 71100 }, { "epoch": 0.42269260718892476, "grad_norm": 1.723482608795166, "learning_rate": 0.00019908459405720713, "loss": 0.6329613208770752, "step": 71110 }, { "epoch": 0.4227520492655931, "grad_norm": 1.6699213981628418, "learning_rate": 0.00019908370828670757, "loss": 0.7188966274261475, "step": 71120 }, { "epoch": 0.42281149134226154, "grad_norm": 1.6124202013015747, "learning_rate": 0.00019908282209006066, "loss": 0.7237062931060791, "step": 71130 }, { "epoch": 0.42287093341892995, "grad_norm": 1.5805870294570923, "learning_rate": 0.0001990819354672706, "loss": 0.6857713222503662, "step": 71140 }, { "epoch": 0.4229303754955983, "grad_norm": 1.7758020162582397, "learning_rate": 0.0001990810484183417, "loss": 0.6753557205200196, "step": 71150 }, { "epoch": 0.4229898175722667, "grad_norm": 1.4802762269973755, "learning_rate": 0.00019908016094327818, "loss": 0.6274406433105468, "step": 71160 }, { "epoch": 0.4230492596489351, "grad_norm": 2.007371664047241, "learning_rate": 0.00019907927304208426, "loss": 0.6949908256530761, "step": 71170 }, { "epoch": 0.4231087017256035, "grad_norm": 1.5902010202407837, "learning_rate": 0.00019907838471476424, "loss": 0.7315605640411377, "step": 71180 }, { "epoch": 0.42316814380227186, "grad_norm": 1.450470209121704, "learning_rate": 0.0001990774959613223, "loss": 0.7146969318389893, "step": 71190 }, { "epoch": 0.42322758587894027, "grad_norm": 1.6571353673934937, "learning_rate": 0.00019907660678176274, "loss": 0.7096432685852051, "step": 71200 }, { "epoch": 0.42328702795560863, "grad_norm": 1.4665629863739014, "learning_rate": 0.0001990757171760898, "loss": 0.7003533363342285, "step": 71210 }, { "epoch": 0.42334647003227704, "grad_norm": 1.5019721984863281, "learning_rate": 0.00019907482714430778, "loss": 0.6382059097290039, "step": 71220 }, { "epoch": 0.42340591210894546, "grad_norm": 1.4474550485610962, "learning_rate": 0.00019907393668642086, "loss": 0.6793749809265137, "step": 71230 }, { "epoch": 0.4234653541856138, "grad_norm": 1.4337081909179688, "learning_rate": 0.00019907304580243335, "loss": 0.7512116432189941, "step": 71240 }, { "epoch": 0.42352479626228223, "grad_norm": 1.5854136943817139, "learning_rate": 0.00019907215449234953, "loss": 0.7416725635528565, "step": 71250 }, { "epoch": 0.4235842383389506, "grad_norm": 1.8742011785507202, "learning_rate": 0.00019907126275617358, "loss": 0.6747282028198243, "step": 71260 }, { "epoch": 0.423643680415619, "grad_norm": 1.6058844327926636, "learning_rate": 0.00019907037059390984, "loss": 0.6821966171264648, "step": 71270 }, { "epoch": 0.42370312249228737, "grad_norm": 1.7598774433135986, "learning_rate": 0.00019906947800556253, "loss": 0.6382502555847168, "step": 71280 }, { "epoch": 0.4237625645689558, "grad_norm": 1.7767589092254639, "learning_rate": 0.00019906858499113596, "loss": 0.6426420211791992, "step": 71290 }, { "epoch": 0.4238220066456242, "grad_norm": 1.7382782697677612, "learning_rate": 0.0001990676915506344, "loss": 0.6630378723144531, "step": 71300 }, { "epoch": 0.42388144872229255, "grad_norm": 1.9594365358352661, "learning_rate": 0.0001990667976840621, "loss": 0.7119248867034912, "step": 71310 }, { "epoch": 0.42394089079896097, "grad_norm": 1.691689372062683, "learning_rate": 0.00019906590339142336, "loss": 0.6487598419189453, "step": 71320 }, { "epoch": 0.4240003328756293, "grad_norm": 1.6926378011703491, "learning_rate": 0.00019906500867272243, "loss": 0.6285412788391114, "step": 71330 }, { "epoch": 0.42405977495229774, "grad_norm": 2.013385772705078, "learning_rate": 0.0001990641135279636, "loss": 0.7472665309906006, "step": 71340 }, { "epoch": 0.4241192170289661, "grad_norm": 1.6787439584732056, "learning_rate": 0.0001990632179571512, "loss": 0.6919954299926758, "step": 71350 }, { "epoch": 0.4241786591056345, "grad_norm": 1.5422207117080688, "learning_rate": 0.00019906232196028942, "loss": 0.7118858814239502, "step": 71360 }, { "epoch": 0.42423810118230293, "grad_norm": 1.2839453220367432, "learning_rate": 0.00019906142553738262, "loss": 0.6895520210266113, "step": 71370 }, { "epoch": 0.4242975432589713, "grad_norm": 1.7900724411010742, "learning_rate": 0.00019906052868843508, "loss": 0.6577261924743653, "step": 71380 }, { "epoch": 0.4243569853356397, "grad_norm": 1.4932420253753662, "learning_rate": 0.00019905963141345106, "loss": 0.6487892627716064, "step": 71390 }, { "epoch": 0.42441642741230806, "grad_norm": 1.6435600519180298, "learning_rate": 0.00019905873371243486, "loss": 0.689943504333496, "step": 71400 }, { "epoch": 0.4244758694889765, "grad_norm": 1.6249520778656006, "learning_rate": 0.0001990578355853908, "loss": 0.7009885787963868, "step": 71410 }, { "epoch": 0.42453531156564484, "grad_norm": 1.5002639293670654, "learning_rate": 0.00019905693703232315, "loss": 0.7069604873657227, "step": 71420 }, { "epoch": 0.42459475364231325, "grad_norm": 1.8164148330688477, "learning_rate": 0.00019905603805323623, "loss": 0.6800341606140137, "step": 71430 }, { "epoch": 0.42465419571898166, "grad_norm": 2.4207074642181396, "learning_rate": 0.0001990551386481343, "loss": 0.7506875038146973, "step": 71440 }, { "epoch": 0.42471363779565, "grad_norm": 1.1585761308670044, "learning_rate": 0.0001990542388170217, "loss": 0.6924448013305664, "step": 71450 }, { "epoch": 0.42477307987231844, "grad_norm": 2.0084421634674072, "learning_rate": 0.00019905333855990275, "loss": 0.7030611038208008, "step": 71460 }, { "epoch": 0.4248325219489868, "grad_norm": 1.705493450164795, "learning_rate": 0.00019905243787678173, "loss": 0.7418484210968017, "step": 71470 }, { "epoch": 0.4248919640256552, "grad_norm": 2.057826042175293, "learning_rate": 0.0001990515367676629, "loss": 0.6458083152770996, "step": 71480 }, { "epoch": 0.42495140610232357, "grad_norm": 1.5127403736114502, "learning_rate": 0.00019905063523255066, "loss": 0.7174943923950196, "step": 71490 }, { "epoch": 0.425010848178992, "grad_norm": 1.5903822183609009, "learning_rate": 0.00019904973327144925, "loss": 0.6690001964569092, "step": 71500 }, { "epoch": 0.4250702902556604, "grad_norm": 1.5339934825897217, "learning_rate": 0.00019904883088436306, "loss": 0.6741095542907715, "step": 71510 }, { "epoch": 0.42512973233232876, "grad_norm": 1.7493795156478882, "learning_rate": 0.00019904792807129632, "loss": 0.7067863464355468, "step": 71520 }, { "epoch": 0.4251891744089972, "grad_norm": 1.6601252555847168, "learning_rate": 0.00019904702483225346, "loss": 0.7030634403228759, "step": 71530 }, { "epoch": 0.42524861648566553, "grad_norm": 1.3534644842147827, "learning_rate": 0.00019904612116723868, "loss": 0.6717575073242188, "step": 71540 }, { "epoch": 0.42530805856233395, "grad_norm": 2.244249105453491, "learning_rate": 0.00019904521707625637, "loss": 0.6429695129394531, "step": 71550 }, { "epoch": 0.4253675006390023, "grad_norm": 1.7911800146102905, "learning_rate": 0.00019904431255931087, "loss": 0.6637354373931885, "step": 71560 }, { "epoch": 0.4254269427156707, "grad_norm": 2.2347025871276855, "learning_rate": 0.00019904340761640646, "loss": 0.6925864696502686, "step": 71570 }, { "epoch": 0.4254863847923391, "grad_norm": 2.5138907432556152, "learning_rate": 0.00019904250224754745, "loss": 0.761687183380127, "step": 71580 }, { "epoch": 0.4255458268690075, "grad_norm": 1.7754677534103394, "learning_rate": 0.00019904159645273823, "loss": 0.6709153652191162, "step": 71590 }, { "epoch": 0.4256052689456759, "grad_norm": 1.7636761665344238, "learning_rate": 0.00019904069023198313, "loss": 0.7703865051269532, "step": 71600 }, { "epoch": 0.42566471102234427, "grad_norm": 2.2522940635681152, "learning_rate": 0.00019903978358528645, "loss": 0.6678648948669433, "step": 71610 }, { "epoch": 0.4257241530990127, "grad_norm": 2.0209360122680664, "learning_rate": 0.00019903887651265257, "loss": 0.6996050357818604, "step": 71620 }, { "epoch": 0.42578359517568104, "grad_norm": 1.878513216972351, "learning_rate": 0.00019903796901408577, "loss": 0.6569486618041992, "step": 71630 }, { "epoch": 0.42584303725234945, "grad_norm": 1.7163704633712769, "learning_rate": 0.00019903706108959044, "loss": 0.6745335578918457, "step": 71640 }, { "epoch": 0.4259024793290178, "grad_norm": 1.7323750257492065, "learning_rate": 0.00019903615273917088, "loss": 0.6826563835144043, "step": 71650 }, { "epoch": 0.42596192140568623, "grad_norm": 1.813788890838623, "learning_rate": 0.0001990352439628315, "loss": 0.6091923713684082, "step": 71660 }, { "epoch": 0.42602136348235464, "grad_norm": 1.6306521892547607, "learning_rate": 0.00019903433476057663, "loss": 0.7011076927185058, "step": 71670 }, { "epoch": 0.426080805559023, "grad_norm": 1.8261915445327759, "learning_rate": 0.00019903342513241055, "loss": 0.6740361213684082, "step": 71680 }, { "epoch": 0.4261402476356914, "grad_norm": 1.8103265762329102, "learning_rate": 0.00019903251507833768, "loss": 0.664863395690918, "step": 71690 }, { "epoch": 0.4261996897123598, "grad_norm": 1.6507718563079834, "learning_rate": 0.00019903160459836235, "loss": 0.7095990180969238, "step": 71700 }, { "epoch": 0.4262591317890282, "grad_norm": 1.6370478868484497, "learning_rate": 0.00019903069369248892, "loss": 0.7548605918884277, "step": 71710 }, { "epoch": 0.42631857386569655, "grad_norm": 2.0418126583099365, "learning_rate": 0.00019902978236072173, "loss": 0.6944391250610351, "step": 71720 }, { "epoch": 0.42637801594236496, "grad_norm": 2.347465991973877, "learning_rate": 0.0001990288706030652, "loss": 0.7709717273712158, "step": 71730 }, { "epoch": 0.4264374580190334, "grad_norm": 2.1774978637695312, "learning_rate": 0.00019902795841952363, "loss": 0.6816282272338867, "step": 71740 }, { "epoch": 0.42649690009570174, "grad_norm": 1.5706968307495117, "learning_rate": 0.00019902704581010138, "loss": 0.6343621730804443, "step": 71750 }, { "epoch": 0.42655634217237015, "grad_norm": 1.3936612606048584, "learning_rate": 0.00019902613277480286, "loss": 0.7184971332550049, "step": 71760 }, { "epoch": 0.4266157842490385, "grad_norm": 1.7537989616394043, "learning_rate": 0.00019902521931363239, "loss": 0.6611193656921387, "step": 71770 }, { "epoch": 0.4266752263257069, "grad_norm": 1.57737135887146, "learning_rate": 0.00019902430542659437, "loss": 0.6424377918243408, "step": 71780 }, { "epoch": 0.4267346684023753, "grad_norm": 2.019137382507324, "learning_rate": 0.00019902339111369319, "loss": 0.6888515472412109, "step": 71790 }, { "epoch": 0.4267941104790437, "grad_norm": 1.9757781028747559, "learning_rate": 0.00019902247637493319, "loss": 0.7013564109802246, "step": 71800 }, { "epoch": 0.4268535525557121, "grad_norm": 1.9773463010787964, "learning_rate": 0.00019902156121031877, "loss": 0.6519901275634765, "step": 71810 }, { "epoch": 0.42691299463238047, "grad_norm": 1.8345699310302734, "learning_rate": 0.00019902064561985424, "loss": 0.7174283981323242, "step": 71820 }, { "epoch": 0.4269724367090489, "grad_norm": 1.4440760612487793, "learning_rate": 0.0001990197296035441, "loss": 0.6306697845458984, "step": 71830 }, { "epoch": 0.42703187878571724, "grad_norm": 1.620962381362915, "learning_rate": 0.00019901881316139263, "loss": 0.6480150699615479, "step": 71840 }, { "epoch": 0.42709132086238566, "grad_norm": 1.5063536167144775, "learning_rate": 0.00019901789629340425, "loss": 0.686016845703125, "step": 71850 }, { "epoch": 0.427150762939054, "grad_norm": 1.7827787399291992, "learning_rate": 0.00019901697899958335, "loss": 0.6626532554626465, "step": 71860 }, { "epoch": 0.42721020501572243, "grad_norm": 1.6881654262542725, "learning_rate": 0.00019901606127993433, "loss": 0.7397876739501953, "step": 71870 }, { "epoch": 0.42726964709239085, "grad_norm": 1.542223572731018, "learning_rate": 0.00019901514313446154, "loss": 0.6764995574951171, "step": 71880 }, { "epoch": 0.4273290891690592, "grad_norm": 2.282745838165283, "learning_rate": 0.0001990142245631694, "loss": 0.7160237312316895, "step": 71890 }, { "epoch": 0.4273885312457276, "grad_norm": 1.824153184890747, "learning_rate": 0.0001990133055660623, "loss": 0.698525857925415, "step": 71900 }, { "epoch": 0.427447973322396, "grad_norm": 1.682916283607483, "learning_rate": 0.00019901238614314465, "loss": 0.6964497089385986, "step": 71910 }, { "epoch": 0.4275074153990644, "grad_norm": 1.3806037902832031, "learning_rate": 0.00019901146629442082, "loss": 0.6783271312713623, "step": 71920 }, { "epoch": 0.42756685747573275, "grad_norm": 2.346482515335083, "learning_rate": 0.0001990105460198952, "loss": 0.6747433185577393, "step": 71930 }, { "epoch": 0.42762629955240117, "grad_norm": 2.107407331466675, "learning_rate": 0.0001990096253195723, "loss": 0.7431565284729004, "step": 71940 }, { "epoch": 0.4276857416290695, "grad_norm": 1.7635109424591064, "learning_rate": 0.00019900870419345637, "loss": 0.6674534797668457, "step": 71950 }, { "epoch": 0.42774518370573794, "grad_norm": 2.0987982749938965, "learning_rate": 0.00019900778264155192, "loss": 0.6918216228485108, "step": 71960 }, { "epoch": 0.42780462578240636, "grad_norm": 2.127040147781372, "learning_rate": 0.00019900686066386328, "loss": 0.7179811477661133, "step": 71970 }, { "epoch": 0.4278640678590747, "grad_norm": 1.7618427276611328, "learning_rate": 0.00019900593826039495, "loss": 0.6954945087432861, "step": 71980 }, { "epoch": 0.42792350993574313, "grad_norm": 1.7677655220031738, "learning_rate": 0.0001990050154311513, "loss": 0.6866266250610351, "step": 71990 }, { "epoch": 0.4279829520124115, "grad_norm": 1.4685314893722534, "learning_rate": 0.00019900409217613673, "loss": 0.6575556755065918, "step": 72000 }, { "epoch": 0.4280423940890799, "grad_norm": 2.2369368076324463, "learning_rate": 0.00019900316849535564, "loss": 0.6858205318450927, "step": 72010 }, { "epoch": 0.42810183616574826, "grad_norm": 1.7138618230819702, "learning_rate": 0.0001990022443888125, "loss": 0.7462923049926757, "step": 72020 }, { "epoch": 0.4281612782424167, "grad_norm": 1.399232268333435, "learning_rate": 0.00019900131985651175, "loss": 0.654921293258667, "step": 72030 }, { "epoch": 0.4282207203190851, "grad_norm": 1.443280577659607, "learning_rate": 0.0001990003948984577, "loss": 0.7225653171539307, "step": 72040 }, { "epoch": 0.42828016239575345, "grad_norm": 1.3207186460494995, "learning_rate": 0.00019899946951465488, "loss": 0.684501838684082, "step": 72050 }, { "epoch": 0.42833960447242186, "grad_norm": 1.7382653951644897, "learning_rate": 0.0001989985437051077, "loss": 0.7008013725280762, "step": 72060 }, { "epoch": 0.4283990465490902, "grad_norm": 1.2064929008483887, "learning_rate": 0.00019899761746982057, "loss": 0.6901495933532715, "step": 72070 }, { "epoch": 0.42845848862575864, "grad_norm": 1.9061044454574585, "learning_rate": 0.0001989966908087979, "loss": 0.6939094543457032, "step": 72080 }, { "epoch": 0.428517930702427, "grad_norm": 1.8368617296218872, "learning_rate": 0.00019899576372204417, "loss": 0.7028990745544433, "step": 72090 }, { "epoch": 0.4285773727790954, "grad_norm": 1.6648268699645996, "learning_rate": 0.00019899483620956375, "loss": 0.7071785926818848, "step": 72100 }, { "epoch": 0.4286368148557638, "grad_norm": 1.4478503465652466, "learning_rate": 0.00019899390827136118, "loss": 0.7523978233337403, "step": 72110 }, { "epoch": 0.4286962569324322, "grad_norm": 1.5729731321334839, "learning_rate": 0.0001989929799074408, "loss": 0.6646286487579346, "step": 72120 }, { "epoch": 0.4287556990091006, "grad_norm": 1.4479020833969116, "learning_rate": 0.00019899205111780708, "loss": 0.7401237487792969, "step": 72130 }, { "epoch": 0.42881514108576896, "grad_norm": 1.570570707321167, "learning_rate": 0.00019899112190246447, "loss": 0.7083732604980468, "step": 72140 }, { "epoch": 0.4288745831624374, "grad_norm": 1.6169911623001099, "learning_rate": 0.00019899019226141747, "loss": 0.7032701015472412, "step": 72150 }, { "epoch": 0.42893402523910573, "grad_norm": 1.9450305700302124, "learning_rate": 0.0001989892621946704, "loss": 0.7526807308197021, "step": 72160 }, { "epoch": 0.42899346731577415, "grad_norm": 1.3040400743484497, "learning_rate": 0.00019898833170222782, "loss": 0.649281644821167, "step": 72170 }, { "epoch": 0.42905290939244256, "grad_norm": 1.9286737442016602, "learning_rate": 0.00019898740078409411, "loss": 0.6644686698913574, "step": 72180 }, { "epoch": 0.4291123514691109, "grad_norm": 1.5341215133666992, "learning_rate": 0.00019898646944027377, "loss": 0.6693882465362548, "step": 72190 }, { "epoch": 0.42917179354577933, "grad_norm": 1.9042001962661743, "learning_rate": 0.00019898553767077126, "loss": 0.7162453651428222, "step": 72200 }, { "epoch": 0.4292312356224477, "grad_norm": 1.8187111616134644, "learning_rate": 0.000198984605475591, "loss": 0.6795133590698242, "step": 72210 }, { "epoch": 0.4292906776991161, "grad_norm": 1.8223280906677246, "learning_rate": 0.0001989836728547375, "loss": 0.7306774139404297, "step": 72220 }, { "epoch": 0.42935011977578447, "grad_norm": 1.7509129047393799, "learning_rate": 0.00019898273980821512, "loss": 0.6553547382354736, "step": 72230 }, { "epoch": 0.4294095618524529, "grad_norm": 1.6335574388504028, "learning_rate": 0.00019898180633602848, "loss": 0.7024760723114014, "step": 72240 }, { "epoch": 0.42946900392912124, "grad_norm": 1.5486122369766235, "learning_rate": 0.00019898087243818192, "loss": 0.7141553878784179, "step": 72250 }, { "epoch": 0.42952844600578965, "grad_norm": 1.6464660167694092, "learning_rate": 0.00019897993811467994, "loss": 0.5930560111999512, "step": 72260 }, { "epoch": 0.42958788808245807, "grad_norm": 1.9288380146026611, "learning_rate": 0.00019897900336552702, "loss": 0.745099687576294, "step": 72270 }, { "epoch": 0.42964733015912643, "grad_norm": 1.7888407707214355, "learning_rate": 0.0001989780681907276, "loss": 0.705836296081543, "step": 72280 }, { "epoch": 0.42970677223579484, "grad_norm": 1.6690784692764282, "learning_rate": 0.00019897713259028622, "loss": 0.6567852020263671, "step": 72290 }, { "epoch": 0.4297662143124632, "grad_norm": 1.683513879776001, "learning_rate": 0.0001989761965642073, "loss": 0.7079604148864747, "step": 72300 }, { "epoch": 0.4298256563891316, "grad_norm": 1.5597378015518188, "learning_rate": 0.00019897526011249532, "loss": 0.6601956844329834, "step": 72310 }, { "epoch": 0.4298850984658, "grad_norm": 1.8187562227249146, "learning_rate": 0.00019897432323515482, "loss": 0.7296581268310547, "step": 72320 }, { "epoch": 0.4299445405424684, "grad_norm": 1.5468182563781738, "learning_rate": 0.00019897338593219017, "loss": 0.6551986694335937, "step": 72330 }, { "epoch": 0.4300039826191368, "grad_norm": 1.97406005859375, "learning_rate": 0.00019897244820360593, "loss": 0.6585869789123535, "step": 72340 }, { "epoch": 0.43006342469580516, "grad_norm": 1.3432685136795044, "learning_rate": 0.00019897151004940662, "loss": 0.70208740234375, "step": 72350 }, { "epoch": 0.4301228667724736, "grad_norm": 1.4291760921478271, "learning_rate": 0.00019897057146959666, "loss": 0.7028110504150391, "step": 72360 }, { "epoch": 0.43018230884914194, "grad_norm": 1.8483574390411377, "learning_rate": 0.00019896963246418057, "loss": 0.667232084274292, "step": 72370 }, { "epoch": 0.43024175092581035, "grad_norm": 1.7642327547073364, "learning_rate": 0.00019896869303316278, "loss": 0.6486686706542969, "step": 72380 }, { "epoch": 0.4303011930024787, "grad_norm": 1.709517002105713, "learning_rate": 0.00019896775317654788, "loss": 0.6955571174621582, "step": 72390 }, { "epoch": 0.4303606350791471, "grad_norm": 1.6073715686798096, "learning_rate": 0.00019896681289434035, "loss": 0.7359606742858886, "step": 72400 }, { "epoch": 0.43042007715581554, "grad_norm": 1.6426059007644653, "learning_rate": 0.00019896587218654462, "loss": 0.6491342067718506, "step": 72410 }, { "epoch": 0.4304795192324839, "grad_norm": 1.539804458618164, "learning_rate": 0.00019896493105316527, "loss": 0.6172828674316406, "step": 72420 }, { "epoch": 0.4305389613091523, "grad_norm": 1.269188642501831, "learning_rate": 0.0001989639894942067, "loss": 0.7458404541015625, "step": 72430 }, { "epoch": 0.43059840338582067, "grad_norm": 1.6053217649459839, "learning_rate": 0.00019896304750967352, "loss": 0.707729434967041, "step": 72440 }, { "epoch": 0.4306578454624891, "grad_norm": 1.5295900106430054, "learning_rate": 0.0001989621050995702, "loss": 0.6309093952178955, "step": 72450 }, { "epoch": 0.43071728753915745, "grad_norm": 2.0794496536254883, "learning_rate": 0.00019896116226390123, "loss": 0.7547464370727539, "step": 72460 }, { "epoch": 0.43077672961582586, "grad_norm": 1.6579928398132324, "learning_rate": 0.00019896021900267115, "loss": 0.7183659553527832, "step": 72470 }, { "epoch": 0.4308361716924943, "grad_norm": 2.488647699356079, "learning_rate": 0.00019895927531588442, "loss": 0.6553079605102539, "step": 72480 }, { "epoch": 0.43089561376916263, "grad_norm": 1.5871714353561401, "learning_rate": 0.00019895833120354566, "loss": 0.7435182571411133, "step": 72490 }, { "epoch": 0.43095505584583105, "grad_norm": 1.6290637254714966, "learning_rate": 0.00019895738666565925, "loss": 0.6553007125854492, "step": 72500 }, { "epoch": 0.4310144979224994, "grad_norm": 1.7727856636047363, "learning_rate": 0.0001989564417022298, "loss": 0.6753265380859375, "step": 72510 }, { "epoch": 0.4310739399991678, "grad_norm": 1.8578821420669556, "learning_rate": 0.00019895549631326176, "loss": 0.6651894569396972, "step": 72520 }, { "epoch": 0.4311333820758362, "grad_norm": 1.7366827726364136, "learning_rate": 0.00019895455049875974, "loss": 0.6997488498687744, "step": 72530 }, { "epoch": 0.4311928241525046, "grad_norm": 1.652626395225525, "learning_rate": 0.0001989536042587282, "loss": 0.7013994693756104, "step": 72540 }, { "epoch": 0.431252266229173, "grad_norm": 1.5112755298614502, "learning_rate": 0.00019895265759317174, "loss": 0.6972262382507324, "step": 72550 }, { "epoch": 0.43131170830584137, "grad_norm": 1.7515095472335815, "learning_rate": 0.00019895171050209477, "loss": 0.7108547687530518, "step": 72560 }, { "epoch": 0.4313711503825098, "grad_norm": 1.8678464889526367, "learning_rate": 0.00019895076298550194, "loss": 0.7106060028076172, "step": 72570 }, { "epoch": 0.43143059245917814, "grad_norm": 1.8133805990219116, "learning_rate": 0.0001989498150433977, "loss": 0.7012301445007324, "step": 72580 }, { "epoch": 0.43149003453584656, "grad_norm": 1.6126000881195068, "learning_rate": 0.00019894886667578662, "loss": 0.7540300369262696, "step": 72590 }, { "epoch": 0.4315494766125149, "grad_norm": 1.9126355648040771, "learning_rate": 0.0001989479178826732, "loss": 0.6449180603027344, "step": 72600 }, { "epoch": 0.43160891868918333, "grad_norm": 1.573608636856079, "learning_rate": 0.00019894696866406205, "loss": 0.7432887077331543, "step": 72610 }, { "epoch": 0.4316683607658517, "grad_norm": 1.144246220588684, "learning_rate": 0.00019894601901995765, "loss": 0.6700188159942627, "step": 72620 }, { "epoch": 0.4317278028425201, "grad_norm": 1.6609570980072021, "learning_rate": 0.00019894506895036458, "loss": 0.6630607128143311, "step": 72630 }, { "epoch": 0.4317872449191885, "grad_norm": 1.78330659866333, "learning_rate": 0.00019894411845528735, "loss": 0.6572043418884277, "step": 72640 }, { "epoch": 0.4318466869958569, "grad_norm": 1.8699039220809937, "learning_rate": 0.00019894316753473054, "loss": 0.6701566696166992, "step": 72650 }, { "epoch": 0.4319061290725253, "grad_norm": 1.789170742034912, "learning_rate": 0.00019894221618869866, "loss": 0.654428768157959, "step": 72660 }, { "epoch": 0.43196557114919365, "grad_norm": 1.4241020679473877, "learning_rate": 0.0001989412644171963, "loss": 0.6785686492919922, "step": 72670 }, { "epoch": 0.43202501322586206, "grad_norm": 1.8388326168060303, "learning_rate": 0.00019894031222022801, "loss": 0.7486096382141113, "step": 72680 }, { "epoch": 0.4320844553025304, "grad_norm": 1.7337563037872314, "learning_rate": 0.0001989393595977983, "loss": 0.7053727149963379, "step": 72690 }, { "epoch": 0.43214389737919884, "grad_norm": 1.8793306350708008, "learning_rate": 0.00019893840654991178, "loss": 0.7463263988494873, "step": 72700 }, { "epoch": 0.43220333945586725, "grad_norm": 1.8475043773651123, "learning_rate": 0.000198937453076573, "loss": 0.694829797744751, "step": 72710 }, { "epoch": 0.4322627815325356, "grad_norm": 1.8041598796844482, "learning_rate": 0.0001989364991777865, "loss": 0.6516054153442383, "step": 72720 }, { "epoch": 0.432322223609204, "grad_norm": 1.6131242513656616, "learning_rate": 0.00019893554485355682, "loss": 0.7236652851104737, "step": 72730 }, { "epoch": 0.4323816656858724, "grad_norm": 1.8239037990570068, "learning_rate": 0.0001989345901038886, "loss": 0.661639928817749, "step": 72740 }, { "epoch": 0.4324411077625408, "grad_norm": 1.7146871089935303, "learning_rate": 0.00019893363492878637, "loss": 0.6312775135040283, "step": 72750 }, { "epoch": 0.43250054983920916, "grad_norm": 2.261484146118164, "learning_rate": 0.00019893267932825465, "loss": 0.6889272689819336, "step": 72760 }, { "epoch": 0.4325599919158776, "grad_norm": 1.8861757516860962, "learning_rate": 0.0001989317233022981, "loss": 0.74026517868042, "step": 72770 }, { "epoch": 0.432619433992546, "grad_norm": 2.012387990951538, "learning_rate": 0.00019893076685092125, "loss": 0.6710708618164063, "step": 72780 }, { "epoch": 0.43267887606921435, "grad_norm": 3.107968330383301, "learning_rate": 0.00019892980997412865, "loss": 0.6766551017761231, "step": 72790 }, { "epoch": 0.43273831814588276, "grad_norm": 1.532328724861145, "learning_rate": 0.0001989288526719249, "loss": 0.7280971050262451, "step": 72800 }, { "epoch": 0.4327977602225511, "grad_norm": 2.0346837043762207, "learning_rate": 0.00019892789494431457, "loss": 0.7084123611450195, "step": 72810 }, { "epoch": 0.43285720229921953, "grad_norm": 1.958309531211853, "learning_rate": 0.00019892693679130229, "loss": 0.7151132106781006, "step": 72820 }, { "epoch": 0.4329166443758879, "grad_norm": 1.362324595451355, "learning_rate": 0.00019892597821289255, "loss": 0.6541896820068359, "step": 72830 }, { "epoch": 0.4329760864525563, "grad_norm": 2.162518262863159, "learning_rate": 0.00019892501920909004, "loss": 0.7511943340301513, "step": 72840 }, { "epoch": 0.4330355285292247, "grad_norm": 1.2978057861328125, "learning_rate": 0.0001989240597798993, "loss": 0.6526584148406982, "step": 72850 }, { "epoch": 0.4330949706058931, "grad_norm": 1.4772552251815796, "learning_rate": 0.0001989230999253249, "loss": 0.6702369689941406, "step": 72860 }, { "epoch": 0.4331544126825615, "grad_norm": 2.318894147872925, "learning_rate": 0.00019892213964537144, "loss": 0.6428352355957031, "step": 72870 }, { "epoch": 0.43321385475922985, "grad_norm": 1.3649437427520752, "learning_rate": 0.00019892117894004357, "loss": 0.7877063274383544, "step": 72880 }, { "epoch": 0.43327329683589827, "grad_norm": 1.823832631111145, "learning_rate": 0.0001989202178093458, "loss": 0.7376321315765381, "step": 72890 }, { "epoch": 0.43333273891256663, "grad_norm": 1.7003157138824463, "learning_rate": 0.0001989192562532828, "loss": 0.7402713775634766, "step": 72900 }, { "epoch": 0.43339218098923504, "grad_norm": 2.232484817504883, "learning_rate": 0.00019891829427185907, "loss": 0.6954882621765137, "step": 72910 }, { "epoch": 0.43345162306590346, "grad_norm": 1.556003212928772, "learning_rate": 0.00019891733186507934, "loss": 0.6856730461120606, "step": 72920 }, { "epoch": 0.4335110651425718, "grad_norm": 1.7339965105056763, "learning_rate": 0.00019891636903294815, "loss": 0.6825605392456054, "step": 72930 }, { "epoch": 0.43357050721924023, "grad_norm": 1.5348879098892212, "learning_rate": 0.00019891540577547008, "loss": 0.6238638401031494, "step": 72940 }, { "epoch": 0.4336299492959086, "grad_norm": 2.0256898403167725, "learning_rate": 0.00019891444209264977, "loss": 0.6850441455841064, "step": 72950 }, { "epoch": 0.433689391372577, "grad_norm": 1.7869113683700562, "learning_rate": 0.00019891347798449188, "loss": 0.6919278621673584, "step": 72960 }, { "epoch": 0.43374883344924536, "grad_norm": 1.7640916109085083, "learning_rate": 0.0001989125134510009, "loss": 0.6720124244689941, "step": 72970 }, { "epoch": 0.4338082755259138, "grad_norm": 1.3191115856170654, "learning_rate": 0.00019891154849218154, "loss": 0.7071905612945557, "step": 72980 }, { "epoch": 0.43386771760258214, "grad_norm": 1.69639253616333, "learning_rate": 0.0001989105831080384, "loss": 0.6810389518737793, "step": 72990 }, { "epoch": 0.43392715967925055, "grad_norm": 1.7218118906021118, "learning_rate": 0.00019890961729857607, "loss": 0.7009084701538086, "step": 73000 }, { "epoch": 0.43398660175591897, "grad_norm": 1.2928763628005981, "learning_rate": 0.0001989086510637992, "loss": 0.6742568016052246, "step": 73010 }, { "epoch": 0.4340460438325873, "grad_norm": 1.4852312803268433, "learning_rate": 0.0001989076844037124, "loss": 0.7537760734558105, "step": 73020 }, { "epoch": 0.43410548590925574, "grad_norm": 1.891884207725525, "learning_rate": 0.00019890671731832027, "loss": 0.689083480834961, "step": 73030 }, { "epoch": 0.4341649279859241, "grad_norm": 1.5595275163650513, "learning_rate": 0.00019890574980762745, "loss": 0.6200518608093262, "step": 73040 }, { "epoch": 0.4342243700625925, "grad_norm": 2.6738405227661133, "learning_rate": 0.0001989047818716386, "loss": 0.7124863147735596, "step": 73050 }, { "epoch": 0.43428381213926087, "grad_norm": 1.953429102897644, "learning_rate": 0.00019890381351035834, "loss": 0.6766372680664062, "step": 73060 }, { "epoch": 0.4343432542159293, "grad_norm": 1.6488412618637085, "learning_rate": 0.00019890284472379128, "loss": 0.6511645317077637, "step": 73070 }, { "epoch": 0.4344026962925977, "grad_norm": 1.9684711694717407, "learning_rate": 0.00019890187551194205, "loss": 0.6444358825683594, "step": 73080 }, { "epoch": 0.43446213836926606, "grad_norm": 1.499943733215332, "learning_rate": 0.0001989009058748153, "loss": 0.6648200988769531, "step": 73090 }, { "epoch": 0.4345215804459345, "grad_norm": 1.4785304069519043, "learning_rate": 0.0001988999358124157, "loss": 0.7119025707244873, "step": 73100 }, { "epoch": 0.43458102252260283, "grad_norm": 1.7162225246429443, "learning_rate": 0.00019889896532474785, "loss": 0.7127858161926269, "step": 73110 }, { "epoch": 0.43464046459927125, "grad_norm": 1.6485668420791626, "learning_rate": 0.0001988979944118164, "loss": 0.6400038719177246, "step": 73120 }, { "epoch": 0.4346999066759396, "grad_norm": 1.4266573190689087, "learning_rate": 0.00019889702307362598, "loss": 0.6900378704071045, "step": 73130 }, { "epoch": 0.434759348752608, "grad_norm": 2.0128695964813232, "learning_rate": 0.00019889605131018128, "loss": 0.702973747253418, "step": 73140 }, { "epoch": 0.43481879082927644, "grad_norm": 1.7430778741836548, "learning_rate": 0.00019889507912148694, "loss": 0.6984174728393555, "step": 73150 }, { "epoch": 0.4348782329059448, "grad_norm": 2.11122989654541, "learning_rate": 0.00019889410650754754, "loss": 0.632359504699707, "step": 73160 }, { "epoch": 0.4349376749826132, "grad_norm": 1.5853694677352905, "learning_rate": 0.0001988931334683678, "loss": 0.6503184318542481, "step": 73170 }, { "epoch": 0.43499711705928157, "grad_norm": 1.6628961563110352, "learning_rate": 0.00019889216000395235, "loss": 0.6687898635864258, "step": 73180 }, { "epoch": 0.43505655913595, "grad_norm": 1.6822415590286255, "learning_rate": 0.0001988911861143059, "loss": 0.6808513641357422, "step": 73190 }, { "epoch": 0.43511600121261834, "grad_norm": 1.7574026584625244, "learning_rate": 0.00019889021179943304, "loss": 0.7217092514038086, "step": 73200 }, { "epoch": 0.43517544328928676, "grad_norm": 2.1182539463043213, "learning_rate": 0.00019888923705933844, "loss": 0.7048886775970459, "step": 73210 }, { "epoch": 0.43523488536595517, "grad_norm": 1.6668918132781982, "learning_rate": 0.0001988882618940268, "loss": 0.7240283012390136, "step": 73220 }, { "epoch": 0.43529432744262353, "grad_norm": 1.9841713905334473, "learning_rate": 0.00019888728630350276, "loss": 0.641492509841919, "step": 73230 }, { "epoch": 0.43535376951929194, "grad_norm": 2.0525217056274414, "learning_rate": 0.000198886310287771, "loss": 0.7016390800476074, "step": 73240 }, { "epoch": 0.4354132115959603, "grad_norm": 1.8148972988128662, "learning_rate": 0.00019888533384683615, "loss": 0.7302604198455811, "step": 73250 }, { "epoch": 0.4354726536726287, "grad_norm": 1.7782617807388306, "learning_rate": 0.00019888435698070295, "loss": 0.6806104183197021, "step": 73260 }, { "epoch": 0.4355320957492971, "grad_norm": 1.3688539266586304, "learning_rate": 0.00019888337968937604, "loss": 0.6807073593139649, "step": 73270 }, { "epoch": 0.4355915378259655, "grad_norm": 1.8492580652236938, "learning_rate": 0.00019888240197286002, "loss": 0.666933250427246, "step": 73280 }, { "epoch": 0.4356509799026339, "grad_norm": 1.9301546812057495, "learning_rate": 0.0001988814238311597, "loss": 0.6524718761444092, "step": 73290 }, { "epoch": 0.43571042197930226, "grad_norm": 1.3718878030776978, "learning_rate": 0.00019888044526427968, "loss": 0.6575127601623535, "step": 73300 }, { "epoch": 0.4357698640559707, "grad_norm": 1.8387949466705322, "learning_rate": 0.00019887946627222464, "loss": 0.7094159126281738, "step": 73310 }, { "epoch": 0.43582930613263904, "grad_norm": 1.5877577066421509, "learning_rate": 0.00019887848685499928, "loss": 0.7094846725463867, "step": 73320 }, { "epoch": 0.43588874820930745, "grad_norm": 1.6670873165130615, "learning_rate": 0.0001988775070126083, "loss": 0.6925754070281982, "step": 73330 }, { "epoch": 0.4359481902859758, "grad_norm": 1.5091156959533691, "learning_rate": 0.00019887652674505636, "loss": 0.651139211654663, "step": 73340 }, { "epoch": 0.4360076323626442, "grad_norm": 1.5238772630691528, "learning_rate": 0.0001988755460523482, "loss": 0.6766729831695557, "step": 73350 }, { "epoch": 0.4360670744393126, "grad_norm": 1.5679479837417603, "learning_rate": 0.0001988745649344884, "loss": 0.7124698638916016, "step": 73360 }, { "epoch": 0.436126516515981, "grad_norm": 1.9879673719406128, "learning_rate": 0.0001988735833914818, "loss": 0.7138423442840576, "step": 73370 }, { "epoch": 0.4361859585926494, "grad_norm": 2.189948320388794, "learning_rate": 0.00019887260142333299, "loss": 0.7029717922210693, "step": 73380 }, { "epoch": 0.4362454006693178, "grad_norm": 1.9266672134399414, "learning_rate": 0.0001988716190300467, "loss": 0.694145917892456, "step": 73390 }, { "epoch": 0.4363048427459862, "grad_norm": 2.023602247238159, "learning_rate": 0.00019887063621162762, "loss": 0.6589478492736817, "step": 73400 }, { "epoch": 0.43636428482265455, "grad_norm": 1.7005988359451294, "learning_rate": 0.00019886965296808047, "loss": 0.6921671390533447, "step": 73410 }, { "epoch": 0.43642372689932296, "grad_norm": 1.7568808794021606, "learning_rate": 0.00019886866929940992, "loss": 0.6680246353149414, "step": 73420 }, { "epoch": 0.4364831689759913, "grad_norm": 1.6007028818130493, "learning_rate": 0.0001988676852056207, "loss": 0.6279398918151855, "step": 73430 }, { "epoch": 0.43654261105265973, "grad_norm": 1.813420057296753, "learning_rate": 0.00019886670068671757, "loss": 0.6763911247253418, "step": 73440 }, { "epoch": 0.43660205312932815, "grad_norm": 1.4554216861724854, "learning_rate": 0.00019886571574270515, "loss": 0.7095602512359619, "step": 73450 }, { "epoch": 0.4366614952059965, "grad_norm": 1.7225830554962158, "learning_rate": 0.00019886473037358817, "loss": 0.689869499206543, "step": 73460 }, { "epoch": 0.4367209372826649, "grad_norm": 1.6477164030075073, "learning_rate": 0.0001988637445793714, "loss": 0.7323636531829834, "step": 73470 }, { "epoch": 0.4367803793593333, "grad_norm": 1.5645532608032227, "learning_rate": 0.00019886275836005946, "loss": 0.6562210083007812, "step": 73480 }, { "epoch": 0.4368398214360017, "grad_norm": 2.206427574157715, "learning_rate": 0.0001988617717156572, "loss": 0.6887539863586426, "step": 73490 }, { "epoch": 0.43689926351267006, "grad_norm": 1.6831655502319336, "learning_rate": 0.00019886078464616922, "loss": 0.790228271484375, "step": 73500 }, { "epoch": 0.43695870558933847, "grad_norm": 1.5206425189971924, "learning_rate": 0.00019885979715160025, "loss": 0.6867383003234864, "step": 73510 }, { "epoch": 0.4370181476660069, "grad_norm": 1.5909366607666016, "learning_rate": 0.0001988588092319551, "loss": 0.6494161128997803, "step": 73520 }, { "epoch": 0.43707758974267524, "grad_norm": 1.8990288972854614, "learning_rate": 0.00019885782088723846, "loss": 0.6445542335510254, "step": 73530 }, { "epoch": 0.43713703181934366, "grad_norm": 1.6648614406585693, "learning_rate": 0.00019885683211745501, "loss": 0.6891785621643066, "step": 73540 }, { "epoch": 0.437196473896012, "grad_norm": 1.9098529815673828, "learning_rate": 0.0001988558429226095, "loss": 0.6594356536865235, "step": 73550 }, { "epoch": 0.43725591597268043, "grad_norm": 2.1113409996032715, "learning_rate": 0.0001988548533027067, "loss": 0.6432948589324952, "step": 73560 }, { "epoch": 0.4373153580493488, "grad_norm": 1.7672303915023804, "learning_rate": 0.00019885386325775134, "loss": 0.723403024673462, "step": 73570 }, { "epoch": 0.4373748001260172, "grad_norm": 2.1648356914520264, "learning_rate": 0.00019885287278774812, "loss": 0.7411511421203614, "step": 73580 }, { "epoch": 0.4374342422026856, "grad_norm": 2.001840591430664, "learning_rate": 0.0001988518818927018, "loss": 0.6966126441955567, "step": 73590 }, { "epoch": 0.437493684279354, "grad_norm": 1.8341103792190552, "learning_rate": 0.00019885089057261707, "loss": 0.7048565864562988, "step": 73600 }, { "epoch": 0.4375531263560224, "grad_norm": 2.0867960453033447, "learning_rate": 0.00019884989882749878, "loss": 0.6679699897766114, "step": 73610 }, { "epoch": 0.43761256843269075, "grad_norm": 1.342923879623413, "learning_rate": 0.00019884890665735158, "loss": 0.6786334991455079, "step": 73620 }, { "epoch": 0.43767201050935917, "grad_norm": 1.8755900859832764, "learning_rate": 0.00019884791406218024, "loss": 0.7041380405426025, "step": 73630 }, { "epoch": 0.4377314525860275, "grad_norm": 2.4449961185455322, "learning_rate": 0.00019884692104198953, "loss": 0.6680933952331543, "step": 73640 }, { "epoch": 0.43779089466269594, "grad_norm": 1.8318443298339844, "learning_rate": 0.00019884592759678417, "loss": 0.6676771163940429, "step": 73650 }, { "epoch": 0.43785033673936435, "grad_norm": 1.7421332597732544, "learning_rate": 0.00019884493372656893, "loss": 0.7155127048492431, "step": 73660 }, { "epoch": 0.4379097788160327, "grad_norm": 2.14619517326355, "learning_rate": 0.00019884393943134858, "loss": 0.6488555431365967, "step": 73670 }, { "epoch": 0.4379692208927011, "grad_norm": 2.29154109954834, "learning_rate": 0.00019884294471112784, "loss": 0.6974673748016358, "step": 73680 }, { "epoch": 0.4380286629693695, "grad_norm": 1.7083998918533325, "learning_rate": 0.0001988419495659115, "loss": 0.7183377265930175, "step": 73690 }, { "epoch": 0.4380881050460379, "grad_norm": 1.6047087907791138, "learning_rate": 0.00019884095399570428, "loss": 0.690467357635498, "step": 73700 }, { "epoch": 0.43814754712270626, "grad_norm": 1.672438144683838, "learning_rate": 0.000198839958000511, "loss": 0.6703702926635742, "step": 73710 }, { "epoch": 0.4382069891993747, "grad_norm": 1.5560158491134644, "learning_rate": 0.0001988389615803364, "loss": 0.6842249870300293, "step": 73720 }, { "epoch": 0.43826643127604303, "grad_norm": 1.5617104768753052, "learning_rate": 0.0001988379647351852, "loss": 0.681800651550293, "step": 73730 }, { "epoch": 0.43832587335271145, "grad_norm": 1.778139591217041, "learning_rate": 0.00019883696746506225, "loss": 0.685795783996582, "step": 73740 }, { "epoch": 0.43838531542937986, "grad_norm": 1.6861344575881958, "learning_rate": 0.00019883596976997224, "loss": 0.7376276016235351, "step": 73750 }, { "epoch": 0.4384447575060482, "grad_norm": 1.8789660930633545, "learning_rate": 0.00019883497164992, "loss": 0.6835366725921631, "step": 73760 }, { "epoch": 0.43850419958271664, "grad_norm": 1.87571120262146, "learning_rate": 0.0001988339731049103, "loss": 0.6633013248443603, "step": 73770 }, { "epoch": 0.438563641659385, "grad_norm": 1.79219651222229, "learning_rate": 0.00019883297413494791, "loss": 0.6665510177612305, "step": 73780 }, { "epoch": 0.4386230837360534, "grad_norm": 1.630579948425293, "learning_rate": 0.00019883197474003758, "loss": 0.6465589046478272, "step": 73790 }, { "epoch": 0.43868252581272177, "grad_norm": 1.695594072341919, "learning_rate": 0.00019883097492018413, "loss": 0.6980626106262207, "step": 73800 }, { "epoch": 0.4387419678893902, "grad_norm": 1.7790395021438599, "learning_rate": 0.00019882997467539232, "loss": 0.7297084331512451, "step": 73810 }, { "epoch": 0.4388014099660586, "grad_norm": 2.13708233833313, "learning_rate": 0.00019882897400566693, "loss": 0.7079219818115234, "step": 73820 }, { "epoch": 0.43886085204272696, "grad_norm": 1.773593783378601, "learning_rate": 0.00019882797291101277, "loss": 0.7028441429138184, "step": 73830 }, { "epoch": 0.43892029411939537, "grad_norm": 1.7877126932144165, "learning_rate": 0.0001988269713914346, "loss": 0.6730062007904053, "step": 73840 }, { "epoch": 0.43897973619606373, "grad_norm": 1.7141914367675781, "learning_rate": 0.00019882596944693727, "loss": 0.6612939357757568, "step": 73850 }, { "epoch": 0.43903917827273214, "grad_norm": 1.6011403799057007, "learning_rate": 0.00019882496707752546, "loss": 0.7402725696563721, "step": 73860 }, { "epoch": 0.4390986203494005, "grad_norm": 1.541758418083191, "learning_rate": 0.00019882396428320408, "loss": 0.6506228446960449, "step": 73870 }, { "epoch": 0.4391580624260689, "grad_norm": 2.2454490661621094, "learning_rate": 0.00019882296106397794, "loss": 0.7614490985870361, "step": 73880 }, { "epoch": 0.43921750450273733, "grad_norm": 1.640993595123291, "learning_rate": 0.0001988219574198517, "loss": 0.7573677062988281, "step": 73890 }, { "epoch": 0.4392769465794057, "grad_norm": 1.672943115234375, "learning_rate": 0.00019882095335083027, "loss": 0.6568879127502442, "step": 73900 }, { "epoch": 0.4393363886560741, "grad_norm": 1.6598875522613525, "learning_rate": 0.00019881994885691842, "loss": 0.6633696556091309, "step": 73910 }, { "epoch": 0.43939583073274247, "grad_norm": 1.9589704275131226, "learning_rate": 0.00019881894393812097, "loss": 0.7078643798828125, "step": 73920 }, { "epoch": 0.4394552728094109, "grad_norm": 1.590103030204773, "learning_rate": 0.0001988179385944427, "loss": 0.6268391132354736, "step": 73930 }, { "epoch": 0.43951471488607924, "grad_norm": 2.2012875080108643, "learning_rate": 0.00019881693282588846, "loss": 0.650028133392334, "step": 73940 }, { "epoch": 0.43957415696274765, "grad_norm": 1.533403992652893, "learning_rate": 0.00019881592663246303, "loss": 0.6764341354370117, "step": 73950 }, { "epoch": 0.43963359903941607, "grad_norm": 1.6036893129348755, "learning_rate": 0.00019881492001417125, "loss": 0.644329833984375, "step": 73960 }, { "epoch": 0.4396930411160844, "grad_norm": 1.5232056379318237, "learning_rate": 0.0001988139129710179, "loss": 0.7048104286193848, "step": 73970 }, { "epoch": 0.43975248319275284, "grad_norm": 2.006988763809204, "learning_rate": 0.0001988129055030078, "loss": 0.686856460571289, "step": 73980 }, { "epoch": 0.4398119252694212, "grad_norm": 1.4212472438812256, "learning_rate": 0.0001988118976101458, "loss": 0.6383048057556152, "step": 73990 }, { "epoch": 0.4398713673460896, "grad_norm": 1.5659148693084717, "learning_rate": 0.0001988108892924367, "loss": 0.7065990447998047, "step": 74000 }, { "epoch": 0.439930809422758, "grad_norm": 1.8934074640274048, "learning_rate": 0.00019880988054988533, "loss": 0.7032363891601563, "step": 74010 }, { "epoch": 0.4399902514994264, "grad_norm": 1.619423270225525, "learning_rate": 0.0001988088713824965, "loss": 0.690026330947876, "step": 74020 }, { "epoch": 0.44004969357609475, "grad_norm": 1.7747833728790283, "learning_rate": 0.00019880786179027508, "loss": 0.667899227142334, "step": 74030 }, { "epoch": 0.44010913565276316, "grad_norm": 1.6222771406173706, "learning_rate": 0.0001988068517732259, "loss": 0.7017646789550781, "step": 74040 }, { "epoch": 0.4401685777294316, "grad_norm": 1.7375836372375488, "learning_rate": 0.0001988058413313537, "loss": 0.6969985485076904, "step": 74050 }, { "epoch": 0.44022801980609993, "grad_norm": 1.8752447366714478, "learning_rate": 0.00019880483046466342, "loss": 0.6520773887634277, "step": 74060 }, { "epoch": 0.44028746188276835, "grad_norm": 2.0198676586151123, "learning_rate": 0.00019880381917315983, "loss": 0.6593591690063476, "step": 74070 }, { "epoch": 0.4403469039594367, "grad_norm": 2.0112829208374023, "learning_rate": 0.00019880280745684782, "loss": 0.7461641311645508, "step": 74080 }, { "epoch": 0.4404063460361051, "grad_norm": 2.847738027572632, "learning_rate": 0.00019880179531573216, "loss": 0.7221609115600586, "step": 74090 }, { "epoch": 0.4404657881127735, "grad_norm": 1.5172637701034546, "learning_rate": 0.00019880078274981774, "loss": 0.6896934986114502, "step": 74100 }, { "epoch": 0.4405252301894419, "grad_norm": 1.9670531749725342, "learning_rate": 0.00019879976975910942, "loss": 0.6745192527770996, "step": 74110 }, { "epoch": 0.4405846722661103, "grad_norm": 2.0516138076782227, "learning_rate": 0.00019879875634361198, "loss": 0.6978381156921387, "step": 74120 }, { "epoch": 0.44064411434277867, "grad_norm": 1.5108052492141724, "learning_rate": 0.00019879774250333035, "loss": 0.6679718971252442, "step": 74130 }, { "epoch": 0.4407035564194471, "grad_norm": 1.7707606554031372, "learning_rate": 0.0001987967282382693, "loss": 0.6934711456298828, "step": 74140 }, { "epoch": 0.44076299849611544, "grad_norm": 2.1640830039978027, "learning_rate": 0.00019879571354843376, "loss": 0.6941645622253418, "step": 74150 }, { "epoch": 0.44082244057278386, "grad_norm": 1.890255331993103, "learning_rate": 0.00019879469843382856, "loss": 0.6946872711181641, "step": 74160 }, { "epoch": 0.4408818826494522, "grad_norm": 1.6026676893234253, "learning_rate": 0.00019879368289445852, "loss": 0.6541204452514648, "step": 74170 }, { "epoch": 0.44094132472612063, "grad_norm": 1.421552300453186, "learning_rate": 0.0001987926669303285, "loss": 0.6628770351409912, "step": 74180 }, { "epoch": 0.44100076680278905, "grad_norm": 1.644897699356079, "learning_rate": 0.0001987916505414434, "loss": 0.7294437885284424, "step": 74190 }, { "epoch": 0.4410602088794574, "grad_norm": 1.469774842262268, "learning_rate": 0.00019879063372780804, "loss": 0.7039436340332031, "step": 74200 }, { "epoch": 0.4411196509561258, "grad_norm": 1.8827537298202515, "learning_rate": 0.00019878961648942732, "loss": 0.6651857852935791, "step": 74210 }, { "epoch": 0.4411790930327942, "grad_norm": 1.4108195304870605, "learning_rate": 0.0001987885988263061, "loss": 0.6894642829895019, "step": 74220 }, { "epoch": 0.4412385351094626, "grad_norm": 1.4686509370803833, "learning_rate": 0.00019878758073844924, "loss": 0.6491752147674561, "step": 74230 }, { "epoch": 0.44129797718613095, "grad_norm": 1.8192933797836304, "learning_rate": 0.00019878656222586157, "loss": 0.6302953720092773, "step": 74240 }, { "epoch": 0.44135741926279937, "grad_norm": 1.4832651615142822, "learning_rate": 0.00019878554328854804, "loss": 0.6548542976379395, "step": 74250 }, { "epoch": 0.4414168613394678, "grad_norm": 1.7604756355285645, "learning_rate": 0.0001987845239265135, "loss": 0.6374567985534668, "step": 74260 }, { "epoch": 0.44147630341613614, "grad_norm": 1.9553980827331543, "learning_rate": 0.00019878350413976277, "loss": 0.667957067489624, "step": 74270 }, { "epoch": 0.44153574549280455, "grad_norm": 1.5813878774642944, "learning_rate": 0.0001987824839283008, "loss": 0.7443404197692871, "step": 74280 }, { "epoch": 0.4415951875694729, "grad_norm": 2.1453018188476562, "learning_rate": 0.00019878146329213242, "loss": 0.7039102077484131, "step": 74290 }, { "epoch": 0.44165462964614133, "grad_norm": 2.014298915863037, "learning_rate": 0.00019878044223126253, "loss": 0.7333812236785888, "step": 74300 }, { "epoch": 0.4417140717228097, "grad_norm": 1.9572346210479736, "learning_rate": 0.00019877942074569604, "loss": 0.7408315181732178, "step": 74310 }, { "epoch": 0.4417735137994781, "grad_norm": 1.8285161256790161, "learning_rate": 0.00019877839883543783, "loss": 0.7146453857421875, "step": 74320 }, { "epoch": 0.4418329558761465, "grad_norm": 2.453049421310425, "learning_rate": 0.00019877737650049273, "loss": 0.7152450561523438, "step": 74330 }, { "epoch": 0.4418923979528149, "grad_norm": 1.8130674362182617, "learning_rate": 0.00019877635374086568, "loss": 0.6320958137512207, "step": 74340 }, { "epoch": 0.4419518400294833, "grad_norm": 1.4789211750030518, "learning_rate": 0.0001987753305565616, "loss": 0.6902014255523682, "step": 74350 }, { "epoch": 0.44201128210615165, "grad_norm": 1.7949594259262085, "learning_rate": 0.00019877430694758536, "loss": 0.7174597263336182, "step": 74360 }, { "epoch": 0.44207072418282006, "grad_norm": 1.6218698024749756, "learning_rate": 0.0001987732829139418, "loss": 0.7180900573730469, "step": 74370 }, { "epoch": 0.4421301662594884, "grad_norm": 1.45489501953125, "learning_rate": 0.0001987722584556359, "loss": 0.743012523651123, "step": 74380 }, { "epoch": 0.44218960833615684, "grad_norm": 2.4908347129821777, "learning_rate": 0.0001987712335726725, "loss": 0.6568694114685059, "step": 74390 }, { "epoch": 0.4422490504128252, "grad_norm": 1.4976236820220947, "learning_rate": 0.00019877020826505654, "loss": 0.7058591365814209, "step": 74400 }, { "epoch": 0.4423084924894936, "grad_norm": 1.8312360048294067, "learning_rate": 0.00019876918253279292, "loss": 0.6973316192626953, "step": 74410 }, { "epoch": 0.442367934566162, "grad_norm": 1.9798442125320435, "learning_rate": 0.00019876815637588652, "loss": 0.7058548927307129, "step": 74420 }, { "epoch": 0.4424273766428304, "grad_norm": 2.087026357650757, "learning_rate": 0.00019876712979434232, "loss": 0.7195571899414063, "step": 74430 }, { "epoch": 0.4424868187194988, "grad_norm": 1.921434760093689, "learning_rate": 0.00019876610278816515, "loss": 0.6577477931976319, "step": 74440 }, { "epoch": 0.44254626079616716, "grad_norm": 2.034534454345703, "learning_rate": 0.00019876507535735994, "loss": 0.7286736965179443, "step": 74450 }, { "epoch": 0.44260570287283557, "grad_norm": 1.9283167123794556, "learning_rate": 0.0001987640475019316, "loss": 0.6730688095092774, "step": 74460 }, { "epoch": 0.44266514494950393, "grad_norm": 1.808156132698059, "learning_rate": 0.0001987630192218851, "loss": 0.6965202331542969, "step": 74470 }, { "epoch": 0.44272458702617234, "grad_norm": 2.0153253078460693, "learning_rate": 0.00019876199051722533, "loss": 0.6755680084228516, "step": 74480 }, { "epoch": 0.44278402910284076, "grad_norm": 1.568490743637085, "learning_rate": 0.0001987609613879572, "loss": 0.6328145027160644, "step": 74490 }, { "epoch": 0.4428434711795091, "grad_norm": 1.641215443611145, "learning_rate": 0.00019875993183408563, "loss": 0.7114620685577393, "step": 74500 }, { "epoch": 0.44290291325617753, "grad_norm": 1.4929702281951904, "learning_rate": 0.00019875890185561555, "loss": 0.653437328338623, "step": 74510 }, { "epoch": 0.4429623553328459, "grad_norm": 2.06900954246521, "learning_rate": 0.0001987578714525519, "loss": 0.6570065498352051, "step": 74520 }, { "epoch": 0.4430217974095143, "grad_norm": 1.7672338485717773, "learning_rate": 0.0001987568406248996, "loss": 0.6432793617248536, "step": 74530 }, { "epoch": 0.44308123948618267, "grad_norm": 1.606673002243042, "learning_rate": 0.0001987558093726636, "loss": 0.6668071746826172, "step": 74540 }, { "epoch": 0.4431406815628511, "grad_norm": 1.6869676113128662, "learning_rate": 0.00019875477769584876, "loss": 0.6916331768035888, "step": 74550 }, { "epoch": 0.4432001236395195, "grad_norm": 1.6177870035171509, "learning_rate": 0.00019875374559446009, "loss": 0.6885581016540527, "step": 74560 }, { "epoch": 0.44325956571618785, "grad_norm": 1.2490215301513672, "learning_rate": 0.0001987527130685025, "loss": 0.6315522193908691, "step": 74570 }, { "epoch": 0.44331900779285627, "grad_norm": 1.2009048461914062, "learning_rate": 0.00019875168011798094, "loss": 0.7283802986145019, "step": 74580 }, { "epoch": 0.4433784498695246, "grad_norm": 1.8739380836486816, "learning_rate": 0.00019875064674290037, "loss": 0.6931819915771484, "step": 74590 }, { "epoch": 0.44343789194619304, "grad_norm": 1.3517868518829346, "learning_rate": 0.00019874961294326571, "loss": 0.6841363906860352, "step": 74600 }, { "epoch": 0.4434973340228614, "grad_norm": 1.8099910020828247, "learning_rate": 0.0001987485787190819, "loss": 0.7148062705993652, "step": 74610 }, { "epoch": 0.4435567760995298, "grad_norm": 1.7484582662582397, "learning_rate": 0.0001987475440703539, "loss": 0.6647203445434571, "step": 74620 }, { "epoch": 0.44361621817619823, "grad_norm": 1.9079889059066772, "learning_rate": 0.0001987465089970866, "loss": 0.7377860069274902, "step": 74630 }, { "epoch": 0.4436756602528666, "grad_norm": 1.8456746339797974, "learning_rate": 0.00019874547349928506, "loss": 0.7179608345031738, "step": 74640 }, { "epoch": 0.443735102329535, "grad_norm": 2.3526952266693115, "learning_rate": 0.00019874443757695413, "loss": 0.6955123901367187, "step": 74650 }, { "epoch": 0.44379454440620336, "grad_norm": 1.4088653326034546, "learning_rate": 0.00019874340123009885, "loss": 0.7425276756286621, "step": 74660 }, { "epoch": 0.4438539864828718, "grad_norm": 1.7200088500976562, "learning_rate": 0.00019874236445872412, "loss": 0.734226131439209, "step": 74670 }, { "epoch": 0.44391342855954014, "grad_norm": 2.3556017875671387, "learning_rate": 0.00019874132726283494, "loss": 0.7299620628356933, "step": 74680 }, { "epoch": 0.44397287063620855, "grad_norm": 1.7256813049316406, "learning_rate": 0.00019874028964243624, "loss": 0.7127432823181152, "step": 74690 }, { "epoch": 0.44403231271287696, "grad_norm": 2.0556318759918213, "learning_rate": 0.000198739251597533, "loss": 0.6461101531982422, "step": 74700 }, { "epoch": 0.4440917547895453, "grad_norm": 1.7528294324874878, "learning_rate": 0.00019873821312813017, "loss": 0.7331375122070313, "step": 74710 }, { "epoch": 0.44415119686621374, "grad_norm": 1.6693789958953857, "learning_rate": 0.00019873717423423272, "loss": 0.6675813674926758, "step": 74720 }, { "epoch": 0.4442106389428821, "grad_norm": 1.4735029935836792, "learning_rate": 0.00019873613491584567, "loss": 0.7056133270263671, "step": 74730 }, { "epoch": 0.4442700810195505, "grad_norm": 1.646053433418274, "learning_rate": 0.0001987350951729739, "loss": 0.6692845344543457, "step": 74740 }, { "epoch": 0.44432952309621887, "grad_norm": 1.6170258522033691, "learning_rate": 0.00019873405500562245, "loss": 0.6517173767089843, "step": 74750 }, { "epoch": 0.4443889651728873, "grad_norm": 2.17912220954895, "learning_rate": 0.0001987330144137963, "loss": 0.6937896251678467, "step": 74760 }, { "epoch": 0.44444840724955564, "grad_norm": 1.5071460008621216, "learning_rate": 0.00019873197339750039, "loss": 0.7004588127136231, "step": 74770 }, { "epoch": 0.44450784932622406, "grad_norm": 1.5752623081207275, "learning_rate": 0.00019873093195673974, "loss": 0.6872724056243896, "step": 74780 }, { "epoch": 0.4445672914028925, "grad_norm": 1.6015506982803345, "learning_rate": 0.00019872989009151926, "loss": 0.7018500328063965, "step": 74790 }, { "epoch": 0.44462673347956083, "grad_norm": 2.070496082305908, "learning_rate": 0.000198728847801844, "loss": 0.7107717990875244, "step": 74800 }, { "epoch": 0.44468617555622925, "grad_norm": 1.8207635879516602, "learning_rate": 0.00019872780508771895, "loss": 0.7277279853820801, "step": 74810 }, { "epoch": 0.4447456176328976, "grad_norm": 1.7086771726608276, "learning_rate": 0.00019872676194914907, "loss": 0.7397514343261719, "step": 74820 }, { "epoch": 0.444805059709566, "grad_norm": 1.6594042778015137, "learning_rate": 0.00019872571838613936, "loss": 0.7229522228240967, "step": 74830 }, { "epoch": 0.4448645017862344, "grad_norm": 1.4760140180587769, "learning_rate": 0.00019872467439869482, "loss": 0.683194923400879, "step": 74840 }, { "epoch": 0.4449239438629028, "grad_norm": 1.5860902070999146, "learning_rate": 0.0001987236299868204, "loss": 0.6781375408172607, "step": 74850 }, { "epoch": 0.4449833859395712, "grad_norm": 1.821750521659851, "learning_rate": 0.00019872258515052116, "loss": 0.6775442600250244, "step": 74860 }, { "epoch": 0.44504282801623957, "grad_norm": 2.1144485473632812, "learning_rate": 0.00019872153988980204, "loss": 0.665971040725708, "step": 74870 }, { "epoch": 0.445102270092908, "grad_norm": 1.4599425792694092, "learning_rate": 0.0001987204942046681, "loss": 0.7077771186828613, "step": 74880 }, { "epoch": 0.44516171216957634, "grad_norm": 1.7746174335479736, "learning_rate": 0.0001987194480951243, "loss": 0.6863481521606445, "step": 74890 }, { "epoch": 0.44522115424624475, "grad_norm": 1.696500539779663, "learning_rate": 0.00019871840156117563, "loss": 0.6531347274780274, "step": 74900 }, { "epoch": 0.4452805963229131, "grad_norm": 1.6128963232040405, "learning_rate": 0.00019871735460282714, "loss": 0.6973482608795166, "step": 74910 }, { "epoch": 0.44534003839958153, "grad_norm": 1.9752854108810425, "learning_rate": 0.0001987163072200838, "loss": 0.7231796741485595, "step": 74920 }, { "epoch": 0.44539948047624994, "grad_norm": 1.5449676513671875, "learning_rate": 0.00019871525941295067, "loss": 0.6677662849426269, "step": 74930 }, { "epoch": 0.4454589225529183, "grad_norm": 1.6245527267456055, "learning_rate": 0.00019871421118143273, "loss": 0.6285770416259766, "step": 74940 }, { "epoch": 0.4455183646295867, "grad_norm": 1.7258903980255127, "learning_rate": 0.00019871316252553496, "loss": 0.7128048419952393, "step": 74950 }, { "epoch": 0.4455778067062551, "grad_norm": 1.5360214710235596, "learning_rate": 0.00019871211344526244, "loss": 0.7110692977905273, "step": 74960 }, { "epoch": 0.4456372487829235, "grad_norm": 1.4109127521514893, "learning_rate": 0.00019871106394062015, "loss": 0.6598275661468506, "step": 74970 }, { "epoch": 0.44569669085959185, "grad_norm": 1.7357138395309448, "learning_rate": 0.00019871001401161313, "loss": 0.6675924301147461, "step": 74980 }, { "epoch": 0.44575613293626026, "grad_norm": 1.5324018001556396, "learning_rate": 0.00019870896365824638, "loss": 0.744987964630127, "step": 74990 }, { "epoch": 0.4458155750129287, "grad_norm": 1.6653063297271729, "learning_rate": 0.00019870791288052495, "loss": 0.7012475013732911, "step": 75000 }, { "epoch": 0.44587501708959704, "grad_norm": 1.8645461797714233, "learning_rate": 0.00019870686167845384, "loss": 0.7308817386627198, "step": 75010 }, { "epoch": 0.44593445916626545, "grad_norm": 1.6053959131240845, "learning_rate": 0.00019870581005203812, "loss": 0.6810980796813965, "step": 75020 }, { "epoch": 0.4459939012429338, "grad_norm": 1.9386625289916992, "learning_rate": 0.00019870475800128277, "loss": 0.675063180923462, "step": 75030 }, { "epoch": 0.4460533433196022, "grad_norm": 1.7478747367858887, "learning_rate": 0.00019870370552619286, "loss": 0.7247337341308594, "step": 75040 }, { "epoch": 0.4461127853962706, "grad_norm": 1.810036063194275, "learning_rate": 0.0001987026526267734, "loss": 0.7619379043579102, "step": 75050 }, { "epoch": 0.446172227472939, "grad_norm": 1.8310688734054565, "learning_rate": 0.00019870159930302945, "loss": 0.7122764587402344, "step": 75060 }, { "epoch": 0.4462316695496074, "grad_norm": 2.2860488891601562, "learning_rate": 0.00019870054555496604, "loss": 0.7154216289520263, "step": 75070 }, { "epoch": 0.44629111162627577, "grad_norm": 1.6294896602630615, "learning_rate": 0.0001986994913825882, "loss": 0.6326018333435058, "step": 75080 }, { "epoch": 0.4463505537029442, "grad_norm": 1.6018263101577759, "learning_rate": 0.00019869843678590101, "loss": 0.6587471008300781, "step": 75090 }, { "epoch": 0.44640999577961255, "grad_norm": 1.9646857976913452, "learning_rate": 0.00019869738176490944, "loss": 0.7790038585662842, "step": 75100 }, { "epoch": 0.44646943785628096, "grad_norm": 1.9114691019058228, "learning_rate": 0.0001986963263196186, "loss": 0.7483743667602539, "step": 75110 }, { "epoch": 0.4465288799329493, "grad_norm": 1.7546138763427734, "learning_rate": 0.00019869527045003352, "loss": 0.7429728507995605, "step": 75120 }, { "epoch": 0.44658832200961773, "grad_norm": 1.887220025062561, "learning_rate": 0.00019869421415615924, "loss": 0.6547161102294922, "step": 75130 }, { "epoch": 0.4466477640862861, "grad_norm": 1.8791258335113525, "learning_rate": 0.00019869315743800084, "loss": 0.647402572631836, "step": 75140 }, { "epoch": 0.4467072061629545, "grad_norm": 1.8294851779937744, "learning_rate": 0.00019869210029556337, "loss": 0.7044660568237304, "step": 75150 }, { "epoch": 0.4467666482396229, "grad_norm": 1.6736506223678589, "learning_rate": 0.00019869104272885187, "loss": 0.7147316455841064, "step": 75160 }, { "epoch": 0.4468260903162913, "grad_norm": 2.2411611080169678, "learning_rate": 0.00019868998473787137, "loss": 0.7066851615905761, "step": 75170 }, { "epoch": 0.4468855323929597, "grad_norm": 1.5855673551559448, "learning_rate": 0.000198688926322627, "loss": 0.7211734771728515, "step": 75180 }, { "epoch": 0.44694497446962805, "grad_norm": 1.881880760192871, "learning_rate": 0.00019868786748312382, "loss": 0.657253646850586, "step": 75190 }, { "epoch": 0.44700441654629647, "grad_norm": 1.9626747369766235, "learning_rate": 0.00019868680821936681, "loss": 0.7474259376525879, "step": 75200 }, { "epoch": 0.4470638586229648, "grad_norm": 1.8435767889022827, "learning_rate": 0.00019868574853136112, "loss": 0.6785573959350586, "step": 75210 }, { "epoch": 0.44712330069963324, "grad_norm": 1.8732678890228271, "learning_rate": 0.00019868468841911178, "loss": 0.7448207855224609, "step": 75220 }, { "epoch": 0.44718274277630166, "grad_norm": 1.6555967330932617, "learning_rate": 0.0001986836278826239, "loss": 0.6577117443084717, "step": 75230 }, { "epoch": 0.44724218485297, "grad_norm": 2.2629146575927734, "learning_rate": 0.0001986825669219025, "loss": 0.6548473358154296, "step": 75240 }, { "epoch": 0.44730162692963843, "grad_norm": 1.8258570432662964, "learning_rate": 0.00019868150553695272, "loss": 0.6780477523803711, "step": 75250 }, { "epoch": 0.4473610690063068, "grad_norm": 1.7949962615966797, "learning_rate": 0.00019868044372777955, "loss": 0.6692736625671387, "step": 75260 }, { "epoch": 0.4474205110829752, "grad_norm": 1.7955399751663208, "learning_rate": 0.00019867938149438814, "loss": 0.7138955116271972, "step": 75270 }, { "epoch": 0.44747995315964356, "grad_norm": 1.4968105554580688, "learning_rate": 0.00019867831883678354, "loss": 0.6751905918121338, "step": 75280 }, { "epoch": 0.447539395236312, "grad_norm": 1.619783639907837, "learning_rate": 0.00019867725575497085, "loss": 0.6712644100189209, "step": 75290 }, { "epoch": 0.4475988373129804, "grad_norm": 1.7741703987121582, "learning_rate": 0.00019867619224895515, "loss": 0.6666516304016114, "step": 75300 }, { "epoch": 0.44765827938964875, "grad_norm": 1.9368271827697754, "learning_rate": 0.0001986751283187415, "loss": 0.7310287475585937, "step": 75310 }, { "epoch": 0.44771772146631716, "grad_norm": 1.6686413288116455, "learning_rate": 0.00019867406396433505, "loss": 0.6245974540710449, "step": 75320 }, { "epoch": 0.4477771635429855, "grad_norm": 1.7312840223312378, "learning_rate": 0.00019867299918574084, "loss": 0.7198213100433349, "step": 75330 }, { "epoch": 0.44783660561965394, "grad_norm": 1.415376901626587, "learning_rate": 0.000198671933982964, "loss": 0.5929860591888427, "step": 75340 }, { "epoch": 0.4478960476963223, "grad_norm": 2.039128303527832, "learning_rate": 0.0001986708683560096, "loss": 0.7498582363128662, "step": 75350 }, { "epoch": 0.4479554897729907, "grad_norm": 1.9468694925308228, "learning_rate": 0.00019866980230488272, "loss": 0.7297705173492431, "step": 75360 }, { "epoch": 0.4480149318496591, "grad_norm": 1.611299991607666, "learning_rate": 0.00019866873582958852, "loss": 0.6620580673217773, "step": 75370 }, { "epoch": 0.4480743739263275, "grad_norm": 1.5807337760925293, "learning_rate": 0.00019866766893013204, "loss": 0.6772478103637696, "step": 75380 }, { "epoch": 0.4481338160029959, "grad_norm": 1.4006707668304443, "learning_rate": 0.0001986666016065184, "loss": 0.7350257873535156, "step": 75390 }, { "epoch": 0.44819325807966426, "grad_norm": 1.411541223526001, "learning_rate": 0.00019866553385875275, "loss": 0.6897101402282715, "step": 75400 }, { "epoch": 0.4482527001563327, "grad_norm": 1.827722191810608, "learning_rate": 0.00019866446568684014, "loss": 0.6801608085632325, "step": 75410 }, { "epoch": 0.44831214223300103, "grad_norm": 1.5466200113296509, "learning_rate": 0.0001986633970907857, "loss": 0.6479371547698974, "step": 75420 }, { "epoch": 0.44837158430966945, "grad_norm": 1.4904671907424927, "learning_rate": 0.00019866232807059454, "loss": 0.7155178546905517, "step": 75430 }, { "epoch": 0.4484310263863378, "grad_norm": 1.5579288005828857, "learning_rate": 0.00019866125862627178, "loss": 0.7179826736450196, "step": 75440 }, { "epoch": 0.4484904684630062, "grad_norm": 1.4310005903244019, "learning_rate": 0.00019866018875782255, "loss": 0.7308884620666504, "step": 75450 }, { "epoch": 0.44854991053967463, "grad_norm": 1.5575814247131348, "learning_rate": 0.00019865911846525194, "loss": 0.7402033805847168, "step": 75460 }, { "epoch": 0.448609352616343, "grad_norm": 1.7118943929672241, "learning_rate": 0.00019865804774856508, "loss": 0.7250038146972656, "step": 75470 }, { "epoch": 0.4486687946930114, "grad_norm": 2.060694456100464, "learning_rate": 0.00019865697660776709, "loss": 0.6451838970184326, "step": 75480 }, { "epoch": 0.44872823676967977, "grad_norm": 1.6898891925811768, "learning_rate": 0.0001986559050428631, "loss": 0.711763858795166, "step": 75490 }, { "epoch": 0.4487876788463482, "grad_norm": 1.4505752325057983, "learning_rate": 0.00019865483305385825, "loss": 0.7226545333862304, "step": 75500 }, { "epoch": 0.44884712092301654, "grad_norm": 2.304892063140869, "learning_rate": 0.00019865376064075765, "loss": 0.660194206237793, "step": 75510 }, { "epoch": 0.44890656299968495, "grad_norm": 1.6260161399841309, "learning_rate": 0.0001986526878035664, "loss": 0.6468375205993653, "step": 75520 }, { "epoch": 0.44896600507635337, "grad_norm": 1.5107812881469727, "learning_rate": 0.00019865161454228966, "loss": 0.6641344547271728, "step": 75530 }, { "epoch": 0.44902544715302173, "grad_norm": 1.3791863918304443, "learning_rate": 0.0001986505408569326, "loss": 0.6479006290435791, "step": 75540 }, { "epoch": 0.44908488922969014, "grad_norm": 1.6497708559036255, "learning_rate": 0.0001986494667475003, "loss": 0.6613618850708007, "step": 75550 }, { "epoch": 0.4491443313063585, "grad_norm": 1.3706653118133545, "learning_rate": 0.00019864839221399793, "loss": 0.678455114364624, "step": 75560 }, { "epoch": 0.4492037733830269, "grad_norm": 1.4189854860305786, "learning_rate": 0.00019864731725643064, "loss": 0.7035648345947265, "step": 75570 }, { "epoch": 0.4492632154596953, "grad_norm": 1.9102224111557007, "learning_rate": 0.00019864624187480357, "loss": 0.7018396377563476, "step": 75580 }, { "epoch": 0.4493226575363637, "grad_norm": 2.3436243534088135, "learning_rate": 0.0001986451660691218, "loss": 0.644904899597168, "step": 75590 }, { "epoch": 0.4493820996130321, "grad_norm": 1.861263394355774, "learning_rate": 0.00019864408983939053, "loss": 0.6706608772277832, "step": 75600 }, { "epoch": 0.44944154168970046, "grad_norm": 1.8362139463424683, "learning_rate": 0.00019864301318561493, "loss": 0.6696643829345703, "step": 75610 }, { "epoch": 0.4495009837663689, "grad_norm": 1.552777647972107, "learning_rate": 0.0001986419361078001, "loss": 0.6336251258850097, "step": 75620 }, { "epoch": 0.44956042584303724, "grad_norm": 1.4916393756866455, "learning_rate": 0.00019864085860595124, "loss": 0.6717499256134033, "step": 75630 }, { "epoch": 0.44961986791970565, "grad_norm": 1.9515573978424072, "learning_rate": 0.00019863978068007348, "loss": 0.6446584224700928, "step": 75640 }, { "epoch": 0.449679309996374, "grad_norm": 1.6736751794815063, "learning_rate": 0.00019863870233017197, "loss": 0.7055916786193848, "step": 75650 }, { "epoch": 0.4497387520730424, "grad_norm": 1.344616413116455, "learning_rate": 0.00019863762355625187, "loss": 0.6648826599121094, "step": 75660 }, { "epoch": 0.44979819414971084, "grad_norm": 1.6110248565673828, "learning_rate": 0.00019863654435831832, "loss": 0.6673806667327881, "step": 75670 }, { "epoch": 0.4498576362263792, "grad_norm": 1.5697041749954224, "learning_rate": 0.00019863546473637656, "loss": 0.696787166595459, "step": 75680 }, { "epoch": 0.4499170783030476, "grad_norm": 1.501742959022522, "learning_rate": 0.00019863438469043169, "loss": 0.7065604209899903, "step": 75690 }, { "epoch": 0.44997652037971597, "grad_norm": 1.6382025480270386, "learning_rate": 0.00019863330422048887, "loss": 0.7309366226196289, "step": 75700 }, { "epoch": 0.4500359624563844, "grad_norm": 1.4824457168579102, "learning_rate": 0.0001986322233265533, "loss": 0.6577757835388184, "step": 75710 }, { "epoch": 0.45009540453305275, "grad_norm": 1.5206702947616577, "learning_rate": 0.00019863114200863015, "loss": 0.719080114364624, "step": 75720 }, { "epoch": 0.45015484660972116, "grad_norm": 1.614903211593628, "learning_rate": 0.00019863006026672454, "loss": 0.70462007522583, "step": 75730 }, { "epoch": 0.4502142886863896, "grad_norm": 1.792566180229187, "learning_rate": 0.00019862897810084173, "loss": 0.687498664855957, "step": 75740 }, { "epoch": 0.45027373076305793, "grad_norm": 1.5048593282699585, "learning_rate": 0.00019862789551098684, "loss": 0.7210640907287598, "step": 75750 }, { "epoch": 0.45033317283972635, "grad_norm": 1.8133503198623657, "learning_rate": 0.00019862681249716504, "loss": 0.6784915924072266, "step": 75760 }, { "epoch": 0.4503926149163947, "grad_norm": 1.7952851057052612, "learning_rate": 0.00019862572905938154, "loss": 0.6954524040222168, "step": 75770 }, { "epoch": 0.4504520569930631, "grad_norm": 1.7929023504257202, "learning_rate": 0.00019862464519764154, "loss": 0.6739592552185059, "step": 75780 }, { "epoch": 0.4505114990697315, "grad_norm": 1.7256250381469727, "learning_rate": 0.00019862356091195017, "loss": 0.7037076950073242, "step": 75790 }, { "epoch": 0.4505709411463999, "grad_norm": 1.8260643482208252, "learning_rate": 0.0001986224762023127, "loss": 0.7292201519012451, "step": 75800 }, { "epoch": 0.45063038322306825, "grad_norm": 1.7492440938949585, "learning_rate": 0.00019862139106873423, "loss": 0.7267288208007813, "step": 75810 }, { "epoch": 0.45068982529973667, "grad_norm": 1.9550660848617554, "learning_rate": 0.00019862030551121997, "loss": 0.6792519569396973, "step": 75820 }, { "epoch": 0.4507492673764051, "grad_norm": 1.614656925201416, "learning_rate": 0.00019861921952977517, "loss": 0.6419238567352294, "step": 75830 }, { "epoch": 0.45080870945307344, "grad_norm": 1.7317408323287964, "learning_rate": 0.00019861813312440493, "loss": 0.6986351013183594, "step": 75840 }, { "epoch": 0.45086815152974186, "grad_norm": 1.8161113262176514, "learning_rate": 0.00019861704629511458, "loss": 0.6284996032714844, "step": 75850 }, { "epoch": 0.4509275936064102, "grad_norm": 1.497568964958191, "learning_rate": 0.00019861595904190917, "loss": 0.7073460578918457, "step": 75860 }, { "epoch": 0.45098703568307863, "grad_norm": 1.5013291835784912, "learning_rate": 0.000198614871364794, "loss": 0.7682402610778809, "step": 75870 }, { "epoch": 0.451046477759747, "grad_norm": 1.876139521598816, "learning_rate": 0.00019861378326377425, "loss": 0.6808657646179199, "step": 75880 }, { "epoch": 0.4511059198364154, "grad_norm": 1.633963704109192, "learning_rate": 0.0001986126947388551, "loss": 0.7113764762878418, "step": 75890 }, { "epoch": 0.4511653619130838, "grad_norm": 1.8694283962249756, "learning_rate": 0.0001986116057900418, "loss": 0.7207727432250977, "step": 75900 }, { "epoch": 0.4512248039897522, "grad_norm": 1.8205479383468628, "learning_rate": 0.0001986105164173395, "loss": 0.6960280418395997, "step": 75910 }, { "epoch": 0.4512842460664206, "grad_norm": 1.2458101511001587, "learning_rate": 0.0001986094266207535, "loss": 0.6606973648071289, "step": 75920 }, { "epoch": 0.45134368814308895, "grad_norm": 1.903404712677002, "learning_rate": 0.00019860833640028894, "loss": 0.7460275173187256, "step": 75930 }, { "epoch": 0.45140313021975736, "grad_norm": 1.4099375009536743, "learning_rate": 0.00019860724575595102, "loss": 0.6524591445922852, "step": 75940 }, { "epoch": 0.4514625722964257, "grad_norm": 1.954068899154663, "learning_rate": 0.00019860615468774505, "loss": 0.6529912948608398, "step": 75950 }, { "epoch": 0.45152201437309414, "grad_norm": 1.8761882781982422, "learning_rate": 0.00019860506319567615, "loss": 0.7297670364379882, "step": 75960 }, { "epoch": 0.45158145644976255, "grad_norm": 1.8341110944747925, "learning_rate": 0.00019860397127974958, "loss": 0.7365108013153077, "step": 75970 }, { "epoch": 0.4516408985264309, "grad_norm": 2.06097674369812, "learning_rate": 0.00019860287893997062, "loss": 0.7090987205505371, "step": 75980 }, { "epoch": 0.4517003406030993, "grad_norm": 1.131372332572937, "learning_rate": 0.00019860178617634442, "loss": 0.6576294422149658, "step": 75990 }, { "epoch": 0.4517597826797677, "grad_norm": 1.9070415496826172, "learning_rate": 0.0001986006929888762, "loss": 0.7667892456054688, "step": 76000 }, { "epoch": 0.4518192247564361, "grad_norm": 1.569762945175171, "learning_rate": 0.00019859959937757124, "loss": 0.6684210777282715, "step": 76010 }, { "epoch": 0.45187866683310446, "grad_norm": 1.8570444583892822, "learning_rate": 0.00019859850534243475, "loss": 0.6801468372344971, "step": 76020 }, { "epoch": 0.4519381089097729, "grad_norm": 1.6322342157363892, "learning_rate": 0.00019859741088347198, "loss": 0.6485294818878173, "step": 76030 }, { "epoch": 0.4519975509864413, "grad_norm": 1.9430831670761108, "learning_rate": 0.00019859631600068812, "loss": 0.6814464569091797, "step": 76040 }, { "epoch": 0.45205699306310965, "grad_norm": 1.652716040611267, "learning_rate": 0.0001985952206940885, "loss": 0.7227901458740235, "step": 76050 }, { "epoch": 0.45211643513977806, "grad_norm": 1.6632587909698486, "learning_rate": 0.00019859412496367823, "loss": 0.7627665042877197, "step": 76060 }, { "epoch": 0.4521758772164464, "grad_norm": 1.6025614738464355, "learning_rate": 0.00019859302880946266, "loss": 0.7300882339477539, "step": 76070 }, { "epoch": 0.45223531929311483, "grad_norm": 1.6275242567062378, "learning_rate": 0.00019859193223144695, "loss": 0.6741738319396973, "step": 76080 }, { "epoch": 0.4522947613697832, "grad_norm": 1.5419857501983643, "learning_rate": 0.0001985908352296364, "loss": 0.7084826946258544, "step": 76090 }, { "epoch": 0.4523542034464516, "grad_norm": 1.7193145751953125, "learning_rate": 0.00019858973780403628, "loss": 0.6558402061462403, "step": 76100 }, { "epoch": 0.45241364552312, "grad_norm": 1.5772103071212769, "learning_rate": 0.00019858863995465177, "loss": 0.6649884223937989, "step": 76110 }, { "epoch": 0.4524730875997884, "grad_norm": 1.9049856662750244, "learning_rate": 0.0001985875416814882, "loss": 0.7398046493530274, "step": 76120 }, { "epoch": 0.4525325296764568, "grad_norm": 1.8707648515701294, "learning_rate": 0.00019858644298455073, "loss": 0.7401480674743652, "step": 76130 }, { "epoch": 0.45259197175312516, "grad_norm": 2.090677499771118, "learning_rate": 0.0001985853438638447, "loss": 0.6450422763824463, "step": 76140 }, { "epoch": 0.45265141382979357, "grad_norm": 2.123999834060669, "learning_rate": 0.00019858424431937535, "loss": 0.7023880004882812, "step": 76150 }, { "epoch": 0.45271085590646193, "grad_norm": 1.7514232397079468, "learning_rate": 0.00019858314435114788, "loss": 0.7378216743469238, "step": 76160 }, { "epoch": 0.45277029798313034, "grad_norm": 1.4884141683578491, "learning_rate": 0.00019858204395916762, "loss": 0.6874414443969726, "step": 76170 }, { "epoch": 0.4528297400597987, "grad_norm": 1.5314950942993164, "learning_rate": 0.0001985809431434398, "loss": 0.6678389549255371, "step": 76180 }, { "epoch": 0.4528891821364671, "grad_norm": 1.6516846418380737, "learning_rate": 0.00019857984190396971, "loss": 0.6123906135559082, "step": 76190 }, { "epoch": 0.45294862421313553, "grad_norm": 1.8183282613754272, "learning_rate": 0.00019857874024076263, "loss": 0.6931187629699707, "step": 76200 }, { "epoch": 0.4530080662898039, "grad_norm": 1.8775264024734497, "learning_rate": 0.00019857763815382375, "loss": 0.6625144958496094, "step": 76210 }, { "epoch": 0.4530675083664723, "grad_norm": 1.9505523443222046, "learning_rate": 0.0001985765356431584, "loss": 0.687302827835083, "step": 76220 }, { "epoch": 0.45312695044314066, "grad_norm": 1.4643222093582153, "learning_rate": 0.00019857543270877188, "loss": 0.6667008876800538, "step": 76230 }, { "epoch": 0.4531863925198091, "grad_norm": 1.7505817413330078, "learning_rate": 0.00019857432935066943, "loss": 0.6958268165588379, "step": 76240 }, { "epoch": 0.45324583459647744, "grad_norm": 1.6594104766845703, "learning_rate": 0.00019857322556885633, "loss": 0.6895517349243164, "step": 76250 }, { "epoch": 0.45330527667314585, "grad_norm": 2.1168763637542725, "learning_rate": 0.00019857212136333786, "loss": 0.633977222442627, "step": 76260 }, { "epoch": 0.45336471874981427, "grad_norm": 1.8698712587356567, "learning_rate": 0.00019857101673411933, "loss": 0.7355323314666748, "step": 76270 }, { "epoch": 0.4534241608264826, "grad_norm": 1.7234917879104614, "learning_rate": 0.000198569911681206, "loss": 0.6829826354980468, "step": 76280 }, { "epoch": 0.45348360290315104, "grad_norm": 1.7316150665283203, "learning_rate": 0.00019856880620460314, "loss": 0.7803798675537109, "step": 76290 }, { "epoch": 0.4535430449798194, "grad_norm": 1.8935127258300781, "learning_rate": 0.00019856770030431603, "loss": 0.6879415512084961, "step": 76300 }, { "epoch": 0.4536024870564878, "grad_norm": 1.8239840269088745, "learning_rate": 0.00019856659398035002, "loss": 0.7012556552886963, "step": 76310 }, { "epoch": 0.45366192913315617, "grad_norm": 1.4912463426589966, "learning_rate": 0.0001985654872327104, "loss": 0.6686934947967529, "step": 76320 }, { "epoch": 0.4537213712098246, "grad_norm": 1.5695780515670776, "learning_rate": 0.00019856438006140239, "loss": 0.6321417808532714, "step": 76330 }, { "epoch": 0.453780813286493, "grad_norm": 1.924509048461914, "learning_rate": 0.00019856327246643132, "loss": 0.6584887504577637, "step": 76340 }, { "epoch": 0.45384025536316136, "grad_norm": 1.694934606552124, "learning_rate": 0.00019856216444780252, "loss": 0.6578036308288574, "step": 76350 }, { "epoch": 0.4538996974398298, "grad_norm": 1.6590209007263184, "learning_rate": 0.00019856105600552125, "loss": 0.6517784118652343, "step": 76360 }, { "epoch": 0.45395913951649813, "grad_norm": 1.5984547138214111, "learning_rate": 0.00019855994713959284, "loss": 0.6784192085266113, "step": 76370 }, { "epoch": 0.45401858159316655, "grad_norm": 1.5911483764648438, "learning_rate": 0.00019855883785002262, "loss": 0.6511656761169433, "step": 76380 }, { "epoch": 0.4540780236698349, "grad_norm": 1.9959126710891724, "learning_rate": 0.0001985577281368158, "loss": 0.7731689929962158, "step": 76390 }, { "epoch": 0.4541374657465033, "grad_norm": 1.5576781034469604, "learning_rate": 0.00019855661799997779, "loss": 0.6555347919464112, "step": 76400 }, { "epoch": 0.45419690782317174, "grad_norm": 1.4345145225524902, "learning_rate": 0.00019855550743951383, "loss": 0.6431631088256836, "step": 76410 }, { "epoch": 0.4542563498998401, "grad_norm": 1.7580312490463257, "learning_rate": 0.0001985543964554293, "loss": 0.7077673435211181, "step": 76420 }, { "epoch": 0.4543157919765085, "grad_norm": 1.9387214183807373, "learning_rate": 0.00019855328504772942, "loss": 0.6048148155212403, "step": 76430 }, { "epoch": 0.45437523405317687, "grad_norm": 1.7635363340377808, "learning_rate": 0.00019855217321641962, "loss": 0.6981348514556884, "step": 76440 }, { "epoch": 0.4544346761298453, "grad_norm": 1.7038612365722656, "learning_rate": 0.00019855106096150512, "loss": 0.6778035163879395, "step": 76450 }, { "epoch": 0.45449411820651364, "grad_norm": 1.4454855918884277, "learning_rate": 0.00019854994828299131, "loss": 0.6288235664367676, "step": 76460 }, { "epoch": 0.45455356028318206, "grad_norm": 1.6325786113739014, "learning_rate": 0.0001985488351808835, "loss": 0.7253405094146729, "step": 76470 }, { "epoch": 0.45461300235985047, "grad_norm": 1.5604431629180908, "learning_rate": 0.00019854772165518698, "loss": 0.6701310634613037, "step": 76480 }, { "epoch": 0.45467244443651883, "grad_norm": 1.539363145828247, "learning_rate": 0.00019854660770590707, "loss": 0.7372848510742187, "step": 76490 }, { "epoch": 0.45473188651318724, "grad_norm": 1.951220989227295, "learning_rate": 0.00019854549333304917, "loss": 0.7150026321411133, "step": 76500 }, { "epoch": 0.4547913285898556, "grad_norm": 1.5329139232635498, "learning_rate": 0.00019854437853661857, "loss": 0.627318000793457, "step": 76510 }, { "epoch": 0.454850770666524, "grad_norm": 1.8605679273605347, "learning_rate": 0.00019854326331662057, "loss": 0.7425715446472168, "step": 76520 }, { "epoch": 0.4549102127431924, "grad_norm": 1.2932345867156982, "learning_rate": 0.00019854214767306053, "loss": 0.6893902778625488, "step": 76530 }, { "epoch": 0.4549696548198608, "grad_norm": 1.3951996564865112, "learning_rate": 0.00019854103160594382, "loss": 0.6715542793273925, "step": 76540 }, { "epoch": 0.45502909689652915, "grad_norm": 1.532091498374939, "learning_rate": 0.00019853991511527573, "loss": 0.6969392776489258, "step": 76550 }, { "epoch": 0.45508853897319756, "grad_norm": 1.4566887617111206, "learning_rate": 0.00019853879820106162, "loss": 0.6697628974914551, "step": 76560 }, { "epoch": 0.455147981049866, "grad_norm": 1.551421880722046, "learning_rate": 0.00019853768086330683, "loss": 0.6574020385742188, "step": 76570 }, { "epoch": 0.45520742312653434, "grad_norm": 1.8974767923355103, "learning_rate": 0.00019853656310201673, "loss": 0.6916206359863282, "step": 76580 }, { "epoch": 0.45526686520320275, "grad_norm": 1.7988842725753784, "learning_rate": 0.00019853544491719665, "loss": 0.6473526954650879, "step": 76590 }, { "epoch": 0.4553263072798711, "grad_norm": 2.349522113800049, "learning_rate": 0.00019853432630885195, "loss": 0.6320278167724609, "step": 76600 }, { "epoch": 0.4553857493565395, "grad_norm": 1.9546380043029785, "learning_rate": 0.00019853320727698792, "loss": 0.7426102638244629, "step": 76610 }, { "epoch": 0.4554451914332079, "grad_norm": 1.9629294872283936, "learning_rate": 0.00019853208782160997, "loss": 0.6855494499206543, "step": 76620 }, { "epoch": 0.4555046335098763, "grad_norm": 1.726326584815979, "learning_rate": 0.00019853096794272346, "loss": 0.6972586631774902, "step": 76630 }, { "epoch": 0.4555640755865447, "grad_norm": 1.4979026317596436, "learning_rate": 0.00019852984764033373, "loss": 0.6562488555908204, "step": 76640 }, { "epoch": 0.4556235176632131, "grad_norm": 1.6264574527740479, "learning_rate": 0.00019852872691444612, "loss": 0.6557681083679199, "step": 76650 }, { "epoch": 0.4556829597398815, "grad_norm": 1.7471708059310913, "learning_rate": 0.00019852760576506603, "loss": 0.6830150604248046, "step": 76660 }, { "epoch": 0.45574240181654985, "grad_norm": 1.6144740581512451, "learning_rate": 0.00019852648419219882, "loss": 0.6916094303131104, "step": 76670 }, { "epoch": 0.45580184389321826, "grad_norm": 2.023172616958618, "learning_rate": 0.0001985253621958498, "loss": 0.6913226127624512, "step": 76680 }, { "epoch": 0.4558612859698866, "grad_norm": 1.715608835220337, "learning_rate": 0.00019852423977602442, "loss": 0.6870394706726074, "step": 76690 }, { "epoch": 0.45592072804655503, "grad_norm": 1.8752683401107788, "learning_rate": 0.00019852311693272797, "loss": 0.6740527153015137, "step": 76700 }, { "epoch": 0.45598017012322345, "grad_norm": 2.0778706073760986, "learning_rate": 0.00019852199366596592, "loss": 0.731527042388916, "step": 76710 }, { "epoch": 0.4560396121998918, "grad_norm": 1.7902008295059204, "learning_rate": 0.0001985208699757435, "loss": 0.6209424018859864, "step": 76720 }, { "epoch": 0.4560990542765602, "grad_norm": 1.7482575178146362, "learning_rate": 0.0001985197458620662, "loss": 0.7072010993957519, "step": 76730 }, { "epoch": 0.4561584963532286, "grad_norm": 1.6634340286254883, "learning_rate": 0.0001985186213249394, "loss": 0.6987354278564453, "step": 76740 }, { "epoch": 0.456217938429897, "grad_norm": 1.506132960319519, "learning_rate": 0.00019851749636436841, "loss": 0.658149242401123, "step": 76750 }, { "epoch": 0.45627738050656536, "grad_norm": 1.9186893701553345, "learning_rate": 0.00019851637098035864, "loss": 0.6877685070037842, "step": 76760 }, { "epoch": 0.45633682258323377, "grad_norm": 2.1106882095336914, "learning_rate": 0.0001985152451729155, "loss": 0.6872340202331543, "step": 76770 }, { "epoch": 0.4563962646599022, "grad_norm": 1.5218467712402344, "learning_rate": 0.00019851411894204431, "loss": 0.6712403297424316, "step": 76780 }, { "epoch": 0.45645570673657054, "grad_norm": 1.6410653591156006, "learning_rate": 0.00019851299228775053, "loss": 0.6594444751739502, "step": 76790 }, { "epoch": 0.45651514881323896, "grad_norm": 1.5098731517791748, "learning_rate": 0.00019851186521003956, "loss": 0.6087462425231933, "step": 76800 }, { "epoch": 0.4565745908899073, "grad_norm": 1.5010082721710205, "learning_rate": 0.0001985107377089167, "loss": 0.6801142692565918, "step": 76810 }, { "epoch": 0.45663403296657573, "grad_norm": 1.5247496366500854, "learning_rate": 0.0001985096097843874, "loss": 0.775143814086914, "step": 76820 }, { "epoch": 0.4566934750432441, "grad_norm": 1.6396448612213135, "learning_rate": 0.00019850848143645707, "loss": 0.7277976036071777, "step": 76830 }, { "epoch": 0.4567529171199125, "grad_norm": 1.5302983522415161, "learning_rate": 0.0001985073526651311, "loss": 0.687416934967041, "step": 76840 }, { "epoch": 0.4568123591965809, "grad_norm": 1.7956336736679077, "learning_rate": 0.00019850622347041488, "loss": 0.6598863124847412, "step": 76850 }, { "epoch": 0.4568718012732493, "grad_norm": 1.6572641134262085, "learning_rate": 0.00019850509385231378, "loss": 0.6243202686309814, "step": 76860 }, { "epoch": 0.4569312433499177, "grad_norm": 1.7110952138900757, "learning_rate": 0.00019850396381083325, "loss": 0.6873217105865479, "step": 76870 }, { "epoch": 0.45699068542658605, "grad_norm": 1.7218116521835327, "learning_rate": 0.0001985028333459787, "loss": 0.6827648162841797, "step": 76880 }, { "epoch": 0.45705012750325447, "grad_norm": 1.6349127292633057, "learning_rate": 0.00019850170245775547, "loss": 0.7489714622497559, "step": 76890 }, { "epoch": 0.4571095695799228, "grad_norm": 1.6483596563339233, "learning_rate": 0.00019850057114616904, "loss": 0.6361219406127929, "step": 76900 }, { "epoch": 0.45716901165659124, "grad_norm": 1.668884515762329, "learning_rate": 0.0001984994394112248, "loss": 0.6864982604980469, "step": 76910 }, { "epoch": 0.4572284537332596, "grad_norm": 1.9440380334854126, "learning_rate": 0.0001984983072529282, "loss": 0.7171134948730469, "step": 76920 }, { "epoch": 0.457287895809928, "grad_norm": 1.7475069761276245, "learning_rate": 0.0001984971746712846, "loss": 0.7300334930419922, "step": 76930 }, { "epoch": 0.45734733788659643, "grad_norm": 1.6655272245407104, "learning_rate": 0.00019849604166629942, "loss": 0.7259975433349609, "step": 76940 }, { "epoch": 0.4574067799632648, "grad_norm": 1.3763108253479004, "learning_rate": 0.0001984949082379781, "loss": 0.7216351509094239, "step": 76950 }, { "epoch": 0.4574662220399332, "grad_norm": 2.096336603164673, "learning_rate": 0.00019849377438632609, "loss": 0.6584989547729492, "step": 76960 }, { "epoch": 0.45752566411660156, "grad_norm": 1.8048077821731567, "learning_rate": 0.00019849264011134873, "loss": 0.7413007736206054, "step": 76970 }, { "epoch": 0.45758510619327, "grad_norm": 1.455963134765625, "learning_rate": 0.00019849150541305152, "loss": 0.7111275672912598, "step": 76980 }, { "epoch": 0.45764454826993833, "grad_norm": 1.7096644639968872, "learning_rate": 0.0001984903702914399, "loss": 0.7328550338745117, "step": 76990 }, { "epoch": 0.45770399034660675, "grad_norm": 1.414401888847351, "learning_rate": 0.00019848923474651922, "loss": 0.6693349361419678, "step": 77000 }, { "epoch": 0.45776343242327516, "grad_norm": 2.1332690715789795, "learning_rate": 0.000198488098778295, "loss": 0.7055886745452881, "step": 77010 }, { "epoch": 0.4578228744999435, "grad_norm": 2.721390724182129, "learning_rate": 0.00019848696238677262, "loss": 0.6768301963806153, "step": 77020 }, { "epoch": 0.45788231657661194, "grad_norm": 1.9361708164215088, "learning_rate": 0.0001984858255719575, "loss": 0.650592041015625, "step": 77030 }, { "epoch": 0.4579417586532803, "grad_norm": 1.8122358322143555, "learning_rate": 0.00019848468833385516, "loss": 0.6593879699707031, "step": 77040 }, { "epoch": 0.4580012007299487, "grad_norm": 1.3743308782577515, "learning_rate": 0.00019848355067247098, "loss": 0.6597084045410156, "step": 77050 }, { "epoch": 0.45806064280661707, "grad_norm": 1.9684760570526123, "learning_rate": 0.00019848241258781037, "loss": 0.7403290748596192, "step": 77060 }, { "epoch": 0.4581200848832855, "grad_norm": 1.4344124794006348, "learning_rate": 0.00019848127407987885, "loss": 0.6954391002655029, "step": 77070 }, { "epoch": 0.4581795269599539, "grad_norm": 2.0868284702301025, "learning_rate": 0.0001984801351486818, "loss": 0.6633023262023926, "step": 77080 }, { "epoch": 0.45823896903662226, "grad_norm": 1.7602554559707642, "learning_rate": 0.00019847899579422473, "loss": 0.7153804779052735, "step": 77090 }, { "epoch": 0.45829841111329067, "grad_norm": 1.386203646659851, "learning_rate": 0.00019847785601651306, "loss": 0.6778989791870117, "step": 77100 }, { "epoch": 0.45835785318995903, "grad_norm": 1.8364962339401245, "learning_rate": 0.0001984767158155522, "loss": 0.6793052673339843, "step": 77110 }, { "epoch": 0.45841729526662744, "grad_norm": 1.4810525178909302, "learning_rate": 0.00019847557519134766, "loss": 0.6960502147674561, "step": 77120 }, { "epoch": 0.4584767373432958, "grad_norm": 1.3948476314544678, "learning_rate": 0.00019847443414390493, "loss": 0.6876343250274658, "step": 77130 }, { "epoch": 0.4585361794199642, "grad_norm": 1.5088245868682861, "learning_rate": 0.00019847329267322936, "loss": 0.6544841766357422, "step": 77140 }, { "epoch": 0.45859562149663263, "grad_norm": 1.82227623462677, "learning_rate": 0.00019847215077932652, "loss": 0.7611496448516846, "step": 77150 }, { "epoch": 0.458655063573301, "grad_norm": 1.4459078311920166, "learning_rate": 0.0001984710084622018, "loss": 0.6822659492492675, "step": 77160 }, { "epoch": 0.4587145056499694, "grad_norm": 1.5987859964370728, "learning_rate": 0.00019846986572186068, "loss": 0.6923130035400391, "step": 77170 }, { "epoch": 0.45877394772663777, "grad_norm": 1.916438102722168, "learning_rate": 0.00019846872255830866, "loss": 0.6672832012176514, "step": 77180 }, { "epoch": 0.4588333898033062, "grad_norm": 1.616703748703003, "learning_rate": 0.00019846757897155117, "loss": 0.678028154373169, "step": 77190 }, { "epoch": 0.45889283187997454, "grad_norm": 1.6397197246551514, "learning_rate": 0.0001984664349615937, "loss": 0.6927668571472168, "step": 77200 }, { "epoch": 0.45895227395664295, "grad_norm": 1.473604440689087, "learning_rate": 0.00019846529052844168, "loss": 0.6825284957885742, "step": 77210 }, { "epoch": 0.4590117160333113, "grad_norm": 1.8142244815826416, "learning_rate": 0.0001984641456721007, "loss": 0.7187467575073242, "step": 77220 }, { "epoch": 0.4590711581099797, "grad_norm": 1.5557825565338135, "learning_rate": 0.00019846300039257607, "loss": 0.6886707782745362, "step": 77230 }, { "epoch": 0.45913060018664814, "grad_norm": 1.952165126800537, "learning_rate": 0.00019846185468987338, "loss": 0.6419553279876709, "step": 77240 }, { "epoch": 0.4591900422633165, "grad_norm": 1.7199288606643677, "learning_rate": 0.0001984607085639981, "loss": 0.6820701599121094, "step": 77250 }, { "epoch": 0.4592494843399849, "grad_norm": 1.4952921867370605, "learning_rate": 0.0001984595620149557, "loss": 0.6014223098754883, "step": 77260 }, { "epoch": 0.4593089264166533, "grad_norm": 1.6875311136245728, "learning_rate": 0.00019845841504275168, "loss": 0.6926761150360108, "step": 77270 }, { "epoch": 0.4593683684933217, "grad_norm": 1.1471261978149414, "learning_rate": 0.0001984572676473915, "loss": 0.6739529609680176, "step": 77280 }, { "epoch": 0.45942781056999005, "grad_norm": 1.8078187704086304, "learning_rate": 0.00019845611982888066, "loss": 0.6550318241119385, "step": 77290 }, { "epoch": 0.45948725264665846, "grad_norm": 1.5770270824432373, "learning_rate": 0.00019845497158722464, "loss": 0.7557415962219238, "step": 77300 }, { "epoch": 0.4595466947233269, "grad_norm": 1.7342606782913208, "learning_rate": 0.00019845382292242895, "loss": 0.6728894233703613, "step": 77310 }, { "epoch": 0.45960613679999524, "grad_norm": 1.865846872329712, "learning_rate": 0.00019845267383449905, "loss": 0.6821793556213379, "step": 77320 }, { "epoch": 0.45966557887666365, "grad_norm": 2.0282387733459473, "learning_rate": 0.00019845152432344053, "loss": 0.7331642150878906, "step": 77330 }, { "epoch": 0.459725020953332, "grad_norm": 1.41953706741333, "learning_rate": 0.00019845037438925874, "loss": 0.6707656860351563, "step": 77340 }, { "epoch": 0.4597844630300004, "grad_norm": 1.652397871017456, "learning_rate": 0.00019844922403195934, "loss": 0.6650324821472168, "step": 77350 }, { "epoch": 0.4598439051066688, "grad_norm": 1.8641486167907715, "learning_rate": 0.00019844807325154775, "loss": 0.6311684608459472, "step": 77360 }, { "epoch": 0.4599033471833372, "grad_norm": 1.7467678785324097, "learning_rate": 0.00019844692204802944, "loss": 0.698219108581543, "step": 77370 }, { "epoch": 0.4599627892600056, "grad_norm": 1.7235209941864014, "learning_rate": 0.00019844577042140996, "loss": 0.6415651321411133, "step": 77380 }, { "epoch": 0.46002223133667397, "grad_norm": 1.7032166719436646, "learning_rate": 0.00019844461837169485, "loss": 0.6697512626647949, "step": 77390 }, { "epoch": 0.4600816734133424, "grad_norm": 1.9682923555374146, "learning_rate": 0.0001984434658988896, "loss": 0.6674509048461914, "step": 77400 }, { "epoch": 0.46014111549001074, "grad_norm": 1.553381323814392, "learning_rate": 0.00019844231300299967, "loss": 0.6664210796356201, "step": 77410 }, { "epoch": 0.46020055756667916, "grad_norm": 1.5459634065628052, "learning_rate": 0.00019844115968403064, "loss": 0.6893688201904297, "step": 77420 }, { "epoch": 0.4602599996433475, "grad_norm": 1.753807544708252, "learning_rate": 0.00019844000594198798, "loss": 0.7754864692687988, "step": 77430 }, { "epoch": 0.46031944172001593, "grad_norm": 1.5934886932373047, "learning_rate": 0.00019843885177687728, "loss": 0.7068122863769531, "step": 77440 }, { "epoch": 0.46037888379668435, "grad_norm": 1.535375952720642, "learning_rate": 0.00019843769718870402, "loss": 0.7086007118225097, "step": 77450 }, { "epoch": 0.4604383258733527, "grad_norm": 1.7566927671432495, "learning_rate": 0.00019843654217747368, "loss": 0.6735947608947754, "step": 77460 }, { "epoch": 0.4604977679500211, "grad_norm": 1.924298644065857, "learning_rate": 0.0001984353867431918, "loss": 0.7085716247558593, "step": 77470 }, { "epoch": 0.4605572100266895, "grad_norm": 1.9241068363189697, "learning_rate": 0.00019843423088586402, "loss": 0.7212506294250488, "step": 77480 }, { "epoch": 0.4606166521033579, "grad_norm": 1.628650426864624, "learning_rate": 0.00019843307460549572, "loss": 0.7423159122467041, "step": 77490 }, { "epoch": 0.46067609418002625, "grad_norm": 2.04495906829834, "learning_rate": 0.0001984319179020925, "loss": 0.6873747825622558, "step": 77500 }, { "epoch": 0.46073553625669467, "grad_norm": 1.951106309890747, "learning_rate": 0.00019843076077565987, "loss": 0.6823129653930664, "step": 77510 }, { "epoch": 0.4607949783333631, "grad_norm": 1.621730923652649, "learning_rate": 0.00019842960322620338, "loss": 0.7343296051025391, "step": 77520 }, { "epoch": 0.46085442041003144, "grad_norm": 1.9824143648147583, "learning_rate": 0.00019842844525372859, "loss": 0.7050070762634277, "step": 77530 }, { "epoch": 0.46091386248669985, "grad_norm": 1.694664478302002, "learning_rate": 0.000198427286858241, "loss": 0.7232533454895019, "step": 77540 }, { "epoch": 0.4609733045633682, "grad_norm": 2.0167696475982666, "learning_rate": 0.00019842612803974618, "loss": 0.6426176071166992, "step": 77550 }, { "epoch": 0.46103274664003663, "grad_norm": 1.9669617414474487, "learning_rate": 0.00019842496879824965, "loss": 0.7154078483581543, "step": 77560 }, { "epoch": 0.461092188716705, "grad_norm": 1.28142249584198, "learning_rate": 0.00019842380913375697, "loss": 0.6496513366699219, "step": 77570 }, { "epoch": 0.4611516307933734, "grad_norm": 1.2434808015823364, "learning_rate": 0.0001984226490462737, "loss": 0.6516467094421386, "step": 77580 }, { "epoch": 0.46121107287004176, "grad_norm": 2.012683868408203, "learning_rate": 0.00019842148853580535, "loss": 0.7750527858734131, "step": 77590 }, { "epoch": 0.4612705149467102, "grad_norm": 1.6448770761489868, "learning_rate": 0.0001984203276023575, "loss": 0.6679322242736816, "step": 77600 }, { "epoch": 0.4613299570233786, "grad_norm": 1.4669150114059448, "learning_rate": 0.00019841916624593572, "loss": 0.6839345932006836, "step": 77610 }, { "epoch": 0.46138939910004695, "grad_norm": 1.3698149919509888, "learning_rate": 0.00019841800446654552, "loss": 0.7138843536376953, "step": 77620 }, { "epoch": 0.46144884117671536, "grad_norm": 2.0272109508514404, "learning_rate": 0.0001984168422641925, "loss": 0.6415456295013428, "step": 77630 }, { "epoch": 0.4615082832533837, "grad_norm": 2.206864356994629, "learning_rate": 0.0001984156796388822, "loss": 0.7337050437927246, "step": 77640 }, { "epoch": 0.46156772533005214, "grad_norm": 1.7200900316238403, "learning_rate": 0.0001984145165906202, "loss": 0.769203519821167, "step": 77650 }, { "epoch": 0.4616271674067205, "grad_norm": 1.555627465248108, "learning_rate": 0.000198413353119412, "loss": 0.6680094718933105, "step": 77660 }, { "epoch": 0.4616866094833889, "grad_norm": 1.7828881740570068, "learning_rate": 0.00019841218922526322, "loss": 0.6841167449951172, "step": 77670 }, { "epoch": 0.4617460515600573, "grad_norm": 2.4429101943969727, "learning_rate": 0.00019841102490817942, "loss": 0.7262710571289063, "step": 77680 }, { "epoch": 0.4618054936367257, "grad_norm": 1.6597882509231567, "learning_rate": 0.00019840986016816622, "loss": 0.7108452796936036, "step": 77690 }, { "epoch": 0.4618649357133941, "grad_norm": 1.4730616807937622, "learning_rate": 0.00019840869500522908, "loss": 0.6801209449768066, "step": 77700 }, { "epoch": 0.46192437779006246, "grad_norm": 1.611451268196106, "learning_rate": 0.00019840752941937366, "loss": 0.7655218124389649, "step": 77710 }, { "epoch": 0.46198381986673087, "grad_norm": 1.676775574684143, "learning_rate": 0.00019840636341060552, "loss": 0.6815931320190429, "step": 77720 }, { "epoch": 0.46204326194339923, "grad_norm": 1.7788134813308716, "learning_rate": 0.00019840519697893023, "loss": 0.76640944480896, "step": 77730 }, { "epoch": 0.46210270402006765, "grad_norm": 1.5796544551849365, "learning_rate": 0.00019840403012435335, "loss": 0.719690990447998, "step": 77740 }, { "epoch": 0.46216214609673606, "grad_norm": 1.8982524871826172, "learning_rate": 0.0001984028628468805, "loss": 0.6686097145080566, "step": 77750 }, { "epoch": 0.4622215881734044, "grad_norm": 1.5348656177520752, "learning_rate": 0.00019840169514651724, "loss": 0.6492423057556153, "step": 77760 }, { "epoch": 0.46228103025007283, "grad_norm": 1.8623126745224, "learning_rate": 0.00019840052702326918, "loss": 0.7031140327453613, "step": 77770 }, { "epoch": 0.4623404723267412, "grad_norm": 1.7196393013000488, "learning_rate": 0.00019839935847714183, "loss": 0.6939958572387696, "step": 77780 }, { "epoch": 0.4623999144034096, "grad_norm": 1.4350576400756836, "learning_rate": 0.0001983981895081409, "loss": 0.682034683227539, "step": 77790 }, { "epoch": 0.46245935648007797, "grad_norm": 1.683661699295044, "learning_rate": 0.00019839702011627188, "loss": 0.713472557067871, "step": 77800 }, { "epoch": 0.4625187985567464, "grad_norm": 1.7092159986495972, "learning_rate": 0.00019839585030154041, "loss": 0.6879871368408204, "step": 77810 }, { "epoch": 0.4625782406334148, "grad_norm": 1.8491820096969604, "learning_rate": 0.00019839468006395213, "loss": 0.6946446895599365, "step": 77820 }, { "epoch": 0.46263768271008315, "grad_norm": 1.3496778011322021, "learning_rate": 0.00019839350940351253, "loss": 0.6678252220153809, "step": 77830 }, { "epoch": 0.46269712478675157, "grad_norm": 1.8302828073501587, "learning_rate": 0.00019839233832022726, "loss": 0.6926304817199707, "step": 77840 }, { "epoch": 0.4627565668634199, "grad_norm": 1.4966044425964355, "learning_rate": 0.00019839116681410197, "loss": 0.6446815013885498, "step": 77850 }, { "epoch": 0.46281600894008834, "grad_norm": 1.580872654914856, "learning_rate": 0.0001983899948851422, "loss": 0.6072317123413086, "step": 77860 }, { "epoch": 0.4628754510167567, "grad_norm": 1.4401881694793701, "learning_rate": 0.00019838882253335357, "loss": 0.6754900932312011, "step": 77870 }, { "epoch": 0.4629348930934251, "grad_norm": 1.5089198350906372, "learning_rate": 0.00019838764975874175, "loss": 0.6706048965454101, "step": 77880 }, { "epoch": 0.46299433517009353, "grad_norm": 1.4687857627868652, "learning_rate": 0.00019838647656131227, "loss": 0.6570602893829346, "step": 77890 }, { "epoch": 0.4630537772467619, "grad_norm": 1.5914782285690308, "learning_rate": 0.00019838530294107075, "loss": 0.7309099197387695, "step": 77900 }, { "epoch": 0.4631132193234303, "grad_norm": 1.4043445587158203, "learning_rate": 0.00019838412889802286, "loss": 0.6782047271728515, "step": 77910 }, { "epoch": 0.46317266140009866, "grad_norm": 2.1629645824432373, "learning_rate": 0.00019838295443217418, "loss": 0.6915027618408203, "step": 77920 }, { "epoch": 0.4632321034767671, "grad_norm": 1.6291600465774536, "learning_rate": 0.0001983817795435303, "loss": 0.700928783416748, "step": 77930 }, { "epoch": 0.46329154555343544, "grad_norm": 1.8874977827072144, "learning_rate": 0.0001983806042320969, "loss": 0.6926952362060547, "step": 77940 }, { "epoch": 0.46335098763010385, "grad_norm": 1.4775279760360718, "learning_rate": 0.00019837942849787956, "loss": 0.6747538566589355, "step": 77950 }, { "epoch": 0.4634104297067722, "grad_norm": 1.3809014558792114, "learning_rate": 0.0001983782523408839, "loss": 0.6302282333374023, "step": 77960 }, { "epoch": 0.4634698717834406, "grad_norm": 1.8544100522994995, "learning_rate": 0.0001983770757611156, "loss": 0.7525849342346191, "step": 77970 }, { "epoch": 0.46352931386010904, "grad_norm": 1.7386170625686646, "learning_rate": 0.0001983758987585802, "loss": 0.6512042999267578, "step": 77980 }, { "epoch": 0.4635887559367774, "grad_norm": 1.6514909267425537, "learning_rate": 0.0001983747213332834, "loss": 0.6741939544677734, "step": 77990 }, { "epoch": 0.4636481980134458, "grad_norm": 1.8292335271835327, "learning_rate": 0.00019837354348523084, "loss": 0.6775514602661132, "step": 78000 }, { "epoch": 0.46370764009011417, "grad_norm": 1.6951850652694702, "learning_rate": 0.00019837236521442813, "loss": 0.6561476707458496, "step": 78010 }, { "epoch": 0.4637670821667826, "grad_norm": 1.531912922859192, "learning_rate": 0.00019837118652088088, "loss": 0.7560277938842773, "step": 78020 }, { "epoch": 0.46382652424345094, "grad_norm": 2.184868812561035, "learning_rate": 0.00019837000740459477, "loss": 0.720357084274292, "step": 78030 }, { "epoch": 0.46388596632011936, "grad_norm": 1.8411850929260254, "learning_rate": 0.00019836882786557542, "loss": 0.6435892105102539, "step": 78040 }, { "epoch": 0.4639454083967878, "grad_norm": 1.8364167213439941, "learning_rate": 0.00019836764790382848, "loss": 0.6918571472167969, "step": 78050 }, { "epoch": 0.46400485047345613, "grad_norm": 2.336552858352661, "learning_rate": 0.0001983664675193596, "loss": 0.7568251132965088, "step": 78060 }, { "epoch": 0.46406429255012455, "grad_norm": 2.239474058151245, "learning_rate": 0.0001983652867121744, "loss": 0.6974370956420899, "step": 78070 }, { "epoch": 0.4641237346267929, "grad_norm": 1.7297362089157104, "learning_rate": 0.00019836410548227854, "loss": 0.6983194351196289, "step": 78080 }, { "epoch": 0.4641831767034613, "grad_norm": 2.1607306003570557, "learning_rate": 0.00019836292382967768, "loss": 0.6740754604339599, "step": 78090 }, { "epoch": 0.4642426187801297, "grad_norm": 1.8049637079238892, "learning_rate": 0.00019836174175437746, "loss": 0.7526992797851563, "step": 78100 }, { "epoch": 0.4643020608567981, "grad_norm": 1.834908366203308, "learning_rate": 0.00019836055925638357, "loss": 0.7399053573608398, "step": 78110 }, { "epoch": 0.4643615029334665, "grad_norm": 1.4155386686325073, "learning_rate": 0.00019835937633570165, "loss": 0.6413462638854981, "step": 78120 }, { "epoch": 0.46442094501013487, "grad_norm": 1.7365919351577759, "learning_rate": 0.00019835819299233732, "loss": 0.6712444305419922, "step": 78130 }, { "epoch": 0.4644803870868033, "grad_norm": 1.8040430545806885, "learning_rate": 0.00019835700922629627, "loss": 0.6833023071289063, "step": 78140 }, { "epoch": 0.46453982916347164, "grad_norm": 1.6923085451126099, "learning_rate": 0.0001983558250375842, "loss": 0.672611141204834, "step": 78150 }, { "epoch": 0.46459927124014005, "grad_norm": 1.219124674797058, "learning_rate": 0.00019835464042620673, "loss": 0.6495745658874512, "step": 78160 }, { "epoch": 0.4646587133168084, "grad_norm": 1.9738891124725342, "learning_rate": 0.0001983534553921695, "loss": 0.6278720378875733, "step": 78170 }, { "epoch": 0.46471815539347683, "grad_norm": 2.0101935863494873, "learning_rate": 0.00019835226993547827, "loss": 0.6933134078979493, "step": 78180 }, { "epoch": 0.46477759747014524, "grad_norm": 1.8676972389221191, "learning_rate": 0.00019835108405613858, "loss": 0.7189538955688477, "step": 78190 }, { "epoch": 0.4648370395468136, "grad_norm": 1.7776433229446411, "learning_rate": 0.00019834989775415623, "loss": 0.7219955921173096, "step": 78200 }, { "epoch": 0.464896481623482, "grad_norm": 1.8457362651824951, "learning_rate": 0.00019834871102953684, "loss": 0.7566034317016601, "step": 78210 }, { "epoch": 0.4649559237001504, "grad_norm": 1.7783534526824951, "learning_rate": 0.00019834752388228603, "loss": 0.7250308990478516, "step": 78220 }, { "epoch": 0.4650153657768188, "grad_norm": 1.7764941453933716, "learning_rate": 0.0001983463363124096, "loss": 0.6867638111114502, "step": 78230 }, { "epoch": 0.46507480785348715, "grad_norm": 1.760856032371521, "learning_rate": 0.00019834514831991315, "loss": 0.6885225772857666, "step": 78240 }, { "epoch": 0.46513424993015556, "grad_norm": 2.341381072998047, "learning_rate": 0.0001983439599048024, "loss": 0.6763351917266845, "step": 78250 }, { "epoch": 0.465193692006824, "grad_norm": 1.7945507764816284, "learning_rate": 0.00019834277106708302, "loss": 0.6980220794677734, "step": 78260 }, { "epoch": 0.46525313408349234, "grad_norm": 2.360750675201416, "learning_rate": 0.00019834158180676066, "loss": 0.7636192321777344, "step": 78270 }, { "epoch": 0.46531257616016075, "grad_norm": 1.8233574628829956, "learning_rate": 0.00019834039212384102, "loss": 0.6684200286865234, "step": 78280 }, { "epoch": 0.4653720182368291, "grad_norm": 1.3280037641525269, "learning_rate": 0.0001983392020183299, "loss": 0.6783819675445557, "step": 78290 }, { "epoch": 0.4654314603134975, "grad_norm": 1.4829490184783936, "learning_rate": 0.00019833801149023283, "loss": 0.6878556251525879, "step": 78300 }, { "epoch": 0.4654909023901659, "grad_norm": 1.4948979616165161, "learning_rate": 0.00019833682053955565, "loss": 0.710980224609375, "step": 78310 }, { "epoch": 0.4655503444668343, "grad_norm": 1.4902515411376953, "learning_rate": 0.00019833562916630394, "loss": 0.7398579120635986, "step": 78320 }, { "epoch": 0.46560978654350266, "grad_norm": 2.0411672592163086, "learning_rate": 0.00019833443737048346, "loss": 0.6922900676727295, "step": 78330 }, { "epoch": 0.46566922862017107, "grad_norm": 1.514663815498352, "learning_rate": 0.0001983332451520999, "loss": 0.6428128242492676, "step": 78340 }, { "epoch": 0.4657286706968395, "grad_norm": 1.8797324895858765, "learning_rate": 0.00019833205251115895, "loss": 0.6414530754089356, "step": 78350 }, { "epoch": 0.46578811277350785, "grad_norm": 1.4699355363845825, "learning_rate": 0.00019833085944766633, "loss": 0.7059307098388672, "step": 78360 }, { "epoch": 0.46584755485017626, "grad_norm": 1.9831682443618774, "learning_rate": 0.0001983296659616278, "loss": 0.7125381469726563, "step": 78370 }, { "epoch": 0.4659069969268446, "grad_norm": 1.506629467010498, "learning_rate": 0.00019832847205304894, "loss": 0.6609443664550781, "step": 78380 }, { "epoch": 0.46596643900351303, "grad_norm": 2.0723001956939697, "learning_rate": 0.00019832727772193558, "loss": 0.6493690013885498, "step": 78390 }, { "epoch": 0.4660258810801814, "grad_norm": 1.8256839513778687, "learning_rate": 0.00019832608296829337, "loss": 0.6971991539001465, "step": 78400 }, { "epoch": 0.4660853231568498, "grad_norm": 1.6222493648529053, "learning_rate": 0.00019832488779212803, "loss": 0.7112897872924805, "step": 78410 }, { "epoch": 0.4661447652335182, "grad_norm": 1.6598281860351562, "learning_rate": 0.00019832369219344534, "loss": 0.7220512866973877, "step": 78420 }, { "epoch": 0.4662042073101866, "grad_norm": 1.8135230541229248, "learning_rate": 0.00019832249617225093, "loss": 0.7290271759033203, "step": 78430 }, { "epoch": 0.466263649386855, "grad_norm": 1.9783419370651245, "learning_rate": 0.00019832129972855057, "loss": 0.6731511116027832, "step": 78440 }, { "epoch": 0.46632309146352335, "grad_norm": 1.4721602201461792, "learning_rate": 0.00019832010286235, "loss": 0.6139767646789551, "step": 78450 }, { "epoch": 0.46638253354019177, "grad_norm": 1.9668776988983154, "learning_rate": 0.0001983189055736549, "loss": 0.7620254993438721, "step": 78460 }, { "epoch": 0.4664419756168601, "grad_norm": 1.7256847620010376, "learning_rate": 0.00019831770786247102, "loss": 0.6870445251464844, "step": 78470 }, { "epoch": 0.46650141769352854, "grad_norm": 1.9583078622817993, "learning_rate": 0.00019831650972880406, "loss": 0.655393409729004, "step": 78480 }, { "epoch": 0.46656085977019696, "grad_norm": 2.308626174926758, "learning_rate": 0.0001983153111726598, "loss": 0.7104811191558837, "step": 78490 }, { "epoch": 0.4666203018468653, "grad_norm": 1.720141887664795, "learning_rate": 0.00019831411219404396, "loss": 0.7363759994506835, "step": 78500 }, { "epoch": 0.46667974392353373, "grad_norm": 1.3169941902160645, "learning_rate": 0.0001983129127929623, "loss": 0.6364657402038574, "step": 78510 }, { "epoch": 0.4667391860002021, "grad_norm": 1.956191062927246, "learning_rate": 0.0001983117129694205, "loss": 0.7055544853210449, "step": 78520 }, { "epoch": 0.4667986280768705, "grad_norm": 2.13604474067688, "learning_rate": 0.00019831051272342434, "loss": 0.7057566165924072, "step": 78530 }, { "epoch": 0.46685807015353886, "grad_norm": 2.1081793308258057, "learning_rate": 0.0001983093120549795, "loss": 0.7165089130401612, "step": 78540 }, { "epoch": 0.4669175122302073, "grad_norm": 1.3829962015151978, "learning_rate": 0.0001983081109640918, "loss": 0.673917293548584, "step": 78550 }, { "epoch": 0.4669769543068757, "grad_norm": 1.5381945371627808, "learning_rate": 0.00019830690945076695, "loss": 0.6783505439758301, "step": 78560 }, { "epoch": 0.46703639638354405, "grad_norm": 1.935022234916687, "learning_rate": 0.0001983057075150107, "loss": 0.7079550743103027, "step": 78570 }, { "epoch": 0.46709583846021246, "grad_norm": 1.9042809009552002, "learning_rate": 0.00019830450515682883, "loss": 0.7131031036376954, "step": 78580 }, { "epoch": 0.4671552805368808, "grad_norm": 1.5301343202590942, "learning_rate": 0.00019830330237622705, "loss": 0.7061189651489258, "step": 78590 }, { "epoch": 0.46721472261354924, "grad_norm": 1.769698143005371, "learning_rate": 0.00019830209917321112, "loss": 0.7226990222930908, "step": 78600 }, { "epoch": 0.4672741646902176, "grad_norm": 1.5859988927841187, "learning_rate": 0.00019830089554778683, "loss": 0.6892725467681885, "step": 78610 }, { "epoch": 0.467333606766886, "grad_norm": 1.8698407411575317, "learning_rate": 0.0001982996914999599, "loss": 0.6515304565429687, "step": 78620 }, { "epoch": 0.4673930488435544, "grad_norm": 2.2035157680511475, "learning_rate": 0.0001982984870297361, "loss": 0.7072042465209961, "step": 78630 }, { "epoch": 0.4674524909202228, "grad_norm": 1.687364101409912, "learning_rate": 0.0001982972821371212, "loss": 0.697683048248291, "step": 78640 }, { "epoch": 0.4675119329968912, "grad_norm": 1.742467999458313, "learning_rate": 0.00019829607682212094, "loss": 0.7090458869934082, "step": 78650 }, { "epoch": 0.46757137507355956, "grad_norm": 1.4863413572311401, "learning_rate": 0.00019829487108474113, "loss": 0.69869065284729, "step": 78660 }, { "epoch": 0.467630817150228, "grad_norm": 1.8024115562438965, "learning_rate": 0.0001982936649249875, "loss": 0.6787171363830566, "step": 78670 }, { "epoch": 0.46769025922689633, "grad_norm": 1.6374375820159912, "learning_rate": 0.0001982924583428658, "loss": 0.7170067310333252, "step": 78680 }, { "epoch": 0.46774970130356475, "grad_norm": 1.3114163875579834, "learning_rate": 0.00019829125133838187, "loss": 0.6190692901611328, "step": 78690 }, { "epoch": 0.4678091433802331, "grad_norm": 1.514212727546692, "learning_rate": 0.00019829004391154145, "loss": 0.606069278717041, "step": 78700 }, { "epoch": 0.4678685854569015, "grad_norm": 1.5972574949264526, "learning_rate": 0.0001982888360623503, "loss": 0.6682783603668213, "step": 78710 }, { "epoch": 0.46792802753356993, "grad_norm": 1.7786893844604492, "learning_rate": 0.00019828762779081421, "loss": 0.7253776550292969, "step": 78720 }, { "epoch": 0.4679874696102383, "grad_norm": 1.1582075357437134, "learning_rate": 0.00019828641909693898, "loss": 0.6573746204376221, "step": 78730 }, { "epoch": 0.4680469116869067, "grad_norm": 1.6385536193847656, "learning_rate": 0.00019828520998073037, "loss": 0.6844363212585449, "step": 78740 }, { "epoch": 0.46810635376357507, "grad_norm": 2.24061918258667, "learning_rate": 0.00019828400044219415, "loss": 0.675259780883789, "step": 78750 }, { "epoch": 0.4681657958402435, "grad_norm": 1.7001491785049438, "learning_rate": 0.00019828279048133613, "loss": 0.7025040626525879, "step": 78760 }, { "epoch": 0.46822523791691184, "grad_norm": 1.5617800951004028, "learning_rate": 0.0001982815800981621, "loss": 0.6931452751159668, "step": 78770 }, { "epoch": 0.46828467999358026, "grad_norm": 1.8236416578292847, "learning_rate": 0.00019828036929267782, "loss": 0.6578986167907714, "step": 78780 }, { "epoch": 0.46834412207024867, "grad_norm": 1.6593581438064575, "learning_rate": 0.00019827915806488913, "loss": 0.6748128890991211, "step": 78790 }, { "epoch": 0.46840356414691703, "grad_norm": 1.5718108415603638, "learning_rate": 0.00019827794641480177, "loss": 0.748045539855957, "step": 78800 }, { "epoch": 0.46846300622358544, "grad_norm": 1.6513515710830688, "learning_rate": 0.00019827673434242158, "loss": 0.6743334770202637, "step": 78810 }, { "epoch": 0.4685224483002538, "grad_norm": 1.4888960123062134, "learning_rate": 0.00019827552184775436, "loss": 0.6468494415283204, "step": 78820 }, { "epoch": 0.4685818903769222, "grad_norm": 2.0414438247680664, "learning_rate": 0.00019827430893080587, "loss": 0.6621546745300293, "step": 78830 }, { "epoch": 0.4686413324535906, "grad_norm": 2.1887385845184326, "learning_rate": 0.00019827309559158194, "loss": 0.6548259735107422, "step": 78840 }, { "epoch": 0.468700774530259, "grad_norm": 1.9625415802001953, "learning_rate": 0.00019827188183008833, "loss": 0.7161951065063477, "step": 78850 }, { "epoch": 0.4687602166069274, "grad_norm": 1.758318305015564, "learning_rate": 0.00019827066764633095, "loss": 0.6533272743225098, "step": 78860 }, { "epoch": 0.46881965868359576, "grad_norm": 2.0232961177825928, "learning_rate": 0.00019826945304031552, "loss": 0.6961173057556153, "step": 78870 }, { "epoch": 0.4688791007602642, "grad_norm": 1.6121025085449219, "learning_rate": 0.00019826823801204785, "loss": 0.6550156116485596, "step": 78880 }, { "epoch": 0.46893854283693254, "grad_norm": 1.7192556858062744, "learning_rate": 0.0001982670225615338, "loss": 0.7336669921875, "step": 78890 }, { "epoch": 0.46899798491360095, "grad_norm": 1.5471428632736206, "learning_rate": 0.00019826580668877916, "loss": 0.6588222503662109, "step": 78900 }, { "epoch": 0.4690574269902693, "grad_norm": 1.8489282131195068, "learning_rate": 0.00019826459039378976, "loss": 0.7017056465148925, "step": 78910 }, { "epoch": 0.4691168690669377, "grad_norm": 1.6858162879943848, "learning_rate": 0.00019826337367657138, "loss": 0.6836203098297119, "step": 78920 }, { "epoch": 0.46917631114360614, "grad_norm": 1.4373228549957275, "learning_rate": 0.00019826215653712988, "loss": 0.6742267608642578, "step": 78930 }, { "epoch": 0.4692357532202745, "grad_norm": 1.7894718647003174, "learning_rate": 0.00019826093897547104, "loss": 0.7261215209960937, "step": 78940 }, { "epoch": 0.4692951952969429, "grad_norm": 2.044224739074707, "learning_rate": 0.00019825972099160073, "loss": 0.676146411895752, "step": 78950 }, { "epoch": 0.46935463737361127, "grad_norm": 1.9784373044967651, "learning_rate": 0.00019825850258552475, "loss": 0.6972716808319092, "step": 78960 }, { "epoch": 0.4694140794502797, "grad_norm": 2.088710308074951, "learning_rate": 0.00019825728375724898, "loss": 0.7252769947052002, "step": 78970 }, { "epoch": 0.46947352152694805, "grad_norm": 1.2561874389648438, "learning_rate": 0.00019825606450677913, "loss": 0.688512134552002, "step": 78980 }, { "epoch": 0.46953296360361646, "grad_norm": 1.896850347518921, "learning_rate": 0.00019825484483412115, "loss": 0.7040077209472656, "step": 78990 }, { "epoch": 0.4695924056802848, "grad_norm": 1.6649470329284668, "learning_rate": 0.00019825362473928086, "loss": 0.6996297359466552, "step": 79000 }, { "epoch": 0.46965184775695323, "grad_norm": 1.630858302116394, "learning_rate": 0.00019825240422226406, "loss": 0.6683093070983886, "step": 79010 }, { "epoch": 0.46971128983362165, "grad_norm": 1.7352855205535889, "learning_rate": 0.00019825118328307658, "loss": 0.6842509746551514, "step": 79020 }, { "epoch": 0.46977073191029, "grad_norm": 1.9845237731933594, "learning_rate": 0.0001982499619217243, "loss": 0.7167839050292969, "step": 79030 }, { "epoch": 0.4698301739869584, "grad_norm": 1.9733577966690063, "learning_rate": 0.000198248740138213, "loss": 0.7457320213317871, "step": 79040 }, { "epoch": 0.4698896160636268, "grad_norm": 1.9636582136154175, "learning_rate": 0.0001982475179325486, "loss": 0.6709462165832519, "step": 79050 }, { "epoch": 0.4699490581402952, "grad_norm": 2.18800687789917, "learning_rate": 0.0001982462953047369, "loss": 0.6891852855682373, "step": 79060 }, { "epoch": 0.47000850021696355, "grad_norm": 2.2592737674713135, "learning_rate": 0.00019824507225478378, "loss": 0.7605521202087402, "step": 79070 }, { "epoch": 0.47006794229363197, "grad_norm": 1.5618231296539307, "learning_rate": 0.00019824384878269505, "loss": 0.6505646705627441, "step": 79080 }, { "epoch": 0.4701273843703004, "grad_norm": 1.4240391254425049, "learning_rate": 0.0001982426248884766, "loss": 0.7076077461242676, "step": 79090 }, { "epoch": 0.47018682644696874, "grad_norm": 1.7449684143066406, "learning_rate": 0.0001982414005721343, "loss": 0.7174827575683593, "step": 79100 }, { "epoch": 0.47024626852363716, "grad_norm": 1.9793996810913086, "learning_rate": 0.00019824017583367393, "loss": 0.7198562145233154, "step": 79110 }, { "epoch": 0.4703057106003055, "grad_norm": 1.9251104593276978, "learning_rate": 0.0001982389506731014, "loss": 0.7069475173950195, "step": 79120 }, { "epoch": 0.47036515267697393, "grad_norm": 1.406896948814392, "learning_rate": 0.00019823772509042263, "loss": 0.6372991561889648, "step": 79130 }, { "epoch": 0.4704245947536423, "grad_norm": 1.7146611213684082, "learning_rate": 0.00019823649908564335, "loss": 0.6525620460510254, "step": 79140 }, { "epoch": 0.4704840368303107, "grad_norm": 2.19099760055542, "learning_rate": 0.0001982352726587695, "loss": 0.7017477989196778, "step": 79150 }, { "epoch": 0.4705434789069791, "grad_norm": 1.730387568473816, "learning_rate": 0.00019823404580980697, "loss": 0.7176972389221191, "step": 79160 }, { "epoch": 0.4706029209836475, "grad_norm": 1.4124702215194702, "learning_rate": 0.0001982328185387616, "loss": 0.6866671562194824, "step": 79170 }, { "epoch": 0.4706623630603159, "grad_norm": 2.0100607872009277, "learning_rate": 0.00019823159084563925, "loss": 0.6423154830932617, "step": 79180 }, { "epoch": 0.47072180513698425, "grad_norm": 1.8491946458816528, "learning_rate": 0.00019823036273044578, "loss": 0.6711292743682862, "step": 79190 }, { "epoch": 0.47078124721365266, "grad_norm": 1.7262790203094482, "learning_rate": 0.00019822913419318712, "loss": 0.6934830665588378, "step": 79200 }, { "epoch": 0.470840689290321, "grad_norm": 1.5136516094207764, "learning_rate": 0.00019822790523386913, "loss": 0.6785901069641114, "step": 79210 }, { "epoch": 0.47090013136698944, "grad_norm": 1.5037833452224731, "learning_rate": 0.00019822667585249763, "loss": 0.6810442924499511, "step": 79220 }, { "epoch": 0.47095957344365785, "grad_norm": 1.6818510293960571, "learning_rate": 0.00019822544604907857, "loss": 0.683696985244751, "step": 79230 }, { "epoch": 0.4710190155203262, "grad_norm": 1.5521973371505737, "learning_rate": 0.0001982242158236178, "loss": 0.6494133472442627, "step": 79240 }, { "epoch": 0.4710784575969946, "grad_norm": 1.3608802556991577, "learning_rate": 0.00019822298517612122, "loss": 0.6957465171813965, "step": 79250 }, { "epoch": 0.471137899673663, "grad_norm": 2.107006311416626, "learning_rate": 0.0001982217541065947, "loss": 0.6988181114196778, "step": 79260 }, { "epoch": 0.4711973417503314, "grad_norm": 1.5188195705413818, "learning_rate": 0.00019822052261504416, "loss": 0.6774528980255127, "step": 79270 }, { "epoch": 0.47125678382699976, "grad_norm": 1.7754896879196167, "learning_rate": 0.00019821929070147547, "loss": 0.685418701171875, "step": 79280 }, { "epoch": 0.4713162259036682, "grad_norm": 1.6462371349334717, "learning_rate": 0.0001982180583658945, "loss": 0.6265697002410888, "step": 79290 }, { "epoch": 0.4713756679803366, "grad_norm": 2.074558734893799, "learning_rate": 0.0001982168256083072, "loss": 0.6500842094421386, "step": 79300 }, { "epoch": 0.47143511005700495, "grad_norm": 1.3279783725738525, "learning_rate": 0.0001982155924287194, "loss": 0.6795069217681885, "step": 79310 }, { "epoch": 0.47149455213367336, "grad_norm": 2.643275737762451, "learning_rate": 0.00019821435882713705, "loss": 0.6537417411804199, "step": 79320 }, { "epoch": 0.4715539942103417, "grad_norm": 2.1596012115478516, "learning_rate": 0.00019821312480356606, "loss": 0.6902212142944336, "step": 79330 }, { "epoch": 0.47161343628701013, "grad_norm": 1.9351390600204468, "learning_rate": 0.00019821189035801228, "loss": 0.7211848735809326, "step": 79340 }, { "epoch": 0.4716728783636785, "grad_norm": 1.8862072229385376, "learning_rate": 0.00019821065549048165, "loss": 0.67903151512146, "step": 79350 }, { "epoch": 0.4717323204403469, "grad_norm": 1.954764723777771, "learning_rate": 0.00019820942020098008, "loss": 0.7177617073059082, "step": 79360 }, { "epoch": 0.47179176251701527, "grad_norm": 1.5728529691696167, "learning_rate": 0.00019820818448951344, "loss": 0.7100074768066407, "step": 79370 }, { "epoch": 0.4718512045936837, "grad_norm": 1.583606481552124, "learning_rate": 0.0001982069483560877, "loss": 0.6892000675201416, "step": 79380 }, { "epoch": 0.4719106466703521, "grad_norm": 1.99703049659729, "learning_rate": 0.00019820571180070875, "loss": 0.7240375518798828, "step": 79390 }, { "epoch": 0.47197008874702046, "grad_norm": 1.8901941776275635, "learning_rate": 0.00019820447482338252, "loss": 0.6972634315490722, "step": 79400 }, { "epoch": 0.47202953082368887, "grad_norm": 1.6705526113510132, "learning_rate": 0.0001982032374241149, "loss": 0.6440006256103515, "step": 79410 }, { "epoch": 0.47208897290035723, "grad_norm": 1.668540596961975, "learning_rate": 0.00019820199960291174, "loss": 0.7297176361083985, "step": 79420 }, { "epoch": 0.47214841497702564, "grad_norm": 2.0642621517181396, "learning_rate": 0.00019820076135977912, "loss": 0.6534478187561035, "step": 79430 }, { "epoch": 0.472207857053694, "grad_norm": 2.0465097427368164, "learning_rate": 0.00019819952269472285, "loss": 0.7185379981994628, "step": 79440 }, { "epoch": 0.4722672991303624, "grad_norm": 1.5425251722335815, "learning_rate": 0.00019819828360774893, "loss": 0.6392105102539063, "step": 79450 }, { "epoch": 0.47232674120703083, "grad_norm": 1.6798527240753174, "learning_rate": 0.0001981970440988632, "loss": 0.71480712890625, "step": 79460 }, { "epoch": 0.4723861832836992, "grad_norm": 1.6942046880722046, "learning_rate": 0.00019819580416807162, "loss": 0.6254480838775635, "step": 79470 }, { "epoch": 0.4724456253603676, "grad_norm": 1.5517477989196777, "learning_rate": 0.0001981945638153802, "loss": 0.7159563064575195, "step": 79480 }, { "epoch": 0.47250506743703596, "grad_norm": 2.348097085952759, "learning_rate": 0.00019819332304079476, "loss": 0.6891536235809326, "step": 79490 }, { "epoch": 0.4725645095137044, "grad_norm": 1.5972806215286255, "learning_rate": 0.00019819208184432128, "loss": 0.7420087814331054, "step": 79500 }, { "epoch": 0.47262395159037274, "grad_norm": 1.4992049932479858, "learning_rate": 0.0001981908402259657, "loss": 0.6951765060424805, "step": 79510 }, { "epoch": 0.47268339366704115, "grad_norm": 1.4079235792160034, "learning_rate": 0.000198189598185734, "loss": 0.6588107109069824, "step": 79520 }, { "epoch": 0.47274283574370957, "grad_norm": 1.801506519317627, "learning_rate": 0.00019818835572363205, "loss": 0.7111388206481933, "step": 79530 }, { "epoch": 0.4728022778203779, "grad_norm": 1.673099160194397, "learning_rate": 0.00019818711283966584, "loss": 0.7441447257995606, "step": 79540 }, { "epoch": 0.47286171989704634, "grad_norm": 2.115100145339966, "learning_rate": 0.0001981858695338413, "loss": 0.7025464057922364, "step": 79550 }, { "epoch": 0.4729211619737147, "grad_norm": 1.9218156337738037, "learning_rate": 0.0001981846258061644, "loss": 0.7251771926879883, "step": 79560 }, { "epoch": 0.4729806040503831, "grad_norm": 1.545765995979309, "learning_rate": 0.00019818338165664102, "loss": 0.7115758895874024, "step": 79570 }, { "epoch": 0.4730400461270515, "grad_norm": 1.601069450378418, "learning_rate": 0.0001981821370852772, "loss": 0.7102872371673584, "step": 79580 }, { "epoch": 0.4730994882037199, "grad_norm": 1.5907915830612183, "learning_rate": 0.00019818089209207884, "loss": 0.6979121685028076, "step": 79590 }, { "epoch": 0.4731589302803883, "grad_norm": 2.012270927429199, "learning_rate": 0.0001981796466770519, "loss": 0.7915854930877686, "step": 79600 }, { "epoch": 0.47321837235705666, "grad_norm": 1.9486243724822998, "learning_rate": 0.0001981784008402024, "loss": 0.6649115562438965, "step": 79610 }, { "epoch": 0.4732778144337251, "grad_norm": 1.5172258615493774, "learning_rate": 0.0001981771545815362, "loss": 0.6373198509216309, "step": 79620 }, { "epoch": 0.47333725651039343, "grad_norm": 1.5183758735656738, "learning_rate": 0.0001981759079010593, "loss": 0.6497889518737793, "step": 79630 }, { "epoch": 0.47339669858706185, "grad_norm": 1.7132866382598877, "learning_rate": 0.0001981746607987777, "loss": 0.6975477695465088, "step": 79640 }, { "epoch": 0.4734561406637302, "grad_norm": 1.6114954948425293, "learning_rate": 0.00019817341327469734, "loss": 0.6785261154174804, "step": 79650 }, { "epoch": 0.4735155827403986, "grad_norm": 1.5837661027908325, "learning_rate": 0.00019817216532882416, "loss": 0.6503749847412109, "step": 79660 }, { "epoch": 0.47357502481706704, "grad_norm": 1.5170868635177612, "learning_rate": 0.00019817091696116415, "loss": 0.629271411895752, "step": 79670 }, { "epoch": 0.4736344668937354, "grad_norm": 1.7148797512054443, "learning_rate": 0.00019816966817172332, "loss": 0.6229591369628906, "step": 79680 }, { "epoch": 0.4736939089704038, "grad_norm": 1.9084134101867676, "learning_rate": 0.0001981684189605076, "loss": 0.6447806358337402, "step": 79690 }, { "epoch": 0.47375335104707217, "grad_norm": 2.003479242324829, "learning_rate": 0.000198167169327523, "loss": 0.6408087730407714, "step": 79700 }, { "epoch": 0.4738127931237406, "grad_norm": 1.5799890756607056, "learning_rate": 0.00019816591927277543, "loss": 0.6959565162658692, "step": 79710 }, { "epoch": 0.47387223520040894, "grad_norm": 1.8865545988082886, "learning_rate": 0.00019816466879627096, "loss": 0.6568456649780273, "step": 79720 }, { "epoch": 0.47393167727707736, "grad_norm": 2.1459527015686035, "learning_rate": 0.0001981634178980155, "loss": 0.7094879150390625, "step": 79730 }, { "epoch": 0.4739911193537457, "grad_norm": 2.047530174255371, "learning_rate": 0.00019816216657801504, "loss": 0.6507038593292236, "step": 79740 }, { "epoch": 0.47405056143041413, "grad_norm": 1.954521656036377, "learning_rate": 0.00019816091483627562, "loss": 0.7164822101593018, "step": 79750 }, { "epoch": 0.47411000350708254, "grad_norm": 1.4275823831558228, "learning_rate": 0.0001981596626728032, "loss": 0.7243195533752441, "step": 79760 }, { "epoch": 0.4741694455837509, "grad_norm": 1.8068889379501343, "learning_rate": 0.00019815841008760375, "loss": 0.7364039421081543, "step": 79770 }, { "epoch": 0.4742288876604193, "grad_norm": 1.705275535583496, "learning_rate": 0.0001981571570806833, "loss": 0.7158999443054199, "step": 79780 }, { "epoch": 0.4742883297370877, "grad_norm": 1.6396828889846802, "learning_rate": 0.0001981559036520478, "loss": 0.6744805335998535, "step": 79790 }, { "epoch": 0.4743477718137561, "grad_norm": 1.7220871448516846, "learning_rate": 0.00019815464980170325, "loss": 0.6855682373046875, "step": 79800 }, { "epoch": 0.47440721389042445, "grad_norm": 1.5946611166000366, "learning_rate": 0.00019815339552965567, "loss": 0.6596248626708985, "step": 79810 }, { "epoch": 0.47446665596709287, "grad_norm": 1.6256794929504395, "learning_rate": 0.0001981521408359111, "loss": 0.6426212310791015, "step": 79820 }, { "epoch": 0.4745260980437613, "grad_norm": 1.7102547883987427, "learning_rate": 0.00019815088572047544, "loss": 0.6638054847717285, "step": 79830 }, { "epoch": 0.47458554012042964, "grad_norm": 1.3990159034729004, "learning_rate": 0.00019814963018335478, "loss": 0.6476668357849121, "step": 79840 }, { "epoch": 0.47464498219709805, "grad_norm": 1.7991799116134644, "learning_rate": 0.0001981483742245551, "loss": 0.6457883834838867, "step": 79850 }, { "epoch": 0.4747044242737664, "grad_norm": 1.572005271911621, "learning_rate": 0.0001981471178440824, "loss": 0.6823514461517334, "step": 79860 }, { "epoch": 0.4747638663504348, "grad_norm": 1.6310042142868042, "learning_rate": 0.00019814586104194268, "loss": 0.6926159858703613, "step": 79870 }, { "epoch": 0.4748233084271032, "grad_norm": 1.7038649320602417, "learning_rate": 0.00019814460381814198, "loss": 0.6982634544372559, "step": 79880 }, { "epoch": 0.4748827505037716, "grad_norm": 2.066704511642456, "learning_rate": 0.00019814334617268632, "loss": 0.733390998840332, "step": 79890 }, { "epoch": 0.47494219258044, "grad_norm": 1.526587724685669, "learning_rate": 0.00019814208810558167, "loss": 0.6837052345275879, "step": 79900 }, { "epoch": 0.4750016346571084, "grad_norm": 1.6800241470336914, "learning_rate": 0.00019814082961683408, "loss": 0.6958714485168457, "step": 79910 }, { "epoch": 0.4750610767337768, "grad_norm": 1.73434579372406, "learning_rate": 0.00019813957070644955, "loss": 0.7154769897460938, "step": 79920 }, { "epoch": 0.47512051881044515, "grad_norm": 1.8468434810638428, "learning_rate": 0.00019813831137443412, "loss": 0.7184802055358886, "step": 79930 }, { "epoch": 0.47517996088711356, "grad_norm": 1.6848629713058472, "learning_rate": 0.00019813705162079382, "loss": 0.666471290588379, "step": 79940 }, { "epoch": 0.4752394029637819, "grad_norm": 2.20173978805542, "learning_rate": 0.00019813579144553468, "loss": 0.671759557723999, "step": 79950 }, { "epoch": 0.47529884504045034, "grad_norm": 1.6044297218322754, "learning_rate": 0.00019813453084866273, "loss": 0.6202743530273438, "step": 79960 }, { "epoch": 0.47535828711711875, "grad_norm": 1.490432858467102, "learning_rate": 0.00019813326983018396, "loss": 0.6204655647277832, "step": 79970 }, { "epoch": 0.4754177291937871, "grad_norm": 1.594771385192871, "learning_rate": 0.00019813200839010445, "loss": 0.6634345054626465, "step": 79980 }, { "epoch": 0.4754771712704555, "grad_norm": 1.6974915266036987, "learning_rate": 0.00019813074652843022, "loss": 0.6970697402954101, "step": 79990 }, { "epoch": 0.4755366133471239, "grad_norm": 1.5413243770599365, "learning_rate": 0.00019812948424516725, "loss": 0.6621049404144287, "step": 80000 }, { "epoch": 0.4755960554237923, "grad_norm": 1.8451889753341675, "learning_rate": 0.0001981282215403217, "loss": 0.6775980472564698, "step": 80010 }, { "epoch": 0.47565549750046066, "grad_norm": 1.6936488151550293, "learning_rate": 0.00019812695841389948, "loss": 0.6792797088623047, "step": 80020 }, { "epoch": 0.47571493957712907, "grad_norm": 1.6407321691513062, "learning_rate": 0.00019812569486590673, "loss": 0.6838544845581055, "step": 80030 }, { "epoch": 0.4757743816537975, "grad_norm": 1.4952956438064575, "learning_rate": 0.00019812443089634943, "loss": 0.6713986873626709, "step": 80040 }, { "epoch": 0.47583382373046584, "grad_norm": 1.7178860902786255, "learning_rate": 0.00019812316650523365, "loss": 0.7549753189086914, "step": 80050 }, { "epoch": 0.47589326580713426, "grad_norm": 1.711598515510559, "learning_rate": 0.00019812190169256547, "loss": 0.6720899105072021, "step": 80060 }, { "epoch": 0.4759527078838026, "grad_norm": 1.8355599641799927, "learning_rate": 0.00019812063645835087, "loss": 0.6789380550384522, "step": 80070 }, { "epoch": 0.47601214996047103, "grad_norm": 1.372401237487793, "learning_rate": 0.000198119370802596, "loss": 0.6928600311279297, "step": 80080 }, { "epoch": 0.4760715920371394, "grad_norm": 1.6792864799499512, "learning_rate": 0.0001981181047253068, "loss": 0.6746024131774903, "step": 80090 }, { "epoch": 0.4761310341138078, "grad_norm": 1.3085829019546509, "learning_rate": 0.00019811683822648938, "loss": 0.6377176761627197, "step": 80100 }, { "epoch": 0.47619047619047616, "grad_norm": 1.6393475532531738, "learning_rate": 0.00019811557130614983, "loss": 0.6992299079895019, "step": 80110 }, { "epoch": 0.4762499182671446, "grad_norm": 1.5375139713287354, "learning_rate": 0.0001981143039642942, "loss": 0.6050560474395752, "step": 80120 }, { "epoch": 0.476309360343813, "grad_norm": 1.5699946880340576, "learning_rate": 0.00019811303620092855, "loss": 0.6512675762176514, "step": 80130 }, { "epoch": 0.47636880242048135, "grad_norm": 1.5843052864074707, "learning_rate": 0.00019811176801605887, "loss": 0.7023502349853515, "step": 80140 }, { "epoch": 0.47642824449714977, "grad_norm": 1.6289262771606445, "learning_rate": 0.00019811049940969132, "loss": 0.5506783485412597, "step": 80150 }, { "epoch": 0.4764876865738181, "grad_norm": 2.1183090209960938, "learning_rate": 0.00019810923038183194, "loss": 0.7852563858032227, "step": 80160 }, { "epoch": 0.47654712865048654, "grad_norm": 1.6724853515625, "learning_rate": 0.00019810796093248679, "loss": 0.7156724452972412, "step": 80170 }, { "epoch": 0.4766065707271549, "grad_norm": 1.8377798795700073, "learning_rate": 0.00019810669106166192, "loss": 0.6995326995849609, "step": 80180 }, { "epoch": 0.4766660128038233, "grad_norm": 2.050168037414551, "learning_rate": 0.00019810542076936346, "loss": 0.6930934906005859, "step": 80190 }, { "epoch": 0.47672545488049173, "grad_norm": 1.4956254959106445, "learning_rate": 0.00019810415005559748, "loss": 0.6558756351470947, "step": 80200 }, { "epoch": 0.4767848969571601, "grad_norm": 2.157616376876831, "learning_rate": 0.00019810287892037002, "loss": 0.7344404220581054, "step": 80210 }, { "epoch": 0.4768443390338285, "grad_norm": 2.094987630844116, "learning_rate": 0.00019810160736368718, "loss": 0.6268695831298828, "step": 80220 }, { "epoch": 0.47690378111049686, "grad_norm": 2.0187625885009766, "learning_rate": 0.00019810033538555504, "loss": 0.6791216373443604, "step": 80230 }, { "epoch": 0.4769632231871653, "grad_norm": 1.7564350366592407, "learning_rate": 0.0001980990629859797, "loss": 0.6524877548217773, "step": 80240 }, { "epoch": 0.47702266526383363, "grad_norm": 1.7012042999267578, "learning_rate": 0.0001980977901649672, "loss": 0.7373644828796386, "step": 80250 }, { "epoch": 0.47708210734050205, "grad_norm": 1.7184730768203735, "learning_rate": 0.0001980965169225237, "loss": 0.6410407066345215, "step": 80260 }, { "epoch": 0.47714154941717046, "grad_norm": 1.9417861700057983, "learning_rate": 0.00019809524325865524, "loss": 0.6477035045623779, "step": 80270 }, { "epoch": 0.4772009914938388, "grad_norm": 1.4000595808029175, "learning_rate": 0.0001980939691733679, "loss": 0.7040534973144531, "step": 80280 }, { "epoch": 0.47726043357050724, "grad_norm": 1.7094740867614746, "learning_rate": 0.00019809269466666786, "loss": 0.64261474609375, "step": 80290 }, { "epoch": 0.4773198756471756, "grad_norm": 1.6005651950836182, "learning_rate": 0.00019809141973856109, "loss": 0.6648991584777832, "step": 80300 }, { "epoch": 0.477379317723844, "grad_norm": 1.9412953853607178, "learning_rate": 0.0001980901443890538, "loss": 0.6929922103881836, "step": 80310 }, { "epoch": 0.47743875980051237, "grad_norm": 1.740709900856018, "learning_rate": 0.00019808886861815203, "loss": 0.6199687957763672, "step": 80320 }, { "epoch": 0.4774982018771808, "grad_norm": 1.9690324068069458, "learning_rate": 0.00019808759242586192, "loss": 0.7011950969696045, "step": 80330 }, { "epoch": 0.4775576439538492, "grad_norm": 1.5579817295074463, "learning_rate": 0.00019808631581218954, "loss": 0.726423978805542, "step": 80340 }, { "epoch": 0.47761708603051756, "grad_norm": 1.8094629049301147, "learning_rate": 0.00019808503877714103, "loss": 0.7161980628967285, "step": 80350 }, { "epoch": 0.47767652810718597, "grad_norm": 1.4032038450241089, "learning_rate": 0.00019808376132072244, "loss": 0.627094841003418, "step": 80360 }, { "epoch": 0.47773597018385433, "grad_norm": 1.6248606443405151, "learning_rate": 0.00019808248344293996, "loss": 0.6337882995605468, "step": 80370 }, { "epoch": 0.47779541226052274, "grad_norm": 1.9300862550735474, "learning_rate": 0.00019808120514379967, "loss": 0.6814654350280762, "step": 80380 }, { "epoch": 0.4778548543371911, "grad_norm": 1.579830288887024, "learning_rate": 0.00019807992642330763, "loss": 0.6377138137817383, "step": 80390 }, { "epoch": 0.4779142964138595, "grad_norm": 1.7276455163955688, "learning_rate": 0.00019807864728147006, "loss": 0.6542344093322754, "step": 80400 }, { "epoch": 0.4779737384905279, "grad_norm": 2.140778064727783, "learning_rate": 0.00019807736771829297, "loss": 0.7019244194030761, "step": 80410 }, { "epoch": 0.4780331805671963, "grad_norm": 1.6761342287063599, "learning_rate": 0.00019807608773378258, "loss": 0.7189380645751953, "step": 80420 }, { "epoch": 0.4780926226438647, "grad_norm": 1.7717669010162354, "learning_rate": 0.00019807480732794496, "loss": 0.7014955520629883, "step": 80430 }, { "epoch": 0.47815206472053307, "grad_norm": 1.920966625213623, "learning_rate": 0.00019807352650078625, "loss": 0.6584083557128906, "step": 80440 }, { "epoch": 0.4782115067972015, "grad_norm": 1.986464262008667, "learning_rate": 0.00019807224525231258, "loss": 0.7857814788818359, "step": 80450 }, { "epoch": 0.47827094887386984, "grad_norm": 2.016462802886963, "learning_rate": 0.00019807096358253004, "loss": 0.6976390361785889, "step": 80460 }, { "epoch": 0.47833039095053825, "grad_norm": 1.7468558549880981, "learning_rate": 0.00019806968149144484, "loss": 0.6141201019287109, "step": 80470 }, { "epoch": 0.4783898330272066, "grad_norm": 1.607540249824524, "learning_rate": 0.000198068398979063, "loss": 0.7111127853393555, "step": 80480 }, { "epoch": 0.478449275103875, "grad_norm": 2.1957314014434814, "learning_rate": 0.00019806711604539078, "loss": 0.6948877811431885, "step": 80490 }, { "epoch": 0.47850871718054344, "grad_norm": 1.6560885906219482, "learning_rate": 0.00019806583269043425, "loss": 0.6598188400268554, "step": 80500 }, { "epoch": 0.4785681592572118, "grad_norm": 2.0918633937835693, "learning_rate": 0.00019806454891419951, "loss": 0.7379027843475342, "step": 80510 }, { "epoch": 0.4786276013338802, "grad_norm": 2.2163689136505127, "learning_rate": 0.0001980632647166928, "loss": 0.6785428047180175, "step": 80520 }, { "epoch": 0.4786870434105486, "grad_norm": 2.1895546913146973, "learning_rate": 0.00019806198009792022, "loss": 0.6716553211212158, "step": 80530 }, { "epoch": 0.478746485487217, "grad_norm": 1.6137906312942505, "learning_rate": 0.00019806069505788786, "loss": 0.6704226016998291, "step": 80540 }, { "epoch": 0.47880592756388535, "grad_norm": 1.8933496475219727, "learning_rate": 0.0001980594095966019, "loss": 0.7362702369689942, "step": 80550 }, { "epoch": 0.47886536964055376, "grad_norm": 1.6581499576568604, "learning_rate": 0.00019805812371406856, "loss": 0.7159543037414551, "step": 80560 }, { "epoch": 0.4789248117172222, "grad_norm": 1.6813215017318726, "learning_rate": 0.0001980568374102939, "loss": 0.6278102397918701, "step": 80570 }, { "epoch": 0.47898425379389054, "grad_norm": 1.5440012216567993, "learning_rate": 0.00019805555068528412, "loss": 0.7101827621459961, "step": 80580 }, { "epoch": 0.47904369587055895, "grad_norm": 1.5520702600479126, "learning_rate": 0.00019805426353904532, "loss": 0.7157506465911865, "step": 80590 }, { "epoch": 0.4791031379472273, "grad_norm": 1.6629414558410645, "learning_rate": 0.00019805297597158374, "loss": 0.7558431625366211, "step": 80600 }, { "epoch": 0.4791625800238957, "grad_norm": 1.8698055744171143, "learning_rate": 0.0001980516879829055, "loss": 0.7080698013305664, "step": 80610 }, { "epoch": 0.4792220221005641, "grad_norm": 1.7867692708969116, "learning_rate": 0.00019805039957301678, "loss": 0.7264215469360351, "step": 80620 }, { "epoch": 0.4792814641772325, "grad_norm": 1.8712764978408813, "learning_rate": 0.0001980491107419237, "loss": 0.6847070217132568, "step": 80630 }, { "epoch": 0.4793409062539009, "grad_norm": 1.6881825923919678, "learning_rate": 0.00019804782148963242, "loss": 0.7024450302124023, "step": 80640 }, { "epoch": 0.47940034833056927, "grad_norm": 1.733838677406311, "learning_rate": 0.00019804653181614915, "loss": 0.6982466220855713, "step": 80650 }, { "epoch": 0.4794597904072377, "grad_norm": 1.6035536527633667, "learning_rate": 0.0001980452417214801, "loss": 0.6324713230133057, "step": 80660 }, { "epoch": 0.47951923248390604, "grad_norm": 1.5496166944503784, "learning_rate": 0.00019804395120563134, "loss": 0.6692037582397461, "step": 80670 }, { "epoch": 0.47957867456057446, "grad_norm": 1.5141675472259521, "learning_rate": 0.00019804266026860907, "loss": 0.6949499130249024, "step": 80680 }, { "epoch": 0.4796381166372428, "grad_norm": 1.878395915031433, "learning_rate": 0.00019804136891041953, "loss": 0.7380507469177247, "step": 80690 }, { "epoch": 0.47969755871391123, "grad_norm": 1.6705759763717651, "learning_rate": 0.00019804007713106883, "loss": 0.681707763671875, "step": 80700 }, { "epoch": 0.47975700079057965, "grad_norm": 1.9740761518478394, "learning_rate": 0.0001980387849305632, "loss": 0.7091225624084473, "step": 80710 }, { "epoch": 0.479816442867248, "grad_norm": 1.9860165119171143, "learning_rate": 0.00019803749230890876, "loss": 0.7729708671569824, "step": 80720 }, { "epoch": 0.4798758849439164, "grad_norm": 1.8131004571914673, "learning_rate": 0.00019803619926611173, "loss": 0.6088645935058594, "step": 80730 }, { "epoch": 0.4799353270205848, "grad_norm": 1.5114818811416626, "learning_rate": 0.00019803490580217828, "loss": 0.7052816390991211, "step": 80740 }, { "epoch": 0.4799947690972532, "grad_norm": 1.6358038187026978, "learning_rate": 0.00019803361191711466, "loss": 0.7014435768127442, "step": 80750 }, { "epoch": 0.48005421117392155, "grad_norm": 1.5460116863250732, "learning_rate": 0.00019803231761092698, "loss": 0.6762999534606934, "step": 80760 }, { "epoch": 0.48011365325058997, "grad_norm": 1.6996183395385742, "learning_rate": 0.00019803102288362147, "loss": 0.6616672515869141, "step": 80770 }, { "epoch": 0.4801730953272583, "grad_norm": 2.0357797145843506, "learning_rate": 0.0001980297277352043, "loss": 0.7423911571502686, "step": 80780 }, { "epoch": 0.48023253740392674, "grad_norm": 1.3545196056365967, "learning_rate": 0.0001980284321656817, "loss": 0.7109546661376953, "step": 80790 }, { "epoch": 0.48029197948059515, "grad_norm": 1.8938989639282227, "learning_rate": 0.00019802713617505987, "loss": 0.7231357574462891, "step": 80800 }, { "epoch": 0.4803514215572635, "grad_norm": 1.9016776084899902, "learning_rate": 0.00019802583976334494, "loss": 0.6965807914733887, "step": 80810 }, { "epoch": 0.48041086363393193, "grad_norm": 1.8080986738204956, "learning_rate": 0.00019802454293054318, "loss": 0.6527725219726562, "step": 80820 }, { "epoch": 0.4804703057106003, "grad_norm": 1.8409593105316162, "learning_rate": 0.00019802324567666076, "loss": 0.6405868530273438, "step": 80830 }, { "epoch": 0.4805297477872687, "grad_norm": 1.7009000778198242, "learning_rate": 0.00019802194800170393, "loss": 0.676969337463379, "step": 80840 }, { "epoch": 0.48058918986393706, "grad_norm": 1.5521323680877686, "learning_rate": 0.00019802064990567887, "loss": 0.7333168029785156, "step": 80850 }, { "epoch": 0.4806486319406055, "grad_norm": 2.0124077796936035, "learning_rate": 0.00019801935138859174, "loss": 0.6599944114685059, "step": 80860 }, { "epoch": 0.4807080740172739, "grad_norm": 1.5437259674072266, "learning_rate": 0.00019801805245044885, "loss": 0.657165813446045, "step": 80870 }, { "epoch": 0.48076751609394225, "grad_norm": 1.4872757196426392, "learning_rate": 0.00019801675309125632, "loss": 0.6802819728851318, "step": 80880 }, { "epoch": 0.48082695817061066, "grad_norm": 1.7964223623275757, "learning_rate": 0.0001980154533110204, "loss": 0.6816648483276367, "step": 80890 }, { "epoch": 0.480886400247279, "grad_norm": 1.7530149221420288, "learning_rate": 0.00019801415310974737, "loss": 0.6877917766571044, "step": 80900 }, { "epoch": 0.48094584232394744, "grad_norm": 1.8315304517745972, "learning_rate": 0.00019801285248744334, "loss": 0.6635110378265381, "step": 80910 }, { "epoch": 0.4810052844006158, "grad_norm": 1.4666343927383423, "learning_rate": 0.00019801155144411463, "loss": 0.767374849319458, "step": 80920 }, { "epoch": 0.4810647264772842, "grad_norm": 1.429097056388855, "learning_rate": 0.00019801024997976736, "loss": 0.6276509761810303, "step": 80930 }, { "epoch": 0.4811241685539526, "grad_norm": 2.124929666519165, "learning_rate": 0.0001980089480944079, "loss": 0.6877059459686279, "step": 80940 }, { "epoch": 0.481183610630621, "grad_norm": 1.3849694728851318, "learning_rate": 0.0001980076457880423, "loss": 0.6578646183013916, "step": 80950 }, { "epoch": 0.4812430527072894, "grad_norm": 1.689957857131958, "learning_rate": 0.00019800634306067695, "loss": 0.7827164649963378, "step": 80960 }, { "epoch": 0.48130249478395776, "grad_norm": 1.7111726999282837, "learning_rate": 0.00019800503991231804, "loss": 0.6692512035369873, "step": 80970 }, { "epoch": 0.48136193686062617, "grad_norm": 1.7042789459228516, "learning_rate": 0.0001980037363429717, "loss": 0.6627896308898926, "step": 80980 }, { "epoch": 0.48142137893729453, "grad_norm": 1.8851979970932007, "learning_rate": 0.0001980024323526443, "loss": 0.6814251899719238, "step": 80990 }, { "epoch": 0.48148082101396295, "grad_norm": 1.4695091247558594, "learning_rate": 0.00019800112794134199, "loss": 0.7088569641113281, "step": 81000 }, { "epoch": 0.48154026309063136, "grad_norm": 1.4366601705551147, "learning_rate": 0.00019799982310907108, "loss": 0.6660078525543213, "step": 81010 }, { "epoch": 0.4815997051672997, "grad_norm": 1.522355079650879, "learning_rate": 0.00019799851785583773, "loss": 0.7250773429870605, "step": 81020 }, { "epoch": 0.48165914724396813, "grad_norm": 1.6170450448989868, "learning_rate": 0.00019799721218164825, "loss": 0.6740954875946045, "step": 81030 }, { "epoch": 0.4817185893206365, "grad_norm": 1.992319941520691, "learning_rate": 0.00019799590608650887, "loss": 0.6841769695281983, "step": 81040 }, { "epoch": 0.4817780313973049, "grad_norm": 1.2947537899017334, "learning_rate": 0.00019799459957042586, "loss": 0.724446439743042, "step": 81050 }, { "epoch": 0.48183747347397327, "grad_norm": 1.7171435356140137, "learning_rate": 0.0001979932926334054, "loss": 0.6502975463867188, "step": 81060 }, { "epoch": 0.4818969155506417, "grad_norm": 3.184271812438965, "learning_rate": 0.00019799198527545376, "loss": 0.6759986877441406, "step": 81070 }, { "epoch": 0.4819563576273101, "grad_norm": 1.7130013704299927, "learning_rate": 0.0001979906774965773, "loss": 0.742490577697754, "step": 81080 }, { "epoch": 0.48201579970397845, "grad_norm": 2.1817924976348877, "learning_rate": 0.00019798936929678212, "loss": 0.7141520500183105, "step": 81090 }, { "epoch": 0.48207524178064687, "grad_norm": 1.5582369565963745, "learning_rate": 0.00019798806067607461, "loss": 0.6293858528137207, "step": 81100 }, { "epoch": 0.4821346838573152, "grad_norm": 1.630598783493042, "learning_rate": 0.00019798675163446095, "loss": 0.6620915412902832, "step": 81110 }, { "epoch": 0.48219412593398364, "grad_norm": 1.7651878595352173, "learning_rate": 0.0001979854421719474, "loss": 0.678339672088623, "step": 81120 }, { "epoch": 0.482253568010652, "grad_norm": 2.117846965789795, "learning_rate": 0.00019798413228854026, "loss": 0.6685906410217285, "step": 81130 }, { "epoch": 0.4823130100873204, "grad_norm": 1.7352473735809326, "learning_rate": 0.0001979828219842458, "loss": 0.7111461639404297, "step": 81140 }, { "epoch": 0.4823724521639888, "grad_norm": 1.867950439453125, "learning_rate": 0.0001979815112590703, "loss": 0.6538080215454102, "step": 81150 }, { "epoch": 0.4824318942406572, "grad_norm": 1.5739465951919556, "learning_rate": 0.00019798020011301996, "loss": 0.6245768547058106, "step": 81160 }, { "epoch": 0.4824913363173256, "grad_norm": 2.078876495361328, "learning_rate": 0.00019797888854610108, "loss": 0.6198554992675781, "step": 81170 }, { "epoch": 0.48255077839399396, "grad_norm": 1.6448787450790405, "learning_rate": 0.00019797757655832, "loss": 0.6744001388549805, "step": 81180 }, { "epoch": 0.4826102204706624, "grad_norm": 1.9434641599655151, "learning_rate": 0.0001979762641496829, "loss": 0.7026627063751221, "step": 81190 }, { "epoch": 0.48266966254733074, "grad_norm": 1.4792975187301636, "learning_rate": 0.00019797495132019613, "loss": 0.6089056015014649, "step": 81200 }, { "epoch": 0.48272910462399915, "grad_norm": 1.561274766921997, "learning_rate": 0.00019797363806986596, "loss": 0.6939696311950684, "step": 81210 }, { "epoch": 0.4827885467006675, "grad_norm": 1.7641913890838623, "learning_rate": 0.0001979723243986986, "loss": 0.610956859588623, "step": 81220 }, { "epoch": 0.4828479887773359, "grad_norm": 2.194478988647461, "learning_rate": 0.00019797101030670042, "loss": 0.6583390235900879, "step": 81230 }, { "epoch": 0.48290743085400434, "grad_norm": 1.7526825666427612, "learning_rate": 0.0001979696957938777, "loss": 0.6892166137695312, "step": 81240 }, { "epoch": 0.4829668729306727, "grad_norm": 1.6840908527374268, "learning_rate": 0.00019796838086023666, "loss": 0.6739749431610107, "step": 81250 }, { "epoch": 0.4830263150073411, "grad_norm": 1.9377775192260742, "learning_rate": 0.00019796706550578364, "loss": 0.7065644264221191, "step": 81260 }, { "epoch": 0.48308575708400947, "grad_norm": 1.9751888513565063, "learning_rate": 0.00019796574973052498, "loss": 0.6743940353393555, "step": 81270 }, { "epoch": 0.4831451991606779, "grad_norm": 1.6046003103256226, "learning_rate": 0.0001979644335344669, "loss": 0.6837649345397949, "step": 81280 }, { "epoch": 0.48320464123734624, "grad_norm": 1.8059934377670288, "learning_rate": 0.00019796311691761567, "loss": 0.6639626502990723, "step": 81290 }, { "epoch": 0.48326408331401466, "grad_norm": 2.0138845443725586, "learning_rate": 0.00019796179987997765, "loss": 0.6985150337219238, "step": 81300 }, { "epoch": 0.4833235253906831, "grad_norm": 1.6186556816101074, "learning_rate": 0.00019796048242155914, "loss": 0.6470891952514648, "step": 81310 }, { "epoch": 0.48338296746735143, "grad_norm": 1.4827214479446411, "learning_rate": 0.00019795916454236646, "loss": 0.6652280807495117, "step": 81320 }, { "epoch": 0.48344240954401985, "grad_norm": 1.88657546043396, "learning_rate": 0.00019795784624240584, "loss": 0.6358330726623536, "step": 81330 }, { "epoch": 0.4835018516206882, "grad_norm": 1.756610631942749, "learning_rate": 0.00019795652752168364, "loss": 0.7331594944000244, "step": 81340 }, { "epoch": 0.4835612936973566, "grad_norm": 1.8620004653930664, "learning_rate": 0.00019795520838020614, "loss": 0.6706125259399414, "step": 81350 }, { "epoch": 0.483620735774025, "grad_norm": 2.0689570903778076, "learning_rate": 0.0001979538888179797, "loss": 0.7091424942016602, "step": 81360 }, { "epoch": 0.4836801778506934, "grad_norm": 1.731711983680725, "learning_rate": 0.00019795256883501055, "loss": 0.6845758438110352, "step": 81370 }, { "epoch": 0.4837396199273618, "grad_norm": 1.6346502304077148, "learning_rate": 0.0001979512484313051, "loss": 0.6724093914031982, "step": 81380 }, { "epoch": 0.48379906200403017, "grad_norm": 1.367603063583374, "learning_rate": 0.0001979499276068696, "loss": 0.646284532546997, "step": 81390 }, { "epoch": 0.4838585040806986, "grad_norm": 1.333836555480957, "learning_rate": 0.0001979486063617104, "loss": 0.6633537292480469, "step": 81400 }, { "epoch": 0.48391794615736694, "grad_norm": 1.3887287378311157, "learning_rate": 0.00019794728469583382, "loss": 0.6916243553161621, "step": 81410 }, { "epoch": 0.48397738823403536, "grad_norm": 1.8926151990890503, "learning_rate": 0.00019794596260924613, "loss": 0.6828145980834961, "step": 81420 }, { "epoch": 0.4840368303107037, "grad_norm": 2.216763973236084, "learning_rate": 0.00019794464010195373, "loss": 0.7226654052734375, "step": 81430 }, { "epoch": 0.48409627238737213, "grad_norm": 1.540935754776001, "learning_rate": 0.00019794331717396291, "loss": 0.6603157997131348, "step": 81440 }, { "epoch": 0.48415571446404054, "grad_norm": 1.817033290863037, "learning_rate": 0.00019794199382527997, "loss": 0.6733376502990722, "step": 81450 }, { "epoch": 0.4842151565407089, "grad_norm": 1.591233491897583, "learning_rate": 0.00019794067005591133, "loss": 0.6293758392333985, "step": 81460 }, { "epoch": 0.4842745986173773, "grad_norm": 1.7222429513931274, "learning_rate": 0.00019793934586586322, "loss": 0.6831870079040527, "step": 81470 }, { "epoch": 0.4843340406940457, "grad_norm": 1.7165615558624268, "learning_rate": 0.00019793802125514203, "loss": 0.7145239353179932, "step": 81480 }, { "epoch": 0.4843934827707141, "grad_norm": 2.008192300796509, "learning_rate": 0.0001979366962237541, "loss": 0.6566618919372559, "step": 81490 }, { "epoch": 0.48445292484738245, "grad_norm": 1.5845839977264404, "learning_rate": 0.00019793537077170573, "loss": 0.6593478202819825, "step": 81500 }, { "epoch": 0.48451236692405086, "grad_norm": 1.8615328073501587, "learning_rate": 0.00019793404489900328, "loss": 0.6992260456085205, "step": 81510 }, { "epoch": 0.4845718090007192, "grad_norm": 1.6536056995391846, "learning_rate": 0.00019793271860565312, "loss": 0.746584415435791, "step": 81520 }, { "epoch": 0.48463125107738764, "grad_norm": 1.6446319818496704, "learning_rate": 0.00019793139189166155, "loss": 0.6553439617156982, "step": 81530 }, { "epoch": 0.48469069315405605, "grad_norm": 1.4413244724273682, "learning_rate": 0.00019793006475703494, "loss": 0.6387170791625977, "step": 81540 }, { "epoch": 0.4847501352307244, "grad_norm": 1.7602614164352417, "learning_rate": 0.00019792873720177965, "loss": 0.6882072448730469, "step": 81550 }, { "epoch": 0.4848095773073928, "grad_norm": 1.6483745574951172, "learning_rate": 0.00019792740922590198, "loss": 0.7283848762512207, "step": 81560 }, { "epoch": 0.4848690193840612, "grad_norm": 1.4956800937652588, "learning_rate": 0.00019792608082940837, "loss": 0.7189547061920166, "step": 81570 }, { "epoch": 0.4849284614607296, "grad_norm": 1.8040210008621216, "learning_rate": 0.0001979247520123051, "loss": 0.7409463882446289, "step": 81580 }, { "epoch": 0.48498790353739796, "grad_norm": 2.0151515007019043, "learning_rate": 0.00019792342277459856, "loss": 0.6641746520996094, "step": 81590 }, { "epoch": 0.48504734561406637, "grad_norm": 1.7080438137054443, "learning_rate": 0.0001979220931162951, "loss": 0.6356173515319824, "step": 81600 }, { "epoch": 0.4851067876907348, "grad_norm": 1.730965495109558, "learning_rate": 0.00019792076303740103, "loss": 0.7107028961181641, "step": 81610 }, { "epoch": 0.48516622976740315, "grad_norm": 1.8000569343566895, "learning_rate": 0.0001979194325379228, "loss": 0.7314855098724365, "step": 81620 }, { "epoch": 0.48522567184407156, "grad_norm": 1.972785234451294, "learning_rate": 0.00019791810161786676, "loss": 0.6507584571838378, "step": 81630 }, { "epoch": 0.4852851139207399, "grad_norm": 2.053835868835449, "learning_rate": 0.00019791677027723923, "loss": 0.6737821578979493, "step": 81640 }, { "epoch": 0.48534455599740833, "grad_norm": 1.3142262697219849, "learning_rate": 0.0001979154385160466, "loss": 0.6269395828247071, "step": 81650 }, { "epoch": 0.4854039980740767, "grad_norm": 1.9771487712860107, "learning_rate": 0.00019791410633429525, "loss": 0.6774063110351562, "step": 81660 }, { "epoch": 0.4854634401507451, "grad_norm": 1.4251596927642822, "learning_rate": 0.00019791277373199155, "loss": 0.6724132537841797, "step": 81670 }, { "epoch": 0.4855228822274135, "grad_norm": 1.7210878133773804, "learning_rate": 0.00019791144070914187, "loss": 0.7028313159942627, "step": 81680 }, { "epoch": 0.4855823243040819, "grad_norm": 2.0096800327301025, "learning_rate": 0.00019791010726575258, "loss": 0.6627877235412598, "step": 81690 }, { "epoch": 0.4856417663807503, "grad_norm": 1.645630121231079, "learning_rate": 0.00019790877340183008, "loss": 0.6605018615722656, "step": 81700 }, { "epoch": 0.48570120845741865, "grad_norm": 1.889272928237915, "learning_rate": 0.0001979074391173807, "loss": 0.6622560501098633, "step": 81710 }, { "epoch": 0.48576065053408707, "grad_norm": 1.7488024234771729, "learning_rate": 0.0001979061044124109, "loss": 0.7653992652893067, "step": 81720 }, { "epoch": 0.4858200926107554, "grad_norm": 1.8457921743392944, "learning_rate": 0.00019790476928692702, "loss": 0.691768741607666, "step": 81730 }, { "epoch": 0.48587953468742384, "grad_norm": 1.7286704778671265, "learning_rate": 0.00019790343374093543, "loss": 0.6425997734069824, "step": 81740 }, { "epoch": 0.48593897676409226, "grad_norm": 1.8082009553909302, "learning_rate": 0.00019790209777444256, "loss": 0.6932246208190918, "step": 81750 }, { "epoch": 0.4859984188407606, "grad_norm": 1.7322033643722534, "learning_rate": 0.00019790076138745478, "loss": 0.6335584640502929, "step": 81760 }, { "epoch": 0.48605786091742903, "grad_norm": 1.806609869003296, "learning_rate": 0.00019789942457997849, "loss": 0.6444355010986328, "step": 81770 }, { "epoch": 0.4861173029940974, "grad_norm": 2.027005195617676, "learning_rate": 0.00019789808735202005, "loss": 0.721731424331665, "step": 81780 }, { "epoch": 0.4861767450707658, "grad_norm": 1.5860189199447632, "learning_rate": 0.00019789674970358592, "loss": 0.6716135025024415, "step": 81790 }, { "epoch": 0.48623618714743416, "grad_norm": 1.885648250579834, "learning_rate": 0.00019789541163468244, "loss": 0.6796599864959717, "step": 81800 }, { "epoch": 0.4862956292241026, "grad_norm": 1.5940444469451904, "learning_rate": 0.00019789407314531603, "loss": 0.6505358695983887, "step": 81810 }, { "epoch": 0.486355071300771, "grad_norm": 1.802938461303711, "learning_rate": 0.0001978927342354931, "loss": 0.7083979606628418, "step": 81820 }, { "epoch": 0.48641451337743935, "grad_norm": 1.6890869140625, "learning_rate": 0.00019789139490522005, "loss": 0.6437506675720215, "step": 81830 }, { "epoch": 0.48647395545410776, "grad_norm": 1.6859298944473267, "learning_rate": 0.00019789005515450332, "loss": 0.7034999847412109, "step": 81840 }, { "epoch": 0.4865333975307761, "grad_norm": 1.5777325630187988, "learning_rate": 0.00019788871498334926, "loss": 0.7502095222473144, "step": 81850 }, { "epoch": 0.48659283960744454, "grad_norm": 2.1879327297210693, "learning_rate": 0.00019788737439176433, "loss": 0.6967504978179931, "step": 81860 }, { "epoch": 0.4866522816841129, "grad_norm": 1.7948009967803955, "learning_rate": 0.00019788603337975492, "loss": 0.6811586380004883, "step": 81870 }, { "epoch": 0.4867117237607813, "grad_norm": 1.5935395956039429, "learning_rate": 0.00019788469194732746, "loss": 0.7213550567626953, "step": 81880 }, { "epoch": 0.48677116583744967, "grad_norm": 1.6357264518737793, "learning_rate": 0.00019788335009448833, "loss": 0.750149154663086, "step": 81890 }, { "epoch": 0.4868306079141181, "grad_norm": 1.749046802520752, "learning_rate": 0.00019788200782124398, "loss": 0.6494296550750732, "step": 81900 }, { "epoch": 0.4868900499907865, "grad_norm": 2.038663625717163, "learning_rate": 0.0001978806651276008, "loss": 0.7237581253051758, "step": 81910 }, { "epoch": 0.48694949206745486, "grad_norm": 1.7302013635635376, "learning_rate": 0.00019787932201356526, "loss": 0.7108139991760254, "step": 81920 }, { "epoch": 0.4870089341441233, "grad_norm": 1.5756709575653076, "learning_rate": 0.00019787797847914377, "loss": 0.6320347309112548, "step": 81930 }, { "epoch": 0.48706837622079163, "grad_norm": 1.3786932229995728, "learning_rate": 0.00019787663452434275, "loss": 0.7006758689880371, "step": 81940 }, { "epoch": 0.48712781829746005, "grad_norm": 1.3659762144088745, "learning_rate": 0.00019787529014916863, "loss": 0.6820803642272949, "step": 81950 }, { "epoch": 0.4871872603741284, "grad_norm": 1.9587039947509766, "learning_rate": 0.00019787394535362784, "loss": 0.7098863601684571, "step": 81960 }, { "epoch": 0.4872467024507968, "grad_norm": 1.955252766609192, "learning_rate": 0.00019787260013772682, "loss": 0.6486087799072265, "step": 81970 }, { "epoch": 0.48730614452746523, "grad_norm": 1.6376498937606812, "learning_rate": 0.00019787125450147197, "loss": 0.6962567329406738, "step": 81980 }, { "epoch": 0.4873655866041336, "grad_norm": 1.3444644212722778, "learning_rate": 0.00019786990844486977, "loss": 0.638517951965332, "step": 81990 }, { "epoch": 0.487425028680802, "grad_norm": 1.5254865884780884, "learning_rate": 0.00019786856196792664, "loss": 0.6821807384490967, "step": 82000 }, { "epoch": 0.48748447075747037, "grad_norm": 1.6271990537643433, "learning_rate": 0.00019786721507064902, "loss": 0.671192216873169, "step": 82010 }, { "epoch": 0.4875439128341388, "grad_norm": 2.0505664348602295, "learning_rate": 0.0001978658677530434, "loss": 0.6311770915985108, "step": 82020 }, { "epoch": 0.48760335491080714, "grad_norm": 2.007937431335449, "learning_rate": 0.00019786452001511613, "loss": 0.7038885116577148, "step": 82030 }, { "epoch": 0.48766279698747556, "grad_norm": 1.4139046669006348, "learning_rate": 0.00019786317185687373, "loss": 0.7220723628997803, "step": 82040 }, { "epoch": 0.48772223906414397, "grad_norm": 1.920457363128662, "learning_rate": 0.0001978618232783226, "loss": 0.6648225784301758, "step": 82050 }, { "epoch": 0.48778168114081233, "grad_norm": 1.707401990890503, "learning_rate": 0.00019786047427946927, "loss": 0.7052062511444092, "step": 82060 }, { "epoch": 0.48784112321748074, "grad_norm": 2.210505485534668, "learning_rate": 0.00019785912486032015, "loss": 0.6280986785888671, "step": 82070 }, { "epoch": 0.4879005652941491, "grad_norm": 2.324678659439087, "learning_rate": 0.00019785777502088169, "loss": 0.7195312976837158, "step": 82080 }, { "epoch": 0.4879600073708175, "grad_norm": 1.6137785911560059, "learning_rate": 0.0001978564247611603, "loss": 0.7075076103210449, "step": 82090 }, { "epoch": 0.4880194494474859, "grad_norm": 1.752964735031128, "learning_rate": 0.00019785507408116252, "loss": 0.6684410095214843, "step": 82100 }, { "epoch": 0.4880788915241543, "grad_norm": 1.8427592515945435, "learning_rate": 0.00019785372298089477, "loss": 0.6980087280273437, "step": 82110 }, { "epoch": 0.4881383336008227, "grad_norm": 1.9028950929641724, "learning_rate": 0.0001978523714603635, "loss": 0.6554104804992675, "step": 82120 }, { "epoch": 0.48819777567749106, "grad_norm": 1.514103651046753, "learning_rate": 0.0001978510195195752, "loss": 0.6543862342834472, "step": 82130 }, { "epoch": 0.4882572177541595, "grad_norm": 1.8293942213058472, "learning_rate": 0.00019784966715853637, "loss": 0.6803569316864013, "step": 82140 }, { "epoch": 0.48831665983082784, "grad_norm": 1.581127643585205, "learning_rate": 0.00019784831437725343, "loss": 0.7202284812927247, "step": 82150 }, { "epoch": 0.48837610190749625, "grad_norm": 1.9106162786483765, "learning_rate": 0.0001978469611757328, "loss": 0.6266016960144043, "step": 82160 }, { "epoch": 0.4884355439841646, "grad_norm": 1.31605064868927, "learning_rate": 0.0001978456075539811, "loss": 0.6799479961395264, "step": 82170 }, { "epoch": 0.488494986060833, "grad_norm": 1.5369256734848022, "learning_rate": 0.00019784425351200465, "loss": 0.6719780921936035, "step": 82180 }, { "epoch": 0.4885544281375014, "grad_norm": 1.5292772054672241, "learning_rate": 0.00019784289904981007, "loss": 0.6440353393554688, "step": 82190 }, { "epoch": 0.4886138702141698, "grad_norm": 1.8117296695709229, "learning_rate": 0.00019784154416740372, "loss": 0.6636134147644043, "step": 82200 }, { "epoch": 0.4886733122908382, "grad_norm": 1.844643235206604, "learning_rate": 0.00019784018886479215, "loss": 0.6576649665832519, "step": 82210 }, { "epoch": 0.48873275436750657, "grad_norm": 1.3073197603225708, "learning_rate": 0.0001978388331419818, "loss": 0.701545524597168, "step": 82220 }, { "epoch": 0.488792196444175, "grad_norm": 1.9102874994277954, "learning_rate": 0.0001978374769989792, "loss": 0.7168754577636719, "step": 82230 }, { "epoch": 0.48885163852084335, "grad_norm": 1.7740495204925537, "learning_rate": 0.00019783612043579082, "loss": 0.6629579544067383, "step": 82240 }, { "epoch": 0.48891108059751176, "grad_norm": 1.8137171268463135, "learning_rate": 0.00019783476345242314, "loss": 0.6767253875732422, "step": 82250 }, { "epoch": 0.4889705226741801, "grad_norm": 1.6540004014968872, "learning_rate": 0.00019783340604888263, "loss": 0.7026097297668457, "step": 82260 }, { "epoch": 0.48902996475084853, "grad_norm": 1.6277379989624023, "learning_rate": 0.00019783204822517586, "loss": 0.6133029937744141, "step": 82270 }, { "epoch": 0.48908940682751695, "grad_norm": 1.8607171773910522, "learning_rate": 0.00019783068998130922, "loss": 0.6970202445983886, "step": 82280 }, { "epoch": 0.4891488489041853, "grad_norm": 1.5586713552474976, "learning_rate": 0.00019782933131728928, "loss": 0.7454410552978515, "step": 82290 }, { "epoch": 0.4892082909808537, "grad_norm": 1.6804288625717163, "learning_rate": 0.00019782797223312257, "loss": 0.6963620185852051, "step": 82300 }, { "epoch": 0.4892677330575221, "grad_norm": 1.8132582902908325, "learning_rate": 0.00019782661272881548, "loss": 0.6411715507507324, "step": 82310 }, { "epoch": 0.4893271751341905, "grad_norm": 1.628814935684204, "learning_rate": 0.00019782525280437463, "loss": 0.678844690322876, "step": 82320 }, { "epoch": 0.48938661721085885, "grad_norm": 1.5710294246673584, "learning_rate": 0.00019782389245980643, "loss": 0.6993696212768554, "step": 82330 }, { "epoch": 0.48944605928752727, "grad_norm": 1.7906887531280518, "learning_rate": 0.00019782253169511744, "loss": 0.7340926170349121, "step": 82340 }, { "epoch": 0.4895055013641957, "grad_norm": 1.6223673820495605, "learning_rate": 0.00019782117051031416, "loss": 0.6410484790802002, "step": 82350 }, { "epoch": 0.48956494344086404, "grad_norm": 1.7666023969650269, "learning_rate": 0.0001978198089054031, "loss": 0.7382744789123535, "step": 82360 }, { "epoch": 0.48962438551753246, "grad_norm": 1.815841794013977, "learning_rate": 0.0001978184468803908, "loss": 0.6138158798217773, "step": 82370 }, { "epoch": 0.4896838275942008, "grad_norm": 2.020622730255127, "learning_rate": 0.00019781708443528372, "loss": 0.6815634727478027, "step": 82380 }, { "epoch": 0.48974326967086923, "grad_norm": 1.7711453437805176, "learning_rate": 0.0001978157215700884, "loss": 0.6827412605285644, "step": 82390 }, { "epoch": 0.4898027117475376, "grad_norm": 2.126371383666992, "learning_rate": 0.0001978143582848114, "loss": 0.6630900382995606, "step": 82400 }, { "epoch": 0.489862153824206, "grad_norm": 1.8995022773742676, "learning_rate": 0.00019781299457945916, "loss": 0.6462553977966309, "step": 82410 }, { "epoch": 0.4899215959008744, "grad_norm": 1.691774845123291, "learning_rate": 0.00019781163045403833, "loss": 0.6764560222625733, "step": 82420 }, { "epoch": 0.4899810379775428, "grad_norm": 1.5555444955825806, "learning_rate": 0.00019781026590855527, "loss": 0.6971819877624512, "step": 82430 }, { "epoch": 0.4900404800542112, "grad_norm": 2.0180790424346924, "learning_rate": 0.00019780890094301662, "loss": 0.7277453422546387, "step": 82440 }, { "epoch": 0.49009992213087955, "grad_norm": 2.3260738849639893, "learning_rate": 0.00019780753555742893, "loss": 0.7054397583007812, "step": 82450 }, { "epoch": 0.49015936420754797, "grad_norm": 2.0590593814849854, "learning_rate": 0.00019780616975179863, "loss": 0.6746891975402832, "step": 82460 }, { "epoch": 0.4902188062842163, "grad_norm": 1.6723248958587646, "learning_rate": 0.00019780480352613234, "loss": 0.6329946517944336, "step": 82470 }, { "epoch": 0.49027824836088474, "grad_norm": 1.7979942560195923, "learning_rate": 0.00019780343688043653, "loss": 0.6894980430603027, "step": 82480 }, { "epoch": 0.49033769043755315, "grad_norm": 1.9687837362289429, "learning_rate": 0.00019780206981471782, "loss": 0.7030786991119384, "step": 82490 }, { "epoch": 0.4903971325142215, "grad_norm": 1.7750481367111206, "learning_rate": 0.00019780070232898266, "loss": 0.6794955730438232, "step": 82500 }, { "epoch": 0.4904565745908899, "grad_norm": 1.4313738346099854, "learning_rate": 0.00019779933442323769, "loss": 0.6843582153320312, "step": 82510 }, { "epoch": 0.4905160166675583, "grad_norm": 1.8492037057876587, "learning_rate": 0.00019779796609748932, "loss": 0.6884288311004638, "step": 82520 }, { "epoch": 0.4905754587442267, "grad_norm": 1.6749252080917358, "learning_rate": 0.00019779659735174422, "loss": 0.7004467964172363, "step": 82530 }, { "epoch": 0.49063490082089506, "grad_norm": 1.7294554710388184, "learning_rate": 0.00019779522818600892, "loss": 0.6660017967224121, "step": 82540 }, { "epoch": 0.4906943428975635, "grad_norm": 1.6297985315322876, "learning_rate": 0.0001977938586002899, "loss": 0.6845493793487549, "step": 82550 }, { "epoch": 0.49075378497423183, "grad_norm": 1.7069435119628906, "learning_rate": 0.00019779248859459376, "loss": 0.6686955451965332, "step": 82560 }, { "epoch": 0.49081322705090025, "grad_norm": 1.657541036605835, "learning_rate": 0.00019779111816892704, "loss": 0.649836540222168, "step": 82570 }, { "epoch": 0.49087266912756866, "grad_norm": 2.045405387878418, "learning_rate": 0.00019778974732329626, "loss": 0.7288969993591309, "step": 82580 }, { "epoch": 0.490932111204237, "grad_norm": 1.6430199146270752, "learning_rate": 0.00019778837605770807, "loss": 0.7026640892028808, "step": 82590 }, { "epoch": 0.49099155328090544, "grad_norm": 1.6750637292861938, "learning_rate": 0.00019778700437216902, "loss": 0.7181579113006592, "step": 82600 }, { "epoch": 0.4910509953575738, "grad_norm": 1.8041486740112305, "learning_rate": 0.00019778563226668556, "loss": 0.7010317802429199, "step": 82610 }, { "epoch": 0.4911104374342422, "grad_norm": 2.257657289505005, "learning_rate": 0.00019778425974126433, "loss": 0.6797702312469482, "step": 82620 }, { "epoch": 0.49116987951091057, "grad_norm": 1.9024261236190796, "learning_rate": 0.0001977828867959119, "loss": 0.6934142112731934, "step": 82630 }, { "epoch": 0.491229321587579, "grad_norm": 1.488555669784546, "learning_rate": 0.00019778151343063485, "loss": 0.6945594310760498, "step": 82640 }, { "epoch": 0.4912887636642474, "grad_norm": 1.5382685661315918, "learning_rate": 0.0001977801396454397, "loss": 0.7065571308135986, "step": 82650 }, { "epoch": 0.49134820574091576, "grad_norm": 1.6789004802703857, "learning_rate": 0.00019777876544033304, "loss": 0.699181079864502, "step": 82660 }, { "epoch": 0.49140764781758417, "grad_norm": 1.5424734354019165, "learning_rate": 0.00019777739081532148, "loss": 0.690063190460205, "step": 82670 }, { "epoch": 0.49146708989425253, "grad_norm": 2.0687127113342285, "learning_rate": 0.00019777601577041157, "loss": 0.6637340545654297, "step": 82680 }, { "epoch": 0.49152653197092094, "grad_norm": 1.5091359615325928, "learning_rate": 0.00019777464030560986, "loss": 0.7030933380126954, "step": 82690 }, { "epoch": 0.4915859740475893, "grad_norm": 1.3080257177352905, "learning_rate": 0.00019777326442092297, "loss": 0.663414716720581, "step": 82700 }, { "epoch": 0.4916454161242577, "grad_norm": 1.7521601915359497, "learning_rate": 0.0001977718881163575, "loss": 0.691311264038086, "step": 82710 }, { "epoch": 0.49170485820092613, "grad_norm": 1.577780842781067, "learning_rate": 0.00019777051139191997, "loss": 0.7076250076293945, "step": 82720 }, { "epoch": 0.4917643002775945, "grad_norm": 1.8976318836212158, "learning_rate": 0.00019776913424761697, "loss": 0.6978039741516113, "step": 82730 }, { "epoch": 0.4918237423542629, "grad_norm": 1.724674105644226, "learning_rate": 0.00019776775668345516, "loss": 0.7011205673217773, "step": 82740 }, { "epoch": 0.49188318443093126, "grad_norm": 2.1700756549835205, "learning_rate": 0.00019776637869944105, "loss": 0.6674836158752442, "step": 82750 }, { "epoch": 0.4919426265075997, "grad_norm": 1.73909592628479, "learning_rate": 0.00019776500029558127, "loss": 0.7466655254364014, "step": 82760 }, { "epoch": 0.49200206858426804, "grad_norm": 1.592415452003479, "learning_rate": 0.00019776362147188244, "loss": 0.711122989654541, "step": 82770 }, { "epoch": 0.49206151066093645, "grad_norm": 1.94785737991333, "learning_rate": 0.0001977622422283511, "loss": 0.7033493995666504, "step": 82780 }, { "epoch": 0.49212095273760487, "grad_norm": 1.6616058349609375, "learning_rate": 0.00019776086256499388, "loss": 0.709815502166748, "step": 82790 }, { "epoch": 0.4921803948142732, "grad_norm": 1.700472354888916, "learning_rate": 0.0001977594824818174, "loss": 0.7324048042297363, "step": 82800 }, { "epoch": 0.49223983689094164, "grad_norm": 1.7007609605789185, "learning_rate": 0.0001977581019788282, "loss": 0.7033472061157227, "step": 82810 }, { "epoch": 0.49229927896761, "grad_norm": 1.8451616764068604, "learning_rate": 0.00019775672105603294, "loss": 0.7051303863525391, "step": 82820 }, { "epoch": 0.4923587210442784, "grad_norm": 1.7552400827407837, "learning_rate": 0.00019775533971343819, "loss": 0.6435995101928711, "step": 82830 }, { "epoch": 0.4924181631209468, "grad_norm": 2.131192445755005, "learning_rate": 0.0001977539579510506, "loss": 0.6638298034667969, "step": 82840 }, { "epoch": 0.4924776051976152, "grad_norm": 1.791795015335083, "learning_rate": 0.00019775257576887674, "loss": 0.6713979244232178, "step": 82850 }, { "epoch": 0.4925370472742836, "grad_norm": 1.5488629341125488, "learning_rate": 0.0001977511931669232, "loss": 0.6290096282958985, "step": 82860 }, { "epoch": 0.49259648935095196, "grad_norm": 1.4990885257720947, "learning_rate": 0.00019774981014519666, "loss": 0.735755205154419, "step": 82870 }, { "epoch": 0.4926559314276204, "grad_norm": 1.6759886741638184, "learning_rate": 0.00019774842670370373, "loss": 0.7759943008422852, "step": 82880 }, { "epoch": 0.49271537350428873, "grad_norm": 1.7317876815795898, "learning_rate": 0.00019774704284245098, "loss": 0.6483274459838867, "step": 82890 }, { "epoch": 0.49277481558095715, "grad_norm": 1.7647528648376465, "learning_rate": 0.00019774565856144505, "loss": 0.6708356857299804, "step": 82900 }, { "epoch": 0.4928342576576255, "grad_norm": 1.777390480041504, "learning_rate": 0.00019774427386069258, "loss": 0.6335925102233887, "step": 82910 }, { "epoch": 0.4928936997342939, "grad_norm": 1.519640326499939, "learning_rate": 0.00019774288874020016, "loss": 0.6825115203857421, "step": 82920 }, { "epoch": 0.4929531418109623, "grad_norm": 2.1195404529571533, "learning_rate": 0.00019774150319997445, "loss": 0.646466064453125, "step": 82930 }, { "epoch": 0.4930125838876307, "grad_norm": 1.8017784357070923, "learning_rate": 0.00019774011724002204, "loss": 0.7078666687011719, "step": 82940 }, { "epoch": 0.4930720259642991, "grad_norm": 1.7439793348312378, "learning_rate": 0.0001977387308603496, "loss": 0.7083412170410156, "step": 82950 }, { "epoch": 0.49313146804096747, "grad_norm": 1.9858139753341675, "learning_rate": 0.00019773734406096374, "loss": 0.7404886245727539, "step": 82960 }, { "epoch": 0.4931909101176359, "grad_norm": 1.9006508588790894, "learning_rate": 0.0001977359568418711, "loss": 0.7125917434692383, "step": 82970 }, { "epoch": 0.49325035219430424, "grad_norm": 2.0695059299468994, "learning_rate": 0.0001977345692030783, "loss": 0.7541853904724121, "step": 82980 }, { "epoch": 0.49330979427097266, "grad_norm": 1.6622142791748047, "learning_rate": 0.00019773318114459201, "loss": 0.7034594535827636, "step": 82990 }, { "epoch": 0.493369236347641, "grad_norm": 1.4419974088668823, "learning_rate": 0.0001977317926664189, "loss": 0.6639520168304444, "step": 83000 }, { "epoch": 0.49342867842430943, "grad_norm": 1.6757067441940308, "learning_rate": 0.00019773040376856548, "loss": 0.6678953170776367, "step": 83010 }, { "epoch": 0.49348812050097784, "grad_norm": 1.6106964349746704, "learning_rate": 0.00019772901445103854, "loss": 0.7193802833557129, "step": 83020 }, { "epoch": 0.4935475625776462, "grad_norm": 1.8553879261016846, "learning_rate": 0.00019772762471384462, "loss": 0.7445986270904541, "step": 83030 }, { "epoch": 0.4936070046543146, "grad_norm": 1.6501082181930542, "learning_rate": 0.00019772623455699043, "loss": 0.690613842010498, "step": 83040 }, { "epoch": 0.493666446730983, "grad_norm": 1.8434147834777832, "learning_rate": 0.00019772484398048262, "loss": 0.6550560474395752, "step": 83050 }, { "epoch": 0.4937258888076514, "grad_norm": 1.5582536458969116, "learning_rate": 0.00019772345298432783, "loss": 0.6814979553222656, "step": 83060 }, { "epoch": 0.49378533088431975, "grad_norm": 1.7147018909454346, "learning_rate": 0.00019772206156853266, "loss": 0.6874472141265869, "step": 83070 }, { "epoch": 0.49384477296098817, "grad_norm": 1.7612255811691284, "learning_rate": 0.00019772066973310385, "loss": 0.7283387184143066, "step": 83080 }, { "epoch": 0.4939042150376566, "grad_norm": 1.8443726301193237, "learning_rate": 0.00019771927747804803, "loss": 0.7316951751708984, "step": 83090 }, { "epoch": 0.49396365711432494, "grad_norm": 2.587675094604492, "learning_rate": 0.00019771788480337185, "loss": 0.7435649871826172, "step": 83100 }, { "epoch": 0.49402309919099335, "grad_norm": 2.118441581726074, "learning_rate": 0.00019771649170908197, "loss": 0.6929239749908447, "step": 83110 }, { "epoch": 0.4940825412676617, "grad_norm": 1.5980587005615234, "learning_rate": 0.00019771509819518506, "loss": 0.6278532981872559, "step": 83120 }, { "epoch": 0.4941419833443301, "grad_norm": 1.9260598421096802, "learning_rate": 0.00019771370426168778, "loss": 0.6405846118927002, "step": 83130 }, { "epoch": 0.4942014254209985, "grad_norm": 1.6544138193130493, "learning_rate": 0.00019771230990859678, "loss": 0.723793888092041, "step": 83140 }, { "epoch": 0.4942608674976669, "grad_norm": 1.495011568069458, "learning_rate": 0.0001977109151359188, "loss": 0.6327358722686768, "step": 83150 }, { "epoch": 0.4943203095743353, "grad_norm": 1.874961018562317, "learning_rate": 0.00019770951994366046, "loss": 0.6886260032653808, "step": 83160 }, { "epoch": 0.4943797516510037, "grad_norm": 1.9938820600509644, "learning_rate": 0.00019770812433182841, "loss": 0.6679025650024414, "step": 83170 }, { "epoch": 0.4944391937276721, "grad_norm": 1.3548784255981445, "learning_rate": 0.0001977067283004294, "loss": 0.6493284225463867, "step": 83180 }, { "epoch": 0.49449863580434045, "grad_norm": 1.7730737924575806, "learning_rate": 0.00019770533184947003, "loss": 0.704798412322998, "step": 83190 }, { "epoch": 0.49455807788100886, "grad_norm": 2.114492893218994, "learning_rate": 0.00019770393497895702, "loss": 0.6831326961517334, "step": 83200 }, { "epoch": 0.4946175199576772, "grad_norm": 1.59609854221344, "learning_rate": 0.00019770253768889705, "loss": 0.6373117923736572, "step": 83210 }, { "epoch": 0.49467696203434564, "grad_norm": 1.5190070867538452, "learning_rate": 0.0001977011399792968, "loss": 0.7069314956665039, "step": 83220 }, { "epoch": 0.49473640411101405, "grad_norm": 1.655577301979065, "learning_rate": 0.00019769974185016297, "loss": 0.7013368129730224, "step": 83230 }, { "epoch": 0.4947958461876824, "grad_norm": 1.753124475479126, "learning_rate": 0.00019769834330150222, "loss": 0.6687904357910156, "step": 83240 }, { "epoch": 0.4948552882643508, "grad_norm": 1.5005927085876465, "learning_rate": 0.00019769694433332128, "loss": 0.6998186111450195, "step": 83250 }, { "epoch": 0.4949147303410192, "grad_norm": 1.6280996799468994, "learning_rate": 0.0001976955449456268, "loss": 0.6885945320129394, "step": 83260 }, { "epoch": 0.4949741724176876, "grad_norm": 1.917689561843872, "learning_rate": 0.00019769414513842547, "loss": 0.7213894844055175, "step": 83270 }, { "epoch": 0.49503361449435596, "grad_norm": 1.7392605543136597, "learning_rate": 0.00019769274491172406, "loss": 0.7071461200714111, "step": 83280 }, { "epoch": 0.49509305657102437, "grad_norm": 1.5930359363555908, "learning_rate": 0.0001976913442655292, "loss": 0.7306073188781739, "step": 83290 }, { "epoch": 0.49515249864769273, "grad_norm": 1.8270998001098633, "learning_rate": 0.00019768994319984757, "loss": 0.6647500991821289, "step": 83300 }, { "epoch": 0.49521194072436114, "grad_norm": 1.8843235969543457, "learning_rate": 0.00019768854171468595, "loss": 0.6970913887023926, "step": 83310 }, { "epoch": 0.49527138280102956, "grad_norm": 1.4925163984298706, "learning_rate": 0.00019768713981005098, "loss": 0.682911491394043, "step": 83320 }, { "epoch": 0.4953308248776979, "grad_norm": 1.876899242401123, "learning_rate": 0.0001976857374859494, "loss": 0.6731980323791504, "step": 83330 }, { "epoch": 0.49539026695436633, "grad_norm": 1.6204254627227783, "learning_rate": 0.00019768433474238792, "loss": 0.7371949195861817, "step": 83340 }, { "epoch": 0.4954497090310347, "grad_norm": 2.2823328971862793, "learning_rate": 0.0001976829315793732, "loss": 0.6479327201843261, "step": 83350 }, { "epoch": 0.4955091511077031, "grad_norm": 1.6283611059188843, "learning_rate": 0.00019768152799691201, "loss": 0.6334666252136231, "step": 83360 }, { "epoch": 0.49556859318437146, "grad_norm": 1.6754367351531982, "learning_rate": 0.00019768012399501105, "loss": 0.6843417167663575, "step": 83370 }, { "epoch": 0.4956280352610399, "grad_norm": 1.6221504211425781, "learning_rate": 0.00019767871957367702, "loss": 0.6801259517669678, "step": 83380 }, { "epoch": 0.4956874773377083, "grad_norm": 1.6407722234725952, "learning_rate": 0.00019767731473291667, "loss": 0.6807696342468261, "step": 83390 }, { "epoch": 0.49574691941437665, "grad_norm": 1.7960326671600342, "learning_rate": 0.0001976759094727367, "loss": 0.6164936065673828, "step": 83400 }, { "epoch": 0.49580636149104507, "grad_norm": 1.7829327583312988, "learning_rate": 0.00019767450379314382, "loss": 0.6811476707458496, "step": 83410 }, { "epoch": 0.4958658035677134, "grad_norm": 1.4196979999542236, "learning_rate": 0.00019767309769414478, "loss": 0.6588518142700195, "step": 83420 }, { "epoch": 0.49592524564438184, "grad_norm": 1.7896336317062378, "learning_rate": 0.00019767169117574626, "loss": 0.6807690620422363, "step": 83430 }, { "epoch": 0.4959846877210502, "grad_norm": 1.6319694519042969, "learning_rate": 0.00019767028423795503, "loss": 0.7202968597412109, "step": 83440 }, { "epoch": 0.4960441297977186, "grad_norm": 1.8631294965744019, "learning_rate": 0.00019766887688077783, "loss": 0.7305719375610351, "step": 83450 }, { "epoch": 0.49610357187438703, "grad_norm": 1.8565800189971924, "learning_rate": 0.00019766746910422135, "loss": 0.6553176879882813, "step": 83460 }, { "epoch": 0.4961630139510554, "grad_norm": 1.6901557445526123, "learning_rate": 0.0001976660609082924, "loss": 0.6440545082092285, "step": 83470 }, { "epoch": 0.4962224560277238, "grad_norm": 2.1034951210021973, "learning_rate": 0.0001976646522929976, "loss": 0.6847240447998046, "step": 83480 }, { "epoch": 0.49628189810439216, "grad_norm": 2.144679069519043, "learning_rate": 0.00019766324325834377, "loss": 0.7198457717895508, "step": 83490 }, { "epoch": 0.4963413401810606, "grad_norm": 1.5584641695022583, "learning_rate": 0.00019766183380433766, "loss": 0.6853335857391357, "step": 83500 }, { "epoch": 0.49640078225772893, "grad_norm": 1.5249509811401367, "learning_rate": 0.00019766042393098594, "loss": 0.6671515464782715, "step": 83510 }, { "epoch": 0.49646022433439735, "grad_norm": 1.9419548511505127, "learning_rate": 0.00019765901363829545, "loss": 0.6994125366210937, "step": 83520 }, { "epoch": 0.49651966641106576, "grad_norm": 2.3326926231384277, "learning_rate": 0.00019765760292627285, "loss": 0.6722150802612304, "step": 83530 }, { "epoch": 0.4965791084877341, "grad_norm": 1.5234524011611938, "learning_rate": 0.00019765619179492493, "loss": 0.7264561653137207, "step": 83540 }, { "epoch": 0.49663855056440254, "grad_norm": 1.352124571800232, "learning_rate": 0.0001976547802442585, "loss": 0.6367342948913575, "step": 83550 }, { "epoch": 0.4966979926410709, "grad_norm": 2.1795618534088135, "learning_rate": 0.00019765336827428013, "loss": 0.6526995182037354, "step": 83560 }, { "epoch": 0.4967574347177393, "grad_norm": 1.753359317779541, "learning_rate": 0.00019765195588499678, "loss": 0.6475666046142579, "step": 83570 }, { "epoch": 0.49681687679440767, "grad_norm": 1.6148139238357544, "learning_rate": 0.0001976505430764151, "loss": 0.7452954292297364, "step": 83580 }, { "epoch": 0.4968763188710761, "grad_norm": 1.312050461769104, "learning_rate": 0.00019764912984854182, "loss": 0.6970820426940918, "step": 83590 }, { "epoch": 0.4969357609477445, "grad_norm": 1.5733537673950195, "learning_rate": 0.00019764771620138378, "loss": 0.7297858715057373, "step": 83600 }, { "epoch": 0.49699520302441286, "grad_norm": 1.6539193391799927, "learning_rate": 0.00019764630213494773, "loss": 0.7183406829833985, "step": 83610 }, { "epoch": 0.49705464510108127, "grad_norm": 1.9183118343353271, "learning_rate": 0.00019764488764924037, "loss": 0.7212161540985107, "step": 83620 }, { "epoch": 0.49711408717774963, "grad_norm": 1.6465998888015747, "learning_rate": 0.00019764347274426857, "loss": 0.697542953491211, "step": 83630 }, { "epoch": 0.49717352925441805, "grad_norm": 1.6332799196243286, "learning_rate": 0.00019764205742003898, "loss": 0.6825998306274415, "step": 83640 }, { "epoch": 0.4972329713310864, "grad_norm": 1.990613341331482, "learning_rate": 0.00019764064167655847, "loss": 0.6443093299865723, "step": 83650 }, { "epoch": 0.4972924134077548, "grad_norm": 1.6529943943023682, "learning_rate": 0.00019763922551383373, "loss": 0.6892489910125732, "step": 83660 }, { "epoch": 0.4973518554844232, "grad_norm": 1.9629753828048706, "learning_rate": 0.0001976378089318716, "loss": 0.6552181243896484, "step": 83670 }, { "epoch": 0.4974112975610916, "grad_norm": 1.6558061838150024, "learning_rate": 0.00019763639193067886, "loss": 0.6671038627624511, "step": 83680 }, { "epoch": 0.49747073963776, "grad_norm": 1.4929633140563965, "learning_rate": 0.00019763497451026223, "loss": 0.6941125869750977, "step": 83690 }, { "epoch": 0.49753018171442837, "grad_norm": 1.6583937406539917, "learning_rate": 0.00019763355667062852, "loss": 0.611354923248291, "step": 83700 }, { "epoch": 0.4975896237910968, "grad_norm": 1.6654670238494873, "learning_rate": 0.00019763213841178452, "loss": 0.6670473098754883, "step": 83710 }, { "epoch": 0.49764906586776514, "grad_norm": 1.7431015968322754, "learning_rate": 0.00019763071973373698, "loss": 0.7104455947875976, "step": 83720 }, { "epoch": 0.49770850794443355, "grad_norm": 2.328425645828247, "learning_rate": 0.00019762930063649275, "loss": 0.6551659107208252, "step": 83730 }, { "epoch": 0.4977679500211019, "grad_norm": 1.7133409976959229, "learning_rate": 0.0001976278811200586, "loss": 0.6370048522949219, "step": 83740 }, { "epoch": 0.4978273920977703, "grad_norm": 1.508327603340149, "learning_rate": 0.00019762646118444128, "loss": 0.6908614158630371, "step": 83750 }, { "epoch": 0.49788683417443874, "grad_norm": 1.8556960821151733, "learning_rate": 0.0001976250408296476, "loss": 0.6544601440429687, "step": 83760 }, { "epoch": 0.4979462762511071, "grad_norm": 1.763168215751648, "learning_rate": 0.00019762362005568436, "loss": 0.6923138618469238, "step": 83770 }, { "epoch": 0.4980057183277755, "grad_norm": 1.817507028579712, "learning_rate": 0.00019762219886255834, "loss": 0.7156339168548584, "step": 83780 }, { "epoch": 0.4980651604044439, "grad_norm": 1.467346429824829, "learning_rate": 0.00019762077725027642, "loss": 0.6307000160217285, "step": 83790 }, { "epoch": 0.4981246024811123, "grad_norm": 1.8634079694747925, "learning_rate": 0.00019761935521884528, "loss": 0.6520829200744629, "step": 83800 }, { "epoch": 0.49818404455778065, "grad_norm": 1.6211735010147095, "learning_rate": 0.0001976179327682718, "loss": 0.6426259040832519, "step": 83810 }, { "epoch": 0.49824348663444906, "grad_norm": 1.5542348623275757, "learning_rate": 0.00019761650989856276, "loss": 0.6332792282104492, "step": 83820 }, { "epoch": 0.4983029287111175, "grad_norm": 1.8695716857910156, "learning_rate": 0.00019761508660972498, "loss": 0.6938935279846191, "step": 83830 }, { "epoch": 0.49836237078778584, "grad_norm": 2.099837064743042, "learning_rate": 0.00019761366290176524, "loss": 0.7046594619750977, "step": 83840 }, { "epoch": 0.49842181286445425, "grad_norm": 1.4585015773773193, "learning_rate": 0.00019761223877469037, "loss": 0.678134822845459, "step": 83850 }, { "epoch": 0.4984812549411226, "grad_norm": 1.991542935371399, "learning_rate": 0.0001976108142285072, "loss": 0.6934958457946777, "step": 83860 }, { "epoch": 0.498540697017791, "grad_norm": 1.7384328842163086, "learning_rate": 0.0001976093892632225, "loss": 0.6832408905029297, "step": 83870 }, { "epoch": 0.4986001390944594, "grad_norm": 1.6371147632598877, "learning_rate": 0.00019760796387884315, "loss": 0.6379053115844726, "step": 83880 }, { "epoch": 0.4986595811711278, "grad_norm": 2.0402979850769043, "learning_rate": 0.0001976065380753759, "loss": 0.6667313575744629, "step": 83890 }, { "epoch": 0.4987190232477962, "grad_norm": 2.342419147491455, "learning_rate": 0.0001976051118528276, "loss": 0.6958646774291992, "step": 83900 }, { "epoch": 0.49877846532446457, "grad_norm": 2.18315052986145, "learning_rate": 0.00019760368521120508, "loss": 0.7092952728271484, "step": 83910 }, { "epoch": 0.498837907401133, "grad_norm": 1.9256724119186401, "learning_rate": 0.00019760225815051516, "loss": 0.6564655303955078, "step": 83920 }, { "epoch": 0.49889734947780134, "grad_norm": 1.7944624423980713, "learning_rate": 0.00019760083067076468, "loss": 0.6899999618530274, "step": 83930 }, { "epoch": 0.49895679155446976, "grad_norm": 1.8759543895721436, "learning_rate": 0.00019759940277196044, "loss": 0.6911311149597168, "step": 83940 }, { "epoch": 0.4990162336311381, "grad_norm": 2.070115566253662, "learning_rate": 0.0001975979744541093, "loss": 0.7087322235107422, "step": 83950 }, { "epoch": 0.49907567570780653, "grad_norm": 1.5818073749542236, "learning_rate": 0.00019759654571721807, "loss": 0.6261678695678711, "step": 83960 }, { "epoch": 0.4991351177844749, "grad_norm": 1.6765942573547363, "learning_rate": 0.00019759511656129356, "loss": 0.6650114059448242, "step": 83970 }, { "epoch": 0.4991945598611433, "grad_norm": 1.7736551761627197, "learning_rate": 0.00019759368698634268, "loss": 0.669041633605957, "step": 83980 }, { "epoch": 0.4992540019378117, "grad_norm": 1.3225339651107788, "learning_rate": 0.00019759225699237222, "loss": 0.6683659553527832, "step": 83990 }, { "epoch": 0.4993134440144801, "grad_norm": 1.7216335535049438, "learning_rate": 0.00019759082657938904, "loss": 0.6144780158996582, "step": 84000 }, { "epoch": 0.4993728860911485, "grad_norm": 1.8047312498092651, "learning_rate": 0.00019758939574739993, "loss": 0.7603472709655762, "step": 84010 }, { "epoch": 0.49943232816781685, "grad_norm": 1.7274616956710815, "learning_rate": 0.00019758796449641182, "loss": 0.6852420806884766, "step": 84020 }, { "epoch": 0.49949177024448527, "grad_norm": 1.4432774782180786, "learning_rate": 0.00019758653282643147, "loss": 0.7170895099639892, "step": 84030 }, { "epoch": 0.4995512123211536, "grad_norm": 1.8303285837173462, "learning_rate": 0.0001975851007374658, "loss": 0.7121034622192383, "step": 84040 }, { "epoch": 0.49961065439782204, "grad_norm": 1.3443549871444702, "learning_rate": 0.0001975836682295216, "loss": 0.6442646026611328, "step": 84050 }, { "epoch": 0.49967009647449045, "grad_norm": 2.013261556625366, "learning_rate": 0.0001975822353026058, "loss": 0.6554322242736816, "step": 84060 }, { "epoch": 0.4997295385511588, "grad_norm": 2.5389773845672607, "learning_rate": 0.00019758080195672516, "loss": 0.7176703453063965, "step": 84070 }, { "epoch": 0.49978898062782723, "grad_norm": 1.6032053232192993, "learning_rate": 0.00019757936819188662, "loss": 0.6825647354125977, "step": 84080 }, { "epoch": 0.4998484227044956, "grad_norm": 1.5599446296691895, "learning_rate": 0.00019757793400809702, "loss": 0.6823094844818115, "step": 84090 }, { "epoch": 0.499907864781164, "grad_norm": 1.3281614780426025, "learning_rate": 0.00019757649940536318, "loss": 0.6991989612579346, "step": 84100 }, { "epoch": 0.49996730685783236, "grad_norm": 1.5190976858139038, "learning_rate": 0.00019757506438369197, "loss": 0.656645679473877, "step": 84110 }, { "epoch": 0.5000267489345008, "grad_norm": 1.6304550170898438, "learning_rate": 0.00019757362894309028, "loss": 0.6890387058258056, "step": 84120 }, { "epoch": 0.5000861910111691, "grad_norm": 2.6364665031433105, "learning_rate": 0.00019757219308356498, "loss": 0.663776969909668, "step": 84130 }, { "epoch": 0.5001456330878375, "grad_norm": 1.783701777458191, "learning_rate": 0.00019757075680512293, "loss": 0.6684400558471679, "step": 84140 }, { "epoch": 0.500205075164506, "grad_norm": 1.3036702871322632, "learning_rate": 0.000197569320107771, "loss": 0.6393681049346924, "step": 84150 }, { "epoch": 0.5002645172411744, "grad_norm": 1.7706246376037598, "learning_rate": 0.00019756788299151606, "loss": 0.6912029266357422, "step": 84160 }, { "epoch": 0.5003239593178427, "grad_norm": 1.7050938606262207, "learning_rate": 0.00019756644545636495, "loss": 0.6626004219055176, "step": 84170 }, { "epoch": 0.5003834013945111, "grad_norm": 2.0925140380859375, "learning_rate": 0.0001975650075023246, "loss": 0.6902565956115723, "step": 84180 }, { "epoch": 0.5004428434711795, "grad_norm": 1.7476606369018555, "learning_rate": 0.0001975635691294019, "loss": 0.6403095245361328, "step": 84190 }, { "epoch": 0.5005022855478479, "grad_norm": 1.9092048406600952, "learning_rate": 0.00019756213033760367, "loss": 0.6928632736206055, "step": 84200 }, { "epoch": 0.5005617276245163, "grad_norm": 1.6683523654937744, "learning_rate": 0.00019756069112693685, "loss": 0.6122082710266114, "step": 84210 }, { "epoch": 0.5006211697011846, "grad_norm": 2.166424512863159, "learning_rate": 0.00019755925149740825, "loss": 0.7015152931213379, "step": 84220 }, { "epoch": 0.5006806117778531, "grad_norm": 1.7892086505889893, "learning_rate": 0.00019755781144902484, "loss": 0.6833137512207031, "step": 84230 }, { "epoch": 0.5007400538545215, "grad_norm": 1.521876335144043, "learning_rate": 0.0001975563709817935, "loss": 0.7037381172180176, "step": 84240 }, { "epoch": 0.5007994959311899, "grad_norm": 2.0728416442871094, "learning_rate": 0.00019755493009572108, "loss": 0.7042212009429931, "step": 84250 }, { "epoch": 0.5008589380078582, "grad_norm": 1.866862416267395, "learning_rate": 0.0001975534887908145, "loss": 0.7162396430969238, "step": 84260 }, { "epoch": 0.5009183800845266, "grad_norm": 1.760400652885437, "learning_rate": 0.0001975520470670806, "loss": 0.6732798099517823, "step": 84270 }, { "epoch": 0.500977822161195, "grad_norm": 2.193525552749634, "learning_rate": 0.00019755060492452633, "loss": 0.6804777145385742, "step": 84280 }, { "epoch": 0.5010372642378634, "grad_norm": 1.2982763051986694, "learning_rate": 0.00019754916236315858, "loss": 0.6881471633911133, "step": 84290 }, { "epoch": 0.5010967063145318, "grad_norm": 1.5118639469146729, "learning_rate": 0.00019754771938298424, "loss": 0.6548726081848144, "step": 84300 }, { "epoch": 0.5011561483912002, "grad_norm": 2.0835721492767334, "learning_rate": 0.00019754627598401024, "loss": 0.6121984481811523, "step": 84310 }, { "epoch": 0.5012155904678686, "grad_norm": 1.20528244972229, "learning_rate": 0.00019754483216624346, "loss": 0.6715405464172364, "step": 84320 }, { "epoch": 0.501275032544537, "grad_norm": 1.6977105140686035, "learning_rate": 0.00019754338792969081, "loss": 0.6421681880950928, "step": 84330 }, { "epoch": 0.5013344746212054, "grad_norm": 1.818687915802002, "learning_rate": 0.00019754194327435923, "loss": 0.6803997993469239, "step": 84340 }, { "epoch": 0.5013939166978738, "grad_norm": 1.878933310508728, "learning_rate": 0.00019754049820025558, "loss": 0.6631917953491211, "step": 84350 }, { "epoch": 0.5014533587745421, "grad_norm": 1.571500539779663, "learning_rate": 0.0001975390527073868, "loss": 0.6839604854583741, "step": 84360 }, { "epoch": 0.5015128008512105, "grad_norm": 2.2572460174560547, "learning_rate": 0.0001975376067957598, "loss": 0.6419363498687745, "step": 84370 }, { "epoch": 0.5015722429278789, "grad_norm": 1.8653285503387451, "learning_rate": 0.0001975361604653815, "loss": 0.7551591873168946, "step": 84380 }, { "epoch": 0.5016316850045474, "grad_norm": 1.75059974193573, "learning_rate": 0.00019753471371625878, "loss": 0.6597566604614258, "step": 84390 }, { "epoch": 0.5016911270812157, "grad_norm": 1.7123034000396729, "learning_rate": 0.00019753326654839862, "loss": 0.6690963745117188, "step": 84400 }, { "epoch": 0.5017505691578841, "grad_norm": 1.630624532699585, "learning_rate": 0.0001975318189618079, "loss": 0.6845196723937989, "step": 84410 }, { "epoch": 0.5018100112345525, "grad_norm": 1.8827025890350342, "learning_rate": 0.00019753037095649362, "loss": 0.667095947265625, "step": 84420 }, { "epoch": 0.5018694533112209, "grad_norm": 2.0438413619995117, "learning_rate": 0.0001975289225324626, "loss": 0.7137387275695801, "step": 84430 }, { "epoch": 0.5019288953878893, "grad_norm": 1.3934909105300903, "learning_rate": 0.00019752747368972185, "loss": 0.6490879058837891, "step": 84440 }, { "epoch": 0.5019883374645576, "grad_norm": 1.5240147113800049, "learning_rate": 0.00019752602442827823, "loss": 0.7826447486877441, "step": 84450 }, { "epoch": 0.502047779541226, "grad_norm": 1.6473002433776855, "learning_rate": 0.00019752457474813876, "loss": 0.6292251110076904, "step": 84460 }, { "epoch": 0.5021072216178945, "grad_norm": 1.594045877456665, "learning_rate": 0.00019752312464931028, "loss": 0.6954592704772949, "step": 84470 }, { "epoch": 0.5021666636945629, "grad_norm": 4.086067199707031, "learning_rate": 0.00019752167413179982, "loss": 0.6694271564483643, "step": 84480 }, { "epoch": 0.5022261057712312, "grad_norm": 1.702944040298462, "learning_rate": 0.00019752022319561425, "loss": 0.7187564849853516, "step": 84490 }, { "epoch": 0.5022855478478996, "grad_norm": 2.177826404571533, "learning_rate": 0.00019751877184076054, "loss": 0.6371074676513672, "step": 84500 }, { "epoch": 0.502344989924568, "grad_norm": 1.6842995882034302, "learning_rate": 0.00019751732006724563, "loss": 0.6923850059509278, "step": 84510 }, { "epoch": 0.5024044320012364, "grad_norm": 1.910728931427002, "learning_rate": 0.00019751586787507643, "loss": 0.6997140407562256, "step": 84520 }, { "epoch": 0.5024638740779048, "grad_norm": 1.8130803108215332, "learning_rate": 0.00019751441526425997, "loss": 0.636360502243042, "step": 84530 }, { "epoch": 0.5025233161545731, "grad_norm": 1.810768485069275, "learning_rate": 0.00019751296223480312, "loss": 0.6655253887176513, "step": 84540 }, { "epoch": 0.5025827582312415, "grad_norm": 1.663230061531067, "learning_rate": 0.00019751150878671286, "loss": 0.7011463642120361, "step": 84550 }, { "epoch": 0.50264220030791, "grad_norm": 2.2147152423858643, "learning_rate": 0.00019751005491999615, "loss": 0.650075626373291, "step": 84560 }, { "epoch": 0.5027016423845784, "grad_norm": 1.4784786701202393, "learning_rate": 0.00019750860063465992, "loss": 0.657207727432251, "step": 84570 }, { "epoch": 0.5027610844612468, "grad_norm": 1.8157384395599365, "learning_rate": 0.00019750714593071112, "loss": 0.7244438171386719, "step": 84580 }, { "epoch": 0.5028205265379151, "grad_norm": 1.3271797895431519, "learning_rate": 0.0001975056908081568, "loss": 0.6696364879608154, "step": 84590 }, { "epoch": 0.5028799686145835, "grad_norm": 1.439356803894043, "learning_rate": 0.0001975042352670038, "loss": 0.6994071483612061, "step": 84600 }, { "epoch": 0.5029394106912519, "grad_norm": 1.6715563535690308, "learning_rate": 0.00019750277930725917, "loss": 0.6890449523925781, "step": 84610 }, { "epoch": 0.5029988527679203, "grad_norm": 1.7104564905166626, "learning_rate": 0.00019750132292892982, "loss": 0.6300711631774902, "step": 84620 }, { "epoch": 0.5030582948445886, "grad_norm": 1.453286051750183, "learning_rate": 0.00019749986613202273, "loss": 0.7092541694641114, "step": 84630 }, { "epoch": 0.503117736921257, "grad_norm": 1.8610038757324219, "learning_rate": 0.00019749840891654488, "loss": 0.6153272151947021, "step": 84640 }, { "epoch": 0.5031771789979255, "grad_norm": 1.6464314460754395, "learning_rate": 0.00019749695128250326, "loss": 0.6918390274047852, "step": 84650 }, { "epoch": 0.5032366210745939, "grad_norm": 1.7979767322540283, "learning_rate": 0.0001974954932299048, "loss": 0.6649067878723145, "step": 84660 }, { "epoch": 0.5032960631512623, "grad_norm": 1.6491436958312988, "learning_rate": 0.00019749403475875646, "loss": 0.6758111000061036, "step": 84670 }, { "epoch": 0.5033555052279306, "grad_norm": 1.47449791431427, "learning_rate": 0.00019749257586906528, "loss": 0.6477461814880371, "step": 84680 }, { "epoch": 0.503414947304599, "grad_norm": 1.1770583391189575, "learning_rate": 0.00019749111656083824, "loss": 0.6339561462402343, "step": 84690 }, { "epoch": 0.5034743893812674, "grad_norm": 2.337519884109497, "learning_rate": 0.00019748965683408226, "loss": 0.7262375831604004, "step": 84700 }, { "epoch": 0.5035338314579358, "grad_norm": 1.7820059061050415, "learning_rate": 0.00019748819668880433, "loss": 0.6759704113006592, "step": 84710 }, { "epoch": 0.5035932735346043, "grad_norm": 2.0772030353546143, "learning_rate": 0.0001974867361250115, "loss": 0.6443878173828125, "step": 84720 }, { "epoch": 0.5036527156112726, "grad_norm": 1.7615031003952026, "learning_rate": 0.00019748527514271068, "loss": 0.7387262344360351, "step": 84730 }, { "epoch": 0.503712157687941, "grad_norm": 1.5230712890625, "learning_rate": 0.00019748381374190893, "loss": 0.679486083984375, "step": 84740 }, { "epoch": 0.5037715997646094, "grad_norm": 1.653738260269165, "learning_rate": 0.0001974823519226132, "loss": 0.6753561973571778, "step": 84750 }, { "epoch": 0.5038310418412778, "grad_norm": 1.8164070844650269, "learning_rate": 0.00019748088968483046, "loss": 0.6913843154907227, "step": 84760 }, { "epoch": 0.5038904839179461, "grad_norm": 1.4788601398468018, "learning_rate": 0.00019747942702856778, "loss": 0.6682806015014648, "step": 84770 }, { "epoch": 0.5039499259946145, "grad_norm": 1.8330718278884888, "learning_rate": 0.00019747796395383206, "loss": 0.644995641708374, "step": 84780 }, { "epoch": 0.5040093680712829, "grad_norm": 1.4076272249221802, "learning_rate": 0.00019747650046063038, "loss": 0.6185893058776856, "step": 84790 }, { "epoch": 0.5040688101479514, "grad_norm": 2.0776073932647705, "learning_rate": 0.0001974750365489697, "loss": 0.6950181007385254, "step": 84800 }, { "epoch": 0.5041282522246198, "grad_norm": 2.2414536476135254, "learning_rate": 0.00019747357221885703, "loss": 0.6363251686096192, "step": 84810 }, { "epoch": 0.5041876943012881, "grad_norm": 2.180389165878296, "learning_rate": 0.0001974721074702994, "loss": 0.6482700347900391, "step": 84820 }, { "epoch": 0.5042471363779565, "grad_norm": 1.7780449390411377, "learning_rate": 0.00019747064230330377, "loss": 0.6611997604370117, "step": 84830 }, { "epoch": 0.5043065784546249, "grad_norm": 1.7443815469741821, "learning_rate": 0.00019746917671787715, "loss": 0.748435115814209, "step": 84840 }, { "epoch": 0.5043660205312933, "grad_norm": 1.8591690063476562, "learning_rate": 0.0001974677107140266, "loss": 0.7108504295349121, "step": 84850 }, { "epoch": 0.5044254626079616, "grad_norm": 1.852736234664917, "learning_rate": 0.0001974662442917591, "loss": 0.7003015041351318, "step": 84860 }, { "epoch": 0.50448490468463, "grad_norm": 1.3688980340957642, "learning_rate": 0.0001974647774510817, "loss": 0.6442996978759765, "step": 84870 }, { "epoch": 0.5045443467612984, "grad_norm": 2.0712389945983887, "learning_rate": 0.00019746331019200136, "loss": 0.7491708755493164, "step": 84880 }, { "epoch": 0.5046037888379669, "grad_norm": 1.570299744606018, "learning_rate": 0.00019746184251452514, "loss": 0.6713755130767822, "step": 84890 }, { "epoch": 0.5046632309146353, "grad_norm": 1.621198296546936, "learning_rate": 0.00019746037441866003, "loss": 0.6825563430786132, "step": 84900 }, { "epoch": 0.5047226729913036, "grad_norm": 1.675856113433838, "learning_rate": 0.00019745890590441308, "loss": 0.6736176490783692, "step": 84910 }, { "epoch": 0.504782115067972, "grad_norm": 1.9891376495361328, "learning_rate": 0.00019745743697179133, "loss": 0.6483943939208985, "step": 84920 }, { "epoch": 0.5048415571446404, "grad_norm": 1.6540991067886353, "learning_rate": 0.00019745596762080176, "loss": 0.6290089607238769, "step": 84930 }, { "epoch": 0.5049009992213088, "grad_norm": 1.6990940570831299, "learning_rate": 0.00019745449785145143, "loss": 0.642539119720459, "step": 84940 }, { "epoch": 0.5049604412979772, "grad_norm": 1.69096839427948, "learning_rate": 0.00019745302766374735, "loss": 0.6788378238677979, "step": 84950 }, { "epoch": 0.5050198833746455, "grad_norm": 2.3797688484191895, "learning_rate": 0.00019745155705769656, "loss": 0.6972845077514649, "step": 84960 }, { "epoch": 0.505079325451314, "grad_norm": 1.420325756072998, "learning_rate": 0.00019745008603330613, "loss": 0.6449708938598633, "step": 84970 }, { "epoch": 0.5051387675279824, "grad_norm": 1.784329891204834, "learning_rate": 0.00019744861459058304, "loss": 0.7010954856872559, "step": 84980 }, { "epoch": 0.5051982096046508, "grad_norm": 1.7231332063674927, "learning_rate": 0.00019744714272953436, "loss": 0.7127281188964844, "step": 84990 }, { "epoch": 0.5052576516813191, "grad_norm": 1.6416181325912476, "learning_rate": 0.00019744567045016712, "loss": 0.6763863563537598, "step": 85000 }, { "epoch": 0.5053170937579875, "grad_norm": 1.5335650444030762, "learning_rate": 0.0001974441977524884, "loss": 0.7132434844970703, "step": 85010 }, { "epoch": 0.5053765358346559, "grad_norm": 1.94203519821167, "learning_rate": 0.0001974427246365052, "loss": 0.6929636001586914, "step": 85020 }, { "epoch": 0.5054359779113243, "grad_norm": 1.8625032901763916, "learning_rate": 0.00019744125110222457, "loss": 0.6691203117370605, "step": 85030 }, { "epoch": 0.5054954199879927, "grad_norm": 1.9295532703399658, "learning_rate": 0.0001974397771496536, "loss": 0.6754228591918945, "step": 85040 }, { "epoch": 0.505554862064661, "grad_norm": 1.408253788948059, "learning_rate": 0.0001974383027787993, "loss": 0.6514063835144043, "step": 85050 }, { "epoch": 0.5056143041413295, "grad_norm": 1.6312767267227173, "learning_rate": 0.00019743682798966872, "loss": 0.6712852478027344, "step": 85060 }, { "epoch": 0.5056737462179979, "grad_norm": 1.8299367427825928, "learning_rate": 0.00019743535278226896, "loss": 0.642243480682373, "step": 85070 }, { "epoch": 0.5057331882946663, "grad_norm": 1.6772054433822632, "learning_rate": 0.000197433877156607, "loss": 0.6778024673461914, "step": 85080 }, { "epoch": 0.5057926303713347, "grad_norm": 1.6935714483261108, "learning_rate": 0.00019743240111268998, "loss": 0.5784579753875733, "step": 85090 }, { "epoch": 0.505852072448003, "grad_norm": 1.8502076864242554, "learning_rate": 0.00019743092465052491, "loss": 0.7464032649993897, "step": 85100 }, { "epoch": 0.5059115145246714, "grad_norm": 1.850977897644043, "learning_rate": 0.00019742944777011886, "loss": 0.7156272888183594, "step": 85110 }, { "epoch": 0.5059709566013398, "grad_norm": 1.7505072355270386, "learning_rate": 0.00019742797047147894, "loss": 0.6670765399932861, "step": 85120 }, { "epoch": 0.5060303986780083, "grad_norm": 1.720617651939392, "learning_rate": 0.00019742649275461215, "loss": 0.652503490447998, "step": 85130 }, { "epoch": 0.5060898407546766, "grad_norm": 1.9856537580490112, "learning_rate": 0.0001974250146195256, "loss": 0.6082405090332031, "step": 85140 }, { "epoch": 0.506149282831345, "grad_norm": 1.696777105331421, "learning_rate": 0.00019742353606622636, "loss": 0.6941728115081787, "step": 85150 }, { "epoch": 0.5062087249080134, "grad_norm": 1.6442890167236328, "learning_rate": 0.00019742205709472147, "loss": 0.6890707015991211, "step": 85160 }, { "epoch": 0.5062681669846818, "grad_norm": 1.6578421592712402, "learning_rate": 0.00019742057770501806, "loss": 0.7198206901550293, "step": 85170 }, { "epoch": 0.5063276090613502, "grad_norm": 1.4996174573898315, "learning_rate": 0.00019741909789712316, "loss": 0.6474410057067871, "step": 85180 }, { "epoch": 0.5063870511380185, "grad_norm": 1.8530948162078857, "learning_rate": 0.00019741761767104387, "loss": 0.6908534049987793, "step": 85190 }, { "epoch": 0.5064464932146869, "grad_norm": 2.0514867305755615, "learning_rate": 0.00019741613702678725, "loss": 0.6615397453308105, "step": 85200 }, { "epoch": 0.5065059352913553, "grad_norm": 1.8576412200927734, "learning_rate": 0.0001974146559643604, "loss": 0.6879500865936279, "step": 85210 }, { "epoch": 0.5065653773680238, "grad_norm": 2.023837089538574, "learning_rate": 0.0001974131744837704, "loss": 0.6721901893615723, "step": 85220 }, { "epoch": 0.5066248194446921, "grad_norm": 1.9657580852508545, "learning_rate": 0.00019741169258502436, "loss": 0.6750454902648926, "step": 85230 }, { "epoch": 0.5066842615213605, "grad_norm": 2.3852450847625732, "learning_rate": 0.00019741021026812935, "loss": 0.6809955596923828, "step": 85240 }, { "epoch": 0.5067437035980289, "grad_norm": 1.4417756795883179, "learning_rate": 0.00019740872753309246, "loss": 0.7104246139526367, "step": 85250 }, { "epoch": 0.5068031456746973, "grad_norm": 1.5175011157989502, "learning_rate": 0.00019740724437992076, "loss": 0.6563777446746826, "step": 85260 }, { "epoch": 0.5068625877513657, "grad_norm": 1.4500634670257568, "learning_rate": 0.0001974057608086214, "loss": 0.6963756561279297, "step": 85270 }, { "epoch": 0.506922029828034, "grad_norm": 1.6797832250595093, "learning_rate": 0.00019740427681920141, "loss": 0.7130252838134765, "step": 85280 }, { "epoch": 0.5069814719047024, "grad_norm": 1.7841747999191284, "learning_rate": 0.00019740279241166794, "loss": 0.7103691101074219, "step": 85290 }, { "epoch": 0.5070409139813709, "grad_norm": 1.992058277130127, "learning_rate": 0.0001974013075860281, "loss": 0.7324962615966797, "step": 85300 }, { "epoch": 0.5071003560580393, "grad_norm": 2.2441282272338867, "learning_rate": 0.00019739982234228892, "loss": 0.7369574546813965, "step": 85310 }, { "epoch": 0.5071597981347077, "grad_norm": 1.3465824127197266, "learning_rate": 0.00019739833668045757, "loss": 0.6755837440490723, "step": 85320 }, { "epoch": 0.507219240211376, "grad_norm": 1.8478529453277588, "learning_rate": 0.00019739685060054114, "loss": 0.6762442588806152, "step": 85330 }, { "epoch": 0.5072786822880444, "grad_norm": 2.04561448097229, "learning_rate": 0.00019739536410254675, "loss": 0.7363247871398926, "step": 85340 }, { "epoch": 0.5073381243647128, "grad_norm": 1.845922827720642, "learning_rate": 0.0001973938771864815, "loss": 0.6995367050170899, "step": 85350 }, { "epoch": 0.5073975664413812, "grad_norm": 1.630881428718567, "learning_rate": 0.00019739238985235248, "loss": 0.6949499130249024, "step": 85360 }, { "epoch": 0.5074570085180495, "grad_norm": 1.9347145557403564, "learning_rate": 0.00019739090210016684, "loss": 0.6875773429870605, "step": 85370 }, { "epoch": 0.507516450594718, "grad_norm": 1.4331351518630981, "learning_rate": 0.00019738941392993172, "loss": 0.6805061817169189, "step": 85380 }, { "epoch": 0.5075758926713864, "grad_norm": 1.456128716468811, "learning_rate": 0.00019738792534165414, "loss": 0.6579176902770996, "step": 85390 }, { "epoch": 0.5076353347480548, "grad_norm": 1.5950816869735718, "learning_rate": 0.0001973864363353413, "loss": 0.6892035484313965, "step": 85400 }, { "epoch": 0.5076947768247232, "grad_norm": 1.9086400270462036, "learning_rate": 0.00019738494691100034, "loss": 0.6683445930480957, "step": 85410 }, { "epoch": 0.5077542189013915, "grad_norm": 1.5682151317596436, "learning_rate": 0.0001973834570686383, "loss": 0.6777718544006348, "step": 85420 }, { "epoch": 0.5078136609780599, "grad_norm": 1.743813395500183, "learning_rate": 0.0001973819668082624, "loss": 0.6872823238372803, "step": 85430 }, { "epoch": 0.5078731030547283, "grad_norm": 1.1130897998809814, "learning_rate": 0.0001973804761298797, "loss": 0.6888668060302734, "step": 85440 }, { "epoch": 0.5079325451313967, "grad_norm": 1.44926917552948, "learning_rate": 0.00019737898503349738, "loss": 0.6547183990478516, "step": 85450 }, { "epoch": 0.5079919872080652, "grad_norm": 1.5030394792556763, "learning_rate": 0.00019737749351912256, "loss": 0.653635311126709, "step": 85460 }, { "epoch": 0.5080514292847335, "grad_norm": 1.8128129243850708, "learning_rate": 0.00019737600158676238, "loss": 0.7204554557800293, "step": 85470 }, { "epoch": 0.5081108713614019, "grad_norm": 1.9896998405456543, "learning_rate": 0.00019737450923642391, "loss": 0.6454208374023438, "step": 85480 }, { "epoch": 0.5081703134380703, "grad_norm": 1.6063282489776611, "learning_rate": 0.00019737301646811437, "loss": 0.7814296245574951, "step": 85490 }, { "epoch": 0.5082297555147387, "grad_norm": 1.948431372642517, "learning_rate": 0.00019737152328184088, "loss": 0.6815109252929688, "step": 85500 }, { "epoch": 0.508289197591407, "grad_norm": 1.259732723236084, "learning_rate": 0.00019737002967761056, "loss": 0.647895336151123, "step": 85510 }, { "epoch": 0.5083486396680754, "grad_norm": 1.7319972515106201, "learning_rate": 0.00019736853565543056, "loss": 0.6525263786315918, "step": 85520 }, { "epoch": 0.5084080817447438, "grad_norm": 1.6331838369369507, "learning_rate": 0.00019736704121530807, "loss": 0.6363044738769531, "step": 85530 }, { "epoch": 0.5084675238214122, "grad_norm": 1.739983081817627, "learning_rate": 0.0001973655463572502, "loss": 0.7505555152893066, "step": 85540 }, { "epoch": 0.5085269658980807, "grad_norm": 1.6263267993927002, "learning_rate": 0.0001973640510812641, "loss": 0.6484871864318847, "step": 85550 }, { "epoch": 0.508586407974749, "grad_norm": 1.6099586486816406, "learning_rate": 0.0001973625553873569, "loss": 0.6847739219665527, "step": 85560 }, { "epoch": 0.5086458500514174, "grad_norm": 1.6989789009094238, "learning_rate": 0.00019736105927553582, "loss": 0.6485730648040772, "step": 85570 }, { "epoch": 0.5087052921280858, "grad_norm": 2.2671594619750977, "learning_rate": 0.000197359562745808, "loss": 0.7985815048217774, "step": 85580 }, { "epoch": 0.5087647342047542, "grad_norm": 1.5477304458618164, "learning_rate": 0.00019735806579818056, "loss": 0.655328369140625, "step": 85590 }, { "epoch": 0.5088241762814225, "grad_norm": 2.3629472255706787, "learning_rate": 0.00019735656843266068, "loss": 0.6606562614440918, "step": 85600 }, { "epoch": 0.5088836183580909, "grad_norm": 2.2342288494110107, "learning_rate": 0.0001973550706492555, "loss": 0.6759934902191163, "step": 85610 }, { "epoch": 0.5089430604347593, "grad_norm": 2.0674633979797363, "learning_rate": 0.00019735357244797226, "loss": 0.7316771507263183, "step": 85620 }, { "epoch": 0.5090025025114278, "grad_norm": 1.4133673906326294, "learning_rate": 0.00019735207382881804, "loss": 0.5990174293518067, "step": 85630 }, { "epoch": 0.5090619445880962, "grad_norm": 2.009333372116089, "learning_rate": 0.0001973505747918001, "loss": 0.6915227890014648, "step": 85640 }, { "epoch": 0.5091213866647645, "grad_norm": 1.8845889568328857, "learning_rate": 0.00019734907533692548, "loss": 0.7165412902832031, "step": 85650 }, { "epoch": 0.5091808287414329, "grad_norm": 1.952647089958191, "learning_rate": 0.00019734757546420147, "loss": 0.6647955894470214, "step": 85660 }, { "epoch": 0.5092402708181013, "grad_norm": 1.6169534921646118, "learning_rate": 0.0001973460751736352, "loss": 0.6993041515350342, "step": 85670 }, { "epoch": 0.5092997128947697, "grad_norm": 1.7977349758148193, "learning_rate": 0.00019734457446523386, "loss": 0.6585254669189453, "step": 85680 }, { "epoch": 0.5093591549714381, "grad_norm": 1.8940151929855347, "learning_rate": 0.00019734307333900463, "loss": 0.6740904808044433, "step": 85690 }, { "epoch": 0.5094185970481064, "grad_norm": 1.60604989528656, "learning_rate": 0.00019734157179495464, "loss": 0.6715987682342529, "step": 85700 }, { "epoch": 0.5094780391247749, "grad_norm": 1.5822027921676636, "learning_rate": 0.00019734006983309114, "loss": 0.6611542701721191, "step": 85710 }, { "epoch": 0.5095374812014433, "grad_norm": 1.6317458152770996, "learning_rate": 0.0001973385674534213, "loss": 0.6700902938842773, "step": 85720 }, { "epoch": 0.5095969232781117, "grad_norm": 1.8725255727767944, "learning_rate": 0.00019733706465595226, "loss": 0.7217671394348144, "step": 85730 }, { "epoch": 0.50965636535478, "grad_norm": 1.5939486026763916, "learning_rate": 0.00019733556144069128, "loss": 0.6920086860656738, "step": 85740 }, { "epoch": 0.5097158074314484, "grad_norm": 1.5607872009277344, "learning_rate": 0.0001973340578076455, "loss": 0.7192947387695312, "step": 85750 }, { "epoch": 0.5097752495081168, "grad_norm": 1.5583549737930298, "learning_rate": 0.00019733255375682212, "loss": 0.683710765838623, "step": 85760 }, { "epoch": 0.5098346915847852, "grad_norm": 2.0765929222106934, "learning_rate": 0.00019733104928822834, "loss": 0.7215603828430176, "step": 85770 }, { "epoch": 0.5098941336614536, "grad_norm": 1.4825947284698486, "learning_rate": 0.0001973295444018714, "loss": 0.6693421363830566, "step": 85780 }, { "epoch": 0.509953575738122, "grad_norm": 2.0401246547698975, "learning_rate": 0.0001973280390977584, "loss": 0.722226619720459, "step": 85790 }, { "epoch": 0.5100130178147904, "grad_norm": 1.3385080099105835, "learning_rate": 0.00019732653337589665, "loss": 0.6688765048980713, "step": 85800 }, { "epoch": 0.5100724598914588, "grad_norm": 2.171435832977295, "learning_rate": 0.00019732502723629328, "loss": 0.739851999282837, "step": 85810 }, { "epoch": 0.5101319019681272, "grad_norm": 1.8641377687454224, "learning_rate": 0.00019732352067895553, "loss": 0.702049970626831, "step": 85820 }, { "epoch": 0.5101913440447956, "grad_norm": 1.7690638303756714, "learning_rate": 0.00019732201370389058, "loss": 0.6885688781738282, "step": 85830 }, { "epoch": 0.5102507861214639, "grad_norm": 1.6476505994796753, "learning_rate": 0.0001973205063111057, "loss": 0.699703311920166, "step": 85840 }, { "epoch": 0.5103102281981323, "grad_norm": 1.7483441829681396, "learning_rate": 0.00019731899850060797, "loss": 0.701418685913086, "step": 85850 }, { "epoch": 0.5103696702748007, "grad_norm": 1.483546257019043, "learning_rate": 0.00019731749027240478, "loss": 0.6925220966339112, "step": 85860 }, { "epoch": 0.5104291123514691, "grad_norm": 1.8140406608581543, "learning_rate": 0.0001973159816265032, "loss": 0.7006327629089355, "step": 85870 }, { "epoch": 0.5104885544281375, "grad_norm": 1.9974327087402344, "learning_rate": 0.0001973144725629105, "loss": 0.7324977874755859, "step": 85880 }, { "epoch": 0.5105479965048059, "grad_norm": 1.7890974283218384, "learning_rate": 0.00019731296308163392, "loss": 0.7170980930328369, "step": 85890 }, { "epoch": 0.5106074385814743, "grad_norm": 1.5346589088439941, "learning_rate": 0.00019731145318268063, "loss": 0.6735603332519531, "step": 85900 }, { "epoch": 0.5106668806581427, "grad_norm": 2.012876033782959, "learning_rate": 0.00019730994286605788, "loss": 0.6872607231140136, "step": 85910 }, { "epoch": 0.5107263227348111, "grad_norm": 1.6416070461273193, "learning_rate": 0.00019730843213177293, "loss": 0.6925817966461182, "step": 85920 }, { "epoch": 0.5107857648114794, "grad_norm": 1.7261319160461426, "learning_rate": 0.00019730692097983294, "loss": 0.7426789283752442, "step": 85930 }, { "epoch": 0.5108452068881478, "grad_norm": 1.8539363145828247, "learning_rate": 0.00019730540941024518, "loss": 0.6713676929473877, "step": 85940 }, { "epoch": 0.5109046489648162, "grad_norm": 1.7531720399856567, "learning_rate": 0.00019730389742301689, "loss": 0.652348518371582, "step": 85950 }, { "epoch": 0.5109640910414847, "grad_norm": 1.6147658824920654, "learning_rate": 0.00019730238501815527, "loss": 0.6837388038635254, "step": 85960 }, { "epoch": 0.511023533118153, "grad_norm": 1.9065650701522827, "learning_rate": 0.00019730087219566758, "loss": 0.7037925720214844, "step": 85970 }, { "epoch": 0.5110829751948214, "grad_norm": 1.6997946500778198, "learning_rate": 0.00019729935895556103, "loss": 0.5906888008117676, "step": 85980 }, { "epoch": 0.5111424172714898, "grad_norm": 1.7825194597244263, "learning_rate": 0.0001972978452978429, "loss": 0.5928188800811768, "step": 85990 }, { "epoch": 0.5112018593481582, "grad_norm": 1.692818284034729, "learning_rate": 0.00019729633122252037, "loss": 0.7413905620574951, "step": 86000 }, { "epoch": 0.5112613014248266, "grad_norm": 1.5150914192199707, "learning_rate": 0.00019729481672960076, "loss": 0.6228640079498291, "step": 86010 }, { "epoch": 0.5113207435014949, "grad_norm": 1.6981452703475952, "learning_rate": 0.00019729330181909128, "loss": 0.673121452331543, "step": 86020 }, { "epoch": 0.5113801855781633, "grad_norm": 1.6440311670303345, "learning_rate": 0.00019729178649099914, "loss": 0.711855697631836, "step": 86030 }, { "epoch": 0.5114396276548318, "grad_norm": 1.476764440536499, "learning_rate": 0.00019729027074533165, "loss": 0.7131563186645508, "step": 86040 }, { "epoch": 0.5114990697315002, "grad_norm": 2.1926565170288086, "learning_rate": 0.00019728875458209603, "loss": 0.7718174457550049, "step": 86050 }, { "epoch": 0.5115585118081686, "grad_norm": 1.7039375305175781, "learning_rate": 0.00019728723800129948, "loss": 0.7203803062438965, "step": 86060 }, { "epoch": 0.5116179538848369, "grad_norm": 2.4412646293640137, "learning_rate": 0.00019728572100294938, "loss": 0.678195571899414, "step": 86070 }, { "epoch": 0.5116773959615053, "grad_norm": 1.958624005317688, "learning_rate": 0.0001972842035870529, "loss": 0.6494187831878662, "step": 86080 }, { "epoch": 0.5117368380381737, "grad_norm": 1.8289744853973389, "learning_rate": 0.0001972826857536173, "loss": 0.6953818321228027, "step": 86090 }, { "epoch": 0.5117962801148421, "grad_norm": 1.4414489269256592, "learning_rate": 0.00019728116750264985, "loss": 0.705219841003418, "step": 86100 }, { "epoch": 0.5118557221915104, "grad_norm": 2.2100045680999756, "learning_rate": 0.0001972796488341578, "loss": 0.6931248664855957, "step": 86110 }, { "epoch": 0.5119151642681788, "grad_norm": 1.726464867591858, "learning_rate": 0.00019727812974814848, "loss": 0.665723180770874, "step": 86120 }, { "epoch": 0.5119746063448473, "grad_norm": 1.4804929494857788, "learning_rate": 0.00019727661024462908, "loss": 0.7417065620422363, "step": 86130 }, { "epoch": 0.5120340484215157, "grad_norm": 1.7322865724563599, "learning_rate": 0.0001972750903236069, "loss": 0.6847018241882324, "step": 86140 }, { "epoch": 0.5120934904981841, "grad_norm": 1.9832361936569214, "learning_rate": 0.00019727356998508922, "loss": 0.7332790851593017, "step": 86150 }, { "epoch": 0.5121529325748524, "grad_norm": 2.0738325119018555, "learning_rate": 0.00019727204922908328, "loss": 0.6267615795135498, "step": 86160 }, { "epoch": 0.5122123746515208, "grad_norm": 1.6473299264907837, "learning_rate": 0.00019727052805559641, "loss": 0.6921651840209961, "step": 86170 }, { "epoch": 0.5122718167281892, "grad_norm": 1.626488208770752, "learning_rate": 0.00019726900646463584, "loss": 0.7146975040435791, "step": 86180 }, { "epoch": 0.5123312588048576, "grad_norm": 1.7792518138885498, "learning_rate": 0.0001972674844562089, "loss": 0.7231410026550293, "step": 86190 }, { "epoch": 0.512390700881526, "grad_norm": 1.7482184171676636, "learning_rate": 0.00019726596203032277, "loss": 0.7293394088745118, "step": 86200 }, { "epoch": 0.5124501429581944, "grad_norm": 1.901850700378418, "learning_rate": 0.00019726443918698482, "loss": 0.7329305171966553, "step": 86210 }, { "epoch": 0.5125095850348628, "grad_norm": 1.638375997543335, "learning_rate": 0.00019726291592620234, "loss": 0.6952091693878174, "step": 86220 }, { "epoch": 0.5125690271115312, "grad_norm": 2.1066465377807617, "learning_rate": 0.00019726139224798256, "loss": 0.7293790340423584, "step": 86230 }, { "epoch": 0.5126284691881996, "grad_norm": 1.941372275352478, "learning_rate": 0.00019725986815233277, "loss": 0.6780641555786133, "step": 86240 }, { "epoch": 0.5126879112648679, "grad_norm": 1.676201581954956, "learning_rate": 0.00019725834363926035, "loss": 0.6848167896270752, "step": 86250 }, { "epoch": 0.5127473533415363, "grad_norm": 1.804222583770752, "learning_rate": 0.00019725681870877247, "loss": 0.6465787887573242, "step": 86260 }, { "epoch": 0.5128067954182047, "grad_norm": 1.4293631315231323, "learning_rate": 0.00019725529336087652, "loss": 0.6878985404968262, "step": 86270 }, { "epoch": 0.5128662374948731, "grad_norm": 1.5213631391525269, "learning_rate": 0.00019725376759557978, "loss": 0.7148853778839112, "step": 86280 }, { "epoch": 0.5129256795715416, "grad_norm": 1.371878743171692, "learning_rate": 0.0001972522414128895, "loss": 0.7188967704772949, "step": 86290 }, { "epoch": 0.5129851216482099, "grad_norm": 1.4681220054626465, "learning_rate": 0.000197250714812813, "loss": 0.6851346492767334, "step": 86300 }, { "epoch": 0.5130445637248783, "grad_norm": 2.0181853771209717, "learning_rate": 0.00019724918779535764, "loss": 0.6927597045898437, "step": 86310 }, { "epoch": 0.5131040058015467, "grad_norm": 1.8795571327209473, "learning_rate": 0.00019724766036053064, "loss": 0.7620939254760742, "step": 86320 }, { "epoch": 0.5131634478782151, "grad_norm": 1.7459877729415894, "learning_rate": 0.00019724613250833933, "loss": 0.6982906341552735, "step": 86330 }, { "epoch": 0.5132228899548834, "grad_norm": 1.715927004814148, "learning_rate": 0.00019724460423879107, "loss": 0.6825023651123047, "step": 86340 }, { "epoch": 0.5132823320315518, "grad_norm": 1.5948877334594727, "learning_rate": 0.00019724307555189313, "loss": 0.6520276069641113, "step": 86350 }, { "epoch": 0.5133417741082202, "grad_norm": 1.496216058731079, "learning_rate": 0.00019724154644765285, "loss": 0.6684954643249512, "step": 86360 }, { "epoch": 0.5134012161848887, "grad_norm": 1.843422532081604, "learning_rate": 0.00019724001692607749, "loss": 0.7371931076049805, "step": 86370 }, { "epoch": 0.5134606582615571, "grad_norm": 1.5781450271606445, "learning_rate": 0.0001972384869871744, "loss": 0.6981425762176514, "step": 86380 }, { "epoch": 0.5135201003382254, "grad_norm": 1.7096774578094482, "learning_rate": 0.0001972369566309509, "loss": 0.730998420715332, "step": 86390 }, { "epoch": 0.5135795424148938, "grad_norm": 1.5493340492248535, "learning_rate": 0.0001972354258574143, "loss": 0.7315817832946777, "step": 86400 }, { "epoch": 0.5136389844915622, "grad_norm": 1.991424560546875, "learning_rate": 0.00019723389466657197, "loss": 0.6463020324707032, "step": 86410 }, { "epoch": 0.5136984265682306, "grad_norm": 1.7805570363998413, "learning_rate": 0.00019723236305843115, "loss": 0.7234340667724609, "step": 86420 }, { "epoch": 0.513757868644899, "grad_norm": 1.5207598209381104, "learning_rate": 0.00019723083103299923, "loss": 0.6843443393707276, "step": 86430 }, { "epoch": 0.5138173107215673, "grad_norm": 1.576636791229248, "learning_rate": 0.00019722929859028354, "loss": 0.7097320556640625, "step": 86440 }, { "epoch": 0.5138767527982357, "grad_norm": 1.7376470565795898, "learning_rate": 0.00019722776573029136, "loss": 0.6538020133972168, "step": 86450 }, { "epoch": 0.5139361948749042, "grad_norm": 1.2192986011505127, "learning_rate": 0.0001972262324530301, "loss": 0.6512690544128418, "step": 86460 }, { "epoch": 0.5139956369515726, "grad_norm": 1.9726805686950684, "learning_rate": 0.00019722469875850702, "loss": 0.7367292881011963, "step": 86470 }, { "epoch": 0.5140550790282409, "grad_norm": 1.628960132598877, "learning_rate": 0.0001972231646467295, "loss": 0.6604226112365723, "step": 86480 }, { "epoch": 0.5141145211049093, "grad_norm": 1.9168589115142822, "learning_rate": 0.00019722163011770484, "loss": 0.6820945739746094, "step": 86490 }, { "epoch": 0.5141739631815777, "grad_norm": 1.391890287399292, "learning_rate": 0.0001972200951714404, "loss": 0.6557097434997559, "step": 86500 }, { "epoch": 0.5142334052582461, "grad_norm": 1.4822636842727661, "learning_rate": 0.00019721855980794358, "loss": 0.6958553314208984, "step": 86510 }, { "epoch": 0.5142928473349145, "grad_norm": 1.5191575288772583, "learning_rate": 0.0001972170240272216, "loss": 0.6282556533813477, "step": 86520 }, { "epoch": 0.5143522894115828, "grad_norm": 1.528002142906189, "learning_rate": 0.00019721548782928198, "loss": 0.6436268806457519, "step": 86530 }, { "epoch": 0.5144117314882513, "grad_norm": 1.5835390090942383, "learning_rate": 0.00019721395121413189, "loss": 0.6602839469909668, "step": 86540 }, { "epoch": 0.5144711735649197, "grad_norm": 1.9814261198043823, "learning_rate": 0.00019721241418177877, "loss": 0.6562139511108398, "step": 86550 }, { "epoch": 0.5145306156415881, "grad_norm": 1.5617105960845947, "learning_rate": 0.00019721087673222996, "loss": 0.6818352699279785, "step": 86560 }, { "epoch": 0.5145900577182565, "grad_norm": 1.5564550161361694, "learning_rate": 0.00019720933886549285, "loss": 0.6830614566802978, "step": 86570 }, { "epoch": 0.5146494997949248, "grad_norm": 1.6210564374923706, "learning_rate": 0.00019720780058157472, "loss": 0.7446345329284668, "step": 86580 }, { "epoch": 0.5147089418715932, "grad_norm": 1.4817829132080078, "learning_rate": 0.000197206261880483, "loss": 0.6993422508239746, "step": 86590 }, { "epoch": 0.5147683839482616, "grad_norm": 1.9256861209869385, "learning_rate": 0.00019720472276222505, "loss": 0.7424264907836914, "step": 86600 }, { "epoch": 0.51482782602493, "grad_norm": 1.92533278465271, "learning_rate": 0.00019720318322680812, "loss": 0.6733451366424561, "step": 86610 }, { "epoch": 0.5148872681015983, "grad_norm": 1.4768067598342896, "learning_rate": 0.00019720164327423974, "loss": 0.6667215347290039, "step": 86620 }, { "epoch": 0.5149467101782668, "grad_norm": 1.9464131593704224, "learning_rate": 0.00019720010290452715, "loss": 0.652528190612793, "step": 86630 }, { "epoch": 0.5150061522549352, "grad_norm": 1.3427278995513916, "learning_rate": 0.0001971985621176778, "loss": 0.6920729637145996, "step": 86640 }, { "epoch": 0.5150655943316036, "grad_norm": 1.7439745664596558, "learning_rate": 0.000197197020913699, "loss": 0.6652742862701416, "step": 86650 }, { "epoch": 0.515125036408272, "grad_norm": 1.8219120502471924, "learning_rate": 0.00019719547929259815, "loss": 0.698397445678711, "step": 86660 }, { "epoch": 0.5151844784849403, "grad_norm": 1.3034175634384155, "learning_rate": 0.00019719393725438263, "loss": 0.6253749847412109, "step": 86670 }, { "epoch": 0.5152439205616087, "grad_norm": 1.8791797161102295, "learning_rate": 0.0001971923947990598, "loss": 0.7257401466369628, "step": 86680 }, { "epoch": 0.5153033626382771, "grad_norm": 1.6608545780181885, "learning_rate": 0.00019719085192663707, "loss": 0.6269908905029297, "step": 86690 }, { "epoch": 0.5153628047149456, "grad_norm": 1.9096306562423706, "learning_rate": 0.00019718930863712179, "loss": 0.7375105857849121, "step": 86700 }, { "epoch": 0.5154222467916139, "grad_norm": 1.7942448854446411, "learning_rate": 0.00019718776493052133, "loss": 0.6973090648651123, "step": 86710 }, { "epoch": 0.5154816888682823, "grad_norm": 1.9229199886322021, "learning_rate": 0.00019718622080684313, "loss": 0.7281176567077636, "step": 86720 }, { "epoch": 0.5155411309449507, "grad_norm": 1.6921380758285522, "learning_rate": 0.00019718467626609452, "loss": 0.6456908226013184, "step": 86730 }, { "epoch": 0.5156005730216191, "grad_norm": 1.8697712421417236, "learning_rate": 0.0001971831313082829, "loss": 0.6677539825439454, "step": 86740 }, { "epoch": 0.5156600150982875, "grad_norm": 1.3409419059753418, "learning_rate": 0.0001971815859334157, "loss": 0.6687289714813233, "step": 86750 }, { "epoch": 0.5157194571749558, "grad_norm": 1.5892060995101929, "learning_rate": 0.00019718004014150026, "loss": 0.6725920677185059, "step": 86760 }, { "epoch": 0.5157788992516242, "grad_norm": 1.3579485416412354, "learning_rate": 0.000197178493932544, "loss": 0.6707422256469726, "step": 86770 }, { "epoch": 0.5158383413282926, "grad_norm": 1.7593073844909668, "learning_rate": 0.00019717694730655435, "loss": 0.6794427871704102, "step": 86780 }, { "epoch": 0.5158977834049611, "grad_norm": 2.0552563667297363, "learning_rate": 0.00019717540026353866, "loss": 0.6871954917907714, "step": 86790 }, { "epoch": 0.5159572254816295, "grad_norm": 1.8756638765335083, "learning_rate": 0.00019717385280350433, "loss": 0.6239628791809082, "step": 86800 }, { "epoch": 0.5160166675582978, "grad_norm": 2.0799639225006104, "learning_rate": 0.00019717230492645875, "loss": 0.6736989974975586, "step": 86810 }, { "epoch": 0.5160761096349662, "grad_norm": 1.7870796918869019, "learning_rate": 0.0001971707566324094, "loss": 0.6702061653137207, "step": 86820 }, { "epoch": 0.5161355517116346, "grad_norm": 1.9328850507736206, "learning_rate": 0.0001971692079213636, "loss": 0.6174234867095947, "step": 86830 }, { "epoch": 0.516194993788303, "grad_norm": 1.5608580112457275, "learning_rate": 0.00019716765879332883, "loss": 0.6612548351287841, "step": 86840 }, { "epoch": 0.5162544358649713, "grad_norm": 1.3192639350891113, "learning_rate": 0.00019716610924831247, "loss": 0.6767183303833008, "step": 86850 }, { "epoch": 0.5163138779416397, "grad_norm": 1.553617000579834, "learning_rate": 0.00019716455928632192, "loss": 0.6855643272399903, "step": 86860 }, { "epoch": 0.5163733200183082, "grad_norm": 1.8254904747009277, "learning_rate": 0.00019716300890736457, "loss": 0.7249805450439453, "step": 86870 }, { "epoch": 0.5164327620949766, "grad_norm": 1.7217861413955688, "learning_rate": 0.00019716145811144787, "loss": 0.7530205249786377, "step": 86880 }, { "epoch": 0.516492204171645, "grad_norm": 1.6910400390625, "learning_rate": 0.0001971599068985793, "loss": 0.6959325790405273, "step": 86890 }, { "epoch": 0.5165516462483133, "grad_norm": 1.4253276586532593, "learning_rate": 0.00019715835526876619, "loss": 0.617801570892334, "step": 86900 }, { "epoch": 0.5166110883249817, "grad_norm": 2.4580273628234863, "learning_rate": 0.00019715680322201598, "loss": 0.7233466148376465, "step": 86910 }, { "epoch": 0.5166705304016501, "grad_norm": 1.4636750221252441, "learning_rate": 0.00019715525075833615, "loss": 0.6480134963989258, "step": 86920 }, { "epoch": 0.5167299724783185, "grad_norm": 1.7856944799423218, "learning_rate": 0.00019715369787773402, "loss": 0.6886481285095215, "step": 86930 }, { "epoch": 0.516789414554987, "grad_norm": 1.7359181642532349, "learning_rate": 0.0001971521445802171, "loss": 0.6858572483062744, "step": 86940 }, { "epoch": 0.5168488566316553, "grad_norm": 1.5292028188705444, "learning_rate": 0.0001971505908657928, "loss": 0.669422721862793, "step": 86950 }, { "epoch": 0.5169082987083237, "grad_norm": 1.79835844039917, "learning_rate": 0.00019714903673446858, "loss": 0.691001558303833, "step": 86960 }, { "epoch": 0.5169677407849921, "grad_norm": 1.8964062929153442, "learning_rate": 0.00019714748218625184, "loss": 0.6998315334320069, "step": 86970 }, { "epoch": 0.5170271828616605, "grad_norm": 1.8806768655776978, "learning_rate": 0.00019714592722115004, "loss": 0.6589799880981445, "step": 86980 }, { "epoch": 0.5170866249383288, "grad_norm": 1.428977131843567, "learning_rate": 0.00019714437183917057, "loss": 0.7294624328613282, "step": 86990 }, { "epoch": 0.5171460670149972, "grad_norm": 2.0728859901428223, "learning_rate": 0.0001971428160403209, "loss": 0.6647823810577392, "step": 87000 }, { "epoch": 0.5172055090916656, "grad_norm": 1.4390531778335571, "learning_rate": 0.00019714125982460849, "loss": 0.6643452644348145, "step": 87010 }, { "epoch": 0.517264951168334, "grad_norm": 1.8766831159591675, "learning_rate": 0.0001971397031920408, "loss": 0.7177562236785888, "step": 87020 }, { "epoch": 0.5173243932450025, "grad_norm": 1.7809102535247803, "learning_rate": 0.0001971381461426252, "loss": 0.622772216796875, "step": 87030 }, { "epoch": 0.5173838353216708, "grad_norm": 2.01542329788208, "learning_rate": 0.00019713658867636922, "loss": 0.7145045280456543, "step": 87040 }, { "epoch": 0.5174432773983392, "grad_norm": 1.7994351387023926, "learning_rate": 0.00019713503079328025, "loss": 0.6325618743896484, "step": 87050 }, { "epoch": 0.5175027194750076, "grad_norm": 1.7216755151748657, "learning_rate": 0.0001971334724933658, "loss": 0.6532476902008056, "step": 87060 }, { "epoch": 0.517562161551676, "grad_norm": 2.005746364593506, "learning_rate": 0.00019713191377663327, "loss": 0.7669440269470215, "step": 87070 }, { "epoch": 0.5176216036283443, "grad_norm": 1.563382863998413, "learning_rate": 0.00019713035464309018, "loss": 0.6924991607666016, "step": 87080 }, { "epoch": 0.5176810457050127, "grad_norm": 1.7659728527069092, "learning_rate": 0.00019712879509274392, "loss": 0.663287353515625, "step": 87090 }, { "epoch": 0.5177404877816811, "grad_norm": 1.9546128511428833, "learning_rate": 0.00019712723512560194, "loss": 0.733013916015625, "step": 87100 }, { "epoch": 0.5177999298583496, "grad_norm": 1.8531460762023926, "learning_rate": 0.00019712567474167178, "loss": 0.6570324420928955, "step": 87110 }, { "epoch": 0.517859371935018, "grad_norm": 1.5831658840179443, "learning_rate": 0.00019712411394096085, "loss": 0.6242714405059815, "step": 87120 }, { "epoch": 0.5179188140116863, "grad_norm": 1.8216456174850464, "learning_rate": 0.00019712255272347665, "loss": 0.6376162528991699, "step": 87130 }, { "epoch": 0.5179782560883547, "grad_norm": 1.5213731527328491, "learning_rate": 0.00019712099108922662, "loss": 0.6834880828857421, "step": 87140 }, { "epoch": 0.5180376981650231, "grad_norm": 1.5058295726776123, "learning_rate": 0.00019711942903821822, "loss": 0.6705190181732178, "step": 87150 }, { "epoch": 0.5180971402416915, "grad_norm": 2.062349796295166, "learning_rate": 0.000197117866570459, "loss": 0.7118313789367676, "step": 87160 }, { "epoch": 0.5181565823183599, "grad_norm": 1.895912528038025, "learning_rate": 0.00019711630368595632, "loss": 0.6301619529724121, "step": 87170 }, { "epoch": 0.5182160243950282, "grad_norm": 1.623895287513733, "learning_rate": 0.00019711474038471772, "loss": 0.6864739418029785, "step": 87180 }, { "epoch": 0.5182754664716966, "grad_norm": 1.552351713180542, "learning_rate": 0.00019711317666675068, "loss": 0.6705114364624023, "step": 87190 }, { "epoch": 0.5183349085483651, "grad_norm": 2.0758254528045654, "learning_rate": 0.0001971116125320627, "loss": 0.709381103515625, "step": 87200 }, { "epoch": 0.5183943506250335, "grad_norm": 1.7682652473449707, "learning_rate": 0.0001971100479806612, "loss": 0.7233596801757812, "step": 87210 }, { "epoch": 0.5184537927017018, "grad_norm": 1.6414321660995483, "learning_rate": 0.00019710848301255368, "loss": 0.7175004005432128, "step": 87220 }, { "epoch": 0.5185132347783702, "grad_norm": 1.955863118171692, "learning_rate": 0.00019710691762774772, "loss": 0.6773772239685059, "step": 87230 }, { "epoch": 0.5185726768550386, "grad_norm": 2.0287389755249023, "learning_rate": 0.00019710535182625066, "loss": 0.6794014930725097, "step": 87240 }, { "epoch": 0.518632118931707, "grad_norm": 1.944451093673706, "learning_rate": 0.0001971037856080701, "loss": 0.6877158164978028, "step": 87250 }, { "epoch": 0.5186915610083754, "grad_norm": 1.6777307987213135, "learning_rate": 0.00019710221897321345, "loss": 0.7267829895019531, "step": 87260 }, { "epoch": 0.5187510030850437, "grad_norm": 2.5099105834960938, "learning_rate": 0.0001971006519216883, "loss": 0.6605793476104737, "step": 87270 }, { "epoch": 0.5188104451617122, "grad_norm": 2.5340185165405273, "learning_rate": 0.00019709908445350208, "loss": 0.7191972732543945, "step": 87280 }, { "epoch": 0.5188698872383806, "grad_norm": 1.4411087036132812, "learning_rate": 0.0001970975165686623, "loss": 0.7136425495147705, "step": 87290 }, { "epoch": 0.518929329315049, "grad_norm": 2.08197283744812, "learning_rate": 0.00019709594826717647, "loss": 0.7223280429840088, "step": 87300 }, { "epoch": 0.5189887713917174, "grad_norm": 1.9089826345443726, "learning_rate": 0.0001970943795490521, "loss": 0.6903616428375244, "step": 87310 }, { "epoch": 0.5190482134683857, "grad_norm": 1.6350197792053223, "learning_rate": 0.00019709281041429665, "loss": 0.6620685577392578, "step": 87320 }, { "epoch": 0.5191076555450541, "grad_norm": 1.672121524810791, "learning_rate": 0.00019709124086291768, "loss": 0.717478084564209, "step": 87330 }, { "epoch": 0.5191670976217225, "grad_norm": 1.5972191095352173, "learning_rate": 0.00019708967089492266, "loss": 0.718419885635376, "step": 87340 }, { "epoch": 0.5192265396983909, "grad_norm": 1.9070650339126587, "learning_rate": 0.00019708810051031914, "loss": 0.6425045013427735, "step": 87350 }, { "epoch": 0.5192859817750592, "grad_norm": 1.5634171962738037, "learning_rate": 0.0001970865297091146, "loss": 0.6587841033935546, "step": 87360 }, { "epoch": 0.5193454238517277, "grad_norm": 1.3607197999954224, "learning_rate": 0.00019708495849131655, "loss": 0.6905010223388672, "step": 87370 }, { "epoch": 0.5194048659283961, "grad_norm": 1.8538029193878174, "learning_rate": 0.00019708338685693253, "loss": 0.6582104682922363, "step": 87380 }, { "epoch": 0.5194643080050645, "grad_norm": 1.649629831314087, "learning_rate": 0.00019708181480597003, "loss": 0.7003049850463867, "step": 87390 }, { "epoch": 0.5195237500817329, "grad_norm": 1.9417606592178345, "learning_rate": 0.0001970802423384366, "loss": 0.7213644981384277, "step": 87400 }, { "epoch": 0.5195831921584012, "grad_norm": 1.7921656370162964, "learning_rate": 0.00019707866945433973, "loss": 0.6759033203125, "step": 87410 }, { "epoch": 0.5196426342350696, "grad_norm": 1.4795063734054565, "learning_rate": 0.00019707709615368697, "loss": 0.6830156803131103, "step": 87420 }, { "epoch": 0.519702076311738, "grad_norm": 1.9697566032409668, "learning_rate": 0.00019707552243648587, "loss": 0.7464371681213379, "step": 87430 }, { "epoch": 0.5197615183884065, "grad_norm": 1.4809596538543701, "learning_rate": 0.0001970739483027439, "loss": 0.6875076770782471, "step": 87440 }, { "epoch": 0.5198209604650748, "grad_norm": 2.1152095794677734, "learning_rate": 0.00019707237375246863, "loss": 0.6852397918701172, "step": 87450 }, { "epoch": 0.5198804025417432, "grad_norm": 2.2047457695007324, "learning_rate": 0.00019707079878566756, "loss": 0.7181129455566406, "step": 87460 }, { "epoch": 0.5199398446184116, "grad_norm": 1.87864351272583, "learning_rate": 0.00019706922340234826, "loss": 0.6822893142700195, "step": 87470 }, { "epoch": 0.51999928669508, "grad_norm": 1.4049569368362427, "learning_rate": 0.00019706764760251823, "loss": 0.7092269897460938, "step": 87480 }, { "epoch": 0.5200587287717484, "grad_norm": 1.3237377405166626, "learning_rate": 0.00019706607138618505, "loss": 0.6572965145111084, "step": 87490 }, { "epoch": 0.5201181708484167, "grad_norm": 1.66909921169281, "learning_rate": 0.00019706449475335625, "loss": 0.6842324256896972, "step": 87500 }, { "epoch": 0.5201776129250851, "grad_norm": 1.83573579788208, "learning_rate": 0.0001970629177040393, "loss": 0.6733081340789795, "step": 87510 }, { "epoch": 0.5202370550017535, "grad_norm": 1.7610523700714111, "learning_rate": 0.00019706134023824185, "loss": 0.7306359291076661, "step": 87520 }, { "epoch": 0.520296497078422, "grad_norm": 1.8724703788757324, "learning_rate": 0.0001970597623559714, "loss": 0.7183724403381347, "step": 87530 }, { "epoch": 0.5203559391550904, "grad_norm": 1.7278064489364624, "learning_rate": 0.00019705818405723547, "loss": 0.6543851852416992, "step": 87540 }, { "epoch": 0.5204153812317587, "grad_norm": 2.0450546741485596, "learning_rate": 0.0001970566053420417, "loss": 0.6596301078796387, "step": 87550 }, { "epoch": 0.5204748233084271, "grad_norm": 1.6779446601867676, "learning_rate": 0.00019705502621039753, "loss": 0.6408087730407714, "step": 87560 }, { "epoch": 0.5205342653850955, "grad_norm": 1.4978811740875244, "learning_rate": 0.00019705344666231058, "loss": 0.6744073867797852, "step": 87570 }, { "epoch": 0.5205937074617639, "grad_norm": 1.8759124279022217, "learning_rate": 0.0001970518666977884, "loss": 0.6919241905212402, "step": 87580 }, { "epoch": 0.5206531495384322, "grad_norm": 1.654944896697998, "learning_rate": 0.0001970502863168385, "loss": 0.6760237693786622, "step": 87590 }, { "epoch": 0.5207125916151006, "grad_norm": 1.7694188356399536, "learning_rate": 0.00019704870551946852, "loss": 0.6206132411956787, "step": 87600 }, { "epoch": 0.520772033691769, "grad_norm": 1.763347864151001, "learning_rate": 0.00019704712430568594, "loss": 0.7321927070617675, "step": 87610 }, { "epoch": 0.5208314757684375, "grad_norm": 1.756961464881897, "learning_rate": 0.00019704554267549842, "loss": 0.6965909957885742, "step": 87620 }, { "epoch": 0.5208909178451059, "grad_norm": 1.5797405242919922, "learning_rate": 0.00019704396062891343, "loss": 0.7556170463562012, "step": 87630 }, { "epoch": 0.5209503599217742, "grad_norm": 1.7423608303070068, "learning_rate": 0.0001970423781659386, "loss": 0.6647404670715332, "step": 87640 }, { "epoch": 0.5210098019984426, "grad_norm": 1.497898817062378, "learning_rate": 0.0001970407952865815, "loss": 0.6935537338256836, "step": 87650 }, { "epoch": 0.521069244075111, "grad_norm": 1.4735862016677856, "learning_rate": 0.0001970392119908496, "loss": 0.6513954162597656, "step": 87660 }, { "epoch": 0.5211286861517794, "grad_norm": 1.6412771940231323, "learning_rate": 0.00019703762827875062, "loss": 0.6931467056274414, "step": 87670 }, { "epoch": 0.5211881282284478, "grad_norm": 1.5943294763565063, "learning_rate": 0.00019703604415029205, "loss": 0.6883820533752442, "step": 87680 }, { "epoch": 0.5212475703051161, "grad_norm": 1.9948359727859497, "learning_rate": 0.00019703445960548148, "loss": 0.6853862285614014, "step": 87690 }, { "epoch": 0.5213070123817846, "grad_norm": 1.7992576360702515, "learning_rate": 0.0001970328746443265, "loss": 0.7339448928833008, "step": 87700 }, { "epoch": 0.521366454458453, "grad_norm": 1.9611252546310425, "learning_rate": 0.0001970312892668347, "loss": 0.742380952835083, "step": 87710 }, { "epoch": 0.5214258965351214, "grad_norm": 1.648672103881836, "learning_rate": 0.00019702970347301366, "loss": 0.6829002380371094, "step": 87720 }, { "epoch": 0.5214853386117897, "grad_norm": 1.6021591424942017, "learning_rate": 0.00019702811726287096, "loss": 0.6933640956878662, "step": 87730 }, { "epoch": 0.5215447806884581, "grad_norm": 1.9991536140441895, "learning_rate": 0.0001970265306364142, "loss": 0.7095531463623047, "step": 87740 }, { "epoch": 0.5216042227651265, "grad_norm": 1.613356351852417, "learning_rate": 0.0001970249435936509, "loss": 0.6462968826293946, "step": 87750 }, { "epoch": 0.5216636648417949, "grad_norm": 1.734481930732727, "learning_rate": 0.0001970233561345888, "loss": 0.6131065368652344, "step": 87760 }, { "epoch": 0.5217231069184634, "grad_norm": 1.7216401100158691, "learning_rate": 0.00019702176825923536, "loss": 0.6350455284118652, "step": 87770 }, { "epoch": 0.5217825489951317, "grad_norm": 1.8509619235992432, "learning_rate": 0.00019702017996759818, "loss": 0.6421628952026367, "step": 87780 }, { "epoch": 0.5218419910718001, "grad_norm": 1.7052934169769287, "learning_rate": 0.00019701859125968496, "loss": 0.7316159248352051, "step": 87790 }, { "epoch": 0.5219014331484685, "grad_norm": 1.528013825416565, "learning_rate": 0.0001970170021355032, "loss": 0.7117880821228028, "step": 87800 }, { "epoch": 0.5219608752251369, "grad_norm": 1.7610505819320679, "learning_rate": 0.00019701541259506053, "loss": 0.6602500438690185, "step": 87810 }, { "epoch": 0.5220203173018052, "grad_norm": 1.7803786993026733, "learning_rate": 0.00019701382263836455, "loss": 0.6659069061279297, "step": 87820 }, { "epoch": 0.5220797593784736, "grad_norm": 1.3884856700897217, "learning_rate": 0.00019701223226542295, "loss": 0.668721866607666, "step": 87830 }, { "epoch": 0.522139201455142, "grad_norm": 1.43856680393219, "learning_rate": 0.00019701064147624323, "loss": 0.748799180984497, "step": 87840 }, { "epoch": 0.5221986435318104, "grad_norm": 1.6083120107650757, "learning_rate": 0.000197009050270833, "loss": 0.665815019607544, "step": 87850 }, { "epoch": 0.5222580856084789, "grad_norm": 1.4593125581741333, "learning_rate": 0.00019700745864919996, "loss": 0.6808189392089844, "step": 87860 }, { "epoch": 0.5223175276851472, "grad_norm": 1.778483510017395, "learning_rate": 0.00019700586661135165, "loss": 0.65386962890625, "step": 87870 }, { "epoch": 0.5223769697618156, "grad_norm": 2.924999713897705, "learning_rate": 0.00019700427415729571, "loss": 0.673157787322998, "step": 87880 }, { "epoch": 0.522436411838484, "grad_norm": 2.0373520851135254, "learning_rate": 0.00019700268128703977, "loss": 0.7323809623718261, "step": 87890 }, { "epoch": 0.5224958539151524, "grad_norm": 2.0476667881011963, "learning_rate": 0.00019700108800059144, "loss": 0.669945764541626, "step": 87900 }, { "epoch": 0.5225552959918208, "grad_norm": 2.014805316925049, "learning_rate": 0.0001969994942979583, "loss": 0.7201725006103515, "step": 87910 }, { "epoch": 0.5226147380684891, "grad_norm": 2.1043901443481445, "learning_rate": 0.00019699790017914804, "loss": 0.6897227764129639, "step": 87920 }, { "epoch": 0.5226741801451575, "grad_norm": 1.6624140739440918, "learning_rate": 0.00019699630564416824, "loss": 0.7053107261657715, "step": 87930 }, { "epoch": 0.522733622221826, "grad_norm": 1.7115129232406616, "learning_rate": 0.00019699471069302657, "loss": 0.7032456398010254, "step": 87940 }, { "epoch": 0.5227930642984944, "grad_norm": 1.8360038995742798, "learning_rate": 0.00019699311532573062, "loss": 0.673225212097168, "step": 87950 }, { "epoch": 0.5228525063751627, "grad_norm": 1.304740071296692, "learning_rate": 0.00019699151954228803, "loss": 0.6144514083862305, "step": 87960 }, { "epoch": 0.5229119484518311, "grad_norm": 1.7217304706573486, "learning_rate": 0.00019698992334270645, "loss": 0.6842032432556152, "step": 87970 }, { "epoch": 0.5229713905284995, "grad_norm": 2.308915615081787, "learning_rate": 0.0001969883267269935, "loss": 0.6872132301330567, "step": 87980 }, { "epoch": 0.5230308326051679, "grad_norm": 1.670305609703064, "learning_rate": 0.00019698672969515682, "loss": 0.7342926025390625, "step": 87990 }, { "epoch": 0.5230902746818363, "grad_norm": 1.5680099725723267, "learning_rate": 0.00019698513224720402, "loss": 0.702731990814209, "step": 88000 }, { "epoch": 0.5231497167585046, "grad_norm": 1.8718434572219849, "learning_rate": 0.00019698353438314285, "loss": 0.7019525527954101, "step": 88010 }, { "epoch": 0.523209158835173, "grad_norm": 1.664555549621582, "learning_rate": 0.00019698193610298085, "loss": 0.6678374767303467, "step": 88020 }, { "epoch": 0.5232686009118415, "grad_norm": 1.5257350206375122, "learning_rate": 0.00019698033740672566, "loss": 0.6646055221557617, "step": 88030 }, { "epoch": 0.5233280429885099, "grad_norm": 1.2008401155471802, "learning_rate": 0.00019697873829438496, "loss": 0.6341273784637451, "step": 88040 }, { "epoch": 0.5233874850651782, "grad_norm": 1.645533800125122, "learning_rate": 0.00019697713876596642, "loss": 0.7287701606750489, "step": 88050 }, { "epoch": 0.5234469271418466, "grad_norm": 2.047139883041382, "learning_rate": 0.0001969755388214777, "loss": 0.6708256721496582, "step": 88060 }, { "epoch": 0.523506369218515, "grad_norm": 2.0339863300323486, "learning_rate": 0.00019697393846092637, "loss": 0.6399115562438965, "step": 88070 }, { "epoch": 0.5235658112951834, "grad_norm": 1.9074032306671143, "learning_rate": 0.0001969723376843202, "loss": 0.6689016819000244, "step": 88080 }, { "epoch": 0.5236252533718518, "grad_norm": 1.4014755487442017, "learning_rate": 0.00019697073649166676, "loss": 0.7079440116882324, "step": 88090 }, { "epoch": 0.5236846954485201, "grad_norm": 1.8062541484832764, "learning_rate": 0.00019696913488297373, "loss": 0.7560806274414062, "step": 88100 }, { "epoch": 0.5237441375251886, "grad_norm": 1.6236933469772339, "learning_rate": 0.0001969675328582488, "loss": 0.7197512626647949, "step": 88110 }, { "epoch": 0.523803579601857, "grad_norm": 1.6862690448760986, "learning_rate": 0.0001969659304174996, "loss": 0.7132050514221191, "step": 88120 }, { "epoch": 0.5238630216785254, "grad_norm": 1.6334000825881958, "learning_rate": 0.00019696432756073382, "loss": 0.6674332618713379, "step": 88130 }, { "epoch": 0.5239224637551938, "grad_norm": 1.5865761041641235, "learning_rate": 0.0001969627242879591, "loss": 0.7225632667541504, "step": 88140 }, { "epoch": 0.5239819058318621, "grad_norm": 1.691354751586914, "learning_rate": 0.00019696112059918317, "loss": 0.665591049194336, "step": 88150 }, { "epoch": 0.5240413479085305, "grad_norm": 1.6239356994628906, "learning_rate": 0.00019695951649441359, "loss": 0.7733654975891113, "step": 88160 }, { "epoch": 0.5241007899851989, "grad_norm": 1.8009295463562012, "learning_rate": 0.00019695791197365815, "loss": 0.7068726062774658, "step": 88170 }, { "epoch": 0.5241602320618673, "grad_norm": 1.8013932704925537, "learning_rate": 0.00019695630703692448, "loss": 0.6926453113555908, "step": 88180 }, { "epoch": 0.5242196741385357, "grad_norm": 1.8726511001586914, "learning_rate": 0.00019695470168422025, "loss": 0.5946137428283691, "step": 88190 }, { "epoch": 0.5242791162152041, "grad_norm": 1.4649207592010498, "learning_rate": 0.00019695309591555312, "loss": 0.64375, "step": 88200 }, { "epoch": 0.5243385582918725, "grad_norm": 2.2443671226501465, "learning_rate": 0.00019695148973093084, "loss": 0.6560717582702636, "step": 88210 }, { "epoch": 0.5243980003685409, "grad_norm": 1.5299049615859985, "learning_rate": 0.000196949883130361, "loss": 0.658745527267456, "step": 88220 }, { "epoch": 0.5244574424452093, "grad_norm": 1.8390026092529297, "learning_rate": 0.00019694827611385133, "loss": 0.697368574142456, "step": 88230 }, { "epoch": 0.5245168845218776, "grad_norm": 1.6449968814849854, "learning_rate": 0.00019694666868140957, "loss": 0.6841185569763184, "step": 88240 }, { "epoch": 0.524576326598546, "grad_norm": 1.338577389717102, "learning_rate": 0.00019694506083304335, "loss": 0.7218029022216796, "step": 88250 }, { "epoch": 0.5246357686752144, "grad_norm": 1.5899606943130493, "learning_rate": 0.00019694345256876034, "loss": 0.6497746467590332, "step": 88260 }, { "epoch": 0.5246952107518829, "grad_norm": 1.7840099334716797, "learning_rate": 0.0001969418438885683, "loss": 0.7150643825531006, "step": 88270 }, { "epoch": 0.5247546528285513, "grad_norm": 2.0189099311828613, "learning_rate": 0.0001969402347924749, "loss": 0.6457048416137695, "step": 88280 }, { "epoch": 0.5248140949052196, "grad_norm": 1.4452162981033325, "learning_rate": 0.0001969386252804878, "loss": 0.6540412425994873, "step": 88290 }, { "epoch": 0.524873536981888, "grad_norm": 1.946912407875061, "learning_rate": 0.00019693701535261472, "loss": 0.6081990242004395, "step": 88300 }, { "epoch": 0.5249329790585564, "grad_norm": 1.8373277187347412, "learning_rate": 0.0001969354050088634, "loss": 0.7658275604248047, "step": 88310 }, { "epoch": 0.5249924211352248, "grad_norm": 1.6914609670639038, "learning_rate": 0.0001969337942492415, "loss": 0.7402840614318847, "step": 88320 }, { "epoch": 0.5250518632118931, "grad_norm": 1.809531807899475, "learning_rate": 0.00019693218307375673, "loss": 0.7412787914276123, "step": 88330 }, { "epoch": 0.5251113052885615, "grad_norm": 1.8771671056747437, "learning_rate": 0.00019693057148241684, "loss": 0.656679344177246, "step": 88340 }, { "epoch": 0.52517074736523, "grad_norm": 1.9551986455917358, "learning_rate": 0.00019692895947522943, "loss": 0.6731697082519531, "step": 88350 }, { "epoch": 0.5252301894418984, "grad_norm": 1.987244725227356, "learning_rate": 0.00019692734705220236, "loss": 0.6435539722442627, "step": 88360 }, { "epoch": 0.5252896315185668, "grad_norm": 1.8361762762069702, "learning_rate": 0.00019692573421334326, "loss": 0.6720970153808594, "step": 88370 }, { "epoch": 0.5253490735952351, "grad_norm": 1.4696509838104248, "learning_rate": 0.00019692412095865985, "loss": 0.6846570014953614, "step": 88380 }, { "epoch": 0.5254085156719035, "grad_norm": 1.8046479225158691, "learning_rate": 0.0001969225072881598, "loss": 0.7379392623901367, "step": 88390 }, { "epoch": 0.5254679577485719, "grad_norm": 1.6255638599395752, "learning_rate": 0.00019692089320185097, "loss": 0.6824304580688476, "step": 88400 }, { "epoch": 0.5255273998252403, "grad_norm": 1.3627550601959229, "learning_rate": 0.00019691927869974093, "loss": 0.6430413246154785, "step": 88410 }, { "epoch": 0.5255868419019086, "grad_norm": 1.6926935911178589, "learning_rate": 0.0001969176637818375, "loss": 0.6631784439086914, "step": 88420 }, { "epoch": 0.525646283978577, "grad_norm": 1.7484235763549805, "learning_rate": 0.00019691604844814838, "loss": 0.6626623153686524, "step": 88430 }, { "epoch": 0.5257057260552455, "grad_norm": 1.7672545909881592, "learning_rate": 0.00019691443269868124, "loss": 0.6405612468719483, "step": 88440 }, { "epoch": 0.5257651681319139, "grad_norm": 2.0806212425231934, "learning_rate": 0.0001969128165334439, "loss": 0.7172722816467285, "step": 88450 }, { "epoch": 0.5258246102085823, "grad_norm": 1.9806437492370605, "learning_rate": 0.00019691119995244403, "loss": 0.6606704235076905, "step": 88460 }, { "epoch": 0.5258840522852506, "grad_norm": 2.0758864879608154, "learning_rate": 0.00019690958295568939, "loss": 0.6619668006896973, "step": 88470 }, { "epoch": 0.525943494361919, "grad_norm": 1.518586277961731, "learning_rate": 0.00019690796554318768, "loss": 0.7041766166687011, "step": 88480 }, { "epoch": 0.5260029364385874, "grad_norm": 1.678503155708313, "learning_rate": 0.00019690634771494668, "loss": 0.6711455345153808, "step": 88490 }, { "epoch": 0.5260623785152558, "grad_norm": 1.58892822265625, "learning_rate": 0.00019690472947097413, "loss": 0.6588641166687011, "step": 88500 }, { "epoch": 0.5261218205919242, "grad_norm": 1.337111234664917, "learning_rate": 0.00019690311081127775, "loss": 0.6024918556213379, "step": 88510 }, { "epoch": 0.5261812626685926, "grad_norm": 1.771227478981018, "learning_rate": 0.00019690149173586527, "loss": 0.7031859397888184, "step": 88520 }, { "epoch": 0.526240704745261, "grad_norm": 1.823686957359314, "learning_rate": 0.00019689987224474448, "loss": 0.650383186340332, "step": 88530 }, { "epoch": 0.5263001468219294, "grad_norm": 1.8893424272537231, "learning_rate": 0.00019689825233792308, "loss": 0.7007170677185058, "step": 88540 }, { "epoch": 0.5263595888985978, "grad_norm": 1.4487154483795166, "learning_rate": 0.00019689663201540887, "loss": 0.6555306911468506, "step": 88550 }, { "epoch": 0.5264190309752661, "grad_norm": 1.7380443811416626, "learning_rate": 0.00019689501127720952, "loss": 0.7059513568878174, "step": 88560 }, { "epoch": 0.5264784730519345, "grad_norm": 1.7234846353530884, "learning_rate": 0.00019689339012333288, "loss": 0.6609573364257812, "step": 88570 }, { "epoch": 0.5265379151286029, "grad_norm": 1.6975950002670288, "learning_rate": 0.00019689176855378665, "loss": 0.6529611110687256, "step": 88580 }, { "epoch": 0.5265973572052713, "grad_norm": 1.9415479898452759, "learning_rate": 0.00019689014656857858, "loss": 0.6992051124572753, "step": 88590 }, { "epoch": 0.5266567992819398, "grad_norm": 1.678619384765625, "learning_rate": 0.00019688852416771644, "loss": 0.6839459419250489, "step": 88600 }, { "epoch": 0.5267162413586081, "grad_norm": 1.7963801622390747, "learning_rate": 0.000196886901351208, "loss": 0.6881457805633545, "step": 88610 }, { "epoch": 0.5267756834352765, "grad_norm": 1.647515892982483, "learning_rate": 0.00019688527811906106, "loss": 0.7485865116119385, "step": 88620 }, { "epoch": 0.5268351255119449, "grad_norm": 1.4695076942443848, "learning_rate": 0.00019688365447128328, "loss": 0.708715295791626, "step": 88630 }, { "epoch": 0.5268945675886133, "grad_norm": 1.896177053451538, "learning_rate": 0.00019688203040788254, "loss": 0.6918067455291748, "step": 88640 }, { "epoch": 0.5269540096652817, "grad_norm": 1.6288542747497559, "learning_rate": 0.00019688040592886653, "loss": 0.7378984451293945, "step": 88650 }, { "epoch": 0.52701345174195, "grad_norm": 2.0794849395751953, "learning_rate": 0.00019687878103424305, "loss": 0.6738540172576905, "step": 88660 }, { "epoch": 0.5270728938186184, "grad_norm": 1.4451009035110474, "learning_rate": 0.0001968771557240199, "loss": 0.6559143543243409, "step": 88670 }, { "epoch": 0.5271323358952869, "grad_norm": 2.0719943046569824, "learning_rate": 0.0001968755299982048, "loss": 0.7062429428100586, "step": 88680 }, { "epoch": 0.5271917779719553, "grad_norm": 1.470333218574524, "learning_rate": 0.0001968739038568056, "loss": 0.7168414115905761, "step": 88690 }, { "epoch": 0.5272512200486236, "grad_norm": 1.5664775371551514, "learning_rate": 0.00019687227729983, "loss": 0.7307490348815918, "step": 88700 }, { "epoch": 0.527310662125292, "grad_norm": 1.4712461233139038, "learning_rate": 0.0001968706503272858, "loss": 0.6547304153442383, "step": 88710 }, { "epoch": 0.5273701042019604, "grad_norm": 1.438264012336731, "learning_rate": 0.00019686902293918084, "loss": 0.7171442985534668, "step": 88720 }, { "epoch": 0.5274295462786288, "grad_norm": 1.5518940687179565, "learning_rate": 0.00019686739513552284, "loss": 0.6797720432281494, "step": 88730 }, { "epoch": 0.5274889883552972, "grad_norm": 1.9738272428512573, "learning_rate": 0.0001968657669163196, "loss": 0.6430760383605957, "step": 88740 }, { "epoch": 0.5275484304319655, "grad_norm": 1.8027937412261963, "learning_rate": 0.00019686413828157891, "loss": 0.7199087142944336, "step": 88750 }, { "epoch": 0.527607872508634, "grad_norm": 1.493132472038269, "learning_rate": 0.0001968625092313086, "loss": 0.7158559322357178, "step": 88760 }, { "epoch": 0.5276673145853024, "grad_norm": 2.2822604179382324, "learning_rate": 0.00019686087976551644, "loss": 0.6883099555969239, "step": 88770 }, { "epoch": 0.5277267566619708, "grad_norm": 1.7887638807296753, "learning_rate": 0.00019685924988421021, "loss": 0.6883132457733154, "step": 88780 }, { "epoch": 0.5277861987386391, "grad_norm": 1.4312028884887695, "learning_rate": 0.0001968576195873977, "loss": 0.653503131866455, "step": 88790 }, { "epoch": 0.5278456408153075, "grad_norm": 1.7082335948944092, "learning_rate": 0.00019685598887508673, "loss": 0.6834047317504883, "step": 88800 }, { "epoch": 0.5279050828919759, "grad_norm": 1.4283276796340942, "learning_rate": 0.00019685435774728508, "loss": 0.6264003276824951, "step": 88810 }, { "epoch": 0.5279645249686443, "grad_norm": 1.7198444604873657, "learning_rate": 0.0001968527262040006, "loss": 0.6997719287872315, "step": 88820 }, { "epoch": 0.5280239670453127, "grad_norm": 2.1019678115844727, "learning_rate": 0.00019685109424524104, "loss": 0.6989928245544433, "step": 88830 }, { "epoch": 0.528083409121981, "grad_norm": 1.9573860168457031, "learning_rate": 0.00019684946187101423, "loss": 0.6769833564758301, "step": 88840 }, { "epoch": 0.5281428511986495, "grad_norm": 1.986779808998108, "learning_rate": 0.00019684782908132797, "loss": 0.6257647514343262, "step": 88850 }, { "epoch": 0.5282022932753179, "grad_norm": 1.5661704540252686, "learning_rate": 0.00019684619587619008, "loss": 0.7065332412719727, "step": 88860 }, { "epoch": 0.5282617353519863, "grad_norm": 2.2024285793304443, "learning_rate": 0.0001968445622556084, "loss": 0.7252634525299072, "step": 88870 }, { "epoch": 0.5283211774286547, "grad_norm": 2.292888641357422, "learning_rate": 0.00019684292821959068, "loss": 0.7477963447570801, "step": 88880 }, { "epoch": 0.528380619505323, "grad_norm": 1.5951279401779175, "learning_rate": 0.0001968412937681448, "loss": 0.6871618270874024, "step": 88890 }, { "epoch": 0.5284400615819914, "grad_norm": 1.8925162553787231, "learning_rate": 0.0001968396589012785, "loss": 0.6855423450469971, "step": 88900 }, { "epoch": 0.5284995036586598, "grad_norm": 2.178327798843384, "learning_rate": 0.0001968380236189997, "loss": 0.7073321342468262, "step": 88910 }, { "epoch": 0.5285589457353282, "grad_norm": 2.086278200149536, "learning_rate": 0.00019683638792131615, "loss": 0.7595158576965332, "step": 88920 }, { "epoch": 0.5286183878119965, "grad_norm": 1.614113688468933, "learning_rate": 0.0001968347518082357, "loss": 0.6509012222290039, "step": 88930 }, { "epoch": 0.528677829888665, "grad_norm": 1.6595224142074585, "learning_rate": 0.0001968331152797662, "loss": 0.7380576610565186, "step": 88940 }, { "epoch": 0.5287372719653334, "grad_norm": 1.4834915399551392, "learning_rate": 0.00019683147833591543, "loss": 0.5945744991302491, "step": 88950 }, { "epoch": 0.5287967140420018, "grad_norm": 1.5613259077072144, "learning_rate": 0.00019682984097669126, "loss": 0.7413212776184082, "step": 88960 }, { "epoch": 0.5288561561186702, "grad_norm": 1.7061398029327393, "learning_rate": 0.0001968282032021015, "loss": 0.7089046955108642, "step": 88970 }, { "epoch": 0.5289155981953385, "grad_norm": 1.5611625909805298, "learning_rate": 0.00019682656501215397, "loss": 0.6529406547546387, "step": 88980 }, { "epoch": 0.5289750402720069, "grad_norm": 1.5315134525299072, "learning_rate": 0.00019682492640685657, "loss": 0.6888100624084472, "step": 88990 }, { "epoch": 0.5290344823486753, "grad_norm": 1.5391759872436523, "learning_rate": 0.00019682328738621706, "loss": 0.6308835983276367, "step": 89000 }, { "epoch": 0.5290939244253438, "grad_norm": 1.5819566249847412, "learning_rate": 0.00019682164795024334, "loss": 0.7055451393127441, "step": 89010 }, { "epoch": 0.5291533665020122, "grad_norm": 1.642051100730896, "learning_rate": 0.00019682000809894323, "loss": 0.6759149074554444, "step": 89020 }, { "epoch": 0.5292128085786805, "grad_norm": 1.7400627136230469, "learning_rate": 0.00019681836783232455, "loss": 0.6786182403564454, "step": 89030 }, { "epoch": 0.5292722506553489, "grad_norm": 2.0095386505126953, "learning_rate": 0.00019681672715039517, "loss": 0.6902544021606445, "step": 89040 }, { "epoch": 0.5293316927320173, "grad_norm": 1.6683485507965088, "learning_rate": 0.000196815086053163, "loss": 0.692633867263794, "step": 89050 }, { "epoch": 0.5293911348086857, "grad_norm": 1.72511625289917, "learning_rate": 0.00019681344454063578, "loss": 0.7454835891723632, "step": 89060 }, { "epoch": 0.529450576885354, "grad_norm": 1.5702718496322632, "learning_rate": 0.0001968118026128214, "loss": 0.6739184379577636, "step": 89070 }, { "epoch": 0.5295100189620224, "grad_norm": 1.3833087682724, "learning_rate": 0.00019681016026972773, "loss": 0.6746801376342774, "step": 89080 }, { "epoch": 0.5295694610386908, "grad_norm": 1.8192598819732666, "learning_rate": 0.00019680851751136268, "loss": 0.6627191543579102, "step": 89090 }, { "epoch": 0.5296289031153593, "grad_norm": 1.4300698041915894, "learning_rate": 0.000196806874337734, "loss": 0.6539302349090577, "step": 89100 }, { "epoch": 0.5296883451920277, "grad_norm": 1.877485990524292, "learning_rate": 0.0001968052307488496, "loss": 0.7721672058105469, "step": 89110 }, { "epoch": 0.529747787268696, "grad_norm": 1.6040303707122803, "learning_rate": 0.00019680358674471735, "loss": 0.7081903457641602, "step": 89120 }, { "epoch": 0.5298072293453644, "grad_norm": 1.5132150650024414, "learning_rate": 0.00019680194232534512, "loss": 0.7459121704101562, "step": 89130 }, { "epoch": 0.5298666714220328, "grad_norm": 1.7742551565170288, "learning_rate": 0.00019680029749074077, "loss": 0.751526927947998, "step": 89140 }, { "epoch": 0.5299261134987012, "grad_norm": 1.708924651145935, "learning_rate": 0.00019679865224091217, "loss": 0.6956700325012207, "step": 89150 }, { "epoch": 0.5299855555753695, "grad_norm": 1.7090476751327515, "learning_rate": 0.00019679700657586715, "loss": 0.7097079753875732, "step": 89160 }, { "epoch": 0.5300449976520379, "grad_norm": 1.6928166151046753, "learning_rate": 0.00019679536049561366, "loss": 0.6414259910583496, "step": 89170 }, { "epoch": 0.5301044397287064, "grad_norm": 1.7920348644256592, "learning_rate": 0.00019679371400015946, "loss": 0.6887961387634277, "step": 89180 }, { "epoch": 0.5301638818053748, "grad_norm": 2.1189820766448975, "learning_rate": 0.00019679206708951257, "loss": 0.6942375659942627, "step": 89190 }, { "epoch": 0.5302233238820432, "grad_norm": 1.5399659872055054, "learning_rate": 0.00019679041976368076, "loss": 0.678398323059082, "step": 89200 }, { "epoch": 0.5302827659587115, "grad_norm": 2.1078548431396484, "learning_rate": 0.00019678877202267193, "loss": 0.7203266143798828, "step": 89210 }, { "epoch": 0.5303422080353799, "grad_norm": 1.5231430530548096, "learning_rate": 0.00019678712386649402, "loss": 0.6523933410644531, "step": 89220 }, { "epoch": 0.5304016501120483, "grad_norm": 1.3561002016067505, "learning_rate": 0.00019678547529515484, "loss": 0.68858642578125, "step": 89230 }, { "epoch": 0.5304610921887167, "grad_norm": 1.7025492191314697, "learning_rate": 0.00019678382630866233, "loss": 0.6584555625915527, "step": 89240 }, { "epoch": 0.5305205342653851, "grad_norm": 2.223759651184082, "learning_rate": 0.00019678217690702435, "loss": 0.6565100669860839, "step": 89250 }, { "epoch": 0.5305799763420534, "grad_norm": 1.638641357421875, "learning_rate": 0.00019678052709024878, "loss": 0.7325901031494141, "step": 89260 }, { "epoch": 0.5306394184187219, "grad_norm": 1.6522588729858398, "learning_rate": 0.00019677887685834352, "loss": 0.7387624740600586, "step": 89270 }, { "epoch": 0.5306988604953903, "grad_norm": 1.5183106660842896, "learning_rate": 0.0001967772262113165, "loss": 0.6253456592559814, "step": 89280 }, { "epoch": 0.5307583025720587, "grad_norm": 2.0335466861724854, "learning_rate": 0.0001967755751491756, "loss": 0.6262427806854248, "step": 89290 }, { "epoch": 0.530817744648727, "grad_norm": 1.9153189659118652, "learning_rate": 0.00019677392367192868, "loss": 0.6965387344360352, "step": 89300 }, { "epoch": 0.5308771867253954, "grad_norm": 1.8393741846084595, "learning_rate": 0.00019677227177958368, "loss": 0.6952882766723633, "step": 89310 }, { "epoch": 0.5309366288020638, "grad_norm": 1.2725218534469604, "learning_rate": 0.0001967706194721485, "loss": 0.6937280654907226, "step": 89320 }, { "epoch": 0.5309960708787322, "grad_norm": 2.0270705223083496, "learning_rate": 0.000196768966749631, "loss": 0.7041483879089355, "step": 89330 }, { "epoch": 0.5310555129554007, "grad_norm": 1.6815779209136963, "learning_rate": 0.00019676731361203915, "loss": 0.660871171951294, "step": 89340 }, { "epoch": 0.531114955032069, "grad_norm": 1.2195484638214111, "learning_rate": 0.00019676566005938083, "loss": 0.636801815032959, "step": 89350 }, { "epoch": 0.5311743971087374, "grad_norm": 1.3059104681015015, "learning_rate": 0.00019676400609166392, "loss": 0.6208516120910644, "step": 89360 }, { "epoch": 0.5312338391854058, "grad_norm": 1.458189606666565, "learning_rate": 0.00019676235170889637, "loss": 0.7065288543701171, "step": 89370 }, { "epoch": 0.5312932812620742, "grad_norm": 1.9945502281188965, "learning_rate": 0.00019676069691108608, "loss": 0.7347279548645019, "step": 89380 }, { "epoch": 0.5313527233387426, "grad_norm": 1.9539544582366943, "learning_rate": 0.000196759041698241, "loss": 0.6460066795349121, "step": 89390 }, { "epoch": 0.5314121654154109, "grad_norm": 1.4729206562042236, "learning_rate": 0.00019675738607036897, "loss": 0.6799644470214844, "step": 89400 }, { "epoch": 0.5314716074920793, "grad_norm": 1.6473342180252075, "learning_rate": 0.00019675573002747799, "loss": 0.6798279762268067, "step": 89410 }, { "epoch": 0.5315310495687477, "grad_norm": 1.4771497249603271, "learning_rate": 0.0001967540735695759, "loss": 0.7012438297271728, "step": 89420 }, { "epoch": 0.5315904916454162, "grad_norm": 1.4771313667297363, "learning_rate": 0.00019675241669667076, "loss": 0.6684220314025879, "step": 89430 }, { "epoch": 0.5316499337220845, "grad_norm": 1.5849332809448242, "learning_rate": 0.00019675075940877034, "loss": 0.6864026546478271, "step": 89440 }, { "epoch": 0.5317093757987529, "grad_norm": 1.912077784538269, "learning_rate": 0.00019674910170588267, "loss": 0.7032238006591797, "step": 89450 }, { "epoch": 0.5317688178754213, "grad_norm": 1.894662857055664, "learning_rate": 0.00019674744358801565, "loss": 0.7098536968231202, "step": 89460 }, { "epoch": 0.5318282599520897, "grad_norm": 1.785400152206421, "learning_rate": 0.0001967457850551772, "loss": 0.6388952255249023, "step": 89470 }, { "epoch": 0.5318877020287581, "grad_norm": 1.682642936706543, "learning_rate": 0.00019674412610737525, "loss": 0.6765448570251464, "step": 89480 }, { "epoch": 0.5319471441054264, "grad_norm": 1.4814364910125732, "learning_rate": 0.00019674246674461775, "loss": 0.680094575881958, "step": 89490 }, { "epoch": 0.5320065861820948, "grad_norm": 1.6880903244018555, "learning_rate": 0.00019674080696691263, "loss": 0.6633177757263183, "step": 89500 }, { "epoch": 0.5320660282587633, "grad_norm": 1.971053957939148, "learning_rate": 0.00019673914677426787, "loss": 0.7179351806640625, "step": 89510 }, { "epoch": 0.5321254703354317, "grad_norm": 1.5161004066467285, "learning_rate": 0.00019673748616669137, "loss": 0.65775146484375, "step": 89520 }, { "epoch": 0.5321849124121, "grad_norm": 1.9417502880096436, "learning_rate": 0.00019673582514419106, "loss": 0.6654541015625, "step": 89530 }, { "epoch": 0.5322443544887684, "grad_norm": 1.5586520433425903, "learning_rate": 0.00019673416370677492, "loss": 0.6794410705566406, "step": 89540 }, { "epoch": 0.5323037965654368, "grad_norm": 2.357424736022949, "learning_rate": 0.0001967325018544509, "loss": 0.8061962127685547, "step": 89550 }, { "epoch": 0.5323632386421052, "grad_norm": 1.8212449550628662, "learning_rate": 0.00019673083958722697, "loss": 0.6733715057373046, "step": 89560 }, { "epoch": 0.5324226807187736, "grad_norm": 1.4934320449829102, "learning_rate": 0.00019672917690511096, "loss": 0.6472752571105957, "step": 89570 }, { "epoch": 0.5324821227954419, "grad_norm": 1.5836786031723022, "learning_rate": 0.00019672751380811097, "loss": 0.6921926498413086, "step": 89580 }, { "epoch": 0.5325415648721104, "grad_norm": 1.703705072402954, "learning_rate": 0.00019672585029623487, "loss": 0.6394941329956054, "step": 89590 }, { "epoch": 0.5326010069487788, "grad_norm": 2.011005163192749, "learning_rate": 0.00019672418636949065, "loss": 0.6927246570587158, "step": 89600 }, { "epoch": 0.5326604490254472, "grad_norm": 1.764620065689087, "learning_rate": 0.00019672252202788628, "loss": 0.6217769622802735, "step": 89610 }, { "epoch": 0.5327198911021156, "grad_norm": 1.4509224891662598, "learning_rate": 0.00019672085727142968, "loss": 0.7540989875793457, "step": 89620 }, { "epoch": 0.5327793331787839, "grad_norm": 2.1515631675720215, "learning_rate": 0.00019671919210012887, "loss": 0.6695720672607421, "step": 89630 }, { "epoch": 0.5328387752554523, "grad_norm": 1.5492370128631592, "learning_rate": 0.00019671752651399178, "loss": 0.7192886352539063, "step": 89640 }, { "epoch": 0.5328982173321207, "grad_norm": 1.4956722259521484, "learning_rate": 0.00019671586051302634, "loss": 0.6940820217132568, "step": 89650 }, { "epoch": 0.5329576594087891, "grad_norm": 1.3534053564071655, "learning_rate": 0.0001967141940972406, "loss": 0.6625210762023925, "step": 89660 }, { "epoch": 0.5330171014854574, "grad_norm": 1.8531759977340698, "learning_rate": 0.0001967125272666425, "loss": 0.649934196472168, "step": 89670 }, { "epoch": 0.5330765435621259, "grad_norm": 1.5005793571472168, "learning_rate": 0.00019671086002123997, "loss": 0.6623315811157227, "step": 89680 }, { "epoch": 0.5331359856387943, "grad_norm": 1.819222331047058, "learning_rate": 0.00019670919236104107, "loss": 0.7177134990692139, "step": 89690 }, { "epoch": 0.5331954277154627, "grad_norm": 1.6786750555038452, "learning_rate": 0.0001967075242860537, "loss": 0.6309603691101074, "step": 89700 }, { "epoch": 0.5332548697921311, "grad_norm": 1.9663633108139038, "learning_rate": 0.0001967058557962859, "loss": 0.7020215511322021, "step": 89710 }, { "epoch": 0.5333143118687994, "grad_norm": 1.6505322456359863, "learning_rate": 0.0001967041868917456, "loss": 0.6437830924987793, "step": 89720 }, { "epoch": 0.5333737539454678, "grad_norm": 1.7633006572723389, "learning_rate": 0.00019670251757244079, "loss": 0.7186562538146972, "step": 89730 }, { "epoch": 0.5334331960221362, "grad_norm": 1.7762399911880493, "learning_rate": 0.0001967008478383795, "loss": 0.6575538635253906, "step": 89740 }, { "epoch": 0.5334926380988047, "grad_norm": 1.5354727506637573, "learning_rate": 0.00019669917768956968, "loss": 0.7204977512359619, "step": 89750 }, { "epoch": 0.5335520801754731, "grad_norm": 1.7405694723129272, "learning_rate": 0.0001966975071260193, "loss": 0.6583889961242676, "step": 89760 }, { "epoch": 0.5336115222521414, "grad_norm": 1.5153881311416626, "learning_rate": 0.0001966958361477364, "loss": 0.6774587631225586, "step": 89770 }, { "epoch": 0.5336709643288098, "grad_norm": 2.406926155090332, "learning_rate": 0.00019669416475472895, "loss": 0.6927237510681152, "step": 89780 }, { "epoch": 0.5337304064054782, "grad_norm": 1.893336534500122, "learning_rate": 0.00019669249294700499, "loss": 0.6936708927154541, "step": 89790 }, { "epoch": 0.5337898484821466, "grad_norm": 1.7508034706115723, "learning_rate": 0.0001966908207245724, "loss": 0.6510453224182129, "step": 89800 }, { "epoch": 0.5338492905588149, "grad_norm": 1.6226235628128052, "learning_rate": 0.0001966891480874393, "loss": 0.6100370407104492, "step": 89810 }, { "epoch": 0.5339087326354833, "grad_norm": 2.159276247024536, "learning_rate": 0.00019668747503561365, "loss": 0.7076696395874024, "step": 89820 }, { "epoch": 0.5339681747121517, "grad_norm": 1.9024677276611328, "learning_rate": 0.00019668580156910343, "loss": 0.664832592010498, "step": 89830 }, { "epoch": 0.5340276167888202, "grad_norm": 1.4840697050094604, "learning_rate": 0.00019668412768791667, "loss": 0.6545554637908936, "step": 89840 }, { "epoch": 0.5340870588654886, "grad_norm": 1.4102901220321655, "learning_rate": 0.00019668245339206136, "loss": 0.7036768913269043, "step": 89850 }, { "epoch": 0.5341465009421569, "grad_norm": 1.498033881187439, "learning_rate": 0.00019668077868154556, "loss": 0.6899523735046387, "step": 89860 }, { "epoch": 0.5342059430188253, "grad_norm": 1.528047800064087, "learning_rate": 0.0001966791035563772, "loss": 0.7378619194030762, "step": 89870 }, { "epoch": 0.5342653850954937, "grad_norm": 1.5549750328063965, "learning_rate": 0.00019667742801656436, "loss": 0.6436193466186524, "step": 89880 }, { "epoch": 0.5343248271721621, "grad_norm": 1.5888102054595947, "learning_rate": 0.00019667575206211503, "loss": 0.6539769649505616, "step": 89890 }, { "epoch": 0.5343842692488304, "grad_norm": 1.584749698638916, "learning_rate": 0.0001966740756930372, "loss": 0.6777916431427002, "step": 89900 }, { "epoch": 0.5344437113254988, "grad_norm": 1.536040186882019, "learning_rate": 0.00019667239890933894, "loss": 0.6405616760253906, "step": 89910 }, { "epoch": 0.5345031534021673, "grad_norm": 1.5775151252746582, "learning_rate": 0.00019667072171102823, "loss": 0.621828556060791, "step": 89920 }, { "epoch": 0.5345625954788357, "grad_norm": 1.5230849981307983, "learning_rate": 0.00019666904409811314, "loss": 0.746005916595459, "step": 89930 }, { "epoch": 0.5346220375555041, "grad_norm": 1.82048499584198, "learning_rate": 0.00019666736607060168, "loss": 0.746752119064331, "step": 89940 }, { "epoch": 0.5346814796321724, "grad_norm": 2.0966668128967285, "learning_rate": 0.00019666568762850183, "loss": 0.6982853412628174, "step": 89950 }, { "epoch": 0.5347409217088408, "grad_norm": 1.5242884159088135, "learning_rate": 0.00019666400877182166, "loss": 0.7243447303771973, "step": 89960 }, { "epoch": 0.5348003637855092, "grad_norm": 1.2999963760375977, "learning_rate": 0.0001966623295005692, "loss": 0.6906085014343262, "step": 89970 }, { "epoch": 0.5348598058621776, "grad_norm": 1.963588833808899, "learning_rate": 0.00019666064981475244, "loss": 0.6739256858825684, "step": 89980 }, { "epoch": 0.534919247938846, "grad_norm": 1.7105733156204224, "learning_rate": 0.0001966589697143795, "loss": 0.697879409790039, "step": 89990 }, { "epoch": 0.5349786900155143, "grad_norm": 1.9890077114105225, "learning_rate": 0.00019665728919945836, "loss": 0.7253478050231934, "step": 90000 }, { "epoch": 0.5350381320921828, "grad_norm": 1.7620720863342285, "learning_rate": 0.00019665560826999707, "loss": 0.7106370449066162, "step": 90010 }, { "epoch": 0.5350975741688512, "grad_norm": 1.4388524293899536, "learning_rate": 0.00019665392692600367, "loss": 0.5904484748840332, "step": 90020 }, { "epoch": 0.5351570162455196, "grad_norm": 2.2161147594451904, "learning_rate": 0.00019665224516748618, "loss": 0.7123501777648926, "step": 90030 }, { "epoch": 0.5352164583221879, "grad_norm": 1.9711405038833618, "learning_rate": 0.0001966505629944527, "loss": 0.7187719345092773, "step": 90040 }, { "epoch": 0.5352759003988563, "grad_norm": 2.12971568107605, "learning_rate": 0.0001966488804069112, "loss": 0.6689622879028321, "step": 90050 }, { "epoch": 0.5353353424755247, "grad_norm": 1.641160249710083, "learning_rate": 0.0001966471974048698, "loss": 0.6888678073883057, "step": 90060 }, { "epoch": 0.5353947845521931, "grad_norm": 1.7771897315979004, "learning_rate": 0.00019664551398833655, "loss": 0.6475047111511231, "step": 90070 }, { "epoch": 0.5354542266288616, "grad_norm": 1.7434184551239014, "learning_rate": 0.00019664383015731944, "loss": 0.6696049213409424, "step": 90080 }, { "epoch": 0.5355136687055299, "grad_norm": 1.7425886392593384, "learning_rate": 0.00019664214591182656, "loss": 0.6939101696014405, "step": 90090 }, { "epoch": 0.5355731107821983, "grad_norm": 1.3421005010604858, "learning_rate": 0.00019664046125186598, "loss": 0.621918773651123, "step": 90100 }, { "epoch": 0.5356325528588667, "grad_norm": 1.926340103149414, "learning_rate": 0.00019663877617744576, "loss": 0.7229567527770996, "step": 90110 }, { "epoch": 0.5356919949355351, "grad_norm": 2.0399954319000244, "learning_rate": 0.00019663709068857391, "loss": 0.6829143524169922, "step": 90120 }, { "epoch": 0.5357514370122035, "grad_norm": 1.5169299840927124, "learning_rate": 0.00019663540478525858, "loss": 0.7092281818389893, "step": 90130 }, { "epoch": 0.5358108790888718, "grad_norm": 2.035165309906006, "learning_rate": 0.00019663371846750778, "loss": 0.7026806831359863, "step": 90140 }, { "epoch": 0.5358703211655402, "grad_norm": 1.749739170074463, "learning_rate": 0.00019663203173532958, "loss": 0.7050095558166504, "step": 90150 }, { "epoch": 0.5359297632422086, "grad_norm": 1.8638030290603638, "learning_rate": 0.00019663034458873203, "loss": 0.6900921821594238, "step": 90160 }, { "epoch": 0.5359892053188771, "grad_norm": 1.7800401449203491, "learning_rate": 0.00019662865702772323, "loss": 0.7028833389282226, "step": 90170 }, { "epoch": 0.5360486473955454, "grad_norm": 1.527302861213684, "learning_rate": 0.00019662696905231122, "loss": 0.7169447898864746, "step": 90180 }, { "epoch": 0.5361080894722138, "grad_norm": 1.7302663326263428, "learning_rate": 0.00019662528066250416, "loss": 0.6324092864990234, "step": 90190 }, { "epoch": 0.5361675315488822, "grad_norm": 1.3277400732040405, "learning_rate": 0.00019662359185831002, "loss": 0.6902861595153809, "step": 90200 }, { "epoch": 0.5362269736255506, "grad_norm": 1.838798999786377, "learning_rate": 0.00019662190263973698, "loss": 0.7379555225372314, "step": 90210 }, { "epoch": 0.536286415702219, "grad_norm": 1.5467450618743896, "learning_rate": 0.000196620213006793, "loss": 0.6457428932189941, "step": 90220 }, { "epoch": 0.5363458577788873, "grad_norm": 1.5198465585708618, "learning_rate": 0.00019661852295948626, "loss": 0.6222233772277832, "step": 90230 }, { "epoch": 0.5364052998555557, "grad_norm": 1.7184854745864868, "learning_rate": 0.00019661683249782482, "loss": 0.6715566635131835, "step": 90240 }, { "epoch": 0.5364647419322242, "grad_norm": 1.2940727472305298, "learning_rate": 0.00019661514162181676, "loss": 0.6587287425994873, "step": 90250 }, { "epoch": 0.5365241840088926, "grad_norm": 1.6469374895095825, "learning_rate": 0.00019661345033147016, "loss": 0.5903207778930664, "step": 90260 }, { "epoch": 0.5365836260855609, "grad_norm": 1.907379388809204, "learning_rate": 0.00019661175862679308, "loss": 0.6240402221679687, "step": 90270 }, { "epoch": 0.5366430681622293, "grad_norm": 1.7166143655776978, "learning_rate": 0.00019661006650779371, "loss": 0.6797723770141602, "step": 90280 }, { "epoch": 0.5367025102388977, "grad_norm": 1.8436064720153809, "learning_rate": 0.00019660837397448007, "loss": 0.6804222106933594, "step": 90290 }, { "epoch": 0.5367619523155661, "grad_norm": 1.9889888763427734, "learning_rate": 0.00019660668102686025, "loss": 0.6844470977783204, "step": 90300 }, { "epoch": 0.5368213943922345, "grad_norm": 1.269896149635315, "learning_rate": 0.00019660498766494242, "loss": 0.6612157821655273, "step": 90310 }, { "epoch": 0.5368808364689028, "grad_norm": 1.8017141819000244, "learning_rate": 0.00019660329388873458, "loss": 0.6182193756103516, "step": 90320 }, { "epoch": 0.5369402785455712, "grad_norm": 2.1257426738739014, "learning_rate": 0.0001966015996982449, "loss": 0.6405776500701904, "step": 90330 }, { "epoch": 0.5369997206222397, "grad_norm": 1.8446102142333984, "learning_rate": 0.0001965999050934815, "loss": 0.6911211967468261, "step": 90340 }, { "epoch": 0.5370591626989081, "grad_norm": 1.639897346496582, "learning_rate": 0.00019659821007445244, "loss": 0.6229710578918457, "step": 90350 }, { "epoch": 0.5371186047755765, "grad_norm": 1.621874451637268, "learning_rate": 0.0001965965146411658, "loss": 0.6636247634887695, "step": 90360 }, { "epoch": 0.5371780468522448, "grad_norm": 1.8309768438339233, "learning_rate": 0.00019659481879362976, "loss": 0.6899830818176269, "step": 90370 }, { "epoch": 0.5372374889289132, "grad_norm": 1.8253777027130127, "learning_rate": 0.00019659312253185243, "loss": 0.6971806526184082, "step": 90380 }, { "epoch": 0.5372969310055816, "grad_norm": 1.7182306051254272, "learning_rate": 0.00019659142585584188, "loss": 0.6650477886199951, "step": 90390 }, { "epoch": 0.53735637308225, "grad_norm": 1.4119155406951904, "learning_rate": 0.00019658972876560626, "loss": 0.6833680152893067, "step": 90400 }, { "epoch": 0.5374158151589183, "grad_norm": 2.9160802364349365, "learning_rate": 0.00019658803126115367, "loss": 0.7095763206481933, "step": 90410 }, { "epoch": 0.5374752572355868, "grad_norm": 1.7149590253829956, "learning_rate": 0.00019658633334249223, "loss": 0.6210546016693115, "step": 90420 }, { "epoch": 0.5375346993122552, "grad_norm": 1.7683255672454834, "learning_rate": 0.00019658463500963008, "loss": 0.6926563262939454, "step": 90430 }, { "epoch": 0.5375941413889236, "grad_norm": 1.7908776998519897, "learning_rate": 0.0001965829362625753, "loss": 0.8078304290771484, "step": 90440 }, { "epoch": 0.537653583465592, "grad_norm": 1.8305855989456177, "learning_rate": 0.0001965812371013361, "loss": 0.6930799961090088, "step": 90450 }, { "epoch": 0.5377130255422603, "grad_norm": 1.8092126846313477, "learning_rate": 0.0001965795375259205, "loss": 0.7262487888336182, "step": 90460 }, { "epoch": 0.5377724676189287, "grad_norm": 1.8911159038543701, "learning_rate": 0.00019657783753633675, "loss": 0.7087748050689697, "step": 90470 }, { "epoch": 0.5378319096955971, "grad_norm": 1.6813747882843018, "learning_rate": 0.0001965761371325929, "loss": 0.6832069396972656, "step": 90480 }, { "epoch": 0.5378913517722655, "grad_norm": 1.4175423383712769, "learning_rate": 0.00019657443631469705, "loss": 0.6694885730743408, "step": 90490 }, { "epoch": 0.537950793848934, "grad_norm": 1.770229697227478, "learning_rate": 0.00019657273508265742, "loss": 0.6581823348999023, "step": 90500 }, { "epoch": 0.5380102359256023, "grad_norm": 1.608903408050537, "learning_rate": 0.00019657103343648217, "loss": 0.6459342956542968, "step": 90510 }, { "epoch": 0.5380696780022707, "grad_norm": 1.636779546737671, "learning_rate": 0.00019656933137617933, "loss": 0.6747799873352051, "step": 90520 }, { "epoch": 0.5381291200789391, "grad_norm": 1.8764294385910034, "learning_rate": 0.0001965676289017571, "loss": 0.7251008510589599, "step": 90530 }, { "epoch": 0.5381885621556075, "grad_norm": 1.589728832244873, "learning_rate": 0.00019656592601322365, "loss": 0.7621238231658936, "step": 90540 }, { "epoch": 0.5382480042322758, "grad_norm": 1.3868834972381592, "learning_rate": 0.00019656422271058707, "loss": 0.6385833263397217, "step": 90550 }, { "epoch": 0.5383074463089442, "grad_norm": 1.7552533149719238, "learning_rate": 0.00019656251899385555, "loss": 0.7235040664672852, "step": 90560 }, { "epoch": 0.5383668883856126, "grad_norm": 4.415674209594727, "learning_rate": 0.00019656081486303724, "loss": 0.6938902854919433, "step": 90570 }, { "epoch": 0.538426330462281, "grad_norm": 1.4824398756027222, "learning_rate": 0.00019655911031814027, "loss": 0.7203763961791992, "step": 90580 }, { "epoch": 0.5384857725389495, "grad_norm": 1.8464927673339844, "learning_rate": 0.00019655740535917283, "loss": 0.6585572242736817, "step": 90590 }, { "epoch": 0.5385452146156178, "grad_norm": 1.7514139413833618, "learning_rate": 0.000196555699986143, "loss": 0.6980573654174804, "step": 90600 }, { "epoch": 0.5386046566922862, "grad_norm": 1.872887134552002, "learning_rate": 0.00019655399419905902, "loss": 0.6922843933105469, "step": 90610 }, { "epoch": 0.5386640987689546, "grad_norm": 2.057645320892334, "learning_rate": 0.000196552287997929, "loss": 0.6486973762512207, "step": 90620 }, { "epoch": 0.538723540845623, "grad_norm": 1.4819207191467285, "learning_rate": 0.00019655058138276117, "loss": 0.6456498146057129, "step": 90630 }, { "epoch": 0.5387829829222913, "grad_norm": 1.7967816591262817, "learning_rate": 0.0001965488743535636, "loss": 0.7105966567993164, "step": 90640 }, { "epoch": 0.5388424249989597, "grad_norm": 2.014821767807007, "learning_rate": 0.0001965471669103445, "loss": 0.7491089820861816, "step": 90650 }, { "epoch": 0.5389018670756281, "grad_norm": 1.7457705736160278, "learning_rate": 0.00019654545905311205, "loss": 0.660047197341919, "step": 90660 }, { "epoch": 0.5389613091522966, "grad_norm": 1.7017977237701416, "learning_rate": 0.0001965437507818744, "loss": 0.6734893798828125, "step": 90670 }, { "epoch": 0.539020751228965, "grad_norm": 1.4031286239624023, "learning_rate": 0.00019654204209663972, "loss": 0.6993938446044922, "step": 90680 }, { "epoch": 0.5390801933056333, "grad_norm": 2.133513927459717, "learning_rate": 0.00019654033299741622, "loss": 0.6396660327911377, "step": 90690 }, { "epoch": 0.5391396353823017, "grad_norm": 1.4783945083618164, "learning_rate": 0.00019653862348421202, "loss": 0.6586487770080567, "step": 90700 }, { "epoch": 0.5391990774589701, "grad_norm": 2.102773666381836, "learning_rate": 0.00019653691355703534, "loss": 0.7221261978149414, "step": 90710 }, { "epoch": 0.5392585195356385, "grad_norm": 1.4448286294937134, "learning_rate": 0.00019653520321589435, "loss": 0.6926140785217285, "step": 90720 }, { "epoch": 0.5393179616123069, "grad_norm": 1.8946678638458252, "learning_rate": 0.00019653349246079722, "loss": 0.6580323219299317, "step": 90730 }, { "epoch": 0.5393774036889752, "grad_norm": 1.5782055854797363, "learning_rate": 0.00019653178129175214, "loss": 0.6551563262939453, "step": 90740 }, { "epoch": 0.5394368457656437, "grad_norm": 1.7711161375045776, "learning_rate": 0.0001965300697087673, "loss": 0.7018893241882325, "step": 90750 }, { "epoch": 0.5394962878423121, "grad_norm": 1.861668586730957, "learning_rate": 0.00019652835771185088, "loss": 0.7291414260864257, "step": 90760 }, { "epoch": 0.5395557299189805, "grad_norm": 1.866245150566101, "learning_rate": 0.0001965266453010111, "loss": 0.6917037487030029, "step": 90770 }, { "epoch": 0.5396151719956488, "grad_norm": 1.7193909883499146, "learning_rate": 0.0001965249324762561, "loss": 0.6424661636352539, "step": 90780 }, { "epoch": 0.5396746140723172, "grad_norm": 1.3987644910812378, "learning_rate": 0.0001965232192375941, "loss": 0.6262881755828857, "step": 90790 }, { "epoch": 0.5397340561489856, "grad_norm": 2.0992302894592285, "learning_rate": 0.0001965215055850333, "loss": 0.648310375213623, "step": 90800 }, { "epoch": 0.539793498225654, "grad_norm": 1.3779700994491577, "learning_rate": 0.0001965197915185819, "loss": 0.6294572353363037, "step": 90810 }, { "epoch": 0.5398529403023224, "grad_norm": 1.6371053457260132, "learning_rate": 0.00019651807703824806, "loss": 0.6348965167999268, "step": 90820 }, { "epoch": 0.5399123823789908, "grad_norm": 1.6903334856033325, "learning_rate": 0.00019651636214404003, "loss": 0.6989034652709961, "step": 90830 }, { "epoch": 0.5399718244556592, "grad_norm": 1.9645112752914429, "learning_rate": 0.00019651464683596604, "loss": 0.6961724281311035, "step": 90840 }, { "epoch": 0.5400312665323276, "grad_norm": 1.510133981704712, "learning_rate": 0.00019651293111403421, "loss": 0.6454176902770996, "step": 90850 }, { "epoch": 0.540090708608996, "grad_norm": 1.6338173151016235, "learning_rate": 0.00019651121497825283, "loss": 0.638542890548706, "step": 90860 }, { "epoch": 0.5401501506856644, "grad_norm": 1.7833744287490845, "learning_rate": 0.00019650949842863, "loss": 0.7359737396240235, "step": 90870 }, { "epoch": 0.5402095927623327, "grad_norm": 1.279960036277771, "learning_rate": 0.00019650778146517405, "loss": 0.6816111087799073, "step": 90880 }, { "epoch": 0.5402690348390011, "grad_norm": 1.5734870433807373, "learning_rate": 0.00019650606408789313, "loss": 0.7042570590972901, "step": 90890 }, { "epoch": 0.5403284769156695, "grad_norm": 1.9699578285217285, "learning_rate": 0.00019650434629679548, "loss": 0.6784619331359864, "step": 90900 }, { "epoch": 0.540387918992338, "grad_norm": 1.6482146978378296, "learning_rate": 0.0001965026280918893, "loss": 0.6877678871154785, "step": 90910 }, { "epoch": 0.5404473610690063, "grad_norm": 1.2965389490127563, "learning_rate": 0.00019650090947318283, "loss": 0.6547848224639893, "step": 90920 }, { "epoch": 0.5405068031456747, "grad_norm": 1.8789544105529785, "learning_rate": 0.0001964991904406843, "loss": 0.7308574676513672, "step": 90930 }, { "epoch": 0.5405662452223431, "grad_norm": 1.9045664072036743, "learning_rate": 0.00019649747099440183, "loss": 0.7263065338134765, "step": 90940 }, { "epoch": 0.5406256872990115, "grad_norm": 1.4495855569839478, "learning_rate": 0.0001964957511343438, "loss": 0.6732467174530029, "step": 90950 }, { "epoch": 0.5406851293756799, "grad_norm": 1.825474739074707, "learning_rate": 0.00019649403086051832, "loss": 0.6667713165283203, "step": 90960 }, { "epoch": 0.5407445714523482, "grad_norm": 2.2018308639526367, "learning_rate": 0.0001964923101729337, "loss": 0.6781436920166015, "step": 90970 }, { "epoch": 0.5408040135290166, "grad_norm": 1.6386021375656128, "learning_rate": 0.0001964905890715981, "loss": 0.6558841705322266, "step": 90980 }, { "epoch": 0.540863455605685, "grad_norm": 1.4618306159973145, "learning_rate": 0.0001964888675565198, "loss": 0.7152820587158203, "step": 90990 }, { "epoch": 0.5409228976823535, "grad_norm": 2.058173894882202, "learning_rate": 0.00019648714562770701, "loss": 0.7377854824066162, "step": 91000 }, { "epoch": 0.5409823397590218, "grad_norm": 1.915323257446289, "learning_rate": 0.00019648542328516802, "loss": 0.697920846939087, "step": 91010 }, { "epoch": 0.5410417818356902, "grad_norm": 1.6777002811431885, "learning_rate": 0.000196483700528911, "loss": 0.6474527835845947, "step": 91020 }, { "epoch": 0.5411012239123586, "grad_norm": 1.7098079919815063, "learning_rate": 0.00019648197735894422, "loss": 0.6724397659301757, "step": 91030 }, { "epoch": 0.541160665989027, "grad_norm": 1.9068598747253418, "learning_rate": 0.00019648025377527596, "loss": 0.6913661003112793, "step": 91040 }, { "epoch": 0.5412201080656954, "grad_norm": 1.6711232662200928, "learning_rate": 0.00019647852977791437, "loss": 0.6705982208251953, "step": 91050 }, { "epoch": 0.5412795501423637, "grad_norm": 2.0503122806549072, "learning_rate": 0.0001964768053668678, "loss": 0.6931769371032714, "step": 91060 }, { "epoch": 0.5413389922190321, "grad_norm": 1.7921513319015503, "learning_rate": 0.0001964750805421444, "loss": 0.6988035202026367, "step": 91070 }, { "epoch": 0.5413984342957006, "grad_norm": 2.183682680130005, "learning_rate": 0.00019647335530375255, "loss": 0.7120217323303223, "step": 91080 }, { "epoch": 0.541457876372369, "grad_norm": 1.5856776237487793, "learning_rate": 0.00019647162965170036, "loss": 0.7103248596191406, "step": 91090 }, { "epoch": 0.5415173184490374, "grad_norm": 1.623942255973816, "learning_rate": 0.00019646990358599618, "loss": 0.716342830657959, "step": 91100 }, { "epoch": 0.5415767605257057, "grad_norm": 1.6561107635498047, "learning_rate": 0.00019646817710664824, "loss": 0.6859872341156006, "step": 91110 }, { "epoch": 0.5416362026023741, "grad_norm": 1.997033715248108, "learning_rate": 0.0001964664502136648, "loss": 0.7412765979766845, "step": 91120 }, { "epoch": 0.5416956446790425, "grad_norm": 1.5725314617156982, "learning_rate": 0.00019646472290705413, "loss": 0.6972557544708252, "step": 91130 }, { "epoch": 0.5417550867557109, "grad_norm": 1.6611255407333374, "learning_rate": 0.00019646299518682447, "loss": 0.6958849430084229, "step": 91140 }, { "epoch": 0.5418145288323792, "grad_norm": 1.9320480823516846, "learning_rate": 0.0001964612670529841, "loss": 0.6734319686889648, "step": 91150 }, { "epoch": 0.5418739709090477, "grad_norm": 1.6455494165420532, "learning_rate": 0.00019645953850554128, "loss": 0.5989916801452637, "step": 91160 }, { "epoch": 0.5419334129857161, "grad_norm": 1.7133845090866089, "learning_rate": 0.0001964578095445043, "loss": 0.6719035148620606, "step": 91170 }, { "epoch": 0.5419928550623845, "grad_norm": 1.642777442932129, "learning_rate": 0.00019645608016988138, "loss": 0.7413297176361084, "step": 91180 }, { "epoch": 0.5420522971390529, "grad_norm": 1.5886163711547852, "learning_rate": 0.00019645435038168085, "loss": 0.6917588233947753, "step": 91190 }, { "epoch": 0.5421117392157212, "grad_norm": 1.8538051843643188, "learning_rate": 0.00019645262017991096, "loss": 0.6839732170104981, "step": 91200 }, { "epoch": 0.5421711812923896, "grad_norm": 2.0212643146514893, "learning_rate": 0.00019645088956458, "loss": 0.6598105430603027, "step": 91210 }, { "epoch": 0.542230623369058, "grad_norm": 1.8717554807662964, "learning_rate": 0.0001964491585356962, "loss": 0.7177424907684327, "step": 91220 }, { "epoch": 0.5422900654457264, "grad_norm": 4.399541854858398, "learning_rate": 0.0001964474270932679, "loss": 0.6848005294799805, "step": 91230 }, { "epoch": 0.5423495075223947, "grad_norm": 1.8436155319213867, "learning_rate": 0.00019644569523730336, "loss": 0.6987300872802734, "step": 91240 }, { "epoch": 0.5424089495990632, "grad_norm": 1.8303797245025635, "learning_rate": 0.00019644396296781088, "loss": 0.7331077575683593, "step": 91250 }, { "epoch": 0.5424683916757316, "grad_norm": 1.616917371749878, "learning_rate": 0.0001964422302847987, "loss": 0.6698158264160157, "step": 91260 }, { "epoch": 0.5425278337524, "grad_norm": 1.7135059833526611, "learning_rate": 0.00019644049718827518, "loss": 0.740303373336792, "step": 91270 }, { "epoch": 0.5425872758290684, "grad_norm": 2.2142696380615234, "learning_rate": 0.00019643876367824855, "loss": 0.664125919342041, "step": 91280 }, { "epoch": 0.5426467179057367, "grad_norm": 1.837529182434082, "learning_rate": 0.00019643702975472707, "loss": 0.7011663913726807, "step": 91290 }, { "epoch": 0.5427061599824051, "grad_norm": 1.8771573305130005, "learning_rate": 0.00019643529541771916, "loss": 0.6307364463806152, "step": 91300 }, { "epoch": 0.5427656020590735, "grad_norm": 1.449065089225769, "learning_rate": 0.00019643356066723303, "loss": 0.6995034217834473, "step": 91310 }, { "epoch": 0.542825044135742, "grad_norm": 1.232692837715149, "learning_rate": 0.00019643182550327699, "loss": 0.6626636505126953, "step": 91320 }, { "epoch": 0.5428844862124104, "grad_norm": 1.818413257598877, "learning_rate": 0.0001964300899258593, "loss": 0.6807493209838867, "step": 91330 }, { "epoch": 0.5429439282890787, "grad_norm": 1.7005033493041992, "learning_rate": 0.0001964283539349884, "loss": 0.6755525588989257, "step": 91340 }, { "epoch": 0.5430033703657471, "grad_norm": 1.8957048654556274, "learning_rate": 0.0001964266175306724, "loss": 0.7179969310760498, "step": 91350 }, { "epoch": 0.5430628124424155, "grad_norm": 1.6821635961532593, "learning_rate": 0.00019642488071291975, "loss": 0.6649633407592773, "step": 91360 }, { "epoch": 0.5431222545190839, "grad_norm": 1.8236759901046753, "learning_rate": 0.00019642314348173874, "loss": 0.6659175872802734, "step": 91370 }, { "epoch": 0.5431816965957522, "grad_norm": 1.9222296476364136, "learning_rate": 0.0001964214058371376, "loss": 0.6660562038421631, "step": 91380 }, { "epoch": 0.5432411386724206, "grad_norm": 2.068059206008911, "learning_rate": 0.00019641966777912475, "loss": 0.7533321380615234, "step": 91390 }, { "epoch": 0.543300580749089, "grad_norm": 2.2939043045043945, "learning_rate": 0.00019641792930770842, "loss": 0.6988247871398926, "step": 91400 }, { "epoch": 0.5433600228257575, "grad_norm": 2.026348829269409, "learning_rate": 0.00019641619042289697, "loss": 0.651888370513916, "step": 91410 }, { "epoch": 0.5434194649024259, "grad_norm": 1.683310627937317, "learning_rate": 0.0001964144511246987, "loss": 0.6708554744720459, "step": 91420 }, { "epoch": 0.5434789069790942, "grad_norm": 1.5710947513580322, "learning_rate": 0.00019641271141312194, "loss": 0.703667163848877, "step": 91430 }, { "epoch": 0.5435383490557626, "grad_norm": 1.7129236459732056, "learning_rate": 0.000196410971288175, "loss": 0.6936793804168702, "step": 91440 }, { "epoch": 0.543597791132431, "grad_norm": 1.8716994524002075, "learning_rate": 0.00019640923074986625, "loss": 0.6606989860534668, "step": 91450 }, { "epoch": 0.5436572332090994, "grad_norm": 2.732820987701416, "learning_rate": 0.00019640748979820393, "loss": 0.6393170833587647, "step": 91460 }, { "epoch": 0.5437166752857678, "grad_norm": 1.3143607378005981, "learning_rate": 0.00019640574843319641, "loss": 0.7042161464691162, "step": 91470 }, { "epoch": 0.5437761173624361, "grad_norm": 2.108179807662964, "learning_rate": 0.00019640400665485206, "loss": 0.7188226699829101, "step": 91480 }, { "epoch": 0.5438355594391046, "grad_norm": 1.4595832824707031, "learning_rate": 0.00019640226446317917, "loss": 0.7138266086578369, "step": 91490 }, { "epoch": 0.543895001515773, "grad_norm": 1.5540199279785156, "learning_rate": 0.00019640052185818612, "loss": 0.6742222785949707, "step": 91500 }, { "epoch": 0.5439544435924414, "grad_norm": 1.6708316802978516, "learning_rate": 0.00019639877883988112, "loss": 0.6259293556213379, "step": 91510 }, { "epoch": 0.5440138856691097, "grad_norm": 1.7882920503616333, "learning_rate": 0.0001963970354082727, "loss": 0.6921464920043945, "step": 91520 }, { "epoch": 0.5440733277457781, "grad_norm": 1.5974310636520386, "learning_rate": 0.00019639529156336902, "loss": 0.7441354751586914, "step": 91530 }, { "epoch": 0.5441327698224465, "grad_norm": 1.5627696514129639, "learning_rate": 0.00019639354730517853, "loss": 0.7202095508575439, "step": 91540 }, { "epoch": 0.5441922118991149, "grad_norm": 1.8929084539413452, "learning_rate": 0.00019639180263370955, "loss": 0.6981307029724121, "step": 91550 }, { "epoch": 0.5442516539757833, "grad_norm": 1.3976812362670898, "learning_rate": 0.00019639005754897043, "loss": 0.6649635314941407, "step": 91560 }, { "epoch": 0.5443110960524516, "grad_norm": 1.7081687450408936, "learning_rate": 0.0001963883120509695, "loss": 0.6995395183563232, "step": 91570 }, { "epoch": 0.5443705381291201, "grad_norm": 1.5940488576889038, "learning_rate": 0.00019638656613971508, "loss": 0.6684479236602783, "step": 91580 }, { "epoch": 0.5444299802057885, "grad_norm": 1.6504019498825073, "learning_rate": 0.00019638481981521557, "loss": 0.6507750511169433, "step": 91590 }, { "epoch": 0.5444894222824569, "grad_norm": 1.5526124238967896, "learning_rate": 0.00019638307307747935, "loss": 0.7102984428405762, "step": 91600 }, { "epoch": 0.5445488643591252, "grad_norm": 1.6930886507034302, "learning_rate": 0.00019638132592651473, "loss": 0.6949090003967285, "step": 91610 }, { "epoch": 0.5446083064357936, "grad_norm": 1.5842349529266357, "learning_rate": 0.00019637957836233006, "loss": 0.6564242362976074, "step": 91620 }, { "epoch": 0.544667748512462, "grad_norm": 1.723784327507019, "learning_rate": 0.00019637783038493371, "loss": 0.749611759185791, "step": 91630 }, { "epoch": 0.5447271905891304, "grad_norm": 2.3614203929901123, "learning_rate": 0.00019637608199433407, "loss": 0.6506597518920898, "step": 91640 }, { "epoch": 0.5447866326657989, "grad_norm": 1.6104710102081299, "learning_rate": 0.00019637433319053945, "loss": 0.7255361557006836, "step": 91650 }, { "epoch": 0.5448460747424672, "grad_norm": 1.3167725801467896, "learning_rate": 0.00019637258397355825, "loss": 0.7062059879302979, "step": 91660 }, { "epoch": 0.5449055168191356, "grad_norm": 1.8172510862350464, "learning_rate": 0.00019637083434339886, "loss": 0.6783249855041504, "step": 91670 }, { "epoch": 0.544964958895804, "grad_norm": 1.4097626209259033, "learning_rate": 0.00019636908430006961, "loss": 0.6569728851318359, "step": 91680 }, { "epoch": 0.5450244009724724, "grad_norm": 1.5828261375427246, "learning_rate": 0.0001963673338435789, "loss": 0.6913491249084472, "step": 91690 }, { "epoch": 0.5450838430491408, "grad_norm": 1.9436392784118652, "learning_rate": 0.0001963655829739351, "loss": 0.6830332756042481, "step": 91700 }, { "epoch": 0.5451432851258091, "grad_norm": 1.6278916597366333, "learning_rate": 0.00019636383169114655, "loss": 0.6388773918151855, "step": 91710 }, { "epoch": 0.5452027272024775, "grad_norm": 1.9334943294525146, "learning_rate": 0.00019636207999522168, "loss": 0.7064157962799072, "step": 91720 }, { "epoch": 0.545262169279146, "grad_norm": 1.554470181465149, "learning_rate": 0.00019636032788616882, "loss": 0.7335880756378174, "step": 91730 }, { "epoch": 0.5453216113558144, "grad_norm": 2.207490921020508, "learning_rate": 0.00019635857536399638, "loss": 0.7059216499328613, "step": 91740 }, { "epoch": 0.5453810534324827, "grad_norm": 1.734872817993164, "learning_rate": 0.00019635682242871274, "loss": 0.6169010639190674, "step": 91750 }, { "epoch": 0.5454404955091511, "grad_norm": 2.2585296630859375, "learning_rate": 0.00019635506908032626, "loss": 0.7311759948730469, "step": 91760 }, { "epoch": 0.5454999375858195, "grad_norm": 1.6623773574829102, "learning_rate": 0.00019635331531884538, "loss": 0.6805819511413574, "step": 91770 }, { "epoch": 0.5455593796624879, "grad_norm": 1.5181142091751099, "learning_rate": 0.00019635156114427844, "loss": 0.6760053157806396, "step": 91780 }, { "epoch": 0.5456188217391563, "grad_norm": 2.352311611175537, "learning_rate": 0.00019634980655663386, "loss": 0.6804476737976074, "step": 91790 }, { "epoch": 0.5456782638158246, "grad_norm": 1.2447237968444824, "learning_rate": 0.00019634805155592004, "loss": 0.66696195602417, "step": 91800 }, { "epoch": 0.545737705892493, "grad_norm": 2.097053050994873, "learning_rate": 0.00019634629614214536, "loss": 0.6746628761291504, "step": 91810 }, { "epoch": 0.5457971479691615, "grad_norm": 1.5758994817733765, "learning_rate": 0.0001963445403153182, "loss": 0.7116686820983886, "step": 91820 }, { "epoch": 0.5458565900458299, "grad_norm": 1.5165787935256958, "learning_rate": 0.00019634278407544697, "loss": 0.6618036270141602, "step": 91830 }, { "epoch": 0.5459160321224983, "grad_norm": 1.205607295036316, "learning_rate": 0.0001963410274225401, "loss": 0.6391756057739257, "step": 91840 }, { "epoch": 0.5459754741991666, "grad_norm": 1.3967680931091309, "learning_rate": 0.00019633927035660596, "loss": 0.7043488502502442, "step": 91850 }, { "epoch": 0.546034916275835, "grad_norm": 1.8061286211013794, "learning_rate": 0.00019633751287765296, "loss": 0.7134872436523437, "step": 91860 }, { "epoch": 0.5460943583525034, "grad_norm": 1.5996923446655273, "learning_rate": 0.00019633575498568954, "loss": 0.7033127784729004, "step": 91870 }, { "epoch": 0.5461538004291718, "grad_norm": 1.957268238067627, "learning_rate": 0.00019633399668072404, "loss": 0.6746143341064453, "step": 91880 }, { "epoch": 0.5462132425058401, "grad_norm": 1.765993595123291, "learning_rate": 0.00019633223796276493, "loss": 0.6866171836853028, "step": 91890 }, { "epoch": 0.5462726845825085, "grad_norm": 1.7203576564788818, "learning_rate": 0.00019633047883182064, "loss": 0.6638426780700684, "step": 91900 }, { "epoch": 0.546332126659177, "grad_norm": 1.6803756952285767, "learning_rate": 0.00019632871928789954, "loss": 0.5775729656219483, "step": 91910 }, { "epoch": 0.5463915687358454, "grad_norm": 1.6724302768707275, "learning_rate": 0.00019632695933101003, "loss": 0.7082358360290527, "step": 91920 }, { "epoch": 0.5464510108125138, "grad_norm": 1.7777260541915894, "learning_rate": 0.00019632519896116058, "loss": 0.7302308559417725, "step": 91930 }, { "epoch": 0.5465104528891821, "grad_norm": 1.2440868616104126, "learning_rate": 0.00019632343817835957, "loss": 0.6422797203063965, "step": 91940 }, { "epoch": 0.5465698949658505, "grad_norm": 1.2260748147964478, "learning_rate": 0.00019632167698261548, "loss": 0.6840221405029296, "step": 91950 }, { "epoch": 0.5466293370425189, "grad_norm": 1.8161813020706177, "learning_rate": 0.00019631991537393665, "loss": 0.6349005699157715, "step": 91960 }, { "epoch": 0.5466887791191873, "grad_norm": 1.832399606704712, "learning_rate": 0.00019631815335233158, "loss": 0.6550380706787109, "step": 91970 }, { "epoch": 0.5467482211958556, "grad_norm": 1.8277900218963623, "learning_rate": 0.00019631639091780868, "loss": 0.6561424255371093, "step": 91980 }, { "epoch": 0.5468076632725241, "grad_norm": 2.111266613006592, "learning_rate": 0.0001963146280703764, "loss": 0.6647612571716308, "step": 91990 }, { "epoch": 0.5468671053491925, "grad_norm": 1.952799677848816, "learning_rate": 0.0001963128648100431, "loss": 0.755331563949585, "step": 92000 }, { "epoch": 0.5469265474258609, "grad_norm": 1.7395646572113037, "learning_rate": 0.00019631110113681725, "loss": 0.6825196266174316, "step": 92010 }, { "epoch": 0.5469859895025293, "grad_norm": 1.6182693243026733, "learning_rate": 0.00019630933705070737, "loss": 0.6484192848205567, "step": 92020 }, { "epoch": 0.5470454315791976, "grad_norm": 1.750438928604126, "learning_rate": 0.00019630757255172178, "loss": 0.6938530921936035, "step": 92030 }, { "epoch": 0.547104873655866, "grad_norm": 1.674773097038269, "learning_rate": 0.00019630580763986896, "loss": 0.643183422088623, "step": 92040 }, { "epoch": 0.5471643157325344, "grad_norm": 1.8195648193359375, "learning_rate": 0.00019630404231515738, "loss": 0.6505156993865967, "step": 92050 }, { "epoch": 0.5472237578092028, "grad_norm": 2.163733959197998, "learning_rate": 0.00019630227657759547, "loss": 0.6900608539581299, "step": 92060 }, { "epoch": 0.5472831998858713, "grad_norm": 1.9716805219650269, "learning_rate": 0.00019630051042719164, "loss": 0.6839483261108399, "step": 92070 }, { "epoch": 0.5473426419625396, "grad_norm": 1.386574625968933, "learning_rate": 0.00019629874386395443, "loss": 0.6931780815124512, "step": 92080 }, { "epoch": 0.547402084039208, "grad_norm": 1.658189058303833, "learning_rate": 0.00019629697688789216, "loss": 0.6792679786682129, "step": 92090 }, { "epoch": 0.5474615261158764, "grad_norm": 1.7407639026641846, "learning_rate": 0.00019629520949901338, "loss": 0.679615831375122, "step": 92100 }, { "epoch": 0.5475209681925448, "grad_norm": 1.1217209100723267, "learning_rate": 0.00019629344169732653, "loss": 0.6646182060241699, "step": 92110 }, { "epoch": 0.5475804102692131, "grad_norm": 1.4664160013198853, "learning_rate": 0.00019629167348284008, "loss": 0.6137032508850098, "step": 92120 }, { "epoch": 0.5476398523458815, "grad_norm": 2.2812867164611816, "learning_rate": 0.00019628990485556246, "loss": 0.7228762626647949, "step": 92130 }, { "epoch": 0.5476992944225499, "grad_norm": 1.4963456392288208, "learning_rate": 0.0001962881358155021, "loss": 0.6901737213134765, "step": 92140 }, { "epoch": 0.5477587364992184, "grad_norm": 1.6774348020553589, "learning_rate": 0.0001962863663626675, "loss": 0.6708332061767578, "step": 92150 }, { "epoch": 0.5478181785758868, "grad_norm": 2.1161551475524902, "learning_rate": 0.00019628459649706715, "loss": 0.657315444946289, "step": 92160 }, { "epoch": 0.5478776206525551, "grad_norm": 1.6673380136489868, "learning_rate": 0.00019628282621870949, "loss": 0.7029761791229248, "step": 92170 }, { "epoch": 0.5479370627292235, "grad_norm": 1.4530432224273682, "learning_rate": 0.00019628105552760294, "loss": 0.6589540481567383, "step": 92180 }, { "epoch": 0.5479965048058919, "grad_norm": 1.5373127460479736, "learning_rate": 0.00019627928442375605, "loss": 0.6924315452575683, "step": 92190 }, { "epoch": 0.5480559468825603, "grad_norm": 2.0038657188415527, "learning_rate": 0.00019627751290717725, "loss": 0.6926032066345215, "step": 92200 }, { "epoch": 0.5481153889592287, "grad_norm": 1.3318666219711304, "learning_rate": 0.00019627574097787505, "loss": 0.6516623497009277, "step": 92210 }, { "epoch": 0.548174831035897, "grad_norm": 1.8835582733154297, "learning_rate": 0.00019627396863585787, "loss": 0.6522547245025635, "step": 92220 }, { "epoch": 0.5482342731125655, "grad_norm": 1.5342233180999756, "learning_rate": 0.00019627219588113422, "loss": 0.6323474407196045, "step": 92230 }, { "epoch": 0.5482937151892339, "grad_norm": 1.315952181816101, "learning_rate": 0.00019627042271371263, "loss": 0.6910378456115722, "step": 92240 }, { "epoch": 0.5483531572659023, "grad_norm": 1.7715672254562378, "learning_rate": 0.00019626864913360148, "loss": 0.6756988048553467, "step": 92250 }, { "epoch": 0.5484125993425706, "grad_norm": 1.9367080926895142, "learning_rate": 0.0001962668751408093, "loss": 0.7437252998352051, "step": 92260 }, { "epoch": 0.548472041419239, "grad_norm": 1.6756833791732788, "learning_rate": 0.00019626510073534462, "loss": 0.783644151687622, "step": 92270 }, { "epoch": 0.5485314834959074, "grad_norm": 1.822244644165039, "learning_rate": 0.00019626332591721584, "loss": 0.7181073188781738, "step": 92280 }, { "epoch": 0.5485909255725758, "grad_norm": 1.551352858543396, "learning_rate": 0.00019626155068643155, "loss": 0.6786204814910889, "step": 92290 }, { "epoch": 0.5486503676492442, "grad_norm": 1.6873375177383423, "learning_rate": 0.00019625977504300016, "loss": 0.6538570404052735, "step": 92300 }, { "epoch": 0.5487098097259125, "grad_norm": 2.10937237739563, "learning_rate": 0.0001962579989869302, "loss": 0.7107180595397949, "step": 92310 }, { "epoch": 0.548769251802581, "grad_norm": 1.5535446405410767, "learning_rate": 0.0001962562225182302, "loss": 0.727297019958496, "step": 92320 }, { "epoch": 0.5488286938792494, "grad_norm": 1.989684820175171, "learning_rate": 0.00019625444563690857, "loss": 0.6842812538146973, "step": 92330 }, { "epoch": 0.5488881359559178, "grad_norm": 1.7474112510681152, "learning_rate": 0.00019625266834297388, "loss": 0.6156933784484864, "step": 92340 }, { "epoch": 0.5489475780325861, "grad_norm": 2.079618453979492, "learning_rate": 0.00019625089063643464, "loss": 0.7419965744018555, "step": 92350 }, { "epoch": 0.5490070201092545, "grad_norm": 1.522740125656128, "learning_rate": 0.00019624911251729928, "loss": 0.7131568908691406, "step": 92360 }, { "epoch": 0.5490664621859229, "grad_norm": 2.2510128021240234, "learning_rate": 0.00019624733398557634, "loss": 0.6728064537048339, "step": 92370 }, { "epoch": 0.5491259042625913, "grad_norm": 2.0092380046844482, "learning_rate": 0.0001962455550412744, "loss": 0.7143534660339356, "step": 92380 }, { "epoch": 0.5491853463392598, "grad_norm": 1.6892433166503906, "learning_rate": 0.00019624377568440188, "loss": 0.6889607429504394, "step": 92390 }, { "epoch": 0.549244788415928, "grad_norm": 1.5678188800811768, "learning_rate": 0.00019624199591496732, "loss": 0.7400816917419434, "step": 92400 }, { "epoch": 0.5493042304925965, "grad_norm": 1.348099708557129, "learning_rate": 0.00019624021573297923, "loss": 0.663197135925293, "step": 92410 }, { "epoch": 0.5493636725692649, "grad_norm": 1.655317783355713, "learning_rate": 0.00019623843513844614, "loss": 0.6300008773803711, "step": 92420 }, { "epoch": 0.5494231146459333, "grad_norm": 1.4682543277740479, "learning_rate": 0.00019623665413137656, "loss": 0.6941112518310547, "step": 92430 }, { "epoch": 0.5494825567226017, "grad_norm": 1.62172269821167, "learning_rate": 0.000196234872711779, "loss": 0.6761122703552246, "step": 92440 }, { "epoch": 0.54954199879927, "grad_norm": 1.6558575630187988, "learning_rate": 0.000196233090879662, "loss": 0.6942187786102295, "step": 92450 }, { "epoch": 0.5496014408759384, "grad_norm": 1.5607236623764038, "learning_rate": 0.0001962313086350341, "loss": 0.6783061504364014, "step": 92460 }, { "epoch": 0.5496608829526068, "grad_norm": 1.5929585695266724, "learning_rate": 0.00019622952597790375, "loss": 0.6832840919494629, "step": 92470 }, { "epoch": 0.5497203250292753, "grad_norm": 1.8096888065338135, "learning_rate": 0.00019622774290827956, "loss": 0.6523449897766114, "step": 92480 }, { "epoch": 0.5497797671059436, "grad_norm": 2.067549705505371, "learning_rate": 0.00019622595942617, "loss": 0.6814297676086426, "step": 92490 }, { "epoch": 0.549839209182612, "grad_norm": 1.5348061323165894, "learning_rate": 0.00019622417553158368, "loss": 0.6188897609710693, "step": 92500 }, { "epoch": 0.5498986512592804, "grad_norm": 2.0813136100769043, "learning_rate": 0.00019622239122452906, "loss": 0.6111434936523438, "step": 92510 }, { "epoch": 0.5499580933359488, "grad_norm": 1.533633828163147, "learning_rate": 0.00019622060650501468, "loss": 0.6994316577911377, "step": 92520 }, { "epoch": 0.5500175354126172, "grad_norm": 1.3126739263534546, "learning_rate": 0.00019621882137304907, "loss": 0.6895359039306641, "step": 92530 }, { "epoch": 0.5500769774892855, "grad_norm": 1.6755291223526, "learning_rate": 0.00019621703582864086, "loss": 0.7111923694610596, "step": 92540 }, { "epoch": 0.5501364195659539, "grad_norm": 1.7166657447814941, "learning_rate": 0.00019621524987179848, "loss": 0.6599996089935303, "step": 92550 }, { "epoch": 0.5501958616426224, "grad_norm": 1.575140357017517, "learning_rate": 0.00019621346350253053, "loss": 0.6858268260955811, "step": 92560 }, { "epoch": 0.5502553037192908, "grad_norm": 1.5327317714691162, "learning_rate": 0.00019621167672084558, "loss": 0.6546375751495361, "step": 92570 }, { "epoch": 0.5503147457959592, "grad_norm": 1.856363296508789, "learning_rate": 0.0001962098895267521, "loss": 0.6885841369628907, "step": 92580 }, { "epoch": 0.5503741878726275, "grad_norm": 1.8053405284881592, "learning_rate": 0.00019620810192025868, "loss": 0.6950738906860352, "step": 92590 }, { "epoch": 0.5504336299492959, "grad_norm": 1.5841028690338135, "learning_rate": 0.00019620631390137393, "loss": 0.6006672382354736, "step": 92600 }, { "epoch": 0.5504930720259643, "grad_norm": 1.8067688941955566, "learning_rate": 0.0001962045254701063, "loss": 0.6942855834960937, "step": 92610 }, { "epoch": 0.5505525141026327, "grad_norm": 2.7343711853027344, "learning_rate": 0.0001962027366264644, "loss": 0.6551589012145996, "step": 92620 }, { "epoch": 0.550611956179301, "grad_norm": 1.6874128580093384, "learning_rate": 0.00019620094737045677, "loss": 0.703646469116211, "step": 92630 }, { "epoch": 0.5506713982559694, "grad_norm": 1.370630145072937, "learning_rate": 0.00019619915770209198, "loss": 0.6834983348846435, "step": 92640 }, { "epoch": 0.5507308403326379, "grad_norm": 1.5996761322021484, "learning_rate": 0.0001961973676213786, "loss": 0.6987429141998291, "step": 92650 }, { "epoch": 0.5507902824093063, "grad_norm": 1.1611942052841187, "learning_rate": 0.0001961955771283252, "loss": 0.6536651611328125, "step": 92660 }, { "epoch": 0.5508497244859747, "grad_norm": 1.7678675651550293, "learning_rate": 0.0001961937862229403, "loss": 0.6533149719238281, "step": 92670 }, { "epoch": 0.550909166562643, "grad_norm": 1.6865366697311401, "learning_rate": 0.0001961919949052325, "loss": 0.6638450622558594, "step": 92680 }, { "epoch": 0.5509686086393114, "grad_norm": 2.159684896469116, "learning_rate": 0.00019619020317521038, "loss": 0.6956772327423095, "step": 92690 }, { "epoch": 0.5510280507159798, "grad_norm": 1.9573683738708496, "learning_rate": 0.00019618841103288245, "loss": 0.6720499515533447, "step": 92700 }, { "epoch": 0.5510874927926482, "grad_norm": 1.972064733505249, "learning_rate": 0.00019618661847825737, "loss": 0.6888193130493164, "step": 92710 }, { "epoch": 0.5511469348693165, "grad_norm": 1.6012753248214722, "learning_rate": 0.00019618482551134368, "loss": 0.7116076469421386, "step": 92720 }, { "epoch": 0.551206376945985, "grad_norm": 1.258971095085144, "learning_rate": 0.00019618303213214992, "loss": 0.6534736633300782, "step": 92730 }, { "epoch": 0.5512658190226534, "grad_norm": 2.12599515914917, "learning_rate": 0.00019618123834068472, "loss": 0.6819646835327149, "step": 92740 }, { "epoch": 0.5513252610993218, "grad_norm": 1.4678324460983276, "learning_rate": 0.00019617944413695664, "loss": 0.6586093902587891, "step": 92750 }, { "epoch": 0.5513847031759902, "grad_norm": 1.5422419309616089, "learning_rate": 0.00019617764952097424, "loss": 0.6356669425964355, "step": 92760 }, { "epoch": 0.5514441452526585, "grad_norm": 1.88489830493927, "learning_rate": 0.00019617585449274616, "loss": 0.6918225288391113, "step": 92770 }, { "epoch": 0.5515035873293269, "grad_norm": 1.995077133178711, "learning_rate": 0.0001961740590522809, "loss": 0.6633990287780762, "step": 92780 }, { "epoch": 0.5515630294059953, "grad_norm": 1.8649166822433472, "learning_rate": 0.00019617226319958717, "loss": 0.8006094932556153, "step": 92790 }, { "epoch": 0.5516224714826637, "grad_norm": 1.593945026397705, "learning_rate": 0.00019617046693467348, "loss": 0.7052188396453858, "step": 92800 }, { "epoch": 0.5516819135593322, "grad_norm": 1.7998507022857666, "learning_rate": 0.00019616867025754845, "loss": 0.6610174655914307, "step": 92810 }, { "epoch": 0.5517413556360005, "grad_norm": 1.8145923614501953, "learning_rate": 0.0001961668731682206, "loss": 0.6888875007629395, "step": 92820 }, { "epoch": 0.5518007977126689, "grad_norm": 1.5654290914535522, "learning_rate": 0.00019616507566669862, "loss": 0.725582504272461, "step": 92830 }, { "epoch": 0.5518602397893373, "grad_norm": 1.9485819339752197, "learning_rate": 0.0001961632777529911, "loss": 0.6644030570983886, "step": 92840 }, { "epoch": 0.5519196818660057, "grad_norm": 1.7316750288009644, "learning_rate": 0.00019616147942710656, "loss": 0.6760543823242188, "step": 92850 }, { "epoch": 0.551979123942674, "grad_norm": 1.8131422996520996, "learning_rate": 0.00019615968068905374, "loss": 0.6977985382080079, "step": 92860 }, { "epoch": 0.5520385660193424, "grad_norm": 1.7947759628295898, "learning_rate": 0.00019615788153884108, "loss": 0.6509547233581543, "step": 92870 }, { "epoch": 0.5520980080960108, "grad_norm": 1.4151850938796997, "learning_rate": 0.00019615608197647732, "loss": 0.6511336326599121, "step": 92880 }, { "epoch": 0.5521574501726793, "grad_norm": 1.6244757175445557, "learning_rate": 0.00019615428200197107, "loss": 0.6504654884338379, "step": 92890 }, { "epoch": 0.5522168922493477, "grad_norm": 2.6978695392608643, "learning_rate": 0.0001961524816153308, "loss": 0.7126546382904053, "step": 92900 }, { "epoch": 0.552276334326016, "grad_norm": 1.4198648929595947, "learning_rate": 0.00019615068081656526, "loss": 0.6832232475280762, "step": 92910 }, { "epoch": 0.5523357764026844, "grad_norm": 1.5712289810180664, "learning_rate": 0.000196148879605683, "loss": 0.6390910625457764, "step": 92920 }, { "epoch": 0.5523952184793528, "grad_norm": 1.723940372467041, "learning_rate": 0.00019614707798269265, "loss": 0.7028667449951171, "step": 92930 }, { "epoch": 0.5524546605560212, "grad_norm": 1.8176189661026, "learning_rate": 0.00019614527594760285, "loss": 0.6991988182067871, "step": 92940 }, { "epoch": 0.5525141026326896, "grad_norm": 1.651841640472412, "learning_rate": 0.0001961434735004222, "loss": 0.6803709983825683, "step": 92950 }, { "epoch": 0.5525735447093579, "grad_norm": 1.7000021934509277, "learning_rate": 0.00019614167064115932, "loss": 0.7005592346191406, "step": 92960 }, { "epoch": 0.5526329867860263, "grad_norm": 1.718103289604187, "learning_rate": 0.00019613986736982284, "loss": 0.646476936340332, "step": 92970 }, { "epoch": 0.5526924288626948, "grad_norm": 1.5102031230926514, "learning_rate": 0.00019613806368642137, "loss": 0.6676040649414062, "step": 92980 }, { "epoch": 0.5527518709393632, "grad_norm": 1.489573359489441, "learning_rate": 0.00019613625959096357, "loss": 0.6853793144226075, "step": 92990 }, { "epoch": 0.5528113130160315, "grad_norm": 2.0649993419647217, "learning_rate": 0.00019613445508345808, "loss": 0.6961640357971192, "step": 93000 }, { "epoch": 0.5528707550926999, "grad_norm": 1.8287514448165894, "learning_rate": 0.00019613265016391344, "loss": 0.6823909759521485, "step": 93010 }, { "epoch": 0.5529301971693683, "grad_norm": 1.5148175954818726, "learning_rate": 0.0001961308448323384, "loss": 0.683747386932373, "step": 93020 }, { "epoch": 0.5529896392460367, "grad_norm": 1.7832603454589844, "learning_rate": 0.00019612903908874157, "loss": 0.6543903827667237, "step": 93030 }, { "epoch": 0.5530490813227051, "grad_norm": 1.812762975692749, "learning_rate": 0.00019612723293313148, "loss": 0.6364853858947754, "step": 93040 }, { "epoch": 0.5531085233993734, "grad_norm": 1.9992793798446655, "learning_rate": 0.0001961254263655169, "loss": 0.7081002235412598, "step": 93050 }, { "epoch": 0.5531679654760419, "grad_norm": 1.4715980291366577, "learning_rate": 0.00019612361938590645, "loss": 0.6663166522979737, "step": 93060 }, { "epoch": 0.5532274075527103, "grad_norm": 1.833327054977417, "learning_rate": 0.00019612181199430873, "loss": 0.6563722610473632, "step": 93070 }, { "epoch": 0.5532868496293787, "grad_norm": 1.7047696113586426, "learning_rate": 0.0001961200041907324, "loss": 0.674053955078125, "step": 93080 }, { "epoch": 0.553346291706047, "grad_norm": 1.4375663995742798, "learning_rate": 0.00019611819597518612, "loss": 0.6207871913909913, "step": 93090 }, { "epoch": 0.5534057337827154, "grad_norm": 1.582767128944397, "learning_rate": 0.00019611638734767854, "loss": 0.6454593658447265, "step": 93100 }, { "epoch": 0.5534651758593838, "grad_norm": 1.5433605909347534, "learning_rate": 0.0001961145783082183, "loss": 0.6944576263427734, "step": 93110 }, { "epoch": 0.5535246179360522, "grad_norm": 2.025744915008545, "learning_rate": 0.00019611276885681404, "loss": 0.6702422142028809, "step": 93120 }, { "epoch": 0.5535840600127206, "grad_norm": 1.515604019165039, "learning_rate": 0.00019611095899347444, "loss": 0.686821174621582, "step": 93130 }, { "epoch": 0.553643502089389, "grad_norm": 1.5014705657958984, "learning_rate": 0.00019610914871820821, "loss": 0.6667072296142578, "step": 93140 }, { "epoch": 0.5537029441660574, "grad_norm": 1.9213650226593018, "learning_rate": 0.0001961073380310239, "loss": 0.6686532020568847, "step": 93150 }, { "epoch": 0.5537623862427258, "grad_norm": 1.454756498336792, "learning_rate": 0.00019610552693193024, "loss": 0.6929154872894288, "step": 93160 }, { "epoch": 0.5538218283193942, "grad_norm": 1.5289223194122314, "learning_rate": 0.00019610371542093586, "loss": 0.6798099040985107, "step": 93170 }, { "epoch": 0.5538812703960626, "grad_norm": 1.8973318338394165, "learning_rate": 0.00019610190349804947, "loss": 0.7098671436309815, "step": 93180 }, { "epoch": 0.5539407124727309, "grad_norm": 1.5704928636550903, "learning_rate": 0.0001961000911632797, "loss": 0.735157060623169, "step": 93190 }, { "epoch": 0.5540001545493993, "grad_norm": 1.438547134399414, "learning_rate": 0.00019609827841663525, "loss": 0.6385186195373536, "step": 93200 }, { "epoch": 0.5540595966260677, "grad_norm": 1.6984413862228394, "learning_rate": 0.00019609646525812474, "loss": 0.721522331237793, "step": 93210 }, { "epoch": 0.5541190387027362, "grad_norm": 2.401433229446411, "learning_rate": 0.0001960946516877569, "loss": 0.683542537689209, "step": 93220 }, { "epoch": 0.5541784807794045, "grad_norm": 1.6016055345535278, "learning_rate": 0.00019609283770554038, "loss": 0.6462558269500732, "step": 93230 }, { "epoch": 0.5542379228560729, "grad_norm": 2.1643505096435547, "learning_rate": 0.00019609102331148384, "loss": 0.688853120803833, "step": 93240 }, { "epoch": 0.5542973649327413, "grad_norm": 1.6732263565063477, "learning_rate": 0.00019608920850559602, "loss": 0.6396766185760498, "step": 93250 }, { "epoch": 0.5543568070094097, "grad_norm": 1.2762452363967896, "learning_rate": 0.00019608739328788553, "loss": 0.623907995223999, "step": 93260 }, { "epoch": 0.5544162490860781, "grad_norm": 1.6881698369979858, "learning_rate": 0.0001960855776583611, "loss": 0.6697376728057861, "step": 93270 }, { "epoch": 0.5544756911627464, "grad_norm": 1.7930536270141602, "learning_rate": 0.00019608376161703138, "loss": 0.7174297332763672, "step": 93280 }, { "epoch": 0.5545351332394148, "grad_norm": 2.169785737991333, "learning_rate": 0.0001960819451639051, "loss": 0.6971555233001709, "step": 93290 }, { "epoch": 0.5545945753160832, "grad_norm": 2.0050439834594727, "learning_rate": 0.0001960801282989909, "loss": 0.6936922073364258, "step": 93300 }, { "epoch": 0.5546540173927517, "grad_norm": 1.3828240633010864, "learning_rate": 0.0001960783110222975, "loss": 0.6955408096313477, "step": 93310 }, { "epoch": 0.5547134594694201, "grad_norm": 1.6610119342803955, "learning_rate": 0.00019607649333383363, "loss": 0.6373323440551758, "step": 93320 }, { "epoch": 0.5547729015460884, "grad_norm": 1.8367724418640137, "learning_rate": 0.0001960746752336079, "loss": 0.686954402923584, "step": 93330 }, { "epoch": 0.5548323436227568, "grad_norm": 1.9969844818115234, "learning_rate": 0.00019607285672162907, "loss": 0.6567994594573975, "step": 93340 }, { "epoch": 0.5548917856994252, "grad_norm": 1.8187297582626343, "learning_rate": 0.0001960710377979058, "loss": 0.6940566062927246, "step": 93350 }, { "epoch": 0.5549512277760936, "grad_norm": 1.1976007223129272, "learning_rate": 0.00019606921846244686, "loss": 0.719942569732666, "step": 93360 }, { "epoch": 0.5550106698527619, "grad_norm": 2.1661088466644287, "learning_rate": 0.00019606739871526089, "loss": 0.6523640155792236, "step": 93370 }, { "epoch": 0.5550701119294303, "grad_norm": 1.7577792406082153, "learning_rate": 0.0001960655785563566, "loss": 0.6765625476837158, "step": 93380 }, { "epoch": 0.5551295540060988, "grad_norm": 1.728118658065796, "learning_rate": 0.00019606375798574273, "loss": 0.6823710918426513, "step": 93390 }, { "epoch": 0.5551889960827672, "grad_norm": 1.7420719861984253, "learning_rate": 0.00019606193700342795, "loss": 0.6908146381378174, "step": 93400 }, { "epoch": 0.5552484381594356, "grad_norm": 1.641111135482788, "learning_rate": 0.00019606011560942098, "loss": 0.7031805992126465, "step": 93410 }, { "epoch": 0.5553078802361039, "grad_norm": 1.5378968715667725, "learning_rate": 0.00019605829380373054, "loss": 0.6652504920959472, "step": 93420 }, { "epoch": 0.5553673223127723, "grad_norm": 1.7238701581954956, "learning_rate": 0.00019605647158636537, "loss": 0.6957321643829346, "step": 93430 }, { "epoch": 0.5554267643894407, "grad_norm": 1.587380290031433, "learning_rate": 0.00019605464895733414, "loss": 0.7413965702056885, "step": 93440 }, { "epoch": 0.5554862064661091, "grad_norm": 1.8055241107940674, "learning_rate": 0.00019605282591664562, "loss": 0.6369936466217041, "step": 93450 }, { "epoch": 0.5555456485427774, "grad_norm": 1.3942233324050903, "learning_rate": 0.00019605100246430847, "loss": 0.6879724502563477, "step": 93460 }, { "epoch": 0.5556050906194459, "grad_norm": 1.8765294551849365, "learning_rate": 0.00019604917860033147, "loss": 0.6995868682861328, "step": 93470 }, { "epoch": 0.5556645326961143, "grad_norm": 1.4674491882324219, "learning_rate": 0.00019604735432472335, "loss": 0.6740097999572754, "step": 93480 }, { "epoch": 0.5557239747727827, "grad_norm": 2.0515565872192383, "learning_rate": 0.00019604552963749274, "loss": 0.6758600234985351, "step": 93490 }, { "epoch": 0.5557834168494511, "grad_norm": 1.5856417417526245, "learning_rate": 0.00019604370453864847, "loss": 0.7217656135559082, "step": 93500 }, { "epoch": 0.5558428589261194, "grad_norm": 1.2147623300552368, "learning_rate": 0.00019604187902819923, "loss": 0.6897513389587402, "step": 93510 }, { "epoch": 0.5559023010027878, "grad_norm": 2.125070810317993, "learning_rate": 0.00019604005310615375, "loss": 0.6695287704467774, "step": 93520 }, { "epoch": 0.5559617430794562, "grad_norm": 1.5766932964324951, "learning_rate": 0.00019603822677252081, "loss": 0.6289813041687011, "step": 93530 }, { "epoch": 0.5560211851561246, "grad_norm": 1.9077974557876587, "learning_rate": 0.0001960364000273091, "loss": 0.7504549026489258, "step": 93540 }, { "epoch": 0.5560806272327931, "grad_norm": 2.111008405685425, "learning_rate": 0.00019603457287052734, "loss": 0.6955992698669433, "step": 93550 }, { "epoch": 0.5561400693094614, "grad_norm": 1.5261749029159546, "learning_rate": 0.00019603274530218432, "loss": 0.6582673072814942, "step": 93560 }, { "epoch": 0.5561995113861298, "grad_norm": 1.5402902364730835, "learning_rate": 0.00019603091732228877, "loss": 0.6874294281005859, "step": 93570 }, { "epoch": 0.5562589534627982, "grad_norm": 1.6081165075302124, "learning_rate": 0.0001960290889308494, "loss": 0.6296459197998047, "step": 93580 }, { "epoch": 0.5563183955394666, "grad_norm": 1.4905328750610352, "learning_rate": 0.00019602726012787504, "loss": 0.6975886821746826, "step": 93590 }, { "epoch": 0.5563778376161349, "grad_norm": 1.5002734661102295, "learning_rate": 0.00019602543091337433, "loss": 0.6310019493103027, "step": 93600 }, { "epoch": 0.5564372796928033, "grad_norm": 1.931217908859253, "learning_rate": 0.0001960236012873561, "loss": 0.7013407707214355, "step": 93610 }, { "epoch": 0.5564967217694717, "grad_norm": 1.946420431137085, "learning_rate": 0.00019602177124982903, "loss": 0.7095990180969238, "step": 93620 }, { "epoch": 0.5565561638461402, "grad_norm": 1.4428364038467407, "learning_rate": 0.00019601994080080195, "loss": 0.6120026588439942, "step": 93630 }, { "epoch": 0.5566156059228086, "grad_norm": 1.7605184316635132, "learning_rate": 0.00019601810994028358, "loss": 0.695221996307373, "step": 93640 }, { "epoch": 0.5566750479994769, "grad_norm": 1.6422234773635864, "learning_rate": 0.0001960162786682827, "loss": 0.682860279083252, "step": 93650 }, { "epoch": 0.5567344900761453, "grad_norm": 2.065871477127075, "learning_rate": 0.00019601444698480802, "loss": 0.6833194732666016, "step": 93660 }, { "epoch": 0.5567939321528137, "grad_norm": 1.617082953453064, "learning_rate": 0.00019601261488986837, "loss": 0.6295164585113525, "step": 93670 }, { "epoch": 0.5568533742294821, "grad_norm": 1.816645860671997, "learning_rate": 0.00019601078238347245, "loss": 0.6640523910522461, "step": 93680 }, { "epoch": 0.5569128163061505, "grad_norm": 1.57224440574646, "learning_rate": 0.00019600894946562907, "loss": 0.6561355590820312, "step": 93690 }, { "epoch": 0.5569722583828188, "grad_norm": 1.8547333478927612, "learning_rate": 0.00019600711613634698, "loss": 0.7057953834533691, "step": 93700 }, { "epoch": 0.5570317004594872, "grad_norm": 1.4419262409210205, "learning_rate": 0.00019600528239563497, "loss": 0.6337571144104004, "step": 93710 }, { "epoch": 0.5570911425361557, "grad_norm": 1.915238380432129, "learning_rate": 0.00019600344824350176, "loss": 0.665254783630371, "step": 93720 }, { "epoch": 0.5571505846128241, "grad_norm": 1.8120245933532715, "learning_rate": 0.0001960016136799562, "loss": 0.6840706825256347, "step": 93730 }, { "epoch": 0.5572100266894924, "grad_norm": 1.598660945892334, "learning_rate": 0.000195999778705007, "loss": 0.733798885345459, "step": 93740 }, { "epoch": 0.5572694687661608, "grad_norm": 1.6905162334442139, "learning_rate": 0.00019599794331866298, "loss": 0.6959177017211914, "step": 93750 }, { "epoch": 0.5573289108428292, "grad_norm": 1.78094482421875, "learning_rate": 0.0001959961075209329, "loss": 0.7458530902862549, "step": 93760 }, { "epoch": 0.5573883529194976, "grad_norm": 1.8594213724136353, "learning_rate": 0.00019599427131182553, "loss": 0.7019329071044922, "step": 93770 }, { "epoch": 0.557447794996166, "grad_norm": 1.3975416421890259, "learning_rate": 0.00019599243469134968, "loss": 0.6340632438659668, "step": 93780 }, { "epoch": 0.5575072370728343, "grad_norm": 2.506434917449951, "learning_rate": 0.0001959905976595141, "loss": 0.68604736328125, "step": 93790 }, { "epoch": 0.5575666791495028, "grad_norm": 1.7862361669540405, "learning_rate": 0.00019598876021632765, "loss": 0.6978271007537842, "step": 93800 }, { "epoch": 0.5576261212261712, "grad_norm": 1.697579026222229, "learning_rate": 0.00019598692236179904, "loss": 0.7402424812316895, "step": 93810 }, { "epoch": 0.5576855633028396, "grad_norm": 1.6730879545211792, "learning_rate": 0.0001959850840959371, "loss": 0.6798649787902832, "step": 93820 }, { "epoch": 0.5577450053795079, "grad_norm": 1.556512475013733, "learning_rate": 0.00019598324541875064, "loss": 0.6809525966644288, "step": 93830 }, { "epoch": 0.5578044474561763, "grad_norm": 1.522106647491455, "learning_rate": 0.0001959814063302484, "loss": 0.6691841125488281, "step": 93840 }, { "epoch": 0.5578638895328447, "grad_norm": 1.7418566942214966, "learning_rate": 0.00019597956683043926, "loss": 0.6839659214019775, "step": 93850 }, { "epoch": 0.5579233316095131, "grad_norm": 1.9605766534805298, "learning_rate": 0.00019597772691933192, "loss": 0.7018675804138184, "step": 93860 }, { "epoch": 0.5579827736861815, "grad_norm": 2.1852664947509766, "learning_rate": 0.00019597588659693525, "loss": 0.711236572265625, "step": 93870 }, { "epoch": 0.5580422157628498, "grad_norm": 1.909489393234253, "learning_rate": 0.00019597404586325806, "loss": 0.7073830604553223, "step": 93880 }, { "epoch": 0.5581016578395183, "grad_norm": 1.9039827585220337, "learning_rate": 0.0001959722047183091, "loss": 0.6745167255401612, "step": 93890 }, { "epoch": 0.5581610999161867, "grad_norm": 1.6658984422683716, "learning_rate": 0.0001959703631620972, "loss": 0.5953598976135254, "step": 93900 }, { "epoch": 0.5582205419928551, "grad_norm": 1.5791480541229248, "learning_rate": 0.0001959685211946312, "loss": 0.6531814098358154, "step": 93910 }, { "epoch": 0.5582799840695235, "grad_norm": 1.9121508598327637, "learning_rate": 0.00019596667881591987, "loss": 0.6633184909820556, "step": 93920 }, { "epoch": 0.5583394261461918, "grad_norm": 1.6188087463378906, "learning_rate": 0.00019596483602597208, "loss": 0.7097821235656738, "step": 93930 }, { "epoch": 0.5583988682228602, "grad_norm": 1.7021198272705078, "learning_rate": 0.0001959629928247966, "loss": 0.7348945617675782, "step": 93940 }, { "epoch": 0.5584583102995286, "grad_norm": 1.6890064477920532, "learning_rate": 0.0001959611492124022, "loss": 0.6397966384887696, "step": 93950 }, { "epoch": 0.558517752376197, "grad_norm": 1.6910525560379028, "learning_rate": 0.00019595930518879782, "loss": 0.6359628677368164, "step": 93960 }, { "epoch": 0.5585771944528654, "grad_norm": 1.4410878419876099, "learning_rate": 0.00019595746075399216, "loss": 0.7081661224365234, "step": 93970 }, { "epoch": 0.5586366365295338, "grad_norm": 1.806345820426941, "learning_rate": 0.00019595561590799414, "loss": 0.6906240463256836, "step": 93980 }, { "epoch": 0.5586960786062022, "grad_norm": 1.6273691654205322, "learning_rate": 0.00019595377065081252, "loss": 0.6600336074829102, "step": 93990 }, { "epoch": 0.5587555206828706, "grad_norm": 1.6861499547958374, "learning_rate": 0.00019595192498245617, "loss": 0.6518237113952636, "step": 94000 }, { "epoch": 0.558814962759539, "grad_norm": 1.4420541524887085, "learning_rate": 0.00019595007890293393, "loss": 0.6350115776062012, "step": 94010 }, { "epoch": 0.5588744048362073, "grad_norm": 1.8538987636566162, "learning_rate": 0.00019594823241225455, "loss": 0.6283339023590088, "step": 94020 }, { "epoch": 0.5589338469128757, "grad_norm": 1.4206175804138184, "learning_rate": 0.00019594638551042692, "loss": 0.6500717639923096, "step": 94030 }, { "epoch": 0.5589932889895441, "grad_norm": 1.969486951828003, "learning_rate": 0.0001959445381974599, "loss": 0.6808964729309082, "step": 94040 }, { "epoch": 0.5590527310662126, "grad_norm": 1.9901421070098877, "learning_rate": 0.00019594269047336227, "loss": 0.7160738945007324, "step": 94050 }, { "epoch": 0.559112173142881, "grad_norm": 2.0942583084106445, "learning_rate": 0.00019594084233814292, "loss": 0.7017583847045898, "step": 94060 }, { "epoch": 0.5591716152195493, "grad_norm": 1.889197826385498, "learning_rate": 0.0001959389937918106, "loss": 0.6573796272277832, "step": 94070 }, { "epoch": 0.5592310572962177, "grad_norm": 1.7316851615905762, "learning_rate": 0.0001959371448343743, "loss": 0.7149688243865967, "step": 94080 }, { "epoch": 0.5592904993728861, "grad_norm": 1.814002513885498, "learning_rate": 0.00019593529546584274, "loss": 0.667594051361084, "step": 94090 }, { "epoch": 0.5593499414495545, "grad_norm": 1.6170768737792969, "learning_rate": 0.00019593344568622482, "loss": 0.5800037384033203, "step": 94100 }, { "epoch": 0.5594093835262228, "grad_norm": 1.8545863628387451, "learning_rate": 0.00019593159549552937, "loss": 0.6505846977233887, "step": 94110 }, { "epoch": 0.5594688256028912, "grad_norm": 1.7335320711135864, "learning_rate": 0.00019592974489376528, "loss": 0.6373112678527832, "step": 94120 }, { "epoch": 0.5595282676795597, "grad_norm": 1.361111044883728, "learning_rate": 0.00019592789388094134, "loss": 0.6207480907440186, "step": 94130 }, { "epoch": 0.5595877097562281, "grad_norm": 2.0277302265167236, "learning_rate": 0.00019592604245706645, "loss": 0.703210973739624, "step": 94140 }, { "epoch": 0.5596471518328965, "grad_norm": 2.034517526626587, "learning_rate": 0.00019592419062214943, "loss": 0.6787089824676513, "step": 94150 }, { "epoch": 0.5597065939095648, "grad_norm": 1.8099788427352905, "learning_rate": 0.00019592233837619922, "loss": 0.701145076751709, "step": 94160 }, { "epoch": 0.5597660359862332, "grad_norm": 1.8685256242752075, "learning_rate": 0.0001959204857192246, "loss": 0.6371888637542724, "step": 94170 }, { "epoch": 0.5598254780629016, "grad_norm": 1.7172231674194336, "learning_rate": 0.0001959186326512344, "loss": 0.6527912616729736, "step": 94180 }, { "epoch": 0.55988492013957, "grad_norm": 1.6320420503616333, "learning_rate": 0.0001959167791722376, "loss": 0.6716238021850586, "step": 94190 }, { "epoch": 0.5599443622162383, "grad_norm": 2.035303831100464, "learning_rate": 0.000195914925282243, "loss": 0.6889430999755859, "step": 94200 }, { "epoch": 0.5600038042929067, "grad_norm": 1.9580399990081787, "learning_rate": 0.00019591307098125945, "loss": 0.6642104148864746, "step": 94210 }, { "epoch": 0.5600632463695752, "grad_norm": 2.042135000228882, "learning_rate": 0.00019591121626929588, "loss": 0.7528502464294433, "step": 94220 }, { "epoch": 0.5601226884462436, "grad_norm": 2.1622562408447266, "learning_rate": 0.0001959093611463611, "loss": 0.7029280662536621, "step": 94230 }, { "epoch": 0.560182130522912, "grad_norm": 1.8427859544754028, "learning_rate": 0.000195907505612464, "loss": 0.6573540687561035, "step": 94240 }, { "epoch": 0.5602415725995803, "grad_norm": 1.7622039318084717, "learning_rate": 0.0001959056496676135, "loss": 0.6965981960296631, "step": 94250 }, { "epoch": 0.5603010146762487, "grad_norm": 2.082947254180908, "learning_rate": 0.00019590379331181843, "loss": 0.728148078918457, "step": 94260 }, { "epoch": 0.5603604567529171, "grad_norm": 1.4652196168899536, "learning_rate": 0.00019590193654508772, "loss": 0.6880982398986817, "step": 94270 }, { "epoch": 0.5604198988295855, "grad_norm": 1.5266190767288208, "learning_rate": 0.00019590007936743015, "loss": 0.6645485877990722, "step": 94280 }, { "epoch": 0.560479340906254, "grad_norm": 1.9189897775650024, "learning_rate": 0.0001958982217788547, "loss": 0.7007539749145508, "step": 94290 }, { "epoch": 0.5605387829829223, "grad_norm": 1.9232745170593262, "learning_rate": 0.00019589636377937027, "loss": 0.7348246097564697, "step": 94300 }, { "epoch": 0.5605982250595907, "grad_norm": 1.760720133781433, "learning_rate": 0.00019589450536898565, "loss": 0.7492150783538818, "step": 94310 }, { "epoch": 0.5606576671362591, "grad_norm": 1.665779948234558, "learning_rate": 0.00019589264654770985, "loss": 0.6603082656860352, "step": 94320 }, { "epoch": 0.5607171092129275, "grad_norm": 1.7107810974121094, "learning_rate": 0.00019589078731555167, "loss": 0.6492185592651367, "step": 94330 }, { "epoch": 0.5607765512895958, "grad_norm": 1.8878631591796875, "learning_rate": 0.00019588892767252, "loss": 0.6707833766937256, "step": 94340 }, { "epoch": 0.5608359933662642, "grad_norm": 1.6687794923782349, "learning_rate": 0.0001958870676186238, "loss": 0.6393630504608154, "step": 94350 }, { "epoch": 0.5608954354429326, "grad_norm": 1.7020444869995117, "learning_rate": 0.00019588520715387194, "loss": 0.6844229221343994, "step": 94360 }, { "epoch": 0.560954877519601, "grad_norm": 1.9021798372268677, "learning_rate": 0.00019588334627827333, "loss": 0.6888307094573974, "step": 94370 }, { "epoch": 0.5610143195962695, "grad_norm": 1.5988249778747559, "learning_rate": 0.0001958814849918368, "loss": 0.717952823638916, "step": 94380 }, { "epoch": 0.5610737616729378, "grad_norm": 1.9438564777374268, "learning_rate": 0.00019587962329457135, "loss": 0.7315426826477051, "step": 94390 }, { "epoch": 0.5611332037496062, "grad_norm": 1.7319319248199463, "learning_rate": 0.00019587776118648587, "loss": 0.6803771018981933, "step": 94400 }, { "epoch": 0.5611926458262746, "grad_norm": 1.8618974685668945, "learning_rate": 0.0001958758986675892, "loss": 0.656494140625, "step": 94410 }, { "epoch": 0.561252087902943, "grad_norm": 1.7398642301559448, "learning_rate": 0.0001958740357378903, "loss": 0.65584716796875, "step": 94420 }, { "epoch": 0.5613115299796113, "grad_norm": 1.6177819967269897, "learning_rate": 0.0001958721723973981, "loss": 0.6741084098815918, "step": 94430 }, { "epoch": 0.5613709720562797, "grad_norm": 1.5661176443099976, "learning_rate": 0.0001958703086461215, "loss": 0.6557851314544678, "step": 94440 }, { "epoch": 0.5614304141329481, "grad_norm": 1.2909437417984009, "learning_rate": 0.00019586844448406937, "loss": 0.6093500137329102, "step": 94450 }, { "epoch": 0.5614898562096166, "grad_norm": 1.8972423076629639, "learning_rate": 0.0001958665799112507, "loss": 0.650893259048462, "step": 94460 }, { "epoch": 0.561549298286285, "grad_norm": 1.905058741569519, "learning_rate": 0.00019586471492767435, "loss": 0.6471084117889404, "step": 94470 }, { "epoch": 0.5616087403629533, "grad_norm": 1.3994359970092773, "learning_rate": 0.00019586284953334928, "loss": 0.6802791595458985, "step": 94480 }, { "epoch": 0.5616681824396217, "grad_norm": 1.6812728643417358, "learning_rate": 0.0001958609837282844, "loss": 0.6704484939575195, "step": 94490 }, { "epoch": 0.5617276245162901, "grad_norm": 1.3259854316711426, "learning_rate": 0.00019585911751248861, "loss": 0.6304489612579346, "step": 94500 }, { "epoch": 0.5617870665929585, "grad_norm": 1.851649284362793, "learning_rate": 0.0001958572508859709, "loss": 0.6764461994171143, "step": 94510 }, { "epoch": 0.5618465086696269, "grad_norm": 1.9890174865722656, "learning_rate": 0.0001958553838487401, "loss": 0.6556539058685302, "step": 94520 }, { "epoch": 0.5619059507462952, "grad_norm": 1.496626377105713, "learning_rate": 0.00019585351640080524, "loss": 0.6417080879211425, "step": 94530 }, { "epoch": 0.5619653928229636, "grad_norm": 1.1999430656433105, "learning_rate": 0.00019585164854217524, "loss": 0.654370927810669, "step": 94540 }, { "epoch": 0.5620248348996321, "grad_norm": 2.1524598598480225, "learning_rate": 0.000195849780272859, "loss": 0.7398443222045898, "step": 94550 }, { "epoch": 0.5620842769763005, "grad_norm": 1.410436749458313, "learning_rate": 0.00019584791159286543, "loss": 0.6863360404968262, "step": 94560 }, { "epoch": 0.5621437190529688, "grad_norm": 1.6806892156600952, "learning_rate": 0.00019584604250220353, "loss": 0.6760566711425782, "step": 94570 }, { "epoch": 0.5622031611296372, "grad_norm": 1.2727903127670288, "learning_rate": 0.0001958441730008822, "loss": 0.6397730827331543, "step": 94580 }, { "epoch": 0.5622626032063056, "grad_norm": 1.7365961074829102, "learning_rate": 0.00019584230308891041, "loss": 0.6312098503112793, "step": 94590 }, { "epoch": 0.562322045282974, "grad_norm": 1.2882189750671387, "learning_rate": 0.00019584043276629708, "loss": 0.644188642501831, "step": 94600 }, { "epoch": 0.5623814873596424, "grad_norm": 1.3467320203781128, "learning_rate": 0.00019583856203305122, "loss": 0.6644454002380371, "step": 94610 }, { "epoch": 0.5624409294363107, "grad_norm": 4.12965202331543, "learning_rate": 0.00019583669088918168, "loss": 0.673678970336914, "step": 94620 }, { "epoch": 0.5625003715129792, "grad_norm": 1.5694622993469238, "learning_rate": 0.00019583481933469748, "loss": 0.681358814239502, "step": 94630 }, { "epoch": 0.5625598135896476, "grad_norm": 1.907526969909668, "learning_rate": 0.00019583294736960757, "loss": 0.7092463493347168, "step": 94640 }, { "epoch": 0.562619255666316, "grad_norm": 1.3940767049789429, "learning_rate": 0.0001958310749939209, "loss": 0.6888449668884278, "step": 94650 }, { "epoch": 0.5626786977429844, "grad_norm": 1.5059369802474976, "learning_rate": 0.0001958292022076464, "loss": 0.6551403999328613, "step": 94660 }, { "epoch": 0.5627381398196527, "grad_norm": 1.3340948820114136, "learning_rate": 0.00019582732901079304, "loss": 0.6613153457641602, "step": 94670 }, { "epoch": 0.5627975818963211, "grad_norm": 1.5370804071426392, "learning_rate": 0.00019582545540336978, "loss": 0.615397310256958, "step": 94680 }, { "epoch": 0.5628570239729895, "grad_norm": 1.6123536825180054, "learning_rate": 0.0001958235813853856, "loss": 0.626489782333374, "step": 94690 }, { "epoch": 0.562916466049658, "grad_norm": 2.0219180583953857, "learning_rate": 0.00019582170695684947, "loss": 0.6652631282806396, "step": 94700 }, { "epoch": 0.5629759081263263, "grad_norm": 1.5307623147964478, "learning_rate": 0.00019581983211777032, "loss": 0.6531510353088379, "step": 94710 }, { "epoch": 0.5630353502029947, "grad_norm": 2.1318318843841553, "learning_rate": 0.00019581795686815715, "loss": 0.6634109497070313, "step": 94720 }, { "epoch": 0.5630947922796631, "grad_norm": 1.5283232927322388, "learning_rate": 0.0001958160812080189, "loss": 0.6400931358337403, "step": 94730 }, { "epoch": 0.5631542343563315, "grad_norm": 2.332127094268799, "learning_rate": 0.00019581420513736458, "loss": 0.6695493698120117, "step": 94740 }, { "epoch": 0.5632136764329999, "grad_norm": 2.049403667449951, "learning_rate": 0.00019581232865620315, "loss": 0.6679216384887695, "step": 94750 }, { "epoch": 0.5632731185096682, "grad_norm": 1.7972384691238403, "learning_rate": 0.0001958104517645436, "loss": 0.6495565891265869, "step": 94760 }, { "epoch": 0.5633325605863366, "grad_norm": 1.4969130754470825, "learning_rate": 0.00019580857446239487, "loss": 0.684476661682129, "step": 94770 }, { "epoch": 0.563392002663005, "grad_norm": 1.9800692796707153, "learning_rate": 0.00019580669674976596, "loss": 0.7037053108215332, "step": 94780 }, { "epoch": 0.5634514447396735, "grad_norm": 1.953214406967163, "learning_rate": 0.00019580481862666586, "loss": 0.6454449653625488, "step": 94790 }, { "epoch": 0.5635108868163418, "grad_norm": 1.5331616401672363, "learning_rate": 0.00019580294009310354, "loss": 0.6702024936676025, "step": 94800 }, { "epoch": 0.5635703288930102, "grad_norm": 1.541616678237915, "learning_rate": 0.000195801061149088, "loss": 0.6908074378967285, "step": 94810 }, { "epoch": 0.5636297709696786, "grad_norm": 1.9755759239196777, "learning_rate": 0.0001957991817946282, "loss": 0.6649252891540527, "step": 94820 }, { "epoch": 0.563689213046347, "grad_norm": 2.009213924407959, "learning_rate": 0.0001957973020297332, "loss": 0.7111194610595704, "step": 94830 }, { "epoch": 0.5637486551230154, "grad_norm": 1.5678550004959106, "learning_rate": 0.00019579542185441194, "loss": 0.6787349700927734, "step": 94840 }, { "epoch": 0.5638080971996837, "grad_norm": 1.76158607006073, "learning_rate": 0.0001957935412686734, "loss": 0.652939748764038, "step": 94850 }, { "epoch": 0.5638675392763521, "grad_norm": 1.8213305473327637, "learning_rate": 0.00019579166027252658, "loss": 0.6649925231933593, "step": 94860 }, { "epoch": 0.5639269813530206, "grad_norm": 1.9372588396072388, "learning_rate": 0.0001957897788659805, "loss": 0.6467242240905762, "step": 94870 }, { "epoch": 0.563986423429689, "grad_norm": 1.648695707321167, "learning_rate": 0.00019578789704904418, "loss": 0.6549175262451172, "step": 94880 }, { "epoch": 0.5640458655063574, "grad_norm": 1.6718741655349731, "learning_rate": 0.0001957860148217266, "loss": 0.6771704673767089, "step": 94890 }, { "epoch": 0.5641053075830257, "grad_norm": 2.039898633956909, "learning_rate": 0.00019578413218403673, "loss": 0.6599593162536621, "step": 94900 }, { "epoch": 0.5641647496596941, "grad_norm": 1.568791389465332, "learning_rate": 0.00019578224913598363, "loss": 0.6958882331848144, "step": 94910 }, { "epoch": 0.5642241917363625, "grad_norm": 1.4995964765548706, "learning_rate": 0.00019578036567757627, "loss": 0.6938686370849609, "step": 94920 }, { "epoch": 0.5642836338130309, "grad_norm": 2.0124990940093994, "learning_rate": 0.00019577848180882368, "loss": 0.6691386699676514, "step": 94930 }, { "epoch": 0.5643430758896992, "grad_norm": 1.3535194396972656, "learning_rate": 0.00019577659752973488, "loss": 0.6879034519195557, "step": 94940 }, { "epoch": 0.5644025179663676, "grad_norm": 2.0655837059020996, "learning_rate": 0.00019577471284031882, "loss": 0.7294098377227783, "step": 94950 }, { "epoch": 0.5644619600430361, "grad_norm": 1.5384877920150757, "learning_rate": 0.00019577282774058463, "loss": 0.7309859752655029, "step": 94960 }, { "epoch": 0.5645214021197045, "grad_norm": 1.7104848623275757, "learning_rate": 0.00019577094223054123, "loss": 0.7059536933898926, "step": 94970 }, { "epoch": 0.5645808441963729, "grad_norm": 1.5473361015319824, "learning_rate": 0.00019576905631019765, "loss": 0.6595590591430665, "step": 94980 }, { "epoch": 0.5646402862730412, "grad_norm": 1.333829641342163, "learning_rate": 0.000195767169979563, "loss": 0.6613572120666504, "step": 94990 }, { "epoch": 0.5646997283497096, "grad_norm": 1.7984236478805542, "learning_rate": 0.00019576528323864617, "loss": 0.7290127277374268, "step": 95000 }, { "epoch": 0.564759170426378, "grad_norm": 1.6656455993652344, "learning_rate": 0.00019576339608745632, "loss": 0.715660285949707, "step": 95010 }, { "epoch": 0.5648186125030464, "grad_norm": 1.6467946767807007, "learning_rate": 0.00019576150852600237, "loss": 0.7196359634399414, "step": 95020 }, { "epoch": 0.5648780545797149, "grad_norm": 1.5421562194824219, "learning_rate": 0.00019575962055429338, "loss": 0.6776633739471436, "step": 95030 }, { "epoch": 0.5649374966563832, "grad_norm": 1.47519052028656, "learning_rate": 0.0001957577321723384, "loss": 0.7014224052429199, "step": 95040 }, { "epoch": 0.5649969387330516, "grad_norm": 1.508765459060669, "learning_rate": 0.00019575584338014644, "loss": 0.6635732173919677, "step": 95050 }, { "epoch": 0.56505638080972, "grad_norm": 2.1388041973114014, "learning_rate": 0.00019575395417772658, "loss": 0.6405440330505371, "step": 95060 }, { "epoch": 0.5651158228863884, "grad_norm": 1.577634334564209, "learning_rate": 0.00019575206456508783, "loss": 0.679243803024292, "step": 95070 }, { "epoch": 0.5651752649630567, "grad_norm": 1.632169246673584, "learning_rate": 0.0001957501745422392, "loss": 0.660839319229126, "step": 95080 }, { "epoch": 0.5652347070397251, "grad_norm": 1.4310979843139648, "learning_rate": 0.0001957482841091898, "loss": 0.6486915588378906, "step": 95090 }, { "epoch": 0.5652941491163935, "grad_norm": 1.9617317914962769, "learning_rate": 0.00019574639326594862, "loss": 0.6805473327636719, "step": 95100 }, { "epoch": 0.5653535911930619, "grad_norm": 1.7663424015045166, "learning_rate": 0.00019574450201252468, "loss": 0.6477478504180908, "step": 95110 }, { "epoch": 0.5654130332697304, "grad_norm": 1.2864744663238525, "learning_rate": 0.0001957426103489271, "loss": 0.6579985618591309, "step": 95120 }, { "epoch": 0.5654724753463987, "grad_norm": 2.2505106925964355, "learning_rate": 0.00019574071827516487, "loss": 0.7588711738586426, "step": 95130 }, { "epoch": 0.5655319174230671, "grad_norm": 1.8664261102676392, "learning_rate": 0.00019573882579124706, "loss": 0.6846725463867187, "step": 95140 }, { "epoch": 0.5655913594997355, "grad_norm": 1.545166254043579, "learning_rate": 0.00019573693289718275, "loss": 0.6581719875335693, "step": 95150 }, { "epoch": 0.5656508015764039, "grad_norm": 1.7861744165420532, "learning_rate": 0.00019573503959298096, "loss": 0.7171393394470215, "step": 95160 }, { "epoch": 0.5657102436530722, "grad_norm": 1.760824203491211, "learning_rate": 0.00019573314587865076, "loss": 0.7042790412902832, "step": 95170 }, { "epoch": 0.5657696857297406, "grad_norm": 1.4452135562896729, "learning_rate": 0.0001957312517542012, "loss": 0.6987798690795899, "step": 95180 }, { "epoch": 0.565829127806409, "grad_norm": 1.9478552341461182, "learning_rate": 0.00019572935721964135, "loss": 0.7007999420166016, "step": 95190 }, { "epoch": 0.5658885698830775, "grad_norm": 1.9704211950302124, "learning_rate": 0.0001957274622749803, "loss": 0.6681068420410157, "step": 95200 }, { "epoch": 0.5659480119597459, "grad_norm": 2.125396490097046, "learning_rate": 0.00019572556692022705, "loss": 0.6658862590789795, "step": 95210 }, { "epoch": 0.5660074540364142, "grad_norm": 1.9056954383850098, "learning_rate": 0.00019572367115539075, "loss": 0.7010316371917724, "step": 95220 }, { "epoch": 0.5660668961130826, "grad_norm": 1.485750675201416, "learning_rate": 0.0001957217749804804, "loss": 0.6842164039611817, "step": 95230 }, { "epoch": 0.566126338189751, "grad_norm": 1.390565037727356, "learning_rate": 0.00019571987839550508, "loss": 0.6145490646362305, "step": 95240 }, { "epoch": 0.5661857802664194, "grad_norm": 1.9473283290863037, "learning_rate": 0.0001957179814004739, "loss": 0.655755615234375, "step": 95250 }, { "epoch": 0.5662452223430878, "grad_norm": 1.7848526239395142, "learning_rate": 0.00019571608399539584, "loss": 0.6382483959197998, "step": 95260 }, { "epoch": 0.5663046644197561, "grad_norm": 1.4878151416778564, "learning_rate": 0.0001957141861802801, "loss": 0.6939614295959473, "step": 95270 }, { "epoch": 0.5663641064964245, "grad_norm": 1.500288963317871, "learning_rate": 0.00019571228795513571, "loss": 0.6712283134460449, "step": 95280 }, { "epoch": 0.566423548573093, "grad_norm": 1.9991803169250488, "learning_rate": 0.00019571038931997175, "loss": 0.6901291370391845, "step": 95290 }, { "epoch": 0.5664829906497614, "grad_norm": 1.8353558778762817, "learning_rate": 0.0001957084902747973, "loss": 0.6612376689910888, "step": 95300 }, { "epoch": 0.5665424327264297, "grad_norm": 1.87924063205719, "learning_rate": 0.0001957065908196214, "loss": 0.6825798034667969, "step": 95310 }, { "epoch": 0.5666018748030981, "grad_norm": 1.9215130805969238, "learning_rate": 0.0001957046909544532, "loss": 0.7227622032165527, "step": 95320 }, { "epoch": 0.5666613168797665, "grad_norm": 1.6721787452697754, "learning_rate": 0.00019570279067930178, "loss": 0.674689769744873, "step": 95330 }, { "epoch": 0.5667207589564349, "grad_norm": 2.3759281635284424, "learning_rate": 0.00019570088999417622, "loss": 0.6674881935119629, "step": 95340 }, { "epoch": 0.5667802010331033, "grad_norm": 1.4880344867706299, "learning_rate": 0.00019569898889908562, "loss": 0.694905138015747, "step": 95350 }, { "epoch": 0.5668396431097716, "grad_norm": 2.123739242553711, "learning_rate": 0.00019569708739403905, "loss": 0.646229887008667, "step": 95360 }, { "epoch": 0.56689908518644, "grad_norm": 2.039198398590088, "learning_rate": 0.0001956951854790456, "loss": 0.6472713947296143, "step": 95370 }, { "epoch": 0.5669585272631085, "grad_norm": 1.5915188789367676, "learning_rate": 0.00019569328315411442, "loss": 0.6987237930297852, "step": 95380 }, { "epoch": 0.5670179693397769, "grad_norm": 1.8478590250015259, "learning_rate": 0.00019569138041925454, "loss": 0.7219169616699219, "step": 95390 }, { "epoch": 0.5670774114164453, "grad_norm": 1.892066240310669, "learning_rate": 0.00019568947727447513, "loss": 0.7306931495666504, "step": 95400 }, { "epoch": 0.5671368534931136, "grad_norm": 1.693039894104004, "learning_rate": 0.00019568757371978525, "loss": 0.7514871597290039, "step": 95410 }, { "epoch": 0.567196295569782, "grad_norm": 1.928365707397461, "learning_rate": 0.00019568566975519403, "loss": 0.6723867893218994, "step": 95420 }, { "epoch": 0.5672557376464504, "grad_norm": 1.3059848546981812, "learning_rate": 0.00019568376538071057, "loss": 0.6482004165649414, "step": 95430 }, { "epoch": 0.5673151797231188, "grad_norm": 1.889725923538208, "learning_rate": 0.00019568186059634396, "loss": 0.7021682262420654, "step": 95440 }, { "epoch": 0.5673746217997871, "grad_norm": 1.8013030290603638, "learning_rate": 0.00019567995540210336, "loss": 0.6667702674865723, "step": 95450 }, { "epoch": 0.5674340638764556, "grad_norm": 1.8318990468978882, "learning_rate": 0.00019567804979799783, "loss": 0.633901834487915, "step": 95460 }, { "epoch": 0.567493505953124, "grad_norm": 1.515893816947937, "learning_rate": 0.0001956761437840365, "loss": 0.6695155620574951, "step": 95470 }, { "epoch": 0.5675529480297924, "grad_norm": 2.3022069931030273, "learning_rate": 0.00019567423736022852, "loss": 0.6616223335266114, "step": 95480 }, { "epoch": 0.5676123901064608, "grad_norm": 1.7767393589019775, "learning_rate": 0.00019567233052658297, "loss": 0.7341022968292237, "step": 95490 }, { "epoch": 0.5676718321831291, "grad_norm": 1.8029084205627441, "learning_rate": 0.00019567042328310903, "loss": 0.6278009414672852, "step": 95500 }, { "epoch": 0.5677312742597975, "grad_norm": 1.7277178764343262, "learning_rate": 0.00019566851562981575, "loss": 0.640838623046875, "step": 95510 }, { "epoch": 0.5677907163364659, "grad_norm": 1.6536420583724976, "learning_rate": 0.00019566660756671227, "loss": 0.6584354877471924, "step": 95520 }, { "epoch": 0.5678501584131344, "grad_norm": 1.9421770572662354, "learning_rate": 0.00019566469909380776, "loss": 0.6635652542114258, "step": 95530 }, { "epoch": 0.5679096004898027, "grad_norm": 1.6412996053695679, "learning_rate": 0.00019566279021111132, "loss": 0.7369265079498291, "step": 95540 }, { "epoch": 0.5679690425664711, "grad_norm": 2.006957530975342, "learning_rate": 0.00019566088091863207, "loss": 0.6898200988769532, "step": 95550 }, { "epoch": 0.5680284846431395, "grad_norm": 1.6359738111495972, "learning_rate": 0.00019565897121637916, "loss": 0.685837697982788, "step": 95560 }, { "epoch": 0.5680879267198079, "grad_norm": 2.5776567459106445, "learning_rate": 0.0001956570611043618, "loss": 0.6679461002349854, "step": 95570 }, { "epoch": 0.5681473687964763, "grad_norm": 1.9625661373138428, "learning_rate": 0.00019565515058258897, "loss": 0.7044246673583985, "step": 95580 }, { "epoch": 0.5682068108731446, "grad_norm": 1.6544148921966553, "learning_rate": 0.0001956532396510699, "loss": 0.7048128128051758, "step": 95590 }, { "epoch": 0.568266252949813, "grad_norm": 1.763947606086731, "learning_rate": 0.00019565132830981374, "loss": 0.7520723819732666, "step": 95600 }, { "epoch": 0.5683256950264814, "grad_norm": 1.576552152633667, "learning_rate": 0.00019564941655882964, "loss": 0.6490437984466553, "step": 95610 }, { "epoch": 0.5683851371031499, "grad_norm": 1.8998043537139893, "learning_rate": 0.0001956475043981267, "loss": 0.7499156475067139, "step": 95620 }, { "epoch": 0.5684445791798183, "grad_norm": 1.608023762702942, "learning_rate": 0.0001956455918277141, "loss": 0.7067546844482422, "step": 95630 }, { "epoch": 0.5685040212564866, "grad_norm": 1.7021591663360596, "learning_rate": 0.00019564367884760095, "loss": 0.6761886596679687, "step": 95640 }, { "epoch": 0.568563463333155, "grad_norm": 1.9358258247375488, "learning_rate": 0.00019564176545779646, "loss": 0.7083022594451904, "step": 95650 }, { "epoch": 0.5686229054098234, "grad_norm": 1.992433786392212, "learning_rate": 0.00019563985165830974, "loss": 0.7196540832519531, "step": 95660 }, { "epoch": 0.5686823474864918, "grad_norm": 1.6150931119918823, "learning_rate": 0.00019563793744914993, "loss": 0.7051160335540771, "step": 95670 }, { "epoch": 0.5687417895631601, "grad_norm": 1.7225476503372192, "learning_rate": 0.00019563602283032626, "loss": 0.6091536521911621, "step": 95680 }, { "epoch": 0.5688012316398285, "grad_norm": 1.6788818836212158, "learning_rate": 0.00019563410780184778, "loss": 0.7653397560119629, "step": 95690 }, { "epoch": 0.568860673716497, "grad_norm": 1.5875742435455322, "learning_rate": 0.0001956321923637238, "loss": 0.6672580718994141, "step": 95700 }, { "epoch": 0.5689201157931654, "grad_norm": 1.6444097757339478, "learning_rate": 0.00019563027651596333, "loss": 0.6648813247680664, "step": 95710 }, { "epoch": 0.5689795578698338, "grad_norm": 1.6561155319213867, "learning_rate": 0.00019562836025857562, "loss": 0.7139524459838867, "step": 95720 }, { "epoch": 0.5690389999465021, "grad_norm": 1.5848913192749023, "learning_rate": 0.00019562644359156982, "loss": 0.6721442222595215, "step": 95730 }, { "epoch": 0.5690984420231705, "grad_norm": 1.700875163078308, "learning_rate": 0.0001956245265149551, "loss": 0.6759603023529053, "step": 95740 }, { "epoch": 0.5691578840998389, "grad_norm": 1.5083426237106323, "learning_rate": 0.00019562260902874064, "loss": 0.7091771602630615, "step": 95750 }, { "epoch": 0.5692173261765073, "grad_norm": 1.87662935256958, "learning_rate": 0.00019562069113293558, "loss": 0.6692124366760254, "step": 95760 }, { "epoch": 0.5692767682531757, "grad_norm": 1.5519119501113892, "learning_rate": 0.00019561877282754913, "loss": 0.6524359703063964, "step": 95770 }, { "epoch": 0.569336210329844, "grad_norm": 1.7207636833190918, "learning_rate": 0.00019561685411259043, "loss": 0.6074150085449219, "step": 95780 }, { "epoch": 0.5693956524065125, "grad_norm": 1.2247748374938965, "learning_rate": 0.0001956149349880687, "loss": 0.6737022876739502, "step": 95790 }, { "epoch": 0.5694550944831809, "grad_norm": 1.5567309856414795, "learning_rate": 0.0001956130154539931, "loss": 0.6865023612976074, "step": 95800 }, { "epoch": 0.5695145365598493, "grad_norm": 1.8675737380981445, "learning_rate": 0.00019561109551037277, "loss": 0.6700342178344727, "step": 95810 }, { "epoch": 0.5695739786365176, "grad_norm": 1.6426321268081665, "learning_rate": 0.000195609175157217, "loss": 0.686085557937622, "step": 95820 }, { "epoch": 0.569633420713186, "grad_norm": 1.59006929397583, "learning_rate": 0.00019560725439453488, "loss": 0.6595154762268066, "step": 95830 }, { "epoch": 0.5696928627898544, "grad_norm": 1.5496464967727661, "learning_rate": 0.00019560533322233564, "loss": 0.700069808959961, "step": 95840 }, { "epoch": 0.5697523048665228, "grad_norm": 1.640112042427063, "learning_rate": 0.00019560341164062846, "loss": 0.6066380023956299, "step": 95850 }, { "epoch": 0.5698117469431913, "grad_norm": 1.6633052825927734, "learning_rate": 0.00019560148964942252, "loss": 0.7338322162628174, "step": 95860 }, { "epoch": 0.5698711890198596, "grad_norm": 1.7114591598510742, "learning_rate": 0.00019559956724872704, "loss": 0.6926604270935058, "step": 95870 }, { "epoch": 0.569930631096528, "grad_norm": 1.815635323524475, "learning_rate": 0.0001955976444385512, "loss": 0.6914234161376953, "step": 95880 }, { "epoch": 0.5699900731731964, "grad_norm": 1.529892086982727, "learning_rate": 0.00019559572121890422, "loss": 0.6745193481445313, "step": 95890 }, { "epoch": 0.5700495152498648, "grad_norm": 1.6117265224456787, "learning_rate": 0.00019559379758979527, "loss": 0.6444224357604981, "step": 95900 }, { "epoch": 0.5701089573265331, "grad_norm": 2.2463066577911377, "learning_rate": 0.00019559187355123355, "loss": 0.6976035594940185, "step": 95910 }, { "epoch": 0.5701683994032015, "grad_norm": 1.8158007860183716, "learning_rate": 0.0001955899491032283, "loss": 0.6315601348876954, "step": 95920 }, { "epoch": 0.5702278414798699, "grad_norm": 1.6123608350753784, "learning_rate": 0.0001955880242457887, "loss": 0.6851423740386963, "step": 95930 }, { "epoch": 0.5702872835565383, "grad_norm": 1.7522311210632324, "learning_rate": 0.00019558609897892397, "loss": 0.6960886955261231, "step": 95940 }, { "epoch": 0.5703467256332068, "grad_norm": 2.1218135356903076, "learning_rate": 0.0001955841733026433, "loss": 0.6926380157470703, "step": 95950 }, { "epoch": 0.5704061677098751, "grad_norm": 2.0466315746307373, "learning_rate": 0.00019558224721695592, "loss": 0.6649043083190918, "step": 95960 }, { "epoch": 0.5704656097865435, "grad_norm": 1.2558913230895996, "learning_rate": 0.00019558032072187104, "loss": 0.7407001972198486, "step": 95970 }, { "epoch": 0.5705250518632119, "grad_norm": 1.5272462368011475, "learning_rate": 0.00019557839381739787, "loss": 0.6923675537109375, "step": 95980 }, { "epoch": 0.5705844939398803, "grad_norm": 1.4659909009933472, "learning_rate": 0.00019557646650354563, "loss": 0.7312582492828369, "step": 95990 }, { "epoch": 0.5706439360165487, "grad_norm": 1.8564964532852173, "learning_rate": 0.00019557453878032356, "loss": 0.6252557754516601, "step": 96000 }, { "epoch": 0.570703378093217, "grad_norm": 1.850326418876648, "learning_rate": 0.00019557261064774085, "loss": 0.7330249309539795, "step": 96010 }, { "epoch": 0.5707628201698854, "grad_norm": 2.3969881534576416, "learning_rate": 0.00019557068210580668, "loss": 0.6753236293792725, "step": 96020 }, { "epoch": 0.5708222622465539, "grad_norm": 2.394686222076416, "learning_rate": 0.0001955687531545304, "loss": 0.622553825378418, "step": 96030 }, { "epoch": 0.5708817043232223, "grad_norm": 2.4354915618896484, "learning_rate": 0.00019556682379392114, "loss": 0.7247650146484375, "step": 96040 }, { "epoch": 0.5709411463998906, "grad_norm": 1.786821961402893, "learning_rate": 0.00019556489402398818, "loss": 0.7310012817382813, "step": 96050 }, { "epoch": 0.571000588476559, "grad_norm": 1.616100549697876, "learning_rate": 0.00019556296384474074, "loss": 0.6533756732940674, "step": 96060 }, { "epoch": 0.5710600305532274, "grad_norm": 1.401110291481018, "learning_rate": 0.000195561033256188, "loss": 0.7347143173217774, "step": 96070 }, { "epoch": 0.5711194726298958, "grad_norm": 1.7969379425048828, "learning_rate": 0.00019555910225833926, "loss": 0.6966980934143067, "step": 96080 }, { "epoch": 0.5711789147065642, "grad_norm": 1.4771767854690552, "learning_rate": 0.00019555717085120375, "loss": 0.6943191528320313, "step": 96090 }, { "epoch": 0.5712383567832325, "grad_norm": 1.613052487373352, "learning_rate": 0.00019555523903479067, "loss": 0.670503044128418, "step": 96100 }, { "epoch": 0.571297798859901, "grad_norm": 1.729996919631958, "learning_rate": 0.00019555330680910932, "loss": 0.6845441818237304, "step": 96110 }, { "epoch": 0.5713572409365694, "grad_norm": 1.8273801803588867, "learning_rate": 0.0001955513741741689, "loss": 0.6942484378814697, "step": 96120 }, { "epoch": 0.5714166830132378, "grad_norm": 1.5213639736175537, "learning_rate": 0.00019554944112997865, "loss": 0.7051167488098145, "step": 96130 }, { "epoch": 0.5714761250899062, "grad_norm": 1.4714980125427246, "learning_rate": 0.00019554750767654782, "loss": 0.6975725173950196, "step": 96140 }, { "epoch": 0.5715355671665745, "grad_norm": 1.8761560916900635, "learning_rate": 0.0001955455738138857, "loss": 0.6575050830841065, "step": 96150 }, { "epoch": 0.5715950092432429, "grad_norm": 1.7944550514221191, "learning_rate": 0.00019554363954200145, "loss": 0.6631821632385254, "step": 96160 }, { "epoch": 0.5716544513199113, "grad_norm": 2.0579721927642822, "learning_rate": 0.00019554170486090446, "loss": 0.7463347434997558, "step": 96170 }, { "epoch": 0.5717138933965797, "grad_norm": 1.7619951963424683, "learning_rate": 0.00019553976977060387, "loss": 0.6651562213897705, "step": 96180 }, { "epoch": 0.571773335473248, "grad_norm": 1.748374342918396, "learning_rate": 0.00019553783427110898, "loss": 0.6638088226318359, "step": 96190 }, { "epoch": 0.5718327775499165, "grad_norm": 2.185490131378174, "learning_rate": 0.00019553589836242906, "loss": 0.7042503833770752, "step": 96200 }, { "epoch": 0.5718922196265849, "grad_norm": 1.7243272066116333, "learning_rate": 0.00019553396204457336, "loss": 0.6202174663543701, "step": 96210 }, { "epoch": 0.5719516617032533, "grad_norm": 1.548905849456787, "learning_rate": 0.0001955320253175511, "loss": 0.6851685523986817, "step": 96220 }, { "epoch": 0.5720111037799217, "grad_norm": 1.9861313104629517, "learning_rate": 0.00019553008818137162, "loss": 0.6958355903625488, "step": 96230 }, { "epoch": 0.57207054585659, "grad_norm": 1.609920859336853, "learning_rate": 0.00019552815063604413, "loss": 0.6876352310180665, "step": 96240 }, { "epoch": 0.5721299879332584, "grad_norm": 1.7215005159378052, "learning_rate": 0.00019552621268157793, "loss": 0.658057975769043, "step": 96250 }, { "epoch": 0.5721894300099268, "grad_norm": 1.6112537384033203, "learning_rate": 0.0001955242743179823, "loss": 0.6437043190002442, "step": 96260 }, { "epoch": 0.5722488720865953, "grad_norm": 1.5124255418777466, "learning_rate": 0.00019552233554526643, "loss": 0.6362598419189454, "step": 96270 }, { "epoch": 0.5723083141632636, "grad_norm": 1.6289950609207153, "learning_rate": 0.0001955203963634397, "loss": 0.7015355110168457, "step": 96280 }, { "epoch": 0.572367756239932, "grad_norm": 2.2237560749053955, "learning_rate": 0.00019551845677251133, "loss": 0.7772834777832032, "step": 96290 }, { "epoch": 0.5724271983166004, "grad_norm": 1.611066460609436, "learning_rate": 0.00019551651677249062, "loss": 0.7101207733154297, "step": 96300 }, { "epoch": 0.5724866403932688, "grad_norm": 1.5183770656585693, "learning_rate": 0.00019551457636338685, "loss": 0.6246075630187988, "step": 96310 }, { "epoch": 0.5725460824699372, "grad_norm": 1.825394868850708, "learning_rate": 0.00019551263554520927, "loss": 0.5469544410705567, "step": 96320 }, { "epoch": 0.5726055245466055, "grad_norm": 2.111171007156372, "learning_rate": 0.0001955106943179672, "loss": 0.674196720123291, "step": 96330 }, { "epoch": 0.5726649666232739, "grad_norm": 1.4704183340072632, "learning_rate": 0.0001955087526816699, "loss": 0.6786868095397949, "step": 96340 }, { "epoch": 0.5727244086999423, "grad_norm": 1.534974217414856, "learning_rate": 0.0001955068106363267, "loss": 0.6265156745910645, "step": 96350 }, { "epoch": 0.5727838507766108, "grad_norm": 1.7978180646896362, "learning_rate": 0.00019550486818194682, "loss": 0.7638593196868897, "step": 96360 }, { "epoch": 0.5728432928532792, "grad_norm": 1.641280174255371, "learning_rate": 0.00019550292531853963, "loss": 0.6963166236877442, "step": 96370 }, { "epoch": 0.5729027349299475, "grad_norm": 1.761120080947876, "learning_rate": 0.00019550098204611439, "loss": 0.7009870529174804, "step": 96380 }, { "epoch": 0.5729621770066159, "grad_norm": 1.6418309211730957, "learning_rate": 0.00019549903836468035, "loss": 0.6653710842132569, "step": 96390 }, { "epoch": 0.5730216190832843, "grad_norm": 2.101102828979492, "learning_rate": 0.0001954970942742469, "loss": 0.6842981815338135, "step": 96400 }, { "epoch": 0.5730810611599527, "grad_norm": 1.5120772123336792, "learning_rate": 0.00019549514977482325, "loss": 0.6748843193054199, "step": 96410 }, { "epoch": 0.573140503236621, "grad_norm": 1.6680419445037842, "learning_rate": 0.00019549320486641879, "loss": 0.6621190071105957, "step": 96420 }, { "epoch": 0.5731999453132894, "grad_norm": 1.788891077041626, "learning_rate": 0.00019549125954904274, "loss": 0.6440502643585205, "step": 96430 }, { "epoch": 0.5732593873899579, "grad_norm": 1.000298023223877, "learning_rate": 0.00019548931382270445, "loss": 0.6103343009948731, "step": 96440 }, { "epoch": 0.5733188294666263, "grad_norm": 1.8256465196609497, "learning_rate": 0.00019548736768741322, "loss": 0.6713085174560547, "step": 96450 }, { "epoch": 0.5733782715432947, "grad_norm": 2.06886887550354, "learning_rate": 0.00019548542114317837, "loss": 0.6433083534240722, "step": 96460 }, { "epoch": 0.573437713619963, "grad_norm": 2.0554113388061523, "learning_rate": 0.0001954834741900092, "loss": 0.6880763053894043, "step": 96470 }, { "epoch": 0.5734971556966314, "grad_norm": 1.9670315980911255, "learning_rate": 0.00019548152682791504, "loss": 0.6730756759643555, "step": 96480 }, { "epoch": 0.5735565977732998, "grad_norm": 1.6181964874267578, "learning_rate": 0.00019547957905690516, "loss": 0.6621764659881592, "step": 96490 }, { "epoch": 0.5736160398499682, "grad_norm": 1.508489966392517, "learning_rate": 0.0001954776308769889, "loss": 0.6756068229675293, "step": 96500 }, { "epoch": 0.5736754819266366, "grad_norm": 2.031090021133423, "learning_rate": 0.00019547568228817566, "loss": 0.7102703094482422, "step": 96510 }, { "epoch": 0.573734924003305, "grad_norm": 1.563651442527771, "learning_rate": 0.00019547373329047464, "loss": 0.6282023429870606, "step": 96520 }, { "epoch": 0.5737943660799734, "grad_norm": 1.9177172183990479, "learning_rate": 0.0001954717838838952, "loss": 0.7157572269439697, "step": 96530 }, { "epoch": 0.5738538081566418, "grad_norm": 2.686765432357788, "learning_rate": 0.0001954698340684467, "loss": 0.699635124206543, "step": 96540 }, { "epoch": 0.5739132502333102, "grad_norm": 1.8336461782455444, "learning_rate": 0.00019546788384413845, "loss": 0.6455371379852295, "step": 96550 }, { "epoch": 0.5739726923099785, "grad_norm": 1.5250509977340698, "learning_rate": 0.00019546593321097976, "loss": 0.6939346313476562, "step": 96560 }, { "epoch": 0.5740321343866469, "grad_norm": 1.8877124786376953, "learning_rate": 0.00019546398216897998, "loss": 0.6818486213684082, "step": 96570 }, { "epoch": 0.5740915764633153, "grad_norm": 1.6919326782226562, "learning_rate": 0.00019546203071814844, "loss": 0.7036571979522706, "step": 96580 }, { "epoch": 0.5741510185399837, "grad_norm": 1.6569881439208984, "learning_rate": 0.0001954600788584945, "loss": 0.7514025688171386, "step": 96590 }, { "epoch": 0.5742104606166522, "grad_norm": 1.8554562330245972, "learning_rate": 0.0001954581265900274, "loss": 0.715481185913086, "step": 96600 }, { "epoch": 0.5742699026933205, "grad_norm": 1.7218350172042847, "learning_rate": 0.00019545617391275664, "loss": 0.7162565231323242, "step": 96610 }, { "epoch": 0.5743293447699889, "grad_norm": 2.1294047832489014, "learning_rate": 0.00019545422082669142, "loss": 0.7038421630859375, "step": 96620 }, { "epoch": 0.5743887868466573, "grad_norm": 1.698169469833374, "learning_rate": 0.00019545226733184114, "loss": 0.6505401134490967, "step": 96630 }, { "epoch": 0.5744482289233257, "grad_norm": 1.6616201400756836, "learning_rate": 0.00019545031342821517, "loss": 0.642672348022461, "step": 96640 }, { "epoch": 0.574507670999994, "grad_norm": 1.7099791765213013, "learning_rate": 0.00019544835911582275, "loss": 0.715532636642456, "step": 96650 }, { "epoch": 0.5745671130766624, "grad_norm": 1.9693007469177246, "learning_rate": 0.0001954464043946734, "loss": 0.6507463932037354, "step": 96660 }, { "epoch": 0.5746265551533308, "grad_norm": 1.4723056554794312, "learning_rate": 0.0001954444492647763, "loss": 0.6222821712493897, "step": 96670 }, { "epoch": 0.5746859972299992, "grad_norm": 1.839598298072815, "learning_rate": 0.0001954424937261409, "loss": 0.6669745445251465, "step": 96680 }, { "epoch": 0.5747454393066677, "grad_norm": 1.676957130432129, "learning_rate": 0.00019544053777877655, "loss": 0.7004525184631347, "step": 96690 }, { "epoch": 0.574804881383336, "grad_norm": 1.5401259660720825, "learning_rate": 0.00019543858142269258, "loss": 0.673624324798584, "step": 96700 }, { "epoch": 0.5748643234600044, "grad_norm": 1.9039381742477417, "learning_rate": 0.00019543662465789838, "loss": 0.6774868488311767, "step": 96710 }, { "epoch": 0.5749237655366728, "grad_norm": 1.7285101413726807, "learning_rate": 0.00019543466748440328, "loss": 0.6817062377929688, "step": 96720 }, { "epoch": 0.5749832076133412, "grad_norm": 1.9658851623535156, "learning_rate": 0.00019543270990221657, "loss": 0.628838062286377, "step": 96730 }, { "epoch": 0.5750426496900096, "grad_norm": 1.8482075929641724, "learning_rate": 0.0001954307519113478, "loss": 0.6734264373779297, "step": 96740 }, { "epoch": 0.5751020917666779, "grad_norm": 1.2392969131469727, "learning_rate": 0.0001954287935118062, "loss": 0.6629441261291504, "step": 96750 }, { "epoch": 0.5751615338433463, "grad_norm": 1.621728777885437, "learning_rate": 0.00019542683470360114, "loss": 0.694600772857666, "step": 96760 }, { "epoch": 0.5752209759200148, "grad_norm": 1.8096944093704224, "learning_rate": 0.00019542487548674205, "loss": 0.7527151107788086, "step": 96770 }, { "epoch": 0.5752804179966832, "grad_norm": 1.4358385801315308, "learning_rate": 0.00019542291586123828, "loss": 0.6741950511932373, "step": 96780 }, { "epoch": 0.5753398600733515, "grad_norm": 1.9133572578430176, "learning_rate": 0.0001954209558270992, "loss": 0.6420399665832519, "step": 96790 }, { "epoch": 0.5753993021500199, "grad_norm": 1.683193564414978, "learning_rate": 0.00019541899538433417, "loss": 0.6464607238769531, "step": 96800 }, { "epoch": 0.5754587442266883, "grad_norm": 1.479303002357483, "learning_rate": 0.00019541703453295256, "loss": 0.6640422344207764, "step": 96810 }, { "epoch": 0.5755181863033567, "grad_norm": 1.2613461017608643, "learning_rate": 0.0001954150732729638, "loss": 0.6895438671112061, "step": 96820 }, { "epoch": 0.5755776283800251, "grad_norm": 1.8063846826553345, "learning_rate": 0.00019541311160437724, "loss": 0.6834508895874023, "step": 96830 }, { "epoch": 0.5756370704566934, "grad_norm": 1.64046311378479, "learning_rate": 0.00019541114952720224, "loss": 0.6653257369995117, "step": 96840 }, { "epoch": 0.5756965125333618, "grad_norm": 1.7942578792572021, "learning_rate": 0.00019540918704144823, "loss": 0.6905193328857422, "step": 96850 }, { "epoch": 0.5757559546100303, "grad_norm": 1.5393643379211426, "learning_rate": 0.0001954072241471246, "loss": 0.6884088516235352, "step": 96860 }, { "epoch": 0.5758153966866987, "grad_norm": 1.6622825860977173, "learning_rate": 0.00019540526084424074, "loss": 0.6450828552246094, "step": 96870 }, { "epoch": 0.5758748387633671, "grad_norm": 1.5814242362976074, "learning_rate": 0.00019540329713280596, "loss": 0.6841809749603271, "step": 96880 }, { "epoch": 0.5759342808400354, "grad_norm": 1.8617238998413086, "learning_rate": 0.00019540133301282976, "loss": 0.6845676898956299, "step": 96890 }, { "epoch": 0.5759937229167038, "grad_norm": 1.8763396739959717, "learning_rate": 0.00019539936848432147, "loss": 0.6970652580261231, "step": 96900 }, { "epoch": 0.5760531649933722, "grad_norm": 2.315000295639038, "learning_rate": 0.00019539740354729051, "loss": 0.6782186508178711, "step": 96910 }, { "epoch": 0.5761126070700406, "grad_norm": 1.998342752456665, "learning_rate": 0.0001953954382017463, "loss": 0.6448896408081055, "step": 96920 }, { "epoch": 0.5761720491467089, "grad_norm": 1.723131537437439, "learning_rate": 0.0001953934724476982, "loss": 0.6190276622772217, "step": 96930 }, { "epoch": 0.5762314912233774, "grad_norm": 1.4211732149124146, "learning_rate": 0.00019539150628515567, "loss": 0.7260210037231445, "step": 96940 }, { "epoch": 0.5762909333000458, "grad_norm": 2.294525623321533, "learning_rate": 0.00019538953971412807, "loss": 0.6810462951660157, "step": 96950 }, { "epoch": 0.5763503753767142, "grad_norm": 1.5594054460525513, "learning_rate": 0.00019538757273462477, "loss": 0.6889984130859375, "step": 96960 }, { "epoch": 0.5764098174533826, "grad_norm": 1.6120556592941284, "learning_rate": 0.00019538560534665528, "loss": 0.6937697887420654, "step": 96970 }, { "epoch": 0.5764692595300509, "grad_norm": 1.8371646404266357, "learning_rate": 0.00019538363755022893, "loss": 0.5848541259765625, "step": 96980 }, { "epoch": 0.5765287016067193, "grad_norm": 1.7422298192977905, "learning_rate": 0.00019538166934535516, "loss": 0.63485689163208, "step": 96990 }, { "epoch": 0.5765881436833877, "grad_norm": 1.6524255275726318, "learning_rate": 0.00019537970073204338, "loss": 0.6434185028076171, "step": 97000 }, { "epoch": 0.5766475857600561, "grad_norm": 1.9915533065795898, "learning_rate": 0.00019537773171030305, "loss": 0.6892895221710205, "step": 97010 }, { "epoch": 0.5767070278367245, "grad_norm": 1.438751220703125, "learning_rate": 0.00019537576228014354, "loss": 0.6787843227386474, "step": 97020 }, { "epoch": 0.5767664699133929, "grad_norm": 1.9439237117767334, "learning_rate": 0.0001953737924415743, "loss": 0.7530478477478028, "step": 97030 }, { "epoch": 0.5768259119900613, "grad_norm": 2.134254217147827, "learning_rate": 0.0001953718221946047, "loss": 0.6520376205444336, "step": 97040 }, { "epoch": 0.5768853540667297, "grad_norm": 1.728318452835083, "learning_rate": 0.0001953698515392442, "loss": 0.69723539352417, "step": 97050 }, { "epoch": 0.5769447961433981, "grad_norm": 1.4253073930740356, "learning_rate": 0.00019536788047550224, "loss": 0.6813769817352295, "step": 97060 }, { "epoch": 0.5770042382200664, "grad_norm": 2.046915054321289, "learning_rate": 0.00019536590900338826, "loss": 0.6683374404907226, "step": 97070 }, { "epoch": 0.5770636802967348, "grad_norm": 1.5634660720825195, "learning_rate": 0.00019536393712291168, "loss": 0.6811937808990478, "step": 97080 }, { "epoch": 0.5771231223734032, "grad_norm": 1.6322400569915771, "learning_rate": 0.0001953619648340819, "loss": 0.6526605606079101, "step": 97090 }, { "epoch": 0.5771825644500717, "grad_norm": 1.7126665115356445, "learning_rate": 0.00019535999213690837, "loss": 0.6448000907897949, "step": 97100 }, { "epoch": 0.5772420065267401, "grad_norm": 1.3241254091262817, "learning_rate": 0.00019535801903140053, "loss": 0.6605913162231445, "step": 97110 }, { "epoch": 0.5773014486034084, "grad_norm": 1.5643072128295898, "learning_rate": 0.00019535604551756784, "loss": 0.6703065872192383, "step": 97120 }, { "epoch": 0.5773608906800768, "grad_norm": 1.7451421022415161, "learning_rate": 0.00019535407159541968, "loss": 0.7078357696533203, "step": 97130 }, { "epoch": 0.5774203327567452, "grad_norm": 1.4704079627990723, "learning_rate": 0.00019535209726496557, "loss": 0.6664316177368164, "step": 97140 }, { "epoch": 0.5774797748334136, "grad_norm": 1.7947874069213867, "learning_rate": 0.00019535012252621493, "loss": 0.713897705078125, "step": 97150 }, { "epoch": 0.5775392169100819, "grad_norm": 1.7025038003921509, "learning_rate": 0.0001953481473791772, "loss": 0.647088623046875, "step": 97160 }, { "epoch": 0.5775986589867503, "grad_norm": 2.0958003997802734, "learning_rate": 0.0001953461718238618, "loss": 0.6833380222320556, "step": 97170 }, { "epoch": 0.5776581010634187, "grad_norm": 1.7274023294448853, "learning_rate": 0.0001953441958602782, "loss": 0.6606766700744628, "step": 97180 }, { "epoch": 0.5777175431400872, "grad_norm": 1.410714030265808, "learning_rate": 0.0001953422194884359, "loss": 0.675043773651123, "step": 97190 }, { "epoch": 0.5777769852167556, "grad_norm": 1.5413740873336792, "learning_rate": 0.0001953402427083443, "loss": 0.6972854614257813, "step": 97200 }, { "epoch": 0.5778364272934239, "grad_norm": 1.918931007385254, "learning_rate": 0.00019533826552001283, "loss": 0.7142414569854736, "step": 97210 }, { "epoch": 0.5778958693700923, "grad_norm": 1.6733838319778442, "learning_rate": 0.000195336287923451, "loss": 0.6895496845245361, "step": 97220 }, { "epoch": 0.5779553114467607, "grad_norm": 1.6633009910583496, "learning_rate": 0.00019533430991866825, "loss": 0.7116372108459472, "step": 97230 }, { "epoch": 0.5780147535234291, "grad_norm": 1.7579001188278198, "learning_rate": 0.0001953323315056741, "loss": 0.6913118839263916, "step": 97240 }, { "epoch": 0.5780741956000975, "grad_norm": 1.8288933038711548, "learning_rate": 0.00019533035268447794, "loss": 0.7343320846557617, "step": 97250 }, { "epoch": 0.5781336376767658, "grad_norm": 1.9030381441116333, "learning_rate": 0.00019532837345508924, "loss": 0.6681829452514648, "step": 97260 }, { "epoch": 0.5781930797534343, "grad_norm": 2.2322030067443848, "learning_rate": 0.00019532639381751748, "loss": 0.6948253631591796, "step": 97270 }, { "epoch": 0.5782525218301027, "grad_norm": 1.6238058805465698, "learning_rate": 0.00019532441377177216, "loss": 0.6396859169006348, "step": 97280 }, { "epoch": 0.5783119639067711, "grad_norm": 1.5792665481567383, "learning_rate": 0.00019532243331786274, "loss": 0.6464614391326904, "step": 97290 }, { "epoch": 0.5783714059834394, "grad_norm": 1.9131683111190796, "learning_rate": 0.00019532045245579865, "loss": 0.6777727127075195, "step": 97300 }, { "epoch": 0.5784308480601078, "grad_norm": 1.6582591533660889, "learning_rate": 0.00019531847118558942, "loss": 0.6714053153991699, "step": 97310 }, { "epoch": 0.5784902901367762, "grad_norm": 1.546265959739685, "learning_rate": 0.00019531648950724448, "loss": 0.6074804306030274, "step": 97320 }, { "epoch": 0.5785497322134446, "grad_norm": 1.8053158521652222, "learning_rate": 0.00019531450742077338, "loss": 0.710184907913208, "step": 97330 }, { "epoch": 0.578609174290113, "grad_norm": 1.7084259986877441, "learning_rate": 0.0001953125249261855, "loss": 0.7008670806884766, "step": 97340 }, { "epoch": 0.5786686163667814, "grad_norm": 1.765448808670044, "learning_rate": 0.00019531054202349043, "loss": 0.6478874206542968, "step": 97350 }, { "epoch": 0.5787280584434498, "grad_norm": 1.540543556213379, "learning_rate": 0.0001953085587126976, "loss": 0.634684944152832, "step": 97360 }, { "epoch": 0.5787875005201182, "grad_norm": 2.1101179122924805, "learning_rate": 0.0001953065749938165, "loss": 0.7195029258728027, "step": 97370 }, { "epoch": 0.5788469425967866, "grad_norm": 2.0414276123046875, "learning_rate": 0.0001953045908668566, "loss": 0.6345639705657959, "step": 97380 }, { "epoch": 0.5789063846734549, "grad_norm": 2.164144515991211, "learning_rate": 0.00019530260633182745, "loss": 0.673332405090332, "step": 97390 }, { "epoch": 0.5789658267501233, "grad_norm": 2.065969705581665, "learning_rate": 0.00019530062138873848, "loss": 0.6582683563232422, "step": 97400 }, { "epoch": 0.5790252688267917, "grad_norm": 2.252307891845703, "learning_rate": 0.00019529863603759922, "loss": 0.7190531253814697, "step": 97410 }, { "epoch": 0.5790847109034601, "grad_norm": 1.5671697854995728, "learning_rate": 0.00019529665027841916, "loss": 0.75425124168396, "step": 97420 }, { "epoch": 0.5791441529801286, "grad_norm": 1.7952299118041992, "learning_rate": 0.00019529466411120783, "loss": 0.6455657958984375, "step": 97430 }, { "epoch": 0.5792035950567969, "grad_norm": 1.4801651239395142, "learning_rate": 0.00019529267753597466, "loss": 0.643988037109375, "step": 97440 }, { "epoch": 0.5792630371334653, "grad_norm": 1.6091777086257935, "learning_rate": 0.0001952906905527292, "loss": 0.7260762214660644, "step": 97450 }, { "epoch": 0.5793224792101337, "grad_norm": 1.4664335250854492, "learning_rate": 0.00019528870316148098, "loss": 0.6927233219146729, "step": 97460 }, { "epoch": 0.5793819212868021, "grad_norm": 1.8738006353378296, "learning_rate": 0.00019528671536223947, "loss": 0.6806728363037109, "step": 97470 }, { "epoch": 0.5794413633634705, "grad_norm": 1.3871088027954102, "learning_rate": 0.00019528472715501418, "loss": 0.6752328872680664, "step": 97480 }, { "epoch": 0.5795008054401388, "grad_norm": 1.5667471885681152, "learning_rate": 0.00019528273853981464, "loss": 0.7434189319610596, "step": 97490 }, { "epoch": 0.5795602475168072, "grad_norm": 1.6905690431594849, "learning_rate": 0.00019528074951665028, "loss": 0.6590291023254394, "step": 97500 }, { "epoch": 0.5796196895934757, "grad_norm": 1.5617557764053345, "learning_rate": 0.00019527876008553077, "loss": 0.6861366271972656, "step": 97510 }, { "epoch": 0.5796791316701441, "grad_norm": 1.8362115621566772, "learning_rate": 0.0001952767702464655, "loss": 0.6952180862426758, "step": 97520 }, { "epoch": 0.5797385737468124, "grad_norm": 1.5617300271987915, "learning_rate": 0.00019527477999946403, "loss": 0.6808476448059082, "step": 97530 }, { "epoch": 0.5797980158234808, "grad_norm": 1.5061129331588745, "learning_rate": 0.00019527278934453588, "loss": 0.7040476322174072, "step": 97540 }, { "epoch": 0.5798574579001492, "grad_norm": 1.649193286895752, "learning_rate": 0.00019527079828169058, "loss": 0.7035690307617187, "step": 97550 }, { "epoch": 0.5799168999768176, "grad_norm": 1.7341575622558594, "learning_rate": 0.00019526880681093765, "loss": 0.6996724128723144, "step": 97560 }, { "epoch": 0.579976342053486, "grad_norm": 1.9301000833511353, "learning_rate": 0.00019526681493228662, "loss": 0.7028212547302246, "step": 97570 }, { "epoch": 0.5800357841301543, "grad_norm": 1.5789270401000977, "learning_rate": 0.000195264822645747, "loss": 0.7462003231048584, "step": 97580 }, { "epoch": 0.5800952262068227, "grad_norm": 1.812398076057434, "learning_rate": 0.0001952628299513283, "loss": 0.6992716789245605, "step": 97590 }, { "epoch": 0.5801546682834912, "grad_norm": 1.5194913148880005, "learning_rate": 0.00019526083684904015, "loss": 0.64644775390625, "step": 97600 }, { "epoch": 0.5802141103601596, "grad_norm": 1.6852017641067505, "learning_rate": 0.00019525884333889199, "loss": 0.6992297649383545, "step": 97610 }, { "epoch": 0.580273552436828, "grad_norm": 1.7905077934265137, "learning_rate": 0.00019525684942089342, "loss": 0.6346604347229003, "step": 97620 }, { "epoch": 0.5803329945134963, "grad_norm": 1.494306206703186, "learning_rate": 0.0001952548550950539, "loss": 0.6473243236541748, "step": 97630 }, { "epoch": 0.5803924365901647, "grad_norm": 1.8705389499664307, "learning_rate": 0.00019525286036138303, "loss": 0.6749283790588378, "step": 97640 }, { "epoch": 0.5804518786668331, "grad_norm": 1.609571099281311, "learning_rate": 0.00019525086521989037, "loss": 0.6646119117736816, "step": 97650 }, { "epoch": 0.5805113207435015, "grad_norm": 1.4748269319534302, "learning_rate": 0.00019524886967058538, "loss": 0.6585827350616456, "step": 97660 }, { "epoch": 0.5805707628201698, "grad_norm": 1.4685091972351074, "learning_rate": 0.00019524687371347767, "loss": 0.6329784393310547, "step": 97670 }, { "epoch": 0.5806302048968383, "grad_norm": 1.4297434091567993, "learning_rate": 0.00019524487734857678, "loss": 0.6827861785888671, "step": 97680 }, { "epoch": 0.5806896469735067, "grad_norm": 1.6835263967514038, "learning_rate": 0.00019524288057589227, "loss": 0.607020902633667, "step": 97690 }, { "epoch": 0.5807490890501751, "grad_norm": 1.3222603797912598, "learning_rate": 0.00019524088339543366, "loss": 0.6438658237457275, "step": 97700 }, { "epoch": 0.5808085311268435, "grad_norm": 1.723862886428833, "learning_rate": 0.00019523888580721052, "loss": 0.6954309463500976, "step": 97710 }, { "epoch": 0.5808679732035118, "grad_norm": 1.9858962297439575, "learning_rate": 0.0001952368878112324, "loss": 0.6519149303436279, "step": 97720 }, { "epoch": 0.5809274152801802, "grad_norm": 1.2565757036209106, "learning_rate": 0.0001952348894075089, "loss": 0.6259150028228759, "step": 97730 }, { "epoch": 0.5809868573568486, "grad_norm": 1.6017131805419922, "learning_rate": 0.0001952328905960495, "loss": 0.694432544708252, "step": 97740 }, { "epoch": 0.581046299433517, "grad_norm": 1.3148760795593262, "learning_rate": 0.0001952308913768638, "loss": 0.706157112121582, "step": 97750 }, { "epoch": 0.5811057415101853, "grad_norm": 1.7226314544677734, "learning_rate": 0.00019522889174996143, "loss": 0.6422847747802735, "step": 97760 }, { "epoch": 0.5811651835868538, "grad_norm": 1.968481183052063, "learning_rate": 0.00019522689171535184, "loss": 0.6908926010131836, "step": 97770 }, { "epoch": 0.5812246256635222, "grad_norm": 1.8148853778839111, "learning_rate": 0.00019522489127304468, "loss": 0.6966911792755127, "step": 97780 }, { "epoch": 0.5812840677401906, "grad_norm": 2.007390022277832, "learning_rate": 0.0001952228904230495, "loss": 0.7267510414123535, "step": 97790 }, { "epoch": 0.581343509816859, "grad_norm": 1.9828664064407349, "learning_rate": 0.00019522088916537584, "loss": 0.6597370147705078, "step": 97800 }, { "epoch": 0.5814029518935273, "grad_norm": 2.0614736080169678, "learning_rate": 0.0001952188875000333, "loss": 0.6394262313842773, "step": 97810 }, { "epoch": 0.5814623939701957, "grad_norm": 1.9357990026474, "learning_rate": 0.00019521688542703145, "loss": 0.654439115524292, "step": 97820 }, { "epoch": 0.5815218360468641, "grad_norm": 1.7634670734405518, "learning_rate": 0.0001952148829463799, "loss": 0.6754268646240235, "step": 97830 }, { "epoch": 0.5815812781235326, "grad_norm": 1.7340147495269775, "learning_rate": 0.00019521288005808815, "loss": 0.6594734191894531, "step": 97840 }, { "epoch": 0.581640720200201, "grad_norm": 2.0021555423736572, "learning_rate": 0.00019521087676216585, "loss": 0.6255788326263427, "step": 97850 }, { "epoch": 0.5817001622768693, "grad_norm": 1.4917786121368408, "learning_rate": 0.00019520887305862257, "loss": 0.7190391540527343, "step": 97860 }, { "epoch": 0.5817596043535377, "grad_norm": 1.9234002828598022, "learning_rate": 0.00019520686894746787, "loss": 0.6901052474975586, "step": 97870 }, { "epoch": 0.5818190464302061, "grad_norm": 1.419276237487793, "learning_rate": 0.00019520486442871137, "loss": 0.6733378887176513, "step": 97880 }, { "epoch": 0.5818784885068745, "grad_norm": 1.6611448526382446, "learning_rate": 0.00019520285950236265, "loss": 0.6389004230499268, "step": 97890 }, { "epoch": 0.5819379305835428, "grad_norm": 1.7506513595581055, "learning_rate": 0.00019520085416843127, "loss": 0.7356062889099121, "step": 97900 }, { "epoch": 0.5819973726602112, "grad_norm": 1.6513209342956543, "learning_rate": 0.00019519884842692688, "loss": 0.7375510215759278, "step": 97910 }, { "epoch": 0.5820568147368796, "grad_norm": 1.8222681283950806, "learning_rate": 0.00019519684227785905, "loss": 0.6684935569763184, "step": 97920 }, { "epoch": 0.5821162568135481, "grad_norm": 1.5467414855957031, "learning_rate": 0.00019519483572123735, "loss": 0.6523089408874512, "step": 97930 }, { "epoch": 0.5821756988902165, "grad_norm": 1.8296838998794556, "learning_rate": 0.00019519282875707136, "loss": 0.6704058647155762, "step": 97940 }, { "epoch": 0.5822351409668848, "grad_norm": 1.8007941246032715, "learning_rate": 0.00019519082138537078, "loss": 0.696226978302002, "step": 97950 }, { "epoch": 0.5822945830435532, "grad_norm": 1.835508942604065, "learning_rate": 0.0001951888136061451, "loss": 0.7132321834564209, "step": 97960 }, { "epoch": 0.5823540251202216, "grad_norm": 1.5693778991699219, "learning_rate": 0.00019518680541940402, "loss": 0.6527010440826416, "step": 97970 }, { "epoch": 0.58241346719689, "grad_norm": 1.6255536079406738, "learning_rate": 0.0001951847968251571, "loss": 0.6813489913940429, "step": 97980 }, { "epoch": 0.5824729092735583, "grad_norm": 1.7239391803741455, "learning_rate": 0.00019518278782341392, "loss": 0.7101803779602051, "step": 97990 }, { "epoch": 0.5825323513502267, "grad_norm": 1.6151221990585327, "learning_rate": 0.00019518077841418412, "loss": 0.6737099647521972, "step": 98000 }, { "epoch": 0.5825917934268952, "grad_norm": 1.6352531909942627, "learning_rate": 0.00019517876859747734, "loss": 0.6786976814270019, "step": 98010 }, { "epoch": 0.5826512355035636, "grad_norm": 1.6838840246200562, "learning_rate": 0.00019517675837330312, "loss": 0.6850201606750488, "step": 98020 }, { "epoch": 0.582710677580232, "grad_norm": 1.6971832513809204, "learning_rate": 0.0001951747477416712, "loss": 0.6182479858398438, "step": 98030 }, { "epoch": 0.5827701196569003, "grad_norm": 1.9324383735656738, "learning_rate": 0.00019517273670259107, "loss": 0.7101956844329834, "step": 98040 }, { "epoch": 0.5828295617335687, "grad_norm": 1.5890114307403564, "learning_rate": 0.00019517072525607242, "loss": 0.6610702037811279, "step": 98050 }, { "epoch": 0.5828890038102371, "grad_norm": 1.4352025985717773, "learning_rate": 0.00019516871340212485, "loss": 0.6403085231781006, "step": 98060 }, { "epoch": 0.5829484458869055, "grad_norm": 2.031876564025879, "learning_rate": 0.00019516670114075796, "loss": 0.6346543312072754, "step": 98070 }, { "epoch": 0.583007887963574, "grad_norm": 1.7073490619659424, "learning_rate": 0.00019516468847198144, "loss": 0.6492556571960449, "step": 98080 }, { "epoch": 0.5830673300402422, "grad_norm": 1.7596864700317383, "learning_rate": 0.00019516267539580488, "loss": 0.6568405628204346, "step": 98090 }, { "epoch": 0.5831267721169107, "grad_norm": 2.529294967651367, "learning_rate": 0.0001951606619122379, "loss": 0.6490248680114746, "step": 98100 }, { "epoch": 0.5831862141935791, "grad_norm": 1.676167368888855, "learning_rate": 0.00019515864802129018, "loss": 0.6421329021453858, "step": 98110 }, { "epoch": 0.5832456562702475, "grad_norm": 1.776397943496704, "learning_rate": 0.00019515663372297125, "loss": 0.6222537517547607, "step": 98120 }, { "epoch": 0.5833050983469158, "grad_norm": 1.6734414100646973, "learning_rate": 0.00019515461901729086, "loss": 0.658854341506958, "step": 98130 }, { "epoch": 0.5833645404235842, "grad_norm": 1.6105595827102661, "learning_rate": 0.0001951526039042586, "loss": 0.6454614639282227, "step": 98140 }, { "epoch": 0.5834239825002526, "grad_norm": 2.032905340194702, "learning_rate": 0.00019515058838388412, "loss": 0.6748267650604248, "step": 98150 }, { "epoch": 0.583483424576921, "grad_norm": 1.9774283170700073, "learning_rate": 0.00019514857245617702, "loss": 0.6876497268676758, "step": 98160 }, { "epoch": 0.5835428666535895, "grad_norm": 1.6572940349578857, "learning_rate": 0.000195146556121147, "loss": 0.6866416931152344, "step": 98170 }, { "epoch": 0.5836023087302578, "grad_norm": 1.7749111652374268, "learning_rate": 0.00019514453937880368, "loss": 0.7072916030883789, "step": 98180 }, { "epoch": 0.5836617508069262, "grad_norm": 1.7716954946517944, "learning_rate": 0.0001951425222291567, "loss": 0.6926305770874024, "step": 98190 }, { "epoch": 0.5837211928835946, "grad_norm": 1.3597216606140137, "learning_rate": 0.00019514050467221573, "loss": 0.6995880126953125, "step": 98200 }, { "epoch": 0.583780634960263, "grad_norm": 1.753411054611206, "learning_rate": 0.0001951384867079904, "loss": 0.6464481353759766, "step": 98210 }, { "epoch": 0.5838400770369314, "grad_norm": 1.7568671703338623, "learning_rate": 0.0001951364683364904, "loss": 0.7071023941040039, "step": 98220 }, { "epoch": 0.5838995191135997, "grad_norm": 1.8290624618530273, "learning_rate": 0.0001951344495577253, "loss": 0.7209418296813965, "step": 98230 }, { "epoch": 0.5839589611902681, "grad_norm": 1.9483933448791504, "learning_rate": 0.00019513243037170487, "loss": 0.6814826965332031, "step": 98240 }, { "epoch": 0.5840184032669365, "grad_norm": 1.3530973196029663, "learning_rate": 0.00019513041077843867, "loss": 0.6681631088256836, "step": 98250 }, { "epoch": 0.584077845343605, "grad_norm": 1.8062390089035034, "learning_rate": 0.00019512839077793644, "loss": 0.6317895889282227, "step": 98260 }, { "epoch": 0.5841372874202733, "grad_norm": 1.6939324140548706, "learning_rate": 0.0001951263703702078, "loss": 0.674195671081543, "step": 98270 }, { "epoch": 0.5841967294969417, "grad_norm": 1.6093428134918213, "learning_rate": 0.00019512434955526242, "loss": 0.6570321083068847, "step": 98280 }, { "epoch": 0.5842561715736101, "grad_norm": 1.7351419925689697, "learning_rate": 0.00019512232833310996, "loss": 0.7228334903717041, "step": 98290 }, { "epoch": 0.5843156136502785, "grad_norm": 1.5456162691116333, "learning_rate": 0.00019512030670376012, "loss": 0.6677798271179199, "step": 98300 }, { "epoch": 0.5843750557269469, "grad_norm": 1.7800428867340088, "learning_rate": 0.00019511828466722256, "loss": 0.7023722648620605, "step": 98310 }, { "epoch": 0.5844344978036152, "grad_norm": 1.9425218105316162, "learning_rate": 0.00019511626222350694, "loss": 0.6998839378356934, "step": 98320 }, { "epoch": 0.5844939398802836, "grad_norm": 1.6103456020355225, "learning_rate": 0.0001951142393726229, "loss": 0.6685948371887207, "step": 98330 }, { "epoch": 0.5845533819569521, "grad_norm": 2.5462429523468018, "learning_rate": 0.0001951122161145802, "loss": 0.6598647594451904, "step": 98340 }, { "epoch": 0.5846128240336205, "grad_norm": 1.9028438329696655, "learning_rate": 0.00019511019244938845, "loss": 0.6811538696289062, "step": 98350 }, { "epoch": 0.5846722661102888, "grad_norm": 1.4269109964370728, "learning_rate": 0.00019510816837705735, "loss": 0.7185676574707032, "step": 98360 }, { "epoch": 0.5847317081869572, "grad_norm": 1.727543830871582, "learning_rate": 0.0001951061438975966, "loss": 0.7128554344177246, "step": 98370 }, { "epoch": 0.5847911502636256, "grad_norm": 2.0314910411834717, "learning_rate": 0.00019510411901101584, "loss": 0.6884743690490722, "step": 98380 }, { "epoch": 0.584850592340294, "grad_norm": 1.8701468706130981, "learning_rate": 0.00019510209371732484, "loss": 0.6240403175354003, "step": 98390 }, { "epoch": 0.5849100344169624, "grad_norm": 1.9777053594589233, "learning_rate": 0.0001951000680165332, "loss": 0.6995827674865722, "step": 98400 }, { "epoch": 0.5849694764936307, "grad_norm": 2.0917348861694336, "learning_rate": 0.00019509804190865064, "loss": 0.6635639667510986, "step": 98410 }, { "epoch": 0.5850289185702992, "grad_norm": 1.665094256401062, "learning_rate": 0.00019509601539368686, "loss": 0.6280592918395996, "step": 98420 }, { "epoch": 0.5850883606469676, "grad_norm": 1.706777572631836, "learning_rate": 0.00019509398847165156, "loss": 0.6330423831939698, "step": 98430 }, { "epoch": 0.585147802723636, "grad_norm": 1.5580147504806519, "learning_rate": 0.00019509196114255445, "loss": 0.6715589046478272, "step": 98440 }, { "epoch": 0.5852072448003044, "grad_norm": 1.9442647695541382, "learning_rate": 0.0001950899334064052, "loss": 0.7131243705749511, "step": 98450 }, { "epoch": 0.5852666868769727, "grad_norm": 1.922528862953186, "learning_rate": 0.00019508790526321347, "loss": 0.7207000732421875, "step": 98460 }, { "epoch": 0.5853261289536411, "grad_norm": 1.487465500831604, "learning_rate": 0.00019508587671298902, "loss": 0.6719451427459717, "step": 98470 }, { "epoch": 0.5853855710303095, "grad_norm": 2.178013801574707, "learning_rate": 0.00019508384775574159, "loss": 0.7338556289672852, "step": 98480 }, { "epoch": 0.5854450131069779, "grad_norm": 1.8011066913604736, "learning_rate": 0.0001950818183914808, "loss": 0.6620810508728028, "step": 98490 }, { "epoch": 0.5855044551836462, "grad_norm": 1.8427294492721558, "learning_rate": 0.0001950797886202164, "loss": 0.6876752853393555, "step": 98500 }, { "epoch": 0.5855638972603147, "grad_norm": 1.684822678565979, "learning_rate": 0.0001950777584419581, "loss": 0.6432923316955567, "step": 98510 }, { "epoch": 0.5856233393369831, "grad_norm": 1.8876744508743286, "learning_rate": 0.0001950757278567156, "loss": 0.7113710403442383, "step": 98520 }, { "epoch": 0.5856827814136515, "grad_norm": 1.7249115705490112, "learning_rate": 0.00019507369686449865, "loss": 0.7010455131530762, "step": 98530 }, { "epoch": 0.5857422234903199, "grad_norm": 1.4437235593795776, "learning_rate": 0.0001950716654653169, "loss": 0.6710682392120362, "step": 98540 }, { "epoch": 0.5858016655669882, "grad_norm": 1.6391302347183228, "learning_rate": 0.0001950696336591801, "loss": 0.6887447357177734, "step": 98550 }, { "epoch": 0.5858611076436566, "grad_norm": 1.7005819082260132, "learning_rate": 0.00019506760144609802, "loss": 0.5862574577331543, "step": 98560 }, { "epoch": 0.585920549720325, "grad_norm": 1.5326074361801147, "learning_rate": 0.00019506556882608033, "loss": 0.6255067348480224, "step": 98570 }, { "epoch": 0.5859799917969934, "grad_norm": 1.6527647972106934, "learning_rate": 0.00019506353579913673, "loss": 0.6594316005706787, "step": 98580 }, { "epoch": 0.5860394338736619, "grad_norm": 1.6516327857971191, "learning_rate": 0.00019506150236527696, "loss": 0.6979138374328613, "step": 98590 }, { "epoch": 0.5860988759503302, "grad_norm": 2.3026134967803955, "learning_rate": 0.0001950594685245108, "loss": 0.6316364765167236, "step": 98600 }, { "epoch": 0.5861583180269986, "grad_norm": 1.7940484285354614, "learning_rate": 0.00019505743427684793, "loss": 0.6998068332672119, "step": 98610 }, { "epoch": 0.586217760103667, "grad_norm": 1.8746227025985718, "learning_rate": 0.00019505539962229808, "loss": 0.6570743560791016, "step": 98620 }, { "epoch": 0.5862772021803354, "grad_norm": 1.3743375539779663, "learning_rate": 0.00019505336456087098, "loss": 0.6419120788574219, "step": 98630 }, { "epoch": 0.5863366442570037, "grad_norm": 1.5322297811508179, "learning_rate": 0.00019505132909257642, "loss": 0.6633567810058594, "step": 98640 }, { "epoch": 0.5863960863336721, "grad_norm": 1.503851056098938, "learning_rate": 0.00019504929321742406, "loss": 0.6182595729827881, "step": 98650 }, { "epoch": 0.5864555284103405, "grad_norm": 1.6735572814941406, "learning_rate": 0.0001950472569354237, "loss": 0.6571321487426758, "step": 98660 }, { "epoch": 0.586514970487009, "grad_norm": 1.9440586566925049, "learning_rate": 0.00019504522024658505, "loss": 0.653691291809082, "step": 98670 }, { "epoch": 0.5865744125636774, "grad_norm": 1.6912897825241089, "learning_rate": 0.00019504318315091785, "loss": 0.6434214115142822, "step": 98680 }, { "epoch": 0.5866338546403457, "grad_norm": 1.9938089847564697, "learning_rate": 0.00019504114564843186, "loss": 0.6867886066436768, "step": 98690 }, { "epoch": 0.5866932967170141, "grad_norm": 1.8082069158554077, "learning_rate": 0.0001950391077391368, "loss": 0.6528512954711914, "step": 98700 }, { "epoch": 0.5867527387936825, "grad_norm": 2.015174627304077, "learning_rate": 0.00019503706942304247, "loss": 0.6368470191955566, "step": 98710 }, { "epoch": 0.5868121808703509, "grad_norm": 1.577684760093689, "learning_rate": 0.0001950350307001586, "loss": 0.6621542930603027, "step": 98720 }, { "epoch": 0.5868716229470192, "grad_norm": 1.8397423028945923, "learning_rate": 0.00019503299157049491, "loss": 0.5907575607299804, "step": 98730 }, { "epoch": 0.5869310650236876, "grad_norm": 1.6604853868484497, "learning_rate": 0.00019503095203406119, "loss": 0.6745387077331543, "step": 98740 }, { "epoch": 0.586990507100356, "grad_norm": 3.3005757331848145, "learning_rate": 0.00019502891209086717, "loss": 0.6877181529998779, "step": 98750 }, { "epoch": 0.5870499491770245, "grad_norm": 1.5536307096481323, "learning_rate": 0.00019502687174092264, "loss": 0.6816671371459961, "step": 98760 }, { "epoch": 0.5871093912536929, "grad_norm": 1.926427960395813, "learning_rate": 0.0001950248309842373, "loss": 0.6710246086120606, "step": 98770 }, { "epoch": 0.5871688333303612, "grad_norm": 1.7125388383865356, "learning_rate": 0.00019502278982082101, "loss": 0.7432361602783203, "step": 98780 }, { "epoch": 0.5872282754070296, "grad_norm": 1.662521481513977, "learning_rate": 0.00019502074825068346, "loss": 0.6598649024963379, "step": 98790 }, { "epoch": 0.587287717483698, "grad_norm": 1.7596346139907837, "learning_rate": 0.00019501870627383443, "loss": 0.6695518970489502, "step": 98800 }, { "epoch": 0.5873471595603664, "grad_norm": 1.7920033931732178, "learning_rate": 0.00019501666389028368, "loss": 0.6819306373596191, "step": 98810 }, { "epoch": 0.5874066016370348, "grad_norm": 2.2496559619903564, "learning_rate": 0.000195014621100041, "loss": 0.733909797668457, "step": 98820 }, { "epoch": 0.5874660437137031, "grad_norm": 1.5006908178329468, "learning_rate": 0.00019501257790311617, "loss": 0.5993073463439942, "step": 98830 }, { "epoch": 0.5875254857903716, "grad_norm": 1.9429116249084473, "learning_rate": 0.00019501053429951895, "loss": 0.728023099899292, "step": 98840 }, { "epoch": 0.58758492786704, "grad_norm": 1.6882539987564087, "learning_rate": 0.0001950084902892591, "loss": 0.7220222473144531, "step": 98850 }, { "epoch": 0.5876443699437084, "grad_norm": 1.3504419326782227, "learning_rate": 0.00019500644587234643, "loss": 0.6159022331237793, "step": 98860 }, { "epoch": 0.5877038120203767, "grad_norm": 1.946909785270691, "learning_rate": 0.00019500440104879073, "loss": 0.6517117977142334, "step": 98870 }, { "epoch": 0.5877632540970451, "grad_norm": 1.7632578611373901, "learning_rate": 0.00019500235581860172, "loss": 0.7626999855041504, "step": 98880 }, { "epoch": 0.5878226961737135, "grad_norm": 1.7161767482757568, "learning_rate": 0.00019500031018178919, "loss": 0.6728769302368164, "step": 98890 }, { "epoch": 0.5878821382503819, "grad_norm": 1.5370999574661255, "learning_rate": 0.000194998264138363, "loss": 0.7104389667510986, "step": 98900 }, { "epoch": 0.5879415803270504, "grad_norm": 1.8295668363571167, "learning_rate": 0.00019499621768833287, "loss": 0.7396879196166992, "step": 98910 }, { "epoch": 0.5880010224037187, "grad_norm": 1.518330693244934, "learning_rate": 0.0001949941708317086, "loss": 0.6222133636474609, "step": 98920 }, { "epoch": 0.5880604644803871, "grad_norm": 2.117525815963745, "learning_rate": 0.00019499212356850003, "loss": 0.6296261787414551, "step": 98930 }, { "epoch": 0.5881199065570555, "grad_norm": 1.786449909210205, "learning_rate": 0.0001949900758987169, "loss": 0.6774661064147949, "step": 98940 }, { "epoch": 0.5881793486337239, "grad_norm": 1.6109004020690918, "learning_rate": 0.00019498802782236903, "loss": 0.6246162414550781, "step": 98950 }, { "epoch": 0.5882387907103923, "grad_norm": 1.5461574792861938, "learning_rate": 0.00019498597933946616, "loss": 0.7026494979858399, "step": 98960 }, { "epoch": 0.5882982327870606, "grad_norm": 1.7561688423156738, "learning_rate": 0.00019498393045001822, "loss": 0.6814032077789307, "step": 98970 }, { "epoch": 0.588357674863729, "grad_norm": 2.2203009128570557, "learning_rate": 0.00019498188115403488, "loss": 0.6938535690307617, "step": 98980 }, { "epoch": 0.5884171169403974, "grad_norm": 1.6671468019485474, "learning_rate": 0.000194979831451526, "loss": 0.6502880573272705, "step": 98990 }, { "epoch": 0.5884765590170659, "grad_norm": 1.7155325412750244, "learning_rate": 0.00019497778134250137, "loss": 0.658544921875, "step": 99000 }, { "epoch": 0.5885360010937342, "grad_norm": 1.7795889377593994, "learning_rate": 0.0001949757308269708, "loss": 0.6784403324127197, "step": 99010 }, { "epoch": 0.5885954431704026, "grad_norm": 1.731606125831604, "learning_rate": 0.00019497367990494412, "loss": 0.6630072593688965, "step": 99020 }, { "epoch": 0.588654885247071, "grad_norm": 1.3847755193710327, "learning_rate": 0.00019497162857643114, "loss": 0.6034678936004638, "step": 99030 }, { "epoch": 0.5887143273237394, "grad_norm": 1.55549955368042, "learning_rate": 0.00019496957684144163, "loss": 0.6844896793365478, "step": 99040 }, { "epoch": 0.5887737694004078, "grad_norm": 1.9358681440353394, "learning_rate": 0.00019496752469998544, "loss": 0.6249449729919434, "step": 99050 }, { "epoch": 0.5888332114770761, "grad_norm": 1.8085894584655762, "learning_rate": 0.0001949654721520724, "loss": 0.6723369598388672, "step": 99060 }, { "epoch": 0.5888926535537445, "grad_norm": 1.4934775829315186, "learning_rate": 0.00019496341919771228, "loss": 0.6824168205261231, "step": 99070 }, { "epoch": 0.588952095630413, "grad_norm": 1.5744386911392212, "learning_rate": 0.00019496136583691494, "loss": 0.6317462921142578, "step": 99080 }, { "epoch": 0.5890115377070814, "grad_norm": 2.0562024116516113, "learning_rate": 0.0001949593120696902, "loss": 0.6270318984985351, "step": 99090 }, { "epoch": 0.5890709797837497, "grad_norm": 2.00512433052063, "learning_rate": 0.00019495725789604786, "loss": 0.6320645332336425, "step": 99100 }, { "epoch": 0.5891304218604181, "grad_norm": 1.8560459613800049, "learning_rate": 0.00019495520331599777, "loss": 0.6618510246276855, "step": 99110 }, { "epoch": 0.5891898639370865, "grad_norm": 1.6878972053527832, "learning_rate": 0.00019495314832954975, "loss": 0.6662096977233887, "step": 99120 }, { "epoch": 0.5892493060137549, "grad_norm": 1.4876102209091187, "learning_rate": 0.00019495109293671362, "loss": 0.665648078918457, "step": 99130 }, { "epoch": 0.5893087480904233, "grad_norm": 1.467490553855896, "learning_rate": 0.00019494903713749925, "loss": 0.6855038166046142, "step": 99140 }, { "epoch": 0.5893681901670916, "grad_norm": 1.6488152742385864, "learning_rate": 0.00019494698093191646, "loss": 0.6921981811523438, "step": 99150 }, { "epoch": 0.58942763224376, "grad_norm": 1.7581948041915894, "learning_rate": 0.000194944924319975, "loss": 0.718660545349121, "step": 99160 }, { "epoch": 0.5894870743204285, "grad_norm": 1.712365984916687, "learning_rate": 0.00019494286730168485, "loss": 0.7304631233215332, "step": 99170 }, { "epoch": 0.5895465163970969, "grad_norm": 1.338736653327942, "learning_rate": 0.00019494080987705577, "loss": 0.693264389038086, "step": 99180 }, { "epoch": 0.5896059584737653, "grad_norm": 1.5655466318130493, "learning_rate": 0.00019493875204609762, "loss": 0.6842916011810303, "step": 99190 }, { "epoch": 0.5896654005504336, "grad_norm": 1.6765633821487427, "learning_rate": 0.00019493669380882023, "loss": 0.7018095016479492, "step": 99200 }, { "epoch": 0.589724842627102, "grad_norm": 1.5134954452514648, "learning_rate": 0.00019493463516523344, "loss": 0.6810028553009033, "step": 99210 }, { "epoch": 0.5897842847037704, "grad_norm": 1.767831563949585, "learning_rate": 0.00019493257611534712, "loss": 0.6588092803955078, "step": 99220 }, { "epoch": 0.5898437267804388, "grad_norm": 1.8941065073013306, "learning_rate": 0.00019493051665917113, "loss": 0.6696566581726074, "step": 99230 }, { "epoch": 0.5899031688571071, "grad_norm": 1.7899526357650757, "learning_rate": 0.0001949284567967153, "loss": 0.7452157974243164, "step": 99240 }, { "epoch": 0.5899626109337756, "grad_norm": 1.7735399007797241, "learning_rate": 0.00019492639652798948, "loss": 0.6579686164855957, "step": 99250 }, { "epoch": 0.590022053010444, "grad_norm": 1.7783222198486328, "learning_rate": 0.0001949243358530035, "loss": 0.6904882431030274, "step": 99260 }, { "epoch": 0.5900814950871124, "grad_norm": 1.8399720191955566, "learning_rate": 0.0001949222747717673, "loss": 0.7572260856628418, "step": 99270 }, { "epoch": 0.5901409371637808, "grad_norm": 1.9979652166366577, "learning_rate": 0.00019492021328429063, "loss": 0.6447965621948242, "step": 99280 }, { "epoch": 0.5902003792404491, "grad_norm": 1.8303658962249756, "learning_rate": 0.00019491815139058348, "loss": 0.6761157035827636, "step": 99290 }, { "epoch": 0.5902598213171175, "grad_norm": 1.6173162460327148, "learning_rate": 0.00019491608909065562, "loss": 0.6876338481903076, "step": 99300 }, { "epoch": 0.5903192633937859, "grad_norm": 1.7581778764724731, "learning_rate": 0.00019491402638451694, "loss": 0.6818688869476318, "step": 99310 }, { "epoch": 0.5903787054704543, "grad_norm": 1.6422202587127686, "learning_rate": 0.0001949119632721773, "loss": 0.6372363567352295, "step": 99320 }, { "epoch": 0.5904381475471228, "grad_norm": 1.5425348281860352, "learning_rate": 0.0001949098997536466, "loss": 0.6674015998840332, "step": 99330 }, { "epoch": 0.5904975896237911, "grad_norm": 1.9332865476608276, "learning_rate": 0.00019490783582893465, "loss": 0.6435949325561523, "step": 99340 }, { "epoch": 0.5905570317004595, "grad_norm": 1.594117522239685, "learning_rate": 0.00019490577149805142, "loss": 0.6907174587249756, "step": 99350 }, { "epoch": 0.5906164737771279, "grad_norm": 1.7870415449142456, "learning_rate": 0.00019490370676100667, "loss": 0.6866250038146973, "step": 99360 }, { "epoch": 0.5906759158537963, "grad_norm": 1.881487250328064, "learning_rate": 0.00019490164161781035, "loss": 0.6440549850463867, "step": 99370 }, { "epoch": 0.5907353579304646, "grad_norm": 1.5747063159942627, "learning_rate": 0.00019489957606847234, "loss": 0.6696939468383789, "step": 99380 }, { "epoch": 0.590794800007133, "grad_norm": 1.7112053632736206, "learning_rate": 0.00019489751011300249, "loss": 0.6749454975128174, "step": 99390 }, { "epoch": 0.5908542420838014, "grad_norm": 1.5867496728897095, "learning_rate": 0.0001948954437514107, "loss": 0.6534645080566406, "step": 99400 }, { "epoch": 0.5909136841604699, "grad_norm": 1.7448471784591675, "learning_rate": 0.00019489337698370686, "loss": 0.6344707012176514, "step": 99410 }, { "epoch": 0.5909731262371383, "grad_norm": 1.8334600925445557, "learning_rate": 0.0001948913098099008, "loss": 0.6829658508300781, "step": 99420 }, { "epoch": 0.5910325683138066, "grad_norm": 1.9168962240219116, "learning_rate": 0.0001948892422300025, "loss": 0.6876240253448487, "step": 99430 }, { "epoch": 0.591092010390475, "grad_norm": 2.082127094268799, "learning_rate": 0.0001948871742440218, "loss": 0.6768842697143554, "step": 99440 }, { "epoch": 0.5911514524671434, "grad_norm": 1.6841062307357788, "learning_rate": 0.00019488510585196863, "loss": 0.6399631500244141, "step": 99450 }, { "epoch": 0.5912108945438118, "grad_norm": 1.6534429788589478, "learning_rate": 0.0001948830370538528, "loss": 0.6793910503387451, "step": 99460 }, { "epoch": 0.5912703366204801, "grad_norm": 1.8410592079162598, "learning_rate": 0.0001948809678496843, "loss": 0.6909152030944824, "step": 99470 }, { "epoch": 0.5913297786971485, "grad_norm": 1.5523730516433716, "learning_rate": 0.00019487889823947295, "loss": 0.6473325252532959, "step": 99480 }, { "epoch": 0.591389220773817, "grad_norm": 1.7656551599502563, "learning_rate": 0.00019487682822322874, "loss": 0.7016627311706543, "step": 99490 }, { "epoch": 0.5914486628504854, "grad_norm": 1.7339457273483276, "learning_rate": 0.00019487475780096149, "loss": 0.7056763172149658, "step": 99500 }, { "epoch": 0.5915081049271538, "grad_norm": 1.6109018325805664, "learning_rate": 0.00019487268697268115, "loss": 0.6894848823547364, "step": 99510 }, { "epoch": 0.5915675470038221, "grad_norm": 1.5079128742218018, "learning_rate": 0.0001948706157383976, "loss": 0.681612777709961, "step": 99520 }, { "epoch": 0.5916269890804905, "grad_norm": 1.4591395854949951, "learning_rate": 0.00019486854409812076, "loss": 0.660331916809082, "step": 99530 }, { "epoch": 0.5916864311571589, "grad_norm": 1.4585163593292236, "learning_rate": 0.00019486647205186055, "loss": 0.7057433128356934, "step": 99540 }, { "epoch": 0.5917458732338273, "grad_norm": 1.862402319908142, "learning_rate": 0.00019486439959962688, "loss": 0.6829584121704102, "step": 99550 }, { "epoch": 0.5918053153104957, "grad_norm": 1.7004364728927612, "learning_rate": 0.00019486232674142964, "loss": 0.6463687896728516, "step": 99560 }, { "epoch": 0.591864757387164, "grad_norm": 1.737343430519104, "learning_rate": 0.00019486025347727876, "loss": 0.698725700378418, "step": 99570 }, { "epoch": 0.5919241994638325, "grad_norm": 1.853177785873413, "learning_rate": 0.00019485817980718415, "loss": 0.6498298645019531, "step": 99580 }, { "epoch": 0.5919836415405009, "grad_norm": 2.4608302116394043, "learning_rate": 0.00019485610573115577, "loss": 0.6673867225646972, "step": 99590 }, { "epoch": 0.5920430836171693, "grad_norm": 1.7282981872558594, "learning_rate": 0.0001948540312492035, "loss": 0.6763469696044921, "step": 99600 }, { "epoch": 0.5921025256938376, "grad_norm": 1.5125328302383423, "learning_rate": 0.00019485195636133727, "loss": 0.6974936485290527, "step": 99610 }, { "epoch": 0.592161967770506, "grad_norm": 1.5748015642166138, "learning_rate": 0.00019484988106756703, "loss": 0.7107574462890625, "step": 99620 }, { "epoch": 0.5922214098471744, "grad_norm": 1.4067401885986328, "learning_rate": 0.00019484780536790268, "loss": 0.6411305427551269, "step": 99630 }, { "epoch": 0.5922808519238428, "grad_norm": 1.4624743461608887, "learning_rate": 0.0001948457292623541, "loss": 0.6489368438720703, "step": 99640 }, { "epoch": 0.5923402940005112, "grad_norm": 2.102654457092285, "learning_rate": 0.00019484365275093134, "loss": 0.7221357345581054, "step": 99650 }, { "epoch": 0.5923997360771796, "grad_norm": 1.6668682098388672, "learning_rate": 0.00019484157583364426, "loss": 0.7114311218261719, "step": 99660 }, { "epoch": 0.592459178153848, "grad_norm": 1.7067360877990723, "learning_rate": 0.00019483949851050283, "loss": 0.6653680801391602, "step": 99670 }, { "epoch": 0.5925186202305164, "grad_norm": 1.885343074798584, "learning_rate": 0.00019483742078151695, "loss": 0.7206261634826661, "step": 99680 }, { "epoch": 0.5925780623071848, "grad_norm": 2.2130889892578125, "learning_rate": 0.00019483534264669655, "loss": 0.7046448230743408, "step": 99690 }, { "epoch": 0.5926375043838532, "grad_norm": 1.6492494344711304, "learning_rate": 0.00019483326410605164, "loss": 0.6531963348388672, "step": 99700 }, { "epoch": 0.5926969464605215, "grad_norm": 1.6330682039260864, "learning_rate": 0.00019483118515959208, "loss": 0.6678966999053955, "step": 99710 }, { "epoch": 0.5927563885371899, "grad_norm": 2.0568959712982178, "learning_rate": 0.00019482910580732784, "loss": 0.674788236618042, "step": 99720 }, { "epoch": 0.5928158306138583, "grad_norm": 1.5477715730667114, "learning_rate": 0.00019482702604926893, "loss": 0.6529246807098389, "step": 99730 }, { "epoch": 0.5928752726905268, "grad_norm": 1.466109275817871, "learning_rate": 0.0001948249458854252, "loss": 0.676573371887207, "step": 99740 }, { "epoch": 0.5929347147671951, "grad_norm": 1.4831793308258057, "learning_rate": 0.00019482286531580668, "loss": 0.6584924221038818, "step": 99750 }, { "epoch": 0.5929941568438635, "grad_norm": 1.650708794593811, "learning_rate": 0.0001948207843404233, "loss": 0.6590128898620605, "step": 99760 }, { "epoch": 0.5930535989205319, "grad_norm": 1.7570973634719849, "learning_rate": 0.000194818702959285, "loss": 0.70071439743042, "step": 99770 }, { "epoch": 0.5931130409972003, "grad_norm": 1.5900346040725708, "learning_rate": 0.00019481662117240174, "loss": 0.736821985244751, "step": 99780 }, { "epoch": 0.5931724830738687, "grad_norm": 2.1077301502227783, "learning_rate": 0.0001948145389797835, "loss": 0.6471625328063965, "step": 99790 }, { "epoch": 0.593231925150537, "grad_norm": 1.8135372400283813, "learning_rate": 0.00019481245638144017, "loss": 0.6944452285766601, "step": 99800 }, { "epoch": 0.5932913672272054, "grad_norm": 1.6437301635742188, "learning_rate": 0.0001948103733773818, "loss": 0.6241950035095215, "step": 99810 }, { "epoch": 0.5933508093038738, "grad_norm": 2.0589492321014404, "learning_rate": 0.00019480828996761834, "loss": 0.6699059486389161, "step": 99820 }, { "epoch": 0.5934102513805423, "grad_norm": 1.6992018222808838, "learning_rate": 0.0001948062061521597, "loss": 0.6772243499755859, "step": 99830 }, { "epoch": 0.5934696934572106, "grad_norm": 1.4700545072555542, "learning_rate": 0.0001948041219310159, "loss": 0.6581212997436523, "step": 99840 }, { "epoch": 0.593529135533879, "grad_norm": 1.9883900880813599, "learning_rate": 0.00019480203730419692, "loss": 0.6403616905212403, "step": 99850 }, { "epoch": 0.5935885776105474, "grad_norm": 2.217298984527588, "learning_rate": 0.00019479995227171269, "loss": 0.6442612648010254, "step": 99860 }, { "epoch": 0.5936480196872158, "grad_norm": 1.6653523445129395, "learning_rate": 0.00019479786683357318, "loss": 0.6476640701293945, "step": 99870 }, { "epoch": 0.5937074617638842, "grad_norm": 1.4473795890808105, "learning_rate": 0.0001947957809897884, "loss": 0.6853362083435058, "step": 99880 }, { "epoch": 0.5937669038405525, "grad_norm": 1.4459465742111206, "learning_rate": 0.0001947936947403683, "loss": 0.6314494132995605, "step": 99890 }, { "epoch": 0.5938263459172209, "grad_norm": 1.4017804861068726, "learning_rate": 0.0001947916080853229, "loss": 0.6642918586730957, "step": 99900 }, { "epoch": 0.5938857879938894, "grad_norm": 1.6112414598464966, "learning_rate": 0.00019478952102466214, "loss": 0.6290882587432861, "step": 99910 }, { "epoch": 0.5939452300705578, "grad_norm": 1.8469825983047485, "learning_rate": 0.00019478743355839606, "loss": 0.6619091987609863, "step": 99920 }, { "epoch": 0.5940046721472262, "grad_norm": 1.8042584657669067, "learning_rate": 0.00019478534568653455, "loss": 0.6820234298706055, "step": 99930 }, { "epoch": 0.5940641142238945, "grad_norm": 1.598270058631897, "learning_rate": 0.0001947832574090877, "loss": 0.6622164249420166, "step": 99940 }, { "epoch": 0.5941235563005629, "grad_norm": 1.8869094848632812, "learning_rate": 0.00019478116872606542, "loss": 0.652967119216919, "step": 99950 }, { "epoch": 0.5941829983772313, "grad_norm": 1.3519096374511719, "learning_rate": 0.00019477907963747775, "loss": 0.6540739059448242, "step": 99960 }, { "epoch": 0.5942424404538997, "grad_norm": 1.7578864097595215, "learning_rate": 0.0001947769901433347, "loss": 0.6650980949401856, "step": 99970 }, { "epoch": 0.594301882530568, "grad_norm": 1.5832737684249878, "learning_rate": 0.00019477490024364617, "loss": 0.6676956653594971, "step": 99980 }, { "epoch": 0.5943613246072365, "grad_norm": 2.380850076675415, "learning_rate": 0.00019477280993842225, "loss": 0.6546863555908203, "step": 99990 }, { "epoch": 0.5944207666839049, "grad_norm": 1.8241078853607178, "learning_rate": 0.00019477071922767295, "loss": 0.7166097640991211, "step": 100000 }, { "epoch": 0.5944802087605733, "grad_norm": 2.009766101837158, "learning_rate": 0.00019476862811140818, "loss": 0.6462011337280273, "step": 100010 }, { "epoch": 0.5945396508372417, "grad_norm": 2.3082189559936523, "learning_rate": 0.000194766536589638, "loss": 0.6841827392578125, "step": 100020 }, { "epoch": 0.59459909291391, "grad_norm": 1.6880074739456177, "learning_rate": 0.00019476444466237246, "loss": 0.6435818672180176, "step": 100030 }, { "epoch": 0.5946585349905784, "grad_norm": 1.9770147800445557, "learning_rate": 0.00019476235232962147, "loss": 0.6867554664611817, "step": 100040 }, { "epoch": 0.5947179770672468, "grad_norm": 1.309289813041687, "learning_rate": 0.00019476025959139513, "loss": 0.628948450088501, "step": 100050 }, { "epoch": 0.5947774191439152, "grad_norm": 1.6681573390960693, "learning_rate": 0.00019475816644770334, "loss": 0.6802222251892089, "step": 100060 }, { "epoch": 0.5948368612205837, "grad_norm": 1.8472009897232056, "learning_rate": 0.00019475607289855625, "loss": 0.7246089458465577, "step": 100070 }, { "epoch": 0.594896303297252, "grad_norm": 1.9252557754516602, "learning_rate": 0.0001947539789439638, "loss": 0.6626783847808838, "step": 100080 }, { "epoch": 0.5949557453739204, "grad_norm": 1.9332798719406128, "learning_rate": 0.00019475188458393597, "loss": 0.642132568359375, "step": 100090 }, { "epoch": 0.5950151874505888, "grad_norm": 1.9092217683792114, "learning_rate": 0.00019474978981848283, "loss": 0.6477486610412597, "step": 100100 }, { "epoch": 0.5950746295272572, "grad_norm": 1.394611120223999, "learning_rate": 0.0001947476946476144, "loss": 0.6120013236999512, "step": 100110 }, { "epoch": 0.5951340716039255, "grad_norm": 1.8819169998168945, "learning_rate": 0.0001947455990713407, "loss": 0.6916400909423828, "step": 100120 }, { "epoch": 0.5951935136805939, "grad_norm": 1.9207340478897095, "learning_rate": 0.00019474350308967174, "loss": 0.6701362133026123, "step": 100130 }, { "epoch": 0.5952529557572623, "grad_norm": 1.7396857738494873, "learning_rate": 0.0001947414067026176, "loss": 0.7562414169311523, "step": 100140 }, { "epoch": 0.5953123978339308, "grad_norm": 1.5443580150604248, "learning_rate": 0.0001947393099101882, "loss": 0.6949438571929931, "step": 100150 }, { "epoch": 0.5953718399105992, "grad_norm": 1.3715373277664185, "learning_rate": 0.00019473721271239368, "loss": 0.6624414443969726, "step": 100160 }, { "epoch": 0.5954312819872675, "grad_norm": 1.6884829998016357, "learning_rate": 0.000194735115109244, "loss": 0.6640047073364258, "step": 100170 }, { "epoch": 0.5954907240639359, "grad_norm": 1.2308111190795898, "learning_rate": 0.00019473301710074922, "loss": 0.7283053398132324, "step": 100180 }, { "epoch": 0.5955501661406043, "grad_norm": 1.7064151763916016, "learning_rate": 0.0001947309186869194, "loss": 0.7024457454681396, "step": 100190 }, { "epoch": 0.5956096082172727, "grad_norm": 2.0834269523620605, "learning_rate": 0.00019472881986776455, "loss": 0.6772363185882568, "step": 100200 }, { "epoch": 0.595669050293941, "grad_norm": 1.7767986059188843, "learning_rate": 0.0001947267206432947, "loss": 0.6549530029296875, "step": 100210 }, { "epoch": 0.5957284923706094, "grad_norm": 1.9116709232330322, "learning_rate": 0.00019472462101351992, "loss": 0.6610222339630127, "step": 100220 }, { "epoch": 0.5957879344472778, "grad_norm": 1.9023375511169434, "learning_rate": 0.00019472252097845022, "loss": 0.6964191436767578, "step": 100230 }, { "epoch": 0.5958473765239463, "grad_norm": 1.3380911350250244, "learning_rate": 0.0001947204205380957, "loss": 0.6846241474151611, "step": 100240 }, { "epoch": 0.5959068186006147, "grad_norm": 1.6777334213256836, "learning_rate": 0.00019471831969246638, "loss": 0.6726866722106933, "step": 100250 }, { "epoch": 0.595966260677283, "grad_norm": 2.0374507904052734, "learning_rate": 0.00019471621844157226, "loss": 0.6768601894378662, "step": 100260 }, { "epoch": 0.5960257027539514, "grad_norm": 1.5593470335006714, "learning_rate": 0.00019471411678542345, "loss": 0.6461262702941895, "step": 100270 }, { "epoch": 0.5960851448306198, "grad_norm": 1.6016919612884521, "learning_rate": 0.00019471201472403003, "loss": 0.6945918083190918, "step": 100280 }, { "epoch": 0.5961445869072882, "grad_norm": 1.6716498136520386, "learning_rate": 0.000194709912257402, "loss": 0.7113243103027344, "step": 100290 }, { "epoch": 0.5962040289839566, "grad_norm": 1.9609371423721313, "learning_rate": 0.00019470780938554938, "loss": 0.6414488792419434, "step": 100300 }, { "epoch": 0.5962634710606249, "grad_norm": 1.6480231285095215, "learning_rate": 0.00019470570610848233, "loss": 0.7122739315032959, "step": 100310 }, { "epoch": 0.5963229131372934, "grad_norm": 1.5322306156158447, "learning_rate": 0.00019470360242621087, "loss": 0.6530018806457519, "step": 100320 }, { "epoch": 0.5963823552139618, "grad_norm": 2.096721887588501, "learning_rate": 0.00019470149833874503, "loss": 0.6477377891540528, "step": 100330 }, { "epoch": 0.5964417972906302, "grad_norm": 1.8915024995803833, "learning_rate": 0.0001946993938460949, "loss": 0.6385107040405273, "step": 100340 }, { "epoch": 0.5965012393672985, "grad_norm": 1.541550636291504, "learning_rate": 0.0001946972889482706, "loss": 0.7171515464782715, "step": 100350 }, { "epoch": 0.5965606814439669, "grad_norm": 1.7016056776046753, "learning_rate": 0.0001946951836452821, "loss": 0.6632606983184814, "step": 100360 }, { "epoch": 0.5966201235206353, "grad_norm": 1.4716265201568604, "learning_rate": 0.00019469307793713953, "loss": 0.6600443840026855, "step": 100370 }, { "epoch": 0.5966795655973037, "grad_norm": 1.8299219608306885, "learning_rate": 0.00019469097182385297, "loss": 0.696065616607666, "step": 100380 }, { "epoch": 0.5967390076739721, "grad_norm": 1.5423939228057861, "learning_rate": 0.00019468886530543244, "loss": 0.6773359775543213, "step": 100390 }, { "epoch": 0.5967984497506404, "grad_norm": 2.099893569946289, "learning_rate": 0.0001946867583818881, "loss": 0.6536413192749023, "step": 100400 }, { "epoch": 0.5968578918273089, "grad_norm": 1.9085512161254883, "learning_rate": 0.00019468465105322997, "loss": 0.658253526687622, "step": 100410 }, { "epoch": 0.5969173339039773, "grad_norm": 1.5052695274353027, "learning_rate": 0.00019468254331946814, "loss": 0.7313693046569825, "step": 100420 }, { "epoch": 0.5969767759806457, "grad_norm": 1.5726100206375122, "learning_rate": 0.0001946804351806127, "loss": 0.6386507987976074, "step": 100430 }, { "epoch": 0.5970362180573141, "grad_norm": 2.157866954803467, "learning_rate": 0.0001946783266366737, "loss": 0.6642780303955078, "step": 100440 }, { "epoch": 0.5970956601339824, "grad_norm": 1.9423010349273682, "learning_rate": 0.00019467621768766132, "loss": 0.6880233287811279, "step": 100450 }, { "epoch": 0.5971551022106508, "grad_norm": 1.4974106550216675, "learning_rate": 0.00019467410833358555, "loss": 0.6450779914855957, "step": 100460 }, { "epoch": 0.5972145442873192, "grad_norm": 2.326599359512329, "learning_rate": 0.00019467199857445652, "loss": 0.6668072700500488, "step": 100470 }, { "epoch": 0.5972739863639877, "grad_norm": 1.3886345624923706, "learning_rate": 0.00019466988841028432, "loss": 0.7116371631622315, "step": 100480 }, { "epoch": 0.597333428440656, "grad_norm": 2.093355894088745, "learning_rate": 0.00019466777784107905, "loss": 0.6001069068908691, "step": 100490 }, { "epoch": 0.5973928705173244, "grad_norm": 1.7135592699050903, "learning_rate": 0.0001946656668668508, "loss": 0.6092577934265136, "step": 100500 }, { "epoch": 0.5974523125939928, "grad_norm": 1.7672044038772583, "learning_rate": 0.00019466355548760966, "loss": 0.6509260177612305, "step": 100510 }, { "epoch": 0.5975117546706612, "grad_norm": 1.7829960584640503, "learning_rate": 0.00019466144370336574, "loss": 0.6559099674224853, "step": 100520 }, { "epoch": 0.5975711967473296, "grad_norm": 1.8096193075180054, "learning_rate": 0.00019465933151412916, "loss": 0.6548470497131348, "step": 100530 }, { "epoch": 0.5976306388239979, "grad_norm": 1.5194671154022217, "learning_rate": 0.00019465721891990997, "loss": 0.6879871368408204, "step": 100540 }, { "epoch": 0.5976900809006663, "grad_norm": 1.642259955406189, "learning_rate": 0.00019465510592071836, "loss": 0.648453664779663, "step": 100550 }, { "epoch": 0.5977495229773347, "grad_norm": 1.7752197980880737, "learning_rate": 0.00019465299251656437, "loss": 0.6913914680480957, "step": 100560 }, { "epoch": 0.5978089650540032, "grad_norm": 1.9936919212341309, "learning_rate": 0.0001946508787074581, "loss": 0.6970301628112793, "step": 100570 }, { "epoch": 0.5978684071306715, "grad_norm": 1.683854579925537, "learning_rate": 0.00019464876449340972, "loss": 0.6704707622528077, "step": 100580 }, { "epoch": 0.5979278492073399, "grad_norm": 1.582364797592163, "learning_rate": 0.0001946466498744293, "loss": 0.708343505859375, "step": 100590 }, { "epoch": 0.5979872912840083, "grad_norm": 1.5791321992874146, "learning_rate": 0.000194644534850527, "loss": 0.7219152450561523, "step": 100600 }, { "epoch": 0.5980467333606767, "grad_norm": 2.055795192718506, "learning_rate": 0.00019464241942171285, "loss": 0.6981119155883789, "step": 100610 }, { "epoch": 0.5981061754373451, "grad_norm": 1.7257028818130493, "learning_rate": 0.00019464030358799707, "loss": 0.629120922088623, "step": 100620 }, { "epoch": 0.5981656175140134, "grad_norm": 1.5050727128982544, "learning_rate": 0.00019463818734938973, "loss": 0.6091893672943115, "step": 100630 }, { "epoch": 0.5982250595906818, "grad_norm": 1.9070417881011963, "learning_rate": 0.00019463607070590094, "loss": 0.7942656993865966, "step": 100640 }, { "epoch": 0.5982845016673503, "grad_norm": 2.0216476917266846, "learning_rate": 0.00019463395365754087, "loss": 0.7741503715515137, "step": 100650 }, { "epoch": 0.5983439437440187, "grad_norm": 1.7215334177017212, "learning_rate": 0.00019463183620431964, "loss": 0.7063214302062988, "step": 100660 }, { "epoch": 0.5984033858206871, "grad_norm": 2.132427453994751, "learning_rate": 0.00019462971834624732, "loss": 0.641254997253418, "step": 100670 }, { "epoch": 0.5984628278973554, "grad_norm": 1.6411082744598389, "learning_rate": 0.0001946276000833341, "loss": 0.7301815032958985, "step": 100680 }, { "epoch": 0.5985222699740238, "grad_norm": 1.3891444206237793, "learning_rate": 0.00019462548141559012, "loss": 0.614982271194458, "step": 100690 }, { "epoch": 0.5985817120506922, "grad_norm": 2.077298641204834, "learning_rate": 0.0001946233623430255, "loss": 0.6559043884277344, "step": 100700 }, { "epoch": 0.5986411541273606, "grad_norm": 1.7297471761703491, "learning_rate": 0.00019462124286565033, "loss": 0.6662969589233398, "step": 100710 }, { "epoch": 0.5987005962040289, "grad_norm": 2.041027069091797, "learning_rate": 0.00019461912298347482, "loss": 0.6834395408630372, "step": 100720 }, { "epoch": 0.5987600382806973, "grad_norm": 1.638553261756897, "learning_rate": 0.00019461700269650904, "loss": 0.6949690341949463, "step": 100730 }, { "epoch": 0.5988194803573658, "grad_norm": 1.5511363744735718, "learning_rate": 0.00019461488200476322, "loss": 0.7115326881408691, "step": 100740 }, { "epoch": 0.5988789224340342, "grad_norm": 1.5802490711212158, "learning_rate": 0.00019461276090824745, "loss": 0.635659122467041, "step": 100750 }, { "epoch": 0.5989383645107026, "grad_norm": 1.6946958303451538, "learning_rate": 0.00019461063940697185, "loss": 0.6822360038757325, "step": 100760 }, { "epoch": 0.5989978065873709, "grad_norm": 1.6394113302230835, "learning_rate": 0.00019460851750094664, "loss": 0.699614143371582, "step": 100770 }, { "epoch": 0.5990572486640393, "grad_norm": 1.4696593284606934, "learning_rate": 0.0001946063951901819, "loss": 0.6672803878784179, "step": 100780 }, { "epoch": 0.5991166907407077, "grad_norm": 1.548410177230835, "learning_rate": 0.00019460427247468785, "loss": 0.6526429653167725, "step": 100790 }, { "epoch": 0.5991761328173761, "grad_norm": 1.7029529809951782, "learning_rate": 0.00019460214935447455, "loss": 0.5847447395324707, "step": 100800 }, { "epoch": 0.5992355748940446, "grad_norm": 1.8359075784683228, "learning_rate": 0.00019460002582955227, "loss": 0.5697835922241211, "step": 100810 }, { "epoch": 0.5992950169707129, "grad_norm": 1.5058043003082275, "learning_rate": 0.00019459790189993112, "loss": 0.7263880729675293, "step": 100820 }, { "epoch": 0.5993544590473813, "grad_norm": 1.4945924282073975, "learning_rate": 0.00019459577756562123, "loss": 0.693788480758667, "step": 100830 }, { "epoch": 0.5994139011240497, "grad_norm": 1.454696536064148, "learning_rate": 0.0001945936528266328, "loss": 0.6790706157684326, "step": 100840 }, { "epoch": 0.5994733432007181, "grad_norm": 1.6480681896209717, "learning_rate": 0.00019459152768297594, "loss": 0.6556618213653564, "step": 100850 }, { "epoch": 0.5995327852773864, "grad_norm": 1.4145774841308594, "learning_rate": 0.00019458940213466091, "loss": 0.6721781730651856, "step": 100860 }, { "epoch": 0.5995922273540548, "grad_norm": 1.9102301597595215, "learning_rate": 0.0001945872761816978, "loss": 0.6826380729675293, "step": 100870 }, { "epoch": 0.5996516694307232, "grad_norm": 1.8426976203918457, "learning_rate": 0.00019458514982409678, "loss": 0.7175744056701661, "step": 100880 }, { "epoch": 0.5997111115073916, "grad_norm": 1.7682180404663086, "learning_rate": 0.00019458302306186808, "loss": 0.7310857772827148, "step": 100890 }, { "epoch": 0.5997705535840601, "grad_norm": 1.654775619506836, "learning_rate": 0.00019458089589502185, "loss": 0.6864877700805664, "step": 100900 }, { "epoch": 0.5998299956607284, "grad_norm": 1.4402896165847778, "learning_rate": 0.00019457876832356823, "loss": 0.643072509765625, "step": 100910 }, { "epoch": 0.5998894377373968, "grad_norm": 1.73654305934906, "learning_rate": 0.0001945766403475174, "loss": 0.6459395408630371, "step": 100920 }, { "epoch": 0.5999488798140652, "grad_norm": 1.7370843887329102, "learning_rate": 0.0001945745119668796, "loss": 0.7111345767974854, "step": 100930 }, { "epoch": 0.6000083218907336, "grad_norm": 1.4078258275985718, "learning_rate": 0.00019457238318166498, "loss": 0.5737404823303223, "step": 100940 }, { "epoch": 0.6000677639674019, "grad_norm": 1.739062786102295, "learning_rate": 0.00019457025399188368, "loss": 0.6678894996643067, "step": 100950 }, { "epoch": 0.6001272060440703, "grad_norm": 1.707953691482544, "learning_rate": 0.00019456812439754597, "loss": 0.6689608573913575, "step": 100960 }, { "epoch": 0.6001866481207387, "grad_norm": 1.2459384202957153, "learning_rate": 0.00019456599439866197, "loss": 0.7094435214996337, "step": 100970 }, { "epoch": 0.6002460901974072, "grad_norm": 1.9733277559280396, "learning_rate": 0.00019456386399524186, "loss": 0.7321748256683349, "step": 100980 }, { "epoch": 0.6003055322740756, "grad_norm": 1.9154062271118164, "learning_rate": 0.00019456173318729592, "loss": 0.6248256683349609, "step": 100990 }, { "epoch": 0.6003649743507439, "grad_norm": 1.8111628293991089, "learning_rate": 0.00019455960197483423, "loss": 0.6409523010253906, "step": 101000 }, { "epoch": 0.6004244164274123, "grad_norm": 1.8173385858535767, "learning_rate": 0.00019455747035786706, "loss": 0.6377545356750488, "step": 101010 }, { "epoch": 0.6004838585040807, "grad_norm": 1.8633090257644653, "learning_rate": 0.0001945553383364046, "loss": 0.6422703742980957, "step": 101020 }, { "epoch": 0.6005433005807491, "grad_norm": 2.017571449279785, "learning_rate": 0.000194553205910457, "loss": 0.6859288692474366, "step": 101030 }, { "epoch": 0.6006027426574175, "grad_norm": 2.0676088333129883, "learning_rate": 0.0001945510730800345, "loss": 0.6597410678863526, "step": 101040 }, { "epoch": 0.6006621847340858, "grad_norm": 1.596875548362732, "learning_rate": 0.00019454893984514733, "loss": 0.6724870204925537, "step": 101050 }, { "epoch": 0.6007216268107543, "grad_norm": 1.731396198272705, "learning_rate": 0.00019454680620580565, "loss": 0.7050321102142334, "step": 101060 }, { "epoch": 0.6007810688874227, "grad_norm": 1.6087565422058105, "learning_rate": 0.00019454467216201967, "loss": 0.6723513603210449, "step": 101070 }, { "epoch": 0.6008405109640911, "grad_norm": 1.7861310243606567, "learning_rate": 0.0001945425377137996, "loss": 0.657773494720459, "step": 101080 }, { "epoch": 0.6008999530407594, "grad_norm": 1.8078681230545044, "learning_rate": 0.0001945404028611557, "loss": 0.7119979858398438, "step": 101090 }, { "epoch": 0.6009593951174278, "grad_norm": 1.668494462966919, "learning_rate": 0.00019453826760409807, "loss": 0.6466434478759766, "step": 101100 }, { "epoch": 0.6010188371940962, "grad_norm": 1.2346792221069336, "learning_rate": 0.00019453613194263706, "loss": 0.636415672302246, "step": 101110 }, { "epoch": 0.6010782792707646, "grad_norm": 1.706686019897461, "learning_rate": 0.00019453399587678277, "loss": 0.6481682300567627, "step": 101120 }, { "epoch": 0.601137721347433, "grad_norm": 1.8378826379776, "learning_rate": 0.00019453185940654553, "loss": 0.6508749008178711, "step": 101130 }, { "epoch": 0.6011971634241013, "grad_norm": 1.740841031074524, "learning_rate": 0.00019452972253193547, "loss": 0.6900650978088378, "step": 101140 }, { "epoch": 0.6012566055007698, "grad_norm": 1.8928312063217163, "learning_rate": 0.00019452758525296282, "loss": 0.6671252250671387, "step": 101150 }, { "epoch": 0.6013160475774382, "grad_norm": 1.5236157178878784, "learning_rate": 0.00019452544756963784, "loss": 0.7060568809509278, "step": 101160 }, { "epoch": 0.6013754896541066, "grad_norm": 1.616227626800537, "learning_rate": 0.00019452330948197075, "loss": 0.6511809825897217, "step": 101170 }, { "epoch": 0.6014349317307749, "grad_norm": 2.025104522705078, "learning_rate": 0.00019452117098997176, "loss": 0.686430835723877, "step": 101180 }, { "epoch": 0.6014943738074433, "grad_norm": 1.8794478178024292, "learning_rate": 0.00019451903209365113, "loss": 0.6401045799255372, "step": 101190 }, { "epoch": 0.6015538158841117, "grad_norm": 1.8355333805084229, "learning_rate": 0.00019451689279301906, "loss": 0.5997552871704102, "step": 101200 }, { "epoch": 0.6016132579607801, "grad_norm": 1.4037609100341797, "learning_rate": 0.00019451475308808578, "loss": 0.7560006141662597, "step": 101210 }, { "epoch": 0.6016727000374485, "grad_norm": 1.3827677965164185, "learning_rate": 0.00019451261297886155, "loss": 0.6866299629211425, "step": 101220 }, { "epoch": 0.6017321421141169, "grad_norm": 1.5825741291046143, "learning_rate": 0.0001945104724653566, "loss": 0.6433559894561768, "step": 101230 }, { "epoch": 0.6017915841907853, "grad_norm": 1.439325213432312, "learning_rate": 0.0001945083315475812, "loss": 0.6976960182189942, "step": 101240 }, { "epoch": 0.6018510262674537, "grad_norm": 1.7590440511703491, "learning_rate": 0.0001945061902255455, "loss": 0.6409010887145996, "step": 101250 }, { "epoch": 0.6019104683441221, "grad_norm": 1.6071263551712036, "learning_rate": 0.00019450404849925986, "loss": 0.6260971069335938, "step": 101260 }, { "epoch": 0.6019699104207905, "grad_norm": 1.7501802444458008, "learning_rate": 0.00019450190636873443, "loss": 0.7035919189453125, "step": 101270 }, { "epoch": 0.6020293524974588, "grad_norm": 2.0725460052490234, "learning_rate": 0.0001944997638339795, "loss": 0.6884239196777344, "step": 101280 }, { "epoch": 0.6020887945741272, "grad_norm": 1.645857810974121, "learning_rate": 0.00019449762089500532, "loss": 0.6738705635070801, "step": 101290 }, { "epoch": 0.6021482366507956, "grad_norm": 2.2860779762268066, "learning_rate": 0.00019449547755182213, "loss": 0.6613352775573731, "step": 101300 }, { "epoch": 0.6022076787274641, "grad_norm": 2.259124994277954, "learning_rate": 0.00019449333380444018, "loss": 0.7170463562011719, "step": 101310 }, { "epoch": 0.6022671208041324, "grad_norm": 2.0772757530212402, "learning_rate": 0.00019449118965286978, "loss": 0.7311609268188477, "step": 101320 }, { "epoch": 0.6023265628808008, "grad_norm": 1.608365774154663, "learning_rate": 0.0001944890450971211, "loss": 0.7008790969848633, "step": 101330 }, { "epoch": 0.6023860049574692, "grad_norm": 1.7391926050186157, "learning_rate": 0.00019448690013720445, "loss": 0.5984445571899414, "step": 101340 }, { "epoch": 0.6024454470341376, "grad_norm": 1.6572072505950928, "learning_rate": 0.0001944847547731301, "loss": 0.6412761688232422, "step": 101350 }, { "epoch": 0.602504889110806, "grad_norm": 1.8704071044921875, "learning_rate": 0.00019448260900490824, "loss": 0.7003423690795898, "step": 101360 }, { "epoch": 0.6025643311874743, "grad_norm": 1.9279402494430542, "learning_rate": 0.00019448046283254924, "loss": 0.7239895820617676, "step": 101370 }, { "epoch": 0.6026237732641427, "grad_norm": 1.4486619234085083, "learning_rate": 0.0001944783162560633, "loss": 0.6785524845123291, "step": 101380 }, { "epoch": 0.6026832153408112, "grad_norm": 1.171101689338684, "learning_rate": 0.00019447616927546069, "loss": 0.6860628604888916, "step": 101390 }, { "epoch": 0.6027426574174796, "grad_norm": 1.7003161907196045, "learning_rate": 0.0001944740218907517, "loss": 0.6273763179779053, "step": 101400 }, { "epoch": 0.602802099494148, "grad_norm": 1.6713030338287354, "learning_rate": 0.0001944718741019466, "loss": 0.6865915775299072, "step": 101410 }, { "epoch": 0.6028615415708163, "grad_norm": 1.6016920804977417, "learning_rate": 0.00019446972590905567, "loss": 0.673155689239502, "step": 101420 }, { "epoch": 0.6029209836474847, "grad_norm": 1.5392911434173584, "learning_rate": 0.00019446757731208915, "loss": 0.6834322452545166, "step": 101430 }, { "epoch": 0.6029804257241531, "grad_norm": 1.7441036701202393, "learning_rate": 0.00019446542831105736, "loss": 0.6958895206451416, "step": 101440 }, { "epoch": 0.6030398678008215, "grad_norm": 1.6992766857147217, "learning_rate": 0.00019446327890597056, "loss": 0.6745757579803466, "step": 101450 }, { "epoch": 0.6030993098774898, "grad_norm": 1.3957027196884155, "learning_rate": 0.00019446112909683903, "loss": 0.6728016853332519, "step": 101460 }, { "epoch": 0.6031587519541582, "grad_norm": 1.6117178201675415, "learning_rate": 0.0001944589788836731, "loss": 0.687682056427002, "step": 101470 }, { "epoch": 0.6032181940308267, "grad_norm": 1.5580942630767822, "learning_rate": 0.00019445682826648298, "loss": 0.6984413146972657, "step": 101480 }, { "epoch": 0.6032776361074951, "grad_norm": 1.8742835521697998, "learning_rate": 0.000194454677245279, "loss": 0.7024135589599609, "step": 101490 }, { "epoch": 0.6033370781841635, "grad_norm": 1.9458973407745361, "learning_rate": 0.00019445252582007142, "loss": 0.7088989734649658, "step": 101500 }, { "epoch": 0.6033965202608318, "grad_norm": 1.7348830699920654, "learning_rate": 0.0001944503739908706, "loss": 0.6957737445831299, "step": 101510 }, { "epoch": 0.6034559623375002, "grad_norm": 1.8886773586273193, "learning_rate": 0.00019444822175768676, "loss": 0.6867017269134521, "step": 101520 }, { "epoch": 0.6035154044141686, "grad_norm": 1.7682934999465942, "learning_rate": 0.00019444606912053024, "loss": 0.6967550277709961, "step": 101530 }, { "epoch": 0.603574846490837, "grad_norm": 1.2459338903427124, "learning_rate": 0.00019444391607941134, "loss": 0.6546989440917969, "step": 101540 }, { "epoch": 0.6036342885675053, "grad_norm": 1.4798402786254883, "learning_rate": 0.0001944417626343403, "loss": 0.6617785453796386, "step": 101550 }, { "epoch": 0.6036937306441738, "grad_norm": 1.8857357501983643, "learning_rate": 0.0001944396087853275, "loss": 0.6596954345703125, "step": 101560 }, { "epoch": 0.6037531727208422, "grad_norm": 1.8930751085281372, "learning_rate": 0.0001944374545323832, "loss": 0.6689258098602295, "step": 101570 }, { "epoch": 0.6038126147975106, "grad_norm": 1.2839593887329102, "learning_rate": 0.00019443529987551766, "loss": 0.6470747947692871, "step": 101580 }, { "epoch": 0.603872056874179, "grad_norm": 1.5587999820709229, "learning_rate": 0.00019443314481474132, "loss": 0.6296658515930176, "step": 101590 }, { "epoch": 0.6039314989508473, "grad_norm": 1.5939841270446777, "learning_rate": 0.00019443098935006435, "loss": 0.6718234062194824, "step": 101600 }, { "epoch": 0.6039909410275157, "grad_norm": 1.3773484230041504, "learning_rate": 0.00019442883348149713, "loss": 0.691523551940918, "step": 101610 }, { "epoch": 0.6040503831041841, "grad_norm": 1.4736871719360352, "learning_rate": 0.00019442667720905, "loss": 0.703371238708496, "step": 101620 }, { "epoch": 0.6041098251808525, "grad_norm": 1.6810122728347778, "learning_rate": 0.0001944245205327332, "loss": 0.6974652290344239, "step": 101630 }, { "epoch": 0.604169267257521, "grad_norm": 1.6667371988296509, "learning_rate": 0.0001944223634525571, "loss": 0.6404811859130859, "step": 101640 }, { "epoch": 0.6042287093341893, "grad_norm": 1.7522529363632202, "learning_rate": 0.00019442020596853197, "loss": 0.6715954303741455, "step": 101650 }, { "epoch": 0.6042881514108577, "grad_norm": 2.095587730407715, "learning_rate": 0.00019441804808066816, "loss": 0.7215962409973145, "step": 101660 }, { "epoch": 0.6043475934875261, "grad_norm": 1.9899860620498657, "learning_rate": 0.00019441588978897603, "loss": 0.6726559638977051, "step": 101670 }, { "epoch": 0.6044070355641945, "grad_norm": 1.5222636461257935, "learning_rate": 0.0001944137310934659, "loss": 0.7032109260559082, "step": 101680 }, { "epoch": 0.6044664776408628, "grad_norm": 1.5493961572647095, "learning_rate": 0.000194411571994148, "loss": 0.6611645221710205, "step": 101690 }, { "epoch": 0.6045259197175312, "grad_norm": 1.3043854236602783, "learning_rate": 0.00019440941249103277, "loss": 0.6753592967987061, "step": 101700 }, { "epoch": 0.6045853617941996, "grad_norm": 1.5482230186462402, "learning_rate": 0.00019440725258413052, "loss": 0.6574090003967286, "step": 101710 }, { "epoch": 0.604644803870868, "grad_norm": 1.219245195388794, "learning_rate": 0.0001944050922734515, "loss": 0.6206886768341064, "step": 101720 }, { "epoch": 0.6047042459475365, "grad_norm": 1.8176639080047607, "learning_rate": 0.00019440293155900614, "loss": 0.6818964958190918, "step": 101730 }, { "epoch": 0.6047636880242048, "grad_norm": 2.0126841068267822, "learning_rate": 0.00019440077044080472, "loss": 0.7066591262817383, "step": 101740 }, { "epoch": 0.6048231301008732, "grad_norm": 1.5278297662734985, "learning_rate": 0.00019439860891885756, "loss": 0.6656582355499268, "step": 101750 }, { "epoch": 0.6048825721775416, "grad_norm": 1.5386847257614136, "learning_rate": 0.00019439644699317509, "loss": 0.616652536392212, "step": 101760 }, { "epoch": 0.60494201425421, "grad_norm": 1.4332877397537231, "learning_rate": 0.00019439428466376762, "loss": 0.6466577053070068, "step": 101770 }, { "epoch": 0.6050014563308784, "grad_norm": 1.5643019676208496, "learning_rate": 0.00019439212193064542, "loss": 0.6890496253967285, "step": 101780 }, { "epoch": 0.6050608984075467, "grad_norm": 2.181475877761841, "learning_rate": 0.0001943899587938189, "loss": 0.6868703842163086, "step": 101790 }, { "epoch": 0.6051203404842151, "grad_norm": 1.6715551614761353, "learning_rate": 0.00019438779525329843, "loss": 0.664098072052002, "step": 101800 }, { "epoch": 0.6051797825608836, "grad_norm": 1.6808357238769531, "learning_rate": 0.0001943856313090943, "loss": 0.6410867691040039, "step": 101810 }, { "epoch": 0.605239224637552, "grad_norm": 1.9482699632644653, "learning_rate": 0.00019438346696121689, "loss": 0.6269071578979493, "step": 101820 }, { "epoch": 0.6052986667142203, "grad_norm": 2.155820846557617, "learning_rate": 0.00019438130220967654, "loss": 0.6813802719116211, "step": 101830 }, { "epoch": 0.6053581087908887, "grad_norm": 2.0617432594299316, "learning_rate": 0.0001943791370544836, "loss": 0.7140084266662597, "step": 101840 }, { "epoch": 0.6054175508675571, "grad_norm": 2.046313762664795, "learning_rate": 0.00019437697149564845, "loss": 0.6905892372131348, "step": 101850 }, { "epoch": 0.6054769929442255, "grad_norm": 1.562285304069519, "learning_rate": 0.00019437480553318148, "loss": 0.6999406337738037, "step": 101860 }, { "epoch": 0.6055364350208939, "grad_norm": 1.3758679628372192, "learning_rate": 0.000194372639167093, "loss": 0.6493579864501953, "step": 101870 }, { "epoch": 0.6055958770975622, "grad_norm": 1.7519233226776123, "learning_rate": 0.0001943704723973934, "loss": 0.6326154708862305, "step": 101880 }, { "epoch": 0.6056553191742307, "grad_norm": 1.509888768196106, "learning_rate": 0.00019436830522409298, "loss": 0.6801795959472656, "step": 101890 }, { "epoch": 0.6057147612508991, "grad_norm": 1.791915774345398, "learning_rate": 0.0001943661376472022, "loss": 0.6519231796264648, "step": 101900 }, { "epoch": 0.6057742033275675, "grad_norm": 1.5910005569458008, "learning_rate": 0.00019436396966673137, "loss": 0.6633670330047607, "step": 101910 }, { "epoch": 0.6058336454042358, "grad_norm": 1.8872915506362915, "learning_rate": 0.00019436180128269093, "loss": 0.6514406204223633, "step": 101920 }, { "epoch": 0.6058930874809042, "grad_norm": 1.8965898752212524, "learning_rate": 0.00019435963249509112, "loss": 0.7043120384216308, "step": 101930 }, { "epoch": 0.6059525295575726, "grad_norm": 1.7094241380691528, "learning_rate": 0.00019435746330394247, "loss": 0.7605152130126953, "step": 101940 }, { "epoch": 0.606011971634241, "grad_norm": 1.8674591779708862, "learning_rate": 0.00019435529370925522, "loss": 0.6369863510131836, "step": 101950 }, { "epoch": 0.6060714137109094, "grad_norm": 1.6153271198272705, "learning_rate": 0.0001943531237110399, "loss": 0.6466226577758789, "step": 101960 }, { "epoch": 0.6061308557875777, "grad_norm": 1.9089994430541992, "learning_rate": 0.00019435095330930672, "loss": 0.7234626770019531, "step": 101970 }, { "epoch": 0.6061902978642462, "grad_norm": 1.3327890634536743, "learning_rate": 0.00019434878250406619, "loss": 0.6844295501708985, "step": 101980 }, { "epoch": 0.6062497399409146, "grad_norm": 1.4392597675323486, "learning_rate": 0.00019434661129532862, "loss": 0.6038957595825195, "step": 101990 }, { "epoch": 0.606309182017583, "grad_norm": 1.56482994556427, "learning_rate": 0.00019434443968310445, "loss": 0.5984673976898194, "step": 102000 }, { "epoch": 0.6063686240942514, "grad_norm": 1.924891471862793, "learning_rate": 0.00019434226766740405, "loss": 0.6618853569030761, "step": 102010 }, { "epoch": 0.6064280661709197, "grad_norm": 1.263291597366333, "learning_rate": 0.00019434009524823778, "loss": 0.6502595901489258, "step": 102020 }, { "epoch": 0.6064875082475881, "grad_norm": 1.7617921829223633, "learning_rate": 0.00019433792242561605, "loss": 0.6503456115722657, "step": 102030 }, { "epoch": 0.6065469503242565, "grad_norm": 1.875229001045227, "learning_rate": 0.0001943357491995493, "loss": 0.720823097229004, "step": 102040 }, { "epoch": 0.606606392400925, "grad_norm": 1.8092048168182373, "learning_rate": 0.00019433357557004788, "loss": 0.6914525985717773, "step": 102050 }, { "epoch": 0.6066658344775933, "grad_norm": 2.039278507232666, "learning_rate": 0.00019433140153712214, "loss": 0.6582732200622559, "step": 102060 }, { "epoch": 0.6067252765542617, "grad_norm": 2.0391736030578613, "learning_rate": 0.0001943292271007826, "loss": 0.6832390308380127, "step": 102070 }, { "epoch": 0.6067847186309301, "grad_norm": 1.8768062591552734, "learning_rate": 0.0001943270522610396, "loss": 0.7231311798095703, "step": 102080 }, { "epoch": 0.6068441607075985, "grad_norm": 1.6569691896438599, "learning_rate": 0.00019432487701790348, "loss": 0.6763234615325928, "step": 102090 }, { "epoch": 0.6069036027842669, "grad_norm": 1.6032179594039917, "learning_rate": 0.00019432270137138474, "loss": 0.6531599521636963, "step": 102100 }, { "epoch": 0.6069630448609352, "grad_norm": 1.8220471143722534, "learning_rate": 0.00019432052532149377, "loss": 0.6416072845458984, "step": 102110 }, { "epoch": 0.6070224869376036, "grad_norm": 1.7470828294754028, "learning_rate": 0.00019431834886824093, "loss": 0.6455934524536133, "step": 102120 }, { "epoch": 0.607081929014272, "grad_norm": 1.602399230003357, "learning_rate": 0.0001943161720116367, "loss": 0.6175640106201172, "step": 102130 }, { "epoch": 0.6071413710909405, "grad_norm": 1.8131814002990723, "learning_rate": 0.00019431399475169144, "loss": 0.6093744277954102, "step": 102140 }, { "epoch": 0.6072008131676089, "grad_norm": 1.5358545780181885, "learning_rate": 0.00019431181708841558, "loss": 0.6909782409667968, "step": 102150 }, { "epoch": 0.6072602552442772, "grad_norm": 1.479076862335205, "learning_rate": 0.00019430963902181955, "loss": 0.6082093238830566, "step": 102160 }, { "epoch": 0.6073196973209456, "grad_norm": 1.5750041007995605, "learning_rate": 0.00019430746055191373, "loss": 0.6256546020507813, "step": 102170 }, { "epoch": 0.607379139397614, "grad_norm": 2.050379753112793, "learning_rate": 0.0001943052816787086, "loss": 0.6811481952667237, "step": 102180 }, { "epoch": 0.6074385814742824, "grad_norm": 1.4419655799865723, "learning_rate": 0.00019430310240221456, "loss": 0.6556999206542968, "step": 102190 }, { "epoch": 0.6074980235509507, "grad_norm": 1.7662450075149536, "learning_rate": 0.000194300922722442, "loss": 0.6866066932678223, "step": 102200 }, { "epoch": 0.6075574656276191, "grad_norm": 1.4653539657592773, "learning_rate": 0.0001942987426394014, "loss": 0.6502422332763672, "step": 102210 }, { "epoch": 0.6076169077042876, "grad_norm": 1.5793404579162598, "learning_rate": 0.00019429656215310317, "loss": 0.5658595085144043, "step": 102220 }, { "epoch": 0.607676349780956, "grad_norm": 1.1881009340286255, "learning_rate": 0.00019429438126355772, "loss": 0.6645498275756836, "step": 102230 }, { "epoch": 0.6077357918576244, "grad_norm": 1.6324249505996704, "learning_rate": 0.00019429219997077547, "loss": 0.6639753341674804, "step": 102240 }, { "epoch": 0.6077952339342927, "grad_norm": 1.4483343362808228, "learning_rate": 0.00019429001827476694, "loss": 0.6807090759277343, "step": 102250 }, { "epoch": 0.6078546760109611, "grad_norm": 1.882965326309204, "learning_rate": 0.00019428783617554248, "loss": 0.6827382564544677, "step": 102260 }, { "epoch": 0.6079141180876295, "grad_norm": 1.5954914093017578, "learning_rate": 0.00019428565367311253, "loss": 0.6303665161132812, "step": 102270 }, { "epoch": 0.6079735601642979, "grad_norm": 1.7430744171142578, "learning_rate": 0.0001942834707674876, "loss": 0.7306617736816406, "step": 102280 }, { "epoch": 0.6080330022409662, "grad_norm": 2.3133652210235596, "learning_rate": 0.00019428128745867807, "loss": 0.6975587368011474, "step": 102290 }, { "epoch": 0.6080924443176347, "grad_norm": 1.6814631223678589, "learning_rate": 0.00019427910374669442, "loss": 0.7245254993438721, "step": 102300 }, { "epoch": 0.6081518863943031, "grad_norm": 1.4854012727737427, "learning_rate": 0.00019427691963154708, "loss": 0.6944958686828613, "step": 102310 }, { "epoch": 0.6082113284709715, "grad_norm": 1.502550482749939, "learning_rate": 0.00019427473511324646, "loss": 0.6386589050292969, "step": 102320 }, { "epoch": 0.6082707705476399, "grad_norm": 1.777075171470642, "learning_rate": 0.00019427255019180309, "loss": 0.6576281547546386, "step": 102330 }, { "epoch": 0.6083302126243082, "grad_norm": 2.16757869720459, "learning_rate": 0.00019427036486722736, "loss": 0.7568188190460206, "step": 102340 }, { "epoch": 0.6083896547009766, "grad_norm": 1.8472490310668945, "learning_rate": 0.00019426817913952975, "loss": 0.6705203533172608, "step": 102350 }, { "epoch": 0.608449096777645, "grad_norm": 1.9589122533798218, "learning_rate": 0.0001942659930087207, "loss": 0.6895739555358886, "step": 102360 }, { "epoch": 0.6085085388543134, "grad_norm": 1.4017237424850464, "learning_rate": 0.0001942638064748107, "loss": 0.611853837966919, "step": 102370 }, { "epoch": 0.6085679809309819, "grad_norm": 1.4947179555892944, "learning_rate": 0.0001942616195378102, "loss": 0.6610465049743652, "step": 102380 }, { "epoch": 0.6086274230076502, "grad_norm": 1.8989179134368896, "learning_rate": 0.00019425943219772963, "loss": 0.7186701774597168, "step": 102390 }, { "epoch": 0.6086868650843186, "grad_norm": 1.518650770187378, "learning_rate": 0.00019425724445457944, "loss": 0.6669282913208008, "step": 102400 }, { "epoch": 0.608746307160987, "grad_norm": 1.7074288129806519, "learning_rate": 0.00019425505630837016, "loss": 0.6761101722717285, "step": 102410 }, { "epoch": 0.6088057492376554, "grad_norm": 1.5565626621246338, "learning_rate": 0.00019425286775911222, "loss": 0.7167901992797852, "step": 102420 }, { "epoch": 0.6088651913143237, "grad_norm": 1.5746428966522217, "learning_rate": 0.0001942506788068161, "loss": 0.634314489364624, "step": 102430 }, { "epoch": 0.6089246333909921, "grad_norm": 1.6213003396987915, "learning_rate": 0.00019424848945149228, "loss": 0.6943136215209961, "step": 102440 }, { "epoch": 0.6089840754676605, "grad_norm": 1.8178303241729736, "learning_rate": 0.00019424629969315118, "loss": 0.6573536396026611, "step": 102450 }, { "epoch": 0.609043517544329, "grad_norm": 1.9360445737838745, "learning_rate": 0.00019424410953180335, "loss": 0.7051377773284913, "step": 102460 }, { "epoch": 0.6091029596209974, "grad_norm": 1.8311611413955688, "learning_rate": 0.00019424191896745923, "loss": 0.6214897155761718, "step": 102470 }, { "epoch": 0.6091624016976657, "grad_norm": 1.7103673219680786, "learning_rate": 0.00019423972800012925, "loss": 0.7136432647705078, "step": 102480 }, { "epoch": 0.6092218437743341, "grad_norm": 1.886343002319336, "learning_rate": 0.000194237536629824, "loss": 0.6464698791503907, "step": 102490 }, { "epoch": 0.6092812858510025, "grad_norm": 1.8498520851135254, "learning_rate": 0.0001942353448565539, "loss": 0.7340453624725342, "step": 102500 }, { "epoch": 0.6093407279276709, "grad_norm": 1.6337538957595825, "learning_rate": 0.0001942331526803294, "loss": 0.7240291118621827, "step": 102510 }, { "epoch": 0.6094001700043393, "grad_norm": 1.999639868736267, "learning_rate": 0.00019423096010116105, "loss": 0.6910937309265137, "step": 102520 }, { "epoch": 0.6094596120810076, "grad_norm": 5.131251335144043, "learning_rate": 0.00019422876711905934, "loss": 0.7377682685852051, "step": 102530 }, { "epoch": 0.609519054157676, "grad_norm": 1.9392813444137573, "learning_rate": 0.00019422657373403468, "loss": 0.674675178527832, "step": 102540 }, { "epoch": 0.6095784962343445, "grad_norm": 1.8195631504058838, "learning_rate": 0.00019422437994609764, "loss": 0.6549026489257812, "step": 102550 }, { "epoch": 0.6096379383110129, "grad_norm": 1.6931694746017456, "learning_rate": 0.0001942221857552587, "loss": 0.6704607009887695, "step": 102560 }, { "epoch": 0.6096973803876812, "grad_norm": 1.7678859233856201, "learning_rate": 0.00019421999116152832, "loss": 0.6049301624298096, "step": 102570 }, { "epoch": 0.6097568224643496, "grad_norm": 1.5921931266784668, "learning_rate": 0.00019421779616491704, "loss": 0.6922182559967041, "step": 102580 }, { "epoch": 0.609816264541018, "grad_norm": 1.744340181350708, "learning_rate": 0.00019421560076543536, "loss": 0.6955024719238281, "step": 102590 }, { "epoch": 0.6098757066176864, "grad_norm": 1.9264506101608276, "learning_rate": 0.00019421340496309376, "loss": 0.714939022064209, "step": 102600 }, { "epoch": 0.6099351486943548, "grad_norm": 2.055039644241333, "learning_rate": 0.00019421120875790274, "loss": 0.735409164428711, "step": 102610 }, { "epoch": 0.6099945907710231, "grad_norm": 1.420805811882019, "learning_rate": 0.00019420901214987283, "loss": 0.6859645843505859, "step": 102620 }, { "epoch": 0.6100540328476916, "grad_norm": 1.291154384613037, "learning_rate": 0.00019420681513901455, "loss": 0.6888717651367188, "step": 102630 }, { "epoch": 0.61011347492436, "grad_norm": 1.7885316610336304, "learning_rate": 0.00019420461772533837, "loss": 0.6716895580291748, "step": 102640 }, { "epoch": 0.6101729170010284, "grad_norm": 1.5254331827163696, "learning_rate": 0.0001942024199088548, "loss": 0.7094046115875244, "step": 102650 }, { "epoch": 0.6102323590776967, "grad_norm": 1.7737877368927002, "learning_rate": 0.00019420022168957436, "loss": 0.5674838066101074, "step": 102660 }, { "epoch": 0.6102918011543651, "grad_norm": 1.5145459175109863, "learning_rate": 0.0001941980230675076, "loss": 0.6245772361755371, "step": 102670 }, { "epoch": 0.6103512432310335, "grad_norm": 1.7283480167388916, "learning_rate": 0.000194195824042665, "loss": 0.6761536598205566, "step": 102680 }, { "epoch": 0.6104106853077019, "grad_norm": 1.6114481687545776, "learning_rate": 0.0001941936246150571, "loss": 0.6231327056884766, "step": 102690 }, { "epoch": 0.6104701273843703, "grad_norm": 1.895174503326416, "learning_rate": 0.00019419142478469442, "loss": 0.6713827133178711, "step": 102700 }, { "epoch": 0.6105295694610386, "grad_norm": 1.7284610271453857, "learning_rate": 0.00019418922455158747, "loss": 0.6806820869445801, "step": 102710 }, { "epoch": 0.6105890115377071, "grad_norm": 1.3866591453552246, "learning_rate": 0.00019418702391574679, "loss": 0.6612561225891114, "step": 102720 }, { "epoch": 0.6106484536143755, "grad_norm": 1.749277114868164, "learning_rate": 0.00019418482287718292, "loss": 0.7204480171203613, "step": 102730 }, { "epoch": 0.6107078956910439, "grad_norm": 1.5611238479614258, "learning_rate": 0.00019418262143590633, "loss": 0.634091854095459, "step": 102740 }, { "epoch": 0.6107673377677123, "grad_norm": 1.9608571529388428, "learning_rate": 0.0001941804195919276, "loss": 0.6409647941589356, "step": 102750 }, { "epoch": 0.6108267798443806, "grad_norm": 1.6003470420837402, "learning_rate": 0.00019417821734525728, "loss": 0.7051401615142823, "step": 102760 }, { "epoch": 0.610886221921049, "grad_norm": 1.3439642190933228, "learning_rate": 0.00019417601469590585, "loss": 0.5983120918273925, "step": 102770 }, { "epoch": 0.6109456639977174, "grad_norm": 1.6593356132507324, "learning_rate": 0.0001941738116438839, "loss": 0.6490932464599609, "step": 102780 }, { "epoch": 0.6110051060743859, "grad_norm": 1.670589566230774, "learning_rate": 0.00019417160818920192, "loss": 0.6746403217315674, "step": 102790 }, { "epoch": 0.6110645481510542, "grad_norm": 1.9392908811569214, "learning_rate": 0.00019416940433187048, "loss": 0.7253918647766113, "step": 102800 }, { "epoch": 0.6111239902277226, "grad_norm": 1.4853465557098389, "learning_rate": 0.0001941672000719001, "loss": 0.6668481826782227, "step": 102810 }, { "epoch": 0.611183432304391, "grad_norm": 1.5508118867874146, "learning_rate": 0.00019416499540930138, "loss": 0.6672592163085938, "step": 102820 }, { "epoch": 0.6112428743810594, "grad_norm": 1.5706104040145874, "learning_rate": 0.0001941627903440848, "loss": 0.63363676071167, "step": 102830 }, { "epoch": 0.6113023164577278, "grad_norm": 1.7040224075317383, "learning_rate": 0.00019416058487626095, "loss": 0.7011376857757569, "step": 102840 }, { "epoch": 0.6113617585343961, "grad_norm": 2.267596483230591, "learning_rate": 0.00019415837900584032, "loss": 0.6559289932250977, "step": 102850 }, { "epoch": 0.6114212006110645, "grad_norm": 1.8984702825546265, "learning_rate": 0.0001941561727328336, "loss": 0.6799164772033691, "step": 102860 }, { "epoch": 0.611480642687733, "grad_norm": 1.886615514755249, "learning_rate": 0.00019415396605725115, "loss": 0.6610867023468018, "step": 102870 }, { "epoch": 0.6115400847644014, "grad_norm": 1.6136231422424316, "learning_rate": 0.0001941517589791037, "loss": 0.6971160411834717, "step": 102880 }, { "epoch": 0.6115995268410698, "grad_norm": 1.5779547691345215, "learning_rate": 0.0001941495514984017, "loss": 0.705491018295288, "step": 102890 }, { "epoch": 0.6116589689177381, "grad_norm": 1.8493432998657227, "learning_rate": 0.00019414734361515576, "loss": 0.7207003593444824, "step": 102900 }, { "epoch": 0.6117184109944065, "grad_norm": 1.6775275468826294, "learning_rate": 0.00019414513532937643, "loss": 0.6568286895751954, "step": 102910 }, { "epoch": 0.6117778530710749, "grad_norm": 1.7824938297271729, "learning_rate": 0.00019414292664107427, "loss": 0.6576982498168945, "step": 102920 }, { "epoch": 0.6118372951477433, "grad_norm": 1.370121717453003, "learning_rate": 0.00019414071755025983, "loss": 0.6833469867706299, "step": 102930 }, { "epoch": 0.6118967372244116, "grad_norm": 1.820989966392517, "learning_rate": 0.00019413850805694374, "loss": 0.6579557895660401, "step": 102940 }, { "epoch": 0.61195617930108, "grad_norm": 1.7046476602554321, "learning_rate": 0.00019413629816113646, "loss": 0.6694142341613769, "step": 102950 }, { "epoch": 0.6120156213777485, "grad_norm": 1.9152414798736572, "learning_rate": 0.00019413408786284866, "loss": 0.7001874923706055, "step": 102960 }, { "epoch": 0.6120750634544169, "grad_norm": 1.8024483919143677, "learning_rate": 0.0001941318771620909, "loss": 0.7110482215881347, "step": 102970 }, { "epoch": 0.6121345055310853, "grad_norm": 1.52005136013031, "learning_rate": 0.0001941296660588737, "loss": 0.6965700149536133, "step": 102980 }, { "epoch": 0.6121939476077536, "grad_norm": 1.7532232999801636, "learning_rate": 0.00019412745455320768, "loss": 0.7307289123535157, "step": 102990 }, { "epoch": 0.612253389684422, "grad_norm": 2.128383159637451, "learning_rate": 0.0001941252426451034, "loss": 0.6602099895477295, "step": 103000 }, { "epoch": 0.6123128317610904, "grad_norm": 1.8545118570327759, "learning_rate": 0.00019412303033457148, "loss": 0.7014176368713378, "step": 103010 }, { "epoch": 0.6123722738377588, "grad_norm": 1.6545240879058838, "learning_rate": 0.00019412081762162247, "loss": 0.6770118713378906, "step": 103020 }, { "epoch": 0.6124317159144271, "grad_norm": 1.5705254077911377, "learning_rate": 0.00019411860450626694, "loss": 0.666812515258789, "step": 103030 }, { "epoch": 0.6124911579910955, "grad_norm": 1.9517896175384521, "learning_rate": 0.0001941163909885155, "loss": 0.7188368797302246, "step": 103040 }, { "epoch": 0.612550600067764, "grad_norm": 2.144543409347534, "learning_rate": 0.00019411417706837876, "loss": 0.6755593299865723, "step": 103050 }, { "epoch": 0.6126100421444324, "grad_norm": 1.4604053497314453, "learning_rate": 0.00019411196274586728, "loss": 0.6467232704162598, "step": 103060 }, { "epoch": 0.6126694842211008, "grad_norm": 2.0111608505249023, "learning_rate": 0.00019410974802099162, "loss": 0.6998779296875, "step": 103070 }, { "epoch": 0.6127289262977691, "grad_norm": 1.8971867561340332, "learning_rate": 0.00019410753289376243, "loss": 0.7439228057861328, "step": 103080 }, { "epoch": 0.6127883683744375, "grad_norm": 1.927813172340393, "learning_rate": 0.00019410531736419032, "loss": 0.7468575954437255, "step": 103090 }, { "epoch": 0.6128478104511059, "grad_norm": 1.826512098312378, "learning_rate": 0.00019410310143228582, "loss": 0.6908319473266602, "step": 103100 }, { "epoch": 0.6129072525277743, "grad_norm": 1.6962624788284302, "learning_rate": 0.0001941008850980596, "loss": 0.6719449043273926, "step": 103110 }, { "epoch": 0.6129666946044428, "grad_norm": 1.5992945432662964, "learning_rate": 0.00019409866836152218, "loss": 0.6793391227722168, "step": 103120 }, { "epoch": 0.6130261366811111, "grad_norm": 1.643207311630249, "learning_rate": 0.00019409645122268426, "loss": 0.6475569725036621, "step": 103130 }, { "epoch": 0.6130855787577795, "grad_norm": 1.6683080196380615, "learning_rate": 0.00019409423368155638, "loss": 0.6938920974731445, "step": 103140 }, { "epoch": 0.6131450208344479, "grad_norm": 1.8758491277694702, "learning_rate": 0.00019409201573814918, "loss": 0.6850805282592773, "step": 103150 }, { "epoch": 0.6132044629111163, "grad_norm": 1.670491337776184, "learning_rate": 0.00019408979739247325, "loss": 0.6789110660552978, "step": 103160 }, { "epoch": 0.6132639049877846, "grad_norm": 1.7675968408584595, "learning_rate": 0.00019408757864453923, "loss": 0.7099740505218506, "step": 103170 }, { "epoch": 0.613323347064453, "grad_norm": 1.4871981143951416, "learning_rate": 0.0001940853594943577, "loss": 0.6263814926147461, "step": 103180 }, { "epoch": 0.6133827891411214, "grad_norm": 2.208771228790283, "learning_rate": 0.0001940831399419393, "loss": 0.6767366409301758, "step": 103190 }, { "epoch": 0.6134422312177898, "grad_norm": 1.8014634847640991, "learning_rate": 0.00019408091998729464, "loss": 0.6792476654052735, "step": 103200 }, { "epoch": 0.6135016732944583, "grad_norm": 1.6991974115371704, "learning_rate": 0.00019407869963043427, "loss": 0.7756014823913574, "step": 103210 }, { "epoch": 0.6135611153711266, "grad_norm": 1.442031979560852, "learning_rate": 0.00019407647887136897, "loss": 0.6596445083618164, "step": 103220 }, { "epoch": 0.613620557447795, "grad_norm": 2.011137008666992, "learning_rate": 0.00019407425771010922, "loss": 0.6231256008148194, "step": 103230 }, { "epoch": 0.6136799995244634, "grad_norm": 1.7332974672317505, "learning_rate": 0.0001940720361466657, "loss": 0.6749482154846191, "step": 103240 }, { "epoch": 0.6137394416011318, "grad_norm": 1.7112772464752197, "learning_rate": 0.00019406981418104905, "loss": 0.618232536315918, "step": 103250 }, { "epoch": 0.6137988836778002, "grad_norm": 1.9766345024108887, "learning_rate": 0.00019406759181326988, "loss": 0.6442977905273437, "step": 103260 }, { "epoch": 0.6138583257544685, "grad_norm": 1.5494967699050903, "learning_rate": 0.00019406536904333882, "loss": 0.6628269195556641, "step": 103270 }, { "epoch": 0.6139177678311369, "grad_norm": 1.7723695039749146, "learning_rate": 0.0001940631458712665, "loss": 0.6634893417358398, "step": 103280 }, { "epoch": 0.6139772099078054, "grad_norm": 1.4409353733062744, "learning_rate": 0.0001940609222970636, "loss": 0.6865301132202148, "step": 103290 }, { "epoch": 0.6140366519844738, "grad_norm": 1.6734005212783813, "learning_rate": 0.0001940586983207407, "loss": 0.6460560321807861, "step": 103300 }, { "epoch": 0.6140960940611421, "grad_norm": 1.7058027982711792, "learning_rate": 0.00019405647394230843, "loss": 0.7099272251129151, "step": 103310 }, { "epoch": 0.6141555361378105, "grad_norm": 1.409135103225708, "learning_rate": 0.00019405424916177748, "loss": 0.6926907062530517, "step": 103320 }, { "epoch": 0.6142149782144789, "grad_norm": 1.9068703651428223, "learning_rate": 0.00019405202397915845, "loss": 0.6320902824401855, "step": 103330 }, { "epoch": 0.6142744202911473, "grad_norm": 1.6535286903381348, "learning_rate": 0.00019404979839446202, "loss": 0.6761509895324707, "step": 103340 }, { "epoch": 0.6143338623678157, "grad_norm": 1.4882899522781372, "learning_rate": 0.00019404757240769883, "loss": 0.6783767700195312, "step": 103350 }, { "epoch": 0.614393304444484, "grad_norm": 1.4429142475128174, "learning_rate": 0.0001940453460188795, "loss": 0.6759583473205566, "step": 103360 }, { "epoch": 0.6144527465211524, "grad_norm": 1.7304140329360962, "learning_rate": 0.00019404311922801472, "loss": 0.6551436901092529, "step": 103370 }, { "epoch": 0.6145121885978209, "grad_norm": 1.8277239799499512, "learning_rate": 0.00019404089203511513, "loss": 0.6719718456268311, "step": 103380 }, { "epoch": 0.6145716306744893, "grad_norm": 1.8520430326461792, "learning_rate": 0.00019403866444019137, "loss": 0.6619878768920898, "step": 103390 }, { "epoch": 0.6146310727511576, "grad_norm": 2.035926103591919, "learning_rate": 0.0001940364364432541, "loss": 0.6491827964782715, "step": 103400 }, { "epoch": 0.614690514827826, "grad_norm": 2.1170005798339844, "learning_rate": 0.00019403420804431397, "loss": 0.7070585250854492, "step": 103410 }, { "epoch": 0.6147499569044944, "grad_norm": 1.7148154973983765, "learning_rate": 0.00019403197924338167, "loss": 0.6961684226989746, "step": 103420 }, { "epoch": 0.6148093989811628, "grad_norm": 1.512351632118225, "learning_rate": 0.00019402975004046783, "loss": 0.7447341442108154, "step": 103430 }, { "epoch": 0.6148688410578312, "grad_norm": 1.8030873537063599, "learning_rate": 0.00019402752043558316, "loss": 0.6857727527618408, "step": 103440 }, { "epoch": 0.6149282831344995, "grad_norm": 1.4271275997161865, "learning_rate": 0.00019402529042873826, "loss": 0.6581474304199219, "step": 103450 }, { "epoch": 0.614987725211168, "grad_norm": 1.6290549039840698, "learning_rate": 0.00019402306001994383, "loss": 0.6764275550842285, "step": 103460 }, { "epoch": 0.6150471672878364, "grad_norm": 2.1236324310302734, "learning_rate": 0.00019402082920921053, "loss": 0.7468648910522461, "step": 103470 }, { "epoch": 0.6151066093645048, "grad_norm": 1.5447596311569214, "learning_rate": 0.00019401859799654907, "loss": 0.6120007991790771, "step": 103480 }, { "epoch": 0.6151660514411732, "grad_norm": 1.5093364715576172, "learning_rate": 0.0001940163663819701, "loss": 0.6364118576049804, "step": 103490 }, { "epoch": 0.6152254935178415, "grad_norm": 1.6115632057189941, "learning_rate": 0.00019401413436548426, "loss": 0.6523477554321289, "step": 103500 }, { "epoch": 0.6152849355945099, "grad_norm": 1.9179054498672485, "learning_rate": 0.00019401190194710225, "loss": 0.6222339630126953, "step": 103510 }, { "epoch": 0.6153443776711783, "grad_norm": 1.5868275165557861, "learning_rate": 0.00019400966912683478, "loss": 0.6800342559814453, "step": 103520 }, { "epoch": 0.6154038197478467, "grad_norm": 1.7690649032592773, "learning_rate": 0.00019400743590469255, "loss": 0.6788683414459229, "step": 103530 }, { "epoch": 0.615463261824515, "grad_norm": 1.2904026508331299, "learning_rate": 0.00019400520228068612, "loss": 0.6700745105743409, "step": 103540 }, { "epoch": 0.6155227039011835, "grad_norm": 1.920847773551941, "learning_rate": 0.00019400296825482628, "loss": 0.7288629531860351, "step": 103550 }, { "epoch": 0.6155821459778519, "grad_norm": 1.6414483785629272, "learning_rate": 0.0001940007338271237, "loss": 0.7225332260131836, "step": 103560 }, { "epoch": 0.6156415880545203, "grad_norm": 1.546506643295288, "learning_rate": 0.0001939984989975891, "loss": 0.6743870735168457, "step": 103570 }, { "epoch": 0.6157010301311887, "grad_norm": 2.070573568344116, "learning_rate": 0.00019399626376623308, "loss": 0.7161959171295166, "step": 103580 }, { "epoch": 0.615760472207857, "grad_norm": 2.0265605449676514, "learning_rate": 0.0001939940281330664, "loss": 0.6583598136901856, "step": 103590 }, { "epoch": 0.6158199142845254, "grad_norm": 2.006713628768921, "learning_rate": 0.00019399179209809975, "loss": 0.6701130867004395, "step": 103600 }, { "epoch": 0.6158793563611938, "grad_norm": 1.8590195178985596, "learning_rate": 0.0001939895556613438, "loss": 0.6312588691711426, "step": 103610 }, { "epoch": 0.6159387984378623, "grad_norm": 1.4816737174987793, "learning_rate": 0.00019398731882280926, "loss": 0.6006511688232422, "step": 103620 }, { "epoch": 0.6159982405145307, "grad_norm": 1.5736531019210815, "learning_rate": 0.00019398508158250684, "loss": 0.7078667163848877, "step": 103630 }, { "epoch": 0.616057682591199, "grad_norm": 1.9607908725738525, "learning_rate": 0.00019398284394044724, "loss": 0.694659423828125, "step": 103640 }, { "epoch": 0.6161171246678674, "grad_norm": 1.49332857131958, "learning_rate": 0.00019398060589664116, "loss": 0.6363942146301269, "step": 103650 }, { "epoch": 0.6161765667445358, "grad_norm": 1.777170181274414, "learning_rate": 0.0001939783674510993, "loss": 0.6181989669799804, "step": 103660 }, { "epoch": 0.6162360088212042, "grad_norm": 2.1013753414154053, "learning_rate": 0.0001939761286038324, "loss": 0.6543398857116699, "step": 103670 }, { "epoch": 0.6162954508978725, "grad_norm": 1.6238149404525757, "learning_rate": 0.0001939738893548511, "loss": 0.660190200805664, "step": 103680 }, { "epoch": 0.6163548929745409, "grad_norm": 1.931276798248291, "learning_rate": 0.0001939716497041662, "loss": 0.7063839912414551, "step": 103690 }, { "epoch": 0.6164143350512093, "grad_norm": 1.2345316410064697, "learning_rate": 0.00019396940965178835, "loss": 0.6163816452026367, "step": 103700 }, { "epoch": 0.6164737771278778, "grad_norm": 1.7666617631912231, "learning_rate": 0.00019396716919772828, "loss": 0.7022736549377442, "step": 103710 }, { "epoch": 0.6165332192045462, "grad_norm": 2.1481454372406006, "learning_rate": 0.00019396492834199673, "loss": 0.7105521202087403, "step": 103720 }, { "epoch": 0.6165926612812145, "grad_norm": 1.8232080936431885, "learning_rate": 0.00019396268708460438, "loss": 0.7002713680267334, "step": 103730 }, { "epoch": 0.6166521033578829, "grad_norm": 1.4331328868865967, "learning_rate": 0.000193960445425562, "loss": 0.6491010189056396, "step": 103740 }, { "epoch": 0.6167115454345513, "grad_norm": 1.9656881093978882, "learning_rate": 0.00019395820336488026, "loss": 0.6891110897064209, "step": 103750 }, { "epoch": 0.6167709875112197, "grad_norm": 1.5828744173049927, "learning_rate": 0.00019395596090256994, "loss": 0.7195573806762695, "step": 103760 }, { "epoch": 0.616830429587888, "grad_norm": 1.3531534671783447, "learning_rate": 0.00019395371803864172, "loss": 0.6513270378112793, "step": 103770 }, { "epoch": 0.6168898716645564, "grad_norm": 1.821759819984436, "learning_rate": 0.00019395147477310637, "loss": 0.6824433326721191, "step": 103780 }, { "epoch": 0.6169493137412249, "grad_norm": 1.4780102968215942, "learning_rate": 0.0001939492311059746, "loss": 0.7124568939208984, "step": 103790 }, { "epoch": 0.6170087558178933, "grad_norm": 1.8759300708770752, "learning_rate": 0.00019394698703725712, "loss": 0.666985034942627, "step": 103800 }, { "epoch": 0.6170681978945617, "grad_norm": 1.8833460807800293, "learning_rate": 0.00019394474256696472, "loss": 0.6737009048461914, "step": 103810 }, { "epoch": 0.61712763997123, "grad_norm": 1.4609720706939697, "learning_rate": 0.00019394249769510806, "loss": 0.6681471347808838, "step": 103820 }, { "epoch": 0.6171870820478984, "grad_norm": 1.3728760480880737, "learning_rate": 0.00019394025242169794, "loss": 0.6526597023010254, "step": 103830 }, { "epoch": 0.6172465241245668, "grad_norm": 2.1559455394744873, "learning_rate": 0.00019393800674674512, "loss": 0.6751131057739258, "step": 103840 }, { "epoch": 0.6173059662012352, "grad_norm": 1.4681766033172607, "learning_rate": 0.00019393576067026027, "loss": 0.626402759552002, "step": 103850 }, { "epoch": 0.6173654082779036, "grad_norm": 1.38652503490448, "learning_rate": 0.00019393351419225415, "loss": 0.6461699962615967, "step": 103860 }, { "epoch": 0.617424850354572, "grad_norm": 2.1619064807891846, "learning_rate": 0.0001939312673127376, "loss": 0.6991202354431152, "step": 103870 }, { "epoch": 0.6174842924312404, "grad_norm": 1.46567964553833, "learning_rate": 0.00019392902003172126, "loss": 0.669189453125, "step": 103880 }, { "epoch": 0.6175437345079088, "grad_norm": 1.6809321641921997, "learning_rate": 0.0001939267723492159, "loss": 0.6959038734436035, "step": 103890 }, { "epoch": 0.6176031765845772, "grad_norm": 1.39443838596344, "learning_rate": 0.0001939245242652323, "loss": 0.6894143581390381, "step": 103900 }, { "epoch": 0.6176626186612455, "grad_norm": 1.798692226409912, "learning_rate": 0.0001939222757797812, "loss": 0.665362024307251, "step": 103910 }, { "epoch": 0.6177220607379139, "grad_norm": 1.50856351852417, "learning_rate": 0.00019392002689287336, "loss": 0.6687067031860352, "step": 103920 }, { "epoch": 0.6177815028145823, "grad_norm": 1.5474823713302612, "learning_rate": 0.00019391777760451953, "loss": 0.7341403961181641, "step": 103930 }, { "epoch": 0.6178409448912507, "grad_norm": 1.830916166305542, "learning_rate": 0.0001939155279147305, "loss": 0.7087020397186279, "step": 103940 }, { "epoch": 0.6179003869679192, "grad_norm": 1.657335638999939, "learning_rate": 0.00019391327782351697, "loss": 0.656379222869873, "step": 103950 }, { "epoch": 0.6179598290445875, "grad_norm": 1.5093928575515747, "learning_rate": 0.00019391102733088978, "loss": 0.672849178314209, "step": 103960 }, { "epoch": 0.6180192711212559, "grad_norm": 1.715529203414917, "learning_rate": 0.00019390877643685962, "loss": 0.6738054275512695, "step": 103970 }, { "epoch": 0.6180787131979243, "grad_norm": 1.4279148578643799, "learning_rate": 0.00019390652514143734, "loss": 0.6689714431762696, "step": 103980 }, { "epoch": 0.6181381552745927, "grad_norm": 1.812211036682129, "learning_rate": 0.00019390427344463364, "loss": 0.6709086894989014, "step": 103990 }, { "epoch": 0.6181975973512611, "grad_norm": 2.134504795074463, "learning_rate": 0.00019390202134645932, "loss": 0.6867193698883056, "step": 104000 }, { "epoch": 0.6182570394279294, "grad_norm": 1.3618566989898682, "learning_rate": 0.00019389976884692513, "loss": 0.6521257400512696, "step": 104010 }, { "epoch": 0.6183164815045978, "grad_norm": 2.246771812438965, "learning_rate": 0.00019389751594604192, "loss": 0.6718960762023926, "step": 104020 }, { "epoch": 0.6183759235812663, "grad_norm": 1.8135895729064941, "learning_rate": 0.00019389526264382037, "loss": 0.7588468551635742, "step": 104030 }, { "epoch": 0.6184353656579347, "grad_norm": 1.933630347251892, "learning_rate": 0.0001938930089402713, "loss": 0.634846305847168, "step": 104040 }, { "epoch": 0.618494807734603, "grad_norm": 2.2091832160949707, "learning_rate": 0.00019389075483540547, "loss": 0.6955471992492676, "step": 104050 }, { "epoch": 0.6185542498112714, "grad_norm": 1.541589379310608, "learning_rate": 0.00019388850032923374, "loss": 0.6895164489746094, "step": 104060 }, { "epoch": 0.6186136918879398, "grad_norm": 1.8492228984832764, "learning_rate": 0.00019388624542176678, "loss": 0.6677507400512696, "step": 104070 }, { "epoch": 0.6186731339646082, "grad_norm": 2.055333137512207, "learning_rate": 0.00019388399011301547, "loss": 0.730295467376709, "step": 104080 }, { "epoch": 0.6187325760412766, "grad_norm": 1.5307223796844482, "learning_rate": 0.0001938817344029906, "loss": 0.6622169971466064, "step": 104090 }, { "epoch": 0.6187920181179449, "grad_norm": 1.83626127243042, "learning_rate": 0.00019387947829170287, "loss": 0.682837724685669, "step": 104100 }, { "epoch": 0.6188514601946133, "grad_norm": 1.7449607849121094, "learning_rate": 0.00019387722177916314, "loss": 0.6669191360473633, "step": 104110 }, { "epoch": 0.6189109022712818, "grad_norm": 1.8144077062606812, "learning_rate": 0.0001938749648653822, "loss": 0.7028580188751221, "step": 104120 }, { "epoch": 0.6189703443479502, "grad_norm": 1.3883390426635742, "learning_rate": 0.00019387270755037085, "loss": 0.6818290710449219, "step": 104130 }, { "epoch": 0.6190297864246185, "grad_norm": 1.6721527576446533, "learning_rate": 0.00019387044983413984, "loss": 0.6541041374206543, "step": 104140 }, { "epoch": 0.6190892285012869, "grad_norm": 1.35708749294281, "learning_rate": 0.00019386819171670003, "loss": 0.7151682853698731, "step": 104150 }, { "epoch": 0.6191486705779553, "grad_norm": 1.9220668077468872, "learning_rate": 0.00019386593319806222, "loss": 0.6575750350952149, "step": 104160 }, { "epoch": 0.6192081126546237, "grad_norm": 1.8532583713531494, "learning_rate": 0.00019386367427823718, "loss": 0.6531247138977051, "step": 104170 }, { "epoch": 0.6192675547312921, "grad_norm": 1.7759854793548584, "learning_rate": 0.0001938614149572357, "loss": 0.7034108161926269, "step": 104180 }, { "epoch": 0.6193269968079604, "grad_norm": 1.2457282543182373, "learning_rate": 0.00019385915523506864, "loss": 0.6572338104248047, "step": 104190 }, { "epoch": 0.6193864388846289, "grad_norm": 1.9039944410324097, "learning_rate": 0.0001938568951117468, "loss": 0.6281638145446777, "step": 104200 }, { "epoch": 0.6194458809612973, "grad_norm": 1.678302526473999, "learning_rate": 0.00019385463458728095, "loss": 0.6391674995422363, "step": 104210 }, { "epoch": 0.6195053230379657, "grad_norm": 1.9471832513809204, "learning_rate": 0.00019385237366168197, "loss": 0.7171175956726075, "step": 104220 }, { "epoch": 0.6195647651146341, "grad_norm": 1.634708046913147, "learning_rate": 0.0001938501123349606, "loss": 0.7363615989685058, "step": 104230 }, { "epoch": 0.6196242071913024, "grad_norm": 1.523709774017334, "learning_rate": 0.0001938478506071277, "loss": 0.703647232055664, "step": 104240 }, { "epoch": 0.6196836492679708, "grad_norm": 1.5115859508514404, "learning_rate": 0.00019384558847819412, "loss": 0.6123270988464355, "step": 104250 }, { "epoch": 0.6197430913446392, "grad_norm": 2.2551236152648926, "learning_rate": 0.0001938433259481706, "loss": 0.6709879398345947, "step": 104260 }, { "epoch": 0.6198025334213076, "grad_norm": 1.8304660320281982, "learning_rate": 0.00019384106301706803, "loss": 0.6549870491027832, "step": 104270 }, { "epoch": 0.619861975497976, "grad_norm": 1.9474806785583496, "learning_rate": 0.0001938387996848972, "loss": 0.6871420860290527, "step": 104280 }, { "epoch": 0.6199214175746444, "grad_norm": 1.7268118858337402, "learning_rate": 0.000193836535951669, "loss": 0.6056977272033691, "step": 104290 }, { "epoch": 0.6199808596513128, "grad_norm": 1.9143861532211304, "learning_rate": 0.00019383427181739418, "loss": 0.633663272857666, "step": 104300 }, { "epoch": 0.6200403017279812, "grad_norm": 1.3260453939437866, "learning_rate": 0.00019383200728208358, "loss": 0.58761625289917, "step": 104310 }, { "epoch": 0.6200997438046496, "grad_norm": 1.485870122909546, "learning_rate": 0.00019382974234574807, "loss": 0.6441505432128907, "step": 104320 }, { "epoch": 0.6201591858813179, "grad_norm": 1.9456251859664917, "learning_rate": 0.00019382747700839848, "loss": 0.6882183074951171, "step": 104330 }, { "epoch": 0.6202186279579863, "grad_norm": 1.4271166324615479, "learning_rate": 0.00019382521127004563, "loss": 0.7152958869934082, "step": 104340 }, { "epoch": 0.6202780700346547, "grad_norm": 2.3239080905914307, "learning_rate": 0.00019382294513070034, "loss": 0.6704689979553222, "step": 104350 }, { "epoch": 0.6203375121113232, "grad_norm": 1.811437964439392, "learning_rate": 0.0001938206785903735, "loss": 0.6892672538757324, "step": 104360 }, { "epoch": 0.6203969541879915, "grad_norm": 1.7069247961044312, "learning_rate": 0.00019381841164907592, "loss": 0.6606629371643067, "step": 104370 }, { "epoch": 0.6204563962646599, "grad_norm": 1.7909413576126099, "learning_rate": 0.00019381614430681845, "loss": 0.6731523036956787, "step": 104380 }, { "epoch": 0.6205158383413283, "grad_norm": 1.8360931873321533, "learning_rate": 0.0001938138765636119, "loss": 0.6513518333435059, "step": 104390 }, { "epoch": 0.6205752804179967, "grad_norm": 1.5296990871429443, "learning_rate": 0.0001938116084194672, "loss": 0.6954802989959716, "step": 104400 }, { "epoch": 0.6206347224946651, "grad_norm": 1.3857104778289795, "learning_rate": 0.00019380933987439515, "loss": 0.678830337524414, "step": 104410 }, { "epoch": 0.6206941645713334, "grad_norm": 1.7182674407958984, "learning_rate": 0.00019380707092840662, "loss": 0.734187126159668, "step": 104420 }, { "epoch": 0.6207536066480018, "grad_norm": 1.5438035726547241, "learning_rate": 0.00019380480158151243, "loss": 0.684520959854126, "step": 104430 }, { "epoch": 0.6208130487246702, "grad_norm": 1.6154136657714844, "learning_rate": 0.0001938025318337235, "loss": 0.6322048664093017, "step": 104440 }, { "epoch": 0.6208724908013387, "grad_norm": 1.3930561542510986, "learning_rate": 0.00019380026168505058, "loss": 0.6670528411865234, "step": 104450 }, { "epoch": 0.6209319328780071, "grad_norm": 2.5737526416778564, "learning_rate": 0.00019379799113550462, "loss": 0.721596622467041, "step": 104460 }, { "epoch": 0.6209913749546754, "grad_norm": 1.791479229927063, "learning_rate": 0.00019379572018509645, "loss": 0.7248289108276367, "step": 104470 }, { "epoch": 0.6210508170313438, "grad_norm": 1.7846473455429077, "learning_rate": 0.00019379344883383692, "loss": 0.7002015113830566, "step": 104480 }, { "epoch": 0.6211102591080122, "grad_norm": 1.9347208738327026, "learning_rate": 0.00019379117708173696, "loss": 0.6308847427368164, "step": 104490 }, { "epoch": 0.6211697011846806, "grad_norm": 1.7784782648086548, "learning_rate": 0.00019378890492880737, "loss": 0.7178886890411377, "step": 104500 }, { "epoch": 0.6212291432613489, "grad_norm": 1.3704967498779297, "learning_rate": 0.00019378663237505905, "loss": 0.6576664924621582, "step": 104510 }, { "epoch": 0.6212885853380173, "grad_norm": 1.4949582815170288, "learning_rate": 0.00019378435942050287, "loss": 0.7276307106018066, "step": 104520 }, { "epoch": 0.6213480274146858, "grad_norm": 1.5712803602218628, "learning_rate": 0.00019378208606514965, "loss": 0.6631635665893555, "step": 104530 }, { "epoch": 0.6214074694913542, "grad_norm": 1.345750093460083, "learning_rate": 0.00019377981230901036, "loss": 0.7292478084564209, "step": 104540 }, { "epoch": 0.6214669115680226, "grad_norm": 2.1167891025543213, "learning_rate": 0.00019377753815209581, "loss": 0.6762410640716553, "step": 104550 }, { "epoch": 0.6215263536446909, "grad_norm": 1.5097821950912476, "learning_rate": 0.0001937752635944169, "loss": 0.6494111061096192, "step": 104560 }, { "epoch": 0.6215857957213593, "grad_norm": 1.752073884010315, "learning_rate": 0.0001937729886359845, "loss": 0.6814937591552734, "step": 104570 }, { "epoch": 0.6216452377980277, "grad_norm": 1.9786893129348755, "learning_rate": 0.00019377071327680948, "loss": 0.6629832267761231, "step": 104580 }, { "epoch": 0.6217046798746961, "grad_norm": 2.16615891456604, "learning_rate": 0.00019376843751690276, "loss": 0.7065948009490967, "step": 104590 }, { "epoch": 0.6217641219513645, "grad_norm": 1.627564787864685, "learning_rate": 0.00019376616135627524, "loss": 0.6734116554260254, "step": 104600 }, { "epoch": 0.6218235640280328, "grad_norm": 1.8232769966125488, "learning_rate": 0.00019376388479493774, "loss": 0.6950835704803466, "step": 104610 }, { "epoch": 0.6218830061047013, "grad_norm": 1.6511353254318237, "learning_rate": 0.00019376160783290123, "loss": 0.6559125900268554, "step": 104620 }, { "epoch": 0.6219424481813697, "grad_norm": 1.923816442489624, "learning_rate": 0.00019375933047017653, "loss": 0.7542415618896484, "step": 104630 }, { "epoch": 0.6220018902580381, "grad_norm": 1.623128890991211, "learning_rate": 0.00019375705270677457, "loss": 0.7079472541809082, "step": 104640 }, { "epoch": 0.6220613323347064, "grad_norm": 1.8063580989837646, "learning_rate": 0.00019375477454270626, "loss": 0.7131011486053467, "step": 104650 }, { "epoch": 0.6221207744113748, "grad_norm": 1.815393328666687, "learning_rate": 0.00019375249597798245, "loss": 0.7231581687927247, "step": 104660 }, { "epoch": 0.6221802164880432, "grad_norm": 1.4574278593063354, "learning_rate": 0.0001937502170126141, "loss": 0.6010313987731933, "step": 104670 }, { "epoch": 0.6222396585647116, "grad_norm": 1.4151673316955566, "learning_rate": 0.00019374793764661205, "loss": 0.7014753341674804, "step": 104680 }, { "epoch": 0.62229910064138, "grad_norm": 1.6271955966949463, "learning_rate": 0.00019374565787998727, "loss": 0.6620876312255859, "step": 104690 }, { "epoch": 0.6223585427180484, "grad_norm": 1.9705864191055298, "learning_rate": 0.0001937433777127506, "loss": 0.7162586688995362, "step": 104700 }, { "epoch": 0.6224179847947168, "grad_norm": 2.115448236465454, "learning_rate": 0.000193741097144913, "loss": 0.6622419834136963, "step": 104710 }, { "epoch": 0.6224774268713852, "grad_norm": 1.6195968389511108, "learning_rate": 0.00019373881617648536, "loss": 0.7313431739807129, "step": 104720 }, { "epoch": 0.6225368689480536, "grad_norm": 1.8027135133743286, "learning_rate": 0.00019373653480747857, "loss": 0.7370580673217774, "step": 104730 }, { "epoch": 0.6225963110247219, "grad_norm": 1.5405819416046143, "learning_rate": 0.00019373425303790358, "loss": 0.738668155670166, "step": 104740 }, { "epoch": 0.6226557531013903, "grad_norm": 1.7149243354797363, "learning_rate": 0.0001937319708677713, "loss": 0.6687373638153076, "step": 104750 }, { "epoch": 0.6227151951780587, "grad_norm": 1.6246535778045654, "learning_rate": 0.0001937296882970926, "loss": 0.7034750938415527, "step": 104760 }, { "epoch": 0.6227746372547271, "grad_norm": 1.8371530771255493, "learning_rate": 0.00019372740532587842, "loss": 0.6703216075897217, "step": 104770 }, { "epoch": 0.6228340793313956, "grad_norm": 1.361222505569458, "learning_rate": 0.00019372512195413975, "loss": 0.6421519756317139, "step": 104780 }, { "epoch": 0.6228935214080639, "grad_norm": 2.252363681793213, "learning_rate": 0.00019372283818188744, "loss": 0.6497341156005859, "step": 104790 }, { "epoch": 0.6229529634847323, "grad_norm": 1.6169021129608154, "learning_rate": 0.00019372055400913242, "loss": 0.6360903739929199, "step": 104800 }, { "epoch": 0.6230124055614007, "grad_norm": 1.8730645179748535, "learning_rate": 0.00019371826943588563, "loss": 0.6973337173461914, "step": 104810 }, { "epoch": 0.6230718476380691, "grad_norm": 2.5247066020965576, "learning_rate": 0.00019371598446215802, "loss": 0.633721113204956, "step": 104820 }, { "epoch": 0.6231312897147375, "grad_norm": 1.6193573474884033, "learning_rate": 0.00019371369908796046, "loss": 0.582497501373291, "step": 104830 }, { "epoch": 0.6231907317914058, "grad_norm": 1.557895302772522, "learning_rate": 0.00019371141331330397, "loss": 0.643943452835083, "step": 104840 }, { "epoch": 0.6232501738680742, "grad_norm": 1.6769508123397827, "learning_rate": 0.0001937091271381994, "loss": 0.7033679962158204, "step": 104850 }, { "epoch": 0.6233096159447427, "grad_norm": 1.7733486890792847, "learning_rate": 0.00019370684056265773, "loss": 0.6710656166076661, "step": 104860 }, { "epoch": 0.6233690580214111, "grad_norm": 1.5346468687057495, "learning_rate": 0.00019370455358668992, "loss": 0.6721223831176758, "step": 104870 }, { "epoch": 0.6234285000980794, "grad_norm": 2.217275857925415, "learning_rate": 0.00019370226621030683, "loss": 0.7047030448913574, "step": 104880 }, { "epoch": 0.6234879421747478, "grad_norm": 1.7422823905944824, "learning_rate": 0.0001936999784335195, "loss": 0.6193181991577148, "step": 104890 }, { "epoch": 0.6235473842514162, "grad_norm": 1.6402537822723389, "learning_rate": 0.00019369769025633882, "loss": 0.6555082321166992, "step": 104900 }, { "epoch": 0.6236068263280846, "grad_norm": 1.88377845287323, "learning_rate": 0.0001936954016787757, "loss": 0.636436939239502, "step": 104910 }, { "epoch": 0.623666268404753, "grad_norm": 1.5100362300872803, "learning_rate": 0.00019369311270084116, "loss": 0.6915438175201416, "step": 104920 }, { "epoch": 0.6237257104814213, "grad_norm": 2.219311237335205, "learning_rate": 0.00019369082332254612, "loss": 0.635035228729248, "step": 104930 }, { "epoch": 0.6237851525580898, "grad_norm": 1.6882051229476929, "learning_rate": 0.00019368853354390152, "loss": 0.6794434070587159, "step": 104940 }, { "epoch": 0.6238445946347582, "grad_norm": 2.1072838306427, "learning_rate": 0.00019368624336491835, "loss": 0.6645120620727539, "step": 104950 }, { "epoch": 0.6239040367114266, "grad_norm": 1.7121837139129639, "learning_rate": 0.0001936839527856075, "loss": 0.694333839416504, "step": 104960 }, { "epoch": 0.623963478788095, "grad_norm": 1.6271178722381592, "learning_rate": 0.00019368166180598002, "loss": 0.6585339546203614, "step": 104970 }, { "epoch": 0.6240229208647633, "grad_norm": 1.511427640914917, "learning_rate": 0.00019367937042604678, "loss": 0.7007818698883057, "step": 104980 }, { "epoch": 0.6240823629414317, "grad_norm": 1.4731717109680176, "learning_rate": 0.0001936770786458188, "loss": 0.6547781944274902, "step": 104990 }, { "epoch": 0.6241418050181001, "grad_norm": 1.7972222566604614, "learning_rate": 0.000193674786465307, "loss": 0.7114859104156495, "step": 105000 }, { "epoch": 0.6242012470947685, "grad_norm": 1.853339433670044, "learning_rate": 0.0001936724938845224, "loss": 0.6900108337402344, "step": 105010 }, { "epoch": 0.6242606891714368, "grad_norm": 1.3176277875900269, "learning_rate": 0.00019367020090347588, "loss": 0.6476794719696045, "step": 105020 }, { "epoch": 0.6243201312481053, "grad_norm": 1.6168394088745117, "learning_rate": 0.00019366790752217851, "loss": 0.7051808834075928, "step": 105030 }, { "epoch": 0.6243795733247737, "grad_norm": 1.413406491279602, "learning_rate": 0.00019366561374064122, "loss": 0.6467608451843262, "step": 105040 }, { "epoch": 0.6244390154014421, "grad_norm": 1.25381338596344, "learning_rate": 0.00019366331955887495, "loss": 0.6470870018005371, "step": 105050 }, { "epoch": 0.6244984574781105, "grad_norm": 1.4016021490097046, "learning_rate": 0.0001936610249768907, "loss": 0.623514461517334, "step": 105060 }, { "epoch": 0.6245578995547788, "grad_norm": 1.4887818098068237, "learning_rate": 0.00019365872999469944, "loss": 0.6202182769775391, "step": 105070 }, { "epoch": 0.6246173416314472, "grad_norm": 1.5917774438858032, "learning_rate": 0.00019365643461231215, "loss": 0.6977980613708497, "step": 105080 }, { "epoch": 0.6246767837081156, "grad_norm": 1.8082143068313599, "learning_rate": 0.00019365413882973983, "loss": 0.6584918022155761, "step": 105090 }, { "epoch": 0.624736225784784, "grad_norm": 1.9167797565460205, "learning_rate": 0.00019365184264699348, "loss": 0.6869128227233887, "step": 105100 }, { "epoch": 0.6247956678614524, "grad_norm": 2.116292953491211, "learning_rate": 0.000193649546064084, "loss": 0.7049517631530762, "step": 105110 }, { "epoch": 0.6248551099381208, "grad_norm": 2.0377748012542725, "learning_rate": 0.0001936472490810225, "loss": 0.6539311408996582, "step": 105120 }, { "epoch": 0.6249145520147892, "grad_norm": 1.9563614130020142, "learning_rate": 0.00019364495169781979, "loss": 0.6411290168762207, "step": 105130 }, { "epoch": 0.6249739940914576, "grad_norm": 2.0621020793914795, "learning_rate": 0.00019364265391448704, "loss": 0.6597986221313477, "step": 105140 }, { "epoch": 0.625033436168126, "grad_norm": 1.4856456518173218, "learning_rate": 0.00019364035573103517, "loss": 0.710054349899292, "step": 105150 }, { "epoch": 0.6250928782447943, "grad_norm": 1.562393307685852, "learning_rate": 0.00019363805714747517, "loss": 0.6616232395172119, "step": 105160 }, { "epoch": 0.6251523203214627, "grad_norm": 1.5328789949417114, "learning_rate": 0.000193635758163818, "loss": 0.7012237071990967, "step": 105170 }, { "epoch": 0.6252117623981311, "grad_norm": 1.6017628908157349, "learning_rate": 0.00019363345878007472, "loss": 0.7031258106231689, "step": 105180 }, { "epoch": 0.6252712044747996, "grad_norm": 1.6659990549087524, "learning_rate": 0.0001936311589962563, "loss": 0.6530885219573974, "step": 105190 }, { "epoch": 0.625330646551468, "grad_norm": 1.769439935684204, "learning_rate": 0.00019362885881237375, "loss": 0.658392333984375, "step": 105200 }, { "epoch": 0.6253900886281363, "grad_norm": 1.8748234510421753, "learning_rate": 0.0001936265582284381, "loss": 0.6633219718933105, "step": 105210 }, { "epoch": 0.6254495307048047, "grad_norm": 1.9257451295852661, "learning_rate": 0.00019362425724446026, "loss": 0.6896434783935547, "step": 105220 }, { "epoch": 0.6255089727814731, "grad_norm": 1.5371648073196411, "learning_rate": 0.00019362195586045136, "loss": 0.6582495689392089, "step": 105230 }, { "epoch": 0.6255684148581415, "grad_norm": 1.5786423683166504, "learning_rate": 0.0001936196540764223, "loss": 0.6543578147888184, "step": 105240 }, { "epoch": 0.6256278569348098, "grad_norm": 1.2986118793487549, "learning_rate": 0.0001936173518923842, "loss": 0.710011625289917, "step": 105250 }, { "epoch": 0.6256872990114782, "grad_norm": 2.165595531463623, "learning_rate": 0.000193615049308348, "loss": 0.6685845851898193, "step": 105260 }, { "epoch": 0.6257467410881467, "grad_norm": 1.7102563381195068, "learning_rate": 0.0001936127463243247, "loss": 0.6491897106170654, "step": 105270 }, { "epoch": 0.6258061831648151, "grad_norm": 1.9295117855072021, "learning_rate": 0.00019361044294032538, "loss": 0.6385642051696777, "step": 105280 }, { "epoch": 0.6258656252414835, "grad_norm": 1.429182767868042, "learning_rate": 0.000193608139156361, "loss": 0.6938890933990478, "step": 105290 }, { "epoch": 0.6259250673181518, "grad_norm": 1.949743390083313, "learning_rate": 0.0001936058349724426, "loss": 0.6444198608398437, "step": 105300 }, { "epoch": 0.6259845093948202, "grad_norm": 1.4567111730575562, "learning_rate": 0.0001936035303885812, "loss": 0.6276185989379883, "step": 105310 }, { "epoch": 0.6260439514714886, "grad_norm": 1.5702662467956543, "learning_rate": 0.00019360122540478788, "loss": 0.6048694133758545, "step": 105320 }, { "epoch": 0.626103393548157, "grad_norm": 1.5674787759780884, "learning_rate": 0.0001935989200210736, "loss": 0.6310042858123779, "step": 105330 }, { "epoch": 0.6261628356248254, "grad_norm": 1.9265376329421997, "learning_rate": 0.0001935966142374494, "loss": 0.7523607730865478, "step": 105340 }, { "epoch": 0.6262222777014937, "grad_norm": 1.961898922920227, "learning_rate": 0.00019359430805392628, "loss": 0.698158597946167, "step": 105350 }, { "epoch": 0.6262817197781622, "grad_norm": 1.4631191492080688, "learning_rate": 0.00019359200147051539, "loss": 0.6455433368682861, "step": 105360 }, { "epoch": 0.6263411618548306, "grad_norm": 1.2698529958724976, "learning_rate": 0.0001935896944872276, "loss": 0.633285665512085, "step": 105370 }, { "epoch": 0.626400603931499, "grad_norm": 1.9167349338531494, "learning_rate": 0.00019358738710407406, "loss": 0.7326687335968017, "step": 105380 }, { "epoch": 0.6264600460081673, "grad_norm": 1.9077718257904053, "learning_rate": 0.00019358507932106583, "loss": 0.676328468322754, "step": 105390 }, { "epoch": 0.6265194880848357, "grad_norm": 1.7301688194274902, "learning_rate": 0.00019358277113821386, "loss": 0.6905913352966309, "step": 105400 }, { "epoch": 0.6265789301615041, "grad_norm": 1.5731180906295776, "learning_rate": 0.0001935804625555292, "loss": 0.6863311767578125, "step": 105410 }, { "epoch": 0.6266383722381725, "grad_norm": 1.4625065326690674, "learning_rate": 0.00019357815357302295, "loss": 0.6852531909942627, "step": 105420 }, { "epoch": 0.626697814314841, "grad_norm": 1.6572363376617432, "learning_rate": 0.0001935758441907061, "loss": 0.6429535865783691, "step": 105430 }, { "epoch": 0.6267572563915093, "grad_norm": 1.5415948629379272, "learning_rate": 0.00019357353440858975, "loss": 0.6712423324584961, "step": 105440 }, { "epoch": 0.6268166984681777, "grad_norm": 1.89191472530365, "learning_rate": 0.00019357122422668493, "loss": 0.6956430912017822, "step": 105450 }, { "epoch": 0.6268761405448461, "grad_norm": 2.3110196590423584, "learning_rate": 0.00019356891364500264, "loss": 0.6651253700256348, "step": 105460 }, { "epoch": 0.6269355826215145, "grad_norm": 2.258378744125366, "learning_rate": 0.000193566602663554, "loss": 0.614330530166626, "step": 105470 }, { "epoch": 0.6269950246981828, "grad_norm": 1.849793553352356, "learning_rate": 0.00019356429128235007, "loss": 0.6633559703826905, "step": 105480 }, { "epoch": 0.6270544667748512, "grad_norm": 1.679681420326233, "learning_rate": 0.00019356197950140186, "loss": 0.6633181571960449, "step": 105490 }, { "epoch": 0.6271139088515196, "grad_norm": 1.6773080825805664, "learning_rate": 0.00019355966732072046, "loss": 0.674748420715332, "step": 105500 }, { "epoch": 0.627173350928188, "grad_norm": 1.7765865325927734, "learning_rate": 0.00019355735474031692, "loss": 0.6953310966491699, "step": 105510 }, { "epoch": 0.6272327930048565, "grad_norm": 1.7938679456710815, "learning_rate": 0.00019355504176020227, "loss": 0.7061813354492188, "step": 105520 }, { "epoch": 0.6272922350815248, "grad_norm": 1.861419916152954, "learning_rate": 0.00019355272838038763, "loss": 0.6650116443634033, "step": 105530 }, { "epoch": 0.6273516771581932, "grad_norm": 1.728469967842102, "learning_rate": 0.00019355041460088402, "loss": 0.66651611328125, "step": 105540 }, { "epoch": 0.6274111192348616, "grad_norm": 1.5557762384414673, "learning_rate": 0.00019354810042170257, "loss": 0.6829201698303222, "step": 105550 }, { "epoch": 0.62747056131153, "grad_norm": 1.7567172050476074, "learning_rate": 0.00019354578584285427, "loss": 0.6358409881591797, "step": 105560 }, { "epoch": 0.6275300033881984, "grad_norm": 1.6717474460601807, "learning_rate": 0.00019354347086435026, "loss": 0.6602609634399415, "step": 105570 }, { "epoch": 0.6275894454648667, "grad_norm": 1.5976355075836182, "learning_rate": 0.0001935411554862016, "loss": 0.6668949127197266, "step": 105580 }, { "epoch": 0.6276488875415351, "grad_norm": 1.717673659324646, "learning_rate": 0.00019353883970841932, "loss": 0.6623912811279297, "step": 105590 }, { "epoch": 0.6277083296182036, "grad_norm": 1.6848026514053345, "learning_rate": 0.00019353652353101456, "loss": 0.7082631587982178, "step": 105600 }, { "epoch": 0.627767771694872, "grad_norm": 1.8304499387741089, "learning_rate": 0.00019353420695399835, "loss": 0.6850179672241211, "step": 105610 }, { "epoch": 0.6278272137715403, "grad_norm": 1.8065952062606812, "learning_rate": 0.00019353188997738184, "loss": 0.6828591346740722, "step": 105620 }, { "epoch": 0.6278866558482087, "grad_norm": 1.8460365533828735, "learning_rate": 0.000193529572601176, "loss": 0.6628557682037354, "step": 105630 }, { "epoch": 0.6279460979248771, "grad_norm": 1.9115455150604248, "learning_rate": 0.00019352725482539202, "loss": 0.6347723007202148, "step": 105640 }, { "epoch": 0.6280055400015455, "grad_norm": 1.5513867139816284, "learning_rate": 0.00019352493665004093, "loss": 0.6532618999481201, "step": 105650 }, { "epoch": 0.6280649820782139, "grad_norm": 1.5494099855422974, "learning_rate": 0.00019352261807513386, "loss": 0.7134478569030762, "step": 105660 }, { "epoch": 0.6281244241548822, "grad_norm": 1.5497878789901733, "learning_rate": 0.00019352029910068186, "loss": 0.7263195991516114, "step": 105670 }, { "epoch": 0.6281838662315506, "grad_norm": 1.5761210918426514, "learning_rate": 0.00019351797972669608, "loss": 0.6090073585510254, "step": 105680 }, { "epoch": 0.6282433083082191, "grad_norm": 1.5403907299041748, "learning_rate": 0.00019351565995318754, "loss": 0.6713473320007324, "step": 105690 }, { "epoch": 0.6283027503848875, "grad_norm": 1.59959077835083, "learning_rate": 0.00019351333978016738, "loss": 0.6787246704101563, "step": 105700 }, { "epoch": 0.6283621924615559, "grad_norm": 1.7698270082473755, "learning_rate": 0.00019351101920764673, "loss": 0.6566688537597656, "step": 105710 }, { "epoch": 0.6284216345382242, "grad_norm": 1.6361637115478516, "learning_rate": 0.00019350869823563663, "loss": 0.7030850410461426, "step": 105720 }, { "epoch": 0.6284810766148926, "grad_norm": 1.7226380109786987, "learning_rate": 0.0001935063768641482, "loss": 0.620697021484375, "step": 105730 }, { "epoch": 0.628540518691561, "grad_norm": 2.036167860031128, "learning_rate": 0.00019350405509319256, "loss": 0.6794271469116211, "step": 105740 }, { "epoch": 0.6285999607682294, "grad_norm": 1.715097188949585, "learning_rate": 0.00019350173292278082, "loss": 0.6854230880737304, "step": 105750 }, { "epoch": 0.6286594028448977, "grad_norm": 2.0162675380706787, "learning_rate": 0.00019349941035292408, "loss": 0.6646684169769287, "step": 105760 }, { "epoch": 0.6287188449215662, "grad_norm": 2.0077085494995117, "learning_rate": 0.00019349708738363342, "loss": 0.6329583168029785, "step": 105770 }, { "epoch": 0.6287782869982346, "grad_norm": 1.8787339925765991, "learning_rate": 0.00019349476401492, "loss": 0.6933173656463623, "step": 105780 }, { "epoch": 0.628837729074903, "grad_norm": 1.400853157043457, "learning_rate": 0.0001934924402467949, "loss": 0.7454416275024414, "step": 105790 }, { "epoch": 0.6288971711515714, "grad_norm": 1.2780485153198242, "learning_rate": 0.0001934901160792693, "loss": 0.7212817192077636, "step": 105800 }, { "epoch": 0.6289566132282397, "grad_norm": 1.7699427604675293, "learning_rate": 0.00019348779151235425, "loss": 0.7273253440856934, "step": 105810 }, { "epoch": 0.6290160553049081, "grad_norm": 1.353466510772705, "learning_rate": 0.00019348546654606087, "loss": 0.6746109008789063, "step": 105820 }, { "epoch": 0.6290754973815765, "grad_norm": 2.2421743869781494, "learning_rate": 0.0001934831411804003, "loss": 0.7009449005126953, "step": 105830 }, { "epoch": 0.629134939458245, "grad_norm": 2.0720279216766357, "learning_rate": 0.00019348081541538368, "loss": 0.7107436656951904, "step": 105840 }, { "epoch": 0.6291943815349132, "grad_norm": 1.779327392578125, "learning_rate": 0.0001934784892510221, "loss": 0.6462165832519531, "step": 105850 }, { "epoch": 0.6292538236115817, "grad_norm": 1.4011282920837402, "learning_rate": 0.00019347616268732673, "loss": 0.6835079193115234, "step": 105860 }, { "epoch": 0.6293132656882501, "grad_norm": 2.290529489517212, "learning_rate": 0.00019347383572430865, "loss": 0.673882007598877, "step": 105870 }, { "epoch": 0.6293727077649185, "grad_norm": 1.502813696861267, "learning_rate": 0.00019347150836197908, "loss": 0.7049166679382324, "step": 105880 }, { "epoch": 0.6294321498415869, "grad_norm": 1.7813829183578491, "learning_rate": 0.000193469180600349, "loss": 0.6312490463256836, "step": 105890 }, { "epoch": 0.6294915919182552, "grad_norm": 1.7419729232788086, "learning_rate": 0.00019346685243942972, "loss": 0.6787405014038086, "step": 105900 }, { "epoch": 0.6295510339949236, "grad_norm": 1.6213017702102661, "learning_rate": 0.00019346452387923227, "loss": 0.7458753108978271, "step": 105910 }, { "epoch": 0.629610476071592, "grad_norm": 1.4647787809371948, "learning_rate": 0.00019346219491976784, "loss": 0.6938408374786377, "step": 105920 }, { "epoch": 0.6296699181482605, "grad_norm": 1.3093119859695435, "learning_rate": 0.00019345986556104747, "loss": 0.5955441474914551, "step": 105930 }, { "epoch": 0.6297293602249289, "grad_norm": 1.8187918663024902, "learning_rate": 0.00019345753580308245, "loss": 0.7015904426574707, "step": 105940 }, { "epoch": 0.6297888023015972, "grad_norm": 1.6751809120178223, "learning_rate": 0.00019345520564588382, "loss": 0.5987245082855225, "step": 105950 }, { "epoch": 0.6298482443782656, "grad_norm": 1.7009341716766357, "learning_rate": 0.00019345287508946277, "loss": 0.7351599216461182, "step": 105960 }, { "epoch": 0.629907686454934, "grad_norm": 2.0284650325775146, "learning_rate": 0.00019345054413383043, "loss": 0.6700069427490234, "step": 105970 }, { "epoch": 0.6299671285316024, "grad_norm": 1.3614897727966309, "learning_rate": 0.00019344821277899796, "loss": 0.6318151950836182, "step": 105980 }, { "epoch": 0.6300265706082707, "grad_norm": 1.2349834442138672, "learning_rate": 0.0001934458810249765, "loss": 0.6185474395751953, "step": 105990 }, { "epoch": 0.6300860126849391, "grad_norm": 1.9088858366012573, "learning_rate": 0.00019344354887177725, "loss": 0.6007508754730224, "step": 106000 }, { "epoch": 0.6301454547616075, "grad_norm": 1.9077767133712769, "learning_rate": 0.0001934412163194113, "loss": 0.6756131172180175, "step": 106010 }, { "epoch": 0.630204896838276, "grad_norm": 1.4494370222091675, "learning_rate": 0.00019343888336788986, "loss": 0.6342679023742676, "step": 106020 }, { "epoch": 0.6302643389149444, "grad_norm": 1.7744636535644531, "learning_rate": 0.00019343655001722408, "loss": 0.6289265632629395, "step": 106030 }, { "epoch": 0.6303237809916127, "grad_norm": 2.0770580768585205, "learning_rate": 0.0001934342162674251, "loss": 0.6615754127502441, "step": 106040 }, { "epoch": 0.6303832230682811, "grad_norm": 1.893872857093811, "learning_rate": 0.00019343188211850407, "loss": 0.6446731567382813, "step": 106050 }, { "epoch": 0.6304426651449495, "grad_norm": 1.460428237915039, "learning_rate": 0.0001934295475704722, "loss": 0.5899672985076905, "step": 106060 }, { "epoch": 0.6305021072216179, "grad_norm": 1.534218668937683, "learning_rate": 0.00019342721262334065, "loss": 0.6986440658569336, "step": 106070 }, { "epoch": 0.6305615492982863, "grad_norm": 1.726144552230835, "learning_rate": 0.0001934248772771206, "loss": 0.6652479648590088, "step": 106080 }, { "epoch": 0.6306209913749546, "grad_norm": 1.490749716758728, "learning_rate": 0.00019342254153182316, "loss": 0.617863655090332, "step": 106090 }, { "epoch": 0.6306804334516231, "grad_norm": 1.8176542520523071, "learning_rate": 0.00019342020538745956, "loss": 0.6899746894836426, "step": 106100 }, { "epoch": 0.6307398755282915, "grad_norm": 1.6896988153457642, "learning_rate": 0.00019341786884404094, "loss": 0.632229995727539, "step": 106110 }, { "epoch": 0.6307993176049599, "grad_norm": 1.6212252378463745, "learning_rate": 0.0001934155319015785, "loss": 0.6284422874450684, "step": 106120 }, { "epoch": 0.6308587596816282, "grad_norm": 1.5939220190048218, "learning_rate": 0.00019341319456008346, "loss": 0.7702981948852539, "step": 106130 }, { "epoch": 0.6309182017582966, "grad_norm": 1.7127047777175903, "learning_rate": 0.0001934108568195669, "loss": 0.7812580585479736, "step": 106140 }, { "epoch": 0.630977643834965, "grad_norm": 2.0438356399536133, "learning_rate": 0.0001934085186800401, "loss": 0.6493114948272705, "step": 106150 }, { "epoch": 0.6310370859116334, "grad_norm": 1.6793036460876465, "learning_rate": 0.00019340618014151417, "loss": 0.7350823879241943, "step": 106160 }, { "epoch": 0.6310965279883018, "grad_norm": 1.5519425868988037, "learning_rate": 0.00019340384120400037, "loss": 0.6672244071960449, "step": 106170 }, { "epoch": 0.6311559700649702, "grad_norm": 1.7567694187164307, "learning_rate": 0.00019340150186750982, "loss": 0.6306606292724609, "step": 106180 }, { "epoch": 0.6312154121416386, "grad_norm": 1.395676612854004, "learning_rate": 0.00019339916213205376, "loss": 0.6755278587341309, "step": 106190 }, { "epoch": 0.631274854218307, "grad_norm": 1.6788625717163086, "learning_rate": 0.00019339682199764335, "loss": 0.6145057678222656, "step": 106200 }, { "epoch": 0.6313342962949754, "grad_norm": 1.697465181350708, "learning_rate": 0.00019339448146428982, "loss": 0.6720991134643555, "step": 106210 }, { "epoch": 0.6313937383716437, "grad_norm": 1.6104936599731445, "learning_rate": 0.00019339214053200432, "loss": 0.678652000427246, "step": 106220 }, { "epoch": 0.6314531804483121, "grad_norm": 1.7833880186080933, "learning_rate": 0.0001933897992007981, "loss": 0.7319272041320801, "step": 106230 }, { "epoch": 0.6315126225249805, "grad_norm": 1.867712140083313, "learning_rate": 0.0001933874574706823, "loss": 0.6898891448974609, "step": 106240 }, { "epoch": 0.6315720646016489, "grad_norm": 2.0946309566497803, "learning_rate": 0.00019338511534166818, "loss": 0.7237271308898926, "step": 106250 }, { "epoch": 0.6316315066783174, "grad_norm": 1.9609551429748535, "learning_rate": 0.0001933827728137669, "loss": 0.6380571842193603, "step": 106260 }, { "epoch": 0.6316909487549857, "grad_norm": 1.733030080795288, "learning_rate": 0.0001933804298869897, "loss": 0.6184037685394287, "step": 106270 }, { "epoch": 0.6317503908316541, "grad_norm": 1.2470917701721191, "learning_rate": 0.00019337808656134776, "loss": 0.6907295227050781, "step": 106280 }, { "epoch": 0.6318098329083225, "grad_norm": 1.694122552871704, "learning_rate": 0.0001933757428368523, "loss": 0.6623285293579102, "step": 106290 }, { "epoch": 0.6318692749849909, "grad_norm": 1.5971866846084595, "learning_rate": 0.0001933733987135145, "loss": 0.6598359107971191, "step": 106300 }, { "epoch": 0.6319287170616593, "grad_norm": 1.6525609493255615, "learning_rate": 0.00019337105419134568, "loss": 0.677927827835083, "step": 106310 }, { "epoch": 0.6319881591383276, "grad_norm": 1.3526744842529297, "learning_rate": 0.00019336870927035696, "loss": 0.6282957077026368, "step": 106320 }, { "epoch": 0.632047601214996, "grad_norm": 1.8259739875793457, "learning_rate": 0.00019336636395055957, "loss": 0.5850667953491211, "step": 106330 }, { "epoch": 0.6321070432916644, "grad_norm": 1.5174962282180786, "learning_rate": 0.00019336401823196473, "loss": 0.7112932205200195, "step": 106340 }, { "epoch": 0.6321664853683329, "grad_norm": 1.4968115091323853, "learning_rate": 0.00019336167211458368, "loss": 0.7066192626953125, "step": 106350 }, { "epoch": 0.6322259274450012, "grad_norm": 1.528877854347229, "learning_rate": 0.00019335932559842763, "loss": 0.668265438079834, "step": 106360 }, { "epoch": 0.6322853695216696, "grad_norm": 1.7082452774047852, "learning_rate": 0.00019335697868350782, "loss": 0.6629118919372559, "step": 106370 }, { "epoch": 0.632344811598338, "grad_norm": 1.6023430824279785, "learning_rate": 0.00019335463136983545, "loss": 0.6808040618896485, "step": 106380 }, { "epoch": 0.6324042536750064, "grad_norm": 1.6915756464004517, "learning_rate": 0.00019335228365742178, "loss": 0.678041648864746, "step": 106390 }, { "epoch": 0.6324636957516748, "grad_norm": 1.6020910739898682, "learning_rate": 0.000193349935546278, "loss": 0.7047359943389893, "step": 106400 }, { "epoch": 0.6325231378283431, "grad_norm": 1.75308096408844, "learning_rate": 0.0001933475870364154, "loss": 0.647175407409668, "step": 106410 }, { "epoch": 0.6325825799050115, "grad_norm": 1.375109076499939, "learning_rate": 0.00019334523812784517, "loss": 0.7105403900146484, "step": 106420 }, { "epoch": 0.63264202198168, "grad_norm": 1.629675030708313, "learning_rate": 0.00019334288882057857, "loss": 0.748078441619873, "step": 106430 }, { "epoch": 0.6327014640583484, "grad_norm": 2.146782636642456, "learning_rate": 0.0001933405391146268, "loss": 0.7064177989959717, "step": 106440 }, { "epoch": 0.6327609061350168, "grad_norm": 1.8786916732788086, "learning_rate": 0.00019333818901000113, "loss": 0.6513637065887451, "step": 106450 }, { "epoch": 0.6328203482116851, "grad_norm": 1.8814736604690552, "learning_rate": 0.0001933358385067128, "loss": 0.7226691246032715, "step": 106460 }, { "epoch": 0.6328797902883535, "grad_norm": 1.8844751119613647, "learning_rate": 0.00019333348760477306, "loss": 0.6849327564239502, "step": 106470 }, { "epoch": 0.6329392323650219, "grad_norm": 1.8847955465316772, "learning_rate": 0.00019333113630419315, "loss": 0.7189409732818604, "step": 106480 }, { "epoch": 0.6329986744416903, "grad_norm": 2.081627130508423, "learning_rate": 0.00019332878460498433, "loss": 0.6662442207336425, "step": 106490 }, { "epoch": 0.6330581165183586, "grad_norm": 1.5013712644577026, "learning_rate": 0.00019332643250715784, "loss": 0.6700466632843017, "step": 106500 }, { "epoch": 0.633117558595027, "grad_norm": 1.4353315830230713, "learning_rate": 0.0001933240800107249, "loss": 0.6280509948730468, "step": 106510 }, { "epoch": 0.6331770006716955, "grad_norm": 1.464289665222168, "learning_rate": 0.0001933217271156968, "loss": 0.6117788791656494, "step": 106520 }, { "epoch": 0.6332364427483639, "grad_norm": 1.9073556661605835, "learning_rate": 0.0001933193738220848, "loss": 0.713143253326416, "step": 106530 }, { "epoch": 0.6332958848250323, "grad_norm": 1.7127509117126465, "learning_rate": 0.00019331702012990009, "loss": 0.6361258506774903, "step": 106540 }, { "epoch": 0.6333553269017006, "grad_norm": 1.5432584285736084, "learning_rate": 0.00019331466603915405, "loss": 0.6269493579864502, "step": 106550 }, { "epoch": 0.633414768978369, "grad_norm": 1.4416979551315308, "learning_rate": 0.00019331231154985786, "loss": 0.6044241905212402, "step": 106560 }, { "epoch": 0.6334742110550374, "grad_norm": 1.6374237537384033, "learning_rate": 0.00019330995666202278, "loss": 0.6190802097320557, "step": 106570 }, { "epoch": 0.6335336531317058, "grad_norm": 1.5994762182235718, "learning_rate": 0.0001933076013756601, "loss": 0.6187878608703613, "step": 106580 }, { "epoch": 0.6335930952083741, "grad_norm": 1.4687824249267578, "learning_rate": 0.0001933052456907811, "loss": 0.6421975135803223, "step": 106590 }, { "epoch": 0.6336525372850426, "grad_norm": 1.7298790216445923, "learning_rate": 0.00019330288960739698, "loss": 0.6557811260223388, "step": 106600 }, { "epoch": 0.633711979361711, "grad_norm": 2.4308531284332275, "learning_rate": 0.00019330053312551914, "loss": 0.6692840576171875, "step": 106610 }, { "epoch": 0.6337714214383794, "grad_norm": 1.3799329996109009, "learning_rate": 0.0001932981762451587, "loss": 0.5819055557250976, "step": 106620 }, { "epoch": 0.6338308635150478, "grad_norm": 1.9212532043457031, "learning_rate": 0.00019329581896632706, "loss": 0.6675716400146484, "step": 106630 }, { "epoch": 0.6338903055917161, "grad_norm": 1.446222186088562, "learning_rate": 0.0001932934612890354, "loss": 0.629346227645874, "step": 106640 }, { "epoch": 0.6339497476683845, "grad_norm": 2.2757012844085693, "learning_rate": 0.00019329110321329504, "loss": 0.66683931350708, "step": 106650 }, { "epoch": 0.6340091897450529, "grad_norm": 1.8195284605026245, "learning_rate": 0.00019328874473911728, "loss": 0.6366849899291992, "step": 106660 }, { "epoch": 0.6340686318217214, "grad_norm": 1.8247523307800293, "learning_rate": 0.00019328638586651342, "loss": 0.7244358062744141, "step": 106670 }, { "epoch": 0.6341280738983898, "grad_norm": 1.4833730459213257, "learning_rate": 0.00019328402659549466, "loss": 0.5987158298492432, "step": 106680 }, { "epoch": 0.6341875159750581, "grad_norm": 1.8814692497253418, "learning_rate": 0.00019328166692607235, "loss": 0.6841886520385743, "step": 106690 }, { "epoch": 0.6342469580517265, "grad_norm": 1.7663615942001343, "learning_rate": 0.00019327930685825775, "loss": 0.6467378616333008, "step": 106700 }, { "epoch": 0.6343064001283949, "grad_norm": 1.4493727684020996, "learning_rate": 0.00019327694639206217, "loss": 0.5965337753295898, "step": 106710 }, { "epoch": 0.6343658422050633, "grad_norm": 1.937923550605774, "learning_rate": 0.0001932745855274969, "loss": 0.5970478057861328, "step": 106720 }, { "epoch": 0.6344252842817316, "grad_norm": 1.699758529663086, "learning_rate": 0.00019327222426457322, "loss": 0.6538544178009034, "step": 106730 }, { "epoch": 0.6344847263584, "grad_norm": 1.9233630895614624, "learning_rate": 0.00019326986260330244, "loss": 0.6774072647094727, "step": 106740 }, { "epoch": 0.6345441684350684, "grad_norm": 1.6471467018127441, "learning_rate": 0.00019326750054369585, "loss": 0.6562539577484131, "step": 106750 }, { "epoch": 0.6346036105117369, "grad_norm": 1.690015435218811, "learning_rate": 0.00019326513808576477, "loss": 0.7220108032226562, "step": 106760 }, { "epoch": 0.6346630525884053, "grad_norm": 1.4981387853622437, "learning_rate": 0.00019326277522952042, "loss": 0.6669086456298828, "step": 106770 }, { "epoch": 0.6347224946650736, "grad_norm": 1.700294017791748, "learning_rate": 0.0001932604119749742, "loss": 0.7123300075531006, "step": 106780 }, { "epoch": 0.634781936741742, "grad_norm": 1.783612847328186, "learning_rate": 0.0001932580483221374, "loss": 0.6703639984130859, "step": 106790 }, { "epoch": 0.6348413788184104, "grad_norm": 1.5391762256622314, "learning_rate": 0.00019325568427102128, "loss": 0.6460123062133789, "step": 106800 }, { "epoch": 0.6349008208950788, "grad_norm": 1.632746934890747, "learning_rate": 0.0001932533198216372, "loss": 0.7011286735534668, "step": 106810 }, { "epoch": 0.6349602629717472, "grad_norm": 1.6861308813095093, "learning_rate": 0.0001932509549739964, "loss": 0.6781786918640137, "step": 106820 }, { "epoch": 0.6350197050484155, "grad_norm": 1.7930034399032593, "learning_rate": 0.00019324858972811026, "loss": 0.6532523155212402, "step": 106830 }, { "epoch": 0.635079147125084, "grad_norm": 1.4450422525405884, "learning_rate": 0.00019324622408399008, "loss": 0.6810272216796875, "step": 106840 }, { "epoch": 0.6351385892017524, "grad_norm": 1.6424082517623901, "learning_rate": 0.00019324385804164715, "loss": 0.7150655269622803, "step": 106850 }, { "epoch": 0.6351980312784208, "grad_norm": 1.7585524320602417, "learning_rate": 0.00019324149160109284, "loss": 0.6286881446838379, "step": 106860 }, { "epoch": 0.6352574733550891, "grad_norm": 2.0960888862609863, "learning_rate": 0.00019323912476233842, "loss": 0.6939483642578125, "step": 106870 }, { "epoch": 0.6353169154317575, "grad_norm": 1.7300430536270142, "learning_rate": 0.00019323675752539523, "loss": 0.6384977340698242, "step": 106880 }, { "epoch": 0.6353763575084259, "grad_norm": 1.4464584589004517, "learning_rate": 0.0001932343898902746, "loss": 0.6641456127166748, "step": 106890 }, { "epoch": 0.6354357995850943, "grad_norm": 2.400195598602295, "learning_rate": 0.00019323202185698784, "loss": 0.700494909286499, "step": 106900 }, { "epoch": 0.6354952416617627, "grad_norm": 2.2881927490234375, "learning_rate": 0.00019322965342554629, "loss": 0.6845637321472168, "step": 106910 }, { "epoch": 0.635554683738431, "grad_norm": 1.5860486030578613, "learning_rate": 0.0001932272845959613, "loss": 0.6915759086608887, "step": 106920 }, { "epoch": 0.6356141258150995, "grad_norm": 1.6743518114089966, "learning_rate": 0.00019322491536824415, "loss": 0.6885206222534179, "step": 106930 }, { "epoch": 0.6356735678917679, "grad_norm": 1.6602586507797241, "learning_rate": 0.00019322254574240618, "loss": 0.6017322540283203, "step": 106940 }, { "epoch": 0.6357330099684363, "grad_norm": 1.5991191864013672, "learning_rate": 0.0001932201757184588, "loss": 0.7342744827270508, "step": 106950 }, { "epoch": 0.6357924520451046, "grad_norm": 1.3692104816436768, "learning_rate": 0.0001932178052964133, "loss": 0.7127534866333007, "step": 106960 }, { "epoch": 0.635851894121773, "grad_norm": 1.641524314880371, "learning_rate": 0.00019321543447628096, "loss": 0.6991352558135986, "step": 106970 }, { "epoch": 0.6359113361984414, "grad_norm": 1.6818195581436157, "learning_rate": 0.0001932130632580732, "loss": 0.7261580467224121, "step": 106980 }, { "epoch": 0.6359707782751098, "grad_norm": 1.9912205934524536, "learning_rate": 0.00019321069164180137, "loss": 0.6543400287628174, "step": 106990 }, { "epoch": 0.6360302203517783, "grad_norm": 1.571333408355713, "learning_rate": 0.00019320831962747677, "loss": 0.6443729400634766, "step": 107000 }, { "epoch": 0.6360896624284466, "grad_norm": 2.021524667739868, "learning_rate": 0.00019320594721511074, "loss": 0.7329872131347657, "step": 107010 }, { "epoch": 0.636149104505115, "grad_norm": 1.6900522708892822, "learning_rate": 0.00019320357440471468, "loss": 0.6384736061096191, "step": 107020 }, { "epoch": 0.6362085465817834, "grad_norm": 1.8988487720489502, "learning_rate": 0.0001932012011962999, "loss": 0.6984608173370361, "step": 107030 }, { "epoch": 0.6362679886584518, "grad_norm": 1.657857894897461, "learning_rate": 0.00019319882758987776, "loss": 0.6818703174591064, "step": 107040 }, { "epoch": 0.6363274307351202, "grad_norm": 1.7853080034255981, "learning_rate": 0.0001931964535854596, "loss": 0.676586389541626, "step": 107050 }, { "epoch": 0.6363868728117885, "grad_norm": 1.9189531803131104, "learning_rate": 0.0001931940791830568, "loss": 0.6803637981414795, "step": 107060 }, { "epoch": 0.6364463148884569, "grad_norm": 1.6497468948364258, "learning_rate": 0.00019319170438268074, "loss": 0.6113960266113281, "step": 107070 }, { "epoch": 0.6365057569651253, "grad_norm": 1.4750481843948364, "learning_rate": 0.00019318932918434276, "loss": 0.6438153266906739, "step": 107080 }, { "epoch": 0.6365651990417938, "grad_norm": 1.9976273775100708, "learning_rate": 0.0001931869535880542, "loss": 0.6710985183715821, "step": 107090 }, { "epoch": 0.6366246411184621, "grad_norm": 2.076284646987915, "learning_rate": 0.00019318457759382642, "loss": 0.6457821369171143, "step": 107100 }, { "epoch": 0.6366840831951305, "grad_norm": 1.2551528215408325, "learning_rate": 0.00019318220120167082, "loss": 0.6855636596679687, "step": 107110 }, { "epoch": 0.6367435252717989, "grad_norm": 2.123100996017456, "learning_rate": 0.00019317982441159878, "loss": 0.7014143466949463, "step": 107120 }, { "epoch": 0.6368029673484673, "grad_norm": 1.5987628698349, "learning_rate": 0.0001931774472236216, "loss": 0.6345304489135742, "step": 107130 }, { "epoch": 0.6368624094251357, "grad_norm": 1.9738526344299316, "learning_rate": 0.00019317506963775072, "loss": 0.6525803089141846, "step": 107140 }, { "epoch": 0.636921851501804, "grad_norm": 1.7324901819229126, "learning_rate": 0.00019317269165399748, "loss": 0.6264493942260743, "step": 107150 }, { "epoch": 0.6369812935784724, "grad_norm": 1.9276883602142334, "learning_rate": 0.00019317031327237326, "loss": 0.6931272029876709, "step": 107160 }, { "epoch": 0.6370407356551409, "grad_norm": 1.8994059562683105, "learning_rate": 0.00019316793449288949, "loss": 0.6868537425994873, "step": 107170 }, { "epoch": 0.6371001777318093, "grad_norm": 1.7948317527770996, "learning_rate": 0.00019316555531555742, "loss": 0.6817118644714355, "step": 107180 }, { "epoch": 0.6371596198084777, "grad_norm": 1.393117070198059, "learning_rate": 0.00019316317574038857, "loss": 0.6706696033477784, "step": 107190 }, { "epoch": 0.637219061885146, "grad_norm": 1.6512517929077148, "learning_rate": 0.00019316079576739425, "loss": 0.6106035232543945, "step": 107200 }, { "epoch": 0.6372785039618144, "grad_norm": 1.8368717432022095, "learning_rate": 0.00019315841539658586, "loss": 0.6161482334136963, "step": 107210 }, { "epoch": 0.6373379460384828, "grad_norm": 1.7035925388336182, "learning_rate": 0.00019315603462797477, "loss": 0.6143730163574219, "step": 107220 }, { "epoch": 0.6373973881151512, "grad_norm": 1.3242806196212769, "learning_rate": 0.00019315365346157242, "loss": 0.6664376258850098, "step": 107230 }, { "epoch": 0.6374568301918195, "grad_norm": 1.9460793733596802, "learning_rate": 0.00019315127189739015, "loss": 0.747028923034668, "step": 107240 }, { "epoch": 0.637516272268488, "grad_norm": 1.5242151021957397, "learning_rate": 0.00019314888993543936, "loss": 0.7011163234710693, "step": 107250 }, { "epoch": 0.6375757143451564, "grad_norm": 1.8699232339859009, "learning_rate": 0.00019314650757573147, "loss": 0.6811386108398437, "step": 107260 }, { "epoch": 0.6376351564218248, "grad_norm": 1.6576048135757446, "learning_rate": 0.00019314412481827786, "loss": 0.6625555992126465, "step": 107270 }, { "epoch": 0.6376945984984932, "grad_norm": 1.7778172492980957, "learning_rate": 0.00019314174166308988, "loss": 0.6377249240875245, "step": 107280 }, { "epoch": 0.6377540405751615, "grad_norm": 1.9528541564941406, "learning_rate": 0.00019313935811017904, "loss": 0.646604347229004, "step": 107290 }, { "epoch": 0.6378134826518299, "grad_norm": 1.7423385381698608, "learning_rate": 0.00019313697415955668, "loss": 0.7275019645690918, "step": 107300 }, { "epoch": 0.6378729247284983, "grad_norm": 1.6568317413330078, "learning_rate": 0.00019313458981123417, "loss": 0.6832483291625977, "step": 107310 }, { "epoch": 0.6379323668051667, "grad_norm": 2.4279847145080566, "learning_rate": 0.000193132205065223, "loss": 0.8027206420898437, "step": 107320 }, { "epoch": 0.637991808881835, "grad_norm": 1.3111257553100586, "learning_rate": 0.00019312981992153448, "loss": 0.5824490547180176, "step": 107330 }, { "epoch": 0.6380512509585035, "grad_norm": 2.1005313396453857, "learning_rate": 0.00019312743438018007, "loss": 0.6533885955810547, "step": 107340 }, { "epoch": 0.6381106930351719, "grad_norm": 1.9213271141052246, "learning_rate": 0.0001931250484411712, "loss": 0.7189498901367187, "step": 107350 }, { "epoch": 0.6381701351118403, "grad_norm": 1.7493189573287964, "learning_rate": 0.00019312266210451924, "loss": 0.6704698085784913, "step": 107360 }, { "epoch": 0.6382295771885087, "grad_norm": 1.493732213973999, "learning_rate": 0.00019312027537023567, "loss": 0.6716100215911865, "step": 107370 }, { "epoch": 0.638289019265177, "grad_norm": 1.7556424140930176, "learning_rate": 0.00019311788823833185, "loss": 0.6346529960632324, "step": 107380 }, { "epoch": 0.6383484613418454, "grad_norm": 1.5760341882705688, "learning_rate": 0.00019311550070881918, "loss": 0.6533278942108154, "step": 107390 }, { "epoch": 0.6384079034185138, "grad_norm": 1.6197259426116943, "learning_rate": 0.00019311311278170915, "loss": 0.6872596740722656, "step": 107400 }, { "epoch": 0.6384673454951822, "grad_norm": 1.8911054134368896, "learning_rate": 0.00019311072445701318, "loss": 0.6072310924530029, "step": 107410 }, { "epoch": 0.6385267875718507, "grad_norm": 1.498822569847107, "learning_rate": 0.00019310833573474263, "loss": 0.6751961231231689, "step": 107420 }, { "epoch": 0.638586229648519, "grad_norm": 1.6249980926513672, "learning_rate": 0.00019310594661490894, "loss": 0.6185526847839355, "step": 107430 }, { "epoch": 0.6386456717251874, "grad_norm": 1.598299503326416, "learning_rate": 0.0001931035570975236, "loss": 0.6368463516235352, "step": 107440 }, { "epoch": 0.6387051138018558, "grad_norm": 2.120380401611328, "learning_rate": 0.000193101167182598, "loss": 0.7242128372192382, "step": 107450 }, { "epoch": 0.6387645558785242, "grad_norm": 1.6269927024841309, "learning_rate": 0.00019309877687014352, "loss": 0.68255615234375, "step": 107460 }, { "epoch": 0.6388239979551925, "grad_norm": 1.6917866468429565, "learning_rate": 0.0001930963861601717, "loss": 0.6197838306427002, "step": 107470 }, { "epoch": 0.6388834400318609, "grad_norm": 1.4039173126220703, "learning_rate": 0.00019309399505269392, "loss": 0.6671122550964356, "step": 107480 }, { "epoch": 0.6389428821085293, "grad_norm": 1.8320212364196777, "learning_rate": 0.00019309160354772162, "loss": 0.7255832195281983, "step": 107490 }, { "epoch": 0.6390023241851978, "grad_norm": 1.6456174850463867, "learning_rate": 0.00019308921164526625, "loss": 0.6532928943634033, "step": 107500 }, { "epoch": 0.6390617662618662, "grad_norm": 1.5858798027038574, "learning_rate": 0.00019308681934533922, "loss": 0.7131094455718994, "step": 107510 }, { "epoch": 0.6391212083385345, "grad_norm": 1.8322219848632812, "learning_rate": 0.00019308442664795204, "loss": 0.671848726272583, "step": 107520 }, { "epoch": 0.6391806504152029, "grad_norm": 1.7392650842666626, "learning_rate": 0.00019308203355311606, "loss": 0.6940816879272461, "step": 107530 }, { "epoch": 0.6392400924918713, "grad_norm": 1.7862626314163208, "learning_rate": 0.00019307964006084284, "loss": 0.695807933807373, "step": 107540 }, { "epoch": 0.6392995345685397, "grad_norm": 1.8898955583572388, "learning_rate": 0.00019307724617114374, "loss": 0.6784477233886719, "step": 107550 }, { "epoch": 0.6393589766452081, "grad_norm": 1.7351632118225098, "learning_rate": 0.00019307485188403022, "loss": 0.6749479293823242, "step": 107560 }, { "epoch": 0.6394184187218764, "grad_norm": 1.5310989618301392, "learning_rate": 0.00019307245719951381, "loss": 0.6594170570373535, "step": 107570 }, { "epoch": 0.6394778607985449, "grad_norm": 2.34798526763916, "learning_rate": 0.0001930700621176059, "loss": 0.7481893539428711, "step": 107580 }, { "epoch": 0.6395373028752133, "grad_norm": 1.2032842636108398, "learning_rate": 0.00019306766663831795, "loss": 0.6516446113586426, "step": 107590 }, { "epoch": 0.6395967449518817, "grad_norm": 1.4603068828582764, "learning_rate": 0.00019306527076166143, "loss": 0.6824065208435058, "step": 107600 }, { "epoch": 0.63965618702855, "grad_norm": 1.1596397161483765, "learning_rate": 0.0001930628744876478, "loss": 0.6505039691925049, "step": 107610 }, { "epoch": 0.6397156291052184, "grad_norm": 1.930840015411377, "learning_rate": 0.00019306047781628854, "loss": 0.6649574279785156, "step": 107620 }, { "epoch": 0.6397750711818868, "grad_norm": 1.372434139251709, "learning_rate": 0.00019305808074759507, "loss": 0.6746497631072998, "step": 107630 }, { "epoch": 0.6398345132585552, "grad_norm": 1.6338939666748047, "learning_rate": 0.0001930556832815789, "loss": 0.686865234375, "step": 107640 }, { "epoch": 0.6398939553352236, "grad_norm": 1.5902472734451294, "learning_rate": 0.00019305328541825148, "loss": 0.6594677448272706, "step": 107650 }, { "epoch": 0.6399533974118919, "grad_norm": 1.697452425956726, "learning_rate": 0.0001930508871576243, "loss": 0.682760763168335, "step": 107660 }, { "epoch": 0.6400128394885604, "grad_norm": 1.5719802379608154, "learning_rate": 0.0001930484884997088, "loss": 0.6900518417358399, "step": 107670 }, { "epoch": 0.6400722815652288, "grad_norm": 1.7034664154052734, "learning_rate": 0.00019304608944451646, "loss": 0.7284789085388184, "step": 107680 }, { "epoch": 0.6401317236418972, "grad_norm": 1.7819030284881592, "learning_rate": 0.0001930436899920588, "loss": 0.6892980575561524, "step": 107690 }, { "epoch": 0.6401911657185655, "grad_norm": 1.4827717542648315, "learning_rate": 0.00019304129014234724, "loss": 0.720662784576416, "step": 107700 }, { "epoch": 0.6402506077952339, "grad_norm": 1.5529139041900635, "learning_rate": 0.0001930388898953933, "loss": 0.6318163394927978, "step": 107710 }, { "epoch": 0.6403100498719023, "grad_norm": 1.7743929624557495, "learning_rate": 0.00019303648925120845, "loss": 0.6883224487304688, "step": 107720 }, { "epoch": 0.6403694919485707, "grad_norm": 1.6609987020492554, "learning_rate": 0.00019303408820980415, "loss": 0.6768485069274902, "step": 107730 }, { "epoch": 0.6404289340252391, "grad_norm": 1.373256802558899, "learning_rate": 0.00019303168677119192, "loss": 0.6109484672546387, "step": 107740 }, { "epoch": 0.6404883761019075, "grad_norm": 1.5080986022949219, "learning_rate": 0.00019302928493538326, "loss": 0.6910199165344239, "step": 107750 }, { "epoch": 0.6405478181785759, "grad_norm": 1.592891812324524, "learning_rate": 0.00019302688270238962, "loss": 0.6889778137207031, "step": 107760 }, { "epoch": 0.6406072602552443, "grad_norm": 1.732657551765442, "learning_rate": 0.00019302448007222248, "loss": 0.6855405330657959, "step": 107770 }, { "epoch": 0.6406667023319127, "grad_norm": 1.7612723112106323, "learning_rate": 0.0001930220770448934, "loss": 0.6460114479064941, "step": 107780 }, { "epoch": 0.6407261444085811, "grad_norm": 1.500159502029419, "learning_rate": 0.0001930196736204138, "loss": 0.66433744430542, "step": 107790 }, { "epoch": 0.6407855864852494, "grad_norm": 1.527444839477539, "learning_rate": 0.00019301726979879523, "loss": 0.6337149143218994, "step": 107800 }, { "epoch": 0.6408450285619178, "grad_norm": 1.4018338918685913, "learning_rate": 0.00019301486558004918, "loss": 0.6725611686706543, "step": 107810 }, { "epoch": 0.6409044706385862, "grad_norm": 1.397839903831482, "learning_rate": 0.00019301246096418712, "loss": 0.7077224731445313, "step": 107820 }, { "epoch": 0.6409639127152547, "grad_norm": 1.5897860527038574, "learning_rate": 0.0001930100559512206, "loss": 0.6386646747589111, "step": 107830 }, { "epoch": 0.641023354791923, "grad_norm": 1.801474690437317, "learning_rate": 0.0001930076505411611, "loss": 0.637464952468872, "step": 107840 }, { "epoch": 0.6410827968685914, "grad_norm": 1.8656188249588013, "learning_rate": 0.0001930052447340201, "loss": 0.7165984630584716, "step": 107850 }, { "epoch": 0.6411422389452598, "grad_norm": 1.4253548383712769, "learning_rate": 0.00019300283852980915, "loss": 0.6687802791595459, "step": 107860 }, { "epoch": 0.6412016810219282, "grad_norm": 1.5339947938919067, "learning_rate": 0.00019300043192853976, "loss": 0.6341190814971924, "step": 107870 }, { "epoch": 0.6412611230985966, "grad_norm": 2.0115201473236084, "learning_rate": 0.00019299802493022344, "loss": 0.690336036682129, "step": 107880 }, { "epoch": 0.6413205651752649, "grad_norm": 2.2294504642486572, "learning_rate": 0.00019299561753487166, "loss": 0.7199448585510254, "step": 107890 }, { "epoch": 0.6413800072519333, "grad_norm": 1.618971586227417, "learning_rate": 0.00019299320974249597, "loss": 0.6388100624084473, "step": 107900 }, { "epoch": 0.6414394493286018, "grad_norm": 1.4850819110870361, "learning_rate": 0.00019299080155310788, "loss": 0.6551810264587402, "step": 107910 }, { "epoch": 0.6414988914052702, "grad_norm": 1.396929144859314, "learning_rate": 0.00019298839296671896, "loss": 0.6510396480560303, "step": 107920 }, { "epoch": 0.6415583334819385, "grad_norm": 1.7333015203475952, "learning_rate": 0.00019298598398334067, "loss": 0.6776651859283447, "step": 107930 }, { "epoch": 0.6416177755586069, "grad_norm": 1.4360028505325317, "learning_rate": 0.00019298357460298453, "loss": 0.721718692779541, "step": 107940 }, { "epoch": 0.6416772176352753, "grad_norm": 2.9820759296417236, "learning_rate": 0.0001929811648256621, "loss": 0.6191473007202148, "step": 107950 }, { "epoch": 0.6417366597119437, "grad_norm": 1.992451548576355, "learning_rate": 0.0001929787546513849, "loss": 0.590656042098999, "step": 107960 }, { "epoch": 0.6417961017886121, "grad_norm": 1.4592602252960205, "learning_rate": 0.00019297634408016446, "loss": 0.6846967697143554, "step": 107970 }, { "epoch": 0.6418555438652804, "grad_norm": 1.8154163360595703, "learning_rate": 0.0001929739331120123, "loss": 0.720720911026001, "step": 107980 }, { "epoch": 0.6419149859419488, "grad_norm": 1.8017544746398926, "learning_rate": 0.00019297152174693998, "loss": 0.659857702255249, "step": 107990 }, { "epoch": 0.6419744280186173, "grad_norm": 1.6248170137405396, "learning_rate": 0.00019296910998495897, "loss": 0.673760986328125, "step": 108000 }, { "epoch": 0.6420338700952857, "grad_norm": 1.3411535024642944, "learning_rate": 0.0001929666978260809, "loss": 0.6484200477600097, "step": 108010 }, { "epoch": 0.6420933121719541, "grad_norm": 1.743564486503601, "learning_rate": 0.00019296428527031725, "loss": 0.7156981468200684, "step": 108020 }, { "epoch": 0.6421527542486224, "grad_norm": 1.9127025604248047, "learning_rate": 0.00019296187231767955, "loss": 0.6660025119781494, "step": 108030 }, { "epoch": 0.6422121963252908, "grad_norm": 1.684301495552063, "learning_rate": 0.0001929594589681794, "loss": 0.6867096900939942, "step": 108040 }, { "epoch": 0.6422716384019592, "grad_norm": 2.186884880065918, "learning_rate": 0.00019295704522182826, "loss": 0.6518235683441163, "step": 108050 }, { "epoch": 0.6423310804786276, "grad_norm": 1.8701343536376953, "learning_rate": 0.00019295463107863776, "loss": 0.6519968509674072, "step": 108060 }, { "epoch": 0.6423905225552959, "grad_norm": 1.677734136581421, "learning_rate": 0.00019295221653861942, "loss": 0.7564579486846924, "step": 108070 }, { "epoch": 0.6424499646319644, "grad_norm": 1.9324465990066528, "learning_rate": 0.00019294980160178477, "loss": 0.6895740509033204, "step": 108080 }, { "epoch": 0.6425094067086328, "grad_norm": 2.040719509124756, "learning_rate": 0.00019294738626814538, "loss": 0.7166141986846923, "step": 108090 }, { "epoch": 0.6425688487853012, "grad_norm": 1.8149244785308838, "learning_rate": 0.00019294497053771282, "loss": 0.6708113193511963, "step": 108100 }, { "epoch": 0.6426282908619696, "grad_norm": 1.5461729764938354, "learning_rate": 0.00019294255441049859, "loss": 0.6214017391204834, "step": 108110 }, { "epoch": 0.6426877329386379, "grad_norm": 1.7372950315475464, "learning_rate": 0.0001929401378865143, "loss": 0.6333958625793457, "step": 108120 }, { "epoch": 0.6427471750153063, "grad_norm": 1.7681758403778076, "learning_rate": 0.0001929377209657715, "loss": 0.682499361038208, "step": 108130 }, { "epoch": 0.6428066170919747, "grad_norm": 1.9176924228668213, "learning_rate": 0.00019293530364828177, "loss": 0.6417900085449219, "step": 108140 }, { "epoch": 0.6428660591686431, "grad_norm": 1.8275200128555298, "learning_rate": 0.00019293288593405663, "loss": 0.6856358528137207, "step": 108150 }, { "epoch": 0.6429255012453116, "grad_norm": 1.6739317178726196, "learning_rate": 0.00019293046782310766, "loss": 0.6435595512390136, "step": 108160 }, { "epoch": 0.6429849433219799, "grad_norm": 1.771302342414856, "learning_rate": 0.00019292804931544645, "loss": 0.6339255332946777, "step": 108170 }, { "epoch": 0.6430443853986483, "grad_norm": 2.0494813919067383, "learning_rate": 0.00019292563041108451, "loss": 0.6670383453369141, "step": 108180 }, { "epoch": 0.6431038274753167, "grad_norm": 1.8424406051635742, "learning_rate": 0.00019292321111003352, "loss": 0.616556453704834, "step": 108190 }, { "epoch": 0.6431632695519851, "grad_norm": 1.4243654012680054, "learning_rate": 0.00019292079141230496, "loss": 0.6638801574707032, "step": 108200 }, { "epoch": 0.6432227116286534, "grad_norm": 1.9551703929901123, "learning_rate": 0.0001929183713179104, "loss": 0.6917040824890137, "step": 108210 }, { "epoch": 0.6432821537053218, "grad_norm": 2.0414059162139893, "learning_rate": 0.0001929159508268615, "loss": 0.6008408546447754, "step": 108220 }, { "epoch": 0.6433415957819902, "grad_norm": 1.8184701204299927, "learning_rate": 0.0001929135299391698, "loss": 0.6275893211364746, "step": 108230 }, { "epoch": 0.6434010378586587, "grad_norm": 1.7611263990402222, "learning_rate": 0.0001929111086548468, "loss": 0.746083927154541, "step": 108240 }, { "epoch": 0.6434604799353271, "grad_norm": 1.5067731142044067, "learning_rate": 0.00019290868697390418, "loss": 0.6489086627960206, "step": 108250 }, { "epoch": 0.6435199220119954, "grad_norm": 1.5241847038269043, "learning_rate": 0.0001929062648963535, "loss": 0.6690690994262696, "step": 108260 }, { "epoch": 0.6435793640886638, "grad_norm": 1.702321171760559, "learning_rate": 0.00019290384242220637, "loss": 0.6396876335144043, "step": 108270 }, { "epoch": 0.6436388061653322, "grad_norm": 1.4650425910949707, "learning_rate": 0.0001929014195514743, "loss": 0.6906652450561523, "step": 108280 }, { "epoch": 0.6436982482420006, "grad_norm": 1.3610163927078247, "learning_rate": 0.00019289899628416896, "loss": 0.6437066555023193, "step": 108290 }, { "epoch": 0.6437576903186689, "grad_norm": 1.9906073808670044, "learning_rate": 0.00019289657262030191, "loss": 0.651770544052124, "step": 108300 }, { "epoch": 0.6438171323953373, "grad_norm": 1.942629098892212, "learning_rate": 0.00019289414855988476, "loss": 0.683651351928711, "step": 108310 }, { "epoch": 0.6438765744720057, "grad_norm": 1.2377891540527344, "learning_rate": 0.0001928917241029291, "loss": 0.6588086605072021, "step": 108320 }, { "epoch": 0.6439360165486742, "grad_norm": 1.8742316961288452, "learning_rate": 0.0001928892992494465, "loss": 0.6899081230163574, "step": 108330 }, { "epoch": 0.6439954586253426, "grad_norm": 1.5869413614273071, "learning_rate": 0.00019288687399944858, "loss": 0.6115521907806396, "step": 108340 }, { "epoch": 0.6440549007020109, "grad_norm": 1.486919641494751, "learning_rate": 0.00019288444835294696, "loss": 0.6734222412109375, "step": 108350 }, { "epoch": 0.6441143427786793, "grad_norm": 1.5745679140090942, "learning_rate": 0.00019288202230995322, "loss": 0.6263252258300781, "step": 108360 }, { "epoch": 0.6441737848553477, "grad_norm": 1.6720248460769653, "learning_rate": 0.00019287959587047896, "loss": 0.7020445346832276, "step": 108370 }, { "epoch": 0.6442332269320161, "grad_norm": 1.177681565284729, "learning_rate": 0.0001928771690345358, "loss": 0.6713521957397461, "step": 108380 }, { "epoch": 0.6442926690086845, "grad_norm": 1.5553126335144043, "learning_rate": 0.00019287474180213537, "loss": 0.7130475044250488, "step": 108390 }, { "epoch": 0.6443521110853528, "grad_norm": 1.687743902206421, "learning_rate": 0.0001928723141732892, "loss": 0.6944437503814698, "step": 108400 }, { "epoch": 0.6444115531620213, "grad_norm": 1.6518915891647339, "learning_rate": 0.00019286988614800903, "loss": 0.6270746231079102, "step": 108410 }, { "epoch": 0.6444709952386897, "grad_norm": 2.0039780139923096, "learning_rate": 0.0001928674577263064, "loss": 0.6840881824493408, "step": 108420 }, { "epoch": 0.6445304373153581, "grad_norm": 2.013465404510498, "learning_rate": 0.00019286502890819291, "loss": 0.7052037239074707, "step": 108430 }, { "epoch": 0.6445898793920264, "grad_norm": 1.8155245780944824, "learning_rate": 0.0001928625996936802, "loss": 0.7264186859130859, "step": 108440 }, { "epoch": 0.6446493214686948, "grad_norm": 1.8093364238739014, "learning_rate": 0.0001928601700827799, "loss": 0.7009681701660156, "step": 108450 }, { "epoch": 0.6447087635453632, "grad_norm": 1.0754846334457397, "learning_rate": 0.00019285774007550362, "loss": 0.6838538169860839, "step": 108460 }, { "epoch": 0.6447682056220316, "grad_norm": 1.806639552116394, "learning_rate": 0.00019285530967186302, "loss": 0.6788232803344727, "step": 108470 }, { "epoch": 0.6448276476987, "grad_norm": 1.8433468341827393, "learning_rate": 0.00019285287887186965, "loss": 0.7019051551818848, "step": 108480 }, { "epoch": 0.6448870897753683, "grad_norm": 1.6863564252853394, "learning_rate": 0.0001928504476755352, "loss": 0.6935886383056641, "step": 108490 }, { "epoch": 0.6449465318520368, "grad_norm": 1.9831082820892334, "learning_rate": 0.00019284801608287128, "loss": 0.7052891254425049, "step": 108500 }, { "epoch": 0.6450059739287052, "grad_norm": 1.505354642868042, "learning_rate": 0.00019284558409388955, "loss": 0.6409416198730469, "step": 108510 }, { "epoch": 0.6450654160053736, "grad_norm": 2.041038990020752, "learning_rate": 0.0001928431517086016, "loss": 0.7023691654205322, "step": 108520 }, { "epoch": 0.645124858082042, "grad_norm": 1.724708080291748, "learning_rate": 0.0001928407189270191, "loss": 0.6316548347473144, "step": 108530 }, { "epoch": 0.6451843001587103, "grad_norm": 1.8929189443588257, "learning_rate": 0.00019283828574915367, "loss": 0.7204341888427734, "step": 108540 }, { "epoch": 0.6452437422353787, "grad_norm": 1.3997260332107544, "learning_rate": 0.00019283585217501692, "loss": 0.6375179767608643, "step": 108550 }, { "epoch": 0.6453031843120471, "grad_norm": 1.4803045988082886, "learning_rate": 0.00019283341820462054, "loss": 0.638099479675293, "step": 108560 }, { "epoch": 0.6453626263887156, "grad_norm": 1.5578354597091675, "learning_rate": 0.00019283098383797618, "loss": 0.6890090465545654, "step": 108570 }, { "epoch": 0.6454220684653839, "grad_norm": 2.300445318222046, "learning_rate": 0.00019282854907509545, "loss": 0.6947840690612793, "step": 108580 }, { "epoch": 0.6454815105420523, "grad_norm": 1.7585270404815674, "learning_rate": 0.00019282611391599, "loss": 0.6724111080169678, "step": 108590 }, { "epoch": 0.6455409526187207, "grad_norm": 2.1373555660247803, "learning_rate": 0.0001928236783606715, "loss": 0.6943721771240234, "step": 108600 }, { "epoch": 0.6456003946953891, "grad_norm": 1.7613856792449951, "learning_rate": 0.0001928212424091516, "loss": 0.6986675262451172, "step": 108610 }, { "epoch": 0.6456598367720575, "grad_norm": 1.6911474466323853, "learning_rate": 0.00019281880606144197, "loss": 0.6355391502380371, "step": 108620 }, { "epoch": 0.6457192788487258, "grad_norm": 2.2732324600219727, "learning_rate": 0.00019281636931755416, "loss": 0.664350938796997, "step": 108630 }, { "epoch": 0.6457787209253942, "grad_norm": 1.5422996282577515, "learning_rate": 0.00019281393217749997, "loss": 0.6370219707489013, "step": 108640 }, { "epoch": 0.6458381630020626, "grad_norm": 1.702393651008606, "learning_rate": 0.00019281149464129096, "loss": 0.6793658256530761, "step": 108650 }, { "epoch": 0.6458976050787311, "grad_norm": 1.6178483963012695, "learning_rate": 0.00019280905670893882, "loss": 0.6673254013061524, "step": 108660 }, { "epoch": 0.6459570471553994, "grad_norm": 1.622509479522705, "learning_rate": 0.00019280661838045522, "loss": 0.6305397033691407, "step": 108670 }, { "epoch": 0.6460164892320678, "grad_norm": 2.060789108276367, "learning_rate": 0.00019280417965585183, "loss": 0.6599260807037354, "step": 108680 }, { "epoch": 0.6460759313087362, "grad_norm": 1.6234394311904907, "learning_rate": 0.0001928017405351403, "loss": 0.739939546585083, "step": 108690 }, { "epoch": 0.6461353733854046, "grad_norm": 1.73866868019104, "learning_rate": 0.0001927993010183323, "loss": 0.6297843933105469, "step": 108700 }, { "epoch": 0.646194815462073, "grad_norm": 1.7621030807495117, "learning_rate": 0.0001927968611054395, "loss": 0.6899624824523926, "step": 108710 }, { "epoch": 0.6462542575387413, "grad_norm": 1.6411300897598267, "learning_rate": 0.00019279442079647358, "loss": 0.6737335681915283, "step": 108720 }, { "epoch": 0.6463136996154097, "grad_norm": 1.6375428438186646, "learning_rate": 0.00019279198009144622, "loss": 0.6516045570373535, "step": 108730 }, { "epoch": 0.6463731416920782, "grad_norm": 2.414938449859619, "learning_rate": 0.00019278953899036906, "loss": 0.718421745300293, "step": 108740 }, { "epoch": 0.6464325837687466, "grad_norm": 1.9807466268539429, "learning_rate": 0.00019278709749325382, "loss": 0.6899232387542724, "step": 108750 }, { "epoch": 0.646492025845415, "grad_norm": 1.6043106317520142, "learning_rate": 0.00019278465560011214, "loss": 0.6476387023925781, "step": 108760 }, { "epoch": 0.6465514679220833, "grad_norm": 1.7262471914291382, "learning_rate": 0.00019278221331095574, "loss": 0.6516180038452148, "step": 108770 }, { "epoch": 0.6466109099987517, "grad_norm": 1.6062794923782349, "learning_rate": 0.0001927797706257963, "loss": 0.6809741020202636, "step": 108780 }, { "epoch": 0.6466703520754201, "grad_norm": 1.7768861055374146, "learning_rate": 0.00019277732754464545, "loss": 0.698748779296875, "step": 108790 }, { "epoch": 0.6467297941520885, "grad_norm": 1.643969178199768, "learning_rate": 0.00019277488406751494, "loss": 0.6349523544311524, "step": 108800 }, { "epoch": 0.6467892362287568, "grad_norm": 1.412494421005249, "learning_rate": 0.00019277244019441642, "loss": 0.6611394882202148, "step": 108810 }, { "epoch": 0.6468486783054253, "grad_norm": 2.0895252227783203, "learning_rate": 0.00019276999592536163, "loss": 0.6869730949401855, "step": 108820 }, { "epoch": 0.6469081203820937, "grad_norm": 1.50260591506958, "learning_rate": 0.00019276755126036222, "loss": 0.664919090270996, "step": 108830 }, { "epoch": 0.6469675624587621, "grad_norm": 2.183450222015381, "learning_rate": 0.00019276510619942988, "loss": 0.6768484115600586, "step": 108840 }, { "epoch": 0.6470270045354305, "grad_norm": 1.9394923448562622, "learning_rate": 0.0001927626607425763, "loss": 0.6454631805419921, "step": 108850 }, { "epoch": 0.6470864466120988, "grad_norm": 2.0008373260498047, "learning_rate": 0.0001927602148898132, "loss": 0.6379351615905762, "step": 108860 }, { "epoch": 0.6471458886887672, "grad_norm": 1.69191575050354, "learning_rate": 0.00019275776864115232, "loss": 0.6596047878265381, "step": 108870 }, { "epoch": 0.6472053307654356, "grad_norm": 1.7454243898391724, "learning_rate": 0.00019275532199660532, "loss": 0.6809132099151611, "step": 108880 }, { "epoch": 0.647264772842104, "grad_norm": 1.8760731220245361, "learning_rate": 0.0001927528749561839, "loss": 0.6777603149414062, "step": 108890 }, { "epoch": 0.6473242149187725, "grad_norm": 1.8685376644134521, "learning_rate": 0.0001927504275198997, "loss": 0.6472501754760742, "step": 108900 }, { "epoch": 0.6473836569954408, "grad_norm": 1.693142294883728, "learning_rate": 0.00019274797968776456, "loss": 0.6931267738342285, "step": 108910 }, { "epoch": 0.6474430990721092, "grad_norm": 1.8917639255523682, "learning_rate": 0.00019274553145979013, "loss": 0.6499737739562989, "step": 108920 }, { "epoch": 0.6475025411487776, "grad_norm": 1.646212100982666, "learning_rate": 0.0001927430828359881, "loss": 0.6776877403259277, "step": 108930 }, { "epoch": 0.647561983225446, "grad_norm": 1.9220799207687378, "learning_rate": 0.0001927406338163702, "loss": 0.6648642539978027, "step": 108940 }, { "epoch": 0.6476214253021143, "grad_norm": 1.9044228792190552, "learning_rate": 0.0001927381844009482, "loss": 0.7423915863037109, "step": 108950 }, { "epoch": 0.6476808673787827, "grad_norm": 1.4086170196533203, "learning_rate": 0.00019273573458973372, "loss": 0.6630577087402344, "step": 108960 }, { "epoch": 0.6477403094554511, "grad_norm": 2.239028215408325, "learning_rate": 0.00019273328438273852, "loss": 0.6944460868835449, "step": 108970 }, { "epoch": 0.6477997515321195, "grad_norm": 1.802884817123413, "learning_rate": 0.00019273083377997432, "loss": 0.6389184951782226, "step": 108980 }, { "epoch": 0.647859193608788, "grad_norm": 1.9881231784820557, "learning_rate": 0.00019272838278145286, "loss": 0.6831369400024414, "step": 108990 }, { "epoch": 0.6479186356854563, "grad_norm": 1.9059386253356934, "learning_rate": 0.00019272593138718584, "loss": 0.6627975940704346, "step": 109000 }, { "epoch": 0.6479780777621247, "grad_norm": 1.8200159072875977, "learning_rate": 0.00019272347959718502, "loss": 0.6937455177307129, "step": 109010 }, { "epoch": 0.6480375198387931, "grad_norm": 2.295001745223999, "learning_rate": 0.0001927210274114621, "loss": 0.684870433807373, "step": 109020 }, { "epoch": 0.6480969619154615, "grad_norm": 2.07234263420105, "learning_rate": 0.00019271857483002883, "loss": 0.6546826362609863, "step": 109030 }, { "epoch": 0.6481564039921298, "grad_norm": 1.6589796543121338, "learning_rate": 0.00019271612185289692, "loss": 0.6444550037384034, "step": 109040 }, { "epoch": 0.6482158460687982, "grad_norm": 1.617187738418579, "learning_rate": 0.0001927136684800781, "loss": 0.6949297904968261, "step": 109050 }, { "epoch": 0.6482752881454666, "grad_norm": 1.557305097579956, "learning_rate": 0.00019271121471158413, "loss": 0.7051356315612793, "step": 109060 }, { "epoch": 0.6483347302221351, "grad_norm": 1.592544674873352, "learning_rate": 0.00019270876054742675, "loss": 0.6297344207763672, "step": 109070 }, { "epoch": 0.6483941722988035, "grad_norm": 1.8679728507995605, "learning_rate": 0.00019270630598761768, "loss": 0.6562269687652588, "step": 109080 }, { "epoch": 0.6484536143754718, "grad_norm": 1.7720873355865479, "learning_rate": 0.0001927038510321687, "loss": 0.7345837593078614, "step": 109090 }, { "epoch": 0.6485130564521402, "grad_norm": 1.681280493736267, "learning_rate": 0.0001927013956810915, "loss": 0.6654481887817383, "step": 109100 }, { "epoch": 0.6485724985288086, "grad_norm": 1.2963296175003052, "learning_rate": 0.00019269893993439786, "loss": 0.6651158809661866, "step": 109110 }, { "epoch": 0.648631940605477, "grad_norm": 1.7331790924072266, "learning_rate": 0.0001926964837920995, "loss": 0.6806543350219727, "step": 109120 }, { "epoch": 0.6486913826821454, "grad_norm": 2.183537483215332, "learning_rate": 0.00019269402725420818, "loss": 0.6731030941009521, "step": 109130 }, { "epoch": 0.6487508247588137, "grad_norm": 1.5896527767181396, "learning_rate": 0.00019269157032073567, "loss": 0.7141522407531739, "step": 109140 }, { "epoch": 0.6488102668354822, "grad_norm": 1.9640216827392578, "learning_rate": 0.00019268911299169373, "loss": 0.6930888175964356, "step": 109150 }, { "epoch": 0.6488697089121506, "grad_norm": 1.755336880683899, "learning_rate": 0.00019268665526709408, "loss": 0.7164399147033691, "step": 109160 }, { "epoch": 0.648929150988819, "grad_norm": 2.041090726852417, "learning_rate": 0.0001926841971469485, "loss": 0.6969473838806153, "step": 109170 }, { "epoch": 0.6489885930654873, "grad_norm": 1.5858231782913208, "learning_rate": 0.0001926817386312687, "loss": 0.6441596031188965, "step": 109180 }, { "epoch": 0.6490480351421557, "grad_norm": 1.5342504978179932, "learning_rate": 0.00019267927972006652, "loss": 0.6893390655517578, "step": 109190 }, { "epoch": 0.6491074772188241, "grad_norm": 2.4553046226501465, "learning_rate": 0.00019267682041335368, "loss": 0.6548242568969727, "step": 109200 }, { "epoch": 0.6491669192954925, "grad_norm": 1.6727176904678345, "learning_rate": 0.00019267436071114196, "loss": 0.7171920776367188, "step": 109210 }, { "epoch": 0.6492263613721609, "grad_norm": 1.5000561475753784, "learning_rate": 0.00019267190061344311, "loss": 0.6211936950683594, "step": 109220 }, { "epoch": 0.6492858034488292, "grad_norm": 1.6615667343139648, "learning_rate": 0.00019266944012026892, "loss": 0.6589120864868164, "step": 109230 }, { "epoch": 0.6493452455254977, "grad_norm": 1.880406379699707, "learning_rate": 0.00019266697923163114, "loss": 0.6755038261413574, "step": 109240 }, { "epoch": 0.6494046876021661, "grad_norm": 1.9196147918701172, "learning_rate": 0.00019266451794754152, "loss": 0.624931001663208, "step": 109250 }, { "epoch": 0.6494641296788345, "grad_norm": 1.484898328781128, "learning_rate": 0.0001926620562680119, "loss": 0.6686104774475098, "step": 109260 }, { "epoch": 0.6495235717555029, "grad_norm": 1.7886384725570679, "learning_rate": 0.000192659594193054, "loss": 0.768471622467041, "step": 109270 }, { "epoch": 0.6495830138321712, "grad_norm": 1.7672810554504395, "learning_rate": 0.00019265713172267958, "loss": 0.7182169437408448, "step": 109280 }, { "epoch": 0.6496424559088396, "grad_norm": 1.4467252492904663, "learning_rate": 0.0001926546688569005, "loss": 0.7104556560516357, "step": 109290 }, { "epoch": 0.649701897985508, "grad_norm": 1.7129822969436646, "learning_rate": 0.00019265220559572848, "loss": 0.6226113319396973, "step": 109300 }, { "epoch": 0.6497613400621765, "grad_norm": 1.9944478273391724, "learning_rate": 0.00019264974193917533, "loss": 0.7220522880554199, "step": 109310 }, { "epoch": 0.6498207821388448, "grad_norm": 1.5120021104812622, "learning_rate": 0.00019264727788725281, "loss": 0.6596523284912109, "step": 109320 }, { "epoch": 0.6498802242155132, "grad_norm": 1.4829418659210205, "learning_rate": 0.00019264481343997275, "loss": 0.660935926437378, "step": 109330 }, { "epoch": 0.6499396662921816, "grad_norm": 1.762327790260315, "learning_rate": 0.00019264234859734687, "loss": 0.7327749252319335, "step": 109340 }, { "epoch": 0.64999910836885, "grad_norm": 1.7548465728759766, "learning_rate": 0.00019263988335938703, "loss": 0.7121092796325683, "step": 109350 }, { "epoch": 0.6500585504455184, "grad_norm": 2.0288784503936768, "learning_rate": 0.000192637417726105, "loss": 0.6914413452148438, "step": 109360 }, { "epoch": 0.6501179925221867, "grad_norm": 2.0392251014709473, "learning_rate": 0.00019263495169751256, "loss": 0.7385795593261719, "step": 109370 }, { "epoch": 0.6501774345988551, "grad_norm": 1.6746128797531128, "learning_rate": 0.0001926324852736215, "loss": 0.6068912506103515, "step": 109380 }, { "epoch": 0.6502368766755235, "grad_norm": 1.894730806350708, "learning_rate": 0.00019263001845444365, "loss": 0.6347012519836426, "step": 109390 }, { "epoch": 0.650296318752192, "grad_norm": 1.3522706031799316, "learning_rate": 0.0001926275512399908, "loss": 0.6843766689300537, "step": 109400 }, { "epoch": 0.6503557608288603, "grad_norm": 1.4074167013168335, "learning_rate": 0.00019262508363027472, "loss": 0.6111555576324463, "step": 109410 }, { "epoch": 0.6504152029055287, "grad_norm": 1.4156137704849243, "learning_rate": 0.00019262261562530728, "loss": 0.669338607788086, "step": 109420 }, { "epoch": 0.6504746449821971, "grad_norm": 1.6775572299957275, "learning_rate": 0.00019262014722510023, "loss": 0.659113597869873, "step": 109430 }, { "epoch": 0.6505340870588655, "grad_norm": 1.6569026708602905, "learning_rate": 0.0001926176784296654, "loss": 0.6641369819641113, "step": 109440 }, { "epoch": 0.6505935291355339, "grad_norm": 1.736319899559021, "learning_rate": 0.00019261520923901458, "loss": 0.7110393524169922, "step": 109450 }, { "epoch": 0.6506529712122022, "grad_norm": 1.8447121381759644, "learning_rate": 0.0001926127396531596, "loss": 0.7228188037872314, "step": 109460 }, { "epoch": 0.6507124132888706, "grad_norm": 2.151242256164551, "learning_rate": 0.00019261026967211232, "loss": 0.7374122619628907, "step": 109470 }, { "epoch": 0.650771855365539, "grad_norm": 1.7328126430511475, "learning_rate": 0.00019260779929588446, "loss": 0.6925270557403564, "step": 109480 }, { "epoch": 0.6508312974422075, "grad_norm": 2.0695791244506836, "learning_rate": 0.0001926053285244879, "loss": 0.6850133419036866, "step": 109490 }, { "epoch": 0.6508907395188759, "grad_norm": 1.3545721769332886, "learning_rate": 0.00019260285735793445, "loss": 0.6676860809326172, "step": 109500 }, { "epoch": 0.6509501815955442, "grad_norm": 1.5235882997512817, "learning_rate": 0.0001926003857962359, "loss": 0.6711226463317871, "step": 109510 }, { "epoch": 0.6510096236722126, "grad_norm": 1.8009287118911743, "learning_rate": 0.0001925979138394041, "loss": 0.7564817428588867, "step": 109520 }, { "epoch": 0.651069065748881, "grad_norm": 1.8023594617843628, "learning_rate": 0.0001925954414874509, "loss": 0.6687666893005371, "step": 109530 }, { "epoch": 0.6511285078255494, "grad_norm": 1.989747166633606, "learning_rate": 0.00019259296874038807, "loss": 0.6472835540771484, "step": 109540 }, { "epoch": 0.6511879499022177, "grad_norm": 2.2653274536132812, "learning_rate": 0.00019259049559822752, "loss": 0.6686594963073731, "step": 109550 }, { "epoch": 0.6512473919788861, "grad_norm": 1.4465159177780151, "learning_rate": 0.00019258802206098096, "loss": 0.6936881065368652, "step": 109560 }, { "epoch": 0.6513068340555546, "grad_norm": 1.7126396894454956, "learning_rate": 0.00019258554812866035, "loss": 0.6077075004577637, "step": 109570 }, { "epoch": 0.651366276132223, "grad_norm": 1.9133002758026123, "learning_rate": 0.00019258307380127745, "loss": 0.6643310546875, "step": 109580 }, { "epoch": 0.6514257182088914, "grad_norm": 1.6419376134872437, "learning_rate": 0.00019258059907884413, "loss": 0.6781899452209472, "step": 109590 }, { "epoch": 0.6514851602855597, "grad_norm": 1.806835651397705, "learning_rate": 0.00019257812396137217, "loss": 0.6677538871765136, "step": 109600 }, { "epoch": 0.6515446023622281, "grad_norm": 1.7549220323562622, "learning_rate": 0.0001925756484488735, "loss": 0.706535530090332, "step": 109610 }, { "epoch": 0.6516040444388965, "grad_norm": 1.2339198589324951, "learning_rate": 0.00019257317254135986, "loss": 0.6190090656280518, "step": 109620 }, { "epoch": 0.6516634865155649, "grad_norm": 1.8742672204971313, "learning_rate": 0.0001925706962388432, "loss": 0.6562754154205322, "step": 109630 }, { "epoch": 0.6517229285922334, "grad_norm": 1.5493019819259644, "learning_rate": 0.00019256821954133528, "loss": 0.7491003036499023, "step": 109640 }, { "epoch": 0.6517823706689017, "grad_norm": 1.5768697261810303, "learning_rate": 0.00019256574244884796, "loss": 0.6883163452148438, "step": 109650 }, { "epoch": 0.6518418127455701, "grad_norm": 1.4675112962722778, "learning_rate": 0.00019256326496139316, "loss": 0.6514121055603027, "step": 109660 }, { "epoch": 0.6519012548222385, "grad_norm": 1.6528700590133667, "learning_rate": 0.00019256078707898265, "loss": 0.6300980567932128, "step": 109670 }, { "epoch": 0.6519606968989069, "grad_norm": 1.6672283411026, "learning_rate": 0.00019255830880162835, "loss": 0.6310752391815185, "step": 109680 }, { "epoch": 0.6520201389755752, "grad_norm": 1.7884235382080078, "learning_rate": 0.00019255583012934207, "loss": 0.6590925216674804, "step": 109690 }, { "epoch": 0.6520795810522436, "grad_norm": 1.5820887088775635, "learning_rate": 0.00019255335106213564, "loss": 0.6855056762695313, "step": 109700 }, { "epoch": 0.652139023128912, "grad_norm": 1.4800704717636108, "learning_rate": 0.00019255087160002102, "loss": 0.6131677627563477, "step": 109710 }, { "epoch": 0.6521984652055804, "grad_norm": 1.4992797374725342, "learning_rate": 0.00019254839174300993, "loss": 0.6821611404418946, "step": 109720 }, { "epoch": 0.6522579072822489, "grad_norm": 1.9631850719451904, "learning_rate": 0.00019254591149111438, "loss": 0.656467866897583, "step": 109730 }, { "epoch": 0.6523173493589172, "grad_norm": 1.5624943971633911, "learning_rate": 0.0001925434308443461, "loss": 0.655586051940918, "step": 109740 }, { "epoch": 0.6523767914355856, "grad_norm": 1.9672977924346924, "learning_rate": 0.00019254094980271708, "loss": 0.7977983474731445, "step": 109750 }, { "epoch": 0.652436233512254, "grad_norm": 1.839065432548523, "learning_rate": 0.00019253846836623912, "loss": 0.6637982368469239, "step": 109760 }, { "epoch": 0.6524956755889224, "grad_norm": 1.9451833963394165, "learning_rate": 0.00019253598653492412, "loss": 0.6774243354797364, "step": 109770 }, { "epoch": 0.6525551176655907, "grad_norm": 1.5868269205093384, "learning_rate": 0.0001925335043087839, "loss": 0.7016641616821289, "step": 109780 }, { "epoch": 0.6526145597422591, "grad_norm": 1.8440449237823486, "learning_rate": 0.00019253102168783037, "loss": 0.6566600799560547, "step": 109790 }, { "epoch": 0.6526740018189275, "grad_norm": 1.7867332696914673, "learning_rate": 0.00019252853867207542, "loss": 0.695919132232666, "step": 109800 }, { "epoch": 0.652733443895596, "grad_norm": 1.8648818731307983, "learning_rate": 0.00019252605526153086, "loss": 0.7098280429840088, "step": 109810 }, { "epoch": 0.6527928859722644, "grad_norm": 2.0999348163604736, "learning_rate": 0.0001925235714562087, "loss": 0.6765668392181396, "step": 109820 }, { "epoch": 0.6528523280489327, "grad_norm": 1.5383458137512207, "learning_rate": 0.0001925210872561207, "loss": 0.6838635444641114, "step": 109830 }, { "epoch": 0.6529117701256011, "grad_norm": 1.714263916015625, "learning_rate": 0.0001925186026612788, "loss": 0.6526905536651612, "step": 109840 }, { "epoch": 0.6529712122022695, "grad_norm": 1.6438255310058594, "learning_rate": 0.00019251611767169484, "loss": 0.6561866760253906, "step": 109850 }, { "epoch": 0.6530306542789379, "grad_norm": 2.126082420349121, "learning_rate": 0.00019251363228738077, "loss": 0.7226287364959717, "step": 109860 }, { "epoch": 0.6530900963556063, "grad_norm": 1.2895222902297974, "learning_rate": 0.00019251114650834845, "loss": 0.6991462230682373, "step": 109870 }, { "epoch": 0.6531495384322746, "grad_norm": 1.5831838846206665, "learning_rate": 0.00019250866033460978, "loss": 0.6570465087890625, "step": 109880 }, { "epoch": 0.653208980508943, "grad_norm": 1.844439148902893, "learning_rate": 0.0001925061737661766, "loss": 0.652469253540039, "step": 109890 }, { "epoch": 0.6532684225856115, "grad_norm": 1.4083243608474731, "learning_rate": 0.00019250368680306088, "loss": 0.6542903423309326, "step": 109900 }, { "epoch": 0.6533278646622799, "grad_norm": 1.7904542684555054, "learning_rate": 0.00019250119944527448, "loss": 0.7334825038909912, "step": 109910 }, { "epoch": 0.6533873067389482, "grad_norm": 1.872451901435852, "learning_rate": 0.0001924987116928293, "loss": 0.6589468002319336, "step": 109920 }, { "epoch": 0.6534467488156166, "grad_norm": 1.5122350454330444, "learning_rate": 0.00019249622354573724, "loss": 0.7459455490112304, "step": 109930 }, { "epoch": 0.653506190892285, "grad_norm": 1.7059893608093262, "learning_rate": 0.00019249373500401025, "loss": 0.6785564422607422, "step": 109940 }, { "epoch": 0.6535656329689534, "grad_norm": 1.7575035095214844, "learning_rate": 0.00019249124606766013, "loss": 0.6868174552917481, "step": 109950 }, { "epoch": 0.6536250750456218, "grad_norm": 1.725413203239441, "learning_rate": 0.00019248875673669885, "loss": 0.7035569667816162, "step": 109960 }, { "epoch": 0.6536845171222901, "grad_norm": 1.519208550453186, "learning_rate": 0.00019248626701113836, "loss": 0.7071460723876953, "step": 109970 }, { "epoch": 0.6537439591989586, "grad_norm": 1.8108246326446533, "learning_rate": 0.0001924837768909905, "loss": 0.6873450756072998, "step": 109980 }, { "epoch": 0.653803401275627, "grad_norm": 1.5841057300567627, "learning_rate": 0.0001924812863762672, "loss": 0.6565109729766846, "step": 109990 }, { "epoch": 0.6538628433522954, "grad_norm": 1.475210189819336, "learning_rate": 0.00019247879546698042, "loss": 0.6544939041137695, "step": 110000 }, { "epoch": 0.6539222854289638, "grad_norm": 1.9928659200668335, "learning_rate": 0.00019247630416314198, "loss": 0.6706242084503173, "step": 110010 }, { "epoch": 0.6539817275056321, "grad_norm": 2.136584520339966, "learning_rate": 0.00019247381246476387, "loss": 0.6408250808715821, "step": 110020 }, { "epoch": 0.6540411695823005, "grad_norm": 1.8283307552337646, "learning_rate": 0.00019247132037185805, "loss": 0.7388760089874268, "step": 110030 }, { "epoch": 0.6541006116589689, "grad_norm": 1.5271520614624023, "learning_rate": 0.00019246882788443633, "loss": 0.685765552520752, "step": 110040 }, { "epoch": 0.6541600537356373, "grad_norm": 1.683013677597046, "learning_rate": 0.0001924663350025107, "loss": 0.6874583721160888, "step": 110050 }, { "epoch": 0.6542194958123057, "grad_norm": 1.517911672592163, "learning_rate": 0.00019246384172609307, "loss": 0.6384764671325683, "step": 110060 }, { "epoch": 0.6542789378889741, "grad_norm": 1.3060243129730225, "learning_rate": 0.00019246134805519537, "loss": 0.6555487632751464, "step": 110070 }, { "epoch": 0.6543383799656425, "grad_norm": 1.474358320236206, "learning_rate": 0.00019245885398982952, "loss": 0.6769781112670898, "step": 110080 }, { "epoch": 0.6543978220423109, "grad_norm": 2.262406349182129, "learning_rate": 0.0001924563595300075, "loss": 0.5885406017303467, "step": 110090 }, { "epoch": 0.6544572641189793, "grad_norm": 1.7775126695632935, "learning_rate": 0.00019245386467574117, "loss": 0.6482490539550781, "step": 110100 }, { "epoch": 0.6545167061956476, "grad_norm": 2.298139810562134, "learning_rate": 0.0001924513694270425, "loss": 0.6886526584625244, "step": 110110 }, { "epoch": 0.654576148272316, "grad_norm": 1.497170329093933, "learning_rate": 0.00019244887378392343, "loss": 0.7230215072631836, "step": 110120 }, { "epoch": 0.6546355903489844, "grad_norm": 1.757172703742981, "learning_rate": 0.00019244637774639588, "loss": 0.6767542362213135, "step": 110130 }, { "epoch": 0.6546950324256529, "grad_norm": 1.71788489818573, "learning_rate": 0.00019244388131447183, "loss": 0.6801338195800781, "step": 110140 }, { "epoch": 0.6547544745023212, "grad_norm": 1.7746686935424805, "learning_rate": 0.0001924413844881632, "loss": 0.7501667976379395, "step": 110150 }, { "epoch": 0.6548139165789896, "grad_norm": 2.060685157775879, "learning_rate": 0.00019243888726748186, "loss": 0.6563398361206054, "step": 110160 }, { "epoch": 0.654873358655658, "grad_norm": 1.686370611190796, "learning_rate": 0.00019243638965243988, "loss": 0.7210197448730469, "step": 110170 }, { "epoch": 0.6549328007323264, "grad_norm": 1.3161767721176147, "learning_rate": 0.00019243389164304918, "loss": 0.6525162696838379, "step": 110180 }, { "epoch": 0.6549922428089948, "grad_norm": 2.1193745136260986, "learning_rate": 0.00019243139323932163, "loss": 0.6537458419799804, "step": 110190 }, { "epoch": 0.6550516848856631, "grad_norm": 1.5459879636764526, "learning_rate": 0.00019242889444126925, "loss": 0.707623291015625, "step": 110200 }, { "epoch": 0.6551111269623315, "grad_norm": 1.7011723518371582, "learning_rate": 0.000192426395248904, "loss": 0.7139184951782227, "step": 110210 }, { "epoch": 0.655170569039, "grad_norm": 1.8007454872131348, "learning_rate": 0.0001924238956622378, "loss": 0.6597535133361816, "step": 110220 }, { "epoch": 0.6552300111156684, "grad_norm": 1.683081030845642, "learning_rate": 0.00019242139568128257, "loss": 0.6635262489318847, "step": 110230 }, { "epoch": 0.6552894531923368, "grad_norm": 1.5165587663650513, "learning_rate": 0.00019241889530605035, "loss": 0.6809998035430909, "step": 110240 }, { "epoch": 0.6553488952690051, "grad_norm": 1.9175753593444824, "learning_rate": 0.00019241639453655308, "loss": 0.6892835617065429, "step": 110250 }, { "epoch": 0.6554083373456735, "grad_norm": 1.5587306022644043, "learning_rate": 0.0001924138933728027, "loss": 0.6540637016296387, "step": 110260 }, { "epoch": 0.6554677794223419, "grad_norm": 1.9485807418823242, "learning_rate": 0.00019241139181481123, "loss": 0.7040513515472412, "step": 110270 }, { "epoch": 0.6555272214990103, "grad_norm": 1.320748209953308, "learning_rate": 0.00019240888986259055, "loss": 0.6445494174957276, "step": 110280 }, { "epoch": 0.6555866635756786, "grad_norm": 2.000633716583252, "learning_rate": 0.00019240638751615269, "loss": 0.6203089714050293, "step": 110290 }, { "epoch": 0.655646105652347, "grad_norm": 1.8949193954467773, "learning_rate": 0.0001924038847755096, "loss": 0.6983415603637695, "step": 110300 }, { "epoch": 0.6557055477290155, "grad_norm": 1.3310433626174927, "learning_rate": 0.00019240138164067325, "loss": 0.66278076171875, "step": 110310 }, { "epoch": 0.6557649898056839, "grad_norm": 1.3922027349472046, "learning_rate": 0.0001923988781116556, "loss": 0.6711583137512207, "step": 110320 }, { "epoch": 0.6558244318823523, "grad_norm": 1.8566806316375732, "learning_rate": 0.00019239637418846868, "loss": 0.6653860092163086, "step": 110330 }, { "epoch": 0.6558838739590206, "grad_norm": 1.5159438848495483, "learning_rate": 0.00019239386987112442, "loss": 0.6252701759338379, "step": 110340 }, { "epoch": 0.655943316035689, "grad_norm": 1.350458025932312, "learning_rate": 0.0001923913651596348, "loss": 0.6500801086425781, "step": 110350 }, { "epoch": 0.6560027581123574, "grad_norm": 2.1178696155548096, "learning_rate": 0.00019238886005401186, "loss": 0.6538921356201172, "step": 110360 }, { "epoch": 0.6560622001890258, "grad_norm": 2.1233372688293457, "learning_rate": 0.0001923863545542675, "loss": 0.6464145183563232, "step": 110370 }, { "epoch": 0.6561216422656942, "grad_norm": 1.7194077968597412, "learning_rate": 0.00019238384866041372, "loss": 0.7072924137115478, "step": 110380 }, { "epoch": 0.6561810843423626, "grad_norm": 1.6543980836868286, "learning_rate": 0.0001923813423724626, "loss": 0.7127506256103515, "step": 110390 }, { "epoch": 0.656240526419031, "grad_norm": 1.6473644971847534, "learning_rate": 0.000192378835690426, "loss": 0.6810277938842774, "step": 110400 }, { "epoch": 0.6562999684956994, "grad_norm": 2.1846764087677, "learning_rate": 0.000192376328614316, "loss": 0.6874428749084472, "step": 110410 }, { "epoch": 0.6563594105723678, "grad_norm": 1.546271562576294, "learning_rate": 0.00019237382114414457, "loss": 0.7063354969024658, "step": 110420 }, { "epoch": 0.6564188526490361, "grad_norm": 1.5259771347045898, "learning_rate": 0.00019237131327992367, "loss": 0.6492549896240234, "step": 110430 }, { "epoch": 0.6564782947257045, "grad_norm": 1.7290937900543213, "learning_rate": 0.00019236880502166535, "loss": 0.7015170574188232, "step": 110440 }, { "epoch": 0.6565377368023729, "grad_norm": 1.3997806310653687, "learning_rate": 0.00019236629636938159, "loss": 0.6962876319885254, "step": 110450 }, { "epoch": 0.6565971788790413, "grad_norm": 1.2738368511199951, "learning_rate": 0.00019236378732308436, "loss": 0.6589527130126953, "step": 110460 }, { "epoch": 0.6566566209557098, "grad_norm": 1.3708900213241577, "learning_rate": 0.0001923612778827857, "loss": 0.6399149417877197, "step": 110470 }, { "epoch": 0.6567160630323781, "grad_norm": 1.9419556856155396, "learning_rate": 0.0001923587680484976, "loss": 0.6618844985961914, "step": 110480 }, { "epoch": 0.6567755051090465, "grad_norm": 2.066103219985962, "learning_rate": 0.0001923562578202321, "loss": 0.6890982627868653, "step": 110490 }, { "epoch": 0.6568349471857149, "grad_norm": 1.4626520872116089, "learning_rate": 0.00019235374719800115, "loss": 0.6271496772766113, "step": 110500 }, { "epoch": 0.6568943892623833, "grad_norm": 1.8845466375350952, "learning_rate": 0.0001923512361818168, "loss": 0.6197689533233642, "step": 110510 }, { "epoch": 0.6569538313390516, "grad_norm": 1.6112123727798462, "learning_rate": 0.00019234872477169102, "loss": 0.6427226066589355, "step": 110520 }, { "epoch": 0.65701327341572, "grad_norm": 1.7180869579315186, "learning_rate": 0.00019234621296763585, "loss": 0.6772653579711914, "step": 110530 }, { "epoch": 0.6570727154923884, "grad_norm": 2.16363787651062, "learning_rate": 0.00019234370076966334, "loss": 0.656278133392334, "step": 110540 }, { "epoch": 0.6571321575690569, "grad_norm": 1.6518676280975342, "learning_rate": 0.00019234118817778545, "loss": 0.6498517990112305, "step": 110550 }, { "epoch": 0.6571915996457253, "grad_norm": 1.9383054971694946, "learning_rate": 0.00019233867519201427, "loss": 0.6613625526428223, "step": 110560 }, { "epoch": 0.6572510417223936, "grad_norm": 1.7965195178985596, "learning_rate": 0.00019233616181236175, "loss": 0.7002358436584473, "step": 110570 }, { "epoch": 0.657310483799062, "grad_norm": 1.4671448469161987, "learning_rate": 0.00019233364803883992, "loss": 0.6547471523284912, "step": 110580 }, { "epoch": 0.6573699258757304, "grad_norm": 1.5864777565002441, "learning_rate": 0.00019233113387146083, "loss": 0.6483297348022461, "step": 110590 }, { "epoch": 0.6574293679523988, "grad_norm": 1.6161571741104126, "learning_rate": 0.00019232861931023652, "loss": 0.6517666816711426, "step": 110600 }, { "epoch": 0.6574888100290672, "grad_norm": 1.7811070680618286, "learning_rate": 0.00019232610435517903, "loss": 0.7146951675415039, "step": 110610 }, { "epoch": 0.6575482521057355, "grad_norm": 1.7612707614898682, "learning_rate": 0.0001923235890063003, "loss": 0.6807280063629151, "step": 110620 }, { "epoch": 0.657607694182404, "grad_norm": 1.841681718826294, "learning_rate": 0.00019232107326361245, "loss": 0.6781167984008789, "step": 110630 }, { "epoch": 0.6576671362590724, "grad_norm": 1.6945730447769165, "learning_rate": 0.00019231855712712747, "loss": 0.6641746997833252, "step": 110640 }, { "epoch": 0.6577265783357408, "grad_norm": 1.5790679454803467, "learning_rate": 0.00019231604059685744, "loss": 0.6467955112457275, "step": 110650 }, { "epoch": 0.6577860204124091, "grad_norm": 1.4412484169006348, "learning_rate": 0.00019231352367281437, "loss": 0.6872986316680908, "step": 110660 }, { "epoch": 0.6578454624890775, "grad_norm": 2.3111491203308105, "learning_rate": 0.00019231100635501032, "loss": 0.710207462310791, "step": 110670 }, { "epoch": 0.6579049045657459, "grad_norm": 1.3423634767532349, "learning_rate": 0.00019230848864345727, "loss": 0.6897178649902344, "step": 110680 }, { "epoch": 0.6579643466424143, "grad_norm": 1.5756216049194336, "learning_rate": 0.0001923059705381673, "loss": 0.6759202003479003, "step": 110690 }, { "epoch": 0.6580237887190827, "grad_norm": 1.4145865440368652, "learning_rate": 0.00019230345203915253, "loss": 0.6340154647827149, "step": 110700 }, { "epoch": 0.658083230795751, "grad_norm": 1.773237705230713, "learning_rate": 0.0001923009331464249, "loss": 0.6413670539855957, "step": 110710 }, { "epoch": 0.6581426728724195, "grad_norm": 1.5675562620162964, "learning_rate": 0.0001922984138599965, "loss": 0.6602304935455322, "step": 110720 }, { "epoch": 0.6582021149490879, "grad_norm": 1.4401214122772217, "learning_rate": 0.0001922958941798794, "loss": 0.6951864242553711, "step": 110730 }, { "epoch": 0.6582615570257563, "grad_norm": 1.7060253620147705, "learning_rate": 0.00019229337410608564, "loss": 0.6913529396057129, "step": 110740 }, { "epoch": 0.6583209991024247, "grad_norm": 1.8459380865097046, "learning_rate": 0.00019229085363862728, "loss": 0.695546817779541, "step": 110750 }, { "epoch": 0.658380441179093, "grad_norm": 1.4456228017807007, "learning_rate": 0.00019228833277751636, "loss": 0.6875739097595215, "step": 110760 }, { "epoch": 0.6584398832557614, "grad_norm": 1.7581394910812378, "learning_rate": 0.00019228581152276491, "loss": 0.6785977363586426, "step": 110770 }, { "epoch": 0.6584993253324298, "grad_norm": 1.7561776638031006, "learning_rate": 0.00019228328987438506, "loss": 0.6627406120300293, "step": 110780 }, { "epoch": 0.6585587674090982, "grad_norm": 1.5524249076843262, "learning_rate": 0.00019228076783238887, "loss": 0.7320857048034668, "step": 110790 }, { "epoch": 0.6586182094857665, "grad_norm": 1.402750849723816, "learning_rate": 0.00019227824539678833, "loss": 0.6002267837524414, "step": 110800 }, { "epoch": 0.658677651562435, "grad_norm": 1.768306016921997, "learning_rate": 0.00019227572256759557, "loss": 0.6867155075073242, "step": 110810 }, { "epoch": 0.6587370936391034, "grad_norm": 2.4074885845184326, "learning_rate": 0.00019227319934482265, "loss": 0.6447611808776855, "step": 110820 }, { "epoch": 0.6587965357157718, "grad_norm": 1.6211931705474854, "learning_rate": 0.0001922706757284816, "loss": 0.6368666648864746, "step": 110830 }, { "epoch": 0.6588559777924402, "grad_norm": 1.6098644733428955, "learning_rate": 0.00019226815171858458, "loss": 0.6768096923828125, "step": 110840 }, { "epoch": 0.6589154198691085, "grad_norm": 1.3696930408477783, "learning_rate": 0.00019226562731514357, "loss": 0.6631961822509765, "step": 110850 }, { "epoch": 0.6589748619457769, "grad_norm": 1.733751654624939, "learning_rate": 0.00019226310251817068, "loss": 0.654137372970581, "step": 110860 }, { "epoch": 0.6590343040224453, "grad_norm": 1.718341588973999, "learning_rate": 0.000192260577327678, "loss": 0.6877938270568847, "step": 110870 }, { "epoch": 0.6590937460991138, "grad_norm": 2.068629741668701, "learning_rate": 0.0001922580517436776, "loss": 0.6858274936676025, "step": 110880 }, { "epoch": 0.6591531881757821, "grad_norm": 1.9210660457611084, "learning_rate": 0.00019225552576618152, "loss": 0.6722532749176026, "step": 110890 }, { "epoch": 0.6592126302524505, "grad_norm": 1.3120851516723633, "learning_rate": 0.00019225299939520197, "loss": 0.6832817077636719, "step": 110900 }, { "epoch": 0.6592720723291189, "grad_norm": 1.4575780630111694, "learning_rate": 0.0001922504726307509, "loss": 0.6772891521453858, "step": 110910 }, { "epoch": 0.6593315144057873, "grad_norm": 1.6157057285308838, "learning_rate": 0.00019224794547284047, "loss": 0.6682562828063965, "step": 110920 }, { "epoch": 0.6593909564824557, "grad_norm": 2.0785906314849854, "learning_rate": 0.00019224541792148275, "loss": 0.698339319229126, "step": 110930 }, { "epoch": 0.659450398559124, "grad_norm": 1.7211860418319702, "learning_rate": 0.0001922428899766898, "loss": 0.6374307155609131, "step": 110940 }, { "epoch": 0.6595098406357924, "grad_norm": 1.3122774362564087, "learning_rate": 0.00019224036163847377, "loss": 0.625977611541748, "step": 110950 }, { "epoch": 0.6595692827124608, "grad_norm": 1.660523533821106, "learning_rate": 0.0001922378329068467, "loss": 0.7060073852539063, "step": 110960 }, { "epoch": 0.6596287247891293, "grad_norm": 1.479182243347168, "learning_rate": 0.0001922353037818207, "loss": 0.7217947959899902, "step": 110970 }, { "epoch": 0.6596881668657977, "grad_norm": 1.9137667417526245, "learning_rate": 0.00019223277426340794, "loss": 0.6438591957092286, "step": 110980 }, { "epoch": 0.659747608942466, "grad_norm": 1.5747795104980469, "learning_rate": 0.00019223024435162042, "loss": 0.6604079246520996, "step": 110990 }, { "epoch": 0.6598070510191344, "grad_norm": 1.6849830150604248, "learning_rate": 0.00019222771404647028, "loss": 0.7423629283905029, "step": 111000 }, { "epoch": 0.6598664930958028, "grad_norm": 1.527786374092102, "learning_rate": 0.00019222518334796967, "loss": 0.6858473777770996, "step": 111010 }, { "epoch": 0.6599259351724712, "grad_norm": 1.6156158447265625, "learning_rate": 0.00019222265225613062, "loss": 0.6481769561767579, "step": 111020 }, { "epoch": 0.6599853772491395, "grad_norm": 2.0421066284179688, "learning_rate": 0.00019222012077096528, "loss": 0.6878799438476563, "step": 111030 }, { "epoch": 0.6600448193258079, "grad_norm": 1.7286216020584106, "learning_rate": 0.00019221758889248575, "loss": 0.6759402275085449, "step": 111040 }, { "epoch": 0.6601042614024764, "grad_norm": 2.048518657684326, "learning_rate": 0.00019221505662070414, "loss": 0.6569975852966309, "step": 111050 }, { "epoch": 0.6601637034791448, "grad_norm": 1.8098971843719482, "learning_rate": 0.00019221252395563258, "loss": 0.6463253021240234, "step": 111060 }, { "epoch": 0.6602231455558132, "grad_norm": 1.4823508262634277, "learning_rate": 0.00019220999089728316, "loss": 0.6671525955200195, "step": 111070 }, { "epoch": 0.6602825876324815, "grad_norm": 1.5977795124053955, "learning_rate": 0.00019220745744566803, "loss": 0.6690784931182862, "step": 111080 }, { "epoch": 0.6603420297091499, "grad_norm": 1.5229078531265259, "learning_rate": 0.00019220492360079924, "loss": 0.7080197334289551, "step": 111090 }, { "epoch": 0.6604014717858183, "grad_norm": 1.2662655115127563, "learning_rate": 0.00019220238936268902, "loss": 0.6809600830078125, "step": 111100 }, { "epoch": 0.6604609138624867, "grad_norm": 1.6933940649032593, "learning_rate": 0.0001921998547313494, "loss": 0.6874528884887695, "step": 111110 }, { "epoch": 0.660520355939155, "grad_norm": 1.9516199827194214, "learning_rate": 0.00019219731970679258, "loss": 0.6767292499542237, "step": 111120 }, { "epoch": 0.6605797980158234, "grad_norm": 1.9174830913543701, "learning_rate": 0.00019219478428903058, "loss": 0.6261743068695068, "step": 111130 }, { "epoch": 0.6606392400924919, "grad_norm": 1.8418620824813843, "learning_rate": 0.00019219224847807562, "loss": 0.6759130477905273, "step": 111140 }, { "epoch": 0.6606986821691603, "grad_norm": 1.8028875589370728, "learning_rate": 0.00019218971227393983, "loss": 0.6612770557403564, "step": 111150 }, { "epoch": 0.6607581242458287, "grad_norm": 1.7678921222686768, "learning_rate": 0.0001921871756766353, "loss": 0.691387939453125, "step": 111160 }, { "epoch": 0.660817566322497, "grad_norm": 1.872705340385437, "learning_rate": 0.00019218463868617415, "loss": 0.638798713684082, "step": 111170 }, { "epoch": 0.6608770083991654, "grad_norm": 1.8334485292434692, "learning_rate": 0.00019218210130256857, "loss": 0.6227332592010498, "step": 111180 }, { "epoch": 0.6609364504758338, "grad_norm": 1.7162392139434814, "learning_rate": 0.00019217956352583069, "loss": 0.7331250190734864, "step": 111190 }, { "epoch": 0.6609958925525022, "grad_norm": 1.5646835565567017, "learning_rate": 0.0001921770253559726, "loss": 0.6988620758056641, "step": 111200 }, { "epoch": 0.6610553346291707, "grad_norm": 1.7588880062103271, "learning_rate": 0.00019217448679300652, "loss": 0.7151781558990479, "step": 111210 }, { "epoch": 0.661114776705839, "grad_norm": 1.6959177255630493, "learning_rate": 0.00019217194783694452, "loss": 0.6076013565063476, "step": 111220 }, { "epoch": 0.6611742187825074, "grad_norm": 1.6502996683120728, "learning_rate": 0.0001921694084877988, "loss": 0.686347770690918, "step": 111230 }, { "epoch": 0.6612336608591758, "grad_norm": 1.9391460418701172, "learning_rate": 0.00019216686874558146, "loss": 0.6441726684570312, "step": 111240 }, { "epoch": 0.6612931029358442, "grad_norm": 1.957214593887329, "learning_rate": 0.0001921643286103047, "loss": 0.6352187633514405, "step": 111250 }, { "epoch": 0.6613525450125125, "grad_norm": 1.6239534616470337, "learning_rate": 0.0001921617880819806, "loss": 0.687862777709961, "step": 111260 }, { "epoch": 0.6614119870891809, "grad_norm": 1.5588620901107788, "learning_rate": 0.00019215924716062138, "loss": 0.6523117065429688, "step": 111270 }, { "epoch": 0.6614714291658493, "grad_norm": 1.6560112237930298, "learning_rate": 0.00019215670584623917, "loss": 0.6734251976013184, "step": 111280 }, { "epoch": 0.6615308712425177, "grad_norm": 1.5266088247299194, "learning_rate": 0.00019215416413884614, "loss": 0.6921671867370606, "step": 111290 }, { "epoch": 0.6615903133191862, "grad_norm": 1.6396214962005615, "learning_rate": 0.0001921516220384544, "loss": 0.6574081420898438, "step": 111300 }, { "epoch": 0.6616497553958545, "grad_norm": 1.7459841966629028, "learning_rate": 0.0001921490795450762, "loss": 0.655637550354004, "step": 111310 }, { "epoch": 0.6617091974725229, "grad_norm": 1.9805067777633667, "learning_rate": 0.00019214653665872362, "loss": 0.633694839477539, "step": 111320 }, { "epoch": 0.6617686395491913, "grad_norm": 1.6328054666519165, "learning_rate": 0.00019214399337940888, "loss": 0.6879891395568848, "step": 111330 }, { "epoch": 0.6618280816258597, "grad_norm": 1.9766961336135864, "learning_rate": 0.00019214144970714408, "loss": 0.6460625648498535, "step": 111340 }, { "epoch": 0.6618875237025281, "grad_norm": 1.4785772562026978, "learning_rate": 0.00019213890564194147, "loss": 0.640176248550415, "step": 111350 }, { "epoch": 0.6619469657791964, "grad_norm": 1.314253568649292, "learning_rate": 0.00019213636118381314, "loss": 0.610969066619873, "step": 111360 }, { "epoch": 0.6620064078558648, "grad_norm": 1.8812750577926636, "learning_rate": 0.0001921338163327713, "loss": 0.6827845096588134, "step": 111370 }, { "epoch": 0.6620658499325333, "grad_norm": 1.8616303205490112, "learning_rate": 0.00019213127108882815, "loss": 0.6498721599578857, "step": 111380 }, { "epoch": 0.6621252920092017, "grad_norm": 1.6195704936981201, "learning_rate": 0.00019212872545199583, "loss": 0.6230926513671875, "step": 111390 }, { "epoch": 0.66218473408587, "grad_norm": 1.5702704191207886, "learning_rate": 0.00019212617942228653, "loss": 0.616239070892334, "step": 111400 }, { "epoch": 0.6622441761625384, "grad_norm": 1.5343619585037231, "learning_rate": 0.00019212363299971242, "loss": 0.5713346481323243, "step": 111410 }, { "epoch": 0.6623036182392068, "grad_norm": 1.6607511043548584, "learning_rate": 0.00019212108618428571, "loss": 0.7389894962310791, "step": 111420 }, { "epoch": 0.6623630603158752, "grad_norm": 1.983547329902649, "learning_rate": 0.00019211853897601854, "loss": 0.6664342403411865, "step": 111430 }, { "epoch": 0.6624225023925436, "grad_norm": 1.694714903831482, "learning_rate": 0.00019211599137492313, "loss": 0.6832474708557129, "step": 111440 }, { "epoch": 0.6624819444692119, "grad_norm": 1.6370741128921509, "learning_rate": 0.00019211344338101164, "loss": 0.7145659446716308, "step": 111450 }, { "epoch": 0.6625413865458804, "grad_norm": 1.6925251483917236, "learning_rate": 0.00019211089499429626, "loss": 0.7203523635864257, "step": 111460 }, { "epoch": 0.6626008286225488, "grad_norm": 1.8231749534606934, "learning_rate": 0.0001921083462147892, "loss": 0.6915075302124023, "step": 111470 }, { "epoch": 0.6626602706992172, "grad_norm": 1.5688585042953491, "learning_rate": 0.0001921057970425027, "loss": 0.6861933708190918, "step": 111480 }, { "epoch": 0.6627197127758855, "grad_norm": 2.039811372756958, "learning_rate": 0.00019210324747744883, "loss": 0.7422013282775879, "step": 111490 }, { "epoch": 0.6627791548525539, "grad_norm": 2.1703855991363525, "learning_rate": 0.00019210069751963987, "loss": 0.7042494773864746, "step": 111500 }, { "epoch": 0.6628385969292223, "grad_norm": 1.4915157556533813, "learning_rate": 0.00019209814716908804, "loss": 0.6736577987670899, "step": 111510 }, { "epoch": 0.6628980390058907, "grad_norm": 1.5766454935073853, "learning_rate": 0.00019209559642580545, "loss": 0.665078592300415, "step": 111520 }, { "epoch": 0.6629574810825591, "grad_norm": 1.7990282773971558, "learning_rate": 0.00019209304528980438, "loss": 0.6702870845794677, "step": 111530 }, { "epoch": 0.6630169231592274, "grad_norm": 1.9263948202133179, "learning_rate": 0.00019209049376109704, "loss": 0.659913444519043, "step": 111540 }, { "epoch": 0.6630763652358959, "grad_norm": 1.5787512063980103, "learning_rate": 0.00019208794183969555, "loss": 0.6051993846893311, "step": 111550 }, { "epoch": 0.6631358073125643, "grad_norm": 1.6339699029922485, "learning_rate": 0.0001920853895256122, "loss": 0.727725887298584, "step": 111560 }, { "epoch": 0.6631952493892327, "grad_norm": 2.0794260501861572, "learning_rate": 0.00019208283681885918, "loss": 0.6614383697509766, "step": 111570 }, { "epoch": 0.6632546914659011, "grad_norm": 1.8082537651062012, "learning_rate": 0.0001920802837194487, "loss": 0.7203161239624023, "step": 111580 }, { "epoch": 0.6633141335425694, "grad_norm": 1.4187240600585938, "learning_rate": 0.00019207773022739293, "loss": 0.7505524635314942, "step": 111590 }, { "epoch": 0.6633735756192378, "grad_norm": 1.924983024597168, "learning_rate": 0.00019207517634270419, "loss": 0.6198083877563476, "step": 111600 }, { "epoch": 0.6634330176959062, "grad_norm": 1.4102388620376587, "learning_rate": 0.00019207262206539453, "loss": 0.6573172569274902, "step": 111610 }, { "epoch": 0.6634924597725746, "grad_norm": 1.3730669021606445, "learning_rate": 0.00019207006739547632, "loss": 0.6736447811126709, "step": 111620 }, { "epoch": 0.663551901849243, "grad_norm": 1.7137446403503418, "learning_rate": 0.00019206751233296173, "loss": 0.5955615520477295, "step": 111630 }, { "epoch": 0.6636113439259114, "grad_norm": 2.1006534099578857, "learning_rate": 0.000192064956877863, "loss": 0.6499732971191406, "step": 111640 }, { "epoch": 0.6636707860025798, "grad_norm": 1.6717897653579712, "learning_rate": 0.0001920624010301923, "loss": 0.6710056781768798, "step": 111650 }, { "epoch": 0.6637302280792482, "grad_norm": 1.8604182004928589, "learning_rate": 0.00019205984478996193, "loss": 0.6341889381408692, "step": 111660 }, { "epoch": 0.6637896701559166, "grad_norm": 1.8823336362838745, "learning_rate": 0.00019205728815718405, "loss": 0.6754602432250977, "step": 111670 }, { "epoch": 0.6638491122325849, "grad_norm": 1.3912255764007568, "learning_rate": 0.00019205473113187094, "loss": 0.6007184982299805, "step": 111680 }, { "epoch": 0.6639085543092533, "grad_norm": 1.6799935102462769, "learning_rate": 0.00019205217371403479, "loss": 0.6713151931762695, "step": 111690 }, { "epoch": 0.6639679963859217, "grad_norm": 1.6590665578842163, "learning_rate": 0.00019204961590368785, "loss": 0.6765581607818604, "step": 111700 }, { "epoch": 0.6640274384625902, "grad_norm": 1.5267459154129028, "learning_rate": 0.0001920470577008424, "loss": 0.6877275943756104, "step": 111710 }, { "epoch": 0.6640868805392586, "grad_norm": 1.8346471786499023, "learning_rate": 0.0001920444991055106, "loss": 0.6791996955871582, "step": 111720 }, { "epoch": 0.6641463226159269, "grad_norm": 2.07067608833313, "learning_rate": 0.00019204194011770477, "loss": 0.7035959243774415, "step": 111730 }, { "epoch": 0.6642057646925953, "grad_norm": 1.7801533937454224, "learning_rate": 0.00019203938073743707, "loss": 0.6935785293579102, "step": 111740 }, { "epoch": 0.6642652067692637, "grad_norm": 1.8223875761032104, "learning_rate": 0.0001920368209647198, "loss": 0.6647977828979492, "step": 111750 }, { "epoch": 0.6643246488459321, "grad_norm": 1.867282748222351, "learning_rate": 0.0001920342607995652, "loss": 0.7099679946899414, "step": 111760 }, { "epoch": 0.6643840909226004, "grad_norm": 1.611228585243225, "learning_rate": 0.00019203170024198547, "loss": 0.64776611328125, "step": 111770 }, { "epoch": 0.6644435329992688, "grad_norm": 1.3585238456726074, "learning_rate": 0.00019202913929199293, "loss": 0.6220876693725585, "step": 111780 }, { "epoch": 0.6645029750759373, "grad_norm": 1.673272967338562, "learning_rate": 0.0001920265779495998, "loss": 0.6706391334533691, "step": 111790 }, { "epoch": 0.6645624171526057, "grad_norm": 1.489512324333191, "learning_rate": 0.00019202401621481828, "loss": 0.6825415134429932, "step": 111800 }, { "epoch": 0.6646218592292741, "grad_norm": 1.7181082963943481, "learning_rate": 0.0001920214540876607, "loss": 0.6681711196899414, "step": 111810 }, { "epoch": 0.6646813013059424, "grad_norm": 1.6501487493515015, "learning_rate": 0.0001920188915681393, "loss": 0.6386540412902832, "step": 111820 }, { "epoch": 0.6647407433826108, "grad_norm": 1.5527280569076538, "learning_rate": 0.00019201632865626633, "loss": 0.6335073471069336, "step": 111830 }, { "epoch": 0.6648001854592792, "grad_norm": 1.872298240661621, "learning_rate": 0.00019201376535205402, "loss": 0.686557674407959, "step": 111840 }, { "epoch": 0.6648596275359476, "grad_norm": 1.5470845699310303, "learning_rate": 0.00019201120165551468, "loss": 0.6824160099029541, "step": 111850 }, { "epoch": 0.6649190696126159, "grad_norm": 1.7720848321914673, "learning_rate": 0.00019200863756666057, "loss": 0.6337869167327881, "step": 111860 }, { "epoch": 0.6649785116892843, "grad_norm": 1.545825481414795, "learning_rate": 0.0001920060730855039, "loss": 0.6916618347167969, "step": 111870 }, { "epoch": 0.6650379537659528, "grad_norm": 1.459641695022583, "learning_rate": 0.00019200350821205696, "loss": 0.6898703575134277, "step": 111880 }, { "epoch": 0.6650973958426212, "grad_norm": 1.5301834344863892, "learning_rate": 0.00019200094294633208, "loss": 0.7008140563964844, "step": 111890 }, { "epoch": 0.6651568379192896, "grad_norm": 1.6959788799285889, "learning_rate": 0.00019199837728834147, "loss": 0.6635104179382324, "step": 111900 }, { "epoch": 0.6652162799959579, "grad_norm": 1.4907448291778564, "learning_rate": 0.00019199581123809746, "loss": 0.7126802921295166, "step": 111910 }, { "epoch": 0.6652757220726263, "grad_norm": 1.7625465393066406, "learning_rate": 0.00019199324479561222, "loss": 0.6817836761474609, "step": 111920 }, { "epoch": 0.6653351641492947, "grad_norm": 2.1469199657440186, "learning_rate": 0.00019199067796089812, "loss": 0.6822726249694824, "step": 111930 }, { "epoch": 0.6653946062259631, "grad_norm": 1.588431715965271, "learning_rate": 0.00019198811073396744, "loss": 0.7415957450866699, "step": 111940 }, { "epoch": 0.6654540483026316, "grad_norm": 1.4179798364639282, "learning_rate": 0.0001919855431148324, "loss": 0.6037288665771484, "step": 111950 }, { "epoch": 0.6655134903792999, "grad_norm": 1.9321216344833374, "learning_rate": 0.00019198297510350528, "loss": 0.7283894538879394, "step": 111960 }, { "epoch": 0.6655729324559683, "grad_norm": 1.8154222965240479, "learning_rate": 0.00019198040669999846, "loss": 0.6965314388275147, "step": 111970 }, { "epoch": 0.6656323745326367, "grad_norm": 2.044027805328369, "learning_rate": 0.00019197783790432418, "loss": 0.6547452449798584, "step": 111980 }, { "epoch": 0.6656918166093051, "grad_norm": 1.9053040742874146, "learning_rate": 0.00019197526871649466, "loss": 0.6390886783599854, "step": 111990 }, { "epoch": 0.6657512586859734, "grad_norm": 1.9722813367843628, "learning_rate": 0.00019197269913652225, "loss": 0.6164593696594238, "step": 112000 }, { "epoch": 0.6658107007626418, "grad_norm": 2.0751848220825195, "learning_rate": 0.00019197012916441925, "loss": 0.6471121311187744, "step": 112010 }, { "epoch": 0.6658701428393102, "grad_norm": 1.9171340465545654, "learning_rate": 0.00019196755880019795, "loss": 0.7320204734802246, "step": 112020 }, { "epoch": 0.6659295849159786, "grad_norm": 1.4875552654266357, "learning_rate": 0.00019196498804387063, "loss": 0.6471033096313477, "step": 112030 }, { "epoch": 0.6659890269926471, "grad_norm": 2.0108635425567627, "learning_rate": 0.0001919624168954496, "loss": 0.6793076992034912, "step": 112040 }, { "epoch": 0.6660484690693154, "grad_norm": 1.3854994773864746, "learning_rate": 0.00019195984535494713, "loss": 0.6192800521850585, "step": 112050 }, { "epoch": 0.6661079111459838, "grad_norm": 1.6737778186798096, "learning_rate": 0.00019195727342237557, "loss": 0.6839850425720215, "step": 112060 }, { "epoch": 0.6661673532226522, "grad_norm": 1.6933085918426514, "learning_rate": 0.0001919547010977472, "loss": 0.6302096366882324, "step": 112070 }, { "epoch": 0.6662267952993206, "grad_norm": 1.3139461278915405, "learning_rate": 0.0001919521283810743, "loss": 0.6794824600219727, "step": 112080 }, { "epoch": 0.666286237375989, "grad_norm": 1.603821873664856, "learning_rate": 0.0001919495552723692, "loss": 0.6630496501922607, "step": 112090 }, { "epoch": 0.6663456794526573, "grad_norm": 1.6802960634231567, "learning_rate": 0.00019194698177164423, "loss": 0.6340541839599609, "step": 112100 }, { "epoch": 0.6664051215293257, "grad_norm": 1.5382319688796997, "learning_rate": 0.00019194440787891165, "loss": 0.6938842296600342, "step": 112110 }, { "epoch": 0.6664645636059942, "grad_norm": 1.4060550928115845, "learning_rate": 0.00019194183359418383, "loss": 0.6918254852294922, "step": 112120 }, { "epoch": 0.6665240056826626, "grad_norm": 1.3853923082351685, "learning_rate": 0.00019193925891747307, "loss": 0.7089697360992432, "step": 112130 }, { "epoch": 0.6665834477593309, "grad_norm": 1.4926191568374634, "learning_rate": 0.0001919366838487916, "loss": 0.6850375175476074, "step": 112140 }, { "epoch": 0.6666428898359993, "grad_norm": 1.6818960905075073, "learning_rate": 0.00019193410838815188, "loss": 0.5816191673278809, "step": 112150 }, { "epoch": 0.6667023319126677, "grad_norm": 1.5216641426086426, "learning_rate": 0.00019193153253556616, "loss": 0.6495602130889893, "step": 112160 }, { "epoch": 0.6667617739893361, "grad_norm": 1.7111228704452515, "learning_rate": 0.00019192895629104674, "loss": 0.6642612457275391, "step": 112170 }, { "epoch": 0.6668212160660045, "grad_norm": 1.5266011953353882, "learning_rate": 0.000191926379654606, "loss": 0.6104726314544677, "step": 112180 }, { "epoch": 0.6668806581426728, "grad_norm": 1.6444268226623535, "learning_rate": 0.0001919238026262562, "loss": 0.7290720462799072, "step": 112190 }, { "epoch": 0.6669401002193412, "grad_norm": 1.6627459526062012, "learning_rate": 0.0001919212252060097, "loss": 0.6842385768890381, "step": 112200 }, { "epoch": 0.6669995422960097, "grad_norm": 1.7368853092193604, "learning_rate": 0.00019191864739387884, "loss": 0.6942812919616699, "step": 112210 }, { "epoch": 0.6670589843726781, "grad_norm": 1.6073755025863647, "learning_rate": 0.00019191606918987595, "loss": 0.6543663024902344, "step": 112220 }, { "epoch": 0.6671184264493464, "grad_norm": 2.025195837020874, "learning_rate": 0.00019191349059401335, "loss": 0.6947750568389892, "step": 112230 }, { "epoch": 0.6671778685260148, "grad_norm": 1.9304858446121216, "learning_rate": 0.00019191091160630335, "loss": 0.6723374366760254, "step": 112240 }, { "epoch": 0.6672373106026832, "grad_norm": 1.5417746305465698, "learning_rate": 0.00019190833222675836, "loss": 0.6636407852172852, "step": 112250 }, { "epoch": 0.6672967526793516, "grad_norm": 1.8539799451828003, "learning_rate": 0.0001919057524553907, "loss": 0.6615521430969238, "step": 112260 }, { "epoch": 0.66735619475602, "grad_norm": 1.7664947509765625, "learning_rate": 0.00019190317229221264, "loss": 0.6878776550292969, "step": 112270 }, { "epoch": 0.6674156368326883, "grad_norm": 1.5534812211990356, "learning_rate": 0.0001919005917372366, "loss": 0.741775369644165, "step": 112280 }, { "epoch": 0.6674750789093568, "grad_norm": 1.561579942703247, "learning_rate": 0.00019189801079047485, "loss": 0.6494956970214844, "step": 112290 }, { "epoch": 0.6675345209860252, "grad_norm": 2.014216184616089, "learning_rate": 0.00019189542945193978, "loss": 0.6899862289428711, "step": 112300 }, { "epoch": 0.6675939630626936, "grad_norm": 1.3647401332855225, "learning_rate": 0.00019189284772164382, "loss": 0.6592934608459473, "step": 112310 }, { "epoch": 0.667653405139362, "grad_norm": 1.3733094930648804, "learning_rate": 0.00019189026559959915, "loss": 0.6397944450378418, "step": 112320 }, { "epoch": 0.6677128472160303, "grad_norm": 1.698873519897461, "learning_rate": 0.00019188768308581823, "loss": 0.7206928730010986, "step": 112330 }, { "epoch": 0.6677722892926987, "grad_norm": 1.813246726989746, "learning_rate": 0.00019188510018031344, "loss": 0.6710786819458008, "step": 112340 }, { "epoch": 0.6678317313693671, "grad_norm": 1.5418044328689575, "learning_rate": 0.00019188251688309705, "loss": 0.6682930946350097, "step": 112350 }, { "epoch": 0.6678911734460355, "grad_norm": 1.944452166557312, "learning_rate": 0.00019187993319418149, "loss": 0.6086470127105713, "step": 112360 }, { "epoch": 0.6679506155227038, "grad_norm": 1.5869202613830566, "learning_rate": 0.00019187734911357908, "loss": 0.6618599891662598, "step": 112370 }, { "epoch": 0.6680100575993723, "grad_norm": 1.3869465589523315, "learning_rate": 0.00019187476464130215, "loss": 0.6658407211303711, "step": 112380 }, { "epoch": 0.6680694996760407, "grad_norm": 1.32719886302948, "learning_rate": 0.00019187217977736316, "loss": 0.6714820861816406, "step": 112390 }, { "epoch": 0.6681289417527091, "grad_norm": 1.3119086027145386, "learning_rate": 0.0001918695945217744, "loss": 0.6761131763458252, "step": 112400 }, { "epoch": 0.6681883838293775, "grad_norm": 1.7607331275939941, "learning_rate": 0.00019186700887454823, "loss": 0.7355081558227539, "step": 112410 }, { "epoch": 0.6682478259060458, "grad_norm": 2.1433603763580322, "learning_rate": 0.00019186442283569704, "loss": 0.6833413124084473, "step": 112420 }, { "epoch": 0.6683072679827142, "grad_norm": 2.0335776805877686, "learning_rate": 0.00019186183640523323, "loss": 0.7019969940185546, "step": 112430 }, { "epoch": 0.6683667100593826, "grad_norm": 1.5761160850524902, "learning_rate": 0.00019185924958316916, "loss": 0.692777156829834, "step": 112440 }, { "epoch": 0.668426152136051, "grad_norm": 1.6870250701904297, "learning_rate": 0.00019185666236951716, "loss": 0.677458381652832, "step": 112450 }, { "epoch": 0.6684855942127195, "grad_norm": 1.8017314672470093, "learning_rate": 0.00019185407476428966, "loss": 0.6540867805480957, "step": 112460 }, { "epoch": 0.6685450362893878, "grad_norm": 1.7284231185913086, "learning_rate": 0.000191851486767499, "loss": 0.7050692558288574, "step": 112470 }, { "epoch": 0.6686044783660562, "grad_norm": 1.696225881576538, "learning_rate": 0.00019184889837915758, "loss": 0.7050528049468994, "step": 112480 }, { "epoch": 0.6686639204427246, "grad_norm": 1.7919268608093262, "learning_rate": 0.00019184630959927782, "loss": 0.616692066192627, "step": 112490 }, { "epoch": 0.668723362519393, "grad_norm": 1.9043303728103638, "learning_rate": 0.000191843720427872, "loss": 0.5922819614410401, "step": 112500 }, { "epoch": 0.6687828045960613, "grad_norm": 1.9718749523162842, "learning_rate": 0.0001918411308649526, "loss": 0.7415726661682129, "step": 112510 }, { "epoch": 0.6688422466727297, "grad_norm": 2.0290050506591797, "learning_rate": 0.00019183854091053197, "loss": 0.628043270111084, "step": 112520 }, { "epoch": 0.6689016887493981, "grad_norm": 1.6438424587249756, "learning_rate": 0.00019183595056462252, "loss": 0.6579775810241699, "step": 112530 }, { "epoch": 0.6689611308260666, "grad_norm": 1.710129976272583, "learning_rate": 0.00019183335982723661, "loss": 0.6714848518371582, "step": 112540 }, { "epoch": 0.669020572902735, "grad_norm": 1.8692574501037598, "learning_rate": 0.00019183076869838667, "loss": 0.7013129234313965, "step": 112550 }, { "epoch": 0.6690800149794033, "grad_norm": 1.546863079071045, "learning_rate": 0.00019182817717808504, "loss": 0.7086188316345214, "step": 112560 }, { "epoch": 0.6691394570560717, "grad_norm": 1.5792604684829712, "learning_rate": 0.00019182558526634416, "loss": 0.6528060436248779, "step": 112570 }, { "epoch": 0.6691988991327401, "grad_norm": 2.018242597579956, "learning_rate": 0.00019182299296317644, "loss": 0.7135121822357178, "step": 112580 }, { "epoch": 0.6692583412094085, "grad_norm": 1.5890753269195557, "learning_rate": 0.00019182040026859425, "loss": 0.699308204650879, "step": 112590 }, { "epoch": 0.6693177832860768, "grad_norm": 1.736063838005066, "learning_rate": 0.00019181780718261003, "loss": 0.6517743587493896, "step": 112600 }, { "epoch": 0.6693772253627452, "grad_norm": 1.8686622381210327, "learning_rate": 0.00019181521370523614, "loss": 0.7283727169036865, "step": 112610 }, { "epoch": 0.6694366674394137, "grad_norm": 1.5270249843597412, "learning_rate": 0.00019181261983648498, "loss": 0.7352837085723877, "step": 112620 }, { "epoch": 0.6694961095160821, "grad_norm": 1.375245213508606, "learning_rate": 0.00019181002557636903, "loss": 0.699683952331543, "step": 112630 }, { "epoch": 0.6695555515927505, "grad_norm": 1.7426681518554688, "learning_rate": 0.0001918074309249006, "loss": 0.6751583099365235, "step": 112640 }, { "epoch": 0.6696149936694188, "grad_norm": 1.5828015804290771, "learning_rate": 0.0001918048358820922, "loss": 0.6156341552734375, "step": 112650 }, { "epoch": 0.6696744357460872, "grad_norm": 1.9812005758285522, "learning_rate": 0.00019180224044795617, "loss": 0.7151164054870606, "step": 112660 }, { "epoch": 0.6697338778227556, "grad_norm": 1.3023065328598022, "learning_rate": 0.00019179964462250496, "loss": 0.6129682540893555, "step": 112670 }, { "epoch": 0.669793319899424, "grad_norm": 1.837118148803711, "learning_rate": 0.00019179704840575099, "loss": 0.6922942638397217, "step": 112680 }, { "epoch": 0.6698527619760924, "grad_norm": 1.62579345703125, "learning_rate": 0.0001917944517977067, "loss": 0.6767947196960449, "step": 112690 }, { "epoch": 0.6699122040527608, "grad_norm": 1.6063957214355469, "learning_rate": 0.00019179185479838444, "loss": 0.615201997756958, "step": 112700 }, { "epoch": 0.6699716461294292, "grad_norm": 1.9807789325714111, "learning_rate": 0.0001917892574077967, "loss": 0.687202262878418, "step": 112710 }, { "epoch": 0.6700310882060976, "grad_norm": 1.4278966188430786, "learning_rate": 0.00019178665962595588, "loss": 0.6622393131256104, "step": 112720 }, { "epoch": 0.670090530282766, "grad_norm": 2.0601298809051514, "learning_rate": 0.00019178406145287438, "loss": 0.6879716873168945, "step": 112730 }, { "epoch": 0.6701499723594343, "grad_norm": 1.9579851627349854, "learning_rate": 0.0001917814628885647, "loss": 0.6336881637573242, "step": 112740 }, { "epoch": 0.6702094144361027, "grad_norm": 1.4427731037139893, "learning_rate": 0.0001917788639330392, "loss": 0.711707878112793, "step": 112750 }, { "epoch": 0.6702688565127711, "grad_norm": 1.5931293964385986, "learning_rate": 0.00019177626458631036, "loss": 0.6518535614013672, "step": 112760 }, { "epoch": 0.6703282985894395, "grad_norm": 1.743147850036621, "learning_rate": 0.00019177366484839057, "loss": 0.6463356971740722, "step": 112770 }, { "epoch": 0.670387740666108, "grad_norm": 1.7280868291854858, "learning_rate": 0.0001917710647192923, "loss": 0.6252745628356934, "step": 112780 }, { "epoch": 0.6704471827427763, "grad_norm": 1.6737005710601807, "learning_rate": 0.000191768464199028, "loss": 0.6852639198303223, "step": 112790 }, { "epoch": 0.6705066248194447, "grad_norm": 1.5919702053070068, "learning_rate": 0.00019176586328761006, "loss": 0.660709285736084, "step": 112800 }, { "epoch": 0.6705660668961131, "grad_norm": 1.7529503107070923, "learning_rate": 0.00019176326198505096, "loss": 0.6161624431610108, "step": 112810 }, { "epoch": 0.6706255089727815, "grad_norm": 2.0179696083068848, "learning_rate": 0.00019176066029136316, "loss": 0.7106578826904297, "step": 112820 }, { "epoch": 0.6706849510494499, "grad_norm": 1.3814820051193237, "learning_rate": 0.00019175805820655906, "loss": 0.6820754051208496, "step": 112830 }, { "epoch": 0.6707443931261182, "grad_norm": 1.6146214008331299, "learning_rate": 0.00019175545573065113, "loss": 0.669658613204956, "step": 112840 }, { "epoch": 0.6708038352027866, "grad_norm": 1.2878003120422363, "learning_rate": 0.0001917528528636518, "loss": 0.6599459648132324, "step": 112850 }, { "epoch": 0.670863277279455, "grad_norm": 1.6922037601470947, "learning_rate": 0.00019175024960557357, "loss": 0.6266611099243165, "step": 112860 }, { "epoch": 0.6709227193561235, "grad_norm": 1.6989014148712158, "learning_rate": 0.00019174764595642884, "loss": 0.6953610420227051, "step": 112870 }, { "epoch": 0.6709821614327918, "grad_norm": 1.5249993801116943, "learning_rate": 0.0001917450419162301, "loss": 0.7065629959106445, "step": 112880 }, { "epoch": 0.6710416035094602, "grad_norm": 1.3373018503189087, "learning_rate": 0.00019174243748498979, "loss": 0.6929366111755371, "step": 112890 }, { "epoch": 0.6711010455861286, "grad_norm": 1.71033775806427, "learning_rate": 0.00019173983266272036, "loss": 0.6873940467834473, "step": 112900 }, { "epoch": 0.671160487662797, "grad_norm": 1.8184939622879028, "learning_rate": 0.00019173722744943432, "loss": 0.6647284507751465, "step": 112910 }, { "epoch": 0.6712199297394654, "grad_norm": 1.674088954925537, "learning_rate": 0.00019173462184514408, "loss": 0.6213826179504395, "step": 112920 }, { "epoch": 0.6712793718161337, "grad_norm": 1.8509831428527832, "learning_rate": 0.0001917320158498621, "loss": 0.6547446250915527, "step": 112930 }, { "epoch": 0.6713388138928021, "grad_norm": 1.741632103919983, "learning_rate": 0.0001917294094636009, "loss": 0.61708984375, "step": 112940 }, { "epoch": 0.6713982559694706, "grad_norm": 1.4481096267700195, "learning_rate": 0.00019172680268637285, "loss": 0.6805192947387695, "step": 112950 }, { "epoch": 0.671457698046139, "grad_norm": 2.162247896194458, "learning_rate": 0.00019172419551819053, "loss": 0.6431673049926758, "step": 112960 }, { "epoch": 0.6715171401228073, "grad_norm": 1.5219794511795044, "learning_rate": 0.0001917215879590664, "loss": 0.7337512969970703, "step": 112970 }, { "epoch": 0.6715765821994757, "grad_norm": 1.7440499067306519, "learning_rate": 0.00019171898000901286, "loss": 0.6502738475799561, "step": 112980 }, { "epoch": 0.6716360242761441, "grad_norm": 1.5903090238571167, "learning_rate": 0.0001917163716680424, "loss": 0.6226654529571534, "step": 112990 }, { "epoch": 0.6716954663528125, "grad_norm": 1.6827398538589478, "learning_rate": 0.00019171376293616757, "loss": 0.6628857612609863, "step": 113000 }, { "epoch": 0.6717549084294809, "grad_norm": 1.629521369934082, "learning_rate": 0.0001917111538134008, "loss": 0.6937256813049316, "step": 113010 }, { "epoch": 0.6718143505061492, "grad_norm": 2.129063367843628, "learning_rate": 0.00019170854429975456, "loss": 0.690514087677002, "step": 113020 }, { "epoch": 0.6718737925828177, "grad_norm": 1.5055598020553589, "learning_rate": 0.00019170593439524132, "loss": 0.67146315574646, "step": 113030 }, { "epoch": 0.6719332346594861, "grad_norm": 1.4923573732376099, "learning_rate": 0.00019170332409987364, "loss": 0.6889181137084961, "step": 113040 }, { "epoch": 0.6719926767361545, "grad_norm": 1.6248886585235596, "learning_rate": 0.00019170071341366394, "loss": 0.6801454544067382, "step": 113050 }, { "epoch": 0.6720521188128229, "grad_norm": 1.3189973831176758, "learning_rate": 0.0001916981023366247, "loss": 0.655397891998291, "step": 113060 }, { "epoch": 0.6721115608894912, "grad_norm": 1.857967495918274, "learning_rate": 0.00019169549086876848, "loss": 0.6830366134643555, "step": 113070 }, { "epoch": 0.6721710029661596, "grad_norm": 1.9514727592468262, "learning_rate": 0.0001916928790101077, "loss": 0.6566400051116943, "step": 113080 }, { "epoch": 0.672230445042828, "grad_norm": 1.6420761346817017, "learning_rate": 0.00019169026676065488, "loss": 0.6635068893432617, "step": 113090 }, { "epoch": 0.6722898871194964, "grad_norm": 1.3802638053894043, "learning_rate": 0.00019168765412042255, "loss": 0.6406717300415039, "step": 113100 }, { "epoch": 0.6723493291961647, "grad_norm": 2.3973886966705322, "learning_rate": 0.00019168504108942316, "loss": 0.6343542098999023, "step": 113110 }, { "epoch": 0.6724087712728332, "grad_norm": 1.6115387678146362, "learning_rate": 0.00019168242766766925, "loss": 0.676598072052002, "step": 113120 }, { "epoch": 0.6724682133495016, "grad_norm": 1.4096254110336304, "learning_rate": 0.00019167981385517327, "loss": 0.7201731681823731, "step": 113130 }, { "epoch": 0.67252765542617, "grad_norm": 1.9164162874221802, "learning_rate": 0.00019167719965194777, "loss": 0.7226368904113769, "step": 113140 }, { "epoch": 0.6725870975028384, "grad_norm": 2.23240065574646, "learning_rate": 0.0001916745850580052, "loss": 0.6410882949829102, "step": 113150 }, { "epoch": 0.6726465395795067, "grad_norm": 1.7762048244476318, "learning_rate": 0.00019167197007335818, "loss": 0.6561816215515137, "step": 113160 }, { "epoch": 0.6727059816561751, "grad_norm": 1.9584497213363647, "learning_rate": 0.0001916693546980191, "loss": 0.6939513206481933, "step": 113170 }, { "epoch": 0.6727654237328435, "grad_norm": 1.4070662260055542, "learning_rate": 0.0001916667389320005, "loss": 0.6183269500732422, "step": 113180 }, { "epoch": 0.672824865809512, "grad_norm": 1.6844995021820068, "learning_rate": 0.00019166412277531495, "loss": 0.6122615814208985, "step": 113190 }, { "epoch": 0.6728843078861804, "grad_norm": 1.641122817993164, "learning_rate": 0.00019166150622797494, "loss": 0.6843098163604736, "step": 113200 }, { "epoch": 0.6729437499628487, "grad_norm": 1.6072298288345337, "learning_rate": 0.00019165888928999292, "loss": 0.6711174011230469, "step": 113210 }, { "epoch": 0.6730031920395171, "grad_norm": 1.9097083806991577, "learning_rate": 0.00019165627196138148, "loss": 0.6770716667175293, "step": 113220 }, { "epoch": 0.6730626341161855, "grad_norm": 2.026395082473755, "learning_rate": 0.00019165365424215315, "loss": 0.7501914024353027, "step": 113230 }, { "epoch": 0.6731220761928539, "grad_norm": 1.777450680732727, "learning_rate": 0.00019165103613232037, "loss": 0.6980051517486572, "step": 113240 }, { "epoch": 0.6731815182695222, "grad_norm": 1.994671106338501, "learning_rate": 0.00019164841763189577, "loss": 0.6864434242248535, "step": 113250 }, { "epoch": 0.6732409603461906, "grad_norm": 1.908413290977478, "learning_rate": 0.00019164579874089176, "loss": 0.7447687149047851, "step": 113260 }, { "epoch": 0.673300402422859, "grad_norm": 1.5071760416030884, "learning_rate": 0.000191643179459321, "loss": 0.6646458625793457, "step": 113270 }, { "epoch": 0.6733598444995275, "grad_norm": 1.7147347927093506, "learning_rate": 0.00019164055978719587, "loss": 0.666530990600586, "step": 113280 }, { "epoch": 0.6734192865761959, "grad_norm": 2.1334855556488037, "learning_rate": 0.00019163793972452905, "loss": 0.6451553344726563, "step": 113290 }, { "epoch": 0.6734787286528642, "grad_norm": 2.121351718902588, "learning_rate": 0.000191635319271333, "loss": 0.7121203422546387, "step": 113300 }, { "epoch": 0.6735381707295326, "grad_norm": 1.6371947526931763, "learning_rate": 0.00019163269842762025, "loss": 0.7224639892578125, "step": 113310 }, { "epoch": 0.673597612806201, "grad_norm": 2.04034161567688, "learning_rate": 0.00019163007719340331, "loss": 0.6900017738342286, "step": 113320 }, { "epoch": 0.6736570548828694, "grad_norm": 1.4316279888153076, "learning_rate": 0.00019162745556869482, "loss": 0.6146116256713867, "step": 113330 }, { "epoch": 0.6737164969595377, "grad_norm": 1.561519742012024, "learning_rate": 0.00019162483355350722, "loss": 0.6681257247924804, "step": 113340 }, { "epoch": 0.6737759390362061, "grad_norm": 1.3872535228729248, "learning_rate": 0.00019162221114785312, "loss": 0.6261390209197998, "step": 113350 }, { "epoch": 0.6738353811128746, "grad_norm": 1.5370469093322754, "learning_rate": 0.00019161958835174503, "loss": 0.704806900024414, "step": 113360 }, { "epoch": 0.673894823189543, "grad_norm": 1.7372736930847168, "learning_rate": 0.0001916169651651955, "loss": 0.5966109275817871, "step": 113370 }, { "epoch": 0.6739542652662114, "grad_norm": 1.9106520414352417, "learning_rate": 0.00019161434158821705, "loss": 0.6768043041229248, "step": 113380 }, { "epoch": 0.6740137073428797, "grad_norm": 1.8336790800094604, "learning_rate": 0.00019161171762082228, "loss": 0.6810066223144531, "step": 113390 }, { "epoch": 0.6740731494195481, "grad_norm": 1.8294720649719238, "learning_rate": 0.00019160909326302374, "loss": 0.675795030593872, "step": 113400 }, { "epoch": 0.6741325914962165, "grad_norm": 1.7266725301742554, "learning_rate": 0.00019160646851483395, "loss": 0.6678194046020508, "step": 113410 }, { "epoch": 0.6741920335728849, "grad_norm": 1.8475676774978638, "learning_rate": 0.0001916038433762655, "loss": 0.6659587860107422, "step": 113420 }, { "epoch": 0.6742514756495533, "grad_norm": 1.5994561910629272, "learning_rate": 0.00019160121784733092, "loss": 0.6771217346191406, "step": 113430 }, { "epoch": 0.6743109177262216, "grad_norm": 1.6071614027023315, "learning_rate": 0.00019159859192804279, "loss": 0.6739166736602783, "step": 113440 }, { "epoch": 0.6743703598028901, "grad_norm": 1.7409210205078125, "learning_rate": 0.00019159596561841365, "loss": 0.6803273677825927, "step": 113450 }, { "epoch": 0.6744298018795585, "grad_norm": 1.7319685220718384, "learning_rate": 0.00019159333891845606, "loss": 0.6907739162445068, "step": 113460 }, { "epoch": 0.6744892439562269, "grad_norm": 1.613823652267456, "learning_rate": 0.00019159071182818263, "loss": 0.7087701320648193, "step": 113470 }, { "epoch": 0.6745486860328952, "grad_norm": 1.8805646896362305, "learning_rate": 0.0001915880843476059, "loss": 0.6759199142456055, "step": 113480 }, { "epoch": 0.6746081281095636, "grad_norm": 1.542203664779663, "learning_rate": 0.00019158545647673844, "loss": 0.6959651470184326, "step": 113490 }, { "epoch": 0.674667570186232, "grad_norm": 1.5761380195617676, "learning_rate": 0.00019158282821559282, "loss": 0.7280801773071289, "step": 113500 }, { "epoch": 0.6747270122629004, "grad_norm": 1.779363751411438, "learning_rate": 0.0001915801995641816, "loss": 0.7087973117828369, "step": 113510 }, { "epoch": 0.6747864543395689, "grad_norm": 1.8451824188232422, "learning_rate": 0.00019157757052251737, "loss": 0.6650424003601074, "step": 113520 }, { "epoch": 0.6748458964162372, "grad_norm": 1.6077513694763184, "learning_rate": 0.00019157494109061268, "loss": 0.6884891510009765, "step": 113530 }, { "epoch": 0.6749053384929056, "grad_norm": 2.0366098880767822, "learning_rate": 0.00019157231126848016, "loss": 0.5994713306427002, "step": 113540 }, { "epoch": 0.674964780569574, "grad_norm": 1.8014791011810303, "learning_rate": 0.00019156968105613233, "loss": 0.698820972442627, "step": 113550 }, { "epoch": 0.6750242226462424, "grad_norm": 1.6632970571517944, "learning_rate": 0.00019156705045358184, "loss": 0.6326677322387695, "step": 113560 }, { "epoch": 0.6750836647229108, "grad_norm": 1.6558432579040527, "learning_rate": 0.00019156441946084125, "loss": 0.7171051979064942, "step": 113570 }, { "epoch": 0.6751431067995791, "grad_norm": 1.8118877410888672, "learning_rate": 0.0001915617880779231, "loss": 0.6522843837738037, "step": 113580 }, { "epoch": 0.6752025488762475, "grad_norm": 1.6354236602783203, "learning_rate": 0.00019155915630484, "loss": 0.6710229873657226, "step": 113590 }, { "epoch": 0.675261990952916, "grad_norm": 1.8695160150527954, "learning_rate": 0.00019155652414160456, "loss": 0.6278727531433106, "step": 113600 }, { "epoch": 0.6753214330295844, "grad_norm": 1.7050567865371704, "learning_rate": 0.00019155389158822937, "loss": 0.7136540412902832, "step": 113610 }, { "epoch": 0.6753808751062527, "grad_norm": 1.3753567934036255, "learning_rate": 0.000191551258644727, "loss": 0.6298824310302734, "step": 113620 }, { "epoch": 0.6754403171829211, "grad_norm": 1.5023490190505981, "learning_rate": 0.0001915486253111101, "loss": 0.6980470180511474, "step": 113630 }, { "epoch": 0.6754997592595895, "grad_norm": 1.745686411857605, "learning_rate": 0.00019154599158739116, "loss": 0.6687884330749512, "step": 113640 }, { "epoch": 0.6755592013362579, "grad_norm": 1.4037892818450928, "learning_rate": 0.0001915433574735829, "loss": 0.6607197761535645, "step": 113650 }, { "epoch": 0.6756186434129263, "grad_norm": 1.8136169910430908, "learning_rate": 0.00019154072296969786, "loss": 0.6408544540405273, "step": 113660 }, { "epoch": 0.6756780854895946, "grad_norm": 1.4840717315673828, "learning_rate": 0.00019153808807574865, "loss": 0.6185636997222901, "step": 113670 }, { "epoch": 0.675737527566263, "grad_norm": 1.8548892736434937, "learning_rate": 0.00019153545279174784, "loss": 0.6475297927856445, "step": 113680 }, { "epoch": 0.6757969696429315, "grad_norm": 1.5576742887496948, "learning_rate": 0.00019153281711770809, "loss": 0.7002099990844727, "step": 113690 }, { "epoch": 0.6758564117195999, "grad_norm": 1.442809820175171, "learning_rate": 0.000191530181053642, "loss": 0.6400014877319335, "step": 113700 }, { "epoch": 0.6759158537962682, "grad_norm": 1.7675615549087524, "learning_rate": 0.00019152754459956218, "loss": 0.6154585838317871, "step": 113710 }, { "epoch": 0.6759752958729366, "grad_norm": 1.7012869119644165, "learning_rate": 0.0001915249077554812, "loss": 0.6857954025268554, "step": 113720 }, { "epoch": 0.676034737949605, "grad_norm": 2.0166773796081543, "learning_rate": 0.0001915222705214117, "loss": 0.7259567260742188, "step": 113730 }, { "epoch": 0.6760941800262734, "grad_norm": 1.641175389289856, "learning_rate": 0.00019151963289736632, "loss": 0.679164981842041, "step": 113740 }, { "epoch": 0.6761536221029418, "grad_norm": 1.952224850654602, "learning_rate": 0.00019151699488335766, "loss": 0.7028446197509766, "step": 113750 }, { "epoch": 0.6762130641796101, "grad_norm": 1.1227092742919922, "learning_rate": 0.00019151435647939832, "loss": 0.7074315547943115, "step": 113760 }, { "epoch": 0.6762725062562785, "grad_norm": 1.8618264198303223, "learning_rate": 0.00019151171768550093, "loss": 0.7196991920471192, "step": 113770 }, { "epoch": 0.676331948332947, "grad_norm": 1.481221318244934, "learning_rate": 0.00019150907850167817, "loss": 0.6279214859008789, "step": 113780 }, { "epoch": 0.6763913904096154, "grad_norm": 1.2997997999191284, "learning_rate": 0.00019150643892794258, "loss": 0.6627920627593994, "step": 113790 }, { "epoch": 0.6764508324862838, "grad_norm": 1.8397895097732544, "learning_rate": 0.0001915037989643068, "loss": 0.6755235195159912, "step": 113800 }, { "epoch": 0.6765102745629521, "grad_norm": 1.3449915647506714, "learning_rate": 0.0001915011586107835, "loss": 0.5900037288665771, "step": 113810 }, { "epoch": 0.6765697166396205, "grad_norm": 1.72871732711792, "learning_rate": 0.00019149851786738533, "loss": 0.6887625217437744, "step": 113820 }, { "epoch": 0.6766291587162889, "grad_norm": 1.4280344247817993, "learning_rate": 0.00019149587673412483, "loss": 0.6500628471374512, "step": 113830 }, { "epoch": 0.6766886007929573, "grad_norm": 1.4984853267669678, "learning_rate": 0.00019149323521101472, "loss": 0.6686198234558105, "step": 113840 }, { "epoch": 0.6767480428696256, "grad_norm": 1.7902567386627197, "learning_rate": 0.00019149059329806757, "loss": 0.712464427947998, "step": 113850 }, { "epoch": 0.6768074849462941, "grad_norm": 1.703735113143921, "learning_rate": 0.0001914879509952961, "loss": 0.6561810493469238, "step": 113860 }, { "epoch": 0.6768669270229625, "grad_norm": 1.9079588651657104, "learning_rate": 0.0001914853083027129, "loss": 0.7307747840881348, "step": 113870 }, { "epoch": 0.6769263690996309, "grad_norm": 1.3163508176803589, "learning_rate": 0.00019148266522033057, "loss": 0.6694190979003907, "step": 113880 }, { "epoch": 0.6769858111762993, "grad_norm": 1.7387237548828125, "learning_rate": 0.00019148002174816184, "loss": 0.6468506813049316, "step": 113890 }, { "epoch": 0.6770452532529676, "grad_norm": 1.9607890844345093, "learning_rate": 0.00019147737788621931, "loss": 0.6084427833557129, "step": 113900 }, { "epoch": 0.677104695329636, "grad_norm": 1.8711858987808228, "learning_rate": 0.0001914747336345156, "loss": 0.6362584114074707, "step": 113910 }, { "epoch": 0.6771641374063044, "grad_norm": 1.6417394876480103, "learning_rate": 0.00019147208899306342, "loss": 0.6506878852844238, "step": 113920 }, { "epoch": 0.6772235794829728, "grad_norm": 1.3370858430862427, "learning_rate": 0.0001914694439618754, "loss": 0.6571754455566406, "step": 113930 }, { "epoch": 0.6772830215596413, "grad_norm": 2.046898603439331, "learning_rate": 0.00019146679854096415, "loss": 0.6963689804077149, "step": 113940 }, { "epoch": 0.6773424636363096, "grad_norm": 1.5264616012573242, "learning_rate": 0.00019146415273034237, "loss": 0.7029897212982178, "step": 113950 }, { "epoch": 0.677401905712978, "grad_norm": 1.852576732635498, "learning_rate": 0.0001914615065300227, "loss": 0.6421761035919189, "step": 113960 }, { "epoch": 0.6774613477896464, "grad_norm": 2.071094036102295, "learning_rate": 0.00019145885994001783, "loss": 0.6706660270690918, "step": 113970 }, { "epoch": 0.6775207898663148, "grad_norm": 1.6417291164398193, "learning_rate": 0.0001914562129603404, "loss": 0.678127670288086, "step": 113980 }, { "epoch": 0.6775802319429831, "grad_norm": 1.6617934703826904, "learning_rate": 0.00019145356559100305, "loss": 0.6899776458740234, "step": 113990 }, { "epoch": 0.6776396740196515, "grad_norm": 1.3805880546569824, "learning_rate": 0.00019145091783201844, "loss": 0.6755720138549804, "step": 114000 }, { "epoch": 0.6776991160963199, "grad_norm": 1.936383605003357, "learning_rate": 0.0001914482696833993, "loss": 0.6659900665283203, "step": 114010 }, { "epoch": 0.6777585581729884, "grad_norm": 2.0673630237579346, "learning_rate": 0.00019144562114515822, "loss": 0.6826938152313232, "step": 114020 }, { "epoch": 0.6778180002496568, "grad_norm": 1.4861795902252197, "learning_rate": 0.0001914429722173079, "loss": 0.6345419883728027, "step": 114030 }, { "epoch": 0.6778774423263251, "grad_norm": 2.077038526535034, "learning_rate": 0.00019144032289986103, "loss": 0.6785287857055664, "step": 114040 }, { "epoch": 0.6779368844029935, "grad_norm": 2.6013364791870117, "learning_rate": 0.00019143767319283031, "loss": 0.6794692516326905, "step": 114050 }, { "epoch": 0.6779963264796619, "grad_norm": 1.6854478120803833, "learning_rate": 0.00019143502309622833, "loss": 0.6743982791900635, "step": 114060 }, { "epoch": 0.6780557685563303, "grad_norm": 1.4235528707504272, "learning_rate": 0.00019143237261006783, "loss": 0.616015100479126, "step": 114070 }, { "epoch": 0.6781152106329986, "grad_norm": 1.6222310066223145, "learning_rate": 0.0001914297217343615, "loss": 0.647979736328125, "step": 114080 }, { "epoch": 0.678174652709667, "grad_norm": 2.1984574794769287, "learning_rate": 0.00019142707046912195, "loss": 0.6148122787475586, "step": 114090 }, { "epoch": 0.6782340947863355, "grad_norm": 1.8059871196746826, "learning_rate": 0.0001914244188143619, "loss": 0.6856702327728271, "step": 114100 }, { "epoch": 0.6782935368630039, "grad_norm": 1.5820395946502686, "learning_rate": 0.00019142176677009406, "loss": 0.6467554569244385, "step": 114110 }, { "epoch": 0.6783529789396723, "grad_norm": 1.8524712324142456, "learning_rate": 0.00019141911433633108, "loss": 0.6507374286651612, "step": 114120 }, { "epoch": 0.6784124210163406, "grad_norm": 1.8364287614822388, "learning_rate": 0.0001914164615130857, "loss": 0.6480359077453614, "step": 114130 }, { "epoch": 0.678471863093009, "grad_norm": 1.504667043685913, "learning_rate": 0.00019141380830037054, "loss": 0.6938948154449462, "step": 114140 }, { "epoch": 0.6785313051696774, "grad_norm": 1.8122586011886597, "learning_rate": 0.00019141115469819834, "loss": 0.6771062850952149, "step": 114150 }, { "epoch": 0.6785907472463458, "grad_norm": 1.6721844673156738, "learning_rate": 0.00019140850070658178, "loss": 0.6520536422729493, "step": 114160 }, { "epoch": 0.6786501893230142, "grad_norm": 1.3132151365280151, "learning_rate": 0.00019140584632553357, "loss": 0.7154802322387696, "step": 114170 }, { "epoch": 0.6787096313996825, "grad_norm": 1.7820923328399658, "learning_rate": 0.00019140319155506636, "loss": 0.6698719978332519, "step": 114180 }, { "epoch": 0.678769073476351, "grad_norm": 1.7437355518341064, "learning_rate": 0.00019140053639519293, "loss": 0.6963188171386718, "step": 114190 }, { "epoch": 0.6788285155530194, "grad_norm": 1.714611291885376, "learning_rate": 0.00019139788084592593, "loss": 0.6521155357360839, "step": 114200 }, { "epoch": 0.6788879576296878, "grad_norm": 1.8800644874572754, "learning_rate": 0.00019139522490727804, "loss": 0.6931553363800049, "step": 114210 }, { "epoch": 0.6789473997063561, "grad_norm": 1.805443286895752, "learning_rate": 0.000191392568579262, "loss": 0.7149141311645508, "step": 114220 }, { "epoch": 0.6790068417830245, "grad_norm": 1.7254801988601685, "learning_rate": 0.00019138991186189053, "loss": 0.6789689540863038, "step": 114230 }, { "epoch": 0.6790662838596929, "grad_norm": 2.0665595531463623, "learning_rate": 0.0001913872547551763, "loss": 0.6568803787231445, "step": 114240 }, { "epoch": 0.6791257259363613, "grad_norm": 1.8194379806518555, "learning_rate": 0.00019138459725913205, "loss": 0.6887997627258301, "step": 114250 }, { "epoch": 0.6791851680130297, "grad_norm": 1.8047860860824585, "learning_rate": 0.0001913819393737705, "loss": 0.6973439216613769, "step": 114260 }, { "epoch": 0.679244610089698, "grad_norm": 1.6341768503189087, "learning_rate": 0.00019137928109910432, "loss": 0.6328850269317627, "step": 114270 }, { "epoch": 0.6793040521663665, "grad_norm": 1.533422589302063, "learning_rate": 0.00019137662243514625, "loss": 0.6286922454833984, "step": 114280 }, { "epoch": 0.6793634942430349, "grad_norm": 1.9314582347869873, "learning_rate": 0.00019137396338190905, "loss": 0.6838418006896972, "step": 114290 }, { "epoch": 0.6794229363197033, "grad_norm": 1.9717285633087158, "learning_rate": 0.00019137130393940538, "loss": 0.6436575412750244, "step": 114300 }, { "epoch": 0.6794823783963716, "grad_norm": 1.7837800979614258, "learning_rate": 0.00019136864410764797, "loss": 0.6531388282775878, "step": 114310 }, { "epoch": 0.67954182047304, "grad_norm": 1.4510564804077148, "learning_rate": 0.0001913659838866496, "loss": 0.7024722099304199, "step": 114320 }, { "epoch": 0.6796012625497084, "grad_norm": 1.465072512626648, "learning_rate": 0.0001913633232764229, "loss": 0.674070930480957, "step": 114330 }, { "epoch": 0.6796607046263768, "grad_norm": 1.6881496906280518, "learning_rate": 0.00019136066227698072, "loss": 0.616507625579834, "step": 114340 }, { "epoch": 0.6797201467030453, "grad_norm": 1.4084018468856812, "learning_rate": 0.00019135800088833564, "loss": 0.6444516181945801, "step": 114350 }, { "epoch": 0.6797795887797136, "grad_norm": 1.4049949645996094, "learning_rate": 0.0001913553391105005, "loss": 0.6666646957397461, "step": 114360 }, { "epoch": 0.679839030856382, "grad_norm": 1.8962202072143555, "learning_rate": 0.00019135267694348805, "loss": 0.7189299583435058, "step": 114370 }, { "epoch": 0.6798984729330504, "grad_norm": 1.6103410720825195, "learning_rate": 0.00019135001438731094, "loss": 0.7193051338195801, "step": 114380 }, { "epoch": 0.6799579150097188, "grad_norm": 1.4313814640045166, "learning_rate": 0.00019134735144198193, "loss": 0.6684215545654297, "step": 114390 }, { "epoch": 0.6800173570863872, "grad_norm": 1.708648443222046, "learning_rate": 0.00019134468810751382, "loss": 0.6687119483947754, "step": 114400 }, { "epoch": 0.6800767991630555, "grad_norm": 1.6877630949020386, "learning_rate": 0.00019134202438391925, "loss": 0.7428363800048828, "step": 114410 }, { "epoch": 0.6801362412397239, "grad_norm": 1.5829994678497314, "learning_rate": 0.00019133936027121106, "loss": 0.656070613861084, "step": 114420 }, { "epoch": 0.6801956833163924, "grad_norm": 1.5085043907165527, "learning_rate": 0.00019133669576940196, "loss": 0.6675806522369385, "step": 114430 }, { "epoch": 0.6802551253930608, "grad_norm": 1.592800259590149, "learning_rate": 0.00019133403087850465, "loss": 0.6764601707458496, "step": 114440 }, { "epoch": 0.6803145674697291, "grad_norm": 2.1173956394195557, "learning_rate": 0.00019133136559853193, "loss": 0.7237851619720459, "step": 114450 }, { "epoch": 0.6803740095463975, "grad_norm": 1.9688609838485718, "learning_rate": 0.00019132869992949657, "loss": 0.618077564239502, "step": 114460 }, { "epoch": 0.6804334516230659, "grad_norm": 1.4222639799118042, "learning_rate": 0.00019132603387141125, "loss": 0.5837697505950927, "step": 114470 }, { "epoch": 0.6804928936997343, "grad_norm": 1.6537549495697021, "learning_rate": 0.0001913233674242888, "loss": 0.6608449935913085, "step": 114480 }, { "epoch": 0.6805523357764027, "grad_norm": 1.8206281661987305, "learning_rate": 0.0001913207005881419, "loss": 0.6508153915405274, "step": 114490 }, { "epoch": 0.680611777853071, "grad_norm": 1.3093695640563965, "learning_rate": 0.00019131803336298336, "loss": 0.6680444240570068, "step": 114500 }, { "epoch": 0.6806712199297394, "grad_norm": 1.30885648727417, "learning_rate": 0.00019131536574882593, "loss": 0.6305863380432128, "step": 114510 }, { "epoch": 0.6807306620064079, "grad_norm": 1.375089168548584, "learning_rate": 0.00019131269774568235, "loss": 0.5744012355804443, "step": 114520 }, { "epoch": 0.6807901040830763, "grad_norm": 1.6663711071014404, "learning_rate": 0.00019131002935356538, "loss": 0.6181967735290528, "step": 114530 }, { "epoch": 0.6808495461597447, "grad_norm": 1.6487280130386353, "learning_rate": 0.00019130736057248785, "loss": 0.6179285526275635, "step": 114540 }, { "epoch": 0.680908988236413, "grad_norm": 1.6609795093536377, "learning_rate": 0.00019130469140246243, "loss": 0.637328052520752, "step": 114550 }, { "epoch": 0.6809684303130814, "grad_norm": 1.768950343132019, "learning_rate": 0.00019130202184350196, "loss": 0.6453341484069824, "step": 114560 }, { "epoch": 0.6810278723897498, "grad_norm": 1.6191126108169556, "learning_rate": 0.0001912993518956192, "loss": 0.6637838363647461, "step": 114570 }, { "epoch": 0.6810873144664182, "grad_norm": 1.4780480861663818, "learning_rate": 0.00019129668155882688, "loss": 0.6355822086334229, "step": 114580 }, { "epoch": 0.6811467565430865, "grad_norm": 1.3121845722198486, "learning_rate": 0.00019129401083313783, "loss": 0.6625736713409424, "step": 114590 }, { "epoch": 0.681206198619755, "grad_norm": 1.7169853448867798, "learning_rate": 0.00019129133971856478, "loss": 0.6814797878265381, "step": 114600 }, { "epoch": 0.6812656406964234, "grad_norm": 1.4981493949890137, "learning_rate": 0.0001912886682151205, "loss": 0.6352493286132812, "step": 114610 }, { "epoch": 0.6813250827730918, "grad_norm": 1.7318730354309082, "learning_rate": 0.00019128599632281786, "loss": 0.6753226280212402, "step": 114620 }, { "epoch": 0.6813845248497602, "grad_norm": 2.0452873706817627, "learning_rate": 0.00019128332404166955, "loss": 0.6971616744995117, "step": 114630 }, { "epoch": 0.6814439669264285, "grad_norm": 2.0598649978637695, "learning_rate": 0.00019128065137168838, "loss": 0.6756121635437011, "step": 114640 }, { "epoch": 0.6815034090030969, "grad_norm": 1.5255937576293945, "learning_rate": 0.00019127797831288717, "loss": 0.6918758869171142, "step": 114650 }, { "epoch": 0.6815628510797653, "grad_norm": 1.5913059711456299, "learning_rate": 0.00019127530486527864, "loss": 0.6893883228302002, "step": 114660 }, { "epoch": 0.6816222931564337, "grad_norm": 1.4457886219024658, "learning_rate": 0.0001912726310288756, "loss": 0.6802836418151855, "step": 114670 }, { "epoch": 0.681681735233102, "grad_norm": 1.6112810373306274, "learning_rate": 0.0001912699568036909, "loss": 0.7283382892608643, "step": 114680 }, { "epoch": 0.6817411773097705, "grad_norm": 1.6563178300857544, "learning_rate": 0.00019126728218973722, "loss": 0.6953655242919922, "step": 114690 }, { "epoch": 0.6818006193864389, "grad_norm": 1.4034608602523804, "learning_rate": 0.00019126460718702748, "loss": 0.6486406326293945, "step": 114700 }, { "epoch": 0.6818600614631073, "grad_norm": 1.7937407493591309, "learning_rate": 0.00019126193179557437, "loss": 0.6927920341491699, "step": 114710 }, { "epoch": 0.6819195035397757, "grad_norm": 1.662416934967041, "learning_rate": 0.00019125925601539074, "loss": 0.6611963272094726, "step": 114720 }, { "epoch": 0.681978945616444, "grad_norm": 2.005575180053711, "learning_rate": 0.00019125657984648943, "loss": 0.713594913482666, "step": 114730 }, { "epoch": 0.6820383876931124, "grad_norm": 1.6952193975448608, "learning_rate": 0.00019125390328888315, "loss": 0.6528901576995849, "step": 114740 }, { "epoch": 0.6820978297697808, "grad_norm": 1.8619163036346436, "learning_rate": 0.00019125122634258476, "loss": 0.6089331626892089, "step": 114750 }, { "epoch": 0.6821572718464493, "grad_norm": 2.2265095710754395, "learning_rate": 0.0001912485490076071, "loss": 0.7011187076568604, "step": 114760 }, { "epoch": 0.6822167139231177, "grad_norm": 1.7874737977981567, "learning_rate": 0.00019124587128396288, "loss": 0.6777939796447754, "step": 114770 }, { "epoch": 0.682276155999786, "grad_norm": 1.367950439453125, "learning_rate": 0.00019124319317166498, "loss": 0.6862602710723877, "step": 114780 }, { "epoch": 0.6823355980764544, "grad_norm": 1.714317798614502, "learning_rate": 0.00019124051467072622, "loss": 0.7073997497558594, "step": 114790 }, { "epoch": 0.6823950401531228, "grad_norm": 1.4235304594039917, "learning_rate": 0.00019123783578115934, "loss": 0.6213392734527587, "step": 114800 }, { "epoch": 0.6824544822297912, "grad_norm": 1.5748189687728882, "learning_rate": 0.00019123515650297724, "loss": 0.5769392967224121, "step": 114810 }, { "epoch": 0.6825139243064595, "grad_norm": 1.601991891860962, "learning_rate": 0.00019123247683619268, "loss": 0.6718583583831788, "step": 114820 }, { "epoch": 0.6825733663831279, "grad_norm": 1.7084721326828003, "learning_rate": 0.00019122979678081852, "loss": 0.6560460090637207, "step": 114830 }, { "epoch": 0.6826328084597963, "grad_norm": 1.6369112730026245, "learning_rate": 0.00019122711633686753, "loss": 0.6792553901672364, "step": 114840 }, { "epoch": 0.6826922505364648, "grad_norm": 1.7699480056762695, "learning_rate": 0.00019122443550435256, "loss": 0.6692992210388183, "step": 114850 }, { "epoch": 0.6827516926131332, "grad_norm": 1.2982666492462158, "learning_rate": 0.00019122175428328643, "loss": 0.6844564437866211, "step": 114860 }, { "epoch": 0.6828111346898015, "grad_norm": 1.5185483694076538, "learning_rate": 0.00019121907267368203, "loss": 0.6883156299591064, "step": 114870 }, { "epoch": 0.6828705767664699, "grad_norm": 1.8270241022109985, "learning_rate": 0.00019121639067555207, "loss": 0.6693297863006592, "step": 114880 }, { "epoch": 0.6829300188431383, "grad_norm": 1.6465027332305908, "learning_rate": 0.00019121370828890946, "loss": 0.6621492862701416, "step": 114890 }, { "epoch": 0.6829894609198067, "grad_norm": 1.8667117357254028, "learning_rate": 0.00019121102551376698, "loss": 0.6761421203613281, "step": 114900 }, { "epoch": 0.6830489029964751, "grad_norm": 1.5914497375488281, "learning_rate": 0.00019120834235013755, "loss": 0.6513987064361573, "step": 114910 }, { "epoch": 0.6831083450731434, "grad_norm": 1.7116442918777466, "learning_rate": 0.0001912056587980339, "loss": 0.6628595352172851, "step": 114920 }, { "epoch": 0.6831677871498119, "grad_norm": 1.6276406049728394, "learning_rate": 0.00019120297485746896, "loss": 0.6923614025115967, "step": 114930 }, { "epoch": 0.6832272292264803, "grad_norm": 1.6209228038787842, "learning_rate": 0.0001912002905284555, "loss": 0.7412379264831543, "step": 114940 }, { "epoch": 0.6832866713031487, "grad_norm": 1.8424603939056396, "learning_rate": 0.0001911976058110064, "loss": 0.6406556129455566, "step": 114950 }, { "epoch": 0.683346113379817, "grad_norm": 1.3726173639297485, "learning_rate": 0.00019119492070513447, "loss": 0.7576682567596436, "step": 114960 }, { "epoch": 0.6834055554564854, "grad_norm": 1.6321707963943481, "learning_rate": 0.00019119223521085255, "loss": 0.7160642623901368, "step": 114970 }, { "epoch": 0.6834649975331538, "grad_norm": 1.4700487852096558, "learning_rate": 0.00019118954932817358, "loss": 0.6476799011230469, "step": 114980 }, { "epoch": 0.6835244396098222, "grad_norm": 1.1359750032424927, "learning_rate": 0.0001911868630571103, "loss": 0.6351217269897461, "step": 114990 }, { "epoch": 0.6835838816864906, "grad_norm": 2.1862740516662598, "learning_rate": 0.00019118417639767558, "loss": 0.6778264999389648, "step": 115000 }, { "epoch": 0.683643323763159, "grad_norm": 1.9949747323989868, "learning_rate": 0.00019118148934988235, "loss": 0.7082941055297851, "step": 115010 }, { "epoch": 0.6837027658398274, "grad_norm": 2.076223850250244, "learning_rate": 0.00019117880191374335, "loss": 0.6825379371643067, "step": 115020 }, { "epoch": 0.6837622079164958, "grad_norm": 1.4909682273864746, "learning_rate": 0.0001911761140892715, "loss": 0.6068181991577148, "step": 115030 }, { "epoch": 0.6838216499931642, "grad_norm": 2.011611223220825, "learning_rate": 0.0001911734258764797, "loss": 0.6524054527282714, "step": 115040 }, { "epoch": 0.6838810920698325, "grad_norm": 1.3714890480041504, "learning_rate": 0.0001911707372753807, "loss": 0.6836717605590821, "step": 115050 }, { "epoch": 0.6839405341465009, "grad_norm": 1.7913908958435059, "learning_rate": 0.00019116804828598743, "loss": 0.6814707756042481, "step": 115060 }, { "epoch": 0.6839999762231693, "grad_norm": 1.6289299726486206, "learning_rate": 0.00019116535890831274, "loss": 0.6451291084289551, "step": 115070 }, { "epoch": 0.6840594182998377, "grad_norm": 1.6209388971328735, "learning_rate": 0.0001911626691423695, "loss": 0.6885847091674805, "step": 115080 }, { "epoch": 0.6841188603765062, "grad_norm": 1.4465445280075073, "learning_rate": 0.00019115997898817063, "loss": 0.6098072052001953, "step": 115090 }, { "epoch": 0.6841783024531745, "grad_norm": 1.4795135259628296, "learning_rate": 0.00019115728844572888, "loss": 0.6915350914001465, "step": 115100 }, { "epoch": 0.6842377445298429, "grad_norm": 1.4971555471420288, "learning_rate": 0.0001911545975150572, "loss": 0.6729769706726074, "step": 115110 }, { "epoch": 0.6842971866065113, "grad_norm": 1.2022846937179565, "learning_rate": 0.00019115190619616845, "loss": 0.5975752353668213, "step": 115120 }, { "epoch": 0.6843566286831797, "grad_norm": 1.8390871286392212, "learning_rate": 0.0001911492144890755, "loss": 0.7353307723999023, "step": 115130 }, { "epoch": 0.6844160707598481, "grad_norm": 1.7649956941604614, "learning_rate": 0.00019114652239379123, "loss": 0.7044047355651856, "step": 115140 }, { "epoch": 0.6844755128365164, "grad_norm": 1.7819074392318726, "learning_rate": 0.0001911438299103285, "loss": 0.7157896995544434, "step": 115150 }, { "epoch": 0.6845349549131848, "grad_norm": 1.686544418334961, "learning_rate": 0.00019114113703870022, "loss": 0.6332254886627198, "step": 115160 }, { "epoch": 0.6845943969898532, "grad_norm": 1.9270148277282715, "learning_rate": 0.00019113844377891928, "loss": 0.670687198638916, "step": 115170 }, { "epoch": 0.6846538390665217, "grad_norm": 2.044159173965454, "learning_rate": 0.0001911357501309985, "loss": 0.6990900993347168, "step": 115180 }, { "epoch": 0.68471328114319, "grad_norm": 1.814465045928955, "learning_rate": 0.00019113305609495086, "loss": 0.675997257232666, "step": 115190 }, { "epoch": 0.6847727232198584, "grad_norm": 1.5463886260986328, "learning_rate": 0.00019113036167078912, "loss": 0.6546402931213379, "step": 115200 }, { "epoch": 0.6848321652965268, "grad_norm": 1.7451629638671875, "learning_rate": 0.0001911276668585263, "loss": 0.6773991584777832, "step": 115210 }, { "epoch": 0.6848916073731952, "grad_norm": 1.648613452911377, "learning_rate": 0.00019112497165817523, "loss": 0.6361905097961426, "step": 115220 }, { "epoch": 0.6849510494498636, "grad_norm": 1.8526346683502197, "learning_rate": 0.00019112227606974877, "loss": 0.7116065979003906, "step": 115230 }, { "epoch": 0.6850104915265319, "grad_norm": 2.340261697769165, "learning_rate": 0.0001911195800932599, "loss": 0.6872869491577148, "step": 115240 }, { "epoch": 0.6850699336032003, "grad_norm": 1.6632041931152344, "learning_rate": 0.00019111688372872146, "loss": 0.6537127494812012, "step": 115250 }, { "epoch": 0.6851293756798688, "grad_norm": 1.5654112100601196, "learning_rate": 0.0001911141869761463, "loss": 0.6533093452453613, "step": 115260 }, { "epoch": 0.6851888177565372, "grad_norm": 1.6015130281448364, "learning_rate": 0.00019111148983554744, "loss": 0.6708880424499511, "step": 115270 }, { "epoch": 0.6852482598332056, "grad_norm": 1.683490514755249, "learning_rate": 0.0001911087923069377, "loss": 0.6770812034606933, "step": 115280 }, { "epoch": 0.6853077019098739, "grad_norm": 1.3763848543167114, "learning_rate": 0.00019110609439033, "loss": 0.6623546600341796, "step": 115290 }, { "epoch": 0.6853671439865423, "grad_norm": 1.7440434694290161, "learning_rate": 0.00019110339608573726, "loss": 0.6945586204528809, "step": 115300 }, { "epoch": 0.6854265860632107, "grad_norm": 1.271620512008667, "learning_rate": 0.00019110069739317238, "loss": 0.6312544822692872, "step": 115310 }, { "epoch": 0.6854860281398791, "grad_norm": 1.7425098419189453, "learning_rate": 0.00019109799831264828, "loss": 0.7573997020721436, "step": 115320 }, { "epoch": 0.6855454702165474, "grad_norm": 1.6593928337097168, "learning_rate": 0.00019109529884417782, "loss": 0.6879040718078613, "step": 115330 }, { "epoch": 0.6856049122932159, "grad_norm": 1.8832110166549683, "learning_rate": 0.00019109259898777398, "loss": 0.6772665977478027, "step": 115340 }, { "epoch": 0.6856643543698843, "grad_norm": 1.6342684030532837, "learning_rate": 0.00019108989874344964, "loss": 0.6698884010314942, "step": 115350 }, { "epoch": 0.6857237964465527, "grad_norm": 1.7329143285751343, "learning_rate": 0.00019108719811121772, "loss": 0.6269855499267578, "step": 115360 }, { "epoch": 0.6857832385232211, "grad_norm": 1.7995659112930298, "learning_rate": 0.00019108449709109116, "loss": 0.6932351589202881, "step": 115370 }, { "epoch": 0.6858426805998894, "grad_norm": 1.6701087951660156, "learning_rate": 0.00019108179568308285, "loss": 0.684865665435791, "step": 115380 }, { "epoch": 0.6859021226765578, "grad_norm": 1.8313525915145874, "learning_rate": 0.00019107909388720574, "loss": 0.6684212207794189, "step": 115390 }, { "epoch": 0.6859615647532262, "grad_norm": 1.6537604331970215, "learning_rate": 0.00019107639170347273, "loss": 0.6383790969848633, "step": 115400 }, { "epoch": 0.6860210068298946, "grad_norm": 1.757838487625122, "learning_rate": 0.00019107368913189675, "loss": 0.6684674739837646, "step": 115410 }, { "epoch": 0.686080448906563, "grad_norm": 2.1313090324401855, "learning_rate": 0.00019107098617249078, "loss": 0.714995002746582, "step": 115420 }, { "epoch": 0.6861398909832314, "grad_norm": 1.4940171241760254, "learning_rate": 0.00019106828282526765, "loss": 0.6949301719665527, "step": 115430 }, { "epoch": 0.6861993330598998, "grad_norm": 1.6719918251037598, "learning_rate": 0.0001910655790902404, "loss": 0.6666394233703613, "step": 115440 }, { "epoch": 0.6862587751365682, "grad_norm": 1.735844612121582, "learning_rate": 0.00019106287496742187, "loss": 0.6600506782531739, "step": 115450 }, { "epoch": 0.6863182172132366, "grad_norm": 2.1735787391662598, "learning_rate": 0.00019106017045682504, "loss": 0.6975804328918457, "step": 115460 }, { "epoch": 0.6863776592899049, "grad_norm": 1.6925307512283325, "learning_rate": 0.00019105746555846286, "loss": 0.7005278110504151, "step": 115470 }, { "epoch": 0.6864371013665733, "grad_norm": 1.4483654499053955, "learning_rate": 0.00019105476027234827, "loss": 0.7262568950653077, "step": 115480 }, { "epoch": 0.6864965434432417, "grad_norm": 1.7107300758361816, "learning_rate": 0.00019105205459849417, "loss": 0.643128776550293, "step": 115490 }, { "epoch": 0.6865559855199102, "grad_norm": 1.5359430313110352, "learning_rate": 0.00019104934853691354, "loss": 0.6807766437530518, "step": 115500 }, { "epoch": 0.6866154275965786, "grad_norm": 1.7773077487945557, "learning_rate": 0.00019104664208761932, "loss": 0.6593318939208984, "step": 115510 }, { "epoch": 0.6866748696732469, "grad_norm": 1.6532353162765503, "learning_rate": 0.00019104393525062446, "loss": 0.6973597049713135, "step": 115520 }, { "epoch": 0.6867343117499153, "grad_norm": 1.8063300848007202, "learning_rate": 0.00019104122802594188, "loss": 0.6974331378936768, "step": 115530 }, { "epoch": 0.6867937538265837, "grad_norm": 1.394708275794983, "learning_rate": 0.00019103852041358455, "loss": 0.6890265464782714, "step": 115540 }, { "epoch": 0.6868531959032521, "grad_norm": 1.6019006967544556, "learning_rate": 0.00019103581241356542, "loss": 0.6790017127990723, "step": 115550 }, { "epoch": 0.6869126379799204, "grad_norm": 1.4699472188949585, "learning_rate": 0.00019103310402589742, "loss": 0.6948695182800293, "step": 115560 }, { "epoch": 0.6869720800565888, "grad_norm": 1.7050762176513672, "learning_rate": 0.00019103039525059356, "loss": 0.6802631378173828, "step": 115570 }, { "epoch": 0.6870315221332572, "grad_norm": 1.4919543266296387, "learning_rate": 0.0001910276860876668, "loss": 0.5589215755462646, "step": 115580 }, { "epoch": 0.6870909642099257, "grad_norm": 1.5652542114257812, "learning_rate": 0.00019102497653713003, "loss": 0.6726243972778321, "step": 115590 }, { "epoch": 0.6871504062865941, "grad_norm": 1.7466368675231934, "learning_rate": 0.00019102226659899627, "loss": 0.7179831504821778, "step": 115600 }, { "epoch": 0.6872098483632624, "grad_norm": 1.9264090061187744, "learning_rate": 0.00019101955627327845, "loss": 0.6494014739990235, "step": 115610 }, { "epoch": 0.6872692904399308, "grad_norm": 1.5236573219299316, "learning_rate": 0.00019101684555998958, "loss": 0.6346903324127198, "step": 115620 }, { "epoch": 0.6873287325165992, "grad_norm": 1.5929917097091675, "learning_rate": 0.0001910141344591426, "loss": 0.6438475608825683, "step": 115630 }, { "epoch": 0.6873881745932676, "grad_norm": 1.5630879402160645, "learning_rate": 0.0001910114229707504, "loss": 0.6420515537261963, "step": 115640 }, { "epoch": 0.687447616669936, "grad_norm": 1.8775080442428589, "learning_rate": 0.00019100871109482611, "loss": 0.7092072486877441, "step": 115650 }, { "epoch": 0.6875070587466043, "grad_norm": 1.5058505535125732, "learning_rate": 0.0001910059988313826, "loss": 0.6591248035430908, "step": 115660 }, { "epoch": 0.6875665008232728, "grad_norm": 2.03330135345459, "learning_rate": 0.00019100328618043287, "loss": 0.6345128059387207, "step": 115670 }, { "epoch": 0.6876259428999412, "grad_norm": 1.7482057809829712, "learning_rate": 0.00019100057314198985, "loss": 0.7249520301818848, "step": 115680 }, { "epoch": 0.6876853849766096, "grad_norm": 1.8706315755844116, "learning_rate": 0.00019099785971606658, "loss": 0.6696013450622559, "step": 115690 }, { "epoch": 0.6877448270532779, "grad_norm": 1.6314674615859985, "learning_rate": 0.00019099514590267602, "loss": 0.6062516212463379, "step": 115700 }, { "epoch": 0.6878042691299463, "grad_norm": 1.6341428756713867, "learning_rate": 0.00019099243170183115, "loss": 0.7093191146850586, "step": 115710 }, { "epoch": 0.6878637112066147, "grad_norm": 2.080301284790039, "learning_rate": 0.00019098971711354498, "loss": 0.6612665176391601, "step": 115720 }, { "epoch": 0.6879231532832831, "grad_norm": 1.7181687355041504, "learning_rate": 0.00019098700213783046, "loss": 0.7036595344543457, "step": 115730 }, { "epoch": 0.6879825953599515, "grad_norm": 2.097778797149658, "learning_rate": 0.00019098428677470058, "loss": 0.6993832588195801, "step": 115740 }, { "epoch": 0.6880420374366198, "grad_norm": 1.3854007720947266, "learning_rate": 0.0001909815710241683, "loss": 0.6773063659667968, "step": 115750 }, { "epoch": 0.6881014795132883, "grad_norm": 1.8618532419204712, "learning_rate": 0.00019097885488624674, "loss": 0.6507999420166015, "step": 115760 }, { "epoch": 0.6881609215899567, "grad_norm": 1.5677601099014282, "learning_rate": 0.00019097613836094874, "loss": 0.6180253982543945, "step": 115770 }, { "epoch": 0.6882203636666251, "grad_norm": 1.7218748331069946, "learning_rate": 0.00019097342144828736, "loss": 0.6425143241882324, "step": 115780 }, { "epoch": 0.6882798057432934, "grad_norm": 1.5158116817474365, "learning_rate": 0.0001909707041482756, "loss": 0.6783867835998535, "step": 115790 }, { "epoch": 0.6883392478199618, "grad_norm": 1.5140342712402344, "learning_rate": 0.00019096798646092643, "loss": 0.6560441017150879, "step": 115800 }, { "epoch": 0.6883986898966302, "grad_norm": 1.7674092054367065, "learning_rate": 0.00019096526838625292, "loss": 0.6685033321380616, "step": 115810 }, { "epoch": 0.6884581319732986, "grad_norm": 1.6425937414169312, "learning_rate": 0.00019096254992426802, "loss": 0.7418638229370117, "step": 115820 }, { "epoch": 0.688517574049967, "grad_norm": 2.63269305229187, "learning_rate": 0.00019095983107498472, "loss": 0.7293325901031494, "step": 115830 }, { "epoch": 0.6885770161266354, "grad_norm": 1.705518126487732, "learning_rate": 0.00019095711183841606, "loss": 0.7035367965698243, "step": 115840 }, { "epoch": 0.6886364582033038, "grad_norm": 1.4857124090194702, "learning_rate": 0.00019095439221457502, "loss": 0.6392212867736816, "step": 115850 }, { "epoch": 0.6886959002799722, "grad_norm": 2.0383479595184326, "learning_rate": 0.00019095167220347463, "loss": 0.6676008224487304, "step": 115860 }, { "epoch": 0.6887553423566406, "grad_norm": 1.7103878259658813, "learning_rate": 0.00019094895180512788, "loss": 0.7073565006256104, "step": 115870 }, { "epoch": 0.688814784433309, "grad_norm": 1.7013146877288818, "learning_rate": 0.00019094623101954784, "loss": 0.6788089752197266, "step": 115880 }, { "epoch": 0.6888742265099773, "grad_norm": 1.9573265314102173, "learning_rate": 0.00019094350984674745, "loss": 0.7033091068267823, "step": 115890 }, { "epoch": 0.6889336685866457, "grad_norm": 1.4358799457550049, "learning_rate": 0.00019094078828673977, "loss": 0.6508448600769043, "step": 115900 }, { "epoch": 0.6889931106633141, "grad_norm": 1.738005518913269, "learning_rate": 0.0001909380663395378, "loss": 0.6991927146911621, "step": 115910 }, { "epoch": 0.6890525527399826, "grad_norm": 1.5664888620376587, "learning_rate": 0.0001909353440051546, "loss": 0.7092769622802735, "step": 115920 }, { "epoch": 0.6891119948166509, "grad_norm": 1.7443643808364868, "learning_rate": 0.00019093262128360312, "loss": 0.7396801471710205, "step": 115930 }, { "epoch": 0.6891714368933193, "grad_norm": 1.8466882705688477, "learning_rate": 0.0001909298981748965, "loss": 0.6837443828582763, "step": 115940 }, { "epoch": 0.6892308789699877, "grad_norm": 1.4409077167510986, "learning_rate": 0.00019092717467904762, "loss": 0.6743412971496582, "step": 115950 }, { "epoch": 0.6892903210466561, "grad_norm": 1.7055906057357788, "learning_rate": 0.0001909244507960696, "loss": 0.6464704513549805, "step": 115960 }, { "epoch": 0.6893497631233245, "grad_norm": 1.777613878250122, "learning_rate": 0.00019092172652597546, "loss": 0.643394947052002, "step": 115970 }, { "epoch": 0.6894092051999928, "grad_norm": 1.4437530040740967, "learning_rate": 0.00019091900186877825, "loss": 0.6042797088623046, "step": 115980 }, { "epoch": 0.6894686472766612, "grad_norm": 1.816994309425354, "learning_rate": 0.00019091627682449097, "loss": 0.7124871253967285, "step": 115990 }, { "epoch": 0.6895280893533297, "grad_norm": 1.5687226057052612, "learning_rate": 0.00019091355139312665, "loss": 0.6472755432128906, "step": 116000 }, { "epoch": 0.6895875314299981, "grad_norm": 2.0163252353668213, "learning_rate": 0.00019091082557469834, "loss": 0.6433338642120361, "step": 116010 }, { "epoch": 0.6896469735066665, "grad_norm": 1.2193689346313477, "learning_rate": 0.0001909080993692191, "loss": 0.6612096786499023, "step": 116020 }, { "epoch": 0.6897064155833348, "grad_norm": 1.4996157884597778, "learning_rate": 0.00019090537277670195, "loss": 0.727671766281128, "step": 116030 }, { "epoch": 0.6897658576600032, "grad_norm": 1.8737285137176514, "learning_rate": 0.00019090264579715995, "loss": 0.6539314270019532, "step": 116040 }, { "epoch": 0.6898252997366716, "grad_norm": 2.23285174369812, "learning_rate": 0.0001908999184306061, "loss": 0.7297933578491211, "step": 116050 }, { "epoch": 0.68988474181334, "grad_norm": 1.7630133628845215, "learning_rate": 0.0001908971906770535, "loss": 0.6673792839050293, "step": 116060 }, { "epoch": 0.6899441838900083, "grad_norm": 1.8585317134857178, "learning_rate": 0.00019089446253651516, "loss": 0.677972412109375, "step": 116070 }, { "epoch": 0.6900036259666767, "grad_norm": 2.1885437965393066, "learning_rate": 0.00019089173400900416, "loss": 0.678328275680542, "step": 116080 }, { "epoch": 0.6900630680433452, "grad_norm": 1.6815193891525269, "learning_rate": 0.00019088900509453357, "loss": 0.6370237350463868, "step": 116090 }, { "epoch": 0.6901225101200136, "grad_norm": 2.0272116661071777, "learning_rate": 0.00019088627579311635, "loss": 0.7155754089355468, "step": 116100 }, { "epoch": 0.690181952196682, "grad_norm": 1.495432734489441, "learning_rate": 0.00019088354610476567, "loss": 0.6397464752197266, "step": 116110 }, { "epoch": 0.6902413942733503, "grad_norm": 1.86581289768219, "learning_rate": 0.0001908808160294945, "loss": 0.6283041477203369, "step": 116120 }, { "epoch": 0.6903008363500187, "grad_norm": 1.6249232292175293, "learning_rate": 0.00019087808556731597, "loss": 0.7132282257080078, "step": 116130 }, { "epoch": 0.6903602784266871, "grad_norm": 1.6910631656646729, "learning_rate": 0.0001908753547182431, "loss": 0.709494161605835, "step": 116140 }, { "epoch": 0.6904197205033555, "grad_norm": 1.732520580291748, "learning_rate": 0.00019087262348228896, "loss": 0.6650456428527832, "step": 116150 }, { "epoch": 0.6904791625800238, "grad_norm": 1.9563966989517212, "learning_rate": 0.00019086989185946665, "loss": 0.6647674560546875, "step": 116160 }, { "epoch": 0.6905386046566923, "grad_norm": 1.8831121921539307, "learning_rate": 0.00019086715984978917, "loss": 0.7037263870239258, "step": 116170 }, { "epoch": 0.6905980467333607, "grad_norm": 1.8090897798538208, "learning_rate": 0.00019086442745326962, "loss": 0.640515661239624, "step": 116180 }, { "epoch": 0.6906574888100291, "grad_norm": 2.150148868560791, "learning_rate": 0.0001908616946699211, "loss": 0.7286263942718506, "step": 116190 }, { "epoch": 0.6907169308866975, "grad_norm": 1.856867790222168, "learning_rate": 0.00019085896149975665, "loss": 0.6603316783905029, "step": 116200 }, { "epoch": 0.6907763729633658, "grad_norm": 2.1883182525634766, "learning_rate": 0.00019085622794278934, "loss": 0.6881092071533204, "step": 116210 }, { "epoch": 0.6908358150400342, "grad_norm": 1.5675066709518433, "learning_rate": 0.00019085349399903227, "loss": 0.664050817489624, "step": 116220 }, { "epoch": 0.6908952571167026, "grad_norm": 1.848832607269287, "learning_rate": 0.00019085075966849852, "loss": 0.6664857864379883, "step": 116230 }, { "epoch": 0.690954699193371, "grad_norm": 1.832074761390686, "learning_rate": 0.00019084802495120115, "loss": 0.6748112201690674, "step": 116240 }, { "epoch": 0.6910141412700395, "grad_norm": 1.6631814241409302, "learning_rate": 0.00019084528984715323, "loss": 0.6773957729339599, "step": 116250 }, { "epoch": 0.6910735833467078, "grad_norm": 2.103482246398926, "learning_rate": 0.0001908425543563679, "loss": 0.6441563606262207, "step": 116260 }, { "epoch": 0.6911330254233762, "grad_norm": 1.8155187368392944, "learning_rate": 0.0001908398184788582, "loss": 0.6529677391052247, "step": 116270 }, { "epoch": 0.6911924675000446, "grad_norm": 1.695373296737671, "learning_rate": 0.00019083708221463721, "loss": 0.6959919929504395, "step": 116280 }, { "epoch": 0.691251909576713, "grad_norm": 1.78213369846344, "learning_rate": 0.00019083434556371804, "loss": 0.6807653427124023, "step": 116290 }, { "epoch": 0.6913113516533813, "grad_norm": 1.6317338943481445, "learning_rate": 0.00019083160852611378, "loss": 0.7228961944580078, "step": 116300 }, { "epoch": 0.6913707937300497, "grad_norm": 1.710148572921753, "learning_rate": 0.00019082887110183754, "loss": 0.7061933517456055, "step": 116310 }, { "epoch": 0.6914302358067181, "grad_norm": 2.1252667903900146, "learning_rate": 0.00019082613329090238, "loss": 0.6668802738189697, "step": 116320 }, { "epoch": 0.6914896778833866, "grad_norm": 1.4908831119537354, "learning_rate": 0.00019082339509332138, "loss": 0.6899000644683838, "step": 116330 }, { "epoch": 0.691549119960055, "grad_norm": 1.7799983024597168, "learning_rate": 0.00019082065650910773, "loss": 0.6968158721923828, "step": 116340 }, { "epoch": 0.6916085620367233, "grad_norm": 1.6956580877304077, "learning_rate": 0.00019081791753827444, "loss": 0.6860762596130371, "step": 116350 }, { "epoch": 0.6916680041133917, "grad_norm": 1.5537827014923096, "learning_rate": 0.00019081517818083464, "loss": 0.692650318145752, "step": 116360 }, { "epoch": 0.6917274461900601, "grad_norm": 1.7170764207839966, "learning_rate": 0.00019081243843680146, "loss": 0.6654945373535156, "step": 116370 }, { "epoch": 0.6917868882667285, "grad_norm": 1.9341994524002075, "learning_rate": 0.00019080969830618795, "loss": 0.6627168178558349, "step": 116380 }, { "epoch": 0.6918463303433969, "grad_norm": 1.5899492502212524, "learning_rate": 0.0001908069577890073, "loss": 0.6852484703063965, "step": 116390 }, { "epoch": 0.6919057724200652, "grad_norm": 1.7695529460906982, "learning_rate": 0.00019080421688527256, "loss": 0.6050941467285156, "step": 116400 }, { "epoch": 0.6919652144967336, "grad_norm": 1.5607271194458008, "learning_rate": 0.00019080147559499678, "loss": 0.6569309711456299, "step": 116410 }, { "epoch": 0.6920246565734021, "grad_norm": 1.704474925994873, "learning_rate": 0.00019079873391819325, "loss": 0.728053617477417, "step": 116420 }, { "epoch": 0.6920840986500705, "grad_norm": 1.743468165397644, "learning_rate": 0.00019079599185487493, "loss": 0.6134121417999268, "step": 116430 }, { "epoch": 0.6921435407267388, "grad_norm": 1.6023999452590942, "learning_rate": 0.000190793249405055, "loss": 0.6370209693908692, "step": 116440 }, { "epoch": 0.6922029828034072, "grad_norm": 1.9213902950286865, "learning_rate": 0.00019079050656874657, "loss": 0.723105525970459, "step": 116450 }, { "epoch": 0.6922624248800756, "grad_norm": 1.6020927429199219, "learning_rate": 0.00019078776334596276, "loss": 0.6953287124633789, "step": 116460 }, { "epoch": 0.692321866956744, "grad_norm": 1.3817143440246582, "learning_rate": 0.0001907850197367167, "loss": 0.6090020179748535, "step": 116470 }, { "epoch": 0.6923813090334124, "grad_norm": 1.8130900859832764, "learning_rate": 0.00019078227574102148, "loss": 0.6903413772583008, "step": 116480 }, { "epoch": 0.6924407511100807, "grad_norm": 1.7222779989242554, "learning_rate": 0.00019077953135889026, "loss": 0.6716832160949707, "step": 116490 }, { "epoch": 0.6925001931867492, "grad_norm": 1.9646705389022827, "learning_rate": 0.00019077678659033616, "loss": 0.6809898853302002, "step": 116500 }, { "epoch": 0.6925596352634176, "grad_norm": 2.3109097480773926, "learning_rate": 0.00019077404143537233, "loss": 0.6581084251403808, "step": 116510 }, { "epoch": 0.692619077340086, "grad_norm": 1.8646219968795776, "learning_rate": 0.00019077129589401188, "loss": 0.640659236907959, "step": 116520 }, { "epoch": 0.6926785194167543, "grad_norm": 1.7600338459014893, "learning_rate": 0.0001907685499662679, "loss": 0.6347939968109131, "step": 116530 }, { "epoch": 0.6927379614934227, "grad_norm": 1.7150912284851074, "learning_rate": 0.00019076580365215363, "loss": 0.692160701751709, "step": 116540 }, { "epoch": 0.6927974035700911, "grad_norm": 1.626602292060852, "learning_rate": 0.00019076305695168213, "loss": 0.6887282371520996, "step": 116550 }, { "epoch": 0.6928568456467595, "grad_norm": 1.7487794160842896, "learning_rate": 0.00019076030986486654, "loss": 0.6911272048950196, "step": 116560 }, { "epoch": 0.692916287723428, "grad_norm": 1.881077527999878, "learning_rate": 0.00019075756239172008, "loss": 0.6680278301239013, "step": 116570 }, { "epoch": 0.6929757298000963, "grad_norm": 1.7482094764709473, "learning_rate": 0.00019075481453225578, "loss": 0.6941850662231446, "step": 116580 }, { "epoch": 0.6930351718767647, "grad_norm": 1.8973637819290161, "learning_rate": 0.00019075206628648686, "loss": 0.6881365776062012, "step": 116590 }, { "epoch": 0.6930946139534331, "grad_norm": 1.3097273111343384, "learning_rate": 0.00019074931765442643, "loss": 0.630699872970581, "step": 116600 }, { "epoch": 0.6931540560301015, "grad_norm": 1.6571269035339355, "learning_rate": 0.00019074656863608767, "loss": 0.6719707489013672, "step": 116610 }, { "epoch": 0.6932134981067699, "grad_norm": 1.2814773321151733, "learning_rate": 0.00019074381923148368, "loss": 0.643086051940918, "step": 116620 }, { "epoch": 0.6932729401834382, "grad_norm": 1.482649326324463, "learning_rate": 0.00019074106944062767, "loss": 0.6633325576782226, "step": 116630 }, { "epoch": 0.6933323822601066, "grad_norm": 1.722847819328308, "learning_rate": 0.0001907383192635328, "loss": 0.6554618835449219, "step": 116640 }, { "epoch": 0.693391824336775, "grad_norm": 1.532657504081726, "learning_rate": 0.00019073556870021215, "loss": 0.6243528842926025, "step": 116650 }, { "epoch": 0.6934512664134435, "grad_norm": 1.3387142419815063, "learning_rate": 0.00019073281775067893, "loss": 0.7163294792175293, "step": 116660 }, { "epoch": 0.6935107084901118, "grad_norm": 1.7610610723495483, "learning_rate": 0.0001907300664149463, "loss": 0.681964921951294, "step": 116670 }, { "epoch": 0.6935701505667802, "grad_norm": 1.422244668006897, "learning_rate": 0.00019072731469302746, "loss": 0.6315422058105469, "step": 116680 }, { "epoch": 0.6936295926434486, "grad_norm": 1.7221978902816772, "learning_rate": 0.00019072456258493548, "loss": 0.6790359020233154, "step": 116690 }, { "epoch": 0.693689034720117, "grad_norm": 1.6474661827087402, "learning_rate": 0.00019072181009068359, "loss": 0.6278486251831055, "step": 116700 }, { "epoch": 0.6937484767967854, "grad_norm": 1.2991173267364502, "learning_rate": 0.0001907190572102849, "loss": 0.6743461608886718, "step": 116710 }, { "epoch": 0.6938079188734537, "grad_norm": 2.1022236347198486, "learning_rate": 0.00019071630394375266, "loss": 0.6643672943115234, "step": 116720 }, { "epoch": 0.6938673609501221, "grad_norm": 2.060161590576172, "learning_rate": 0.0001907135502911, "loss": 0.6535739421844482, "step": 116730 }, { "epoch": 0.6939268030267906, "grad_norm": 1.7853045463562012, "learning_rate": 0.00019071079625234007, "loss": 0.6739975929260253, "step": 116740 }, { "epoch": 0.693986245103459, "grad_norm": 1.836498498916626, "learning_rate": 0.00019070804182748607, "loss": 0.6248127937316894, "step": 116750 }, { "epoch": 0.6940456871801274, "grad_norm": 1.8098626136779785, "learning_rate": 0.0001907052870165512, "loss": 0.6656360626220703, "step": 116760 }, { "epoch": 0.6941051292567957, "grad_norm": 1.3405191898345947, "learning_rate": 0.0001907025318195486, "loss": 0.6460220336914062, "step": 116770 }, { "epoch": 0.6941645713334641, "grad_norm": 1.7717431783676147, "learning_rate": 0.00019069977623649146, "loss": 0.6984024047851562, "step": 116780 }, { "epoch": 0.6942240134101325, "grad_norm": 1.4645894765853882, "learning_rate": 0.00019069702026739297, "loss": 0.6079646110534668, "step": 116790 }, { "epoch": 0.6942834554868009, "grad_norm": 1.3215492963790894, "learning_rate": 0.00019069426391226632, "loss": 0.6197210788726807, "step": 116800 }, { "epoch": 0.6943428975634692, "grad_norm": 1.8656256198883057, "learning_rate": 0.00019069150717112462, "loss": 0.6439522743225098, "step": 116810 }, { "epoch": 0.6944023396401376, "grad_norm": 1.7032771110534668, "learning_rate": 0.0001906887500439812, "loss": 0.679390811920166, "step": 116820 }, { "epoch": 0.6944617817168061, "grad_norm": 1.8969593048095703, "learning_rate": 0.00019068599253084913, "loss": 0.6844573020935059, "step": 116830 }, { "epoch": 0.6945212237934745, "grad_norm": 1.5618616342544556, "learning_rate": 0.00019068323463174164, "loss": 0.7346185684204102, "step": 116840 }, { "epoch": 0.6945806658701429, "grad_norm": 1.6311984062194824, "learning_rate": 0.00019068047634667192, "loss": 0.6346721649169922, "step": 116850 }, { "epoch": 0.6946401079468112, "grad_norm": 1.7121531963348389, "learning_rate": 0.00019067771767565316, "loss": 0.6670877456665039, "step": 116860 }, { "epoch": 0.6946995500234796, "grad_norm": 1.7953063249588013, "learning_rate": 0.0001906749586186986, "loss": 0.5896005630493164, "step": 116870 }, { "epoch": 0.694758992100148, "grad_norm": 1.457434892654419, "learning_rate": 0.00019067219917582136, "loss": 0.651052713394165, "step": 116880 }, { "epoch": 0.6948184341768164, "grad_norm": 1.5521939992904663, "learning_rate": 0.0001906694393470347, "loss": 0.6752548217773438, "step": 116890 }, { "epoch": 0.6948778762534847, "grad_norm": 1.4077801704406738, "learning_rate": 0.00019066667913235184, "loss": 0.642646598815918, "step": 116900 }, { "epoch": 0.6949373183301532, "grad_norm": 1.7546991109848022, "learning_rate": 0.0001906639185317859, "loss": 0.6546602249145508, "step": 116910 }, { "epoch": 0.6949967604068216, "grad_norm": 1.8305453062057495, "learning_rate": 0.00019066115754535015, "loss": 0.7157536506652832, "step": 116920 }, { "epoch": 0.69505620248349, "grad_norm": 1.6480313539505005, "learning_rate": 0.0001906583961730578, "loss": 0.5994736671447753, "step": 116930 }, { "epoch": 0.6951156445601584, "grad_norm": 1.9531041383743286, "learning_rate": 0.00019065563441492201, "loss": 0.6933406829833985, "step": 116940 }, { "epoch": 0.6951750866368267, "grad_norm": 1.7793642282485962, "learning_rate": 0.00019065287227095604, "loss": 0.6652366638183593, "step": 116950 }, { "epoch": 0.6952345287134951, "grad_norm": 1.4304996728897095, "learning_rate": 0.0001906501097411731, "loss": 0.649260425567627, "step": 116960 }, { "epoch": 0.6952939707901635, "grad_norm": 1.49122154712677, "learning_rate": 0.00019064734682558638, "loss": 0.6472380638122559, "step": 116970 }, { "epoch": 0.6953534128668319, "grad_norm": 1.9934567213058472, "learning_rate": 0.0001906445835242091, "loss": 0.6937445640563965, "step": 116980 }, { "epoch": 0.6954128549435004, "grad_norm": 1.6519439220428467, "learning_rate": 0.0001906418198370545, "loss": 0.676214599609375, "step": 116990 }, { "epoch": 0.6954722970201687, "grad_norm": 1.4294203519821167, "learning_rate": 0.00019063905576413578, "loss": 0.6635541915893555, "step": 117000 }, { "epoch": 0.6955317390968371, "grad_norm": 2.140329599380493, "learning_rate": 0.00019063629130546618, "loss": 0.6613300323486329, "step": 117010 }, { "epoch": 0.6955911811735055, "grad_norm": 1.6800910234451294, "learning_rate": 0.00019063352646105889, "loss": 0.6735238552093505, "step": 117020 }, { "epoch": 0.6956506232501739, "grad_norm": 1.3681451082229614, "learning_rate": 0.00019063076123092718, "loss": 0.6529771327972412, "step": 117030 }, { "epoch": 0.6957100653268422, "grad_norm": 1.8431639671325684, "learning_rate": 0.00019062799561508426, "loss": 0.7059432983398437, "step": 117040 }, { "epoch": 0.6957695074035106, "grad_norm": 1.9987947940826416, "learning_rate": 0.00019062522961354336, "loss": 0.6227553367614747, "step": 117050 }, { "epoch": 0.695828949480179, "grad_norm": 1.7763317823410034, "learning_rate": 0.00019062246322631773, "loss": 0.6667725563049316, "step": 117060 }, { "epoch": 0.6958883915568475, "grad_norm": 1.7898027896881104, "learning_rate": 0.00019061969645342054, "loss": 0.6623353481292724, "step": 117070 }, { "epoch": 0.6959478336335159, "grad_norm": 1.4694256782531738, "learning_rate": 0.0001906169292948651, "loss": 0.5877380847930909, "step": 117080 }, { "epoch": 0.6960072757101842, "grad_norm": 1.871634840965271, "learning_rate": 0.00019061416175066462, "loss": 0.6985446453094483, "step": 117090 }, { "epoch": 0.6960667177868526, "grad_norm": 1.3964176177978516, "learning_rate": 0.00019061139382083232, "loss": 0.6885666847229004, "step": 117100 }, { "epoch": 0.696126159863521, "grad_norm": 1.710761547088623, "learning_rate": 0.00019060862550538142, "loss": 0.6434681415557861, "step": 117110 }, { "epoch": 0.6961856019401894, "grad_norm": 1.9027994871139526, "learning_rate": 0.00019060585680432527, "loss": 0.7090349674224854, "step": 117120 }, { "epoch": 0.6962450440168578, "grad_norm": 1.6928647756576538, "learning_rate": 0.000190603087717677, "loss": 0.7022783756256104, "step": 117130 }, { "epoch": 0.6963044860935261, "grad_norm": 1.3674801588058472, "learning_rate": 0.00019060031824544987, "loss": 0.6975373268127442, "step": 117140 }, { "epoch": 0.6963639281701945, "grad_norm": 1.6539379358291626, "learning_rate": 0.00019059754838765726, "loss": 0.6402050971984863, "step": 117150 }, { "epoch": 0.696423370246863, "grad_norm": 1.5708290338516235, "learning_rate": 0.0001905947781443122, "loss": 0.7109795570373535, "step": 117160 }, { "epoch": 0.6964828123235314, "grad_norm": 2.287440776824951, "learning_rate": 0.00019059200751542812, "loss": 0.6624798774719238, "step": 117170 }, { "epoch": 0.6965422544001997, "grad_norm": 1.431386947631836, "learning_rate": 0.00019058923650101822, "loss": 0.6168337345123291, "step": 117180 }, { "epoch": 0.6966016964768681, "grad_norm": 1.6188641786575317, "learning_rate": 0.00019058646510109576, "loss": 0.6372843742370605, "step": 117190 }, { "epoch": 0.6966611385535365, "grad_norm": 1.7966352701187134, "learning_rate": 0.00019058369331567397, "loss": 0.6636663913726807, "step": 117200 }, { "epoch": 0.6967205806302049, "grad_norm": 2.0556843280792236, "learning_rate": 0.0001905809211447661, "loss": 0.6954351425170898, "step": 117210 }, { "epoch": 0.6967800227068733, "grad_norm": 1.7657872438430786, "learning_rate": 0.00019057814858838547, "loss": 0.718721580505371, "step": 117220 }, { "epoch": 0.6968394647835416, "grad_norm": 1.6480541229248047, "learning_rate": 0.0001905753756465453, "loss": 0.6343651294708252, "step": 117230 }, { "epoch": 0.69689890686021, "grad_norm": 1.9037189483642578, "learning_rate": 0.00019057260231925886, "loss": 0.713349723815918, "step": 117240 }, { "epoch": 0.6969583489368785, "grad_norm": 1.9143080711364746, "learning_rate": 0.00019056982860653942, "loss": 0.7284796714782715, "step": 117250 }, { "epoch": 0.6970177910135469, "grad_norm": 1.7752493619918823, "learning_rate": 0.00019056705450840026, "loss": 0.7169792175292968, "step": 117260 }, { "epoch": 0.6970772330902152, "grad_norm": 2.038334846496582, "learning_rate": 0.00019056428002485465, "loss": 0.6646296501159668, "step": 117270 }, { "epoch": 0.6971366751668836, "grad_norm": 1.8287831544876099, "learning_rate": 0.00019056150515591583, "loss": 0.6474490165710449, "step": 117280 }, { "epoch": 0.697196117243552, "grad_norm": 1.7558624744415283, "learning_rate": 0.0001905587299015971, "loss": 0.6149971961975098, "step": 117290 }, { "epoch": 0.6972555593202204, "grad_norm": 1.9696377515792847, "learning_rate": 0.00019055595426191173, "loss": 0.712695837020874, "step": 117300 }, { "epoch": 0.6973150013968888, "grad_norm": 1.3910255432128906, "learning_rate": 0.00019055317823687303, "loss": 0.6650309562683105, "step": 117310 }, { "epoch": 0.6973744434735571, "grad_norm": 1.8010709285736084, "learning_rate": 0.00019055040182649422, "loss": 0.6776094436645508, "step": 117320 }, { "epoch": 0.6974338855502256, "grad_norm": 1.455863118171692, "learning_rate": 0.00019054762503078866, "loss": 0.6677974700927735, "step": 117330 }, { "epoch": 0.697493327626894, "grad_norm": 1.7471376657485962, "learning_rate": 0.00019054484784976952, "loss": 0.6542793273925781, "step": 117340 }, { "epoch": 0.6975527697035624, "grad_norm": 1.5601502656936646, "learning_rate": 0.00019054207028345018, "loss": 0.6131175994873047, "step": 117350 }, { "epoch": 0.6976122117802308, "grad_norm": 1.7881108522415161, "learning_rate": 0.00019053929233184389, "loss": 0.6880517482757569, "step": 117360 }, { "epoch": 0.6976716538568991, "grad_norm": 2.1016693115234375, "learning_rate": 0.00019053651399496396, "loss": 0.6482017517089844, "step": 117370 }, { "epoch": 0.6977310959335675, "grad_norm": 1.9166369438171387, "learning_rate": 0.00019053373527282366, "loss": 0.6720736026763916, "step": 117380 }, { "epoch": 0.6977905380102359, "grad_norm": 1.8147244453430176, "learning_rate": 0.00019053095616543628, "loss": 0.6629150390625, "step": 117390 }, { "epoch": 0.6978499800869044, "grad_norm": 2.0623230934143066, "learning_rate": 0.00019052817667281513, "loss": 0.6506414890289307, "step": 117400 }, { "epoch": 0.6979094221635727, "grad_norm": 1.6629186868667603, "learning_rate": 0.0001905253967949735, "loss": 0.6682369709014893, "step": 117410 }, { "epoch": 0.6979688642402411, "grad_norm": 1.7614505290985107, "learning_rate": 0.00019052261653192468, "loss": 0.6980577945709229, "step": 117420 }, { "epoch": 0.6980283063169095, "grad_norm": 1.6636842489242554, "learning_rate": 0.000190519835883682, "loss": 0.6942620754241944, "step": 117430 }, { "epoch": 0.6980877483935779, "grad_norm": 1.4478143453598022, "learning_rate": 0.0001905170548502587, "loss": 0.6512898921966552, "step": 117440 }, { "epoch": 0.6981471904702463, "grad_norm": 1.8956598043441772, "learning_rate": 0.00019051427343166818, "loss": 0.6908827781677246, "step": 117450 }, { "epoch": 0.6982066325469146, "grad_norm": 1.140335202217102, "learning_rate": 0.00019051149162792365, "loss": 0.6930332660675049, "step": 117460 }, { "epoch": 0.698266074623583, "grad_norm": 2.2714650630950928, "learning_rate": 0.00019050870943903848, "loss": 0.6993311882019043, "step": 117470 }, { "epoch": 0.6983255167002514, "grad_norm": 1.6412769556045532, "learning_rate": 0.00019050592686502594, "loss": 0.6534690856933594, "step": 117480 }, { "epoch": 0.6983849587769199, "grad_norm": 1.7527230978012085, "learning_rate": 0.00019050314390589934, "loss": 0.650044059753418, "step": 117490 }, { "epoch": 0.6984444008535883, "grad_norm": 1.3738367557525635, "learning_rate": 0.00019050036056167199, "loss": 0.7155220985412598, "step": 117500 }, { "epoch": 0.6985038429302566, "grad_norm": 1.5627307891845703, "learning_rate": 0.00019049757683235727, "loss": 0.6151198863983154, "step": 117510 }, { "epoch": 0.698563285006925, "grad_norm": 1.4632129669189453, "learning_rate": 0.00019049479271796845, "loss": 0.6678489685058594, "step": 117520 }, { "epoch": 0.6986227270835934, "grad_norm": 1.5139615535736084, "learning_rate": 0.00019049200821851883, "loss": 0.6643219470977784, "step": 117530 }, { "epoch": 0.6986821691602618, "grad_norm": 1.8852778673171997, "learning_rate": 0.00019048922333402173, "loss": 0.6846518516540527, "step": 117540 }, { "epoch": 0.6987416112369301, "grad_norm": 1.5347282886505127, "learning_rate": 0.00019048643806449052, "loss": 0.6270983695983887, "step": 117550 }, { "epoch": 0.6988010533135985, "grad_norm": 1.9827862977981567, "learning_rate": 0.0001904836524099385, "loss": 0.716913890838623, "step": 117560 }, { "epoch": 0.698860495390267, "grad_norm": 1.9109307527542114, "learning_rate": 0.00019048086637037895, "loss": 0.6628009796142578, "step": 117570 }, { "epoch": 0.6989199374669354, "grad_norm": 2.0386805534362793, "learning_rate": 0.00019047807994582524, "loss": 0.6981296062469482, "step": 117580 }, { "epoch": 0.6989793795436038, "grad_norm": 1.77798330783844, "learning_rate": 0.00019047529313629072, "loss": 0.6666322708129883, "step": 117590 }, { "epoch": 0.6990388216202721, "grad_norm": 1.7988383769989014, "learning_rate": 0.0001904725059417887, "loss": 0.672982120513916, "step": 117600 }, { "epoch": 0.6990982636969405, "grad_norm": 2.284775733947754, "learning_rate": 0.0001904697183623325, "loss": 0.6629995822906494, "step": 117610 }, { "epoch": 0.6991577057736089, "grad_norm": 1.5841667652130127, "learning_rate": 0.00019046693039793548, "loss": 0.7057440757751465, "step": 117620 }, { "epoch": 0.6992171478502773, "grad_norm": 1.6884188652038574, "learning_rate": 0.00019046414204861094, "loss": 0.7044023513793946, "step": 117630 }, { "epoch": 0.6992765899269456, "grad_norm": 1.871586799621582, "learning_rate": 0.00019046135331437226, "loss": 0.6527932167053223, "step": 117640 }, { "epoch": 0.699336032003614, "grad_norm": 1.4934073686599731, "learning_rate": 0.00019045856419523273, "loss": 0.6640175819396973, "step": 117650 }, { "epoch": 0.6993954740802825, "grad_norm": 1.6906569004058838, "learning_rate": 0.00019045577469120573, "loss": 0.6602143287658692, "step": 117660 }, { "epoch": 0.6994549161569509, "grad_norm": 2.413891315460205, "learning_rate": 0.00019045298480230462, "loss": 0.7286844730377198, "step": 117670 }, { "epoch": 0.6995143582336193, "grad_norm": 1.5013049840927124, "learning_rate": 0.0001904501945285427, "loss": 0.6567625999450684, "step": 117680 }, { "epoch": 0.6995738003102876, "grad_norm": 2.0587520599365234, "learning_rate": 0.00019044740386993337, "loss": 0.6147029876708985, "step": 117690 }, { "epoch": 0.699633242386956, "grad_norm": 1.5951749086380005, "learning_rate": 0.00019044461282648995, "loss": 0.6700505256652832, "step": 117700 }, { "epoch": 0.6996926844636244, "grad_norm": 1.6125422716140747, "learning_rate": 0.00019044182139822576, "loss": 0.6654953956604004, "step": 117710 }, { "epoch": 0.6997521265402928, "grad_norm": 1.4108631610870361, "learning_rate": 0.00019043902958515422, "loss": 0.5876155376434327, "step": 117720 }, { "epoch": 0.6998115686169613, "grad_norm": 1.9370603561401367, "learning_rate": 0.0001904362373872886, "loss": 0.7007248878479004, "step": 117730 }, { "epoch": 0.6998710106936296, "grad_norm": 2.1454713344573975, "learning_rate": 0.00019043344480464236, "loss": 0.7516511917114258, "step": 117740 }, { "epoch": 0.699930452770298, "grad_norm": 1.9541995525360107, "learning_rate": 0.00019043065183722876, "loss": 0.6762879848480224, "step": 117750 }, { "epoch": 0.6999898948469664, "grad_norm": 1.8705044984817505, "learning_rate": 0.00019042785848506124, "loss": 0.673045015335083, "step": 117760 }, { "epoch": 0.7000493369236348, "grad_norm": 1.4405485391616821, "learning_rate": 0.00019042506474815314, "loss": 0.6916525840759278, "step": 117770 }, { "epoch": 0.7001087790003031, "grad_norm": 1.5697894096374512, "learning_rate": 0.0001904222706265178, "loss": 0.645815086364746, "step": 117780 }, { "epoch": 0.7001682210769715, "grad_norm": 1.437859296798706, "learning_rate": 0.00019041947612016857, "loss": 0.6505620002746582, "step": 117790 }, { "epoch": 0.7002276631536399, "grad_norm": 1.5440272092819214, "learning_rate": 0.00019041668122911888, "loss": 0.7330272197723389, "step": 117800 }, { "epoch": 0.7002871052303083, "grad_norm": 1.3995567560195923, "learning_rate": 0.00019041388595338206, "loss": 0.6560564994812011, "step": 117810 }, { "epoch": 0.7003465473069768, "grad_norm": 2.0572152137756348, "learning_rate": 0.00019041109029297148, "loss": 0.7101180553436279, "step": 117820 }, { "epoch": 0.7004059893836451, "grad_norm": 1.5339304208755493, "learning_rate": 0.00019040829424790052, "loss": 0.6767838478088379, "step": 117830 }, { "epoch": 0.7004654314603135, "grad_norm": 2.0029351711273193, "learning_rate": 0.00019040549781818258, "loss": 0.7067521572113037, "step": 117840 }, { "epoch": 0.7005248735369819, "grad_norm": 1.6390429735183716, "learning_rate": 0.000190402701003831, "loss": 0.6688167095184326, "step": 117850 }, { "epoch": 0.7005843156136503, "grad_norm": 1.6029657125473022, "learning_rate": 0.00019039990380485916, "loss": 0.6876834869384766, "step": 117860 }, { "epoch": 0.7006437576903186, "grad_norm": 1.7542474269866943, "learning_rate": 0.0001903971062212805, "loss": 0.5995527744293213, "step": 117870 }, { "epoch": 0.700703199766987, "grad_norm": 1.5881257057189941, "learning_rate": 0.00019039430825310832, "loss": 0.6536216735839844, "step": 117880 }, { "epoch": 0.7007626418436554, "grad_norm": 1.7204155921936035, "learning_rate": 0.00019039150990035606, "loss": 0.6931626319885253, "step": 117890 }, { "epoch": 0.7008220839203239, "grad_norm": 1.6835483312606812, "learning_rate": 0.0001903887111630371, "loss": 0.6719043731689454, "step": 117900 }, { "epoch": 0.7008815259969923, "grad_norm": 2.1538658142089844, "learning_rate": 0.0001903859120411648, "loss": 0.6167503356933594, "step": 117910 }, { "epoch": 0.7009409680736606, "grad_norm": 1.8288019895553589, "learning_rate": 0.00019038311253475256, "loss": 0.6812000274658203, "step": 117920 }, { "epoch": 0.701000410150329, "grad_norm": 1.425830364227295, "learning_rate": 0.00019038031264381378, "loss": 0.6339561462402343, "step": 117930 }, { "epoch": 0.7010598522269974, "grad_norm": 1.8248847723007202, "learning_rate": 0.00019037751236836186, "loss": 0.6247138977050781, "step": 117940 }, { "epoch": 0.7011192943036658, "grad_norm": 1.6373051404953003, "learning_rate": 0.0001903747117084102, "loss": 0.6987015724182128, "step": 117950 }, { "epoch": 0.7011787363803342, "grad_norm": 1.6302284002304077, "learning_rate": 0.00019037191066397215, "loss": 0.6546815872192383, "step": 117960 }, { "epoch": 0.7012381784570025, "grad_norm": 1.578808069229126, "learning_rate": 0.00019036910923506115, "loss": 0.6259169578552246, "step": 117970 }, { "epoch": 0.701297620533671, "grad_norm": 1.5929102897644043, "learning_rate": 0.00019036630742169064, "loss": 0.6192150115966797, "step": 117980 }, { "epoch": 0.7013570626103394, "grad_norm": 2.1426503658294678, "learning_rate": 0.00019036350522387395, "loss": 0.7040133476257324, "step": 117990 }, { "epoch": 0.7014165046870078, "grad_norm": 1.319061040878296, "learning_rate": 0.0001903607026416245, "loss": 0.6572963237762451, "step": 118000 }, { "epoch": 0.7014759467636761, "grad_norm": 2.316208600997925, "learning_rate": 0.00019035789967495573, "loss": 0.672946834564209, "step": 118010 }, { "epoch": 0.7015353888403445, "grad_norm": 1.7490732669830322, "learning_rate": 0.00019035509632388104, "loss": 0.6929077625274658, "step": 118020 }, { "epoch": 0.7015948309170129, "grad_norm": 1.7940011024475098, "learning_rate": 0.0001903522925884138, "loss": 0.7200371742248535, "step": 118030 }, { "epoch": 0.7016542729936813, "grad_norm": 1.4555504322052002, "learning_rate": 0.0001903494884685675, "loss": 0.6093251228332519, "step": 118040 }, { "epoch": 0.7017137150703497, "grad_norm": 1.772085428237915, "learning_rate": 0.00019034668396435546, "loss": 0.754638671875, "step": 118050 }, { "epoch": 0.701773157147018, "grad_norm": 1.5810705423355103, "learning_rate": 0.00019034387907579115, "loss": 0.650657844543457, "step": 118060 }, { "epoch": 0.7018325992236865, "grad_norm": 1.3917367458343506, "learning_rate": 0.000190341073802888, "loss": 0.6095152854919433, "step": 118070 }, { "epoch": 0.7018920413003549, "grad_norm": 1.5119742155075073, "learning_rate": 0.00019033826814565937, "loss": 0.6629182815551757, "step": 118080 }, { "epoch": 0.7019514833770233, "grad_norm": 1.6160860061645508, "learning_rate": 0.00019033546210411878, "loss": 0.6438138961791993, "step": 118090 }, { "epoch": 0.7020109254536917, "grad_norm": 1.5564402341842651, "learning_rate": 0.00019033265567827953, "loss": 0.6625729560852051, "step": 118100 }, { "epoch": 0.70207036753036, "grad_norm": 1.9689387083053589, "learning_rate": 0.00019032984886815512, "loss": 0.6623094081878662, "step": 118110 }, { "epoch": 0.7021298096070284, "grad_norm": 1.9187395572662354, "learning_rate": 0.000190327041673759, "loss": 0.6734034061431885, "step": 118120 }, { "epoch": 0.7021892516836968, "grad_norm": 1.702086091041565, "learning_rate": 0.00019032423409510456, "loss": 0.6459248065948486, "step": 118130 }, { "epoch": 0.7022486937603653, "grad_norm": 2.1248092651367188, "learning_rate": 0.00019032142613220517, "loss": 0.6893385887145996, "step": 118140 }, { "epoch": 0.7023081358370336, "grad_norm": 1.7071499824523926, "learning_rate": 0.0001903186177850744, "loss": 0.6907975196838378, "step": 118150 }, { "epoch": 0.702367577913702, "grad_norm": 1.4890128374099731, "learning_rate": 0.0001903158090537256, "loss": 0.6399134635925293, "step": 118160 }, { "epoch": 0.7024270199903704, "grad_norm": 1.7377722263336182, "learning_rate": 0.0001903129999381722, "loss": 0.7089569568634033, "step": 118170 }, { "epoch": 0.7024864620670388, "grad_norm": 2.4837284088134766, "learning_rate": 0.00019031019043842765, "loss": 0.6856903076171875, "step": 118180 }, { "epoch": 0.7025459041437072, "grad_norm": 2.289802074432373, "learning_rate": 0.0001903073805545054, "loss": 0.6710699081420899, "step": 118190 }, { "epoch": 0.7026053462203755, "grad_norm": 1.9377135038375854, "learning_rate": 0.0001903045702864189, "loss": 0.6763123512268067, "step": 118200 }, { "epoch": 0.7026647882970439, "grad_norm": 1.930351734161377, "learning_rate": 0.00019030175963418157, "loss": 0.6509593963623047, "step": 118210 }, { "epoch": 0.7027242303737123, "grad_norm": 2.266526699066162, "learning_rate": 0.00019029894859780687, "loss": 0.7058454513549804, "step": 118220 }, { "epoch": 0.7027836724503808, "grad_norm": 1.473319172859192, "learning_rate": 0.0001902961371773082, "loss": 0.6751355648040771, "step": 118230 }, { "epoch": 0.7028431145270491, "grad_norm": 1.854095458984375, "learning_rate": 0.0001902933253726991, "loss": 0.7124260902404785, "step": 118240 }, { "epoch": 0.7029025566037175, "grad_norm": 1.2943706512451172, "learning_rate": 0.00019029051318399296, "loss": 0.6840832710266114, "step": 118250 }, { "epoch": 0.7029619986803859, "grad_norm": 1.4258183240890503, "learning_rate": 0.00019028770061120328, "loss": 0.6289473533630371, "step": 118260 }, { "epoch": 0.7030214407570543, "grad_norm": 1.4084724187850952, "learning_rate": 0.00019028488765434343, "loss": 0.6281979560852051, "step": 118270 }, { "epoch": 0.7030808828337227, "grad_norm": 1.757304310798645, "learning_rate": 0.00019028207431342692, "loss": 0.750401496887207, "step": 118280 }, { "epoch": 0.703140324910391, "grad_norm": 2.008728265762329, "learning_rate": 0.00019027926058846719, "loss": 0.6775494575500488, "step": 118290 }, { "epoch": 0.7031997669870594, "grad_norm": 1.8076207637786865, "learning_rate": 0.00019027644647947773, "loss": 0.6329655647277832, "step": 118300 }, { "epoch": 0.7032592090637279, "grad_norm": 1.2847832441329956, "learning_rate": 0.000190273631986472, "loss": 0.6876171112060547, "step": 118310 }, { "epoch": 0.7033186511403963, "grad_norm": 1.5817338228225708, "learning_rate": 0.00019027081710946343, "loss": 0.6155261039733887, "step": 118320 }, { "epoch": 0.7033780932170647, "grad_norm": 1.8915319442749023, "learning_rate": 0.0001902680018484655, "loss": 0.6301158905029297, "step": 118330 }, { "epoch": 0.703437535293733, "grad_norm": 1.5529557466506958, "learning_rate": 0.0001902651862034917, "loss": 0.6713173866271973, "step": 118340 }, { "epoch": 0.7034969773704014, "grad_norm": 1.6410568952560425, "learning_rate": 0.00019026237017455547, "loss": 0.6828391075134277, "step": 118350 }, { "epoch": 0.7035564194470698, "grad_norm": 1.9417742490768433, "learning_rate": 0.00019025955376167028, "loss": 0.6752264022827148, "step": 118360 }, { "epoch": 0.7036158615237382, "grad_norm": 1.3681459426879883, "learning_rate": 0.00019025673696484964, "loss": 0.6008187294006347, "step": 118370 }, { "epoch": 0.7036753036004065, "grad_norm": 1.7119243144989014, "learning_rate": 0.00019025391978410696, "loss": 0.7084331512451172, "step": 118380 }, { "epoch": 0.703734745677075, "grad_norm": 2.0411956310272217, "learning_rate": 0.00019025110221945578, "loss": 0.7253572463989257, "step": 118390 }, { "epoch": 0.7037941877537434, "grad_norm": 1.818585753440857, "learning_rate": 0.00019024828427090956, "loss": 0.6660947799682617, "step": 118400 }, { "epoch": 0.7038536298304118, "grad_norm": 1.3510347604751587, "learning_rate": 0.00019024546593848177, "loss": 0.6466931343078614, "step": 118410 }, { "epoch": 0.7039130719070802, "grad_norm": 2.171908378601074, "learning_rate": 0.00019024264722218587, "loss": 0.6985330581665039, "step": 118420 }, { "epoch": 0.7039725139837485, "grad_norm": 1.5182582139968872, "learning_rate": 0.0001902398281220354, "loss": 0.6172504425048828, "step": 118430 }, { "epoch": 0.7040319560604169, "grad_norm": 1.7696841955184937, "learning_rate": 0.0001902370086380438, "loss": 0.669675874710083, "step": 118440 }, { "epoch": 0.7040913981370853, "grad_norm": 1.6595005989074707, "learning_rate": 0.00019023418877022456, "loss": 0.6779935836791993, "step": 118450 }, { "epoch": 0.7041508402137537, "grad_norm": 1.6156851053237915, "learning_rate": 0.0001902313685185912, "loss": 0.7041807174682617, "step": 118460 }, { "epoch": 0.7042102822904222, "grad_norm": 1.9776930809020996, "learning_rate": 0.00019022854788315721, "loss": 0.7071067810058593, "step": 118470 }, { "epoch": 0.7042697243670905, "grad_norm": 1.8098200559616089, "learning_rate": 0.00019022572686393604, "loss": 0.6330808639526367, "step": 118480 }, { "epoch": 0.7043291664437589, "grad_norm": 1.4144079685211182, "learning_rate": 0.0001902229054609412, "loss": 0.6372604846954346, "step": 118490 }, { "epoch": 0.7043886085204273, "grad_norm": 1.664250135421753, "learning_rate": 0.0001902200836741862, "loss": 0.6875138282775879, "step": 118500 }, { "epoch": 0.7044480505970957, "grad_norm": 1.4425432682037354, "learning_rate": 0.00019021726150368458, "loss": 0.7010536193847656, "step": 118510 }, { "epoch": 0.704507492673764, "grad_norm": 1.8111432790756226, "learning_rate": 0.00019021443894944978, "loss": 0.6846431732177735, "step": 118520 }, { "epoch": 0.7045669347504324, "grad_norm": 1.406007170677185, "learning_rate": 0.0001902116160114953, "loss": 0.6771690368652343, "step": 118530 }, { "epoch": 0.7046263768271008, "grad_norm": 1.805148959159851, "learning_rate": 0.00019020879268983468, "loss": 0.7976540565490723, "step": 118540 }, { "epoch": 0.7046858189037692, "grad_norm": 1.6267889738082886, "learning_rate": 0.00019020596898448137, "loss": 0.6445485115051269, "step": 118550 }, { "epoch": 0.7047452609804377, "grad_norm": 1.4773995876312256, "learning_rate": 0.00019020314489544895, "loss": 0.7349980354309082, "step": 118560 }, { "epoch": 0.704804703057106, "grad_norm": 1.5471522808074951, "learning_rate": 0.00019020032042275087, "loss": 0.6883726119995117, "step": 118570 }, { "epoch": 0.7048641451337744, "grad_norm": 1.367281198501587, "learning_rate": 0.0001901974955664007, "loss": 0.6372721195220947, "step": 118580 }, { "epoch": 0.7049235872104428, "grad_norm": 1.4477119445800781, "learning_rate": 0.0001901946703264119, "loss": 0.6313416481018066, "step": 118590 }, { "epoch": 0.7049830292871112, "grad_norm": 1.7325226068496704, "learning_rate": 0.000190191844702798, "loss": 0.6429622650146485, "step": 118600 }, { "epoch": 0.7050424713637795, "grad_norm": 1.5395587682724, "learning_rate": 0.00019018901869557255, "loss": 0.6928441524505615, "step": 118610 }, { "epoch": 0.7051019134404479, "grad_norm": 1.6089602708816528, "learning_rate": 0.00019018619230474904, "loss": 0.650304651260376, "step": 118620 }, { "epoch": 0.7051613555171163, "grad_norm": 1.538923978805542, "learning_rate": 0.00019018336553034096, "loss": 0.6675046920776367, "step": 118630 }, { "epoch": 0.7052207975937848, "grad_norm": 2.183474540710449, "learning_rate": 0.00019018053837236188, "loss": 0.6509355545043946, "step": 118640 }, { "epoch": 0.7052802396704532, "grad_norm": 1.481655478477478, "learning_rate": 0.0001901777108308253, "loss": 0.6944392204284668, "step": 118650 }, { "epoch": 0.7053396817471215, "grad_norm": 1.8306348323822021, "learning_rate": 0.00019017488290574476, "loss": 0.6815036773681641, "step": 118660 }, { "epoch": 0.7053991238237899, "grad_norm": 1.8095524311065674, "learning_rate": 0.0001901720545971338, "loss": 0.6408082962036132, "step": 118670 }, { "epoch": 0.7054585659004583, "grad_norm": 2.0716030597686768, "learning_rate": 0.0001901692259050059, "loss": 0.6499138832092285, "step": 118680 }, { "epoch": 0.7055180079771267, "grad_norm": 1.8335955142974854, "learning_rate": 0.0001901663968293746, "loss": 0.6210203170776367, "step": 118690 }, { "epoch": 0.7055774500537951, "grad_norm": 1.8728026151657104, "learning_rate": 0.0001901635673702535, "loss": 0.690274715423584, "step": 118700 }, { "epoch": 0.7056368921304634, "grad_norm": 1.990249514579773, "learning_rate": 0.00019016073752765612, "loss": 0.6699880599975586, "step": 118710 }, { "epoch": 0.7056963342071318, "grad_norm": 2.2663819789886475, "learning_rate": 0.0001901579073015959, "loss": 0.6525437831878662, "step": 118720 }, { "epoch": 0.7057557762838003, "grad_norm": 2.108961343765259, "learning_rate": 0.00019015507669208648, "loss": 0.7115799903869628, "step": 118730 }, { "epoch": 0.7058152183604687, "grad_norm": 1.6861662864685059, "learning_rate": 0.00019015224569914136, "loss": 0.6765592575073243, "step": 118740 }, { "epoch": 0.705874660437137, "grad_norm": 1.565973162651062, "learning_rate": 0.0001901494143227741, "loss": 0.6451340198516846, "step": 118750 }, { "epoch": 0.7059341025138054, "grad_norm": 1.4417537450790405, "learning_rate": 0.00019014658256299825, "loss": 0.6434163093566895, "step": 118760 }, { "epoch": 0.7059935445904738, "grad_norm": 1.8280234336853027, "learning_rate": 0.0001901437504198273, "loss": 0.5973245143890381, "step": 118770 }, { "epoch": 0.7060529866671422, "grad_norm": 1.8574554920196533, "learning_rate": 0.00019014091789327486, "loss": 0.6652497291564942, "step": 118780 }, { "epoch": 0.7061124287438106, "grad_norm": 2.054896116256714, "learning_rate": 0.00019013808498335446, "loss": 0.6761343955993653, "step": 118790 }, { "epoch": 0.7061718708204789, "grad_norm": 1.8376833200454712, "learning_rate": 0.00019013525169007966, "loss": 0.6469813346862793, "step": 118800 }, { "epoch": 0.7062313128971474, "grad_norm": 1.6635351181030273, "learning_rate": 0.000190132418013464, "loss": 0.7299007415771485, "step": 118810 }, { "epoch": 0.7062907549738158, "grad_norm": 1.6491637229919434, "learning_rate": 0.00019012958395352102, "loss": 0.6525164604187011, "step": 118820 }, { "epoch": 0.7063501970504842, "grad_norm": 1.7113962173461914, "learning_rate": 0.00019012674951026433, "loss": 0.5819430828094483, "step": 118830 }, { "epoch": 0.7064096391271526, "grad_norm": 1.552579641342163, "learning_rate": 0.00019012391468370743, "loss": 0.6569205760955811, "step": 118840 }, { "epoch": 0.7064690812038209, "grad_norm": 1.7900763750076294, "learning_rate": 0.00019012107947386392, "loss": 0.7164813995361328, "step": 118850 }, { "epoch": 0.7065285232804893, "grad_norm": 1.4640649557113647, "learning_rate": 0.00019011824388074736, "loss": 0.6642190456390381, "step": 118860 }, { "epoch": 0.7065879653571577, "grad_norm": 1.389000415802002, "learning_rate": 0.00019011540790437128, "loss": 0.6501042366027832, "step": 118870 }, { "epoch": 0.7066474074338261, "grad_norm": 1.4916285276412964, "learning_rate": 0.00019011257154474928, "loss": 0.6368378639221192, "step": 118880 }, { "epoch": 0.7067068495104945, "grad_norm": 1.4696294069290161, "learning_rate": 0.00019010973480189494, "loss": 0.6640289306640625, "step": 118890 }, { "epoch": 0.7067662915871629, "grad_norm": 1.8373656272888184, "learning_rate": 0.00019010689767582178, "loss": 0.6501856803894043, "step": 118900 }, { "epoch": 0.7068257336638313, "grad_norm": 1.7115544080734253, "learning_rate": 0.00019010406016654337, "loss": 0.6489367008209228, "step": 118910 }, { "epoch": 0.7068851757404997, "grad_norm": 1.7476307153701782, "learning_rate": 0.00019010122227407336, "loss": 0.6287860870361328, "step": 118920 }, { "epoch": 0.7069446178171681, "grad_norm": 1.9548019170761108, "learning_rate": 0.0001900983839984253, "loss": 0.6643593311309814, "step": 118930 }, { "epoch": 0.7070040598938364, "grad_norm": 1.3600223064422607, "learning_rate": 0.00019009554533961273, "loss": 0.6783446788787841, "step": 118940 }, { "epoch": 0.7070635019705048, "grad_norm": 1.7066187858581543, "learning_rate": 0.00019009270629764921, "loss": 0.6274383544921875, "step": 118950 }, { "epoch": 0.7071229440471732, "grad_norm": 1.5050042867660522, "learning_rate": 0.0001900898668725484, "loss": 0.5798072814941406, "step": 118960 }, { "epoch": 0.7071823861238417, "grad_norm": 1.6721878051757812, "learning_rate": 0.00019008702706432384, "loss": 0.6941920280456543, "step": 118970 }, { "epoch": 0.70724182820051, "grad_norm": 1.6475528478622437, "learning_rate": 0.00019008418687298907, "loss": 0.6501615524291993, "step": 118980 }, { "epoch": 0.7073012702771784, "grad_norm": 1.334977388381958, "learning_rate": 0.00019008134629855777, "loss": 0.6342174530029296, "step": 118990 }, { "epoch": 0.7073607123538468, "grad_norm": 1.551891565322876, "learning_rate": 0.00019007850534104344, "loss": 0.6173494338989258, "step": 119000 }, { "epoch": 0.7074201544305152, "grad_norm": 1.6249291896820068, "learning_rate": 0.00019007566400045976, "loss": 0.637601089477539, "step": 119010 }, { "epoch": 0.7074795965071836, "grad_norm": 1.6144981384277344, "learning_rate": 0.00019007282227682023, "loss": 0.7161971092224121, "step": 119020 }, { "epoch": 0.7075390385838519, "grad_norm": 1.406024694442749, "learning_rate": 0.0001900699801701385, "loss": 0.6760987281799317, "step": 119030 }, { "epoch": 0.7075984806605203, "grad_norm": 1.9053754806518555, "learning_rate": 0.00019006713768042818, "loss": 0.6605399131774903, "step": 119040 }, { "epoch": 0.7076579227371887, "grad_norm": 1.8523927927017212, "learning_rate": 0.00019006429480770281, "loss": 0.6301825046539307, "step": 119050 }, { "epoch": 0.7077173648138572, "grad_norm": 1.8113365173339844, "learning_rate": 0.000190061451551976, "loss": 0.6511316299438477, "step": 119060 }, { "epoch": 0.7077768068905256, "grad_norm": 2.143281936645508, "learning_rate": 0.0001900586079132614, "loss": 0.68778395652771, "step": 119070 }, { "epoch": 0.7078362489671939, "grad_norm": 1.8186384439468384, "learning_rate": 0.0001900557638915726, "loss": 0.6712033748626709, "step": 119080 }, { "epoch": 0.7078956910438623, "grad_norm": 1.537071704864502, "learning_rate": 0.00019005291948692314, "loss": 0.6966863155364991, "step": 119090 }, { "epoch": 0.7079551331205307, "grad_norm": 1.902496576309204, "learning_rate": 0.0001900500746993267, "loss": 0.6509229660034179, "step": 119100 }, { "epoch": 0.7080145751971991, "grad_norm": 1.632622480392456, "learning_rate": 0.00019004722952879687, "loss": 0.7106158256530761, "step": 119110 }, { "epoch": 0.7080740172738674, "grad_norm": 1.7471107244491577, "learning_rate": 0.00019004438397534726, "loss": 0.6425097465515137, "step": 119120 }, { "epoch": 0.7081334593505358, "grad_norm": 1.573190450668335, "learning_rate": 0.00019004153803899143, "loss": 0.6682836532592773, "step": 119130 }, { "epoch": 0.7081929014272043, "grad_norm": 1.904075264930725, "learning_rate": 0.0001900386917197431, "loss": 0.6810372829437256, "step": 119140 }, { "epoch": 0.7082523435038727, "grad_norm": 1.3465815782546997, "learning_rate": 0.0001900358450176158, "loss": 0.6522883415222168, "step": 119150 }, { "epoch": 0.7083117855805411, "grad_norm": 1.8459008932113647, "learning_rate": 0.00019003299793262315, "loss": 0.6460735321044921, "step": 119160 }, { "epoch": 0.7083712276572094, "grad_norm": 2.0484747886657715, "learning_rate": 0.00019003015046477881, "loss": 0.7469866752624512, "step": 119170 }, { "epoch": 0.7084306697338778, "grad_norm": 1.412038803100586, "learning_rate": 0.0001900273026140964, "loss": 0.6963711738586426, "step": 119180 }, { "epoch": 0.7084901118105462, "grad_norm": 1.4767990112304688, "learning_rate": 0.0001900244543805895, "loss": 0.6829830646514893, "step": 119190 }, { "epoch": 0.7085495538872146, "grad_norm": 1.8031868934631348, "learning_rate": 0.00019002160576427182, "loss": 0.7041686534881592, "step": 119200 }, { "epoch": 0.708608995963883, "grad_norm": 2.1574206352233887, "learning_rate": 0.00019001875676515686, "loss": 0.7191251754760742, "step": 119210 }, { "epoch": 0.7086684380405514, "grad_norm": 1.6493507623672485, "learning_rate": 0.00019001590738325835, "loss": 0.7005019187927246, "step": 119220 }, { "epoch": 0.7087278801172198, "grad_norm": 1.6478404998779297, "learning_rate": 0.00019001305761858988, "loss": 0.6714983940124511, "step": 119230 }, { "epoch": 0.7087873221938882, "grad_norm": 1.9722039699554443, "learning_rate": 0.0001900102074711651, "loss": 0.7088403701782227, "step": 119240 }, { "epoch": 0.7088467642705566, "grad_norm": 1.7990401983261108, "learning_rate": 0.00019000735694099763, "loss": 0.6624999523162842, "step": 119250 }, { "epoch": 0.7089062063472249, "grad_norm": 1.5218478441238403, "learning_rate": 0.0001900045060281011, "loss": 0.7197055339813232, "step": 119260 }, { "epoch": 0.7089656484238933, "grad_norm": 1.8852800130844116, "learning_rate": 0.00019000165473248917, "loss": 0.7228532314300538, "step": 119270 }, { "epoch": 0.7090250905005617, "grad_norm": 1.4316625595092773, "learning_rate": 0.0001899988030541755, "loss": 0.6616435050964355, "step": 119280 }, { "epoch": 0.7090845325772301, "grad_norm": 1.508105754852295, "learning_rate": 0.00018999595099317365, "loss": 0.6425336837768555, "step": 119290 }, { "epoch": 0.7091439746538986, "grad_norm": 1.994247555732727, "learning_rate": 0.00018999309854949732, "loss": 0.6683565139770508, "step": 119300 }, { "epoch": 0.7092034167305669, "grad_norm": 1.6942784786224365, "learning_rate": 0.00018999024572316015, "loss": 0.6742148399353027, "step": 119310 }, { "epoch": 0.7092628588072353, "grad_norm": 2.0140647888183594, "learning_rate": 0.0001899873925141758, "loss": 0.7022655010223389, "step": 119320 }, { "epoch": 0.7093223008839037, "grad_norm": 1.6785017251968384, "learning_rate": 0.00018998453892255792, "loss": 0.7129820346832275, "step": 119330 }, { "epoch": 0.7093817429605721, "grad_norm": 1.9164589643478394, "learning_rate": 0.0001899816849483201, "loss": 0.6683382987976074, "step": 119340 }, { "epoch": 0.7094411850372404, "grad_norm": 1.8414435386657715, "learning_rate": 0.00018997883059147607, "loss": 0.6333413124084473, "step": 119350 }, { "epoch": 0.7095006271139088, "grad_norm": 1.7195374965667725, "learning_rate": 0.00018997597585203944, "loss": 0.633030891418457, "step": 119360 }, { "epoch": 0.7095600691905772, "grad_norm": 1.9595953226089478, "learning_rate": 0.0001899731207300239, "loss": 0.7438162326812744, "step": 119370 }, { "epoch": 0.7096195112672457, "grad_norm": 1.75410795211792, "learning_rate": 0.00018997026522544306, "loss": 0.5901246070861816, "step": 119380 }, { "epoch": 0.7096789533439141, "grad_norm": 1.5272587537765503, "learning_rate": 0.00018996740933831062, "loss": 0.6719624519348144, "step": 119390 }, { "epoch": 0.7097383954205824, "grad_norm": 1.5656346082687378, "learning_rate": 0.00018996455306864021, "loss": 0.6565462589263916, "step": 119400 }, { "epoch": 0.7097978374972508, "grad_norm": 1.7446203231811523, "learning_rate": 0.00018996169641644555, "loss": 0.6814838409423828, "step": 119410 }, { "epoch": 0.7098572795739192, "grad_norm": 1.8654142618179321, "learning_rate": 0.00018995883938174022, "loss": 0.6892260551452637, "step": 119420 }, { "epoch": 0.7099167216505876, "grad_norm": 2.310197353363037, "learning_rate": 0.00018995598196453796, "loss": 0.667096757888794, "step": 119430 }, { "epoch": 0.709976163727256, "grad_norm": 1.6050325632095337, "learning_rate": 0.00018995312416485242, "loss": 0.6726120471954345, "step": 119440 }, { "epoch": 0.7100356058039243, "grad_norm": 2.016878128051758, "learning_rate": 0.00018995026598269722, "loss": 0.6841828346252441, "step": 119450 }, { "epoch": 0.7100950478805927, "grad_norm": 2.080915689468384, "learning_rate": 0.00018994740741808613, "loss": 0.6426869392395019, "step": 119460 }, { "epoch": 0.7101544899572612, "grad_norm": 1.5733973979949951, "learning_rate": 0.00018994454847103275, "loss": 0.6616963863372802, "step": 119470 }, { "epoch": 0.7102139320339296, "grad_norm": 1.4709824323654175, "learning_rate": 0.00018994168914155074, "loss": 0.7070115089416504, "step": 119480 }, { "epoch": 0.7102733741105979, "grad_norm": 1.6211252212524414, "learning_rate": 0.00018993882942965385, "loss": 0.6740141391754151, "step": 119490 }, { "epoch": 0.7103328161872663, "grad_norm": 1.6823195219039917, "learning_rate": 0.0001899359693353557, "loss": 0.6833651542663575, "step": 119500 }, { "epoch": 0.7103922582639347, "grad_norm": 1.6881091594696045, "learning_rate": 0.00018993310885867003, "loss": 0.6855550765991211, "step": 119510 }, { "epoch": 0.7104517003406031, "grad_norm": 1.2879664897918701, "learning_rate": 0.00018993024799961048, "loss": 0.6493961811065674, "step": 119520 }, { "epoch": 0.7105111424172715, "grad_norm": 1.7738038301467896, "learning_rate": 0.00018992738675819074, "loss": 0.7230213165283204, "step": 119530 }, { "epoch": 0.7105705844939398, "grad_norm": 1.3703739643096924, "learning_rate": 0.0001899245251344245, "loss": 0.6558997154235839, "step": 119540 }, { "epoch": 0.7106300265706083, "grad_norm": 1.396042823791504, "learning_rate": 0.00018992166312832546, "loss": 0.6962708950042724, "step": 119550 }, { "epoch": 0.7106894686472767, "grad_norm": 1.8879423141479492, "learning_rate": 0.0001899188007399073, "loss": 0.6666290760040283, "step": 119560 }, { "epoch": 0.7107489107239451, "grad_norm": 1.5467311143875122, "learning_rate": 0.0001899159379691837, "loss": 0.6917295455932617, "step": 119570 }, { "epoch": 0.7108083528006135, "grad_norm": 1.435017466545105, "learning_rate": 0.00018991307481616837, "loss": 0.6481860637664795, "step": 119580 }, { "epoch": 0.7108677948772818, "grad_norm": 1.596795678138733, "learning_rate": 0.00018991021128087501, "loss": 0.6797391891479492, "step": 119590 }, { "epoch": 0.7109272369539502, "grad_norm": 1.6985361576080322, "learning_rate": 0.00018990734736331732, "loss": 0.6328680992126465, "step": 119600 }, { "epoch": 0.7109866790306186, "grad_norm": 1.6418695449829102, "learning_rate": 0.000189904483063509, "loss": 0.7321939468383789, "step": 119610 }, { "epoch": 0.711046121107287, "grad_norm": 2.1881062984466553, "learning_rate": 0.0001899016183814637, "loss": 0.6351334571838378, "step": 119620 }, { "epoch": 0.7111055631839553, "grad_norm": 1.7921168804168701, "learning_rate": 0.00018989875331719525, "loss": 0.6684839248657226, "step": 119630 }, { "epoch": 0.7111650052606238, "grad_norm": 1.8123406171798706, "learning_rate": 0.00018989588787071723, "loss": 0.7209711074829102, "step": 119640 }, { "epoch": 0.7112244473372922, "grad_norm": 1.7297419309616089, "learning_rate": 0.00018989302204204344, "loss": 0.7131862640380859, "step": 119650 }, { "epoch": 0.7112838894139606, "grad_norm": 1.6174999475479126, "learning_rate": 0.00018989015583118746, "loss": 0.5899253845214844, "step": 119660 }, { "epoch": 0.711343331490629, "grad_norm": 1.2894260883331299, "learning_rate": 0.00018988728923816312, "loss": 0.6473485946655273, "step": 119670 }, { "epoch": 0.7114027735672973, "grad_norm": 1.8634804487228394, "learning_rate": 0.0001898844222629841, "loss": 0.7393607139587403, "step": 119680 }, { "epoch": 0.7114622156439657, "grad_norm": 1.7318699359893799, "learning_rate": 0.0001898815549056641, "loss": 0.6861071586608887, "step": 119690 }, { "epoch": 0.7115216577206341, "grad_norm": 1.5744236707687378, "learning_rate": 0.00018987868716621687, "loss": 0.6545379161834717, "step": 119700 }, { "epoch": 0.7115810997973026, "grad_norm": 1.7876006364822388, "learning_rate": 0.00018987581904465607, "loss": 0.662939453125, "step": 119710 }, { "epoch": 0.7116405418739709, "grad_norm": 1.618158221244812, "learning_rate": 0.00018987295054099547, "loss": 0.6687860012054443, "step": 119720 }, { "epoch": 0.7116999839506393, "grad_norm": 1.2737213373184204, "learning_rate": 0.0001898700816552488, "loss": 0.6963727951049805, "step": 119730 }, { "epoch": 0.7117594260273077, "grad_norm": 1.6864665746688843, "learning_rate": 0.00018986721238742972, "loss": 0.6607672214508057, "step": 119740 }, { "epoch": 0.7118188681039761, "grad_norm": 1.8572056293487549, "learning_rate": 0.00018986434273755205, "loss": 0.720705223083496, "step": 119750 }, { "epoch": 0.7118783101806445, "grad_norm": 2.163379669189453, "learning_rate": 0.00018986147270562943, "loss": 0.680594539642334, "step": 119760 }, { "epoch": 0.7119377522573128, "grad_norm": 1.3996500968933105, "learning_rate": 0.00018985860229167562, "loss": 0.6445717811584473, "step": 119770 }, { "epoch": 0.7119971943339812, "grad_norm": 1.5412424802780151, "learning_rate": 0.0001898557314957044, "loss": 0.7191781997680664, "step": 119780 }, { "epoch": 0.7120566364106496, "grad_norm": 1.3674516677856445, "learning_rate": 0.00018985286031772942, "loss": 0.6601045608520508, "step": 119790 }, { "epoch": 0.7121160784873181, "grad_norm": 1.6265316009521484, "learning_rate": 0.00018984998875776443, "loss": 0.6256519317626953, "step": 119800 }, { "epoch": 0.7121755205639865, "grad_norm": 1.3975718021392822, "learning_rate": 0.00018984711681582322, "loss": 0.6689187049865722, "step": 119810 }, { "epoch": 0.7122349626406548, "grad_norm": 1.965501308441162, "learning_rate": 0.0001898442444919195, "loss": 0.677219009399414, "step": 119820 }, { "epoch": 0.7122944047173232, "grad_norm": 1.9672046899795532, "learning_rate": 0.00018984137178606697, "loss": 0.6411611557006835, "step": 119830 }, { "epoch": 0.7123538467939916, "grad_norm": 1.35536789894104, "learning_rate": 0.00018983849869827946, "loss": 0.6079741477966308, "step": 119840 }, { "epoch": 0.71241328887066, "grad_norm": 1.8967771530151367, "learning_rate": 0.00018983562522857065, "loss": 0.6785222053527832, "step": 119850 }, { "epoch": 0.7124727309473283, "grad_norm": 1.790234923362732, "learning_rate": 0.00018983275137695428, "loss": 0.7669106960296631, "step": 119860 }, { "epoch": 0.7125321730239967, "grad_norm": 1.4547230005264282, "learning_rate": 0.00018982987714344412, "loss": 0.7008859634399414, "step": 119870 }, { "epoch": 0.7125916151006652, "grad_norm": 1.6955064535140991, "learning_rate": 0.00018982700252805394, "loss": 0.6948441982269287, "step": 119880 }, { "epoch": 0.7126510571773336, "grad_norm": 1.4233291149139404, "learning_rate": 0.00018982412753079745, "loss": 0.6242353439331054, "step": 119890 }, { "epoch": 0.712710499254002, "grad_norm": 1.2370758056640625, "learning_rate": 0.0001898212521516884, "loss": 0.6088093757629395, "step": 119900 }, { "epoch": 0.7127699413306703, "grad_norm": 1.3549848794937134, "learning_rate": 0.00018981837639074061, "loss": 0.7177571296691895, "step": 119910 }, { "epoch": 0.7128293834073387, "grad_norm": 2.1618587970733643, "learning_rate": 0.00018981550024796778, "loss": 0.6916817188262939, "step": 119920 }, { "epoch": 0.7128888254840071, "grad_norm": 1.916744351387024, "learning_rate": 0.00018981262372338366, "loss": 0.6472032070159912, "step": 119930 }, { "epoch": 0.7129482675606755, "grad_norm": 1.925177812576294, "learning_rate": 0.00018980974681700202, "loss": 0.6671298027038575, "step": 119940 }, { "epoch": 0.713007709637344, "grad_norm": 1.6248984336853027, "learning_rate": 0.00018980686952883667, "loss": 0.6726498126983642, "step": 119950 }, { "epoch": 0.7130671517140122, "grad_norm": 1.6934878826141357, "learning_rate": 0.00018980399185890133, "loss": 0.6769455909729004, "step": 119960 }, { "epoch": 0.7131265937906807, "grad_norm": 1.935978651046753, "learning_rate": 0.00018980111380720974, "loss": 0.7439340114593506, "step": 119970 }, { "epoch": 0.7131860358673491, "grad_norm": 1.7547309398651123, "learning_rate": 0.00018979823537377576, "loss": 0.7170228004455567, "step": 119980 }, { "epoch": 0.7132454779440175, "grad_norm": 2.062556505203247, "learning_rate": 0.00018979535655861305, "loss": 0.6300956249237061, "step": 119990 }, { "epoch": 0.7133049200206858, "grad_norm": 1.4602279663085938, "learning_rate": 0.00018979247736173547, "loss": 0.6745482444763183, "step": 120000 }, { "epoch": 0.7133643620973542, "grad_norm": 2.2501041889190674, "learning_rate": 0.00018978959778315674, "loss": 0.6861001491546631, "step": 120010 }, { "epoch": 0.7134238041740226, "grad_norm": 1.450203537940979, "learning_rate": 0.00018978671782289065, "loss": 0.6805940628051758, "step": 120020 }, { "epoch": 0.713483246250691, "grad_norm": 1.3999022245407104, "learning_rate": 0.00018978383748095094, "loss": 0.756125545501709, "step": 120030 }, { "epoch": 0.7135426883273595, "grad_norm": 1.7056113481521606, "learning_rate": 0.00018978095675735145, "loss": 0.6794159412384033, "step": 120040 }, { "epoch": 0.7136021304040278, "grad_norm": 1.8485417366027832, "learning_rate": 0.00018977807565210596, "loss": 0.6821229934692383, "step": 120050 }, { "epoch": 0.7136615724806962, "grad_norm": 1.702470302581787, "learning_rate": 0.0001897751941652282, "loss": 0.6880561828613281, "step": 120060 }, { "epoch": 0.7137210145573646, "grad_norm": 1.4945887327194214, "learning_rate": 0.000189772312296732, "loss": 0.6467158317565918, "step": 120070 }, { "epoch": 0.713780456634033, "grad_norm": 1.9179633855819702, "learning_rate": 0.00018976943004663112, "loss": 0.7018725395202636, "step": 120080 }, { "epoch": 0.7138398987107013, "grad_norm": 1.5132324695587158, "learning_rate": 0.00018976654741493937, "loss": 0.687054443359375, "step": 120090 }, { "epoch": 0.7138993407873697, "grad_norm": 1.4458619356155396, "learning_rate": 0.00018976366440167047, "loss": 0.7539712905883789, "step": 120100 }, { "epoch": 0.7139587828640381, "grad_norm": 1.8028095960617065, "learning_rate": 0.00018976078100683833, "loss": 0.6324239730834961, "step": 120110 }, { "epoch": 0.7140182249407065, "grad_norm": 1.763030767440796, "learning_rate": 0.00018975789723045666, "loss": 0.7143696784973145, "step": 120120 }, { "epoch": 0.714077667017375, "grad_norm": 1.699143648147583, "learning_rate": 0.00018975501307253926, "loss": 0.6582901000976562, "step": 120130 }, { "epoch": 0.7141371090940433, "grad_norm": 1.670717716217041, "learning_rate": 0.00018975212853309997, "loss": 0.6748565673828125, "step": 120140 }, { "epoch": 0.7141965511707117, "grad_norm": 1.6365742683410645, "learning_rate": 0.00018974924361215255, "loss": 0.6397859573364257, "step": 120150 }, { "epoch": 0.7142559932473801, "grad_norm": 1.7022461891174316, "learning_rate": 0.00018974635830971078, "loss": 0.6493865966796875, "step": 120160 }, { "epoch": 0.7143154353240485, "grad_norm": 1.6751154661178589, "learning_rate": 0.00018974347262578852, "loss": 0.7375033855438232, "step": 120170 }, { "epoch": 0.7143748774007169, "grad_norm": 1.7966797351837158, "learning_rate": 0.00018974058656039954, "loss": 0.6787396430969238, "step": 120180 }, { "epoch": 0.7144343194773852, "grad_norm": 2.198523759841919, "learning_rate": 0.00018973770011355767, "loss": 0.6784908294677734, "step": 120190 }, { "epoch": 0.7144937615540536, "grad_norm": 1.6394782066345215, "learning_rate": 0.00018973481328527669, "loss": 0.6749514579772949, "step": 120200 }, { "epoch": 0.7145532036307221, "grad_norm": 1.5430129766464233, "learning_rate": 0.00018973192607557043, "loss": 0.6516519546508789, "step": 120210 }, { "epoch": 0.7146126457073905, "grad_norm": 1.4653555154800415, "learning_rate": 0.00018972903848445266, "loss": 0.6597997665405273, "step": 120220 }, { "epoch": 0.7146720877840588, "grad_norm": 1.5275163650512695, "learning_rate": 0.00018972615051193726, "loss": 0.6230349063873291, "step": 120230 }, { "epoch": 0.7147315298607272, "grad_norm": 1.6076085567474365, "learning_rate": 0.000189723262158038, "loss": 0.6398709297180176, "step": 120240 }, { "epoch": 0.7147909719373956, "grad_norm": 1.8422749042510986, "learning_rate": 0.00018972037342276872, "loss": 0.6747833728790283, "step": 120250 }, { "epoch": 0.714850414014064, "grad_norm": 1.6702388525009155, "learning_rate": 0.0001897174843061432, "loss": 0.6522677421569825, "step": 120260 }, { "epoch": 0.7149098560907324, "grad_norm": 1.8965086936950684, "learning_rate": 0.0001897145948081753, "loss": 0.676616096496582, "step": 120270 }, { "epoch": 0.7149692981674007, "grad_norm": 1.6200122833251953, "learning_rate": 0.00018971170492887882, "loss": 0.6983930587768554, "step": 120280 }, { "epoch": 0.7150287402440691, "grad_norm": 1.5971988439559937, "learning_rate": 0.00018970881466826763, "loss": 0.6535476684570313, "step": 120290 }, { "epoch": 0.7150881823207376, "grad_norm": 1.793881893157959, "learning_rate": 0.00018970592402635546, "loss": 0.7038910388946533, "step": 120300 }, { "epoch": 0.715147624397406, "grad_norm": 1.3352060317993164, "learning_rate": 0.00018970303300315625, "loss": 0.6321802139282227, "step": 120310 }, { "epoch": 0.7152070664740744, "grad_norm": 1.7076412439346313, "learning_rate": 0.00018970014159868374, "loss": 0.6735478401184082, "step": 120320 }, { "epoch": 0.7152665085507427, "grad_norm": 1.7590950727462769, "learning_rate": 0.00018969724981295183, "loss": 0.5677505016326905, "step": 120330 }, { "epoch": 0.7153259506274111, "grad_norm": 1.5753251314163208, "learning_rate": 0.00018969435764597432, "loss": 0.7214884757995605, "step": 120340 }, { "epoch": 0.7153853927040795, "grad_norm": 1.666532039642334, "learning_rate": 0.000189691465097765, "loss": 0.6683286666870117, "step": 120350 }, { "epoch": 0.7154448347807479, "grad_norm": 1.5205628871917725, "learning_rate": 0.00018968857216833783, "loss": 0.7021738052368164, "step": 120360 }, { "epoch": 0.7155042768574162, "grad_norm": 1.4305495023727417, "learning_rate": 0.00018968567885770652, "loss": 0.6909771919250488, "step": 120370 }, { "epoch": 0.7155637189340847, "grad_norm": 1.4855287075042725, "learning_rate": 0.000189682785165885, "loss": 0.6895584106445313, "step": 120380 }, { "epoch": 0.7156231610107531, "grad_norm": 1.513363242149353, "learning_rate": 0.00018967989109288703, "loss": 0.6662958145141602, "step": 120390 }, { "epoch": 0.7156826030874215, "grad_norm": 2.367396593093872, "learning_rate": 0.00018967699663872652, "loss": 0.7055712699890136, "step": 120400 }, { "epoch": 0.7157420451640899, "grad_norm": 1.6728863716125488, "learning_rate": 0.0001896741018034173, "loss": 0.6786542892456054, "step": 120410 }, { "epoch": 0.7158014872407582, "grad_norm": 1.3434606790542603, "learning_rate": 0.0001896712065869732, "loss": 0.6416730880737305, "step": 120420 }, { "epoch": 0.7158609293174266, "grad_norm": 1.7747832536697388, "learning_rate": 0.00018966831098940815, "loss": 0.6700199127197266, "step": 120430 }, { "epoch": 0.715920371394095, "grad_norm": 2.0976877212524414, "learning_rate": 0.00018966541501073587, "loss": 0.7118739128112793, "step": 120440 }, { "epoch": 0.7159798134707634, "grad_norm": 1.6607897281646729, "learning_rate": 0.0001896625186509703, "loss": 0.7265597343444824, "step": 120450 }, { "epoch": 0.7160392555474318, "grad_norm": 1.7834789752960205, "learning_rate": 0.00018965962191012527, "loss": 0.6866805076599121, "step": 120460 }, { "epoch": 0.7160986976241002, "grad_norm": 1.4842493534088135, "learning_rate": 0.00018965672478821462, "loss": 0.6393560409545899, "step": 120470 }, { "epoch": 0.7161581397007686, "grad_norm": 2.0875771045684814, "learning_rate": 0.00018965382728525226, "loss": 0.6205252170562744, "step": 120480 }, { "epoch": 0.716217581777437, "grad_norm": 1.507580041885376, "learning_rate": 0.00018965092940125203, "loss": 0.6746072769165039, "step": 120490 }, { "epoch": 0.7162770238541054, "grad_norm": 1.7324764728546143, "learning_rate": 0.0001896480311362278, "loss": 0.6635243415832519, "step": 120500 }, { "epoch": 0.7163364659307737, "grad_norm": 1.9485292434692383, "learning_rate": 0.00018964513249019335, "loss": 0.6540661334991456, "step": 120510 }, { "epoch": 0.7163959080074421, "grad_norm": 1.6605180501937866, "learning_rate": 0.00018964223346316266, "loss": 0.6831818580627441, "step": 120520 }, { "epoch": 0.7164553500841105, "grad_norm": 1.3140933513641357, "learning_rate": 0.00018963933405514953, "loss": 0.6258701324462891, "step": 120530 }, { "epoch": 0.716514792160779, "grad_norm": 1.77312433719635, "learning_rate": 0.0001896364342661679, "loss": 0.6357439994812012, "step": 120540 }, { "epoch": 0.7165742342374474, "grad_norm": 1.6993820667266846, "learning_rate": 0.00018963353409623155, "loss": 0.655710506439209, "step": 120550 }, { "epoch": 0.7166336763141157, "grad_norm": 1.9472856521606445, "learning_rate": 0.0001896306335453544, "loss": 0.7087553977966309, "step": 120560 }, { "epoch": 0.7166931183907841, "grad_norm": 1.4694006443023682, "learning_rate": 0.00018962773261355033, "loss": 0.6254326820373535, "step": 120570 }, { "epoch": 0.7167525604674525, "grad_norm": 1.6583061218261719, "learning_rate": 0.0001896248313008332, "loss": 0.6647750854492187, "step": 120580 }, { "epoch": 0.7168120025441209, "grad_norm": 1.5858017206192017, "learning_rate": 0.00018962192960721692, "loss": 0.704283618927002, "step": 120590 }, { "epoch": 0.7168714446207892, "grad_norm": 1.568244218826294, "learning_rate": 0.00018961902753271534, "loss": 0.6627814769744873, "step": 120600 }, { "epoch": 0.7169308866974576, "grad_norm": 1.6531028747558594, "learning_rate": 0.00018961612507734235, "loss": 0.6123723983764648, "step": 120610 }, { "epoch": 0.716990328774126, "grad_norm": 1.6312310695648193, "learning_rate": 0.00018961322224111184, "loss": 0.6796143531799317, "step": 120620 }, { "epoch": 0.7170497708507945, "grad_norm": 1.5687435865402222, "learning_rate": 0.0001896103190240377, "loss": 0.675255537033081, "step": 120630 }, { "epoch": 0.7171092129274629, "grad_norm": 1.775566577911377, "learning_rate": 0.00018960741542613382, "loss": 0.6808719158172607, "step": 120640 }, { "epoch": 0.7171686550041312, "grad_norm": 1.5556044578552246, "learning_rate": 0.00018960451144741402, "loss": 0.6094073295593262, "step": 120650 }, { "epoch": 0.7172280970807996, "grad_norm": 1.6235792636871338, "learning_rate": 0.0001896016070878923, "loss": 0.5977571487426758, "step": 120660 }, { "epoch": 0.717287539157468, "grad_norm": 1.568466067314148, "learning_rate": 0.00018959870234758251, "loss": 0.6687605381011963, "step": 120670 }, { "epoch": 0.7173469812341364, "grad_norm": 1.8018938302993774, "learning_rate": 0.00018959579722649852, "loss": 0.6942300796508789, "step": 120680 }, { "epoch": 0.7174064233108048, "grad_norm": 1.2981151342391968, "learning_rate": 0.00018959289172465425, "loss": 0.6695223808288574, "step": 120690 }, { "epoch": 0.7174658653874731, "grad_norm": 1.5748456716537476, "learning_rate": 0.00018958998584206363, "loss": 0.646486473083496, "step": 120700 }, { "epoch": 0.7175253074641416, "grad_norm": 1.7345490455627441, "learning_rate": 0.0001895870795787405, "loss": 0.6723630428314209, "step": 120710 }, { "epoch": 0.71758474954081, "grad_norm": 1.6973284482955933, "learning_rate": 0.00018958417293469878, "loss": 0.7017746925354004, "step": 120720 }, { "epoch": 0.7176441916174784, "grad_norm": 1.7656980752944946, "learning_rate": 0.00018958126590995242, "loss": 0.6548656463623047, "step": 120730 }, { "epoch": 0.7177036336941467, "grad_norm": 1.5412890911102295, "learning_rate": 0.00018957835850451525, "loss": 0.6384796142578125, "step": 120740 }, { "epoch": 0.7177630757708151, "grad_norm": 1.6788780689239502, "learning_rate": 0.00018957545071840125, "loss": 0.6463955879211426, "step": 120750 }, { "epoch": 0.7178225178474835, "grad_norm": 1.4669806957244873, "learning_rate": 0.0001895725425516243, "loss": 0.6567292213439941, "step": 120760 }, { "epoch": 0.7178819599241519, "grad_norm": 1.4987273216247559, "learning_rate": 0.0001895696340041983, "loss": 0.7012324333190918, "step": 120770 }, { "epoch": 0.7179414020008204, "grad_norm": 1.5912725925445557, "learning_rate": 0.0001895667250761372, "loss": 0.6938098430633545, "step": 120780 }, { "epoch": 0.7180008440774887, "grad_norm": 1.5434287786483765, "learning_rate": 0.00018956381576745485, "loss": 0.6910608291625977, "step": 120790 }, { "epoch": 0.7180602861541571, "grad_norm": 2.1607542037963867, "learning_rate": 0.0001895609060781652, "loss": 0.6236563205718995, "step": 120800 }, { "epoch": 0.7181197282308255, "grad_norm": 1.400076150894165, "learning_rate": 0.0001895579960082822, "loss": 0.6561391830444336, "step": 120810 }, { "epoch": 0.7181791703074939, "grad_norm": 1.246134877204895, "learning_rate": 0.00018955508555781975, "loss": 0.7167416572570801, "step": 120820 }, { "epoch": 0.7182386123841622, "grad_norm": 1.50675368309021, "learning_rate": 0.0001895521747267918, "loss": 0.6321808815002441, "step": 120830 }, { "epoch": 0.7182980544608306, "grad_norm": 2.017944574356079, "learning_rate": 0.00018954926351521218, "loss": 0.724753999710083, "step": 120840 }, { "epoch": 0.718357496537499, "grad_norm": 1.465075969696045, "learning_rate": 0.0001895463519230949, "loss": 0.642905330657959, "step": 120850 }, { "epoch": 0.7184169386141674, "grad_norm": 1.533869743347168, "learning_rate": 0.0001895434399504539, "loss": 0.6442957878112793, "step": 120860 }, { "epoch": 0.7184763806908359, "grad_norm": 1.4593201875686646, "learning_rate": 0.00018954052759730304, "loss": 0.5865195751190185, "step": 120870 }, { "epoch": 0.7185358227675042, "grad_norm": 1.8154399394989014, "learning_rate": 0.0001895376148636563, "loss": 0.6952489852905274, "step": 120880 }, { "epoch": 0.7185952648441726, "grad_norm": 1.7471998929977417, "learning_rate": 0.00018953470174952762, "loss": 0.6886552810668946, "step": 120890 }, { "epoch": 0.718654706920841, "grad_norm": 1.9038431644439697, "learning_rate": 0.00018953178825493092, "loss": 0.6909621238708497, "step": 120900 }, { "epoch": 0.7187141489975094, "grad_norm": 1.8108084201812744, "learning_rate": 0.00018952887437988014, "loss": 0.7246707916259766, "step": 120910 }, { "epoch": 0.7187735910741778, "grad_norm": 1.870985507965088, "learning_rate": 0.00018952596012438919, "loss": 0.6286308288574218, "step": 120920 }, { "epoch": 0.7188330331508461, "grad_norm": 1.462113380432129, "learning_rate": 0.00018952304548847202, "loss": 0.6864891052246094, "step": 120930 }, { "epoch": 0.7188924752275145, "grad_norm": 1.5743563175201416, "learning_rate": 0.00018952013047214263, "loss": 0.6384693145751953, "step": 120940 }, { "epoch": 0.718951917304183, "grad_norm": 1.7849267721176147, "learning_rate": 0.0001895172150754149, "loss": 0.6776323318481445, "step": 120950 }, { "epoch": 0.7190113593808514, "grad_norm": 1.7105945348739624, "learning_rate": 0.00018951429929830283, "loss": 0.6568864345550537, "step": 120960 }, { "epoch": 0.7190708014575197, "grad_norm": 1.7506046295166016, "learning_rate": 0.00018951138314082032, "loss": 0.631539249420166, "step": 120970 }, { "epoch": 0.7191302435341881, "grad_norm": 1.691746473312378, "learning_rate": 0.00018950846660298134, "loss": 0.6823334693908691, "step": 120980 }, { "epoch": 0.7191896856108565, "grad_norm": 1.7982288599014282, "learning_rate": 0.00018950554968479982, "loss": 0.7403143882751465, "step": 120990 }, { "epoch": 0.7192491276875249, "grad_norm": 2.0071990489959717, "learning_rate": 0.00018950263238628977, "loss": 0.6675749778747558, "step": 121000 }, { "epoch": 0.7193085697641933, "grad_norm": 1.7571948766708374, "learning_rate": 0.00018949971470746507, "loss": 0.6596065044403077, "step": 121010 }, { "epoch": 0.7193680118408616, "grad_norm": 1.9601331949234009, "learning_rate": 0.00018949679664833973, "loss": 0.7427594661712646, "step": 121020 }, { "epoch": 0.71942745391753, "grad_norm": 1.6187281608581543, "learning_rate": 0.0001894938782089277, "loss": 0.6804319858551026, "step": 121030 }, { "epoch": 0.7194868959941985, "grad_norm": 1.5746105909347534, "learning_rate": 0.0001894909593892429, "loss": 0.610563087463379, "step": 121040 }, { "epoch": 0.7195463380708669, "grad_norm": 1.6632084846496582, "learning_rate": 0.00018948804018929937, "loss": 0.6793547630310058, "step": 121050 }, { "epoch": 0.7196057801475352, "grad_norm": 1.3404966592788696, "learning_rate": 0.00018948512060911103, "loss": 0.6269221305847168, "step": 121060 }, { "epoch": 0.7196652222242036, "grad_norm": 1.7007642984390259, "learning_rate": 0.00018948220064869182, "loss": 0.6891628742218018, "step": 121070 }, { "epoch": 0.719724664300872, "grad_norm": 1.421868920326233, "learning_rate": 0.00018947928030805579, "loss": 0.598674201965332, "step": 121080 }, { "epoch": 0.7197841063775404, "grad_norm": 1.4351757764816284, "learning_rate": 0.0001894763595872168, "loss": 0.6949478626251221, "step": 121090 }, { "epoch": 0.7198435484542088, "grad_norm": 1.5921063423156738, "learning_rate": 0.0001894734384861889, "loss": 0.6820194721221924, "step": 121100 }, { "epoch": 0.7199029905308771, "grad_norm": 1.761654019355774, "learning_rate": 0.0001894705170049861, "loss": 0.6361275672912597, "step": 121110 }, { "epoch": 0.7199624326075456, "grad_norm": 1.8252946138381958, "learning_rate": 0.00018946759514362223, "loss": 0.6358734130859375, "step": 121120 }, { "epoch": 0.720021874684214, "grad_norm": 1.4753962755203247, "learning_rate": 0.00018946467290211142, "loss": 0.6560355186462402, "step": 121130 }, { "epoch": 0.7200813167608824, "grad_norm": 1.5834842920303345, "learning_rate": 0.00018946175028046754, "loss": 0.6189105033874511, "step": 121140 }, { "epoch": 0.7201407588375508, "grad_norm": 1.8139500617980957, "learning_rate": 0.00018945882727870462, "loss": 0.7022825241088867, "step": 121150 }, { "epoch": 0.7202002009142191, "grad_norm": 1.7892104387283325, "learning_rate": 0.00018945590389683666, "loss": 0.6487508773803711, "step": 121160 }, { "epoch": 0.7202596429908875, "grad_norm": 1.698385238647461, "learning_rate": 0.0001894529801348776, "loss": 0.6284876823425293, "step": 121170 }, { "epoch": 0.7203190850675559, "grad_norm": 1.3513470888137817, "learning_rate": 0.00018945005599284144, "loss": 0.6481369018554688, "step": 121180 }, { "epoch": 0.7203785271442243, "grad_norm": 2.5316686630249023, "learning_rate": 0.0001894471314707422, "loss": 0.6732616424560547, "step": 121190 }, { "epoch": 0.7204379692208926, "grad_norm": 1.5336768627166748, "learning_rate": 0.00018944420656859384, "loss": 0.6300054073333741, "step": 121200 }, { "epoch": 0.7204974112975611, "grad_norm": 1.6493947505950928, "learning_rate": 0.00018944128128641036, "loss": 0.7182686805725098, "step": 121210 }, { "epoch": 0.7205568533742295, "grad_norm": 1.7977145910263062, "learning_rate": 0.00018943835562420575, "loss": 0.6690192699432373, "step": 121220 }, { "epoch": 0.7206162954508979, "grad_norm": 1.7115992307662964, "learning_rate": 0.000189435429581994, "loss": 0.664960241317749, "step": 121230 }, { "epoch": 0.7206757375275663, "grad_norm": 1.4642558097839355, "learning_rate": 0.00018943250315978913, "loss": 0.6722770690917969, "step": 121240 }, { "epoch": 0.7207351796042346, "grad_norm": 1.754055142402649, "learning_rate": 0.00018942957635760513, "loss": 0.6729555130004883, "step": 121250 }, { "epoch": 0.720794621680903, "grad_norm": 1.5532679557800293, "learning_rate": 0.00018942664917545596, "loss": 0.6122354984283447, "step": 121260 }, { "epoch": 0.7208540637575714, "grad_norm": 1.9096821546554565, "learning_rate": 0.0001894237216133557, "loss": 0.7220487594604492, "step": 121270 }, { "epoch": 0.7209135058342399, "grad_norm": 1.8827540874481201, "learning_rate": 0.0001894207936713183, "loss": 0.6577696800231934, "step": 121280 }, { "epoch": 0.7209729479109083, "grad_norm": 2.2077856063842773, "learning_rate": 0.00018941786534935776, "loss": 0.6408709526062012, "step": 121290 }, { "epoch": 0.7210323899875766, "grad_norm": 1.824220895767212, "learning_rate": 0.0001894149366474881, "loss": 0.7129812240600586, "step": 121300 }, { "epoch": 0.721091832064245, "grad_norm": 1.5730383396148682, "learning_rate": 0.00018941200756572335, "loss": 0.6795065879821778, "step": 121310 }, { "epoch": 0.7211512741409134, "grad_norm": 1.5826970338821411, "learning_rate": 0.00018940907810407752, "loss": 0.6223749160766602, "step": 121320 }, { "epoch": 0.7212107162175818, "grad_norm": 1.544755458831787, "learning_rate": 0.0001894061482625646, "loss": 0.6451963901519775, "step": 121330 }, { "epoch": 0.7212701582942501, "grad_norm": 2.7732439041137695, "learning_rate": 0.00018940321804119864, "loss": 0.7076457023620606, "step": 121340 }, { "epoch": 0.7213296003709185, "grad_norm": 1.8482997417449951, "learning_rate": 0.0001894002874399936, "loss": 0.6885455131530762, "step": 121350 }, { "epoch": 0.721389042447587, "grad_norm": 1.6544872522354126, "learning_rate": 0.00018939735645896353, "loss": 0.7219302177429199, "step": 121360 }, { "epoch": 0.7214484845242554, "grad_norm": 1.8371174335479736, "learning_rate": 0.00018939442509812246, "loss": 0.6967854022979736, "step": 121370 }, { "epoch": 0.7215079266009238, "grad_norm": 1.6592376232147217, "learning_rate": 0.00018939149335748444, "loss": 0.6548009872436523, "step": 121380 }, { "epoch": 0.7215673686775921, "grad_norm": 1.5765275955200195, "learning_rate": 0.0001893885612370634, "loss": 0.6803114891052247, "step": 121390 }, { "epoch": 0.7216268107542605, "grad_norm": 1.9758092164993286, "learning_rate": 0.0001893856287368735, "loss": 0.660345458984375, "step": 121400 }, { "epoch": 0.7216862528309289, "grad_norm": 2.0824942588806152, "learning_rate": 0.00018938269585692865, "loss": 0.6541214942932129, "step": 121410 }, { "epoch": 0.7217456949075973, "grad_norm": 1.5668151378631592, "learning_rate": 0.00018937976259724294, "loss": 0.6607582569122314, "step": 121420 }, { "epoch": 0.7218051369842656, "grad_norm": 1.5008487701416016, "learning_rate": 0.00018937682895783038, "loss": 0.6689754962921143, "step": 121430 }, { "epoch": 0.721864579060934, "grad_norm": 1.729006290435791, "learning_rate": 0.00018937389493870502, "loss": 0.6083875179290772, "step": 121440 }, { "epoch": 0.7219240211376025, "grad_norm": 1.4970462322235107, "learning_rate": 0.00018937096053988085, "loss": 0.6668011665344238, "step": 121450 }, { "epoch": 0.7219834632142709, "grad_norm": 1.452028512954712, "learning_rate": 0.000189368025761372, "loss": 0.6926297664642334, "step": 121460 }, { "epoch": 0.7220429052909393, "grad_norm": 1.6798298358917236, "learning_rate": 0.00018936509060319244, "loss": 0.6605940341949463, "step": 121470 }, { "epoch": 0.7221023473676076, "grad_norm": 1.832737684249878, "learning_rate": 0.0001893621550653562, "loss": 0.6262980937957764, "step": 121480 }, { "epoch": 0.722161789444276, "grad_norm": 2.181957244873047, "learning_rate": 0.00018935921914787736, "loss": 0.7129339218139649, "step": 121490 }, { "epoch": 0.7222212315209444, "grad_norm": 1.452662706375122, "learning_rate": 0.0001893562828507699, "loss": 0.7056928634643554, "step": 121500 }, { "epoch": 0.7222806735976128, "grad_norm": 1.4749653339385986, "learning_rate": 0.000189353346174048, "loss": 0.6604043006896972, "step": 121510 }, { "epoch": 0.7223401156742812, "grad_norm": 1.922273874282837, "learning_rate": 0.00018935040911772556, "loss": 0.6682552337646485, "step": 121520 }, { "epoch": 0.7223995577509496, "grad_norm": 1.637258529663086, "learning_rate": 0.00018934747168181673, "loss": 0.7835715293884278, "step": 121530 }, { "epoch": 0.722458999827618, "grad_norm": 2.140920400619507, "learning_rate": 0.00018934453386633553, "loss": 0.6943249225616455, "step": 121540 }, { "epoch": 0.7225184419042864, "grad_norm": 1.7308584451675415, "learning_rate": 0.00018934159567129602, "loss": 0.6963115692138672, "step": 121550 }, { "epoch": 0.7225778839809548, "grad_norm": 1.7588082551956177, "learning_rate": 0.00018933865709671222, "loss": 0.6519632339477539, "step": 121560 }, { "epoch": 0.7226373260576231, "grad_norm": 1.9282951354980469, "learning_rate": 0.00018933571814259818, "loss": 0.7052424907684326, "step": 121570 }, { "epoch": 0.7226967681342915, "grad_norm": 1.462709665298462, "learning_rate": 0.00018933277880896806, "loss": 0.6987955093383789, "step": 121580 }, { "epoch": 0.7227562102109599, "grad_norm": 1.9872395992279053, "learning_rate": 0.00018932983909583583, "loss": 0.6821343421936035, "step": 121590 }, { "epoch": 0.7228156522876283, "grad_norm": 1.7538743019104004, "learning_rate": 0.00018932689900321556, "loss": 0.6474949359893799, "step": 121600 }, { "epoch": 0.7228750943642968, "grad_norm": 1.7831594944000244, "learning_rate": 0.00018932395853112131, "loss": 0.7119669437408447, "step": 121610 }, { "epoch": 0.7229345364409651, "grad_norm": 1.5476516485214233, "learning_rate": 0.0001893210176795672, "loss": 0.6442946910858154, "step": 121620 }, { "epoch": 0.7229939785176335, "grad_norm": 2.1464920043945312, "learning_rate": 0.00018931807644856726, "loss": 0.6928482055664062, "step": 121630 }, { "epoch": 0.7230534205943019, "grad_norm": 1.370314598083496, "learning_rate": 0.00018931513483813557, "loss": 0.6525217533111572, "step": 121640 }, { "epoch": 0.7231128626709703, "grad_norm": 1.2711076736450195, "learning_rate": 0.00018931219284828616, "loss": 0.6435635566711426, "step": 121650 }, { "epoch": 0.7231723047476387, "grad_norm": 1.4615263938903809, "learning_rate": 0.00018930925047903318, "loss": 0.6071685791015625, "step": 121660 }, { "epoch": 0.723231746824307, "grad_norm": 2.0145223140716553, "learning_rate": 0.00018930630773039066, "loss": 0.670433759689331, "step": 121670 }, { "epoch": 0.7232911889009754, "grad_norm": 2.1313745975494385, "learning_rate": 0.00018930336460237267, "loss": 0.6528852939605713, "step": 121680 }, { "epoch": 0.7233506309776438, "grad_norm": 1.58083975315094, "learning_rate": 0.0001893004210949933, "loss": 0.648020601272583, "step": 121690 }, { "epoch": 0.7234100730543123, "grad_norm": 1.885661005973816, "learning_rate": 0.00018929747720826664, "loss": 0.6317255020141601, "step": 121700 }, { "epoch": 0.7234695151309806, "grad_norm": 2.13330078125, "learning_rate": 0.00018929453294220673, "loss": 0.6727653980255127, "step": 121710 }, { "epoch": 0.723528957207649, "grad_norm": 2.047515392303467, "learning_rate": 0.00018929158829682772, "loss": 0.6225652694702148, "step": 121720 }, { "epoch": 0.7235883992843174, "grad_norm": 1.868491291999817, "learning_rate": 0.00018928864327214364, "loss": 0.7675660610198974, "step": 121730 }, { "epoch": 0.7236478413609858, "grad_norm": 1.4776437282562256, "learning_rate": 0.00018928569786816864, "loss": 0.677088451385498, "step": 121740 }, { "epoch": 0.7237072834376542, "grad_norm": 1.4685450792312622, "learning_rate": 0.00018928275208491676, "loss": 0.6048739433288575, "step": 121750 }, { "epoch": 0.7237667255143225, "grad_norm": 1.7247079610824585, "learning_rate": 0.00018927980592240207, "loss": 0.6789388656616211, "step": 121760 }, { "epoch": 0.7238261675909909, "grad_norm": 1.5918705463409424, "learning_rate": 0.00018927685938063872, "loss": 0.6746316432952881, "step": 121770 }, { "epoch": 0.7238856096676594, "grad_norm": 1.9374268054962158, "learning_rate": 0.0001892739124596408, "loss": 0.6993186950683594, "step": 121780 }, { "epoch": 0.7239450517443278, "grad_norm": 2.3337488174438477, "learning_rate": 0.00018927096515942236, "loss": 0.6337356090545654, "step": 121790 }, { "epoch": 0.7240044938209961, "grad_norm": 2.9185054302215576, "learning_rate": 0.00018926801747999757, "loss": 0.7408360004425049, "step": 121800 }, { "epoch": 0.7240639358976645, "grad_norm": 1.8316789865493774, "learning_rate": 0.0001892650694213804, "loss": 0.6895984649658203, "step": 121810 }, { "epoch": 0.7241233779743329, "grad_norm": 1.4258555173873901, "learning_rate": 0.00018926212098358515, "loss": 0.594170093536377, "step": 121820 }, { "epoch": 0.7241828200510013, "grad_norm": 1.681109070777893, "learning_rate": 0.0001892591721666258, "loss": 0.6279430389404297, "step": 121830 }, { "epoch": 0.7242422621276697, "grad_norm": 1.7533609867095947, "learning_rate": 0.0001892562229705164, "loss": 0.6792912006378173, "step": 121840 }, { "epoch": 0.724301704204338, "grad_norm": 1.733031988143921, "learning_rate": 0.0001892532733952712, "loss": 0.6633769989013671, "step": 121850 }, { "epoch": 0.7243611462810065, "grad_norm": 1.9727333784103394, "learning_rate": 0.0001892503234409042, "loss": 0.659822940826416, "step": 121860 }, { "epoch": 0.7244205883576749, "grad_norm": 1.7107319831848145, "learning_rate": 0.00018924737310742958, "loss": 0.6182597637176513, "step": 121870 }, { "epoch": 0.7244800304343433, "grad_norm": 1.9326156377792358, "learning_rate": 0.00018924442239486142, "loss": 0.6475037097930908, "step": 121880 }, { "epoch": 0.7245394725110117, "grad_norm": 1.8907463550567627, "learning_rate": 0.0001892414713032138, "loss": 0.6238755226135254, "step": 121890 }, { "epoch": 0.72459891458768, "grad_norm": 2.0193498134613037, "learning_rate": 0.00018923851983250093, "loss": 0.7218663215637207, "step": 121900 }, { "epoch": 0.7246583566643484, "grad_norm": 2.3975987434387207, "learning_rate": 0.00018923556798273685, "loss": 0.7025291442871093, "step": 121910 }, { "epoch": 0.7247177987410168, "grad_norm": 1.5792731046676636, "learning_rate": 0.00018923261575393575, "loss": 0.6778327941894531, "step": 121920 }, { "epoch": 0.7247772408176852, "grad_norm": 1.7043805122375488, "learning_rate": 0.00018922966314611166, "loss": 0.6329924583435058, "step": 121930 }, { "epoch": 0.7248366828943535, "grad_norm": 1.588557481765747, "learning_rate": 0.00018922671015927876, "loss": 0.6519717216491699, "step": 121940 }, { "epoch": 0.724896124971022, "grad_norm": 1.6587247848510742, "learning_rate": 0.00018922375679345118, "loss": 0.7038733959197998, "step": 121950 }, { "epoch": 0.7249555670476904, "grad_norm": 1.70621919631958, "learning_rate": 0.00018922080304864303, "loss": 0.5983391761779785, "step": 121960 }, { "epoch": 0.7250150091243588, "grad_norm": 1.7798681259155273, "learning_rate": 0.00018921784892486846, "loss": 0.6519797325134278, "step": 121970 }, { "epoch": 0.7250744512010272, "grad_norm": 2.154381036758423, "learning_rate": 0.00018921489442214154, "loss": 0.6715221881866456, "step": 121980 }, { "epoch": 0.7251338932776955, "grad_norm": 1.388960599899292, "learning_rate": 0.00018921193954047653, "loss": 0.6530447959899902, "step": 121990 }, { "epoch": 0.7251933353543639, "grad_norm": 1.5655980110168457, "learning_rate": 0.00018920898427988745, "loss": 0.6896151065826416, "step": 122000 }, { "epoch": 0.7252527774310323, "grad_norm": 1.351747751235962, "learning_rate": 0.00018920602864038849, "loss": 0.6022528171539306, "step": 122010 }, { "epoch": 0.7253122195077008, "grad_norm": 1.5624783039093018, "learning_rate": 0.00018920307262199374, "loss": 0.5940508842468262, "step": 122020 }, { "epoch": 0.7253716615843692, "grad_norm": 1.3938766717910767, "learning_rate": 0.0001892001162247174, "loss": 0.5724486351013184, "step": 122030 }, { "epoch": 0.7254311036610375, "grad_norm": 1.5892094373703003, "learning_rate": 0.00018919715944857362, "loss": 0.687695837020874, "step": 122040 }, { "epoch": 0.7254905457377059, "grad_norm": 1.6135469675064087, "learning_rate": 0.00018919420229357645, "loss": 0.671441125869751, "step": 122050 }, { "epoch": 0.7255499878143743, "grad_norm": 1.657863736152649, "learning_rate": 0.00018919124475974013, "loss": 0.6702909469604492, "step": 122060 }, { "epoch": 0.7256094298910427, "grad_norm": 1.9631818532943726, "learning_rate": 0.00018918828684707877, "loss": 0.6814210414886475, "step": 122070 }, { "epoch": 0.725668871967711, "grad_norm": 1.5328338146209717, "learning_rate": 0.00018918532855560652, "loss": 0.6518941879272461, "step": 122080 }, { "epoch": 0.7257283140443794, "grad_norm": 1.5386157035827637, "learning_rate": 0.00018918236988533753, "loss": 0.745302152633667, "step": 122090 }, { "epoch": 0.7257877561210478, "grad_norm": 1.4323513507843018, "learning_rate": 0.00018917941083628596, "loss": 0.6951086521148682, "step": 122100 }, { "epoch": 0.7258471981977163, "grad_norm": 1.6084423065185547, "learning_rate": 0.000189176451408466, "loss": 0.6576415538787842, "step": 122110 }, { "epoch": 0.7259066402743847, "grad_norm": 2.0242056846618652, "learning_rate": 0.00018917349160189174, "loss": 0.6956451416015625, "step": 122120 }, { "epoch": 0.725966082351053, "grad_norm": 1.4840425252914429, "learning_rate": 0.00018917053141657736, "loss": 0.6987936496734619, "step": 122130 }, { "epoch": 0.7260255244277214, "grad_norm": 1.9860446453094482, "learning_rate": 0.00018916757085253707, "loss": 0.700947618484497, "step": 122140 }, { "epoch": 0.7260849665043898, "grad_norm": 1.6026872396469116, "learning_rate": 0.00018916460990978494, "loss": 0.6589175224304199, "step": 122150 }, { "epoch": 0.7261444085810582, "grad_norm": 1.8675457239151, "learning_rate": 0.00018916164858833522, "loss": 0.6836073875427247, "step": 122160 }, { "epoch": 0.7262038506577265, "grad_norm": 2.1800146102905273, "learning_rate": 0.00018915868688820203, "loss": 0.6925055503845214, "step": 122170 }, { "epoch": 0.7262632927343949, "grad_norm": 1.9990819692611694, "learning_rate": 0.00018915572480939958, "loss": 0.6821382999420166, "step": 122180 }, { "epoch": 0.7263227348110634, "grad_norm": 1.9146597385406494, "learning_rate": 0.00018915276235194198, "loss": 0.6755113124847412, "step": 122190 }, { "epoch": 0.7263821768877318, "grad_norm": 1.7095056772232056, "learning_rate": 0.00018914979951584348, "loss": 0.669924545288086, "step": 122200 }, { "epoch": 0.7264416189644002, "grad_norm": 1.759509801864624, "learning_rate": 0.00018914683630111815, "loss": 0.6732633590698243, "step": 122210 }, { "epoch": 0.7265010610410685, "grad_norm": 1.3471851348876953, "learning_rate": 0.00018914387270778022, "loss": 0.6159996032714844, "step": 122220 }, { "epoch": 0.7265605031177369, "grad_norm": 1.607026219367981, "learning_rate": 0.0001891409087358439, "loss": 0.6624679565429688, "step": 122230 }, { "epoch": 0.7266199451944053, "grad_norm": 1.557215690612793, "learning_rate": 0.00018913794438532334, "loss": 0.6326943874359131, "step": 122240 }, { "epoch": 0.7266793872710737, "grad_norm": 1.9248112440109253, "learning_rate": 0.0001891349796562327, "loss": 0.6639413833618164, "step": 122250 }, { "epoch": 0.7267388293477421, "grad_norm": 1.354136347770691, "learning_rate": 0.0001891320145485862, "loss": 0.6605213165283204, "step": 122260 }, { "epoch": 0.7267982714244104, "grad_norm": 1.7262355089187622, "learning_rate": 0.00018912904906239795, "loss": 0.6837942123413085, "step": 122270 }, { "epoch": 0.7268577135010789, "grad_norm": 1.7361066341400146, "learning_rate": 0.00018912608319768224, "loss": 0.7162907600402832, "step": 122280 }, { "epoch": 0.7269171555777473, "grad_norm": 1.8391950130462646, "learning_rate": 0.00018912311695445317, "loss": 0.6671435356140136, "step": 122290 }, { "epoch": 0.7269765976544157, "grad_norm": 1.7879505157470703, "learning_rate": 0.00018912015033272498, "loss": 0.6025218009948731, "step": 122300 }, { "epoch": 0.727036039731084, "grad_norm": 1.912409782409668, "learning_rate": 0.00018911718333251186, "loss": 0.6651583671569824, "step": 122310 }, { "epoch": 0.7270954818077524, "grad_norm": 1.5382355451583862, "learning_rate": 0.000189114215953828, "loss": 0.6802514553070068, "step": 122320 }, { "epoch": 0.7271549238844208, "grad_norm": 1.6603447198867798, "learning_rate": 0.00018911124819668754, "loss": 0.660954475402832, "step": 122330 }, { "epoch": 0.7272143659610892, "grad_norm": 1.9306106567382812, "learning_rate": 0.0001891082800611048, "loss": 0.7076356410980225, "step": 122340 }, { "epoch": 0.7272738080377577, "grad_norm": 1.7226049900054932, "learning_rate": 0.0001891053115470938, "loss": 0.6837396621704102, "step": 122350 }, { "epoch": 0.727333250114426, "grad_norm": 1.7747163772583008, "learning_rate": 0.0001891023426546689, "loss": 0.5801347732543946, "step": 122360 }, { "epoch": 0.7273926921910944, "grad_norm": 1.5355583429336548, "learning_rate": 0.00018909937338384427, "loss": 0.6115879535675048, "step": 122370 }, { "epoch": 0.7274521342677628, "grad_norm": 1.7446649074554443, "learning_rate": 0.00018909640373463403, "loss": 0.7040592193603515, "step": 122380 }, { "epoch": 0.7275115763444312, "grad_norm": 1.9201580286026, "learning_rate": 0.0001890934337070525, "loss": 0.5962762832641602, "step": 122390 }, { "epoch": 0.7275710184210996, "grad_norm": 1.5575352907180786, "learning_rate": 0.0001890904633011138, "loss": 0.7065786361694336, "step": 122400 }, { "epoch": 0.7276304604977679, "grad_norm": 1.6977407932281494, "learning_rate": 0.00018908749251683214, "loss": 0.680203914642334, "step": 122410 }, { "epoch": 0.7276899025744363, "grad_norm": 1.8171226978302002, "learning_rate": 0.0001890845213542218, "loss": 0.6489602088928222, "step": 122420 }, { "epoch": 0.7277493446511047, "grad_norm": 1.5259666442871094, "learning_rate": 0.00018908154981329696, "loss": 0.7011406898498536, "step": 122430 }, { "epoch": 0.7278087867277732, "grad_norm": 2.135104179382324, "learning_rate": 0.00018907857789407178, "loss": 0.6388591766357422, "step": 122440 }, { "epoch": 0.7278682288044415, "grad_norm": 1.5754029750823975, "learning_rate": 0.00018907560559656058, "loss": 0.6775569438934326, "step": 122450 }, { "epoch": 0.7279276708811099, "grad_norm": 1.6956599950790405, "learning_rate": 0.0001890726329207775, "loss": 0.6514978408813477, "step": 122460 }, { "epoch": 0.7279871129577783, "grad_norm": 1.717585563659668, "learning_rate": 0.00018906965986673684, "loss": 0.6386339664459229, "step": 122470 }, { "epoch": 0.7280465550344467, "grad_norm": 1.5934125185012817, "learning_rate": 0.00018906668643445268, "loss": 0.664447546005249, "step": 122480 }, { "epoch": 0.7281059971111151, "grad_norm": 1.5354950428009033, "learning_rate": 0.0001890637126239394, "loss": 0.6983616828918457, "step": 122490 }, { "epoch": 0.7281654391877834, "grad_norm": 2.0194244384765625, "learning_rate": 0.00018906073843521113, "loss": 0.7047222137451172, "step": 122500 }, { "epoch": 0.7282248812644518, "grad_norm": 1.6419594287872314, "learning_rate": 0.00018905776386828212, "loss": 0.6434905052185058, "step": 122510 }, { "epoch": 0.7282843233411203, "grad_norm": 1.980707049369812, "learning_rate": 0.0001890547889231666, "loss": 0.6748453617095947, "step": 122520 }, { "epoch": 0.7283437654177887, "grad_norm": 1.391192078590393, "learning_rate": 0.0001890518135998788, "loss": 0.7383620262145996, "step": 122530 }, { "epoch": 0.728403207494457, "grad_norm": 1.7502778768539429, "learning_rate": 0.000189048837898433, "loss": 0.6754257202148437, "step": 122540 }, { "epoch": 0.7284626495711254, "grad_norm": 3.1625969409942627, "learning_rate": 0.00018904586181884336, "loss": 0.7581770420074463, "step": 122550 }, { "epoch": 0.7285220916477938, "grad_norm": 1.5170235633850098, "learning_rate": 0.00018904288536112415, "loss": 0.6265894412994385, "step": 122560 }, { "epoch": 0.7285815337244622, "grad_norm": 1.6312988996505737, "learning_rate": 0.00018903990852528964, "loss": 0.6551923751831055, "step": 122570 }, { "epoch": 0.7286409758011306, "grad_norm": 1.5761140584945679, "learning_rate": 0.00018903693131135397, "loss": 0.7116969108581543, "step": 122580 }, { "epoch": 0.7287004178777989, "grad_norm": 1.620449423789978, "learning_rate": 0.0001890339537193315, "loss": 0.6579261302947998, "step": 122590 }, { "epoch": 0.7287598599544673, "grad_norm": 2.0786731243133545, "learning_rate": 0.0001890309757492364, "loss": 0.6831146717071533, "step": 122600 }, { "epoch": 0.7288193020311358, "grad_norm": 1.34660804271698, "learning_rate": 0.00018902799740108298, "loss": 0.6290470123291015, "step": 122610 }, { "epoch": 0.7288787441078042, "grad_norm": 1.496727466583252, "learning_rate": 0.0001890250186748854, "loss": 0.6596044540405274, "step": 122620 }, { "epoch": 0.7289381861844726, "grad_norm": 1.5506941080093384, "learning_rate": 0.00018902203957065798, "loss": 0.6805389404296875, "step": 122630 }, { "epoch": 0.7289976282611409, "grad_norm": 1.8008137941360474, "learning_rate": 0.00018901906008841494, "loss": 0.6958023071289062, "step": 122640 }, { "epoch": 0.7290570703378093, "grad_norm": 1.485243558883667, "learning_rate": 0.00018901608022817056, "loss": 0.6914680957794189, "step": 122650 }, { "epoch": 0.7291165124144777, "grad_norm": 1.7643119096755981, "learning_rate": 0.00018901309998993905, "loss": 0.6481203079223633, "step": 122660 }, { "epoch": 0.7291759544911461, "grad_norm": 1.336098074913025, "learning_rate": 0.00018901011937373473, "loss": 0.6828431129455567, "step": 122670 }, { "epoch": 0.7292353965678144, "grad_norm": 1.9554452896118164, "learning_rate": 0.0001890071383795718, "loss": 0.641784381866455, "step": 122680 }, { "epoch": 0.7292948386444829, "grad_norm": 1.7488764524459839, "learning_rate": 0.0001890041570074645, "loss": 0.7174785614013672, "step": 122690 }, { "epoch": 0.7293542807211513, "grad_norm": 1.506744146347046, "learning_rate": 0.00018900117525742717, "loss": 0.644978141784668, "step": 122700 }, { "epoch": 0.7294137227978197, "grad_norm": 1.553242802619934, "learning_rate": 0.000188998193129474, "loss": 0.6557622909545898, "step": 122710 }, { "epoch": 0.7294731648744881, "grad_norm": 1.7411302328109741, "learning_rate": 0.00018899521062361936, "loss": 0.6136738777160644, "step": 122720 }, { "epoch": 0.7295326069511564, "grad_norm": 2.103700876235962, "learning_rate": 0.00018899222773987738, "loss": 0.6376728057861328, "step": 122730 }, { "epoch": 0.7295920490278248, "grad_norm": 1.8357834815979004, "learning_rate": 0.00018898924447826245, "loss": 0.6530269622802735, "step": 122740 }, { "epoch": 0.7296514911044932, "grad_norm": 2.134206533432007, "learning_rate": 0.00018898626083878876, "loss": 0.6952733039855957, "step": 122750 }, { "epoch": 0.7297109331811616, "grad_norm": 2.014261484146118, "learning_rate": 0.0001889832768214706, "loss": 0.6858298778533936, "step": 122760 }, { "epoch": 0.7297703752578301, "grad_norm": 1.3767582178115845, "learning_rate": 0.00018898029242632228, "loss": 0.6390450477600098, "step": 122770 }, { "epoch": 0.7298298173344984, "grad_norm": 1.5546438694000244, "learning_rate": 0.00018897730765335803, "loss": 0.6045787811279297, "step": 122780 }, { "epoch": 0.7298892594111668, "grad_norm": 1.6018954515457153, "learning_rate": 0.0001889743225025922, "loss": 0.6356132984161377, "step": 122790 }, { "epoch": 0.7299487014878352, "grad_norm": 1.3480538129806519, "learning_rate": 0.00018897133697403897, "loss": 0.6256929874420166, "step": 122800 }, { "epoch": 0.7300081435645036, "grad_norm": 1.384610652923584, "learning_rate": 0.00018896835106771266, "loss": 0.7303779602050782, "step": 122810 }, { "epoch": 0.7300675856411719, "grad_norm": 1.9409042596817017, "learning_rate": 0.0001889653647836276, "loss": 0.6719219207763671, "step": 122820 }, { "epoch": 0.7301270277178403, "grad_norm": 1.5077271461486816, "learning_rate": 0.00018896237812179802, "loss": 0.7283945083618164, "step": 122830 }, { "epoch": 0.7301864697945087, "grad_norm": 2.247506856918335, "learning_rate": 0.00018895939108223825, "loss": 0.6745678901672363, "step": 122840 }, { "epoch": 0.7302459118711772, "grad_norm": 1.88556706905365, "learning_rate": 0.00018895640366496254, "loss": 0.7269855976104737, "step": 122850 }, { "epoch": 0.7303053539478456, "grad_norm": 1.842018485069275, "learning_rate": 0.00018895341586998524, "loss": 0.6221748352050781, "step": 122860 }, { "epoch": 0.7303647960245139, "grad_norm": 1.8497816324234009, "learning_rate": 0.00018895042769732055, "loss": 0.6973729610443116, "step": 122870 }, { "epoch": 0.7304242381011823, "grad_norm": 1.230757236480713, "learning_rate": 0.00018894743914698282, "loss": 0.6348958492279053, "step": 122880 }, { "epoch": 0.7304836801778507, "grad_norm": 1.8130258321762085, "learning_rate": 0.00018894445021898636, "loss": 0.664949607849121, "step": 122890 }, { "epoch": 0.7305431222545191, "grad_norm": 1.4966953992843628, "learning_rate": 0.00018894146091334545, "loss": 0.6257356643676758, "step": 122900 }, { "epoch": 0.7306025643311874, "grad_norm": 1.7994520664215088, "learning_rate": 0.00018893847123007434, "loss": 0.7057733535766602, "step": 122910 }, { "epoch": 0.7306620064078558, "grad_norm": 1.259040355682373, "learning_rate": 0.00018893548116918744, "loss": 0.6908045768737793, "step": 122920 }, { "epoch": 0.7307214484845242, "grad_norm": 1.3637664318084717, "learning_rate": 0.000188932490730699, "loss": 0.6542322158813476, "step": 122930 }, { "epoch": 0.7307808905611927, "grad_norm": 1.3344346284866333, "learning_rate": 0.00018892949991462327, "loss": 0.620390796661377, "step": 122940 }, { "epoch": 0.7308403326378611, "grad_norm": 1.5636398792266846, "learning_rate": 0.00018892650872097465, "loss": 0.618720817565918, "step": 122950 }, { "epoch": 0.7308997747145294, "grad_norm": 2.0161659717559814, "learning_rate": 0.0001889235171497674, "loss": 0.674588680267334, "step": 122960 }, { "epoch": 0.7309592167911978, "grad_norm": 1.8532503843307495, "learning_rate": 0.00018892052520101582, "loss": 0.6636914253234864, "step": 122970 }, { "epoch": 0.7310186588678662, "grad_norm": 1.8315138816833496, "learning_rate": 0.00018891753287473423, "loss": 0.6962338447570801, "step": 122980 }, { "epoch": 0.7310781009445346, "grad_norm": 1.5972614288330078, "learning_rate": 0.000188914540170937, "loss": 0.6967000961303711, "step": 122990 }, { "epoch": 0.731137543021203, "grad_norm": 1.5881171226501465, "learning_rate": 0.00018891154708963834, "loss": 0.7186580657958984, "step": 123000 }, { "epoch": 0.7311969850978713, "grad_norm": 1.4565914869308472, "learning_rate": 0.00018890855363085267, "loss": 0.5864132881164551, "step": 123010 }, { "epoch": 0.7312564271745398, "grad_norm": 1.3540594577789307, "learning_rate": 0.00018890555979459423, "loss": 0.6582183361053466, "step": 123020 }, { "epoch": 0.7313158692512082, "grad_norm": 2.093514919281006, "learning_rate": 0.00018890256558087742, "loss": 0.6711344718933105, "step": 123030 }, { "epoch": 0.7313753113278766, "grad_norm": 1.6318845748901367, "learning_rate": 0.0001888995709897165, "loss": 0.6448257446289063, "step": 123040 }, { "epoch": 0.7314347534045449, "grad_norm": 1.5725691318511963, "learning_rate": 0.00018889657602112582, "loss": 0.6205056190490723, "step": 123050 }, { "epoch": 0.7314941954812133, "grad_norm": 1.7950888872146606, "learning_rate": 0.00018889358067511968, "loss": 0.6361253738403321, "step": 123060 }, { "epoch": 0.7315536375578817, "grad_norm": 1.4825212955474854, "learning_rate": 0.0001888905849517125, "loss": 0.6874761581420898, "step": 123070 }, { "epoch": 0.7316130796345501, "grad_norm": 1.5396356582641602, "learning_rate": 0.0001888875888509185, "loss": 0.6223591804504395, "step": 123080 }, { "epoch": 0.7316725217112185, "grad_norm": 1.3030400276184082, "learning_rate": 0.00018888459237275204, "loss": 0.5920719146728516, "step": 123090 }, { "epoch": 0.7317319637878869, "grad_norm": 1.438798189163208, "learning_rate": 0.00018888159551722747, "loss": 0.6688692569732666, "step": 123100 }, { "epoch": 0.7317914058645553, "grad_norm": 1.6108475923538208, "learning_rate": 0.00018887859828435914, "loss": 0.6237815856933594, "step": 123110 }, { "epoch": 0.7318508479412237, "grad_norm": 1.2529593706130981, "learning_rate": 0.00018887560067416137, "loss": 0.6494842529296875, "step": 123120 }, { "epoch": 0.7319102900178921, "grad_norm": 1.763012170791626, "learning_rate": 0.00018887260268664853, "loss": 0.6778359413146973, "step": 123130 }, { "epoch": 0.7319697320945605, "grad_norm": 2.1545462608337402, "learning_rate": 0.00018886960432183488, "loss": 0.6945279121398926, "step": 123140 }, { "epoch": 0.7320291741712288, "grad_norm": 1.3912631273269653, "learning_rate": 0.00018886660557973487, "loss": 0.5718727111816406, "step": 123150 }, { "epoch": 0.7320886162478972, "grad_norm": 1.6445540189743042, "learning_rate": 0.00018886360646036277, "loss": 0.6911612510681152, "step": 123160 }, { "epoch": 0.7321480583245656, "grad_norm": 1.7149289846420288, "learning_rate": 0.00018886060696373297, "loss": 0.6927626132965088, "step": 123170 }, { "epoch": 0.7322075004012341, "grad_norm": 1.4484893083572388, "learning_rate": 0.00018885760708985979, "loss": 0.6847242832183837, "step": 123180 }, { "epoch": 0.7322669424779024, "grad_norm": 2.535003662109375, "learning_rate": 0.00018885460683875754, "loss": 0.6962810516357422, "step": 123190 }, { "epoch": 0.7323263845545708, "grad_norm": 1.5887097120285034, "learning_rate": 0.00018885160621044068, "loss": 0.6675033569335938, "step": 123200 }, { "epoch": 0.7323858266312392, "grad_norm": 1.5660277605056763, "learning_rate": 0.00018884860520492348, "loss": 0.6103440284729004, "step": 123210 }, { "epoch": 0.7324452687079076, "grad_norm": 1.7727831602096558, "learning_rate": 0.00018884560382222035, "loss": 0.6202051162719726, "step": 123220 }, { "epoch": 0.732504710784576, "grad_norm": 1.451753854751587, "learning_rate": 0.00018884260206234555, "loss": 0.728909969329834, "step": 123230 }, { "epoch": 0.7325641528612443, "grad_norm": 1.7479208707809448, "learning_rate": 0.00018883959992531358, "loss": 0.6745311737060546, "step": 123240 }, { "epoch": 0.7326235949379127, "grad_norm": 1.7248204946517944, "learning_rate": 0.00018883659741113869, "loss": 0.6865321636199951, "step": 123250 }, { "epoch": 0.7326830370145812, "grad_norm": 1.884433627128601, "learning_rate": 0.00018883359451983528, "loss": 0.6033006191253663, "step": 123260 }, { "epoch": 0.7327424790912496, "grad_norm": 1.6771303415298462, "learning_rate": 0.00018883059125141775, "loss": 0.6290281295776368, "step": 123270 }, { "epoch": 0.7328019211679179, "grad_norm": 1.6915010213851929, "learning_rate": 0.0001888275876059004, "loss": 0.6573557376861572, "step": 123280 }, { "epoch": 0.7328613632445863, "grad_norm": 1.669171690940857, "learning_rate": 0.00018882458358329766, "loss": 0.6527079582214356, "step": 123290 }, { "epoch": 0.7329208053212547, "grad_norm": 1.5093573331832886, "learning_rate": 0.00018882157918362387, "loss": 0.6237039566040039, "step": 123300 }, { "epoch": 0.7329802473979231, "grad_norm": 1.7936687469482422, "learning_rate": 0.00018881857440689338, "loss": 0.6763510227203369, "step": 123310 }, { "epoch": 0.7330396894745915, "grad_norm": 1.9913525581359863, "learning_rate": 0.0001888155692531206, "loss": 0.6687322616577148, "step": 123320 }, { "epoch": 0.7330991315512598, "grad_norm": 1.596989393234253, "learning_rate": 0.0001888125637223199, "loss": 0.6626592636108398, "step": 123330 }, { "epoch": 0.7331585736279282, "grad_norm": 2.1083250045776367, "learning_rate": 0.00018880955781450565, "loss": 0.6339253425598145, "step": 123340 }, { "epoch": 0.7332180157045967, "grad_norm": 1.8517194986343384, "learning_rate": 0.00018880655152969222, "loss": 0.6553783416748047, "step": 123350 }, { "epoch": 0.7332774577812651, "grad_norm": 1.507171392440796, "learning_rate": 0.000188803544867894, "loss": 0.649187421798706, "step": 123360 }, { "epoch": 0.7333368998579335, "grad_norm": 1.6650491952896118, "learning_rate": 0.00018880053782912537, "loss": 0.6505935668945313, "step": 123370 }, { "epoch": 0.7333963419346018, "grad_norm": 1.7504241466522217, "learning_rate": 0.00018879753041340074, "loss": 0.6820592403411865, "step": 123380 }, { "epoch": 0.7334557840112702, "grad_norm": 1.4872761964797974, "learning_rate": 0.00018879452262073447, "loss": 0.6818696975708007, "step": 123390 }, { "epoch": 0.7335152260879386, "grad_norm": 1.5638266801834106, "learning_rate": 0.00018879151445114095, "loss": 0.6585581779479981, "step": 123400 }, { "epoch": 0.733574668164607, "grad_norm": 1.5132476091384888, "learning_rate": 0.00018878850590463457, "loss": 0.682218074798584, "step": 123410 }, { "epoch": 0.7336341102412753, "grad_norm": 1.8473889827728271, "learning_rate": 0.00018878549698122973, "loss": 0.7463756561279297, "step": 123420 }, { "epoch": 0.7336935523179438, "grad_norm": 1.433159589767456, "learning_rate": 0.00018878248768094082, "loss": 0.6155736923217774, "step": 123430 }, { "epoch": 0.7337529943946122, "grad_norm": 1.6659997701644897, "learning_rate": 0.00018877947800378226, "loss": 0.6750919342041015, "step": 123440 }, { "epoch": 0.7338124364712806, "grad_norm": 1.5439645051956177, "learning_rate": 0.0001887764679497684, "loss": 0.6514153957366944, "step": 123450 }, { "epoch": 0.733871878547949, "grad_norm": 1.646916389465332, "learning_rate": 0.00018877345751891364, "loss": 0.6464437961578369, "step": 123460 }, { "epoch": 0.7339313206246173, "grad_norm": 1.6274293661117554, "learning_rate": 0.00018877044671123243, "loss": 0.6665688514709472, "step": 123470 }, { "epoch": 0.7339907627012857, "grad_norm": 1.5905362367630005, "learning_rate": 0.00018876743552673913, "loss": 0.7035280704498291, "step": 123480 }, { "epoch": 0.7340502047779541, "grad_norm": 2.0471839904785156, "learning_rate": 0.00018876442396544818, "loss": 0.6601826667785644, "step": 123490 }, { "epoch": 0.7341096468546225, "grad_norm": 2.030043840408325, "learning_rate": 0.000188761412027374, "loss": 0.6560354709625245, "step": 123500 }, { "epoch": 0.734169088931291, "grad_norm": 1.3524320125579834, "learning_rate": 0.0001887583997125309, "loss": 0.6141066551208496, "step": 123510 }, { "epoch": 0.7342285310079593, "grad_norm": 1.1889358758926392, "learning_rate": 0.00018875538702093337, "loss": 0.6986627578735352, "step": 123520 }, { "epoch": 0.7342879730846277, "grad_norm": 2.0491297245025635, "learning_rate": 0.0001887523739525958, "loss": 0.6653034210205078, "step": 123530 }, { "epoch": 0.7343474151612961, "grad_norm": 1.6680140495300293, "learning_rate": 0.00018874936050753262, "loss": 0.655883502960205, "step": 123540 }, { "epoch": 0.7344068572379645, "grad_norm": 2.393913745880127, "learning_rate": 0.00018874634668575822, "loss": 0.6556116104125976, "step": 123550 }, { "epoch": 0.7344662993146328, "grad_norm": 1.2527748346328735, "learning_rate": 0.00018874333248728706, "loss": 0.6730812072753907, "step": 123560 }, { "epoch": 0.7345257413913012, "grad_norm": 1.4701875448226929, "learning_rate": 0.0001887403179121335, "loss": 0.5985617160797119, "step": 123570 }, { "epoch": 0.7345851834679696, "grad_norm": 2.034543037414551, "learning_rate": 0.00018873730296031205, "loss": 0.6603203296661377, "step": 123580 }, { "epoch": 0.734644625544638, "grad_norm": 1.387157917022705, "learning_rate": 0.000188734287631837, "loss": 0.6130764961242676, "step": 123590 }, { "epoch": 0.7347040676213065, "grad_norm": 1.8092941045761108, "learning_rate": 0.0001887312719267229, "loss": 0.7165326595306396, "step": 123600 }, { "epoch": 0.7347635096979748, "grad_norm": 1.6829183101654053, "learning_rate": 0.0001887282558449841, "loss": 0.6976371765136719, "step": 123610 }, { "epoch": 0.7348229517746432, "grad_norm": 1.7038578987121582, "learning_rate": 0.0001887252393866351, "loss": 0.6333195686340332, "step": 123620 }, { "epoch": 0.7348823938513116, "grad_norm": 1.574381709098816, "learning_rate": 0.00018872222255169024, "loss": 0.6404155731201172, "step": 123630 }, { "epoch": 0.73494183592798, "grad_norm": 1.527830719947815, "learning_rate": 0.00018871920534016396, "loss": 0.7075587749481201, "step": 123640 }, { "epoch": 0.7350012780046483, "grad_norm": 1.9283980131149292, "learning_rate": 0.0001887161877520708, "loss": 0.6862510681152344, "step": 123650 }, { "epoch": 0.7350607200813167, "grad_norm": 1.5872666835784912, "learning_rate": 0.00018871316978742503, "loss": 0.627599048614502, "step": 123660 }, { "epoch": 0.7351201621579851, "grad_norm": 1.2974810600280762, "learning_rate": 0.00018871015144624124, "loss": 0.7210841178894043, "step": 123670 }, { "epoch": 0.7351796042346536, "grad_norm": 1.7268640995025635, "learning_rate": 0.00018870713272853382, "loss": 0.6741178512573243, "step": 123680 }, { "epoch": 0.735239046311322, "grad_norm": 1.5304250717163086, "learning_rate": 0.0001887041136343172, "loss": 0.6681292533874512, "step": 123690 }, { "epoch": 0.7352984883879903, "grad_norm": 1.4293240308761597, "learning_rate": 0.0001887010941636058, "loss": 0.7073121070861816, "step": 123700 }, { "epoch": 0.7353579304646587, "grad_norm": 1.8988038301467896, "learning_rate": 0.00018869807431641408, "loss": 0.6758220672607422, "step": 123710 }, { "epoch": 0.7354173725413271, "grad_norm": 1.9188778400421143, "learning_rate": 0.00018869505409275651, "loss": 0.6765114784240722, "step": 123720 }, { "epoch": 0.7354768146179955, "grad_norm": 1.9079551696777344, "learning_rate": 0.00018869203349264753, "loss": 0.777553939819336, "step": 123730 }, { "epoch": 0.7355362566946639, "grad_norm": 1.588477373123169, "learning_rate": 0.0001886890125161015, "loss": 0.6955761432647705, "step": 123740 }, { "epoch": 0.7355956987713322, "grad_norm": 1.6574580669403076, "learning_rate": 0.00018868599116313303, "loss": 0.6801522254943848, "step": 123750 }, { "epoch": 0.7356551408480007, "grad_norm": 1.8634127378463745, "learning_rate": 0.0001886829694337565, "loss": 0.631233024597168, "step": 123760 }, { "epoch": 0.7357145829246691, "grad_norm": 2.1317992210388184, "learning_rate": 0.00018867994732798632, "loss": 0.6735447883605957, "step": 123770 }, { "epoch": 0.7357740250013375, "grad_norm": 1.3964744806289673, "learning_rate": 0.000188676924845837, "loss": 0.681171989440918, "step": 123780 }, { "epoch": 0.7358334670780058, "grad_norm": 1.5345814228057861, "learning_rate": 0.00018867390198732298, "loss": 0.6382718563079834, "step": 123790 }, { "epoch": 0.7358929091546742, "grad_norm": 1.8247865438461304, "learning_rate": 0.00018867087875245873, "loss": 0.6613344192504883, "step": 123800 }, { "epoch": 0.7359523512313426, "grad_norm": 1.6003891229629517, "learning_rate": 0.00018866785514125867, "loss": 0.6180564403533936, "step": 123810 }, { "epoch": 0.736011793308011, "grad_norm": 1.7905924320220947, "learning_rate": 0.00018866483115373734, "loss": 0.70069580078125, "step": 123820 }, { "epoch": 0.7360712353846794, "grad_norm": 2.362049102783203, "learning_rate": 0.00018866180678990915, "loss": 0.697087574005127, "step": 123830 }, { "epoch": 0.7361306774613477, "grad_norm": 1.3741281032562256, "learning_rate": 0.00018865878204978858, "loss": 0.5928851127624511, "step": 123840 }, { "epoch": 0.7361901195380162, "grad_norm": 1.9163144826889038, "learning_rate": 0.0001886557569333901, "loss": 0.6861819267272949, "step": 123850 }, { "epoch": 0.7362495616146846, "grad_norm": 1.7432023286819458, "learning_rate": 0.00018865273144072823, "loss": 0.6926650524139404, "step": 123860 }, { "epoch": 0.736309003691353, "grad_norm": 1.8535170555114746, "learning_rate": 0.00018864970557181732, "loss": 0.7056544303894043, "step": 123870 }, { "epoch": 0.7363684457680214, "grad_norm": 1.6638855934143066, "learning_rate": 0.000188646679326672, "loss": 0.6874626159667969, "step": 123880 }, { "epoch": 0.7364278878446897, "grad_norm": 1.6979738473892212, "learning_rate": 0.00018864365270530664, "loss": 0.6431037902832031, "step": 123890 }, { "epoch": 0.7364873299213581, "grad_norm": 1.5477590560913086, "learning_rate": 0.00018864062570773572, "loss": 0.6472994804382324, "step": 123900 }, { "epoch": 0.7365467719980265, "grad_norm": 1.7174512147903442, "learning_rate": 0.00018863759833397377, "loss": 0.6666680812835694, "step": 123910 }, { "epoch": 0.736606214074695, "grad_norm": 1.6130565404891968, "learning_rate": 0.00018863457058403523, "loss": 0.636873722076416, "step": 123920 }, { "epoch": 0.7366656561513633, "grad_norm": 1.7639281749725342, "learning_rate": 0.00018863154245793459, "loss": 0.6374839782714844, "step": 123930 }, { "epoch": 0.7367250982280317, "grad_norm": 1.7443171739578247, "learning_rate": 0.00018862851395568637, "loss": 0.7059367179870606, "step": 123940 }, { "epoch": 0.7367845403047001, "grad_norm": 1.7342051267623901, "learning_rate": 0.00018862548507730506, "loss": 0.6371779441833496, "step": 123950 }, { "epoch": 0.7368439823813685, "grad_norm": 1.7566382884979248, "learning_rate": 0.00018862245582280512, "loss": 0.6651668071746826, "step": 123960 }, { "epoch": 0.7369034244580369, "grad_norm": 1.902848482131958, "learning_rate": 0.000188619426192201, "loss": 0.6586365699768066, "step": 123970 }, { "epoch": 0.7369628665347052, "grad_norm": 1.5847680568695068, "learning_rate": 0.0001886163961855073, "loss": 0.6912463665008545, "step": 123980 }, { "epoch": 0.7370223086113736, "grad_norm": 1.4310131072998047, "learning_rate": 0.0001886133658027384, "loss": 0.6805407047271729, "step": 123990 }, { "epoch": 0.737081750688042, "grad_norm": 1.6955537796020508, "learning_rate": 0.00018861033504390885, "loss": 0.6439695358276367, "step": 124000 }, { "epoch": 0.7371411927647105, "grad_norm": 1.28286874294281, "learning_rate": 0.00018860730390903317, "loss": 0.636977243423462, "step": 124010 }, { "epoch": 0.7372006348413788, "grad_norm": 2.09635591506958, "learning_rate": 0.00018860427239812582, "loss": 0.7244638442993164, "step": 124020 }, { "epoch": 0.7372600769180472, "grad_norm": 1.5603779554367065, "learning_rate": 0.00018860124051120133, "loss": 0.6611831188201904, "step": 124030 }, { "epoch": 0.7373195189947156, "grad_norm": 1.537764549255371, "learning_rate": 0.0001885982082482742, "loss": 0.6686028480529785, "step": 124040 }, { "epoch": 0.737378961071384, "grad_norm": 1.5856958627700806, "learning_rate": 0.00018859517560935893, "loss": 0.6342488765716553, "step": 124050 }, { "epoch": 0.7374384031480524, "grad_norm": 1.424254059791565, "learning_rate": 0.00018859214259447002, "loss": 0.6359325885772705, "step": 124060 }, { "epoch": 0.7374978452247207, "grad_norm": 1.9913678169250488, "learning_rate": 0.000188589109203622, "loss": 0.6866947174072265, "step": 124070 }, { "epoch": 0.7375572873013891, "grad_norm": 1.8795573711395264, "learning_rate": 0.0001885860754368293, "loss": 0.6019095420837403, "step": 124080 }, { "epoch": 0.7376167293780576, "grad_norm": 1.3259035348892212, "learning_rate": 0.00018858304129410657, "loss": 0.6444800853729248, "step": 124090 }, { "epoch": 0.737676171454726, "grad_norm": 2.1085636615753174, "learning_rate": 0.00018858000677546822, "loss": 0.6265278339385987, "step": 124100 }, { "epoch": 0.7377356135313944, "grad_norm": 1.26357901096344, "learning_rate": 0.0001885769718809288, "loss": 0.64332594871521, "step": 124110 }, { "epoch": 0.7377950556080627, "grad_norm": 1.8379400968551636, "learning_rate": 0.00018857393661050284, "loss": 0.6486413955688477, "step": 124120 }, { "epoch": 0.7378544976847311, "grad_norm": 1.919419765472412, "learning_rate": 0.00018857090096420482, "loss": 0.7186031341552734, "step": 124130 }, { "epoch": 0.7379139397613995, "grad_norm": 1.4672620296478271, "learning_rate": 0.00018856786494204932, "loss": 0.6626610279083252, "step": 124140 }, { "epoch": 0.7379733818380679, "grad_norm": 1.7683194875717163, "learning_rate": 0.0001885648285440508, "loss": 0.6497254371643066, "step": 124150 }, { "epoch": 0.7380328239147362, "grad_norm": 1.9978781938552856, "learning_rate": 0.00018856179177022383, "loss": 0.6056457042694092, "step": 124160 }, { "epoch": 0.7380922659914047, "grad_norm": 1.6935724020004272, "learning_rate": 0.0001885587546205829, "loss": 0.6487907409667969, "step": 124170 }, { "epoch": 0.7381517080680731, "grad_norm": 1.7889111042022705, "learning_rate": 0.0001885557170951426, "loss": 0.7045760154724121, "step": 124180 }, { "epoch": 0.7382111501447415, "grad_norm": 1.3584890365600586, "learning_rate": 0.0001885526791939174, "loss": 0.6209333419799805, "step": 124190 }, { "epoch": 0.7382705922214099, "grad_norm": 1.4701517820358276, "learning_rate": 0.00018854964091692187, "loss": 0.6231433868408203, "step": 124200 }, { "epoch": 0.7383300342980782, "grad_norm": 2.164790153503418, "learning_rate": 0.0001885466022641705, "loss": 0.661353874206543, "step": 124210 }, { "epoch": 0.7383894763747466, "grad_norm": 1.5484882593154907, "learning_rate": 0.00018854356323567788, "loss": 0.6397546768188477, "step": 124220 }, { "epoch": 0.738448918451415, "grad_norm": 1.722468614578247, "learning_rate": 0.00018854052383145847, "loss": 0.6652121067047119, "step": 124230 }, { "epoch": 0.7385083605280834, "grad_norm": 1.6118532419204712, "learning_rate": 0.0001885374840515269, "loss": 0.6923304557800293, "step": 124240 }, { "epoch": 0.7385678026047517, "grad_norm": 1.7802093029022217, "learning_rate": 0.0001885344438958977, "loss": 0.678326416015625, "step": 124250 }, { "epoch": 0.7386272446814202, "grad_norm": 1.755786418914795, "learning_rate": 0.00018853140336458536, "loss": 0.6690889358520508, "step": 124260 }, { "epoch": 0.7386866867580886, "grad_norm": 1.8954130411148071, "learning_rate": 0.00018852836245760444, "loss": 0.7051403999328614, "step": 124270 }, { "epoch": 0.738746128834757, "grad_norm": 1.7022215127944946, "learning_rate": 0.0001885253211749695, "loss": 0.5797267436981202, "step": 124280 }, { "epoch": 0.7388055709114254, "grad_norm": 1.848672866821289, "learning_rate": 0.0001885222795166951, "loss": 0.6734467029571534, "step": 124290 }, { "epoch": 0.7388650129880937, "grad_norm": 1.579301357269287, "learning_rate": 0.00018851923748279577, "loss": 0.6768716812133789, "step": 124300 }, { "epoch": 0.7389244550647621, "grad_norm": 1.667021632194519, "learning_rate": 0.0001885161950732861, "loss": 0.6520707607269287, "step": 124310 }, { "epoch": 0.7389838971414305, "grad_norm": 2.543454170227051, "learning_rate": 0.00018851315228818056, "loss": 0.6621166229248047, "step": 124320 }, { "epoch": 0.739043339218099, "grad_norm": 1.8169128894805908, "learning_rate": 0.0001885101091274938, "loss": 0.683541202545166, "step": 124330 }, { "epoch": 0.7391027812947674, "grad_norm": 1.5763646364212036, "learning_rate": 0.0001885070655912403, "loss": 0.6606556415557862, "step": 124340 }, { "epoch": 0.7391622233714357, "grad_norm": 1.4903159141540527, "learning_rate": 0.00018850402167943465, "loss": 0.645181941986084, "step": 124350 }, { "epoch": 0.7392216654481041, "grad_norm": 1.6399915218353271, "learning_rate": 0.00018850097739209142, "loss": 0.6636532783508301, "step": 124360 }, { "epoch": 0.7392811075247725, "grad_norm": 1.8543835878372192, "learning_rate": 0.0001884979327292252, "loss": 0.662868070602417, "step": 124370 }, { "epoch": 0.7393405496014409, "grad_norm": 1.4262827634811401, "learning_rate": 0.0001884948876908505, "loss": 0.6166396141052246, "step": 124380 }, { "epoch": 0.7393999916781092, "grad_norm": 1.2765965461730957, "learning_rate": 0.0001884918422769819, "loss": 0.6513703823089599, "step": 124390 }, { "epoch": 0.7394594337547776, "grad_norm": 1.8403512239456177, "learning_rate": 0.00018848879648763401, "loss": 0.6865208625793457, "step": 124400 }, { "epoch": 0.739518875831446, "grad_norm": 1.4120254516601562, "learning_rate": 0.00018848575032282135, "loss": 0.6091759681701661, "step": 124410 }, { "epoch": 0.7395783179081145, "grad_norm": 1.4341404438018799, "learning_rate": 0.00018848270378255853, "loss": 0.6238391876220704, "step": 124420 }, { "epoch": 0.7396377599847829, "grad_norm": 1.7368501424789429, "learning_rate": 0.00018847965686686005, "loss": 0.7116778373718262, "step": 124430 }, { "epoch": 0.7396972020614512, "grad_norm": 1.6394039392471313, "learning_rate": 0.0001884766095757406, "loss": 0.7004767417907715, "step": 124440 }, { "epoch": 0.7397566441381196, "grad_norm": 1.6597095727920532, "learning_rate": 0.00018847356190921467, "loss": 0.6827820777893067, "step": 124450 }, { "epoch": 0.739816086214788, "grad_norm": 1.8594743013381958, "learning_rate": 0.00018847051386729685, "loss": 0.7134106636047364, "step": 124460 }, { "epoch": 0.7398755282914564, "grad_norm": 1.0618318319320679, "learning_rate": 0.00018846746545000175, "loss": 0.6693188190460205, "step": 124470 }, { "epoch": 0.7399349703681248, "grad_norm": 1.4298839569091797, "learning_rate": 0.00018846441665734397, "loss": 0.6262913703918457, "step": 124480 }, { "epoch": 0.7399944124447931, "grad_norm": 1.552390217781067, "learning_rate": 0.00018846136748933802, "loss": 0.6669693470001221, "step": 124490 }, { "epoch": 0.7400538545214616, "grad_norm": 1.6028449535369873, "learning_rate": 0.00018845831794599854, "loss": 0.6455793380737305, "step": 124500 }, { "epoch": 0.74011329659813, "grad_norm": 1.704626202583313, "learning_rate": 0.00018845526802734012, "loss": 0.6363136291503906, "step": 124510 }, { "epoch": 0.7401727386747984, "grad_norm": 1.8867908716201782, "learning_rate": 0.0001884522177333773, "loss": 0.7281001567840576, "step": 124520 }, { "epoch": 0.7402321807514667, "grad_norm": 1.8564249277114868, "learning_rate": 0.00018844916706412475, "loss": 0.6801998138427734, "step": 124530 }, { "epoch": 0.7402916228281351, "grad_norm": 1.410709023475647, "learning_rate": 0.000188446116019597, "loss": 0.6657087802886963, "step": 124540 }, { "epoch": 0.7403510649048035, "grad_norm": 1.6152327060699463, "learning_rate": 0.00018844306459980868, "loss": 0.7141735553741455, "step": 124550 }, { "epoch": 0.7404105069814719, "grad_norm": 1.6650184392929077, "learning_rate": 0.00018844001280477436, "loss": 0.6413445472717285, "step": 124560 }, { "epoch": 0.7404699490581403, "grad_norm": 1.31885826587677, "learning_rate": 0.00018843696063450868, "loss": 0.6170021533966065, "step": 124570 }, { "epoch": 0.7405293911348086, "grad_norm": 1.7781562805175781, "learning_rate": 0.00018843390808902618, "loss": 0.7255471706390381, "step": 124580 }, { "epoch": 0.7405888332114771, "grad_norm": 1.5635221004486084, "learning_rate": 0.00018843085516834153, "loss": 0.6701706886291504, "step": 124590 }, { "epoch": 0.7406482752881455, "grad_norm": 1.73454749584198, "learning_rate": 0.00018842780187246927, "loss": 0.634829330444336, "step": 124600 }, { "epoch": 0.7407077173648139, "grad_norm": 2.2651572227478027, "learning_rate": 0.00018842474820142405, "loss": 0.6886768817901612, "step": 124610 }, { "epoch": 0.7407671594414822, "grad_norm": 1.3910915851593018, "learning_rate": 0.00018842169415522048, "loss": 0.6095232009887696, "step": 124620 }, { "epoch": 0.7408266015181506, "grad_norm": 1.2244560718536377, "learning_rate": 0.00018841863973387312, "loss": 0.605256986618042, "step": 124630 }, { "epoch": 0.740886043594819, "grad_norm": 2.0636770725250244, "learning_rate": 0.00018841558493739663, "loss": 0.7114502429962158, "step": 124640 }, { "epoch": 0.7409454856714874, "grad_norm": 1.9998620748519897, "learning_rate": 0.0001884125297658056, "loss": 0.7012054443359375, "step": 124650 }, { "epoch": 0.7410049277481559, "grad_norm": 1.733264446258545, "learning_rate": 0.0001884094742191147, "loss": 0.6410954475402832, "step": 124660 }, { "epoch": 0.7410643698248242, "grad_norm": 1.8820902109146118, "learning_rate": 0.00018840641829733846, "loss": 0.7154009819030762, "step": 124670 }, { "epoch": 0.7411238119014926, "grad_norm": 1.6397825479507446, "learning_rate": 0.0001884033620004915, "loss": 0.6339428901672364, "step": 124680 }, { "epoch": 0.741183253978161, "grad_norm": 1.9876590967178345, "learning_rate": 0.00018840030532858856, "loss": 0.6905983448028564, "step": 124690 }, { "epoch": 0.7412426960548294, "grad_norm": 1.7327505350112915, "learning_rate": 0.00018839724828164414, "loss": 0.6580986976623535, "step": 124700 }, { "epoch": 0.7413021381314978, "grad_norm": 1.7667386531829834, "learning_rate": 0.0001883941908596729, "loss": 0.6318785667419433, "step": 124710 }, { "epoch": 0.7413615802081661, "grad_norm": 1.7384772300720215, "learning_rate": 0.00018839113306268947, "loss": 0.6924448490142823, "step": 124720 }, { "epoch": 0.7414210222848345, "grad_norm": 1.5024611949920654, "learning_rate": 0.0001883880748907085, "loss": 0.6936661720275878, "step": 124730 }, { "epoch": 0.7414804643615029, "grad_norm": 1.8952373266220093, "learning_rate": 0.00018838501634374456, "loss": 0.6752228736877441, "step": 124740 }, { "epoch": 0.7415399064381714, "grad_norm": 2.196246862411499, "learning_rate": 0.00018838195742181235, "loss": 0.6795123100280762, "step": 124750 }, { "epoch": 0.7415993485148397, "grad_norm": 1.789902687072754, "learning_rate": 0.00018837889812492646, "loss": 0.6921270370483399, "step": 124760 }, { "epoch": 0.7416587905915081, "grad_norm": 2.2300541400909424, "learning_rate": 0.00018837583845310153, "loss": 0.6572494506835938, "step": 124770 }, { "epoch": 0.7417182326681765, "grad_norm": 1.6320844888687134, "learning_rate": 0.00018837277840635222, "loss": 0.6691120147705079, "step": 124780 }, { "epoch": 0.7417776747448449, "grad_norm": 1.964971661567688, "learning_rate": 0.00018836971798469313, "loss": 0.6696040153503418, "step": 124790 }, { "epoch": 0.7418371168215133, "grad_norm": 2.165740728378296, "learning_rate": 0.00018836665718813893, "loss": 0.6872154235839844, "step": 124800 }, { "epoch": 0.7418965588981816, "grad_norm": 1.6376065015792847, "learning_rate": 0.00018836359601670426, "loss": 0.6659875869750976, "step": 124810 }, { "epoch": 0.74195600097485, "grad_norm": 1.7253919839859009, "learning_rate": 0.00018836053447040375, "loss": 0.6730888366699219, "step": 124820 }, { "epoch": 0.7420154430515185, "grad_norm": 1.4788910150527954, "learning_rate": 0.00018835747254925203, "loss": 0.6210894107818603, "step": 124830 }, { "epoch": 0.7420748851281869, "grad_norm": 1.6721347570419312, "learning_rate": 0.00018835441025326382, "loss": 0.6675856590270997, "step": 124840 }, { "epoch": 0.7421343272048553, "grad_norm": 1.4525943994522095, "learning_rate": 0.00018835134758245366, "loss": 0.599896240234375, "step": 124850 }, { "epoch": 0.7421937692815236, "grad_norm": 1.4164470434188843, "learning_rate": 0.0001883482845368363, "loss": 0.7135817527770996, "step": 124860 }, { "epoch": 0.742253211358192, "grad_norm": 1.5102211236953735, "learning_rate": 0.00018834522111642633, "loss": 0.6830059051513672, "step": 124870 }, { "epoch": 0.7423126534348604, "grad_norm": 1.564679741859436, "learning_rate": 0.00018834215732123845, "loss": 0.6804312229156494, "step": 124880 }, { "epoch": 0.7423720955115288, "grad_norm": 1.4902493953704834, "learning_rate": 0.0001883390931512873, "loss": 0.6667149066925049, "step": 124890 }, { "epoch": 0.7424315375881971, "grad_norm": 1.5434021949768066, "learning_rate": 0.00018833602860658747, "loss": 0.6919914722442627, "step": 124900 }, { "epoch": 0.7424909796648655, "grad_norm": 1.7005351781845093, "learning_rate": 0.00018833296368715372, "loss": 0.7149827957153321, "step": 124910 }, { "epoch": 0.742550421741534, "grad_norm": 1.5821411609649658, "learning_rate": 0.00018832989839300066, "loss": 0.6517179012298584, "step": 124920 }, { "epoch": 0.7426098638182024, "grad_norm": 1.9117670059204102, "learning_rate": 0.000188326832724143, "loss": 0.7028151988983155, "step": 124930 }, { "epoch": 0.7426693058948708, "grad_norm": 1.7715774774551392, "learning_rate": 0.00018832376668059532, "loss": 0.6741853713989258, "step": 124940 }, { "epoch": 0.7427287479715391, "grad_norm": 1.4195517301559448, "learning_rate": 0.00018832070026237235, "loss": 0.6712079524993897, "step": 124950 }, { "epoch": 0.7427881900482075, "grad_norm": 1.6848024129867554, "learning_rate": 0.00018831763346948877, "loss": 0.6627854347229004, "step": 124960 }, { "epoch": 0.7428476321248759, "grad_norm": 2.0608456134796143, "learning_rate": 0.0001883145663019592, "loss": 0.6565941333770752, "step": 124970 }, { "epoch": 0.7429070742015443, "grad_norm": 1.6282142400741577, "learning_rate": 0.00018831149875979833, "loss": 0.685276460647583, "step": 124980 }, { "epoch": 0.7429665162782126, "grad_norm": 1.3594402074813843, "learning_rate": 0.0001883084308430209, "loss": 0.6291186332702636, "step": 124990 }, { "epoch": 0.743025958354881, "grad_norm": 1.6057549715042114, "learning_rate": 0.00018830536255164145, "loss": 0.6789119720458985, "step": 125000 }, { "epoch": 0.7430854004315495, "grad_norm": 1.630130648612976, "learning_rate": 0.0001883022938856748, "loss": 0.5505605697631836, "step": 125010 }, { "epoch": 0.7431448425082179, "grad_norm": 1.501042366027832, "learning_rate": 0.00018829922484513552, "loss": 0.7047254562377929, "step": 125020 }, { "epoch": 0.7432042845848863, "grad_norm": 1.696760654449463, "learning_rate": 0.00018829615543003835, "loss": 0.6354330062866211, "step": 125030 }, { "epoch": 0.7432637266615546, "grad_norm": 1.2496089935302734, "learning_rate": 0.00018829308564039795, "loss": 0.6562793731689454, "step": 125040 }, { "epoch": 0.743323168738223, "grad_norm": 1.4205811023712158, "learning_rate": 0.00018829001547622905, "loss": 0.6293792724609375, "step": 125050 }, { "epoch": 0.7433826108148914, "grad_norm": 1.4907902479171753, "learning_rate": 0.0001882869449375463, "loss": 0.6602575778961182, "step": 125060 }, { "epoch": 0.7434420528915598, "grad_norm": 1.8617424964904785, "learning_rate": 0.00018828387402436436, "loss": 0.6807267189025878, "step": 125070 }, { "epoch": 0.7435014949682283, "grad_norm": 1.6784157752990723, "learning_rate": 0.00018828080273669798, "loss": 0.7065571784973145, "step": 125080 }, { "epoch": 0.7435609370448966, "grad_norm": 1.6156880855560303, "learning_rate": 0.00018827773107456177, "loss": 0.6547002792358398, "step": 125090 }, { "epoch": 0.743620379121565, "grad_norm": 1.9888463020324707, "learning_rate": 0.0001882746590379705, "loss": 0.678466510772705, "step": 125100 }, { "epoch": 0.7436798211982334, "grad_norm": 1.8264044523239136, "learning_rate": 0.00018827158662693887, "loss": 0.7291687965393067, "step": 125110 }, { "epoch": 0.7437392632749018, "grad_norm": 1.8952652215957642, "learning_rate": 0.00018826851384148155, "loss": 0.6434932231903077, "step": 125120 }, { "epoch": 0.7437987053515701, "grad_norm": 1.4473289251327515, "learning_rate": 0.00018826544068161318, "loss": 0.6200924873352051, "step": 125130 }, { "epoch": 0.7438581474282385, "grad_norm": 1.6258689165115356, "learning_rate": 0.00018826236714734857, "loss": 0.6380822658538818, "step": 125140 }, { "epoch": 0.7439175895049069, "grad_norm": 1.44536292552948, "learning_rate": 0.00018825929323870236, "loss": 0.6584902763366699, "step": 125150 }, { "epoch": 0.7439770315815754, "grad_norm": 2.122720956802368, "learning_rate": 0.00018825621895568928, "loss": 0.6520269393920899, "step": 125160 }, { "epoch": 0.7440364736582438, "grad_norm": 1.7800379991531372, "learning_rate": 0.00018825314429832398, "loss": 0.6872182846069336, "step": 125170 }, { "epoch": 0.7440959157349121, "grad_norm": 1.6578439474105835, "learning_rate": 0.00018825006926662127, "loss": 0.7095887184143066, "step": 125180 }, { "epoch": 0.7441553578115805, "grad_norm": 1.568927526473999, "learning_rate": 0.00018824699386059578, "loss": 0.6838493347167969, "step": 125190 }, { "epoch": 0.7442147998882489, "grad_norm": 2.020045280456543, "learning_rate": 0.00018824391808026222, "loss": 0.6607991218566894, "step": 125200 }, { "epoch": 0.7442742419649173, "grad_norm": 1.317639946937561, "learning_rate": 0.00018824084192563536, "loss": 0.6176743507385254, "step": 125210 }, { "epoch": 0.7443336840415857, "grad_norm": 1.595255970954895, "learning_rate": 0.00018823776539672984, "loss": 0.6701350212097168, "step": 125220 }, { "epoch": 0.744393126118254, "grad_norm": 1.8385478258132935, "learning_rate": 0.00018823468849356044, "loss": 0.6709372997283936, "step": 125230 }, { "epoch": 0.7444525681949224, "grad_norm": 1.5128114223480225, "learning_rate": 0.00018823161121614185, "loss": 0.7155048370361328, "step": 125240 }, { "epoch": 0.7445120102715909, "grad_norm": 2.1208746433258057, "learning_rate": 0.00018822853356448882, "loss": 0.7289384841918946, "step": 125250 }, { "epoch": 0.7445714523482593, "grad_norm": 1.7239311933517456, "learning_rate": 0.00018822545553861603, "loss": 0.5915418148040772, "step": 125260 }, { "epoch": 0.7446308944249276, "grad_norm": 1.9778523445129395, "learning_rate": 0.00018822237713853824, "loss": 0.7409860610961914, "step": 125270 }, { "epoch": 0.744690336501596, "grad_norm": 1.3139796257019043, "learning_rate": 0.00018821929836427013, "loss": 0.5753745555877685, "step": 125280 }, { "epoch": 0.7447497785782644, "grad_norm": 1.6996809244155884, "learning_rate": 0.00018821621921582654, "loss": 0.6832052230834961, "step": 125290 }, { "epoch": 0.7448092206549328, "grad_norm": 1.7973206043243408, "learning_rate": 0.00018821313969322203, "loss": 0.6816575050354003, "step": 125300 }, { "epoch": 0.7448686627316012, "grad_norm": 1.6145563125610352, "learning_rate": 0.00018821005979647145, "loss": 0.6255792617797852, "step": 125310 }, { "epoch": 0.7449281048082695, "grad_norm": 1.6301039457321167, "learning_rate": 0.0001882069795255895, "loss": 0.6792452812194825, "step": 125320 }, { "epoch": 0.744987546884938, "grad_norm": 1.6111136674880981, "learning_rate": 0.00018820389888059093, "loss": 0.5779820442199707, "step": 125330 }, { "epoch": 0.7450469889616064, "grad_norm": 1.4646106958389282, "learning_rate": 0.00018820081786149047, "loss": 0.6246084690093994, "step": 125340 }, { "epoch": 0.7451064310382748, "grad_norm": 1.3889684677124023, "learning_rate": 0.00018819773646830282, "loss": 0.6733310699462891, "step": 125350 }, { "epoch": 0.7451658731149431, "grad_norm": 1.3966697454452515, "learning_rate": 0.0001881946547010428, "loss": 0.6147092819213867, "step": 125360 }, { "epoch": 0.7452253151916115, "grad_norm": 1.5259202718734741, "learning_rate": 0.00018819157255972507, "loss": 0.6167088508605957, "step": 125370 }, { "epoch": 0.7452847572682799, "grad_norm": 1.2641009092330933, "learning_rate": 0.0001881884900443644, "loss": 0.6621110439300537, "step": 125380 }, { "epoch": 0.7453441993449483, "grad_norm": 1.486743688583374, "learning_rate": 0.0001881854071549756, "loss": 0.6929615497589111, "step": 125390 }, { "epoch": 0.7454036414216167, "grad_norm": 1.718366026878357, "learning_rate": 0.00018818232389157332, "loss": 0.6979652404785156, "step": 125400 }, { "epoch": 0.745463083498285, "grad_norm": 1.9557679891586304, "learning_rate": 0.00018817924025417234, "loss": 0.7272649765014648, "step": 125410 }, { "epoch": 0.7455225255749535, "grad_norm": 1.4983237981796265, "learning_rate": 0.00018817615624278748, "loss": 0.6250108242034912, "step": 125420 }, { "epoch": 0.7455819676516219, "grad_norm": 1.543800950050354, "learning_rate": 0.0001881730718574334, "loss": 0.7286933898925781, "step": 125430 }, { "epoch": 0.7456414097282903, "grad_norm": 7.150722026824951, "learning_rate": 0.00018816998709812488, "loss": 0.6487319946289063, "step": 125440 }, { "epoch": 0.7457008518049587, "grad_norm": 1.7212369441986084, "learning_rate": 0.00018816690196487673, "loss": 0.6601967811584473, "step": 125450 }, { "epoch": 0.745760293881627, "grad_norm": 1.5807632207870483, "learning_rate": 0.00018816381645770362, "loss": 0.7073452472686768, "step": 125460 }, { "epoch": 0.7458197359582954, "grad_norm": 1.448943018913269, "learning_rate": 0.00018816073057662037, "loss": 0.6355763912200928, "step": 125470 }, { "epoch": 0.7458791780349638, "grad_norm": 1.271541953086853, "learning_rate": 0.00018815764432164177, "loss": 0.6559081554412842, "step": 125480 }, { "epoch": 0.7459386201116323, "grad_norm": 1.7637426853179932, "learning_rate": 0.0001881545576927825, "loss": 0.6891785621643066, "step": 125490 }, { "epoch": 0.7459980621883006, "grad_norm": 1.4649218320846558, "learning_rate": 0.00018815147069005736, "loss": 0.6788475036621093, "step": 125500 }, { "epoch": 0.746057504264969, "grad_norm": 1.3815369606018066, "learning_rate": 0.00018814838331348115, "loss": 0.7242630958557129, "step": 125510 }, { "epoch": 0.7461169463416374, "grad_norm": 1.5174293518066406, "learning_rate": 0.0001881452955630686, "loss": 0.7071861267089844, "step": 125520 }, { "epoch": 0.7461763884183058, "grad_norm": 1.903544306755066, "learning_rate": 0.00018814220743883448, "loss": 0.7085615158081054, "step": 125530 }, { "epoch": 0.7462358304949742, "grad_norm": 1.7212891578674316, "learning_rate": 0.0001881391189407936, "loss": 0.7077443122863769, "step": 125540 }, { "epoch": 0.7462952725716425, "grad_norm": 1.638028860092163, "learning_rate": 0.0001881360300689607, "loss": 0.6490634441375732, "step": 125550 }, { "epoch": 0.7463547146483109, "grad_norm": 1.7341911792755127, "learning_rate": 0.00018813294082335058, "loss": 0.6654795646667481, "step": 125560 }, { "epoch": 0.7464141567249793, "grad_norm": 1.6676374673843384, "learning_rate": 0.000188129851203978, "loss": 0.6300467014312744, "step": 125570 }, { "epoch": 0.7464735988016478, "grad_norm": 1.567789077758789, "learning_rate": 0.00018812676121085774, "loss": 0.6694323539733886, "step": 125580 }, { "epoch": 0.7465330408783162, "grad_norm": 1.5084450244903564, "learning_rate": 0.00018812367084400456, "loss": 0.674161148071289, "step": 125590 }, { "epoch": 0.7465924829549845, "grad_norm": 1.5055347681045532, "learning_rate": 0.00018812058010343332, "loss": 0.5829768180847168, "step": 125600 }, { "epoch": 0.7466519250316529, "grad_norm": 1.9676257371902466, "learning_rate": 0.00018811748898915875, "loss": 0.6792878150939942, "step": 125610 }, { "epoch": 0.7467113671083213, "grad_norm": 1.5283327102661133, "learning_rate": 0.00018811439750119558, "loss": 0.7238380908966064, "step": 125620 }, { "epoch": 0.7467708091849897, "grad_norm": 2.2255403995513916, "learning_rate": 0.00018811130563955872, "loss": 0.7510456562042236, "step": 125630 }, { "epoch": 0.746830251261658, "grad_norm": 1.7761776447296143, "learning_rate": 0.0001881082134042629, "loss": 0.6617108345031738, "step": 125640 }, { "epoch": 0.7468896933383264, "grad_norm": 1.4359328746795654, "learning_rate": 0.0001881051207953229, "loss": 0.6443176746368409, "step": 125650 }, { "epoch": 0.7469491354149949, "grad_norm": 1.5664942264556885, "learning_rate": 0.00018810202781275353, "loss": 0.699046516418457, "step": 125660 }, { "epoch": 0.7470085774916633, "grad_norm": 1.6855353116989136, "learning_rate": 0.0001880989344565696, "loss": 0.6396282196044922, "step": 125670 }, { "epoch": 0.7470680195683317, "grad_norm": 1.4936606884002686, "learning_rate": 0.00018809584072678584, "loss": 0.6100082397460938, "step": 125680 }, { "epoch": 0.747127461645, "grad_norm": 1.7087751626968384, "learning_rate": 0.00018809274662341712, "loss": 0.676171350479126, "step": 125690 }, { "epoch": 0.7471869037216684, "grad_norm": 1.5152127742767334, "learning_rate": 0.0001880896521464782, "loss": 0.7186129570007325, "step": 125700 }, { "epoch": 0.7472463457983368, "grad_norm": 1.3830411434173584, "learning_rate": 0.00018808655729598398, "loss": 0.6923625946044922, "step": 125710 }, { "epoch": 0.7473057878750052, "grad_norm": 1.6202775239944458, "learning_rate": 0.00018808346207194914, "loss": 0.7534104347229004, "step": 125720 }, { "epoch": 0.7473652299516735, "grad_norm": 1.6572009325027466, "learning_rate": 0.00018808036647438854, "loss": 0.6776689529418946, "step": 125730 }, { "epoch": 0.747424672028342, "grad_norm": 1.7912403345108032, "learning_rate": 0.000188077270503317, "loss": 0.6708386421203614, "step": 125740 }, { "epoch": 0.7474841141050104, "grad_norm": 1.767286777496338, "learning_rate": 0.0001880741741587493, "loss": 0.6607733726501465, "step": 125750 }, { "epoch": 0.7475435561816788, "grad_norm": 1.8134219646453857, "learning_rate": 0.00018807107744070025, "loss": 0.6893245220184326, "step": 125760 }, { "epoch": 0.7476029982583472, "grad_norm": 1.9582316875457764, "learning_rate": 0.00018806798034918469, "loss": 0.612907886505127, "step": 125770 }, { "epoch": 0.7476624403350155, "grad_norm": 1.6656936407089233, "learning_rate": 0.0001880648828842174, "loss": 0.6533790111541748, "step": 125780 }, { "epoch": 0.7477218824116839, "grad_norm": 1.1388942003250122, "learning_rate": 0.00018806178504581327, "loss": 0.637169885635376, "step": 125790 }, { "epoch": 0.7477813244883523, "grad_norm": 1.4722654819488525, "learning_rate": 0.00018805868683398704, "loss": 0.6673240661621094, "step": 125800 }, { "epoch": 0.7478407665650207, "grad_norm": 1.4558618068695068, "learning_rate": 0.00018805558824875357, "loss": 0.6067993640899658, "step": 125810 }, { "epoch": 0.7479002086416892, "grad_norm": 1.9310317039489746, "learning_rate": 0.0001880524892901277, "loss": 0.7078348636627197, "step": 125820 }, { "epoch": 0.7479596507183575, "grad_norm": 1.8426085710525513, "learning_rate": 0.0001880493899581242, "loss": 0.6416191101074219, "step": 125830 }, { "epoch": 0.7480190927950259, "grad_norm": 1.604438304901123, "learning_rate": 0.00018804629025275793, "loss": 0.647727108001709, "step": 125840 }, { "epoch": 0.7480785348716943, "grad_norm": 1.6015130281448364, "learning_rate": 0.0001880431901740437, "loss": 0.6875114440917969, "step": 125850 }, { "epoch": 0.7481379769483627, "grad_norm": 1.5579123497009277, "learning_rate": 0.00018804008972199638, "loss": 0.6558972358703613, "step": 125860 }, { "epoch": 0.748197419025031, "grad_norm": 1.5505752563476562, "learning_rate": 0.00018803698889663075, "loss": 0.692255687713623, "step": 125870 }, { "epoch": 0.7482568611016994, "grad_norm": 2.128945827484131, "learning_rate": 0.00018803388769796168, "loss": 0.7052299976348877, "step": 125880 }, { "epoch": 0.7483163031783678, "grad_norm": 1.7111684083938599, "learning_rate": 0.00018803078612600397, "loss": 0.6560650825500488, "step": 125890 }, { "epoch": 0.7483757452550363, "grad_norm": 1.7663588523864746, "learning_rate": 0.00018802768418077254, "loss": 0.6773534297943116, "step": 125900 }, { "epoch": 0.7484351873317047, "grad_norm": 1.7245326042175293, "learning_rate": 0.00018802458186228214, "loss": 0.6476047039031982, "step": 125910 }, { "epoch": 0.748494629408373, "grad_norm": 1.6152725219726562, "learning_rate": 0.0001880214791705476, "loss": 0.6158576965332031, "step": 125920 }, { "epoch": 0.7485540714850414, "grad_norm": 1.7900302410125732, "learning_rate": 0.00018801837610558383, "loss": 0.667819595336914, "step": 125930 }, { "epoch": 0.7486135135617098, "grad_norm": 1.7471688985824585, "learning_rate": 0.00018801527266740567, "loss": 0.6892923831939697, "step": 125940 }, { "epoch": 0.7486729556383782, "grad_norm": 1.947782278060913, "learning_rate": 0.00018801216885602792, "loss": 0.6920351028442383, "step": 125950 }, { "epoch": 0.7487323977150466, "grad_norm": 1.6589559316635132, "learning_rate": 0.00018800906467146547, "loss": 0.6521448135375977, "step": 125960 }, { "epoch": 0.7487918397917149, "grad_norm": 1.5913130044937134, "learning_rate": 0.00018800596011373308, "loss": 0.6355330467224121, "step": 125970 }, { "epoch": 0.7488512818683833, "grad_norm": 1.7469089031219482, "learning_rate": 0.00018800285518284573, "loss": 0.6891103267669678, "step": 125980 }, { "epoch": 0.7489107239450518, "grad_norm": 1.5734163522720337, "learning_rate": 0.00018799974987881822, "loss": 0.6731768608093261, "step": 125990 }, { "epoch": 0.7489701660217202, "grad_norm": 1.472280740737915, "learning_rate": 0.00018799664420166535, "loss": 0.6733406066894532, "step": 126000 }, { "epoch": 0.7490296080983885, "grad_norm": 1.5111514329910278, "learning_rate": 0.00018799353815140204, "loss": 0.7117503166198731, "step": 126010 }, { "epoch": 0.7490890501750569, "grad_norm": 1.643731951713562, "learning_rate": 0.00018799043172804315, "loss": 0.6691272735595704, "step": 126020 }, { "epoch": 0.7491484922517253, "grad_norm": 2.122701406478882, "learning_rate": 0.00018798732493160352, "loss": 0.6309315204620362, "step": 126030 }, { "epoch": 0.7492079343283937, "grad_norm": 1.7370916604995728, "learning_rate": 0.000187984217762098, "loss": 0.684969425201416, "step": 126040 }, { "epoch": 0.7492673764050621, "grad_norm": 2.1991238594055176, "learning_rate": 0.00018798111021954146, "loss": 0.7141966819763184, "step": 126050 }, { "epoch": 0.7493268184817304, "grad_norm": 1.918710708618164, "learning_rate": 0.0001879780023039488, "loss": 0.6294437408447265, "step": 126060 }, { "epoch": 0.7493862605583989, "grad_norm": 1.2070488929748535, "learning_rate": 0.00018797489401533484, "loss": 0.651715087890625, "step": 126070 }, { "epoch": 0.7494457026350673, "grad_norm": 1.473207712173462, "learning_rate": 0.00018797178535371448, "loss": 0.6517480850219727, "step": 126080 }, { "epoch": 0.7495051447117357, "grad_norm": 1.5890448093414307, "learning_rate": 0.00018796867631910258, "loss": 0.650038194656372, "step": 126090 }, { "epoch": 0.749564586788404, "grad_norm": 1.4506471157073975, "learning_rate": 0.00018796556691151402, "loss": 0.6120617389678955, "step": 126100 }, { "epoch": 0.7496240288650724, "grad_norm": 1.6058982610702515, "learning_rate": 0.00018796245713096366, "loss": 0.6672623634338379, "step": 126110 }, { "epoch": 0.7496834709417408, "grad_norm": 1.6104236841201782, "learning_rate": 0.00018795934697746637, "loss": 0.683866310119629, "step": 126120 }, { "epoch": 0.7497429130184092, "grad_norm": 2.0444040298461914, "learning_rate": 0.00018795623645103705, "loss": 0.6717907428741455, "step": 126130 }, { "epoch": 0.7498023550950776, "grad_norm": 2.0929148197174072, "learning_rate": 0.00018795312555169058, "loss": 0.6661504745483399, "step": 126140 }, { "epoch": 0.749861797171746, "grad_norm": 1.3684858083724976, "learning_rate": 0.00018795001427944182, "loss": 0.6095535278320312, "step": 126150 }, { "epoch": 0.7499212392484144, "grad_norm": 1.7711009979248047, "learning_rate": 0.00018794690263430568, "loss": 0.6430891513824463, "step": 126160 }, { "epoch": 0.7499806813250828, "grad_norm": 1.6080368757247925, "learning_rate": 0.00018794379061629703, "loss": 0.6351386070251465, "step": 126170 }, { "epoch": 0.7500401234017512, "grad_norm": 1.4559193849563599, "learning_rate": 0.00018794067822543075, "loss": 0.667609691619873, "step": 126180 }, { "epoch": 0.7500995654784196, "grad_norm": 1.2393372058868408, "learning_rate": 0.00018793756546172172, "loss": 0.691808032989502, "step": 126190 }, { "epoch": 0.7501590075550879, "grad_norm": 1.7467180490493774, "learning_rate": 0.00018793445232518488, "loss": 0.6138349533081054, "step": 126200 }, { "epoch": 0.7502184496317563, "grad_norm": 2.06050181388855, "learning_rate": 0.00018793133881583508, "loss": 0.6405177116394043, "step": 126210 }, { "epoch": 0.7502778917084247, "grad_norm": 1.848300814628601, "learning_rate": 0.00018792822493368723, "loss": 0.6418380737304688, "step": 126220 }, { "epoch": 0.7503373337850932, "grad_norm": 1.801898717880249, "learning_rate": 0.0001879251106787562, "loss": 0.659588623046875, "step": 126230 }, { "epoch": 0.7503967758617615, "grad_norm": 1.5310581922531128, "learning_rate": 0.00018792199605105692, "loss": 0.6778550148010254, "step": 126240 }, { "epoch": 0.7504562179384299, "grad_norm": 1.4773945808410645, "learning_rate": 0.00018791888105060427, "loss": 0.6790312767028809, "step": 126250 }, { "epoch": 0.7505156600150983, "grad_norm": 1.6557828187942505, "learning_rate": 0.00018791576567741313, "loss": 0.6143523216247558, "step": 126260 }, { "epoch": 0.7505751020917667, "grad_norm": 2.247576951980591, "learning_rate": 0.00018791264993149847, "loss": 0.6875955581665039, "step": 126270 }, { "epoch": 0.7506345441684351, "grad_norm": 1.5168066024780273, "learning_rate": 0.00018790953381287516, "loss": 0.6118348598480224, "step": 126280 }, { "epoch": 0.7506939862451034, "grad_norm": 2.364078998565674, "learning_rate": 0.00018790641732155806, "loss": 0.7161499977111816, "step": 126290 }, { "epoch": 0.7507534283217718, "grad_norm": 1.8323856592178345, "learning_rate": 0.00018790330045756216, "loss": 0.666668701171875, "step": 126300 }, { "epoch": 0.7508128703984402, "grad_norm": 1.503746747970581, "learning_rate": 0.0001879001832209023, "loss": 0.7635001182556153, "step": 126310 }, { "epoch": 0.7508723124751087, "grad_norm": 1.9969377517700195, "learning_rate": 0.00018789706561159346, "loss": 0.6972310066223144, "step": 126320 }, { "epoch": 0.7509317545517771, "grad_norm": 1.5447089672088623, "learning_rate": 0.00018789394762965046, "loss": 0.6171798229217529, "step": 126330 }, { "epoch": 0.7509911966284454, "grad_norm": 1.6937284469604492, "learning_rate": 0.00018789082927508831, "loss": 0.6577130317687988, "step": 126340 }, { "epoch": 0.7510506387051138, "grad_norm": 1.931355357170105, "learning_rate": 0.0001878877105479219, "loss": 0.6487792015075684, "step": 126350 }, { "epoch": 0.7511100807817822, "grad_norm": 2.113063335418701, "learning_rate": 0.0001878845914481661, "loss": 0.7170809268951416, "step": 126360 }, { "epoch": 0.7511695228584506, "grad_norm": 1.79727041721344, "learning_rate": 0.00018788147197583587, "loss": 0.685523509979248, "step": 126370 }, { "epoch": 0.7512289649351189, "grad_norm": 1.6501177549362183, "learning_rate": 0.00018787835213094617, "loss": 0.5961146831512452, "step": 126380 }, { "epoch": 0.7512884070117873, "grad_norm": 2.0112903118133545, "learning_rate": 0.0001878752319135118, "loss": 0.6433449268341065, "step": 126390 }, { "epoch": 0.7513478490884558, "grad_norm": 1.43883216381073, "learning_rate": 0.00018787211132354788, "loss": 0.6525755405426026, "step": 126400 }, { "epoch": 0.7514072911651242, "grad_norm": 2.1458580493927, "learning_rate": 0.00018786899036106917, "loss": 0.6568806648254395, "step": 126410 }, { "epoch": 0.7514667332417926, "grad_norm": 1.9470680952072144, "learning_rate": 0.00018786586902609065, "loss": 0.6936298370361328, "step": 126420 }, { "epoch": 0.7515261753184609, "grad_norm": 1.3098340034484863, "learning_rate": 0.0001878627473186273, "loss": 0.6720758438110351, "step": 126430 }, { "epoch": 0.7515856173951293, "grad_norm": 1.3213481903076172, "learning_rate": 0.00018785962523869395, "loss": 0.6577316284179687, "step": 126440 }, { "epoch": 0.7516450594717977, "grad_norm": 1.4017958641052246, "learning_rate": 0.00018785650278630567, "loss": 0.6303755760192871, "step": 126450 }, { "epoch": 0.7517045015484661, "grad_norm": 1.514174222946167, "learning_rate": 0.00018785337996147727, "loss": 0.608730411529541, "step": 126460 }, { "epoch": 0.7517639436251344, "grad_norm": 1.859736680984497, "learning_rate": 0.00018785025676422375, "loss": 0.6060279846191406, "step": 126470 }, { "epoch": 0.7518233857018028, "grad_norm": 1.886460304260254, "learning_rate": 0.00018784713319456006, "loss": 0.6670336723327637, "step": 126480 }, { "epoch": 0.7518828277784713, "grad_norm": 1.7048225402832031, "learning_rate": 0.0001878440092525011, "loss": 0.7018350601196289, "step": 126490 }, { "epoch": 0.7519422698551397, "grad_norm": 1.5502358675003052, "learning_rate": 0.00018784088493806187, "loss": 0.6631299972534179, "step": 126500 }, { "epoch": 0.7520017119318081, "grad_norm": 1.7715442180633545, "learning_rate": 0.0001878377602512573, "loss": 0.6450612068176269, "step": 126510 }, { "epoch": 0.7520611540084764, "grad_norm": 1.713998556137085, "learning_rate": 0.00018783463519210226, "loss": 0.6913302421569825, "step": 126520 }, { "epoch": 0.7521205960851448, "grad_norm": 1.9196199178695679, "learning_rate": 0.00018783150976061183, "loss": 0.6727167129516601, "step": 126530 }, { "epoch": 0.7521800381618132, "grad_norm": 1.7386492490768433, "learning_rate": 0.00018782838395680083, "loss": 0.7001566886901855, "step": 126540 }, { "epoch": 0.7522394802384816, "grad_norm": 1.6787734031677246, "learning_rate": 0.00018782525778068433, "loss": 0.6497722148895264, "step": 126550 }, { "epoch": 0.75229892231515, "grad_norm": 1.3939565420150757, "learning_rate": 0.00018782213123227722, "loss": 0.6269188404083252, "step": 126560 }, { "epoch": 0.7523583643918184, "grad_norm": 1.56321120262146, "learning_rate": 0.00018781900431159444, "loss": 0.6493762016296387, "step": 126570 }, { "epoch": 0.7524178064684868, "grad_norm": 1.519494891166687, "learning_rate": 0.00018781587701865098, "loss": 0.6562814712524414, "step": 126580 }, { "epoch": 0.7524772485451552, "grad_norm": 1.7551087141036987, "learning_rate": 0.00018781274935346183, "loss": 0.6693881511688232, "step": 126590 }, { "epoch": 0.7525366906218236, "grad_norm": 1.6055907011032104, "learning_rate": 0.0001878096213160419, "loss": 0.6735115051269531, "step": 126600 }, { "epoch": 0.7525961326984919, "grad_norm": 1.5311402082443237, "learning_rate": 0.00018780649290640615, "loss": 0.6933414459228515, "step": 126610 }, { "epoch": 0.7526555747751603, "grad_norm": 1.5140117406845093, "learning_rate": 0.00018780336412456958, "loss": 0.6282824039459228, "step": 126620 }, { "epoch": 0.7527150168518287, "grad_norm": 1.6292669773101807, "learning_rate": 0.00018780023497054713, "loss": 0.6361223697662354, "step": 126630 }, { "epoch": 0.7527744589284971, "grad_norm": 1.5381908416748047, "learning_rate": 0.00018779710544435376, "loss": 0.6132641792297363, "step": 126640 }, { "epoch": 0.7528339010051656, "grad_norm": 1.6516666412353516, "learning_rate": 0.0001877939755460045, "loss": 0.6523104667663574, "step": 126650 }, { "epoch": 0.7528933430818339, "grad_norm": 2.137547492980957, "learning_rate": 0.00018779084527551429, "loss": 0.6481239318847656, "step": 126660 }, { "epoch": 0.7529527851585023, "grad_norm": 1.3158940076828003, "learning_rate": 0.00018778771463289807, "loss": 0.6331623077392579, "step": 126670 }, { "epoch": 0.7530122272351707, "grad_norm": 1.8474373817443848, "learning_rate": 0.00018778458361817088, "loss": 0.7044333934783935, "step": 126680 }, { "epoch": 0.7530716693118391, "grad_norm": 1.7445708513259888, "learning_rate": 0.00018778145223134765, "loss": 0.6294103622436523, "step": 126690 }, { "epoch": 0.7531311113885075, "grad_norm": 2.267169713973999, "learning_rate": 0.00018777832047244336, "loss": 0.5955696105957031, "step": 126700 }, { "epoch": 0.7531905534651758, "grad_norm": 1.8883452415466309, "learning_rate": 0.00018777518834147298, "loss": 0.6465789794921875, "step": 126710 }, { "epoch": 0.7532499955418442, "grad_norm": 1.6972401142120361, "learning_rate": 0.0001877720558384516, "loss": 0.6074155807495117, "step": 126720 }, { "epoch": 0.7533094376185127, "grad_norm": 1.815895676612854, "learning_rate": 0.00018776892296339402, "loss": 0.6751643180847168, "step": 126730 }, { "epoch": 0.7533688796951811, "grad_norm": 1.8534812927246094, "learning_rate": 0.00018776578971631537, "loss": 0.7020668983459473, "step": 126740 }, { "epoch": 0.7534283217718494, "grad_norm": 1.4342650175094604, "learning_rate": 0.00018776265609723062, "loss": 0.6212488174438476, "step": 126750 }, { "epoch": 0.7534877638485178, "grad_norm": 1.583013653755188, "learning_rate": 0.0001877595221061547, "loss": 0.613491153717041, "step": 126760 }, { "epoch": 0.7535472059251862, "grad_norm": 1.4492998123168945, "learning_rate": 0.00018775638774310265, "loss": 0.6371473789215087, "step": 126770 }, { "epoch": 0.7536066480018546, "grad_norm": 1.5904312133789062, "learning_rate": 0.00018775325300808947, "loss": 0.56883544921875, "step": 126780 }, { "epoch": 0.753666090078523, "grad_norm": 2.168621778488159, "learning_rate": 0.0001877501179011301, "loss": 0.6515531539916992, "step": 126790 }, { "epoch": 0.7537255321551913, "grad_norm": 1.5239976644515991, "learning_rate": 0.00018774698242223962, "loss": 0.7190861701965332, "step": 126800 }, { "epoch": 0.7537849742318598, "grad_norm": 1.3197510242462158, "learning_rate": 0.00018774384657143295, "loss": 0.6574240684509277, "step": 126810 }, { "epoch": 0.7538444163085282, "grad_norm": 2.058762311935425, "learning_rate": 0.00018774071034872517, "loss": 0.6363222122192382, "step": 126820 }, { "epoch": 0.7539038583851966, "grad_norm": 1.810825228691101, "learning_rate": 0.00018773757375413117, "loss": 0.6271707534790039, "step": 126830 }, { "epoch": 0.7539633004618649, "grad_norm": 1.5807169675827026, "learning_rate": 0.00018773443678766607, "loss": 0.6544580936431885, "step": 126840 }, { "epoch": 0.7540227425385333, "grad_norm": 1.9819629192352295, "learning_rate": 0.0001877312994493448, "loss": 0.6994624137878418, "step": 126850 }, { "epoch": 0.7540821846152017, "grad_norm": 1.6702488660812378, "learning_rate": 0.00018772816173918242, "loss": 0.623438549041748, "step": 126860 }, { "epoch": 0.7541416266918701, "grad_norm": 2.0852296352386475, "learning_rate": 0.00018772502365719388, "loss": 0.7212636947631836, "step": 126870 }, { "epoch": 0.7542010687685385, "grad_norm": 1.8549110889434814, "learning_rate": 0.0001877218852033943, "loss": 0.6375360488891602, "step": 126880 }, { "epoch": 0.7542605108452068, "grad_norm": 1.3426612615585327, "learning_rate": 0.00018771874637779854, "loss": 0.6642785549163819, "step": 126890 }, { "epoch": 0.7543199529218753, "grad_norm": 1.6673221588134766, "learning_rate": 0.00018771560718042175, "loss": 0.6227208614349365, "step": 126900 }, { "epoch": 0.7543793949985437, "grad_norm": 1.400813102722168, "learning_rate": 0.00018771246761127886, "loss": 0.7004491329193115, "step": 126910 }, { "epoch": 0.7544388370752121, "grad_norm": 1.8518524169921875, "learning_rate": 0.00018770932767038493, "loss": 0.6727199554443359, "step": 126920 }, { "epoch": 0.7544982791518805, "grad_norm": 1.9488842487335205, "learning_rate": 0.000187706187357755, "loss": 0.6978405952453614, "step": 126930 }, { "epoch": 0.7545577212285488, "grad_norm": 1.448119878768921, "learning_rate": 0.00018770304667340405, "loss": 0.6736477851867676, "step": 126940 }, { "epoch": 0.7546171633052172, "grad_norm": 1.8240745067596436, "learning_rate": 0.00018769990561734708, "loss": 0.7049796104431152, "step": 126950 }, { "epoch": 0.7546766053818856, "grad_norm": 1.61436128616333, "learning_rate": 0.00018769676418959921, "loss": 0.6765392780303955, "step": 126960 }, { "epoch": 0.754736047458554, "grad_norm": 1.5305578708648682, "learning_rate": 0.00018769362239017537, "loss": 0.6659753799438477, "step": 126970 }, { "epoch": 0.7547954895352224, "grad_norm": 1.7381336688995361, "learning_rate": 0.00018769048021909066, "loss": 0.7148731708526611, "step": 126980 }, { "epoch": 0.7548549316118908, "grad_norm": 1.8181911706924438, "learning_rate": 0.00018768733767636007, "loss": 0.658270263671875, "step": 126990 }, { "epoch": 0.7549143736885592, "grad_norm": 1.5549434423446655, "learning_rate": 0.00018768419476199863, "loss": 0.6425301551818847, "step": 127000 }, { "epoch": 0.7549738157652276, "grad_norm": 1.7864997386932373, "learning_rate": 0.0001876810514760214, "loss": 0.7140838623046875, "step": 127010 }, { "epoch": 0.755033257841896, "grad_norm": 1.6186110973358154, "learning_rate": 0.00018767790781844344, "loss": 0.6978766441345214, "step": 127020 }, { "epoch": 0.7550926999185643, "grad_norm": 2.0344150066375732, "learning_rate": 0.0001876747637892797, "loss": 0.6726233959197998, "step": 127030 }, { "epoch": 0.7551521419952327, "grad_norm": 1.868219017982483, "learning_rate": 0.00018767161938854532, "loss": 0.717633056640625, "step": 127040 }, { "epoch": 0.7552115840719011, "grad_norm": 1.1635504961013794, "learning_rate": 0.00018766847461625525, "loss": 0.5730886459350586, "step": 127050 }, { "epoch": 0.7552710261485696, "grad_norm": 1.8438104391098022, "learning_rate": 0.0001876653294724246, "loss": 0.6315779685974121, "step": 127060 }, { "epoch": 0.755330468225238, "grad_norm": 1.4898490905761719, "learning_rate": 0.00018766218395706842, "loss": 0.6400034904479981, "step": 127070 }, { "epoch": 0.7553899103019063, "grad_norm": 1.767025113105774, "learning_rate": 0.00018765903807020174, "loss": 0.6755506515502929, "step": 127080 }, { "epoch": 0.7554493523785747, "grad_norm": 1.7130227088928223, "learning_rate": 0.00018765589181183952, "loss": 0.6541521072387695, "step": 127090 }, { "epoch": 0.7555087944552431, "grad_norm": 1.6476022005081177, "learning_rate": 0.00018765274518199696, "loss": 0.6832877159118652, "step": 127100 }, { "epoch": 0.7555682365319115, "grad_norm": 1.426823616027832, "learning_rate": 0.00018764959818068906, "loss": 0.6612616062164307, "step": 127110 }, { "epoch": 0.7556276786085798, "grad_norm": 1.8348180055618286, "learning_rate": 0.0001876464508079308, "loss": 0.6631088256835938, "step": 127120 }, { "epoch": 0.7556871206852482, "grad_norm": 1.5883266925811768, "learning_rate": 0.00018764330306373733, "loss": 0.7507454872131347, "step": 127130 }, { "epoch": 0.7557465627619167, "grad_norm": 1.5488492250442505, "learning_rate": 0.00018764015494812365, "loss": 0.6908525466918946, "step": 127140 }, { "epoch": 0.7558060048385851, "grad_norm": 1.878272294998169, "learning_rate": 0.0001876370064611049, "loss": 0.6561226844787598, "step": 127150 }, { "epoch": 0.7558654469152535, "grad_norm": 1.2717156410217285, "learning_rate": 0.00018763385760269604, "loss": 0.5872499942779541, "step": 127160 }, { "epoch": 0.7559248889919218, "grad_norm": 1.2804123163223267, "learning_rate": 0.00018763070837291216, "loss": 0.6549657821655274, "step": 127170 }, { "epoch": 0.7559843310685902, "grad_norm": 1.8345746994018555, "learning_rate": 0.00018762755877176833, "loss": 0.6904082298278809, "step": 127180 }, { "epoch": 0.7560437731452586, "grad_norm": 1.8643035888671875, "learning_rate": 0.00018762440879927967, "loss": 0.6774600505828857, "step": 127190 }, { "epoch": 0.756103215221927, "grad_norm": 2.0249695777893066, "learning_rate": 0.0001876212584554612, "loss": 0.6846450328826904, "step": 127200 }, { "epoch": 0.7561626572985953, "grad_norm": 2.112295389175415, "learning_rate": 0.00018761810774032796, "loss": 0.6506137847900391, "step": 127210 }, { "epoch": 0.7562220993752637, "grad_norm": 1.84363853931427, "learning_rate": 0.0001876149566538951, "loss": 0.6190279960632324, "step": 127220 }, { "epoch": 0.7562815414519322, "grad_norm": 1.692997932434082, "learning_rate": 0.00018761180519617765, "loss": 0.623235034942627, "step": 127230 }, { "epoch": 0.7563409835286006, "grad_norm": 1.9041377305984497, "learning_rate": 0.00018760865336719067, "loss": 0.7043039321899414, "step": 127240 }, { "epoch": 0.756400425605269, "grad_norm": 1.8116626739501953, "learning_rate": 0.00018760550116694928, "loss": 0.612233829498291, "step": 127250 }, { "epoch": 0.7564598676819373, "grad_norm": 1.8641748428344727, "learning_rate": 0.0001876023485954685, "loss": 0.6525144577026367, "step": 127260 }, { "epoch": 0.7565193097586057, "grad_norm": 1.518282175064087, "learning_rate": 0.00018759919565276346, "loss": 0.6971985816955566, "step": 127270 }, { "epoch": 0.7565787518352741, "grad_norm": 1.9429420232772827, "learning_rate": 0.00018759604233884922, "loss": 0.6682091236114502, "step": 127280 }, { "epoch": 0.7566381939119425, "grad_norm": 1.9620543718338013, "learning_rate": 0.0001875928886537409, "loss": 0.6284588813781739, "step": 127290 }, { "epoch": 0.756697635988611, "grad_norm": 1.6346834897994995, "learning_rate": 0.00018758973459745355, "loss": 0.6730043411254882, "step": 127300 }, { "epoch": 0.7567570780652793, "grad_norm": 1.9700301885604858, "learning_rate": 0.00018758658017000227, "loss": 0.7113735198974609, "step": 127310 }, { "epoch": 0.7568165201419477, "grad_norm": 2.083270788192749, "learning_rate": 0.0001875834253714021, "loss": 0.6571713447570801, "step": 127320 }, { "epoch": 0.7568759622186161, "grad_norm": 1.9260237216949463, "learning_rate": 0.0001875802702016682, "loss": 0.6602112770080566, "step": 127330 }, { "epoch": 0.7569354042952845, "grad_norm": 1.9005104303359985, "learning_rate": 0.0001875771146608157, "loss": 0.6996653556823731, "step": 127340 }, { "epoch": 0.7569948463719528, "grad_norm": 1.5929961204528809, "learning_rate": 0.00018757395874885953, "loss": 0.6856492042541504, "step": 127350 }, { "epoch": 0.7570542884486212, "grad_norm": 1.696441888809204, "learning_rate": 0.00018757080246581498, "loss": 0.6469752788543701, "step": 127360 }, { "epoch": 0.7571137305252896, "grad_norm": 1.6121315956115723, "learning_rate": 0.000187567645811697, "loss": 0.7007959365844727, "step": 127370 }, { "epoch": 0.757173172601958, "grad_norm": 1.7524213790893555, "learning_rate": 0.00018756448878652082, "loss": 0.7030800819396973, "step": 127380 }, { "epoch": 0.7572326146786265, "grad_norm": 1.6723525524139404, "learning_rate": 0.00018756133139030142, "loss": 0.6412801742553711, "step": 127390 }, { "epoch": 0.7572920567552948, "grad_norm": 2.015942096710205, "learning_rate": 0.00018755817362305397, "loss": 0.6670181751251221, "step": 127400 }, { "epoch": 0.7573514988319632, "grad_norm": 1.4450877904891968, "learning_rate": 0.00018755501548479357, "loss": 0.6546185970306396, "step": 127410 }, { "epoch": 0.7574109409086316, "grad_norm": 1.3952683210372925, "learning_rate": 0.00018755185697553531, "loss": 0.704768180847168, "step": 127420 }, { "epoch": 0.7574703829853, "grad_norm": 2.1607494354248047, "learning_rate": 0.00018754869809529433, "loss": 0.6603309154510498, "step": 127430 }, { "epoch": 0.7575298250619684, "grad_norm": 1.6393502950668335, "learning_rate": 0.0001875455388440857, "loss": 0.6827902317047119, "step": 127440 }, { "epoch": 0.7575892671386367, "grad_norm": 1.6828490495681763, "learning_rate": 0.00018754237922192457, "loss": 0.7227166175842286, "step": 127450 }, { "epoch": 0.7576487092153051, "grad_norm": 1.3779346942901611, "learning_rate": 0.00018753921922882606, "loss": 0.6652424812316895, "step": 127460 }, { "epoch": 0.7577081512919736, "grad_norm": 1.7828006744384766, "learning_rate": 0.0001875360588648052, "loss": 0.6562367439270019, "step": 127470 }, { "epoch": 0.757767593368642, "grad_norm": 1.499019980430603, "learning_rate": 0.0001875328981298772, "loss": 0.6671936988830567, "step": 127480 }, { "epoch": 0.7578270354453103, "grad_norm": 1.7420645952224731, "learning_rate": 0.00018752973702405718, "loss": 0.6843033790588379, "step": 127490 }, { "epoch": 0.7578864775219787, "grad_norm": 1.5178337097167969, "learning_rate": 0.00018752657554736024, "loss": 0.6295682907104492, "step": 127500 }, { "epoch": 0.7579459195986471, "grad_norm": 1.569370985031128, "learning_rate": 0.00018752341369980148, "loss": 0.6584437370300293, "step": 127510 }, { "epoch": 0.7580053616753155, "grad_norm": 1.820684790611267, "learning_rate": 0.00018752025148139606, "loss": 0.6726679325103759, "step": 127520 }, { "epoch": 0.7580648037519839, "grad_norm": 1.512904405593872, "learning_rate": 0.00018751708889215907, "loss": 0.6609477519989013, "step": 127530 }, { "epoch": 0.7581242458286522, "grad_norm": 1.5968888998031616, "learning_rate": 0.00018751392593210564, "loss": 0.6627619743347168, "step": 127540 }, { "epoch": 0.7581836879053206, "grad_norm": 1.5641032457351685, "learning_rate": 0.00018751076260125095, "loss": 0.6504651069641113, "step": 127550 }, { "epoch": 0.7582431299819891, "grad_norm": 1.6785582304000854, "learning_rate": 0.00018750759889961009, "loss": 0.6152743816375732, "step": 127560 }, { "epoch": 0.7583025720586575, "grad_norm": 1.4415016174316406, "learning_rate": 0.00018750443482719821, "loss": 0.6735264778137207, "step": 127570 }, { "epoch": 0.7583620141353258, "grad_norm": 1.7846331596374512, "learning_rate": 0.00018750127038403048, "loss": 0.6829314708709717, "step": 127580 }, { "epoch": 0.7584214562119942, "grad_norm": 1.8649370670318604, "learning_rate": 0.00018749810557012195, "loss": 0.6858233451843262, "step": 127590 }, { "epoch": 0.7584808982886626, "grad_norm": 1.6318652629852295, "learning_rate": 0.00018749494038548781, "loss": 0.6510313034057618, "step": 127600 }, { "epoch": 0.758540340365331, "grad_norm": 1.869206428527832, "learning_rate": 0.00018749177483014324, "loss": 0.6800268650054931, "step": 127610 }, { "epoch": 0.7585997824419994, "grad_norm": 1.602405071258545, "learning_rate": 0.0001874886089041033, "loss": 0.6853102207183838, "step": 127620 }, { "epoch": 0.7586592245186677, "grad_norm": 1.6673476696014404, "learning_rate": 0.0001874854426073832, "loss": 0.7062849044799805, "step": 127630 }, { "epoch": 0.7587186665953362, "grad_norm": 1.2264988422393799, "learning_rate": 0.00018748227593999808, "loss": 0.6865353584289551, "step": 127640 }, { "epoch": 0.7587781086720046, "grad_norm": 1.2987104654312134, "learning_rate": 0.00018747910890196305, "loss": 0.731212043762207, "step": 127650 }, { "epoch": 0.758837550748673, "grad_norm": 1.2268069982528687, "learning_rate": 0.0001874759414932933, "loss": 0.6318796157836915, "step": 127660 }, { "epoch": 0.7588969928253414, "grad_norm": 1.4896736145019531, "learning_rate": 0.00018747277371400394, "loss": 0.6198922157287597, "step": 127670 }, { "epoch": 0.7589564349020097, "grad_norm": 1.7878665924072266, "learning_rate": 0.00018746960556411017, "loss": 0.6693027496337891, "step": 127680 }, { "epoch": 0.7590158769786781, "grad_norm": 1.7582000494003296, "learning_rate": 0.00018746643704362713, "loss": 0.6200765132904053, "step": 127690 }, { "epoch": 0.7590753190553465, "grad_norm": 1.6888315677642822, "learning_rate": 0.00018746326815256996, "loss": 0.7072627544403076, "step": 127700 }, { "epoch": 0.759134761132015, "grad_norm": 1.5046159029006958, "learning_rate": 0.00018746009889095383, "loss": 0.6463647365570069, "step": 127710 }, { "epoch": 0.7591942032086832, "grad_norm": 1.4181464910507202, "learning_rate": 0.0001874569292587939, "loss": 0.6744357585906983, "step": 127720 }, { "epoch": 0.7592536452853517, "grad_norm": 1.809265375137329, "learning_rate": 0.00018745375925610533, "loss": 0.6091391563415527, "step": 127730 }, { "epoch": 0.7593130873620201, "grad_norm": 1.6261622905731201, "learning_rate": 0.00018745058888290327, "loss": 0.6765063762664795, "step": 127740 }, { "epoch": 0.7593725294386885, "grad_norm": 1.5082975625991821, "learning_rate": 0.00018744741813920296, "loss": 0.717167854309082, "step": 127750 }, { "epoch": 0.7594319715153569, "grad_norm": 1.626900553703308, "learning_rate": 0.00018744424702501946, "loss": 0.7081473350524903, "step": 127760 }, { "epoch": 0.7594914135920252, "grad_norm": 1.7057816982269287, "learning_rate": 0.00018744107554036804, "loss": 0.710674238204956, "step": 127770 }, { "epoch": 0.7595508556686936, "grad_norm": 1.4752647876739502, "learning_rate": 0.00018743790368526376, "loss": 0.6842767715454101, "step": 127780 }, { "epoch": 0.759610297745362, "grad_norm": 1.8786981105804443, "learning_rate": 0.0001874347314597219, "loss": 0.7029284000396728, "step": 127790 }, { "epoch": 0.7596697398220305, "grad_norm": 2.005796432495117, "learning_rate": 0.00018743155886375757, "loss": 0.635871171951294, "step": 127800 }, { "epoch": 0.7597291818986988, "grad_norm": 1.3649251461029053, "learning_rate": 0.000187428385897386, "loss": 0.6232583045959472, "step": 127810 }, { "epoch": 0.7597886239753672, "grad_norm": 1.8499467372894287, "learning_rate": 0.0001874252125606223, "loss": 0.6285206317901612, "step": 127820 }, { "epoch": 0.7598480660520356, "grad_norm": 1.6856766939163208, "learning_rate": 0.00018742203885348168, "loss": 0.6604451656341552, "step": 127830 }, { "epoch": 0.759907508128704, "grad_norm": 1.3932011127471924, "learning_rate": 0.00018741886477597938, "loss": 0.6613419532775879, "step": 127840 }, { "epoch": 0.7599669502053724, "grad_norm": 1.672128677368164, "learning_rate": 0.00018741569032813045, "loss": 0.6943059921264648, "step": 127850 }, { "epoch": 0.7600263922820407, "grad_norm": 1.703628659248352, "learning_rate": 0.00018741251550995024, "loss": 0.6663306713104248, "step": 127860 }, { "epoch": 0.7600858343587091, "grad_norm": 1.86198091506958, "learning_rate": 0.00018740934032145383, "loss": 0.6651302337646484, "step": 127870 }, { "epoch": 0.7601452764353775, "grad_norm": 2.4993996620178223, "learning_rate": 0.00018740616476265641, "loss": 0.6797470092773438, "step": 127880 }, { "epoch": 0.760204718512046, "grad_norm": 1.3290514945983887, "learning_rate": 0.00018740298883357322, "loss": 0.5926426887512207, "step": 127890 }, { "epoch": 0.7602641605887144, "grad_norm": 1.2765274047851562, "learning_rate": 0.00018739981253421942, "loss": 0.5888481616973877, "step": 127900 }, { "epoch": 0.7603236026653827, "grad_norm": 1.3203179836273193, "learning_rate": 0.0001873966358646102, "loss": 0.6627134799957275, "step": 127910 }, { "epoch": 0.7603830447420511, "grad_norm": 1.1945768594741821, "learning_rate": 0.0001873934588247608, "loss": 0.6312732696533203, "step": 127920 }, { "epoch": 0.7604424868187195, "grad_norm": 1.7605139017105103, "learning_rate": 0.00018739028141468632, "loss": 0.7021825790405274, "step": 127930 }, { "epoch": 0.7605019288953879, "grad_norm": 1.718855857849121, "learning_rate": 0.00018738710363440207, "loss": 0.6644272804260254, "step": 127940 }, { "epoch": 0.7605613709720562, "grad_norm": 1.9370924234390259, "learning_rate": 0.0001873839254839232, "loss": 0.6999229431152344, "step": 127950 }, { "epoch": 0.7606208130487246, "grad_norm": 1.6125057935714722, "learning_rate": 0.00018738074696326493, "loss": 0.5951452732086182, "step": 127960 }, { "epoch": 0.7606802551253931, "grad_norm": 1.6179417371749878, "learning_rate": 0.00018737756807244243, "loss": 0.6725926399230957, "step": 127970 }, { "epoch": 0.7607396972020615, "grad_norm": 1.7076538801193237, "learning_rate": 0.00018737438881147095, "loss": 0.7034690856933594, "step": 127980 }, { "epoch": 0.7607991392787299, "grad_norm": 1.9053586721420288, "learning_rate": 0.0001873712091803657, "loss": 0.7015589714050293, "step": 127990 }, { "epoch": 0.7608585813553982, "grad_norm": 1.5745558738708496, "learning_rate": 0.00018736802917914184, "loss": 0.6246344089508057, "step": 128000 }, { "epoch": 0.7609180234320666, "grad_norm": 1.5033937692642212, "learning_rate": 0.00018736484880781462, "loss": 0.6121175765991211, "step": 128010 }, { "epoch": 0.760977465508735, "grad_norm": 1.7223058938980103, "learning_rate": 0.00018736166806639922, "loss": 0.6678780555725098, "step": 128020 }, { "epoch": 0.7610369075854034, "grad_norm": 1.513101577758789, "learning_rate": 0.00018735848695491093, "loss": 0.6530324935913085, "step": 128030 }, { "epoch": 0.7610963496620718, "grad_norm": 1.533057451248169, "learning_rate": 0.00018735530547336492, "loss": 0.7270444393157959, "step": 128040 }, { "epoch": 0.7611557917387402, "grad_norm": 1.7210638523101807, "learning_rate": 0.0001873521236217764, "loss": 0.6294684886932373, "step": 128050 }, { "epoch": 0.7612152338154086, "grad_norm": 1.5337170362472534, "learning_rate": 0.00018734894140016057, "loss": 0.6727993965148926, "step": 128060 }, { "epoch": 0.761274675892077, "grad_norm": 2.0310747623443604, "learning_rate": 0.0001873457588085327, "loss": 0.6864455223083497, "step": 128070 }, { "epoch": 0.7613341179687454, "grad_norm": 1.490623116493225, "learning_rate": 0.00018734257584690798, "loss": 0.6605406761169433, "step": 128080 }, { "epoch": 0.7613935600454137, "grad_norm": 1.7240214347839355, "learning_rate": 0.00018733939251530166, "loss": 0.6259648323059082, "step": 128090 }, { "epoch": 0.7614530021220821, "grad_norm": 1.7282944917678833, "learning_rate": 0.00018733620881372897, "loss": 0.6378742218017578, "step": 128100 }, { "epoch": 0.7615124441987505, "grad_norm": 1.6109697818756104, "learning_rate": 0.00018733302474220514, "loss": 0.6381977081298829, "step": 128110 }, { "epoch": 0.7615718862754189, "grad_norm": 1.4533495903015137, "learning_rate": 0.0001873298403007454, "loss": 0.6686464309692383, "step": 128120 }, { "epoch": 0.7616313283520874, "grad_norm": 1.8159945011138916, "learning_rate": 0.00018732665548936494, "loss": 0.6989544868469239, "step": 128130 }, { "epoch": 0.7616907704287557, "grad_norm": 1.4980366230010986, "learning_rate": 0.00018732347030807906, "loss": 0.6416022300720214, "step": 128140 }, { "epoch": 0.7617502125054241, "grad_norm": 1.7235486507415771, "learning_rate": 0.00018732028475690294, "loss": 0.6259640693664551, "step": 128150 }, { "epoch": 0.7618096545820925, "grad_norm": 1.5080311298370361, "learning_rate": 0.00018731709883585188, "loss": 0.6375261306762695, "step": 128160 }, { "epoch": 0.7618690966587609, "grad_norm": 1.6456506252288818, "learning_rate": 0.00018731391254494107, "loss": 0.6968722343444824, "step": 128170 }, { "epoch": 0.7619285387354292, "grad_norm": 1.7004696130752563, "learning_rate": 0.00018731072588418576, "loss": 0.6773754119873047, "step": 128180 }, { "epoch": 0.7619879808120976, "grad_norm": 1.5374094247817993, "learning_rate": 0.00018730753885360123, "loss": 0.7196321964263916, "step": 128190 }, { "epoch": 0.762047422888766, "grad_norm": 1.4481455087661743, "learning_rate": 0.00018730435145320268, "loss": 0.6989016532897949, "step": 128200 }, { "epoch": 0.7621068649654344, "grad_norm": 1.3794782161712646, "learning_rate": 0.00018730116368300537, "loss": 0.6464077949523925, "step": 128210 }, { "epoch": 0.7621663070421029, "grad_norm": 1.5488646030426025, "learning_rate": 0.00018729797554302454, "loss": 0.6262931823730469, "step": 128220 }, { "epoch": 0.7622257491187712, "grad_norm": 1.5196040868759155, "learning_rate": 0.0001872947870332755, "loss": 0.6625290393829346, "step": 128230 }, { "epoch": 0.7622851911954396, "grad_norm": 1.3093147277832031, "learning_rate": 0.00018729159815377344, "loss": 0.6882999897003174, "step": 128240 }, { "epoch": 0.762344633272108, "grad_norm": 1.5386561155319214, "learning_rate": 0.0001872884089045336, "loss": 0.672053050994873, "step": 128250 }, { "epoch": 0.7624040753487764, "grad_norm": 1.5354526042938232, "learning_rate": 0.0001872852192855713, "loss": 0.6845277309417724, "step": 128260 }, { "epoch": 0.7624635174254448, "grad_norm": 1.5934964418411255, "learning_rate": 0.00018728202929690178, "loss": 0.633327054977417, "step": 128270 }, { "epoch": 0.7625229595021131, "grad_norm": 1.9697335958480835, "learning_rate": 0.00018727883893854028, "loss": 0.6944802284240723, "step": 128280 }, { "epoch": 0.7625824015787815, "grad_norm": 1.9665287733078003, "learning_rate": 0.00018727564821050205, "loss": 0.729363203048706, "step": 128290 }, { "epoch": 0.76264184365545, "grad_norm": 1.9506124258041382, "learning_rate": 0.0001872724571128024, "loss": 0.674958324432373, "step": 128300 }, { "epoch": 0.7627012857321184, "grad_norm": 1.6381828784942627, "learning_rate": 0.00018726926564545656, "loss": 0.6556803703308105, "step": 128310 }, { "epoch": 0.7627607278087867, "grad_norm": 1.6274102926254272, "learning_rate": 0.00018726607380847981, "loss": 0.6281330585479736, "step": 128320 }, { "epoch": 0.7628201698854551, "grad_norm": 1.7006884813308716, "learning_rate": 0.00018726288160188738, "loss": 0.6902788162231446, "step": 128330 }, { "epoch": 0.7628796119621235, "grad_norm": 1.4087095260620117, "learning_rate": 0.00018725968902569463, "loss": 0.6859563827514649, "step": 128340 }, { "epoch": 0.7629390540387919, "grad_norm": 1.3013836145401, "learning_rate": 0.0001872564960799167, "loss": 0.5349557876586915, "step": 128350 }, { "epoch": 0.7629984961154603, "grad_norm": 1.4802695512771606, "learning_rate": 0.000187253302764569, "loss": 0.6947760105133056, "step": 128360 }, { "epoch": 0.7630579381921286, "grad_norm": 1.5664355754852295, "learning_rate": 0.00018725010907966677, "loss": 0.648280143737793, "step": 128370 }, { "epoch": 0.763117380268797, "grad_norm": 1.5419098138809204, "learning_rate": 0.00018724691502522523, "loss": 0.6341510772705078, "step": 128380 }, { "epoch": 0.7631768223454655, "grad_norm": 1.742400884628296, "learning_rate": 0.00018724372060125968, "loss": 0.6890461444854736, "step": 128390 }, { "epoch": 0.7632362644221339, "grad_norm": 1.5255178213119507, "learning_rate": 0.00018724052580778542, "loss": 0.709043025970459, "step": 128400 }, { "epoch": 0.7632957064988023, "grad_norm": 1.7072819471359253, "learning_rate": 0.00018723733064481771, "loss": 0.628076171875, "step": 128410 }, { "epoch": 0.7633551485754706, "grad_norm": 1.925255298614502, "learning_rate": 0.00018723413511237188, "loss": 0.6822163581848144, "step": 128420 }, { "epoch": 0.763414590652139, "grad_norm": 1.6912862062454224, "learning_rate": 0.00018723093921046318, "loss": 0.6521194458007813, "step": 128430 }, { "epoch": 0.7634740327288074, "grad_norm": 1.4808136224746704, "learning_rate": 0.0001872277429391069, "loss": 0.6763804435729981, "step": 128440 }, { "epoch": 0.7635334748054758, "grad_norm": 1.7344883680343628, "learning_rate": 0.00018722454629831835, "loss": 0.6881558895111084, "step": 128450 }, { "epoch": 0.7635929168821441, "grad_norm": 1.907351016998291, "learning_rate": 0.0001872213492881128, "loss": 0.760089111328125, "step": 128460 }, { "epoch": 0.7636523589588126, "grad_norm": 1.9487088918685913, "learning_rate": 0.00018721815190850553, "loss": 0.6618482589721679, "step": 128470 }, { "epoch": 0.763711801035481, "grad_norm": 1.8164787292480469, "learning_rate": 0.0001872149541595119, "loss": 0.6886582374572754, "step": 128480 }, { "epoch": 0.7637712431121494, "grad_norm": 1.6868929862976074, "learning_rate": 0.00018721175604114715, "loss": 0.6768523216247558, "step": 128490 }, { "epoch": 0.7638306851888178, "grad_norm": 1.6302138566970825, "learning_rate": 0.00018720855755342656, "loss": 0.6447846412658691, "step": 128500 }, { "epoch": 0.7638901272654861, "grad_norm": 1.8114815950393677, "learning_rate": 0.00018720535869636552, "loss": 0.622988224029541, "step": 128510 }, { "epoch": 0.7639495693421545, "grad_norm": 1.3414911031723022, "learning_rate": 0.00018720215946997921, "loss": 0.614159107208252, "step": 128520 }, { "epoch": 0.7640090114188229, "grad_norm": 1.463188886642456, "learning_rate": 0.00018719895987428305, "loss": 0.6273331642150879, "step": 128530 }, { "epoch": 0.7640684534954914, "grad_norm": 1.7215992212295532, "learning_rate": 0.00018719575990929226, "loss": 0.6787840843200683, "step": 128540 }, { "epoch": 0.7641278955721597, "grad_norm": 1.7181203365325928, "learning_rate": 0.0001871925595750222, "loss": 0.6456439971923829, "step": 128550 }, { "epoch": 0.7641873376488281, "grad_norm": 1.6171571016311646, "learning_rate": 0.00018718935887148818, "loss": 0.6838137626647949, "step": 128560 }, { "epoch": 0.7642467797254965, "grad_norm": 1.9534024000167847, "learning_rate": 0.00018718615779870546, "loss": 0.6550777435302735, "step": 128570 }, { "epoch": 0.7643062218021649, "grad_norm": 1.6476337909698486, "learning_rate": 0.0001871829563566894, "loss": 0.6338386535644531, "step": 128580 }, { "epoch": 0.7643656638788333, "grad_norm": 1.695133090019226, "learning_rate": 0.00018717975454545532, "loss": 0.665162181854248, "step": 128590 }, { "epoch": 0.7644251059555016, "grad_norm": 1.618016004562378, "learning_rate": 0.00018717655236501847, "loss": 0.7332795143127442, "step": 128600 }, { "epoch": 0.76448454803217, "grad_norm": 1.6282272338867188, "learning_rate": 0.00018717334981539424, "loss": 0.6205733776092529, "step": 128610 }, { "epoch": 0.7645439901088384, "grad_norm": 1.5420104265213013, "learning_rate": 0.00018717014689659793, "loss": 0.6185848712921143, "step": 128620 }, { "epoch": 0.7646034321855069, "grad_norm": 1.8178150653839111, "learning_rate": 0.00018716694360864484, "loss": 0.696810531616211, "step": 128630 }, { "epoch": 0.7646628742621753, "grad_norm": 1.7410457134246826, "learning_rate": 0.00018716373995155035, "loss": 0.595344877243042, "step": 128640 }, { "epoch": 0.7647223163388436, "grad_norm": 1.8327257633209229, "learning_rate": 0.00018716053592532969, "loss": 0.6591005325317383, "step": 128650 }, { "epoch": 0.764781758415512, "grad_norm": 1.5926529169082642, "learning_rate": 0.00018715733152999828, "loss": 0.5927859306335449, "step": 128660 }, { "epoch": 0.7648412004921804, "grad_norm": 1.7876108884811401, "learning_rate": 0.0001871541267655714, "loss": 0.5914698600769043, "step": 128670 }, { "epoch": 0.7649006425688488, "grad_norm": 1.791977047920227, "learning_rate": 0.0001871509216320644, "loss": 0.698802900314331, "step": 128680 }, { "epoch": 0.7649600846455171, "grad_norm": 1.4435629844665527, "learning_rate": 0.0001871477161294926, "loss": 0.6673340797424316, "step": 128690 }, { "epoch": 0.7650195267221855, "grad_norm": 1.993085265159607, "learning_rate": 0.0001871445102578713, "loss": 0.671574068069458, "step": 128700 }, { "epoch": 0.765078968798854, "grad_norm": 1.6822330951690674, "learning_rate": 0.00018714130401721596, "loss": 0.6118923187255859, "step": 128710 }, { "epoch": 0.7651384108755224, "grad_norm": 1.7363256216049194, "learning_rate": 0.00018713809740754175, "loss": 0.6446422100067138, "step": 128720 }, { "epoch": 0.7651978529521908, "grad_norm": 1.842374563217163, "learning_rate": 0.00018713489042886415, "loss": 0.6886653900146484, "step": 128730 }, { "epoch": 0.7652572950288591, "grad_norm": 1.9718881845474243, "learning_rate": 0.0001871316830811984, "loss": 0.6537096977233887, "step": 128740 }, { "epoch": 0.7653167371055275, "grad_norm": 1.7881780862808228, "learning_rate": 0.0001871284753645599, "loss": 0.675861406326294, "step": 128750 }, { "epoch": 0.7653761791821959, "grad_norm": 1.5701398849487305, "learning_rate": 0.00018712526727896397, "loss": 0.6601325035095215, "step": 128760 }, { "epoch": 0.7654356212588643, "grad_norm": 1.3160700798034668, "learning_rate": 0.000187122058824426, "loss": 0.6206563949584961, "step": 128770 }, { "epoch": 0.7654950633355327, "grad_norm": 2.148691177368164, "learning_rate": 0.00018711885000096125, "loss": 0.6353668689727783, "step": 128780 }, { "epoch": 0.765554505412201, "grad_norm": 2.8302550315856934, "learning_rate": 0.00018711564080858516, "loss": 0.6484872817993164, "step": 128790 }, { "epoch": 0.7656139474888695, "grad_norm": 1.9645413160324097, "learning_rate": 0.00018711243124731305, "loss": 0.6598121166229248, "step": 128800 }, { "epoch": 0.7656733895655379, "grad_norm": 1.7999893426895142, "learning_rate": 0.00018710922131716024, "loss": 0.7035019874572754, "step": 128810 }, { "epoch": 0.7657328316422063, "grad_norm": 1.7072267532348633, "learning_rate": 0.00018710601101814216, "loss": 0.6763724327087403, "step": 128820 }, { "epoch": 0.7657922737188746, "grad_norm": 1.2645059823989868, "learning_rate": 0.0001871028003502741, "loss": 0.6282205581665039, "step": 128830 }, { "epoch": 0.765851715795543, "grad_norm": 1.7629002332687378, "learning_rate": 0.00018709958931357144, "loss": 0.6640019416809082, "step": 128840 }, { "epoch": 0.7659111578722114, "grad_norm": 1.4014174938201904, "learning_rate": 0.00018709637790804954, "loss": 0.6482599258422852, "step": 128850 }, { "epoch": 0.7659705999488798, "grad_norm": 1.7695573568344116, "learning_rate": 0.00018709316613372377, "loss": 0.6966547012329102, "step": 128860 }, { "epoch": 0.7660300420255483, "grad_norm": 1.4678846597671509, "learning_rate": 0.00018708995399060947, "loss": 0.6074314117431641, "step": 128870 }, { "epoch": 0.7660894841022166, "grad_norm": 1.5752806663513184, "learning_rate": 0.00018708674147872203, "loss": 0.6558004379272461, "step": 128880 }, { "epoch": 0.766148926178885, "grad_norm": 1.9700875282287598, "learning_rate": 0.00018708352859807682, "loss": 0.643730640411377, "step": 128890 }, { "epoch": 0.7662083682555534, "grad_norm": 1.4472615718841553, "learning_rate": 0.00018708031534868917, "loss": 0.6480024337768555, "step": 128900 }, { "epoch": 0.7662678103322218, "grad_norm": 1.567406177520752, "learning_rate": 0.00018707710173057452, "loss": 0.712153148651123, "step": 128910 }, { "epoch": 0.7663272524088901, "grad_norm": 1.3533567190170288, "learning_rate": 0.0001870738877437482, "loss": 0.6790081024169922, "step": 128920 }, { "epoch": 0.7663866944855585, "grad_norm": 1.504836916923523, "learning_rate": 0.00018707067338822556, "loss": 0.6429457187652587, "step": 128930 }, { "epoch": 0.7664461365622269, "grad_norm": 1.4731100797653198, "learning_rate": 0.000187067458664022, "loss": 0.6642658710479736, "step": 128940 }, { "epoch": 0.7665055786388953, "grad_norm": 1.7800201177597046, "learning_rate": 0.00018706424357115296, "loss": 0.673114538192749, "step": 128950 }, { "epoch": 0.7665650207155638, "grad_norm": 2.2133898735046387, "learning_rate": 0.0001870610281096337, "loss": 0.6938320159912109, "step": 128960 }, { "epoch": 0.7666244627922321, "grad_norm": 2.001725673675537, "learning_rate": 0.0001870578122794797, "loss": 0.64810209274292, "step": 128970 }, { "epoch": 0.7666839048689005, "grad_norm": 1.4434542655944824, "learning_rate": 0.00018705459608070633, "loss": 0.7113161563873291, "step": 128980 }, { "epoch": 0.7667433469455689, "grad_norm": 1.4296340942382812, "learning_rate": 0.00018705137951332895, "loss": 0.6248543739318848, "step": 128990 }, { "epoch": 0.7668027890222373, "grad_norm": 1.547805666923523, "learning_rate": 0.0001870481625773629, "loss": 0.6188135147094727, "step": 129000 }, { "epoch": 0.7668622310989057, "grad_norm": 1.5740710496902466, "learning_rate": 0.00018704494527282365, "loss": 0.5919474124908447, "step": 129010 }, { "epoch": 0.766921673175574, "grad_norm": 1.586256980895996, "learning_rate": 0.00018704172759972658, "loss": 0.6697477340698242, "step": 129020 }, { "epoch": 0.7669811152522424, "grad_norm": 1.5107717514038086, "learning_rate": 0.00018703850955808704, "loss": 0.701612138748169, "step": 129030 }, { "epoch": 0.7670405573289109, "grad_norm": 1.5712255239486694, "learning_rate": 0.00018703529114792047, "loss": 0.6941050052642822, "step": 129040 }, { "epoch": 0.7670999994055793, "grad_norm": 2.1477267742156982, "learning_rate": 0.0001870320723692422, "loss": 0.7085903644561767, "step": 129050 }, { "epoch": 0.7671594414822476, "grad_norm": 2.055241346359253, "learning_rate": 0.00018702885322206768, "loss": 0.652100944519043, "step": 129060 }, { "epoch": 0.767218883558916, "grad_norm": 1.6933687925338745, "learning_rate": 0.00018702563370641233, "loss": 0.6708540916442871, "step": 129070 }, { "epoch": 0.7672783256355844, "grad_norm": 2.0339818000793457, "learning_rate": 0.0001870224138222915, "loss": 0.7072715282440185, "step": 129080 }, { "epoch": 0.7673377677122528, "grad_norm": 1.8165441751480103, "learning_rate": 0.00018701919356972063, "loss": 0.6634032249450683, "step": 129090 }, { "epoch": 0.7673972097889212, "grad_norm": 1.5656996965408325, "learning_rate": 0.00018701597294871507, "loss": 0.6836284637451172, "step": 129100 }, { "epoch": 0.7674566518655895, "grad_norm": 1.4956611394882202, "learning_rate": 0.0001870127519592903, "loss": 0.6079297065734863, "step": 129110 }, { "epoch": 0.767516093942258, "grad_norm": 1.5650290250778198, "learning_rate": 0.0001870095306014617, "loss": 0.6910761833190918, "step": 129120 }, { "epoch": 0.7675755360189264, "grad_norm": 1.7107508182525635, "learning_rate": 0.00018700630887524464, "loss": 0.6876105308532715, "step": 129130 }, { "epoch": 0.7676349780955948, "grad_norm": 1.3954741954803467, "learning_rate": 0.00018700308678065456, "loss": 0.6896608829498291, "step": 129140 }, { "epoch": 0.7676944201722632, "grad_norm": 1.2668136358261108, "learning_rate": 0.0001869998643177069, "loss": 0.5814701557159424, "step": 129150 }, { "epoch": 0.7677538622489315, "grad_norm": 1.3120691776275635, "learning_rate": 0.00018699664148641706, "loss": 0.6456530570983887, "step": 129160 }, { "epoch": 0.7678133043255999, "grad_norm": 1.7622630596160889, "learning_rate": 0.00018699341828680045, "loss": 0.6650618553161621, "step": 129170 }, { "epoch": 0.7678727464022683, "grad_norm": 1.6472607851028442, "learning_rate": 0.00018699019471887248, "loss": 0.609773826599121, "step": 129180 }, { "epoch": 0.7679321884789367, "grad_norm": 1.5943732261657715, "learning_rate": 0.00018698697078264857, "loss": 0.6975417137145996, "step": 129190 }, { "epoch": 0.767991630555605, "grad_norm": 1.7245341539382935, "learning_rate": 0.00018698374647814416, "loss": 0.7197839260101319, "step": 129200 }, { "epoch": 0.7680510726322735, "grad_norm": 1.9711614847183228, "learning_rate": 0.00018698052180537465, "loss": 0.5859275817871094, "step": 129210 }, { "epoch": 0.7681105147089419, "grad_norm": 1.5862065553665161, "learning_rate": 0.0001869772967643555, "loss": 0.6769744873046875, "step": 129220 }, { "epoch": 0.7681699567856103, "grad_norm": 2.1606454849243164, "learning_rate": 0.00018697407135510213, "loss": 0.6554001808166504, "step": 129230 }, { "epoch": 0.7682293988622787, "grad_norm": 2.476891040802002, "learning_rate": 0.00018697084557762995, "loss": 0.6157667160034179, "step": 129240 }, { "epoch": 0.768288840938947, "grad_norm": 1.4445101022720337, "learning_rate": 0.00018696761943195437, "loss": 0.6758195877075195, "step": 129250 }, { "epoch": 0.7683482830156154, "grad_norm": 1.9087772369384766, "learning_rate": 0.00018696439291809088, "loss": 0.6964782238006592, "step": 129260 }, { "epoch": 0.7684077250922838, "grad_norm": 2.2561440467834473, "learning_rate": 0.0001869611660360549, "loss": 0.7106753349304199, "step": 129270 }, { "epoch": 0.7684671671689522, "grad_norm": 1.4952718019485474, "learning_rate": 0.00018695793878586184, "loss": 0.6908088684082031, "step": 129280 }, { "epoch": 0.7685266092456206, "grad_norm": 1.6366013288497925, "learning_rate": 0.00018695471116752713, "loss": 0.6919407844543457, "step": 129290 }, { "epoch": 0.768586051322289, "grad_norm": 1.6025631427764893, "learning_rate": 0.00018695148318106624, "loss": 0.6450598239898682, "step": 129300 }, { "epoch": 0.7686454933989574, "grad_norm": 1.2631803750991821, "learning_rate": 0.0001869482548264946, "loss": 0.6036056041717529, "step": 129310 }, { "epoch": 0.7687049354756258, "grad_norm": 1.7121107578277588, "learning_rate": 0.00018694502610382767, "loss": 0.6513971328735352, "step": 129320 }, { "epoch": 0.7687643775522942, "grad_norm": 1.739776849746704, "learning_rate": 0.00018694179701308084, "loss": 0.6859416961669922, "step": 129330 }, { "epoch": 0.7688238196289625, "grad_norm": 1.4096264839172363, "learning_rate": 0.00018693856755426966, "loss": 0.6592289924621582, "step": 129340 }, { "epoch": 0.7688832617056309, "grad_norm": 2.2383463382720947, "learning_rate": 0.00018693533772740949, "loss": 0.705349349975586, "step": 129350 }, { "epoch": 0.7689427037822993, "grad_norm": 1.7525845766067505, "learning_rate": 0.0001869321075325158, "loss": 0.6957025527954102, "step": 129360 }, { "epoch": 0.7690021458589678, "grad_norm": 1.7376497983932495, "learning_rate": 0.00018692887696960406, "loss": 0.6697828292846679, "step": 129370 }, { "epoch": 0.7690615879356362, "grad_norm": 1.8159618377685547, "learning_rate": 0.00018692564603868972, "loss": 0.7086137771606446, "step": 129380 }, { "epoch": 0.7691210300123045, "grad_norm": 1.28458833694458, "learning_rate": 0.00018692241473978823, "loss": 0.6616373062133789, "step": 129390 }, { "epoch": 0.7691804720889729, "grad_norm": 1.5843982696533203, "learning_rate": 0.000186919183072915, "loss": 0.611722469329834, "step": 129400 }, { "epoch": 0.7692399141656413, "grad_norm": 1.7376188039779663, "learning_rate": 0.00018691595103808559, "loss": 0.6583099365234375, "step": 129410 }, { "epoch": 0.7692993562423097, "grad_norm": 1.342284083366394, "learning_rate": 0.00018691271863531536, "loss": 0.6782196521759033, "step": 129420 }, { "epoch": 0.769358798318978, "grad_norm": 1.592742681503296, "learning_rate": 0.00018690948586461985, "loss": 0.6046149253845214, "step": 129430 }, { "epoch": 0.7694182403956464, "grad_norm": 1.372891902923584, "learning_rate": 0.0001869062527260145, "loss": 0.6553791046142579, "step": 129440 }, { "epoch": 0.7694776824723149, "grad_norm": 1.496759057044983, "learning_rate": 0.00018690301921951477, "loss": 0.7106026172637939, "step": 129450 }, { "epoch": 0.7695371245489833, "grad_norm": 1.6196807622909546, "learning_rate": 0.0001868997853451361, "loss": 0.690244197845459, "step": 129460 }, { "epoch": 0.7695965666256517, "grad_norm": 1.7824419736862183, "learning_rate": 0.000186896551102894, "loss": 0.6216862201690674, "step": 129470 }, { "epoch": 0.76965600870232, "grad_norm": 2.0977957248687744, "learning_rate": 0.00018689331649280393, "loss": 0.6984129428863526, "step": 129480 }, { "epoch": 0.7697154507789884, "grad_norm": 1.747830867767334, "learning_rate": 0.0001868900815148814, "loss": 0.6688212871551513, "step": 129490 }, { "epoch": 0.7697748928556568, "grad_norm": 1.669379711151123, "learning_rate": 0.0001868868461691418, "loss": 0.6648674011230469, "step": 129500 }, { "epoch": 0.7698343349323252, "grad_norm": 1.8183372020721436, "learning_rate": 0.00018688361045560067, "loss": 0.6888913631439209, "step": 129510 }, { "epoch": 0.7698937770089936, "grad_norm": 1.9685490131378174, "learning_rate": 0.00018688037437427347, "loss": 0.6941886901855469, "step": 129520 }, { "epoch": 0.7699532190856619, "grad_norm": 1.6580679416656494, "learning_rate": 0.00018687713792517568, "loss": 0.6899094581604004, "step": 129530 }, { "epoch": 0.7700126611623304, "grad_norm": 1.3210673332214355, "learning_rate": 0.0001868739011083228, "loss": 0.6715371131896972, "step": 129540 }, { "epoch": 0.7700721032389988, "grad_norm": 1.6764891147613525, "learning_rate": 0.0001868706639237303, "loss": 0.7161829948425293, "step": 129550 }, { "epoch": 0.7701315453156672, "grad_norm": 1.657678484916687, "learning_rate": 0.00018686742637141366, "loss": 0.6330467224121094, "step": 129560 }, { "epoch": 0.7701909873923355, "grad_norm": 1.8221158981323242, "learning_rate": 0.00018686418845138838, "loss": 0.6479379653930664, "step": 129570 }, { "epoch": 0.7702504294690039, "grad_norm": 1.370944619178772, "learning_rate": 0.00018686095016366992, "loss": 0.5849325656890869, "step": 129580 }, { "epoch": 0.7703098715456723, "grad_norm": 1.770216703414917, "learning_rate": 0.00018685771150827384, "loss": 0.688343858718872, "step": 129590 }, { "epoch": 0.7703693136223407, "grad_norm": 1.6597957611083984, "learning_rate": 0.00018685447248521553, "loss": 0.645658016204834, "step": 129600 }, { "epoch": 0.7704287556990091, "grad_norm": 2.1897542476654053, "learning_rate": 0.00018685123309451055, "loss": 0.7129199981689454, "step": 129610 }, { "epoch": 0.7704881977756775, "grad_norm": 1.5919055938720703, "learning_rate": 0.0001868479933361744, "loss": 0.6576554298400878, "step": 129620 }, { "epoch": 0.7705476398523459, "grad_norm": 1.5443662405014038, "learning_rate": 0.00018684475321022257, "loss": 0.6290163993835449, "step": 129630 }, { "epoch": 0.7706070819290143, "grad_norm": 1.7661044597625732, "learning_rate": 0.00018684151271667053, "loss": 0.5880204200744629, "step": 129640 }, { "epoch": 0.7706665240056827, "grad_norm": 1.588903784751892, "learning_rate": 0.00018683827185553384, "loss": 0.6008466720581055, "step": 129650 }, { "epoch": 0.770725966082351, "grad_norm": 1.5000534057617188, "learning_rate": 0.00018683503062682795, "loss": 0.6290400505065918, "step": 129660 }, { "epoch": 0.7707854081590194, "grad_norm": 1.5158348083496094, "learning_rate": 0.00018683178903056838, "loss": 0.6926284313201905, "step": 129670 }, { "epoch": 0.7708448502356878, "grad_norm": 2.4200656414031982, "learning_rate": 0.00018682854706677062, "loss": 0.6691681861877441, "step": 129680 }, { "epoch": 0.7709042923123562, "grad_norm": 1.9921987056732178, "learning_rate": 0.00018682530473545023, "loss": 0.6826366424560547, "step": 129690 }, { "epoch": 0.7709637343890247, "grad_norm": 1.7719050645828247, "learning_rate": 0.0001868220620366227, "loss": 0.6414929389953613, "step": 129700 }, { "epoch": 0.771023176465693, "grad_norm": 1.7159229516983032, "learning_rate": 0.00018681881897030352, "loss": 0.595697546005249, "step": 129710 }, { "epoch": 0.7710826185423614, "grad_norm": 1.321882724761963, "learning_rate": 0.00018681557553650816, "loss": 0.6377654075622559, "step": 129720 }, { "epoch": 0.7711420606190298, "grad_norm": 1.7489230632781982, "learning_rate": 0.00018681233173525226, "loss": 0.5938595294952392, "step": 129730 }, { "epoch": 0.7712015026956982, "grad_norm": 1.3779679536819458, "learning_rate": 0.00018680908756655125, "loss": 0.6224344730377197, "step": 129740 }, { "epoch": 0.7712609447723666, "grad_norm": 1.4528611898422241, "learning_rate": 0.00018680584303042066, "loss": 0.6498357772827148, "step": 129750 }, { "epoch": 0.7713203868490349, "grad_norm": 1.4754866361618042, "learning_rate": 0.000186802598126876, "loss": 0.6393217086791992, "step": 129760 }, { "epoch": 0.7713798289257033, "grad_norm": 1.5173310041427612, "learning_rate": 0.00018679935285593284, "loss": 0.6512395858764648, "step": 129770 }, { "epoch": 0.7714392710023718, "grad_norm": 1.620296597480774, "learning_rate": 0.00018679610721760668, "loss": 0.6429819107055664, "step": 129780 }, { "epoch": 0.7714987130790402, "grad_norm": 1.5915374755859375, "learning_rate": 0.000186792861211913, "loss": 0.6706966400146485, "step": 129790 }, { "epoch": 0.7715581551557085, "grad_norm": 1.8689402341842651, "learning_rate": 0.0001867896148388674, "loss": 0.7055279731750488, "step": 129800 }, { "epoch": 0.7716175972323769, "grad_norm": 1.5163359642028809, "learning_rate": 0.00018678636809848538, "loss": 0.6368406295776368, "step": 129810 }, { "epoch": 0.7716770393090453, "grad_norm": 1.7611044645309448, "learning_rate": 0.00018678312099078246, "loss": 0.7183023452758789, "step": 129820 }, { "epoch": 0.7717364813857137, "grad_norm": 1.7646452188491821, "learning_rate": 0.00018677987351577415, "loss": 0.653076457977295, "step": 129830 }, { "epoch": 0.7717959234623821, "grad_norm": 1.946275234222412, "learning_rate": 0.00018677662567347604, "loss": 0.6764961242675781, "step": 129840 }, { "epoch": 0.7718553655390504, "grad_norm": 1.6418684720993042, "learning_rate": 0.0001867733774639037, "loss": 0.6395253658294677, "step": 129850 }, { "epoch": 0.7719148076157188, "grad_norm": 1.842002034187317, "learning_rate": 0.00018677012888707254, "loss": 0.649547529220581, "step": 129860 }, { "epoch": 0.7719742496923873, "grad_norm": 1.610668420791626, "learning_rate": 0.0001867668799429982, "loss": 0.6836228370666504, "step": 129870 }, { "epoch": 0.7720336917690557, "grad_norm": 1.9251517057418823, "learning_rate": 0.00018676363063169617, "loss": 0.669527244567871, "step": 129880 }, { "epoch": 0.7720931338457241, "grad_norm": 1.7289012670516968, "learning_rate": 0.00018676038095318207, "loss": 0.6572851657867431, "step": 129890 }, { "epoch": 0.7721525759223924, "grad_norm": 1.5539004802703857, "learning_rate": 0.00018675713090747135, "loss": 0.6507913589477539, "step": 129900 }, { "epoch": 0.7722120179990608, "grad_norm": 1.3438899517059326, "learning_rate": 0.0001867538804945796, "loss": 0.6805341243743896, "step": 129910 }, { "epoch": 0.7722714600757292, "grad_norm": 1.5653245449066162, "learning_rate": 0.00018675062971452237, "loss": 0.6418035507202149, "step": 129920 }, { "epoch": 0.7723309021523976, "grad_norm": 1.6283721923828125, "learning_rate": 0.00018674737856731524, "loss": 0.6683232307434082, "step": 129930 }, { "epoch": 0.7723903442290659, "grad_norm": 1.8210009336471558, "learning_rate": 0.00018674412705297372, "loss": 0.639985466003418, "step": 129940 }, { "epoch": 0.7724497863057344, "grad_norm": 1.7997287511825562, "learning_rate": 0.00018674087517151335, "loss": 0.65252685546875, "step": 129950 }, { "epoch": 0.7725092283824028, "grad_norm": 1.3215633630752563, "learning_rate": 0.00018673762292294974, "loss": 0.6750842094421386, "step": 129960 }, { "epoch": 0.7725686704590712, "grad_norm": 2.2439379692077637, "learning_rate": 0.00018673437030729842, "loss": 0.6504909992218018, "step": 129970 }, { "epoch": 0.7726281125357396, "grad_norm": 1.6442610025405884, "learning_rate": 0.0001867311173245749, "loss": 0.6971240520477295, "step": 129980 }, { "epoch": 0.7726875546124079, "grad_norm": 1.6096906661987305, "learning_rate": 0.00018672786397479484, "loss": 0.6615097522735596, "step": 129990 }, { "epoch": 0.7727469966890763, "grad_norm": 1.7481473684310913, "learning_rate": 0.00018672461025797378, "loss": 0.6875029563903808, "step": 130000 }, { "epoch": 0.7728064387657447, "grad_norm": 1.668289065361023, "learning_rate": 0.0001867213561741272, "loss": 0.6198795318603516, "step": 130010 }, { "epoch": 0.7728658808424131, "grad_norm": 1.63810133934021, "learning_rate": 0.00018671810172327073, "loss": 0.6153207778930664, "step": 130020 }, { "epoch": 0.7729253229190814, "grad_norm": 1.569288730621338, "learning_rate": 0.00018671484690542, "loss": 0.7019833564758301, "step": 130030 }, { "epoch": 0.7729847649957499, "grad_norm": 1.4592559337615967, "learning_rate": 0.00018671159172059044, "loss": 0.676953935623169, "step": 130040 }, { "epoch": 0.7730442070724183, "grad_norm": 1.9897514581680298, "learning_rate": 0.00018670833616879772, "loss": 0.7099337577819824, "step": 130050 }, { "epoch": 0.7731036491490867, "grad_norm": 1.63428795337677, "learning_rate": 0.00018670508025005737, "loss": 0.5973424911499023, "step": 130060 }, { "epoch": 0.7731630912257551, "grad_norm": 1.8970603942871094, "learning_rate": 0.00018670182396438503, "loss": 0.675051498413086, "step": 130070 }, { "epoch": 0.7732225333024234, "grad_norm": 1.488396406173706, "learning_rate": 0.00018669856731179618, "loss": 0.6440230369567871, "step": 130080 }, { "epoch": 0.7732819753790918, "grad_norm": 1.8219900131225586, "learning_rate": 0.00018669531029230646, "loss": 0.6351998329162598, "step": 130090 }, { "epoch": 0.7733414174557602, "grad_norm": 1.8643282651901245, "learning_rate": 0.00018669205290593145, "loss": 0.6599098205566406, "step": 130100 }, { "epoch": 0.7734008595324287, "grad_norm": 1.6544970273971558, "learning_rate": 0.00018668879515268674, "loss": 0.6563393592834472, "step": 130110 }, { "epoch": 0.7734603016090971, "grad_norm": 1.6615699529647827, "learning_rate": 0.00018668553703258785, "loss": 0.7113341331481934, "step": 130120 }, { "epoch": 0.7735197436857654, "grad_norm": 1.2794349193572998, "learning_rate": 0.00018668227854565047, "loss": 0.6433505058288574, "step": 130130 }, { "epoch": 0.7735791857624338, "grad_norm": 2.162999391555786, "learning_rate": 0.00018667901969189008, "loss": 0.7154109477996826, "step": 130140 }, { "epoch": 0.7736386278391022, "grad_norm": 1.557213306427002, "learning_rate": 0.00018667576047132236, "loss": 0.6184406280517578, "step": 130150 }, { "epoch": 0.7736980699157706, "grad_norm": 1.9322117567062378, "learning_rate": 0.0001866725008839628, "loss": 0.7111341476440429, "step": 130160 }, { "epoch": 0.7737575119924389, "grad_norm": 1.7414642572402954, "learning_rate": 0.00018666924092982713, "loss": 0.6374341964721679, "step": 130170 }, { "epoch": 0.7738169540691073, "grad_norm": 1.397322654724121, "learning_rate": 0.0001866659806089308, "loss": 0.6326066017150879, "step": 130180 }, { "epoch": 0.7738763961457757, "grad_norm": 1.8000704050064087, "learning_rate": 0.00018666271992128953, "loss": 0.7083990097045898, "step": 130190 }, { "epoch": 0.7739358382224442, "grad_norm": 2.0460352897644043, "learning_rate": 0.00018665945886691882, "loss": 0.7294686794281006, "step": 130200 }, { "epoch": 0.7739952802991126, "grad_norm": 1.585760235786438, "learning_rate": 0.0001866561974458343, "loss": 0.6436972618103027, "step": 130210 }, { "epoch": 0.7740547223757809, "grad_norm": 1.8889514207839966, "learning_rate": 0.00018665293565805162, "loss": 0.6596839904785157, "step": 130220 }, { "epoch": 0.7741141644524493, "grad_norm": 1.7678903341293335, "learning_rate": 0.00018664967350358634, "loss": 0.6921077728271484, "step": 130230 }, { "epoch": 0.7741736065291177, "grad_norm": 1.5604946613311768, "learning_rate": 0.00018664641098245407, "loss": 0.5880232810974121, "step": 130240 }, { "epoch": 0.7742330486057861, "grad_norm": 1.8198550939559937, "learning_rate": 0.00018664314809467043, "loss": 0.6707720756530762, "step": 130250 }, { "epoch": 0.7742924906824545, "grad_norm": 1.666939377784729, "learning_rate": 0.00018663988484025098, "loss": 0.6309847831726074, "step": 130260 }, { "epoch": 0.7743519327591228, "grad_norm": 2.2742743492126465, "learning_rate": 0.00018663662121921136, "loss": 0.6475956439971924, "step": 130270 }, { "epoch": 0.7744113748357913, "grad_norm": 2.416524887084961, "learning_rate": 0.00018663335723156726, "loss": 0.6811382293701171, "step": 130280 }, { "epoch": 0.7744708169124597, "grad_norm": 1.5106374025344849, "learning_rate": 0.00018663009287733418, "loss": 0.6239390850067139, "step": 130290 }, { "epoch": 0.7745302589891281, "grad_norm": 2.105435609817505, "learning_rate": 0.00018662682815652777, "loss": 0.7030926704406738, "step": 130300 }, { "epoch": 0.7745897010657964, "grad_norm": 1.620424509048462, "learning_rate": 0.00018662356306916366, "loss": 0.6377348899841309, "step": 130310 }, { "epoch": 0.7746491431424648, "grad_norm": 1.3833452463150024, "learning_rate": 0.00018662029761525747, "loss": 0.6433558940887452, "step": 130320 }, { "epoch": 0.7747085852191332, "grad_norm": 1.389632225036621, "learning_rate": 0.0001866170317948248, "loss": 0.6863187789916992, "step": 130330 }, { "epoch": 0.7747680272958016, "grad_norm": 1.9152804613113403, "learning_rate": 0.00018661376560788134, "loss": 0.7037761688232422, "step": 130340 }, { "epoch": 0.77482746937247, "grad_norm": 1.3462177515029907, "learning_rate": 0.0001866104990544426, "loss": 0.6514932632446289, "step": 130350 }, { "epoch": 0.7748869114491383, "grad_norm": 1.8314309120178223, "learning_rate": 0.0001866072321345243, "loss": 0.6706198692321778, "step": 130360 }, { "epoch": 0.7749463535258068, "grad_norm": 1.8487725257873535, "learning_rate": 0.00018660396484814203, "loss": 0.669789171218872, "step": 130370 }, { "epoch": 0.7750057956024752, "grad_norm": 2.4727771282196045, "learning_rate": 0.00018660069719531145, "loss": 0.6599814891815186, "step": 130380 }, { "epoch": 0.7750652376791436, "grad_norm": 1.2710247039794922, "learning_rate": 0.00018659742917604812, "loss": 0.6606018543243408, "step": 130390 }, { "epoch": 0.7751246797558119, "grad_norm": 1.3092418909072876, "learning_rate": 0.00018659416079036778, "loss": 0.6869834899902344, "step": 130400 }, { "epoch": 0.7751841218324803, "grad_norm": 1.7779337167739868, "learning_rate": 0.00018659089203828597, "loss": 0.6677806854248047, "step": 130410 }, { "epoch": 0.7752435639091487, "grad_norm": 1.5316041707992554, "learning_rate": 0.00018658762291981834, "loss": 0.6670400619506835, "step": 130420 }, { "epoch": 0.7753030059858171, "grad_norm": 1.4856826066970825, "learning_rate": 0.0001865843534349806, "loss": 0.6692485809326172, "step": 130430 }, { "epoch": 0.7753624480624856, "grad_norm": 1.5871093273162842, "learning_rate": 0.0001865810835837883, "loss": 0.7055118083953857, "step": 130440 }, { "epoch": 0.7754218901391539, "grad_norm": 1.9087036848068237, "learning_rate": 0.00018657781336625716, "loss": 0.6519445419311524, "step": 130450 }, { "epoch": 0.7754813322158223, "grad_norm": 1.4897722005844116, "learning_rate": 0.00018657454278240277, "loss": 0.6132684707641601, "step": 130460 }, { "epoch": 0.7755407742924907, "grad_norm": 1.9327679872512817, "learning_rate": 0.00018657127183224079, "loss": 0.6986844539642334, "step": 130470 }, { "epoch": 0.7756002163691591, "grad_norm": 1.540235161781311, "learning_rate": 0.00018656800051578687, "loss": 0.7051410675048828, "step": 130480 }, { "epoch": 0.7756596584458275, "grad_norm": 1.7343273162841797, "learning_rate": 0.00018656472883305666, "loss": 0.6732269287109375, "step": 130490 }, { "epoch": 0.7757191005224958, "grad_norm": 2.0267748832702637, "learning_rate": 0.0001865614567840658, "loss": 0.6456974983215332, "step": 130500 }, { "epoch": 0.7757785425991642, "grad_norm": 1.8672337532043457, "learning_rate": 0.00018655818436882996, "loss": 0.711247444152832, "step": 130510 }, { "epoch": 0.7758379846758326, "grad_norm": 1.5695194005966187, "learning_rate": 0.0001865549115873648, "loss": 0.6513197898864747, "step": 130520 }, { "epoch": 0.7758974267525011, "grad_norm": 1.3526005744934082, "learning_rate": 0.00018655163843968596, "loss": 0.6824112415313721, "step": 130530 }, { "epoch": 0.7759568688291694, "grad_norm": 1.7783474922180176, "learning_rate": 0.00018654836492580908, "loss": 0.6962718963623047, "step": 130540 }, { "epoch": 0.7760163109058378, "grad_norm": 1.8972663879394531, "learning_rate": 0.0001865450910457498, "loss": 0.6355092525482178, "step": 130550 }, { "epoch": 0.7760757529825062, "grad_norm": 1.9582685232162476, "learning_rate": 0.0001865418167995239, "loss": 0.6779270172119141, "step": 130560 }, { "epoch": 0.7761351950591746, "grad_norm": 1.8363279104232788, "learning_rate": 0.0001865385421871469, "loss": 0.7136495590209961, "step": 130570 }, { "epoch": 0.776194637135843, "grad_norm": 1.3014674186706543, "learning_rate": 0.0001865352672086346, "loss": 0.610175371170044, "step": 130580 }, { "epoch": 0.7762540792125113, "grad_norm": 1.6709668636322021, "learning_rate": 0.00018653199186400253, "loss": 0.7338859558105468, "step": 130590 }, { "epoch": 0.7763135212891797, "grad_norm": 1.8422883749008179, "learning_rate": 0.00018652871615326642, "loss": 0.6652003288269043, "step": 130600 }, { "epoch": 0.7763729633658482, "grad_norm": 1.8751431703567505, "learning_rate": 0.00018652544007644197, "loss": 0.6323754787445068, "step": 130610 }, { "epoch": 0.7764324054425166, "grad_norm": 1.9811673164367676, "learning_rate": 0.0001865221636335448, "loss": 0.6809857368469239, "step": 130620 }, { "epoch": 0.776491847519185, "grad_norm": 1.5452662706375122, "learning_rate": 0.00018651888682459064, "loss": 0.6524801254272461, "step": 130630 }, { "epoch": 0.7765512895958533, "grad_norm": 1.6369811296463013, "learning_rate": 0.0001865156096495951, "loss": 0.6301104545593261, "step": 130640 }, { "epoch": 0.7766107316725217, "grad_norm": 1.6737942695617676, "learning_rate": 0.0001865123321085739, "loss": 0.6754871368408203, "step": 130650 }, { "epoch": 0.7766701737491901, "grad_norm": 1.5215951204299927, "learning_rate": 0.0001865090542015427, "loss": 0.6878533363342285, "step": 130660 }, { "epoch": 0.7767296158258585, "grad_norm": 1.4236804246902466, "learning_rate": 0.00018650577592851722, "loss": 0.6799372673034668, "step": 130670 }, { "epoch": 0.7767890579025268, "grad_norm": 2.295879364013672, "learning_rate": 0.00018650249728951307, "loss": 0.6834160804748535, "step": 130680 }, { "epoch": 0.7768484999791953, "grad_norm": 1.9777092933654785, "learning_rate": 0.00018649921828454603, "loss": 0.639006233215332, "step": 130690 }, { "epoch": 0.7769079420558637, "grad_norm": 1.6462548971176147, "learning_rate": 0.00018649593891363167, "loss": 0.6100229740142822, "step": 130700 }, { "epoch": 0.7769673841325321, "grad_norm": 1.6243488788604736, "learning_rate": 0.00018649265917678576, "loss": 0.7458098411560059, "step": 130710 }, { "epoch": 0.7770268262092005, "grad_norm": 1.3558759689331055, "learning_rate": 0.00018648937907402398, "loss": 0.6763626575469971, "step": 130720 }, { "epoch": 0.7770862682858688, "grad_norm": 1.6141797304153442, "learning_rate": 0.000186486098605362, "loss": 0.6679903984069824, "step": 130730 }, { "epoch": 0.7771457103625372, "grad_norm": 1.7659624814987183, "learning_rate": 0.00018648281777081552, "loss": 0.6807115554809571, "step": 130740 }, { "epoch": 0.7772051524392056, "grad_norm": 1.614189863204956, "learning_rate": 0.0001864795365704002, "loss": 0.6517831325531006, "step": 130750 }, { "epoch": 0.777264594515874, "grad_norm": 2.112056255340576, "learning_rate": 0.0001864762550041318, "loss": 0.6184647083282471, "step": 130760 }, { "epoch": 0.7773240365925423, "grad_norm": 1.5898845195770264, "learning_rate": 0.00018647297307202598, "loss": 0.697446632385254, "step": 130770 }, { "epoch": 0.7773834786692108, "grad_norm": 1.5498957633972168, "learning_rate": 0.0001864696907740985, "loss": 0.6469648838043213, "step": 130780 }, { "epoch": 0.7774429207458792, "grad_norm": 1.8368266820907593, "learning_rate": 0.00018646640811036493, "loss": 0.6256213665008545, "step": 130790 }, { "epoch": 0.7775023628225476, "grad_norm": 1.506598949432373, "learning_rate": 0.0001864631250808411, "loss": 0.691338300704956, "step": 130800 }, { "epoch": 0.777561804899216, "grad_norm": 1.6541105508804321, "learning_rate": 0.00018645984168554265, "loss": 0.6975114345550537, "step": 130810 }, { "epoch": 0.7776212469758843, "grad_norm": 1.8610057830810547, "learning_rate": 0.0001864565579244853, "loss": 0.6932216644287109, "step": 130820 }, { "epoch": 0.7776806890525527, "grad_norm": 1.289023995399475, "learning_rate": 0.0001864532737976848, "loss": 0.720381498336792, "step": 130830 }, { "epoch": 0.7777401311292211, "grad_norm": 1.680755853652954, "learning_rate": 0.0001864499893051568, "loss": 0.6371196746826172, "step": 130840 }, { "epoch": 0.7777995732058895, "grad_norm": 1.765669345855713, "learning_rate": 0.00018644670444691703, "loss": 0.6492086410522461, "step": 130850 }, { "epoch": 0.777859015282558, "grad_norm": 1.55441153049469, "learning_rate": 0.0001864434192229812, "loss": 0.6321459770202636, "step": 130860 }, { "epoch": 0.7779184573592263, "grad_norm": 1.6951035261154175, "learning_rate": 0.00018644013363336507, "loss": 0.59648118019104, "step": 130870 }, { "epoch": 0.7779778994358947, "grad_norm": 1.6737427711486816, "learning_rate": 0.0001864368476780843, "loss": 0.6837497234344483, "step": 130880 }, { "epoch": 0.7780373415125631, "grad_norm": 1.7343804836273193, "learning_rate": 0.00018643356135715462, "loss": 0.5968631744384766, "step": 130890 }, { "epoch": 0.7780967835892315, "grad_norm": 1.5152337551116943, "learning_rate": 0.0001864302746705918, "loss": 0.6597848892211914, "step": 130900 }, { "epoch": 0.7781562256658998, "grad_norm": 1.2890832424163818, "learning_rate": 0.00018642698761841146, "loss": 0.6054847240447998, "step": 130910 }, { "epoch": 0.7782156677425682, "grad_norm": 1.3597859144210815, "learning_rate": 0.00018642370020062943, "loss": 0.6321304321289063, "step": 130920 }, { "epoch": 0.7782751098192366, "grad_norm": 1.4131137132644653, "learning_rate": 0.00018642041241726141, "loss": 0.6237280368804932, "step": 130930 }, { "epoch": 0.7783345518959051, "grad_norm": 2.1336190700531006, "learning_rate": 0.00018641712426832306, "loss": 0.5979263305664062, "step": 130940 }, { "epoch": 0.7783939939725735, "grad_norm": 1.7789220809936523, "learning_rate": 0.00018641383575383017, "loss": 0.7421750068664551, "step": 130950 }, { "epoch": 0.7784534360492418, "grad_norm": 1.5502530336380005, "learning_rate": 0.0001864105468737985, "loss": 0.6242717742919922, "step": 130960 }, { "epoch": 0.7785128781259102, "grad_norm": 1.8203946352005005, "learning_rate": 0.00018640725762824375, "loss": 0.68177490234375, "step": 130970 }, { "epoch": 0.7785723202025786, "grad_norm": 1.605800747871399, "learning_rate": 0.0001864039680171816, "loss": 0.6458039283752441, "step": 130980 }, { "epoch": 0.778631762279247, "grad_norm": 1.7630231380462646, "learning_rate": 0.00018640067804062788, "loss": 0.6563480377197266, "step": 130990 }, { "epoch": 0.7786912043559153, "grad_norm": 1.9194602966308594, "learning_rate": 0.00018639738769859828, "loss": 0.6313400268554688, "step": 131000 }, { "epoch": 0.7787506464325837, "grad_norm": 1.6515154838562012, "learning_rate": 0.0001863940969911085, "loss": 0.6803871631622315, "step": 131010 }, { "epoch": 0.7788100885092522, "grad_norm": 1.7201249599456787, "learning_rate": 0.00018639080591817438, "loss": 0.6783245086669922, "step": 131020 }, { "epoch": 0.7788695305859206, "grad_norm": 1.455068826675415, "learning_rate": 0.0001863875144798116, "loss": 0.6530176639556885, "step": 131030 }, { "epoch": 0.778928972662589, "grad_norm": 1.9267252683639526, "learning_rate": 0.00018638422267603586, "loss": 0.6324053287506104, "step": 131040 }, { "epoch": 0.7789884147392573, "grad_norm": 1.8705682754516602, "learning_rate": 0.00018638093050686304, "loss": 0.6315550804138184, "step": 131050 }, { "epoch": 0.7790478568159257, "grad_norm": 1.8411203622817993, "learning_rate": 0.00018637763797230876, "loss": 0.6556448936462402, "step": 131060 }, { "epoch": 0.7791072988925941, "grad_norm": 1.485294222831726, "learning_rate": 0.00018637434507238882, "loss": 0.6888257026672363, "step": 131070 }, { "epoch": 0.7791667409692625, "grad_norm": 1.5819072723388672, "learning_rate": 0.000186371051807119, "loss": 0.5947789192199707, "step": 131080 }, { "epoch": 0.7792261830459309, "grad_norm": 1.4462249279022217, "learning_rate": 0.000186367758176515, "loss": 0.6701614856719971, "step": 131090 }, { "epoch": 0.7792856251225992, "grad_norm": 1.9990113973617554, "learning_rate": 0.00018636446418059262, "loss": 0.6781117439270019, "step": 131100 }, { "epoch": 0.7793450671992677, "grad_norm": 1.4921879768371582, "learning_rate": 0.0001863611698193676, "loss": 0.711052942276001, "step": 131110 }, { "epoch": 0.7794045092759361, "grad_norm": 1.6787937879562378, "learning_rate": 0.00018635787509285566, "loss": 0.5916287899017334, "step": 131120 }, { "epoch": 0.7794639513526045, "grad_norm": 1.9445065259933472, "learning_rate": 0.00018635458000107263, "loss": 0.7616090774536133, "step": 131130 }, { "epoch": 0.7795233934292728, "grad_norm": 1.6271380186080933, "learning_rate": 0.00018635128454403427, "loss": 0.6830991268157959, "step": 131140 }, { "epoch": 0.7795828355059412, "grad_norm": 1.9370743036270142, "learning_rate": 0.00018634798872175628, "loss": 0.6563200950622559, "step": 131150 }, { "epoch": 0.7796422775826096, "grad_norm": 1.471329927444458, "learning_rate": 0.00018634469253425446, "loss": 0.6524659633636475, "step": 131160 }, { "epoch": 0.779701719659278, "grad_norm": 1.7184900045394897, "learning_rate": 0.00018634139598154462, "loss": 0.6975831031799317, "step": 131170 }, { "epoch": 0.7797611617359465, "grad_norm": 1.516329288482666, "learning_rate": 0.00018633809906364244, "loss": 0.6686530590057373, "step": 131180 }, { "epoch": 0.7798206038126148, "grad_norm": 1.3558043241500854, "learning_rate": 0.00018633480178056378, "loss": 0.6453138828277588, "step": 131190 }, { "epoch": 0.7798800458892832, "grad_norm": 2.201443910598755, "learning_rate": 0.00018633150413232438, "loss": 0.6759197235107421, "step": 131200 }, { "epoch": 0.7799394879659516, "grad_norm": 1.99402916431427, "learning_rate": 0.00018632820611893999, "loss": 0.6861796379089355, "step": 131210 }, { "epoch": 0.77999893004262, "grad_norm": 1.688899040222168, "learning_rate": 0.00018632490774042636, "loss": 0.6795852184295654, "step": 131220 }, { "epoch": 0.7800583721192884, "grad_norm": 1.6302119493484497, "learning_rate": 0.0001863216089967994, "loss": 0.6484731674194336, "step": 131230 }, { "epoch": 0.7801178141959567, "grad_norm": 1.9521416425704956, "learning_rate": 0.00018631830988807474, "loss": 0.6647969245910644, "step": 131240 }, { "epoch": 0.7801772562726251, "grad_norm": 1.8132966756820679, "learning_rate": 0.00018631501041426824, "loss": 0.6672470569610596, "step": 131250 }, { "epoch": 0.7802366983492935, "grad_norm": 1.5335438251495361, "learning_rate": 0.00018631171057539568, "loss": 0.7169937133789063, "step": 131260 }, { "epoch": 0.780296140425962, "grad_norm": 1.7869549989700317, "learning_rate": 0.00018630841037147285, "loss": 0.7115039825439453, "step": 131270 }, { "epoch": 0.7803555825026303, "grad_norm": 1.9058290719985962, "learning_rate": 0.00018630510980251552, "loss": 0.6708455085754395, "step": 131280 }, { "epoch": 0.7804150245792987, "grad_norm": 1.854308843612671, "learning_rate": 0.00018630180886853944, "loss": 0.6488336086273193, "step": 131290 }, { "epoch": 0.7804744666559671, "grad_norm": 1.573016881942749, "learning_rate": 0.0001862985075695605, "loss": 0.6699378967285157, "step": 131300 }, { "epoch": 0.7805339087326355, "grad_norm": 1.5637133121490479, "learning_rate": 0.00018629520590559442, "loss": 0.6879603385925293, "step": 131310 }, { "epoch": 0.7805933508093039, "grad_norm": 1.7214807271957397, "learning_rate": 0.00018629190387665698, "loss": 0.7132340908050537, "step": 131320 }, { "epoch": 0.7806527928859722, "grad_norm": 2.0882182121276855, "learning_rate": 0.00018628860148276402, "loss": 0.6891424179077148, "step": 131330 }, { "epoch": 0.7807122349626406, "grad_norm": 1.5366103649139404, "learning_rate": 0.00018628529872393132, "loss": 0.6346056938171387, "step": 131340 }, { "epoch": 0.780771677039309, "grad_norm": 1.7879631519317627, "learning_rate": 0.00018628199560017468, "loss": 0.6612910747528076, "step": 131350 }, { "epoch": 0.7808311191159775, "grad_norm": 1.362405776977539, "learning_rate": 0.0001862786921115099, "loss": 0.6030335426330566, "step": 131360 }, { "epoch": 0.7808905611926458, "grad_norm": 1.658406376838684, "learning_rate": 0.00018627538825795282, "loss": 0.656230878829956, "step": 131370 }, { "epoch": 0.7809500032693142, "grad_norm": 1.8807367086410522, "learning_rate": 0.00018627208403951918, "loss": 0.6242241859436035, "step": 131380 }, { "epoch": 0.7810094453459826, "grad_norm": 1.6505943536758423, "learning_rate": 0.0001862687794562248, "loss": 0.6959458827972412, "step": 131390 }, { "epoch": 0.781068887422651, "grad_norm": 1.4747201204299927, "learning_rate": 0.00018626547450808554, "loss": 0.6427701950073242, "step": 131400 }, { "epoch": 0.7811283294993194, "grad_norm": 1.2799550294876099, "learning_rate": 0.00018626216919511715, "loss": 0.6101637840270996, "step": 131410 }, { "epoch": 0.7811877715759877, "grad_norm": 2.020700454711914, "learning_rate": 0.00018625886351733545, "loss": 0.7021229267120361, "step": 131420 }, { "epoch": 0.7812472136526561, "grad_norm": 1.9135650396347046, "learning_rate": 0.0001862555574747563, "loss": 0.6170531749725342, "step": 131430 }, { "epoch": 0.7813066557293246, "grad_norm": 1.6180287599563599, "learning_rate": 0.00018625225106739545, "loss": 0.7088570117950439, "step": 131440 }, { "epoch": 0.781366097805993, "grad_norm": 2.014174461364746, "learning_rate": 0.0001862489442952688, "loss": 0.648909616470337, "step": 131450 }, { "epoch": 0.7814255398826614, "grad_norm": 1.5436997413635254, "learning_rate": 0.0001862456371583921, "loss": 0.6105810642242432, "step": 131460 }, { "epoch": 0.7814849819593297, "grad_norm": 1.7055970430374146, "learning_rate": 0.00018624232965678116, "loss": 0.6729931354522705, "step": 131470 }, { "epoch": 0.7815444240359981, "grad_norm": 1.4422653913497925, "learning_rate": 0.00018623902179045187, "loss": 0.6186150550842285, "step": 131480 }, { "epoch": 0.7816038661126665, "grad_norm": 1.6967988014221191, "learning_rate": 0.00018623571355942, "loss": 0.6662041664123535, "step": 131490 }, { "epoch": 0.7816633081893349, "grad_norm": 1.9880403280258179, "learning_rate": 0.00018623240496370137, "loss": 0.7023648262023926, "step": 131500 }, { "epoch": 0.7817227502660032, "grad_norm": 1.808984398841858, "learning_rate": 0.00018622909600331188, "loss": 0.6256988525390625, "step": 131510 }, { "epoch": 0.7817821923426717, "grad_norm": 1.4600111246109009, "learning_rate": 0.00018622578667826725, "loss": 0.6767587184906005, "step": 131520 }, { "epoch": 0.7818416344193401, "grad_norm": 1.5367220640182495, "learning_rate": 0.0001862224769885834, "loss": 0.6589997291564942, "step": 131530 }, { "epoch": 0.7819010764960085, "grad_norm": 2.040454387664795, "learning_rate": 0.0001862191669342761, "loss": 0.6880060195922851, "step": 131540 }, { "epoch": 0.7819605185726769, "grad_norm": 1.5490145683288574, "learning_rate": 0.00018621585651536123, "loss": 0.7049661636352539, "step": 131550 }, { "epoch": 0.7820199606493452, "grad_norm": 1.9859428405761719, "learning_rate": 0.00018621254573185462, "loss": 0.634991455078125, "step": 131560 }, { "epoch": 0.7820794027260136, "grad_norm": 1.3901598453521729, "learning_rate": 0.0001862092345837721, "loss": 0.6149496078491211, "step": 131570 }, { "epoch": 0.782138844802682, "grad_norm": 1.357831597328186, "learning_rate": 0.00018620592307112949, "loss": 0.7109622001647949, "step": 131580 }, { "epoch": 0.7821982868793504, "grad_norm": 2.028836250305176, "learning_rate": 0.00018620261119394266, "loss": 0.6648893356323242, "step": 131590 }, { "epoch": 0.7822577289560189, "grad_norm": 1.5874820947647095, "learning_rate": 0.0001861992989522274, "loss": 0.6713289260864258, "step": 131600 }, { "epoch": 0.7823171710326872, "grad_norm": 1.5158109664916992, "learning_rate": 0.00018619598634599967, "loss": 0.700440788269043, "step": 131610 }, { "epoch": 0.7823766131093556, "grad_norm": 1.801748275756836, "learning_rate": 0.0001861926733752752, "loss": 0.6224157333374023, "step": 131620 }, { "epoch": 0.782436055186024, "grad_norm": 1.7191619873046875, "learning_rate": 0.0001861893600400699, "loss": 0.6729945182800293, "step": 131630 }, { "epoch": 0.7824954972626924, "grad_norm": 1.4878638982772827, "learning_rate": 0.00018618604634039959, "loss": 0.6590919017791748, "step": 131640 }, { "epoch": 0.7825549393393607, "grad_norm": 1.7130975723266602, "learning_rate": 0.00018618273227628013, "loss": 0.6094318389892578, "step": 131650 }, { "epoch": 0.7826143814160291, "grad_norm": 1.8935596942901611, "learning_rate": 0.00018617941784772736, "loss": 0.6680435180664063, "step": 131660 }, { "epoch": 0.7826738234926975, "grad_norm": 1.7304707765579224, "learning_rate": 0.00018617610305475717, "loss": 0.6301527976989746, "step": 131670 }, { "epoch": 0.782733265569366, "grad_norm": 1.604417085647583, "learning_rate": 0.0001861727878973854, "loss": 0.5930800437927246, "step": 131680 }, { "epoch": 0.7827927076460344, "grad_norm": 1.3741579055786133, "learning_rate": 0.0001861694723756279, "loss": 0.7185295104980469, "step": 131690 }, { "epoch": 0.7828521497227027, "grad_norm": 1.3563549518585205, "learning_rate": 0.00018616615648950054, "loss": 0.6268057823181152, "step": 131700 }, { "epoch": 0.7829115917993711, "grad_norm": 1.4683918952941895, "learning_rate": 0.00018616284023901915, "loss": 0.6758196830749512, "step": 131710 }, { "epoch": 0.7829710338760395, "grad_norm": 1.607908844947815, "learning_rate": 0.00018615952362419967, "loss": 0.6787552833557129, "step": 131720 }, { "epoch": 0.7830304759527079, "grad_norm": 1.5723692178726196, "learning_rate": 0.00018615620664505787, "loss": 0.6362629890441894, "step": 131730 }, { "epoch": 0.7830899180293762, "grad_norm": 1.337329626083374, "learning_rate": 0.0001861528893016097, "loss": 0.6468115329742432, "step": 131740 }, { "epoch": 0.7831493601060446, "grad_norm": 1.977716088294983, "learning_rate": 0.00018614957159387099, "loss": 0.7094887256622314, "step": 131750 }, { "epoch": 0.783208802182713, "grad_norm": 1.6296123266220093, "learning_rate": 0.0001861462535218576, "loss": 0.7292690277099609, "step": 131760 }, { "epoch": 0.7832682442593815, "grad_norm": 1.3891737461090088, "learning_rate": 0.00018614293508558541, "loss": 0.7096607208251953, "step": 131770 }, { "epoch": 0.7833276863360499, "grad_norm": 1.6295887231826782, "learning_rate": 0.00018613961628507035, "loss": 0.7627268314361573, "step": 131780 }, { "epoch": 0.7833871284127182, "grad_norm": 1.3042923212051392, "learning_rate": 0.0001861362971203282, "loss": 0.6097320556640625, "step": 131790 }, { "epoch": 0.7834465704893866, "grad_norm": 1.7645602226257324, "learning_rate": 0.00018613297759137494, "loss": 0.6145339012145996, "step": 131800 }, { "epoch": 0.783506012566055, "grad_norm": 1.8181939125061035, "learning_rate": 0.00018612965769822636, "loss": 0.6481510639190674, "step": 131810 }, { "epoch": 0.7835654546427234, "grad_norm": 1.560078501701355, "learning_rate": 0.00018612633744089838, "loss": 0.6365616798400879, "step": 131820 }, { "epoch": 0.7836248967193918, "grad_norm": 1.915718674659729, "learning_rate": 0.00018612301681940688, "loss": 0.6687385559082031, "step": 131830 }, { "epoch": 0.7836843387960601, "grad_norm": 1.6963826417922974, "learning_rate": 0.00018611969583376775, "loss": 0.7247974872589111, "step": 131840 }, { "epoch": 0.7837437808727286, "grad_norm": 1.8341410160064697, "learning_rate": 0.00018611637448399685, "loss": 0.6529546737670898, "step": 131850 }, { "epoch": 0.783803222949397, "grad_norm": 1.9625530242919922, "learning_rate": 0.00018611305277011013, "loss": 0.6261488437652588, "step": 131860 }, { "epoch": 0.7838626650260654, "grad_norm": 1.95942223072052, "learning_rate": 0.00018610973069212337, "loss": 0.7114066123962403, "step": 131870 }, { "epoch": 0.7839221071027337, "grad_norm": 1.4102935791015625, "learning_rate": 0.0001861064082500526, "loss": 0.5873008728027344, "step": 131880 }, { "epoch": 0.7839815491794021, "grad_norm": 1.6126021146774292, "learning_rate": 0.00018610308544391363, "loss": 0.6365423679351807, "step": 131890 }, { "epoch": 0.7840409912560705, "grad_norm": 1.1954022645950317, "learning_rate": 0.00018609976227372234, "loss": 0.6300145626068115, "step": 131900 }, { "epoch": 0.7841004333327389, "grad_norm": 1.76526939868927, "learning_rate": 0.0001860964387394947, "loss": 0.6255605697631836, "step": 131910 }, { "epoch": 0.7841598754094073, "grad_norm": 1.7728780508041382, "learning_rate": 0.00018609311484124653, "loss": 0.6425780296325684, "step": 131920 }, { "epoch": 0.7842193174860757, "grad_norm": 1.6688008308410645, "learning_rate": 0.00018608979057899378, "loss": 0.5812944412231446, "step": 131930 }, { "epoch": 0.7842787595627441, "grad_norm": 1.5445423126220703, "learning_rate": 0.00018608646595275231, "loss": 0.6513525962829589, "step": 131940 }, { "epoch": 0.7843382016394125, "grad_norm": 1.9430230855941772, "learning_rate": 0.0001860831409625381, "loss": 0.6620205402374267, "step": 131950 }, { "epoch": 0.7843976437160809, "grad_norm": 1.4913525581359863, "learning_rate": 0.00018607981560836697, "loss": 0.7147244453430176, "step": 131960 }, { "epoch": 0.7844570857927493, "grad_norm": 1.5447349548339844, "learning_rate": 0.00018607648989025493, "loss": 0.6372628211975098, "step": 131970 }, { "epoch": 0.7845165278694176, "grad_norm": 1.9776537418365479, "learning_rate": 0.00018607316380821778, "loss": 0.6928003787994385, "step": 131980 }, { "epoch": 0.784575969946086, "grad_norm": 1.9006813764572144, "learning_rate": 0.00018606983736227145, "loss": 0.6093272686004638, "step": 131990 }, { "epoch": 0.7846354120227544, "grad_norm": 1.1331710815429688, "learning_rate": 0.0001860665105524319, "loss": 0.6577332019805908, "step": 132000 }, { "epoch": 0.7846948540994229, "grad_norm": 1.5970184803009033, "learning_rate": 0.00018606318337871503, "loss": 0.6995489597320557, "step": 132010 }, { "epoch": 0.7847542961760912, "grad_norm": 2.094486951828003, "learning_rate": 0.00018605985584113673, "loss": 0.6415276527404785, "step": 132020 }, { "epoch": 0.7848137382527596, "grad_norm": 1.667673110961914, "learning_rate": 0.00018605652793971295, "loss": 0.6522537708282471, "step": 132030 }, { "epoch": 0.784873180329428, "grad_norm": 3.48791241645813, "learning_rate": 0.0001860531996744596, "loss": 0.7309561252593995, "step": 132040 }, { "epoch": 0.7849326224060964, "grad_norm": 1.8017970323562622, "learning_rate": 0.0001860498710453926, "loss": 0.6607595443725586, "step": 132050 }, { "epoch": 0.7849920644827648, "grad_norm": 1.4061875343322754, "learning_rate": 0.00018604654205252788, "loss": 0.6443600654602051, "step": 132060 }, { "epoch": 0.7850515065594331, "grad_norm": 1.6551514863967896, "learning_rate": 0.0001860432126958813, "loss": 0.5785926342010498, "step": 132070 }, { "epoch": 0.7851109486361015, "grad_norm": 1.7033731937408447, "learning_rate": 0.0001860398829754689, "loss": 0.6786479949951172, "step": 132080 }, { "epoch": 0.78517039071277, "grad_norm": 1.6490010023117065, "learning_rate": 0.00018603655289130651, "loss": 0.6730885028839111, "step": 132090 }, { "epoch": 0.7852298327894384, "grad_norm": 1.532678246498108, "learning_rate": 0.00018603322244341013, "loss": 0.680759048461914, "step": 132100 }, { "epoch": 0.7852892748661067, "grad_norm": 1.687987208366394, "learning_rate": 0.00018602989163179565, "loss": 0.6431477069854736, "step": 132110 }, { "epoch": 0.7853487169427751, "grad_norm": 1.6047899723052979, "learning_rate": 0.00018602656045647902, "loss": 0.5941483497619628, "step": 132120 }, { "epoch": 0.7854081590194435, "grad_norm": 1.9630645513534546, "learning_rate": 0.00018602322891747615, "loss": 0.7201849460601807, "step": 132130 }, { "epoch": 0.7854676010961119, "grad_norm": 1.239671230316162, "learning_rate": 0.00018601989701480304, "loss": 0.6788467407226563, "step": 132140 }, { "epoch": 0.7855270431727803, "grad_norm": 1.5555870532989502, "learning_rate": 0.00018601656474847553, "loss": 0.6828085899353027, "step": 132150 }, { "epoch": 0.7855864852494486, "grad_norm": 1.8883196115493774, "learning_rate": 0.00018601323211850962, "loss": 0.683012866973877, "step": 132160 }, { "epoch": 0.785645927326117, "grad_norm": 1.722348690032959, "learning_rate": 0.0001860098991249213, "loss": 0.6900145530700683, "step": 132170 }, { "epoch": 0.7857053694027855, "grad_norm": 2.2488207817077637, "learning_rate": 0.00018600656576772643, "loss": 0.6490405559539795, "step": 132180 }, { "epoch": 0.7857648114794539, "grad_norm": 1.6249440908432007, "learning_rate": 0.00018600323204694098, "loss": 0.6612486839294434, "step": 132190 }, { "epoch": 0.7858242535561223, "grad_norm": 1.814332127571106, "learning_rate": 0.00018599989796258095, "loss": 0.6265700817108154, "step": 132200 }, { "epoch": 0.7858836956327906, "grad_norm": 1.6319551467895508, "learning_rate": 0.00018599656351466222, "loss": 0.6307577133178711, "step": 132210 }, { "epoch": 0.785943137709459, "grad_norm": 1.55406653881073, "learning_rate": 0.00018599322870320074, "loss": 0.6223915100097657, "step": 132220 }, { "epoch": 0.7860025797861274, "grad_norm": 1.4964619874954224, "learning_rate": 0.00018598989352821253, "loss": 0.6271871089935303, "step": 132230 }, { "epoch": 0.7860620218627958, "grad_norm": 1.5335904359817505, "learning_rate": 0.00018598655798971348, "loss": 0.6649178504943848, "step": 132240 }, { "epoch": 0.7861214639394641, "grad_norm": 1.6712006330490112, "learning_rate": 0.00018598322208771958, "loss": 0.6367288589477539, "step": 132250 }, { "epoch": 0.7861809060161326, "grad_norm": 1.7086645364761353, "learning_rate": 0.00018597988582224676, "loss": 0.6154831886291504, "step": 132260 }, { "epoch": 0.786240348092801, "grad_norm": 1.6431562900543213, "learning_rate": 0.00018597654919331102, "loss": 0.6002280235290527, "step": 132270 }, { "epoch": 0.7862997901694694, "grad_norm": 1.6364686489105225, "learning_rate": 0.0001859732122009283, "loss": 0.6917880535125732, "step": 132280 }, { "epoch": 0.7863592322461378, "grad_norm": 1.530975580215454, "learning_rate": 0.00018596987484511453, "loss": 0.6583128929138183, "step": 132290 }, { "epoch": 0.7864186743228061, "grad_norm": 1.5696303844451904, "learning_rate": 0.0001859665371258857, "loss": 0.6350537300109863, "step": 132300 }, { "epoch": 0.7864781163994745, "grad_norm": 1.750372290611267, "learning_rate": 0.00018596319904325785, "loss": 0.6906474113464356, "step": 132310 }, { "epoch": 0.7865375584761429, "grad_norm": 1.5515995025634766, "learning_rate": 0.0001859598605972468, "loss": 0.6334954261779785, "step": 132320 }, { "epoch": 0.7865970005528113, "grad_norm": 1.9309501647949219, "learning_rate": 0.00018595652178786867, "loss": 0.625910472869873, "step": 132330 }, { "epoch": 0.7866564426294798, "grad_norm": 2.0748398303985596, "learning_rate": 0.00018595318261513933, "loss": 0.6352822303771972, "step": 132340 }, { "epoch": 0.7867158847061481, "grad_norm": 1.9731956720352173, "learning_rate": 0.0001859498430790748, "loss": 0.6869824409484864, "step": 132350 }, { "epoch": 0.7867753267828165, "grad_norm": 1.8310761451721191, "learning_rate": 0.000185946503179691, "loss": 0.6359156608581543, "step": 132360 }, { "epoch": 0.7868347688594849, "grad_norm": 3.2403604984283447, "learning_rate": 0.000185943162917004, "loss": 0.735387659072876, "step": 132370 }, { "epoch": 0.7868942109361533, "grad_norm": 1.9523041248321533, "learning_rate": 0.00018593982229102968, "loss": 0.754392671585083, "step": 132380 }, { "epoch": 0.7869536530128216, "grad_norm": 1.4736248254776, "learning_rate": 0.00018593648130178412, "loss": 0.645871639251709, "step": 132390 }, { "epoch": 0.78701309508949, "grad_norm": 1.625566840171814, "learning_rate": 0.00018593313994928322, "loss": 0.6141817092895507, "step": 132400 }, { "epoch": 0.7870725371661584, "grad_norm": 1.8710612058639526, "learning_rate": 0.00018592979823354297, "loss": 0.6720625877380371, "step": 132410 }, { "epoch": 0.7871319792428269, "grad_norm": 2.022449016571045, "learning_rate": 0.0001859264561545794, "loss": 0.7075333595275879, "step": 132420 }, { "epoch": 0.7871914213194953, "grad_norm": 1.64313542842865, "learning_rate": 0.0001859231137124085, "loss": 0.673280906677246, "step": 132430 }, { "epoch": 0.7872508633961636, "grad_norm": 1.3295953273773193, "learning_rate": 0.0001859197709070462, "loss": 0.6704554557800293, "step": 132440 }, { "epoch": 0.787310305472832, "grad_norm": 1.5875022411346436, "learning_rate": 0.00018591642773850857, "loss": 0.7460458755493165, "step": 132450 }, { "epoch": 0.7873697475495004, "grad_norm": 1.4507876634597778, "learning_rate": 0.00018591308420681153, "loss": 0.653016471862793, "step": 132460 }, { "epoch": 0.7874291896261688, "grad_norm": 1.5805253982543945, "learning_rate": 0.0001859097403119711, "loss": 0.6749869346618652, "step": 132470 }, { "epoch": 0.7874886317028371, "grad_norm": 2.037360429763794, "learning_rate": 0.0001859063960540033, "loss": 0.6614172458648682, "step": 132480 }, { "epoch": 0.7875480737795055, "grad_norm": 2.0453343391418457, "learning_rate": 0.00018590305143292407, "loss": 0.6996635437011719, "step": 132490 }, { "epoch": 0.787607515856174, "grad_norm": 1.6552067995071411, "learning_rate": 0.0001858997064487495, "loss": 0.6941064834594727, "step": 132500 }, { "epoch": 0.7876669579328424, "grad_norm": 1.8261703252792358, "learning_rate": 0.00018589636110149548, "loss": 0.6427847862243652, "step": 132510 }, { "epoch": 0.7877264000095108, "grad_norm": 1.4847288131713867, "learning_rate": 0.00018589301539117815, "loss": 0.6049534320831299, "step": 132520 }, { "epoch": 0.7877858420861791, "grad_norm": 1.5201605558395386, "learning_rate": 0.00018588966931781334, "loss": 0.6934209823608398, "step": 132530 }, { "epoch": 0.7878452841628475, "grad_norm": 1.7095379829406738, "learning_rate": 0.0001858863228814172, "loss": 0.7119217872619629, "step": 132540 }, { "epoch": 0.7879047262395159, "grad_norm": 1.3880088329315186, "learning_rate": 0.0001858829760820057, "loss": 0.6509403705596923, "step": 132550 }, { "epoch": 0.7879641683161843, "grad_norm": 1.6268572807312012, "learning_rate": 0.00018587962891959483, "loss": 0.68089599609375, "step": 132560 }, { "epoch": 0.7880236103928527, "grad_norm": 1.9229744672775269, "learning_rate": 0.00018587628139420063, "loss": 0.6877682209014893, "step": 132570 }, { "epoch": 0.788083052469521, "grad_norm": 1.7739434242248535, "learning_rate": 0.0001858729335058391, "loss": 0.6576114654541015, "step": 132580 }, { "epoch": 0.7881424945461895, "grad_norm": 1.5470443964004517, "learning_rate": 0.00018586958525452623, "loss": 0.6208992958068847, "step": 132590 }, { "epoch": 0.7882019366228579, "grad_norm": 1.7701319456100464, "learning_rate": 0.00018586623664027804, "loss": 0.6497638702392579, "step": 132600 }, { "epoch": 0.7882613786995263, "grad_norm": 1.7587627172470093, "learning_rate": 0.00018586288766311062, "loss": 0.6313097953796387, "step": 132610 }, { "epoch": 0.7883208207761946, "grad_norm": 1.5033645629882812, "learning_rate": 0.0001858595383230399, "loss": 0.6683835983276367, "step": 132620 }, { "epoch": 0.788380262852863, "grad_norm": 1.7679980993270874, "learning_rate": 0.00018585618862008193, "loss": 0.6519915580749511, "step": 132630 }, { "epoch": 0.7884397049295314, "grad_norm": 1.7679394483566284, "learning_rate": 0.00018585283855425278, "loss": 0.6684593677520752, "step": 132640 }, { "epoch": 0.7884991470061998, "grad_norm": 1.8479089736938477, "learning_rate": 0.00018584948812556842, "loss": 0.6048613548278808, "step": 132650 }, { "epoch": 0.7885585890828682, "grad_norm": 1.4134358167648315, "learning_rate": 0.0001858461373340449, "loss": 0.658045768737793, "step": 132660 }, { "epoch": 0.7886180311595365, "grad_norm": 1.517278790473938, "learning_rate": 0.00018584278617969825, "loss": 0.6826936721801757, "step": 132670 }, { "epoch": 0.788677473236205, "grad_norm": 1.5789202451705933, "learning_rate": 0.00018583943466254446, "loss": 0.70950288772583, "step": 132680 }, { "epoch": 0.7887369153128734, "grad_norm": 1.6267354488372803, "learning_rate": 0.00018583608278259966, "loss": 0.7160470008850097, "step": 132690 }, { "epoch": 0.7887963573895418, "grad_norm": 1.944683313369751, "learning_rate": 0.0001858327305398798, "loss": 0.6552407741546631, "step": 132700 }, { "epoch": 0.7888557994662102, "grad_norm": 1.6885271072387695, "learning_rate": 0.0001858293779344009, "loss": 0.684437370300293, "step": 132710 }, { "epoch": 0.7889152415428785, "grad_norm": 1.8492324352264404, "learning_rate": 0.0001858260249661791, "loss": 0.675083065032959, "step": 132720 }, { "epoch": 0.7889746836195469, "grad_norm": 1.9077054262161255, "learning_rate": 0.00018582267163523033, "loss": 0.6639563560485839, "step": 132730 }, { "epoch": 0.7890341256962153, "grad_norm": 1.5091828107833862, "learning_rate": 0.0001858193179415707, "loss": 0.675311279296875, "step": 132740 }, { "epoch": 0.7890935677728838, "grad_norm": 1.627205729484558, "learning_rate": 0.00018581596388521625, "loss": 0.693115234375, "step": 132750 }, { "epoch": 0.7891530098495521, "grad_norm": 1.8832451105117798, "learning_rate": 0.00018581260946618297, "loss": 0.6623238086700439, "step": 132760 }, { "epoch": 0.7892124519262205, "grad_norm": 2.1866037845611572, "learning_rate": 0.00018580925468448696, "loss": 0.6315552234649658, "step": 132770 }, { "epoch": 0.7892718940028889, "grad_norm": 2.1060593128204346, "learning_rate": 0.00018580589954014424, "loss": 0.626006031036377, "step": 132780 }, { "epoch": 0.7893313360795573, "grad_norm": 1.578335165977478, "learning_rate": 0.00018580254403317088, "loss": 0.6230396270751953, "step": 132790 }, { "epoch": 0.7893907781562257, "grad_norm": 1.5763764381408691, "learning_rate": 0.00018579918816358291, "loss": 0.6708164215087891, "step": 132800 }, { "epoch": 0.789450220232894, "grad_norm": 1.8609553575515747, "learning_rate": 0.0001857958319313964, "loss": 0.6691978931427002, "step": 132810 }, { "epoch": 0.7895096623095624, "grad_norm": 1.491965413093567, "learning_rate": 0.0001857924753366274, "loss": 0.626986312866211, "step": 132820 }, { "epoch": 0.7895691043862308, "grad_norm": 1.8263063430786133, "learning_rate": 0.00018578911837929197, "loss": 0.6719266891479492, "step": 132830 }, { "epoch": 0.7896285464628993, "grad_norm": 1.3772605657577515, "learning_rate": 0.00018578576105940617, "loss": 0.5817215919494629, "step": 132840 }, { "epoch": 0.7896879885395676, "grad_norm": 1.3770006895065308, "learning_rate": 0.00018578240337698606, "loss": 0.5705419540405273, "step": 132850 }, { "epoch": 0.789747430616236, "grad_norm": 1.4720921516418457, "learning_rate": 0.0001857790453320477, "loss": 0.6904510498046875, "step": 132860 }, { "epoch": 0.7898068726929044, "grad_norm": 1.4383615255355835, "learning_rate": 0.00018577568692460712, "loss": 0.6973369121551514, "step": 132870 }, { "epoch": 0.7898663147695728, "grad_norm": 1.8432483673095703, "learning_rate": 0.00018577232815468044, "loss": 0.634485912322998, "step": 132880 }, { "epoch": 0.7899257568462412, "grad_norm": 1.6692737340927124, "learning_rate": 0.00018576896902228372, "loss": 0.7043152332305909, "step": 132890 }, { "epoch": 0.7899851989229095, "grad_norm": 1.7911983728408813, "learning_rate": 0.00018576560952743296, "loss": 0.5940629005432129, "step": 132900 }, { "epoch": 0.7900446409995779, "grad_norm": 1.9914788007736206, "learning_rate": 0.00018576224967014433, "loss": 0.6306509971618652, "step": 132910 }, { "epoch": 0.7901040830762464, "grad_norm": 1.8478996753692627, "learning_rate": 0.00018575888945043386, "loss": 0.6104371070861816, "step": 132920 }, { "epoch": 0.7901635251529148, "grad_norm": 1.5920283794403076, "learning_rate": 0.00018575552886831762, "loss": 0.641380500793457, "step": 132930 }, { "epoch": 0.7902229672295832, "grad_norm": 1.780425786972046, "learning_rate": 0.00018575216792381168, "loss": 0.6427694320678711, "step": 132940 }, { "epoch": 0.7902824093062515, "grad_norm": 1.8095037937164307, "learning_rate": 0.0001857488066169321, "loss": 0.6326119899749756, "step": 132950 }, { "epoch": 0.7903418513829199, "grad_norm": 1.6238242387771606, "learning_rate": 0.00018574544494769503, "loss": 0.6535935401916504, "step": 132960 }, { "epoch": 0.7904012934595883, "grad_norm": 1.3070894479751587, "learning_rate": 0.00018574208291611646, "loss": 0.6696032524108887, "step": 132970 }, { "epoch": 0.7904607355362567, "grad_norm": 1.9894907474517822, "learning_rate": 0.00018573872052221255, "loss": 0.6016244888305664, "step": 132980 }, { "epoch": 0.790520177612925, "grad_norm": 1.7063521146774292, "learning_rate": 0.00018573535776599936, "loss": 0.6808897972106933, "step": 132990 }, { "epoch": 0.7905796196895934, "grad_norm": 1.5923564434051514, "learning_rate": 0.00018573199464749294, "loss": 0.7280879020690918, "step": 133000 }, { "epoch": 0.7906390617662619, "grad_norm": 1.6986192464828491, "learning_rate": 0.00018572863116670941, "loss": 0.6459205627441407, "step": 133010 }, { "epoch": 0.7906985038429303, "grad_norm": 1.8239325284957886, "learning_rate": 0.00018572526732366486, "loss": 0.7097193241119385, "step": 133020 }, { "epoch": 0.7907579459195987, "grad_norm": 2.214495897293091, "learning_rate": 0.00018572190311837538, "loss": 0.6825140953063965, "step": 133030 }, { "epoch": 0.790817387996267, "grad_norm": 1.5634821653366089, "learning_rate": 0.00018571853855085707, "loss": 0.6415321350097656, "step": 133040 }, { "epoch": 0.7908768300729354, "grad_norm": 1.6436388492584229, "learning_rate": 0.00018571517362112603, "loss": 0.6902164459228516, "step": 133050 }, { "epoch": 0.7909362721496038, "grad_norm": 1.5359805822372437, "learning_rate": 0.00018571180832919833, "loss": 0.6221927642822266, "step": 133060 }, { "epoch": 0.7909957142262722, "grad_norm": 1.7736902236938477, "learning_rate": 0.00018570844267509006, "loss": 0.6580791473388672, "step": 133070 }, { "epoch": 0.7910551563029407, "grad_norm": 1.9397821426391602, "learning_rate": 0.00018570507665881735, "loss": 0.6328038215637207, "step": 133080 }, { "epoch": 0.791114598379609, "grad_norm": 1.7005749940872192, "learning_rate": 0.00018570171028039632, "loss": 0.6695663452148437, "step": 133090 }, { "epoch": 0.7911740404562774, "grad_norm": 2.128821849822998, "learning_rate": 0.000185698343539843, "loss": 0.6998813629150391, "step": 133100 }, { "epoch": 0.7912334825329458, "grad_norm": 1.6174005270004272, "learning_rate": 0.00018569497643717363, "loss": 0.6462707996368409, "step": 133110 }, { "epoch": 0.7912929246096142, "grad_norm": 2.2949435710906982, "learning_rate": 0.00018569160897240414, "loss": 0.6508603096008301, "step": 133120 }, { "epoch": 0.7913523666862825, "grad_norm": 1.5924780368804932, "learning_rate": 0.00018568824114555078, "loss": 0.6572783946990967, "step": 133130 }, { "epoch": 0.7914118087629509, "grad_norm": 2.108809232711792, "learning_rate": 0.00018568487295662957, "loss": 0.6451412200927734, "step": 133140 }, { "epoch": 0.7914712508396193, "grad_norm": 2.124464273452759, "learning_rate": 0.0001856815044056567, "loss": 0.6518525123596192, "step": 133150 }, { "epoch": 0.7915306929162877, "grad_norm": 1.5392793416976929, "learning_rate": 0.00018567813549264824, "loss": 0.6793334484100342, "step": 133160 }, { "epoch": 0.7915901349929562, "grad_norm": 1.4826606512069702, "learning_rate": 0.0001856747662176203, "loss": 0.6126712799072266, "step": 133170 }, { "epoch": 0.7916495770696245, "grad_norm": 1.8839173316955566, "learning_rate": 0.000185671396580589, "loss": 0.6127071857452393, "step": 133180 }, { "epoch": 0.7917090191462929, "grad_norm": 2.0073091983795166, "learning_rate": 0.00018566802658157047, "loss": 0.6865977287292481, "step": 133190 }, { "epoch": 0.7917684612229613, "grad_norm": 2.07776141166687, "learning_rate": 0.00018566465622058085, "loss": 0.6606511116027832, "step": 133200 }, { "epoch": 0.7918279032996297, "grad_norm": 1.4625993967056274, "learning_rate": 0.00018566128549763622, "loss": 0.6642070770263672, "step": 133210 }, { "epoch": 0.791887345376298, "grad_norm": 1.6316293478012085, "learning_rate": 0.00018565791441275275, "loss": 0.7052477359771728, "step": 133220 }, { "epoch": 0.7919467874529664, "grad_norm": 1.6687865257263184, "learning_rate": 0.0001856545429659465, "loss": 0.6920028686523437, "step": 133230 }, { "epoch": 0.7920062295296348, "grad_norm": 1.9854425191879272, "learning_rate": 0.0001856511711572337, "loss": 0.6211459159851074, "step": 133240 }, { "epoch": 0.7920656716063033, "grad_norm": 2.4724159240722656, "learning_rate": 0.0001856477989866304, "loss": 0.6581799983978271, "step": 133250 }, { "epoch": 0.7921251136829717, "grad_norm": 1.6229867935180664, "learning_rate": 0.00018564442645415275, "loss": 0.6533380508422851, "step": 133260 }, { "epoch": 0.79218455575964, "grad_norm": 1.4983646869659424, "learning_rate": 0.00018564105355981688, "loss": 0.6908978939056396, "step": 133270 }, { "epoch": 0.7922439978363084, "grad_norm": 2.1011962890625, "learning_rate": 0.00018563768030363891, "loss": 0.7276407241821289, "step": 133280 }, { "epoch": 0.7923034399129768, "grad_norm": 1.5325217247009277, "learning_rate": 0.000185634306685635, "loss": 0.6806070327758789, "step": 133290 }, { "epoch": 0.7923628819896452, "grad_norm": 1.6150152683258057, "learning_rate": 0.0001856309327058213, "loss": 0.6730531692504883, "step": 133300 }, { "epoch": 0.7924223240663136, "grad_norm": 1.714280605316162, "learning_rate": 0.00018562755836421392, "loss": 0.6669299125671386, "step": 133310 }, { "epoch": 0.7924817661429819, "grad_norm": 1.4368146657943726, "learning_rate": 0.00018562418366082904, "loss": 0.6062314510345459, "step": 133320 }, { "epoch": 0.7925412082196504, "grad_norm": 2.141326904296875, "learning_rate": 0.0001856208085956828, "loss": 0.6282580375671387, "step": 133330 }, { "epoch": 0.7926006502963188, "grad_norm": 1.236139178276062, "learning_rate": 0.00018561743316879126, "loss": 0.6537901878356933, "step": 133340 }, { "epoch": 0.7926600923729872, "grad_norm": 1.5913128852844238, "learning_rate": 0.00018561405738017067, "loss": 0.6729288101196289, "step": 133350 }, { "epoch": 0.7927195344496555, "grad_norm": 1.9042079448699951, "learning_rate": 0.00018561068122983714, "loss": 0.6507155418395996, "step": 133360 }, { "epoch": 0.7927789765263239, "grad_norm": 1.4502507448196411, "learning_rate": 0.00018560730471780683, "loss": 0.5716904640197754, "step": 133370 }, { "epoch": 0.7928384186029923, "grad_norm": 1.5747783184051514, "learning_rate": 0.00018560392784409586, "loss": 0.6779909133911133, "step": 133380 }, { "epoch": 0.7928978606796607, "grad_norm": 1.84241783618927, "learning_rate": 0.0001856005506087204, "loss": 0.6833281517028809, "step": 133390 }, { "epoch": 0.7929573027563291, "grad_norm": 1.7800557613372803, "learning_rate": 0.00018559717301169662, "loss": 0.66490797996521, "step": 133400 }, { "epoch": 0.7930167448329974, "grad_norm": 1.7476277351379395, "learning_rate": 0.00018559379505304072, "loss": 0.6306502819061279, "step": 133410 }, { "epoch": 0.7930761869096659, "grad_norm": 1.6453715562820435, "learning_rate": 0.00018559041673276873, "loss": 0.6586071014404297, "step": 133420 }, { "epoch": 0.7931356289863343, "grad_norm": 1.7670743465423584, "learning_rate": 0.00018558703805089696, "loss": 0.6858297348022461, "step": 133430 }, { "epoch": 0.7931950710630027, "grad_norm": 1.5997830629348755, "learning_rate": 0.00018558365900744146, "loss": 0.6134150505065918, "step": 133440 }, { "epoch": 0.7932545131396711, "grad_norm": 1.627577543258667, "learning_rate": 0.00018558027960241844, "loss": 0.6294493675231934, "step": 133450 }, { "epoch": 0.7933139552163394, "grad_norm": 1.5879216194152832, "learning_rate": 0.0001855768998358441, "loss": 0.6505553245544433, "step": 133460 }, { "epoch": 0.7933733972930078, "grad_norm": 2.0990307331085205, "learning_rate": 0.00018557351970773452, "loss": 0.6531866073608399, "step": 133470 }, { "epoch": 0.7934328393696762, "grad_norm": 1.997207522392273, "learning_rate": 0.00018557013921810593, "loss": 0.7014098167419434, "step": 133480 }, { "epoch": 0.7934922814463446, "grad_norm": 1.9299381971359253, "learning_rate": 0.0001855667583669745, "loss": 0.7085428714752198, "step": 133490 }, { "epoch": 0.793551723523013, "grad_norm": 1.734071969985962, "learning_rate": 0.00018556337715435638, "loss": 0.6433595657348633, "step": 133500 }, { "epoch": 0.7936111655996814, "grad_norm": 2.6288633346557617, "learning_rate": 0.00018555999558026777, "loss": 0.6685741901397705, "step": 133510 }, { "epoch": 0.7936706076763498, "grad_norm": 1.602974534034729, "learning_rate": 0.00018555661364472482, "loss": 0.6013329982757568, "step": 133520 }, { "epoch": 0.7937300497530182, "grad_norm": 1.549942135810852, "learning_rate": 0.00018555323134774373, "loss": 0.575784969329834, "step": 133530 }, { "epoch": 0.7937894918296866, "grad_norm": 1.6099985837936401, "learning_rate": 0.0001855498486893407, "loss": 0.6776242733001709, "step": 133540 }, { "epoch": 0.7938489339063549, "grad_norm": 1.7978286743164062, "learning_rate": 0.00018554646566953185, "loss": 0.6559791564941406, "step": 133550 }, { "epoch": 0.7939083759830233, "grad_norm": 1.964940071105957, "learning_rate": 0.0001855430822883334, "loss": 0.6508284091949463, "step": 133560 }, { "epoch": 0.7939678180596917, "grad_norm": 1.6724799871444702, "learning_rate": 0.00018553969854576155, "loss": 0.5780791282653809, "step": 133570 }, { "epoch": 0.7940272601363602, "grad_norm": 2.001138687133789, "learning_rate": 0.00018553631444183247, "loss": 0.7053847789764405, "step": 133580 }, { "epoch": 0.7940867022130285, "grad_norm": 1.761664867401123, "learning_rate": 0.00018553292997656234, "loss": 0.6882901668548584, "step": 133590 }, { "epoch": 0.7941461442896969, "grad_norm": 2.109456777572632, "learning_rate": 0.00018552954514996736, "loss": 0.7038260459899902, "step": 133600 }, { "epoch": 0.7942055863663653, "grad_norm": 1.8732566833496094, "learning_rate": 0.0001855261599620637, "loss": 0.7283604145050049, "step": 133610 }, { "epoch": 0.7942650284430337, "grad_norm": 1.6539332866668701, "learning_rate": 0.00018552277441286758, "loss": 0.6516491413116455, "step": 133620 }, { "epoch": 0.7943244705197021, "grad_norm": 1.6005630493164062, "learning_rate": 0.0001855193885023952, "loss": 0.6262824058532714, "step": 133630 }, { "epoch": 0.7943839125963704, "grad_norm": 1.8024791479110718, "learning_rate": 0.00018551600223066275, "loss": 0.6716980457305908, "step": 133640 }, { "epoch": 0.7944433546730388, "grad_norm": 1.875149130821228, "learning_rate": 0.0001855126155976864, "loss": 0.6817157745361329, "step": 133650 }, { "epoch": 0.7945027967497073, "grad_norm": 1.8757258653640747, "learning_rate": 0.00018550922860348238, "loss": 0.6499795913696289, "step": 133660 }, { "epoch": 0.7945622388263757, "grad_norm": 2.0293891429901123, "learning_rate": 0.0001855058412480669, "loss": 0.6258432388305664, "step": 133670 }, { "epoch": 0.7946216809030441, "grad_norm": 2.123673677444458, "learning_rate": 0.00018550245353145614, "loss": 0.6153483867645264, "step": 133680 }, { "epoch": 0.7946811229797124, "grad_norm": 1.454980492591858, "learning_rate": 0.00018549906545366633, "loss": 0.6407604217529297, "step": 133690 }, { "epoch": 0.7947405650563808, "grad_norm": 1.4728449583053589, "learning_rate": 0.0001854956770147137, "loss": 0.7268057346343995, "step": 133700 }, { "epoch": 0.7948000071330492, "grad_norm": 1.542414665222168, "learning_rate": 0.00018549228821461436, "loss": 0.6622946262359619, "step": 133710 }, { "epoch": 0.7948594492097176, "grad_norm": 1.6901428699493408, "learning_rate": 0.0001854888990533846, "loss": 0.6828173160552978, "step": 133720 }, { "epoch": 0.7949188912863859, "grad_norm": 1.6758989095687866, "learning_rate": 0.00018548550953104061, "loss": 0.6254076957702637, "step": 133730 }, { "epoch": 0.7949783333630543, "grad_norm": 1.5580753087997437, "learning_rate": 0.00018548211964759863, "loss": 0.6307279586791992, "step": 133740 }, { "epoch": 0.7950377754397228, "grad_norm": 1.4696969985961914, "learning_rate": 0.00018547872940307485, "loss": 0.6182425498962403, "step": 133750 }, { "epoch": 0.7950972175163912, "grad_norm": 1.1805046796798706, "learning_rate": 0.0001854753387974855, "loss": 0.6580196857452393, "step": 133760 }, { "epoch": 0.7951566595930596, "grad_norm": 1.4700255393981934, "learning_rate": 0.0001854719478308468, "loss": 0.6281597137451171, "step": 133770 }, { "epoch": 0.7952161016697279, "grad_norm": 1.753719449043274, "learning_rate": 0.00018546855650317497, "loss": 0.7081349849700928, "step": 133780 }, { "epoch": 0.7952755437463963, "grad_norm": 1.848095417022705, "learning_rate": 0.00018546516481448622, "loss": 0.6764120101928711, "step": 133790 }, { "epoch": 0.7953349858230647, "grad_norm": 1.582720160484314, "learning_rate": 0.00018546177276479675, "loss": 0.662544059753418, "step": 133800 }, { "epoch": 0.7953944278997331, "grad_norm": 1.571103572845459, "learning_rate": 0.00018545838035412287, "loss": 0.5820212364196777, "step": 133810 }, { "epoch": 0.7954538699764016, "grad_norm": 1.5887073278427124, "learning_rate": 0.0001854549875824807, "loss": 0.6113710403442383, "step": 133820 }, { "epoch": 0.7955133120530699, "grad_norm": 1.4724884033203125, "learning_rate": 0.0001854515944498866, "loss": 0.6039948463439941, "step": 133830 }, { "epoch": 0.7955727541297383, "grad_norm": 1.5214695930480957, "learning_rate": 0.00018544820095635668, "loss": 0.6553433418273926, "step": 133840 }, { "epoch": 0.7956321962064067, "grad_norm": 1.7694674730300903, "learning_rate": 0.00018544480710190725, "loss": 0.6376755714416504, "step": 133850 }, { "epoch": 0.7956916382830751, "grad_norm": 1.872820258140564, "learning_rate": 0.0001854414128865545, "loss": 0.6455216407775879, "step": 133860 }, { "epoch": 0.7957510803597434, "grad_norm": 1.9867535829544067, "learning_rate": 0.0001854380183103147, "loss": 0.7370988845825195, "step": 133870 }, { "epoch": 0.7958105224364118, "grad_norm": 1.7049102783203125, "learning_rate": 0.00018543462337320408, "loss": 0.6701387405395508, "step": 133880 }, { "epoch": 0.7958699645130802, "grad_norm": 1.8135554790496826, "learning_rate": 0.00018543122807523888, "loss": 0.6166746616363525, "step": 133890 }, { "epoch": 0.7959294065897486, "grad_norm": 1.4355318546295166, "learning_rate": 0.00018542783241643534, "loss": 0.5747042655944824, "step": 133900 }, { "epoch": 0.7959888486664171, "grad_norm": 1.8524730205535889, "learning_rate": 0.00018542443639680964, "loss": 0.7256328105926514, "step": 133910 }, { "epoch": 0.7960482907430854, "grad_norm": 1.5396573543548584, "learning_rate": 0.00018542104001637814, "loss": 0.655885887145996, "step": 133920 }, { "epoch": 0.7961077328197538, "grad_norm": 1.6826603412628174, "learning_rate": 0.00018541764327515702, "loss": 0.6812626838684082, "step": 133930 }, { "epoch": 0.7961671748964222, "grad_norm": 1.4160776138305664, "learning_rate": 0.0001854142461731625, "loss": 0.6503695487976074, "step": 133940 }, { "epoch": 0.7962266169730906, "grad_norm": 1.6560620069503784, "learning_rate": 0.00018541084871041095, "loss": 0.6472090721130371, "step": 133950 }, { "epoch": 0.7962860590497589, "grad_norm": 1.4717020988464355, "learning_rate": 0.0001854074508869185, "loss": 0.6542349815368652, "step": 133960 }, { "epoch": 0.7963455011264273, "grad_norm": 1.358430027961731, "learning_rate": 0.00018540405270270143, "loss": 0.6601340770721436, "step": 133970 }, { "epoch": 0.7964049432030957, "grad_norm": 1.5043983459472656, "learning_rate": 0.00018540065415777605, "loss": 0.6395783424377441, "step": 133980 }, { "epoch": 0.7964643852797642, "grad_norm": 1.345417857170105, "learning_rate": 0.00018539725525215856, "loss": 0.6593497276306153, "step": 133990 }, { "epoch": 0.7965238273564326, "grad_norm": 1.438900351524353, "learning_rate": 0.00018539385598586528, "loss": 0.6694572925567627, "step": 134000 }, { "epoch": 0.7965832694331009, "grad_norm": 1.6130608320236206, "learning_rate": 0.00018539045635891237, "loss": 0.6749070644378662, "step": 134010 }, { "epoch": 0.7966427115097693, "grad_norm": 1.2692809104919434, "learning_rate": 0.0001853870563713162, "loss": 0.7000640869140625, "step": 134020 }, { "epoch": 0.7967021535864377, "grad_norm": 1.6707762479782104, "learning_rate": 0.00018538365602309298, "loss": 0.6775328636169433, "step": 134030 }, { "epoch": 0.7967615956631061, "grad_norm": 1.7983894348144531, "learning_rate": 0.00018538025531425898, "loss": 0.7257036209106446, "step": 134040 }, { "epoch": 0.7968210377397745, "grad_norm": 1.56009840965271, "learning_rate": 0.00018537685424483048, "loss": 0.6129463195800782, "step": 134050 }, { "epoch": 0.7968804798164428, "grad_norm": 1.7650868892669678, "learning_rate": 0.0001853734528148237, "loss": 0.603585147857666, "step": 134060 }, { "epoch": 0.7969399218931112, "grad_norm": 1.436224341392517, "learning_rate": 0.000185370051024255, "loss": 0.6082455158233643, "step": 134070 }, { "epoch": 0.7969993639697797, "grad_norm": 1.776038646697998, "learning_rate": 0.0001853666488731406, "loss": 0.6485774040222168, "step": 134080 }, { "epoch": 0.7970588060464481, "grad_norm": 1.255539894104004, "learning_rate": 0.0001853632463614968, "loss": 0.6676576137542725, "step": 134090 }, { "epoch": 0.7971182481231164, "grad_norm": 1.8019182682037354, "learning_rate": 0.00018535984348933983, "loss": 0.6833602905273437, "step": 134100 }, { "epoch": 0.7971776901997848, "grad_norm": 2.3589019775390625, "learning_rate": 0.000185356440256686, "loss": 0.6563878536224366, "step": 134110 }, { "epoch": 0.7972371322764532, "grad_norm": 1.5392632484436035, "learning_rate": 0.0001853530366635516, "loss": 0.6372590065002441, "step": 134120 }, { "epoch": 0.7972965743531216, "grad_norm": 1.9345107078552246, "learning_rate": 0.00018534963270995286, "loss": 0.7386160373687745, "step": 134130 }, { "epoch": 0.79735601642979, "grad_norm": 1.5992523431777954, "learning_rate": 0.00018534622839590616, "loss": 0.7011748313903808, "step": 134140 }, { "epoch": 0.7974154585064583, "grad_norm": 1.5787378549575806, "learning_rate": 0.00018534282372142767, "loss": 0.6923547744750976, "step": 134150 }, { "epoch": 0.7974749005831268, "grad_norm": 1.7513000965118408, "learning_rate": 0.00018533941868653376, "loss": 0.6118425369262696, "step": 134160 }, { "epoch": 0.7975343426597952, "grad_norm": 1.6791218519210815, "learning_rate": 0.0001853360132912407, "loss": 0.6225467205047608, "step": 134170 }, { "epoch": 0.7975937847364636, "grad_norm": 1.4408456087112427, "learning_rate": 0.0001853326075355648, "loss": 0.7031121253967285, "step": 134180 }, { "epoch": 0.7976532268131319, "grad_norm": 1.6878678798675537, "learning_rate": 0.00018532920141952228, "loss": 0.632809066772461, "step": 134190 }, { "epoch": 0.7977126688898003, "grad_norm": 1.8188825845718384, "learning_rate": 0.00018532579494312946, "loss": 0.6901745796203613, "step": 134200 }, { "epoch": 0.7977721109664687, "grad_norm": 1.516363501548767, "learning_rate": 0.0001853223881064027, "loss": 0.6514592647552491, "step": 134210 }, { "epoch": 0.7978315530431371, "grad_norm": 1.504839301109314, "learning_rate": 0.00018531898090935823, "loss": 0.7310044288635253, "step": 134220 }, { "epoch": 0.7978909951198055, "grad_norm": 1.9989373683929443, "learning_rate": 0.00018531557335201238, "loss": 0.6364809989929199, "step": 134230 }, { "epoch": 0.7979504371964738, "grad_norm": 1.8498690128326416, "learning_rate": 0.00018531216543438142, "loss": 0.6566296577453613, "step": 134240 }, { "epoch": 0.7980098792731423, "grad_norm": 1.8695759773254395, "learning_rate": 0.00018530875715648169, "loss": 0.6818592548370361, "step": 134250 }, { "epoch": 0.7980693213498107, "grad_norm": 1.6976124048233032, "learning_rate": 0.0001853053485183295, "loss": 0.6071281433105469, "step": 134260 }, { "epoch": 0.7981287634264791, "grad_norm": 1.6049813032150269, "learning_rate": 0.0001853019395199411, "loss": 0.6662734031677247, "step": 134270 }, { "epoch": 0.7981882055031475, "grad_norm": 1.4809889793395996, "learning_rate": 0.0001852985301613328, "loss": 0.6989398002624512, "step": 134280 }, { "epoch": 0.7982476475798158, "grad_norm": 1.662253975868225, "learning_rate": 0.000185295120442521, "loss": 0.6196545600891114, "step": 134290 }, { "epoch": 0.7983070896564842, "grad_norm": 1.5315767526626587, "learning_rate": 0.00018529171036352194, "loss": 0.6813566207885742, "step": 134300 }, { "epoch": 0.7983665317331526, "grad_norm": 1.597042202949524, "learning_rate": 0.0001852882999243519, "loss": 0.5795134544372559, "step": 134310 }, { "epoch": 0.798425973809821, "grad_norm": 1.4824788570404053, "learning_rate": 0.0001852848891250273, "loss": 0.667751693725586, "step": 134320 }, { "epoch": 0.7984854158864894, "grad_norm": 1.364799976348877, "learning_rate": 0.00018528147796556435, "loss": 0.6112741470336914, "step": 134330 }, { "epoch": 0.7985448579631578, "grad_norm": 1.3394969701766968, "learning_rate": 0.0001852780664459794, "loss": 0.6462421894073487, "step": 134340 }, { "epoch": 0.7986043000398262, "grad_norm": 1.384057641029358, "learning_rate": 0.00018527465456628884, "loss": 0.612408447265625, "step": 134350 }, { "epoch": 0.7986637421164946, "grad_norm": 1.586475133895874, "learning_rate": 0.00018527124232650888, "loss": 0.6541812419891357, "step": 134360 }, { "epoch": 0.798723184193163, "grad_norm": 1.4461780786514282, "learning_rate": 0.0001852678297266559, "loss": 0.5525901794433594, "step": 134370 }, { "epoch": 0.7987826262698313, "grad_norm": 1.7061375379562378, "learning_rate": 0.00018526441676674623, "loss": 0.643627405166626, "step": 134380 }, { "epoch": 0.7988420683464997, "grad_norm": 1.7348394393920898, "learning_rate": 0.0001852610034467962, "loss": 0.6718478202819824, "step": 134390 }, { "epoch": 0.7989015104231681, "grad_norm": 1.7527176141738892, "learning_rate": 0.00018525758976682214, "loss": 0.631101417541504, "step": 134400 }, { "epoch": 0.7989609524998366, "grad_norm": 1.7332851886749268, "learning_rate": 0.00018525417572684032, "loss": 0.6369710922241211, "step": 134410 }, { "epoch": 0.799020394576505, "grad_norm": 1.1981639862060547, "learning_rate": 0.00018525076132686714, "loss": 0.6264153957366944, "step": 134420 }, { "epoch": 0.7990798366531733, "grad_norm": 1.6362977027893066, "learning_rate": 0.00018524734656691892, "loss": 0.65437912940979, "step": 134430 }, { "epoch": 0.7991392787298417, "grad_norm": 1.8008681535720825, "learning_rate": 0.00018524393144701194, "loss": 0.6915790557861328, "step": 134440 }, { "epoch": 0.7991987208065101, "grad_norm": 1.7465450763702393, "learning_rate": 0.00018524051596716264, "loss": 0.699445390701294, "step": 134450 }, { "epoch": 0.7992581628831785, "grad_norm": 1.494202733039856, "learning_rate": 0.0001852371001273873, "loss": 0.686436939239502, "step": 134460 }, { "epoch": 0.7993176049598468, "grad_norm": 1.8151311874389648, "learning_rate": 0.00018523368392770218, "loss": 0.6613905906677247, "step": 134470 }, { "epoch": 0.7993770470365152, "grad_norm": 1.5349922180175781, "learning_rate": 0.00018523026736812378, "loss": 0.6537406921386719, "step": 134480 }, { "epoch": 0.7994364891131837, "grad_norm": 1.43008553981781, "learning_rate": 0.00018522685044866833, "loss": 0.7200538635253906, "step": 134490 }, { "epoch": 0.7994959311898521, "grad_norm": 1.6737840175628662, "learning_rate": 0.00018522343316935223, "loss": 0.6518475532531738, "step": 134500 }, { "epoch": 0.7995553732665205, "grad_norm": 1.908539891242981, "learning_rate": 0.0001852200155301918, "loss": 0.608821964263916, "step": 134510 }, { "epoch": 0.7996148153431888, "grad_norm": 1.7882866859436035, "learning_rate": 0.0001852165975312034, "loss": 0.6924870014190674, "step": 134520 }, { "epoch": 0.7996742574198572, "grad_norm": 1.7170233726501465, "learning_rate": 0.00018521317917240339, "loss": 0.6473320960998535, "step": 134530 }, { "epoch": 0.7997336994965256, "grad_norm": 1.5263268947601318, "learning_rate": 0.00018520976045380811, "loss": 0.6247915267944336, "step": 134540 }, { "epoch": 0.799793141573194, "grad_norm": 1.5582815408706665, "learning_rate": 0.00018520634137543388, "loss": 0.61142578125, "step": 134550 }, { "epoch": 0.7998525836498623, "grad_norm": 1.6503150463104248, "learning_rate": 0.00018520292193729713, "loss": 0.6418342113494873, "step": 134560 }, { "epoch": 0.7999120257265308, "grad_norm": 1.6921621561050415, "learning_rate": 0.00018519950213941418, "loss": 0.6592795372009277, "step": 134570 }, { "epoch": 0.7999714678031992, "grad_norm": 1.9907644987106323, "learning_rate": 0.0001851960819818014, "loss": 0.6681346893310547, "step": 134580 }, { "epoch": 0.8000309098798676, "grad_norm": 1.8518695831298828, "learning_rate": 0.00018519266146447508, "loss": 0.6426426887512207, "step": 134590 }, { "epoch": 0.800090351956536, "grad_norm": 1.9681590795516968, "learning_rate": 0.00018518924058745167, "loss": 0.6851473331451416, "step": 134600 }, { "epoch": 0.8001497940332043, "grad_norm": 1.8810980319976807, "learning_rate": 0.0001851858193507475, "loss": 0.6722037315368652, "step": 134610 }, { "epoch": 0.8002092361098727, "grad_norm": 1.4647890329360962, "learning_rate": 0.00018518239775437896, "loss": 0.703333568572998, "step": 134620 }, { "epoch": 0.8002686781865411, "grad_norm": 1.7881717681884766, "learning_rate": 0.0001851789757983624, "loss": 0.6694177627563477, "step": 134630 }, { "epoch": 0.8003281202632095, "grad_norm": 1.339879035949707, "learning_rate": 0.00018517555348271416, "loss": 0.677889633178711, "step": 134640 }, { "epoch": 0.800387562339878, "grad_norm": 1.1300740242004395, "learning_rate": 0.00018517213080745064, "loss": 0.6229431629180908, "step": 134650 }, { "epoch": 0.8004470044165463, "grad_norm": 1.659327507019043, "learning_rate": 0.00018516870777258825, "loss": 0.7017021179199219, "step": 134660 }, { "epoch": 0.8005064464932147, "grad_norm": 1.4545152187347412, "learning_rate": 0.0001851652843781433, "loss": 0.6031276702880859, "step": 134670 }, { "epoch": 0.8005658885698831, "grad_norm": 2.6712381839752197, "learning_rate": 0.0001851618606241322, "loss": 0.7218457221984863, "step": 134680 }, { "epoch": 0.8006253306465515, "grad_norm": 1.6301993131637573, "learning_rate": 0.0001851584365105713, "loss": 0.6317528247833252, "step": 134690 }, { "epoch": 0.8006847727232198, "grad_norm": 1.6951959133148193, "learning_rate": 0.00018515501203747702, "loss": 0.6756857395172119, "step": 134700 }, { "epoch": 0.8007442147998882, "grad_norm": 1.7853868007659912, "learning_rate": 0.00018515158720486575, "loss": 0.7099678993225098, "step": 134710 }, { "epoch": 0.8008036568765566, "grad_norm": 1.6060073375701904, "learning_rate": 0.0001851481620127538, "loss": 0.6723337173461914, "step": 134720 }, { "epoch": 0.800863098953225, "grad_norm": 1.518046498298645, "learning_rate": 0.00018514473646115764, "loss": 0.6488246917724609, "step": 134730 }, { "epoch": 0.8009225410298935, "grad_norm": 1.8600819110870361, "learning_rate": 0.00018514131055009358, "loss": 0.6836412906646728, "step": 134740 }, { "epoch": 0.8009819831065618, "grad_norm": 1.8438640832901, "learning_rate": 0.00018513788427957807, "loss": 0.7029953002929688, "step": 134750 }, { "epoch": 0.8010414251832302, "grad_norm": 1.9972670078277588, "learning_rate": 0.0001851344576496275, "loss": 0.6864490985870362, "step": 134760 }, { "epoch": 0.8011008672598986, "grad_norm": 1.5217509269714355, "learning_rate": 0.00018513103066025821, "loss": 0.7245307445526123, "step": 134770 }, { "epoch": 0.801160309336567, "grad_norm": 2.0756008625030518, "learning_rate": 0.00018512760331148662, "loss": 0.6655783653259277, "step": 134780 }, { "epoch": 0.8012197514132354, "grad_norm": 1.6122922897338867, "learning_rate": 0.00018512417560332916, "loss": 0.6379225254058838, "step": 134790 }, { "epoch": 0.8012791934899037, "grad_norm": 3.480562686920166, "learning_rate": 0.00018512074753580216, "loss": 0.6534655094146729, "step": 134800 }, { "epoch": 0.8013386355665721, "grad_norm": 1.6173704862594604, "learning_rate": 0.00018511731910892206, "loss": 0.6160807609558105, "step": 134810 }, { "epoch": 0.8013980776432406, "grad_norm": 1.165122151374817, "learning_rate": 0.00018511389032270525, "loss": 0.6321640968322754, "step": 134820 }, { "epoch": 0.801457519719909, "grad_norm": 2.2664504051208496, "learning_rate": 0.00018511046117716814, "loss": 0.6598149299621582, "step": 134830 }, { "epoch": 0.8015169617965773, "grad_norm": 1.345792531967163, "learning_rate": 0.00018510703167232714, "loss": 0.694638442993164, "step": 134840 }, { "epoch": 0.8015764038732457, "grad_norm": 1.1790540218353271, "learning_rate": 0.00018510360180819865, "loss": 0.6178157806396485, "step": 134850 }, { "epoch": 0.8016358459499141, "grad_norm": 1.8501384258270264, "learning_rate": 0.00018510017158479908, "loss": 0.6512703418731689, "step": 134860 }, { "epoch": 0.8016952880265825, "grad_norm": 1.3952776193618774, "learning_rate": 0.0001850967410021448, "loss": 0.6581378936767578, "step": 134870 }, { "epoch": 0.8017547301032509, "grad_norm": 1.5162346363067627, "learning_rate": 0.00018509331006025227, "loss": 0.6417883396148681, "step": 134880 }, { "epoch": 0.8018141721799192, "grad_norm": 1.3231595754623413, "learning_rate": 0.00018508987875913787, "loss": 0.6805418014526368, "step": 134890 }, { "epoch": 0.8018736142565877, "grad_norm": 1.58049738407135, "learning_rate": 0.00018508644709881806, "loss": 0.6633638858795166, "step": 134900 }, { "epoch": 0.8019330563332561, "grad_norm": 1.6158008575439453, "learning_rate": 0.0001850830150793092, "loss": 0.6645672798156739, "step": 134910 }, { "epoch": 0.8019924984099245, "grad_norm": 1.6551499366760254, "learning_rate": 0.00018507958270062773, "loss": 0.5656478404998779, "step": 134920 }, { "epoch": 0.8020519404865928, "grad_norm": 1.541306734085083, "learning_rate": 0.0001850761499627901, "loss": 0.642600679397583, "step": 134930 }, { "epoch": 0.8021113825632612, "grad_norm": 1.6812933683395386, "learning_rate": 0.0001850727168658127, "loss": 0.6044220447540283, "step": 134940 }, { "epoch": 0.8021708246399296, "grad_norm": 1.67717707157135, "learning_rate": 0.00018506928340971193, "loss": 0.6741668701171875, "step": 134950 }, { "epoch": 0.802230266716598, "grad_norm": 1.5890283584594727, "learning_rate": 0.00018506584959450425, "loss": 0.6629245758056641, "step": 134960 }, { "epoch": 0.8022897087932664, "grad_norm": 1.404924750328064, "learning_rate": 0.00018506241542020607, "loss": 0.6703257083892822, "step": 134970 }, { "epoch": 0.8023491508699347, "grad_norm": 1.459890604019165, "learning_rate": 0.00018505898088683388, "loss": 0.710352897644043, "step": 134980 }, { "epoch": 0.8024085929466032, "grad_norm": 1.9564096927642822, "learning_rate": 0.000185055545994404, "loss": 0.6724629402160645, "step": 134990 }, { "epoch": 0.8024680350232716, "grad_norm": 1.3722470998764038, "learning_rate": 0.00018505211074293292, "loss": 0.635124683380127, "step": 135000 }, { "epoch": 0.80252747709994, "grad_norm": 1.5564243793487549, "learning_rate": 0.0001850486751324371, "loss": 0.6918906211853028, "step": 135010 }, { "epoch": 0.8025869191766084, "grad_norm": 1.7099946737289429, "learning_rate": 0.0001850452391629329, "loss": 0.6582660675048828, "step": 135020 }, { "epoch": 0.8026463612532767, "grad_norm": 1.827620267868042, "learning_rate": 0.0001850418028344368, "loss": 0.704037094116211, "step": 135030 }, { "epoch": 0.8027058033299451, "grad_norm": 2.275334358215332, "learning_rate": 0.0001850383661469653, "loss": 0.6548820972442627, "step": 135040 }, { "epoch": 0.8027652454066135, "grad_norm": 1.3681267499923706, "learning_rate": 0.00018503492910053473, "loss": 0.7129909038543701, "step": 135050 }, { "epoch": 0.802824687483282, "grad_norm": 1.891329050064087, "learning_rate": 0.0001850314916951616, "loss": 0.6537467002868652, "step": 135060 }, { "epoch": 0.8028841295599503, "grad_norm": 1.8294954299926758, "learning_rate": 0.00018502805393086233, "loss": 0.663211441040039, "step": 135070 }, { "epoch": 0.8029435716366187, "grad_norm": 1.9353976249694824, "learning_rate": 0.00018502461580765337, "loss": 0.6540909290313721, "step": 135080 }, { "epoch": 0.8030030137132871, "grad_norm": 1.63155996799469, "learning_rate": 0.00018502117732555116, "loss": 0.6567354202270508, "step": 135090 }, { "epoch": 0.8030624557899555, "grad_norm": 1.5331509113311768, "learning_rate": 0.00018501773848457215, "loss": 0.676363468170166, "step": 135100 }, { "epoch": 0.8031218978666239, "grad_norm": 2.2265143394470215, "learning_rate": 0.00018501429928473282, "loss": 0.7150491237640381, "step": 135110 }, { "epoch": 0.8031813399432922, "grad_norm": 1.5953292846679688, "learning_rate": 0.00018501085972604957, "loss": 0.6305145263671875, "step": 135120 }, { "epoch": 0.8032407820199606, "grad_norm": 1.8423354625701904, "learning_rate": 0.0001850074198085389, "loss": 0.6373991012573242, "step": 135130 }, { "epoch": 0.803300224096629, "grad_norm": 1.624664545059204, "learning_rate": 0.0001850039795322172, "loss": 0.652344799041748, "step": 135140 }, { "epoch": 0.8033596661732975, "grad_norm": 1.3328044414520264, "learning_rate": 0.00018500053889710104, "loss": 0.6567010402679443, "step": 135150 }, { "epoch": 0.8034191082499659, "grad_norm": 1.96509850025177, "learning_rate": 0.00018499709790320679, "loss": 0.6553933143615722, "step": 135160 }, { "epoch": 0.8034785503266342, "grad_norm": 1.883678674697876, "learning_rate": 0.00018499365655055095, "loss": 0.6759569644927979, "step": 135170 }, { "epoch": 0.8035379924033026, "grad_norm": 1.7856358289718628, "learning_rate": 0.00018499021483914992, "loss": 0.6825413703918457, "step": 135180 }, { "epoch": 0.803597434479971, "grad_norm": 1.3621113300323486, "learning_rate": 0.00018498677276902024, "loss": 0.6180177688598633, "step": 135190 }, { "epoch": 0.8036568765566394, "grad_norm": 2.2452571392059326, "learning_rate": 0.0001849833303401783, "loss": 0.5914238452911377, "step": 135200 }, { "epoch": 0.8037163186333077, "grad_norm": 1.5066746473312378, "learning_rate": 0.00018497988755264067, "loss": 0.5850622653961182, "step": 135210 }, { "epoch": 0.8037757607099761, "grad_norm": 1.7747687101364136, "learning_rate": 0.00018497644440642374, "loss": 0.6412007331848144, "step": 135220 }, { "epoch": 0.8038352027866446, "grad_norm": 1.5544322729110718, "learning_rate": 0.000184973000901544, "loss": 0.6534252166748047, "step": 135230 }, { "epoch": 0.803894644863313, "grad_norm": 1.5548317432403564, "learning_rate": 0.00018496955703801792, "loss": 0.6372124195098877, "step": 135240 }, { "epoch": 0.8039540869399814, "grad_norm": 1.24039626121521, "learning_rate": 0.000184966112815862, "loss": 0.6067675590515137, "step": 135250 }, { "epoch": 0.8040135290166497, "grad_norm": 1.5562963485717773, "learning_rate": 0.0001849626682350927, "loss": 0.630267858505249, "step": 135260 }, { "epoch": 0.8040729710933181, "grad_norm": 1.9019538164138794, "learning_rate": 0.00018495922329572645, "loss": 0.6404961109161377, "step": 135270 }, { "epoch": 0.8041324131699865, "grad_norm": 1.5956270694732666, "learning_rate": 0.0001849557779977798, "loss": 0.692060136795044, "step": 135280 }, { "epoch": 0.8041918552466549, "grad_norm": 1.156185507774353, "learning_rate": 0.0001849523323412692, "loss": 0.6313015937805175, "step": 135290 }, { "epoch": 0.8042512973233232, "grad_norm": 1.7559477090835571, "learning_rate": 0.00018494888632621117, "loss": 0.6843136787414551, "step": 135300 }, { "epoch": 0.8043107393999916, "grad_norm": 1.708675503730774, "learning_rate": 0.00018494543995262213, "loss": 0.6064473628997803, "step": 135310 }, { "epoch": 0.8043701814766601, "grad_norm": 1.9042054414749146, "learning_rate": 0.0001849419932205186, "loss": 0.6586755752563477, "step": 135320 }, { "epoch": 0.8044296235533285, "grad_norm": 1.9747040271759033, "learning_rate": 0.00018493854612991706, "loss": 0.6619968414306641, "step": 135330 }, { "epoch": 0.8044890656299969, "grad_norm": 1.7288473844528198, "learning_rate": 0.00018493509868083402, "loss": 0.6953204154968262, "step": 135340 }, { "epoch": 0.8045485077066652, "grad_norm": 1.6546903848648071, "learning_rate": 0.00018493165087328595, "loss": 0.6756778717041015, "step": 135350 }, { "epoch": 0.8046079497833336, "grad_norm": 1.8637638092041016, "learning_rate": 0.00018492820270728935, "loss": 0.6563800811767578, "step": 135360 }, { "epoch": 0.804667391860002, "grad_norm": 1.5597116947174072, "learning_rate": 0.0001849247541828607, "loss": 0.6009472846984864, "step": 135370 }, { "epoch": 0.8047268339366704, "grad_norm": 1.5399898290634155, "learning_rate": 0.00018492130530001652, "loss": 0.6149118423461915, "step": 135380 }, { "epoch": 0.8047862760133389, "grad_norm": 1.3903464078903198, "learning_rate": 0.00018491785605877329, "loss": 0.6783718585968017, "step": 135390 }, { "epoch": 0.8048457180900072, "grad_norm": 1.434210181236267, "learning_rate": 0.00018491440645914756, "loss": 0.6370443820953369, "step": 135400 }, { "epoch": 0.8049051601666756, "grad_norm": 1.725318431854248, "learning_rate": 0.00018491095650115575, "loss": 0.7249309062957764, "step": 135410 }, { "epoch": 0.804964602243344, "grad_norm": 1.2880820035934448, "learning_rate": 0.00018490750618481444, "loss": 0.6215796947479248, "step": 135420 }, { "epoch": 0.8050240443200124, "grad_norm": 1.8838695287704468, "learning_rate": 0.00018490405551014008, "loss": 0.6925140380859375, "step": 135430 }, { "epoch": 0.8050834863966807, "grad_norm": 1.4682869911193848, "learning_rate": 0.00018490060447714918, "loss": 0.6579019546508789, "step": 135440 }, { "epoch": 0.8051429284733491, "grad_norm": 1.7454890012741089, "learning_rate": 0.00018489715308585828, "loss": 0.6086842060089112, "step": 135450 }, { "epoch": 0.8052023705500175, "grad_norm": 1.759485125541687, "learning_rate": 0.0001848937013362839, "loss": 0.6602506637573242, "step": 135460 }, { "epoch": 0.805261812626686, "grad_norm": 1.6113166809082031, "learning_rate": 0.00018489024922844252, "loss": 0.6838430404663086, "step": 135470 }, { "epoch": 0.8053212547033544, "grad_norm": 1.746124505996704, "learning_rate": 0.00018488679676235064, "loss": 0.6589774131774903, "step": 135480 }, { "epoch": 0.8053806967800227, "grad_norm": 1.919350266456604, "learning_rate": 0.0001848833439380248, "loss": 0.6430659294128418, "step": 135490 }, { "epoch": 0.8054401388566911, "grad_norm": 1.6790069341659546, "learning_rate": 0.00018487989075548154, "loss": 0.6470568180084229, "step": 135500 }, { "epoch": 0.8054995809333595, "grad_norm": 1.658085823059082, "learning_rate": 0.00018487643721473734, "loss": 0.577330207824707, "step": 135510 }, { "epoch": 0.8055590230100279, "grad_norm": 1.2627642154693604, "learning_rate": 0.0001848729833158087, "loss": 0.6405655860900878, "step": 135520 }, { "epoch": 0.8056184650866963, "grad_norm": 2.1009609699249268, "learning_rate": 0.00018486952905871225, "loss": 0.6948592185974121, "step": 135530 }, { "epoch": 0.8056779071633646, "grad_norm": 2.327897787094116, "learning_rate": 0.0001848660744434644, "loss": 0.6608365058898926, "step": 135540 }, { "epoch": 0.805737349240033, "grad_norm": 1.5510565042495728, "learning_rate": 0.00018486261947008167, "loss": 0.6572251319885254, "step": 135550 }, { "epoch": 0.8057967913167015, "grad_norm": 1.9452639818191528, "learning_rate": 0.0001848591641385807, "loss": 0.6673475742340088, "step": 135560 }, { "epoch": 0.8058562333933699, "grad_norm": 2.121276378631592, "learning_rate": 0.00018485570844897794, "loss": 0.6445153713226318, "step": 135570 }, { "epoch": 0.8059156754700382, "grad_norm": 1.5525904893875122, "learning_rate": 0.00018485225240128992, "loss": 0.6633749008178711, "step": 135580 }, { "epoch": 0.8059751175467066, "grad_norm": 1.6933252811431885, "learning_rate": 0.0001848487959955332, "loss": 0.6312330722808838, "step": 135590 }, { "epoch": 0.806034559623375, "grad_norm": 1.3738967180252075, "learning_rate": 0.00018484533923172428, "loss": 0.602029275894165, "step": 135600 }, { "epoch": 0.8060940017000434, "grad_norm": 1.7717353105545044, "learning_rate": 0.00018484188210987973, "loss": 0.743993091583252, "step": 135610 }, { "epoch": 0.8061534437767118, "grad_norm": 1.8385909795761108, "learning_rate": 0.00018483842463001607, "loss": 0.697358512878418, "step": 135620 }, { "epoch": 0.8062128858533801, "grad_norm": 1.705113172531128, "learning_rate": 0.00018483496679214988, "loss": 0.6609506607055664, "step": 135630 }, { "epoch": 0.8062723279300485, "grad_norm": 1.6136585474014282, "learning_rate": 0.00018483150859629764, "loss": 0.6717938423156739, "step": 135640 }, { "epoch": 0.806331770006717, "grad_norm": 1.6141248941421509, "learning_rate": 0.0001848280500424759, "loss": 0.6698897361755372, "step": 135650 }, { "epoch": 0.8063912120833854, "grad_norm": 1.471805453300476, "learning_rate": 0.0001848245911307012, "loss": 0.6297893524169922, "step": 135660 }, { "epoch": 0.8064506541600537, "grad_norm": 1.7723963260650635, "learning_rate": 0.00018482113186099017, "loss": 0.6797056198120117, "step": 135670 }, { "epoch": 0.8065100962367221, "grad_norm": 1.5127811431884766, "learning_rate": 0.00018481767223335927, "loss": 0.6614723205566406, "step": 135680 }, { "epoch": 0.8065695383133905, "grad_norm": 1.9398306608200073, "learning_rate": 0.00018481421224782508, "loss": 0.5544023990631104, "step": 135690 }, { "epoch": 0.8066289803900589, "grad_norm": 1.815954327583313, "learning_rate": 0.00018481075190440415, "loss": 0.6776036262512207, "step": 135700 }, { "epoch": 0.8066884224667273, "grad_norm": 1.4810198545455933, "learning_rate": 0.00018480729120311302, "loss": 0.658942985534668, "step": 135710 }, { "epoch": 0.8067478645433956, "grad_norm": 1.9090533256530762, "learning_rate": 0.00018480383014396825, "loss": 0.650549840927124, "step": 135720 }, { "epoch": 0.8068073066200641, "grad_norm": 1.7987174987792969, "learning_rate": 0.00018480036872698644, "loss": 0.6078814506530762, "step": 135730 }, { "epoch": 0.8068667486967325, "grad_norm": 1.840118646621704, "learning_rate": 0.00018479690695218407, "loss": 0.6362502098083496, "step": 135740 }, { "epoch": 0.8069261907734009, "grad_norm": 1.6583232879638672, "learning_rate": 0.00018479344481957776, "loss": 0.6620522499084472, "step": 135750 }, { "epoch": 0.8069856328500693, "grad_norm": 1.8753814697265625, "learning_rate": 0.00018478998232918404, "loss": 0.6496574401855468, "step": 135760 }, { "epoch": 0.8070450749267376, "grad_norm": 1.650837779045105, "learning_rate": 0.0001847865194810195, "loss": 0.7031050205230713, "step": 135770 }, { "epoch": 0.807104517003406, "grad_norm": 1.9351749420166016, "learning_rate": 0.0001847830562751007, "loss": 0.6532777309417724, "step": 135780 }, { "epoch": 0.8071639590800744, "grad_norm": 1.6898475885391235, "learning_rate": 0.00018477959271144418, "loss": 0.6698395729064941, "step": 135790 }, { "epoch": 0.8072234011567428, "grad_norm": 1.6858760118484497, "learning_rate": 0.00018477612879006655, "loss": 0.6483401775360107, "step": 135800 }, { "epoch": 0.8072828432334112, "grad_norm": 1.617970585823059, "learning_rate": 0.0001847726645109843, "loss": 0.6171142578125, "step": 135810 }, { "epoch": 0.8073422853100796, "grad_norm": 1.4982377290725708, "learning_rate": 0.00018476919987421412, "loss": 0.6821413516998291, "step": 135820 }, { "epoch": 0.807401727386748, "grad_norm": 1.2288168668746948, "learning_rate": 0.00018476573487977252, "loss": 0.6165550231933594, "step": 135830 }, { "epoch": 0.8074611694634164, "grad_norm": 1.7194113731384277, "learning_rate": 0.00018476226952767605, "loss": 0.6880917549133301, "step": 135840 }, { "epoch": 0.8075206115400848, "grad_norm": 1.5865989923477173, "learning_rate": 0.00018475880381794133, "loss": 0.6829442977905273, "step": 135850 }, { "epoch": 0.8075800536167531, "grad_norm": 1.3244445323944092, "learning_rate": 0.00018475533775058492, "loss": 0.656378173828125, "step": 135860 }, { "epoch": 0.8076394956934215, "grad_norm": 1.558980107307434, "learning_rate": 0.0001847518713256234, "loss": 0.7389555931091308, "step": 135870 }, { "epoch": 0.8076989377700899, "grad_norm": 1.3207842111587524, "learning_rate": 0.00018474840454307337, "loss": 0.6363471031188965, "step": 135880 }, { "epoch": 0.8077583798467584, "grad_norm": 1.5878247022628784, "learning_rate": 0.00018474493740295138, "loss": 0.690265417098999, "step": 135890 }, { "epoch": 0.8078178219234268, "grad_norm": 1.507349967956543, "learning_rate": 0.00018474146990527405, "loss": 0.739916181564331, "step": 135900 }, { "epoch": 0.8078772640000951, "grad_norm": 1.4538434743881226, "learning_rate": 0.00018473800205005795, "loss": 0.6646477699279785, "step": 135910 }, { "epoch": 0.8079367060767635, "grad_norm": 1.8030894994735718, "learning_rate": 0.00018473453383731966, "loss": 0.7151436805725098, "step": 135920 }, { "epoch": 0.8079961481534319, "grad_norm": 1.7479944229125977, "learning_rate": 0.00018473106526707583, "loss": 0.6989398956298828, "step": 135930 }, { "epoch": 0.8080555902301003, "grad_norm": 1.8770952224731445, "learning_rate": 0.00018472759633934296, "loss": 0.7018717765808106, "step": 135940 }, { "epoch": 0.8081150323067686, "grad_norm": 1.659637689590454, "learning_rate": 0.0001847241270541377, "loss": 0.720524787902832, "step": 135950 }, { "epoch": 0.808174474383437, "grad_norm": 1.7192214727401733, "learning_rate": 0.00018472065741147664, "loss": 0.6861214637756348, "step": 135960 }, { "epoch": 0.8082339164601055, "grad_norm": 1.7144291400909424, "learning_rate": 0.0001847171874113764, "loss": 0.6368864059448243, "step": 135970 }, { "epoch": 0.8082933585367739, "grad_norm": 2.0817975997924805, "learning_rate": 0.00018471371705385353, "loss": 0.6648606777191162, "step": 135980 }, { "epoch": 0.8083528006134423, "grad_norm": 1.5658659934997559, "learning_rate": 0.0001847102463389246, "loss": 0.7147974967956543, "step": 135990 }, { "epoch": 0.8084122426901106, "grad_norm": 1.306459665298462, "learning_rate": 0.00018470677526660634, "loss": 0.6205597877502441, "step": 136000 }, { "epoch": 0.808471684766779, "grad_norm": 1.7734036445617676, "learning_rate": 0.00018470330383691525, "loss": 0.6921240806579589, "step": 136010 }, { "epoch": 0.8085311268434474, "grad_norm": 2.154926061630249, "learning_rate": 0.00018469983204986797, "loss": 0.6268667697906494, "step": 136020 }, { "epoch": 0.8085905689201158, "grad_norm": 1.6546671390533447, "learning_rate": 0.00018469635990548113, "loss": 0.6345565319061279, "step": 136030 }, { "epoch": 0.8086500109967841, "grad_norm": 1.7226355075836182, "learning_rate": 0.00018469288740377132, "loss": 0.6289602279663086, "step": 136040 }, { "epoch": 0.8087094530734525, "grad_norm": 1.3946119546890259, "learning_rate": 0.0001846894145447551, "loss": 0.7013577461242676, "step": 136050 }, { "epoch": 0.808768895150121, "grad_norm": 1.5017285346984863, "learning_rate": 0.0001846859413284492, "loss": 0.6896665573120118, "step": 136060 }, { "epoch": 0.8088283372267894, "grad_norm": 1.5391829013824463, "learning_rate": 0.0001846824677548701, "loss": 0.6493470191955566, "step": 136070 }, { "epoch": 0.8088877793034578, "grad_norm": 1.480798363685608, "learning_rate": 0.0001846789938240345, "loss": 0.6321340560913086, "step": 136080 }, { "epoch": 0.8089472213801261, "grad_norm": 2.255323886871338, "learning_rate": 0.000184675519535959, "loss": 0.5985666275024414, "step": 136090 }, { "epoch": 0.8090066634567945, "grad_norm": 1.7783275842666626, "learning_rate": 0.0001846720448906602, "loss": 0.6656151294708252, "step": 136100 }, { "epoch": 0.8090661055334629, "grad_norm": 1.475370168685913, "learning_rate": 0.00018466856988815476, "loss": 0.5850875854492188, "step": 136110 }, { "epoch": 0.8091255476101313, "grad_norm": 1.5409773588180542, "learning_rate": 0.0001846650945284593, "loss": 0.6573780059814454, "step": 136120 }, { "epoch": 0.8091849896867997, "grad_norm": 2.080314874649048, "learning_rate": 0.0001846616188115904, "loss": 0.6299825668334961, "step": 136130 }, { "epoch": 0.809244431763468, "grad_norm": 1.936988115310669, "learning_rate": 0.00018465814273756472, "loss": 0.6732770919799804, "step": 136140 }, { "epoch": 0.8093038738401365, "grad_norm": 1.8509596586227417, "learning_rate": 0.0001846546663063989, "loss": 0.6711389541625976, "step": 136150 }, { "epoch": 0.8093633159168049, "grad_norm": 1.698156714439392, "learning_rate": 0.00018465118951810954, "loss": 0.6392224311828614, "step": 136160 }, { "epoch": 0.8094227579934733, "grad_norm": 1.8012959957122803, "learning_rate": 0.00018464771237271328, "loss": 0.6680976867675781, "step": 136170 }, { "epoch": 0.8094822000701416, "grad_norm": 1.3088678121566772, "learning_rate": 0.00018464423487022679, "loss": 0.6136993885040283, "step": 136180 }, { "epoch": 0.80954164214681, "grad_norm": 1.4539672136306763, "learning_rate": 0.00018464075701066666, "loss": 0.6152446269989014, "step": 136190 }, { "epoch": 0.8096010842234784, "grad_norm": 1.5116857290267944, "learning_rate": 0.00018463727879404953, "loss": 0.6343696117401123, "step": 136200 }, { "epoch": 0.8096605263001468, "grad_norm": 1.6432183980941772, "learning_rate": 0.00018463380022039206, "loss": 0.6366344928741455, "step": 136210 }, { "epoch": 0.8097199683768153, "grad_norm": 1.6624239683151245, "learning_rate": 0.00018463032128971087, "loss": 0.6650219440460206, "step": 136220 }, { "epoch": 0.8097794104534836, "grad_norm": 1.5704175233840942, "learning_rate": 0.0001846268420020226, "loss": 0.6525908470153808, "step": 136230 }, { "epoch": 0.809838852530152, "grad_norm": 1.2371798753738403, "learning_rate": 0.00018462336235734392, "loss": 0.6469100952148438, "step": 136240 }, { "epoch": 0.8098982946068204, "grad_norm": 1.7881708145141602, "learning_rate": 0.00018461988235569148, "loss": 0.6860199928283691, "step": 136250 }, { "epoch": 0.8099577366834888, "grad_norm": 1.6375075578689575, "learning_rate": 0.00018461640199708189, "loss": 0.6882884979248047, "step": 136260 }, { "epoch": 0.8100171787601572, "grad_norm": 1.6422876119613647, "learning_rate": 0.00018461292128153182, "loss": 0.6545904159545899, "step": 136270 }, { "epoch": 0.8100766208368255, "grad_norm": 1.1757028102874756, "learning_rate": 0.0001846094402090579, "loss": 0.6841333389282227, "step": 136280 }, { "epoch": 0.8101360629134939, "grad_norm": 1.630520224571228, "learning_rate": 0.00018460595877967684, "loss": 0.6205665588378906, "step": 136290 }, { "epoch": 0.8101955049901624, "grad_norm": 1.2594285011291504, "learning_rate": 0.00018460247699340522, "loss": 0.7077054023742676, "step": 136300 }, { "epoch": 0.8102549470668308, "grad_norm": 1.3430626392364502, "learning_rate": 0.00018459899485025975, "loss": 0.6603019714355469, "step": 136310 }, { "epoch": 0.8103143891434991, "grad_norm": 1.5178743600845337, "learning_rate": 0.00018459551235025707, "loss": 0.6308385848999023, "step": 136320 }, { "epoch": 0.8103738312201675, "grad_norm": 1.6083894968032837, "learning_rate": 0.00018459202949341384, "loss": 0.6374590396881104, "step": 136330 }, { "epoch": 0.8104332732968359, "grad_norm": 1.6791458129882812, "learning_rate": 0.0001845885462797467, "loss": 0.6067626953125, "step": 136340 }, { "epoch": 0.8104927153735043, "grad_norm": 1.572391152381897, "learning_rate": 0.00018458506270927234, "loss": 0.659766674041748, "step": 136350 }, { "epoch": 0.8105521574501727, "grad_norm": 1.7679853439331055, "learning_rate": 0.00018458157878200742, "loss": 0.5726200103759765, "step": 136360 }, { "epoch": 0.810611599526841, "grad_norm": 1.7241840362548828, "learning_rate": 0.00018457809449796858, "loss": 0.6374005794525146, "step": 136370 }, { "epoch": 0.8106710416035094, "grad_norm": 1.4872959852218628, "learning_rate": 0.00018457460985717253, "loss": 0.6786021232604981, "step": 136380 }, { "epoch": 0.8107304836801779, "grad_norm": 1.7412983179092407, "learning_rate": 0.00018457112485963591, "loss": 0.7036745071411132, "step": 136390 }, { "epoch": 0.8107899257568463, "grad_norm": 1.991347312927246, "learning_rate": 0.0001845676395053754, "loss": 0.6014650344848633, "step": 136400 }, { "epoch": 0.8108493678335146, "grad_norm": 1.7446969747543335, "learning_rate": 0.00018456415379440767, "loss": 0.6679507255554199, "step": 136410 }, { "epoch": 0.810908809910183, "grad_norm": 1.9798712730407715, "learning_rate": 0.0001845606677267494, "loss": 0.709780502319336, "step": 136420 }, { "epoch": 0.8109682519868514, "grad_norm": 1.4730091094970703, "learning_rate": 0.00018455718130241724, "loss": 0.6554585456848144, "step": 136430 }, { "epoch": 0.8110276940635198, "grad_norm": 2.0494282245635986, "learning_rate": 0.00018455369452142792, "loss": 0.5806575775146484, "step": 136440 }, { "epoch": 0.8110871361401882, "grad_norm": 1.4987215995788574, "learning_rate": 0.00018455020738379808, "loss": 0.6349583625793457, "step": 136450 }, { "epoch": 0.8111465782168565, "grad_norm": 1.79975426197052, "learning_rate": 0.0001845467198895444, "loss": 0.6997740745544434, "step": 136460 }, { "epoch": 0.811206020293525, "grad_norm": 1.483211636543274, "learning_rate": 0.0001845432320386836, "loss": 0.6662548542022705, "step": 136470 }, { "epoch": 0.8112654623701934, "grad_norm": 1.4312102794647217, "learning_rate": 0.00018453974383123232, "loss": 0.6283405303955079, "step": 136480 }, { "epoch": 0.8113249044468618, "grad_norm": 1.3952586650848389, "learning_rate": 0.00018453625526720728, "loss": 0.5244095802307129, "step": 136490 }, { "epoch": 0.8113843465235302, "grad_norm": 2.027940273284912, "learning_rate": 0.00018453276634662513, "loss": 0.6647528648376465, "step": 136500 }, { "epoch": 0.8114437886001985, "grad_norm": 1.4109653234481812, "learning_rate": 0.0001845292770695026, "loss": 0.6626197814941406, "step": 136510 }, { "epoch": 0.8115032306768669, "grad_norm": 1.7779194116592407, "learning_rate": 0.00018452578743585635, "loss": 0.6728055000305175, "step": 136520 }, { "epoch": 0.8115626727535353, "grad_norm": 1.8042244911193848, "learning_rate": 0.0001845222974457031, "loss": 0.6703508853912353, "step": 136530 }, { "epoch": 0.8116221148302037, "grad_norm": 1.4596693515777588, "learning_rate": 0.00018451880709905954, "loss": 0.6581855773925781, "step": 136540 }, { "epoch": 0.811681556906872, "grad_norm": 1.4292415380477905, "learning_rate": 0.00018451531639594236, "loss": 0.6533473014831543, "step": 136550 }, { "epoch": 0.8117409989835405, "grad_norm": 1.7484798431396484, "learning_rate": 0.00018451182533636823, "loss": 0.6683713436126709, "step": 136560 }, { "epoch": 0.8118004410602089, "grad_norm": 1.7089554071426392, "learning_rate": 0.00018450833392035388, "loss": 0.7114343643188477, "step": 136570 }, { "epoch": 0.8118598831368773, "grad_norm": 1.8160139322280884, "learning_rate": 0.00018450484214791607, "loss": 0.6410129070281982, "step": 136580 }, { "epoch": 0.8119193252135457, "grad_norm": 1.3246653079986572, "learning_rate": 0.0001845013500190714, "loss": 0.6787118911743164, "step": 136590 }, { "epoch": 0.811978767290214, "grad_norm": 1.8473674058914185, "learning_rate": 0.0001844978575338366, "loss": 0.6036339282989502, "step": 136600 }, { "epoch": 0.8120382093668824, "grad_norm": 1.7066106796264648, "learning_rate": 0.00018449436469222843, "loss": 0.711892557144165, "step": 136610 }, { "epoch": 0.8120976514435508, "grad_norm": 1.6586589813232422, "learning_rate": 0.00018449087149426357, "loss": 0.5856692790985107, "step": 136620 }, { "epoch": 0.8121570935202193, "grad_norm": 2.353095531463623, "learning_rate": 0.00018448737793995868, "loss": 0.7261786460876465, "step": 136630 }, { "epoch": 0.8122165355968877, "grad_norm": 1.760538935661316, "learning_rate": 0.00018448388402933052, "loss": 0.6736720085144043, "step": 136640 }, { "epoch": 0.812275977673556, "grad_norm": 1.712196946144104, "learning_rate": 0.00018448038976239586, "loss": 0.6718719005584717, "step": 136650 }, { "epoch": 0.8123354197502244, "grad_norm": 1.576804757118225, "learning_rate": 0.0001844768951391713, "loss": 0.7336122512817382, "step": 136660 }, { "epoch": 0.8123948618268928, "grad_norm": 1.4022607803344727, "learning_rate": 0.00018447340015967365, "loss": 0.650934886932373, "step": 136670 }, { "epoch": 0.8124543039035612, "grad_norm": 1.9232956171035767, "learning_rate": 0.00018446990482391955, "loss": 0.6609325885772706, "step": 136680 }, { "epoch": 0.8125137459802295, "grad_norm": 1.2383919954299927, "learning_rate": 0.00018446640913192579, "loss": 0.5746143341064454, "step": 136690 }, { "epoch": 0.8125731880568979, "grad_norm": 1.753401517868042, "learning_rate": 0.00018446291308370908, "loss": 0.6245539665222168, "step": 136700 }, { "epoch": 0.8126326301335663, "grad_norm": 1.6580538749694824, "learning_rate": 0.0001844594166792861, "loss": 0.6600855350494385, "step": 136710 }, { "epoch": 0.8126920722102348, "grad_norm": 1.6817070245742798, "learning_rate": 0.0001844559199186736, "loss": 0.6793581008911133, "step": 136720 }, { "epoch": 0.8127515142869032, "grad_norm": 1.9070160388946533, "learning_rate": 0.00018445242280188832, "loss": 0.6495877265930176, "step": 136730 }, { "epoch": 0.8128109563635715, "grad_norm": 1.7025620937347412, "learning_rate": 0.000184448925328947, "loss": 0.6775060653686523, "step": 136740 }, { "epoch": 0.8128703984402399, "grad_norm": 1.5724235773086548, "learning_rate": 0.00018444542749986633, "loss": 0.693877124786377, "step": 136750 }, { "epoch": 0.8129298405169083, "grad_norm": 2.097282648086548, "learning_rate": 0.00018444192931466307, "loss": 0.6256946086883545, "step": 136760 }, { "epoch": 0.8129892825935767, "grad_norm": 2.0845301151275635, "learning_rate": 0.00018443843077335393, "loss": 0.6925295829772949, "step": 136770 }, { "epoch": 0.813048724670245, "grad_norm": 1.5730692148208618, "learning_rate": 0.0001844349318759557, "loss": 0.638955020904541, "step": 136780 }, { "epoch": 0.8131081667469134, "grad_norm": 1.366059422492981, "learning_rate": 0.00018443143262248505, "loss": 0.6495309829711914, "step": 136790 }, { "epoch": 0.8131676088235819, "grad_norm": 1.7520637512207031, "learning_rate": 0.00018442793301295875, "loss": 0.6544268608093262, "step": 136800 }, { "epoch": 0.8132270509002503, "grad_norm": 1.7674007415771484, "learning_rate": 0.00018442443304739358, "loss": 0.6476205825805664, "step": 136810 }, { "epoch": 0.8132864929769187, "grad_norm": 1.527600884437561, "learning_rate": 0.0001844209327258062, "loss": 0.6444570064544678, "step": 136820 }, { "epoch": 0.813345935053587, "grad_norm": 1.8750741481781006, "learning_rate": 0.00018441743204821346, "loss": 0.6741657257080078, "step": 136830 }, { "epoch": 0.8134053771302554, "grad_norm": 1.8773598670959473, "learning_rate": 0.00018441393101463198, "loss": 0.6691060066223145, "step": 136840 }, { "epoch": 0.8134648192069238, "grad_norm": 1.6415138244628906, "learning_rate": 0.0001844104296250786, "loss": 0.6887527465820312, "step": 136850 }, { "epoch": 0.8135242612835922, "grad_norm": 1.8228715658187866, "learning_rate": 0.00018440692787957002, "loss": 0.6676450729370117, "step": 136860 }, { "epoch": 0.8135837033602606, "grad_norm": 1.3535677194595337, "learning_rate": 0.00018440342577812308, "loss": 0.6725737571716308, "step": 136870 }, { "epoch": 0.813643145436929, "grad_norm": 1.574874997138977, "learning_rate": 0.0001843999233207544, "loss": 0.7094074249267578, "step": 136880 }, { "epoch": 0.8137025875135974, "grad_norm": 1.8072298765182495, "learning_rate": 0.00018439642050748083, "loss": 0.6718018531799317, "step": 136890 }, { "epoch": 0.8137620295902658, "grad_norm": 1.6886811256408691, "learning_rate": 0.00018439291733831907, "loss": 0.6235470771789551, "step": 136900 }, { "epoch": 0.8138214716669342, "grad_norm": 1.7704544067382812, "learning_rate": 0.00018438941381328594, "loss": 0.6569378852844239, "step": 136910 }, { "epoch": 0.8138809137436025, "grad_norm": 1.676528811454773, "learning_rate": 0.00018438590993239814, "loss": 0.6412464141845703, "step": 136920 }, { "epoch": 0.8139403558202709, "grad_norm": 1.5398271083831787, "learning_rate": 0.00018438240569567247, "loss": 0.6168590545654297, "step": 136930 }, { "epoch": 0.8139997978969393, "grad_norm": 1.7435283660888672, "learning_rate": 0.00018437890110312564, "loss": 0.6745424270629883, "step": 136940 }, { "epoch": 0.8140592399736077, "grad_norm": 1.716447114944458, "learning_rate": 0.0001843753961547745, "loss": 0.6716057777404785, "step": 136950 }, { "epoch": 0.8141186820502762, "grad_norm": 1.6099785566329956, "learning_rate": 0.0001843718908506358, "loss": 0.6297470569610596, "step": 136960 }, { "epoch": 0.8141781241269445, "grad_norm": 2.1074259281158447, "learning_rate": 0.00018436838519072618, "loss": 0.6457676887512207, "step": 136970 }, { "epoch": 0.8142375662036129, "grad_norm": 1.8187617063522339, "learning_rate": 0.0001843648791750626, "loss": 0.6950047016143799, "step": 136980 }, { "epoch": 0.8142970082802813, "grad_norm": 1.3786364793777466, "learning_rate": 0.0001843613728036617, "loss": 0.5851208209991455, "step": 136990 }, { "epoch": 0.8143564503569497, "grad_norm": 1.7143442630767822, "learning_rate": 0.0001843578660765403, "loss": 0.7326460361480713, "step": 137000 }, { "epoch": 0.8144158924336181, "grad_norm": 1.6845911741256714, "learning_rate": 0.00018435435899371517, "loss": 0.697344970703125, "step": 137010 }, { "epoch": 0.8144753345102864, "grad_norm": 1.2597498893737793, "learning_rate": 0.0001843508515552031, "loss": 0.6153323650360107, "step": 137020 }, { "epoch": 0.8145347765869548, "grad_norm": 1.861348271369934, "learning_rate": 0.00018434734376102083, "loss": 0.6625799179077149, "step": 137030 }, { "epoch": 0.8145942186636232, "grad_norm": 1.6845966577529907, "learning_rate": 0.0001843438356111852, "loss": 0.6442493915557861, "step": 137040 }, { "epoch": 0.8146536607402917, "grad_norm": 1.9877471923828125, "learning_rate": 0.00018434032710571295, "loss": 0.669914722442627, "step": 137050 }, { "epoch": 0.81471310281696, "grad_norm": 1.5980817079544067, "learning_rate": 0.0001843368182446208, "loss": 0.6905066490173339, "step": 137060 }, { "epoch": 0.8147725448936284, "grad_norm": 1.65580153465271, "learning_rate": 0.00018433330902792568, "loss": 0.6541632652282715, "step": 137070 }, { "epoch": 0.8148319869702968, "grad_norm": 1.6952478885650635, "learning_rate": 0.00018432979945564427, "loss": 0.6693746089935303, "step": 137080 }, { "epoch": 0.8148914290469652, "grad_norm": 2.2446682453155518, "learning_rate": 0.00018432628952779343, "loss": 0.6868160247802735, "step": 137090 }, { "epoch": 0.8149508711236336, "grad_norm": 1.5886889696121216, "learning_rate": 0.00018432277924438988, "loss": 0.6811857223510742, "step": 137100 }, { "epoch": 0.8150103132003019, "grad_norm": 1.6750527620315552, "learning_rate": 0.00018431926860545042, "loss": 0.616605567932129, "step": 137110 }, { "epoch": 0.8150697552769703, "grad_norm": 2.258410692214966, "learning_rate": 0.0001843157576109919, "loss": 0.6325060844421386, "step": 137120 }, { "epoch": 0.8151291973536388, "grad_norm": 1.724623441696167, "learning_rate": 0.00018431224626103108, "loss": 0.7072311401367187, "step": 137130 }, { "epoch": 0.8151886394303072, "grad_norm": 1.5310688018798828, "learning_rate": 0.00018430873455558476, "loss": 0.6384823799133301, "step": 137140 }, { "epoch": 0.8152480815069755, "grad_norm": 1.9462015628814697, "learning_rate": 0.0001843052224946697, "loss": 0.628560733795166, "step": 137150 }, { "epoch": 0.8153075235836439, "grad_norm": 1.5798381567001343, "learning_rate": 0.0001843017100783028, "loss": 0.6443404674530029, "step": 137160 }, { "epoch": 0.8153669656603123, "grad_norm": 1.3622931241989136, "learning_rate": 0.00018429819730650076, "loss": 0.661983585357666, "step": 137170 }, { "epoch": 0.8154264077369807, "grad_norm": 1.7934106588363647, "learning_rate": 0.00018429468417928042, "loss": 0.6921409130096435, "step": 137180 }, { "epoch": 0.8154858498136491, "grad_norm": 1.9324859380722046, "learning_rate": 0.00018429117069665863, "loss": 0.6192627906799316, "step": 137190 }, { "epoch": 0.8155452918903174, "grad_norm": 1.253281593322754, "learning_rate": 0.00018428765685865213, "loss": 0.690265703201294, "step": 137200 }, { "epoch": 0.8156047339669859, "grad_norm": 1.7558603286743164, "learning_rate": 0.00018428414266527776, "loss": 0.6469786643981934, "step": 137210 }, { "epoch": 0.8156641760436543, "grad_norm": 1.539294958114624, "learning_rate": 0.0001842806281165523, "loss": 0.6679361820220947, "step": 137220 }, { "epoch": 0.8157236181203227, "grad_norm": 1.653427004814148, "learning_rate": 0.00018427711321249263, "loss": 0.6012374877929687, "step": 137230 }, { "epoch": 0.8157830601969911, "grad_norm": 1.4739258289337158, "learning_rate": 0.0001842735979531155, "loss": 0.6637004852294922, "step": 137240 }, { "epoch": 0.8158425022736594, "grad_norm": 1.8034180402755737, "learning_rate": 0.0001842700823384378, "loss": 0.6652087211608887, "step": 137250 }, { "epoch": 0.8159019443503278, "grad_norm": 1.272605299949646, "learning_rate": 0.00018426656636847625, "loss": 0.606210994720459, "step": 137260 }, { "epoch": 0.8159613864269962, "grad_norm": 1.919496774673462, "learning_rate": 0.00018426305004324772, "loss": 0.6389154911041259, "step": 137270 }, { "epoch": 0.8160208285036646, "grad_norm": 1.575308918952942, "learning_rate": 0.00018425953336276906, "loss": 0.6649924755096436, "step": 137280 }, { "epoch": 0.816080270580333, "grad_norm": 1.9260170459747314, "learning_rate": 0.000184256016327057, "loss": 0.6469389438629151, "step": 137290 }, { "epoch": 0.8161397126570014, "grad_norm": 1.6036986112594604, "learning_rate": 0.00018425249893612848, "loss": 0.6913352966308594, "step": 137300 }, { "epoch": 0.8161991547336698, "grad_norm": 1.6234749555587769, "learning_rate": 0.00018424898119000026, "loss": 0.6823503494262695, "step": 137310 }, { "epoch": 0.8162585968103382, "grad_norm": 1.6429990530014038, "learning_rate": 0.0001842454630886892, "loss": 0.6135010242462158, "step": 137320 }, { "epoch": 0.8163180388870066, "grad_norm": 1.7230305671691895, "learning_rate": 0.00018424194463221205, "loss": 0.6880539417266845, "step": 137330 }, { "epoch": 0.8163774809636749, "grad_norm": 1.6805353164672852, "learning_rate": 0.00018423842582058575, "loss": 0.6959150314331055, "step": 137340 }, { "epoch": 0.8164369230403433, "grad_norm": 1.7525742053985596, "learning_rate": 0.00018423490665382705, "loss": 0.6580565452575684, "step": 137350 }, { "epoch": 0.8164963651170117, "grad_norm": 1.6151694059371948, "learning_rate": 0.00018423138713195283, "loss": 0.6826357841491699, "step": 137360 }, { "epoch": 0.8165558071936801, "grad_norm": 2.3787553310394287, "learning_rate": 0.0001842278672549799, "loss": 0.6709346771240234, "step": 137370 }, { "epoch": 0.8166152492703486, "grad_norm": 1.505982518196106, "learning_rate": 0.00018422434702292513, "loss": 0.6172049045562744, "step": 137380 }, { "epoch": 0.8166746913470169, "grad_norm": 1.673762559890747, "learning_rate": 0.00018422082643580534, "loss": 0.6499358177185058, "step": 137390 }, { "epoch": 0.8167341334236853, "grad_norm": 1.8653253316879272, "learning_rate": 0.00018421730549363736, "loss": 0.6721207141876221, "step": 137400 }, { "epoch": 0.8167935755003537, "grad_norm": 1.4851528406143188, "learning_rate": 0.00018421378419643803, "loss": 0.6722000122070313, "step": 137410 }, { "epoch": 0.8168530175770221, "grad_norm": 1.3999922275543213, "learning_rate": 0.00018421026254422426, "loss": 0.619837760925293, "step": 137420 }, { "epoch": 0.8169124596536904, "grad_norm": 1.4954034090042114, "learning_rate": 0.0001842067405370128, "loss": 0.6811851501464844, "step": 137430 }, { "epoch": 0.8169719017303588, "grad_norm": 1.540614128112793, "learning_rate": 0.00018420321817482055, "loss": 0.6661629199981689, "step": 137440 }, { "epoch": 0.8170313438070272, "grad_norm": 1.563471794128418, "learning_rate": 0.00018419969545766437, "loss": 0.6728699684143067, "step": 137450 }, { "epoch": 0.8170907858836957, "grad_norm": 1.707946538925171, "learning_rate": 0.00018419617238556112, "loss": 0.6252568244934082, "step": 137460 }, { "epoch": 0.8171502279603641, "grad_norm": 2.037302017211914, "learning_rate": 0.00018419264895852758, "loss": 0.6955066680908203, "step": 137470 }, { "epoch": 0.8172096700370324, "grad_norm": 1.5213552713394165, "learning_rate": 0.00018418912517658068, "loss": 0.6448589324951172, "step": 137480 }, { "epoch": 0.8172691121137008, "grad_norm": 1.4900949001312256, "learning_rate": 0.00018418560103973725, "loss": 0.7281956672668457, "step": 137490 }, { "epoch": 0.8173285541903692, "grad_norm": 1.2960155010223389, "learning_rate": 0.00018418207654801415, "loss": 0.6335296630859375, "step": 137500 }, { "epoch": 0.8173879962670376, "grad_norm": 1.4707926511764526, "learning_rate": 0.0001841785517014282, "loss": 0.5941593170166015, "step": 137510 }, { "epoch": 0.8174474383437059, "grad_norm": 1.6557331085205078, "learning_rate": 0.00018417502649999636, "loss": 0.6711856365203858, "step": 137520 }, { "epoch": 0.8175068804203743, "grad_norm": 1.7636326551437378, "learning_rate": 0.0001841715009437354, "loss": 0.6245480537414551, "step": 137530 }, { "epoch": 0.8175663224970428, "grad_norm": 1.7350623607635498, "learning_rate": 0.00018416797503266222, "loss": 0.6861658096313477, "step": 137540 }, { "epoch": 0.8176257645737112, "grad_norm": 1.5187888145446777, "learning_rate": 0.0001841644487667937, "loss": 0.6605801582336426, "step": 137550 }, { "epoch": 0.8176852066503796, "grad_norm": 1.54364812374115, "learning_rate": 0.00018416092214614669, "loss": 0.6147935867309571, "step": 137560 }, { "epoch": 0.8177446487270479, "grad_norm": 1.5697613954544067, "learning_rate": 0.00018415739517073807, "loss": 0.6570589065551757, "step": 137570 }, { "epoch": 0.8178040908037163, "grad_norm": 1.666115403175354, "learning_rate": 0.00018415386784058468, "loss": 0.6491377830505372, "step": 137580 }, { "epoch": 0.8178635328803847, "grad_norm": 1.3356969356536865, "learning_rate": 0.00018415034015570344, "loss": 0.7236527442932129, "step": 137590 }, { "epoch": 0.8179229749570531, "grad_norm": 1.3288458585739136, "learning_rate": 0.0001841468121161112, "loss": 0.6850086212158203, "step": 137600 }, { "epoch": 0.8179824170337215, "grad_norm": 1.6894733905792236, "learning_rate": 0.00018414328372182484, "loss": 0.6932991027832032, "step": 137610 }, { "epoch": 0.8180418591103898, "grad_norm": 1.5234991312026978, "learning_rate": 0.00018413975497286124, "loss": 0.6909432411193848, "step": 137620 }, { "epoch": 0.8181013011870583, "grad_norm": 1.794419527053833, "learning_rate": 0.00018413622586923732, "loss": 0.6739393711090088, "step": 137630 }, { "epoch": 0.8181607432637267, "grad_norm": 1.5569393634796143, "learning_rate": 0.00018413269641096987, "loss": 0.6218182563781738, "step": 137640 }, { "epoch": 0.8182201853403951, "grad_norm": 1.8220887184143066, "learning_rate": 0.00018412916659807586, "loss": 0.632443904876709, "step": 137650 }, { "epoch": 0.8182796274170634, "grad_norm": 1.5749335289001465, "learning_rate": 0.0001841256364305721, "loss": 0.6394097328186035, "step": 137660 }, { "epoch": 0.8183390694937318, "grad_norm": 1.7206705808639526, "learning_rate": 0.0001841221059084756, "loss": 0.6181053161621094, "step": 137670 }, { "epoch": 0.8183985115704002, "grad_norm": 1.5213980674743652, "learning_rate": 0.00018411857503180309, "loss": 0.5963541030883789, "step": 137680 }, { "epoch": 0.8184579536470686, "grad_norm": 1.7137353420257568, "learning_rate": 0.00018411504380057154, "loss": 0.6170572280883789, "step": 137690 }, { "epoch": 0.818517395723737, "grad_norm": 1.4996411800384521, "learning_rate": 0.0001841115122147979, "loss": 0.6022642135620118, "step": 137700 }, { "epoch": 0.8185768378004054, "grad_norm": 1.531412959098816, "learning_rate": 0.00018410798027449895, "loss": 0.6425973415374756, "step": 137710 }, { "epoch": 0.8186362798770738, "grad_norm": 1.6187821626663208, "learning_rate": 0.00018410444797969168, "loss": 0.6934703350067138, "step": 137720 }, { "epoch": 0.8186957219537422, "grad_norm": 1.6857842206954956, "learning_rate": 0.00018410091533039292, "loss": 0.6905471801757812, "step": 137730 }, { "epoch": 0.8187551640304106, "grad_norm": 1.5336028337478638, "learning_rate": 0.00018409738232661962, "loss": 0.657513952255249, "step": 137740 }, { "epoch": 0.8188146061070789, "grad_norm": 1.4831328392028809, "learning_rate": 0.00018409384896838867, "loss": 0.6820239543914794, "step": 137750 }, { "epoch": 0.8188740481837473, "grad_norm": 1.5889885425567627, "learning_rate": 0.0001840903152557169, "loss": 0.6692285537719727, "step": 137760 }, { "epoch": 0.8189334902604157, "grad_norm": 1.3720479011535645, "learning_rate": 0.00018408678118862136, "loss": 0.646329402923584, "step": 137770 }, { "epoch": 0.8189929323370841, "grad_norm": 1.6414169073104858, "learning_rate": 0.0001840832467671188, "loss": 0.7221789360046387, "step": 137780 }, { "epoch": 0.8190523744137526, "grad_norm": 1.6778963804244995, "learning_rate": 0.00018407971199122625, "loss": 0.621405839920044, "step": 137790 }, { "epoch": 0.8191118164904209, "grad_norm": 1.526699185371399, "learning_rate": 0.00018407617686096053, "loss": 0.6571609497070312, "step": 137800 }, { "epoch": 0.8191712585670893, "grad_norm": 1.7421488761901855, "learning_rate": 0.00018407264137633856, "loss": 0.688832426071167, "step": 137810 }, { "epoch": 0.8192307006437577, "grad_norm": 1.669465184211731, "learning_rate": 0.00018406910553737734, "loss": 0.6542107105255127, "step": 137820 }, { "epoch": 0.8192901427204261, "grad_norm": 1.7135734558105469, "learning_rate": 0.0001840655693440937, "loss": 0.6434449195861817, "step": 137830 }, { "epoch": 0.8193495847970945, "grad_norm": 1.2869601249694824, "learning_rate": 0.0001840620327965046, "loss": 0.6307306289672852, "step": 137840 }, { "epoch": 0.8194090268737628, "grad_norm": 1.810364842414856, "learning_rate": 0.00018405849589462695, "loss": 0.6748405456542969, "step": 137850 }, { "epoch": 0.8194684689504312, "grad_norm": 1.9024269580841064, "learning_rate": 0.0001840549586384776, "loss": 0.7215198516845703, "step": 137860 }, { "epoch": 0.8195279110270997, "grad_norm": 1.3442738056182861, "learning_rate": 0.00018405142102807356, "loss": 0.6634572982788086, "step": 137870 }, { "epoch": 0.8195873531037681, "grad_norm": 1.6452910900115967, "learning_rate": 0.00018404788306343174, "loss": 0.6382081508636475, "step": 137880 }, { "epoch": 0.8196467951804364, "grad_norm": 2.02116060256958, "learning_rate": 0.000184044344744569, "loss": 0.7584084510803223, "step": 137890 }, { "epoch": 0.8197062372571048, "grad_norm": 1.4399032592773438, "learning_rate": 0.00018404080607150239, "loss": 0.6765772819519043, "step": 137900 }, { "epoch": 0.8197656793337732, "grad_norm": 1.6075135469436646, "learning_rate": 0.0001840372670442487, "loss": 0.6352442741394043, "step": 137910 }, { "epoch": 0.8198251214104416, "grad_norm": 1.6465414762496948, "learning_rate": 0.0001840337276628249, "loss": 0.6977739334106445, "step": 137920 }, { "epoch": 0.81988456348711, "grad_norm": 1.8812129497528076, "learning_rate": 0.000184030187927248, "loss": 0.6572466373443604, "step": 137930 }, { "epoch": 0.8199440055637783, "grad_norm": 1.864540696144104, "learning_rate": 0.00018402664783753484, "loss": 0.6680929660797119, "step": 137940 }, { "epoch": 0.8200034476404467, "grad_norm": 1.7006090879440308, "learning_rate": 0.00018402310739370242, "loss": 0.6587743759155273, "step": 137950 }, { "epoch": 0.8200628897171152, "grad_norm": 1.695481300354004, "learning_rate": 0.00018401956659576762, "loss": 0.6081056594848633, "step": 137960 }, { "epoch": 0.8201223317937836, "grad_norm": 1.9843811988830566, "learning_rate": 0.0001840160254437474, "loss": 0.6416284561157226, "step": 137970 }, { "epoch": 0.820181773870452, "grad_norm": 1.6069066524505615, "learning_rate": 0.00018401248393765872, "loss": 0.6883028030395508, "step": 137980 }, { "epoch": 0.8202412159471203, "grad_norm": 1.9351164102554321, "learning_rate": 0.0001840089420775185, "loss": 0.7012135028839112, "step": 137990 }, { "epoch": 0.8203006580237887, "grad_norm": 1.451033592224121, "learning_rate": 0.00018400539986334366, "loss": 0.6150205612182618, "step": 138000 }, { "epoch": 0.8203601001004571, "grad_norm": 1.8331389427185059, "learning_rate": 0.00018400185729515123, "loss": 0.6382241249084473, "step": 138010 }, { "epoch": 0.8204195421771255, "grad_norm": 2.043970823287964, "learning_rate": 0.00018399831437295805, "loss": 0.7107403755187989, "step": 138020 }, { "epoch": 0.8204789842537938, "grad_norm": 1.7522752285003662, "learning_rate": 0.00018399477109678114, "loss": 0.6805920600891113, "step": 138030 }, { "epoch": 0.8205384263304623, "grad_norm": 1.532375693321228, "learning_rate": 0.00018399122746663743, "loss": 0.7283000946044922, "step": 138040 }, { "epoch": 0.8205978684071307, "grad_norm": 1.2644623517990112, "learning_rate": 0.00018398768348254382, "loss": 0.631981086730957, "step": 138050 }, { "epoch": 0.8206573104837991, "grad_norm": 1.3580896854400635, "learning_rate": 0.00018398413914451735, "loss": 0.6659152984619141, "step": 138060 }, { "epoch": 0.8207167525604675, "grad_norm": 1.9743152856826782, "learning_rate": 0.00018398059445257493, "loss": 0.6694717407226562, "step": 138070 }, { "epoch": 0.8207761946371358, "grad_norm": 1.8083668947219849, "learning_rate": 0.00018397704940673355, "loss": 0.6801936149597168, "step": 138080 }, { "epoch": 0.8208356367138042, "grad_norm": 1.439568042755127, "learning_rate": 0.00018397350400701013, "loss": 0.5806924343109131, "step": 138090 }, { "epoch": 0.8208950787904726, "grad_norm": 1.5848904848098755, "learning_rate": 0.0001839699582534216, "loss": 0.6246675968170166, "step": 138100 }, { "epoch": 0.820954520867141, "grad_norm": 1.1241848468780518, "learning_rate": 0.00018396641214598502, "loss": 0.5657513618469239, "step": 138110 }, { "epoch": 0.8210139629438094, "grad_norm": 1.8420246839523315, "learning_rate": 0.00018396286568471727, "loss": 0.6949440956115722, "step": 138120 }, { "epoch": 0.8210734050204778, "grad_norm": 2.7133941650390625, "learning_rate": 0.00018395931886963535, "loss": 0.6496167182922363, "step": 138130 }, { "epoch": 0.8211328470971462, "grad_norm": 1.5139747858047485, "learning_rate": 0.0001839557717007562, "loss": 0.6535471916198731, "step": 138140 }, { "epoch": 0.8211922891738146, "grad_norm": 1.6148653030395508, "learning_rate": 0.0001839522241780968, "loss": 0.6472501754760742, "step": 138150 }, { "epoch": 0.821251731250483, "grad_norm": 1.5486111640930176, "learning_rate": 0.00018394867630167416, "loss": 0.6773430824279785, "step": 138160 }, { "epoch": 0.8213111733271513, "grad_norm": 1.630105972290039, "learning_rate": 0.00018394512807150523, "loss": 0.6419234275817871, "step": 138170 }, { "epoch": 0.8213706154038197, "grad_norm": 1.3927595615386963, "learning_rate": 0.00018394157948760693, "loss": 0.6539562225341797, "step": 138180 }, { "epoch": 0.8214300574804881, "grad_norm": 1.4218924045562744, "learning_rate": 0.0001839380305499963, "loss": 0.6589048385620118, "step": 138190 }, { "epoch": 0.8214894995571566, "grad_norm": 1.5075476169586182, "learning_rate": 0.00018393448125869028, "loss": 0.5860811233520508, "step": 138200 }, { "epoch": 0.821548941633825, "grad_norm": 1.8445026874542236, "learning_rate": 0.0001839309316137059, "loss": 0.6623448371887207, "step": 138210 }, { "epoch": 0.8216083837104933, "grad_norm": 1.5140174627304077, "learning_rate": 0.00018392738161506007, "loss": 0.6647495269775391, "step": 138220 }, { "epoch": 0.8216678257871617, "grad_norm": 1.6202800273895264, "learning_rate": 0.0001839238312627698, "loss": 0.6841062068939209, "step": 138230 }, { "epoch": 0.8217272678638301, "grad_norm": 1.6645424365997314, "learning_rate": 0.0001839202805568521, "loss": 0.6874838829040527, "step": 138240 }, { "epoch": 0.8217867099404985, "grad_norm": 1.4587234258651733, "learning_rate": 0.00018391672949732394, "loss": 0.6169082641601562, "step": 138250 }, { "epoch": 0.8218461520171668, "grad_norm": 2.2220849990844727, "learning_rate": 0.00018391317808420226, "loss": 0.6581609725952149, "step": 138260 }, { "epoch": 0.8219055940938352, "grad_norm": 1.371888279914856, "learning_rate": 0.00018390962631750416, "loss": 0.6369139671325683, "step": 138270 }, { "epoch": 0.8219650361705036, "grad_norm": 1.8276830911636353, "learning_rate": 0.00018390607419724653, "loss": 0.6642309188842773, "step": 138280 }, { "epoch": 0.8220244782471721, "grad_norm": 1.536207675933838, "learning_rate": 0.00018390252172344638, "loss": 0.6882461547851563, "step": 138290 }, { "epoch": 0.8220839203238405, "grad_norm": 1.686163306236267, "learning_rate": 0.00018389896889612072, "loss": 0.7010043144226075, "step": 138300 }, { "epoch": 0.8221433624005088, "grad_norm": 1.4411319494247437, "learning_rate": 0.00018389541571528655, "loss": 0.6471270084381103, "step": 138310 }, { "epoch": 0.8222028044771772, "grad_norm": 3.3611042499542236, "learning_rate": 0.00018389186218096087, "loss": 0.6784364700317382, "step": 138320 }, { "epoch": 0.8222622465538456, "grad_norm": 1.6411466598510742, "learning_rate": 0.00018388830829316067, "loss": 0.731930923461914, "step": 138330 }, { "epoch": 0.822321688630514, "grad_norm": 1.8497188091278076, "learning_rate": 0.00018388475405190294, "loss": 0.6552376747131348, "step": 138340 }, { "epoch": 0.8223811307071824, "grad_norm": 1.9775376319885254, "learning_rate": 0.00018388119945720468, "loss": 0.6270201683044434, "step": 138350 }, { "epoch": 0.8224405727838507, "grad_norm": 1.4249565601348877, "learning_rate": 0.00018387764450908292, "loss": 0.6380139350891113, "step": 138360 }, { "epoch": 0.8225000148605192, "grad_norm": 1.6073113679885864, "learning_rate": 0.00018387408920755464, "loss": 0.6729668617248535, "step": 138370 }, { "epoch": 0.8225594569371876, "grad_norm": 1.7021108865737915, "learning_rate": 0.00018387053355263687, "loss": 0.7048233032226563, "step": 138380 }, { "epoch": 0.822618899013856, "grad_norm": 1.9124817848205566, "learning_rate": 0.0001838669775443466, "loss": 0.6440184593200684, "step": 138390 }, { "epoch": 0.8226783410905243, "grad_norm": 1.5663294792175293, "learning_rate": 0.00018386342118270087, "loss": 0.6565764904022217, "step": 138400 }, { "epoch": 0.8227377831671927, "grad_norm": 1.883501648902893, "learning_rate": 0.00018385986446771668, "loss": 0.647270679473877, "step": 138410 }, { "epoch": 0.8227972252438611, "grad_norm": 1.5159560441970825, "learning_rate": 0.000183856307399411, "loss": 0.6138917922973632, "step": 138420 }, { "epoch": 0.8228566673205295, "grad_norm": 2.565842390060425, "learning_rate": 0.0001838527499778009, "loss": 0.6510462760925293, "step": 138430 }, { "epoch": 0.822916109397198, "grad_norm": 1.6316636800765991, "learning_rate": 0.0001838491922029034, "loss": 0.6605905532836914, "step": 138440 }, { "epoch": 0.8229755514738663, "grad_norm": 2.35627818107605, "learning_rate": 0.00018384563407473545, "loss": 0.6836775779724121, "step": 138450 }, { "epoch": 0.8230349935505347, "grad_norm": 1.9254083633422852, "learning_rate": 0.00018384207559331417, "loss": 0.7071382522583007, "step": 138460 }, { "epoch": 0.8230944356272031, "grad_norm": 1.67486572265625, "learning_rate": 0.00018383851675865648, "loss": 0.6249436378479004, "step": 138470 }, { "epoch": 0.8231538777038715, "grad_norm": 3.275084972381592, "learning_rate": 0.0001838349575707795, "loss": 0.6321230888366699, "step": 138480 }, { "epoch": 0.8232133197805398, "grad_norm": 1.9652650356292725, "learning_rate": 0.0001838313980297002, "loss": 0.6150280952453613, "step": 138490 }, { "epoch": 0.8232727618572082, "grad_norm": 1.7830688953399658, "learning_rate": 0.00018382783813543563, "loss": 0.6861268520355225, "step": 138500 }, { "epoch": 0.8233322039338766, "grad_norm": 1.4585500955581665, "learning_rate": 0.00018382427788800278, "loss": 0.6315697193145752, "step": 138510 }, { "epoch": 0.823391646010545, "grad_norm": 1.9851529598236084, "learning_rate": 0.0001838207172874187, "loss": 0.6526654243469239, "step": 138520 }, { "epoch": 0.8234510880872135, "grad_norm": 1.1418542861938477, "learning_rate": 0.00018381715633370048, "loss": 0.7024715423583985, "step": 138530 }, { "epoch": 0.8235105301638818, "grad_norm": 1.9749947786331177, "learning_rate": 0.0001838135950268651, "loss": 0.7076011657714844, "step": 138540 }, { "epoch": 0.8235699722405502, "grad_norm": 1.6334408521652222, "learning_rate": 0.0001838100333669296, "loss": 0.6224171161651612, "step": 138550 }, { "epoch": 0.8236294143172186, "grad_norm": 1.6100997924804688, "learning_rate": 0.00018380647135391102, "loss": 0.712092399597168, "step": 138560 }, { "epoch": 0.823688856393887, "grad_norm": 1.9404208660125732, "learning_rate": 0.00018380290898782636, "loss": 0.6842644691467286, "step": 138570 }, { "epoch": 0.8237482984705554, "grad_norm": 1.8919788599014282, "learning_rate": 0.00018379934626869276, "loss": 0.5858197689056397, "step": 138580 }, { "epoch": 0.8238077405472237, "grad_norm": 1.7203142642974854, "learning_rate": 0.0001837957831965272, "loss": 0.6933398723602295, "step": 138590 }, { "epoch": 0.8238671826238921, "grad_norm": 1.8139883279800415, "learning_rate": 0.00018379221977134672, "loss": 0.6174729347229004, "step": 138600 }, { "epoch": 0.8239266247005606, "grad_norm": 1.8157100677490234, "learning_rate": 0.00018378865599316834, "loss": 0.6354658126831054, "step": 138610 }, { "epoch": 0.823986066777229, "grad_norm": 1.8577176332473755, "learning_rate": 0.00018378509186200919, "loss": 0.7237996101379395, "step": 138620 }, { "epoch": 0.8240455088538973, "grad_norm": 1.5550577640533447, "learning_rate": 0.00018378152737788626, "loss": 0.665675163269043, "step": 138630 }, { "epoch": 0.8241049509305657, "grad_norm": 1.7407903671264648, "learning_rate": 0.0001837779625408166, "loss": 0.6608234882354737, "step": 138640 }, { "epoch": 0.8241643930072341, "grad_norm": 1.108555793762207, "learning_rate": 0.0001837743973508173, "loss": 0.6482666969299317, "step": 138650 }, { "epoch": 0.8242238350839025, "grad_norm": 1.744316577911377, "learning_rate": 0.0001837708318079054, "loss": 0.6133774757385254, "step": 138660 }, { "epoch": 0.8242832771605709, "grad_norm": 1.674469232559204, "learning_rate": 0.00018376726591209791, "loss": 0.6661540031433105, "step": 138670 }, { "epoch": 0.8243427192372392, "grad_norm": 1.5847797393798828, "learning_rate": 0.00018376369966341196, "loss": 0.6072173118591309, "step": 138680 }, { "epoch": 0.8244021613139076, "grad_norm": 1.5881731510162354, "learning_rate": 0.00018376013306186458, "loss": 0.6122072219848633, "step": 138690 }, { "epoch": 0.8244616033905761, "grad_norm": 1.4944782257080078, "learning_rate": 0.0001837565661074728, "loss": 0.6914706707000733, "step": 138700 }, { "epoch": 0.8245210454672445, "grad_norm": 1.419124722480774, "learning_rate": 0.00018375299880025374, "loss": 0.649553918838501, "step": 138710 }, { "epoch": 0.8245804875439129, "grad_norm": 2.0994367599487305, "learning_rate": 0.00018374943114022444, "loss": 0.6515393257141113, "step": 138720 }, { "epoch": 0.8246399296205812, "grad_norm": 1.7017303705215454, "learning_rate": 0.00018374586312740193, "loss": 0.6488288879394531, "step": 138730 }, { "epoch": 0.8246993716972496, "grad_norm": 1.6217243671417236, "learning_rate": 0.00018374229476180332, "loss": 0.6903774261474609, "step": 138740 }, { "epoch": 0.824758813773918, "grad_norm": 1.8396070003509521, "learning_rate": 0.00018373872604344566, "loss": 0.7283269882202148, "step": 138750 }, { "epoch": 0.8248182558505864, "grad_norm": 1.7148141860961914, "learning_rate": 0.00018373515697234607, "loss": 0.6717905044555664, "step": 138760 }, { "epoch": 0.8248776979272547, "grad_norm": 1.8885830640792847, "learning_rate": 0.00018373158754852157, "loss": 0.6677103996276855, "step": 138770 }, { "epoch": 0.8249371400039232, "grad_norm": 1.6089916229248047, "learning_rate": 0.00018372801777198926, "loss": 0.6791769027709961, "step": 138780 }, { "epoch": 0.8249965820805916, "grad_norm": 1.7751847505569458, "learning_rate": 0.0001837244476427662, "loss": 0.7071679592132568, "step": 138790 }, { "epoch": 0.82505602415726, "grad_norm": 1.9320476055145264, "learning_rate": 0.00018372087716086945, "loss": 0.6082999229431152, "step": 138800 }, { "epoch": 0.8251154662339284, "grad_norm": 1.7456419467926025, "learning_rate": 0.00018371730632631616, "loss": 0.6746334075927735, "step": 138810 }, { "epoch": 0.8251749083105967, "grad_norm": 1.7869664430618286, "learning_rate": 0.00018371373513912333, "loss": 0.659477949142456, "step": 138820 }, { "epoch": 0.8252343503872651, "grad_norm": 1.7498470544815063, "learning_rate": 0.0001837101635993081, "loss": 0.6330855846405029, "step": 138830 }, { "epoch": 0.8252937924639335, "grad_norm": 1.7413322925567627, "learning_rate": 0.00018370659170688757, "loss": 0.6505252838134765, "step": 138840 }, { "epoch": 0.8253532345406019, "grad_norm": 1.5533756017684937, "learning_rate": 0.00018370301946187874, "loss": 0.6258885383605957, "step": 138850 }, { "epoch": 0.8254126766172702, "grad_norm": 1.7399605512619019, "learning_rate": 0.00018369944686429874, "loss": 0.6494722366333008, "step": 138860 }, { "epoch": 0.8254721186939387, "grad_norm": 1.4941301345825195, "learning_rate": 0.0001836958739141647, "loss": 0.6188549995422363, "step": 138870 }, { "epoch": 0.8255315607706071, "grad_norm": 2.088432788848877, "learning_rate": 0.0001836923006114937, "loss": 0.6593719005584717, "step": 138880 }, { "epoch": 0.8255910028472755, "grad_norm": 1.5766706466674805, "learning_rate": 0.00018368872695630277, "loss": 0.6551804542541504, "step": 138890 }, { "epoch": 0.8256504449239439, "grad_norm": 1.8712022304534912, "learning_rate": 0.0001836851529486091, "loss": 0.6696737289428711, "step": 138900 }, { "epoch": 0.8257098870006122, "grad_norm": 1.9670493602752686, "learning_rate": 0.00018368157858842974, "loss": 0.6797371864318847, "step": 138910 }, { "epoch": 0.8257693290772806, "grad_norm": 1.9242560863494873, "learning_rate": 0.00018367800387578175, "loss": 0.6541987419128418, "step": 138920 }, { "epoch": 0.825828771153949, "grad_norm": 1.8675079345703125, "learning_rate": 0.0001836744288106823, "loss": 0.6262341499328613, "step": 138930 }, { "epoch": 0.8258882132306175, "grad_norm": 1.5461018085479736, "learning_rate": 0.00018367085339314842, "loss": 0.6703019142150879, "step": 138940 }, { "epoch": 0.8259476553072859, "grad_norm": 1.7815932035446167, "learning_rate": 0.00018366727762319726, "loss": 0.6427752494812011, "step": 138950 }, { "epoch": 0.8260070973839542, "grad_norm": 1.3088390827178955, "learning_rate": 0.00018366370150084597, "loss": 0.6521044731140136, "step": 138960 }, { "epoch": 0.8260665394606226, "grad_norm": 1.5806106328964233, "learning_rate": 0.00018366012502611157, "loss": 0.7194826602935791, "step": 138970 }, { "epoch": 0.826125981537291, "grad_norm": 1.420649528503418, "learning_rate": 0.0001836565481990112, "loss": 0.6299233436584473, "step": 138980 }, { "epoch": 0.8261854236139594, "grad_norm": 1.7217813730239868, "learning_rate": 0.00018365297101956198, "loss": 0.6116143226623535, "step": 138990 }, { "epoch": 0.8262448656906277, "grad_norm": 1.8320896625518799, "learning_rate": 0.00018364939348778102, "loss": 0.6988768100738525, "step": 139000 }, { "epoch": 0.8263043077672961, "grad_norm": 1.5725237131118774, "learning_rate": 0.00018364581560368547, "loss": 0.6473024368286133, "step": 139010 }, { "epoch": 0.8263637498439645, "grad_norm": 1.547210454940796, "learning_rate": 0.00018364223736729233, "loss": 0.5702920913696289, "step": 139020 }, { "epoch": 0.826423191920633, "grad_norm": 2.2030274868011475, "learning_rate": 0.00018363865877861883, "loss": 0.6323455810546875, "step": 139030 }, { "epoch": 0.8264826339973014, "grad_norm": 1.3880776166915894, "learning_rate": 0.00018363507983768204, "loss": 0.6586459159851075, "step": 139040 }, { "epoch": 0.8265420760739697, "grad_norm": 1.8906280994415283, "learning_rate": 0.0001836315005444991, "loss": 0.6425336837768555, "step": 139050 }, { "epoch": 0.8266015181506381, "grad_norm": 2.1012237071990967, "learning_rate": 0.00018362792089908714, "loss": 0.7186746597290039, "step": 139060 }, { "epoch": 0.8266609602273065, "grad_norm": 1.7437198162078857, "learning_rate": 0.00018362434090146324, "loss": 0.6408461570739746, "step": 139070 }, { "epoch": 0.8267204023039749, "grad_norm": 1.663661003112793, "learning_rate": 0.00018362076055164457, "loss": 0.6541447639465332, "step": 139080 }, { "epoch": 0.8267798443806433, "grad_norm": 1.859356164932251, "learning_rate": 0.00018361717984964826, "loss": 0.6676017761230468, "step": 139090 }, { "epoch": 0.8268392864573116, "grad_norm": 1.8066576719284058, "learning_rate": 0.0001836135987954914, "loss": 0.6577577590942383, "step": 139100 }, { "epoch": 0.82689872853398, "grad_norm": 1.6092512607574463, "learning_rate": 0.00018361001738919112, "loss": 0.6053619384765625, "step": 139110 }, { "epoch": 0.8269581706106485, "grad_norm": 1.8249542713165283, "learning_rate": 0.0001836064356307646, "loss": 0.6542956829071045, "step": 139120 }, { "epoch": 0.8270176126873169, "grad_norm": 1.7822113037109375, "learning_rate": 0.00018360285352022894, "loss": 0.6122987747192383, "step": 139130 }, { "epoch": 0.8270770547639852, "grad_norm": 1.708141803741455, "learning_rate": 0.00018359927105760128, "loss": 0.6365211486816407, "step": 139140 }, { "epoch": 0.8271364968406536, "grad_norm": 1.459094524383545, "learning_rate": 0.00018359568824289875, "loss": 0.6451468467712402, "step": 139150 }, { "epoch": 0.827195938917322, "grad_norm": 1.7776353359222412, "learning_rate": 0.00018359210507613852, "loss": 0.7078360557556153, "step": 139160 }, { "epoch": 0.8272553809939904, "grad_norm": 1.9144467115402222, "learning_rate": 0.00018358852155733767, "loss": 0.7268702507019043, "step": 139170 }, { "epoch": 0.8273148230706588, "grad_norm": 1.4125487804412842, "learning_rate": 0.00018358493768651343, "loss": 0.6596856117248535, "step": 139180 }, { "epoch": 0.8273742651473271, "grad_norm": 1.8955814838409424, "learning_rate": 0.00018358135346368287, "loss": 0.7053639888763428, "step": 139190 }, { "epoch": 0.8274337072239956, "grad_norm": 1.656316876411438, "learning_rate": 0.00018357776888886318, "loss": 0.714310884475708, "step": 139200 }, { "epoch": 0.827493149300664, "grad_norm": 1.3425120115280151, "learning_rate": 0.00018357418396207148, "loss": 0.6075046539306641, "step": 139210 }, { "epoch": 0.8275525913773324, "grad_norm": 1.5482673645019531, "learning_rate": 0.0001835705986833249, "loss": 0.706744384765625, "step": 139220 }, { "epoch": 0.8276120334540007, "grad_norm": 1.7280850410461426, "learning_rate": 0.0001835670130526407, "loss": 0.6674701690673828, "step": 139230 }, { "epoch": 0.8276714755306691, "grad_norm": 1.7663971185684204, "learning_rate": 0.00018356342707003586, "loss": 0.5982123374938965, "step": 139240 }, { "epoch": 0.8277309176073375, "grad_norm": 1.6365509033203125, "learning_rate": 0.0001835598407355277, "loss": 0.6945376396179199, "step": 139250 }, { "epoch": 0.8277903596840059, "grad_norm": 1.944022297859192, "learning_rate": 0.00018355625404913321, "loss": 0.6527937412261963, "step": 139260 }, { "epoch": 0.8278498017606744, "grad_norm": 1.4277012348175049, "learning_rate": 0.0001835526670108697, "loss": 0.6576450347900391, "step": 139270 }, { "epoch": 0.8279092438373427, "grad_norm": 1.4478943347930908, "learning_rate": 0.00018354907962075427, "loss": 0.6586590766906738, "step": 139280 }, { "epoch": 0.8279686859140111, "grad_norm": 2.4470622539520264, "learning_rate": 0.00018354549187880406, "loss": 0.6700055122375488, "step": 139290 }, { "epoch": 0.8280281279906795, "grad_norm": 1.8531639575958252, "learning_rate": 0.00018354190378503627, "loss": 0.6946094512939454, "step": 139300 }, { "epoch": 0.8280875700673479, "grad_norm": 1.3431490659713745, "learning_rate": 0.00018353831533946807, "loss": 0.6585373878479004, "step": 139310 }, { "epoch": 0.8281470121440163, "grad_norm": 1.6671384572982788, "learning_rate": 0.00018353472654211657, "loss": 0.634928035736084, "step": 139320 }, { "epoch": 0.8282064542206846, "grad_norm": 1.7982783317565918, "learning_rate": 0.00018353113739299893, "loss": 0.6280660629272461, "step": 139330 }, { "epoch": 0.828265896297353, "grad_norm": 1.7498403787612915, "learning_rate": 0.0001835275478921324, "loss": 0.6206892967224121, "step": 139340 }, { "epoch": 0.8283253383740214, "grad_norm": 1.7874525785446167, "learning_rate": 0.00018352395803953412, "loss": 0.6847496032714844, "step": 139350 }, { "epoch": 0.8283847804506899, "grad_norm": 1.56137216091156, "learning_rate": 0.00018352036783522124, "loss": 0.658099889755249, "step": 139360 }, { "epoch": 0.8284442225273582, "grad_norm": 1.8808890581130981, "learning_rate": 0.00018351677727921096, "loss": 0.6911192417144776, "step": 139370 }, { "epoch": 0.8285036646040266, "grad_norm": 1.4882237911224365, "learning_rate": 0.0001835131863715204, "loss": 0.6365311145782471, "step": 139380 }, { "epoch": 0.828563106680695, "grad_norm": 1.764761209487915, "learning_rate": 0.00018350959511216684, "loss": 0.6329960346221923, "step": 139390 }, { "epoch": 0.8286225487573634, "grad_norm": 1.7489006519317627, "learning_rate": 0.00018350600350116737, "loss": 0.6550023078918457, "step": 139400 }, { "epoch": 0.8286819908340318, "grad_norm": 1.7533098459243774, "learning_rate": 0.0001835024115385392, "loss": 0.6104186058044434, "step": 139410 }, { "epoch": 0.8287414329107001, "grad_norm": 2.004021167755127, "learning_rate": 0.00018349881922429952, "loss": 0.706282091140747, "step": 139420 }, { "epoch": 0.8288008749873685, "grad_norm": 1.5147641897201538, "learning_rate": 0.0001834952265584655, "loss": 0.5512115001678467, "step": 139430 }, { "epoch": 0.828860317064037, "grad_norm": 1.5328783988952637, "learning_rate": 0.00018349163354105434, "loss": 0.6228700637817383, "step": 139440 }, { "epoch": 0.8289197591407054, "grad_norm": 1.3762452602386475, "learning_rate": 0.00018348804017208326, "loss": 0.6480432987213135, "step": 139450 }, { "epoch": 0.8289792012173738, "grad_norm": 1.888733148574829, "learning_rate": 0.00018348444645156935, "loss": 0.6774003982543946, "step": 139460 }, { "epoch": 0.8290386432940421, "grad_norm": 1.7387388944625854, "learning_rate": 0.0001834808523795299, "loss": 0.6502214431762695, "step": 139470 }, { "epoch": 0.8290980853707105, "grad_norm": 1.9365899562835693, "learning_rate": 0.00018347725795598205, "loss": 0.7192863464355469, "step": 139480 }, { "epoch": 0.8291575274473789, "grad_norm": 1.943296194076538, "learning_rate": 0.00018347366318094302, "loss": 0.6608732223510743, "step": 139490 }, { "epoch": 0.8292169695240473, "grad_norm": 1.742775797843933, "learning_rate": 0.00018347006805443, "loss": 0.6620275497436523, "step": 139500 }, { "epoch": 0.8292764116007156, "grad_norm": 1.6078081130981445, "learning_rate": 0.00018346647257646016, "loss": 0.6984529495239258, "step": 139510 }, { "epoch": 0.829335853677384, "grad_norm": 1.7242366075515747, "learning_rate": 0.00018346287674705073, "loss": 0.7044543266296387, "step": 139520 }, { "epoch": 0.8293952957540525, "grad_norm": 1.384674072265625, "learning_rate": 0.00018345928056621893, "loss": 0.6141530036926269, "step": 139530 }, { "epoch": 0.8294547378307209, "grad_norm": 1.2562255859375, "learning_rate": 0.0001834556840339819, "loss": 0.6878622531890869, "step": 139540 }, { "epoch": 0.8295141799073893, "grad_norm": 2.1056528091430664, "learning_rate": 0.00018345208715035694, "loss": 0.635334825515747, "step": 139550 }, { "epoch": 0.8295736219840576, "grad_norm": 1.3976188898086548, "learning_rate": 0.00018344848991536116, "loss": 0.662789249420166, "step": 139560 }, { "epoch": 0.829633064060726, "grad_norm": 2.0717806816101074, "learning_rate": 0.00018344489232901184, "loss": 0.6120664596557617, "step": 139570 }, { "epoch": 0.8296925061373944, "grad_norm": 1.5035737752914429, "learning_rate": 0.0001834412943913261, "loss": 0.6596922397613525, "step": 139580 }, { "epoch": 0.8297519482140628, "grad_norm": 1.4660471677780151, "learning_rate": 0.00018343769610232124, "loss": 0.6561033248901367, "step": 139590 }, { "epoch": 0.8298113902907311, "grad_norm": 1.7641361951828003, "learning_rate": 0.00018343409746201446, "loss": 0.6619494438171387, "step": 139600 }, { "epoch": 0.8298708323673996, "grad_norm": 1.897581696510315, "learning_rate": 0.00018343049847042292, "loss": 0.7215414047241211, "step": 139610 }, { "epoch": 0.829930274444068, "grad_norm": 2.113004207611084, "learning_rate": 0.0001834268991275639, "loss": 0.6154279232025146, "step": 139620 }, { "epoch": 0.8299897165207364, "grad_norm": 1.8331036567687988, "learning_rate": 0.0001834232994334546, "loss": 0.7222668647766113, "step": 139630 }, { "epoch": 0.8300491585974048, "grad_norm": 1.5010687112808228, "learning_rate": 0.00018341969938811222, "loss": 0.6029709815979004, "step": 139640 }, { "epoch": 0.8301086006740731, "grad_norm": 1.9818370342254639, "learning_rate": 0.00018341609899155393, "loss": 0.6778665542602539, "step": 139650 }, { "epoch": 0.8301680427507415, "grad_norm": 1.8947713375091553, "learning_rate": 0.0001834124982437971, "loss": 0.6533708572387695, "step": 139660 }, { "epoch": 0.8302274848274099, "grad_norm": 1.4542067050933838, "learning_rate": 0.00018340889714485884, "loss": 0.6731517791748047, "step": 139670 }, { "epoch": 0.8302869269040783, "grad_norm": 1.964612364768982, "learning_rate": 0.0001834052956947564, "loss": 0.6402781486511231, "step": 139680 }, { "epoch": 0.8303463689807468, "grad_norm": 1.8157007694244385, "learning_rate": 0.00018340169389350703, "loss": 0.6387300968170166, "step": 139690 }, { "epoch": 0.8304058110574151, "grad_norm": 1.5010634660720825, "learning_rate": 0.00018339809174112794, "loss": 0.6156893253326416, "step": 139700 }, { "epoch": 0.8304652531340835, "grad_norm": 1.5810977220535278, "learning_rate": 0.00018339448923763635, "loss": 0.675718116760254, "step": 139710 }, { "epoch": 0.8305246952107519, "grad_norm": 1.585500955581665, "learning_rate": 0.0001833908863830495, "loss": 0.6981813907623291, "step": 139720 }, { "epoch": 0.8305841372874203, "grad_norm": 1.3810441493988037, "learning_rate": 0.00018338728317738467, "loss": 0.6291109085083008, "step": 139730 }, { "epoch": 0.8306435793640886, "grad_norm": 1.5024973154067993, "learning_rate": 0.00018338367962065906, "loss": 0.6605253219604492, "step": 139740 }, { "epoch": 0.830703021440757, "grad_norm": 2.037541627883911, "learning_rate": 0.0001833800757128899, "loss": 0.6283584594726562, "step": 139750 }, { "epoch": 0.8307624635174254, "grad_norm": 1.969820261001587, "learning_rate": 0.00018337647145409442, "loss": 0.6857432365417481, "step": 139760 }, { "epoch": 0.8308219055940939, "grad_norm": 1.3005685806274414, "learning_rate": 0.0001833728668442899, "loss": 0.6281229972839355, "step": 139770 }, { "epoch": 0.8308813476707623, "grad_norm": 1.5772877931594849, "learning_rate": 0.00018336926188349355, "loss": 0.6686245918273925, "step": 139780 }, { "epoch": 0.8309407897474306, "grad_norm": 1.3969992399215698, "learning_rate": 0.0001833656565717226, "loss": 0.5719369888305664, "step": 139790 }, { "epoch": 0.831000231824099, "grad_norm": 1.5325508117675781, "learning_rate": 0.0001833620509089944, "loss": 0.6564370155334472, "step": 139800 }, { "epoch": 0.8310596739007674, "grad_norm": 1.843125820159912, "learning_rate": 0.00018335844489532607, "loss": 0.7253655910491943, "step": 139810 }, { "epoch": 0.8311191159774358, "grad_norm": 1.3740239143371582, "learning_rate": 0.0001833548385307349, "loss": 0.6430747985839844, "step": 139820 }, { "epoch": 0.8311785580541042, "grad_norm": 1.7395323514938354, "learning_rate": 0.0001833512318152382, "loss": 0.6350752830505371, "step": 139830 }, { "epoch": 0.8312380001307725, "grad_norm": 1.5480281114578247, "learning_rate": 0.00018334762474885317, "loss": 0.606321907043457, "step": 139840 }, { "epoch": 0.831297442207441, "grad_norm": 1.3727964162826538, "learning_rate": 0.00018334401733159704, "loss": 0.6756690979003906, "step": 139850 }, { "epoch": 0.8313568842841094, "grad_norm": 1.6018283367156982, "learning_rate": 0.00018334040956348715, "loss": 0.647116756439209, "step": 139860 }, { "epoch": 0.8314163263607778, "grad_norm": 1.4396967887878418, "learning_rate": 0.00018333680144454065, "loss": 0.6445455551147461, "step": 139870 }, { "epoch": 0.8314757684374461, "grad_norm": 1.2983808517456055, "learning_rate": 0.00018333319297477493, "loss": 0.6250474929809571, "step": 139880 }, { "epoch": 0.8315352105141145, "grad_norm": 1.6439062356948853, "learning_rate": 0.0001833295841542071, "loss": 0.6036129951477051, "step": 139890 }, { "epoch": 0.8315946525907829, "grad_norm": 1.6241704225540161, "learning_rate": 0.00018332597498285457, "loss": 0.6192870140075684, "step": 139900 }, { "epoch": 0.8316540946674513, "grad_norm": 1.8742311000823975, "learning_rate": 0.00018332236546073451, "loss": 0.7185478687286377, "step": 139910 }, { "epoch": 0.8317135367441197, "grad_norm": 2.0355441570281982, "learning_rate": 0.0001833187555878642, "loss": 0.6565897464752197, "step": 139920 }, { "epoch": 0.831772978820788, "grad_norm": 1.694181203842163, "learning_rate": 0.00018331514536426094, "loss": 0.6582038402557373, "step": 139930 }, { "epoch": 0.8318324208974565, "grad_norm": 1.3364328145980835, "learning_rate": 0.000183311534789942, "loss": 0.6932624816894531, "step": 139940 }, { "epoch": 0.8318918629741249, "grad_norm": 1.7821426391601562, "learning_rate": 0.00018330792386492462, "loss": 0.6058122634887695, "step": 139950 }, { "epoch": 0.8319513050507933, "grad_norm": 1.3770952224731445, "learning_rate": 0.00018330431258922612, "loss": 0.7131074905395508, "step": 139960 }, { "epoch": 0.8320107471274616, "grad_norm": 1.3421415090560913, "learning_rate": 0.00018330070096286372, "loss": 0.6773474216461182, "step": 139970 }, { "epoch": 0.83207018920413, "grad_norm": 1.4601707458496094, "learning_rate": 0.0001832970889858547, "loss": 0.6027168273925781, "step": 139980 }, { "epoch": 0.8321296312807984, "grad_norm": 1.5568236112594604, "learning_rate": 0.00018329347665821638, "loss": 0.6472821235656738, "step": 139990 }, { "epoch": 0.8321890733574668, "grad_norm": 1.5057651996612549, "learning_rate": 0.00018328986397996602, "loss": 0.692084264755249, "step": 140000 }, { "epoch": 0.8322485154341352, "grad_norm": 1.4132052659988403, "learning_rate": 0.00018328625095112092, "loss": 0.6899418830871582, "step": 140010 }, { "epoch": 0.8323079575108036, "grad_norm": 1.6713593006134033, "learning_rate": 0.00018328263757169832, "loss": 0.613184642791748, "step": 140020 }, { "epoch": 0.832367399587472, "grad_norm": 1.653422236442566, "learning_rate": 0.00018327902384171553, "loss": 0.6246572494506836, "step": 140030 }, { "epoch": 0.8324268416641404, "grad_norm": 2.075568914413452, "learning_rate": 0.00018327540976118985, "loss": 0.6635581016540527, "step": 140040 }, { "epoch": 0.8324862837408088, "grad_norm": 1.3803589344024658, "learning_rate": 0.00018327179533013857, "loss": 0.6415148735046386, "step": 140050 }, { "epoch": 0.8325457258174772, "grad_norm": 1.7232117652893066, "learning_rate": 0.0001832681805485789, "loss": 0.6032132148742676, "step": 140060 }, { "epoch": 0.8326051678941455, "grad_norm": 1.7721281051635742, "learning_rate": 0.00018326456541652828, "loss": 0.669955062866211, "step": 140070 }, { "epoch": 0.8326646099708139, "grad_norm": 1.4834952354431152, "learning_rate": 0.00018326094993400386, "loss": 0.65946044921875, "step": 140080 }, { "epoch": 0.8327240520474823, "grad_norm": 1.6375352144241333, "learning_rate": 0.00018325733410102304, "loss": 0.6206880569458008, "step": 140090 }, { "epoch": 0.8327834941241508, "grad_norm": 1.636022686958313, "learning_rate": 0.00018325371791760305, "loss": 0.7395461559295654, "step": 140100 }, { "epoch": 0.8328429362008191, "grad_norm": 1.7633157968521118, "learning_rate": 0.00018325010138376126, "loss": 0.6503646373748779, "step": 140110 }, { "epoch": 0.8329023782774875, "grad_norm": 1.4806238412857056, "learning_rate": 0.00018324648449951486, "loss": 0.6464715003967285, "step": 140120 }, { "epoch": 0.8329618203541559, "grad_norm": 1.4471967220306396, "learning_rate": 0.00018324286726488124, "loss": 0.6449729919433593, "step": 140130 }, { "epoch": 0.8330212624308243, "grad_norm": 1.6766191720962524, "learning_rate": 0.00018323924967987768, "loss": 0.6795796394348145, "step": 140140 }, { "epoch": 0.8330807045074927, "grad_norm": 1.4939309358596802, "learning_rate": 0.00018323563174452149, "loss": 0.6575292587280274, "step": 140150 }, { "epoch": 0.833140146584161, "grad_norm": 1.6336555480957031, "learning_rate": 0.00018323201345883, "loss": 0.6388041019439697, "step": 140160 }, { "epoch": 0.8331995886608294, "grad_norm": 1.7437827587127686, "learning_rate": 0.00018322839482282045, "loss": 0.7062516689300538, "step": 140170 }, { "epoch": 0.8332590307374979, "grad_norm": 1.4565746784210205, "learning_rate": 0.0001832247758365102, "loss": 0.6726584434509277, "step": 140180 }, { "epoch": 0.8333184728141663, "grad_norm": 1.5225002765655518, "learning_rate": 0.00018322115649991653, "loss": 0.6724607467651367, "step": 140190 }, { "epoch": 0.8333779148908347, "grad_norm": 1.757239818572998, "learning_rate": 0.00018321753681305682, "loss": 0.6090004444122314, "step": 140200 }, { "epoch": 0.833437356967503, "grad_norm": 2.356435775756836, "learning_rate": 0.0001832139167759483, "loss": 0.6831209182739257, "step": 140210 }, { "epoch": 0.8334967990441714, "grad_norm": 1.6809332370758057, "learning_rate": 0.00018321029638860835, "loss": 0.6708046913146972, "step": 140220 }, { "epoch": 0.8335562411208398, "grad_norm": 1.8012207746505737, "learning_rate": 0.0001832066756510543, "loss": 0.6290634632110595, "step": 140230 }, { "epoch": 0.8336156831975082, "grad_norm": 1.7621382474899292, "learning_rate": 0.00018320305456330337, "loss": 0.6061169147491455, "step": 140240 }, { "epoch": 0.8336751252741765, "grad_norm": 1.179848313331604, "learning_rate": 0.000183199433125373, "loss": 0.6285992622375488, "step": 140250 }, { "epoch": 0.833734567350845, "grad_norm": 1.5568208694458008, "learning_rate": 0.00018319581133728044, "loss": 0.5905568599700928, "step": 140260 }, { "epoch": 0.8337940094275134, "grad_norm": 1.526309847831726, "learning_rate": 0.00018319218919904303, "loss": 0.6405472755432129, "step": 140270 }, { "epoch": 0.8338534515041818, "grad_norm": 1.5631147623062134, "learning_rate": 0.00018318856671067812, "loss": 0.5817757606506347, "step": 140280 }, { "epoch": 0.8339128935808502, "grad_norm": 1.8027353286743164, "learning_rate": 0.00018318494387220305, "loss": 0.6494478225708008, "step": 140290 }, { "epoch": 0.8339723356575185, "grad_norm": 1.8544530868530273, "learning_rate": 0.0001831813206836351, "loss": 0.7115912437438965, "step": 140300 }, { "epoch": 0.8340317777341869, "grad_norm": 1.5800122022628784, "learning_rate": 0.00018317769714499164, "loss": 0.6278498649597168, "step": 140310 }, { "epoch": 0.8340912198108553, "grad_norm": 1.4778141975402832, "learning_rate": 0.00018317407325628996, "loss": 0.6623631477355957, "step": 140320 }, { "epoch": 0.8341506618875237, "grad_norm": 2.360156536102295, "learning_rate": 0.00018317044901754745, "loss": 0.7002576351165771, "step": 140330 }, { "epoch": 0.834210103964192, "grad_norm": 1.5742751359939575, "learning_rate": 0.00018316682442878144, "loss": 0.6443225860595703, "step": 140340 }, { "epoch": 0.8342695460408605, "grad_norm": 1.4327338933944702, "learning_rate": 0.00018316319949000922, "loss": 0.6554126262664794, "step": 140350 }, { "epoch": 0.8343289881175289, "grad_norm": 1.1527459621429443, "learning_rate": 0.0001831595742012482, "loss": 0.6053771018981934, "step": 140360 }, { "epoch": 0.8343884301941973, "grad_norm": 1.2942276000976562, "learning_rate": 0.00018315594856251565, "loss": 0.6335050582885742, "step": 140370 }, { "epoch": 0.8344478722708657, "grad_norm": 1.5160163640975952, "learning_rate": 0.00018315232257382896, "loss": 0.6967563152313232, "step": 140380 }, { "epoch": 0.834507314347534, "grad_norm": 1.6109647750854492, "learning_rate": 0.0001831486962352055, "loss": 0.6387701034545898, "step": 140390 }, { "epoch": 0.8345667564242024, "grad_norm": 1.5669386386871338, "learning_rate": 0.00018314506954666252, "loss": 0.7025049209594727, "step": 140400 }, { "epoch": 0.8346261985008708, "grad_norm": 1.6094568967819214, "learning_rate": 0.0001831414425082175, "loss": 0.7059316158294677, "step": 140410 }, { "epoch": 0.8346856405775392, "grad_norm": 1.340662956237793, "learning_rate": 0.00018313781511988768, "loss": 0.6375192642211914, "step": 140420 }, { "epoch": 0.8347450826542077, "grad_norm": 1.157206416130066, "learning_rate": 0.00018313418738169046, "loss": 0.6239099502563477, "step": 140430 }, { "epoch": 0.834804524730876, "grad_norm": 1.2433485984802246, "learning_rate": 0.00018313055929364318, "loss": 0.633715295791626, "step": 140440 }, { "epoch": 0.8348639668075444, "grad_norm": 2.0233399868011475, "learning_rate": 0.0001831269308557632, "loss": 0.6575835704803467, "step": 140450 }, { "epoch": 0.8349234088842128, "grad_norm": 1.667184591293335, "learning_rate": 0.00018312330206806792, "loss": 0.7231856346130371, "step": 140460 }, { "epoch": 0.8349828509608812, "grad_norm": 1.9212632179260254, "learning_rate": 0.00018311967293057463, "loss": 0.6513002395629883, "step": 140470 }, { "epoch": 0.8350422930375495, "grad_norm": 1.4556502103805542, "learning_rate": 0.0001831160434433007, "loss": 0.6380269050598144, "step": 140480 }, { "epoch": 0.8351017351142179, "grad_norm": 1.3203195333480835, "learning_rate": 0.00018311241360626356, "loss": 0.6428751945495605, "step": 140490 }, { "epoch": 0.8351611771908863, "grad_norm": 1.7255799770355225, "learning_rate": 0.0001831087834194805, "loss": 0.6502059936523438, "step": 140500 }, { "epoch": 0.8352206192675548, "grad_norm": 1.3817325830459595, "learning_rate": 0.00018310515288296893, "loss": 0.5991017341613769, "step": 140510 }, { "epoch": 0.8352800613442232, "grad_norm": 1.7056119441986084, "learning_rate": 0.00018310152199674614, "loss": 0.6594024658203125, "step": 140520 }, { "epoch": 0.8353395034208915, "grad_norm": 1.5618565082550049, "learning_rate": 0.00018309789076082964, "loss": 0.6856855392456055, "step": 140530 }, { "epoch": 0.8353989454975599, "grad_norm": 1.4343528747558594, "learning_rate": 0.00018309425917523668, "loss": 0.7207511901855469, "step": 140540 }, { "epoch": 0.8354583875742283, "grad_norm": 1.4121363162994385, "learning_rate": 0.00018309062723998468, "loss": 0.6498078346252442, "step": 140550 }, { "epoch": 0.8355178296508967, "grad_norm": 1.991921067237854, "learning_rate": 0.00018308699495509097, "loss": 0.6990084648132324, "step": 140560 }, { "epoch": 0.8355772717275651, "grad_norm": 1.462348461151123, "learning_rate": 0.00018308336232057302, "loss": 0.6794007778167724, "step": 140570 }, { "epoch": 0.8356367138042334, "grad_norm": 1.5765718221664429, "learning_rate": 0.00018307972933644811, "loss": 0.676998519897461, "step": 140580 }, { "epoch": 0.8356961558809018, "grad_norm": 2.031339168548584, "learning_rate": 0.00018307609600273368, "loss": 0.6810901165008545, "step": 140590 }, { "epoch": 0.8357555979575703, "grad_norm": 1.8915926218032837, "learning_rate": 0.00018307246231944705, "loss": 0.6253469467163086, "step": 140600 }, { "epoch": 0.8358150400342387, "grad_norm": 1.382967233657837, "learning_rate": 0.0001830688282866057, "loss": 0.6569262504577636, "step": 140610 }, { "epoch": 0.835874482110907, "grad_norm": 2.0306453704833984, "learning_rate": 0.00018306519390422693, "loss": 0.6709574699401856, "step": 140620 }, { "epoch": 0.8359339241875754, "grad_norm": 1.6707557439804077, "learning_rate": 0.0001830615591723281, "loss": 0.5663859367370605, "step": 140630 }, { "epoch": 0.8359933662642438, "grad_norm": 1.486140489578247, "learning_rate": 0.0001830579240909267, "loss": 0.6665960788726807, "step": 140640 }, { "epoch": 0.8360528083409122, "grad_norm": 1.7196952104568481, "learning_rate": 0.00018305428866004006, "loss": 0.6978316307067871, "step": 140650 }, { "epoch": 0.8361122504175806, "grad_norm": 1.3346037864685059, "learning_rate": 0.0001830506528796856, "loss": 0.6460357189178467, "step": 140660 }, { "epoch": 0.8361716924942489, "grad_norm": 1.8748530149459839, "learning_rate": 0.00018304701674988065, "loss": 0.7075370788574219, "step": 140670 }, { "epoch": 0.8362311345709174, "grad_norm": 1.4975969791412354, "learning_rate": 0.00018304338027064264, "loss": 0.6837169170379639, "step": 140680 }, { "epoch": 0.8362905766475858, "grad_norm": 1.5438779592514038, "learning_rate": 0.000183039743441989, "loss": 0.6834969520568848, "step": 140690 }, { "epoch": 0.8363500187242542, "grad_norm": 2.1474504470825195, "learning_rate": 0.00018303610626393708, "loss": 0.6941117763519287, "step": 140700 }, { "epoch": 0.8364094608009225, "grad_norm": 1.8386627435684204, "learning_rate": 0.0001830324687365043, "loss": 0.6613752365112304, "step": 140710 }, { "epoch": 0.8364689028775909, "grad_norm": 1.665466070175171, "learning_rate": 0.00018302883085970806, "loss": 0.6656625270843506, "step": 140720 }, { "epoch": 0.8365283449542593, "grad_norm": 1.4860700368881226, "learning_rate": 0.00018302519263356577, "loss": 0.7199949264526367, "step": 140730 }, { "epoch": 0.8365877870309277, "grad_norm": 1.881529450416565, "learning_rate": 0.0001830215540580948, "loss": 0.7172947406768799, "step": 140740 }, { "epoch": 0.8366472291075961, "grad_norm": 1.4683668613433838, "learning_rate": 0.00018301791513331258, "loss": 0.6517974853515625, "step": 140750 }, { "epoch": 0.8367066711842644, "grad_norm": 1.8362350463867188, "learning_rate": 0.00018301427585923653, "loss": 0.655902099609375, "step": 140760 }, { "epoch": 0.8367661132609329, "grad_norm": 2.0387141704559326, "learning_rate": 0.00018301063623588407, "loss": 0.6971536636352539, "step": 140770 }, { "epoch": 0.8368255553376013, "grad_norm": 1.5441550016403198, "learning_rate": 0.00018300699626327252, "loss": 0.606439208984375, "step": 140780 }, { "epoch": 0.8368849974142697, "grad_norm": 1.5462918281555176, "learning_rate": 0.0001830033559414194, "loss": 0.5918913841247558, "step": 140790 }, { "epoch": 0.8369444394909381, "grad_norm": 1.8404918909072876, "learning_rate": 0.0001829997152703421, "loss": 0.6209814071655273, "step": 140800 }, { "epoch": 0.8370038815676064, "grad_norm": 1.6472434997558594, "learning_rate": 0.00018299607425005797, "loss": 0.616938591003418, "step": 140810 }, { "epoch": 0.8370633236442748, "grad_norm": 1.477359414100647, "learning_rate": 0.00018299243288058453, "loss": 0.6721677780151367, "step": 140820 }, { "epoch": 0.8371227657209432, "grad_norm": 1.5661909580230713, "learning_rate": 0.00018298879116193913, "loss": 0.655034351348877, "step": 140830 }, { "epoch": 0.8371822077976117, "grad_norm": 1.360684871673584, "learning_rate": 0.00018298514909413917, "loss": 0.6577402591705322, "step": 140840 }, { "epoch": 0.83724164987428, "grad_norm": 1.5497196912765503, "learning_rate": 0.00018298150667720212, "loss": 0.6376713275909424, "step": 140850 }, { "epoch": 0.8373010919509484, "grad_norm": 1.6957429647445679, "learning_rate": 0.00018297786391114541, "loss": 0.6416547298431396, "step": 140860 }, { "epoch": 0.8373605340276168, "grad_norm": 2.4565927982330322, "learning_rate": 0.00018297422079598647, "loss": 0.6584127426147461, "step": 140870 }, { "epoch": 0.8374199761042852, "grad_norm": 1.3193198442459106, "learning_rate": 0.00018297057733174268, "loss": 0.613507604598999, "step": 140880 }, { "epoch": 0.8374794181809536, "grad_norm": 1.6380093097686768, "learning_rate": 0.00018296693351843148, "loss": 0.700331163406372, "step": 140890 }, { "epoch": 0.8375388602576219, "grad_norm": 1.5142470598220825, "learning_rate": 0.00018296328935607032, "loss": 0.6229523658752442, "step": 140900 }, { "epoch": 0.8375983023342903, "grad_norm": 1.9666484594345093, "learning_rate": 0.00018295964484467666, "loss": 0.7678908824920654, "step": 140910 }, { "epoch": 0.8376577444109587, "grad_norm": 1.1649549007415771, "learning_rate": 0.0001829559999842679, "loss": 0.6859614372253418, "step": 140920 }, { "epoch": 0.8377171864876272, "grad_norm": 1.5561480522155762, "learning_rate": 0.00018295235477486143, "loss": 0.6574498176574707, "step": 140930 }, { "epoch": 0.8377766285642955, "grad_norm": 1.649642825126648, "learning_rate": 0.0001829487092164748, "loss": 0.6304898262023926, "step": 140940 }, { "epoch": 0.8378360706409639, "grad_norm": 1.9371994733810425, "learning_rate": 0.00018294506330912533, "loss": 0.7225100994110107, "step": 140950 }, { "epoch": 0.8378955127176323, "grad_norm": 1.9127188920974731, "learning_rate": 0.00018294141705283055, "loss": 0.6335296630859375, "step": 140960 }, { "epoch": 0.8379549547943007, "grad_norm": 1.6496070623397827, "learning_rate": 0.00018293777044760785, "loss": 0.6935165405273438, "step": 140970 }, { "epoch": 0.8380143968709691, "grad_norm": 1.7021650075912476, "learning_rate": 0.0001829341234934747, "loss": 0.664771032333374, "step": 140980 }, { "epoch": 0.8380738389476374, "grad_norm": 1.527310848236084, "learning_rate": 0.00018293047619044855, "loss": 0.6536731243133544, "step": 140990 }, { "epoch": 0.8381332810243058, "grad_norm": 1.830177664756775, "learning_rate": 0.0001829268285385468, "loss": 0.662213134765625, "step": 141000 }, { "epoch": 0.8381927231009743, "grad_norm": 1.4731454849243164, "learning_rate": 0.00018292318053778696, "loss": 0.704789686203003, "step": 141010 }, { "epoch": 0.8382521651776427, "grad_norm": 1.340484857559204, "learning_rate": 0.00018291953218818645, "loss": 0.6276817321777344, "step": 141020 }, { "epoch": 0.8383116072543111, "grad_norm": 1.9965417385101318, "learning_rate": 0.00018291588348976273, "loss": 0.6474493980407715, "step": 141030 }, { "epoch": 0.8383710493309794, "grad_norm": 1.6974643468856812, "learning_rate": 0.00018291223444253326, "loss": 0.6522675514221191, "step": 141040 }, { "epoch": 0.8384304914076478, "grad_norm": 1.5275169610977173, "learning_rate": 0.00018290858504651548, "loss": 0.6688190460205078, "step": 141050 }, { "epoch": 0.8384899334843162, "grad_norm": 1.490876317024231, "learning_rate": 0.00018290493530172686, "loss": 0.6685960769653321, "step": 141060 }, { "epoch": 0.8385493755609846, "grad_norm": 1.7520358562469482, "learning_rate": 0.00018290128520818486, "loss": 0.6980082988739014, "step": 141070 }, { "epoch": 0.8386088176376529, "grad_norm": 1.272748351097107, "learning_rate": 0.00018289763476590695, "loss": 0.6440327167510986, "step": 141080 }, { "epoch": 0.8386682597143214, "grad_norm": 1.7236618995666504, "learning_rate": 0.00018289398397491056, "loss": 0.6179017543792724, "step": 141090 }, { "epoch": 0.8387277017909898, "grad_norm": 1.9821323156356812, "learning_rate": 0.00018289033283521315, "loss": 0.6504243850708008, "step": 141100 }, { "epoch": 0.8387871438676582, "grad_norm": 1.7775533199310303, "learning_rate": 0.00018288668134683225, "loss": 0.6835024356842041, "step": 141110 }, { "epoch": 0.8388465859443266, "grad_norm": 1.6510471105575562, "learning_rate": 0.00018288302950978527, "loss": 0.6520278453826904, "step": 141120 }, { "epoch": 0.8389060280209949, "grad_norm": 1.6419177055358887, "learning_rate": 0.0001828793773240897, "loss": 0.671273136138916, "step": 141130 }, { "epoch": 0.8389654700976633, "grad_norm": 2.0923726558685303, "learning_rate": 0.00018287572478976297, "loss": 0.6799685478210449, "step": 141140 }, { "epoch": 0.8390249121743317, "grad_norm": 1.5294482707977295, "learning_rate": 0.00018287207190682264, "loss": 0.6529090881347657, "step": 141150 }, { "epoch": 0.8390843542510001, "grad_norm": 1.6151431798934937, "learning_rate": 0.00018286841867528608, "loss": 0.6104609489440918, "step": 141160 }, { "epoch": 0.8391437963276686, "grad_norm": 1.7419122457504272, "learning_rate": 0.00018286476509517087, "loss": 0.6944704532623291, "step": 141170 }, { "epoch": 0.8392032384043369, "grad_norm": 1.76901113986969, "learning_rate": 0.0001828611111664944, "loss": 0.6607595920562744, "step": 141180 }, { "epoch": 0.8392626804810053, "grad_norm": 1.488342046737671, "learning_rate": 0.0001828574568892742, "loss": 0.5877213478088379, "step": 141190 }, { "epoch": 0.8393221225576737, "grad_norm": 1.7421356439590454, "learning_rate": 0.00018285380226352774, "loss": 0.6794319152832031, "step": 141200 }, { "epoch": 0.8393815646343421, "grad_norm": 2.590775728225708, "learning_rate": 0.0001828501472892725, "loss": 0.6903122901916504, "step": 141210 }, { "epoch": 0.8394410067110104, "grad_norm": 1.3355659246444702, "learning_rate": 0.00018284649196652594, "loss": 0.669985008239746, "step": 141220 }, { "epoch": 0.8395004487876788, "grad_norm": 1.6559194326400757, "learning_rate": 0.0001828428362953056, "loss": 0.6431037425994873, "step": 141230 }, { "epoch": 0.8395598908643472, "grad_norm": 1.7614974975585938, "learning_rate": 0.0001828391802756289, "loss": 0.6367284774780273, "step": 141240 }, { "epoch": 0.8396193329410157, "grad_norm": 1.698508858680725, "learning_rate": 0.0001828355239075134, "loss": 0.6886996746063232, "step": 141250 }, { "epoch": 0.8396787750176841, "grad_norm": 2.4248263835906982, "learning_rate": 0.00018283186719097655, "loss": 0.6733098030090332, "step": 141260 }, { "epoch": 0.8397382170943524, "grad_norm": 1.7999242544174194, "learning_rate": 0.00018282821012603585, "loss": 0.6493584632873535, "step": 141270 }, { "epoch": 0.8397976591710208, "grad_norm": 1.4243048429489136, "learning_rate": 0.0001828245527127088, "loss": 0.6561444282531739, "step": 141280 }, { "epoch": 0.8398571012476892, "grad_norm": 1.6054935455322266, "learning_rate": 0.00018282089495101286, "loss": 0.6274086952209472, "step": 141290 }, { "epoch": 0.8399165433243576, "grad_norm": 1.4530385732650757, "learning_rate": 0.0001828172368409656, "loss": 0.5741336822509766, "step": 141300 }, { "epoch": 0.8399759854010259, "grad_norm": 1.6116317510604858, "learning_rate": 0.00018281357838258443, "loss": 0.7123572349548339, "step": 141310 }, { "epoch": 0.8400354274776943, "grad_norm": 1.4537458419799805, "learning_rate": 0.0001828099195758869, "loss": 0.6488212585449219, "step": 141320 }, { "epoch": 0.8400948695543627, "grad_norm": 1.9515409469604492, "learning_rate": 0.00018280626042089054, "loss": 0.6230276584625244, "step": 141330 }, { "epoch": 0.8401543116310312, "grad_norm": 1.7807142734527588, "learning_rate": 0.00018280260091761282, "loss": 0.6733697891235352, "step": 141340 }, { "epoch": 0.8402137537076996, "grad_norm": 1.839038372039795, "learning_rate": 0.0001827989410660712, "loss": 0.6498566627502441, "step": 141350 }, { "epoch": 0.8402731957843679, "grad_norm": 2.2755045890808105, "learning_rate": 0.00018279528086628333, "loss": 0.6003045082092285, "step": 141360 }, { "epoch": 0.8403326378610363, "grad_norm": 1.5595265626907349, "learning_rate": 0.00018279162031826655, "loss": 0.7000170707702636, "step": 141370 }, { "epoch": 0.8403920799377047, "grad_norm": 1.3901664018630981, "learning_rate": 0.00018278795942203846, "loss": 0.6445114135742187, "step": 141380 }, { "epoch": 0.8404515220143731, "grad_norm": 1.590861201286316, "learning_rate": 0.00018278429817761657, "loss": 0.6484453201293945, "step": 141390 }, { "epoch": 0.8405109640910415, "grad_norm": 1.450950026512146, "learning_rate": 0.00018278063658501838, "loss": 0.6623834133148193, "step": 141400 }, { "epoch": 0.8405704061677098, "grad_norm": 1.624433994293213, "learning_rate": 0.00018277697464426143, "loss": 0.6584475994110107, "step": 141410 }, { "epoch": 0.8406298482443783, "grad_norm": 1.9116714000701904, "learning_rate": 0.00018277331235536318, "loss": 0.6003349304199219, "step": 141420 }, { "epoch": 0.8406892903210467, "grad_norm": 1.5931648015975952, "learning_rate": 0.00018276964971834122, "loss": 0.6497222900390625, "step": 141430 }, { "epoch": 0.8407487323977151, "grad_norm": 1.556747555732727, "learning_rate": 0.000182765986733213, "loss": 0.6580851554870606, "step": 141440 }, { "epoch": 0.8408081744743834, "grad_norm": 1.4051026105880737, "learning_rate": 0.0001827623233999961, "loss": 0.6592560291290284, "step": 141450 }, { "epoch": 0.8408676165510518, "grad_norm": 2.0812432765960693, "learning_rate": 0.00018275865971870804, "loss": 0.6569050312042236, "step": 141460 }, { "epoch": 0.8409270586277202, "grad_norm": 1.6154351234436035, "learning_rate": 0.0001827549956893663, "loss": 0.6630154609680176, "step": 141470 }, { "epoch": 0.8409865007043886, "grad_norm": 1.5475454330444336, "learning_rate": 0.00018275133131198844, "loss": 0.6904796123504638, "step": 141480 }, { "epoch": 0.841045942781057, "grad_norm": 2.0654757022857666, "learning_rate": 0.00018274766658659203, "loss": 0.7203917503356934, "step": 141490 }, { "epoch": 0.8411053848577253, "grad_norm": 1.420659065246582, "learning_rate": 0.00018274400151319453, "loss": 0.6042379856109619, "step": 141500 }, { "epoch": 0.8411648269343938, "grad_norm": 1.6759495735168457, "learning_rate": 0.00018274033609181348, "loss": 0.6801250457763672, "step": 141510 }, { "epoch": 0.8412242690110622, "grad_norm": 1.468557357788086, "learning_rate": 0.00018273667032246645, "loss": 0.6761763095855713, "step": 141520 }, { "epoch": 0.8412837110877306, "grad_norm": 1.655909776687622, "learning_rate": 0.00018273300420517096, "loss": 0.5545409202575684, "step": 141530 }, { "epoch": 0.841343153164399, "grad_norm": 1.7486591339111328, "learning_rate": 0.00018272933773994454, "loss": 0.6861414909362793, "step": 141540 }, { "epoch": 0.8414025952410673, "grad_norm": 1.709994912147522, "learning_rate": 0.00018272567092680474, "loss": 0.6411191940307617, "step": 141550 }, { "epoch": 0.8414620373177357, "grad_norm": 1.62334406375885, "learning_rate": 0.0001827220037657691, "loss": 0.6539151191711425, "step": 141560 }, { "epoch": 0.8415214793944041, "grad_norm": 1.3981552124023438, "learning_rate": 0.00018271833625685516, "loss": 0.6137980461120606, "step": 141570 }, { "epoch": 0.8415809214710726, "grad_norm": 1.8760335445404053, "learning_rate": 0.00018271466840008048, "loss": 0.6449926376342774, "step": 141580 }, { "epoch": 0.8416403635477409, "grad_norm": 1.4343777894973755, "learning_rate": 0.00018271100019546258, "loss": 0.5706499576568603, "step": 141590 }, { "epoch": 0.8416998056244093, "grad_norm": 1.6518083810806274, "learning_rate": 0.00018270733164301898, "loss": 0.6575539588928223, "step": 141600 }, { "epoch": 0.8417592477010777, "grad_norm": 1.3683016300201416, "learning_rate": 0.0001827036627427673, "loss": 0.59764723777771, "step": 141610 }, { "epoch": 0.8418186897777461, "grad_norm": 1.8178564310073853, "learning_rate": 0.00018269999349472505, "loss": 0.6981638908386231, "step": 141620 }, { "epoch": 0.8418781318544145, "grad_norm": 1.3419898748397827, "learning_rate": 0.0001826963238989098, "loss": 0.5928819656372071, "step": 141630 }, { "epoch": 0.8419375739310828, "grad_norm": 1.9323785305023193, "learning_rate": 0.0001826926539553391, "loss": 0.6726045608520508, "step": 141640 }, { "epoch": 0.8419970160077512, "grad_norm": 1.6275686025619507, "learning_rate": 0.0001826889836640305, "loss": 0.6482995986938477, "step": 141650 }, { "epoch": 0.8420564580844196, "grad_norm": 1.562219500541687, "learning_rate": 0.00018268531302500154, "loss": 0.6342732906341553, "step": 141660 }, { "epoch": 0.8421159001610881, "grad_norm": 1.828371286392212, "learning_rate": 0.00018268164203826982, "loss": 0.7170359134674072, "step": 141670 }, { "epoch": 0.8421753422377564, "grad_norm": 1.5326991081237793, "learning_rate": 0.00018267797070385284, "loss": 0.5794646739959717, "step": 141680 }, { "epoch": 0.8422347843144248, "grad_norm": 1.5549393892288208, "learning_rate": 0.00018267429902176822, "loss": 0.6459228515625, "step": 141690 }, { "epoch": 0.8422942263910932, "grad_norm": 1.78564453125, "learning_rate": 0.00018267062699203353, "loss": 0.6094846248626709, "step": 141700 }, { "epoch": 0.8423536684677616, "grad_norm": 1.5866779088974, "learning_rate": 0.00018266695461466626, "loss": 0.6286702156066895, "step": 141710 }, { "epoch": 0.84241311054443, "grad_norm": 1.4489535093307495, "learning_rate": 0.00018266328188968402, "loss": 0.6557573318481446, "step": 141720 }, { "epoch": 0.8424725526210983, "grad_norm": 1.661982536315918, "learning_rate": 0.00018265960881710445, "loss": 0.665345287322998, "step": 141730 }, { "epoch": 0.8425319946977667, "grad_norm": 1.9020622968673706, "learning_rate": 0.000182655935396945, "loss": 0.6410750389099121, "step": 141740 }, { "epoch": 0.8425914367744352, "grad_norm": 1.5801455974578857, "learning_rate": 0.0001826522616292233, "loss": 0.6514937400817871, "step": 141750 }, { "epoch": 0.8426508788511036, "grad_norm": 1.688314437866211, "learning_rate": 0.00018264858751395696, "loss": 0.6861037254333496, "step": 141760 }, { "epoch": 0.842710320927772, "grad_norm": 1.416883111000061, "learning_rate": 0.00018264491305116355, "loss": 0.6439646244049072, "step": 141770 }, { "epoch": 0.8427697630044403, "grad_norm": 1.5802251100540161, "learning_rate": 0.0001826412382408605, "loss": 0.6367283821105957, "step": 141780 }, { "epoch": 0.8428292050811087, "grad_norm": 1.5497314929962158, "learning_rate": 0.00018263756308306564, "loss": 0.6316591262817383, "step": 141790 }, { "epoch": 0.8428886471577771, "grad_norm": 1.6888549327850342, "learning_rate": 0.0001826338875777963, "loss": 0.6697675704956054, "step": 141800 }, { "epoch": 0.8429480892344455, "grad_norm": 1.8896455764770508, "learning_rate": 0.00018263021172507023, "loss": 0.6389714241027832, "step": 141810 }, { "epoch": 0.8430075313111138, "grad_norm": 1.7985022068023682, "learning_rate": 0.00018262653552490502, "loss": 0.5913326263427734, "step": 141820 }, { "epoch": 0.8430669733877822, "grad_norm": 1.6892096996307373, "learning_rate": 0.0001826228589773181, "loss": 0.6718269348144531, "step": 141830 }, { "epoch": 0.8431264154644507, "grad_norm": 1.5083930492401123, "learning_rate": 0.0001826191820823272, "loss": 0.6327473163604737, "step": 141840 }, { "epoch": 0.8431858575411191, "grad_norm": 1.6774321794509888, "learning_rate": 0.00018261550483994986, "loss": 0.6108917236328125, "step": 141850 }, { "epoch": 0.8432452996177875, "grad_norm": 1.4539421796798706, "learning_rate": 0.0001826118272502037, "loss": 0.6518697261810302, "step": 141860 }, { "epoch": 0.8433047416944558, "grad_norm": 1.4775786399841309, "learning_rate": 0.00018260814931310627, "loss": 0.6033353805541992, "step": 141870 }, { "epoch": 0.8433641837711242, "grad_norm": 1.5841330289840698, "learning_rate": 0.00018260447102867516, "loss": 0.6870083808898926, "step": 141880 }, { "epoch": 0.8434236258477926, "grad_norm": 1.5971699953079224, "learning_rate": 0.000182600792396928, "loss": 0.6948492050170898, "step": 141890 }, { "epoch": 0.843483067924461, "grad_norm": 1.3180105686187744, "learning_rate": 0.0001825971134178824, "loss": 0.6459027767181397, "step": 141900 }, { "epoch": 0.8435425100011295, "grad_norm": 1.8839200735092163, "learning_rate": 0.0001825934340915559, "loss": 0.7085139274597168, "step": 141910 }, { "epoch": 0.8436019520777978, "grad_norm": 1.4203321933746338, "learning_rate": 0.00018258975441796618, "loss": 0.6217506885528564, "step": 141920 }, { "epoch": 0.8436613941544662, "grad_norm": 1.7268760204315186, "learning_rate": 0.00018258607439713078, "loss": 0.586106252670288, "step": 141930 }, { "epoch": 0.8437208362311346, "grad_norm": 1.6374539136886597, "learning_rate": 0.0001825823940290673, "loss": 0.628108024597168, "step": 141940 }, { "epoch": 0.843780278307803, "grad_norm": 1.4216786623001099, "learning_rate": 0.00018257871331379337, "loss": 0.6008973598480225, "step": 141950 }, { "epoch": 0.8438397203844713, "grad_norm": 1.5706840753555298, "learning_rate": 0.00018257503225132662, "loss": 0.5839052200317383, "step": 141960 }, { "epoch": 0.8438991624611397, "grad_norm": 2.1968040466308594, "learning_rate": 0.00018257135084168459, "loss": 0.6504727363586426, "step": 141970 }, { "epoch": 0.8439586045378081, "grad_norm": 1.65113365650177, "learning_rate": 0.00018256766908488495, "loss": 0.6392600059509277, "step": 141980 }, { "epoch": 0.8440180466144765, "grad_norm": 1.3644973039627075, "learning_rate": 0.00018256398698094536, "loss": 0.6628018379211426, "step": 141990 }, { "epoch": 0.844077488691145, "grad_norm": 1.8744747638702393, "learning_rate": 0.00018256030452988329, "loss": 0.6107622623443604, "step": 142000 }, { "epoch": 0.8441369307678133, "grad_norm": 1.7950316667556763, "learning_rate": 0.00018255662173171646, "loss": 0.6747243881225586, "step": 142010 }, { "epoch": 0.8441963728444817, "grad_norm": 1.5674794912338257, "learning_rate": 0.00018255293858646245, "loss": 0.6438909053802491, "step": 142020 }, { "epoch": 0.8442558149211501, "grad_norm": 1.86864173412323, "learning_rate": 0.0001825492550941389, "loss": 0.6696455955505372, "step": 142030 }, { "epoch": 0.8443152569978185, "grad_norm": 1.7057276964187622, "learning_rate": 0.00018254557125476346, "loss": 0.6835638046264648, "step": 142040 }, { "epoch": 0.8443746990744868, "grad_norm": 1.7809576988220215, "learning_rate": 0.00018254188706835368, "loss": 0.6730015754699707, "step": 142050 }, { "epoch": 0.8444341411511552, "grad_norm": 2.1354784965515137, "learning_rate": 0.00018253820253492724, "loss": 0.6706341743469239, "step": 142060 }, { "epoch": 0.8444935832278236, "grad_norm": 1.5402817726135254, "learning_rate": 0.0001825345176545017, "loss": 0.6424198150634766, "step": 142070 }, { "epoch": 0.844553025304492, "grad_norm": 1.6114227771759033, "learning_rate": 0.0001825308324270948, "loss": 0.6901018142700195, "step": 142080 }, { "epoch": 0.8446124673811605, "grad_norm": 1.764823079109192, "learning_rate": 0.00018252714685272408, "loss": 0.6646823406219482, "step": 142090 }, { "epoch": 0.8446719094578288, "grad_norm": 1.653822660446167, "learning_rate": 0.00018252346093140717, "loss": 0.6656872749328613, "step": 142100 }, { "epoch": 0.8447313515344972, "grad_norm": 1.607203722000122, "learning_rate": 0.0001825197746631617, "loss": 0.6948560237884521, "step": 142110 }, { "epoch": 0.8447907936111656, "grad_norm": 1.6283267736434937, "learning_rate": 0.00018251608804800538, "loss": 0.6898041725158691, "step": 142120 }, { "epoch": 0.844850235687834, "grad_norm": 1.8091329336166382, "learning_rate": 0.00018251240108595575, "loss": 0.7024507522583008, "step": 142130 }, { "epoch": 0.8449096777645024, "grad_norm": 1.5023908615112305, "learning_rate": 0.00018250871377703052, "loss": 0.6196379661560059, "step": 142140 }, { "epoch": 0.8449691198411707, "grad_norm": 1.8268474340438843, "learning_rate": 0.00018250502612124732, "loss": 0.648613166809082, "step": 142150 }, { "epoch": 0.8450285619178391, "grad_norm": 1.4909465312957764, "learning_rate": 0.0001825013381186237, "loss": 0.6497170925140381, "step": 142160 }, { "epoch": 0.8450880039945076, "grad_norm": 1.2376153469085693, "learning_rate": 0.00018249764976917743, "loss": 0.6546819686889649, "step": 142170 }, { "epoch": 0.845147446071176, "grad_norm": 1.5640891790390015, "learning_rate": 0.0001824939610729261, "loss": 0.5915297031402588, "step": 142180 }, { "epoch": 0.8452068881478443, "grad_norm": 1.6389033794403076, "learning_rate": 0.0001824902720298873, "loss": 0.634484052658081, "step": 142190 }, { "epoch": 0.8452663302245127, "grad_norm": 2.0943965911865234, "learning_rate": 0.00018248658264007878, "loss": 0.7269633293151856, "step": 142200 }, { "epoch": 0.8453257723011811, "grad_norm": 1.9503775835037231, "learning_rate": 0.0001824828929035181, "loss": 0.6558528423309327, "step": 142210 }, { "epoch": 0.8453852143778495, "grad_norm": 1.7638033628463745, "learning_rate": 0.000182479202820223, "loss": 0.6555517196655274, "step": 142220 }, { "epoch": 0.8454446564545179, "grad_norm": 1.5774791240692139, "learning_rate": 0.00018247551239021102, "loss": 0.6689625263214112, "step": 142230 }, { "epoch": 0.8455040985311862, "grad_norm": 1.8204731941223145, "learning_rate": 0.00018247182161349989, "loss": 0.6274396419525147, "step": 142240 }, { "epoch": 0.8455635406078547, "grad_norm": 1.7301723957061768, "learning_rate": 0.00018246813049010727, "loss": 0.6406884670257569, "step": 142250 }, { "epoch": 0.8456229826845231, "grad_norm": 1.88846755027771, "learning_rate": 0.0001824644390200508, "loss": 0.6750035285949707, "step": 142260 }, { "epoch": 0.8456824247611915, "grad_norm": 1.9956353902816772, "learning_rate": 0.00018246074720334812, "loss": 0.7068651676177978, "step": 142270 }, { "epoch": 0.8457418668378599, "grad_norm": 1.8227540254592896, "learning_rate": 0.0001824570550400169, "loss": 0.6553013801574707, "step": 142280 }, { "epoch": 0.8458013089145282, "grad_norm": 1.4874275922775269, "learning_rate": 0.00018245336253007482, "loss": 0.6287103652954101, "step": 142290 }, { "epoch": 0.8458607509911966, "grad_norm": 1.9426759481430054, "learning_rate": 0.00018244966967353952, "loss": 0.6025146484375, "step": 142300 }, { "epoch": 0.845920193067865, "grad_norm": 1.7346054315567017, "learning_rate": 0.0001824459764704287, "loss": 0.7164689064025879, "step": 142310 }, { "epoch": 0.8459796351445334, "grad_norm": 1.3957878351211548, "learning_rate": 0.00018244228292075998, "loss": 0.6212417602539062, "step": 142320 }, { "epoch": 0.8460390772212018, "grad_norm": 1.5973049402236938, "learning_rate": 0.00018243858902455105, "loss": 0.5978902816772461, "step": 142330 }, { "epoch": 0.8460985192978702, "grad_norm": 1.784590244293213, "learning_rate": 0.00018243489478181958, "loss": 0.6588289737701416, "step": 142340 }, { "epoch": 0.8461579613745386, "grad_norm": 1.5104745626449585, "learning_rate": 0.00018243120019258326, "loss": 0.6386965751647949, "step": 142350 }, { "epoch": 0.846217403451207, "grad_norm": 1.6822069883346558, "learning_rate": 0.00018242750525685977, "loss": 0.6659951686859131, "step": 142360 }, { "epoch": 0.8462768455278754, "grad_norm": 1.9043664932250977, "learning_rate": 0.00018242380997466674, "loss": 0.6329726219177246, "step": 142370 }, { "epoch": 0.8463362876045437, "grad_norm": 1.353588342666626, "learning_rate": 0.0001824201143460219, "loss": 0.5816812992095948, "step": 142380 }, { "epoch": 0.8463957296812121, "grad_norm": 2.1094014644622803, "learning_rate": 0.00018241641837094287, "loss": 0.6798321723937988, "step": 142390 }, { "epoch": 0.8464551717578805, "grad_norm": 1.7045897245407104, "learning_rate": 0.00018241272204944732, "loss": 0.6328878402709961, "step": 142400 }, { "epoch": 0.846514613834549, "grad_norm": 1.7218116521835327, "learning_rate": 0.00018240902538155303, "loss": 0.7056097030639649, "step": 142410 }, { "epoch": 0.8465740559112173, "grad_norm": 1.56410551071167, "learning_rate": 0.0001824053283672776, "loss": 0.6573239326477051, "step": 142420 }, { "epoch": 0.8466334979878857, "grad_norm": 1.5246466398239136, "learning_rate": 0.00018240163100663876, "loss": 0.5706219673156738, "step": 142430 }, { "epoch": 0.8466929400645541, "grad_norm": 1.5548096895217896, "learning_rate": 0.0001823979332996542, "loss": 0.6359371185302735, "step": 142440 }, { "epoch": 0.8467523821412225, "grad_norm": 1.7716412544250488, "learning_rate": 0.00018239423524634153, "loss": 0.6603460788726807, "step": 142450 }, { "epoch": 0.8468118242178909, "grad_norm": 1.8583331108093262, "learning_rate": 0.00018239053684671855, "loss": 0.649044418334961, "step": 142460 }, { "epoch": 0.8468712662945592, "grad_norm": 2.1491949558258057, "learning_rate": 0.00018238683810080285, "loss": 0.6674449920654297, "step": 142470 }, { "epoch": 0.8469307083712276, "grad_norm": 1.8356131315231323, "learning_rate": 0.0001823831390086122, "loss": 0.6726159572601318, "step": 142480 }, { "epoch": 0.846990150447896, "grad_norm": 1.5781209468841553, "learning_rate": 0.00018237943957016427, "loss": 0.6604212284088135, "step": 142490 }, { "epoch": 0.8470495925245645, "grad_norm": 1.756446123123169, "learning_rate": 0.00018237573978547678, "loss": 0.6557962417602539, "step": 142500 }, { "epoch": 0.8471090346012329, "grad_norm": 1.5341527462005615, "learning_rate": 0.00018237203965456734, "loss": 0.667971420288086, "step": 142510 }, { "epoch": 0.8471684766779012, "grad_norm": 1.686838984489441, "learning_rate": 0.00018236833917745378, "loss": 0.662717342376709, "step": 142520 }, { "epoch": 0.8472279187545696, "grad_norm": 1.56200110912323, "learning_rate": 0.0001823646383541537, "loss": 0.635464859008789, "step": 142530 }, { "epoch": 0.847287360831238, "grad_norm": 1.6470927000045776, "learning_rate": 0.00018236093718468485, "loss": 0.6632549285888671, "step": 142540 }, { "epoch": 0.8473468029079064, "grad_norm": 1.1156803369522095, "learning_rate": 0.0001823572356690649, "loss": 0.6785061359405518, "step": 142550 }, { "epoch": 0.8474062449845747, "grad_norm": 1.8323662281036377, "learning_rate": 0.00018235353380731162, "loss": 0.675646448135376, "step": 142560 }, { "epoch": 0.8474656870612431, "grad_norm": 1.6666216850280762, "learning_rate": 0.00018234983159944265, "loss": 0.702301025390625, "step": 142570 }, { "epoch": 0.8475251291379116, "grad_norm": 1.5666993856430054, "learning_rate": 0.00018234612904547573, "loss": 0.6272111892700195, "step": 142580 }, { "epoch": 0.84758457121458, "grad_norm": 1.8652076721191406, "learning_rate": 0.0001823424261454286, "loss": 0.6356224060058594, "step": 142590 }, { "epoch": 0.8476440132912484, "grad_norm": 1.4262831211090088, "learning_rate": 0.0001823387228993189, "loss": 0.6079282760620117, "step": 142600 }, { "epoch": 0.8477034553679167, "grad_norm": 1.7802222967147827, "learning_rate": 0.00018233501930716442, "loss": 0.6163177967071534, "step": 142610 }, { "epoch": 0.8477628974445851, "grad_norm": 1.6856025457382202, "learning_rate": 0.00018233131536898284, "loss": 0.6853197097778321, "step": 142620 }, { "epoch": 0.8478223395212535, "grad_norm": 1.4800249338150024, "learning_rate": 0.0001823276110847919, "loss": 0.7052831649780273, "step": 142630 }, { "epoch": 0.8478817815979219, "grad_norm": 1.1733390092849731, "learning_rate": 0.0001823239064546093, "loss": 0.5910056114196778, "step": 142640 }, { "epoch": 0.8479412236745903, "grad_norm": 1.4932925701141357, "learning_rate": 0.00018232020147845277, "loss": 0.6303690433502197, "step": 142650 }, { "epoch": 0.8480006657512587, "grad_norm": 1.4460492134094238, "learning_rate": 0.00018231649615634002, "loss": 0.6752542495727539, "step": 142660 }, { "epoch": 0.8480601078279271, "grad_norm": 1.6169301271438599, "learning_rate": 0.00018231279048828877, "loss": 0.6784668445587159, "step": 142670 }, { "epoch": 0.8481195499045955, "grad_norm": 1.7051407098770142, "learning_rate": 0.0001823090844743168, "loss": 0.6979489326477051, "step": 142680 }, { "epoch": 0.8481789919812639, "grad_norm": 2.1092443466186523, "learning_rate": 0.00018230537811444176, "loss": 0.6216404914855957, "step": 142690 }, { "epoch": 0.8482384340579322, "grad_norm": 1.4785730838775635, "learning_rate": 0.00018230167140868147, "loss": 0.7030428886413574, "step": 142700 }, { "epoch": 0.8482978761346006, "grad_norm": 1.7544958591461182, "learning_rate": 0.00018229796435705357, "loss": 0.6239129066467285, "step": 142710 }, { "epoch": 0.848357318211269, "grad_norm": 1.713051676750183, "learning_rate": 0.00018229425695957585, "loss": 0.6858238220214844, "step": 142720 }, { "epoch": 0.8484167602879374, "grad_norm": 1.368528962135315, "learning_rate": 0.00018229054921626604, "loss": 0.6340062141418457, "step": 142730 }, { "epoch": 0.8484762023646059, "grad_norm": 1.8824565410614014, "learning_rate": 0.00018228684112714185, "loss": 0.7021535873413086, "step": 142740 }, { "epoch": 0.8485356444412742, "grad_norm": 1.428812026977539, "learning_rate": 0.00018228313269222102, "loss": 0.642202091217041, "step": 142750 }, { "epoch": 0.8485950865179426, "grad_norm": 1.6358791589736938, "learning_rate": 0.00018227942391152134, "loss": 0.6557046890258789, "step": 142760 }, { "epoch": 0.848654528594611, "grad_norm": 1.794924259185791, "learning_rate": 0.0001822757147850605, "loss": 0.6121879100799561, "step": 142770 }, { "epoch": 0.8487139706712794, "grad_norm": 1.969308853149414, "learning_rate": 0.00018227200531285628, "loss": 0.6020447731018066, "step": 142780 }, { "epoch": 0.8487734127479477, "grad_norm": 1.2594879865646362, "learning_rate": 0.00018226829549492638, "loss": 0.6905100822448731, "step": 142790 }, { "epoch": 0.8488328548246161, "grad_norm": 1.6741981506347656, "learning_rate": 0.0001822645853312886, "loss": 0.6501962661743164, "step": 142800 }, { "epoch": 0.8488922969012845, "grad_norm": 1.5710644721984863, "learning_rate": 0.00018226087482196065, "loss": 0.6230589866638183, "step": 142810 }, { "epoch": 0.848951738977953, "grad_norm": 1.3916321992874146, "learning_rate": 0.00018225716396696028, "loss": 0.6452464103698731, "step": 142820 }, { "epoch": 0.8490111810546214, "grad_norm": 2.0630388259887695, "learning_rate": 0.00018225345276630525, "loss": 0.7052340030670166, "step": 142830 }, { "epoch": 0.8490706231312897, "grad_norm": 1.53126060962677, "learning_rate": 0.00018224974122001331, "loss": 0.6640928268432618, "step": 142840 }, { "epoch": 0.8491300652079581, "grad_norm": 1.4913233518600464, "learning_rate": 0.00018224602932810223, "loss": 0.587623119354248, "step": 142850 }, { "epoch": 0.8491895072846265, "grad_norm": 1.375866413116455, "learning_rate": 0.00018224231709058976, "loss": 0.6639300346374511, "step": 142860 }, { "epoch": 0.8492489493612949, "grad_norm": 1.441266655921936, "learning_rate": 0.00018223860450749366, "loss": 0.6449281692504882, "step": 142870 }, { "epoch": 0.8493083914379633, "grad_norm": 4.701686382293701, "learning_rate": 0.00018223489157883165, "loss": 0.6477874755859375, "step": 142880 }, { "epoch": 0.8493678335146316, "grad_norm": 1.4328625202178955, "learning_rate": 0.00018223117830462157, "loss": 0.6341062545776367, "step": 142890 }, { "epoch": 0.8494272755913, "grad_norm": 1.7313567399978638, "learning_rate": 0.00018222746468488113, "loss": 0.6241285324096679, "step": 142900 }, { "epoch": 0.8494867176679685, "grad_norm": 1.6394869089126587, "learning_rate": 0.00018222375071962808, "loss": 0.6580928325653076, "step": 142910 }, { "epoch": 0.8495461597446369, "grad_norm": 1.5668994188308716, "learning_rate": 0.00018222003640888022, "loss": 0.6464214324951172, "step": 142920 }, { "epoch": 0.8496056018213052, "grad_norm": 1.2772762775421143, "learning_rate": 0.0001822163217526553, "loss": 0.6024202823638916, "step": 142930 }, { "epoch": 0.8496650438979736, "grad_norm": 1.5485188961029053, "learning_rate": 0.00018221260675097112, "loss": 0.6638970851898194, "step": 142940 }, { "epoch": 0.849724485974642, "grad_norm": 2.086207866668701, "learning_rate": 0.0001822088914038454, "loss": 0.6384533882141114, "step": 142950 }, { "epoch": 0.8497839280513104, "grad_norm": 1.1136314868927002, "learning_rate": 0.00018220517571129597, "loss": 0.6405706405639648, "step": 142960 }, { "epoch": 0.8498433701279788, "grad_norm": 1.5765711069107056, "learning_rate": 0.00018220145967334054, "loss": 0.6383059978485107, "step": 142970 }, { "epoch": 0.8499028122046471, "grad_norm": 1.782850742340088, "learning_rate": 0.00018219774328999695, "loss": 0.6484482765197754, "step": 142980 }, { "epoch": 0.8499622542813156, "grad_norm": 1.4903820753097534, "learning_rate": 0.00018219402656128296, "loss": 0.6309990882873535, "step": 142990 }, { "epoch": 0.850021696357984, "grad_norm": 1.2511534690856934, "learning_rate": 0.0001821903094872163, "loss": 0.6741826057434082, "step": 143000 }, { "epoch": 0.8500811384346524, "grad_norm": 1.3266570568084717, "learning_rate": 0.00018218659206781484, "loss": 0.6584771156311036, "step": 143010 }, { "epoch": 0.8501405805113208, "grad_norm": 1.2046335935592651, "learning_rate": 0.00018218287430309625, "loss": 0.6021485805511475, "step": 143020 }, { "epoch": 0.8502000225879891, "grad_norm": 1.5625230073928833, "learning_rate": 0.00018217915619307847, "loss": 0.6742600917816162, "step": 143030 }, { "epoch": 0.8502594646646575, "grad_norm": 1.7177220582962036, "learning_rate": 0.00018217543773777913, "loss": 0.6666414737701416, "step": 143040 }, { "epoch": 0.8503189067413259, "grad_norm": 1.7868057489395142, "learning_rate": 0.0001821717189372161, "loss": 0.6335748672485352, "step": 143050 }, { "epoch": 0.8503783488179943, "grad_norm": 1.9257783889770508, "learning_rate": 0.00018216799979140714, "loss": 0.6169404506683349, "step": 143060 }, { "epoch": 0.8504377908946626, "grad_norm": 1.9517375230789185, "learning_rate": 0.00018216428030037006, "loss": 0.6820757865905762, "step": 143070 }, { "epoch": 0.8504972329713311, "grad_norm": 1.711142659187317, "learning_rate": 0.00018216056046412265, "loss": 0.6593355178833008, "step": 143080 }, { "epoch": 0.8505566750479995, "grad_norm": 2.007050037384033, "learning_rate": 0.0001821568402826827, "loss": 0.622459602355957, "step": 143090 }, { "epoch": 0.8506161171246679, "grad_norm": 1.6884084939956665, "learning_rate": 0.00018215311975606802, "loss": 0.6443978786468506, "step": 143100 }, { "epoch": 0.8506755592013363, "grad_norm": 1.638449788093567, "learning_rate": 0.00018214939888429638, "loss": 0.6864323616027832, "step": 143110 }, { "epoch": 0.8507350012780046, "grad_norm": 1.7692230939865112, "learning_rate": 0.0001821456776673856, "loss": 0.6381878852844238, "step": 143120 }, { "epoch": 0.850794443354673, "grad_norm": 1.836243748664856, "learning_rate": 0.0001821419561053535, "loss": 0.657260799407959, "step": 143130 }, { "epoch": 0.8508538854313414, "grad_norm": 1.1948341131210327, "learning_rate": 0.0001821382341982178, "loss": 0.6390907287597656, "step": 143140 }, { "epoch": 0.8509133275080099, "grad_norm": 2.27697491645813, "learning_rate": 0.00018213451194599637, "loss": 0.6581127166748046, "step": 143150 }, { "epoch": 0.8509727695846782, "grad_norm": 1.5825316905975342, "learning_rate": 0.00018213078934870708, "loss": 0.6411581993103027, "step": 143160 }, { "epoch": 0.8510322116613466, "grad_norm": 1.554540753364563, "learning_rate": 0.0001821270664063676, "loss": 0.689594841003418, "step": 143170 }, { "epoch": 0.851091653738015, "grad_norm": 1.436294436454773, "learning_rate": 0.00018212334311899583, "loss": 0.595957899093628, "step": 143180 }, { "epoch": 0.8511510958146834, "grad_norm": 1.4500253200531006, "learning_rate": 0.00018211961948660953, "loss": 0.6962389469146728, "step": 143190 }, { "epoch": 0.8512105378913518, "grad_norm": 1.6163408756256104, "learning_rate": 0.00018211589550922661, "loss": 0.6945701122283936, "step": 143200 }, { "epoch": 0.8512699799680201, "grad_norm": 1.438671350479126, "learning_rate": 0.0001821121711868647, "loss": 0.614588737487793, "step": 143210 }, { "epoch": 0.8513294220446885, "grad_norm": 1.409164309501648, "learning_rate": 0.00018210844651954185, "loss": 0.6228522777557373, "step": 143220 }, { "epoch": 0.851388864121357, "grad_norm": 1.6108026504516602, "learning_rate": 0.00018210472150727568, "loss": 0.708762788772583, "step": 143230 }, { "epoch": 0.8514483061980254, "grad_norm": 1.2450616359710693, "learning_rate": 0.00018210099615008411, "loss": 0.6538854598999023, "step": 143240 }, { "epoch": 0.8515077482746938, "grad_norm": 1.985602855682373, "learning_rate": 0.00018209727044798496, "loss": 0.6154204368591308, "step": 143250 }, { "epoch": 0.8515671903513621, "grad_norm": 1.6489735841751099, "learning_rate": 0.00018209354440099597, "loss": 0.6705801486968994, "step": 143260 }, { "epoch": 0.8516266324280305, "grad_norm": 1.361720323562622, "learning_rate": 0.0001820898180091351, "loss": 0.6655857563018799, "step": 143270 }, { "epoch": 0.8516860745046989, "grad_norm": 1.6150524616241455, "learning_rate": 0.00018208609127242005, "loss": 0.6357385158538819, "step": 143280 }, { "epoch": 0.8517455165813673, "grad_norm": 1.6119123697280884, "learning_rate": 0.0001820823641908687, "loss": 0.6670062065124511, "step": 143290 }, { "epoch": 0.8518049586580356, "grad_norm": 1.6984037160873413, "learning_rate": 0.0001820786367644989, "loss": 0.6172770500183106, "step": 143300 }, { "epoch": 0.851864400734704, "grad_norm": 1.8709416389465332, "learning_rate": 0.00018207490899332842, "loss": 0.6063624858856201, "step": 143310 }, { "epoch": 0.8519238428113725, "grad_norm": 1.6633228063583374, "learning_rate": 0.00018207118087737513, "loss": 0.6336400508880615, "step": 143320 }, { "epoch": 0.8519832848880409, "grad_norm": 1.7351417541503906, "learning_rate": 0.00018206745241665688, "loss": 0.7207179546356202, "step": 143330 }, { "epoch": 0.8520427269647093, "grad_norm": 1.8109869956970215, "learning_rate": 0.00018206372361119152, "loss": 0.6465886116027832, "step": 143340 }, { "epoch": 0.8521021690413776, "grad_norm": 1.8997029066085815, "learning_rate": 0.00018205999446099683, "loss": 0.6285692691802979, "step": 143350 }, { "epoch": 0.852161611118046, "grad_norm": 1.8330519199371338, "learning_rate": 0.00018205626496609067, "loss": 0.6401188373565674, "step": 143360 }, { "epoch": 0.8522210531947144, "grad_norm": 1.7016518115997314, "learning_rate": 0.0001820525351264909, "loss": 0.6674485683441163, "step": 143370 }, { "epoch": 0.8522804952713828, "grad_norm": 2.212907552719116, "learning_rate": 0.00018204880494221534, "loss": 0.6130305290222168, "step": 143380 }, { "epoch": 0.8523399373480512, "grad_norm": 1.606834053993225, "learning_rate": 0.00018204507441328183, "loss": 0.6741735935211182, "step": 143390 }, { "epoch": 0.8523993794247195, "grad_norm": 1.4017342329025269, "learning_rate": 0.00018204134353970826, "loss": 0.6009943008422851, "step": 143400 }, { "epoch": 0.852458821501388, "grad_norm": 1.5592228174209595, "learning_rate": 0.00018203761232151242, "loss": 0.6852406024932861, "step": 143410 }, { "epoch": 0.8525182635780564, "grad_norm": 1.9362084865570068, "learning_rate": 0.00018203388075871223, "loss": 0.6743341445922851, "step": 143420 }, { "epoch": 0.8525777056547248, "grad_norm": 1.5243529081344604, "learning_rate": 0.00018203014885132543, "loss": 0.7348608493804931, "step": 143430 }, { "epoch": 0.8526371477313931, "grad_norm": 1.5248003005981445, "learning_rate": 0.00018202641659936997, "loss": 0.6089502811431885, "step": 143440 }, { "epoch": 0.8526965898080615, "grad_norm": 2.2617785930633545, "learning_rate": 0.00018202268400286365, "loss": 0.619768762588501, "step": 143450 }, { "epoch": 0.8527560318847299, "grad_norm": 1.3969354629516602, "learning_rate": 0.0001820189510618244, "loss": 0.6853533744812011, "step": 143460 }, { "epoch": 0.8528154739613983, "grad_norm": 1.7470972537994385, "learning_rate": 0.00018201521777626997, "loss": 0.677863883972168, "step": 143470 }, { "epoch": 0.8528749160380668, "grad_norm": 1.7085318565368652, "learning_rate": 0.0001820114841462183, "loss": 0.640446949005127, "step": 143480 }, { "epoch": 0.8529343581147351, "grad_norm": 1.4493000507354736, "learning_rate": 0.0001820077501716872, "loss": 0.5947441101074219, "step": 143490 }, { "epoch": 0.8529938001914035, "grad_norm": 1.6417123079299927, "learning_rate": 0.00018200401585269458, "loss": 0.6920915603637695, "step": 143500 }, { "epoch": 0.8530532422680719, "grad_norm": 2.0434188842773438, "learning_rate": 0.00018200028118925827, "loss": 0.6012460231781006, "step": 143510 }, { "epoch": 0.8531126843447403, "grad_norm": 1.8959347009658813, "learning_rate": 0.00018199654618139617, "loss": 0.6517024040222168, "step": 143520 }, { "epoch": 0.8531721264214086, "grad_norm": 1.6491413116455078, "learning_rate": 0.00018199281082912608, "loss": 0.6376888751983643, "step": 143530 }, { "epoch": 0.853231568498077, "grad_norm": 1.8044726848602295, "learning_rate": 0.00018198907513246592, "loss": 0.6304821968078613, "step": 143540 }, { "epoch": 0.8532910105747454, "grad_norm": 1.44865083694458, "learning_rate": 0.00018198533909143355, "loss": 0.6474685192108154, "step": 143550 }, { "epoch": 0.8533504526514138, "grad_norm": 1.318995714187622, "learning_rate": 0.00018198160270604686, "loss": 0.6618280410766602, "step": 143560 }, { "epoch": 0.8534098947280823, "grad_norm": 1.1299411058425903, "learning_rate": 0.0001819778659763237, "loss": 0.6499968528747558, "step": 143570 }, { "epoch": 0.8534693368047506, "grad_norm": 2.0130062103271484, "learning_rate": 0.00018197412890228197, "loss": 0.6392329216003418, "step": 143580 }, { "epoch": 0.853528778881419, "grad_norm": 1.4371683597564697, "learning_rate": 0.0001819703914839395, "loss": 0.6385912418365478, "step": 143590 }, { "epoch": 0.8535882209580874, "grad_norm": 1.647939920425415, "learning_rate": 0.0001819666537213142, "loss": 0.6365921974182129, "step": 143600 }, { "epoch": 0.8536476630347558, "grad_norm": 1.335632562637329, "learning_rate": 0.00018196291561442396, "loss": 0.63316650390625, "step": 143610 }, { "epoch": 0.8537071051114242, "grad_norm": 1.5720040798187256, "learning_rate": 0.00018195917716328666, "loss": 0.6615793228149414, "step": 143620 }, { "epoch": 0.8537665471880925, "grad_norm": 1.489440679550171, "learning_rate": 0.00018195543836792014, "loss": 0.6694815158843994, "step": 143630 }, { "epoch": 0.8538259892647609, "grad_norm": 2.062298536300659, "learning_rate": 0.00018195169922834235, "loss": 0.6445635795593262, "step": 143640 }, { "epoch": 0.8538854313414294, "grad_norm": 1.4008105993270874, "learning_rate": 0.0001819479597445711, "loss": 0.6008403301239014, "step": 143650 }, { "epoch": 0.8539448734180978, "grad_norm": 1.4182484149932861, "learning_rate": 0.00018194421991662437, "loss": 0.6140525817871094, "step": 143660 }, { "epoch": 0.8540043154947661, "grad_norm": 1.4196746349334717, "learning_rate": 0.00018194047974452, "loss": 0.6521599769592286, "step": 143670 }, { "epoch": 0.8540637575714345, "grad_norm": 1.6520228385925293, "learning_rate": 0.00018193673922827584, "loss": 0.6746578216552734, "step": 143680 }, { "epoch": 0.8541231996481029, "grad_norm": 1.960430383682251, "learning_rate": 0.0001819329983679099, "loss": 0.6515971660614014, "step": 143690 }, { "epoch": 0.8541826417247713, "grad_norm": 1.4599535465240479, "learning_rate": 0.00018192925716343996, "loss": 0.6561614513397217, "step": 143700 }, { "epoch": 0.8542420838014397, "grad_norm": 1.2963342666625977, "learning_rate": 0.00018192551561488395, "loss": 0.6658922672271729, "step": 143710 }, { "epoch": 0.854301525878108, "grad_norm": 1.7196869850158691, "learning_rate": 0.00018192177372225977, "loss": 0.6923202991485595, "step": 143720 }, { "epoch": 0.8543609679547765, "grad_norm": 1.3634487390518188, "learning_rate": 0.00018191803148558537, "loss": 0.6461410522460938, "step": 143730 }, { "epoch": 0.8544204100314449, "grad_norm": 1.2747057676315308, "learning_rate": 0.0001819142889048786, "loss": 0.6828501224517822, "step": 143740 }, { "epoch": 0.8544798521081133, "grad_norm": 1.4840023517608643, "learning_rate": 0.00018191054598015738, "loss": 0.6991402626037597, "step": 143750 }, { "epoch": 0.8545392941847817, "grad_norm": 1.683031678199768, "learning_rate": 0.00018190680271143957, "loss": 0.6760939598083496, "step": 143760 }, { "epoch": 0.85459873626145, "grad_norm": 1.8501344919204712, "learning_rate": 0.00018190305909874315, "loss": 0.7133743762969971, "step": 143770 }, { "epoch": 0.8546581783381184, "grad_norm": 1.4433586597442627, "learning_rate": 0.00018189931514208597, "loss": 0.6540396213531494, "step": 143780 }, { "epoch": 0.8547176204147868, "grad_norm": 2.0524585247039795, "learning_rate": 0.00018189557084148598, "loss": 0.5940324783325195, "step": 143790 }, { "epoch": 0.8547770624914552, "grad_norm": 1.1796128749847412, "learning_rate": 0.00018189182619696108, "loss": 0.6151815414428711, "step": 143800 }, { "epoch": 0.8548365045681235, "grad_norm": 1.7579779624938965, "learning_rate": 0.00018188808120852916, "loss": 0.6497028350830079, "step": 143810 }, { "epoch": 0.854895946644792, "grad_norm": 1.4234939813613892, "learning_rate": 0.00018188433587620816, "loss": 0.6496394634246826, "step": 143820 }, { "epoch": 0.8549553887214604, "grad_norm": 1.891487717628479, "learning_rate": 0.000181880590200016, "loss": 0.6492983341217041, "step": 143830 }, { "epoch": 0.8550148307981288, "grad_norm": 1.7035226821899414, "learning_rate": 0.0001818768441799706, "loss": 0.6653247356414795, "step": 143840 }, { "epoch": 0.8550742728747972, "grad_norm": 1.8257650136947632, "learning_rate": 0.00018187309781608982, "loss": 0.7084980010986328, "step": 143850 }, { "epoch": 0.8551337149514655, "grad_norm": 1.4733918905258179, "learning_rate": 0.00018186935110839166, "loss": 0.7098289489746094, "step": 143860 }, { "epoch": 0.8551931570281339, "grad_norm": 1.4927687644958496, "learning_rate": 0.00018186560405689402, "loss": 0.6246955871582032, "step": 143870 }, { "epoch": 0.8552525991048023, "grad_norm": 1.4874688386917114, "learning_rate": 0.0001818618566616148, "loss": 0.6445126533508301, "step": 143880 }, { "epoch": 0.8553120411814708, "grad_norm": 1.4577487707138062, "learning_rate": 0.00018185810892257194, "loss": 0.6349247932434082, "step": 143890 }, { "epoch": 0.855371483258139, "grad_norm": 1.3724509477615356, "learning_rate": 0.00018185436083978338, "loss": 0.6546721458435059, "step": 143900 }, { "epoch": 0.8554309253348075, "grad_norm": 1.792325496673584, "learning_rate": 0.00018185061241326702, "loss": 0.6899943351745605, "step": 143910 }, { "epoch": 0.8554903674114759, "grad_norm": 1.6209807395935059, "learning_rate": 0.0001818468636430408, "loss": 0.6253466129302978, "step": 143920 }, { "epoch": 0.8555498094881443, "grad_norm": 1.630873680114746, "learning_rate": 0.00018184311452912273, "loss": 0.6837178230285644, "step": 143930 }, { "epoch": 0.8556092515648127, "grad_norm": 1.8324670791625977, "learning_rate": 0.00018183936507153064, "loss": 0.6633211612701416, "step": 143940 }, { "epoch": 0.855668693641481, "grad_norm": 1.7930299043655396, "learning_rate": 0.0001818356152702825, "loss": 0.7472697257995605, "step": 143950 }, { "epoch": 0.8557281357181494, "grad_norm": 1.4348170757293701, "learning_rate": 0.00018183186512539626, "loss": 0.6146106243133544, "step": 143960 }, { "epoch": 0.8557875777948178, "grad_norm": 1.3363280296325684, "learning_rate": 0.00018182811463688983, "loss": 0.6318952560424804, "step": 143970 }, { "epoch": 0.8558470198714863, "grad_norm": 1.8918999433517456, "learning_rate": 0.00018182436380478122, "loss": 0.6760951042175293, "step": 143980 }, { "epoch": 0.8559064619481547, "grad_norm": 1.4953603744506836, "learning_rate": 0.0001818206126290883, "loss": 0.5991798877716065, "step": 143990 }, { "epoch": 0.855965904024823, "grad_norm": 1.3222471475601196, "learning_rate": 0.00018181686110982904, "loss": 0.6022711277008057, "step": 144000 }, { "epoch": 0.8560253461014914, "grad_norm": 2.074141502380371, "learning_rate": 0.00018181310924702138, "loss": 0.6926345348358154, "step": 144010 }, { "epoch": 0.8560847881781598, "grad_norm": 1.4644817113876343, "learning_rate": 0.00018180935704068327, "loss": 0.6524383544921875, "step": 144020 }, { "epoch": 0.8561442302548282, "grad_norm": 2.656331777572632, "learning_rate": 0.00018180560449083266, "loss": 0.7325276374816895, "step": 144030 }, { "epoch": 0.8562036723314965, "grad_norm": 1.6038264036178589, "learning_rate": 0.00018180185159748753, "loss": 0.6951522350311279, "step": 144040 }, { "epoch": 0.8562631144081649, "grad_norm": 1.8281410932540894, "learning_rate": 0.0001817980983606658, "loss": 0.6582879066467285, "step": 144050 }, { "epoch": 0.8563225564848334, "grad_norm": 1.6968028545379639, "learning_rate": 0.0001817943447803854, "loss": 0.6479106903076172, "step": 144060 }, { "epoch": 0.8563819985615018, "grad_norm": 1.844847321510315, "learning_rate": 0.00018179059085666436, "loss": 0.6650176048278809, "step": 144070 }, { "epoch": 0.8564414406381702, "grad_norm": 1.3370587825775146, "learning_rate": 0.00018178683658952058, "loss": 0.693203353881836, "step": 144080 }, { "epoch": 0.8565008827148385, "grad_norm": 1.5482587814331055, "learning_rate": 0.00018178308197897204, "loss": 0.6666259765625, "step": 144090 }, { "epoch": 0.8565603247915069, "grad_norm": 1.8317276239395142, "learning_rate": 0.00018177932702503668, "loss": 0.6305887222290039, "step": 144100 }, { "epoch": 0.8566197668681753, "grad_norm": 1.4960001707077026, "learning_rate": 0.0001817755717277325, "loss": 0.6865353584289551, "step": 144110 }, { "epoch": 0.8566792089448437, "grad_norm": 1.797188401222229, "learning_rate": 0.0001817718160870774, "loss": 0.6742629528045654, "step": 144120 }, { "epoch": 0.856738651021512, "grad_norm": 1.6513248682022095, "learning_rate": 0.00018176806010308943, "loss": 0.6666741847991944, "step": 144130 }, { "epoch": 0.8567980930981804, "grad_norm": 1.5164544582366943, "learning_rate": 0.00018176430377578648, "loss": 0.6638753890991211, "step": 144140 }, { "epoch": 0.8568575351748489, "grad_norm": 1.9561669826507568, "learning_rate": 0.00018176054710518656, "loss": 0.6440483093261719, "step": 144150 }, { "epoch": 0.8569169772515173, "grad_norm": 2.0489554405212402, "learning_rate": 0.00018175679009130766, "loss": 0.6943555355072022, "step": 144160 }, { "epoch": 0.8569764193281857, "grad_norm": 1.2114129066467285, "learning_rate": 0.00018175303273416772, "loss": 0.6905652046203613, "step": 144170 }, { "epoch": 0.857035861404854, "grad_norm": 1.6815372705459595, "learning_rate": 0.00018174927503378468, "loss": 0.6448184013366699, "step": 144180 }, { "epoch": 0.8570953034815224, "grad_norm": 1.850632667541504, "learning_rate": 0.00018174551699017664, "loss": 0.7125547409057618, "step": 144190 }, { "epoch": 0.8571547455581908, "grad_norm": 1.50894033908844, "learning_rate": 0.0001817417586033614, "loss": 0.6475857734680176, "step": 144200 }, { "epoch": 0.8572141876348592, "grad_norm": 1.8577409982681274, "learning_rate": 0.00018173799987335708, "loss": 0.6122228145599365, "step": 144210 }, { "epoch": 0.8572736297115277, "grad_norm": 1.4658453464508057, "learning_rate": 0.0001817342408001816, "loss": 0.6321439743041992, "step": 144220 }, { "epoch": 0.857333071788196, "grad_norm": 1.4659267663955688, "learning_rate": 0.00018173048138385298, "loss": 0.6365020275115967, "step": 144230 }, { "epoch": 0.8573925138648644, "grad_norm": 1.7279605865478516, "learning_rate": 0.00018172672162438915, "loss": 0.6639440536499024, "step": 144240 }, { "epoch": 0.8574519559415328, "grad_norm": 1.6791118383407593, "learning_rate": 0.00018172296152180816, "loss": 0.6558930397033691, "step": 144250 }, { "epoch": 0.8575113980182012, "grad_norm": 1.6481019258499146, "learning_rate": 0.00018171920107612792, "loss": 0.6393681526184082, "step": 144260 }, { "epoch": 0.8575708400948695, "grad_norm": 1.911206841468811, "learning_rate": 0.00018171544028736648, "loss": 0.6842328548431397, "step": 144270 }, { "epoch": 0.8576302821715379, "grad_norm": 1.95577871799469, "learning_rate": 0.0001817116791555418, "loss": 0.6522994041442871, "step": 144280 }, { "epoch": 0.8576897242482063, "grad_norm": 1.7167364358901978, "learning_rate": 0.00018170791768067188, "loss": 0.6726757049560547, "step": 144290 }, { "epoch": 0.8577491663248747, "grad_norm": 1.1411195993423462, "learning_rate": 0.00018170415586277473, "loss": 0.6152436256408691, "step": 144300 }, { "epoch": 0.8578086084015432, "grad_norm": 1.6141880750656128, "learning_rate": 0.00018170039370186833, "loss": 0.5821283340454102, "step": 144310 }, { "epoch": 0.8578680504782115, "grad_norm": 1.324467658996582, "learning_rate": 0.0001816966311979707, "loss": 0.6171080589294433, "step": 144320 }, { "epoch": 0.8579274925548799, "grad_norm": 1.9902230501174927, "learning_rate": 0.00018169286835109977, "loss": 0.6782416820526123, "step": 144330 }, { "epoch": 0.8579869346315483, "grad_norm": 1.744309425354004, "learning_rate": 0.0001816891051612736, "loss": 0.6449212074279785, "step": 144340 }, { "epoch": 0.8580463767082167, "grad_norm": 1.5190894603729248, "learning_rate": 0.0001816853416285102, "loss": 0.7095995903015136, "step": 144350 }, { "epoch": 0.8581058187848851, "grad_norm": 1.5205276012420654, "learning_rate": 0.00018168157775282754, "loss": 0.6133194923400879, "step": 144360 }, { "epoch": 0.8581652608615534, "grad_norm": 1.438696026802063, "learning_rate": 0.00018167781353424365, "loss": 0.6806508541107178, "step": 144370 }, { "epoch": 0.8582247029382218, "grad_norm": 1.21530020236969, "learning_rate": 0.0001816740489727765, "loss": 0.5959479331970214, "step": 144380 }, { "epoch": 0.8582841450148903, "grad_norm": 1.5393608808517456, "learning_rate": 0.00018167028406844416, "loss": 0.6938436508178711, "step": 144390 }, { "epoch": 0.8583435870915587, "grad_norm": 1.3989124298095703, "learning_rate": 0.00018166651882126455, "loss": 0.6693128108978271, "step": 144400 }, { "epoch": 0.858403029168227, "grad_norm": 1.5853639841079712, "learning_rate": 0.0001816627532312558, "loss": 0.5956826210021973, "step": 144410 }, { "epoch": 0.8584624712448954, "grad_norm": 1.609235167503357, "learning_rate": 0.0001816589872984358, "loss": 0.6274647235870361, "step": 144420 }, { "epoch": 0.8585219133215638, "grad_norm": 1.6476420164108276, "learning_rate": 0.00018165522102282265, "loss": 0.6353913307189941, "step": 144430 }, { "epoch": 0.8585813553982322, "grad_norm": 1.511526346206665, "learning_rate": 0.00018165145440443434, "loss": 0.6965196609497071, "step": 144440 }, { "epoch": 0.8586407974749006, "grad_norm": 1.8338655233383179, "learning_rate": 0.00018164768744328888, "loss": 0.6297436237335206, "step": 144450 }, { "epoch": 0.8587002395515689, "grad_norm": 1.416215419769287, "learning_rate": 0.00018164392013940434, "loss": 0.6919572830200196, "step": 144460 }, { "epoch": 0.8587596816282373, "grad_norm": 1.598783254623413, "learning_rate": 0.0001816401524927986, "loss": 0.6847776412963867, "step": 144470 }, { "epoch": 0.8588191237049058, "grad_norm": 1.6004555225372314, "learning_rate": 0.00018163638450348989, "loss": 0.657056474685669, "step": 144480 }, { "epoch": 0.8588785657815742, "grad_norm": 1.578648567199707, "learning_rate": 0.00018163261617149608, "loss": 0.6385974407196044, "step": 144490 }, { "epoch": 0.8589380078582425, "grad_norm": 1.772257924079895, "learning_rate": 0.00018162884749683522, "loss": 0.6451755046844483, "step": 144500 }, { "epoch": 0.8589974499349109, "grad_norm": 1.669540524482727, "learning_rate": 0.0001816250784795254, "loss": 0.6909510612487793, "step": 144510 }, { "epoch": 0.8590568920115793, "grad_norm": 1.4711664915084839, "learning_rate": 0.00018162130911958459, "loss": 0.5838345527648926, "step": 144520 }, { "epoch": 0.8591163340882477, "grad_norm": 1.5959911346435547, "learning_rate": 0.00018161753941703086, "loss": 0.6522900581359863, "step": 144530 }, { "epoch": 0.8591757761649161, "grad_norm": 1.6568735837936401, "learning_rate": 0.00018161376937188221, "loss": 0.6153281211853028, "step": 144540 }, { "epoch": 0.8592352182415844, "grad_norm": 1.602246880531311, "learning_rate": 0.0001816099989841567, "loss": 0.6666226387023926, "step": 144550 }, { "epoch": 0.8592946603182529, "grad_norm": 1.6882089376449585, "learning_rate": 0.00018160622825387236, "loss": 0.6967651844024658, "step": 144560 }, { "epoch": 0.8593541023949213, "grad_norm": 1.741199016571045, "learning_rate": 0.00018160245718104725, "loss": 0.746622371673584, "step": 144570 }, { "epoch": 0.8594135444715897, "grad_norm": 2.205519914627075, "learning_rate": 0.00018159868576569934, "loss": 0.6451747417449951, "step": 144580 }, { "epoch": 0.8594729865482581, "grad_norm": 1.7540178298950195, "learning_rate": 0.00018159491400784674, "loss": 0.6449837684631348, "step": 144590 }, { "epoch": 0.8595324286249264, "grad_norm": 1.739963412284851, "learning_rate": 0.00018159114190750746, "loss": 0.7009449005126953, "step": 144600 }, { "epoch": 0.8595918707015948, "grad_norm": 1.994370460510254, "learning_rate": 0.00018158736946469957, "loss": 0.647271203994751, "step": 144610 }, { "epoch": 0.8596513127782632, "grad_norm": 1.4701436758041382, "learning_rate": 0.00018158359667944107, "loss": 0.623758602142334, "step": 144620 }, { "epoch": 0.8597107548549316, "grad_norm": 1.9251011610031128, "learning_rate": 0.00018157982355175006, "loss": 0.6261750221252441, "step": 144630 }, { "epoch": 0.8597701969316, "grad_norm": 2.027771472930908, "learning_rate": 0.00018157605008164456, "loss": 0.7040548324584961, "step": 144640 }, { "epoch": 0.8598296390082684, "grad_norm": 1.727736234664917, "learning_rate": 0.00018157227626914264, "loss": 0.6153165340423584, "step": 144650 }, { "epoch": 0.8598890810849368, "grad_norm": 1.4995918273925781, "learning_rate": 0.0001815685021142623, "loss": 0.5910088062286377, "step": 144660 }, { "epoch": 0.8599485231616052, "grad_norm": 1.4654322862625122, "learning_rate": 0.00018156472761702165, "loss": 0.6616145610809326, "step": 144670 }, { "epoch": 0.8600079652382736, "grad_norm": 1.5968537330627441, "learning_rate": 0.00018156095277743878, "loss": 0.6345185279846192, "step": 144680 }, { "epoch": 0.8600674073149419, "grad_norm": 1.6900736093521118, "learning_rate": 0.00018155717759553165, "loss": 0.709561824798584, "step": 144690 }, { "epoch": 0.8601268493916103, "grad_norm": 1.364396333694458, "learning_rate": 0.0001815534020713184, "loss": 0.6434333801269532, "step": 144700 }, { "epoch": 0.8601862914682787, "grad_norm": 1.4798345565795898, "learning_rate": 0.000181549626204817, "loss": 0.6083309650421143, "step": 144710 }, { "epoch": 0.8602457335449472, "grad_norm": 2.179283618927002, "learning_rate": 0.00018154584999604566, "loss": 0.6319190979003906, "step": 144720 }, { "epoch": 0.8603051756216156, "grad_norm": 1.5402288436889648, "learning_rate": 0.00018154207344502229, "loss": 0.6612444877624511, "step": 144730 }, { "epoch": 0.8603646176982839, "grad_norm": 1.4157365560531616, "learning_rate": 0.00018153829655176502, "loss": 0.6435883998870849, "step": 144740 }, { "epoch": 0.8604240597749523, "grad_norm": 1.4342153072357178, "learning_rate": 0.00018153451931629194, "loss": 0.6475643634796142, "step": 144750 }, { "epoch": 0.8604835018516207, "grad_norm": 1.4116461277008057, "learning_rate": 0.00018153074173862108, "loss": 0.6944245338439942, "step": 144760 }, { "epoch": 0.8605429439282891, "grad_norm": 1.6339335441589355, "learning_rate": 0.00018152696381877056, "loss": 0.6094415664672852, "step": 144770 }, { "epoch": 0.8606023860049574, "grad_norm": 1.849727749824524, "learning_rate": 0.00018152318555675838, "loss": 0.7120933532714844, "step": 144780 }, { "epoch": 0.8606618280816258, "grad_norm": 1.3319025039672852, "learning_rate": 0.00018151940695260266, "loss": 0.6538581848144531, "step": 144790 }, { "epoch": 0.8607212701582942, "grad_norm": 1.9296207427978516, "learning_rate": 0.00018151562800632147, "loss": 0.6586162090301514, "step": 144800 }, { "epoch": 0.8607807122349627, "grad_norm": 1.5522691011428833, "learning_rate": 0.00018151184871793293, "loss": 0.671997356414795, "step": 144810 }, { "epoch": 0.8608401543116311, "grad_norm": 1.4414429664611816, "learning_rate": 0.00018150806908745503, "loss": 0.6182470321655273, "step": 144820 }, { "epoch": 0.8608995963882994, "grad_norm": 1.936787724494934, "learning_rate": 0.0001815042891149059, "loss": 0.6501115322113037, "step": 144830 }, { "epoch": 0.8609590384649678, "grad_norm": 1.4524669647216797, "learning_rate": 0.00018150050880030364, "loss": 0.6502795219421387, "step": 144840 }, { "epoch": 0.8610184805416362, "grad_norm": 1.6558786630630493, "learning_rate": 0.0001814967281436663, "loss": 0.6692218780517578, "step": 144850 }, { "epoch": 0.8610779226183046, "grad_norm": 1.6868764162063599, "learning_rate": 0.000181492947145012, "loss": 0.6502434730529785, "step": 144860 }, { "epoch": 0.8611373646949729, "grad_norm": 1.6754000186920166, "learning_rate": 0.00018148916580435878, "loss": 0.6423260688781738, "step": 144870 }, { "epoch": 0.8611968067716413, "grad_norm": 1.6489651203155518, "learning_rate": 0.00018148538412172475, "loss": 0.6655243873596192, "step": 144880 }, { "epoch": 0.8612562488483098, "grad_norm": 1.4474592208862305, "learning_rate": 0.00018148160209712803, "loss": 0.6191930294036865, "step": 144890 }, { "epoch": 0.8613156909249782, "grad_norm": 2.9182968139648438, "learning_rate": 0.00018147781973058667, "loss": 0.7209656715393067, "step": 144900 }, { "epoch": 0.8613751330016466, "grad_norm": 1.5927791595458984, "learning_rate": 0.0001814740370221188, "loss": 0.6084877490997315, "step": 144910 }, { "epoch": 0.8614345750783149, "grad_norm": 1.54569411277771, "learning_rate": 0.00018147025397174244, "loss": 0.5936911582946778, "step": 144920 }, { "epoch": 0.8614940171549833, "grad_norm": 1.674925446510315, "learning_rate": 0.00018146647057947578, "loss": 0.6528874397277832, "step": 144930 }, { "epoch": 0.8615534592316517, "grad_norm": 1.4414604902267456, "learning_rate": 0.00018146268684533686, "loss": 0.5922715187072753, "step": 144940 }, { "epoch": 0.8616129013083201, "grad_norm": 1.768609881401062, "learning_rate": 0.00018145890276934383, "loss": 0.6533596992492676, "step": 144950 }, { "epoch": 0.8616723433849885, "grad_norm": 2.037777900695801, "learning_rate": 0.00018145511835151478, "loss": 0.6604977130889893, "step": 144960 }, { "epoch": 0.8617317854616569, "grad_norm": 1.307837963104248, "learning_rate": 0.00018145133359186773, "loss": 0.6294047355651855, "step": 144970 }, { "epoch": 0.8617912275383253, "grad_norm": 1.7811349630355835, "learning_rate": 0.0001814475484904209, "loss": 0.609000825881958, "step": 144980 }, { "epoch": 0.8618506696149937, "grad_norm": 2.0479013919830322, "learning_rate": 0.00018144376304719232, "loss": 0.6710598468780518, "step": 144990 }, { "epoch": 0.8619101116916621, "grad_norm": 1.7196158170700073, "learning_rate": 0.00018143997726220015, "loss": 0.7370985507965088, "step": 145000 }, { "epoch": 0.8619695537683304, "grad_norm": 1.6318798065185547, "learning_rate": 0.00018143619113546245, "loss": 0.6413256168365479, "step": 145010 }, { "epoch": 0.8620289958449988, "grad_norm": 1.499619722366333, "learning_rate": 0.00018143240466699737, "loss": 0.7325557708740235, "step": 145020 }, { "epoch": 0.8620884379216672, "grad_norm": 1.7568694353103638, "learning_rate": 0.00018142861785682305, "loss": 0.6609084606170654, "step": 145030 }, { "epoch": 0.8621478799983356, "grad_norm": 1.1349762678146362, "learning_rate": 0.00018142483070495753, "loss": 0.6728603363037109, "step": 145040 }, { "epoch": 0.8622073220750041, "grad_norm": 1.311467170715332, "learning_rate": 0.00018142104321141892, "loss": 0.5994620323181152, "step": 145050 }, { "epoch": 0.8622667641516724, "grad_norm": 1.6476184129714966, "learning_rate": 0.00018141725537622542, "loss": 0.6212074279785156, "step": 145060 }, { "epoch": 0.8623262062283408, "grad_norm": 2.636692762374878, "learning_rate": 0.00018141346719939512, "loss": 0.6186785697937012, "step": 145070 }, { "epoch": 0.8623856483050092, "grad_norm": 1.6086653470993042, "learning_rate": 0.0001814096786809461, "loss": 0.6166253566741944, "step": 145080 }, { "epoch": 0.8624450903816776, "grad_norm": 1.5919781923294067, "learning_rate": 0.00018140588982089656, "loss": 0.6225855350494385, "step": 145090 }, { "epoch": 0.862504532458346, "grad_norm": 1.5398099422454834, "learning_rate": 0.00018140210061926454, "loss": 0.6515054702758789, "step": 145100 }, { "epoch": 0.8625639745350143, "grad_norm": 1.7050875425338745, "learning_rate": 0.00018139831107606824, "loss": 0.6090145587921143, "step": 145110 }, { "epoch": 0.8626234166116827, "grad_norm": 2.3138222694396973, "learning_rate": 0.00018139452119132573, "loss": 0.6669372081756592, "step": 145120 }, { "epoch": 0.8626828586883512, "grad_norm": 1.9383461475372314, "learning_rate": 0.00018139073096505516, "loss": 0.6334042072296142, "step": 145130 }, { "epoch": 0.8627423007650196, "grad_norm": 1.3397269248962402, "learning_rate": 0.00018138694039727466, "loss": 0.6081861019134521, "step": 145140 }, { "epoch": 0.8628017428416879, "grad_norm": 1.7276980876922607, "learning_rate": 0.00018138314948800237, "loss": 0.6479060173034668, "step": 145150 }, { "epoch": 0.8628611849183563, "grad_norm": 1.4486169815063477, "learning_rate": 0.00018137935823725641, "loss": 0.6252392768859864, "step": 145160 }, { "epoch": 0.8629206269950247, "grad_norm": 1.9312636852264404, "learning_rate": 0.00018137556664505497, "loss": 0.7336816787719727, "step": 145170 }, { "epoch": 0.8629800690716931, "grad_norm": 1.8220880031585693, "learning_rate": 0.00018137177471141613, "loss": 0.6260884284973145, "step": 145180 }, { "epoch": 0.8630395111483615, "grad_norm": 1.337355613708496, "learning_rate": 0.00018136798243635803, "loss": 0.6164809226989746, "step": 145190 }, { "epoch": 0.8630989532250298, "grad_norm": 1.6569403409957886, "learning_rate": 0.00018136418981989883, "loss": 0.69284086227417, "step": 145200 }, { "epoch": 0.8631583953016982, "grad_norm": 1.365585207939148, "learning_rate": 0.00018136039686205666, "loss": 0.6063137054443359, "step": 145210 }, { "epoch": 0.8632178373783667, "grad_norm": 1.3847264051437378, "learning_rate": 0.00018135660356284966, "loss": 0.6820521354675293, "step": 145220 }, { "epoch": 0.8632772794550351, "grad_norm": 2.055582046508789, "learning_rate": 0.00018135280992229603, "loss": 0.5655498504638672, "step": 145230 }, { "epoch": 0.8633367215317034, "grad_norm": 1.870289921760559, "learning_rate": 0.0001813490159404138, "loss": 0.6234921932220459, "step": 145240 }, { "epoch": 0.8633961636083718, "grad_norm": 1.7168411016464233, "learning_rate": 0.00018134522161722128, "loss": 0.6964141845703125, "step": 145250 }, { "epoch": 0.8634556056850402, "grad_norm": 2.1819400787353516, "learning_rate": 0.0001813414269527365, "loss": 0.6864149093627929, "step": 145260 }, { "epoch": 0.8635150477617086, "grad_norm": 1.5668761730194092, "learning_rate": 0.00018133763194697766, "loss": 0.6897203922271729, "step": 145270 }, { "epoch": 0.863574489838377, "grad_norm": 2.0467591285705566, "learning_rate": 0.00018133383659996288, "loss": 0.7066196441650391, "step": 145280 }, { "epoch": 0.8636339319150453, "grad_norm": 1.3227421045303345, "learning_rate": 0.00018133004091171033, "loss": 0.61435866355896, "step": 145290 }, { "epoch": 0.8636933739917138, "grad_norm": 1.263062596321106, "learning_rate": 0.0001813262448822382, "loss": 0.6699594497680664, "step": 145300 }, { "epoch": 0.8637528160683822, "grad_norm": 1.4961152076721191, "learning_rate": 0.00018132244851156462, "loss": 0.6850544452667237, "step": 145310 }, { "epoch": 0.8638122581450506, "grad_norm": 1.76479172706604, "learning_rate": 0.00018131865179970777, "loss": 0.6636818408966064, "step": 145320 }, { "epoch": 0.863871700221719, "grad_norm": 1.6862006187438965, "learning_rate": 0.00018131485474668578, "loss": 0.6712869644165039, "step": 145330 }, { "epoch": 0.8639311422983873, "grad_norm": 1.6305649280548096, "learning_rate": 0.00018131105735251683, "loss": 0.6544200897216796, "step": 145340 }, { "epoch": 0.8639905843750557, "grad_norm": 1.7551648616790771, "learning_rate": 0.00018130725961721907, "loss": 0.6360324859619141, "step": 145350 }, { "epoch": 0.8640500264517241, "grad_norm": 1.661902904510498, "learning_rate": 0.0001813034615408107, "loss": 0.621855640411377, "step": 145360 }, { "epoch": 0.8641094685283925, "grad_norm": 1.914141297340393, "learning_rate": 0.0001812996631233099, "loss": 0.7338311672210693, "step": 145370 }, { "epoch": 0.8641689106050608, "grad_norm": 1.5925793647766113, "learning_rate": 0.00018129586436473478, "loss": 0.632913875579834, "step": 145380 }, { "epoch": 0.8642283526817293, "grad_norm": 1.7271333932876587, "learning_rate": 0.00018129206526510357, "loss": 0.680356502532959, "step": 145390 }, { "epoch": 0.8642877947583977, "grad_norm": 1.2855026721954346, "learning_rate": 0.0001812882658244344, "loss": 0.632102108001709, "step": 145400 }, { "epoch": 0.8643472368350661, "grad_norm": 1.7688333988189697, "learning_rate": 0.00018128446604274545, "loss": 0.6425952911376953, "step": 145410 }, { "epoch": 0.8644066789117345, "grad_norm": 1.735351800918579, "learning_rate": 0.0001812806659200549, "loss": 0.7809905529022216, "step": 145420 }, { "epoch": 0.8644661209884028, "grad_norm": 1.7525882720947266, "learning_rate": 0.00018127686545638095, "loss": 0.6330100059509277, "step": 145430 }, { "epoch": 0.8645255630650712, "grad_norm": 1.509526014328003, "learning_rate": 0.0001812730646517418, "loss": 0.6288444519042968, "step": 145440 }, { "epoch": 0.8645850051417396, "grad_norm": 1.5629531145095825, "learning_rate": 0.00018126926350615558, "loss": 0.6606978416442871, "step": 145450 }, { "epoch": 0.864644447218408, "grad_norm": 1.9503116607666016, "learning_rate": 0.00018126546201964052, "loss": 0.6621684074401856, "step": 145460 }, { "epoch": 0.8647038892950765, "grad_norm": 1.7817795276641846, "learning_rate": 0.00018126166019221472, "loss": 0.6410757064819336, "step": 145470 }, { "epoch": 0.8647633313717448, "grad_norm": 1.7450085878372192, "learning_rate": 0.0001812578580238965, "loss": 0.6922575473785401, "step": 145480 }, { "epoch": 0.8648227734484132, "grad_norm": 1.7256864309310913, "learning_rate": 0.00018125405551470394, "loss": 0.6393826484680176, "step": 145490 }, { "epoch": 0.8648822155250816, "grad_norm": 1.8900452852249146, "learning_rate": 0.00018125025266465522, "loss": 0.6783658504486084, "step": 145500 }, { "epoch": 0.86494165760175, "grad_norm": 1.688470721244812, "learning_rate": 0.00018124644947376865, "loss": 0.5996944904327393, "step": 145510 }, { "epoch": 0.8650010996784183, "grad_norm": 1.686821460723877, "learning_rate": 0.00018124264594206231, "loss": 0.6444737911224365, "step": 145520 }, { "epoch": 0.8650605417550867, "grad_norm": 1.685847282409668, "learning_rate": 0.00018123884206955443, "loss": 0.6739953041076661, "step": 145530 }, { "epoch": 0.8651199838317551, "grad_norm": 1.5854555368423462, "learning_rate": 0.00018123503785626323, "loss": 0.6527869224548339, "step": 145540 }, { "epoch": 0.8651794259084236, "grad_norm": 1.9994382858276367, "learning_rate": 0.00018123123330220689, "loss": 0.6260593414306641, "step": 145550 }, { "epoch": 0.865238867985092, "grad_norm": 1.6822656393051147, "learning_rate": 0.00018122742840740358, "loss": 0.6432864189147949, "step": 145560 }, { "epoch": 0.8652983100617603, "grad_norm": 2.1526472568511963, "learning_rate": 0.00018122362317187155, "loss": 0.6862568855285645, "step": 145570 }, { "epoch": 0.8653577521384287, "grad_norm": 2.0979931354522705, "learning_rate": 0.000181219817595629, "loss": 0.6730147361755371, "step": 145580 }, { "epoch": 0.8654171942150971, "grad_norm": 1.8002257347106934, "learning_rate": 0.0001812160116786941, "loss": 0.6335830211639404, "step": 145590 }, { "epoch": 0.8654766362917655, "grad_norm": 1.6060227155685425, "learning_rate": 0.00018121220542108505, "loss": 0.6699559211730957, "step": 145600 }, { "epoch": 0.8655360783684338, "grad_norm": 1.5229673385620117, "learning_rate": 0.00018120839882282012, "loss": 0.6320808410644532, "step": 145610 }, { "epoch": 0.8655955204451022, "grad_norm": 1.6939277648925781, "learning_rate": 0.00018120459188391747, "loss": 0.7100199699401856, "step": 145620 }, { "epoch": 0.8656549625217707, "grad_norm": 1.8546088933944702, "learning_rate": 0.0001812007846043953, "loss": 0.6160345554351807, "step": 145630 }, { "epoch": 0.8657144045984391, "grad_norm": 1.8462649583816528, "learning_rate": 0.0001811969769842719, "loss": 0.6719139099121094, "step": 145640 }, { "epoch": 0.8657738466751075, "grad_norm": 1.8249526023864746, "learning_rate": 0.00018119316902356536, "loss": 0.6488827228546142, "step": 145650 }, { "epoch": 0.8658332887517758, "grad_norm": 1.5916659832000732, "learning_rate": 0.00018118936072229402, "loss": 0.7031675338745117, "step": 145660 }, { "epoch": 0.8658927308284442, "grad_norm": 1.44711434841156, "learning_rate": 0.00018118555208047603, "loss": 0.6496399402618408, "step": 145670 }, { "epoch": 0.8659521729051126, "grad_norm": 1.5700773000717163, "learning_rate": 0.00018118174309812962, "loss": 0.6082516670227051, "step": 145680 }, { "epoch": 0.866011614981781, "grad_norm": 1.5189059972763062, "learning_rate": 0.00018117793377527298, "loss": 0.6142508506774902, "step": 145690 }, { "epoch": 0.8660710570584494, "grad_norm": 2.1105897426605225, "learning_rate": 0.00018117412411192442, "loss": 0.6586650371551513, "step": 145700 }, { "epoch": 0.8661304991351177, "grad_norm": 1.9702788591384888, "learning_rate": 0.00018117031410810208, "loss": 0.6428870677947998, "step": 145710 }, { "epoch": 0.8661899412117862, "grad_norm": 1.4909133911132812, "learning_rate": 0.00018116650376382421, "loss": 0.7053855895996094, "step": 145720 }, { "epoch": 0.8662493832884546, "grad_norm": 1.3621797561645508, "learning_rate": 0.00018116269307910904, "loss": 0.6480298519134522, "step": 145730 }, { "epoch": 0.866308825365123, "grad_norm": 1.399269461631775, "learning_rate": 0.0001811588820539748, "loss": 0.6355602264404296, "step": 145740 }, { "epoch": 0.8663682674417913, "grad_norm": 1.527174949645996, "learning_rate": 0.00018115507068843976, "loss": 0.5882917404174804, "step": 145750 }, { "epoch": 0.8664277095184597, "grad_norm": 1.6168744564056396, "learning_rate": 0.0001811512589825221, "loss": 0.6178091526031494, "step": 145760 }, { "epoch": 0.8664871515951281, "grad_norm": 1.4310393333435059, "learning_rate": 0.00018114744693624007, "loss": 0.6662842750549316, "step": 145770 }, { "epoch": 0.8665465936717965, "grad_norm": 1.3761111497879028, "learning_rate": 0.00018114363454961192, "loss": 0.6472014427185059, "step": 145780 }, { "epoch": 0.866606035748465, "grad_norm": 1.9484641551971436, "learning_rate": 0.00018113982182265583, "loss": 0.6849367141723632, "step": 145790 }, { "epoch": 0.8666654778251333, "grad_norm": 1.493462324142456, "learning_rate": 0.00018113600875539008, "loss": 0.6833696842193604, "step": 145800 }, { "epoch": 0.8667249199018017, "grad_norm": 1.424173355102539, "learning_rate": 0.00018113219534783293, "loss": 0.6340246677398682, "step": 145810 }, { "epoch": 0.8667843619784701, "grad_norm": 1.6710715293884277, "learning_rate": 0.00018112838160000262, "loss": 0.6193494319915771, "step": 145820 }, { "epoch": 0.8668438040551385, "grad_norm": 1.8063883781433105, "learning_rate": 0.0001811245675119174, "loss": 0.6834170341491699, "step": 145830 }, { "epoch": 0.8669032461318069, "grad_norm": 1.406955361366272, "learning_rate": 0.00018112075308359543, "loss": 0.6450805187225341, "step": 145840 }, { "epoch": 0.8669626882084752, "grad_norm": 1.6023674011230469, "learning_rate": 0.00018111693831505504, "loss": 0.6683401107788086, "step": 145850 }, { "epoch": 0.8670221302851436, "grad_norm": 1.9919633865356445, "learning_rate": 0.00018111312320631448, "loss": 0.6630171298980713, "step": 145860 }, { "epoch": 0.867081572361812, "grad_norm": 1.4498330354690552, "learning_rate": 0.00018110930775739196, "loss": 0.632505989074707, "step": 145870 }, { "epoch": 0.8671410144384805, "grad_norm": 1.5802079439163208, "learning_rate": 0.00018110549196830578, "loss": 0.6939659118652344, "step": 145880 }, { "epoch": 0.8672004565151488, "grad_norm": 1.6294618844985962, "learning_rate": 0.0001811016758390741, "loss": 0.6557689666748047, "step": 145890 }, { "epoch": 0.8672598985918172, "grad_norm": 2.07993221282959, "learning_rate": 0.0001810978593697153, "loss": 0.6532658576965332, "step": 145900 }, { "epoch": 0.8673193406684856, "grad_norm": 1.7485098838806152, "learning_rate": 0.00018109404256024756, "loss": 0.6643836975097657, "step": 145910 }, { "epoch": 0.867378782745154, "grad_norm": 1.823464035987854, "learning_rate": 0.00018109022541068915, "loss": 0.6397102355957032, "step": 145920 }, { "epoch": 0.8674382248218224, "grad_norm": 1.6327385902404785, "learning_rate": 0.00018108640792105832, "loss": 0.68241286277771, "step": 145930 }, { "epoch": 0.8674976668984907, "grad_norm": 1.7341339588165283, "learning_rate": 0.0001810825900913734, "loss": 0.6471545696258545, "step": 145940 }, { "epoch": 0.8675571089751591, "grad_norm": 1.574810266494751, "learning_rate": 0.0001810787719216525, "loss": 0.6563924312591553, "step": 145950 }, { "epoch": 0.8676165510518276, "grad_norm": 1.5802589654922485, "learning_rate": 0.00018107495341191404, "loss": 0.6544147491455078, "step": 145960 }, { "epoch": 0.867675993128496, "grad_norm": 1.8668862581253052, "learning_rate": 0.00018107113456217625, "loss": 0.6802417755126953, "step": 145970 }, { "epoch": 0.8677354352051643, "grad_norm": 1.4994713068008423, "learning_rate": 0.00018106731537245735, "loss": 0.6337030410766602, "step": 145980 }, { "epoch": 0.8677948772818327, "grad_norm": 1.576229453086853, "learning_rate": 0.00018106349584277566, "loss": 0.7177921295166015, "step": 145990 }, { "epoch": 0.8678543193585011, "grad_norm": 2.066065549850464, "learning_rate": 0.00018105967597314943, "loss": 0.6393694400787353, "step": 146000 }, { "epoch": 0.8679137614351695, "grad_norm": 1.7246381044387817, "learning_rate": 0.00018105585576359693, "loss": 0.6313464641571045, "step": 146010 }, { "epoch": 0.8679732035118379, "grad_norm": 1.9942224025726318, "learning_rate": 0.00018105203521413642, "loss": 0.6529349327087403, "step": 146020 }, { "epoch": 0.8680326455885062, "grad_norm": 1.703952431678772, "learning_rate": 0.0001810482143247862, "loss": 0.6701308727264405, "step": 146030 }, { "epoch": 0.8680920876651746, "grad_norm": 1.5694326162338257, "learning_rate": 0.00018104439309556453, "loss": 0.6801226139068604, "step": 146040 }, { "epoch": 0.8681515297418431, "grad_norm": 1.682839035987854, "learning_rate": 0.00018104057152648972, "loss": 0.6870229721069336, "step": 146050 }, { "epoch": 0.8682109718185115, "grad_norm": 1.4407728910446167, "learning_rate": 0.00018103674961758004, "loss": 0.6818088531494141, "step": 146060 }, { "epoch": 0.8682704138951799, "grad_norm": 1.7281643152236938, "learning_rate": 0.00018103292736885374, "loss": 0.6845171928405762, "step": 146070 }, { "epoch": 0.8683298559718482, "grad_norm": 1.7818653583526611, "learning_rate": 0.00018102910478032914, "loss": 0.6337624073028565, "step": 146080 }, { "epoch": 0.8683892980485166, "grad_norm": 1.8858658075332642, "learning_rate": 0.00018102528185202452, "loss": 0.6604931354522705, "step": 146090 }, { "epoch": 0.868448740125185, "grad_norm": 1.4656671285629272, "learning_rate": 0.00018102145858395815, "loss": 0.6675931453704834, "step": 146100 }, { "epoch": 0.8685081822018534, "grad_norm": 1.6863704919815063, "learning_rate": 0.00018101763497614835, "loss": 0.6247114181518555, "step": 146110 }, { "epoch": 0.8685676242785217, "grad_norm": 2.435825824737549, "learning_rate": 0.00018101381102861338, "loss": 0.6364075183868408, "step": 146120 }, { "epoch": 0.8686270663551902, "grad_norm": 1.471139669418335, "learning_rate": 0.00018100998674137154, "loss": 0.6099645137786865, "step": 146130 }, { "epoch": 0.8686865084318586, "grad_norm": 1.5347998142242432, "learning_rate": 0.00018100616211444117, "loss": 0.6957229614257813, "step": 146140 }, { "epoch": 0.868745950508527, "grad_norm": 1.486698031425476, "learning_rate": 0.0001810023371478405, "loss": 0.6229554176330566, "step": 146150 }, { "epoch": 0.8688053925851954, "grad_norm": 2.0043139457702637, "learning_rate": 0.00018099851184158784, "loss": 0.6886455535888671, "step": 146160 }, { "epoch": 0.8688648346618637, "grad_norm": 1.8278205394744873, "learning_rate": 0.00018099468619570152, "loss": 0.6570242881774903, "step": 146170 }, { "epoch": 0.8689242767385321, "grad_norm": 1.655403733253479, "learning_rate": 0.0001809908602101998, "loss": 0.6721136093139648, "step": 146180 }, { "epoch": 0.8689837188152005, "grad_norm": 1.5995359420776367, "learning_rate": 0.00018098703388510102, "loss": 0.5848972797393799, "step": 146190 }, { "epoch": 0.869043160891869, "grad_norm": 1.9643020629882812, "learning_rate": 0.00018098320722042345, "loss": 0.6548628807067871, "step": 146200 }, { "epoch": 0.8691026029685374, "grad_norm": 1.4711378812789917, "learning_rate": 0.00018097938021618544, "loss": 0.6736501693725586, "step": 146210 }, { "epoch": 0.8691620450452057, "grad_norm": 1.7451562881469727, "learning_rate": 0.00018097555287240527, "loss": 0.6705112457275391, "step": 146220 }, { "epoch": 0.8692214871218741, "grad_norm": 2.3416786193847656, "learning_rate": 0.00018097172518910127, "loss": 0.6861937522888184, "step": 146230 }, { "epoch": 0.8692809291985425, "grad_norm": 1.5173183679580688, "learning_rate": 0.00018096789716629167, "loss": 0.6119802474975586, "step": 146240 }, { "epoch": 0.8693403712752109, "grad_norm": 2.662386178970337, "learning_rate": 0.00018096406880399487, "loss": 0.6281676292419434, "step": 146250 }, { "epoch": 0.8693998133518792, "grad_norm": 1.8838939666748047, "learning_rate": 0.00018096024010222917, "loss": 0.6726563453674317, "step": 146260 }, { "epoch": 0.8694592554285476, "grad_norm": 1.2513197660446167, "learning_rate": 0.00018095641106101286, "loss": 0.6468565940856934, "step": 146270 }, { "epoch": 0.869518697505216, "grad_norm": 1.3356635570526123, "learning_rate": 0.0001809525816803643, "loss": 0.7036001205444335, "step": 146280 }, { "epoch": 0.8695781395818845, "grad_norm": 1.4559305906295776, "learning_rate": 0.00018094875196030173, "loss": 0.583320426940918, "step": 146290 }, { "epoch": 0.8696375816585529, "grad_norm": 1.5552339553833008, "learning_rate": 0.00018094492190084353, "loss": 0.6380647659301758, "step": 146300 }, { "epoch": 0.8696970237352212, "grad_norm": 1.8806551694869995, "learning_rate": 0.000180941091502008, "loss": 0.6543875217437745, "step": 146310 }, { "epoch": 0.8697564658118896, "grad_norm": 1.7424266338348389, "learning_rate": 0.00018093726076381348, "loss": 0.669379711151123, "step": 146320 }, { "epoch": 0.869815907888558, "grad_norm": 1.804761528968811, "learning_rate": 0.00018093342968627832, "loss": 0.6779498100280762, "step": 146330 }, { "epoch": 0.8698753499652264, "grad_norm": 1.3776905536651611, "learning_rate": 0.00018092959826942077, "loss": 0.7054913520812989, "step": 146340 }, { "epoch": 0.8699347920418947, "grad_norm": 1.669470191001892, "learning_rate": 0.00018092576651325924, "loss": 0.6314674854278565, "step": 146350 }, { "epoch": 0.8699942341185631, "grad_norm": 2.2395246028900146, "learning_rate": 0.000180921934417812, "loss": 0.6683182716369629, "step": 146360 }, { "epoch": 0.8700536761952316, "grad_norm": 1.5518338680267334, "learning_rate": 0.0001809181019830974, "loss": 0.6020066261291503, "step": 146370 }, { "epoch": 0.8701131182719, "grad_norm": 1.5067039728164673, "learning_rate": 0.00018091426920913378, "loss": 0.6478078365325928, "step": 146380 }, { "epoch": 0.8701725603485684, "grad_norm": 1.6673271656036377, "learning_rate": 0.00018091043609593947, "loss": 0.6546525001525879, "step": 146390 }, { "epoch": 0.8702320024252367, "grad_norm": 1.97773277759552, "learning_rate": 0.00018090660264353278, "loss": 0.6260031700134278, "step": 146400 }, { "epoch": 0.8702914445019051, "grad_norm": 1.2564010620117188, "learning_rate": 0.0001809027688519321, "loss": 0.6312915802001953, "step": 146410 }, { "epoch": 0.8703508865785735, "grad_norm": 1.5923717021942139, "learning_rate": 0.00018089893472115576, "loss": 0.6757933616638183, "step": 146420 }, { "epoch": 0.8704103286552419, "grad_norm": 1.6052416563034058, "learning_rate": 0.0001808951002512221, "loss": 0.6418482780456543, "step": 146430 }, { "epoch": 0.8704697707319103, "grad_norm": 1.690627932548523, "learning_rate": 0.00018089126544214943, "loss": 0.6532434940338134, "step": 146440 }, { "epoch": 0.8705292128085786, "grad_norm": 1.7442222833633423, "learning_rate": 0.00018088743029395608, "loss": 0.6780150413513184, "step": 146450 }, { "epoch": 0.8705886548852471, "grad_norm": 1.625512957572937, "learning_rate": 0.00018088359480666048, "loss": 0.606595230102539, "step": 146460 }, { "epoch": 0.8706480969619155, "grad_norm": 1.735805630683899, "learning_rate": 0.00018087975898028091, "loss": 0.6566797256469726, "step": 146470 }, { "epoch": 0.8707075390385839, "grad_norm": 1.730010747909546, "learning_rate": 0.00018087592281483571, "loss": 0.621268367767334, "step": 146480 }, { "epoch": 0.8707669811152522, "grad_norm": 1.905821442604065, "learning_rate": 0.00018087208631034328, "loss": 0.6198089599609375, "step": 146490 }, { "epoch": 0.8708264231919206, "grad_norm": 1.7281805276870728, "learning_rate": 0.00018086824946682195, "loss": 0.6290281772613525, "step": 146500 }, { "epoch": 0.870885865268589, "grad_norm": 1.8731424808502197, "learning_rate": 0.0001808644122842901, "loss": 0.7692689895629883, "step": 146510 }, { "epoch": 0.8709453073452574, "grad_norm": 1.8170307874679565, "learning_rate": 0.000180860574762766, "loss": 0.6465526580810547, "step": 146520 }, { "epoch": 0.8710047494219259, "grad_norm": 1.4036613702774048, "learning_rate": 0.00018085673690226812, "loss": 0.6529372215270997, "step": 146530 }, { "epoch": 0.8710641914985942, "grad_norm": 1.8425711393356323, "learning_rate": 0.00018085289870281473, "loss": 0.6812491893768311, "step": 146540 }, { "epoch": 0.8711236335752626, "grad_norm": 1.710789680480957, "learning_rate": 0.00018084906016442427, "loss": 0.64517822265625, "step": 146550 }, { "epoch": 0.871183075651931, "grad_norm": 1.8031240701675415, "learning_rate": 0.00018084522128711502, "loss": 0.6688309669494629, "step": 146560 }, { "epoch": 0.8712425177285994, "grad_norm": 1.412584900856018, "learning_rate": 0.00018084138207090543, "loss": 0.6140105247497558, "step": 146570 }, { "epoch": 0.8713019598052678, "grad_norm": 1.7687113285064697, "learning_rate": 0.00018083754251581378, "loss": 0.6876258850097656, "step": 146580 }, { "epoch": 0.8713614018819361, "grad_norm": 2.083216428756714, "learning_rate": 0.0001808337026218585, "loss": 0.6595832347869873, "step": 146590 }, { "epoch": 0.8714208439586045, "grad_norm": 1.7519625425338745, "learning_rate": 0.00018082986238905792, "loss": 0.6492234230041504, "step": 146600 }, { "epoch": 0.8714802860352729, "grad_norm": 1.634601354598999, "learning_rate": 0.00018082602181743044, "loss": 0.6950217247009277, "step": 146610 }, { "epoch": 0.8715397281119414, "grad_norm": 1.6636037826538086, "learning_rate": 0.00018082218090699435, "loss": 0.568056297302246, "step": 146620 }, { "epoch": 0.8715991701886097, "grad_norm": 1.536270022392273, "learning_rate": 0.00018081833965776818, "loss": 0.7092211246490479, "step": 146630 }, { "epoch": 0.8716586122652781, "grad_norm": 1.7276744842529297, "learning_rate": 0.00018081449806977017, "loss": 0.6686649799346924, "step": 146640 }, { "epoch": 0.8717180543419465, "grad_norm": 1.3669171333312988, "learning_rate": 0.00018081065614301877, "loss": 0.5983725547790527, "step": 146650 }, { "epoch": 0.8717774964186149, "grad_norm": 1.5027117729187012, "learning_rate": 0.00018080681387753233, "loss": 0.6145856380462646, "step": 146660 }, { "epoch": 0.8718369384952833, "grad_norm": 1.6670169830322266, "learning_rate": 0.00018080297127332921, "loss": 0.6639583587646485, "step": 146670 }, { "epoch": 0.8718963805719516, "grad_norm": 1.5991681814193726, "learning_rate": 0.00018079912833042784, "loss": 0.6695025444030762, "step": 146680 }, { "epoch": 0.87195582264862, "grad_norm": 2.1423447132110596, "learning_rate": 0.00018079528504884654, "loss": 0.6868369102478027, "step": 146690 }, { "epoch": 0.8720152647252885, "grad_norm": 1.7647870779037476, "learning_rate": 0.0001807914414286038, "loss": 0.670781135559082, "step": 146700 }, { "epoch": 0.8720747068019569, "grad_norm": 1.3677297830581665, "learning_rate": 0.00018078759746971784, "loss": 0.6428807258605957, "step": 146710 }, { "epoch": 0.8721341488786252, "grad_norm": 1.9746251106262207, "learning_rate": 0.00018078375317220723, "loss": 0.6638298988342285, "step": 146720 }, { "epoch": 0.8721935909552936, "grad_norm": 1.4215505123138428, "learning_rate": 0.00018077990853609024, "loss": 0.6337056159973145, "step": 146730 }, { "epoch": 0.872253033031962, "grad_norm": 1.643625020980835, "learning_rate": 0.00018077606356138533, "loss": 0.6890378952026367, "step": 146740 }, { "epoch": 0.8723124751086304, "grad_norm": 1.804984211921692, "learning_rate": 0.00018077221824811082, "loss": 0.6755670070648193, "step": 146750 }, { "epoch": 0.8723719171852988, "grad_norm": 1.5709786415100098, "learning_rate": 0.0001807683725962852, "loss": 0.6736570358276367, "step": 146760 }, { "epoch": 0.8724313592619671, "grad_norm": 1.860425353050232, "learning_rate": 0.00018076452660592676, "loss": 0.648149061203003, "step": 146770 }, { "epoch": 0.8724908013386355, "grad_norm": 1.7665077447891235, "learning_rate": 0.00018076068027705398, "loss": 0.6343992233276368, "step": 146780 }, { "epoch": 0.872550243415304, "grad_norm": 1.5559680461883545, "learning_rate": 0.0001807568336096852, "loss": 0.636324119567871, "step": 146790 }, { "epoch": 0.8726096854919724, "grad_norm": 2.002131462097168, "learning_rate": 0.0001807529866038389, "loss": 0.6423290252685547, "step": 146800 }, { "epoch": 0.8726691275686408, "grad_norm": 1.7489339113235474, "learning_rate": 0.0001807491392595334, "loss": 0.611142921447754, "step": 146810 }, { "epoch": 0.8727285696453091, "grad_norm": 1.6911523342132568, "learning_rate": 0.00018074529157678713, "loss": 0.6705290794372558, "step": 146820 }, { "epoch": 0.8727880117219775, "grad_norm": 1.5507458448410034, "learning_rate": 0.00018074144355561853, "loss": 0.6763711452484131, "step": 146830 }, { "epoch": 0.8728474537986459, "grad_norm": 1.5953197479248047, "learning_rate": 0.00018073759519604597, "loss": 0.6638388633728027, "step": 146840 }, { "epoch": 0.8729068958753143, "grad_norm": 1.4355462789535522, "learning_rate": 0.00018073374649808788, "loss": 0.6655533790588379, "step": 146850 }, { "epoch": 0.8729663379519826, "grad_norm": 2.3250515460968018, "learning_rate": 0.00018072989746176264, "loss": 0.6589637756347656, "step": 146860 }, { "epoch": 0.873025780028651, "grad_norm": 1.7090703248977661, "learning_rate": 0.0001807260480870887, "loss": 0.679612112045288, "step": 146870 }, { "epoch": 0.8730852221053195, "grad_norm": 1.5142114162445068, "learning_rate": 0.0001807221983740845, "loss": 0.6608798027038574, "step": 146880 }, { "epoch": 0.8731446641819879, "grad_norm": 1.9860336780548096, "learning_rate": 0.00018071834832276837, "loss": 0.7046349525451661, "step": 146890 }, { "epoch": 0.8732041062586563, "grad_norm": 1.7689613103866577, "learning_rate": 0.00018071449793315877, "loss": 0.6715781211853027, "step": 146900 }, { "epoch": 0.8732635483353246, "grad_norm": 1.5727291107177734, "learning_rate": 0.00018071064720527415, "loss": 0.6021759033203125, "step": 146910 }, { "epoch": 0.873322990411993, "grad_norm": 1.5262978076934814, "learning_rate": 0.00018070679613913288, "loss": 0.6658288955688476, "step": 146920 }, { "epoch": 0.8733824324886614, "grad_norm": 1.3317450284957886, "learning_rate": 0.0001807029447347534, "loss": 0.6434943675994873, "step": 146930 }, { "epoch": 0.8734418745653298, "grad_norm": 1.7557467222213745, "learning_rate": 0.00018069909299215416, "loss": 0.6240930557250977, "step": 146940 }, { "epoch": 0.8735013166419983, "grad_norm": 1.8860878944396973, "learning_rate": 0.00018069524091135356, "loss": 0.6945073127746582, "step": 146950 }, { "epoch": 0.8735607587186666, "grad_norm": 1.4195232391357422, "learning_rate": 0.00018069138849237, "loss": 0.6470314979553222, "step": 146960 }, { "epoch": 0.873620200795335, "grad_norm": 1.6377044916152954, "learning_rate": 0.00018068753573522196, "loss": 0.6135349273681641, "step": 146970 }, { "epoch": 0.8736796428720034, "grad_norm": 1.6296850442886353, "learning_rate": 0.00018068368263992785, "loss": 0.6771621704101562, "step": 146980 }, { "epoch": 0.8737390849486718, "grad_norm": 1.501893401145935, "learning_rate": 0.0001806798292065061, "loss": 0.6493918418884277, "step": 146990 }, { "epoch": 0.8737985270253401, "grad_norm": 1.9549932479858398, "learning_rate": 0.00018067597543497518, "loss": 0.6484688282012939, "step": 147000 }, { "epoch": 0.8738579691020085, "grad_norm": 1.574513554573059, "learning_rate": 0.00018067212132535346, "loss": 0.6918122291564941, "step": 147010 }, { "epoch": 0.8739174111786769, "grad_norm": 1.8867125511169434, "learning_rate": 0.0001806682668776594, "loss": 0.6420377254486084, "step": 147020 }, { "epoch": 0.8739768532553454, "grad_norm": 1.7196763753890991, "learning_rate": 0.00018066441209191146, "loss": 0.7024692535400391, "step": 147030 }, { "epoch": 0.8740362953320138, "grad_norm": 1.17018723487854, "learning_rate": 0.00018066055696812808, "loss": 0.6093153953552246, "step": 147040 }, { "epoch": 0.8740957374086821, "grad_norm": 1.4997279644012451, "learning_rate": 0.00018065670150632765, "loss": 0.6234687805175781, "step": 147050 }, { "epoch": 0.8741551794853505, "grad_norm": 2.048935651779175, "learning_rate": 0.00018065284570652866, "loss": 0.6320827960968017, "step": 147060 }, { "epoch": 0.8742146215620189, "grad_norm": 1.4844920635223389, "learning_rate": 0.00018064898956874956, "loss": 0.6286555290222168, "step": 147070 }, { "epoch": 0.8742740636386873, "grad_norm": 1.620995044708252, "learning_rate": 0.00018064513309300876, "loss": 0.6614895343780518, "step": 147080 }, { "epoch": 0.8743335057153556, "grad_norm": 1.5843760967254639, "learning_rate": 0.00018064127627932474, "loss": 0.6649406433105469, "step": 147090 }, { "epoch": 0.874392947792024, "grad_norm": 1.7131004333496094, "learning_rate": 0.00018063741912771594, "loss": 0.6895054817199707, "step": 147100 }, { "epoch": 0.8744523898686924, "grad_norm": 1.6382840871810913, "learning_rate": 0.00018063356163820085, "loss": 0.6829305648803711, "step": 147110 }, { "epoch": 0.8745118319453609, "grad_norm": 1.6616700887680054, "learning_rate": 0.00018062970381079786, "loss": 0.628041934967041, "step": 147120 }, { "epoch": 0.8745712740220293, "grad_norm": 1.8304593563079834, "learning_rate": 0.00018062584564552543, "loss": 0.6729809761047363, "step": 147130 }, { "epoch": 0.8746307160986976, "grad_norm": 1.5085152387619019, "learning_rate": 0.00018062198714240206, "loss": 0.6865492343902588, "step": 147140 }, { "epoch": 0.874690158175366, "grad_norm": 1.6766728162765503, "learning_rate": 0.00018061812830144617, "loss": 0.656544828414917, "step": 147150 }, { "epoch": 0.8747496002520344, "grad_norm": 1.6740115880966187, "learning_rate": 0.00018061426912267621, "loss": 0.6602584838867187, "step": 147160 }, { "epoch": 0.8748090423287028, "grad_norm": 1.623733639717102, "learning_rate": 0.0001806104096061107, "loss": 0.6651957511901856, "step": 147170 }, { "epoch": 0.8748684844053712, "grad_norm": 1.7896146774291992, "learning_rate": 0.00018060654975176805, "loss": 0.643366527557373, "step": 147180 }, { "epoch": 0.8749279264820395, "grad_norm": 1.8259485960006714, "learning_rate": 0.00018060268955966672, "loss": 0.7110270023345947, "step": 147190 }, { "epoch": 0.874987368558708, "grad_norm": 1.6669002771377563, "learning_rate": 0.00018059882902982522, "loss": 0.7228490829467773, "step": 147200 }, { "epoch": 0.8750468106353764, "grad_norm": 1.3800281286239624, "learning_rate": 0.00018059496816226202, "loss": 0.6109652042388916, "step": 147210 }, { "epoch": 0.8751062527120448, "grad_norm": 1.4466496706008911, "learning_rate": 0.0001805911069569955, "loss": 0.6638800621032714, "step": 147220 }, { "epoch": 0.8751656947887131, "grad_norm": 1.953813910484314, "learning_rate": 0.00018058724541404427, "loss": 0.6551848411560058, "step": 147230 }, { "epoch": 0.8752251368653815, "grad_norm": 1.519798755645752, "learning_rate": 0.00018058338353342667, "loss": 0.6397163391113281, "step": 147240 }, { "epoch": 0.8752845789420499, "grad_norm": 1.6030899286270142, "learning_rate": 0.00018057952131516123, "loss": 0.6686853408813477, "step": 147250 }, { "epoch": 0.8753440210187183, "grad_norm": 1.6433309316635132, "learning_rate": 0.00018057565875926647, "loss": 0.6757279396057129, "step": 147260 }, { "epoch": 0.8754034630953867, "grad_norm": 1.5359470844268799, "learning_rate": 0.00018057179586576078, "loss": 0.6971739292144775, "step": 147270 }, { "epoch": 0.875462905172055, "grad_norm": 1.422365665435791, "learning_rate": 0.0001805679326346627, "loss": 0.610064697265625, "step": 147280 }, { "epoch": 0.8755223472487235, "grad_norm": 1.4516143798828125, "learning_rate": 0.0001805640690659907, "loss": 0.5873056411743164, "step": 147290 }, { "epoch": 0.8755817893253919, "grad_norm": 1.7616814374923706, "learning_rate": 0.00018056020515976322, "loss": 0.6370738029479981, "step": 147300 }, { "epoch": 0.8756412314020603, "grad_norm": 1.3066151142120361, "learning_rate": 0.0001805563409159988, "loss": 0.6209197998046875, "step": 147310 }, { "epoch": 0.8757006734787287, "grad_norm": 1.4726457595825195, "learning_rate": 0.0001805524763347159, "loss": 0.670295524597168, "step": 147320 }, { "epoch": 0.875760115555397, "grad_norm": 1.8497498035430908, "learning_rate": 0.00018054861141593304, "loss": 0.5976961135864258, "step": 147330 }, { "epoch": 0.8758195576320654, "grad_norm": 1.3458722829818726, "learning_rate": 0.00018054474615966862, "loss": 0.6247662544250489, "step": 147340 }, { "epoch": 0.8758789997087338, "grad_norm": 1.425856113433838, "learning_rate": 0.00018054088056594124, "loss": 0.6630763530731201, "step": 147350 }, { "epoch": 0.8759384417854023, "grad_norm": 1.6823439598083496, "learning_rate": 0.00018053701463476932, "loss": 0.6631877899169922, "step": 147360 }, { "epoch": 0.8759978838620706, "grad_norm": 2.296255588531494, "learning_rate": 0.00018053314836617137, "loss": 0.6831463813781739, "step": 147370 }, { "epoch": 0.876057325938739, "grad_norm": 1.5530794858932495, "learning_rate": 0.0001805292817601659, "loss": 0.6511980056762695, "step": 147380 }, { "epoch": 0.8761167680154074, "grad_norm": 1.491394281387329, "learning_rate": 0.00018052541481677136, "loss": 0.6767434120178223, "step": 147390 }, { "epoch": 0.8761762100920758, "grad_norm": 1.6110448837280273, "learning_rate": 0.0001805215475360063, "loss": 0.6181097030639648, "step": 147400 }, { "epoch": 0.8762356521687442, "grad_norm": 1.5225064754486084, "learning_rate": 0.00018051767991788926, "loss": 0.6340390205383301, "step": 147410 }, { "epoch": 0.8762950942454125, "grad_norm": 1.4260388612747192, "learning_rate": 0.00018051381196243862, "loss": 0.6926002979278565, "step": 147420 }, { "epoch": 0.8763545363220809, "grad_norm": 1.3384478092193604, "learning_rate": 0.00018050994366967298, "loss": 0.6312673568725586, "step": 147430 }, { "epoch": 0.8764139783987493, "grad_norm": 1.855548620223999, "learning_rate": 0.00018050607503961082, "loss": 0.6749121665954589, "step": 147440 }, { "epoch": 0.8764734204754178, "grad_norm": 1.5696660280227661, "learning_rate": 0.0001805022060722706, "loss": 0.7003127098083496, "step": 147450 }, { "epoch": 0.8765328625520861, "grad_norm": 1.2851026058197021, "learning_rate": 0.0001804983367676709, "loss": 0.5969990730285645, "step": 147460 }, { "epoch": 0.8765923046287545, "grad_norm": 1.387758493423462, "learning_rate": 0.0001804944671258302, "loss": 0.6685295104980469, "step": 147470 }, { "epoch": 0.8766517467054229, "grad_norm": 1.8866225481033325, "learning_rate": 0.00018049059714676696, "loss": 0.7238023757934571, "step": 147480 }, { "epoch": 0.8767111887820913, "grad_norm": 1.802136778831482, "learning_rate": 0.00018048672683049975, "loss": 0.6652896881103516, "step": 147490 }, { "epoch": 0.8767706308587597, "grad_norm": 1.8288732767105103, "learning_rate": 0.0001804828561770471, "loss": 0.6744741439819336, "step": 147500 }, { "epoch": 0.876830072935428, "grad_norm": 1.8222880363464355, "learning_rate": 0.0001804789851864275, "loss": 0.6060701370239258, "step": 147510 }, { "epoch": 0.8768895150120964, "grad_norm": 1.702366590499878, "learning_rate": 0.00018047511385865946, "loss": 0.6920073509216309, "step": 147520 }, { "epoch": 0.8769489570887649, "grad_norm": 1.81923508644104, "learning_rate": 0.0001804712421937615, "loss": 0.67036452293396, "step": 147530 }, { "epoch": 0.8770083991654333, "grad_norm": 1.757764458656311, "learning_rate": 0.00018046737019175216, "loss": 0.6365947723388672, "step": 147540 }, { "epoch": 0.8770678412421017, "grad_norm": 1.56515371799469, "learning_rate": 0.00018046349785264993, "loss": 0.6196723937988281, "step": 147550 }, { "epoch": 0.87712728331877, "grad_norm": 1.7523565292358398, "learning_rate": 0.00018045962517647336, "loss": 0.6501027107238769, "step": 147560 }, { "epoch": 0.8771867253954384, "grad_norm": 1.5764362812042236, "learning_rate": 0.000180455752163241, "loss": 0.6684270858764648, "step": 147570 }, { "epoch": 0.8772461674721068, "grad_norm": 1.8947710990905762, "learning_rate": 0.00018045187881297133, "loss": 0.6310998916625976, "step": 147580 }, { "epoch": 0.8773056095487752, "grad_norm": 1.8666383028030396, "learning_rate": 0.00018044800512568288, "loss": 0.6289760589599609, "step": 147590 }, { "epoch": 0.8773650516254435, "grad_norm": 1.686394214630127, "learning_rate": 0.0001804441311013942, "loss": 0.6426316738128662, "step": 147600 }, { "epoch": 0.877424493702112, "grad_norm": 1.4755337238311768, "learning_rate": 0.00018044025674012384, "loss": 0.6063332557678223, "step": 147610 }, { "epoch": 0.8774839357787804, "grad_norm": 1.4941401481628418, "learning_rate": 0.0001804363820418903, "loss": 0.5859969139099122, "step": 147620 }, { "epoch": 0.8775433778554488, "grad_norm": 1.3867257833480835, "learning_rate": 0.00018043250700671212, "loss": 0.6770224571228027, "step": 147630 }, { "epoch": 0.8776028199321172, "grad_norm": 1.642714262008667, "learning_rate": 0.00018042863163460785, "loss": 0.6717396736145019, "step": 147640 }, { "epoch": 0.8776622620087855, "grad_norm": 1.6848500967025757, "learning_rate": 0.000180424755925596, "loss": 0.6479750633239746, "step": 147650 }, { "epoch": 0.8777217040854539, "grad_norm": 1.7602167129516602, "learning_rate": 0.00018042087987969518, "loss": 0.6423540115356445, "step": 147660 }, { "epoch": 0.8777811461621223, "grad_norm": 1.5413613319396973, "learning_rate": 0.00018041700349692385, "loss": 0.6624837875366211, "step": 147670 }, { "epoch": 0.8778405882387907, "grad_norm": 1.682083010673523, "learning_rate": 0.0001804131267773006, "loss": 0.7296528816223145, "step": 147680 }, { "epoch": 0.877900030315459, "grad_norm": 1.9974467754364014, "learning_rate": 0.00018040924972084397, "loss": 0.620777940750122, "step": 147690 }, { "epoch": 0.8779594723921275, "grad_norm": 1.7784807682037354, "learning_rate": 0.00018040537232757246, "loss": 0.6030648231506348, "step": 147700 }, { "epoch": 0.8780189144687959, "grad_norm": 1.482157588005066, "learning_rate": 0.0001804014945975047, "loss": 0.6497501373291016, "step": 147710 }, { "epoch": 0.8780783565454643, "grad_norm": 1.9965633153915405, "learning_rate": 0.00018039761653065918, "loss": 0.6671374320983887, "step": 147720 }, { "epoch": 0.8781377986221327, "grad_norm": 1.5967661142349243, "learning_rate": 0.00018039373812705448, "loss": 0.6354273796081543, "step": 147730 }, { "epoch": 0.878197240698801, "grad_norm": 1.617601752281189, "learning_rate": 0.0001803898593867091, "loss": 0.6194312572479248, "step": 147740 }, { "epoch": 0.8782566827754694, "grad_norm": 1.3806407451629639, "learning_rate": 0.0001803859803096417, "loss": 0.6846038818359375, "step": 147750 }, { "epoch": 0.8783161248521378, "grad_norm": 1.7295230627059937, "learning_rate": 0.00018038210089587074, "loss": 0.6093779563903808, "step": 147760 }, { "epoch": 0.8783755669288063, "grad_norm": 1.4853836297988892, "learning_rate": 0.00018037822114541483, "loss": 0.6670993804931641, "step": 147770 }, { "epoch": 0.8784350090054747, "grad_norm": 2.01656174659729, "learning_rate": 0.00018037434105829247, "loss": 0.6783963680267334, "step": 147780 }, { "epoch": 0.878494451082143, "grad_norm": 1.3539894819259644, "learning_rate": 0.0001803704606345223, "loss": 0.6503469944000244, "step": 147790 }, { "epoch": 0.8785538931588114, "grad_norm": 2.112950325012207, "learning_rate": 0.00018036657987412281, "loss": 0.6219793319702148, "step": 147800 }, { "epoch": 0.8786133352354798, "grad_norm": 1.677737832069397, "learning_rate": 0.00018036269877711264, "loss": 0.6888193130493164, "step": 147810 }, { "epoch": 0.8786727773121482, "grad_norm": 1.277872085571289, "learning_rate": 0.00018035881734351027, "loss": 0.6804283142089844, "step": 147820 }, { "epoch": 0.8787322193888165, "grad_norm": 6.70301628112793, "learning_rate": 0.00018035493557333433, "loss": 0.6694347381591796, "step": 147830 }, { "epoch": 0.8787916614654849, "grad_norm": 2.034618616104126, "learning_rate": 0.00018035105346660336, "loss": 0.7296100616455078, "step": 147840 }, { "epoch": 0.8788511035421533, "grad_norm": 1.4655547142028809, "learning_rate": 0.00018034717102333596, "loss": 0.6438578605651856, "step": 147850 }, { "epoch": 0.8789105456188218, "grad_norm": 1.8209118843078613, "learning_rate": 0.00018034328824355066, "loss": 0.6365139007568359, "step": 147860 }, { "epoch": 0.8789699876954902, "grad_norm": 1.5365382432937622, "learning_rate": 0.00018033940512726608, "loss": 0.6296128273010254, "step": 147870 }, { "epoch": 0.8790294297721585, "grad_norm": 1.4590692520141602, "learning_rate": 0.00018033552167450077, "loss": 0.6414812088012696, "step": 147880 }, { "epoch": 0.8790888718488269, "grad_norm": 1.6513705253601074, "learning_rate": 0.00018033163788527332, "loss": 0.6918416976928711, "step": 147890 }, { "epoch": 0.8791483139254953, "grad_norm": 1.706820011138916, "learning_rate": 0.00018032775375960227, "loss": 0.633668327331543, "step": 147900 }, { "epoch": 0.8792077560021637, "grad_norm": 1.4602737426757812, "learning_rate": 0.00018032386929750627, "loss": 0.5873737335205078, "step": 147910 }, { "epoch": 0.8792671980788321, "grad_norm": 1.9989750385284424, "learning_rate": 0.0001803199844990038, "loss": 0.6269173622131348, "step": 147920 }, { "epoch": 0.8793266401555004, "grad_norm": 1.5137156248092651, "learning_rate": 0.0001803160993641136, "loss": 0.6214890956878663, "step": 147930 }, { "epoch": 0.8793860822321689, "grad_norm": 2.078857660293579, "learning_rate": 0.00018031221389285408, "loss": 0.6846571922302246, "step": 147940 }, { "epoch": 0.8794455243088373, "grad_norm": 1.814484715461731, "learning_rate": 0.0001803083280852439, "loss": 0.6187413215637207, "step": 147950 }, { "epoch": 0.8795049663855057, "grad_norm": 1.7178058624267578, "learning_rate": 0.00018030444194130172, "loss": 0.6803339004516602, "step": 147960 }, { "epoch": 0.879564408462174, "grad_norm": 1.6472984552383423, "learning_rate": 0.000180300555461046, "loss": 0.609197998046875, "step": 147970 }, { "epoch": 0.8796238505388424, "grad_norm": 2.029369831085205, "learning_rate": 0.00018029666864449544, "loss": 0.6171045303344727, "step": 147980 }, { "epoch": 0.8796832926155108, "grad_norm": 1.403031587600708, "learning_rate": 0.00018029278149166858, "loss": 0.662755298614502, "step": 147990 }, { "epoch": 0.8797427346921792, "grad_norm": 1.5057990550994873, "learning_rate": 0.00018028889400258403, "loss": 0.6852468490600586, "step": 148000 }, { "epoch": 0.8798021767688476, "grad_norm": 1.4780735969543457, "learning_rate": 0.00018028500617726034, "loss": 0.6340672969818115, "step": 148010 }, { "epoch": 0.879861618845516, "grad_norm": 1.810975432395935, "learning_rate": 0.00018028111801571622, "loss": 0.6717475891113281, "step": 148020 }, { "epoch": 0.8799210609221844, "grad_norm": 1.6027804613113403, "learning_rate": 0.00018027722951797012, "loss": 0.6735102653503418, "step": 148030 }, { "epoch": 0.8799805029988528, "grad_norm": 1.7627315521240234, "learning_rate": 0.00018027334068404077, "loss": 0.6516412258148193, "step": 148040 }, { "epoch": 0.8800399450755212, "grad_norm": 1.6416913270950317, "learning_rate": 0.00018026945151394675, "loss": 0.6691810607910156, "step": 148050 }, { "epoch": 0.8800993871521895, "grad_norm": 1.8873906135559082, "learning_rate": 0.00018026556200770658, "loss": 0.6694831848144531, "step": 148060 }, { "epoch": 0.8801588292288579, "grad_norm": 1.9679969549179077, "learning_rate": 0.00018026167216533896, "loss": 0.7179198741912842, "step": 148070 }, { "epoch": 0.8802182713055263, "grad_norm": 1.5246044397354126, "learning_rate": 0.00018025778198686246, "loss": 0.646002721786499, "step": 148080 }, { "epoch": 0.8802777133821947, "grad_norm": 1.5971765518188477, "learning_rate": 0.00018025389147229568, "loss": 0.69178786277771, "step": 148090 }, { "epoch": 0.8803371554588632, "grad_norm": 1.7593183517456055, "learning_rate": 0.00018025000062165726, "loss": 0.6904574394226074, "step": 148100 }, { "epoch": 0.8803965975355315, "grad_norm": 1.3920220136642456, "learning_rate": 0.00018024610943496576, "loss": 0.658218240737915, "step": 148110 }, { "epoch": 0.8804560396121999, "grad_norm": 1.4767701625823975, "learning_rate": 0.00018024221791223982, "loss": 0.6224551200866699, "step": 148120 }, { "epoch": 0.8805154816888683, "grad_norm": 1.4881250858306885, "learning_rate": 0.00018023832605349813, "loss": 0.6480618476867676, "step": 148130 }, { "epoch": 0.8805749237655367, "grad_norm": 1.2785849571228027, "learning_rate": 0.00018023443385875923, "loss": 0.6076675415039062, "step": 148140 }, { "epoch": 0.8806343658422051, "grad_norm": 1.6341129541397095, "learning_rate": 0.0001802305413280417, "loss": 0.6866085052490234, "step": 148150 }, { "epoch": 0.8806938079188734, "grad_norm": 1.6679598093032837, "learning_rate": 0.00018022664846136427, "loss": 0.6276944160461426, "step": 148160 }, { "epoch": 0.8807532499955418, "grad_norm": 1.8198248147964478, "learning_rate": 0.00018022275525874545, "loss": 0.6174046993255615, "step": 148170 }, { "epoch": 0.8808126920722102, "grad_norm": 1.8590677976608276, "learning_rate": 0.00018021886172020396, "loss": 0.6675004959106445, "step": 148180 }, { "epoch": 0.8808721341488787, "grad_norm": 1.6391512155532837, "learning_rate": 0.00018021496784575834, "loss": 0.6595131874084472, "step": 148190 }, { "epoch": 0.880931576225547, "grad_norm": 1.4413175582885742, "learning_rate": 0.00018021107363542732, "loss": 0.6235510826110839, "step": 148200 }, { "epoch": 0.8809910183022154, "grad_norm": 1.4562422037124634, "learning_rate": 0.00018020717908922939, "loss": 0.6040661811828614, "step": 148210 }, { "epoch": 0.8810504603788838, "grad_norm": 1.5051349401474, "learning_rate": 0.0001802032842071833, "loss": 0.6970216751098632, "step": 148220 }, { "epoch": 0.8811099024555522, "grad_norm": 1.4107778072357178, "learning_rate": 0.00018019938898930767, "loss": 0.6329676151275635, "step": 148230 }, { "epoch": 0.8811693445322206, "grad_norm": 1.5960628986358643, "learning_rate": 0.00018019549343562108, "loss": 0.6630317211151123, "step": 148240 }, { "epoch": 0.8812287866088889, "grad_norm": 2.0407559871673584, "learning_rate": 0.0001801915975461422, "loss": 0.6311050415039062, "step": 148250 }, { "epoch": 0.8812882286855573, "grad_norm": 1.7664082050323486, "learning_rate": 0.00018018770132088963, "loss": 0.7183359146118165, "step": 148260 }, { "epoch": 0.8813476707622258, "grad_norm": 1.7499730587005615, "learning_rate": 0.00018018380475988204, "loss": 0.6119650840759278, "step": 148270 }, { "epoch": 0.8814071128388942, "grad_norm": 1.6637648344039917, "learning_rate": 0.00018017990786313808, "loss": 0.6333750247955322, "step": 148280 }, { "epoch": 0.8814665549155626, "grad_norm": 1.524715781211853, "learning_rate": 0.00018017601063067637, "loss": 0.6903565406799317, "step": 148290 }, { "epoch": 0.8815259969922309, "grad_norm": 1.7557957172393799, "learning_rate": 0.00018017211306251555, "loss": 0.6726624011993408, "step": 148300 }, { "epoch": 0.8815854390688993, "grad_norm": 1.6581512689590454, "learning_rate": 0.0001801682151586743, "loss": 0.7142253398895264, "step": 148310 }, { "epoch": 0.8816448811455677, "grad_norm": 1.459665298461914, "learning_rate": 0.0001801643169191712, "loss": 0.6933238983154297, "step": 148320 }, { "epoch": 0.8817043232222361, "grad_norm": 1.8005540370941162, "learning_rate": 0.00018016041834402499, "loss": 0.7375575065612793, "step": 148330 }, { "epoch": 0.8817637652989044, "grad_norm": 2.33579421043396, "learning_rate": 0.00018015651943325422, "loss": 0.6730666160583496, "step": 148340 }, { "epoch": 0.8818232073755728, "grad_norm": 1.4365547895431519, "learning_rate": 0.00018015262018687762, "loss": 0.6685959339141846, "step": 148350 }, { "epoch": 0.8818826494522413, "grad_norm": 1.7548203468322754, "learning_rate": 0.00018014872060491378, "loss": 0.6289718627929688, "step": 148360 }, { "epoch": 0.8819420915289097, "grad_norm": 1.5404399633407593, "learning_rate": 0.00018014482068738142, "loss": 0.6141351222991943, "step": 148370 }, { "epoch": 0.8820015336055781, "grad_norm": 1.6799665689468384, "learning_rate": 0.00018014092043429914, "loss": 0.6655412197113038, "step": 148380 }, { "epoch": 0.8820609756822464, "grad_norm": 1.5635132789611816, "learning_rate": 0.00018013701984568564, "loss": 0.6246545314788818, "step": 148390 }, { "epoch": 0.8821204177589148, "grad_norm": 1.3478552103042603, "learning_rate": 0.00018013311892155952, "loss": 0.6412197113037109, "step": 148400 }, { "epoch": 0.8821798598355832, "grad_norm": 1.4923079013824463, "learning_rate": 0.0001801292176619395, "loss": 0.6286362648010254, "step": 148410 }, { "epoch": 0.8822393019122516, "grad_norm": 2.1246633529663086, "learning_rate": 0.00018012531606684425, "loss": 0.6277644634246826, "step": 148420 }, { "epoch": 0.8822987439889199, "grad_norm": 1.2634249925613403, "learning_rate": 0.0001801214141362924, "loss": 0.6283688545227051, "step": 148430 }, { "epoch": 0.8823581860655884, "grad_norm": 1.5995721817016602, "learning_rate": 0.00018011751187030256, "loss": 0.6220310211181641, "step": 148440 }, { "epoch": 0.8824176281422568, "grad_norm": 1.7074079513549805, "learning_rate": 0.0001801136092688935, "loss": 0.6382304191589355, "step": 148450 }, { "epoch": 0.8824770702189252, "grad_norm": 1.7870917320251465, "learning_rate": 0.00018010970633208385, "loss": 0.6320053100585937, "step": 148460 }, { "epoch": 0.8825365122955936, "grad_norm": 2.1251914501190186, "learning_rate": 0.00018010580305989228, "loss": 0.7224474430084229, "step": 148470 }, { "epoch": 0.8825959543722619, "grad_norm": 1.822763442993164, "learning_rate": 0.00018010189945233743, "loss": 0.6551345348358154, "step": 148480 }, { "epoch": 0.8826553964489303, "grad_norm": 1.1458021402359009, "learning_rate": 0.00018009799550943803, "loss": 0.5985439777374267, "step": 148490 }, { "epoch": 0.8827148385255987, "grad_norm": 1.7513210773468018, "learning_rate": 0.0001800940912312127, "loss": 0.6437232971191407, "step": 148500 }, { "epoch": 0.8827742806022671, "grad_norm": 1.5958908796310425, "learning_rate": 0.00018009018661768018, "loss": 0.7182272911071778, "step": 148510 }, { "epoch": 0.8828337226789356, "grad_norm": 1.4639806747436523, "learning_rate": 0.0001800862816688591, "loss": 0.6590409278869629, "step": 148520 }, { "epoch": 0.8828931647556039, "grad_norm": 1.6518136262893677, "learning_rate": 0.00018008237638476813, "loss": 0.6410433292388916, "step": 148530 }, { "epoch": 0.8829526068322723, "grad_norm": 1.6302590370178223, "learning_rate": 0.00018007847076542598, "loss": 0.6538320541381836, "step": 148540 }, { "epoch": 0.8830120489089407, "grad_norm": 1.9443767070770264, "learning_rate": 0.00018007456481085134, "loss": 0.7035457611083984, "step": 148550 }, { "epoch": 0.8830714909856091, "grad_norm": 1.574057936668396, "learning_rate": 0.0001800706585210629, "loss": 0.6263667106628418, "step": 148560 }, { "epoch": 0.8831309330622774, "grad_norm": 1.467381477355957, "learning_rate": 0.0001800667518960793, "loss": 0.6993083000183106, "step": 148570 }, { "epoch": 0.8831903751389458, "grad_norm": 1.358039379119873, "learning_rate": 0.00018006284493591928, "loss": 0.6547554969787598, "step": 148580 }, { "epoch": 0.8832498172156142, "grad_norm": 1.2822774648666382, "learning_rate": 0.0001800589376406015, "loss": 0.6386611461639404, "step": 148590 }, { "epoch": 0.8833092592922827, "grad_norm": 1.7162132263183594, "learning_rate": 0.00018005503001014466, "loss": 0.6513526439666748, "step": 148600 }, { "epoch": 0.8833687013689511, "grad_norm": 1.8170833587646484, "learning_rate": 0.00018005112204456743, "loss": 0.6627068519592285, "step": 148610 }, { "epoch": 0.8834281434456194, "grad_norm": 2.3608155250549316, "learning_rate": 0.00018004721374388852, "loss": 0.6403194427490234, "step": 148620 }, { "epoch": 0.8834875855222878, "grad_norm": 1.8530848026275635, "learning_rate": 0.00018004330510812668, "loss": 0.6961091995239258, "step": 148630 }, { "epoch": 0.8835470275989562, "grad_norm": 1.300436019897461, "learning_rate": 0.00018003939613730054, "loss": 0.608799934387207, "step": 148640 }, { "epoch": 0.8836064696756246, "grad_norm": 1.4909894466400146, "learning_rate": 0.0001800354868314288, "loss": 0.7206879615783691, "step": 148650 }, { "epoch": 0.883665911752293, "grad_norm": 1.5548356771469116, "learning_rate": 0.00018003157719053016, "loss": 0.6182454586029053, "step": 148660 }, { "epoch": 0.8837253538289613, "grad_norm": 1.7221065759658813, "learning_rate": 0.0001800276672146234, "loss": 0.5647119522094727, "step": 148670 }, { "epoch": 0.8837847959056297, "grad_norm": 1.4910839796066284, "learning_rate": 0.00018002375690372713, "loss": 0.7081813335418701, "step": 148680 }, { "epoch": 0.8838442379822982, "grad_norm": 1.9888250827789307, "learning_rate": 0.00018001984625786008, "loss": 0.673496675491333, "step": 148690 }, { "epoch": 0.8839036800589666, "grad_norm": 1.4516441822052002, "learning_rate": 0.00018001593527704098, "loss": 0.6628455638885498, "step": 148700 }, { "epoch": 0.8839631221356349, "grad_norm": 2.0750772953033447, "learning_rate": 0.00018001202396128856, "loss": 0.6093379974365234, "step": 148710 }, { "epoch": 0.8840225642123033, "grad_norm": 2.552621841430664, "learning_rate": 0.00018000811231062144, "loss": 0.6371734619140625, "step": 148720 }, { "epoch": 0.8840820062889717, "grad_norm": 2.1920700073242188, "learning_rate": 0.00018000420032505843, "loss": 0.6780601501464844, "step": 148730 }, { "epoch": 0.8841414483656401, "grad_norm": 1.5009050369262695, "learning_rate": 0.00018000028800461819, "loss": 0.6415701866149902, "step": 148740 }, { "epoch": 0.8842008904423085, "grad_norm": 1.7863680124282837, "learning_rate": 0.00017999637534931945, "loss": 0.589899730682373, "step": 148750 }, { "epoch": 0.8842603325189768, "grad_norm": 1.6092798709869385, "learning_rate": 0.00017999246235918094, "loss": 0.6091831684112549, "step": 148760 }, { "epoch": 0.8843197745956453, "grad_norm": 1.8736422061920166, "learning_rate": 0.00017998854903422134, "loss": 0.6359821796417237, "step": 148770 }, { "epoch": 0.8843792166723137, "grad_norm": 1.645787239074707, "learning_rate": 0.00017998463537445937, "loss": 0.6570725440979004, "step": 148780 }, { "epoch": 0.8844386587489821, "grad_norm": 1.244265079498291, "learning_rate": 0.00017998072137991383, "loss": 0.6000986576080323, "step": 148790 }, { "epoch": 0.8844981008256504, "grad_norm": 1.6900709867477417, "learning_rate": 0.00017997680705060336, "loss": 0.6540081024169921, "step": 148800 }, { "epoch": 0.8845575429023188, "grad_norm": 1.8503761291503906, "learning_rate": 0.00017997289238654672, "loss": 0.7983271598815918, "step": 148810 }, { "epoch": 0.8846169849789872, "grad_norm": 1.3753236532211304, "learning_rate": 0.00017996897738776265, "loss": 0.631880807876587, "step": 148820 }, { "epoch": 0.8846764270556556, "grad_norm": 1.4502253532409668, "learning_rate": 0.00017996506205426982, "loss": 0.667803955078125, "step": 148830 }, { "epoch": 0.884735869132324, "grad_norm": 1.6100027561187744, "learning_rate": 0.00017996114638608703, "loss": 0.706180477142334, "step": 148840 }, { "epoch": 0.8847953112089924, "grad_norm": 1.4102444648742676, "learning_rate": 0.00017995723038323298, "loss": 0.6824797630310059, "step": 148850 }, { "epoch": 0.8848547532856608, "grad_norm": 1.555720567703247, "learning_rate": 0.00017995331404572636, "loss": 0.6847973346710206, "step": 148860 }, { "epoch": 0.8849141953623292, "grad_norm": 2.2798616886138916, "learning_rate": 0.000179949397373586, "loss": 0.6137511253356933, "step": 148870 }, { "epoch": 0.8849736374389976, "grad_norm": 1.5806787014007568, "learning_rate": 0.00017994548036683053, "loss": 0.5922553539276123, "step": 148880 }, { "epoch": 0.885033079515666, "grad_norm": 2.1523547172546387, "learning_rate": 0.00017994156302547878, "loss": 0.6509166717529297, "step": 148890 }, { "epoch": 0.8850925215923343, "grad_norm": 1.6332359313964844, "learning_rate": 0.00017993764534954943, "loss": 0.6225162506103515, "step": 148900 }, { "epoch": 0.8851519636690027, "grad_norm": 1.2372931241989136, "learning_rate": 0.00017993372733906125, "loss": 0.6415366172790528, "step": 148910 }, { "epoch": 0.8852114057456711, "grad_norm": 1.6419512033462524, "learning_rate": 0.00017992980899403298, "loss": 0.6529489517211914, "step": 148920 }, { "epoch": 0.8852708478223396, "grad_norm": 1.8770298957824707, "learning_rate": 0.00017992589031448332, "loss": 0.6675568580627441, "step": 148930 }, { "epoch": 0.8853302898990079, "grad_norm": 1.7721636295318604, "learning_rate": 0.0001799219713004311, "loss": 0.6508255958557129, "step": 148940 }, { "epoch": 0.8853897319756763, "grad_norm": 1.414685606956482, "learning_rate": 0.000179918051951895, "loss": 0.6799958705902099, "step": 148950 }, { "epoch": 0.8854491740523447, "grad_norm": 1.9210892915725708, "learning_rate": 0.0001799141322688938, "loss": 0.6721712112426758, "step": 148960 }, { "epoch": 0.8855086161290131, "grad_norm": 1.7978616952896118, "learning_rate": 0.0001799102122514462, "loss": 0.6727882862091065, "step": 148970 }, { "epoch": 0.8855680582056815, "grad_norm": 1.6431715488433838, "learning_rate": 0.00017990629189957105, "loss": 0.628132963180542, "step": 148980 }, { "epoch": 0.8856275002823498, "grad_norm": 1.541581153869629, "learning_rate": 0.000179902371213287, "loss": 0.6437122821807861, "step": 148990 }, { "epoch": 0.8856869423590182, "grad_norm": 1.8030883073806763, "learning_rate": 0.00017989845019261288, "loss": 0.6306240081787109, "step": 149000 }, { "epoch": 0.8857463844356867, "grad_norm": 1.726892352104187, "learning_rate": 0.0001798945288375674, "loss": 0.6511331558227539, "step": 149010 }, { "epoch": 0.8858058265123551, "grad_norm": 2.211921453475952, "learning_rate": 0.00017989060714816935, "loss": 0.655848217010498, "step": 149020 }, { "epoch": 0.8858652685890235, "grad_norm": 1.6638964414596558, "learning_rate": 0.0001798866851244374, "loss": 0.6397546768188477, "step": 149030 }, { "epoch": 0.8859247106656918, "grad_norm": 1.4625663757324219, "learning_rate": 0.0001798827627663905, "loss": 0.6113448143005371, "step": 149040 }, { "epoch": 0.8859841527423602, "grad_norm": 1.8138879537582397, "learning_rate": 0.00017987884007404726, "loss": 0.6425710678100586, "step": 149050 }, { "epoch": 0.8860435948190286, "grad_norm": 1.6734575033187866, "learning_rate": 0.00017987491704742647, "loss": 0.6516216278076172, "step": 149060 }, { "epoch": 0.886103036895697, "grad_norm": 1.736729383468628, "learning_rate": 0.00017987099368654692, "loss": 0.6950938701629639, "step": 149070 }, { "epoch": 0.8861624789723653, "grad_norm": 1.9293872117996216, "learning_rate": 0.00017986706999142737, "loss": 0.7175424098968506, "step": 149080 }, { "epoch": 0.8862219210490337, "grad_norm": 2.225937843322754, "learning_rate": 0.0001798631459620866, "loss": 0.6288230895996094, "step": 149090 }, { "epoch": 0.8862813631257022, "grad_norm": 1.582041621208191, "learning_rate": 0.00017985922159854335, "loss": 0.6966487884521484, "step": 149100 }, { "epoch": 0.8863408052023706, "grad_norm": 1.6780750751495361, "learning_rate": 0.00017985529690081644, "loss": 0.6643537044525146, "step": 149110 }, { "epoch": 0.886400247279039, "grad_norm": 1.8210176229476929, "learning_rate": 0.0001798513718689246, "loss": 0.6614949226379394, "step": 149120 }, { "epoch": 0.8864596893557073, "grad_norm": 1.7980341911315918, "learning_rate": 0.00017984744650288663, "loss": 0.6948718547821044, "step": 149130 }, { "epoch": 0.8865191314323757, "grad_norm": 1.8158777952194214, "learning_rate": 0.00017984352080272132, "loss": 0.6685075759887695, "step": 149140 }, { "epoch": 0.8865785735090441, "grad_norm": 1.7614400386810303, "learning_rate": 0.0001798395947684474, "loss": 0.6444768905639648, "step": 149150 }, { "epoch": 0.8866380155857125, "grad_norm": 1.6307380199432373, "learning_rate": 0.0001798356684000837, "loss": 0.6503550052642822, "step": 149160 }, { "epoch": 0.8866974576623808, "grad_norm": 1.607483148574829, "learning_rate": 0.00017983174169764897, "loss": 0.6843660354614258, "step": 149170 }, { "epoch": 0.8867568997390493, "grad_norm": 1.533503532409668, "learning_rate": 0.00017982781466116204, "loss": 0.6615970611572266, "step": 149180 }, { "epoch": 0.8868163418157177, "grad_norm": 1.5121463537216187, "learning_rate": 0.00017982388729064164, "loss": 0.6168664932250977, "step": 149190 }, { "epoch": 0.8868757838923861, "grad_norm": 2.031853199005127, "learning_rate": 0.00017981995958610657, "loss": 0.5530342578887939, "step": 149200 }, { "epoch": 0.8869352259690545, "grad_norm": 1.5312206745147705, "learning_rate": 0.00017981603154757568, "loss": 0.6678025722503662, "step": 149210 }, { "epoch": 0.8869946680457228, "grad_norm": 1.8891688585281372, "learning_rate": 0.00017981210317506764, "loss": 0.6772946357727051, "step": 149220 }, { "epoch": 0.8870541101223912, "grad_norm": 1.6692585945129395, "learning_rate": 0.00017980817446860137, "loss": 0.6689918994903564, "step": 149230 }, { "epoch": 0.8871135521990596, "grad_norm": 1.5267800092697144, "learning_rate": 0.0001798042454281956, "loss": 0.6901618003845215, "step": 149240 }, { "epoch": 0.887172994275728, "grad_norm": 1.7019542455673218, "learning_rate": 0.00017980031605386914, "loss": 0.6598389625549317, "step": 149250 }, { "epoch": 0.8872324363523965, "grad_norm": 1.739939570426941, "learning_rate": 0.00017979638634564073, "loss": 0.6383354187011718, "step": 149260 }, { "epoch": 0.8872918784290648, "grad_norm": 1.5286566019058228, "learning_rate": 0.00017979245630352927, "loss": 0.6521745204925538, "step": 149270 }, { "epoch": 0.8873513205057332, "grad_norm": 1.2782756090164185, "learning_rate": 0.0001797885259275535, "loss": 0.7009990692138672, "step": 149280 }, { "epoch": 0.8874107625824016, "grad_norm": 1.4523295164108276, "learning_rate": 0.0001797845952177322, "loss": 0.6339374542236328, "step": 149290 }, { "epoch": 0.88747020465907, "grad_norm": 2.0314199924468994, "learning_rate": 0.0001797806641740842, "loss": 0.718003511428833, "step": 149300 }, { "epoch": 0.8875296467357383, "grad_norm": 1.4573109149932861, "learning_rate": 0.0001797767327966283, "loss": 0.6675372123718262, "step": 149310 }, { "epoch": 0.8875890888124067, "grad_norm": 1.8596522808074951, "learning_rate": 0.00017977280108538336, "loss": 0.6192123889923096, "step": 149320 }, { "epoch": 0.8876485308890751, "grad_norm": 1.448304295539856, "learning_rate": 0.00017976886904036811, "loss": 0.6755659103393554, "step": 149330 }, { "epoch": 0.8877079729657436, "grad_norm": 1.565018892288208, "learning_rate": 0.00017976493666160143, "loss": 0.7050125598907471, "step": 149340 }, { "epoch": 0.887767415042412, "grad_norm": 1.4030030965805054, "learning_rate": 0.00017976100394910205, "loss": 0.6552132129669189, "step": 149350 }, { "epoch": 0.8878268571190803, "grad_norm": 1.8064504861831665, "learning_rate": 0.00017975707090288882, "loss": 0.6750728130340576, "step": 149360 }, { "epoch": 0.8878862991957487, "grad_norm": 1.811579942703247, "learning_rate": 0.00017975313752298058, "loss": 0.6227271080017089, "step": 149370 }, { "epoch": 0.8879457412724171, "grad_norm": 1.806550145149231, "learning_rate": 0.00017974920380939613, "loss": 0.6457484245300293, "step": 149380 }, { "epoch": 0.8880051833490855, "grad_norm": 1.652429223060608, "learning_rate": 0.0001797452697621543, "loss": 0.7010434150695801, "step": 149390 }, { "epoch": 0.8880646254257539, "grad_norm": 1.6304072141647339, "learning_rate": 0.00017974133538127386, "loss": 0.6313910961151123, "step": 149400 }, { "epoch": 0.8881240675024222, "grad_norm": 1.7596397399902344, "learning_rate": 0.00017973740066677367, "loss": 0.6778824806213379, "step": 149410 }, { "epoch": 0.8881835095790906, "grad_norm": 1.4480232000350952, "learning_rate": 0.00017973346561867256, "loss": 0.6307137489318848, "step": 149420 }, { "epoch": 0.8882429516557591, "grad_norm": 1.7891751527786255, "learning_rate": 0.0001797295302369893, "loss": 0.6537883758544922, "step": 149430 }, { "epoch": 0.8883023937324275, "grad_norm": 1.4582754373550415, "learning_rate": 0.0001797255945217428, "loss": 0.6911883354187012, "step": 149440 }, { "epoch": 0.8883618358090958, "grad_norm": 1.5453685522079468, "learning_rate": 0.00017972165847295182, "loss": 0.6647927284240722, "step": 149450 }, { "epoch": 0.8884212778857642, "grad_norm": 1.9026179313659668, "learning_rate": 0.00017971772209063522, "loss": 0.6774191856384277, "step": 149460 }, { "epoch": 0.8884807199624326, "grad_norm": 1.6102505922317505, "learning_rate": 0.00017971378537481183, "loss": 0.7110806941986084, "step": 149470 }, { "epoch": 0.888540162039101, "grad_norm": 1.5283420085906982, "learning_rate": 0.00017970984832550046, "loss": 0.6744344234466553, "step": 149480 }, { "epoch": 0.8885996041157694, "grad_norm": 1.6085572242736816, "learning_rate": 0.00017970591094271994, "loss": 0.5979486465454101, "step": 149490 }, { "epoch": 0.8886590461924377, "grad_norm": 1.7792335748672485, "learning_rate": 0.00017970197322648916, "loss": 0.7287714958190918, "step": 149500 }, { "epoch": 0.8887184882691062, "grad_norm": 1.6255826950073242, "learning_rate": 0.00017969803517682686, "loss": 0.6762622833251953, "step": 149510 }, { "epoch": 0.8887779303457746, "grad_norm": 1.3914214372634888, "learning_rate": 0.000179694096793752, "loss": 0.6355211734771729, "step": 149520 }, { "epoch": 0.888837372422443, "grad_norm": 1.5144102573394775, "learning_rate": 0.00017969015807728334, "loss": 0.7223231315612793, "step": 149530 }, { "epoch": 0.8888968144991113, "grad_norm": 1.7071202993392944, "learning_rate": 0.0001796862190274397, "loss": 0.6692628860473633, "step": 149540 }, { "epoch": 0.8889562565757797, "grad_norm": 1.5506685972213745, "learning_rate": 0.00017968227964424005, "loss": 0.6399158000946045, "step": 149550 }, { "epoch": 0.8890156986524481, "grad_norm": 1.6661462783813477, "learning_rate": 0.00017967833992770307, "loss": 0.6719175815582276, "step": 149560 }, { "epoch": 0.8890751407291165, "grad_norm": 1.5548452138900757, "learning_rate": 0.0001796743998778477, "loss": 0.6805333614349365, "step": 149570 }, { "epoch": 0.889134582805785, "grad_norm": 1.5869710445404053, "learning_rate": 0.00017967045949469278, "loss": 0.6926319122314453, "step": 149580 }, { "epoch": 0.8891940248824532, "grad_norm": 1.7007495164871216, "learning_rate": 0.00017966651877825713, "loss": 0.6634454727172852, "step": 149590 }, { "epoch": 0.8892534669591217, "grad_norm": 1.4924936294555664, "learning_rate": 0.00017966257772855966, "loss": 0.7046329498291015, "step": 149600 }, { "epoch": 0.8893129090357901, "grad_norm": 1.3354222774505615, "learning_rate": 0.00017965863634561915, "loss": 0.5885660171508789, "step": 149610 }, { "epoch": 0.8893723511124585, "grad_norm": 1.4117958545684814, "learning_rate": 0.00017965469462945447, "loss": 0.6523199081420898, "step": 149620 }, { "epoch": 0.8894317931891269, "grad_norm": 1.9629541635513306, "learning_rate": 0.00017965075258008454, "loss": 0.6597516059875488, "step": 149630 }, { "epoch": 0.8894912352657952, "grad_norm": 1.4608924388885498, "learning_rate": 0.00017964681019752815, "loss": 0.6878172397613526, "step": 149640 }, { "epoch": 0.8895506773424636, "grad_norm": 1.9712998867034912, "learning_rate": 0.0001796428674818042, "loss": 0.6606235504150391, "step": 149650 }, { "epoch": 0.889610119419132, "grad_norm": 1.8361074924468994, "learning_rate": 0.00017963892443293152, "loss": 0.6397542953491211, "step": 149660 }, { "epoch": 0.8896695614958005, "grad_norm": 1.4691376686096191, "learning_rate": 0.00017963498105092897, "loss": 0.6286890983581543, "step": 149670 }, { "epoch": 0.8897290035724688, "grad_norm": 1.47322678565979, "learning_rate": 0.00017963103733581546, "loss": 0.645048999786377, "step": 149680 }, { "epoch": 0.8897884456491372, "grad_norm": 1.6532214879989624, "learning_rate": 0.00017962709328760978, "loss": 0.6287936210632324, "step": 149690 }, { "epoch": 0.8898478877258056, "grad_norm": 1.7250475883483887, "learning_rate": 0.00017962314890633088, "loss": 0.6696280479431153, "step": 149700 }, { "epoch": 0.889907329802474, "grad_norm": 1.7395817041397095, "learning_rate": 0.00017961920419199757, "loss": 0.6563028335571289, "step": 149710 }, { "epoch": 0.8899667718791424, "grad_norm": 1.5928542613983154, "learning_rate": 0.00017961525914462876, "loss": 0.6837942123413085, "step": 149720 }, { "epoch": 0.8900262139558107, "grad_norm": 1.9423937797546387, "learning_rate": 0.00017961131376424325, "loss": 0.6682456016540528, "step": 149730 }, { "epoch": 0.8900856560324791, "grad_norm": 1.7948464155197144, "learning_rate": 0.00017960736805086, "loss": 0.6568106651306153, "step": 149740 }, { "epoch": 0.8901450981091475, "grad_norm": 1.5121766328811646, "learning_rate": 0.00017960342200449786, "loss": 0.6635803699493408, "step": 149750 }, { "epoch": 0.890204540185816, "grad_norm": 1.8940088748931885, "learning_rate": 0.00017959947562517568, "loss": 0.6937570571899414, "step": 149760 }, { "epoch": 0.8902639822624844, "grad_norm": 1.5419996976852417, "learning_rate": 0.00017959552891291233, "loss": 0.660066032409668, "step": 149770 }, { "epoch": 0.8903234243391527, "grad_norm": 1.9228754043579102, "learning_rate": 0.00017959158186772677, "loss": 0.6694670200347901, "step": 149780 }, { "epoch": 0.8903828664158211, "grad_norm": 1.7430579662322998, "learning_rate": 0.00017958763448963776, "loss": 0.6458512306213379, "step": 149790 }, { "epoch": 0.8904423084924895, "grad_norm": 1.8215839862823486, "learning_rate": 0.00017958368677866427, "loss": 0.6661408901214599, "step": 149800 }, { "epoch": 0.8905017505691579, "grad_norm": 1.443885087966919, "learning_rate": 0.00017957973873482518, "loss": 0.6784239292144776, "step": 149810 }, { "epoch": 0.8905611926458262, "grad_norm": 1.356515645980835, "learning_rate": 0.00017957579035813936, "loss": 0.6726195335388183, "step": 149820 }, { "epoch": 0.8906206347224946, "grad_norm": 1.3160157203674316, "learning_rate": 0.00017957184164862572, "loss": 0.6345341682434082, "step": 149830 }, { "epoch": 0.8906800767991631, "grad_norm": 1.4652739763259888, "learning_rate": 0.00017956789260630308, "loss": 0.6122000694274903, "step": 149840 }, { "epoch": 0.8907395188758315, "grad_norm": 1.4102507829666138, "learning_rate": 0.00017956394323119038, "loss": 0.7077874183654785, "step": 149850 }, { "epoch": 0.8907989609524999, "grad_norm": 2.0389740467071533, "learning_rate": 0.00017955999352330652, "loss": 0.5879474639892578, "step": 149860 }, { "epoch": 0.8908584030291682, "grad_norm": 1.4210784435272217, "learning_rate": 0.00017955604348267039, "loss": 0.6376371383666992, "step": 149870 }, { "epoch": 0.8909178451058366, "grad_norm": 1.7756707668304443, "learning_rate": 0.0001795520931093009, "loss": 0.6290136337280273, "step": 149880 }, { "epoch": 0.890977287182505, "grad_norm": 1.3489923477172852, "learning_rate": 0.00017954814240321687, "loss": 0.702340030670166, "step": 149890 }, { "epoch": 0.8910367292591734, "grad_norm": 1.687568187713623, "learning_rate": 0.0001795441913644373, "loss": 0.6606422424316406, "step": 149900 }, { "epoch": 0.8910961713358417, "grad_norm": 1.5319321155548096, "learning_rate": 0.00017954023999298103, "loss": 0.7097502231597901, "step": 149910 }, { "epoch": 0.8911556134125102, "grad_norm": 1.5579307079315186, "learning_rate": 0.00017953628828886698, "loss": 0.6684148788452149, "step": 149920 }, { "epoch": 0.8912150554891786, "grad_norm": 1.491486668586731, "learning_rate": 0.00017953233625211406, "loss": 0.6176539421081543, "step": 149930 }, { "epoch": 0.891274497565847, "grad_norm": 1.6105320453643799, "learning_rate": 0.00017952838388274114, "loss": 0.6462141513824463, "step": 149940 }, { "epoch": 0.8913339396425154, "grad_norm": 1.4216699600219727, "learning_rate": 0.00017952443118076717, "loss": 0.695673656463623, "step": 149950 }, { "epoch": 0.8913933817191837, "grad_norm": 1.3567259311676025, "learning_rate": 0.00017952047814621104, "loss": 0.5677448749542237, "step": 149960 }, { "epoch": 0.8914528237958521, "grad_norm": 2.2654199600219727, "learning_rate": 0.0001795165247790917, "loss": 0.5966793060302734, "step": 149970 }, { "epoch": 0.8915122658725205, "grad_norm": 1.6677848100662231, "learning_rate": 0.00017951257107942794, "loss": 0.7197662830352783, "step": 149980 }, { "epoch": 0.8915717079491889, "grad_norm": 1.8404957056045532, "learning_rate": 0.00017950861704723884, "loss": 0.6171542167663574, "step": 149990 }, { "epoch": 0.8916311500258574, "grad_norm": 1.43938410282135, "learning_rate": 0.00017950466268254318, "loss": 0.6876942634582519, "step": 150000 }, { "epoch": 0.8916905921025257, "grad_norm": 1.549060344696045, "learning_rate": 0.00017950070798535995, "loss": 0.6026205539703369, "step": 150010 }, { "epoch": 0.8917500341791941, "grad_norm": 1.8076063394546509, "learning_rate": 0.00017949675295570805, "loss": 0.6170270919799805, "step": 150020 }, { "epoch": 0.8918094762558625, "grad_norm": 1.7340518236160278, "learning_rate": 0.0001794927975936064, "loss": 0.635988712310791, "step": 150030 }, { "epoch": 0.8918689183325309, "grad_norm": 1.889829158782959, "learning_rate": 0.0001794888418990739, "loss": 0.6977147102355957, "step": 150040 }, { "epoch": 0.8919283604091992, "grad_norm": 1.600407600402832, "learning_rate": 0.00017948488587212947, "loss": 0.5656648635864258, "step": 150050 }, { "epoch": 0.8919878024858676, "grad_norm": 2.1017866134643555, "learning_rate": 0.0001794809295127921, "loss": 0.6200255393981934, "step": 150060 }, { "epoch": 0.892047244562536, "grad_norm": 1.561493992805481, "learning_rate": 0.00017947697282108064, "loss": 0.6229795932769775, "step": 150070 }, { "epoch": 0.8921066866392044, "grad_norm": 1.9793850183486938, "learning_rate": 0.00017947301579701404, "loss": 0.6779908180236817, "step": 150080 }, { "epoch": 0.8921661287158729, "grad_norm": 1.487908959388733, "learning_rate": 0.00017946905844061126, "loss": 0.6876556396484375, "step": 150090 }, { "epoch": 0.8922255707925412, "grad_norm": 1.538542628288269, "learning_rate": 0.0001794651007518912, "loss": 0.6077081680297851, "step": 150100 }, { "epoch": 0.8922850128692096, "grad_norm": 1.4701001644134521, "learning_rate": 0.00017946114273087278, "loss": 0.6142470836639404, "step": 150110 }, { "epoch": 0.892344454945878, "grad_norm": 1.9085198640823364, "learning_rate": 0.000179457184377575, "loss": 0.6342060565948486, "step": 150120 }, { "epoch": 0.8924038970225464, "grad_norm": 1.6078368425369263, "learning_rate": 0.0001794532256920167, "loss": 0.641781234741211, "step": 150130 }, { "epoch": 0.8924633390992148, "grad_norm": 1.8235228061676025, "learning_rate": 0.0001794492666742169, "loss": 0.6450780391693115, "step": 150140 }, { "epoch": 0.8925227811758831, "grad_norm": 1.7457612752914429, "learning_rate": 0.0001794453073241945, "loss": 0.703447961807251, "step": 150150 }, { "epoch": 0.8925822232525515, "grad_norm": 1.7688086032867432, "learning_rate": 0.00017944134764196843, "loss": 0.6333681583404541, "step": 150160 }, { "epoch": 0.89264166532922, "grad_norm": 1.6566171646118164, "learning_rate": 0.00017943738762755764, "loss": 0.6876027107238769, "step": 150170 }, { "epoch": 0.8927011074058884, "grad_norm": 1.3284965753555298, "learning_rate": 0.00017943342728098108, "loss": 0.6528692245483398, "step": 150180 }, { "epoch": 0.8927605494825567, "grad_norm": 1.8614228963851929, "learning_rate": 0.00017942946660225772, "loss": 0.6219453811645508, "step": 150190 }, { "epoch": 0.8928199915592251, "grad_norm": 1.4367395639419556, "learning_rate": 0.00017942550559140648, "loss": 0.6123668670654296, "step": 150200 }, { "epoch": 0.8928794336358935, "grad_norm": 1.309354305267334, "learning_rate": 0.00017942154424844628, "loss": 0.6211101531982421, "step": 150210 }, { "epoch": 0.8929388757125619, "grad_norm": 1.6709482669830322, "learning_rate": 0.00017941758257339612, "loss": 0.6946197986602783, "step": 150220 }, { "epoch": 0.8929983177892303, "grad_norm": 1.8777847290039062, "learning_rate": 0.00017941362056627492, "loss": 0.621140718460083, "step": 150230 }, { "epoch": 0.8930577598658986, "grad_norm": 1.5975430011749268, "learning_rate": 0.00017940965822710168, "loss": 0.6620698928833008, "step": 150240 }, { "epoch": 0.893117201942567, "grad_norm": 1.4680445194244385, "learning_rate": 0.00017940569555589526, "loss": 0.6288521766662598, "step": 150250 }, { "epoch": 0.8931766440192355, "grad_norm": 1.7790439128875732, "learning_rate": 0.00017940173255267473, "loss": 0.7159527778625489, "step": 150260 }, { "epoch": 0.8932360860959039, "grad_norm": 1.6531929969787598, "learning_rate": 0.00017939776921745897, "loss": 0.6038505077362061, "step": 150270 }, { "epoch": 0.8932955281725722, "grad_norm": 1.515541911125183, "learning_rate": 0.00017939380555026695, "loss": 0.6828933715820312, "step": 150280 }, { "epoch": 0.8933549702492406, "grad_norm": 1.5867624282836914, "learning_rate": 0.00017938984155111765, "loss": 0.6230483055114746, "step": 150290 }, { "epoch": 0.893414412325909, "grad_norm": 1.5479297637939453, "learning_rate": 0.00017938587722003002, "loss": 0.6233675003051757, "step": 150300 }, { "epoch": 0.8934738544025774, "grad_norm": 1.8146817684173584, "learning_rate": 0.00017938191255702305, "loss": 0.6072235584259034, "step": 150310 }, { "epoch": 0.8935332964792458, "grad_norm": 1.920466423034668, "learning_rate": 0.00017937794756211565, "loss": 0.6419083595275878, "step": 150320 }, { "epoch": 0.8935927385559141, "grad_norm": 2.2970998287200928, "learning_rate": 0.00017937398223532685, "loss": 0.6080939292907714, "step": 150330 }, { "epoch": 0.8936521806325826, "grad_norm": 1.8544137477874756, "learning_rate": 0.0001793700165766756, "loss": 0.7140429496765137, "step": 150340 }, { "epoch": 0.893711622709251, "grad_norm": 1.6830240488052368, "learning_rate": 0.00017936605058618084, "loss": 0.6430383682250976, "step": 150350 }, { "epoch": 0.8937710647859194, "grad_norm": 1.7045222520828247, "learning_rate": 0.00017936208426386154, "loss": 0.6852931022644043, "step": 150360 }, { "epoch": 0.8938305068625878, "grad_norm": 2.032149076461792, "learning_rate": 0.00017935811760973674, "loss": 0.6797697067260742, "step": 150370 }, { "epoch": 0.8938899489392561, "grad_norm": 1.4969209432601929, "learning_rate": 0.00017935415062382535, "loss": 0.6880176067352295, "step": 150380 }, { "epoch": 0.8939493910159245, "grad_norm": 1.934494972229004, "learning_rate": 0.00017935018330614638, "loss": 0.6324204921722412, "step": 150390 }, { "epoch": 0.8940088330925929, "grad_norm": 1.6651177406311035, "learning_rate": 0.0001793462156567188, "loss": 0.6919290542602539, "step": 150400 }, { "epoch": 0.8940682751692614, "grad_norm": 1.5758261680603027, "learning_rate": 0.00017934224767556157, "loss": 0.6281004428863526, "step": 150410 }, { "epoch": 0.8941277172459297, "grad_norm": 1.32955801486969, "learning_rate": 0.00017933827936269367, "loss": 0.6373941898345947, "step": 150420 }, { "epoch": 0.8941871593225981, "grad_norm": 1.5821894407272339, "learning_rate": 0.00017933431071813413, "loss": 0.6426308631896973, "step": 150430 }, { "epoch": 0.8942466013992665, "grad_norm": 1.4944075345993042, "learning_rate": 0.00017933034174190193, "loss": 0.6616154670715332, "step": 150440 }, { "epoch": 0.8943060434759349, "grad_norm": 1.3256158828735352, "learning_rate": 0.000179326372434016, "loss": 0.6232349395751953, "step": 150450 }, { "epoch": 0.8943654855526033, "grad_norm": 1.5129445791244507, "learning_rate": 0.00017932240279449534, "loss": 0.6501900672912597, "step": 150460 }, { "epoch": 0.8944249276292716, "grad_norm": 1.8342320919036865, "learning_rate": 0.000179318432823359, "loss": 0.6465323448181153, "step": 150470 }, { "epoch": 0.89448436970594, "grad_norm": 1.9747035503387451, "learning_rate": 0.0001793144625206259, "loss": 0.6330904960632324, "step": 150480 }, { "epoch": 0.8945438117826084, "grad_norm": 1.5190140008926392, "learning_rate": 0.00017931049188631512, "loss": 0.6265322685241699, "step": 150490 }, { "epoch": 0.8946032538592769, "grad_norm": 1.5168088674545288, "learning_rate": 0.00017930652092044554, "loss": 0.6245463371276856, "step": 150500 }, { "epoch": 0.8946626959359453, "grad_norm": 1.5340676307678223, "learning_rate": 0.00017930254962303624, "loss": 0.6578536033630371, "step": 150510 }, { "epoch": 0.8947221380126136, "grad_norm": 1.9037606716156006, "learning_rate": 0.00017929857799410615, "loss": 0.688052749633789, "step": 150520 }, { "epoch": 0.894781580089282, "grad_norm": 1.4773515462875366, "learning_rate": 0.0001792946060336744, "loss": 0.5992876052856445, "step": 150530 }, { "epoch": 0.8948410221659504, "grad_norm": 1.4685512781143188, "learning_rate": 0.0001792906337417598, "loss": 0.6746582984924316, "step": 150540 }, { "epoch": 0.8949004642426188, "grad_norm": 1.2945771217346191, "learning_rate": 0.00017928666111838152, "loss": 0.5706282615661621, "step": 150550 }, { "epoch": 0.8949599063192871, "grad_norm": 1.9757384061813354, "learning_rate": 0.00017928268816355845, "loss": 0.6910860538482666, "step": 150560 }, { "epoch": 0.8950193483959555, "grad_norm": 1.8500372171401978, "learning_rate": 0.00017927871487730967, "loss": 0.6371968269348145, "step": 150570 }, { "epoch": 0.895078790472624, "grad_norm": 1.6712629795074463, "learning_rate": 0.00017927474125965415, "loss": 0.6909939765930175, "step": 150580 }, { "epoch": 0.8951382325492924, "grad_norm": 1.6206153631210327, "learning_rate": 0.0001792707673106109, "loss": 0.6778521537780762, "step": 150590 }, { "epoch": 0.8951976746259608, "grad_norm": 1.7445826530456543, "learning_rate": 0.00017926679303019896, "loss": 0.6973933219909668, "step": 150600 }, { "epoch": 0.8952571167026291, "grad_norm": 1.7889280319213867, "learning_rate": 0.00017926281841843732, "loss": 0.6695355415344239, "step": 150610 }, { "epoch": 0.8953165587792975, "grad_norm": 1.5789999961853027, "learning_rate": 0.00017925884347534497, "loss": 0.6089847564697266, "step": 150620 }, { "epoch": 0.8953760008559659, "grad_norm": 1.9159482717514038, "learning_rate": 0.00017925486820094094, "loss": 0.6199999332427979, "step": 150630 }, { "epoch": 0.8954354429326343, "grad_norm": 1.4526346921920776, "learning_rate": 0.0001792508925952443, "loss": 0.5956591606140137, "step": 150640 }, { "epoch": 0.8954948850093026, "grad_norm": 1.770509958267212, "learning_rate": 0.00017924691665827396, "loss": 0.6580991744995117, "step": 150650 }, { "epoch": 0.895554327085971, "grad_norm": 2.0440921783447266, "learning_rate": 0.00017924294039004904, "loss": 0.661924934387207, "step": 150660 }, { "epoch": 0.8956137691626395, "grad_norm": 1.5766823291778564, "learning_rate": 0.0001792389637905885, "loss": 0.6838614463806152, "step": 150670 }, { "epoch": 0.8956732112393079, "grad_norm": 2.221640110015869, "learning_rate": 0.0001792349868599114, "loss": 0.6186258792877197, "step": 150680 }, { "epoch": 0.8957326533159763, "grad_norm": 1.3928420543670654, "learning_rate": 0.00017923100959803674, "loss": 0.6489983081817627, "step": 150690 }, { "epoch": 0.8957920953926446, "grad_norm": 1.7425622940063477, "learning_rate": 0.00017922703200498355, "loss": 0.6518062591552735, "step": 150700 }, { "epoch": 0.895851537469313, "grad_norm": 1.721396565437317, "learning_rate": 0.0001792230540807709, "loss": 0.6307309150695801, "step": 150710 }, { "epoch": 0.8959109795459814, "grad_norm": 1.0489370822906494, "learning_rate": 0.00017921907582541774, "loss": 0.621570634841919, "step": 150720 }, { "epoch": 0.8959704216226498, "grad_norm": 1.7203749418258667, "learning_rate": 0.00017921509723894315, "loss": 0.6229119300842285, "step": 150730 }, { "epoch": 0.8960298636993183, "grad_norm": 1.3557493686676025, "learning_rate": 0.00017921111832136616, "loss": 0.6159696578979492, "step": 150740 }, { "epoch": 0.8960893057759866, "grad_norm": 1.561414122581482, "learning_rate": 0.00017920713907270582, "loss": 0.6604766845703125, "step": 150750 }, { "epoch": 0.896148747852655, "grad_norm": 2.164963722229004, "learning_rate": 0.00017920315949298112, "loss": 0.6445093631744385, "step": 150760 }, { "epoch": 0.8962081899293234, "grad_norm": 2.2540535926818848, "learning_rate": 0.00017919917958221114, "loss": 0.629274559020996, "step": 150770 }, { "epoch": 0.8962676320059918, "grad_norm": 1.6005064249038696, "learning_rate": 0.00017919519934041486, "loss": 0.6104542255401612, "step": 150780 }, { "epoch": 0.8963270740826601, "grad_norm": 1.6334872245788574, "learning_rate": 0.0001791912187676114, "loss": 0.6263064384460449, "step": 150790 }, { "epoch": 0.8963865161593285, "grad_norm": 1.8014556169509888, "learning_rate": 0.00017918723786381974, "loss": 0.6325328826904297, "step": 150800 }, { "epoch": 0.8964459582359969, "grad_norm": 1.8412492275238037, "learning_rate": 0.00017918325662905895, "loss": 0.605308198928833, "step": 150810 }, { "epoch": 0.8965054003126653, "grad_norm": 1.9037458896636963, "learning_rate": 0.0001791792750633481, "loss": 0.6011538505554199, "step": 150820 }, { "epoch": 0.8965648423893338, "grad_norm": 1.718246579170227, "learning_rate": 0.00017917529316670614, "loss": 0.6341248035430909, "step": 150830 }, { "epoch": 0.8966242844660021, "grad_norm": 1.4327746629714966, "learning_rate": 0.00017917131093915222, "loss": 0.6351102828979492, "step": 150840 }, { "epoch": 0.8966837265426705, "grad_norm": 1.7336658239364624, "learning_rate": 0.00017916732838070535, "loss": 0.5996841430664063, "step": 150850 }, { "epoch": 0.8967431686193389, "grad_norm": 1.5108745098114014, "learning_rate": 0.00017916334549138458, "loss": 0.5933587551116943, "step": 150860 }, { "epoch": 0.8968026106960073, "grad_norm": 1.54289972782135, "learning_rate": 0.00017915936227120899, "loss": 0.6339888572692871, "step": 150870 }, { "epoch": 0.8968620527726756, "grad_norm": 1.4540610313415527, "learning_rate": 0.00017915537872019758, "loss": 0.6420651435852051, "step": 150880 }, { "epoch": 0.896921494849344, "grad_norm": 2.0329678058624268, "learning_rate": 0.00017915139483836947, "loss": 0.5855071067810058, "step": 150890 }, { "epoch": 0.8969809369260124, "grad_norm": 1.6553318500518799, "learning_rate": 0.0001791474106257437, "loss": 0.6237053871154785, "step": 150900 }, { "epoch": 0.8970403790026809, "grad_norm": 1.589830994606018, "learning_rate": 0.00017914342608233927, "loss": 0.6535123825073242, "step": 150910 }, { "epoch": 0.8970998210793493, "grad_norm": 1.9187955856323242, "learning_rate": 0.0001791394412081753, "loss": 0.6595866203308105, "step": 150920 }, { "epoch": 0.8971592631560176, "grad_norm": 1.57270085811615, "learning_rate": 0.00017913545600327084, "loss": 0.5769629955291748, "step": 150930 }, { "epoch": 0.897218705232686, "grad_norm": 1.6288511753082275, "learning_rate": 0.00017913147046764495, "loss": 0.5939266204833984, "step": 150940 }, { "epoch": 0.8972781473093544, "grad_norm": 1.3476332426071167, "learning_rate": 0.0001791274846013167, "loss": 0.6751562118530273, "step": 150950 }, { "epoch": 0.8973375893860228, "grad_norm": 1.3967305421829224, "learning_rate": 0.00017912349840430519, "loss": 0.6241305351257325, "step": 150960 }, { "epoch": 0.8973970314626912, "grad_norm": 1.4281615018844604, "learning_rate": 0.0001791195118766294, "loss": 0.652180290222168, "step": 150970 }, { "epoch": 0.8974564735393595, "grad_norm": 1.8426704406738281, "learning_rate": 0.00017911552501830846, "loss": 0.6725285530090332, "step": 150980 }, { "epoch": 0.897515915616028, "grad_norm": 1.9474694728851318, "learning_rate": 0.00017911153782936145, "loss": 0.7185850143432617, "step": 150990 }, { "epoch": 0.8975753576926964, "grad_norm": 1.5411330461502075, "learning_rate": 0.00017910755030980743, "loss": 0.6368467807769775, "step": 151000 }, { "epoch": 0.8976347997693648, "grad_norm": 2.0311672687530518, "learning_rate": 0.0001791035624596655, "loss": 0.6111911296844482, "step": 151010 }, { "epoch": 0.8976942418460331, "grad_norm": 1.5692354440689087, "learning_rate": 0.00017909957427895469, "loss": 0.6240105628967285, "step": 151020 }, { "epoch": 0.8977536839227015, "grad_norm": 1.7170608043670654, "learning_rate": 0.00017909558576769408, "loss": 0.652684497833252, "step": 151030 }, { "epoch": 0.8978131259993699, "grad_norm": 1.9711222648620605, "learning_rate": 0.0001790915969259028, "loss": 0.7109696388244628, "step": 151040 }, { "epoch": 0.8978725680760383, "grad_norm": 1.8985586166381836, "learning_rate": 0.00017908760775359986, "loss": 0.6194353103637695, "step": 151050 }, { "epoch": 0.8979320101527067, "grad_norm": 1.6910349130630493, "learning_rate": 0.00017908361825080439, "loss": 0.649890947341919, "step": 151060 }, { "epoch": 0.897991452229375, "grad_norm": 2.339142322540283, "learning_rate": 0.0001790796284175355, "loss": 0.6328676700592041, "step": 151070 }, { "epoch": 0.8980508943060435, "grad_norm": 1.7437511682510376, "learning_rate": 0.00017907563825381222, "loss": 0.6278108596801758, "step": 151080 }, { "epoch": 0.8981103363827119, "grad_norm": 1.6941511631011963, "learning_rate": 0.00017907164775965366, "loss": 0.6793965339660645, "step": 151090 }, { "epoch": 0.8981697784593803, "grad_norm": 1.4089218378067017, "learning_rate": 0.0001790676569350789, "loss": 0.6102108001708985, "step": 151100 }, { "epoch": 0.8982292205360487, "grad_norm": 1.785685420036316, "learning_rate": 0.00017906366578010707, "loss": 0.627164363861084, "step": 151110 }, { "epoch": 0.898288662612717, "grad_norm": 1.3834574222564697, "learning_rate": 0.00017905967429475723, "loss": 0.5760968685150146, "step": 151120 }, { "epoch": 0.8983481046893854, "grad_norm": 2.00581431388855, "learning_rate": 0.00017905568247904844, "loss": 0.6614682674407959, "step": 151130 }, { "epoch": 0.8984075467660538, "grad_norm": 1.4333912134170532, "learning_rate": 0.00017905169033299986, "loss": 0.659496259689331, "step": 151140 }, { "epoch": 0.8984669888427222, "grad_norm": 1.2874919176101685, "learning_rate": 0.00017904769785663055, "loss": 0.6276669979095459, "step": 151150 }, { "epoch": 0.8985264309193906, "grad_norm": 1.3816577196121216, "learning_rate": 0.00017904370504995964, "loss": 0.6571102619171143, "step": 151160 }, { "epoch": 0.898585872996059, "grad_norm": 1.3241755962371826, "learning_rate": 0.00017903971191300623, "loss": 0.6597376823425293, "step": 151170 }, { "epoch": 0.8986453150727274, "grad_norm": 1.853424072265625, "learning_rate": 0.00017903571844578932, "loss": 0.6471817970275879, "step": 151180 }, { "epoch": 0.8987047571493958, "grad_norm": 1.8235610723495483, "learning_rate": 0.00017903172464832815, "loss": 0.6651922702789307, "step": 151190 }, { "epoch": 0.8987641992260642, "grad_norm": 1.8709133863449097, "learning_rate": 0.00017902773052064176, "loss": 0.6456841468811035, "step": 151200 }, { "epoch": 0.8988236413027325, "grad_norm": 1.4447511434555054, "learning_rate": 0.00017902373606274927, "loss": 0.611288595199585, "step": 151210 }, { "epoch": 0.8988830833794009, "grad_norm": 2.4509551525115967, "learning_rate": 0.00017901974127466978, "loss": 0.6553361892700196, "step": 151220 }, { "epoch": 0.8989425254560693, "grad_norm": 1.6050605773925781, "learning_rate": 0.00017901574615642238, "loss": 0.680970287322998, "step": 151230 }, { "epoch": 0.8990019675327378, "grad_norm": 2.0559542179107666, "learning_rate": 0.00017901175070802623, "loss": 0.6424712181091309, "step": 151240 }, { "epoch": 0.8990614096094061, "grad_norm": 1.6791961193084717, "learning_rate": 0.0001790077549295004, "loss": 0.6833547592163086, "step": 151250 }, { "epoch": 0.8991208516860745, "grad_norm": 1.6635135412216187, "learning_rate": 0.00017900375882086403, "loss": 0.6201118469238281, "step": 151260 }, { "epoch": 0.8991802937627429, "grad_norm": 1.4458650350570679, "learning_rate": 0.00017899976238213626, "loss": 0.7153949737548828, "step": 151270 }, { "epoch": 0.8992397358394113, "grad_norm": 1.8400393724441528, "learning_rate": 0.00017899576561333612, "loss": 0.6246521472930908, "step": 151280 }, { "epoch": 0.8992991779160797, "grad_norm": 2.081281900405884, "learning_rate": 0.00017899176851448285, "loss": 0.6924398422241211, "step": 151290 }, { "epoch": 0.899358619992748, "grad_norm": 1.602217197418213, "learning_rate": 0.0001789877710855955, "loss": 0.6805374145507812, "step": 151300 }, { "epoch": 0.8994180620694164, "grad_norm": 1.4901820421218872, "learning_rate": 0.00017898377332669315, "loss": 0.6671659469604492, "step": 151310 }, { "epoch": 0.8994775041460848, "grad_norm": 2.155871868133545, "learning_rate": 0.000178979775237795, "loss": 0.6840715885162354, "step": 151320 }, { "epoch": 0.8995369462227533, "grad_norm": 1.7165240049362183, "learning_rate": 0.00017897577681892014, "loss": 0.6479109287261963, "step": 151330 }, { "epoch": 0.8995963882994217, "grad_norm": 1.6602238416671753, "learning_rate": 0.00017897177807008768, "loss": 0.6252650260925293, "step": 151340 }, { "epoch": 0.89965583037609, "grad_norm": 1.2652469873428345, "learning_rate": 0.00017896777899131686, "loss": 0.6074741363525391, "step": 151350 }, { "epoch": 0.8997152724527584, "grad_norm": 1.604082703590393, "learning_rate": 0.00017896377958262662, "loss": 0.6831689834594726, "step": 151360 }, { "epoch": 0.8997747145294268, "grad_norm": 1.5949766635894775, "learning_rate": 0.00017895977984403624, "loss": 0.6545109748840332, "step": 151370 }, { "epoch": 0.8998341566060952, "grad_norm": 2.1359546184539795, "learning_rate": 0.00017895577977556485, "loss": 0.6596094131469726, "step": 151380 }, { "epoch": 0.8998935986827635, "grad_norm": 1.4383001327514648, "learning_rate": 0.00017895177937723146, "loss": 0.6697898387908936, "step": 151390 }, { "epoch": 0.8999530407594319, "grad_norm": 1.8936799764633179, "learning_rate": 0.00017894777864905535, "loss": 0.6186781883239746, "step": 151400 }, { "epoch": 0.9000124828361004, "grad_norm": 1.540166974067688, "learning_rate": 0.00017894377759105558, "loss": 0.6035727024078369, "step": 151410 }, { "epoch": 0.9000719249127688, "grad_norm": 2.173194169998169, "learning_rate": 0.0001789397762032513, "loss": 0.6784198760986329, "step": 151420 }, { "epoch": 0.9001313669894372, "grad_norm": 1.50388765335083, "learning_rate": 0.0001789357744856617, "loss": 0.6705891609191894, "step": 151430 }, { "epoch": 0.9001908090661055, "grad_norm": 1.6597625017166138, "learning_rate": 0.00017893177243830588, "loss": 0.6643535614013671, "step": 151440 }, { "epoch": 0.9002502511427739, "grad_norm": 2.019333839416504, "learning_rate": 0.00017892777006120293, "loss": 0.7015148639678955, "step": 151450 }, { "epoch": 0.9003096932194423, "grad_norm": 1.4525504112243652, "learning_rate": 0.0001789237673543721, "loss": 0.6823271751403809, "step": 151460 }, { "epoch": 0.9003691352961107, "grad_norm": 1.462498664855957, "learning_rate": 0.0001789197643178325, "loss": 0.7102407455444336, "step": 151470 }, { "epoch": 0.9004285773727791, "grad_norm": 1.9332752227783203, "learning_rate": 0.00017891576095160325, "loss": 0.7133330345153809, "step": 151480 }, { "epoch": 0.9004880194494475, "grad_norm": 1.6955232620239258, "learning_rate": 0.00017891175725570353, "loss": 0.7433857440948486, "step": 151490 }, { "epoch": 0.9005474615261159, "grad_norm": 1.551135540008545, "learning_rate": 0.00017890775323015244, "loss": 0.6260174751281739, "step": 151500 }, { "epoch": 0.9006069036027843, "grad_norm": 1.4416747093200684, "learning_rate": 0.00017890374887496923, "loss": 0.6560030937194824, "step": 151510 }, { "epoch": 0.9006663456794527, "grad_norm": 1.6447274684906006, "learning_rate": 0.00017889974419017302, "loss": 0.6174176216125489, "step": 151520 }, { "epoch": 0.900725787756121, "grad_norm": 1.449526309967041, "learning_rate": 0.0001788957391757829, "loss": 0.6596610069274902, "step": 151530 }, { "epoch": 0.9007852298327894, "grad_norm": 1.2955231666564941, "learning_rate": 0.0001788917338318181, "loss": 0.6523987770080566, "step": 151540 }, { "epoch": 0.9008446719094578, "grad_norm": 1.5729384422302246, "learning_rate": 0.00017888772815829776, "loss": 0.6275675773620606, "step": 151550 }, { "epoch": 0.9009041139861262, "grad_norm": 2.043487787246704, "learning_rate": 0.00017888372215524106, "loss": 0.6999982833862305, "step": 151560 }, { "epoch": 0.9009635560627947, "grad_norm": 1.701046109199524, "learning_rate": 0.00017887971582266713, "loss": 0.5860382556915283, "step": 151570 }, { "epoch": 0.901022998139463, "grad_norm": 1.4917190074920654, "learning_rate": 0.00017887570916059513, "loss": 0.6588308334350585, "step": 151580 }, { "epoch": 0.9010824402161314, "grad_norm": 2.009869337081909, "learning_rate": 0.00017887170216904428, "loss": 0.657143497467041, "step": 151590 }, { "epoch": 0.9011418822927998, "grad_norm": 1.7977993488311768, "learning_rate": 0.00017886769484803366, "loss": 0.6518787860870361, "step": 151600 }, { "epoch": 0.9012013243694682, "grad_norm": 1.134254813194275, "learning_rate": 0.00017886368719758256, "loss": 0.6396640777587891, "step": 151610 }, { "epoch": 0.9012607664461365, "grad_norm": 1.730376958847046, "learning_rate": 0.00017885967921771003, "loss": 0.6635159492492676, "step": 151620 }, { "epoch": 0.9013202085228049, "grad_norm": 1.8803210258483887, "learning_rate": 0.00017885567090843531, "loss": 0.624461555480957, "step": 151630 }, { "epoch": 0.9013796505994733, "grad_norm": 1.6259034872055054, "learning_rate": 0.0001788516622697776, "loss": 0.6321206569671631, "step": 151640 }, { "epoch": 0.9014390926761418, "grad_norm": 1.599301815032959, "learning_rate": 0.00017884765330175603, "loss": 0.6075719356536865, "step": 151650 }, { "epoch": 0.9014985347528102, "grad_norm": 1.5354914665222168, "learning_rate": 0.00017884364400438976, "loss": 0.6544872760772705, "step": 151660 }, { "epoch": 0.9015579768294785, "grad_norm": 1.6284120082855225, "learning_rate": 0.000178839634377698, "loss": 0.5596630096435546, "step": 151670 }, { "epoch": 0.9016174189061469, "grad_norm": 1.873288631439209, "learning_rate": 0.0001788356244216999, "loss": 0.6310080528259278, "step": 151680 }, { "epoch": 0.9016768609828153, "grad_norm": 1.724886417388916, "learning_rate": 0.00017883161413641472, "loss": 0.6542886734008789, "step": 151690 }, { "epoch": 0.9017363030594837, "grad_norm": 1.7761131525039673, "learning_rate": 0.00017882760352186156, "loss": 0.6381341934204101, "step": 151700 }, { "epoch": 0.9017957451361521, "grad_norm": 1.4774158000946045, "learning_rate": 0.00017882359257805967, "loss": 0.6565146923065186, "step": 151710 }, { "epoch": 0.9018551872128204, "grad_norm": 1.6936768293380737, "learning_rate": 0.00017881958130502816, "loss": 0.6229216575622558, "step": 151720 }, { "epoch": 0.9019146292894888, "grad_norm": 1.6725902557373047, "learning_rate": 0.0001788155697027863, "loss": 0.6426469802856445, "step": 151730 }, { "epoch": 0.9019740713661573, "grad_norm": 1.403676986694336, "learning_rate": 0.00017881155777135324, "loss": 0.6216808319091797, "step": 151740 }, { "epoch": 0.9020335134428257, "grad_norm": 2.135256767272949, "learning_rate": 0.00017880754551074816, "loss": 0.6238312721252441, "step": 151750 }, { "epoch": 0.902092955519494, "grad_norm": 2.2067856788635254, "learning_rate": 0.00017880353292099027, "loss": 0.6875606536865234, "step": 151760 }, { "epoch": 0.9021523975961624, "grad_norm": 1.249338984489441, "learning_rate": 0.00017879952000209877, "loss": 0.592842960357666, "step": 151770 }, { "epoch": 0.9022118396728308, "grad_norm": 1.668296456336975, "learning_rate": 0.00017879550675409286, "loss": 0.6688060760498047, "step": 151780 }, { "epoch": 0.9022712817494992, "grad_norm": 1.688798189163208, "learning_rate": 0.0001787914931769917, "loss": 0.6236773490905761, "step": 151790 }, { "epoch": 0.9023307238261676, "grad_norm": 2.012430191040039, "learning_rate": 0.00017878747927081457, "loss": 0.667626953125, "step": 151800 }, { "epoch": 0.9023901659028359, "grad_norm": 1.9107578992843628, "learning_rate": 0.00017878346503558059, "loss": 0.7007820129394531, "step": 151810 }, { "epoch": 0.9024496079795044, "grad_norm": 1.8503669500350952, "learning_rate": 0.00017877945047130897, "loss": 0.6697779655456543, "step": 151820 }, { "epoch": 0.9025090500561728, "grad_norm": 1.9090759754180908, "learning_rate": 0.00017877543557801896, "loss": 0.7298760414123535, "step": 151830 }, { "epoch": 0.9025684921328412, "grad_norm": 1.4280656576156616, "learning_rate": 0.00017877142035572973, "loss": 0.6548057556152344, "step": 151840 }, { "epoch": 0.9026279342095096, "grad_norm": 1.9126083850860596, "learning_rate": 0.0001787674048044605, "loss": 0.6621439933776856, "step": 151850 }, { "epoch": 0.9026873762861779, "grad_norm": 1.8530194759368896, "learning_rate": 0.0001787633889242305, "loss": 0.6558676719665527, "step": 151860 }, { "epoch": 0.9027468183628463, "grad_norm": 1.5907306671142578, "learning_rate": 0.00017875937271505892, "loss": 0.6666023254394531, "step": 151870 }, { "epoch": 0.9028062604395147, "grad_norm": 2.0751240253448486, "learning_rate": 0.00017875535617696496, "loss": 0.6541703224182129, "step": 151880 }, { "epoch": 0.9028657025161831, "grad_norm": 1.8385992050170898, "learning_rate": 0.00017875133930996784, "loss": 0.6757653713226318, "step": 151890 }, { "epoch": 0.9029251445928514, "grad_norm": 1.0876511335372925, "learning_rate": 0.00017874732211408675, "loss": 0.6039505004882812, "step": 151900 }, { "epoch": 0.9029845866695199, "grad_norm": 1.8015000820159912, "learning_rate": 0.00017874330458934098, "loss": 0.6872929573059082, "step": 151910 }, { "epoch": 0.9030440287461883, "grad_norm": 1.8917055130004883, "learning_rate": 0.00017873928673574972, "loss": 0.6551852703094483, "step": 151920 }, { "epoch": 0.9031034708228567, "grad_norm": 1.506407618522644, "learning_rate": 0.00017873526855333215, "loss": 0.6912636756896973, "step": 151930 }, { "epoch": 0.9031629128995251, "grad_norm": 1.7785874605178833, "learning_rate": 0.00017873125004210752, "loss": 0.7236620426177979, "step": 151940 }, { "epoch": 0.9032223549761934, "grad_norm": 1.8223297595977783, "learning_rate": 0.00017872723120209504, "loss": 0.6807963848114014, "step": 151950 }, { "epoch": 0.9032817970528618, "grad_norm": 1.4101823568344116, "learning_rate": 0.00017872321203331396, "loss": 0.636197280883789, "step": 151960 }, { "epoch": 0.9033412391295302, "grad_norm": 1.2705470323562622, "learning_rate": 0.00017871919253578352, "loss": 0.6634916305541992, "step": 151970 }, { "epoch": 0.9034006812061987, "grad_norm": 1.5260326862335205, "learning_rate": 0.00017871517270952287, "loss": 0.627044677734375, "step": 151980 }, { "epoch": 0.903460123282867, "grad_norm": 1.547815203666687, "learning_rate": 0.0001787111525545513, "loss": 0.6968571662902832, "step": 151990 }, { "epoch": 0.9035195653595354, "grad_norm": 1.241392970085144, "learning_rate": 0.00017870713207088806, "loss": 0.6083091259002685, "step": 152000 }, { "epoch": 0.9035790074362038, "grad_norm": 1.4654173851013184, "learning_rate": 0.00017870311125855234, "loss": 0.6415679454803467, "step": 152010 }, { "epoch": 0.9036384495128722, "grad_norm": 1.5588126182556152, "learning_rate": 0.0001786990901175634, "loss": 0.6978033065795899, "step": 152020 }, { "epoch": 0.9036978915895406, "grad_norm": 1.4480619430541992, "learning_rate": 0.00017869506864794045, "loss": 0.6224122524261475, "step": 152030 }, { "epoch": 0.9037573336662089, "grad_norm": 1.4813789129257202, "learning_rate": 0.00017869104684970272, "loss": 0.6542013168334961, "step": 152040 }, { "epoch": 0.9038167757428773, "grad_norm": 1.4811406135559082, "learning_rate": 0.00017868702472286952, "loss": 0.642525577545166, "step": 152050 }, { "epoch": 0.9038762178195457, "grad_norm": 1.8391913175582886, "learning_rate": 0.00017868300226745997, "loss": 0.6169329643249511, "step": 152060 }, { "epoch": 0.9039356598962142, "grad_norm": 1.6200107336044312, "learning_rate": 0.00017867897948349343, "loss": 0.6982653141021729, "step": 152070 }, { "epoch": 0.9039951019728826, "grad_norm": 1.5120866298675537, "learning_rate": 0.0001786749563709891, "loss": 0.6267951488494873, "step": 152080 }, { "epoch": 0.9040545440495509, "grad_norm": 2.1846187114715576, "learning_rate": 0.00017867093292996624, "loss": 0.6379488468170166, "step": 152090 }, { "epoch": 0.9041139861262193, "grad_norm": 1.3913370370864868, "learning_rate": 0.00017866690916044405, "loss": 0.6566879749298096, "step": 152100 }, { "epoch": 0.9041734282028877, "grad_norm": 2.104952096939087, "learning_rate": 0.0001786628850624418, "loss": 0.6054459571838379, "step": 152110 }, { "epoch": 0.9042328702795561, "grad_norm": 1.6910316944122314, "learning_rate": 0.00017865886063597877, "loss": 0.6440465450286865, "step": 152120 }, { "epoch": 0.9042923123562244, "grad_norm": 1.326460838317871, "learning_rate": 0.00017865483588107417, "loss": 0.626597785949707, "step": 152130 }, { "epoch": 0.9043517544328928, "grad_norm": 1.425755500793457, "learning_rate": 0.00017865081079774728, "loss": 0.6518403053283691, "step": 152140 }, { "epoch": 0.9044111965095613, "grad_norm": 1.7296756505966187, "learning_rate": 0.00017864678538601734, "loss": 0.686042308807373, "step": 152150 }, { "epoch": 0.9044706385862297, "grad_norm": 1.5621020793914795, "learning_rate": 0.00017864275964590365, "loss": 0.5856375694274902, "step": 152160 }, { "epoch": 0.9045300806628981, "grad_norm": 1.5786629915237427, "learning_rate": 0.00017863873357742535, "loss": 0.597430944442749, "step": 152170 }, { "epoch": 0.9045895227395664, "grad_norm": 1.6341509819030762, "learning_rate": 0.00017863470718060184, "loss": 0.6482558727264405, "step": 152180 }, { "epoch": 0.9046489648162348, "grad_norm": 2.230598211288452, "learning_rate": 0.00017863068045545234, "loss": 0.5853599548339844, "step": 152190 }, { "epoch": 0.9047084068929032, "grad_norm": 1.6959184408187866, "learning_rate": 0.00017862665340199604, "loss": 0.5829856872558594, "step": 152200 }, { "epoch": 0.9047678489695716, "grad_norm": 2.0819501876831055, "learning_rate": 0.0001786226260202523, "loss": 0.6900515556335449, "step": 152210 }, { "epoch": 0.90482729104624, "grad_norm": 1.366600751876831, "learning_rate": 0.0001786185983102403, "loss": 0.6572710037231445, "step": 152220 }, { "epoch": 0.9048867331229083, "grad_norm": 1.8588035106658936, "learning_rate": 0.00017861457027197936, "loss": 0.6962942123413086, "step": 152230 }, { "epoch": 0.9049461751995768, "grad_norm": 1.4154354333877563, "learning_rate": 0.00017861054190548877, "loss": 0.5814373016357421, "step": 152240 }, { "epoch": 0.9050056172762452, "grad_norm": 1.1760540008544922, "learning_rate": 0.00017860651321078774, "loss": 0.7105773448944092, "step": 152250 }, { "epoch": 0.9050650593529136, "grad_norm": 1.306057333946228, "learning_rate": 0.00017860248418789557, "loss": 0.6383189678192138, "step": 152260 }, { "epoch": 0.9051245014295819, "grad_norm": 1.3798900842666626, "learning_rate": 0.00017859845483683158, "loss": 0.6598965644836425, "step": 152270 }, { "epoch": 0.9051839435062503, "grad_norm": 1.5544368028640747, "learning_rate": 0.00017859442515761497, "loss": 0.7068013191223145, "step": 152280 }, { "epoch": 0.9052433855829187, "grad_norm": 1.9286963939666748, "learning_rate": 0.00017859039515026503, "loss": 0.6851502895355225, "step": 152290 }, { "epoch": 0.9053028276595871, "grad_norm": 1.5690964460372925, "learning_rate": 0.0001785863648148011, "loss": 0.6637363433837891, "step": 152300 }, { "epoch": 0.9053622697362556, "grad_norm": 1.743009328842163, "learning_rate": 0.00017858233415124237, "loss": 0.6645759582519531, "step": 152310 }, { "epoch": 0.9054217118129239, "grad_norm": 1.334550380706787, "learning_rate": 0.00017857830315960819, "loss": 0.5652130603790283, "step": 152320 }, { "epoch": 0.9054811538895923, "grad_norm": 1.8333470821380615, "learning_rate": 0.00017857427183991782, "loss": 0.6437374114990234, "step": 152330 }, { "epoch": 0.9055405959662607, "grad_norm": 1.669087290763855, "learning_rate": 0.00017857024019219054, "loss": 0.6515413284301758, "step": 152340 }, { "epoch": 0.9056000380429291, "grad_norm": 1.77129065990448, "learning_rate": 0.00017856620821644564, "loss": 0.6487300872802735, "step": 152350 }, { "epoch": 0.9056594801195974, "grad_norm": 2.161959171295166, "learning_rate": 0.00017856217591270238, "loss": 0.7610418796539307, "step": 152360 }, { "epoch": 0.9057189221962658, "grad_norm": 1.7263444662094116, "learning_rate": 0.00017855814328098012, "loss": 0.6866852760314941, "step": 152370 }, { "epoch": 0.9057783642729342, "grad_norm": 1.2813621759414673, "learning_rate": 0.00017855411032129806, "loss": 0.6505778312683106, "step": 152380 }, { "epoch": 0.9058378063496026, "grad_norm": 1.8150147199630737, "learning_rate": 0.00017855007703367556, "loss": 0.6311276912689209, "step": 152390 }, { "epoch": 0.9058972484262711, "grad_norm": 1.6744850873947144, "learning_rate": 0.00017854604341813193, "loss": 0.6298298358917236, "step": 152400 }, { "epoch": 0.9059566905029394, "grad_norm": 1.8846267461776733, "learning_rate": 0.0001785420094746864, "loss": 0.678993034362793, "step": 152410 }, { "epoch": 0.9060161325796078, "grad_norm": 1.426059365272522, "learning_rate": 0.0001785379752033583, "loss": 0.6912883758544922, "step": 152420 }, { "epoch": 0.9060755746562762, "grad_norm": 2.0546562671661377, "learning_rate": 0.0001785339406041669, "loss": 0.6250603675842286, "step": 152430 }, { "epoch": 0.9061350167329446, "grad_norm": 1.6432021856307983, "learning_rate": 0.00017852990567713157, "loss": 0.6548004150390625, "step": 152440 }, { "epoch": 0.906194458809613, "grad_norm": 1.6542450189590454, "learning_rate": 0.00017852587042227155, "loss": 0.6646896839141846, "step": 152450 }, { "epoch": 0.9062539008862813, "grad_norm": 1.543634057044983, "learning_rate": 0.00017852183483960614, "loss": 0.6349123001098633, "step": 152460 }, { "epoch": 0.9063133429629497, "grad_norm": 1.5809712409973145, "learning_rate": 0.0001785177989291547, "loss": 0.6392762184143066, "step": 152470 }, { "epoch": 0.9063727850396182, "grad_norm": 1.5371248722076416, "learning_rate": 0.00017851376269093647, "loss": 0.6117889404296875, "step": 152480 }, { "epoch": 0.9064322271162866, "grad_norm": 1.642601728439331, "learning_rate": 0.00017850972612497081, "loss": 0.6913942813873291, "step": 152490 }, { "epoch": 0.9064916691929549, "grad_norm": 1.4835008382797241, "learning_rate": 0.00017850568923127703, "loss": 0.6647385597229004, "step": 152500 }, { "epoch": 0.9065511112696233, "grad_norm": 1.5504868030548096, "learning_rate": 0.00017850165200987436, "loss": 0.6175487518310547, "step": 152510 }, { "epoch": 0.9066105533462917, "grad_norm": 1.6239908933639526, "learning_rate": 0.0001784976144607822, "loss": 0.6492397785186768, "step": 152520 }, { "epoch": 0.9066699954229601, "grad_norm": 1.3850008249282837, "learning_rate": 0.00017849357658401984, "loss": 0.6460710525512695, "step": 152530 }, { "epoch": 0.9067294374996285, "grad_norm": 1.8281209468841553, "learning_rate": 0.0001784895383796066, "loss": 0.6302118301391602, "step": 152540 }, { "epoch": 0.9067888795762968, "grad_norm": 1.671944260597229, "learning_rate": 0.0001784854998475618, "loss": 0.6140409469604492, "step": 152550 }, { "epoch": 0.9068483216529653, "grad_norm": 1.8978911638259888, "learning_rate": 0.00017848146098790472, "loss": 0.6796951293945312, "step": 152560 }, { "epoch": 0.9069077637296337, "grad_norm": 1.509187936782837, "learning_rate": 0.00017847742180065475, "loss": 0.6189372062683105, "step": 152570 }, { "epoch": 0.9069672058063021, "grad_norm": 1.4642313718795776, "learning_rate": 0.00017847338228583115, "loss": 0.6159204483032227, "step": 152580 }, { "epoch": 0.9070266478829705, "grad_norm": 1.2946542501449585, "learning_rate": 0.0001784693424434533, "loss": 0.6139229297637939, "step": 152590 }, { "epoch": 0.9070860899596388, "grad_norm": 1.7529101371765137, "learning_rate": 0.00017846530227354045, "loss": 0.6308757305145264, "step": 152600 }, { "epoch": 0.9071455320363072, "grad_norm": 1.6337538957595825, "learning_rate": 0.00017846126177611195, "loss": 0.6454689025878906, "step": 152610 }, { "epoch": 0.9072049741129756, "grad_norm": 1.467585802078247, "learning_rate": 0.0001784572209511872, "loss": 0.6305768013000488, "step": 152620 }, { "epoch": 0.907264416189644, "grad_norm": 1.9999815225601196, "learning_rate": 0.00017845317979878545, "loss": 0.6416824340820313, "step": 152630 }, { "epoch": 0.9073238582663123, "grad_norm": 1.51524019241333, "learning_rate": 0.00017844913831892607, "loss": 0.6647468566894531, "step": 152640 }, { "epoch": 0.9073833003429808, "grad_norm": 1.8459491729736328, "learning_rate": 0.00017844509651162836, "loss": 0.5376114845275879, "step": 152650 }, { "epoch": 0.9074427424196492, "grad_norm": 1.6384919881820679, "learning_rate": 0.0001784410543769117, "loss": 0.729067325592041, "step": 152660 }, { "epoch": 0.9075021844963176, "grad_norm": 1.7722609043121338, "learning_rate": 0.0001784370119147954, "loss": 0.6427461624145507, "step": 152670 }, { "epoch": 0.907561626572986, "grad_norm": 1.576482892036438, "learning_rate": 0.00017843296912529877, "loss": 0.6646126747131348, "step": 152680 }, { "epoch": 0.9076210686496543, "grad_norm": 1.660198450088501, "learning_rate": 0.00017842892600844118, "loss": 0.6303743839263916, "step": 152690 }, { "epoch": 0.9076805107263227, "grad_norm": 1.5749406814575195, "learning_rate": 0.000178424882564242, "loss": 0.6156374931335449, "step": 152700 }, { "epoch": 0.9077399528029911, "grad_norm": 1.6362100839614868, "learning_rate": 0.00017842083879272055, "loss": 0.6021366119384766, "step": 152710 }, { "epoch": 0.9077993948796595, "grad_norm": 1.4380465745925903, "learning_rate": 0.00017841679469389615, "loss": 0.6038528442382812, "step": 152720 }, { "epoch": 0.9078588369563279, "grad_norm": 1.5983633995056152, "learning_rate": 0.00017841275026778816, "loss": 0.6227513313293457, "step": 152730 }, { "epoch": 0.9079182790329963, "grad_norm": 2.2198996543884277, "learning_rate": 0.00017840870551441595, "loss": 0.6037238121032715, "step": 152740 }, { "epoch": 0.9079777211096647, "grad_norm": 1.5457148551940918, "learning_rate": 0.00017840466043379883, "loss": 0.6622823715209961, "step": 152750 }, { "epoch": 0.9080371631863331, "grad_norm": 1.798262119293213, "learning_rate": 0.0001784006150259562, "loss": 0.6039161682128906, "step": 152760 }, { "epoch": 0.9080966052630015, "grad_norm": 1.4837123155593872, "learning_rate": 0.00017839656929090732, "loss": 0.6684661865234375, "step": 152770 }, { "epoch": 0.9081560473396698, "grad_norm": 1.8319278955459595, "learning_rate": 0.00017839252322867166, "loss": 0.6376140594482422, "step": 152780 }, { "epoch": 0.9082154894163382, "grad_norm": 1.7702133655548096, "learning_rate": 0.00017838847683926848, "loss": 0.6468049049377441, "step": 152790 }, { "epoch": 0.9082749314930066, "grad_norm": 1.5793592929840088, "learning_rate": 0.00017838443012271722, "loss": 0.6176278114318847, "step": 152800 }, { "epoch": 0.9083343735696751, "grad_norm": 1.3236103057861328, "learning_rate": 0.00017838038307903717, "loss": 0.618036937713623, "step": 152810 }, { "epoch": 0.9083938156463435, "grad_norm": 1.6918472051620483, "learning_rate": 0.00017837633570824771, "loss": 0.6627641201019288, "step": 152820 }, { "epoch": 0.9084532577230118, "grad_norm": 1.3906464576721191, "learning_rate": 0.00017837228801036823, "loss": 0.5721930980682373, "step": 152830 }, { "epoch": 0.9085126997996802, "grad_norm": 1.4914849996566772, "learning_rate": 0.00017836823998541802, "loss": 0.6783809661865234, "step": 152840 }, { "epoch": 0.9085721418763486, "grad_norm": 1.6788287162780762, "learning_rate": 0.00017836419163341655, "loss": 0.6173078536987304, "step": 152850 }, { "epoch": 0.908631583953017, "grad_norm": 2.340683698654175, "learning_rate": 0.0001783601429543831, "loss": 0.6305665016174317, "step": 152860 }, { "epoch": 0.9086910260296853, "grad_norm": 1.5881632566452026, "learning_rate": 0.00017835609394833708, "loss": 0.6610708236694336, "step": 152870 }, { "epoch": 0.9087504681063537, "grad_norm": 1.5335322618484497, "learning_rate": 0.00017835204461529781, "loss": 0.6601431846618653, "step": 152880 }, { "epoch": 0.9088099101830222, "grad_norm": 1.5212992429733276, "learning_rate": 0.00017834799495528472, "loss": 0.6331305503845215, "step": 152890 }, { "epoch": 0.9088693522596906, "grad_norm": 1.7179182767868042, "learning_rate": 0.00017834394496831716, "loss": 0.6920902252197265, "step": 152900 }, { "epoch": 0.908928794336359, "grad_norm": 2.0514016151428223, "learning_rate": 0.00017833989465441453, "loss": 0.6532770156860351, "step": 152910 }, { "epoch": 0.9089882364130273, "grad_norm": 1.4598928689956665, "learning_rate": 0.00017833584401359613, "loss": 0.6299032211303711, "step": 152920 }, { "epoch": 0.9090476784896957, "grad_norm": 1.6034462451934814, "learning_rate": 0.0001783317930458814, "loss": 0.671298885345459, "step": 152930 }, { "epoch": 0.9091071205663641, "grad_norm": 1.5810092687606812, "learning_rate": 0.00017832774175128972, "loss": 0.6540355205535888, "step": 152940 }, { "epoch": 0.9091665626430325, "grad_norm": 1.7430020570755005, "learning_rate": 0.00017832369012984046, "loss": 0.6954523086547851, "step": 152950 }, { "epoch": 0.9092260047197009, "grad_norm": 1.8594188690185547, "learning_rate": 0.00017831963818155296, "loss": 0.6463239669799805, "step": 152960 }, { "epoch": 0.9092854467963692, "grad_norm": 1.3767169713974, "learning_rate": 0.00017831558590644664, "loss": 0.6602413654327393, "step": 152970 }, { "epoch": 0.9093448888730377, "grad_norm": 1.2899848222732544, "learning_rate": 0.0001783115333045409, "loss": 0.6384223937988281, "step": 152980 }, { "epoch": 0.9094043309497061, "grad_norm": 1.3352768421173096, "learning_rate": 0.00017830748037585511, "loss": 0.6024898052215576, "step": 152990 }, { "epoch": 0.9094637730263745, "grad_norm": 1.6081856489181519, "learning_rate": 0.00017830342712040867, "loss": 0.6643085956573487, "step": 153000 }, { "epoch": 0.9095232151030428, "grad_norm": 1.7762534618377686, "learning_rate": 0.00017829937353822093, "loss": 0.6139123916625977, "step": 153010 }, { "epoch": 0.9095826571797112, "grad_norm": 1.653702974319458, "learning_rate": 0.00017829531962931133, "loss": 0.6656663417816162, "step": 153020 }, { "epoch": 0.9096420992563796, "grad_norm": 1.408691644668579, "learning_rate": 0.0001782912653936992, "loss": 0.6542265892028809, "step": 153030 }, { "epoch": 0.909701541333048, "grad_norm": 1.533158540725708, "learning_rate": 0.00017828721083140402, "loss": 0.6182507038116455, "step": 153040 }, { "epoch": 0.9097609834097165, "grad_norm": 1.5660115480422974, "learning_rate": 0.0001782831559424451, "loss": 0.6700019836425781, "step": 153050 }, { "epoch": 0.9098204254863848, "grad_norm": 1.5938444137573242, "learning_rate": 0.0001782791007268419, "loss": 0.6846304893493652, "step": 153060 }, { "epoch": 0.9098798675630532, "grad_norm": 1.6146756410598755, "learning_rate": 0.0001782750451846138, "loss": 0.6265178680419922, "step": 153070 }, { "epoch": 0.9099393096397216, "grad_norm": 1.5523966550827026, "learning_rate": 0.0001782709893157802, "loss": 0.6681666374206543, "step": 153080 }, { "epoch": 0.90999875171639, "grad_norm": 1.6964175701141357, "learning_rate": 0.0001782669331203605, "loss": 0.6586552143096924, "step": 153090 }, { "epoch": 0.9100581937930583, "grad_norm": 1.585313081741333, "learning_rate": 0.00017826287659837407, "loss": 0.6472506999969483, "step": 153100 }, { "epoch": 0.9101176358697267, "grad_norm": 1.6559875011444092, "learning_rate": 0.00017825881974984037, "loss": 0.6245742797851562, "step": 153110 }, { "epoch": 0.9101770779463951, "grad_norm": 1.994986653327942, "learning_rate": 0.00017825476257477877, "loss": 0.6302203178405762, "step": 153120 }, { "epoch": 0.9102365200230635, "grad_norm": 1.1967068910598755, "learning_rate": 0.00017825070507320872, "loss": 0.5757108688354492, "step": 153130 }, { "epoch": 0.910295962099732, "grad_norm": 1.9071111679077148, "learning_rate": 0.00017824664724514958, "loss": 0.6254978179931641, "step": 153140 }, { "epoch": 0.9103554041764003, "grad_norm": 1.592910885810852, "learning_rate": 0.00017824258909062077, "loss": 0.6243937492370606, "step": 153150 }, { "epoch": 0.9104148462530687, "grad_norm": 1.978513240814209, "learning_rate": 0.00017823853060964175, "loss": 0.7144378185272217, "step": 153160 }, { "epoch": 0.9104742883297371, "grad_norm": 1.9456580877304077, "learning_rate": 0.00017823447180223187, "loss": 0.6691067695617676, "step": 153170 }, { "epoch": 0.9105337304064055, "grad_norm": 1.86100435256958, "learning_rate": 0.0001782304126684106, "loss": 0.7072102546691894, "step": 153180 }, { "epoch": 0.9105931724830739, "grad_norm": 1.5762659311294556, "learning_rate": 0.0001782263532081973, "loss": 0.6816583156585694, "step": 153190 }, { "epoch": 0.9106526145597422, "grad_norm": 1.5268179178237915, "learning_rate": 0.0001782222934216115, "loss": 0.6306962013244629, "step": 153200 }, { "epoch": 0.9107120566364106, "grad_norm": 1.2649495601654053, "learning_rate": 0.00017821823330867246, "loss": 0.5929573059082032, "step": 153210 }, { "epoch": 0.910771498713079, "grad_norm": 1.540267825126648, "learning_rate": 0.00017821417286939973, "loss": 0.610969352722168, "step": 153220 }, { "epoch": 0.9108309407897475, "grad_norm": 1.7082818746566772, "learning_rate": 0.00017821011210381266, "loss": 0.6058842658996582, "step": 153230 }, { "epoch": 0.9108903828664158, "grad_norm": 1.844570279121399, "learning_rate": 0.00017820605101193072, "loss": 0.6741040706634521, "step": 153240 }, { "epoch": 0.9109498249430842, "grad_norm": 1.3880465030670166, "learning_rate": 0.0001782019895937733, "loss": 0.6467724800109863, "step": 153250 }, { "epoch": 0.9110092670197526, "grad_norm": 1.4565863609313965, "learning_rate": 0.0001781979278493599, "loss": 0.6263566493988038, "step": 153260 }, { "epoch": 0.911068709096421, "grad_norm": 1.694777488708496, "learning_rate": 0.00017819386577870984, "loss": 0.6373117446899415, "step": 153270 }, { "epoch": 0.9111281511730894, "grad_norm": 1.4439176321029663, "learning_rate": 0.00017818980338184267, "loss": 0.6305785655975342, "step": 153280 }, { "epoch": 0.9111875932497577, "grad_norm": 1.3225018978118896, "learning_rate": 0.00017818574065877772, "loss": 0.6662683963775635, "step": 153290 }, { "epoch": 0.9112470353264261, "grad_norm": 2.3581831455230713, "learning_rate": 0.00017818167760953453, "loss": 0.6366519927978516, "step": 153300 }, { "epoch": 0.9113064774030946, "grad_norm": 1.8681235313415527, "learning_rate": 0.0001781776142341324, "loss": 0.6594104766845703, "step": 153310 }, { "epoch": 0.911365919479763, "grad_norm": 1.5289311408996582, "learning_rate": 0.0001781735505325909, "loss": 0.6166378021240234, "step": 153320 }, { "epoch": 0.9114253615564314, "grad_norm": 1.4043731689453125, "learning_rate": 0.00017816948650492938, "loss": 0.6424368858337403, "step": 153330 }, { "epoch": 0.9114848036330997, "grad_norm": 1.3049147129058838, "learning_rate": 0.00017816542215116733, "loss": 0.7451502799987793, "step": 153340 }, { "epoch": 0.9115442457097681, "grad_norm": 1.3141313791275024, "learning_rate": 0.00017816135747132417, "loss": 0.6703322410583497, "step": 153350 }, { "epoch": 0.9116036877864365, "grad_norm": 1.206841230392456, "learning_rate": 0.00017815729246541936, "loss": 0.677475881576538, "step": 153360 }, { "epoch": 0.9116631298631049, "grad_norm": 1.8972511291503906, "learning_rate": 0.00017815322713347234, "loss": 0.610087251663208, "step": 153370 }, { "epoch": 0.9117225719397732, "grad_norm": 1.3051831722259521, "learning_rate": 0.00017814916147550257, "loss": 0.629035472869873, "step": 153380 }, { "epoch": 0.9117820140164417, "grad_norm": 1.5986032485961914, "learning_rate": 0.00017814509549152945, "loss": 0.6360571384429932, "step": 153390 }, { "epoch": 0.9118414560931101, "grad_norm": 2.1586694717407227, "learning_rate": 0.00017814102918157246, "loss": 0.5700015544891357, "step": 153400 }, { "epoch": 0.9119008981697785, "grad_norm": 1.6892426013946533, "learning_rate": 0.00017813696254565108, "loss": 0.6201632499694825, "step": 153410 }, { "epoch": 0.9119603402464469, "grad_norm": 2.006899833679199, "learning_rate": 0.0001781328955837847, "loss": 0.6754456520080566, "step": 153420 }, { "epoch": 0.9120197823231152, "grad_norm": 1.346937656402588, "learning_rate": 0.00017812882829599286, "loss": 0.7060782432556152, "step": 153430 }, { "epoch": 0.9120792243997836, "grad_norm": 1.7859296798706055, "learning_rate": 0.00017812476068229495, "loss": 0.6888645172119141, "step": 153440 }, { "epoch": 0.912138666476452, "grad_norm": 1.626236081123352, "learning_rate": 0.00017812069274271043, "loss": 0.6673512935638428, "step": 153450 }, { "epoch": 0.9121981085531204, "grad_norm": 1.4067285060882568, "learning_rate": 0.00017811662447725883, "loss": 0.623252010345459, "step": 153460 }, { "epoch": 0.9122575506297887, "grad_norm": 1.5174458026885986, "learning_rate": 0.00017811255588595952, "loss": 0.6876092910766601, "step": 153470 }, { "epoch": 0.9123169927064572, "grad_norm": 1.8765556812286377, "learning_rate": 0.00017810848696883202, "loss": 0.7191309928894043, "step": 153480 }, { "epoch": 0.9123764347831256, "grad_norm": 1.6856356859207153, "learning_rate": 0.00017810441772589576, "loss": 0.7201581954956054, "step": 153490 }, { "epoch": 0.912435876859794, "grad_norm": 1.7567048072814941, "learning_rate": 0.00017810034815717021, "loss": 0.627971076965332, "step": 153500 }, { "epoch": 0.9124953189364624, "grad_norm": 2.204188108444214, "learning_rate": 0.00017809627826267488, "loss": 0.659693431854248, "step": 153510 }, { "epoch": 0.9125547610131307, "grad_norm": 1.707983374595642, "learning_rate": 0.00017809220804242918, "loss": 0.6327614784240723, "step": 153520 }, { "epoch": 0.9126142030897991, "grad_norm": 1.3531523942947388, "learning_rate": 0.00017808813749645267, "loss": 0.610193920135498, "step": 153530 }, { "epoch": 0.9126736451664675, "grad_norm": 1.6092110872268677, "learning_rate": 0.0001780840666247647, "loss": 0.5676648139953613, "step": 153540 }, { "epoch": 0.912733087243136, "grad_norm": 1.5548919439315796, "learning_rate": 0.0001780799954273848, "loss": 0.6662989139556885, "step": 153550 }, { "epoch": 0.9127925293198044, "grad_norm": 1.5293011665344238, "learning_rate": 0.0001780759239043325, "loss": 0.5659594535827637, "step": 153560 }, { "epoch": 0.9128519713964727, "grad_norm": 1.6567574739456177, "learning_rate": 0.00017807185205562717, "loss": 0.6536314010620117, "step": 153570 }, { "epoch": 0.9129114134731411, "grad_norm": 1.4162182807922363, "learning_rate": 0.0001780677798812884, "loss": 0.6797597408294678, "step": 153580 }, { "epoch": 0.9129708555498095, "grad_norm": 1.4904009103775024, "learning_rate": 0.0001780637073813356, "loss": 0.6608080863952637, "step": 153590 }, { "epoch": 0.9130302976264779, "grad_norm": 1.5635501146316528, "learning_rate": 0.00017805963455578826, "loss": 0.6698821067810059, "step": 153600 }, { "epoch": 0.9130897397031462, "grad_norm": 1.7215989828109741, "learning_rate": 0.00017805556140466585, "loss": 0.6081113815307617, "step": 153610 }, { "epoch": 0.9131491817798146, "grad_norm": 1.658212661743164, "learning_rate": 0.00017805148792798792, "loss": 0.6425051689147949, "step": 153620 }, { "epoch": 0.913208623856483, "grad_norm": 1.6272698640823364, "learning_rate": 0.00017804741412577385, "loss": 0.6450599670410156, "step": 153630 }, { "epoch": 0.9132680659331515, "grad_norm": 1.803205966949463, "learning_rate": 0.00017804333999804324, "loss": 0.6226506710052491, "step": 153640 }, { "epoch": 0.9133275080098199, "grad_norm": 1.886825442314148, "learning_rate": 0.00017803926554481553, "loss": 0.6685381412506104, "step": 153650 }, { "epoch": 0.9133869500864882, "grad_norm": 1.418305516242981, "learning_rate": 0.00017803519076611018, "loss": 0.6513373374938964, "step": 153660 }, { "epoch": 0.9134463921631566, "grad_norm": 1.771332025527954, "learning_rate": 0.00017803111566194673, "loss": 0.6948118686676026, "step": 153670 }, { "epoch": 0.913505834239825, "grad_norm": 1.4429062604904175, "learning_rate": 0.00017802704023234465, "loss": 0.6515639781951904, "step": 153680 }, { "epoch": 0.9135652763164934, "grad_norm": 1.5326058864593506, "learning_rate": 0.00017802296447732343, "loss": 0.6635131359100341, "step": 153690 }, { "epoch": 0.9136247183931618, "grad_norm": 1.7868473529815674, "learning_rate": 0.00017801888839690262, "loss": 0.6378970146179199, "step": 153700 }, { "epoch": 0.9136841604698301, "grad_norm": 2.0401103496551514, "learning_rate": 0.00017801481199110163, "loss": 0.6746726512908936, "step": 153710 }, { "epoch": 0.9137436025464986, "grad_norm": 1.5175812244415283, "learning_rate": 0.00017801073525994002, "loss": 0.6127708911895752, "step": 153720 }, { "epoch": 0.913803044623167, "grad_norm": 1.365861415863037, "learning_rate": 0.00017800665820343726, "loss": 0.6626562118530274, "step": 153730 }, { "epoch": 0.9138624866998354, "grad_norm": 1.6768509149551392, "learning_rate": 0.00017800258082161289, "loss": 0.6214725494384765, "step": 153740 }, { "epoch": 0.9139219287765037, "grad_norm": 1.4985450506210327, "learning_rate": 0.00017799850311448642, "loss": 0.6779058456420899, "step": 153750 }, { "epoch": 0.9139813708531721, "grad_norm": 1.8162081241607666, "learning_rate": 0.00017799442508207734, "loss": 0.6806446552276612, "step": 153760 }, { "epoch": 0.9140408129298405, "grad_norm": 1.6225632429122925, "learning_rate": 0.00017799034672440512, "loss": 0.6583134651184082, "step": 153770 }, { "epoch": 0.9141002550065089, "grad_norm": 1.564742922782898, "learning_rate": 0.0001779862680414893, "loss": 0.7043580055236817, "step": 153780 }, { "epoch": 0.9141596970831773, "grad_norm": 9.797492027282715, "learning_rate": 0.0001779821890333494, "loss": 0.5616438865661622, "step": 153790 }, { "epoch": 0.9142191391598457, "grad_norm": 1.7523850202560425, "learning_rate": 0.0001779781097000049, "loss": 0.6675126075744628, "step": 153800 }, { "epoch": 0.9142785812365141, "grad_norm": 1.4083616733551025, "learning_rate": 0.0001779740300414754, "loss": 0.6123520851135253, "step": 153810 }, { "epoch": 0.9143380233131825, "grad_norm": 1.7148183584213257, "learning_rate": 0.0001779699500577803, "loss": 0.6111618518829346, "step": 153820 }, { "epoch": 0.9143974653898509, "grad_norm": 1.7046414613723755, "learning_rate": 0.00017796586974893916, "loss": 0.6534539699554444, "step": 153830 }, { "epoch": 0.9144569074665192, "grad_norm": 2.227260112762451, "learning_rate": 0.00017796178911497155, "loss": 0.6396225452423095, "step": 153840 }, { "epoch": 0.9145163495431876, "grad_norm": 1.261218547821045, "learning_rate": 0.00017795770815589695, "loss": 0.6448719024658203, "step": 153850 }, { "epoch": 0.914575791619856, "grad_norm": 1.7643975019454956, "learning_rate": 0.00017795362687173487, "loss": 0.6284379959106445, "step": 153860 }, { "epoch": 0.9146352336965244, "grad_norm": 1.7614521980285645, "learning_rate": 0.00017794954526250488, "loss": 0.6635374069213867, "step": 153870 }, { "epoch": 0.9146946757731929, "grad_norm": 1.1879093647003174, "learning_rate": 0.00017794546332822642, "loss": 0.6425508975982666, "step": 153880 }, { "epoch": 0.9147541178498612, "grad_norm": 1.3881675004959106, "learning_rate": 0.00017794138106891908, "loss": 0.6622400283813477, "step": 153890 }, { "epoch": 0.9148135599265296, "grad_norm": 1.4280146360397339, "learning_rate": 0.00017793729848460238, "loss": 0.6357813358306885, "step": 153900 }, { "epoch": 0.914873002003198, "grad_norm": 1.721117615699768, "learning_rate": 0.00017793321557529586, "loss": 0.6903761386871338, "step": 153910 }, { "epoch": 0.9149324440798664, "grad_norm": 1.8635120391845703, "learning_rate": 0.000177929132341019, "loss": 0.6506927013397217, "step": 153920 }, { "epoch": 0.9149918861565348, "grad_norm": 1.6803689002990723, "learning_rate": 0.0001779250487817914, "loss": 0.6911895275115967, "step": 153930 }, { "epoch": 0.9150513282332031, "grad_norm": 1.7967885732650757, "learning_rate": 0.00017792096489763258, "loss": 0.6480675220489502, "step": 153940 }, { "epoch": 0.9151107703098715, "grad_norm": 1.719879388809204, "learning_rate": 0.00017791688068856206, "loss": 0.6511367797851563, "step": 153950 }, { "epoch": 0.91517021238654, "grad_norm": 1.322422742843628, "learning_rate": 0.00017791279615459935, "loss": 0.6074562072753906, "step": 153960 }, { "epoch": 0.9152296544632084, "grad_norm": 1.5374810695648193, "learning_rate": 0.00017790871129576402, "loss": 0.5734367847442627, "step": 153970 }, { "epoch": 0.9152890965398767, "grad_norm": 1.5703397989273071, "learning_rate": 0.00017790462611207565, "loss": 0.5807117938995361, "step": 153980 }, { "epoch": 0.9153485386165451, "grad_norm": 1.4619946479797363, "learning_rate": 0.0001779005406035537, "loss": 0.6402132034301757, "step": 153990 }, { "epoch": 0.9154079806932135, "grad_norm": 1.7974543571472168, "learning_rate": 0.00017789645477021775, "loss": 0.6396834373474121, "step": 154000 }, { "epoch": 0.9154674227698819, "grad_norm": 1.7086387872695923, "learning_rate": 0.00017789236861208736, "loss": 0.6575494766235351, "step": 154010 }, { "epoch": 0.9155268648465503, "grad_norm": 1.6512638330459595, "learning_rate": 0.00017788828212918207, "loss": 0.6008180141448974, "step": 154020 }, { "epoch": 0.9155863069232186, "grad_norm": 1.5524593591690063, "learning_rate": 0.00017788419532152144, "loss": 0.6884288787841797, "step": 154030 }, { "epoch": 0.915645748999887, "grad_norm": 1.7793947458267212, "learning_rate": 0.00017788010818912495, "loss": 0.6235215187072753, "step": 154040 }, { "epoch": 0.9157051910765555, "grad_norm": 1.636338233947754, "learning_rate": 0.00017787602073201226, "loss": 0.6154661178588867, "step": 154050 }, { "epoch": 0.9157646331532239, "grad_norm": 1.6653003692626953, "learning_rate": 0.00017787193295020287, "loss": 0.6261874675750733, "step": 154060 }, { "epoch": 0.9158240752298922, "grad_norm": 1.715206265449524, "learning_rate": 0.0001778678448437163, "loss": 0.6928329467773438, "step": 154070 }, { "epoch": 0.9158835173065606, "grad_norm": 1.3892607688903809, "learning_rate": 0.00017786375641257215, "loss": 0.5881043434143066, "step": 154080 }, { "epoch": 0.915942959383229, "grad_norm": 1.6030962467193604, "learning_rate": 0.00017785966765678998, "loss": 0.6950940132141114, "step": 154090 }, { "epoch": 0.9160024014598974, "grad_norm": 1.4679145812988281, "learning_rate": 0.00017785557857638934, "loss": 0.6056282043457031, "step": 154100 }, { "epoch": 0.9160618435365658, "grad_norm": 1.8776981830596924, "learning_rate": 0.00017785148917138973, "loss": 0.7015481472015381, "step": 154110 }, { "epoch": 0.9161212856132341, "grad_norm": 2.0385262966156006, "learning_rate": 0.00017784739944181084, "loss": 0.6751156806945801, "step": 154120 }, { "epoch": 0.9161807276899026, "grad_norm": 1.4519660472869873, "learning_rate": 0.00017784330938767212, "loss": 0.6494344234466553, "step": 154130 }, { "epoch": 0.916240169766571, "grad_norm": 2.0323808193206787, "learning_rate": 0.0001778392190089932, "loss": 0.6470050811767578, "step": 154140 }, { "epoch": 0.9162996118432394, "grad_norm": 1.6531716585159302, "learning_rate": 0.00017783512830579364, "loss": 0.61842360496521, "step": 154150 }, { "epoch": 0.9163590539199078, "grad_norm": 1.8760943412780762, "learning_rate": 0.00017783103727809298, "loss": 0.6342989444732666, "step": 154160 }, { "epoch": 0.9164184959965761, "grad_norm": 1.5723648071289062, "learning_rate": 0.00017782694592591083, "loss": 0.6640353202819824, "step": 154170 }, { "epoch": 0.9164779380732445, "grad_norm": 1.6610409021377563, "learning_rate": 0.00017782285424926668, "loss": 0.6045077323913575, "step": 154180 }, { "epoch": 0.9165373801499129, "grad_norm": 1.9716131687164307, "learning_rate": 0.0001778187622481802, "loss": 0.6283860683441163, "step": 154190 }, { "epoch": 0.9165968222265813, "grad_norm": 1.9100773334503174, "learning_rate": 0.00017781466992267093, "loss": 0.6319883823394775, "step": 154200 }, { "epoch": 0.9166562643032496, "grad_norm": 1.7612814903259277, "learning_rate": 0.00017781057727275844, "loss": 0.6413628578186035, "step": 154210 }, { "epoch": 0.9167157063799181, "grad_norm": 2.0460968017578125, "learning_rate": 0.0001778064842984623, "loss": 0.6591511726379394, "step": 154220 }, { "epoch": 0.9167751484565865, "grad_norm": 1.4336987733840942, "learning_rate": 0.0001778023909998021, "loss": 0.6108007431030273, "step": 154230 }, { "epoch": 0.9168345905332549, "grad_norm": 1.6861318349838257, "learning_rate": 0.00017779829737679738, "loss": 0.6518090248107911, "step": 154240 }, { "epoch": 0.9168940326099233, "grad_norm": 1.3378946781158447, "learning_rate": 0.0001777942034294678, "loss": 0.6420144081115723, "step": 154250 }, { "epoch": 0.9169534746865916, "grad_norm": 1.8089412450790405, "learning_rate": 0.0001777901091578329, "loss": 0.6185243129730225, "step": 154260 }, { "epoch": 0.91701291676326, "grad_norm": 1.5798234939575195, "learning_rate": 0.00017778601456191229, "loss": 0.6248186111450196, "step": 154270 }, { "epoch": 0.9170723588399284, "grad_norm": 1.4928902387619019, "learning_rate": 0.00017778191964172552, "loss": 0.6843447685241699, "step": 154280 }, { "epoch": 0.9171318009165969, "grad_norm": 1.7087503671646118, "learning_rate": 0.00017777782439729221, "loss": 0.6263656616210938, "step": 154290 }, { "epoch": 0.9171912429932653, "grad_norm": 1.375497579574585, "learning_rate": 0.00017777372882863193, "loss": 0.6645969390869141, "step": 154300 }, { "epoch": 0.9172506850699336, "grad_norm": 1.5300326347351074, "learning_rate": 0.00017776963293576428, "loss": 0.672311544418335, "step": 154310 }, { "epoch": 0.917310127146602, "grad_norm": 1.4487056732177734, "learning_rate": 0.00017776553671870887, "loss": 0.6436755180358886, "step": 154320 }, { "epoch": 0.9173695692232704, "grad_norm": 1.562957763671875, "learning_rate": 0.00017776144017748525, "loss": 0.630064058303833, "step": 154330 }, { "epoch": 0.9174290112999388, "grad_norm": 1.7583563327789307, "learning_rate": 0.00017775734331211304, "loss": 0.6510621070861816, "step": 154340 }, { "epoch": 0.9174884533766071, "grad_norm": 1.4522379636764526, "learning_rate": 0.00017775324612261188, "loss": 0.6352427482604981, "step": 154350 }, { "epoch": 0.9175478954532755, "grad_norm": 1.4220951795578003, "learning_rate": 0.00017774914860900132, "loss": 0.6733895301818847, "step": 154360 }, { "epoch": 0.917607337529944, "grad_norm": 1.7627277374267578, "learning_rate": 0.00017774505077130094, "loss": 0.6915123939514161, "step": 154370 }, { "epoch": 0.9176667796066124, "grad_norm": 1.6752920150756836, "learning_rate": 0.00017774095260953042, "loss": 0.6894668579101563, "step": 154380 }, { "epoch": 0.9177262216832808, "grad_norm": 1.6640276908874512, "learning_rate": 0.0001777368541237093, "loss": 0.6610663414001465, "step": 154390 }, { "epoch": 0.9177856637599491, "grad_norm": 1.693528413772583, "learning_rate": 0.0001777327553138572, "loss": 0.6651149749755859, "step": 154400 }, { "epoch": 0.9178451058366175, "grad_norm": 1.8121979236602783, "learning_rate": 0.00017772865617999374, "loss": 0.634359884262085, "step": 154410 }, { "epoch": 0.9179045479132859, "grad_norm": 1.4106017351150513, "learning_rate": 0.00017772455672213856, "loss": 0.746005630493164, "step": 154420 }, { "epoch": 0.9179639899899543, "grad_norm": 1.8268606662750244, "learning_rate": 0.0001777204569403112, "loss": 0.6807194232940674, "step": 154430 }, { "epoch": 0.9180234320666226, "grad_norm": 1.4576208591461182, "learning_rate": 0.0001777163568345313, "loss": 0.6602503299713135, "step": 154440 }, { "epoch": 0.918082874143291, "grad_norm": 1.2979848384857178, "learning_rate": 0.00017771225640481845, "loss": 0.6993535041809082, "step": 154450 }, { "epoch": 0.9181423162199595, "grad_norm": 1.34938645362854, "learning_rate": 0.00017770815565119235, "loss": 0.7123616218566895, "step": 154460 }, { "epoch": 0.9182017582966279, "grad_norm": 1.435014009475708, "learning_rate": 0.00017770405457367253, "loss": 0.6510814666748047, "step": 154470 }, { "epoch": 0.9182612003732963, "grad_norm": 1.7329007387161255, "learning_rate": 0.00017769995317227865, "loss": 0.6464740753173828, "step": 154480 }, { "epoch": 0.9183206424499646, "grad_norm": 1.4344955682754517, "learning_rate": 0.00017769585144703033, "loss": 0.6501181125640869, "step": 154490 }, { "epoch": 0.918380084526633, "grad_norm": 1.4208552837371826, "learning_rate": 0.00017769174939794716, "loss": 0.6753514289855957, "step": 154500 }, { "epoch": 0.9184395266033014, "grad_norm": 1.740007758140564, "learning_rate": 0.00017768764702504877, "loss": 0.6515357017517089, "step": 154510 }, { "epoch": 0.9184989686799698, "grad_norm": 1.3833727836608887, "learning_rate": 0.00017768354432835484, "loss": 0.6397313117980957, "step": 154520 }, { "epoch": 0.9185584107566382, "grad_norm": 1.5210167169570923, "learning_rate": 0.0001776794413078849, "loss": 0.6584722518920898, "step": 154530 }, { "epoch": 0.9186178528333065, "grad_norm": 1.5480220317840576, "learning_rate": 0.00017767533796365868, "loss": 0.706492567062378, "step": 154540 }, { "epoch": 0.918677294909975, "grad_norm": 1.373142957687378, "learning_rate": 0.00017767123429569573, "loss": 0.6233969688415527, "step": 154550 }, { "epoch": 0.9187367369866434, "grad_norm": 1.4093327522277832, "learning_rate": 0.0001776671303040157, "loss": 0.6615443229675293, "step": 154560 }, { "epoch": 0.9187961790633118, "grad_norm": 1.419685959815979, "learning_rate": 0.0001776630259886383, "loss": 0.6475800514221192, "step": 154570 }, { "epoch": 0.9188556211399801, "grad_norm": 1.155793309211731, "learning_rate": 0.00017765892134958305, "loss": 0.6327549934387207, "step": 154580 }, { "epoch": 0.9189150632166485, "grad_norm": 1.1677972078323364, "learning_rate": 0.0001776548163868696, "loss": 0.628855037689209, "step": 154590 }, { "epoch": 0.9189745052933169, "grad_norm": 2.1414098739624023, "learning_rate": 0.00017765071110051764, "loss": 0.6397336959838867, "step": 154600 }, { "epoch": 0.9190339473699853, "grad_norm": 1.2225180864334106, "learning_rate": 0.00017764660549054683, "loss": 0.5777270317077636, "step": 154610 }, { "epoch": 0.9190933894466538, "grad_norm": 2.0225517749786377, "learning_rate": 0.00017764249955697672, "loss": 0.6488096237182617, "step": 154620 }, { "epoch": 0.9191528315233221, "grad_norm": 1.409829020500183, "learning_rate": 0.000177638393299827, "loss": 0.646731185913086, "step": 154630 }, { "epoch": 0.9192122735999905, "grad_norm": 1.7383536100387573, "learning_rate": 0.00017763428671911733, "loss": 0.6163826942443847, "step": 154640 }, { "epoch": 0.9192717156766589, "grad_norm": 1.4649757146835327, "learning_rate": 0.0001776301798148673, "loss": 0.6270287036895752, "step": 154650 }, { "epoch": 0.9193311577533273, "grad_norm": 1.4002692699432373, "learning_rate": 0.00017762607258709664, "loss": 0.6634212493896484, "step": 154660 }, { "epoch": 0.9193905998299957, "grad_norm": 1.5803630352020264, "learning_rate": 0.00017762196503582495, "loss": 0.6069465637207031, "step": 154670 }, { "epoch": 0.919450041906664, "grad_norm": 2.113283634185791, "learning_rate": 0.00017761785716107183, "loss": 0.7111055850982666, "step": 154680 }, { "epoch": 0.9195094839833324, "grad_norm": 1.7694591283798218, "learning_rate": 0.000177613748962857, "loss": 0.6324992179870605, "step": 154690 }, { "epoch": 0.9195689260600008, "grad_norm": 1.2526116371154785, "learning_rate": 0.00017760964044120009, "loss": 0.6308675289154053, "step": 154700 }, { "epoch": 0.9196283681366693, "grad_norm": 1.5806256532669067, "learning_rate": 0.00017760553159612078, "loss": 0.6331067562103272, "step": 154710 }, { "epoch": 0.9196878102133376, "grad_norm": 1.4166666269302368, "learning_rate": 0.00017760142242763865, "loss": 0.6596575736999511, "step": 154720 }, { "epoch": 0.919747252290006, "grad_norm": 1.3909884691238403, "learning_rate": 0.00017759731293577347, "loss": 0.6513827323913575, "step": 154730 }, { "epoch": 0.9198066943666744, "grad_norm": 1.4586607217788696, "learning_rate": 0.0001775932031205448, "loss": 0.6326919555664062, "step": 154740 }, { "epoch": 0.9198661364433428, "grad_norm": 1.5892966985702515, "learning_rate": 0.00017758909298197232, "loss": 0.6746665477752686, "step": 154750 }, { "epoch": 0.9199255785200112, "grad_norm": 1.7229669094085693, "learning_rate": 0.00017758498252007574, "loss": 0.6236494541168213, "step": 154760 }, { "epoch": 0.9199850205966795, "grad_norm": 1.613550066947937, "learning_rate": 0.00017758087173487468, "loss": 0.6243947982788086, "step": 154770 }, { "epoch": 0.9200444626733479, "grad_norm": 1.8757615089416504, "learning_rate": 0.00017757676062638881, "loss": 0.6662903785705566, "step": 154780 }, { "epoch": 0.9201039047500164, "grad_norm": 1.2521822452545166, "learning_rate": 0.0001775726491946378, "loss": 0.6118258476257324, "step": 154790 }, { "epoch": 0.9201633468266848, "grad_norm": 1.1547696590423584, "learning_rate": 0.0001775685374396413, "loss": 0.5733818531036377, "step": 154800 }, { "epoch": 0.9202227889033531, "grad_norm": 1.3683198690414429, "learning_rate": 0.00017756442536141906, "loss": 0.6489787101745605, "step": 154810 }, { "epoch": 0.9202822309800215, "grad_norm": 1.7425819635391235, "learning_rate": 0.00017756031295999066, "loss": 0.6163700103759766, "step": 154820 }, { "epoch": 0.9203416730566899, "grad_norm": 1.889890432357788, "learning_rate": 0.00017755620023537577, "loss": 0.6054740905761719, "step": 154830 }, { "epoch": 0.9204011151333583, "grad_norm": 1.4565120935440063, "learning_rate": 0.00017755208718759412, "loss": 0.6011407375335693, "step": 154840 }, { "epoch": 0.9204605572100267, "grad_norm": 1.4192326068878174, "learning_rate": 0.0001775479738166654, "loss": 0.6391668319702148, "step": 154850 }, { "epoch": 0.920519999286695, "grad_norm": 1.5847077369689941, "learning_rate": 0.0001775438601226092, "loss": 0.638033390045166, "step": 154860 }, { "epoch": 0.9205794413633634, "grad_norm": 1.7534359693527222, "learning_rate": 0.00017753974610544527, "loss": 0.6250860691070557, "step": 154870 }, { "epoch": 0.9206388834400319, "grad_norm": 1.5700289011001587, "learning_rate": 0.00017753563176519323, "loss": 0.6387577056884766, "step": 154880 }, { "epoch": 0.9206983255167003, "grad_norm": 1.5981674194335938, "learning_rate": 0.0001775315171018728, "loss": 0.6345202922821045, "step": 154890 }, { "epoch": 0.9207577675933687, "grad_norm": 1.7905235290527344, "learning_rate": 0.0001775274021155037, "loss": 0.6468422889709473, "step": 154900 }, { "epoch": 0.920817209670037, "grad_norm": 1.2623200416564941, "learning_rate": 0.00017752328680610557, "loss": 0.7053131103515625, "step": 154910 }, { "epoch": 0.9208766517467054, "grad_norm": 2.0346744060516357, "learning_rate": 0.00017751917117369808, "loss": 0.675958251953125, "step": 154920 }, { "epoch": 0.9209360938233738, "grad_norm": 1.7959178686141968, "learning_rate": 0.00017751505521830096, "loss": 0.6503415107727051, "step": 154930 }, { "epoch": 0.9209955359000422, "grad_norm": 1.6415138244628906, "learning_rate": 0.00017751093893993386, "loss": 0.5795514106750488, "step": 154940 }, { "epoch": 0.9210549779767105, "grad_norm": 1.830171823501587, "learning_rate": 0.00017750682233861652, "loss": 0.6880292892456055, "step": 154950 }, { "epoch": 0.921114420053379, "grad_norm": 1.405240774154663, "learning_rate": 0.00017750270541436858, "loss": 0.651776123046875, "step": 154960 }, { "epoch": 0.9211738621300474, "grad_norm": 1.6891378164291382, "learning_rate": 0.00017749858816720976, "loss": 0.6948511123657226, "step": 154970 }, { "epoch": 0.9212333042067158, "grad_norm": 2.2274508476257324, "learning_rate": 0.00017749447059715978, "loss": 0.664369010925293, "step": 154980 }, { "epoch": 0.9212927462833842, "grad_norm": 1.8036260604858398, "learning_rate": 0.00017749035270423828, "loss": 0.6722659111022949, "step": 154990 }, { "epoch": 0.9213521883600525, "grad_norm": 1.9987910985946655, "learning_rate": 0.00017748623448846497, "loss": 0.6818530559539795, "step": 155000 }, { "epoch": 0.9214116304367209, "grad_norm": 1.7232333421707153, "learning_rate": 0.0001774821159498596, "loss": 0.6128194808959961, "step": 155010 }, { "epoch": 0.9214710725133893, "grad_norm": 1.7655277252197266, "learning_rate": 0.00017747799708844184, "loss": 0.6430553913116455, "step": 155020 }, { "epoch": 0.9215305145900577, "grad_norm": 2.069371223449707, "learning_rate": 0.00017747387790423137, "loss": 0.6359456539154053, "step": 155030 }, { "epoch": 0.9215899566667262, "grad_norm": 1.4591114521026611, "learning_rate": 0.00017746975839724797, "loss": 0.6058870315551758, "step": 155040 }, { "epoch": 0.9216493987433945, "grad_norm": 1.7357481718063354, "learning_rate": 0.00017746563856751126, "loss": 0.5885905265808106, "step": 155050 }, { "epoch": 0.9217088408200629, "grad_norm": 1.8162649869918823, "learning_rate": 0.000177461518415041, "loss": 0.644656753540039, "step": 155060 }, { "epoch": 0.9217682828967313, "grad_norm": 1.269338846206665, "learning_rate": 0.00017745739793985688, "loss": 0.6007522106170654, "step": 155070 }, { "epoch": 0.9218277249733997, "grad_norm": 1.5785107612609863, "learning_rate": 0.00017745327714197858, "loss": 0.6642367362976074, "step": 155080 }, { "epoch": 0.921887167050068, "grad_norm": 1.899186372756958, "learning_rate": 0.00017744915602142586, "loss": 0.6400649070739746, "step": 155090 }, { "epoch": 0.9219466091267364, "grad_norm": 1.566437005996704, "learning_rate": 0.00017744503457821847, "loss": 0.6733440399169922, "step": 155100 }, { "epoch": 0.9220060512034048, "grad_norm": 1.8936349153518677, "learning_rate": 0.00017744091281237601, "loss": 0.6950504302978515, "step": 155110 }, { "epoch": 0.9220654932800733, "grad_norm": 1.6808993816375732, "learning_rate": 0.0001774367907239183, "loss": 0.6548844337463379, "step": 155120 }, { "epoch": 0.9221249353567417, "grad_norm": 1.8959376811981201, "learning_rate": 0.000177432668312865, "loss": 0.6452834606170654, "step": 155130 }, { "epoch": 0.92218437743341, "grad_norm": 1.2886874675750732, "learning_rate": 0.00017742854557923585, "loss": 0.64976487159729, "step": 155140 }, { "epoch": 0.9222438195100784, "grad_norm": 2.1707191467285156, "learning_rate": 0.0001774244225230506, "loss": 0.6863746643066406, "step": 155150 }, { "epoch": 0.9223032615867468, "grad_norm": 1.6149141788482666, "learning_rate": 0.00017742029914432893, "loss": 0.5949841499328613, "step": 155160 }, { "epoch": 0.9223627036634152, "grad_norm": 1.4101356267929077, "learning_rate": 0.0001774161754430906, "loss": 0.6586935520172119, "step": 155170 }, { "epoch": 0.9224221457400835, "grad_norm": 1.7071274518966675, "learning_rate": 0.0001774120514193553, "loss": 0.6562385559082031, "step": 155180 }, { "epoch": 0.9224815878167519, "grad_norm": 2.069526195526123, "learning_rate": 0.00017740792707314279, "loss": 0.6618785858154297, "step": 155190 }, { "epoch": 0.9225410298934204, "grad_norm": 1.554707407951355, "learning_rate": 0.00017740380240447275, "loss": 0.683591651916504, "step": 155200 }, { "epoch": 0.9226004719700888, "grad_norm": 1.917725682258606, "learning_rate": 0.00017739967741336497, "loss": 0.6725998878479004, "step": 155210 }, { "epoch": 0.9226599140467572, "grad_norm": 1.5162899494171143, "learning_rate": 0.00017739555209983916, "loss": 0.5694647789001465, "step": 155220 }, { "epoch": 0.9227193561234255, "grad_norm": 1.8376070261001587, "learning_rate": 0.00017739142646391507, "loss": 0.617570161819458, "step": 155230 }, { "epoch": 0.9227787982000939, "grad_norm": 1.1593519449234009, "learning_rate": 0.00017738730050561243, "loss": 0.6098592281341553, "step": 155240 }, { "epoch": 0.9228382402767623, "grad_norm": 1.545443058013916, "learning_rate": 0.00017738317422495093, "loss": 0.6890956878662109, "step": 155250 }, { "epoch": 0.9228976823534307, "grad_norm": 1.8921600580215454, "learning_rate": 0.00017737904762195038, "loss": 0.6103687286376953, "step": 155260 }, { "epoch": 0.9229571244300991, "grad_norm": 1.7857798337936401, "learning_rate": 0.00017737492069663045, "loss": 0.7113494873046875, "step": 155270 }, { "epoch": 0.9230165665067674, "grad_norm": 1.626415729522705, "learning_rate": 0.00017737079344901094, "loss": 0.6718181610107422, "step": 155280 }, { "epoch": 0.9230760085834359, "grad_norm": 1.4059449434280396, "learning_rate": 0.00017736666587911154, "loss": 0.6752483367919921, "step": 155290 }, { "epoch": 0.9231354506601043, "grad_norm": 1.4530105590820312, "learning_rate": 0.00017736253798695205, "loss": 0.6494924545288085, "step": 155300 }, { "epoch": 0.9231948927367727, "grad_norm": 1.230546474456787, "learning_rate": 0.0001773584097725522, "loss": 0.6581499576568604, "step": 155310 }, { "epoch": 0.923254334813441, "grad_norm": 1.5987401008605957, "learning_rate": 0.00017735428123593172, "loss": 0.636293888092041, "step": 155320 }, { "epoch": 0.9233137768901094, "grad_norm": 1.7031480073928833, "learning_rate": 0.0001773501523771104, "loss": 0.606314754486084, "step": 155330 }, { "epoch": 0.9233732189667778, "grad_norm": 1.8030396699905396, "learning_rate": 0.00017734602319610792, "loss": 0.655810546875, "step": 155340 }, { "epoch": 0.9234326610434462, "grad_norm": 1.4379451274871826, "learning_rate": 0.0001773418936929441, "loss": 0.6737090110778808, "step": 155350 }, { "epoch": 0.9234921031201146, "grad_norm": 1.3648831844329834, "learning_rate": 0.00017733776386763864, "loss": 0.668757152557373, "step": 155360 }, { "epoch": 0.923551545196783, "grad_norm": 2.4330732822418213, "learning_rate": 0.00017733363372021135, "loss": 0.6658172607421875, "step": 155370 }, { "epoch": 0.9236109872734514, "grad_norm": 1.4457272291183472, "learning_rate": 0.00017732950325068195, "loss": 0.6249374389648438, "step": 155380 }, { "epoch": 0.9236704293501198, "grad_norm": 1.1548465490341187, "learning_rate": 0.00017732537245907022, "loss": 0.6073409080505371, "step": 155390 }, { "epoch": 0.9237298714267882, "grad_norm": 1.6481889486312866, "learning_rate": 0.0001773212413453959, "loss": 0.6301457405090332, "step": 155400 }, { "epoch": 0.9237893135034566, "grad_norm": 2.2120771408081055, "learning_rate": 0.00017731710990967877, "loss": 0.6178979873657227, "step": 155410 }, { "epoch": 0.9238487555801249, "grad_norm": 1.8848965167999268, "learning_rate": 0.0001773129781519386, "loss": 0.5755285739898681, "step": 155420 }, { "epoch": 0.9239081976567933, "grad_norm": 1.6209354400634766, "learning_rate": 0.0001773088460721951, "loss": 0.6916313171386719, "step": 155430 }, { "epoch": 0.9239676397334617, "grad_norm": 1.3305261135101318, "learning_rate": 0.00017730471367046808, "loss": 0.5989933013916016, "step": 155440 }, { "epoch": 0.9240270818101302, "grad_norm": 1.541421890258789, "learning_rate": 0.00017730058094677734, "loss": 0.6731424331665039, "step": 155450 }, { "epoch": 0.9240865238867985, "grad_norm": 1.3624285459518433, "learning_rate": 0.0001772964479011426, "loss": 0.6545445442199707, "step": 155460 }, { "epoch": 0.9241459659634669, "grad_norm": 1.5395128726959229, "learning_rate": 0.00017729231453358362, "loss": 0.6243301391601562, "step": 155470 }, { "epoch": 0.9242054080401353, "grad_norm": 1.9161953926086426, "learning_rate": 0.00017728818084412025, "loss": 0.6947714805603027, "step": 155480 }, { "epoch": 0.9242648501168037, "grad_norm": 1.5922696590423584, "learning_rate": 0.0001772840468327722, "loss": 0.650178861618042, "step": 155490 }, { "epoch": 0.9243242921934721, "grad_norm": 1.5364627838134766, "learning_rate": 0.00017727991249955923, "loss": 0.7308900833129883, "step": 155500 }, { "epoch": 0.9243837342701404, "grad_norm": 1.9782190322875977, "learning_rate": 0.00017727577784450114, "loss": 0.6296195983886719, "step": 155510 }, { "epoch": 0.9244431763468088, "grad_norm": 1.7353050708770752, "learning_rate": 0.00017727164286761773, "loss": 0.637433385848999, "step": 155520 }, { "epoch": 0.9245026184234773, "grad_norm": 1.5397945642471313, "learning_rate": 0.00017726750756892875, "loss": 0.6670888900756836, "step": 155530 }, { "epoch": 0.9245620605001457, "grad_norm": 1.3854328393936157, "learning_rate": 0.00017726337194845407, "loss": 0.6571342945098877, "step": 155540 }, { "epoch": 0.924621502576814, "grad_norm": 1.430299997329712, "learning_rate": 0.00017725923600621333, "loss": 0.6582865715026855, "step": 155550 }, { "epoch": 0.9246809446534824, "grad_norm": 1.6121577024459839, "learning_rate": 0.0001772550997422264, "loss": 0.6615361213684082, "step": 155560 }, { "epoch": 0.9247403867301508, "grad_norm": 2.0556082725524902, "learning_rate": 0.00017725096315651307, "loss": 0.6758729934692382, "step": 155570 }, { "epoch": 0.9247998288068192, "grad_norm": 1.7587742805480957, "learning_rate": 0.0001772468262490931, "loss": 0.6224854946136474, "step": 155580 }, { "epoch": 0.9248592708834876, "grad_norm": 1.753352165222168, "learning_rate": 0.00017724268901998626, "loss": 0.699713945388794, "step": 155590 }, { "epoch": 0.9249187129601559, "grad_norm": 1.9607146978378296, "learning_rate": 0.0001772385514692124, "loss": 0.7101953506469727, "step": 155600 }, { "epoch": 0.9249781550368243, "grad_norm": 2.0854990482330322, "learning_rate": 0.00017723441359679127, "loss": 0.6638431549072266, "step": 155610 }, { "epoch": 0.9250375971134928, "grad_norm": 1.760528326034546, "learning_rate": 0.0001772302754027427, "loss": 0.6028553962707519, "step": 155620 }, { "epoch": 0.9250970391901612, "grad_norm": 1.7253220081329346, "learning_rate": 0.00017722613688708644, "loss": 0.6489587783813476, "step": 155630 }, { "epoch": 0.9251564812668296, "grad_norm": 1.5916354656219482, "learning_rate": 0.00017722199804984232, "loss": 0.6791521072387695, "step": 155640 }, { "epoch": 0.9252159233434979, "grad_norm": 1.9276976585388184, "learning_rate": 0.00017721785889103015, "loss": 0.6884130001068115, "step": 155650 }, { "epoch": 0.9252753654201663, "grad_norm": 1.3984521627426147, "learning_rate": 0.0001772137194106697, "loss": 0.6291725635528564, "step": 155660 }, { "epoch": 0.9253348074968347, "grad_norm": 1.6538677215576172, "learning_rate": 0.00017720957960878076, "loss": 0.6165709972381592, "step": 155670 }, { "epoch": 0.9253942495735031, "grad_norm": 1.7557882070541382, "learning_rate": 0.00017720543948538314, "loss": 0.5983972072601318, "step": 155680 }, { "epoch": 0.9254536916501714, "grad_norm": 1.4781012535095215, "learning_rate": 0.00017720129904049675, "loss": 0.5739823341369629, "step": 155690 }, { "epoch": 0.9255131337268399, "grad_norm": 1.3758856058120728, "learning_rate": 0.0001771971582741412, "loss": 0.6393595695495605, "step": 155700 }, { "epoch": 0.9255725758035083, "grad_norm": 1.812987208366394, "learning_rate": 0.00017719301718633647, "loss": 0.6310263633728027, "step": 155710 }, { "epoch": 0.9256320178801767, "grad_norm": 1.3295202255249023, "learning_rate": 0.00017718887577710229, "loss": 0.6314099311828614, "step": 155720 }, { "epoch": 0.9256914599568451, "grad_norm": 1.4280009269714355, "learning_rate": 0.00017718473404645848, "loss": 0.6591106414794922, "step": 155730 }, { "epoch": 0.9257509020335134, "grad_norm": 1.742224097251892, "learning_rate": 0.00017718059199442487, "loss": 0.7051119804382324, "step": 155740 }, { "epoch": 0.9258103441101818, "grad_norm": 1.3888028860092163, "learning_rate": 0.00017717644962102124, "loss": 0.6315282821655274, "step": 155750 }, { "epoch": 0.9258697861868502, "grad_norm": 1.7427436113357544, "learning_rate": 0.00017717230692626746, "loss": 0.6941740989685059, "step": 155760 }, { "epoch": 0.9259292282635186, "grad_norm": 1.3675888776779175, "learning_rate": 0.00017716816391018326, "loss": 0.6118121147155762, "step": 155770 }, { "epoch": 0.9259886703401871, "grad_norm": 1.5227082967758179, "learning_rate": 0.0001771640205727886, "loss": 0.7322641372680664, "step": 155780 }, { "epoch": 0.9260481124168554, "grad_norm": 1.5263696908950806, "learning_rate": 0.00017715987691410313, "loss": 0.6655549526214599, "step": 155790 }, { "epoch": 0.9261075544935238, "grad_norm": 1.5752105712890625, "learning_rate": 0.0001771557329341468, "loss": 0.6595058441162109, "step": 155800 }, { "epoch": 0.9261669965701922, "grad_norm": 1.7210814952850342, "learning_rate": 0.0001771515886329394, "loss": 0.7139510154724121, "step": 155810 }, { "epoch": 0.9262264386468606, "grad_norm": 1.4565739631652832, "learning_rate": 0.00017714744401050073, "loss": 0.7059412002563477, "step": 155820 }, { "epoch": 0.9262858807235289, "grad_norm": 1.4426378011703491, "learning_rate": 0.00017714329906685062, "loss": 0.6719279289245605, "step": 155830 }, { "epoch": 0.9263453228001973, "grad_norm": 1.4518991708755493, "learning_rate": 0.00017713915380200893, "loss": 0.6356112480163574, "step": 155840 }, { "epoch": 0.9264047648768657, "grad_norm": 1.8838446140289307, "learning_rate": 0.00017713500821599546, "loss": 0.6714784622192382, "step": 155850 }, { "epoch": 0.9264642069535342, "grad_norm": 1.3863118886947632, "learning_rate": 0.00017713086230883006, "loss": 0.5891629695892334, "step": 155860 }, { "epoch": 0.9265236490302026, "grad_norm": 1.3608980178833008, "learning_rate": 0.00017712671608053254, "loss": 0.6174107074737549, "step": 155870 }, { "epoch": 0.9265830911068709, "grad_norm": 1.6194199323654175, "learning_rate": 0.00017712256953112277, "loss": 0.6908685684204101, "step": 155880 }, { "epoch": 0.9266425331835393, "grad_norm": 1.2877784967422485, "learning_rate": 0.00017711842266062054, "loss": 0.6430728912353516, "step": 155890 }, { "epoch": 0.9267019752602077, "grad_norm": 2.040418863296509, "learning_rate": 0.00017711427546904568, "loss": 0.6501465797424316, "step": 155900 }, { "epoch": 0.9267614173368761, "grad_norm": 1.4063557386398315, "learning_rate": 0.0001771101279564181, "loss": 0.6026576042175293, "step": 155910 }, { "epoch": 0.9268208594135444, "grad_norm": 1.5359151363372803, "learning_rate": 0.0001771059801227576, "loss": 0.5660553932189941, "step": 155920 }, { "epoch": 0.9268803014902128, "grad_norm": 1.1965407133102417, "learning_rate": 0.00017710183196808404, "loss": 0.6556053161621094, "step": 155930 }, { "epoch": 0.9269397435668812, "grad_norm": 1.4011708498001099, "learning_rate": 0.00017709768349241723, "loss": 0.6577876091003418, "step": 155940 }, { "epoch": 0.9269991856435497, "grad_norm": 1.5433778762817383, "learning_rate": 0.00017709353469577701, "loss": 0.6927519321441651, "step": 155950 }, { "epoch": 0.9270586277202181, "grad_norm": 1.4138110876083374, "learning_rate": 0.00017708938557818327, "loss": 0.6412276268005371, "step": 155960 }, { "epoch": 0.9271180697968864, "grad_norm": 1.4054088592529297, "learning_rate": 0.00017708523613965582, "loss": 0.7254904270172119, "step": 155970 }, { "epoch": 0.9271775118735548, "grad_norm": 1.7259938716888428, "learning_rate": 0.00017708108638021453, "loss": 0.6003442764282226, "step": 155980 }, { "epoch": 0.9272369539502232, "grad_norm": 1.7255476713180542, "learning_rate": 0.00017707693629987923, "loss": 0.7604068756103516, "step": 155990 }, { "epoch": 0.9272963960268916, "grad_norm": 1.5793178081512451, "learning_rate": 0.0001770727858986698, "loss": 0.6044817447662354, "step": 156000 }, { "epoch": 0.92735583810356, "grad_norm": 1.7216198444366455, "learning_rate": 0.0001770686351766061, "loss": 0.6375372886657715, "step": 156010 }, { "epoch": 0.9274152801802283, "grad_norm": 1.2743180990219116, "learning_rate": 0.00017706448413370792, "loss": 0.6169322490692138, "step": 156020 }, { "epoch": 0.9274747222568968, "grad_norm": 1.3710745573043823, "learning_rate": 0.0001770603327699952, "loss": 0.6883150100708008, "step": 156030 }, { "epoch": 0.9275341643335652, "grad_norm": 1.5110195875167847, "learning_rate": 0.00017705618108548778, "loss": 0.6046935081481933, "step": 156040 }, { "epoch": 0.9275936064102336, "grad_norm": 1.5291860103607178, "learning_rate": 0.00017705202908020547, "loss": 0.6885058403015136, "step": 156050 }, { "epoch": 0.9276530484869019, "grad_norm": 1.7791762351989746, "learning_rate": 0.00017704787675416818, "loss": 0.6596889019012451, "step": 156060 }, { "epoch": 0.9277124905635703, "grad_norm": 1.829501748085022, "learning_rate": 0.00017704372410739575, "loss": 0.6451167583465576, "step": 156070 }, { "epoch": 0.9277719326402387, "grad_norm": 1.4484397172927856, "learning_rate": 0.00017703957113990808, "loss": 0.6213484764099121, "step": 156080 }, { "epoch": 0.9278313747169071, "grad_norm": 1.861250877380371, "learning_rate": 0.00017703541785172498, "loss": 0.6694112777709961, "step": 156090 }, { "epoch": 0.9278908167935755, "grad_norm": 1.5593044757843018, "learning_rate": 0.00017703126424286635, "loss": 0.7018509387969971, "step": 156100 }, { "epoch": 0.9279502588702438, "grad_norm": 1.8546563386917114, "learning_rate": 0.00017702711031335208, "loss": 0.6146669387817383, "step": 156110 }, { "epoch": 0.9280097009469123, "grad_norm": 1.6570900678634644, "learning_rate": 0.000177022956063202, "loss": 0.6642339706420899, "step": 156120 }, { "epoch": 0.9280691430235807, "grad_norm": 1.8080079555511475, "learning_rate": 0.000177018801492436, "loss": 0.6592236995697022, "step": 156130 }, { "epoch": 0.9281285851002491, "grad_norm": 1.4519778490066528, "learning_rate": 0.00017701464660107398, "loss": 0.6705069541931152, "step": 156140 }, { "epoch": 0.9281880271769175, "grad_norm": 1.6462552547454834, "learning_rate": 0.00017701049138913578, "loss": 0.6358520984649658, "step": 156150 }, { "epoch": 0.9282474692535858, "grad_norm": 2.1557226181030273, "learning_rate": 0.00017700633585664125, "loss": 0.7122605323791504, "step": 156160 }, { "epoch": 0.9283069113302542, "grad_norm": 1.5235276222229004, "learning_rate": 0.00017700218000361035, "loss": 0.6473265171051026, "step": 156170 }, { "epoch": 0.9283663534069226, "grad_norm": 1.3992077112197876, "learning_rate": 0.0001769980238300629, "loss": 0.6224258422851563, "step": 156180 }, { "epoch": 0.928425795483591, "grad_norm": 1.8499419689178467, "learning_rate": 0.00017699386733601883, "loss": 0.6705760002136231, "step": 156190 }, { "epoch": 0.9284852375602594, "grad_norm": 1.6785091161727905, "learning_rate": 0.00017698971052149798, "loss": 0.6383835315704346, "step": 156200 }, { "epoch": 0.9285446796369278, "grad_norm": 1.9828226566314697, "learning_rate": 0.00017698555338652023, "loss": 0.6917017936706543, "step": 156210 }, { "epoch": 0.9286041217135962, "grad_norm": 1.7029290199279785, "learning_rate": 0.00017698139593110547, "loss": 0.6810630798339844, "step": 156220 }, { "epoch": 0.9286635637902646, "grad_norm": 1.4908777475357056, "learning_rate": 0.00017697723815527364, "loss": 0.654494333267212, "step": 156230 }, { "epoch": 0.928723005866933, "grad_norm": 2.0457823276519775, "learning_rate": 0.00017697308005904457, "loss": 0.6526388168334961, "step": 156240 }, { "epoch": 0.9287824479436013, "grad_norm": 1.7719426155090332, "learning_rate": 0.00017696892164243818, "loss": 0.6698098659515381, "step": 156250 }, { "epoch": 0.9288418900202697, "grad_norm": 1.6469770669937134, "learning_rate": 0.00017696476290547436, "loss": 0.6360664367675781, "step": 156260 }, { "epoch": 0.9289013320969381, "grad_norm": 1.5972105264663696, "learning_rate": 0.00017696060384817297, "loss": 0.6102431297302247, "step": 156270 }, { "epoch": 0.9289607741736066, "grad_norm": 2.0033986568450928, "learning_rate": 0.00017695644447055398, "loss": 0.6893611907958984, "step": 156280 }, { "epoch": 0.9290202162502749, "grad_norm": 1.6974369287490845, "learning_rate": 0.00017695228477263722, "loss": 0.6999212265014648, "step": 156290 }, { "epoch": 0.9290796583269433, "grad_norm": 1.6496554613113403, "learning_rate": 0.00017694812475444258, "loss": 0.6175393104553223, "step": 156300 }, { "epoch": 0.9291391004036117, "grad_norm": 1.7928153276443481, "learning_rate": 0.00017694396441599, "loss": 0.6395028591156006, "step": 156310 }, { "epoch": 0.9291985424802801, "grad_norm": 1.525407075881958, "learning_rate": 0.0001769398037572994, "loss": 0.6877051830291748, "step": 156320 }, { "epoch": 0.9292579845569485, "grad_norm": 1.7243549823760986, "learning_rate": 0.00017693564277839063, "loss": 0.594975471496582, "step": 156330 }, { "epoch": 0.9293174266336168, "grad_norm": 1.8942201137542725, "learning_rate": 0.00017693148147928365, "loss": 0.671910285949707, "step": 156340 }, { "epoch": 0.9293768687102852, "grad_norm": 1.4125258922576904, "learning_rate": 0.0001769273198599983, "loss": 0.6664317607879638, "step": 156350 }, { "epoch": 0.9294363107869537, "grad_norm": 1.6758309602737427, "learning_rate": 0.00017692315792055456, "loss": 0.6048237323760987, "step": 156360 }, { "epoch": 0.9294957528636221, "grad_norm": 2.0045688152313232, "learning_rate": 0.00017691899566097226, "loss": 0.6602723121643066, "step": 156370 }, { "epoch": 0.9295551949402905, "grad_norm": 1.7026500701904297, "learning_rate": 0.0001769148330812714, "loss": 0.6612692832946777, "step": 156380 }, { "epoch": 0.9296146370169588, "grad_norm": 1.5728423595428467, "learning_rate": 0.00017691067018147183, "loss": 0.64857177734375, "step": 156390 }, { "epoch": 0.9296740790936272, "grad_norm": 1.8618395328521729, "learning_rate": 0.00017690650696159345, "loss": 0.6692344665527343, "step": 156400 }, { "epoch": 0.9297335211702956, "grad_norm": 1.4784420728683472, "learning_rate": 0.00017690234342165623, "loss": 0.7028416156768799, "step": 156410 }, { "epoch": 0.929792963246964, "grad_norm": 1.714619755744934, "learning_rate": 0.00017689817956168007, "loss": 0.6309877395629883, "step": 156420 }, { "epoch": 0.9298524053236323, "grad_norm": 1.5036392211914062, "learning_rate": 0.0001768940153816849, "loss": 0.6697288036346436, "step": 156430 }, { "epoch": 0.9299118474003008, "grad_norm": 1.6193286180496216, "learning_rate": 0.00017688985088169058, "loss": 0.6405314922332763, "step": 156440 }, { "epoch": 0.9299712894769692, "grad_norm": 1.5558117628097534, "learning_rate": 0.0001768856860617171, "loss": 0.6532240390777588, "step": 156450 }, { "epoch": 0.9300307315536376, "grad_norm": 1.6346795558929443, "learning_rate": 0.00017688152092178435, "loss": 0.6663708686828613, "step": 156460 }, { "epoch": 0.930090173630306, "grad_norm": 2.0435845851898193, "learning_rate": 0.00017687735546191225, "loss": 0.6503765106201171, "step": 156470 }, { "epoch": 0.9301496157069743, "grad_norm": 1.500591516494751, "learning_rate": 0.00017687318968212073, "loss": 0.6346067428588867, "step": 156480 }, { "epoch": 0.9302090577836427, "grad_norm": 1.520128846168518, "learning_rate": 0.00017686902358242975, "loss": 0.6257962703704834, "step": 156490 }, { "epoch": 0.9302684998603111, "grad_norm": 1.785520315170288, "learning_rate": 0.0001768648571628592, "loss": 0.7030631065368652, "step": 156500 }, { "epoch": 0.9303279419369795, "grad_norm": 1.8782168626785278, "learning_rate": 0.00017686069042342902, "loss": 0.6381672859191895, "step": 156510 }, { "epoch": 0.930387384013648, "grad_norm": 1.9371033906936646, "learning_rate": 0.00017685652336415917, "loss": 0.6863005638122559, "step": 156520 }, { "epoch": 0.9304468260903163, "grad_norm": 1.2146306037902832, "learning_rate": 0.00017685235598506954, "loss": 0.5525583744049072, "step": 156530 }, { "epoch": 0.9305062681669847, "grad_norm": 1.7601343393325806, "learning_rate": 0.00017684818828618012, "loss": 0.7134056091308594, "step": 156540 }, { "epoch": 0.9305657102436531, "grad_norm": 1.6854859590530396, "learning_rate": 0.00017684402026751076, "loss": 0.6112388134002685, "step": 156550 }, { "epoch": 0.9306251523203215, "grad_norm": 1.8110363483428955, "learning_rate": 0.0001768398519290815, "loss": 0.6670153617858887, "step": 156560 }, { "epoch": 0.9306845943969898, "grad_norm": 1.7003979682922363, "learning_rate": 0.00017683568327091223, "loss": 0.6953522682189941, "step": 156570 }, { "epoch": 0.9307440364736582, "grad_norm": 1.2193046808242798, "learning_rate": 0.00017683151429302284, "loss": 0.6167755126953125, "step": 156580 }, { "epoch": 0.9308034785503266, "grad_norm": 1.3186933994293213, "learning_rate": 0.00017682734499543338, "loss": 0.6419598579406738, "step": 156590 }, { "epoch": 0.930862920626995, "grad_norm": 1.4906524419784546, "learning_rate": 0.00017682317537816373, "loss": 0.606442928314209, "step": 156600 }, { "epoch": 0.9309223627036635, "grad_norm": 1.6010146141052246, "learning_rate": 0.0001768190054412338, "loss": 0.643953514099121, "step": 156610 }, { "epoch": 0.9309818047803318, "grad_norm": 1.353424310684204, "learning_rate": 0.00017681483518466366, "loss": 0.576329517364502, "step": 156620 }, { "epoch": 0.9310412468570002, "grad_norm": 1.8004767894744873, "learning_rate": 0.00017681066460847314, "loss": 0.6820932388305664, "step": 156630 }, { "epoch": 0.9311006889336686, "grad_norm": 1.610526204109192, "learning_rate": 0.00017680649371268223, "loss": 0.6719552040100097, "step": 156640 }, { "epoch": 0.931160131010337, "grad_norm": 1.8736634254455566, "learning_rate": 0.0001768023224973109, "loss": 0.583377742767334, "step": 156650 }, { "epoch": 0.9312195730870053, "grad_norm": 1.3038877248764038, "learning_rate": 0.00017679815096237908, "loss": 0.6855063438415527, "step": 156660 }, { "epoch": 0.9312790151636737, "grad_norm": 1.6917541027069092, "learning_rate": 0.00017679397910790677, "loss": 0.7160072326660156, "step": 156670 }, { "epoch": 0.9313384572403421, "grad_norm": 2.029290199279785, "learning_rate": 0.00017678980693391387, "loss": 0.6909170150756836, "step": 156680 }, { "epoch": 0.9313978993170106, "grad_norm": 1.5008529424667358, "learning_rate": 0.00017678563444042033, "loss": 0.647001314163208, "step": 156690 }, { "epoch": 0.931457341393679, "grad_norm": 1.6241711378097534, "learning_rate": 0.0001767814616274462, "loss": 0.6270421028137207, "step": 156700 }, { "epoch": 0.9315167834703473, "grad_norm": 1.6338613033294678, "learning_rate": 0.00017677728849501133, "loss": 0.6528068542480469, "step": 156710 }, { "epoch": 0.9315762255470157, "grad_norm": 1.5529792308807373, "learning_rate": 0.00017677311504313577, "loss": 0.5932286262512207, "step": 156720 }, { "epoch": 0.9316356676236841, "grad_norm": 1.747811198234558, "learning_rate": 0.00017676894127183942, "loss": 0.6413961410522461, "step": 156730 }, { "epoch": 0.9316951097003525, "grad_norm": 1.4112048149108887, "learning_rate": 0.0001767647671811423, "loss": 0.6276240348815918, "step": 156740 }, { "epoch": 0.9317545517770209, "grad_norm": 1.4493030309677124, "learning_rate": 0.00017676059277106437, "loss": 0.5996183395385742, "step": 156750 }, { "epoch": 0.9318139938536892, "grad_norm": 1.734850287437439, "learning_rate": 0.00017675641804162554, "loss": 0.6277253150939941, "step": 156760 }, { "epoch": 0.9318734359303577, "grad_norm": 1.6951912641525269, "learning_rate": 0.00017675224299284583, "loss": 0.6162662506103516, "step": 156770 }, { "epoch": 0.9319328780070261, "grad_norm": 1.3980281352996826, "learning_rate": 0.0001767480676247452, "loss": 0.7041717052459717, "step": 156780 }, { "epoch": 0.9319923200836945, "grad_norm": 1.6077629327774048, "learning_rate": 0.00017674389193734363, "loss": 0.6291006088256836, "step": 156790 }, { "epoch": 0.9320517621603628, "grad_norm": 1.389753818511963, "learning_rate": 0.0001767397159306611, "loss": 0.6711861610412597, "step": 156800 }, { "epoch": 0.9321112042370312, "grad_norm": 1.7145711183547974, "learning_rate": 0.0001767355396047176, "loss": 0.6273415565490723, "step": 156810 }, { "epoch": 0.9321706463136996, "grad_norm": 1.795065999031067, "learning_rate": 0.00017673136295953307, "loss": 0.6016595840454102, "step": 156820 }, { "epoch": 0.932230088390368, "grad_norm": 1.7956115007400513, "learning_rate": 0.0001767271859951275, "loss": 0.6065445423126221, "step": 156830 }, { "epoch": 0.9322895304670364, "grad_norm": 1.5325610637664795, "learning_rate": 0.0001767230087115209, "loss": 0.6583439350128174, "step": 156840 }, { "epoch": 0.9323489725437047, "grad_norm": 1.4534997940063477, "learning_rate": 0.0001767188311087332, "loss": 0.626404094696045, "step": 156850 }, { "epoch": 0.9324084146203732, "grad_norm": 1.3308442831039429, "learning_rate": 0.00017671465318678443, "loss": 0.6366988182067871, "step": 156860 }, { "epoch": 0.9324678566970416, "grad_norm": 1.6099063158035278, "learning_rate": 0.00017671047494569457, "loss": 0.7159358024597168, "step": 156870 }, { "epoch": 0.93252729877371, "grad_norm": 1.7139852046966553, "learning_rate": 0.0001767062963854836, "loss": 0.6265609741210938, "step": 156880 }, { "epoch": 0.9325867408503784, "grad_norm": 1.9711525440216064, "learning_rate": 0.0001767021175061715, "loss": 0.6583870887756348, "step": 156890 }, { "epoch": 0.9326461829270467, "grad_norm": 1.4784106016159058, "learning_rate": 0.0001766979383077783, "loss": 0.6338336944580079, "step": 156900 }, { "epoch": 0.9327056250037151, "grad_norm": 1.9738860130310059, "learning_rate": 0.00017669375879032393, "loss": 0.6391250610351562, "step": 156910 }, { "epoch": 0.9327650670803835, "grad_norm": 1.6933497190475464, "learning_rate": 0.0001766895789538284, "loss": 0.6386701583862304, "step": 156920 }, { "epoch": 0.932824509157052, "grad_norm": 1.6055076122283936, "learning_rate": 0.00017668539879831175, "loss": 0.673461627960205, "step": 156930 }, { "epoch": 0.9328839512337203, "grad_norm": 1.5962728261947632, "learning_rate": 0.00017668121832379392, "loss": 0.6438188552856445, "step": 156940 }, { "epoch": 0.9329433933103887, "grad_norm": 1.53661048412323, "learning_rate": 0.00017667703753029493, "loss": 0.6235373020172119, "step": 156950 }, { "epoch": 0.9330028353870571, "grad_norm": 1.65745210647583, "learning_rate": 0.0001766728564178348, "loss": 0.6534951210021973, "step": 156960 }, { "epoch": 0.9330622774637255, "grad_norm": 1.9679523706436157, "learning_rate": 0.00017666867498643352, "loss": 0.6252460479736328, "step": 156970 }, { "epoch": 0.9331217195403939, "grad_norm": 1.7774020433425903, "learning_rate": 0.00017666449323611107, "loss": 0.6245386600494385, "step": 156980 }, { "epoch": 0.9331811616170622, "grad_norm": 1.6893420219421387, "learning_rate": 0.00017666031116688748, "loss": 0.6650581359863281, "step": 156990 }, { "epoch": 0.9332406036937306, "grad_norm": 1.568082571029663, "learning_rate": 0.00017665612877878275, "loss": 0.6622031688690185, "step": 157000 }, { "epoch": 0.933300045770399, "grad_norm": 1.3990269899368286, "learning_rate": 0.0001766519460718169, "loss": 0.634925365447998, "step": 157010 }, { "epoch": 0.9333594878470675, "grad_norm": 1.6990810632705688, "learning_rate": 0.00017664776304600989, "loss": 0.6565956115722656, "step": 157020 }, { "epoch": 0.9334189299237358, "grad_norm": 1.7058513164520264, "learning_rate": 0.00017664357970138174, "loss": 0.6336488723754883, "step": 157030 }, { "epoch": 0.9334783720004042, "grad_norm": 1.5336774587631226, "learning_rate": 0.00017663939603795251, "loss": 0.6539254665374756, "step": 157040 }, { "epoch": 0.9335378140770726, "grad_norm": 1.6638221740722656, "learning_rate": 0.0001766352120557422, "loss": 0.6922452449798584, "step": 157050 }, { "epoch": 0.933597256153741, "grad_norm": 1.868937373161316, "learning_rate": 0.0001766310277547708, "loss": 0.6492037773132324, "step": 157060 }, { "epoch": 0.9336566982304094, "grad_norm": 1.6316344738006592, "learning_rate": 0.00017662684313505834, "loss": 0.5757981300354004, "step": 157070 }, { "epoch": 0.9337161403070777, "grad_norm": 1.4975534677505493, "learning_rate": 0.00017662265819662484, "loss": 0.6489365577697754, "step": 157080 }, { "epoch": 0.9337755823837461, "grad_norm": 1.61246919631958, "learning_rate": 0.00017661847293949033, "loss": 0.6672519207000732, "step": 157090 }, { "epoch": 0.9338350244604146, "grad_norm": 2.086160182952881, "learning_rate": 0.0001766142873636748, "loss": 0.6290945529937744, "step": 157100 }, { "epoch": 0.933894466537083, "grad_norm": 1.715814232826233, "learning_rate": 0.0001766101014691983, "loss": 0.6874963283538819, "step": 157110 }, { "epoch": 0.9339539086137514, "grad_norm": 1.4803966283798218, "learning_rate": 0.00017660591525608084, "loss": 0.5957914352416992, "step": 157120 }, { "epoch": 0.9340133506904197, "grad_norm": 1.5991408824920654, "learning_rate": 0.00017660172872434242, "loss": 0.6462908744812011, "step": 157130 }, { "epoch": 0.9340727927670881, "grad_norm": 2.1350090503692627, "learning_rate": 0.00017659754187400312, "loss": 0.6086101531982422, "step": 157140 }, { "epoch": 0.9341322348437565, "grad_norm": 1.5199137926101685, "learning_rate": 0.00017659335470508294, "loss": 0.6071441650390625, "step": 157150 }, { "epoch": 0.9341916769204249, "grad_norm": 1.484002709388733, "learning_rate": 0.00017658916721760193, "loss": 0.670400333404541, "step": 157160 }, { "epoch": 0.9342511189970932, "grad_norm": 1.6290230751037598, "learning_rate": 0.00017658497941158008, "loss": 0.6245110511779786, "step": 157170 }, { "epoch": 0.9343105610737616, "grad_norm": 1.6400715112686157, "learning_rate": 0.00017658079128703743, "loss": 0.689954137802124, "step": 157180 }, { "epoch": 0.9343700031504301, "grad_norm": 1.7227801084518433, "learning_rate": 0.00017657660284399406, "loss": 0.6344679355621338, "step": 157190 }, { "epoch": 0.9344294452270985, "grad_norm": 1.5567814111709595, "learning_rate": 0.00017657241408247, "loss": 0.6108687400817872, "step": 157200 }, { "epoch": 0.9344888873037669, "grad_norm": 1.4881161451339722, "learning_rate": 0.00017656822500248528, "loss": 0.6284358024597168, "step": 157210 }, { "epoch": 0.9345483293804352, "grad_norm": 1.6407225131988525, "learning_rate": 0.0001765640356040599, "loss": 0.7011534690856933, "step": 157220 }, { "epoch": 0.9346077714571036, "grad_norm": 1.54459547996521, "learning_rate": 0.0001765598458872139, "loss": 0.6030441761016846, "step": 157230 }, { "epoch": 0.934667213533772, "grad_norm": 1.9218553304672241, "learning_rate": 0.00017655565585196736, "loss": 0.6100697994232178, "step": 157240 }, { "epoch": 0.9347266556104404, "grad_norm": 1.8525816202163696, "learning_rate": 0.00017655146549834034, "loss": 0.6640610694885254, "step": 157250 }, { "epoch": 0.9347860976871089, "grad_norm": 2.1679160594940186, "learning_rate": 0.00017654727482635283, "loss": 0.6787889003753662, "step": 157260 }, { "epoch": 0.9348455397637772, "grad_norm": 1.6287294626235962, "learning_rate": 0.00017654308383602493, "loss": 0.6079437732696533, "step": 157270 }, { "epoch": 0.9349049818404456, "grad_norm": 1.507575511932373, "learning_rate": 0.00017653889252737664, "loss": 0.6307252883911133, "step": 157280 }, { "epoch": 0.934964423917114, "grad_norm": 1.6471771001815796, "learning_rate": 0.00017653470090042806, "loss": 0.6852846622467041, "step": 157290 }, { "epoch": 0.9350238659937824, "grad_norm": 1.5808225870132446, "learning_rate": 0.0001765305089551992, "loss": 0.5882343292236328, "step": 157300 }, { "epoch": 0.9350833080704507, "grad_norm": 1.3058058023452759, "learning_rate": 0.0001765263166917101, "loss": 0.6452692031860352, "step": 157310 }, { "epoch": 0.9351427501471191, "grad_norm": 1.72890305519104, "learning_rate": 0.0001765221241099809, "loss": 0.7199461460113525, "step": 157320 }, { "epoch": 0.9352021922237875, "grad_norm": 1.7789796590805054, "learning_rate": 0.00017651793121003156, "loss": 0.6678582191467285, "step": 157330 }, { "epoch": 0.935261634300456, "grad_norm": 1.8058228492736816, "learning_rate": 0.00017651373799188217, "loss": 0.6452093124389648, "step": 157340 }, { "epoch": 0.9353210763771244, "grad_norm": 1.8198301792144775, "learning_rate": 0.0001765095444555528, "loss": 0.6967645645141601, "step": 157350 }, { "epoch": 0.9353805184537927, "grad_norm": 1.695656418800354, "learning_rate": 0.0001765053506010635, "loss": 0.6621376037597656, "step": 157360 }, { "epoch": 0.9354399605304611, "grad_norm": 1.8912832736968994, "learning_rate": 0.00017650115642843438, "loss": 0.7164569854736328, "step": 157370 }, { "epoch": 0.9354994026071295, "grad_norm": 1.5354994535446167, "learning_rate": 0.0001764969619376854, "loss": 0.6631646156311035, "step": 157380 }, { "epoch": 0.9355588446837979, "grad_norm": 1.8996766805648804, "learning_rate": 0.00017649276712883674, "loss": 0.6565357685089112, "step": 157390 }, { "epoch": 0.9356182867604662, "grad_norm": 1.6525572538375854, "learning_rate": 0.00017648857200190839, "loss": 0.6345190048217774, "step": 157400 }, { "epoch": 0.9356777288371346, "grad_norm": 1.945504069328308, "learning_rate": 0.00017648437655692044, "loss": 0.6184590339660645, "step": 157410 }, { "epoch": 0.935737170913803, "grad_norm": 1.7563064098358154, "learning_rate": 0.00017648018079389295, "loss": 0.6711641311645508, "step": 157420 }, { "epoch": 0.9357966129904715, "grad_norm": 1.277477741241455, "learning_rate": 0.000176475984712846, "loss": 0.6447747230529786, "step": 157430 }, { "epoch": 0.9358560550671399, "grad_norm": 1.5493183135986328, "learning_rate": 0.0001764717883137997, "loss": 0.6427643775939942, "step": 157440 }, { "epoch": 0.9359154971438082, "grad_norm": 1.6261101961135864, "learning_rate": 0.00017646759159677404, "loss": 0.6558210372924804, "step": 157450 }, { "epoch": 0.9359749392204766, "grad_norm": 1.7228972911834717, "learning_rate": 0.0001764633945617892, "loss": 0.7237981796264649, "step": 157460 }, { "epoch": 0.936034381297145, "grad_norm": 1.6282185316085815, "learning_rate": 0.00017645919720886514, "loss": 0.5843130111694336, "step": 157470 }, { "epoch": 0.9360938233738134, "grad_norm": 1.4638588428497314, "learning_rate": 0.00017645499953802203, "loss": 0.645234203338623, "step": 157480 }, { "epoch": 0.9361532654504818, "grad_norm": 1.3679389953613281, "learning_rate": 0.0001764508015492799, "loss": 0.6541213989257812, "step": 157490 }, { "epoch": 0.9362127075271501, "grad_norm": 1.4687938690185547, "learning_rate": 0.00017644660324265887, "loss": 0.6814902305603028, "step": 157500 }, { "epoch": 0.9362721496038185, "grad_norm": 1.7305933237075806, "learning_rate": 0.000176442404618179, "loss": 0.6407051086425781, "step": 157510 }, { "epoch": 0.936331591680487, "grad_norm": 2.0561370849609375, "learning_rate": 0.00017643820567586038, "loss": 0.6730311393737793, "step": 157520 }, { "epoch": 0.9363910337571554, "grad_norm": 1.3925882577896118, "learning_rate": 0.0001764340064157231, "loss": 0.6257928848266602, "step": 157530 }, { "epoch": 0.9364504758338237, "grad_norm": 1.4568853378295898, "learning_rate": 0.00017642980683778726, "loss": 0.6473781585693359, "step": 157540 }, { "epoch": 0.9365099179104921, "grad_norm": 1.74973726272583, "learning_rate": 0.00017642560694207287, "loss": 0.7203921318054199, "step": 157550 }, { "epoch": 0.9365693599871605, "grad_norm": 1.475419521331787, "learning_rate": 0.00017642140672860014, "loss": 0.6229963302612305, "step": 157560 }, { "epoch": 0.9366288020638289, "grad_norm": 2.237562417984009, "learning_rate": 0.0001764172061973891, "loss": 0.6768260955810547, "step": 157570 }, { "epoch": 0.9366882441404973, "grad_norm": 1.777787208557129, "learning_rate": 0.00017641300534845987, "loss": 0.6857769012451171, "step": 157580 }, { "epoch": 0.9367476862171656, "grad_norm": 1.4055664539337158, "learning_rate": 0.0001764088041818325, "loss": 0.681010627746582, "step": 157590 }, { "epoch": 0.9368071282938341, "grad_norm": 1.902987003326416, "learning_rate": 0.0001764046026975271, "loss": 0.667358112335205, "step": 157600 }, { "epoch": 0.9368665703705025, "grad_norm": 1.556612491607666, "learning_rate": 0.0001764004008955638, "loss": 0.6309538841247558, "step": 157610 }, { "epoch": 0.9369260124471709, "grad_norm": 1.3449410200119019, "learning_rate": 0.0001763961987759627, "loss": 0.6178511619567871, "step": 157620 }, { "epoch": 0.9369854545238392, "grad_norm": 1.4968395233154297, "learning_rate": 0.00017639199633874385, "loss": 0.6874641418457031, "step": 157630 }, { "epoch": 0.9370448966005076, "grad_norm": 1.6511656045913696, "learning_rate": 0.0001763877935839274, "loss": 0.6340820789337158, "step": 157640 }, { "epoch": 0.937104338677176, "grad_norm": 1.6122230291366577, "learning_rate": 0.00017638359051153342, "loss": 0.6840329647064209, "step": 157650 }, { "epoch": 0.9371637807538444, "grad_norm": 1.9887465238571167, "learning_rate": 0.00017637938712158208, "loss": 0.6419942855834961, "step": 157660 }, { "epoch": 0.9372232228305128, "grad_norm": 1.7515584230422974, "learning_rate": 0.00017637518341409342, "loss": 0.6793725490570068, "step": 157670 }, { "epoch": 0.9372826649071812, "grad_norm": 1.5875974893569946, "learning_rate": 0.0001763709793890876, "loss": 0.6016408920288085, "step": 157680 }, { "epoch": 0.9373421069838496, "grad_norm": 1.5685312747955322, "learning_rate": 0.00017636677504658468, "loss": 0.6618817329406739, "step": 157690 }, { "epoch": 0.937401549060518, "grad_norm": 2.0272376537323, "learning_rate": 0.00017636257038660479, "loss": 0.648561429977417, "step": 157700 }, { "epoch": 0.9374609911371864, "grad_norm": 2.179579257965088, "learning_rate": 0.00017635836540916806, "loss": 0.6681163787841797, "step": 157710 }, { "epoch": 0.9375204332138548, "grad_norm": 1.8114902973175049, "learning_rate": 0.0001763541601142946, "loss": 0.6391644954681397, "step": 157720 }, { "epoch": 0.9375798752905231, "grad_norm": 1.8372081518173218, "learning_rate": 0.00017634995450200452, "loss": 0.6711155891418457, "step": 157730 }, { "epoch": 0.9376393173671915, "grad_norm": 1.8658664226531982, "learning_rate": 0.00017634574857231796, "loss": 0.6462997436523438, "step": 157740 }, { "epoch": 0.9376987594438599, "grad_norm": 1.5696661472320557, "learning_rate": 0.000176341542325255, "loss": 0.5984707832336426, "step": 157750 }, { "epoch": 0.9377582015205284, "grad_norm": 1.6462860107421875, "learning_rate": 0.00017633733576083576, "loss": 0.6672362327575684, "step": 157760 }, { "epoch": 0.9378176435971967, "grad_norm": 1.4431451559066772, "learning_rate": 0.00017633312887908043, "loss": 0.6827069282531738, "step": 157770 }, { "epoch": 0.9378770856738651, "grad_norm": 1.44081449508667, "learning_rate": 0.00017632892168000907, "loss": 0.6318609237670898, "step": 157780 }, { "epoch": 0.9379365277505335, "grad_norm": 1.6996278762817383, "learning_rate": 0.00017632471416364183, "loss": 0.7019730567932129, "step": 157790 }, { "epoch": 0.9379959698272019, "grad_norm": 1.9554293155670166, "learning_rate": 0.0001763205063299988, "loss": 0.6920969009399414, "step": 157800 }, { "epoch": 0.9380554119038703, "grad_norm": 1.333030343055725, "learning_rate": 0.00017631629817910018, "loss": 0.6824786186218261, "step": 157810 }, { "epoch": 0.9381148539805386, "grad_norm": 1.5683279037475586, "learning_rate": 0.00017631208971096603, "loss": 0.6694024562835693, "step": 157820 }, { "epoch": 0.938174296057207, "grad_norm": 1.7709975242614746, "learning_rate": 0.00017630788092561656, "loss": 0.6549788475036621, "step": 157830 }, { "epoch": 0.9382337381338755, "grad_norm": 1.3593326807022095, "learning_rate": 0.00017630367182307183, "loss": 0.6703635215759277, "step": 157840 }, { "epoch": 0.9382931802105439, "grad_norm": 1.6407970190048218, "learning_rate": 0.000176299462403352, "loss": 0.6563194274902344, "step": 157850 }, { "epoch": 0.9383526222872123, "grad_norm": 1.4894607067108154, "learning_rate": 0.0001762952526664772, "loss": 0.6640376567840576, "step": 157860 }, { "epoch": 0.9384120643638806, "grad_norm": 1.7174125909805298, "learning_rate": 0.00017629104261246761, "loss": 0.6204277038574219, "step": 157870 }, { "epoch": 0.938471506440549, "grad_norm": 2.279350996017456, "learning_rate": 0.00017628683224134333, "loss": 0.6480648517608643, "step": 157880 }, { "epoch": 0.9385309485172174, "grad_norm": 1.658647894859314, "learning_rate": 0.00017628262155312447, "loss": 0.657379150390625, "step": 157890 }, { "epoch": 0.9385903905938858, "grad_norm": 1.8080267906188965, "learning_rate": 0.00017627841054783125, "loss": 0.6291797637939454, "step": 157900 }, { "epoch": 0.9386498326705541, "grad_norm": 1.8101224899291992, "learning_rate": 0.00017627419922548377, "loss": 0.6732641220092773, "step": 157910 }, { "epoch": 0.9387092747472225, "grad_norm": 2.00984525680542, "learning_rate": 0.00017626998758610215, "loss": 0.629312801361084, "step": 157920 }, { "epoch": 0.938768716823891, "grad_norm": 1.6503872871398926, "learning_rate": 0.00017626577562970656, "loss": 0.6441582202911377, "step": 157930 }, { "epoch": 0.9388281589005594, "grad_norm": 1.8112972974777222, "learning_rate": 0.0001762615633563172, "loss": 0.655265998840332, "step": 157940 }, { "epoch": 0.9388876009772278, "grad_norm": 1.418637752532959, "learning_rate": 0.00017625735076595413, "loss": 0.6351218700408936, "step": 157950 }, { "epoch": 0.9389470430538961, "grad_norm": 1.3920624256134033, "learning_rate": 0.00017625313785863759, "loss": 0.6673482894897461, "step": 157960 }, { "epoch": 0.9390064851305645, "grad_norm": 1.7343084812164307, "learning_rate": 0.00017624892463438766, "loss": 0.6903093338012696, "step": 157970 }, { "epoch": 0.9390659272072329, "grad_norm": 1.6440001726150513, "learning_rate": 0.00017624471109322455, "loss": 0.6082616806030273, "step": 157980 }, { "epoch": 0.9391253692839013, "grad_norm": 1.5228383541107178, "learning_rate": 0.00017624049723516838, "loss": 0.6624894142150879, "step": 157990 }, { "epoch": 0.9391848113605696, "grad_norm": 1.4923028945922852, "learning_rate": 0.00017623628306023934, "loss": 0.7176042556762695, "step": 158000 }, { "epoch": 0.939244253437238, "grad_norm": 1.4772266149520874, "learning_rate": 0.00017623206856845754, "loss": 0.667483901977539, "step": 158010 }, { "epoch": 0.9393036955139065, "grad_norm": 1.6747781038284302, "learning_rate": 0.00017622785375984317, "loss": 0.6416930198669434, "step": 158020 }, { "epoch": 0.9393631375905749, "grad_norm": 2.14400315284729, "learning_rate": 0.00017622363863441638, "loss": 0.6666021823883057, "step": 158030 }, { "epoch": 0.9394225796672433, "grad_norm": 1.8436007499694824, "learning_rate": 0.00017621942319219735, "loss": 0.6352604389190674, "step": 158040 }, { "epoch": 0.9394820217439116, "grad_norm": 2.1090786457061768, "learning_rate": 0.00017621520743320627, "loss": 0.6697813034057617, "step": 158050 }, { "epoch": 0.93954146382058, "grad_norm": 1.8434674739837646, "learning_rate": 0.00017621099135746324, "loss": 0.6259562492370605, "step": 158060 }, { "epoch": 0.9396009058972484, "grad_norm": 1.3818243741989136, "learning_rate": 0.00017620677496498846, "loss": 0.6160001754760742, "step": 158070 }, { "epoch": 0.9396603479739168, "grad_norm": 1.671476125717163, "learning_rate": 0.00017620255825580216, "loss": 0.704277753829956, "step": 158080 }, { "epoch": 0.9397197900505853, "grad_norm": 1.1639407873153687, "learning_rate": 0.0001761983412299244, "loss": 0.5895451545715332, "step": 158090 }, { "epoch": 0.9397792321272536, "grad_norm": 1.1390392780303955, "learning_rate": 0.00017619412388737544, "loss": 0.6328465461730957, "step": 158100 }, { "epoch": 0.939838674203922, "grad_norm": 1.5364052057266235, "learning_rate": 0.00017618990622817544, "loss": 0.6748203754425048, "step": 158110 }, { "epoch": 0.9398981162805904, "grad_norm": 1.6329877376556396, "learning_rate": 0.0001761856882523445, "loss": 0.642770528793335, "step": 158120 }, { "epoch": 0.9399575583572588, "grad_norm": 1.6072683334350586, "learning_rate": 0.00017618146995990292, "loss": 0.6276827812194824, "step": 158130 }, { "epoch": 0.9400170004339271, "grad_norm": 1.5938690900802612, "learning_rate": 0.00017617725135087077, "loss": 0.6467537879943848, "step": 158140 }, { "epoch": 0.9400764425105955, "grad_norm": 1.453301191329956, "learning_rate": 0.0001761730324252683, "loss": 0.6407589912414551, "step": 158150 }, { "epoch": 0.9401358845872639, "grad_norm": 1.9930299520492554, "learning_rate": 0.0001761688131831157, "loss": 0.619649600982666, "step": 158160 }, { "epoch": 0.9401953266639324, "grad_norm": 1.5086679458618164, "learning_rate": 0.00017616459362443306, "loss": 0.6544065952301026, "step": 158170 }, { "epoch": 0.9402547687406008, "grad_norm": 1.5906682014465332, "learning_rate": 0.00017616037374924067, "loss": 0.6216651916503906, "step": 158180 }, { "epoch": 0.9403142108172691, "grad_norm": 1.8490955829620361, "learning_rate": 0.00017615615355755864, "loss": 0.6454865455627441, "step": 158190 }, { "epoch": 0.9403736528939375, "grad_norm": 1.5741965770721436, "learning_rate": 0.00017615193304940723, "loss": 0.6202995300292968, "step": 158200 }, { "epoch": 0.9404330949706059, "grad_norm": 1.1992775201797485, "learning_rate": 0.00017614771222480654, "loss": 0.6141551017761231, "step": 158210 }, { "epoch": 0.9404925370472743, "grad_norm": 1.9158926010131836, "learning_rate": 0.00017614349108377683, "loss": 0.6639052391052246, "step": 158220 }, { "epoch": 0.9405519791239427, "grad_norm": 1.5489921569824219, "learning_rate": 0.0001761392696263383, "loss": 0.6336699962615967, "step": 158230 }, { "epoch": 0.940611421200611, "grad_norm": 1.702505111694336, "learning_rate": 0.0001761350478525111, "loss": 0.631624984741211, "step": 158240 }, { "epoch": 0.9406708632772794, "grad_norm": 1.5166865587234497, "learning_rate": 0.00017613082576231544, "loss": 0.6426115512847901, "step": 158250 }, { "epoch": 0.9407303053539479, "grad_norm": 1.8095567226409912, "learning_rate": 0.00017612660335577154, "loss": 0.6729184150695801, "step": 158260 }, { "epoch": 0.9407897474306163, "grad_norm": 1.6326431035995483, "learning_rate": 0.00017612238063289957, "loss": 0.7004758834838867, "step": 158270 }, { "epoch": 0.9408491895072846, "grad_norm": 1.6062326431274414, "learning_rate": 0.00017611815759371974, "loss": 0.5636794090270996, "step": 158280 }, { "epoch": 0.940908631583953, "grad_norm": 1.4902169704437256, "learning_rate": 0.00017611393423825226, "loss": 0.6889992713928222, "step": 158290 }, { "epoch": 0.9409680736606214, "grad_norm": 1.5015569925308228, "learning_rate": 0.0001761097105665173, "loss": 0.6343983173370361, "step": 158300 }, { "epoch": 0.9410275157372898, "grad_norm": 1.4610087871551514, "learning_rate": 0.0001761054865785351, "loss": 0.6200174808502197, "step": 158310 }, { "epoch": 0.9410869578139582, "grad_norm": 1.5993847846984863, "learning_rate": 0.0001761012622743259, "loss": 0.6592080116271972, "step": 158320 }, { "epoch": 0.9411463998906265, "grad_norm": 1.9068242311477661, "learning_rate": 0.00017609703765390978, "loss": 0.6049762725830078, "step": 158330 }, { "epoch": 0.941205841967295, "grad_norm": 1.4516197443008423, "learning_rate": 0.00017609281271730712, "loss": 0.5794936180114746, "step": 158340 }, { "epoch": 0.9412652840439634, "grad_norm": 1.692105770111084, "learning_rate": 0.00017608858746453798, "loss": 0.6758432388305664, "step": 158350 }, { "epoch": 0.9413247261206318, "grad_norm": 1.7888212203979492, "learning_rate": 0.00017608436189562267, "loss": 0.6261027812957763, "step": 158360 }, { "epoch": 0.9413841681973001, "grad_norm": 1.8011372089385986, "learning_rate": 0.00017608013601058136, "loss": 0.6878138542175293, "step": 158370 }, { "epoch": 0.9414436102739685, "grad_norm": 1.7869350910186768, "learning_rate": 0.00017607590980943424, "loss": 0.678506326675415, "step": 158380 }, { "epoch": 0.9415030523506369, "grad_norm": 1.62992525100708, "learning_rate": 0.00017607168329220163, "loss": 0.6897109508514404, "step": 158390 }, { "epoch": 0.9415624944273053, "grad_norm": 1.966644048690796, "learning_rate": 0.00017606745645890363, "loss": 0.6720575809478759, "step": 158400 }, { "epoch": 0.9416219365039737, "grad_norm": 1.7429088354110718, "learning_rate": 0.00017606322930956053, "loss": 0.6551470279693603, "step": 158410 }, { "epoch": 0.941681378580642, "grad_norm": 1.8156017065048218, "learning_rate": 0.00017605900184419253, "loss": 0.6522389888763428, "step": 158420 }, { "epoch": 0.9417408206573105, "grad_norm": 1.588037133216858, "learning_rate": 0.00017605477406281981, "loss": 0.6243794441223145, "step": 158430 }, { "epoch": 0.9418002627339789, "grad_norm": 1.4579963684082031, "learning_rate": 0.00017605054596546272, "loss": 0.6898554801940918, "step": 158440 }, { "epoch": 0.9418597048106473, "grad_norm": 1.68588125705719, "learning_rate": 0.00017604631755214134, "loss": 0.6769548892974854, "step": 158450 }, { "epoch": 0.9419191468873157, "grad_norm": 1.9932851791381836, "learning_rate": 0.00017604208882287595, "loss": 0.6670948028564453, "step": 158460 }, { "epoch": 0.941978588963984, "grad_norm": 1.5349558591842651, "learning_rate": 0.00017603785977768683, "loss": 0.6578966617584229, "step": 158470 }, { "epoch": 0.9420380310406524, "grad_norm": 2.1612906455993652, "learning_rate": 0.00017603363041659414, "loss": 0.5919754028320312, "step": 158480 }, { "epoch": 0.9420974731173208, "grad_norm": 1.6528992652893066, "learning_rate": 0.00017602940073961818, "loss": 0.7366450309753418, "step": 158490 }, { "epoch": 0.9421569151939893, "grad_norm": 1.3061379194259644, "learning_rate": 0.00017602517074677914, "loss": 0.6188475131988526, "step": 158500 }, { "epoch": 0.9422163572706576, "grad_norm": 1.6412608623504639, "learning_rate": 0.00017602094043809725, "loss": 0.6672326564788819, "step": 158510 }, { "epoch": 0.942275799347326, "grad_norm": 1.3273175954818726, "learning_rate": 0.00017601670981359275, "loss": 0.6715281486511231, "step": 158520 }, { "epoch": 0.9423352414239944, "grad_norm": 1.6254451274871826, "learning_rate": 0.00017601247887328588, "loss": 0.6500326156616211, "step": 158530 }, { "epoch": 0.9423946835006628, "grad_norm": 1.2566566467285156, "learning_rate": 0.0001760082476171969, "loss": 0.6596773147583008, "step": 158540 }, { "epoch": 0.9424541255773312, "grad_norm": 1.761387825012207, "learning_rate": 0.00017600401604534602, "loss": 0.6633918762207032, "step": 158550 }, { "epoch": 0.9425135676539995, "grad_norm": 1.3829147815704346, "learning_rate": 0.0001759997841577535, "loss": 0.6343398094177246, "step": 158560 }, { "epoch": 0.9425730097306679, "grad_norm": 1.5673161745071411, "learning_rate": 0.00017599555195443956, "loss": 0.6905671119689941, "step": 158570 }, { "epoch": 0.9426324518073363, "grad_norm": 2.1124749183654785, "learning_rate": 0.0001759913194354245, "loss": 0.707904577255249, "step": 158580 }, { "epoch": 0.9426918938840048, "grad_norm": 1.446271300315857, "learning_rate": 0.00017598708660072855, "loss": 0.6534853935241699, "step": 158590 }, { "epoch": 0.9427513359606732, "grad_norm": 1.4006315469741821, "learning_rate": 0.0001759828534503719, "loss": 0.6276374816894531, "step": 158600 }, { "epoch": 0.9428107780373415, "grad_norm": 1.3617361783981323, "learning_rate": 0.00017597861998437485, "loss": 0.6432228088378906, "step": 158610 }, { "epoch": 0.9428702201140099, "grad_norm": 1.69246506690979, "learning_rate": 0.00017597438620275767, "loss": 0.6522003173828125, "step": 158620 }, { "epoch": 0.9429296621906783, "grad_norm": 2.6278462409973145, "learning_rate": 0.00017597015210554058, "loss": 0.6664600849151612, "step": 158630 }, { "epoch": 0.9429891042673467, "grad_norm": 1.5570650100708008, "learning_rate": 0.00017596591769274383, "loss": 0.6342034339904785, "step": 158640 }, { "epoch": 0.943048546344015, "grad_norm": 1.236464023590088, "learning_rate": 0.0001759616829643877, "loss": 0.6281764030456543, "step": 158650 }, { "epoch": 0.9431079884206834, "grad_norm": 2.7370944023132324, "learning_rate": 0.00017595744792049241, "loss": 0.6321210861206055, "step": 158660 }, { "epoch": 0.9431674304973519, "grad_norm": 1.0776842832565308, "learning_rate": 0.0001759532125610783, "loss": 0.6318627834320069, "step": 158670 }, { "epoch": 0.9432268725740203, "grad_norm": 1.5290850400924683, "learning_rate": 0.0001759489768861655, "loss": 0.6679687023162841, "step": 158680 }, { "epoch": 0.9432863146506887, "grad_norm": 1.8655956983566284, "learning_rate": 0.0001759447408957744, "loss": 0.6085890769958496, "step": 158690 }, { "epoch": 0.943345756727357, "grad_norm": 1.7528923749923706, "learning_rate": 0.00017594050458992518, "loss": 0.620814847946167, "step": 158700 }, { "epoch": 0.9434051988040254, "grad_norm": 1.7080820798873901, "learning_rate": 0.00017593626796863816, "loss": 0.7073873519897461, "step": 158710 }, { "epoch": 0.9434646408806938, "grad_norm": 1.5471237897872925, "learning_rate": 0.00017593203103193357, "loss": 0.6487622737884522, "step": 158720 }, { "epoch": 0.9435240829573622, "grad_norm": 1.9252713918685913, "learning_rate": 0.0001759277937798317, "loss": 0.7249130249023438, "step": 158730 }, { "epoch": 0.9435835250340305, "grad_norm": 1.3341888189315796, "learning_rate": 0.00017592355621235282, "loss": 0.6487709045410156, "step": 158740 }, { "epoch": 0.943642967110699, "grad_norm": 1.5073951482772827, "learning_rate": 0.00017591931832951715, "loss": 0.6883597850799561, "step": 158750 }, { "epoch": 0.9437024091873674, "grad_norm": 1.6529908180236816, "learning_rate": 0.00017591508013134504, "loss": 0.6398244857788086, "step": 158760 }, { "epoch": 0.9437618512640358, "grad_norm": 1.7262778282165527, "learning_rate": 0.00017591084161785672, "loss": 0.6861778259277344, "step": 158770 }, { "epoch": 0.9438212933407042, "grad_norm": 1.5194110870361328, "learning_rate": 0.00017590660278907246, "loss": 0.6448273181915283, "step": 158780 }, { "epoch": 0.9438807354173725, "grad_norm": 1.8818460702896118, "learning_rate": 0.00017590236364501256, "loss": 0.7207211494445801, "step": 158790 }, { "epoch": 0.9439401774940409, "grad_norm": 1.6194738149642944, "learning_rate": 0.00017589812418569728, "loss": 0.6685863494873047, "step": 158800 }, { "epoch": 0.9439996195707093, "grad_norm": 1.412468433380127, "learning_rate": 0.0001758938844111469, "loss": 0.6653177261352539, "step": 158810 }, { "epoch": 0.9440590616473777, "grad_norm": 1.6529194116592407, "learning_rate": 0.00017588964432138174, "loss": 0.7030976772308349, "step": 158820 }, { "epoch": 0.9441185037240462, "grad_norm": 1.9150195121765137, "learning_rate": 0.00017588540391642207, "loss": 0.6651718616485596, "step": 158830 }, { "epoch": 0.9441779458007145, "grad_norm": 1.9216073751449585, "learning_rate": 0.0001758811631962881, "loss": 0.6063596725463867, "step": 158840 }, { "epoch": 0.9442373878773829, "grad_norm": 1.8055678606033325, "learning_rate": 0.00017587692216100025, "loss": 0.6620455741882324, "step": 158850 }, { "epoch": 0.9442968299540513, "grad_norm": 1.3773106336593628, "learning_rate": 0.0001758726808105787, "loss": 0.6497315406799317, "step": 158860 }, { "epoch": 0.9443562720307197, "grad_norm": 1.6930034160614014, "learning_rate": 0.00017586843914504377, "loss": 0.6736328601837158, "step": 158870 }, { "epoch": 0.944415714107388, "grad_norm": 1.397750973701477, "learning_rate": 0.0001758641971644157, "loss": 0.6456064701080322, "step": 158880 }, { "epoch": 0.9444751561840564, "grad_norm": 1.5240644216537476, "learning_rate": 0.0001758599548687149, "loss": 0.6307012557983398, "step": 158890 }, { "epoch": 0.9445345982607248, "grad_norm": 1.5271692276000977, "learning_rate": 0.0001758557122579616, "loss": 0.6635612487792969, "step": 158900 }, { "epoch": 0.9445940403373932, "grad_norm": 1.7723901271820068, "learning_rate": 0.00017585146933217608, "loss": 0.6380013942718505, "step": 158910 }, { "epoch": 0.9446534824140617, "grad_norm": 1.5951037406921387, "learning_rate": 0.00017584722609137864, "loss": 0.6441296577453614, "step": 158920 }, { "epoch": 0.94471292449073, "grad_norm": 1.8067179918289185, "learning_rate": 0.0001758429825355896, "loss": 0.6239373207092285, "step": 158930 }, { "epoch": 0.9447723665673984, "grad_norm": 1.4705162048339844, "learning_rate": 0.00017583873866482925, "loss": 0.6539605140686036, "step": 158940 }, { "epoch": 0.9448318086440668, "grad_norm": 1.616261601448059, "learning_rate": 0.00017583449447911787, "loss": 0.6500458717346191, "step": 158950 }, { "epoch": 0.9448912507207352, "grad_norm": 1.6360595226287842, "learning_rate": 0.0001758302499784758, "loss": 0.6165889739990235, "step": 158960 }, { "epoch": 0.9449506927974036, "grad_norm": 1.9806300401687622, "learning_rate": 0.0001758260051629233, "loss": 0.7301594734191894, "step": 158970 }, { "epoch": 0.9450101348740719, "grad_norm": 1.520949125289917, "learning_rate": 0.00017582176003248074, "loss": 0.6649378776550293, "step": 158980 }, { "epoch": 0.9450695769507403, "grad_norm": 1.6969895362854004, "learning_rate": 0.0001758175145871684, "loss": 0.6510017395019532, "step": 158990 }, { "epoch": 0.9451290190274088, "grad_norm": 1.588416337966919, "learning_rate": 0.00017581326882700656, "loss": 0.662765645980835, "step": 159000 }, { "epoch": 0.9451884611040772, "grad_norm": 1.5815653800964355, "learning_rate": 0.00017580902275201557, "loss": 0.646631908416748, "step": 159010 }, { "epoch": 0.9452479031807455, "grad_norm": 1.25962233543396, "learning_rate": 0.0001758047763622157, "loss": 0.6234831809997559, "step": 159020 }, { "epoch": 0.9453073452574139, "grad_norm": 1.495131254196167, "learning_rate": 0.0001758005296576273, "loss": 0.6521082878112793, "step": 159030 }, { "epoch": 0.9453667873340823, "grad_norm": 1.3475576639175415, "learning_rate": 0.00017579628263827065, "loss": 0.6415048599243164, "step": 159040 }, { "epoch": 0.9454262294107507, "grad_norm": 1.3878711462020874, "learning_rate": 0.00017579203530416608, "loss": 0.6995925903320312, "step": 159050 }, { "epoch": 0.9454856714874191, "grad_norm": 1.7178906202316284, "learning_rate": 0.00017578778765533394, "loss": 0.6612131595611572, "step": 159060 }, { "epoch": 0.9455451135640874, "grad_norm": 1.4583570957183838, "learning_rate": 0.00017578353969179453, "loss": 0.6664348602294922, "step": 159070 }, { "epoch": 0.9456045556407559, "grad_norm": 2.0458669662475586, "learning_rate": 0.00017577929141356815, "loss": 0.6931580066680908, "step": 159080 }, { "epoch": 0.9456639977174243, "grad_norm": 1.3433799743652344, "learning_rate": 0.00017577504282067512, "loss": 0.6601302146911621, "step": 159090 }, { "epoch": 0.9457234397940927, "grad_norm": 1.7980693578720093, "learning_rate": 0.00017577079391313581, "loss": 0.6853338241577148, "step": 159100 }, { "epoch": 0.945782881870761, "grad_norm": 1.5422186851501465, "learning_rate": 0.0001757665446909705, "loss": 0.6686444282531738, "step": 159110 }, { "epoch": 0.9458423239474294, "grad_norm": 1.3933051824569702, "learning_rate": 0.00017576229515419952, "loss": 0.6669669151306152, "step": 159120 }, { "epoch": 0.9459017660240978, "grad_norm": 1.202415108680725, "learning_rate": 0.00017575804530284324, "loss": 0.6365317344665528, "step": 159130 }, { "epoch": 0.9459612081007662, "grad_norm": 1.464399814605713, "learning_rate": 0.00017575379513692194, "loss": 0.658435583114624, "step": 159140 }, { "epoch": 0.9460206501774346, "grad_norm": 1.3600950241088867, "learning_rate": 0.00017574954465645598, "loss": 0.6197344303131104, "step": 159150 }, { "epoch": 0.946080092254103, "grad_norm": 1.436753511428833, "learning_rate": 0.00017574529386146567, "loss": 0.636417293548584, "step": 159160 }, { "epoch": 0.9461395343307714, "grad_norm": 1.2933896780014038, "learning_rate": 0.0001757410427519714, "loss": 0.6526504516601562, "step": 159170 }, { "epoch": 0.9461989764074398, "grad_norm": 1.3629156351089478, "learning_rate": 0.00017573679132799343, "loss": 0.609315824508667, "step": 159180 }, { "epoch": 0.9462584184841082, "grad_norm": 1.4452214241027832, "learning_rate": 0.00017573253958955213, "loss": 0.6433803081512451, "step": 159190 }, { "epoch": 0.9463178605607766, "grad_norm": 1.8412129878997803, "learning_rate": 0.00017572828753666787, "loss": 0.6980070114135742, "step": 159200 }, { "epoch": 0.9463773026374449, "grad_norm": 1.7687443494796753, "learning_rate": 0.00017572403516936095, "loss": 0.6845943450927734, "step": 159210 }, { "epoch": 0.9464367447141133, "grad_norm": 1.554255485534668, "learning_rate": 0.00017571978248765173, "loss": 0.6467994213104248, "step": 159220 }, { "epoch": 0.9464961867907817, "grad_norm": 1.762643814086914, "learning_rate": 0.00017571552949156055, "loss": 0.6166654109954834, "step": 159230 }, { "epoch": 0.9465556288674501, "grad_norm": 1.396195650100708, "learning_rate": 0.00017571127618110774, "loss": 0.6069908142089844, "step": 159240 }, { "epoch": 0.9466150709441185, "grad_norm": 1.7745909690856934, "learning_rate": 0.00017570702255631366, "loss": 0.6249856948852539, "step": 159250 }, { "epoch": 0.9466745130207869, "grad_norm": 1.5735434293746948, "learning_rate": 0.0001757027686171987, "loss": 0.6026693820953369, "step": 159260 }, { "epoch": 0.9467339550974553, "grad_norm": 1.3185137510299683, "learning_rate": 0.00017569851436378308, "loss": 0.6711984634399414, "step": 159270 }, { "epoch": 0.9467933971741237, "grad_norm": 1.4333873987197876, "learning_rate": 0.0001756942597960873, "loss": 0.6222599983215332, "step": 159280 }, { "epoch": 0.9468528392507921, "grad_norm": 1.9579607248306274, "learning_rate": 0.00017569000491413162, "loss": 0.6744696617126464, "step": 159290 }, { "epoch": 0.9469122813274604, "grad_norm": 1.5294065475463867, "learning_rate": 0.00017568574971793644, "loss": 0.6493046760559082, "step": 159300 }, { "epoch": 0.9469717234041288, "grad_norm": 1.584924340248108, "learning_rate": 0.00017568149420752212, "loss": 0.6324356079101563, "step": 159310 }, { "epoch": 0.9470311654807972, "grad_norm": 1.8916741609573364, "learning_rate": 0.00017567723838290896, "loss": 0.6487330436706543, "step": 159320 }, { "epoch": 0.9470906075574657, "grad_norm": 1.28373122215271, "learning_rate": 0.0001756729822441174, "loss": 0.6527878761291503, "step": 159330 }, { "epoch": 0.9471500496341341, "grad_norm": 1.9136497974395752, "learning_rate": 0.00017566872579116773, "loss": 0.6167535305023193, "step": 159340 }, { "epoch": 0.9472094917108024, "grad_norm": 1.620606780052185, "learning_rate": 0.0001756644690240803, "loss": 0.6671451568603516, "step": 159350 }, { "epoch": 0.9472689337874708, "grad_norm": 1.7454196214675903, "learning_rate": 0.00017566021194287556, "loss": 0.6732405185699463, "step": 159360 }, { "epoch": 0.9473283758641392, "grad_norm": 1.3179097175598145, "learning_rate": 0.0001756559545475738, "loss": 0.621032428741455, "step": 159370 }, { "epoch": 0.9473878179408076, "grad_norm": 1.3163065910339355, "learning_rate": 0.0001756516968381954, "loss": 0.6173373222351074, "step": 159380 }, { "epoch": 0.9474472600174759, "grad_norm": 1.7949789762496948, "learning_rate": 0.00017564743881476078, "loss": 0.6816159248352051, "step": 159390 }, { "epoch": 0.9475067020941443, "grad_norm": 1.7006804943084717, "learning_rate": 0.00017564318047729024, "loss": 0.668796443939209, "step": 159400 }, { "epoch": 0.9475661441708128, "grad_norm": 1.636470079421997, "learning_rate": 0.00017563892182580418, "loss": 0.6489876270294189, "step": 159410 }, { "epoch": 0.9476255862474812, "grad_norm": 1.747631311416626, "learning_rate": 0.00017563466286032298, "loss": 0.6600315570831299, "step": 159420 }, { "epoch": 0.9476850283241496, "grad_norm": 1.6002018451690674, "learning_rate": 0.000175630403580867, "loss": 0.6236237525939942, "step": 159430 }, { "epoch": 0.9477444704008179, "grad_norm": 1.676940679550171, "learning_rate": 0.0001756261439874566, "loss": 0.6736740112304688, "step": 159440 }, { "epoch": 0.9478039124774863, "grad_norm": 1.6482945680618286, "learning_rate": 0.00017562188408011217, "loss": 0.657513427734375, "step": 159450 }, { "epoch": 0.9478633545541547, "grad_norm": 1.4318305253982544, "learning_rate": 0.0001756176238588541, "loss": 0.621082878112793, "step": 159460 }, { "epoch": 0.9479227966308231, "grad_norm": 1.736491084098816, "learning_rate": 0.00017561336332370275, "loss": 0.6392898082733154, "step": 159470 }, { "epoch": 0.9479822387074914, "grad_norm": 1.8759446144104004, "learning_rate": 0.00017560910247467856, "loss": 0.6694716930389404, "step": 159480 }, { "epoch": 0.9480416807841598, "grad_norm": 1.4589608907699585, "learning_rate": 0.0001756048413118018, "loss": 0.7245912551879883, "step": 159490 }, { "epoch": 0.9481011228608283, "grad_norm": 1.3620274066925049, "learning_rate": 0.00017560057983509298, "loss": 0.6789384841918945, "step": 159500 }, { "epoch": 0.9481605649374967, "grad_norm": 1.5839585065841675, "learning_rate": 0.00017559631804457237, "loss": 0.6087379455566406, "step": 159510 }, { "epoch": 0.9482200070141651, "grad_norm": 1.3810434341430664, "learning_rate": 0.00017559205594026045, "loss": 0.6569426536560059, "step": 159520 }, { "epoch": 0.9482794490908334, "grad_norm": 1.2774217128753662, "learning_rate": 0.00017558779352217754, "loss": 0.5990467071533203, "step": 159530 }, { "epoch": 0.9483388911675018, "grad_norm": 1.437224268913269, "learning_rate": 0.00017558353079034412, "loss": 0.5990823268890381, "step": 159540 }, { "epoch": 0.9483983332441702, "grad_norm": 1.9780908823013306, "learning_rate": 0.00017557926774478046, "loss": 0.6735307693481445, "step": 159550 }, { "epoch": 0.9484577753208386, "grad_norm": 1.859618902206421, "learning_rate": 0.000175575004385507, "loss": 0.6695936679840088, "step": 159560 }, { "epoch": 0.948517217397507, "grad_norm": 1.4530460834503174, "learning_rate": 0.00017557074071254423, "loss": 0.6316367149353027, "step": 159570 }, { "epoch": 0.9485766594741754, "grad_norm": 1.5966190099716187, "learning_rate": 0.00017556647672591243, "loss": 0.6142120361328125, "step": 159580 }, { "epoch": 0.9486361015508438, "grad_norm": 1.4819307327270508, "learning_rate": 0.00017556221242563197, "loss": 0.666492509841919, "step": 159590 }, { "epoch": 0.9486955436275122, "grad_norm": 1.5217936038970947, "learning_rate": 0.00017555794781172338, "loss": 0.6444644451141357, "step": 159600 }, { "epoch": 0.9487549857041806, "grad_norm": 1.8902524709701538, "learning_rate": 0.000175553682884207, "loss": 0.5803076744079589, "step": 159610 }, { "epoch": 0.9488144277808489, "grad_norm": 1.5892932415008545, "learning_rate": 0.0001755494176431032, "loss": 0.6023079872131347, "step": 159620 }, { "epoch": 0.9488738698575173, "grad_norm": 1.6787197589874268, "learning_rate": 0.0001755451520884324, "loss": 0.6812264442443847, "step": 159630 }, { "epoch": 0.9489333119341857, "grad_norm": 1.6455166339874268, "learning_rate": 0.00017554088622021501, "loss": 0.6636150360107422, "step": 159640 }, { "epoch": 0.9489927540108541, "grad_norm": 2.0145225524902344, "learning_rate": 0.00017553662003847147, "loss": 0.6842659950256348, "step": 159650 }, { "epoch": 0.9490521960875226, "grad_norm": 1.753013014793396, "learning_rate": 0.00017553235354322212, "loss": 0.6213313102722168, "step": 159660 }, { "epoch": 0.9491116381641909, "grad_norm": 1.4450148344039917, "learning_rate": 0.00017552808673448745, "loss": 0.6754179954528808, "step": 159670 }, { "epoch": 0.9491710802408593, "grad_norm": 1.7152111530303955, "learning_rate": 0.00017552381961228778, "loss": 0.6025270462036133, "step": 159680 }, { "epoch": 0.9492305223175277, "grad_norm": 1.7927401065826416, "learning_rate": 0.00017551955217664359, "loss": 0.6328472137451172, "step": 159690 }, { "epoch": 0.9492899643941961, "grad_norm": 1.7130006551742554, "learning_rate": 0.00017551528442757527, "loss": 0.5889951705932617, "step": 159700 }, { "epoch": 0.9493494064708645, "grad_norm": 1.6758928298950195, "learning_rate": 0.00017551101636510325, "loss": 0.5780697345733643, "step": 159710 }, { "epoch": 0.9494088485475328, "grad_norm": 1.5750359296798706, "learning_rate": 0.00017550674798924796, "loss": 0.6525076389312744, "step": 159720 }, { "epoch": 0.9494682906242012, "grad_norm": 1.5456148386001587, "learning_rate": 0.00017550247930002975, "loss": 0.6789112091064453, "step": 159730 }, { "epoch": 0.9495277327008697, "grad_norm": 1.648192286491394, "learning_rate": 0.00017549821029746911, "loss": 0.6603439331054688, "step": 159740 }, { "epoch": 0.9495871747775381, "grad_norm": 1.708216905593872, "learning_rate": 0.00017549394098158641, "loss": 0.6402838706970215, "step": 159750 }, { "epoch": 0.9496466168542064, "grad_norm": 1.5103583335876465, "learning_rate": 0.00017548967135240214, "loss": 0.6630730628967285, "step": 159760 }, { "epoch": 0.9497060589308748, "grad_norm": 1.6217771768569946, "learning_rate": 0.00017548540140993667, "loss": 0.6801815986633301, "step": 159770 }, { "epoch": 0.9497655010075432, "grad_norm": 1.6280815601348877, "learning_rate": 0.00017548113115421044, "loss": 0.6254977226257324, "step": 159780 }, { "epoch": 0.9498249430842116, "grad_norm": 1.6714307069778442, "learning_rate": 0.0001754768605852439, "loss": 0.6442714691162109, "step": 159790 }, { "epoch": 0.94988438516088, "grad_norm": 1.4866948127746582, "learning_rate": 0.0001754725897030574, "loss": 0.5579281330108643, "step": 159800 }, { "epoch": 0.9499438272375483, "grad_norm": 1.7170121669769287, "learning_rate": 0.00017546831850767146, "loss": 0.6547316074371338, "step": 159810 }, { "epoch": 0.9500032693142167, "grad_norm": 1.6196930408477783, "learning_rate": 0.00017546404699910647, "loss": 0.695721960067749, "step": 159820 }, { "epoch": 0.9500627113908852, "grad_norm": 1.5403075218200684, "learning_rate": 0.0001754597751773829, "loss": 0.6295745372772217, "step": 159830 }, { "epoch": 0.9501221534675536, "grad_norm": 1.692488431930542, "learning_rate": 0.0001754555030425211, "loss": 0.6449581146240234, "step": 159840 }, { "epoch": 0.9501815955442219, "grad_norm": 1.6224647760391235, "learning_rate": 0.00017545123059454161, "loss": 0.6639641761779785, "step": 159850 }, { "epoch": 0.9502410376208903, "grad_norm": 1.7524536848068237, "learning_rate": 0.00017544695783346486, "loss": 0.6858166694641114, "step": 159860 }, { "epoch": 0.9503004796975587, "grad_norm": 1.5335142612457275, "learning_rate": 0.00017544268475931118, "loss": 0.6787684440612793, "step": 159870 }, { "epoch": 0.9503599217742271, "grad_norm": 1.8476814031600952, "learning_rate": 0.00017543841137210113, "loss": 0.6728384971618653, "step": 159880 }, { "epoch": 0.9504193638508955, "grad_norm": 1.4634199142456055, "learning_rate": 0.0001754341376718551, "loss": 0.6568430423736572, "step": 159890 }, { "epoch": 0.9504788059275638, "grad_norm": 1.6261188983917236, "learning_rate": 0.0001754298636585935, "loss": 0.6089415550231934, "step": 159900 }, { "epoch": 0.9505382480042323, "grad_norm": 1.4963735342025757, "learning_rate": 0.00017542558933233686, "loss": 0.6044646263122558, "step": 159910 }, { "epoch": 0.9505976900809007, "grad_norm": 2.1949126720428467, "learning_rate": 0.00017542131469310554, "loss": 0.6127778053283691, "step": 159920 }, { "epoch": 0.9506571321575691, "grad_norm": 1.8863602876663208, "learning_rate": 0.00017541703974092009, "loss": 0.7223011016845703, "step": 159930 }, { "epoch": 0.9507165742342375, "grad_norm": 1.997880458831787, "learning_rate": 0.00017541276447580087, "loss": 0.6393690586090088, "step": 159940 }, { "epoch": 0.9507760163109058, "grad_norm": 1.4020644426345825, "learning_rate": 0.00017540848889776832, "loss": 0.5971519947052002, "step": 159950 }, { "epoch": 0.9508354583875742, "grad_norm": 1.4338483810424805, "learning_rate": 0.000175404213006843, "loss": 0.5757009983062744, "step": 159960 }, { "epoch": 0.9508949004642426, "grad_norm": 1.605871319770813, "learning_rate": 0.00017539993680304526, "loss": 0.616220760345459, "step": 159970 }, { "epoch": 0.950954342540911, "grad_norm": 1.503719449043274, "learning_rate": 0.0001753956602863956, "loss": 0.6473044395446778, "step": 159980 }, { "epoch": 0.9510137846175793, "grad_norm": 1.7355350255966187, "learning_rate": 0.00017539138345691447, "loss": 0.6678003311157227, "step": 159990 }, { "epoch": 0.9510732266942478, "grad_norm": 1.969157099723816, "learning_rate": 0.00017538710631462233, "loss": 0.6815799713134766, "step": 160000 }, { "epoch": 0.9511326687709162, "grad_norm": 1.6650573015213013, "learning_rate": 0.0001753828288595397, "loss": 0.7167218685150146, "step": 160010 }, { "epoch": 0.9511921108475846, "grad_norm": 1.9272199869155884, "learning_rate": 0.0001753785510916869, "loss": 0.603210163116455, "step": 160020 }, { "epoch": 0.951251552924253, "grad_norm": 1.953244686126709, "learning_rate": 0.00017537427301108453, "loss": 0.6405301094055176, "step": 160030 }, { "epoch": 0.9513109950009213, "grad_norm": 1.8765162229537964, "learning_rate": 0.00017536999461775297, "loss": 0.6360551834106445, "step": 160040 }, { "epoch": 0.9513704370775897, "grad_norm": 1.8560938835144043, "learning_rate": 0.00017536571591171275, "loss": 0.6957637786865234, "step": 160050 }, { "epoch": 0.9514298791542581, "grad_norm": 1.7593287229537964, "learning_rate": 0.0001753614368929843, "loss": 0.6548994541168213, "step": 160060 }, { "epoch": 0.9514893212309266, "grad_norm": 1.6323095560073853, "learning_rate": 0.0001753571575615881, "loss": 0.6301867961883545, "step": 160070 }, { "epoch": 0.951548763307595, "grad_norm": 1.3538252115249634, "learning_rate": 0.00017535287791754458, "loss": 0.6450240135192871, "step": 160080 }, { "epoch": 0.9516082053842633, "grad_norm": 1.8125847578048706, "learning_rate": 0.00017534859796087429, "loss": 0.7846527099609375, "step": 160090 }, { "epoch": 0.9516676474609317, "grad_norm": 1.6709449291229248, "learning_rate": 0.00017534431769159766, "loss": 0.6234927654266358, "step": 160100 }, { "epoch": 0.9517270895376001, "grad_norm": 1.4057410955429077, "learning_rate": 0.0001753400371097351, "loss": 0.6347838401794433, "step": 160110 }, { "epoch": 0.9517865316142685, "grad_norm": 1.5247293710708618, "learning_rate": 0.00017533575621530727, "loss": 0.6258869171142578, "step": 160120 }, { "epoch": 0.9518459736909368, "grad_norm": 1.4953672885894775, "learning_rate": 0.00017533147500833446, "loss": 0.6422150611877442, "step": 160130 }, { "epoch": 0.9519054157676052, "grad_norm": 1.407218098640442, "learning_rate": 0.00017532719348883723, "loss": 0.6230090141296387, "step": 160140 }, { "epoch": 0.9519648578442736, "grad_norm": 1.8481022119522095, "learning_rate": 0.00017532291165683607, "loss": 0.6792315006256103, "step": 160150 }, { "epoch": 0.9520242999209421, "grad_norm": 1.2397688627243042, "learning_rate": 0.00017531862951235147, "loss": 0.5812190055847168, "step": 160160 }, { "epoch": 0.9520837419976105, "grad_norm": 1.5900613069534302, "learning_rate": 0.00017531434705540385, "loss": 0.6284295082092285, "step": 160170 }, { "epoch": 0.9521431840742788, "grad_norm": 1.7666079998016357, "learning_rate": 0.00017531006428601374, "loss": 0.6230602741241456, "step": 160180 }, { "epoch": 0.9522026261509472, "grad_norm": 2.1569595336914062, "learning_rate": 0.00017530578120420167, "loss": 0.567137336730957, "step": 160190 }, { "epoch": 0.9522620682276156, "grad_norm": 1.5999245643615723, "learning_rate": 0.00017530149780998805, "loss": 0.610226058959961, "step": 160200 }, { "epoch": 0.952321510304284, "grad_norm": 1.694417119026184, "learning_rate": 0.00017529721410339342, "loss": 0.7043728828430176, "step": 160210 }, { "epoch": 0.9523809523809523, "grad_norm": 1.6729907989501953, "learning_rate": 0.00017529293008443825, "loss": 0.6376773834228515, "step": 160220 }, { "epoch": 0.9524403944576207, "grad_norm": 1.6079633235931396, "learning_rate": 0.00017528864575314302, "loss": 0.6124698638916015, "step": 160230 }, { "epoch": 0.9524998365342892, "grad_norm": 1.6889264583587646, "learning_rate": 0.0001752843611095283, "loss": 0.6789830207824707, "step": 160240 }, { "epoch": 0.9525592786109576, "grad_norm": 1.5279823541641235, "learning_rate": 0.0001752800761536145, "loss": 0.638704490661621, "step": 160250 }, { "epoch": 0.952618720687626, "grad_norm": 1.580794334411621, "learning_rate": 0.00017527579088542214, "loss": 0.6181985855102539, "step": 160260 }, { "epoch": 0.9526781627642943, "grad_norm": 1.751841425895691, "learning_rate": 0.00017527150530497173, "loss": 0.6775250911712647, "step": 160270 }, { "epoch": 0.9527376048409627, "grad_norm": 2.184746503829956, "learning_rate": 0.00017526721941228378, "loss": 0.6654767036437989, "step": 160280 }, { "epoch": 0.9527970469176311, "grad_norm": 1.837618112564087, "learning_rate": 0.00017526293320737878, "loss": 0.6384056091308594, "step": 160290 }, { "epoch": 0.9528564889942995, "grad_norm": 1.5458896160125732, "learning_rate": 0.00017525864669027722, "loss": 0.6152313232421875, "step": 160300 }, { "epoch": 0.952915931070968, "grad_norm": 1.5889801979064941, "learning_rate": 0.00017525435986099965, "loss": 0.620487642288208, "step": 160310 }, { "epoch": 0.9529753731476363, "grad_norm": 1.6221270561218262, "learning_rate": 0.00017525007271956654, "loss": 0.6806163311004638, "step": 160320 }, { "epoch": 0.9530348152243047, "grad_norm": 1.6259210109710693, "learning_rate": 0.00017524578526599837, "loss": 0.7036755084991455, "step": 160330 }, { "epoch": 0.9530942573009731, "grad_norm": 1.4013302326202393, "learning_rate": 0.00017524149750031574, "loss": 0.6465271472930908, "step": 160340 }, { "epoch": 0.9531536993776415, "grad_norm": 1.9020987749099731, "learning_rate": 0.00017523720942253906, "loss": 0.6555109024047852, "step": 160350 }, { "epoch": 0.9532131414543098, "grad_norm": 1.5684713125228882, "learning_rate": 0.0001752329210326889, "loss": 0.6559762954711914, "step": 160360 }, { "epoch": 0.9532725835309782, "grad_norm": 1.7640025615692139, "learning_rate": 0.0001752286323307858, "loss": 0.5979755401611329, "step": 160370 }, { "epoch": 0.9533320256076466, "grad_norm": 1.4863837957382202, "learning_rate": 0.0001752243433168502, "loss": 0.6525712966918945, "step": 160380 }, { "epoch": 0.953391467684315, "grad_norm": 1.5026746988296509, "learning_rate": 0.0001752200539909027, "loss": 0.6150797843933106, "step": 160390 }, { "epoch": 0.9534509097609835, "grad_norm": 1.652368426322937, "learning_rate": 0.00017521576435296373, "loss": 0.6488184928894043, "step": 160400 }, { "epoch": 0.9535103518376518, "grad_norm": 1.9911513328552246, "learning_rate": 0.00017521147440305388, "loss": 0.6990010261535644, "step": 160410 }, { "epoch": 0.9535697939143202, "grad_norm": 1.4418772459030151, "learning_rate": 0.00017520718414119364, "loss": 0.649333143234253, "step": 160420 }, { "epoch": 0.9536292359909886, "grad_norm": 1.8189581632614136, "learning_rate": 0.00017520289356740356, "loss": 0.6304301261901856, "step": 160430 }, { "epoch": 0.953688678067657, "grad_norm": 1.6115481853485107, "learning_rate": 0.0001751986026817041, "loss": 0.6192043781280517, "step": 160440 }, { "epoch": 0.9537481201443254, "grad_norm": 1.5446140766143799, "learning_rate": 0.00017519431148411586, "loss": 0.6471902847290039, "step": 160450 }, { "epoch": 0.9538075622209937, "grad_norm": 1.8147517442703247, "learning_rate": 0.00017519001997465936, "loss": 0.6100443363189697, "step": 160460 }, { "epoch": 0.9538670042976621, "grad_norm": 1.7232320308685303, "learning_rate": 0.0001751857281533551, "loss": 0.6588790416717529, "step": 160470 }, { "epoch": 0.9539264463743305, "grad_norm": 1.5489580631256104, "learning_rate": 0.0001751814360202236, "loss": 0.5691244602203369, "step": 160480 }, { "epoch": 0.953985888450999, "grad_norm": 1.7796951532363892, "learning_rate": 0.00017517714357528542, "loss": 0.5868123054504395, "step": 160490 }, { "epoch": 0.9540453305276673, "grad_norm": 1.4770023822784424, "learning_rate": 0.00017517285081856108, "loss": 0.6148128509521484, "step": 160500 }, { "epoch": 0.9541047726043357, "grad_norm": 1.7475576400756836, "learning_rate": 0.00017516855775007113, "loss": 0.645111083984375, "step": 160510 }, { "epoch": 0.9541642146810041, "grad_norm": 1.2780808210372925, "learning_rate": 0.0001751642643698361, "loss": 0.6181020736694336, "step": 160520 }, { "epoch": 0.9542236567576725, "grad_norm": 1.8571723699569702, "learning_rate": 0.00017515997067787652, "loss": 0.6873492240905762, "step": 160530 }, { "epoch": 0.9542830988343409, "grad_norm": 1.3347446918487549, "learning_rate": 0.00017515567667421292, "loss": 0.6621397972106934, "step": 160540 }, { "epoch": 0.9543425409110092, "grad_norm": 1.6702640056610107, "learning_rate": 0.00017515138235886586, "loss": 0.6051498889923096, "step": 160550 }, { "epoch": 0.9544019829876776, "grad_norm": 1.4754210710525513, "learning_rate": 0.0001751470877318559, "loss": 0.5877094745635987, "step": 160560 }, { "epoch": 0.9544614250643461, "grad_norm": 1.3864144086837769, "learning_rate": 0.00017514279279320355, "loss": 0.6471765518188477, "step": 160570 }, { "epoch": 0.9545208671410145, "grad_norm": 1.7776503562927246, "learning_rate": 0.00017513849754292936, "loss": 0.6852155685424804, "step": 160580 }, { "epoch": 0.9545803092176828, "grad_norm": 1.475813388824463, "learning_rate": 0.0001751342019810539, "loss": 0.6331904411315918, "step": 160590 }, { "epoch": 0.9546397512943512, "grad_norm": 1.23367440700531, "learning_rate": 0.0001751299061075977, "loss": 0.6371623992919921, "step": 160600 }, { "epoch": 0.9546991933710196, "grad_norm": 1.575397253036499, "learning_rate": 0.0001751256099225813, "loss": 0.6725619792938232, "step": 160610 }, { "epoch": 0.954758635447688, "grad_norm": 1.939024567604065, "learning_rate": 0.00017512131342602527, "loss": 0.6720892906188964, "step": 160620 }, { "epoch": 0.9548180775243564, "grad_norm": 1.3406256437301636, "learning_rate": 0.00017511701661795018, "loss": 0.6563643455505371, "step": 160630 }, { "epoch": 0.9548775196010247, "grad_norm": 1.4203025102615356, "learning_rate": 0.00017511271949837654, "loss": 0.5693888187408447, "step": 160640 }, { "epoch": 0.9549369616776932, "grad_norm": 1.57314932346344, "learning_rate": 0.00017510842206732493, "loss": 0.5642915725708008, "step": 160650 }, { "epoch": 0.9549964037543616, "grad_norm": 1.7006059885025024, "learning_rate": 0.00017510412432481591, "loss": 0.6891497135162353, "step": 160660 }, { "epoch": 0.95505584583103, "grad_norm": 1.511582612991333, "learning_rate": 0.00017509982627087001, "loss": 0.7001427173614502, "step": 160670 }, { "epoch": 0.9551152879076984, "grad_norm": 1.8167829513549805, "learning_rate": 0.00017509552790550789, "loss": 0.641754150390625, "step": 160680 }, { "epoch": 0.9551747299843667, "grad_norm": 1.834463357925415, "learning_rate": 0.00017509122922875, "loss": 0.6744471073150635, "step": 160690 }, { "epoch": 0.9552341720610351, "grad_norm": 1.7854422330856323, "learning_rate": 0.0001750869302406169, "loss": 0.5829092979431152, "step": 160700 }, { "epoch": 0.9552936141377035, "grad_norm": 1.5626518726348877, "learning_rate": 0.00017508263094112927, "loss": 0.5825145244598389, "step": 160710 }, { "epoch": 0.9553530562143719, "grad_norm": 1.6672642230987549, "learning_rate": 0.00017507833133030754, "loss": 0.6947233200073242, "step": 160720 }, { "epoch": 0.9554124982910402, "grad_norm": 1.591741681098938, "learning_rate": 0.00017507403140817237, "loss": 0.6530877113342285, "step": 160730 }, { "epoch": 0.9554719403677087, "grad_norm": 1.1015081405639648, "learning_rate": 0.0001750697311747443, "loss": 0.6626612186431885, "step": 160740 }, { "epoch": 0.9555313824443771, "grad_norm": 1.6231266260147095, "learning_rate": 0.00017506543063004388, "loss": 0.6444093704223632, "step": 160750 }, { "epoch": 0.9555908245210455, "grad_norm": 1.463578701019287, "learning_rate": 0.00017506112977409174, "loss": 0.6329106330871582, "step": 160760 }, { "epoch": 0.9556502665977139, "grad_norm": 1.2226768732070923, "learning_rate": 0.0001750568286069084, "loss": 0.6343184471130371, "step": 160770 }, { "epoch": 0.9557097086743822, "grad_norm": 1.505497694015503, "learning_rate": 0.00017505252712851443, "loss": 0.5663830757141113, "step": 160780 }, { "epoch": 0.9557691507510506, "grad_norm": 1.8455325365066528, "learning_rate": 0.00017504822533893043, "loss": 0.6216204643249512, "step": 160790 }, { "epoch": 0.955828592827719, "grad_norm": 1.585894227027893, "learning_rate": 0.000175043923238177, "loss": 0.6204939842224121, "step": 160800 }, { "epoch": 0.9558880349043875, "grad_norm": 1.62196946144104, "learning_rate": 0.0001750396208262747, "loss": 0.6201267719268799, "step": 160810 }, { "epoch": 0.9559474769810558, "grad_norm": 1.5788016319274902, "learning_rate": 0.0001750353181032441, "loss": 0.7209368228912354, "step": 160820 }, { "epoch": 0.9560069190577242, "grad_norm": 1.6278148889541626, "learning_rate": 0.00017503101506910582, "loss": 0.6887073516845703, "step": 160830 }, { "epoch": 0.9560663611343926, "grad_norm": 1.363978385925293, "learning_rate": 0.00017502671172388038, "loss": 0.6567075252532959, "step": 160840 }, { "epoch": 0.956125803211061, "grad_norm": 1.5903995037078857, "learning_rate": 0.0001750224080675884, "loss": 0.6490151405334472, "step": 160850 }, { "epoch": 0.9561852452877294, "grad_norm": 1.7144641876220703, "learning_rate": 0.0001750181041002505, "loss": 0.6970991611480712, "step": 160860 }, { "epoch": 0.9562446873643977, "grad_norm": 1.5124534368515015, "learning_rate": 0.00017501379982188723, "loss": 0.6792604923248291, "step": 160870 }, { "epoch": 0.9563041294410661, "grad_norm": 2.1785502433776855, "learning_rate": 0.0001750094952325192, "loss": 0.6660861015319824, "step": 160880 }, { "epoch": 0.9563635715177345, "grad_norm": 1.456394076347351, "learning_rate": 0.00017500519033216696, "loss": 0.6733426094055176, "step": 160890 }, { "epoch": 0.956423013594403, "grad_norm": 1.4218313694000244, "learning_rate": 0.00017500088512085112, "loss": 0.6680004119873046, "step": 160900 }, { "epoch": 0.9564824556710714, "grad_norm": 1.592767357826233, "learning_rate": 0.0001749965795985923, "loss": 0.6243979930877686, "step": 160910 }, { "epoch": 0.9565418977477397, "grad_norm": 1.2403639554977417, "learning_rate": 0.0001749922737654111, "loss": 0.6674653053283691, "step": 160920 }, { "epoch": 0.9566013398244081, "grad_norm": 1.5109912157058716, "learning_rate": 0.00017498796762132813, "loss": 0.6397167205810547, "step": 160930 }, { "epoch": 0.9566607819010765, "grad_norm": 1.6931838989257812, "learning_rate": 0.00017498366116636393, "loss": 0.638700532913208, "step": 160940 }, { "epoch": 0.9567202239777449, "grad_norm": 1.7605676651000977, "learning_rate": 0.00017497935440053913, "loss": 0.7046820640563964, "step": 160950 }, { "epoch": 0.9567796660544132, "grad_norm": 2.0381007194519043, "learning_rate": 0.0001749750473238743, "loss": 0.6345027446746826, "step": 160960 }, { "epoch": 0.9568391081310816, "grad_norm": 1.6626887321472168, "learning_rate": 0.00017497073993639014, "loss": 0.6614643096923828, "step": 160970 }, { "epoch": 0.95689855020775, "grad_norm": 1.764248013496399, "learning_rate": 0.00017496643223810713, "loss": 0.6448330879211426, "step": 160980 }, { "epoch": 0.9569579922844185, "grad_norm": 1.5429526567459106, "learning_rate": 0.000174962124229046, "loss": 0.6460816383361816, "step": 160990 }, { "epoch": 0.9570174343610869, "grad_norm": 1.5072511434555054, "learning_rate": 0.00017495781590922728, "loss": 0.6579487800598145, "step": 161000 }, { "epoch": 0.9570768764377552, "grad_norm": 1.6607674360275269, "learning_rate": 0.00017495350727867156, "loss": 0.6778989791870117, "step": 161010 }, { "epoch": 0.9571363185144236, "grad_norm": 1.6300514936447144, "learning_rate": 0.00017494919833739955, "loss": 0.6008146286010743, "step": 161020 }, { "epoch": 0.957195760591092, "grad_norm": 1.9238479137420654, "learning_rate": 0.00017494488908543175, "loss": 0.6465636253356933, "step": 161030 }, { "epoch": 0.9572552026677604, "grad_norm": 1.5967602729797363, "learning_rate": 0.00017494057952278886, "loss": 0.6545783996582031, "step": 161040 }, { "epoch": 0.9573146447444288, "grad_norm": 1.6142821311950684, "learning_rate": 0.00017493626964949142, "loss": 0.6223702430725098, "step": 161050 }, { "epoch": 0.9573740868210971, "grad_norm": 1.642553687095642, "learning_rate": 0.00017493195946556014, "loss": 0.6110081672668457, "step": 161060 }, { "epoch": 0.9574335288977656, "grad_norm": 1.7366188764572144, "learning_rate": 0.00017492764897101556, "loss": 0.6971762657165528, "step": 161070 }, { "epoch": 0.957492970974434, "grad_norm": 1.6978129148483276, "learning_rate": 0.00017492333816587828, "loss": 0.6223855018615723, "step": 161080 }, { "epoch": 0.9575524130511024, "grad_norm": 1.5494883060455322, "learning_rate": 0.000174919027050169, "loss": 0.6391457557678223, "step": 161090 }, { "epoch": 0.9576118551277707, "grad_norm": 1.5419306755065918, "learning_rate": 0.00017491471562390836, "loss": 0.6219498634338378, "step": 161100 }, { "epoch": 0.9576712972044391, "grad_norm": 1.5957238674163818, "learning_rate": 0.0001749104038871169, "loss": 0.681500244140625, "step": 161110 }, { "epoch": 0.9577307392811075, "grad_norm": 1.8014049530029297, "learning_rate": 0.00017490609183981528, "loss": 0.6131345748901367, "step": 161120 }, { "epoch": 0.9577901813577759, "grad_norm": 1.576607584953308, "learning_rate": 0.00017490177948202408, "loss": 0.621484375, "step": 161130 }, { "epoch": 0.9578496234344444, "grad_norm": 1.870505452156067, "learning_rate": 0.00017489746681376408, "loss": 0.6515165328979492, "step": 161140 }, { "epoch": 0.9579090655111127, "grad_norm": 1.363778829574585, "learning_rate": 0.00017489315383505574, "loss": 0.6386507987976074, "step": 161150 }, { "epoch": 0.9579685075877811, "grad_norm": 2.101440906524658, "learning_rate": 0.00017488884054591973, "loss": 0.6778830051422119, "step": 161160 }, { "epoch": 0.9580279496644495, "grad_norm": 1.4576692581176758, "learning_rate": 0.00017488452694637677, "loss": 0.6290469646453858, "step": 161170 }, { "epoch": 0.9580873917411179, "grad_norm": 1.682816982269287, "learning_rate": 0.0001748802130364474, "loss": 0.6354955673217774, "step": 161180 }, { "epoch": 0.9581468338177862, "grad_norm": 1.1981332302093506, "learning_rate": 0.00017487589881615235, "loss": 0.591900634765625, "step": 161190 }, { "epoch": 0.9582062758944546, "grad_norm": 1.3901110887527466, "learning_rate": 0.00017487158428551214, "loss": 0.629443359375, "step": 161200 }, { "epoch": 0.958265717971123, "grad_norm": 1.8563103675842285, "learning_rate": 0.0001748672694445475, "loss": 0.6072801113128662, "step": 161210 }, { "epoch": 0.9583251600477914, "grad_norm": 1.817482829093933, "learning_rate": 0.00017486295429327902, "loss": 0.7980656623840332, "step": 161220 }, { "epoch": 0.9583846021244599, "grad_norm": 1.6432050466537476, "learning_rate": 0.00017485863883172738, "loss": 0.6568604469299316, "step": 161230 }, { "epoch": 0.9584440442011282, "grad_norm": 1.507666826248169, "learning_rate": 0.00017485432305991324, "loss": 0.6042433261871338, "step": 161240 }, { "epoch": 0.9585034862777966, "grad_norm": 1.3899531364440918, "learning_rate": 0.00017485000697785717, "loss": 0.6468640804290772, "step": 161250 }, { "epoch": 0.958562928354465, "grad_norm": 1.6630743741989136, "learning_rate": 0.0001748456905855799, "loss": 0.6324065685272217, "step": 161260 }, { "epoch": 0.9586223704311334, "grad_norm": 1.8279266357421875, "learning_rate": 0.00017484137388310198, "loss": 0.5965417861938477, "step": 161270 }, { "epoch": 0.9586818125078018, "grad_norm": 1.4339536428451538, "learning_rate": 0.00017483705687044412, "loss": 0.6419493675231933, "step": 161280 }, { "epoch": 0.9587412545844701, "grad_norm": 1.6702202558517456, "learning_rate": 0.00017483273954762703, "loss": 0.6520246505737305, "step": 161290 }, { "epoch": 0.9588006966611385, "grad_norm": 1.490850567817688, "learning_rate": 0.00017482842191467125, "loss": 0.6490365982055664, "step": 161300 }, { "epoch": 0.958860138737807, "grad_norm": 1.8876451253890991, "learning_rate": 0.00017482410397159752, "loss": 0.6707462310791016, "step": 161310 }, { "epoch": 0.9589195808144754, "grad_norm": 1.9206310510635376, "learning_rate": 0.00017481978571842646, "loss": 0.6779347896575928, "step": 161320 }, { "epoch": 0.9589790228911437, "grad_norm": 1.6030277013778687, "learning_rate": 0.0001748154671551787, "loss": 0.6502065181732177, "step": 161330 }, { "epoch": 0.9590384649678121, "grad_norm": 1.3764970302581787, "learning_rate": 0.00017481114828187496, "loss": 0.6337679386138916, "step": 161340 }, { "epoch": 0.9590979070444805, "grad_norm": 2.033975839614868, "learning_rate": 0.00017480682909853582, "loss": 0.6497725486755371, "step": 161350 }, { "epoch": 0.9591573491211489, "grad_norm": 1.5407441854476929, "learning_rate": 0.00017480250960518203, "loss": 0.6403678894042969, "step": 161360 }, { "epoch": 0.9592167911978173, "grad_norm": 1.73557448387146, "learning_rate": 0.0001747981898018342, "loss": 0.6352801322937012, "step": 161370 }, { "epoch": 0.9592762332744856, "grad_norm": 1.3768351078033447, "learning_rate": 0.000174793869688513, "loss": 0.6685181140899659, "step": 161380 }, { "epoch": 0.959335675351154, "grad_norm": 1.4436452388763428, "learning_rate": 0.0001747895492652391, "loss": 0.5884124755859375, "step": 161390 }, { "epoch": 0.9593951174278225, "grad_norm": 1.5848712921142578, "learning_rate": 0.0001747852285320332, "loss": 0.7034701824188232, "step": 161400 }, { "epoch": 0.9594545595044909, "grad_norm": 1.7118229866027832, "learning_rate": 0.0001747809074889159, "loss": 0.7188357830047607, "step": 161410 }, { "epoch": 0.9595140015811593, "grad_norm": 1.3530335426330566, "learning_rate": 0.00017477658613590793, "loss": 0.687916374206543, "step": 161420 }, { "epoch": 0.9595734436578276, "grad_norm": 1.6820363998413086, "learning_rate": 0.00017477226447302994, "loss": 0.6820783615112305, "step": 161430 }, { "epoch": 0.959632885734496, "grad_norm": 2.0079143047332764, "learning_rate": 0.0001747679425003026, "loss": 0.6584583282470703, "step": 161440 }, { "epoch": 0.9596923278111644, "grad_norm": 1.523340106010437, "learning_rate": 0.00017476362021774658, "loss": 0.6650502204895019, "step": 161450 }, { "epoch": 0.9597517698878328, "grad_norm": 1.6861690282821655, "learning_rate": 0.00017475929762538256, "loss": 0.6441722393035889, "step": 161460 }, { "epoch": 0.9598112119645011, "grad_norm": 1.8021998405456543, "learning_rate": 0.00017475497472323125, "loss": 0.7226052284240723, "step": 161470 }, { "epoch": 0.9598706540411696, "grad_norm": 1.6133571863174438, "learning_rate": 0.00017475065151131332, "loss": 0.5997678756713867, "step": 161480 }, { "epoch": 0.959930096117838, "grad_norm": 1.6423490047454834, "learning_rate": 0.0001747463279896494, "loss": 0.6597573280334472, "step": 161490 }, { "epoch": 0.9599895381945064, "grad_norm": 1.8100626468658447, "learning_rate": 0.00017474200415826022, "loss": 0.7014768600463868, "step": 161500 }, { "epoch": 0.9600489802711748, "grad_norm": 1.5174750089645386, "learning_rate": 0.00017473768001716644, "loss": 0.6373820304870605, "step": 161510 }, { "epoch": 0.9601084223478431, "grad_norm": 1.6711585521697998, "learning_rate": 0.00017473335556638877, "loss": 0.6419244766235351, "step": 161520 }, { "epoch": 0.9601678644245115, "grad_norm": 1.8559958934783936, "learning_rate": 0.0001747290308059478, "loss": 0.6415180206298828, "step": 161530 }, { "epoch": 0.9602273065011799, "grad_norm": 1.4071441888809204, "learning_rate": 0.0001747247057358644, "loss": 0.6211968898773194, "step": 161540 }, { "epoch": 0.9602867485778483, "grad_norm": 1.3158645629882812, "learning_rate": 0.00017472038035615915, "loss": 0.6199163436889649, "step": 161550 }, { "epoch": 0.9603461906545167, "grad_norm": 1.4814006090164185, "learning_rate": 0.00017471605466685272, "loss": 0.6318978309631348, "step": 161560 }, { "epoch": 0.9604056327311851, "grad_norm": 1.8168917894363403, "learning_rate": 0.00017471172866796587, "loss": 0.6014670372009278, "step": 161570 }, { "epoch": 0.9604650748078535, "grad_norm": 1.5728977918624878, "learning_rate": 0.0001747074023595192, "loss": 0.6972280502319336, "step": 161580 }, { "epoch": 0.9605245168845219, "grad_norm": 1.8345894813537598, "learning_rate": 0.0001747030757415335, "loss": 0.6272465705871582, "step": 161590 }, { "epoch": 0.9605839589611903, "grad_norm": 1.7793010473251343, "learning_rate": 0.00017469874881402943, "loss": 0.5933315277099609, "step": 161600 }, { "epoch": 0.9606434010378586, "grad_norm": 1.5179771184921265, "learning_rate": 0.0001746944215770277, "loss": 0.6225615501403808, "step": 161610 }, { "epoch": 0.960702843114527, "grad_norm": 1.6260943412780762, "learning_rate": 0.000174690094030549, "loss": 0.6739909172058105, "step": 161620 }, { "epoch": 0.9607622851911954, "grad_norm": 1.4904636144638062, "learning_rate": 0.00017468576617461404, "loss": 0.6453791618347168, "step": 161630 }, { "epoch": 0.9608217272678639, "grad_norm": 1.5220588445663452, "learning_rate": 0.00017468143800924345, "loss": 0.6457517623901368, "step": 161640 }, { "epoch": 0.9608811693445323, "grad_norm": 1.4931117296218872, "learning_rate": 0.00017467710953445804, "loss": 0.5608166694641114, "step": 161650 }, { "epoch": 0.9609406114212006, "grad_norm": 1.9280797243118286, "learning_rate": 0.00017467278075027849, "loss": 0.6288340568542481, "step": 161660 }, { "epoch": 0.961000053497869, "grad_norm": 1.7080124616622925, "learning_rate": 0.00017466845165672548, "loss": 0.6646228313446045, "step": 161670 }, { "epoch": 0.9610594955745374, "grad_norm": 1.4909894466400146, "learning_rate": 0.00017466412225381972, "loss": 0.6169004440307617, "step": 161680 }, { "epoch": 0.9611189376512058, "grad_norm": 2.001574754714966, "learning_rate": 0.00017465979254158195, "loss": 0.6115573406219482, "step": 161690 }, { "epoch": 0.9611783797278741, "grad_norm": 1.6419192552566528, "learning_rate": 0.00017465546252003284, "loss": 0.6289766311645508, "step": 161700 }, { "epoch": 0.9612378218045425, "grad_norm": 2.1652727127075195, "learning_rate": 0.00017465113218919316, "loss": 0.6597301959991455, "step": 161710 }, { "epoch": 0.961297263881211, "grad_norm": 1.5624336004257202, "learning_rate": 0.00017464680154908357, "loss": 0.654144287109375, "step": 161720 }, { "epoch": 0.9613567059578794, "grad_norm": 2.056957721710205, "learning_rate": 0.00017464247059972482, "loss": 0.643935251235962, "step": 161730 }, { "epoch": 0.9614161480345478, "grad_norm": 1.3945046663284302, "learning_rate": 0.0001746381393411376, "loss": 0.6340298652648926, "step": 161740 }, { "epoch": 0.9614755901112161, "grad_norm": 1.784714698791504, "learning_rate": 0.00017463380777334267, "loss": 0.5928252220153809, "step": 161750 }, { "epoch": 0.9615350321878845, "grad_norm": 1.5586371421813965, "learning_rate": 0.0001746294758963607, "loss": 0.5965895175933837, "step": 161760 }, { "epoch": 0.9615944742645529, "grad_norm": 1.6714470386505127, "learning_rate": 0.00017462514371021246, "loss": 0.6290581703186036, "step": 161770 }, { "epoch": 0.9616539163412213, "grad_norm": 1.7343711853027344, "learning_rate": 0.0001746208112149186, "loss": 0.711332893371582, "step": 161780 }, { "epoch": 0.9617133584178897, "grad_norm": 1.3238955736160278, "learning_rate": 0.00017461647841049996, "loss": 0.6749716758728027, "step": 161790 }, { "epoch": 0.961772800494558, "grad_norm": 1.4867327213287354, "learning_rate": 0.00017461214529697718, "loss": 0.6054112434387207, "step": 161800 }, { "epoch": 0.9618322425712265, "grad_norm": 1.6686078310012817, "learning_rate": 0.000174607811874371, "loss": 0.5878633975982666, "step": 161810 }, { "epoch": 0.9618916846478949, "grad_norm": 1.5200235843658447, "learning_rate": 0.0001746034781427022, "loss": 0.5762593269348144, "step": 161820 }, { "epoch": 0.9619511267245633, "grad_norm": 1.4722875356674194, "learning_rate": 0.00017459914410199146, "loss": 0.6107373237609863, "step": 161830 }, { "epoch": 0.9620105688012316, "grad_norm": 1.3598557710647583, "learning_rate": 0.00017459480975225947, "loss": 0.7010872840881348, "step": 161840 }, { "epoch": 0.9620700108779, "grad_norm": 1.5869884490966797, "learning_rate": 0.0001745904750935271, "loss": 0.6534844398498535, "step": 161850 }, { "epoch": 0.9621294529545684, "grad_norm": 1.8346223831176758, "learning_rate": 0.000174586140125815, "loss": 0.6541682720184326, "step": 161860 }, { "epoch": 0.9621888950312368, "grad_norm": 1.544040322303772, "learning_rate": 0.00017458180484914384, "loss": 0.676344633102417, "step": 161870 }, { "epoch": 0.9622483371079052, "grad_norm": 1.4769212007522583, "learning_rate": 0.00017457746926353448, "loss": 0.6612895965576172, "step": 161880 }, { "epoch": 0.9623077791845736, "grad_norm": 2.0026910305023193, "learning_rate": 0.00017457313336900762, "loss": 0.6438629150390625, "step": 161890 }, { "epoch": 0.962367221261242, "grad_norm": 1.3768941164016724, "learning_rate": 0.00017456879716558398, "loss": 0.6476978302001953, "step": 161900 }, { "epoch": 0.9624266633379104, "grad_norm": 1.7390297651290894, "learning_rate": 0.00017456446065328428, "loss": 0.6551499366760254, "step": 161910 }, { "epoch": 0.9624861054145788, "grad_norm": 1.890836238861084, "learning_rate": 0.00017456012383212935, "loss": 0.6189135074615478, "step": 161920 }, { "epoch": 0.9625455474912471, "grad_norm": 1.5642457008361816, "learning_rate": 0.00017455578670213986, "loss": 0.6355470657348633, "step": 161930 }, { "epoch": 0.9626049895679155, "grad_norm": 1.4054681062698364, "learning_rate": 0.0001745514492633366, "loss": 0.6325795650482178, "step": 161940 }, { "epoch": 0.9626644316445839, "grad_norm": 1.646925449371338, "learning_rate": 0.00017454711151574027, "loss": 0.6074643135070801, "step": 161950 }, { "epoch": 0.9627238737212523, "grad_norm": 1.760623574256897, "learning_rate": 0.00017454277345937172, "loss": 0.6802196502685547, "step": 161960 }, { "epoch": 0.9627833157979208, "grad_norm": 1.7845757007598877, "learning_rate": 0.00017453843509425158, "loss": 0.6223078727722168, "step": 161970 }, { "epoch": 0.9628427578745891, "grad_norm": 1.4819368124008179, "learning_rate": 0.00017453409642040067, "loss": 0.6377283096313476, "step": 161980 }, { "epoch": 0.9629021999512575, "grad_norm": 1.8563112020492554, "learning_rate": 0.00017452975743783975, "loss": 0.7362456321716309, "step": 161990 }, { "epoch": 0.9629616420279259, "grad_norm": 1.4839810132980347, "learning_rate": 0.00017452541814658954, "loss": 0.6690796852111817, "step": 162000 }, { "epoch": 0.9630210841045943, "grad_norm": 1.9333429336547852, "learning_rate": 0.00017452107854667081, "loss": 0.6218433380126953, "step": 162010 }, { "epoch": 0.9630805261812627, "grad_norm": 1.7560036182403564, "learning_rate": 0.00017451673863810432, "loss": 0.6544681549072265, "step": 162020 }, { "epoch": 0.963139968257931, "grad_norm": 1.1787749528884888, "learning_rate": 0.00017451239842091086, "loss": 0.650786304473877, "step": 162030 }, { "epoch": 0.9631994103345994, "grad_norm": 1.4858222007751465, "learning_rate": 0.00017450805789511118, "loss": 0.601339054107666, "step": 162040 }, { "epoch": 0.9632588524112679, "grad_norm": 1.3930449485778809, "learning_rate": 0.000174503717060726, "loss": 0.6568633556365967, "step": 162050 }, { "epoch": 0.9633182944879363, "grad_norm": 1.9142396450042725, "learning_rate": 0.00017449937591777613, "loss": 0.6491811752319336, "step": 162060 }, { "epoch": 0.9633777365646046, "grad_norm": 1.5761512517929077, "learning_rate": 0.00017449503446628233, "loss": 0.6811715126037597, "step": 162070 }, { "epoch": 0.963437178641273, "grad_norm": 1.300585150718689, "learning_rate": 0.00017449069270626536, "loss": 0.6292176246643066, "step": 162080 }, { "epoch": 0.9634966207179414, "grad_norm": 1.5713591575622559, "learning_rate": 0.00017448635063774598, "loss": 0.6225629806518554, "step": 162090 }, { "epoch": 0.9635560627946098, "grad_norm": 1.6489170789718628, "learning_rate": 0.00017448200826074498, "loss": 0.6658571243286133, "step": 162100 }, { "epoch": 0.9636155048712782, "grad_norm": 1.7098309993743896, "learning_rate": 0.00017447766557528312, "loss": 0.7346813678741455, "step": 162110 }, { "epoch": 0.9636749469479465, "grad_norm": 1.4303457736968994, "learning_rate": 0.0001744733225813812, "loss": 0.6303790092468262, "step": 162120 }, { "epoch": 0.963734389024615, "grad_norm": 1.9481861591339111, "learning_rate": 0.00017446897927905997, "loss": 0.6964813709259033, "step": 162130 }, { "epoch": 0.9637938311012834, "grad_norm": 1.45576012134552, "learning_rate": 0.0001744646356683402, "loss": 0.5480992794036865, "step": 162140 }, { "epoch": 0.9638532731779518, "grad_norm": 1.8344175815582275, "learning_rate": 0.00017446029174924266, "loss": 0.6776562213897706, "step": 162150 }, { "epoch": 0.9639127152546202, "grad_norm": 1.4970117807388306, "learning_rate": 0.0001744559475217882, "loss": 0.6564108371734619, "step": 162160 }, { "epoch": 0.9639721573312885, "grad_norm": 2.3598787784576416, "learning_rate": 0.00017445160298599753, "loss": 0.6300041198730468, "step": 162170 }, { "epoch": 0.9640315994079569, "grad_norm": 1.4185692071914673, "learning_rate": 0.00017444725814189145, "loss": 0.6385033130645752, "step": 162180 }, { "epoch": 0.9640910414846253, "grad_norm": 2.950249671936035, "learning_rate": 0.00017444291298949073, "loss": 0.6280688285827637, "step": 162190 }, { "epoch": 0.9641504835612937, "grad_norm": 1.3862788677215576, "learning_rate": 0.0001744385675288162, "loss": 0.6461273670196533, "step": 162200 }, { "epoch": 0.964209925637962, "grad_norm": 1.7486848831176758, "learning_rate": 0.00017443422175988861, "loss": 0.6695221900939942, "step": 162210 }, { "epoch": 0.9642693677146305, "grad_norm": 1.2186570167541504, "learning_rate": 0.00017442987568272878, "loss": 0.600311279296875, "step": 162220 }, { "epoch": 0.9643288097912989, "grad_norm": 1.9475027322769165, "learning_rate": 0.00017442552929735746, "loss": 0.6486710548400879, "step": 162230 }, { "epoch": 0.9643882518679673, "grad_norm": 1.5102900266647339, "learning_rate": 0.00017442118260379546, "loss": 0.602692985534668, "step": 162240 }, { "epoch": 0.9644476939446357, "grad_norm": 1.6177879571914673, "learning_rate": 0.00017441683560206358, "loss": 0.6649098873138428, "step": 162250 }, { "epoch": 0.964507136021304, "grad_norm": 2.1325151920318604, "learning_rate": 0.00017441248829218263, "loss": 0.6363191604614258, "step": 162260 }, { "epoch": 0.9645665780979724, "grad_norm": 1.5797109603881836, "learning_rate": 0.00017440814067417337, "loss": 0.656101131439209, "step": 162270 }, { "epoch": 0.9646260201746408, "grad_norm": 1.921586275100708, "learning_rate": 0.00017440379274805663, "loss": 0.6844227313995361, "step": 162280 }, { "epoch": 0.9646854622513092, "grad_norm": 1.2913480997085571, "learning_rate": 0.00017439944451385318, "loss": 0.5908429145812988, "step": 162290 }, { "epoch": 0.9647449043279775, "grad_norm": 1.7945747375488281, "learning_rate": 0.0001743950959715838, "loss": 0.6486412048339844, "step": 162300 }, { "epoch": 0.964804346404646, "grad_norm": 1.6421613693237305, "learning_rate": 0.00017439074712126938, "loss": 0.6357314109802246, "step": 162310 }, { "epoch": 0.9648637884813144, "grad_norm": 1.7335139513015747, "learning_rate": 0.00017438639796293063, "loss": 0.6194369792938232, "step": 162320 }, { "epoch": 0.9649232305579828, "grad_norm": 1.564085841178894, "learning_rate": 0.00017438204849658842, "loss": 0.60052490234375, "step": 162330 }, { "epoch": 0.9649826726346512, "grad_norm": 1.4713170528411865, "learning_rate": 0.0001743776987222635, "loss": 0.6016439914703369, "step": 162340 }, { "epoch": 0.9650421147113195, "grad_norm": 1.5073139667510986, "learning_rate": 0.00017437334863997677, "loss": 0.6607266426086426, "step": 162350 }, { "epoch": 0.9651015567879879, "grad_norm": 1.9373211860656738, "learning_rate": 0.00017436899824974892, "loss": 0.6628637313842773, "step": 162360 }, { "epoch": 0.9651609988646563, "grad_norm": 2.0472235679626465, "learning_rate": 0.00017436464755160081, "loss": 0.6879523754119873, "step": 162370 }, { "epoch": 0.9652204409413248, "grad_norm": 1.363617181777954, "learning_rate": 0.0001743602965455533, "loss": 0.6436691284179688, "step": 162380 }, { "epoch": 0.9652798830179932, "grad_norm": 1.5776504278182983, "learning_rate": 0.00017435594523162713, "loss": 0.5723244667053222, "step": 162390 }, { "epoch": 0.9653393250946615, "grad_norm": 1.5000921487808228, "learning_rate": 0.0001743515936098432, "loss": 0.5814646720886231, "step": 162400 }, { "epoch": 0.9653987671713299, "grad_norm": 1.6496598720550537, "learning_rate": 0.0001743472416802222, "loss": 0.6773629188537598, "step": 162410 }, { "epoch": 0.9654582092479983, "grad_norm": 1.4380522966384888, "learning_rate": 0.0001743428894427851, "loss": 0.6252471446990967, "step": 162420 }, { "epoch": 0.9655176513246667, "grad_norm": 1.5405234098434448, "learning_rate": 0.00017433853689755263, "loss": 0.647282600402832, "step": 162430 }, { "epoch": 0.965577093401335, "grad_norm": 2.2464663982391357, "learning_rate": 0.00017433418404454558, "loss": 0.6339794158935547, "step": 162440 }, { "epoch": 0.9656365354780034, "grad_norm": 1.9470213651657104, "learning_rate": 0.00017432983088378482, "loss": 0.6737118244171143, "step": 162450 }, { "epoch": 0.9656959775546718, "grad_norm": 1.983380913734436, "learning_rate": 0.00017432547741529124, "loss": 0.6123558044433594, "step": 162460 }, { "epoch": 0.9657554196313403, "grad_norm": 1.6591413021087646, "learning_rate": 0.00017432112363908553, "loss": 0.5962953567504883, "step": 162470 }, { "epoch": 0.9658148617080087, "grad_norm": 1.6673898696899414, "learning_rate": 0.00017431676955518863, "loss": 0.6242499351501465, "step": 162480 }, { "epoch": 0.965874303784677, "grad_norm": 1.9120659828186035, "learning_rate": 0.00017431241516362132, "loss": 0.6183767318725586, "step": 162490 }, { "epoch": 0.9659337458613454, "grad_norm": 1.6582280397415161, "learning_rate": 0.0001743080604644044, "loss": 0.6376209259033203, "step": 162500 }, { "epoch": 0.9659931879380138, "grad_norm": 1.976320505142212, "learning_rate": 0.00017430370545755877, "loss": 0.6279228210449219, "step": 162510 }, { "epoch": 0.9660526300146822, "grad_norm": 1.3893333673477173, "learning_rate": 0.0001742993501431052, "loss": 0.6362606048583984, "step": 162520 }, { "epoch": 0.9661120720913506, "grad_norm": 1.4578745365142822, "learning_rate": 0.00017429499452106456, "loss": 0.5979039669036865, "step": 162530 }, { "epoch": 0.9661715141680189, "grad_norm": 1.816829800605774, "learning_rate": 0.00017429063859145767, "loss": 0.607251787185669, "step": 162540 }, { "epoch": 0.9662309562446874, "grad_norm": 1.3900563716888428, "learning_rate": 0.0001742862823543054, "loss": 0.6788806915283203, "step": 162550 }, { "epoch": 0.9662903983213558, "grad_norm": 1.6761046648025513, "learning_rate": 0.00017428192580962854, "loss": 0.6990347862243652, "step": 162560 }, { "epoch": 0.9663498403980242, "grad_norm": 1.470271348953247, "learning_rate": 0.000174277568957448, "loss": 0.617639684677124, "step": 162570 }, { "epoch": 0.9664092824746925, "grad_norm": 1.5269712209701538, "learning_rate": 0.00017427321179778454, "loss": 0.6168842315673828, "step": 162580 }, { "epoch": 0.9664687245513609, "grad_norm": 1.617743968963623, "learning_rate": 0.00017426885433065903, "loss": 0.6066566467285156, "step": 162590 }, { "epoch": 0.9665281666280293, "grad_norm": 1.6259299516677856, "learning_rate": 0.00017426449655609234, "loss": 0.6912832260131836, "step": 162600 }, { "epoch": 0.9665876087046977, "grad_norm": 1.3475415706634521, "learning_rate": 0.00017426013847410529, "loss": 0.6472125053405762, "step": 162610 }, { "epoch": 0.9666470507813661, "grad_norm": 1.8498185873031616, "learning_rate": 0.00017425578008471875, "loss": 0.6259123802185058, "step": 162620 }, { "epoch": 0.9667064928580344, "grad_norm": 1.5102590322494507, "learning_rate": 0.00017425142138795355, "loss": 0.6905297756195068, "step": 162630 }, { "epoch": 0.9667659349347029, "grad_norm": 1.3935177326202393, "learning_rate": 0.00017424706238383054, "loss": 0.673273754119873, "step": 162640 }, { "epoch": 0.9668253770113713, "grad_norm": 1.86202073097229, "learning_rate": 0.00017424270307237058, "loss": 0.6740745544433594, "step": 162650 }, { "epoch": 0.9668848190880397, "grad_norm": 1.2583662271499634, "learning_rate": 0.00017423834345359457, "loss": 0.6490809917449951, "step": 162660 }, { "epoch": 0.966944261164708, "grad_norm": 1.6391340494155884, "learning_rate": 0.00017423398352752324, "loss": 0.6037663459777832, "step": 162670 }, { "epoch": 0.9670037032413764, "grad_norm": 1.3738070726394653, "learning_rate": 0.0001742296232941776, "loss": 0.6096538543701172, "step": 162680 }, { "epoch": 0.9670631453180448, "grad_norm": 1.2790776491165161, "learning_rate": 0.0001742252627535784, "loss": 0.6364087104797364, "step": 162690 }, { "epoch": 0.9671225873947132, "grad_norm": 1.7433720827102661, "learning_rate": 0.0001742209019057465, "loss": 0.5821365356445313, "step": 162700 }, { "epoch": 0.9671820294713817, "grad_norm": 1.8882373571395874, "learning_rate": 0.00017421654075070283, "loss": 0.6591591835021973, "step": 162710 }, { "epoch": 0.96724147154805, "grad_norm": 1.5983808040618896, "learning_rate": 0.0001742121792884682, "loss": 0.6960986614227295, "step": 162720 }, { "epoch": 0.9673009136247184, "grad_norm": 1.2579927444458008, "learning_rate": 0.0001742078175190635, "loss": 0.6638102531433105, "step": 162730 }, { "epoch": 0.9673603557013868, "grad_norm": 1.9234068393707275, "learning_rate": 0.00017420345544250958, "loss": 0.6807115554809571, "step": 162740 }, { "epoch": 0.9674197977780552, "grad_norm": 1.5851192474365234, "learning_rate": 0.00017419909305882734, "loss": 0.6012064933776855, "step": 162750 }, { "epoch": 0.9674792398547236, "grad_norm": 1.7209528684616089, "learning_rate": 0.00017419473036803758, "loss": 0.6320686340332031, "step": 162760 }, { "epoch": 0.9675386819313919, "grad_norm": 1.8968756198883057, "learning_rate": 0.00017419036737016119, "loss": 0.6891278266906739, "step": 162770 }, { "epoch": 0.9675981240080603, "grad_norm": 1.6121516227722168, "learning_rate": 0.0001741860040652191, "loss": 0.6113594532012939, "step": 162780 }, { "epoch": 0.9676575660847287, "grad_norm": 1.4254878759384155, "learning_rate": 0.00017418164045323212, "loss": 0.7077884674072266, "step": 162790 }, { "epoch": 0.9677170081613972, "grad_norm": 1.5635242462158203, "learning_rate": 0.0001741772765342212, "loss": 0.6203380107879639, "step": 162800 }, { "epoch": 0.9677764502380655, "grad_norm": 1.783396601676941, "learning_rate": 0.00017417291230820714, "loss": 0.7084691047668457, "step": 162810 }, { "epoch": 0.9678358923147339, "grad_norm": 1.2945152521133423, "learning_rate": 0.0001741685477752108, "loss": 0.598923635482788, "step": 162820 }, { "epoch": 0.9678953343914023, "grad_norm": 1.60829758644104, "learning_rate": 0.0001741641829352531, "loss": 0.6735751152038574, "step": 162830 }, { "epoch": 0.9679547764680707, "grad_norm": 1.5354925394058228, "learning_rate": 0.00017415981778835492, "loss": 0.6306605339050293, "step": 162840 }, { "epoch": 0.9680142185447391, "grad_norm": 1.606855034828186, "learning_rate": 0.00017415545233453718, "loss": 0.6183244228363037, "step": 162850 }, { "epoch": 0.9680736606214074, "grad_norm": 1.9415733814239502, "learning_rate": 0.00017415108657382072, "loss": 0.6005880832672119, "step": 162860 }, { "epoch": 0.9681331026980758, "grad_norm": 1.4988642930984497, "learning_rate": 0.00017414672050622637, "loss": 0.648094367980957, "step": 162870 }, { "epoch": 0.9681925447747443, "grad_norm": 1.7101622819900513, "learning_rate": 0.00017414235413177513, "loss": 0.6377987861633301, "step": 162880 }, { "epoch": 0.9682519868514127, "grad_norm": 2.2025411128997803, "learning_rate": 0.00017413798745048782, "loss": 0.6295392036437988, "step": 162890 }, { "epoch": 0.9683114289280811, "grad_norm": 1.6807762384414673, "learning_rate": 0.00017413362046238534, "loss": 0.6875494480133056, "step": 162900 }, { "epoch": 0.9683708710047494, "grad_norm": 1.4887837171554565, "learning_rate": 0.00017412925316748857, "loss": 0.6619524002075196, "step": 162910 }, { "epoch": 0.9684303130814178, "grad_norm": 1.9604071378707886, "learning_rate": 0.00017412488556581838, "loss": 0.6530626773834228, "step": 162920 }, { "epoch": 0.9684897551580862, "grad_norm": 1.805893898010254, "learning_rate": 0.00017412051765739573, "loss": 0.6565789222717285, "step": 162930 }, { "epoch": 0.9685491972347546, "grad_norm": 2.2749388217926025, "learning_rate": 0.00017411614944224147, "loss": 0.605754280090332, "step": 162940 }, { "epoch": 0.9686086393114229, "grad_norm": 1.934226155281067, "learning_rate": 0.00017411178092037653, "loss": 0.6631438255310058, "step": 162950 }, { "epoch": 0.9686680813880914, "grad_norm": 1.5414320230484009, "learning_rate": 0.00017410741209182172, "loss": 0.6202276229858399, "step": 162960 }, { "epoch": 0.9687275234647598, "grad_norm": 1.4636857509613037, "learning_rate": 0.00017410304295659805, "loss": 0.6234102249145508, "step": 162970 }, { "epoch": 0.9687869655414282, "grad_norm": 1.3936759233474731, "learning_rate": 0.00017409867351472636, "loss": 0.6030651092529297, "step": 162980 }, { "epoch": 0.9688464076180966, "grad_norm": 1.1054470539093018, "learning_rate": 0.00017409430376622755, "loss": 0.6595768928527832, "step": 162990 }, { "epoch": 0.9689058496947649, "grad_norm": 1.5860035419464111, "learning_rate": 0.00017408993371112255, "loss": 0.6178291797637939, "step": 163000 }, { "epoch": 0.9689652917714333, "grad_norm": 2.3349366188049316, "learning_rate": 0.00017408556334943225, "loss": 0.6576834678649902, "step": 163010 }, { "epoch": 0.9690247338481017, "grad_norm": 1.7809677124023438, "learning_rate": 0.00017408119268117757, "loss": 0.6026893138885498, "step": 163020 }, { "epoch": 0.9690841759247701, "grad_norm": 2.068998098373413, "learning_rate": 0.00017407682170637938, "loss": 0.6665985107421875, "step": 163030 }, { "epoch": 0.9691436180014384, "grad_norm": 2.0212559700012207, "learning_rate": 0.00017407245042505863, "loss": 0.6396602153778076, "step": 163040 }, { "epoch": 0.9692030600781069, "grad_norm": 1.2503972053527832, "learning_rate": 0.0001740680788372362, "loss": 0.6215644836425781, "step": 163050 }, { "epoch": 0.9692625021547753, "grad_norm": 1.6114118099212646, "learning_rate": 0.00017406370694293306, "loss": 0.6682866096496582, "step": 163060 }, { "epoch": 0.9693219442314437, "grad_norm": 1.566765546798706, "learning_rate": 0.00017405933474217005, "loss": 0.6446115970611572, "step": 163070 }, { "epoch": 0.9693813863081121, "grad_norm": 1.504759430885315, "learning_rate": 0.00017405496223496812, "loss": 0.6469699382781983, "step": 163080 }, { "epoch": 0.9694408283847804, "grad_norm": 1.3554816246032715, "learning_rate": 0.00017405058942134818, "loss": 0.6076796054840088, "step": 163090 }, { "epoch": 0.9695002704614488, "grad_norm": 1.5748132467269897, "learning_rate": 0.00017404621630133117, "loss": 0.624351692199707, "step": 163100 }, { "epoch": 0.9695597125381172, "grad_norm": 1.5878584384918213, "learning_rate": 0.000174041842874938, "loss": 0.5849658966064453, "step": 163110 }, { "epoch": 0.9696191546147856, "grad_norm": 1.6581166982650757, "learning_rate": 0.00017403746914218957, "loss": 0.6457976341247559, "step": 163120 }, { "epoch": 0.9696785966914541, "grad_norm": 1.520541787147522, "learning_rate": 0.0001740330951031068, "loss": 0.6322054862976074, "step": 163130 }, { "epoch": 0.9697380387681224, "grad_norm": 1.4822181463241577, "learning_rate": 0.00017402872075771063, "loss": 0.6707401752471924, "step": 163140 }, { "epoch": 0.9697974808447908, "grad_norm": 1.315851092338562, "learning_rate": 0.00017402434610602204, "loss": 0.6468840599060058, "step": 163150 }, { "epoch": 0.9698569229214592, "grad_norm": 1.9540152549743652, "learning_rate": 0.00017401997114806185, "loss": 0.640727186203003, "step": 163160 }, { "epoch": 0.9699163649981276, "grad_norm": 1.7514512538909912, "learning_rate": 0.00017401559588385102, "loss": 0.6320095062255859, "step": 163170 }, { "epoch": 0.9699758070747959, "grad_norm": 1.599291443824768, "learning_rate": 0.00017401122031341054, "loss": 0.5999941349029541, "step": 163180 }, { "epoch": 0.9700352491514643, "grad_norm": 1.8199429512023926, "learning_rate": 0.00017400684443676125, "loss": 0.6428059577941895, "step": 163190 }, { "epoch": 0.9700946912281327, "grad_norm": 1.597031831741333, "learning_rate": 0.0001740024682539242, "loss": 0.6152936935424804, "step": 163200 }, { "epoch": 0.9701541333048012, "grad_norm": 1.8360624313354492, "learning_rate": 0.00017399809176492023, "loss": 0.6447766304016114, "step": 163210 }, { "epoch": 0.9702135753814696, "grad_norm": 1.6111490726470947, "learning_rate": 0.0001739937149697703, "loss": 0.6049764156341553, "step": 163220 }, { "epoch": 0.9702730174581379, "grad_norm": 1.6254582405090332, "learning_rate": 0.00017398933786849535, "loss": 0.7137397289276123, "step": 163230 }, { "epoch": 0.9703324595348063, "grad_norm": 1.8676245212554932, "learning_rate": 0.0001739849604611163, "loss": 0.6478515625, "step": 163240 }, { "epoch": 0.9703919016114747, "grad_norm": 1.7283855676651, "learning_rate": 0.00017398058274765415, "loss": 0.6683842658996582, "step": 163250 }, { "epoch": 0.9704513436881431, "grad_norm": 1.4828100204467773, "learning_rate": 0.0001739762047281298, "loss": 0.6260832786560059, "step": 163260 }, { "epoch": 0.9705107857648115, "grad_norm": 1.5449539422988892, "learning_rate": 0.00017397182640256417, "loss": 0.6876580238342285, "step": 163270 }, { "epoch": 0.9705702278414798, "grad_norm": 1.5401723384857178, "learning_rate": 0.00017396744777097825, "loss": 0.6389706134796143, "step": 163280 }, { "epoch": 0.9706296699181483, "grad_norm": 1.479849934577942, "learning_rate": 0.00017396306883339294, "loss": 0.6687936782836914, "step": 163290 }, { "epoch": 0.9706891119948167, "grad_norm": 1.8400050401687622, "learning_rate": 0.0001739586895898292, "loss": 0.7017383098602294, "step": 163300 }, { "epoch": 0.9707485540714851, "grad_norm": 1.4595109224319458, "learning_rate": 0.00017395431004030802, "loss": 0.6696394920349121, "step": 163310 }, { "epoch": 0.9708079961481534, "grad_norm": 1.5770779848098755, "learning_rate": 0.00017394993018485035, "loss": 0.6438930988311767, "step": 163320 }, { "epoch": 0.9708674382248218, "grad_norm": 1.8484666347503662, "learning_rate": 0.00017394555002347704, "loss": 0.6355499744415283, "step": 163330 }, { "epoch": 0.9709268803014902, "grad_norm": 1.6509435176849365, "learning_rate": 0.00017394116955620918, "loss": 0.6531123161315918, "step": 163340 }, { "epoch": 0.9709863223781586, "grad_norm": 1.750465750694275, "learning_rate": 0.00017393678878306764, "loss": 0.6929311752319336, "step": 163350 }, { "epoch": 0.971045764454827, "grad_norm": 1.6357812881469727, "learning_rate": 0.0001739324077040734, "loss": 0.6431671619415283, "step": 163360 }, { "epoch": 0.9711052065314953, "grad_norm": 1.651396632194519, "learning_rate": 0.0001739280263192474, "loss": 0.6549854278564453, "step": 163370 }, { "epoch": 0.9711646486081638, "grad_norm": 1.4257014989852905, "learning_rate": 0.00017392364462861062, "loss": 0.6238286972045899, "step": 163380 }, { "epoch": 0.9712240906848322, "grad_norm": 1.825505256652832, "learning_rate": 0.000173919262632184, "loss": 0.6548582077026367, "step": 163390 }, { "epoch": 0.9712835327615006, "grad_norm": 1.916292667388916, "learning_rate": 0.00017391488032998857, "loss": 0.6336217880249023, "step": 163400 }, { "epoch": 0.9713429748381689, "grad_norm": 1.7384928464889526, "learning_rate": 0.0001739104977220452, "loss": 0.6736648559570313, "step": 163410 }, { "epoch": 0.9714024169148373, "grad_norm": 1.895225167274475, "learning_rate": 0.0001739061148083749, "loss": 0.6151191711425781, "step": 163420 }, { "epoch": 0.9714618589915057, "grad_norm": 1.660153865814209, "learning_rate": 0.00017390173158899862, "loss": 0.6221866607666016, "step": 163430 }, { "epoch": 0.9715213010681741, "grad_norm": 1.772219181060791, "learning_rate": 0.00017389734806393735, "loss": 0.6796635150909424, "step": 163440 }, { "epoch": 0.9715807431448426, "grad_norm": 2.0374088287353516, "learning_rate": 0.00017389296423321203, "loss": 0.6422666549682617, "step": 163450 }, { "epoch": 0.9716401852215109, "grad_norm": 1.3359496593475342, "learning_rate": 0.0001738885800968437, "loss": 0.6531699657440185, "step": 163460 }, { "epoch": 0.9716996272981793, "grad_norm": 1.5899566411972046, "learning_rate": 0.00017388419565485323, "loss": 0.6079179763793945, "step": 163470 }, { "epoch": 0.9717590693748477, "grad_norm": 1.4673362970352173, "learning_rate": 0.0001738798109072617, "loss": 0.6165185451507569, "step": 163480 }, { "epoch": 0.9718185114515161, "grad_norm": 1.6322176456451416, "learning_rate": 0.00017387542585408999, "loss": 0.5858367443084717, "step": 163490 }, { "epoch": 0.9718779535281845, "grad_norm": 2.078235626220703, "learning_rate": 0.0001738710404953591, "loss": 0.5787981033325196, "step": 163500 }, { "epoch": 0.9719373956048528, "grad_norm": 1.651095986366272, "learning_rate": 0.00017386665483109005, "loss": 0.5954056739807129, "step": 163510 }, { "epoch": 0.9719968376815212, "grad_norm": 1.490912675857544, "learning_rate": 0.00017386226886130382, "loss": 0.6334398269653321, "step": 163520 }, { "epoch": 0.9720562797581896, "grad_norm": 1.47575044631958, "learning_rate": 0.0001738578825860213, "loss": 0.6254979133605957, "step": 163530 }, { "epoch": 0.9721157218348581, "grad_norm": 1.8680264949798584, "learning_rate": 0.0001738534960052636, "loss": 0.6144126892089844, "step": 163540 }, { "epoch": 0.9721751639115264, "grad_norm": 1.215380311012268, "learning_rate": 0.00017384910911905164, "loss": 0.639558219909668, "step": 163550 }, { "epoch": 0.9722346059881948, "grad_norm": 1.5785385370254517, "learning_rate": 0.00017384472192740638, "loss": 0.6587242603302002, "step": 163560 }, { "epoch": 0.9722940480648632, "grad_norm": 1.6314148902893066, "learning_rate": 0.00017384033443034884, "loss": 0.6296443939208984, "step": 163570 }, { "epoch": 0.9723534901415316, "grad_norm": 1.798683762550354, "learning_rate": 0.00017383594662790001, "loss": 0.5790766716003418, "step": 163580 }, { "epoch": 0.9724129322182, "grad_norm": 1.3449311256408691, "learning_rate": 0.00017383155852008088, "loss": 0.6262723922729492, "step": 163590 }, { "epoch": 0.9724723742948683, "grad_norm": 1.3880994319915771, "learning_rate": 0.00017382717010691243, "loss": 0.6604000091552734, "step": 163600 }, { "epoch": 0.9725318163715367, "grad_norm": 1.7912393808364868, "learning_rate": 0.00017382278138841563, "loss": 0.6475821018218995, "step": 163610 }, { "epoch": 0.9725912584482052, "grad_norm": 1.8341494798660278, "learning_rate": 0.00017381839236461154, "loss": 0.5871126174926757, "step": 163620 }, { "epoch": 0.9726507005248736, "grad_norm": 1.5854432582855225, "learning_rate": 0.0001738140030355211, "loss": 0.6345102310180664, "step": 163630 }, { "epoch": 0.972710142601542, "grad_norm": 1.3036149740219116, "learning_rate": 0.00017380961340116534, "loss": 0.6511956214904785, "step": 163640 }, { "epoch": 0.9727695846782103, "grad_norm": 1.791732907295227, "learning_rate": 0.00017380522346156522, "loss": 0.667069673538208, "step": 163650 }, { "epoch": 0.9728290267548787, "grad_norm": 1.7683972120285034, "learning_rate": 0.00017380083321674177, "loss": 0.7011192798614502, "step": 163660 }, { "epoch": 0.9728884688315471, "grad_norm": 1.6266083717346191, "learning_rate": 0.000173796442666716, "loss": 0.6509366512298584, "step": 163670 }, { "epoch": 0.9729479109082155, "grad_norm": 1.698951244354248, "learning_rate": 0.00017379205181150887, "loss": 0.6163786888122559, "step": 163680 }, { "epoch": 0.9730073529848838, "grad_norm": 1.7221351861953735, "learning_rate": 0.0001737876606511414, "loss": 0.6682494163513184, "step": 163690 }, { "epoch": 0.9730667950615522, "grad_norm": 1.7246757745742798, "learning_rate": 0.00017378326918563467, "loss": 0.6301834106445312, "step": 163700 }, { "epoch": 0.9731262371382207, "grad_norm": 2.1109132766723633, "learning_rate": 0.00017377887741500957, "loss": 0.7224269390106202, "step": 163710 }, { "epoch": 0.9731856792148891, "grad_norm": 1.430711269378662, "learning_rate": 0.00017377448533928717, "loss": 0.6316947937011719, "step": 163720 }, { "epoch": 0.9732451212915575, "grad_norm": 1.6709296703338623, "learning_rate": 0.0001737700929584885, "loss": 0.6333842277526855, "step": 163730 }, { "epoch": 0.9733045633682258, "grad_norm": 1.7423940896987915, "learning_rate": 0.00017376570027263454, "loss": 0.6759384155273438, "step": 163740 }, { "epoch": 0.9733640054448942, "grad_norm": 1.5461984872817993, "learning_rate": 0.0001737613072817463, "loss": 0.6695638656616211, "step": 163750 }, { "epoch": 0.9734234475215626, "grad_norm": 1.8055306673049927, "learning_rate": 0.0001737569139858448, "loss": 0.6336793899536133, "step": 163760 }, { "epoch": 0.973482889598231, "grad_norm": 1.5450278520584106, "learning_rate": 0.00017375252038495106, "loss": 0.6583209991455078, "step": 163770 }, { "epoch": 0.9735423316748993, "grad_norm": 1.6458295583724976, "learning_rate": 0.0001737481264790861, "loss": 0.6502914428710938, "step": 163780 }, { "epoch": 0.9736017737515678, "grad_norm": 1.3709712028503418, "learning_rate": 0.00017374373226827092, "loss": 0.6433110237121582, "step": 163790 }, { "epoch": 0.9736612158282362, "grad_norm": 1.6635076999664307, "learning_rate": 0.0001737393377525266, "loss": 0.6202907562255859, "step": 163800 }, { "epoch": 0.9737206579049046, "grad_norm": 1.6103429794311523, "learning_rate": 0.00017373494293187406, "loss": 0.6634880065917969, "step": 163810 }, { "epoch": 0.973780099981573, "grad_norm": 1.3847393989562988, "learning_rate": 0.00017373054780633443, "loss": 0.6445445060729981, "step": 163820 }, { "epoch": 0.9738395420582413, "grad_norm": 1.4994016885757446, "learning_rate": 0.00017372615237592866, "loss": 0.6219069480895996, "step": 163830 }, { "epoch": 0.9738989841349097, "grad_norm": 1.874579906463623, "learning_rate": 0.00017372175664067782, "loss": 0.6656107902526855, "step": 163840 }, { "epoch": 0.9739584262115781, "grad_norm": 1.4278780221939087, "learning_rate": 0.00017371736060060292, "loss": 0.6478240013122558, "step": 163850 }, { "epoch": 0.9740178682882465, "grad_norm": 1.4370121955871582, "learning_rate": 0.00017371296425572496, "loss": 0.6229077339172363, "step": 163860 }, { "epoch": 0.974077310364915, "grad_norm": 1.6721899509429932, "learning_rate": 0.00017370856760606503, "loss": 0.6438628673553467, "step": 163870 }, { "epoch": 0.9741367524415833, "grad_norm": 1.448959469795227, "learning_rate": 0.0001737041706516441, "loss": 0.6391614437103271, "step": 163880 }, { "epoch": 0.9741961945182517, "grad_norm": 1.8746289014816284, "learning_rate": 0.00017369977339248328, "loss": 0.6563441276550293, "step": 163890 }, { "epoch": 0.9742556365949201, "grad_norm": 1.6206904649734497, "learning_rate": 0.00017369537582860353, "loss": 0.6527740478515625, "step": 163900 }, { "epoch": 0.9743150786715885, "grad_norm": 1.5647141933441162, "learning_rate": 0.00017369097796002595, "loss": 0.6549818992614747, "step": 163910 }, { "epoch": 0.9743745207482568, "grad_norm": 2.3625526428222656, "learning_rate": 0.00017368657978677153, "loss": 0.7275706768035889, "step": 163920 }, { "epoch": 0.9744339628249252, "grad_norm": 1.7071037292480469, "learning_rate": 0.0001736821813088613, "loss": 0.6635540962219239, "step": 163930 }, { "epoch": 0.9744934049015936, "grad_norm": 2.003955364227295, "learning_rate": 0.00017367778252631638, "loss": 0.6433864593505859, "step": 163940 }, { "epoch": 0.974552846978262, "grad_norm": 1.8123221397399902, "learning_rate": 0.0001736733834391577, "loss": 0.6577085494995117, "step": 163950 }, { "epoch": 0.9746122890549305, "grad_norm": 2.2198984622955322, "learning_rate": 0.00017366898404740642, "loss": 0.6497224807739258, "step": 163960 }, { "epoch": 0.9746717311315988, "grad_norm": 1.6186954975128174, "learning_rate": 0.00017366458435108347, "loss": 0.6661031723022461, "step": 163970 }, { "epoch": 0.9747311732082672, "grad_norm": 1.4183024168014526, "learning_rate": 0.00017366018435021, "loss": 0.6600921154022217, "step": 163980 }, { "epoch": 0.9747906152849356, "grad_norm": 1.6257821321487427, "learning_rate": 0.00017365578404480701, "loss": 0.6172329902648925, "step": 163990 }, { "epoch": 0.974850057361604, "grad_norm": 1.849764347076416, "learning_rate": 0.00017365138343489552, "loss": 0.6587536811828614, "step": 164000 }, { "epoch": 0.9749094994382723, "grad_norm": 1.6193742752075195, "learning_rate": 0.0001736469825204966, "loss": 0.6752668380737304, "step": 164010 }, { "epoch": 0.9749689415149407, "grad_norm": 1.8631821870803833, "learning_rate": 0.00017364258130163134, "loss": 0.6314993858337402, "step": 164020 }, { "epoch": 0.9750283835916091, "grad_norm": 1.5560568571090698, "learning_rate": 0.0001736381797783208, "loss": 0.6464932441711426, "step": 164030 }, { "epoch": 0.9750878256682776, "grad_norm": 1.813348412513733, "learning_rate": 0.00017363377795058597, "loss": 0.682358694076538, "step": 164040 }, { "epoch": 0.975147267744946, "grad_norm": 1.5556046962738037, "learning_rate": 0.00017362937581844796, "loss": 0.6233662128448486, "step": 164050 }, { "epoch": 0.9752067098216143, "grad_norm": 1.5935593843460083, "learning_rate": 0.0001736249733819278, "loss": 0.62336745262146, "step": 164060 }, { "epoch": 0.9752661518982827, "grad_norm": 1.5502984523773193, "learning_rate": 0.00017362057064104655, "loss": 0.6329294204711914, "step": 164070 }, { "epoch": 0.9753255939749511, "grad_norm": 1.2044371366500854, "learning_rate": 0.00017361616759582532, "loss": 0.6531318664550781, "step": 164080 }, { "epoch": 0.9753850360516195, "grad_norm": 1.531752109527588, "learning_rate": 0.0001736117642462851, "loss": 0.6118951797485351, "step": 164090 }, { "epoch": 0.9754444781282879, "grad_norm": 1.5428447723388672, "learning_rate": 0.00017360736059244698, "loss": 0.6733694553375245, "step": 164100 }, { "epoch": 0.9755039202049562, "grad_norm": 1.6178158521652222, "learning_rate": 0.00017360295663433205, "loss": 0.6646861076354981, "step": 164110 }, { "epoch": 0.9755633622816247, "grad_norm": 1.7706464529037476, "learning_rate": 0.00017359855237196136, "loss": 0.6648737907409668, "step": 164120 }, { "epoch": 0.9756228043582931, "grad_norm": 1.7837356328964233, "learning_rate": 0.00017359414780535599, "loss": 0.6490211963653565, "step": 164130 }, { "epoch": 0.9756822464349615, "grad_norm": 2.0289087295532227, "learning_rate": 0.00017358974293453698, "loss": 0.6789948463439941, "step": 164140 }, { "epoch": 0.9757416885116298, "grad_norm": 1.5257662534713745, "learning_rate": 0.00017358533775952545, "loss": 0.6531191349029541, "step": 164150 }, { "epoch": 0.9758011305882982, "grad_norm": 1.2812936305999756, "learning_rate": 0.0001735809322803424, "loss": 0.6316788673400879, "step": 164160 }, { "epoch": 0.9758605726649666, "grad_norm": 1.2162256240844727, "learning_rate": 0.000173576526497009, "loss": 0.6483089447021484, "step": 164170 }, { "epoch": 0.975920014741635, "grad_norm": 1.462680459022522, "learning_rate": 0.00017357212040954625, "loss": 0.6304454803466797, "step": 164180 }, { "epoch": 0.9759794568183034, "grad_norm": 1.6928141117095947, "learning_rate": 0.00017356771401797524, "loss": 0.6525108337402343, "step": 164190 }, { "epoch": 0.9760388988949718, "grad_norm": 1.640105128288269, "learning_rate": 0.00017356330732231707, "loss": 0.6307401657104492, "step": 164200 }, { "epoch": 0.9760983409716402, "grad_norm": 1.7756437063217163, "learning_rate": 0.0001735589003225928, "loss": 0.6514166831970215, "step": 164210 }, { "epoch": 0.9761577830483086, "grad_norm": 1.6797853708267212, "learning_rate": 0.00017355449301882355, "loss": 0.6470291137695312, "step": 164220 }, { "epoch": 0.976217225124977, "grad_norm": 1.1776325702667236, "learning_rate": 0.00017355008541103034, "loss": 0.5719168663024903, "step": 164230 }, { "epoch": 0.9762766672016454, "grad_norm": 1.6105395555496216, "learning_rate": 0.0001735456774992343, "loss": 0.6133987426757812, "step": 164240 }, { "epoch": 0.9763361092783137, "grad_norm": 1.5763771533966064, "learning_rate": 0.00017354126928345655, "loss": 0.65155930519104, "step": 164250 }, { "epoch": 0.9763955513549821, "grad_norm": 1.7891165018081665, "learning_rate": 0.0001735368607637181, "loss": 0.6560341835021972, "step": 164260 }, { "epoch": 0.9764549934316505, "grad_norm": 1.7682825326919556, "learning_rate": 0.00017353245194004006, "loss": 0.6853960037231446, "step": 164270 }, { "epoch": 0.976514435508319, "grad_norm": 1.5871143341064453, "learning_rate": 0.00017352804281244353, "loss": 0.6156005859375, "step": 164280 }, { "epoch": 0.9765738775849873, "grad_norm": 1.6290849447250366, "learning_rate": 0.0001735236333809496, "loss": 0.7351607799530029, "step": 164290 }, { "epoch": 0.9766333196616557, "grad_norm": 1.321455955505371, "learning_rate": 0.0001735192236455794, "loss": 0.6289329528808594, "step": 164300 }, { "epoch": 0.9766927617383241, "grad_norm": 1.767048716545105, "learning_rate": 0.00017351481360635397, "loss": 0.6605383872985839, "step": 164310 }, { "epoch": 0.9767522038149925, "grad_norm": 1.7796770334243774, "learning_rate": 0.00017351040326329443, "loss": 0.6762583732604981, "step": 164320 }, { "epoch": 0.9768116458916609, "grad_norm": 1.708810567855835, "learning_rate": 0.0001735059926164219, "loss": 0.70173020362854, "step": 164330 }, { "epoch": 0.9768710879683292, "grad_norm": 1.6942589282989502, "learning_rate": 0.00017350158166575742, "loss": 0.6874144554138184, "step": 164340 }, { "epoch": 0.9769305300449976, "grad_norm": 1.5215098857879639, "learning_rate": 0.00017349717041132217, "loss": 0.6580731868743896, "step": 164350 }, { "epoch": 0.976989972121666, "grad_norm": 1.485661268234253, "learning_rate": 0.00017349275885313717, "loss": 0.6652113914489746, "step": 164360 }, { "epoch": 0.9770494141983345, "grad_norm": 1.6818379163742065, "learning_rate": 0.00017348834699122359, "loss": 0.6316362380981445, "step": 164370 }, { "epoch": 0.9771088562750028, "grad_norm": 1.668697714805603, "learning_rate": 0.00017348393482560247, "loss": 0.5909011363983154, "step": 164380 }, { "epoch": 0.9771682983516712, "grad_norm": 1.463280200958252, "learning_rate": 0.00017347952235629498, "loss": 0.587010669708252, "step": 164390 }, { "epoch": 0.9772277404283396, "grad_norm": 1.8137180805206299, "learning_rate": 0.00017347510958332218, "loss": 0.6004703998565674, "step": 164400 }, { "epoch": 0.977287182505008, "grad_norm": 1.7351880073547363, "learning_rate": 0.00017347069650670523, "loss": 0.5986154079437256, "step": 164410 }, { "epoch": 0.9773466245816764, "grad_norm": 1.7585417032241821, "learning_rate": 0.00017346628312646517, "loss": 0.6498492240905762, "step": 164420 }, { "epoch": 0.9774060666583447, "grad_norm": 1.6711536645889282, "learning_rate": 0.0001734618694426232, "loss": 0.627543306350708, "step": 164430 }, { "epoch": 0.9774655087350131, "grad_norm": 1.658202886581421, "learning_rate": 0.00017345745545520035, "loss": 0.6179548740386963, "step": 164440 }, { "epoch": 0.9775249508116816, "grad_norm": 1.86815345287323, "learning_rate": 0.00017345304116421774, "loss": 0.6409877300262451, "step": 164450 }, { "epoch": 0.97758439288835, "grad_norm": 1.8189393281936646, "learning_rate": 0.00017344862656969655, "loss": 0.6576858520507812, "step": 164460 }, { "epoch": 0.9776438349650184, "grad_norm": 2.034973621368408, "learning_rate": 0.0001734442116716579, "loss": 0.6184398651123046, "step": 164470 }, { "epoch": 0.9777032770416867, "grad_norm": 1.4684607982635498, "learning_rate": 0.00017343979647012285, "loss": 0.6106138706207276, "step": 164480 }, { "epoch": 0.9777627191183551, "grad_norm": 1.8321588039398193, "learning_rate": 0.00017343538096511256, "loss": 0.6407116889953614, "step": 164490 }, { "epoch": 0.9778221611950235, "grad_norm": 1.6386313438415527, "learning_rate": 0.0001734309651566481, "loss": 0.6337778091430664, "step": 164500 }, { "epoch": 0.9778816032716919, "grad_norm": 1.6020787954330444, "learning_rate": 0.00017342654904475068, "loss": 0.6166056632995606, "step": 164510 }, { "epoch": 0.9779410453483602, "grad_norm": 2.120736598968506, "learning_rate": 0.00017342213262944135, "loss": 0.6703433036804199, "step": 164520 }, { "epoch": 0.9780004874250287, "grad_norm": 1.4816231727600098, "learning_rate": 0.00017341771591074126, "loss": 0.5921967983245849, "step": 164530 }, { "epoch": 0.9780599295016971, "grad_norm": 1.84044349193573, "learning_rate": 0.00017341329888867155, "loss": 0.6596296787261963, "step": 164540 }, { "epoch": 0.9781193715783655, "grad_norm": 1.6006752252578735, "learning_rate": 0.00017340888156325334, "loss": 0.6652966022491456, "step": 164550 }, { "epoch": 0.9781788136550339, "grad_norm": 1.8871687650680542, "learning_rate": 0.00017340446393450775, "loss": 0.6286854267120361, "step": 164560 }, { "epoch": 0.9782382557317022, "grad_norm": 1.7993509769439697, "learning_rate": 0.00017340004600245593, "loss": 0.627086591720581, "step": 164570 }, { "epoch": 0.9782976978083706, "grad_norm": 1.8157153129577637, "learning_rate": 0.000173395627767119, "loss": 0.6246697425842285, "step": 164580 }, { "epoch": 0.978357139885039, "grad_norm": 2.053493022918701, "learning_rate": 0.00017339120922851817, "loss": 0.7200452804565429, "step": 164590 }, { "epoch": 0.9784165819617074, "grad_norm": 1.7792609930038452, "learning_rate": 0.00017338679038667447, "loss": 0.705956506729126, "step": 164600 }, { "epoch": 0.9784760240383759, "grad_norm": 1.9136745929718018, "learning_rate": 0.00017338237124160904, "loss": 0.6660210609436035, "step": 164610 }, { "epoch": 0.9785354661150442, "grad_norm": 1.5668153762817383, "learning_rate": 0.00017337795179334312, "loss": 0.58944673538208, "step": 164620 }, { "epoch": 0.9785949081917126, "grad_norm": 1.6788535118103027, "learning_rate": 0.00017337353204189776, "loss": 0.6508125305175781, "step": 164630 }, { "epoch": 0.978654350268381, "grad_norm": 1.629791498184204, "learning_rate": 0.00017336911198729413, "loss": 0.6604674339294434, "step": 164640 }, { "epoch": 0.9787137923450494, "grad_norm": 1.7389976978302002, "learning_rate": 0.0001733646916295534, "loss": 0.6410174369812012, "step": 164650 }, { "epoch": 0.9787732344217177, "grad_norm": 1.553829312324524, "learning_rate": 0.00017336027096869668, "loss": 0.5964191913604736, "step": 164660 }, { "epoch": 0.9788326764983861, "grad_norm": 1.5673439502716064, "learning_rate": 0.00017335585000474515, "loss": 0.6121506690979004, "step": 164670 }, { "epoch": 0.9788921185750545, "grad_norm": 1.4190064668655396, "learning_rate": 0.0001733514287377199, "loss": 0.5911595821380615, "step": 164680 }, { "epoch": 0.978951560651723, "grad_norm": 1.8471814393997192, "learning_rate": 0.00017334700716764215, "loss": 0.6279354095458984, "step": 164690 }, { "epoch": 0.9790110027283914, "grad_norm": 1.8069988489151, "learning_rate": 0.00017334258529453297, "loss": 0.6461676597595215, "step": 164700 }, { "epoch": 0.9790704448050597, "grad_norm": 1.6267274618148804, "learning_rate": 0.00017333816311841362, "loss": 0.6552411079406738, "step": 164710 }, { "epoch": 0.9791298868817281, "grad_norm": 1.347070574760437, "learning_rate": 0.00017333374063930516, "loss": 0.6024893760681153, "step": 164720 }, { "epoch": 0.9791893289583965, "grad_norm": 1.9340406656265259, "learning_rate": 0.0001733293178572288, "loss": 0.7007773876190185, "step": 164730 }, { "epoch": 0.9792487710350649, "grad_norm": 2.149583101272583, "learning_rate": 0.0001733248947722057, "loss": 0.7079466819763184, "step": 164740 }, { "epoch": 0.9793082131117332, "grad_norm": 1.3461012840270996, "learning_rate": 0.00017332047138425696, "loss": 0.6199390411376953, "step": 164750 }, { "epoch": 0.9793676551884016, "grad_norm": 1.050169825553894, "learning_rate": 0.0001733160476934038, "loss": 0.6319891929626464, "step": 164760 }, { "epoch": 0.97942709726507, "grad_norm": 1.4595305919647217, "learning_rate": 0.00017331162369966735, "loss": 0.6078435897827148, "step": 164770 }, { "epoch": 0.9794865393417385, "grad_norm": 1.924291729927063, "learning_rate": 0.00017330719940306878, "loss": 0.64219069480896, "step": 164780 }, { "epoch": 0.9795459814184069, "grad_norm": 1.338597059249878, "learning_rate": 0.00017330277480362926, "loss": 0.5943346500396729, "step": 164790 }, { "epoch": 0.9796054234950752, "grad_norm": 1.5665555000305176, "learning_rate": 0.00017329834990136998, "loss": 0.6417953491210937, "step": 164800 }, { "epoch": 0.9796648655717436, "grad_norm": 1.5548250675201416, "learning_rate": 0.00017329392469631202, "loss": 0.6611823081970215, "step": 164810 }, { "epoch": 0.979724307648412, "grad_norm": 1.5809922218322754, "learning_rate": 0.0001732894991884767, "loss": 0.7004443168640136, "step": 164820 }, { "epoch": 0.9797837497250804, "grad_norm": 1.9678095579147339, "learning_rate": 0.00017328507337788503, "loss": 0.6766694068908692, "step": 164830 }, { "epoch": 0.9798431918017488, "grad_norm": 1.8391631841659546, "learning_rate": 0.00017328064726455827, "loss": 0.6387873649597168, "step": 164840 }, { "epoch": 0.9799026338784171, "grad_norm": 2.3958170413970947, "learning_rate": 0.00017327622084851755, "loss": 0.6496382713317871, "step": 164850 }, { "epoch": 0.9799620759550856, "grad_norm": 1.717917799949646, "learning_rate": 0.00017327179412978408, "loss": 0.6746023178100586, "step": 164860 }, { "epoch": 0.980021518031754, "grad_norm": 1.7676503658294678, "learning_rate": 0.00017326736710837902, "loss": 0.6100556373596191, "step": 164870 }, { "epoch": 0.9800809601084224, "grad_norm": 1.695307731628418, "learning_rate": 0.00017326293978432359, "loss": 0.6974074363708496, "step": 164880 }, { "epoch": 0.9801404021850907, "grad_norm": 1.8180004358291626, "learning_rate": 0.0001732585121576389, "loss": 0.686952781677246, "step": 164890 }, { "epoch": 0.9801998442617591, "grad_norm": 2.059563398361206, "learning_rate": 0.00017325408422834616, "loss": 0.6561427116394043, "step": 164900 }, { "epoch": 0.9802592863384275, "grad_norm": 1.8821191787719727, "learning_rate": 0.00017324965599646653, "loss": 0.6262719631195068, "step": 164910 }, { "epoch": 0.9803187284150959, "grad_norm": 1.8867477178573608, "learning_rate": 0.00017324522746202126, "loss": 0.6441836833953858, "step": 164920 }, { "epoch": 0.9803781704917643, "grad_norm": 1.5208044052124023, "learning_rate": 0.00017324079862503146, "loss": 0.6094315052032471, "step": 164930 }, { "epoch": 0.9804376125684326, "grad_norm": 2.2206385135650635, "learning_rate": 0.00017323636948551839, "loss": 0.6799857139587402, "step": 164940 }, { "epoch": 0.9804970546451011, "grad_norm": 1.2482459545135498, "learning_rate": 0.00017323194004350317, "loss": 0.6258207798004151, "step": 164950 }, { "epoch": 0.9805564967217695, "grad_norm": 1.29774808883667, "learning_rate": 0.000173227510299007, "loss": 0.5763112545013428, "step": 164960 }, { "epoch": 0.9806159387984379, "grad_norm": 1.394376516342163, "learning_rate": 0.0001732230802520511, "loss": 0.6472399711608887, "step": 164970 }, { "epoch": 0.9806753808751063, "grad_norm": 1.5278781652450562, "learning_rate": 0.00017321864990265661, "loss": 0.6116931915283204, "step": 164980 }, { "epoch": 0.9807348229517746, "grad_norm": 1.6825377941131592, "learning_rate": 0.0001732142192508448, "loss": 0.620755386352539, "step": 164990 }, { "epoch": 0.980794265028443, "grad_norm": 1.1742472648620605, "learning_rate": 0.0001732097882966368, "loss": 0.5985980033874512, "step": 165000 }, { "epoch": 0.9808537071051114, "grad_norm": 1.3038856983184814, "learning_rate": 0.00017320535704005386, "loss": 0.6096381187438965, "step": 165010 }, { "epoch": 0.9809131491817799, "grad_norm": 1.2821602821350098, "learning_rate": 0.00017320092548111713, "loss": 0.6166036605834961, "step": 165020 }, { "epoch": 0.9809725912584482, "grad_norm": 1.7398127317428589, "learning_rate": 0.00017319649361984782, "loss": 0.7081336975097656, "step": 165030 }, { "epoch": 0.9810320333351166, "grad_norm": 1.7948740720748901, "learning_rate": 0.00017319206145626715, "loss": 0.595212173461914, "step": 165040 }, { "epoch": 0.981091475411785, "grad_norm": 1.6556782722473145, "learning_rate": 0.0001731876289903963, "loss": 0.6331316947937011, "step": 165050 }, { "epoch": 0.9811509174884534, "grad_norm": 1.6887000799179077, "learning_rate": 0.00017318319622225647, "loss": 0.6280447006225586, "step": 165060 }, { "epoch": 0.9812103595651218, "grad_norm": 1.6800668239593506, "learning_rate": 0.0001731787631518689, "loss": 0.7228809356689453, "step": 165070 }, { "epoch": 0.9812698016417901, "grad_norm": 1.4274684190750122, "learning_rate": 0.00017317432977925475, "loss": 0.6254447937011719, "step": 165080 }, { "epoch": 0.9813292437184585, "grad_norm": 1.4683730602264404, "learning_rate": 0.00017316989610443527, "loss": 0.6207540988922119, "step": 165090 }, { "epoch": 0.981388685795127, "grad_norm": 1.45828378200531, "learning_rate": 0.00017316546212743167, "loss": 0.6016716957092285, "step": 165100 }, { "epoch": 0.9814481278717954, "grad_norm": 1.7641212940216064, "learning_rate": 0.0001731610278482651, "loss": 0.5981770992279053, "step": 165110 }, { "epoch": 0.9815075699484637, "grad_norm": 2.030627727508545, "learning_rate": 0.00017315659326695685, "loss": 0.6767971038818359, "step": 165120 }, { "epoch": 0.9815670120251321, "grad_norm": 1.6427838802337646, "learning_rate": 0.00017315215838352807, "loss": 0.6348803520202637, "step": 165130 }, { "epoch": 0.9816264541018005, "grad_norm": 1.5188990831375122, "learning_rate": 0.00017314772319800004, "loss": 0.6161544322967529, "step": 165140 }, { "epoch": 0.9816858961784689, "grad_norm": 1.2664679288864136, "learning_rate": 0.00017314328771039393, "loss": 0.6369073867797852, "step": 165150 }, { "epoch": 0.9817453382551373, "grad_norm": 1.2808563709259033, "learning_rate": 0.00017313885192073094, "loss": 0.6519756317138672, "step": 165160 }, { "epoch": 0.9818047803318056, "grad_norm": 1.520541787147522, "learning_rate": 0.0001731344158290323, "loss": 0.6393579483032227, "step": 165170 }, { "epoch": 0.981864222408474, "grad_norm": 1.601435661315918, "learning_rate": 0.00017312997943531928, "loss": 0.7068936347961425, "step": 165180 }, { "epoch": 0.9819236644851425, "grad_norm": 1.3943052291870117, "learning_rate": 0.00017312554273961307, "loss": 0.6321468830108643, "step": 165190 }, { "epoch": 0.9819831065618109, "grad_norm": 1.6783424615859985, "learning_rate": 0.0001731211057419349, "loss": 0.6459455490112305, "step": 165200 }, { "epoch": 0.9820425486384793, "grad_norm": 1.2784335613250732, "learning_rate": 0.00017311666844230597, "loss": 0.5720556259155274, "step": 165210 }, { "epoch": 0.9821019907151476, "grad_norm": 1.6810554265975952, "learning_rate": 0.00017311223084074754, "loss": 0.6032411575317382, "step": 165220 }, { "epoch": 0.982161432791816, "grad_norm": 1.8645765781402588, "learning_rate": 0.0001731077929372808, "loss": 0.6576747894287109, "step": 165230 }, { "epoch": 0.9822208748684844, "grad_norm": 1.5223067998886108, "learning_rate": 0.000173103354731927, "loss": 0.6396690368652344, "step": 165240 }, { "epoch": 0.9822803169451528, "grad_norm": 1.7830723524093628, "learning_rate": 0.0001730989162247074, "loss": 0.694960355758667, "step": 165250 }, { "epoch": 0.9823397590218211, "grad_norm": 1.3916224241256714, "learning_rate": 0.00017309447741564323, "loss": 0.666368055343628, "step": 165260 }, { "epoch": 0.9823992010984895, "grad_norm": 1.3823864459991455, "learning_rate": 0.00017309003830475562, "loss": 0.6262149810791016, "step": 165270 }, { "epoch": 0.982458643175158, "grad_norm": 1.8612985610961914, "learning_rate": 0.00017308559889206597, "loss": 0.6237167358398438, "step": 165280 }, { "epoch": 0.9825180852518264, "grad_norm": 1.6768593788146973, "learning_rate": 0.00017308115917759537, "loss": 0.6387864112854004, "step": 165290 }, { "epoch": 0.9825775273284948, "grad_norm": 1.4747209548950195, "learning_rate": 0.00017307671916136515, "loss": 0.5774779319763184, "step": 165300 }, { "epoch": 0.9826369694051631, "grad_norm": 1.4865989685058594, "learning_rate": 0.0001730722788433965, "loss": 0.6270832061767578, "step": 165310 }, { "epoch": 0.9826964114818315, "grad_norm": 1.8624045848846436, "learning_rate": 0.0001730678382237107, "loss": 0.6061228752136231, "step": 165320 }, { "epoch": 0.9827558535584999, "grad_norm": 1.6189157962799072, "learning_rate": 0.00017306339730232894, "loss": 0.692170238494873, "step": 165330 }, { "epoch": 0.9828152956351683, "grad_norm": 1.7176295518875122, "learning_rate": 0.00017305895607927255, "loss": 0.6325733184814453, "step": 165340 }, { "epoch": 0.9828747377118368, "grad_norm": 1.7185560464859009, "learning_rate": 0.00017305451455456268, "loss": 0.6095039367675781, "step": 165350 }, { "epoch": 0.9829341797885051, "grad_norm": 1.61935293674469, "learning_rate": 0.00017305007272822064, "loss": 0.6491946220397949, "step": 165360 }, { "epoch": 0.9829936218651735, "grad_norm": 1.5921257734298706, "learning_rate": 0.00017304563060026765, "loss": 0.5816806316375732, "step": 165370 }, { "epoch": 0.9830530639418419, "grad_norm": 1.2791293859481812, "learning_rate": 0.00017304118817072493, "loss": 0.6512735843658447, "step": 165380 }, { "epoch": 0.9831125060185103, "grad_norm": 1.3280049562454224, "learning_rate": 0.00017303674543961382, "loss": 0.6481144428253174, "step": 165390 }, { "epoch": 0.9831719480951786, "grad_norm": 1.6115895509719849, "learning_rate": 0.0001730323024069555, "loss": 0.611180591583252, "step": 165400 }, { "epoch": 0.983231390171847, "grad_norm": 1.5873719453811646, "learning_rate": 0.00017302785907277125, "loss": 0.6526938438415527, "step": 165410 }, { "epoch": 0.9832908322485154, "grad_norm": 1.091291904449463, "learning_rate": 0.00017302341543708232, "loss": 0.6027089118957519, "step": 165420 }, { "epoch": 0.9833502743251838, "grad_norm": 1.6217495203018188, "learning_rate": 0.00017301897149990997, "loss": 0.6018052577972413, "step": 165430 }, { "epoch": 0.9834097164018523, "grad_norm": 1.4781404733657837, "learning_rate": 0.00017301452726127545, "loss": 0.6639529228210449, "step": 165440 }, { "epoch": 0.9834691584785206, "grad_norm": 1.4783577919006348, "learning_rate": 0.00017301008272120003, "loss": 0.6145359516143799, "step": 165450 }, { "epoch": 0.983528600555189, "grad_norm": 1.891397476196289, "learning_rate": 0.00017300563787970495, "loss": 0.6550501823425293, "step": 165460 }, { "epoch": 0.9835880426318574, "grad_norm": 1.7200071811676025, "learning_rate": 0.0001730011927368115, "loss": 0.635770845413208, "step": 165470 }, { "epoch": 0.9836474847085258, "grad_norm": 1.4253041744232178, "learning_rate": 0.0001729967472925409, "loss": 0.6950263500213623, "step": 165480 }, { "epoch": 0.9837069267851941, "grad_norm": 1.5636066198349, "learning_rate": 0.0001729923015469145, "loss": 0.698533296585083, "step": 165490 }, { "epoch": 0.9837663688618625, "grad_norm": 1.9219146966934204, "learning_rate": 0.0001729878554999535, "loss": 0.7061679363250732, "step": 165500 }, { "epoch": 0.9838258109385309, "grad_norm": 1.6754481792449951, "learning_rate": 0.00017298340915167918, "loss": 0.6382840156555176, "step": 165510 }, { "epoch": 0.9838852530151994, "grad_norm": 1.72300124168396, "learning_rate": 0.00017297896250211282, "loss": 0.6889135837554932, "step": 165520 }, { "epoch": 0.9839446950918678, "grad_norm": 1.6261602640151978, "learning_rate": 0.0001729745155512757, "loss": 0.6756845951080322, "step": 165530 }, { "epoch": 0.9840041371685361, "grad_norm": 1.6419419050216675, "learning_rate": 0.00017297006829918905, "loss": 0.6140695571899414, "step": 165540 }, { "epoch": 0.9840635792452045, "grad_norm": 2.092582941055298, "learning_rate": 0.00017296562074587416, "loss": 0.6229601860046386, "step": 165550 }, { "epoch": 0.9841230213218729, "grad_norm": 1.4493626356124878, "learning_rate": 0.00017296117289135237, "loss": 0.6404647827148438, "step": 165560 }, { "epoch": 0.9841824633985413, "grad_norm": 1.1397837400436401, "learning_rate": 0.00017295672473564489, "loss": 0.6083278656005859, "step": 165570 }, { "epoch": 0.9842419054752097, "grad_norm": 1.5501682758331299, "learning_rate": 0.00017295227627877298, "loss": 0.6516824722290039, "step": 165580 }, { "epoch": 0.984301347551878, "grad_norm": 1.669327735900879, "learning_rate": 0.00017294782752075795, "loss": 0.6633169651031494, "step": 165590 }, { "epoch": 0.9843607896285465, "grad_norm": 1.4564907550811768, "learning_rate": 0.0001729433784616211, "loss": 0.5943337440490722, "step": 165600 }, { "epoch": 0.9844202317052149, "grad_norm": 1.3021219968795776, "learning_rate": 0.0001729389291013837, "loss": 0.6074475288391114, "step": 165610 }, { "epoch": 0.9844796737818833, "grad_norm": 1.6390057802200317, "learning_rate": 0.00017293447944006704, "loss": 0.6625563621520996, "step": 165620 }, { "epoch": 0.9845391158585516, "grad_norm": 1.7063899040222168, "learning_rate": 0.00017293002947769238, "loss": 0.5974915981292724, "step": 165630 }, { "epoch": 0.98459855793522, "grad_norm": 1.8995221853256226, "learning_rate": 0.00017292557921428105, "loss": 0.6083069801330566, "step": 165640 }, { "epoch": 0.9846580000118884, "grad_norm": 1.6387742757797241, "learning_rate": 0.0001729211286498543, "loss": 0.6666118144989014, "step": 165650 }, { "epoch": 0.9847174420885568, "grad_norm": 1.4694286584854126, "learning_rate": 0.0001729166777844334, "loss": 0.6178129196166993, "step": 165660 }, { "epoch": 0.9847768841652252, "grad_norm": 1.7373207807540894, "learning_rate": 0.00017291222661803974, "loss": 0.6365399837493897, "step": 165670 }, { "epoch": 0.9848363262418935, "grad_norm": 1.1401170492172241, "learning_rate": 0.0001729077751506945, "loss": 0.6820992469787598, "step": 165680 }, { "epoch": 0.984895768318562, "grad_norm": 1.1720999479293823, "learning_rate": 0.00017290332338241904, "loss": 0.6776765823364258, "step": 165690 }, { "epoch": 0.9849552103952304, "grad_norm": 1.5738998651504517, "learning_rate": 0.00017289887131323464, "loss": 0.6769880294799805, "step": 165700 }, { "epoch": 0.9850146524718988, "grad_norm": 1.2966506481170654, "learning_rate": 0.00017289441894316257, "loss": 0.6786285400390625, "step": 165710 }, { "epoch": 0.9850740945485672, "grad_norm": 2.141174554824829, "learning_rate": 0.0001728899662722242, "loss": 0.6633100509643555, "step": 165720 }, { "epoch": 0.9851335366252355, "grad_norm": 1.7424414157867432, "learning_rate": 0.00017288551330044074, "loss": 0.6742466926574707, "step": 165730 }, { "epoch": 0.9851929787019039, "grad_norm": 1.661375641822815, "learning_rate": 0.00017288106002783356, "loss": 0.618131446838379, "step": 165740 }, { "epoch": 0.9852524207785723, "grad_norm": 1.4896353483200073, "learning_rate": 0.00017287660645442393, "loss": 0.6626201152801514, "step": 165750 }, { "epoch": 0.9853118628552407, "grad_norm": 1.2911033630371094, "learning_rate": 0.00017287215258023316, "loss": 0.634101676940918, "step": 165760 }, { "epoch": 0.985371304931909, "grad_norm": 1.8340286016464233, "learning_rate": 0.00017286769840528258, "loss": 0.6593605041503906, "step": 165770 }, { "epoch": 0.9854307470085775, "grad_norm": 1.2018890380859375, "learning_rate": 0.00017286324392959344, "loss": 0.6237935543060302, "step": 165780 }, { "epoch": 0.9854901890852459, "grad_norm": 1.6506245136260986, "learning_rate": 0.00017285878915318715, "loss": 0.6271531105041503, "step": 165790 }, { "epoch": 0.9855496311619143, "grad_norm": 1.3108876943588257, "learning_rate": 0.0001728543340760849, "loss": 0.5662242889404296, "step": 165800 }, { "epoch": 0.9856090732385827, "grad_norm": 1.2464258670806885, "learning_rate": 0.00017284987869830806, "loss": 0.5687151432037354, "step": 165810 }, { "epoch": 0.985668515315251, "grad_norm": 1.6048964262008667, "learning_rate": 0.00017284542301987795, "loss": 0.5968695163726807, "step": 165820 }, { "epoch": 0.9857279573919194, "grad_norm": 1.5151045322418213, "learning_rate": 0.00017284096704081584, "loss": 0.6706892013549804, "step": 165830 }, { "epoch": 0.9857873994685878, "grad_norm": 1.425494909286499, "learning_rate": 0.00017283651076114312, "loss": 0.6414447784423828, "step": 165840 }, { "epoch": 0.9858468415452563, "grad_norm": 1.6743476390838623, "learning_rate": 0.00017283205418088107, "loss": 0.5897557258605957, "step": 165850 }, { "epoch": 0.9859062836219246, "grad_norm": 1.4751321077346802, "learning_rate": 0.000172827597300051, "loss": 0.6462883949279785, "step": 165860 }, { "epoch": 0.985965725698593, "grad_norm": 1.460977554321289, "learning_rate": 0.0001728231401186742, "loss": 0.7396730422973633, "step": 165870 }, { "epoch": 0.9860251677752614, "grad_norm": 1.4617080688476562, "learning_rate": 0.0001728186826367721, "loss": 0.6551855087280274, "step": 165880 }, { "epoch": 0.9860846098519298, "grad_norm": 1.610911250114441, "learning_rate": 0.0001728142248543659, "loss": 0.6101973533630372, "step": 165890 }, { "epoch": 0.9861440519285982, "grad_norm": 1.856856346130371, "learning_rate": 0.000172809766771477, "loss": 0.6756937026977539, "step": 165900 }, { "epoch": 0.9862034940052665, "grad_norm": 1.6349408626556396, "learning_rate": 0.00017280530838812666, "loss": 0.6384961128234863, "step": 165910 }, { "epoch": 0.9862629360819349, "grad_norm": 2.0604066848754883, "learning_rate": 0.00017280084970433627, "loss": 0.602892255783081, "step": 165920 }, { "epoch": 0.9863223781586034, "grad_norm": 1.547574758529663, "learning_rate": 0.0001727963907201272, "loss": 0.6506598949432373, "step": 165930 }, { "epoch": 0.9863818202352718, "grad_norm": 1.8743716478347778, "learning_rate": 0.00017279193143552064, "loss": 0.7189372062683106, "step": 165940 }, { "epoch": 0.9864412623119402, "grad_norm": 1.3957067728042603, "learning_rate": 0.00017278747185053806, "loss": 0.6583095073699952, "step": 165950 }, { "epoch": 0.9865007043886085, "grad_norm": 1.3161365985870361, "learning_rate": 0.00017278301196520067, "loss": 0.6538887977600097, "step": 165960 }, { "epoch": 0.9865601464652769, "grad_norm": 1.5804671049118042, "learning_rate": 0.0001727785517795299, "loss": 0.6852879524230957, "step": 165970 }, { "epoch": 0.9866195885419453, "grad_norm": 1.731844186782837, "learning_rate": 0.00017277409129354707, "loss": 0.6715950012207031, "step": 165980 }, { "epoch": 0.9866790306186137, "grad_norm": 1.3999481201171875, "learning_rate": 0.0001727696305072735, "loss": 0.6571815490722657, "step": 165990 }, { "epoch": 0.986738472695282, "grad_norm": 1.8051888942718506, "learning_rate": 0.00017276516942073053, "loss": 0.6361928939819336, "step": 166000 }, { "epoch": 0.9867979147719504, "grad_norm": 1.653374195098877, "learning_rate": 0.0001727607080339395, "loss": 0.6250668525695801, "step": 166010 }, { "epoch": 0.9868573568486189, "grad_norm": 1.81074059009552, "learning_rate": 0.00017275624634692174, "loss": 0.6565849781036377, "step": 166020 }, { "epoch": 0.9869167989252873, "grad_norm": 1.4726083278656006, "learning_rate": 0.0001727517843596986, "loss": 0.6271532058715821, "step": 166030 }, { "epoch": 0.9869762410019557, "grad_norm": 1.477798581123352, "learning_rate": 0.00017274732207229145, "loss": 0.6131635665893554, "step": 166040 }, { "epoch": 0.987035683078624, "grad_norm": 1.7928359508514404, "learning_rate": 0.00017274285948472157, "loss": 0.6792553901672364, "step": 166050 }, { "epoch": 0.9870951251552924, "grad_norm": 1.6320534944534302, "learning_rate": 0.0001727383965970104, "loss": 0.6424067497253418, "step": 166060 }, { "epoch": 0.9871545672319608, "grad_norm": 1.899796724319458, "learning_rate": 0.00017273393340917924, "loss": 0.6836117744445801, "step": 166070 }, { "epoch": 0.9872140093086292, "grad_norm": 1.6582037210464478, "learning_rate": 0.00017272946992124942, "loss": 0.6974202156066894, "step": 166080 }, { "epoch": 0.9872734513852977, "grad_norm": 1.3990743160247803, "learning_rate": 0.0001727250061332424, "loss": 0.6277585506439209, "step": 166090 }, { "epoch": 0.987332893461966, "grad_norm": 1.6355637311935425, "learning_rate": 0.00017272054204517934, "loss": 0.5834083557128906, "step": 166100 }, { "epoch": 0.9873923355386344, "grad_norm": 1.8374550342559814, "learning_rate": 0.00017271607765708178, "loss": 0.6470073699951172, "step": 166110 }, { "epoch": 0.9874517776153028, "grad_norm": 1.7634809017181396, "learning_rate": 0.00017271161296897097, "loss": 0.6570443153381348, "step": 166120 }, { "epoch": 0.9875112196919712, "grad_norm": 1.7157585620880127, "learning_rate": 0.00017270714798086828, "loss": 0.6037521362304688, "step": 166130 }, { "epoch": 0.9875706617686395, "grad_norm": 1.9465336799621582, "learning_rate": 0.0001727026826927951, "loss": 0.6685371398925781, "step": 166140 }, { "epoch": 0.9876301038453079, "grad_norm": 1.6537500619888306, "learning_rate": 0.00017269821710477282, "loss": 0.7001066207885742, "step": 166150 }, { "epoch": 0.9876895459219763, "grad_norm": 1.6348505020141602, "learning_rate": 0.00017269375121682268, "loss": 0.6576908111572266, "step": 166160 }, { "epoch": 0.9877489879986447, "grad_norm": 1.6418403387069702, "learning_rate": 0.00017268928502896618, "loss": 0.6774585247039795, "step": 166170 }, { "epoch": 0.9878084300753132, "grad_norm": 2.0022435188293457, "learning_rate": 0.00017268481854122462, "loss": 0.5811329841613769, "step": 166180 }, { "epoch": 0.9878678721519815, "grad_norm": 2.164748430252075, "learning_rate": 0.00017268035175361938, "loss": 0.5698752403259277, "step": 166190 }, { "epoch": 0.9879273142286499, "grad_norm": 1.3351553678512573, "learning_rate": 0.00017267588466617176, "loss": 0.6333145141601563, "step": 166200 }, { "epoch": 0.9879867563053183, "grad_norm": 1.6323843002319336, "learning_rate": 0.00017267141727890327, "loss": 0.6513236999511719, "step": 166210 }, { "epoch": 0.9880461983819867, "grad_norm": 1.699786901473999, "learning_rate": 0.00017266694959183515, "loss": 0.5947233200073242, "step": 166220 }, { "epoch": 0.988105640458655, "grad_norm": 1.2927651405334473, "learning_rate": 0.00017266248160498885, "loss": 0.6539824485778809, "step": 166230 }, { "epoch": 0.9881650825353234, "grad_norm": 1.8557920455932617, "learning_rate": 0.00017265801331838574, "loss": 0.6886275291442872, "step": 166240 }, { "epoch": 0.9882245246119918, "grad_norm": 1.4152108430862427, "learning_rate": 0.0001726535447320471, "loss": 0.6499866485595703, "step": 166250 }, { "epoch": 0.9882839666886603, "grad_norm": 1.7763644456863403, "learning_rate": 0.00017264907584599445, "loss": 0.6809425354003906, "step": 166260 }, { "epoch": 0.9883434087653287, "grad_norm": 1.5723483562469482, "learning_rate": 0.00017264460666024904, "loss": 0.6319413185119629, "step": 166270 }, { "epoch": 0.988402850841997, "grad_norm": 1.5773040056228638, "learning_rate": 0.00017264013717483234, "loss": 0.6393924236297608, "step": 166280 }, { "epoch": 0.9884622929186654, "grad_norm": 1.463792085647583, "learning_rate": 0.0001726356673897657, "loss": 0.6695159435272217, "step": 166290 }, { "epoch": 0.9885217349953338, "grad_norm": 1.391741156578064, "learning_rate": 0.00017263119730507047, "loss": 0.6177549362182617, "step": 166300 }, { "epoch": 0.9885811770720022, "grad_norm": 1.5810184478759766, "learning_rate": 0.00017262672692076807, "loss": 0.5986463546752929, "step": 166310 }, { "epoch": 0.9886406191486706, "grad_norm": 1.2197213172912598, "learning_rate": 0.00017262225623687987, "loss": 0.719499921798706, "step": 166320 }, { "epoch": 0.9887000612253389, "grad_norm": 1.519345760345459, "learning_rate": 0.00017261778525342724, "loss": 0.6276013374328613, "step": 166330 }, { "epoch": 0.9887595033020073, "grad_norm": 1.5520532131195068, "learning_rate": 0.00017261331397043164, "loss": 0.6390762805938721, "step": 166340 }, { "epoch": 0.9888189453786758, "grad_norm": 1.9829577207565308, "learning_rate": 0.00017260884238791437, "loss": 0.6751569747924805, "step": 166350 }, { "epoch": 0.9888783874553442, "grad_norm": 1.3864792585372925, "learning_rate": 0.00017260437050589685, "loss": 0.7321770668029786, "step": 166360 }, { "epoch": 0.9889378295320125, "grad_norm": 1.7606494426727295, "learning_rate": 0.00017259989832440052, "loss": 0.5934237003326416, "step": 166370 }, { "epoch": 0.9889972716086809, "grad_norm": 1.8815510272979736, "learning_rate": 0.0001725954258434467, "loss": 0.6794463157653808, "step": 166380 }, { "epoch": 0.9890567136853493, "grad_norm": 1.5280187129974365, "learning_rate": 0.00017259095306305686, "loss": 0.5940483093261719, "step": 166390 }, { "epoch": 0.9891161557620177, "grad_norm": 1.7161176204681396, "learning_rate": 0.00017258647998325233, "loss": 0.6314657211303711, "step": 166400 }, { "epoch": 0.9891755978386861, "grad_norm": 1.7214823961257935, "learning_rate": 0.00017258200660405455, "loss": 0.6405316352844238, "step": 166410 }, { "epoch": 0.9892350399153544, "grad_norm": 1.6507912874221802, "learning_rate": 0.00017257753292548487, "loss": 0.6152688503265381, "step": 166420 }, { "epoch": 0.9892944819920229, "grad_norm": 1.4799233675003052, "learning_rate": 0.00017257305894756471, "loss": 0.6793342590332031, "step": 166430 }, { "epoch": 0.9893539240686913, "grad_norm": 1.938873052597046, "learning_rate": 0.00017256858467031556, "loss": 0.6794474601745606, "step": 166440 }, { "epoch": 0.9894133661453597, "grad_norm": 1.8981225490570068, "learning_rate": 0.0001725641100937587, "loss": 0.6351555824279785, "step": 166450 }, { "epoch": 0.9894728082220281, "grad_norm": 1.847951889038086, "learning_rate": 0.00017255963521791557, "loss": 0.6707603454589843, "step": 166460 }, { "epoch": 0.9895322502986964, "grad_norm": 1.4277623891830444, "learning_rate": 0.00017255516004280764, "loss": 0.6401370525360107, "step": 166470 }, { "epoch": 0.9895916923753648, "grad_norm": 1.5002723932266235, "learning_rate": 0.0001725506845684562, "loss": 0.6671265602111817, "step": 166480 }, { "epoch": 0.9896511344520332, "grad_norm": 1.689202070236206, "learning_rate": 0.0001725462087948828, "loss": 0.6433540344238281, "step": 166490 }, { "epoch": 0.9897105765287016, "grad_norm": 1.534686803817749, "learning_rate": 0.00017254173272210872, "loss": 0.5974585533142089, "step": 166500 }, { "epoch": 0.98977001860537, "grad_norm": 1.6317095756530762, "learning_rate": 0.00017253725635015544, "loss": 0.6353539943695068, "step": 166510 }, { "epoch": 0.9898294606820384, "grad_norm": 2.162691831588745, "learning_rate": 0.00017253277967904434, "loss": 0.6565915107727051, "step": 166520 }, { "epoch": 0.9898889027587068, "grad_norm": 1.3294453620910645, "learning_rate": 0.0001725283027087969, "loss": 0.5932509422302246, "step": 166530 }, { "epoch": 0.9899483448353752, "grad_norm": 1.8198240995407104, "learning_rate": 0.0001725238254394345, "loss": 0.7079501152038574, "step": 166540 }, { "epoch": 0.9900077869120436, "grad_norm": 1.565460205078125, "learning_rate": 0.00017251934787097854, "loss": 0.658119010925293, "step": 166550 }, { "epoch": 0.9900672289887119, "grad_norm": 1.8354068994522095, "learning_rate": 0.00017251487000345043, "loss": 0.6827393531799316, "step": 166560 }, { "epoch": 0.9901266710653803, "grad_norm": 1.5263370275497437, "learning_rate": 0.00017251039183687164, "loss": 0.6606040000915527, "step": 166570 }, { "epoch": 0.9901861131420487, "grad_norm": 1.2760493755340576, "learning_rate": 0.00017250591337126357, "loss": 0.6457296848297119, "step": 166580 }, { "epoch": 0.9902455552187172, "grad_norm": 1.5912036895751953, "learning_rate": 0.00017250143460664763, "loss": 0.6675129890441894, "step": 166590 }, { "epoch": 0.9903049972953855, "grad_norm": 1.7827601432800293, "learning_rate": 0.00017249695554304523, "loss": 0.6606377601623535, "step": 166600 }, { "epoch": 0.9903644393720539, "grad_norm": 1.6563074588775635, "learning_rate": 0.0001724924761804778, "loss": 0.6301089286804199, "step": 166610 }, { "epoch": 0.9904238814487223, "grad_norm": 1.677161693572998, "learning_rate": 0.00017248799651896685, "loss": 0.7364805221557618, "step": 166620 }, { "epoch": 0.9904833235253907, "grad_norm": 2.32133412361145, "learning_rate": 0.0001724835165585337, "loss": 0.6944070339202881, "step": 166630 }, { "epoch": 0.9905427656020591, "grad_norm": 1.4548414945602417, "learning_rate": 0.00017247903629919985, "loss": 0.6126186370849609, "step": 166640 }, { "epoch": 0.9906022076787274, "grad_norm": 1.6763720512390137, "learning_rate": 0.0001724745557409867, "loss": 0.6583164691925049, "step": 166650 }, { "epoch": 0.9906616497553958, "grad_norm": 1.2499746084213257, "learning_rate": 0.0001724700748839157, "loss": 0.6118155479431152, "step": 166660 }, { "epoch": 0.9907210918320642, "grad_norm": 2.9987332820892334, "learning_rate": 0.00017246559372800828, "loss": 0.7115639686584473, "step": 166670 }, { "epoch": 0.9907805339087327, "grad_norm": 1.361698031425476, "learning_rate": 0.00017246111227328583, "loss": 0.5978196144104004, "step": 166680 }, { "epoch": 0.9908399759854011, "grad_norm": 1.6913939714431763, "learning_rate": 0.0001724566305197699, "loss": 0.5855311393737793, "step": 166690 }, { "epoch": 0.9908994180620694, "grad_norm": 1.5259501934051514, "learning_rate": 0.00017245214846748182, "loss": 0.6297126293182373, "step": 166700 }, { "epoch": 0.9909588601387378, "grad_norm": 1.7473196983337402, "learning_rate": 0.00017244766611644306, "loss": 0.6660096168518066, "step": 166710 }, { "epoch": 0.9910183022154062, "grad_norm": 1.8434693813323975, "learning_rate": 0.00017244318346667508, "loss": 0.6385758399963379, "step": 166720 }, { "epoch": 0.9910777442920746, "grad_norm": 10.511941909790039, "learning_rate": 0.00017243870051819935, "loss": 0.6000933647155762, "step": 166730 }, { "epoch": 0.9911371863687429, "grad_norm": 1.5833549499511719, "learning_rate": 0.00017243421727103724, "loss": 0.6595640182495117, "step": 166740 }, { "epoch": 0.9911966284454113, "grad_norm": 1.7474826574325562, "learning_rate": 0.00017242973372521027, "loss": 0.7255893230438233, "step": 166750 }, { "epoch": 0.9912560705220798, "grad_norm": 1.543715476989746, "learning_rate": 0.00017242524988073983, "loss": 0.6311620235443115, "step": 166760 }, { "epoch": 0.9913155125987482, "grad_norm": 1.8589298725128174, "learning_rate": 0.0001724207657376474, "loss": 0.6483704566955566, "step": 166770 }, { "epoch": 0.9913749546754166, "grad_norm": 1.4776957035064697, "learning_rate": 0.00017241628129595444, "loss": 0.5794211387634277, "step": 166780 }, { "epoch": 0.9914343967520849, "grad_norm": 1.6648157835006714, "learning_rate": 0.00017241179655568242, "loss": 0.6264570713043213, "step": 166790 }, { "epoch": 0.9914938388287533, "grad_norm": 1.6470896005630493, "learning_rate": 0.0001724073115168527, "loss": 0.652247953414917, "step": 166800 }, { "epoch": 0.9915532809054217, "grad_norm": 1.8836480379104614, "learning_rate": 0.00017240282617948682, "loss": 0.6345852375030517, "step": 166810 }, { "epoch": 0.9916127229820901, "grad_norm": 1.4200693368911743, "learning_rate": 0.0001723983405436062, "loss": 0.6436676025390625, "step": 166820 }, { "epoch": 0.9916721650587585, "grad_norm": 1.3746784925460815, "learning_rate": 0.00017239385460923235, "loss": 0.628989315032959, "step": 166830 }, { "epoch": 0.9917316071354269, "grad_norm": 1.6906553506851196, "learning_rate": 0.00017238936837638666, "loss": 0.6940961837768554, "step": 166840 }, { "epoch": 0.9917910492120953, "grad_norm": 1.5958642959594727, "learning_rate": 0.0001723848818450906, "loss": 0.6549274921417236, "step": 166850 }, { "epoch": 0.9918504912887637, "grad_norm": 1.693540096282959, "learning_rate": 0.00017238039501536569, "loss": 0.6038144111633301, "step": 166860 }, { "epoch": 0.9919099333654321, "grad_norm": 1.787222146987915, "learning_rate": 0.00017237590788723336, "loss": 0.6634360790252686, "step": 166870 }, { "epoch": 0.9919693754421004, "grad_norm": 1.6661790609359741, "learning_rate": 0.00017237142046071507, "loss": 0.6561896800994873, "step": 166880 }, { "epoch": 0.9920288175187688, "grad_norm": 1.6424039602279663, "learning_rate": 0.00017236693273583225, "loss": 0.6658812522888183, "step": 166890 }, { "epoch": 0.9920882595954372, "grad_norm": 1.436386227607727, "learning_rate": 0.00017236244471260644, "loss": 0.6757894992828369, "step": 166900 }, { "epoch": 0.9921477016721056, "grad_norm": 1.364735722541809, "learning_rate": 0.00017235795639105906, "loss": 0.632099723815918, "step": 166910 }, { "epoch": 0.9922071437487741, "grad_norm": 1.5536088943481445, "learning_rate": 0.00017235346777121158, "loss": 0.6367754936218262, "step": 166920 }, { "epoch": 0.9922665858254424, "grad_norm": 1.6924107074737549, "learning_rate": 0.00017234897885308554, "loss": 0.6275844573974609, "step": 166930 }, { "epoch": 0.9923260279021108, "grad_norm": 1.57261323928833, "learning_rate": 0.0001723444896367023, "loss": 0.6900865077972412, "step": 166940 }, { "epoch": 0.9923854699787792, "grad_norm": 1.3210489749908447, "learning_rate": 0.00017234000012208343, "loss": 0.6456219673156738, "step": 166950 }, { "epoch": 0.9924449120554476, "grad_norm": 1.955820918083191, "learning_rate": 0.00017233551030925036, "loss": 0.6420891284942627, "step": 166960 }, { "epoch": 0.9925043541321159, "grad_norm": 1.4621260166168213, "learning_rate": 0.0001723310201982246, "loss": 0.6326231956481934, "step": 166970 }, { "epoch": 0.9925637962087843, "grad_norm": 1.535695195198059, "learning_rate": 0.0001723265297890276, "loss": 0.6430535316467285, "step": 166980 }, { "epoch": 0.9926232382854527, "grad_norm": 1.497483253479004, "learning_rate": 0.00017232203908168082, "loss": 0.6257014274597168, "step": 166990 }, { "epoch": 0.9926826803621212, "grad_norm": 1.6241220235824585, "learning_rate": 0.00017231754807620582, "loss": 0.6494657516479492, "step": 167000 }, { "epoch": 0.9927421224387896, "grad_norm": 2.242006778717041, "learning_rate": 0.000172313056772624, "loss": 0.7117891788482666, "step": 167010 }, { "epoch": 0.9928015645154579, "grad_norm": 2.253425359725952, "learning_rate": 0.00017230856517095691, "loss": 0.6961988925933837, "step": 167020 }, { "epoch": 0.9928610065921263, "grad_norm": 1.717214584350586, "learning_rate": 0.000172304073271226, "loss": 0.6444788455963135, "step": 167030 }, { "epoch": 0.9929204486687947, "grad_norm": 1.6152987480163574, "learning_rate": 0.00017229958107345275, "loss": 0.6044766426086425, "step": 167040 }, { "epoch": 0.9929798907454631, "grad_norm": 1.426645278930664, "learning_rate": 0.00017229508857765865, "loss": 0.698941707611084, "step": 167050 }, { "epoch": 0.9930393328221315, "grad_norm": 1.6053402423858643, "learning_rate": 0.00017229059578386527, "loss": 0.6372232437133789, "step": 167060 }, { "epoch": 0.9930987748987998, "grad_norm": 1.5523911714553833, "learning_rate": 0.000172286102692094, "loss": 0.6176706314086914, "step": 167070 }, { "epoch": 0.9931582169754682, "grad_norm": 1.810554027557373, "learning_rate": 0.00017228160930236633, "loss": 0.6601494789123535, "step": 167080 }, { "epoch": 0.9932176590521367, "grad_norm": 1.3485454320907593, "learning_rate": 0.00017227711561470382, "loss": 0.6456803321838379, "step": 167090 }, { "epoch": 0.9932771011288051, "grad_norm": 1.2649052143096924, "learning_rate": 0.00017227262162912793, "loss": 0.632078742980957, "step": 167100 }, { "epoch": 0.9933365432054734, "grad_norm": 1.461248517036438, "learning_rate": 0.0001722681273456602, "loss": 0.6364839553833008, "step": 167110 }, { "epoch": 0.9933959852821418, "grad_norm": 1.6717877388000488, "learning_rate": 0.0001722636327643221, "loss": 0.6661493301391601, "step": 167120 }, { "epoch": 0.9934554273588102, "grad_norm": 1.5602611303329468, "learning_rate": 0.00017225913788513513, "loss": 0.587613582611084, "step": 167130 }, { "epoch": 0.9935148694354786, "grad_norm": 1.8459492921829224, "learning_rate": 0.00017225464270812074, "loss": 0.6358953475952148, "step": 167140 }, { "epoch": 0.993574311512147, "grad_norm": 1.9221253395080566, "learning_rate": 0.00017225014723330054, "loss": 0.7312829494476318, "step": 167150 }, { "epoch": 0.9936337535888153, "grad_norm": 1.7240455150604248, "learning_rate": 0.00017224565146069592, "loss": 0.5698911666870117, "step": 167160 }, { "epoch": 0.9936931956654838, "grad_norm": 1.9633655548095703, "learning_rate": 0.00017224115539032851, "loss": 0.7254467487335206, "step": 167170 }, { "epoch": 0.9937526377421522, "grad_norm": 1.629048466682434, "learning_rate": 0.00017223665902221973, "loss": 0.6258492946624756, "step": 167180 }, { "epoch": 0.9938120798188206, "grad_norm": 1.591646671295166, "learning_rate": 0.00017223216235639114, "loss": 0.62496919631958, "step": 167190 }, { "epoch": 0.993871521895489, "grad_norm": 1.329446792602539, "learning_rate": 0.00017222766539286416, "loss": 0.6390965461730957, "step": 167200 }, { "epoch": 0.9939309639721573, "grad_norm": 1.61447274684906, "learning_rate": 0.0001722231681316604, "loss": 0.6559267997741699, "step": 167210 }, { "epoch": 0.9939904060488257, "grad_norm": 1.4296013116836548, "learning_rate": 0.00017221867057280133, "loss": 0.6397970199584961, "step": 167220 }, { "epoch": 0.9940498481254941, "grad_norm": 1.5689631700515747, "learning_rate": 0.00017221417271630847, "loss": 0.6014056205749512, "step": 167230 }, { "epoch": 0.9941092902021625, "grad_norm": 1.512561321258545, "learning_rate": 0.0001722096745622034, "loss": 0.6999757766723633, "step": 167240 }, { "epoch": 0.9941687322788308, "grad_norm": 1.5651205778121948, "learning_rate": 0.00017220517611050745, "loss": 0.6747039318084717, "step": 167250 }, { "epoch": 0.9942281743554993, "grad_norm": 2.022318124771118, "learning_rate": 0.00017220067736124236, "loss": 0.676666259765625, "step": 167260 }, { "epoch": 0.9942876164321677, "grad_norm": 1.6166328191757202, "learning_rate": 0.00017219617831442955, "loss": 0.6368069648742676, "step": 167270 }, { "epoch": 0.9943470585088361, "grad_norm": 2.4463796615600586, "learning_rate": 0.00017219167897009055, "loss": 0.6777744293212891, "step": 167280 }, { "epoch": 0.9944065005855045, "grad_norm": 1.4985896348953247, "learning_rate": 0.00017218717932824686, "loss": 0.7398761749267578, "step": 167290 }, { "epoch": 0.9944659426621728, "grad_norm": 1.638371467590332, "learning_rate": 0.00017218267938892004, "loss": 0.6774991512298584, "step": 167300 }, { "epoch": 0.9945253847388412, "grad_norm": 2.195518732070923, "learning_rate": 0.00017217817915213162, "loss": 0.6680962085723877, "step": 167310 }, { "epoch": 0.9945848268155096, "grad_norm": 1.7417105436325073, "learning_rate": 0.00017217367861790308, "loss": 0.6124180316925049, "step": 167320 }, { "epoch": 0.994644268892178, "grad_norm": 1.3402749300003052, "learning_rate": 0.00017216917778625597, "loss": 0.6307859897613526, "step": 167330 }, { "epoch": 0.9947037109688464, "grad_norm": 1.533363938331604, "learning_rate": 0.00017216467665721186, "loss": 0.66873779296875, "step": 167340 }, { "epoch": 0.9947631530455148, "grad_norm": 1.1917190551757812, "learning_rate": 0.00017216017523079223, "loss": 0.6290618896484375, "step": 167350 }, { "epoch": 0.9948225951221832, "grad_norm": 1.5019474029541016, "learning_rate": 0.0001721556735070187, "loss": 0.6810550212860107, "step": 167360 }, { "epoch": 0.9948820371988516, "grad_norm": 1.9106303453445435, "learning_rate": 0.00017215117148591265, "loss": 0.5865530014038086, "step": 167370 }, { "epoch": 0.99494147927552, "grad_norm": 1.8041889667510986, "learning_rate": 0.00017214666916749575, "loss": 0.6586683750152588, "step": 167380 }, { "epoch": 0.9950009213521883, "grad_norm": 1.9104557037353516, "learning_rate": 0.0001721421665517895, "loss": 0.6556844711303711, "step": 167390 }, { "epoch": 0.9950603634288567, "grad_norm": 1.7624177932739258, "learning_rate": 0.00017213766363881542, "loss": 0.6345285415649414, "step": 167400 }, { "epoch": 0.9951198055055251, "grad_norm": 1.4297672510147095, "learning_rate": 0.00017213316042859506, "loss": 0.6745513916015625, "step": 167410 }, { "epoch": 0.9951792475821936, "grad_norm": 1.583046317100525, "learning_rate": 0.00017212865692114998, "loss": 0.6376747131347656, "step": 167420 }, { "epoch": 0.995238689658862, "grad_norm": 1.5130219459533691, "learning_rate": 0.00017212415311650172, "loss": 0.683714771270752, "step": 167430 }, { "epoch": 0.9952981317355303, "grad_norm": 1.7941644191741943, "learning_rate": 0.0001721196490146718, "loss": 0.7007750034332275, "step": 167440 }, { "epoch": 0.9953575738121987, "grad_norm": 1.6386555433273315, "learning_rate": 0.00017211514461568176, "loss": 0.6825653076171875, "step": 167450 }, { "epoch": 0.9954170158888671, "grad_norm": 1.2831954956054688, "learning_rate": 0.0001721106399195532, "loss": 0.6252822875976562, "step": 167460 }, { "epoch": 0.9954764579655355, "grad_norm": 1.5855116844177246, "learning_rate": 0.00017210613492630762, "loss": 0.6302883148193359, "step": 167470 }, { "epoch": 0.9955359000422038, "grad_norm": 1.5464352369308472, "learning_rate": 0.0001721016296359666, "loss": 0.6271829605102539, "step": 167480 }, { "epoch": 0.9955953421188722, "grad_norm": 1.7037032842636108, "learning_rate": 0.00017209712404855164, "loss": 0.6405844688415527, "step": 167490 }, { "epoch": 0.9956547841955407, "grad_norm": 1.9407919645309448, "learning_rate": 0.0001720926181640844, "loss": 0.6142053604125977, "step": 167500 }, { "epoch": 0.9957142262722091, "grad_norm": 1.4196549654006958, "learning_rate": 0.0001720881119825863, "loss": 0.6403719902038574, "step": 167510 }, { "epoch": 0.9957736683488775, "grad_norm": 1.338699221611023, "learning_rate": 0.000172083605504079, "loss": 0.6016392230987548, "step": 167520 }, { "epoch": 0.9958331104255458, "grad_norm": 1.6359933614730835, "learning_rate": 0.00017207909872858401, "loss": 0.6612949371337891, "step": 167530 }, { "epoch": 0.9958925525022142, "grad_norm": 1.2437858581542969, "learning_rate": 0.0001720745916561229, "loss": 0.6681251049041748, "step": 167540 }, { "epoch": 0.9959519945788826, "grad_norm": 1.3196381330490112, "learning_rate": 0.00017207008428671722, "loss": 0.6395345687866211, "step": 167550 }, { "epoch": 0.996011436655551, "grad_norm": 1.5648386478424072, "learning_rate": 0.0001720655766203886, "loss": 0.7171560764312744, "step": 167560 }, { "epoch": 0.9960708787322193, "grad_norm": 1.6459956169128418, "learning_rate": 0.00017206106865715848, "loss": 0.6415688514709472, "step": 167570 }, { "epoch": 0.9961303208088877, "grad_norm": 1.5629509687423706, "learning_rate": 0.00017205656039704848, "loss": 0.6682482242584229, "step": 167580 }, { "epoch": 0.9961897628855562, "grad_norm": 1.5238754749298096, "learning_rate": 0.0001720520518400802, "loss": 0.6141130447387695, "step": 167590 }, { "epoch": 0.9962492049622246, "grad_norm": 1.5585564374923706, "learning_rate": 0.00017204754298627518, "loss": 0.5961039543151856, "step": 167600 }, { "epoch": 0.996308647038893, "grad_norm": 1.4202823638916016, "learning_rate": 0.00017204303383565501, "loss": 0.6640767574310302, "step": 167610 }, { "epoch": 0.9963680891155613, "grad_norm": 2.0224878787994385, "learning_rate": 0.00017203852438824123, "loss": 0.6337617874145508, "step": 167620 }, { "epoch": 0.9964275311922297, "grad_norm": 1.3627995252609253, "learning_rate": 0.00017203401464405542, "loss": 0.6459556579589844, "step": 167630 }, { "epoch": 0.9964869732688981, "grad_norm": 1.7559410333633423, "learning_rate": 0.00017202950460311914, "loss": 0.6737667083740234, "step": 167640 }, { "epoch": 0.9965464153455665, "grad_norm": 1.7036957740783691, "learning_rate": 0.00017202499426545402, "loss": 0.6543142318725585, "step": 167650 }, { "epoch": 0.996605857422235, "grad_norm": 1.4131287336349487, "learning_rate": 0.00017202048363108158, "loss": 0.6559427738189697, "step": 167660 }, { "epoch": 0.9966652994989033, "grad_norm": 1.772139072418213, "learning_rate": 0.00017201597270002342, "loss": 0.6032548427581788, "step": 167670 }, { "epoch": 0.9967247415755717, "grad_norm": 1.3617016077041626, "learning_rate": 0.0001720114614723011, "loss": 0.5997145652770997, "step": 167680 }, { "epoch": 0.9967841836522401, "grad_norm": 1.906067132949829, "learning_rate": 0.0001720069499479362, "loss": 0.6467029571533203, "step": 167690 }, { "epoch": 0.9968436257289085, "grad_norm": 1.7193989753723145, "learning_rate": 0.00017200243812695034, "loss": 0.6531457901000977, "step": 167700 }, { "epoch": 0.9969030678055768, "grad_norm": 1.4664909839630127, "learning_rate": 0.0001719979260093651, "loss": 0.5954139709472657, "step": 167710 }, { "epoch": 0.9969625098822452, "grad_norm": 1.2752549648284912, "learning_rate": 0.00017199341359520198, "loss": 0.5604260921478271, "step": 167720 }, { "epoch": 0.9970219519589136, "grad_norm": 1.7894656658172607, "learning_rate": 0.00017198890088448266, "loss": 0.6107093811035156, "step": 167730 }, { "epoch": 0.997081394035582, "grad_norm": 1.3891994953155518, "learning_rate": 0.00017198438787722873, "loss": 0.6054532051086425, "step": 167740 }, { "epoch": 0.9971408361122505, "grad_norm": 1.8538938760757446, "learning_rate": 0.0001719798745734617, "loss": 0.7245020866394043, "step": 167750 }, { "epoch": 0.9972002781889188, "grad_norm": 2.0342118740081787, "learning_rate": 0.00017197536097320323, "loss": 0.6155354499816894, "step": 167760 }, { "epoch": 0.9972597202655872, "grad_norm": 1.6178768873214722, "learning_rate": 0.00017197084707647488, "loss": 0.6207070827484131, "step": 167770 }, { "epoch": 0.9973191623422556, "grad_norm": 1.4524775743484497, "learning_rate": 0.00017196633288329825, "loss": 0.6156919479370118, "step": 167780 }, { "epoch": 0.997378604418924, "grad_norm": 1.4897174835205078, "learning_rate": 0.00017196181839369495, "loss": 0.6267052173614502, "step": 167790 }, { "epoch": 0.9974380464955924, "grad_norm": 1.7343275547027588, "learning_rate": 0.00017195730360768652, "loss": 0.608027458190918, "step": 167800 }, { "epoch": 0.9974974885722607, "grad_norm": 1.3884873390197754, "learning_rate": 0.00017195278852529463, "loss": 0.6104964256286621, "step": 167810 }, { "epoch": 0.9975569306489291, "grad_norm": 1.4374333620071411, "learning_rate": 0.00017194827314654084, "loss": 0.6154026508331298, "step": 167820 }, { "epoch": 0.9976163727255976, "grad_norm": 1.662251353263855, "learning_rate": 0.00017194375747144674, "loss": 0.6016986846923829, "step": 167830 }, { "epoch": 0.997675814802266, "grad_norm": 1.5259308815002441, "learning_rate": 0.00017193924150003394, "loss": 0.6506607055664062, "step": 167840 }, { "epoch": 0.9977352568789343, "grad_norm": 1.5056086778640747, "learning_rate": 0.0001719347252323241, "loss": 0.6825471878051758, "step": 167850 }, { "epoch": 0.9977946989556027, "grad_norm": 1.6263210773468018, "learning_rate": 0.00017193020866833873, "loss": 0.6725423812866211, "step": 167860 }, { "epoch": 0.9978541410322711, "grad_norm": 1.5427879095077515, "learning_rate": 0.00017192569180809949, "loss": 0.6932642936706543, "step": 167870 }, { "epoch": 0.9979135831089395, "grad_norm": 1.4369794130325317, "learning_rate": 0.000171921174651628, "loss": 0.6056015014648437, "step": 167880 }, { "epoch": 0.9979730251856079, "grad_norm": 1.9450350999832153, "learning_rate": 0.00017191665719894583, "loss": 0.6018322467803955, "step": 167890 }, { "epoch": 0.9980324672622762, "grad_norm": 1.2613508701324463, "learning_rate": 0.00017191213945007462, "loss": 0.5855248451232911, "step": 167900 }, { "epoch": 0.9980919093389446, "grad_norm": 1.6181308031082153, "learning_rate": 0.00017190762140503597, "loss": 0.6584979057312011, "step": 167910 }, { "epoch": 0.9981513514156131, "grad_norm": 1.7597017288208008, "learning_rate": 0.00017190310306385148, "loss": 0.59803786277771, "step": 167920 }, { "epoch": 0.9982107934922815, "grad_norm": 1.725894570350647, "learning_rate": 0.00017189858442654275, "loss": 0.6120265007019043, "step": 167930 }, { "epoch": 0.9982702355689498, "grad_norm": 1.9308016300201416, "learning_rate": 0.00017189406549313144, "loss": 0.6448639869689942, "step": 167940 }, { "epoch": 0.9983296776456182, "grad_norm": 1.4005699157714844, "learning_rate": 0.00017188954626363916, "loss": 0.6701792716979981, "step": 167950 }, { "epoch": 0.9983891197222866, "grad_norm": 1.6599857807159424, "learning_rate": 0.0001718850267380875, "loss": 0.6691378593444824, "step": 167960 }, { "epoch": 0.998448561798955, "grad_norm": 1.5874594449996948, "learning_rate": 0.0001718805069164981, "loss": 0.6768131732940674, "step": 167970 }, { "epoch": 0.9985080038756234, "grad_norm": 1.66463303565979, "learning_rate": 0.0001718759867988926, "loss": 0.6474769592285157, "step": 167980 }, { "epoch": 0.9985674459522917, "grad_norm": 1.2952710390090942, "learning_rate": 0.00017187146638529256, "loss": 0.6725424289703369, "step": 167990 }, { "epoch": 0.9986268880289602, "grad_norm": 1.3648146390914917, "learning_rate": 0.00017186694567571968, "loss": 0.6891338348388671, "step": 168000 }, { "epoch": 0.9986863301056286, "grad_norm": 1.7252386808395386, "learning_rate": 0.00017186242467019555, "loss": 0.7258615970611573, "step": 168010 }, { "epoch": 0.998745772182297, "grad_norm": 1.5679317712783813, "learning_rate": 0.0001718579033687418, "loss": 0.6398512840270996, "step": 168020 }, { "epoch": 0.9988052142589654, "grad_norm": 0.9316823482513428, "learning_rate": 0.00017185338177138002, "loss": 0.5826421737670898, "step": 168030 }, { "epoch": 0.9988646563356337, "grad_norm": 1.6892168521881104, "learning_rate": 0.00017184885987813189, "loss": 0.6383526802062989, "step": 168040 }, { "epoch": 0.9989240984123021, "grad_norm": 1.635770559310913, "learning_rate": 0.00017184433768901904, "loss": 0.6412968635559082, "step": 168050 }, { "epoch": 0.9989835404889705, "grad_norm": 1.746219515800476, "learning_rate": 0.00017183981520406307, "loss": 0.6656251907348633, "step": 168060 }, { "epoch": 0.999042982565639, "grad_norm": 1.6449048519134521, "learning_rate": 0.00017183529242328566, "loss": 0.65497727394104, "step": 168070 }, { "epoch": 0.9991024246423073, "grad_norm": 1.4682788848876953, "learning_rate": 0.0001718307693467084, "loss": 0.6128349304199219, "step": 168080 }, { "epoch": 0.9991618667189757, "grad_norm": 1.44957435131073, "learning_rate": 0.00017182624597435292, "loss": 0.6172636032104493, "step": 168090 }, { "epoch": 0.9992213087956441, "grad_norm": 1.449653148651123, "learning_rate": 0.00017182172230624095, "loss": 0.6558595657348633, "step": 168100 }, { "epoch": 0.9992807508723125, "grad_norm": 2.0037193298339844, "learning_rate": 0.00017181719834239402, "loss": 0.5854051589965821, "step": 168110 }, { "epoch": 0.9993401929489809, "grad_norm": 1.6446654796600342, "learning_rate": 0.00017181267408283382, "loss": 0.6387171268463134, "step": 168120 }, { "epoch": 0.9993996350256492, "grad_norm": 1.7225720882415771, "learning_rate": 0.00017180814952758199, "loss": 0.6312575340270996, "step": 168130 }, { "epoch": 0.9994590771023176, "grad_norm": 1.9091267585754395, "learning_rate": 0.0001718036246766602, "loss": 0.6653746604919434, "step": 168140 }, { "epoch": 0.999518519178986, "grad_norm": 1.7932264804840088, "learning_rate": 0.00017179909953009, "loss": 0.622321367263794, "step": 168150 }, { "epoch": 0.9995779612556545, "grad_norm": 1.5554600954055786, "learning_rate": 0.00017179457408789315, "loss": 0.6053462028503418, "step": 168160 }, { "epoch": 0.9996374033323229, "grad_norm": 1.74146568775177, "learning_rate": 0.00017179004835009127, "loss": 0.6711771011352539, "step": 168170 }, { "epoch": 0.9996968454089912, "grad_norm": 1.5318230390548706, "learning_rate": 0.00017178552231670596, "loss": 0.5850697040557862, "step": 168180 }, { "epoch": 0.9997562874856596, "grad_norm": 1.5986862182617188, "learning_rate": 0.00017178099598775889, "loss": 0.638623046875, "step": 168190 }, { "epoch": 0.999815729562328, "grad_norm": 1.4915122985839844, "learning_rate": 0.00017177646936327178, "loss": 0.6067381381988526, "step": 168200 }, { "epoch": 0.9998751716389964, "grad_norm": 1.5926443338394165, "learning_rate": 0.00017177194244326617, "loss": 0.647951602935791, "step": 168210 }, { "epoch": 0.9999346137156647, "grad_norm": 1.2756187915802002, "learning_rate": 0.00017176741522776382, "loss": 0.7245916843414306, "step": 168220 }, { "epoch": 0.9999940557923331, "grad_norm": 1.598058819770813, "learning_rate": 0.0001717628877167863, "loss": 0.6615960121154785, "step": 168230 }, { "epoch": 1.0000534978690017, "grad_norm": 1.647395133972168, "learning_rate": 0.00017175835991035533, "loss": 0.6115042209625244, "step": 168240 }, { "epoch": 1.0001129399456699, "grad_norm": 1.315451741218567, "learning_rate": 0.00017175383180849258, "loss": 0.585538673400879, "step": 168250 }, { "epoch": 1.0001723820223383, "grad_norm": 1.743236780166626, "learning_rate": 0.0001717493034112196, "loss": 0.5916519641876221, "step": 168260 }, { "epoch": 1.0002318240990067, "grad_norm": 1.6456091403961182, "learning_rate": 0.0001717447747185582, "loss": 0.6049816131591796, "step": 168270 }, { "epoch": 1.000291266175675, "grad_norm": 1.6096704006195068, "learning_rate": 0.00017174024573052995, "loss": 0.6398134231567383, "step": 168280 }, { "epoch": 1.0003507082523435, "grad_norm": 2.051578998565674, "learning_rate": 0.00017173571644715657, "loss": 0.588234806060791, "step": 168290 }, { "epoch": 1.000410150329012, "grad_norm": 1.351927638053894, "learning_rate": 0.00017173118686845967, "loss": 0.5813261508941651, "step": 168300 }, { "epoch": 1.0004695924056803, "grad_norm": 1.555224895477295, "learning_rate": 0.00017172665699446095, "loss": 0.6175083160400391, "step": 168310 }, { "epoch": 1.0005290344823488, "grad_norm": 1.3666054010391235, "learning_rate": 0.0001717221268251821, "loss": 0.6118086814880371, "step": 168320 }, { "epoch": 1.0005884765590172, "grad_norm": 1.407271146774292, "learning_rate": 0.00017171759636064475, "loss": 0.6396962165832519, "step": 168330 }, { "epoch": 1.0006479186356854, "grad_norm": 1.9272314310073853, "learning_rate": 0.00017171306560087056, "loss": 0.6237705707550049, "step": 168340 }, { "epoch": 1.0007073607123538, "grad_norm": 1.3452768325805664, "learning_rate": 0.00017170853454588126, "loss": 0.6445136070251465, "step": 168350 }, { "epoch": 1.0007668027890222, "grad_norm": 1.5187960863113403, "learning_rate": 0.00017170400319569852, "loss": 0.5804748058319091, "step": 168360 }, { "epoch": 1.0008262448656906, "grad_norm": 1.4527409076690674, "learning_rate": 0.00017169947155034395, "loss": 0.6340756416320801, "step": 168370 }, { "epoch": 1.000885686942359, "grad_norm": 1.2065099477767944, "learning_rate": 0.0001716949396098393, "loss": 0.569519329071045, "step": 168380 }, { "epoch": 1.0009451290190274, "grad_norm": 1.7540223598480225, "learning_rate": 0.0001716904073742062, "loss": 0.7059202194213867, "step": 168390 }, { "epoch": 1.0010045710956958, "grad_norm": 1.161838412284851, "learning_rate": 0.0001716858748434664, "loss": 0.662239933013916, "step": 168400 }, { "epoch": 1.0010640131723643, "grad_norm": 1.750354290008545, "learning_rate": 0.00017168134201764145, "loss": 0.6412726879119873, "step": 168410 }, { "epoch": 1.0011234552490327, "grad_norm": 1.5371190309524536, "learning_rate": 0.00017167680889675318, "loss": 0.6386383533477783, "step": 168420 }, { "epoch": 1.0011828973257009, "grad_norm": 1.7483327388763428, "learning_rate": 0.00017167227548082318, "loss": 0.687446403503418, "step": 168430 }, { "epoch": 1.0012423394023693, "grad_norm": 1.652652621269226, "learning_rate": 0.00017166774176987322, "loss": 0.6182546138763427, "step": 168440 }, { "epoch": 1.0013017814790377, "grad_norm": 1.7194054126739502, "learning_rate": 0.0001716632077639249, "loss": 0.6622457504272461, "step": 168450 }, { "epoch": 1.0013612235557061, "grad_norm": 1.4003368616104126, "learning_rate": 0.00017165867346299996, "loss": 0.6107136726379394, "step": 168460 }, { "epoch": 1.0014206656323745, "grad_norm": 2.043048143386841, "learning_rate": 0.00017165413886712004, "loss": 0.6324874877929687, "step": 168470 }, { "epoch": 1.001480107709043, "grad_norm": 1.971325159072876, "learning_rate": 0.00017164960397630688, "loss": 0.6661089897155762, "step": 168480 }, { "epoch": 1.0015395497857114, "grad_norm": 2.0352954864501953, "learning_rate": 0.0001716450687905822, "loss": 0.5854358673095703, "step": 168490 }, { "epoch": 1.0015989918623798, "grad_norm": 1.2606244087219238, "learning_rate": 0.00017164053330996764, "loss": 0.6200309276580811, "step": 168500 }, { "epoch": 1.0016584339390482, "grad_norm": 1.816280722618103, "learning_rate": 0.0001716359975344849, "loss": 0.6513670921325684, "step": 168510 }, { "epoch": 1.0017178760157164, "grad_norm": 1.82088041305542, "learning_rate": 0.00017163146146415568, "loss": 0.6487034797668457, "step": 168520 }, { "epoch": 1.0017773180923848, "grad_norm": 1.325270652770996, "learning_rate": 0.0001716269250990017, "loss": 0.6001554012298584, "step": 168530 }, { "epoch": 1.0018367601690532, "grad_norm": 1.4824546575546265, "learning_rate": 0.00017162238843904465, "loss": 0.5951628684997559, "step": 168540 }, { "epoch": 1.0018962022457216, "grad_norm": 1.4928396940231323, "learning_rate": 0.00017161785148430626, "loss": 0.6090734958648681, "step": 168550 }, { "epoch": 1.00195564432239, "grad_norm": 1.4211511611938477, "learning_rate": 0.0001716133142348082, "loss": 0.6370753288269043, "step": 168560 }, { "epoch": 1.0020150863990585, "grad_norm": 1.411682367324829, "learning_rate": 0.00017160877669057211, "loss": 0.6039731979370118, "step": 168570 }, { "epoch": 1.0020745284757269, "grad_norm": 1.7031476497650146, "learning_rate": 0.00017160423885161986, "loss": 0.6329997062683106, "step": 168580 }, { "epoch": 1.0021339705523953, "grad_norm": 2.2941997051239014, "learning_rate": 0.000171599700717973, "loss": 0.6847107887268067, "step": 168590 }, { "epoch": 1.0021934126290637, "grad_norm": 1.463059902191162, "learning_rate": 0.00017159516228965334, "loss": 0.6294291496276856, "step": 168600 }, { "epoch": 1.002252854705732, "grad_norm": 1.9009778499603271, "learning_rate": 0.00017159062356668253, "loss": 0.6640740871429444, "step": 168610 }, { "epoch": 1.0023122967824003, "grad_norm": 1.6770235300064087, "learning_rate": 0.00017158608454908233, "loss": 0.6092628479003906, "step": 168620 }, { "epoch": 1.0023717388590687, "grad_norm": 1.587947964668274, "learning_rate": 0.00017158154523687442, "loss": 0.6069043636322021, "step": 168630 }, { "epoch": 1.0024311809357371, "grad_norm": 1.7193628549575806, "learning_rate": 0.0001715770056300805, "loss": 0.6387270927429199, "step": 168640 }, { "epoch": 1.0024906230124055, "grad_norm": 1.6253560781478882, "learning_rate": 0.0001715724657287223, "loss": 0.6194968223571777, "step": 168650 }, { "epoch": 1.002550065089074, "grad_norm": 1.642107605934143, "learning_rate": 0.00017156792553282157, "loss": 0.6271445274353027, "step": 168660 }, { "epoch": 1.0026095071657424, "grad_norm": 1.823395013809204, "learning_rate": 0.00017156338504240002, "loss": 0.6198197841644287, "step": 168670 }, { "epoch": 1.0026689492424108, "grad_norm": 1.6262390613555908, "learning_rate": 0.00017155884425747934, "loss": 0.6302407264709473, "step": 168680 }, { "epoch": 1.0027283913190792, "grad_norm": 1.5828323364257812, "learning_rate": 0.00017155430317808125, "loss": 0.5822766780853271, "step": 168690 }, { "epoch": 1.0027878333957476, "grad_norm": 1.2641029357910156, "learning_rate": 0.0001715497618042275, "loss": 0.6502638816833496, "step": 168700 }, { "epoch": 1.0028472754724158, "grad_norm": 1.5170462131500244, "learning_rate": 0.00017154522013593983, "loss": 0.6600467681884765, "step": 168710 }, { "epoch": 1.0029067175490842, "grad_norm": 2.106783628463745, "learning_rate": 0.00017154067817323992, "loss": 0.6676137924194336, "step": 168720 }, { "epoch": 1.0029661596257526, "grad_norm": 1.5506463050842285, "learning_rate": 0.00017153613591614953, "loss": 0.6627059936523437, "step": 168730 }, { "epoch": 1.003025601702421, "grad_norm": 1.7616791725158691, "learning_rate": 0.00017153159336469033, "loss": 0.6385228633880615, "step": 168740 }, { "epoch": 1.0030850437790895, "grad_norm": 1.613478183746338, "learning_rate": 0.00017152705051888415, "loss": 0.6809205055236817, "step": 168750 }, { "epoch": 1.0031444858557579, "grad_norm": 1.303822636604309, "learning_rate": 0.00017152250737875266, "loss": 0.5700125217437744, "step": 168760 }, { "epoch": 1.0032039279324263, "grad_norm": 1.4597957134246826, "learning_rate": 0.00017151796394431756, "loss": 0.5744020938873291, "step": 168770 }, { "epoch": 1.0032633700090947, "grad_norm": 1.6940034627914429, "learning_rate": 0.00017151342021560066, "loss": 0.5891425132751464, "step": 168780 }, { "epoch": 1.0033228120857631, "grad_norm": 1.4102894067764282, "learning_rate": 0.00017150887619262365, "loss": 0.6541460037231446, "step": 168790 }, { "epoch": 1.0033822541624313, "grad_norm": 1.476440191268921, "learning_rate": 0.0001715043318754083, "loss": 0.6532905578613282, "step": 168800 }, { "epoch": 1.0034416962390997, "grad_norm": 1.9330987930297852, "learning_rate": 0.00017149978726397632, "loss": 0.6356735229492188, "step": 168810 }, { "epoch": 1.0035011383157681, "grad_norm": 1.6759735345840454, "learning_rate": 0.00017149524235834942, "loss": 0.6059694290161133, "step": 168820 }, { "epoch": 1.0035605803924366, "grad_norm": 1.5725501775741577, "learning_rate": 0.00017149069715854937, "loss": 0.6409260272979737, "step": 168830 }, { "epoch": 1.003620022469105, "grad_norm": 1.6611545085906982, "learning_rate": 0.00017148615166459797, "loss": 0.63214111328125, "step": 168840 }, { "epoch": 1.0036794645457734, "grad_norm": 1.603859305381775, "learning_rate": 0.0001714816058765169, "loss": 0.5915414810180664, "step": 168850 }, { "epoch": 1.0037389066224418, "grad_norm": 1.7301161289215088, "learning_rate": 0.00017147705979432792, "loss": 0.6234374523162842, "step": 168860 }, { "epoch": 1.0037983486991102, "grad_norm": 1.4261376857757568, "learning_rate": 0.00017147251341805274, "loss": 0.5973476886749267, "step": 168870 }, { "epoch": 1.0038577907757786, "grad_norm": 1.4204837083816528, "learning_rate": 0.0001714679667477132, "loss": 0.6664708137512207, "step": 168880 }, { "epoch": 1.0039172328524468, "grad_norm": 1.7149409055709839, "learning_rate": 0.00017146341978333096, "loss": 0.6866006851196289, "step": 168890 }, { "epoch": 1.0039766749291152, "grad_norm": 1.784168004989624, "learning_rate": 0.00017145887252492783, "loss": 0.6319882869720459, "step": 168900 }, { "epoch": 1.0040361170057837, "grad_norm": 1.6362181901931763, "learning_rate": 0.00017145432497252554, "loss": 0.6069455146789551, "step": 168910 }, { "epoch": 1.004095559082452, "grad_norm": 1.7561382055282593, "learning_rate": 0.0001714497771261458, "loss": 0.5859476089477539, "step": 168920 }, { "epoch": 1.0041550011591205, "grad_norm": 1.888478398323059, "learning_rate": 0.00017144522898581045, "loss": 0.6604412078857422, "step": 168930 }, { "epoch": 1.004214443235789, "grad_norm": 1.7734947204589844, "learning_rate": 0.0001714406805515412, "loss": 0.6333996295928955, "step": 168940 }, { "epoch": 1.0042738853124573, "grad_norm": 1.6773370504379272, "learning_rate": 0.0001714361318233598, "loss": 0.6336345672607422, "step": 168950 }, { "epoch": 1.0043333273891257, "grad_norm": 1.4126805067062378, "learning_rate": 0.00017143158280128802, "loss": 0.659709358215332, "step": 168960 }, { "epoch": 1.0043927694657941, "grad_norm": 1.5570838451385498, "learning_rate": 0.00017142703348534764, "loss": 0.5781235694885254, "step": 168970 }, { "epoch": 1.0044522115424623, "grad_norm": 1.6146351099014282, "learning_rate": 0.0001714224838755604, "loss": 0.6713921546936035, "step": 168980 }, { "epoch": 1.0045116536191308, "grad_norm": 1.5767090320587158, "learning_rate": 0.00017141793397194808, "loss": 0.6684862613677979, "step": 168990 }, { "epoch": 1.0045710956957992, "grad_norm": 1.5886883735656738, "learning_rate": 0.00017141338377453242, "loss": 0.6060671806335449, "step": 169000 }, { "epoch": 1.0046305377724676, "grad_norm": 1.3863948583602905, "learning_rate": 0.0001714088332833352, "loss": 0.6884068489074707, "step": 169010 }, { "epoch": 1.004689979849136, "grad_norm": 1.6015053987503052, "learning_rate": 0.0001714042824983782, "loss": 0.6849806785583497, "step": 169020 }, { "epoch": 1.0047494219258044, "grad_norm": 1.6963536739349365, "learning_rate": 0.0001713997314196832, "loss": 0.6397369384765625, "step": 169030 }, { "epoch": 1.0048088640024728, "grad_norm": 1.466471552848816, "learning_rate": 0.0001713951800472719, "loss": 0.5839919567108154, "step": 169040 }, { "epoch": 1.0048683060791412, "grad_norm": 1.8693568706512451, "learning_rate": 0.00017139062838116616, "loss": 0.6396050930023194, "step": 169050 }, { "epoch": 1.0049277481558097, "grad_norm": 1.594741940498352, "learning_rate": 0.0001713860764213877, "loss": 0.640782356262207, "step": 169060 }, { "epoch": 1.004987190232478, "grad_norm": 1.9589980840682983, "learning_rate": 0.00017138152416795832, "loss": 0.5838381767272949, "step": 169070 }, { "epoch": 1.0050466323091463, "grad_norm": 1.8491778373718262, "learning_rate": 0.00017137697162089978, "loss": 0.5940601348876953, "step": 169080 }, { "epoch": 1.0051060743858147, "grad_norm": 1.658036470413208, "learning_rate": 0.0001713724187802339, "loss": 0.5826434135437012, "step": 169090 }, { "epoch": 1.005165516462483, "grad_norm": 1.6800484657287598, "learning_rate": 0.00017136786564598237, "loss": 0.6732857704162598, "step": 169100 }, { "epoch": 1.0052249585391515, "grad_norm": 1.40916109085083, "learning_rate": 0.00017136331221816707, "loss": 0.5925228595733643, "step": 169110 }, { "epoch": 1.00528440061582, "grad_norm": 1.6967251300811768, "learning_rate": 0.00017135875849680972, "loss": 0.6586469650268555, "step": 169120 }, { "epoch": 1.0053438426924883, "grad_norm": 2.0278213024139404, "learning_rate": 0.00017135420448193212, "loss": 0.5803640365600586, "step": 169130 }, { "epoch": 1.0054032847691567, "grad_norm": 1.334180474281311, "learning_rate": 0.00017134965017355605, "loss": 0.5423746585845948, "step": 169140 }, { "epoch": 1.0054627268458252, "grad_norm": 2.206853151321411, "learning_rate": 0.00017134509557170332, "loss": 0.6319385528564453, "step": 169150 }, { "epoch": 1.0055221689224936, "grad_norm": 1.6195861101150513, "learning_rate": 0.0001713405406763957, "loss": 0.6234574317932129, "step": 169160 }, { "epoch": 1.0055816109991618, "grad_norm": 1.4166033267974854, "learning_rate": 0.00017133598548765497, "loss": 0.582386589050293, "step": 169170 }, { "epoch": 1.0056410530758302, "grad_norm": 1.9572868347167969, "learning_rate": 0.00017133143000550293, "loss": 0.5816861629486084, "step": 169180 }, { "epoch": 1.0057004951524986, "grad_norm": 1.5700809955596924, "learning_rate": 0.00017132687422996136, "loss": 0.589273738861084, "step": 169190 }, { "epoch": 1.005759937229167, "grad_norm": 1.3643299341201782, "learning_rate": 0.0001713223181610521, "loss": 0.6258156776428223, "step": 169200 }, { "epoch": 1.0058193793058354, "grad_norm": 1.4372830390930176, "learning_rate": 0.00017131776179879688, "loss": 0.5739762783050537, "step": 169210 }, { "epoch": 1.0058788213825038, "grad_norm": 1.612563133239746, "learning_rate": 0.00017131320514321755, "loss": 0.6509276390075683, "step": 169220 }, { "epoch": 1.0059382634591723, "grad_norm": 1.6406861543655396, "learning_rate": 0.00017130864819433586, "loss": 0.6496981620788574, "step": 169230 }, { "epoch": 1.0059977055358407, "grad_norm": 2.061113119125366, "learning_rate": 0.00017130409095217366, "loss": 0.6322559356689453, "step": 169240 }, { "epoch": 1.006057147612509, "grad_norm": 1.6989444494247437, "learning_rate": 0.0001712995334167527, "loss": 0.6615281105041504, "step": 169250 }, { "epoch": 1.0061165896891773, "grad_norm": 1.9214081764221191, "learning_rate": 0.0001712949755880948, "loss": 0.6427280902862549, "step": 169260 }, { "epoch": 1.0061760317658457, "grad_norm": 1.2676399946212769, "learning_rate": 0.0001712904174662218, "loss": 0.5935533046722412, "step": 169270 }, { "epoch": 1.006235473842514, "grad_norm": 1.4995105266571045, "learning_rate": 0.00017128585905115543, "loss": 0.616159725189209, "step": 169280 }, { "epoch": 1.0062949159191825, "grad_norm": 2.0477559566497803, "learning_rate": 0.00017128130034291757, "loss": 0.6311477661132813, "step": 169290 }, { "epoch": 1.006354357995851, "grad_norm": 1.4232078790664673, "learning_rate": 0.00017127674134153, "loss": 0.6819634914398194, "step": 169300 }, { "epoch": 1.0064138000725193, "grad_norm": 2.0252599716186523, "learning_rate": 0.00017127218204701452, "loss": 0.617410135269165, "step": 169310 }, { "epoch": 1.0064732421491878, "grad_norm": 1.8950302600860596, "learning_rate": 0.00017126762245939293, "loss": 0.5877602100372314, "step": 169320 }, { "epoch": 1.0065326842258562, "grad_norm": 1.6261991262435913, "learning_rate": 0.00017126306257868708, "loss": 0.6199360370635987, "step": 169330 }, { "epoch": 1.0065921263025246, "grad_norm": 1.8782482147216797, "learning_rate": 0.00017125850240491873, "loss": 0.6371667861938477, "step": 169340 }, { "epoch": 1.0066515683791928, "grad_norm": 1.1867001056671143, "learning_rate": 0.00017125394193810974, "loss": 0.6542109489440918, "step": 169350 }, { "epoch": 1.0067110104558612, "grad_norm": 2.165226697921753, "learning_rate": 0.00017124938117828192, "loss": 0.6621414184570312, "step": 169360 }, { "epoch": 1.0067704525325296, "grad_norm": 1.4796737432479858, "learning_rate": 0.00017124482012545705, "loss": 0.6683093070983886, "step": 169370 }, { "epoch": 1.006829894609198, "grad_norm": 1.7187659740447998, "learning_rate": 0.00017124025877965698, "loss": 0.587614917755127, "step": 169380 }, { "epoch": 1.0068893366858664, "grad_norm": 1.2764074802398682, "learning_rate": 0.00017123569714090354, "loss": 0.5712436199188232, "step": 169390 }, { "epoch": 1.0069487787625349, "grad_norm": 1.54790198802948, "learning_rate": 0.00017123113520921854, "loss": 0.5882537841796875, "step": 169400 }, { "epoch": 1.0070082208392033, "grad_norm": 1.3556592464447021, "learning_rate": 0.0001712265729846238, "loss": 0.6640059947967529, "step": 169410 }, { "epoch": 1.0070676629158717, "grad_norm": 1.5750528573989868, "learning_rate": 0.00017122201046714116, "loss": 0.6611714839935303, "step": 169420 }, { "epoch": 1.00712710499254, "grad_norm": 1.8004399538040161, "learning_rate": 0.0001712174476567924, "loss": 0.6249448776245117, "step": 169430 }, { "epoch": 1.0071865470692085, "grad_norm": 1.470906138420105, "learning_rate": 0.00017121288455359935, "loss": 0.5835593223571778, "step": 169440 }, { "epoch": 1.0072459891458767, "grad_norm": 1.760465145111084, "learning_rate": 0.00017120832115758393, "loss": 0.6169429779052734, "step": 169450 }, { "epoch": 1.0073054312225451, "grad_norm": 1.4604672193527222, "learning_rate": 0.00017120375746876787, "loss": 0.6576472282409668, "step": 169460 }, { "epoch": 1.0073648732992135, "grad_norm": 1.3873686790466309, "learning_rate": 0.000171199193487173, "loss": 0.6533695220947265, "step": 169470 }, { "epoch": 1.007424315375882, "grad_norm": 1.7042468786239624, "learning_rate": 0.00017119462921282128, "loss": 0.6277962684631347, "step": 169480 }, { "epoch": 1.0074837574525504, "grad_norm": 1.7128417491912842, "learning_rate": 0.00017119006464573437, "loss": 0.5926937103271485, "step": 169490 }, { "epoch": 1.0075431995292188, "grad_norm": 1.5731419324874878, "learning_rate": 0.0001711854997859342, "loss": 0.6870878219604493, "step": 169500 }, { "epoch": 1.0076026416058872, "grad_norm": 1.6315014362335205, "learning_rate": 0.00017118093463344266, "loss": 0.610900592803955, "step": 169510 }, { "epoch": 1.0076620836825556, "grad_norm": 1.584444522857666, "learning_rate": 0.00017117636918828147, "loss": 0.6219027519226075, "step": 169520 }, { "epoch": 1.007721525759224, "grad_norm": 1.6829971075057983, "learning_rate": 0.0001711718034504725, "loss": 0.6908225536346435, "step": 169530 }, { "epoch": 1.0077809678358922, "grad_norm": 1.47838294506073, "learning_rate": 0.00017116723742003763, "loss": 0.653343391418457, "step": 169540 }, { "epoch": 1.0078404099125606, "grad_norm": 1.5960613489151, "learning_rate": 0.0001711626710969987, "loss": 0.6882284164428711, "step": 169550 }, { "epoch": 1.007899851989229, "grad_norm": 1.782787561416626, "learning_rate": 0.00017115810448137755, "loss": 0.5803497314453125, "step": 169560 }, { "epoch": 1.0079592940658975, "grad_norm": 1.3641895055770874, "learning_rate": 0.00017115353757319598, "loss": 0.6114755630493164, "step": 169570 }, { "epoch": 1.0080187361425659, "grad_norm": 1.3261585235595703, "learning_rate": 0.0001711489703724759, "loss": 0.6556019306182861, "step": 169580 }, { "epoch": 1.0080781782192343, "grad_norm": 1.8084160089492798, "learning_rate": 0.00017114440287923914, "loss": 0.6213107109069824, "step": 169590 }, { "epoch": 1.0081376202959027, "grad_norm": 1.9594571590423584, "learning_rate": 0.00017113983509350753, "loss": 0.665614652633667, "step": 169600 }, { "epoch": 1.0081970623725711, "grad_norm": 1.2932473421096802, "learning_rate": 0.0001711352670153029, "loss": 0.6096856594085693, "step": 169610 }, { "epoch": 1.0082565044492395, "grad_norm": 1.891908049583435, "learning_rate": 0.00017113069864464718, "loss": 0.6045036315917969, "step": 169620 }, { "epoch": 1.0083159465259077, "grad_norm": 1.825698971748352, "learning_rate": 0.00017112612998156212, "loss": 0.6697833061218261, "step": 169630 }, { "epoch": 1.0083753886025761, "grad_norm": 1.549560308456421, "learning_rate": 0.00017112156102606967, "loss": 0.6590081214904785, "step": 169640 }, { "epoch": 1.0084348306792446, "grad_norm": 1.4088046550750732, "learning_rate": 0.00017111699177819166, "loss": 0.7067924022674561, "step": 169650 }, { "epoch": 1.008494272755913, "grad_norm": 1.9171746969223022, "learning_rate": 0.0001711124222379499, "loss": 0.6455684185028077, "step": 169660 }, { "epoch": 1.0085537148325814, "grad_norm": 2.337341785430908, "learning_rate": 0.00017110785240536628, "loss": 0.6348804473876953, "step": 169670 }, { "epoch": 1.0086131569092498, "grad_norm": 1.4712145328521729, "learning_rate": 0.00017110328228046265, "loss": 0.5945676803588867, "step": 169680 }, { "epoch": 1.0086725989859182, "grad_norm": 1.6672755479812622, "learning_rate": 0.00017109871186326095, "loss": 0.6282893180847168, "step": 169690 }, { "epoch": 1.0087320410625866, "grad_norm": 1.3656885623931885, "learning_rate": 0.00017109414115378294, "loss": 0.6045660018920899, "step": 169700 }, { "epoch": 1.008791483139255, "grad_norm": 1.3472892045974731, "learning_rate": 0.00017108957015205052, "loss": 0.6180854320526123, "step": 169710 }, { "epoch": 1.0088509252159232, "grad_norm": 1.5047551393508911, "learning_rate": 0.00017108499885808558, "loss": 0.6172295570373535, "step": 169720 }, { "epoch": 1.0089103672925916, "grad_norm": 1.7489904165267944, "learning_rate": 0.00017108042727190993, "loss": 0.6190690994262695, "step": 169730 }, { "epoch": 1.00896980936926, "grad_norm": 1.4111443758010864, "learning_rate": 0.00017107585539354552, "loss": 0.6258628368377686, "step": 169740 }, { "epoch": 1.0090292514459285, "grad_norm": 1.8389207124710083, "learning_rate": 0.00017107128322301418, "loss": 0.7076951026916504, "step": 169750 }, { "epoch": 1.009088693522597, "grad_norm": 1.6710014343261719, "learning_rate": 0.00017106671076033776, "loss": 0.5988335132598877, "step": 169760 }, { "epoch": 1.0091481355992653, "grad_norm": 1.680105447769165, "learning_rate": 0.00017106213800553816, "loss": 0.6190601825714112, "step": 169770 }, { "epoch": 1.0092075776759337, "grad_norm": 1.746999979019165, "learning_rate": 0.0001710575649586372, "loss": 0.5978538990020752, "step": 169780 }, { "epoch": 1.0092670197526021, "grad_norm": 1.6041938066482544, "learning_rate": 0.0001710529916196569, "loss": 0.6467813491821289, "step": 169790 }, { "epoch": 1.0093264618292705, "grad_norm": 1.6213523149490356, "learning_rate": 0.00017104841798861896, "loss": 0.6054304122924805, "step": 169800 }, { "epoch": 1.009385903905939, "grad_norm": 1.8456854820251465, "learning_rate": 0.00017104384406554533, "loss": 0.6039684295654297, "step": 169810 }, { "epoch": 1.0094453459826072, "grad_norm": 1.7658441066741943, "learning_rate": 0.00017103926985045798, "loss": 0.5717266082763672, "step": 169820 }, { "epoch": 1.0095047880592756, "grad_norm": 1.5399425029754639, "learning_rate": 0.00017103469534337866, "loss": 0.6771350383758545, "step": 169830 }, { "epoch": 1.009564230135944, "grad_norm": 1.7143124341964722, "learning_rate": 0.0001710301205443293, "loss": 0.5904118537902832, "step": 169840 }, { "epoch": 1.0096236722126124, "grad_norm": 1.3127068281173706, "learning_rate": 0.0001710255454533318, "loss": 0.5932490348815918, "step": 169850 }, { "epoch": 1.0096831142892808, "grad_norm": 1.917409062385559, "learning_rate": 0.000171020970070408, "loss": 0.6319547176361084, "step": 169860 }, { "epoch": 1.0097425563659492, "grad_norm": 1.617838740348816, "learning_rate": 0.00017101639439557988, "loss": 0.6296828269958497, "step": 169870 }, { "epoch": 1.0098019984426176, "grad_norm": 1.6774359941482544, "learning_rate": 0.00017101181842886924, "loss": 0.5830425262451172, "step": 169880 }, { "epoch": 1.009861440519286, "grad_norm": 1.4119778871536255, "learning_rate": 0.000171007242170298, "loss": 0.5677626132965088, "step": 169890 }, { "epoch": 1.0099208825959545, "grad_norm": 1.6199802160263062, "learning_rate": 0.00017100266561988805, "loss": 0.6348386764526367, "step": 169900 }, { "epoch": 1.0099803246726227, "grad_norm": 1.680018663406372, "learning_rate": 0.00017099808877766128, "loss": 0.6423029899597168, "step": 169910 }, { "epoch": 1.010039766749291, "grad_norm": 1.669430136680603, "learning_rate": 0.0001709935116436396, "loss": 0.6323568820953369, "step": 169920 }, { "epoch": 1.0100992088259595, "grad_norm": 1.9171509742736816, "learning_rate": 0.00017098893421784489, "loss": 0.5877998352050782, "step": 169930 }, { "epoch": 1.010158650902628, "grad_norm": 1.6590211391448975, "learning_rate": 0.00017098435650029904, "loss": 0.6415677547454834, "step": 169940 }, { "epoch": 1.0102180929792963, "grad_norm": 1.3287779092788696, "learning_rate": 0.00017097977849102395, "loss": 0.5763415336608887, "step": 169950 }, { "epoch": 1.0102775350559647, "grad_norm": 2.0332939624786377, "learning_rate": 0.00017097520019004154, "loss": 0.6518287181854248, "step": 169960 }, { "epoch": 1.0103369771326332, "grad_norm": 1.2351150512695312, "learning_rate": 0.00017097062159737375, "loss": 0.6674893379211426, "step": 169970 }, { "epoch": 1.0103964192093016, "grad_norm": 1.82586669921875, "learning_rate": 0.00017096604271304235, "loss": 0.6724417686462403, "step": 169980 }, { "epoch": 1.01045586128597, "grad_norm": 1.2637051343917847, "learning_rate": 0.00017096146353706934, "loss": 0.6332379341125488, "step": 169990 }, { "epoch": 1.0105153033626382, "grad_norm": 2.301422119140625, "learning_rate": 0.00017095688406947666, "loss": 0.5678187370300293, "step": 170000 }, { "epoch": 1.0105747454393066, "grad_norm": 1.5364576578140259, "learning_rate": 0.00017095230431028613, "loss": 0.6259757041931152, "step": 170010 }, { "epoch": 1.010634187515975, "grad_norm": 1.5806996822357178, "learning_rate": 0.00017094772425951967, "loss": 0.6495851039886474, "step": 170020 }, { "epoch": 1.0106936295926434, "grad_norm": 1.6426292657852173, "learning_rate": 0.0001709431439171993, "loss": 0.5631987571716308, "step": 170030 }, { "epoch": 1.0107530716693118, "grad_norm": 1.5758435726165771, "learning_rate": 0.00017093856328334673, "loss": 0.618828010559082, "step": 170040 }, { "epoch": 1.0108125137459802, "grad_norm": 1.8854153156280518, "learning_rate": 0.0001709339823579841, "loss": 0.6754279613494873, "step": 170050 }, { "epoch": 1.0108719558226487, "grad_norm": 1.57969331741333, "learning_rate": 0.00017092940114113317, "loss": 0.6349583625793457, "step": 170060 }, { "epoch": 1.010931397899317, "grad_norm": 1.771524429321289, "learning_rate": 0.0001709248196328159, "loss": 0.6475547790527344, "step": 170070 }, { "epoch": 1.0109908399759855, "grad_norm": 1.7372573614120483, "learning_rate": 0.00017092023783305416, "loss": 0.6724870681762696, "step": 170080 }, { "epoch": 1.0110502820526537, "grad_norm": 2.316502094268799, "learning_rate": 0.00017091565574186996, "loss": 0.6113430976867675, "step": 170090 }, { "epoch": 1.011109724129322, "grad_norm": 1.7821794748306274, "learning_rate": 0.00017091107335928516, "loss": 0.6441206932067871, "step": 170100 }, { "epoch": 1.0111691662059905, "grad_norm": 1.5388727188110352, "learning_rate": 0.00017090649068532169, "loss": 0.619286060333252, "step": 170110 }, { "epoch": 1.011228608282659, "grad_norm": 2.052266836166382, "learning_rate": 0.00017090190772000145, "loss": 0.6334083557128907, "step": 170120 }, { "epoch": 1.0112880503593273, "grad_norm": 1.2497847080230713, "learning_rate": 0.00017089732446334642, "loss": 0.6517075538635254, "step": 170130 }, { "epoch": 1.0113474924359958, "grad_norm": 1.4410456418991089, "learning_rate": 0.0001708927409153785, "loss": 0.6202696800231934, "step": 170140 }, { "epoch": 1.0114069345126642, "grad_norm": 1.6459689140319824, "learning_rate": 0.00017088815707611956, "loss": 0.6442758560180664, "step": 170150 }, { "epoch": 1.0114663765893326, "grad_norm": 1.868108868598938, "learning_rate": 0.0001708835729455916, "loss": 0.6421990394592285, "step": 170160 }, { "epoch": 1.011525818666001, "grad_norm": 1.861856460571289, "learning_rate": 0.00017087898852381653, "loss": 0.7012991428375244, "step": 170170 }, { "epoch": 1.0115852607426694, "grad_norm": 1.3420342206954956, "learning_rate": 0.00017087440381081628, "loss": 0.5948875904083252, "step": 170180 }, { "epoch": 1.0116447028193376, "grad_norm": 1.4354515075683594, "learning_rate": 0.00017086981880661272, "loss": 0.6204727172851563, "step": 170190 }, { "epoch": 1.011704144896006, "grad_norm": 1.433586597442627, "learning_rate": 0.0001708652335112279, "loss": 0.6659214496612549, "step": 170200 }, { "epoch": 1.0117635869726744, "grad_norm": 1.3798627853393555, "learning_rate": 0.0001708606479246837, "loss": 0.6388344764709473, "step": 170210 }, { "epoch": 1.0118230290493428, "grad_norm": 1.6570396423339844, "learning_rate": 0.000170856062047002, "loss": 0.611481761932373, "step": 170220 }, { "epoch": 1.0118824711260113, "grad_norm": 1.859134316444397, "learning_rate": 0.00017085147587820484, "loss": 0.661408519744873, "step": 170230 }, { "epoch": 1.0119419132026797, "grad_norm": 1.529773473739624, "learning_rate": 0.00017084688941831406, "loss": 0.6455982208251954, "step": 170240 }, { "epoch": 1.012001355279348, "grad_norm": 2.0807576179504395, "learning_rate": 0.00017084230266735167, "loss": 0.641912841796875, "step": 170250 }, { "epoch": 1.0120607973560165, "grad_norm": 1.9672274589538574, "learning_rate": 0.00017083771562533958, "loss": 0.6438180923461914, "step": 170260 }, { "epoch": 1.012120239432685, "grad_norm": 1.3318053483963013, "learning_rate": 0.00017083312829229973, "loss": 0.6419992446899414, "step": 170270 }, { "epoch": 1.0121796815093531, "grad_norm": 1.5310715436935425, "learning_rate": 0.0001708285406682541, "loss": 0.6840168476104737, "step": 170280 }, { "epoch": 1.0122391235860215, "grad_norm": 1.5533106327056885, "learning_rate": 0.0001708239527532246, "loss": 0.602785873413086, "step": 170290 }, { "epoch": 1.01229856566269, "grad_norm": 1.633174180984497, "learning_rate": 0.00017081936454723317, "loss": 0.6589468955993653, "step": 170300 }, { "epoch": 1.0123580077393584, "grad_norm": 1.5668941736221313, "learning_rate": 0.0001708147760503018, "loss": 0.5596595764160156, "step": 170310 }, { "epoch": 1.0124174498160268, "grad_norm": 1.7333400249481201, "learning_rate": 0.00017081018726245242, "loss": 0.578211498260498, "step": 170320 }, { "epoch": 1.0124768918926952, "grad_norm": 1.769930124282837, "learning_rate": 0.00017080559818370697, "loss": 0.605353593826294, "step": 170330 }, { "epoch": 1.0125363339693636, "grad_norm": 1.7212114334106445, "learning_rate": 0.0001708010088140874, "loss": 0.64295654296875, "step": 170340 }, { "epoch": 1.012595776046032, "grad_norm": 1.3663411140441895, "learning_rate": 0.00017079641915361565, "loss": 0.5832141876220703, "step": 170350 }, { "epoch": 1.0126552181227004, "grad_norm": 1.3574895858764648, "learning_rate": 0.00017079182920231377, "loss": 0.6154032230377198, "step": 170360 }, { "epoch": 1.0127146601993686, "grad_norm": 1.5032222270965576, "learning_rate": 0.00017078723896020358, "loss": 0.6088288307189942, "step": 170370 }, { "epoch": 1.012774102276037, "grad_norm": 1.338889479637146, "learning_rate": 0.00017078264842730715, "loss": 0.5557727813720703, "step": 170380 }, { "epoch": 1.0128335443527055, "grad_norm": 1.739648699760437, "learning_rate": 0.0001707780576036464, "loss": 0.6226596832275391, "step": 170390 }, { "epoch": 1.0128929864293739, "grad_norm": 1.7417304515838623, "learning_rate": 0.00017077346648924322, "loss": 0.6402103424072265, "step": 170400 }, { "epoch": 1.0129524285060423, "grad_norm": 1.7496929168701172, "learning_rate": 0.00017076887508411968, "loss": 0.5576525688171386, "step": 170410 }, { "epoch": 1.0130118705827107, "grad_norm": 1.3515949249267578, "learning_rate": 0.0001707642833882977, "loss": 0.7000107288360595, "step": 170420 }, { "epoch": 1.013071312659379, "grad_norm": 1.8810359239578247, "learning_rate": 0.00017075969140179924, "loss": 0.6539684295654297, "step": 170430 }, { "epoch": 1.0131307547360475, "grad_norm": 1.4946523904800415, "learning_rate": 0.00017075509912464626, "loss": 0.5974525451660156, "step": 170440 }, { "epoch": 1.013190196812716, "grad_norm": 1.7269906997680664, "learning_rate": 0.00017075050655686078, "loss": 0.627405309677124, "step": 170450 }, { "epoch": 1.0132496388893841, "grad_norm": 1.5012855529785156, "learning_rate": 0.0001707459136984647, "loss": 0.6536542892456054, "step": 170460 }, { "epoch": 1.0133090809660525, "grad_norm": 2.0581297874450684, "learning_rate": 0.00017074132054948002, "loss": 0.6127728939056396, "step": 170470 }, { "epoch": 1.013368523042721, "grad_norm": 1.5928874015808105, "learning_rate": 0.00017073672710992872, "loss": 0.5929089546203613, "step": 170480 }, { "epoch": 1.0134279651193894, "grad_norm": 1.6233654022216797, "learning_rate": 0.00017073213337983278, "loss": 0.6531025886535644, "step": 170490 }, { "epoch": 1.0134874071960578, "grad_norm": 1.5449179410934448, "learning_rate": 0.00017072753935921413, "loss": 0.6596017360687256, "step": 170500 }, { "epoch": 1.0135468492727262, "grad_norm": 1.8403526544570923, "learning_rate": 0.00017072294504809482, "loss": 0.6728047370910645, "step": 170510 }, { "epoch": 1.0136062913493946, "grad_norm": 2.4134044647216797, "learning_rate": 0.00017071835044649676, "loss": 0.6395195960998535, "step": 170520 }, { "epoch": 1.013665733426063, "grad_norm": 1.5119233131408691, "learning_rate": 0.00017071375555444195, "loss": 0.6063042163848877, "step": 170530 }, { "epoch": 1.0137251755027314, "grad_norm": 1.664230227470398, "learning_rate": 0.00017070916037195238, "loss": 0.6010244369506836, "step": 170540 }, { "epoch": 1.0137846175793999, "grad_norm": 1.4440546035766602, "learning_rate": 0.00017070456489905002, "loss": 0.6479193687438964, "step": 170550 }, { "epoch": 1.013844059656068, "grad_norm": 1.6919775009155273, "learning_rate": 0.00017069996913575687, "loss": 0.6705385208129883, "step": 170560 }, { "epoch": 1.0139035017327365, "grad_norm": 1.60552978515625, "learning_rate": 0.0001706953730820949, "loss": 0.591567850112915, "step": 170570 }, { "epoch": 1.0139629438094049, "grad_norm": 3.0920603275299072, "learning_rate": 0.0001706907767380861, "loss": 0.6787560462951661, "step": 170580 }, { "epoch": 1.0140223858860733, "grad_norm": 1.5435911417007446, "learning_rate": 0.00017068618010375247, "loss": 0.6262318611145019, "step": 170590 }, { "epoch": 1.0140818279627417, "grad_norm": 1.704270839691162, "learning_rate": 0.00017068158317911597, "loss": 0.6246310234069824, "step": 170600 }, { "epoch": 1.0141412700394101, "grad_norm": 1.6840969324111938, "learning_rate": 0.0001706769859641986, "loss": 0.6151645660400391, "step": 170610 }, { "epoch": 1.0142007121160785, "grad_norm": 1.6468017101287842, "learning_rate": 0.00017067238845902238, "loss": 0.5884355068206787, "step": 170620 }, { "epoch": 1.014260154192747, "grad_norm": 1.9357773065567017, "learning_rate": 0.00017066779066360926, "loss": 0.6132018089294433, "step": 170630 }, { "epoch": 1.0143195962694154, "grad_norm": 1.3105967044830322, "learning_rate": 0.0001706631925779813, "loss": 0.6428802967071533, "step": 170640 }, { "epoch": 1.0143790383460836, "grad_norm": 1.18799889087677, "learning_rate": 0.00017065859420216042, "loss": 0.6143942832946777, "step": 170650 }, { "epoch": 1.014438480422752, "grad_norm": 1.7735553979873657, "learning_rate": 0.00017065399553616863, "loss": 0.6174216270446777, "step": 170660 }, { "epoch": 1.0144979224994204, "grad_norm": 1.8851996660232544, "learning_rate": 0.000170649396580028, "loss": 0.5512868881225585, "step": 170670 }, { "epoch": 1.0145573645760888, "grad_norm": 1.866987705230713, "learning_rate": 0.00017064479733376045, "loss": 0.655922794342041, "step": 170680 }, { "epoch": 1.0146168066527572, "grad_norm": 1.5854768753051758, "learning_rate": 0.00017064019779738799, "loss": 0.6295230865478516, "step": 170690 }, { "epoch": 1.0146762487294256, "grad_norm": 1.5800057649612427, "learning_rate": 0.00017063559797093265, "loss": 0.6390872478485108, "step": 170700 }, { "epoch": 1.014735690806094, "grad_norm": 2.453298568725586, "learning_rate": 0.00017063099785441643, "loss": 0.6978967666625977, "step": 170710 }, { "epoch": 1.0147951328827625, "grad_norm": 1.223201036453247, "learning_rate": 0.00017062639744786133, "loss": 0.600151777267456, "step": 170720 }, { "epoch": 1.0148545749594309, "grad_norm": 2.1842427253723145, "learning_rate": 0.00017062179675128938, "loss": 0.6448620796203614, "step": 170730 }, { "epoch": 1.014914017036099, "grad_norm": 1.8468716144561768, "learning_rate": 0.00017061719576472252, "loss": 0.6246517658233642, "step": 170740 }, { "epoch": 1.0149734591127675, "grad_norm": 1.4405556917190552, "learning_rate": 0.00017061259448818286, "loss": 0.6234354496002197, "step": 170750 }, { "epoch": 1.015032901189436, "grad_norm": 1.7033771276474, "learning_rate": 0.0001706079929216923, "loss": 0.6103705406188965, "step": 170760 }, { "epoch": 1.0150923432661043, "grad_norm": 1.4952654838562012, "learning_rate": 0.00017060339106527293, "loss": 0.6186299324035645, "step": 170770 }, { "epoch": 1.0151517853427727, "grad_norm": 1.5955346822738647, "learning_rate": 0.00017059878891894677, "loss": 0.6092283248901367, "step": 170780 }, { "epoch": 1.0152112274194411, "grad_norm": 1.8713945150375366, "learning_rate": 0.00017059418648273576, "loss": 0.5828303337097168, "step": 170790 }, { "epoch": 1.0152706694961096, "grad_norm": 1.4640861749649048, "learning_rate": 0.00017058958375666198, "loss": 0.6690994262695312, "step": 170800 }, { "epoch": 1.015330111572778, "grad_norm": 1.4279563426971436, "learning_rate": 0.00017058498074074745, "loss": 0.6271250247955322, "step": 170810 }, { "epoch": 1.0153895536494464, "grad_norm": 1.7420543432235718, "learning_rate": 0.0001705803774350142, "loss": 0.6199455738067627, "step": 170820 }, { "epoch": 1.0154489957261146, "grad_norm": 1.306015968322754, "learning_rate": 0.00017057577383948415, "loss": 0.6208674430847168, "step": 170830 }, { "epoch": 1.015508437802783, "grad_norm": 1.7064639329910278, "learning_rate": 0.00017057116995417942, "loss": 0.6064848899841309, "step": 170840 }, { "epoch": 1.0155678798794514, "grad_norm": 1.9087294340133667, "learning_rate": 0.00017056656577912207, "loss": 0.6116910934448242, "step": 170850 }, { "epoch": 1.0156273219561198, "grad_norm": 1.475803256034851, "learning_rate": 0.00017056196131433397, "loss": 0.5944385528564453, "step": 170860 }, { "epoch": 1.0156867640327882, "grad_norm": 1.4722812175750732, "learning_rate": 0.00017055735655983732, "loss": 0.6139457702636719, "step": 170870 }, { "epoch": 1.0157462061094567, "grad_norm": 1.5270678997039795, "learning_rate": 0.000170552751515654, "loss": 0.6059118270874023, "step": 170880 }, { "epoch": 1.015805648186125, "grad_norm": 1.7700165510177612, "learning_rate": 0.00017054814618180613, "loss": 0.6510437965393067, "step": 170890 }, { "epoch": 1.0158650902627935, "grad_norm": 1.9191656112670898, "learning_rate": 0.0001705435405583157, "loss": 0.6086994171142578, "step": 170900 }, { "epoch": 1.015924532339462, "grad_norm": 1.7998288869857788, "learning_rate": 0.0001705389346452048, "loss": 0.6733807563781739, "step": 170910 }, { "epoch": 1.0159839744161303, "grad_norm": 1.4957334995269775, "learning_rate": 0.00017053432844249536, "loss": 0.6596587181091309, "step": 170920 }, { "epoch": 1.0160434164927985, "grad_norm": 1.8921246528625488, "learning_rate": 0.00017052972195020954, "loss": 0.6431791305541992, "step": 170930 }, { "epoch": 1.016102858569467, "grad_norm": 2.0364186763763428, "learning_rate": 0.0001705251151683693, "loss": 0.6144503593444824, "step": 170940 }, { "epoch": 1.0161623006461353, "grad_norm": 1.614853024482727, "learning_rate": 0.00017052050809699665, "loss": 0.5676825523376465, "step": 170950 }, { "epoch": 1.0162217427228037, "grad_norm": 1.4244765043258667, "learning_rate": 0.00017051590073611367, "loss": 0.6202080726623536, "step": 170960 }, { "epoch": 1.0162811847994722, "grad_norm": 1.5467491149902344, "learning_rate": 0.00017051129308574242, "loss": 0.6280923843383789, "step": 170970 }, { "epoch": 1.0163406268761406, "grad_norm": 1.5104258060455322, "learning_rate": 0.00017050668514590492, "loss": 0.6088577270507812, "step": 170980 }, { "epoch": 1.016400068952809, "grad_norm": 1.639517068862915, "learning_rate": 0.00017050207691662325, "loss": 0.6332414627075196, "step": 170990 }, { "epoch": 1.0164595110294774, "grad_norm": 1.6242660284042358, "learning_rate": 0.00017049746839791933, "loss": 0.6180748462677002, "step": 171000 }, { "epoch": 1.0165189531061458, "grad_norm": 1.652928113937378, "learning_rate": 0.00017049285958981535, "loss": 0.655021858215332, "step": 171010 }, { "epoch": 1.016578395182814, "grad_norm": 1.1988369226455688, "learning_rate": 0.00017048825049233328, "loss": 0.5652677059173584, "step": 171020 }, { "epoch": 1.0166378372594824, "grad_norm": 1.4513059854507446, "learning_rate": 0.00017048364110549522, "loss": 0.6300071716308594, "step": 171030 }, { "epoch": 1.0166972793361508, "grad_norm": 1.781333565711975, "learning_rate": 0.00017047903142932314, "loss": 0.6709009170532226, "step": 171040 }, { "epoch": 1.0167567214128193, "grad_norm": 1.7499282360076904, "learning_rate": 0.00017047442146383916, "loss": 0.611478328704834, "step": 171050 }, { "epoch": 1.0168161634894877, "grad_norm": 1.5768547058105469, "learning_rate": 0.0001704698112090653, "loss": 0.6006012439727784, "step": 171060 }, { "epoch": 1.016875605566156, "grad_norm": 2.1714227199554443, "learning_rate": 0.00017046520066502365, "loss": 0.6301958560943604, "step": 171070 }, { "epoch": 1.0169350476428245, "grad_norm": 1.564446210861206, "learning_rate": 0.00017046058983173623, "loss": 0.6674258232116699, "step": 171080 }, { "epoch": 1.016994489719493, "grad_norm": 1.6280436515808105, "learning_rate": 0.00017045597870922507, "loss": 0.5868309497833252, "step": 171090 }, { "epoch": 1.0170539317961613, "grad_norm": 1.7518088817596436, "learning_rate": 0.00017045136729751232, "loss": 0.614188814163208, "step": 171100 }, { "epoch": 1.0171133738728295, "grad_norm": 1.3169078826904297, "learning_rate": 0.00017044675559661998, "loss": 0.6360115051269531, "step": 171110 }, { "epoch": 1.017172815949498, "grad_norm": 1.2151871919631958, "learning_rate": 0.00017044214360657008, "loss": 0.7002664089202881, "step": 171120 }, { "epoch": 1.0172322580261663, "grad_norm": 1.6174626350402832, "learning_rate": 0.00017043753132738477, "loss": 0.6612938404083252, "step": 171130 }, { "epoch": 1.0172917001028348, "grad_norm": 1.7321536540985107, "learning_rate": 0.000170432918759086, "loss": 0.6559486389160156, "step": 171140 }, { "epoch": 1.0173511421795032, "grad_norm": 1.4849213361740112, "learning_rate": 0.00017042830590169593, "loss": 0.6171015739440918, "step": 171150 }, { "epoch": 1.0174105842561716, "grad_norm": 1.6168830394744873, "learning_rate": 0.00017042369275523656, "loss": 0.5999382019042969, "step": 171160 }, { "epoch": 1.01747002633284, "grad_norm": 1.9698879718780518, "learning_rate": 0.00017041907931973003, "loss": 0.6024443626403808, "step": 171170 }, { "epoch": 1.0175294684095084, "grad_norm": 1.9246262311935425, "learning_rate": 0.00017041446559519835, "loss": 0.6892827033996582, "step": 171180 }, { "epoch": 1.0175889104861768, "grad_norm": 1.5429331064224243, "learning_rate": 0.00017040985158166364, "loss": 0.5935894966125488, "step": 171190 }, { "epoch": 1.017648352562845, "grad_norm": 1.4573220014572144, "learning_rate": 0.0001704052372791479, "loss": 0.5683454513549805, "step": 171200 }, { "epoch": 1.0177077946395134, "grad_norm": 1.690596580505371, "learning_rate": 0.00017040062268767328, "loss": 0.6555120944976807, "step": 171210 }, { "epoch": 1.0177672367161819, "grad_norm": 1.1954506635665894, "learning_rate": 0.0001703960078072618, "loss": 0.6111281394958497, "step": 171220 }, { "epoch": 1.0178266787928503, "grad_norm": 1.7534526586532593, "learning_rate": 0.00017039139263793555, "loss": 0.6652639865875244, "step": 171230 }, { "epoch": 1.0178861208695187, "grad_norm": 2.3296573162078857, "learning_rate": 0.00017038677717971662, "loss": 0.5716448783874511, "step": 171240 }, { "epoch": 1.017945562946187, "grad_norm": 1.7403401136398315, "learning_rate": 0.0001703821614326271, "loss": 0.6462997436523438, "step": 171250 }, { "epoch": 1.0180050050228555, "grad_norm": 1.392775535583496, "learning_rate": 0.00017037754539668903, "loss": 0.6769250869750977, "step": 171260 }, { "epoch": 1.018064447099524, "grad_norm": 1.3625409603118896, "learning_rate": 0.0001703729290719245, "loss": 0.6333223342895508, "step": 171270 }, { "epoch": 1.0181238891761923, "grad_norm": 1.7956622838974, "learning_rate": 0.00017036831245835564, "loss": 0.6587752342224121, "step": 171280 }, { "epoch": 1.0181833312528608, "grad_norm": 1.8951503038406372, "learning_rate": 0.0001703636955560045, "loss": 0.5809303283691406, "step": 171290 }, { "epoch": 1.018242773329529, "grad_norm": 1.6521105766296387, "learning_rate": 0.00017035907836489316, "loss": 0.6096145629882812, "step": 171300 }, { "epoch": 1.0183022154061974, "grad_norm": 1.4973368644714355, "learning_rate": 0.00017035446088504373, "loss": 0.6463277816772461, "step": 171310 }, { "epoch": 1.0183616574828658, "grad_norm": 1.7442240715026855, "learning_rate": 0.00017034984311647825, "loss": 0.631039047241211, "step": 171320 }, { "epoch": 1.0184210995595342, "grad_norm": 1.87265944480896, "learning_rate": 0.00017034522505921887, "loss": 0.6001886367797852, "step": 171330 }, { "epoch": 1.0184805416362026, "grad_norm": 1.7577059268951416, "learning_rate": 0.00017034060671328765, "loss": 0.5730881690979004, "step": 171340 }, { "epoch": 1.018539983712871, "grad_norm": 1.6376250982284546, "learning_rate": 0.00017033598807870666, "loss": 0.6342350006103515, "step": 171350 }, { "epoch": 1.0185994257895394, "grad_norm": 1.9693949222564697, "learning_rate": 0.00017033136915549807, "loss": 0.6735038757324219, "step": 171360 }, { "epoch": 1.0186588678662079, "grad_norm": 1.5572878122329712, "learning_rate": 0.0001703267499436839, "loss": 0.6007484436035156, "step": 171370 }, { "epoch": 1.0187183099428763, "grad_norm": 2.075803518295288, "learning_rate": 0.00017032213044328626, "loss": 0.7007736682891845, "step": 171380 }, { "epoch": 1.0187777520195445, "grad_norm": 1.1114461421966553, "learning_rate": 0.0001703175106543273, "loss": 0.5580680847167969, "step": 171390 }, { "epoch": 1.0188371940962129, "grad_norm": 2.2668652534484863, "learning_rate": 0.00017031289057682904, "loss": 0.6527328014373779, "step": 171400 }, { "epoch": 1.0188966361728813, "grad_norm": 1.2892937660217285, "learning_rate": 0.00017030827021081364, "loss": 0.6058586120605469, "step": 171410 }, { "epoch": 1.0189560782495497, "grad_norm": 1.5542646646499634, "learning_rate": 0.00017030364955630318, "loss": 0.5648640155792236, "step": 171420 }, { "epoch": 1.0190155203262181, "grad_norm": 1.7427552938461304, "learning_rate": 0.00017029902861331978, "loss": 0.6231308937072754, "step": 171430 }, { "epoch": 1.0190749624028865, "grad_norm": 1.5515328645706177, "learning_rate": 0.0001702944073818855, "loss": 0.7214113235473633, "step": 171440 }, { "epoch": 1.019134404479555, "grad_norm": 1.4639054536819458, "learning_rate": 0.00017028978586202252, "loss": 0.6329301834106446, "step": 171450 }, { "epoch": 1.0191938465562234, "grad_norm": 1.4868160486221313, "learning_rate": 0.00017028516405375287, "loss": 0.6365469455718994, "step": 171460 }, { "epoch": 1.0192532886328918, "grad_norm": 1.5540820360183716, "learning_rate": 0.00017028054195709875, "loss": 0.6142312049865722, "step": 171470 }, { "epoch": 1.01931273070956, "grad_norm": 1.691450834274292, "learning_rate": 0.00017027591957208214, "loss": 0.7114354610443115, "step": 171480 }, { "epoch": 1.0193721727862284, "grad_norm": 1.4387246370315552, "learning_rate": 0.0001702712968987253, "loss": 0.6071710109710693, "step": 171490 }, { "epoch": 1.0194316148628968, "grad_norm": 1.6132841110229492, "learning_rate": 0.00017026667393705024, "loss": 0.6436051845550537, "step": 171500 }, { "epoch": 1.0194910569395652, "grad_norm": 1.537448763847351, "learning_rate": 0.00017026205068707912, "loss": 0.643001937866211, "step": 171510 }, { "epoch": 1.0195504990162336, "grad_norm": 1.354673981666565, "learning_rate": 0.000170257427148834, "loss": 0.6485001564025878, "step": 171520 }, { "epoch": 1.019609941092902, "grad_norm": 1.501454472541809, "learning_rate": 0.0001702528033223371, "loss": 0.6565376281738281, "step": 171530 }, { "epoch": 1.0196693831695705, "grad_norm": 1.181486964225769, "learning_rate": 0.00017024817920761046, "loss": 0.6086275100708007, "step": 171540 }, { "epoch": 1.0197288252462389, "grad_norm": 1.6584442853927612, "learning_rate": 0.00017024355480467623, "loss": 0.7030035018920898, "step": 171550 }, { "epoch": 1.0197882673229073, "grad_norm": 1.884476900100708, "learning_rate": 0.0001702389301135565, "loss": 0.6773768901824951, "step": 171560 }, { "epoch": 1.0198477093995755, "grad_norm": 1.5787793397903442, "learning_rate": 0.0001702343051342734, "loss": 0.6554308891296386, "step": 171570 }, { "epoch": 1.019907151476244, "grad_norm": 1.4546668529510498, "learning_rate": 0.0001702296798668491, "loss": 0.5973895072937012, "step": 171580 }, { "epoch": 1.0199665935529123, "grad_norm": 1.6054418087005615, "learning_rate": 0.00017022505431130573, "loss": 0.6692825317382812, "step": 171590 }, { "epoch": 1.0200260356295807, "grad_norm": 1.5941567420959473, "learning_rate": 0.0001702204284676653, "loss": 0.5836583137512207, "step": 171600 }, { "epoch": 1.0200854777062491, "grad_norm": 1.89049232006073, "learning_rate": 0.0001702158023359501, "loss": 0.6378663063049317, "step": 171610 }, { "epoch": 1.0201449197829175, "grad_norm": 1.292770504951477, "learning_rate": 0.00017021117591618212, "loss": 0.5894835472106934, "step": 171620 }, { "epoch": 1.020204361859586, "grad_norm": 2.2345774173736572, "learning_rate": 0.00017020654920838355, "loss": 0.6759956359863282, "step": 171630 }, { "epoch": 1.0202638039362544, "grad_norm": 1.3598246574401855, "learning_rate": 0.00017020192221257655, "loss": 0.6656022548675538, "step": 171640 }, { "epoch": 1.0203232460129228, "grad_norm": 1.5702193975448608, "learning_rate": 0.00017019729492878324, "loss": 0.6365015506744385, "step": 171650 }, { "epoch": 1.0203826880895912, "grad_norm": 1.6991349458694458, "learning_rate": 0.0001701926673570257, "loss": 0.6592326164245605, "step": 171660 }, { "epoch": 1.0204421301662594, "grad_norm": 1.4781577587127686, "learning_rate": 0.00017018803949732616, "loss": 0.6823465347290039, "step": 171670 }, { "epoch": 1.0205015722429278, "grad_norm": 1.2444007396697998, "learning_rate": 0.0001701834113497067, "loss": 0.6362209796905518, "step": 171680 }, { "epoch": 1.0205610143195962, "grad_norm": 1.5083106756210327, "learning_rate": 0.00017017878291418945, "loss": 0.6317631721496582, "step": 171690 }, { "epoch": 1.0206204563962646, "grad_norm": 1.6351450681686401, "learning_rate": 0.00017017415419079657, "loss": 0.6557882785797119, "step": 171700 }, { "epoch": 1.020679898472933, "grad_norm": 1.6020954847335815, "learning_rate": 0.00017016952517955017, "loss": 0.5898062229156494, "step": 171710 }, { "epoch": 1.0207393405496015, "grad_norm": 1.7375354766845703, "learning_rate": 0.00017016489588047247, "loss": 0.6031825065612793, "step": 171720 }, { "epoch": 1.0207987826262699, "grad_norm": 1.5389049053192139, "learning_rate": 0.00017016026629358558, "loss": 0.6165878295898437, "step": 171730 }, { "epoch": 1.0208582247029383, "grad_norm": 1.31490957736969, "learning_rate": 0.00017015563641891162, "loss": 0.6101864337921142, "step": 171740 }, { "epoch": 1.0209176667796067, "grad_norm": 1.2938414812088013, "learning_rate": 0.00017015100625647275, "loss": 0.5999238014221191, "step": 171750 }, { "epoch": 1.020977108856275, "grad_norm": 1.3422737121582031, "learning_rate": 0.00017014637580629112, "loss": 0.6501278877258301, "step": 171760 }, { "epoch": 1.0210365509329433, "grad_norm": 1.5784111022949219, "learning_rate": 0.0001701417450683889, "loss": 0.5948979377746582, "step": 171770 }, { "epoch": 1.0210959930096117, "grad_norm": 1.5925196409225464, "learning_rate": 0.00017013711404278823, "loss": 0.6351569652557373, "step": 171780 }, { "epoch": 1.0211554350862801, "grad_norm": 1.4075372219085693, "learning_rate": 0.00017013248272951123, "loss": 0.5438127994537354, "step": 171790 }, { "epoch": 1.0212148771629486, "grad_norm": 1.5620867013931274, "learning_rate": 0.00017012785112858008, "loss": 0.6461559772491455, "step": 171800 }, { "epoch": 1.021274319239617, "grad_norm": 1.582473635673523, "learning_rate": 0.00017012321924001698, "loss": 0.6367373466491699, "step": 171810 }, { "epoch": 1.0213337613162854, "grad_norm": 2.1758525371551514, "learning_rate": 0.00017011858706384402, "loss": 0.6685535430908203, "step": 171820 }, { "epoch": 1.0213932033929538, "grad_norm": 1.253078818321228, "learning_rate": 0.0001701139546000834, "loss": 0.5664770126342773, "step": 171830 }, { "epoch": 1.0214526454696222, "grad_norm": 1.5604642629623413, "learning_rate": 0.00017010932184875727, "loss": 0.6262061119079589, "step": 171840 }, { "epoch": 1.0215120875462904, "grad_norm": 1.4560319185256958, "learning_rate": 0.00017010468880988779, "loss": 0.6332578659057617, "step": 171850 }, { "epoch": 1.0215715296229588, "grad_norm": 1.2442476749420166, "learning_rate": 0.00017010005548349707, "loss": 0.6027169227600098, "step": 171860 }, { "epoch": 1.0216309716996272, "grad_norm": 1.5023013353347778, "learning_rate": 0.00017009542186960738, "loss": 0.6091330528259278, "step": 171870 }, { "epoch": 1.0216904137762957, "grad_norm": 1.7823890447616577, "learning_rate": 0.00017009078796824086, "loss": 0.660644817352295, "step": 171880 }, { "epoch": 1.021749855852964, "grad_norm": 1.7396056652069092, "learning_rate": 0.00017008615377941958, "loss": 0.6144784927368164, "step": 171890 }, { "epoch": 1.0218092979296325, "grad_norm": 1.4316729307174683, "learning_rate": 0.0001700815193031658, "loss": 0.6257074356079102, "step": 171900 }, { "epoch": 1.021868740006301, "grad_norm": 1.6002981662750244, "learning_rate": 0.00017007688453950166, "loss": 0.6515217304229737, "step": 171910 }, { "epoch": 1.0219281820829693, "grad_norm": 1.4482734203338623, "learning_rate": 0.00017007224948844936, "loss": 0.5787777900695801, "step": 171920 }, { "epoch": 1.0219876241596377, "grad_norm": 1.5637763738632202, "learning_rate": 0.00017006761415003103, "loss": 0.6182764530181885, "step": 171930 }, { "epoch": 1.022047066236306, "grad_norm": 1.2253302335739136, "learning_rate": 0.00017006297852426884, "loss": 0.5624540328979493, "step": 171940 }, { "epoch": 1.0221065083129743, "grad_norm": 1.7900804281234741, "learning_rate": 0.00017005834261118503, "loss": 0.7156229019165039, "step": 171950 }, { "epoch": 1.0221659503896428, "grad_norm": 2.0608859062194824, "learning_rate": 0.00017005370641080177, "loss": 0.6387266159057617, "step": 171960 }, { "epoch": 1.0222253924663112, "grad_norm": 1.8759653568267822, "learning_rate": 0.00017004906992314114, "loss": 0.5707582473754883, "step": 171970 }, { "epoch": 1.0222848345429796, "grad_norm": 1.7281253337860107, "learning_rate": 0.0001700444331482254, "loss": 0.5994421958923339, "step": 171980 }, { "epoch": 1.022344276619648, "grad_norm": 1.7986525297164917, "learning_rate": 0.00017003979608607673, "loss": 0.6183189392089844, "step": 171990 }, { "epoch": 1.0224037186963164, "grad_norm": 1.6640360355377197, "learning_rate": 0.00017003515873671726, "loss": 0.6252961158752441, "step": 172000 }, { "epoch": 1.0224631607729848, "grad_norm": 1.6501532793045044, "learning_rate": 0.00017003052110016925, "loss": 0.6072279453277588, "step": 172010 }, { "epoch": 1.0225226028496532, "grad_norm": 2.694657564163208, "learning_rate": 0.00017002588317645482, "loss": 0.6126167297363281, "step": 172020 }, { "epoch": 1.0225820449263217, "grad_norm": 1.7917829751968384, "learning_rate": 0.00017002124496559622, "loss": 0.7535585403442383, "step": 172030 }, { "epoch": 1.0226414870029898, "grad_norm": 1.904797911643982, "learning_rate": 0.00017001660646761554, "loss": 0.6385337829589843, "step": 172040 }, { "epoch": 1.0227009290796583, "grad_norm": 1.5251840353012085, "learning_rate": 0.00017001196768253506, "loss": 0.654130220413208, "step": 172050 }, { "epoch": 1.0227603711563267, "grad_norm": 1.597100019454956, "learning_rate": 0.00017000732861037696, "loss": 0.6411657810211182, "step": 172060 }, { "epoch": 1.022819813232995, "grad_norm": 1.7101856470108032, "learning_rate": 0.00017000268925116338, "loss": 0.6488665580749512, "step": 172070 }, { "epoch": 1.0228792553096635, "grad_norm": 1.8462376594543457, "learning_rate": 0.00016999804960491656, "loss": 0.6461438655853271, "step": 172080 }, { "epoch": 1.022938697386332, "grad_norm": 1.2929186820983887, "learning_rate": 0.00016999340967165867, "loss": 0.6301588535308837, "step": 172090 }, { "epoch": 1.0229981394630003, "grad_norm": 1.2050679922103882, "learning_rate": 0.00016998876945141191, "loss": 0.5592713356018066, "step": 172100 }, { "epoch": 1.0230575815396687, "grad_norm": 1.7209885120391846, "learning_rate": 0.00016998412894419848, "loss": 0.5957103252410889, "step": 172110 }, { "epoch": 1.0231170236163372, "grad_norm": 1.5329548120498657, "learning_rate": 0.0001699794881500406, "loss": 0.5694952964782715, "step": 172120 }, { "epoch": 1.0231764656930054, "grad_norm": 2.010136604309082, "learning_rate": 0.00016997484706896042, "loss": 0.6750651836395264, "step": 172130 }, { "epoch": 1.0232359077696738, "grad_norm": 1.3993648290634155, "learning_rate": 0.0001699702057009802, "loss": 0.5707292556762695, "step": 172140 }, { "epoch": 1.0232953498463422, "grad_norm": 1.8942208290100098, "learning_rate": 0.0001699655640461221, "loss": 0.6511432647705078, "step": 172150 }, { "epoch": 1.0233547919230106, "grad_norm": 2.3226728439331055, "learning_rate": 0.00016996092210440838, "loss": 0.631538724899292, "step": 172160 }, { "epoch": 1.023414233999679, "grad_norm": 1.8898439407348633, "learning_rate": 0.00016995627987586114, "loss": 0.5868665695190429, "step": 172170 }, { "epoch": 1.0234736760763474, "grad_norm": 1.6896473169326782, "learning_rate": 0.00016995163736050265, "loss": 0.6021864891052247, "step": 172180 }, { "epoch": 1.0235331181530158, "grad_norm": 1.3872872591018677, "learning_rate": 0.00016994699455835516, "loss": 0.6449332714080811, "step": 172190 }, { "epoch": 1.0235925602296843, "grad_norm": 1.7616616487503052, "learning_rate": 0.00016994235146944084, "loss": 0.609835147857666, "step": 172200 }, { "epoch": 1.0236520023063527, "grad_norm": 1.5430251359939575, "learning_rate": 0.0001699377080937819, "loss": 0.6131323337554931, "step": 172210 }, { "epoch": 1.0237114443830209, "grad_norm": 1.6804020404815674, "learning_rate": 0.00016993306443140052, "loss": 0.6117196083068848, "step": 172220 }, { "epoch": 1.0237708864596893, "grad_norm": 1.6723037958145142, "learning_rate": 0.00016992842048231896, "loss": 0.6264164447784424, "step": 172230 }, { "epoch": 1.0238303285363577, "grad_norm": 1.5922383069992065, "learning_rate": 0.00016992377624655943, "loss": 0.5803480625152588, "step": 172240 }, { "epoch": 1.023889770613026, "grad_norm": 1.5215171575546265, "learning_rate": 0.00016991913172414414, "loss": 0.5977907180786133, "step": 172250 }, { "epoch": 1.0239492126896945, "grad_norm": 1.530041217803955, "learning_rate": 0.00016991448691509528, "loss": 0.6275101661682129, "step": 172260 }, { "epoch": 1.024008654766363, "grad_norm": 1.1928306818008423, "learning_rate": 0.0001699098418194351, "loss": 0.5862599372863769, "step": 172270 }, { "epoch": 1.0240680968430314, "grad_norm": 1.4780452251434326, "learning_rate": 0.00016990519643718586, "loss": 0.6265496253967285, "step": 172280 }, { "epoch": 1.0241275389196998, "grad_norm": 1.8062841892242432, "learning_rate": 0.00016990055076836967, "loss": 0.6383676052093505, "step": 172290 }, { "epoch": 1.0241869809963682, "grad_norm": 1.318717122077942, "learning_rate": 0.00016989590481300887, "loss": 0.6381108283996582, "step": 172300 }, { "epoch": 1.0242464230730364, "grad_norm": 1.5563675165176392, "learning_rate": 0.00016989125857112561, "loss": 0.6401255607604981, "step": 172310 }, { "epoch": 1.0243058651497048, "grad_norm": 1.5769952535629272, "learning_rate": 0.00016988661204274218, "loss": 0.6470918655395508, "step": 172320 }, { "epoch": 1.0243653072263732, "grad_norm": 1.704513669013977, "learning_rate": 0.00016988196522788076, "loss": 0.6260066509246827, "step": 172330 }, { "epoch": 1.0244247493030416, "grad_norm": 1.6747223138809204, "learning_rate": 0.00016987731812656356, "loss": 0.6356329917907715, "step": 172340 }, { "epoch": 1.02448419137971, "grad_norm": 1.2637606859207153, "learning_rate": 0.00016987267073881286, "loss": 0.6232022285461426, "step": 172350 }, { "epoch": 1.0245436334563784, "grad_norm": 1.6927417516708374, "learning_rate": 0.00016986802306465085, "loss": 0.6322414875030518, "step": 172360 }, { "epoch": 1.0246030755330469, "grad_norm": 1.3598947525024414, "learning_rate": 0.0001698633751040998, "loss": 0.5753236770629883, "step": 172370 }, { "epoch": 1.0246625176097153, "grad_norm": 1.7761659622192383, "learning_rate": 0.00016985872685718192, "loss": 0.6389567852020264, "step": 172380 }, { "epoch": 1.0247219596863837, "grad_norm": 1.4986662864685059, "learning_rate": 0.00016985407832391944, "loss": 0.6483256340026855, "step": 172390 }, { "epoch": 1.024781401763052, "grad_norm": 1.62087881565094, "learning_rate": 0.00016984942950433462, "loss": 0.6266362190246582, "step": 172400 }, { "epoch": 1.0248408438397203, "grad_norm": 1.5641981363296509, "learning_rate": 0.0001698447803984497, "loss": 0.5492016792297363, "step": 172410 }, { "epoch": 1.0249002859163887, "grad_norm": 1.9036445617675781, "learning_rate": 0.00016984013100628691, "loss": 0.6423686981201172, "step": 172420 }, { "epoch": 1.0249597279930571, "grad_norm": 2.0302374362945557, "learning_rate": 0.00016983548132786847, "loss": 0.6321619987487793, "step": 172430 }, { "epoch": 1.0250191700697255, "grad_norm": 1.8655046224594116, "learning_rate": 0.00016983083136321662, "loss": 0.5708266258239746, "step": 172440 }, { "epoch": 1.025078612146394, "grad_norm": 1.6775453090667725, "learning_rate": 0.0001698261811123537, "loss": 0.6667524337768554, "step": 172450 }, { "epoch": 1.0251380542230624, "grad_norm": 1.856848120689392, "learning_rate": 0.0001698215305753018, "loss": 0.6353648185729981, "step": 172460 }, { "epoch": 1.0251974962997308, "grad_norm": 1.614203929901123, "learning_rate": 0.0001698168797520833, "loss": 0.6675918579101563, "step": 172470 }, { "epoch": 1.0252569383763992, "grad_norm": 1.3153784275054932, "learning_rate": 0.00016981222864272038, "loss": 0.667817497253418, "step": 172480 }, { "epoch": 1.0253163804530676, "grad_norm": 1.5620275735855103, "learning_rate": 0.00016980757724723532, "loss": 0.679951286315918, "step": 172490 }, { "epoch": 1.0253758225297358, "grad_norm": 1.9206297397613525, "learning_rate": 0.0001698029255656503, "loss": 0.6322770118713379, "step": 172500 }, { "epoch": 1.0254352646064042, "grad_norm": 1.3632358312606812, "learning_rate": 0.0001697982735979877, "loss": 0.614406156539917, "step": 172510 }, { "epoch": 1.0254947066830726, "grad_norm": 1.6408276557922363, "learning_rate": 0.0001697936213442697, "loss": 0.6218080997467041, "step": 172520 }, { "epoch": 1.025554148759741, "grad_norm": 1.9561327695846558, "learning_rate": 0.0001697889688045185, "loss": 0.6510281085968017, "step": 172530 }, { "epoch": 1.0256135908364095, "grad_norm": 1.4346458911895752, "learning_rate": 0.00016978431597875642, "loss": 0.6062038898468017, "step": 172540 }, { "epoch": 1.0256730329130779, "grad_norm": 1.5369256734848022, "learning_rate": 0.00016977966286700573, "loss": 0.5943434715270997, "step": 172550 }, { "epoch": 1.0257324749897463, "grad_norm": 1.8325520753860474, "learning_rate": 0.00016977500946928868, "loss": 0.6518710136413575, "step": 172560 }, { "epoch": 1.0257919170664147, "grad_norm": 1.2777400016784668, "learning_rate": 0.0001697703557856275, "loss": 0.6061408996582032, "step": 172570 }, { "epoch": 1.0258513591430831, "grad_norm": 1.6387897729873657, "learning_rate": 0.0001697657018160445, "loss": 0.5851632118225097, "step": 172580 }, { "epoch": 1.0259108012197513, "grad_norm": 1.7639350891113281, "learning_rate": 0.00016976104756056187, "loss": 0.6856225967407227, "step": 172590 }, { "epoch": 1.0259702432964197, "grad_norm": 1.4184261560440063, "learning_rate": 0.00016975639301920195, "loss": 0.6118532657623291, "step": 172600 }, { "epoch": 1.0260296853730881, "grad_norm": 1.7113821506500244, "learning_rate": 0.00016975173819198694, "loss": 0.5878150939941407, "step": 172610 }, { "epoch": 1.0260891274497566, "grad_norm": 1.6016300916671753, "learning_rate": 0.0001697470830789392, "loss": 0.5921830177307129, "step": 172620 }, { "epoch": 1.026148569526425, "grad_norm": 1.8574252128601074, "learning_rate": 0.00016974242768008087, "loss": 0.6329338073730468, "step": 172630 }, { "epoch": 1.0262080116030934, "grad_norm": 1.6251366138458252, "learning_rate": 0.0001697377719954343, "loss": 0.6512003898620605, "step": 172640 }, { "epoch": 1.0262674536797618, "grad_norm": 1.6714656352996826, "learning_rate": 0.00016973311602502185, "loss": 0.6608684539794922, "step": 172650 }, { "epoch": 1.0263268957564302, "grad_norm": 1.4605613946914673, "learning_rate": 0.0001697284597688656, "loss": 0.6119467735290527, "step": 172660 }, { "epoch": 1.0263863378330986, "grad_norm": 1.6549348831176758, "learning_rate": 0.00016972380322698792, "loss": 0.6612964630126953, "step": 172670 }, { "epoch": 1.0264457799097668, "grad_norm": 1.265560269355774, "learning_rate": 0.0001697191463994111, "loss": 0.5918111324310302, "step": 172680 }, { "epoch": 1.0265052219864352, "grad_norm": 1.201369285583496, "learning_rate": 0.00016971448928615742, "loss": 0.5785019397735596, "step": 172690 }, { "epoch": 1.0265646640631036, "grad_norm": 1.3281012773513794, "learning_rate": 0.00016970983188724915, "loss": 0.558054256439209, "step": 172700 }, { "epoch": 1.026624106139772, "grad_norm": 1.5848844051361084, "learning_rate": 0.0001697051742027085, "loss": 0.5917842864990235, "step": 172710 }, { "epoch": 1.0266835482164405, "grad_norm": 1.3340147733688354, "learning_rate": 0.00016970051623255782, "loss": 0.7149927616119385, "step": 172720 }, { "epoch": 1.026742990293109, "grad_norm": 1.3101402521133423, "learning_rate": 0.00016969585797681943, "loss": 0.5729810714721679, "step": 172730 }, { "epoch": 1.0268024323697773, "grad_norm": 1.6825282573699951, "learning_rate": 0.0001696911994355155, "loss": 0.6047867774963379, "step": 172740 }, { "epoch": 1.0268618744464457, "grad_norm": 1.2747865915298462, "learning_rate": 0.00016968654060866843, "loss": 0.6140639305114746, "step": 172750 }, { "epoch": 1.0269213165231141, "grad_norm": 1.6787645816802979, "learning_rate": 0.00016968188149630044, "loss": 0.6652823448181152, "step": 172760 }, { "epoch": 1.0269807585997826, "grad_norm": 1.6980983018875122, "learning_rate": 0.00016967722209843382, "loss": 0.6714985847473145, "step": 172770 }, { "epoch": 1.0270402006764507, "grad_norm": 1.6122008562088013, "learning_rate": 0.0001696725624150909, "loss": 0.6590098381042481, "step": 172780 }, { "epoch": 1.0270996427531192, "grad_norm": 1.6148730516433716, "learning_rate": 0.0001696679024462939, "loss": 0.6142485618591309, "step": 172790 }, { "epoch": 1.0271590848297876, "grad_norm": 1.773298978805542, "learning_rate": 0.0001696632421920652, "loss": 0.6198874473571777, "step": 172800 }, { "epoch": 1.027218526906456, "grad_norm": 1.6242623329162598, "learning_rate": 0.000169658581652427, "loss": 0.6101170539855957, "step": 172810 }, { "epoch": 1.0272779689831244, "grad_norm": 1.7188705205917358, "learning_rate": 0.00016965392082740168, "loss": 0.6600462436676026, "step": 172820 }, { "epoch": 1.0273374110597928, "grad_norm": 1.441562533378601, "learning_rate": 0.00016964925971701148, "loss": 0.6569554805755615, "step": 172830 }, { "epoch": 1.0273968531364612, "grad_norm": 1.6138461828231812, "learning_rate": 0.00016964459832127874, "loss": 0.6168250560760498, "step": 172840 }, { "epoch": 1.0274562952131296, "grad_norm": 1.4180771112442017, "learning_rate": 0.0001696399366402257, "loss": 0.5547712326049805, "step": 172850 }, { "epoch": 1.027515737289798, "grad_norm": 1.5675584077835083, "learning_rate": 0.00016963527467387472, "loss": 0.6581366539001465, "step": 172860 }, { "epoch": 1.0275751793664663, "grad_norm": 1.7845813035964966, "learning_rate": 0.00016963061242224807, "loss": 0.6081218719482422, "step": 172870 }, { "epoch": 1.0276346214431347, "grad_norm": 1.4585217237472534, "learning_rate": 0.00016962594988536805, "loss": 0.6401768207550049, "step": 172880 }, { "epoch": 1.027694063519803, "grad_norm": 1.7404447793960571, "learning_rate": 0.00016962128706325696, "loss": 0.6371860027313232, "step": 172890 }, { "epoch": 1.0277535055964715, "grad_norm": 1.4343613386154175, "learning_rate": 0.00016961662395593714, "loss": 0.6084717750549317, "step": 172900 }, { "epoch": 1.02781294767314, "grad_norm": 1.5949941873550415, "learning_rate": 0.00016961196056343087, "loss": 0.6158593654632568, "step": 172910 }, { "epoch": 1.0278723897498083, "grad_norm": 1.6154299974441528, "learning_rate": 0.00016960729688576045, "loss": 0.624793291091919, "step": 172920 }, { "epoch": 1.0279318318264767, "grad_norm": 1.8025673627853394, "learning_rate": 0.00016960263292294822, "loss": 0.668553638458252, "step": 172930 }, { "epoch": 1.0279912739031452, "grad_norm": 1.9200080633163452, "learning_rate": 0.00016959796867501648, "loss": 0.5639647960662841, "step": 172940 }, { "epoch": 1.0280507159798136, "grad_norm": 1.4452778100967407, "learning_rate": 0.00016959330414198747, "loss": 0.5887966156005859, "step": 172950 }, { "epoch": 1.0281101580564818, "grad_norm": 1.210930347442627, "learning_rate": 0.00016958863932388366, "loss": 0.6057706832885742, "step": 172960 }, { "epoch": 1.0281696001331502, "grad_norm": 1.588970422744751, "learning_rate": 0.00016958397422072718, "loss": 0.5899540424346924, "step": 172970 }, { "epoch": 1.0282290422098186, "grad_norm": 1.4939384460449219, "learning_rate": 0.00016957930883254048, "loss": 0.6152304172515869, "step": 172980 }, { "epoch": 1.028288484286487, "grad_norm": 1.3927054405212402, "learning_rate": 0.00016957464315934585, "loss": 0.5910731315612793, "step": 172990 }, { "epoch": 1.0283479263631554, "grad_norm": 1.5119904279708862, "learning_rate": 0.0001695699772011656, "loss": 0.6292470932006836, "step": 173000 }, { "epoch": 1.0284073684398238, "grad_norm": 1.7904138565063477, "learning_rate": 0.00016956531095802205, "loss": 0.5706283569335937, "step": 173010 }, { "epoch": 1.0284668105164922, "grad_norm": 1.3642481565475464, "learning_rate": 0.0001695606444299375, "loss": 0.7090198993682861, "step": 173020 }, { "epoch": 1.0285262525931607, "grad_norm": 1.874460220336914, "learning_rate": 0.0001695559776169343, "loss": 0.6035079002380371, "step": 173030 }, { "epoch": 1.028585694669829, "grad_norm": 1.7981441020965576, "learning_rate": 0.00016955131051903476, "loss": 0.5859342098236084, "step": 173040 }, { "epoch": 1.0286451367464973, "grad_norm": 1.3875255584716797, "learning_rate": 0.00016954664313626123, "loss": 0.5835522651672364, "step": 173050 }, { "epoch": 1.0287045788231657, "grad_norm": 1.714667558670044, "learning_rate": 0.000169541975468636, "loss": 0.592745018005371, "step": 173060 }, { "epoch": 1.028764020899834, "grad_norm": 1.5098931789398193, "learning_rate": 0.00016953730751618142, "loss": 0.6179506301879882, "step": 173070 }, { "epoch": 1.0288234629765025, "grad_norm": 1.8265621662139893, "learning_rate": 0.0001695326392789198, "loss": 0.6019632339477539, "step": 173080 }, { "epoch": 1.028882905053171, "grad_norm": 1.3625754117965698, "learning_rate": 0.00016952797075687353, "loss": 0.6008252143859864, "step": 173090 }, { "epoch": 1.0289423471298393, "grad_norm": 1.6554538011550903, "learning_rate": 0.00016952330195006487, "loss": 0.6307940483093262, "step": 173100 }, { "epoch": 1.0290017892065078, "grad_norm": 1.6166459321975708, "learning_rate": 0.0001695186328585162, "loss": 0.5830227851867675, "step": 173110 }, { "epoch": 1.0290612312831762, "grad_norm": 1.6702724695205688, "learning_rate": 0.00016951396348224984, "loss": 0.6280169486999512, "step": 173120 }, { "epoch": 1.0291206733598446, "grad_norm": 2.2491815090179443, "learning_rate": 0.0001695092938212881, "loss": 0.6584418773651123, "step": 173130 }, { "epoch": 1.029180115436513, "grad_norm": 1.8331390619277954, "learning_rate": 0.0001695046238756534, "loss": 0.6262989997863769, "step": 173140 }, { "epoch": 1.0292395575131812, "grad_norm": 2.0157063007354736, "learning_rate": 0.00016949995364536798, "loss": 0.6319415092468261, "step": 173150 }, { "epoch": 1.0292989995898496, "grad_norm": 1.8463345766067505, "learning_rate": 0.00016949528313045425, "loss": 0.6225242614746094, "step": 173160 }, { "epoch": 1.029358441666518, "grad_norm": 1.2593398094177246, "learning_rate": 0.00016949061233093455, "loss": 0.6246545791625977, "step": 173170 }, { "epoch": 1.0294178837431864, "grad_norm": 1.5152523517608643, "learning_rate": 0.00016948594124683116, "loss": 0.5848441123962402, "step": 173180 }, { "epoch": 1.0294773258198548, "grad_norm": 1.4929184913635254, "learning_rate": 0.0001694812698781665, "loss": 0.6439948558807373, "step": 173190 }, { "epoch": 1.0295367678965233, "grad_norm": 1.528589129447937, "learning_rate": 0.00016947659822496287, "loss": 0.6092791557312012, "step": 173200 }, { "epoch": 1.0295962099731917, "grad_norm": 1.891045331954956, "learning_rate": 0.00016947192628724263, "loss": 0.6138729095458985, "step": 173210 }, { "epoch": 1.02965565204986, "grad_norm": 1.6228996515274048, "learning_rate": 0.00016946725406502813, "loss": 0.6196105003356933, "step": 173220 }, { "epoch": 1.0297150941265285, "grad_norm": 1.708883285522461, "learning_rate": 0.0001694625815583417, "loss": 0.6560803413391113, "step": 173230 }, { "epoch": 1.0297745362031967, "grad_norm": 1.6312516927719116, "learning_rate": 0.00016945790876720575, "loss": 0.6247068881988526, "step": 173240 }, { "epoch": 1.0298339782798651, "grad_norm": 1.8228724002838135, "learning_rate": 0.00016945323569164257, "loss": 0.5817800521850586, "step": 173250 }, { "epoch": 1.0298934203565335, "grad_norm": 1.5502641201019287, "learning_rate": 0.00016944856233167457, "loss": 0.5976327419281006, "step": 173260 }, { "epoch": 1.029952862433202, "grad_norm": 1.6366119384765625, "learning_rate": 0.00016944388868732403, "loss": 0.6145168304443359, "step": 173270 }, { "epoch": 1.0300123045098704, "grad_norm": 1.5155675411224365, "learning_rate": 0.00016943921475861336, "loss": 0.664252758026123, "step": 173280 }, { "epoch": 1.0300717465865388, "grad_norm": 1.3004322052001953, "learning_rate": 0.00016943454054556495, "loss": 0.6417372226715088, "step": 173290 }, { "epoch": 1.0301311886632072, "grad_norm": 1.4230045080184937, "learning_rate": 0.00016942986604820108, "loss": 0.5757639884948731, "step": 173300 }, { "epoch": 1.0301906307398756, "grad_norm": 1.4785493612289429, "learning_rate": 0.0001694251912665442, "loss": 0.6410172462463379, "step": 173310 }, { "epoch": 1.030250072816544, "grad_norm": 1.300572156906128, "learning_rate": 0.00016942051620061658, "loss": 0.6494558334350586, "step": 173320 }, { "epoch": 1.0303095148932122, "grad_norm": 1.134541630744934, "learning_rate": 0.00016941584085044064, "loss": 0.6041204452514648, "step": 173330 }, { "epoch": 1.0303689569698806, "grad_norm": 1.7797982692718506, "learning_rate": 0.00016941116521603875, "loss": 0.6042569160461426, "step": 173340 }, { "epoch": 1.030428399046549, "grad_norm": 1.6891289949417114, "learning_rate": 0.00016940648929743328, "loss": 0.6165967464447022, "step": 173350 }, { "epoch": 1.0304878411232175, "grad_norm": 1.4875227212905884, "learning_rate": 0.0001694018130946465, "loss": 0.6492244720458984, "step": 173360 }, { "epoch": 1.0305472831998859, "grad_norm": 1.62095308303833, "learning_rate": 0.00016939713660770096, "loss": 0.6467447757720948, "step": 173370 }, { "epoch": 1.0306067252765543, "grad_norm": 2.047848701477051, "learning_rate": 0.00016939245983661888, "loss": 0.6267104148864746, "step": 173380 }, { "epoch": 1.0306661673532227, "grad_norm": 1.6521059274673462, "learning_rate": 0.00016938778278142267, "loss": 0.6972305774688721, "step": 173390 }, { "epoch": 1.030725609429891, "grad_norm": 1.5972850322723389, "learning_rate": 0.00016938310544213473, "loss": 0.6624452590942382, "step": 173400 }, { "epoch": 1.0307850515065595, "grad_norm": 1.700460433959961, "learning_rate": 0.0001693784278187774, "loss": 0.7297078132629394, "step": 173410 }, { "epoch": 1.0308444935832277, "grad_norm": 1.7906014919281006, "learning_rate": 0.0001693737499113731, "loss": 0.729640007019043, "step": 173420 }, { "epoch": 1.0309039356598961, "grad_norm": 1.3356891870498657, "learning_rate": 0.0001693690717199442, "loss": 0.6095407962799072, "step": 173430 }, { "epoch": 1.0309633777365645, "grad_norm": 1.4289637804031372, "learning_rate": 0.00016936439324451302, "loss": 0.657022762298584, "step": 173440 }, { "epoch": 1.031022819813233, "grad_norm": 1.8074547052383423, "learning_rate": 0.00016935971448510203, "loss": 0.6703465461730957, "step": 173450 }, { "epoch": 1.0310822618899014, "grad_norm": 1.4118889570236206, "learning_rate": 0.00016935503544173353, "loss": 0.6767133712768555, "step": 173460 }, { "epoch": 1.0311417039665698, "grad_norm": 1.5997496843338013, "learning_rate": 0.0001693503561144299, "loss": 0.5539919376373291, "step": 173470 }, { "epoch": 1.0312011460432382, "grad_norm": 1.9079298973083496, "learning_rate": 0.00016934567650321364, "loss": 0.6010149478912353, "step": 173480 }, { "epoch": 1.0312605881199066, "grad_norm": 2.052617073059082, "learning_rate": 0.00016934099660810702, "loss": 0.613333797454834, "step": 173490 }, { "epoch": 1.031320030196575, "grad_norm": 1.797590732574463, "learning_rate": 0.0001693363164291325, "loss": 0.6756825923919678, "step": 173500 }, { "epoch": 1.0313794722732434, "grad_norm": 1.2283666133880615, "learning_rate": 0.00016933163596631238, "loss": 0.6141282081604004, "step": 173510 }, { "epoch": 1.0314389143499116, "grad_norm": 1.5321648120880127, "learning_rate": 0.00016932695521966915, "loss": 0.6208895683288574, "step": 173520 }, { "epoch": 1.03149835642658, "grad_norm": 1.7112884521484375, "learning_rate": 0.00016932227418922513, "loss": 0.6239728927612305, "step": 173530 }, { "epoch": 1.0315577985032485, "grad_norm": 1.2267862558364868, "learning_rate": 0.00016931759287500272, "loss": 0.6017379760742188, "step": 173540 }, { "epoch": 1.0316172405799169, "grad_norm": 1.0072107315063477, "learning_rate": 0.00016931291127702435, "loss": 0.5721559524536133, "step": 173550 }, { "epoch": 1.0316766826565853, "grad_norm": 1.4304964542388916, "learning_rate": 0.0001693082293953124, "loss": 0.6039294242858887, "step": 173560 }, { "epoch": 1.0317361247332537, "grad_norm": 1.8892756700515747, "learning_rate": 0.00016930354722988927, "loss": 0.6933629035949707, "step": 173570 }, { "epoch": 1.0317955668099221, "grad_norm": 2.3719022274017334, "learning_rate": 0.00016929886478077733, "loss": 0.6336805343627929, "step": 173580 }, { "epoch": 1.0318550088865905, "grad_norm": 1.6764687299728394, "learning_rate": 0.00016929418204799905, "loss": 0.6368416786193848, "step": 173590 }, { "epoch": 1.031914450963259, "grad_norm": 1.6699005365371704, "learning_rate": 0.0001692894990315767, "loss": 0.6495393753051758, "step": 173600 }, { "epoch": 1.0319738930399271, "grad_norm": 2.063753843307495, "learning_rate": 0.00016928481573153282, "loss": 0.6991966724395752, "step": 173610 }, { "epoch": 1.0320333351165956, "grad_norm": 1.4000691175460815, "learning_rate": 0.00016928013214788972, "loss": 0.6618464469909668, "step": 173620 }, { "epoch": 1.032092777193264, "grad_norm": 1.9250224828720093, "learning_rate": 0.0001692754482806699, "loss": 0.6463402271270752, "step": 173630 }, { "epoch": 1.0321522192699324, "grad_norm": 2.0958235263824463, "learning_rate": 0.00016927076412989565, "loss": 0.6386306762695313, "step": 173640 }, { "epoch": 1.0322116613466008, "grad_norm": 1.4766901731491089, "learning_rate": 0.00016926607969558949, "loss": 0.6294904708862304, "step": 173650 }, { "epoch": 1.0322711034232692, "grad_norm": 1.4511502981185913, "learning_rate": 0.00016926139497777372, "loss": 0.6438047409057617, "step": 173660 }, { "epoch": 1.0323305454999376, "grad_norm": 1.5924874544143677, "learning_rate": 0.0001692567099764708, "loss": 0.57423095703125, "step": 173670 }, { "epoch": 1.032389987576606, "grad_norm": 1.785555124282837, "learning_rate": 0.0001692520246917032, "loss": 0.582704734802246, "step": 173680 }, { "epoch": 1.0324494296532745, "grad_norm": 1.6184202432632446, "learning_rate": 0.00016924733912349323, "loss": 0.653870677947998, "step": 173690 }, { "epoch": 1.0325088717299427, "grad_norm": 1.849522590637207, "learning_rate": 0.00016924265327186334, "loss": 0.6930288791656494, "step": 173700 }, { "epoch": 1.032568313806611, "grad_norm": 1.7422099113464355, "learning_rate": 0.000169237967136836, "loss": 0.638002872467041, "step": 173710 }, { "epoch": 1.0326277558832795, "grad_norm": 1.5156978368759155, "learning_rate": 0.00016923328071843355, "loss": 0.6143194675445557, "step": 173720 }, { "epoch": 1.032687197959948, "grad_norm": 1.540909767150879, "learning_rate": 0.00016922859401667846, "loss": 0.619916296005249, "step": 173730 }, { "epoch": 1.0327466400366163, "grad_norm": 1.9027113914489746, "learning_rate": 0.00016922390703159315, "loss": 0.6093598365783691, "step": 173740 }, { "epoch": 1.0328060821132847, "grad_norm": 2.0336084365844727, "learning_rate": 0.00016921921976319998, "loss": 0.5868816375732422, "step": 173750 }, { "epoch": 1.0328655241899531, "grad_norm": 1.7234991788864136, "learning_rate": 0.00016921453221152146, "loss": 0.6581415176391602, "step": 173760 }, { "epoch": 1.0329249662666216, "grad_norm": 1.7568209171295166, "learning_rate": 0.00016920984437657994, "loss": 0.672739315032959, "step": 173770 }, { "epoch": 1.03298440834329, "grad_norm": 1.8309781551361084, "learning_rate": 0.00016920515625839787, "loss": 0.6776852130889892, "step": 173780 }, { "epoch": 1.0330438504199582, "grad_norm": 1.3690508604049683, "learning_rate": 0.0001692004678569977, "loss": 0.6479537010192871, "step": 173790 }, { "epoch": 1.0331032924966266, "grad_norm": 1.6990021467208862, "learning_rate": 0.00016919577917240183, "loss": 0.5841900825500488, "step": 173800 }, { "epoch": 1.033162734573295, "grad_norm": 1.5925649404525757, "learning_rate": 0.0001691910902046327, "loss": 0.6703928947448731, "step": 173810 }, { "epoch": 1.0332221766499634, "grad_norm": 1.64384126663208, "learning_rate": 0.00016918640095371274, "loss": 0.5907849311828614, "step": 173820 }, { "epoch": 1.0332816187266318, "grad_norm": 2.1385087966918945, "learning_rate": 0.00016918171141966438, "loss": 0.5537397384643554, "step": 173830 }, { "epoch": 1.0333410608033002, "grad_norm": 1.8703339099884033, "learning_rate": 0.00016917702160251005, "loss": 0.617539358139038, "step": 173840 }, { "epoch": 1.0334005028799687, "grad_norm": 1.6560498476028442, "learning_rate": 0.0001691723315022722, "loss": 0.5997862339019775, "step": 173850 }, { "epoch": 1.033459944956637, "grad_norm": 1.9135788679122925, "learning_rate": 0.00016916764111897325, "loss": 0.6284285545349121, "step": 173860 }, { "epoch": 1.0335193870333055, "grad_norm": 1.7285149097442627, "learning_rate": 0.0001691629504526356, "loss": 0.6265448570251465, "step": 173870 }, { "epoch": 1.033578829109974, "grad_norm": 1.7512283325195312, "learning_rate": 0.00016915825950328177, "loss": 0.5991410255432129, "step": 173880 }, { "epoch": 1.033638271186642, "grad_norm": 1.790792465209961, "learning_rate": 0.00016915356827093417, "loss": 0.6368467330932617, "step": 173890 }, { "epoch": 1.0336977132633105, "grad_norm": 1.523381233215332, "learning_rate": 0.00016914887675561523, "loss": 0.6203368663787842, "step": 173900 }, { "epoch": 1.033757155339979, "grad_norm": 1.3604494333267212, "learning_rate": 0.00016914418495734738, "loss": 0.5517436981201171, "step": 173910 }, { "epoch": 1.0338165974166473, "grad_norm": 1.2274084091186523, "learning_rate": 0.00016913949287615307, "loss": 0.6177033424377442, "step": 173920 }, { "epoch": 1.0338760394933157, "grad_norm": 1.9545925855636597, "learning_rate": 0.00016913480051205477, "loss": 0.6083609104156494, "step": 173930 }, { "epoch": 1.0339354815699842, "grad_norm": 1.5175665616989136, "learning_rate": 0.0001691301078650749, "loss": 0.6006592750549317, "step": 173940 }, { "epoch": 1.0339949236466526, "grad_norm": 1.7295151948928833, "learning_rate": 0.00016912541493523591, "loss": 0.6255946636199952, "step": 173950 }, { "epoch": 1.034054365723321, "grad_norm": 2.0698533058166504, "learning_rate": 0.00016912072172256025, "loss": 0.6183046340942383, "step": 173960 }, { "epoch": 1.0341138077999894, "grad_norm": 1.77164888381958, "learning_rate": 0.0001691160282270704, "loss": 0.613456916809082, "step": 173970 }, { "epoch": 1.0341732498766576, "grad_norm": 1.810036540031433, "learning_rate": 0.0001691113344487888, "loss": 0.611151123046875, "step": 173980 }, { "epoch": 1.034232691953326, "grad_norm": 1.5694491863250732, "learning_rate": 0.00016910664038773788, "loss": 0.6080082893371582, "step": 173990 }, { "epoch": 1.0342921340299944, "grad_norm": 1.6227902173995972, "learning_rate": 0.0001691019460439401, "loss": 0.6399755477905273, "step": 174000 }, { "epoch": 1.0343515761066628, "grad_norm": 1.177980899810791, "learning_rate": 0.00016909725141741791, "loss": 0.6728304386138916, "step": 174010 }, { "epoch": 1.0344110181833313, "grad_norm": 1.682803988456726, "learning_rate": 0.00016909255650819383, "loss": 0.6337007045745849, "step": 174020 }, { "epoch": 1.0344704602599997, "grad_norm": 1.9247117042541504, "learning_rate": 0.00016908786131629024, "loss": 0.5746468067169189, "step": 174030 }, { "epoch": 1.034529902336668, "grad_norm": 1.3169409036636353, "learning_rate": 0.00016908316584172964, "loss": 0.6353943824768067, "step": 174040 }, { "epoch": 1.0345893444133365, "grad_norm": 1.4206172227859497, "learning_rate": 0.00016907847008453445, "loss": 0.6137903213500977, "step": 174050 }, { "epoch": 1.034648786490005, "grad_norm": 1.6575645208358765, "learning_rate": 0.0001690737740447272, "loss": 0.6424202919006348, "step": 174060 }, { "epoch": 1.034708228566673, "grad_norm": 1.413874626159668, "learning_rate": 0.00016906907772233033, "loss": 0.6251736640930176, "step": 174070 }, { "epoch": 1.0347676706433415, "grad_norm": 1.254799246788025, "learning_rate": 0.00016906438111736628, "loss": 0.6113641738891602, "step": 174080 }, { "epoch": 1.03482711272001, "grad_norm": 1.6302132606506348, "learning_rate": 0.00016905968422985756, "loss": 0.5993166923522949, "step": 174090 }, { "epoch": 1.0348865547966783, "grad_norm": 1.795292854309082, "learning_rate": 0.00016905498705982656, "loss": 0.6449684619903564, "step": 174100 }, { "epoch": 1.0349459968733468, "grad_norm": 1.1153557300567627, "learning_rate": 0.00016905028960729584, "loss": 0.5580004692077637, "step": 174110 }, { "epoch": 1.0350054389500152, "grad_norm": 1.866275668144226, "learning_rate": 0.00016904559187228783, "loss": 0.6305230617523193, "step": 174120 }, { "epoch": 1.0350648810266836, "grad_norm": 1.5793416500091553, "learning_rate": 0.00016904089385482498, "loss": 0.6247808933258057, "step": 174130 }, { "epoch": 1.035124323103352, "grad_norm": 1.6630821228027344, "learning_rate": 0.0001690361955549298, "loss": 0.6288185119628906, "step": 174140 }, { "epoch": 1.0351837651800204, "grad_norm": 1.7991753816604614, "learning_rate": 0.00016903149697262477, "loss": 0.6348097324371338, "step": 174150 }, { "epoch": 1.0352432072566886, "grad_norm": 1.2319200038909912, "learning_rate": 0.00016902679810793233, "loss": 0.5860642433166504, "step": 174160 }, { "epoch": 1.035302649333357, "grad_norm": 1.4205013513565063, "learning_rate": 0.00016902209896087499, "loss": 0.6391807556152344, "step": 174170 }, { "epoch": 1.0353620914100254, "grad_norm": 1.6809300184249878, "learning_rate": 0.00016901739953147522, "loss": 0.620549488067627, "step": 174180 }, { "epoch": 1.0354215334866939, "grad_norm": 1.4271283149719238, "learning_rate": 0.00016901269981975546, "loss": 0.7071356773376465, "step": 174190 }, { "epoch": 1.0354809755633623, "grad_norm": 1.424437165260315, "learning_rate": 0.0001690079998257383, "loss": 0.6720785140991211, "step": 174200 }, { "epoch": 1.0355404176400307, "grad_norm": 1.2255173921585083, "learning_rate": 0.00016900329954944613, "loss": 0.5888573169708252, "step": 174210 }, { "epoch": 1.035599859716699, "grad_norm": 1.7025738954544067, "learning_rate": 0.00016899859899090143, "loss": 0.6318315029144287, "step": 174220 }, { "epoch": 1.0356593017933675, "grad_norm": 1.2192175388336182, "learning_rate": 0.00016899389815012669, "loss": 0.6633255004882812, "step": 174230 }, { "epoch": 1.035718743870036, "grad_norm": 1.435509204864502, "learning_rate": 0.00016898919702714447, "loss": 0.6755499362945556, "step": 174240 }, { "epoch": 1.0357781859467043, "grad_norm": 1.4552874565124512, "learning_rate": 0.0001689844956219772, "loss": 0.5870565414428711, "step": 174250 }, { "epoch": 1.0358376280233725, "grad_norm": 1.636867880821228, "learning_rate": 0.00016897979393464736, "loss": 0.6630861282348632, "step": 174260 }, { "epoch": 1.035897070100041, "grad_norm": 1.5687156915664673, "learning_rate": 0.0001689750919651775, "loss": 0.6102081298828125, "step": 174270 }, { "epoch": 1.0359565121767094, "grad_norm": 1.3225011825561523, "learning_rate": 0.00016897038971359004, "loss": 0.6123502731323243, "step": 174280 }, { "epoch": 1.0360159542533778, "grad_norm": 1.5038155317306519, "learning_rate": 0.0001689656871799075, "loss": 0.7009573936462402, "step": 174290 }, { "epoch": 1.0360753963300462, "grad_norm": 1.5673305988311768, "learning_rate": 0.0001689609843641524, "loss": 0.6126264572143555, "step": 174300 }, { "epoch": 1.0361348384067146, "grad_norm": 1.549015760421753, "learning_rate": 0.0001689562812663472, "loss": 0.713284969329834, "step": 174310 }, { "epoch": 1.036194280483383, "grad_norm": 2.4697554111480713, "learning_rate": 0.00016895157788651444, "loss": 0.6433499336242676, "step": 174320 }, { "epoch": 1.0362537225600514, "grad_norm": 1.4417085647583008, "learning_rate": 0.00016894687422467662, "loss": 0.6376701354980469, "step": 174330 }, { "epoch": 1.0363131646367199, "grad_norm": 1.7392852306365967, "learning_rate": 0.00016894217028085617, "loss": 0.6281476020812988, "step": 174340 }, { "epoch": 1.036372606713388, "grad_norm": 1.831178069114685, "learning_rate": 0.0001689374660550757, "loss": 0.6268142700195313, "step": 174350 }, { "epoch": 1.0364320487900565, "grad_norm": 1.2870006561279297, "learning_rate": 0.00016893276154735757, "loss": 0.6096614837646485, "step": 174360 }, { "epoch": 1.0364914908667249, "grad_norm": 1.5780984163284302, "learning_rate": 0.0001689280567577244, "loss": 0.6094151020050049, "step": 174370 }, { "epoch": 1.0365509329433933, "grad_norm": 1.6742545366287231, "learning_rate": 0.0001689233516861987, "loss": 0.6438142776489257, "step": 174380 }, { "epoch": 1.0366103750200617, "grad_norm": 1.619989037513733, "learning_rate": 0.0001689186463328029, "loss": 0.6009781360626221, "step": 174390 }, { "epoch": 1.0366698170967301, "grad_norm": 1.3894799947738647, "learning_rate": 0.0001689139406975596, "loss": 0.5839652061462403, "step": 174400 }, { "epoch": 1.0367292591733985, "grad_norm": 1.3115917444229126, "learning_rate": 0.0001689092347804912, "loss": 0.6331331253051757, "step": 174410 }, { "epoch": 1.036788701250067, "grad_norm": 1.5440720319747925, "learning_rate": 0.00016890452858162028, "loss": 0.6773309707641602, "step": 174420 }, { "epoch": 1.0368481433267354, "grad_norm": 1.6764144897460938, "learning_rate": 0.0001688998221009694, "loss": 0.5860917091369628, "step": 174430 }, { "epoch": 1.0369075854034036, "grad_norm": 2.0204763412475586, "learning_rate": 0.00016889511533856098, "loss": 0.5863276481628418, "step": 174440 }, { "epoch": 1.036967027480072, "grad_norm": 1.4568474292755127, "learning_rate": 0.0001688904082944176, "loss": 0.6093635559082031, "step": 174450 }, { "epoch": 1.0370264695567404, "grad_norm": 1.8283129930496216, "learning_rate": 0.0001688857009685617, "loss": 0.6438802719116211, "step": 174460 }, { "epoch": 1.0370859116334088, "grad_norm": 1.6542567014694214, "learning_rate": 0.00016888099336101592, "loss": 0.6490982055664063, "step": 174470 }, { "epoch": 1.0371453537100772, "grad_norm": 1.4292309284210205, "learning_rate": 0.00016887628547180265, "loss": 0.5691381454467773, "step": 174480 }, { "epoch": 1.0372047957867456, "grad_norm": 2.09389591217041, "learning_rate": 0.0001688715773009445, "loss": 0.6895203113555908, "step": 174490 }, { "epoch": 1.037264237863414, "grad_norm": 1.296927809715271, "learning_rate": 0.00016886686884846398, "loss": 0.6297972679138184, "step": 174500 }, { "epoch": 1.0373236799400825, "grad_norm": 1.3868820667266846, "learning_rate": 0.00016886216011438357, "loss": 0.641927433013916, "step": 174510 }, { "epoch": 1.0373831220167509, "grad_norm": 1.6541965007781982, "learning_rate": 0.00016885745109872585, "loss": 0.6032856941223145, "step": 174520 }, { "epoch": 1.037442564093419, "grad_norm": 2.0191006660461426, "learning_rate": 0.0001688527418015133, "loss": 0.5536109447479248, "step": 174530 }, { "epoch": 1.0375020061700875, "grad_norm": 1.7236320972442627, "learning_rate": 0.00016884803222276846, "loss": 0.62581787109375, "step": 174540 }, { "epoch": 1.037561448246756, "grad_norm": 1.8317644596099854, "learning_rate": 0.00016884332236251386, "loss": 0.6195826530456543, "step": 174550 }, { "epoch": 1.0376208903234243, "grad_norm": 1.5692813396453857, "learning_rate": 0.00016883861222077206, "loss": 0.5948862552642822, "step": 174560 }, { "epoch": 1.0376803324000927, "grad_norm": 1.813216209411621, "learning_rate": 0.00016883390179756554, "loss": 0.6108160018920898, "step": 174570 }, { "epoch": 1.0377397744767611, "grad_norm": 1.5288269519805908, "learning_rate": 0.0001688291910929169, "loss": 0.6133421897888184, "step": 174580 }, { "epoch": 1.0377992165534295, "grad_norm": 1.5490096807479858, "learning_rate": 0.00016882448010684857, "loss": 0.6539105415344239, "step": 174590 }, { "epoch": 1.037858658630098, "grad_norm": 1.4770185947418213, "learning_rate": 0.00016881976883938323, "loss": 0.6377663612365723, "step": 174600 }, { "epoch": 1.0379181007067664, "grad_norm": 1.4379651546478271, "learning_rate": 0.00016881505729054327, "loss": 0.5799512386322021, "step": 174610 }, { "epoch": 1.0379775427834348, "grad_norm": 1.476938009262085, "learning_rate": 0.00016881034546035133, "loss": 0.6556536197662354, "step": 174620 }, { "epoch": 1.038036984860103, "grad_norm": 1.776881217956543, "learning_rate": 0.00016880563334882993, "loss": 0.7056965827941895, "step": 174630 }, { "epoch": 1.0380964269367714, "grad_norm": 1.8823679685592651, "learning_rate": 0.00016880092095600157, "loss": 0.6080759048461915, "step": 174640 }, { "epoch": 1.0381558690134398, "grad_norm": 1.4211398363113403, "learning_rate": 0.00016879620828188883, "loss": 0.5723375797271728, "step": 174650 }, { "epoch": 1.0382153110901082, "grad_norm": 1.3247770071029663, "learning_rate": 0.00016879149532651424, "loss": 0.6019150257110596, "step": 174660 }, { "epoch": 1.0382747531667766, "grad_norm": 1.95207679271698, "learning_rate": 0.00016878678208990036, "loss": 0.6298362731933593, "step": 174670 }, { "epoch": 1.038334195243445, "grad_norm": 1.8180443048477173, "learning_rate": 0.0001687820685720697, "loss": 0.6402782440185547, "step": 174680 }, { "epoch": 1.0383936373201135, "grad_norm": 1.687596082687378, "learning_rate": 0.00016877735477304487, "loss": 0.6058411598205566, "step": 174690 }, { "epoch": 1.0384530793967819, "grad_norm": 1.67332923412323, "learning_rate": 0.00016877264069284836, "loss": 0.5667823791503906, "step": 174700 }, { "epoch": 1.0385125214734503, "grad_norm": 1.869657039642334, "learning_rate": 0.00016876792633150277, "loss": 0.6450179100036622, "step": 174710 }, { "epoch": 1.0385719635501185, "grad_norm": 1.5522773265838623, "learning_rate": 0.00016876321168903061, "loss": 0.5779661655426025, "step": 174720 }, { "epoch": 1.038631405626787, "grad_norm": 2.0333101749420166, "learning_rate": 0.00016875849676545445, "loss": 0.6909446239471435, "step": 174730 }, { "epoch": 1.0386908477034553, "grad_norm": 1.7123631238937378, "learning_rate": 0.00016875378156079688, "loss": 0.6733959197998047, "step": 174740 }, { "epoch": 1.0387502897801237, "grad_norm": 1.807206630706787, "learning_rate": 0.00016874906607508038, "loss": 0.6533631324768067, "step": 174750 }, { "epoch": 1.0388097318567922, "grad_norm": 1.727934718132019, "learning_rate": 0.00016874435030832753, "loss": 0.6333348274230957, "step": 174760 }, { "epoch": 1.0388691739334606, "grad_norm": 1.9104290008544922, "learning_rate": 0.00016873963426056093, "loss": 0.6161186695098877, "step": 174770 }, { "epoch": 1.038928616010129, "grad_norm": 1.4425685405731201, "learning_rate": 0.0001687349179318031, "loss": 0.5881834506988526, "step": 174780 }, { "epoch": 1.0389880580867974, "grad_norm": 1.5632226467132568, "learning_rate": 0.00016873020132207665, "loss": 0.5575368881225586, "step": 174790 }, { "epoch": 1.0390475001634658, "grad_norm": 1.6851197481155396, "learning_rate": 0.00016872548443140406, "loss": 0.5829651355743408, "step": 174800 }, { "epoch": 1.039106942240134, "grad_norm": 1.6261855363845825, "learning_rate": 0.00016872076725980799, "loss": 0.5906643390655517, "step": 174810 }, { "epoch": 1.0391663843168024, "grad_norm": 1.692832350730896, "learning_rate": 0.00016871604980731096, "loss": 0.564659309387207, "step": 174820 }, { "epoch": 1.0392258263934708, "grad_norm": 1.498847484588623, "learning_rate": 0.0001687113320739355, "loss": 0.6302779197692872, "step": 174830 }, { "epoch": 1.0392852684701392, "grad_norm": 1.6099461317062378, "learning_rate": 0.00016870661405970423, "loss": 0.5629914760589599, "step": 174840 }, { "epoch": 1.0393447105468077, "grad_norm": 1.3532500267028809, "learning_rate": 0.00016870189576463973, "loss": 0.5602700233459472, "step": 174850 }, { "epoch": 1.039404152623476, "grad_norm": 1.609369158744812, "learning_rate": 0.00016869717718876452, "loss": 0.5800163269042968, "step": 174860 }, { "epoch": 1.0394635947001445, "grad_norm": 1.619729995727539, "learning_rate": 0.0001686924583321012, "loss": 0.5895423889160156, "step": 174870 }, { "epoch": 1.039523036776813, "grad_norm": 1.678102731704712, "learning_rate": 0.00016868773919467234, "loss": 0.6121428966522217, "step": 174880 }, { "epoch": 1.0395824788534813, "grad_norm": 2.1562602519989014, "learning_rate": 0.00016868301977650052, "loss": 0.6507479190826416, "step": 174890 }, { "epoch": 1.0396419209301495, "grad_norm": 1.2231438159942627, "learning_rate": 0.0001686783000776083, "loss": 0.6449362754821777, "step": 174900 }, { "epoch": 1.039701363006818, "grad_norm": 1.7750799655914307, "learning_rate": 0.00016867358009801828, "loss": 0.6204952239990235, "step": 174910 }, { "epoch": 1.0397608050834863, "grad_norm": 1.7853046655654907, "learning_rate": 0.00016866885983775302, "loss": 0.6212390422821045, "step": 174920 }, { "epoch": 1.0398202471601548, "grad_norm": 1.3845608234405518, "learning_rate": 0.00016866413929683512, "loss": 0.5536124229431152, "step": 174930 }, { "epoch": 1.0398796892368232, "grad_norm": 1.7145967483520508, "learning_rate": 0.00016865941847528715, "loss": 0.6607865333557129, "step": 174940 }, { "epoch": 1.0399391313134916, "grad_norm": 1.452754020690918, "learning_rate": 0.00016865469737313164, "loss": 0.5824752807617187, "step": 174950 }, { "epoch": 1.03999857339016, "grad_norm": 1.6790841817855835, "learning_rate": 0.00016864997599039128, "loss": 0.6272212982177734, "step": 174960 }, { "epoch": 1.0400580154668284, "grad_norm": 1.343184232711792, "learning_rate": 0.00016864525432708861, "loss": 0.5870429992675781, "step": 174970 }, { "epoch": 1.0401174575434968, "grad_norm": 2.081761121749878, "learning_rate": 0.00016864053238324617, "loss": 0.6706701278686523, "step": 174980 }, { "epoch": 1.0401768996201652, "grad_norm": 1.283578634262085, "learning_rate": 0.00016863581015888663, "loss": 0.6685162544250488, "step": 174990 }, { "epoch": 1.0402363416968334, "grad_norm": 1.5545538663864136, "learning_rate": 0.0001686310876540325, "loss": 0.6645626544952392, "step": 175000 }, { "epoch": 1.0402957837735018, "grad_norm": 1.9028767347335815, "learning_rate": 0.0001686263648687064, "loss": 0.6552845954895019, "step": 175010 }, { "epoch": 1.0403552258501703, "grad_norm": 2.01255202293396, "learning_rate": 0.000168621641802931, "loss": 0.6618180274963379, "step": 175020 }, { "epoch": 1.0404146679268387, "grad_norm": 1.851688027381897, "learning_rate": 0.00016861691845672876, "loss": 0.593247365951538, "step": 175030 }, { "epoch": 1.040474110003507, "grad_norm": 1.350606083869934, "learning_rate": 0.00016861219483012234, "loss": 0.5886188507080078, "step": 175040 }, { "epoch": 1.0405335520801755, "grad_norm": 1.5805574655532837, "learning_rate": 0.00016860747092313437, "loss": 0.5802383422851562, "step": 175050 }, { "epoch": 1.040592994156844, "grad_norm": 1.3622279167175293, "learning_rate": 0.00016860274673578736, "loss": 0.5852249145507813, "step": 175060 }, { "epoch": 1.0406524362335123, "grad_norm": 1.3166524171829224, "learning_rate": 0.000168598022268104, "loss": 0.629452896118164, "step": 175070 }, { "epoch": 1.0407118783101807, "grad_norm": 1.5987162590026855, "learning_rate": 0.00016859329752010683, "loss": 0.6294193267822266, "step": 175080 }, { "epoch": 1.040771320386849, "grad_norm": 1.3907227516174316, "learning_rate": 0.0001685885724918185, "loss": 0.6320640087127686, "step": 175090 }, { "epoch": 1.0408307624635174, "grad_norm": 1.7749357223510742, "learning_rate": 0.00016858384718326157, "loss": 0.6111307144165039, "step": 175100 }, { "epoch": 1.0408902045401858, "grad_norm": 1.7900846004486084, "learning_rate": 0.00016857912159445865, "loss": 0.5866668701171875, "step": 175110 }, { "epoch": 1.0409496466168542, "grad_norm": 1.8581626415252686, "learning_rate": 0.00016857439572543238, "loss": 0.6008766651153564, "step": 175120 }, { "epoch": 1.0410090886935226, "grad_norm": 1.560447096824646, "learning_rate": 0.00016856966957620533, "loss": 0.6457481384277344, "step": 175130 }, { "epoch": 1.041068530770191, "grad_norm": 2.0416419506073, "learning_rate": 0.00016856494314680011, "loss": 0.6369203090667724, "step": 175140 }, { "epoch": 1.0411279728468594, "grad_norm": 1.6217195987701416, "learning_rate": 0.00016856021643723936, "loss": 0.6168620586395264, "step": 175150 }, { "epoch": 1.0411874149235278, "grad_norm": 1.6295709609985352, "learning_rate": 0.00016855548944754565, "loss": 0.6102675914764404, "step": 175160 }, { "epoch": 1.0412468570001963, "grad_norm": 1.703132152557373, "learning_rate": 0.00016855076217774163, "loss": 0.619974946975708, "step": 175170 }, { "epoch": 1.0413062990768645, "grad_norm": 1.395686149597168, "learning_rate": 0.0001685460346278499, "loss": 0.6495578289031982, "step": 175180 }, { "epoch": 1.0413657411535329, "grad_norm": 1.6423466205596924, "learning_rate": 0.00016854130679789308, "loss": 0.5671161651611328, "step": 175190 }, { "epoch": 1.0414251832302013, "grad_norm": 2.201047420501709, "learning_rate": 0.00016853657868789377, "loss": 0.631772804260254, "step": 175200 }, { "epoch": 1.0414846253068697, "grad_norm": 1.6335002183914185, "learning_rate": 0.0001685318502978746, "loss": 0.5958908557891845, "step": 175210 }, { "epoch": 1.041544067383538, "grad_norm": 1.8908579349517822, "learning_rate": 0.00016852712162785817, "loss": 0.6089991569519043, "step": 175220 }, { "epoch": 1.0416035094602065, "grad_norm": 1.5361833572387695, "learning_rate": 0.00016852239267786716, "loss": 0.6455368995666504, "step": 175230 }, { "epoch": 1.041662951536875, "grad_norm": 1.5321893692016602, "learning_rate": 0.0001685176634479241, "loss": 0.6159915924072266, "step": 175240 }, { "epoch": 1.0417223936135434, "grad_norm": 1.4791135787963867, "learning_rate": 0.0001685129339380517, "loss": 0.605094051361084, "step": 175250 }, { "epoch": 1.0417818356902118, "grad_norm": 1.5759505033493042, "learning_rate": 0.00016850820414827253, "loss": 0.5744775295257568, "step": 175260 }, { "epoch": 1.04184127776688, "grad_norm": 1.6829417943954468, "learning_rate": 0.00016850347407860924, "loss": 0.6490124702453614, "step": 175270 }, { "epoch": 1.0419007198435484, "grad_norm": 2.4294626712799072, "learning_rate": 0.00016849874372908442, "loss": 0.5967988014221192, "step": 175280 }, { "epoch": 1.0419601619202168, "grad_norm": 1.7404669523239136, "learning_rate": 0.00016849401309972076, "loss": 0.6385556697845459, "step": 175290 }, { "epoch": 1.0420196039968852, "grad_norm": 1.5810374021530151, "learning_rate": 0.00016848928219054086, "loss": 0.6717742919921875, "step": 175300 }, { "epoch": 1.0420790460735536, "grad_norm": 1.4626374244689941, "learning_rate": 0.00016848455100156734, "loss": 0.6332811832427978, "step": 175310 }, { "epoch": 1.042138488150222, "grad_norm": 2.1281349658966064, "learning_rate": 0.00016847981953282284, "loss": 0.614561939239502, "step": 175320 }, { "epoch": 1.0421979302268904, "grad_norm": 1.3843694925308228, "learning_rate": 0.00016847508778432998, "loss": 0.6296515941619873, "step": 175330 }, { "epoch": 1.0422573723035589, "grad_norm": 1.6897916793823242, "learning_rate": 0.0001684703557561114, "loss": 0.5866259574890137, "step": 175340 }, { "epoch": 1.0423168143802273, "grad_norm": 2.0275275707244873, "learning_rate": 0.00016846562344818977, "loss": 0.6686661720275879, "step": 175350 }, { "epoch": 1.0423762564568957, "grad_norm": 2.3948450088500977, "learning_rate": 0.00016846089086058772, "loss": 0.6496409893035888, "step": 175360 }, { "epoch": 1.0424356985335639, "grad_norm": 1.2459838390350342, "learning_rate": 0.00016845615799332785, "loss": 0.588559341430664, "step": 175370 }, { "epoch": 1.0424951406102323, "grad_norm": 1.4350827932357788, "learning_rate": 0.00016845142484643285, "loss": 0.6368906021118164, "step": 175380 }, { "epoch": 1.0425545826869007, "grad_norm": 1.6721992492675781, "learning_rate": 0.0001684466914199253, "loss": 0.6368471145629883, "step": 175390 }, { "epoch": 1.0426140247635691, "grad_norm": 1.555479645729065, "learning_rate": 0.00016844195771382786, "loss": 0.6225520133972168, "step": 175400 }, { "epoch": 1.0426734668402375, "grad_norm": 1.7214195728302002, "learning_rate": 0.00016843722372816323, "loss": 0.64589524269104, "step": 175410 }, { "epoch": 1.042732908916906, "grad_norm": 1.1284629106521606, "learning_rate": 0.00016843248946295402, "loss": 0.629426383972168, "step": 175420 }, { "epoch": 1.0427923509935744, "grad_norm": 1.0868639945983887, "learning_rate": 0.00016842775491822287, "loss": 0.6557411670684814, "step": 175430 }, { "epoch": 1.0428517930702428, "grad_norm": 1.4942137002944946, "learning_rate": 0.00016842302009399245, "loss": 0.6649835586547852, "step": 175440 }, { "epoch": 1.0429112351469112, "grad_norm": 1.3515839576721191, "learning_rate": 0.00016841828499028537, "loss": 0.6395059585571289, "step": 175450 }, { "epoch": 1.0429706772235794, "grad_norm": 1.9859923124313354, "learning_rate": 0.0001684135496071243, "loss": 0.6482347011566162, "step": 175460 }, { "epoch": 1.0430301193002478, "grad_norm": 1.7022266387939453, "learning_rate": 0.00016840881394453194, "loss": 0.6444834709167481, "step": 175470 }, { "epoch": 1.0430895613769162, "grad_norm": 1.8552290201187134, "learning_rate": 0.00016840407800253088, "loss": 0.6704982280731201, "step": 175480 }, { "epoch": 1.0431490034535846, "grad_norm": 1.4830143451690674, "learning_rate": 0.0001683993417811438, "loss": 0.6402508735656738, "step": 175490 }, { "epoch": 1.043208445530253, "grad_norm": 1.4332104921340942, "learning_rate": 0.0001683946052803933, "loss": 0.6553906440734864, "step": 175500 }, { "epoch": 1.0432678876069215, "grad_norm": 1.3320387601852417, "learning_rate": 0.00016838986850030218, "loss": 0.629841947555542, "step": 175510 }, { "epoch": 1.0433273296835899, "grad_norm": 2.0714499950408936, "learning_rate": 0.00016838513144089298, "loss": 0.6353005409240723, "step": 175520 }, { "epoch": 1.0433867717602583, "grad_norm": 1.6132888793945312, "learning_rate": 0.00016838039410218837, "loss": 0.5523182868957519, "step": 175530 }, { "epoch": 1.0434462138369267, "grad_norm": 1.6536400318145752, "learning_rate": 0.00016837565648421105, "loss": 0.5875091552734375, "step": 175540 }, { "epoch": 1.043505655913595, "grad_norm": 2.5255701541900635, "learning_rate": 0.00016837091858698365, "loss": 0.6578594207763672, "step": 175550 }, { "epoch": 1.0435650979902633, "grad_norm": 1.3646215200424194, "learning_rate": 0.00016836618041052886, "loss": 0.6350231170654297, "step": 175560 }, { "epoch": 1.0436245400669317, "grad_norm": 1.4841638803482056, "learning_rate": 0.00016836144195486936, "loss": 0.6039738655090332, "step": 175570 }, { "epoch": 1.0436839821436001, "grad_norm": 1.702754259109497, "learning_rate": 0.0001683567032200278, "loss": 0.6312685489654541, "step": 175580 }, { "epoch": 1.0437434242202686, "grad_norm": 1.646828532218933, "learning_rate": 0.0001683519642060268, "loss": 0.5736436367034912, "step": 175590 }, { "epoch": 1.043802866296937, "grad_norm": 1.7352179288864136, "learning_rate": 0.0001683472249128891, "loss": 0.6405405044555664, "step": 175600 }, { "epoch": 1.0438623083736054, "grad_norm": 1.618039608001709, "learning_rate": 0.00016834248534063732, "loss": 0.6163599967956543, "step": 175610 }, { "epoch": 1.0439217504502738, "grad_norm": 1.598656415939331, "learning_rate": 0.0001683377454892942, "loss": 0.6210526466369629, "step": 175620 }, { "epoch": 1.0439811925269422, "grad_norm": 1.3802204132080078, "learning_rate": 0.0001683330053588823, "loss": 0.585530948638916, "step": 175630 }, { "epoch": 1.0440406346036104, "grad_norm": 1.7055813074111938, "learning_rate": 0.00016832826494942444, "loss": 0.6435420989990235, "step": 175640 }, { "epoch": 1.0441000766802788, "grad_norm": 1.2896111011505127, "learning_rate": 0.0001683235242609432, "loss": 0.6128707885742187, "step": 175650 }, { "epoch": 1.0441595187569472, "grad_norm": 1.8514924049377441, "learning_rate": 0.00016831878329346127, "loss": 0.6024988174438477, "step": 175660 }, { "epoch": 1.0442189608336157, "grad_norm": 1.4411684274673462, "learning_rate": 0.00016831404204700135, "loss": 0.6284219741821289, "step": 175670 }, { "epoch": 1.044278402910284, "grad_norm": 1.4462432861328125, "learning_rate": 0.00016830930052158608, "loss": 0.6292383193969726, "step": 175680 }, { "epoch": 1.0443378449869525, "grad_norm": 1.4542632102966309, "learning_rate": 0.0001683045587172382, "loss": 0.6325802326202392, "step": 175690 }, { "epoch": 1.044397287063621, "grad_norm": 1.9802496433258057, "learning_rate": 0.00016829981663398036, "loss": 0.6086616516113281, "step": 175700 }, { "epoch": 1.0444567291402893, "grad_norm": 1.7519596815109253, "learning_rate": 0.00016829507427183526, "loss": 0.6011909484863281, "step": 175710 }, { "epoch": 1.0445161712169577, "grad_norm": 1.9184879064559937, "learning_rate": 0.00016829033163082556, "loss": 0.6178399085998535, "step": 175720 }, { "epoch": 1.0445756132936261, "grad_norm": 1.4322113990783691, "learning_rate": 0.00016828558871097396, "loss": 0.6240191459655762, "step": 175730 }, { "epoch": 1.0446350553702943, "grad_norm": 1.5224673748016357, "learning_rate": 0.00016828084551230316, "loss": 0.6571496009826661, "step": 175740 }, { "epoch": 1.0446944974469627, "grad_norm": 1.3453248739242554, "learning_rate": 0.00016827610203483585, "loss": 0.608222770690918, "step": 175750 }, { "epoch": 1.0447539395236312, "grad_norm": 1.6509480476379395, "learning_rate": 0.00016827135827859467, "loss": 0.7056876659393311, "step": 175760 }, { "epoch": 1.0448133816002996, "grad_norm": 1.954376220703125, "learning_rate": 0.0001682666142436024, "loss": 0.6532135009765625, "step": 175770 }, { "epoch": 1.044872823676968, "grad_norm": 1.5597987174987793, "learning_rate": 0.0001682618699298817, "loss": 0.6179564476013184, "step": 175780 }, { "epoch": 1.0449322657536364, "grad_norm": 1.251407265663147, "learning_rate": 0.00016825712533745523, "loss": 0.5978206634521485, "step": 175790 }, { "epoch": 1.0449917078303048, "grad_norm": 1.4986292123794556, "learning_rate": 0.00016825238046634574, "loss": 0.6272945404052734, "step": 175800 }, { "epoch": 1.0450511499069732, "grad_norm": 1.7412102222442627, "learning_rate": 0.00016824763531657585, "loss": 0.6763229846954346, "step": 175810 }, { "epoch": 1.0451105919836416, "grad_norm": 1.5681341886520386, "learning_rate": 0.00016824288988816834, "loss": 0.6425287246704101, "step": 175820 }, { "epoch": 1.0451700340603098, "grad_norm": 1.0946236848831177, "learning_rate": 0.00016823814418114586, "loss": 0.548165225982666, "step": 175830 }, { "epoch": 1.0452294761369783, "grad_norm": 1.4466838836669922, "learning_rate": 0.00016823339819553115, "loss": 0.6175619602203369, "step": 175840 }, { "epoch": 1.0452889182136467, "grad_norm": 1.2560796737670898, "learning_rate": 0.00016822865193134688, "loss": 0.6220391273498536, "step": 175850 }, { "epoch": 1.045348360290315, "grad_norm": 1.176972508430481, "learning_rate": 0.00016822390538861576, "loss": 0.6194144248962402, "step": 175860 }, { "epoch": 1.0454078023669835, "grad_norm": 1.6187201738357544, "learning_rate": 0.00016821915856736052, "loss": 0.5921988487243652, "step": 175870 }, { "epoch": 1.045467244443652, "grad_norm": 1.3720015287399292, "learning_rate": 0.00016821441146760386, "loss": 0.5755189895629883, "step": 175880 }, { "epoch": 1.0455266865203203, "grad_norm": 1.4898349046707153, "learning_rate": 0.00016820966408936846, "loss": 0.674859619140625, "step": 175890 }, { "epoch": 1.0455861285969887, "grad_norm": 1.6905790567398071, "learning_rate": 0.00016820491643267706, "loss": 0.6603455066680908, "step": 175900 }, { "epoch": 1.0456455706736572, "grad_norm": 2.044426918029785, "learning_rate": 0.00016820016849755236, "loss": 0.5973919868469239, "step": 175910 }, { "epoch": 1.0457050127503253, "grad_norm": 1.811161756515503, "learning_rate": 0.00016819542028401706, "loss": 0.6547687530517579, "step": 175920 }, { "epoch": 1.0457644548269938, "grad_norm": 1.6626627445220947, "learning_rate": 0.0001681906717920939, "loss": 0.6488306045532226, "step": 175930 }, { "epoch": 1.0458238969036622, "grad_norm": 1.7432752847671509, "learning_rate": 0.0001681859230218056, "loss": 0.6346665382385254, "step": 175940 }, { "epoch": 1.0458833389803306, "grad_norm": 1.4325443506240845, "learning_rate": 0.00016818117397317486, "loss": 0.667595386505127, "step": 175950 }, { "epoch": 1.045942781056999, "grad_norm": 2.031049966812134, "learning_rate": 0.00016817642464622438, "loss": 0.5916065216064453, "step": 175960 }, { "epoch": 1.0460022231336674, "grad_norm": 1.293725609779358, "learning_rate": 0.00016817167504097692, "loss": 0.5761762619018554, "step": 175970 }, { "epoch": 1.0460616652103358, "grad_norm": 1.8749216794967651, "learning_rate": 0.00016816692515745512, "loss": 0.6904094696044922, "step": 175980 }, { "epoch": 1.0461211072870042, "grad_norm": 1.6655815839767456, "learning_rate": 0.0001681621749956818, "loss": 0.6438873291015625, "step": 175990 }, { "epoch": 1.0461805493636727, "grad_norm": 1.3343724012374878, "learning_rate": 0.00016815742455567964, "loss": 0.6232846260070801, "step": 176000 }, { "epoch": 1.0462399914403409, "grad_norm": 1.9431653022766113, "learning_rate": 0.00016815267383747136, "loss": 0.5985662937164307, "step": 176010 }, { "epoch": 1.0462994335170093, "grad_norm": 2.2710423469543457, "learning_rate": 0.0001681479228410797, "loss": 0.6431523323059082, "step": 176020 }, { "epoch": 1.0463588755936777, "grad_norm": 1.508882761001587, "learning_rate": 0.0001681431715665274, "loss": 0.5945365905761719, "step": 176030 }, { "epoch": 1.046418317670346, "grad_norm": 1.5176067352294922, "learning_rate": 0.00016813842001383713, "loss": 0.6424303531646729, "step": 176040 }, { "epoch": 1.0464777597470145, "grad_norm": 1.724413275718689, "learning_rate": 0.00016813366818303166, "loss": 0.6051277160644531, "step": 176050 }, { "epoch": 1.046537201823683, "grad_norm": 1.4722895622253418, "learning_rate": 0.00016812891607413376, "loss": 0.5762066841125488, "step": 176060 }, { "epoch": 1.0465966439003513, "grad_norm": 2.0745222568511963, "learning_rate": 0.00016812416368716608, "loss": 0.6372232437133789, "step": 176070 }, { "epoch": 1.0466560859770198, "grad_norm": 1.8023128509521484, "learning_rate": 0.0001681194110221514, "loss": 0.6377472400665283, "step": 176080 }, { "epoch": 1.0467155280536882, "grad_norm": 1.344623327255249, "learning_rate": 0.00016811465807911247, "loss": 0.6189091205596924, "step": 176090 }, { "epoch": 1.0467749701303566, "grad_norm": 1.5808106660842896, "learning_rate": 0.00016810990485807204, "loss": 0.576693058013916, "step": 176100 }, { "epoch": 1.0468344122070248, "grad_norm": 1.5970133543014526, "learning_rate": 0.00016810515135905275, "loss": 0.6111452102661132, "step": 176110 }, { "epoch": 1.0468938542836932, "grad_norm": 1.3488428592681885, "learning_rate": 0.00016810039758207744, "loss": 0.5873950958251953, "step": 176120 }, { "epoch": 1.0469532963603616, "grad_norm": 1.5443265438079834, "learning_rate": 0.00016809564352716883, "loss": 0.5913155555725098, "step": 176130 }, { "epoch": 1.04701273843703, "grad_norm": 2.0307793617248535, "learning_rate": 0.0001680908891943496, "loss": 0.6344996929168701, "step": 176140 }, { "epoch": 1.0470721805136984, "grad_norm": 1.4060583114624023, "learning_rate": 0.0001680861345836426, "loss": 0.6309659957885743, "step": 176150 }, { "epoch": 1.0471316225903669, "grad_norm": 2.058852195739746, "learning_rate": 0.00016808137969507043, "loss": 0.626523780822754, "step": 176160 }, { "epoch": 1.0471910646670353, "grad_norm": 1.4009894132614136, "learning_rate": 0.00016807662452865597, "loss": 0.5910892963409424, "step": 176170 }, { "epoch": 1.0472505067437037, "grad_norm": 1.495040774345398, "learning_rate": 0.00016807186908442194, "loss": 0.5714579582214355, "step": 176180 }, { "epoch": 1.047309948820372, "grad_norm": 1.4837011098861694, "learning_rate": 0.00016806711336239102, "loss": 0.6182693481445313, "step": 176190 }, { "epoch": 1.0473693908970403, "grad_norm": 2.0088021755218506, "learning_rate": 0.00016806235736258605, "loss": 0.6492095947265625, "step": 176200 }, { "epoch": 1.0474288329737087, "grad_norm": 1.859703779220581, "learning_rate": 0.00016805760108502973, "loss": 0.6132250785827636, "step": 176210 }, { "epoch": 1.0474882750503771, "grad_norm": 2.1031532287597656, "learning_rate": 0.0001680528445297448, "loss": 0.6731500625610352, "step": 176220 }, { "epoch": 1.0475477171270455, "grad_norm": 1.8833423852920532, "learning_rate": 0.00016804808769675406, "loss": 0.5737546920776367, "step": 176230 }, { "epoch": 1.047607159203714, "grad_norm": 1.2836350202560425, "learning_rate": 0.00016804333058608023, "loss": 0.5959503173828125, "step": 176240 }, { "epoch": 1.0476666012803824, "grad_norm": 1.3003644943237305, "learning_rate": 0.00016803857319774604, "loss": 0.6000396728515625, "step": 176250 }, { "epoch": 1.0477260433570508, "grad_norm": 1.6794003248214722, "learning_rate": 0.00016803381553177432, "loss": 0.7711552619934082, "step": 176260 }, { "epoch": 1.0477854854337192, "grad_norm": 1.449515461921692, "learning_rate": 0.00016802905758818776, "loss": 0.6620201110839844, "step": 176270 }, { "epoch": 1.0478449275103876, "grad_norm": 1.867676019668579, "learning_rate": 0.0001680242993670092, "loss": 0.6547659873962403, "step": 176280 }, { "epoch": 1.0479043695870558, "grad_norm": 1.5473557710647583, "learning_rate": 0.00016801954086826136, "loss": 0.6525284767150878, "step": 176290 }, { "epoch": 1.0479638116637242, "grad_norm": 1.4064104557037354, "learning_rate": 0.00016801478209196692, "loss": 0.6475759029388428, "step": 176300 }, { "epoch": 1.0480232537403926, "grad_norm": 1.39295494556427, "learning_rate": 0.00016801002303814877, "loss": 0.5351336479187012, "step": 176310 }, { "epoch": 1.048082695817061, "grad_norm": 1.466567039489746, "learning_rate": 0.00016800526370682966, "loss": 0.609010887145996, "step": 176320 }, { "epoch": 1.0481421378937295, "grad_norm": 1.3542630672454834, "learning_rate": 0.00016800050409803224, "loss": 0.6064284324645997, "step": 176330 }, { "epoch": 1.0482015799703979, "grad_norm": 1.606980323791504, "learning_rate": 0.00016799574421177946, "loss": 0.6191967010498047, "step": 176340 }, { "epoch": 1.0482610220470663, "grad_norm": 1.4066296815872192, "learning_rate": 0.00016799098404809393, "loss": 0.6264640331268311, "step": 176350 }, { "epoch": 1.0483204641237347, "grad_norm": 1.5757147073745728, "learning_rate": 0.00016798622360699852, "loss": 0.6477330207824707, "step": 176360 }, { "epoch": 1.0483799062004031, "grad_norm": 1.4676989316940308, "learning_rate": 0.00016798146288851592, "loss": 0.6103974342346191, "step": 176370 }, { "epoch": 1.0484393482770713, "grad_norm": 1.5311256647109985, "learning_rate": 0.00016797670189266898, "loss": 0.5947818756103516, "step": 176380 }, { "epoch": 1.0484987903537397, "grad_norm": 1.5061808824539185, "learning_rate": 0.00016797194061948044, "loss": 0.6355465412139892, "step": 176390 }, { "epoch": 1.0485582324304081, "grad_norm": 1.219773292541504, "learning_rate": 0.0001679671790689731, "loss": 0.6201217651367188, "step": 176400 }, { "epoch": 1.0486176745070765, "grad_norm": 1.7221711874008179, "learning_rate": 0.0001679624172411697, "loss": 0.6631082534790039, "step": 176410 }, { "epoch": 1.048677116583745, "grad_norm": 1.6046706438064575, "learning_rate": 0.00016795765513609302, "loss": 0.5872309684753418, "step": 176420 }, { "epoch": 1.0487365586604134, "grad_norm": 1.7117410898208618, "learning_rate": 0.0001679528927537659, "loss": 0.6129497528076172, "step": 176430 }, { "epoch": 1.0487960007370818, "grad_norm": 1.7800031900405884, "learning_rate": 0.00016794813009421108, "loss": 0.6370577812194824, "step": 176440 }, { "epoch": 1.0488554428137502, "grad_norm": 1.8037207126617432, "learning_rate": 0.00016794336715745132, "loss": 0.6216285705566407, "step": 176450 }, { "epoch": 1.0489148848904186, "grad_norm": 2.2205235958099365, "learning_rate": 0.00016793860394350942, "loss": 0.6362551689147949, "step": 176460 }, { "epoch": 1.048974326967087, "grad_norm": 1.8328399658203125, "learning_rate": 0.00016793384045240818, "loss": 0.6456533432006836, "step": 176470 }, { "epoch": 1.0490337690437552, "grad_norm": 1.6804770231246948, "learning_rate": 0.0001679290766841704, "loss": 0.6385827541351319, "step": 176480 }, { "epoch": 1.0490932111204236, "grad_norm": 1.1165980100631714, "learning_rate": 0.00016792431263881882, "loss": 0.5814935684204101, "step": 176490 }, { "epoch": 1.049152653197092, "grad_norm": 1.7843291759490967, "learning_rate": 0.00016791954831637626, "loss": 0.6165340900421142, "step": 176500 }, { "epoch": 1.0492120952737605, "grad_norm": 1.7260984182357788, "learning_rate": 0.00016791478371686554, "loss": 0.6706007480621338, "step": 176510 }, { "epoch": 1.0492715373504289, "grad_norm": 1.3924428224563599, "learning_rate": 0.00016791001884030942, "loss": 0.5965004920959472, "step": 176520 }, { "epoch": 1.0493309794270973, "grad_norm": 1.7847663164138794, "learning_rate": 0.00016790525368673065, "loss": 0.6847854137420655, "step": 176530 }, { "epoch": 1.0493904215037657, "grad_norm": 1.6656776666641235, "learning_rate": 0.0001679004882561521, "loss": 0.6145910263061524, "step": 176540 }, { "epoch": 1.0494498635804341, "grad_norm": 1.8424395322799683, "learning_rate": 0.00016789572254859655, "loss": 0.6942413330078125, "step": 176550 }, { "epoch": 1.0495093056571025, "grad_norm": 1.7954171895980835, "learning_rate": 0.00016789095656408672, "loss": 0.6927406311035156, "step": 176560 }, { "epoch": 1.0495687477337707, "grad_norm": 1.6068452596664429, "learning_rate": 0.00016788619030264556, "loss": 0.630799388885498, "step": 176570 }, { "epoch": 1.0496281898104391, "grad_norm": 1.747393250465393, "learning_rate": 0.00016788142376429575, "loss": 0.6492484092712403, "step": 176580 }, { "epoch": 1.0496876318871076, "grad_norm": 2.0247604846954346, "learning_rate": 0.00016787665694906008, "loss": 0.6263018131256104, "step": 176590 }, { "epoch": 1.049747073963776, "grad_norm": 1.3444604873657227, "learning_rate": 0.00016787188985696147, "loss": 0.620035457611084, "step": 176600 }, { "epoch": 1.0498065160404444, "grad_norm": 2.0338122844696045, "learning_rate": 0.0001678671224880226, "loss": 0.6585973739624024, "step": 176610 }, { "epoch": 1.0498659581171128, "grad_norm": 1.809522271156311, "learning_rate": 0.00016786235484226637, "loss": 0.6217743873596191, "step": 176620 }, { "epoch": 1.0499254001937812, "grad_norm": 1.8187940120697021, "learning_rate": 0.00016785758691971548, "loss": 0.6414265632629395, "step": 176630 }, { "epoch": 1.0499848422704496, "grad_norm": 1.8850880861282349, "learning_rate": 0.00016785281872039288, "loss": 0.6654744148254395, "step": 176640 }, { "epoch": 1.050044284347118, "grad_norm": 1.7469607591629028, "learning_rate": 0.00016784805024432125, "loss": 0.5496901035308838, "step": 176650 }, { "epoch": 1.0501037264237862, "grad_norm": 2.0490269660949707, "learning_rate": 0.00016784328149152346, "loss": 0.6089648723602294, "step": 176660 }, { "epoch": 1.0501631685004547, "grad_norm": 2.077698230743408, "learning_rate": 0.00016783851246202232, "loss": 0.6730508804321289, "step": 176670 }, { "epoch": 1.050222610577123, "grad_norm": 1.414971113204956, "learning_rate": 0.00016783374315584065, "loss": 0.5649579524993896, "step": 176680 }, { "epoch": 1.0502820526537915, "grad_norm": 2.087883710861206, "learning_rate": 0.0001678289735730012, "loss": 0.6106221199035644, "step": 176690 }, { "epoch": 1.05034149473046, "grad_norm": 1.783219337463379, "learning_rate": 0.0001678242037135269, "loss": 0.6253278732299805, "step": 176700 }, { "epoch": 1.0504009368071283, "grad_norm": 1.8622972965240479, "learning_rate": 0.00016781943357744048, "loss": 0.636487340927124, "step": 176710 }, { "epoch": 1.0504603788837967, "grad_norm": 1.824618935585022, "learning_rate": 0.0001678146631647648, "loss": 0.5924751281738281, "step": 176720 }, { "epoch": 1.0505198209604651, "grad_norm": 1.0576646327972412, "learning_rate": 0.00016780989247552268, "loss": 0.5886845588684082, "step": 176730 }, { "epoch": 1.0505792630371336, "grad_norm": 1.5613425970077515, "learning_rate": 0.00016780512150973688, "loss": 0.5793929100036621, "step": 176740 }, { "epoch": 1.0506387051138018, "grad_norm": 2.2101404666900635, "learning_rate": 0.0001678003502674303, "loss": 0.6320045471191407, "step": 176750 }, { "epoch": 1.0506981471904702, "grad_norm": 2.0447752475738525, "learning_rate": 0.00016779557874862573, "loss": 0.6838998794555664, "step": 176760 }, { "epoch": 1.0507575892671386, "grad_norm": 1.911801815032959, "learning_rate": 0.000167790806953346, "loss": 0.7012411117553711, "step": 176770 }, { "epoch": 1.050817031343807, "grad_norm": 1.9662458896636963, "learning_rate": 0.0001677860348816139, "loss": 0.6541873455047608, "step": 176780 }, { "epoch": 1.0508764734204754, "grad_norm": 1.7534540891647339, "learning_rate": 0.00016778126253345235, "loss": 0.5682360649108886, "step": 176790 }, { "epoch": 1.0509359154971438, "grad_norm": 1.6291635036468506, "learning_rate": 0.0001677764899088841, "loss": 0.5688477993011475, "step": 176800 }, { "epoch": 1.0509953575738122, "grad_norm": 1.5095345973968506, "learning_rate": 0.00016777171700793202, "loss": 0.5994890213012696, "step": 176810 }, { "epoch": 1.0510547996504807, "grad_norm": 1.7368963956832886, "learning_rate": 0.0001677669438306189, "loss": 0.6464564323425293, "step": 176820 }, { "epoch": 1.051114241727149, "grad_norm": 1.7007931470870972, "learning_rate": 0.00016776217037696762, "loss": 0.6658021926879882, "step": 176830 }, { "epoch": 1.0511736838038175, "grad_norm": 1.5340641736984253, "learning_rate": 0.00016775739664700096, "loss": 0.6110664367675781, "step": 176840 }, { "epoch": 1.0512331258804857, "grad_norm": 1.5764585733413696, "learning_rate": 0.00016775262264074182, "loss": 0.622102689743042, "step": 176850 }, { "epoch": 1.051292567957154, "grad_norm": 1.4371916055679321, "learning_rate": 0.000167747848358213, "loss": 0.6554432868957519, "step": 176860 }, { "epoch": 1.0513520100338225, "grad_norm": 1.6404743194580078, "learning_rate": 0.00016774307379943736, "loss": 0.6614663124084472, "step": 176870 }, { "epoch": 1.051411452110491, "grad_norm": 1.5801317691802979, "learning_rate": 0.0001677382989644377, "loss": 0.6310691833496094, "step": 176880 }, { "epoch": 1.0514708941871593, "grad_norm": 1.5837684869766235, "learning_rate": 0.00016773352385323687, "loss": 0.6018136024475098, "step": 176890 }, { "epoch": 1.0515303362638277, "grad_norm": 1.7377985715866089, "learning_rate": 0.0001677287484658578, "loss": 0.611642599105835, "step": 176900 }, { "epoch": 1.0515897783404962, "grad_norm": 1.869268536567688, "learning_rate": 0.0001677239728023232, "loss": 0.6306753158569336, "step": 176910 }, { "epoch": 1.0516492204171646, "grad_norm": 1.6668201684951782, "learning_rate": 0.000167719196862656, "loss": 0.6415203094482422, "step": 176920 }, { "epoch": 1.051708662493833, "grad_norm": 1.5233392715454102, "learning_rate": 0.00016771442064687902, "loss": 0.6380234718322754, "step": 176930 }, { "epoch": 1.0517681045705012, "grad_norm": 1.609246015548706, "learning_rate": 0.0001677096441550151, "loss": 0.6612100601196289, "step": 176940 }, { "epoch": 1.0518275466471696, "grad_norm": 1.5404469966888428, "learning_rate": 0.00016770486738708712, "loss": 0.6269269943237304, "step": 176950 }, { "epoch": 1.051886988723838, "grad_norm": 1.4998699426651, "learning_rate": 0.0001677000903431179, "loss": 0.5876312255859375, "step": 176960 }, { "epoch": 1.0519464308005064, "grad_norm": 1.4313865900039673, "learning_rate": 0.00016769531302313032, "loss": 0.6494430541992188, "step": 176970 }, { "epoch": 1.0520058728771748, "grad_norm": 1.5743809938430786, "learning_rate": 0.00016769053542714724, "loss": 0.5989672183990479, "step": 176980 }, { "epoch": 1.0520653149538433, "grad_norm": 1.8988417387008667, "learning_rate": 0.00016768575755519145, "loss": 0.6645776748657226, "step": 176990 }, { "epoch": 1.0521247570305117, "grad_norm": 1.2050336599349976, "learning_rate": 0.00016768097940728587, "loss": 0.6005749702453613, "step": 177000 }, { "epoch": 1.05218419910718, "grad_norm": 1.607330322265625, "learning_rate": 0.0001676762009834533, "loss": 0.621097469329834, "step": 177010 }, { "epoch": 1.0522436411838485, "grad_norm": 1.5004669427871704, "learning_rate": 0.0001676714222837167, "loss": 0.6229389190673829, "step": 177020 }, { "epoch": 1.0523030832605167, "grad_norm": 1.681368350982666, "learning_rate": 0.00016766664330809884, "loss": 0.6680724143981933, "step": 177030 }, { "epoch": 1.052362525337185, "grad_norm": 1.6047346591949463, "learning_rate": 0.00016766186405662255, "loss": 0.6506304740905762, "step": 177040 }, { "epoch": 1.0524219674138535, "grad_norm": 1.7176698446273804, "learning_rate": 0.00016765708452931078, "loss": 0.6567461013793945, "step": 177050 }, { "epoch": 1.052481409490522, "grad_norm": 2.2080869674682617, "learning_rate": 0.00016765230472618638, "loss": 0.6259572505950928, "step": 177060 }, { "epoch": 1.0525408515671903, "grad_norm": 1.6772576570510864, "learning_rate": 0.00016764752464727218, "loss": 0.6184188842773437, "step": 177070 }, { "epoch": 1.0526002936438588, "grad_norm": 1.7125543355941772, "learning_rate": 0.00016764274429259107, "loss": 0.6255931854248047, "step": 177080 }, { "epoch": 1.0526597357205272, "grad_norm": 1.4332025051116943, "learning_rate": 0.00016763796366216587, "loss": 0.5856451034545899, "step": 177090 }, { "epoch": 1.0527191777971956, "grad_norm": 1.3362493515014648, "learning_rate": 0.00016763318275601953, "loss": 0.6029976844787598, "step": 177100 }, { "epoch": 1.052778619873864, "grad_norm": 1.4259092807769775, "learning_rate": 0.0001676284015741749, "loss": 0.6486715793609619, "step": 177110 }, { "epoch": 1.0528380619505322, "grad_norm": 1.8214763402938843, "learning_rate": 0.00016762362011665477, "loss": 0.6939301490783691, "step": 177120 }, { "epoch": 1.0528975040272006, "grad_norm": 1.9560242891311646, "learning_rate": 0.0001676188383834821, "loss": 0.6183197975158692, "step": 177130 }, { "epoch": 1.052956946103869, "grad_norm": 1.7924754619598389, "learning_rate": 0.00016761405637467976, "loss": 0.6451664924621582, "step": 177140 }, { "epoch": 1.0530163881805374, "grad_norm": 1.5653698444366455, "learning_rate": 0.00016760927409027057, "loss": 0.6005431652069092, "step": 177150 }, { "epoch": 1.0530758302572059, "grad_norm": 1.424512505531311, "learning_rate": 0.00016760449153027743, "loss": 0.6837769031524659, "step": 177160 }, { "epoch": 1.0531352723338743, "grad_norm": 1.3406708240509033, "learning_rate": 0.00016759970869472326, "loss": 0.6881136417388916, "step": 177170 }, { "epoch": 1.0531947144105427, "grad_norm": 1.5643842220306396, "learning_rate": 0.00016759492558363087, "loss": 0.6240240097045898, "step": 177180 }, { "epoch": 1.053254156487211, "grad_norm": 1.6538573503494263, "learning_rate": 0.0001675901421970232, "loss": 0.5552488327026367, "step": 177190 }, { "epoch": 1.0533135985638795, "grad_norm": 1.3065855503082275, "learning_rate": 0.00016758535853492315, "loss": 0.6041993618011474, "step": 177200 }, { "epoch": 1.053373040640548, "grad_norm": 1.6055759191513062, "learning_rate": 0.0001675805745973535, "loss": 0.6131617546081543, "step": 177210 }, { "epoch": 1.0534324827172161, "grad_norm": 1.4951276779174805, "learning_rate": 0.00016757579038433724, "loss": 0.6410621643066406, "step": 177220 }, { "epoch": 1.0534919247938845, "grad_norm": 1.5212337970733643, "learning_rate": 0.0001675710058958972, "loss": 0.6354889869689941, "step": 177230 }, { "epoch": 1.053551366870553, "grad_norm": 1.5510390996932983, "learning_rate": 0.0001675662211320563, "loss": 0.5919625759124756, "step": 177240 }, { "epoch": 1.0536108089472214, "grad_norm": 1.6508429050445557, "learning_rate": 0.00016756143609283737, "loss": 0.6438965797424316, "step": 177250 }, { "epoch": 1.0536702510238898, "grad_norm": 1.659050464630127, "learning_rate": 0.00016755665077826338, "loss": 0.6518525123596192, "step": 177260 }, { "epoch": 1.0537296931005582, "grad_norm": 1.483917474746704, "learning_rate": 0.00016755186518835718, "loss": 0.5702754974365234, "step": 177270 }, { "epoch": 1.0537891351772266, "grad_norm": 1.6094310283660889, "learning_rate": 0.00016754707932314163, "loss": 0.6283649444580078, "step": 177280 }, { "epoch": 1.053848577253895, "grad_norm": 1.3323768377304077, "learning_rate": 0.00016754229318263967, "loss": 0.5803257465362549, "step": 177290 }, { "epoch": 1.0539080193305634, "grad_norm": 1.7653965950012207, "learning_rate": 0.0001675375067668742, "loss": 0.623645544052124, "step": 177300 }, { "epoch": 1.0539674614072316, "grad_norm": 1.3628225326538086, "learning_rate": 0.00016753272007586812, "loss": 0.6261761665344239, "step": 177310 }, { "epoch": 1.0540269034839, "grad_norm": 1.890236496925354, "learning_rate": 0.0001675279331096443, "loss": 0.6505084037780762, "step": 177320 }, { "epoch": 1.0540863455605685, "grad_norm": 1.7990591526031494, "learning_rate": 0.0001675231458682256, "loss": 0.5941591262817383, "step": 177330 }, { "epoch": 1.0541457876372369, "grad_norm": 1.6002384424209595, "learning_rate": 0.000167518358351635, "loss": 0.6109916687011718, "step": 177340 }, { "epoch": 1.0542052297139053, "grad_norm": 1.9698646068572998, "learning_rate": 0.00016751357055989538, "loss": 0.6727021694183349, "step": 177350 }, { "epoch": 1.0542646717905737, "grad_norm": 1.7157166004180908, "learning_rate": 0.00016750878249302962, "loss": 0.6154112815856934, "step": 177360 }, { "epoch": 1.0543241138672421, "grad_norm": 1.677117109298706, "learning_rate": 0.00016750399415106065, "loss": 0.6704831123352051, "step": 177370 }, { "epoch": 1.0543835559439105, "grad_norm": 1.6161361932754517, "learning_rate": 0.00016749920553401138, "loss": 0.6549699306488037, "step": 177380 }, { "epoch": 1.054442998020579, "grad_norm": 1.611506700515747, "learning_rate": 0.00016749441664190467, "loss": 0.6397864341735839, "step": 177390 }, { "epoch": 1.0545024400972471, "grad_norm": 1.4132964611053467, "learning_rate": 0.0001674896274747635, "loss": 0.6483449935913086, "step": 177400 }, { "epoch": 1.0545618821739156, "grad_norm": 1.5000156164169312, "learning_rate": 0.00016748483803261067, "loss": 0.6032501220703125, "step": 177410 }, { "epoch": 1.054621324250584, "grad_norm": 1.6633350849151611, "learning_rate": 0.00016748004831546924, "loss": 0.6512058258056641, "step": 177420 }, { "epoch": 1.0546807663272524, "grad_norm": 1.420316219329834, "learning_rate": 0.000167475258323362, "loss": 0.5982145309448242, "step": 177430 }, { "epoch": 1.0547402084039208, "grad_norm": 1.652206540107727, "learning_rate": 0.00016747046805631194, "loss": 0.6467815399169922, "step": 177440 }, { "epoch": 1.0547996504805892, "grad_norm": 2.233809232711792, "learning_rate": 0.00016746567751434188, "loss": 0.6604985237121582, "step": 177450 }, { "epoch": 1.0548590925572576, "grad_norm": 1.483469009399414, "learning_rate": 0.00016746088669747483, "loss": 0.621941089630127, "step": 177460 }, { "epoch": 1.054918534633926, "grad_norm": 1.6308116912841797, "learning_rate": 0.0001674560956057337, "loss": 0.6186923980712891, "step": 177470 }, { "epoch": 1.0549779767105945, "grad_norm": 2.0606048107147217, "learning_rate": 0.00016745130423914136, "loss": 0.6271486759185791, "step": 177480 }, { "epoch": 1.0550374187872626, "grad_norm": 1.6061874628067017, "learning_rate": 0.00016744651259772078, "loss": 0.6108718872070312, "step": 177490 }, { "epoch": 1.055096860863931, "grad_norm": 1.3147915601730347, "learning_rate": 0.00016744172068149484, "loss": 0.6069021701812745, "step": 177500 }, { "epoch": 1.0551563029405995, "grad_norm": 1.7941735982894897, "learning_rate": 0.00016743692849048648, "loss": 0.6611616134643554, "step": 177510 }, { "epoch": 1.055215745017268, "grad_norm": 1.4074684381484985, "learning_rate": 0.00016743213602471863, "loss": 0.6359638214111328, "step": 177520 }, { "epoch": 1.0552751870939363, "grad_norm": 2.176297187805176, "learning_rate": 0.0001674273432842142, "loss": 0.6109928607940673, "step": 177530 }, { "epoch": 1.0553346291706047, "grad_norm": 1.2998871803283691, "learning_rate": 0.00016742255026899614, "loss": 0.589655876159668, "step": 177540 }, { "epoch": 1.0553940712472731, "grad_norm": 1.6543396711349487, "learning_rate": 0.00016741775697908735, "loss": 0.5472848415374756, "step": 177550 }, { "epoch": 1.0554535133239416, "grad_norm": 1.8294886350631714, "learning_rate": 0.0001674129634145108, "loss": 0.6034641265869141, "step": 177560 }, { "epoch": 1.05551295540061, "grad_norm": 1.2664028406143188, "learning_rate": 0.00016740816957528938, "loss": 0.6233772277832031, "step": 177570 }, { "epoch": 1.0555723974772784, "grad_norm": 1.5894805192947388, "learning_rate": 0.00016740337546144603, "loss": 0.6092180252075196, "step": 177580 }, { "epoch": 1.0556318395539466, "grad_norm": 1.852612018585205, "learning_rate": 0.00016739858107300368, "loss": 0.6006905555725097, "step": 177590 }, { "epoch": 1.055691281630615, "grad_norm": 1.3697694540023804, "learning_rate": 0.0001673937864099853, "loss": 0.5794180870056153, "step": 177600 }, { "epoch": 1.0557507237072834, "grad_norm": 1.4821909666061401, "learning_rate": 0.00016738899147241383, "loss": 0.6775363922119141, "step": 177610 }, { "epoch": 1.0558101657839518, "grad_norm": 1.9352234601974487, "learning_rate": 0.00016738419626031214, "loss": 0.6742475509643555, "step": 177620 }, { "epoch": 1.0558696078606202, "grad_norm": 1.7316808700561523, "learning_rate": 0.00016737940077370323, "loss": 0.5458699226379394, "step": 177630 }, { "epoch": 1.0559290499372886, "grad_norm": 1.5942046642303467, "learning_rate": 0.00016737460501261, "loss": 0.6531137466430664, "step": 177640 }, { "epoch": 1.055988492013957, "grad_norm": 1.4521503448486328, "learning_rate": 0.0001673698089770554, "loss": 0.6276309013366699, "step": 177650 }, { "epoch": 1.0560479340906255, "grad_norm": 1.4780349731445312, "learning_rate": 0.00016736501266706238, "loss": 0.5657317638397217, "step": 177660 }, { "epoch": 1.0561073761672939, "grad_norm": 1.5680699348449707, "learning_rate": 0.00016736021608265394, "loss": 0.609682273864746, "step": 177670 }, { "epoch": 1.056166818243962, "grad_norm": 1.4997283220291138, "learning_rate": 0.00016735541922385292, "loss": 0.643684196472168, "step": 177680 }, { "epoch": 1.0562262603206305, "grad_norm": 1.562330961227417, "learning_rate": 0.00016735062209068233, "loss": 0.5967252731323243, "step": 177690 }, { "epoch": 1.056285702397299, "grad_norm": 1.4313005208969116, "learning_rate": 0.0001673458246831651, "loss": 0.5975258827209473, "step": 177700 }, { "epoch": 1.0563451444739673, "grad_norm": 1.9262521266937256, "learning_rate": 0.00016734102700132421, "loss": 0.657382869720459, "step": 177710 }, { "epoch": 1.0564045865506357, "grad_norm": 1.6243876218795776, "learning_rate": 0.00016733622904518256, "loss": 0.7065502166748047, "step": 177720 }, { "epoch": 1.0564640286273042, "grad_norm": 1.5786335468292236, "learning_rate": 0.00016733143081476318, "loss": 0.6439250946044922, "step": 177730 }, { "epoch": 1.0565234707039726, "grad_norm": 1.6352936029434204, "learning_rate": 0.00016732663231008892, "loss": 0.6227422237396241, "step": 177740 }, { "epoch": 1.056582912780641, "grad_norm": 1.680095911026001, "learning_rate": 0.00016732183353118278, "loss": 0.5982434272766113, "step": 177750 }, { "epoch": 1.0566423548573094, "grad_norm": 1.751131534576416, "learning_rate": 0.00016731703447806772, "loss": 0.6377160549163818, "step": 177760 }, { "epoch": 1.0567017969339776, "grad_norm": 1.7409604787826538, "learning_rate": 0.00016731223515076672, "loss": 0.6117863655090332, "step": 177770 }, { "epoch": 1.056761239010646, "grad_norm": 1.7824844121932983, "learning_rate": 0.00016730743554930274, "loss": 0.6421042442321777, "step": 177780 }, { "epoch": 1.0568206810873144, "grad_norm": 1.6723082065582275, "learning_rate": 0.00016730263567369866, "loss": 0.6456847190856934, "step": 177790 }, { "epoch": 1.0568801231639828, "grad_norm": 1.6128349304199219, "learning_rate": 0.00016729783552397754, "loss": 0.6273218631744385, "step": 177800 }, { "epoch": 1.0569395652406512, "grad_norm": 1.258791208267212, "learning_rate": 0.0001672930351001623, "loss": 0.567391300201416, "step": 177810 }, { "epoch": 1.0569990073173197, "grad_norm": 1.41306471824646, "learning_rate": 0.00016728823440227588, "loss": 0.5702874660491943, "step": 177820 }, { "epoch": 1.057058449393988, "grad_norm": 1.6825337409973145, "learning_rate": 0.00016728343343034126, "loss": 0.5902206420898437, "step": 177830 }, { "epoch": 1.0571178914706565, "grad_norm": 1.6296263933181763, "learning_rate": 0.00016727863218438146, "loss": 0.6341375350952149, "step": 177840 }, { "epoch": 1.057177333547325, "grad_norm": 1.2520883083343506, "learning_rate": 0.00016727383066441937, "loss": 0.6371585845947265, "step": 177850 }, { "epoch": 1.057236775623993, "grad_norm": 1.6384234428405762, "learning_rate": 0.00016726902887047803, "loss": 0.630108118057251, "step": 177860 }, { "epoch": 1.0572962177006615, "grad_norm": 1.4429171085357666, "learning_rate": 0.00016726422680258033, "loss": 0.6021561622619629, "step": 177870 }, { "epoch": 1.05735565977733, "grad_norm": 1.3926761150360107, "learning_rate": 0.0001672594244607493, "loss": 0.635270357131958, "step": 177880 }, { "epoch": 1.0574151018539983, "grad_norm": 1.503896713256836, "learning_rate": 0.0001672546218450079, "loss": 0.6655165195465088, "step": 177890 }, { "epoch": 1.0574745439306668, "grad_norm": 1.5438082218170166, "learning_rate": 0.00016724981895537908, "loss": 0.624699592590332, "step": 177900 }, { "epoch": 1.0575339860073352, "grad_norm": 1.4241000413894653, "learning_rate": 0.0001672450157918858, "loss": 0.610450267791748, "step": 177910 }, { "epoch": 1.0575934280840036, "grad_norm": 1.5666735172271729, "learning_rate": 0.00016724021235455113, "loss": 0.6393211364746094, "step": 177920 }, { "epoch": 1.057652870160672, "grad_norm": 2.0057365894317627, "learning_rate": 0.000167235408643398, "loss": 0.6386075019836426, "step": 177930 }, { "epoch": 1.0577123122373404, "grad_norm": 1.6143873929977417, "learning_rate": 0.00016723060465844935, "loss": 0.6356090545654297, "step": 177940 }, { "epoch": 1.0577717543140088, "grad_norm": 1.7772092819213867, "learning_rate": 0.00016722580039972817, "loss": 0.5596823692321777, "step": 177950 }, { "epoch": 1.057831196390677, "grad_norm": 1.3837854862213135, "learning_rate": 0.0001672209958672575, "loss": 0.6126895904541015, "step": 177960 }, { "epoch": 1.0578906384673454, "grad_norm": 1.4226093292236328, "learning_rate": 0.0001672161910610603, "loss": 0.5845240116119385, "step": 177970 }, { "epoch": 1.0579500805440138, "grad_norm": 1.6911929845809937, "learning_rate": 0.0001672113859811595, "loss": 0.6174417495727539, "step": 177980 }, { "epoch": 1.0580095226206823, "grad_norm": 1.2405972480773926, "learning_rate": 0.00016720658062757815, "loss": 0.6209201335906982, "step": 177990 }, { "epoch": 1.0580689646973507, "grad_norm": 1.391115427017212, "learning_rate": 0.0001672017750003392, "loss": 0.62309889793396, "step": 178000 }, { "epoch": 1.058128406774019, "grad_norm": 1.5173438787460327, "learning_rate": 0.00016719696909946568, "loss": 0.6270746231079102, "step": 178010 }, { "epoch": 1.0581878488506875, "grad_norm": 1.6577112674713135, "learning_rate": 0.0001671921629249805, "loss": 0.5791136741638183, "step": 178020 }, { "epoch": 1.058247290927356, "grad_norm": 1.7591114044189453, "learning_rate": 0.00016718735647690676, "loss": 0.5809516429901123, "step": 178030 }, { "epoch": 1.0583067330040243, "grad_norm": 1.2704349756240845, "learning_rate": 0.00016718254975526734, "loss": 0.6065223217010498, "step": 178040 }, { "epoch": 1.0583661750806925, "grad_norm": 1.3937729597091675, "learning_rate": 0.00016717774276008533, "loss": 0.6040284633636475, "step": 178050 }, { "epoch": 1.058425617157361, "grad_norm": 2.0213353633880615, "learning_rate": 0.00016717293549138368, "loss": 0.6087706565856934, "step": 178060 }, { "epoch": 1.0584850592340294, "grad_norm": 1.131076693534851, "learning_rate": 0.00016716812794918538, "loss": 0.5946864128112793, "step": 178070 }, { "epoch": 1.0585445013106978, "grad_norm": 1.4176539182662964, "learning_rate": 0.00016716332013351346, "loss": 0.6033269882202148, "step": 178080 }, { "epoch": 1.0586039433873662, "grad_norm": 1.6715961694717407, "learning_rate": 0.00016715851204439087, "loss": 0.5863775253295899, "step": 178090 }, { "epoch": 1.0586633854640346, "grad_norm": 1.5436838865280151, "learning_rate": 0.00016715370368184065, "loss": 0.6249249935150146, "step": 178100 }, { "epoch": 1.058722827540703, "grad_norm": 1.7341231107711792, "learning_rate": 0.0001671488950458858, "loss": 0.5831695556640625, "step": 178110 }, { "epoch": 1.0587822696173714, "grad_norm": 1.6796542406082153, "learning_rate": 0.0001671440861365493, "loss": 0.5778133392333984, "step": 178120 }, { "epoch": 1.0588417116940398, "grad_norm": 1.4693610668182373, "learning_rate": 0.00016713927695385415, "loss": 0.6696469783782959, "step": 178130 }, { "epoch": 1.058901153770708, "grad_norm": 1.3166388273239136, "learning_rate": 0.0001671344674978234, "loss": 0.5869421005249024, "step": 178140 }, { "epoch": 1.0589605958473765, "grad_norm": 2.0309853553771973, "learning_rate": 0.00016712965776848003, "loss": 0.6721511840820312, "step": 178150 }, { "epoch": 1.0590200379240449, "grad_norm": 1.319145679473877, "learning_rate": 0.00016712484776584702, "loss": 0.5856430530548096, "step": 178160 }, { "epoch": 1.0590794800007133, "grad_norm": 1.5186501741409302, "learning_rate": 0.0001671200374899474, "loss": 0.5608892440795898, "step": 178170 }, { "epoch": 1.0591389220773817, "grad_norm": 1.3526989221572876, "learning_rate": 0.00016711522694080424, "loss": 0.643189811706543, "step": 178180 }, { "epoch": 1.05919836415405, "grad_norm": 1.5369696617126465, "learning_rate": 0.00016711041611844048, "loss": 0.5978838920593261, "step": 178190 }, { "epoch": 1.0592578062307185, "grad_norm": 1.7233119010925293, "learning_rate": 0.00016710560502287912, "loss": 0.6754954338073731, "step": 178200 }, { "epoch": 1.059317248307387, "grad_norm": 1.525887370109558, "learning_rate": 0.00016710079365414324, "loss": 0.5881047248840332, "step": 178210 }, { "epoch": 1.0593766903840554, "grad_norm": 1.57823646068573, "learning_rate": 0.00016709598201225583, "loss": 0.7043748378753663, "step": 178220 }, { "epoch": 1.0594361324607235, "grad_norm": 1.5858756303787231, "learning_rate": 0.00016709117009723986, "loss": 0.6000104904174804, "step": 178230 }, { "epoch": 1.059495574537392, "grad_norm": 1.6351690292358398, "learning_rate": 0.00016708635790911843, "loss": 0.6477190971374511, "step": 178240 }, { "epoch": 1.0595550166140604, "grad_norm": 1.4670666456222534, "learning_rate": 0.0001670815454479145, "loss": 0.6194367408752441, "step": 178250 }, { "epoch": 1.0596144586907288, "grad_norm": 1.436546802520752, "learning_rate": 0.00016707673271365114, "loss": 0.5924211978912354, "step": 178260 }, { "epoch": 1.0596739007673972, "grad_norm": 1.4549871683120728, "learning_rate": 0.0001670719197063513, "loss": 0.612330150604248, "step": 178270 }, { "epoch": 1.0597333428440656, "grad_norm": 1.411132574081421, "learning_rate": 0.00016706710642603806, "loss": 0.6306268215179444, "step": 178280 }, { "epoch": 1.059792784920734, "grad_norm": 1.3013356924057007, "learning_rate": 0.00016706229287273447, "loss": 0.6389729499816894, "step": 178290 }, { "epoch": 1.0598522269974024, "grad_norm": 1.3965747356414795, "learning_rate": 0.00016705747904646346, "loss": 0.669731616973877, "step": 178300 }, { "epoch": 1.0599116690740709, "grad_norm": 1.6090794801712036, "learning_rate": 0.00016705266494724817, "loss": 0.5923996925354004, "step": 178310 }, { "epoch": 1.0599711111507393, "grad_norm": 1.5801899433135986, "learning_rate": 0.0001670478505751116, "loss": 0.6058842658996582, "step": 178320 }, { "epoch": 1.0600305532274075, "grad_norm": 1.3706101179122925, "learning_rate": 0.00016704303593007667, "loss": 0.6161446571350098, "step": 178330 }, { "epoch": 1.0600899953040759, "grad_norm": 1.5795055627822876, "learning_rate": 0.00016703822101216654, "loss": 0.6367315292358399, "step": 178340 }, { "epoch": 1.0601494373807443, "grad_norm": 1.8992213010787964, "learning_rate": 0.0001670334058214042, "loss": 0.6296411514282226, "step": 178350 }, { "epoch": 1.0602088794574127, "grad_norm": 1.562565803527832, "learning_rate": 0.00016702859035781266, "loss": 0.6500739097595215, "step": 178360 }, { "epoch": 1.0602683215340811, "grad_norm": 1.4816384315490723, "learning_rate": 0.00016702377462141503, "loss": 0.666322135925293, "step": 178370 }, { "epoch": 1.0603277636107495, "grad_norm": 1.6765451431274414, "learning_rate": 0.00016701895861223428, "loss": 0.6040923595428467, "step": 178380 }, { "epoch": 1.060387205687418, "grad_norm": 1.3265494108200073, "learning_rate": 0.00016701414233029344, "loss": 0.6133889198303223, "step": 178390 }, { "epoch": 1.0604466477640864, "grad_norm": 1.3501962423324585, "learning_rate": 0.0001670093257756156, "loss": 0.642212200164795, "step": 178400 }, { "epoch": 1.0605060898407546, "grad_norm": 1.5558288097381592, "learning_rate": 0.00016700450894822374, "loss": 0.6338788986206054, "step": 178410 }, { "epoch": 1.060565531917423, "grad_norm": 1.8173339366912842, "learning_rate": 0.000166999691848141, "loss": 0.6164168357849121, "step": 178420 }, { "epoch": 1.0606249739940914, "grad_norm": 1.6440913677215576, "learning_rate": 0.00016699487447539036, "loss": 0.6271153450012207, "step": 178430 }, { "epoch": 1.0606844160707598, "grad_norm": 1.6984443664550781, "learning_rate": 0.0001669900568299948, "loss": 0.6324244976043701, "step": 178440 }, { "epoch": 1.0607438581474282, "grad_norm": 1.7566206455230713, "learning_rate": 0.00016698523891197747, "loss": 0.6457694053649903, "step": 178450 }, { "epoch": 1.0608033002240966, "grad_norm": 1.6219346523284912, "learning_rate": 0.00016698042072136137, "loss": 0.5881209373474121, "step": 178460 }, { "epoch": 1.060862742300765, "grad_norm": 1.9100921154022217, "learning_rate": 0.00016697560225816958, "loss": 0.6593592643737793, "step": 178470 }, { "epoch": 1.0609221843774335, "grad_norm": 1.907984972000122, "learning_rate": 0.00016697078352242512, "loss": 0.6543813705444336, "step": 178480 }, { "epoch": 1.0609816264541019, "grad_norm": 1.6405760049819946, "learning_rate": 0.00016696596451415104, "loss": 0.6528506278991699, "step": 178490 }, { "epoch": 1.0610410685307703, "grad_norm": 1.682034969329834, "learning_rate": 0.00016696114523337042, "loss": 0.6520156860351562, "step": 178500 }, { "epoch": 1.0611005106074385, "grad_norm": 1.2597764730453491, "learning_rate": 0.0001669563256801063, "loss": 0.5665516376495361, "step": 178510 }, { "epoch": 1.061159952684107, "grad_norm": 2.3100295066833496, "learning_rate": 0.00016695150585438172, "loss": 0.5923882484436035, "step": 178520 }, { "epoch": 1.0612193947607753, "grad_norm": 1.7696894407272339, "learning_rate": 0.00016694668575621975, "loss": 0.7193746566772461, "step": 178530 }, { "epoch": 1.0612788368374437, "grad_norm": 1.9854170083999634, "learning_rate": 0.00016694186538564342, "loss": 0.6590653419494629, "step": 178540 }, { "epoch": 1.0613382789141121, "grad_norm": 1.8058207035064697, "learning_rate": 0.00016693704474267585, "loss": 0.5923407554626465, "step": 178550 }, { "epoch": 1.0613977209907806, "grad_norm": 2.117548942565918, "learning_rate": 0.00016693222382734005, "loss": 0.6326458930969239, "step": 178560 }, { "epoch": 1.061457163067449, "grad_norm": 1.7482062578201294, "learning_rate": 0.00016692740263965906, "loss": 0.6464781761169434, "step": 178570 }, { "epoch": 1.0615166051441174, "grad_norm": 1.8257049322128296, "learning_rate": 0.00016692258117965604, "loss": 0.6297242164611816, "step": 178580 }, { "epoch": 1.0615760472207858, "grad_norm": 1.7992037534713745, "learning_rate": 0.000166917759447354, "loss": 0.6504325866699219, "step": 178590 }, { "epoch": 1.061635489297454, "grad_norm": 1.7834471464157104, "learning_rate": 0.00016691293744277596, "loss": 0.5750033378601074, "step": 178600 }, { "epoch": 1.0616949313741224, "grad_norm": 2.0419278144836426, "learning_rate": 0.000166908115165945, "loss": 0.6648114204406739, "step": 178610 }, { "epoch": 1.0617543734507908, "grad_norm": 1.7643941640853882, "learning_rate": 0.0001669032926168843, "loss": 0.608615779876709, "step": 178620 }, { "epoch": 1.0618138155274592, "grad_norm": 1.5154088735580444, "learning_rate": 0.00016689846979561678, "loss": 0.6532600879669189, "step": 178630 }, { "epoch": 1.0618732576041277, "grad_norm": 1.6727354526519775, "learning_rate": 0.0001668936467021656, "loss": 0.6357187747955322, "step": 178640 }, { "epoch": 1.061932699680796, "grad_norm": 1.3446786403656006, "learning_rate": 0.0001668888233365538, "loss": 0.6467433929443359, "step": 178650 }, { "epoch": 1.0619921417574645, "grad_norm": 1.642794132232666, "learning_rate": 0.00016688399969880447, "loss": 0.6106304168701172, "step": 178660 }, { "epoch": 1.062051583834133, "grad_norm": 1.5859119892120361, "learning_rate": 0.00016687917578894065, "loss": 0.6638255596160889, "step": 178670 }, { "epoch": 1.0621110259108013, "grad_norm": 1.8452445268630981, "learning_rate": 0.00016687435160698546, "loss": 0.6004962921142578, "step": 178680 }, { "epoch": 1.0621704679874697, "grad_norm": 1.4710829257965088, "learning_rate": 0.00016686952715296195, "loss": 0.6338494300842286, "step": 178690 }, { "epoch": 1.062229910064138, "grad_norm": 1.5698730945587158, "learning_rate": 0.0001668647024268932, "loss": 0.6767382144927978, "step": 178700 }, { "epoch": 1.0622893521408063, "grad_norm": 1.629501461982727, "learning_rate": 0.00016685987742880233, "loss": 0.6264930725097656, "step": 178710 }, { "epoch": 1.0623487942174747, "grad_norm": 1.6692407131195068, "learning_rate": 0.00016685505215871237, "loss": 0.5926121234893799, "step": 178720 }, { "epoch": 1.0624082362941432, "grad_norm": 1.2561594247817993, "learning_rate": 0.00016685022661664642, "loss": 0.6452313423156738, "step": 178730 }, { "epoch": 1.0624676783708116, "grad_norm": 1.5385297536849976, "learning_rate": 0.00016684540080262757, "loss": 0.6337990760803223, "step": 178740 }, { "epoch": 1.06252712044748, "grad_norm": 1.6930731534957886, "learning_rate": 0.0001668405747166789, "loss": 0.59990234375, "step": 178750 }, { "epoch": 1.0625865625241484, "grad_norm": 1.5912995338439941, "learning_rate": 0.00016683574835882348, "loss": 0.6399076461791993, "step": 178760 }, { "epoch": 1.0626460046008168, "grad_norm": 1.4070582389831543, "learning_rate": 0.00016683092172908444, "loss": 0.6335665702819824, "step": 178770 }, { "epoch": 1.062705446677485, "grad_norm": 1.624505639076233, "learning_rate": 0.0001668260948274848, "loss": 0.657243013381958, "step": 178780 }, { "epoch": 1.0627648887541534, "grad_norm": 1.6754828691482544, "learning_rate": 0.00016682126765404774, "loss": 0.6119789123535156, "step": 178790 }, { "epoch": 1.0628243308308218, "grad_norm": 1.3759585618972778, "learning_rate": 0.00016681644020879628, "loss": 0.6553784370422363, "step": 178800 }, { "epoch": 1.0628837729074903, "grad_norm": 1.7754138708114624, "learning_rate": 0.00016681161249175355, "loss": 0.6725521087646484, "step": 178810 }, { "epoch": 1.0629432149841587, "grad_norm": 1.4034035205841064, "learning_rate": 0.00016680678450294262, "loss": 0.614128303527832, "step": 178820 }, { "epoch": 1.063002657060827, "grad_norm": 1.606111764907837, "learning_rate": 0.0001668019562423866, "loss": 0.5816534996032715, "step": 178830 }, { "epoch": 1.0630620991374955, "grad_norm": 1.398780345916748, "learning_rate": 0.0001667971277101086, "loss": 0.6153826713562012, "step": 178840 }, { "epoch": 1.063121541214164, "grad_norm": 1.4638317823410034, "learning_rate": 0.0001667922989061317, "loss": 0.6495262145996094, "step": 178850 }, { "epoch": 1.0631809832908323, "grad_norm": 1.4186971187591553, "learning_rate": 0.00016678746983047897, "loss": 0.6281286239624023, "step": 178860 }, { "epoch": 1.0632404253675007, "grad_norm": 1.347617745399475, "learning_rate": 0.00016678264048317355, "loss": 0.6223171710968017, "step": 178870 }, { "epoch": 1.063299867444169, "grad_norm": 1.693034052848816, "learning_rate": 0.00016677781086423855, "loss": 0.6406459808349609, "step": 178880 }, { "epoch": 1.0633593095208373, "grad_norm": 1.7884169816970825, "learning_rate": 0.00016677298097369708, "loss": 0.6153741836547851, "step": 178890 }, { "epoch": 1.0634187515975058, "grad_norm": 1.6518017053604126, "learning_rate": 0.0001667681508115722, "loss": 0.6651713848114014, "step": 178900 }, { "epoch": 1.0634781936741742, "grad_norm": 1.7311739921569824, "learning_rate": 0.000166763320377887, "loss": 0.6309284687042236, "step": 178910 }, { "epoch": 1.0635376357508426, "grad_norm": 1.8623136281967163, "learning_rate": 0.00016675848967266473, "loss": 0.6044991970062256, "step": 178920 }, { "epoch": 1.063597077827511, "grad_norm": 1.8399468660354614, "learning_rate": 0.00016675365869592832, "loss": 0.6553083896636963, "step": 178930 }, { "epoch": 1.0636565199041794, "grad_norm": 1.5556281805038452, "learning_rate": 0.00016674882744770094, "loss": 0.6231152534484863, "step": 178940 }, { "epoch": 1.0637159619808478, "grad_norm": 1.7297098636627197, "learning_rate": 0.00016674399592800574, "loss": 0.5772998332977295, "step": 178950 }, { "epoch": 1.0637754040575162, "grad_norm": 1.1549171209335327, "learning_rate": 0.0001667391641368658, "loss": 0.5921970844268799, "step": 178960 }, { "epoch": 1.0638348461341844, "grad_norm": 1.6277267932891846, "learning_rate": 0.00016673433207430423, "loss": 0.6980617046356201, "step": 178970 }, { "epoch": 1.0638942882108529, "grad_norm": 1.4716997146606445, "learning_rate": 0.0001667294997403442, "loss": 0.6186385154724121, "step": 178980 }, { "epoch": 1.0639537302875213, "grad_norm": 1.5750373601913452, "learning_rate": 0.00016672466713500876, "loss": 0.6175166130065918, "step": 178990 }, { "epoch": 1.0640131723641897, "grad_norm": 1.737826943397522, "learning_rate": 0.00016671983425832102, "loss": 0.665806770324707, "step": 179000 }, { "epoch": 1.064072614440858, "grad_norm": 1.4574662446975708, "learning_rate": 0.00016671500111030418, "loss": 0.6207784175872803, "step": 179010 }, { "epoch": 1.0641320565175265, "grad_norm": 1.5605653524398804, "learning_rate": 0.00016671016769098128, "loss": 0.6152504920959473, "step": 179020 }, { "epoch": 1.064191498594195, "grad_norm": 1.8882149457931519, "learning_rate": 0.00016670533400037546, "loss": 0.6216847419738769, "step": 179030 }, { "epoch": 1.0642509406708633, "grad_norm": 1.7033129930496216, "learning_rate": 0.00016670050003850988, "loss": 0.6092819213867188, "step": 179040 }, { "epoch": 1.0643103827475318, "grad_norm": 1.6040620803833008, "learning_rate": 0.00016669566580540762, "loss": 0.6219102382659912, "step": 179050 }, { "epoch": 1.0643698248242002, "grad_norm": 1.1470386981964111, "learning_rate": 0.00016669083130109184, "loss": 0.6139800548553467, "step": 179060 }, { "epoch": 1.0644292669008684, "grad_norm": 1.357569932937622, "learning_rate": 0.00016668599652558565, "loss": 0.5381921768188477, "step": 179070 }, { "epoch": 1.0644887089775368, "grad_norm": 1.9778822660446167, "learning_rate": 0.00016668116147891215, "loss": 0.5973721504211426, "step": 179080 }, { "epoch": 1.0645481510542052, "grad_norm": 1.9793918132781982, "learning_rate": 0.00016667632616109454, "loss": 0.6324980735778809, "step": 179090 }, { "epoch": 1.0646075931308736, "grad_norm": 1.543487548828125, "learning_rate": 0.00016667149057215589, "loss": 0.7128054618835449, "step": 179100 }, { "epoch": 1.064667035207542, "grad_norm": 1.2288559675216675, "learning_rate": 0.0001666666547121193, "loss": 0.6228252410888672, "step": 179110 }, { "epoch": 1.0647264772842104, "grad_norm": 1.974780797958374, "learning_rate": 0.00016666181858100804, "loss": 0.567314863204956, "step": 179120 }, { "epoch": 1.0647859193608789, "grad_norm": 1.62485933303833, "learning_rate": 0.0001666569821788451, "loss": 0.607886791229248, "step": 179130 }, { "epoch": 1.0648453614375473, "grad_norm": 1.4601539373397827, "learning_rate": 0.00016665214550565368, "loss": 0.6450860023498535, "step": 179140 }, { "epoch": 1.0649048035142155, "grad_norm": 1.3276184797286987, "learning_rate": 0.00016664730856145692, "loss": 0.571938419342041, "step": 179150 }, { "epoch": 1.0649642455908839, "grad_norm": 1.7423385381698608, "learning_rate": 0.00016664247134627792, "loss": 0.6447061538696289, "step": 179160 }, { "epoch": 1.0650236876675523, "grad_norm": 2.06819486618042, "learning_rate": 0.00016663763386013988, "loss": 0.5916786193847656, "step": 179170 }, { "epoch": 1.0650831297442207, "grad_norm": 1.8742847442626953, "learning_rate": 0.0001666327961030659, "loss": 0.6452363491058349, "step": 179180 }, { "epoch": 1.0651425718208891, "grad_norm": 1.6500495672225952, "learning_rate": 0.00016662795807507915, "loss": 0.5953798294067383, "step": 179190 }, { "epoch": 1.0652020138975575, "grad_norm": 1.4920992851257324, "learning_rate": 0.00016662311977620273, "loss": 0.6858820915222168, "step": 179200 }, { "epoch": 1.065261455974226, "grad_norm": 1.6001722812652588, "learning_rate": 0.0001666182812064598, "loss": 0.6814909934997558, "step": 179210 }, { "epoch": 1.0653208980508944, "grad_norm": 1.3642114400863647, "learning_rate": 0.00016661344236587356, "loss": 0.6529767513275146, "step": 179220 }, { "epoch": 1.0653803401275628, "grad_norm": 2.0591607093811035, "learning_rate": 0.00016660860325446708, "loss": 0.585629940032959, "step": 179230 }, { "epoch": 1.0654397822042312, "grad_norm": 1.5417677164077759, "learning_rate": 0.00016660376387226354, "loss": 0.6017533302307129, "step": 179240 }, { "epoch": 1.0654992242808994, "grad_norm": 1.9665417671203613, "learning_rate": 0.00016659892421928612, "loss": 0.6132647514343261, "step": 179250 }, { "epoch": 1.0655586663575678, "grad_norm": 1.4787917137145996, "learning_rate": 0.0001665940842955579, "loss": 0.5893573760986328, "step": 179260 }, { "epoch": 1.0656181084342362, "grad_norm": 1.1599866151809692, "learning_rate": 0.0001665892441011021, "loss": 0.6447549343109131, "step": 179270 }, { "epoch": 1.0656775505109046, "grad_norm": 1.8204916715621948, "learning_rate": 0.00016658440363594187, "loss": 0.6712310791015625, "step": 179280 }, { "epoch": 1.065736992587573, "grad_norm": 2.400785446166992, "learning_rate": 0.00016657956290010032, "loss": 0.6293376922607422, "step": 179290 }, { "epoch": 1.0657964346642415, "grad_norm": 1.2224433422088623, "learning_rate": 0.00016657472189360065, "loss": 0.6011094570159912, "step": 179300 }, { "epoch": 1.0658558767409099, "grad_norm": 1.5680924654006958, "learning_rate": 0.00016656988061646593, "loss": 0.6894626140594482, "step": 179310 }, { "epoch": 1.0659153188175783, "grad_norm": 1.5654391050338745, "learning_rate": 0.00016656503906871948, "loss": 0.6265374183654785, "step": 179320 }, { "epoch": 1.0659747608942467, "grad_norm": 2.258094072341919, "learning_rate": 0.0001665601972503843, "loss": 0.7394833564758301, "step": 179330 }, { "epoch": 1.066034202970915, "grad_norm": 1.922303318977356, "learning_rate": 0.00016655535516148367, "loss": 0.6067388534545899, "step": 179340 }, { "epoch": 1.0660936450475833, "grad_norm": 1.9043755531311035, "learning_rate": 0.00016655051280204067, "loss": 0.6564228057861328, "step": 179350 }, { "epoch": 1.0661530871242517, "grad_norm": 1.4399791955947876, "learning_rate": 0.00016654567017207854, "loss": 0.6317740440368652, "step": 179360 }, { "epoch": 1.0662125292009201, "grad_norm": 1.594560146331787, "learning_rate": 0.00016654082727162034, "loss": 0.604004955291748, "step": 179370 }, { "epoch": 1.0662719712775885, "grad_norm": 1.8694217205047607, "learning_rate": 0.00016653598410068938, "loss": 0.6147260665893555, "step": 179380 }, { "epoch": 1.066331413354257, "grad_norm": 1.8485584259033203, "learning_rate": 0.00016653114065930867, "loss": 0.5787606716156006, "step": 179390 }, { "epoch": 1.0663908554309254, "grad_norm": 1.6374032497406006, "learning_rate": 0.0001665262969475015, "loss": 0.6844899654388428, "step": 179400 }, { "epoch": 1.0664502975075938, "grad_norm": 2.0911688804626465, "learning_rate": 0.00016652145296529097, "loss": 0.6551739692687988, "step": 179410 }, { "epoch": 1.0665097395842622, "grad_norm": 1.4957292079925537, "learning_rate": 0.00016651660871270032, "loss": 0.5608690738677978, "step": 179420 }, { "epoch": 1.0665691816609306, "grad_norm": 1.5844038724899292, "learning_rate": 0.00016651176418975268, "loss": 0.5992426872253418, "step": 179430 }, { "epoch": 1.0666286237375988, "grad_norm": 1.398898959159851, "learning_rate": 0.0001665069193964712, "loss": 0.6268719673156739, "step": 179440 }, { "epoch": 1.0666880658142672, "grad_norm": 1.5918835401535034, "learning_rate": 0.0001665020743328791, "loss": 0.6073909759521484, "step": 179450 }, { "epoch": 1.0667475078909356, "grad_norm": 1.5331374406814575, "learning_rate": 0.00016649722899899955, "loss": 0.6206707954406738, "step": 179460 }, { "epoch": 1.066806949967604, "grad_norm": 1.6725502014160156, "learning_rate": 0.00016649238339485568, "loss": 0.6173888206481933, "step": 179470 }, { "epoch": 1.0668663920442725, "grad_norm": 2.0060276985168457, "learning_rate": 0.00016648753752047075, "loss": 0.577031135559082, "step": 179480 }, { "epoch": 1.0669258341209409, "grad_norm": 1.850915789604187, "learning_rate": 0.0001664826913758679, "loss": 0.5800823211669922, "step": 179490 }, { "epoch": 1.0669852761976093, "grad_norm": 1.832255244255066, "learning_rate": 0.0001664778449610703, "loss": 0.6111951351165772, "step": 179500 }, { "epoch": 1.0670447182742777, "grad_norm": 1.4806792736053467, "learning_rate": 0.00016647299827610113, "loss": 0.6565448760986328, "step": 179510 }, { "epoch": 1.067104160350946, "grad_norm": 1.4471611976623535, "learning_rate": 0.00016646815132098362, "loss": 0.7053421020507813, "step": 179520 }, { "epoch": 1.0671636024276143, "grad_norm": 1.7896476984024048, "learning_rate": 0.0001664633040957409, "loss": 0.6527868270874023, "step": 179530 }, { "epoch": 1.0672230445042827, "grad_norm": 1.721874475479126, "learning_rate": 0.00016645845660039622, "loss": 0.6153296947479248, "step": 179540 }, { "epoch": 1.0672824865809512, "grad_norm": 1.7479978799819946, "learning_rate": 0.00016645360883497275, "loss": 0.6201128482818603, "step": 179550 }, { "epoch": 1.0673419286576196, "grad_norm": 1.807255506515503, "learning_rate": 0.0001664487607994936, "loss": 0.6841912269592285, "step": 179560 }, { "epoch": 1.067401370734288, "grad_norm": 1.5279436111450195, "learning_rate": 0.00016644391249398205, "loss": 0.6592432975769043, "step": 179570 }, { "epoch": 1.0674608128109564, "grad_norm": 1.704406976699829, "learning_rate": 0.0001664390639184613, "loss": 0.649234390258789, "step": 179580 }, { "epoch": 1.0675202548876248, "grad_norm": 1.440995693206787, "learning_rate": 0.00016643421507295448, "loss": 0.6224668502807618, "step": 179590 }, { "epoch": 1.0675796969642932, "grad_norm": 1.4947912693023682, "learning_rate": 0.00016642936595748483, "loss": 0.6135248184204102, "step": 179600 }, { "epoch": 1.0676391390409616, "grad_norm": 2.2842283248901367, "learning_rate": 0.00016642451657207554, "loss": 0.6853593826293946, "step": 179610 }, { "epoch": 1.0676985811176298, "grad_norm": 1.981759786605835, "learning_rate": 0.00016641966691674978, "loss": 0.6463129997253418, "step": 179620 }, { "epoch": 1.0677580231942982, "grad_norm": 1.6761057376861572, "learning_rate": 0.0001664148169915308, "loss": 0.6365350723266602, "step": 179630 }, { "epoch": 1.0678174652709667, "grad_norm": 1.6387158632278442, "learning_rate": 0.00016640996679644177, "loss": 0.6950044631958008, "step": 179640 }, { "epoch": 1.067876907347635, "grad_norm": 1.395331859588623, "learning_rate": 0.00016640511633150587, "loss": 0.6337271690368652, "step": 179650 }, { "epoch": 1.0679363494243035, "grad_norm": 1.5373954772949219, "learning_rate": 0.00016640026559674634, "loss": 0.6316361427307129, "step": 179660 }, { "epoch": 1.067995791500972, "grad_norm": 1.6923609972000122, "learning_rate": 0.00016639541459218638, "loss": 0.6090084075927734, "step": 179670 }, { "epoch": 1.0680552335776403, "grad_norm": 1.6961251497268677, "learning_rate": 0.0001663905633178492, "loss": 0.5919577598571777, "step": 179680 }, { "epoch": 1.0681146756543087, "grad_norm": 1.4066306352615356, "learning_rate": 0.00016638571177375795, "loss": 0.5778049468994141, "step": 179690 }, { "epoch": 1.0681741177309771, "grad_norm": 1.7092747688293457, "learning_rate": 0.00016638085995993593, "loss": 0.5894691467285156, "step": 179700 }, { "epoch": 1.0682335598076453, "grad_norm": 1.8124114274978638, "learning_rate": 0.00016637600787640627, "loss": 0.6247907638549804, "step": 179710 }, { "epoch": 1.0682930018843138, "grad_norm": 1.7053968906402588, "learning_rate": 0.0001663711555231922, "loss": 0.615317964553833, "step": 179720 }, { "epoch": 1.0683524439609822, "grad_norm": 1.3759005069732666, "learning_rate": 0.00016636630290031696, "loss": 0.6359347820281982, "step": 179730 }, { "epoch": 1.0684118860376506, "grad_norm": 1.4770588874816895, "learning_rate": 0.00016636145000780377, "loss": 0.6842231273651123, "step": 179740 }, { "epoch": 1.068471328114319, "grad_norm": 1.6116409301757812, "learning_rate": 0.0001663565968456758, "loss": 0.6014372825622558, "step": 179750 }, { "epoch": 1.0685307701909874, "grad_norm": 2.003818988800049, "learning_rate": 0.00016635174341395628, "loss": 0.643796157836914, "step": 179760 }, { "epoch": 1.0685902122676558, "grad_norm": 1.226749300956726, "learning_rate": 0.00016634688971266842, "loss": 0.6251629829406739, "step": 179770 }, { "epoch": 1.0686496543443242, "grad_norm": 1.3688024282455444, "learning_rate": 0.0001663420357418355, "loss": 0.6507290840148926, "step": 179780 }, { "epoch": 1.0687090964209927, "grad_norm": 2.0948023796081543, "learning_rate": 0.00016633718150148066, "loss": 0.6331417560577393, "step": 179790 }, { "epoch": 1.068768538497661, "grad_norm": 1.7632615566253662, "learning_rate": 0.00016633232699162718, "loss": 0.6605648994445801, "step": 179800 }, { "epoch": 1.0688279805743293, "grad_norm": 1.8475632667541504, "learning_rate": 0.00016632747221229826, "loss": 0.6262162208557129, "step": 179810 }, { "epoch": 1.0688874226509977, "grad_norm": 1.7989145517349243, "learning_rate": 0.0001663226171635171, "loss": 0.6340951919555664, "step": 179820 }, { "epoch": 1.068946864727666, "grad_norm": 1.4626728296279907, "learning_rate": 0.00016631776184530695, "loss": 0.6132141590118408, "step": 179830 }, { "epoch": 1.0690063068043345, "grad_norm": 1.4428868293762207, "learning_rate": 0.00016631290625769102, "loss": 0.6122573852539063, "step": 179840 }, { "epoch": 1.069065748881003, "grad_norm": 1.7460312843322754, "learning_rate": 0.00016630805040069257, "loss": 0.6350762367248535, "step": 179850 }, { "epoch": 1.0691251909576713, "grad_norm": 2.0444159507751465, "learning_rate": 0.00016630319427433482, "loss": 0.6474996089935303, "step": 179860 }, { "epoch": 1.0691846330343397, "grad_norm": 1.6311331987380981, "learning_rate": 0.00016629833787864095, "loss": 0.6485534191131592, "step": 179870 }, { "epoch": 1.0692440751110082, "grad_norm": 1.3920060396194458, "learning_rate": 0.00016629348121363426, "loss": 0.6284550666809082, "step": 179880 }, { "epoch": 1.0693035171876764, "grad_norm": 1.4207663536071777, "learning_rate": 0.00016628862427933795, "loss": 0.6594073295593261, "step": 179890 }, { "epoch": 1.0693629592643448, "grad_norm": 1.8645766973495483, "learning_rate": 0.00016628376707577525, "loss": 0.5875004291534424, "step": 179900 }, { "epoch": 1.0694224013410132, "grad_norm": 1.7474967241287231, "learning_rate": 0.0001662789096029694, "loss": 0.6256167411804199, "step": 179910 }, { "epoch": 1.0694818434176816, "grad_norm": 1.2674587965011597, "learning_rate": 0.00016627405186094368, "loss": 0.5854351997375489, "step": 179920 }, { "epoch": 1.06954128549435, "grad_norm": 1.3438833951950073, "learning_rate": 0.00016626919384972122, "loss": 0.5771354675292969, "step": 179930 }, { "epoch": 1.0696007275710184, "grad_norm": 1.407426118850708, "learning_rate": 0.00016626433556932534, "loss": 0.6431154727935791, "step": 179940 }, { "epoch": 1.0696601696476868, "grad_norm": 1.4846057891845703, "learning_rate": 0.00016625947701977932, "loss": 0.6362513542175293, "step": 179950 }, { "epoch": 1.0697196117243553, "grad_norm": 1.3674020767211914, "learning_rate": 0.00016625461820110626, "loss": 0.6269670009613038, "step": 179960 }, { "epoch": 1.0697790538010237, "grad_norm": 1.6923612356185913, "learning_rate": 0.00016624975911332956, "loss": 0.6191523551940918, "step": 179970 }, { "epoch": 1.069838495877692, "grad_norm": 1.4945943355560303, "learning_rate": 0.00016624489975647236, "loss": 0.6306952476501465, "step": 179980 }, { "epoch": 1.0698979379543603, "grad_norm": 1.956484079360962, "learning_rate": 0.00016624004013055798, "loss": 0.6420600414276123, "step": 179990 }, { "epoch": 1.0699573800310287, "grad_norm": 1.5330702066421509, "learning_rate": 0.00016623518023560957, "loss": 0.5942554473876953, "step": 180000 }, { "epoch": 1.070016822107697, "grad_norm": 1.637302279472351, "learning_rate": 0.00016623032007165046, "loss": 0.6374982357025146, "step": 180010 }, { "epoch": 1.0700762641843655, "grad_norm": 1.855818271636963, "learning_rate": 0.0001662254596387039, "loss": 0.5753908634185791, "step": 180020 }, { "epoch": 1.070135706261034, "grad_norm": 1.5546495914459229, "learning_rate": 0.00016622059893679308, "loss": 0.5863369464874267, "step": 180030 }, { "epoch": 1.0701951483377024, "grad_norm": 1.3585609197616577, "learning_rate": 0.00016621573796594133, "loss": 0.6538962841033935, "step": 180040 }, { "epoch": 1.0702545904143708, "grad_norm": 1.5252914428710938, "learning_rate": 0.00016621087672617183, "loss": 0.6840051651000977, "step": 180050 }, { "epoch": 1.0703140324910392, "grad_norm": 1.9823931455612183, "learning_rate": 0.00016620601521750788, "loss": 0.6759003162384033, "step": 180060 }, { "epoch": 1.0703734745677076, "grad_norm": 1.5543489456176758, "learning_rate": 0.0001662011534399727, "loss": 0.6015399932861328, "step": 180070 }, { "epoch": 1.0704329166443758, "grad_norm": 2.1782500743865967, "learning_rate": 0.0001661962913935896, "loss": 0.6434607028961181, "step": 180080 }, { "epoch": 1.0704923587210442, "grad_norm": 1.3821934461593628, "learning_rate": 0.00016619142907838176, "loss": 0.5953774452209473, "step": 180090 }, { "epoch": 1.0705518007977126, "grad_norm": 1.3016955852508545, "learning_rate": 0.00016618656649437254, "loss": 0.6225412368774415, "step": 180100 }, { "epoch": 1.070611242874381, "grad_norm": 1.4545674324035645, "learning_rate": 0.00016618170364158513, "loss": 0.6004697799682617, "step": 180110 }, { "epoch": 1.0706706849510494, "grad_norm": 1.4744497537612915, "learning_rate": 0.0001661768405200428, "loss": 0.6242624282836914, "step": 180120 }, { "epoch": 1.0707301270277179, "grad_norm": 1.7185571193695068, "learning_rate": 0.0001661719771297688, "loss": 0.6087018013000488, "step": 180130 }, { "epoch": 1.0707895691043863, "grad_norm": 1.7859903573989868, "learning_rate": 0.00016616711347078647, "loss": 0.6170219421386719, "step": 180140 }, { "epoch": 1.0708490111810547, "grad_norm": 1.8661235570907593, "learning_rate": 0.000166162249543119, "loss": 0.6499697685241699, "step": 180150 }, { "epoch": 1.070908453257723, "grad_norm": 1.9048784971237183, "learning_rate": 0.0001661573853467897, "loss": 0.6077136993408203, "step": 180160 }, { "epoch": 1.0709678953343915, "grad_norm": 2.314602851867676, "learning_rate": 0.0001661525208818218, "loss": 0.6529793262481689, "step": 180170 }, { "epoch": 1.0710273374110597, "grad_norm": 1.4307067394256592, "learning_rate": 0.0001661476561482386, "loss": 0.5738025188446045, "step": 180180 }, { "epoch": 1.0710867794877281, "grad_norm": 1.91696298122406, "learning_rate": 0.00016614279114606336, "loss": 0.6408237457275391, "step": 180190 }, { "epoch": 1.0711462215643965, "grad_norm": 1.340636134147644, "learning_rate": 0.00016613792587531935, "loss": 0.59239501953125, "step": 180200 }, { "epoch": 1.071205663641065, "grad_norm": 1.5942695140838623, "learning_rate": 0.00016613306033602985, "loss": 0.6433539390563965, "step": 180210 }, { "epoch": 1.0712651057177334, "grad_norm": 1.3039606809616089, "learning_rate": 0.00016612819452821814, "loss": 0.6536819934844971, "step": 180220 }, { "epoch": 1.0713245477944018, "grad_norm": 1.8151812553405762, "learning_rate": 0.00016612332845190747, "loss": 0.669898509979248, "step": 180230 }, { "epoch": 1.0713839898710702, "grad_norm": 1.455743670463562, "learning_rate": 0.00016611846210712113, "loss": 0.5990335464477539, "step": 180240 }, { "epoch": 1.0714434319477386, "grad_norm": 1.5995155572891235, "learning_rate": 0.0001661135954938825, "loss": 0.6331319808959961, "step": 180250 }, { "epoch": 1.0715028740244068, "grad_norm": 1.6497646570205688, "learning_rate": 0.00016610872861221466, "loss": 0.6401631355285644, "step": 180260 }, { "epoch": 1.0715623161010752, "grad_norm": 1.6899378299713135, "learning_rate": 0.00016610386146214103, "loss": 0.6525244235992431, "step": 180270 }, { "epoch": 1.0716217581777436, "grad_norm": 2.0189859867095947, "learning_rate": 0.00016609899404368487, "loss": 0.6342567443847656, "step": 180280 }, { "epoch": 1.071681200254412, "grad_norm": 1.593959093093872, "learning_rate": 0.00016609412635686948, "loss": 0.6580004692077637, "step": 180290 }, { "epoch": 1.0717406423310805, "grad_norm": 1.5619462728500366, "learning_rate": 0.0001660892584017181, "loss": 0.6368785381317139, "step": 180300 }, { "epoch": 1.0718000844077489, "grad_norm": 1.6611882448196411, "learning_rate": 0.00016608439017825404, "loss": 0.6409400939941406, "step": 180310 }, { "epoch": 1.0718595264844173, "grad_norm": 1.4894089698791504, "learning_rate": 0.00016607952168650055, "loss": 0.5966261863708496, "step": 180320 }, { "epoch": 1.0719189685610857, "grad_norm": 1.4206656217575073, "learning_rate": 0.00016607465292648097, "loss": 0.646799373626709, "step": 180330 }, { "epoch": 1.0719784106377541, "grad_norm": 1.6647627353668213, "learning_rate": 0.00016606978389821858, "loss": 0.6562044143676757, "step": 180340 }, { "epoch": 1.0720378527144225, "grad_norm": 1.9724761247634888, "learning_rate": 0.0001660649146017367, "loss": 0.6610593795776367, "step": 180350 }, { "epoch": 1.0720972947910907, "grad_norm": 1.7102437019348145, "learning_rate": 0.00016606004503705857, "loss": 0.6116785049438477, "step": 180360 }, { "epoch": 1.0721567368677591, "grad_norm": 1.6303867101669312, "learning_rate": 0.0001660551752042075, "loss": 0.6925191402435302, "step": 180370 }, { "epoch": 1.0722161789444276, "grad_norm": 1.6022722721099854, "learning_rate": 0.0001660503051032068, "loss": 0.6140684127807617, "step": 180380 }, { "epoch": 1.072275621021096, "grad_norm": 2.05029296875, "learning_rate": 0.00016604543473407976, "loss": 0.6241178989410401, "step": 180390 }, { "epoch": 1.0723350630977644, "grad_norm": 1.6345192193984985, "learning_rate": 0.00016604056409684966, "loss": 0.6492070198059082, "step": 180400 }, { "epoch": 1.0723945051744328, "grad_norm": 1.6924763917922974, "learning_rate": 0.00016603569319153985, "loss": 0.62855224609375, "step": 180410 }, { "epoch": 1.0724539472511012, "grad_norm": 1.63970947265625, "learning_rate": 0.00016603082201817354, "loss": 0.6430370330810546, "step": 180420 }, { "epoch": 1.0725133893277696, "grad_norm": 1.7763535976409912, "learning_rate": 0.00016602595057677415, "loss": 0.6403401851654053, "step": 180430 }, { "epoch": 1.072572831404438, "grad_norm": 1.8788466453552246, "learning_rate": 0.00016602107886736487, "loss": 0.5876136779785156, "step": 180440 }, { "epoch": 1.0726322734811062, "grad_norm": 1.7223129272460938, "learning_rate": 0.00016601620688996906, "loss": 0.6940620422363282, "step": 180450 }, { "epoch": 1.0726917155577746, "grad_norm": 1.501936674118042, "learning_rate": 0.00016601133464461007, "loss": 0.5914267539978028, "step": 180460 }, { "epoch": 1.072751157634443, "grad_norm": 1.4131344556808472, "learning_rate": 0.00016600646213131112, "loss": 0.6484740257263184, "step": 180470 }, { "epoch": 1.0728105997111115, "grad_norm": 1.4054230451583862, "learning_rate": 0.00016600158935009557, "loss": 0.6010231018066406, "step": 180480 }, { "epoch": 1.07287004178778, "grad_norm": 1.8743005990982056, "learning_rate": 0.00016599671630098672, "loss": 0.6467320442199707, "step": 180490 }, { "epoch": 1.0729294838644483, "grad_norm": 1.835645079612732, "learning_rate": 0.00016599184298400787, "loss": 0.6529926300048828, "step": 180500 }, { "epoch": 1.0729889259411167, "grad_norm": 1.5158637762069702, "learning_rate": 0.00016598696939918237, "loss": 0.5392004966735839, "step": 180510 }, { "epoch": 1.0730483680177851, "grad_norm": 1.5628288984298706, "learning_rate": 0.00016598209554653345, "loss": 0.659145450592041, "step": 180520 }, { "epoch": 1.0731078100944536, "grad_norm": 1.295746088027954, "learning_rate": 0.0001659772214260845, "loss": 0.6196964263916016, "step": 180530 }, { "epoch": 1.073167252171122, "grad_norm": 1.5895329713821411, "learning_rate": 0.00016597234703785886, "loss": 0.6452682495117188, "step": 180540 }, { "epoch": 1.0732266942477902, "grad_norm": 1.6692676544189453, "learning_rate": 0.00016596747238187978, "loss": 0.675827932357788, "step": 180550 }, { "epoch": 1.0732861363244586, "grad_norm": 1.4552463293075562, "learning_rate": 0.00016596259745817058, "loss": 0.6246597766876221, "step": 180560 }, { "epoch": 1.073345578401127, "grad_norm": 1.9332081079483032, "learning_rate": 0.00016595772226675462, "loss": 0.6381598949432373, "step": 180570 }, { "epoch": 1.0734050204777954, "grad_norm": 1.4635456800460815, "learning_rate": 0.00016595284680765522, "loss": 0.6559168815612793, "step": 180580 }, { "epoch": 1.0734644625544638, "grad_norm": 1.6303808689117432, "learning_rate": 0.00016594797108089566, "loss": 0.5715290546417237, "step": 180590 }, { "epoch": 1.0735239046311322, "grad_norm": 1.8281714916229248, "learning_rate": 0.00016594309508649927, "loss": 0.6031581878662109, "step": 180600 }, { "epoch": 1.0735833467078006, "grad_norm": 1.9329227209091187, "learning_rate": 0.00016593821882448945, "loss": 0.5888412475585938, "step": 180610 }, { "epoch": 1.073642788784469, "grad_norm": 1.6527162790298462, "learning_rate": 0.00016593334229488943, "loss": 0.5913171768188477, "step": 180620 }, { "epoch": 1.0737022308611373, "grad_norm": 1.7580437660217285, "learning_rate": 0.00016592846549772262, "loss": 0.696185302734375, "step": 180630 }, { "epoch": 1.0737616729378057, "grad_norm": 1.5010836124420166, "learning_rate": 0.00016592358843301228, "loss": 0.580228042602539, "step": 180640 }, { "epoch": 1.073821115014474, "grad_norm": 2.077312707901001, "learning_rate": 0.00016591871110078175, "loss": 0.6883040428161621, "step": 180650 }, { "epoch": 1.0738805570911425, "grad_norm": 1.2088268995285034, "learning_rate": 0.00016591383350105443, "loss": 0.6309311866760254, "step": 180660 }, { "epoch": 1.073939999167811, "grad_norm": 1.165095329284668, "learning_rate": 0.00016590895563385358, "loss": 0.6020186424255372, "step": 180670 }, { "epoch": 1.0739994412444793, "grad_norm": 1.7032102346420288, "learning_rate": 0.00016590407749920253, "loss": 0.5789194107055664, "step": 180680 }, { "epoch": 1.0740588833211477, "grad_norm": 1.4878910779953003, "learning_rate": 0.0001658991990971247, "loss": 0.6007050991058349, "step": 180690 }, { "epoch": 1.0741183253978162, "grad_norm": 1.5379422903060913, "learning_rate": 0.00016589432042764333, "loss": 0.6091057300567627, "step": 180700 }, { "epoch": 1.0741777674744846, "grad_norm": 1.8339537382125854, "learning_rate": 0.0001658894414907818, "loss": 0.596258544921875, "step": 180710 }, { "epoch": 1.074237209551153, "grad_norm": 2.215177536010742, "learning_rate": 0.00016588456228656343, "loss": 0.650244951248169, "step": 180720 }, { "epoch": 1.0742966516278212, "grad_norm": 1.5623985528945923, "learning_rate": 0.00016587968281501163, "loss": 0.6457764625549316, "step": 180730 }, { "epoch": 1.0743560937044896, "grad_norm": 1.751559853553772, "learning_rate": 0.00016587480307614965, "loss": 0.6896049976348877, "step": 180740 }, { "epoch": 1.074415535781158, "grad_norm": 1.651207685470581, "learning_rate": 0.00016586992307000085, "loss": 0.6184977531433106, "step": 180750 }, { "epoch": 1.0744749778578264, "grad_norm": 1.6769968271255493, "learning_rate": 0.00016586504279658863, "loss": 0.6219098091125488, "step": 180760 }, { "epoch": 1.0745344199344948, "grad_norm": 1.981027364730835, "learning_rate": 0.00016586016225593632, "loss": 0.6595477104187012, "step": 180770 }, { "epoch": 1.0745938620111632, "grad_norm": 1.3103128671646118, "learning_rate": 0.00016585528144806723, "loss": 0.6101183891296387, "step": 180780 }, { "epoch": 1.0746533040878317, "grad_norm": 1.9186605215072632, "learning_rate": 0.00016585040037300473, "loss": 0.6238749027252197, "step": 180790 }, { "epoch": 1.0747127461645, "grad_norm": 1.4806698560714722, "learning_rate": 0.00016584551903077213, "loss": 0.5958746433258056, "step": 180800 }, { "epoch": 1.0747721882411685, "grad_norm": 1.7366803884506226, "learning_rate": 0.00016584063742139287, "loss": 0.5755579471588135, "step": 180810 }, { "epoch": 1.0748316303178367, "grad_norm": 1.3827879428863525, "learning_rate": 0.00016583575554489022, "loss": 0.6570022106170654, "step": 180820 }, { "epoch": 1.074891072394505, "grad_norm": 1.8163455724716187, "learning_rate": 0.00016583087340128758, "loss": 0.6724871635437012, "step": 180830 }, { "epoch": 1.0749505144711735, "grad_norm": 1.4955687522888184, "learning_rate": 0.00016582599099060826, "loss": 0.6005528926849365, "step": 180840 }, { "epoch": 1.075009956547842, "grad_norm": 1.4735586643218994, "learning_rate": 0.00016582110831287567, "loss": 0.6439753532409668, "step": 180850 }, { "epoch": 1.0750693986245103, "grad_norm": 1.8442922830581665, "learning_rate": 0.00016581622536811314, "loss": 0.6932725429534912, "step": 180860 }, { "epoch": 1.0751288407011788, "grad_norm": 1.7654470205307007, "learning_rate": 0.00016581134215634403, "loss": 0.6304353237152099, "step": 180870 }, { "epoch": 1.0751882827778472, "grad_norm": 1.5303056240081787, "learning_rate": 0.00016580645867759168, "loss": 0.6306341171264649, "step": 180880 }, { "epoch": 1.0752477248545156, "grad_norm": 1.1462537050247192, "learning_rate": 0.00016580157493187948, "loss": 0.6278759002685547, "step": 180890 }, { "epoch": 1.075307166931184, "grad_norm": 1.6932990550994873, "learning_rate": 0.00016579669091923077, "loss": 0.6476955890655518, "step": 180900 }, { "epoch": 1.0753666090078524, "grad_norm": 1.5052945613861084, "learning_rate": 0.00016579180663966894, "loss": 0.5913976669311524, "step": 180910 }, { "epoch": 1.0754260510845206, "grad_norm": 1.6814470291137695, "learning_rate": 0.00016578692209321736, "loss": 0.7077163696289063, "step": 180920 }, { "epoch": 1.075485493161189, "grad_norm": 1.4323817491531372, "learning_rate": 0.00016578203727989933, "loss": 0.6329729080200195, "step": 180930 }, { "epoch": 1.0755449352378574, "grad_norm": 1.7598788738250732, "learning_rate": 0.00016577715219973828, "loss": 0.6069190502166748, "step": 180940 }, { "epoch": 1.0756043773145259, "grad_norm": 1.895443320274353, "learning_rate": 0.0001657722668527576, "loss": 0.6466590881347656, "step": 180950 }, { "epoch": 1.0756638193911943, "grad_norm": 1.5981942415237427, "learning_rate": 0.00016576738123898058, "loss": 0.6209820747375489, "step": 180960 }, { "epoch": 1.0757232614678627, "grad_norm": 1.2999159097671509, "learning_rate": 0.00016576249535843064, "loss": 0.6853219985961914, "step": 180970 }, { "epoch": 1.075782703544531, "grad_norm": 1.7209439277648926, "learning_rate": 0.00016575760921113116, "loss": 0.5960550308227539, "step": 180980 }, { "epoch": 1.0758421456211995, "grad_norm": 1.6596553325653076, "learning_rate": 0.00016575272279710547, "loss": 0.6255175590515136, "step": 180990 }, { "epoch": 1.0759015876978677, "grad_norm": 1.2437490224838257, "learning_rate": 0.000165747836116377, "loss": 0.5425067901611328, "step": 181000 }, { "epoch": 1.0759610297745361, "grad_norm": 1.0909342765808105, "learning_rate": 0.00016574294916896912, "loss": 0.5623126029968262, "step": 181010 }, { "epoch": 1.0760204718512045, "grad_norm": 1.556605339050293, "learning_rate": 0.00016573806195490515, "loss": 0.6427798748016358, "step": 181020 }, { "epoch": 1.076079913927873, "grad_norm": 1.5074467658996582, "learning_rate": 0.0001657331744742085, "loss": 0.6792853355407715, "step": 181030 }, { "epoch": 1.0761393560045414, "grad_norm": 1.9304349422454834, "learning_rate": 0.00016572828672690258, "loss": 0.6482815265655517, "step": 181040 }, { "epoch": 1.0761987980812098, "grad_norm": 1.9732619524002075, "learning_rate": 0.00016572339871301074, "loss": 0.7045321941375733, "step": 181050 }, { "epoch": 1.0762582401578782, "grad_norm": 1.5547950267791748, "learning_rate": 0.00016571851043255639, "loss": 0.6101502418518067, "step": 181060 }, { "epoch": 1.0763176822345466, "grad_norm": 1.6567590236663818, "learning_rate": 0.00016571362188556285, "loss": 0.7078942775726318, "step": 181070 }, { "epoch": 1.076377124311215, "grad_norm": 1.363830804824829, "learning_rate": 0.0001657087330720536, "loss": 0.6563405513763427, "step": 181080 }, { "epoch": 1.0764365663878834, "grad_norm": 1.4325674772262573, "learning_rate": 0.00016570384399205196, "loss": 0.5772073268890381, "step": 181090 }, { "epoch": 1.0764960084645516, "grad_norm": 1.816975474357605, "learning_rate": 0.00016569895464558135, "loss": 0.6210683822631836, "step": 181100 }, { "epoch": 1.07655545054122, "grad_norm": 1.6144427061080933, "learning_rate": 0.0001656940650326651, "loss": 0.6427515029907227, "step": 181110 }, { "epoch": 1.0766148926178885, "grad_norm": 1.3787835836410522, "learning_rate": 0.00016568917515332664, "loss": 0.5676015853881836, "step": 181120 }, { "epoch": 1.0766743346945569, "grad_norm": 2.0266342163085938, "learning_rate": 0.00016568428500758942, "loss": 0.7100141525268555, "step": 181130 }, { "epoch": 1.0767337767712253, "grad_norm": 1.5834050178527832, "learning_rate": 0.00016567939459547677, "loss": 0.5555785179138184, "step": 181140 }, { "epoch": 1.0767932188478937, "grad_norm": 1.841078758239746, "learning_rate": 0.00016567450391701208, "loss": 0.6473874568939209, "step": 181150 }, { "epoch": 1.076852660924562, "grad_norm": 1.4165070056915283, "learning_rate": 0.00016566961297221873, "loss": 0.5532186508178711, "step": 181160 }, { "epoch": 1.0769121030012305, "grad_norm": 1.4656457901000977, "learning_rate": 0.00016566472176112015, "loss": 0.611540412902832, "step": 181170 }, { "epoch": 1.076971545077899, "grad_norm": 1.3089573383331299, "learning_rate": 0.00016565983028373976, "loss": 0.5960560798645019, "step": 181180 }, { "epoch": 1.0770309871545671, "grad_norm": 1.9317514896392822, "learning_rate": 0.00016565493854010094, "loss": 0.6117613792419434, "step": 181190 }, { "epoch": 1.0770904292312355, "grad_norm": 1.6181927919387817, "learning_rate": 0.00016565004653022706, "loss": 0.6706998825073243, "step": 181200 }, { "epoch": 1.077149871307904, "grad_norm": 1.2610619068145752, "learning_rate": 0.00016564515425414154, "loss": 0.615359115600586, "step": 181210 }, { "epoch": 1.0772093133845724, "grad_norm": 1.5676287412643433, "learning_rate": 0.0001656402617118678, "loss": 0.6556066513061524, "step": 181220 }, { "epoch": 1.0772687554612408, "grad_norm": 1.263441801071167, "learning_rate": 0.0001656353689034292, "loss": 0.6090053081512451, "step": 181230 }, { "epoch": 1.0773281975379092, "grad_norm": 1.8760179281234741, "learning_rate": 0.00016563047582884922, "loss": 0.6531383514404296, "step": 181240 }, { "epoch": 1.0773876396145776, "grad_norm": 2.305626630783081, "learning_rate": 0.00016562558248815122, "loss": 0.594530439376831, "step": 181250 }, { "epoch": 1.077447081691246, "grad_norm": 1.940431833267212, "learning_rate": 0.0001656206888813586, "loss": 0.6409897327423095, "step": 181260 }, { "epoch": 1.0775065237679144, "grad_norm": 1.7703112363815308, "learning_rate": 0.00016561579500849478, "loss": 0.5863692760467529, "step": 181270 }, { "epoch": 1.0775659658445829, "grad_norm": 1.8185697793960571, "learning_rate": 0.00016561090086958318, "loss": 0.676078462600708, "step": 181280 }, { "epoch": 1.077625407921251, "grad_norm": 1.487934947013855, "learning_rate": 0.0001656060064646472, "loss": 0.6095479011535645, "step": 181290 }, { "epoch": 1.0776848499979195, "grad_norm": 1.476059079170227, "learning_rate": 0.00016560111179371025, "loss": 0.6040441513061523, "step": 181300 }, { "epoch": 1.0777442920745879, "grad_norm": 1.4535623788833618, "learning_rate": 0.00016559621685679576, "loss": 0.6614205360412597, "step": 181310 }, { "epoch": 1.0778037341512563, "grad_norm": 1.4874625205993652, "learning_rate": 0.00016559132165392713, "loss": 0.6123913764953614, "step": 181320 }, { "epoch": 1.0778631762279247, "grad_norm": 1.8027070760726929, "learning_rate": 0.00016558642618512778, "loss": 0.6400262355804444, "step": 181330 }, { "epoch": 1.0779226183045931, "grad_norm": 1.4674266576766968, "learning_rate": 0.00016558153045042115, "loss": 0.6098210334777832, "step": 181340 }, { "epoch": 1.0779820603812615, "grad_norm": 1.6003000736236572, "learning_rate": 0.00016557663444983063, "loss": 0.6251388549804687, "step": 181350 }, { "epoch": 1.07804150245793, "grad_norm": 1.3823633193969727, "learning_rate": 0.00016557173818337965, "loss": 0.6131071090698242, "step": 181360 }, { "epoch": 1.0781009445345981, "grad_norm": 1.9739820957183838, "learning_rate": 0.00016556684165109164, "loss": 0.6437870979309082, "step": 181370 }, { "epoch": 1.0781603866112666, "grad_norm": 1.788156509399414, "learning_rate": 0.00016556194485299006, "loss": 0.7615781307220459, "step": 181380 }, { "epoch": 1.078219828687935, "grad_norm": 1.848855972290039, "learning_rate": 0.00016555704778909821, "loss": 0.6634895324707031, "step": 181390 }, { "epoch": 1.0782792707646034, "grad_norm": 1.5609054565429688, "learning_rate": 0.00016555215045943966, "loss": 0.6448164939880371, "step": 181400 }, { "epoch": 1.0783387128412718, "grad_norm": 1.4041246175765991, "learning_rate": 0.00016554725286403778, "loss": 0.5920844554901123, "step": 181410 }, { "epoch": 1.0783981549179402, "grad_norm": 1.7251014709472656, "learning_rate": 0.00016554235500291595, "loss": 0.6541006088256835, "step": 181420 }, { "epoch": 1.0784575969946086, "grad_norm": 1.7158485651016235, "learning_rate": 0.0001655374568760977, "loss": 0.6682814121246338, "step": 181430 }, { "epoch": 1.078517039071277, "grad_norm": 2.090017080307007, "learning_rate": 0.0001655325584836064, "loss": 0.61065673828125, "step": 181440 }, { "epoch": 1.0785764811479455, "grad_norm": 1.5587867498397827, "learning_rate": 0.00016552765982546543, "loss": 0.6478123664855957, "step": 181450 }, { "epoch": 1.0786359232246139, "grad_norm": 1.8331878185272217, "learning_rate": 0.00016552276090169832, "loss": 0.60732421875, "step": 181460 }, { "epoch": 1.078695365301282, "grad_norm": 1.6577951908111572, "learning_rate": 0.00016551786171232848, "loss": 0.5735078811645508, "step": 181470 }, { "epoch": 1.0787548073779505, "grad_norm": 1.5087110996246338, "learning_rate": 0.0001655129622573793, "loss": 0.6100321769714355, "step": 181480 }, { "epoch": 1.078814249454619, "grad_norm": 1.4445613622665405, "learning_rate": 0.00016550806253687428, "loss": 0.6666592597961426, "step": 181490 }, { "epoch": 1.0788736915312873, "grad_norm": 1.551971197128296, "learning_rate": 0.0001655031625508368, "loss": 0.6055720329284668, "step": 181500 }, { "epoch": 1.0789331336079557, "grad_norm": 1.395056128501892, "learning_rate": 0.00016549826229929037, "loss": 0.6099217414855957, "step": 181510 }, { "epoch": 1.0789925756846241, "grad_norm": 1.2285511493682861, "learning_rate": 0.00016549336178225835, "loss": 0.5584887504577637, "step": 181520 }, { "epoch": 1.0790520177612926, "grad_norm": 1.3282419443130493, "learning_rate": 0.00016548846099976425, "loss": 0.5845930099487304, "step": 181530 }, { "epoch": 1.079111459837961, "grad_norm": 1.3893646001815796, "learning_rate": 0.0001654835599518315, "loss": 0.5502427101135254, "step": 181540 }, { "epoch": 1.0791709019146294, "grad_norm": 2.190896987915039, "learning_rate": 0.0001654786586384835, "loss": 0.5982367515563964, "step": 181550 }, { "epoch": 1.0792303439912976, "grad_norm": 1.1204047203063965, "learning_rate": 0.00016547375705974372, "loss": 0.6045485496520996, "step": 181560 }, { "epoch": 1.079289786067966, "grad_norm": 2.0854744911193848, "learning_rate": 0.0001654688552156356, "loss": 0.6450698852539063, "step": 181570 }, { "epoch": 1.0793492281446344, "grad_norm": 1.5720473527908325, "learning_rate": 0.00016546395310618265, "loss": 0.6244043350219727, "step": 181580 }, { "epoch": 1.0794086702213028, "grad_norm": 1.2310255765914917, "learning_rate": 0.0001654590507314083, "loss": 0.6182847023010254, "step": 181590 }, { "epoch": 1.0794681122979712, "grad_norm": 1.552523136138916, "learning_rate": 0.00016545414809133593, "loss": 0.6571182250976563, "step": 181600 }, { "epoch": 1.0795275543746397, "grad_norm": 1.5766549110412598, "learning_rate": 0.00016544924518598902, "loss": 0.5928764343261719, "step": 181610 }, { "epoch": 1.079586996451308, "grad_norm": 1.409065842628479, "learning_rate": 0.0001654443420153911, "loss": 0.6401601314544678, "step": 181620 }, { "epoch": 1.0796464385279765, "grad_norm": 1.4342209100723267, "learning_rate": 0.00016543943857956551, "loss": 0.6422160148620606, "step": 181630 }, { "epoch": 1.079705880604645, "grad_norm": 1.761281967163086, "learning_rate": 0.0001654345348785358, "loss": 0.6033353805541992, "step": 181640 }, { "epoch": 1.0797653226813133, "grad_norm": 1.8010140657424927, "learning_rate": 0.00016542963091232537, "loss": 0.6581429958343505, "step": 181650 }, { "epoch": 1.0798247647579815, "grad_norm": 1.6541287899017334, "learning_rate": 0.0001654247266809577, "loss": 0.6431925296783447, "step": 181660 }, { "epoch": 1.07988420683465, "grad_norm": 1.597860336303711, "learning_rate": 0.0001654198221844563, "loss": 0.6656004905700683, "step": 181670 }, { "epoch": 1.0799436489113183, "grad_norm": 1.5266344547271729, "learning_rate": 0.0001654149174228445, "loss": 0.6619358062744141, "step": 181680 }, { "epoch": 1.0800030909879867, "grad_norm": 1.6493412256240845, "learning_rate": 0.00016541001239614588, "loss": 0.5808310508728027, "step": 181690 }, { "epoch": 1.0800625330646552, "grad_norm": 1.8665319681167603, "learning_rate": 0.00016540510710438388, "loss": 0.5787277221679688, "step": 181700 }, { "epoch": 1.0801219751413236, "grad_norm": 1.7092453241348267, "learning_rate": 0.00016540020154758194, "loss": 0.6273491859436036, "step": 181710 }, { "epoch": 1.080181417217992, "grad_norm": 1.7814903259277344, "learning_rate": 0.00016539529572576355, "loss": 0.6371813774108886, "step": 181720 }, { "epoch": 1.0802408592946604, "grad_norm": 1.317736268043518, "learning_rate": 0.0001653903896389522, "loss": 0.6204243659973144, "step": 181730 }, { "epoch": 1.0803003013713286, "grad_norm": 2.1969025135040283, "learning_rate": 0.00016538548328717126, "loss": 0.6617920875549317, "step": 181740 }, { "epoch": 1.080359743447997, "grad_norm": 2.1924548149108887, "learning_rate": 0.0001653805766704443, "loss": 0.6800484180450439, "step": 181750 }, { "epoch": 1.0804191855246654, "grad_norm": 1.7435181140899658, "learning_rate": 0.00016537566978879476, "loss": 0.6742833137512207, "step": 181760 }, { "epoch": 1.0804786276013338, "grad_norm": 1.4554721117019653, "learning_rate": 0.00016537076264224615, "loss": 0.6232837677001953, "step": 181770 }, { "epoch": 1.0805380696780023, "grad_norm": 1.5005594491958618, "learning_rate": 0.00016536585523082187, "loss": 0.650087547302246, "step": 181780 }, { "epoch": 1.0805975117546707, "grad_norm": 1.7115633487701416, "learning_rate": 0.0001653609475545454, "loss": 0.6222111701965332, "step": 181790 }, { "epoch": 1.080656953831339, "grad_norm": 1.9109740257263184, "learning_rate": 0.00016535603961344032, "loss": 0.6557214736938477, "step": 181800 }, { "epoch": 1.0807163959080075, "grad_norm": 1.3545604944229126, "learning_rate": 0.00016535113140752998, "loss": 0.6535942554473877, "step": 181810 }, { "epoch": 1.080775837984676, "grad_norm": 1.9132977724075317, "learning_rate": 0.00016534622293683793, "loss": 0.6336124420166016, "step": 181820 }, { "epoch": 1.0808352800613443, "grad_norm": 1.5048567056655884, "learning_rate": 0.00016534131420138767, "loss": 0.6140501976013184, "step": 181830 }, { "epoch": 1.0808947221380125, "grad_norm": 1.512020468711853, "learning_rate": 0.00016533640520120262, "loss": 0.6418728828430176, "step": 181840 }, { "epoch": 1.080954164214681, "grad_norm": 1.4883009195327759, "learning_rate": 0.00016533149593630627, "loss": 0.6134679794311524, "step": 181850 }, { "epoch": 1.0810136062913493, "grad_norm": 1.4287083148956299, "learning_rate": 0.00016532658640672215, "loss": 0.5907074928283691, "step": 181860 }, { "epoch": 1.0810730483680178, "grad_norm": 1.9973245859146118, "learning_rate": 0.00016532167661247374, "loss": 0.6774691104888916, "step": 181870 }, { "epoch": 1.0811324904446862, "grad_norm": 1.6446096897125244, "learning_rate": 0.0001653167665535845, "loss": 0.5792784690856934, "step": 181880 }, { "epoch": 1.0811919325213546, "grad_norm": 1.728028655052185, "learning_rate": 0.0001653118562300779, "loss": 0.6064732551574707, "step": 181890 }, { "epoch": 1.081251374598023, "grad_norm": 1.544851541519165, "learning_rate": 0.0001653069456419775, "loss": 0.6082162857055664, "step": 181900 }, { "epoch": 1.0813108166746914, "grad_norm": 1.6375315189361572, "learning_rate": 0.0001653020347893067, "loss": 0.6242118835449219, "step": 181910 }, { "epoch": 1.0813702587513598, "grad_norm": 1.9407933950424194, "learning_rate": 0.00016529712367208905, "loss": 0.5862013816833496, "step": 181920 }, { "epoch": 1.081429700828028, "grad_norm": 1.9772512912750244, "learning_rate": 0.00016529221229034805, "loss": 0.6017595767974854, "step": 181930 }, { "epoch": 1.0814891429046964, "grad_norm": 1.7547472715377808, "learning_rate": 0.00016528730064410718, "loss": 0.5873438835144043, "step": 181940 }, { "epoch": 1.0815485849813649, "grad_norm": 1.4135503768920898, "learning_rate": 0.00016528238873338993, "loss": 0.6420598983764648, "step": 181950 }, { "epoch": 1.0816080270580333, "grad_norm": 1.35709547996521, "learning_rate": 0.00016527747655821978, "loss": 0.6450617790222168, "step": 181960 }, { "epoch": 1.0816674691347017, "grad_norm": 1.5748255252838135, "learning_rate": 0.00016527256411862022, "loss": 0.6019648551940918, "step": 181970 }, { "epoch": 1.08172691121137, "grad_norm": 1.5753943920135498, "learning_rate": 0.00016526765141461485, "loss": 0.6053424835205078, "step": 181980 }, { "epoch": 1.0817863532880385, "grad_norm": 1.759932279586792, "learning_rate": 0.00016526273844622705, "loss": 0.6304709434509277, "step": 181990 }, { "epoch": 1.081845795364707, "grad_norm": 1.6807130575180054, "learning_rate": 0.00016525782521348037, "loss": 0.6307237625122071, "step": 182000 }, { "epoch": 1.0819052374413753, "grad_norm": 1.6754695177078247, "learning_rate": 0.00016525291171639832, "loss": 0.558552598953247, "step": 182010 }, { "epoch": 1.0819646795180438, "grad_norm": 1.8576215505599976, "learning_rate": 0.0001652479979550044, "loss": 0.6681602954864502, "step": 182020 }, { "epoch": 1.082024121594712, "grad_norm": 1.595950722694397, "learning_rate": 0.0001652430839293221, "loss": 0.6296582698822022, "step": 182030 }, { "epoch": 1.0820835636713804, "grad_norm": 1.4684580564498901, "learning_rate": 0.00016523816963937495, "loss": 0.6030779838562011, "step": 182040 }, { "epoch": 1.0821430057480488, "grad_norm": 1.6500909328460693, "learning_rate": 0.00016523325508518646, "loss": 0.7101536750793457, "step": 182050 }, { "epoch": 1.0822024478247172, "grad_norm": 1.5086345672607422, "learning_rate": 0.0001652283402667801, "loss": 0.6377080917358399, "step": 182060 }, { "epoch": 1.0822618899013856, "grad_norm": 1.7460715770721436, "learning_rate": 0.0001652234251841794, "loss": 0.5784000396728516, "step": 182070 }, { "epoch": 1.082321331978054, "grad_norm": 1.5804188251495361, "learning_rate": 0.00016521850983740793, "loss": 0.626859188079834, "step": 182080 }, { "epoch": 1.0823807740547224, "grad_norm": 1.3805015087127686, "learning_rate": 0.00016521359422648913, "loss": 0.6532055854797363, "step": 182090 }, { "epoch": 1.0824402161313909, "grad_norm": 1.393791675567627, "learning_rate": 0.00016520867835144654, "loss": 0.6063296318054199, "step": 182100 }, { "epoch": 1.082499658208059, "grad_norm": 1.8634283542633057, "learning_rate": 0.0001652037622123037, "loss": 0.6459625244140625, "step": 182110 }, { "epoch": 1.0825591002847275, "grad_norm": 1.4621084928512573, "learning_rate": 0.00016519884580908407, "loss": 0.634366798400879, "step": 182120 }, { "epoch": 1.0826185423613959, "grad_norm": 1.2788259983062744, "learning_rate": 0.0001651939291418112, "loss": 0.6838230609893798, "step": 182130 }, { "epoch": 1.0826779844380643, "grad_norm": 1.4643744230270386, "learning_rate": 0.0001651890122105086, "loss": 0.6442543506622315, "step": 182140 }, { "epoch": 1.0827374265147327, "grad_norm": 1.6988084316253662, "learning_rate": 0.00016518409501519986, "loss": 0.6410057544708252, "step": 182150 }, { "epoch": 1.0827968685914011, "grad_norm": 1.6280784606933594, "learning_rate": 0.0001651791775559084, "loss": 0.6387715339660645, "step": 182160 }, { "epoch": 1.0828563106680695, "grad_norm": 1.5089364051818848, "learning_rate": 0.00016517425983265778, "loss": 0.6073167800903321, "step": 182170 }, { "epoch": 1.082915752744738, "grad_norm": 2.3183536529541016, "learning_rate": 0.00016516934184547156, "loss": 0.6330137252807617, "step": 182180 }, { "epoch": 1.0829751948214064, "grad_norm": 1.4243190288543701, "learning_rate": 0.0001651644235943732, "loss": 0.6330469608306885, "step": 182190 }, { "epoch": 1.0830346368980748, "grad_norm": 1.1905326843261719, "learning_rate": 0.00016515950507938628, "loss": 0.6794084548950196, "step": 182200 }, { "epoch": 1.083094078974743, "grad_norm": 1.9411154985427856, "learning_rate": 0.00016515458630053437, "loss": 0.6583109855651855, "step": 182210 }, { "epoch": 1.0831535210514114, "grad_norm": 1.3550317287445068, "learning_rate": 0.00016514966725784085, "loss": 0.6450250148773193, "step": 182220 }, { "epoch": 1.0832129631280798, "grad_norm": 2.066309928894043, "learning_rate": 0.00016514474795132941, "loss": 0.6918922901153565, "step": 182230 }, { "epoch": 1.0832724052047482, "grad_norm": 1.7170363664627075, "learning_rate": 0.00016513982838102352, "loss": 0.611954927444458, "step": 182240 }, { "epoch": 1.0833318472814166, "grad_norm": 1.4253263473510742, "learning_rate": 0.00016513490854694666, "loss": 0.6180314064025879, "step": 182250 }, { "epoch": 1.083391289358085, "grad_norm": 1.74718177318573, "learning_rate": 0.00016512998844912244, "loss": 0.6325878143310547, "step": 182260 }, { "epoch": 1.0834507314347535, "grad_norm": 1.692989706993103, "learning_rate": 0.00016512506808757439, "loss": 0.5925541400909424, "step": 182270 }, { "epoch": 1.0835101735114219, "grad_norm": 1.4354569911956787, "learning_rate": 0.000165120147462326, "loss": 0.5754025936126709, "step": 182280 }, { "epoch": 1.0835696155880903, "grad_norm": 1.7216637134552002, "learning_rate": 0.00016511522657340085, "loss": 0.645721435546875, "step": 182290 }, { "epoch": 1.0836290576647585, "grad_norm": 1.6056674718856812, "learning_rate": 0.0001651103054208225, "loss": 0.6246827125549317, "step": 182300 }, { "epoch": 1.083688499741427, "grad_norm": 1.4776146411895752, "learning_rate": 0.00016510538400461443, "loss": 0.6556703567504882, "step": 182310 }, { "epoch": 1.0837479418180953, "grad_norm": 1.6744391918182373, "learning_rate": 0.0001651004623248002, "loss": 0.6689682960510254, "step": 182320 }, { "epoch": 1.0838073838947637, "grad_norm": 1.4537700414657593, "learning_rate": 0.0001650955403814034, "loss": 0.6112603187561035, "step": 182330 }, { "epoch": 1.0838668259714321, "grad_norm": 1.4179656505584717, "learning_rate": 0.00016509061817444748, "loss": 0.664330530166626, "step": 182340 }, { "epoch": 1.0839262680481005, "grad_norm": 1.6630070209503174, "learning_rate": 0.0001650856957039561, "loss": 0.5777112960815429, "step": 182350 }, { "epoch": 1.083985710124769, "grad_norm": 1.5167102813720703, "learning_rate": 0.00016508077296995276, "loss": 0.6084437847137452, "step": 182360 }, { "epoch": 1.0840451522014374, "grad_norm": 1.4991436004638672, "learning_rate": 0.00016507584997246095, "loss": 0.6496729373931884, "step": 182370 }, { "epoch": 1.0841045942781058, "grad_norm": 1.4481068849563599, "learning_rate": 0.0001650709267115043, "loss": 0.6449908256530762, "step": 182380 }, { "epoch": 1.0841640363547742, "grad_norm": 1.4074639081954956, "learning_rate": 0.00016506600318710635, "loss": 0.6332881927490235, "step": 182390 }, { "epoch": 1.0842234784314424, "grad_norm": 1.4515657424926758, "learning_rate": 0.00016506107939929062, "loss": 0.6138092041015625, "step": 182400 }, { "epoch": 1.0842829205081108, "grad_norm": 1.3054875135421753, "learning_rate": 0.00016505615534808069, "loss": 0.590904712677002, "step": 182410 }, { "epoch": 1.0843423625847792, "grad_norm": 1.5607937574386597, "learning_rate": 0.0001650512310335001, "loss": 0.6207474708557129, "step": 182420 }, { "epoch": 1.0844018046614476, "grad_norm": 1.8678752183914185, "learning_rate": 0.0001650463064555724, "loss": 0.6088198661804199, "step": 182430 }, { "epoch": 1.084461246738116, "grad_norm": 1.3131089210510254, "learning_rate": 0.0001650413816143212, "loss": 0.5597879886627197, "step": 182440 }, { "epoch": 1.0845206888147845, "grad_norm": 1.3176835775375366, "learning_rate": 0.00016503645650976995, "loss": 0.6354148864746094, "step": 182450 }, { "epoch": 1.0845801308914529, "grad_norm": 1.792855978012085, "learning_rate": 0.00016503153114194233, "loss": 0.6427209854125977, "step": 182460 }, { "epoch": 1.0846395729681213, "grad_norm": 1.2238904237747192, "learning_rate": 0.00016502660551086183, "loss": 0.6474028587341308, "step": 182470 }, { "epoch": 1.0846990150447895, "grad_norm": 1.9389382600784302, "learning_rate": 0.00016502167961655203, "loss": 0.6423508167266846, "step": 182480 }, { "epoch": 1.084758457121458, "grad_norm": 1.8429579734802246, "learning_rate": 0.00016501675345903652, "loss": 0.6102463722229003, "step": 182490 }, { "epoch": 1.0848178991981263, "grad_norm": 1.7891912460327148, "learning_rate": 0.00016501182703833884, "loss": 0.6711145401000976, "step": 182500 }, { "epoch": 1.0848773412747947, "grad_norm": 1.784530520439148, "learning_rate": 0.00016500690035448255, "loss": 0.606772518157959, "step": 182510 }, { "epoch": 1.0849367833514632, "grad_norm": 1.527679681777954, "learning_rate": 0.0001650019734074912, "loss": 0.6054492950439453, "step": 182520 }, { "epoch": 1.0849962254281316, "grad_norm": 1.7148067951202393, "learning_rate": 0.0001649970461973884, "loss": 0.6258053779602051, "step": 182530 }, { "epoch": 1.0850556675048, "grad_norm": 1.841321587562561, "learning_rate": 0.00016499211872419772, "loss": 0.6458923816680908, "step": 182540 }, { "epoch": 1.0851151095814684, "grad_norm": 1.4608334302902222, "learning_rate": 0.0001649871909879427, "loss": 0.642152976989746, "step": 182550 }, { "epoch": 1.0851745516581368, "grad_norm": 1.699509620666504, "learning_rate": 0.0001649822629886469, "loss": 0.5383689880371094, "step": 182560 }, { "epoch": 1.0852339937348052, "grad_norm": 1.6060506105422974, "learning_rate": 0.000164977334726334, "loss": 0.6166407585144043, "step": 182570 }, { "epoch": 1.0852934358114734, "grad_norm": 1.6158121824264526, "learning_rate": 0.00016497240620102745, "loss": 0.6669100761413574, "step": 182580 }, { "epoch": 1.0853528778881418, "grad_norm": 1.5063852071762085, "learning_rate": 0.00016496747741275085, "loss": 0.5988527774810791, "step": 182590 }, { "epoch": 1.0854123199648102, "grad_norm": 1.4991587400436401, "learning_rate": 0.00016496254836152781, "loss": 0.5763960838317871, "step": 182600 }, { "epoch": 1.0854717620414787, "grad_norm": 1.2248070240020752, "learning_rate": 0.0001649576190473819, "loss": 0.5958327293395996, "step": 182610 }, { "epoch": 1.085531204118147, "grad_norm": 1.7913262844085693, "learning_rate": 0.00016495268947033676, "loss": 0.6771498680114746, "step": 182620 }, { "epoch": 1.0855906461948155, "grad_norm": 1.8360620737075806, "learning_rate": 0.00016494775963041587, "loss": 0.6584591865539551, "step": 182630 }, { "epoch": 1.085650088271484, "grad_norm": 1.1587998867034912, "learning_rate": 0.00016494282952764285, "loss": 0.6370501041412353, "step": 182640 }, { "epoch": 1.0857095303481523, "grad_norm": 1.6252931356430054, "learning_rate": 0.0001649378991620413, "loss": 0.6405082225799561, "step": 182650 }, { "epoch": 1.0857689724248207, "grad_norm": 2.286398410797119, "learning_rate": 0.0001649329685336348, "loss": 0.6246139526367187, "step": 182660 }, { "epoch": 1.085828414501489, "grad_norm": 1.5963616371154785, "learning_rate": 0.00016492803764244692, "loss": 0.6200469970703125, "step": 182670 }, { "epoch": 1.0858878565781573, "grad_norm": 1.5980287790298462, "learning_rate": 0.00016492310648850124, "loss": 0.6415622234344482, "step": 182680 }, { "epoch": 1.0859472986548258, "grad_norm": 1.419758677482605, "learning_rate": 0.0001649181750718214, "loss": 0.6396785736083984, "step": 182690 }, { "epoch": 1.0860067407314942, "grad_norm": 1.735634684562683, "learning_rate": 0.00016491324339243092, "loss": 0.6683456420898437, "step": 182700 }, { "epoch": 1.0860661828081626, "grad_norm": 1.8823727369308472, "learning_rate": 0.00016490831145035345, "loss": 0.6362978458404541, "step": 182710 }, { "epoch": 1.086125624884831, "grad_norm": 1.6094402074813843, "learning_rate": 0.00016490337924561258, "loss": 0.6317086219787598, "step": 182720 }, { "epoch": 1.0861850669614994, "grad_norm": 1.3355023860931396, "learning_rate": 0.00016489844677823186, "loss": 0.6243313789367676, "step": 182730 }, { "epoch": 1.0862445090381678, "grad_norm": 1.3983594179153442, "learning_rate": 0.0001648935140482349, "loss": 0.6058607578277588, "step": 182740 }, { "epoch": 1.0863039511148362, "grad_norm": 1.6393378973007202, "learning_rate": 0.00016488858105564536, "loss": 0.5967730522155762, "step": 182750 }, { "epoch": 1.0863633931915047, "grad_norm": 1.8010578155517578, "learning_rate": 0.00016488364780048678, "loss": 0.6747358322143555, "step": 182760 }, { "epoch": 1.0864228352681728, "grad_norm": 1.465851902961731, "learning_rate": 0.00016487871428278272, "loss": 0.5895632743835449, "step": 182770 }, { "epoch": 1.0864822773448413, "grad_norm": 1.7967126369476318, "learning_rate": 0.00016487378050255685, "loss": 0.6329363822937012, "step": 182780 }, { "epoch": 1.0865417194215097, "grad_norm": 2.041290521621704, "learning_rate": 0.00016486884645983274, "loss": 0.6765549659729004, "step": 182790 }, { "epoch": 1.086601161498178, "grad_norm": 1.8741090297698975, "learning_rate": 0.000164863912154634, "loss": 0.6353316307067871, "step": 182800 }, { "epoch": 1.0866606035748465, "grad_norm": 1.746057152748108, "learning_rate": 0.00016485897758698425, "loss": 0.6409254550933838, "step": 182810 }, { "epoch": 1.086720045651515, "grad_norm": 1.9728584289550781, "learning_rate": 0.00016485404275690707, "loss": 0.6312102317810059, "step": 182820 }, { "epoch": 1.0867794877281833, "grad_norm": 1.6259987354278564, "learning_rate": 0.00016484910766442607, "loss": 0.639014482498169, "step": 182830 }, { "epoch": 1.0868389298048517, "grad_norm": 2.01546049118042, "learning_rate": 0.00016484417230956485, "loss": 0.6222167491912842, "step": 182840 }, { "epoch": 1.08689837188152, "grad_norm": 2.0124523639678955, "learning_rate": 0.00016483923669234708, "loss": 0.6556228637695313, "step": 182850 }, { "epoch": 1.0869578139581884, "grad_norm": 1.7511793375015259, "learning_rate": 0.00016483430081279626, "loss": 0.595227575302124, "step": 182860 }, { "epoch": 1.0870172560348568, "grad_norm": 1.3107017278671265, "learning_rate": 0.00016482936467093612, "loss": 0.6354601860046387, "step": 182870 }, { "epoch": 1.0870766981115252, "grad_norm": 2.0008108615875244, "learning_rate": 0.00016482442826679021, "loss": 0.6377870559692382, "step": 182880 }, { "epoch": 1.0871361401881936, "grad_norm": 1.385252594947815, "learning_rate": 0.00016481949160038211, "loss": 0.652254867553711, "step": 182890 }, { "epoch": 1.087195582264862, "grad_norm": 1.522803544998169, "learning_rate": 0.00016481455467173554, "loss": 0.6885712623596192, "step": 182900 }, { "epoch": 1.0872550243415304, "grad_norm": 1.597619891166687, "learning_rate": 0.000164809617480874, "loss": 0.6229487419128418, "step": 182910 }, { "epoch": 1.0873144664181988, "grad_norm": 1.4658641815185547, "learning_rate": 0.0001648046800278212, "loss": 0.5906540393829346, "step": 182920 }, { "epoch": 1.0873739084948673, "grad_norm": 1.3113640546798706, "learning_rate": 0.0001647997423126007, "loss": 0.603737211227417, "step": 182930 }, { "epoch": 1.0874333505715357, "grad_norm": 1.6428213119506836, "learning_rate": 0.00016479480433523612, "loss": 0.6146012306213379, "step": 182940 }, { "epoch": 1.0874927926482039, "grad_norm": 1.5286097526550293, "learning_rate": 0.00016478986609575114, "loss": 0.5830336570739746, "step": 182950 }, { "epoch": 1.0875522347248723, "grad_norm": 1.1679561138153076, "learning_rate": 0.00016478492759416932, "loss": 0.5573811531066895, "step": 182960 }, { "epoch": 1.0876116768015407, "grad_norm": 1.8463234901428223, "learning_rate": 0.00016477998883051434, "loss": 0.5787568092346191, "step": 182970 }, { "epoch": 1.087671118878209, "grad_norm": 1.6737151145935059, "learning_rate": 0.0001647750498048098, "loss": 0.5670985221862793, "step": 182980 }, { "epoch": 1.0877305609548775, "grad_norm": 1.6772701740264893, "learning_rate": 0.0001647701105170793, "loss": 0.6448030948638916, "step": 182990 }, { "epoch": 1.087790003031546, "grad_norm": 1.8163377046585083, "learning_rate": 0.00016476517096734647, "loss": 0.6291627407073974, "step": 183000 }, { "epoch": 1.0878494451082144, "grad_norm": 1.5728673934936523, "learning_rate": 0.00016476023115563499, "loss": 0.649342155456543, "step": 183010 }, { "epoch": 1.0879088871848828, "grad_norm": 1.5518378019332886, "learning_rate": 0.00016475529108196844, "loss": 0.5725625038146973, "step": 183020 }, { "epoch": 1.0879683292615512, "grad_norm": 1.6565970182418823, "learning_rate": 0.0001647503507463705, "loss": 0.6320058345794678, "step": 183030 }, { "epoch": 1.0880277713382194, "grad_norm": 1.4437403678894043, "learning_rate": 0.00016474541014886476, "loss": 0.6380767345428466, "step": 183040 }, { "epoch": 1.0880872134148878, "grad_norm": 1.4959769248962402, "learning_rate": 0.00016474046928947487, "loss": 0.644411849975586, "step": 183050 }, { "epoch": 1.0881466554915562, "grad_norm": 1.4369925260543823, "learning_rate": 0.00016473552816822446, "loss": 0.6082145690917968, "step": 183060 }, { "epoch": 1.0882060975682246, "grad_norm": 1.3740794658660889, "learning_rate": 0.00016473058678513717, "loss": 0.6749321937561035, "step": 183070 }, { "epoch": 1.088265539644893, "grad_norm": 1.8198589086532593, "learning_rate": 0.00016472564514023665, "loss": 0.6619937896728516, "step": 183080 }, { "epoch": 1.0883249817215614, "grad_norm": 1.8484176397323608, "learning_rate": 0.00016472070323354652, "loss": 0.6570418834686279, "step": 183090 }, { "epoch": 1.0883844237982299, "grad_norm": 1.342604398727417, "learning_rate": 0.0001647157610650904, "loss": 0.6328964233398438, "step": 183100 }, { "epoch": 1.0884438658748983, "grad_norm": 2.2984442710876465, "learning_rate": 0.000164710818634892, "loss": 0.6765944480895996, "step": 183110 }, { "epoch": 1.0885033079515667, "grad_norm": 1.4910860061645508, "learning_rate": 0.0001647058759429749, "loss": 0.573567008972168, "step": 183120 }, { "epoch": 1.088562750028235, "grad_norm": 1.6021389961242676, "learning_rate": 0.0001647009329893628, "loss": 0.6651859760284424, "step": 183130 }, { "epoch": 1.0886221921049033, "grad_norm": 1.5324467420578003, "learning_rate": 0.00016469598977407931, "loss": 0.696665096282959, "step": 183140 }, { "epoch": 1.0886816341815717, "grad_norm": 1.518821120262146, "learning_rate": 0.00016469104629714804, "loss": 0.6595668792724609, "step": 183150 }, { "epoch": 1.0887410762582401, "grad_norm": 1.9320098161697388, "learning_rate": 0.0001646861025585927, "loss": 0.5931515693664551, "step": 183160 }, { "epoch": 1.0888005183349085, "grad_norm": 1.6724451780319214, "learning_rate": 0.0001646811585584369, "loss": 0.6140119075775147, "step": 183170 }, { "epoch": 1.088859960411577, "grad_norm": 1.745048999786377, "learning_rate": 0.00016467621429670434, "loss": 0.5489925861358642, "step": 183180 }, { "epoch": 1.0889194024882454, "grad_norm": 1.7472001314163208, "learning_rate": 0.00016467126977341863, "loss": 0.6723911762237549, "step": 183190 }, { "epoch": 1.0889788445649138, "grad_norm": 1.6026856899261475, "learning_rate": 0.00016466632498860344, "loss": 0.6844043254852294, "step": 183200 }, { "epoch": 1.0890382866415822, "grad_norm": 2.2948858737945557, "learning_rate": 0.00016466137994228242, "loss": 0.6460270881652832, "step": 183210 }, { "epoch": 1.0890977287182504, "grad_norm": 1.8340550661087036, "learning_rate": 0.00016465643463447918, "loss": 0.6045906066894531, "step": 183220 }, { "epoch": 1.0891571707949188, "grad_norm": 1.481217861175537, "learning_rate": 0.00016465148906521745, "loss": 0.6076282501220703, "step": 183230 }, { "epoch": 1.0892166128715872, "grad_norm": 1.813062071800232, "learning_rate": 0.00016464654323452088, "loss": 0.5860452651977539, "step": 183240 }, { "epoch": 1.0892760549482556, "grad_norm": 1.9615055322647095, "learning_rate": 0.00016464159714241303, "loss": 0.6169548988342285, "step": 183250 }, { "epoch": 1.089335497024924, "grad_norm": 1.9278044700622559, "learning_rate": 0.00016463665078891767, "loss": 0.5940101146697998, "step": 183260 }, { "epoch": 1.0893949391015925, "grad_norm": 1.488102912902832, "learning_rate": 0.00016463170417405846, "loss": 0.6526867866516113, "step": 183270 }, { "epoch": 1.0894543811782609, "grad_norm": 1.6717203855514526, "learning_rate": 0.000164626757297859, "loss": 0.636718463897705, "step": 183280 }, { "epoch": 1.0895138232549293, "grad_norm": 1.6903537511825562, "learning_rate": 0.00016462181016034302, "loss": 0.6110917568206787, "step": 183290 }, { "epoch": 1.0895732653315977, "grad_norm": 1.330881953239441, "learning_rate": 0.00016461686276153411, "loss": 0.570035171508789, "step": 183300 }, { "epoch": 1.0896327074082661, "grad_norm": 1.8288995027542114, "learning_rate": 0.00016461191510145598, "loss": 0.6725705146789551, "step": 183310 }, { "epoch": 1.0896921494849343, "grad_norm": 1.8904699087142944, "learning_rate": 0.00016460696718013235, "loss": 0.6435420989990235, "step": 183320 }, { "epoch": 1.0897515915616027, "grad_norm": 1.2918275594711304, "learning_rate": 0.00016460201899758678, "loss": 0.6284185409545898, "step": 183330 }, { "epoch": 1.0898110336382711, "grad_norm": 1.479324221611023, "learning_rate": 0.000164597070553843, "loss": 0.6058911800384521, "step": 183340 }, { "epoch": 1.0898704757149396, "grad_norm": 1.9930869340896606, "learning_rate": 0.0001645921218489247, "loss": 0.6632673263549804, "step": 183350 }, { "epoch": 1.089929917791608, "grad_norm": 2.0182034969329834, "learning_rate": 0.0001645871728828555, "loss": 0.6018857479095459, "step": 183360 }, { "epoch": 1.0899893598682764, "grad_norm": 1.7051223516464233, "learning_rate": 0.00016458222365565913, "loss": 0.6251742362976074, "step": 183370 }, { "epoch": 1.0900488019449448, "grad_norm": 1.4971116781234741, "learning_rate": 0.00016457727416735923, "loss": 0.635691785812378, "step": 183380 }, { "epoch": 1.0901082440216132, "grad_norm": 1.7823718786239624, "learning_rate": 0.0001645723244179795, "loss": 0.6123401641845703, "step": 183390 }, { "epoch": 1.0901676860982816, "grad_norm": 1.3324828147888184, "learning_rate": 0.00016456737440754358, "loss": 0.5771878242492676, "step": 183400 }, { "epoch": 1.0902271281749498, "grad_norm": 1.521438717842102, "learning_rate": 0.0001645624241360752, "loss": 0.6101752281188965, "step": 183410 }, { "epoch": 1.0902865702516182, "grad_norm": 1.8160899877548218, "learning_rate": 0.000164557473603598, "loss": 0.6117561340332032, "step": 183420 }, { "epoch": 1.0903460123282867, "grad_norm": 1.8160693645477295, "learning_rate": 0.00016455252281013567, "loss": 0.6207223415374756, "step": 183430 }, { "epoch": 1.090405454404955, "grad_norm": 2.008176565170288, "learning_rate": 0.0001645475717557119, "loss": 0.654448413848877, "step": 183440 }, { "epoch": 1.0904648964816235, "grad_norm": 1.3313201665878296, "learning_rate": 0.00016454262044035038, "loss": 0.6565797805786133, "step": 183450 }, { "epoch": 1.090524338558292, "grad_norm": 1.9138610363006592, "learning_rate": 0.00016453766886407478, "loss": 0.5963742733001709, "step": 183460 }, { "epoch": 1.0905837806349603, "grad_norm": 1.6950864791870117, "learning_rate": 0.0001645327170269088, "loss": 0.6529661178588867, "step": 183470 }, { "epoch": 1.0906432227116287, "grad_norm": 1.7765743732452393, "learning_rate": 0.00016452776492887613, "loss": 0.5662569999694824, "step": 183480 }, { "epoch": 1.0907026647882971, "grad_norm": 1.5813591480255127, "learning_rate": 0.00016452281257000044, "loss": 0.5905407905578614, "step": 183490 }, { "epoch": 1.0907621068649653, "grad_norm": 1.845589280128479, "learning_rate": 0.00016451785995030545, "loss": 0.5939818382263183, "step": 183500 }, { "epoch": 1.0908215489416337, "grad_norm": 1.2753610610961914, "learning_rate": 0.00016451290706981483, "loss": 0.5820460319519043, "step": 183510 }, { "epoch": 1.0908809910183022, "grad_norm": 1.5338283777236938, "learning_rate": 0.00016450795392855227, "loss": 0.5829318046569825, "step": 183520 }, { "epoch": 1.0909404330949706, "grad_norm": 1.4902042150497437, "learning_rate": 0.0001645030005265415, "loss": 0.6828105926513672, "step": 183530 }, { "epoch": 1.090999875171639, "grad_norm": 1.6068103313446045, "learning_rate": 0.0001644980468638061, "loss": 0.6209062576293946, "step": 183540 }, { "epoch": 1.0910593172483074, "grad_norm": 1.388168215751648, "learning_rate": 0.00016449309294036993, "loss": 0.5871271133422852, "step": 183550 }, { "epoch": 1.0911187593249758, "grad_norm": 1.7627220153808594, "learning_rate": 0.0001644881387562566, "loss": 0.6244346618652343, "step": 183560 }, { "epoch": 1.0911782014016442, "grad_norm": 1.7466639280319214, "learning_rate": 0.00016448318431148986, "loss": 0.620057487487793, "step": 183570 }, { "epoch": 1.0912376434783126, "grad_norm": 1.2096558809280396, "learning_rate": 0.00016447822960609333, "loss": 0.5698068618774415, "step": 183580 }, { "epoch": 1.0912970855549808, "grad_norm": 1.814396858215332, "learning_rate": 0.00016447327464009072, "loss": 0.5995406150817871, "step": 183590 }, { "epoch": 1.0913565276316493, "grad_norm": 1.6376826763153076, "learning_rate": 0.0001644683194135058, "loss": 0.6011777877807617, "step": 183600 }, { "epoch": 1.0914159697083177, "grad_norm": 1.5119858980178833, "learning_rate": 0.00016446336392636225, "loss": 0.5984576225280762, "step": 183610 }, { "epoch": 1.091475411784986, "grad_norm": 1.5638225078582764, "learning_rate": 0.00016445840817868375, "loss": 0.6941761493682861, "step": 183620 }, { "epoch": 1.0915348538616545, "grad_norm": 1.8993817567825317, "learning_rate": 0.00016445345217049403, "loss": 0.6501265048980713, "step": 183630 }, { "epoch": 1.091594295938323, "grad_norm": 1.7073191404342651, "learning_rate": 0.0001644484959018168, "loss": 0.595461654663086, "step": 183640 }, { "epoch": 1.0916537380149913, "grad_norm": 2.15891695022583, "learning_rate": 0.00016444353937267574, "loss": 0.5673629760742187, "step": 183650 }, { "epoch": 1.0917131800916597, "grad_norm": 1.575086236000061, "learning_rate": 0.00016443858258309457, "loss": 0.6168071269989014, "step": 183660 }, { "epoch": 1.0917726221683282, "grad_norm": 1.7835720777511597, "learning_rate": 0.00016443362553309704, "loss": 0.6303656578063965, "step": 183670 }, { "epoch": 1.0918320642449966, "grad_norm": 1.6053141355514526, "learning_rate": 0.00016442866822270684, "loss": 0.6706520080566406, "step": 183680 }, { "epoch": 1.0918915063216648, "grad_norm": 1.535859227180481, "learning_rate": 0.00016442371065194763, "loss": 0.6821057319641113, "step": 183690 }, { "epoch": 1.0919509483983332, "grad_norm": 1.5377757549285889, "learning_rate": 0.00016441875282084326, "loss": 0.6463085174560547, "step": 183700 }, { "epoch": 1.0920103904750016, "grad_norm": 1.3047963380813599, "learning_rate": 0.00016441379472941726, "loss": 0.5793344020843506, "step": 183710 }, { "epoch": 1.09206983255167, "grad_norm": 1.4493266344070435, "learning_rate": 0.0001644088363776935, "loss": 0.5925710678100586, "step": 183720 }, { "epoch": 1.0921292746283384, "grad_norm": 1.44927978515625, "learning_rate": 0.00016440387776569566, "loss": 0.6519709587097168, "step": 183730 }, { "epoch": 1.0921887167050068, "grad_norm": 1.9677852392196655, "learning_rate": 0.00016439891889344742, "loss": 0.631613302230835, "step": 183740 }, { "epoch": 1.0922481587816752, "grad_norm": 1.1223382949829102, "learning_rate": 0.00016439395976097256, "loss": 0.6400226593017578, "step": 183750 }, { "epoch": 1.0923076008583437, "grad_norm": 1.7161585092544556, "learning_rate": 0.00016438900036829478, "loss": 0.6767582416534423, "step": 183760 }, { "epoch": 1.092367042935012, "grad_norm": 1.7794840335845947, "learning_rate": 0.00016438404071543773, "loss": 0.6286050796508789, "step": 183770 }, { "epoch": 1.0924264850116803, "grad_norm": 1.7406202554702759, "learning_rate": 0.00016437908080242525, "loss": 0.671603775024414, "step": 183780 }, { "epoch": 1.0924859270883487, "grad_norm": 1.4831335544586182, "learning_rate": 0.00016437412062928104, "loss": 0.6453009128570557, "step": 183790 }, { "epoch": 1.092545369165017, "grad_norm": 1.3842800855636597, "learning_rate": 0.00016436916019602874, "loss": 0.6565681457519531, "step": 183800 }, { "epoch": 1.0926048112416855, "grad_norm": 1.9663187265396118, "learning_rate": 0.0001643641995026922, "loss": 0.5992605209350585, "step": 183810 }, { "epoch": 1.092664253318354, "grad_norm": 1.1515856981277466, "learning_rate": 0.00016435923854929508, "loss": 0.6317222118377686, "step": 183820 }, { "epoch": 1.0927236953950223, "grad_norm": 1.3770571947097778, "learning_rate": 0.00016435427733586114, "loss": 0.6056076049804687, "step": 183830 }, { "epoch": 1.0927831374716908, "grad_norm": 1.8104041814804077, "learning_rate": 0.0001643493158624141, "loss": 0.6439969539642334, "step": 183840 }, { "epoch": 1.0928425795483592, "grad_norm": 1.2605667114257812, "learning_rate": 0.00016434435412897766, "loss": 0.6789797782897949, "step": 183850 }, { "epoch": 1.0929020216250276, "grad_norm": 1.5950530767440796, "learning_rate": 0.0001643393921355756, "loss": 0.6847669601440429, "step": 183860 }, { "epoch": 1.0929614637016958, "grad_norm": 1.8056581020355225, "learning_rate": 0.00016433442988223168, "loss": 0.6351505279541015, "step": 183870 }, { "epoch": 1.0930209057783642, "grad_norm": 1.5006440877914429, "learning_rate": 0.00016432946736896957, "loss": 0.5804886817932129, "step": 183880 }, { "epoch": 1.0930803478550326, "grad_norm": 1.5249855518341064, "learning_rate": 0.00016432450459581308, "loss": 0.6137961387634278, "step": 183890 }, { "epoch": 1.093139789931701, "grad_norm": 1.7682359218597412, "learning_rate": 0.0001643195415627859, "loss": 0.6889891624450684, "step": 183900 }, { "epoch": 1.0931992320083694, "grad_norm": 2.0092897415161133, "learning_rate": 0.00016431457826991176, "loss": 0.5947815895080566, "step": 183910 }, { "epoch": 1.0932586740850379, "grad_norm": 2.155629873275757, "learning_rate": 0.00016430961471721443, "loss": 0.6601975440979004, "step": 183920 }, { "epoch": 1.0933181161617063, "grad_norm": 1.5004454851150513, "learning_rate": 0.00016430465090471765, "loss": 0.6344603538513184, "step": 183930 }, { "epoch": 1.0933775582383747, "grad_norm": 1.3385494947433472, "learning_rate": 0.0001642996868324452, "loss": 0.5971457958221436, "step": 183940 }, { "epoch": 1.093437000315043, "grad_norm": 1.5798054933547974, "learning_rate": 0.00016429472250042076, "loss": 0.619030237197876, "step": 183950 }, { "epoch": 1.0934964423917113, "grad_norm": 1.8670597076416016, "learning_rate": 0.00016428975790866814, "loss": 0.6160138607025146, "step": 183960 }, { "epoch": 1.0935558844683797, "grad_norm": 1.8061506748199463, "learning_rate": 0.00016428479305721102, "loss": 0.5875054359436035, "step": 183970 }, { "epoch": 1.0936153265450481, "grad_norm": 1.5839240550994873, "learning_rate": 0.00016427982794607322, "loss": 0.6386429309844971, "step": 183980 }, { "epoch": 1.0936747686217165, "grad_norm": 1.7284198999404907, "learning_rate": 0.00016427486257527846, "loss": 0.5906916618347168, "step": 183990 }, { "epoch": 1.093734210698385, "grad_norm": 1.937895655632019, "learning_rate": 0.00016426989694485051, "loss": 0.6176029205322265, "step": 184000 }, { "epoch": 1.0937936527750534, "grad_norm": 1.291210651397705, "learning_rate": 0.00016426493105481312, "loss": 0.6080012321472168, "step": 184010 }, { "epoch": 1.0938530948517218, "grad_norm": 1.1208337545394897, "learning_rate": 0.00016425996490518997, "loss": 0.6006065845489502, "step": 184020 }, { "epoch": 1.0939125369283902, "grad_norm": 1.9423491954803467, "learning_rate": 0.00016425499849600492, "loss": 0.6192656517028808, "step": 184030 }, { "epoch": 1.0939719790050586, "grad_norm": 1.7998857498168945, "learning_rate": 0.0001642500318272817, "loss": 0.6054942607879639, "step": 184040 }, { "epoch": 1.094031421081727, "grad_norm": 2.166541576385498, "learning_rate": 0.00016424506489904402, "loss": 0.6358580112457275, "step": 184050 }, { "epoch": 1.0940908631583952, "grad_norm": 1.6123417615890503, "learning_rate": 0.0001642400977113157, "loss": 0.6926022529602051, "step": 184060 }, { "epoch": 1.0941503052350636, "grad_norm": 1.9538321495056152, "learning_rate": 0.0001642351302641205, "loss": 0.5796493530273438, "step": 184070 }, { "epoch": 1.094209747311732, "grad_norm": 1.5648869276046753, "learning_rate": 0.00016423016255748211, "loss": 0.644719123840332, "step": 184080 }, { "epoch": 1.0942691893884005, "grad_norm": 1.326696515083313, "learning_rate": 0.00016422519459142438, "loss": 0.649239444732666, "step": 184090 }, { "epoch": 1.0943286314650689, "grad_norm": 1.6934287548065186, "learning_rate": 0.00016422022636597105, "loss": 0.5909824848175049, "step": 184100 }, { "epoch": 1.0943880735417373, "grad_norm": 1.4189977645874023, "learning_rate": 0.00016421525788114585, "loss": 0.5759788513183594, "step": 184110 }, { "epoch": 1.0944475156184057, "grad_norm": 1.5442019701004028, "learning_rate": 0.0001642102891369726, "loss": 0.5557803630828857, "step": 184120 }, { "epoch": 1.0945069576950741, "grad_norm": 1.3369839191436768, "learning_rate": 0.00016420532013347502, "loss": 0.5799949645996094, "step": 184130 }, { "epoch": 1.0945663997717425, "grad_norm": 1.781999945640564, "learning_rate": 0.0001642003508706769, "loss": 0.6285907745361328, "step": 184140 }, { "epoch": 1.0946258418484107, "grad_norm": 1.4050670862197876, "learning_rate": 0.00016419538134860204, "loss": 0.6073142528533936, "step": 184150 }, { "epoch": 1.0946852839250791, "grad_norm": 1.8659822940826416, "learning_rate": 0.00016419041156727417, "loss": 0.6202578544616699, "step": 184160 }, { "epoch": 1.0947447260017475, "grad_norm": 1.2383899688720703, "learning_rate": 0.00016418544152671706, "loss": 0.6123284339904785, "step": 184170 }, { "epoch": 1.094804168078416, "grad_norm": 1.5190740823745728, "learning_rate": 0.00016418047122695453, "loss": 0.6097600936889649, "step": 184180 }, { "epoch": 1.0948636101550844, "grad_norm": 1.582755208015442, "learning_rate": 0.00016417550066801033, "loss": 0.628219747543335, "step": 184190 }, { "epoch": 1.0949230522317528, "grad_norm": 1.5848889350891113, "learning_rate": 0.00016417052984990825, "loss": 0.6924118995666504, "step": 184200 }, { "epoch": 1.0949824943084212, "grad_norm": 1.5844407081604004, "learning_rate": 0.00016416555877267204, "loss": 0.6239180564880371, "step": 184210 }, { "epoch": 1.0950419363850896, "grad_norm": 1.3630640506744385, "learning_rate": 0.0001641605874363255, "loss": 0.5496054649353027, "step": 184220 }, { "epoch": 1.095101378461758, "grad_norm": 1.269811987876892, "learning_rate": 0.0001641556158408924, "loss": 0.5880621433258056, "step": 184230 }, { "epoch": 1.0951608205384262, "grad_norm": 1.41660737991333, "learning_rate": 0.00016415064398639658, "loss": 0.6187187194824219, "step": 184240 }, { "epoch": 1.0952202626150946, "grad_norm": 1.7094712257385254, "learning_rate": 0.00016414567187286172, "loss": 0.6575861930847168, "step": 184250 }, { "epoch": 1.095279704691763, "grad_norm": 1.5025246143341064, "learning_rate": 0.0001641406995003117, "loss": 0.6104717254638672, "step": 184260 }, { "epoch": 1.0953391467684315, "grad_norm": 1.5415904521942139, "learning_rate": 0.00016413572686877024, "loss": 0.6203225612640381, "step": 184270 }, { "epoch": 1.0953985888450999, "grad_norm": 1.5255422592163086, "learning_rate": 0.00016413075397826113, "loss": 0.6463189601898194, "step": 184280 }, { "epoch": 1.0954580309217683, "grad_norm": 1.5320740938186646, "learning_rate": 0.00016412578082880826, "loss": 0.6315902709960938, "step": 184290 }, { "epoch": 1.0955174729984367, "grad_norm": 1.6372957229614258, "learning_rate": 0.0001641208074204353, "loss": 0.6321254730224609, "step": 184300 }, { "epoch": 1.0955769150751051, "grad_norm": 1.7663148641586304, "learning_rate": 0.00016411583375316609, "loss": 0.6770759582519531, "step": 184310 }, { "epoch": 1.0956363571517735, "grad_norm": 1.5610473155975342, "learning_rate": 0.00016411085982702438, "loss": 0.5907933235168457, "step": 184320 }, { "epoch": 1.0956957992284417, "grad_norm": 1.2133104801177979, "learning_rate": 0.00016410588564203405, "loss": 0.5721735477447509, "step": 184330 }, { "epoch": 1.0957552413051102, "grad_norm": 1.5543296337127686, "learning_rate": 0.00016410091119821882, "loss": 0.6006056785583496, "step": 184340 }, { "epoch": 1.0958146833817786, "grad_norm": 1.6968913078308105, "learning_rate": 0.00016409593649560254, "loss": 0.6025066375732422, "step": 184350 }, { "epoch": 1.095874125458447, "grad_norm": 1.341741919517517, "learning_rate": 0.00016409096153420893, "loss": 0.5706059455871582, "step": 184360 }, { "epoch": 1.0959335675351154, "grad_norm": 1.658166766166687, "learning_rate": 0.00016408598631406188, "loss": 0.6407320976257325, "step": 184370 }, { "epoch": 1.0959930096117838, "grad_norm": 1.6176339387893677, "learning_rate": 0.00016408101083518513, "loss": 0.5822379112243652, "step": 184380 }, { "epoch": 1.0960524516884522, "grad_norm": 1.4047175645828247, "learning_rate": 0.00016407603509760248, "loss": 0.5688935279846191, "step": 184390 }, { "epoch": 1.0961118937651206, "grad_norm": 2.0492987632751465, "learning_rate": 0.00016407105910133776, "loss": 0.6507320404052734, "step": 184400 }, { "epoch": 1.096171335841789, "grad_norm": 1.4528255462646484, "learning_rate": 0.00016406608284641477, "loss": 0.6109599590301513, "step": 184410 }, { "epoch": 1.0962307779184575, "grad_norm": 1.8614673614501953, "learning_rate": 0.00016406110633285733, "loss": 0.6466083526611328, "step": 184420 }, { "epoch": 1.0962902199951257, "grad_norm": 1.510270118713379, "learning_rate": 0.0001640561295606892, "loss": 0.5932846069335938, "step": 184430 }, { "epoch": 1.096349662071794, "grad_norm": 1.6219743490219116, "learning_rate": 0.0001640511525299342, "loss": 0.6565040588378906, "step": 184440 }, { "epoch": 1.0964091041484625, "grad_norm": 1.7411540746688843, "learning_rate": 0.00016404617524061617, "loss": 0.6011510848999023, "step": 184450 }, { "epoch": 1.096468546225131, "grad_norm": 1.5056499242782593, "learning_rate": 0.00016404119769275892, "loss": 0.5935039043426513, "step": 184460 }, { "epoch": 1.0965279883017993, "grad_norm": 1.706286907196045, "learning_rate": 0.0001640362198863862, "loss": 0.6062726974487305, "step": 184470 }, { "epoch": 1.0965874303784677, "grad_norm": 1.5331180095672607, "learning_rate": 0.0001640312418215219, "loss": 0.6177181243896485, "step": 184480 }, { "epoch": 1.0966468724551361, "grad_norm": 2.025684118270874, "learning_rate": 0.00016402626349818977, "loss": 0.6472785949707032, "step": 184490 }, { "epoch": 1.0967063145318046, "grad_norm": 1.4670315980911255, "learning_rate": 0.00016402128491641366, "loss": 0.6285752296447754, "step": 184500 }, { "epoch": 1.096765756608473, "grad_norm": 1.5706169605255127, "learning_rate": 0.00016401630607621736, "loss": 0.5929428100585937, "step": 184510 }, { "epoch": 1.0968251986851412, "grad_norm": 1.3594434261322021, "learning_rate": 0.00016401132697762473, "loss": 0.6600559234619141, "step": 184520 }, { "epoch": 1.0968846407618096, "grad_norm": 1.4035420417785645, "learning_rate": 0.0001640063476206596, "loss": 0.5780170440673829, "step": 184530 }, { "epoch": 1.096944082838478, "grad_norm": 1.6148569583892822, "learning_rate": 0.00016400136800534567, "loss": 0.5978879928588867, "step": 184540 }, { "epoch": 1.0970035249151464, "grad_norm": 1.4498413801193237, "learning_rate": 0.0001639963881317069, "loss": 0.5940542221069336, "step": 184550 }, { "epoch": 1.0970629669918148, "grad_norm": 1.492272973060608, "learning_rate": 0.00016399140799976705, "loss": 0.5925396919250489, "step": 184560 }, { "epoch": 1.0971224090684832, "grad_norm": 1.2953394651412964, "learning_rate": 0.00016398642760954993, "loss": 0.6329715251922607, "step": 184570 }, { "epoch": 1.0971818511451517, "grad_norm": 1.529162049293518, "learning_rate": 0.00016398144696107937, "loss": 0.6514315128326416, "step": 184580 }, { "epoch": 1.09724129322182, "grad_norm": 1.6099920272827148, "learning_rate": 0.00016397646605437923, "loss": 0.6375682830810547, "step": 184590 }, { "epoch": 1.0973007352984885, "grad_norm": 1.7081133127212524, "learning_rate": 0.0001639714848894733, "loss": 0.6141371250152587, "step": 184600 }, { "epoch": 1.0973601773751567, "grad_norm": 1.6223703622817993, "learning_rate": 0.00016396650346638545, "loss": 0.6487695693969726, "step": 184610 }, { "epoch": 1.097419619451825, "grad_norm": 1.2814955711364746, "learning_rate": 0.0001639615217851395, "loss": 0.6293073654174804, "step": 184620 }, { "epoch": 1.0974790615284935, "grad_norm": 1.5152047872543335, "learning_rate": 0.00016395653984575923, "loss": 0.6261233329772949, "step": 184630 }, { "epoch": 1.097538503605162, "grad_norm": 1.3899978399276733, "learning_rate": 0.0001639515576482685, "loss": 0.584017276763916, "step": 184640 }, { "epoch": 1.0975979456818303, "grad_norm": 1.4650886058807373, "learning_rate": 0.00016394657519269116, "loss": 0.5880276679992675, "step": 184650 }, { "epoch": 1.0976573877584987, "grad_norm": 1.4661335945129395, "learning_rate": 0.00016394159247905106, "loss": 0.6478874683380127, "step": 184660 }, { "epoch": 1.0977168298351672, "grad_norm": 1.7168877124786377, "learning_rate": 0.00016393660950737198, "loss": 0.6176746845245361, "step": 184670 }, { "epoch": 1.0977762719118356, "grad_norm": 1.47411048412323, "learning_rate": 0.00016393162627767778, "loss": 0.6558008193969727, "step": 184680 }, { "epoch": 1.097835713988504, "grad_norm": 1.587209939956665, "learning_rate": 0.00016392664278999232, "loss": 0.6270994186401367, "step": 184690 }, { "epoch": 1.0978951560651722, "grad_norm": 1.2178363800048828, "learning_rate": 0.00016392165904433942, "loss": 0.6569514274597168, "step": 184700 }, { "epoch": 1.0979545981418406, "grad_norm": 1.3190679550170898, "learning_rate": 0.00016391667504074293, "loss": 0.6345134735107422, "step": 184710 }, { "epoch": 1.098014040218509, "grad_norm": 1.6337318420410156, "learning_rate": 0.0001639116907792267, "loss": 0.6269680976867675, "step": 184720 }, { "epoch": 1.0980734822951774, "grad_norm": 1.9008351564407349, "learning_rate": 0.00016390670625981456, "loss": 0.6104336738586426, "step": 184730 }, { "epoch": 1.0981329243718458, "grad_norm": 1.8362115621566772, "learning_rate": 0.0001639017214825303, "loss": 0.6051698684692383, "step": 184740 }, { "epoch": 1.0981923664485143, "grad_norm": 1.6226049661636353, "learning_rate": 0.00016389673644739785, "loss": 0.6323739528656006, "step": 184750 }, { "epoch": 1.0982518085251827, "grad_norm": 1.8396843671798706, "learning_rate": 0.00016389175115444108, "loss": 0.6739025592803956, "step": 184760 }, { "epoch": 1.098311250601851, "grad_norm": 1.3769416809082031, "learning_rate": 0.00016388676560368372, "loss": 0.6413507461547852, "step": 184770 }, { "epoch": 1.0983706926785195, "grad_norm": 1.6880033016204834, "learning_rate": 0.0001638817797951497, "loss": 0.6130022525787353, "step": 184780 }, { "epoch": 1.098430134755188, "grad_norm": 1.8170353174209595, "learning_rate": 0.00016387679372886286, "loss": 0.7019564628601074, "step": 184790 }, { "epoch": 1.098489576831856, "grad_norm": 1.6061160564422607, "learning_rate": 0.00016387180740484703, "loss": 0.650409460067749, "step": 184800 }, { "epoch": 1.0985490189085245, "grad_norm": 1.4053255319595337, "learning_rate": 0.0001638668208231261, "loss": 0.5812664985656738, "step": 184810 }, { "epoch": 1.098608460985193, "grad_norm": 1.4377894401550293, "learning_rate": 0.0001638618339837239, "loss": 0.6481731414794922, "step": 184820 }, { "epoch": 1.0986679030618614, "grad_norm": 1.568122386932373, "learning_rate": 0.00016385684688666427, "loss": 0.6278424263000488, "step": 184830 }, { "epoch": 1.0987273451385298, "grad_norm": 1.5511980056762695, "learning_rate": 0.0001638518595319711, "loss": 0.5948273181915283, "step": 184840 }, { "epoch": 1.0987867872151982, "grad_norm": 1.7935214042663574, "learning_rate": 0.00016384687191966824, "loss": 0.5985379219055176, "step": 184850 }, { "epoch": 1.0988462292918666, "grad_norm": 1.7949057817459106, "learning_rate": 0.00016384188404977953, "loss": 0.6295689582824707, "step": 184860 }, { "epoch": 1.098905671368535, "grad_norm": 1.6748305559158325, "learning_rate": 0.00016383689592232886, "loss": 0.6314291954040527, "step": 184870 }, { "epoch": 1.0989651134452034, "grad_norm": 1.8409106731414795, "learning_rate": 0.00016383190753734003, "loss": 0.6305230617523193, "step": 184880 }, { "epoch": 1.0990245555218716, "grad_norm": 1.8826206922531128, "learning_rate": 0.000163826918894837, "loss": 0.6240478992462158, "step": 184890 }, { "epoch": 1.09908399759854, "grad_norm": 1.5888736248016357, "learning_rate": 0.00016382192999484356, "loss": 0.6193448066711426, "step": 184900 }, { "epoch": 1.0991434396752084, "grad_norm": 1.207499384880066, "learning_rate": 0.0001638169408373836, "loss": 0.618276309967041, "step": 184910 }, { "epoch": 1.0992028817518769, "grad_norm": 1.8238558769226074, "learning_rate": 0.00016381195142248098, "loss": 0.6399590492248535, "step": 184920 }, { "epoch": 1.0992623238285453, "grad_norm": 1.6433041095733643, "learning_rate": 0.00016380696175015956, "loss": 0.6312031269073486, "step": 184930 }, { "epoch": 1.0993217659052137, "grad_norm": 1.9270087480545044, "learning_rate": 0.00016380197182044322, "loss": 0.6456579208374024, "step": 184940 }, { "epoch": 1.099381207981882, "grad_norm": 1.4885356426239014, "learning_rate": 0.00016379698163335583, "loss": 0.5797460556030274, "step": 184950 }, { "epoch": 1.0994406500585505, "grad_norm": 1.4314996004104614, "learning_rate": 0.00016379199118892127, "loss": 0.6477416038513184, "step": 184960 }, { "epoch": 1.099500092135219, "grad_norm": 1.2548613548278809, "learning_rate": 0.0001637870004871634, "loss": 0.6367228507995606, "step": 184970 }, { "epoch": 1.0995595342118871, "grad_norm": 1.4082616567611694, "learning_rate": 0.0001637820095281061, "loss": 0.6211843013763427, "step": 184980 }, { "epoch": 1.0996189762885555, "grad_norm": 1.316443920135498, "learning_rate": 0.00016377701831177325, "loss": 0.6219520092010498, "step": 184990 }, { "epoch": 1.099678418365224, "grad_norm": 1.5045572519302368, "learning_rate": 0.0001637720268381887, "loss": 0.6220390319824218, "step": 185000 }, { "epoch": 1.0997378604418924, "grad_norm": 1.8112361431121826, "learning_rate": 0.00016376703510737634, "loss": 0.6311532974243164, "step": 185010 }, { "epoch": 1.0997973025185608, "grad_norm": 1.3368359804153442, "learning_rate": 0.0001637620431193601, "loss": 0.6245149612426758, "step": 185020 }, { "epoch": 1.0998567445952292, "grad_norm": 1.5957896709442139, "learning_rate": 0.00016375705087416377, "loss": 0.6236001491546631, "step": 185030 }, { "epoch": 1.0999161866718976, "grad_norm": 1.6191498041152954, "learning_rate": 0.0001637520583718113, "loss": 0.6041234016418457, "step": 185040 }, { "epoch": 1.099975628748566, "grad_norm": 1.4742439985275269, "learning_rate": 0.00016374706561232656, "loss": 0.6110059261322022, "step": 185050 }, { "epoch": 1.1000350708252344, "grad_norm": 1.5653823614120483, "learning_rate": 0.00016374207259573339, "loss": 0.6157852172851562, "step": 185060 }, { "epoch": 1.1000945129019026, "grad_norm": 1.3240842819213867, "learning_rate": 0.00016373707932205574, "loss": 0.6330420494079589, "step": 185070 }, { "epoch": 1.100153954978571, "grad_norm": 1.6951930522918701, "learning_rate": 0.00016373208579131742, "loss": 0.7089333057403564, "step": 185080 }, { "epoch": 1.1002133970552395, "grad_norm": 1.5560907125473022, "learning_rate": 0.0001637270920035424, "loss": 0.6657682418823242, "step": 185090 }, { "epoch": 1.1002728391319079, "grad_norm": 1.4539216756820679, "learning_rate": 0.0001637220979587545, "loss": 0.6347498893737793, "step": 185100 }, { "epoch": 1.1003322812085763, "grad_norm": 1.7415286302566528, "learning_rate": 0.0001637171036569777, "loss": 0.5980043411254883, "step": 185110 }, { "epoch": 1.1003917232852447, "grad_norm": 1.4753655195236206, "learning_rate": 0.00016371210909823578, "loss": 0.5858061790466309, "step": 185120 }, { "epoch": 1.1004511653619131, "grad_norm": 1.6864662170410156, "learning_rate": 0.00016370711428255268, "loss": 0.6501177787780762, "step": 185130 }, { "epoch": 1.1005106074385815, "grad_norm": 1.8161170482635498, "learning_rate": 0.0001637021192099523, "loss": 0.6377475738525391, "step": 185140 }, { "epoch": 1.10057004951525, "grad_norm": 1.4181687831878662, "learning_rate": 0.00016369712388045857, "loss": 0.5755069255828857, "step": 185150 }, { "epoch": 1.1006294915919184, "grad_norm": 1.5432294607162476, "learning_rate": 0.0001636921282940953, "loss": 0.6350937843322754, "step": 185160 }, { "epoch": 1.1006889336685866, "grad_norm": 1.4884923696517944, "learning_rate": 0.00016368713245088647, "loss": 0.6253742218017578, "step": 185170 }, { "epoch": 1.100748375745255, "grad_norm": 1.7359142303466797, "learning_rate": 0.0001636821363508559, "loss": 0.622487735748291, "step": 185180 }, { "epoch": 1.1008078178219234, "grad_norm": 2.0135080814361572, "learning_rate": 0.00016367713999402753, "loss": 0.7160287857055664, "step": 185190 }, { "epoch": 1.1008672598985918, "grad_norm": 1.4783656597137451, "learning_rate": 0.00016367214338042533, "loss": 0.6211837768554688, "step": 185200 }, { "epoch": 1.1009267019752602, "grad_norm": 1.3801137208938599, "learning_rate": 0.0001636671465100731, "loss": 0.5984103202819824, "step": 185210 }, { "epoch": 1.1009861440519286, "grad_norm": 2.0258443355560303, "learning_rate": 0.0001636621493829948, "loss": 0.5757732391357422, "step": 185220 }, { "epoch": 1.101045586128597, "grad_norm": 1.4580227136611938, "learning_rate": 0.00016365715199921426, "loss": 0.5800608634948731, "step": 185230 }, { "epoch": 1.1011050282052655, "grad_norm": 1.59624445438385, "learning_rate": 0.00016365215435875548, "loss": 0.6219138145446778, "step": 185240 }, { "epoch": 1.1011644702819339, "grad_norm": 1.5632798671722412, "learning_rate": 0.00016364715646164234, "loss": 0.5456202507019043, "step": 185250 }, { "epoch": 1.101223912358602, "grad_norm": 1.3998761177062988, "learning_rate": 0.0001636421583078987, "loss": 0.6380373954772949, "step": 185260 }, { "epoch": 1.1012833544352705, "grad_norm": 1.5327246189117432, "learning_rate": 0.00016363715989754855, "loss": 0.6666544914245606, "step": 185270 }, { "epoch": 1.101342796511939, "grad_norm": 1.4944775104522705, "learning_rate": 0.0001636321612306157, "loss": 0.6471940994262695, "step": 185280 }, { "epoch": 1.1014022385886073, "grad_norm": 1.6320627927780151, "learning_rate": 0.00016362716230712416, "loss": 0.5842884063720704, "step": 185290 }, { "epoch": 1.1014616806652757, "grad_norm": 1.4620540142059326, "learning_rate": 0.0001636221631270978, "loss": 0.6311744689941406, "step": 185300 }, { "epoch": 1.1015211227419441, "grad_norm": 1.6396241188049316, "learning_rate": 0.0001636171636905605, "loss": 0.6267504692077637, "step": 185310 }, { "epoch": 1.1015805648186126, "grad_norm": 1.311223030090332, "learning_rate": 0.00016361216399753625, "loss": 0.5965879440307618, "step": 185320 }, { "epoch": 1.101640006895281, "grad_norm": 1.5695475339889526, "learning_rate": 0.00016360716404804893, "loss": 0.6315207481384277, "step": 185330 }, { "epoch": 1.1016994489719494, "grad_norm": 1.5889322757720947, "learning_rate": 0.00016360216384212243, "loss": 0.6047852516174317, "step": 185340 }, { "epoch": 1.1017588910486176, "grad_norm": 1.3269630670547485, "learning_rate": 0.00016359716337978073, "loss": 0.6318148612976074, "step": 185350 }, { "epoch": 1.101818333125286, "grad_norm": 1.9975355863571167, "learning_rate": 0.00016359216266104764, "loss": 0.5917560577392578, "step": 185360 }, { "epoch": 1.1018777752019544, "grad_norm": 1.68450129032135, "learning_rate": 0.00016358716168594721, "loss": 0.595313549041748, "step": 185370 }, { "epoch": 1.1019372172786228, "grad_norm": 1.6121079921722412, "learning_rate": 0.00016358216045450334, "loss": 0.6168037414550781, "step": 185380 }, { "epoch": 1.1019966593552912, "grad_norm": 1.3960609436035156, "learning_rate": 0.00016357715896673987, "loss": 0.6088403701782227, "step": 185390 }, { "epoch": 1.1020561014319596, "grad_norm": 1.6883586645126343, "learning_rate": 0.00016357215722268085, "loss": 0.6195034503936767, "step": 185400 }, { "epoch": 1.102115543508628, "grad_norm": 1.4468384981155396, "learning_rate": 0.00016356715522235007, "loss": 0.6434361457824707, "step": 185410 }, { "epoch": 1.1021749855852965, "grad_norm": 1.5197663307189941, "learning_rate": 0.00016356215296577155, "loss": 0.6114902496337891, "step": 185420 }, { "epoch": 1.1022344276619649, "grad_norm": 1.424818515777588, "learning_rate": 0.0001635571504529692, "loss": 0.6581074714660644, "step": 185430 }, { "epoch": 1.102293869738633, "grad_norm": 1.343959093093872, "learning_rate": 0.00016355214768396694, "loss": 0.6034841537475586, "step": 185440 }, { "epoch": 1.1023533118153015, "grad_norm": 1.7461893558502197, "learning_rate": 0.0001635471446587887, "loss": 0.6271519184112548, "step": 185450 }, { "epoch": 1.10241275389197, "grad_norm": 1.6916368007659912, "learning_rate": 0.0001635421413774584, "loss": 0.6719574928283691, "step": 185460 }, { "epoch": 1.1024721959686383, "grad_norm": 2.3686234951019287, "learning_rate": 0.00016353713784000005, "loss": 0.5983903408050537, "step": 185470 }, { "epoch": 1.1025316380453067, "grad_norm": 1.633046269416809, "learning_rate": 0.00016353213404643748, "loss": 0.6271384239196778, "step": 185480 }, { "epoch": 1.1025910801219752, "grad_norm": 1.2691230773925781, "learning_rate": 0.0001635271299967947, "loss": 0.6428112983703613, "step": 185490 }, { "epoch": 1.1026505221986436, "grad_norm": 1.6415369510650635, "learning_rate": 0.00016352212569109562, "loss": 0.6714013099670411, "step": 185500 }, { "epoch": 1.102709964275312, "grad_norm": 1.5189180374145508, "learning_rate": 0.00016351712112936415, "loss": 0.6201306343078613, "step": 185510 }, { "epoch": 1.1027694063519804, "grad_norm": 1.7606945037841797, "learning_rate": 0.0001635121163116243, "loss": 0.6086302757263183, "step": 185520 }, { "epoch": 1.1028288484286488, "grad_norm": 1.8525182008743286, "learning_rate": 0.00016350711123789996, "loss": 0.6476721286773681, "step": 185530 }, { "epoch": 1.102888290505317, "grad_norm": 1.404795527458191, "learning_rate": 0.00016350210590821508, "loss": 0.6008484840393067, "step": 185540 }, { "epoch": 1.1029477325819854, "grad_norm": 1.3069850206375122, "learning_rate": 0.00016349710032259363, "loss": 0.6266998291015625, "step": 185550 }, { "epoch": 1.1030071746586538, "grad_norm": 1.7934770584106445, "learning_rate": 0.00016349209448105953, "loss": 0.6371118545532226, "step": 185560 }, { "epoch": 1.1030666167353222, "grad_norm": 1.8045297861099243, "learning_rate": 0.0001634870883836367, "loss": 0.6345920562744141, "step": 185570 }, { "epoch": 1.1031260588119907, "grad_norm": 1.6779569387435913, "learning_rate": 0.00016348208203034918, "loss": 0.6447458744049073, "step": 185580 }, { "epoch": 1.103185500888659, "grad_norm": 1.8634744882583618, "learning_rate": 0.00016347707542122082, "loss": 0.6138283729553222, "step": 185590 }, { "epoch": 1.1032449429653275, "grad_norm": 2.2843666076660156, "learning_rate": 0.00016347206855627557, "loss": 0.6745306968688964, "step": 185600 }, { "epoch": 1.103304385041996, "grad_norm": 2.0070903301239014, "learning_rate": 0.0001634670614355375, "loss": 0.6226571559906006, "step": 185610 }, { "epoch": 1.1033638271186643, "grad_norm": 1.7637161016464233, "learning_rate": 0.0001634620540590304, "loss": 0.6620932579040527, "step": 185620 }, { "epoch": 1.1034232691953325, "grad_norm": 1.5056040287017822, "learning_rate": 0.00016345704642677835, "loss": 0.6010915756225585, "step": 185630 }, { "epoch": 1.103482711272001, "grad_norm": 1.551210641860962, "learning_rate": 0.00016345203853880525, "loss": 0.6305244445800782, "step": 185640 }, { "epoch": 1.1035421533486693, "grad_norm": 1.8705604076385498, "learning_rate": 0.00016344703039513508, "loss": 0.6114708423614502, "step": 185650 }, { "epoch": 1.1036015954253378, "grad_norm": 1.573348879814148, "learning_rate": 0.0001634420219957918, "loss": 0.612033748626709, "step": 185660 }, { "epoch": 1.1036610375020062, "grad_norm": 1.2595939636230469, "learning_rate": 0.0001634370133407993, "loss": 0.6036327362060547, "step": 185670 }, { "epoch": 1.1037204795786746, "grad_norm": 1.7960445880889893, "learning_rate": 0.0001634320044301816, "loss": 0.6104745864868164, "step": 185680 }, { "epoch": 1.103779921655343, "grad_norm": 1.4818214178085327, "learning_rate": 0.0001634269952639627, "loss": 0.5498674869537353, "step": 185690 }, { "epoch": 1.1038393637320114, "grad_norm": 1.5443583726882935, "learning_rate": 0.0001634219858421665, "loss": 0.6060192108154296, "step": 185700 }, { "epoch": 1.1038988058086798, "grad_norm": 1.6653848886489868, "learning_rate": 0.00016341697616481692, "loss": 0.6581465721130371, "step": 185710 }, { "epoch": 1.103958247885348, "grad_norm": 1.739920735359192, "learning_rate": 0.00016341196623193807, "loss": 0.6498994350433349, "step": 185720 }, { "epoch": 1.1040176899620164, "grad_norm": 1.9116466045379639, "learning_rate": 0.00016340695604355376, "loss": 0.6870248794555665, "step": 185730 }, { "epoch": 1.1040771320386848, "grad_norm": 1.5114617347717285, "learning_rate": 0.00016340194559968805, "loss": 0.613400650024414, "step": 185740 }, { "epoch": 1.1041365741153533, "grad_norm": 1.6659958362579346, "learning_rate": 0.00016339693490036487, "loss": 0.5705914974212647, "step": 185750 }, { "epoch": 1.1041960161920217, "grad_norm": 1.5732134580612183, "learning_rate": 0.00016339192394560826, "loss": 0.6420021057128906, "step": 185760 }, { "epoch": 1.10425545826869, "grad_norm": 1.9375182390213013, "learning_rate": 0.00016338691273544206, "loss": 0.675414752960205, "step": 185770 }, { "epoch": 1.1043149003453585, "grad_norm": 2.502185344696045, "learning_rate": 0.00016338190126989036, "loss": 0.6781588554382324, "step": 185780 }, { "epoch": 1.104374342422027, "grad_norm": 1.913628339767456, "learning_rate": 0.00016337688954897708, "loss": 0.6727786064147949, "step": 185790 }, { "epoch": 1.1044337844986953, "grad_norm": 1.5423656702041626, "learning_rate": 0.00016337187757272618, "loss": 0.5908714294433594, "step": 185800 }, { "epoch": 1.1044932265753635, "grad_norm": 1.6264498233795166, "learning_rate": 0.00016336686534116168, "loss": 0.6337398529052735, "step": 185810 }, { "epoch": 1.104552668652032, "grad_norm": 1.3657200336456299, "learning_rate": 0.00016336185285430757, "loss": 0.6157027244567871, "step": 185820 }, { "epoch": 1.1046121107287004, "grad_norm": 1.9986212253570557, "learning_rate": 0.00016335684011218772, "loss": 0.6954027652740479, "step": 185830 }, { "epoch": 1.1046715528053688, "grad_norm": 1.4546067714691162, "learning_rate": 0.00016335182711482626, "loss": 0.6031829833984375, "step": 185840 }, { "epoch": 1.1047309948820372, "grad_norm": 1.8519920110702515, "learning_rate": 0.00016334681386224705, "loss": 0.6405269622802734, "step": 185850 }, { "epoch": 1.1047904369587056, "grad_norm": 1.6004235744476318, "learning_rate": 0.0001633418003544741, "loss": 0.6651662826538086, "step": 185860 }, { "epoch": 1.104849879035374, "grad_norm": 1.5119322538375854, "learning_rate": 0.00016333678659153148, "loss": 0.614220380783081, "step": 185870 }, { "epoch": 1.1049093211120424, "grad_norm": 1.5572224855422974, "learning_rate": 0.00016333177257344306, "loss": 0.6391571998596192, "step": 185880 }, { "epoch": 1.1049687631887108, "grad_norm": 1.7035435438156128, "learning_rate": 0.00016332675830023287, "loss": 0.6530054092407227, "step": 185890 }, { "epoch": 1.1050282052653793, "grad_norm": 1.739017367362976, "learning_rate": 0.00016332174377192487, "loss": 0.6158722877502442, "step": 185900 }, { "epoch": 1.1050876473420475, "grad_norm": 1.489404320716858, "learning_rate": 0.0001633167289885431, "loss": 0.6170706748962402, "step": 185910 }, { "epoch": 1.1051470894187159, "grad_norm": 1.8458086252212524, "learning_rate": 0.00016331171395011156, "loss": 0.6589011669158935, "step": 185920 }, { "epoch": 1.1052065314953843, "grad_norm": 1.5375815629959106, "learning_rate": 0.00016330669865665415, "loss": 0.6524840831756592, "step": 185930 }, { "epoch": 1.1052659735720527, "grad_norm": 1.7076606750488281, "learning_rate": 0.0001633016831081949, "loss": 0.6722405433654786, "step": 185940 }, { "epoch": 1.105325415648721, "grad_norm": 1.5012279748916626, "learning_rate": 0.0001632966673047579, "loss": 0.6058704376220703, "step": 185950 }, { "epoch": 1.1053848577253895, "grad_norm": 1.4827337265014648, "learning_rate": 0.00016329165124636698, "loss": 0.6463760375976563, "step": 185960 }, { "epoch": 1.105444299802058, "grad_norm": 1.8749947547912598, "learning_rate": 0.00016328663493304625, "loss": 0.5895051002502442, "step": 185970 }, { "epoch": 1.1055037418787264, "grad_norm": 1.5475422143936157, "learning_rate": 0.00016328161836481967, "loss": 0.6644620895385742, "step": 185980 }, { "epoch": 1.1055631839553948, "grad_norm": 1.5089919567108154, "learning_rate": 0.00016327660154171123, "loss": 0.6252059936523438, "step": 185990 }, { "epoch": 1.105622626032063, "grad_norm": 1.2677313089370728, "learning_rate": 0.00016327158446374494, "loss": 0.6111459255218505, "step": 186000 }, { "epoch": 1.1056820681087314, "grad_norm": 1.2923822402954102, "learning_rate": 0.00016326656713094482, "loss": 0.5807926654815674, "step": 186010 }, { "epoch": 1.1057415101853998, "grad_norm": 2.020798921585083, "learning_rate": 0.00016326154954333485, "loss": 0.65379958152771, "step": 186020 }, { "epoch": 1.1058009522620682, "grad_norm": 1.5924993753433228, "learning_rate": 0.00016325653170093902, "loss": 0.5669394493103027, "step": 186030 }, { "epoch": 1.1058603943387366, "grad_norm": 1.4812804460525513, "learning_rate": 0.00016325151360378133, "loss": 0.5714001178741455, "step": 186040 }, { "epoch": 1.105919836415405, "grad_norm": 1.7565412521362305, "learning_rate": 0.00016324649525188584, "loss": 0.6568855285644531, "step": 186050 }, { "epoch": 1.1059792784920734, "grad_norm": 1.696731686592102, "learning_rate": 0.0001632414766452765, "loss": 0.6408734321594238, "step": 186060 }, { "epoch": 1.1060387205687419, "grad_norm": 1.339294195175171, "learning_rate": 0.00016323645778397735, "loss": 0.5721086502075196, "step": 186070 }, { "epoch": 1.1060981626454103, "grad_norm": 1.3187875747680664, "learning_rate": 0.00016323143866801232, "loss": 0.6179628372192383, "step": 186080 }, { "epoch": 1.1061576047220785, "grad_norm": 1.3137396574020386, "learning_rate": 0.00016322641929740554, "loss": 0.5912274837493896, "step": 186090 }, { "epoch": 1.1062170467987469, "grad_norm": 1.5366684198379517, "learning_rate": 0.00016322139967218095, "loss": 0.6399402618408203, "step": 186100 }, { "epoch": 1.1062764888754153, "grad_norm": 1.411455750465393, "learning_rate": 0.0001632163797923626, "loss": 0.588671350479126, "step": 186110 }, { "epoch": 1.1063359309520837, "grad_norm": 1.5643844604492188, "learning_rate": 0.00016321135965797446, "loss": 0.6041399002075195, "step": 186120 }, { "epoch": 1.1063953730287521, "grad_norm": 1.2859143018722534, "learning_rate": 0.00016320633926904054, "loss": 0.619732666015625, "step": 186130 }, { "epoch": 1.1064548151054205, "grad_norm": 2.0834853649139404, "learning_rate": 0.00016320131862558493, "loss": 0.622186803817749, "step": 186140 }, { "epoch": 1.106514257182089, "grad_norm": 1.5694141387939453, "learning_rate": 0.00016319629772763156, "loss": 0.6375326156616211, "step": 186150 }, { "epoch": 1.1065736992587574, "grad_norm": 1.4334850311279297, "learning_rate": 0.0001631912765752045, "loss": 0.6080096244812012, "step": 186160 }, { "epoch": 1.1066331413354258, "grad_norm": 2.123716115951538, "learning_rate": 0.00016318625516832774, "loss": 0.6114946842193604, "step": 186170 }, { "epoch": 1.106692583412094, "grad_norm": 1.7222625017166138, "learning_rate": 0.00016318123350702536, "loss": 0.6510156631469727, "step": 186180 }, { "epoch": 1.1067520254887624, "grad_norm": 1.549203872680664, "learning_rate": 0.00016317621159132133, "loss": 0.6448103427886963, "step": 186190 }, { "epoch": 1.1068114675654308, "grad_norm": 1.4614542722702026, "learning_rate": 0.00016317118942123964, "loss": 0.5762633323669434, "step": 186200 }, { "epoch": 1.1068709096420992, "grad_norm": 1.4456830024719238, "learning_rate": 0.0001631661669968044, "loss": 0.6199383735656738, "step": 186210 }, { "epoch": 1.1069303517187676, "grad_norm": 2.170217752456665, "learning_rate": 0.00016316114431803955, "loss": 0.6308346748352051, "step": 186220 }, { "epoch": 1.106989793795436, "grad_norm": 1.479569673538208, "learning_rate": 0.0001631561213849692, "loss": 0.612881851196289, "step": 186230 }, { "epoch": 1.1070492358721045, "grad_norm": 1.4579850435256958, "learning_rate": 0.00016315109819761733, "loss": 0.6419039726257324, "step": 186240 }, { "epoch": 1.1071086779487729, "grad_norm": 1.585955023765564, "learning_rate": 0.00016314607475600797, "loss": 0.645264720916748, "step": 186250 }, { "epoch": 1.1071681200254413, "grad_norm": 1.4673470258712769, "learning_rate": 0.00016314105106016513, "loss": 0.5856376647949219, "step": 186260 }, { "epoch": 1.1072275621021097, "grad_norm": 1.8393861055374146, "learning_rate": 0.00016313602711011288, "loss": 0.6216900825500489, "step": 186270 }, { "epoch": 1.107287004178778, "grad_norm": 1.2344084978103638, "learning_rate": 0.00016313100290587525, "loss": 0.5794725894927979, "step": 186280 }, { "epoch": 1.1073464462554463, "grad_norm": 2.0409536361694336, "learning_rate": 0.00016312597844747627, "loss": 0.6721099853515625, "step": 186290 }, { "epoch": 1.1074058883321147, "grad_norm": 1.562262773513794, "learning_rate": 0.00016312095373493995, "loss": 0.6021969318389893, "step": 186300 }, { "epoch": 1.1074653304087831, "grad_norm": 1.3118548393249512, "learning_rate": 0.00016311592876829038, "loss": 0.6415717124938964, "step": 186310 }, { "epoch": 1.1075247724854516, "grad_norm": 1.598771095275879, "learning_rate": 0.00016311090354755156, "loss": 0.6123392581939697, "step": 186320 }, { "epoch": 1.10758421456212, "grad_norm": 1.6517198085784912, "learning_rate": 0.00016310587807274752, "loss": 0.579857587814331, "step": 186330 }, { "epoch": 1.1076436566387884, "grad_norm": 1.678999900817871, "learning_rate": 0.00016310085234390233, "loss": 0.6142716407775879, "step": 186340 }, { "epoch": 1.1077030987154568, "grad_norm": 1.5515333414077759, "learning_rate": 0.00016309582636104, "loss": 0.5914549350738525, "step": 186350 }, { "epoch": 1.1077625407921252, "grad_norm": 1.2844736576080322, "learning_rate": 0.0001630908001241846, "loss": 0.614526891708374, "step": 186360 }, { "epoch": 1.1078219828687934, "grad_norm": 1.788435697555542, "learning_rate": 0.00016308577363336016, "loss": 0.6545153617858886, "step": 186370 }, { "epoch": 1.1078814249454618, "grad_norm": 1.5707510709762573, "learning_rate": 0.0001630807468885907, "loss": 0.5759392261505127, "step": 186380 }, { "epoch": 1.1079408670221302, "grad_norm": 1.518667459487915, "learning_rate": 0.00016307571988990034, "loss": 0.6511420726776123, "step": 186390 }, { "epoch": 1.1080003090987987, "grad_norm": 1.6858046054840088, "learning_rate": 0.00016307069263731306, "loss": 0.6103872299194336, "step": 186400 }, { "epoch": 1.108059751175467, "grad_norm": 1.8421478271484375, "learning_rate": 0.00016306566513085293, "loss": 0.6673125743865966, "step": 186410 }, { "epoch": 1.1081191932521355, "grad_norm": 1.4674131870269775, "learning_rate": 0.000163060637370544, "loss": 0.6073598861694336, "step": 186420 }, { "epoch": 1.108178635328804, "grad_norm": 1.5785925388336182, "learning_rate": 0.0001630556093564103, "loss": 0.6191230773925781, "step": 186430 }, { "epoch": 1.1082380774054723, "grad_norm": 1.6286851167678833, "learning_rate": 0.00016305058108847595, "loss": 0.5869853496551514, "step": 186440 }, { "epoch": 1.1082975194821407, "grad_norm": 1.6033474206924438, "learning_rate": 0.00016304555256676492, "loss": 0.6164373397827149, "step": 186450 }, { "epoch": 1.108356961558809, "grad_norm": 1.7117629051208496, "learning_rate": 0.0001630405237913013, "loss": 0.6031466484069824, "step": 186460 }, { "epoch": 1.1084164036354773, "grad_norm": 1.2293227910995483, "learning_rate": 0.00016303549476210917, "loss": 0.5917073249816894, "step": 186470 }, { "epoch": 1.1084758457121457, "grad_norm": 1.4013524055480957, "learning_rate": 0.00016303046547921254, "loss": 0.6598694801330567, "step": 186480 }, { "epoch": 1.1085352877888142, "grad_norm": 1.9133925437927246, "learning_rate": 0.00016302543594263552, "loss": 0.6013460159301758, "step": 186490 }, { "epoch": 1.1085947298654826, "grad_norm": 1.629226803779602, "learning_rate": 0.00016302040615240215, "loss": 0.6242772102355957, "step": 186500 }, { "epoch": 1.108654171942151, "grad_norm": 1.5845537185668945, "learning_rate": 0.00016301537610853648, "loss": 0.6070728302001953, "step": 186510 }, { "epoch": 1.1087136140188194, "grad_norm": 1.443879246711731, "learning_rate": 0.00016301034581106256, "loss": 0.5906885147094727, "step": 186520 }, { "epoch": 1.1087730560954878, "grad_norm": 1.8252311944961548, "learning_rate": 0.00016300531526000446, "loss": 0.6010806083679199, "step": 186530 }, { "epoch": 1.1088324981721562, "grad_norm": 1.8180062770843506, "learning_rate": 0.00016300028445538625, "loss": 0.6238045692443848, "step": 186540 }, { "epoch": 1.1088919402488244, "grad_norm": 1.6404175758361816, "learning_rate": 0.00016299525339723202, "loss": 0.6424909591674804, "step": 186550 }, { "epoch": 1.1089513823254928, "grad_norm": 2.245298385620117, "learning_rate": 0.00016299022208556585, "loss": 0.5882562637329102, "step": 186560 }, { "epoch": 1.1090108244021613, "grad_norm": 1.6300398111343384, "learning_rate": 0.00016298519052041172, "loss": 0.6123419284820557, "step": 186570 }, { "epoch": 1.1090702664788297, "grad_norm": 1.6876357793807983, "learning_rate": 0.00016298015870179377, "loss": 0.612863826751709, "step": 186580 }, { "epoch": 1.109129708555498, "grad_norm": 1.211759090423584, "learning_rate": 0.00016297512662973607, "loss": 0.600684118270874, "step": 186590 }, { "epoch": 1.1091891506321665, "grad_norm": 1.4983339309692383, "learning_rate": 0.00016297009430426266, "loss": 0.6101136207580566, "step": 186600 }, { "epoch": 1.109248592708835, "grad_norm": 1.4183290004730225, "learning_rate": 0.00016296506172539766, "loss": 0.6002951622009277, "step": 186610 }, { "epoch": 1.1093080347855033, "grad_norm": 1.7747915983200073, "learning_rate": 0.0001629600288931651, "loss": 0.5979729652404785, "step": 186620 }, { "epoch": 1.1093674768621717, "grad_norm": 1.5133366584777832, "learning_rate": 0.00016295499580758902, "loss": 0.6230609893798829, "step": 186630 }, { "epoch": 1.1094269189388402, "grad_norm": 1.5053327083587646, "learning_rate": 0.00016294996246869357, "loss": 0.5958088874816895, "step": 186640 }, { "epoch": 1.1094863610155083, "grad_norm": 1.449730634689331, "learning_rate": 0.00016294492887650286, "loss": 0.5981544494628906, "step": 186650 }, { "epoch": 1.1095458030921768, "grad_norm": 1.82329261302948, "learning_rate": 0.00016293989503104084, "loss": 0.6051138877868653, "step": 186660 }, { "epoch": 1.1096052451688452, "grad_norm": 1.5491548776626587, "learning_rate": 0.00016293486093233171, "loss": 0.6616337299346924, "step": 186670 }, { "epoch": 1.1096646872455136, "grad_norm": 1.9331870079040527, "learning_rate": 0.00016292982658039948, "loss": 0.6070049285888672, "step": 186680 }, { "epoch": 1.109724129322182, "grad_norm": 1.4689525365829468, "learning_rate": 0.0001629247919752683, "loss": 0.6147177219390869, "step": 186690 }, { "epoch": 1.1097835713988504, "grad_norm": 1.7582765817642212, "learning_rate": 0.00016291975711696215, "loss": 0.6259625434875489, "step": 186700 }, { "epoch": 1.1098430134755188, "grad_norm": 1.7049614191055298, "learning_rate": 0.0001629147220055052, "loss": 0.5987980842590332, "step": 186710 }, { "epoch": 1.1099024555521873, "grad_norm": 1.2610571384429932, "learning_rate": 0.0001629096866409215, "loss": 0.6362765789031982, "step": 186720 }, { "epoch": 1.1099618976288557, "grad_norm": 1.8345263004302979, "learning_rate": 0.0001629046510232352, "loss": 0.6688312530517578, "step": 186730 }, { "epoch": 1.1100213397055239, "grad_norm": 1.7725427150726318, "learning_rate": 0.00016289961515247026, "loss": 0.5928773880004883, "step": 186740 }, { "epoch": 1.1100807817821923, "grad_norm": 1.453016996383667, "learning_rate": 0.00016289457902865092, "loss": 0.664385986328125, "step": 186750 }, { "epoch": 1.1101402238588607, "grad_norm": 1.7464830875396729, "learning_rate": 0.0001628895426518012, "loss": 0.6547666549682617, "step": 186760 }, { "epoch": 1.110199665935529, "grad_norm": 1.633736491203308, "learning_rate": 0.00016288450602194512, "loss": 0.5651360511779785, "step": 186770 }, { "epoch": 1.1102591080121975, "grad_norm": 1.52765953540802, "learning_rate": 0.0001628794691391069, "loss": 0.570105791091919, "step": 186780 }, { "epoch": 1.110318550088866, "grad_norm": 1.6449438333511353, "learning_rate": 0.00016287443200331062, "loss": 0.6415282249450683, "step": 186790 }, { "epoch": 1.1103779921655343, "grad_norm": 1.3226252794265747, "learning_rate": 0.00016286939461458027, "loss": 0.6120635509490967, "step": 186800 }, { "epoch": 1.1104374342422028, "grad_norm": 1.1765037775039673, "learning_rate": 0.00016286435697294004, "loss": 0.6253901958465576, "step": 186810 }, { "epoch": 1.1104968763188712, "grad_norm": 1.4119621515274048, "learning_rate": 0.00016285931907841398, "loss": 0.5917045593261718, "step": 186820 }, { "epoch": 1.1105563183955394, "grad_norm": 1.4475425481796265, "learning_rate": 0.00016285428093102623, "loss": 0.6364846229553223, "step": 186830 }, { "epoch": 1.1106157604722078, "grad_norm": 1.6240439414978027, "learning_rate": 0.00016284924253080087, "loss": 0.6135085582733154, "step": 186840 }, { "epoch": 1.1106752025488762, "grad_norm": 2.0238916873931885, "learning_rate": 0.00016284420387776202, "loss": 0.599894666671753, "step": 186850 }, { "epoch": 1.1107346446255446, "grad_norm": 1.5650569200515747, "learning_rate": 0.00016283916497193376, "loss": 0.587040901184082, "step": 186860 }, { "epoch": 1.110794086702213, "grad_norm": 1.2961515188217163, "learning_rate": 0.00016283412581334018, "loss": 0.6790194511413574, "step": 186870 }, { "epoch": 1.1108535287788814, "grad_norm": 1.6147751808166504, "learning_rate": 0.00016282908640200545, "loss": 0.6033064842224121, "step": 186880 }, { "epoch": 1.1109129708555499, "grad_norm": 1.626811146736145, "learning_rate": 0.0001628240467379536, "loss": 0.6711179733276367, "step": 186890 }, { "epoch": 1.1109724129322183, "grad_norm": 1.648615837097168, "learning_rate": 0.00016281900682120877, "loss": 0.6508725643157959, "step": 186900 }, { "epoch": 1.1110318550088867, "grad_norm": 1.5592057704925537, "learning_rate": 0.00016281396665179508, "loss": 0.6830899238586425, "step": 186910 }, { "epoch": 1.1110912970855549, "grad_norm": 1.8574384450912476, "learning_rate": 0.00016280892622973667, "loss": 0.6252073287963867, "step": 186920 }, { "epoch": 1.1111507391622233, "grad_norm": 1.7521620988845825, "learning_rate": 0.00016280388555505755, "loss": 0.6407153129577636, "step": 186930 }, { "epoch": 1.1112101812388917, "grad_norm": 1.838031530380249, "learning_rate": 0.00016279884462778196, "loss": 0.6608229637145996, "step": 186940 }, { "epoch": 1.1112696233155601, "grad_norm": 1.3903876543045044, "learning_rate": 0.00016279380344793394, "loss": 0.6409206390380859, "step": 186950 }, { "epoch": 1.1113290653922285, "grad_norm": 1.8809738159179688, "learning_rate": 0.00016278876201553758, "loss": 0.6269103050231933, "step": 186960 }, { "epoch": 1.111388507468897, "grad_norm": 1.7300885915756226, "learning_rate": 0.00016278372033061707, "loss": 0.6700314998626709, "step": 186970 }, { "epoch": 1.1114479495455654, "grad_norm": 1.720681071281433, "learning_rate": 0.0001627786783931965, "loss": 0.6763018131256103, "step": 186980 }, { "epoch": 1.1115073916222338, "grad_norm": 1.9038634300231934, "learning_rate": 0.00016277363620329993, "loss": 0.6088836669921875, "step": 186990 }, { "epoch": 1.1115668336989022, "grad_norm": 1.7387615442276, "learning_rate": 0.0001627685937609516, "loss": 0.6264252662658691, "step": 187000 }, { "epoch": 1.1116262757755706, "grad_norm": 1.4398939609527588, "learning_rate": 0.0001627635510661755, "loss": 0.6197854042053222, "step": 187010 }, { "epoch": 1.1116857178522388, "grad_norm": 1.4022557735443115, "learning_rate": 0.00016275850811899582, "loss": 0.6191770553588867, "step": 187020 }, { "epoch": 1.1117451599289072, "grad_norm": 1.4221646785736084, "learning_rate": 0.00016275346491943674, "loss": 0.6138986587524414, "step": 187030 }, { "epoch": 1.1118046020055756, "grad_norm": 1.566038966178894, "learning_rate": 0.00016274842146752225, "loss": 0.649632740020752, "step": 187040 }, { "epoch": 1.111864044082244, "grad_norm": 1.3395875692367554, "learning_rate": 0.0001627433777632766, "loss": 0.552853775024414, "step": 187050 }, { "epoch": 1.1119234861589125, "grad_norm": 1.8091247081756592, "learning_rate": 0.00016273833380672385, "loss": 0.7160953521728516, "step": 187060 }, { "epoch": 1.1119829282355809, "grad_norm": 1.4085338115692139, "learning_rate": 0.00016273328959788813, "loss": 0.5789209842681885, "step": 187070 }, { "epoch": 1.1120423703122493, "grad_norm": 1.5610806941986084, "learning_rate": 0.0001627282451367936, "loss": 0.5912316322326661, "step": 187080 }, { "epoch": 1.1121018123889177, "grad_norm": 1.5797985792160034, "learning_rate": 0.00016272320042346437, "loss": 0.5866330146789551, "step": 187090 }, { "epoch": 1.1121612544655861, "grad_norm": 1.9485447406768799, "learning_rate": 0.00016271815545792462, "loss": 0.6475006580352783, "step": 187100 }, { "epoch": 1.1122206965422543, "grad_norm": 1.7397079467773438, "learning_rate": 0.0001627131102401984, "loss": 0.6240694999694825, "step": 187110 }, { "epoch": 1.1122801386189227, "grad_norm": 1.4813376665115356, "learning_rate": 0.0001627080647703099, "loss": 0.6139115810394287, "step": 187120 }, { "epoch": 1.1123395806955911, "grad_norm": 1.3059861660003662, "learning_rate": 0.00016270301904828326, "loss": 0.6067500114440918, "step": 187130 }, { "epoch": 1.1123990227722595, "grad_norm": 1.3109087944030762, "learning_rate": 0.0001626979730741426, "loss": 0.6081634998321533, "step": 187140 }, { "epoch": 1.112458464848928, "grad_norm": 1.5961259603500366, "learning_rate": 0.00016269292684791198, "loss": 0.625677490234375, "step": 187150 }, { "epoch": 1.1125179069255964, "grad_norm": 1.8591974973678589, "learning_rate": 0.0001626878803696157, "loss": 0.6552956581115723, "step": 187160 }, { "epoch": 1.1125773490022648, "grad_norm": 1.3291170597076416, "learning_rate": 0.00016268283363927782, "loss": 0.5840322494506835, "step": 187170 }, { "epoch": 1.1126367910789332, "grad_norm": 1.6854188442230225, "learning_rate": 0.00016267778665692245, "loss": 0.6488551139831543, "step": 187180 }, { "epoch": 1.1126962331556016, "grad_norm": 1.5722569227218628, "learning_rate": 0.00016267273942257378, "loss": 0.652642822265625, "step": 187190 }, { "epoch": 1.1127556752322698, "grad_norm": 1.606799602508545, "learning_rate": 0.00016266769193625592, "loss": 0.707897424697876, "step": 187200 }, { "epoch": 1.1128151173089382, "grad_norm": 1.7387663125991821, "learning_rate": 0.00016266264419799304, "loss": 0.6067479610443115, "step": 187210 }, { "epoch": 1.1128745593856066, "grad_norm": 1.8268094062805176, "learning_rate": 0.0001626575962078093, "loss": 0.5643145561218261, "step": 187220 }, { "epoch": 1.112934001462275, "grad_norm": 1.4005964994430542, "learning_rate": 0.0001626525479657288, "loss": 0.5771451950073242, "step": 187230 }, { "epoch": 1.1129934435389435, "grad_norm": 1.7403186559677124, "learning_rate": 0.00016264749947177574, "loss": 0.566461706161499, "step": 187240 }, { "epoch": 1.1130528856156119, "grad_norm": 1.3656846284866333, "learning_rate": 0.00016264245072597424, "loss": 0.5721381664276123, "step": 187250 }, { "epoch": 1.1131123276922803, "grad_norm": 1.6286782026290894, "learning_rate": 0.00016263740172834846, "loss": 0.6446759223937988, "step": 187260 }, { "epoch": 1.1131717697689487, "grad_norm": 2.163994073867798, "learning_rate": 0.00016263235247892255, "loss": 0.6174599170684815, "step": 187270 }, { "epoch": 1.1132312118456171, "grad_norm": 1.772737979888916, "learning_rate": 0.0001626273029777207, "loss": 0.6397258758544921, "step": 187280 }, { "epoch": 1.1132906539222853, "grad_norm": 1.3181865215301514, "learning_rate": 0.000162622253224767, "loss": 0.6217046737670898, "step": 187290 }, { "epoch": 1.1133500959989537, "grad_norm": 1.7306740283966064, "learning_rate": 0.00016261720322008558, "loss": 0.5564330577850342, "step": 187300 }, { "epoch": 1.1134095380756222, "grad_norm": 2.153404712677002, "learning_rate": 0.00016261215296370073, "loss": 0.7117226600646973, "step": 187310 }, { "epoch": 1.1134689801522906, "grad_norm": 1.694154977798462, "learning_rate": 0.0001626071024556365, "loss": 0.6181565284729004, "step": 187320 }, { "epoch": 1.113528422228959, "grad_norm": 1.4585034847259521, "learning_rate": 0.0001626020516959171, "loss": 0.6351283073425293, "step": 187330 }, { "epoch": 1.1135878643056274, "grad_norm": 1.722524642944336, "learning_rate": 0.0001625970006845667, "loss": 0.7018064498901367, "step": 187340 }, { "epoch": 1.1136473063822958, "grad_norm": 1.872529149055481, "learning_rate": 0.0001625919494216094, "loss": 0.6469122886657714, "step": 187350 }, { "epoch": 1.1137067484589642, "grad_norm": 1.6626087427139282, "learning_rate": 0.00016258689790706943, "loss": 0.6427406311035156, "step": 187360 }, { "epoch": 1.1137661905356326, "grad_norm": 1.5765690803527832, "learning_rate": 0.0001625818461409709, "loss": 0.596518611907959, "step": 187370 }, { "epoch": 1.113825632612301, "grad_norm": 1.680287480354309, "learning_rate": 0.00016257679412333802, "loss": 0.6734199047088623, "step": 187380 }, { "epoch": 1.1138850746889692, "grad_norm": 1.4256044626235962, "learning_rate": 0.00016257174185419494, "loss": 0.6152531623840332, "step": 187390 }, { "epoch": 1.1139445167656377, "grad_norm": 1.4533182382583618, "learning_rate": 0.0001625666893335658, "loss": 0.5675915718078614, "step": 187400 }, { "epoch": 1.114003958842306, "grad_norm": 1.2962071895599365, "learning_rate": 0.00016256163656147484, "loss": 0.6267284393310547, "step": 187410 }, { "epoch": 1.1140634009189745, "grad_norm": 1.9945740699768066, "learning_rate": 0.00016255658353794616, "loss": 0.6446099281311035, "step": 187420 }, { "epoch": 1.114122842995643, "grad_norm": 1.483992576599121, "learning_rate": 0.00016255153026300393, "loss": 0.5884251117706298, "step": 187430 }, { "epoch": 1.1141822850723113, "grad_norm": 1.1502832174301147, "learning_rate": 0.00016254647673667242, "loss": 0.6380922317504882, "step": 187440 }, { "epoch": 1.1142417271489797, "grad_norm": 2.1068174839019775, "learning_rate": 0.0001625414229589757, "loss": 0.5567087650299072, "step": 187450 }, { "epoch": 1.1143011692256481, "grad_norm": 1.8664443492889404, "learning_rate": 0.00016253636892993797, "loss": 0.5716665267944336, "step": 187460 }, { "epoch": 1.1143606113023166, "grad_norm": 1.6365669965744019, "learning_rate": 0.00016253131464958345, "loss": 0.6124938488006592, "step": 187470 }, { "epoch": 1.1144200533789848, "grad_norm": 1.2610344886779785, "learning_rate": 0.00016252626011793625, "loss": 0.5447526931762695, "step": 187480 }, { "epoch": 1.1144794954556532, "grad_norm": 1.602999210357666, "learning_rate": 0.00016252120533502063, "loss": 0.6283404350280761, "step": 187490 }, { "epoch": 1.1145389375323216, "grad_norm": 1.6585017442703247, "learning_rate": 0.0001625161503008607, "loss": 0.6364851951599121, "step": 187500 }, { "epoch": 1.11459837960899, "grad_norm": 1.3123598098754883, "learning_rate": 0.0001625110950154807, "loss": 0.6299357414245605, "step": 187510 }, { "epoch": 1.1146578216856584, "grad_norm": 1.6921753883361816, "learning_rate": 0.00016250603947890477, "loss": 0.6223263263702392, "step": 187520 }, { "epoch": 1.1147172637623268, "grad_norm": 1.8241287469863892, "learning_rate": 0.0001625009836911571, "loss": 0.6161512851715087, "step": 187530 }, { "epoch": 1.1147767058389952, "grad_norm": 1.374080777168274, "learning_rate": 0.00016249592765226186, "loss": 0.5900362968444824, "step": 187540 }, { "epoch": 1.1148361479156637, "grad_norm": 1.5220638513565063, "learning_rate": 0.0001624908713622433, "loss": 0.6137893199920654, "step": 187550 }, { "epoch": 1.114895589992332, "grad_norm": 1.5220905542373657, "learning_rate": 0.00016248581482112553, "loss": 0.6477842330932617, "step": 187560 }, { "epoch": 1.1149550320690003, "grad_norm": 1.3206636905670166, "learning_rate": 0.00016248075802893279, "loss": 0.6126948356628418, "step": 187570 }, { "epoch": 1.1150144741456687, "grad_norm": 1.408715009689331, "learning_rate": 0.00016247570098568926, "loss": 0.6244563579559326, "step": 187580 }, { "epoch": 1.115073916222337, "grad_norm": 1.6270322799682617, "learning_rate": 0.00016247064369141913, "loss": 0.6163689613342285, "step": 187590 }, { "epoch": 1.1151333582990055, "grad_norm": 1.6896008253097534, "learning_rate": 0.00016246558614614658, "loss": 0.598678731918335, "step": 187600 }, { "epoch": 1.115192800375674, "grad_norm": 2.3242366313934326, "learning_rate": 0.0001624605283498958, "loss": 0.6256197452545166, "step": 187610 }, { "epoch": 1.1152522424523423, "grad_norm": 1.4403561353683472, "learning_rate": 0.000162455470302691, "loss": 0.5452484130859375, "step": 187620 }, { "epoch": 1.1153116845290107, "grad_norm": 1.4595837593078613, "learning_rate": 0.00016245041200455639, "loss": 0.631532859802246, "step": 187630 }, { "epoch": 1.1153711266056792, "grad_norm": 1.628469705581665, "learning_rate": 0.00016244535345551615, "loss": 0.6497533798217774, "step": 187640 }, { "epoch": 1.1154305686823476, "grad_norm": 1.3928110599517822, "learning_rate": 0.00016244029465559446, "loss": 0.6169627189636231, "step": 187650 }, { "epoch": 1.1154900107590158, "grad_norm": 1.6947263479232788, "learning_rate": 0.00016243523560481552, "loss": 0.6734692573547363, "step": 187660 }, { "epoch": 1.1155494528356842, "grad_norm": 1.6856940984725952, "learning_rate": 0.00016243017630320362, "loss": 0.6021594047546387, "step": 187670 }, { "epoch": 1.1156088949123526, "grad_norm": 1.9769444465637207, "learning_rate": 0.0001624251167507828, "loss": 0.5762706279754639, "step": 187680 }, { "epoch": 1.115668336989021, "grad_norm": 1.376232385635376, "learning_rate": 0.0001624200569475774, "loss": 0.6043136596679688, "step": 187690 }, { "epoch": 1.1157277790656894, "grad_norm": 1.684019923210144, "learning_rate": 0.0001624149968936116, "loss": 0.653485631942749, "step": 187700 }, { "epoch": 1.1157872211423578, "grad_norm": 1.5066717863082886, "learning_rate": 0.00016240993658890956, "loss": 0.603139591217041, "step": 187710 }, { "epoch": 1.1158466632190263, "grad_norm": 1.4958207607269287, "learning_rate": 0.00016240487603349553, "loss": 0.596142578125, "step": 187720 }, { "epoch": 1.1159061052956947, "grad_norm": 1.3036023378372192, "learning_rate": 0.00016239981522739368, "loss": 0.6195292949676514, "step": 187730 }, { "epoch": 1.115965547372363, "grad_norm": 1.3381400108337402, "learning_rate": 0.00016239475417062824, "loss": 0.606138801574707, "step": 187740 }, { "epoch": 1.1160249894490315, "grad_norm": 1.555712342262268, "learning_rate": 0.0001623896928632234, "loss": 0.6417965412139892, "step": 187750 }, { "epoch": 1.1160844315256997, "grad_norm": 1.662238597869873, "learning_rate": 0.0001623846313052034, "loss": 0.6480892181396485, "step": 187760 }, { "epoch": 1.116143873602368, "grad_norm": 1.4936906099319458, "learning_rate": 0.00016237956949659247, "loss": 0.5851424694061279, "step": 187770 }, { "epoch": 1.1162033156790365, "grad_norm": 1.6995112895965576, "learning_rate": 0.00016237450743741475, "loss": 0.6504203796386718, "step": 187780 }, { "epoch": 1.116262757755705, "grad_norm": 1.993434190750122, "learning_rate": 0.00016236944512769454, "loss": 0.5728711605072021, "step": 187790 }, { "epoch": 1.1163221998323734, "grad_norm": 1.4500466585159302, "learning_rate": 0.00016236438256745606, "loss": 0.6442754745483399, "step": 187800 }, { "epoch": 1.1163816419090418, "grad_norm": 2.0946152210235596, "learning_rate": 0.0001623593197567234, "loss": 0.6182711601257325, "step": 187810 }, { "epoch": 1.1164410839857102, "grad_norm": 1.7793477773666382, "learning_rate": 0.0001623542566955209, "loss": 0.7030409336090088, "step": 187820 }, { "epoch": 1.1165005260623786, "grad_norm": 1.8738690614700317, "learning_rate": 0.00016234919338387274, "loss": 0.6420570373535156, "step": 187830 }, { "epoch": 1.1165599681390468, "grad_norm": 1.737156867980957, "learning_rate": 0.00016234412982180319, "loss": 0.5954972267150879, "step": 187840 }, { "epoch": 1.1166194102157152, "grad_norm": 1.8370697498321533, "learning_rate": 0.0001623390660093364, "loss": 0.7111645698547363, "step": 187850 }, { "epoch": 1.1166788522923836, "grad_norm": 1.685699701309204, "learning_rate": 0.00016233400194649663, "loss": 0.5651898384094238, "step": 187860 }, { "epoch": 1.116738294369052, "grad_norm": 1.6345893144607544, "learning_rate": 0.00016232893763330804, "loss": 0.6466506481170654, "step": 187870 }, { "epoch": 1.1167977364457204, "grad_norm": 1.1696877479553223, "learning_rate": 0.000162323873069795, "loss": 0.571877384185791, "step": 187880 }, { "epoch": 1.1168571785223889, "grad_norm": 1.7137045860290527, "learning_rate": 0.0001623188082559816, "loss": 0.6586883544921875, "step": 187890 }, { "epoch": 1.1169166205990573, "grad_norm": 1.7936930656433105, "learning_rate": 0.00016231374319189214, "loss": 0.6486348152160645, "step": 187900 }, { "epoch": 1.1169760626757257, "grad_norm": 1.4697670936584473, "learning_rate": 0.0001623086778775508, "loss": 0.6003622531890869, "step": 187910 }, { "epoch": 1.117035504752394, "grad_norm": 1.3332798480987549, "learning_rate": 0.00016230361231298185, "loss": 0.5773153305053711, "step": 187920 }, { "epoch": 1.1170949468290625, "grad_norm": 1.8272947072982788, "learning_rate": 0.00016229854649820954, "loss": 0.618379020690918, "step": 187930 }, { "epoch": 1.1171543889057307, "grad_norm": 1.6271655559539795, "learning_rate": 0.00016229348043325805, "loss": 0.6151970386505127, "step": 187940 }, { "epoch": 1.1172138309823991, "grad_norm": 1.5670775175094604, "learning_rate": 0.00016228841411815162, "loss": 0.6307590007781982, "step": 187950 }, { "epoch": 1.1172732730590675, "grad_norm": 1.4866228103637695, "learning_rate": 0.00016228334755291455, "loss": 0.6589708805084229, "step": 187960 }, { "epoch": 1.117332715135736, "grad_norm": 1.485350251197815, "learning_rate": 0.00016227828073757101, "loss": 0.6409051895141602, "step": 187970 }, { "epoch": 1.1173921572124044, "grad_norm": 1.8178905248641968, "learning_rate": 0.00016227321367214527, "loss": 0.6517200946807862, "step": 187980 }, { "epoch": 1.1174515992890728, "grad_norm": 1.5343284606933594, "learning_rate": 0.00016226814635666154, "loss": 0.635091495513916, "step": 187990 }, { "epoch": 1.1175110413657412, "grad_norm": 1.2565104961395264, "learning_rate": 0.00016226307879114407, "loss": 0.6226815223693848, "step": 188000 }, { "epoch": 1.1175704834424096, "grad_norm": 1.7547540664672852, "learning_rate": 0.00016225801097561717, "loss": 0.6397494316101074, "step": 188010 }, { "epoch": 1.117629925519078, "grad_norm": 1.4328662157058716, "learning_rate": 0.00016225294291010497, "loss": 0.5559170246124268, "step": 188020 }, { "epoch": 1.1176893675957462, "grad_norm": 1.438796877861023, "learning_rate": 0.0001622478745946318, "loss": 0.6815804481506348, "step": 188030 }, { "epoch": 1.1177488096724146, "grad_norm": 1.7836812734603882, "learning_rate": 0.00016224280602922185, "loss": 0.6024325370788575, "step": 188040 }, { "epoch": 1.117808251749083, "grad_norm": 1.239683985710144, "learning_rate": 0.00016223773721389938, "loss": 0.6411561012268067, "step": 188050 }, { "epoch": 1.1178676938257515, "grad_norm": 1.5211538076400757, "learning_rate": 0.00016223266814868864, "loss": 0.6327259063720703, "step": 188060 }, { "epoch": 1.1179271359024199, "grad_norm": 1.3310092687606812, "learning_rate": 0.00016222759883361394, "loss": 0.6326959609985352, "step": 188070 }, { "epoch": 1.1179865779790883, "grad_norm": 1.589737892150879, "learning_rate": 0.00016222252926869943, "loss": 0.6267066955566406, "step": 188080 }, { "epoch": 1.1180460200557567, "grad_norm": 1.5831547975540161, "learning_rate": 0.00016221745945396943, "loss": 0.6615317821502685, "step": 188090 }, { "epoch": 1.1181054621324251, "grad_norm": 2.131037473678589, "learning_rate": 0.00016221238938944813, "loss": 0.6554885864257812, "step": 188100 }, { "epoch": 1.1181649042090935, "grad_norm": 1.6539493799209595, "learning_rate": 0.00016220731907515986, "loss": 0.5868916511535645, "step": 188110 }, { "epoch": 1.118224346285762, "grad_norm": 2.280421495437622, "learning_rate": 0.00016220224851112882, "loss": 0.630806303024292, "step": 188120 }, { "epoch": 1.1182837883624301, "grad_norm": 1.285888671875, "learning_rate": 0.00016219717769737926, "loss": 0.591982078552246, "step": 188130 }, { "epoch": 1.1183432304390986, "grad_norm": 1.483046054840088, "learning_rate": 0.0001621921066339355, "loss": 0.6537728309631348, "step": 188140 }, { "epoch": 1.118402672515767, "grad_norm": 1.52921724319458, "learning_rate": 0.00016218703532082176, "loss": 0.5889369487762451, "step": 188150 }, { "epoch": 1.1184621145924354, "grad_norm": 1.5816494226455688, "learning_rate": 0.0001621819637580623, "loss": 0.6071007728576661, "step": 188160 }, { "epoch": 1.1185215566691038, "grad_norm": 1.523414134979248, "learning_rate": 0.00016217689194568136, "loss": 0.6245424270629882, "step": 188170 }, { "epoch": 1.1185809987457722, "grad_norm": 1.9794745445251465, "learning_rate": 0.0001621718198837032, "loss": 0.6014968872070312, "step": 188180 }, { "epoch": 1.1186404408224406, "grad_norm": 1.6538876295089722, "learning_rate": 0.00016216674757215215, "loss": 0.624150276184082, "step": 188190 }, { "epoch": 1.118699882899109, "grad_norm": 1.6932905912399292, "learning_rate": 0.00016216167501105242, "loss": 0.6249743461608886, "step": 188200 }, { "epoch": 1.1187593249757772, "grad_norm": 1.6609776020050049, "learning_rate": 0.00016215660220042825, "loss": 0.6076017379760742, "step": 188210 }, { "epoch": 1.1188187670524457, "grad_norm": 2.0349395275115967, "learning_rate": 0.00016215152914030395, "loss": 0.6140423774719238, "step": 188220 }, { "epoch": 1.118878209129114, "grad_norm": 1.924882173538208, "learning_rate": 0.0001621464558307038, "loss": 0.6718103885650635, "step": 188230 }, { "epoch": 1.1189376512057825, "grad_norm": 1.5027556419372559, "learning_rate": 0.00016214138227165203, "loss": 0.5531262397766114, "step": 188240 }, { "epoch": 1.118997093282451, "grad_norm": 1.339503526687622, "learning_rate": 0.00016213630846317293, "loss": 0.5874626159667968, "step": 188250 }, { "epoch": 1.1190565353591193, "grad_norm": 1.587546467781067, "learning_rate": 0.0001621312344052908, "loss": 0.6370431900024414, "step": 188260 }, { "epoch": 1.1191159774357877, "grad_norm": 1.5156253576278687, "learning_rate": 0.00016212616009802982, "loss": 0.64346284866333, "step": 188270 }, { "epoch": 1.1191754195124561, "grad_norm": 1.7557916641235352, "learning_rate": 0.00016212108554141435, "loss": 0.6029534816741944, "step": 188280 }, { "epoch": 1.1192348615891246, "grad_norm": 1.369131326675415, "learning_rate": 0.00016211601073546866, "loss": 0.5918136596679687, "step": 188290 }, { "epoch": 1.119294303665793, "grad_norm": 1.93233060836792, "learning_rate": 0.000162110935680217, "loss": 0.6137357711791992, "step": 188300 }, { "epoch": 1.1193537457424612, "grad_norm": 1.4542053937911987, "learning_rate": 0.00016210586037568366, "loss": 0.6126775741577148, "step": 188310 }, { "epoch": 1.1194131878191296, "grad_norm": 1.606834888458252, "learning_rate": 0.00016210078482189287, "loss": 0.6383413314819336, "step": 188320 }, { "epoch": 1.119472629895798, "grad_norm": 1.3929742574691772, "learning_rate": 0.000162095709018869, "loss": 0.6298892974853516, "step": 188330 }, { "epoch": 1.1195320719724664, "grad_norm": 1.3745239973068237, "learning_rate": 0.00016209063296663626, "loss": 0.6184018135070801, "step": 188340 }, { "epoch": 1.1195915140491348, "grad_norm": 1.5658364295959473, "learning_rate": 0.00016208555666521893, "loss": 0.5980003833770752, "step": 188350 }, { "epoch": 1.1196509561258032, "grad_norm": 1.3895516395568848, "learning_rate": 0.00016208048011464134, "loss": 0.6909173011779786, "step": 188360 }, { "epoch": 1.1197103982024716, "grad_norm": 1.6836669445037842, "learning_rate": 0.00016207540331492776, "loss": 0.6193949699401855, "step": 188370 }, { "epoch": 1.11976984027914, "grad_norm": 1.5448161363601685, "learning_rate": 0.0001620703262661025, "loss": 0.6717665672302247, "step": 188380 }, { "epoch": 1.1198292823558085, "grad_norm": 1.462154746055603, "learning_rate": 0.0001620652489681898, "loss": 0.6217789649963379, "step": 188390 }, { "epoch": 1.1198887244324767, "grad_norm": 1.6162657737731934, "learning_rate": 0.00016206017142121392, "loss": 0.6319538116455078, "step": 188400 }, { "epoch": 1.119948166509145, "grad_norm": 1.5541784763336182, "learning_rate": 0.0001620550936251992, "loss": 0.6193541526794434, "step": 188410 }, { "epoch": 1.1200076085858135, "grad_norm": 1.8366212844848633, "learning_rate": 0.00016205001558017, "loss": 0.6083538055419921, "step": 188420 }, { "epoch": 1.120067050662482, "grad_norm": 1.6769828796386719, "learning_rate": 0.00016204493728615046, "loss": 0.6249368190765381, "step": 188430 }, { "epoch": 1.1201264927391503, "grad_norm": 1.2570942640304565, "learning_rate": 0.00016203985874316498, "loss": 0.6259410381317139, "step": 188440 }, { "epoch": 1.1201859348158187, "grad_norm": 2.016758441925049, "learning_rate": 0.0001620347799512378, "loss": 0.6280069351196289, "step": 188450 }, { "epoch": 1.1202453768924872, "grad_norm": 1.7788746356964111, "learning_rate": 0.00016202970091039326, "loss": 0.5876047134399414, "step": 188460 }, { "epoch": 1.1203048189691556, "grad_norm": 2.028102397918701, "learning_rate": 0.00016202462162065564, "loss": 0.653260612487793, "step": 188470 }, { "epoch": 1.120364261045824, "grad_norm": 1.8603484630584717, "learning_rate": 0.00016201954208204918, "loss": 0.6227516174316406, "step": 188480 }, { "epoch": 1.1204237031224924, "grad_norm": 1.3467077016830444, "learning_rate": 0.00016201446229459828, "loss": 0.616319227218628, "step": 188490 }, { "epoch": 1.1204831451991606, "grad_norm": 1.2221546173095703, "learning_rate": 0.0001620093822583272, "loss": 0.6420334815979004, "step": 188500 }, { "epoch": 1.120542587275829, "grad_norm": 1.6069554090499878, "learning_rate": 0.0001620043019732602, "loss": 0.645073413848877, "step": 188510 }, { "epoch": 1.1206020293524974, "grad_norm": 1.4741557836532593, "learning_rate": 0.00016199922143942164, "loss": 0.5696239471435547, "step": 188520 }, { "epoch": 1.1206614714291658, "grad_norm": 1.4125474691390991, "learning_rate": 0.00016199414065683576, "loss": 0.6331507205963135, "step": 188530 }, { "epoch": 1.1207209135058342, "grad_norm": 1.4818637371063232, "learning_rate": 0.00016198905962552695, "loss": 0.5695947647094727, "step": 188540 }, { "epoch": 1.1207803555825027, "grad_norm": 1.6943758726119995, "learning_rate": 0.00016198397834551944, "loss": 0.6301052570343018, "step": 188550 }, { "epoch": 1.120839797659171, "grad_norm": 1.65155827999115, "learning_rate": 0.00016197889681683758, "loss": 0.5690571784973144, "step": 188560 }, { "epoch": 1.1208992397358395, "grad_norm": 5.5455851554870605, "learning_rate": 0.00016197381503950566, "loss": 0.7622929573059082, "step": 188570 }, { "epoch": 1.1209586818125077, "grad_norm": 1.8826472759246826, "learning_rate": 0.000161968733013548, "loss": 0.6589779853820801, "step": 188580 }, { "epoch": 1.121018123889176, "grad_norm": 1.445645809173584, "learning_rate": 0.00016196365073898887, "loss": 0.6322935581207275, "step": 188590 }, { "epoch": 1.1210775659658445, "grad_norm": 1.5454246997833252, "learning_rate": 0.00016195856821585265, "loss": 0.6191751480102539, "step": 188600 }, { "epoch": 1.121137008042513, "grad_norm": 1.6627476215362549, "learning_rate": 0.00016195348544416363, "loss": 0.6236868858337402, "step": 188610 }, { "epoch": 1.1211964501191813, "grad_norm": 1.0161455869674683, "learning_rate": 0.00016194840242394608, "loss": 0.5917639255523681, "step": 188620 }, { "epoch": 1.1212558921958498, "grad_norm": 1.6151320934295654, "learning_rate": 0.00016194331915522436, "loss": 0.6664239883422851, "step": 188630 }, { "epoch": 1.1213153342725182, "grad_norm": 1.5512168407440186, "learning_rate": 0.0001619382356380228, "loss": 0.6154714584350586, "step": 188640 }, { "epoch": 1.1213747763491866, "grad_norm": 1.508531093597412, "learning_rate": 0.00016193315187236566, "loss": 0.643302583694458, "step": 188650 }, { "epoch": 1.121434218425855, "grad_norm": 1.5910606384277344, "learning_rate": 0.0001619280678582773, "loss": 0.5722685813903808, "step": 188660 }, { "epoch": 1.1214936605025234, "grad_norm": 1.4088249206542969, "learning_rate": 0.00016192298359578205, "loss": 0.6202677249908447, "step": 188670 }, { "epoch": 1.1215531025791916, "grad_norm": 1.7240854501724243, "learning_rate": 0.0001619178990849042, "loss": 0.6417782783508301, "step": 188680 }, { "epoch": 1.12161254465586, "grad_norm": 1.5685818195343018, "learning_rate": 0.0001619128143256681, "loss": 0.6558547019958496, "step": 188690 }, { "epoch": 1.1216719867325284, "grad_norm": 1.6103113889694214, "learning_rate": 0.00016190772931809808, "loss": 0.572272539138794, "step": 188700 }, { "epoch": 1.1217314288091969, "grad_norm": 1.8486963510513306, "learning_rate": 0.00016190264406221842, "loss": 0.5952045440673828, "step": 188710 }, { "epoch": 1.1217908708858653, "grad_norm": 1.4635499715805054, "learning_rate": 0.00016189755855805347, "loss": 0.604926347732544, "step": 188720 }, { "epoch": 1.1218503129625337, "grad_norm": 1.6291402578353882, "learning_rate": 0.0001618924728056276, "loss": 0.6566410064697266, "step": 188730 }, { "epoch": 1.121909755039202, "grad_norm": 1.4012372493743896, "learning_rate": 0.00016188738680496506, "loss": 0.5296585083007812, "step": 188740 }, { "epoch": 1.1219691971158705, "grad_norm": 1.8101426362991333, "learning_rate": 0.0001618823005560902, "loss": 0.6356059074401855, "step": 188750 }, { "epoch": 1.122028639192539, "grad_norm": 1.3547699451446533, "learning_rate": 0.00016187721405902742, "loss": 0.5546637535095215, "step": 188760 }, { "epoch": 1.1220880812692071, "grad_norm": 1.654884696006775, "learning_rate": 0.00016187212731380097, "loss": 0.6469542980194092, "step": 188770 }, { "epoch": 1.1221475233458755, "grad_norm": 1.7255312204360962, "learning_rate": 0.00016186704032043522, "loss": 0.6394773483276367, "step": 188780 }, { "epoch": 1.122206965422544, "grad_norm": 1.3288333415985107, "learning_rate": 0.0001618619530789545, "loss": 0.6202025413513184, "step": 188790 }, { "epoch": 1.1222664074992124, "grad_norm": 1.9376578330993652, "learning_rate": 0.00016185686558938315, "loss": 0.634483814239502, "step": 188800 }, { "epoch": 1.1223258495758808, "grad_norm": 1.759037733078003, "learning_rate": 0.0001618517778517455, "loss": 0.5656567096710206, "step": 188810 }, { "epoch": 1.1223852916525492, "grad_norm": 1.5415209531784058, "learning_rate": 0.00016184668986606588, "loss": 0.552696704864502, "step": 188820 }, { "epoch": 1.1224447337292176, "grad_norm": 1.380322813987732, "learning_rate": 0.00016184160163236865, "loss": 0.5957791805267334, "step": 188830 }, { "epoch": 1.122504175805886, "grad_norm": 1.671180248260498, "learning_rate": 0.00016183651315067815, "loss": 0.5977376461029053, "step": 188840 }, { "epoch": 1.1225636178825544, "grad_norm": 1.6100391149520874, "learning_rate": 0.00016183142442101868, "loss": 0.630150318145752, "step": 188850 }, { "epoch": 1.1226230599592228, "grad_norm": 1.920226812362671, "learning_rate": 0.00016182633544341467, "loss": 0.6266613006591797, "step": 188860 }, { "epoch": 1.122682502035891, "grad_norm": 1.7005528211593628, "learning_rate": 0.00016182124621789032, "loss": 0.6580415725708008, "step": 188870 }, { "epoch": 1.1227419441125595, "grad_norm": 1.596828579902649, "learning_rate": 0.00016181615674447014, "loss": 0.6386729717254639, "step": 188880 }, { "epoch": 1.1228013861892279, "grad_norm": 1.635593056678772, "learning_rate": 0.00016181106702317836, "loss": 0.6548192977905274, "step": 188890 }, { "epoch": 1.1228608282658963, "grad_norm": 1.8204339742660522, "learning_rate": 0.00016180597705403937, "loss": 0.6364933967590332, "step": 188900 }, { "epoch": 1.1229202703425647, "grad_norm": 1.937671184539795, "learning_rate": 0.00016180088683707757, "loss": 0.7097090721130371, "step": 188910 }, { "epoch": 1.1229797124192331, "grad_norm": 1.510077953338623, "learning_rate": 0.0001617957963723172, "loss": 0.611090087890625, "step": 188920 }, { "epoch": 1.1230391544959015, "grad_norm": 1.4168163537979126, "learning_rate": 0.0001617907056597827, "loss": 0.6788200378417969, "step": 188930 }, { "epoch": 1.12309859657257, "grad_norm": 1.4517735242843628, "learning_rate": 0.00016178561469949834, "loss": 0.6156414985656739, "step": 188940 }, { "epoch": 1.1231580386492381, "grad_norm": 1.865037441253662, "learning_rate": 0.00016178052349148856, "loss": 0.6923026084899903, "step": 188950 }, { "epoch": 1.1232174807259065, "grad_norm": 1.6761982440948486, "learning_rate": 0.00016177543203577767, "loss": 0.6085319519042969, "step": 188960 }, { "epoch": 1.123276922802575, "grad_norm": 1.6455692052841187, "learning_rate": 0.00016177034033239005, "loss": 0.6278545379638671, "step": 188970 }, { "epoch": 1.1233363648792434, "grad_norm": 1.963735818862915, "learning_rate": 0.00016176524838135001, "loss": 0.5645929336547851, "step": 188980 }, { "epoch": 1.1233958069559118, "grad_norm": 1.4860297441482544, "learning_rate": 0.00016176015618268196, "loss": 0.6177149772644043, "step": 188990 }, { "epoch": 1.1234552490325802, "grad_norm": 2.1024246215820312, "learning_rate": 0.00016175506373641025, "loss": 0.6514240264892578, "step": 189000 }, { "epoch": 1.1235146911092486, "grad_norm": 1.830304503440857, "learning_rate": 0.0001617499710425592, "loss": 0.6565037727355957, "step": 189010 }, { "epoch": 1.123574133185917, "grad_norm": 1.3763080835342407, "learning_rate": 0.00016174487810115322, "loss": 0.6319737911224366, "step": 189020 }, { "epoch": 1.1236335752625854, "grad_norm": 1.771202802658081, "learning_rate": 0.00016173978491221665, "loss": 0.6344608306884766, "step": 189030 }, { "epoch": 1.1236930173392539, "grad_norm": 1.560760498046875, "learning_rate": 0.00016173469147577385, "loss": 0.6073308944702148, "step": 189040 }, { "epoch": 1.123752459415922, "grad_norm": 1.4085842370986938, "learning_rate": 0.0001617295977918492, "loss": 0.6314645290374756, "step": 189050 }, { "epoch": 1.1238119014925905, "grad_norm": 1.6394952535629272, "learning_rate": 0.00016172450386046705, "loss": 0.6167330741882324, "step": 189060 }, { "epoch": 1.1238713435692589, "grad_norm": 1.8825881481170654, "learning_rate": 0.00016171940968165178, "loss": 0.5291736602783204, "step": 189070 }, { "epoch": 1.1239307856459273, "grad_norm": 1.4905810356140137, "learning_rate": 0.00016171431525542775, "loss": 0.6006383419036865, "step": 189080 }, { "epoch": 1.1239902277225957, "grad_norm": 1.3609691858291626, "learning_rate": 0.00016170922058181936, "loss": 0.6096039772033691, "step": 189090 }, { "epoch": 1.1240496697992641, "grad_norm": 1.3498573303222656, "learning_rate": 0.00016170412566085093, "loss": 0.6790557861328125, "step": 189100 }, { "epoch": 1.1241091118759325, "grad_norm": 1.4823086261749268, "learning_rate": 0.0001616990304925469, "loss": 0.6148905754089355, "step": 189110 }, { "epoch": 1.124168553952601, "grad_norm": 1.686847448348999, "learning_rate": 0.00016169393507693155, "loss": 0.5895936012268066, "step": 189120 }, { "epoch": 1.1242279960292694, "grad_norm": 1.5214240550994873, "learning_rate": 0.00016168883941402933, "loss": 0.620270824432373, "step": 189130 }, { "epoch": 1.1242874381059376, "grad_norm": 1.6729062795639038, "learning_rate": 0.00016168374350386463, "loss": 0.6192299365997315, "step": 189140 }, { "epoch": 1.124346880182606, "grad_norm": 1.6983025074005127, "learning_rate": 0.00016167864734646173, "loss": 0.6533615589141846, "step": 189150 }, { "epoch": 1.1244063222592744, "grad_norm": 1.2250382900238037, "learning_rate": 0.00016167355094184513, "loss": 0.5968182563781739, "step": 189160 }, { "epoch": 1.1244657643359428, "grad_norm": 1.4507757425308228, "learning_rate": 0.0001616684542900391, "loss": 0.6067156314849853, "step": 189170 }, { "epoch": 1.1245252064126112, "grad_norm": 1.863322377204895, "learning_rate": 0.0001616633573910681, "loss": 0.6279110431671142, "step": 189180 }, { "epoch": 1.1245846484892796, "grad_norm": 1.6070201396942139, "learning_rate": 0.0001616582602449565, "loss": 0.6310630798339844, "step": 189190 }, { "epoch": 1.124644090565948, "grad_norm": 1.618247151374817, "learning_rate": 0.0001616531628517286, "loss": 0.614385986328125, "step": 189200 }, { "epoch": 1.1247035326426165, "grad_norm": 1.6850467920303345, "learning_rate": 0.00016164806521140889, "loss": 0.593330717086792, "step": 189210 }, { "epoch": 1.1247629747192849, "grad_norm": 1.495637059211731, "learning_rate": 0.0001616429673240217, "loss": 0.5838703155517578, "step": 189220 }, { "epoch": 1.1248224167959533, "grad_norm": 1.655003309249878, "learning_rate": 0.00016163786918959146, "loss": 0.6194987773895264, "step": 189230 }, { "epoch": 1.1248818588726215, "grad_norm": 1.3641338348388672, "learning_rate": 0.0001616327708081425, "loss": 0.57312912940979, "step": 189240 }, { "epoch": 1.12494130094929, "grad_norm": 1.6664916276931763, "learning_rate": 0.0001616276721796993, "loss": 0.5792860984802246, "step": 189250 }, { "epoch": 1.1250007430259583, "grad_norm": 1.161780595779419, "learning_rate": 0.00016162257330428612, "loss": 0.655312967300415, "step": 189260 }, { "epoch": 1.1250601851026267, "grad_norm": 1.5418130159378052, "learning_rate": 0.00016161747418192744, "loss": 0.6309784889221192, "step": 189270 }, { "epoch": 1.1251196271792951, "grad_norm": 1.4146302938461304, "learning_rate": 0.0001616123748126476, "loss": 0.6103302001953125, "step": 189280 }, { "epoch": 1.1251790692559636, "grad_norm": 1.5758272409439087, "learning_rate": 0.00016160727519647108, "loss": 0.7134722709655762, "step": 189290 }, { "epoch": 1.125238511332632, "grad_norm": 1.6467443704605103, "learning_rate": 0.00016160217533342218, "loss": 0.6031885147094727, "step": 189300 }, { "epoch": 1.1252979534093004, "grad_norm": 1.53895902633667, "learning_rate": 0.00016159707522352533, "loss": 0.6579980850219727, "step": 189310 }, { "epoch": 1.1253573954859686, "grad_norm": 1.5459281206130981, "learning_rate": 0.00016159197486680498, "loss": 0.6219260215759277, "step": 189320 }, { "epoch": 1.125416837562637, "grad_norm": 1.5273998975753784, "learning_rate": 0.00016158687426328546, "loss": 0.6883476734161377, "step": 189330 }, { "epoch": 1.1254762796393054, "grad_norm": 1.8659605979919434, "learning_rate": 0.0001615817734129912, "loss": 0.5974576950073243, "step": 189340 }, { "epoch": 1.1255357217159738, "grad_norm": 1.467111587524414, "learning_rate": 0.0001615766723159466, "loss": 0.6501970291137695, "step": 189350 }, { "epoch": 1.1255951637926422, "grad_norm": 1.3223243951797485, "learning_rate": 0.00016157157097217604, "loss": 0.5438727378845215, "step": 189360 }, { "epoch": 1.1256546058693107, "grad_norm": 1.4519788026809692, "learning_rate": 0.00016156646938170395, "loss": 0.7057703495025635, "step": 189370 }, { "epoch": 1.125714047945979, "grad_norm": 1.6292239427566528, "learning_rate": 0.0001615613675445547, "loss": 0.6300395965576172, "step": 189380 }, { "epoch": 1.1257734900226475, "grad_norm": 1.4038665294647217, "learning_rate": 0.00016155626546075273, "loss": 0.6256688117980957, "step": 189390 }, { "epoch": 1.125832932099316, "grad_norm": 1.3900779485702515, "learning_rate": 0.00016155116313032247, "loss": 0.6166462898254395, "step": 189400 }, { "epoch": 1.1258923741759843, "grad_norm": 1.6755173206329346, "learning_rate": 0.00016154606055328823, "loss": 0.6244410514831543, "step": 189410 }, { "epoch": 1.1259518162526527, "grad_norm": 1.4134758710861206, "learning_rate": 0.0001615409577296745, "loss": 0.603042459487915, "step": 189420 }, { "epoch": 1.126011258329321, "grad_norm": 2.0271074771881104, "learning_rate": 0.0001615358546595057, "loss": 0.5495636940002442, "step": 189430 }, { "epoch": 1.1260707004059893, "grad_norm": 1.7260793447494507, "learning_rate": 0.0001615307513428062, "loss": 0.6061138153076172, "step": 189440 }, { "epoch": 1.1261301424826577, "grad_norm": 1.3978514671325684, "learning_rate": 0.00016152564777960042, "loss": 0.670048713684082, "step": 189450 }, { "epoch": 1.1261895845593262, "grad_norm": 1.7765005826950073, "learning_rate": 0.00016152054396991277, "loss": 0.6071652412414551, "step": 189460 }, { "epoch": 1.1262490266359946, "grad_norm": 1.7732980251312256, "learning_rate": 0.0001615154399137677, "loss": 0.609508752822876, "step": 189470 }, { "epoch": 1.126308468712663, "grad_norm": 2.0224502086639404, "learning_rate": 0.00016151033561118957, "loss": 0.6871718406677246, "step": 189480 }, { "epoch": 1.1263679107893314, "grad_norm": 1.688586950302124, "learning_rate": 0.00016150523106220287, "loss": 0.5830533981323243, "step": 189490 }, { "epoch": 1.1264273528659998, "grad_norm": 1.6134010553359985, "learning_rate": 0.00016150012626683192, "loss": 0.5683226585388184, "step": 189500 }, { "epoch": 1.126486794942668, "grad_norm": 1.4081476926803589, "learning_rate": 0.00016149502122510124, "loss": 0.6172715663909912, "step": 189510 }, { "epoch": 1.1265462370193364, "grad_norm": 1.578192114830017, "learning_rate": 0.00016148991593703521, "loss": 0.6225134372711182, "step": 189520 }, { "epoch": 1.1266056790960048, "grad_norm": 1.282243013381958, "learning_rate": 0.00016148481040265824, "loss": 0.5865883350372314, "step": 189530 }, { "epoch": 1.1266651211726733, "grad_norm": 1.819480299949646, "learning_rate": 0.00016147970462199475, "loss": 0.5787156581878662, "step": 189540 }, { "epoch": 1.1267245632493417, "grad_norm": 1.4028469324111938, "learning_rate": 0.0001614745985950692, "loss": 0.6066747188568116, "step": 189550 }, { "epoch": 1.12678400532601, "grad_norm": 1.1796170473098755, "learning_rate": 0.00016146949232190595, "loss": 0.6252134799957275, "step": 189560 }, { "epoch": 1.1268434474026785, "grad_norm": 1.5463857650756836, "learning_rate": 0.00016146438580252952, "loss": 0.6468786716461181, "step": 189570 }, { "epoch": 1.126902889479347, "grad_norm": 2.0338635444641113, "learning_rate": 0.00016145927903696424, "loss": 0.6430789947509765, "step": 189580 }, { "epoch": 1.1269623315560153, "grad_norm": 1.7139323949813843, "learning_rate": 0.00016145417202523464, "loss": 0.6574429035186767, "step": 189590 }, { "epoch": 1.1270217736326837, "grad_norm": 1.6926569938659668, "learning_rate": 0.00016144906476736503, "loss": 0.677116060256958, "step": 189600 }, { "epoch": 1.127081215709352, "grad_norm": 1.8530482053756714, "learning_rate": 0.00016144395726337997, "loss": 0.6307126522064209, "step": 189610 }, { "epoch": 1.1271406577860204, "grad_norm": 1.8294603824615479, "learning_rate": 0.0001614388495133038, "loss": 0.6237566947937012, "step": 189620 }, { "epoch": 1.1272000998626888, "grad_norm": 1.5446950197219849, "learning_rate": 0.00016143374151716098, "loss": 0.6399231910705566, "step": 189630 }, { "epoch": 1.1272595419393572, "grad_norm": 1.4688161611557007, "learning_rate": 0.00016142863327497597, "loss": 0.6070703506469727, "step": 189640 }, { "epoch": 1.1273189840160256, "grad_norm": 1.630454659461975, "learning_rate": 0.00016142352478677318, "loss": 0.6010338306427002, "step": 189650 }, { "epoch": 1.127378426092694, "grad_norm": 1.8727067708969116, "learning_rate": 0.00016141841605257703, "loss": 0.6107723236083984, "step": 189660 }, { "epoch": 1.1274378681693624, "grad_norm": 1.567646861076355, "learning_rate": 0.000161413307072412, "loss": 0.5778976440429687, "step": 189670 }, { "epoch": 1.1274973102460308, "grad_norm": 1.6158937215805054, "learning_rate": 0.00016140819784630253, "loss": 0.6390556812286377, "step": 189680 }, { "epoch": 1.127556752322699, "grad_norm": 1.5237785577774048, "learning_rate": 0.000161403088374273, "loss": 0.5580128192901611, "step": 189690 }, { "epoch": 1.1276161943993674, "grad_norm": 1.2578009366989136, "learning_rate": 0.0001613979786563479, "loss": 0.6132752895355225, "step": 189700 }, { "epoch": 1.1276756364760359, "grad_norm": 2.275900363922119, "learning_rate": 0.00016139286869255168, "loss": 0.6619151115417481, "step": 189710 }, { "epoch": 1.1277350785527043, "grad_norm": 1.8577935695648193, "learning_rate": 0.00016138775848290878, "loss": 0.6058133125305176, "step": 189720 }, { "epoch": 1.1277945206293727, "grad_norm": 1.4004640579223633, "learning_rate": 0.00016138264802744362, "loss": 0.6150800704956054, "step": 189730 }, { "epoch": 1.127853962706041, "grad_norm": 1.289960265159607, "learning_rate": 0.00016137753732618068, "loss": 0.626618480682373, "step": 189740 }, { "epoch": 1.1279134047827095, "grad_norm": 1.6682254076004028, "learning_rate": 0.0001613724263791444, "loss": 0.5908808231353759, "step": 189750 }, { "epoch": 1.127972846859378, "grad_norm": 1.3951525688171387, "learning_rate": 0.0001613673151863592, "loss": 0.6511222839355468, "step": 189760 }, { "epoch": 1.1280322889360463, "grad_norm": 1.6101953983306885, "learning_rate": 0.00016136220374784956, "loss": 0.5737754821777343, "step": 189770 }, { "epoch": 1.1280917310127148, "grad_norm": 1.9306561946868896, "learning_rate": 0.0001613570920636399, "loss": 0.6090281009674072, "step": 189780 }, { "epoch": 1.1281511730893832, "grad_norm": 1.541856050491333, "learning_rate": 0.00016135198013375474, "loss": 0.6384646892547607, "step": 189790 }, { "epoch": 1.1282106151660514, "grad_norm": 1.5922164916992188, "learning_rate": 0.00016134686795821846, "loss": 0.642582368850708, "step": 189800 }, { "epoch": 1.1282700572427198, "grad_norm": 1.4913768768310547, "learning_rate": 0.00016134175553705554, "loss": 0.5666563987731934, "step": 189810 }, { "epoch": 1.1283294993193882, "grad_norm": 1.9326022863388062, "learning_rate": 0.00016133664287029046, "loss": 0.586742639541626, "step": 189820 }, { "epoch": 1.1283889413960566, "grad_norm": 1.5520216226577759, "learning_rate": 0.00016133152995794766, "loss": 0.6548761367797852, "step": 189830 }, { "epoch": 1.128448383472725, "grad_norm": 1.6129283905029297, "learning_rate": 0.00016132641680005158, "loss": 0.6171976089477539, "step": 189840 }, { "epoch": 1.1285078255493934, "grad_norm": 1.2421860694885254, "learning_rate": 0.0001613213033966267, "loss": 0.6460776329040527, "step": 189850 }, { "epoch": 1.1285672676260619, "grad_norm": 1.3081809282302856, "learning_rate": 0.00016131618974769748, "loss": 0.6119392871856689, "step": 189860 }, { "epoch": 1.1286267097027303, "grad_norm": 1.5260025262832642, "learning_rate": 0.00016131107585328836, "loss": 0.6404423713684082, "step": 189870 }, { "epoch": 1.1286861517793985, "grad_norm": 1.7195098400115967, "learning_rate": 0.00016130596171342384, "loss": 0.6487396717071533, "step": 189880 }, { "epoch": 1.1287455938560669, "grad_norm": 1.842925786972046, "learning_rate": 0.0001613008473281284, "loss": 0.5860841274261475, "step": 189890 }, { "epoch": 1.1288050359327353, "grad_norm": 1.830502986907959, "learning_rate": 0.0001612957326974264, "loss": 0.6478628635406494, "step": 189900 }, { "epoch": 1.1288644780094037, "grad_norm": 1.9881620407104492, "learning_rate": 0.0001612906178213424, "loss": 0.6001997947692871, "step": 189910 }, { "epoch": 1.1289239200860721, "grad_norm": 1.5055261850357056, "learning_rate": 0.00016128550269990086, "loss": 0.5890469551086426, "step": 189920 }, { "epoch": 1.1289833621627405, "grad_norm": 1.7164629697799683, "learning_rate": 0.0001612803873331262, "loss": 0.5749325275421142, "step": 189930 }, { "epoch": 1.129042804239409, "grad_norm": 1.6549769639968872, "learning_rate": 0.00016127527172104302, "loss": 0.6268185138702392, "step": 189940 }, { "epoch": 1.1291022463160774, "grad_norm": 1.5287611484527588, "learning_rate": 0.0001612701558636756, "loss": 0.6241623878479003, "step": 189950 }, { "epoch": 1.1291616883927458, "grad_norm": 2.261284112930298, "learning_rate": 0.00016126503976104857, "loss": 0.6828172683715821, "step": 189960 }, { "epoch": 1.1292211304694142, "grad_norm": 1.7178945541381836, "learning_rate": 0.00016125992341318632, "loss": 0.6277483940124512, "step": 189970 }, { "epoch": 1.1292805725460824, "grad_norm": 1.5528053045272827, "learning_rate": 0.00016125480682011335, "loss": 0.5781688690185547, "step": 189980 }, { "epoch": 1.1293400146227508, "grad_norm": 1.5226184129714966, "learning_rate": 0.0001612496899818541, "loss": 0.6318551540374756, "step": 189990 }, { "epoch": 1.1293994566994192, "grad_norm": 1.6950268745422363, "learning_rate": 0.00016124457289843312, "loss": 0.6281239032745362, "step": 190000 }, { "epoch": 1.1294588987760876, "grad_norm": 1.361020565032959, "learning_rate": 0.00016123945556987485, "loss": 0.6266207218170166, "step": 190010 }, { "epoch": 1.129518340852756, "grad_norm": 2.3149609565734863, "learning_rate": 0.00016123433799620376, "loss": 0.6862473011016845, "step": 190020 }, { "epoch": 1.1295777829294245, "grad_norm": 1.38356614112854, "learning_rate": 0.00016122922017744435, "loss": 0.6896510124206543, "step": 190030 }, { "epoch": 1.1296372250060929, "grad_norm": 1.6109579801559448, "learning_rate": 0.0001612241021136211, "loss": 0.579413652420044, "step": 190040 }, { "epoch": 1.1296966670827613, "grad_norm": 1.8215572834014893, "learning_rate": 0.00016121898380475847, "loss": 0.5635169982910156, "step": 190050 }, { "epoch": 1.1297561091594295, "grad_norm": 1.8896429538726807, "learning_rate": 0.00016121386525088093, "loss": 0.6401352882385254, "step": 190060 }, { "epoch": 1.129815551236098, "grad_norm": 1.4563477039337158, "learning_rate": 0.00016120874645201305, "loss": 0.5800620555877686, "step": 190070 }, { "epoch": 1.1298749933127663, "grad_norm": 1.9885355234146118, "learning_rate": 0.00016120362740817924, "loss": 0.6055143356323243, "step": 190080 }, { "epoch": 1.1299344353894347, "grad_norm": 1.255595326423645, "learning_rate": 0.000161198508119404, "loss": 0.5959784507751464, "step": 190090 }, { "epoch": 1.1299938774661031, "grad_norm": 1.2024991512298584, "learning_rate": 0.00016119338858571188, "loss": 0.6509013652801514, "step": 190100 }, { "epoch": 1.1300533195427716, "grad_norm": 1.831965446472168, "learning_rate": 0.00016118826880712724, "loss": 0.6397252082824707, "step": 190110 }, { "epoch": 1.13011276161944, "grad_norm": 2.1535067558288574, "learning_rate": 0.0001611831487836747, "loss": 0.6382513999938965, "step": 190120 }, { "epoch": 1.1301722036961084, "grad_norm": 1.727413296699524, "learning_rate": 0.0001611780285153787, "loss": 0.6372029304504394, "step": 190130 }, { "epoch": 1.1302316457727768, "grad_norm": 1.7026959657669067, "learning_rate": 0.00016117290800226372, "loss": 0.6452218055725097, "step": 190140 }, { "epoch": 1.1302910878494452, "grad_norm": 1.6983674764633179, "learning_rate": 0.00016116778724435427, "loss": 0.6294173717498779, "step": 190150 }, { "epoch": 1.1303505299261136, "grad_norm": 1.7693008184432983, "learning_rate": 0.00016116266624167485, "loss": 0.6020699501037597, "step": 190160 }, { "epoch": 1.1304099720027818, "grad_norm": 1.5229899883270264, "learning_rate": 0.00016115754499424997, "loss": 0.5856488227844239, "step": 190170 }, { "epoch": 1.1304694140794502, "grad_norm": 1.2680943012237549, "learning_rate": 0.00016115242350210412, "loss": 0.6468248844146729, "step": 190180 }, { "epoch": 1.1305288561561186, "grad_norm": 2.1523685455322266, "learning_rate": 0.00016114730176526175, "loss": 0.6981031417846679, "step": 190190 }, { "epoch": 1.130588298232787, "grad_norm": 1.6433372497558594, "learning_rate": 0.00016114217978374743, "loss": 0.6381093025207519, "step": 190200 }, { "epoch": 1.1306477403094555, "grad_norm": 1.7253366708755493, "learning_rate": 0.00016113705755758565, "loss": 0.5909741878509521, "step": 190210 }, { "epoch": 1.1307071823861239, "grad_norm": 1.541925072669983, "learning_rate": 0.0001611319350868009, "loss": 0.6187268257141113, "step": 190220 }, { "epoch": 1.1307666244627923, "grad_norm": 1.4150222539901733, "learning_rate": 0.00016112681237141766, "loss": 0.5680681228637695, "step": 190230 }, { "epoch": 1.1308260665394607, "grad_norm": 1.5817830562591553, "learning_rate": 0.00016112168941146047, "loss": 0.6362909317016602, "step": 190240 }, { "epoch": 1.130885508616129, "grad_norm": 2.0005300045013428, "learning_rate": 0.00016111656620695382, "loss": 0.6124863624572754, "step": 190250 }, { "epoch": 1.1309449506927973, "grad_norm": 1.680845022201538, "learning_rate": 0.00016111144275792223, "loss": 0.6521741390228272, "step": 190260 }, { "epoch": 1.1310043927694657, "grad_norm": 1.8202377557754517, "learning_rate": 0.0001611063190643902, "loss": 0.6212895393371582, "step": 190270 }, { "epoch": 1.1310638348461342, "grad_norm": 1.7092866897583008, "learning_rate": 0.00016110119512638223, "loss": 0.6034049034118653, "step": 190280 }, { "epoch": 1.1311232769228026, "grad_norm": 1.3751397132873535, "learning_rate": 0.00016109607094392283, "loss": 0.5933131694793701, "step": 190290 }, { "epoch": 1.131182718999471, "grad_norm": 1.9959183931350708, "learning_rate": 0.00016109094651703656, "loss": 0.5764206409454345, "step": 190300 }, { "epoch": 1.1312421610761394, "grad_norm": 1.8540829420089722, "learning_rate": 0.00016108582184574786, "loss": 0.5970655918121338, "step": 190310 }, { "epoch": 1.1313016031528078, "grad_norm": 1.4719878435134888, "learning_rate": 0.00016108069693008132, "loss": 0.5527678966522217, "step": 190320 }, { "epoch": 1.1313610452294762, "grad_norm": 1.5241518020629883, "learning_rate": 0.00016107557177006142, "loss": 0.634335708618164, "step": 190330 }, { "epoch": 1.1314204873061446, "grad_norm": 1.9060397148132324, "learning_rate": 0.00016107044636571265, "loss": 0.6805774211883545, "step": 190340 }, { "epoch": 1.1314799293828128, "grad_norm": 1.5162925720214844, "learning_rate": 0.00016106532071705955, "loss": 0.6967269897460937, "step": 190350 }, { "epoch": 1.1315393714594812, "grad_norm": 1.7242625951766968, "learning_rate": 0.00016106019482412667, "loss": 0.5851066589355469, "step": 190360 }, { "epoch": 1.1315988135361497, "grad_norm": 1.3802437782287598, "learning_rate": 0.0001610550686869385, "loss": 0.6046499252319336, "step": 190370 }, { "epoch": 1.131658255612818, "grad_norm": 1.831310510635376, "learning_rate": 0.00016104994230551955, "loss": 0.5942132472991943, "step": 190380 }, { "epoch": 1.1317176976894865, "grad_norm": 1.7090388536453247, "learning_rate": 0.00016104481567989437, "loss": 0.5666223526000976, "step": 190390 }, { "epoch": 1.131777139766155, "grad_norm": 1.9737305641174316, "learning_rate": 0.00016103968881008747, "loss": 0.7230368614196777, "step": 190400 }, { "epoch": 1.1318365818428233, "grad_norm": 1.6797759532928467, "learning_rate": 0.0001610345616961234, "loss": 0.6225944519042969, "step": 190410 }, { "epoch": 1.1318960239194917, "grad_norm": 1.9705175161361694, "learning_rate": 0.00016102943433802665, "loss": 0.635440444946289, "step": 190420 }, { "epoch": 1.13195546599616, "grad_norm": 1.3648784160614014, "learning_rate": 0.00016102430673582173, "loss": 0.6243885040283204, "step": 190430 }, { "epoch": 1.1320149080728283, "grad_norm": 1.9545143842697144, "learning_rate": 0.00016101917888953327, "loss": 0.5558950901031494, "step": 190440 }, { "epoch": 1.1320743501494968, "grad_norm": 1.564847469329834, "learning_rate": 0.0001610140507991857, "loss": 0.6113009452819824, "step": 190450 }, { "epoch": 1.1321337922261652, "grad_norm": 1.823194980621338, "learning_rate": 0.00016100892246480355, "loss": 0.6277687072753906, "step": 190460 }, { "epoch": 1.1321932343028336, "grad_norm": 1.4490917921066284, "learning_rate": 0.00016100379388641142, "loss": 0.5828225612640381, "step": 190470 }, { "epoch": 1.132252676379502, "grad_norm": 1.8816865682601929, "learning_rate": 0.0001609986650640338, "loss": 0.6288436889648438, "step": 190480 }, { "epoch": 1.1323121184561704, "grad_norm": 1.7606616020202637, "learning_rate": 0.0001609935359976952, "loss": 0.6257579803466797, "step": 190490 }, { "epoch": 1.1323715605328388, "grad_norm": 2.0666518211364746, "learning_rate": 0.00016098840668742027, "loss": 0.6403321743011474, "step": 190500 }, { "epoch": 1.1324310026095072, "grad_norm": 1.321574091911316, "learning_rate": 0.0001609832771332334, "loss": 0.6227000236511231, "step": 190510 }, { "epoch": 1.1324904446861757, "grad_norm": 1.4359153509140015, "learning_rate": 0.0001609781473351592, "loss": 0.5707626819610596, "step": 190520 }, { "epoch": 1.132549886762844, "grad_norm": 1.6302038431167603, "learning_rate": 0.00016097301729322224, "loss": 0.6007346153259278, "step": 190530 }, { "epoch": 1.1326093288395123, "grad_norm": 1.5829411745071411, "learning_rate": 0.00016096788700744696, "loss": 0.5828783988952637, "step": 190540 }, { "epoch": 1.1326687709161807, "grad_norm": 1.8379058837890625, "learning_rate": 0.000160962756477858, "loss": 0.6049537658691406, "step": 190550 }, { "epoch": 1.132728212992849, "grad_norm": 1.3932874202728271, "learning_rate": 0.00016095762570447988, "loss": 0.5792264938354492, "step": 190560 }, { "epoch": 1.1327876550695175, "grad_norm": 1.2414381504058838, "learning_rate": 0.00016095249468733714, "loss": 0.6066148281097412, "step": 190570 }, { "epoch": 1.132847097146186, "grad_norm": 1.8084079027175903, "learning_rate": 0.00016094736342645428, "loss": 0.5995409488677979, "step": 190580 }, { "epoch": 1.1329065392228543, "grad_norm": 1.3750042915344238, "learning_rate": 0.0001609422319218559, "loss": 0.6560717105865479, "step": 190590 }, { "epoch": 1.1329659812995228, "grad_norm": 1.3714485168457031, "learning_rate": 0.00016093710017356654, "loss": 0.6325218200683593, "step": 190600 }, { "epoch": 1.1330254233761912, "grad_norm": 1.7976586818695068, "learning_rate": 0.0001609319681816107, "loss": 0.6652796745300293, "step": 190610 }, { "epoch": 1.1330848654528594, "grad_norm": 1.6491128206253052, "learning_rate": 0.000160926835946013, "loss": 0.6018640518188476, "step": 190620 }, { "epoch": 1.1331443075295278, "grad_norm": 1.7594751119613647, "learning_rate": 0.00016092170346679796, "loss": 0.654271936416626, "step": 190630 }, { "epoch": 1.1332037496061962, "grad_norm": 1.737349033355713, "learning_rate": 0.00016091657074399014, "loss": 0.6478397369384765, "step": 190640 }, { "epoch": 1.1332631916828646, "grad_norm": 1.6213997602462769, "learning_rate": 0.0001609114377776141, "loss": 0.5976689338684082, "step": 190650 }, { "epoch": 1.133322633759533, "grad_norm": 1.8782095909118652, "learning_rate": 0.00016090630456769433, "loss": 0.7015279293060303, "step": 190660 }, { "epoch": 1.1333820758362014, "grad_norm": 1.7939867973327637, "learning_rate": 0.00016090117111425547, "loss": 0.6700485229492188, "step": 190670 }, { "epoch": 1.1334415179128698, "grad_norm": 1.6361095905303955, "learning_rate": 0.00016089603741732203, "loss": 0.5968629837036132, "step": 190680 }, { "epoch": 1.1335009599895383, "grad_norm": 1.3632718324661255, "learning_rate": 0.00016089090347691856, "loss": 0.6022826194763183, "step": 190690 }, { "epoch": 1.1335604020662067, "grad_norm": 2.017728567123413, "learning_rate": 0.0001608857692930697, "loss": 0.6111806392669678, "step": 190700 }, { "epoch": 1.133619844142875, "grad_norm": 1.5278371572494507, "learning_rate": 0.00016088063486579992, "loss": 0.6147382736206055, "step": 190710 }, { "epoch": 1.1336792862195433, "grad_norm": 1.444034457206726, "learning_rate": 0.0001608755001951338, "loss": 0.5968455314636231, "step": 190720 }, { "epoch": 1.1337387282962117, "grad_norm": 1.8463664054870605, "learning_rate": 0.00016087036528109592, "loss": 0.6480956077575684, "step": 190730 }, { "epoch": 1.13379817037288, "grad_norm": 1.5534641742706299, "learning_rate": 0.00016086523012371083, "loss": 0.6036558151245117, "step": 190740 }, { "epoch": 1.1338576124495485, "grad_norm": 1.220731496810913, "learning_rate": 0.00016086009472300307, "loss": 0.5695186614990234, "step": 190750 }, { "epoch": 1.133917054526217, "grad_norm": 1.6653398275375366, "learning_rate": 0.00016085495907899728, "loss": 0.6059402465820313, "step": 190760 }, { "epoch": 1.1339764966028854, "grad_norm": 1.3574508428573608, "learning_rate": 0.000160849823191718, "loss": 0.567957592010498, "step": 190770 }, { "epoch": 1.1340359386795538, "grad_norm": 1.4264612197875977, "learning_rate": 0.00016084468706118973, "loss": 0.6197429180145264, "step": 190780 }, { "epoch": 1.1340953807562222, "grad_norm": 1.7308176755905151, "learning_rate": 0.00016083955068743713, "loss": 0.6529460430145264, "step": 190790 }, { "epoch": 1.1341548228328904, "grad_norm": 1.6825593709945679, "learning_rate": 0.00016083441407048477, "loss": 0.6523448944091796, "step": 190800 }, { "epoch": 1.1342142649095588, "grad_norm": 1.4615687131881714, "learning_rate": 0.00016082927721035716, "loss": 0.6240072250366211, "step": 190810 }, { "epoch": 1.1342737069862272, "grad_norm": 1.6670335531234741, "learning_rate": 0.00016082414010707886, "loss": 0.5837430953979492, "step": 190820 }, { "epoch": 1.1343331490628956, "grad_norm": 1.627219319343567, "learning_rate": 0.0001608190027606745, "loss": 0.5983931541442871, "step": 190830 }, { "epoch": 1.134392591139564, "grad_norm": 1.6455941200256348, "learning_rate": 0.00016081386517116864, "loss": 0.6654872894287109, "step": 190840 }, { "epoch": 1.1344520332162324, "grad_norm": 1.560346007347107, "learning_rate": 0.00016080872733858587, "loss": 0.6282384872436524, "step": 190850 }, { "epoch": 1.1345114752929009, "grad_norm": 1.2279062271118164, "learning_rate": 0.00016080358926295074, "loss": 0.6567757606506348, "step": 190860 }, { "epoch": 1.1345709173695693, "grad_norm": 1.3866323232650757, "learning_rate": 0.00016079845094428785, "loss": 0.5963526725769043, "step": 190870 }, { "epoch": 1.1346303594462377, "grad_norm": 1.4299236536026, "learning_rate": 0.00016079331238262175, "loss": 0.6136239051818848, "step": 190880 }, { "epoch": 1.134689801522906, "grad_norm": 1.8620803356170654, "learning_rate": 0.00016078817357797706, "loss": 0.6242820739746093, "step": 190890 }, { "epoch": 1.1347492435995743, "grad_norm": 1.5449424982070923, "learning_rate": 0.00016078303453037835, "loss": 0.5990217208862305, "step": 190900 }, { "epoch": 1.1348086856762427, "grad_norm": 1.2613575458526611, "learning_rate": 0.0001607778952398502, "loss": 0.633342981338501, "step": 190910 }, { "epoch": 1.1348681277529111, "grad_norm": 1.4926856756210327, "learning_rate": 0.0001607727557064172, "loss": 0.6649701595306396, "step": 190920 }, { "epoch": 1.1349275698295795, "grad_norm": 2.910186290740967, "learning_rate": 0.00016076761593010393, "loss": 0.6619940757751465, "step": 190930 }, { "epoch": 1.134987011906248, "grad_norm": 1.7894744873046875, "learning_rate": 0.00016076247591093496, "loss": 0.6199494361877441, "step": 190940 }, { "epoch": 1.1350464539829164, "grad_norm": 1.5357720851898193, "learning_rate": 0.00016075733564893487, "loss": 0.6260687351226807, "step": 190950 }, { "epoch": 1.1351058960595848, "grad_norm": 1.903555989265442, "learning_rate": 0.00016075219514412832, "loss": 0.6120296478271484, "step": 190960 }, { "epoch": 1.1351653381362532, "grad_norm": 1.1999651193618774, "learning_rate": 0.00016074705439653983, "loss": 0.5787535190582276, "step": 190970 }, { "epoch": 1.1352247802129216, "grad_norm": 1.363625168800354, "learning_rate": 0.00016074191340619402, "loss": 0.5998757362365723, "step": 190980 }, { "epoch": 1.1352842222895898, "grad_norm": 1.420896291732788, "learning_rate": 0.00016073677217311552, "loss": 0.6210769653320313, "step": 190990 }, { "epoch": 1.1353436643662582, "grad_norm": 1.2521578073501587, "learning_rate": 0.0001607316306973288, "loss": 0.5933804512023926, "step": 191000 }, { "epoch": 1.1354031064429266, "grad_norm": 1.295029640197754, "learning_rate": 0.0001607264889788586, "loss": 0.6142972469329834, "step": 191010 }, { "epoch": 1.135462548519595, "grad_norm": 1.4939953088760376, "learning_rate": 0.00016072134701772947, "loss": 0.6436520576477051, "step": 191020 }, { "epoch": 1.1355219905962635, "grad_norm": 2.2495715618133545, "learning_rate": 0.00016071620481396596, "loss": 0.6544273853302002, "step": 191030 }, { "epoch": 1.1355814326729319, "grad_norm": 1.446587085723877, "learning_rate": 0.00016071106236759266, "loss": 0.658252763748169, "step": 191040 }, { "epoch": 1.1356408747496003, "grad_norm": 1.4371191263198853, "learning_rate": 0.00016070591967863427, "loss": 0.5973960399627686, "step": 191050 }, { "epoch": 1.1357003168262687, "grad_norm": 2.233877658843994, "learning_rate": 0.0001607007767471153, "loss": 0.6038256645202636, "step": 191060 }, { "epoch": 1.1357597589029371, "grad_norm": 1.45143723487854, "learning_rate": 0.00016069563357306042, "loss": 0.6475384712219239, "step": 191070 }, { "epoch": 1.1358192009796055, "grad_norm": 1.3743780851364136, "learning_rate": 0.00016069049015649415, "loss": 0.5592682361602783, "step": 191080 }, { "epoch": 1.1358786430562737, "grad_norm": 1.8765734434127808, "learning_rate": 0.00016068534649744118, "loss": 0.625519847869873, "step": 191090 }, { "epoch": 1.1359380851329421, "grad_norm": 1.6422375440597534, "learning_rate": 0.00016068020259592605, "loss": 0.664975643157959, "step": 191100 }, { "epoch": 1.1359975272096106, "grad_norm": 1.4542567729949951, "learning_rate": 0.0001606750584519734, "loss": 0.6577893257141113, "step": 191110 }, { "epoch": 1.136056969286279, "grad_norm": 1.3603171110153198, "learning_rate": 0.00016066991406560782, "loss": 0.6274178504943848, "step": 191120 }, { "epoch": 1.1361164113629474, "grad_norm": 1.8981983661651611, "learning_rate": 0.00016066476943685394, "loss": 0.7028249740600586, "step": 191130 }, { "epoch": 1.1361758534396158, "grad_norm": 2.1515486240386963, "learning_rate": 0.00016065962456573638, "loss": 0.6572034358978271, "step": 191140 }, { "epoch": 1.1362352955162842, "grad_norm": 1.4662086963653564, "learning_rate": 0.00016065447945227973, "loss": 0.5647151947021485, "step": 191150 }, { "epoch": 1.1362947375929526, "grad_norm": 1.6423072814941406, "learning_rate": 0.00016064933409650858, "loss": 0.6104577064514161, "step": 191160 }, { "epoch": 1.1363541796696208, "grad_norm": 1.5698683261871338, "learning_rate": 0.00016064418849844758, "loss": 0.5659246444702148, "step": 191170 }, { "epoch": 1.1364136217462892, "grad_norm": 1.3484078645706177, "learning_rate": 0.00016063904265812133, "loss": 0.6111620426177978, "step": 191180 }, { "epoch": 1.1364730638229577, "grad_norm": 1.5790835618972778, "learning_rate": 0.00016063389657555445, "loss": 0.6273510456085205, "step": 191190 }, { "epoch": 1.136532505899626, "grad_norm": 1.3829959630966187, "learning_rate": 0.00016062875025077156, "loss": 0.6692514419555664, "step": 191200 }, { "epoch": 1.1365919479762945, "grad_norm": 1.8260754346847534, "learning_rate": 0.00016062360368379727, "loss": 0.6293660163879394, "step": 191210 }, { "epoch": 1.136651390052963, "grad_norm": 1.5264118909835815, "learning_rate": 0.0001606184568746562, "loss": 0.6080199241638183, "step": 191220 }, { "epoch": 1.1367108321296313, "grad_norm": 1.714340329170227, "learning_rate": 0.000160613309823373, "loss": 0.6492032051086426, "step": 191230 }, { "epoch": 1.1367702742062997, "grad_norm": 1.3626837730407715, "learning_rate": 0.00016060816252997222, "loss": 0.6231258392333985, "step": 191240 }, { "epoch": 1.1368297162829681, "grad_norm": 1.6556336879730225, "learning_rate": 0.00016060301499447855, "loss": 0.726039981842041, "step": 191250 }, { "epoch": 1.1368891583596366, "grad_norm": 1.9945353269577026, "learning_rate": 0.00016059786721691664, "loss": 0.570534610748291, "step": 191260 }, { "epoch": 1.1369486004363047, "grad_norm": 1.4134207963943481, "learning_rate": 0.00016059271919731098, "loss": 0.6431032657623291, "step": 191270 }, { "epoch": 1.1370080425129732, "grad_norm": 1.5090618133544922, "learning_rate": 0.00016058757093568638, "loss": 0.6327743530273438, "step": 191280 }, { "epoch": 1.1370674845896416, "grad_norm": 1.3476779460906982, "learning_rate": 0.0001605824224320673, "loss": 0.5708877563476562, "step": 191290 }, { "epoch": 1.13712692666631, "grad_norm": 1.5647586584091187, "learning_rate": 0.00016057727368647847, "loss": 0.6249959945678711, "step": 191300 }, { "epoch": 1.1371863687429784, "grad_norm": 1.6821504831314087, "learning_rate": 0.00016057212469894447, "loss": 0.6061574459075928, "step": 191310 }, { "epoch": 1.1372458108196468, "grad_norm": 1.4921302795410156, "learning_rate": 0.00016056697546948997, "loss": 0.6139606475830078, "step": 191320 }, { "epoch": 1.1373052528963152, "grad_norm": 1.5527480840682983, "learning_rate": 0.0001605618259981396, "loss": 0.6397815704345703, "step": 191330 }, { "epoch": 1.1373646949729836, "grad_norm": 1.7646169662475586, "learning_rate": 0.00016055667628491794, "loss": 0.6221569538116455, "step": 191340 }, { "epoch": 1.137424137049652, "grad_norm": 1.467032551765442, "learning_rate": 0.0001605515263298497, "loss": 0.6214706420898437, "step": 191350 }, { "epoch": 1.1374835791263203, "grad_norm": 1.0007226467132568, "learning_rate": 0.00016054637613295946, "loss": 0.6332108497619628, "step": 191360 }, { "epoch": 1.1375430212029887, "grad_norm": 1.538315773010254, "learning_rate": 0.00016054122569427189, "loss": 0.6226996898651123, "step": 191370 }, { "epoch": 1.137602463279657, "grad_norm": 1.572615146636963, "learning_rate": 0.00016053607501381162, "loss": 0.5824583053588868, "step": 191380 }, { "epoch": 1.1376619053563255, "grad_norm": 1.090640664100647, "learning_rate": 0.00016053092409160327, "loss": 0.6778043746948242, "step": 191390 }, { "epoch": 1.137721347432994, "grad_norm": 1.8547086715698242, "learning_rate": 0.00016052577292767145, "loss": 0.6292477607727051, "step": 191400 }, { "epoch": 1.1377807895096623, "grad_norm": 1.5001767873764038, "learning_rate": 0.0001605206215220409, "loss": 0.6447537422180176, "step": 191410 }, { "epoch": 1.1378402315863307, "grad_norm": 1.5200852155685425, "learning_rate": 0.0001605154698747362, "loss": 0.6548477172851562, "step": 191420 }, { "epoch": 1.1378996736629992, "grad_norm": 1.3005095720291138, "learning_rate": 0.000160510317985782, "loss": 0.6267153739929199, "step": 191430 }, { "epoch": 1.1379591157396676, "grad_norm": 2.290600061416626, "learning_rate": 0.0001605051658552029, "loss": 0.6385670661926269, "step": 191440 }, { "epoch": 1.138018557816336, "grad_norm": 1.5556225776672363, "learning_rate": 0.00016050001348302364, "loss": 0.6119603157043457, "step": 191450 }, { "epoch": 1.1380779998930042, "grad_norm": 1.5260751247406006, "learning_rate": 0.00016049486086926884, "loss": 0.5998049259185791, "step": 191460 }, { "epoch": 1.1381374419696726, "grad_norm": 1.6051092147827148, "learning_rate": 0.0001604897080139631, "loss": 0.5836050033569335, "step": 191470 }, { "epoch": 1.138196884046341, "grad_norm": 1.496326208114624, "learning_rate": 0.0001604845549171311, "loss": 0.5959048271179199, "step": 191480 }, { "epoch": 1.1382563261230094, "grad_norm": 1.807450294494629, "learning_rate": 0.00016047940157879747, "loss": 0.5668757915496826, "step": 191490 }, { "epoch": 1.1383157681996778, "grad_norm": 1.2143199443817139, "learning_rate": 0.0001604742479989869, "loss": 0.5634081840515137, "step": 191500 }, { "epoch": 1.1383752102763462, "grad_norm": 1.7982743978500366, "learning_rate": 0.000160469094177724, "loss": 0.6080492973327637, "step": 191510 }, { "epoch": 1.1384346523530147, "grad_norm": 1.6463899612426758, "learning_rate": 0.00016046394011503344, "loss": 0.6289309501647949, "step": 191520 }, { "epoch": 1.138494094429683, "grad_norm": 2.48046612739563, "learning_rate": 0.0001604587858109399, "loss": 0.6214139938354493, "step": 191530 }, { "epoch": 1.1385535365063513, "grad_norm": 1.9037271738052368, "learning_rate": 0.00016045363126546803, "loss": 0.6146892547607422, "step": 191540 }, { "epoch": 1.1386129785830197, "grad_norm": 1.1789536476135254, "learning_rate": 0.00016044847647864248, "loss": 0.5886107921600342, "step": 191550 }, { "epoch": 1.138672420659688, "grad_norm": 1.677607774734497, "learning_rate": 0.00016044332145048789, "loss": 0.6436900138854981, "step": 191560 }, { "epoch": 1.1387318627363565, "grad_norm": 1.7485003471374512, "learning_rate": 0.00016043816618102892, "loss": 0.6718161106109619, "step": 191570 }, { "epoch": 1.138791304813025, "grad_norm": 1.693139672279358, "learning_rate": 0.00016043301067029028, "loss": 0.5630270957946777, "step": 191580 }, { "epoch": 1.1388507468896933, "grad_norm": 1.2742482423782349, "learning_rate": 0.0001604278549182966, "loss": 0.5883806228637696, "step": 191590 }, { "epoch": 1.1389101889663618, "grad_norm": 1.4295897483825684, "learning_rate": 0.00016042269892507248, "loss": 0.5502660751342774, "step": 191600 }, { "epoch": 1.1389696310430302, "grad_norm": 1.7883630990982056, "learning_rate": 0.00016041754269064271, "loss": 0.6087298393249512, "step": 191610 }, { "epoch": 1.1390290731196986, "grad_norm": 1.577764630317688, "learning_rate": 0.0001604123862150319, "loss": 0.6043325424194336, "step": 191620 }, { "epoch": 1.139088515196367, "grad_norm": 1.7453104257583618, "learning_rate": 0.00016040722949826466, "loss": 0.5956079483032226, "step": 191630 }, { "epoch": 1.1391479572730352, "grad_norm": 1.4633216857910156, "learning_rate": 0.00016040207254036575, "loss": 0.632528018951416, "step": 191640 }, { "epoch": 1.1392073993497036, "grad_norm": 1.4380576610565186, "learning_rate": 0.00016039691534135974, "loss": 0.6676660537719726, "step": 191650 }, { "epoch": 1.139266841426372, "grad_norm": 1.775036334991455, "learning_rate": 0.0001603917579012714, "loss": 0.6306070327758789, "step": 191660 }, { "epoch": 1.1393262835030404, "grad_norm": 1.629324197769165, "learning_rate": 0.00016038660022012538, "loss": 0.6241389274597168, "step": 191670 }, { "epoch": 1.1393857255797089, "grad_norm": 1.5425519943237305, "learning_rate": 0.00016038144229794628, "loss": 0.5970928192138671, "step": 191680 }, { "epoch": 1.1394451676563773, "grad_norm": 1.4542232751846313, "learning_rate": 0.00016037628413475885, "loss": 0.6151258945465088, "step": 191690 }, { "epoch": 1.1395046097330457, "grad_norm": 1.4516396522521973, "learning_rate": 0.00016037112573058775, "loss": 0.596916389465332, "step": 191700 }, { "epoch": 1.139564051809714, "grad_norm": 1.6781924962997437, "learning_rate": 0.0001603659670854576, "loss": 0.6282380580902099, "step": 191710 }, { "epoch": 1.1396234938863825, "grad_norm": 1.7108945846557617, "learning_rate": 0.0001603608081993932, "loss": 0.6551948547363281, "step": 191720 }, { "epoch": 1.1396829359630507, "grad_norm": 1.7624489068984985, "learning_rate": 0.0001603556490724191, "loss": 0.6266918182373047, "step": 191730 }, { "epoch": 1.1397423780397191, "grad_norm": 1.432316541671753, "learning_rate": 0.00016035048970456005, "loss": 0.6082811832427979, "step": 191740 }, { "epoch": 1.1398018201163875, "grad_norm": 1.2693086862564087, "learning_rate": 0.0001603453300958407, "loss": 0.6963382720947265, "step": 191750 }, { "epoch": 1.139861262193056, "grad_norm": 2.812857151031494, "learning_rate": 0.00016034017024628574, "loss": 0.6434767723083497, "step": 191760 }, { "epoch": 1.1399207042697244, "grad_norm": 1.066789984703064, "learning_rate": 0.00016033501015591986, "loss": 0.6284794807434082, "step": 191770 }, { "epoch": 1.1399801463463928, "grad_norm": 1.7293298244476318, "learning_rate": 0.00016032984982476776, "loss": 0.6797050476074219, "step": 191780 }, { "epoch": 1.1400395884230612, "grad_norm": 1.6198794841766357, "learning_rate": 0.00016032468925285408, "loss": 0.6134585380554199, "step": 191790 }, { "epoch": 1.1400990304997296, "grad_norm": 1.5390924215316772, "learning_rate": 0.00016031952844020354, "loss": 0.5902953147888184, "step": 191800 }, { "epoch": 1.140158472576398, "grad_norm": 1.4225424528121948, "learning_rate": 0.00016031436738684084, "loss": 0.6437802314758301, "step": 191810 }, { "epoch": 1.1402179146530664, "grad_norm": 1.7430856227874756, "learning_rate": 0.00016030920609279062, "loss": 0.6096043586730957, "step": 191820 }, { "epoch": 1.1402773567297346, "grad_norm": 1.7765710353851318, "learning_rate": 0.0001603040445580776, "loss": 0.6368066310882569, "step": 191830 }, { "epoch": 1.140336798806403, "grad_norm": 1.7831182479858398, "learning_rate": 0.00016029888278272652, "loss": 0.6906739234924316, "step": 191840 }, { "epoch": 1.1403962408830715, "grad_norm": 1.688292384147644, "learning_rate": 0.00016029372076676197, "loss": 0.6527176856994629, "step": 191850 }, { "epoch": 1.1404556829597399, "grad_norm": 1.5246175527572632, "learning_rate": 0.0001602885585102087, "loss": 0.6555099487304688, "step": 191860 }, { "epoch": 1.1405151250364083, "grad_norm": 1.666129231452942, "learning_rate": 0.0001602833960130914, "loss": 0.631983757019043, "step": 191870 }, { "epoch": 1.1405745671130767, "grad_norm": 1.7337815761566162, "learning_rate": 0.00016027823327543478, "loss": 0.6351919174194336, "step": 191880 }, { "epoch": 1.1406340091897451, "grad_norm": 1.577776551246643, "learning_rate": 0.00016027307029726354, "loss": 0.6483107566833496, "step": 191890 }, { "epoch": 1.1406934512664135, "grad_norm": 1.2390611171722412, "learning_rate": 0.00016026790707860232, "loss": 0.5547178745269775, "step": 191900 }, { "epoch": 1.1407528933430817, "grad_norm": 1.2719005346298218, "learning_rate": 0.0001602627436194759, "loss": 0.6611791133880616, "step": 191910 }, { "epoch": 1.1408123354197501, "grad_norm": 1.8736661672592163, "learning_rate": 0.00016025757991990894, "loss": 0.6239967346191406, "step": 191920 }, { "epoch": 1.1408717774964185, "grad_norm": 2.1818349361419678, "learning_rate": 0.00016025241597992612, "loss": 0.6620573043823242, "step": 191930 }, { "epoch": 1.140931219573087, "grad_norm": 1.7885746955871582, "learning_rate": 0.00016024725179955216, "loss": 0.6101173400878906, "step": 191940 }, { "epoch": 1.1409906616497554, "grad_norm": 1.6045788526535034, "learning_rate": 0.0001602420873788118, "loss": 0.6192329406738282, "step": 191950 }, { "epoch": 1.1410501037264238, "grad_norm": 1.5973894596099854, "learning_rate": 0.00016023692271772969, "loss": 0.6833085536956787, "step": 191960 }, { "epoch": 1.1411095458030922, "grad_norm": 1.1176130771636963, "learning_rate": 0.00016023175781633054, "loss": 0.6526787757873536, "step": 191970 }, { "epoch": 1.1411689878797606, "grad_norm": 1.415501356124878, "learning_rate": 0.0001602265926746391, "loss": 0.6463263511657715, "step": 191980 }, { "epoch": 1.141228429956429, "grad_norm": 1.615441083908081, "learning_rate": 0.00016022142729268005, "loss": 0.6372363090515136, "step": 191990 }, { "epoch": 1.1412878720330975, "grad_norm": 1.6716809272766113, "learning_rate": 0.00016021626167047814, "loss": 0.6360580444335937, "step": 192000 }, { "epoch": 1.1413473141097656, "grad_norm": 1.4637706279754639, "learning_rate": 0.00016021109580805797, "loss": 0.6326110363006592, "step": 192010 }, { "epoch": 1.141406756186434, "grad_norm": 1.466867208480835, "learning_rate": 0.0001602059297054444, "loss": 0.5653655052185058, "step": 192020 }, { "epoch": 1.1414661982631025, "grad_norm": 1.915009617805481, "learning_rate": 0.00016020076336266203, "loss": 0.6395985603332519, "step": 192030 }, { "epoch": 1.1415256403397709, "grad_norm": 1.8912957906723022, "learning_rate": 0.00016019559677973562, "loss": 0.5939498901367187, "step": 192040 }, { "epoch": 1.1415850824164393, "grad_norm": 1.9481353759765625, "learning_rate": 0.0001601904299566899, "loss": 0.6157814979553222, "step": 192050 }, { "epoch": 1.1416445244931077, "grad_norm": 1.5624072551727295, "learning_rate": 0.00016018526289354954, "loss": 0.6525109291076661, "step": 192060 }, { "epoch": 1.1417039665697761, "grad_norm": 1.9293686151504517, "learning_rate": 0.00016018009559033927, "loss": 0.6060916423797608, "step": 192070 }, { "epoch": 1.1417634086464445, "grad_norm": 1.3770675659179688, "learning_rate": 0.00016017492804708386, "loss": 0.6300839424133301, "step": 192080 }, { "epoch": 1.141822850723113, "grad_norm": 1.4655743837356567, "learning_rate": 0.00016016976026380795, "loss": 0.6008701801300049, "step": 192090 }, { "epoch": 1.1418822927997812, "grad_norm": 1.555931568145752, "learning_rate": 0.00016016459224053634, "loss": 0.6847933292388916, "step": 192100 }, { "epoch": 1.1419417348764496, "grad_norm": 1.5785658359527588, "learning_rate": 0.0001601594239772937, "loss": 0.669923734664917, "step": 192110 }, { "epoch": 1.142001176953118, "grad_norm": 1.6210788488388062, "learning_rate": 0.00016015425547410473, "loss": 0.630434513092041, "step": 192120 }, { "epoch": 1.1420606190297864, "grad_norm": 1.4064133167266846, "learning_rate": 0.00016014908673099427, "loss": 0.5983863353729248, "step": 192130 }, { "epoch": 1.1421200611064548, "grad_norm": 1.5517548322677612, "learning_rate": 0.00016014391774798694, "loss": 0.628476619720459, "step": 192140 }, { "epoch": 1.1421795031831232, "grad_norm": 1.763154149055481, "learning_rate": 0.00016013874852510747, "loss": 0.5921140670776367, "step": 192150 }, { "epoch": 1.1422389452597916, "grad_norm": 1.5393123626708984, "learning_rate": 0.0001601335790623806, "loss": 0.6386916637420654, "step": 192160 }, { "epoch": 1.14229838733646, "grad_norm": 1.2169029712677002, "learning_rate": 0.0001601284093598311, "loss": 0.5769474983215332, "step": 192170 }, { "epoch": 1.1423578294131285, "grad_norm": 1.4218753576278687, "learning_rate": 0.0001601232394174837, "loss": 0.5943038940429688, "step": 192180 }, { "epoch": 1.1424172714897969, "grad_norm": 1.2074863910675049, "learning_rate": 0.00016011806923536305, "loss": 0.6262050628662109, "step": 192190 }, { "epoch": 1.142476713566465, "grad_norm": 1.7655495405197144, "learning_rate": 0.000160112898813494, "loss": 0.6101063251495361, "step": 192200 }, { "epoch": 1.1425361556431335, "grad_norm": 1.3656911849975586, "learning_rate": 0.00016010772815190112, "loss": 0.6509566307067871, "step": 192210 }, { "epoch": 1.142595597719802, "grad_norm": 1.9657632112503052, "learning_rate": 0.00016010255725060934, "loss": 0.5716423988342285, "step": 192220 }, { "epoch": 1.1426550397964703, "grad_norm": 1.4043877124786377, "learning_rate": 0.00016009738610964328, "loss": 0.6211428642272949, "step": 192230 }, { "epoch": 1.1427144818731387, "grad_norm": 1.8742350339889526, "learning_rate": 0.00016009221472902763, "loss": 0.6094352722167968, "step": 192240 }, { "epoch": 1.1427739239498071, "grad_norm": 1.7910642623901367, "learning_rate": 0.00016008704310878727, "loss": 0.5925946235656738, "step": 192250 }, { "epoch": 1.1428333660264756, "grad_norm": 1.4507684707641602, "learning_rate": 0.00016008187124894684, "loss": 0.6101772308349609, "step": 192260 }, { "epoch": 1.142892808103144, "grad_norm": 1.5138615369796753, "learning_rate": 0.0001600766991495311, "loss": 0.5916766166687012, "step": 192270 }, { "epoch": 1.1429522501798122, "grad_norm": 1.3056352138519287, "learning_rate": 0.0001600715268105648, "loss": 0.5965821266174316, "step": 192280 }, { "epoch": 1.1430116922564806, "grad_norm": 2.9365785121917725, "learning_rate": 0.00016006635423207268, "loss": 0.6346420288085938, "step": 192290 }, { "epoch": 1.143071134333149, "grad_norm": 1.772577166557312, "learning_rate": 0.00016006118141407948, "loss": 0.668995475769043, "step": 192300 }, { "epoch": 1.1431305764098174, "grad_norm": 1.4223493337631226, "learning_rate": 0.00016005600835660997, "loss": 0.5643375873565674, "step": 192310 }, { "epoch": 1.1431900184864858, "grad_norm": 1.5577079057693481, "learning_rate": 0.00016005083505968884, "loss": 0.6269745826721191, "step": 192320 }, { "epoch": 1.1432494605631542, "grad_norm": 1.671868085861206, "learning_rate": 0.00016004566152334087, "loss": 0.689769172668457, "step": 192330 }, { "epoch": 1.1433089026398227, "grad_norm": 1.7380918264389038, "learning_rate": 0.00016004048774759084, "loss": 0.6100752830505372, "step": 192340 }, { "epoch": 1.143368344716491, "grad_norm": 1.4284701347351074, "learning_rate": 0.00016003531373246345, "loss": 0.6350218772888183, "step": 192350 }, { "epoch": 1.1434277867931595, "grad_norm": 1.598885416984558, "learning_rate": 0.00016003013947798347, "loss": 0.6214591979980468, "step": 192360 }, { "epoch": 1.143487228869828, "grad_norm": 1.5546754598617554, "learning_rate": 0.00016002496498417567, "loss": 0.6167162895202637, "step": 192370 }, { "epoch": 1.143546670946496, "grad_norm": 1.6502937078475952, "learning_rate": 0.00016001979025106477, "loss": 0.6308869361877442, "step": 192380 }, { "epoch": 1.1436061130231645, "grad_norm": 1.5358010530471802, "learning_rate": 0.00016001461527867555, "loss": 0.7049171924591064, "step": 192390 }, { "epoch": 1.143665555099833, "grad_norm": 1.2428828477859497, "learning_rate": 0.00016000944006703275, "loss": 0.5871007919311524, "step": 192400 }, { "epoch": 1.1437249971765013, "grad_norm": 1.7440396547317505, "learning_rate": 0.00016000426461616114, "loss": 0.6442187309265137, "step": 192410 }, { "epoch": 1.1437844392531697, "grad_norm": 1.7126173973083496, "learning_rate": 0.00015999908892608546, "loss": 0.6115259647369384, "step": 192420 }, { "epoch": 1.1438438813298382, "grad_norm": 1.2948524951934814, "learning_rate": 0.0001599939129968305, "loss": 0.6345840454101562, "step": 192430 }, { "epoch": 1.1439033234065066, "grad_norm": 1.5625377893447876, "learning_rate": 0.00015998873682842096, "loss": 0.6397866249084473, "step": 192440 }, { "epoch": 1.143962765483175, "grad_norm": 1.5295161008834839, "learning_rate": 0.00015998356042088165, "loss": 0.6433187961578369, "step": 192450 }, { "epoch": 1.1440222075598434, "grad_norm": 1.971555471420288, "learning_rate": 0.00015997838377423734, "loss": 0.5799018859863281, "step": 192460 }, { "epoch": 1.1440816496365116, "grad_norm": 1.6306039094924927, "learning_rate": 0.00015997320688851277, "loss": 0.620638084411621, "step": 192470 }, { "epoch": 1.14414109171318, "grad_norm": 1.4966789484024048, "learning_rate": 0.0001599680297637327, "loss": 0.6567304611206055, "step": 192480 }, { "epoch": 1.1442005337898484, "grad_norm": 1.6251568794250488, "learning_rate": 0.00015996285239992193, "loss": 0.6310848236083985, "step": 192490 }, { "epoch": 1.1442599758665168, "grad_norm": 1.348950982093811, "learning_rate": 0.00015995767479710517, "loss": 0.6279382228851318, "step": 192500 }, { "epoch": 1.1443194179431853, "grad_norm": 1.6229102611541748, "learning_rate": 0.00015995249695530724, "loss": 0.5778120994567871, "step": 192510 }, { "epoch": 1.1443788600198537, "grad_norm": 1.299919605255127, "learning_rate": 0.00015994731887455287, "loss": 0.5831845760345459, "step": 192520 }, { "epoch": 1.144438302096522, "grad_norm": 1.7131973505020142, "learning_rate": 0.00015994214055486687, "loss": 0.5866049289703369, "step": 192530 }, { "epoch": 1.1444977441731905, "grad_norm": 1.459693431854248, "learning_rate": 0.000159936961996274, "loss": 0.6157154560089111, "step": 192540 }, { "epoch": 1.144557186249859, "grad_norm": 1.8387073278427124, "learning_rate": 0.000159931783198799, "loss": 0.5879953384399415, "step": 192550 }, { "epoch": 1.1446166283265273, "grad_norm": 1.7473827600479126, "learning_rate": 0.00015992660416246665, "loss": 0.618349552154541, "step": 192560 }, { "epoch": 1.1446760704031955, "grad_norm": 2.038699150085449, "learning_rate": 0.00015992142488730176, "loss": 0.6034067153930665, "step": 192570 }, { "epoch": 1.144735512479864, "grad_norm": 1.895169973373413, "learning_rate": 0.00015991624537332912, "loss": 0.6605345726013183, "step": 192580 }, { "epoch": 1.1447949545565324, "grad_norm": 1.361132264137268, "learning_rate": 0.00015991106562057345, "loss": 0.6280640602111817, "step": 192590 }, { "epoch": 1.1448543966332008, "grad_norm": 1.6520588397979736, "learning_rate": 0.00015990588562905952, "loss": 0.6075862407684326, "step": 192600 }, { "epoch": 1.1449138387098692, "grad_norm": 1.6151071786880493, "learning_rate": 0.00015990070539881218, "loss": 0.67303466796875, "step": 192610 }, { "epoch": 1.1449732807865376, "grad_norm": 1.4388149976730347, "learning_rate": 0.0001598955249298562, "loss": 0.5556690692901611, "step": 192620 }, { "epoch": 1.145032722863206, "grad_norm": 1.7030997276306152, "learning_rate": 0.00015989034422221626, "loss": 0.6401334762573242, "step": 192630 }, { "epoch": 1.1450921649398744, "grad_norm": 1.7573555707931519, "learning_rate": 0.0001598851632759173, "loss": 0.6246713638305664, "step": 192640 }, { "epoch": 1.1451516070165426, "grad_norm": 1.7354754209518433, "learning_rate": 0.00015987998209098398, "loss": 0.5847334861755371, "step": 192650 }, { "epoch": 1.145211049093211, "grad_norm": 1.4208025932312012, "learning_rate": 0.00015987480066744113, "loss": 0.6128709793090821, "step": 192660 }, { "epoch": 1.1452704911698794, "grad_norm": 1.2671226263046265, "learning_rate": 0.00015986961900531352, "loss": 0.6070728302001953, "step": 192670 }, { "epoch": 1.1453299332465479, "grad_norm": 1.5282816886901855, "learning_rate": 0.00015986443710462594, "loss": 0.6330165863037109, "step": 192680 }, { "epoch": 1.1453893753232163, "grad_norm": 1.6140661239624023, "learning_rate": 0.00015985925496540324, "loss": 0.622714900970459, "step": 192690 }, { "epoch": 1.1454488173998847, "grad_norm": 1.820736289024353, "learning_rate": 0.0001598540725876701, "loss": 0.6379076957702636, "step": 192700 }, { "epoch": 1.145508259476553, "grad_norm": 1.6710171699523926, "learning_rate": 0.0001598488899714514, "loss": 0.6227635860443115, "step": 192710 }, { "epoch": 1.1455677015532215, "grad_norm": 1.528903603553772, "learning_rate": 0.00015984370711677194, "loss": 0.6234947204589844, "step": 192720 }, { "epoch": 1.14562714362989, "grad_norm": 1.597517728805542, "learning_rate": 0.0001598385240236564, "loss": 0.6074374198913575, "step": 192730 }, { "epoch": 1.1456865857065583, "grad_norm": 1.5638935565948486, "learning_rate": 0.00015983334069212969, "loss": 0.5943583488464356, "step": 192740 }, { "epoch": 1.1457460277832265, "grad_norm": 1.8515431880950928, "learning_rate": 0.00015982815712221654, "loss": 0.603575611114502, "step": 192750 }, { "epoch": 1.145805469859895, "grad_norm": 1.474473476409912, "learning_rate": 0.0001598229733139418, "loss": 0.6179943084716797, "step": 192760 }, { "epoch": 1.1458649119365634, "grad_norm": 1.7211185693740845, "learning_rate": 0.00015981778926733024, "loss": 0.6126873016357421, "step": 192770 }, { "epoch": 1.1459243540132318, "grad_norm": 1.9076801538467407, "learning_rate": 0.0001598126049824066, "loss": 0.6278419017791748, "step": 192780 }, { "epoch": 1.1459837960899002, "grad_norm": 1.7379645109176636, "learning_rate": 0.0001598074204591958, "loss": 0.6109419822692871, "step": 192790 }, { "epoch": 1.1460432381665686, "grad_norm": 1.4689891338348389, "learning_rate": 0.00015980223569772256, "loss": 0.5822585105895997, "step": 192800 }, { "epoch": 1.146102680243237, "grad_norm": 1.4931299686431885, "learning_rate": 0.0001597970506980117, "loss": 0.5853504180908203, "step": 192810 }, { "epoch": 1.1461621223199054, "grad_norm": 1.5548629760742188, "learning_rate": 0.000159791865460088, "loss": 0.6105363845825196, "step": 192820 }, { "epoch": 1.1462215643965739, "grad_norm": 1.5283921957015991, "learning_rate": 0.00015978667998397633, "loss": 0.6311882972717285, "step": 192830 }, { "epoch": 1.146281006473242, "grad_norm": 1.5527238845825195, "learning_rate": 0.0001597814942697014, "loss": 0.6116101264953613, "step": 192840 }, { "epoch": 1.1463404485499105, "grad_norm": 1.5356453657150269, "learning_rate": 0.0001597763083172881, "loss": 0.5391660690307617, "step": 192850 }, { "epoch": 1.1463998906265789, "grad_norm": 1.1616836786270142, "learning_rate": 0.00015977112212676124, "loss": 0.5783348083496094, "step": 192860 }, { "epoch": 1.1464593327032473, "grad_norm": 1.3786808252334595, "learning_rate": 0.00015976593569814557, "loss": 0.5550100326538085, "step": 192870 }, { "epoch": 1.1465187747799157, "grad_norm": 1.4137924909591675, "learning_rate": 0.00015976074903146592, "loss": 0.5592320919036865, "step": 192880 }, { "epoch": 1.1465782168565841, "grad_norm": 2.0284416675567627, "learning_rate": 0.0001597555621267471, "loss": 0.6679833412170411, "step": 192890 }, { "epoch": 1.1466376589332525, "grad_norm": 1.6881356239318848, "learning_rate": 0.00015975037498401395, "loss": 0.639924144744873, "step": 192900 }, { "epoch": 1.146697101009921, "grad_norm": 1.7774596214294434, "learning_rate": 0.00015974518760329126, "loss": 0.673470401763916, "step": 192910 }, { "epoch": 1.1467565430865894, "grad_norm": 1.5779780149459839, "learning_rate": 0.00015973999998460383, "loss": 0.5895074844360352, "step": 192920 }, { "epoch": 1.1468159851632578, "grad_norm": 1.8038558959960938, "learning_rate": 0.00015973481212797652, "loss": 0.6552738189697266, "step": 192930 }, { "epoch": 1.146875427239926, "grad_norm": 1.4363473653793335, "learning_rate": 0.00015972962403343409, "loss": 0.6510171890258789, "step": 192940 }, { "epoch": 1.1469348693165944, "grad_norm": 1.6796631813049316, "learning_rate": 0.0001597244357010014, "loss": 0.645200538635254, "step": 192950 }, { "epoch": 1.1469943113932628, "grad_norm": 1.6028962135314941, "learning_rate": 0.0001597192471307033, "loss": 0.5816814422607421, "step": 192960 }, { "epoch": 1.1470537534699312, "grad_norm": 1.5725383758544922, "learning_rate": 0.00015971405832256453, "loss": 0.6122696876525879, "step": 192970 }, { "epoch": 1.1471131955465996, "grad_norm": 1.8827100992202759, "learning_rate": 0.00015970886927660997, "loss": 0.6253865242004395, "step": 192980 }, { "epoch": 1.147172637623268, "grad_norm": 1.8856195211410522, "learning_rate": 0.00015970367999286442, "loss": 0.6430246829986572, "step": 192990 }, { "epoch": 1.1472320796999365, "grad_norm": 1.4459506273269653, "learning_rate": 0.00015969849047135272, "loss": 0.6155708312988282, "step": 193000 }, { "epoch": 1.1472915217766049, "grad_norm": 1.5876542329788208, "learning_rate": 0.00015969330071209968, "loss": 0.5633405685424805, "step": 193010 }, { "epoch": 1.147350963853273, "grad_norm": 1.8604731559753418, "learning_rate": 0.00015968811071513008, "loss": 0.5950394630432129, "step": 193020 }, { "epoch": 1.1474104059299415, "grad_norm": 1.457262396812439, "learning_rate": 0.00015968292048046886, "loss": 0.6076964378356934, "step": 193030 }, { "epoch": 1.14746984800661, "grad_norm": 1.4426590204238892, "learning_rate": 0.00015967773000814077, "loss": 0.6349320411682129, "step": 193040 }, { "epoch": 1.1475292900832783, "grad_norm": 1.414807677268982, "learning_rate": 0.00015967253929817063, "loss": 0.6611774921417236, "step": 193050 }, { "epoch": 1.1475887321599467, "grad_norm": 1.6384427547454834, "learning_rate": 0.00015966734835058335, "loss": 0.6401141166687012, "step": 193060 }, { "epoch": 1.1476481742366151, "grad_norm": 1.8100255727767944, "learning_rate": 0.00015966215716540363, "loss": 0.6273819923400878, "step": 193070 }, { "epoch": 1.1477076163132836, "grad_norm": 2.1344666481018066, "learning_rate": 0.00015965696574265644, "loss": 0.6757831573486328, "step": 193080 }, { "epoch": 1.147767058389952, "grad_norm": 1.4116194248199463, "learning_rate": 0.00015965177408236653, "loss": 0.6338587284088135, "step": 193090 }, { "epoch": 1.1478265004666204, "grad_norm": 1.320257544517517, "learning_rate": 0.00015964658218455875, "loss": 0.613009262084961, "step": 193100 }, { "epoch": 1.1478859425432888, "grad_norm": 1.342523455619812, "learning_rate": 0.00015964139004925797, "loss": 0.6282054424285889, "step": 193110 }, { "epoch": 1.147945384619957, "grad_norm": 1.4778814315795898, "learning_rate": 0.00015963619767648898, "loss": 0.682857608795166, "step": 193120 }, { "epoch": 1.1480048266966254, "grad_norm": 1.469569206237793, "learning_rate": 0.00015963100506627667, "loss": 0.5738914489746094, "step": 193130 }, { "epoch": 1.1480642687732938, "grad_norm": 1.6091147661209106, "learning_rate": 0.00015962581221864582, "loss": 0.6383954048156738, "step": 193140 }, { "epoch": 1.1481237108499622, "grad_norm": 1.9012008905410767, "learning_rate": 0.00015962061913362132, "loss": 0.5967143058776856, "step": 193150 }, { "epoch": 1.1481831529266306, "grad_norm": 1.8075193166732788, "learning_rate": 0.000159615425811228, "loss": 0.5933319568634033, "step": 193160 }, { "epoch": 1.148242595003299, "grad_norm": 1.4485763311386108, "learning_rate": 0.0001596102322514907, "loss": 0.6318995475769043, "step": 193170 }, { "epoch": 1.1483020370799675, "grad_norm": 1.2009565830230713, "learning_rate": 0.00015960503845443424, "loss": 0.6466095924377442, "step": 193180 }, { "epoch": 1.148361479156636, "grad_norm": 1.9723751544952393, "learning_rate": 0.00015959984442008346, "loss": 0.6224802494049072, "step": 193190 }, { "epoch": 1.1484209212333043, "grad_norm": 1.490151286125183, "learning_rate": 0.00015959465014846327, "loss": 0.6259609222412109, "step": 193200 }, { "epoch": 1.1484803633099725, "grad_norm": 1.551737666130066, "learning_rate": 0.0001595894556395985, "loss": 0.6589481353759765, "step": 193210 }, { "epoch": 1.148539805386641, "grad_norm": 1.4241271018981934, "learning_rate": 0.00015958426089351398, "loss": 0.6122723579406738, "step": 193220 }, { "epoch": 1.1485992474633093, "grad_norm": 1.7617994546890259, "learning_rate": 0.00015957906591023452, "loss": 0.6190628051757813, "step": 193230 }, { "epoch": 1.1486586895399777, "grad_norm": 1.7485681772232056, "learning_rate": 0.00015957387068978504, "loss": 0.6710068225860596, "step": 193240 }, { "epoch": 1.1487181316166462, "grad_norm": 1.2874479293823242, "learning_rate": 0.00015956867523219038, "loss": 0.5600399494171142, "step": 193250 }, { "epoch": 1.1487775736933146, "grad_norm": 1.687456727027893, "learning_rate": 0.0001595634795374753, "loss": 0.5951109886169433, "step": 193260 }, { "epoch": 1.148837015769983, "grad_norm": 1.193827748298645, "learning_rate": 0.0001595582836056648, "loss": 0.6167004585266114, "step": 193270 }, { "epoch": 1.1488964578466514, "grad_norm": 1.5065033435821533, "learning_rate": 0.00015955308743678367, "loss": 0.5553279399871827, "step": 193280 }, { "epoch": 1.1489558999233198, "grad_norm": 1.230298399925232, "learning_rate": 0.00015954789103085677, "loss": 0.6632309913635254, "step": 193290 }, { "epoch": 1.1490153419999882, "grad_norm": 1.7286463975906372, "learning_rate": 0.00015954269438790887, "loss": 0.6605350494384765, "step": 193300 }, { "epoch": 1.1490747840766564, "grad_norm": 1.2002538442611694, "learning_rate": 0.00015953749750796502, "loss": 0.5905313491821289, "step": 193310 }, { "epoch": 1.1491342261533248, "grad_norm": 1.5817803144454956, "learning_rate": 0.00015953230039104991, "loss": 0.5805414199829102, "step": 193320 }, { "epoch": 1.1491936682299932, "grad_norm": 1.4383987188339233, "learning_rate": 0.00015952710303718845, "loss": 0.5967327117919922, "step": 193330 }, { "epoch": 1.1492531103066617, "grad_norm": 1.6441069841384888, "learning_rate": 0.00015952190544640555, "loss": 0.6413164615631104, "step": 193340 }, { "epoch": 1.14931255238333, "grad_norm": 1.300779104232788, "learning_rate": 0.00015951670761872605, "loss": 0.5448722839355469, "step": 193350 }, { "epoch": 1.1493719944599985, "grad_norm": 2.1715190410614014, "learning_rate": 0.00015951150955417475, "loss": 0.6367037773132325, "step": 193360 }, { "epoch": 1.149431436536667, "grad_norm": 1.2746745347976685, "learning_rate": 0.00015950631125277658, "loss": 0.5900956153869629, "step": 193370 }, { "epoch": 1.1494908786133353, "grad_norm": 1.8102885484695435, "learning_rate": 0.00015950111271455643, "loss": 0.5961443424224854, "step": 193380 }, { "epoch": 1.1495503206900035, "grad_norm": 1.7157810926437378, "learning_rate": 0.00015949591393953912, "loss": 0.6305424690246582, "step": 193390 }, { "epoch": 1.149609762766672, "grad_norm": 1.5426111221313477, "learning_rate": 0.00015949071492774952, "loss": 0.620029878616333, "step": 193400 }, { "epoch": 1.1496692048433403, "grad_norm": 1.442821741104126, "learning_rate": 0.00015948551567921253, "loss": 0.6126952648162842, "step": 193410 }, { "epoch": 1.1497286469200088, "grad_norm": 1.6990879774093628, "learning_rate": 0.000159480316193953, "loss": 0.5312845706939697, "step": 193420 }, { "epoch": 1.1497880889966772, "grad_norm": 1.8255283832550049, "learning_rate": 0.0001594751164719958, "loss": 0.6498810768127441, "step": 193430 }, { "epoch": 1.1498475310733456, "grad_norm": 1.6900529861450195, "learning_rate": 0.00015946991651336583, "loss": 0.6561136245727539, "step": 193440 }, { "epoch": 1.149906973150014, "grad_norm": 1.4602352380752563, "learning_rate": 0.00015946471631808794, "loss": 0.6430725574493408, "step": 193450 }, { "epoch": 1.1499664152266824, "grad_norm": 1.711361050605774, "learning_rate": 0.00015945951588618697, "loss": 0.6547651290893555, "step": 193460 }, { "epoch": 1.1500258573033508, "grad_norm": 1.4659578800201416, "learning_rate": 0.00015945431521768787, "loss": 0.6525809288024902, "step": 193470 }, { "epoch": 1.1500852993800192, "grad_norm": 1.4238089323043823, "learning_rate": 0.0001594491143126155, "loss": 0.6141201019287109, "step": 193480 }, { "epoch": 1.1501447414566874, "grad_norm": 1.7523348331451416, "learning_rate": 0.00015944391317099474, "loss": 0.6212827682495117, "step": 193490 }, { "epoch": 1.1502041835333559, "grad_norm": 1.8133145570755005, "learning_rate": 0.0001594387117928504, "loss": 0.606939697265625, "step": 193500 }, { "epoch": 1.1502636256100243, "grad_norm": 1.2951812744140625, "learning_rate": 0.00015943351017820746, "loss": 0.6311286926269531, "step": 193510 }, { "epoch": 1.1503230676866927, "grad_norm": 2.0784647464752197, "learning_rate": 0.00015942830832709078, "loss": 0.6255736351013184, "step": 193520 }, { "epoch": 1.150382509763361, "grad_norm": 1.7418301105499268, "learning_rate": 0.00015942310623952524, "loss": 0.6663007736206055, "step": 193530 }, { "epoch": 1.1504419518400295, "grad_norm": 1.368666410446167, "learning_rate": 0.00015941790391553565, "loss": 0.586893367767334, "step": 193540 }, { "epoch": 1.150501393916698, "grad_norm": 1.4613317251205444, "learning_rate": 0.000159412701355147, "loss": 0.6109541893005371, "step": 193550 }, { "epoch": 1.1505608359933663, "grad_norm": 1.794512152671814, "learning_rate": 0.0001594074985583841, "loss": 0.6845250129699707, "step": 193560 }, { "epoch": 1.1506202780700345, "grad_norm": 1.6093629598617554, "learning_rate": 0.00015940229552527193, "loss": 0.6259510040283203, "step": 193570 }, { "epoch": 1.150679720146703, "grad_norm": 1.3473780155181885, "learning_rate": 0.00015939709225583525, "loss": 0.6831461906433105, "step": 193580 }, { "epoch": 1.1507391622233714, "grad_norm": 1.1668317317962646, "learning_rate": 0.00015939188875009906, "loss": 0.6534381866455078, "step": 193590 }, { "epoch": 1.1507986043000398, "grad_norm": 1.5951281785964966, "learning_rate": 0.00015938668500808822, "loss": 0.6478457450866699, "step": 193600 }, { "epoch": 1.1508580463767082, "grad_norm": 1.5413886308670044, "learning_rate": 0.00015938148102982762, "loss": 0.559539794921875, "step": 193610 }, { "epoch": 1.1509174884533766, "grad_norm": 1.7515453100204468, "learning_rate": 0.00015937627681534216, "loss": 0.5806033611297607, "step": 193620 }, { "epoch": 1.150976930530045, "grad_norm": 1.6556838750839233, "learning_rate": 0.00015937107236465672, "loss": 0.6326588153839111, "step": 193630 }, { "epoch": 1.1510363726067134, "grad_norm": 1.5328425168991089, "learning_rate": 0.0001593658676777962, "loss": 0.5722816467285157, "step": 193640 }, { "epoch": 1.1510958146833818, "grad_norm": 2.145210027694702, "learning_rate": 0.0001593606627547855, "loss": 0.6282143115997314, "step": 193650 }, { "epoch": 1.1511552567600503, "grad_norm": 1.5066485404968262, "learning_rate": 0.00015935545759564952, "loss": 0.6449490547180176, "step": 193660 }, { "epoch": 1.1512146988367187, "grad_norm": 1.1928865909576416, "learning_rate": 0.00015935025220041317, "loss": 0.6301053047180176, "step": 193670 }, { "epoch": 1.1512741409133869, "grad_norm": 1.58657705783844, "learning_rate": 0.00015934504656910133, "loss": 0.6309889793395996, "step": 193680 }, { "epoch": 1.1513335829900553, "grad_norm": 1.3929030895233154, "learning_rate": 0.0001593398407017389, "loss": 0.6021913528442383, "step": 193690 }, { "epoch": 1.1513930250667237, "grad_norm": 1.170363187789917, "learning_rate": 0.0001593346345983508, "loss": 0.5902385234832763, "step": 193700 }, { "epoch": 1.1514524671433921, "grad_norm": 1.7846399545669556, "learning_rate": 0.00015932942825896195, "loss": 0.5898967742919922, "step": 193710 }, { "epoch": 1.1515119092200605, "grad_norm": 1.6276806592941284, "learning_rate": 0.00015932422168359725, "loss": 0.6089997291564941, "step": 193720 }, { "epoch": 1.151571351296729, "grad_norm": 1.8422696590423584, "learning_rate": 0.00015931901487228157, "loss": 0.6321425914764405, "step": 193730 }, { "epoch": 1.1516307933733974, "grad_norm": 1.6139110326766968, "learning_rate": 0.00015931380782503984, "loss": 0.6246165275573731, "step": 193740 }, { "epoch": 1.1516902354500658, "grad_norm": 1.5449671745300293, "learning_rate": 0.000159308600541897, "loss": 0.6365854263305664, "step": 193750 }, { "epoch": 1.151749677526734, "grad_norm": 1.4016145467758179, "learning_rate": 0.00015930339302287788, "loss": 0.5404937744140625, "step": 193760 }, { "epoch": 1.1518091196034024, "grad_norm": 1.587737798690796, "learning_rate": 0.00015929818526800747, "loss": 0.6061375617980957, "step": 193770 }, { "epoch": 1.1518685616800708, "grad_norm": 1.4787601232528687, "learning_rate": 0.00015929297727731065, "loss": 0.619603157043457, "step": 193780 }, { "epoch": 1.1519280037567392, "grad_norm": 1.5025010108947754, "learning_rate": 0.00015928776905081233, "loss": 0.6114055633544921, "step": 193790 }, { "epoch": 1.1519874458334076, "grad_norm": 1.4878544807434082, "learning_rate": 0.00015928256058853743, "loss": 0.5823400497436524, "step": 193800 }, { "epoch": 1.152046887910076, "grad_norm": 1.2233434915542603, "learning_rate": 0.00015927735189051086, "loss": 0.6277857303619385, "step": 193810 }, { "epoch": 1.1521063299867444, "grad_norm": 1.5738813877105713, "learning_rate": 0.00015927214295675753, "loss": 0.5997038841247558, "step": 193820 }, { "epoch": 1.1521657720634129, "grad_norm": 1.357753872871399, "learning_rate": 0.00015926693378730242, "loss": 0.5761194229125977, "step": 193830 }, { "epoch": 1.1522252141400813, "grad_norm": 1.5685125589370728, "learning_rate": 0.00015926172438217038, "loss": 0.658354663848877, "step": 193840 }, { "epoch": 1.1522846562167497, "grad_norm": 1.570820689201355, "learning_rate": 0.00015925651474138635, "loss": 0.6223149299621582, "step": 193850 }, { "epoch": 1.1523440982934179, "grad_norm": 1.629575252532959, "learning_rate": 0.0001592513048649752, "loss": 0.6596694946289062, "step": 193860 }, { "epoch": 1.1524035403700863, "grad_norm": 1.6463416814804077, "learning_rate": 0.00015924609475296197, "loss": 0.5932626724243164, "step": 193870 }, { "epoch": 1.1524629824467547, "grad_norm": 1.7815830707550049, "learning_rate": 0.0001592408844053715, "loss": 0.649678087234497, "step": 193880 }, { "epoch": 1.1525224245234231, "grad_norm": 1.6650747060775757, "learning_rate": 0.0001592356738222287, "loss": 0.6224794864654541, "step": 193890 }, { "epoch": 1.1525818666000915, "grad_norm": 1.5551356077194214, "learning_rate": 0.00015923046300355854, "loss": 0.6628069877624512, "step": 193900 }, { "epoch": 1.15264130867676, "grad_norm": 1.4519855976104736, "learning_rate": 0.00015922525194938595, "loss": 0.6267869949340821, "step": 193910 }, { "epoch": 1.1527007507534284, "grad_norm": 1.996241569519043, "learning_rate": 0.00015922004065973587, "loss": 0.5875413894653321, "step": 193920 }, { "epoch": 1.1527601928300968, "grad_norm": 1.7372955083847046, "learning_rate": 0.00015921482913463315, "loss": 0.7484500408172607, "step": 193930 }, { "epoch": 1.152819634906765, "grad_norm": 1.4114211797714233, "learning_rate": 0.00015920961737410277, "loss": 0.5693389892578125, "step": 193940 }, { "epoch": 1.1528790769834334, "grad_norm": 1.3221545219421387, "learning_rate": 0.00015920440537816967, "loss": 0.6398015022277832, "step": 193950 }, { "epoch": 1.1529385190601018, "grad_norm": 1.9325510263442993, "learning_rate": 0.0001591991931468588, "loss": 0.6126927375793457, "step": 193960 }, { "epoch": 1.1529979611367702, "grad_norm": 1.8401621580123901, "learning_rate": 0.00015919398068019503, "loss": 0.612610912322998, "step": 193970 }, { "epoch": 1.1530574032134386, "grad_norm": 1.8026220798492432, "learning_rate": 0.00015918876797820338, "loss": 0.6170300960540771, "step": 193980 }, { "epoch": 1.153116845290107, "grad_norm": 1.753882884979248, "learning_rate": 0.0001591835550409087, "loss": 0.6333279609680176, "step": 193990 }, { "epoch": 1.1531762873667755, "grad_norm": 1.3535687923431396, "learning_rate": 0.00015917834186833597, "loss": 0.6597814083099365, "step": 194000 }, { "epoch": 1.1532357294434439, "grad_norm": 1.4407497644424438, "learning_rate": 0.00015917312846051016, "loss": 0.610951042175293, "step": 194010 }, { "epoch": 1.1532951715201123, "grad_norm": 1.551819086074829, "learning_rate": 0.00015916791481745612, "loss": 0.5974505424499512, "step": 194020 }, { "epoch": 1.1533546135967807, "grad_norm": 1.601623773574829, "learning_rate": 0.0001591627009391989, "loss": 0.5394173622131347, "step": 194030 }, { "epoch": 1.1534140556734491, "grad_norm": 2.0701448917388916, "learning_rate": 0.00015915748682576332, "loss": 0.6272829055786133, "step": 194040 }, { "epoch": 1.1534734977501173, "grad_norm": 1.584622859954834, "learning_rate": 0.00015915227247717445, "loss": 0.5725985050201416, "step": 194050 }, { "epoch": 1.1535329398267857, "grad_norm": 1.6274232864379883, "learning_rate": 0.00015914705789345714, "loss": 0.6007026672363281, "step": 194060 }, { "epoch": 1.1535923819034541, "grad_norm": 1.928828477859497, "learning_rate": 0.00015914184307463635, "loss": 0.6312177658081055, "step": 194070 }, { "epoch": 1.1536518239801226, "grad_norm": 1.5424480438232422, "learning_rate": 0.00015913662802073705, "loss": 0.6218608856201172, "step": 194080 }, { "epoch": 1.153711266056791, "grad_norm": 1.4151586294174194, "learning_rate": 0.00015913141273178423, "loss": 0.6031941890716552, "step": 194090 }, { "epoch": 1.1537707081334594, "grad_norm": 1.8517825603485107, "learning_rate": 0.00015912619720780276, "loss": 0.6391126632690429, "step": 194100 }, { "epoch": 1.1538301502101278, "grad_norm": 1.4858802556991577, "learning_rate": 0.0001591209814488176, "loss": 0.6122547149658203, "step": 194110 }, { "epoch": 1.1538895922867962, "grad_norm": 1.8938300609588623, "learning_rate": 0.00015911576545485373, "loss": 0.6310628890991211, "step": 194120 }, { "epoch": 1.1539490343634644, "grad_norm": 1.4343221187591553, "learning_rate": 0.00015911054922593607, "loss": 0.5728752613067627, "step": 194130 }, { "epoch": 1.1540084764401328, "grad_norm": 1.6411939859390259, "learning_rate": 0.00015910533276208963, "loss": 0.6038647651672363, "step": 194140 }, { "epoch": 1.1540679185168012, "grad_norm": 1.3674185276031494, "learning_rate": 0.00015910011606333927, "loss": 0.6375962257385254, "step": 194150 }, { "epoch": 1.1541273605934697, "grad_norm": 1.3680826425552368, "learning_rate": 0.00015909489912971006, "loss": 0.5916666984558105, "step": 194160 }, { "epoch": 1.154186802670138, "grad_norm": 1.6274842023849487, "learning_rate": 0.00015908968196122686, "loss": 0.6461404800415039, "step": 194170 }, { "epoch": 1.1542462447468065, "grad_norm": 1.7129818201065063, "learning_rate": 0.0001590844645579147, "loss": 0.6190709590911865, "step": 194180 }, { "epoch": 1.154305686823475, "grad_norm": 1.6372489929199219, "learning_rate": 0.00015907924691979845, "loss": 0.6135813236236572, "step": 194190 }, { "epoch": 1.1543651289001433, "grad_norm": 1.402754306793213, "learning_rate": 0.00015907402904690316, "loss": 0.6167635917663574, "step": 194200 }, { "epoch": 1.1544245709768117, "grad_norm": 1.5659905672073364, "learning_rate": 0.00015906881093925374, "loss": 0.6340157508850097, "step": 194210 }, { "epoch": 1.1544840130534801, "grad_norm": 1.5296916961669922, "learning_rate": 0.00015906359259687517, "loss": 0.6070158004760742, "step": 194220 }, { "epoch": 1.1545434551301483, "grad_norm": 1.9467579126358032, "learning_rate": 0.0001590583740197924, "loss": 0.6760453224182129, "step": 194230 }, { "epoch": 1.1546028972068167, "grad_norm": 1.882365107536316, "learning_rate": 0.0001590531552080304, "loss": 0.6308466911315918, "step": 194240 }, { "epoch": 1.1546623392834852, "grad_norm": 1.3573929071426392, "learning_rate": 0.00015904793616161415, "loss": 0.6500473499298096, "step": 194250 }, { "epoch": 1.1547217813601536, "grad_norm": 1.4973576068878174, "learning_rate": 0.00015904271688056858, "loss": 0.636309289932251, "step": 194260 }, { "epoch": 1.154781223436822, "grad_norm": 1.7197284698486328, "learning_rate": 0.0001590374973649187, "loss": 0.5637708187103272, "step": 194270 }, { "epoch": 1.1548406655134904, "grad_norm": 1.7200943231582642, "learning_rate": 0.00015903227761468946, "loss": 0.6177192687988281, "step": 194280 }, { "epoch": 1.1549001075901588, "grad_norm": 1.640133023262024, "learning_rate": 0.00015902705762990582, "loss": 0.6490677833557129, "step": 194290 }, { "epoch": 1.1549595496668272, "grad_norm": 1.486598253250122, "learning_rate": 0.00015902183741059277, "loss": 0.6437224388122559, "step": 194300 }, { "epoch": 1.1550189917434954, "grad_norm": 1.4111785888671875, "learning_rate": 0.00015901661695677524, "loss": 0.6473742008209229, "step": 194310 }, { "epoch": 1.1550784338201638, "grad_norm": 1.1519211530685425, "learning_rate": 0.00015901139626847826, "loss": 0.619047212600708, "step": 194320 }, { "epoch": 1.1551378758968323, "grad_norm": 1.5276246070861816, "learning_rate": 0.00015900617534572676, "loss": 0.6293180465698243, "step": 194330 }, { "epoch": 1.1551973179735007, "grad_norm": 1.544161319732666, "learning_rate": 0.00015900095418854577, "loss": 0.5622092247009277, "step": 194340 }, { "epoch": 1.155256760050169, "grad_norm": 1.4374186992645264, "learning_rate": 0.00015899573279696018, "loss": 0.5672353744506836, "step": 194350 }, { "epoch": 1.1553162021268375, "grad_norm": 1.103304147720337, "learning_rate": 0.000158990511170995, "loss": 0.5742069244384765, "step": 194360 }, { "epoch": 1.155375644203506, "grad_norm": 1.5348896980285645, "learning_rate": 0.00015898528931067532, "loss": 0.6154931068420411, "step": 194370 }, { "epoch": 1.1554350862801743, "grad_norm": 1.7093026638031006, "learning_rate": 0.00015898006721602593, "loss": 0.5981228828430176, "step": 194380 }, { "epoch": 1.1554945283568427, "grad_norm": 1.3882192373275757, "learning_rate": 0.00015897484488707197, "loss": 0.5442137718200684, "step": 194390 }, { "epoch": 1.1555539704335112, "grad_norm": 1.3600130081176758, "learning_rate": 0.00015896962232383834, "loss": 0.6645715713500977, "step": 194400 }, { "epoch": 1.1556134125101796, "grad_norm": 1.4773741960525513, "learning_rate": 0.00015896439952635, "loss": 0.5880251407623291, "step": 194410 }, { "epoch": 1.1556728545868478, "grad_norm": 1.6163229942321777, "learning_rate": 0.000158959176494632, "loss": 0.6469340324401855, "step": 194420 }, { "epoch": 1.1557322966635162, "grad_norm": 1.643080711364746, "learning_rate": 0.00015895395322870935, "loss": 0.6597039699554443, "step": 194430 }, { "epoch": 1.1557917387401846, "grad_norm": 1.5482650995254517, "learning_rate": 0.0001589487297286069, "loss": 0.5979754447937011, "step": 194440 }, { "epoch": 1.155851180816853, "grad_norm": 1.5591038465499878, "learning_rate": 0.00015894350599434976, "loss": 0.5556430816650391, "step": 194450 }, { "epoch": 1.1559106228935214, "grad_norm": 1.5816303491592407, "learning_rate": 0.00015893828202596287, "loss": 0.6202332973480225, "step": 194460 }, { "epoch": 1.1559700649701898, "grad_norm": 1.5898573398590088, "learning_rate": 0.0001589330578234713, "loss": 0.6252408504486084, "step": 194470 }, { "epoch": 1.1560295070468583, "grad_norm": 1.6753227710723877, "learning_rate": 0.0001589278333868999, "loss": 0.6264259815216064, "step": 194480 }, { "epoch": 1.1560889491235267, "grad_norm": 1.2575170993804932, "learning_rate": 0.00015892260871627376, "loss": 0.6320965766906739, "step": 194490 }, { "epoch": 1.1561483912001949, "grad_norm": 1.4272807836532593, "learning_rate": 0.00015891738381161783, "loss": 0.6068301200866699, "step": 194500 }, { "epoch": 1.1562078332768633, "grad_norm": 2.0291359424591064, "learning_rate": 0.0001589121586729571, "loss": 0.6511703491210937, "step": 194510 }, { "epoch": 1.1562672753535317, "grad_norm": 1.561774492263794, "learning_rate": 0.00015890693330031667, "loss": 0.5769538402557373, "step": 194520 }, { "epoch": 1.1563267174302, "grad_norm": 1.4416375160217285, "learning_rate": 0.00015890170769372142, "loss": 0.6453682899475097, "step": 194530 }, { "epoch": 1.1563861595068685, "grad_norm": 1.3168604373931885, "learning_rate": 0.00015889648185319635, "loss": 0.5806843757629394, "step": 194540 }, { "epoch": 1.156445601583537, "grad_norm": 1.8814467191696167, "learning_rate": 0.00015889125577876653, "loss": 0.6826337814331055, "step": 194550 }, { "epoch": 1.1565050436602053, "grad_norm": 1.6871424913406372, "learning_rate": 0.00015888602947045687, "loss": 0.6497987747192383, "step": 194560 }, { "epoch": 1.1565644857368738, "grad_norm": 1.2878456115722656, "learning_rate": 0.00015888080292829245, "loss": 0.6560859680175781, "step": 194570 }, { "epoch": 1.1566239278135422, "grad_norm": 1.4749999046325684, "learning_rate": 0.00015887557615229823, "loss": 0.641786766052246, "step": 194580 }, { "epoch": 1.1566833698902106, "grad_norm": 1.4175235033035278, "learning_rate": 0.00015887034914249926, "loss": 0.6062422752380371, "step": 194590 }, { "epoch": 1.1567428119668788, "grad_norm": 1.458551049232483, "learning_rate": 0.00015886512189892051, "loss": 0.6489679336547851, "step": 194600 }, { "epoch": 1.1568022540435472, "grad_norm": 1.986330270767212, "learning_rate": 0.00015885989442158694, "loss": 0.6828634738922119, "step": 194610 }, { "epoch": 1.1568616961202156, "grad_norm": 1.168799638748169, "learning_rate": 0.00015885466671052362, "loss": 0.597203540802002, "step": 194620 }, { "epoch": 1.156921138196884, "grad_norm": 1.586620569229126, "learning_rate": 0.00015884943876575558, "loss": 0.6006495475769043, "step": 194630 }, { "epoch": 1.1569805802735524, "grad_norm": 1.4917153120040894, "learning_rate": 0.00015884421058730774, "loss": 0.6023788452148438, "step": 194640 }, { "epoch": 1.1570400223502209, "grad_norm": 1.5681108236312866, "learning_rate": 0.0001588389821752052, "loss": 0.6335386753082275, "step": 194650 }, { "epoch": 1.1570994644268893, "grad_norm": 1.5017683506011963, "learning_rate": 0.00015883375352947288, "loss": 0.6413635730743408, "step": 194660 }, { "epoch": 1.1571589065035577, "grad_norm": 1.6220446825027466, "learning_rate": 0.00015882852465013588, "loss": 0.6261675834655762, "step": 194670 }, { "epoch": 1.1572183485802259, "grad_norm": 1.567022442817688, "learning_rate": 0.00015882329553721918, "loss": 0.6178683757781982, "step": 194680 }, { "epoch": 1.1572777906568943, "grad_norm": 1.831495761871338, "learning_rate": 0.00015881806619074778, "loss": 0.6573113918304443, "step": 194690 }, { "epoch": 1.1573372327335627, "grad_norm": 1.7295950651168823, "learning_rate": 0.00015881283661074667, "loss": 0.6271199226379395, "step": 194700 }, { "epoch": 1.1573966748102311, "grad_norm": 1.5876212120056152, "learning_rate": 0.00015880760679724094, "loss": 0.6516968250274658, "step": 194710 }, { "epoch": 1.1574561168868995, "grad_norm": 1.298194408416748, "learning_rate": 0.00015880237675025557, "loss": 0.6459805488586425, "step": 194720 }, { "epoch": 1.157515558963568, "grad_norm": 1.5574030876159668, "learning_rate": 0.0001587971464698156, "loss": 0.5964350700378418, "step": 194730 }, { "epoch": 1.1575750010402364, "grad_norm": 1.6736716032028198, "learning_rate": 0.00015879191595594597, "loss": 0.6056180000305176, "step": 194740 }, { "epoch": 1.1576344431169048, "grad_norm": 1.9506813287734985, "learning_rate": 0.00015878668520867177, "loss": 0.6449822902679443, "step": 194750 }, { "epoch": 1.1576938851935732, "grad_norm": 1.5721919536590576, "learning_rate": 0.00015878145422801806, "loss": 0.5867138862609863, "step": 194760 }, { "epoch": 1.1577533272702416, "grad_norm": 1.5260065793991089, "learning_rate": 0.00015877622301400975, "loss": 0.606725025177002, "step": 194770 }, { "epoch": 1.15781276934691, "grad_norm": 1.4005751609802246, "learning_rate": 0.00015877099156667198, "loss": 0.5841829776763916, "step": 194780 }, { "epoch": 1.1578722114235782, "grad_norm": 1.6574766635894775, "learning_rate": 0.0001587657598860297, "loss": 0.5730932235717774, "step": 194790 }, { "epoch": 1.1579316535002466, "grad_norm": 1.3570964336395264, "learning_rate": 0.00015876052797210796, "loss": 0.5775679111480713, "step": 194800 }, { "epoch": 1.157991095576915, "grad_norm": 1.5426212549209595, "learning_rate": 0.00015875529582493183, "loss": 0.55630464553833, "step": 194810 }, { "epoch": 1.1580505376535835, "grad_norm": 1.6579347848892212, "learning_rate": 0.00015875006344452625, "loss": 0.6179821491241455, "step": 194820 }, { "epoch": 1.1581099797302519, "grad_norm": 1.728385090827942, "learning_rate": 0.00015874483083091632, "loss": 0.5784380912780762, "step": 194830 }, { "epoch": 1.1581694218069203, "grad_norm": 1.7268998622894287, "learning_rate": 0.00015873959798412706, "loss": 0.6360766410827636, "step": 194840 }, { "epoch": 1.1582288638835887, "grad_norm": 1.9778454303741455, "learning_rate": 0.00015873436490418345, "loss": 0.6229746818542481, "step": 194850 }, { "epoch": 1.1582883059602571, "grad_norm": 1.4943348169326782, "learning_rate": 0.00015872913159111063, "loss": 0.6757055282592773, "step": 194860 }, { "epoch": 1.1583477480369253, "grad_norm": 1.5794603824615479, "learning_rate": 0.0001587238980449335, "loss": 0.598116111755371, "step": 194870 }, { "epoch": 1.1584071901135937, "grad_norm": 1.6277987957000732, "learning_rate": 0.0001587186642656772, "loss": 0.6503064155578613, "step": 194880 }, { "epoch": 1.1584666321902621, "grad_norm": 1.660681962966919, "learning_rate": 0.00015871343025336673, "loss": 0.6307361602783204, "step": 194890 }, { "epoch": 1.1585260742669306, "grad_norm": 1.827327013015747, "learning_rate": 0.00015870819600802714, "loss": 0.644862174987793, "step": 194900 }, { "epoch": 1.158585516343599, "grad_norm": 1.3851574659347534, "learning_rate": 0.00015870296152968342, "loss": 0.5699596881866456, "step": 194910 }, { "epoch": 1.1586449584202674, "grad_norm": 1.3357445001602173, "learning_rate": 0.0001586977268183607, "loss": 0.6193777084350586, "step": 194920 }, { "epoch": 1.1587044004969358, "grad_norm": 1.7463802099227905, "learning_rate": 0.00015869249187408393, "loss": 0.5697173118591309, "step": 194930 }, { "epoch": 1.1587638425736042, "grad_norm": 1.4298481941223145, "learning_rate": 0.0001586872566968782, "loss": 0.6309446334838867, "step": 194940 }, { "epoch": 1.1588232846502726, "grad_norm": 1.2498023509979248, "learning_rate": 0.00015868202128676854, "loss": 0.5879153728485107, "step": 194950 }, { "epoch": 1.158882726726941, "grad_norm": 1.3569597005844116, "learning_rate": 0.00015867678564378002, "loss": 0.6011832237243653, "step": 194960 }, { "epoch": 1.1589421688036092, "grad_norm": 1.2293126583099365, "learning_rate": 0.00015867154976793765, "loss": 0.6336463928222656, "step": 194970 }, { "epoch": 1.1590016108802776, "grad_norm": 1.3918204307556152, "learning_rate": 0.0001586663136592665, "loss": 0.6255347251892089, "step": 194980 }, { "epoch": 1.159061052956946, "grad_norm": 1.2533210515975952, "learning_rate": 0.00015866107731779162, "loss": 0.5919878005981445, "step": 194990 }, { "epoch": 1.1591204950336145, "grad_norm": 1.3457069396972656, "learning_rate": 0.00015865584074353803, "loss": 0.6156910419464111, "step": 195000 }, { "epoch": 1.1591799371102829, "grad_norm": 1.5496011972427368, "learning_rate": 0.00015865060393653078, "loss": 0.6273031234741211, "step": 195010 }, { "epoch": 1.1592393791869513, "grad_norm": 1.5134360790252686, "learning_rate": 0.000158645366896795, "loss": 0.6179720878601074, "step": 195020 }, { "epoch": 1.1592988212636197, "grad_norm": 1.4489378929138184, "learning_rate": 0.00015864012962435564, "loss": 0.6253596305847168, "step": 195030 }, { "epoch": 1.1593582633402881, "grad_norm": 1.5953161716461182, "learning_rate": 0.00015863489211923778, "loss": 0.6314165592193604, "step": 195040 }, { "epoch": 1.1594177054169563, "grad_norm": 2.0424695014953613, "learning_rate": 0.00015862965438146652, "loss": 0.6235452175140381, "step": 195050 }, { "epoch": 1.1594771474936247, "grad_norm": 1.8276948928833008, "learning_rate": 0.0001586244164110669, "loss": 0.6688365936279297, "step": 195060 }, { "epoch": 1.1595365895702932, "grad_norm": 1.7984707355499268, "learning_rate": 0.0001586191782080639, "loss": 0.6197562217712402, "step": 195070 }, { "epoch": 1.1595960316469616, "grad_norm": 1.5598889589309692, "learning_rate": 0.0001586139397724827, "loss": 0.564774465560913, "step": 195080 }, { "epoch": 1.15965547372363, "grad_norm": 1.6450132131576538, "learning_rate": 0.0001586087011043483, "loss": 0.6105998992919922, "step": 195090 }, { "epoch": 1.1597149158002984, "grad_norm": 1.48801851272583, "learning_rate": 0.00015860346220368572, "loss": 0.5885247230529785, "step": 195100 }, { "epoch": 1.1597743578769668, "grad_norm": 1.684355616569519, "learning_rate": 0.0001585982230705201, "loss": 0.648242712020874, "step": 195110 }, { "epoch": 1.1598337999536352, "grad_norm": 1.2521450519561768, "learning_rate": 0.00015859298370487644, "loss": 0.5737017631530762, "step": 195120 }, { "epoch": 1.1598932420303036, "grad_norm": 1.6964459419250488, "learning_rate": 0.0001585877441067798, "loss": 0.6493474006652832, "step": 195130 }, { "epoch": 1.159952684106972, "grad_norm": 1.3024859428405762, "learning_rate": 0.00015858250427625532, "loss": 0.6749755382537842, "step": 195140 }, { "epoch": 1.1600121261836405, "grad_norm": 1.7667306661605835, "learning_rate": 0.000158577264213328, "loss": 0.5785866737365722, "step": 195150 }, { "epoch": 1.1600715682603087, "grad_norm": 1.6155234575271606, "learning_rate": 0.00015857202391802292, "loss": 0.6347865104675293, "step": 195160 }, { "epoch": 1.160131010336977, "grad_norm": 1.317128300666809, "learning_rate": 0.00015856678339036515, "loss": 0.6360498905181885, "step": 195170 }, { "epoch": 1.1601904524136455, "grad_norm": 1.5442057847976685, "learning_rate": 0.00015856154263037977, "loss": 0.6668338298797607, "step": 195180 }, { "epoch": 1.160249894490314, "grad_norm": 1.8656275272369385, "learning_rate": 0.00015855630163809183, "loss": 0.6175792694091797, "step": 195190 }, { "epoch": 1.1603093365669823, "grad_norm": 1.6614633798599243, "learning_rate": 0.0001585510604135264, "loss": 0.6792124748229981, "step": 195200 }, { "epoch": 1.1603687786436507, "grad_norm": 1.464785099029541, "learning_rate": 0.00015854581895670858, "loss": 0.5814234256744385, "step": 195210 }, { "epoch": 1.1604282207203191, "grad_norm": 1.744295358657837, "learning_rate": 0.00015854057726766342, "loss": 0.5986444473266601, "step": 195220 }, { "epoch": 1.1604876627969876, "grad_norm": 1.4885308742523193, "learning_rate": 0.000158535335346416, "loss": 0.6098753929138183, "step": 195230 }, { "epoch": 1.1605471048736558, "grad_norm": 1.8940850496292114, "learning_rate": 0.00015853009319299143, "loss": 0.5729989051818848, "step": 195240 }, { "epoch": 1.1606065469503242, "grad_norm": 1.8287038803100586, "learning_rate": 0.0001585248508074147, "loss": 0.5976521492004394, "step": 195250 }, { "epoch": 1.1606659890269926, "grad_norm": 1.955785870552063, "learning_rate": 0.00015851960818971095, "loss": 0.6443812370300293, "step": 195260 }, { "epoch": 1.160725431103661, "grad_norm": 1.852453351020813, "learning_rate": 0.00015851436533990528, "loss": 0.5711431503295898, "step": 195270 }, { "epoch": 1.1607848731803294, "grad_norm": 1.4278159141540527, "learning_rate": 0.00015850912225802275, "loss": 0.5899857521057129, "step": 195280 }, { "epoch": 1.1608443152569978, "grad_norm": 1.190840482711792, "learning_rate": 0.00015850387894408838, "loss": 0.6497928619384765, "step": 195290 }, { "epoch": 1.1609037573336662, "grad_norm": 1.3536629676818848, "learning_rate": 0.00015849863539812737, "loss": 0.5468610763549805, "step": 195300 }, { "epoch": 1.1609631994103347, "grad_norm": 1.4916245937347412, "learning_rate": 0.00015849339162016468, "loss": 0.6315202713012695, "step": 195310 }, { "epoch": 1.161022641487003, "grad_norm": 1.3373346328735352, "learning_rate": 0.00015848814761022548, "loss": 0.6261318683624267, "step": 195320 }, { "epoch": 1.1610820835636715, "grad_norm": 1.9746848344802856, "learning_rate": 0.00015848290336833485, "loss": 0.6577095031738281, "step": 195330 }, { "epoch": 1.1611415256403397, "grad_norm": 1.605549931526184, "learning_rate": 0.0001584776588945178, "loss": 0.6684056282043457, "step": 195340 }, { "epoch": 1.161200967717008, "grad_norm": 1.663954496383667, "learning_rate": 0.0001584724141887995, "loss": 0.6159928321838379, "step": 195350 }, { "epoch": 1.1612604097936765, "grad_norm": 2.058131217956543, "learning_rate": 0.00015846716925120504, "loss": 0.5936505794525146, "step": 195360 }, { "epoch": 1.161319851870345, "grad_norm": 1.4648040533065796, "learning_rate": 0.00015846192408175945, "loss": 0.5518481254577636, "step": 195370 }, { "epoch": 1.1613792939470133, "grad_norm": 1.6843684911727905, "learning_rate": 0.00015845667868048783, "loss": 0.6461204528808594, "step": 195380 }, { "epoch": 1.1614387360236818, "grad_norm": 1.5647220611572266, "learning_rate": 0.00015845143304741536, "loss": 0.6325136184692383, "step": 195390 }, { "epoch": 1.1614981781003502, "grad_norm": 2.138455629348755, "learning_rate": 0.00015844618718256702, "loss": 0.6520895957946777, "step": 195400 }, { "epoch": 1.1615576201770186, "grad_norm": 1.273193359375, "learning_rate": 0.00015844094108596798, "loss": 0.651900339126587, "step": 195410 }, { "epoch": 1.1616170622536868, "grad_norm": 1.935632348060608, "learning_rate": 0.00015843569475764327, "loss": 0.6007324695587158, "step": 195420 }, { "epoch": 1.1616765043303552, "grad_norm": 1.6466645002365112, "learning_rate": 0.00015843044819761803, "loss": 0.6365514755249023, "step": 195430 }, { "epoch": 1.1617359464070236, "grad_norm": 1.7262481451034546, "learning_rate": 0.00015842520140591738, "loss": 0.6650898933410645, "step": 195440 }, { "epoch": 1.161795388483692, "grad_norm": 1.9605846405029297, "learning_rate": 0.00015841995438256641, "loss": 0.6328406810760498, "step": 195450 }, { "epoch": 1.1618548305603604, "grad_norm": 1.4613523483276367, "learning_rate": 0.00015841470712759016, "loss": 0.6047715187072754, "step": 195460 }, { "epoch": 1.1619142726370288, "grad_norm": 2.347766160964966, "learning_rate": 0.00015840945964101376, "loss": 0.6411322593688965, "step": 195470 }, { "epoch": 1.1619737147136973, "grad_norm": 1.4464231729507446, "learning_rate": 0.00015840421192286238, "loss": 0.597322940826416, "step": 195480 }, { "epoch": 1.1620331567903657, "grad_norm": 1.4116685390472412, "learning_rate": 0.00015839896397316103, "loss": 0.6643033504486084, "step": 195490 }, { "epoch": 1.162092598867034, "grad_norm": 1.421947717666626, "learning_rate": 0.00015839371579193487, "loss": 0.5920894622802735, "step": 195500 }, { "epoch": 1.1621520409437025, "grad_norm": 1.7970095872879028, "learning_rate": 0.000158388467379209, "loss": 0.5861023902893067, "step": 195510 }, { "epoch": 1.162211483020371, "grad_norm": 2.035372495651245, "learning_rate": 0.0001583832187350085, "loss": 0.6765936374664306, "step": 195520 }, { "epoch": 1.162270925097039, "grad_norm": 1.583795189857483, "learning_rate": 0.00015837796985935848, "loss": 0.659486961364746, "step": 195530 }, { "epoch": 1.1623303671737075, "grad_norm": 1.5406079292297363, "learning_rate": 0.00015837272075228408, "loss": 0.6322928905487061, "step": 195540 }, { "epoch": 1.162389809250376, "grad_norm": 1.72074556350708, "learning_rate": 0.00015836747141381038, "loss": 0.5479048252105713, "step": 195550 }, { "epoch": 1.1624492513270444, "grad_norm": 1.620823860168457, "learning_rate": 0.0001583622218439625, "loss": 0.588555908203125, "step": 195560 }, { "epoch": 1.1625086934037128, "grad_norm": 1.4735350608825684, "learning_rate": 0.00015835697204276557, "loss": 0.6159669876098632, "step": 195570 }, { "epoch": 1.1625681354803812, "grad_norm": 1.4453191757202148, "learning_rate": 0.00015835172201024468, "loss": 0.6603297233581543, "step": 195580 }, { "epoch": 1.1626275775570496, "grad_norm": 1.8291327953338623, "learning_rate": 0.00015834647174642496, "loss": 0.620175838470459, "step": 195590 }, { "epoch": 1.162687019633718, "grad_norm": 1.7808624505996704, "learning_rate": 0.00015834122125133154, "loss": 0.6164676189422608, "step": 195600 }, { "epoch": 1.1627464617103862, "grad_norm": 1.3867024183273315, "learning_rate": 0.00015833597052498948, "loss": 0.629241943359375, "step": 195610 }, { "epoch": 1.1628059037870546, "grad_norm": 1.4600948095321655, "learning_rate": 0.00015833071956742394, "loss": 0.5676780700683594, "step": 195620 }, { "epoch": 1.162865345863723, "grad_norm": 1.6675595045089722, "learning_rate": 0.00015832546837866003, "loss": 0.6854966163635254, "step": 195630 }, { "epoch": 1.1629247879403914, "grad_norm": 1.467199444770813, "learning_rate": 0.0001583202169587229, "loss": 0.6217508316040039, "step": 195640 }, { "epoch": 1.1629842300170599, "grad_norm": 1.4205979108810425, "learning_rate": 0.00015831496530763762, "loss": 0.6301451683044433, "step": 195650 }, { "epoch": 1.1630436720937283, "grad_norm": 1.5864813327789307, "learning_rate": 0.00015830971342542936, "loss": 0.6623313903808594, "step": 195660 }, { "epoch": 1.1631031141703967, "grad_norm": 1.2848072052001953, "learning_rate": 0.00015830446131212317, "loss": 0.6174347877502442, "step": 195670 }, { "epoch": 1.163162556247065, "grad_norm": 1.312738299369812, "learning_rate": 0.00015829920896774427, "loss": 0.6150199413299561, "step": 195680 }, { "epoch": 1.1632219983237335, "grad_norm": 1.3818389177322388, "learning_rate": 0.0001582939563923177, "loss": 0.6512533187866211, "step": 195690 }, { "epoch": 1.163281440400402, "grad_norm": 1.4117130041122437, "learning_rate": 0.00015828870358586866, "loss": 0.592390775680542, "step": 195700 }, { "epoch": 1.1633408824770701, "grad_norm": 1.466858983039856, "learning_rate": 0.00015828345054842222, "loss": 0.6541823387145996, "step": 195710 }, { "epoch": 1.1634003245537385, "grad_norm": 1.7607684135437012, "learning_rate": 0.00015827819728000354, "loss": 0.5113964080810547, "step": 195720 }, { "epoch": 1.163459766630407, "grad_norm": 1.8194193840026855, "learning_rate": 0.00015827294378063778, "loss": 0.6113358497619629, "step": 195730 }, { "epoch": 1.1635192087070754, "grad_norm": 2.133423328399658, "learning_rate": 0.00015826769005034997, "loss": 0.6193079948425293, "step": 195740 }, { "epoch": 1.1635786507837438, "grad_norm": 1.6307555437088013, "learning_rate": 0.00015826243608916535, "loss": 0.6732163429260254, "step": 195750 }, { "epoch": 1.1636380928604122, "grad_norm": 1.864193320274353, "learning_rate": 0.00015825718189710897, "loss": 0.5740512847900391, "step": 195760 }, { "epoch": 1.1636975349370806, "grad_norm": 1.8542944192886353, "learning_rate": 0.000158251927474206, "loss": 0.5874312400817872, "step": 195770 }, { "epoch": 1.163756977013749, "grad_norm": 1.4577895402908325, "learning_rate": 0.00015824667282048164, "loss": 0.6262103080749511, "step": 195780 }, { "epoch": 1.1638164190904172, "grad_norm": 1.829393744468689, "learning_rate": 0.0001582414179359609, "loss": 0.6564406871795654, "step": 195790 }, { "epoch": 1.1638758611670856, "grad_norm": 1.6909178495407104, "learning_rate": 0.00015823616282066902, "loss": 0.6453989982604981, "step": 195800 }, { "epoch": 1.163935303243754, "grad_norm": 1.404083013534546, "learning_rate": 0.00015823090747463107, "loss": 0.5696221351623535, "step": 195810 }, { "epoch": 1.1639947453204225, "grad_norm": 1.4489059448242188, "learning_rate": 0.00015822565189787223, "loss": 0.5812067031860352, "step": 195820 }, { "epoch": 1.1640541873970909, "grad_norm": 1.4183142185211182, "learning_rate": 0.00015822039609041764, "loss": 0.6651390075683594, "step": 195830 }, { "epoch": 1.1641136294737593, "grad_norm": 1.1604492664337158, "learning_rate": 0.00015821514005229245, "loss": 0.6605443954467773, "step": 195840 }, { "epoch": 1.1641730715504277, "grad_norm": 1.679162621498108, "learning_rate": 0.00015820988378352176, "loss": 0.6055683135986328, "step": 195850 }, { "epoch": 1.1642325136270961, "grad_norm": 1.7885531187057495, "learning_rate": 0.00015820462728413076, "loss": 0.6523643016815186, "step": 195860 }, { "epoch": 1.1642919557037645, "grad_norm": 1.8530149459838867, "learning_rate": 0.00015819937055414456, "loss": 0.6411112785339356, "step": 195870 }, { "epoch": 1.164351397780433, "grad_norm": 1.6754631996154785, "learning_rate": 0.00015819411359358832, "loss": 0.6422624588012695, "step": 195880 }, { "epoch": 1.1644108398571014, "grad_norm": 1.6116026639938354, "learning_rate": 0.0001581888564024872, "loss": 0.6416876316070557, "step": 195890 }, { "epoch": 1.1644702819337696, "grad_norm": 1.6993664503097534, "learning_rate": 0.00015818359898086634, "loss": 0.613179874420166, "step": 195900 }, { "epoch": 1.164529724010438, "grad_norm": 1.6287868022918701, "learning_rate": 0.00015817834132875088, "loss": 0.6330669403076172, "step": 195910 }, { "epoch": 1.1645891660871064, "grad_norm": 1.6675398349761963, "learning_rate": 0.000158173083446166, "loss": 0.6347992420196533, "step": 195920 }, { "epoch": 1.1646486081637748, "grad_norm": 1.3385294675827026, "learning_rate": 0.0001581678253331368, "loss": 0.6164697647094727, "step": 195930 }, { "epoch": 1.1647080502404432, "grad_norm": 1.5824369192123413, "learning_rate": 0.0001581625669896885, "loss": 0.5658995628356933, "step": 195940 }, { "epoch": 1.1647674923171116, "grad_norm": 1.2691068649291992, "learning_rate": 0.00015815730841584622, "loss": 0.5783174514770508, "step": 195950 }, { "epoch": 1.16482693439378, "grad_norm": 1.6902223825454712, "learning_rate": 0.00015815204961163509, "loss": 0.6651263236999512, "step": 195960 }, { "epoch": 1.1648863764704485, "grad_norm": 1.6118690967559814, "learning_rate": 0.0001581467905770803, "loss": 0.6361287593841553, "step": 195970 }, { "epoch": 1.1649458185471167, "grad_norm": 1.4008655548095703, "learning_rate": 0.000158141531312207, "loss": 0.5733226776123047, "step": 195980 }, { "epoch": 1.165005260623785, "grad_norm": 1.392019271850586, "learning_rate": 0.00015813627181704033, "loss": 0.5504944324493408, "step": 195990 }, { "epoch": 1.1650647027004535, "grad_norm": 1.661914587020874, "learning_rate": 0.0001581310120916055, "loss": 0.5551072120666504, "step": 196000 }, { "epoch": 1.165124144777122, "grad_norm": 1.5040620565414429, "learning_rate": 0.0001581257521359276, "loss": 0.5479031562805176, "step": 196010 }, { "epoch": 1.1651835868537903, "grad_norm": 1.6491246223449707, "learning_rate": 0.00015812049195003186, "loss": 0.629457950592041, "step": 196020 }, { "epoch": 1.1652430289304587, "grad_norm": 1.664251685142517, "learning_rate": 0.0001581152315339434, "loss": 0.5883830070495606, "step": 196030 }, { "epoch": 1.1653024710071271, "grad_norm": 1.5650904178619385, "learning_rate": 0.00015810997088768738, "loss": 0.573291826248169, "step": 196040 }, { "epoch": 1.1653619130837956, "grad_norm": 1.4667888879776, "learning_rate": 0.00015810471001128902, "loss": 0.6291584014892578, "step": 196050 }, { "epoch": 1.165421355160464, "grad_norm": 1.6782984733581543, "learning_rate": 0.00015809944890477344, "loss": 0.6562094688415527, "step": 196060 }, { "epoch": 1.1654807972371324, "grad_norm": 1.7855147123336792, "learning_rate": 0.00015809418756816581, "loss": 0.5919283866882324, "step": 196070 }, { "epoch": 1.1655402393138006, "grad_norm": 1.5009030103683472, "learning_rate": 0.00015808892600149127, "loss": 0.5688457489013672, "step": 196080 }, { "epoch": 1.165599681390469, "grad_norm": 1.4270672798156738, "learning_rate": 0.00015808366420477505, "loss": 0.5657275199890137, "step": 196090 }, { "epoch": 1.1656591234671374, "grad_norm": 1.3404279947280884, "learning_rate": 0.0001580784021780423, "loss": 0.5462994575500488, "step": 196100 }, { "epoch": 1.1657185655438058, "grad_norm": 1.7085903882980347, "learning_rate": 0.00015807313992131816, "loss": 0.6404105186462402, "step": 196110 }, { "epoch": 1.1657780076204742, "grad_norm": 1.6870701313018799, "learning_rate": 0.00015806787743462787, "loss": 0.6493509769439697, "step": 196120 }, { "epoch": 1.1658374496971426, "grad_norm": 1.9223220348358154, "learning_rate": 0.00015806261471799655, "loss": 0.6264351844787598, "step": 196130 }, { "epoch": 1.165896891773811, "grad_norm": 1.5304418802261353, "learning_rate": 0.0001580573517714494, "loss": 0.6343605041503906, "step": 196140 }, { "epoch": 1.1659563338504795, "grad_norm": 1.5285744667053223, "learning_rate": 0.00015805208859501156, "loss": 0.6081987380981445, "step": 196150 }, { "epoch": 1.1660157759271477, "grad_norm": 1.4821093082427979, "learning_rate": 0.0001580468251887082, "loss": 0.6833498477935791, "step": 196160 }, { "epoch": 1.166075218003816, "grad_norm": 1.5256742238998413, "learning_rate": 0.0001580415615525646, "loss": 0.624992561340332, "step": 196170 }, { "epoch": 1.1661346600804845, "grad_norm": 1.3456370830535889, "learning_rate": 0.00015803629768660585, "loss": 0.5427407264709473, "step": 196180 }, { "epoch": 1.166194102157153, "grad_norm": 1.2666062116622925, "learning_rate": 0.00015803103359085714, "loss": 0.6838794708251953, "step": 196190 }, { "epoch": 1.1662535442338213, "grad_norm": 1.9187253713607788, "learning_rate": 0.00015802576926534365, "loss": 0.5990084171295166, "step": 196200 }, { "epoch": 1.1663129863104897, "grad_norm": 1.6368619203567505, "learning_rate": 0.00015802050471009057, "loss": 0.6196938514709472, "step": 196210 }, { "epoch": 1.1663724283871582, "grad_norm": 1.583014965057373, "learning_rate": 0.00015801523992512313, "loss": 0.6458722114562988, "step": 196220 }, { "epoch": 1.1664318704638266, "grad_norm": 1.4063488245010376, "learning_rate": 0.00015800997491046643, "loss": 0.625719690322876, "step": 196230 }, { "epoch": 1.166491312540495, "grad_norm": 1.3631972074508667, "learning_rate": 0.0001580047096661457, "loss": 0.6028262138366699, "step": 196240 }, { "epoch": 1.1665507546171634, "grad_norm": 1.309545636177063, "learning_rate": 0.00015799944419218618, "loss": 0.6752788543701171, "step": 196250 }, { "epoch": 1.1666101966938318, "grad_norm": 1.8262799978256226, "learning_rate": 0.00015799417848861297, "loss": 0.5675213813781739, "step": 196260 }, { "epoch": 1.1666696387705, "grad_norm": 1.8583627939224243, "learning_rate": 0.00015798891255545125, "loss": 0.6578303337097168, "step": 196270 }, { "epoch": 1.1667290808471684, "grad_norm": 1.5940593481063843, "learning_rate": 0.00015798364639272637, "loss": 0.6597351551055908, "step": 196280 }, { "epoch": 1.1667885229238368, "grad_norm": 1.2370425462722778, "learning_rate": 0.00015797838000046328, "loss": 0.5993952751159668, "step": 196290 }, { "epoch": 1.1668479650005052, "grad_norm": 1.121679663658142, "learning_rate": 0.00015797311337868738, "loss": 0.6035465240478516, "step": 196300 }, { "epoch": 1.1669074070771737, "grad_norm": 1.890861988067627, "learning_rate": 0.00015796784652742375, "loss": 0.5732227802276612, "step": 196310 }, { "epoch": 1.166966849153842, "grad_norm": 1.3853175640106201, "learning_rate": 0.00015796257944669762, "loss": 0.6279279708862304, "step": 196320 }, { "epoch": 1.1670262912305105, "grad_norm": 1.6511743068695068, "learning_rate": 0.00015795731213653422, "loss": 0.6092007637023926, "step": 196330 }, { "epoch": 1.167085733307179, "grad_norm": 1.7758837938308716, "learning_rate": 0.00015795204459695866, "loss": 0.6350543022155761, "step": 196340 }, { "epoch": 1.167145175383847, "grad_norm": 1.6524933576583862, "learning_rate": 0.00015794677682799623, "loss": 0.6012584686279296, "step": 196350 }, { "epoch": 1.1672046174605155, "grad_norm": 1.623611569404602, "learning_rate": 0.00015794150882967204, "loss": 0.6085726261138916, "step": 196360 }, { "epoch": 1.167264059537184, "grad_norm": 1.6169134378433228, "learning_rate": 0.0001579362406020114, "loss": 0.6065803050994873, "step": 196370 }, { "epoch": 1.1673235016138523, "grad_norm": 1.3342866897583008, "learning_rate": 0.00015793097214503944, "loss": 0.6136926651000977, "step": 196380 }, { "epoch": 1.1673829436905208, "grad_norm": 1.5708186626434326, "learning_rate": 0.00015792570345878133, "loss": 0.6068242073059082, "step": 196390 }, { "epoch": 1.1674423857671892, "grad_norm": 1.7614485025405884, "learning_rate": 0.00015792043454326235, "loss": 0.5846556663513184, "step": 196400 }, { "epoch": 1.1675018278438576, "grad_norm": 1.7831529378890991, "learning_rate": 0.00015791516539850767, "loss": 0.6085206508636475, "step": 196410 }, { "epoch": 1.167561269920526, "grad_norm": 1.5343477725982666, "learning_rate": 0.00015790989602454248, "loss": 0.5543922901153564, "step": 196420 }, { "epoch": 1.1676207119971944, "grad_norm": 1.6677910089492798, "learning_rate": 0.000157904626421392, "loss": 0.6260902404785156, "step": 196430 }, { "epoch": 1.1676801540738628, "grad_norm": 1.756844162940979, "learning_rate": 0.00015789935658908148, "loss": 0.5717452526092529, "step": 196440 }, { "epoch": 1.167739596150531, "grad_norm": 1.568442940711975, "learning_rate": 0.00015789408652763605, "loss": 0.6671613693237305, "step": 196450 }, { "epoch": 1.1677990382271994, "grad_norm": 1.3690108060836792, "learning_rate": 0.00015788881623708098, "loss": 0.6033309936523438, "step": 196460 }, { "epoch": 1.1678584803038679, "grad_norm": 1.4788089990615845, "learning_rate": 0.00015788354571744147, "loss": 0.6121562004089356, "step": 196470 }, { "epoch": 1.1679179223805363, "grad_norm": 1.2486293315887451, "learning_rate": 0.00015787827496874273, "loss": 0.63898606300354, "step": 196480 }, { "epoch": 1.1679773644572047, "grad_norm": 1.2914223670959473, "learning_rate": 0.00015787300399100997, "loss": 0.5859305381774902, "step": 196490 }, { "epoch": 1.168036806533873, "grad_norm": 1.4626080989837646, "learning_rate": 0.0001578677327842684, "loss": 0.5958873271942139, "step": 196500 }, { "epoch": 1.1680962486105415, "grad_norm": 1.32371187210083, "learning_rate": 0.0001578624613485432, "loss": 0.6331168651580811, "step": 196510 }, { "epoch": 1.16815569068721, "grad_norm": 1.5856863260269165, "learning_rate": 0.00015785718968385967, "loss": 0.6429636955261231, "step": 196520 }, { "epoch": 1.1682151327638781, "grad_norm": 1.523479700088501, "learning_rate": 0.000157851917790243, "loss": 0.638408088684082, "step": 196530 }, { "epoch": 1.1682745748405465, "grad_norm": 1.1635677814483643, "learning_rate": 0.00015784664566771835, "loss": 0.5748216152191162, "step": 196540 }, { "epoch": 1.168334016917215, "grad_norm": 1.9468268156051636, "learning_rate": 0.000157841373316311, "loss": 0.6086039066314697, "step": 196550 }, { "epoch": 1.1683934589938834, "grad_norm": 1.5479809045791626, "learning_rate": 0.00015783610073604617, "loss": 0.6803906917572021, "step": 196560 }, { "epoch": 1.1684529010705518, "grad_norm": 2.071223497390747, "learning_rate": 0.00015783082792694906, "loss": 0.6815845489501953, "step": 196570 }, { "epoch": 1.1685123431472202, "grad_norm": 1.6511892080307007, "learning_rate": 0.0001578255548890449, "loss": 0.6655079841613769, "step": 196580 }, { "epoch": 1.1685717852238886, "grad_norm": 1.603883981704712, "learning_rate": 0.0001578202816223589, "loss": 0.6353338241577149, "step": 196590 }, { "epoch": 1.168631227300557, "grad_norm": 1.567494511604309, "learning_rate": 0.00015781500812691633, "loss": 0.583331823348999, "step": 196600 }, { "epoch": 1.1686906693772254, "grad_norm": 1.4150336980819702, "learning_rate": 0.00015780973440274236, "loss": 0.6082719326019287, "step": 196610 }, { "epoch": 1.1687501114538938, "grad_norm": 1.610379695892334, "learning_rate": 0.00015780446044986226, "loss": 0.6512075424194336, "step": 196620 }, { "epoch": 1.1688095535305623, "grad_norm": 1.5553138256072998, "learning_rate": 0.0001577991862683012, "loss": 0.6232211589813232, "step": 196630 }, { "epoch": 1.1688689956072305, "grad_norm": 1.7293246984481812, "learning_rate": 0.00015779391185808452, "loss": 0.6466385841369628, "step": 196640 }, { "epoch": 1.1689284376838989, "grad_norm": 1.6192251443862915, "learning_rate": 0.00015778863721923732, "loss": 0.5694644451141357, "step": 196650 }, { "epoch": 1.1689878797605673, "grad_norm": 1.8223495483398438, "learning_rate": 0.00015778336235178496, "loss": 0.614031457901001, "step": 196660 }, { "epoch": 1.1690473218372357, "grad_norm": 1.4538519382476807, "learning_rate": 0.00015777808725575258, "loss": 0.5559223651885986, "step": 196670 }, { "epoch": 1.1691067639139041, "grad_norm": 1.6241577863693237, "learning_rate": 0.00015777281193116546, "loss": 0.5477818012237549, "step": 196680 }, { "epoch": 1.1691662059905725, "grad_norm": 1.7750229835510254, "learning_rate": 0.00015776753637804878, "loss": 0.6381693840026855, "step": 196690 }, { "epoch": 1.169225648067241, "grad_norm": 1.7893754243850708, "learning_rate": 0.00015776226059642786, "loss": 0.5936030864715576, "step": 196700 }, { "epoch": 1.1692850901439094, "grad_norm": 1.4559426307678223, "learning_rate": 0.00015775698458632789, "loss": 0.5955242156982422, "step": 196710 }, { "epoch": 1.1693445322205775, "grad_norm": 1.9574936628341675, "learning_rate": 0.0001577517083477741, "loss": 0.6244900703430176, "step": 196720 }, { "epoch": 1.169403974297246, "grad_norm": 1.470306634902954, "learning_rate": 0.00015774643188079174, "loss": 0.6358212471008301, "step": 196730 }, { "epoch": 1.1694634163739144, "grad_norm": 1.8266472816467285, "learning_rate": 0.00015774115518540606, "loss": 0.6275129318237305, "step": 196740 }, { "epoch": 1.1695228584505828, "grad_norm": 1.4878705739974976, "learning_rate": 0.00015773587826164228, "loss": 0.5904661178588867, "step": 196750 }, { "epoch": 1.1695823005272512, "grad_norm": 1.770766258239746, "learning_rate": 0.00015773060110952568, "loss": 0.5640414714813232, "step": 196760 }, { "epoch": 1.1696417426039196, "grad_norm": 1.7993625402450562, "learning_rate": 0.0001577253237290815, "loss": 0.599111270904541, "step": 196770 }, { "epoch": 1.169701184680588, "grad_norm": 2.024381160736084, "learning_rate": 0.0001577200461203349, "loss": 0.6608426094055175, "step": 196780 }, { "epoch": 1.1697606267572564, "grad_norm": 1.6373239755630493, "learning_rate": 0.00015771476828331125, "loss": 0.6494227409362793, "step": 196790 }, { "epoch": 1.1698200688339249, "grad_norm": 1.5513548851013184, "learning_rate": 0.00015770949021803575, "loss": 0.6157322883605957, "step": 196800 }, { "epoch": 1.1698795109105933, "grad_norm": 1.6219617128372192, "learning_rate": 0.0001577042119245336, "loss": 0.6142306327819824, "step": 196810 }, { "epoch": 1.1699389529872615, "grad_norm": 2.2631592750549316, "learning_rate": 0.00015769893340283013, "loss": 0.6540689945220948, "step": 196820 }, { "epoch": 1.1699983950639299, "grad_norm": 1.634149432182312, "learning_rate": 0.0001576936546529505, "loss": 0.5913454055786133, "step": 196830 }, { "epoch": 1.1700578371405983, "grad_norm": 1.6827304363250732, "learning_rate": 0.00015768837567492006, "loss": 0.5949671745300293, "step": 196840 }, { "epoch": 1.1701172792172667, "grad_norm": 1.7986935377120972, "learning_rate": 0.000157683096468764, "loss": 0.5839090347290039, "step": 196850 }, { "epoch": 1.1701767212939351, "grad_norm": 1.8052732944488525, "learning_rate": 0.0001576778170345076, "loss": 0.5774178981781006, "step": 196860 }, { "epoch": 1.1702361633706035, "grad_norm": 1.5428577661514282, "learning_rate": 0.00015767253737217609, "loss": 0.6201443672180176, "step": 196870 }, { "epoch": 1.170295605447272, "grad_norm": 1.5166041851043701, "learning_rate": 0.00015766725748179474, "loss": 0.5777605056762696, "step": 196880 }, { "epoch": 1.1703550475239404, "grad_norm": 1.4365707635879517, "learning_rate": 0.00015766197736338878, "loss": 0.6362104892730713, "step": 196890 }, { "epoch": 1.1704144896006086, "grad_norm": 1.2921407222747803, "learning_rate": 0.00015765669701698357, "loss": 0.6174615383148193, "step": 196900 }, { "epoch": 1.170473931677277, "grad_norm": 1.4432265758514404, "learning_rate": 0.00015765141644260425, "loss": 0.6302728652954102, "step": 196910 }, { "epoch": 1.1705333737539454, "grad_norm": 1.582331895828247, "learning_rate": 0.0001576461356402761, "loss": 0.594485855102539, "step": 196920 }, { "epoch": 1.1705928158306138, "grad_norm": 1.7081670761108398, "learning_rate": 0.00015764085461002447, "loss": 0.6293401718139648, "step": 196930 }, { "epoch": 1.1706522579072822, "grad_norm": 1.456714153289795, "learning_rate": 0.0001576355733518745, "loss": 0.6154394149780273, "step": 196940 }, { "epoch": 1.1707116999839506, "grad_norm": 1.3989516496658325, "learning_rate": 0.00015763029186585155, "loss": 0.5978608131408691, "step": 196950 }, { "epoch": 1.170771142060619, "grad_norm": 1.4067975282669067, "learning_rate": 0.00015762501015198084, "loss": 0.6589560031890869, "step": 196960 }, { "epoch": 1.1708305841372875, "grad_norm": 1.7677654027938843, "learning_rate": 0.00015761972821028765, "loss": 0.6011459827423096, "step": 196970 }, { "epoch": 1.1708900262139559, "grad_norm": 1.9100984334945679, "learning_rate": 0.00015761444604079725, "loss": 0.6830421447753906, "step": 196980 }, { "epoch": 1.1709494682906243, "grad_norm": 1.4628562927246094, "learning_rate": 0.00015760916364353488, "loss": 0.6003762245178222, "step": 196990 }, { "epoch": 1.1710089103672927, "grad_norm": 1.653904914855957, "learning_rate": 0.00015760388101852585, "loss": 0.6331242561340332, "step": 197000 }, { "epoch": 1.171068352443961, "grad_norm": 1.7233712673187256, "learning_rate": 0.00015759859816579538, "loss": 0.6032742023468017, "step": 197010 }, { "epoch": 1.1711277945206293, "grad_norm": 1.5870782136917114, "learning_rate": 0.00015759331508536883, "loss": 0.6754537105560303, "step": 197020 }, { "epoch": 1.1711872365972977, "grad_norm": 1.7146039009094238, "learning_rate": 0.00015758803177727136, "loss": 0.6544537544250488, "step": 197030 }, { "epoch": 1.1712466786739661, "grad_norm": 1.6023577451705933, "learning_rate": 0.00015758274824152833, "loss": 0.621504545211792, "step": 197040 }, { "epoch": 1.1713061207506346, "grad_norm": 1.8547022342681885, "learning_rate": 0.00015757746447816494, "loss": 0.6336041450500488, "step": 197050 }, { "epoch": 1.171365562827303, "grad_norm": 1.5735480785369873, "learning_rate": 0.00015757218048720654, "loss": 0.6293384552001953, "step": 197060 }, { "epoch": 1.1714250049039714, "grad_norm": 1.4504607915878296, "learning_rate": 0.00015756689626867838, "loss": 0.5716168880462646, "step": 197070 }, { "epoch": 1.1714844469806398, "grad_norm": 1.6445063352584839, "learning_rate": 0.00015756161182260573, "loss": 0.6838030338287353, "step": 197080 }, { "epoch": 1.171543889057308, "grad_norm": 1.69230318069458, "learning_rate": 0.00015755632714901387, "loss": 0.5997325897216796, "step": 197090 }, { "epoch": 1.1716033311339764, "grad_norm": 1.5930367708206177, "learning_rate": 0.0001575510422479281, "loss": 0.616179370880127, "step": 197100 }, { "epoch": 1.1716627732106448, "grad_norm": 1.6920915842056274, "learning_rate": 0.00015754575711937366, "loss": 0.5913876533508301, "step": 197110 }, { "epoch": 1.1717222152873132, "grad_norm": 1.4780827760696411, "learning_rate": 0.00015754047176337583, "loss": 0.6072998046875, "step": 197120 }, { "epoch": 1.1717816573639817, "grad_norm": 1.5791934728622437, "learning_rate": 0.00015753518617995995, "loss": 0.6225817680358887, "step": 197130 }, { "epoch": 1.17184109944065, "grad_norm": 1.461018443107605, "learning_rate": 0.00015752990036915128, "loss": 0.6283102989196777, "step": 197140 }, { "epoch": 1.1719005415173185, "grad_norm": 1.9931614398956299, "learning_rate": 0.0001575246143309751, "loss": 0.605908203125, "step": 197150 }, { "epoch": 1.171959983593987, "grad_norm": 1.7275681495666504, "learning_rate": 0.00015751932806545667, "loss": 0.6059774398803711, "step": 197160 }, { "epoch": 1.1720194256706553, "grad_norm": 2.0352835655212402, "learning_rate": 0.00015751404157262136, "loss": 0.6181859970092773, "step": 197170 }, { "epoch": 1.1720788677473237, "grad_norm": 1.5216275453567505, "learning_rate": 0.00015750875485249436, "loss": 0.6388466835021973, "step": 197180 }, { "epoch": 1.172138309823992, "grad_norm": 1.4336771965026855, "learning_rate": 0.000157503467905101, "loss": 0.6099531173706054, "step": 197190 }, { "epoch": 1.1721977519006603, "grad_norm": 1.2541098594665527, "learning_rate": 0.0001574981807304666, "loss": 0.6235720157623291, "step": 197200 }, { "epoch": 1.1722571939773287, "grad_norm": 1.5442653894424438, "learning_rate": 0.0001574928933286164, "loss": 0.640648365020752, "step": 197210 }, { "epoch": 1.1723166360539972, "grad_norm": 1.6941943168640137, "learning_rate": 0.0001574876056995757, "loss": 0.5732294082641601, "step": 197220 }, { "epoch": 1.1723760781306656, "grad_norm": 1.7197872400283813, "learning_rate": 0.00015748231784336986, "loss": 0.609520149230957, "step": 197230 }, { "epoch": 1.172435520207334, "grad_norm": 1.7279770374298096, "learning_rate": 0.0001574770297600241, "loss": 0.6329110622406006, "step": 197240 }, { "epoch": 1.1724949622840024, "grad_norm": 1.1336874961853027, "learning_rate": 0.00015747174144956378, "loss": 0.6133857727050781, "step": 197250 }, { "epoch": 1.1725544043606708, "grad_norm": 1.4325660467147827, "learning_rate": 0.0001574664529120141, "loss": 0.6179993629455567, "step": 197260 }, { "epoch": 1.172613846437339, "grad_norm": 1.5373194217681885, "learning_rate": 0.0001574611641474005, "loss": 0.6154531478881836, "step": 197270 }, { "epoch": 1.1726732885140074, "grad_norm": 1.603997826576233, "learning_rate": 0.00015745587515574814, "loss": 0.6065116405487061, "step": 197280 }, { "epoch": 1.1727327305906758, "grad_norm": 1.2028175592422485, "learning_rate": 0.0001574505859370824, "loss": 0.5918369293212891, "step": 197290 }, { "epoch": 1.1727921726673443, "grad_norm": 1.596387267112732, "learning_rate": 0.00015744529649142856, "loss": 0.5544267654418945, "step": 197300 }, { "epoch": 1.1728516147440127, "grad_norm": 1.5713462829589844, "learning_rate": 0.00015744000681881196, "loss": 0.583013391494751, "step": 197310 }, { "epoch": 1.172911056820681, "grad_norm": 1.5685901641845703, "learning_rate": 0.00015743471691925782, "loss": 0.6243294239044189, "step": 197320 }, { "epoch": 1.1729704988973495, "grad_norm": 1.6168336868286133, "learning_rate": 0.00015742942679279154, "loss": 0.631477165222168, "step": 197330 }, { "epoch": 1.173029940974018, "grad_norm": 1.575448989868164, "learning_rate": 0.00015742413643943836, "loss": 0.6234347343444824, "step": 197340 }, { "epoch": 1.1730893830506863, "grad_norm": 1.546658992767334, "learning_rate": 0.0001574188458592236, "loss": 0.5729840278625489, "step": 197350 }, { "epoch": 1.1731488251273547, "grad_norm": 1.7626389265060425, "learning_rate": 0.00015741355505217262, "loss": 0.6100925445556641, "step": 197360 }, { "epoch": 1.1732082672040232, "grad_norm": 1.6143085956573486, "learning_rate": 0.00015740826401831065, "loss": 0.5965443611145019, "step": 197370 }, { "epoch": 1.1732677092806914, "grad_norm": 1.2949467897415161, "learning_rate": 0.00015740297275766303, "loss": 0.6393099784851074, "step": 197380 }, { "epoch": 1.1733271513573598, "grad_norm": 1.4564026594161987, "learning_rate": 0.00015739768127025512, "loss": 0.6437837600708007, "step": 197390 }, { "epoch": 1.1733865934340282, "grad_norm": 1.5405265092849731, "learning_rate": 0.00015739238955611213, "loss": 0.6565662384033203, "step": 197400 }, { "epoch": 1.1734460355106966, "grad_norm": 1.4867786169052124, "learning_rate": 0.0001573870976152595, "loss": 0.6154899597167969, "step": 197410 }, { "epoch": 1.173505477587365, "grad_norm": 1.7991878986358643, "learning_rate": 0.00015738180544772246, "loss": 0.6482219219207763, "step": 197420 }, { "epoch": 1.1735649196640334, "grad_norm": 1.4204275608062744, "learning_rate": 0.00015737651305352635, "loss": 0.5862622737884522, "step": 197430 }, { "epoch": 1.1736243617407018, "grad_norm": 1.4332975149154663, "learning_rate": 0.00015737122043269646, "loss": 0.6023842811584472, "step": 197440 }, { "epoch": 1.1736838038173703, "grad_norm": 1.7551933526992798, "learning_rate": 0.00015736592758525816, "loss": 0.6347276210784912, "step": 197450 }, { "epoch": 1.1737432458940384, "grad_norm": 1.5606473684310913, "learning_rate": 0.00015736063451123674, "loss": 0.6218656539916992, "step": 197460 }, { "epoch": 1.1738026879707069, "grad_norm": 1.6767467260360718, "learning_rate": 0.0001573553412106575, "loss": 0.5833002090454101, "step": 197470 }, { "epoch": 1.1738621300473753, "grad_norm": 1.0879062414169312, "learning_rate": 0.0001573500476835458, "loss": 0.5738848686218262, "step": 197480 }, { "epoch": 1.1739215721240437, "grad_norm": 1.7898696660995483, "learning_rate": 0.00015734475392992694, "loss": 0.6989956855773926, "step": 197490 }, { "epoch": 1.173981014200712, "grad_norm": 1.4175488948822021, "learning_rate": 0.00015733945994982624, "loss": 0.6160701751708985, "step": 197500 }, { "epoch": 1.1740404562773805, "grad_norm": 1.4763271808624268, "learning_rate": 0.00015733416574326907, "loss": 0.592692756652832, "step": 197510 }, { "epoch": 1.174099898354049, "grad_norm": 1.7039510011672974, "learning_rate": 0.0001573288713102807, "loss": 0.612918758392334, "step": 197520 }, { "epoch": 1.1741593404307173, "grad_norm": 1.9096837043762207, "learning_rate": 0.00015732357665088645, "loss": 0.6616642951965332, "step": 197530 }, { "epoch": 1.1742187825073858, "grad_norm": 1.5100858211517334, "learning_rate": 0.00015731828176511172, "loss": 0.606974983215332, "step": 197540 }, { "epoch": 1.1742782245840542, "grad_norm": 1.5661851167678833, "learning_rate": 0.00015731298665298178, "loss": 0.6174919128417968, "step": 197550 }, { "epoch": 1.1743376666607224, "grad_norm": 1.7870126962661743, "learning_rate": 0.00015730769131452196, "loss": 0.6000958919525147, "step": 197560 }, { "epoch": 1.1743971087373908, "grad_norm": 1.8980554342269897, "learning_rate": 0.00015730239574975762, "loss": 0.6297990798950195, "step": 197570 }, { "epoch": 1.1744565508140592, "grad_norm": 1.1551133394241333, "learning_rate": 0.00015729709995871406, "loss": 0.6166921138763428, "step": 197580 }, { "epoch": 1.1745159928907276, "grad_norm": 1.265427827835083, "learning_rate": 0.00015729180394141666, "loss": 0.6035811424255371, "step": 197590 }, { "epoch": 1.174575434967396, "grad_norm": 1.4662857055664062, "learning_rate": 0.0001572865076978907, "loss": 0.5922824382781983, "step": 197600 }, { "epoch": 1.1746348770440644, "grad_norm": 1.8131176233291626, "learning_rate": 0.00015728121122816156, "loss": 0.6407338619232178, "step": 197610 }, { "epoch": 1.1746943191207329, "grad_norm": 1.3897626399993896, "learning_rate": 0.00015727591453225452, "loss": 0.6520739555358886, "step": 197620 }, { "epoch": 1.1747537611974013, "grad_norm": 1.4679977893829346, "learning_rate": 0.000157270617610195, "loss": 0.5881410598754883, "step": 197630 }, { "epoch": 1.1748132032740695, "grad_norm": 1.3656169176101685, "learning_rate": 0.00015726532046200827, "loss": 0.5683924674987793, "step": 197640 }, { "epoch": 1.1748726453507379, "grad_norm": 1.4823881387710571, "learning_rate": 0.00015726002308771967, "loss": 0.6374482631683349, "step": 197650 }, { "epoch": 1.1749320874274063, "grad_norm": 1.6692616939544678, "learning_rate": 0.00015725472548735464, "loss": 0.6997851371765137, "step": 197660 }, { "epoch": 1.1749915295040747, "grad_norm": 1.5276299715042114, "learning_rate": 0.00015724942766093839, "loss": 0.683314037322998, "step": 197670 }, { "epoch": 1.1750509715807431, "grad_norm": 1.5878437757492065, "learning_rate": 0.0001572441296084963, "loss": 0.6174861907958984, "step": 197680 }, { "epoch": 1.1751104136574115, "grad_norm": 1.8659690618515015, "learning_rate": 0.00015723883133005376, "loss": 0.6343828201293945, "step": 197690 }, { "epoch": 1.17516985573408, "grad_norm": 1.7081130743026733, "learning_rate": 0.00015723353282563607, "loss": 0.6393604278564453, "step": 197700 }, { "epoch": 1.1752292978107484, "grad_norm": 1.3849419355392456, "learning_rate": 0.00015722823409526862, "loss": 0.5967260837554932, "step": 197710 }, { "epoch": 1.1752887398874168, "grad_norm": 1.4636310338974, "learning_rate": 0.00015722293513897672, "loss": 0.5531244277954102, "step": 197720 }, { "epoch": 1.1753481819640852, "grad_norm": 1.622401237487793, "learning_rate": 0.00015721763595678574, "loss": 0.6047580718994141, "step": 197730 }, { "epoch": 1.1754076240407536, "grad_norm": 1.5505000352859497, "learning_rate": 0.00015721233654872105, "loss": 0.6264309883117676, "step": 197740 }, { "epoch": 1.1754670661174218, "grad_norm": 1.7706719636917114, "learning_rate": 0.0001572070369148079, "loss": 0.566199779510498, "step": 197750 }, { "epoch": 1.1755265081940902, "grad_norm": 1.6051620244979858, "learning_rate": 0.00015720173705507178, "loss": 0.5311002731323242, "step": 197760 }, { "epoch": 1.1755859502707586, "grad_norm": 1.5250142812728882, "learning_rate": 0.0001571964369695379, "loss": 0.5657665252685546, "step": 197770 }, { "epoch": 1.175645392347427, "grad_norm": 1.4675610065460205, "learning_rate": 0.00015719113665823176, "loss": 0.5956936836242676, "step": 197780 }, { "epoch": 1.1757048344240955, "grad_norm": 1.5651780366897583, "learning_rate": 0.00015718583612117862, "loss": 0.6391650676727295, "step": 197790 }, { "epoch": 1.1757642765007639, "grad_norm": 1.2218108177185059, "learning_rate": 0.00015718053535840386, "loss": 0.620124626159668, "step": 197800 }, { "epoch": 1.1758237185774323, "grad_norm": 1.5276498794555664, "learning_rate": 0.00015717523436993282, "loss": 0.6330727577209473, "step": 197810 }, { "epoch": 1.1758831606541007, "grad_norm": 2.03509521484375, "learning_rate": 0.00015716993315579092, "loss": 0.6652158737182617, "step": 197820 }, { "epoch": 1.175942602730769, "grad_norm": 1.1505850553512573, "learning_rate": 0.00015716463171600343, "loss": 0.5966225624084472, "step": 197830 }, { "epoch": 1.1760020448074373, "grad_norm": 1.7314903736114502, "learning_rate": 0.00015715933005059577, "loss": 0.6630836486816406, "step": 197840 }, { "epoch": 1.1760614868841057, "grad_norm": 1.8175615072250366, "learning_rate": 0.00015715402815959332, "loss": 0.6604089736938477, "step": 197850 }, { "epoch": 1.1761209289607741, "grad_norm": 1.631093144416809, "learning_rate": 0.00015714872604302135, "loss": 0.6556837558746338, "step": 197860 }, { "epoch": 1.1761803710374426, "grad_norm": 1.3433761596679688, "learning_rate": 0.00015714342370090533, "loss": 0.5934422492980957, "step": 197870 }, { "epoch": 1.176239813114111, "grad_norm": 1.1844267845153809, "learning_rate": 0.00015713812113327057, "loss": 0.5706047058105469, "step": 197880 }, { "epoch": 1.1762992551907794, "grad_norm": 1.6309897899627686, "learning_rate": 0.00015713281834014243, "loss": 0.60897798538208, "step": 197890 }, { "epoch": 1.1763586972674478, "grad_norm": 1.6688814163208008, "learning_rate": 0.0001571275153215463, "loss": 0.6343103408813476, "step": 197900 }, { "epoch": 1.1764181393441162, "grad_norm": 1.5453946590423584, "learning_rate": 0.00015712221207750754, "loss": 0.607875394821167, "step": 197910 }, { "epoch": 1.1764775814207846, "grad_norm": 1.2964651584625244, "learning_rate": 0.00015711690860805151, "loss": 0.6370958805084228, "step": 197920 }, { "epoch": 1.1765370234974528, "grad_norm": 1.6673856973648071, "learning_rate": 0.00015711160491320357, "loss": 0.65030517578125, "step": 197930 }, { "epoch": 1.1765964655741212, "grad_norm": 2.065260887145996, "learning_rate": 0.00015710630099298914, "loss": 0.6079028129577637, "step": 197940 }, { "epoch": 1.1766559076507896, "grad_norm": 1.63813054561615, "learning_rate": 0.00015710099684743353, "loss": 0.6533534049987793, "step": 197950 }, { "epoch": 1.176715349727458, "grad_norm": 1.978724718093872, "learning_rate": 0.00015709569247656215, "loss": 0.631953763961792, "step": 197960 }, { "epoch": 1.1767747918041265, "grad_norm": 1.4390244483947754, "learning_rate": 0.00015709038788040038, "loss": 0.6422795295715332, "step": 197970 }, { "epoch": 1.1768342338807949, "grad_norm": 1.3911372423171997, "learning_rate": 0.00015708508305897363, "loss": 0.6288093090057373, "step": 197980 }, { "epoch": 1.1768936759574633, "grad_norm": 1.178013563156128, "learning_rate": 0.00015707977801230713, "loss": 0.5361739158630371, "step": 197990 }, { "epoch": 1.1769531180341317, "grad_norm": 1.4692760705947876, "learning_rate": 0.00015707447274042644, "loss": 0.6344212532043457, "step": 198000 }, { "epoch": 1.1770125601108, "grad_norm": 1.8111709356307983, "learning_rate": 0.0001570691672433568, "loss": 0.5902738571166992, "step": 198010 }, { "epoch": 1.1770720021874683, "grad_norm": 1.9161498546600342, "learning_rate": 0.00015706386152112368, "loss": 0.6937217712402344, "step": 198020 }, { "epoch": 1.1771314442641367, "grad_norm": 1.6464190483093262, "learning_rate": 0.0001570585555737524, "loss": 0.566309928894043, "step": 198030 }, { "epoch": 1.1771908863408052, "grad_norm": 1.6418700218200684, "learning_rate": 0.00015705324940126842, "loss": 0.6915389060974121, "step": 198040 }, { "epoch": 1.1772503284174736, "grad_norm": 1.439763069152832, "learning_rate": 0.00015704794300369702, "loss": 0.6207060813903809, "step": 198050 }, { "epoch": 1.177309770494142, "grad_norm": 1.5154001712799072, "learning_rate": 0.00015704263638106368, "loss": 0.587901258468628, "step": 198060 }, { "epoch": 1.1773692125708104, "grad_norm": 1.749471664428711, "learning_rate": 0.00015703732953339372, "loss": 0.6253507614135743, "step": 198070 }, { "epoch": 1.1774286546474788, "grad_norm": 1.7062904834747314, "learning_rate": 0.00015703202246071253, "loss": 0.611696720123291, "step": 198080 }, { "epoch": 1.1774880967241472, "grad_norm": 1.3051849603652954, "learning_rate": 0.00015702671516304553, "loss": 0.5899228572845459, "step": 198090 }, { "epoch": 1.1775475388008156, "grad_norm": 1.341923713684082, "learning_rate": 0.00015702140764041814, "loss": 0.6196728706359863, "step": 198100 }, { "epoch": 1.177606980877484, "grad_norm": 1.4349766969680786, "learning_rate": 0.00015701609989285563, "loss": 0.6346782207489013, "step": 198110 }, { "epoch": 1.1776664229541522, "grad_norm": 1.42904794216156, "learning_rate": 0.0001570107919203835, "loss": 0.6306252479553223, "step": 198120 }, { "epoch": 1.1777258650308207, "grad_norm": 1.6402024030685425, "learning_rate": 0.0001570054837230271, "loss": 0.6400849342346191, "step": 198130 }, { "epoch": 1.177785307107489, "grad_norm": 1.5555154085159302, "learning_rate": 0.0001570001753008118, "loss": 0.6486928462982178, "step": 198140 }, { "epoch": 1.1778447491841575, "grad_norm": 1.3893585205078125, "learning_rate": 0.00015699486665376306, "loss": 0.5988483428955078, "step": 198150 }, { "epoch": 1.177904191260826, "grad_norm": 1.4509834051132202, "learning_rate": 0.0001569895577819062, "loss": 0.6324490547180176, "step": 198160 }, { "epoch": 1.1779636333374943, "grad_norm": 1.485214114189148, "learning_rate": 0.00015698424868526667, "loss": 0.5679994106292725, "step": 198170 }, { "epoch": 1.1780230754141627, "grad_norm": 2.1970129013061523, "learning_rate": 0.00015697893936386987, "loss": 0.6940937519073487, "step": 198180 }, { "epoch": 1.1780825174908311, "grad_norm": 1.3645939826965332, "learning_rate": 0.00015697362981774115, "loss": 0.5910770416259765, "step": 198190 }, { "epoch": 1.1781419595674993, "grad_norm": 2.094172716140747, "learning_rate": 0.00015696832004690595, "loss": 0.6775894641876221, "step": 198200 }, { "epoch": 1.1782014016441678, "grad_norm": 1.9793206453323364, "learning_rate": 0.00015696301005138966, "loss": 0.6333002567291259, "step": 198210 }, { "epoch": 1.1782608437208362, "grad_norm": 1.6954500675201416, "learning_rate": 0.00015695769983121766, "loss": 0.6035691738128662, "step": 198220 }, { "epoch": 1.1783202857975046, "grad_norm": 1.3559017181396484, "learning_rate": 0.00015695238938641536, "loss": 0.5813229560852051, "step": 198230 }, { "epoch": 1.178379727874173, "grad_norm": 1.4894533157348633, "learning_rate": 0.00015694707871700817, "loss": 0.5926838874816894, "step": 198240 }, { "epoch": 1.1784391699508414, "grad_norm": 1.1445305347442627, "learning_rate": 0.00015694176782302154, "loss": 0.628162956237793, "step": 198250 }, { "epoch": 1.1784986120275098, "grad_norm": 1.59647798538208, "learning_rate": 0.0001569364567044808, "loss": 0.5850340366363526, "step": 198260 }, { "epoch": 1.1785580541041782, "grad_norm": 1.6435649394989014, "learning_rate": 0.00015693114536141143, "loss": 0.6631223678588867, "step": 198270 }, { "epoch": 1.1786174961808467, "grad_norm": 1.4643676280975342, "learning_rate": 0.00015692583379383877, "loss": 0.6331810474395752, "step": 198280 }, { "epoch": 1.178676938257515, "grad_norm": 1.5761696100234985, "learning_rate": 0.00015692052200178824, "loss": 0.6138524532318115, "step": 198290 }, { "epoch": 1.1787363803341833, "grad_norm": 1.5788671970367432, "learning_rate": 0.00015691520998528527, "loss": 0.5877881526947022, "step": 198300 }, { "epoch": 1.1787958224108517, "grad_norm": 1.5573424100875854, "learning_rate": 0.0001569098977443553, "loss": 0.6069713115692139, "step": 198310 }, { "epoch": 1.17885526448752, "grad_norm": 1.4700268507003784, "learning_rate": 0.0001569045852790237, "loss": 0.6532365322113037, "step": 198320 }, { "epoch": 1.1789147065641885, "grad_norm": 1.6130555868148804, "learning_rate": 0.00015689927258931584, "loss": 0.6232456207275391, "step": 198330 }, { "epoch": 1.178974148640857, "grad_norm": 1.1084645986557007, "learning_rate": 0.00015689395967525727, "loss": 0.5585588455200196, "step": 198340 }, { "epoch": 1.1790335907175253, "grad_norm": 1.7376708984375, "learning_rate": 0.00015688864653687327, "loss": 0.6684846401214599, "step": 198350 }, { "epoch": 1.1790930327941938, "grad_norm": 1.6994123458862305, "learning_rate": 0.0001568833331741893, "loss": 0.6660935401916503, "step": 198360 }, { "epoch": 1.1791524748708622, "grad_norm": 1.3913028240203857, "learning_rate": 0.00015687801958723084, "loss": 0.5963407993316651, "step": 198370 }, { "epoch": 1.1792119169475304, "grad_norm": 1.6696628332138062, "learning_rate": 0.00015687270577602317, "loss": 0.656687593460083, "step": 198380 }, { "epoch": 1.1792713590241988, "grad_norm": 1.5235400199890137, "learning_rate": 0.00015686739174059186, "loss": 0.7011383533477783, "step": 198390 }, { "epoch": 1.1793308011008672, "grad_norm": 1.4113414287567139, "learning_rate": 0.00015686207748096226, "loss": 0.6120011329650878, "step": 198400 }, { "epoch": 1.1793902431775356, "grad_norm": 1.8739863634109497, "learning_rate": 0.0001568567629971598, "loss": 0.6172218322753906, "step": 198410 }, { "epoch": 1.179449685254204, "grad_norm": 1.8933825492858887, "learning_rate": 0.00015685144828920985, "loss": 0.640046215057373, "step": 198420 }, { "epoch": 1.1795091273308724, "grad_norm": 1.7429481744766235, "learning_rate": 0.00015684613335713795, "loss": 0.6312434196472168, "step": 198430 }, { "epoch": 1.1795685694075408, "grad_norm": 1.5881609916687012, "learning_rate": 0.0001568408182009694, "loss": 0.6537498950958252, "step": 198440 }, { "epoch": 1.1796280114842093, "grad_norm": 1.911487102508545, "learning_rate": 0.0001568355028207297, "loss": 0.5809778690338134, "step": 198450 }, { "epoch": 1.1796874535608777, "grad_norm": 1.4714939594268799, "learning_rate": 0.00015683018721644428, "loss": 0.6066069602966309, "step": 198460 }, { "epoch": 1.179746895637546, "grad_norm": 1.5085434913635254, "learning_rate": 0.00015682487138813853, "loss": 0.5970798969268799, "step": 198470 }, { "epoch": 1.1798063377142145, "grad_norm": 1.3841782808303833, "learning_rate": 0.0001568195553358379, "loss": 0.6044423580169678, "step": 198480 }, { "epoch": 1.1798657797908827, "grad_norm": 1.5314698219299316, "learning_rate": 0.00015681423905956784, "loss": 0.6641577243804931, "step": 198490 }, { "epoch": 1.179925221867551, "grad_norm": 1.6883983612060547, "learning_rate": 0.00015680892255935373, "loss": 0.6379170417785645, "step": 198500 }, { "epoch": 1.1799846639442195, "grad_norm": 1.7593626976013184, "learning_rate": 0.00015680360583522106, "loss": 0.6178119659423829, "step": 198510 }, { "epoch": 1.180044106020888, "grad_norm": 1.7336721420288086, "learning_rate": 0.0001567982888871952, "loss": 0.5875438690185547, "step": 198520 }, { "epoch": 1.1801035480975564, "grad_norm": 1.7741984128952026, "learning_rate": 0.00015679297171530162, "loss": 0.6767753601074219, "step": 198530 }, { "epoch": 1.1801629901742248, "grad_norm": 1.408729910850525, "learning_rate": 0.00015678765431956582, "loss": 0.6188823699951171, "step": 198540 }, { "epoch": 1.1802224322508932, "grad_norm": 1.3060895204544067, "learning_rate": 0.0001567823367000131, "loss": 0.6210486412048339, "step": 198550 }, { "epoch": 1.1802818743275616, "grad_norm": 1.4671406745910645, "learning_rate": 0.000156777018856669, "loss": 0.5971346855163574, "step": 198560 }, { "epoch": 1.1803413164042298, "grad_norm": 1.5886480808258057, "learning_rate": 0.00015677170078955892, "loss": 0.6234266281127929, "step": 198570 }, { "epoch": 1.1804007584808982, "grad_norm": 1.711068868637085, "learning_rate": 0.0001567663824987083, "loss": 0.6490292072296142, "step": 198580 }, { "epoch": 1.1804602005575666, "grad_norm": 1.8850204944610596, "learning_rate": 0.0001567610639841426, "loss": 0.6026993751525879, "step": 198590 }, { "epoch": 1.180519642634235, "grad_norm": 1.6754069328308105, "learning_rate": 0.00015675574524588729, "loss": 0.6593358993530274, "step": 198600 }, { "epoch": 1.1805790847109034, "grad_norm": 1.8668839931488037, "learning_rate": 0.0001567504262839677, "loss": 0.6083882331848145, "step": 198610 }, { "epoch": 1.1806385267875719, "grad_norm": 1.234866976737976, "learning_rate": 0.00015674510709840942, "loss": 0.5875201225280762, "step": 198620 }, { "epoch": 1.1806979688642403, "grad_norm": 1.535314679145813, "learning_rate": 0.00015673978768923776, "loss": 0.6337996482849121, "step": 198630 }, { "epoch": 1.1807574109409087, "grad_norm": 1.473737120628357, "learning_rate": 0.00015673446805647827, "loss": 0.6539661407470703, "step": 198640 }, { "epoch": 1.180816853017577, "grad_norm": 1.4229270219802856, "learning_rate": 0.00015672914820015637, "loss": 0.5738361358642579, "step": 198650 }, { "epoch": 1.1808762950942455, "grad_norm": 1.5553553104400635, "learning_rate": 0.00015672382812029746, "loss": 0.6099414825439453, "step": 198660 }, { "epoch": 1.1809357371709137, "grad_norm": 1.6215403079986572, "learning_rate": 0.00015671850781692702, "loss": 0.6069870471954346, "step": 198670 }, { "epoch": 1.1809951792475821, "grad_norm": 2.0377204418182373, "learning_rate": 0.00015671318729007055, "loss": 0.612964391708374, "step": 198680 }, { "epoch": 1.1810546213242505, "grad_norm": 1.2579506635665894, "learning_rate": 0.00015670786653975343, "loss": 0.6067940711975097, "step": 198690 }, { "epoch": 1.181114063400919, "grad_norm": 1.3897614479064941, "learning_rate": 0.00015670254556600114, "loss": 0.6525226593017578, "step": 198700 }, { "epoch": 1.1811735054775874, "grad_norm": 1.1926143169403076, "learning_rate": 0.00015669722436883915, "loss": 0.5681509017944336, "step": 198710 }, { "epoch": 1.1812329475542558, "grad_norm": 1.504603624343872, "learning_rate": 0.0001566919029482929, "loss": 0.6048161506652832, "step": 198720 }, { "epoch": 1.1812923896309242, "grad_norm": 1.5014631748199463, "learning_rate": 0.0001566865813043878, "loss": 0.627016830444336, "step": 198730 }, { "epoch": 1.1813518317075926, "grad_norm": 1.645378828048706, "learning_rate": 0.00015668125943714943, "loss": 0.6366765975952149, "step": 198740 }, { "epoch": 1.1814112737842608, "grad_norm": 1.5648889541625977, "learning_rate": 0.00015667593734660314, "loss": 0.570872688293457, "step": 198750 }, { "epoch": 1.1814707158609292, "grad_norm": 1.9872509241104126, "learning_rate": 0.00015667061503277439, "loss": 0.6632281303405761, "step": 198760 }, { "epoch": 1.1815301579375976, "grad_norm": 1.6906871795654297, "learning_rate": 0.0001566652924956887, "loss": 0.6451414108276368, "step": 198770 }, { "epoch": 1.181589600014266, "grad_norm": 1.3578174114227295, "learning_rate": 0.00015665996973537148, "loss": 0.6006669044494629, "step": 198780 }, { "epoch": 1.1816490420909345, "grad_norm": 1.9236817359924316, "learning_rate": 0.0001566546467518482, "loss": 0.650985860824585, "step": 198790 }, { "epoch": 1.1817084841676029, "grad_norm": 1.662470817565918, "learning_rate": 0.00015664932354514437, "loss": 0.5864986896514892, "step": 198800 }, { "epoch": 1.1817679262442713, "grad_norm": 1.4002236127853394, "learning_rate": 0.0001566440001152854, "loss": 0.5903736114501953, "step": 198810 }, { "epoch": 1.1818273683209397, "grad_norm": 1.6650254726409912, "learning_rate": 0.00015663867646229678, "loss": 0.6396625518798829, "step": 198820 }, { "epoch": 1.1818868103976081, "grad_norm": 1.529189109802246, "learning_rate": 0.00015663335258620398, "loss": 0.5732868194580079, "step": 198830 }, { "epoch": 1.1819462524742765, "grad_norm": 1.3971779346466064, "learning_rate": 0.0001566280284870325, "loss": 0.6671717643737793, "step": 198840 }, { "epoch": 1.182005694550945, "grad_norm": 1.3644437789916992, "learning_rate": 0.00015662270416480771, "loss": 0.5986297607421875, "step": 198850 }, { "epoch": 1.1820651366276131, "grad_norm": 1.5050910711288452, "learning_rate": 0.00015661737961955517, "loss": 0.5769181251525879, "step": 198860 }, { "epoch": 1.1821245787042816, "grad_norm": 1.3420641422271729, "learning_rate": 0.00015661205485130032, "loss": 0.5770376205444336, "step": 198870 }, { "epoch": 1.18218402078095, "grad_norm": 1.7544612884521484, "learning_rate": 0.00015660672986006862, "loss": 0.6261990070343018, "step": 198880 }, { "epoch": 1.1822434628576184, "grad_norm": 1.818204402923584, "learning_rate": 0.00015660140464588557, "loss": 0.5591779232025147, "step": 198890 }, { "epoch": 1.1823029049342868, "grad_norm": 1.8459253311157227, "learning_rate": 0.0001565960792087766, "loss": 0.6026657581329345, "step": 198900 }, { "epoch": 1.1823623470109552, "grad_norm": 1.9680476188659668, "learning_rate": 0.00015659075354876724, "loss": 0.6504651069641113, "step": 198910 }, { "epoch": 1.1824217890876236, "grad_norm": 2.081261396408081, "learning_rate": 0.00015658542766588295, "loss": 0.6050084114074707, "step": 198920 }, { "epoch": 1.182481231164292, "grad_norm": 1.3653769493103027, "learning_rate": 0.00015658010156014917, "loss": 0.5847785472869873, "step": 198930 }, { "epoch": 1.1825406732409602, "grad_norm": 1.1658581495285034, "learning_rate": 0.00015657477523159141, "loss": 0.5862459182739258, "step": 198940 }, { "epoch": 1.1826001153176287, "grad_norm": 1.4125261306762695, "learning_rate": 0.00015656944868023518, "loss": 0.6319592475891114, "step": 198950 }, { "epoch": 1.182659557394297, "grad_norm": 1.7523442506790161, "learning_rate": 0.0001565641219061059, "loss": 0.63533034324646, "step": 198960 }, { "epoch": 1.1827189994709655, "grad_norm": 1.7447264194488525, "learning_rate": 0.00015655879490922907, "loss": 0.6058449745178223, "step": 198970 }, { "epoch": 1.182778441547634, "grad_norm": 1.8477598428726196, "learning_rate": 0.00015655346768963022, "loss": 0.6286664485931397, "step": 198980 }, { "epoch": 1.1828378836243023, "grad_norm": 1.550017237663269, "learning_rate": 0.00015654814024733475, "loss": 0.6273658275604248, "step": 198990 }, { "epoch": 1.1828973257009707, "grad_norm": 1.37606680393219, "learning_rate": 0.0001565428125823682, "loss": 0.607776689529419, "step": 199000 }, { "epoch": 1.1829567677776391, "grad_norm": 1.8817909955978394, "learning_rate": 0.00015653748469475606, "loss": 0.6133103847503663, "step": 199010 }, { "epoch": 1.1830162098543076, "grad_norm": 1.2340978384017944, "learning_rate": 0.0001565321565845238, "loss": 0.5962194442749024, "step": 199020 }, { "epoch": 1.183075651930976, "grad_norm": 1.276711106300354, "learning_rate": 0.0001565268282516969, "loss": 0.616523551940918, "step": 199030 }, { "epoch": 1.1831350940076442, "grad_norm": 1.455937385559082, "learning_rate": 0.00015652149969630085, "loss": 0.6190753936767578, "step": 199040 }, { "epoch": 1.1831945360843126, "grad_norm": 1.5491352081298828, "learning_rate": 0.00015651617091836116, "loss": 0.6056304931640625, "step": 199050 }, { "epoch": 1.183253978160981, "grad_norm": 1.4040265083312988, "learning_rate": 0.00015651084191790332, "loss": 0.6040386199951172, "step": 199060 }, { "epoch": 1.1833134202376494, "grad_norm": 1.330145001411438, "learning_rate": 0.0001565055126949528, "loss": 0.6135331153869629, "step": 199070 }, { "epoch": 1.1833728623143178, "grad_norm": 1.3909428119659424, "learning_rate": 0.0001565001832495351, "loss": 0.5701735496520997, "step": 199080 }, { "epoch": 1.1834323043909862, "grad_norm": 1.937233805656433, "learning_rate": 0.00015649485358167574, "loss": 0.6637036323547363, "step": 199090 }, { "epoch": 1.1834917464676546, "grad_norm": 1.7192845344543457, "learning_rate": 0.00015648952369140017, "loss": 0.6479644298553466, "step": 199100 }, { "epoch": 1.183551188544323, "grad_norm": 2.3231475353240967, "learning_rate": 0.00015648419357873394, "loss": 0.5775890350341797, "step": 199110 }, { "epoch": 1.1836106306209913, "grad_norm": 2.1950106620788574, "learning_rate": 0.0001564788632437025, "loss": 0.7030139923095703, "step": 199120 }, { "epoch": 1.1836700726976597, "grad_norm": 1.4540321826934814, "learning_rate": 0.00015647353268633137, "loss": 0.6368914604187011, "step": 199130 }, { "epoch": 1.183729514774328, "grad_norm": 2.0837926864624023, "learning_rate": 0.00015646820190664607, "loss": 0.6582335472106934, "step": 199140 }, { "epoch": 1.1837889568509965, "grad_norm": 1.7206679582595825, "learning_rate": 0.000156462870904672, "loss": 0.6120028972625733, "step": 199150 }, { "epoch": 1.183848398927665, "grad_norm": 1.4381195306777954, "learning_rate": 0.00015645753968043482, "loss": 0.5331289291381835, "step": 199160 }, { "epoch": 1.1839078410043333, "grad_norm": 1.684198021888733, "learning_rate": 0.00015645220823395995, "loss": 0.5728707313537598, "step": 199170 }, { "epoch": 1.1839672830810017, "grad_norm": 1.303580641746521, "learning_rate": 0.00015644687656527287, "loss": 0.6027607917785645, "step": 199180 }, { "epoch": 1.1840267251576702, "grad_norm": 1.7416882514953613, "learning_rate": 0.00015644154467439912, "loss": 0.6305423736572265, "step": 199190 }, { "epoch": 1.1840861672343386, "grad_norm": 1.6442809104919434, "learning_rate": 0.00015643621256136419, "loss": 0.6054595947265625, "step": 199200 }, { "epoch": 1.184145609311007, "grad_norm": 1.3926883935928345, "learning_rate": 0.0001564308802261936, "loss": 0.6047447204589844, "step": 199210 }, { "epoch": 1.1842050513876754, "grad_norm": 1.469810962677002, "learning_rate": 0.00015642554766891285, "loss": 0.5840829372406006, "step": 199220 }, { "epoch": 1.1842644934643436, "grad_norm": 1.795621633529663, "learning_rate": 0.00015642021488954748, "loss": 0.5988302230834961, "step": 199230 }, { "epoch": 1.184323935541012, "grad_norm": 1.5781426429748535, "learning_rate": 0.00015641488188812292, "loss": 0.5564821243286133, "step": 199240 }, { "epoch": 1.1843833776176804, "grad_norm": 1.9130052328109741, "learning_rate": 0.00015640954866466474, "loss": 0.6341209888458252, "step": 199250 }, { "epoch": 1.1844428196943488, "grad_norm": 1.6757608652114868, "learning_rate": 0.0001564042152191985, "loss": 0.5925388336181641, "step": 199260 }, { "epoch": 1.1845022617710173, "grad_norm": 1.7172815799713135, "learning_rate": 0.00015639888155174962, "loss": 0.6461688041687011, "step": 199270 }, { "epoch": 1.1845617038476857, "grad_norm": 1.5588146448135376, "learning_rate": 0.00015639354766234368, "loss": 0.6305295944213867, "step": 199280 }, { "epoch": 1.184621145924354, "grad_norm": 1.8882379531860352, "learning_rate": 0.00015638821355100612, "loss": 0.6236460685729981, "step": 199290 }, { "epoch": 1.1846805880010225, "grad_norm": 1.6209168434143066, "learning_rate": 0.00015638287921776253, "loss": 0.6315098762512207, "step": 199300 }, { "epoch": 1.1847400300776907, "grad_norm": 1.4999321699142456, "learning_rate": 0.00015637754466263842, "loss": 0.6055762290954589, "step": 199310 }, { "epoch": 1.184799472154359, "grad_norm": 1.5798300504684448, "learning_rate": 0.00015637220988565928, "loss": 0.6154533863067627, "step": 199320 }, { "epoch": 1.1848589142310275, "grad_norm": 1.7605869770050049, "learning_rate": 0.00015636687488685064, "loss": 0.5909718990325927, "step": 199330 }, { "epoch": 1.184918356307696, "grad_norm": 1.5453381538391113, "learning_rate": 0.00015636153966623804, "loss": 0.6006365776062011, "step": 199340 }, { "epoch": 1.1849777983843643, "grad_norm": 1.5598647594451904, "learning_rate": 0.00015635620422384697, "loss": 0.6618977546691894, "step": 199350 }, { "epoch": 1.1850372404610328, "grad_norm": 1.7333605289459229, "learning_rate": 0.00015635086855970298, "loss": 0.597537899017334, "step": 199360 }, { "epoch": 1.1850966825377012, "grad_norm": 1.689890742301941, "learning_rate": 0.00015634553267383157, "loss": 0.6506290435791016, "step": 199370 }, { "epoch": 1.1851561246143696, "grad_norm": 1.8022390604019165, "learning_rate": 0.00015634019656625826, "loss": 0.5941699028015137, "step": 199380 }, { "epoch": 1.185215566691038, "grad_norm": 1.9161168336868286, "learning_rate": 0.00015633486023700866, "loss": 0.5725696086883545, "step": 199390 }, { "epoch": 1.1852750087677064, "grad_norm": 1.6004899740219116, "learning_rate": 0.00015632952368610815, "loss": 0.6254641056060791, "step": 199400 }, { "epoch": 1.1853344508443746, "grad_norm": 1.2219009399414062, "learning_rate": 0.00015632418691358238, "loss": 0.6208749771118164, "step": 199410 }, { "epoch": 1.185393892921043, "grad_norm": 1.8161823749542236, "learning_rate": 0.00015631884991945688, "loss": 0.6388670921325683, "step": 199420 }, { "epoch": 1.1854533349977114, "grad_norm": 1.4061280488967896, "learning_rate": 0.00015631351270375707, "loss": 0.6805086135864258, "step": 199430 }, { "epoch": 1.1855127770743799, "grad_norm": 1.1303060054779053, "learning_rate": 0.00015630817526650855, "loss": 0.6264102935791016, "step": 199440 }, { "epoch": 1.1855722191510483, "grad_norm": 1.6992120742797852, "learning_rate": 0.0001563028376077369, "loss": 0.5953619956970215, "step": 199450 }, { "epoch": 1.1856316612277167, "grad_norm": 1.9778122901916504, "learning_rate": 0.00015629749972746756, "loss": 0.6218380451202392, "step": 199460 }, { "epoch": 1.185691103304385, "grad_norm": 1.316308617591858, "learning_rate": 0.00015629216162572616, "loss": 0.616961669921875, "step": 199470 }, { "epoch": 1.1857505453810535, "grad_norm": 1.4848328828811646, "learning_rate": 0.00015628682330253815, "loss": 0.616530466079712, "step": 199480 }, { "epoch": 1.1858099874577217, "grad_norm": 1.569380760192871, "learning_rate": 0.00015628148475792911, "loss": 0.5927962779998779, "step": 199490 }, { "epoch": 1.1858694295343901, "grad_norm": 1.5030447244644165, "learning_rate": 0.00015627614599192458, "loss": 0.5699345588684082, "step": 199500 }, { "epoch": 1.1859288716110585, "grad_norm": 1.4308797121047974, "learning_rate": 0.0001562708070045501, "loss": 0.5645222663879395, "step": 199510 }, { "epoch": 1.185988313687727, "grad_norm": 1.5422970056533813, "learning_rate": 0.00015626546779583123, "loss": 0.6269410133361817, "step": 199520 }, { "epoch": 1.1860477557643954, "grad_norm": 1.4085979461669922, "learning_rate": 0.0001562601283657934, "loss": 0.6099949836730957, "step": 199530 }, { "epoch": 1.1861071978410638, "grad_norm": 1.4895389080047607, "learning_rate": 0.0001562547887144623, "loss": 0.6717710494995117, "step": 199540 }, { "epoch": 1.1861666399177322, "grad_norm": 1.7577605247497559, "learning_rate": 0.00015624944884186338, "loss": 0.5884997367858886, "step": 199550 }, { "epoch": 1.1862260819944006, "grad_norm": 1.8956044912338257, "learning_rate": 0.0001562441087480222, "loss": 0.6508924007415772, "step": 199560 }, { "epoch": 1.186285524071069, "grad_norm": 1.5719181299209595, "learning_rate": 0.00015623876843296435, "loss": 0.5575978279113769, "step": 199570 }, { "epoch": 1.1863449661477374, "grad_norm": 1.502383828163147, "learning_rate": 0.0001562334278967153, "loss": 0.6540859699249267, "step": 199580 }, { "epoch": 1.1864044082244058, "grad_norm": 1.7388339042663574, "learning_rate": 0.00015622808713930067, "loss": 0.6655524253845215, "step": 199590 }, { "epoch": 1.186463850301074, "grad_norm": 1.6736737489700317, "learning_rate": 0.00015622274616074598, "loss": 0.6429522514343262, "step": 199600 }, { "epoch": 1.1865232923777425, "grad_norm": 1.4359502792358398, "learning_rate": 0.00015621740496107674, "loss": 0.6380397796630859, "step": 199610 }, { "epoch": 1.1865827344544109, "grad_norm": 1.8104597330093384, "learning_rate": 0.0001562120635403186, "loss": 0.6510360240936279, "step": 199620 }, { "epoch": 1.1866421765310793, "grad_norm": 1.6979619264602661, "learning_rate": 0.00015620672189849702, "loss": 0.594890546798706, "step": 199630 }, { "epoch": 1.1867016186077477, "grad_norm": 1.9396711587905884, "learning_rate": 0.00015620138003563755, "loss": 0.6267555713653564, "step": 199640 }, { "epoch": 1.1867610606844161, "grad_norm": 1.7211564779281616, "learning_rate": 0.00015619603795176583, "loss": 0.6238411426544189, "step": 199650 }, { "epoch": 1.1868205027610845, "grad_norm": 1.427641749382019, "learning_rate": 0.00015619069564690733, "loss": 0.6406155586242676, "step": 199660 }, { "epoch": 1.186879944837753, "grad_norm": 1.4356367588043213, "learning_rate": 0.00015618535312108766, "loss": 0.5610066413879394, "step": 199670 }, { "epoch": 1.1869393869144211, "grad_norm": 1.7315442562103271, "learning_rate": 0.00015618001037433235, "loss": 0.6255773544311524, "step": 199680 }, { "epoch": 1.1869988289910895, "grad_norm": 1.7355198860168457, "learning_rate": 0.00015617466740666696, "loss": 0.5620772838592529, "step": 199690 }, { "epoch": 1.187058271067758, "grad_norm": 1.4925414323806763, "learning_rate": 0.00015616932421811706, "loss": 0.6218145370483399, "step": 199700 }, { "epoch": 1.1871177131444264, "grad_norm": 2.1105399131774902, "learning_rate": 0.00015616398080870817, "loss": 0.5861320972442627, "step": 199710 }, { "epoch": 1.1871771552210948, "grad_norm": 1.6794370412826538, "learning_rate": 0.0001561586371784659, "loss": 0.6281223297119141, "step": 199720 }, { "epoch": 1.1872365972977632, "grad_norm": 1.7490729093551636, "learning_rate": 0.0001561532933274158, "loss": 0.5911911964416504, "step": 199730 }, { "epoch": 1.1872960393744316, "grad_norm": 1.3243601322174072, "learning_rate": 0.0001561479492555834, "loss": 0.5810737133026123, "step": 199740 }, { "epoch": 1.1873554814511, "grad_norm": 1.6516746282577515, "learning_rate": 0.00015614260496299431, "loss": 0.6488467216491699, "step": 199750 }, { "epoch": 1.1874149235277685, "grad_norm": 1.6952052116394043, "learning_rate": 0.0001561372604496741, "loss": 0.6514239311218262, "step": 199760 }, { "epoch": 1.1874743656044369, "grad_norm": 1.2980085611343384, "learning_rate": 0.0001561319157156483, "loss": 0.6676460266113281, "step": 199770 }, { "epoch": 1.187533807681105, "grad_norm": 1.5024954080581665, "learning_rate": 0.00015612657076094247, "loss": 0.6257133960723877, "step": 199780 }, { "epoch": 1.1875932497577735, "grad_norm": 1.6584821939468384, "learning_rate": 0.00015612122558558223, "loss": 0.6098404884338379, "step": 199790 }, { "epoch": 1.1876526918344419, "grad_norm": 1.3922713994979858, "learning_rate": 0.0001561158801895931, "loss": 0.6432413101196289, "step": 199800 }, { "epoch": 1.1877121339111103, "grad_norm": 1.6379176378250122, "learning_rate": 0.00015611053457300066, "loss": 0.5920415878295898, "step": 199810 }, { "epoch": 1.1877715759877787, "grad_norm": 1.754015326499939, "learning_rate": 0.0001561051887358305, "loss": 0.6175745487213135, "step": 199820 }, { "epoch": 1.1878310180644471, "grad_norm": 1.6425182819366455, "learning_rate": 0.0001560998426781082, "loss": 0.638101863861084, "step": 199830 }, { "epoch": 1.1878904601411155, "grad_norm": 1.5943193435668945, "learning_rate": 0.0001560944963998593, "loss": 0.6499979019165039, "step": 199840 }, { "epoch": 1.187949902217784, "grad_norm": 1.767423391342163, "learning_rate": 0.00015608914990110945, "loss": 0.6427506446838379, "step": 199850 }, { "epoch": 1.1880093442944522, "grad_norm": 1.7690337896347046, "learning_rate": 0.00015608380318188412, "loss": 0.5534953117370606, "step": 199860 }, { "epoch": 1.1880687863711206, "grad_norm": 1.4659703969955444, "learning_rate": 0.00015607845624220892, "loss": 0.609953784942627, "step": 199870 }, { "epoch": 1.188128228447789, "grad_norm": 1.4013826847076416, "learning_rate": 0.00015607310908210946, "loss": 0.5725923538208008, "step": 199880 }, { "epoch": 1.1881876705244574, "grad_norm": 1.604880452156067, "learning_rate": 0.0001560677617016113, "loss": 0.6136992931365967, "step": 199890 }, { "epoch": 1.1882471126011258, "grad_norm": 1.7470258474349976, "learning_rate": 0.00015606241410074002, "loss": 0.643494701385498, "step": 199900 }, { "epoch": 1.1883065546777942, "grad_norm": 1.8089754581451416, "learning_rate": 0.00015605706627952123, "loss": 0.5955690860748291, "step": 199910 }, { "epoch": 1.1883659967544626, "grad_norm": 1.5827161073684692, "learning_rate": 0.00015605171823798047, "loss": 0.6771574974060058, "step": 199920 }, { "epoch": 1.188425438831131, "grad_norm": 1.228895664215088, "learning_rate": 0.00015604636997614335, "loss": 0.6824919700622558, "step": 199930 }, { "epoch": 1.1884848809077995, "grad_norm": 1.913169264793396, "learning_rate": 0.00015604102149403544, "loss": 0.618022346496582, "step": 199940 }, { "epoch": 1.1885443229844679, "grad_norm": 1.5688172578811646, "learning_rate": 0.00015603567279168226, "loss": 0.6297976016998291, "step": 199950 }, { "epoch": 1.1886037650611363, "grad_norm": 1.3909275531768799, "learning_rate": 0.00015603032386910957, "loss": 0.6790851593017578, "step": 199960 }, { "epoch": 1.1886632071378045, "grad_norm": 1.7646338939666748, "learning_rate": 0.00015602497472634282, "loss": 0.6156089782714844, "step": 199970 }, { "epoch": 1.188722649214473, "grad_norm": 2.174236536026001, "learning_rate": 0.00015601962536340762, "loss": 0.6079753875732422, "step": 199980 }, { "epoch": 1.1887820912911413, "grad_norm": 1.867775559425354, "learning_rate": 0.00015601427578032956, "loss": 0.6434810638427735, "step": 199990 }, { "epoch": 1.1888415333678097, "grad_norm": 2.203294038772583, "learning_rate": 0.00015600892597713426, "loss": 0.6560533523559571, "step": 200000 }, { "epoch": 1.1889009754444781, "grad_norm": 1.7228070497512817, "learning_rate": 0.0001560035759538473, "loss": 0.6705411911010742, "step": 200010 }, { "epoch": 1.1889604175211466, "grad_norm": 1.5357260704040527, "learning_rate": 0.00015599822571049426, "loss": 0.5703799724578857, "step": 200020 }, { "epoch": 1.189019859597815, "grad_norm": 2.0959928035736084, "learning_rate": 0.00015599287524710077, "loss": 0.6447022914886474, "step": 200030 }, { "epoch": 1.1890793016744834, "grad_norm": 1.9744688272476196, "learning_rate": 0.00015598752456369232, "loss": 0.6387567520141602, "step": 200040 }, { "epoch": 1.1891387437511516, "grad_norm": 1.381496787071228, "learning_rate": 0.00015598217366029465, "loss": 0.6574193954467773, "step": 200050 }, { "epoch": 1.18919818582782, "grad_norm": 1.5990631580352783, "learning_rate": 0.00015597682253693323, "loss": 0.6139141082763672, "step": 200060 }, { "epoch": 1.1892576279044884, "grad_norm": 1.3984256982803345, "learning_rate": 0.00015597147119363375, "loss": 0.5593355655670166, "step": 200070 }, { "epoch": 1.1893170699811568, "grad_norm": 1.4752347469329834, "learning_rate": 0.00015596611963042178, "loss": 0.6304279327392578, "step": 200080 }, { "epoch": 1.1893765120578252, "grad_norm": 1.6550242900848389, "learning_rate": 0.0001559607678473229, "loss": 0.6476672172546387, "step": 200090 }, { "epoch": 1.1894359541344937, "grad_norm": 1.374180555343628, "learning_rate": 0.00015595541584436276, "loss": 0.6254282474517823, "step": 200100 }, { "epoch": 1.189495396211162, "grad_norm": 0.9744839072227478, "learning_rate": 0.00015595006362156691, "loss": 0.5713353157043457, "step": 200110 }, { "epoch": 1.1895548382878305, "grad_norm": 1.4656736850738525, "learning_rate": 0.000155944711178961, "loss": 0.6545835018157959, "step": 200120 }, { "epoch": 1.189614280364499, "grad_norm": 1.7656750679016113, "learning_rate": 0.00015593935851657056, "loss": 0.6000028133392334, "step": 200130 }, { "epoch": 1.1896737224411673, "grad_norm": 1.2863599061965942, "learning_rate": 0.00015593400563442128, "loss": 0.585204029083252, "step": 200140 }, { "epoch": 1.1897331645178355, "grad_norm": 2.6691606044769287, "learning_rate": 0.0001559286525325387, "loss": 0.6420665740966797, "step": 200150 }, { "epoch": 1.189792606594504, "grad_norm": 1.1615198850631714, "learning_rate": 0.00015592329921094845, "loss": 0.6649331092834473, "step": 200160 }, { "epoch": 1.1898520486711723, "grad_norm": 2.0038678646087646, "learning_rate": 0.00015591794566967616, "loss": 0.6175052642822265, "step": 200170 }, { "epoch": 1.1899114907478407, "grad_norm": 1.2467061281204224, "learning_rate": 0.0001559125919087474, "loss": 0.624632740020752, "step": 200180 }, { "epoch": 1.1899709328245092, "grad_norm": 1.7082148790359497, "learning_rate": 0.00015590723792818784, "loss": 0.6041343688964844, "step": 200190 }, { "epoch": 1.1900303749011776, "grad_norm": 1.627510905265808, "learning_rate": 0.00015590188372802304, "loss": 0.6022921562194824, "step": 200200 }, { "epoch": 1.190089816977846, "grad_norm": 1.6975226402282715, "learning_rate": 0.00015589652930827862, "loss": 0.65005521774292, "step": 200210 }, { "epoch": 1.1901492590545144, "grad_norm": 1.347264051437378, "learning_rate": 0.00015589117466898022, "loss": 0.6019970893859863, "step": 200220 }, { "epoch": 1.1902087011311826, "grad_norm": 2.1018500328063965, "learning_rate": 0.0001558858198101534, "loss": 0.5746072769165039, "step": 200230 }, { "epoch": 1.190268143207851, "grad_norm": 1.5705287456512451, "learning_rate": 0.00015588046473182388, "loss": 0.6008002281188964, "step": 200240 }, { "epoch": 1.1903275852845194, "grad_norm": 1.703640103340149, "learning_rate": 0.0001558751094340172, "loss": 0.5684903621673584, "step": 200250 }, { "epoch": 1.1903870273611878, "grad_norm": 1.707152009010315, "learning_rate": 0.00015586975391675893, "loss": 0.5608109474182129, "step": 200260 }, { "epoch": 1.1904464694378563, "grad_norm": 1.938820719718933, "learning_rate": 0.0001558643981800748, "loss": 0.6233283996582031, "step": 200270 }, { "epoch": 1.1905059115145247, "grad_norm": 1.5318776369094849, "learning_rate": 0.00015585904222399036, "loss": 0.5979663848876953, "step": 200280 }, { "epoch": 1.190565353591193, "grad_norm": 1.3486093282699585, "learning_rate": 0.00015585368604853126, "loss": 0.6053207397460938, "step": 200290 }, { "epoch": 1.1906247956678615, "grad_norm": 1.6145172119140625, "learning_rate": 0.0001558483296537231, "loss": 0.6324792385101319, "step": 200300 }, { "epoch": 1.19068423774453, "grad_norm": 2.0535387992858887, "learning_rate": 0.0001558429730395915, "loss": 0.6873033523559571, "step": 200310 }, { "epoch": 1.1907436798211983, "grad_norm": 1.142791986465454, "learning_rate": 0.0001558376162061621, "loss": 0.6385876655578613, "step": 200320 }, { "epoch": 1.1908031218978667, "grad_norm": 1.264884114265442, "learning_rate": 0.00015583225915346055, "loss": 0.5799503326416016, "step": 200330 }, { "epoch": 1.190862563974535, "grad_norm": 1.645349144935608, "learning_rate": 0.00015582690188151245, "loss": 0.5655770301818848, "step": 200340 }, { "epoch": 1.1909220060512034, "grad_norm": 1.0921300649642944, "learning_rate": 0.00015582154439034343, "loss": 0.6028120040893554, "step": 200350 }, { "epoch": 1.1909814481278718, "grad_norm": 1.2827575206756592, "learning_rate": 0.0001558161866799791, "loss": 0.6198967933654785, "step": 200360 }, { "epoch": 1.1910408902045402, "grad_norm": 1.881484866142273, "learning_rate": 0.0001558108287504451, "loss": 0.6314452171325684, "step": 200370 }, { "epoch": 1.1911003322812086, "grad_norm": 1.6621278524398804, "learning_rate": 0.00015580547060176707, "loss": 0.5834181785583497, "step": 200380 }, { "epoch": 1.191159774357877, "grad_norm": 1.4878183603286743, "learning_rate": 0.00015580011223397062, "loss": 0.633430814743042, "step": 200390 }, { "epoch": 1.1912192164345454, "grad_norm": 1.1924415826797485, "learning_rate": 0.00015579475364708143, "loss": 0.6592134952545166, "step": 200400 }, { "epoch": 1.1912786585112138, "grad_norm": 1.7975815534591675, "learning_rate": 0.00015578939484112508, "loss": 0.6419586658477783, "step": 200410 }, { "epoch": 1.191338100587882, "grad_norm": 2.015960931777954, "learning_rate": 0.00015578403581612726, "loss": 0.6612799167633057, "step": 200420 }, { "epoch": 1.1913975426645504, "grad_norm": 1.2270786762237549, "learning_rate": 0.00015577867657211357, "loss": 0.6159738540649414, "step": 200430 }, { "epoch": 1.1914569847412189, "grad_norm": 1.6359078884124756, "learning_rate": 0.00015577331710910964, "loss": 0.6219819545745849, "step": 200440 }, { "epoch": 1.1915164268178873, "grad_norm": 1.8223673105239868, "learning_rate": 0.0001557679574271411, "loss": 0.6095035552978516, "step": 200450 }, { "epoch": 1.1915758688945557, "grad_norm": 1.628217339515686, "learning_rate": 0.00015576259752623367, "loss": 0.5576536655426025, "step": 200460 }, { "epoch": 1.191635310971224, "grad_norm": 1.547358512878418, "learning_rate": 0.0001557572374064129, "loss": 0.5485972881317138, "step": 200470 }, { "epoch": 1.1916947530478925, "grad_norm": 1.3521734476089478, "learning_rate": 0.00015575187706770444, "loss": 0.6052196025848389, "step": 200480 }, { "epoch": 1.191754195124561, "grad_norm": 1.9135159254074097, "learning_rate": 0.00015574651651013396, "loss": 0.6717372417449952, "step": 200490 }, { "epoch": 1.1918136372012293, "grad_norm": 1.5011016130447388, "learning_rate": 0.0001557411557337271, "loss": 0.5886970520019531, "step": 200500 }, { "epoch": 1.1918730792778978, "grad_norm": 1.3195301294326782, "learning_rate": 0.00015573579473850948, "loss": 0.6103368759155273, "step": 200510 }, { "epoch": 1.191932521354566, "grad_norm": 1.59595787525177, "learning_rate": 0.0001557304335245068, "loss": 0.6324540138244629, "step": 200520 }, { "epoch": 1.1919919634312344, "grad_norm": 1.3282418251037598, "learning_rate": 0.00015572507209174466, "loss": 0.5477473258972168, "step": 200530 }, { "epoch": 1.1920514055079028, "grad_norm": 1.366884708404541, "learning_rate": 0.0001557197104402487, "loss": 0.581141471862793, "step": 200540 }, { "epoch": 1.1921108475845712, "grad_norm": 1.1616326570510864, "learning_rate": 0.0001557143485700446, "loss": 0.604233694076538, "step": 200550 }, { "epoch": 1.1921702896612396, "grad_norm": 1.6371560096740723, "learning_rate": 0.00015570898648115803, "loss": 0.6092683792114257, "step": 200560 }, { "epoch": 1.192229731737908, "grad_norm": 1.4599945545196533, "learning_rate": 0.00015570362417361452, "loss": 0.5617338180541992, "step": 200570 }, { "epoch": 1.1922891738145764, "grad_norm": 1.5207511186599731, "learning_rate": 0.00015569826164743987, "loss": 0.5947908878326416, "step": 200580 }, { "epoch": 1.1923486158912449, "grad_norm": 1.2337820529937744, "learning_rate": 0.00015569289890265966, "loss": 0.6318169116973877, "step": 200590 }, { "epoch": 1.192408057967913, "grad_norm": 1.405618667602539, "learning_rate": 0.00015568753593929956, "loss": 0.5619347572326661, "step": 200600 }, { "epoch": 1.1924675000445815, "grad_norm": 1.4987980127334595, "learning_rate": 0.0001556821727573852, "loss": 0.6263452529907226, "step": 200610 }, { "epoch": 1.1925269421212499, "grad_norm": 1.6562467813491821, "learning_rate": 0.00015567680935694227, "loss": 0.6242791652679444, "step": 200620 }, { "epoch": 1.1925863841979183, "grad_norm": 1.6758408546447754, "learning_rate": 0.00015567144573799642, "loss": 0.6244442939758301, "step": 200630 }, { "epoch": 1.1926458262745867, "grad_norm": 1.3293815851211548, "learning_rate": 0.00015566608190057326, "loss": 0.5833105564117431, "step": 200640 }, { "epoch": 1.1927052683512551, "grad_norm": 1.7193301916122437, "learning_rate": 0.00015566071784469854, "loss": 0.56600341796875, "step": 200650 }, { "epoch": 1.1927647104279235, "grad_norm": 1.5870362520217896, "learning_rate": 0.00015565535357039785, "loss": 0.6149675369262695, "step": 200660 }, { "epoch": 1.192824152504592, "grad_norm": 1.54694664478302, "learning_rate": 0.00015564998907769686, "loss": 0.611792516708374, "step": 200670 }, { "epoch": 1.1928835945812604, "grad_norm": 1.487393856048584, "learning_rate": 0.00015564462436662123, "loss": 0.6006412029266357, "step": 200680 }, { "epoch": 1.1929430366579288, "grad_norm": 1.5103037357330322, "learning_rate": 0.00015563925943719664, "loss": 0.5703996658325196, "step": 200690 }, { "epoch": 1.1930024787345972, "grad_norm": 1.9128520488739014, "learning_rate": 0.00015563389428944875, "loss": 0.6048794746398926, "step": 200700 }, { "epoch": 1.1930619208112654, "grad_norm": 1.7494031190872192, "learning_rate": 0.00015562852892340325, "loss": 0.5971769332885742, "step": 200710 }, { "epoch": 1.1931213628879338, "grad_norm": 1.422255039215088, "learning_rate": 0.00015562316333908574, "loss": 0.6287396907806396, "step": 200720 }, { "epoch": 1.1931808049646022, "grad_norm": 1.205488681793213, "learning_rate": 0.00015561779753652194, "loss": 0.6373795509338379, "step": 200730 }, { "epoch": 1.1932402470412706, "grad_norm": 1.262634038925171, "learning_rate": 0.00015561243151573752, "loss": 0.6259838104248047, "step": 200740 }, { "epoch": 1.193299689117939, "grad_norm": 1.783361792564392, "learning_rate": 0.0001556070652767581, "loss": 0.6171193599700928, "step": 200750 }, { "epoch": 1.1933591311946075, "grad_norm": 1.710497260093689, "learning_rate": 0.00015560169881960944, "loss": 0.6564698219299316, "step": 200760 }, { "epoch": 1.1934185732712759, "grad_norm": 1.7084630727767944, "learning_rate": 0.00015559633214431713, "loss": 0.6234070777893066, "step": 200770 }, { "epoch": 1.1934780153479443, "grad_norm": 2.332206964492798, "learning_rate": 0.00015559096525090687, "loss": 0.6097352981567383, "step": 200780 }, { "epoch": 1.1935374574246125, "grad_norm": 1.3410286903381348, "learning_rate": 0.0001555855981394043, "loss": 0.6213382720947266, "step": 200790 }, { "epoch": 1.193596899501281, "grad_norm": 1.796082854270935, "learning_rate": 0.00015558023080983514, "loss": 0.5775659561157227, "step": 200800 }, { "epoch": 1.1936563415779493, "grad_norm": 2.1161882877349854, "learning_rate": 0.0001555748632622251, "loss": 0.5892640113830566, "step": 200810 }, { "epoch": 1.1937157836546177, "grad_norm": 1.5323798656463623, "learning_rate": 0.00015556949549659974, "loss": 0.6478723049163818, "step": 200820 }, { "epoch": 1.1937752257312861, "grad_norm": 1.4647732973098755, "learning_rate": 0.00015556412751298483, "loss": 0.6293624877929688, "step": 200830 }, { "epoch": 1.1938346678079546, "grad_norm": 1.5665156841278076, "learning_rate": 0.00015555875931140602, "loss": 0.6065603256225586, "step": 200840 }, { "epoch": 1.193894109884623, "grad_norm": 1.8248199224472046, "learning_rate": 0.000155553390891889, "loss": 0.6501987457275391, "step": 200850 }, { "epoch": 1.1939535519612914, "grad_norm": 1.2855967283248901, "learning_rate": 0.0001555480222544595, "loss": 0.6326972484588623, "step": 200860 }, { "epoch": 1.1940129940379598, "grad_norm": 1.3148632049560547, "learning_rate": 0.00015554265339914306, "loss": 0.6598376750946044, "step": 200870 }, { "epoch": 1.1940724361146282, "grad_norm": 2.1571121215820312, "learning_rate": 0.00015553728432596547, "loss": 0.5924581050872803, "step": 200880 }, { "epoch": 1.1941318781912964, "grad_norm": 1.5634102821350098, "learning_rate": 0.00015553191503495242, "loss": 0.6507243156433106, "step": 200890 }, { "epoch": 1.1941913202679648, "grad_norm": 1.7386574745178223, "learning_rate": 0.00015552654552612955, "loss": 0.632386302947998, "step": 200900 }, { "epoch": 1.1942507623446332, "grad_norm": 1.7328161001205444, "learning_rate": 0.00015552117579952258, "loss": 0.5796125888824463, "step": 200910 }, { "epoch": 1.1943102044213016, "grad_norm": 1.8173871040344238, "learning_rate": 0.00015551580585515716, "loss": 0.6030153751373291, "step": 200920 }, { "epoch": 1.19436964649797, "grad_norm": 1.4147493839263916, "learning_rate": 0.000155510435693059, "loss": 0.5674539566040039, "step": 200930 }, { "epoch": 1.1944290885746385, "grad_norm": 1.879386305809021, "learning_rate": 0.00015550506531325378, "loss": 0.5902109622955323, "step": 200940 }, { "epoch": 1.194488530651307, "grad_norm": 1.3382344245910645, "learning_rate": 0.00015549969471576725, "loss": 0.6052248001098632, "step": 200950 }, { "epoch": 1.1945479727279753, "grad_norm": 1.4850257635116577, "learning_rate": 0.00015549432390062502, "loss": 0.5933334350585937, "step": 200960 }, { "epoch": 1.1946074148046435, "grad_norm": 1.750608205795288, "learning_rate": 0.00015548895286785278, "loss": 0.6139131546020508, "step": 200970 }, { "epoch": 1.194666856881312, "grad_norm": 1.511767029762268, "learning_rate": 0.0001554835816174763, "loss": 0.61650071144104, "step": 200980 }, { "epoch": 1.1947262989579803, "grad_norm": 1.2740525007247925, "learning_rate": 0.00015547821014952123, "loss": 0.658962345123291, "step": 200990 }, { "epoch": 1.1947857410346487, "grad_norm": 1.5145885944366455, "learning_rate": 0.00015547283846401323, "loss": 0.6771235466003418, "step": 201000 }, { "epoch": 1.1948451831113172, "grad_norm": 1.8006439208984375, "learning_rate": 0.0001554674665609781, "loss": 0.6288917541503907, "step": 201010 }, { "epoch": 1.1949046251879856, "grad_norm": 1.5521899461746216, "learning_rate": 0.00015546209444044137, "loss": 0.6992305755615235, "step": 201020 }, { "epoch": 1.194964067264654, "grad_norm": 1.5000044107437134, "learning_rate": 0.0001554567221024289, "loss": 0.5705995559692383, "step": 201030 }, { "epoch": 1.1950235093413224, "grad_norm": 1.5113599300384521, "learning_rate": 0.00015545134954696632, "loss": 0.6529190540313721, "step": 201040 }, { "epoch": 1.1950829514179908, "grad_norm": 1.6437864303588867, "learning_rate": 0.00015544597677407936, "loss": 0.6774851322174072, "step": 201050 }, { "epoch": 1.1951423934946592, "grad_norm": 1.3693225383758545, "learning_rate": 0.00015544060378379365, "loss": 0.5882784366607666, "step": 201060 }, { "epoch": 1.1952018355713276, "grad_norm": 1.4483848810195923, "learning_rate": 0.00015543523057613497, "loss": 0.5845778942108154, "step": 201070 }, { "epoch": 1.1952612776479958, "grad_norm": 1.5047637224197388, "learning_rate": 0.00015542985715112897, "loss": 0.5941066741943359, "step": 201080 }, { "epoch": 1.1953207197246642, "grad_norm": 1.3955448865890503, "learning_rate": 0.00015542448350880145, "loss": 0.6567520141601563, "step": 201090 }, { "epoch": 1.1953801618013327, "grad_norm": 1.1704399585723877, "learning_rate": 0.00015541910964917793, "loss": 0.5916065692901611, "step": 201100 }, { "epoch": 1.195439603878001, "grad_norm": 1.5035114288330078, "learning_rate": 0.00015541373557228431, "loss": 0.6279747009277343, "step": 201110 }, { "epoch": 1.1954990459546695, "grad_norm": 2.0752761363983154, "learning_rate": 0.0001554083612781462, "loss": 0.636662769317627, "step": 201120 }, { "epoch": 1.195558488031338, "grad_norm": 1.3128142356872559, "learning_rate": 0.00015540298676678936, "loss": 0.653086519241333, "step": 201130 }, { "epoch": 1.1956179301080063, "grad_norm": 1.3855876922607422, "learning_rate": 0.00015539761203823947, "loss": 0.6065425872802734, "step": 201140 }, { "epoch": 1.1956773721846747, "grad_norm": 1.5576276779174805, "learning_rate": 0.0001553922370925222, "loss": 0.6080492973327637, "step": 201150 }, { "epoch": 1.195736814261343, "grad_norm": 1.819969654083252, "learning_rate": 0.0001553868619296633, "loss": 0.6380949497222901, "step": 201160 }, { "epoch": 1.1957962563380113, "grad_norm": 1.6196420192718506, "learning_rate": 0.00015538148654968851, "loss": 0.6181995391845703, "step": 201170 }, { "epoch": 1.1958556984146798, "grad_norm": 1.566213607788086, "learning_rate": 0.0001553761109526235, "loss": 0.5865712642669678, "step": 201180 }, { "epoch": 1.1959151404913482, "grad_norm": 1.3445570468902588, "learning_rate": 0.000155370735138494, "loss": 0.5796639442443847, "step": 201190 }, { "epoch": 1.1959745825680166, "grad_norm": 1.6578624248504639, "learning_rate": 0.00015536535910732577, "loss": 0.592906379699707, "step": 201200 }, { "epoch": 1.196034024644685, "grad_norm": 1.4602664709091187, "learning_rate": 0.00015535998285914448, "loss": 0.6085616111755371, "step": 201210 }, { "epoch": 1.1960934667213534, "grad_norm": 1.6504409313201904, "learning_rate": 0.00015535460639397582, "loss": 0.6641685962677002, "step": 201220 }, { "epoch": 1.1961529087980218, "grad_norm": 1.3637664318084717, "learning_rate": 0.00015534922971184557, "loss": 0.6534160614013672, "step": 201230 }, { "epoch": 1.1962123508746902, "grad_norm": 1.5347803831100464, "learning_rate": 0.0001553438528127794, "loss": 0.6411040782928467, "step": 201240 }, { "epoch": 1.1962717929513587, "grad_norm": 1.8931281566619873, "learning_rate": 0.00015533847569680308, "loss": 0.6466220855712891, "step": 201250 }, { "epoch": 1.1963312350280269, "grad_norm": 1.707968831062317, "learning_rate": 0.00015533309836394233, "loss": 0.6544499397277832, "step": 201260 }, { "epoch": 1.1963906771046953, "grad_norm": 1.4393293857574463, "learning_rate": 0.00015532772081422284, "loss": 0.5770043849945068, "step": 201270 }, { "epoch": 1.1964501191813637, "grad_norm": 1.2607461214065552, "learning_rate": 0.0001553223430476703, "loss": 0.6308495998382568, "step": 201280 }, { "epoch": 1.196509561258032, "grad_norm": 1.371381402015686, "learning_rate": 0.00015531696506431054, "loss": 0.647104549407959, "step": 201290 }, { "epoch": 1.1965690033347005, "grad_norm": 1.4500601291656494, "learning_rate": 0.00015531158686416923, "loss": 0.5398513317108155, "step": 201300 }, { "epoch": 1.196628445411369, "grad_norm": 1.2088031768798828, "learning_rate": 0.00015530620844727205, "loss": 0.5793943881988526, "step": 201310 }, { "epoch": 1.1966878874880373, "grad_norm": 1.2165415287017822, "learning_rate": 0.00015530082981364483, "loss": 0.5687596321105957, "step": 201320 }, { "epoch": 1.1967473295647058, "grad_norm": 1.7728779315948486, "learning_rate": 0.0001552954509633132, "loss": 0.6171436786651612, "step": 201330 }, { "epoch": 1.196806771641374, "grad_norm": 1.7504584789276123, "learning_rate": 0.00015529007189630294, "loss": 0.6360507488250733, "step": 201340 }, { "epoch": 1.1968662137180424, "grad_norm": 1.3267873525619507, "learning_rate": 0.0001552846926126398, "loss": 0.5813212394714355, "step": 201350 }, { "epoch": 1.1969256557947108, "grad_norm": 1.9938178062438965, "learning_rate": 0.00015527931311234945, "loss": 0.6079616546630859, "step": 201360 }, { "epoch": 1.1969850978713792, "grad_norm": 1.514784336090088, "learning_rate": 0.00015527393339545767, "loss": 0.6011168956756592, "step": 201370 }, { "epoch": 1.1970445399480476, "grad_norm": 1.6425939798355103, "learning_rate": 0.00015526855346199023, "loss": 0.6232328891754151, "step": 201380 }, { "epoch": 1.197103982024716, "grad_norm": 1.4528335332870483, "learning_rate": 0.00015526317331197279, "loss": 0.5761498928070068, "step": 201390 }, { "epoch": 1.1971634241013844, "grad_norm": 1.7904096841812134, "learning_rate": 0.00015525779294543114, "loss": 0.5246030330657959, "step": 201400 }, { "epoch": 1.1972228661780528, "grad_norm": 1.6656244993209839, "learning_rate": 0.000155252412362391, "loss": 0.5684661388397216, "step": 201410 }, { "epoch": 1.1972823082547213, "grad_norm": 1.3580507040023804, "learning_rate": 0.0001552470315628781, "loss": 0.5685749053955078, "step": 201420 }, { "epoch": 1.1973417503313897, "grad_norm": 1.5144555568695068, "learning_rate": 0.00015524165054691817, "loss": 0.6273755550384521, "step": 201430 }, { "epoch": 1.197401192408058, "grad_norm": 1.6198487281799316, "learning_rate": 0.00015523626931453698, "loss": 0.5748832702636719, "step": 201440 }, { "epoch": 1.1974606344847263, "grad_norm": 1.458206057548523, "learning_rate": 0.0001552308878657603, "loss": 0.6231575012207031, "step": 201450 }, { "epoch": 1.1975200765613947, "grad_norm": 1.6520816087722778, "learning_rate": 0.00015522550620061378, "loss": 0.6184234142303466, "step": 201460 }, { "epoch": 1.1975795186380631, "grad_norm": 1.6740458011627197, "learning_rate": 0.00015522012431912324, "loss": 0.606143569946289, "step": 201470 }, { "epoch": 1.1976389607147315, "grad_norm": 1.7194088697433472, "learning_rate": 0.00015521474222131442, "loss": 0.6402215003967285, "step": 201480 }, { "epoch": 1.1976984027914, "grad_norm": 1.3328819274902344, "learning_rate": 0.000155209359907213, "loss": 0.579158878326416, "step": 201490 }, { "epoch": 1.1977578448680684, "grad_norm": 1.6628696918487549, "learning_rate": 0.00015520397737684485, "loss": 0.6296136856079102, "step": 201500 }, { "epoch": 1.1978172869447368, "grad_norm": 1.3706218004226685, "learning_rate": 0.0001551985946302356, "loss": 0.5985829830169678, "step": 201510 }, { "epoch": 1.1978767290214052, "grad_norm": 1.7220635414123535, "learning_rate": 0.00015519321166741103, "loss": 0.5916319370269776, "step": 201520 }, { "epoch": 1.1979361710980734, "grad_norm": 1.5594512224197388, "learning_rate": 0.00015518782848839694, "loss": 0.635966682434082, "step": 201530 }, { "epoch": 1.1979956131747418, "grad_norm": 1.4083209037780762, "learning_rate": 0.00015518244509321903, "loss": 0.5673402786254883, "step": 201540 }, { "epoch": 1.1980550552514102, "grad_norm": 0.9750536680221558, "learning_rate": 0.00015517706148190306, "loss": 0.6037619590759278, "step": 201550 }, { "epoch": 1.1981144973280786, "grad_norm": 1.5838490724563599, "learning_rate": 0.00015517167765447478, "loss": 0.6286261558532715, "step": 201560 }, { "epoch": 1.198173939404747, "grad_norm": 1.31165611743927, "learning_rate": 0.00015516629361096, "loss": 0.6135535717010498, "step": 201570 }, { "epoch": 1.1982333814814154, "grad_norm": 1.4775923490524292, "learning_rate": 0.00015516090935138442, "loss": 0.6263167381286621, "step": 201580 }, { "epoch": 1.1982928235580839, "grad_norm": 1.5040127038955688, "learning_rate": 0.00015515552487577376, "loss": 0.5947881698608398, "step": 201590 }, { "epoch": 1.1983522656347523, "grad_norm": 1.503280758857727, "learning_rate": 0.0001551501401841539, "loss": 0.634002685546875, "step": 201600 }, { "epoch": 1.1984117077114207, "grad_norm": 1.542751669883728, "learning_rate": 0.00015514475527655047, "loss": 0.544407844543457, "step": 201610 }, { "epoch": 1.198471149788089, "grad_norm": 1.7050845623016357, "learning_rate": 0.0001551393701529893, "loss": 0.6362370014190674, "step": 201620 }, { "epoch": 1.1985305918647573, "grad_norm": 1.6618726253509521, "learning_rate": 0.00015513398481349614, "loss": 0.6323310375213623, "step": 201630 }, { "epoch": 1.1985900339414257, "grad_norm": 1.250686526298523, "learning_rate": 0.00015512859925809674, "loss": 0.6286064147949219, "step": 201640 }, { "epoch": 1.1986494760180941, "grad_norm": 1.7024493217468262, "learning_rate": 0.00015512321348681686, "loss": 0.5937005043029785, "step": 201650 }, { "epoch": 1.1987089180947625, "grad_norm": 1.7511484622955322, "learning_rate": 0.0001551178274996823, "loss": 0.6687210083007813, "step": 201660 }, { "epoch": 1.198768360171431, "grad_norm": 1.5032556056976318, "learning_rate": 0.00015511244129671876, "loss": 0.6434444427490235, "step": 201670 }, { "epoch": 1.1988278022480994, "grad_norm": 3.782017707824707, "learning_rate": 0.00015510705487795204, "loss": 0.560356855392456, "step": 201680 }, { "epoch": 1.1988872443247678, "grad_norm": 1.6668574810028076, "learning_rate": 0.000155101668243408, "loss": 0.5711148738861084, "step": 201690 }, { "epoch": 1.1989466864014362, "grad_norm": 1.4519257545471191, "learning_rate": 0.00015509628139311223, "loss": 0.5998365402221679, "step": 201700 }, { "epoch": 1.1990061284781044, "grad_norm": 1.662530779838562, "learning_rate": 0.00015509089432709064, "loss": 0.6248770236968995, "step": 201710 }, { "epoch": 1.1990655705547728, "grad_norm": 1.3535794019699097, "learning_rate": 0.00015508550704536892, "loss": 0.5786061763763428, "step": 201720 }, { "epoch": 1.1991250126314412, "grad_norm": 1.3851646184921265, "learning_rate": 0.00015508011954797285, "loss": 0.6189255714416504, "step": 201730 }, { "epoch": 1.1991844547081096, "grad_norm": 1.64156174659729, "learning_rate": 0.00015507473183492822, "loss": 0.6870142936706543, "step": 201740 }, { "epoch": 1.199243896784778, "grad_norm": 1.7066261768341064, "learning_rate": 0.00015506934390626084, "loss": 0.593869400024414, "step": 201750 }, { "epoch": 1.1993033388614465, "grad_norm": 1.3367060422897339, "learning_rate": 0.00015506395576199644, "loss": 0.6109334468841553, "step": 201760 }, { "epoch": 1.1993627809381149, "grad_norm": 1.4935276508331299, "learning_rate": 0.00015505856740216076, "loss": 0.6021891593933105, "step": 201770 }, { "epoch": 1.1994222230147833, "grad_norm": 1.8309646844863892, "learning_rate": 0.00015505317882677969, "loss": 0.6661819458007813, "step": 201780 }, { "epoch": 1.1994816650914517, "grad_norm": 1.8435665369033813, "learning_rate": 0.00015504779003587887, "loss": 0.6786887168884277, "step": 201790 }, { "epoch": 1.1995411071681201, "grad_norm": 1.7135945558547974, "learning_rate": 0.00015504240102948418, "loss": 0.6068629264831543, "step": 201800 }, { "epoch": 1.1996005492447885, "grad_norm": 1.5037778615951538, "learning_rate": 0.00015503701180762138, "loss": 0.6226462841033935, "step": 201810 }, { "epoch": 1.1996599913214567, "grad_norm": 1.655135989189148, "learning_rate": 0.0001550316223703162, "loss": 0.637612247467041, "step": 201820 }, { "epoch": 1.1997194333981251, "grad_norm": 1.4990592002868652, "learning_rate": 0.00015502623271759444, "loss": 0.6129930019378662, "step": 201830 }, { "epoch": 1.1997788754747936, "grad_norm": 1.2994190454483032, "learning_rate": 0.00015502084284948196, "loss": 0.5982228279113769, "step": 201840 }, { "epoch": 1.199838317551462, "grad_norm": 1.6011868715286255, "learning_rate": 0.00015501545276600445, "loss": 0.6796551704406738, "step": 201850 }, { "epoch": 1.1998977596281304, "grad_norm": 1.636806607246399, "learning_rate": 0.00015501006246718767, "loss": 0.5892501831054687, "step": 201860 }, { "epoch": 1.1999572017047988, "grad_norm": 2.0013294219970703, "learning_rate": 0.0001550046719530575, "loss": 0.6470291137695312, "step": 201870 }, { "epoch": 1.2000166437814672, "grad_norm": 1.4965300559997559, "learning_rate": 0.0001549992812236397, "loss": 0.604690408706665, "step": 201880 }, { "epoch": 1.2000760858581356, "grad_norm": 1.769237756729126, "learning_rate": 0.00015499389027896006, "loss": 0.6085936546325683, "step": 201890 }, { "epoch": 1.2001355279348038, "grad_norm": 1.3133021593093872, "learning_rate": 0.00015498849911904433, "loss": 0.6464426040649414, "step": 201900 }, { "epoch": 1.2001949700114722, "grad_norm": 1.6639755964279175, "learning_rate": 0.00015498310774391834, "loss": 0.7105012893676758, "step": 201910 }, { "epoch": 1.2002544120881407, "grad_norm": 1.4248558282852173, "learning_rate": 0.00015497771615360784, "loss": 0.6182392597198486, "step": 201920 }, { "epoch": 1.200313854164809, "grad_norm": 1.6397285461425781, "learning_rate": 0.00015497232434813864, "loss": 0.5932077407836914, "step": 201930 }, { "epoch": 1.2003732962414775, "grad_norm": 1.569177269935608, "learning_rate": 0.00015496693232753658, "loss": 0.603649377822876, "step": 201940 }, { "epoch": 1.200432738318146, "grad_norm": 1.3921629190444946, "learning_rate": 0.00015496154009182736, "loss": 0.6397359848022461, "step": 201950 }, { "epoch": 1.2004921803948143, "grad_norm": 1.801114797592163, "learning_rate": 0.00015495614764103683, "loss": 0.6148137092590332, "step": 201960 }, { "epoch": 1.2005516224714827, "grad_norm": 1.8359947204589844, "learning_rate": 0.00015495075497519084, "loss": 0.6165613174438477, "step": 201970 }, { "epoch": 1.2006110645481511, "grad_norm": 1.2552964687347412, "learning_rate": 0.00015494536209431506, "loss": 0.5782933235168457, "step": 201980 }, { "epoch": 1.2006705066248196, "grad_norm": 2.1561014652252197, "learning_rate": 0.00015493996899843538, "loss": 0.5952404975891114, "step": 201990 }, { "epoch": 1.2007299487014877, "grad_norm": 2.136477470397949, "learning_rate": 0.00015493457568757762, "loss": 0.6363829135894775, "step": 202000 }, { "epoch": 1.2007893907781562, "grad_norm": 1.278148889541626, "learning_rate": 0.00015492918216176746, "loss": 0.6466574192047119, "step": 202010 }, { "epoch": 1.2008488328548246, "grad_norm": 1.619136095046997, "learning_rate": 0.0001549237884210308, "loss": 0.6695006370544434, "step": 202020 }, { "epoch": 1.200908274931493, "grad_norm": 1.7573963403701782, "learning_rate": 0.00015491839446539346, "loss": 0.6303057193756103, "step": 202030 }, { "epoch": 1.2009677170081614, "grad_norm": 1.6184309720993042, "learning_rate": 0.00015491300029488116, "loss": 0.6079679965972901, "step": 202040 }, { "epoch": 1.2010271590848298, "grad_norm": 1.224809169769287, "learning_rate": 0.00015490760590951977, "loss": 0.623518705368042, "step": 202050 }, { "epoch": 1.2010866011614982, "grad_norm": 1.6812156438827515, "learning_rate": 0.00015490221130933505, "loss": 0.6141544342041015, "step": 202060 }, { "epoch": 1.2011460432381666, "grad_norm": 0.9159267544746399, "learning_rate": 0.0001548968164943528, "loss": 0.5685378551483155, "step": 202070 }, { "epoch": 1.2012054853148348, "grad_norm": 1.7123134136199951, "learning_rate": 0.00015489142146459886, "loss": 0.5585608959197998, "step": 202080 }, { "epoch": 1.2012649273915033, "grad_norm": 2.079364776611328, "learning_rate": 0.00015488602622009906, "loss": 0.5608982086181641, "step": 202090 }, { "epoch": 1.2013243694681717, "grad_norm": 1.4359887838363647, "learning_rate": 0.0001548806307608792, "loss": 0.6034279823303222, "step": 202100 }, { "epoch": 1.20138381154484, "grad_norm": 1.3380438089370728, "learning_rate": 0.000154875235086965, "loss": 0.5878287315368652, "step": 202110 }, { "epoch": 1.2014432536215085, "grad_norm": 0.9873372316360474, "learning_rate": 0.00015486983919838239, "loss": 0.6321730136871337, "step": 202120 }, { "epoch": 1.201502695698177, "grad_norm": 1.6977721452713013, "learning_rate": 0.00015486444309515714, "loss": 0.6172807216644287, "step": 202130 }, { "epoch": 1.2015621377748453, "grad_norm": 1.481000542640686, "learning_rate": 0.00015485904677731502, "loss": 0.6083282470703125, "step": 202140 }, { "epoch": 1.2016215798515137, "grad_norm": 1.3567419052124023, "learning_rate": 0.0001548536502448819, "loss": 0.5856593132019043, "step": 202150 }, { "epoch": 1.2016810219281822, "grad_norm": 1.6613191366195679, "learning_rate": 0.00015484825349788357, "loss": 0.5797459602355957, "step": 202160 }, { "epoch": 1.2017404640048506, "grad_norm": 1.4189704656600952, "learning_rate": 0.00015484285653634587, "loss": 0.5747956752777099, "step": 202170 }, { "epoch": 1.201799906081519, "grad_norm": 1.4134377241134644, "learning_rate": 0.0001548374593602946, "loss": 0.6155325889587402, "step": 202180 }, { "epoch": 1.2018593481581872, "grad_norm": 1.3186237812042236, "learning_rate": 0.00015483206196975554, "loss": 0.6285501480102539, "step": 202190 }, { "epoch": 1.2019187902348556, "grad_norm": 1.5549535751342773, "learning_rate": 0.00015482666436475456, "loss": 0.5978713989257812, "step": 202200 }, { "epoch": 1.201978232311524, "grad_norm": 1.1591955423355103, "learning_rate": 0.0001548212665453175, "loss": 0.6483772754669189, "step": 202210 }, { "epoch": 1.2020376743881924, "grad_norm": 1.6851483583450317, "learning_rate": 0.0001548158685114701, "loss": 0.6319879531860352, "step": 202220 }, { "epoch": 1.2020971164648608, "grad_norm": 1.519394040107727, "learning_rate": 0.00015481047026323828, "loss": 0.6872483730316162, "step": 202230 }, { "epoch": 1.2021565585415293, "grad_norm": 1.5859235525131226, "learning_rate": 0.00015480507180064778, "loss": 0.6198790550231934, "step": 202240 }, { "epoch": 1.2022160006181977, "grad_norm": 1.7179604768753052, "learning_rate": 0.00015479967312372446, "loss": 0.5931488990783691, "step": 202250 }, { "epoch": 1.202275442694866, "grad_norm": 1.4243351221084595, "learning_rate": 0.00015479427423249414, "loss": 0.6837852954864502, "step": 202260 }, { "epoch": 1.2023348847715343, "grad_norm": 3.56601881980896, "learning_rate": 0.00015478887512698268, "loss": 0.6470118522644043, "step": 202270 }, { "epoch": 1.2023943268482027, "grad_norm": 1.4472469091415405, "learning_rate": 0.00015478347580721586, "loss": 0.6327017784118653, "step": 202280 }, { "epoch": 1.202453768924871, "grad_norm": 1.7929959297180176, "learning_rate": 0.00015477807627321954, "loss": 0.6461055755615235, "step": 202290 }, { "epoch": 1.2025132110015395, "grad_norm": 1.539921522140503, "learning_rate": 0.00015477267652501953, "loss": 0.6758098602294922, "step": 202300 }, { "epoch": 1.202572653078208, "grad_norm": 1.405214548110962, "learning_rate": 0.00015476727656264167, "loss": 0.5748595237731934, "step": 202310 }, { "epoch": 1.2026320951548763, "grad_norm": 1.648681879043579, "learning_rate": 0.00015476187638611177, "loss": 0.6471024513244629, "step": 202320 }, { "epoch": 1.2026915372315448, "grad_norm": 1.7595094442367554, "learning_rate": 0.0001547564759954557, "loss": 0.6219527244567871, "step": 202330 }, { "epoch": 1.2027509793082132, "grad_norm": 1.455479621887207, "learning_rate": 0.00015475107539069925, "loss": 0.5720271110534668, "step": 202340 }, { "epoch": 1.2028104213848816, "grad_norm": 1.770333170890808, "learning_rate": 0.0001547456745718683, "loss": 0.6420621871948242, "step": 202350 }, { "epoch": 1.20286986346155, "grad_norm": 1.2693451642990112, "learning_rate": 0.0001547402735389887, "loss": 0.684146499633789, "step": 202360 }, { "epoch": 1.2029293055382182, "grad_norm": 1.3002480268478394, "learning_rate": 0.00015473487229208618, "loss": 0.585103702545166, "step": 202370 }, { "epoch": 1.2029887476148866, "grad_norm": 1.5578268766403198, "learning_rate": 0.00015472947083118672, "loss": 0.638297700881958, "step": 202380 }, { "epoch": 1.203048189691555, "grad_norm": 1.4702597856521606, "learning_rate": 0.00015472406915631603, "loss": 0.6128991127014161, "step": 202390 }, { "epoch": 1.2031076317682234, "grad_norm": 1.334889531135559, "learning_rate": 0.00015471866726750005, "loss": 0.6058919429779053, "step": 202400 }, { "epoch": 1.2031670738448919, "grad_norm": 1.867466926574707, "learning_rate": 0.00015471326516476456, "loss": 0.6018714904785156, "step": 202410 }, { "epoch": 1.2032265159215603, "grad_norm": 1.3455960750579834, "learning_rate": 0.00015470786284813544, "loss": 0.59111008644104, "step": 202420 }, { "epoch": 1.2032859579982287, "grad_norm": 1.5664288997650146, "learning_rate": 0.0001547024603176385, "loss": 0.6289953231811524, "step": 202430 }, { "epoch": 1.203345400074897, "grad_norm": 1.4788166284561157, "learning_rate": 0.0001546970575732996, "loss": 0.6070865631103516, "step": 202440 }, { "epoch": 1.2034048421515653, "grad_norm": 1.505000352859497, "learning_rate": 0.00015469165461514458, "loss": 0.6193596363067627, "step": 202450 }, { "epoch": 1.2034642842282337, "grad_norm": 1.535758376121521, "learning_rate": 0.0001546862514431993, "loss": 0.6185573101043701, "step": 202460 }, { "epoch": 1.2035237263049021, "grad_norm": 1.6734983921051025, "learning_rate": 0.00015468084805748958, "loss": 0.6547901153564453, "step": 202470 }, { "epoch": 1.2035831683815705, "grad_norm": 1.6428260803222656, "learning_rate": 0.0001546754444580413, "loss": 0.5805434703826904, "step": 202480 }, { "epoch": 1.203642610458239, "grad_norm": 1.4133176803588867, "learning_rate": 0.00015467004064488032, "loss": 0.5782932758331298, "step": 202490 }, { "epoch": 1.2037020525349074, "grad_norm": 1.1044113636016846, "learning_rate": 0.00015466463661803243, "loss": 0.5961255073547364, "step": 202500 }, { "epoch": 1.2037614946115758, "grad_norm": 1.659153938293457, "learning_rate": 0.00015465923237752353, "loss": 0.6092296600341797, "step": 202510 }, { "epoch": 1.2038209366882442, "grad_norm": 1.1423490047454834, "learning_rate": 0.00015465382792337944, "loss": 0.6401695728302002, "step": 202520 }, { "epoch": 1.2038803787649126, "grad_norm": 1.861733317375183, "learning_rate": 0.00015464842325562606, "loss": 0.6146474838256836, "step": 202530 }, { "epoch": 1.203939820841581, "grad_norm": 1.5756962299346924, "learning_rate": 0.0001546430183742892, "loss": 0.5967080116271972, "step": 202540 }, { "epoch": 1.2039992629182494, "grad_norm": 1.8651310205459595, "learning_rate": 0.0001546376132793947, "loss": 0.6297008991241455, "step": 202550 }, { "epoch": 1.2040587049949176, "grad_norm": 1.8082219362258911, "learning_rate": 0.0001546322079709685, "loss": 0.6010462760925293, "step": 202560 }, { "epoch": 1.204118147071586, "grad_norm": 1.5061731338500977, "learning_rate": 0.00015462680244903633, "loss": 0.6335453987121582, "step": 202570 }, { "epoch": 1.2041775891482545, "grad_norm": 1.5564640760421753, "learning_rate": 0.00015462139671362416, "loss": 0.6572037696838379, "step": 202580 }, { "epoch": 1.2042370312249229, "grad_norm": 1.9229462146759033, "learning_rate": 0.00015461599076475784, "loss": 0.6236257553100586, "step": 202590 }, { "epoch": 1.2042964733015913, "grad_norm": 1.46310555934906, "learning_rate": 0.00015461058460246313, "loss": 0.5422952175140381, "step": 202600 }, { "epoch": 1.2043559153782597, "grad_norm": 1.6820498704910278, "learning_rate": 0.00015460517822676604, "loss": 0.6413109779357911, "step": 202610 }, { "epoch": 1.2044153574549281, "grad_norm": 1.7672004699707031, "learning_rate": 0.00015459977163769233, "loss": 0.6702225208282471, "step": 202620 }, { "epoch": 1.2044747995315965, "grad_norm": 1.348383903503418, "learning_rate": 0.00015459436483526785, "loss": 0.5984440326690674, "step": 202630 }, { "epoch": 1.2045342416082647, "grad_norm": 1.299490213394165, "learning_rate": 0.00015458895781951854, "loss": 0.6069322109222413, "step": 202640 }, { "epoch": 1.2045936836849331, "grad_norm": 2.0327746868133545, "learning_rate": 0.00015458355059047024, "loss": 0.6415796279907227, "step": 202650 }, { "epoch": 1.2046531257616016, "grad_norm": 1.4329544305801392, "learning_rate": 0.00015457814314814877, "loss": 0.5740448951721191, "step": 202660 }, { "epoch": 1.20471256783827, "grad_norm": 1.9316853284835815, "learning_rate": 0.00015457273549258004, "loss": 0.6224678039550782, "step": 202670 }, { "epoch": 1.2047720099149384, "grad_norm": 1.3813554048538208, "learning_rate": 0.00015456732762378993, "loss": 0.587095832824707, "step": 202680 }, { "epoch": 1.2048314519916068, "grad_norm": 1.6602835655212402, "learning_rate": 0.00015456191954180427, "loss": 0.6255212783813476, "step": 202690 }, { "epoch": 1.2048908940682752, "grad_norm": 1.207490086555481, "learning_rate": 0.00015455651124664894, "loss": 0.5428802490234375, "step": 202700 }, { "epoch": 1.2049503361449436, "grad_norm": 1.765310287475586, "learning_rate": 0.00015455110273834984, "loss": 0.6023844242095947, "step": 202710 }, { "epoch": 1.205009778221612, "grad_norm": 1.6425323486328125, "learning_rate": 0.0001545456940169328, "loss": 0.6563166618347168, "step": 202720 }, { "epoch": 1.2050692202982805, "grad_norm": 1.6011143922805786, "learning_rate": 0.00015454028508242373, "loss": 0.573942232131958, "step": 202730 }, { "epoch": 1.2051286623749486, "grad_norm": 1.5398772954940796, "learning_rate": 0.00015453487593484853, "loss": 0.629392433166504, "step": 202740 }, { "epoch": 1.205188104451617, "grad_norm": 1.709403395652771, "learning_rate": 0.00015452946657423298, "loss": 0.6906953811645508, "step": 202750 }, { "epoch": 1.2052475465282855, "grad_norm": 1.6962823867797852, "learning_rate": 0.00015452405700060304, "loss": 0.6456774711608887, "step": 202760 }, { "epoch": 1.2053069886049539, "grad_norm": 1.2949867248535156, "learning_rate": 0.00015451864721398458, "loss": 0.5830487251281739, "step": 202770 }, { "epoch": 1.2053664306816223, "grad_norm": 1.2304227352142334, "learning_rate": 0.00015451323721440342, "loss": 0.6681827545166016, "step": 202780 }, { "epoch": 1.2054258727582907, "grad_norm": 1.5132721662521362, "learning_rate": 0.00015450782700188553, "loss": 0.6150211811065673, "step": 202790 }, { "epoch": 1.2054853148349591, "grad_norm": 1.612325668334961, "learning_rate": 0.00015450241657645673, "loss": 0.6012630462646484, "step": 202800 }, { "epoch": 1.2055447569116275, "grad_norm": 1.687973976135254, "learning_rate": 0.00015449700593814288, "loss": 0.5905771255493164, "step": 202810 }, { "epoch": 1.2056041989882957, "grad_norm": 1.4693514108657837, "learning_rate": 0.0001544915950869699, "loss": 0.6181845664978027, "step": 202820 }, { "epoch": 1.2056636410649642, "grad_norm": 1.7181174755096436, "learning_rate": 0.00015448618402296368, "loss": 0.614785099029541, "step": 202830 }, { "epoch": 1.2057230831416326, "grad_norm": 1.6727889776229858, "learning_rate": 0.0001544807727461501, "loss": 0.5800904273986817, "step": 202840 }, { "epoch": 1.205782525218301, "grad_norm": 1.6398563385009766, "learning_rate": 0.00015447536125655505, "loss": 0.6102847576141357, "step": 202850 }, { "epoch": 1.2058419672949694, "grad_norm": 1.4744397401809692, "learning_rate": 0.00015446994955420438, "loss": 0.5741545677185058, "step": 202860 }, { "epoch": 1.2059014093716378, "grad_norm": 1.4772073030471802, "learning_rate": 0.00015446453763912402, "loss": 0.5863945007324218, "step": 202870 }, { "epoch": 1.2059608514483062, "grad_norm": 1.5804574489593506, "learning_rate": 0.00015445912551133984, "loss": 0.6801509857177734, "step": 202880 }, { "epoch": 1.2060202935249746, "grad_norm": 2.093569040298462, "learning_rate": 0.00015445371317087772, "loss": 0.6066262245178222, "step": 202890 }, { "epoch": 1.206079735601643, "grad_norm": 1.5206794738769531, "learning_rate": 0.00015444830061776357, "loss": 0.5980365753173829, "step": 202900 }, { "epoch": 1.2061391776783115, "grad_norm": 1.4902420043945312, "learning_rate": 0.0001544428878520233, "loss": 0.6227196216583252, "step": 202910 }, { "epoch": 1.2061986197549799, "grad_norm": 1.2236183881759644, "learning_rate": 0.00015443747487368277, "loss": 0.5992570877075195, "step": 202920 }, { "epoch": 1.206258061831648, "grad_norm": 1.7689344882965088, "learning_rate": 0.00015443206168276784, "loss": 0.6353792190551758, "step": 202930 }, { "epoch": 1.2063175039083165, "grad_norm": 1.3419392108917236, "learning_rate": 0.0001544266482793045, "loss": 0.5375613212585449, "step": 202940 }, { "epoch": 1.206376945984985, "grad_norm": 1.241136074066162, "learning_rate": 0.00015442123466331858, "loss": 0.6322595596313476, "step": 202950 }, { "epoch": 1.2064363880616533, "grad_norm": 1.5631738901138306, "learning_rate": 0.00015441582083483595, "loss": 0.6539544105529785, "step": 202960 }, { "epoch": 1.2064958301383217, "grad_norm": 1.3961986303329468, "learning_rate": 0.00015441040679388258, "loss": 0.5856708526611328, "step": 202970 }, { "epoch": 1.2065552722149901, "grad_norm": 1.3600043058395386, "learning_rate": 0.00015440499254048434, "loss": 0.6079534530639649, "step": 202980 }, { "epoch": 1.2066147142916586, "grad_norm": 1.487021565437317, "learning_rate": 0.00015439957807466715, "loss": 0.6250332355499267, "step": 202990 }, { "epoch": 1.206674156368327, "grad_norm": 2.018367290496826, "learning_rate": 0.00015439416339645685, "loss": 0.6252663612365723, "step": 203000 }, { "epoch": 1.2067335984449952, "grad_norm": 1.3924307823181152, "learning_rate": 0.00015438874850587942, "loss": 0.6439446449279785, "step": 203010 }, { "epoch": 1.2067930405216636, "grad_norm": 1.456327199935913, "learning_rate": 0.00015438333340296066, "loss": 0.6529915809631348, "step": 203020 }, { "epoch": 1.206852482598332, "grad_norm": 1.4339338541030884, "learning_rate": 0.0001543779180877266, "loss": 0.630012035369873, "step": 203030 }, { "epoch": 1.2069119246750004, "grad_norm": 1.2730296850204468, "learning_rate": 0.00015437250256020307, "loss": 0.6230657577514649, "step": 203040 }, { "epoch": 1.2069713667516688, "grad_norm": 1.2548151016235352, "learning_rate": 0.00015436708682041596, "loss": 0.5345006942749023, "step": 203050 }, { "epoch": 1.2070308088283372, "grad_norm": 1.3895046710968018, "learning_rate": 0.00015436167086839122, "loss": 0.6552347660064697, "step": 203060 }, { "epoch": 1.2070902509050057, "grad_norm": 1.2007876634597778, "learning_rate": 0.00015435625470415476, "loss": 0.5844169139862061, "step": 203070 }, { "epoch": 1.207149692981674, "grad_norm": 1.8648887872695923, "learning_rate": 0.00015435083832773244, "loss": 0.584578275680542, "step": 203080 }, { "epoch": 1.2072091350583425, "grad_norm": 1.6792291402816772, "learning_rate": 0.00015434542173915024, "loss": 0.6364025592803955, "step": 203090 }, { "epoch": 1.207268577135011, "grad_norm": 1.4301332235336304, "learning_rate": 0.000154340004938434, "loss": 0.5815396308898926, "step": 203100 }, { "epoch": 1.207328019211679, "grad_norm": 2.009291887283325, "learning_rate": 0.0001543345879256097, "loss": 0.6180395126342774, "step": 203110 }, { "epoch": 1.2073874612883475, "grad_norm": 1.5785808563232422, "learning_rate": 0.00015432917070070323, "loss": 0.5869391441345215, "step": 203120 }, { "epoch": 1.207446903365016, "grad_norm": 1.4160802364349365, "learning_rate": 0.00015432375326374044, "loss": 0.6059505462646484, "step": 203130 }, { "epoch": 1.2075063454416843, "grad_norm": 2.0785322189331055, "learning_rate": 0.00015431833561474736, "loss": 0.5907526969909668, "step": 203140 }, { "epoch": 1.2075657875183528, "grad_norm": 1.3324326276779175, "learning_rate": 0.0001543129177537498, "loss": 0.6371557235717773, "step": 203150 }, { "epoch": 1.2076252295950212, "grad_norm": 1.5478943586349487, "learning_rate": 0.00015430749968077374, "loss": 0.6582624435424804, "step": 203160 }, { "epoch": 1.2076846716716896, "grad_norm": 1.4144796133041382, "learning_rate": 0.0001543020813958451, "loss": 0.6239099502563477, "step": 203170 }, { "epoch": 1.207744113748358, "grad_norm": 1.553192377090454, "learning_rate": 0.00015429666289898974, "loss": 0.6526169300079345, "step": 203180 }, { "epoch": 1.2078035558250262, "grad_norm": 1.4462568759918213, "learning_rate": 0.00015429124419023363, "loss": 0.6174407958984375, "step": 203190 }, { "epoch": 1.2078629979016946, "grad_norm": 1.4191977977752686, "learning_rate": 0.0001542858252696027, "loss": 0.6441305160522461, "step": 203200 }, { "epoch": 1.207922439978363, "grad_norm": 1.185643196105957, "learning_rate": 0.00015428040613712287, "loss": 0.5768363952636719, "step": 203210 }, { "epoch": 1.2079818820550314, "grad_norm": 1.3954306840896606, "learning_rate": 0.00015427498679282, "loss": 0.5452387809753418, "step": 203220 }, { "epoch": 1.2080413241316998, "grad_norm": 1.4483033418655396, "learning_rate": 0.00015426956723672012, "loss": 0.612246036529541, "step": 203230 }, { "epoch": 1.2081007662083683, "grad_norm": 1.5491918325424194, "learning_rate": 0.00015426414746884905, "loss": 0.5948822021484375, "step": 203240 }, { "epoch": 1.2081602082850367, "grad_norm": 1.0896594524383545, "learning_rate": 0.00015425872748923278, "loss": 0.6076147079467773, "step": 203250 }, { "epoch": 1.208219650361705, "grad_norm": 1.0802260637283325, "learning_rate": 0.00015425330729789725, "loss": 0.5290483474731446, "step": 203260 }, { "epoch": 1.2082790924383735, "grad_norm": 1.8262518644332886, "learning_rate": 0.0001542478868948683, "loss": 0.6372524738311768, "step": 203270 }, { "epoch": 1.208338534515042, "grad_norm": 1.9373942613601685, "learning_rate": 0.00015424246628017196, "loss": 0.617803955078125, "step": 203280 }, { "epoch": 1.2083979765917103, "grad_norm": 1.7496118545532227, "learning_rate": 0.00015423704545383413, "loss": 0.5974693298339844, "step": 203290 }, { "epoch": 1.2084574186683785, "grad_norm": 1.7830264568328857, "learning_rate": 0.00015423162441588072, "loss": 0.6366081714630127, "step": 203300 }, { "epoch": 1.208516860745047, "grad_norm": 1.61831533908844, "learning_rate": 0.00015422620316633766, "loss": 0.5717850208282471, "step": 203310 }, { "epoch": 1.2085763028217154, "grad_norm": 1.5777639150619507, "learning_rate": 0.0001542207817052309, "loss": 0.6527953147888184, "step": 203320 }, { "epoch": 1.2086357448983838, "grad_norm": 1.7027250528335571, "learning_rate": 0.0001542153600325864, "loss": 0.596028470993042, "step": 203330 }, { "epoch": 1.2086951869750522, "grad_norm": 1.5757256746292114, "learning_rate": 0.00015420993814843002, "loss": 0.5752743721008301, "step": 203340 }, { "epoch": 1.2087546290517206, "grad_norm": 1.712433099746704, "learning_rate": 0.00015420451605278776, "loss": 0.6546785354614257, "step": 203350 }, { "epoch": 1.208814071128389, "grad_norm": 1.6709076166152954, "learning_rate": 0.00015419909374568558, "loss": 0.6347683906555176, "step": 203360 }, { "epoch": 1.2088735132050574, "grad_norm": 1.4793503284454346, "learning_rate": 0.0001541936712271493, "loss": 0.5814372539520264, "step": 203370 }, { "epoch": 1.2089329552817256, "grad_norm": 1.5732696056365967, "learning_rate": 0.000154188248497205, "loss": 0.5691077232360839, "step": 203380 }, { "epoch": 1.208992397358394, "grad_norm": 2.5859389305114746, "learning_rate": 0.00015418282555587856, "loss": 0.6422875404357911, "step": 203390 }, { "epoch": 1.2090518394350624, "grad_norm": 2.0208215713500977, "learning_rate": 0.00015417740240319591, "loss": 0.6336322784423828, "step": 203400 }, { "epoch": 1.2091112815117309, "grad_norm": 1.4176318645477295, "learning_rate": 0.00015417197903918302, "loss": 0.5923885345458985, "step": 203410 }, { "epoch": 1.2091707235883993, "grad_norm": 1.509281873703003, "learning_rate": 0.0001541665554638658, "loss": 0.5840521812438965, "step": 203420 }, { "epoch": 1.2092301656650677, "grad_norm": 1.7069082260131836, "learning_rate": 0.0001541611316772702, "loss": 0.6254988670349121, "step": 203430 }, { "epoch": 1.209289607741736, "grad_norm": 1.3954997062683105, "learning_rate": 0.0001541557076794222, "loss": 0.6059132575988769, "step": 203440 }, { "epoch": 1.2093490498184045, "grad_norm": 1.614605188369751, "learning_rate": 0.00015415028347034773, "loss": 0.6292453289031983, "step": 203450 }, { "epoch": 1.209408491895073, "grad_norm": 1.3143526315689087, "learning_rate": 0.00015414485905007272, "loss": 0.6509909629821777, "step": 203460 }, { "epoch": 1.2094679339717413, "grad_norm": 1.2634260654449463, "learning_rate": 0.0001541394344186231, "loss": 0.555116844177246, "step": 203470 }, { "epoch": 1.2095273760484095, "grad_norm": 1.6512709856033325, "learning_rate": 0.0001541340095760249, "loss": 0.6273360252380371, "step": 203480 }, { "epoch": 1.209586818125078, "grad_norm": 1.297393560409546, "learning_rate": 0.000154128584522304, "loss": 0.6129245758056641, "step": 203490 }, { "epoch": 1.2096462602017464, "grad_norm": 1.3270514011383057, "learning_rate": 0.0001541231592574864, "loss": 0.6031906127929687, "step": 203500 }, { "epoch": 1.2097057022784148, "grad_norm": 1.5686930418014526, "learning_rate": 0.00015411773378159799, "loss": 0.6208492279052734, "step": 203510 }, { "epoch": 1.2097651443550832, "grad_norm": 1.5382195711135864, "learning_rate": 0.00015411230809466478, "loss": 0.546918535232544, "step": 203520 }, { "epoch": 1.2098245864317516, "grad_norm": 1.5675312280654907, "learning_rate": 0.00015410688219671267, "loss": 0.5815979957580566, "step": 203530 }, { "epoch": 1.20988402850842, "grad_norm": 1.5359350442886353, "learning_rate": 0.00015410145608776773, "loss": 0.5904492378234864, "step": 203540 }, { "epoch": 1.2099434705850884, "grad_norm": 1.1767226457595825, "learning_rate": 0.00015409602976785574, "loss": 0.6006368637084961, "step": 203550 }, { "epoch": 1.2100029126617566, "grad_norm": 2.437384843826294, "learning_rate": 0.0001540906032370028, "loss": 0.6570357322692871, "step": 203560 }, { "epoch": 1.210062354738425, "grad_norm": 1.4249728918075562, "learning_rate": 0.00015408517649523484, "loss": 0.6413716316223145, "step": 203570 }, { "epoch": 1.2101217968150935, "grad_norm": 1.5963948965072632, "learning_rate": 0.00015407974954257777, "loss": 0.6367243766784668, "step": 203580 }, { "epoch": 1.2101812388917619, "grad_norm": 1.5459941625595093, "learning_rate": 0.0001540743223790576, "loss": 0.5822402954101562, "step": 203590 }, { "epoch": 1.2102406809684303, "grad_norm": 1.2660037279129028, "learning_rate": 0.00015406889500470028, "loss": 0.6056227207183837, "step": 203600 }, { "epoch": 1.2103001230450987, "grad_norm": 1.5427143573760986, "learning_rate": 0.00015406346741953176, "loss": 0.6545875549316407, "step": 203610 }, { "epoch": 1.2103595651217671, "grad_norm": 1.2428725957870483, "learning_rate": 0.00015405803962357799, "loss": 0.6151450157165528, "step": 203620 }, { "epoch": 1.2104190071984355, "grad_norm": 1.7253645658493042, "learning_rate": 0.000154052611616865, "loss": 0.6199233055114746, "step": 203630 }, { "epoch": 1.210478449275104, "grad_norm": 1.3683598041534424, "learning_rate": 0.00015404718339941868, "loss": 0.5971431732177734, "step": 203640 }, { "epoch": 1.2105378913517724, "grad_norm": 1.8626118898391724, "learning_rate": 0.00015404175497126503, "loss": 0.5946532726287842, "step": 203650 }, { "epoch": 1.2105973334284408, "grad_norm": 1.6775234937667847, "learning_rate": 0.00015403632633243005, "loss": 0.6334904670715332, "step": 203660 }, { "epoch": 1.210656775505109, "grad_norm": 1.6383572816848755, "learning_rate": 0.00015403089748293965, "loss": 0.6416184425354003, "step": 203670 }, { "epoch": 1.2107162175817774, "grad_norm": 1.4056583642959595, "learning_rate": 0.0001540254684228198, "loss": 0.6119651794433594, "step": 203680 }, { "epoch": 1.2107756596584458, "grad_norm": 1.469077706336975, "learning_rate": 0.00015402003915209657, "loss": 0.5961905479431152, "step": 203690 }, { "epoch": 1.2108351017351142, "grad_norm": 1.2410798072814941, "learning_rate": 0.0001540146096707958, "loss": 0.6511874198913574, "step": 203700 }, { "epoch": 1.2108945438117826, "grad_norm": 1.5873368978500366, "learning_rate": 0.00015400917997894351, "loss": 0.6635943412780761, "step": 203710 }, { "epoch": 1.210953985888451, "grad_norm": 1.7905373573303223, "learning_rate": 0.00015400375007656574, "loss": 0.6171802520751953, "step": 203720 }, { "epoch": 1.2110134279651195, "grad_norm": 1.823592185974121, "learning_rate": 0.00015399831996368838, "loss": 0.662618350982666, "step": 203730 }, { "epoch": 1.2110728700417879, "grad_norm": 1.7506855726242065, "learning_rate": 0.00015399288964033743, "loss": 0.62205810546875, "step": 203740 }, { "epoch": 1.211132312118456, "grad_norm": 1.8353859186172485, "learning_rate": 0.00015398745910653888, "loss": 0.666136360168457, "step": 203750 }, { "epoch": 1.2111917541951245, "grad_norm": 1.4302923679351807, "learning_rate": 0.0001539820283623187, "loss": 0.5833789825439453, "step": 203760 }, { "epoch": 1.211251196271793, "grad_norm": 1.7811726331710815, "learning_rate": 0.00015397659740770287, "loss": 0.6221250534057617, "step": 203770 }, { "epoch": 1.2113106383484613, "grad_norm": 1.6526893377304077, "learning_rate": 0.00015397116624271738, "loss": 0.6638326644897461, "step": 203780 }, { "epoch": 1.2113700804251297, "grad_norm": 1.5873667001724243, "learning_rate": 0.00015396573486738818, "loss": 0.6189845085144043, "step": 203790 }, { "epoch": 1.2114295225017981, "grad_norm": 1.6633137464523315, "learning_rate": 0.0001539603032817413, "loss": 0.6775980949401855, "step": 203800 }, { "epoch": 1.2114889645784666, "grad_norm": 1.3539491891860962, "learning_rate": 0.00015395487148580267, "loss": 0.636202621459961, "step": 203810 }, { "epoch": 1.211548406655135, "grad_norm": 1.6835438013076782, "learning_rate": 0.00015394943947959832, "loss": 0.5978618621826172, "step": 203820 }, { "epoch": 1.2116078487318034, "grad_norm": 1.7360725402832031, "learning_rate": 0.0001539440072631542, "loss": 0.6204683303833007, "step": 203830 }, { "epoch": 1.2116672908084718, "grad_norm": 2.2793686389923096, "learning_rate": 0.0001539385748364963, "loss": 0.6756571769714356, "step": 203840 }, { "epoch": 1.21172673288514, "grad_norm": 1.8631460666656494, "learning_rate": 0.00015393314219965066, "loss": 0.5845811843872071, "step": 203850 }, { "epoch": 1.2117861749618084, "grad_norm": 1.7726216316223145, "learning_rate": 0.00015392770935264319, "loss": 0.6191802978515625, "step": 203860 }, { "epoch": 1.2118456170384768, "grad_norm": 1.4917649030685425, "learning_rate": 0.0001539222762954999, "loss": 0.646553897857666, "step": 203870 }, { "epoch": 1.2119050591151452, "grad_norm": 2.0693790912628174, "learning_rate": 0.00015391684302824683, "loss": 0.5875689506530761, "step": 203880 }, { "epoch": 1.2119645011918136, "grad_norm": 1.666355848312378, "learning_rate": 0.0001539114095509099, "loss": 0.6482463836669922, "step": 203890 }, { "epoch": 1.212023943268482, "grad_norm": 1.9631685018539429, "learning_rate": 0.00015390597586351518, "loss": 0.6447409629821778, "step": 203900 }, { "epoch": 1.2120833853451505, "grad_norm": 1.286351203918457, "learning_rate": 0.0001539005419660886, "loss": 0.5284123420715332, "step": 203910 }, { "epoch": 1.212142827421819, "grad_norm": 1.881757378578186, "learning_rate": 0.00015389510785865615, "loss": 0.5796003341674805, "step": 203920 }, { "epoch": 1.212202269498487, "grad_norm": 1.7735953330993652, "learning_rate": 0.00015388967354124387, "loss": 0.6225831985473633, "step": 203930 }, { "epoch": 1.2122617115751555, "grad_norm": 1.416996955871582, "learning_rate": 0.00015388423901387775, "loss": 0.6306665897369385, "step": 203940 }, { "epoch": 1.212321153651824, "grad_norm": 1.7421828508377075, "learning_rate": 0.00015387880427658376, "loss": 0.596006441116333, "step": 203950 }, { "epoch": 1.2123805957284923, "grad_norm": 1.6500588655471802, "learning_rate": 0.00015387336932938788, "loss": 0.6525256633758545, "step": 203960 }, { "epoch": 1.2124400378051607, "grad_norm": 1.3513333797454834, "learning_rate": 0.00015386793417231619, "loss": 0.5852225303649903, "step": 203970 }, { "epoch": 1.2124994798818292, "grad_norm": 1.5777311325073242, "learning_rate": 0.0001538624988053946, "loss": 0.6241122245788574, "step": 203980 }, { "epoch": 1.2125589219584976, "grad_norm": 1.7489368915557861, "learning_rate": 0.00015385706322864918, "loss": 0.6379812240600586, "step": 203990 }, { "epoch": 1.212618364035166, "grad_norm": 1.4301077127456665, "learning_rate": 0.0001538516274421059, "loss": 0.5634012222290039, "step": 204000 }, { "epoch": 1.2126778061118344, "grad_norm": 1.4417961835861206, "learning_rate": 0.00015384619144579074, "loss": 0.60260910987854, "step": 204010 }, { "epoch": 1.2127372481885028, "grad_norm": 1.318130373954773, "learning_rate": 0.00015384075523972973, "loss": 0.6013592720031739, "step": 204020 }, { "epoch": 1.2127966902651712, "grad_norm": 1.4990506172180176, "learning_rate": 0.00015383531882394894, "loss": 0.5888711452484131, "step": 204030 }, { "epoch": 1.2128561323418394, "grad_norm": 1.4507087469100952, "learning_rate": 0.00015382988219847423, "loss": 0.536799144744873, "step": 204040 }, { "epoch": 1.2129155744185078, "grad_norm": 1.7697383165359497, "learning_rate": 0.00015382444536333169, "loss": 0.6170168876647949, "step": 204050 }, { "epoch": 1.2129750164951763, "grad_norm": 1.6429845094680786, "learning_rate": 0.00015381900831854737, "loss": 0.6273123741149902, "step": 204060 }, { "epoch": 1.2130344585718447, "grad_norm": 1.4498331546783447, "learning_rate": 0.0001538135710641472, "loss": 0.5626926898956299, "step": 204070 }, { "epoch": 1.213093900648513, "grad_norm": 1.1137157678604126, "learning_rate": 0.00015380813360015724, "loss": 0.5789096832275391, "step": 204080 }, { "epoch": 1.2131533427251815, "grad_norm": 1.2701773643493652, "learning_rate": 0.0001538026959266035, "loss": 0.6342711448669434, "step": 204090 }, { "epoch": 1.21321278480185, "grad_norm": 1.5821843147277832, "learning_rate": 0.00015379725804351194, "loss": 0.6673762321472168, "step": 204100 }, { "epoch": 1.2132722268785183, "grad_norm": 1.573286533355713, "learning_rate": 0.00015379181995090865, "loss": 0.571350383758545, "step": 204110 }, { "epoch": 1.2133316689551865, "grad_norm": 1.5285398960113525, "learning_rate": 0.0001537863816488196, "loss": 0.6521305084228516, "step": 204120 }, { "epoch": 1.213391111031855, "grad_norm": 1.8747566938400269, "learning_rate": 0.00015378094313727082, "loss": 0.6200600624084472, "step": 204130 }, { "epoch": 1.2134505531085233, "grad_norm": 1.2885136604309082, "learning_rate": 0.00015377550441628826, "loss": 0.6150568008422852, "step": 204140 }, { "epoch": 1.2135099951851918, "grad_norm": 1.2237025499343872, "learning_rate": 0.00015377006548589802, "loss": 0.5688307762145997, "step": 204150 }, { "epoch": 1.2135694372618602, "grad_norm": 1.1582045555114746, "learning_rate": 0.00015376462634612612, "loss": 0.5989841938018798, "step": 204160 }, { "epoch": 1.2136288793385286, "grad_norm": 1.3718942403793335, "learning_rate": 0.0001537591869969985, "loss": 0.5702383518218994, "step": 204170 }, { "epoch": 1.213688321415197, "grad_norm": 1.8866100311279297, "learning_rate": 0.00015375374743854128, "loss": 0.6081634044647217, "step": 204180 }, { "epoch": 1.2137477634918654, "grad_norm": 2.294764757156372, "learning_rate": 0.00015374830767078042, "loss": 0.6232113838195801, "step": 204190 }, { "epoch": 1.2138072055685338, "grad_norm": 1.9430667161941528, "learning_rate": 0.00015374286769374192, "loss": 0.6126763343811035, "step": 204200 }, { "epoch": 1.2138666476452022, "grad_norm": 1.4088118076324463, "learning_rate": 0.00015373742750745187, "loss": 0.5950058937072754, "step": 204210 }, { "epoch": 1.2139260897218704, "grad_norm": 1.5926733016967773, "learning_rate": 0.00015373198711193624, "loss": 0.6388872623443603, "step": 204220 }, { "epoch": 1.2139855317985389, "grad_norm": 1.9700835943222046, "learning_rate": 0.00015372654650722107, "loss": 0.6396652698516846, "step": 204230 }, { "epoch": 1.2140449738752073, "grad_norm": 1.5774623155593872, "learning_rate": 0.00015372110569333242, "loss": 0.6432596206665039, "step": 204240 }, { "epoch": 1.2141044159518757, "grad_norm": 1.9531997442245483, "learning_rate": 0.00015371566467029625, "loss": 0.580225944519043, "step": 204250 }, { "epoch": 1.214163858028544, "grad_norm": 2.2434229850769043, "learning_rate": 0.00015371022343813867, "loss": 0.5865223407745361, "step": 204260 }, { "epoch": 1.2142233001052125, "grad_norm": 1.6148041486740112, "learning_rate": 0.00015370478199688565, "loss": 0.6481761932373047, "step": 204270 }, { "epoch": 1.214282742181881, "grad_norm": 1.8656086921691895, "learning_rate": 0.00015369934034656322, "loss": 0.613003158569336, "step": 204280 }, { "epoch": 1.2143421842585493, "grad_norm": 1.6966949701309204, "learning_rate": 0.00015369389848719745, "loss": 0.5710113525390625, "step": 204290 }, { "epoch": 1.2144016263352175, "grad_norm": 1.676013469696045, "learning_rate": 0.00015368845641881433, "loss": 0.6016069412231445, "step": 204300 }, { "epoch": 1.214461068411886, "grad_norm": 1.661197304725647, "learning_rate": 0.00015368301414143992, "loss": 0.6157496929168701, "step": 204310 }, { "epoch": 1.2145205104885544, "grad_norm": 1.5056222677230835, "learning_rate": 0.00015367757165510025, "loss": 0.6509166717529297, "step": 204320 }, { "epoch": 1.2145799525652228, "grad_norm": 1.5890864133834839, "learning_rate": 0.00015367212895982135, "loss": 0.5571925163269043, "step": 204330 }, { "epoch": 1.2146393946418912, "grad_norm": 1.4068081378936768, "learning_rate": 0.00015366668605562925, "loss": 0.6464946746826172, "step": 204340 }, { "epoch": 1.2146988367185596, "grad_norm": 1.6419934034347534, "learning_rate": 0.00015366124294254998, "loss": 0.6114361763000489, "step": 204350 }, { "epoch": 1.214758278795228, "grad_norm": 1.6768828630447388, "learning_rate": 0.00015365579962060963, "loss": 0.6336355686187745, "step": 204360 }, { "epoch": 1.2148177208718964, "grad_norm": 1.7665923833847046, "learning_rate": 0.00015365035608983418, "loss": 0.6645854949951172, "step": 204370 }, { "epoch": 1.2148771629485648, "grad_norm": 1.6896274089813232, "learning_rate": 0.0001536449123502497, "loss": 0.6071660995483399, "step": 204380 }, { "epoch": 1.2149366050252333, "grad_norm": 1.3553329706192017, "learning_rate": 0.0001536394684018822, "loss": 0.6192798137664794, "step": 204390 }, { "epoch": 1.2149960471019015, "grad_norm": 1.7890523672103882, "learning_rate": 0.00015363402424475777, "loss": 0.6032945156097412, "step": 204400 }, { "epoch": 1.2150554891785699, "grad_norm": 1.768812656402588, "learning_rate": 0.0001536285798789024, "loss": 0.606106185913086, "step": 204410 }, { "epoch": 1.2151149312552383, "grad_norm": 1.4005104303359985, "learning_rate": 0.00015362313530434217, "loss": 0.6374086380004883, "step": 204420 }, { "epoch": 1.2151743733319067, "grad_norm": 1.3881638050079346, "learning_rate": 0.00015361769052110315, "loss": 0.6144433975219726, "step": 204430 }, { "epoch": 1.2152338154085751, "grad_norm": 1.5096303224563599, "learning_rate": 0.00015361224552921135, "loss": 0.6360995292663574, "step": 204440 }, { "epoch": 1.2152932574852435, "grad_norm": 1.4260529279708862, "learning_rate": 0.00015360680032869278, "loss": 0.6429980278015137, "step": 204450 }, { "epoch": 1.215352699561912, "grad_norm": 1.7683805227279663, "learning_rate": 0.00015360135491957356, "loss": 0.6169197082519531, "step": 204460 }, { "epoch": 1.2154121416385804, "grad_norm": 1.5290721654891968, "learning_rate": 0.0001535959093018797, "loss": 0.6717187404632569, "step": 204470 }, { "epoch": 1.2154715837152488, "grad_norm": 1.723454236984253, "learning_rate": 0.00015359046347563723, "loss": 0.568327808380127, "step": 204480 }, { "epoch": 1.215531025791917, "grad_norm": 1.9044831991195679, "learning_rate": 0.0001535850174408723, "loss": 0.6254362106323242, "step": 204490 }, { "epoch": 1.2155904678685854, "grad_norm": 1.5620830059051514, "learning_rate": 0.0001535795711976108, "loss": 0.5791845321655273, "step": 204500 }, { "epoch": 1.2156499099452538, "grad_norm": 1.6112154722213745, "learning_rate": 0.0001535741247458789, "loss": 0.6234518051147461, "step": 204510 }, { "epoch": 1.2157093520219222, "grad_norm": 1.5090938806533813, "learning_rate": 0.0001535686780857027, "loss": 0.5295631408691406, "step": 204520 }, { "epoch": 1.2157687940985906, "grad_norm": 1.4324710369110107, "learning_rate": 0.0001535632312171081, "loss": 0.6178637981414795, "step": 204530 }, { "epoch": 1.215828236175259, "grad_norm": 1.5555399656295776, "learning_rate": 0.00015355778414012126, "loss": 0.6073822975158691, "step": 204540 }, { "epoch": 1.2158876782519275, "grad_norm": 1.6493000984191895, "learning_rate": 0.00015355233685476822, "loss": 0.5597940444946289, "step": 204550 }, { "epoch": 1.2159471203285959, "grad_norm": 1.734144926071167, "learning_rate": 0.00015354688936107503, "loss": 0.6037290096282959, "step": 204560 }, { "epoch": 1.2160065624052643, "grad_norm": 1.5161240100860596, "learning_rate": 0.00015354144165906776, "loss": 0.6485414981842041, "step": 204570 }, { "epoch": 1.2160660044819327, "grad_norm": 1.6286295652389526, "learning_rate": 0.00015353599374877245, "loss": 0.5730355262756348, "step": 204580 }, { "epoch": 1.2161254465586009, "grad_norm": 1.6075825691223145, "learning_rate": 0.0001535305456302152, "loss": 0.5738285064697266, "step": 204590 }, { "epoch": 1.2161848886352693, "grad_norm": 1.725360631942749, "learning_rate": 0.000153525097303422, "loss": 0.6508929252624511, "step": 204600 }, { "epoch": 1.2162443307119377, "grad_norm": 1.820515513420105, "learning_rate": 0.000153519648768419, "loss": 0.5821354866027832, "step": 204610 }, { "epoch": 1.2163037727886061, "grad_norm": 1.6826627254486084, "learning_rate": 0.0001535142000252322, "loss": 0.58920316696167, "step": 204620 }, { "epoch": 1.2163632148652745, "grad_norm": 1.6505008935928345, "learning_rate": 0.0001535087510738877, "loss": 0.5989240646362305, "step": 204630 }, { "epoch": 1.216422656941943, "grad_norm": 1.804772973060608, "learning_rate": 0.00015350330191441153, "loss": 0.6159708023071289, "step": 204640 }, { "epoch": 1.2164820990186114, "grad_norm": 1.924899935722351, "learning_rate": 0.00015349785254682982, "loss": 0.6577552795410156, "step": 204650 }, { "epoch": 1.2165415410952798, "grad_norm": 1.4401904344558716, "learning_rate": 0.00015349240297116856, "loss": 0.6186213016510009, "step": 204660 }, { "epoch": 1.216600983171948, "grad_norm": 1.4851384162902832, "learning_rate": 0.0001534869531874539, "loss": 0.6440889358520507, "step": 204670 }, { "epoch": 1.2166604252486164, "grad_norm": 1.5710831880569458, "learning_rate": 0.0001534815031957118, "loss": 0.5731851577758789, "step": 204680 }, { "epoch": 1.2167198673252848, "grad_norm": 1.401510238647461, "learning_rate": 0.00015347605299596847, "loss": 0.5852955341339111, "step": 204690 }, { "epoch": 1.2167793094019532, "grad_norm": 1.8144235610961914, "learning_rate": 0.00015347060258824987, "loss": 0.6156792640686035, "step": 204700 }, { "epoch": 1.2168387514786216, "grad_norm": 2.0544281005859375, "learning_rate": 0.00015346515197258212, "loss": 0.5990009307861328, "step": 204710 }, { "epoch": 1.21689819355529, "grad_norm": 1.6584502458572388, "learning_rate": 0.00015345970114899132, "loss": 0.6226815700531005, "step": 204720 }, { "epoch": 1.2169576356319585, "grad_norm": 1.4827316999435425, "learning_rate": 0.00015345425011750348, "loss": 0.6471853256225586, "step": 204730 }, { "epoch": 1.2170170777086269, "grad_norm": 1.4157220125198364, "learning_rate": 0.00015344879887814472, "loss": 0.5829487800598144, "step": 204740 }, { "epoch": 1.2170765197852953, "grad_norm": 1.7701679468154907, "learning_rate": 0.00015344334743094107, "loss": 0.6105876922607422, "step": 204750 }, { "epoch": 1.2171359618619637, "grad_norm": 1.25496244430542, "learning_rate": 0.0001534378957759187, "loss": 0.6298738956451416, "step": 204760 }, { "epoch": 1.217195403938632, "grad_norm": 1.6038316488265991, "learning_rate": 0.0001534324439131036, "loss": 0.627956485748291, "step": 204770 }, { "epoch": 1.2172548460153003, "grad_norm": 1.4678958654403687, "learning_rate": 0.0001534269918425219, "loss": 0.5748441696166993, "step": 204780 }, { "epoch": 1.2173142880919687, "grad_norm": 1.4664433002471924, "learning_rate": 0.00015342153956419966, "loss": 0.5708552360534668, "step": 204790 }, { "epoch": 1.2173737301686371, "grad_norm": 1.4130827188491821, "learning_rate": 0.00015341608707816295, "loss": 0.6326148033142089, "step": 204800 }, { "epoch": 1.2174331722453056, "grad_norm": 1.5520604848861694, "learning_rate": 0.00015341063438443787, "loss": 0.5485403060913085, "step": 204810 }, { "epoch": 1.217492614321974, "grad_norm": 1.4550986289978027, "learning_rate": 0.0001534051814830505, "loss": 0.6388195991516114, "step": 204820 }, { "epoch": 1.2175520563986424, "grad_norm": 1.2487179040908813, "learning_rate": 0.00015339972837402697, "loss": 0.5978822708129883, "step": 204830 }, { "epoch": 1.2176114984753108, "grad_norm": 1.4398914575576782, "learning_rate": 0.00015339427505739326, "loss": 0.6413829803466797, "step": 204840 }, { "epoch": 1.2176709405519792, "grad_norm": 1.5001662969589233, "learning_rate": 0.00015338882153317554, "loss": 0.5693149566650391, "step": 204850 }, { "epoch": 1.2177303826286474, "grad_norm": 1.347001314163208, "learning_rate": 0.0001533833678013999, "loss": 0.6262213706970214, "step": 204860 }, { "epoch": 1.2177898247053158, "grad_norm": 2.1675360202789307, "learning_rate": 0.00015337791386209237, "loss": 0.6625310897827148, "step": 204870 }, { "epoch": 1.2178492667819842, "grad_norm": 1.5102051496505737, "learning_rate": 0.0001533724597152791, "loss": 0.5703675270080566, "step": 204880 }, { "epoch": 1.2179087088586527, "grad_norm": 1.480236530303955, "learning_rate": 0.00015336700536098616, "loss": 0.6126718044281005, "step": 204890 }, { "epoch": 1.217968150935321, "grad_norm": 1.4376431703567505, "learning_rate": 0.00015336155079923963, "loss": 0.614262580871582, "step": 204900 }, { "epoch": 1.2180275930119895, "grad_norm": 1.4647406339645386, "learning_rate": 0.0001533560960300656, "loss": 0.6050937652587891, "step": 204910 }, { "epoch": 1.218087035088658, "grad_norm": 1.379411220550537, "learning_rate": 0.0001533506410534902, "loss": 0.6479848384857178, "step": 204920 }, { "epoch": 1.2181464771653263, "grad_norm": 1.5097121000289917, "learning_rate": 0.0001533451858695395, "loss": 0.6754390716552734, "step": 204930 }, { "epoch": 1.2182059192419947, "grad_norm": 1.65520179271698, "learning_rate": 0.00015333973047823959, "loss": 0.5975310325622558, "step": 204940 }, { "epoch": 1.2182653613186631, "grad_norm": 1.536366581916809, "learning_rate": 0.00015333427487961655, "loss": 0.5736471176147461, "step": 204950 }, { "epoch": 1.2183248033953313, "grad_norm": 1.4901224374771118, "learning_rate": 0.00015332881907369653, "loss": 0.6117667198181153, "step": 204960 }, { "epoch": 1.2183842454719997, "grad_norm": 1.760208249092102, "learning_rate": 0.00015332336306050556, "loss": 0.662261962890625, "step": 204970 }, { "epoch": 1.2184436875486682, "grad_norm": 1.900850772857666, "learning_rate": 0.00015331790684006987, "loss": 0.6030934810638428, "step": 204980 }, { "epoch": 1.2185031296253366, "grad_norm": 1.6044955253601074, "learning_rate": 0.00015331245041241536, "loss": 0.5968399047851562, "step": 204990 }, { "epoch": 1.218562571702005, "grad_norm": 1.567938208580017, "learning_rate": 0.00015330699377756827, "loss": 0.6048068046569824, "step": 205000 }, { "epoch": 1.2186220137786734, "grad_norm": 1.6079373359680176, "learning_rate": 0.00015330153693555472, "loss": 0.6641758918762207, "step": 205010 }, { "epoch": 1.2186814558553418, "grad_norm": 2.207068681716919, "learning_rate": 0.00015329607988640072, "loss": 0.6509982109069824, "step": 205020 }, { "epoch": 1.2187408979320102, "grad_norm": 1.9252824783325195, "learning_rate": 0.00015329062263013247, "loss": 0.6456178665161133, "step": 205030 }, { "epoch": 1.2188003400086784, "grad_norm": 2.1637091636657715, "learning_rate": 0.00015328516516677603, "loss": 0.6165609359741211, "step": 205040 }, { "epoch": 1.2188597820853468, "grad_norm": 1.4356110095977783, "learning_rate": 0.00015327970749635746, "loss": 0.6415814399719239, "step": 205050 }, { "epoch": 1.2189192241620153, "grad_norm": 1.2963000535964966, "learning_rate": 0.00015327424961890292, "loss": 0.5581783294677735, "step": 205060 }, { "epoch": 1.2189786662386837, "grad_norm": 1.650036334991455, "learning_rate": 0.00015326879153443855, "loss": 0.6477411270141602, "step": 205070 }, { "epoch": 1.219038108315352, "grad_norm": 1.339023470878601, "learning_rate": 0.00015326333324299039, "loss": 0.6530898571014404, "step": 205080 }, { "epoch": 1.2190975503920205, "grad_norm": 1.47965669631958, "learning_rate": 0.0001532578747445846, "loss": 0.5984313488006592, "step": 205090 }, { "epoch": 1.219156992468689, "grad_norm": 1.7217557430267334, "learning_rate": 0.00015325241603924726, "loss": 0.5864691734313965, "step": 205100 }, { "epoch": 1.2192164345453573, "grad_norm": 1.3822654485702515, "learning_rate": 0.00015324695712700447, "loss": 0.575597095489502, "step": 205110 }, { "epoch": 1.2192758766220257, "grad_norm": 1.9537887573242188, "learning_rate": 0.00015324149800788242, "loss": 0.6437281608581543, "step": 205120 }, { "epoch": 1.2193353186986942, "grad_norm": 1.2867519855499268, "learning_rate": 0.00015323603868190716, "loss": 0.6119184017181396, "step": 205130 }, { "epoch": 1.2193947607753624, "grad_norm": 1.5654116868972778, "learning_rate": 0.0001532305791491048, "loss": 0.6023874759674073, "step": 205140 }, { "epoch": 1.2194542028520308, "grad_norm": 2.026771306991577, "learning_rate": 0.00015322511940950152, "loss": 0.6156540870666504, "step": 205150 }, { "epoch": 1.2195136449286992, "grad_norm": 1.3282349109649658, "learning_rate": 0.00015321965946312334, "loss": 0.5802642345428467, "step": 205160 }, { "epoch": 1.2195730870053676, "grad_norm": 1.350526213645935, "learning_rate": 0.00015321419930999647, "loss": 0.6306518077850342, "step": 205170 }, { "epoch": 1.219632529082036, "grad_norm": 2.0471432209014893, "learning_rate": 0.00015320873895014698, "loss": 0.6188478469848633, "step": 205180 }, { "epoch": 1.2196919711587044, "grad_norm": 1.3706527948379517, "learning_rate": 0.00015320327838360103, "loss": 0.5929719924926757, "step": 205190 }, { "epoch": 1.2197514132353728, "grad_norm": 1.6544368267059326, "learning_rate": 0.0001531978176103847, "loss": 0.5712904930114746, "step": 205200 }, { "epoch": 1.2198108553120413, "grad_norm": 1.8216632604599, "learning_rate": 0.00015319235663052412, "loss": 0.6259932518005371, "step": 205210 }, { "epoch": 1.2198702973887097, "grad_norm": 1.9350119829177856, "learning_rate": 0.0001531868954440454, "loss": 0.5680010795593262, "step": 205220 }, { "epoch": 1.2199297394653779, "grad_norm": 1.8234978914260864, "learning_rate": 0.0001531814340509747, "loss": 0.6675098896026611, "step": 205230 }, { "epoch": 1.2199891815420463, "grad_norm": 1.7947759628295898, "learning_rate": 0.00015317597245133815, "loss": 0.5960389614105225, "step": 205240 }, { "epoch": 1.2200486236187147, "grad_norm": 1.7165663242340088, "learning_rate": 0.00015317051064516184, "loss": 0.5909215927124023, "step": 205250 }, { "epoch": 1.220108065695383, "grad_norm": 1.890112042427063, "learning_rate": 0.0001531650486324719, "loss": 0.6396828651428222, "step": 205260 }, { "epoch": 1.2201675077720515, "grad_norm": 1.419296383857727, "learning_rate": 0.00015315958641329454, "loss": 0.6508533477783203, "step": 205270 }, { "epoch": 1.22022694984872, "grad_norm": 1.7877511978149414, "learning_rate": 0.00015315412398765577, "loss": 0.5734594821929931, "step": 205280 }, { "epoch": 1.2202863919253883, "grad_norm": 1.5622395277023315, "learning_rate": 0.00015314866135558182, "loss": 0.5923292636871338, "step": 205290 }, { "epoch": 1.2203458340020568, "grad_norm": 1.2704089879989624, "learning_rate": 0.0001531431985170987, "loss": 0.6099030017852783, "step": 205300 }, { "epoch": 1.2204052760787252, "grad_norm": 1.667171835899353, "learning_rate": 0.00015313773547223264, "loss": 0.6390306949615479, "step": 205310 }, { "epoch": 1.2204647181553936, "grad_norm": 1.7768434286117554, "learning_rate": 0.00015313227222100978, "loss": 0.6479741096496582, "step": 205320 }, { "epoch": 1.2205241602320618, "grad_norm": 1.7263067960739136, "learning_rate": 0.00015312680876345623, "loss": 0.570728874206543, "step": 205330 }, { "epoch": 1.2205836023087302, "grad_norm": 1.717088222503662, "learning_rate": 0.0001531213450995981, "loss": 0.5679686546325684, "step": 205340 }, { "epoch": 1.2206430443853986, "grad_norm": 1.4659473896026611, "learning_rate": 0.00015311588122946155, "loss": 0.599180793762207, "step": 205350 }, { "epoch": 1.220702486462067, "grad_norm": 1.465738296508789, "learning_rate": 0.0001531104171530727, "loss": 0.7095417499542236, "step": 205360 }, { "epoch": 1.2207619285387354, "grad_norm": 1.459437608718872, "learning_rate": 0.00015310495287045774, "loss": 0.6034498691558838, "step": 205370 }, { "epoch": 1.2208213706154039, "grad_norm": 1.4232909679412842, "learning_rate": 0.00015309948838164274, "loss": 0.6696062564849854, "step": 205380 }, { "epoch": 1.2208808126920723, "grad_norm": 1.3166214227676392, "learning_rate": 0.0001530940236866539, "loss": 0.5945912837982178, "step": 205390 }, { "epoch": 1.2209402547687407, "grad_norm": 1.8684879541397095, "learning_rate": 0.00015308855878551732, "loss": 0.6186139106750488, "step": 205400 }, { "epoch": 1.2209996968454089, "grad_norm": 1.36086905002594, "learning_rate": 0.00015308309367825914, "loss": 0.5716357231140137, "step": 205410 }, { "epoch": 1.2210591389220773, "grad_norm": 1.4220596551895142, "learning_rate": 0.00015307762836490554, "loss": 0.6238405227661132, "step": 205420 }, { "epoch": 1.2211185809987457, "grad_norm": 1.816758155822754, "learning_rate": 0.00015307216284548262, "loss": 0.6172013759613038, "step": 205430 }, { "epoch": 1.2211780230754141, "grad_norm": 1.7977217435836792, "learning_rate": 0.00015306669712001657, "loss": 0.5874792098999023, "step": 205440 }, { "epoch": 1.2212374651520825, "grad_norm": 1.5672379732131958, "learning_rate": 0.00015306123118853353, "loss": 0.6464191436767578, "step": 205450 }, { "epoch": 1.221296907228751, "grad_norm": 1.9705276489257812, "learning_rate": 0.00015305576505105962, "loss": 0.6372480869293213, "step": 205460 }, { "epoch": 1.2213563493054194, "grad_norm": 1.3765171766281128, "learning_rate": 0.00015305029870762098, "loss": 0.614979362487793, "step": 205470 }, { "epoch": 1.2214157913820878, "grad_norm": 1.5226987600326538, "learning_rate": 0.0001530448321582438, "loss": 0.608746337890625, "step": 205480 }, { "epoch": 1.2214752334587562, "grad_norm": 1.3642240762710571, "learning_rate": 0.0001530393654029542, "loss": 0.6460658550262451, "step": 205490 }, { "epoch": 1.2215346755354246, "grad_norm": 1.496980905532837, "learning_rate": 0.00015303389844177834, "loss": 0.6037043571472168, "step": 205500 }, { "epoch": 1.2215941176120928, "grad_norm": 1.5338079929351807, "learning_rate": 0.0001530284312747424, "loss": 0.586237096786499, "step": 205510 }, { "epoch": 1.2216535596887612, "grad_norm": 1.4253785610198975, "learning_rate": 0.00015302296390187246, "loss": 0.5976519584655762, "step": 205520 }, { "epoch": 1.2217130017654296, "grad_norm": 1.732209324836731, "learning_rate": 0.00015301749632319478, "loss": 0.5848294734954834, "step": 205530 }, { "epoch": 1.221772443842098, "grad_norm": 1.5795259475708008, "learning_rate": 0.0001530120285387354, "loss": 0.6629704475402832, "step": 205540 }, { "epoch": 1.2218318859187665, "grad_norm": 1.5203801393508911, "learning_rate": 0.0001530065605485206, "loss": 0.7110167503356933, "step": 205550 }, { "epoch": 1.2218913279954349, "grad_norm": 1.3900883197784424, "learning_rate": 0.0001530010923525764, "loss": 0.5811491966247558, "step": 205560 }, { "epoch": 1.2219507700721033, "grad_norm": 1.733333945274353, "learning_rate": 0.00015299562395092905, "loss": 0.6261979103088379, "step": 205570 }, { "epoch": 1.2220102121487717, "grad_norm": 1.339943766593933, "learning_rate": 0.0001529901553436047, "loss": 0.5680666923522949, "step": 205580 }, { "epoch": 1.2220696542254401, "grad_norm": 1.6547355651855469, "learning_rate": 0.00015298468653062946, "loss": 0.6029407978057861, "step": 205590 }, { "epoch": 1.2221290963021083, "grad_norm": 1.5100219249725342, "learning_rate": 0.0001529792175120296, "loss": 0.5784917831420898, "step": 205600 }, { "epoch": 1.2221885383787767, "grad_norm": 1.9376546144485474, "learning_rate": 0.0001529737482878311, "loss": 0.6732772827148438, "step": 205610 }, { "epoch": 1.2222479804554451, "grad_norm": 1.4979021549224854, "learning_rate": 0.00015296827885806033, "loss": 0.6145458221435547, "step": 205620 }, { "epoch": 1.2223074225321136, "grad_norm": 1.7089649438858032, "learning_rate": 0.00015296280922274332, "loss": 0.6109127044677735, "step": 205630 }, { "epoch": 1.222366864608782, "grad_norm": 1.4368306398391724, "learning_rate": 0.00015295733938190624, "loss": 0.5906253814697265, "step": 205640 }, { "epoch": 1.2224263066854504, "grad_norm": 1.6749017238616943, "learning_rate": 0.00015295186933557536, "loss": 0.5693586349487305, "step": 205650 }, { "epoch": 1.2224857487621188, "grad_norm": 1.6910078525543213, "learning_rate": 0.0001529463990837767, "loss": 0.6206811904907227, "step": 205660 }, { "epoch": 1.2225451908387872, "grad_norm": 1.5781521797180176, "learning_rate": 0.00015294092862653652, "loss": 0.6099694252014161, "step": 205670 }, { "epoch": 1.2226046329154556, "grad_norm": 1.4375170469284058, "learning_rate": 0.000152935457963881, "loss": 0.6567521095275879, "step": 205680 }, { "epoch": 1.222664074992124, "grad_norm": 1.9409676790237427, "learning_rate": 0.00015292998709583625, "loss": 0.609459114074707, "step": 205690 }, { "epoch": 1.2227235170687922, "grad_norm": 1.7181625366210938, "learning_rate": 0.0001529245160224285, "loss": 0.6137293815612793, "step": 205700 }, { "epoch": 1.2227829591454606, "grad_norm": 1.8757765293121338, "learning_rate": 0.0001529190447436839, "loss": 0.6091212272644043, "step": 205710 }, { "epoch": 1.222842401222129, "grad_norm": 1.3801510334014893, "learning_rate": 0.00015291357325962856, "loss": 0.5958608627319336, "step": 205720 }, { "epoch": 1.2229018432987975, "grad_norm": 1.7689688205718994, "learning_rate": 0.00015290810157028877, "loss": 0.6689766883850098, "step": 205730 }, { "epoch": 1.222961285375466, "grad_norm": 1.776703953742981, "learning_rate": 0.0001529026296756906, "loss": 0.6577723503112793, "step": 205740 }, { "epoch": 1.2230207274521343, "grad_norm": 1.7424421310424805, "learning_rate": 0.0001528971575758603, "loss": 0.53634614944458, "step": 205750 }, { "epoch": 1.2230801695288027, "grad_norm": 1.6492191553115845, "learning_rate": 0.000152891685270824, "loss": 0.6029036521911622, "step": 205760 }, { "epoch": 1.2231396116054711, "grad_norm": 1.4940128326416016, "learning_rate": 0.0001528862127606079, "loss": 0.590825080871582, "step": 205770 }, { "epoch": 1.2231990536821393, "grad_norm": 1.7363560199737549, "learning_rate": 0.0001528807400452382, "loss": 0.6207012176513672, "step": 205780 }, { "epoch": 1.2232584957588077, "grad_norm": 1.6799664497375488, "learning_rate": 0.00015287526712474102, "loss": 0.59880690574646, "step": 205790 }, { "epoch": 1.2233179378354762, "grad_norm": 1.5392001867294312, "learning_rate": 0.00015286979399914253, "loss": 0.5673007965087891, "step": 205800 }, { "epoch": 1.2233773799121446, "grad_norm": 1.256003737449646, "learning_rate": 0.00015286432066846905, "loss": 0.6166929244995117, "step": 205810 }, { "epoch": 1.223436821988813, "grad_norm": 1.556532382965088, "learning_rate": 0.00015285884713274662, "loss": 0.6070103168487548, "step": 205820 }, { "epoch": 1.2234962640654814, "grad_norm": 1.776230812072754, "learning_rate": 0.0001528533733920015, "loss": 0.5590864181518554, "step": 205830 }, { "epoch": 1.2235557061421498, "grad_norm": 1.6900441646575928, "learning_rate": 0.0001528478994462598, "loss": 0.5870450973510742, "step": 205840 }, { "epoch": 1.2236151482188182, "grad_norm": 1.2165182828903198, "learning_rate": 0.0001528424252955478, "loss": 0.5801665306091308, "step": 205850 }, { "epoch": 1.2236745902954866, "grad_norm": 1.3456034660339355, "learning_rate": 0.00015283695093989158, "loss": 0.5724397659301758, "step": 205860 }, { "epoch": 1.223734032372155, "grad_norm": 1.4870394468307495, "learning_rate": 0.00015283147637931742, "loss": 0.6388921737670898, "step": 205870 }, { "epoch": 1.2237934744488232, "grad_norm": 1.6519793272018433, "learning_rate": 0.0001528260016138515, "loss": 0.5899481773376465, "step": 205880 }, { "epoch": 1.2238529165254917, "grad_norm": 1.8355458974838257, "learning_rate": 0.00015282052664351996, "loss": 0.6046280860900879, "step": 205890 }, { "epoch": 1.22391235860216, "grad_norm": 1.3774759769439697, "learning_rate": 0.000152815051468349, "loss": 0.6020108699798584, "step": 205900 }, { "epoch": 1.2239718006788285, "grad_norm": 1.7328813076019287, "learning_rate": 0.00015280957608836487, "loss": 0.5892070770263672, "step": 205910 }, { "epoch": 1.224031242755497, "grad_norm": 1.551716923713684, "learning_rate": 0.00015280410050359366, "loss": 0.6231144905090332, "step": 205920 }, { "epoch": 1.2240906848321653, "grad_norm": 1.673880934715271, "learning_rate": 0.00015279862471406165, "loss": 0.6770729541778564, "step": 205930 }, { "epoch": 1.2241501269088337, "grad_norm": 1.7927494049072266, "learning_rate": 0.00015279314871979502, "loss": 0.635460615158081, "step": 205940 }, { "epoch": 1.2242095689855022, "grad_norm": 1.6401219367980957, "learning_rate": 0.00015278767252081992, "loss": 0.6107370853424072, "step": 205950 }, { "epoch": 1.2242690110621706, "grad_norm": 1.7407306432724, "learning_rate": 0.0001527821961171626, "loss": 0.5748506546020508, "step": 205960 }, { "epoch": 1.2243284531388388, "grad_norm": 1.4273408651351929, "learning_rate": 0.00015277671950884923, "loss": 0.6004670143127442, "step": 205970 }, { "epoch": 1.2243878952155072, "grad_norm": 2.1151721477508545, "learning_rate": 0.00015277124269590602, "loss": 0.5799009323120117, "step": 205980 }, { "epoch": 1.2244473372921756, "grad_norm": 1.5828202962875366, "learning_rate": 0.00015276576567835914, "loss": 0.6253487586975097, "step": 205990 }, { "epoch": 1.224506779368844, "grad_norm": 1.7984880208969116, "learning_rate": 0.00015276028845623486, "loss": 0.6285350322723389, "step": 206000 }, { "epoch": 1.2245662214455124, "grad_norm": 1.5188090801239014, "learning_rate": 0.00015275481102955927, "loss": 0.5848967552185058, "step": 206010 }, { "epoch": 1.2246256635221808, "grad_norm": 1.5897130966186523, "learning_rate": 0.00015274933339835865, "loss": 0.612302589416504, "step": 206020 }, { "epoch": 1.2246851055988492, "grad_norm": 1.6781097650527954, "learning_rate": 0.0001527438555626592, "loss": 0.6849520206451416, "step": 206030 }, { "epoch": 1.2247445476755177, "grad_norm": 1.397041916847229, "learning_rate": 0.00015273837752248718, "loss": 0.5681501388549804, "step": 206040 }, { "epoch": 1.224803989752186, "grad_norm": 1.7972148656845093, "learning_rate": 0.00015273289927786863, "loss": 0.6444052696228028, "step": 206050 }, { "epoch": 1.2248634318288545, "grad_norm": 1.7702568769454956, "learning_rate": 0.00015272742082882994, "loss": 0.631054162979126, "step": 206060 }, { "epoch": 1.2249228739055227, "grad_norm": 1.2366398572921753, "learning_rate": 0.00015272194217539717, "loss": 0.6014191150665283, "step": 206070 }, { "epoch": 1.224982315982191, "grad_norm": 1.9632760286331177, "learning_rate": 0.0001527164633175966, "loss": 0.6323693752288818, "step": 206080 }, { "epoch": 1.2250417580588595, "grad_norm": 1.4382333755493164, "learning_rate": 0.00015271098425545445, "loss": 0.5969951629638672, "step": 206090 }, { "epoch": 1.225101200135528, "grad_norm": 1.4676023721694946, "learning_rate": 0.0001527055049889969, "loss": 0.6092164993286133, "step": 206100 }, { "epoch": 1.2251606422121963, "grad_norm": 1.4796581268310547, "learning_rate": 0.00015270002551825016, "loss": 0.6047441482543945, "step": 206110 }, { "epoch": 1.2252200842888648, "grad_norm": 1.921026587486267, "learning_rate": 0.00015269454584324047, "loss": 0.5817554473876954, "step": 206120 }, { "epoch": 1.2252795263655332, "grad_norm": 1.491877794265747, "learning_rate": 0.000152689065963994, "loss": 0.5672272682189942, "step": 206130 }, { "epoch": 1.2253389684422016, "grad_norm": 1.878967046737671, "learning_rate": 0.000152683585880537, "loss": 0.6615662574768066, "step": 206140 }, { "epoch": 1.2253984105188698, "grad_norm": 1.70530104637146, "learning_rate": 0.0001526781055928957, "loss": 0.6060462474822998, "step": 206150 }, { "epoch": 1.2254578525955382, "grad_norm": 1.5766487121582031, "learning_rate": 0.00015267262510109628, "loss": 0.588941240310669, "step": 206160 }, { "epoch": 1.2255172946722066, "grad_norm": 1.519999384880066, "learning_rate": 0.00015266714440516493, "loss": 0.5951976776123047, "step": 206170 }, { "epoch": 1.225576736748875, "grad_norm": 1.6468032598495483, "learning_rate": 0.00015266166350512796, "loss": 0.6536724090576171, "step": 206180 }, { "epoch": 1.2256361788255434, "grad_norm": 1.2497323751449585, "learning_rate": 0.0001526561824010115, "loss": 0.5435178756713868, "step": 206190 }, { "epoch": 1.2256956209022118, "grad_norm": 1.3784046173095703, "learning_rate": 0.00015265070109284182, "loss": 0.5535189628601074, "step": 206200 }, { "epoch": 1.2257550629788803, "grad_norm": 1.2857695817947388, "learning_rate": 0.0001526452195806451, "loss": 0.6898739814758301, "step": 206210 }, { "epoch": 1.2258145050555487, "grad_norm": 1.5882391929626465, "learning_rate": 0.00015263973786444762, "loss": 0.6459559440612793, "step": 206220 }, { "epoch": 1.225873947132217, "grad_norm": 1.4089596271514893, "learning_rate": 0.00015263425594427553, "loss": 0.6363857746124267, "step": 206230 }, { "epoch": 1.2259333892088855, "grad_norm": 1.735863208770752, "learning_rate": 0.0001526287738201551, "loss": 0.6302014827728272, "step": 206240 }, { "epoch": 1.2259928312855537, "grad_norm": 1.7837553024291992, "learning_rate": 0.00015262329149211257, "loss": 0.6379185676574707, "step": 206250 }, { "epoch": 1.2260522733622221, "grad_norm": 1.6730586290359497, "learning_rate": 0.00015261780896017412, "loss": 0.6107799530029296, "step": 206260 }, { "epoch": 1.2261117154388905, "grad_norm": 1.728882908821106, "learning_rate": 0.00015261232622436604, "loss": 0.6635591506958007, "step": 206270 }, { "epoch": 1.226171157515559, "grad_norm": 1.4558367729187012, "learning_rate": 0.00015260684328471447, "loss": 0.5860645294189453, "step": 206280 }, { "epoch": 1.2262305995922274, "grad_norm": 1.3730632066726685, "learning_rate": 0.00015260136014124572, "loss": 0.6133791446685791, "step": 206290 }, { "epoch": 1.2262900416688958, "grad_norm": 1.800125002861023, "learning_rate": 0.00015259587679398597, "loss": 0.6127353191375733, "step": 206300 }, { "epoch": 1.2263494837455642, "grad_norm": 1.5709819793701172, "learning_rate": 0.00015259039324296144, "loss": 0.5831811904907227, "step": 206310 }, { "epoch": 1.2264089258222326, "grad_norm": 1.5339672565460205, "learning_rate": 0.00015258490948819845, "loss": 0.5958719253540039, "step": 206320 }, { "epoch": 1.226468367898901, "grad_norm": 1.5093876123428345, "learning_rate": 0.0001525794255297231, "loss": 0.5935700893402099, "step": 206330 }, { "epoch": 1.2265278099755692, "grad_norm": 1.6997495889663696, "learning_rate": 0.00015257394136756173, "loss": 0.5588562488555908, "step": 206340 }, { "epoch": 1.2265872520522376, "grad_norm": 1.61793851852417, "learning_rate": 0.00015256845700174055, "loss": 0.5777915000915528, "step": 206350 }, { "epoch": 1.226646694128906, "grad_norm": 1.5528894662857056, "learning_rate": 0.00015256297243228576, "loss": 0.6132550716400147, "step": 206360 }, { "epoch": 1.2267061362055744, "grad_norm": 1.9010273218154907, "learning_rate": 0.00015255748765922365, "loss": 0.5854611396789551, "step": 206370 }, { "epoch": 1.2267655782822429, "grad_norm": 1.6044269800186157, "learning_rate": 0.00015255200268258037, "loss": 0.5845666885375976, "step": 206380 }, { "epoch": 1.2268250203589113, "grad_norm": 1.9202511310577393, "learning_rate": 0.00015254651750238227, "loss": 0.5909751415252685, "step": 206390 }, { "epoch": 1.2268844624355797, "grad_norm": 1.5915628671646118, "learning_rate": 0.00015254103211865552, "loss": 0.5777978897094727, "step": 206400 }, { "epoch": 1.226943904512248, "grad_norm": 1.2849369049072266, "learning_rate": 0.00015253554653142637, "loss": 0.573056983947754, "step": 206410 }, { "epoch": 1.2270033465889165, "grad_norm": 1.637823224067688, "learning_rate": 0.00015253006074072108, "loss": 0.5920238971710206, "step": 206420 }, { "epoch": 1.227062788665585, "grad_norm": 1.6399898529052734, "learning_rate": 0.00015252457474656582, "loss": 0.6203519821166992, "step": 206430 }, { "epoch": 1.2271222307422531, "grad_norm": 1.8814035654067993, "learning_rate": 0.00015251908854898693, "loss": 0.6008051872253418, "step": 206440 }, { "epoch": 1.2271816728189215, "grad_norm": 1.5586659908294678, "learning_rate": 0.00015251360214801063, "loss": 0.5493419647216797, "step": 206450 }, { "epoch": 1.22724111489559, "grad_norm": 1.8008376359939575, "learning_rate": 0.00015250811554366316, "loss": 0.6251449584960938, "step": 206460 }, { "epoch": 1.2273005569722584, "grad_norm": 1.6021170616149902, "learning_rate": 0.00015250262873597073, "loss": 0.5996041297912598, "step": 206470 }, { "epoch": 1.2273599990489268, "grad_norm": 1.5524892807006836, "learning_rate": 0.00015249714172495962, "loss": 0.6563737392425537, "step": 206480 }, { "epoch": 1.2274194411255952, "grad_norm": 1.336708664894104, "learning_rate": 0.00015249165451065608, "loss": 0.6103835582733155, "step": 206490 }, { "epoch": 1.2274788832022636, "grad_norm": 1.3374024629592896, "learning_rate": 0.00015248616709308635, "loss": 0.5828687667846679, "step": 206500 }, { "epoch": 1.227538325278932, "grad_norm": 1.6425392627716064, "learning_rate": 0.00015248067947227668, "loss": 0.5800319671630859, "step": 206510 }, { "epoch": 1.2275977673556002, "grad_norm": 1.5024311542510986, "learning_rate": 0.00015247519164825332, "loss": 0.6305213928222656, "step": 206520 }, { "epoch": 1.2276572094322686, "grad_norm": 1.928505539894104, "learning_rate": 0.00015246970362104253, "loss": 0.6298315525054932, "step": 206530 }, { "epoch": 1.227716651508937, "grad_norm": 1.8836379051208496, "learning_rate": 0.00015246421539067052, "loss": 0.6670659065246582, "step": 206540 }, { "epoch": 1.2277760935856055, "grad_norm": 1.5020166635513306, "learning_rate": 0.00015245872695716367, "loss": 0.594969367980957, "step": 206550 }, { "epoch": 1.2278355356622739, "grad_norm": 1.4636776447296143, "learning_rate": 0.00015245323832054804, "loss": 0.5492721557617187, "step": 206560 }, { "epoch": 1.2278949777389423, "grad_norm": 1.7338476181030273, "learning_rate": 0.00015244774948085005, "loss": 0.6030791282653809, "step": 206570 }, { "epoch": 1.2279544198156107, "grad_norm": 1.4800260066986084, "learning_rate": 0.0001524422604380959, "loss": 0.5905411720275879, "step": 206580 }, { "epoch": 1.2280138618922791, "grad_norm": 1.6708955764770508, "learning_rate": 0.00015243677119231182, "loss": 0.6062130928039551, "step": 206590 }, { "epoch": 1.2280733039689475, "grad_norm": 1.58745539188385, "learning_rate": 0.00015243128174352412, "loss": 0.6113198757171631, "step": 206600 }, { "epoch": 1.228132746045616, "grad_norm": 1.160235047340393, "learning_rate": 0.00015242579209175902, "loss": 0.5779530525207519, "step": 206610 }, { "epoch": 1.2281921881222841, "grad_norm": 1.8016592264175415, "learning_rate": 0.0001524203022370428, "loss": 0.5953094482421875, "step": 206620 }, { "epoch": 1.2282516301989526, "grad_norm": 1.3875770568847656, "learning_rate": 0.00015241481217940172, "loss": 0.5612982749938965, "step": 206630 }, { "epoch": 1.228311072275621, "grad_norm": 1.2909585237503052, "learning_rate": 0.00015240932191886203, "loss": 0.577619981765747, "step": 206640 }, { "epoch": 1.2283705143522894, "grad_norm": 1.6054409742355347, "learning_rate": 0.00015240383145545002, "loss": 0.5818174362182618, "step": 206650 }, { "epoch": 1.2284299564289578, "grad_norm": 1.5385626554489136, "learning_rate": 0.00015239834078919194, "loss": 0.6610594749450683, "step": 206660 }, { "epoch": 1.2284893985056262, "grad_norm": 1.952967882156372, "learning_rate": 0.00015239284992011405, "loss": 0.6595308303833007, "step": 206670 }, { "epoch": 1.2285488405822946, "grad_norm": 1.5629260540008545, "learning_rate": 0.0001523873588482426, "loss": 0.6286005020141602, "step": 206680 }, { "epoch": 1.228608282658963, "grad_norm": 1.379879117012024, "learning_rate": 0.00015238186757360388, "loss": 0.5919776439666748, "step": 206690 }, { "epoch": 1.2286677247356312, "grad_norm": 1.3354735374450684, "learning_rate": 0.00015237637609622417, "loss": 0.5872861385345459, "step": 206700 }, { "epoch": 1.2287271668122997, "grad_norm": 1.7626930475234985, "learning_rate": 0.00015237088441612975, "loss": 0.6272602558135987, "step": 206710 }, { "epoch": 1.228786608888968, "grad_norm": 1.996951699256897, "learning_rate": 0.00015236539253334682, "loss": 0.6336639404296875, "step": 206720 }, { "epoch": 1.2288460509656365, "grad_norm": 1.5889042615890503, "learning_rate": 0.0001523599004479017, "loss": 0.5894604682922363, "step": 206730 }, { "epoch": 1.228905493042305, "grad_norm": 1.7059574127197266, "learning_rate": 0.00015235440815982066, "loss": 0.5976365089416504, "step": 206740 }, { "epoch": 1.2289649351189733, "grad_norm": 1.8133673667907715, "learning_rate": 0.00015234891566913002, "loss": 0.6380345344543457, "step": 206750 }, { "epoch": 1.2290243771956417, "grad_norm": 1.7746570110321045, "learning_rate": 0.000152343422975856, "loss": 0.627889347076416, "step": 206760 }, { "epoch": 1.2290838192723101, "grad_norm": 1.8507373332977295, "learning_rate": 0.00015233793008002483, "loss": 0.6531164646148682, "step": 206770 }, { "epoch": 1.2291432613489786, "grad_norm": 2.0797128677368164, "learning_rate": 0.00015233243698166283, "loss": 0.6314261436462403, "step": 206780 }, { "epoch": 1.229202703425647, "grad_norm": 1.5186291933059692, "learning_rate": 0.00015232694368079634, "loss": 0.6578173637390137, "step": 206790 }, { "epoch": 1.2292621455023154, "grad_norm": 1.3358455896377563, "learning_rate": 0.0001523214501774516, "loss": 0.6231883049011231, "step": 206800 }, { "epoch": 1.2293215875789836, "grad_norm": 1.6145447492599487, "learning_rate": 0.00015231595647165482, "loss": 0.5657764434814453, "step": 206810 }, { "epoch": 1.229381029655652, "grad_norm": 1.1008667945861816, "learning_rate": 0.00015231046256343236, "loss": 0.6249546527862548, "step": 206820 }, { "epoch": 1.2294404717323204, "grad_norm": 1.466065764427185, "learning_rate": 0.00015230496845281046, "loss": 0.5521207332611084, "step": 206830 }, { "epoch": 1.2294999138089888, "grad_norm": 1.6833817958831787, "learning_rate": 0.00015229947413981544, "loss": 0.6367595672607422, "step": 206840 }, { "epoch": 1.2295593558856572, "grad_norm": 1.6779191493988037, "learning_rate": 0.00015229397962447351, "loss": 0.6049946308135986, "step": 206850 }, { "epoch": 1.2296187979623256, "grad_norm": 1.460208535194397, "learning_rate": 0.00015228848490681106, "loss": 0.5539528846740722, "step": 206860 }, { "epoch": 1.229678240038994, "grad_norm": 2.0419631004333496, "learning_rate": 0.0001522829899868543, "loss": 0.6806230545043945, "step": 206870 }, { "epoch": 1.2297376821156625, "grad_norm": 1.2708491086959839, "learning_rate": 0.0001522774948646295, "loss": 0.61934814453125, "step": 206880 }, { "epoch": 1.2297971241923307, "grad_norm": 1.60391104221344, "learning_rate": 0.00015227199954016303, "loss": 0.6378638744354248, "step": 206890 }, { "epoch": 1.229856566268999, "grad_norm": 1.75521719455719, "learning_rate": 0.0001522665040134811, "loss": 0.6254805564880371, "step": 206900 }, { "epoch": 1.2299160083456675, "grad_norm": 1.840405821800232, "learning_rate": 0.00015226100828461006, "loss": 0.6094977855682373, "step": 206910 }, { "epoch": 1.229975450422336, "grad_norm": 1.543357253074646, "learning_rate": 0.00015225551235357614, "loss": 0.5875336170196533, "step": 206920 }, { "epoch": 1.2300348924990043, "grad_norm": 1.4985253810882568, "learning_rate": 0.00015225001622040565, "loss": 0.6283058166503906, "step": 206930 }, { "epoch": 1.2300943345756727, "grad_norm": 1.5206973552703857, "learning_rate": 0.0001522445198851249, "loss": 0.5720705986022949, "step": 206940 }, { "epoch": 1.2301537766523412, "grad_norm": 1.6873886585235596, "learning_rate": 0.00015223902334776017, "loss": 0.560191297531128, "step": 206950 }, { "epoch": 1.2302132187290096, "grad_norm": 1.8922169208526611, "learning_rate": 0.00015223352660833776, "loss": 0.6609313488006592, "step": 206960 }, { "epoch": 1.230272660805678, "grad_norm": 1.8768569231033325, "learning_rate": 0.00015222802966688396, "loss": 0.5955766677856446, "step": 206970 }, { "epoch": 1.2303321028823464, "grad_norm": 1.4943037033081055, "learning_rate": 0.00015222253252342508, "loss": 0.5941265106201172, "step": 206980 }, { "epoch": 1.2303915449590146, "grad_norm": 1.616652011871338, "learning_rate": 0.00015221703517798738, "loss": 0.6407746315002442, "step": 206990 }, { "epoch": 1.230450987035683, "grad_norm": 1.8237653970718384, "learning_rate": 0.00015221153763059718, "loss": 0.6266090393066406, "step": 207000 }, { "epoch": 1.2305104291123514, "grad_norm": 1.907333493232727, "learning_rate": 0.0001522060398812808, "loss": 0.6488970756530762, "step": 207010 }, { "epoch": 1.2305698711890198, "grad_norm": 1.8048393726348877, "learning_rate": 0.00015220054193006453, "loss": 0.6526291847229004, "step": 207020 }, { "epoch": 1.2306293132656883, "grad_norm": 1.828426718711853, "learning_rate": 0.0001521950437769746, "loss": 0.6059797286987305, "step": 207030 }, { "epoch": 1.2306887553423567, "grad_norm": 1.8255730867385864, "learning_rate": 0.00015218954542203743, "loss": 0.6250000476837159, "step": 207040 }, { "epoch": 1.230748197419025, "grad_norm": 1.3818941116333008, "learning_rate": 0.00015218404686527924, "loss": 0.6403711795806885, "step": 207050 }, { "epoch": 1.2308076394956935, "grad_norm": 1.5938403606414795, "learning_rate": 0.00015217854810672634, "loss": 0.5974011898040772, "step": 207060 }, { "epoch": 1.2308670815723617, "grad_norm": 1.4206622838974, "learning_rate": 0.00015217304914640507, "loss": 0.6019692897796631, "step": 207070 }, { "epoch": 1.23092652364903, "grad_norm": 2.099250316619873, "learning_rate": 0.00015216754998434171, "loss": 0.6041581630706787, "step": 207080 }, { "epoch": 1.2309859657256985, "grad_norm": 1.4480262994766235, "learning_rate": 0.00015216205062056255, "loss": 0.5857724189758301, "step": 207090 }, { "epoch": 1.231045407802367, "grad_norm": 1.7852485179901123, "learning_rate": 0.00015215655105509397, "loss": 0.6336675167083741, "step": 207100 }, { "epoch": 1.2311048498790353, "grad_norm": 1.970928430557251, "learning_rate": 0.00015215105128796216, "loss": 0.6153834819793701, "step": 207110 }, { "epoch": 1.2311642919557038, "grad_norm": 1.5297011137008667, "learning_rate": 0.00015214555131919355, "loss": 0.6469795227050781, "step": 207120 }, { "epoch": 1.2312237340323722, "grad_norm": 1.6816773414611816, "learning_rate": 0.00015214005114881437, "loss": 0.617940616607666, "step": 207130 }, { "epoch": 1.2312831761090406, "grad_norm": 1.5521855354309082, "learning_rate": 0.00015213455077685097, "loss": 0.5719244003295898, "step": 207140 }, { "epoch": 1.231342618185709, "grad_norm": 1.6689306497573853, "learning_rate": 0.00015212905020332965, "loss": 0.6064784526824951, "step": 207150 }, { "epoch": 1.2314020602623774, "grad_norm": 1.7110787630081177, "learning_rate": 0.0001521235494282767, "loss": 0.6576334476470947, "step": 207160 }, { "epoch": 1.2314615023390458, "grad_norm": 1.5759587287902832, "learning_rate": 0.0001521180484517185, "loss": 0.6162809371948242, "step": 207170 }, { "epoch": 1.231520944415714, "grad_norm": 1.6722520589828491, "learning_rate": 0.00015211254727368127, "loss": 0.6171045303344727, "step": 207180 }, { "epoch": 1.2315803864923824, "grad_norm": 1.4722422361373901, "learning_rate": 0.0001521070458941914, "loss": 0.5668634414672852, "step": 207190 }, { "epoch": 1.2316398285690509, "grad_norm": 1.2644164562225342, "learning_rate": 0.0001521015443132752, "loss": 0.5982825279235839, "step": 207200 }, { "epoch": 1.2316992706457193, "grad_norm": 1.5299938917160034, "learning_rate": 0.00015209604253095893, "loss": 0.6768664360046387, "step": 207210 }, { "epoch": 1.2317587127223877, "grad_norm": 1.3417307138442993, "learning_rate": 0.00015209054054726896, "loss": 0.5849783897399903, "step": 207220 }, { "epoch": 1.231818154799056, "grad_norm": 1.5393999814987183, "learning_rate": 0.00015208503836223162, "loss": 0.5982182025909424, "step": 207230 }, { "epoch": 1.2318775968757245, "grad_norm": 2.1088674068450928, "learning_rate": 0.0001520795359758732, "loss": 0.5935158729553223, "step": 207240 }, { "epoch": 1.231937038952393, "grad_norm": 1.9085099697113037, "learning_rate": 0.00015207403338822004, "loss": 0.6377269744873046, "step": 207250 }, { "epoch": 1.2319964810290611, "grad_norm": 1.3386223316192627, "learning_rate": 0.00015206853059929843, "loss": 0.5512092590332032, "step": 207260 }, { "epoch": 1.2320559231057295, "grad_norm": 1.6090645790100098, "learning_rate": 0.00015206302760913473, "loss": 0.6391941547393799, "step": 207270 }, { "epoch": 1.232115365182398, "grad_norm": 1.9766979217529297, "learning_rate": 0.00015205752441775527, "loss": 0.5658596992492676, "step": 207280 }, { "epoch": 1.2321748072590664, "grad_norm": 1.0902197360992432, "learning_rate": 0.00015205202102518635, "loss": 0.5635584831237793, "step": 207290 }, { "epoch": 1.2322342493357348, "grad_norm": 1.2642548084259033, "learning_rate": 0.0001520465174314543, "loss": 0.5925588607788086, "step": 207300 }, { "epoch": 1.2322936914124032, "grad_norm": 1.3293169736862183, "learning_rate": 0.00015204101363658546, "loss": 0.6113947868347168, "step": 207310 }, { "epoch": 1.2323531334890716, "grad_norm": 1.9605416059494019, "learning_rate": 0.00015203550964060613, "loss": 0.6266491889953614, "step": 207320 }, { "epoch": 1.23241257556574, "grad_norm": 1.7824996709823608, "learning_rate": 0.00015203000544354266, "loss": 0.6242576122283936, "step": 207330 }, { "epoch": 1.2324720176424084, "grad_norm": 1.3619264364242554, "learning_rate": 0.0001520245010454214, "loss": 0.6540855407714844, "step": 207340 }, { "epoch": 1.2325314597190768, "grad_norm": 1.5151216983795166, "learning_rate": 0.00015201899644626864, "loss": 0.5711363792419434, "step": 207350 }, { "epoch": 1.232590901795745, "grad_norm": 1.4933733940124512, "learning_rate": 0.00015201349164611073, "loss": 0.6276859760284423, "step": 207360 }, { "epoch": 1.2326503438724135, "grad_norm": 2.071429967880249, "learning_rate": 0.000152007986644974, "loss": 0.5689376831054688, "step": 207370 }, { "epoch": 1.2327097859490819, "grad_norm": 1.40299654006958, "learning_rate": 0.00015200248144288487, "loss": 0.5891628265380859, "step": 207380 }, { "epoch": 1.2327692280257503, "grad_norm": 1.2304459810256958, "learning_rate": 0.0001519969760398695, "loss": 0.5784161567687989, "step": 207390 }, { "epoch": 1.2328286701024187, "grad_norm": 1.6451581716537476, "learning_rate": 0.00015199147043595435, "loss": 0.6481056213378906, "step": 207400 }, { "epoch": 1.2328881121790871, "grad_norm": 1.5358405113220215, "learning_rate": 0.00015198596463116576, "loss": 0.591649341583252, "step": 207410 }, { "epoch": 1.2329475542557555, "grad_norm": 1.8000296354293823, "learning_rate": 0.00015198045862553001, "loss": 0.5624802112579346, "step": 207420 }, { "epoch": 1.233006996332424, "grad_norm": 1.2300890684127808, "learning_rate": 0.00015197495241907344, "loss": 0.6147014617919921, "step": 207430 }, { "epoch": 1.2330664384090921, "grad_norm": 1.3280633687973022, "learning_rate": 0.00015196944601182245, "loss": 0.6171362400054932, "step": 207440 }, { "epoch": 1.2331258804857606, "grad_norm": 1.2940844297409058, "learning_rate": 0.00015196393940380333, "loss": 0.6038977622985839, "step": 207450 }, { "epoch": 1.233185322562429, "grad_norm": 1.9207557439804077, "learning_rate": 0.00015195843259504247, "loss": 0.6298720359802246, "step": 207460 }, { "epoch": 1.2332447646390974, "grad_norm": 1.7588914632797241, "learning_rate": 0.00015195292558556616, "loss": 0.5949729919433594, "step": 207470 }, { "epoch": 1.2333042067157658, "grad_norm": 1.5789525508880615, "learning_rate": 0.00015194741837540077, "loss": 0.6290744781494141, "step": 207480 }, { "epoch": 1.2333636487924342, "grad_norm": 1.6893080472946167, "learning_rate": 0.0001519419109645726, "loss": 0.6054695129394532, "step": 207490 }, { "epoch": 1.2334230908691026, "grad_norm": 1.7166645526885986, "learning_rate": 0.00015193640335310808, "loss": 0.6559980392456055, "step": 207500 }, { "epoch": 1.233482532945771, "grad_norm": 1.5755727291107178, "learning_rate": 0.0001519308955410335, "loss": 0.5874792098999023, "step": 207510 }, { "epoch": 1.2335419750224395, "grad_norm": 1.3839768171310425, "learning_rate": 0.0001519253875283752, "loss": 0.6379919052124023, "step": 207520 }, { "epoch": 1.2336014170991079, "grad_norm": 1.5963844060897827, "learning_rate": 0.00015191987931515954, "loss": 0.6049478054046631, "step": 207530 }, { "epoch": 1.2336608591757763, "grad_norm": 1.7782231569290161, "learning_rate": 0.00015191437090141292, "loss": 0.5865307807922363, "step": 207540 }, { "epoch": 1.2337203012524445, "grad_norm": 1.5704816579818726, "learning_rate": 0.00015190886228716162, "loss": 0.5966449737548828, "step": 207550 }, { "epoch": 1.2337797433291129, "grad_norm": 1.5641803741455078, "learning_rate": 0.00015190335347243204, "loss": 0.5930486679077148, "step": 207560 }, { "epoch": 1.2338391854057813, "grad_norm": 1.3141294717788696, "learning_rate": 0.00015189784445725045, "loss": 0.5962178707122803, "step": 207570 }, { "epoch": 1.2338986274824497, "grad_norm": 1.872515082359314, "learning_rate": 0.00015189233524164335, "loss": 0.6704938888549805, "step": 207580 }, { "epoch": 1.2339580695591181, "grad_norm": 1.884861707687378, "learning_rate": 0.00015188682582563696, "loss": 0.5904778480529785, "step": 207590 }, { "epoch": 1.2340175116357865, "grad_norm": 1.802217960357666, "learning_rate": 0.0001518813162092577, "loss": 0.5563447952270508, "step": 207600 }, { "epoch": 1.234076953712455, "grad_norm": 1.5942845344543457, "learning_rate": 0.00015187580639253192, "loss": 0.5236064910888671, "step": 207610 }, { "epoch": 1.2341363957891234, "grad_norm": 1.6642833948135376, "learning_rate": 0.00015187029637548594, "loss": 0.5955497741699218, "step": 207620 }, { "epoch": 1.2341958378657916, "grad_norm": 1.6319983005523682, "learning_rate": 0.00015186478615814613, "loss": 0.5976963043212891, "step": 207630 }, { "epoch": 1.23425527994246, "grad_norm": 1.6000874042510986, "learning_rate": 0.0001518592757405389, "loss": 0.6878212928771973, "step": 207640 }, { "epoch": 1.2343147220191284, "grad_norm": 1.4784427881240845, "learning_rate": 0.00015185376512269057, "loss": 0.6189927101135254, "step": 207650 }, { "epoch": 1.2343741640957968, "grad_norm": 1.9068691730499268, "learning_rate": 0.00015184825430462751, "loss": 0.6224468231201172, "step": 207660 }, { "epoch": 1.2344336061724652, "grad_norm": 1.6971964836120605, "learning_rate": 0.00015184274328637604, "loss": 0.5912695407867432, "step": 207670 }, { "epoch": 1.2344930482491336, "grad_norm": 1.6559478044509888, "learning_rate": 0.00015183723206796257, "loss": 0.6355905532836914, "step": 207680 }, { "epoch": 1.234552490325802, "grad_norm": 1.409274935722351, "learning_rate": 0.00015183172064941352, "loss": 0.6072717666625976, "step": 207690 }, { "epoch": 1.2346119324024705, "grad_norm": 1.4340527057647705, "learning_rate": 0.00015182620903075514, "loss": 0.5998610496520996, "step": 207700 }, { "epoch": 1.2346713744791389, "grad_norm": 1.8381965160369873, "learning_rate": 0.00015182069721201384, "loss": 0.5513118267059326, "step": 207710 }, { "epoch": 1.2347308165558073, "grad_norm": 2.0529117584228516, "learning_rate": 0.000151815185193216, "loss": 0.6543993473052978, "step": 207720 }, { "epoch": 1.2347902586324755, "grad_norm": 1.733908772468567, "learning_rate": 0.00015180967297438795, "loss": 0.6009228706359864, "step": 207730 }, { "epoch": 1.234849700709144, "grad_norm": 1.6535500288009644, "learning_rate": 0.00015180416055555614, "loss": 0.667143726348877, "step": 207740 }, { "epoch": 1.2349091427858123, "grad_norm": 1.6262469291687012, "learning_rate": 0.00015179864793674687, "loss": 0.5587665557861328, "step": 207750 }, { "epoch": 1.2349685848624807, "grad_norm": 1.552892804145813, "learning_rate": 0.0001517931351179865, "loss": 0.6136029720306396, "step": 207760 }, { "epoch": 1.2350280269391491, "grad_norm": 1.5094844102859497, "learning_rate": 0.00015178762209930145, "loss": 0.6613075733184814, "step": 207770 }, { "epoch": 1.2350874690158176, "grad_norm": 1.4581489562988281, "learning_rate": 0.0001517821088807181, "loss": 0.5508085250854492, "step": 207780 }, { "epoch": 1.235146911092486, "grad_norm": 1.4536653757095337, "learning_rate": 0.00015177659546226278, "loss": 0.5989665985107422, "step": 207790 }, { "epoch": 1.2352063531691544, "grad_norm": 2.111729383468628, "learning_rate": 0.00015177108184396185, "loss": 0.6270876407623291, "step": 207800 }, { "epoch": 1.2352657952458226, "grad_norm": 1.6747528314590454, "learning_rate": 0.00015176556802584174, "loss": 0.6047790050506592, "step": 207810 }, { "epoch": 1.235325237322491, "grad_norm": 1.9825129508972168, "learning_rate": 0.0001517600540079288, "loss": 0.6277789115905762, "step": 207820 }, { "epoch": 1.2353846793991594, "grad_norm": 1.4620052576065063, "learning_rate": 0.00015175453979024937, "loss": 0.5833873748779297, "step": 207830 }, { "epoch": 1.2354441214758278, "grad_norm": 1.0327345132827759, "learning_rate": 0.00015174902537282996, "loss": 0.5759522914886475, "step": 207840 }, { "epoch": 1.2355035635524962, "grad_norm": 1.187816858291626, "learning_rate": 0.00015174351075569677, "loss": 0.5867771148681641, "step": 207850 }, { "epoch": 1.2355630056291647, "grad_norm": 1.6160444021224976, "learning_rate": 0.00015173799593887628, "loss": 0.6014543533325195, "step": 207860 }, { "epoch": 1.235622447705833, "grad_norm": 1.6240214109420776, "learning_rate": 0.00015173248092239492, "loss": 0.6588437557220459, "step": 207870 }, { "epoch": 1.2356818897825015, "grad_norm": 1.7442044019699097, "learning_rate": 0.00015172696570627894, "loss": 0.6418922901153564, "step": 207880 }, { "epoch": 1.23574133185917, "grad_norm": 1.3245630264282227, "learning_rate": 0.0001517214502905548, "loss": 0.6206966400146484, "step": 207890 }, { "epoch": 1.2358007739358383, "grad_norm": 1.5956649780273438, "learning_rate": 0.00015171593467524892, "loss": 0.5838430404663086, "step": 207900 }, { "epoch": 1.2358602160125067, "grad_norm": 1.6254135370254517, "learning_rate": 0.0001517104188603876, "loss": 0.658119010925293, "step": 207910 }, { "epoch": 1.235919658089175, "grad_norm": 1.7442269325256348, "learning_rate": 0.00015170490284599727, "loss": 0.5850459575653076, "step": 207920 }, { "epoch": 1.2359791001658433, "grad_norm": 1.5247619152069092, "learning_rate": 0.00015169938663210436, "loss": 0.6305514812469483, "step": 207930 }, { "epoch": 1.2360385422425118, "grad_norm": 1.4176573753356934, "learning_rate": 0.00015169387021873512, "loss": 0.5607720375061035, "step": 207940 }, { "epoch": 1.2360979843191802, "grad_norm": 1.4670696258544922, "learning_rate": 0.00015168835360591612, "loss": 0.6137639999389648, "step": 207950 }, { "epoch": 1.2361574263958486, "grad_norm": 2.043825387954712, "learning_rate": 0.00015168283679367362, "loss": 0.6440237998962403, "step": 207960 }, { "epoch": 1.236216868472517, "grad_norm": 1.4487519264221191, "learning_rate": 0.00015167731978203407, "loss": 0.6108289241790772, "step": 207970 }, { "epoch": 1.2362763105491854, "grad_norm": 1.627233624458313, "learning_rate": 0.00015167180257102383, "loss": 0.5842711448669433, "step": 207980 }, { "epoch": 1.2363357526258538, "grad_norm": 1.8665497303009033, "learning_rate": 0.0001516662851606693, "loss": 0.6003932952880859, "step": 207990 }, { "epoch": 1.236395194702522, "grad_norm": 1.3956345319747925, "learning_rate": 0.0001516607675509969, "loss": 0.5694740295410157, "step": 208000 }, { "epoch": 1.2364546367791904, "grad_norm": 1.5145390033721924, "learning_rate": 0.000151655249742033, "loss": 0.5884188652038574, "step": 208010 }, { "epoch": 1.2365140788558588, "grad_norm": 1.2737903594970703, "learning_rate": 0.00015164973173380396, "loss": 0.6595887184143067, "step": 208020 }, { "epoch": 1.2365735209325273, "grad_norm": 1.7896047830581665, "learning_rate": 0.00015164421352633625, "loss": 0.6917859077453613, "step": 208030 }, { "epoch": 1.2366329630091957, "grad_norm": 1.6470128297805786, "learning_rate": 0.0001516386951196562, "loss": 0.6314092636108398, "step": 208040 }, { "epoch": 1.236692405085864, "grad_norm": 1.5480003356933594, "learning_rate": 0.00015163317651379027, "loss": 0.5927677631378174, "step": 208050 }, { "epoch": 1.2367518471625325, "grad_norm": 2.1427977085113525, "learning_rate": 0.0001516276577087648, "loss": 0.6639420509338378, "step": 208060 }, { "epoch": 1.236811289239201, "grad_norm": 1.7800098657608032, "learning_rate": 0.00015162213870460628, "loss": 0.6194014549255371, "step": 208070 }, { "epoch": 1.2368707313158693, "grad_norm": 1.4782618284225464, "learning_rate": 0.000151616619501341, "loss": 0.6007512092590332, "step": 208080 }, { "epoch": 1.2369301733925377, "grad_norm": 1.5260709524154663, "learning_rate": 0.00015161110009899543, "loss": 0.5510889530181885, "step": 208090 }, { "epoch": 1.236989615469206, "grad_norm": 1.905250072479248, "learning_rate": 0.00015160558049759595, "loss": 0.6371206283569336, "step": 208100 }, { "epoch": 1.2370490575458744, "grad_norm": 1.4116092920303345, "learning_rate": 0.00015160006069716897, "loss": 0.607830286026001, "step": 208110 }, { "epoch": 1.2371084996225428, "grad_norm": 1.5395591259002686, "learning_rate": 0.0001515945406977409, "loss": 0.618247127532959, "step": 208120 }, { "epoch": 1.2371679416992112, "grad_norm": 1.2929531335830688, "learning_rate": 0.0001515890204993381, "loss": 0.619323444366455, "step": 208130 }, { "epoch": 1.2372273837758796, "grad_norm": 1.6815123558044434, "learning_rate": 0.0001515835001019871, "loss": 0.6154835224151611, "step": 208140 }, { "epoch": 1.237286825852548, "grad_norm": 1.6243282556533813, "learning_rate": 0.00015157797950571418, "loss": 0.6254354000091553, "step": 208150 }, { "epoch": 1.2373462679292164, "grad_norm": 1.7370845079421997, "learning_rate": 0.00015157245871054575, "loss": 0.5565398216247559, "step": 208160 }, { "epoch": 1.2374057100058848, "grad_norm": 1.7664562463760376, "learning_rate": 0.00015156693771650832, "loss": 0.6218401908874511, "step": 208170 }, { "epoch": 1.237465152082553, "grad_norm": 1.6261529922485352, "learning_rate": 0.00015156141652362826, "loss": 0.6647714138031006, "step": 208180 }, { "epoch": 1.2375245941592214, "grad_norm": 1.623305082321167, "learning_rate": 0.00015155589513193192, "loss": 0.5737642288208008, "step": 208190 }, { "epoch": 1.2375840362358899, "grad_norm": 1.3511388301849365, "learning_rate": 0.00015155037354144577, "loss": 0.622611141204834, "step": 208200 }, { "epoch": 1.2376434783125583, "grad_norm": 1.5408625602722168, "learning_rate": 0.0001515448517521962, "loss": 0.5944776058197021, "step": 208210 }, { "epoch": 1.2377029203892267, "grad_norm": 1.4202839136123657, "learning_rate": 0.00015153932976420966, "loss": 0.624342966079712, "step": 208220 }, { "epoch": 1.237762362465895, "grad_norm": 1.3072443008422852, "learning_rate": 0.00015153380757751254, "loss": 0.5679570198059082, "step": 208230 }, { "epoch": 1.2378218045425635, "grad_norm": 1.5605524778366089, "learning_rate": 0.00015152828519213125, "loss": 0.6004837989807129, "step": 208240 }, { "epoch": 1.237881246619232, "grad_norm": 1.483574390411377, "learning_rate": 0.00015152276260809223, "loss": 0.6109509468078613, "step": 208250 }, { "epoch": 1.2379406886959003, "grad_norm": 1.6104097366333008, "learning_rate": 0.00015151723982542186, "loss": 0.6556347846984864, "step": 208260 }, { "epoch": 1.2380001307725688, "grad_norm": 1.796862006187439, "learning_rate": 0.0001515117168441466, "loss": 0.5914541244506836, "step": 208270 }, { "epoch": 1.2380595728492372, "grad_norm": 1.4471611976623535, "learning_rate": 0.00015150619366429284, "loss": 0.5892528057098388, "step": 208280 }, { "epoch": 1.2381190149259054, "grad_norm": 1.84904944896698, "learning_rate": 0.000151500670285887, "loss": 0.5987564563751221, "step": 208290 }, { "epoch": 1.2381784570025738, "grad_norm": 1.4984503984451294, "learning_rate": 0.00015149514670895556, "loss": 0.6257696628570557, "step": 208300 }, { "epoch": 1.2382378990792422, "grad_norm": 1.5363283157348633, "learning_rate": 0.00015148962293352487, "loss": 0.6001992702484131, "step": 208310 }, { "epoch": 1.2382973411559106, "grad_norm": 1.7673953771591187, "learning_rate": 0.00015148409895962136, "loss": 0.6831371307373046, "step": 208320 }, { "epoch": 1.238356783232579, "grad_norm": 1.5629255771636963, "learning_rate": 0.00015147857478727155, "loss": 0.6454080104827881, "step": 208330 }, { "epoch": 1.2384162253092474, "grad_norm": 2.9720356464385986, "learning_rate": 0.00015147305041650173, "loss": 0.6216719627380372, "step": 208340 }, { "epoch": 1.2384756673859159, "grad_norm": 1.494468331336975, "learning_rate": 0.00015146752584733838, "loss": 0.5411991596221923, "step": 208350 }, { "epoch": 1.2385351094625843, "grad_norm": 1.5426841974258423, "learning_rate": 0.000151462001079808, "loss": 0.5951200485229492, "step": 208360 }, { "epoch": 1.2385945515392525, "grad_norm": 1.6978158950805664, "learning_rate": 0.0001514564761139369, "loss": 0.6468677043914794, "step": 208370 }, { "epoch": 1.2386539936159209, "grad_norm": 1.3998678922653198, "learning_rate": 0.0001514509509497516, "loss": 0.5875473022460938, "step": 208380 }, { "epoch": 1.2387134356925893, "grad_norm": 1.424752950668335, "learning_rate": 0.0001514454255872785, "loss": 0.6418292045593261, "step": 208390 }, { "epoch": 1.2387728777692577, "grad_norm": 1.4840333461761475, "learning_rate": 0.000151439900026544, "loss": 0.6023664474487305, "step": 208400 }, { "epoch": 1.2388323198459261, "grad_norm": 1.6118155717849731, "learning_rate": 0.0001514343742675746, "loss": 0.6380680084228516, "step": 208410 }, { "epoch": 1.2388917619225945, "grad_norm": 1.4397835731506348, "learning_rate": 0.00015142884831039667, "loss": 0.5297568321228028, "step": 208420 }, { "epoch": 1.238951203999263, "grad_norm": 1.9792678356170654, "learning_rate": 0.00015142332215503665, "loss": 0.6224629402160644, "step": 208430 }, { "epoch": 1.2390106460759314, "grad_norm": 1.5207602977752686, "learning_rate": 0.00015141779580152103, "loss": 0.6334986686706543, "step": 208440 }, { "epoch": 1.2390700881525998, "grad_norm": 1.6721636056900024, "learning_rate": 0.00015141226924987619, "loss": 0.5906455993652344, "step": 208450 }, { "epoch": 1.2391295302292682, "grad_norm": 1.475499153137207, "learning_rate": 0.0001514067425001286, "loss": 0.6240387916564941, "step": 208460 }, { "epoch": 1.2391889723059364, "grad_norm": 1.9012298583984375, "learning_rate": 0.00015140121555230467, "loss": 0.6041292667388916, "step": 208470 }, { "epoch": 1.2392484143826048, "grad_norm": 1.7699085474014282, "learning_rate": 0.00015139568840643087, "loss": 0.5855148315429688, "step": 208480 }, { "epoch": 1.2393078564592732, "grad_norm": 2.0075340270996094, "learning_rate": 0.00015139016106253362, "loss": 0.598534631729126, "step": 208490 }, { "epoch": 1.2393672985359416, "grad_norm": 1.5762417316436768, "learning_rate": 0.00015138463352063934, "loss": 0.6037800788879395, "step": 208500 }, { "epoch": 1.23942674061261, "grad_norm": 1.4857152700424194, "learning_rate": 0.0001513791057807745, "loss": 0.5970654010772705, "step": 208510 }, { "epoch": 1.2394861826892785, "grad_norm": 1.5223424434661865, "learning_rate": 0.0001513735778429656, "loss": 0.6077613353729248, "step": 208520 }, { "epoch": 1.2395456247659469, "grad_norm": 1.2917335033416748, "learning_rate": 0.00015136804970723898, "loss": 0.6139552593231201, "step": 208530 }, { "epoch": 1.2396050668426153, "grad_norm": 1.6524169445037842, "learning_rate": 0.00015136252137362113, "loss": 0.6106997966766358, "step": 208540 }, { "epoch": 1.2396645089192835, "grad_norm": 1.5347117185592651, "learning_rate": 0.0001513569928421385, "loss": 0.5934815406799316, "step": 208550 }, { "epoch": 1.239723950995952, "grad_norm": 1.4351491928100586, "learning_rate": 0.00015135146411281752, "loss": 0.5920557975769043, "step": 208560 }, { "epoch": 1.2397833930726203, "grad_norm": 1.6791431903839111, "learning_rate": 0.00015134593518568466, "loss": 0.5873779773712158, "step": 208570 }, { "epoch": 1.2398428351492887, "grad_norm": 1.784505844116211, "learning_rate": 0.0001513404060607664, "loss": 0.599254035949707, "step": 208580 }, { "epoch": 1.2399022772259571, "grad_norm": 1.8212920427322388, "learning_rate": 0.0001513348767380891, "loss": 0.5867260456085205, "step": 208590 }, { "epoch": 1.2399617193026256, "grad_norm": 1.667304277420044, "learning_rate": 0.00015132934721767924, "loss": 0.6156740188598633, "step": 208600 }, { "epoch": 1.240021161379294, "grad_norm": 1.686022400856018, "learning_rate": 0.00015132381749956335, "loss": 0.6122688293457031, "step": 208610 }, { "epoch": 1.2400806034559624, "grad_norm": 2.065113067626953, "learning_rate": 0.00015131828758376778, "loss": 0.6500207901000976, "step": 208620 }, { "epoch": 1.2401400455326308, "grad_norm": 1.450616478919983, "learning_rate": 0.00015131275747031902, "loss": 0.5965993881225586, "step": 208630 }, { "epoch": 1.2401994876092992, "grad_norm": 1.6679154634475708, "learning_rate": 0.00015130722715924356, "loss": 0.6553311824798584, "step": 208640 }, { "epoch": 1.2402589296859676, "grad_norm": 1.4673936367034912, "learning_rate": 0.00015130169665056778, "loss": 0.6100871086120605, "step": 208650 }, { "epoch": 1.2403183717626358, "grad_norm": 1.5327578783035278, "learning_rate": 0.00015129616594431822, "loss": 0.6322575092315674, "step": 208660 }, { "epoch": 1.2403778138393042, "grad_norm": 1.323957920074463, "learning_rate": 0.0001512906350405213, "loss": 0.5935844421386719, "step": 208670 }, { "epoch": 1.2404372559159726, "grad_norm": 1.7474435567855835, "learning_rate": 0.00015128510393920346, "loss": 0.6245792388916016, "step": 208680 }, { "epoch": 1.240496697992641, "grad_norm": 1.8390716314315796, "learning_rate": 0.00015127957264039117, "loss": 0.5945323944091797, "step": 208690 }, { "epoch": 1.2405561400693095, "grad_norm": 2.598721981048584, "learning_rate": 0.0001512740411441109, "loss": 0.6241001129150391, "step": 208700 }, { "epoch": 1.240615582145978, "grad_norm": 1.3219481706619263, "learning_rate": 0.00015126850945038908, "loss": 0.6041166305541992, "step": 208710 }, { "epoch": 1.2406750242226463, "grad_norm": 1.534618616104126, "learning_rate": 0.00015126297755925226, "loss": 0.567377758026123, "step": 208720 }, { "epoch": 1.2407344662993147, "grad_norm": 1.3702574968338013, "learning_rate": 0.0001512574454707268, "loss": 0.5331259727478027, "step": 208730 }, { "epoch": 1.240793908375983, "grad_norm": 2.020681619644165, "learning_rate": 0.00015125191318483922, "loss": 0.6128005981445312, "step": 208740 }, { "epoch": 1.2408533504526513, "grad_norm": 1.4487483501434326, "learning_rate": 0.00015124638070161594, "loss": 0.6203222274780273, "step": 208750 }, { "epoch": 1.2409127925293197, "grad_norm": 1.2215319871902466, "learning_rate": 0.00015124084802108347, "loss": 0.645404863357544, "step": 208760 }, { "epoch": 1.2409722346059882, "grad_norm": 1.7349727153778076, "learning_rate": 0.00015123531514326828, "loss": 0.5703300476074219, "step": 208770 }, { "epoch": 1.2410316766826566, "grad_norm": 1.8335005044937134, "learning_rate": 0.00015122978206819678, "loss": 0.611359691619873, "step": 208780 }, { "epoch": 1.241091118759325, "grad_norm": 1.812063217163086, "learning_rate": 0.0001512242487958955, "loss": 0.5827619552612304, "step": 208790 }, { "epoch": 1.2411505608359934, "grad_norm": 1.80622136592865, "learning_rate": 0.0001512187153263909, "loss": 0.5980594635009766, "step": 208800 }, { "epoch": 1.2412100029126618, "grad_norm": 1.3491243124008179, "learning_rate": 0.0001512131816597094, "loss": 0.6584748268127442, "step": 208810 }, { "epoch": 1.2412694449893302, "grad_norm": 1.2758021354675293, "learning_rate": 0.00015120764779587753, "loss": 0.5589494228363037, "step": 208820 }, { "epoch": 1.2413288870659986, "grad_norm": 1.9006273746490479, "learning_rate": 0.00015120211373492176, "loss": 0.610474967956543, "step": 208830 }, { "epoch": 1.2413883291426668, "grad_norm": 1.5278117656707764, "learning_rate": 0.00015119657947686846, "loss": 0.6239786148071289, "step": 208840 }, { "epoch": 1.2414477712193352, "grad_norm": 1.3562582731246948, "learning_rate": 0.0001511910450217443, "loss": 0.5650184154510498, "step": 208850 }, { "epoch": 1.2415072132960037, "grad_norm": 1.2856245040893555, "learning_rate": 0.0001511855103695756, "loss": 0.6006786346435546, "step": 208860 }, { "epoch": 1.241566655372672, "grad_norm": 1.4958336353302002, "learning_rate": 0.00015117997552038884, "loss": 0.6250340938568115, "step": 208870 }, { "epoch": 1.2416260974493405, "grad_norm": 1.6707226037979126, "learning_rate": 0.00015117444047421053, "loss": 0.6480698108673095, "step": 208880 }, { "epoch": 1.241685539526009, "grad_norm": 1.7806810140609741, "learning_rate": 0.00015116890523106722, "loss": 0.5686107635498047, "step": 208890 }, { "epoch": 1.2417449816026773, "grad_norm": 1.623057246208191, "learning_rate": 0.0001511633697909853, "loss": 0.6281482219696045, "step": 208900 }, { "epoch": 1.2418044236793457, "grad_norm": 1.339845061302185, "learning_rate": 0.00015115783415399126, "loss": 0.5965677738189697, "step": 208910 }, { "epoch": 1.241863865756014, "grad_norm": 1.4207139015197754, "learning_rate": 0.00015115229832011158, "loss": 0.6543376922607422, "step": 208920 }, { "epoch": 1.2419233078326823, "grad_norm": 2.282341241836548, "learning_rate": 0.00015114676228937274, "loss": 0.6194717407226562, "step": 208930 }, { "epoch": 1.2419827499093508, "grad_norm": 1.5882045030593872, "learning_rate": 0.00015114122606180126, "loss": 0.5924376964569091, "step": 208940 }, { "epoch": 1.2420421919860192, "grad_norm": 1.940156102180481, "learning_rate": 0.0001511356896374236, "loss": 0.6291042327880859, "step": 208950 }, { "epoch": 1.2421016340626876, "grad_norm": 1.6106889247894287, "learning_rate": 0.00015113015301626624, "loss": 0.6103250503540039, "step": 208960 }, { "epoch": 1.242161076139356, "grad_norm": 1.2851020097732544, "learning_rate": 0.00015112461619835567, "loss": 0.6157033443450928, "step": 208970 }, { "epoch": 1.2422205182160244, "grad_norm": 1.8260436058044434, "learning_rate": 0.00015111907918371838, "loss": 0.6108097076416016, "step": 208980 }, { "epoch": 1.2422799602926928, "grad_norm": 1.7533470392227173, "learning_rate": 0.00015111354197238085, "loss": 0.6248040199279785, "step": 208990 }, { "epoch": 1.2423394023693612, "grad_norm": 2.1604433059692383, "learning_rate": 0.00015110800456436958, "loss": 0.6915701866149903, "step": 209000 }, { "epoch": 1.2423988444460297, "grad_norm": 1.3928669691085815, "learning_rate": 0.00015110246695971104, "loss": 0.6088080406188965, "step": 209010 }, { "epoch": 1.242458286522698, "grad_norm": 1.4477434158325195, "learning_rate": 0.00015109692915843173, "loss": 0.5711066246032714, "step": 209020 }, { "epoch": 1.2425177285993663, "grad_norm": 1.6871167421340942, "learning_rate": 0.00015109139116055816, "loss": 0.5944492816925049, "step": 209030 }, { "epoch": 1.2425771706760347, "grad_norm": 1.5549063682556152, "learning_rate": 0.00015108585296611676, "loss": 0.5796882629394531, "step": 209040 }, { "epoch": 1.242636612752703, "grad_norm": 1.906733512878418, "learning_rate": 0.00015108031457513409, "loss": 0.6393793106079102, "step": 209050 }, { "epoch": 1.2426960548293715, "grad_norm": 1.6667790412902832, "learning_rate": 0.00015107477598763665, "loss": 0.6444152355194092, "step": 209060 }, { "epoch": 1.24275549690604, "grad_norm": 1.6428195238113403, "learning_rate": 0.00015106923720365086, "loss": 0.5891057014465332, "step": 209070 }, { "epoch": 1.2428149389827083, "grad_norm": 1.167445182800293, "learning_rate": 0.0001510636982232033, "loss": 0.615750789642334, "step": 209080 }, { "epoch": 1.2428743810593768, "grad_norm": 1.8568084239959717, "learning_rate": 0.0001510581590463204, "loss": 0.6018896102905273, "step": 209090 }, { "epoch": 1.2429338231360452, "grad_norm": 1.5620007514953613, "learning_rate": 0.0001510526196730287, "loss": 0.6013402938842773, "step": 209100 }, { "epoch": 1.2429932652127134, "grad_norm": 1.7620019912719727, "learning_rate": 0.0001510470801033547, "loss": 0.5772802829742432, "step": 209110 }, { "epoch": 1.2430527072893818, "grad_norm": 1.5057989358901978, "learning_rate": 0.0001510415403373248, "loss": 0.5939093589782715, "step": 209120 }, { "epoch": 1.2431121493660502, "grad_norm": 1.715225100517273, "learning_rate": 0.0001510360003749657, "loss": 0.6525252342224122, "step": 209130 }, { "epoch": 1.2431715914427186, "grad_norm": 1.4871330261230469, "learning_rate": 0.0001510304602163037, "loss": 0.6130416870117188, "step": 209140 }, { "epoch": 1.243231033519387, "grad_norm": 1.6924992799758911, "learning_rate": 0.0001510249198613654, "loss": 0.6542969703674316, "step": 209150 }, { "epoch": 1.2432904755960554, "grad_norm": 1.2383712530136108, "learning_rate": 0.00015101937931017733, "loss": 0.6309823036193848, "step": 209160 }, { "epoch": 1.2433499176727238, "grad_norm": 1.50704824924469, "learning_rate": 0.0001510138385627659, "loss": 0.6587719440460205, "step": 209170 }, { "epoch": 1.2434093597493923, "grad_norm": 1.677819013595581, "learning_rate": 0.0001510082976191577, "loss": 0.6386301517486572, "step": 209180 }, { "epoch": 1.2434688018260607, "grad_norm": 1.3462674617767334, "learning_rate": 0.00015100275647937924, "loss": 0.5401679992675781, "step": 209190 }, { "epoch": 1.243528243902729, "grad_norm": 1.2316313982009888, "learning_rate": 0.00015099721514345691, "loss": 0.591371726989746, "step": 209200 }, { "epoch": 1.2435876859793973, "grad_norm": 1.3719706535339355, "learning_rate": 0.00015099167361141738, "loss": 0.5641042709350585, "step": 209210 }, { "epoch": 1.2436471280560657, "grad_norm": 2.645261764526367, "learning_rate": 0.00015098613188328704, "loss": 0.6013171195983886, "step": 209220 }, { "epoch": 1.2437065701327341, "grad_norm": 1.2129067182540894, "learning_rate": 0.00015098058995909248, "loss": 0.5707755565643311, "step": 209230 }, { "epoch": 1.2437660122094025, "grad_norm": 1.5261290073394775, "learning_rate": 0.00015097504783886012, "loss": 0.5806598663330078, "step": 209240 }, { "epoch": 1.243825454286071, "grad_norm": 1.3665820360183716, "learning_rate": 0.00015096950552261656, "loss": 0.6224761009216309, "step": 209250 }, { "epoch": 1.2438848963627394, "grad_norm": 1.1954225301742554, "learning_rate": 0.00015096396301038825, "loss": 0.5747558116912842, "step": 209260 }, { "epoch": 1.2439443384394078, "grad_norm": 1.7311336994171143, "learning_rate": 0.0001509584203022017, "loss": 0.6257383346557617, "step": 209270 }, { "epoch": 1.2440037805160762, "grad_norm": 1.675202488899231, "learning_rate": 0.0001509528773980835, "loss": 0.6083033561706543, "step": 209280 }, { "epoch": 1.2440632225927444, "grad_norm": 1.6707851886749268, "learning_rate": 0.00015094733429806012, "loss": 0.6359865188598632, "step": 209290 }, { "epoch": 1.2441226646694128, "grad_norm": 1.6596345901489258, "learning_rate": 0.00015094179100215804, "loss": 0.5865521430969238, "step": 209300 }, { "epoch": 1.2441821067460812, "grad_norm": 1.5761021375656128, "learning_rate": 0.00015093624751040383, "loss": 0.6496184825897217, "step": 209310 }, { "epoch": 1.2442415488227496, "grad_norm": 1.4696733951568604, "learning_rate": 0.000150930703822824, "loss": 0.6158246517181396, "step": 209320 }, { "epoch": 1.244300990899418, "grad_norm": 1.1582667827606201, "learning_rate": 0.00015092515993944504, "loss": 0.5758742809295654, "step": 209330 }, { "epoch": 1.2443604329760865, "grad_norm": 1.5079514980316162, "learning_rate": 0.0001509196158602935, "loss": 0.6185088157653809, "step": 209340 }, { "epoch": 1.2444198750527549, "grad_norm": 1.888521432876587, "learning_rate": 0.0001509140715853959, "loss": 0.6375243186950683, "step": 209350 }, { "epoch": 1.2444793171294233, "grad_norm": 1.3602633476257324, "learning_rate": 0.00015090852711477875, "loss": 0.5758517265319825, "step": 209360 }, { "epoch": 1.2445387592060917, "grad_norm": 1.9257248640060425, "learning_rate": 0.00015090298244846857, "loss": 0.6315191745758056, "step": 209370 }, { "epoch": 1.24459820128276, "grad_norm": 1.7124199867248535, "learning_rate": 0.00015089743758649185, "loss": 0.6080615520477295, "step": 209380 }, { "epoch": 1.2446576433594285, "grad_norm": 1.4679511785507202, "learning_rate": 0.00015089189252887522, "loss": 0.6221304416656495, "step": 209390 }, { "epoch": 1.2447170854360967, "grad_norm": 1.5149295330047607, "learning_rate": 0.0001508863472756451, "loss": 0.6079599857330322, "step": 209400 }, { "epoch": 1.2447765275127651, "grad_norm": 1.6153483390808105, "learning_rate": 0.0001508808018268281, "loss": 0.6554834842681885, "step": 209410 }, { "epoch": 1.2448359695894335, "grad_norm": 1.4691200256347656, "learning_rate": 0.00015087525618245065, "loss": 0.604917049407959, "step": 209420 }, { "epoch": 1.244895411666102, "grad_norm": 1.4694331884384155, "learning_rate": 0.00015086971034253933, "loss": 0.5926801681518554, "step": 209430 }, { "epoch": 1.2449548537427704, "grad_norm": 1.7395086288452148, "learning_rate": 0.0001508641643071207, "loss": 0.5916415214538574, "step": 209440 }, { "epoch": 1.2450142958194388, "grad_norm": 1.6806563138961792, "learning_rate": 0.00015085861807622125, "loss": 0.6284224033355713, "step": 209450 }, { "epoch": 1.2450737378961072, "grad_norm": 1.3457611799240112, "learning_rate": 0.00015085307164986752, "loss": 0.5962460041046143, "step": 209460 }, { "epoch": 1.2451331799727756, "grad_norm": 1.69441556930542, "learning_rate": 0.0001508475250280861, "loss": 0.6391110420227051, "step": 209470 }, { "epoch": 1.2451926220494438, "grad_norm": 1.3578051328659058, "learning_rate": 0.00015084197821090342, "loss": 0.5724967002868653, "step": 209480 }, { "epoch": 1.2452520641261122, "grad_norm": 1.6075046062469482, "learning_rate": 0.00015083643119834605, "loss": 0.5765197277069092, "step": 209490 }, { "epoch": 1.2453115062027806, "grad_norm": 1.7824386358261108, "learning_rate": 0.00015083088399044057, "loss": 0.610652494430542, "step": 209500 }, { "epoch": 1.245370948279449, "grad_norm": 1.6263315677642822, "learning_rate": 0.00015082533658721347, "loss": 0.6719734191894531, "step": 209510 }, { "epoch": 1.2454303903561175, "grad_norm": 1.80565345287323, "learning_rate": 0.0001508197889886913, "loss": 0.5716497421264648, "step": 209520 }, { "epoch": 1.2454898324327859, "grad_norm": 1.7121450901031494, "learning_rate": 0.00015081424119490062, "loss": 0.6934792518615722, "step": 209530 }, { "epoch": 1.2455492745094543, "grad_norm": 1.5113840103149414, "learning_rate": 0.00015080869320586795, "loss": 0.6144886970520019, "step": 209540 }, { "epoch": 1.2456087165861227, "grad_norm": 1.5679718255996704, "learning_rate": 0.00015080314502161982, "loss": 0.5733284473419189, "step": 209550 }, { "epoch": 1.2456681586627911, "grad_norm": 2.2630600929260254, "learning_rate": 0.00015079759664218275, "loss": 0.6526983261108399, "step": 209560 }, { "epoch": 1.2457276007394595, "grad_norm": 1.7628655433654785, "learning_rate": 0.00015079204806758332, "loss": 0.584708309173584, "step": 209570 }, { "epoch": 1.2457870428161277, "grad_norm": 1.8839887380599976, "learning_rate": 0.0001507864992978481, "loss": 0.589762830734253, "step": 209580 }, { "epoch": 1.2458464848927961, "grad_norm": 1.5315933227539062, "learning_rate": 0.00015078095033300355, "loss": 0.6296416282653808, "step": 209590 }, { "epoch": 1.2459059269694646, "grad_norm": 1.4953893423080444, "learning_rate": 0.0001507754011730763, "loss": 0.5778814315795898, "step": 209600 }, { "epoch": 1.245965369046133, "grad_norm": 1.977112889289856, "learning_rate": 0.0001507698518180928, "loss": 0.6718624114990235, "step": 209610 }, { "epoch": 1.2460248111228014, "grad_norm": 2.1161882877349854, "learning_rate": 0.00015076430226807972, "loss": 0.6389591217041015, "step": 209620 }, { "epoch": 1.2460842531994698, "grad_norm": 1.1456902027130127, "learning_rate": 0.0001507587525230635, "loss": 0.620154857635498, "step": 209630 }, { "epoch": 1.2461436952761382, "grad_norm": 1.7686668634414673, "learning_rate": 0.00015075320258307073, "loss": 0.6180302619934082, "step": 209640 }, { "epoch": 1.2462031373528066, "grad_norm": 2.099247694015503, "learning_rate": 0.00015074765244812798, "loss": 0.5996715545654296, "step": 209650 }, { "epoch": 1.2462625794294748, "grad_norm": 1.8359326124191284, "learning_rate": 0.00015074210211826175, "loss": 0.6126734733581543, "step": 209660 }, { "epoch": 1.2463220215061432, "grad_norm": 1.6878600120544434, "learning_rate": 0.00015073655159349863, "loss": 0.6430340766906738, "step": 209670 }, { "epoch": 1.2463814635828117, "grad_norm": 1.351306438446045, "learning_rate": 0.0001507310008738652, "loss": 0.6495705604553222, "step": 209680 }, { "epoch": 1.24644090565948, "grad_norm": 1.5041236877441406, "learning_rate": 0.0001507254499593879, "loss": 0.5943150520324707, "step": 209690 }, { "epoch": 1.2465003477361485, "grad_norm": 1.6454219818115234, "learning_rate": 0.0001507198988500934, "loss": 0.6223245143890381, "step": 209700 }, { "epoch": 1.246559789812817, "grad_norm": 1.6929399967193604, "learning_rate": 0.0001507143475460082, "loss": 0.5975079536437988, "step": 209710 }, { "epoch": 1.2466192318894853, "grad_norm": 1.534111499786377, "learning_rate": 0.00015070879604715888, "loss": 0.6494696140289307, "step": 209720 }, { "epoch": 1.2466786739661537, "grad_norm": 1.6233513355255127, "learning_rate": 0.00015070324435357196, "loss": 0.6216892719268798, "step": 209730 }, { "epoch": 1.2467381160428221, "grad_norm": 1.5378620624542236, "learning_rate": 0.00015069769246527404, "loss": 0.6035887718200683, "step": 209740 }, { "epoch": 1.2467975581194906, "grad_norm": 2.2385361194610596, "learning_rate": 0.00015069214038229163, "loss": 0.6442785739898682, "step": 209750 }, { "epoch": 1.246857000196159, "grad_norm": 1.5620555877685547, "learning_rate": 0.00015068658810465135, "loss": 0.5801876068115235, "step": 209760 }, { "epoch": 1.2469164422728272, "grad_norm": 1.454214096069336, "learning_rate": 0.00015068103563237975, "loss": 0.5818565368652344, "step": 209770 }, { "epoch": 1.2469758843494956, "grad_norm": 1.6890934705734253, "learning_rate": 0.0001506754829655033, "loss": 0.6404980659484864, "step": 209780 }, { "epoch": 1.247035326426164, "grad_norm": 1.705286979675293, "learning_rate": 0.0001506699301040487, "loss": 0.6314823150634765, "step": 209790 }, { "epoch": 1.2470947685028324, "grad_norm": 1.8194187879562378, "learning_rate": 0.00015066437704804243, "loss": 0.5696244239807129, "step": 209800 }, { "epoch": 1.2471542105795008, "grad_norm": 1.4842318296432495, "learning_rate": 0.00015065882379751105, "loss": 0.6153107643127441, "step": 209810 }, { "epoch": 1.2472136526561692, "grad_norm": 1.7589186429977417, "learning_rate": 0.00015065327035248115, "loss": 0.6315913200378418, "step": 209820 }, { "epoch": 1.2472730947328377, "grad_norm": 1.5410858392715454, "learning_rate": 0.00015064771671297929, "loss": 0.6971033096313477, "step": 209830 }, { "epoch": 1.247332536809506, "grad_norm": 1.487699031829834, "learning_rate": 0.00015064216287903202, "loss": 0.6442652702331543, "step": 209840 }, { "epoch": 1.2473919788861743, "grad_norm": 1.4054418802261353, "learning_rate": 0.00015063660885066596, "loss": 0.6035183906555176, "step": 209850 }, { "epoch": 1.2474514209628427, "grad_norm": 1.4040427207946777, "learning_rate": 0.00015063105462790761, "loss": 0.6006597995758056, "step": 209860 }, { "epoch": 1.247510863039511, "grad_norm": 1.7357410192489624, "learning_rate": 0.0001506255002107836, "loss": 0.6710216522216796, "step": 209870 }, { "epoch": 1.2475703051161795, "grad_norm": 1.5796185731887817, "learning_rate": 0.00015061994559932047, "loss": 0.6141330242156983, "step": 209880 }, { "epoch": 1.247629747192848, "grad_norm": 1.592978835105896, "learning_rate": 0.00015061439079354477, "loss": 0.609127140045166, "step": 209890 }, { "epoch": 1.2476891892695163, "grad_norm": 1.4300328493118286, "learning_rate": 0.00015060883579348316, "loss": 0.5981723308563233, "step": 209900 }, { "epoch": 1.2477486313461847, "grad_norm": 1.6694904565811157, "learning_rate": 0.0001506032805991621, "loss": 0.559742784500122, "step": 209910 }, { "epoch": 1.2478080734228532, "grad_norm": 1.2700105905532837, "learning_rate": 0.00015059772521060818, "loss": 0.6325221061706543, "step": 209920 }, { "epoch": 1.2478675154995216, "grad_norm": 1.3872666358947754, "learning_rate": 0.0001505921696278481, "loss": 0.6392360210418702, "step": 209930 }, { "epoch": 1.24792695757619, "grad_norm": 1.482830286026001, "learning_rate": 0.00015058661385090825, "loss": 0.6243884086608886, "step": 209940 }, { "epoch": 1.2479863996528582, "grad_norm": 1.642077922821045, "learning_rate": 0.0001505810578798154, "loss": 0.6113677978515625, "step": 209950 }, { "epoch": 1.2480458417295266, "grad_norm": 1.4397668838500977, "learning_rate": 0.00015057550171459596, "loss": 0.6127376079559326, "step": 209960 }, { "epoch": 1.248105283806195, "grad_norm": 1.5649833679199219, "learning_rate": 0.0001505699453552766, "loss": 0.6028385162353516, "step": 209970 }, { "epoch": 1.2481647258828634, "grad_norm": 1.3959453105926514, "learning_rate": 0.0001505643888018839, "loss": 0.6096132278442383, "step": 209980 }, { "epoch": 1.2482241679595318, "grad_norm": 1.8107270002365112, "learning_rate": 0.00015055883205444438, "loss": 0.5900588989257812, "step": 209990 }, { "epoch": 1.2482836100362003, "grad_norm": 1.46116304397583, "learning_rate": 0.0001505532751129847, "loss": 0.6444029808044434, "step": 210000 }, { "epoch": 1.2483430521128687, "grad_norm": 1.5086172819137573, "learning_rate": 0.00015054771797753139, "loss": 0.5874199867248535, "step": 210010 }, { "epoch": 1.248402494189537, "grad_norm": 1.7509808540344238, "learning_rate": 0.00015054216064811103, "loss": 0.6126808166503906, "step": 210020 }, { "epoch": 1.2484619362662053, "grad_norm": 1.2688711881637573, "learning_rate": 0.00015053660312475025, "loss": 0.6181803703308105, "step": 210030 }, { "epoch": 1.2485213783428737, "grad_norm": 1.5344399213790894, "learning_rate": 0.0001505310454074756, "loss": 0.6061094284057618, "step": 210040 }, { "epoch": 1.248580820419542, "grad_norm": 1.512507438659668, "learning_rate": 0.00015052548749631368, "loss": 0.6372138977050781, "step": 210050 }, { "epoch": 1.2486402624962105, "grad_norm": 1.6119338274002075, "learning_rate": 0.00015051992939129106, "loss": 0.565795612335205, "step": 210060 }, { "epoch": 1.248699704572879, "grad_norm": 1.714931607246399, "learning_rate": 0.00015051437109243434, "loss": 0.616610336303711, "step": 210070 }, { "epoch": 1.2487591466495473, "grad_norm": 1.671995997428894, "learning_rate": 0.00015050881259977012, "loss": 0.625359058380127, "step": 210080 }, { "epoch": 1.2488185887262158, "grad_norm": 1.5342466831207275, "learning_rate": 0.00015050325391332498, "loss": 0.6164849281311036, "step": 210090 }, { "epoch": 1.2488780308028842, "grad_norm": 1.6268951892852783, "learning_rate": 0.0001504976950331255, "loss": 0.5728157520294189, "step": 210100 }, { "epoch": 1.2489374728795526, "grad_norm": 1.471282720565796, "learning_rate": 0.00015049213595919828, "loss": 0.5989014625549316, "step": 210110 }, { "epoch": 1.248996914956221, "grad_norm": 1.4769361019134521, "learning_rate": 0.00015048657669156993, "loss": 0.681905460357666, "step": 210120 }, { "epoch": 1.2490563570328894, "grad_norm": 1.4157100915908813, "learning_rate": 0.00015048101723026702, "loss": 0.5661130905151367, "step": 210130 }, { "epoch": 1.2491157991095576, "grad_norm": 1.5249444246292114, "learning_rate": 0.00015047545757531614, "loss": 0.5886754035949707, "step": 210140 }, { "epoch": 1.249175241186226, "grad_norm": 1.5722107887268066, "learning_rate": 0.0001504698977267439, "loss": 0.6018354892730713, "step": 210150 }, { "epoch": 1.2492346832628944, "grad_norm": 1.5242409706115723, "learning_rate": 0.00015046433768457692, "loss": 0.5615467071533203, "step": 210160 }, { "epoch": 1.2492941253395629, "grad_norm": 1.7785584926605225, "learning_rate": 0.00015045877744884176, "loss": 0.6647315979003906, "step": 210170 }, { "epoch": 1.2493535674162313, "grad_norm": 1.4382116794586182, "learning_rate": 0.00015045321701956504, "loss": 0.6744396686553955, "step": 210180 }, { "epoch": 1.2494130094928997, "grad_norm": 1.380285620689392, "learning_rate": 0.00015044765639677334, "loss": 0.600004768371582, "step": 210190 }, { "epoch": 1.249472451569568, "grad_norm": 1.5941920280456543, "learning_rate": 0.00015044209558049323, "loss": 0.6042188167572021, "step": 210200 }, { "epoch": 1.2495318936462365, "grad_norm": 1.6452845335006714, "learning_rate": 0.00015043653457075143, "loss": 0.6198881149291993, "step": 210210 }, { "epoch": 1.2495913357229047, "grad_norm": 1.4851123094558716, "learning_rate": 0.0001504309733675744, "loss": 0.6115416526794434, "step": 210220 }, { "epoch": 1.2496507777995731, "grad_norm": 1.1391252279281616, "learning_rate": 0.0001504254119709888, "loss": 0.5940030097961426, "step": 210230 }, { "epoch": 1.2497102198762415, "grad_norm": 1.5957897901535034, "learning_rate": 0.00015041985038102132, "loss": 0.564129114151001, "step": 210240 }, { "epoch": 1.24976966195291, "grad_norm": 1.5637222528457642, "learning_rate": 0.00015041428859769842, "loss": 0.5801166534423828, "step": 210250 }, { "epoch": 1.2498291040295784, "grad_norm": 1.7558879852294922, "learning_rate": 0.0001504087266210468, "loss": 0.6048499584197998, "step": 210260 }, { "epoch": 1.2498885461062468, "grad_norm": 1.8265314102172852, "learning_rate": 0.000150403164451093, "loss": 0.6263057708740234, "step": 210270 }, { "epoch": 1.2499479881829152, "grad_norm": 1.5130915641784668, "learning_rate": 0.0001503976020878637, "loss": 0.5744938373565673, "step": 210280 }, { "epoch": 1.2500074302595836, "grad_norm": 1.6731525659561157, "learning_rate": 0.00015039203953138544, "loss": 0.6438371181488037, "step": 210290 }, { "epoch": 1.250066872336252, "grad_norm": 1.5515952110290527, "learning_rate": 0.00015038647678168493, "loss": 0.6364220142364502, "step": 210300 }, { "epoch": 1.2501263144129204, "grad_norm": 1.505432367324829, "learning_rate": 0.00015038091383878864, "loss": 0.5925246238708496, "step": 210310 }, { "epoch": 1.2501857564895889, "grad_norm": 1.2189935445785522, "learning_rate": 0.00015037535070272327, "loss": 0.6317027568817138, "step": 210320 }, { "epoch": 1.250245198566257, "grad_norm": 1.4724068641662598, "learning_rate": 0.00015036978737351545, "loss": 0.6357619762420654, "step": 210330 }, { "epoch": 1.2503046406429255, "grad_norm": 1.2480663061141968, "learning_rate": 0.00015036422385119176, "loss": 0.6098330020904541, "step": 210340 }, { "epoch": 1.2503640827195939, "grad_norm": 1.78700590133667, "learning_rate": 0.00015035866013577876, "loss": 0.6109809875488281, "step": 210350 }, { "epoch": 1.2504235247962623, "grad_norm": 1.887136697769165, "learning_rate": 0.00015035309622730316, "loss": 0.5905018806457519, "step": 210360 }, { "epoch": 1.2504829668729307, "grad_norm": 1.381757378578186, "learning_rate": 0.00015034753212579154, "loss": 0.6146526336669922, "step": 210370 }, { "epoch": 1.2505424089495991, "grad_norm": 1.290035367012024, "learning_rate": 0.0001503419678312705, "loss": 0.6304937362670898, "step": 210380 }, { "epoch": 1.2506018510262675, "grad_norm": 1.326446294784546, "learning_rate": 0.0001503364033437667, "loss": 0.6101850509643555, "step": 210390 }, { "epoch": 1.2506612931029357, "grad_norm": 1.4733786582946777, "learning_rate": 0.00015033083866330667, "loss": 0.608936882019043, "step": 210400 }, { "epoch": 1.2507207351796041, "grad_norm": 1.3920867443084717, "learning_rate": 0.0001503252737899171, "loss": 0.658989143371582, "step": 210410 }, { "epoch": 1.2507801772562726, "grad_norm": 1.5816553831100464, "learning_rate": 0.00015031970872362465, "loss": 0.6190958023071289, "step": 210420 }, { "epoch": 1.250839619332941, "grad_norm": 1.5088064670562744, "learning_rate": 0.00015031414346445583, "loss": 0.6006134033203125, "step": 210430 }, { "epoch": 1.2508990614096094, "grad_norm": 1.2917938232421875, "learning_rate": 0.00015030857801243735, "loss": 0.6560317993164062, "step": 210440 }, { "epoch": 1.2509585034862778, "grad_norm": 1.4074537754058838, "learning_rate": 0.0001503030123675958, "loss": 0.5905989646911621, "step": 210450 }, { "epoch": 1.2510179455629462, "grad_norm": 1.619773268699646, "learning_rate": 0.00015029744652995784, "loss": 0.649479866027832, "step": 210460 }, { "epoch": 1.2510773876396146, "grad_norm": 1.3968241214752197, "learning_rate": 0.00015029188049955002, "loss": 0.5632466316223145, "step": 210470 }, { "epoch": 1.251136829716283, "grad_norm": 1.4332143068313599, "learning_rate": 0.00015028631427639906, "loss": 0.5844290733337403, "step": 210480 }, { "epoch": 1.2511962717929515, "grad_norm": 1.6404513120651245, "learning_rate": 0.00015028074786053148, "loss": 0.6360280990600586, "step": 210490 }, { "epoch": 1.2512557138696199, "grad_norm": 1.460291862487793, "learning_rate": 0.000150275181251974, "loss": 0.6426876068115235, "step": 210500 }, { "epoch": 1.251315155946288, "grad_norm": 1.9399809837341309, "learning_rate": 0.00015026961445075324, "loss": 0.6276667594909668, "step": 210510 }, { "epoch": 1.2513745980229565, "grad_norm": 1.3252278566360474, "learning_rate": 0.00015026404745689578, "loss": 0.5785396575927735, "step": 210520 }, { "epoch": 1.251434040099625, "grad_norm": 1.756047248840332, "learning_rate": 0.00015025848027042823, "loss": 0.578729248046875, "step": 210530 }, { "epoch": 1.2514934821762933, "grad_norm": 1.9385439157485962, "learning_rate": 0.00015025291289137732, "loss": 0.6152920722961426, "step": 210540 }, { "epoch": 1.2515529242529617, "grad_norm": 1.626975417137146, "learning_rate": 0.00015024734531976963, "loss": 0.6045721054077149, "step": 210550 }, { "epoch": 1.2516123663296301, "grad_norm": 1.2297335863113403, "learning_rate": 0.00015024177755563177, "loss": 0.5763366222381592, "step": 210560 }, { "epoch": 1.2516718084062985, "grad_norm": 1.1719006299972534, "learning_rate": 0.0001502362095989904, "loss": 0.5729701042175293, "step": 210570 }, { "epoch": 1.2517312504829667, "grad_norm": 1.2369927167892456, "learning_rate": 0.00015023064144987217, "loss": 0.6482501983642578, "step": 210580 }, { "epoch": 1.2517906925596352, "grad_norm": 1.448951244354248, "learning_rate": 0.00015022507310830368, "loss": 0.616022777557373, "step": 210590 }, { "epoch": 1.2518501346363036, "grad_norm": 1.5958161354064941, "learning_rate": 0.0001502195045743116, "loss": 0.6598194599151611, "step": 210600 }, { "epoch": 1.251909576712972, "grad_norm": 2.074493408203125, "learning_rate": 0.00015021393584792255, "loss": 0.6129388809204102, "step": 210610 }, { "epoch": 1.2519690187896404, "grad_norm": 1.4157650470733643, "learning_rate": 0.00015020836692916317, "loss": 0.6508089065551758, "step": 210620 }, { "epoch": 1.2520284608663088, "grad_norm": 1.6803220510482788, "learning_rate": 0.0001502027978180601, "loss": 0.6266057968139649, "step": 210630 }, { "epoch": 1.2520879029429772, "grad_norm": 1.576833963394165, "learning_rate": 0.00015019722851464, "loss": 0.6331123352050781, "step": 210640 }, { "epoch": 1.2521473450196456, "grad_norm": 1.3247153759002686, "learning_rate": 0.00015019165901892947, "loss": 0.6193493366241455, "step": 210650 }, { "epoch": 1.252206787096314, "grad_norm": 2.634481191635132, "learning_rate": 0.00015018608933095516, "loss": 0.6157142162322998, "step": 210660 }, { "epoch": 1.2522662291729825, "grad_norm": 1.4405488967895508, "learning_rate": 0.0001501805194507438, "loss": 0.6243428230285645, "step": 210670 }, { "epoch": 1.2523256712496509, "grad_norm": 1.719317078590393, "learning_rate": 0.00015017494937832193, "loss": 0.6067360877990723, "step": 210680 }, { "epoch": 1.2523851133263193, "grad_norm": 1.5869793891906738, "learning_rate": 0.00015016937911371621, "loss": 0.6007323741912842, "step": 210690 }, { "epoch": 1.2524445554029875, "grad_norm": 1.308388113975525, "learning_rate": 0.00015016380865695334, "loss": 0.6757465362548828, "step": 210700 }, { "epoch": 1.252503997479656, "grad_norm": 1.6767966747283936, "learning_rate": 0.00015015823800805994, "loss": 0.6611452579498291, "step": 210710 }, { "epoch": 1.2525634395563243, "grad_norm": 1.4125252962112427, "learning_rate": 0.0001501526671670626, "loss": 0.6303958892822266, "step": 210720 }, { "epoch": 1.2526228816329927, "grad_norm": 1.5641855001449585, "learning_rate": 0.00015014709613398808, "loss": 0.6013545989990234, "step": 210730 }, { "epoch": 1.2526823237096611, "grad_norm": 1.6391513347625732, "learning_rate": 0.00015014152490886297, "loss": 0.6416514873504638, "step": 210740 }, { "epoch": 1.2527417657863296, "grad_norm": 1.6636704206466675, "learning_rate": 0.0001501359534917139, "loss": 0.622995662689209, "step": 210750 }, { "epoch": 1.252801207862998, "grad_norm": 1.333142876625061, "learning_rate": 0.00015013038188256753, "loss": 0.5527589321136475, "step": 210760 }, { "epoch": 1.2528606499396662, "grad_norm": 1.7231920957565308, "learning_rate": 0.00015012481008145056, "loss": 0.6083930492401123, "step": 210770 }, { "epoch": 1.2529200920163346, "grad_norm": 1.358839988708496, "learning_rate": 0.00015011923808838962, "loss": 0.6198885917663575, "step": 210780 }, { "epoch": 1.252979534093003, "grad_norm": 1.2734782695770264, "learning_rate": 0.00015011366590341133, "loss": 0.5696871757507325, "step": 210790 }, { "epoch": 1.2530389761696714, "grad_norm": 1.349706768989563, "learning_rate": 0.00015010809352654237, "loss": 0.609759521484375, "step": 210800 }, { "epoch": 1.2530984182463398, "grad_norm": 1.338592767715454, "learning_rate": 0.00015010252095780938, "loss": 0.6226013660430908, "step": 210810 }, { "epoch": 1.2531578603230082, "grad_norm": 1.442916750907898, "learning_rate": 0.00015009694819723908, "loss": 0.6410140037536621, "step": 210820 }, { "epoch": 1.2532173023996767, "grad_norm": 1.707248330116272, "learning_rate": 0.00015009137524485806, "loss": 0.5831518173217773, "step": 210830 }, { "epoch": 1.253276744476345, "grad_norm": 1.7605069875717163, "learning_rate": 0.00015008580210069302, "loss": 0.6739948272705079, "step": 210840 }, { "epoch": 1.2533361865530135, "grad_norm": 1.7513800859451294, "learning_rate": 0.00015008022876477058, "loss": 0.679865837097168, "step": 210850 }, { "epoch": 1.253395628629682, "grad_norm": 1.3888798952102661, "learning_rate": 0.00015007465523711743, "loss": 0.643644905090332, "step": 210860 }, { "epoch": 1.2534550707063503, "grad_norm": 1.3993632793426514, "learning_rate": 0.00015006908151776022, "loss": 0.6340319633483886, "step": 210870 }, { "epoch": 1.2535145127830185, "grad_norm": 1.5630251169204712, "learning_rate": 0.00015006350760672562, "loss": 0.6433453559875488, "step": 210880 }, { "epoch": 1.253573954859687, "grad_norm": 1.6626120805740356, "learning_rate": 0.0001500579335040403, "loss": 0.5963333129882813, "step": 210890 }, { "epoch": 1.2536333969363553, "grad_norm": 1.9001824855804443, "learning_rate": 0.00015005235920973094, "loss": 0.6544379234313965, "step": 210900 }, { "epoch": 1.2536928390130238, "grad_norm": 1.6225242614746094, "learning_rate": 0.00015004678472382415, "loss": 0.6207237243652344, "step": 210910 }, { "epoch": 1.2537522810896922, "grad_norm": 1.6023615598678589, "learning_rate": 0.00015004121004634667, "loss": 0.5987338542938232, "step": 210920 }, { "epoch": 1.2538117231663606, "grad_norm": 1.5416332483291626, "learning_rate": 0.00015003563517732507, "loss": 0.6602884769439697, "step": 210930 }, { "epoch": 1.253871165243029, "grad_norm": 1.5595721006393433, "learning_rate": 0.0001500300601167861, "loss": 0.6478738784790039, "step": 210940 }, { "epoch": 1.2539306073196972, "grad_norm": 1.9193693399429321, "learning_rate": 0.0001500244848647564, "loss": 0.6515406608581543, "step": 210950 }, { "epoch": 1.2539900493963656, "grad_norm": 1.2463172674179077, "learning_rate": 0.00015001890942126266, "loss": 0.5828969955444336, "step": 210960 }, { "epoch": 1.254049491473034, "grad_norm": 1.590839147567749, "learning_rate": 0.00015001333378633153, "loss": 0.5928044795989991, "step": 210970 }, { "epoch": 1.2541089335497024, "grad_norm": 1.2782477140426636, "learning_rate": 0.00015000775795998968, "loss": 0.5846563816070557, "step": 210980 }, { "epoch": 1.2541683756263708, "grad_norm": 1.7388522624969482, "learning_rate": 0.0001500021819422638, "loss": 0.6401172161102295, "step": 210990 }, { "epoch": 1.2542278177030393, "grad_norm": 1.8487868309020996, "learning_rate": 0.00014999660573318055, "loss": 0.5820740222930908, "step": 211000 }, { "epoch": 1.2542872597797077, "grad_norm": 1.3901830911636353, "learning_rate": 0.00014999102933276664, "loss": 0.6254838943481446, "step": 211010 }, { "epoch": 1.254346701856376, "grad_norm": 1.5565896034240723, "learning_rate": 0.00014998545274104864, "loss": 0.6573923110961915, "step": 211020 }, { "epoch": 1.2544061439330445, "grad_norm": 1.3681920766830444, "learning_rate": 0.00014997987595805336, "loss": 0.5891457557678222, "step": 211030 }, { "epoch": 1.254465586009713, "grad_norm": 1.5861567258834839, "learning_rate": 0.00014997429898380742, "loss": 0.5942705154418946, "step": 211040 }, { "epoch": 1.2545250280863813, "grad_norm": 1.5140386819839478, "learning_rate": 0.00014996872181833747, "loss": 0.5834742069244385, "step": 211050 }, { "epoch": 1.2545844701630497, "grad_norm": 1.61684250831604, "learning_rate": 0.00014996314446167022, "loss": 0.6179487228393554, "step": 211060 }, { "epoch": 1.254643912239718, "grad_norm": 1.3473637104034424, "learning_rate": 0.00014995756691383235, "loss": 0.6125861167907715, "step": 211070 }, { "epoch": 1.2547033543163864, "grad_norm": 1.7499648332595825, "learning_rate": 0.00014995198917485054, "loss": 0.6119955539703369, "step": 211080 }, { "epoch": 1.2547627963930548, "grad_norm": 1.627668857574463, "learning_rate": 0.00014994641124475147, "loss": 0.5786527633666992, "step": 211090 }, { "epoch": 1.2548222384697232, "grad_norm": 1.5514519214630127, "learning_rate": 0.00014994083312356183, "loss": 0.6300756454467773, "step": 211100 }, { "epoch": 1.2548816805463916, "grad_norm": 1.4213886260986328, "learning_rate": 0.0001499352548113083, "loss": 0.6173259735107421, "step": 211110 }, { "epoch": 1.25494112262306, "grad_norm": 1.8781147003173828, "learning_rate": 0.00014992967630801754, "loss": 0.6290283203125, "step": 211120 }, { "epoch": 1.2550005646997284, "grad_norm": 1.4451977014541626, "learning_rate": 0.00014992409761371627, "loss": 0.5662727355957031, "step": 211130 }, { "epoch": 1.2550600067763966, "grad_norm": 1.683866262435913, "learning_rate": 0.0001499185187284312, "loss": 0.5901593208312989, "step": 211140 }, { "epoch": 1.255119448853065, "grad_norm": 1.593543291091919, "learning_rate": 0.00014991293965218894, "loss": 0.6331870079040527, "step": 211150 }, { "epoch": 1.2551788909297334, "grad_norm": 1.4847875833511353, "learning_rate": 0.00014990736038501622, "loss": 0.6254272937774659, "step": 211160 }, { "epoch": 1.2552383330064019, "grad_norm": 2.053992748260498, "learning_rate": 0.00014990178092693973, "loss": 0.5992030143737793, "step": 211170 }, { "epoch": 1.2552977750830703, "grad_norm": 1.4880105257034302, "learning_rate": 0.00014989620127798617, "loss": 0.5835916519165039, "step": 211180 }, { "epoch": 1.2553572171597387, "grad_norm": 1.435453176498413, "learning_rate": 0.00014989062143818226, "loss": 0.6331906318664551, "step": 211190 }, { "epoch": 1.255416659236407, "grad_norm": 1.5149471759796143, "learning_rate": 0.0001498850414075546, "loss": 0.6706413269042969, "step": 211200 }, { "epoch": 1.2554761013130755, "grad_norm": 1.236139178276062, "learning_rate": 0.00014987946118612995, "loss": 0.5535205841064453, "step": 211210 }, { "epoch": 1.255535543389744, "grad_norm": 1.5271695852279663, "learning_rate": 0.000149873880773935, "loss": 0.6067834854125976, "step": 211220 }, { "epoch": 1.2555949854664123, "grad_norm": 1.572066307067871, "learning_rate": 0.00014986830017099643, "loss": 0.6099820137023926, "step": 211230 }, { "epoch": 1.2556544275430808, "grad_norm": 1.6400291919708252, "learning_rate": 0.00014986271937734094, "loss": 0.5385304450988769, "step": 211240 }, { "epoch": 1.255713869619749, "grad_norm": 1.3111993074417114, "learning_rate": 0.0001498571383929952, "loss": 0.5791606903076172, "step": 211250 }, { "epoch": 1.2557733116964174, "grad_norm": 1.3650165796279907, "learning_rate": 0.00014985155721798597, "loss": 0.5936331748962402, "step": 211260 }, { "epoch": 1.2558327537730858, "grad_norm": 1.472743034362793, "learning_rate": 0.0001498459758523399, "loss": 0.5657636165618897, "step": 211270 }, { "epoch": 1.2558921958497542, "grad_norm": 1.4907742738723755, "learning_rate": 0.00014984039429608373, "loss": 0.6054948329925537, "step": 211280 }, { "epoch": 1.2559516379264226, "grad_norm": 1.3256874084472656, "learning_rate": 0.0001498348125492441, "loss": 0.6292431831359864, "step": 211290 }, { "epoch": 1.256011080003091, "grad_norm": 1.7947564125061035, "learning_rate": 0.00014982923061184774, "loss": 0.5922219276428222, "step": 211300 }, { "epoch": 1.2560705220797594, "grad_norm": 1.435486078262329, "learning_rate": 0.0001498236484839214, "loss": 0.5771966934204101, "step": 211310 }, { "epoch": 1.2561299641564276, "grad_norm": 1.586581826210022, "learning_rate": 0.00014981806616549173, "loss": 0.641998291015625, "step": 211320 }, { "epoch": 1.256189406233096, "grad_norm": 1.6985338926315308, "learning_rate": 0.0001498124836565854, "loss": 0.6806479930877686, "step": 211330 }, { "epoch": 1.2562488483097645, "grad_norm": 1.3169792890548706, "learning_rate": 0.00014980690095722917, "loss": 0.5616692543029785, "step": 211340 }, { "epoch": 1.2563082903864329, "grad_norm": 1.6181604862213135, "learning_rate": 0.00014980131806744976, "loss": 0.6231548309326171, "step": 211350 }, { "epoch": 1.2563677324631013, "grad_norm": 1.4840575456619263, "learning_rate": 0.00014979573498727383, "loss": 0.5317179203033447, "step": 211360 }, { "epoch": 1.2564271745397697, "grad_norm": 1.611359715461731, "learning_rate": 0.00014979015171672814, "loss": 0.5518229484558106, "step": 211370 }, { "epoch": 1.2564866166164381, "grad_norm": 1.726494312286377, "learning_rate": 0.00014978456825583936, "loss": 0.6208882331848145, "step": 211380 }, { "epoch": 1.2565460586931065, "grad_norm": 1.6420140266418457, "learning_rate": 0.0001497789846046342, "loss": 0.6699860572814942, "step": 211390 }, { "epoch": 1.256605500769775, "grad_norm": 1.5409315824508667, "learning_rate": 0.00014977340076313938, "loss": 0.5567313194274902, "step": 211400 }, { "epoch": 1.2566649428464434, "grad_norm": 1.8323297500610352, "learning_rate": 0.00014976781673138159, "loss": 0.583671760559082, "step": 211410 }, { "epoch": 1.2567243849231118, "grad_norm": 1.6347293853759766, "learning_rate": 0.0001497622325093876, "loss": 0.6298617839813232, "step": 211420 }, { "epoch": 1.2567838269997802, "grad_norm": 1.4728357791900635, "learning_rate": 0.000149756648097184, "loss": 0.6002330780029297, "step": 211430 }, { "epoch": 1.2568432690764484, "grad_norm": 2.0139434337615967, "learning_rate": 0.0001497510634947977, "loss": 0.6195316314697266, "step": 211440 }, { "epoch": 1.2569027111531168, "grad_norm": 1.5829015970230103, "learning_rate": 0.00014974547870225523, "loss": 0.5857557773590087, "step": 211450 }, { "epoch": 1.2569621532297852, "grad_norm": 1.7175589799880981, "learning_rate": 0.0001497398937195834, "loss": 0.675136137008667, "step": 211460 }, { "epoch": 1.2570215953064536, "grad_norm": 2.0890817642211914, "learning_rate": 0.00014973430854680892, "loss": 0.6356617927551269, "step": 211470 }, { "epoch": 1.257081037383122, "grad_norm": 1.5447638034820557, "learning_rate": 0.00014972872318395848, "loss": 0.6234989166259766, "step": 211480 }, { "epoch": 1.2571404794597905, "grad_norm": 1.3742321729660034, "learning_rate": 0.0001497231376310588, "loss": 0.5861262798309326, "step": 211490 }, { "epoch": 1.2571999215364589, "grad_norm": 1.7784528732299805, "learning_rate": 0.00014971755188813662, "loss": 0.6033806800842285, "step": 211500 }, { "epoch": 1.257259363613127, "grad_norm": 1.436090111732483, "learning_rate": 0.00014971196595521866, "loss": 0.6098602294921875, "step": 211510 }, { "epoch": 1.2573188056897955, "grad_norm": 1.455976128578186, "learning_rate": 0.0001497063798323316, "loss": 0.6206487655639649, "step": 211520 }, { "epoch": 1.257378247766464, "grad_norm": 1.5999805927276611, "learning_rate": 0.00014970079351950223, "loss": 0.6181188583374023, "step": 211530 }, { "epoch": 1.2574376898431323, "grad_norm": 1.6758524179458618, "learning_rate": 0.00014969520701675723, "loss": 0.6195396423339844, "step": 211540 }, { "epoch": 1.2574971319198007, "grad_norm": 1.3953098058700562, "learning_rate": 0.00014968962032412334, "loss": 0.6459941864013672, "step": 211550 }, { "epoch": 1.2575565739964691, "grad_norm": 1.339329719543457, "learning_rate": 0.00014968403344162726, "loss": 0.6148537158966064, "step": 211560 }, { "epoch": 1.2576160160731376, "grad_norm": 1.8842766284942627, "learning_rate": 0.00014967844636929576, "loss": 0.5877914428710938, "step": 211570 }, { "epoch": 1.257675458149806, "grad_norm": 1.5138291120529175, "learning_rate": 0.0001496728591071555, "loss": 0.6004541397094727, "step": 211580 }, { "epoch": 1.2577349002264744, "grad_norm": 1.6178516149520874, "learning_rate": 0.00014966727165523328, "loss": 0.6570059776306152, "step": 211590 }, { "epoch": 1.2577943423031428, "grad_norm": 1.395564317703247, "learning_rate": 0.0001496616840135558, "loss": 0.586560583114624, "step": 211600 }, { "epoch": 1.2578537843798112, "grad_norm": 1.6167489290237427, "learning_rate": 0.00014965609618214975, "loss": 0.593962287902832, "step": 211610 }, { "epoch": 1.2579132264564794, "grad_norm": 2.114291191101074, "learning_rate": 0.00014965050816104192, "loss": 0.6309148788452148, "step": 211620 }, { "epoch": 1.2579726685331478, "grad_norm": 1.0817621946334839, "learning_rate": 0.00014964491995025903, "loss": 0.5943037033081054, "step": 211630 }, { "epoch": 1.2580321106098162, "grad_norm": 1.6209052801132202, "learning_rate": 0.00014963933154982776, "loss": 0.6285970687866211, "step": 211640 }, { "epoch": 1.2580915526864846, "grad_norm": 1.2374211549758911, "learning_rate": 0.0001496337429597749, "loss": 0.5657577514648438, "step": 211650 }, { "epoch": 1.258150994763153, "grad_norm": 1.622593641281128, "learning_rate": 0.00014962815418012717, "loss": 0.6444941997528076, "step": 211660 }, { "epoch": 1.2582104368398215, "grad_norm": 1.6923452615737915, "learning_rate": 0.0001496225652109113, "loss": 0.5564762115478515, "step": 211670 }, { "epoch": 1.25826987891649, "grad_norm": 1.5694388151168823, "learning_rate": 0.00014961697605215404, "loss": 0.5988181114196778, "step": 211680 }, { "epoch": 1.258329320993158, "grad_norm": 1.3683035373687744, "learning_rate": 0.0001496113867038821, "loss": 0.6007065773010254, "step": 211690 }, { "epoch": 1.2583887630698265, "grad_norm": 1.214619755744934, "learning_rate": 0.00014960579716612223, "loss": 0.5987709045410157, "step": 211700 }, { "epoch": 1.258448205146495, "grad_norm": 1.6091724634170532, "learning_rate": 0.00014960020743890118, "loss": 0.5887834072113037, "step": 211710 }, { "epoch": 1.2585076472231633, "grad_norm": 1.4947490692138672, "learning_rate": 0.00014959461752224565, "loss": 0.6018373489379882, "step": 211720 }, { "epoch": 1.2585670892998317, "grad_norm": 1.9961400032043457, "learning_rate": 0.00014958902741618246, "loss": 0.5985628604888916, "step": 211730 }, { "epoch": 1.2586265313765002, "grad_norm": 1.925020456314087, "learning_rate": 0.00014958343712073827, "loss": 0.571654224395752, "step": 211740 }, { "epoch": 1.2586859734531686, "grad_norm": 1.784389853477478, "learning_rate": 0.00014957784663593984, "loss": 0.599131441116333, "step": 211750 }, { "epoch": 1.258745415529837, "grad_norm": 1.6774520874023438, "learning_rate": 0.00014957225596181392, "loss": 0.6208515167236328, "step": 211760 }, { "epoch": 1.2588048576065054, "grad_norm": 1.3852910995483398, "learning_rate": 0.0001495666650983873, "loss": 0.5664333820343017, "step": 211770 }, { "epoch": 1.2588642996831738, "grad_norm": 2.0961313247680664, "learning_rate": 0.00014956107404568667, "loss": 0.5800758361816406, "step": 211780 }, { "epoch": 1.2589237417598422, "grad_norm": 1.5091129541397095, "learning_rate": 0.00014955548280373877, "loss": 0.6258656024932862, "step": 211790 }, { "epoch": 1.2589831838365106, "grad_norm": 1.9114584922790527, "learning_rate": 0.0001495498913725704, "loss": 0.6053878784179687, "step": 211800 }, { "epoch": 1.2590426259131788, "grad_norm": 1.6348470449447632, "learning_rate": 0.00014954429975220826, "loss": 0.6227759838104248, "step": 211810 }, { "epoch": 1.2591020679898473, "grad_norm": 1.602701187133789, "learning_rate": 0.0001495387079426791, "loss": 0.5801949501037598, "step": 211820 }, { "epoch": 1.2591615100665157, "grad_norm": 1.7534621953964233, "learning_rate": 0.00014953311594400966, "loss": 0.6520033836364746, "step": 211830 }, { "epoch": 1.259220952143184, "grad_norm": 1.6147819757461548, "learning_rate": 0.00014952752375622675, "loss": 0.6609755992889405, "step": 211840 }, { "epoch": 1.2592803942198525, "grad_norm": 1.4518252611160278, "learning_rate": 0.00014952193137935708, "loss": 0.6090779781341553, "step": 211850 }, { "epoch": 1.259339836296521, "grad_norm": 1.4279886484146118, "learning_rate": 0.0001495163388134274, "loss": 0.5812146186828613, "step": 211860 }, { "epoch": 1.2593992783731893, "grad_norm": 1.6928596496582031, "learning_rate": 0.0001495107460584645, "loss": 0.6367359161376953, "step": 211870 }, { "epoch": 1.2594587204498575, "grad_norm": 1.220674753189087, "learning_rate": 0.00014950515311449507, "loss": 0.6390422821044922, "step": 211880 }, { "epoch": 1.259518162526526, "grad_norm": 1.5035498142242432, "learning_rate": 0.00014949955998154593, "loss": 0.6226582527160645, "step": 211890 }, { "epoch": 1.2595776046031943, "grad_norm": 1.8465228080749512, "learning_rate": 0.00014949396665964374, "loss": 0.6142760276794433, "step": 211900 }, { "epoch": 1.2596370466798628, "grad_norm": 1.4607229232788086, "learning_rate": 0.00014948837314881537, "loss": 0.6381275653839111, "step": 211910 }, { "epoch": 1.2596964887565312, "grad_norm": 1.6836578845977783, "learning_rate": 0.00014948277944908754, "loss": 0.6222846984863282, "step": 211920 }, { "epoch": 1.2597559308331996, "grad_norm": 1.407335877418518, "learning_rate": 0.00014947718556048694, "loss": 0.5776405334472656, "step": 211930 }, { "epoch": 1.259815372909868, "grad_norm": 1.527314305305481, "learning_rate": 0.00014947159148304045, "loss": 0.6309231281280517, "step": 211940 }, { "epoch": 1.2598748149865364, "grad_norm": 1.5072698593139648, "learning_rate": 0.00014946599721677473, "loss": 0.6230201721191406, "step": 211950 }, { "epoch": 1.2599342570632048, "grad_norm": 1.8791011571884155, "learning_rate": 0.00014946040276171658, "loss": 0.5638219833374023, "step": 211960 }, { "epoch": 1.2599936991398732, "grad_norm": 1.0761247873306274, "learning_rate": 0.00014945480811789274, "loss": 0.6196767807006835, "step": 211970 }, { "epoch": 1.2600531412165417, "grad_norm": 1.530894160270691, "learning_rate": 0.00014944921328533, "loss": 0.5983373641967773, "step": 211980 }, { "epoch": 1.2601125832932099, "grad_norm": 1.51143217086792, "learning_rate": 0.00014944361826405519, "loss": 0.5893137454986572, "step": 211990 }, { "epoch": 1.2601720253698783, "grad_norm": 1.5414886474609375, "learning_rate": 0.00014943802305409488, "loss": 0.6044055461883545, "step": 212000 }, { "epoch": 1.2602314674465467, "grad_norm": 1.4233125448226929, "learning_rate": 0.00014943242765547602, "loss": 0.5891692161560058, "step": 212010 }, { "epoch": 1.260290909523215, "grad_norm": 1.4450066089630127, "learning_rate": 0.00014942683206822533, "loss": 0.6189794540405273, "step": 212020 }, { "epoch": 1.2603503515998835, "grad_norm": 1.727120041847229, "learning_rate": 0.00014942123629236955, "loss": 0.5785089015960694, "step": 212030 }, { "epoch": 1.260409793676552, "grad_norm": 1.419631004333496, "learning_rate": 0.00014941564032793541, "loss": 0.635814619064331, "step": 212040 }, { "epoch": 1.2604692357532203, "grad_norm": 1.62058424949646, "learning_rate": 0.0001494100441749498, "loss": 0.5902101516723632, "step": 212050 }, { "epoch": 1.2605286778298885, "grad_norm": 1.329131841659546, "learning_rate": 0.00014940444783343937, "loss": 0.6178704261779785, "step": 212060 }, { "epoch": 1.260588119906557, "grad_norm": 1.539235234260559, "learning_rate": 0.00014939885130343096, "loss": 0.6102632999420166, "step": 212070 }, { "epoch": 1.2606475619832254, "grad_norm": 1.2757595777511597, "learning_rate": 0.00014939325458495132, "loss": 0.5724146842956543, "step": 212080 }, { "epoch": 1.2607070040598938, "grad_norm": 1.3150032758712769, "learning_rate": 0.0001493876576780272, "loss": 0.589540672302246, "step": 212090 }, { "epoch": 1.2607664461365622, "grad_norm": 1.7203763723373413, "learning_rate": 0.0001493820605826854, "loss": 0.6447094917297364, "step": 212100 }, { "epoch": 1.2608258882132306, "grad_norm": 1.5774277448654175, "learning_rate": 0.00014937646329895272, "loss": 0.5953457355499268, "step": 212110 }, { "epoch": 1.260885330289899, "grad_norm": 1.6159443855285645, "learning_rate": 0.00014937086582685592, "loss": 0.5874130249023437, "step": 212120 }, { "epoch": 1.2609447723665674, "grad_norm": 1.5339272022247314, "learning_rate": 0.0001493652681664217, "loss": 0.6158692836761475, "step": 212130 }, { "epoch": 1.2610042144432358, "grad_norm": 1.2935670614242554, "learning_rate": 0.00014935967031767694, "loss": 0.5577587127685547, "step": 212140 }, { "epoch": 1.2610636565199043, "grad_norm": 1.4948068857192993, "learning_rate": 0.0001493540722806484, "loss": 0.6375584602355957, "step": 212150 }, { "epoch": 1.2611230985965727, "grad_norm": 1.8264403343200684, "learning_rate": 0.00014934847405536278, "loss": 0.6290804862976074, "step": 212160 }, { "epoch": 1.261182540673241, "grad_norm": 2.0027096271514893, "learning_rate": 0.000149342875641847, "loss": 0.6220613479614258, "step": 212170 }, { "epoch": 1.2612419827499093, "grad_norm": 1.5238455533981323, "learning_rate": 0.00014933727704012772, "loss": 0.6264175415039063, "step": 212180 }, { "epoch": 1.2613014248265777, "grad_norm": 1.2738327980041504, "learning_rate": 0.00014933167825023175, "loss": 0.6623175621032715, "step": 212190 }, { "epoch": 1.2613608669032461, "grad_norm": 1.1665130853652954, "learning_rate": 0.0001493260792721859, "loss": 0.5662366867065429, "step": 212200 }, { "epoch": 1.2614203089799145, "grad_norm": 1.7355550527572632, "learning_rate": 0.00014932048010601697, "loss": 0.6377202987670898, "step": 212210 }, { "epoch": 1.261479751056583, "grad_norm": 1.437479019165039, "learning_rate": 0.00014931488075175167, "loss": 0.6186282157897949, "step": 212220 }, { "epoch": 1.2615391931332514, "grad_norm": 1.8878724575042725, "learning_rate": 0.0001493092812094168, "loss": 0.6651526927947998, "step": 212230 }, { "epoch": 1.2615986352099198, "grad_norm": 1.4614607095718384, "learning_rate": 0.0001493036814790392, "loss": 0.5733167171478272, "step": 212240 }, { "epoch": 1.261658077286588, "grad_norm": 1.309506893157959, "learning_rate": 0.00014929808156064568, "loss": 0.5864340782165527, "step": 212250 }, { "epoch": 1.2617175193632564, "grad_norm": 1.7804455757141113, "learning_rate": 0.0001492924814542629, "loss": 0.608234977722168, "step": 212260 }, { "epoch": 1.2617769614399248, "grad_norm": 1.2405017614364624, "learning_rate": 0.0001492868811599178, "loss": 0.5894225120544434, "step": 212270 }, { "epoch": 1.2618364035165932, "grad_norm": 1.5535889863967896, "learning_rate": 0.00014928128067763708, "loss": 0.5906051635742188, "step": 212280 }, { "epoch": 1.2618958455932616, "grad_norm": 1.4343894720077515, "learning_rate": 0.00014927568000744755, "loss": 0.6332442283630371, "step": 212290 }, { "epoch": 1.26195528766993, "grad_norm": 1.4761755466461182, "learning_rate": 0.000149270079149376, "loss": 0.6197586536407471, "step": 212300 }, { "epoch": 1.2620147297465985, "grad_norm": 1.5708484649658203, "learning_rate": 0.00014926447810344925, "loss": 0.675693416595459, "step": 212310 }, { "epoch": 1.2620741718232669, "grad_norm": 0.9872385859489441, "learning_rate": 0.00014925887686969403, "loss": 0.5677911281585694, "step": 212320 }, { "epoch": 1.2621336138999353, "grad_norm": 1.359020709991455, "learning_rate": 0.0001492532754481372, "loss": 0.618734073638916, "step": 212330 }, { "epoch": 1.2621930559766037, "grad_norm": 1.7478063106536865, "learning_rate": 0.0001492476738388055, "loss": 0.5807547569274902, "step": 212340 }, { "epoch": 1.262252498053272, "grad_norm": 1.4833788871765137, "learning_rate": 0.00014924207204172575, "loss": 0.5566178321838379, "step": 212350 }, { "epoch": 1.2623119401299403, "grad_norm": 1.6685869693756104, "learning_rate": 0.00014923647005692477, "loss": 0.6195113182067871, "step": 212360 }, { "epoch": 1.2623713822066087, "grad_norm": 1.655314326286316, "learning_rate": 0.00014923086788442934, "loss": 0.6050247192382813, "step": 212370 }, { "epoch": 1.2624308242832771, "grad_norm": 1.3799424171447754, "learning_rate": 0.00014922526552426627, "loss": 0.5726274490356446, "step": 212380 }, { "epoch": 1.2624902663599455, "grad_norm": 1.694449782371521, "learning_rate": 0.0001492196629764623, "loss": 0.5776863098144531, "step": 212390 }, { "epoch": 1.262549708436614, "grad_norm": 1.7768296003341675, "learning_rate": 0.00014921406024104433, "loss": 0.6173480033874512, "step": 212400 }, { "epoch": 1.2626091505132824, "grad_norm": 1.7278128862380981, "learning_rate": 0.0001492084573180391, "loss": 0.5977642059326171, "step": 212410 }, { "epoch": 1.2626685925899508, "grad_norm": 1.255083441734314, "learning_rate": 0.00014920285420747342, "loss": 0.6172236919403076, "step": 212420 }, { "epoch": 1.262728034666619, "grad_norm": 1.28294837474823, "learning_rate": 0.00014919725090937412, "loss": 0.6069113731384277, "step": 212430 }, { "epoch": 1.2627874767432874, "grad_norm": 1.5542653799057007, "learning_rate": 0.00014919164742376793, "loss": 0.6289502143859863, "step": 212440 }, { "epoch": 1.2628469188199558, "grad_norm": 1.7296661138534546, "learning_rate": 0.00014918604375068178, "loss": 0.6220704078674316, "step": 212450 }, { "epoch": 1.2629063608966242, "grad_norm": 1.9383926391601562, "learning_rate": 0.00014918043989014233, "loss": 0.5506613254547119, "step": 212460 }, { "epoch": 1.2629658029732926, "grad_norm": 2.3843278884887695, "learning_rate": 0.0001491748358421765, "loss": 0.6467017650604248, "step": 212470 }, { "epoch": 1.263025245049961, "grad_norm": 1.5833073854446411, "learning_rate": 0.00014916923160681104, "loss": 0.6263449192047119, "step": 212480 }, { "epoch": 1.2630846871266295, "grad_norm": 1.220497727394104, "learning_rate": 0.00014916362718407278, "loss": 0.5983527183532715, "step": 212490 }, { "epoch": 1.2631441292032979, "grad_norm": 1.8719862699508667, "learning_rate": 0.0001491580225739885, "loss": 0.5955845355987549, "step": 212500 }, { "epoch": 1.2632035712799663, "grad_norm": 1.5447207689285278, "learning_rate": 0.0001491524177765851, "loss": 0.6253715515136719, "step": 212510 }, { "epoch": 1.2632630133566347, "grad_norm": 2.1301000118255615, "learning_rate": 0.00014914681279188928, "loss": 0.6014167785644531, "step": 212520 }, { "epoch": 1.2633224554333031, "grad_norm": 1.6775343418121338, "learning_rate": 0.0001491412076199279, "loss": 0.6033289909362793, "step": 212530 }, { "epoch": 1.2633818975099715, "grad_norm": 1.618876576423645, "learning_rate": 0.00014913560226072784, "loss": 0.6505872726440429, "step": 212540 }, { "epoch": 1.2634413395866397, "grad_norm": 1.6840851306915283, "learning_rate": 0.00014912999671431575, "loss": 0.5797752380371094, "step": 212550 }, { "epoch": 1.2635007816633081, "grad_norm": 1.3226070404052734, "learning_rate": 0.00014912439098071863, "loss": 0.5863948822021484, "step": 212560 }, { "epoch": 1.2635602237399766, "grad_norm": 1.0960931777954102, "learning_rate": 0.00014911878505996314, "loss": 0.5758449554443359, "step": 212570 }, { "epoch": 1.263619665816645, "grad_norm": 2.129213333129883, "learning_rate": 0.00014911317895207623, "loss": 0.5826593399047851, "step": 212580 }, { "epoch": 1.2636791078933134, "grad_norm": 1.4358930587768555, "learning_rate": 0.0001491075726570846, "loss": 0.6247909545898438, "step": 212590 }, { "epoch": 1.2637385499699818, "grad_norm": 1.7315263748168945, "learning_rate": 0.00014910196617501516, "loss": 0.5377167701721192, "step": 212600 }, { "epoch": 1.2637979920466502, "grad_norm": 1.4641824960708618, "learning_rate": 0.00014909635950589466, "loss": 0.6344389915466309, "step": 212610 }, { "epoch": 1.2638574341233184, "grad_norm": 1.8732057809829712, "learning_rate": 0.00014909075264974998, "loss": 0.6026465892791748, "step": 212620 }, { "epoch": 1.2639168761999868, "grad_norm": 1.6071630716323853, "learning_rate": 0.0001490851456066079, "loss": 0.6035710334777832, "step": 212630 }, { "epoch": 1.2639763182766552, "grad_norm": 1.2565362453460693, "learning_rate": 0.00014907953837649525, "loss": 0.5798463821411133, "step": 212640 }, { "epoch": 1.2640357603533237, "grad_norm": 1.5782467126846313, "learning_rate": 0.00014907393095943888, "loss": 0.6276372909545899, "step": 212650 }, { "epoch": 1.264095202429992, "grad_norm": 1.2946727275848389, "learning_rate": 0.0001490683233554656, "loss": 0.5301887512207031, "step": 212660 }, { "epoch": 1.2641546445066605, "grad_norm": 1.6881157159805298, "learning_rate": 0.00014906271556460222, "loss": 0.5977177143096923, "step": 212670 }, { "epoch": 1.264214086583329, "grad_norm": 1.8183462619781494, "learning_rate": 0.00014905710758687554, "loss": 0.6237027645111084, "step": 212680 }, { "epoch": 1.2642735286599973, "grad_norm": 1.6979820728302002, "learning_rate": 0.00014905149942231246, "loss": 0.6476943016052246, "step": 212690 }, { "epoch": 1.2643329707366657, "grad_norm": 1.4392434358596802, "learning_rate": 0.00014904589107093977, "loss": 0.5464614391326904, "step": 212700 }, { "epoch": 1.2643924128133341, "grad_norm": 1.871268391609192, "learning_rate": 0.0001490402825327843, "loss": 0.6234367370605469, "step": 212710 }, { "epoch": 1.2644518548900026, "grad_norm": 1.9714349508285522, "learning_rate": 0.00014903467380787284, "loss": 0.6370097160339355, "step": 212720 }, { "epoch": 1.2645112969666708, "grad_norm": 1.512728214263916, "learning_rate": 0.0001490290648962323, "loss": 0.6332216262817383, "step": 212730 }, { "epoch": 1.2645707390433392, "grad_norm": 1.213851809501648, "learning_rate": 0.00014902345579788942, "loss": 0.5127805709838867, "step": 212740 }, { "epoch": 1.2646301811200076, "grad_norm": 1.22642982006073, "learning_rate": 0.0001490178465128711, "loss": 0.5425478935241699, "step": 212750 }, { "epoch": 1.264689623196676, "grad_norm": 1.5547151565551758, "learning_rate": 0.0001490122370412042, "loss": 0.5490723609924316, "step": 212760 }, { "epoch": 1.2647490652733444, "grad_norm": 1.457043170928955, "learning_rate": 0.00014900662738291545, "loss": 0.7022546768188477, "step": 212770 }, { "epoch": 1.2648085073500128, "grad_norm": 2.1014597415924072, "learning_rate": 0.00014900101753803174, "loss": 0.619965648651123, "step": 212780 }, { "epoch": 1.2648679494266812, "grad_norm": 1.5218929052352905, "learning_rate": 0.00014899540750657996, "loss": 0.5597792625427246, "step": 212790 }, { "epoch": 1.2649273915033494, "grad_norm": 1.865494966506958, "learning_rate": 0.00014898979728858686, "loss": 0.6349621295928956, "step": 212800 }, { "epoch": 1.2649868335800178, "grad_norm": 2.1124377250671387, "learning_rate": 0.00014898418688407932, "loss": 0.6209277153015137, "step": 212810 }, { "epoch": 1.2650462756566863, "grad_norm": 1.82119882106781, "learning_rate": 0.00014897857629308419, "loss": 0.6698022842407226, "step": 212820 }, { "epoch": 1.2651057177333547, "grad_norm": 1.4846303462982178, "learning_rate": 0.00014897296551562823, "loss": 0.6338680267333985, "step": 212830 }, { "epoch": 1.265165159810023, "grad_norm": 1.469765067100525, "learning_rate": 0.00014896735455173838, "loss": 0.6176395416259766, "step": 212840 }, { "epoch": 1.2652246018866915, "grad_norm": 1.3437466621398926, "learning_rate": 0.00014896174340144145, "loss": 0.5728754043579102, "step": 212850 }, { "epoch": 1.26528404396336, "grad_norm": 1.524081826210022, "learning_rate": 0.00014895613206476424, "loss": 0.6013109683990479, "step": 212860 }, { "epoch": 1.2653434860400283, "grad_norm": 1.5164271593093872, "learning_rate": 0.00014895052054173367, "loss": 0.5847394466400146, "step": 212870 }, { "epoch": 1.2654029281166967, "grad_norm": 1.457667350769043, "learning_rate": 0.00014894490883237652, "loss": 0.6677309989929199, "step": 212880 }, { "epoch": 1.2654623701933652, "grad_norm": 1.3346712589263916, "learning_rate": 0.00014893929693671963, "loss": 0.6164691925048829, "step": 212890 }, { "epoch": 1.2655218122700336, "grad_norm": 1.5453240871429443, "learning_rate": 0.00014893368485478987, "loss": 0.6919342994689941, "step": 212900 }, { "epoch": 1.265581254346702, "grad_norm": 1.7837789058685303, "learning_rate": 0.0001489280725866141, "loss": 0.5595424175262451, "step": 212910 }, { "epoch": 1.2656406964233702, "grad_norm": 1.545483112335205, "learning_rate": 0.00014892246013221915, "loss": 0.5738139152526855, "step": 212920 }, { "epoch": 1.2657001385000386, "grad_norm": 1.3060591220855713, "learning_rate": 0.00014891684749163185, "loss": 0.6543062686920166, "step": 212930 }, { "epoch": 1.265759580576707, "grad_norm": 1.5940614938735962, "learning_rate": 0.0001489112346648791, "loss": 0.6400982856750488, "step": 212940 }, { "epoch": 1.2658190226533754, "grad_norm": 1.2163057327270508, "learning_rate": 0.00014890562165198774, "loss": 0.5784202575683594, "step": 212950 }, { "epoch": 1.2658784647300438, "grad_norm": 1.408782720565796, "learning_rate": 0.00014890000845298456, "loss": 0.6364212036132812, "step": 212960 }, { "epoch": 1.2659379068067123, "grad_norm": 1.2700726985931396, "learning_rate": 0.00014889439506789645, "loss": 0.6436046600341797, "step": 212970 }, { "epoch": 1.2659973488833807, "grad_norm": 1.3202604055404663, "learning_rate": 0.0001488887814967503, "loss": 0.5462555885314941, "step": 212980 }, { "epoch": 1.2660567909600489, "grad_norm": 1.5108439922332764, "learning_rate": 0.00014888316773957293, "loss": 0.6250129699707031, "step": 212990 }, { "epoch": 1.2661162330367173, "grad_norm": 1.9121774435043335, "learning_rate": 0.00014887755379639116, "loss": 0.6097149848937988, "step": 213000 }, { "epoch": 1.2661756751133857, "grad_norm": 1.4651297330856323, "learning_rate": 0.00014887193966723187, "loss": 0.5538169384002686, "step": 213010 }, { "epoch": 1.266235117190054, "grad_norm": 1.5063482522964478, "learning_rate": 0.00014886632535212195, "loss": 0.5908487796783447, "step": 213020 }, { "epoch": 1.2662945592667225, "grad_norm": 1.3722800016403198, "learning_rate": 0.0001488607108510882, "loss": 0.5676579475402832, "step": 213030 }, { "epoch": 1.266354001343391, "grad_norm": 1.6012916564941406, "learning_rate": 0.00014885509616415757, "loss": 0.6545517921447754, "step": 213040 }, { "epoch": 1.2664134434200593, "grad_norm": 1.7775578498840332, "learning_rate": 0.0001488494812913568, "loss": 0.5994676113128662, "step": 213050 }, { "epoch": 1.2664728854967278, "grad_norm": 1.4347127676010132, "learning_rate": 0.00014884386623271285, "loss": 0.5372013092041016, "step": 213060 }, { "epoch": 1.2665323275733962, "grad_norm": 1.4944641590118408, "learning_rate": 0.0001488382509882525, "loss": 0.5984508991241455, "step": 213070 }, { "epoch": 1.2665917696500646, "grad_norm": 1.9602802991867065, "learning_rate": 0.00014883263555800266, "loss": 0.6586081027984619, "step": 213080 }, { "epoch": 1.266651211726733, "grad_norm": 1.5997172594070435, "learning_rate": 0.0001488270199419902, "loss": 0.6505743980407714, "step": 213090 }, { "epoch": 1.2667106538034012, "grad_norm": 1.6876226663589478, "learning_rate": 0.00014882140414024196, "loss": 0.5920831203460694, "step": 213100 }, { "epoch": 1.2667700958800696, "grad_norm": 1.7611980438232422, "learning_rate": 0.0001488157881527848, "loss": 0.689623498916626, "step": 213110 }, { "epoch": 1.266829537956738, "grad_norm": 1.3770952224731445, "learning_rate": 0.0001488101719796456, "loss": 0.5685402870178222, "step": 213120 }, { "epoch": 1.2668889800334064, "grad_norm": 1.594504714012146, "learning_rate": 0.00014880455562085122, "loss": 0.6111580848693847, "step": 213130 }, { "epoch": 1.2669484221100749, "grad_norm": 1.4910718202590942, "learning_rate": 0.00014879893907642852, "loss": 0.6350615978240967, "step": 213140 }, { "epoch": 1.2670078641867433, "grad_norm": 1.3948723077774048, "learning_rate": 0.00014879332234640438, "loss": 0.6426972389221192, "step": 213150 }, { "epoch": 1.2670673062634117, "grad_norm": 1.676719307899475, "learning_rate": 0.0001487877054308057, "loss": 0.5879979610443116, "step": 213160 }, { "epoch": 1.2671267483400799, "grad_norm": 1.5627835988998413, "learning_rate": 0.00014878208832965923, "loss": 0.6271486759185791, "step": 213170 }, { "epoch": 1.2671861904167483, "grad_norm": 1.6052016019821167, "learning_rate": 0.00014877647104299198, "loss": 0.5757647037506104, "step": 213180 }, { "epoch": 1.2672456324934167, "grad_norm": 1.5073003768920898, "learning_rate": 0.00014877085357083077, "loss": 0.5952461242675782, "step": 213190 }, { "epoch": 1.2673050745700851, "grad_norm": 1.8324062824249268, "learning_rate": 0.00014876523591320247, "loss": 0.5792004585266113, "step": 213200 }, { "epoch": 1.2673645166467535, "grad_norm": 1.6987543106079102, "learning_rate": 0.0001487596180701339, "loss": 0.6002460479736328, "step": 213210 }, { "epoch": 1.267423958723422, "grad_norm": 1.2044930458068848, "learning_rate": 0.000148754000041652, "loss": 0.6227294921875, "step": 213220 }, { "epoch": 1.2674834008000904, "grad_norm": 1.7124055624008179, "learning_rate": 0.00014874838182778367, "loss": 0.6412552833557129, "step": 213230 }, { "epoch": 1.2675428428767588, "grad_norm": 1.402139663696289, "learning_rate": 0.00014874276342855572, "loss": 0.5681961059570313, "step": 213240 }, { "epoch": 1.2676022849534272, "grad_norm": 1.5634498596191406, "learning_rate": 0.00014873714484399506, "loss": 0.6044806480407715, "step": 213250 }, { "epoch": 1.2676617270300956, "grad_norm": 1.4275602102279663, "learning_rate": 0.00014873152607412855, "loss": 0.5813788414001465, "step": 213260 }, { "epoch": 1.267721169106764, "grad_norm": 1.8480300903320312, "learning_rate": 0.00014872590711898306, "loss": 0.6271974563598632, "step": 213270 }, { "epoch": 1.2677806111834324, "grad_norm": 1.6082595586776733, "learning_rate": 0.00014872028797858553, "loss": 0.6125286102294922, "step": 213280 }, { "epoch": 1.2678400532601006, "grad_norm": 2.0102782249450684, "learning_rate": 0.00014871466865296276, "loss": 0.6010019779205322, "step": 213290 }, { "epoch": 1.267899495336769, "grad_norm": 1.2000830173492432, "learning_rate": 0.00014870904914214168, "loss": 0.5678912162780761, "step": 213300 }, { "epoch": 1.2679589374134375, "grad_norm": 1.3193445205688477, "learning_rate": 0.00014870342944614916, "loss": 0.5750689029693603, "step": 213310 }, { "epoch": 1.2680183794901059, "grad_norm": 1.899085283279419, "learning_rate": 0.00014869780956501208, "loss": 0.6032778739929199, "step": 213320 }, { "epoch": 1.2680778215667743, "grad_norm": 1.7157738208770752, "learning_rate": 0.0001486921894987573, "loss": 0.532007884979248, "step": 213330 }, { "epoch": 1.2681372636434427, "grad_norm": 1.565665364265442, "learning_rate": 0.00014868656924741177, "loss": 0.6119363307952881, "step": 213340 }, { "epoch": 1.2681967057201111, "grad_norm": 1.5872918367385864, "learning_rate": 0.0001486809488110023, "loss": 0.5803241729736328, "step": 213350 }, { "epoch": 1.2682561477967793, "grad_norm": 1.442156195640564, "learning_rate": 0.00014867532818955585, "loss": 0.6178956031799316, "step": 213360 }, { "epoch": 1.2683155898734477, "grad_norm": 1.452439308166504, "learning_rate": 0.00014866970738309924, "loss": 0.6112988471984864, "step": 213370 }, { "epoch": 1.2683750319501161, "grad_norm": 1.3693045377731323, "learning_rate": 0.0001486640863916594, "loss": 0.6366116523742675, "step": 213380 }, { "epoch": 1.2684344740267846, "grad_norm": 1.4248361587524414, "learning_rate": 0.0001486584652152632, "loss": 0.5947779655456543, "step": 213390 }, { "epoch": 1.268493916103453, "grad_norm": 1.4568099975585938, "learning_rate": 0.00014865284385393756, "loss": 0.6253782749176026, "step": 213400 }, { "epoch": 1.2685533581801214, "grad_norm": 1.4231070280075073, "learning_rate": 0.00014864722230770934, "loss": 0.6237901210784912, "step": 213410 }, { "epoch": 1.2686128002567898, "grad_norm": 1.5487686395645142, "learning_rate": 0.0001486416005766054, "loss": 0.6271713256835938, "step": 213420 }, { "epoch": 1.2686722423334582, "grad_norm": 1.7296926975250244, "learning_rate": 0.0001486359786606527, "loss": 0.5762123584747314, "step": 213430 }, { "epoch": 1.2687316844101266, "grad_norm": 1.5461883544921875, "learning_rate": 0.0001486303565598781, "loss": 0.6016444683074951, "step": 213440 }, { "epoch": 1.268791126486795, "grad_norm": 1.476017713546753, "learning_rate": 0.0001486247342743085, "loss": 0.6719452381134033, "step": 213450 }, { "epoch": 1.2688505685634635, "grad_norm": 1.5685930252075195, "learning_rate": 0.0001486191118039708, "loss": 0.6342785835266114, "step": 213460 }, { "epoch": 1.2689100106401316, "grad_norm": 1.6273415088653564, "learning_rate": 0.00014861348914889188, "loss": 0.6016539573669434, "step": 213470 }, { "epoch": 1.2689694527168, "grad_norm": 1.5132129192352295, "learning_rate": 0.00014860786630909866, "loss": 0.5836230278015136, "step": 213480 }, { "epoch": 1.2690288947934685, "grad_norm": 1.6724739074707031, "learning_rate": 0.000148602243284618, "loss": 0.6084859848022461, "step": 213490 }, { "epoch": 1.269088336870137, "grad_norm": 1.9134597778320312, "learning_rate": 0.00014859662007547683, "loss": 0.6249518394470215, "step": 213500 }, { "epoch": 1.2691477789468053, "grad_norm": 1.9096044301986694, "learning_rate": 0.00014859099668170205, "loss": 0.6332952499389648, "step": 213510 }, { "epoch": 1.2692072210234737, "grad_norm": 1.8873651027679443, "learning_rate": 0.00014858537310332058, "loss": 0.630166482925415, "step": 213520 }, { "epoch": 1.2692666631001421, "grad_norm": 1.4121813774108887, "learning_rate": 0.00014857974934035927, "loss": 0.6784075736999512, "step": 213530 }, { "epoch": 1.2693261051768103, "grad_norm": 1.8855178356170654, "learning_rate": 0.00014857412539284504, "loss": 0.645441198348999, "step": 213540 }, { "epoch": 1.2693855472534787, "grad_norm": 2.057086229324341, "learning_rate": 0.0001485685012608048, "loss": 0.5968340873718262, "step": 213550 }, { "epoch": 1.2694449893301472, "grad_norm": 1.5437514781951904, "learning_rate": 0.00014856287694426547, "loss": 0.619953966140747, "step": 213560 }, { "epoch": 1.2695044314068156, "grad_norm": 1.4494564533233643, "learning_rate": 0.00014855725244325394, "loss": 0.6275116920471191, "step": 213570 }, { "epoch": 1.269563873483484, "grad_norm": 1.3505840301513672, "learning_rate": 0.0001485516277577971, "loss": 0.5908150672912598, "step": 213580 }, { "epoch": 1.2696233155601524, "grad_norm": 1.5265017747879028, "learning_rate": 0.0001485460028879219, "loss": 0.5864768028259277, "step": 213590 }, { "epoch": 1.2696827576368208, "grad_norm": 1.5200296640396118, "learning_rate": 0.0001485403778336552, "loss": 0.6227644920349121, "step": 213600 }, { "epoch": 1.2697421997134892, "grad_norm": 1.4884917736053467, "learning_rate": 0.00014853475259502392, "loss": 0.559721565246582, "step": 213610 }, { "epoch": 1.2698016417901576, "grad_norm": 1.680582046508789, "learning_rate": 0.00014852912717205495, "loss": 0.6435282707214356, "step": 213620 }, { "epoch": 1.269861083866826, "grad_norm": 1.6609190702438354, "learning_rate": 0.00014852350156477527, "loss": 0.6002671718597412, "step": 213630 }, { "epoch": 1.2699205259434945, "grad_norm": 1.632501482963562, "learning_rate": 0.0001485178757732117, "loss": 0.5793075561523438, "step": 213640 }, { "epoch": 1.2699799680201629, "grad_norm": 1.5787914991378784, "learning_rate": 0.0001485122497973913, "loss": 0.6462451934814453, "step": 213650 }, { "epoch": 1.270039410096831, "grad_norm": 1.3907707929611206, "learning_rate": 0.00014850662363734082, "loss": 0.6494436264038086, "step": 213660 }, { "epoch": 1.2700988521734995, "grad_norm": 1.4820932149887085, "learning_rate": 0.00014850099729308723, "loss": 0.5879271984100342, "step": 213670 }, { "epoch": 1.270158294250168, "grad_norm": 1.689359188079834, "learning_rate": 0.00014849537076465745, "loss": 0.6144436359405517, "step": 213680 }, { "epoch": 1.2702177363268363, "grad_norm": 1.71314537525177, "learning_rate": 0.0001484897440520784, "loss": 0.6139147758483887, "step": 213690 }, { "epoch": 1.2702771784035047, "grad_norm": 1.5706849098205566, "learning_rate": 0.00014848411715537698, "loss": 0.6181835651397705, "step": 213700 }, { "epoch": 1.2703366204801732, "grad_norm": 1.2028334140777588, "learning_rate": 0.00014847849007458016, "loss": 0.6285524845123291, "step": 213710 }, { "epoch": 1.2703960625568416, "grad_norm": 1.5034210681915283, "learning_rate": 0.00014847286280971479, "loss": 0.6012533187866211, "step": 213720 }, { "epoch": 1.2704555046335098, "grad_norm": 1.3358880281448364, "learning_rate": 0.00014846723536080783, "loss": 0.5942857265472412, "step": 213730 }, { "epoch": 1.2705149467101782, "grad_norm": 1.2562865018844604, "learning_rate": 0.0001484616077278862, "loss": 0.5871124267578125, "step": 213740 }, { "epoch": 1.2705743887868466, "grad_norm": 1.6865549087524414, "learning_rate": 0.00014845597991097677, "loss": 0.591652774810791, "step": 213750 }, { "epoch": 1.270633830863515, "grad_norm": 1.7556612491607666, "learning_rate": 0.0001484503519101065, "loss": 0.6106717109680175, "step": 213760 }, { "epoch": 1.2706932729401834, "grad_norm": 1.4939044713974, "learning_rate": 0.00014844472372530236, "loss": 0.6004129409790039, "step": 213770 }, { "epoch": 1.2707527150168518, "grad_norm": 1.7397445440292358, "learning_rate": 0.0001484390953565912, "loss": 0.6932188987731933, "step": 213780 }, { "epoch": 1.2708121570935202, "grad_norm": 1.2636648416519165, "learning_rate": 0.00014843346680399995, "loss": 0.6952844619750976, "step": 213790 }, { "epoch": 1.2708715991701887, "grad_norm": 1.5982438325881958, "learning_rate": 0.00014842783806755559, "loss": 0.5568666458129883, "step": 213800 }, { "epoch": 1.270931041246857, "grad_norm": 1.868446946144104, "learning_rate": 0.00014842220914728496, "loss": 0.5930705070495605, "step": 213810 }, { "epoch": 1.2709904833235255, "grad_norm": 1.5685545206069946, "learning_rate": 0.00014841658004321508, "loss": 0.5721837520599365, "step": 213820 }, { "epoch": 1.271049925400194, "grad_norm": 1.4901683330535889, "learning_rate": 0.00014841095075537284, "loss": 0.5607210159301758, "step": 213830 }, { "epoch": 1.271109367476862, "grad_norm": 1.5777599811553955, "learning_rate": 0.00014840532128378514, "loss": 0.6053763866424561, "step": 213840 }, { "epoch": 1.2711688095535305, "grad_norm": 1.7465229034423828, "learning_rate": 0.00014839969162847892, "loss": 0.6091127395629883, "step": 213850 }, { "epoch": 1.271228251630199, "grad_norm": 1.1740056276321411, "learning_rate": 0.00014839406178948118, "loss": 0.7040651321411133, "step": 213860 }, { "epoch": 1.2712876937068673, "grad_norm": 2.217278003692627, "learning_rate": 0.00014838843176681875, "loss": 0.5864038467407227, "step": 213870 }, { "epoch": 1.2713471357835358, "grad_norm": 1.4031755924224854, "learning_rate": 0.00014838280156051863, "loss": 0.565488052368164, "step": 213880 }, { "epoch": 1.2714065778602042, "grad_norm": 1.7014014720916748, "learning_rate": 0.0001483771711706077, "loss": 0.6528090000152588, "step": 213890 }, { "epoch": 1.2714660199368726, "grad_norm": 1.9554085731506348, "learning_rate": 0.00014837154059711298, "loss": 0.5901426315307617, "step": 213900 }, { "epoch": 1.2715254620135408, "grad_norm": 1.85086190700531, "learning_rate": 0.0001483659098400613, "loss": 0.6427489280700683, "step": 213910 }, { "epoch": 1.2715849040902092, "grad_norm": 1.509183406829834, "learning_rate": 0.00014836027889947965, "loss": 0.6101970672607422, "step": 213920 }, { "epoch": 1.2716443461668776, "grad_norm": 1.2120087146759033, "learning_rate": 0.000148354647775395, "loss": 0.5711843490600585, "step": 213930 }, { "epoch": 1.271703788243546, "grad_norm": 1.5845988988876343, "learning_rate": 0.00014834901646783422, "loss": 0.6419125556945801, "step": 213940 }, { "epoch": 1.2717632303202144, "grad_norm": 1.2710697650909424, "learning_rate": 0.00014834338497682426, "loss": 0.5965997219085694, "step": 213950 }, { "epoch": 1.2718226723968828, "grad_norm": 1.5723992586135864, "learning_rate": 0.00014833775330239213, "loss": 0.6022519111633301, "step": 213960 }, { "epoch": 1.2718821144735513, "grad_norm": 1.7690197229385376, "learning_rate": 0.0001483321214445647, "loss": 0.6412517547607421, "step": 213970 }, { "epoch": 1.2719415565502197, "grad_norm": 1.6257485151290894, "learning_rate": 0.00014832648940336888, "loss": 0.6780802726745605, "step": 213980 }, { "epoch": 1.272000998626888, "grad_norm": 1.5900846719741821, "learning_rate": 0.0001483208571788317, "loss": 0.6327824592590332, "step": 213990 }, { "epoch": 1.2720604407035565, "grad_norm": 1.3152168989181519, "learning_rate": 0.0001483152247709801, "loss": 0.63828125, "step": 214000 }, { "epoch": 1.272119882780225, "grad_norm": 1.3150631189346313, "learning_rate": 0.0001483095921798409, "loss": 0.6216165542602539, "step": 214010 }, { "epoch": 1.2721793248568933, "grad_norm": 1.2840416431427002, "learning_rate": 0.0001483039594054412, "loss": 0.5827241897583008, "step": 214020 }, { "epoch": 1.2722387669335615, "grad_norm": 1.2931593656539917, "learning_rate": 0.00014829832644780785, "loss": 0.5850800514221192, "step": 214030 }, { "epoch": 1.27229820901023, "grad_norm": 2.0422000885009766, "learning_rate": 0.0001482926933069678, "loss": 0.6546483516693116, "step": 214040 }, { "epoch": 1.2723576510868984, "grad_norm": 1.6002393960952759, "learning_rate": 0.00014828705998294806, "loss": 0.6059380531311035, "step": 214050 }, { "epoch": 1.2724170931635668, "grad_norm": 1.7718212604522705, "learning_rate": 0.0001482814264757755, "loss": 0.5891956329345703, "step": 214060 }, { "epoch": 1.2724765352402352, "grad_norm": 1.7988574504852295, "learning_rate": 0.00014827579278547712, "loss": 0.628051471710205, "step": 214070 }, { "epoch": 1.2725359773169036, "grad_norm": 1.9352234601974487, "learning_rate": 0.00014827015891207988, "loss": 0.622036075592041, "step": 214080 }, { "epoch": 1.272595419393572, "grad_norm": 1.5192698240280151, "learning_rate": 0.0001482645248556107, "loss": 0.6150246620178222, "step": 214090 }, { "epoch": 1.2726548614702402, "grad_norm": 1.492329478263855, "learning_rate": 0.0001482588906160965, "loss": 0.6184916019439697, "step": 214100 }, { "epoch": 1.2727143035469086, "grad_norm": 1.5287654399871826, "learning_rate": 0.00014825325619356432, "loss": 0.604738426208496, "step": 214110 }, { "epoch": 1.272773745623577, "grad_norm": 1.6036159992218018, "learning_rate": 0.00014824762158804103, "loss": 0.6591331481933593, "step": 214120 }, { "epoch": 1.2728331877002454, "grad_norm": 1.8290201425552368, "learning_rate": 0.00014824198679955363, "loss": 0.6568652629852295, "step": 214130 }, { "epoch": 1.2728926297769139, "grad_norm": 1.6586782932281494, "learning_rate": 0.00014823635182812907, "loss": 0.6799152374267579, "step": 214140 }, { "epoch": 1.2729520718535823, "grad_norm": 1.593018651008606, "learning_rate": 0.0001482307166737943, "loss": 0.5953275680541992, "step": 214150 }, { "epoch": 1.2730115139302507, "grad_norm": 1.6950279474258423, "learning_rate": 0.00014822508133657624, "loss": 0.6018519401550293, "step": 214160 }, { "epoch": 1.273070956006919, "grad_norm": 1.346940517425537, "learning_rate": 0.0001482194458165019, "loss": 0.6144656658172607, "step": 214170 }, { "epoch": 1.2731303980835875, "grad_norm": 1.6248142719268799, "learning_rate": 0.00014821381011359826, "loss": 0.6238472938537598, "step": 214180 }, { "epoch": 1.273189840160256, "grad_norm": 1.3061610460281372, "learning_rate": 0.0001482081742278922, "loss": 0.5970411777496338, "step": 214190 }, { "epoch": 1.2732492822369244, "grad_norm": 1.4934333562850952, "learning_rate": 0.00014820253815941073, "loss": 0.5484052658081054, "step": 214200 }, { "epoch": 1.2733087243135925, "grad_norm": 1.6296865940093994, "learning_rate": 0.0001481969019081808, "loss": 0.5623056411743164, "step": 214210 }, { "epoch": 1.273368166390261, "grad_norm": 1.7302888631820679, "learning_rate": 0.00014819126547422937, "loss": 0.5462018013000488, "step": 214220 }, { "epoch": 1.2734276084669294, "grad_norm": 1.633545160293579, "learning_rate": 0.00014818562885758342, "loss": 0.5900654792785645, "step": 214230 }, { "epoch": 1.2734870505435978, "grad_norm": 1.5466526746749878, "learning_rate": 0.0001481799920582699, "loss": 0.5823205471038818, "step": 214240 }, { "epoch": 1.2735464926202662, "grad_norm": 1.754033088684082, "learning_rate": 0.00014817435507631576, "loss": 0.5480108261108398, "step": 214250 }, { "epoch": 1.2736059346969346, "grad_norm": 1.5326703786849976, "learning_rate": 0.000148168717911748, "loss": 0.6066108703613281, "step": 214260 }, { "epoch": 1.273665376773603, "grad_norm": 2.1501386165618896, "learning_rate": 0.00014816308056459358, "loss": 0.5923891067504883, "step": 214270 }, { "epoch": 1.2737248188502712, "grad_norm": 1.9094504117965698, "learning_rate": 0.00014815744303487942, "loss": 0.604634952545166, "step": 214280 }, { "epoch": 1.2737842609269396, "grad_norm": 1.575840711593628, "learning_rate": 0.00014815180532263254, "loss": 0.6335531711578369, "step": 214290 }, { "epoch": 1.273843703003608, "grad_norm": 1.8114359378814697, "learning_rate": 0.00014814616742787987, "loss": 0.6529618740081787, "step": 214300 }, { "epoch": 1.2739031450802765, "grad_norm": 1.4912623167037964, "learning_rate": 0.0001481405293506484, "loss": 0.5704163551330567, "step": 214310 }, { "epoch": 1.2739625871569449, "grad_norm": 1.6608878374099731, "learning_rate": 0.00014813489109096514, "loss": 0.5839707374572753, "step": 214320 }, { "epoch": 1.2740220292336133, "grad_norm": 1.6589566469192505, "learning_rate": 0.00014812925264885704, "loss": 0.6547682285308838, "step": 214330 }, { "epoch": 1.2740814713102817, "grad_norm": 1.616943597793579, "learning_rate": 0.000148123614024351, "loss": 0.6522366523742675, "step": 214340 }, { "epoch": 1.2741409133869501, "grad_norm": 1.8198479413986206, "learning_rate": 0.00014811797521747407, "loss": 0.5943738460540772, "step": 214350 }, { "epoch": 1.2742003554636185, "grad_norm": 1.6370468139648438, "learning_rate": 0.00014811233622825321, "loss": 0.618367862701416, "step": 214360 }, { "epoch": 1.274259797540287, "grad_norm": 1.8142236471176147, "learning_rate": 0.0001481066970567154, "loss": 0.5715517044067383, "step": 214370 }, { "epoch": 1.2743192396169554, "grad_norm": 1.5265400409698486, "learning_rate": 0.00014810105770288756, "loss": 0.6235860347747803, "step": 214380 }, { "epoch": 1.2743786816936238, "grad_norm": 1.3899544477462769, "learning_rate": 0.00014809541816679676, "loss": 0.6089015007019043, "step": 214390 }, { "epoch": 1.274438123770292, "grad_norm": 1.449537754058838, "learning_rate": 0.00014808977844846987, "loss": 0.6355499744415283, "step": 214400 }, { "epoch": 1.2744975658469604, "grad_norm": 1.532704472541809, "learning_rate": 0.000148084138547934, "loss": 0.5561966896057129, "step": 214410 }, { "epoch": 1.2745570079236288, "grad_norm": 1.5188225507736206, "learning_rate": 0.000148078498465216, "loss": 0.6376813888549805, "step": 214420 }, { "epoch": 1.2746164500002972, "grad_norm": 1.257936954498291, "learning_rate": 0.00014807285820034294, "loss": 0.6057398796081543, "step": 214430 }, { "epoch": 1.2746758920769656, "grad_norm": 2.1649768352508545, "learning_rate": 0.00014806721775334177, "loss": 0.6252923488616944, "step": 214440 }, { "epoch": 1.274735334153634, "grad_norm": 2.0830681324005127, "learning_rate": 0.00014806157712423946, "loss": 0.6028022289276123, "step": 214450 }, { "epoch": 1.2747947762303025, "grad_norm": 1.6470733880996704, "learning_rate": 0.00014805593631306302, "loss": 0.5577699184417725, "step": 214460 }, { "epoch": 1.2748542183069707, "grad_norm": 1.9950850009918213, "learning_rate": 0.00014805029531983935, "loss": 0.5632113933563232, "step": 214470 }, { "epoch": 1.274913660383639, "grad_norm": 1.6893528699874878, "learning_rate": 0.00014804465414459557, "loss": 0.6813875198364258, "step": 214480 }, { "epoch": 1.2749731024603075, "grad_norm": 1.7840569019317627, "learning_rate": 0.00014803901278735858, "loss": 0.6311006546020508, "step": 214490 }, { "epoch": 1.275032544536976, "grad_norm": 1.3779215812683105, "learning_rate": 0.0001480333712481554, "loss": 0.5796920776367187, "step": 214500 }, { "epoch": 1.2750919866136443, "grad_norm": 1.5960862636566162, "learning_rate": 0.00014802772952701297, "loss": 0.5224565505981446, "step": 214510 }, { "epoch": 1.2751514286903127, "grad_norm": 2.1579859256744385, "learning_rate": 0.00014802208762395834, "loss": 0.6777867317199707, "step": 214520 }, { "epoch": 1.2752108707669811, "grad_norm": 2.0143606662750244, "learning_rate": 0.00014801644553901844, "loss": 0.628622579574585, "step": 214530 }, { "epoch": 1.2752703128436496, "grad_norm": 1.5854356288909912, "learning_rate": 0.00014801080327222032, "loss": 0.6046593189239502, "step": 214540 }, { "epoch": 1.275329754920318, "grad_norm": 1.5851563215255737, "learning_rate": 0.0001480051608235909, "loss": 0.5971652030944824, "step": 214550 }, { "epoch": 1.2753891969969864, "grad_norm": 1.6078147888183594, "learning_rate": 0.00014799951819315722, "loss": 0.6578101634979248, "step": 214560 }, { "epoch": 1.2754486390736548, "grad_norm": 1.637090802192688, "learning_rate": 0.00014799387538094632, "loss": 0.6011074542999267, "step": 214570 }, { "epoch": 1.275508081150323, "grad_norm": 1.3288596868515015, "learning_rate": 0.00014798823238698508, "loss": 0.6047774314880371, "step": 214580 }, { "epoch": 1.2755675232269914, "grad_norm": 1.6359025239944458, "learning_rate": 0.00014798258921130058, "loss": 0.5995992660522461, "step": 214590 }, { "epoch": 1.2756269653036598, "grad_norm": 1.2139105796813965, "learning_rate": 0.00014797694585391976, "loss": 0.5821922302246094, "step": 214600 }, { "epoch": 1.2756864073803282, "grad_norm": 1.6194185018539429, "learning_rate": 0.00014797130231486964, "loss": 0.5575371742248535, "step": 214610 }, { "epoch": 1.2757458494569967, "grad_norm": 1.4630954265594482, "learning_rate": 0.00014796565859417722, "loss": 0.6415988445281983, "step": 214620 }, { "epoch": 1.275805291533665, "grad_norm": 1.7125338315963745, "learning_rate": 0.00014796001469186953, "loss": 0.6207218647003174, "step": 214630 }, { "epoch": 1.2758647336103335, "grad_norm": 1.5383620262145996, "learning_rate": 0.00014795437060797354, "loss": 0.6127336502075196, "step": 214640 }, { "epoch": 1.2759241756870017, "grad_norm": 1.2560720443725586, "learning_rate": 0.00014794872634251618, "loss": 0.5642584800720215, "step": 214650 }, { "epoch": 1.27598361776367, "grad_norm": 1.808779239654541, "learning_rate": 0.00014794308189552456, "loss": 0.5812625885009766, "step": 214660 }, { "epoch": 1.2760430598403385, "grad_norm": 1.9060478210449219, "learning_rate": 0.00014793743726702562, "loss": 0.5822982788085938, "step": 214670 }, { "epoch": 1.276102501917007, "grad_norm": 1.8088030815124512, "learning_rate": 0.00014793179245704637, "loss": 0.6223328113555908, "step": 214680 }, { "epoch": 1.2761619439936753, "grad_norm": 1.4591758251190186, "learning_rate": 0.00014792614746561385, "loss": 0.618297004699707, "step": 214690 }, { "epoch": 1.2762213860703437, "grad_norm": 1.5328950881958008, "learning_rate": 0.00014792050229275503, "loss": 0.584898567199707, "step": 214700 }, { "epoch": 1.2762808281470122, "grad_norm": 1.3764673471450806, "learning_rate": 0.0001479148569384969, "loss": 0.5491811752319335, "step": 214710 }, { "epoch": 1.2763402702236806, "grad_norm": 1.5049705505371094, "learning_rate": 0.0001479092114028665, "loss": 0.6031733512878418, "step": 214720 }, { "epoch": 1.276399712300349, "grad_norm": 1.2388797998428345, "learning_rate": 0.00014790356568589083, "loss": 0.5984811305999755, "step": 214730 }, { "epoch": 1.2764591543770174, "grad_norm": 1.374405860900879, "learning_rate": 0.00014789791978759686, "loss": 0.6039341926574707, "step": 214740 }, { "epoch": 1.2765185964536858, "grad_norm": 1.240450382232666, "learning_rate": 0.00014789227370801166, "loss": 0.5630687713623047, "step": 214750 }, { "epoch": 1.2765780385303542, "grad_norm": 1.5833594799041748, "learning_rate": 0.0001478866274471622, "loss": 0.5943614959716796, "step": 214760 }, { "epoch": 1.2766374806070224, "grad_norm": 1.5494416952133179, "learning_rate": 0.00014788098100507549, "loss": 0.6027018070220947, "step": 214770 }, { "epoch": 1.2766969226836908, "grad_norm": 1.4615256786346436, "learning_rate": 0.0001478753343817785, "loss": 0.6700827598571777, "step": 214780 }, { "epoch": 1.2767563647603593, "grad_norm": 1.411332607269287, "learning_rate": 0.00014786968757729836, "loss": 0.5961021423339844, "step": 214790 }, { "epoch": 1.2768158068370277, "grad_norm": 1.3430759906768799, "learning_rate": 0.000147864040591662, "loss": 0.6229024887084961, "step": 214800 }, { "epoch": 1.276875248913696, "grad_norm": 1.636904001235962, "learning_rate": 0.0001478583934248964, "loss": 0.541557788848877, "step": 214810 }, { "epoch": 1.2769346909903645, "grad_norm": 1.6755702495574951, "learning_rate": 0.00014785274607702866, "loss": 0.5860464096069335, "step": 214820 }, { "epoch": 1.276994133067033, "grad_norm": 1.734444260597229, "learning_rate": 0.0001478470985480857, "loss": 0.5998169898986816, "step": 214830 }, { "epoch": 1.277053575143701, "grad_norm": 1.4773530960083008, "learning_rate": 0.00014784145083809465, "loss": 0.653404426574707, "step": 214840 }, { "epoch": 1.2771130172203695, "grad_norm": 1.5851680040359497, "learning_rate": 0.00014783580294708246, "loss": 0.6197176933288574, "step": 214850 }, { "epoch": 1.277172459297038, "grad_norm": 1.7413384914398193, "learning_rate": 0.00014783015487507611, "loss": 0.6695380210876465, "step": 214860 }, { "epoch": 1.2772319013737063, "grad_norm": 2.7867937088012695, "learning_rate": 0.00014782450662210268, "loss": 0.6761349678039551, "step": 214870 }, { "epoch": 1.2772913434503748, "grad_norm": 1.3973824977874756, "learning_rate": 0.0001478188581881892, "loss": 0.5963260650634765, "step": 214880 }, { "epoch": 1.2773507855270432, "grad_norm": 1.7918272018432617, "learning_rate": 0.00014781320957336263, "loss": 0.6188185691833497, "step": 214890 }, { "epoch": 1.2774102276037116, "grad_norm": 1.2282719612121582, "learning_rate": 0.00014780756077765003, "loss": 0.6130667686462402, "step": 214900 }, { "epoch": 1.27746966968038, "grad_norm": 1.5374691486358643, "learning_rate": 0.00014780191180107846, "loss": 0.6464418888092041, "step": 214910 }, { "epoch": 1.2775291117570484, "grad_norm": 1.5719866752624512, "learning_rate": 0.00014779626264367483, "loss": 0.5775265693664551, "step": 214920 }, { "epoch": 1.2775885538337168, "grad_norm": 2.0828423500061035, "learning_rate": 0.00014779061330546627, "loss": 0.5940464019775391, "step": 214930 }, { "epoch": 1.2776479959103852, "grad_norm": 1.677004337310791, "learning_rate": 0.00014778496378647978, "loss": 0.577955961227417, "step": 214940 }, { "epoch": 1.2777074379870534, "grad_norm": 1.7808023691177368, "learning_rate": 0.00014777931408674233, "loss": 0.6099271297454834, "step": 214950 }, { "epoch": 1.2777668800637219, "grad_norm": 1.7464903593063354, "learning_rate": 0.00014777366420628098, "loss": 0.6542101860046386, "step": 214960 }, { "epoch": 1.2778263221403903, "grad_norm": 1.6561957597732544, "learning_rate": 0.0001477680141451228, "loss": 0.6151587009429932, "step": 214970 }, { "epoch": 1.2778857642170587, "grad_norm": 1.4252214431762695, "learning_rate": 0.00014776236390329477, "loss": 0.6303036689758301, "step": 214980 }, { "epoch": 1.277945206293727, "grad_norm": 1.5539400577545166, "learning_rate": 0.00014775671348082393, "loss": 0.592888593673706, "step": 214990 }, { "epoch": 1.2780046483703955, "grad_norm": 1.5636974573135376, "learning_rate": 0.00014775106287773733, "loss": 0.5983224868774414, "step": 215000 }, { "epoch": 1.278064090447064, "grad_norm": 1.6792113780975342, "learning_rate": 0.00014774541209406196, "loss": 0.5903897285461426, "step": 215010 }, { "epoch": 1.2781235325237321, "grad_norm": 2.2882323265075684, "learning_rate": 0.00014773976112982486, "loss": 0.6365554809570313, "step": 215020 }, { "epoch": 1.2781829746004005, "grad_norm": 1.8999983072280884, "learning_rate": 0.0001477341099850531, "loss": 0.6121062278747559, "step": 215030 }, { "epoch": 1.278242416677069, "grad_norm": 1.470162034034729, "learning_rate": 0.0001477284586597737, "loss": 0.5771683692932129, "step": 215040 }, { "epoch": 1.2783018587537374, "grad_norm": 1.809289574623108, "learning_rate": 0.00014772280715401366, "loss": 0.6643474578857422, "step": 215050 }, { "epoch": 1.2783613008304058, "grad_norm": 1.6199413537979126, "learning_rate": 0.00014771715546780007, "loss": 0.5971694469451905, "step": 215060 }, { "epoch": 1.2784207429070742, "grad_norm": 1.4889646768569946, "learning_rate": 0.00014771150360115987, "loss": 0.5376605987548828, "step": 215070 }, { "epoch": 1.2784801849837426, "grad_norm": 1.4579145908355713, "learning_rate": 0.00014770585155412025, "loss": 0.5606095790863037, "step": 215080 }, { "epoch": 1.278539627060411, "grad_norm": 1.2536659240722656, "learning_rate": 0.00014770019932670812, "loss": 0.6050291061401367, "step": 215090 }, { "epoch": 1.2785990691370794, "grad_norm": 1.5943474769592285, "learning_rate": 0.0001476945469189505, "loss": 0.6474120616912842, "step": 215100 }, { "epoch": 1.2786585112137479, "grad_norm": 1.687807559967041, "learning_rate": 0.00014768889433087456, "loss": 0.5634145736694336, "step": 215110 }, { "epoch": 1.2787179532904163, "grad_norm": 2.0207743644714355, "learning_rate": 0.00014768324156250726, "loss": 0.6239080429077148, "step": 215120 }, { "epoch": 1.2787773953670847, "grad_norm": 1.72995126247406, "learning_rate": 0.00014767758861387563, "loss": 0.6275464057922363, "step": 215130 }, { "epoch": 1.2788368374437529, "grad_norm": 1.809226632118225, "learning_rate": 0.0001476719354850067, "loss": 0.6119158744812012, "step": 215140 }, { "epoch": 1.2788962795204213, "grad_norm": 1.364144206047058, "learning_rate": 0.0001476662821759276, "loss": 0.6111492156982422, "step": 215150 }, { "epoch": 1.2789557215970897, "grad_norm": 1.4059484004974365, "learning_rate": 0.0001476606286866653, "loss": 0.5649563312530518, "step": 215160 }, { "epoch": 1.2790151636737581, "grad_norm": 1.6142436265945435, "learning_rate": 0.00014765497501724684, "loss": 0.5957446098327637, "step": 215170 }, { "epoch": 1.2790746057504265, "grad_norm": 1.5386184453964233, "learning_rate": 0.00014764932116769928, "loss": 0.6131431579589843, "step": 215180 }, { "epoch": 1.279134047827095, "grad_norm": 1.2807884216308594, "learning_rate": 0.00014764366713804967, "loss": 0.6402207374572754, "step": 215190 }, { "epoch": 1.2791934899037634, "grad_norm": 1.428977370262146, "learning_rate": 0.00014763801292832506, "loss": 0.6292831420898437, "step": 215200 }, { "epoch": 1.2792529319804316, "grad_norm": 1.7044751644134521, "learning_rate": 0.00014763235853855252, "loss": 0.5834288597106934, "step": 215210 }, { "epoch": 1.2793123740571, "grad_norm": 1.3450043201446533, "learning_rate": 0.00014762670396875906, "loss": 0.6166027069091797, "step": 215220 }, { "epoch": 1.2793718161337684, "grad_norm": 1.6173782348632812, "learning_rate": 0.00014762104921897174, "loss": 0.5863664627075196, "step": 215230 }, { "epoch": 1.2794312582104368, "grad_norm": 1.5424559116363525, "learning_rate": 0.00014761539428921765, "loss": 0.6432317733764649, "step": 215240 }, { "epoch": 1.2794907002871052, "grad_norm": 1.5252126455307007, "learning_rate": 0.00014760973917952379, "loss": 0.6149738311767579, "step": 215250 }, { "epoch": 1.2795501423637736, "grad_norm": 1.3721450567245483, "learning_rate": 0.0001476040838899172, "loss": 0.5966965675354003, "step": 215260 }, { "epoch": 1.279609584440442, "grad_norm": 1.4788569211959839, "learning_rate": 0.00014759842842042498, "loss": 0.5772065162658692, "step": 215270 }, { "epoch": 1.2796690265171105, "grad_norm": 1.4373676776885986, "learning_rate": 0.00014759277277107417, "loss": 0.624554443359375, "step": 215280 }, { "epoch": 1.2797284685937789, "grad_norm": 1.4320244789123535, "learning_rate": 0.00014758711694189182, "loss": 0.584262466430664, "step": 215290 }, { "epoch": 1.2797879106704473, "grad_norm": 1.3876476287841797, "learning_rate": 0.00014758146093290497, "loss": 0.6028857231140137, "step": 215300 }, { "epoch": 1.2798473527471157, "grad_norm": 1.5834486484527588, "learning_rate": 0.00014757580474414073, "loss": 0.6710872173309326, "step": 215310 }, { "epoch": 1.2799067948237839, "grad_norm": 1.4348808526992798, "learning_rate": 0.00014757014837562607, "loss": 0.6582169532775879, "step": 215320 }, { "epoch": 1.2799662369004523, "grad_norm": 1.6238263845443726, "learning_rate": 0.00014756449182738813, "loss": 0.6329522132873535, "step": 215330 }, { "epoch": 1.2800256789771207, "grad_norm": 1.5535911321640015, "learning_rate": 0.00014755883509945394, "loss": 0.6298457145690918, "step": 215340 }, { "epoch": 1.2800851210537891, "grad_norm": 1.5286635160446167, "learning_rate": 0.00014755317819185052, "loss": 0.5796528339385987, "step": 215350 }, { "epoch": 1.2801445631304575, "grad_norm": 1.7696118354797363, "learning_rate": 0.000147547521104605, "loss": 0.6354013442993164, "step": 215360 }, { "epoch": 1.280204005207126, "grad_norm": 1.8368149995803833, "learning_rate": 0.00014754186383774445, "loss": 0.5784039497375488, "step": 215370 }, { "epoch": 1.2802634472837944, "grad_norm": 1.2411445379257202, "learning_rate": 0.00014753620639129582, "loss": 0.6016545772552491, "step": 215380 }, { "epoch": 1.2803228893604626, "grad_norm": 1.3182902336120605, "learning_rate": 0.0001475305487652863, "loss": 0.6113557815551758, "step": 215390 }, { "epoch": 1.280382331437131, "grad_norm": 1.5185267925262451, "learning_rate": 0.00014752489095974284, "loss": 0.613125991821289, "step": 215400 }, { "epoch": 1.2804417735137994, "grad_norm": 1.312071681022644, "learning_rate": 0.0001475192329746926, "loss": 0.5963655471801758, "step": 215410 }, { "epoch": 1.2805012155904678, "grad_norm": 1.6709874868392944, "learning_rate": 0.00014751357481016263, "loss": 0.6758235454559326, "step": 215420 }, { "epoch": 1.2805606576671362, "grad_norm": 1.2765218019485474, "learning_rate": 0.00014750791646617995, "loss": 0.5838757514953613, "step": 215430 }, { "epoch": 1.2806200997438046, "grad_norm": 1.3826217651367188, "learning_rate": 0.00014750225794277167, "loss": 0.5894883155822754, "step": 215440 }, { "epoch": 1.280679541820473, "grad_norm": 1.2158421277999878, "learning_rate": 0.0001474965992399648, "loss": 0.6034038543701172, "step": 215450 }, { "epoch": 1.2807389838971415, "grad_norm": 1.3763961791992188, "learning_rate": 0.00014749094035778652, "loss": 0.5502617835998536, "step": 215460 }, { "epoch": 1.2807984259738099, "grad_norm": 1.516020655632019, "learning_rate": 0.00014748528129626383, "loss": 0.6352091312408448, "step": 215470 }, { "epoch": 1.2808578680504783, "grad_norm": 1.579689860343933, "learning_rate": 0.00014747962205542375, "loss": 0.6414043426513671, "step": 215480 }, { "epoch": 1.2809173101271467, "grad_norm": 1.6585516929626465, "learning_rate": 0.00014747396263529343, "loss": 0.5619093894958496, "step": 215490 }, { "epoch": 1.2809767522038151, "grad_norm": 1.2128764390945435, "learning_rate": 0.00014746830303589994, "loss": 0.550431203842163, "step": 215500 }, { "epoch": 1.2810361942804833, "grad_norm": 1.602175235748291, "learning_rate": 0.0001474626432572703, "loss": 0.6346265792846679, "step": 215510 }, { "epoch": 1.2810956363571517, "grad_norm": 1.6390082836151123, "learning_rate": 0.00014745698329943164, "loss": 0.600210428237915, "step": 215520 }, { "epoch": 1.2811550784338201, "grad_norm": 1.3395133018493652, "learning_rate": 0.00014745132316241102, "loss": 0.5686704635620117, "step": 215530 }, { "epoch": 1.2812145205104886, "grad_norm": 1.5024480819702148, "learning_rate": 0.00014744566284623546, "loss": 0.5675629615783692, "step": 215540 }, { "epoch": 1.281273962587157, "grad_norm": 1.6268527507781982, "learning_rate": 0.00014744000235093215, "loss": 0.627143383026123, "step": 215550 }, { "epoch": 1.2813334046638254, "grad_norm": 1.7375869750976562, "learning_rate": 0.00014743434167652808, "loss": 0.623665714263916, "step": 215560 }, { "epoch": 1.2813928467404938, "grad_norm": 1.273607850074768, "learning_rate": 0.00014742868082305035, "loss": 0.581146240234375, "step": 215570 }, { "epoch": 1.281452288817162, "grad_norm": 1.4850883483886719, "learning_rate": 0.00014742301979052603, "loss": 0.646228551864624, "step": 215580 }, { "epoch": 1.2815117308938304, "grad_norm": 1.5118739604949951, "learning_rate": 0.00014741735857898224, "loss": 0.5881542205810547, "step": 215590 }, { "epoch": 1.2815711729704988, "grad_norm": 1.6703453063964844, "learning_rate": 0.00014741169718844604, "loss": 0.6069868087768555, "step": 215600 }, { "epoch": 1.2816306150471672, "grad_norm": 1.2479174137115479, "learning_rate": 0.00014740603561894447, "loss": 0.6203916549682618, "step": 215610 }, { "epoch": 1.2816900571238357, "grad_norm": 1.7177985906600952, "learning_rate": 0.00014740037387050468, "loss": 0.5831034660339356, "step": 215620 }, { "epoch": 1.281749499200504, "grad_norm": 1.5805542469024658, "learning_rate": 0.00014739471194315367, "loss": 0.6305077552795411, "step": 215630 }, { "epoch": 1.2818089412771725, "grad_norm": 1.4677224159240723, "learning_rate": 0.00014738904983691863, "loss": 0.559089183807373, "step": 215640 }, { "epoch": 1.281868383353841, "grad_norm": 1.4874331951141357, "learning_rate": 0.0001473833875518266, "loss": 0.5508095264434815, "step": 215650 }, { "epoch": 1.2819278254305093, "grad_norm": 1.4768117666244507, "learning_rate": 0.00014737772508790464, "loss": 0.5990370273590088, "step": 215660 }, { "epoch": 1.2819872675071777, "grad_norm": 1.3830146789550781, "learning_rate": 0.00014737206244517986, "loss": 0.5525842666625976, "step": 215670 }, { "epoch": 1.2820467095838461, "grad_norm": 1.7760356664657593, "learning_rate": 0.00014736639962367937, "loss": 0.6256563186645507, "step": 215680 }, { "epoch": 1.2821061516605143, "grad_norm": 1.7674205303192139, "learning_rate": 0.00014736073662343022, "loss": 0.6095401763916015, "step": 215690 }, { "epoch": 1.2821655937371828, "grad_norm": 1.593467116355896, "learning_rate": 0.0001473550734444595, "loss": 0.6005092620849609, "step": 215700 }, { "epoch": 1.2822250358138512, "grad_norm": 1.551900029182434, "learning_rate": 0.00014734941008679434, "loss": 0.5477510929107666, "step": 215710 }, { "epoch": 1.2822844778905196, "grad_norm": 1.9453511238098145, "learning_rate": 0.00014734374655046178, "loss": 0.6166552543640137, "step": 215720 }, { "epoch": 1.282343919967188, "grad_norm": 1.5700349807739258, "learning_rate": 0.00014733808283548896, "loss": 0.5723609924316406, "step": 215730 }, { "epoch": 1.2824033620438564, "grad_norm": 1.667309284210205, "learning_rate": 0.00014733241894190294, "loss": 0.5840858459472656, "step": 215740 }, { "epoch": 1.2824628041205248, "grad_norm": 1.7329059839248657, "learning_rate": 0.00014732675486973086, "loss": 0.607394790649414, "step": 215750 }, { "epoch": 1.282522246197193, "grad_norm": 1.4686167240142822, "learning_rate": 0.00014732109061899978, "loss": 0.6475466728210449, "step": 215760 }, { "epoch": 1.2825816882738614, "grad_norm": 1.6462630033493042, "learning_rate": 0.00014731542618973676, "loss": 0.6433013916015625, "step": 215770 }, { "epoch": 1.2826411303505298, "grad_norm": 1.5155930519104004, "learning_rate": 0.00014730976158196897, "loss": 0.6919637680053711, "step": 215780 }, { "epoch": 1.2827005724271983, "grad_norm": 1.4434101581573486, "learning_rate": 0.00014730409679572344, "loss": 0.6221102714538574, "step": 215790 }, { "epoch": 1.2827600145038667, "grad_norm": 1.6894394159317017, "learning_rate": 0.00014729843183102737, "loss": 0.5914090156555176, "step": 215800 }, { "epoch": 1.282819456580535, "grad_norm": 1.8599469661712646, "learning_rate": 0.0001472927666879077, "loss": 0.6637193202972412, "step": 215810 }, { "epoch": 1.2828788986572035, "grad_norm": 1.2376631498336792, "learning_rate": 0.00014728710136639167, "loss": 0.6181057453155517, "step": 215820 }, { "epoch": 1.282938340733872, "grad_norm": 1.036484718322754, "learning_rate": 0.00014728143586650635, "loss": 0.5858159065246582, "step": 215830 }, { "epoch": 1.2829977828105403, "grad_norm": 1.2670769691467285, "learning_rate": 0.00014727577018827878, "loss": 0.6273517608642578, "step": 215840 }, { "epoch": 1.2830572248872087, "grad_norm": 1.7834705114364624, "learning_rate": 0.00014727010433173617, "loss": 0.6410282611846924, "step": 215850 }, { "epoch": 1.2831166669638772, "grad_norm": 1.8398733139038086, "learning_rate": 0.0001472644382969055, "loss": 0.6624586105346679, "step": 215860 }, { "epoch": 1.2831761090405456, "grad_norm": 1.1819579601287842, "learning_rate": 0.00014725877208381395, "loss": 0.5775259971618653, "step": 215870 }, { "epoch": 1.2832355511172138, "grad_norm": 2.2464089393615723, "learning_rate": 0.00014725310569248864, "loss": 0.6242661476135254, "step": 215880 }, { "epoch": 1.2832949931938822, "grad_norm": 1.3855853080749512, "learning_rate": 0.00014724743912295662, "loss": 0.5873300552368164, "step": 215890 }, { "epoch": 1.2833544352705506, "grad_norm": 1.4303735494613647, "learning_rate": 0.000147241772375245, "loss": 0.6182084083557129, "step": 215900 }, { "epoch": 1.283413877347219, "grad_norm": 1.5910112857818604, "learning_rate": 0.00014723610544938097, "loss": 0.6047043800354004, "step": 215910 }, { "epoch": 1.2834733194238874, "grad_norm": 1.5458287000656128, "learning_rate": 0.00014723043834539154, "loss": 0.6107076644897461, "step": 215920 }, { "epoch": 1.2835327615005558, "grad_norm": 1.3574187755584717, "learning_rate": 0.0001472247710633039, "loss": 0.6170559406280518, "step": 215930 }, { "epoch": 1.2835922035772243, "grad_norm": 1.4785974025726318, "learning_rate": 0.00014721910360314505, "loss": 0.5869019508361817, "step": 215940 }, { "epoch": 1.2836516456538924, "grad_norm": 1.6501669883728027, "learning_rate": 0.00014721343596494222, "loss": 0.6033977508544922, "step": 215950 }, { "epoch": 1.2837110877305609, "grad_norm": 1.493173360824585, "learning_rate": 0.00014720776814872247, "loss": 0.6147234916687012, "step": 215960 }, { "epoch": 1.2837705298072293, "grad_norm": 1.2490134239196777, "learning_rate": 0.00014720210015451292, "loss": 0.6440599441528321, "step": 215970 }, { "epoch": 1.2838299718838977, "grad_norm": 1.0229465961456299, "learning_rate": 0.00014719643198234065, "loss": 0.6402088642120362, "step": 215980 }, { "epoch": 1.283889413960566, "grad_norm": 1.3917547464370728, "learning_rate": 0.00014719076363223287, "loss": 0.5763115882873535, "step": 215990 }, { "epoch": 1.2839488560372345, "grad_norm": 2.149477243423462, "learning_rate": 0.00014718509510421656, "loss": 0.5555760860443115, "step": 216000 }, { "epoch": 1.284008298113903, "grad_norm": 1.4534661769866943, "learning_rate": 0.00014717942639831894, "loss": 0.6057800769805908, "step": 216010 }, { "epoch": 1.2840677401905713, "grad_norm": 2.0512475967407227, "learning_rate": 0.00014717375751456711, "loss": 0.648113203048706, "step": 216020 }, { "epoch": 1.2841271822672398, "grad_norm": 1.4632720947265625, "learning_rate": 0.00014716808845298816, "loss": 0.6340800285339355, "step": 216030 }, { "epoch": 1.2841866243439082, "grad_norm": 1.3563320636749268, "learning_rate": 0.0001471624192136092, "loss": 0.6386580467224121, "step": 216040 }, { "epoch": 1.2842460664205766, "grad_norm": 1.6037712097167969, "learning_rate": 0.00014715674979645738, "loss": 0.5676596641540528, "step": 216050 }, { "epoch": 1.2843055084972448, "grad_norm": 1.524979829788208, "learning_rate": 0.00014715108020155984, "loss": 0.5987039566040039, "step": 216060 }, { "epoch": 1.2843649505739132, "grad_norm": 1.0753419399261475, "learning_rate": 0.00014714541042894363, "loss": 0.606795358657837, "step": 216070 }, { "epoch": 1.2844243926505816, "grad_norm": 1.3638129234313965, "learning_rate": 0.00014713974047863594, "loss": 0.606829023361206, "step": 216080 }, { "epoch": 1.28448383472725, "grad_norm": 1.661388874053955, "learning_rate": 0.0001471340703506639, "loss": 0.6098527908325195, "step": 216090 }, { "epoch": 1.2845432768039184, "grad_norm": 1.5581754446029663, "learning_rate": 0.00014712840004505451, "loss": 0.6420622825622558, "step": 216100 }, { "epoch": 1.2846027188805869, "grad_norm": 1.334447979927063, "learning_rate": 0.00014712272956183512, "loss": 0.6060408592224121, "step": 216110 }, { "epoch": 1.2846621609572553, "grad_norm": 1.7526401281356812, "learning_rate": 0.00014711705890103262, "loss": 0.6064108371734619, "step": 216120 }, { "epoch": 1.2847216030339235, "grad_norm": 1.6612648963928223, "learning_rate": 0.00014711138806267426, "loss": 0.588167381286621, "step": 216130 }, { "epoch": 1.2847810451105919, "grad_norm": 1.881172776222229, "learning_rate": 0.0001471057170467872, "loss": 0.5769641399383545, "step": 216140 }, { "epoch": 1.2848404871872603, "grad_norm": 2.000476121902466, "learning_rate": 0.00014710004585339844, "loss": 0.6206315040588379, "step": 216150 }, { "epoch": 1.2848999292639287, "grad_norm": 1.4709560871124268, "learning_rate": 0.00014709437448253522, "loss": 0.5340729236602784, "step": 216160 }, { "epoch": 1.2849593713405971, "grad_norm": 1.5584808588027954, "learning_rate": 0.00014708870293422463, "loss": 0.646639060974121, "step": 216170 }, { "epoch": 1.2850188134172655, "grad_norm": 1.4889854192733765, "learning_rate": 0.0001470830312084938, "loss": 0.619000244140625, "step": 216180 }, { "epoch": 1.285078255493934, "grad_norm": 1.3740822076797485, "learning_rate": 0.00014707735930536992, "loss": 0.5666628360748291, "step": 216190 }, { "epoch": 1.2851376975706024, "grad_norm": 1.5369203090667725, "learning_rate": 0.00014707168722488003, "loss": 0.6100125312805176, "step": 216200 }, { "epoch": 1.2851971396472708, "grad_norm": 1.4429856538772583, "learning_rate": 0.00014706601496705128, "loss": 0.6194312572479248, "step": 216210 }, { "epoch": 1.2852565817239392, "grad_norm": 1.1640617847442627, "learning_rate": 0.00014706034253191087, "loss": 0.5850824356079102, "step": 216220 }, { "epoch": 1.2853160238006076, "grad_norm": 1.904782772064209, "learning_rate": 0.00014705466991948586, "loss": 0.6126733779907226, "step": 216230 }, { "epoch": 1.285375465877276, "grad_norm": 1.4357243776321411, "learning_rate": 0.00014704899712980344, "loss": 0.5993446350097656, "step": 216240 }, { "epoch": 1.2854349079539442, "grad_norm": 1.5512008666992188, "learning_rate": 0.0001470433241628907, "loss": 0.5541701316833496, "step": 216250 }, { "epoch": 1.2854943500306126, "grad_norm": 1.7160181999206543, "learning_rate": 0.0001470376510187748, "loss": 0.5919992446899414, "step": 216260 }, { "epoch": 1.285553792107281, "grad_norm": 1.5424671173095703, "learning_rate": 0.00014703197769748295, "loss": 0.5955965995788575, "step": 216270 }, { "epoch": 1.2856132341839495, "grad_norm": 1.3372329473495483, "learning_rate": 0.00014702630419904215, "loss": 0.6415424346923828, "step": 216280 }, { "epoch": 1.2856726762606179, "grad_norm": 1.7155190706253052, "learning_rate": 0.00014702063052347963, "loss": 0.6105086803436279, "step": 216290 }, { "epoch": 1.2857321183372863, "grad_norm": 1.6911275386810303, "learning_rate": 0.00014701495667082253, "loss": 0.6446177959442139, "step": 216300 }, { "epoch": 1.2857915604139547, "grad_norm": 1.6681751012802124, "learning_rate": 0.00014700928264109795, "loss": 0.5196630477905273, "step": 216310 }, { "epoch": 1.285851002490623, "grad_norm": 1.4667242765426636, "learning_rate": 0.00014700360843433307, "loss": 0.5917021751403808, "step": 216320 }, { "epoch": 1.2859104445672913, "grad_norm": 1.9781657457351685, "learning_rate": 0.00014699793405055503, "loss": 0.6315102577209473, "step": 216330 }, { "epoch": 1.2859698866439597, "grad_norm": 2.1268460750579834, "learning_rate": 0.00014699225948979096, "loss": 0.628138542175293, "step": 216340 }, { "epoch": 1.2860293287206281, "grad_norm": 1.4893066883087158, "learning_rate": 0.000146986584752068, "loss": 0.6525696277618408, "step": 216350 }, { "epoch": 1.2860887707972966, "grad_norm": 1.8940881490707397, "learning_rate": 0.0001469809098374133, "loss": 0.5996391773223877, "step": 216360 }, { "epoch": 1.286148212873965, "grad_norm": 1.8706969022750854, "learning_rate": 0.00014697523474585403, "loss": 0.6004916191101074, "step": 216370 }, { "epoch": 1.2862076549506334, "grad_norm": 1.7387340068817139, "learning_rate": 0.0001469695594774173, "loss": 0.6406033515930176, "step": 216380 }, { "epoch": 1.2862670970273018, "grad_norm": 1.280653715133667, "learning_rate": 0.00014696388403213025, "loss": 0.6704976081848144, "step": 216390 }, { "epoch": 1.2863265391039702, "grad_norm": 1.0109951496124268, "learning_rate": 0.00014695820841002013, "loss": 0.5442549705505371, "step": 216400 }, { "epoch": 1.2863859811806386, "grad_norm": 1.5033657550811768, "learning_rate": 0.00014695253261111398, "loss": 0.5375271320343018, "step": 216410 }, { "epoch": 1.286445423257307, "grad_norm": 1.6543810367584229, "learning_rate": 0.00014694685663543903, "loss": 0.5633361339569092, "step": 216420 }, { "epoch": 1.2865048653339752, "grad_norm": 1.715282917022705, "learning_rate": 0.00014694118048302234, "loss": 0.5937353610992432, "step": 216430 }, { "epoch": 1.2865643074106436, "grad_norm": 1.6272364854812622, "learning_rate": 0.00014693550415389114, "loss": 0.589162540435791, "step": 216440 }, { "epoch": 1.286623749487312, "grad_norm": 1.0498806238174438, "learning_rate": 0.00014692982764807257, "loss": 0.6173124790191651, "step": 216450 }, { "epoch": 1.2866831915639805, "grad_norm": 1.6608238220214844, "learning_rate": 0.00014692415096559372, "loss": 0.6295590877532959, "step": 216460 }, { "epoch": 1.286742633640649, "grad_norm": 1.6591110229492188, "learning_rate": 0.00014691847410648186, "loss": 0.6081701278686523, "step": 216470 }, { "epoch": 1.2868020757173173, "grad_norm": 1.590924620628357, "learning_rate": 0.00014691279707076404, "loss": 0.6467048645019531, "step": 216480 }, { "epoch": 1.2868615177939857, "grad_norm": 1.891186237335205, "learning_rate": 0.0001469071198584675, "loss": 0.6072441577911377, "step": 216490 }, { "epoch": 1.286920959870654, "grad_norm": 1.7984216213226318, "learning_rate": 0.00014690144246961933, "loss": 0.6450508594512939, "step": 216500 }, { "epoch": 1.2869804019473223, "grad_norm": 1.683842420578003, "learning_rate": 0.00014689576490424674, "loss": 0.6046898841857911, "step": 216510 }, { "epoch": 1.2870398440239907, "grad_norm": 1.4282350540161133, "learning_rate": 0.00014689008716237687, "loss": 0.6164070129394531, "step": 216520 }, { "epoch": 1.2870992861006592, "grad_norm": 1.4905030727386475, "learning_rate": 0.00014688440924403686, "loss": 0.5982173919677735, "step": 216530 }, { "epoch": 1.2871587281773276, "grad_norm": 1.7548041343688965, "learning_rate": 0.0001468787311492539, "loss": 0.6630917072296143, "step": 216540 }, { "epoch": 1.287218170253996, "grad_norm": 1.0505603551864624, "learning_rate": 0.00014687305287805513, "loss": 0.5760636329650879, "step": 216550 }, { "epoch": 1.2872776123306644, "grad_norm": 1.3833580017089844, "learning_rate": 0.00014686737443046774, "loss": 0.5762154579162597, "step": 216560 }, { "epoch": 1.2873370544073328, "grad_norm": 1.5796741247177124, "learning_rate": 0.0001468616958065189, "loss": 0.5643108367919922, "step": 216570 }, { "epoch": 1.2873964964840012, "grad_norm": 1.8077300786972046, "learning_rate": 0.0001468560170062357, "loss": 0.5806004524230957, "step": 216580 }, { "epoch": 1.2874559385606696, "grad_norm": 1.4426300525665283, "learning_rate": 0.0001468503380296454, "loss": 0.5834518432617187, "step": 216590 }, { "epoch": 1.287515380637338, "grad_norm": 1.6532114744186401, "learning_rate": 0.0001468446588767751, "loss": 0.604214859008789, "step": 216600 }, { "epoch": 1.2875748227140065, "grad_norm": 1.05936861038208, "learning_rate": 0.00014683897954765202, "loss": 0.5699570655822754, "step": 216610 }, { "epoch": 1.2876342647906747, "grad_norm": 1.6032854318618774, "learning_rate": 0.00014683330004230328, "loss": 0.6559775352478028, "step": 216620 }, { "epoch": 1.287693706867343, "grad_norm": 2.3862664699554443, "learning_rate": 0.0001468276203607561, "loss": 0.581291675567627, "step": 216630 }, { "epoch": 1.2877531489440115, "grad_norm": 1.4862620830535889, "learning_rate": 0.0001468219405030376, "loss": 0.594382905960083, "step": 216640 }, { "epoch": 1.28781259102068, "grad_norm": 1.647039771080017, "learning_rate": 0.00014681626046917495, "loss": 0.6101515769958497, "step": 216650 }, { "epoch": 1.2878720330973483, "grad_norm": 1.614608883857727, "learning_rate": 0.00014681058025919536, "loss": 0.5917681217193603, "step": 216660 }, { "epoch": 1.2879314751740167, "grad_norm": 1.3971346616744995, "learning_rate": 0.00014680489987312596, "loss": 0.6104798316955566, "step": 216670 }, { "epoch": 1.2879909172506852, "grad_norm": 1.4767976999282837, "learning_rate": 0.000146799219310994, "loss": 0.5956396102905274, "step": 216680 }, { "epoch": 1.2880503593273533, "grad_norm": 1.5124932527542114, "learning_rate": 0.00014679353857282657, "loss": 0.6426446914672852, "step": 216690 }, { "epoch": 1.2881098014040218, "grad_norm": 1.3260620832443237, "learning_rate": 0.00014678785765865092, "loss": 0.5924531936645507, "step": 216700 }, { "epoch": 1.2881692434806902, "grad_norm": 1.744490623474121, "learning_rate": 0.0001467821765684941, "loss": 0.6397435665130615, "step": 216710 }, { "epoch": 1.2882286855573586, "grad_norm": 1.0691425800323486, "learning_rate": 0.0001467764953023834, "loss": 0.6111451148986816, "step": 216720 }, { "epoch": 1.288288127634027, "grad_norm": 1.703792929649353, "learning_rate": 0.00014677081386034598, "loss": 0.6103954792022706, "step": 216730 }, { "epoch": 1.2883475697106954, "grad_norm": 1.6265686750411987, "learning_rate": 0.000146765132242409, "loss": 0.5967324256896973, "step": 216740 }, { "epoch": 1.2884070117873638, "grad_norm": 1.2916302680969238, "learning_rate": 0.00014675945044859964, "loss": 0.5851458072662353, "step": 216750 }, { "epoch": 1.2884664538640322, "grad_norm": 1.4007532596588135, "learning_rate": 0.00014675376847894507, "loss": 0.5603795051574707, "step": 216760 }, { "epoch": 1.2885258959407007, "grad_norm": 1.4042575359344482, "learning_rate": 0.00014674808633347247, "loss": 0.6047461032867432, "step": 216770 }, { "epoch": 1.288585338017369, "grad_norm": 1.1699620485305786, "learning_rate": 0.00014674240401220908, "loss": 0.5665426254272461, "step": 216780 }, { "epoch": 1.2886447800940375, "grad_norm": 2.0604567527770996, "learning_rate": 0.00014673672151518203, "loss": 0.5698806285858155, "step": 216790 }, { "epoch": 1.2887042221707057, "grad_norm": 1.5431947708129883, "learning_rate": 0.00014673103884241847, "loss": 0.5937877655029297, "step": 216800 }, { "epoch": 1.288763664247374, "grad_norm": 1.3827664852142334, "learning_rate": 0.00014672535599394564, "loss": 0.5520837783813477, "step": 216810 }, { "epoch": 1.2888231063240425, "grad_norm": 1.8222479820251465, "learning_rate": 0.00014671967296979072, "loss": 0.6088216781616211, "step": 216820 }, { "epoch": 1.288882548400711, "grad_norm": 1.5742690563201904, "learning_rate": 0.0001467139897699809, "loss": 0.6330394744873047, "step": 216830 }, { "epoch": 1.2889419904773793, "grad_norm": 1.4730900526046753, "learning_rate": 0.00014670830639454331, "loss": 0.6386067390441894, "step": 216840 }, { "epoch": 1.2890014325540478, "grad_norm": 1.2506206035614014, "learning_rate": 0.00014670262284350523, "loss": 0.6043973445892334, "step": 216850 }, { "epoch": 1.2890608746307162, "grad_norm": 1.5513026714324951, "learning_rate": 0.00014669693911689374, "loss": 0.6049850463867188, "step": 216860 }, { "epoch": 1.2891203167073844, "grad_norm": 1.3990157842636108, "learning_rate": 0.00014669125521473613, "loss": 0.6185014724731446, "step": 216870 }, { "epoch": 1.2891797587840528, "grad_norm": 1.3664422035217285, "learning_rate": 0.00014668557113705952, "loss": 0.5666542053222656, "step": 216880 }, { "epoch": 1.2892392008607212, "grad_norm": 1.8349968194961548, "learning_rate": 0.00014667988688389112, "loss": 0.6281070232391357, "step": 216890 }, { "epoch": 1.2892986429373896, "grad_norm": 1.1324514150619507, "learning_rate": 0.00014667420245525816, "loss": 0.5992745399475098, "step": 216900 }, { "epoch": 1.289358085014058, "grad_norm": 1.3871817588806152, "learning_rate": 0.0001466685178511878, "loss": 0.577338457107544, "step": 216910 }, { "epoch": 1.2894175270907264, "grad_norm": 1.7859880924224854, "learning_rate": 0.0001466628330717072, "loss": 0.6581587314605712, "step": 216920 }, { "epoch": 1.2894769691673948, "grad_norm": 1.4940606355667114, "learning_rate": 0.0001466571481168436, "loss": 0.5702306747436523, "step": 216930 }, { "epoch": 1.2895364112440633, "grad_norm": 1.3883097171783447, "learning_rate": 0.0001466514629866242, "loss": 0.5607677936553955, "step": 216940 }, { "epoch": 1.2895958533207317, "grad_norm": 1.4631580114364624, "learning_rate": 0.00014664577768107616, "loss": 0.5753373146057129, "step": 216950 }, { "epoch": 1.2896552953974, "grad_norm": 1.4256151914596558, "learning_rate": 0.00014664009220022672, "loss": 0.604587173461914, "step": 216960 }, { "epoch": 1.2897147374740685, "grad_norm": 1.5392524003982544, "learning_rate": 0.00014663440654410302, "loss": 0.6230334281921387, "step": 216970 }, { "epoch": 1.289774179550737, "grad_norm": 1.6150208711624146, "learning_rate": 0.00014662872071273233, "loss": 0.6463099002838135, "step": 216980 }, { "epoch": 1.2898336216274051, "grad_norm": 1.5626928806304932, "learning_rate": 0.0001466230347061418, "loss": 0.6119050502777099, "step": 216990 }, { "epoch": 1.2898930637040735, "grad_norm": 1.567380666732788, "learning_rate": 0.00014661734852435863, "loss": 0.6266789436340332, "step": 217000 }, { "epoch": 1.289952505780742, "grad_norm": 1.8918488025665283, "learning_rate": 0.00014661166216741, "loss": 0.6658558368682861, "step": 217010 }, { "epoch": 1.2900119478574104, "grad_norm": 1.2937259674072266, "learning_rate": 0.00014660597563532316, "loss": 0.5719571590423584, "step": 217020 }, { "epoch": 1.2900713899340788, "grad_norm": 1.6248968839645386, "learning_rate": 0.00014660028892812533, "loss": 0.5695330619812011, "step": 217030 }, { "epoch": 1.2901308320107472, "grad_norm": 1.532152533531189, "learning_rate": 0.00014659460204584368, "loss": 0.5524662971496582, "step": 217040 }, { "epoch": 1.2901902740874156, "grad_norm": 1.8506799936294556, "learning_rate": 0.00014658891498850539, "loss": 0.601344108581543, "step": 217050 }, { "epoch": 1.2902497161640838, "grad_norm": 1.5451382398605347, "learning_rate": 0.0001465832277561377, "loss": 0.6053049087524414, "step": 217060 }, { "epoch": 1.2903091582407522, "grad_norm": 1.591579556465149, "learning_rate": 0.0001465775403487678, "loss": 0.6371560096740723, "step": 217070 }, { "epoch": 1.2903686003174206, "grad_norm": 1.5895535945892334, "learning_rate": 0.00014657185276642287, "loss": 0.6298724174499511, "step": 217080 }, { "epoch": 1.290428042394089, "grad_norm": 2.045651912689209, "learning_rate": 0.00014656616500913019, "loss": 0.6343024253845215, "step": 217090 }, { "epoch": 1.2904874844707575, "grad_norm": 1.5742651224136353, "learning_rate": 0.00014656047707691688, "loss": 0.6073953628540039, "step": 217100 }, { "epoch": 1.2905469265474259, "grad_norm": 1.4535315036773682, "learning_rate": 0.00014655478896981024, "loss": 0.6263082504272461, "step": 217110 }, { "epoch": 1.2906063686240943, "grad_norm": 1.5627467632293701, "learning_rate": 0.00014654910068783743, "loss": 0.6742210388183594, "step": 217120 }, { "epoch": 1.2906658107007627, "grad_norm": 1.6425366401672363, "learning_rate": 0.00014654341223102564, "loss": 0.6191828727722168, "step": 217130 }, { "epoch": 1.290725252777431, "grad_norm": 1.4783052206039429, "learning_rate": 0.00014653772359940215, "loss": 0.6225108623504638, "step": 217140 }, { "epoch": 1.2907846948540995, "grad_norm": 1.3072935342788696, "learning_rate": 0.0001465320347929941, "loss": 0.6481025695800782, "step": 217150 }, { "epoch": 1.290844136930768, "grad_norm": 1.8423296213150024, "learning_rate": 0.00014652634581182873, "loss": 0.6130287170410156, "step": 217160 }, { "epoch": 1.2909035790074361, "grad_norm": 1.364707350730896, "learning_rate": 0.0001465206566559333, "loss": 0.5726161956787109, "step": 217170 }, { "epoch": 1.2909630210841045, "grad_norm": 1.6249430179595947, "learning_rate": 0.00014651496732533492, "loss": 0.5994686603546142, "step": 217180 }, { "epoch": 1.291022463160773, "grad_norm": 1.526653528213501, "learning_rate": 0.00014650927782006095, "loss": 0.6167704582214355, "step": 217190 }, { "epoch": 1.2910819052374414, "grad_norm": 1.150443434715271, "learning_rate": 0.00014650358814013846, "loss": 0.5599446773529053, "step": 217200 }, { "epoch": 1.2911413473141098, "grad_norm": 1.572346568107605, "learning_rate": 0.00014649789828559472, "loss": 0.5606306552886963, "step": 217210 }, { "epoch": 1.2912007893907782, "grad_norm": 1.1654244661331177, "learning_rate": 0.00014649220825645702, "loss": 0.5838051795959472, "step": 217220 }, { "epoch": 1.2912602314674466, "grad_norm": 1.3403980731964111, "learning_rate": 0.00014648651805275248, "loss": 0.6330673217773437, "step": 217230 }, { "epoch": 1.2913196735441148, "grad_norm": 1.1780544519424438, "learning_rate": 0.0001464808276745084, "loss": 0.6323685646057129, "step": 217240 }, { "epoch": 1.2913791156207832, "grad_norm": 1.299552321434021, "learning_rate": 0.0001464751371217519, "loss": 0.6186703681945801, "step": 217250 }, { "epoch": 1.2914385576974516, "grad_norm": 1.466692328453064, "learning_rate": 0.00014646944639451031, "loss": 0.6242393970489502, "step": 217260 }, { "epoch": 1.29149799977412, "grad_norm": 1.7643771171569824, "learning_rate": 0.0001464637554928108, "loss": 0.5981713771820069, "step": 217270 }, { "epoch": 1.2915574418507885, "grad_norm": 1.4886174201965332, "learning_rate": 0.00014645806441668065, "loss": 0.6605054378509522, "step": 217280 }, { "epoch": 1.2916168839274569, "grad_norm": 1.5398008823394775, "learning_rate": 0.00014645237316614695, "loss": 0.616975975036621, "step": 217290 }, { "epoch": 1.2916763260041253, "grad_norm": 1.6808933019638062, "learning_rate": 0.00014644668174123703, "loss": 0.5899924278259278, "step": 217300 }, { "epoch": 1.2917357680807937, "grad_norm": 1.3194433450698853, "learning_rate": 0.00014644099014197813, "loss": 0.5892964363098144, "step": 217310 }, { "epoch": 1.2917952101574621, "grad_norm": 1.5122591257095337, "learning_rate": 0.00014643529836839744, "loss": 0.6453303337097168, "step": 217320 }, { "epoch": 1.2918546522341305, "grad_norm": 1.5011755228042603, "learning_rate": 0.00014642960642052217, "loss": 0.6059413909912109, "step": 217330 }, { "epoch": 1.291914094310799, "grad_norm": 1.681479573249817, "learning_rate": 0.0001464239142983796, "loss": 0.6220084190368652, "step": 217340 }, { "epoch": 1.2919735363874674, "grad_norm": 1.3736780881881714, "learning_rate": 0.00014641822200199686, "loss": 0.6297693252563477, "step": 217350 }, { "epoch": 1.2920329784641356, "grad_norm": 1.8410160541534424, "learning_rate": 0.00014641252953140127, "loss": 0.5668792724609375, "step": 217360 }, { "epoch": 1.292092420540804, "grad_norm": 1.8052232265472412, "learning_rate": 0.0001464068368866201, "loss": 0.6628805160522461, "step": 217370 }, { "epoch": 1.2921518626174724, "grad_norm": 1.5856451988220215, "learning_rate": 0.00014640114406768047, "loss": 0.5706346035003662, "step": 217380 }, { "epoch": 1.2922113046941408, "grad_norm": 1.4227840900421143, "learning_rate": 0.00014639545107460967, "loss": 0.5787757873535156, "step": 217390 }, { "epoch": 1.2922707467708092, "grad_norm": 1.6157928705215454, "learning_rate": 0.00014638975790743492, "loss": 0.6217605590820312, "step": 217400 }, { "epoch": 1.2923301888474776, "grad_norm": 1.4575252532958984, "learning_rate": 0.00014638406456618345, "loss": 0.6027572154998779, "step": 217410 }, { "epoch": 1.292389630924146, "grad_norm": 1.575880765914917, "learning_rate": 0.00014637837105088252, "loss": 0.5870875358581543, "step": 217420 }, { "epoch": 1.2924490730008142, "grad_norm": 1.9014906883239746, "learning_rate": 0.00014637267736155934, "loss": 0.6438440799713134, "step": 217430 }, { "epoch": 1.2925085150774827, "grad_norm": 1.6018489599227905, "learning_rate": 0.0001463669834982412, "loss": 0.6216497421264648, "step": 217440 }, { "epoch": 1.292567957154151, "grad_norm": 2.1086292266845703, "learning_rate": 0.00014636128946095525, "loss": 0.5778156757354737, "step": 217450 }, { "epoch": 1.2926273992308195, "grad_norm": 1.4046339988708496, "learning_rate": 0.0001463555952497288, "loss": 0.5511081695556641, "step": 217460 }, { "epoch": 1.292686841307488, "grad_norm": 1.4966368675231934, "learning_rate": 0.00014634990086458905, "loss": 0.6110823154449463, "step": 217470 }, { "epoch": 1.2927462833841563, "grad_norm": 1.4982491731643677, "learning_rate": 0.00014634420630556326, "loss": 0.5945671081542969, "step": 217480 }, { "epoch": 1.2928057254608247, "grad_norm": 1.3538869619369507, "learning_rate": 0.00014633851157267865, "loss": 0.6161860942840576, "step": 217490 }, { "epoch": 1.2928651675374931, "grad_norm": 1.3784774541854858, "learning_rate": 0.0001463328166659625, "loss": 0.5947323799133301, "step": 217500 }, { "epoch": 1.2929246096141616, "grad_norm": 1.4535810947418213, "learning_rate": 0.00014632712158544202, "loss": 0.5872166633605957, "step": 217510 }, { "epoch": 1.29298405169083, "grad_norm": 1.6470104455947876, "learning_rate": 0.00014632142633114444, "loss": 0.6264995574951172, "step": 217520 }, { "epoch": 1.2930434937674984, "grad_norm": 1.2669463157653809, "learning_rate": 0.00014631573090309708, "loss": 0.5967132091522217, "step": 217530 }, { "epoch": 1.2931029358441666, "grad_norm": 1.4393647909164429, "learning_rate": 0.00014631003530132707, "loss": 0.5716400146484375, "step": 217540 }, { "epoch": 1.293162377920835, "grad_norm": 1.4449318647384644, "learning_rate": 0.00014630433952586173, "loss": 0.6010860443115235, "step": 217550 }, { "epoch": 1.2932218199975034, "grad_norm": 1.6711620092391968, "learning_rate": 0.00014629864357672834, "loss": 0.6597946166992188, "step": 217560 }, { "epoch": 1.2932812620741718, "grad_norm": 1.6861116886138916, "learning_rate": 0.00014629294745395407, "loss": 0.653781795501709, "step": 217570 }, { "epoch": 1.2933407041508402, "grad_norm": 1.6801632642745972, "learning_rate": 0.0001462872511575662, "loss": 0.5730270862579345, "step": 217580 }, { "epoch": 1.2934001462275087, "grad_norm": 1.683618426322937, "learning_rate": 0.00014628155468759198, "loss": 0.6272659301757812, "step": 217590 }, { "epoch": 1.293459588304177, "grad_norm": 1.3594944477081299, "learning_rate": 0.00014627585804405862, "loss": 0.6383153915405273, "step": 217600 }, { "epoch": 1.2935190303808453, "grad_norm": 1.4219709634780884, "learning_rate": 0.00014627016122699347, "loss": 0.5414529800415039, "step": 217610 }, { "epoch": 1.2935784724575137, "grad_norm": 1.4049832820892334, "learning_rate": 0.0001462644642364237, "loss": 0.5761216640472412, "step": 217620 }, { "epoch": 1.293637914534182, "grad_norm": 1.5817103385925293, "learning_rate": 0.00014625876707237659, "loss": 0.6480906963348388, "step": 217630 }, { "epoch": 1.2936973566108505, "grad_norm": 1.3105489015579224, "learning_rate": 0.00014625306973487938, "loss": 0.5864452362060547, "step": 217640 }, { "epoch": 1.293756798687519, "grad_norm": 1.6526474952697754, "learning_rate": 0.00014624737222395932, "loss": 0.5809425354003906, "step": 217650 }, { "epoch": 1.2938162407641873, "grad_norm": 1.589856743812561, "learning_rate": 0.00014624167453964373, "loss": 0.6221150398254395, "step": 217660 }, { "epoch": 1.2938756828408557, "grad_norm": 1.5511723756790161, "learning_rate": 0.00014623597668195974, "loss": 0.5882654190063477, "step": 217670 }, { "epoch": 1.2939351249175242, "grad_norm": 1.6976854801177979, "learning_rate": 0.00014623027865093475, "loss": 0.619490385055542, "step": 217680 }, { "epoch": 1.2939945669941926, "grad_norm": 1.3497860431671143, "learning_rate": 0.0001462245804465959, "loss": 0.5627034664154053, "step": 217690 }, { "epoch": 1.294054009070861, "grad_norm": 1.7381047010421753, "learning_rate": 0.0001462188820689705, "loss": 0.5614454269409179, "step": 217700 }, { "epoch": 1.2941134511475294, "grad_norm": 1.430953025817871, "learning_rate": 0.0001462131835180858, "loss": 0.6710018634796142, "step": 217710 }, { "epoch": 1.2941728932241978, "grad_norm": 1.4241365194320679, "learning_rate": 0.00014620748479396908, "loss": 0.5917775154113769, "step": 217720 }, { "epoch": 1.294232335300866, "grad_norm": 1.5448086261749268, "learning_rate": 0.00014620178589664758, "loss": 0.6469382286071778, "step": 217730 }, { "epoch": 1.2942917773775344, "grad_norm": 1.3623548746109009, "learning_rate": 0.00014619608682614861, "loss": 0.6106255531311036, "step": 217740 }, { "epoch": 1.2943512194542028, "grad_norm": 1.145479679107666, "learning_rate": 0.0001461903875824993, "loss": 0.5625877857208252, "step": 217750 }, { "epoch": 1.2944106615308713, "grad_norm": 1.2855324745178223, "learning_rate": 0.00014618468816572706, "loss": 0.5914735317230224, "step": 217760 }, { "epoch": 1.2944701036075397, "grad_norm": 1.4155079126358032, "learning_rate": 0.0001461789885758591, "loss": 0.6297239303588867, "step": 217770 }, { "epoch": 1.294529545684208, "grad_norm": 1.2685904502868652, "learning_rate": 0.00014617328881292267, "loss": 0.5848818778991699, "step": 217780 }, { "epoch": 1.2945889877608763, "grad_norm": 1.5799460411071777, "learning_rate": 0.00014616758887694504, "loss": 0.6687936782836914, "step": 217790 }, { "epoch": 1.2946484298375447, "grad_norm": 1.3701459169387817, "learning_rate": 0.0001461618887679535, "loss": 0.5811484336853028, "step": 217800 }, { "epoch": 1.294707871914213, "grad_norm": 1.7225474119186401, "learning_rate": 0.0001461561884859753, "loss": 0.6958086013793945, "step": 217810 }, { "epoch": 1.2947673139908815, "grad_norm": 1.5193877220153809, "learning_rate": 0.00014615048803103768, "loss": 0.5769178390502929, "step": 217820 }, { "epoch": 1.29482675606755, "grad_norm": 1.4538887739181519, "learning_rate": 0.000146144787403168, "loss": 0.6301408767700195, "step": 217830 }, { "epoch": 1.2948861981442183, "grad_norm": 1.157718300819397, "learning_rate": 0.0001461390866023934, "loss": 0.5126080513000488, "step": 217840 }, { "epoch": 1.2949456402208868, "grad_norm": 1.9105901718139648, "learning_rate": 0.00014613338562874127, "loss": 0.6060422897338867, "step": 217850 }, { "epoch": 1.2950050822975552, "grad_norm": 1.5788078308105469, "learning_rate": 0.00014612768448223884, "loss": 0.5543356895446777, "step": 217860 }, { "epoch": 1.2950645243742236, "grad_norm": 1.259386658668518, "learning_rate": 0.0001461219831629133, "loss": 0.6293331623077393, "step": 217870 }, { "epoch": 1.295123966450892, "grad_norm": 1.5697866678237915, "learning_rate": 0.00014611628167079209, "loss": 0.6521455764770507, "step": 217880 }, { "epoch": 1.2951834085275604, "grad_norm": 1.4683403968811035, "learning_rate": 0.00014611058000590235, "loss": 0.5924197673797608, "step": 217890 }, { "epoch": 1.2952428506042288, "grad_norm": 1.7145904302597046, "learning_rate": 0.00014610487816827137, "loss": 0.6372697830200196, "step": 217900 }, { "epoch": 1.295302292680897, "grad_norm": 1.5516220331192017, "learning_rate": 0.00014609917615792647, "loss": 0.5933416366577149, "step": 217910 }, { "epoch": 1.2953617347575654, "grad_norm": 1.2713605165481567, "learning_rate": 0.00014609347397489495, "loss": 0.6214349746704102, "step": 217920 }, { "epoch": 1.2954211768342339, "grad_norm": 1.605319857597351, "learning_rate": 0.00014608777161920398, "loss": 0.6105246543884277, "step": 217930 }, { "epoch": 1.2954806189109023, "grad_norm": 1.4499820470809937, "learning_rate": 0.00014608206909088095, "loss": 0.6734339714050293, "step": 217940 }, { "epoch": 1.2955400609875707, "grad_norm": 2.0187299251556396, "learning_rate": 0.0001460763663899531, "loss": 0.5590703010559082, "step": 217950 }, { "epoch": 1.295599503064239, "grad_norm": 1.288161277770996, "learning_rate": 0.00014607066351644767, "loss": 0.6400480270385742, "step": 217960 }, { "epoch": 1.2956589451409075, "grad_norm": 1.4342232942581177, "learning_rate": 0.00014606496047039197, "loss": 0.6257367134094238, "step": 217970 }, { "epoch": 1.2957183872175757, "grad_norm": 1.7744297981262207, "learning_rate": 0.0001460592572518133, "loss": 0.617980670928955, "step": 217980 }, { "epoch": 1.2957778292942441, "grad_norm": 1.5307610034942627, "learning_rate": 0.00014605355386073892, "loss": 0.6021507740020752, "step": 217990 }, { "epoch": 1.2958372713709125, "grad_norm": 1.2001034021377563, "learning_rate": 0.00014604785029719613, "loss": 0.56990966796875, "step": 218000 }, { "epoch": 1.295896713447581, "grad_norm": 1.4543150663375854, "learning_rate": 0.00014604214656121223, "loss": 0.6257863998413086, "step": 218010 }, { "epoch": 1.2959561555242494, "grad_norm": 1.712979793548584, "learning_rate": 0.00014603644265281446, "loss": 0.5961787223815918, "step": 218020 }, { "epoch": 1.2960155976009178, "grad_norm": 1.3464574813842773, "learning_rate": 0.0001460307385720301, "loss": 0.6395250797271729, "step": 218030 }, { "epoch": 1.2960750396775862, "grad_norm": 1.6377301216125488, "learning_rate": 0.0001460250343188865, "loss": 0.6012425422668457, "step": 218040 }, { "epoch": 1.2961344817542546, "grad_norm": 1.4550946950912476, "learning_rate": 0.00014601932989341087, "loss": 0.6332385063171386, "step": 218050 }, { "epoch": 1.296193923830923, "grad_norm": 1.4556512832641602, "learning_rate": 0.00014601362529563055, "loss": 0.5877266883850097, "step": 218060 }, { "epoch": 1.2962533659075914, "grad_norm": 1.9701125621795654, "learning_rate": 0.00014600792052557284, "loss": 0.6033233642578125, "step": 218070 }, { "epoch": 1.2963128079842599, "grad_norm": 1.2800350189208984, "learning_rate": 0.000146002215583265, "loss": 0.5324233055114747, "step": 218080 }, { "epoch": 1.2963722500609283, "grad_norm": 1.4866901636123657, "learning_rate": 0.0001459965104687343, "loss": 0.5827528953552246, "step": 218090 }, { "epoch": 1.2964316921375965, "grad_norm": 1.6811623573303223, "learning_rate": 0.00014599080518200804, "loss": 0.5582233905792237, "step": 218100 }, { "epoch": 1.2964911342142649, "grad_norm": 1.6996055841445923, "learning_rate": 0.0001459850997231136, "loss": 0.6370420455932617, "step": 218110 }, { "epoch": 1.2965505762909333, "grad_norm": 1.9481345415115356, "learning_rate": 0.00014597939409207816, "loss": 0.6905586242675781, "step": 218120 }, { "epoch": 1.2966100183676017, "grad_norm": 1.607841968536377, "learning_rate": 0.00014597368828892906, "loss": 0.6069488525390625, "step": 218130 }, { "epoch": 1.2966694604442701, "grad_norm": 1.477409839630127, "learning_rate": 0.0001459679823136936, "loss": 0.5561923503875732, "step": 218140 }, { "epoch": 1.2967289025209385, "grad_norm": 1.2889280319213867, "learning_rate": 0.00014596227616639907, "loss": 0.6510483741760253, "step": 218150 }, { "epoch": 1.2967883445976067, "grad_norm": 1.4318252801895142, "learning_rate": 0.00014595656984707272, "loss": 0.6359083175659179, "step": 218160 }, { "epoch": 1.2968477866742751, "grad_norm": 1.6481834650039673, "learning_rate": 0.00014595086335574198, "loss": 0.6232229709625244, "step": 218170 }, { "epoch": 1.2969072287509436, "grad_norm": 1.3867608308792114, "learning_rate": 0.00014594515669243396, "loss": 0.64598708152771, "step": 218180 }, { "epoch": 1.296966670827612, "grad_norm": 1.3407847881317139, "learning_rate": 0.0001459394498571761, "loss": 0.5949177265167236, "step": 218190 }, { "epoch": 1.2970261129042804, "grad_norm": 1.547865629196167, "learning_rate": 0.00014593374284999568, "loss": 0.6411896705627441, "step": 218200 }, { "epoch": 1.2970855549809488, "grad_norm": 1.3976833820343018, "learning_rate": 0.00014592803567091994, "loss": 0.5889948844909668, "step": 218210 }, { "epoch": 1.2971449970576172, "grad_norm": 1.6695531606674194, "learning_rate": 0.00014592232831997626, "loss": 0.5694854736328125, "step": 218220 }, { "epoch": 1.2972044391342856, "grad_norm": 2.0916993618011475, "learning_rate": 0.00014591662079719187, "loss": 0.6548600196838379, "step": 218230 }, { "epoch": 1.297263881210954, "grad_norm": 1.55294668674469, "learning_rate": 0.0001459109131025941, "loss": 0.5656808376312256, "step": 218240 }, { "epoch": 1.2973233232876225, "grad_norm": 1.420166015625, "learning_rate": 0.00014590520523621026, "loss": 0.6223118782043457, "step": 218250 }, { "epoch": 1.2973827653642909, "grad_norm": 1.797384262084961, "learning_rate": 0.00014589949719806766, "loss": 0.6146769523620605, "step": 218260 }, { "epoch": 1.2974422074409593, "grad_norm": 1.5346086025238037, "learning_rate": 0.0001458937889881936, "loss": 0.6190624237060547, "step": 218270 }, { "epoch": 1.2975016495176275, "grad_norm": 1.5559662580490112, "learning_rate": 0.00014588808060661537, "loss": 0.6226305484771728, "step": 218280 }, { "epoch": 1.297561091594296, "grad_norm": 1.322855830192566, "learning_rate": 0.0001458823720533603, "loss": 0.6031591415405273, "step": 218290 }, { "epoch": 1.2976205336709643, "grad_norm": 1.5612821578979492, "learning_rate": 0.00014587666332845572, "loss": 0.6300399780273438, "step": 218300 }, { "epoch": 1.2976799757476327, "grad_norm": 1.6923656463623047, "learning_rate": 0.00014587095443192885, "loss": 0.6336729049682617, "step": 218310 }, { "epoch": 1.2977394178243011, "grad_norm": 1.4986985921859741, "learning_rate": 0.00014586524536380709, "loss": 0.5686934471130372, "step": 218320 }, { "epoch": 1.2977988599009695, "grad_norm": 1.4890720844268799, "learning_rate": 0.0001458595361241177, "loss": 0.6269856452941894, "step": 218330 }, { "epoch": 1.297858301977638, "grad_norm": 1.8150200843811035, "learning_rate": 0.00014585382671288802, "loss": 0.6260805130004883, "step": 218340 }, { "epoch": 1.2979177440543062, "grad_norm": 1.71206796169281, "learning_rate": 0.00014584811713014534, "loss": 0.6398538589477539, "step": 218350 }, { "epoch": 1.2979771861309746, "grad_norm": 1.3537514209747314, "learning_rate": 0.00014584240737591702, "loss": 0.6026294708251954, "step": 218360 }, { "epoch": 1.298036628207643, "grad_norm": 1.6449676752090454, "learning_rate": 0.00014583669745023026, "loss": 0.5827542304992676, "step": 218370 }, { "epoch": 1.2980960702843114, "grad_norm": 1.2956870794296265, "learning_rate": 0.00014583098735311252, "loss": 0.5908718109130859, "step": 218380 }, { "epoch": 1.2981555123609798, "grad_norm": 1.765418291091919, "learning_rate": 0.00014582527708459104, "loss": 0.6622788429260253, "step": 218390 }, { "epoch": 1.2982149544376482, "grad_norm": 1.9261279106140137, "learning_rate": 0.0001458195666446931, "loss": 0.6410016059875489, "step": 218400 }, { "epoch": 1.2982743965143166, "grad_norm": 1.2502853870391846, "learning_rate": 0.0001458138560334461, "loss": 0.6071496486663819, "step": 218410 }, { "epoch": 1.298333838590985, "grad_norm": 2.069939613342285, "learning_rate": 0.0001458081452508773, "loss": 0.6146230697631836, "step": 218420 }, { "epoch": 1.2983932806676535, "grad_norm": 1.6020686626434326, "learning_rate": 0.00014580243429701407, "loss": 0.5844295501708985, "step": 218430 }, { "epoch": 1.2984527227443219, "grad_norm": 1.49626624584198, "learning_rate": 0.00014579672317188363, "loss": 0.5541390419006348, "step": 218440 }, { "epoch": 1.2985121648209903, "grad_norm": 1.8047782182693481, "learning_rate": 0.00014579101187551342, "loss": 0.6466696262359619, "step": 218450 }, { "epoch": 1.2985716068976587, "grad_norm": 1.4511749744415283, "learning_rate": 0.00014578530040793068, "loss": 0.5904049873352051, "step": 218460 }, { "epoch": 1.298631048974327, "grad_norm": 1.5986015796661377, "learning_rate": 0.00014577958876916275, "loss": 0.6280147552490234, "step": 218470 }, { "epoch": 1.2986904910509953, "grad_norm": 1.2534183263778687, "learning_rate": 0.000145773876959237, "loss": 0.6315544128417969, "step": 218480 }, { "epoch": 1.2987499331276637, "grad_norm": 1.8446247577667236, "learning_rate": 0.00014576816497818064, "loss": 0.5356677532196045, "step": 218490 }, { "epoch": 1.2988093752043322, "grad_norm": 1.3695240020751953, "learning_rate": 0.00014576245282602114, "loss": 0.611391258239746, "step": 218500 }, { "epoch": 1.2988688172810006, "grad_norm": 2.1082236766815186, "learning_rate": 0.00014575674050278575, "loss": 0.6214023113250733, "step": 218510 }, { "epoch": 1.298928259357669, "grad_norm": 1.5456631183624268, "learning_rate": 0.00014575102800850172, "loss": 0.6098265171051025, "step": 218520 }, { "epoch": 1.2989877014343372, "grad_norm": 1.5139542818069458, "learning_rate": 0.00014574531534319654, "loss": 0.5663662433624268, "step": 218530 }, { "epoch": 1.2990471435110056, "grad_norm": 1.5395737886428833, "learning_rate": 0.0001457396025068974, "loss": 0.61741042137146, "step": 218540 }, { "epoch": 1.299106585587674, "grad_norm": 1.3117444515228271, "learning_rate": 0.00014573388949963172, "loss": 0.5509978771209717, "step": 218550 }, { "epoch": 1.2991660276643424, "grad_norm": 1.333581566810608, "learning_rate": 0.00014572817632142678, "loss": 0.6350802421569824, "step": 218560 }, { "epoch": 1.2992254697410108, "grad_norm": 1.2803527116775513, "learning_rate": 0.00014572246297230992, "loss": 0.5769537925720215, "step": 218570 }, { "epoch": 1.2992849118176792, "grad_norm": 1.6931415796279907, "learning_rate": 0.00014571674945230845, "loss": 0.5865797996520996, "step": 218580 }, { "epoch": 1.2993443538943477, "grad_norm": 1.3662455081939697, "learning_rate": 0.00014571103576144977, "loss": 0.6249704360961914, "step": 218590 }, { "epoch": 1.299403795971016, "grad_norm": 1.2883766889572144, "learning_rate": 0.00014570532189976115, "loss": 0.5337318897247314, "step": 218600 }, { "epoch": 1.2994632380476845, "grad_norm": 1.3836321830749512, "learning_rate": 0.0001456996078672699, "loss": 0.6247172832489014, "step": 218610 }, { "epoch": 1.299522680124353, "grad_norm": 1.5666245222091675, "learning_rate": 0.0001456938936640034, "loss": 0.5873717308044434, "step": 218620 }, { "epoch": 1.2995821222010213, "grad_norm": 1.2861051559448242, "learning_rate": 0.00014568817928998902, "loss": 0.6172978401184082, "step": 218630 }, { "epoch": 1.2996415642776897, "grad_norm": 1.4975963830947876, "learning_rate": 0.00014568246474525403, "loss": 0.5754854202270507, "step": 218640 }, { "epoch": 1.299701006354358, "grad_norm": 1.6699856519699097, "learning_rate": 0.00014567675002982578, "loss": 0.5499225616455078, "step": 218650 }, { "epoch": 1.2997604484310263, "grad_norm": 1.9199419021606445, "learning_rate": 0.00014567103514373164, "loss": 0.5848625659942627, "step": 218660 }, { "epoch": 1.2998198905076948, "grad_norm": 1.4757388830184937, "learning_rate": 0.00014566532008699888, "loss": 0.5998457431793213, "step": 218670 }, { "epoch": 1.2998793325843632, "grad_norm": 1.6094341278076172, "learning_rate": 0.00014565960485965493, "loss": 0.590895414352417, "step": 218680 }, { "epoch": 1.2999387746610316, "grad_norm": 1.588127613067627, "learning_rate": 0.00014565388946172707, "loss": 0.6390145301818848, "step": 218690 }, { "epoch": 1.2999982167377, "grad_norm": 1.2470929622650146, "learning_rate": 0.00014564817389324265, "loss": 0.5919022560119629, "step": 218700 }, { "epoch": 1.3000576588143684, "grad_norm": 1.575120449066162, "learning_rate": 0.00014564245815422905, "loss": 0.6074933052062989, "step": 218710 }, { "epoch": 1.3001171008910366, "grad_norm": 1.3498363494873047, "learning_rate": 0.00014563674224471354, "loss": 0.6572528839111328, "step": 218720 }, { "epoch": 1.300176542967705, "grad_norm": 1.4542133808135986, "learning_rate": 0.00014563102616472348, "loss": 0.6052799224853516, "step": 218730 }, { "epoch": 1.3002359850443734, "grad_norm": 1.1892776489257812, "learning_rate": 0.00014562530991428627, "loss": 0.6439506530761718, "step": 218740 }, { "epoch": 1.3002954271210418, "grad_norm": 1.5504447221755981, "learning_rate": 0.00014561959349342922, "loss": 0.5450210571289062, "step": 218750 }, { "epoch": 1.3003548691977103, "grad_norm": 1.4681625366210938, "learning_rate": 0.00014561387690217964, "loss": 0.6193764686584473, "step": 218760 }, { "epoch": 1.3004143112743787, "grad_norm": 1.6450231075286865, "learning_rate": 0.00014560816014056496, "loss": 0.5808166980743408, "step": 218770 }, { "epoch": 1.300473753351047, "grad_norm": 1.4796767234802246, "learning_rate": 0.00014560244320861246, "loss": 0.6476630210876465, "step": 218780 }, { "epoch": 1.3005331954277155, "grad_norm": 2.0087485313415527, "learning_rate": 0.0001455967261063495, "loss": 0.5948598384857178, "step": 218790 }, { "epoch": 1.300592637504384, "grad_norm": 1.3409368991851807, "learning_rate": 0.00014559100883380346, "loss": 0.6237802982330323, "step": 218800 }, { "epoch": 1.3006520795810523, "grad_norm": 1.7228256464004517, "learning_rate": 0.00014558529139100166, "loss": 0.6352252006530762, "step": 218810 }, { "epoch": 1.3007115216577207, "grad_norm": 1.4266246557235718, "learning_rate": 0.00014557957377797143, "loss": 0.5947102069854736, "step": 218820 }, { "epoch": 1.3007709637343892, "grad_norm": 1.4691866636276245, "learning_rate": 0.00014557385599474015, "loss": 0.5716725349426269, "step": 218830 }, { "epoch": 1.3008304058110574, "grad_norm": 1.935142159461975, "learning_rate": 0.00014556813804133517, "loss": 0.6065209388732911, "step": 218840 }, { "epoch": 1.3008898478877258, "grad_norm": 1.6004630327224731, "learning_rate": 0.00014556241991778388, "loss": 0.6598265647888184, "step": 218850 }, { "epoch": 1.3009492899643942, "grad_norm": 2.1048262119293213, "learning_rate": 0.00014555670162411354, "loss": 0.6432194709777832, "step": 218860 }, { "epoch": 1.3010087320410626, "grad_norm": 1.9500312805175781, "learning_rate": 0.0001455509831603516, "loss": 0.7281645774841309, "step": 218870 }, { "epoch": 1.301068174117731, "grad_norm": 1.45481538772583, "learning_rate": 0.00014554526452652535, "loss": 0.6493740081787109, "step": 218880 }, { "epoch": 1.3011276161943994, "grad_norm": 1.3728371858596802, "learning_rate": 0.00014553954572266219, "loss": 0.5865883827209473, "step": 218890 }, { "epoch": 1.3011870582710676, "grad_norm": 1.5104897022247314, "learning_rate": 0.00014553382674878943, "loss": 0.6189825534820557, "step": 218900 }, { "epoch": 1.301246500347736, "grad_norm": 1.5247141122817993, "learning_rate": 0.0001455281076049345, "loss": 0.633624792098999, "step": 218910 }, { "epoch": 1.3013059424244044, "grad_norm": 1.6363316774368286, "learning_rate": 0.00014552238829112468, "loss": 0.6441738128662109, "step": 218920 }, { "epoch": 1.3013653845010729, "grad_norm": 1.6229947805404663, "learning_rate": 0.00014551666880738734, "loss": 0.5532080650329589, "step": 218930 }, { "epoch": 1.3014248265777413, "grad_norm": 1.6785274744033813, "learning_rate": 0.0001455109491537499, "loss": 0.6506823539733887, "step": 218940 }, { "epoch": 1.3014842686544097, "grad_norm": 1.1969281435012817, "learning_rate": 0.00014550522933023968, "loss": 0.6128724098205567, "step": 218950 }, { "epoch": 1.301543710731078, "grad_norm": 1.4423582553863525, "learning_rate": 0.00014549950933688403, "loss": 0.5930799007415771, "step": 218960 }, { "epoch": 1.3016031528077465, "grad_norm": 1.5574963092803955, "learning_rate": 0.00014549378917371036, "loss": 0.6483046531677246, "step": 218970 }, { "epoch": 1.301662594884415, "grad_norm": 1.9043362140655518, "learning_rate": 0.000145488068840746, "loss": 0.5865945816040039, "step": 218980 }, { "epoch": 1.3017220369610834, "grad_norm": 1.6649620532989502, "learning_rate": 0.0001454823483380183, "loss": 0.5609662055969238, "step": 218990 }, { "epoch": 1.3017814790377518, "grad_norm": 1.5250296592712402, "learning_rate": 0.00014547662766555464, "loss": 0.6035849094390869, "step": 219000 }, { "epoch": 1.3018409211144202, "grad_norm": 1.802200436592102, "learning_rate": 0.0001454709068233824, "loss": 0.5954711437225342, "step": 219010 }, { "epoch": 1.3019003631910884, "grad_norm": 1.296755313873291, "learning_rate": 0.0001454651858115289, "loss": 0.6026296138763427, "step": 219020 }, { "epoch": 1.3019598052677568, "grad_norm": 2.224700927734375, "learning_rate": 0.00014545946463002157, "loss": 0.5846888542175293, "step": 219030 }, { "epoch": 1.3020192473444252, "grad_norm": 1.8532241582870483, "learning_rate": 0.00014545374327888772, "loss": 0.6200480937957764, "step": 219040 }, { "epoch": 1.3020786894210936, "grad_norm": 1.6237359046936035, "learning_rate": 0.0001454480217581548, "loss": 0.6129711151123047, "step": 219050 }, { "epoch": 1.302138131497762, "grad_norm": 1.450558066368103, "learning_rate": 0.00014544230006785012, "loss": 0.5553431034088134, "step": 219060 }, { "epoch": 1.3021975735744304, "grad_norm": 1.6760146617889404, "learning_rate": 0.00014543657820800102, "loss": 0.6281925678253174, "step": 219070 }, { "epoch": 1.3022570156510989, "grad_norm": 1.2876312732696533, "learning_rate": 0.00014543085617863493, "loss": 0.6623175621032715, "step": 219080 }, { "epoch": 1.302316457727767, "grad_norm": 1.3516581058502197, "learning_rate": 0.0001454251339797792, "loss": 0.6716655731201172, "step": 219090 }, { "epoch": 1.3023758998044355, "grad_norm": 1.3408079147338867, "learning_rate": 0.0001454194116114612, "loss": 0.6169698715209961, "step": 219100 }, { "epoch": 1.3024353418811039, "grad_norm": 1.767431378364563, "learning_rate": 0.0001454136890737083, "loss": 0.5517908096313476, "step": 219110 }, { "epoch": 1.3024947839577723, "grad_norm": 1.480441927909851, "learning_rate": 0.00014540796636654794, "loss": 0.5900773048400879, "step": 219120 }, { "epoch": 1.3025542260344407, "grad_norm": 1.6546695232391357, "learning_rate": 0.0001454022434900074, "loss": 0.604986572265625, "step": 219130 }, { "epoch": 1.3026136681111091, "grad_norm": 1.8618156909942627, "learning_rate": 0.0001453965204441141, "loss": 0.6004269123077393, "step": 219140 }, { "epoch": 1.3026731101877775, "grad_norm": 1.5536959171295166, "learning_rate": 0.0001453907972288954, "loss": 0.6227256774902343, "step": 219150 }, { "epoch": 1.302732552264446, "grad_norm": 1.4829777479171753, "learning_rate": 0.0001453850738443787, "loss": 0.6112494468688965, "step": 219160 }, { "epoch": 1.3027919943411144, "grad_norm": 1.4904046058654785, "learning_rate": 0.00014537935029059138, "loss": 0.5327554702758789, "step": 219170 }, { "epoch": 1.3028514364177828, "grad_norm": 1.3880808353424072, "learning_rate": 0.00014537362656756085, "loss": 0.5757815361022949, "step": 219180 }, { "epoch": 1.3029108784944512, "grad_norm": 1.5582212209701538, "learning_rate": 0.00014536790267531438, "loss": 0.6260457038879395, "step": 219190 }, { "epoch": 1.3029703205711196, "grad_norm": 1.3818984031677246, "learning_rate": 0.00014536217861387947, "loss": 0.5792701721191407, "step": 219200 }, { "epoch": 1.3030297626477878, "grad_norm": 1.6337758302688599, "learning_rate": 0.00014535645438328344, "loss": 0.6264132499694824, "step": 219210 }, { "epoch": 1.3030892047244562, "grad_norm": 1.675747275352478, "learning_rate": 0.00014535072998355365, "loss": 0.5793209075927734, "step": 219220 }, { "epoch": 1.3031486468011246, "grad_norm": 1.7186036109924316, "learning_rate": 0.0001453450054147176, "loss": 0.523134183883667, "step": 219230 }, { "epoch": 1.303208088877793, "grad_norm": 1.6754134893417358, "learning_rate": 0.00014533928067680252, "loss": 0.6124326705932617, "step": 219240 }, { "epoch": 1.3032675309544615, "grad_norm": 1.1963614225387573, "learning_rate": 0.00014533355576983587, "loss": 0.5920494079589844, "step": 219250 }, { "epoch": 1.3033269730311299, "grad_norm": 1.5029706954956055, "learning_rate": 0.0001453278306938451, "loss": 0.614562702178955, "step": 219260 }, { "epoch": 1.303386415107798, "grad_norm": 1.383880615234375, "learning_rate": 0.00014532210544885747, "loss": 0.5846541404724122, "step": 219270 }, { "epoch": 1.3034458571844665, "grad_norm": 1.6177363395690918, "learning_rate": 0.00014531638003490048, "loss": 0.628179931640625, "step": 219280 }, { "epoch": 1.303505299261135, "grad_norm": 1.8574353456497192, "learning_rate": 0.00014531065445200144, "loss": 0.5541897773742676, "step": 219290 }, { "epoch": 1.3035647413378033, "grad_norm": 1.6212918758392334, "learning_rate": 0.00014530492870018776, "loss": 0.6299095153808594, "step": 219300 }, { "epoch": 1.3036241834144717, "grad_norm": 1.5575472116470337, "learning_rate": 0.00014529920277948688, "loss": 0.5729594230651855, "step": 219310 }, { "epoch": 1.3036836254911401, "grad_norm": 1.4812880754470825, "learning_rate": 0.0001452934766899261, "loss": 0.6139619827270508, "step": 219320 }, { "epoch": 1.3037430675678086, "grad_norm": 1.6435970067977905, "learning_rate": 0.00014528775043153288, "loss": 0.6041862010955811, "step": 219330 }, { "epoch": 1.303802509644477, "grad_norm": 2.0638389587402344, "learning_rate": 0.00014528202400433465, "loss": 0.6935090065002442, "step": 219340 }, { "epoch": 1.3038619517211454, "grad_norm": 1.4216619729995728, "learning_rate": 0.00014527629740835864, "loss": 0.6266722679138184, "step": 219350 }, { "epoch": 1.3039213937978138, "grad_norm": 1.7890193462371826, "learning_rate": 0.00014527057064363244, "loss": 0.6823628425598145, "step": 219360 }, { "epoch": 1.3039808358744822, "grad_norm": 1.7910676002502441, "learning_rate": 0.00014526484371018335, "loss": 0.6207494258880615, "step": 219370 }, { "epoch": 1.3040402779511506, "grad_norm": 1.7913322448730469, "learning_rate": 0.00014525911660803872, "loss": 0.6120360374450684, "step": 219380 }, { "epoch": 1.3040997200278188, "grad_norm": 1.5446254014968872, "learning_rate": 0.000145253389337226, "loss": 0.6908001899719238, "step": 219390 }, { "epoch": 1.3041591621044872, "grad_norm": 1.4784446954727173, "learning_rate": 0.00014524766189777266, "loss": 0.5823944091796875, "step": 219400 }, { "epoch": 1.3042186041811556, "grad_norm": 1.3539799451828003, "learning_rate": 0.00014524193428970596, "loss": 0.6248237133026123, "step": 219410 }, { "epoch": 1.304278046257824, "grad_norm": 1.7641828060150146, "learning_rate": 0.00014523620651305335, "loss": 0.5522274017333985, "step": 219420 }, { "epoch": 1.3043374883344925, "grad_norm": 1.6724976301193237, "learning_rate": 0.0001452304785678423, "loss": 0.6091235160827637, "step": 219430 }, { "epoch": 1.304396930411161, "grad_norm": 1.5372416973114014, "learning_rate": 0.00014522475045410013, "loss": 0.6280118942260742, "step": 219440 }, { "epoch": 1.3044563724878293, "grad_norm": 1.0925323963165283, "learning_rate": 0.00014521902217185428, "loss": 0.6170738220214844, "step": 219450 }, { "epoch": 1.3045158145644975, "grad_norm": 1.403371810913086, "learning_rate": 0.00014521329372113213, "loss": 0.6045519828796386, "step": 219460 }, { "epoch": 1.304575256641166, "grad_norm": 1.6665295362472534, "learning_rate": 0.00014520756510196108, "loss": 0.5988831520080566, "step": 219470 }, { "epoch": 1.3046346987178343, "grad_norm": 1.621782660484314, "learning_rate": 0.00014520183631436853, "loss": 0.6451942443847656, "step": 219480 }, { "epoch": 1.3046941407945027, "grad_norm": 1.2989153861999512, "learning_rate": 0.00014519610735838195, "loss": 0.5502265930175781, "step": 219490 }, { "epoch": 1.3047535828711712, "grad_norm": 1.574972152709961, "learning_rate": 0.00014519037823402864, "loss": 0.6319607257843017, "step": 219500 }, { "epoch": 1.3048130249478396, "grad_norm": 1.4733829498291016, "learning_rate": 0.00014518464894133608, "loss": 0.5578657150268554, "step": 219510 }, { "epoch": 1.304872467024508, "grad_norm": 1.4788166284561157, "learning_rate": 0.00014517891948033167, "loss": 0.6168973445892334, "step": 219520 }, { "epoch": 1.3049319091011764, "grad_norm": 1.7898753881454468, "learning_rate": 0.00014517318985104278, "loss": 0.5527868270874023, "step": 219530 }, { "epoch": 1.3049913511778448, "grad_norm": 1.6395437717437744, "learning_rate": 0.00014516746005349687, "loss": 0.5786373138427734, "step": 219540 }, { "epoch": 1.3050507932545132, "grad_norm": 1.5797643661499023, "learning_rate": 0.0001451617300877213, "loss": 0.6386851787567138, "step": 219550 }, { "epoch": 1.3051102353311816, "grad_norm": 1.4994162321090698, "learning_rate": 0.00014515599995374353, "loss": 0.64630126953125, "step": 219560 }, { "epoch": 1.3051696774078498, "grad_norm": 1.2956300973892212, "learning_rate": 0.00014515026965159094, "loss": 0.5927988052368164, "step": 219570 }, { "epoch": 1.3052291194845183, "grad_norm": 1.4023864269256592, "learning_rate": 0.00014514453918129091, "loss": 0.5703889846801757, "step": 219580 }, { "epoch": 1.3052885615611867, "grad_norm": 1.4946315288543701, "learning_rate": 0.00014513880854287095, "loss": 0.5923791408538819, "step": 219590 }, { "epoch": 1.305348003637855, "grad_norm": 1.3499023914337158, "learning_rate": 0.00014513307773635835, "loss": 0.6283955574035645, "step": 219600 }, { "epoch": 1.3054074457145235, "grad_norm": 1.3602296113967896, "learning_rate": 0.00014512734676178063, "loss": 0.5898396492004394, "step": 219610 }, { "epoch": 1.305466887791192, "grad_norm": 1.6773854494094849, "learning_rate": 0.00014512161561916516, "loss": 0.5887233734130859, "step": 219620 }, { "epoch": 1.3055263298678603, "grad_norm": 1.574088454246521, "learning_rate": 0.00014511588430853934, "loss": 0.6005114078521728, "step": 219630 }, { "epoch": 1.3055857719445285, "grad_norm": 1.078238606452942, "learning_rate": 0.00014511015282993065, "loss": 0.6466724872589111, "step": 219640 }, { "epoch": 1.305645214021197, "grad_norm": 0.8705070614814758, "learning_rate": 0.00014510442118336643, "loss": 0.6527656555175781, "step": 219650 }, { "epoch": 1.3057046560978653, "grad_norm": 1.5343143939971924, "learning_rate": 0.00014509868936887413, "loss": 0.5531668663024902, "step": 219660 }, { "epoch": 1.3057640981745338, "grad_norm": 1.9470562934875488, "learning_rate": 0.0001450929573864812, "loss": 0.608116340637207, "step": 219670 }, { "epoch": 1.3058235402512022, "grad_norm": 1.760393500328064, "learning_rate": 0.00014508722523621498, "loss": 0.5776515007019043, "step": 219680 }, { "epoch": 1.3058829823278706, "grad_norm": 1.6265252828598022, "learning_rate": 0.00014508149291810296, "loss": 0.5779866218566895, "step": 219690 }, { "epoch": 1.305942424404539, "grad_norm": 1.3530182838439941, "learning_rate": 0.00014507576043217254, "loss": 0.647855567932129, "step": 219700 }, { "epoch": 1.3060018664812074, "grad_norm": 1.323283076286316, "learning_rate": 0.00014507002777845116, "loss": 0.5849995613098145, "step": 219710 }, { "epoch": 1.3060613085578758, "grad_norm": 1.3410440683364868, "learning_rate": 0.00014506429495696622, "loss": 0.6237655639648437, "step": 219720 }, { "epoch": 1.3061207506345442, "grad_norm": 1.966689109802246, "learning_rate": 0.00014505856196774517, "loss": 0.6928153991699219, "step": 219730 }, { "epoch": 1.3061801927112127, "grad_norm": 1.4520105123519897, "learning_rate": 0.00014505282881081542, "loss": 0.6108800888061523, "step": 219740 }, { "epoch": 1.306239634787881, "grad_norm": 1.5181884765625, "learning_rate": 0.00014504709548620435, "loss": 0.6340104103088379, "step": 219750 }, { "epoch": 1.3062990768645493, "grad_norm": 1.501238465309143, "learning_rate": 0.00014504136199393946, "loss": 0.6403039932250977, "step": 219760 }, { "epoch": 1.3063585189412177, "grad_norm": 1.6611177921295166, "learning_rate": 0.00014503562833404813, "loss": 0.6395183563232422, "step": 219770 }, { "epoch": 1.306417961017886, "grad_norm": 1.595870018005371, "learning_rate": 0.0001450298945065578, "loss": 0.6062677383422852, "step": 219780 }, { "epoch": 1.3064774030945545, "grad_norm": 1.5389376878738403, "learning_rate": 0.0001450241605114959, "loss": 0.6302576541900635, "step": 219790 }, { "epoch": 1.306536845171223, "grad_norm": 1.5373756885528564, "learning_rate": 0.00014501842634888988, "loss": 0.632907772064209, "step": 219800 }, { "epoch": 1.3065962872478913, "grad_norm": 1.632576823234558, "learning_rate": 0.00014501269201876716, "loss": 0.5997723579406739, "step": 219810 }, { "epoch": 1.3066557293245598, "grad_norm": 1.851375937461853, "learning_rate": 0.00014500695752115515, "loss": 0.6278841495513916, "step": 219820 }, { "epoch": 1.306715171401228, "grad_norm": 1.5973339080810547, "learning_rate": 0.0001450012228560813, "loss": 0.5661314964294434, "step": 219830 }, { "epoch": 1.3067746134778964, "grad_norm": 1.4227713346481323, "learning_rate": 0.000144995488023573, "loss": 0.5391221046447754, "step": 219840 }, { "epoch": 1.3068340555545648, "grad_norm": 1.6285605430603027, "learning_rate": 0.0001449897530236578, "loss": 0.6090919971466064, "step": 219850 }, { "epoch": 1.3068934976312332, "grad_norm": 1.2792810201644897, "learning_rate": 0.000144984017856363, "loss": 0.5642889976501465, "step": 219860 }, { "epoch": 1.3069529397079016, "grad_norm": 1.6407884359359741, "learning_rate": 0.00014497828252171613, "loss": 0.6271281719207764, "step": 219870 }, { "epoch": 1.30701238178457, "grad_norm": 2.2778995037078857, "learning_rate": 0.00014497254701974454, "loss": 0.5852606773376465, "step": 219880 }, { "epoch": 1.3070718238612384, "grad_norm": 1.4240608215332031, "learning_rate": 0.00014496681135047574, "loss": 0.6165999889373779, "step": 219890 }, { "epoch": 1.3071312659379068, "grad_norm": 1.3413387537002563, "learning_rate": 0.00014496107551393713, "loss": 0.5805205345153809, "step": 219900 }, { "epoch": 1.3071907080145753, "grad_norm": 1.4383739233016968, "learning_rate": 0.00014495533951015618, "loss": 0.6584881782531739, "step": 219910 }, { "epoch": 1.3072501500912437, "grad_norm": 1.6359330415725708, "learning_rate": 0.0001449496033391603, "loss": 0.628791618347168, "step": 219920 }, { "epoch": 1.307309592167912, "grad_norm": 1.833998203277588, "learning_rate": 0.00014494386700097692, "loss": 0.662978982925415, "step": 219930 }, { "epoch": 1.3073690342445803, "grad_norm": 1.4579871892929077, "learning_rate": 0.00014493813049563353, "loss": 0.6210057735443115, "step": 219940 }, { "epoch": 1.3074284763212487, "grad_norm": 1.5176602602005005, "learning_rate": 0.00014493239382315753, "loss": 0.6326972961425781, "step": 219950 }, { "epoch": 1.3074879183979171, "grad_norm": 1.58334219455719, "learning_rate": 0.00014492665698357638, "loss": 0.6578145027160645, "step": 219960 }, { "epoch": 1.3075473604745855, "grad_norm": 1.7585641145706177, "learning_rate": 0.00014492091997691747, "loss": 0.5957672119140625, "step": 219970 }, { "epoch": 1.307606802551254, "grad_norm": 1.6553843021392822, "learning_rate": 0.00014491518280320838, "loss": 0.598992919921875, "step": 219980 }, { "epoch": 1.3076662446279224, "grad_norm": 1.6361395120620728, "learning_rate": 0.0001449094454624764, "loss": 0.5609846591949463, "step": 219990 }, { "epoch": 1.3077256867045908, "grad_norm": 1.1180453300476074, "learning_rate": 0.00014490370795474907, "loss": 0.5847768783569336, "step": 220000 }, { "epoch": 1.307785128781259, "grad_norm": 1.6083565950393677, "learning_rate": 0.0001448979702800538, "loss": 0.6218876838684082, "step": 220010 }, { "epoch": 1.3078445708579274, "grad_norm": 1.529518485069275, "learning_rate": 0.00014489223243841802, "loss": 0.5939467906951904, "step": 220020 }, { "epoch": 1.3079040129345958, "grad_norm": 1.8344639539718628, "learning_rate": 0.00014488649442986925, "loss": 0.6131053924560547, "step": 220030 }, { "epoch": 1.3079634550112642, "grad_norm": 1.529850721359253, "learning_rate": 0.00014488075625443484, "loss": 0.6165009021759034, "step": 220040 }, { "epoch": 1.3080228970879326, "grad_norm": 1.517362356185913, "learning_rate": 0.00014487501791214235, "loss": 0.668916130065918, "step": 220050 }, { "epoch": 1.308082339164601, "grad_norm": 1.479145884513855, "learning_rate": 0.00014486927940301914, "loss": 0.5492528915405274, "step": 220060 }, { "epoch": 1.3081417812412695, "grad_norm": 2.015023708343506, "learning_rate": 0.0001448635407270927, "loss": 0.57720947265625, "step": 220070 }, { "epoch": 1.3082012233179379, "grad_norm": 2.084383487701416, "learning_rate": 0.00014485780188439043, "loss": 0.6688260078430176, "step": 220080 }, { "epoch": 1.3082606653946063, "grad_norm": 1.6708265542984009, "learning_rate": 0.00014485206287493988, "loss": 0.6382377624511719, "step": 220090 }, { "epoch": 1.3083201074712747, "grad_norm": 1.3698275089263916, "learning_rate": 0.00014484632369876843, "loss": 0.5748899459838868, "step": 220100 }, { "epoch": 1.308379549547943, "grad_norm": 1.7801545858383179, "learning_rate": 0.00014484058435590354, "loss": 0.6274212837219239, "step": 220110 }, { "epoch": 1.3084389916246115, "grad_norm": 1.5037310123443604, "learning_rate": 0.0001448348448463727, "loss": 0.6139787673950196, "step": 220120 }, { "epoch": 1.3084984337012797, "grad_norm": 1.2910963296890259, "learning_rate": 0.00014482910517020335, "loss": 0.5748879432678222, "step": 220130 }, { "epoch": 1.3085578757779481, "grad_norm": 1.2611833810806274, "learning_rate": 0.00014482336532742297, "loss": 0.6189338684082031, "step": 220140 }, { "epoch": 1.3086173178546165, "grad_norm": 1.824845314025879, "learning_rate": 0.00014481762531805894, "loss": 0.6353356838226318, "step": 220150 }, { "epoch": 1.308676759931285, "grad_norm": 1.4185631275177002, "learning_rate": 0.0001448118851421388, "loss": 0.6398560523986816, "step": 220160 }, { "epoch": 1.3087362020079534, "grad_norm": 2.142159938812256, "learning_rate": 0.00014480614479968996, "loss": 0.6381564140319824, "step": 220170 }, { "epoch": 1.3087956440846218, "grad_norm": 1.4870065450668335, "learning_rate": 0.0001448004042907399, "loss": 0.6046545028686523, "step": 220180 }, { "epoch": 1.3088550861612902, "grad_norm": 1.6110066175460815, "learning_rate": 0.00014479466361531608, "loss": 0.5791493415832519, "step": 220190 }, { "epoch": 1.3089145282379584, "grad_norm": 1.6383236646652222, "learning_rate": 0.00014478892277344598, "loss": 0.6289133071899414, "step": 220200 }, { "epoch": 1.3089739703146268, "grad_norm": 1.809305191040039, "learning_rate": 0.00014478318176515702, "loss": 0.6126949310302734, "step": 220210 }, { "epoch": 1.3090334123912952, "grad_norm": 1.652169108390808, "learning_rate": 0.00014477744059047669, "loss": 0.6058585166931152, "step": 220220 }, { "epoch": 1.3090928544679636, "grad_norm": 1.786471962928772, "learning_rate": 0.00014477169924943247, "loss": 0.6433918952941895, "step": 220230 }, { "epoch": 1.309152296544632, "grad_norm": 1.6129893064498901, "learning_rate": 0.0001447659577420518, "loss": 0.6307197570800781, "step": 220240 }, { "epoch": 1.3092117386213005, "grad_norm": 1.3944480419158936, "learning_rate": 0.0001447602160683621, "loss": 0.626563835144043, "step": 220250 }, { "epoch": 1.3092711806979689, "grad_norm": 1.3521860837936401, "learning_rate": 0.00014475447422839094, "loss": 0.5932497024536133, "step": 220260 }, { "epoch": 1.3093306227746373, "grad_norm": 1.417351484298706, "learning_rate": 0.00014474873222216573, "loss": 0.5837088584899902, "step": 220270 }, { "epoch": 1.3093900648513057, "grad_norm": 1.3122507333755493, "learning_rate": 0.0001447429900497139, "loss": 0.5995632171630859, "step": 220280 }, { "epoch": 1.3094495069279741, "grad_norm": 1.6061503887176514, "learning_rate": 0.00014473724771106304, "loss": 0.6385838508605957, "step": 220290 }, { "epoch": 1.3095089490046425, "grad_norm": 1.6658865213394165, "learning_rate": 0.00014473150520624044, "loss": 0.608268928527832, "step": 220300 }, { "epoch": 1.3095683910813107, "grad_norm": 1.733615517616272, "learning_rate": 0.00014472576253527373, "loss": 0.6057346820831299, "step": 220310 }, { "epoch": 1.3096278331579791, "grad_norm": 1.5668070316314697, "learning_rate": 0.0001447200196981903, "loss": 0.5889211654663086, "step": 220320 }, { "epoch": 1.3096872752346476, "grad_norm": 1.6313371658325195, "learning_rate": 0.00014471427669501764, "loss": 0.5758028984069824, "step": 220330 }, { "epoch": 1.309746717311316, "grad_norm": 1.9162887334823608, "learning_rate": 0.00014470853352578324, "loss": 0.6117255210876464, "step": 220340 }, { "epoch": 1.3098061593879844, "grad_norm": 1.3854800462722778, "learning_rate": 0.00014470279019051455, "loss": 0.6162366390228271, "step": 220350 }, { "epoch": 1.3098656014646528, "grad_norm": 1.2527104616165161, "learning_rate": 0.00014469704668923906, "loss": 0.5740526199340821, "step": 220360 }, { "epoch": 1.3099250435413212, "grad_norm": 1.4828194379806519, "learning_rate": 0.00014469130302198423, "loss": 0.5928755760192871, "step": 220370 }, { "epoch": 1.3099844856179894, "grad_norm": 1.818250060081482, "learning_rate": 0.00014468555918877756, "loss": 0.5923868179321289, "step": 220380 }, { "epoch": 1.3100439276946578, "grad_norm": 1.612356424331665, "learning_rate": 0.0001446798151896465, "loss": 0.5593235969543457, "step": 220390 }, { "epoch": 1.3101033697713262, "grad_norm": 1.5602147579193115, "learning_rate": 0.00014467407102461852, "loss": 0.6047141551971436, "step": 220400 }, { "epoch": 1.3101628118479947, "grad_norm": 1.4467030763626099, "learning_rate": 0.00014466832669372115, "loss": 0.5892664909362793, "step": 220410 }, { "epoch": 1.310222253924663, "grad_norm": 1.323348879814148, "learning_rate": 0.0001446625821969818, "loss": 0.5310475349426269, "step": 220420 }, { "epoch": 1.3102816960013315, "grad_norm": 1.365567684173584, "learning_rate": 0.000144656837534428, "loss": 0.6492855072021484, "step": 220430 }, { "epoch": 1.310341138078, "grad_norm": 1.6031559705734253, "learning_rate": 0.0001446510927060872, "loss": 0.6302337646484375, "step": 220440 }, { "epoch": 1.3104005801546683, "grad_norm": 1.5168685913085938, "learning_rate": 0.0001446453477119869, "loss": 0.6242158889770508, "step": 220450 }, { "epoch": 1.3104600222313367, "grad_norm": 1.6529873609542847, "learning_rate": 0.0001446396025521546, "loss": 0.6021754264831543, "step": 220460 }, { "epoch": 1.3105194643080051, "grad_norm": 1.4467339515686035, "learning_rate": 0.00014463385722661778, "loss": 0.5742437362670898, "step": 220470 }, { "epoch": 1.3105789063846736, "grad_norm": 1.2495516538619995, "learning_rate": 0.00014462811173540386, "loss": 0.553673267364502, "step": 220480 }, { "epoch": 1.310638348461342, "grad_norm": 1.4463274478912354, "learning_rate": 0.0001446223660785404, "loss": 0.5814053535461425, "step": 220490 }, { "epoch": 1.3106977905380102, "grad_norm": 1.5522041320800781, "learning_rate": 0.00014461662025605485, "loss": 0.6234219551086426, "step": 220500 }, { "epoch": 1.3107572326146786, "grad_norm": 1.4984233379364014, "learning_rate": 0.00014461087426797468, "loss": 0.5980854988098144, "step": 220510 }, { "epoch": 1.310816674691347, "grad_norm": 1.8025580644607544, "learning_rate": 0.00014460512811432743, "loss": 0.5565530300140381, "step": 220520 }, { "epoch": 1.3108761167680154, "grad_norm": 1.301348328590393, "learning_rate": 0.0001445993817951405, "loss": 0.5741635799407959, "step": 220530 }, { "epoch": 1.3109355588446838, "grad_norm": 1.4885692596435547, "learning_rate": 0.0001445936353104415, "loss": 0.5896567344665528, "step": 220540 }, { "epoch": 1.3109950009213522, "grad_norm": 1.6701198816299438, "learning_rate": 0.0001445878886602578, "loss": 0.6211361885070801, "step": 220550 }, { "epoch": 1.3110544429980207, "grad_norm": 1.3051140308380127, "learning_rate": 0.000144582141844617, "loss": 0.5662727355957031, "step": 220560 }, { "epoch": 1.3111138850746888, "grad_norm": 1.464754343032837, "learning_rate": 0.00014457639486354653, "loss": 0.5883785724639893, "step": 220570 }, { "epoch": 1.3111733271513573, "grad_norm": 1.7846004962921143, "learning_rate": 0.00014457064771707386, "loss": 0.5663802146911621, "step": 220580 }, { "epoch": 1.3112327692280257, "grad_norm": 1.8446985483169556, "learning_rate": 0.00014456490040522647, "loss": 0.5842377185821533, "step": 220590 }, { "epoch": 1.311292211304694, "grad_norm": 1.938238263130188, "learning_rate": 0.00014455915292803194, "loss": 0.6076085090637207, "step": 220600 }, { "epoch": 1.3113516533813625, "grad_norm": 1.4107167720794678, "learning_rate": 0.0001445534052855177, "loss": 0.5531994819641113, "step": 220610 }, { "epoch": 1.311411095458031, "grad_norm": 1.406967043876648, "learning_rate": 0.0001445476574777113, "loss": 0.6321159362792969, "step": 220620 }, { "epoch": 1.3114705375346993, "grad_norm": 1.5301152467727661, "learning_rate": 0.00014454190950464018, "loss": 0.6435283660888672, "step": 220630 }, { "epoch": 1.3115299796113677, "grad_norm": 1.359408974647522, "learning_rate": 0.00014453616136633182, "loss": 0.5783656597137451, "step": 220640 }, { "epoch": 1.3115894216880362, "grad_norm": 1.5126543045043945, "learning_rate": 0.00014453041306281377, "loss": 0.6442252159118652, "step": 220650 }, { "epoch": 1.3116488637647046, "grad_norm": 2.237623453140259, "learning_rate": 0.0001445246645941135, "loss": 0.5918038845062256, "step": 220660 }, { "epoch": 1.311708305841373, "grad_norm": 1.6994550228118896, "learning_rate": 0.00014451891596025857, "loss": 0.659824800491333, "step": 220670 }, { "epoch": 1.3117677479180412, "grad_norm": 1.6287139654159546, "learning_rate": 0.00014451316716127636, "loss": 0.594447135925293, "step": 220680 }, { "epoch": 1.3118271899947096, "grad_norm": 1.696916937828064, "learning_rate": 0.00014450741819719448, "loss": 0.5239415645599366, "step": 220690 }, { "epoch": 1.311886632071378, "grad_norm": 1.4808813333511353, "learning_rate": 0.0001445016690680404, "loss": 0.5912722587585449, "step": 220700 }, { "epoch": 1.3119460741480464, "grad_norm": 1.598193883895874, "learning_rate": 0.00014449591977384153, "loss": 0.5918138027191162, "step": 220710 }, { "epoch": 1.3120055162247148, "grad_norm": 1.5682103633880615, "learning_rate": 0.00014449017031462554, "loss": 0.5803269386291504, "step": 220720 }, { "epoch": 1.3120649583013833, "grad_norm": 1.7307889461517334, "learning_rate": 0.00014448442069041982, "loss": 0.6492444038391113, "step": 220730 }, { "epoch": 1.3121244003780517, "grad_norm": 1.375647783279419, "learning_rate": 0.00014447867090125184, "loss": 0.6442864418029786, "step": 220740 }, { "epoch": 1.3121838424547199, "grad_norm": 1.4150621891021729, "learning_rate": 0.00014447292094714925, "loss": 0.5796045303344727, "step": 220750 }, { "epoch": 1.3122432845313883, "grad_norm": 2.2616100311279297, "learning_rate": 0.00014446717082813943, "loss": 0.637682294845581, "step": 220760 }, { "epoch": 1.3123027266080567, "grad_norm": 1.63654363155365, "learning_rate": 0.00014446142054424995, "loss": 0.6061516761779785, "step": 220770 }, { "epoch": 1.312362168684725, "grad_norm": 1.4435497522354126, "learning_rate": 0.0001444556700955083, "loss": 0.608843183517456, "step": 220780 }, { "epoch": 1.3124216107613935, "grad_norm": 2.1802492141723633, "learning_rate": 0.00014444991948194195, "loss": 0.6023219108581543, "step": 220790 }, { "epoch": 1.312481052838062, "grad_norm": 1.2751425504684448, "learning_rate": 0.00014444416870357848, "loss": 0.6172980308532715, "step": 220800 }, { "epoch": 1.3125404949147303, "grad_norm": 1.798629879951477, "learning_rate": 0.00014443841776044537, "loss": 0.5885848522186279, "step": 220810 }, { "epoch": 1.3125999369913988, "grad_norm": 1.9217010736465454, "learning_rate": 0.00014443266665257006, "loss": 0.6129248142242432, "step": 220820 }, { "epoch": 1.3126593790680672, "grad_norm": 1.335975170135498, "learning_rate": 0.00014442691537998016, "loss": 0.5726202011108399, "step": 220830 }, { "epoch": 1.3127188211447356, "grad_norm": 1.4192615747451782, "learning_rate": 0.00014442116394270318, "loss": 0.6659340381622314, "step": 220840 }, { "epoch": 1.312778263221404, "grad_norm": 1.3298614025115967, "learning_rate": 0.0001444154123407666, "loss": 0.6619350910186768, "step": 220850 }, { "epoch": 1.3128377052980724, "grad_norm": 1.8082084655761719, "learning_rate": 0.0001444096605741979, "loss": 0.6036348819732666, "step": 220860 }, { "epoch": 1.3128971473747406, "grad_norm": 1.9630943536758423, "learning_rate": 0.00014440390864302462, "loss": 0.6300576210021973, "step": 220870 }, { "epoch": 1.312956589451409, "grad_norm": 1.533854365348816, "learning_rate": 0.0001443981565472743, "loss": 0.6461630821228027, "step": 220880 }, { "epoch": 1.3130160315280774, "grad_norm": 1.68876314163208, "learning_rate": 0.00014439240428697445, "loss": 0.7072896003723145, "step": 220890 }, { "epoch": 1.3130754736047459, "grad_norm": 2.0265254974365234, "learning_rate": 0.00014438665186215256, "loss": 0.6601529121398926, "step": 220900 }, { "epoch": 1.3131349156814143, "grad_norm": 1.4069578647613525, "learning_rate": 0.0001443808992728362, "loss": 0.6725314140319825, "step": 220910 }, { "epoch": 1.3131943577580827, "grad_norm": 1.5036401748657227, "learning_rate": 0.00014437514651905283, "loss": 0.5918425559997559, "step": 220920 }, { "epoch": 1.313253799834751, "grad_norm": 1.4375386238098145, "learning_rate": 0.00014436939360083, "loss": 0.5886894226074219, "step": 220930 }, { "epoch": 1.3133132419114193, "grad_norm": 1.3987864255905151, "learning_rate": 0.0001443636405181952, "loss": 0.5463481903076172, "step": 220940 }, { "epoch": 1.3133726839880877, "grad_norm": 1.8156393766403198, "learning_rate": 0.000144357887271176, "loss": 0.562712287902832, "step": 220950 }, { "epoch": 1.3134321260647561, "grad_norm": 2.0585787296295166, "learning_rate": 0.0001443521338597999, "loss": 0.6577515602111816, "step": 220960 }, { "epoch": 1.3134915681414245, "grad_norm": 1.9458527565002441, "learning_rate": 0.0001443463802840944, "loss": 0.6100547790527344, "step": 220970 }, { "epoch": 1.313551010218093, "grad_norm": 1.3638272285461426, "learning_rate": 0.00014434062654408706, "loss": 0.6067625999450683, "step": 220980 }, { "epoch": 1.3136104522947614, "grad_norm": 1.1682541370391846, "learning_rate": 0.00014433487263980534, "loss": 0.565275239944458, "step": 220990 }, { "epoch": 1.3136698943714298, "grad_norm": 1.682167887687683, "learning_rate": 0.00014432911857127685, "loss": 0.6230044364929199, "step": 221000 }, { "epoch": 1.3137293364480982, "grad_norm": 1.5545681715011597, "learning_rate": 0.00014432336433852907, "loss": 0.5784177780151367, "step": 221010 }, { "epoch": 1.3137887785247666, "grad_norm": 1.396228551864624, "learning_rate": 0.0001443176099415895, "loss": 0.5759140014648437, "step": 221020 }, { "epoch": 1.313848220601435, "grad_norm": 1.4948322772979736, "learning_rate": 0.00014431185538048578, "loss": 0.5863124370574951, "step": 221030 }, { "epoch": 1.3139076626781034, "grad_norm": 1.649609088897705, "learning_rate": 0.00014430610065524528, "loss": 0.5951505661010742, "step": 221040 }, { "epoch": 1.3139671047547716, "grad_norm": 1.7284119129180908, "learning_rate": 0.0001443003457658956, "loss": 0.5379709243774414, "step": 221050 }, { "epoch": 1.31402654683144, "grad_norm": 1.3016959428787231, "learning_rate": 0.00014429459071246435, "loss": 0.5860072612762451, "step": 221060 }, { "epoch": 1.3140859889081085, "grad_norm": 1.462701678276062, "learning_rate": 0.0001442888354949789, "loss": 0.6496436119079589, "step": 221070 }, { "epoch": 1.3141454309847769, "grad_norm": 1.6243839263916016, "learning_rate": 0.00014428308011346693, "loss": 0.5563559532165527, "step": 221080 }, { "epoch": 1.3142048730614453, "grad_norm": 1.1467540264129639, "learning_rate": 0.00014427732456795587, "loss": 0.6567776203155518, "step": 221090 }, { "epoch": 1.3142643151381137, "grad_norm": 1.8362560272216797, "learning_rate": 0.0001442715688584733, "loss": 0.5596903800964356, "step": 221100 }, { "epoch": 1.3143237572147821, "grad_norm": 1.5680956840515137, "learning_rate": 0.00014426581298504677, "loss": 0.5763442039489746, "step": 221110 }, { "epoch": 1.3143831992914503, "grad_norm": 1.5820002555847168, "learning_rate": 0.0001442600569477038, "loss": 0.6250124931335449, "step": 221120 }, { "epoch": 1.3144426413681187, "grad_norm": 2.0695881843566895, "learning_rate": 0.00014425430074647185, "loss": 0.6274043560028076, "step": 221130 }, { "epoch": 1.3145020834447871, "grad_norm": 1.5341134071350098, "learning_rate": 0.00014424854438137855, "loss": 0.6033468246459961, "step": 221140 }, { "epoch": 1.3145615255214556, "grad_norm": 1.5700583457946777, "learning_rate": 0.00014424278785245143, "loss": 0.6226727485656738, "step": 221150 }, { "epoch": 1.314620967598124, "grad_norm": 1.5235220193862915, "learning_rate": 0.000144237031159718, "loss": 0.6906765937805176, "step": 221160 }, { "epoch": 1.3146804096747924, "grad_norm": 1.4999042749404907, "learning_rate": 0.00014423127430320578, "loss": 0.5571729660034179, "step": 221170 }, { "epoch": 1.3147398517514608, "grad_norm": 1.5956732034683228, "learning_rate": 0.0001442255172829423, "loss": 0.5710389614105225, "step": 221180 }, { "epoch": 1.3147992938281292, "grad_norm": 1.577157974243164, "learning_rate": 0.0001442197600989552, "loss": 0.6344048500061035, "step": 221190 }, { "epoch": 1.3148587359047976, "grad_norm": 1.7207554578781128, "learning_rate": 0.0001442140027512719, "loss": 0.5809746742248535, "step": 221200 }, { "epoch": 1.314918177981466, "grad_norm": 1.405541181564331, "learning_rate": 0.00014420824523992006, "loss": 0.5467839717864991, "step": 221210 }, { "epoch": 1.3149776200581345, "grad_norm": 1.9581316709518433, "learning_rate": 0.00014420248756492708, "loss": 0.5773868560791016, "step": 221220 }, { "epoch": 1.3150370621348029, "grad_norm": 1.6108417510986328, "learning_rate": 0.0001441967297263206, "loss": 0.6698439598083497, "step": 221230 }, { "epoch": 1.315096504211471, "grad_norm": 1.7705368995666504, "learning_rate": 0.00014419097172412815, "loss": 0.6568767547607421, "step": 221240 }, { "epoch": 1.3151559462881395, "grad_norm": 1.7822173833847046, "learning_rate": 0.00014418521355837724, "loss": 0.6150185585021972, "step": 221250 }, { "epoch": 1.315215388364808, "grad_norm": 0.9612923860549927, "learning_rate": 0.00014417945522909547, "loss": 0.6192543506622314, "step": 221260 }, { "epoch": 1.3152748304414763, "grad_norm": 1.3207945823669434, "learning_rate": 0.00014417369673631035, "loss": 0.5809059143066406, "step": 221270 }, { "epoch": 1.3153342725181447, "grad_norm": 1.4654731750488281, "learning_rate": 0.00014416793808004943, "loss": 0.5427228927612304, "step": 221280 }, { "epoch": 1.3153937145948131, "grad_norm": 1.601643681526184, "learning_rate": 0.00014416217926034025, "loss": 0.6254025459289551, "step": 221290 }, { "epoch": 1.3154531566714815, "grad_norm": 1.690718173980713, "learning_rate": 0.00014415642027721038, "loss": 0.6133284568786621, "step": 221300 }, { "epoch": 1.3155125987481497, "grad_norm": 1.6163814067840576, "learning_rate": 0.00014415066113068734, "loss": 0.5822813510894775, "step": 221310 }, { "epoch": 1.3155720408248182, "grad_norm": 1.4671777486801147, "learning_rate": 0.00014414490182079872, "loss": 0.6054241180419921, "step": 221320 }, { "epoch": 1.3156314829014866, "grad_norm": 1.478549599647522, "learning_rate": 0.00014413914234757204, "loss": 0.6075150966644287, "step": 221330 }, { "epoch": 1.315690924978155, "grad_norm": 1.8037909269332886, "learning_rate": 0.00014413338271103486, "loss": 0.6373562335968017, "step": 221340 }, { "epoch": 1.3157503670548234, "grad_norm": 1.3588253259658813, "learning_rate": 0.00014412762291121474, "loss": 0.6013266563415527, "step": 221350 }, { "epoch": 1.3158098091314918, "grad_norm": 1.4951010942459106, "learning_rate": 0.0001441218629481392, "loss": 0.5617695331573487, "step": 221360 }, { "epoch": 1.3158692512081602, "grad_norm": 1.1902697086334229, "learning_rate": 0.00014411610282183586, "loss": 0.5814843654632569, "step": 221370 }, { "epoch": 1.3159286932848286, "grad_norm": 1.4668705463409424, "learning_rate": 0.00014411034253233217, "loss": 0.5991646766662597, "step": 221380 }, { "epoch": 1.315988135361497, "grad_norm": 1.2572687864303589, "learning_rate": 0.0001441045820796558, "loss": 0.5895815849304199, "step": 221390 }, { "epoch": 1.3160475774381655, "grad_norm": 1.6945781707763672, "learning_rate": 0.00014409882146383424, "loss": 0.6243088245391846, "step": 221400 }, { "epoch": 1.3161070195148339, "grad_norm": 1.4488714933395386, "learning_rate": 0.00014409306068489505, "loss": 0.6596702575683594, "step": 221410 }, { "epoch": 1.316166461591502, "grad_norm": 1.358506441116333, "learning_rate": 0.00014408729974286583, "loss": 0.5731130599975586, "step": 221420 }, { "epoch": 1.3162259036681705, "grad_norm": 1.665748119354248, "learning_rate": 0.0001440815386377741, "loss": 0.6070229530334472, "step": 221430 }, { "epoch": 1.316285345744839, "grad_norm": 1.658793568611145, "learning_rate": 0.0001440757773696474, "loss": 0.6618074893951416, "step": 221440 }, { "epoch": 1.3163447878215073, "grad_norm": 1.7825816869735718, "learning_rate": 0.00014407001593851333, "loss": 0.6605129241943359, "step": 221450 }, { "epoch": 1.3164042298981757, "grad_norm": 1.958587408065796, "learning_rate": 0.00014406425434439945, "loss": 0.6192877769470215, "step": 221460 }, { "epoch": 1.3164636719748442, "grad_norm": 1.2088724374771118, "learning_rate": 0.0001440584925873333, "loss": 0.6338268280029297, "step": 221470 }, { "epoch": 1.3165231140515126, "grad_norm": 1.4334845542907715, "learning_rate": 0.00014405273066734245, "loss": 0.5959131240844726, "step": 221480 }, { "epoch": 1.3165825561281808, "grad_norm": 1.4154932498931885, "learning_rate": 0.00014404696858445447, "loss": 0.595552921295166, "step": 221490 }, { "epoch": 1.3166419982048492, "grad_norm": 1.7928637266159058, "learning_rate": 0.00014404120633869694, "loss": 0.5623705863952637, "step": 221500 }, { "epoch": 1.3167014402815176, "grad_norm": 1.4832522869110107, "learning_rate": 0.00014403544393009737, "loss": 0.6532645225524902, "step": 221510 }, { "epoch": 1.316760882358186, "grad_norm": 1.2589768171310425, "learning_rate": 0.0001440296813586834, "loss": 0.604969835281372, "step": 221520 }, { "epoch": 1.3168203244348544, "grad_norm": 1.6358171701431274, "learning_rate": 0.0001440239186244825, "loss": 0.575711727142334, "step": 221530 }, { "epoch": 1.3168797665115228, "grad_norm": 1.780460000038147, "learning_rate": 0.00014401815572752234, "loss": 0.6163746356964112, "step": 221540 }, { "epoch": 1.3169392085881912, "grad_norm": 1.3403925895690918, "learning_rate": 0.0001440123926678304, "loss": 0.6414296150207519, "step": 221550 }, { "epoch": 1.3169986506648597, "grad_norm": 1.4240444898605347, "learning_rate": 0.00014400662944543432, "loss": 0.5586737632751465, "step": 221560 }, { "epoch": 1.317058092741528, "grad_norm": 1.7372937202453613, "learning_rate": 0.00014400086606036164, "loss": 0.5952261924743653, "step": 221570 }, { "epoch": 1.3171175348181965, "grad_norm": 1.3703765869140625, "learning_rate": 0.0001439951025126399, "loss": 0.6243346691131592, "step": 221580 }, { "epoch": 1.317176976894865, "grad_norm": 1.7984340190887451, "learning_rate": 0.0001439893388022967, "loss": 0.5568969249725342, "step": 221590 }, { "epoch": 1.3172364189715333, "grad_norm": 1.6925829648971558, "learning_rate": 0.00014398357492935963, "loss": 0.659354829788208, "step": 221600 }, { "epoch": 1.3172958610482015, "grad_norm": 1.8243085145950317, "learning_rate": 0.00014397781089385623, "loss": 0.5952808380126953, "step": 221610 }, { "epoch": 1.31735530312487, "grad_norm": 1.3243788480758667, "learning_rate": 0.00014397204669581412, "loss": 0.6039776802062988, "step": 221620 }, { "epoch": 1.3174147452015383, "grad_norm": 1.6890618801116943, "learning_rate": 0.0001439662823352608, "loss": 0.6247686386108399, "step": 221630 }, { "epoch": 1.3174741872782068, "grad_norm": 1.350898265838623, "learning_rate": 0.00014396051781222392, "loss": 0.646397876739502, "step": 221640 }, { "epoch": 1.3175336293548752, "grad_norm": 1.519904613494873, "learning_rate": 0.00014395475312673102, "loss": 0.5935293674468994, "step": 221650 }, { "epoch": 1.3175930714315436, "grad_norm": 1.2994307279586792, "learning_rate": 0.00014394898827880962, "loss": 0.5676098346710206, "step": 221660 }, { "epoch": 1.317652513508212, "grad_norm": 1.304604172706604, "learning_rate": 0.0001439432232684874, "loss": 0.5780930995941163, "step": 221670 }, { "epoch": 1.3177119555848802, "grad_norm": 1.9350899457931519, "learning_rate": 0.00014393745809579192, "loss": 0.5712282657623291, "step": 221680 }, { "epoch": 1.3177713976615486, "grad_norm": 1.943347692489624, "learning_rate": 0.00014393169276075068, "loss": 0.6297823905944824, "step": 221690 }, { "epoch": 1.317830839738217, "grad_norm": 1.843718409538269, "learning_rate": 0.0001439259272633913, "loss": 0.5842585086822509, "step": 221700 }, { "epoch": 1.3178902818148854, "grad_norm": 1.3059002161026, "learning_rate": 0.00014392016160374142, "loss": 0.5970920562744141, "step": 221710 }, { "epoch": 1.3179497238915538, "grad_norm": 1.0416467189788818, "learning_rate": 0.00014391439578182854, "loss": 0.6155323028564453, "step": 221720 }, { "epoch": 1.3180091659682223, "grad_norm": 1.901706576347351, "learning_rate": 0.0001439086297976803, "loss": 0.6260955333709717, "step": 221730 }, { "epoch": 1.3180686080448907, "grad_norm": 1.258263111114502, "learning_rate": 0.00014390286365132426, "loss": 0.6211624145507812, "step": 221740 }, { "epoch": 1.318128050121559, "grad_norm": 1.5719752311706543, "learning_rate": 0.000143897097342788, "loss": 0.6186509132385254, "step": 221750 }, { "epoch": 1.3181874921982275, "grad_norm": 1.987341284751892, "learning_rate": 0.00014389133087209908, "loss": 0.6136590003967285, "step": 221760 }, { "epoch": 1.318246934274896, "grad_norm": 1.7031667232513428, "learning_rate": 0.0001438855642392851, "loss": 0.60167236328125, "step": 221770 }, { "epoch": 1.3183063763515643, "grad_norm": 1.6812255382537842, "learning_rate": 0.0001438797974443737, "loss": 0.6248964309692383, "step": 221780 }, { "epoch": 1.3183658184282325, "grad_norm": 1.691421389579773, "learning_rate": 0.00014387403048739237, "loss": 0.6404844284057617, "step": 221790 }, { "epoch": 1.318425260504901, "grad_norm": 1.5127410888671875, "learning_rate": 0.0001438682633683688, "loss": 0.5550528526306152, "step": 221800 }, { "epoch": 1.3184847025815694, "grad_norm": 1.7709225416183472, "learning_rate": 0.00014386249608733048, "loss": 0.6151129245758057, "step": 221810 }, { "epoch": 1.3185441446582378, "grad_norm": 1.370719075202942, "learning_rate": 0.00014385672864430506, "loss": 0.6172182559967041, "step": 221820 }, { "epoch": 1.3186035867349062, "grad_norm": 1.1823484897613525, "learning_rate": 0.00014385096103932012, "loss": 0.6143366813659668, "step": 221830 }, { "epoch": 1.3186630288115746, "grad_norm": 1.7849200963974, "learning_rate": 0.0001438451932724032, "loss": 0.5916242122650146, "step": 221840 }, { "epoch": 1.318722470888243, "grad_norm": 1.4733521938323975, "learning_rate": 0.00014383942534358204, "loss": 0.5567800998687744, "step": 221850 }, { "epoch": 1.3187819129649112, "grad_norm": 1.712672233581543, "learning_rate": 0.00014383365725288404, "loss": 0.5935544013977051, "step": 221860 }, { "epoch": 1.3188413550415796, "grad_norm": 1.4378645420074463, "learning_rate": 0.0001438278890003369, "loss": 0.562440013885498, "step": 221870 }, { "epoch": 1.318900797118248, "grad_norm": 1.6560242176055908, "learning_rate": 0.0001438221205859682, "loss": 0.5822320938110351, "step": 221880 }, { "epoch": 1.3189602391949165, "grad_norm": 1.3058807849884033, "learning_rate": 0.00014381635200980553, "loss": 0.5777664184570312, "step": 221890 }, { "epoch": 1.3190196812715849, "grad_norm": 1.5164915323257446, "learning_rate": 0.00014381058327187648, "loss": 0.6790619373321534, "step": 221900 }, { "epoch": 1.3190791233482533, "grad_norm": 1.6011544466018677, "learning_rate": 0.00014380481437220867, "loss": 0.6162156105041504, "step": 221910 }, { "epoch": 1.3191385654249217, "grad_norm": 1.6699055433273315, "learning_rate": 0.00014379904531082967, "loss": 0.6544756889343262, "step": 221920 }, { "epoch": 1.31919800750159, "grad_norm": 1.7679301500320435, "learning_rate": 0.00014379327608776704, "loss": 0.6255888938903809, "step": 221930 }, { "epoch": 1.3192574495782585, "grad_norm": 1.5699137449264526, "learning_rate": 0.00014378750670304845, "loss": 0.6133311271667481, "step": 221940 }, { "epoch": 1.319316891654927, "grad_norm": 1.671391248703003, "learning_rate": 0.00014378173715670148, "loss": 0.5988097190856934, "step": 221950 }, { "epoch": 1.3193763337315954, "grad_norm": 1.544458031654358, "learning_rate": 0.00014377596744875372, "loss": 0.6348844528198242, "step": 221960 }, { "epoch": 1.3194357758082638, "grad_norm": 1.5376278162002563, "learning_rate": 0.00014377019757923275, "loss": 0.6257540702819824, "step": 221970 }, { "epoch": 1.319495217884932, "grad_norm": 1.6268655061721802, "learning_rate": 0.00014376442754816622, "loss": 0.6182451248168945, "step": 221980 }, { "epoch": 1.3195546599616004, "grad_norm": 1.8541799783706665, "learning_rate": 0.00014375865735558166, "loss": 0.5925449371337891, "step": 221990 }, { "epoch": 1.3196141020382688, "grad_norm": 1.6266422271728516, "learning_rate": 0.00014375288700150675, "loss": 0.5878639221191406, "step": 222000 }, { "epoch": 1.3196735441149372, "grad_norm": 1.197035312652588, "learning_rate": 0.00014374711648596907, "loss": 0.5669720649719239, "step": 222010 }, { "epoch": 1.3197329861916056, "grad_norm": 1.7694830894470215, "learning_rate": 0.00014374134580899618, "loss": 0.6380536079406738, "step": 222020 }, { "epoch": 1.319792428268274, "grad_norm": 1.3315423727035522, "learning_rate": 0.00014373557497061572, "loss": 0.5522912025451661, "step": 222030 }, { "epoch": 1.3198518703449424, "grad_norm": 1.520442247390747, "learning_rate": 0.00014372980397085532, "loss": 0.6308838367462158, "step": 222040 }, { "epoch": 1.3199113124216106, "grad_norm": 1.7320210933685303, "learning_rate": 0.00014372403280974252, "loss": 0.6027926445007324, "step": 222050 }, { "epoch": 1.319970754498279, "grad_norm": 1.503614068031311, "learning_rate": 0.00014371826148730502, "loss": 0.6024348258972168, "step": 222060 }, { "epoch": 1.3200301965749475, "grad_norm": 2.0063648223876953, "learning_rate": 0.00014371249000357035, "loss": 0.6205055713653564, "step": 222070 }, { "epoch": 1.3200896386516159, "grad_norm": 1.3144910335540771, "learning_rate": 0.00014370671835856614, "loss": 0.5668827056884765, "step": 222080 }, { "epoch": 1.3201490807282843, "grad_norm": 1.6267132759094238, "learning_rate": 0.00014370094655232, "loss": 0.5864696502685547, "step": 222090 }, { "epoch": 1.3202085228049527, "grad_norm": 1.35554838180542, "learning_rate": 0.00014369517458485956, "loss": 0.5252725601196289, "step": 222100 }, { "epoch": 1.3202679648816211, "grad_norm": 1.6774885654449463, "learning_rate": 0.00014368940245621244, "loss": 0.625130033493042, "step": 222110 }, { "epoch": 1.3203274069582895, "grad_norm": 1.2329422235488892, "learning_rate": 0.00014368363016640614, "loss": 0.5616244316101074, "step": 222120 }, { "epoch": 1.320386849034958, "grad_norm": 1.625845193862915, "learning_rate": 0.00014367785771546846, "loss": 0.58847074508667, "step": 222130 }, { "epoch": 1.3204462911116264, "grad_norm": 1.6148803234100342, "learning_rate": 0.0001436720851034269, "loss": 0.63302583694458, "step": 222140 }, { "epoch": 1.3205057331882948, "grad_norm": 1.1337902545928955, "learning_rate": 0.00014366631233030903, "loss": 0.585191011428833, "step": 222150 }, { "epoch": 1.320565175264963, "grad_norm": 1.5198184251785278, "learning_rate": 0.00014366053939614257, "loss": 0.5737859725952148, "step": 222160 }, { "epoch": 1.3206246173416314, "grad_norm": 1.4759562015533447, "learning_rate": 0.00014365476630095507, "loss": 0.568203353881836, "step": 222170 }, { "epoch": 1.3206840594182998, "grad_norm": 1.7006369829177856, "learning_rate": 0.00014364899304477417, "loss": 0.6213538646697998, "step": 222180 }, { "epoch": 1.3207435014949682, "grad_norm": 1.6722184419631958, "learning_rate": 0.00014364321962762747, "loss": 0.6452366828918457, "step": 222190 }, { "epoch": 1.3208029435716366, "grad_norm": 1.339934229850769, "learning_rate": 0.00014363744604954266, "loss": 0.6120548725128174, "step": 222200 }, { "epoch": 1.320862385648305, "grad_norm": 1.6429738998413086, "learning_rate": 0.00014363167231054723, "loss": 0.5864917755126953, "step": 222210 }, { "epoch": 1.3209218277249735, "grad_norm": 1.4967347383499146, "learning_rate": 0.00014362589841066895, "loss": 0.5590085029602051, "step": 222220 }, { "epoch": 1.3209812698016417, "grad_norm": 1.5616832971572876, "learning_rate": 0.0001436201243499353, "loss": 0.6222082138061523, "step": 222230 }, { "epoch": 1.32104071187831, "grad_norm": 1.5965465307235718, "learning_rate": 0.00014361435012837396, "loss": 0.5636889934539795, "step": 222240 }, { "epoch": 1.3211001539549785, "grad_norm": 1.2324950695037842, "learning_rate": 0.0001436085757460126, "loss": 0.5940323829650879, "step": 222250 }, { "epoch": 1.321159596031647, "grad_norm": 1.714663028717041, "learning_rate": 0.00014360280120287878, "loss": 0.6538872241973877, "step": 222260 }, { "epoch": 1.3212190381083153, "grad_norm": 1.4682388305664062, "learning_rate": 0.0001435970264990001, "loss": 0.5983186721801758, "step": 222270 }, { "epoch": 1.3212784801849837, "grad_norm": 1.384619951248169, "learning_rate": 0.00014359125163440425, "loss": 0.6039931297302246, "step": 222280 }, { "epoch": 1.3213379222616521, "grad_norm": 1.8240553140640259, "learning_rate": 0.00014358547660911882, "loss": 0.6408045768737793, "step": 222290 }, { "epoch": 1.3213973643383206, "grad_norm": 1.4683126211166382, "learning_rate": 0.0001435797014231715, "loss": 0.5992726802825927, "step": 222300 }, { "epoch": 1.321456806414989, "grad_norm": 1.4808881282806396, "learning_rate": 0.00014357392607658976, "loss": 0.6116950511932373, "step": 222310 }, { "epoch": 1.3215162484916574, "grad_norm": 1.3843903541564941, "learning_rate": 0.00014356815056940146, "loss": 0.5689897060394287, "step": 222320 }, { "epoch": 1.3215756905683258, "grad_norm": 1.5967175960540771, "learning_rate": 0.000143562374901634, "loss": 0.6025792121887207, "step": 222330 }, { "epoch": 1.3216351326449942, "grad_norm": 1.165818691253662, "learning_rate": 0.00014355659907331513, "loss": 0.5704606533050537, "step": 222340 }, { "epoch": 1.3216945747216624, "grad_norm": 1.9174716472625732, "learning_rate": 0.00014355082308447248, "loss": 0.6330676078796387, "step": 222350 }, { "epoch": 1.3217540167983308, "grad_norm": 1.6740747690200806, "learning_rate": 0.00014354504693513362, "loss": 0.6561988830566406, "step": 222360 }, { "epoch": 1.3218134588749992, "grad_norm": 1.713178038597107, "learning_rate": 0.00014353927062532625, "loss": 0.5950081825256348, "step": 222370 }, { "epoch": 1.3218729009516677, "grad_norm": 1.655651330947876, "learning_rate": 0.00014353349415507796, "loss": 0.5653324127197266, "step": 222380 }, { "epoch": 1.321932343028336, "grad_norm": 1.4231867790222168, "learning_rate": 0.00014352771752441636, "loss": 0.6413256645202636, "step": 222390 }, { "epoch": 1.3219917851050045, "grad_norm": 1.8419263362884521, "learning_rate": 0.00014352194073336918, "loss": 0.6345761299133301, "step": 222400 }, { "epoch": 1.322051227181673, "grad_norm": 1.8819587230682373, "learning_rate": 0.00014351616378196396, "loss": 0.5985328674316406, "step": 222410 }, { "epoch": 1.322110669258341, "grad_norm": 1.3602081537246704, "learning_rate": 0.00014351038667022835, "loss": 0.6248110771179199, "step": 222420 }, { "epoch": 1.3221701113350095, "grad_norm": 1.4899399280548096, "learning_rate": 0.00014350460939819, "loss": 0.6186511039733886, "step": 222430 }, { "epoch": 1.322229553411678, "grad_norm": 1.2494479417800903, "learning_rate": 0.0001434988319658766, "loss": 0.601513671875, "step": 222440 }, { "epoch": 1.3222889954883463, "grad_norm": 1.4809989929199219, "learning_rate": 0.00014349305437331568, "loss": 0.6450375556945801, "step": 222450 }, { "epoch": 1.3223484375650147, "grad_norm": 1.2993592023849487, "learning_rate": 0.00014348727662053494, "loss": 0.5172737121582032, "step": 222460 }, { "epoch": 1.3224078796416832, "grad_norm": 1.726646065711975, "learning_rate": 0.00014348149870756203, "loss": 0.5752621173858643, "step": 222470 }, { "epoch": 1.3224673217183516, "grad_norm": 1.76614248752594, "learning_rate": 0.0001434757206344246, "loss": 0.6321850776672363, "step": 222480 }, { "epoch": 1.32252676379502, "grad_norm": 1.3170993328094482, "learning_rate": 0.00014346994240115016, "loss": 0.5354690551757812, "step": 222490 }, { "epoch": 1.3225862058716884, "grad_norm": 1.6976178884506226, "learning_rate": 0.0001434641640077666, "loss": 0.6170126914978027, "step": 222500 }, { "epoch": 1.3226456479483568, "grad_norm": 1.5819025039672852, "learning_rate": 0.00014345838545430127, "loss": 0.5741215705871582, "step": 222510 }, { "epoch": 1.3227050900250252, "grad_norm": 1.4214216470718384, "learning_rate": 0.00014345260674078201, "loss": 0.6552881240844727, "step": 222520 }, { "epoch": 1.3227645321016934, "grad_norm": 1.7326122522354126, "learning_rate": 0.00014344682786723647, "loss": 0.6829438209533691, "step": 222530 }, { "epoch": 1.3228239741783618, "grad_norm": 1.648637056350708, "learning_rate": 0.00014344104883369217, "loss": 0.6545967102050781, "step": 222540 }, { "epoch": 1.3228834162550303, "grad_norm": 1.2275480031967163, "learning_rate": 0.00014343526964017686, "loss": 0.603784704208374, "step": 222550 }, { "epoch": 1.3229428583316987, "grad_norm": 1.7602970600128174, "learning_rate": 0.00014342949028671814, "loss": 0.6335923194885253, "step": 222560 }, { "epoch": 1.323002300408367, "grad_norm": 1.225419044494629, "learning_rate": 0.00014342371077334364, "loss": 0.596738624572754, "step": 222570 }, { "epoch": 1.3230617424850355, "grad_norm": 1.3332343101501465, "learning_rate": 0.00014341793110008106, "loss": 0.6313412189483643, "step": 222580 }, { "epoch": 1.323121184561704, "grad_norm": 1.2267117500305176, "learning_rate": 0.000143412151266958, "loss": 0.5507739067077637, "step": 222590 }, { "epoch": 1.323180626638372, "grad_norm": 1.4016664028167725, "learning_rate": 0.00014340637127400216, "loss": 0.6149236679077148, "step": 222600 }, { "epoch": 1.3232400687150405, "grad_norm": 1.4427942037582397, "learning_rate": 0.0001434005911212411, "loss": 0.5958535671234131, "step": 222610 }, { "epoch": 1.323299510791709, "grad_norm": 1.6193186044692993, "learning_rate": 0.00014339481080870257, "loss": 0.5816706657409668, "step": 222620 }, { "epoch": 1.3233589528683773, "grad_norm": 1.6205092668533325, "learning_rate": 0.00014338903033641416, "loss": 0.5949015617370605, "step": 222630 }, { "epoch": 1.3234183949450458, "grad_norm": 1.493849754333496, "learning_rate": 0.00014338324970440352, "loss": 0.6134625434875488, "step": 222640 }, { "epoch": 1.3234778370217142, "grad_norm": 1.3884133100509644, "learning_rate": 0.00014337746891269836, "loss": 0.6604522705078125, "step": 222650 }, { "epoch": 1.3235372790983826, "grad_norm": 1.6980916261672974, "learning_rate": 0.00014337168796132633, "loss": 0.6161481857299804, "step": 222660 }, { "epoch": 1.323596721175051, "grad_norm": 2.1660470962524414, "learning_rate": 0.00014336590685031495, "loss": 0.6616966247558593, "step": 222670 }, { "epoch": 1.3236561632517194, "grad_norm": 1.5986014604568481, "learning_rate": 0.00014336012557969205, "loss": 0.6061794281005859, "step": 222680 }, { "epoch": 1.3237156053283878, "grad_norm": 1.0641003847122192, "learning_rate": 0.00014335434414948522, "loss": 0.5895366668701172, "step": 222690 }, { "epoch": 1.3237750474050562, "grad_norm": 1.7516835927963257, "learning_rate": 0.00014334856255972207, "loss": 0.6752893447875976, "step": 222700 }, { "epoch": 1.3238344894817247, "grad_norm": 1.594462275505066, "learning_rate": 0.00014334278081043028, "loss": 0.6277846813201904, "step": 222710 }, { "epoch": 1.3238939315583929, "grad_norm": 1.9627963304519653, "learning_rate": 0.00014333699890163758, "loss": 0.5756525993347168, "step": 222720 }, { "epoch": 1.3239533736350613, "grad_norm": 1.410649061203003, "learning_rate": 0.00014333121683337153, "loss": 0.5492715835571289, "step": 222730 }, { "epoch": 1.3240128157117297, "grad_norm": 1.5676209926605225, "learning_rate": 0.00014332543460565984, "loss": 0.6061076641082763, "step": 222740 }, { "epoch": 1.324072257788398, "grad_norm": 1.4169540405273438, "learning_rate": 0.00014331965221853018, "loss": 0.6078049659729003, "step": 222750 }, { "epoch": 1.3241316998650665, "grad_norm": 1.4109450578689575, "learning_rate": 0.00014331386967201016, "loss": 0.6132577419281006, "step": 222760 }, { "epoch": 1.324191141941735, "grad_norm": 1.4692277908325195, "learning_rate": 0.0001433080869661275, "loss": 0.5520389556884766, "step": 222770 }, { "epoch": 1.3242505840184033, "grad_norm": 1.4839861392974854, "learning_rate": 0.00014330230410090984, "loss": 0.6536048889160156, "step": 222780 }, { "epoch": 1.3243100260950715, "grad_norm": 1.2532612085342407, "learning_rate": 0.0001432965210763848, "loss": 0.574547815322876, "step": 222790 }, { "epoch": 1.32436946817174, "grad_norm": 1.4657320976257324, "learning_rate": 0.00014329073789258012, "loss": 0.6080328941345214, "step": 222800 }, { "epoch": 1.3244289102484084, "grad_norm": 1.4838145971298218, "learning_rate": 0.00014328495454952347, "loss": 0.6505270957946777, "step": 222810 }, { "epoch": 1.3244883523250768, "grad_norm": 1.4698271751403809, "learning_rate": 0.00014327917104724238, "loss": 0.6038165092468262, "step": 222820 }, { "epoch": 1.3245477944017452, "grad_norm": 1.4016900062561035, "learning_rate": 0.00014327338738576466, "loss": 0.6094135284423828, "step": 222830 }, { "epoch": 1.3246072364784136, "grad_norm": 1.5255974531173706, "learning_rate": 0.00014326760356511798, "loss": 0.5204023361206055, "step": 222840 }, { "epoch": 1.324666678555082, "grad_norm": 1.6101831197738647, "learning_rate": 0.00014326181958532988, "loss": 0.6333901405334472, "step": 222850 }, { "epoch": 1.3247261206317504, "grad_norm": 1.4671385288238525, "learning_rate": 0.00014325603544642813, "loss": 0.6093295574188232, "step": 222860 }, { "epoch": 1.3247855627084189, "grad_norm": 1.3448166847229004, "learning_rate": 0.00014325025114844038, "loss": 0.611306619644165, "step": 222870 }, { "epoch": 1.3248450047850873, "grad_norm": 1.4041911363601685, "learning_rate": 0.00014324446669139427, "loss": 0.549649715423584, "step": 222880 }, { "epoch": 1.3249044468617557, "grad_norm": 1.481026291847229, "learning_rate": 0.00014323868207531752, "loss": 0.6094798088073731, "step": 222890 }, { "epoch": 1.3249638889384239, "grad_norm": 1.3762205839157104, "learning_rate": 0.0001432328973002378, "loss": 0.5967596054077149, "step": 222900 }, { "epoch": 1.3250233310150923, "grad_norm": 1.7527841329574585, "learning_rate": 0.0001432271123661827, "loss": 0.5769429206848145, "step": 222910 }, { "epoch": 1.3250827730917607, "grad_norm": 1.0338244438171387, "learning_rate": 0.00014322132727317998, "loss": 0.5388628959655761, "step": 222920 }, { "epoch": 1.3251422151684291, "grad_norm": 2.227017879486084, "learning_rate": 0.0001432155420212573, "loss": 0.629140567779541, "step": 222930 }, { "epoch": 1.3252016572450975, "grad_norm": 1.8128480911254883, "learning_rate": 0.00014320975661044234, "loss": 0.6379110813140869, "step": 222940 }, { "epoch": 1.325261099321766, "grad_norm": 1.8910503387451172, "learning_rate": 0.0001432039710407627, "loss": 0.6077948570251465, "step": 222950 }, { "epoch": 1.3253205413984344, "grad_norm": 1.7000904083251953, "learning_rate": 0.00014319818531224616, "loss": 0.6328252792358399, "step": 222960 }, { "epoch": 1.3253799834751026, "grad_norm": 1.5353260040283203, "learning_rate": 0.00014319239942492035, "loss": 0.5844913959503174, "step": 222970 }, { "epoch": 1.325439425551771, "grad_norm": 1.5526387691497803, "learning_rate": 0.00014318661337881295, "loss": 0.6572993755340576, "step": 222980 }, { "epoch": 1.3254988676284394, "grad_norm": 1.3570009469985962, "learning_rate": 0.00014318082717395162, "loss": 0.6328509330749512, "step": 222990 }, { "epoch": 1.3255583097051078, "grad_norm": 1.6469874382019043, "learning_rate": 0.00014317504081036404, "loss": 0.5898651123046875, "step": 223000 }, { "epoch": 1.3256177517817762, "grad_norm": 1.6831144094467163, "learning_rate": 0.0001431692542880779, "loss": 0.6010345458984375, "step": 223010 }, { "epoch": 1.3256771938584446, "grad_norm": 1.8112752437591553, "learning_rate": 0.00014316346760712094, "loss": 0.6184976100921631, "step": 223020 }, { "epoch": 1.325736635935113, "grad_norm": 1.3103101253509521, "learning_rate": 0.00014315768076752076, "loss": 0.6647331714630127, "step": 223030 }, { "epoch": 1.3257960780117815, "grad_norm": 1.6051595211029053, "learning_rate": 0.0001431518937693051, "loss": 0.6017545223236084, "step": 223040 }, { "epoch": 1.3258555200884499, "grad_norm": 1.7388372421264648, "learning_rate": 0.00014314610661250157, "loss": 0.5843914031982422, "step": 223050 }, { "epoch": 1.3259149621651183, "grad_norm": 1.6307306289672852, "learning_rate": 0.0001431403192971379, "loss": 0.5538052558898926, "step": 223060 }, { "epoch": 1.3259744042417867, "grad_norm": 2.0643763542175293, "learning_rate": 0.0001431345318232418, "loss": 0.6134584426879883, "step": 223070 }, { "epoch": 1.3260338463184551, "grad_norm": 1.2258893251419067, "learning_rate": 0.0001431287441908409, "loss": 0.5750341892242432, "step": 223080 }, { "epoch": 1.3260932883951233, "grad_norm": 1.348429799079895, "learning_rate": 0.00014312295639996297, "loss": 0.5829557418823242, "step": 223090 }, { "epoch": 1.3261527304717917, "grad_norm": 1.9037840366363525, "learning_rate": 0.00014311716845063558, "loss": 0.5791138172149658, "step": 223100 }, { "epoch": 1.3262121725484601, "grad_norm": 1.4327579736709595, "learning_rate": 0.0001431113803428865, "loss": 0.5895680904388427, "step": 223110 }, { "epoch": 1.3262716146251285, "grad_norm": 1.2978136539459229, "learning_rate": 0.0001431055920767434, "loss": 0.5976572036743164, "step": 223120 }, { "epoch": 1.326331056701797, "grad_norm": 2.489079236984253, "learning_rate": 0.00014309980365223397, "loss": 0.6240219116210938, "step": 223130 }, { "epoch": 1.3263904987784654, "grad_norm": 1.5511362552642822, "learning_rate": 0.0001430940150693859, "loss": 0.600257396697998, "step": 223140 }, { "epoch": 1.3264499408551338, "grad_norm": 1.9984185695648193, "learning_rate": 0.00014308822632822687, "loss": 0.619451904296875, "step": 223150 }, { "epoch": 1.326509382931802, "grad_norm": 2.178623676300049, "learning_rate": 0.00014308243742878454, "loss": 0.5892989635467529, "step": 223160 }, { "epoch": 1.3265688250084704, "grad_norm": 1.5456230640411377, "learning_rate": 0.0001430766483710867, "loss": 0.5940264701843262, "step": 223170 }, { "epoch": 1.3266282670851388, "grad_norm": 1.4156755208969116, "learning_rate": 0.00014307085915516097, "loss": 0.578216552734375, "step": 223180 }, { "epoch": 1.3266877091618072, "grad_norm": 1.4669606685638428, "learning_rate": 0.00014306506978103504, "loss": 0.5442807674407959, "step": 223190 }, { "epoch": 1.3267471512384756, "grad_norm": 1.2874886989593506, "learning_rate": 0.00014305928024873664, "loss": 0.5911818504333496, "step": 223200 }, { "epoch": 1.326806593315144, "grad_norm": 1.3635388612747192, "learning_rate": 0.00014305349055829345, "loss": 0.6185446739196777, "step": 223210 }, { "epoch": 1.3268660353918125, "grad_norm": 1.6900779008865356, "learning_rate": 0.00014304770070973314, "loss": 0.6507980346679687, "step": 223220 }, { "epoch": 1.3269254774684809, "grad_norm": 1.3826501369476318, "learning_rate": 0.00014304191070308345, "loss": 0.576653528213501, "step": 223230 }, { "epoch": 1.3269849195451493, "grad_norm": 1.3169291019439697, "learning_rate": 0.00014303612053837207, "loss": 0.6257729530334473, "step": 223240 }, { "epoch": 1.3270443616218177, "grad_norm": 2.0315539836883545, "learning_rate": 0.00014303033021562664, "loss": 0.5896714210510254, "step": 223250 }, { "epoch": 1.3271038036984861, "grad_norm": 1.3524342775344849, "learning_rate": 0.00014302453973487494, "loss": 0.6730822563171387, "step": 223260 }, { "epoch": 1.3271632457751543, "grad_norm": 1.2323275804519653, "learning_rate": 0.00014301874909614464, "loss": 0.5969629287719727, "step": 223270 }, { "epoch": 1.3272226878518227, "grad_norm": 1.7163689136505127, "learning_rate": 0.0001430129582994634, "loss": 0.549558448791504, "step": 223280 }, { "epoch": 1.3272821299284912, "grad_norm": 1.439365029335022, "learning_rate": 0.00014300716734485898, "loss": 0.5531728744506836, "step": 223290 }, { "epoch": 1.3273415720051596, "grad_norm": 1.6057542562484741, "learning_rate": 0.00014300137623235906, "loss": 0.5879404544830322, "step": 223300 }, { "epoch": 1.327401014081828, "grad_norm": 2.0201120376586914, "learning_rate": 0.00014299558496199132, "loss": 0.650389289855957, "step": 223310 }, { "epoch": 1.3274604561584964, "grad_norm": 1.5203338861465454, "learning_rate": 0.00014298979353378347, "loss": 0.5496313095092773, "step": 223320 }, { "epoch": 1.3275198982351648, "grad_norm": 1.4440151453018188, "learning_rate": 0.0001429840019477633, "loss": 0.5394003868103028, "step": 223330 }, { "epoch": 1.327579340311833, "grad_norm": 1.396400809288025, "learning_rate": 0.0001429782102039584, "loss": 0.5102204322814942, "step": 223340 }, { "epoch": 1.3276387823885014, "grad_norm": 1.6959904432296753, "learning_rate": 0.00014297241830239652, "loss": 0.605764627456665, "step": 223350 }, { "epoch": 1.3276982244651698, "grad_norm": 1.3218973875045776, "learning_rate": 0.00014296662624310535, "loss": 0.5934624671936035, "step": 223360 }, { "epoch": 1.3277576665418382, "grad_norm": 2.08602237701416, "learning_rate": 0.00014296083402611263, "loss": 0.61134352684021, "step": 223370 }, { "epoch": 1.3278171086185067, "grad_norm": 1.7966252565383911, "learning_rate": 0.00014295504165144608, "loss": 0.6486511707305909, "step": 223380 }, { "epoch": 1.327876550695175, "grad_norm": 1.3108903169631958, "learning_rate": 0.00014294924911913338, "loss": 0.5498615264892578, "step": 223390 }, { "epoch": 1.3279359927718435, "grad_norm": 1.5209003686904907, "learning_rate": 0.0001429434564292022, "loss": 0.6168032646179199, "step": 223400 }, { "epoch": 1.327995434848512, "grad_norm": 1.7786812782287598, "learning_rate": 0.0001429376635816803, "loss": 0.5795263290405274, "step": 223410 }, { "epoch": 1.3280548769251803, "grad_norm": 1.7126721143722534, "learning_rate": 0.00014293187057659536, "loss": 0.5587417602539062, "step": 223420 }, { "epoch": 1.3281143190018487, "grad_norm": 1.1764696836471558, "learning_rate": 0.00014292607741397514, "loss": 0.590824031829834, "step": 223430 }, { "epoch": 1.3281737610785171, "grad_norm": 1.4401110410690308, "learning_rate": 0.00014292028409384732, "loss": 0.5909770965576172, "step": 223440 }, { "epoch": 1.3282332031551856, "grad_norm": 1.785253643989563, "learning_rate": 0.00014291449061623965, "loss": 0.6311366081237793, "step": 223450 }, { "epoch": 1.3282926452318538, "grad_norm": 1.5619921684265137, "learning_rate": 0.00014290869698117977, "loss": 0.6486727237701416, "step": 223460 }, { "epoch": 1.3283520873085222, "grad_norm": 1.632179617881775, "learning_rate": 0.00014290290318869545, "loss": 0.6234273910522461, "step": 223470 }, { "epoch": 1.3284115293851906, "grad_norm": 1.4663074016571045, "learning_rate": 0.0001428971092388144, "loss": 0.6284040451049805, "step": 223480 }, { "epoch": 1.328470971461859, "grad_norm": 1.3979977369308472, "learning_rate": 0.00014289131513156434, "loss": 0.6089795112609864, "step": 223490 }, { "epoch": 1.3285304135385274, "grad_norm": 1.585990309715271, "learning_rate": 0.00014288552086697296, "loss": 0.6141310691833496, "step": 223500 }, { "epoch": 1.3285898556151958, "grad_norm": 1.5087906122207642, "learning_rate": 0.00014287972644506803, "loss": 0.5768876075744629, "step": 223510 }, { "epoch": 1.3286492976918642, "grad_norm": 1.3032578229904175, "learning_rate": 0.0001428739318658772, "loss": 0.5896577835083008, "step": 223520 }, { "epoch": 1.3287087397685324, "grad_norm": 1.8300498723983765, "learning_rate": 0.00014286813712942824, "loss": 0.6113777160644531, "step": 223530 }, { "epoch": 1.3287681818452008, "grad_norm": 1.5733532905578613, "learning_rate": 0.0001428623422357488, "loss": 0.5938490867614746, "step": 223540 }, { "epoch": 1.3288276239218693, "grad_norm": 1.506636142730713, "learning_rate": 0.00014285654718486674, "loss": 0.5868073463439941, "step": 223550 }, { "epoch": 1.3288870659985377, "grad_norm": 1.563156008720398, "learning_rate": 0.00014285075197680963, "loss": 0.5746787071228028, "step": 223560 }, { "epoch": 1.328946508075206, "grad_norm": 1.2814475297927856, "learning_rate": 0.0001428449566116053, "loss": 0.5870640754699707, "step": 223570 }, { "epoch": 1.3290059501518745, "grad_norm": 1.5599071979522705, "learning_rate": 0.00014283916108928145, "loss": 0.5909719944000245, "step": 223580 }, { "epoch": 1.329065392228543, "grad_norm": 1.573356032371521, "learning_rate": 0.00014283336540986573, "loss": 0.6028926849365235, "step": 223590 }, { "epoch": 1.3291248343052113, "grad_norm": 1.6792880296707153, "learning_rate": 0.00014282756957338593, "loss": 0.616762113571167, "step": 223600 }, { "epoch": 1.3291842763818797, "grad_norm": 1.8032361268997192, "learning_rate": 0.0001428217735798698, "loss": 0.6199650764465332, "step": 223610 }, { "epoch": 1.3292437184585482, "grad_norm": 1.5891811847686768, "learning_rate": 0.00014281597742934497, "loss": 0.6045289039611816, "step": 223620 }, { "epoch": 1.3293031605352166, "grad_norm": 1.6899200677871704, "learning_rate": 0.00014281018112183928, "loss": 0.568886661529541, "step": 223630 }, { "epoch": 1.3293626026118848, "grad_norm": 1.4113267660140991, "learning_rate": 0.0001428043846573804, "loss": 0.5494795799255371, "step": 223640 }, { "epoch": 1.3294220446885532, "grad_norm": 1.2853449583053589, "learning_rate": 0.00014279858803599603, "loss": 0.6188261032104492, "step": 223650 }, { "epoch": 1.3294814867652216, "grad_norm": 1.6381133794784546, "learning_rate": 0.00014279279125771396, "loss": 0.6066403865814209, "step": 223660 }, { "epoch": 1.32954092884189, "grad_norm": 1.9165046215057373, "learning_rate": 0.0001427869943225619, "loss": 0.6120643615722656, "step": 223670 }, { "epoch": 1.3296003709185584, "grad_norm": 1.5520806312561035, "learning_rate": 0.00014278119723056757, "loss": 0.5694060325622559, "step": 223680 }, { "epoch": 1.3296598129952268, "grad_norm": 1.622004508972168, "learning_rate": 0.0001427753999817587, "loss": 0.6062802791595459, "step": 223690 }, { "epoch": 1.3297192550718953, "grad_norm": 1.6925766468048096, "learning_rate": 0.00014276960257616304, "loss": 0.6452444553375244, "step": 223700 }, { "epoch": 1.3297786971485634, "grad_norm": 1.2247775793075562, "learning_rate": 0.00014276380501380831, "loss": 0.537086296081543, "step": 223710 }, { "epoch": 1.3298381392252319, "grad_norm": 1.915496587753296, "learning_rate": 0.00014275800729472222, "loss": 0.6261373519897461, "step": 223720 }, { "epoch": 1.3298975813019003, "grad_norm": 1.3740824460983276, "learning_rate": 0.00014275220941893256, "loss": 0.6148334503173828, "step": 223730 }, { "epoch": 1.3299570233785687, "grad_norm": 1.828417420387268, "learning_rate": 0.000142746411386467, "loss": 0.5669253826141357, "step": 223740 }, { "epoch": 1.330016465455237, "grad_norm": 1.5016368627548218, "learning_rate": 0.00014274061319735333, "loss": 0.6233551979064942, "step": 223750 }, { "epoch": 1.3300759075319055, "grad_norm": 1.5345592498779297, "learning_rate": 0.00014273481485161922, "loss": 0.5682662963867188, "step": 223760 }, { "epoch": 1.330135349608574, "grad_norm": 1.6015150547027588, "learning_rate": 0.00014272901634929252, "loss": 0.6273149967193603, "step": 223770 }, { "epoch": 1.3301947916852424, "grad_norm": 1.3538981676101685, "learning_rate": 0.00014272321769040087, "loss": 0.5946806907653809, "step": 223780 }, { "epoch": 1.3302542337619108, "grad_norm": 1.3651319742202759, "learning_rate": 0.00014271741887497206, "loss": 0.566621208190918, "step": 223790 }, { "epoch": 1.3303136758385792, "grad_norm": 1.6970692873001099, "learning_rate": 0.0001427116199030338, "loss": 0.644735050201416, "step": 223800 }, { "epoch": 1.3303731179152476, "grad_norm": 1.259339690208435, "learning_rate": 0.00014270582077461383, "loss": 0.5800381660461426, "step": 223810 }, { "epoch": 1.330432559991916, "grad_norm": 1.4475351572036743, "learning_rate": 0.00014270002148973995, "loss": 0.6383847236633301, "step": 223820 }, { "epoch": 1.3304920020685842, "grad_norm": 1.6283059120178223, "learning_rate": 0.00014269422204843982, "loss": 0.6029999732971192, "step": 223830 }, { "epoch": 1.3305514441452526, "grad_norm": 1.3160842657089233, "learning_rate": 0.0001426884224507412, "loss": 0.6116127014160156, "step": 223840 }, { "epoch": 1.330610886221921, "grad_norm": 1.6222187280654907, "learning_rate": 0.00014268262269667185, "loss": 0.5649877548217773, "step": 223850 }, { "epoch": 1.3306703282985894, "grad_norm": 1.3715181350708008, "learning_rate": 0.00014267682278625954, "loss": 0.5701571464538574, "step": 223860 }, { "epoch": 1.3307297703752579, "grad_norm": 1.818198800086975, "learning_rate": 0.00014267102271953193, "loss": 0.6814325332641602, "step": 223870 }, { "epoch": 1.3307892124519263, "grad_norm": 1.9669075012207031, "learning_rate": 0.00014266522249651691, "loss": 0.630131721496582, "step": 223880 }, { "epoch": 1.3308486545285947, "grad_norm": 1.559639573097229, "learning_rate": 0.0001426594221172421, "loss": 0.6333653450012207, "step": 223890 }, { "epoch": 1.3309080966052629, "grad_norm": 1.8653509616851807, "learning_rate": 0.00014265362158173527, "loss": 0.5916062831878662, "step": 223900 }, { "epoch": 1.3309675386819313, "grad_norm": 1.3158440589904785, "learning_rate": 0.00014264782089002423, "loss": 0.6127616882324218, "step": 223910 }, { "epoch": 1.3310269807585997, "grad_norm": 1.1194610595703125, "learning_rate": 0.00014264202004213663, "loss": 0.6257775306701661, "step": 223920 }, { "epoch": 1.3310864228352681, "grad_norm": 1.6446990966796875, "learning_rate": 0.00014263621903810026, "loss": 0.630970048904419, "step": 223930 }, { "epoch": 1.3311458649119365, "grad_norm": 1.0635476112365723, "learning_rate": 0.00014263041787794295, "loss": 0.5519873619079589, "step": 223940 }, { "epoch": 1.331205306988605, "grad_norm": 1.2628084421157837, "learning_rate": 0.00014262461656169238, "loss": 0.5625152587890625, "step": 223950 }, { "epoch": 1.3312647490652734, "grad_norm": 1.3972195386886597, "learning_rate": 0.00014261881508937627, "loss": 0.6133311271667481, "step": 223960 }, { "epoch": 1.3313241911419418, "grad_norm": 1.4780815839767456, "learning_rate": 0.00014261301346102243, "loss": 0.5916181564331054, "step": 223970 }, { "epoch": 1.3313836332186102, "grad_norm": 1.304795265197754, "learning_rate": 0.0001426072116766586, "loss": 0.6156563758850098, "step": 223980 }, { "epoch": 1.3314430752952786, "grad_norm": 1.5722253322601318, "learning_rate": 0.00014260140973631246, "loss": 0.6014533042907715, "step": 223990 }, { "epoch": 1.331502517371947, "grad_norm": 1.47298002243042, "learning_rate": 0.0001425956076400119, "loss": 0.6568286895751954, "step": 224000 }, { "epoch": 1.3315619594486152, "grad_norm": 1.382535457611084, "learning_rate": 0.00014258980538778458, "loss": 0.5824974536895752, "step": 224010 }, { "epoch": 1.3316214015252836, "grad_norm": 1.6975146532058716, "learning_rate": 0.0001425840029796583, "loss": 0.589347505569458, "step": 224020 }, { "epoch": 1.331680843601952, "grad_norm": 1.6811892986297607, "learning_rate": 0.0001425782004156608, "loss": 0.6247950553894043, "step": 224030 }, { "epoch": 1.3317402856786205, "grad_norm": 1.3638919591903687, "learning_rate": 0.00014257239769581981, "loss": 0.5543289661407471, "step": 224040 }, { "epoch": 1.3317997277552889, "grad_norm": 1.5338068008422852, "learning_rate": 0.00014256659482016313, "loss": 0.5949068069458008, "step": 224050 }, { "epoch": 1.3318591698319573, "grad_norm": 1.6433225870132446, "learning_rate": 0.00014256079178871848, "loss": 0.5574186325073243, "step": 224060 }, { "epoch": 1.3319186119086257, "grad_norm": 1.4167824983596802, "learning_rate": 0.0001425549886015137, "loss": 0.5897257804870606, "step": 224070 }, { "epoch": 1.331978053985294, "grad_norm": 1.462769627571106, "learning_rate": 0.00014254918525857644, "loss": 0.5538480281829834, "step": 224080 }, { "epoch": 1.3320374960619623, "grad_norm": 1.4554332494735718, "learning_rate": 0.0001425433817599345, "loss": 0.613826847076416, "step": 224090 }, { "epoch": 1.3320969381386307, "grad_norm": 1.37956964969635, "learning_rate": 0.0001425375781056157, "loss": 0.5940000534057617, "step": 224100 }, { "epoch": 1.3321563802152991, "grad_norm": 1.808387279510498, "learning_rate": 0.00014253177429564775, "loss": 0.6275997161865234, "step": 224110 }, { "epoch": 1.3322158222919676, "grad_norm": 2.1130363941192627, "learning_rate": 0.00014252597033005844, "loss": 0.6148452758789062, "step": 224120 }, { "epoch": 1.332275264368636, "grad_norm": 2.736497640609741, "learning_rate": 0.0001425201662088755, "loss": 0.5694626808166504, "step": 224130 }, { "epoch": 1.3323347064453044, "grad_norm": 1.7916135787963867, "learning_rate": 0.00014251436193212668, "loss": 0.6327726364135742, "step": 224140 }, { "epoch": 1.3323941485219728, "grad_norm": 1.5960054397583008, "learning_rate": 0.00014250855749983982, "loss": 0.6235053062438964, "step": 224150 }, { "epoch": 1.3324535905986412, "grad_norm": 1.32649827003479, "learning_rate": 0.00014250275291204263, "loss": 0.6465324401855469, "step": 224160 }, { "epoch": 1.3325130326753096, "grad_norm": 1.033622145652771, "learning_rate": 0.0001424969481687629, "loss": 0.5782951831817627, "step": 224170 }, { "epoch": 1.332572474751978, "grad_norm": 1.3556833267211914, "learning_rate": 0.0001424911432700284, "loss": 0.5405689239501953, "step": 224180 }, { "epoch": 1.3326319168286465, "grad_norm": 1.6658766269683838, "learning_rate": 0.00014248533821586688, "loss": 0.6602555274963379, "step": 224190 }, { "epoch": 1.3326913589053146, "grad_norm": 1.5787039995193481, "learning_rate": 0.0001424795330063061, "loss": 0.617558479309082, "step": 224200 }, { "epoch": 1.332750800981983, "grad_norm": 1.9355442523956299, "learning_rate": 0.00014247372764137386, "loss": 0.5740438461303711, "step": 224210 }, { "epoch": 1.3328102430586515, "grad_norm": 1.3869173526763916, "learning_rate": 0.00014246792212109792, "loss": 0.6101909637451172, "step": 224220 }, { "epoch": 1.33286968513532, "grad_norm": 1.4694982767105103, "learning_rate": 0.00014246211644550606, "loss": 0.5665499687194824, "step": 224230 }, { "epoch": 1.3329291272119883, "grad_norm": 1.8858208656311035, "learning_rate": 0.00014245631061462604, "loss": 0.5978880405426026, "step": 224240 }, { "epoch": 1.3329885692886567, "grad_norm": 1.2868629693984985, "learning_rate": 0.00014245050462848558, "loss": 0.6076155662536621, "step": 224250 }, { "epoch": 1.3330480113653251, "grad_norm": 1.0137771368026733, "learning_rate": 0.00014244469848711258, "loss": 0.5524802207946777, "step": 224260 }, { "epoch": 1.3331074534419933, "grad_norm": 1.2123329639434814, "learning_rate": 0.00014243889219053474, "loss": 0.6423101425170898, "step": 224270 }, { "epoch": 1.3331668955186617, "grad_norm": 1.3878897428512573, "learning_rate": 0.00014243308573877981, "loss": 0.6112313270568848, "step": 224280 }, { "epoch": 1.3332263375953302, "grad_norm": 1.4103392362594604, "learning_rate": 0.00014242727913187564, "loss": 0.5646158218383789, "step": 224290 }, { "epoch": 1.3332857796719986, "grad_norm": 1.5662766695022583, "learning_rate": 0.00014242147236984994, "loss": 0.6037472724914551, "step": 224300 }, { "epoch": 1.333345221748667, "grad_norm": 1.7374212741851807, "learning_rate": 0.0001424156654527305, "loss": 0.6563084125518799, "step": 224310 }, { "epoch": 1.3334046638253354, "grad_norm": 1.4244884252548218, "learning_rate": 0.00014240985838054514, "loss": 0.6104621410369873, "step": 224320 }, { "epoch": 1.3334641059020038, "grad_norm": 1.16914701461792, "learning_rate": 0.0001424040511533216, "loss": 0.5612628936767579, "step": 224330 }, { "epoch": 1.3335235479786722, "grad_norm": 1.3056788444519043, "learning_rate": 0.00014239824377108764, "loss": 0.6356513023376464, "step": 224340 }, { "epoch": 1.3335829900553406, "grad_norm": 1.7080525159835815, "learning_rate": 0.00014239243623387108, "loss": 0.6523775100708008, "step": 224350 }, { "epoch": 1.333642432132009, "grad_norm": 1.255962610244751, "learning_rate": 0.00014238662854169974, "loss": 0.5171181678771972, "step": 224360 }, { "epoch": 1.3337018742086775, "grad_norm": 1.9603428840637207, "learning_rate": 0.00014238082069460128, "loss": 0.6311563968658447, "step": 224370 }, { "epoch": 1.3337613162853457, "grad_norm": 1.9948081970214844, "learning_rate": 0.00014237501269260362, "loss": 0.6190350532531739, "step": 224380 }, { "epoch": 1.333820758362014, "grad_norm": 1.627691626548767, "learning_rate": 0.00014236920453573442, "loss": 0.6197770118713379, "step": 224390 }, { "epoch": 1.3338802004386825, "grad_norm": 1.6396344900131226, "learning_rate": 0.00014236339622402156, "loss": 0.6129053115844727, "step": 224400 }, { "epoch": 1.333939642515351, "grad_norm": 1.6615943908691406, "learning_rate": 0.00014235758775749281, "loss": 0.597806453704834, "step": 224410 }, { "epoch": 1.3339990845920193, "grad_norm": 1.5309988260269165, "learning_rate": 0.0001423517791361759, "loss": 0.6004939079284668, "step": 224420 }, { "epoch": 1.3340585266686877, "grad_norm": 2.371800422668457, "learning_rate": 0.00014234597036009864, "loss": 0.6178628921508789, "step": 224430 }, { "epoch": 1.3341179687453562, "grad_norm": 1.5683674812316895, "learning_rate": 0.00014234016142928885, "loss": 0.5974774360656738, "step": 224440 }, { "epoch": 1.3341774108220243, "grad_norm": 1.705918788909912, "learning_rate": 0.0001423343523437743, "loss": 0.6114970207214355, "step": 224450 }, { "epoch": 1.3342368528986928, "grad_norm": 1.6921985149383545, "learning_rate": 0.00014232854310358277, "loss": 0.6021415233612061, "step": 224460 }, { "epoch": 1.3342962949753612, "grad_norm": 1.4182935953140259, "learning_rate": 0.00014232273370874207, "loss": 0.6135851860046386, "step": 224470 }, { "epoch": 1.3343557370520296, "grad_norm": 1.6007237434387207, "learning_rate": 0.00014231692415927994, "loss": 0.6350451469421386, "step": 224480 }, { "epoch": 1.334415179128698, "grad_norm": 1.45254385471344, "learning_rate": 0.00014231111445522422, "loss": 0.5841516494750977, "step": 224490 }, { "epoch": 1.3344746212053664, "grad_norm": 1.6590608358383179, "learning_rate": 0.00014230530459660273, "loss": 0.6072704792022705, "step": 224500 }, { "epoch": 1.3345340632820348, "grad_norm": 1.9734089374542236, "learning_rate": 0.00014229949458344318, "loss": 0.6367767810821533, "step": 224510 }, { "epoch": 1.3345935053587032, "grad_norm": 1.5313515663146973, "learning_rate": 0.0001422936844157734, "loss": 0.6071713924407959, "step": 224520 }, { "epoch": 1.3346529474353717, "grad_norm": 1.4640133380889893, "learning_rate": 0.0001422878740936212, "loss": 0.5419984340667725, "step": 224530 }, { "epoch": 1.33471238951204, "grad_norm": 1.4393428564071655, "learning_rate": 0.00014228206361701433, "loss": 0.5318608283996582, "step": 224540 }, { "epoch": 1.3347718315887085, "grad_norm": 1.5531275272369385, "learning_rate": 0.00014227625298598065, "loss": 0.5869645595550537, "step": 224550 }, { "epoch": 1.334831273665377, "grad_norm": 1.4069101810455322, "learning_rate": 0.00014227044220054794, "loss": 0.6076889514923096, "step": 224560 }, { "epoch": 1.334890715742045, "grad_norm": 1.7454897165298462, "learning_rate": 0.00014226463126074395, "loss": 0.6048970222473145, "step": 224570 }, { "epoch": 1.3349501578187135, "grad_norm": 1.2157390117645264, "learning_rate": 0.0001422588201665965, "loss": 0.5997138977050781, "step": 224580 }, { "epoch": 1.335009599895382, "grad_norm": 1.3387328386306763, "learning_rate": 0.0001422530089181334, "loss": 0.57186861038208, "step": 224590 }, { "epoch": 1.3350690419720503, "grad_norm": 1.5428694486618042, "learning_rate": 0.0001422471975153825, "loss": 0.5854905605316162, "step": 224600 }, { "epoch": 1.3351284840487188, "grad_norm": 2.0043399333953857, "learning_rate": 0.0001422413859583715, "loss": 0.631777286529541, "step": 224610 }, { "epoch": 1.3351879261253872, "grad_norm": 1.2879267930984497, "learning_rate": 0.00014223557424712822, "loss": 0.5890095710754395, "step": 224620 }, { "epoch": 1.3352473682020556, "grad_norm": 1.5524317026138306, "learning_rate": 0.0001422297623816805, "loss": 0.6745655536651611, "step": 224630 }, { "epoch": 1.3353068102787238, "grad_norm": 1.9129365682601929, "learning_rate": 0.0001422239503620562, "loss": 0.5964337348937988, "step": 224640 }, { "epoch": 1.3353662523553922, "grad_norm": 1.176162838935852, "learning_rate": 0.00014221813818828297, "loss": 0.5531064033508301, "step": 224650 }, { "epoch": 1.3354256944320606, "grad_norm": 1.9683027267456055, "learning_rate": 0.00014221232586038873, "loss": 0.6331651687622071, "step": 224660 }, { "epoch": 1.335485136508729, "grad_norm": 1.0602554082870483, "learning_rate": 0.00014220651337840126, "loss": 0.647434663772583, "step": 224670 }, { "epoch": 1.3355445785853974, "grad_norm": 1.6453063488006592, "learning_rate": 0.00014220070074234833, "loss": 0.5807219505310058, "step": 224680 }, { "epoch": 1.3356040206620658, "grad_norm": 1.303655743598938, "learning_rate": 0.0001421948879522578, "loss": 0.6666450500488281, "step": 224690 }, { "epoch": 1.3356634627387343, "grad_norm": 1.745157241821289, "learning_rate": 0.0001421890750081574, "loss": 0.610383415222168, "step": 224700 }, { "epoch": 1.3357229048154027, "grad_norm": 1.4190956354141235, "learning_rate": 0.00014218326191007505, "loss": 0.5834070205688476, "step": 224710 }, { "epoch": 1.335782346892071, "grad_norm": 1.5119189023971558, "learning_rate": 0.00014217744865803846, "loss": 0.6365192413330079, "step": 224720 }, { "epoch": 1.3358417889687395, "grad_norm": 1.6365152597427368, "learning_rate": 0.00014217163525207543, "loss": 0.641375732421875, "step": 224730 }, { "epoch": 1.335901231045408, "grad_norm": 1.4618310928344727, "learning_rate": 0.00014216582169221387, "loss": 0.5690426826477051, "step": 224740 }, { "epoch": 1.3359606731220761, "grad_norm": 1.4570170640945435, "learning_rate": 0.00014216000797848152, "loss": 0.6487850189208985, "step": 224750 }, { "epoch": 1.3360201151987445, "grad_norm": 1.452536702156067, "learning_rate": 0.0001421541941109062, "loss": 0.6053875923156739, "step": 224760 }, { "epoch": 1.336079557275413, "grad_norm": 1.2364333868026733, "learning_rate": 0.00014214838008951567, "loss": 0.572260570526123, "step": 224770 }, { "epoch": 1.3361389993520814, "grad_norm": 1.4166439771652222, "learning_rate": 0.00014214256591433787, "loss": 0.6043477535247803, "step": 224780 }, { "epoch": 1.3361984414287498, "grad_norm": 1.2546950578689575, "learning_rate": 0.0001421367515854005, "loss": 0.623636531829834, "step": 224790 }, { "epoch": 1.3362578835054182, "grad_norm": 1.296817660331726, "learning_rate": 0.00014213093710273143, "loss": 0.5760991096496582, "step": 224800 }, { "epoch": 1.3363173255820866, "grad_norm": 1.594590663909912, "learning_rate": 0.00014212512246635845, "loss": 0.6283211231231689, "step": 224810 }, { "epoch": 1.3363767676587548, "grad_norm": 1.5934479236602783, "learning_rate": 0.00014211930767630938, "loss": 0.5644332885742187, "step": 224820 }, { "epoch": 1.3364362097354232, "grad_norm": 1.4098576307296753, "learning_rate": 0.00014211349273261206, "loss": 0.5644150257110596, "step": 224830 }, { "epoch": 1.3364956518120916, "grad_norm": 1.3401426076889038, "learning_rate": 0.00014210767763529424, "loss": 0.6481608867645263, "step": 224840 }, { "epoch": 1.33655509388876, "grad_norm": 1.9808694124221802, "learning_rate": 0.00014210186238438382, "loss": 0.6179994106292724, "step": 224850 }, { "epoch": 1.3366145359654285, "grad_norm": 1.9390569925308228, "learning_rate": 0.00014209604697990857, "loss": 0.6364733695983886, "step": 224860 }, { "epoch": 1.3366739780420969, "grad_norm": 1.5064038038253784, "learning_rate": 0.00014209023142189634, "loss": 0.662047290802002, "step": 224870 }, { "epoch": 1.3367334201187653, "grad_norm": 1.5406994819641113, "learning_rate": 0.0001420844157103749, "loss": 0.6125955581665039, "step": 224880 }, { "epoch": 1.3367928621954337, "grad_norm": 1.837862491607666, "learning_rate": 0.0001420785998453721, "loss": 0.6103872299194336, "step": 224890 }, { "epoch": 1.336852304272102, "grad_norm": 1.2392326593399048, "learning_rate": 0.0001420727838269158, "loss": 0.6073527336120605, "step": 224900 }, { "epoch": 1.3369117463487705, "grad_norm": 1.6257407665252686, "learning_rate": 0.00014206696765503376, "loss": 0.6343124389648438, "step": 224910 }, { "epoch": 1.336971188425439, "grad_norm": 1.8008487224578857, "learning_rate": 0.00014206115132975382, "loss": 0.6268910884857177, "step": 224920 }, { "epoch": 1.3370306305021074, "grad_norm": 2.084172010421753, "learning_rate": 0.00014205533485110383, "loss": 0.6232525825500488, "step": 224930 }, { "epoch": 1.3370900725787755, "grad_norm": 1.4599019289016724, "learning_rate": 0.00014204951821911158, "loss": 0.6054588317871094, "step": 224940 }, { "epoch": 1.337149514655444, "grad_norm": 1.4834764003753662, "learning_rate": 0.0001420437014338049, "loss": 0.6195547580718994, "step": 224950 }, { "epoch": 1.3372089567321124, "grad_norm": 1.4937623739242554, "learning_rate": 0.00014203788449521163, "loss": 0.6307892799377441, "step": 224960 }, { "epoch": 1.3372683988087808, "grad_norm": 1.9957677125930786, "learning_rate": 0.00014203206740335958, "loss": 0.6085470199584961, "step": 224970 }, { "epoch": 1.3373278408854492, "grad_norm": 1.3901358842849731, "learning_rate": 0.0001420262501582766, "loss": 0.5977416038513184, "step": 224980 }, { "epoch": 1.3373872829621176, "grad_norm": 1.9089996814727783, "learning_rate": 0.0001420204327599905, "loss": 0.5967580795288085, "step": 224990 }, { "epoch": 1.337446725038786, "grad_norm": 1.4315022230148315, "learning_rate": 0.00014201461520852915, "loss": 0.569437313079834, "step": 225000 }, { "epoch": 1.3375061671154542, "grad_norm": 1.6901799440383911, "learning_rate": 0.0001420087975039203, "loss": 0.6221064567565918, "step": 225010 }, { "epoch": 1.3375656091921226, "grad_norm": 1.6593215465545654, "learning_rate": 0.00014200297964619182, "loss": 0.6123764038085937, "step": 225020 }, { "epoch": 1.337625051268791, "grad_norm": 1.7424392700195312, "learning_rate": 0.00014199716163537155, "loss": 0.6192222595214844, "step": 225030 }, { "epoch": 1.3376844933454595, "grad_norm": 1.985986590385437, "learning_rate": 0.00014199134347148734, "loss": 0.601501750946045, "step": 225040 }, { "epoch": 1.3377439354221279, "grad_norm": 1.4780665636062622, "learning_rate": 0.00014198552515456699, "loss": 0.5565009117126465, "step": 225050 }, { "epoch": 1.3378033774987963, "grad_norm": 1.1296160221099854, "learning_rate": 0.0001419797066846383, "loss": 0.6344338893890381, "step": 225060 }, { "epoch": 1.3378628195754647, "grad_norm": 1.5793331861495972, "learning_rate": 0.0001419738880617292, "loss": 0.596964168548584, "step": 225070 }, { "epoch": 1.3379222616521331, "grad_norm": 1.9823029041290283, "learning_rate": 0.00014196806928586746, "loss": 0.6122488975524902, "step": 225080 }, { "epoch": 1.3379817037288015, "grad_norm": 2.066343069076538, "learning_rate": 0.0001419622503570809, "loss": 0.5547210216522217, "step": 225090 }, { "epoch": 1.33804114580547, "grad_norm": 1.6415249109268188, "learning_rate": 0.0001419564312753974, "loss": 0.5570170402526855, "step": 225100 }, { "epoch": 1.3381005878821384, "grad_norm": 1.5257761478424072, "learning_rate": 0.00014195061204084477, "loss": 0.6304298400878906, "step": 225110 }, { "epoch": 1.3381600299588066, "grad_norm": 1.406254529953003, "learning_rate": 0.00014194479265345085, "loss": 0.6155952453613281, "step": 225120 }, { "epoch": 1.338219472035475, "grad_norm": 1.3753286600112915, "learning_rate": 0.00014193897311324348, "loss": 0.5614032745361328, "step": 225130 }, { "epoch": 1.3382789141121434, "grad_norm": 1.535420298576355, "learning_rate": 0.00014193315342025047, "loss": 0.6282715320587158, "step": 225140 }, { "epoch": 1.3383383561888118, "grad_norm": 1.5516518354415894, "learning_rate": 0.00014192733357449975, "loss": 0.600438404083252, "step": 225150 }, { "epoch": 1.3383977982654802, "grad_norm": 1.6540429592132568, "learning_rate": 0.00014192151357601907, "loss": 0.6152238368988037, "step": 225160 }, { "epoch": 1.3384572403421486, "grad_norm": 1.6928188800811768, "learning_rate": 0.0001419156934248363, "loss": 0.6707432746887207, "step": 225170 }, { "epoch": 1.338516682418817, "grad_norm": 1.8760493993759155, "learning_rate": 0.0001419098731209793, "loss": 0.5869914054870605, "step": 225180 }, { "epoch": 1.3385761244954852, "grad_norm": 2.372206687927246, "learning_rate": 0.00014190405266447588, "loss": 0.617704439163208, "step": 225190 }, { "epoch": 1.3386355665721537, "grad_norm": 1.5927377939224243, "learning_rate": 0.00014189823205535388, "loss": 0.5960698127746582, "step": 225200 }, { "epoch": 1.338695008648822, "grad_norm": 1.6179119348526, "learning_rate": 0.00014189241129364122, "loss": 0.5577899932861328, "step": 225210 }, { "epoch": 1.3387544507254905, "grad_norm": 1.560114860534668, "learning_rate": 0.00014188659037936562, "loss": 0.5719005107879639, "step": 225220 }, { "epoch": 1.338813892802159, "grad_norm": 1.734380841255188, "learning_rate": 0.00014188076931255506, "loss": 0.5474798202514648, "step": 225230 }, { "epoch": 1.3388733348788273, "grad_norm": 1.4888375997543335, "learning_rate": 0.00014187494809323728, "loss": 0.6055105209350586, "step": 225240 }, { "epoch": 1.3389327769554957, "grad_norm": 1.4833203554153442, "learning_rate": 0.00014186912672144012, "loss": 0.6516662120819092, "step": 225250 }, { "epoch": 1.3389922190321641, "grad_norm": 1.635329246520996, "learning_rate": 0.00014186330519719154, "loss": 0.6387776374816895, "step": 225260 }, { "epoch": 1.3390516611088326, "grad_norm": 1.593279242515564, "learning_rate": 0.0001418574835205193, "loss": 0.6227335929870605, "step": 225270 }, { "epoch": 1.339111103185501, "grad_norm": 2.0533952713012695, "learning_rate": 0.00014185166169145127, "loss": 0.6153565883636475, "step": 225280 }, { "epoch": 1.3391705452621694, "grad_norm": 1.6073030233383179, "learning_rate": 0.00014184583971001532, "loss": 0.6393056869506836, "step": 225290 }, { "epoch": 1.3392299873388378, "grad_norm": 1.809658408164978, "learning_rate": 0.00014184001757623925, "loss": 0.6185413360595703, "step": 225300 }, { "epoch": 1.339289429415506, "grad_norm": 1.5604032278060913, "learning_rate": 0.00014183419529015094, "loss": 0.569705581665039, "step": 225310 }, { "epoch": 1.3393488714921744, "grad_norm": 1.6076550483703613, "learning_rate": 0.00014182837285177825, "loss": 0.5521716594696044, "step": 225320 }, { "epoch": 1.3394083135688428, "grad_norm": 1.5535283088684082, "learning_rate": 0.00014182255026114904, "loss": 0.5599167823791504, "step": 225330 }, { "epoch": 1.3394677556455112, "grad_norm": 2.070181369781494, "learning_rate": 0.00014181672751829115, "loss": 0.5474782466888428, "step": 225340 }, { "epoch": 1.3395271977221797, "grad_norm": 1.0866212844848633, "learning_rate": 0.0001418109046232324, "loss": 0.5840677261352539, "step": 225350 }, { "epoch": 1.339586639798848, "grad_norm": 1.6055551767349243, "learning_rate": 0.0001418050815760007, "loss": 0.6200160980224609, "step": 225360 }, { "epoch": 1.3396460818755165, "grad_norm": 1.4161770343780518, "learning_rate": 0.00014179925837662388, "loss": 0.6308817863464355, "step": 225370 }, { "epoch": 1.3397055239521847, "grad_norm": 1.3267780542373657, "learning_rate": 0.00014179343502512977, "loss": 0.5702166557312012, "step": 225380 }, { "epoch": 1.339764966028853, "grad_norm": 1.770098090171814, "learning_rate": 0.00014178761152154634, "loss": 0.6386007308959961, "step": 225390 }, { "epoch": 1.3398244081055215, "grad_norm": 1.6279247999191284, "learning_rate": 0.0001417817878659013, "loss": 0.5781740188598633, "step": 225400 }, { "epoch": 1.33988385018219, "grad_norm": 1.5994350910186768, "learning_rate": 0.0001417759640582226, "loss": 0.5982696533203125, "step": 225410 }, { "epoch": 1.3399432922588583, "grad_norm": 1.5264092683792114, "learning_rate": 0.0001417701400985381, "loss": 0.5918281555175782, "step": 225420 }, { "epoch": 1.3400027343355267, "grad_norm": 1.5089445114135742, "learning_rate": 0.00014176431598687553, "loss": 0.5452446460723877, "step": 225430 }, { "epoch": 1.3400621764121952, "grad_norm": 1.5400992631912231, "learning_rate": 0.00014175849172326293, "loss": 0.657494592666626, "step": 225440 }, { "epoch": 1.3401216184888636, "grad_norm": 1.6191821098327637, "learning_rate": 0.00014175266730772807, "loss": 0.5976530551910401, "step": 225450 }, { "epoch": 1.340181060565532, "grad_norm": 1.4214686155319214, "learning_rate": 0.00014174684274029885, "loss": 0.6376317977905274, "step": 225460 }, { "epoch": 1.3402405026422004, "grad_norm": 1.4114001989364624, "learning_rate": 0.00014174101802100306, "loss": 0.5719053745269775, "step": 225470 }, { "epoch": 1.3402999447188688, "grad_norm": 1.580350399017334, "learning_rate": 0.00014173519314986864, "loss": 0.5981428146362304, "step": 225480 }, { "epoch": 1.340359386795537, "grad_norm": 1.3094874620437622, "learning_rate": 0.00014172936812692345, "loss": 0.5931966781616211, "step": 225490 }, { "epoch": 1.3404188288722054, "grad_norm": 1.6998320817947388, "learning_rate": 0.0001417235429521953, "loss": 0.574463939666748, "step": 225500 }, { "epoch": 1.3404782709488738, "grad_norm": 1.6664294004440308, "learning_rate": 0.00014171771762571208, "loss": 0.6520447731018066, "step": 225510 }, { "epoch": 1.3405377130255423, "grad_norm": 2.560011148452759, "learning_rate": 0.00014171189214750172, "loss": 0.6299343585968018, "step": 225520 }, { "epoch": 1.3405971551022107, "grad_norm": 1.7808730602264404, "learning_rate": 0.00014170606651759196, "loss": 0.5964373588562012, "step": 225530 }, { "epoch": 1.340656597178879, "grad_norm": 1.3551033735275269, "learning_rate": 0.00014170024073601077, "loss": 0.6177994728088378, "step": 225540 }, { "epoch": 1.3407160392555475, "grad_norm": 1.8376007080078125, "learning_rate": 0.000141694414802786, "loss": 0.600827407836914, "step": 225550 }, { "epoch": 1.3407754813322157, "grad_norm": 1.5736254453659058, "learning_rate": 0.0001416885887179455, "loss": 0.6224853515625, "step": 225560 }, { "epoch": 1.340834923408884, "grad_norm": 1.7699036598205566, "learning_rate": 0.00014168276248151712, "loss": 0.6324903011322022, "step": 225570 }, { "epoch": 1.3408943654855525, "grad_norm": 1.5003890991210938, "learning_rate": 0.0001416769360935288, "loss": 0.5431293964385986, "step": 225580 }, { "epoch": 1.340953807562221, "grad_norm": 1.8417280912399292, "learning_rate": 0.00014167110955400837, "loss": 0.5464111328125, "step": 225590 }, { "epoch": 1.3410132496388893, "grad_norm": 1.7262581586837769, "learning_rate": 0.00014166528286298365, "loss": 0.5855401039123536, "step": 225600 }, { "epoch": 1.3410726917155578, "grad_norm": 1.8953450918197632, "learning_rate": 0.00014165945602048264, "loss": 0.6046878337860108, "step": 225610 }, { "epoch": 1.3411321337922262, "grad_norm": 1.3243684768676758, "learning_rate": 0.00014165362902653308, "loss": 0.6277114868164062, "step": 225620 }, { "epoch": 1.3411915758688946, "grad_norm": 1.3919404745101929, "learning_rate": 0.00014164780188116293, "loss": 0.610963249206543, "step": 225630 }, { "epoch": 1.341251017945563, "grad_norm": 1.5124298334121704, "learning_rate": 0.00014164197458440005, "loss": 0.5354877948760987, "step": 225640 }, { "epoch": 1.3413104600222314, "grad_norm": 1.4074057340621948, "learning_rate": 0.00014163614713627227, "loss": 0.6124953269958496, "step": 225650 }, { "epoch": 1.3413699020988998, "grad_norm": 1.4570845365524292, "learning_rate": 0.00014163031953680753, "loss": 0.6546120643615723, "step": 225660 }, { "epoch": 1.3414293441755683, "grad_norm": 1.5914908647537231, "learning_rate": 0.00014162449178603366, "loss": 0.5698030948638916, "step": 225670 }, { "epoch": 1.3414887862522364, "grad_norm": 1.6791880130767822, "learning_rate": 0.00014161866388397856, "loss": 0.5977611064910888, "step": 225680 }, { "epoch": 1.3415482283289049, "grad_norm": 1.5010461807250977, "learning_rate": 0.00014161283583067008, "loss": 0.6162961959838867, "step": 225690 }, { "epoch": 1.3416076704055733, "grad_norm": 1.1947047710418701, "learning_rate": 0.00014160700762613616, "loss": 0.5629911422729492, "step": 225700 }, { "epoch": 1.3416671124822417, "grad_norm": 1.517342448234558, "learning_rate": 0.00014160117927040463, "loss": 0.5364598274230957, "step": 225710 }, { "epoch": 1.34172655455891, "grad_norm": 1.5568039417266846, "learning_rate": 0.00014159535076350342, "loss": 0.5661965370178222, "step": 225720 }, { "epoch": 1.3417859966355785, "grad_norm": 1.4167392253875732, "learning_rate": 0.00014158952210546034, "loss": 0.5582290649414062, "step": 225730 }, { "epoch": 1.341845438712247, "grad_norm": 1.6760793924331665, "learning_rate": 0.0001415836932963033, "loss": 0.5568720817565918, "step": 225740 }, { "epoch": 1.3419048807889151, "grad_norm": 1.5843451023101807, "learning_rate": 0.0001415778643360602, "loss": 0.5279681205749511, "step": 225750 }, { "epoch": 1.3419643228655835, "grad_norm": 1.5949618816375732, "learning_rate": 0.00014157203522475895, "loss": 0.6056529998779296, "step": 225760 }, { "epoch": 1.342023764942252, "grad_norm": 1.4759960174560547, "learning_rate": 0.0001415662059624274, "loss": 0.5947407722473145, "step": 225770 }, { "epoch": 1.3420832070189204, "grad_norm": 1.6822352409362793, "learning_rate": 0.00014156037654909339, "loss": 0.5762730598449707, "step": 225780 }, { "epoch": 1.3421426490955888, "grad_norm": 1.9185835123062134, "learning_rate": 0.0001415545469847849, "loss": 0.6049000263214112, "step": 225790 }, { "epoch": 1.3422020911722572, "grad_norm": 1.5438292026519775, "learning_rate": 0.00014154871726952973, "loss": 0.5790344715118408, "step": 225800 }, { "epoch": 1.3422615332489256, "grad_norm": 1.424390435218811, "learning_rate": 0.00014154288740335583, "loss": 0.572900915145874, "step": 225810 }, { "epoch": 1.342320975325594, "grad_norm": 1.558830976486206, "learning_rate": 0.00014153705738629107, "loss": 0.6604486465454101, "step": 225820 }, { "epoch": 1.3423804174022624, "grad_norm": 1.3616580963134766, "learning_rate": 0.00014153122721836332, "loss": 0.5803758144378662, "step": 225830 }, { "epoch": 1.3424398594789309, "grad_norm": 1.8023719787597656, "learning_rate": 0.0001415253968996005, "loss": 0.5840178489685058, "step": 225840 }, { "epoch": 1.3424993015555993, "grad_norm": 1.6608572006225586, "learning_rate": 0.00014151956643003045, "loss": 0.6196208953857422, "step": 225850 }, { "epoch": 1.3425587436322675, "grad_norm": 1.6912336349487305, "learning_rate": 0.00014151373580968113, "loss": 0.619538688659668, "step": 225860 }, { "epoch": 1.3426181857089359, "grad_norm": 1.875267744064331, "learning_rate": 0.00014150790503858037, "loss": 0.5955307960510254, "step": 225870 }, { "epoch": 1.3426776277856043, "grad_norm": 1.6075938940048218, "learning_rate": 0.0001415020741167561, "loss": 0.6633340835571289, "step": 225880 }, { "epoch": 1.3427370698622727, "grad_norm": 1.448083519935608, "learning_rate": 0.0001414962430442362, "loss": 0.5756774425506592, "step": 225890 }, { "epoch": 1.3427965119389411, "grad_norm": 1.4391592741012573, "learning_rate": 0.0001414904118210486, "loss": 0.5628591060638428, "step": 225900 }, { "epoch": 1.3428559540156095, "grad_norm": 1.6789655685424805, "learning_rate": 0.00014148458044722112, "loss": 0.6096151828765869, "step": 225910 }, { "epoch": 1.342915396092278, "grad_norm": 1.5619927644729614, "learning_rate": 0.0001414787489227817, "loss": 0.5780436038970947, "step": 225920 }, { "epoch": 1.3429748381689461, "grad_norm": 1.743774652481079, "learning_rate": 0.00014147291724775826, "loss": 0.5829419136047364, "step": 225930 }, { "epoch": 1.3430342802456146, "grad_norm": 1.2040507793426514, "learning_rate": 0.00014146708542217865, "loss": 0.5744441032409668, "step": 225940 }, { "epoch": 1.343093722322283, "grad_norm": 1.7376168966293335, "learning_rate": 0.0001414612534460708, "loss": 0.6260798454284668, "step": 225950 }, { "epoch": 1.3431531643989514, "grad_norm": 1.5673123598098755, "learning_rate": 0.00014145542131946257, "loss": 0.5948610305786133, "step": 225960 }, { "epoch": 1.3432126064756198, "grad_norm": 1.6066160202026367, "learning_rate": 0.00014144958904238188, "loss": 0.5483322143554688, "step": 225970 }, { "epoch": 1.3432720485522882, "grad_norm": 1.982471227645874, "learning_rate": 0.00014144375661485667, "loss": 0.6097017288208008, "step": 225980 }, { "epoch": 1.3433314906289566, "grad_norm": 1.604076862335205, "learning_rate": 0.00014143792403691476, "loss": 0.6246062278747558, "step": 225990 }, { "epoch": 1.343390932705625, "grad_norm": 1.4059545993804932, "learning_rate": 0.00014143209130858416, "loss": 0.6035775661468505, "step": 226000 }, { "epoch": 1.3434503747822935, "grad_norm": 1.1705679893493652, "learning_rate": 0.00014142625842989266, "loss": 0.6245304107666015, "step": 226010 }, { "epoch": 1.3435098168589619, "grad_norm": 1.8535504341125488, "learning_rate": 0.00014142042540086816, "loss": 0.5975755214691162, "step": 226020 }, { "epoch": 1.3435692589356303, "grad_norm": 1.753462314605713, "learning_rate": 0.0001414145922215387, "loss": 0.5960846424102784, "step": 226030 }, { "epoch": 1.3436287010122987, "grad_norm": 1.9110708236694336, "learning_rate": 0.00014140875889193208, "loss": 0.6320105075836182, "step": 226040 }, { "epoch": 1.343688143088967, "grad_norm": 1.8469350337982178, "learning_rate": 0.0001414029254120762, "loss": 0.6076351165771484, "step": 226050 }, { "epoch": 1.3437475851656353, "grad_norm": 1.574052333831787, "learning_rate": 0.000141397091781999, "loss": 0.6216697692871094, "step": 226060 }, { "epoch": 1.3438070272423037, "grad_norm": 1.6127607822418213, "learning_rate": 0.0001413912580017284, "loss": 0.5668683528900147, "step": 226070 }, { "epoch": 1.3438664693189721, "grad_norm": 1.8305267095565796, "learning_rate": 0.00014138542407129222, "loss": 0.6050187110900879, "step": 226080 }, { "epoch": 1.3439259113956405, "grad_norm": 1.595975637435913, "learning_rate": 0.00014137958999071846, "loss": 0.6347943305969238, "step": 226090 }, { "epoch": 1.343985353472309, "grad_norm": 1.6120673418045044, "learning_rate": 0.000141373755760035, "loss": 0.5799920082092285, "step": 226100 }, { "epoch": 1.3440447955489774, "grad_norm": 1.3836897611618042, "learning_rate": 0.00014136792137926975, "loss": 0.6060297966003418, "step": 226110 }, { "epoch": 1.3441042376256456, "grad_norm": 1.3487763404846191, "learning_rate": 0.00014136208684845057, "loss": 0.611044979095459, "step": 226120 }, { "epoch": 1.344163679702314, "grad_norm": 1.3553624153137207, "learning_rate": 0.00014135625216760552, "loss": 0.6580010890960694, "step": 226130 }, { "epoch": 1.3442231217789824, "grad_norm": 1.6463712453842163, "learning_rate": 0.0001413504173367623, "loss": 0.6067756652832031, "step": 226140 }, { "epoch": 1.3442825638556508, "grad_norm": 1.5100311040878296, "learning_rate": 0.00014134458235594895, "loss": 0.677246379852295, "step": 226150 }, { "epoch": 1.3443420059323192, "grad_norm": 1.3192284107208252, "learning_rate": 0.0001413387472251934, "loss": 0.5882487773895264, "step": 226160 }, { "epoch": 1.3444014480089876, "grad_norm": 1.12544584274292, "learning_rate": 0.00014133291194452349, "loss": 0.5739392280578614, "step": 226170 }, { "epoch": 1.344460890085656, "grad_norm": 1.8303561210632324, "learning_rate": 0.00014132707651396718, "loss": 0.5836348056793212, "step": 226180 }, { "epoch": 1.3445203321623245, "grad_norm": 1.420491099357605, "learning_rate": 0.0001413212409335524, "loss": 0.5909639835357666, "step": 226190 }, { "epoch": 1.3445797742389929, "grad_norm": 1.3802872896194458, "learning_rate": 0.000141315405203307, "loss": 0.5831831455230713, "step": 226200 }, { "epoch": 1.3446392163156613, "grad_norm": 1.4598023891448975, "learning_rate": 0.00014130956932325897, "loss": 0.5666871070861816, "step": 226210 }, { "epoch": 1.3446986583923297, "grad_norm": 1.678116798400879, "learning_rate": 0.00014130373329343618, "loss": 0.6407424926757812, "step": 226220 }, { "epoch": 1.344758100468998, "grad_norm": 1.5361578464508057, "learning_rate": 0.00014129789711386654, "loss": 0.6018115520477295, "step": 226230 }, { "epoch": 1.3448175425456663, "grad_norm": 1.4161715507507324, "learning_rate": 0.000141292060784578, "loss": 0.6436216831207275, "step": 226240 }, { "epoch": 1.3448769846223347, "grad_norm": 1.1592724323272705, "learning_rate": 0.00014128622430559847, "loss": 0.5892319202423095, "step": 226250 }, { "epoch": 1.3449364266990032, "grad_norm": 1.5649710893630981, "learning_rate": 0.0001412803876769559, "loss": 0.6416166305541993, "step": 226260 }, { "epoch": 1.3449958687756716, "grad_norm": 1.653531789779663, "learning_rate": 0.00014127455089867812, "loss": 0.6063737869262695, "step": 226270 }, { "epoch": 1.34505531085234, "grad_norm": 1.6116400957107544, "learning_rate": 0.00014126871397079313, "loss": 0.5671519279479981, "step": 226280 }, { "epoch": 1.3451147529290084, "grad_norm": 2.090193033218384, "learning_rate": 0.00014126287689332885, "loss": 0.5843191146850586, "step": 226290 }, { "epoch": 1.3451741950056766, "grad_norm": 1.6977102756500244, "learning_rate": 0.00014125703966631317, "loss": 0.6541004180908203, "step": 226300 }, { "epoch": 1.345233637082345, "grad_norm": 1.7172720432281494, "learning_rate": 0.00014125120228977402, "loss": 0.5651003360748291, "step": 226310 }, { "epoch": 1.3452930791590134, "grad_norm": 1.7333250045776367, "learning_rate": 0.00014124536476373933, "loss": 0.5758852958679199, "step": 226320 }, { "epoch": 1.3453525212356818, "grad_norm": 1.8561547994613647, "learning_rate": 0.00014123952708823705, "loss": 0.5554081916809082, "step": 226330 }, { "epoch": 1.3454119633123502, "grad_norm": 1.3928532600402832, "learning_rate": 0.00014123368926329506, "loss": 0.6137666225433349, "step": 226340 }, { "epoch": 1.3454714053890187, "grad_norm": 1.5425623655319214, "learning_rate": 0.00014122785128894128, "loss": 0.5574539184570313, "step": 226350 }, { "epoch": 1.345530847465687, "grad_norm": 1.4252833127975464, "learning_rate": 0.00014122201316520372, "loss": 0.5766583919525147, "step": 226360 }, { "epoch": 1.3455902895423555, "grad_norm": 1.4949924945831299, "learning_rate": 0.00014121617489211023, "loss": 0.6010702133178711, "step": 226370 }, { "epoch": 1.345649731619024, "grad_norm": 1.7571214437484741, "learning_rate": 0.00014121033646968877, "loss": 0.579417371749878, "step": 226380 }, { "epoch": 1.3457091736956923, "grad_norm": 1.260180950164795, "learning_rate": 0.00014120449789796727, "loss": 0.5408688068389893, "step": 226390 }, { "epoch": 1.3457686157723607, "grad_norm": 1.484298586845398, "learning_rate": 0.0001411986591769736, "loss": 0.6059042453765869, "step": 226400 }, { "epoch": 1.3458280578490291, "grad_norm": 1.6557221412658691, "learning_rate": 0.00014119282030673579, "loss": 0.6138273239135742, "step": 226410 }, { "epoch": 1.3458874999256973, "grad_norm": 1.4396682977676392, "learning_rate": 0.00014118698128728172, "loss": 0.5789891242980957, "step": 226420 }, { "epoch": 1.3459469420023658, "grad_norm": 1.440325379371643, "learning_rate": 0.00014118114211863927, "loss": 0.5883246898651123, "step": 226430 }, { "epoch": 1.3460063840790342, "grad_norm": 1.8573774099349976, "learning_rate": 0.0001411753028008365, "loss": 0.606854772567749, "step": 226440 }, { "epoch": 1.3460658261557026, "grad_norm": 1.4605480432510376, "learning_rate": 0.0001411694633339012, "loss": 0.6319039344787598, "step": 226450 }, { "epoch": 1.346125268232371, "grad_norm": 1.4383471012115479, "learning_rate": 0.0001411636237178614, "loss": 0.5742907524108887, "step": 226460 }, { "epoch": 1.3461847103090394, "grad_norm": 1.3583976030349731, "learning_rate": 0.00014115778395274505, "loss": 0.6153527736663819, "step": 226470 }, { "epoch": 1.3462441523857078, "grad_norm": 1.462522029876709, "learning_rate": 0.00014115194403857998, "loss": 0.6357117176055909, "step": 226480 }, { "epoch": 1.346303594462376, "grad_norm": 1.589334487915039, "learning_rate": 0.00014114610397539422, "loss": 0.5762152671813965, "step": 226490 }, { "epoch": 1.3463630365390444, "grad_norm": 1.1082367897033691, "learning_rate": 0.0001411402637632157, "loss": 0.5410459995269775, "step": 226500 }, { "epoch": 1.3464224786157128, "grad_norm": 1.5754969120025635, "learning_rate": 0.0001411344234020723, "loss": 0.5751118659973145, "step": 226510 }, { "epoch": 1.3464819206923813, "grad_norm": 1.4609655141830444, "learning_rate": 0.000141128582891992, "loss": 0.6054365158081054, "step": 226520 }, { "epoch": 1.3465413627690497, "grad_norm": 1.3346840143203735, "learning_rate": 0.00014112274223300274, "loss": 0.5814616680145264, "step": 226530 }, { "epoch": 1.346600804845718, "grad_norm": 1.1867798566818237, "learning_rate": 0.00014111690142513245, "loss": 0.5130399703979492, "step": 226540 }, { "epoch": 1.3466602469223865, "grad_norm": 1.3845949172973633, "learning_rate": 0.00014111106046840909, "loss": 0.6271143913269043, "step": 226550 }, { "epoch": 1.346719688999055, "grad_norm": 1.502727746963501, "learning_rate": 0.00014110521936286057, "loss": 0.6425002098083497, "step": 226560 }, { "epoch": 1.3467791310757233, "grad_norm": 1.5832033157348633, "learning_rate": 0.00014109937810851485, "loss": 0.637654161453247, "step": 226570 }, { "epoch": 1.3468385731523917, "grad_norm": 1.3402810096740723, "learning_rate": 0.0001410935367053998, "loss": 0.5480245590209961, "step": 226580 }, { "epoch": 1.3468980152290602, "grad_norm": 1.8577821254730225, "learning_rate": 0.00014108769515354353, "loss": 0.6144087791442872, "step": 226590 }, { "epoch": 1.3469574573057284, "grad_norm": 1.8597915172576904, "learning_rate": 0.00014108185345297386, "loss": 0.6356846809387207, "step": 226600 }, { "epoch": 1.3470168993823968, "grad_norm": 1.3739206790924072, "learning_rate": 0.00014107601160371876, "loss": 0.587571096420288, "step": 226610 }, { "epoch": 1.3470763414590652, "grad_norm": 1.71048104763031, "learning_rate": 0.00014107016960580615, "loss": 0.5590453147888184, "step": 226620 }, { "epoch": 1.3471357835357336, "grad_norm": 1.5742236375808716, "learning_rate": 0.000141064327459264, "loss": 0.6451292514801026, "step": 226630 }, { "epoch": 1.347195225612402, "grad_norm": 1.5660672187805176, "learning_rate": 0.00014105848516412028, "loss": 0.6386038780212402, "step": 226640 }, { "epoch": 1.3472546676890704, "grad_norm": 1.382441520690918, "learning_rate": 0.00014105264272040293, "loss": 0.5917394161224365, "step": 226650 }, { "epoch": 1.3473141097657388, "grad_norm": 1.3421088457107544, "learning_rate": 0.00014104680012813986, "loss": 0.6061584949493408, "step": 226660 }, { "epoch": 1.347373551842407, "grad_norm": 1.2062276601791382, "learning_rate": 0.00014104095738735908, "loss": 0.5871289253234864, "step": 226670 }, { "epoch": 1.3474329939190755, "grad_norm": 1.4252712726593018, "learning_rate": 0.00014103511449808847, "loss": 0.6058337688446045, "step": 226680 }, { "epoch": 1.3474924359957439, "grad_norm": 1.3513818979263306, "learning_rate": 0.000141029271460356, "loss": 0.5251548290252686, "step": 226690 }, { "epoch": 1.3475518780724123, "grad_norm": 1.4078876972198486, "learning_rate": 0.00014102342827418968, "loss": 0.6002238750457763, "step": 226700 }, { "epoch": 1.3476113201490807, "grad_norm": 1.6364772319793701, "learning_rate": 0.0001410175849396174, "loss": 0.5667678833007812, "step": 226710 }, { "epoch": 1.347670762225749, "grad_norm": 1.45405912399292, "learning_rate": 0.0001410117414566671, "loss": 0.5841959953308106, "step": 226720 }, { "epoch": 1.3477302043024175, "grad_norm": 1.5644667148590088, "learning_rate": 0.0001410058978253668, "loss": 0.5803988456726075, "step": 226730 }, { "epoch": 1.347789646379086, "grad_norm": 1.6095943450927734, "learning_rate": 0.0001410000540457444, "loss": 0.6044292449951172, "step": 226740 }, { "epoch": 1.3478490884557544, "grad_norm": 1.8146171569824219, "learning_rate": 0.0001409942101178279, "loss": 0.6018235206604003, "step": 226750 }, { "epoch": 1.3479085305324228, "grad_norm": 1.9080379009246826, "learning_rate": 0.00014098836604164517, "loss": 0.6141988277435303, "step": 226760 }, { "epoch": 1.3479679726090912, "grad_norm": 1.7631927728652954, "learning_rate": 0.00014098252181722428, "loss": 0.6019767761230469, "step": 226770 }, { "epoch": 1.3480274146857596, "grad_norm": 1.5149081945419312, "learning_rate": 0.00014097667744459314, "loss": 0.6097146987915039, "step": 226780 }, { "epoch": 1.3480868567624278, "grad_norm": 1.7604427337646484, "learning_rate": 0.00014097083292377964, "loss": 0.5989439964294434, "step": 226790 }, { "epoch": 1.3481462988390962, "grad_norm": 1.5194278955459595, "learning_rate": 0.00014096498825481185, "loss": 0.6045644760131836, "step": 226800 }, { "epoch": 1.3482057409157646, "grad_norm": 1.4232949018478394, "learning_rate": 0.00014095914343771767, "loss": 0.5461643218994141, "step": 226810 }, { "epoch": 1.348265182992433, "grad_norm": 1.531923532485962, "learning_rate": 0.00014095329847252502, "loss": 0.5908559799194336, "step": 226820 }, { "epoch": 1.3483246250691014, "grad_norm": 2.021380662918091, "learning_rate": 0.00014094745335926193, "loss": 0.7083361625671387, "step": 226830 }, { "epoch": 1.3483840671457699, "grad_norm": 1.364249587059021, "learning_rate": 0.00014094160809795633, "loss": 0.6026001930236816, "step": 226840 }, { "epoch": 1.3484435092224383, "grad_norm": 1.5082345008850098, "learning_rate": 0.0001409357626886362, "loss": 0.6121867179870606, "step": 226850 }, { "epoch": 1.3485029512991065, "grad_norm": 1.317981481552124, "learning_rate": 0.0001409299171313295, "loss": 0.5777820587158203, "step": 226860 }, { "epoch": 1.3485623933757749, "grad_norm": 1.654050350189209, "learning_rate": 0.00014092407142606418, "loss": 0.6214899063110352, "step": 226870 }, { "epoch": 1.3486218354524433, "grad_norm": 1.5121361017227173, "learning_rate": 0.0001409182255728682, "loss": 0.5830848217010498, "step": 226880 }, { "epoch": 1.3486812775291117, "grad_norm": 1.623844027519226, "learning_rate": 0.00014091237957176953, "loss": 0.6214706420898437, "step": 226890 }, { "epoch": 1.3487407196057801, "grad_norm": 1.3920037746429443, "learning_rate": 0.00014090653342279616, "loss": 0.5689779758453369, "step": 226900 }, { "epoch": 1.3488001616824485, "grad_norm": 1.3527806997299194, "learning_rate": 0.00014090068712597603, "loss": 0.5806849956512451, "step": 226910 }, { "epoch": 1.348859603759117, "grad_norm": 1.6560102701187134, "learning_rate": 0.0001408948406813371, "loss": 0.6748292922973633, "step": 226920 }, { "epoch": 1.3489190458357854, "grad_norm": 1.6941325664520264, "learning_rate": 0.00014088899408890734, "loss": 0.6110261917114258, "step": 226930 }, { "epoch": 1.3489784879124538, "grad_norm": 1.2059189081192017, "learning_rate": 0.00014088314734871473, "loss": 0.5922242164611816, "step": 226940 }, { "epoch": 1.3490379299891222, "grad_norm": 1.5179293155670166, "learning_rate": 0.00014087730046078725, "loss": 0.5926812648773193, "step": 226950 }, { "epoch": 1.3490973720657906, "grad_norm": 1.5466710329055786, "learning_rate": 0.00014087145342515288, "loss": 0.6617726802825927, "step": 226960 }, { "epoch": 1.3491568141424588, "grad_norm": 1.4823271036148071, "learning_rate": 0.0001408656062418395, "loss": 0.5572448253631592, "step": 226970 }, { "epoch": 1.3492162562191272, "grad_norm": 1.4801065921783447, "learning_rate": 0.00014085975891087518, "loss": 0.5333539009094238, "step": 226980 }, { "epoch": 1.3492756982957956, "grad_norm": 1.630829095840454, "learning_rate": 0.00014085391143228788, "loss": 0.6393319129943847, "step": 226990 }, { "epoch": 1.349335140372464, "grad_norm": 1.8021090030670166, "learning_rate": 0.0001408480638061055, "loss": 0.5755784988403321, "step": 227000 }, { "epoch": 1.3493945824491325, "grad_norm": 1.5155372619628906, "learning_rate": 0.0001408422160323561, "loss": 0.6212048053741455, "step": 227010 }, { "epoch": 1.3494540245258009, "grad_norm": 1.6379849910736084, "learning_rate": 0.00014083636811106762, "loss": 0.6019529819488525, "step": 227020 }, { "epoch": 1.3495134666024693, "grad_norm": 1.1076023578643799, "learning_rate": 0.00014083052004226803, "loss": 0.6647838592529297, "step": 227030 }, { "epoch": 1.3495729086791375, "grad_norm": 1.2925362586975098, "learning_rate": 0.0001408246718259853, "loss": 0.5984263896942139, "step": 227040 }, { "epoch": 1.349632350755806, "grad_norm": 1.6111948490142822, "learning_rate": 0.0001408188234622474, "loss": 0.5624067306518554, "step": 227050 }, { "epoch": 1.3496917928324743, "grad_norm": 1.5570011138916016, "learning_rate": 0.00014081297495108236, "loss": 0.6185105800628662, "step": 227060 }, { "epoch": 1.3497512349091427, "grad_norm": 1.615587592124939, "learning_rate": 0.00014080712629251806, "loss": 0.5876439094543457, "step": 227070 }, { "epoch": 1.3498106769858111, "grad_norm": 2.113524913787842, "learning_rate": 0.0001408012774865826, "loss": 0.6343982696533204, "step": 227080 }, { "epoch": 1.3498701190624796, "grad_norm": 1.614499568939209, "learning_rate": 0.00014079542853330388, "loss": 0.5768511772155762, "step": 227090 }, { "epoch": 1.349929561139148, "grad_norm": 1.5265601873397827, "learning_rate": 0.00014078957943270984, "loss": 0.6263908863067627, "step": 227100 }, { "epoch": 1.3499890032158164, "grad_norm": 1.606398105621338, "learning_rate": 0.00014078373018482855, "loss": 0.574073314666748, "step": 227110 }, { "epoch": 1.3500484452924848, "grad_norm": 1.6744483709335327, "learning_rate": 0.00014077788078968798, "loss": 0.6095901012420655, "step": 227120 }, { "epoch": 1.3501078873691532, "grad_norm": 1.68317449092865, "learning_rate": 0.00014077203124731607, "loss": 0.610166072845459, "step": 227130 }, { "epoch": 1.3501673294458216, "grad_norm": 1.6645337343215942, "learning_rate": 0.0001407661815577408, "loss": 0.5771000862121582, "step": 227140 }, { "epoch": 1.35022677152249, "grad_norm": 1.7956758737564087, "learning_rate": 0.00014076033172099017, "loss": 0.5664974689483643, "step": 227150 }, { "epoch": 1.3502862135991582, "grad_norm": 1.6626070737838745, "learning_rate": 0.0001407544817370922, "loss": 0.5950113773345947, "step": 227160 }, { "epoch": 1.3503456556758267, "grad_norm": 1.6439027786254883, "learning_rate": 0.00014074863160607482, "loss": 0.6102072238922119, "step": 227170 }, { "epoch": 1.350405097752495, "grad_norm": 1.9298089742660522, "learning_rate": 0.00014074278132796605, "loss": 0.6247758865356445, "step": 227180 }, { "epoch": 1.3504645398291635, "grad_norm": 1.8111262321472168, "learning_rate": 0.00014073693090279382, "loss": 0.5667246818542481, "step": 227190 }, { "epoch": 1.350523981905832, "grad_norm": 1.534589409828186, "learning_rate": 0.00014073108033058618, "loss": 0.6158030986785888, "step": 227200 }, { "epoch": 1.3505834239825003, "grad_norm": 1.2325685024261475, "learning_rate": 0.0001407252296113711, "loss": 0.5904598236083984, "step": 227210 }, { "epoch": 1.3506428660591687, "grad_norm": 1.5768835544586182, "learning_rate": 0.00014071937874517658, "loss": 0.5664620399475098, "step": 227220 }, { "epoch": 1.350702308135837, "grad_norm": 1.5473276376724243, "learning_rate": 0.00014071352773203057, "loss": 0.5521932601928711, "step": 227230 }, { "epoch": 1.3507617502125053, "grad_norm": 1.6730201244354248, "learning_rate": 0.0001407076765719611, "loss": 0.5956973075866699, "step": 227240 }, { "epoch": 1.3508211922891737, "grad_norm": 1.7540632486343384, "learning_rate": 0.0001407018252649961, "loss": 0.637536096572876, "step": 227250 }, { "epoch": 1.3508806343658422, "grad_norm": 1.7778114080429077, "learning_rate": 0.0001406959738111636, "loss": 0.6131232738494873, "step": 227260 }, { "epoch": 1.3509400764425106, "grad_norm": 1.5560230016708374, "learning_rate": 0.00014069012221049166, "loss": 0.5832237243652344, "step": 227270 }, { "epoch": 1.350999518519179, "grad_norm": 1.2793049812316895, "learning_rate": 0.00014068427046300813, "loss": 0.6011101722717285, "step": 227280 }, { "epoch": 1.3510589605958474, "grad_norm": 1.5519789457321167, "learning_rate": 0.00014067841856874112, "loss": 0.5691225051879882, "step": 227290 }, { "epoch": 1.3511184026725158, "grad_norm": 1.7862340211868286, "learning_rate": 0.0001406725665277186, "loss": 0.6215424060821533, "step": 227300 }, { "epoch": 1.3511778447491842, "grad_norm": 1.435366153717041, "learning_rate": 0.00014066671433996848, "loss": 0.6324787139892578, "step": 227310 }, { "epoch": 1.3512372868258526, "grad_norm": 1.789823055267334, "learning_rate": 0.00014066086200551886, "loss": 0.6760970115661621, "step": 227320 }, { "epoch": 1.351296728902521, "grad_norm": 1.4197107553482056, "learning_rate": 0.00014065500952439768, "loss": 0.5953572750091553, "step": 227330 }, { "epoch": 1.3513561709791893, "grad_norm": 1.5754783153533936, "learning_rate": 0.00014064915689663302, "loss": 0.621499490737915, "step": 227340 }, { "epoch": 1.3514156130558577, "grad_norm": 1.7451846599578857, "learning_rate": 0.00014064330412225272, "loss": 0.5871241092681885, "step": 227350 }, { "epoch": 1.351475055132526, "grad_norm": 1.5685241222381592, "learning_rate": 0.0001406374512012849, "loss": 0.5655499458312988, "step": 227360 }, { "epoch": 1.3515344972091945, "grad_norm": 1.8210338354110718, "learning_rate": 0.00014063159813375756, "loss": 0.6683838844299317, "step": 227370 }, { "epoch": 1.351593939285863, "grad_norm": 1.6530919075012207, "learning_rate": 0.0001406257449196986, "loss": 0.6113856315612793, "step": 227380 }, { "epoch": 1.3516533813625313, "grad_norm": 1.7009440660476685, "learning_rate": 0.00014061989155913612, "loss": 0.5806005477905274, "step": 227390 }, { "epoch": 1.3517128234391997, "grad_norm": 1.6741660833358765, "learning_rate": 0.00014061403805209813, "loss": 0.6146428108215332, "step": 227400 }, { "epoch": 1.351772265515868, "grad_norm": 1.0829002857208252, "learning_rate": 0.0001406081843986125, "loss": 0.5336361885070801, "step": 227410 }, { "epoch": 1.3518317075925363, "grad_norm": 1.726127028465271, "learning_rate": 0.0001406023305987074, "loss": 0.642998218536377, "step": 227420 }, { "epoch": 1.3518911496692048, "grad_norm": 1.3860864639282227, "learning_rate": 0.0001405964766524107, "loss": 0.6054304122924805, "step": 227430 }, { "epoch": 1.3519505917458732, "grad_norm": 1.2237752676010132, "learning_rate": 0.00014059062255975045, "loss": 0.5843645095825195, "step": 227440 }, { "epoch": 1.3520100338225416, "grad_norm": 1.6201597452163696, "learning_rate": 0.0001405847683207547, "loss": 0.6140965461730957, "step": 227450 }, { "epoch": 1.35206947589921, "grad_norm": 1.7502243518829346, "learning_rate": 0.00014057891393545136, "loss": 0.6532564163208008, "step": 227460 }, { "epoch": 1.3521289179758784, "grad_norm": 1.2967888116836548, "learning_rate": 0.0001405730594038685, "loss": 0.5398387908935547, "step": 227470 }, { "epoch": 1.3521883600525468, "grad_norm": 1.2743128538131714, "learning_rate": 0.00014056720472603416, "loss": 0.6662043571472168, "step": 227480 }, { "epoch": 1.3522478021292152, "grad_norm": 1.7952601909637451, "learning_rate": 0.00014056134990197627, "loss": 0.5900907993316651, "step": 227490 }, { "epoch": 1.3523072442058837, "grad_norm": 1.6549283266067505, "learning_rate": 0.00014055549493172288, "loss": 0.5810487747192383, "step": 227500 }, { "epoch": 1.352366686282552, "grad_norm": 1.764067530632019, "learning_rate": 0.00014054963981530202, "loss": 0.6662904262542725, "step": 227510 }, { "epoch": 1.3524261283592205, "grad_norm": 1.3871220350265503, "learning_rate": 0.00014054378455274162, "loss": 0.5945061683654785, "step": 227520 }, { "epoch": 1.3524855704358887, "grad_norm": 1.2018723487854004, "learning_rate": 0.00014053792914406972, "loss": 0.5555299758911133, "step": 227530 }, { "epoch": 1.352545012512557, "grad_norm": 1.3325871229171753, "learning_rate": 0.0001405320735893144, "loss": 0.6061714172363282, "step": 227540 }, { "epoch": 1.3526044545892255, "grad_norm": 1.4452321529388428, "learning_rate": 0.0001405262178885036, "loss": 0.5951534271240234, "step": 227550 }, { "epoch": 1.352663896665894, "grad_norm": 1.7852301597595215, "learning_rate": 0.00014052036204166533, "loss": 0.6576634883880615, "step": 227560 }, { "epoch": 1.3527233387425623, "grad_norm": 1.2824465036392212, "learning_rate": 0.0001405145060488276, "loss": 0.5843459606170655, "step": 227570 }, { "epoch": 1.3527827808192308, "grad_norm": 1.6944373846054077, "learning_rate": 0.00014050864991001848, "loss": 0.5711117267608643, "step": 227580 }, { "epoch": 1.3528422228958992, "grad_norm": 1.6083743572235107, "learning_rate": 0.00014050279362526596, "loss": 0.6080073833465576, "step": 227590 }, { "epoch": 1.3529016649725674, "grad_norm": 1.5826489925384521, "learning_rate": 0.00014049693719459804, "loss": 0.6206564903259277, "step": 227600 }, { "epoch": 1.3529611070492358, "grad_norm": 1.6253873109817505, "learning_rate": 0.00014049108061804273, "loss": 0.5769414901733398, "step": 227610 }, { "epoch": 1.3530205491259042, "grad_norm": 1.3685210943222046, "learning_rate": 0.00014048522389562804, "loss": 0.5747323989868164, "step": 227620 }, { "epoch": 1.3530799912025726, "grad_norm": 1.412902593612671, "learning_rate": 0.00014047936702738203, "loss": 0.5901521682739258, "step": 227630 }, { "epoch": 1.353139433279241, "grad_norm": 1.6198874711990356, "learning_rate": 0.00014047351001333265, "loss": 0.6225761890411377, "step": 227640 }, { "epoch": 1.3531988753559094, "grad_norm": 1.382461428642273, "learning_rate": 0.000140467652853508, "loss": 0.6040981769561767, "step": 227650 }, { "epoch": 1.3532583174325779, "grad_norm": 1.6530839204788208, "learning_rate": 0.00014046179554793605, "loss": 0.5551665306091309, "step": 227660 }, { "epoch": 1.3533177595092463, "grad_norm": 1.4428046941757202, "learning_rate": 0.00014045593809664482, "loss": 0.5918519973754883, "step": 227670 }, { "epoch": 1.3533772015859147, "grad_norm": 1.3219352960586548, "learning_rate": 0.0001404500804996623, "loss": 0.566578483581543, "step": 227680 }, { "epoch": 1.353436643662583, "grad_norm": 1.4438061714172363, "learning_rate": 0.0001404442227570166, "loss": 0.6361902236938477, "step": 227690 }, { "epoch": 1.3534960857392515, "grad_norm": 1.5154625177383423, "learning_rate": 0.00014043836486873562, "loss": 0.6728261470794678, "step": 227700 }, { "epoch": 1.3535555278159197, "grad_norm": 1.1505556106567383, "learning_rate": 0.00014043250683484752, "loss": 0.5696917057037354, "step": 227710 }, { "epoch": 1.3536149698925881, "grad_norm": 1.567145824432373, "learning_rate": 0.00014042664865538022, "loss": 0.6041759967803955, "step": 227720 }, { "epoch": 1.3536744119692565, "grad_norm": 1.41650390625, "learning_rate": 0.00014042079033036182, "loss": 0.6072055339813233, "step": 227730 }, { "epoch": 1.353733854045925, "grad_norm": 1.6931792497634888, "learning_rate": 0.00014041493185982024, "loss": 0.5640865325927734, "step": 227740 }, { "epoch": 1.3537932961225934, "grad_norm": 1.459285020828247, "learning_rate": 0.00014040907324378357, "loss": 0.5886557102203369, "step": 227750 }, { "epoch": 1.3538527381992618, "grad_norm": 1.31574547290802, "learning_rate": 0.00014040321448227988, "loss": 0.5341922760009765, "step": 227760 }, { "epoch": 1.3539121802759302, "grad_norm": 1.5093766450881958, "learning_rate": 0.00014039735557533708, "loss": 0.5688012123107911, "step": 227770 }, { "epoch": 1.3539716223525984, "grad_norm": 1.971514344215393, "learning_rate": 0.0001403914965229833, "loss": 0.6645156383514405, "step": 227780 }, { "epoch": 1.3540310644292668, "grad_norm": 1.6345239877700806, "learning_rate": 0.00014038563732524656, "loss": 0.5977034091949462, "step": 227790 }, { "epoch": 1.3540905065059352, "grad_norm": 1.7514151334762573, "learning_rate": 0.00014037977798215482, "loss": 0.5827206611633301, "step": 227800 }, { "epoch": 1.3541499485826036, "grad_norm": 1.3945845365524292, "learning_rate": 0.00014037391849373618, "loss": 0.5875102996826171, "step": 227810 }, { "epoch": 1.354209390659272, "grad_norm": 1.426239252090454, "learning_rate": 0.00014036805886001862, "loss": 0.5783836364746093, "step": 227820 }, { "epoch": 1.3542688327359405, "grad_norm": 1.6312572956085205, "learning_rate": 0.00014036219908103022, "loss": 0.6169812202453613, "step": 227830 }, { "epoch": 1.3543282748126089, "grad_norm": 1.727866768836975, "learning_rate": 0.00014035633915679893, "loss": 0.6191956043243408, "step": 227840 }, { "epoch": 1.3543877168892773, "grad_norm": 1.7221568822860718, "learning_rate": 0.00014035047908735285, "loss": 0.5574199676513671, "step": 227850 }, { "epoch": 1.3544471589659457, "grad_norm": 1.4573765993118286, "learning_rate": 0.00014034461887272004, "loss": 0.5864130020141601, "step": 227860 }, { "epoch": 1.3545066010426141, "grad_norm": 1.2178045511245728, "learning_rate": 0.00014033875851292844, "loss": 0.5588427543640136, "step": 227870 }, { "epoch": 1.3545660431192825, "grad_norm": 1.364350438117981, "learning_rate": 0.00014033289800800616, "loss": 0.5653446197509766, "step": 227880 }, { "epoch": 1.354625485195951, "grad_norm": 1.5341657400131226, "learning_rate": 0.0001403270373579812, "loss": 0.5626595497131348, "step": 227890 }, { "epoch": 1.3546849272726191, "grad_norm": 1.710697054862976, "learning_rate": 0.00014032117656288158, "loss": 0.6023494720458984, "step": 227900 }, { "epoch": 1.3547443693492875, "grad_norm": 1.1720261573791504, "learning_rate": 0.0001403153156227354, "loss": 0.5888361930847168, "step": 227910 }, { "epoch": 1.354803811425956, "grad_norm": 1.5592155456542969, "learning_rate": 0.00014030945453757067, "loss": 0.53040452003479, "step": 227920 }, { "epoch": 1.3548632535026244, "grad_norm": 1.5444103479385376, "learning_rate": 0.00014030359330741537, "loss": 0.6196773529052735, "step": 227930 }, { "epoch": 1.3549226955792928, "grad_norm": 1.6080150604248047, "learning_rate": 0.00014029773193229762, "loss": 0.584548044204712, "step": 227940 }, { "epoch": 1.3549821376559612, "grad_norm": 1.547881007194519, "learning_rate": 0.00014029187041224542, "loss": 0.6288361549377441, "step": 227950 }, { "epoch": 1.3550415797326296, "grad_norm": 1.2544450759887695, "learning_rate": 0.0001402860087472868, "loss": 0.569178581237793, "step": 227960 }, { "epoch": 1.3551010218092978, "grad_norm": 1.5423890352249146, "learning_rate": 0.0001402801469374498, "loss": 0.6257212162017822, "step": 227970 }, { "epoch": 1.3551604638859662, "grad_norm": 1.5633013248443604, "learning_rate": 0.00014027428498276248, "loss": 0.6198736667633057, "step": 227980 }, { "epoch": 1.3552199059626346, "grad_norm": 1.5648316144943237, "learning_rate": 0.0001402684228832529, "loss": 0.5743968963623047, "step": 227990 }, { "epoch": 1.355279348039303, "grad_norm": 1.3119882345199585, "learning_rate": 0.00014026256063894902, "loss": 0.580176830291748, "step": 228000 }, { "epoch": 1.3553387901159715, "grad_norm": 1.4923348426818848, "learning_rate": 0.00014025669824987896, "loss": 0.6106462955474854, "step": 228010 }, { "epoch": 1.3553982321926399, "grad_norm": 2.89033842086792, "learning_rate": 0.00014025083571607075, "loss": 0.5702253818511963, "step": 228020 }, { "epoch": 1.3554576742693083, "grad_norm": 2.143660306930542, "learning_rate": 0.00014024497303755245, "loss": 0.6045906066894531, "step": 228030 }, { "epoch": 1.3555171163459767, "grad_norm": 1.7983357906341553, "learning_rate": 0.0001402391102143521, "loss": 0.6253602504730225, "step": 228040 }, { "epoch": 1.3555765584226451, "grad_norm": 1.7634639739990234, "learning_rate": 0.00014023324724649763, "loss": 0.6104571342468261, "step": 228050 }, { "epoch": 1.3556360004993135, "grad_norm": 1.6070141792297363, "learning_rate": 0.00014022738413401728, "loss": 0.6482103347778321, "step": 228060 }, { "epoch": 1.355695442575982, "grad_norm": 1.5253914594650269, "learning_rate": 0.00014022152087693896, "loss": 0.6543516159057617, "step": 228070 }, { "epoch": 1.3557548846526501, "grad_norm": 1.5914524793624878, "learning_rate": 0.00014021565747529078, "loss": 0.6558905124664307, "step": 228080 }, { "epoch": 1.3558143267293186, "grad_norm": 1.4452650547027588, "learning_rate": 0.00014020979392910076, "loss": 0.6055197715759277, "step": 228090 }, { "epoch": 1.355873768805987, "grad_norm": 1.4322097301483154, "learning_rate": 0.00014020393023839696, "loss": 0.5662972450256347, "step": 228100 }, { "epoch": 1.3559332108826554, "grad_norm": 1.7632282972335815, "learning_rate": 0.00014019806640320744, "loss": 0.609478235244751, "step": 228110 }, { "epoch": 1.3559926529593238, "grad_norm": 1.6358389854431152, "learning_rate": 0.00014019220242356023, "loss": 0.650812816619873, "step": 228120 }, { "epoch": 1.3560520950359922, "grad_norm": 1.5605864524841309, "learning_rate": 0.00014018633829948339, "loss": 0.6152117252349854, "step": 228130 }, { "epoch": 1.3561115371126606, "grad_norm": 1.0816850662231445, "learning_rate": 0.00014018047403100496, "loss": 0.5931781768798828, "step": 228140 }, { "epoch": 1.3561709791893288, "grad_norm": 1.4672929048538208, "learning_rate": 0.000140174609618153, "loss": 0.5535013198852539, "step": 228150 }, { "epoch": 1.3562304212659972, "grad_norm": 1.2954747676849365, "learning_rate": 0.00014016874506095562, "loss": 0.5798335075378418, "step": 228160 }, { "epoch": 1.3562898633426657, "grad_norm": 1.5155887603759766, "learning_rate": 0.00014016288035944077, "loss": 0.6309248924255371, "step": 228170 }, { "epoch": 1.356349305419334, "grad_norm": 1.4570438861846924, "learning_rate": 0.0001401570155136366, "loss": 0.6428044319152832, "step": 228180 }, { "epoch": 1.3564087474960025, "grad_norm": 1.5242342948913574, "learning_rate": 0.0001401511505235711, "loss": 0.5887735843658447, "step": 228190 }, { "epoch": 1.356468189572671, "grad_norm": 1.3196481466293335, "learning_rate": 0.00014014528538927235, "loss": 0.6161429405212402, "step": 228200 }, { "epoch": 1.3565276316493393, "grad_norm": 1.7034618854522705, "learning_rate": 0.0001401394201107684, "loss": 0.6022343635559082, "step": 228210 }, { "epoch": 1.3565870737260077, "grad_norm": 1.0397679805755615, "learning_rate": 0.0001401335546880873, "loss": 0.5705960273742676, "step": 228220 }, { "epoch": 1.3566465158026761, "grad_norm": 1.4290412664413452, "learning_rate": 0.00014012768912125716, "loss": 0.5986990451812744, "step": 228230 }, { "epoch": 1.3567059578793446, "grad_norm": 1.4538745880126953, "learning_rate": 0.00014012182341030594, "loss": 0.6233196258544922, "step": 228240 }, { "epoch": 1.356765399956013, "grad_norm": 1.3888611793518066, "learning_rate": 0.00014011595755526184, "loss": 0.5820669174194336, "step": 228250 }, { "epoch": 1.3568248420326814, "grad_norm": 1.5809019804000854, "learning_rate": 0.0001401100915561528, "loss": 0.6230438232421875, "step": 228260 }, { "epoch": 1.3568842841093496, "grad_norm": 1.4637126922607422, "learning_rate": 0.00014010422541300694, "loss": 0.6448979377746582, "step": 228270 }, { "epoch": 1.356943726186018, "grad_norm": 1.604777455329895, "learning_rate": 0.00014009835912585228, "loss": 0.6486242294311524, "step": 228280 }, { "epoch": 1.3570031682626864, "grad_norm": 2.0537264347076416, "learning_rate": 0.00014009249269471692, "loss": 0.5724672317504883, "step": 228290 }, { "epoch": 1.3570626103393548, "grad_norm": 1.7917569875717163, "learning_rate": 0.0001400866261196289, "loss": 0.6736923217773437, "step": 228300 }, { "epoch": 1.3571220524160232, "grad_norm": 1.3919492959976196, "learning_rate": 0.0001400807594006163, "loss": 0.5947570323944091, "step": 228310 }, { "epoch": 1.3571814944926917, "grad_norm": 1.7742605209350586, "learning_rate": 0.00014007489253770717, "loss": 0.5949745178222656, "step": 228320 }, { "epoch": 1.35724093656936, "grad_norm": 1.645743727684021, "learning_rate": 0.0001400690255309296, "loss": 0.5837952136993408, "step": 228330 }, { "epoch": 1.3573003786460283, "grad_norm": 1.6595832109451294, "learning_rate": 0.00014006315838031164, "loss": 0.5592916488647461, "step": 228340 }, { "epoch": 1.3573598207226967, "grad_norm": 1.4700074195861816, "learning_rate": 0.00014005729108588133, "loss": 0.5825654983520507, "step": 228350 }, { "epoch": 1.357419262799365, "grad_norm": 1.785385251045227, "learning_rate": 0.00014005142364766678, "loss": 0.5669503211975098, "step": 228360 }, { "epoch": 1.3574787048760335, "grad_norm": 1.4673672914505005, "learning_rate": 0.00014004555606569606, "loss": 0.5952242851257324, "step": 228370 }, { "epoch": 1.357538146952702, "grad_norm": 1.7747690677642822, "learning_rate": 0.00014003968833999718, "loss": 0.580226469039917, "step": 228380 }, { "epoch": 1.3575975890293703, "grad_norm": 1.3995776176452637, "learning_rate": 0.00014003382047059822, "loss": 0.6154438018798828, "step": 228390 }, { "epoch": 1.3576570311060387, "grad_norm": 1.0192663669586182, "learning_rate": 0.00014002795245752732, "loss": 0.5893013000488281, "step": 228400 }, { "epoch": 1.3577164731827072, "grad_norm": 2.4811244010925293, "learning_rate": 0.00014002208430081254, "loss": 0.6701526165008544, "step": 228410 }, { "epoch": 1.3577759152593756, "grad_norm": 1.8771233558654785, "learning_rate": 0.00014001621600048187, "loss": 0.6121632575988769, "step": 228420 }, { "epoch": 1.357835357336044, "grad_norm": 2.2005457878112793, "learning_rate": 0.00014001034755656345, "loss": 0.5779422760009766, "step": 228430 }, { "epoch": 1.3578947994127124, "grad_norm": 1.2745189666748047, "learning_rate": 0.00014000447896908536, "loss": 0.5433284759521484, "step": 228440 }, { "epoch": 1.3579542414893806, "grad_norm": 1.0773074626922607, "learning_rate": 0.0001399986102380756, "loss": 0.5614835739135742, "step": 228450 }, { "epoch": 1.358013683566049, "grad_norm": 1.4772425889968872, "learning_rate": 0.00013999274136356233, "loss": 0.6042454719543457, "step": 228460 }, { "epoch": 1.3580731256427174, "grad_norm": 1.6031540632247925, "learning_rate": 0.00013998687234557358, "loss": 0.5900262832641602, "step": 228470 }, { "epoch": 1.3581325677193858, "grad_norm": 1.1637403964996338, "learning_rate": 0.00013998100318413743, "loss": 0.6213666439056397, "step": 228480 }, { "epoch": 1.3581920097960543, "grad_norm": 1.386365294456482, "learning_rate": 0.00013997513387928193, "loss": 0.5550532817840577, "step": 228490 }, { "epoch": 1.3582514518727227, "grad_norm": 1.4419407844543457, "learning_rate": 0.00013996926443103524, "loss": 0.6270385265350342, "step": 228500 }, { "epoch": 1.358310893949391, "grad_norm": 1.367981195449829, "learning_rate": 0.00013996339483942534, "loss": 0.604362154006958, "step": 228510 }, { "epoch": 1.3583703360260593, "grad_norm": 1.7553035020828247, "learning_rate": 0.00013995752510448034, "loss": 0.5967938423156738, "step": 228520 }, { "epoch": 1.3584297781027277, "grad_norm": 1.31256902217865, "learning_rate": 0.0001399516552262284, "loss": 0.584281587600708, "step": 228530 }, { "epoch": 1.358489220179396, "grad_norm": 1.7059452533721924, "learning_rate": 0.00013994578520469745, "loss": 0.6026601791381836, "step": 228540 }, { "epoch": 1.3585486622560645, "grad_norm": 1.1851075887680054, "learning_rate": 0.00013993991503991567, "loss": 0.6310505867004395, "step": 228550 }, { "epoch": 1.358608104332733, "grad_norm": 1.4858767986297607, "learning_rate": 0.00013993404473191116, "loss": 0.6202186107635498, "step": 228560 }, { "epoch": 1.3586675464094013, "grad_norm": 1.8494783639907837, "learning_rate": 0.00013992817428071192, "loss": 0.6233351707458497, "step": 228570 }, { "epoch": 1.3587269884860698, "grad_norm": 1.7649412155151367, "learning_rate": 0.00013992230368634612, "loss": 0.6008404731750489, "step": 228580 }, { "epoch": 1.3587864305627382, "grad_norm": 1.6602052450180054, "learning_rate": 0.00013991643294884176, "loss": 0.6010683059692383, "step": 228590 }, { "epoch": 1.3588458726394066, "grad_norm": 1.7566097974777222, "learning_rate": 0.00013991056206822696, "loss": 0.6005688667297363, "step": 228600 }, { "epoch": 1.358905314716075, "grad_norm": 1.8075897693634033, "learning_rate": 0.00013990469104452983, "loss": 0.6407853126525879, "step": 228610 }, { "epoch": 1.3589647567927434, "grad_norm": 1.462910532951355, "learning_rate": 0.00013989881987777842, "loss": 0.6155046939849853, "step": 228620 }, { "epoch": 1.3590241988694118, "grad_norm": 1.2899454832077026, "learning_rate": 0.00013989294856800083, "loss": 0.5635055065155029, "step": 228630 }, { "epoch": 1.35908364094608, "grad_norm": 1.556401252746582, "learning_rate": 0.00013988707711522512, "loss": 0.5540639400482178, "step": 228640 }, { "epoch": 1.3591430830227484, "grad_norm": 1.6110866069793701, "learning_rate": 0.00013988120551947943, "loss": 0.5892532348632813, "step": 228650 }, { "epoch": 1.3592025250994169, "grad_norm": 2.80534291267395, "learning_rate": 0.0001398753337807918, "loss": 0.5872960090637207, "step": 228660 }, { "epoch": 1.3592619671760853, "grad_norm": 1.5911809206008911, "learning_rate": 0.00013986946189919035, "loss": 0.5544605731964112, "step": 228670 }, { "epoch": 1.3593214092527537, "grad_norm": 1.7490276098251343, "learning_rate": 0.00013986358987470317, "loss": 0.6300930976867676, "step": 228680 }, { "epoch": 1.359380851329422, "grad_norm": 1.5655124187469482, "learning_rate": 0.00013985771770735832, "loss": 0.6426103591918946, "step": 228690 }, { "epoch": 1.3594402934060905, "grad_norm": 1.4699724912643433, "learning_rate": 0.00013985184539718384, "loss": 0.5666202068328857, "step": 228700 }, { "epoch": 1.3594997354827587, "grad_norm": 1.457287311553955, "learning_rate": 0.00013984597294420802, "loss": 0.5989145278930664, "step": 228710 }, { "epoch": 1.3595591775594271, "grad_norm": 1.5773557424545288, "learning_rate": 0.00013984010034845873, "loss": 0.5632352352142334, "step": 228720 }, { "epoch": 1.3596186196360955, "grad_norm": 1.187678575515747, "learning_rate": 0.00013983422760996414, "loss": 0.6183103084564209, "step": 228730 }, { "epoch": 1.359678061712764, "grad_norm": 1.5156325101852417, "learning_rate": 0.0001398283547287524, "loss": 0.5584558486938477, "step": 228740 }, { "epoch": 1.3597375037894324, "grad_norm": 1.482627272605896, "learning_rate": 0.00013982248170485155, "loss": 0.5433688163757324, "step": 228750 }, { "epoch": 1.3597969458661008, "grad_norm": 1.6452451944351196, "learning_rate": 0.00013981660853828968, "loss": 0.5882575035095214, "step": 228760 }, { "epoch": 1.3598563879427692, "grad_norm": 1.437105417251587, "learning_rate": 0.00013981073522909492, "loss": 0.5996476173400879, "step": 228770 }, { "epoch": 1.3599158300194376, "grad_norm": 1.3255510330200195, "learning_rate": 0.00013980486177729532, "loss": 0.606181526184082, "step": 228780 }, { "epoch": 1.359975272096106, "grad_norm": 1.5334689617156982, "learning_rate": 0.00013979898818291902, "loss": 0.640810489654541, "step": 228790 }, { "epoch": 1.3600347141727744, "grad_norm": 1.6075893640518188, "learning_rate": 0.00013979311444599409, "loss": 0.5573530197143555, "step": 228800 }, { "epoch": 1.3600941562494429, "grad_norm": 1.5344324111938477, "learning_rate": 0.00013978724056654864, "loss": 0.6250903606414795, "step": 228810 }, { "epoch": 1.360153598326111, "grad_norm": 1.7746241092681885, "learning_rate": 0.00013978136654461073, "loss": 0.5736136913299561, "step": 228820 }, { "epoch": 1.3602130404027795, "grad_norm": 1.3965895175933838, "learning_rate": 0.00013977549238020854, "loss": 0.624362564086914, "step": 228830 }, { "epoch": 1.3602724824794479, "grad_norm": 1.6168022155761719, "learning_rate": 0.00013976961807337014, "loss": 0.5558376312255859, "step": 228840 }, { "epoch": 1.3603319245561163, "grad_norm": 1.143996000289917, "learning_rate": 0.0001397637436241236, "loss": 0.5534405708312988, "step": 228850 }, { "epoch": 1.3603913666327847, "grad_norm": 1.5480523109436035, "learning_rate": 0.00013975786903249702, "loss": 0.5540408611297607, "step": 228860 }, { "epoch": 1.3604508087094531, "grad_norm": 1.6984257698059082, "learning_rate": 0.00013975199429851852, "loss": 0.622867488861084, "step": 228870 }, { "epoch": 1.3605102507861215, "grad_norm": 2.1155974864959717, "learning_rate": 0.00013974611942221618, "loss": 0.605233907699585, "step": 228880 }, { "epoch": 1.3605696928627897, "grad_norm": 1.7059170007705688, "learning_rate": 0.00013974024440361818, "loss": 0.5606410503387451, "step": 228890 }, { "epoch": 1.3606291349394581, "grad_norm": 1.745105266571045, "learning_rate": 0.00013973436924275253, "loss": 0.6211092948913575, "step": 228900 }, { "epoch": 1.3606885770161266, "grad_norm": 1.8390778303146362, "learning_rate": 0.0001397284939396474, "loss": 0.6096768379211426, "step": 228910 }, { "epoch": 1.360748019092795, "grad_norm": 1.8268927335739136, "learning_rate": 0.00013972261849433087, "loss": 0.6446373939514161, "step": 228920 }, { "epoch": 1.3608074611694634, "grad_norm": 1.3498812913894653, "learning_rate": 0.00013971674290683104, "loss": 0.5816093444824219, "step": 228930 }, { "epoch": 1.3608669032461318, "grad_norm": 1.776042103767395, "learning_rate": 0.00013971086717717602, "loss": 0.629435920715332, "step": 228940 }, { "epoch": 1.3609263453228002, "grad_norm": 1.7613980770111084, "learning_rate": 0.0001397049913053939, "loss": 0.6560340881347656, "step": 228950 }, { "epoch": 1.3609857873994686, "grad_norm": 1.1742807626724243, "learning_rate": 0.00013969911529151285, "loss": 0.6235268592834473, "step": 228960 }, { "epoch": 1.361045229476137, "grad_norm": 1.759964942932129, "learning_rate": 0.00013969323913556091, "loss": 0.6077836513519287, "step": 228970 }, { "epoch": 1.3611046715528055, "grad_norm": 1.920907974243164, "learning_rate": 0.00013968736283756622, "loss": 0.5775105953216553, "step": 228980 }, { "epoch": 1.3611641136294739, "grad_norm": 1.5425593852996826, "learning_rate": 0.00013968148639755692, "loss": 0.610690975189209, "step": 228990 }, { "epoch": 1.3612235557061423, "grad_norm": 1.8932068347930908, "learning_rate": 0.00013967560981556105, "loss": 0.6175120353698731, "step": 229000 }, { "epoch": 1.3612829977828105, "grad_norm": 1.533799648284912, "learning_rate": 0.00013966973309160677, "loss": 0.5814467430114746, "step": 229010 }, { "epoch": 1.361342439859479, "grad_norm": 1.5269354581832886, "learning_rate": 0.00013966385622572223, "loss": 0.5971626281738281, "step": 229020 }, { "epoch": 1.3614018819361473, "grad_norm": 1.544866681098938, "learning_rate": 0.00013965797921793542, "loss": 0.5712215423583984, "step": 229030 }, { "epoch": 1.3614613240128157, "grad_norm": 1.4860355854034424, "learning_rate": 0.00013965210206827458, "loss": 0.6094018936157226, "step": 229040 }, { "epoch": 1.3615207660894841, "grad_norm": 1.6391987800598145, "learning_rate": 0.00013964622477676775, "loss": 0.6053107261657715, "step": 229050 }, { "epoch": 1.3615802081661526, "grad_norm": 1.2609889507293701, "learning_rate": 0.00013964034734344305, "loss": 0.5580412864685058, "step": 229060 }, { "epoch": 1.361639650242821, "grad_norm": 1.3822834491729736, "learning_rate": 0.00013963446976832865, "loss": 0.562136459350586, "step": 229070 }, { "epoch": 1.3616990923194892, "grad_norm": 1.570097804069519, "learning_rate": 0.00013962859205145264, "loss": 0.5887836456298828, "step": 229080 }, { "epoch": 1.3617585343961576, "grad_norm": 1.4951177835464478, "learning_rate": 0.0001396227141928431, "loss": 0.5911737442016601, "step": 229090 }, { "epoch": 1.361817976472826, "grad_norm": 1.6008789539337158, "learning_rate": 0.0001396168361925282, "loss": 0.6322437286376953, "step": 229100 }, { "epoch": 1.3618774185494944, "grad_norm": 1.2607483863830566, "learning_rate": 0.00013961095805053604, "loss": 0.5692033767700195, "step": 229110 }, { "epoch": 1.3619368606261628, "grad_norm": 1.952493667602539, "learning_rate": 0.0001396050797668947, "loss": 0.6538468360900879, "step": 229120 }, { "epoch": 1.3619963027028312, "grad_norm": 1.239977240562439, "learning_rate": 0.00013959920134163235, "loss": 0.6022992134094238, "step": 229130 }, { "epoch": 1.3620557447794996, "grad_norm": 1.5900448560714722, "learning_rate": 0.0001395933227747771, "loss": 0.6084304332733155, "step": 229140 }, { "epoch": 1.362115186856168, "grad_norm": 1.3941229581832886, "learning_rate": 0.00013958744406635705, "loss": 0.6350029945373535, "step": 229150 }, { "epoch": 1.3621746289328365, "grad_norm": 1.4313387870788574, "learning_rate": 0.00013958156521640033, "loss": 0.5986042022705078, "step": 229160 }, { "epoch": 1.3622340710095049, "grad_norm": 1.649951457977295, "learning_rate": 0.00013957568622493508, "loss": 0.6048768997192383, "step": 229170 }, { "epoch": 1.3622935130861733, "grad_norm": 1.210781216621399, "learning_rate": 0.00013956980709198944, "loss": 0.609188461303711, "step": 229180 }, { "epoch": 1.3623529551628415, "grad_norm": 1.3860665559768677, "learning_rate": 0.00013956392781759147, "loss": 0.5860130310058593, "step": 229190 }, { "epoch": 1.36241239723951, "grad_norm": 1.7848985195159912, "learning_rate": 0.00013955804840176935, "loss": 0.5546137809753418, "step": 229200 }, { "epoch": 1.3624718393161783, "grad_norm": 1.6120405197143555, "learning_rate": 0.00013955216884455117, "loss": 0.5943207263946533, "step": 229210 }, { "epoch": 1.3625312813928467, "grad_norm": 1.3664169311523438, "learning_rate": 0.0001395462891459651, "loss": 0.5767122268676758, "step": 229220 }, { "epoch": 1.3625907234695152, "grad_norm": 2.0399887561798096, "learning_rate": 0.0001395404093060392, "loss": 0.5996449947357178, "step": 229230 }, { "epoch": 1.3626501655461836, "grad_norm": 1.2049105167388916, "learning_rate": 0.00013953452932480168, "loss": 0.5781517028808594, "step": 229240 }, { "epoch": 1.362709607622852, "grad_norm": 1.8248382806777954, "learning_rate": 0.0001395286492022806, "loss": 0.6127546310424805, "step": 229250 }, { "epoch": 1.3627690496995202, "grad_norm": 1.5401743650436401, "learning_rate": 0.00013952276893850412, "loss": 0.5719732284545899, "step": 229260 }, { "epoch": 1.3628284917761886, "grad_norm": 1.691278100013733, "learning_rate": 0.00013951688853350034, "loss": 0.5489508152008057, "step": 229270 }, { "epoch": 1.362887933852857, "grad_norm": 1.6778805255889893, "learning_rate": 0.00013951100798729744, "loss": 0.5608777523040771, "step": 229280 }, { "epoch": 1.3629473759295254, "grad_norm": 1.3829302787780762, "learning_rate": 0.00013950512729992348, "loss": 0.6367462158203125, "step": 229290 }, { "epoch": 1.3630068180061938, "grad_norm": 1.4509927034378052, "learning_rate": 0.00013949924647140672, "loss": 0.5986424922943115, "step": 229300 }, { "epoch": 1.3630662600828622, "grad_norm": 1.6636391878128052, "learning_rate": 0.0001394933655017751, "loss": 0.6331701755523682, "step": 229310 }, { "epoch": 1.3631257021595307, "grad_norm": 1.2549796104431152, "learning_rate": 0.00013948748439105693, "loss": 0.6375225067138672, "step": 229320 }, { "epoch": 1.363185144236199, "grad_norm": 1.6559752225875854, "learning_rate": 0.00013948160313928022, "loss": 0.5501714706420898, "step": 229330 }, { "epoch": 1.3632445863128675, "grad_norm": 1.4051620960235596, "learning_rate": 0.00013947572174647318, "loss": 0.6396514892578125, "step": 229340 }, { "epoch": 1.363304028389536, "grad_norm": 1.9296274185180664, "learning_rate": 0.0001394698402126639, "loss": 0.6693302154541015, "step": 229350 }, { "epoch": 1.3633634704662043, "grad_norm": 1.5571285486221313, "learning_rate": 0.0001394639585378806, "loss": 0.5717856407165527, "step": 229360 }, { "epoch": 1.3634229125428727, "grad_norm": 1.3841017484664917, "learning_rate": 0.00013945807672215127, "loss": 0.5949526786804199, "step": 229370 }, { "epoch": 1.363482354619541, "grad_norm": 1.5836341381072998, "learning_rate": 0.00013945219476550419, "loss": 0.6048624515533447, "step": 229380 }, { "epoch": 1.3635417966962093, "grad_norm": 1.616623044013977, "learning_rate": 0.0001394463126679674, "loss": 0.6967124938964844, "step": 229390 }, { "epoch": 1.3636012387728778, "grad_norm": 1.6949105262756348, "learning_rate": 0.00013944043042956908, "loss": 0.5353184700012207, "step": 229400 }, { "epoch": 1.3636606808495462, "grad_norm": 1.5816638469696045, "learning_rate": 0.00013943454805033736, "loss": 0.6092078685760498, "step": 229410 }, { "epoch": 1.3637201229262146, "grad_norm": 1.5288219451904297, "learning_rate": 0.00013942866553030042, "loss": 0.5974102973937988, "step": 229420 }, { "epoch": 1.363779565002883, "grad_norm": 1.576315999031067, "learning_rate": 0.00013942278286948633, "loss": 0.5797663688659668, "step": 229430 }, { "epoch": 1.3638390070795514, "grad_norm": 1.3983941078186035, "learning_rate": 0.00013941690006792325, "loss": 0.6039907932281494, "step": 229440 }, { "epoch": 1.3638984491562196, "grad_norm": 1.4718490839004517, "learning_rate": 0.00013941101712563935, "loss": 0.5442026138305665, "step": 229450 }, { "epoch": 1.363957891232888, "grad_norm": 1.6767494678497314, "learning_rate": 0.00013940513404266276, "loss": 0.6120377540588379, "step": 229460 }, { "epoch": 1.3640173333095564, "grad_norm": 1.4028884172439575, "learning_rate": 0.0001393992508190216, "loss": 0.5893546581268311, "step": 229470 }, { "epoch": 1.3640767753862248, "grad_norm": 1.678984522819519, "learning_rate": 0.00013939336745474404, "loss": 0.6120291233062745, "step": 229480 }, { "epoch": 1.3641362174628933, "grad_norm": 1.9148318767547607, "learning_rate": 0.00013938748394985823, "loss": 0.6288289070129395, "step": 229490 }, { "epoch": 1.3641956595395617, "grad_norm": 1.1404056549072266, "learning_rate": 0.00013938160030439224, "loss": 0.5764030456542969, "step": 229500 }, { "epoch": 1.36425510161623, "grad_norm": 1.580234169960022, "learning_rate": 0.00013937571651837438, "loss": 0.5829268455505371, "step": 229510 }, { "epoch": 1.3643145436928985, "grad_norm": 1.7059907913208008, "learning_rate": 0.0001393698325918326, "loss": 0.6058348178863525, "step": 229520 }, { "epoch": 1.364373985769567, "grad_norm": 1.3994650840759277, "learning_rate": 0.0001393639485247952, "loss": 0.5905003547668457, "step": 229530 }, { "epoch": 1.3644334278462353, "grad_norm": 1.2835110425949097, "learning_rate": 0.00013935806431729023, "loss": 0.5527557373046875, "step": 229540 }, { "epoch": 1.3644928699229038, "grad_norm": 1.601045846939087, "learning_rate": 0.00013935217996934588, "loss": 0.5761281967163085, "step": 229550 }, { "epoch": 1.364552311999572, "grad_norm": 1.4815868139266968, "learning_rate": 0.0001393462954809903, "loss": 0.5652571678161621, "step": 229560 }, { "epoch": 1.3646117540762404, "grad_norm": 1.3554425239562988, "learning_rate": 0.00013934041085225164, "loss": 0.584908390045166, "step": 229570 }, { "epoch": 1.3646711961529088, "grad_norm": 1.619698405265808, "learning_rate": 0.000139334526083158, "loss": 0.5699784755706787, "step": 229580 }, { "epoch": 1.3647306382295772, "grad_norm": 1.5768381357192993, "learning_rate": 0.00013932864117373762, "loss": 0.646552562713623, "step": 229590 }, { "epoch": 1.3647900803062456, "grad_norm": 1.632728099822998, "learning_rate": 0.00013932275612401864, "loss": 0.5421742916107177, "step": 229600 }, { "epoch": 1.364849522382914, "grad_norm": 1.3547699451446533, "learning_rate": 0.0001393168709340291, "loss": 0.691073226928711, "step": 229610 }, { "epoch": 1.3649089644595824, "grad_norm": 1.4117785692214966, "learning_rate": 0.00013931098560379727, "loss": 0.5755719661712646, "step": 229620 }, { "epoch": 1.3649684065362506, "grad_norm": 1.6550976037979126, "learning_rate": 0.00013930510013335129, "loss": 0.6120733261108399, "step": 229630 }, { "epoch": 1.365027848612919, "grad_norm": 1.5307003259658813, "learning_rate": 0.00013929921452271923, "loss": 0.6068666458129883, "step": 229640 }, { "epoch": 1.3650872906895875, "grad_norm": 1.7764701843261719, "learning_rate": 0.00013929332877192933, "loss": 0.6032697677612304, "step": 229650 }, { "epoch": 1.3651467327662559, "grad_norm": 1.1983393430709839, "learning_rate": 0.0001392874428810097, "loss": 0.6160715579986572, "step": 229660 }, { "epoch": 1.3652061748429243, "grad_norm": 1.706380844116211, "learning_rate": 0.00013928155684998853, "loss": 0.5905938148498535, "step": 229670 }, { "epoch": 1.3652656169195927, "grad_norm": 1.7702144384384155, "learning_rate": 0.00013927567067889397, "loss": 0.6086201667785645, "step": 229680 }, { "epoch": 1.365325058996261, "grad_norm": 1.8063722848892212, "learning_rate": 0.00013926978436775418, "loss": 0.6073464393615723, "step": 229690 }, { "epoch": 1.3653845010729295, "grad_norm": 1.5267497301101685, "learning_rate": 0.0001392638979165973, "loss": 0.6080691337585449, "step": 229700 }, { "epoch": 1.365443943149598, "grad_norm": 1.6390615701675415, "learning_rate": 0.00013925801132545147, "loss": 0.6214935779571533, "step": 229710 }, { "epoch": 1.3655033852262664, "grad_norm": 1.6048779487609863, "learning_rate": 0.00013925212459434488, "loss": 0.5742333889007568, "step": 229720 }, { "epoch": 1.3655628273029348, "grad_norm": 1.4541767835617065, "learning_rate": 0.00013924623772330568, "loss": 0.610819149017334, "step": 229730 }, { "epoch": 1.3656222693796032, "grad_norm": 1.4773836135864258, "learning_rate": 0.00013924035071236207, "loss": 0.5983607292175293, "step": 229740 }, { "epoch": 1.3656817114562714, "grad_norm": 1.831475853919983, "learning_rate": 0.00013923446356154214, "loss": 0.6124113082885743, "step": 229750 }, { "epoch": 1.3657411535329398, "grad_norm": 1.3905807733535767, "learning_rate": 0.00013922857627087412, "loss": 0.5832646369934082, "step": 229760 }, { "epoch": 1.3658005956096082, "grad_norm": 1.3268349170684814, "learning_rate": 0.00013922268884038614, "loss": 0.5868588447570801, "step": 229770 }, { "epoch": 1.3658600376862766, "grad_norm": 1.4533412456512451, "learning_rate": 0.00013921680127010634, "loss": 0.5887626647949219, "step": 229780 }, { "epoch": 1.365919479762945, "grad_norm": 1.5742390155792236, "learning_rate": 0.00013921091356006296, "loss": 0.561872911453247, "step": 229790 }, { "epoch": 1.3659789218396134, "grad_norm": 1.7562159299850464, "learning_rate": 0.00013920502571028407, "loss": 0.5882148742675781, "step": 229800 }, { "epoch": 1.3660383639162819, "grad_norm": 1.6633250713348389, "learning_rate": 0.00013919913772079788, "loss": 0.636065673828125, "step": 229810 }, { "epoch": 1.36609780599295, "grad_norm": 1.5343596935272217, "learning_rate": 0.0001391932495916326, "loss": 0.6216997146606446, "step": 229820 }, { "epoch": 1.3661572480696185, "grad_norm": 1.6601414680480957, "learning_rate": 0.00013918736132281632, "loss": 0.6122661590576172, "step": 229830 }, { "epoch": 1.3662166901462869, "grad_norm": 1.294305443763733, "learning_rate": 0.00013918147291437725, "loss": 0.5519647598266602, "step": 229840 }, { "epoch": 1.3662761322229553, "grad_norm": 1.2574198246002197, "learning_rate": 0.00013917558436634357, "loss": 0.5734441757202149, "step": 229850 }, { "epoch": 1.3663355742996237, "grad_norm": 1.460778832435608, "learning_rate": 0.0001391696956787434, "loss": 0.5830586433410645, "step": 229860 }, { "epoch": 1.3663950163762921, "grad_norm": 1.8813469409942627, "learning_rate": 0.00013916380685160496, "loss": 0.5759576320648193, "step": 229870 }, { "epoch": 1.3664544584529605, "grad_norm": 1.6104072332382202, "learning_rate": 0.00013915791788495638, "loss": 0.6428669929504395, "step": 229880 }, { "epoch": 1.366513900529629, "grad_norm": 1.7470422983169556, "learning_rate": 0.00013915202877882584, "loss": 0.5904544830322266, "step": 229890 }, { "epoch": 1.3665733426062974, "grad_norm": 1.7015085220336914, "learning_rate": 0.00013914613953324153, "loss": 0.6313485622406005, "step": 229900 }, { "epoch": 1.3666327846829658, "grad_norm": 1.5950385332107544, "learning_rate": 0.00013914025014823164, "loss": 0.6316132545471191, "step": 229910 }, { "epoch": 1.3666922267596342, "grad_norm": 1.3135672807693481, "learning_rate": 0.0001391343606238243, "loss": 0.6042745590209961, "step": 229920 }, { "epoch": 1.3667516688363024, "grad_norm": 1.418880820274353, "learning_rate": 0.0001391284709600477, "loss": 0.5805651187896729, "step": 229930 }, { "epoch": 1.3668111109129708, "grad_norm": 1.6484063863754272, "learning_rate": 0.00013912258115693, "loss": 0.5741470336914063, "step": 229940 }, { "epoch": 1.3668705529896392, "grad_norm": 1.4409923553466797, "learning_rate": 0.00013911669121449943, "loss": 0.5620120525360107, "step": 229950 }, { "epoch": 1.3669299950663076, "grad_norm": 1.9616210460662842, "learning_rate": 0.00013911080113278407, "loss": 0.6065295696258545, "step": 229960 }, { "epoch": 1.366989437142976, "grad_norm": 1.2568700313568115, "learning_rate": 0.0001391049109118122, "loss": 0.5946426391601562, "step": 229970 }, { "epoch": 1.3670488792196445, "grad_norm": 1.4136481285095215, "learning_rate": 0.00013909902055161193, "loss": 0.584861946105957, "step": 229980 }, { "epoch": 1.3671083212963129, "grad_norm": 1.621242880821228, "learning_rate": 0.00013909313005221142, "loss": 0.5335031032562256, "step": 229990 }, { "epoch": 1.367167763372981, "grad_norm": 1.6079436540603638, "learning_rate": 0.00013908723941363896, "loss": 0.686451768875122, "step": 230000 }, { "epoch": 1.3672272054496495, "grad_norm": 1.4014424085617065, "learning_rate": 0.00013908134863592256, "loss": 0.6669286727905274, "step": 230010 }, { "epoch": 1.367286647526318, "grad_norm": 2.394035816192627, "learning_rate": 0.00013907545771909055, "loss": 0.6628484725952148, "step": 230020 }, { "epoch": 1.3673460896029863, "grad_norm": 1.881522297859192, "learning_rate": 0.00013906956666317105, "loss": 0.6158489227294922, "step": 230030 }, { "epoch": 1.3674055316796547, "grad_norm": 1.5738484859466553, "learning_rate": 0.00013906367546819224, "loss": 0.6491504192352295, "step": 230040 }, { "epoch": 1.3674649737563231, "grad_norm": 1.596105933189392, "learning_rate": 0.0001390577841341823, "loss": 0.5084370613098145, "step": 230050 }, { "epoch": 1.3675244158329916, "grad_norm": 1.4198462963104248, "learning_rate": 0.00013905189266116944, "loss": 0.609934139251709, "step": 230060 }, { "epoch": 1.36758385790966, "grad_norm": 1.7671276330947876, "learning_rate": 0.00013904600104918175, "loss": 0.7303866386413574, "step": 230070 }, { "epoch": 1.3676432999863284, "grad_norm": 1.3818252086639404, "learning_rate": 0.00013904010929824753, "loss": 0.5994046211242676, "step": 230080 }, { "epoch": 1.3677027420629968, "grad_norm": 1.7971237897872925, "learning_rate": 0.00013903421740839493, "loss": 0.5880770683288574, "step": 230090 }, { "epoch": 1.3677621841396652, "grad_norm": 1.571569561958313, "learning_rate": 0.00013902832537965212, "loss": 0.6142245292663574, "step": 230100 }, { "epoch": 1.3678216262163336, "grad_norm": 1.4964501857757568, "learning_rate": 0.00013902243321204727, "loss": 0.6402376651763916, "step": 230110 }, { "epoch": 1.3678810682930018, "grad_norm": 1.3284640312194824, "learning_rate": 0.00013901654090560858, "loss": 0.6255889415740967, "step": 230120 }, { "epoch": 1.3679405103696702, "grad_norm": 1.8640700578689575, "learning_rate": 0.00013901064846036425, "loss": 0.6029031276702881, "step": 230130 }, { "epoch": 1.3679999524463387, "grad_norm": 1.3633708953857422, "learning_rate": 0.00013900475587634247, "loss": 0.5925850391387939, "step": 230140 }, { "epoch": 1.368059394523007, "grad_norm": 1.540961503982544, "learning_rate": 0.0001389988631535714, "loss": 0.5906665802001954, "step": 230150 }, { "epoch": 1.3681188365996755, "grad_norm": 1.645222544670105, "learning_rate": 0.00013899297029207924, "loss": 0.6001945495605469, "step": 230160 }, { "epoch": 1.368178278676344, "grad_norm": 1.7670198678970337, "learning_rate": 0.0001389870772918942, "loss": 0.604672622680664, "step": 230170 }, { "epoch": 1.3682377207530123, "grad_norm": 1.4825581312179565, "learning_rate": 0.00013898118415304447, "loss": 0.5968002319335938, "step": 230180 }, { "epoch": 1.3682971628296805, "grad_norm": 1.4162527322769165, "learning_rate": 0.00013897529087555824, "loss": 0.5880845546722412, "step": 230190 }, { "epoch": 1.368356604906349, "grad_norm": 1.4299014806747437, "learning_rate": 0.00013896939745946363, "loss": 0.6358686923980713, "step": 230200 }, { "epoch": 1.3684160469830173, "grad_norm": 1.4466261863708496, "learning_rate": 0.0001389635039047889, "loss": 0.619930362701416, "step": 230210 }, { "epoch": 1.3684754890596857, "grad_norm": 1.74795663356781, "learning_rate": 0.00013895761021156226, "loss": 0.7016534805297852, "step": 230220 }, { "epoch": 1.3685349311363542, "grad_norm": 1.7388381958007812, "learning_rate": 0.00013895171637981187, "loss": 0.6615039348602295, "step": 230230 }, { "epoch": 1.3685943732130226, "grad_norm": 2.0361292362213135, "learning_rate": 0.0001389458224095659, "loss": 0.6130270481109619, "step": 230240 }, { "epoch": 1.368653815289691, "grad_norm": 1.4827632904052734, "learning_rate": 0.00013893992830085262, "loss": 0.6311868190765381, "step": 230250 }, { "epoch": 1.3687132573663594, "grad_norm": 1.2161130905151367, "learning_rate": 0.0001389340340537002, "loss": 0.5672406196594239, "step": 230260 }, { "epoch": 1.3687726994430278, "grad_norm": 1.5807089805603027, "learning_rate": 0.00013892813966813672, "loss": 0.6437921524047852, "step": 230270 }, { "epoch": 1.3688321415196962, "grad_norm": 1.1768734455108643, "learning_rate": 0.0001389222451441906, "loss": 0.589924955368042, "step": 230280 }, { "epoch": 1.3688915835963646, "grad_norm": 1.473259687423706, "learning_rate": 0.0001389163504818898, "loss": 0.5916502952575684, "step": 230290 }, { "epoch": 1.3689510256730328, "grad_norm": 1.6164226531982422, "learning_rate": 0.0001389104556812627, "loss": 0.5567290306091308, "step": 230300 }, { "epoch": 1.3690104677497013, "grad_norm": 1.6738340854644775, "learning_rate": 0.0001389045607423374, "loss": 0.6261754035949707, "step": 230310 }, { "epoch": 1.3690699098263697, "grad_norm": 1.5622859001159668, "learning_rate": 0.0001388986656651421, "loss": 0.575650691986084, "step": 230320 }, { "epoch": 1.369129351903038, "grad_norm": 1.5549322366714478, "learning_rate": 0.0001388927704497051, "loss": 0.6205703735351562, "step": 230330 }, { "epoch": 1.3691887939797065, "grad_norm": 1.8464208841323853, "learning_rate": 0.00013888687509605444, "loss": 0.6066904067993164, "step": 230340 }, { "epoch": 1.369248236056375, "grad_norm": 1.3648923635482788, "learning_rate": 0.00013888097960421846, "loss": 0.6339095115661622, "step": 230350 }, { "epoch": 1.3693076781330433, "grad_norm": 1.8482404947280884, "learning_rate": 0.0001388750839742253, "loss": 0.6714141845703125, "step": 230360 }, { "epoch": 1.3693671202097115, "grad_norm": 1.4735358953475952, "learning_rate": 0.0001388691882061032, "loss": 0.5871390342712403, "step": 230370 }, { "epoch": 1.36942656228638, "grad_norm": 1.089003562927246, "learning_rate": 0.00013886329229988032, "loss": 0.6067452430725098, "step": 230380 }, { "epoch": 1.3694860043630483, "grad_norm": 1.2844517230987549, "learning_rate": 0.00013885739625558487, "loss": 0.6520933151245117, "step": 230390 }, { "epoch": 1.3695454464397168, "grad_norm": 1.2287635803222656, "learning_rate": 0.0001388515000732451, "loss": 0.5965107917785645, "step": 230400 }, { "epoch": 1.3696048885163852, "grad_norm": 1.8599694967269897, "learning_rate": 0.00013884560375288914, "loss": 0.5998068809509277, "step": 230410 }, { "epoch": 1.3696643305930536, "grad_norm": 1.181249737739563, "learning_rate": 0.00013883970729454526, "loss": 0.5513503074645996, "step": 230420 }, { "epoch": 1.369723772669722, "grad_norm": 1.3446617126464844, "learning_rate": 0.00013883381069824163, "loss": 0.5210204124450684, "step": 230430 }, { "epoch": 1.3697832147463904, "grad_norm": 1.5018465518951416, "learning_rate": 0.0001388279139640065, "loss": 0.599949836730957, "step": 230440 }, { "epoch": 1.3698426568230588, "grad_norm": 1.5552839040756226, "learning_rate": 0.00013882201709186805, "loss": 0.5744083404541016, "step": 230450 }, { "epoch": 1.3699020988997272, "grad_norm": 1.651943325996399, "learning_rate": 0.00013881612008185447, "loss": 0.6437831401824952, "step": 230460 }, { "epoch": 1.3699615409763957, "grad_norm": 1.544205665588379, "learning_rate": 0.000138810222933994, "loss": 0.631009864807129, "step": 230470 }, { "epoch": 1.370020983053064, "grad_norm": 1.7897568941116333, "learning_rate": 0.0001388043256483148, "loss": 0.6007863998413085, "step": 230480 }, { "epoch": 1.3700804251297323, "grad_norm": 1.5505560636520386, "learning_rate": 0.00013879842822484519, "loss": 0.5993106842041016, "step": 230490 }, { "epoch": 1.3701398672064007, "grad_norm": 2.018362283706665, "learning_rate": 0.00013879253066361325, "loss": 0.6214624881744385, "step": 230500 }, { "epoch": 1.370199309283069, "grad_norm": 1.2842127084732056, "learning_rate": 0.0001387866329646473, "loss": 0.5769147396087646, "step": 230510 }, { "epoch": 1.3702587513597375, "grad_norm": 1.304599404335022, "learning_rate": 0.00013878073512797547, "loss": 0.5771674156188965, "step": 230520 }, { "epoch": 1.370318193436406, "grad_norm": 1.3923721313476562, "learning_rate": 0.00013877483715362605, "loss": 0.5925094604492187, "step": 230530 }, { "epoch": 1.3703776355130743, "grad_norm": 1.3145171403884888, "learning_rate": 0.00013876893904162717, "loss": 0.6000255584716797, "step": 230540 }, { "epoch": 1.3704370775897428, "grad_norm": 1.4491370916366577, "learning_rate": 0.00013876304079200711, "loss": 0.5757019996643067, "step": 230550 }, { "epoch": 1.370496519666411, "grad_norm": 1.428708791732788, "learning_rate": 0.00013875714240479408, "loss": 0.5778000831604004, "step": 230560 }, { "epoch": 1.3705559617430794, "grad_norm": 1.3692412376403809, "learning_rate": 0.00013875124388001623, "loss": 0.6180235862731933, "step": 230570 }, { "epoch": 1.3706154038197478, "grad_norm": 1.2083877325057983, "learning_rate": 0.00013874534521770185, "loss": 0.61714186668396, "step": 230580 }, { "epoch": 1.3706748458964162, "grad_norm": 1.7540265321731567, "learning_rate": 0.00013873944641787912, "loss": 0.6346085548400879, "step": 230590 }, { "epoch": 1.3707342879730846, "grad_norm": 1.5478572845458984, "learning_rate": 0.00013873354748057627, "loss": 0.619754409790039, "step": 230600 }, { "epoch": 1.370793730049753, "grad_norm": 0.9834818840026855, "learning_rate": 0.00013872764840582155, "loss": 0.5568168640136719, "step": 230610 }, { "epoch": 1.3708531721264214, "grad_norm": 1.607085108757019, "learning_rate": 0.00013872174919364315, "loss": 0.6221665859222412, "step": 230620 }, { "epoch": 1.3709126142030899, "grad_norm": 1.5825172662734985, "learning_rate": 0.00013871584984406925, "loss": 0.6087321281433106, "step": 230630 }, { "epoch": 1.3709720562797583, "grad_norm": 1.501138687133789, "learning_rate": 0.00013870995035712813, "loss": 0.631458854675293, "step": 230640 }, { "epoch": 1.3710314983564267, "grad_norm": 1.5394445657730103, "learning_rate": 0.00013870405073284798, "loss": 0.583941650390625, "step": 230650 }, { "epoch": 1.371090940433095, "grad_norm": 1.6088366508483887, "learning_rate": 0.00013869815097125704, "loss": 0.6023588180541992, "step": 230660 }, { "epoch": 1.3711503825097633, "grad_norm": 1.4734631776809692, "learning_rate": 0.00013869225107238353, "loss": 0.5844759464263916, "step": 230670 }, { "epoch": 1.3712098245864317, "grad_norm": 1.3563838005065918, "learning_rate": 0.00013868635103625568, "loss": 0.5979772090911866, "step": 230680 }, { "epoch": 1.3712692666631001, "grad_norm": 1.5174646377563477, "learning_rate": 0.00013868045086290167, "loss": 0.5752011299133301, "step": 230690 }, { "epoch": 1.3713287087397685, "grad_norm": 1.6079093217849731, "learning_rate": 0.00013867455055234976, "loss": 0.5972015380859375, "step": 230700 }, { "epoch": 1.371388150816437, "grad_norm": 1.5426214933395386, "learning_rate": 0.00013866865010462817, "loss": 0.5808979034423828, "step": 230710 }, { "epoch": 1.3714475928931054, "grad_norm": 1.358386516571045, "learning_rate": 0.00013866274951976514, "loss": 0.570352840423584, "step": 230720 }, { "epoch": 1.3715070349697738, "grad_norm": 1.5222971439361572, "learning_rate": 0.00013865684879778889, "loss": 0.5797390460968017, "step": 230730 }, { "epoch": 1.371566477046442, "grad_norm": 1.1015310287475586, "learning_rate": 0.0001386509479387276, "loss": 0.5888309478759766, "step": 230740 }, { "epoch": 1.3716259191231104, "grad_norm": 1.4796584844589233, "learning_rate": 0.00013864504694260961, "loss": 0.5916986465454102, "step": 230750 }, { "epoch": 1.3716853611997788, "grad_norm": 1.7858574390411377, "learning_rate": 0.000138639145809463, "loss": 0.5926698207855224, "step": 230760 }, { "epoch": 1.3717448032764472, "grad_norm": 1.2057290077209473, "learning_rate": 0.00013863324453931614, "loss": 0.5669816970825196, "step": 230770 }, { "epoch": 1.3718042453531156, "grad_norm": 1.108667016029358, "learning_rate": 0.00013862734313219716, "loss": 0.6544021129608154, "step": 230780 }, { "epoch": 1.371863687429784, "grad_norm": 1.1924335956573486, "learning_rate": 0.00013862144158813432, "loss": 0.5974211692810059, "step": 230790 }, { "epoch": 1.3719231295064525, "grad_norm": 1.701921820640564, "learning_rate": 0.00013861553990715588, "loss": 0.606041955947876, "step": 230800 }, { "epoch": 1.3719825715831209, "grad_norm": 1.5343561172485352, "learning_rate": 0.00013860963808929002, "loss": 0.5876686096191406, "step": 230810 }, { "epoch": 1.3720420136597893, "grad_norm": 1.2201555967330933, "learning_rate": 0.00013860373613456506, "loss": 0.5719662666320801, "step": 230820 }, { "epoch": 1.3721014557364577, "grad_norm": 1.495328664779663, "learning_rate": 0.00013859783404300912, "loss": 0.5875713348388671, "step": 230830 }, { "epoch": 1.3721608978131261, "grad_norm": 1.4454585313796997, "learning_rate": 0.00013859193181465048, "loss": 0.6252510070800781, "step": 230840 }, { "epoch": 1.3722203398897945, "grad_norm": 1.451744794845581, "learning_rate": 0.00013858602944951743, "loss": 0.581365966796875, "step": 230850 }, { "epoch": 1.3722797819664627, "grad_norm": 1.4981489181518555, "learning_rate": 0.0001385801269476381, "loss": 0.5856028079986573, "step": 230860 }, { "epoch": 1.3723392240431311, "grad_norm": 1.3093525171279907, "learning_rate": 0.00013857422430904083, "loss": 0.6536730289459228, "step": 230870 }, { "epoch": 1.3723986661197995, "grad_norm": 1.8586736917495728, "learning_rate": 0.0001385683215337538, "loss": 0.5911364078521728, "step": 230880 }, { "epoch": 1.372458108196468, "grad_norm": 1.0750844478607178, "learning_rate": 0.00013856241862180525, "loss": 0.6172463417053222, "step": 230890 }, { "epoch": 1.3725175502731364, "grad_norm": 1.4707708358764648, "learning_rate": 0.00013855651557322343, "loss": 0.5930329322814941, "step": 230900 }, { "epoch": 1.3725769923498048, "grad_norm": 1.201674461364746, "learning_rate": 0.00013855061238803653, "loss": 0.5655271053314209, "step": 230910 }, { "epoch": 1.3726364344264732, "grad_norm": 1.5555946826934814, "learning_rate": 0.0001385447090662729, "loss": 0.622124195098877, "step": 230920 }, { "epoch": 1.3726958765031414, "grad_norm": 1.5913364887237549, "learning_rate": 0.00013853880560796067, "loss": 0.6523931503295899, "step": 230930 }, { "epoch": 1.3727553185798098, "grad_norm": 1.5566210746765137, "learning_rate": 0.00013853290201312808, "loss": 0.5769217491149903, "step": 230940 }, { "epoch": 1.3728147606564782, "grad_norm": 1.3513596057891846, "learning_rate": 0.00013852699828180348, "loss": 0.6024301052093506, "step": 230950 }, { "epoch": 1.3728742027331466, "grad_norm": 1.6220080852508545, "learning_rate": 0.00013852109441401503, "loss": 0.5692824840545654, "step": 230960 }, { "epoch": 1.372933644809815, "grad_norm": 1.6036486625671387, "learning_rate": 0.00013851519040979096, "loss": 0.5746973991394043, "step": 230970 }, { "epoch": 1.3729930868864835, "grad_norm": 1.7001293897628784, "learning_rate": 0.00013850928626915957, "loss": 0.5894390106201172, "step": 230980 }, { "epoch": 1.3730525289631519, "grad_norm": 1.8238308429718018, "learning_rate": 0.00013850338199214904, "loss": 0.6279136657714843, "step": 230990 }, { "epoch": 1.3731119710398203, "grad_norm": 1.3533273935317993, "learning_rate": 0.00013849747757878767, "loss": 0.6247270584106446, "step": 231000 }, { "epoch": 1.3731714131164887, "grad_norm": 1.2968523502349854, "learning_rate": 0.00013849157302910366, "loss": 0.5867875099182129, "step": 231010 }, { "epoch": 1.3732308551931571, "grad_norm": 1.965890645980835, "learning_rate": 0.0001384856683431253, "loss": 0.6233912944793701, "step": 231020 }, { "epoch": 1.3732902972698255, "grad_norm": 1.3991003036499023, "learning_rate": 0.00013847976352088082, "loss": 0.5494831562042236, "step": 231030 }, { "epoch": 1.3733497393464937, "grad_norm": 1.6231729984283447, "learning_rate": 0.0001384738585623984, "loss": 0.5798232555389404, "step": 231040 }, { "epoch": 1.3734091814231622, "grad_norm": 1.8020920753479004, "learning_rate": 0.0001384679534677064, "loss": 0.5914568901062012, "step": 231050 }, { "epoch": 1.3734686234998306, "grad_norm": 1.2063884735107422, "learning_rate": 0.000138462048236833, "loss": 0.5873790264129639, "step": 231060 }, { "epoch": 1.373528065576499, "grad_norm": 1.328528881072998, "learning_rate": 0.00013845614286980644, "loss": 0.5758902549743652, "step": 231070 }, { "epoch": 1.3735875076531674, "grad_norm": 1.0194693803787231, "learning_rate": 0.00013845023736665504, "loss": 0.580649995803833, "step": 231080 }, { "epoch": 1.3736469497298358, "grad_norm": 1.4555572271347046, "learning_rate": 0.00013844433172740696, "loss": 0.5692196846008301, "step": 231090 }, { "epoch": 1.3737063918065042, "grad_norm": 1.753474473953247, "learning_rate": 0.0001384384259520905, "loss": 0.6017833232879639, "step": 231100 }, { "epoch": 1.3737658338831724, "grad_norm": 1.4171279668807983, "learning_rate": 0.0001384325200407339, "loss": 0.6199511528015137, "step": 231110 }, { "epoch": 1.3738252759598408, "grad_norm": 1.2990853786468506, "learning_rate": 0.00013842661399336543, "loss": 0.567528486251831, "step": 231120 }, { "epoch": 1.3738847180365092, "grad_norm": 1.4782980680465698, "learning_rate": 0.00013842070781001334, "loss": 0.5961824417114258, "step": 231130 }, { "epoch": 1.3739441601131777, "grad_norm": 1.1597931385040283, "learning_rate": 0.00013841480149070587, "loss": 0.5842284679412841, "step": 231140 }, { "epoch": 1.374003602189846, "grad_norm": 1.4657756090164185, "learning_rate": 0.00013840889503547124, "loss": 0.559147834777832, "step": 231150 }, { "epoch": 1.3740630442665145, "grad_norm": 1.8068724870681763, "learning_rate": 0.00013840298844433778, "loss": 0.5639910221099853, "step": 231160 }, { "epoch": 1.374122486343183, "grad_norm": 1.4218131303787231, "learning_rate": 0.0001383970817173337, "loss": 0.6395632743835449, "step": 231170 }, { "epoch": 1.3741819284198513, "grad_norm": 1.7080390453338623, "learning_rate": 0.00013839117485448725, "loss": 0.6655088424682617, "step": 231180 }, { "epoch": 1.3742413704965197, "grad_norm": 1.4537198543548584, "learning_rate": 0.00013838526785582667, "loss": 0.6303987026214599, "step": 231190 }, { "epoch": 1.3743008125731881, "grad_norm": 1.7935562133789062, "learning_rate": 0.00013837936072138028, "loss": 0.6355875968933106, "step": 231200 }, { "epoch": 1.3743602546498566, "grad_norm": 1.1057106256484985, "learning_rate": 0.0001383734534511763, "loss": 0.5296773433685302, "step": 231210 }, { "epoch": 1.374419696726525, "grad_norm": 1.9880555868148804, "learning_rate": 0.00013836754604524298, "loss": 0.6145878791809082, "step": 231220 }, { "epoch": 1.3744791388031932, "grad_norm": 1.5919771194458008, "learning_rate": 0.00013836163850360856, "loss": 0.6676895618438721, "step": 231230 }, { "epoch": 1.3745385808798616, "grad_norm": 1.4020899534225464, "learning_rate": 0.0001383557308263014, "loss": 0.5613176345825195, "step": 231240 }, { "epoch": 1.37459802295653, "grad_norm": 1.486763834953308, "learning_rate": 0.00013834982301334965, "loss": 0.6242821693420411, "step": 231250 }, { "epoch": 1.3746574650331984, "grad_norm": 1.602207899093628, "learning_rate": 0.00013834391506478162, "loss": 0.5536470890045166, "step": 231260 }, { "epoch": 1.3747169071098668, "grad_norm": 1.3763412237167358, "learning_rate": 0.00013833800698062555, "loss": 0.5589144229888916, "step": 231270 }, { "epoch": 1.3747763491865352, "grad_norm": 1.3594858646392822, "learning_rate": 0.00013833209876090973, "loss": 0.5998773574829102, "step": 231280 }, { "epoch": 1.3748357912632034, "grad_norm": 1.524790644645691, "learning_rate": 0.0001383261904056624, "loss": 0.6102563381195069, "step": 231290 }, { "epoch": 1.3748952333398718, "grad_norm": 1.6692434549331665, "learning_rate": 0.00013832028191491187, "loss": 0.6086668491363525, "step": 231300 }, { "epoch": 1.3749546754165403, "grad_norm": 1.3683420419692993, "learning_rate": 0.00013831437328868632, "loss": 0.5720420837402344, "step": 231310 }, { "epoch": 1.3750141174932087, "grad_norm": 1.6623283624649048, "learning_rate": 0.0001383084645270141, "loss": 0.6017074584960938, "step": 231320 }, { "epoch": 1.375073559569877, "grad_norm": 1.4898293018341064, "learning_rate": 0.0001383025556299234, "loss": 0.5820282936096192, "step": 231330 }, { "epoch": 1.3751330016465455, "grad_norm": 1.7116773128509521, "learning_rate": 0.00013829664659744252, "loss": 0.5789344310760498, "step": 231340 }, { "epoch": 1.375192443723214, "grad_norm": 1.4198801517486572, "learning_rate": 0.00013829073742959976, "loss": 0.6205575466156006, "step": 231350 }, { "epoch": 1.3752518857998823, "grad_norm": 1.4237605333328247, "learning_rate": 0.00013828482812642336, "loss": 0.553261661529541, "step": 231360 }, { "epoch": 1.3753113278765507, "grad_norm": 2.0674076080322266, "learning_rate": 0.00013827891868794154, "loss": 0.6400338649749756, "step": 231370 }, { "epoch": 1.3753707699532192, "grad_norm": 1.982968807220459, "learning_rate": 0.00013827300911418267, "loss": 0.575258207321167, "step": 231380 }, { "epoch": 1.3754302120298876, "grad_norm": 1.871490716934204, "learning_rate": 0.00013826709940517492, "loss": 0.5779263496398925, "step": 231390 }, { "epoch": 1.375489654106556, "grad_norm": 1.1191531419754028, "learning_rate": 0.00013826118956094662, "loss": 0.6299824237823486, "step": 231400 }, { "epoch": 1.3755490961832242, "grad_norm": 1.5018295049667358, "learning_rate": 0.00013825527958152603, "loss": 0.5458425521850586, "step": 231410 }, { "epoch": 1.3756085382598926, "grad_norm": 1.3639497756958008, "learning_rate": 0.00013824936946694143, "loss": 0.6762764930725098, "step": 231420 }, { "epoch": 1.375667980336561, "grad_norm": 1.380750060081482, "learning_rate": 0.00013824345921722105, "loss": 0.5375537872314453, "step": 231430 }, { "epoch": 1.3757274224132294, "grad_norm": 1.568571925163269, "learning_rate": 0.00013823754883239323, "loss": 0.577428150177002, "step": 231440 }, { "epoch": 1.3757868644898978, "grad_norm": 1.3856916427612305, "learning_rate": 0.00013823163831248617, "loss": 0.645984411239624, "step": 231450 }, { "epoch": 1.3758463065665663, "grad_norm": 1.6693116426467896, "learning_rate": 0.00013822572765752816, "loss": 0.6326352119445801, "step": 231460 }, { "epoch": 1.3759057486432347, "grad_norm": 1.188081979751587, "learning_rate": 0.00013821981686754753, "loss": 0.5545975685119628, "step": 231470 }, { "epoch": 1.3759651907199029, "grad_norm": 1.2408095598220825, "learning_rate": 0.00013821390594257252, "loss": 0.5805561065673828, "step": 231480 }, { "epoch": 1.3760246327965713, "grad_norm": 1.5995287895202637, "learning_rate": 0.00013820799488263138, "loss": 0.5586581707000733, "step": 231490 }, { "epoch": 1.3760840748732397, "grad_norm": 1.5477169752120972, "learning_rate": 0.00013820208368775242, "loss": 0.6179539680480957, "step": 231500 }, { "epoch": 1.376143516949908, "grad_norm": 1.6128500699996948, "learning_rate": 0.00013819617235796394, "loss": 0.585338544845581, "step": 231510 }, { "epoch": 1.3762029590265765, "grad_norm": 1.6690592765808105, "learning_rate": 0.00013819026089329414, "loss": 0.5971463680267334, "step": 231520 }, { "epoch": 1.376262401103245, "grad_norm": 1.5402710437774658, "learning_rate": 0.00013818434929377136, "loss": 0.6255552291870117, "step": 231530 }, { "epoch": 1.3763218431799134, "grad_norm": 1.5307639837265015, "learning_rate": 0.0001381784375594239, "loss": 0.6228973388671875, "step": 231540 }, { "epoch": 1.3763812852565818, "grad_norm": 1.6691280603408813, "learning_rate": 0.00013817252569027995, "loss": 0.5550187587738037, "step": 231550 }, { "epoch": 1.3764407273332502, "grad_norm": 1.3311537504196167, "learning_rate": 0.00013816661368636784, "loss": 0.6084428787231445, "step": 231560 }, { "epoch": 1.3765001694099186, "grad_norm": 1.3479106426239014, "learning_rate": 0.0001381607015477159, "loss": 0.6381646156311035, "step": 231570 }, { "epoch": 1.376559611486587, "grad_norm": 1.5371990203857422, "learning_rate": 0.00013815478927435234, "loss": 0.5597604751586914, "step": 231580 }, { "epoch": 1.3766190535632554, "grad_norm": 1.410725712776184, "learning_rate": 0.00013814887686630547, "loss": 0.5953340053558349, "step": 231590 }, { "epoch": 1.3766784956399236, "grad_norm": 1.371169090270996, "learning_rate": 0.0001381429643236036, "loss": 0.6039436340332032, "step": 231600 }, { "epoch": 1.376737937716592, "grad_norm": 1.3695558309555054, "learning_rate": 0.00013813705164627494, "loss": 0.5781920433044434, "step": 231610 }, { "epoch": 1.3767973797932604, "grad_norm": 1.205082893371582, "learning_rate": 0.00013813113883434788, "loss": 0.5806001663208008, "step": 231620 }, { "epoch": 1.3768568218699289, "grad_norm": 1.4854629039764404, "learning_rate": 0.0001381252258878506, "loss": 0.5305474281311036, "step": 231630 }, { "epoch": 1.3769162639465973, "grad_norm": 1.2515848875045776, "learning_rate": 0.00013811931280681143, "loss": 0.6183590412139892, "step": 231640 }, { "epoch": 1.3769757060232657, "grad_norm": 1.5736300945281982, "learning_rate": 0.00013811339959125864, "loss": 0.5565376281738281, "step": 231650 }, { "epoch": 1.3770351480999339, "grad_norm": 1.480913519859314, "learning_rate": 0.0001381074862412206, "loss": 0.624996566772461, "step": 231660 }, { "epoch": 1.3770945901766023, "grad_norm": 1.491743803024292, "learning_rate": 0.0001381015727567255, "loss": 0.6087343692779541, "step": 231670 }, { "epoch": 1.3771540322532707, "grad_norm": 1.78987717628479, "learning_rate": 0.0001380956591378016, "loss": 0.6351911544799804, "step": 231680 }, { "epoch": 1.3772134743299391, "grad_norm": 1.372948169708252, "learning_rate": 0.00013808974538447732, "loss": 0.5610263347625732, "step": 231690 }, { "epoch": 1.3772729164066075, "grad_norm": 1.2987273931503296, "learning_rate": 0.00013808383149678085, "loss": 0.6198126792907714, "step": 231700 }, { "epoch": 1.377332358483276, "grad_norm": 1.535420536994934, "learning_rate": 0.0001380779174747405, "loss": 0.5710202693939209, "step": 231710 }, { "epoch": 1.3773918005599444, "grad_norm": 2.2099502086639404, "learning_rate": 0.00013807200331838462, "loss": 0.6398246765136719, "step": 231720 }, { "epoch": 1.3774512426366128, "grad_norm": 1.2141647338867188, "learning_rate": 0.0001380660890277414, "loss": 0.5965332508087158, "step": 231730 }, { "epoch": 1.3775106847132812, "grad_norm": 1.5574533939361572, "learning_rate": 0.00013806017460283917, "loss": 0.5892528533935547, "step": 231740 }, { "epoch": 1.3775701267899496, "grad_norm": 1.8574368953704834, "learning_rate": 0.0001380542600437063, "loss": 0.5757084846496582, "step": 231750 }, { "epoch": 1.377629568866618, "grad_norm": 1.5769935846328735, "learning_rate": 0.00013804834535037098, "loss": 0.557990837097168, "step": 231760 }, { "epoch": 1.3776890109432864, "grad_norm": 1.732792615890503, "learning_rate": 0.00013804243052286153, "loss": 0.6309762001037598, "step": 231770 }, { "epoch": 1.3777484530199546, "grad_norm": 1.5257556438446045, "learning_rate": 0.00013803651556120627, "loss": 0.5939303874969483, "step": 231780 }, { "epoch": 1.377807895096623, "grad_norm": 1.8446526527404785, "learning_rate": 0.00013803060046543348, "loss": 0.591319465637207, "step": 231790 }, { "epoch": 1.3778673371732915, "grad_norm": 1.2518718242645264, "learning_rate": 0.00013802468523557146, "loss": 0.6110437393188477, "step": 231800 }, { "epoch": 1.3779267792499599, "grad_norm": 1.3268511295318604, "learning_rate": 0.0001380187698716485, "loss": 0.5978468894958496, "step": 231810 }, { "epoch": 1.3779862213266283, "grad_norm": 1.1675994396209717, "learning_rate": 0.00013801285437369288, "loss": 0.5625662803649902, "step": 231820 }, { "epoch": 1.3780456634032967, "grad_norm": 1.9346174001693726, "learning_rate": 0.00013800693874173298, "loss": 0.6175097465515137, "step": 231830 }, { "epoch": 1.3781051054799651, "grad_norm": 1.6365044116973877, "learning_rate": 0.00013800102297579697, "loss": 0.5758553504943847, "step": 231840 }, { "epoch": 1.3781645475566333, "grad_norm": 1.1717123985290527, "learning_rate": 0.0001379951070759133, "loss": 0.5811854362487793, "step": 231850 }, { "epoch": 1.3782239896333017, "grad_norm": 1.6721782684326172, "learning_rate": 0.0001379891910421101, "loss": 0.6397347450256348, "step": 231860 }, { "epoch": 1.3782834317099701, "grad_norm": 1.544753909111023, "learning_rate": 0.0001379832748744158, "loss": 0.5840234756469727, "step": 231870 }, { "epoch": 1.3783428737866386, "grad_norm": 1.292535662651062, "learning_rate": 0.00013797735857285864, "loss": 0.5581277847290039, "step": 231880 }, { "epoch": 1.378402315863307, "grad_norm": 1.6104735136032104, "learning_rate": 0.00013797144213746696, "loss": 0.6249746799468994, "step": 231890 }, { "epoch": 1.3784617579399754, "grad_norm": 1.4004817008972168, "learning_rate": 0.00013796552556826904, "loss": 0.6471583366394043, "step": 231900 }, { "epoch": 1.3785212000166438, "grad_norm": 1.5325642824172974, "learning_rate": 0.00013795960886529317, "loss": 0.6083294868469238, "step": 231910 }, { "epoch": 1.3785806420933122, "grad_norm": 1.3080400228500366, "learning_rate": 0.00013795369202856768, "loss": 0.6066583156585693, "step": 231920 }, { "epoch": 1.3786400841699806, "grad_norm": 1.2447036504745483, "learning_rate": 0.00013794777505812087, "loss": 0.5959268569946289, "step": 231930 }, { "epoch": 1.378699526246649, "grad_norm": 1.6345794200897217, "learning_rate": 0.000137941857953981, "loss": 0.6314496040344239, "step": 231940 }, { "epoch": 1.3787589683233175, "grad_norm": 1.4803340435028076, "learning_rate": 0.00013793594071617642, "loss": 0.5425874710083007, "step": 231950 }, { "epoch": 1.3788184103999859, "grad_norm": 1.8974374532699585, "learning_rate": 0.0001379300233447355, "loss": 0.5889874458312988, "step": 231960 }, { "epoch": 1.378877852476654, "grad_norm": 1.6159937381744385, "learning_rate": 0.00013792410583968642, "loss": 0.5937609672546387, "step": 231970 }, { "epoch": 1.3789372945533225, "grad_norm": 1.3154454231262207, "learning_rate": 0.00013791818820105755, "loss": 0.5845124244689941, "step": 231980 }, { "epoch": 1.378996736629991, "grad_norm": 1.400818109512329, "learning_rate": 0.00013791227042887717, "loss": 0.5944217681884766, "step": 231990 }, { "epoch": 1.3790561787066593, "grad_norm": 1.4006901979446411, "learning_rate": 0.00013790635252317363, "loss": 0.5967232704162597, "step": 232000 }, { "epoch": 1.3791156207833277, "grad_norm": 1.2036784887313843, "learning_rate": 0.00013790043448397524, "loss": 0.5747224807739257, "step": 232010 }, { "epoch": 1.3791750628599961, "grad_norm": 1.8506765365600586, "learning_rate": 0.00013789451631131023, "loss": 0.6318291664123535, "step": 232020 }, { "epoch": 1.3792345049366643, "grad_norm": 1.679965853691101, "learning_rate": 0.00013788859800520703, "loss": 0.5443066596984864, "step": 232030 }, { "epoch": 1.3792939470133327, "grad_norm": 1.1717740297317505, "learning_rate": 0.00013788267956569387, "loss": 0.565403938293457, "step": 232040 }, { "epoch": 1.3793533890900012, "grad_norm": 1.4262055158615112, "learning_rate": 0.00013787676099279907, "loss": 0.6429624080657959, "step": 232050 }, { "epoch": 1.3794128311666696, "grad_norm": 1.5457371473312378, "learning_rate": 0.000137870842286551, "loss": 0.5705314159393311, "step": 232060 }, { "epoch": 1.379472273243338, "grad_norm": 1.5056228637695312, "learning_rate": 0.00013786492344697787, "loss": 0.632665491104126, "step": 232070 }, { "epoch": 1.3795317153200064, "grad_norm": 1.5338133573532104, "learning_rate": 0.0001378590044741081, "loss": 0.5717342376708985, "step": 232080 }, { "epoch": 1.3795911573966748, "grad_norm": 1.4892603158950806, "learning_rate": 0.00013785308536796992, "loss": 0.5975242614746094, "step": 232090 }, { "epoch": 1.3796505994733432, "grad_norm": 1.8347164392471313, "learning_rate": 0.0001378471661285917, "loss": 0.6130064964294434, "step": 232100 }, { "epoch": 1.3797100415500116, "grad_norm": 1.5764892101287842, "learning_rate": 0.00013784124675600174, "loss": 0.5605427742004394, "step": 232110 }, { "epoch": 1.37976948362668, "grad_norm": 1.5251933336257935, "learning_rate": 0.00013783532725022835, "loss": 0.5464473247528077, "step": 232120 }, { "epoch": 1.3798289257033485, "grad_norm": 1.587212085723877, "learning_rate": 0.00013782940761129984, "loss": 0.5802891731262207, "step": 232130 }, { "epoch": 1.379888367780017, "grad_norm": 1.5066797733306885, "learning_rate": 0.00013782348783924456, "loss": 0.5928411960601807, "step": 232140 }, { "epoch": 1.379947809856685, "grad_norm": 1.760380506515503, "learning_rate": 0.0001378175679340908, "loss": 0.617086935043335, "step": 232150 }, { "epoch": 1.3800072519333535, "grad_norm": 1.2791341543197632, "learning_rate": 0.0001378116478958669, "loss": 0.6313864231109619, "step": 232160 }, { "epoch": 1.380066694010022, "grad_norm": 1.6103354692459106, "learning_rate": 0.0001378057277246011, "loss": 0.6191071510314942, "step": 232170 }, { "epoch": 1.3801261360866903, "grad_norm": 1.6293317079544067, "learning_rate": 0.00013779980742032187, "loss": 0.6047197341918945, "step": 232180 }, { "epoch": 1.3801855781633587, "grad_norm": 1.2341411113739014, "learning_rate": 0.0001377938869830574, "loss": 0.545657730102539, "step": 232190 }, { "epoch": 1.3802450202400272, "grad_norm": 1.3330367803573608, "learning_rate": 0.00013778796641283607, "loss": 0.650595760345459, "step": 232200 }, { "epoch": 1.3803044623166956, "grad_norm": 1.521543264389038, "learning_rate": 0.0001377820457096862, "loss": 0.5611767292022705, "step": 232210 }, { "epoch": 1.3803639043933638, "grad_norm": 1.2486276626586914, "learning_rate": 0.00013777612487363608, "loss": 0.576259994506836, "step": 232220 }, { "epoch": 1.3804233464700322, "grad_norm": 1.2605397701263428, "learning_rate": 0.00013777020390471405, "loss": 0.5381998538970947, "step": 232230 }, { "epoch": 1.3804827885467006, "grad_norm": 1.6808223724365234, "learning_rate": 0.00013776428280294848, "loss": 0.5750651359558105, "step": 232240 }, { "epoch": 1.380542230623369, "grad_norm": 1.7207798957824707, "learning_rate": 0.00013775836156836764, "loss": 0.5941255569458008, "step": 232250 }, { "epoch": 1.3806016727000374, "grad_norm": 1.2843408584594727, "learning_rate": 0.00013775244020099983, "loss": 0.6126853942871093, "step": 232260 }, { "epoch": 1.3806611147767058, "grad_norm": 1.5796234607696533, "learning_rate": 0.00013774651870087344, "loss": 0.5802195549011231, "step": 232270 }, { "epoch": 1.3807205568533742, "grad_norm": 1.4389829635620117, "learning_rate": 0.0001377405970680168, "loss": 0.6344806671142578, "step": 232280 }, { "epoch": 1.3807799989300427, "grad_norm": 1.714096188545227, "learning_rate": 0.0001377346753024582, "loss": 0.5591823577880859, "step": 232290 }, { "epoch": 1.380839441006711, "grad_norm": 1.4349972009658813, "learning_rate": 0.00013772875340422596, "loss": 0.6067723751068115, "step": 232300 }, { "epoch": 1.3808988830833795, "grad_norm": 1.6081475019454956, "learning_rate": 0.0001377228313733484, "loss": 0.5800676345825195, "step": 232310 }, { "epoch": 1.380958325160048, "grad_norm": 1.5357717275619507, "learning_rate": 0.00013771690920985394, "loss": 0.5911075592041015, "step": 232320 }, { "epoch": 1.3810177672367163, "grad_norm": 1.6691536903381348, "learning_rate": 0.0001377109869137708, "loss": 0.5895939826965332, "step": 232330 }, { "epoch": 1.3810772093133845, "grad_norm": 1.2122607231140137, "learning_rate": 0.00013770506448512737, "loss": 0.5964379787445069, "step": 232340 }, { "epoch": 1.381136651390053, "grad_norm": 1.7028900384902954, "learning_rate": 0.00013769914192395197, "loss": 0.6261449813842773, "step": 232350 }, { "epoch": 1.3811960934667213, "grad_norm": 1.2980258464813232, "learning_rate": 0.0001376932192302729, "loss": 0.561616039276123, "step": 232360 }, { "epoch": 1.3812555355433898, "grad_norm": 1.772304892539978, "learning_rate": 0.00013768729640411856, "loss": 0.595362663269043, "step": 232370 }, { "epoch": 1.3813149776200582, "grad_norm": 1.1910796165466309, "learning_rate": 0.00013768137344551723, "loss": 0.5838945865631103, "step": 232380 }, { "epoch": 1.3813744196967266, "grad_norm": 1.5141870975494385, "learning_rate": 0.0001376754503544972, "loss": 0.6168002128601074, "step": 232390 }, { "epoch": 1.3814338617733948, "grad_norm": 1.4967938661575317, "learning_rate": 0.00013766952713108692, "loss": 0.5886563301086426, "step": 232400 }, { "epoch": 1.3814933038500632, "grad_norm": 1.557010531425476, "learning_rate": 0.00013766360377531463, "loss": 0.5910015106201172, "step": 232410 }, { "epoch": 1.3815527459267316, "grad_norm": 1.851279377937317, "learning_rate": 0.00013765768028720874, "loss": 0.669119930267334, "step": 232420 }, { "epoch": 1.3816121880034, "grad_norm": 1.675044298171997, "learning_rate": 0.00013765175666679752, "loss": 0.6389780044555664, "step": 232430 }, { "epoch": 1.3816716300800684, "grad_norm": 1.5760923624038696, "learning_rate": 0.00013764583291410936, "loss": 0.564131498336792, "step": 232440 }, { "epoch": 1.3817310721567369, "grad_norm": 1.4057105779647827, "learning_rate": 0.00013763990902917252, "loss": 0.622192668914795, "step": 232450 }, { "epoch": 1.3817905142334053, "grad_norm": 1.4982999563217163, "learning_rate": 0.00013763398501201544, "loss": 0.578819751739502, "step": 232460 }, { "epoch": 1.3818499563100737, "grad_norm": 1.4648067951202393, "learning_rate": 0.00013762806086266638, "loss": 0.5751577377319336, "step": 232470 }, { "epoch": 1.381909398386742, "grad_norm": 1.5241659879684448, "learning_rate": 0.0001376221365811537, "loss": 0.6437242984771728, "step": 232480 }, { "epoch": 1.3819688404634105, "grad_norm": 1.5825294256210327, "learning_rate": 0.00013761621216750575, "loss": 0.6269344329833985, "step": 232490 }, { "epoch": 1.382028282540079, "grad_norm": 1.6710282564163208, "learning_rate": 0.00013761028762175088, "loss": 0.5990055561065674, "step": 232500 }, { "epoch": 1.3820877246167473, "grad_norm": 1.6784871816635132, "learning_rate": 0.0001376043629439174, "loss": 0.582979679107666, "step": 232510 }, { "epoch": 1.3821471666934155, "grad_norm": 1.323506474494934, "learning_rate": 0.00013759843813403367, "loss": 0.5546874046325684, "step": 232520 }, { "epoch": 1.382206608770084, "grad_norm": 1.5999436378479004, "learning_rate": 0.00013759251319212806, "loss": 0.5883179664611816, "step": 232530 }, { "epoch": 1.3822660508467524, "grad_norm": 1.509617805480957, "learning_rate": 0.00013758658811822882, "loss": 0.5648746967315674, "step": 232540 }, { "epoch": 1.3823254929234208, "grad_norm": 1.4822605848312378, "learning_rate": 0.00013758066291236445, "loss": 0.6301037788391113, "step": 232550 }, { "epoch": 1.3823849350000892, "grad_norm": 1.56636381149292, "learning_rate": 0.00013757473757456315, "loss": 0.6216618061065674, "step": 232560 }, { "epoch": 1.3824443770767576, "grad_norm": 1.8594125509262085, "learning_rate": 0.0001375688121048533, "loss": 0.6525007247924804, "step": 232570 }, { "epoch": 1.382503819153426, "grad_norm": 1.4801435470581055, "learning_rate": 0.00013756288650326328, "loss": 0.5722791671752929, "step": 232580 }, { "epoch": 1.3825632612300942, "grad_norm": 1.3866618871688843, "learning_rate": 0.00013755696076982142, "loss": 0.5638947486877441, "step": 232590 }, { "epoch": 1.3826227033067626, "grad_norm": 1.6230274438858032, "learning_rate": 0.00013755103490455608, "loss": 0.6170690536499024, "step": 232600 }, { "epoch": 1.382682145383431, "grad_norm": 1.2020580768585205, "learning_rate": 0.00013754510890749556, "loss": 0.6061991691589356, "step": 232610 }, { "epoch": 1.3827415874600995, "grad_norm": 1.5913066864013672, "learning_rate": 0.00013753918277866826, "loss": 0.6154766082763672, "step": 232620 }, { "epoch": 1.3828010295367679, "grad_norm": 1.232109546661377, "learning_rate": 0.0001375332565181025, "loss": 0.5612927436828613, "step": 232630 }, { "epoch": 1.3828604716134363, "grad_norm": 1.45707368850708, "learning_rate": 0.00013752733012582666, "loss": 0.5849742889404297, "step": 232640 }, { "epoch": 1.3829199136901047, "grad_norm": 1.426937222480774, "learning_rate": 0.00013752140360186906, "loss": 0.5914081573486328, "step": 232650 }, { "epoch": 1.382979355766773, "grad_norm": 1.942274808883667, "learning_rate": 0.00013751547694625807, "loss": 0.5739737510681152, "step": 232660 }, { "epoch": 1.3830387978434415, "grad_norm": 1.524246335029602, "learning_rate": 0.000137509550159022, "loss": 0.5505771636962891, "step": 232670 }, { "epoch": 1.38309823992011, "grad_norm": 1.4911069869995117, "learning_rate": 0.00013750362324018925, "loss": 0.5962471485137939, "step": 232680 }, { "epoch": 1.3831576819967784, "grad_norm": 1.5199140310287476, "learning_rate": 0.00013749769618978813, "loss": 0.586593770980835, "step": 232690 }, { "epoch": 1.3832171240734465, "grad_norm": 1.2270090579986572, "learning_rate": 0.00013749176900784707, "loss": 0.5819267749786377, "step": 232700 }, { "epoch": 1.383276566150115, "grad_norm": 1.2420294284820557, "learning_rate": 0.00013748584169439435, "loss": 0.6373555183410644, "step": 232710 }, { "epoch": 1.3833360082267834, "grad_norm": 1.3973643779754639, "learning_rate": 0.00013747991424945831, "loss": 0.60008544921875, "step": 232720 }, { "epoch": 1.3833954503034518, "grad_norm": 1.546717882156372, "learning_rate": 0.0001374739866730674, "loss": 0.568481159210205, "step": 232730 }, { "epoch": 1.3834548923801202, "grad_norm": 1.3323798179626465, "learning_rate": 0.00013746805896524986, "loss": 0.5488807678222656, "step": 232740 }, { "epoch": 1.3835143344567886, "grad_norm": 1.262548565864563, "learning_rate": 0.0001374621311260341, "loss": 0.5559863090515137, "step": 232750 }, { "epoch": 1.383573776533457, "grad_norm": 1.2906385660171509, "learning_rate": 0.0001374562031554485, "loss": 0.616394329071045, "step": 232760 }, { "epoch": 1.3836332186101252, "grad_norm": 1.404218077659607, "learning_rate": 0.00013745027505352144, "loss": 0.5666305541992187, "step": 232770 }, { "epoch": 1.3836926606867936, "grad_norm": 1.6833622455596924, "learning_rate": 0.00013744434682028123, "loss": 0.5667763710021972, "step": 232780 }, { "epoch": 1.383752102763462, "grad_norm": 1.3957041501998901, "learning_rate": 0.00013743841845575616, "loss": 0.5823792457580567, "step": 232790 }, { "epoch": 1.3838115448401305, "grad_norm": 1.8409560918807983, "learning_rate": 0.00013743248995997471, "loss": 0.601033878326416, "step": 232800 }, { "epoch": 1.3838709869167989, "grad_norm": 1.626366376876831, "learning_rate": 0.0001374265613329652, "loss": 0.6063077926635743, "step": 232810 }, { "epoch": 1.3839304289934673, "grad_norm": 1.3533800840377808, "learning_rate": 0.00013742063257475597, "loss": 0.5949948787689209, "step": 232820 }, { "epoch": 1.3839898710701357, "grad_norm": 1.4167609214782715, "learning_rate": 0.00013741470368537541, "loss": 0.5472830772399903, "step": 232830 }, { "epoch": 1.3840493131468041, "grad_norm": 1.384735345840454, "learning_rate": 0.00013740877466485185, "loss": 0.6167888641357422, "step": 232840 }, { "epoch": 1.3841087552234725, "grad_norm": 1.6293320655822754, "learning_rate": 0.00013740284551321365, "loss": 0.578640079498291, "step": 232850 }, { "epoch": 1.384168197300141, "grad_norm": 1.5516345500946045, "learning_rate": 0.00013739691623048923, "loss": 0.589715576171875, "step": 232860 }, { "epoch": 1.3842276393768094, "grad_norm": 1.5986024141311646, "learning_rate": 0.0001373909868167069, "loss": 0.5656598091125489, "step": 232870 }, { "epoch": 1.3842870814534778, "grad_norm": 1.5471127033233643, "learning_rate": 0.00013738505727189506, "loss": 0.5987911224365234, "step": 232880 }, { "epoch": 1.384346523530146, "grad_norm": 1.4556981325149536, "learning_rate": 0.00013737912759608203, "loss": 0.5638063430786133, "step": 232890 }, { "epoch": 1.3844059656068144, "grad_norm": 1.2304743528366089, "learning_rate": 0.0001373731977892962, "loss": 0.6144794464111328, "step": 232900 }, { "epoch": 1.3844654076834828, "grad_norm": 1.235439419746399, "learning_rate": 0.00013736726785156596, "loss": 0.6119590759277344, "step": 232910 }, { "epoch": 1.3845248497601512, "grad_norm": 1.9803087711334229, "learning_rate": 0.00013736133778291965, "loss": 0.6082779884338378, "step": 232920 }, { "epoch": 1.3845842918368196, "grad_norm": 1.907310962677002, "learning_rate": 0.00013735540758338564, "loss": 0.5766753196716309, "step": 232930 }, { "epoch": 1.384643733913488, "grad_norm": 1.4863314628601074, "learning_rate": 0.00013734947725299224, "loss": 0.5900053024291992, "step": 232940 }, { "epoch": 1.3847031759901565, "grad_norm": 1.5584758520126343, "learning_rate": 0.00013734354679176795, "loss": 0.5965679168701172, "step": 232950 }, { "epoch": 1.3847626180668247, "grad_norm": 1.3633136749267578, "learning_rate": 0.00013733761619974107, "loss": 0.580873680114746, "step": 232960 }, { "epoch": 1.384822060143493, "grad_norm": 1.4315062761306763, "learning_rate": 0.00013733168547693994, "loss": 0.5776490211486817, "step": 232970 }, { "epoch": 1.3848815022201615, "grad_norm": 1.5690714120864868, "learning_rate": 0.00013732575462339298, "loss": 0.6359720706939698, "step": 232980 }, { "epoch": 1.38494094429683, "grad_norm": 1.2832263708114624, "learning_rate": 0.00013731982363912853, "loss": 0.5675977230072021, "step": 232990 }, { "epoch": 1.3850003863734983, "grad_norm": 1.5188103914260864, "learning_rate": 0.00013731389252417495, "loss": 0.5857507705688476, "step": 233000 }, { "epoch": 1.3850598284501667, "grad_norm": 1.7470110654830933, "learning_rate": 0.00013730796127856064, "loss": 0.6227792263031006, "step": 233010 }, { "epoch": 1.3851192705268351, "grad_norm": 1.4508942365646362, "learning_rate": 0.000137302029902314, "loss": 0.5943116664886474, "step": 233020 }, { "epoch": 1.3851787126035036, "grad_norm": 1.6721208095550537, "learning_rate": 0.00013729609839546335, "loss": 0.6412735462188721, "step": 233030 }, { "epoch": 1.385238154680172, "grad_norm": 1.6508746147155762, "learning_rate": 0.00013729016675803708, "loss": 0.5788337707519531, "step": 233040 }, { "epoch": 1.3852975967568404, "grad_norm": 1.363659143447876, "learning_rate": 0.00013728423499006356, "loss": 0.6869390964508056, "step": 233050 }, { "epoch": 1.3853570388335088, "grad_norm": 1.5260958671569824, "learning_rate": 0.00013727830309157125, "loss": 0.5950767040252686, "step": 233060 }, { "epoch": 1.385416480910177, "grad_norm": 1.5785000324249268, "learning_rate": 0.00013727237106258834, "loss": 0.6091302871704102, "step": 233070 }, { "epoch": 1.3854759229868454, "grad_norm": 2.281296968460083, "learning_rate": 0.0001372664389031434, "loss": 0.6332927227020264, "step": 233080 }, { "epoch": 1.3855353650635138, "grad_norm": 1.6943811178207397, "learning_rate": 0.0001372605066132647, "loss": 0.6170408725738525, "step": 233090 }, { "epoch": 1.3855948071401822, "grad_norm": 1.4645391702651978, "learning_rate": 0.00013725457419298066, "loss": 0.5696902275085449, "step": 233100 }, { "epoch": 1.3856542492168507, "grad_norm": 1.5082534551620483, "learning_rate": 0.00013724864164231962, "loss": 0.5376996040344239, "step": 233110 }, { "epoch": 1.385713691293519, "grad_norm": 1.2730151414871216, "learning_rate": 0.00013724270896131003, "loss": 0.570750617980957, "step": 233120 }, { "epoch": 1.3857731333701875, "grad_norm": 1.6033291816711426, "learning_rate": 0.00013723677614998014, "loss": 0.6395713806152343, "step": 233130 }, { "epoch": 1.3858325754468557, "grad_norm": 1.8209677934646606, "learning_rate": 0.0001372308432083585, "loss": 0.6117686271667481, "step": 233140 }, { "epoch": 1.385892017523524, "grad_norm": 1.528740644454956, "learning_rate": 0.00013722491013647337, "loss": 0.6252573966979981, "step": 233150 }, { "epoch": 1.3859514596001925, "grad_norm": 1.7414947748184204, "learning_rate": 0.00013721897693435314, "loss": 0.6190931320190429, "step": 233160 }, { "epoch": 1.386010901676861, "grad_norm": 1.3262656927108765, "learning_rate": 0.00013721304360202628, "loss": 0.5760553359985352, "step": 233170 }, { "epoch": 1.3860703437535293, "grad_norm": 1.1186634302139282, "learning_rate": 0.00013720711013952107, "loss": 0.5568859100341796, "step": 233180 }, { "epoch": 1.3861297858301977, "grad_norm": 1.3320424556732178, "learning_rate": 0.00013720117654686593, "loss": 0.49570608139038086, "step": 233190 }, { "epoch": 1.3861892279068662, "grad_norm": 1.4949146509170532, "learning_rate": 0.0001371952428240893, "loss": 0.5668277740478516, "step": 233200 }, { "epoch": 1.3862486699835346, "grad_norm": 1.5689208507537842, "learning_rate": 0.00013718930897121945, "loss": 0.6254645347595215, "step": 233210 }, { "epoch": 1.386308112060203, "grad_norm": 1.3634278774261475, "learning_rate": 0.00013718337498828487, "loss": 0.5714668273925781, "step": 233220 }, { "epoch": 1.3863675541368714, "grad_norm": 1.7229982614517212, "learning_rate": 0.0001371774408753139, "loss": 0.589180326461792, "step": 233230 }, { "epoch": 1.3864269962135398, "grad_norm": 1.3684877157211304, "learning_rate": 0.00013717150663233497, "loss": 0.6171282291412353, "step": 233240 }, { "epoch": 1.3864864382902082, "grad_norm": 1.5085846185684204, "learning_rate": 0.00013716557225937635, "loss": 0.6100642204284668, "step": 233250 }, { "epoch": 1.3865458803668764, "grad_norm": 1.6724478006362915, "learning_rate": 0.00013715963775646657, "loss": 0.6178577899932861, "step": 233260 }, { "epoch": 1.3866053224435448, "grad_norm": 1.3457320928573608, "learning_rate": 0.00013715370312363396, "loss": 0.5564860343933106, "step": 233270 }, { "epoch": 1.3866647645202133, "grad_norm": 1.3841438293457031, "learning_rate": 0.0001371477683609069, "loss": 0.6119905471801758, "step": 233280 }, { "epoch": 1.3867242065968817, "grad_norm": 1.3809735774993896, "learning_rate": 0.00013714183346831375, "loss": 0.5959386825561523, "step": 233290 }, { "epoch": 1.38678364867355, "grad_norm": 1.7496650218963623, "learning_rate": 0.000137135898445883, "loss": 0.6496105194091797, "step": 233300 }, { "epoch": 1.3868430907502185, "grad_norm": 1.187530517578125, "learning_rate": 0.00013712996329364293, "loss": 0.6066434383392334, "step": 233310 }, { "epoch": 1.386902532826887, "grad_norm": 1.7160723209381104, "learning_rate": 0.00013712402801162202, "loss": 0.608786153793335, "step": 233320 }, { "epoch": 1.386961974903555, "grad_norm": 1.7559207677841187, "learning_rate": 0.0001371180925998486, "loss": 0.6383302688598633, "step": 233330 }, { "epoch": 1.3870214169802235, "grad_norm": 1.819213628768921, "learning_rate": 0.0001371121570583511, "loss": 0.5849905014038086, "step": 233340 }, { "epoch": 1.387080859056892, "grad_norm": 1.7844318151474, "learning_rate": 0.00013710622138715789, "loss": 0.6605049133300781, "step": 233350 }, { "epoch": 1.3871403011335603, "grad_norm": 2.0173192024230957, "learning_rate": 0.00013710028558629737, "loss": 0.6167763710021973, "step": 233360 }, { "epoch": 1.3871997432102288, "grad_norm": 1.4239956140518188, "learning_rate": 0.00013709434965579798, "loss": 0.5985570907592773, "step": 233370 }, { "epoch": 1.3872591852868972, "grad_norm": 1.4899309873580933, "learning_rate": 0.00013708841359568805, "loss": 0.5681578636169433, "step": 233380 }, { "epoch": 1.3873186273635656, "grad_norm": 2.126495122909546, "learning_rate": 0.000137082477405996, "loss": 0.6251530647277832, "step": 233390 }, { "epoch": 1.387378069440234, "grad_norm": 1.1466562747955322, "learning_rate": 0.00013707654108675022, "loss": 0.641215705871582, "step": 233400 }, { "epoch": 1.3874375115169024, "grad_norm": 1.7637335062026978, "learning_rate": 0.0001370706046379791, "loss": 0.6034399986267089, "step": 233410 }, { "epoch": 1.3874969535935708, "grad_norm": 1.406079888343811, "learning_rate": 0.0001370646680597111, "loss": 0.5929802894592285, "step": 233420 }, { "epoch": 1.3875563956702393, "grad_norm": 1.4206758737564087, "learning_rate": 0.00013705873135197455, "loss": 0.5506341934204102, "step": 233430 }, { "epoch": 1.3876158377469074, "grad_norm": 1.2108911275863647, "learning_rate": 0.00013705279451479787, "loss": 0.5662811279296875, "step": 233440 }, { "epoch": 1.3876752798235759, "grad_norm": 1.2350964546203613, "learning_rate": 0.00013704685754820946, "loss": 0.5865456104278565, "step": 233450 }, { "epoch": 1.3877347219002443, "grad_norm": 1.5243881940841675, "learning_rate": 0.00013704092045223773, "loss": 0.7047689437866211, "step": 233460 }, { "epoch": 1.3877941639769127, "grad_norm": 1.8839269876480103, "learning_rate": 0.00013703498322691107, "loss": 0.6786168098449707, "step": 233470 }, { "epoch": 1.387853606053581, "grad_norm": 1.4444950819015503, "learning_rate": 0.0001370290458722579, "loss": 0.6479104995727539, "step": 233480 }, { "epoch": 1.3879130481302495, "grad_norm": 1.536031723022461, "learning_rate": 0.00013702310838830656, "loss": 0.5907955169677734, "step": 233490 }, { "epoch": 1.387972490206918, "grad_norm": 1.7893638610839844, "learning_rate": 0.00013701717077508555, "loss": 0.5987500190734864, "step": 233500 }, { "epoch": 1.3880319322835861, "grad_norm": 1.6683605909347534, "learning_rate": 0.00013701123303262323, "loss": 0.6042468547821045, "step": 233510 }, { "epoch": 1.3880913743602545, "grad_norm": 1.4375406503677368, "learning_rate": 0.00013700529516094795, "loss": 0.6173933029174805, "step": 233520 }, { "epoch": 1.388150816436923, "grad_norm": 1.7615010738372803, "learning_rate": 0.0001369993571600882, "loss": 0.5975939750671386, "step": 233530 }, { "epoch": 1.3882102585135914, "grad_norm": 1.655120849609375, "learning_rate": 0.00013699341903007235, "loss": 0.6007909774780273, "step": 233540 }, { "epoch": 1.3882697005902598, "grad_norm": 1.6873319149017334, "learning_rate": 0.0001369874807709288, "loss": 0.5349249839782715, "step": 233550 }, { "epoch": 1.3883291426669282, "grad_norm": 1.0702506303787231, "learning_rate": 0.00013698154238268593, "loss": 0.6000924587249756, "step": 233560 }, { "epoch": 1.3883885847435966, "grad_norm": 1.144731879234314, "learning_rate": 0.0001369756038653722, "loss": 0.5970838069915771, "step": 233570 }, { "epoch": 1.388448026820265, "grad_norm": 1.394354224205017, "learning_rate": 0.00013696966521901602, "loss": 0.5997806072235108, "step": 233580 }, { "epoch": 1.3885074688969334, "grad_norm": 1.3743371963500977, "learning_rate": 0.00013696372644364575, "loss": 0.5783668994903565, "step": 233590 }, { "epoch": 1.3885669109736019, "grad_norm": 1.8012640476226807, "learning_rate": 0.00013695778753928985, "loss": 0.5624542713165284, "step": 233600 }, { "epoch": 1.3886263530502703, "grad_norm": 2.243617296218872, "learning_rate": 0.00013695184850597667, "loss": 0.679974365234375, "step": 233610 }, { "epoch": 1.3886857951269387, "grad_norm": 1.3668749332427979, "learning_rate": 0.00013694590934373467, "loss": 0.550998592376709, "step": 233620 }, { "epoch": 1.3887452372036069, "grad_norm": 1.8593409061431885, "learning_rate": 0.00013693997005259227, "loss": 0.6287014484405518, "step": 233630 }, { "epoch": 1.3888046792802753, "grad_norm": 1.5002800226211548, "learning_rate": 0.00013693403063257781, "loss": 0.6227073669433594, "step": 233640 }, { "epoch": 1.3888641213569437, "grad_norm": 1.6015828847885132, "learning_rate": 0.00013692809108371975, "loss": 0.5557902336120606, "step": 233650 }, { "epoch": 1.3889235634336121, "grad_norm": 1.2165898084640503, "learning_rate": 0.0001369221514060466, "loss": 0.6288654804229736, "step": 233660 }, { "epoch": 1.3889830055102805, "grad_norm": 1.4058685302734375, "learning_rate": 0.00013691621159958654, "loss": 0.653108024597168, "step": 233670 }, { "epoch": 1.389042447586949, "grad_norm": 1.5777714252471924, "learning_rate": 0.0001369102716643682, "loss": 0.5520267486572266, "step": 233680 }, { "epoch": 1.3891018896636174, "grad_norm": 1.3257101774215698, "learning_rate": 0.00013690433160041992, "loss": 0.5808544158935547, "step": 233690 }, { "epoch": 1.3891613317402856, "grad_norm": 1.6667959690093994, "learning_rate": 0.00013689839140777006, "loss": 0.6212369441986084, "step": 233700 }, { "epoch": 1.389220773816954, "grad_norm": 1.555005431175232, "learning_rate": 0.00013689245108644712, "loss": 0.5977875709533691, "step": 233710 }, { "epoch": 1.3892802158936224, "grad_norm": 1.7774211168289185, "learning_rate": 0.0001368865106364795, "loss": 0.6263835906982422, "step": 233720 }, { "epoch": 1.3893396579702908, "grad_norm": 2.1148993968963623, "learning_rate": 0.00013688057005789556, "loss": 0.6052825927734375, "step": 233730 }, { "epoch": 1.3893991000469592, "grad_norm": 1.2848291397094727, "learning_rate": 0.00013687462935072376, "loss": 0.5656785488128662, "step": 233740 }, { "epoch": 1.3894585421236276, "grad_norm": 1.4598371982574463, "learning_rate": 0.00013686868851499256, "loss": 0.5829314231872559, "step": 233750 }, { "epoch": 1.389517984200296, "grad_norm": 1.74847412109375, "learning_rate": 0.00013686274755073027, "loss": 0.5848736763000488, "step": 233760 }, { "epoch": 1.3895774262769645, "grad_norm": 1.9892323017120361, "learning_rate": 0.0001368568064579654, "loss": 0.5723390102386474, "step": 233770 }, { "epoch": 1.3896368683536329, "grad_norm": 1.6694456338882446, "learning_rate": 0.00013685086523672636, "loss": 0.606119966506958, "step": 233780 }, { "epoch": 1.3896963104303013, "grad_norm": 1.8194048404693604, "learning_rate": 0.00013684492388704156, "loss": 0.5907588005065918, "step": 233790 }, { "epoch": 1.3897557525069697, "grad_norm": 1.6419284343719482, "learning_rate": 0.00013683898240893938, "loss": 0.5790693283081054, "step": 233800 }, { "epoch": 1.389815194583638, "grad_norm": 1.418541669845581, "learning_rate": 0.00013683304080244833, "loss": 0.605507755279541, "step": 233810 }, { "epoch": 1.3898746366603063, "grad_norm": 1.6027021408081055, "learning_rate": 0.00013682709906759677, "loss": 0.6500889778137207, "step": 233820 }, { "epoch": 1.3899340787369747, "grad_norm": 1.4676604270935059, "learning_rate": 0.0001368211572044131, "loss": 0.5774681568145752, "step": 233830 }, { "epoch": 1.3899935208136431, "grad_norm": 1.5299996137619019, "learning_rate": 0.0001368152152129258, "loss": 0.5548989295959472, "step": 233840 }, { "epoch": 1.3900529628903115, "grad_norm": 1.3233412504196167, "learning_rate": 0.00013680927309316326, "loss": 0.5420106887817383, "step": 233850 }, { "epoch": 1.39011240496698, "grad_norm": 1.6991440057754517, "learning_rate": 0.00013680333084515396, "loss": 0.6628591537475585, "step": 233860 }, { "epoch": 1.3901718470436484, "grad_norm": 1.4218062162399292, "learning_rate": 0.00013679738846892624, "loss": 0.6220965385437012, "step": 233870 }, { "epoch": 1.3902312891203166, "grad_norm": 1.187298059463501, "learning_rate": 0.00013679144596450858, "loss": 0.5877642631530762, "step": 233880 }, { "epoch": 1.390290731196985, "grad_norm": 1.6478956937789917, "learning_rate": 0.00013678550333192944, "loss": 0.5883075714111328, "step": 233890 }, { "epoch": 1.3903501732736534, "grad_norm": 1.3393363952636719, "learning_rate": 0.00013677956057121714, "loss": 0.585905933380127, "step": 233900 }, { "epoch": 1.3904096153503218, "grad_norm": 1.503856897354126, "learning_rate": 0.00013677361768240024, "loss": 0.6423878192901611, "step": 233910 }, { "epoch": 1.3904690574269902, "grad_norm": 1.612754464149475, "learning_rate": 0.00013676767466550707, "loss": 0.5867316246032714, "step": 233920 }, { "epoch": 1.3905284995036586, "grad_norm": 1.7153661251068115, "learning_rate": 0.00013676173152056607, "loss": 0.6151429176330566, "step": 233930 }, { "epoch": 1.390587941580327, "grad_norm": 1.70224928855896, "learning_rate": 0.00013675578824760574, "loss": 0.5601634025573731, "step": 233940 }, { "epoch": 1.3906473836569955, "grad_norm": 1.5491043329238892, "learning_rate": 0.00013674984484665444, "loss": 0.581661605834961, "step": 233950 }, { "epoch": 1.3907068257336639, "grad_norm": 1.2731727361679077, "learning_rate": 0.0001367439013177406, "loss": 0.6123803615570068, "step": 233960 }, { "epoch": 1.3907662678103323, "grad_norm": 1.3757766485214233, "learning_rate": 0.0001367379576608927, "loss": 0.6267389297485352, "step": 233970 }, { "epoch": 1.3908257098870007, "grad_norm": 1.929612398147583, "learning_rate": 0.00013673201387613915, "loss": 0.5902031421661377, "step": 233980 }, { "epoch": 1.3908851519636691, "grad_norm": 1.832463264465332, "learning_rate": 0.0001367260699635084, "loss": 0.6004868507385254, "step": 233990 }, { "epoch": 1.3909445940403373, "grad_norm": 1.785650372505188, "learning_rate": 0.00013672012592302882, "loss": 0.5908114433288574, "step": 234000 }, { "epoch": 1.3910040361170057, "grad_norm": 1.5330713987350464, "learning_rate": 0.0001367141817547289, "loss": 0.5756395816802978, "step": 234010 }, { "epoch": 1.3910634781936742, "grad_norm": 1.2255852222442627, "learning_rate": 0.00013670823745863707, "loss": 0.6066102981567383, "step": 234020 }, { "epoch": 1.3911229202703426, "grad_norm": 1.776981234550476, "learning_rate": 0.0001367022930347818, "loss": 0.6681995391845703, "step": 234030 }, { "epoch": 1.391182362347011, "grad_norm": 1.4899808168411255, "learning_rate": 0.00013669634848319145, "loss": 0.5533917427062989, "step": 234040 }, { "epoch": 1.3912418044236794, "grad_norm": 1.3302372694015503, "learning_rate": 0.0001366904038038945, "loss": 0.6493119716644287, "step": 234050 }, { "epoch": 1.3913012465003478, "grad_norm": 1.3792314529418945, "learning_rate": 0.0001366844589969194, "loss": 0.5610907554626465, "step": 234060 }, { "epoch": 1.391360688577016, "grad_norm": 1.5923569202423096, "learning_rate": 0.00013667851406229452, "loss": 0.5918779850006104, "step": 234070 }, { "epoch": 1.3914201306536844, "grad_norm": 1.9491705894470215, "learning_rate": 0.00013667256900004837, "loss": 0.6490791797637939, "step": 234080 }, { "epoch": 1.3914795727303528, "grad_norm": 1.4874019622802734, "learning_rate": 0.0001366666238102094, "loss": 0.552531099319458, "step": 234090 }, { "epoch": 1.3915390148070212, "grad_norm": 1.4053069353103638, "learning_rate": 0.00013666067849280598, "loss": 0.564886474609375, "step": 234100 }, { "epoch": 1.3915984568836897, "grad_norm": 1.4790312051773071, "learning_rate": 0.00013665473304786657, "loss": 0.5364726543426513, "step": 234110 }, { "epoch": 1.391657898960358, "grad_norm": 1.5589617490768433, "learning_rate": 0.00013664878747541968, "loss": 0.5779383182525635, "step": 234120 }, { "epoch": 1.3917173410370265, "grad_norm": 1.6483203172683716, "learning_rate": 0.00013664284177549368, "loss": 0.5943245887756348, "step": 234130 }, { "epoch": 1.391776783113695, "grad_norm": 1.4491777420043945, "learning_rate": 0.000136636895948117, "loss": 0.5598290443420411, "step": 234140 }, { "epoch": 1.3918362251903633, "grad_norm": 1.335333228111267, "learning_rate": 0.00013663094999331817, "loss": 0.5857983589172363, "step": 234150 }, { "epoch": 1.3918956672670317, "grad_norm": 1.3171100616455078, "learning_rate": 0.00013662500391112552, "loss": 0.5651041984558105, "step": 234160 }, { "epoch": 1.3919551093437001, "grad_norm": 1.3003803491592407, "learning_rate": 0.0001366190577015676, "loss": 0.6045775413513184, "step": 234170 }, { "epoch": 1.3920145514203683, "grad_norm": 1.6185942888259888, "learning_rate": 0.00013661311136467277, "loss": 0.6205322742462158, "step": 234180 }, { "epoch": 1.3920739934970368, "grad_norm": 1.360565185546875, "learning_rate": 0.00013660716490046954, "loss": 0.5478181838989258, "step": 234190 }, { "epoch": 1.3921334355737052, "grad_norm": 1.5899972915649414, "learning_rate": 0.00013660121830898631, "loss": 0.5759111404418945, "step": 234200 }, { "epoch": 1.3921928776503736, "grad_norm": 1.806422472000122, "learning_rate": 0.00013659527159025155, "loss": 0.638411283493042, "step": 234210 }, { "epoch": 1.392252319727042, "grad_norm": 1.7415918111801147, "learning_rate": 0.00013658932474429371, "loss": 0.5435222625732422, "step": 234220 }, { "epoch": 1.3923117618037104, "grad_norm": 1.7404271364212036, "learning_rate": 0.00013658337777114124, "loss": 0.5507623195648194, "step": 234230 }, { "epoch": 1.3923712038803788, "grad_norm": 1.4692155122756958, "learning_rate": 0.00013657743067082255, "loss": 0.6047599792480469, "step": 234240 }, { "epoch": 1.392430645957047, "grad_norm": 1.520268440246582, "learning_rate": 0.00013657148344336614, "loss": 0.5579304695129395, "step": 234250 }, { "epoch": 1.3924900880337154, "grad_norm": 1.3805221319198608, "learning_rate": 0.00013656553608880042, "loss": 0.5946914672851562, "step": 234260 }, { "epoch": 1.3925495301103838, "grad_norm": 1.4341838359832764, "learning_rate": 0.00013655958860715387, "loss": 0.5994383811950683, "step": 234270 }, { "epoch": 1.3926089721870523, "grad_norm": 1.7320822477340698, "learning_rate": 0.00013655364099845492, "loss": 0.6301647186279297, "step": 234280 }, { "epoch": 1.3926684142637207, "grad_norm": 1.2880761623382568, "learning_rate": 0.00013654769326273202, "loss": 0.6328328132629395, "step": 234290 }, { "epoch": 1.392727856340389, "grad_norm": 1.449985384941101, "learning_rate": 0.00013654174540001366, "loss": 0.5935938358306885, "step": 234300 }, { "epoch": 1.3927872984170575, "grad_norm": 1.2531300783157349, "learning_rate": 0.00013653579741032822, "loss": 0.5317433834075928, "step": 234310 }, { "epoch": 1.392846740493726, "grad_norm": 1.5434048175811768, "learning_rate": 0.00013652984929370422, "loss": 0.6047148704528809, "step": 234320 }, { "epoch": 1.3929061825703943, "grad_norm": 2.3008675575256348, "learning_rate": 0.00013652390105017013, "loss": 0.6184386253356934, "step": 234330 }, { "epoch": 1.3929656246470628, "grad_norm": 1.4190224409103394, "learning_rate": 0.00013651795267975432, "loss": 0.6616971015930175, "step": 234340 }, { "epoch": 1.3930250667237312, "grad_norm": 1.3268474340438843, "learning_rate": 0.00013651200418248531, "loss": 0.621416711807251, "step": 234350 }, { "epoch": 1.3930845088003996, "grad_norm": 1.388453483581543, "learning_rate": 0.00013650605555839152, "loss": 0.5859485149383545, "step": 234360 }, { "epoch": 1.3931439508770678, "grad_norm": 1.436898112297058, "learning_rate": 0.00013650010680750144, "loss": 0.5694676876068115, "step": 234370 }, { "epoch": 1.3932033929537362, "grad_norm": 1.6488615274429321, "learning_rate": 0.0001364941579298435, "loss": 0.6173006534576416, "step": 234380 }, { "epoch": 1.3932628350304046, "grad_norm": 1.6367053985595703, "learning_rate": 0.00013648820892544613, "loss": 0.689304256439209, "step": 234390 }, { "epoch": 1.393322277107073, "grad_norm": 1.22078537940979, "learning_rate": 0.0001364822597943379, "loss": 0.5736837387084961, "step": 234400 }, { "epoch": 1.3933817191837414, "grad_norm": 1.4329009056091309, "learning_rate": 0.00013647631053654715, "loss": 0.6189841747283935, "step": 234410 }, { "epoch": 1.3934411612604098, "grad_norm": 1.7451227903366089, "learning_rate": 0.00013647036115210236, "loss": 0.5738199710845947, "step": 234420 }, { "epoch": 1.3935006033370783, "grad_norm": 1.5121651887893677, "learning_rate": 0.00013646441164103207, "loss": 0.5912814140319824, "step": 234430 }, { "epoch": 1.3935600454137465, "grad_norm": 1.846751093864441, "learning_rate": 0.00013645846200336466, "loss": 0.5640386581420899, "step": 234440 }, { "epoch": 1.3936194874904149, "grad_norm": 1.6773667335510254, "learning_rate": 0.00013645251223912857, "loss": 0.6091232776641846, "step": 234450 }, { "epoch": 1.3936789295670833, "grad_norm": 1.4250078201293945, "learning_rate": 0.00013644656234835237, "loss": 0.5896654605865479, "step": 234460 }, { "epoch": 1.3937383716437517, "grad_norm": 1.14034104347229, "learning_rate": 0.00013644061233106442, "loss": 0.5972142219543457, "step": 234470 }, { "epoch": 1.39379781372042, "grad_norm": 1.5623650550842285, "learning_rate": 0.00013643466218729323, "loss": 0.594583797454834, "step": 234480 }, { "epoch": 1.3938572557970885, "grad_norm": 1.6408804655075073, "learning_rate": 0.00013642871191706728, "loss": 0.6596325874328614, "step": 234490 }, { "epoch": 1.393916697873757, "grad_norm": 1.41362464427948, "learning_rate": 0.00013642276152041498, "loss": 0.6202831268310547, "step": 234500 }, { "epoch": 1.3939761399504254, "grad_norm": 1.022524356842041, "learning_rate": 0.00013641681099736482, "loss": 0.6206619739532471, "step": 234510 }, { "epoch": 1.3940355820270938, "grad_norm": 1.5142754316329956, "learning_rate": 0.00013641086034794531, "loss": 0.5597760200500488, "step": 234520 }, { "epoch": 1.3940950241037622, "grad_norm": 1.8324111700057983, "learning_rate": 0.00013640490957218487, "loss": 0.5893229007720947, "step": 234530 }, { "epoch": 1.3941544661804306, "grad_norm": 1.3175824880599976, "learning_rate": 0.0001363989586701119, "loss": 0.6104625225067138, "step": 234540 }, { "epoch": 1.3942139082570988, "grad_norm": 1.6176888942718506, "learning_rate": 0.000136393007641755, "loss": 0.5711176872253418, "step": 234550 }, { "epoch": 1.3942733503337672, "grad_norm": 1.5047215223312378, "learning_rate": 0.0001363870564871426, "loss": 0.5354305744171143, "step": 234560 }, { "epoch": 1.3943327924104356, "grad_norm": 1.531825065612793, "learning_rate": 0.00013638110520630307, "loss": 0.5666730403900146, "step": 234570 }, { "epoch": 1.394392234487104, "grad_norm": 1.7019550800323486, "learning_rate": 0.000136375153799265, "loss": 0.6426033020019531, "step": 234580 }, { "epoch": 1.3944516765637724, "grad_norm": 1.6459460258483887, "learning_rate": 0.0001363692022660568, "loss": 0.5837440490722656, "step": 234590 }, { "epoch": 1.3945111186404409, "grad_norm": 1.328373670578003, "learning_rate": 0.00013636325060670696, "loss": 0.56390380859375, "step": 234600 }, { "epoch": 1.3945705607171093, "grad_norm": 1.7970730066299438, "learning_rate": 0.00013635729882124396, "loss": 0.5984631538391113, "step": 234610 }, { "epoch": 1.3946300027937775, "grad_norm": 1.533994436264038, "learning_rate": 0.00013635134690969625, "loss": 0.5783572673797608, "step": 234620 }, { "epoch": 1.3946894448704459, "grad_norm": 1.6747150421142578, "learning_rate": 0.00013634539487209228, "loss": 0.6621872901916503, "step": 234630 }, { "epoch": 1.3947488869471143, "grad_norm": 1.743464708328247, "learning_rate": 0.0001363394427084606, "loss": 0.6244192123413086, "step": 234640 }, { "epoch": 1.3948083290237827, "grad_norm": 1.3730182647705078, "learning_rate": 0.0001363334904188296, "loss": 0.5845019340515136, "step": 234650 }, { "epoch": 1.3948677711004511, "grad_norm": 1.2273335456848145, "learning_rate": 0.0001363275380032278, "loss": 0.5993251323699951, "step": 234660 }, { "epoch": 1.3949272131771195, "grad_norm": 1.6157652139663696, "learning_rate": 0.00013632158546168362, "loss": 0.6106209754943848, "step": 234670 }, { "epoch": 1.394986655253788, "grad_norm": 1.4959901571273804, "learning_rate": 0.00013631563279422563, "loss": 0.5817204475402832, "step": 234680 }, { "epoch": 1.3950460973304564, "grad_norm": 1.5027915239334106, "learning_rate": 0.00013630968000088225, "loss": 0.5177321910858155, "step": 234690 }, { "epoch": 1.3951055394071248, "grad_norm": 1.3706847429275513, "learning_rate": 0.00013630372708168194, "loss": 0.5568943500518799, "step": 234700 }, { "epoch": 1.3951649814837932, "grad_norm": 1.5529729127883911, "learning_rate": 0.0001362977740366532, "loss": 0.6324036598205567, "step": 234710 }, { "epoch": 1.3952244235604616, "grad_norm": 1.131378173828125, "learning_rate": 0.0001362918208658245, "loss": 0.5899126529693604, "step": 234720 }, { "epoch": 1.39528386563713, "grad_norm": 1.6573411226272583, "learning_rate": 0.00013628586756922432, "loss": 0.6039727210998536, "step": 234730 }, { "epoch": 1.3953433077137982, "grad_norm": 1.7057071924209595, "learning_rate": 0.00013627991414688116, "loss": 0.6113882064819336, "step": 234740 }, { "epoch": 1.3954027497904666, "grad_norm": 1.4575793743133545, "learning_rate": 0.00013627396059882345, "loss": 0.6068305492401123, "step": 234750 }, { "epoch": 1.395462191867135, "grad_norm": 1.5319463014602661, "learning_rate": 0.00013626800692507972, "loss": 0.5887567520141601, "step": 234760 }, { "epoch": 1.3955216339438035, "grad_norm": 1.6901453733444214, "learning_rate": 0.00013626205312567845, "loss": 0.5911082267761231, "step": 234770 }, { "epoch": 1.3955810760204719, "grad_norm": 1.9272884130477905, "learning_rate": 0.00013625609920064804, "loss": 0.5931288719177246, "step": 234780 }, { "epoch": 1.3956405180971403, "grad_norm": 1.4432436227798462, "learning_rate": 0.00013625014515001706, "loss": 0.5614080905914307, "step": 234790 }, { "epoch": 1.3956999601738087, "grad_norm": 1.3574166297912598, "learning_rate": 0.00013624419097381398, "loss": 0.6131924629211426, "step": 234800 }, { "epoch": 1.395759402250477, "grad_norm": 1.7535232305526733, "learning_rate": 0.00013623823667206723, "loss": 0.575256061553955, "step": 234810 }, { "epoch": 1.3958188443271453, "grad_norm": 1.452195405960083, "learning_rate": 0.00013623228224480535, "loss": 0.6444331169128418, "step": 234820 }, { "epoch": 1.3958782864038137, "grad_norm": 1.7831742763519287, "learning_rate": 0.00013622632769205685, "loss": 0.6125691890716553, "step": 234830 }, { "epoch": 1.3959377284804821, "grad_norm": 1.4237200021743774, "learning_rate": 0.00013622037301385013, "loss": 0.6108307838439941, "step": 234840 }, { "epoch": 1.3959971705571506, "grad_norm": 1.43040931224823, "learning_rate": 0.0001362144182102137, "loss": 0.599720048904419, "step": 234850 }, { "epoch": 1.396056612633819, "grad_norm": 1.1085649728775024, "learning_rate": 0.00013620846328117606, "loss": 0.5121517181396484, "step": 234860 }, { "epoch": 1.3961160547104874, "grad_norm": 1.6157357692718506, "learning_rate": 0.00013620250822676572, "loss": 0.584589672088623, "step": 234870 }, { "epoch": 1.3961754967871558, "grad_norm": 1.7077436447143555, "learning_rate": 0.00013619655304701112, "loss": 0.575728178024292, "step": 234880 }, { "epoch": 1.3962349388638242, "grad_norm": 1.8983728885650635, "learning_rate": 0.00013619059774194083, "loss": 0.6214495182037354, "step": 234890 }, { "epoch": 1.3962943809404926, "grad_norm": 1.3831709623336792, "learning_rate": 0.0001361846423115832, "loss": 0.593682336807251, "step": 234900 }, { "epoch": 1.396353823017161, "grad_norm": 1.2707051038742065, "learning_rate": 0.00013617868675596683, "loss": 0.5882826328277588, "step": 234910 }, { "epoch": 1.3964132650938292, "grad_norm": 1.5137237310409546, "learning_rate": 0.0001361727310751202, "loss": 0.6278074264526368, "step": 234920 }, { "epoch": 1.3964727071704977, "grad_norm": 1.377811074256897, "learning_rate": 0.00013616677526907174, "loss": 0.5307087421417236, "step": 234930 }, { "epoch": 1.396532149247166, "grad_norm": 1.4268443584442139, "learning_rate": 0.00013616081933785003, "loss": 0.5735708236694336, "step": 234940 }, { "epoch": 1.3965915913238345, "grad_norm": 1.3767937421798706, "learning_rate": 0.00013615486328148347, "loss": 0.6639334678649902, "step": 234950 }, { "epoch": 1.396651033400503, "grad_norm": 1.5221017599105835, "learning_rate": 0.00013614890710000058, "loss": 0.5914653778076172, "step": 234960 }, { "epoch": 1.3967104754771713, "grad_norm": 1.9762229919433594, "learning_rate": 0.00013614295079342992, "loss": 0.5890409469604492, "step": 234970 }, { "epoch": 1.3967699175538397, "grad_norm": 1.6130303144454956, "learning_rate": 0.00013613699436179988, "loss": 0.6235748291015625, "step": 234980 }, { "epoch": 1.396829359630508, "grad_norm": 1.000824213027954, "learning_rate": 0.00013613103780513899, "loss": 0.5477154731750489, "step": 234990 }, { "epoch": 1.3968888017071763, "grad_norm": 1.2051702737808228, "learning_rate": 0.0001361250811234758, "loss": 0.5739795684814453, "step": 235000 }, { "epoch": 1.3969482437838447, "grad_norm": 1.4471455812454224, "learning_rate": 0.0001361191243168387, "loss": 0.6006373405456543, "step": 235010 }, { "epoch": 1.3970076858605132, "grad_norm": 1.012486219406128, "learning_rate": 0.0001361131673852563, "loss": 0.5796589851379395, "step": 235020 }, { "epoch": 1.3970671279371816, "grad_norm": 1.655989170074463, "learning_rate": 0.00013610721032875702, "loss": 0.6743892192840576, "step": 235030 }, { "epoch": 1.39712657001385, "grad_norm": 1.5447688102722168, "learning_rate": 0.00013610125314736938, "loss": 0.579855489730835, "step": 235040 }, { "epoch": 1.3971860120905184, "grad_norm": 1.5225951671600342, "learning_rate": 0.0001360952958411219, "loss": 0.5789385795593261, "step": 235050 }, { "epoch": 1.3972454541671868, "grad_norm": 1.6254289150238037, "learning_rate": 0.000136089338410043, "loss": 0.6143045425415039, "step": 235060 }, { "epoch": 1.3973048962438552, "grad_norm": 2.2510364055633545, "learning_rate": 0.00013608338085416126, "loss": 0.6041010856628418, "step": 235070 }, { "epoch": 1.3973643383205236, "grad_norm": 1.3449175357818604, "learning_rate": 0.00013607742317350515, "loss": 0.6000535964965821, "step": 235080 }, { "epoch": 1.397423780397192, "grad_norm": 1.560028076171875, "learning_rate": 0.0001360714653681032, "loss": 0.5974605560302735, "step": 235090 }, { "epoch": 1.3974832224738605, "grad_norm": 1.4375056028366089, "learning_rate": 0.0001360655074379838, "loss": 0.6569306373596191, "step": 235100 }, { "epoch": 1.3975426645505287, "grad_norm": 1.3656339645385742, "learning_rate": 0.00013605954938317562, "loss": 0.6174785614013671, "step": 235110 }, { "epoch": 1.397602106627197, "grad_norm": 1.3731416463851929, "learning_rate": 0.00013605359120370702, "loss": 0.6361218452453613, "step": 235120 }, { "epoch": 1.3976615487038655, "grad_norm": 1.0997552871704102, "learning_rate": 0.00013604763289960654, "loss": 0.572946834564209, "step": 235130 }, { "epoch": 1.397720990780534, "grad_norm": 1.6865445375442505, "learning_rate": 0.00013604167447090273, "loss": 0.6643822669982911, "step": 235140 }, { "epoch": 1.3977804328572023, "grad_norm": 1.1588913202285767, "learning_rate": 0.00013603571591762407, "loss": 0.5952512741088867, "step": 235150 }, { "epoch": 1.3978398749338707, "grad_norm": 1.7358884811401367, "learning_rate": 0.00013602975723979902, "loss": 0.604743480682373, "step": 235160 }, { "epoch": 1.3978993170105392, "grad_norm": 1.3757296800613403, "learning_rate": 0.00013602379843745613, "loss": 0.6128993988037109, "step": 235170 }, { "epoch": 1.3979587590872073, "grad_norm": 1.4665528535842896, "learning_rate": 0.00013601783951062394, "loss": 0.5517366409301758, "step": 235180 }, { "epoch": 1.3980182011638758, "grad_norm": 1.421545386314392, "learning_rate": 0.00013601188045933083, "loss": 0.6026420593261719, "step": 235190 }, { "epoch": 1.3980776432405442, "grad_norm": 1.193244457244873, "learning_rate": 0.00013600592128360544, "loss": 0.625147533416748, "step": 235200 }, { "epoch": 1.3981370853172126, "grad_norm": 1.543511152267456, "learning_rate": 0.00013599996198347618, "loss": 0.577372932434082, "step": 235210 }, { "epoch": 1.398196527393881, "grad_norm": 1.628395676612854, "learning_rate": 0.0001359940025589716, "loss": 0.6004298210144043, "step": 235220 }, { "epoch": 1.3982559694705494, "grad_norm": 1.1867759227752686, "learning_rate": 0.00013598804301012026, "loss": 0.5128392696380615, "step": 235230 }, { "epoch": 1.3983154115472178, "grad_norm": 1.8325875997543335, "learning_rate": 0.00013598208333695058, "loss": 0.5927343368530273, "step": 235240 }, { "epoch": 1.3983748536238862, "grad_norm": 1.9464744329452515, "learning_rate": 0.0001359761235394911, "loss": 0.6045714855194092, "step": 235250 }, { "epoch": 1.3984342957005547, "grad_norm": 1.4720052480697632, "learning_rate": 0.00013597016361777036, "loss": 0.5616073608398438, "step": 235260 }, { "epoch": 1.398493737777223, "grad_norm": 1.1919580698013306, "learning_rate": 0.0001359642035718168, "loss": 0.5522342681884765, "step": 235270 }, { "epoch": 1.3985531798538915, "grad_norm": 1.1838934421539307, "learning_rate": 0.000135958243401659, "loss": 0.6468355178833007, "step": 235280 }, { "epoch": 1.3986126219305597, "grad_norm": 1.7316054105758667, "learning_rate": 0.00013595228310732545, "loss": 0.6385983943939209, "step": 235290 }, { "epoch": 1.398672064007228, "grad_norm": 1.6753902435302734, "learning_rate": 0.00013594632268884463, "loss": 0.6118009090423584, "step": 235300 }, { "epoch": 1.3987315060838965, "grad_norm": 1.6323939561843872, "learning_rate": 0.00013594036214624512, "loss": 0.5933797836303711, "step": 235310 }, { "epoch": 1.398790948160565, "grad_norm": 1.3623459339141846, "learning_rate": 0.0001359344014795554, "loss": 0.6193918228149414, "step": 235320 }, { "epoch": 1.3988503902372333, "grad_norm": 1.4874796867370605, "learning_rate": 0.00013592844068880397, "loss": 0.5979036808013916, "step": 235330 }, { "epoch": 1.3989098323139018, "grad_norm": 1.4451862573623657, "learning_rate": 0.0001359224797740193, "loss": 0.646384859085083, "step": 235340 }, { "epoch": 1.3989692743905702, "grad_norm": 1.2012437582015991, "learning_rate": 0.00013591651873523004, "loss": 0.6414790153503418, "step": 235350 }, { "epoch": 1.3990287164672384, "grad_norm": 1.0964852571487427, "learning_rate": 0.0001359105575724646, "loss": 0.5232260227203369, "step": 235360 }, { "epoch": 1.3990881585439068, "grad_norm": 1.4757124185562134, "learning_rate": 0.00013590459628575147, "loss": 0.557152271270752, "step": 235370 }, { "epoch": 1.3991476006205752, "grad_norm": 1.3254566192626953, "learning_rate": 0.00013589863487511927, "loss": 0.5406895637512207, "step": 235380 }, { "epoch": 1.3992070426972436, "grad_norm": 1.799747109413147, "learning_rate": 0.00013589267334059645, "loss": 0.598804521560669, "step": 235390 }, { "epoch": 1.399266484773912, "grad_norm": 1.7897958755493164, "learning_rate": 0.00013588671168221153, "loss": 0.6047990798950196, "step": 235400 }, { "epoch": 1.3993259268505804, "grad_norm": 1.349714756011963, "learning_rate": 0.00013588074989999307, "loss": 0.6221758842468261, "step": 235410 }, { "epoch": 1.3993853689272489, "grad_norm": 1.6262180805206299, "learning_rate": 0.00013587478799396952, "loss": 0.5895095825195312, "step": 235420 }, { "epoch": 1.3994448110039173, "grad_norm": 1.6229122877120972, "learning_rate": 0.0001358688259641695, "loss": 0.563076114654541, "step": 235430 }, { "epoch": 1.3995042530805857, "grad_norm": 1.2635383605957031, "learning_rate": 0.00013586286381062142, "loss": 0.5636722564697265, "step": 235440 }, { "epoch": 1.399563695157254, "grad_norm": 1.8261607885360718, "learning_rate": 0.00013585690153335386, "loss": 0.6339983463287353, "step": 235450 }, { "epoch": 1.3996231372339225, "grad_norm": 1.3393404483795166, "learning_rate": 0.00013585093913239535, "loss": 0.5944785118103028, "step": 235460 }, { "epoch": 1.399682579310591, "grad_norm": 1.6631040573120117, "learning_rate": 0.00013584497660777437, "loss": 0.5391474723815918, "step": 235470 }, { "epoch": 1.3997420213872591, "grad_norm": 1.7541327476501465, "learning_rate": 0.00013583901395951948, "loss": 0.6310781478881836, "step": 235480 }, { "epoch": 1.3998014634639275, "grad_norm": 1.7481228113174438, "learning_rate": 0.0001358330511876592, "loss": 0.5687283039093017, "step": 235490 }, { "epoch": 1.399860905540596, "grad_norm": 1.4563111066818237, "learning_rate": 0.00013582708829222204, "loss": 0.663004207611084, "step": 235500 }, { "epoch": 1.3999203476172644, "grad_norm": 1.6660504341125488, "learning_rate": 0.00013582112527323653, "loss": 0.5259406089782714, "step": 235510 }, { "epoch": 1.3999797896939328, "grad_norm": 1.564875602722168, "learning_rate": 0.0001358151621307312, "loss": 0.5766576290130615, "step": 235520 }, { "epoch": 1.4000392317706012, "grad_norm": 1.7375547885894775, "learning_rate": 0.00013580919886473452, "loss": 0.6714165687561036, "step": 235530 }, { "epoch": 1.4000986738472696, "grad_norm": 1.399025797843933, "learning_rate": 0.00013580323547527514, "loss": 0.5572253227233886, "step": 235540 }, { "epoch": 1.4001581159239378, "grad_norm": 1.536970853805542, "learning_rate": 0.0001357972719623815, "loss": 0.6752398490905762, "step": 235550 }, { "epoch": 1.4002175580006062, "grad_norm": 1.0952790975570679, "learning_rate": 0.0001357913083260821, "loss": 0.5908295154571533, "step": 235560 }, { "epoch": 1.4002770000772746, "grad_norm": 1.2829724550247192, "learning_rate": 0.00013578534456640555, "loss": 0.6535014152526856, "step": 235570 }, { "epoch": 1.400336442153943, "grad_norm": 1.5869781970977783, "learning_rate": 0.00013577938068338032, "loss": 0.6004329204559327, "step": 235580 }, { "epoch": 1.4003958842306115, "grad_norm": 1.3464758396148682, "learning_rate": 0.00013577341667703495, "loss": 0.5979960918426513, "step": 235590 }, { "epoch": 1.4004553263072799, "grad_norm": 1.804170846939087, "learning_rate": 0.000135767452547398, "loss": 0.6252448081970214, "step": 235600 }, { "epoch": 1.4005147683839483, "grad_norm": 2.190674066543579, "learning_rate": 0.00013576148829449797, "loss": 0.5651067733764649, "step": 235610 }, { "epoch": 1.4005742104606167, "grad_norm": 1.6281427145004272, "learning_rate": 0.00013575552391836338, "loss": 0.5825193405151368, "step": 235620 }, { "epoch": 1.4006336525372851, "grad_norm": 1.6664011478424072, "learning_rate": 0.0001357495594190228, "loss": 0.5673747062683105, "step": 235630 }, { "epoch": 1.4006930946139535, "grad_norm": 1.9918993711471558, "learning_rate": 0.00013574359479650476, "loss": 0.5201774597167969, "step": 235640 }, { "epoch": 1.400752536690622, "grad_norm": 1.5918515920639038, "learning_rate": 0.00013573763005083776, "loss": 0.5911003112792969, "step": 235650 }, { "epoch": 1.4008119787672901, "grad_norm": 1.6292461156845093, "learning_rate": 0.00013573166518205036, "loss": 0.6336145877838135, "step": 235660 }, { "epoch": 1.4008714208439585, "grad_norm": 1.628137469291687, "learning_rate": 0.00013572570019017107, "loss": 0.569218635559082, "step": 235670 }, { "epoch": 1.400930862920627, "grad_norm": 1.990204095840454, "learning_rate": 0.00013571973507522838, "loss": 0.579604959487915, "step": 235680 }, { "epoch": 1.4009903049972954, "grad_norm": 1.192408561706543, "learning_rate": 0.00013571376983725097, "loss": 0.6150449752807617, "step": 235690 }, { "epoch": 1.4010497470739638, "grad_norm": 1.3784176111221313, "learning_rate": 0.00013570780447626725, "loss": 0.5847664833068847, "step": 235700 }, { "epoch": 1.4011091891506322, "grad_norm": 1.6613987684249878, "learning_rate": 0.00013570183899230579, "loss": 0.5853699207305908, "step": 235710 }, { "epoch": 1.4011686312273006, "grad_norm": 1.5486657619476318, "learning_rate": 0.00013569587338539517, "loss": 0.65234375, "step": 235720 }, { "epoch": 1.4012280733039688, "grad_norm": 1.627303957939148, "learning_rate": 0.00013568990765556386, "loss": 0.5283677577972412, "step": 235730 }, { "epoch": 1.4012875153806372, "grad_norm": 1.491178035736084, "learning_rate": 0.00013568394180284044, "loss": 0.656801414489746, "step": 235740 }, { "epoch": 1.4013469574573056, "grad_norm": 1.5715830326080322, "learning_rate": 0.0001356779758272534, "loss": 0.6339569091796875, "step": 235750 }, { "epoch": 1.401406399533974, "grad_norm": 1.284903883934021, "learning_rate": 0.00013567200972883133, "loss": 0.5981451988220214, "step": 235760 }, { "epoch": 1.4014658416106425, "grad_norm": 1.3547379970550537, "learning_rate": 0.00013566604350760282, "loss": 0.5801121711730957, "step": 235770 }, { "epoch": 1.4015252836873109, "grad_norm": 1.3942677974700928, "learning_rate": 0.00013566007716359627, "loss": 0.6372285842895508, "step": 235780 }, { "epoch": 1.4015847257639793, "grad_norm": 1.3940130472183228, "learning_rate": 0.0001356541106968403, "loss": 0.6037989616394043, "step": 235790 }, { "epoch": 1.4016441678406477, "grad_norm": 1.531380534172058, "learning_rate": 0.00013564814410736348, "loss": 0.5929197788238525, "step": 235800 }, { "epoch": 1.4017036099173161, "grad_norm": 1.5394554138183594, "learning_rate": 0.0001356421773951943, "loss": 0.5926315307617187, "step": 235810 }, { "epoch": 1.4017630519939845, "grad_norm": 1.4896130561828613, "learning_rate": 0.00013563621056036134, "loss": 0.5941724300384521, "step": 235820 }, { "epoch": 1.401822494070653, "grad_norm": 1.4599084854125977, "learning_rate": 0.00013563024360289312, "loss": 0.5651430130004883, "step": 235830 }, { "epoch": 1.4018819361473214, "grad_norm": 1.692534327507019, "learning_rate": 0.00013562427652281817, "loss": 0.5244694709777832, "step": 235840 }, { "epoch": 1.4019413782239896, "grad_norm": 1.6323515176773071, "learning_rate": 0.00013561830932016508, "loss": 0.6290356159210205, "step": 235850 }, { "epoch": 1.402000820300658, "grad_norm": 1.4677687883377075, "learning_rate": 0.00013561234199496237, "loss": 0.5842751026153564, "step": 235860 }, { "epoch": 1.4020602623773264, "grad_norm": 1.6150357723236084, "learning_rate": 0.00013560637454723858, "loss": 0.6050284385681153, "step": 235870 }, { "epoch": 1.4021197044539948, "grad_norm": 1.48370361328125, "learning_rate": 0.00013560040697702225, "loss": 0.5986687660217285, "step": 235880 }, { "epoch": 1.4021791465306632, "grad_norm": 1.8539479970932007, "learning_rate": 0.00013559443928434195, "loss": 0.577934980392456, "step": 235890 }, { "epoch": 1.4022385886073316, "grad_norm": 1.9283374547958374, "learning_rate": 0.00013558847146922625, "loss": 0.6244109153747559, "step": 235900 }, { "epoch": 1.402298030684, "grad_norm": 1.455910086631775, "learning_rate": 0.00013558250353170364, "loss": 0.611855411529541, "step": 235910 }, { "epoch": 1.4023574727606682, "grad_norm": 1.3507550954818726, "learning_rate": 0.00013557653547180266, "loss": 0.5986529350280761, "step": 235920 }, { "epoch": 1.4024169148373367, "grad_norm": 1.6839889287948608, "learning_rate": 0.0001355705672895519, "loss": 0.6406648635864258, "step": 235930 }, { "epoch": 1.402476356914005, "grad_norm": 1.4623116254806519, "learning_rate": 0.00013556459898497996, "loss": 0.5410265922546387, "step": 235940 }, { "epoch": 1.4025357989906735, "grad_norm": 1.481886625289917, "learning_rate": 0.00013555863055811528, "loss": 0.6319579124450684, "step": 235950 }, { "epoch": 1.402595241067342, "grad_norm": 1.3369516134262085, "learning_rate": 0.00013555266200898647, "loss": 0.5491695404052734, "step": 235960 }, { "epoch": 1.4026546831440103, "grad_norm": 1.4415397644042969, "learning_rate": 0.0001355466933376221, "loss": 0.5988702774047852, "step": 235970 }, { "epoch": 1.4027141252206787, "grad_norm": 1.3319926261901855, "learning_rate": 0.00013554072454405067, "loss": 0.6069779396057129, "step": 235980 }, { "epoch": 1.4027735672973471, "grad_norm": 1.5582472085952759, "learning_rate": 0.00013553475562830077, "loss": 0.6125460147857666, "step": 235990 }, { "epoch": 1.4028330093740156, "grad_norm": 1.551682949066162, "learning_rate": 0.000135528786590401, "loss": 0.5715313911437988, "step": 236000 }, { "epoch": 1.402892451450684, "grad_norm": 1.8146759271621704, "learning_rate": 0.00013552281743037977, "loss": 0.6288575649261474, "step": 236010 }, { "epoch": 1.4029518935273524, "grad_norm": 1.4562253952026367, "learning_rate": 0.00013551684814826575, "loss": 0.5052918910980224, "step": 236020 }, { "epoch": 1.4030113356040206, "grad_norm": 1.892870306968689, "learning_rate": 0.0001355108787440875, "loss": 0.650794506072998, "step": 236030 }, { "epoch": 1.403070777680689, "grad_norm": 1.807098627090454, "learning_rate": 0.00013550490921787348, "loss": 0.5635120391845703, "step": 236040 }, { "epoch": 1.4031302197573574, "grad_norm": 1.3430808782577515, "learning_rate": 0.00013549893956965237, "loss": 0.6204845428466796, "step": 236050 }, { "epoch": 1.4031896618340258, "grad_norm": 1.2864855527877808, "learning_rate": 0.00013549296979945265, "loss": 0.6114024162292481, "step": 236060 }, { "epoch": 1.4032491039106942, "grad_norm": 1.2880077362060547, "learning_rate": 0.00013548699990730288, "loss": 0.6096609115600586, "step": 236070 }, { "epoch": 1.4033085459873627, "grad_norm": 1.7290080785751343, "learning_rate": 0.00013548102989323165, "loss": 0.6069097995758057, "step": 236080 }, { "epoch": 1.403367988064031, "grad_norm": 1.4544379711151123, "learning_rate": 0.0001354750597572675, "loss": 0.5769147872924805, "step": 236090 }, { "epoch": 1.4034274301406993, "grad_norm": 1.3760294914245605, "learning_rate": 0.00013546908949943896, "loss": 0.5886226654052734, "step": 236100 }, { "epoch": 1.4034868722173677, "grad_norm": 1.533677577972412, "learning_rate": 0.00013546311911977462, "loss": 0.6526484489440918, "step": 236110 }, { "epoch": 1.403546314294036, "grad_norm": 1.2758457660675049, "learning_rate": 0.00013545714861830306, "loss": 0.6045868396759033, "step": 236120 }, { "epoch": 1.4036057563707045, "grad_norm": 1.7236708402633667, "learning_rate": 0.00013545117799505283, "loss": 0.6756791114807129, "step": 236130 }, { "epoch": 1.403665198447373, "grad_norm": 1.3206746578216553, "learning_rate": 0.00013544520725005245, "loss": 0.6399497032165528, "step": 236140 }, { "epoch": 1.4037246405240413, "grad_norm": 1.7578033208847046, "learning_rate": 0.00013543923638333053, "loss": 0.573495626449585, "step": 236150 }, { "epoch": 1.4037840826007097, "grad_norm": 1.7784318923950195, "learning_rate": 0.00013543326539491564, "loss": 0.6620494842529296, "step": 236160 }, { "epoch": 1.4038435246773782, "grad_norm": 1.529060959815979, "learning_rate": 0.0001354272942848363, "loss": 0.5655893802642822, "step": 236170 }, { "epoch": 1.4039029667540466, "grad_norm": 1.608338475227356, "learning_rate": 0.0001354213230531211, "loss": 0.6957083702087402, "step": 236180 }, { "epoch": 1.403962408830715, "grad_norm": 1.825616717338562, "learning_rate": 0.0001354153516997986, "loss": 0.6872619152069092, "step": 236190 }, { "epoch": 1.4040218509073834, "grad_norm": 1.4578241109848022, "learning_rate": 0.00013540938022489732, "loss": 0.5438263893127442, "step": 236200 }, { "epoch": 1.4040812929840518, "grad_norm": 1.4447929859161377, "learning_rate": 0.00013540340862844594, "loss": 0.5869873523712158, "step": 236210 }, { "epoch": 1.40414073506072, "grad_norm": 1.648949146270752, "learning_rate": 0.00013539743691047293, "loss": 0.5536178588867188, "step": 236220 }, { "epoch": 1.4042001771373884, "grad_norm": 1.6502519845962524, "learning_rate": 0.00013539146507100686, "loss": 0.5998375892639161, "step": 236230 }, { "epoch": 1.4042596192140568, "grad_norm": 1.72771418094635, "learning_rate": 0.00013538549311007634, "loss": 0.6529440879821777, "step": 236240 }, { "epoch": 1.4043190612907253, "grad_norm": 1.7055855989456177, "learning_rate": 0.0001353795210277099, "loss": 0.5794432163238525, "step": 236250 }, { "epoch": 1.4043785033673937, "grad_norm": 1.51073157787323, "learning_rate": 0.00013537354882393613, "loss": 0.587733793258667, "step": 236260 }, { "epoch": 1.404437945444062, "grad_norm": 1.3158560991287231, "learning_rate": 0.0001353675764987836, "loss": 0.5682395935058594, "step": 236270 }, { "epoch": 1.4044973875207305, "grad_norm": 1.4512227773666382, "learning_rate": 0.0001353616040522809, "loss": 0.5525951385498047, "step": 236280 }, { "epoch": 1.4045568295973987, "grad_norm": 1.6861655712127686, "learning_rate": 0.0001353556314844565, "loss": 0.579108715057373, "step": 236290 }, { "epoch": 1.404616271674067, "grad_norm": 1.7113234996795654, "learning_rate": 0.0001353496587953391, "loss": 0.574059009552002, "step": 236300 }, { "epoch": 1.4046757137507355, "grad_norm": 1.8544161319732666, "learning_rate": 0.00013534368598495721, "loss": 0.6396224975585938, "step": 236310 }, { "epoch": 1.404735155827404, "grad_norm": 1.6313598155975342, "learning_rate": 0.00013533771305333943, "loss": 0.6402859687805176, "step": 236320 }, { "epoch": 1.4047945979040724, "grad_norm": 1.4694966077804565, "learning_rate": 0.00013533174000051427, "loss": 0.5915075302124023, "step": 236330 }, { "epoch": 1.4048540399807408, "grad_norm": 1.7942759990692139, "learning_rate": 0.00013532576682651038, "loss": 0.6082498073577881, "step": 236340 }, { "epoch": 1.4049134820574092, "grad_norm": 1.4912984371185303, "learning_rate": 0.00013531979353135628, "loss": 0.6373161792755127, "step": 236350 }, { "epoch": 1.4049729241340776, "grad_norm": 1.364736557006836, "learning_rate": 0.00013531382011508055, "loss": 0.564872932434082, "step": 236360 }, { "epoch": 1.405032366210746, "grad_norm": 1.4802254438400269, "learning_rate": 0.0001353078465777118, "loss": 0.5419713020324707, "step": 236370 }, { "epoch": 1.4050918082874144, "grad_norm": 1.413651704788208, "learning_rate": 0.00013530187291927855, "loss": 0.5750054359436035, "step": 236380 }, { "epoch": 1.4051512503640828, "grad_norm": 1.7182000875473022, "learning_rate": 0.00013529589913980947, "loss": 0.6065351486206054, "step": 236390 }, { "epoch": 1.405210692440751, "grad_norm": 1.823203444480896, "learning_rate": 0.000135289925239333, "loss": 0.577003288269043, "step": 236400 }, { "epoch": 1.4052701345174194, "grad_norm": 1.4890973567962646, "learning_rate": 0.00013528395121787783, "loss": 0.5768070697784424, "step": 236410 }, { "epoch": 1.4053295765940879, "grad_norm": 1.0958786010742188, "learning_rate": 0.0001352779770754725, "loss": 0.6033531188964844, "step": 236420 }, { "epoch": 1.4053890186707563, "grad_norm": 1.7139464616775513, "learning_rate": 0.00013527200281214562, "loss": 0.6005288124084472, "step": 236430 }, { "epoch": 1.4054484607474247, "grad_norm": 1.4035017490386963, "learning_rate": 0.0001352660284279257, "loss": 0.6556787967681885, "step": 236440 }, { "epoch": 1.405507902824093, "grad_norm": 1.5832419395446777, "learning_rate": 0.00013526005392284135, "loss": 0.5873030185699463, "step": 236450 }, { "epoch": 1.4055673449007615, "grad_norm": 1.2020797729492188, "learning_rate": 0.0001352540792969212, "loss": 0.5866427421569824, "step": 236460 }, { "epoch": 1.4056267869774297, "grad_norm": 1.8569462299346924, "learning_rate": 0.00013524810455019376, "loss": 0.566894245147705, "step": 236470 }, { "epoch": 1.4056862290540981, "grad_norm": 1.3771165609359741, "learning_rate": 0.00013524212968268762, "loss": 0.6271166324615478, "step": 236480 }, { "epoch": 1.4057456711307665, "grad_norm": 1.4716706275939941, "learning_rate": 0.0001352361546944314, "loss": 0.565008544921875, "step": 236490 }, { "epoch": 1.405805113207435, "grad_norm": 0.9073529839515686, "learning_rate": 0.00013523017958545365, "loss": 0.5438334465026855, "step": 236500 }, { "epoch": 1.4058645552841034, "grad_norm": 1.5812650918960571, "learning_rate": 0.00013522420435578295, "loss": 0.599560022354126, "step": 236510 }, { "epoch": 1.4059239973607718, "grad_norm": 1.3716882467269897, "learning_rate": 0.00013521822900544795, "loss": 0.6529786586761475, "step": 236520 }, { "epoch": 1.4059834394374402, "grad_norm": 1.4560850858688354, "learning_rate": 0.00013521225353447716, "loss": 0.562065601348877, "step": 236530 }, { "epoch": 1.4060428815141086, "grad_norm": 1.5777779817581177, "learning_rate": 0.00013520627794289918, "loss": 0.5623324871063232, "step": 236540 }, { "epoch": 1.406102323590777, "grad_norm": 1.6467845439910889, "learning_rate": 0.00013520030223074264, "loss": 0.5999291419982911, "step": 236550 }, { "epoch": 1.4061617656674454, "grad_norm": 1.7659763097763062, "learning_rate": 0.00013519432639803603, "loss": 0.6133913516998291, "step": 236560 }, { "epoch": 1.4062212077441139, "grad_norm": 1.2073025703430176, "learning_rate": 0.00013518835044480805, "loss": 0.616825008392334, "step": 236570 }, { "epoch": 1.4062806498207823, "grad_norm": 1.1552637815475464, "learning_rate": 0.00013518237437108724, "loss": 0.5777042865753174, "step": 236580 }, { "epoch": 1.4063400918974505, "grad_norm": 1.259324312210083, "learning_rate": 0.00013517639817690213, "loss": 0.5526495933532715, "step": 236590 }, { "epoch": 1.4063995339741189, "grad_norm": 1.5217047929763794, "learning_rate": 0.00013517042186228138, "loss": 0.5652475357055664, "step": 236600 }, { "epoch": 1.4064589760507873, "grad_norm": 1.2795100212097168, "learning_rate": 0.00013516444542725358, "loss": 0.5997785091400146, "step": 236610 }, { "epoch": 1.4065184181274557, "grad_norm": 1.8814077377319336, "learning_rate": 0.00013515846887184727, "loss": 0.5702632904052735, "step": 236620 }, { "epoch": 1.4065778602041241, "grad_norm": 1.1374410390853882, "learning_rate": 0.00013515249219609105, "loss": 0.6096156120300293, "step": 236630 }, { "epoch": 1.4066373022807925, "grad_norm": 1.490320086479187, "learning_rate": 0.00013514651540001354, "loss": 0.5817395687103272, "step": 236640 }, { "epoch": 1.406696744357461, "grad_norm": 1.4476289749145508, "learning_rate": 0.00013514053848364337, "loss": 0.6061050415039062, "step": 236650 }, { "epoch": 1.4067561864341291, "grad_norm": 1.7225408554077148, "learning_rate": 0.00013513456144700903, "loss": 0.6087677478790283, "step": 236660 }, { "epoch": 1.4068156285107976, "grad_norm": 1.8562018871307373, "learning_rate": 0.00013512858429013918, "loss": 0.5845575332641602, "step": 236670 }, { "epoch": 1.406875070587466, "grad_norm": 1.6101559400558472, "learning_rate": 0.00013512260701306237, "loss": 0.5910141944885254, "step": 236680 }, { "epoch": 1.4069345126641344, "grad_norm": 1.4056121110916138, "learning_rate": 0.00013511662961580723, "loss": 0.6134973526000976, "step": 236690 }, { "epoch": 1.4069939547408028, "grad_norm": 1.5717594623565674, "learning_rate": 0.00013511065209840235, "loss": 0.6282039642333984, "step": 236700 }, { "epoch": 1.4070533968174712, "grad_norm": 1.5050618648529053, "learning_rate": 0.00013510467446087632, "loss": 0.620964241027832, "step": 236710 }, { "epoch": 1.4071128388941396, "grad_norm": 2.016212224960327, "learning_rate": 0.00013509869670325772, "loss": 0.6083706855773926, "step": 236720 }, { "epoch": 1.407172280970808, "grad_norm": 1.8501325845718384, "learning_rate": 0.0001350927188255752, "loss": 0.611773681640625, "step": 236730 }, { "epoch": 1.4072317230474765, "grad_norm": 1.564586877822876, "learning_rate": 0.00013508674082785723, "loss": 0.5761109828948975, "step": 236740 }, { "epoch": 1.4072911651241449, "grad_norm": 1.5551868677139282, "learning_rate": 0.00013508076271013253, "loss": 0.5771572113037109, "step": 236750 }, { "epoch": 1.4073506072008133, "grad_norm": 1.6324673891067505, "learning_rate": 0.0001350747844724297, "loss": 0.5439955234527588, "step": 236760 }, { "epoch": 1.4074100492774815, "grad_norm": 1.2174789905548096, "learning_rate": 0.00013506880611477727, "loss": 0.639521598815918, "step": 236770 }, { "epoch": 1.40746949135415, "grad_norm": 1.2804361581802368, "learning_rate": 0.0001350628276372038, "loss": 0.6111269950866699, "step": 236780 }, { "epoch": 1.4075289334308183, "grad_norm": 1.599544882774353, "learning_rate": 0.00013505684903973803, "loss": 0.580228042602539, "step": 236790 }, { "epoch": 1.4075883755074867, "grad_norm": 1.5027178525924683, "learning_rate": 0.00013505087032240846, "loss": 0.5824560165405274, "step": 236800 }, { "epoch": 1.4076478175841551, "grad_norm": 1.6648004055023193, "learning_rate": 0.00013504489148524372, "loss": 0.5623900890350342, "step": 236810 }, { "epoch": 1.4077072596608236, "grad_norm": 1.7356836795806885, "learning_rate": 0.00013503891252827238, "loss": 0.6086522102355957, "step": 236820 }, { "epoch": 1.407766701737492, "grad_norm": 1.324557900428772, "learning_rate": 0.00013503293345152307, "loss": 0.5597743034362793, "step": 236830 }, { "epoch": 1.4078261438141602, "grad_norm": 1.5215531587600708, "learning_rate": 0.0001350269542550244, "loss": 0.5579422950744629, "step": 236840 }, { "epoch": 1.4078855858908286, "grad_norm": 1.5254464149475098, "learning_rate": 0.00013502097493880497, "loss": 0.6155369758605957, "step": 236850 }, { "epoch": 1.407945027967497, "grad_norm": 1.5338176488876343, "learning_rate": 0.00013501499550289337, "loss": 0.5889692306518555, "step": 236860 }, { "epoch": 1.4080044700441654, "grad_norm": 1.458943247795105, "learning_rate": 0.00013500901594731818, "loss": 0.5988970279693604, "step": 236870 }, { "epoch": 1.4080639121208338, "grad_norm": 1.534891128540039, "learning_rate": 0.00013500303627210806, "loss": 0.5934108257293701, "step": 236880 }, { "epoch": 1.4081233541975022, "grad_norm": 1.2462882995605469, "learning_rate": 0.00013499705647729158, "loss": 0.5429924964904785, "step": 236890 }, { "epoch": 1.4081827962741706, "grad_norm": 1.5716973543167114, "learning_rate": 0.00013499107656289735, "loss": 0.5824350833892822, "step": 236900 }, { "epoch": 1.408242238350839, "grad_norm": 1.455219030380249, "learning_rate": 0.00013498509652895397, "loss": 0.5758695602416992, "step": 236910 }, { "epoch": 1.4083016804275075, "grad_norm": 1.3487145900726318, "learning_rate": 0.00013497911637549002, "loss": 0.5785161018371582, "step": 236920 }, { "epoch": 1.4083611225041759, "grad_norm": 1.5841295719146729, "learning_rate": 0.0001349731361025342, "loss": 0.6322278499603271, "step": 236930 }, { "epoch": 1.4084205645808443, "grad_norm": 1.3996860980987549, "learning_rate": 0.00013496715571011502, "loss": 0.5846795558929443, "step": 236940 }, { "epoch": 1.4084800066575127, "grad_norm": 1.5925548076629639, "learning_rate": 0.00013496117519826116, "loss": 0.6360183238983155, "step": 236950 }, { "epoch": 1.408539448734181, "grad_norm": 1.5492520332336426, "learning_rate": 0.00013495519456700115, "loss": 0.6073904037475586, "step": 236960 }, { "epoch": 1.4085988908108493, "grad_norm": 1.5664604902267456, "learning_rate": 0.00013494921381636366, "loss": 0.5635092735290528, "step": 236970 }, { "epoch": 1.4086583328875177, "grad_norm": 1.1915351152420044, "learning_rate": 0.00013494323294637733, "loss": 0.5349188804626465, "step": 236980 }, { "epoch": 1.4087177749641862, "grad_norm": 1.1758217811584473, "learning_rate": 0.0001349372519570707, "loss": 0.5418859481811523, "step": 236990 }, { "epoch": 1.4087772170408546, "grad_norm": 1.7027976512908936, "learning_rate": 0.00013493127084847237, "loss": 0.5467984199523925, "step": 237000 }, { "epoch": 1.408836659117523, "grad_norm": 1.1063421964645386, "learning_rate": 0.00013492528962061104, "loss": 0.5952239990234375, "step": 237010 }, { "epoch": 1.4088961011941914, "grad_norm": 1.5285875797271729, "learning_rate": 0.00013491930827351522, "loss": 0.6170037269592286, "step": 237020 }, { "epoch": 1.4089555432708596, "grad_norm": 1.107160210609436, "learning_rate": 0.00013491332680721363, "loss": 0.5454213619232178, "step": 237030 }, { "epoch": 1.409014985347528, "grad_norm": 1.4020878076553345, "learning_rate": 0.00013490734522173477, "loss": 0.5856764316558838, "step": 237040 }, { "epoch": 1.4090744274241964, "grad_norm": 1.429283857345581, "learning_rate": 0.00013490136351710733, "loss": 0.6312366962432862, "step": 237050 }, { "epoch": 1.4091338695008648, "grad_norm": 1.7135612964630127, "learning_rate": 0.00013489538169335992, "loss": 0.5791867256164551, "step": 237060 }, { "epoch": 1.4091933115775332, "grad_norm": 1.5659741163253784, "learning_rate": 0.00013488939975052114, "loss": 0.6323379039764404, "step": 237070 }, { "epoch": 1.4092527536542017, "grad_norm": 1.7329049110412598, "learning_rate": 0.00013488341768861962, "loss": 0.6610291957855224, "step": 237080 }, { "epoch": 1.40931219573087, "grad_norm": 1.9010487794876099, "learning_rate": 0.00013487743550768391, "loss": 0.6158286094665527, "step": 237090 }, { "epoch": 1.4093716378075385, "grad_norm": 1.5387052297592163, "learning_rate": 0.0001348714532077427, "loss": 0.6181026935577393, "step": 237100 }, { "epoch": 1.409431079884207, "grad_norm": 1.3674653768539429, "learning_rate": 0.00013486547078882458, "loss": 0.5617371082305909, "step": 237110 }, { "epoch": 1.4094905219608753, "grad_norm": 1.5474929809570312, "learning_rate": 0.00013485948825095817, "loss": 0.5574690341949463, "step": 237120 }, { "epoch": 1.4095499640375437, "grad_norm": 1.196882724761963, "learning_rate": 0.00013485350559417212, "loss": 0.6045075416564941, "step": 237130 }, { "epoch": 1.409609406114212, "grad_norm": 1.7171388864517212, "learning_rate": 0.00013484752281849502, "loss": 0.6349397659301758, "step": 237140 }, { "epoch": 1.4096688481908803, "grad_norm": 1.5721062421798706, "learning_rate": 0.00013484153992395544, "loss": 0.5717498779296875, "step": 237150 }, { "epoch": 1.4097282902675488, "grad_norm": 1.3957079648971558, "learning_rate": 0.0001348355569105821, "loss": 0.5920734405517578, "step": 237160 }, { "epoch": 1.4097877323442172, "grad_norm": 1.285740613937378, "learning_rate": 0.0001348295737784036, "loss": 0.5702010154724121, "step": 237170 }, { "epoch": 1.4098471744208856, "grad_norm": 2.0547616481781006, "learning_rate": 0.00013482359052744845, "loss": 0.5959819793701172, "step": 237180 }, { "epoch": 1.409906616497554, "grad_norm": 1.6969120502471924, "learning_rate": 0.00013481760715774543, "loss": 0.6502652168273926, "step": 237190 }, { "epoch": 1.4099660585742224, "grad_norm": 1.286588430404663, "learning_rate": 0.00013481162366932306, "loss": 0.5470193862915039, "step": 237200 }, { "epoch": 1.4100255006508906, "grad_norm": 1.3699547052383423, "learning_rate": 0.00013480564006221, "loss": 0.6082364082336426, "step": 237210 }, { "epoch": 1.410084942727559, "grad_norm": 1.7682112455368042, "learning_rate": 0.00013479965633643483, "loss": 0.623408031463623, "step": 237220 }, { "epoch": 1.4101443848042274, "grad_norm": 1.2313709259033203, "learning_rate": 0.00013479367249202623, "loss": 0.5836886882781982, "step": 237230 }, { "epoch": 1.4102038268808958, "grad_norm": 1.7007746696472168, "learning_rate": 0.0001347876885290128, "loss": 0.5724478721618652, "step": 237240 }, { "epoch": 1.4102632689575643, "grad_norm": 1.6874241828918457, "learning_rate": 0.0001347817044474232, "loss": 0.6303012847900391, "step": 237250 }, { "epoch": 1.4103227110342327, "grad_norm": 1.4941165447235107, "learning_rate": 0.00013477572024728603, "loss": 0.622669792175293, "step": 237260 }, { "epoch": 1.410382153110901, "grad_norm": 1.8269509077072144, "learning_rate": 0.00013476973592862985, "loss": 0.6234970092773438, "step": 237270 }, { "epoch": 1.4104415951875695, "grad_norm": 1.3839735984802246, "learning_rate": 0.00013476375149148336, "loss": 0.5562992095947266, "step": 237280 }, { "epoch": 1.410501037264238, "grad_norm": 1.1883041858673096, "learning_rate": 0.00013475776693587524, "loss": 0.5861475944519043, "step": 237290 }, { "epoch": 1.4105604793409063, "grad_norm": 1.3788180351257324, "learning_rate": 0.00013475178226183402, "loss": 0.626854419708252, "step": 237300 }, { "epoch": 1.4106199214175748, "grad_norm": 1.502174973487854, "learning_rate": 0.00013474579746938835, "loss": 0.585308313369751, "step": 237310 }, { "epoch": 1.4106793634942432, "grad_norm": 1.2153422832489014, "learning_rate": 0.00013473981255856686, "loss": 0.6284294128417969, "step": 237320 }, { "epoch": 1.4107388055709114, "grad_norm": 1.1472207307815552, "learning_rate": 0.0001347338275293982, "loss": 0.6369844436645508, "step": 237330 }, { "epoch": 1.4107982476475798, "grad_norm": 1.4344383478164673, "learning_rate": 0.00013472784238191098, "loss": 0.5627169609069824, "step": 237340 }, { "epoch": 1.4108576897242482, "grad_norm": 1.806408405303955, "learning_rate": 0.00013472185711613387, "loss": 0.6450750827789307, "step": 237350 }, { "epoch": 1.4109171318009166, "grad_norm": 2.0803956985473633, "learning_rate": 0.00013471587173209546, "loss": 0.6761827945709229, "step": 237360 }, { "epoch": 1.410976573877585, "grad_norm": 1.558523416519165, "learning_rate": 0.0001347098862298244, "loss": 0.6085299015045166, "step": 237370 }, { "epoch": 1.4110360159542534, "grad_norm": 1.6622637510299683, "learning_rate": 0.00013470390060934932, "loss": 0.6545520305633545, "step": 237380 }, { "epoch": 1.4110954580309218, "grad_norm": 1.4501447677612305, "learning_rate": 0.00013469791487069887, "loss": 0.5361292839050293, "step": 237390 }, { "epoch": 1.41115490010759, "grad_norm": 1.0267977714538574, "learning_rate": 0.00013469192901390163, "loss": 0.5647150993347168, "step": 237400 }, { "epoch": 1.4112143421842585, "grad_norm": 1.4099348783493042, "learning_rate": 0.0001346859430389863, "loss": 0.5964105129241943, "step": 237410 }, { "epoch": 1.4112737842609269, "grad_norm": 1.7961676120758057, "learning_rate": 0.00013467995694598148, "loss": 0.6166407108306885, "step": 237420 }, { "epoch": 1.4113332263375953, "grad_norm": 1.4744954109191895, "learning_rate": 0.00013467397073491582, "loss": 0.6048066139221191, "step": 237430 }, { "epoch": 1.4113926684142637, "grad_norm": 1.9448994398117065, "learning_rate": 0.00013466798440581797, "loss": 0.6468325138092041, "step": 237440 }, { "epoch": 1.411452110490932, "grad_norm": 1.4170331954956055, "learning_rate": 0.00013466199795871648, "loss": 0.5971336364746094, "step": 237450 }, { "epoch": 1.4115115525676005, "grad_norm": 1.3310269117355347, "learning_rate": 0.00013465601139364008, "loss": 0.5402990341186523, "step": 237460 }, { "epoch": 1.411570994644269, "grad_norm": 1.4654611349105835, "learning_rate": 0.0001346500247106174, "loss": 0.627023983001709, "step": 237470 }, { "epoch": 1.4116304367209374, "grad_norm": 1.3764073848724365, "learning_rate": 0.000134644037909677, "loss": 0.5949643611907959, "step": 237480 }, { "epoch": 1.4116898787976058, "grad_norm": 1.3945717811584473, "learning_rate": 0.00013463805099084766, "loss": 0.5867870330810547, "step": 237490 }, { "epoch": 1.4117493208742742, "grad_norm": 1.4709060192108154, "learning_rate": 0.0001346320639541579, "loss": 0.5878928661346435, "step": 237500 }, { "epoch": 1.4118087629509424, "grad_norm": 1.6862236261367798, "learning_rate": 0.00013462607679963633, "loss": 0.63577880859375, "step": 237510 }, { "epoch": 1.4118682050276108, "grad_norm": 1.5843896865844727, "learning_rate": 0.00013462008952731176, "loss": 0.6276876926422119, "step": 237520 }, { "epoch": 1.4119276471042792, "grad_norm": 1.6011213064193726, "learning_rate": 0.0001346141021372127, "loss": 0.5953056812286377, "step": 237530 }, { "epoch": 1.4119870891809476, "grad_norm": 1.5627683401107788, "learning_rate": 0.00013460811462936775, "loss": 0.609433937072754, "step": 237540 }, { "epoch": 1.412046531257616, "grad_norm": 1.558072805404663, "learning_rate": 0.0001346021270038057, "loss": 0.5619040489196777, "step": 237550 }, { "epoch": 1.4121059733342844, "grad_norm": 2.01104474067688, "learning_rate": 0.00013459613926055508, "loss": 0.5988698959350586, "step": 237560 }, { "epoch": 1.4121654154109529, "grad_norm": 1.670161247253418, "learning_rate": 0.00013459015139964458, "loss": 0.5562568187713623, "step": 237570 }, { "epoch": 1.412224857487621, "grad_norm": 1.6452112197875977, "learning_rate": 0.00013458416342110283, "loss": 0.5907639980316162, "step": 237580 }, { "epoch": 1.4122842995642895, "grad_norm": 1.7500005960464478, "learning_rate": 0.00013457817532495846, "loss": 0.6735810279846192, "step": 237590 }, { "epoch": 1.4123437416409579, "grad_norm": 1.7583941221237183, "learning_rate": 0.00013457218711124014, "loss": 0.6235079288482666, "step": 237600 }, { "epoch": 1.4124031837176263, "grad_norm": 1.5020809173583984, "learning_rate": 0.00013456619877997653, "loss": 0.5986517906188965, "step": 237610 }, { "epoch": 1.4124626257942947, "grad_norm": 1.4086546897888184, "learning_rate": 0.0001345602103311962, "loss": 0.5892876625061035, "step": 237620 }, { "epoch": 1.4125220678709631, "grad_norm": 1.7473926544189453, "learning_rate": 0.0001345542217649279, "loss": 0.6081389427185059, "step": 237630 }, { "epoch": 1.4125815099476315, "grad_norm": 1.2178103923797607, "learning_rate": 0.00013454823308120021, "loss": 0.5583168983459472, "step": 237640 }, { "epoch": 1.4126409520243, "grad_norm": 1.532602071762085, "learning_rate": 0.0001345422442800418, "loss": 0.6255725860595703, "step": 237650 }, { "epoch": 1.4127003941009684, "grad_norm": 1.699214220046997, "learning_rate": 0.00013453625536148132, "loss": 0.5864099025726318, "step": 237660 }, { "epoch": 1.4127598361776368, "grad_norm": 1.3657780885696411, "learning_rate": 0.0001345302663255474, "loss": 0.5145849227905274, "step": 237670 }, { "epoch": 1.4128192782543052, "grad_norm": 1.4054391384124756, "learning_rate": 0.0001345242771722687, "loss": 0.588719654083252, "step": 237680 }, { "epoch": 1.4128787203309736, "grad_norm": 3.098241090774536, "learning_rate": 0.00013451828790167388, "loss": 0.6431965351104736, "step": 237690 }, { "epoch": 1.4129381624076418, "grad_norm": 1.220660924911499, "learning_rate": 0.0001345122985137916, "loss": 0.6382875442504883, "step": 237700 }, { "epoch": 1.4129976044843102, "grad_norm": 1.8810592889785767, "learning_rate": 0.00013450630900865046, "loss": 0.6046917915344239, "step": 237710 }, { "epoch": 1.4130570465609786, "grad_norm": 1.635371208190918, "learning_rate": 0.0001345003193862792, "loss": 0.6506651401519775, "step": 237720 }, { "epoch": 1.413116488637647, "grad_norm": 1.9232920408248901, "learning_rate": 0.00013449432964670637, "loss": 0.5584263324737548, "step": 237730 }, { "epoch": 1.4131759307143155, "grad_norm": 1.591039776802063, "learning_rate": 0.00013448833978996067, "loss": 0.6370665073394776, "step": 237740 }, { "epoch": 1.4132353727909839, "grad_norm": 1.5002079010009766, "learning_rate": 0.0001344823498160708, "loss": 0.5633157730102539, "step": 237750 }, { "epoch": 1.4132948148676523, "grad_norm": 2.515657901763916, "learning_rate": 0.00013447635972506535, "loss": 0.562348461151123, "step": 237760 }, { "epoch": 1.4133542569443205, "grad_norm": 1.277138590812683, "learning_rate": 0.00013447036951697293, "loss": 0.5283340454101563, "step": 237770 }, { "epoch": 1.413413699020989, "grad_norm": 1.2882853746414185, "learning_rate": 0.00013446437919182236, "loss": 0.6104345321655273, "step": 237780 }, { "epoch": 1.4134731410976573, "grad_norm": 1.6446691751480103, "learning_rate": 0.00013445838874964213, "loss": 0.5922098636627198, "step": 237790 }, { "epoch": 1.4135325831743257, "grad_norm": 1.361031174659729, "learning_rate": 0.00013445239819046098, "loss": 0.6009073734283448, "step": 237800 }, { "epoch": 1.4135920252509941, "grad_norm": 1.6822338104248047, "learning_rate": 0.00013444640751430757, "loss": 0.5980611801147461, "step": 237810 }, { "epoch": 1.4136514673276626, "grad_norm": 1.3274024724960327, "learning_rate": 0.00013444041672121048, "loss": 0.5703387260437012, "step": 237820 }, { "epoch": 1.413710909404331, "grad_norm": 1.4920238256454468, "learning_rate": 0.00013443442581119848, "loss": 0.626421594619751, "step": 237830 }, { "epoch": 1.4137703514809994, "grad_norm": 1.5535322427749634, "learning_rate": 0.00013442843478430014, "loss": 0.606800651550293, "step": 237840 }, { "epoch": 1.4138297935576678, "grad_norm": 1.6114791631698608, "learning_rate": 0.00013442244364054415, "loss": 0.5819661140441894, "step": 237850 }, { "epoch": 1.4138892356343362, "grad_norm": 1.3151729106903076, "learning_rate": 0.0001344164523799592, "loss": 0.600179386138916, "step": 237860 }, { "epoch": 1.4139486777110046, "grad_norm": 1.57782781124115, "learning_rate": 0.0001344104610025739, "loss": 0.5867714405059814, "step": 237870 }, { "epoch": 1.4140081197876728, "grad_norm": 1.471506118774414, "learning_rate": 0.00013440446950841695, "loss": 0.581943416595459, "step": 237880 }, { "epoch": 1.4140675618643412, "grad_norm": 1.8118566274642944, "learning_rate": 0.00013439847789751695, "loss": 0.6085656166076661, "step": 237890 }, { "epoch": 1.4141270039410097, "grad_norm": 1.404367208480835, "learning_rate": 0.00013439248616990265, "loss": 0.5988275527954101, "step": 237900 }, { "epoch": 1.414186446017678, "grad_norm": 1.3337311744689941, "learning_rate": 0.00013438649432560265, "loss": 0.5699965000152588, "step": 237910 }, { "epoch": 1.4142458880943465, "grad_norm": 1.878786563873291, "learning_rate": 0.00013438050236464562, "loss": 0.5722846031188965, "step": 237920 }, { "epoch": 1.414305330171015, "grad_norm": 1.8250360488891602, "learning_rate": 0.00013437451028706026, "loss": 0.5901391983032227, "step": 237930 }, { "epoch": 1.4143647722476833, "grad_norm": 1.5827678442001343, "learning_rate": 0.00013436851809287519, "loss": 0.5887996196746826, "step": 237940 }, { "epoch": 1.4144242143243515, "grad_norm": 1.4285204410552979, "learning_rate": 0.00013436252578211908, "loss": 0.6406853199005127, "step": 237950 }, { "epoch": 1.41448365640102, "grad_norm": 1.3492320775985718, "learning_rate": 0.00013435653335482065, "loss": 0.5382879257202149, "step": 237960 }, { "epoch": 1.4145430984776883, "grad_norm": 1.606940746307373, "learning_rate": 0.00013435054081100848, "loss": 0.5831008434295655, "step": 237970 }, { "epoch": 1.4146025405543567, "grad_norm": 1.4206594228744507, "learning_rate": 0.00013434454815071132, "loss": 0.6316610336303711, "step": 237980 }, { "epoch": 1.4146619826310252, "grad_norm": 1.508894920349121, "learning_rate": 0.00013433855537395777, "loss": 0.7032033443450928, "step": 237990 }, { "epoch": 1.4147214247076936, "grad_norm": 1.755614161491394, "learning_rate": 0.00013433256248077653, "loss": 0.631903076171875, "step": 238000 }, { "epoch": 1.414780866784362, "grad_norm": 1.842822551727295, "learning_rate": 0.0001343265694711963, "loss": 0.5872121810913086, "step": 238010 }, { "epoch": 1.4148403088610304, "grad_norm": 1.3504927158355713, "learning_rate": 0.00013432057634524562, "loss": 0.5859370231628418, "step": 238020 }, { "epoch": 1.4148997509376988, "grad_norm": 1.3920201063156128, "learning_rate": 0.00013431458310295336, "loss": 0.5901896476745605, "step": 238030 }, { "epoch": 1.4149591930143672, "grad_norm": 1.7073242664337158, "learning_rate": 0.000134308589744348, "loss": 0.5738662719726563, "step": 238040 }, { "epoch": 1.4150186350910356, "grad_norm": 1.1748220920562744, "learning_rate": 0.0001343025962694583, "loss": 0.6012770652770996, "step": 238050 }, { "epoch": 1.415078077167704, "grad_norm": 1.3802318572998047, "learning_rate": 0.00013429660267831297, "loss": 0.544086503982544, "step": 238060 }, { "epoch": 1.4151375192443723, "grad_norm": 1.1621519327163696, "learning_rate": 0.0001342906089709406, "loss": 0.5569485664367676, "step": 238070 }, { "epoch": 1.4151969613210407, "grad_norm": 1.2246686220169067, "learning_rate": 0.0001342846151473699, "loss": 0.5482039451599121, "step": 238080 }, { "epoch": 1.415256403397709, "grad_norm": 1.476839542388916, "learning_rate": 0.00013427862120762954, "loss": 0.5826766014099121, "step": 238090 }, { "epoch": 1.4153158454743775, "grad_norm": 1.5253819227218628, "learning_rate": 0.0001342726271517482, "loss": 0.6008216857910156, "step": 238100 }, { "epoch": 1.415375287551046, "grad_norm": 1.4132035970687866, "learning_rate": 0.0001342666329797545, "loss": 0.6360541343688965, "step": 238110 }, { "epoch": 1.4154347296277143, "grad_norm": 1.5746052265167236, "learning_rate": 0.00013426063869167722, "loss": 0.644711685180664, "step": 238120 }, { "epoch": 1.4154941717043827, "grad_norm": 1.4281837940216064, "learning_rate": 0.00013425464428754494, "loss": 0.6142254829406738, "step": 238130 }, { "epoch": 1.415553613781051, "grad_norm": 2.0312559604644775, "learning_rate": 0.00013424864976738636, "loss": 0.5471187114715577, "step": 238140 }, { "epoch": 1.4156130558577193, "grad_norm": 1.1610045433044434, "learning_rate": 0.0001342426551312302, "loss": 0.602644681930542, "step": 238150 }, { "epoch": 1.4156724979343878, "grad_norm": 1.5735722780227661, "learning_rate": 0.00013423666037910509, "loss": 0.621258020401001, "step": 238160 }, { "epoch": 1.4157319400110562, "grad_norm": 2.1919312477111816, "learning_rate": 0.00013423066551103966, "loss": 0.5132708072662353, "step": 238170 }, { "epoch": 1.4157913820877246, "grad_norm": 1.506437063217163, "learning_rate": 0.0001342246705270627, "loss": 0.5988739490509033, "step": 238180 }, { "epoch": 1.415850824164393, "grad_norm": 1.345274806022644, "learning_rate": 0.00013421867542720282, "loss": 0.5691328048706055, "step": 238190 }, { "epoch": 1.4159102662410614, "grad_norm": 1.7918126583099365, "learning_rate": 0.0001342126802114887, "loss": 0.5811135292053222, "step": 238200 }, { "epoch": 1.4159697083177298, "grad_norm": 1.835200548171997, "learning_rate": 0.00013420668487994908, "loss": 0.6073267459869385, "step": 238210 }, { "epoch": 1.4160291503943983, "grad_norm": 1.7326956987380981, "learning_rate": 0.00013420068943261254, "loss": 0.5461499214172363, "step": 238220 }, { "epoch": 1.4160885924710667, "grad_norm": 1.6580003499984741, "learning_rate": 0.0001341946938695078, "loss": 0.6313344001770019, "step": 238230 }, { "epoch": 1.416148034547735, "grad_norm": 1.5606770515441895, "learning_rate": 0.00013418869819066363, "loss": 0.5929625988006592, "step": 238240 }, { "epoch": 1.4162074766244033, "grad_norm": 1.8454277515411377, "learning_rate": 0.00013418270239610856, "loss": 0.5803481578826905, "step": 238250 }, { "epoch": 1.4162669187010717, "grad_norm": 2.0247223377227783, "learning_rate": 0.00013417670648587133, "loss": 0.5744487762451171, "step": 238260 }, { "epoch": 1.41632636077774, "grad_norm": 1.625725507736206, "learning_rate": 0.00013417071045998072, "loss": 0.5841806411743165, "step": 238270 }, { "epoch": 1.4163858028544085, "grad_norm": 1.7559359073638916, "learning_rate": 0.00013416471431846526, "loss": 0.56752028465271, "step": 238280 }, { "epoch": 1.416445244931077, "grad_norm": 1.496898889541626, "learning_rate": 0.00013415871806135373, "loss": 0.6095147132873535, "step": 238290 }, { "epoch": 1.4165046870077453, "grad_norm": 1.6418217420578003, "learning_rate": 0.0001341527216886748, "loss": 0.5902638912200928, "step": 238300 }, { "epoch": 1.4165641290844138, "grad_norm": 1.3918088674545288, "learning_rate": 0.00013414672520045709, "loss": 0.5738171577453614, "step": 238310 }, { "epoch": 1.416623571161082, "grad_norm": 1.8064824342727661, "learning_rate": 0.0001341407285967294, "loss": 0.6032962322235107, "step": 238320 }, { "epoch": 1.4166830132377504, "grad_norm": 1.5098540782928467, "learning_rate": 0.0001341347318775203, "loss": 0.6224784851074219, "step": 238330 }, { "epoch": 1.4167424553144188, "grad_norm": 1.7997478246688843, "learning_rate": 0.00013412873504285854, "loss": 0.590170955657959, "step": 238340 }, { "epoch": 1.4168018973910872, "grad_norm": 1.3510817289352417, "learning_rate": 0.00013412273809277283, "loss": 0.6282601356506348, "step": 238350 }, { "epoch": 1.4168613394677556, "grad_norm": 1.41758394241333, "learning_rate": 0.00013411674102729182, "loss": 0.6006502151489258, "step": 238360 }, { "epoch": 1.416920781544424, "grad_norm": 1.487553596496582, "learning_rate": 0.00013411074384644419, "loss": 0.6081042289733887, "step": 238370 }, { "epoch": 1.4169802236210924, "grad_norm": 1.2451879978179932, "learning_rate": 0.00013410474655025864, "loss": 0.5479774475097656, "step": 238380 }, { "epoch": 1.4170396656977609, "grad_norm": 1.1337018013000488, "learning_rate": 0.00013409874913876386, "loss": 0.5493194103240967, "step": 238390 }, { "epoch": 1.4170991077744293, "grad_norm": 1.2244291305541992, "learning_rate": 0.00013409275161198854, "loss": 0.5505293369293213, "step": 238400 }, { "epoch": 1.4171585498510977, "grad_norm": 1.2354490756988525, "learning_rate": 0.00013408675396996136, "loss": 0.596903133392334, "step": 238410 }, { "epoch": 1.417217991927766, "grad_norm": 1.9480774402618408, "learning_rate": 0.00013408075621271104, "loss": 0.6171329498291016, "step": 238420 }, { "epoch": 1.4172774340044345, "grad_norm": 1.5273971557617188, "learning_rate": 0.00013407475834026624, "loss": 0.6154984474182129, "step": 238430 }, { "epoch": 1.4173368760811027, "grad_norm": 1.3270982503890991, "learning_rate": 0.00013406876035265567, "loss": 0.6286489486694335, "step": 238440 }, { "epoch": 1.4173963181577711, "grad_norm": 1.2579632997512817, "learning_rate": 0.000134062762249908, "loss": 0.5984214782714844, "step": 238450 }, { "epoch": 1.4174557602344395, "grad_norm": 1.3595651388168335, "learning_rate": 0.00013405676403205197, "loss": 0.5440339565277099, "step": 238460 }, { "epoch": 1.417515202311108, "grad_norm": 1.6752128601074219, "learning_rate": 0.0001340507656991162, "loss": 0.6228701591491699, "step": 238470 }, { "epoch": 1.4175746443877764, "grad_norm": 1.620632290840149, "learning_rate": 0.00013404476725112946, "loss": 0.5896025657653808, "step": 238480 }, { "epoch": 1.4176340864644448, "grad_norm": 1.9510751962661743, "learning_rate": 0.0001340387686881204, "loss": 0.6633702278137207, "step": 238490 }, { "epoch": 1.4176935285411132, "grad_norm": 1.3283581733703613, "learning_rate": 0.00013403277001011775, "loss": 0.6340902328491211, "step": 238500 }, { "epoch": 1.4177529706177814, "grad_norm": 1.5519756078720093, "learning_rate": 0.00013402677121715015, "loss": 0.55160493850708, "step": 238510 }, { "epoch": 1.4178124126944498, "grad_norm": 1.550185203552246, "learning_rate": 0.00013402077230924633, "loss": 0.6078289031982422, "step": 238520 }, { "epoch": 1.4178718547711182, "grad_norm": 1.3154453039169312, "learning_rate": 0.000134014773286435, "loss": 0.5879621028900146, "step": 238530 }, { "epoch": 1.4179312968477866, "grad_norm": 1.776441216468811, "learning_rate": 0.00013400877414874483, "loss": 0.6418161869049073, "step": 238540 }, { "epoch": 1.417990738924455, "grad_norm": 1.810874104499817, "learning_rate": 0.00013400277489620458, "loss": 0.6151288986206055, "step": 238550 }, { "epoch": 1.4180501810011235, "grad_norm": 1.7982450723648071, "learning_rate": 0.00013399677552884285, "loss": 0.5738027095794678, "step": 238560 }, { "epoch": 1.4181096230777919, "grad_norm": 1.5686148405075073, "learning_rate": 0.00013399077604668837, "loss": 0.5773929595947266, "step": 238570 }, { "epoch": 1.4181690651544603, "grad_norm": 1.2767013311386108, "learning_rate": 0.00013398477644976993, "loss": 0.5778053283691407, "step": 238580 }, { "epoch": 1.4182285072311287, "grad_norm": 1.4834927320480347, "learning_rate": 0.00013397877673811608, "loss": 0.682856273651123, "step": 238590 }, { "epoch": 1.4182879493077971, "grad_norm": 1.2771562337875366, "learning_rate": 0.00013397277691175566, "loss": 0.5633277893066406, "step": 238600 }, { "epoch": 1.4183473913844655, "grad_norm": 1.7075181007385254, "learning_rate": 0.00013396677697071727, "loss": 0.6095250129699707, "step": 238610 }, { "epoch": 1.4184068334611337, "grad_norm": 1.8517086505889893, "learning_rate": 0.00013396077691502965, "loss": 0.6093891620635986, "step": 238620 }, { "epoch": 1.4184662755378021, "grad_norm": 1.000475287437439, "learning_rate": 0.00013395477674472153, "loss": 0.5695637226104736, "step": 238630 }, { "epoch": 1.4185257176144705, "grad_norm": 2.557838201522827, "learning_rate": 0.00013394877645982157, "loss": 0.598146629333496, "step": 238640 }, { "epoch": 1.418585159691139, "grad_norm": 1.617088794708252, "learning_rate": 0.00013394277606035849, "loss": 0.6106451034545899, "step": 238650 }, { "epoch": 1.4186446017678074, "grad_norm": 1.8578280210494995, "learning_rate": 0.000133936775546361, "loss": 0.5932716369628906, "step": 238660 }, { "epoch": 1.4187040438444758, "grad_norm": 1.5659267902374268, "learning_rate": 0.0001339307749178578, "loss": 0.6088356971740723, "step": 238670 }, { "epoch": 1.4187634859211442, "grad_norm": 1.6638169288635254, "learning_rate": 0.00013392477417487758, "loss": 0.5585556983947754, "step": 238680 }, { "epoch": 1.4188229279978124, "grad_norm": 1.585497498512268, "learning_rate": 0.00013391877331744907, "loss": 0.6682289123535157, "step": 238690 }, { "epoch": 1.4188823700744808, "grad_norm": 1.8694499731063843, "learning_rate": 0.00013391277234560094, "loss": 0.6083438873291016, "step": 238700 }, { "epoch": 1.4189418121511492, "grad_norm": 2.0422539710998535, "learning_rate": 0.00013390677125936195, "loss": 0.5705687522888183, "step": 238710 }, { "epoch": 1.4190012542278176, "grad_norm": 1.1927422285079956, "learning_rate": 0.00013390077005876076, "loss": 0.5768858909606933, "step": 238720 }, { "epoch": 1.419060696304486, "grad_norm": 1.4883400201797485, "learning_rate": 0.00013389476874382613, "loss": 0.5226636409759522, "step": 238730 }, { "epoch": 1.4191201383811545, "grad_norm": 1.6879907846450806, "learning_rate": 0.0001338887673145867, "loss": 0.5738224506378173, "step": 238740 }, { "epoch": 1.4191795804578229, "grad_norm": 1.4851107597351074, "learning_rate": 0.00013388276577107122, "loss": 0.6257441520690918, "step": 238750 }, { "epoch": 1.4192390225344913, "grad_norm": 1.864201307296753, "learning_rate": 0.0001338767641133084, "loss": 0.610022783279419, "step": 238760 }, { "epoch": 1.4192984646111597, "grad_norm": 1.5447789430618286, "learning_rate": 0.000133870762341327, "loss": 0.5702915668487549, "step": 238770 }, { "epoch": 1.4193579066878281, "grad_norm": 1.8790160417556763, "learning_rate": 0.00013386476045515558, "loss": 0.5945346832275391, "step": 238780 }, { "epoch": 1.4194173487644965, "grad_norm": 1.5032860040664673, "learning_rate": 0.000133858758454823, "loss": 0.6143382072448731, "step": 238790 }, { "epoch": 1.419476790841165, "grad_norm": 1.5623356103897095, "learning_rate": 0.0001338527563403579, "loss": 0.5754345417022705, "step": 238800 }, { "epoch": 1.4195362329178332, "grad_norm": 1.7697887420654297, "learning_rate": 0.00013384675411178898, "loss": 0.6323402404785157, "step": 238810 }, { "epoch": 1.4195956749945016, "grad_norm": 2.117077589035034, "learning_rate": 0.00013384075176914507, "loss": 0.570477294921875, "step": 238820 }, { "epoch": 1.41965511707117, "grad_norm": 1.4084709882736206, "learning_rate": 0.00013383474931245471, "loss": 0.5474076747894288, "step": 238830 }, { "epoch": 1.4197145591478384, "grad_norm": 1.444197654724121, "learning_rate": 0.00013382874674174673, "loss": 0.6146585464477539, "step": 238840 }, { "epoch": 1.4197740012245068, "grad_norm": 1.2337149381637573, "learning_rate": 0.0001338227440570498, "loss": 0.5812760353088379, "step": 238850 }, { "epoch": 1.4198334433011752, "grad_norm": 1.6042240858078003, "learning_rate": 0.00013381674125839265, "loss": 0.6084124565124511, "step": 238860 }, { "epoch": 1.4198928853778436, "grad_norm": 1.4961376190185547, "learning_rate": 0.00013381073834580403, "loss": 0.6127735137939453, "step": 238870 }, { "epoch": 1.4199523274545118, "grad_norm": 1.5171480178833008, "learning_rate": 0.00013380473531931258, "loss": 0.5947783470153809, "step": 238880 }, { "epoch": 1.4200117695311802, "grad_norm": 1.2499624490737915, "learning_rate": 0.00013379873217894708, "loss": 0.5990639686584472, "step": 238890 }, { "epoch": 1.4200712116078487, "grad_norm": 1.471524953842163, "learning_rate": 0.00013379272892473617, "loss": 0.5857731342315674, "step": 238900 }, { "epoch": 1.420130653684517, "grad_norm": 1.4916781187057495, "learning_rate": 0.00013378672555670868, "loss": 0.5776642799377442, "step": 238910 }, { "epoch": 1.4201900957611855, "grad_norm": 1.6776466369628906, "learning_rate": 0.00013378072207489321, "loss": 0.6395426750183105, "step": 238920 }, { "epoch": 1.420249537837854, "grad_norm": 1.3953958749771118, "learning_rate": 0.0001337747184793186, "loss": 0.5820749282836915, "step": 238930 }, { "epoch": 1.4203089799145223, "grad_norm": 1.175110936164856, "learning_rate": 0.00013376871477001348, "loss": 0.5979762077331543, "step": 238940 }, { "epoch": 1.4203684219911907, "grad_norm": 1.5411107540130615, "learning_rate": 0.00013376271094700659, "loss": 0.6147138118743897, "step": 238950 }, { "epoch": 1.4204278640678591, "grad_norm": 1.567246913909912, "learning_rate": 0.00013375670701032668, "loss": 0.5635627746582031, "step": 238960 }, { "epoch": 1.4204873061445276, "grad_norm": 1.4326344728469849, "learning_rate": 0.0001337507029600024, "loss": 0.5710065364837646, "step": 238970 }, { "epoch": 1.420546748221196, "grad_norm": 1.6822153329849243, "learning_rate": 0.00013374469879606259, "loss": 0.6039129734039307, "step": 238980 }, { "epoch": 1.4206061902978642, "grad_norm": 1.2083436250686646, "learning_rate": 0.00013373869451853583, "loss": 0.5954333305358886, "step": 238990 }, { "epoch": 1.4206656323745326, "grad_norm": 1.3053903579711914, "learning_rate": 0.00013373269012745097, "loss": 0.5504596710205079, "step": 239000 }, { "epoch": 1.420725074451201, "grad_norm": 1.3570905923843384, "learning_rate": 0.00013372668562283666, "loss": 0.596259593963623, "step": 239010 }, { "epoch": 1.4207845165278694, "grad_norm": 1.468353033065796, "learning_rate": 0.0001337206810047216, "loss": 0.5324639320373535, "step": 239020 }, { "epoch": 1.4208439586045378, "grad_norm": 1.1287063360214233, "learning_rate": 0.00013371467627313458, "loss": 0.622163963317871, "step": 239030 }, { "epoch": 1.4209034006812062, "grad_norm": 1.215427279472351, "learning_rate": 0.00013370867142810432, "loss": 0.5992230892181396, "step": 239040 }, { "epoch": 1.4209628427578747, "grad_norm": 1.630982518196106, "learning_rate": 0.00013370266646965946, "loss": 0.609902811050415, "step": 239050 }, { "epoch": 1.4210222848345428, "grad_norm": 1.8558405637741089, "learning_rate": 0.00013369666139782885, "loss": 0.6020854949951172, "step": 239060 }, { "epoch": 1.4210817269112113, "grad_norm": 1.3203001022338867, "learning_rate": 0.00013369065621264117, "loss": 0.5929819107055664, "step": 239070 }, { "epoch": 1.4211411689878797, "grad_norm": 1.4967681169509888, "learning_rate": 0.0001336846509141251, "loss": 0.6216988563537598, "step": 239080 }, { "epoch": 1.421200611064548, "grad_norm": 1.295428991317749, "learning_rate": 0.00013367864550230943, "loss": 0.5879114151000977, "step": 239090 }, { "epoch": 1.4212600531412165, "grad_norm": 1.2116142511367798, "learning_rate": 0.00013367263997722282, "loss": 0.6082880020141601, "step": 239100 }, { "epoch": 1.421319495217885, "grad_norm": 1.192923665046692, "learning_rate": 0.00013366663433889402, "loss": 0.5585797786712646, "step": 239110 }, { "epoch": 1.4213789372945533, "grad_norm": 1.274125099182129, "learning_rate": 0.0001336606285873518, "loss": 0.5820591926574707, "step": 239120 }, { "epoch": 1.4214383793712217, "grad_norm": 1.8437896966934204, "learning_rate": 0.0001336546227226249, "loss": 0.6304648399353028, "step": 239130 }, { "epoch": 1.4214978214478902, "grad_norm": 1.3958065509796143, "learning_rate": 0.000133648616744742, "loss": 0.5916520118713379, "step": 239140 }, { "epoch": 1.4215572635245586, "grad_norm": 1.5115151405334473, "learning_rate": 0.0001336426106537318, "loss": 0.5356298923492432, "step": 239150 }, { "epoch": 1.421616705601227, "grad_norm": 1.4990490674972534, "learning_rate": 0.00013363660444962313, "loss": 0.5855748176574707, "step": 239160 }, { "epoch": 1.4216761476778954, "grad_norm": 1.9126641750335693, "learning_rate": 0.00013363059813244465, "loss": 0.6524168968200683, "step": 239170 }, { "epoch": 1.4217355897545636, "grad_norm": 1.191829800605774, "learning_rate": 0.0001336245917022251, "loss": 0.5964524269104003, "step": 239180 }, { "epoch": 1.421795031831232, "grad_norm": 1.4348328113555908, "learning_rate": 0.00013361858515899323, "loss": 0.5920027732849121, "step": 239190 }, { "epoch": 1.4218544739079004, "grad_norm": 1.3921234607696533, "learning_rate": 0.00013361257850277777, "loss": 0.5679256439208984, "step": 239200 }, { "epoch": 1.4219139159845688, "grad_norm": 2.046992301940918, "learning_rate": 0.00013360657173360743, "loss": 0.5636716842651367, "step": 239210 }, { "epoch": 1.4219733580612373, "grad_norm": 1.291032314300537, "learning_rate": 0.000133600564851511, "loss": 0.5892333507537841, "step": 239220 }, { "epoch": 1.4220328001379057, "grad_norm": 1.2063918113708496, "learning_rate": 0.00013359455785651717, "loss": 0.5448369026184082, "step": 239230 }, { "epoch": 1.422092242214574, "grad_norm": 1.3308935165405273, "learning_rate": 0.00013358855074865469, "loss": 0.6179015159606933, "step": 239240 }, { "epoch": 1.4221516842912423, "grad_norm": 1.8504730463027954, "learning_rate": 0.00013358254352795228, "loss": 0.5796768188476562, "step": 239250 }, { "epoch": 1.4222111263679107, "grad_norm": 1.6267913579940796, "learning_rate": 0.00013357653619443867, "loss": 0.5566246032714843, "step": 239260 }, { "epoch": 1.422270568444579, "grad_norm": 1.2381565570831299, "learning_rate": 0.00013357052874814267, "loss": 0.5654218673706055, "step": 239270 }, { "epoch": 1.4223300105212475, "grad_norm": 1.549928069114685, "learning_rate": 0.00013356452118909294, "loss": 0.5576966762542724, "step": 239280 }, { "epoch": 1.422389452597916, "grad_norm": 1.149897813796997, "learning_rate": 0.0001335585135173182, "loss": 0.5256298065185547, "step": 239290 }, { "epoch": 1.4224488946745844, "grad_norm": 1.1761715412139893, "learning_rate": 0.0001335525057328473, "loss": 0.5631623268127441, "step": 239300 }, { "epoch": 1.4225083367512528, "grad_norm": 1.2441452741622925, "learning_rate": 0.00013354649783570884, "loss": 0.6129164218902587, "step": 239310 }, { "epoch": 1.4225677788279212, "grad_norm": 1.6027038097381592, "learning_rate": 0.0001335404898259317, "loss": 0.5278229236602783, "step": 239320 }, { "epoch": 1.4226272209045896, "grad_norm": 1.1884772777557373, "learning_rate": 0.0001335344817035445, "loss": 0.5456472396850586, "step": 239330 }, { "epoch": 1.422686662981258, "grad_norm": 1.6761571168899536, "learning_rate": 0.00013352847346857603, "loss": 0.5834836959838867, "step": 239340 }, { "epoch": 1.4227461050579264, "grad_norm": 1.3355673551559448, "learning_rate": 0.00013352246512105507, "loss": 0.6126425743103028, "step": 239350 }, { "epoch": 1.4228055471345946, "grad_norm": 1.60271418094635, "learning_rate": 0.0001335164566610103, "loss": 0.577394437789917, "step": 239360 }, { "epoch": 1.422864989211263, "grad_norm": 1.5351381301879883, "learning_rate": 0.00013351044808847048, "loss": 0.5662958145141601, "step": 239370 }, { "epoch": 1.4229244312879314, "grad_norm": 1.4838370084762573, "learning_rate": 0.00013350443940346438, "loss": 0.6140005111694335, "step": 239380 }, { "epoch": 1.4229838733645999, "grad_norm": 1.5047625303268433, "learning_rate": 0.0001334984306060207, "loss": 0.584237813949585, "step": 239390 }, { "epoch": 1.4230433154412683, "grad_norm": 1.184686303138733, "learning_rate": 0.00013349242169616822, "loss": 0.6247045516967773, "step": 239400 }, { "epoch": 1.4231027575179367, "grad_norm": 1.2788760662078857, "learning_rate": 0.00013348641267393568, "loss": 0.5821667194366456, "step": 239410 }, { "epoch": 1.423162199594605, "grad_norm": 1.2795169353485107, "learning_rate": 0.00013348040353935179, "loss": 0.6460444927215576, "step": 239420 }, { "epoch": 1.4232216416712733, "grad_norm": 1.6719402074813843, "learning_rate": 0.00013347439429244534, "loss": 0.6455288887023926, "step": 239430 }, { "epoch": 1.4232810837479417, "grad_norm": 1.3223059177398682, "learning_rate": 0.00013346838493324506, "loss": 0.632075023651123, "step": 239440 }, { "epoch": 1.4233405258246101, "grad_norm": 1.1766692399978638, "learning_rate": 0.0001334623754617797, "loss": 0.5240013122558593, "step": 239450 }, { "epoch": 1.4233999679012785, "grad_norm": 1.3611443042755127, "learning_rate": 0.000133456365878078, "loss": 0.5805155277252197, "step": 239460 }, { "epoch": 1.423459409977947, "grad_norm": 1.678972840309143, "learning_rate": 0.0001334503561821687, "loss": 0.5695881843566895, "step": 239470 }, { "epoch": 1.4235188520546154, "grad_norm": 1.3653712272644043, "learning_rate": 0.0001334443463740806, "loss": 0.6330737590789794, "step": 239480 }, { "epoch": 1.4235782941312838, "grad_norm": 1.8117339611053467, "learning_rate": 0.00013343833645384234, "loss": 0.6279991626739502, "step": 239490 }, { "epoch": 1.4236377362079522, "grad_norm": 1.5000464916229248, "learning_rate": 0.0001334323264214828, "loss": 0.598177433013916, "step": 239500 }, { "epoch": 1.4236971782846206, "grad_norm": 1.6532143354415894, "learning_rate": 0.00013342631627703063, "loss": 0.5841742515563965, "step": 239510 }, { "epoch": 1.423756620361289, "grad_norm": 1.5447908639907837, "learning_rate": 0.00013342030602051463, "loss": 0.5588548660278321, "step": 239520 }, { "epoch": 1.4238160624379574, "grad_norm": 1.4988384246826172, "learning_rate": 0.00013341429565196357, "loss": 0.6120190620422363, "step": 239530 }, { "epoch": 1.4238755045146259, "grad_norm": 1.799551248550415, "learning_rate": 0.00013340828517140614, "loss": 0.6867556571960449, "step": 239540 }, { "epoch": 1.423934946591294, "grad_norm": 1.7444474697113037, "learning_rate": 0.00013340227457887108, "loss": 0.6122270107269288, "step": 239550 }, { "epoch": 1.4239943886679625, "grad_norm": 1.7084332704544067, "learning_rate": 0.00013339626387438727, "loss": 0.5955083847045899, "step": 239560 }, { "epoch": 1.4240538307446309, "grad_norm": 1.8310407400131226, "learning_rate": 0.00013339025305798334, "loss": 0.6098770141601563, "step": 239570 }, { "epoch": 1.4241132728212993, "grad_norm": 1.6753262281417847, "learning_rate": 0.0001333842421296881, "loss": 0.657225513458252, "step": 239580 }, { "epoch": 1.4241727148979677, "grad_norm": 1.426992416381836, "learning_rate": 0.00013337823108953027, "loss": 0.5890360832214355, "step": 239590 }, { "epoch": 1.4242321569746361, "grad_norm": 1.541311264038086, "learning_rate": 0.00013337221993753862, "loss": 0.5766763687133789, "step": 239600 }, { "epoch": 1.4242915990513045, "grad_norm": 1.425385594367981, "learning_rate": 0.0001333662086737419, "loss": 0.5928876399993896, "step": 239610 }, { "epoch": 1.4243510411279727, "grad_norm": 1.4164347648620605, "learning_rate": 0.00013336019729816894, "loss": 0.5488799095153809, "step": 239620 }, { "epoch": 1.4244104832046411, "grad_norm": 1.675473928451538, "learning_rate": 0.00013335418581084837, "loss": 0.5867045402526856, "step": 239630 }, { "epoch": 1.4244699252813096, "grad_norm": 1.9531499147415161, "learning_rate": 0.000133348174211809, "loss": 0.5938885688781739, "step": 239640 }, { "epoch": 1.424529367357978, "grad_norm": 1.6396260261535645, "learning_rate": 0.00013334216250107962, "loss": 0.6144383430480957, "step": 239650 }, { "epoch": 1.4245888094346464, "grad_norm": 1.4101158380508423, "learning_rate": 0.00013333615067868894, "loss": 0.5698696136474609, "step": 239660 }, { "epoch": 1.4246482515113148, "grad_norm": 1.5027953386306763, "learning_rate": 0.00013333013874466577, "loss": 0.5774734020233154, "step": 239670 }, { "epoch": 1.4247076935879832, "grad_norm": 1.9252420663833618, "learning_rate": 0.00013332412669903883, "loss": 0.5747758388519287, "step": 239680 }, { "epoch": 1.4247671356646516, "grad_norm": 1.4195892810821533, "learning_rate": 0.0001333181145418369, "loss": 0.5373315811157227, "step": 239690 }, { "epoch": 1.42482657774132, "grad_norm": 1.7427247762680054, "learning_rate": 0.00013331210227308867, "loss": 0.536489200592041, "step": 239700 }, { "epoch": 1.4248860198179885, "grad_norm": 1.4809041023254395, "learning_rate": 0.00013330608989282303, "loss": 0.6337143898010253, "step": 239710 }, { "epoch": 1.4249454618946569, "grad_norm": 1.322134017944336, "learning_rate": 0.00013330007740106867, "loss": 0.5884501457214355, "step": 239720 }, { "epoch": 1.425004903971325, "grad_norm": 1.6303638219833374, "learning_rate": 0.0001332940647978543, "loss": 0.6333689212799072, "step": 239730 }, { "epoch": 1.4250643460479935, "grad_norm": 1.3447872400283813, "learning_rate": 0.0001332880520832088, "loss": 0.6153326034545898, "step": 239740 }, { "epoch": 1.425123788124662, "grad_norm": 1.7244023084640503, "learning_rate": 0.00013328203925716084, "loss": 0.5776157379150391, "step": 239750 }, { "epoch": 1.4251832302013303, "grad_norm": 1.4959025382995605, "learning_rate": 0.0001332760263197392, "loss": 0.5515937328338623, "step": 239760 }, { "epoch": 1.4252426722779987, "grad_norm": 1.4392321109771729, "learning_rate": 0.00013327001327097268, "loss": 0.5921509742736817, "step": 239770 }, { "epoch": 1.4253021143546671, "grad_norm": 1.4319146871566772, "learning_rate": 0.00013326400011089002, "loss": 0.5956713199615479, "step": 239780 }, { "epoch": 1.4253615564313356, "grad_norm": 1.6136863231658936, "learning_rate": 0.00013325798683952, "loss": 0.6018271446228027, "step": 239790 }, { "epoch": 1.4254209985080037, "grad_norm": 1.5578757524490356, "learning_rate": 0.00013325197345689132, "loss": 0.5771444320678711, "step": 239800 }, { "epoch": 1.4254804405846722, "grad_norm": 1.3721678256988525, "learning_rate": 0.00013324595996303285, "loss": 0.5679915428161622, "step": 239810 }, { "epoch": 1.4255398826613406, "grad_norm": 1.831087589263916, "learning_rate": 0.00013323994635797327, "loss": 0.6148297786712646, "step": 239820 }, { "epoch": 1.425599324738009, "grad_norm": 1.654457449913025, "learning_rate": 0.00013323393264174139, "loss": 0.5839317321777344, "step": 239830 }, { "epoch": 1.4256587668146774, "grad_norm": 1.4726589918136597, "learning_rate": 0.00013322791881436598, "loss": 0.6129768848419189, "step": 239840 }, { "epoch": 1.4257182088913458, "grad_norm": 1.3541064262390137, "learning_rate": 0.00013322190487587577, "loss": 0.6334352970123291, "step": 239850 }, { "epoch": 1.4257776509680142, "grad_norm": 1.6220558881759644, "learning_rate": 0.00013321589082629959, "loss": 0.6086787223815918, "step": 239860 }, { "epoch": 1.4258370930446826, "grad_norm": 1.6843422651290894, "learning_rate": 0.00013320987666566619, "loss": 0.5739124774932861, "step": 239870 }, { "epoch": 1.425896535121351, "grad_norm": 1.220616102218628, "learning_rate": 0.00013320386239400428, "loss": 0.6402382850646973, "step": 239880 }, { "epoch": 1.4259559771980195, "grad_norm": 1.2528460025787354, "learning_rate": 0.00013319784801134267, "loss": 0.6066677093505859, "step": 239890 }, { "epoch": 1.426015419274688, "grad_norm": 1.1949419975280762, "learning_rate": 0.00013319183351771018, "loss": 0.588132667541504, "step": 239900 }, { "epoch": 1.4260748613513563, "grad_norm": 1.7072943449020386, "learning_rate": 0.00013318581891313554, "loss": 0.5851970672607422, "step": 239910 }, { "epoch": 1.4261343034280245, "grad_norm": 1.516019582748413, "learning_rate": 0.00013317980419764747, "loss": 0.6111824035644531, "step": 239920 }, { "epoch": 1.426193745504693, "grad_norm": 1.4741427898406982, "learning_rate": 0.00013317378937127483, "loss": 0.584011173248291, "step": 239930 }, { "epoch": 1.4262531875813613, "grad_norm": 1.4105643033981323, "learning_rate": 0.00013316777443404636, "loss": 0.6073162078857421, "step": 239940 }, { "epoch": 1.4263126296580297, "grad_norm": 1.614054560661316, "learning_rate": 0.00013316175938599077, "loss": 0.6306782722473144, "step": 239950 }, { "epoch": 1.4263720717346982, "grad_norm": 1.7630667686462402, "learning_rate": 0.00013315574422713696, "loss": 0.5915566921234131, "step": 239960 }, { "epoch": 1.4264315138113666, "grad_norm": 1.4135897159576416, "learning_rate": 0.0001331497289575136, "loss": 0.5897793292999267, "step": 239970 }, { "epoch": 1.426490955888035, "grad_norm": 1.5843260288238525, "learning_rate": 0.00013314371357714953, "loss": 0.5628083705902099, "step": 239980 }, { "epoch": 1.4265503979647032, "grad_norm": 1.1006911993026733, "learning_rate": 0.00013313769808607345, "loss": 0.5725395202636718, "step": 239990 }, { "epoch": 1.4266098400413716, "grad_norm": 1.7037228345870972, "learning_rate": 0.00013313168248431422, "loss": 0.584693717956543, "step": 240000 }, { "epoch": 1.42666928211804, "grad_norm": 1.586875319480896, "learning_rate": 0.00013312566677190057, "loss": 0.5610676288604737, "step": 240010 }, { "epoch": 1.4267287241947084, "grad_norm": 1.394250750541687, "learning_rate": 0.00013311965094886129, "loss": 0.6160186290740967, "step": 240020 }, { "epoch": 1.4267881662713768, "grad_norm": 1.5353723764419556, "learning_rate": 0.0001331136350152252, "loss": 0.6011082649230957, "step": 240030 }, { "epoch": 1.4268476083480452, "grad_norm": 1.411492943763733, "learning_rate": 0.00013310761897102096, "loss": 0.5864736557006835, "step": 240040 }, { "epoch": 1.4269070504247137, "grad_norm": 1.7069321870803833, "learning_rate": 0.00013310160281627747, "loss": 0.5847681522369385, "step": 240050 }, { "epoch": 1.426966492501382, "grad_norm": 1.7107274532318115, "learning_rate": 0.00013309558655102342, "loss": 0.6315161705017089, "step": 240060 }, { "epoch": 1.4270259345780505, "grad_norm": 1.3548364639282227, "learning_rate": 0.00013308957017528768, "loss": 0.5843396186828613, "step": 240070 }, { "epoch": 1.427085376654719, "grad_norm": 1.407300591468811, "learning_rate": 0.00013308355368909895, "loss": 0.5407508850097656, "step": 240080 }, { "epoch": 1.4271448187313873, "grad_norm": 1.505913496017456, "learning_rate": 0.00013307753709248605, "loss": 0.5642381191253663, "step": 240090 }, { "epoch": 1.4272042608080555, "grad_norm": 1.5173383951187134, "learning_rate": 0.00013307152038547778, "loss": 0.599104642868042, "step": 240100 }, { "epoch": 1.427263702884724, "grad_norm": 1.673673391342163, "learning_rate": 0.00013306550356810285, "loss": 0.5211353778839112, "step": 240110 }, { "epoch": 1.4273231449613923, "grad_norm": 1.4123246669769287, "learning_rate": 0.00013305948664039014, "loss": 0.6016207695007324, "step": 240120 }, { "epoch": 1.4273825870380608, "grad_norm": 1.7313140630722046, "learning_rate": 0.00013305346960236836, "loss": 0.6072660446166992, "step": 240130 }, { "epoch": 1.4274420291147292, "grad_norm": 1.0422016382217407, "learning_rate": 0.00013304745245406628, "loss": 0.6210530281066895, "step": 240140 }, { "epoch": 1.4275014711913976, "grad_norm": 1.622820496559143, "learning_rate": 0.00013304143519551274, "loss": 0.6571541786193847, "step": 240150 }, { "epoch": 1.427560913268066, "grad_norm": 1.3273546695709229, "learning_rate": 0.00013303541782673652, "loss": 0.6011677742004394, "step": 240160 }, { "epoch": 1.4276203553447342, "grad_norm": 1.4882310628890991, "learning_rate": 0.0001330294003477664, "loss": 0.6274993419647217, "step": 240170 }, { "epoch": 1.4276797974214026, "grad_norm": 1.53148353099823, "learning_rate": 0.00013302338275863115, "loss": 0.5137715816497803, "step": 240180 }, { "epoch": 1.427739239498071, "grad_norm": 1.162461757659912, "learning_rate": 0.0001330173650593595, "loss": 0.584160327911377, "step": 240190 }, { "epoch": 1.4277986815747394, "grad_norm": 1.2729798555374146, "learning_rate": 0.00013301134724998036, "loss": 0.5887252807617187, "step": 240200 }, { "epoch": 1.4278581236514079, "grad_norm": 1.5217790603637695, "learning_rate": 0.00013300532933052247, "loss": 0.5765049934387207, "step": 240210 }, { "epoch": 1.4279175657280763, "grad_norm": 1.7939070463180542, "learning_rate": 0.00013299931130101455, "loss": 0.6268978118896484, "step": 240220 }, { "epoch": 1.4279770078047447, "grad_norm": 2.0230093002319336, "learning_rate": 0.00013299329316148546, "loss": 0.665393877029419, "step": 240230 }, { "epoch": 1.428036449881413, "grad_norm": 2.0264649391174316, "learning_rate": 0.00013298727491196398, "loss": 0.6205916404724121, "step": 240240 }, { "epoch": 1.4280958919580815, "grad_norm": 1.678792119026184, "learning_rate": 0.0001329812565524789, "loss": 0.5875555992126464, "step": 240250 }, { "epoch": 1.42815533403475, "grad_norm": 1.2555780410766602, "learning_rate": 0.00013297523808305896, "loss": 0.5598633766174317, "step": 240260 }, { "epoch": 1.4282147761114183, "grad_norm": 1.6259589195251465, "learning_rate": 0.00013296921950373301, "loss": 0.6219799518585205, "step": 240270 }, { "epoch": 1.4282742181880868, "grad_norm": 1.5489529371261597, "learning_rate": 0.00013296320081452985, "loss": 0.57286376953125, "step": 240280 }, { "epoch": 1.428333660264755, "grad_norm": 1.625018835067749, "learning_rate": 0.0001329571820154782, "loss": 0.5134829521179199, "step": 240290 }, { "epoch": 1.4283931023414234, "grad_norm": 1.4718515872955322, "learning_rate": 0.0001329511631066069, "loss": 0.5332706451416016, "step": 240300 }, { "epoch": 1.4284525444180918, "grad_norm": 1.1892480850219727, "learning_rate": 0.00013294514408794476, "loss": 0.6261889457702636, "step": 240310 }, { "epoch": 1.4285119864947602, "grad_norm": 1.4545820951461792, "learning_rate": 0.0001329391249595205, "loss": 0.5550380706787109, "step": 240320 }, { "epoch": 1.4285714285714286, "grad_norm": 1.2567510604858398, "learning_rate": 0.00013293310572136304, "loss": 0.5335342884063721, "step": 240330 }, { "epoch": 1.428630870648097, "grad_norm": 1.709784746170044, "learning_rate": 0.00013292708637350104, "loss": 0.564104413986206, "step": 240340 }, { "epoch": 1.4286903127247654, "grad_norm": 1.260616421699524, "learning_rate": 0.00013292106691596337, "loss": 0.5987223625183106, "step": 240350 }, { "epoch": 1.4287497548014336, "grad_norm": 1.6427626609802246, "learning_rate": 0.00013291504734877878, "loss": 0.5706235885620117, "step": 240360 }, { "epoch": 1.428809196878102, "grad_norm": 1.556313157081604, "learning_rate": 0.00013290902767197613, "loss": 0.5737281799316406, "step": 240370 }, { "epoch": 1.4288686389547705, "grad_norm": 1.7505015134811401, "learning_rate": 0.00013290300788558416, "loss": 0.5115490913391113, "step": 240380 }, { "epoch": 1.4289280810314389, "grad_norm": 1.717164397239685, "learning_rate": 0.00013289698798963167, "loss": 0.5563071250915528, "step": 240390 }, { "epoch": 1.4289875231081073, "grad_norm": 1.5974040031433105, "learning_rate": 0.00013289096798414752, "loss": 0.5189838409423828, "step": 240400 }, { "epoch": 1.4290469651847757, "grad_norm": 1.7539983987808228, "learning_rate": 0.0001328849478691604, "loss": 0.598700475692749, "step": 240410 }, { "epoch": 1.4291064072614441, "grad_norm": 1.3424153327941895, "learning_rate": 0.0001328789276446992, "loss": 0.6361705303192139, "step": 240420 }, { "epoch": 1.4291658493381125, "grad_norm": 1.3005034923553467, "learning_rate": 0.00013287290731079268, "loss": 0.6244044303894043, "step": 240430 }, { "epoch": 1.429225291414781, "grad_norm": 1.184092402458191, "learning_rate": 0.00013286688686746967, "loss": 0.5532041549682617, "step": 240440 }, { "epoch": 1.4292847334914494, "grad_norm": 1.7668709754943848, "learning_rate": 0.00013286086631475891, "loss": 0.5704620361328125, "step": 240450 }, { "epoch": 1.4293441755681178, "grad_norm": 1.5023760795593262, "learning_rate": 0.0001328548456526893, "loss": 0.5620986938476562, "step": 240460 }, { "epoch": 1.429403617644786, "grad_norm": 1.771885633468628, "learning_rate": 0.0001328488248812895, "loss": 0.5681702613830566, "step": 240470 }, { "epoch": 1.4294630597214544, "grad_norm": 1.5001035928726196, "learning_rate": 0.00013284280400058842, "loss": 0.6562656402587891, "step": 240480 }, { "epoch": 1.4295225017981228, "grad_norm": 1.1048369407653809, "learning_rate": 0.00013283678301061484, "loss": 0.6486211776733398, "step": 240490 }, { "epoch": 1.4295819438747912, "grad_norm": 1.4462025165557861, "learning_rate": 0.0001328307619113975, "loss": 0.566644287109375, "step": 240500 }, { "epoch": 1.4296413859514596, "grad_norm": 1.565645694732666, "learning_rate": 0.00013282474070296533, "loss": 0.6152751922607422, "step": 240510 }, { "epoch": 1.429700828028128, "grad_norm": 1.3388829231262207, "learning_rate": 0.00013281871938534702, "loss": 0.5702908515930176, "step": 240520 }, { "epoch": 1.4297602701047964, "grad_norm": 1.6047441959381104, "learning_rate": 0.00013281269795857142, "loss": 0.5423399925231933, "step": 240530 }, { "epoch": 1.4298197121814646, "grad_norm": 1.8483279943466187, "learning_rate": 0.00013280667642266732, "loss": 0.5730802536010742, "step": 240540 }, { "epoch": 1.429879154258133, "grad_norm": 1.420932650566101, "learning_rate": 0.00013280065477766357, "loss": 0.6018044471740722, "step": 240550 }, { "epoch": 1.4299385963348015, "grad_norm": 1.3076244592666626, "learning_rate": 0.0001327946330235889, "loss": 0.5674921035766601, "step": 240560 }, { "epoch": 1.4299980384114699, "grad_norm": 1.3787052631378174, "learning_rate": 0.00013278861116047217, "loss": 0.5756086349487305, "step": 240570 }, { "epoch": 1.4300574804881383, "grad_norm": 1.4477481842041016, "learning_rate": 0.00013278258918834218, "loss": 0.6251782417297364, "step": 240580 }, { "epoch": 1.4301169225648067, "grad_norm": 1.377867341041565, "learning_rate": 0.00013277656710722772, "loss": 0.5350530624389649, "step": 240590 }, { "epoch": 1.4301763646414751, "grad_norm": 1.519147276878357, "learning_rate": 0.00013277054491715758, "loss": 0.6266798973083496, "step": 240600 }, { "epoch": 1.4302358067181435, "grad_norm": 1.6829946041107178, "learning_rate": 0.00013276452261816067, "loss": 0.5768364429473877, "step": 240610 }, { "epoch": 1.430295248794812, "grad_norm": 1.5316576957702637, "learning_rate": 0.00013275850021026564, "loss": 0.6188311576843262, "step": 240620 }, { "epoch": 1.4303546908714804, "grad_norm": 1.3227564096450806, "learning_rate": 0.0001327524776935014, "loss": 0.635436725616455, "step": 240630 }, { "epoch": 1.4304141329481488, "grad_norm": 1.402296781539917, "learning_rate": 0.00013274645506789677, "loss": 0.515713119506836, "step": 240640 }, { "epoch": 1.4304735750248172, "grad_norm": 1.6393204927444458, "learning_rate": 0.00013274043233348052, "loss": 0.6290844917297364, "step": 240650 }, { "epoch": 1.4305330171014854, "grad_norm": 1.4678751230239868, "learning_rate": 0.0001327344094902815, "loss": 0.5405017375946045, "step": 240660 }, { "epoch": 1.4305924591781538, "grad_norm": 1.5250046253204346, "learning_rate": 0.00013272838653832845, "loss": 0.5832863807678222, "step": 240670 }, { "epoch": 1.4306519012548222, "grad_norm": 1.6188229322433472, "learning_rate": 0.00013272236347765023, "loss": 0.5591883659362793, "step": 240680 }, { "epoch": 1.4307113433314906, "grad_norm": 1.41043221950531, "learning_rate": 0.00013271634030827568, "loss": 0.5533143997192382, "step": 240690 }, { "epoch": 1.430770785408159, "grad_norm": 1.3942270278930664, "learning_rate": 0.00013271031703023358, "loss": 0.6118309497833252, "step": 240700 }, { "epoch": 1.4308302274848275, "grad_norm": 1.4881539344787598, "learning_rate": 0.00013270429364355273, "loss": 0.562861442565918, "step": 240710 }, { "epoch": 1.4308896695614959, "grad_norm": 1.5179250240325928, "learning_rate": 0.00013269827014826194, "loss": 0.5949784278869629, "step": 240720 }, { "epoch": 1.430949111638164, "grad_norm": 1.6963481903076172, "learning_rate": 0.0001326922465443901, "loss": 0.623990249633789, "step": 240730 }, { "epoch": 1.4310085537148325, "grad_norm": 1.5212700366973877, "learning_rate": 0.0001326862228319659, "loss": 0.6217087745666504, "step": 240740 }, { "epoch": 1.431067995791501, "grad_norm": 1.4873710870742798, "learning_rate": 0.00013268019901101826, "loss": 0.6243405342102051, "step": 240750 }, { "epoch": 1.4311274378681693, "grad_norm": 1.694162368774414, "learning_rate": 0.00013267417508157597, "loss": 0.5552554130554199, "step": 240760 }, { "epoch": 1.4311868799448377, "grad_norm": 1.5664273500442505, "learning_rate": 0.00013266815104366782, "loss": 0.6054561614990235, "step": 240770 }, { "epoch": 1.4312463220215061, "grad_norm": 1.5351669788360596, "learning_rate": 0.00013266212689732264, "loss": 0.6221175193786621, "step": 240780 }, { "epoch": 1.4313057640981746, "grad_norm": 1.6432483196258545, "learning_rate": 0.00013265610264256923, "loss": 0.5607651233673095, "step": 240790 }, { "epoch": 1.431365206174843, "grad_norm": 1.8073222637176514, "learning_rate": 0.00013265007827943648, "loss": 0.5987918853759766, "step": 240800 }, { "epoch": 1.4314246482515114, "grad_norm": 1.5527220964431763, "learning_rate": 0.00013264405380795311, "loss": 0.5347434520721436, "step": 240810 }, { "epoch": 1.4314840903281798, "grad_norm": 1.4163973331451416, "learning_rate": 0.00013263802922814806, "loss": 0.5832441329956055, "step": 240820 }, { "epoch": 1.4315435324048482, "grad_norm": 1.7364863157272339, "learning_rate": 0.00013263200454005, "loss": 0.6275389671325684, "step": 240830 }, { "epoch": 1.4316029744815164, "grad_norm": 1.4728139638900757, "learning_rate": 0.00013262597974368786, "loss": 0.5882724761962891, "step": 240840 }, { "epoch": 1.4316624165581848, "grad_norm": 1.549698829650879, "learning_rate": 0.00013261995483909042, "loss": 0.5996025085449219, "step": 240850 }, { "epoch": 1.4317218586348532, "grad_norm": 1.6670790910720825, "learning_rate": 0.00013261392982628648, "loss": 0.5820703506469727, "step": 240860 }, { "epoch": 1.4317813007115217, "grad_norm": 1.8223704099655151, "learning_rate": 0.00013260790470530492, "loss": 0.5875390052795411, "step": 240870 }, { "epoch": 1.43184074278819, "grad_norm": 1.8809314966201782, "learning_rate": 0.00013260187947617454, "loss": 0.5568357467651367, "step": 240880 }, { "epoch": 1.4319001848648585, "grad_norm": 1.3349425792694092, "learning_rate": 0.00013259585413892414, "loss": 0.5160721778869629, "step": 240890 }, { "epoch": 1.431959626941527, "grad_norm": 1.6166497468948364, "learning_rate": 0.00013258982869358257, "loss": 0.646718168258667, "step": 240900 }, { "epoch": 1.432019069018195, "grad_norm": 1.6493903398513794, "learning_rate": 0.00013258380314017863, "loss": 0.6182150363922119, "step": 240910 }, { "epoch": 1.4320785110948635, "grad_norm": 1.5275757312774658, "learning_rate": 0.0001325777774787412, "loss": 0.5991111755371094, "step": 240920 }, { "epoch": 1.432137953171532, "grad_norm": 1.8536075353622437, "learning_rate": 0.000132571751709299, "loss": 0.6272131443023682, "step": 240930 }, { "epoch": 1.4321973952482003, "grad_norm": 1.7828187942504883, "learning_rate": 0.00013256572583188097, "loss": 0.6242795944213867, "step": 240940 }, { "epoch": 1.4322568373248687, "grad_norm": 1.5827511548995972, "learning_rate": 0.00013255969984651584, "loss": 0.6260345458984375, "step": 240950 }, { "epoch": 1.4323162794015372, "grad_norm": 1.2561635971069336, "learning_rate": 0.00013255367375323248, "loss": 0.5987563133239746, "step": 240960 }, { "epoch": 1.4323757214782056, "grad_norm": 1.5968528985977173, "learning_rate": 0.00013254764755205972, "loss": 0.5785839080810546, "step": 240970 }, { "epoch": 1.432435163554874, "grad_norm": 1.1975642442703247, "learning_rate": 0.0001325416212430264, "loss": 0.6171401023864747, "step": 240980 }, { "epoch": 1.4324946056315424, "grad_norm": 1.3576648235321045, "learning_rate": 0.00013253559482616129, "loss": 0.5654183864593506, "step": 240990 }, { "epoch": 1.4325540477082108, "grad_norm": 1.4816746711730957, "learning_rate": 0.0001325295683014933, "loss": 0.6392199039459229, "step": 241000 }, { "epoch": 1.4326134897848792, "grad_norm": 1.5355496406555176, "learning_rate": 0.0001325235416690512, "loss": 0.5849267482757569, "step": 241010 }, { "epoch": 1.4326729318615476, "grad_norm": 1.7374563217163086, "learning_rate": 0.00013251751492886386, "loss": 0.5710119247436524, "step": 241020 }, { "epoch": 1.4327323739382158, "grad_norm": 1.4898964166641235, "learning_rate": 0.00013251148808096007, "loss": 0.675407886505127, "step": 241030 }, { "epoch": 1.4327918160148843, "grad_norm": 1.3009040355682373, "learning_rate": 0.00013250546112536868, "loss": 0.5562803268432617, "step": 241040 }, { "epoch": 1.4328512580915527, "grad_norm": 1.6404281854629517, "learning_rate": 0.00013249943406211853, "loss": 0.5730307102203369, "step": 241050 }, { "epoch": 1.432910700168221, "grad_norm": 1.284172534942627, "learning_rate": 0.0001324934068912384, "loss": 0.5573905944824219, "step": 241060 }, { "epoch": 1.4329701422448895, "grad_norm": 1.8698869943618774, "learning_rate": 0.00013248737961275722, "loss": 0.5978609561920166, "step": 241070 }, { "epoch": 1.433029584321558, "grad_norm": 1.319841742515564, "learning_rate": 0.00013248135222670372, "loss": 0.5333989143371582, "step": 241080 }, { "epoch": 1.4330890263982263, "grad_norm": 1.5289430618286133, "learning_rate": 0.00013247532473310679, "loss": 0.6345034599304199, "step": 241090 }, { "epoch": 1.4331484684748945, "grad_norm": 1.5582106113433838, "learning_rate": 0.00013246929713199527, "loss": 0.5720090866088867, "step": 241100 }, { "epoch": 1.433207910551563, "grad_norm": 1.555213212966919, "learning_rate": 0.00013246326942339796, "loss": 0.6251867294311524, "step": 241110 }, { "epoch": 1.4332673526282314, "grad_norm": 1.5727893114089966, "learning_rate": 0.00013245724160734367, "loss": 0.6047862052917481, "step": 241120 }, { "epoch": 1.4333267947048998, "grad_norm": 1.1909722089767456, "learning_rate": 0.00013245121368386136, "loss": 0.6267071723937988, "step": 241130 }, { "epoch": 1.4333862367815682, "grad_norm": 1.2521430253982544, "learning_rate": 0.00013244518565297972, "loss": 0.6043845176696777, "step": 241140 }, { "epoch": 1.4334456788582366, "grad_norm": 1.5368348360061646, "learning_rate": 0.00013243915751472767, "loss": 0.624505615234375, "step": 241150 }, { "epoch": 1.433505120934905, "grad_norm": 1.7033771276474, "learning_rate": 0.00013243312926913402, "loss": 0.5794374465942382, "step": 241160 }, { "epoch": 1.4335645630115734, "grad_norm": 1.1748712062835693, "learning_rate": 0.00013242710091622762, "loss": 0.6118213653564453, "step": 241170 }, { "epoch": 1.4336240050882418, "grad_norm": 1.5243128538131714, "learning_rate": 0.00013242107245603726, "loss": 0.6129897117614747, "step": 241180 }, { "epoch": 1.4336834471649103, "grad_norm": 1.6285022497177124, "learning_rate": 0.00013241504388859186, "loss": 0.6484749794006348, "step": 241190 }, { "epoch": 1.4337428892415787, "grad_norm": 1.4445651769638062, "learning_rate": 0.00013240901521392018, "loss": 0.632297420501709, "step": 241200 }, { "epoch": 1.4338023313182469, "grad_norm": 1.2989356517791748, "learning_rate": 0.00013240298643205114, "loss": 0.6084046840667725, "step": 241210 }, { "epoch": 1.4338617733949153, "grad_norm": 1.4510993957519531, "learning_rate": 0.00013239695754301348, "loss": 0.5879280090332031, "step": 241220 }, { "epoch": 1.4339212154715837, "grad_norm": 2.2964136600494385, "learning_rate": 0.00013239092854683615, "loss": 0.6194700241088867, "step": 241230 }, { "epoch": 1.433980657548252, "grad_norm": 1.3891574144363403, "learning_rate": 0.0001323848994435479, "loss": 0.586423110961914, "step": 241240 }, { "epoch": 1.4340400996249205, "grad_norm": 1.2888084650039673, "learning_rate": 0.00013237887023317762, "loss": 0.560045576095581, "step": 241250 }, { "epoch": 1.434099541701589, "grad_norm": 1.6556901931762695, "learning_rate": 0.00013237284091575412, "loss": 0.5483209609985351, "step": 241260 }, { "epoch": 1.4341589837782573, "grad_norm": 1.3646162748336792, "learning_rate": 0.00013236681149130625, "loss": 0.525714111328125, "step": 241270 }, { "epoch": 1.4342184258549255, "grad_norm": 1.5104886293411255, "learning_rate": 0.00013236078195986287, "loss": 0.6226622104644776, "step": 241280 }, { "epoch": 1.434277867931594, "grad_norm": 1.796628475189209, "learning_rate": 0.00013235475232145286, "loss": 0.6360263824462891, "step": 241290 }, { "epoch": 1.4343373100082624, "grad_norm": 1.1873053312301636, "learning_rate": 0.00013234872257610498, "loss": 0.6054395198822021, "step": 241300 }, { "epoch": 1.4343967520849308, "grad_norm": 1.8766893148422241, "learning_rate": 0.00013234269272384815, "loss": 0.629648494720459, "step": 241310 }, { "epoch": 1.4344561941615992, "grad_norm": 1.3525941371917725, "learning_rate": 0.00013233666276471118, "loss": 0.5666790962219238, "step": 241320 }, { "epoch": 1.4345156362382676, "grad_norm": 1.6102155447006226, "learning_rate": 0.00013233063269872287, "loss": 0.6151996612548828, "step": 241330 }, { "epoch": 1.434575078314936, "grad_norm": 1.554761290550232, "learning_rate": 0.00013232460252591213, "loss": 0.6446736335754395, "step": 241340 }, { "epoch": 1.4346345203916044, "grad_norm": 1.3604185581207275, "learning_rate": 0.0001323185722463078, "loss": 0.570036792755127, "step": 241350 }, { "epoch": 1.4346939624682729, "grad_norm": 1.8015223741531372, "learning_rate": 0.0001323125418599387, "loss": 0.6449434280395507, "step": 241360 }, { "epoch": 1.4347534045449413, "grad_norm": 1.5581730604171753, "learning_rate": 0.00013230651136683367, "loss": 0.5597601890563965, "step": 241370 }, { "epoch": 1.4348128466216097, "grad_norm": 1.5819748640060425, "learning_rate": 0.00013230048076702162, "loss": 0.5805065631866455, "step": 241380 }, { "epoch": 1.434872288698278, "grad_norm": 1.2289798259735107, "learning_rate": 0.00013229445006053135, "loss": 0.5831331253051758, "step": 241390 }, { "epoch": 1.4349317307749463, "grad_norm": 1.4957114458084106, "learning_rate": 0.0001322884192473917, "loss": 0.5789855003356934, "step": 241400 }, { "epoch": 1.4349911728516147, "grad_norm": 1.6238995790481567, "learning_rate": 0.00013228238832763156, "loss": 0.6233402252197265, "step": 241410 }, { "epoch": 1.4350506149282831, "grad_norm": 1.5711638927459717, "learning_rate": 0.00013227635730127973, "loss": 0.5865473747253418, "step": 241420 }, { "epoch": 1.4351100570049515, "grad_norm": 1.2250869274139404, "learning_rate": 0.0001322703261683651, "loss": 0.613667106628418, "step": 241430 }, { "epoch": 1.43516949908162, "grad_norm": 1.2950849533081055, "learning_rate": 0.00013226429492891651, "loss": 0.574176549911499, "step": 241440 }, { "epoch": 1.4352289411582884, "grad_norm": 1.1755236387252808, "learning_rate": 0.0001322582635829628, "loss": 0.5598845481872559, "step": 241450 }, { "epoch": 1.4352883832349568, "grad_norm": 1.0301175117492676, "learning_rate": 0.00013225223213053286, "loss": 0.5394400119781494, "step": 241460 }, { "epoch": 1.435347825311625, "grad_norm": 1.4064555168151855, "learning_rate": 0.00013224620057165548, "loss": 0.574842882156372, "step": 241470 }, { "epoch": 1.4354072673882934, "grad_norm": 1.2973825931549072, "learning_rate": 0.00013224016890635954, "loss": 0.6203938007354737, "step": 241480 }, { "epoch": 1.4354667094649618, "grad_norm": 1.5642452239990234, "learning_rate": 0.00013223413713467393, "loss": 0.6127216339111328, "step": 241490 }, { "epoch": 1.4355261515416302, "grad_norm": 1.778774380683899, "learning_rate": 0.00013222810525662747, "loss": 0.6172065734863281, "step": 241500 }, { "epoch": 1.4355855936182986, "grad_norm": 1.5927015542984009, "learning_rate": 0.00013222207327224904, "loss": 0.6472769260406495, "step": 241510 }, { "epoch": 1.435645035694967, "grad_norm": 1.5498474836349487, "learning_rate": 0.00013221604118156743, "loss": 0.6654742240905762, "step": 241520 }, { "epoch": 1.4357044777716355, "grad_norm": 1.4248813390731812, "learning_rate": 0.00013221000898461154, "loss": 0.5725837707519531, "step": 241530 }, { "epoch": 1.4357639198483039, "grad_norm": 1.446001410484314, "learning_rate": 0.00013220397668141023, "loss": 0.5376914024353028, "step": 241540 }, { "epoch": 1.4358233619249723, "grad_norm": 1.4849448204040527, "learning_rate": 0.00013219794427199235, "loss": 0.5921972274780274, "step": 241550 }, { "epoch": 1.4358828040016407, "grad_norm": 1.6722958087921143, "learning_rate": 0.0001321919117563868, "loss": 0.6048279762268066, "step": 241560 }, { "epoch": 1.4359422460783091, "grad_norm": 1.8121352195739746, "learning_rate": 0.00013218587913462238, "loss": 0.554026985168457, "step": 241570 }, { "epoch": 1.4360016881549773, "grad_norm": 1.3978567123413086, "learning_rate": 0.00013217984640672795, "loss": 0.5724038124084473, "step": 241580 }, { "epoch": 1.4360611302316457, "grad_norm": 1.287872314453125, "learning_rate": 0.00013217381357273237, "loss": 0.6292980194091797, "step": 241590 }, { "epoch": 1.4361205723083141, "grad_norm": 1.393090009689331, "learning_rate": 0.00013216778063266453, "loss": 0.603999137878418, "step": 241600 }, { "epoch": 1.4361800143849826, "grad_norm": 1.9036980867385864, "learning_rate": 0.00013216174758655323, "loss": 0.6043255805969239, "step": 241610 }, { "epoch": 1.436239456461651, "grad_norm": 1.5284242630004883, "learning_rate": 0.00013215571443442748, "loss": 0.5467430114746094, "step": 241620 }, { "epoch": 1.4362988985383194, "grad_norm": 1.2726736068725586, "learning_rate": 0.00013214968117631593, "loss": 0.5687638282775879, "step": 241630 }, { "epoch": 1.4363583406149878, "grad_norm": 1.4007596969604492, "learning_rate": 0.00013214364781224757, "loss": 0.5483782291412354, "step": 241640 }, { "epoch": 1.436417782691656, "grad_norm": 1.4065951108932495, "learning_rate": 0.00013213761434225125, "loss": 0.6453685760498047, "step": 241650 }, { "epoch": 1.4364772247683244, "grad_norm": 1.7047028541564941, "learning_rate": 0.00013213158076635578, "loss": 0.6701041221618652, "step": 241660 }, { "epoch": 1.4365366668449928, "grad_norm": 1.5578498840332031, "learning_rate": 0.0001321255470845901, "loss": 0.5943249702453614, "step": 241670 }, { "epoch": 1.4365961089216612, "grad_norm": 1.2629590034484863, "learning_rate": 0.00013211951329698306, "loss": 0.5715814590454101, "step": 241680 }, { "epoch": 1.4366555509983296, "grad_norm": 1.8366302251815796, "learning_rate": 0.00013211347940356345, "loss": 0.589419174194336, "step": 241690 }, { "epoch": 1.436714993074998, "grad_norm": 2.445571184158325, "learning_rate": 0.00013210744540436016, "loss": 0.5718060493469238, "step": 241700 }, { "epoch": 1.4367744351516665, "grad_norm": 2.214938163757324, "learning_rate": 0.00013210141129940214, "loss": 0.5674485206604004, "step": 241710 }, { "epoch": 1.4368338772283349, "grad_norm": 1.320143222808838, "learning_rate": 0.00013209537708871815, "loss": 0.5872204780578614, "step": 241720 }, { "epoch": 1.4368933193050033, "grad_norm": 1.256939172744751, "learning_rate": 0.0001320893427723371, "loss": 0.5469350337982177, "step": 241730 }, { "epoch": 1.4369527613816717, "grad_norm": 1.5981569290161133, "learning_rate": 0.0001320833083502879, "loss": 0.6065223217010498, "step": 241740 }, { "epoch": 1.4370122034583401, "grad_norm": 1.5568938255310059, "learning_rate": 0.0001320772738225993, "loss": 0.623662281036377, "step": 241750 }, { "epoch": 1.4370716455350085, "grad_norm": 1.583600401878357, "learning_rate": 0.00013207123918930027, "loss": 0.5528976440429687, "step": 241760 }, { "epoch": 1.4371310876116767, "grad_norm": 1.1748026609420776, "learning_rate": 0.00013206520445041962, "loss": 0.559163761138916, "step": 241770 }, { "epoch": 1.4371905296883452, "grad_norm": 1.5500072240829468, "learning_rate": 0.0001320591696059863, "loss": 0.5996330261230469, "step": 241780 }, { "epoch": 1.4372499717650136, "grad_norm": 1.2971299886703491, "learning_rate": 0.00013205313465602906, "loss": 0.505466890335083, "step": 241790 }, { "epoch": 1.437309413841682, "grad_norm": 1.2953742742538452, "learning_rate": 0.00013204709960057685, "loss": 0.5674695014953614, "step": 241800 }, { "epoch": 1.4373688559183504, "grad_norm": 1.2209749221801758, "learning_rate": 0.00013204106443965853, "loss": 0.5389753341674804, "step": 241810 }, { "epoch": 1.4374282979950188, "grad_norm": 1.6583118438720703, "learning_rate": 0.00013203502917330298, "loss": 0.5246190547943115, "step": 241820 }, { "epoch": 1.4374877400716872, "grad_norm": 1.4283881187438965, "learning_rate": 0.00013202899380153902, "loss": 0.5994494438171387, "step": 241830 }, { "epoch": 1.4375471821483554, "grad_norm": 1.3081246614456177, "learning_rate": 0.00013202295832439556, "loss": 0.6153960227966309, "step": 241840 }, { "epoch": 1.4376066242250238, "grad_norm": 1.6509137153625488, "learning_rate": 0.00013201692274190146, "loss": 0.6102690696716309, "step": 241850 }, { "epoch": 1.4376660663016922, "grad_norm": 1.4417939186096191, "learning_rate": 0.0001320108870540856, "loss": 0.5616725444793701, "step": 241860 }, { "epoch": 1.4377255083783607, "grad_norm": 1.2690837383270264, "learning_rate": 0.00013200485126097687, "loss": 0.6049846172332763, "step": 241870 }, { "epoch": 1.437784950455029, "grad_norm": 1.1087952852249146, "learning_rate": 0.0001319988153626041, "loss": 0.5156851768493652, "step": 241880 }, { "epoch": 1.4378443925316975, "grad_norm": 1.314164400100708, "learning_rate": 0.00013199277935899617, "loss": 0.5497710227966308, "step": 241890 }, { "epoch": 1.437903834608366, "grad_norm": 1.643670916557312, "learning_rate": 0.00013198674325018203, "loss": 0.5702783584594726, "step": 241900 }, { "epoch": 1.4379632766850343, "grad_norm": 1.53065824508667, "learning_rate": 0.00013198070703619047, "loss": 0.6114170551300049, "step": 241910 }, { "epoch": 1.4380227187617027, "grad_norm": 1.1139661073684692, "learning_rate": 0.00013197467071705035, "loss": 0.5735893249511719, "step": 241920 }, { "epoch": 1.4380821608383711, "grad_norm": 1.441593885421753, "learning_rate": 0.00013196863429279062, "loss": 0.5332661628723144, "step": 241930 }, { "epoch": 1.4381416029150396, "grad_norm": 1.5723861455917358, "learning_rate": 0.00013196259776344013, "loss": 0.6062003135681152, "step": 241940 }, { "epoch": 1.4382010449917078, "grad_norm": 1.5611803531646729, "learning_rate": 0.00013195656112902773, "loss": 0.5745418548583985, "step": 241950 }, { "epoch": 1.4382604870683762, "grad_norm": 2.0421621799468994, "learning_rate": 0.00013195052438958233, "loss": 0.5843104362487793, "step": 241960 }, { "epoch": 1.4383199291450446, "grad_norm": 2.0350747108459473, "learning_rate": 0.0001319444875451328, "loss": 0.5826493740081787, "step": 241970 }, { "epoch": 1.438379371221713, "grad_norm": 1.483405590057373, "learning_rate": 0.000131938450595708, "loss": 0.713803482055664, "step": 241980 }, { "epoch": 1.4384388132983814, "grad_norm": 1.5156428813934326, "learning_rate": 0.00013193241354133683, "loss": 0.651204776763916, "step": 241990 }, { "epoch": 1.4384982553750498, "grad_norm": 1.7251425981521606, "learning_rate": 0.00013192637638204818, "loss": 0.6041922092437744, "step": 242000 }, { "epoch": 1.4385576974517182, "grad_norm": 1.4908735752105713, "learning_rate": 0.00013192033911787088, "loss": 0.580974006652832, "step": 242010 }, { "epoch": 1.4386171395283864, "grad_norm": 1.8509973287582397, "learning_rate": 0.00013191430174883383, "loss": 0.5276907920837403, "step": 242020 }, { "epoch": 1.4386765816050548, "grad_norm": 1.7093628644943237, "learning_rate": 0.00013190826427496598, "loss": 0.5436465263366699, "step": 242030 }, { "epoch": 1.4387360236817233, "grad_norm": 1.3352906703948975, "learning_rate": 0.00013190222669629608, "loss": 0.606495475769043, "step": 242040 }, { "epoch": 1.4387954657583917, "grad_norm": 1.3616641759872437, "learning_rate": 0.0001318961890128531, "loss": 0.6067972183227539, "step": 242050 }, { "epoch": 1.43885490783506, "grad_norm": 1.4138644933700562, "learning_rate": 0.00013189015122466594, "loss": 0.6161848068237304, "step": 242060 }, { "epoch": 1.4389143499117285, "grad_norm": 1.669063925743103, "learning_rate": 0.00013188411333176346, "loss": 0.6009378433227539, "step": 242070 }, { "epoch": 1.438973791988397, "grad_norm": 1.1419786214828491, "learning_rate": 0.00013187807533417449, "loss": 0.5913447380065918, "step": 242080 }, { "epoch": 1.4390332340650653, "grad_norm": 1.2714813947677612, "learning_rate": 0.000131872037231928, "loss": 0.5953571796417236, "step": 242090 }, { "epoch": 1.4390926761417338, "grad_norm": 1.6940443515777588, "learning_rate": 0.0001318659990250528, "loss": 0.5558109760284424, "step": 242100 }, { "epoch": 1.4391521182184022, "grad_norm": 1.3373814821243286, "learning_rate": 0.00013185996071357782, "loss": 0.6080758094787597, "step": 242110 }, { "epoch": 1.4392115602950706, "grad_norm": 1.7396186590194702, "learning_rate": 0.00013185392229753194, "loss": 0.5941054344177246, "step": 242120 }, { "epoch": 1.439271002371739, "grad_norm": 1.5934237241744995, "learning_rate": 0.000131847883776944, "loss": 0.6162291526794433, "step": 242130 }, { "epoch": 1.4393304444484072, "grad_norm": 1.4699387550354004, "learning_rate": 0.00013184184515184296, "loss": 0.5953681945800782, "step": 242140 }, { "epoch": 1.4393898865250756, "grad_norm": 1.5429213047027588, "learning_rate": 0.00013183580642225765, "loss": 0.5786770343780517, "step": 242150 }, { "epoch": 1.439449328601744, "grad_norm": 1.187314510345459, "learning_rate": 0.000131829767588217, "loss": 0.5346307277679443, "step": 242160 }, { "epoch": 1.4395087706784124, "grad_norm": 1.2790806293487549, "learning_rate": 0.00013182372864974987, "loss": 0.6198556900024415, "step": 242170 }, { "epoch": 1.4395682127550808, "grad_norm": 1.314581036567688, "learning_rate": 0.00013181768960688516, "loss": 0.6020000457763672, "step": 242180 }, { "epoch": 1.4396276548317493, "grad_norm": 1.664128065109253, "learning_rate": 0.00013181165045965176, "loss": 0.5658004760742188, "step": 242190 }, { "epoch": 1.4396870969084177, "grad_norm": 1.7468881607055664, "learning_rate": 0.00013180561120807854, "loss": 0.6065462112426758, "step": 242200 }, { "epoch": 1.4397465389850859, "grad_norm": 1.1051052808761597, "learning_rate": 0.00013179957185219438, "loss": 0.6541983127593994, "step": 242210 }, { "epoch": 1.4398059810617543, "grad_norm": 1.5010640621185303, "learning_rate": 0.00013179353239202817, "loss": 0.609825611114502, "step": 242220 }, { "epoch": 1.4398654231384227, "grad_norm": 1.4284268617630005, "learning_rate": 0.0001317874928276089, "loss": 0.5958978652954101, "step": 242230 }, { "epoch": 1.439924865215091, "grad_norm": 1.1792678833007812, "learning_rate": 0.00013178145315896535, "loss": 0.5341747283935547, "step": 242240 }, { "epoch": 1.4399843072917595, "grad_norm": 1.4627093076705933, "learning_rate": 0.00013177541338612643, "loss": 0.6082242012023926, "step": 242250 }, { "epoch": 1.440043749368428, "grad_norm": 1.5843127965927124, "learning_rate": 0.00013176937350912107, "loss": 0.6242026329040528, "step": 242260 }, { "epoch": 1.4401031914450964, "grad_norm": 1.6373100280761719, "learning_rate": 0.00013176333352797815, "loss": 0.5967474460601807, "step": 242270 }, { "epoch": 1.4401626335217648, "grad_norm": 2.0523741245269775, "learning_rate": 0.0001317572934427265, "loss": 0.5659302234649658, "step": 242280 }, { "epoch": 1.4402220755984332, "grad_norm": 1.5343413352966309, "learning_rate": 0.00013175125325339514, "loss": 0.5862833023071289, "step": 242290 }, { "epoch": 1.4402815176751016, "grad_norm": 1.4541841745376587, "learning_rate": 0.00013174521296001286, "loss": 0.6161574363708496, "step": 242300 }, { "epoch": 1.44034095975177, "grad_norm": 1.131874442100525, "learning_rate": 0.0001317391725626086, "loss": 0.5739130020141602, "step": 242310 }, { "epoch": 1.4404004018284382, "grad_norm": 1.2095838785171509, "learning_rate": 0.0001317331320612112, "loss": 0.5992486953735352, "step": 242320 }, { "epoch": 1.4404598439051066, "grad_norm": 2.111276626586914, "learning_rate": 0.00013172709145584964, "loss": 0.5781220436096192, "step": 242330 }, { "epoch": 1.440519285981775, "grad_norm": 1.5756109952926636, "learning_rate": 0.00013172105074655277, "loss": 0.5822525978088379, "step": 242340 }, { "epoch": 1.4405787280584434, "grad_norm": 1.323022723197937, "learning_rate": 0.0001317150099333495, "loss": 0.5692397117614746, "step": 242350 }, { "epoch": 1.4406381701351119, "grad_norm": 1.3741991519927979, "learning_rate": 0.00013170896901626872, "loss": 0.5464524269104004, "step": 242360 }, { "epoch": 1.4406976122117803, "grad_norm": 1.0191773176193237, "learning_rate": 0.00013170292799533927, "loss": 0.6244441986083984, "step": 242370 }, { "epoch": 1.4407570542884487, "grad_norm": 1.621307373046875, "learning_rate": 0.00013169688687059014, "loss": 0.5915528297424316, "step": 242380 }, { "epoch": 1.4408164963651169, "grad_norm": 1.480148196220398, "learning_rate": 0.00013169084564205023, "loss": 0.5970154762268066, "step": 242390 }, { "epoch": 1.4408759384417853, "grad_norm": 1.2275668382644653, "learning_rate": 0.00013168480430974836, "loss": 0.5608251571655274, "step": 242400 }, { "epoch": 1.4409353805184537, "grad_norm": 1.3309937715530396, "learning_rate": 0.00013167876287371348, "loss": 0.5726740837097168, "step": 242410 }, { "epoch": 1.4409948225951221, "grad_norm": 1.581713080406189, "learning_rate": 0.0001316727213339745, "loss": 0.5506088256835937, "step": 242420 }, { "epoch": 1.4410542646717905, "grad_norm": 1.4744722843170166, "learning_rate": 0.0001316666796905603, "loss": 0.623455810546875, "step": 242430 }, { "epoch": 1.441113706748459, "grad_norm": 1.7515591382980347, "learning_rate": 0.00013166063794349978, "loss": 0.5833872795104981, "step": 242440 }, { "epoch": 1.4411731488251274, "grad_norm": 1.2928415536880493, "learning_rate": 0.00013165459609282184, "loss": 0.5949076652526856, "step": 242450 }, { "epoch": 1.4412325909017958, "grad_norm": 1.4210870265960693, "learning_rate": 0.00013164855413855538, "loss": 0.5713641166687011, "step": 242460 }, { "epoch": 1.4412920329784642, "grad_norm": 1.45171058177948, "learning_rate": 0.00013164251208072934, "loss": 0.6042237281799316, "step": 242470 }, { "epoch": 1.4413514750551326, "grad_norm": 1.402547836303711, "learning_rate": 0.0001316364699193726, "loss": 0.613764476776123, "step": 242480 }, { "epoch": 1.441410917131801, "grad_norm": 1.494970679283142, "learning_rate": 0.00013163042765451403, "loss": 0.6052910804748535, "step": 242490 }, { "epoch": 1.4414703592084694, "grad_norm": 1.632684588432312, "learning_rate": 0.00013162438528618257, "loss": 0.5607813835144043, "step": 242500 }, { "epoch": 1.4415298012851376, "grad_norm": 1.5288889408111572, "learning_rate": 0.00013161834281440714, "loss": 0.5637136459350586, "step": 242510 }, { "epoch": 1.441589243361806, "grad_norm": 1.6287121772766113, "learning_rate": 0.0001316123002392166, "loss": 0.6157226085662841, "step": 242520 }, { "epoch": 1.4416486854384745, "grad_norm": 1.352385401725769, "learning_rate": 0.00013160625756063988, "loss": 0.6192981719970703, "step": 242530 }, { "epoch": 1.4417081275151429, "grad_norm": 1.0289623737335205, "learning_rate": 0.0001316002147787059, "loss": 0.5357906818389893, "step": 242540 }, { "epoch": 1.4417675695918113, "grad_norm": 1.0542469024658203, "learning_rate": 0.00013159417189344353, "loss": 0.5868089675903321, "step": 242550 }, { "epoch": 1.4418270116684797, "grad_norm": 1.607190728187561, "learning_rate": 0.0001315881289048817, "loss": 0.5576757907867431, "step": 242560 }, { "epoch": 1.4418864537451481, "grad_norm": 1.711238145828247, "learning_rate": 0.0001315820858130493, "loss": 0.5149722099304199, "step": 242570 }, { "epoch": 1.4419458958218163, "grad_norm": 1.6849976778030396, "learning_rate": 0.00013157604261797529, "loss": 0.625373363494873, "step": 242580 }, { "epoch": 1.4420053378984847, "grad_norm": 1.4879082441329956, "learning_rate": 0.00013156999931968855, "loss": 0.5986051082611084, "step": 242590 }, { "epoch": 1.4420647799751531, "grad_norm": 1.1073729991912842, "learning_rate": 0.00013156395591821797, "loss": 0.5402361392974854, "step": 242600 }, { "epoch": 1.4421242220518216, "grad_norm": 1.2379062175750732, "learning_rate": 0.00013155791241359246, "loss": 0.540875768661499, "step": 242610 }, { "epoch": 1.44218366412849, "grad_norm": 1.7290817499160767, "learning_rate": 0.00013155186880584095, "loss": 0.6964282035827637, "step": 242620 }, { "epoch": 1.4422431062051584, "grad_norm": 1.8409276008605957, "learning_rate": 0.00013154582509499233, "loss": 0.5874221324920654, "step": 242630 }, { "epoch": 1.4423025482818268, "grad_norm": 1.0941190719604492, "learning_rate": 0.00013153978128107555, "loss": 0.6036744117736816, "step": 242640 }, { "epoch": 1.4423619903584952, "grad_norm": 1.5928874015808105, "learning_rate": 0.0001315337373641195, "loss": 0.5988842010498047, "step": 242650 }, { "epoch": 1.4424214324351636, "grad_norm": 1.3683713674545288, "learning_rate": 0.00013152769334415305, "loss": 0.5725069522857666, "step": 242660 }, { "epoch": 1.442480874511832, "grad_norm": 1.4818499088287354, "learning_rate": 0.00013152164922120517, "loss": 0.6078825473785401, "step": 242670 }, { "epoch": 1.4425403165885005, "grad_norm": 1.525354266166687, "learning_rate": 0.00013151560499530477, "loss": 0.5730321884155274, "step": 242680 }, { "epoch": 1.4425997586651687, "grad_norm": 1.6315288543701172, "learning_rate": 0.00013150956066648067, "loss": 0.5742672920227051, "step": 242690 }, { "epoch": 1.442659200741837, "grad_norm": 1.0085777044296265, "learning_rate": 0.00013150351623476196, "loss": 0.5257111072540284, "step": 242700 }, { "epoch": 1.4427186428185055, "grad_norm": 1.40255868434906, "learning_rate": 0.00013149747170017743, "loss": 0.609987735748291, "step": 242710 }, { "epoch": 1.442778084895174, "grad_norm": 1.7128493785858154, "learning_rate": 0.000131491427062756, "loss": 0.6390815734863281, "step": 242720 }, { "epoch": 1.4428375269718423, "grad_norm": 1.0041929483413696, "learning_rate": 0.00013148538232252662, "loss": 0.5853558540344238, "step": 242730 }, { "epoch": 1.4428969690485107, "grad_norm": 1.5131011009216309, "learning_rate": 0.00013147933747951817, "loss": 0.6304477691650391, "step": 242740 }, { "epoch": 1.4429564111251791, "grad_norm": 1.1257272958755493, "learning_rate": 0.00013147329253375962, "loss": 0.595334529876709, "step": 242750 }, { "epoch": 1.4430158532018473, "grad_norm": 1.4020224809646606, "learning_rate": 0.00013146724748527982, "loss": 0.5658610343933106, "step": 242760 }, { "epoch": 1.4430752952785157, "grad_norm": 1.6437193155288696, "learning_rate": 0.00013146120233410778, "loss": 0.6143654346466064, "step": 242770 }, { "epoch": 1.4431347373551842, "grad_norm": 1.520926833152771, "learning_rate": 0.00013145515708027229, "loss": 0.5696295738220215, "step": 242780 }, { "epoch": 1.4431941794318526, "grad_norm": 1.3652684688568115, "learning_rate": 0.00013144911172380242, "loss": 0.5584877014160157, "step": 242790 }, { "epoch": 1.443253621508521, "grad_norm": 1.5464448928833008, "learning_rate": 0.00013144306626472696, "loss": 0.6176937103271485, "step": 242800 }, { "epoch": 1.4433130635851894, "grad_norm": 1.4075367450714111, "learning_rate": 0.00013143702070307487, "loss": 0.587893295288086, "step": 242810 }, { "epoch": 1.4433725056618578, "grad_norm": 2.459430456161499, "learning_rate": 0.00013143097503887509, "loss": 0.5743914127349854, "step": 242820 }, { "epoch": 1.4434319477385262, "grad_norm": 1.215732216835022, "learning_rate": 0.00013142492927215653, "loss": 0.5742178916931152, "step": 242830 }, { "epoch": 1.4434913898151946, "grad_norm": 1.6306246519088745, "learning_rate": 0.0001314188834029481, "loss": 0.5915095329284668, "step": 242840 }, { "epoch": 1.443550831891863, "grad_norm": 1.1787892580032349, "learning_rate": 0.0001314128374312788, "loss": 0.5772031307220459, "step": 242850 }, { "epoch": 1.4436102739685315, "grad_norm": 1.648279070854187, "learning_rate": 0.0001314067913571774, "loss": 0.6029728889465332, "step": 242860 }, { "epoch": 1.4436697160452, "grad_norm": 1.438002347946167, "learning_rate": 0.00013140074518067291, "loss": 0.5628138542175293, "step": 242870 }, { "epoch": 1.443729158121868, "grad_norm": 1.3642627000808716, "learning_rate": 0.00013139469890179433, "loss": 0.5970914840698243, "step": 242880 }, { "epoch": 1.4437886001985365, "grad_norm": 1.7435100078582764, "learning_rate": 0.00013138865252057042, "loss": 0.6225417613983154, "step": 242890 }, { "epoch": 1.443848042275205, "grad_norm": 1.7024742364883423, "learning_rate": 0.0001313826060370302, "loss": 0.584106159210205, "step": 242900 }, { "epoch": 1.4439074843518733, "grad_norm": 1.4465185403823853, "learning_rate": 0.0001313765594512026, "loss": 0.5884357452392578, "step": 242910 }, { "epoch": 1.4439669264285417, "grad_norm": 1.4839612245559692, "learning_rate": 0.00013137051276311648, "loss": 0.5822043418884277, "step": 242920 }, { "epoch": 1.4440263685052102, "grad_norm": 1.3704090118408203, "learning_rate": 0.00013136446597280087, "loss": 0.620408296585083, "step": 242930 }, { "epoch": 1.4440858105818786, "grad_norm": 1.4504318237304688, "learning_rate": 0.00013135841908028465, "loss": 0.617182731628418, "step": 242940 }, { "epoch": 1.4441452526585468, "grad_norm": 1.3388406038284302, "learning_rate": 0.00013135237208559668, "loss": 0.5406285285949707, "step": 242950 }, { "epoch": 1.4442046947352152, "grad_norm": 1.755983591079712, "learning_rate": 0.00013134632498876595, "loss": 0.5326642513275146, "step": 242960 }, { "epoch": 1.4442641368118836, "grad_norm": 1.3647983074188232, "learning_rate": 0.0001313402777898214, "loss": 0.5721044063568115, "step": 242970 }, { "epoch": 1.444323578888552, "grad_norm": 1.8962435722351074, "learning_rate": 0.0001313342304887919, "loss": 0.5599679470062255, "step": 242980 }, { "epoch": 1.4443830209652204, "grad_norm": 1.8304529190063477, "learning_rate": 0.00013132818308570645, "loss": 0.6070981502532959, "step": 242990 }, { "epoch": 1.4444424630418888, "grad_norm": 1.345401644706726, "learning_rate": 0.0001313221355805939, "loss": 0.5724678039550781, "step": 243000 }, { "epoch": 1.4445019051185573, "grad_norm": 1.455000400543213, "learning_rate": 0.00013131608797348326, "loss": 0.5576777458190918, "step": 243010 }, { "epoch": 1.4445613471952257, "grad_norm": 1.9961175918579102, "learning_rate": 0.0001313100402644034, "loss": 0.5925133705139161, "step": 243020 }, { "epoch": 1.444620789271894, "grad_norm": 1.438109278678894, "learning_rate": 0.0001313039924533833, "loss": 0.5871423721313477, "step": 243030 }, { "epoch": 1.4446802313485625, "grad_norm": 1.5235604047775269, "learning_rate": 0.00013129794454045185, "loss": 0.5733156204223633, "step": 243040 }, { "epoch": 1.444739673425231, "grad_norm": 1.3897299766540527, "learning_rate": 0.00013129189652563795, "loss": 0.593783950805664, "step": 243050 }, { "epoch": 1.444799115501899, "grad_norm": 1.4057263135910034, "learning_rate": 0.00013128584840897066, "loss": 0.6083685874938964, "step": 243060 }, { "epoch": 1.4448585575785675, "grad_norm": 1.2581321001052856, "learning_rate": 0.00013127980019047875, "loss": 0.5642011642456055, "step": 243070 }, { "epoch": 1.444917999655236, "grad_norm": 1.8852213621139526, "learning_rate": 0.00013127375187019127, "loss": 0.6140659332275391, "step": 243080 }, { "epoch": 1.4449774417319043, "grad_norm": 1.3771024942398071, "learning_rate": 0.0001312677034481371, "loss": 0.5957327842712402, "step": 243090 }, { "epoch": 1.4450368838085728, "grad_norm": 1.3761427402496338, "learning_rate": 0.0001312616549243452, "loss": 0.5666604042053223, "step": 243100 }, { "epoch": 1.4450963258852412, "grad_norm": 1.4979151487350464, "learning_rate": 0.0001312556062988445, "loss": 0.5622290134429931, "step": 243110 }, { "epoch": 1.4451557679619096, "grad_norm": 1.677614688873291, "learning_rate": 0.0001312495575716639, "loss": 0.5907149314880371, "step": 243120 }, { "epoch": 1.4452152100385778, "grad_norm": 1.6803690195083618, "learning_rate": 0.00013124350874283236, "loss": 0.6217610359191894, "step": 243130 }, { "epoch": 1.4452746521152462, "grad_norm": 1.3099268674850464, "learning_rate": 0.00013123745981237882, "loss": 0.5486348152160645, "step": 243140 }, { "epoch": 1.4453340941919146, "grad_norm": 1.5259344577789307, "learning_rate": 0.0001312314107803322, "loss": 0.5548598766326904, "step": 243150 }, { "epoch": 1.445393536268583, "grad_norm": 1.5388158559799194, "learning_rate": 0.0001312253616467215, "loss": 0.6124113082885743, "step": 243160 }, { "epoch": 1.4454529783452514, "grad_norm": 1.5366277694702148, "learning_rate": 0.00013121931241157555, "loss": 0.5801359653472901, "step": 243170 }, { "epoch": 1.4455124204219199, "grad_norm": 2.136301279067993, "learning_rate": 0.00013121326307492337, "loss": 0.5984514713287353, "step": 243180 }, { "epoch": 1.4455718624985883, "grad_norm": 1.5372737646102905, "learning_rate": 0.0001312072136367939, "loss": 0.5299246788024903, "step": 243190 }, { "epoch": 1.4456313045752567, "grad_norm": 1.3071677684783936, "learning_rate": 0.00013120116409721602, "loss": 0.6036216735839843, "step": 243200 }, { "epoch": 1.445690746651925, "grad_norm": 1.5017344951629639, "learning_rate": 0.0001311951144562187, "loss": 0.5469165802001953, "step": 243210 }, { "epoch": 1.4457501887285935, "grad_norm": 1.5467183589935303, "learning_rate": 0.00013118906471383085, "loss": 0.585844612121582, "step": 243220 }, { "epoch": 1.445809630805262, "grad_norm": 1.8965266942977905, "learning_rate": 0.00013118301487008148, "loss": 0.5700743675231934, "step": 243230 }, { "epoch": 1.4458690728819303, "grad_norm": 1.7673684358596802, "learning_rate": 0.00013117696492499946, "loss": 0.6091680526733398, "step": 243240 }, { "epoch": 1.4459285149585985, "grad_norm": 1.4676358699798584, "learning_rate": 0.0001311709148786138, "loss": 0.6262708187103272, "step": 243250 }, { "epoch": 1.445987957035267, "grad_norm": 1.68106210231781, "learning_rate": 0.00013116486473095337, "loss": 0.6512832641601562, "step": 243260 }, { "epoch": 1.4460473991119354, "grad_norm": 1.3459994792938232, "learning_rate": 0.00013115881448204713, "loss": 0.619212532043457, "step": 243270 }, { "epoch": 1.4461068411886038, "grad_norm": 1.4668257236480713, "learning_rate": 0.00013115276413192407, "loss": 0.6232767105102539, "step": 243280 }, { "epoch": 1.4461662832652722, "grad_norm": 2.0321831703186035, "learning_rate": 0.0001311467136806131, "loss": 0.6179841041564942, "step": 243290 }, { "epoch": 1.4462257253419406, "grad_norm": 2.025810480117798, "learning_rate": 0.00013114066312814316, "loss": 0.5779451370239258, "step": 243300 }, { "epoch": 1.446285167418609, "grad_norm": 1.4920202493667603, "learning_rate": 0.0001311346124745432, "loss": 0.5792798042297364, "step": 243310 }, { "epoch": 1.4463446094952772, "grad_norm": 1.3151167631149292, "learning_rate": 0.00013112856171984213, "loss": 0.5269284248352051, "step": 243320 }, { "epoch": 1.4464040515719456, "grad_norm": 1.95182466506958, "learning_rate": 0.00013112251086406894, "loss": 0.6209357261657715, "step": 243330 }, { "epoch": 1.446463493648614, "grad_norm": 1.422183632850647, "learning_rate": 0.00013111645990725258, "loss": 0.6356127738952637, "step": 243340 }, { "epoch": 1.4465229357252825, "grad_norm": 1.5025454759597778, "learning_rate": 0.00013111040884942197, "loss": 0.6046092987060547, "step": 243350 }, { "epoch": 1.4465823778019509, "grad_norm": 1.1999770402908325, "learning_rate": 0.00013110435769060603, "loss": 0.5136813163757324, "step": 243360 }, { "epoch": 1.4466418198786193, "grad_norm": 1.7833666801452637, "learning_rate": 0.0001310983064308338, "loss": 0.5471668243408203, "step": 243370 }, { "epoch": 1.4467012619552877, "grad_norm": 1.2103208303451538, "learning_rate": 0.00013109225507013412, "loss": 0.6061516761779785, "step": 243380 }, { "epoch": 1.4467607040319561, "grad_norm": 1.7204080820083618, "learning_rate": 0.000131086203608536, "loss": 0.5320467948913574, "step": 243390 }, { "epoch": 1.4468201461086245, "grad_norm": 1.3159774541854858, "learning_rate": 0.00013108015204606836, "loss": 0.5446854591369629, "step": 243400 }, { "epoch": 1.446879588185293, "grad_norm": 1.6226152181625366, "learning_rate": 0.00013107410038276017, "loss": 0.5581559658050537, "step": 243410 }, { "epoch": 1.4469390302619614, "grad_norm": 1.0922802686691284, "learning_rate": 0.00013106804861864036, "loss": 0.5553829193115234, "step": 243420 }, { "epoch": 1.4469984723386295, "grad_norm": 1.3784223794937134, "learning_rate": 0.0001310619967537379, "loss": 0.6298253059387207, "step": 243430 }, { "epoch": 1.447057914415298, "grad_norm": 1.4976085424423218, "learning_rate": 0.00013105594478808174, "loss": 0.5755244255065918, "step": 243440 }, { "epoch": 1.4471173564919664, "grad_norm": 1.4035372734069824, "learning_rate": 0.00013104989272170084, "loss": 0.5381583213806153, "step": 243450 }, { "epoch": 1.4471767985686348, "grad_norm": 1.8078826665878296, "learning_rate": 0.0001310438405546241, "loss": 0.6178505897521973, "step": 243460 }, { "epoch": 1.4472362406453032, "grad_norm": 1.1216275691986084, "learning_rate": 0.0001310377882868805, "loss": 0.5777583599090577, "step": 243470 }, { "epoch": 1.4472956827219716, "grad_norm": 1.7053674459457397, "learning_rate": 0.00013103173591849903, "loss": 0.5800145149230957, "step": 243480 }, { "epoch": 1.44735512479864, "grad_norm": 1.2010958194732666, "learning_rate": 0.00013102568344950858, "loss": 0.5808122158050537, "step": 243490 }, { "epoch": 1.4474145668753082, "grad_norm": 1.4455183744430542, "learning_rate": 0.00013101963087993815, "loss": 0.6231228828430175, "step": 243500 }, { "epoch": 1.4474740089519766, "grad_norm": 1.3022714853286743, "learning_rate": 0.00013101357820981664, "loss": 0.6093254566192627, "step": 243510 }, { "epoch": 1.447533451028645, "grad_norm": 1.9682615995407104, "learning_rate": 0.00013100752543917306, "loss": 0.6048633098602295, "step": 243520 }, { "epoch": 1.4475928931053135, "grad_norm": 1.4030861854553223, "learning_rate": 0.00013100147256803635, "loss": 0.6145418167114258, "step": 243530 }, { "epoch": 1.4476523351819819, "grad_norm": 1.451064944267273, "learning_rate": 0.00013099541959643547, "loss": 0.5370256423950195, "step": 243540 }, { "epoch": 1.4477117772586503, "grad_norm": 1.8395509719848633, "learning_rate": 0.00013098936652439932, "loss": 0.6146252155303955, "step": 243550 }, { "epoch": 1.4477712193353187, "grad_norm": 1.461597204208374, "learning_rate": 0.00013098331335195695, "loss": 0.547518539428711, "step": 243560 }, { "epoch": 1.4478306614119871, "grad_norm": 1.6544535160064697, "learning_rate": 0.00013097726007913724, "loss": 0.607112455368042, "step": 243570 }, { "epoch": 1.4478901034886555, "grad_norm": 1.4586482048034668, "learning_rate": 0.00013097120670596917, "loss": 0.5653380393981934, "step": 243580 }, { "epoch": 1.447949545565324, "grad_norm": 1.4352190494537354, "learning_rate": 0.00013096515323248172, "loss": 0.5494822025299072, "step": 243590 }, { "epoch": 1.4480089876419924, "grad_norm": 1.2823467254638672, "learning_rate": 0.0001309590996587038, "loss": 0.6325813293457031, "step": 243600 }, { "epoch": 1.4480684297186608, "grad_norm": 1.2973910570144653, "learning_rate": 0.00013095304598466443, "loss": 0.6180813789367676, "step": 243610 }, { "epoch": 1.448127871795329, "grad_norm": 1.7624093294143677, "learning_rate": 0.00013094699221039252, "loss": 0.5932567119598389, "step": 243620 }, { "epoch": 1.4481873138719974, "grad_norm": 1.7577245235443115, "learning_rate": 0.00013094093833591704, "loss": 0.6088051795959473, "step": 243630 }, { "epoch": 1.4482467559486658, "grad_norm": 2.0998971462249756, "learning_rate": 0.00013093488436126692, "loss": 0.6629765510559082, "step": 243640 }, { "epoch": 1.4483061980253342, "grad_norm": 1.5840481519699097, "learning_rate": 0.00013092883028647124, "loss": 0.6444340705871582, "step": 243650 }, { "epoch": 1.4483656401020026, "grad_norm": 1.4663437604904175, "learning_rate": 0.00013092277611155881, "loss": 0.6081727027893067, "step": 243660 }, { "epoch": 1.448425082178671, "grad_norm": 1.1587867736816406, "learning_rate": 0.00013091672183655867, "loss": 0.5700389862060546, "step": 243670 }, { "epoch": 1.4484845242553395, "grad_norm": 1.6560343503952026, "learning_rate": 0.00013091066746149979, "loss": 0.5739528656005859, "step": 243680 }, { "epoch": 1.4485439663320077, "grad_norm": 1.6540354490280151, "learning_rate": 0.0001309046129864111, "loss": 0.5812879085540772, "step": 243690 }, { "epoch": 1.448603408408676, "grad_norm": 1.528275728225708, "learning_rate": 0.00013089855841132158, "loss": 0.5858454704284668, "step": 243700 }, { "epoch": 1.4486628504853445, "grad_norm": 1.1143293380737305, "learning_rate": 0.00013089250373626016, "loss": 0.5671091556549073, "step": 243710 }, { "epoch": 1.448722292562013, "grad_norm": 1.5294517278671265, "learning_rate": 0.00013088644896125585, "loss": 0.555058765411377, "step": 243720 }, { "epoch": 1.4487817346386813, "grad_norm": 1.432563066482544, "learning_rate": 0.00013088039408633759, "loss": 0.6085195064544677, "step": 243730 }, { "epoch": 1.4488411767153497, "grad_norm": 1.4111156463623047, "learning_rate": 0.00013087433911153433, "loss": 0.6194765090942382, "step": 243740 }, { "epoch": 1.4489006187920181, "grad_norm": 1.4838135242462158, "learning_rate": 0.00013086828403687504, "loss": 0.6034346580505371, "step": 243750 }, { "epoch": 1.4489600608686866, "grad_norm": 1.8319566249847412, "learning_rate": 0.00013086222886238877, "loss": 0.5897146224975586, "step": 243760 }, { "epoch": 1.449019502945355, "grad_norm": 1.598154902458191, "learning_rate": 0.00013085617358810436, "loss": 0.5932082176208496, "step": 243770 }, { "epoch": 1.4490789450220234, "grad_norm": 1.5781567096710205, "learning_rate": 0.00013085011821405086, "loss": 0.5793057441711426, "step": 243780 }, { "epoch": 1.4491383870986918, "grad_norm": 1.552315592765808, "learning_rate": 0.00013084406274025719, "loss": 0.5497196674346924, "step": 243790 }, { "epoch": 1.44919782917536, "grad_norm": 1.428087592124939, "learning_rate": 0.00013083800716675234, "loss": 0.5884373664855957, "step": 243800 }, { "epoch": 1.4492572712520284, "grad_norm": 1.4559625387191772, "learning_rate": 0.0001308319514935653, "loss": 0.6107859134674072, "step": 243810 }, { "epoch": 1.4493167133286968, "grad_norm": 1.3679364919662476, "learning_rate": 0.00013082589572072494, "loss": 0.5980435371398926, "step": 243820 }, { "epoch": 1.4493761554053652, "grad_norm": 2.161674976348877, "learning_rate": 0.00013081983984826036, "loss": 0.5855323791503906, "step": 243830 }, { "epoch": 1.4494355974820337, "grad_norm": 1.7557079792022705, "learning_rate": 0.00013081378387620044, "loss": 0.5906728267669678, "step": 243840 }, { "epoch": 1.449495039558702, "grad_norm": 1.6514699459075928, "learning_rate": 0.00013080772780457419, "loss": 0.6434428691864014, "step": 243850 }, { "epoch": 1.4495544816353705, "grad_norm": 1.161545991897583, "learning_rate": 0.00013080167163341059, "loss": 0.5637324333190918, "step": 243860 }, { "epoch": 1.4496139237120387, "grad_norm": 2.243983745574951, "learning_rate": 0.00013079561536273859, "loss": 0.5849216461181641, "step": 243870 }, { "epoch": 1.449673365788707, "grad_norm": 1.4530143737792969, "learning_rate": 0.00013078955899258713, "loss": 0.5722095012664795, "step": 243880 }, { "epoch": 1.4497328078653755, "grad_norm": 1.5625150203704834, "learning_rate": 0.00013078350252298523, "loss": 0.7027600765228271, "step": 243890 }, { "epoch": 1.449792249942044, "grad_norm": 1.7711869478225708, "learning_rate": 0.00013077744595396185, "loss": 0.5884584426879883, "step": 243900 }, { "epoch": 1.4498516920187123, "grad_norm": 1.8149734735488892, "learning_rate": 0.000130771389285546, "loss": 0.6116737365722656, "step": 243910 }, { "epoch": 1.4499111340953807, "grad_norm": 1.442739725112915, "learning_rate": 0.00013076533251776652, "loss": 0.6021136283874512, "step": 243920 }, { "epoch": 1.4499705761720492, "grad_norm": 1.6977895498275757, "learning_rate": 0.00013075927565065254, "loss": 0.5925562381744385, "step": 243930 }, { "epoch": 1.4500300182487176, "grad_norm": 1.6425905227661133, "learning_rate": 0.00013075321868423297, "loss": 0.6091198444366455, "step": 243940 }, { "epoch": 1.450089460325386, "grad_norm": 1.272760272026062, "learning_rate": 0.00013074716161853676, "loss": 0.6378824234008789, "step": 243950 }, { "epoch": 1.4501489024020544, "grad_norm": 1.152147650718689, "learning_rate": 0.00013074110445359294, "loss": 0.5603384017944336, "step": 243960 }, { "epoch": 1.4502083444787228, "grad_norm": 1.6442241668701172, "learning_rate": 0.0001307350471894304, "loss": 0.5809295177459717, "step": 243970 }, { "epoch": 1.4502677865553912, "grad_norm": 1.8596950769424438, "learning_rate": 0.0001307289898260782, "loss": 0.6174822330474854, "step": 243980 }, { "epoch": 1.4503272286320594, "grad_norm": 1.7487298250198364, "learning_rate": 0.00013072293236356531, "loss": 0.6342560768127441, "step": 243990 }, { "epoch": 1.4503866707087278, "grad_norm": 1.61940598487854, "learning_rate": 0.00013071687480192064, "loss": 0.6471817016601562, "step": 244000 }, { "epoch": 1.4504461127853963, "grad_norm": 1.5310161113739014, "learning_rate": 0.00013071081714117325, "loss": 0.5592391967773438, "step": 244010 }, { "epoch": 1.4505055548620647, "grad_norm": 1.5602316856384277, "learning_rate": 0.00013070475938135206, "loss": 0.6026258945465088, "step": 244020 }, { "epoch": 1.450564996938733, "grad_norm": 1.4570773839950562, "learning_rate": 0.00013069870152248607, "loss": 0.5750547885894776, "step": 244030 }, { "epoch": 1.4506244390154015, "grad_norm": 1.3850789070129395, "learning_rate": 0.0001306926435646043, "loss": 0.5603070735931397, "step": 244040 }, { "epoch": 1.45068388109207, "grad_norm": 1.17732572555542, "learning_rate": 0.0001306865855077356, "loss": 0.6050881385803223, "step": 244050 }, { "epoch": 1.450743323168738, "grad_norm": 1.7753489017486572, "learning_rate": 0.0001306805273519091, "loss": 0.5252474308013916, "step": 244060 }, { "epoch": 1.4508027652454065, "grad_norm": 1.346875786781311, "learning_rate": 0.00013067446909715368, "loss": 0.6386696338653565, "step": 244070 }, { "epoch": 1.450862207322075, "grad_norm": 1.5877609252929688, "learning_rate": 0.0001306684107434984, "loss": 0.5250576972961426, "step": 244080 }, { "epoch": 1.4509216493987434, "grad_norm": 1.4911656379699707, "learning_rate": 0.00013066235229097214, "loss": 0.584016227722168, "step": 244090 }, { "epoch": 1.4509810914754118, "grad_norm": 1.4353545904159546, "learning_rate": 0.00013065629373960397, "loss": 0.5302906036376953, "step": 244100 }, { "epoch": 1.4510405335520802, "grad_norm": 1.7279961109161377, "learning_rate": 0.00013065023508942284, "loss": 0.5410519599914551, "step": 244110 }, { "epoch": 1.4510999756287486, "grad_norm": 1.6971123218536377, "learning_rate": 0.00013064417634045777, "loss": 0.5585729598999023, "step": 244120 }, { "epoch": 1.451159417705417, "grad_norm": 1.0352027416229248, "learning_rate": 0.00013063811749273763, "loss": 0.5616333484649658, "step": 244130 }, { "epoch": 1.4512188597820854, "grad_norm": 1.550993800163269, "learning_rate": 0.00013063205854629153, "loss": 0.562070894241333, "step": 244140 }, { "epoch": 1.4512783018587538, "grad_norm": 1.5204671621322632, "learning_rate": 0.0001306259995011484, "loss": 0.5272728443145752, "step": 244150 }, { "epoch": 1.4513377439354223, "grad_norm": 1.451851487159729, "learning_rate": 0.0001306199403573372, "loss": 0.6130280494689941, "step": 244160 }, { "epoch": 1.4513971860120904, "grad_norm": 1.3689403533935547, "learning_rate": 0.000130613881114887, "loss": 0.5632946014404296, "step": 244170 }, { "epoch": 1.4514566280887589, "grad_norm": 1.374672770500183, "learning_rate": 0.0001306078217738267, "loss": 0.5964803695678711, "step": 244180 }, { "epoch": 1.4515160701654273, "grad_norm": 1.1637762784957886, "learning_rate": 0.00013060176233418527, "loss": 0.5713181495666504, "step": 244190 }, { "epoch": 1.4515755122420957, "grad_norm": 1.2009592056274414, "learning_rate": 0.00013059570279599182, "loss": 0.5399538993835449, "step": 244200 }, { "epoch": 1.451634954318764, "grad_norm": 1.3523443937301636, "learning_rate": 0.00013058964315927523, "loss": 0.5707064151763916, "step": 244210 }, { "epoch": 1.4516943963954325, "grad_norm": 1.4431174993515015, "learning_rate": 0.0001305835834240645, "loss": 0.6154994010925293, "step": 244220 }, { "epoch": 1.451753838472101, "grad_norm": 1.5776797533035278, "learning_rate": 0.00013057752359038865, "loss": 0.6001702308654785, "step": 244230 }, { "epoch": 1.4518132805487691, "grad_norm": 1.3256490230560303, "learning_rate": 0.00013057146365827666, "loss": 0.5809346199035644, "step": 244240 }, { "epoch": 1.4518727226254375, "grad_norm": 1.4170416593551636, "learning_rate": 0.00013056540362775746, "loss": 0.6525799751281738, "step": 244250 }, { "epoch": 1.451932164702106, "grad_norm": 1.7445021867752075, "learning_rate": 0.00013055934349886014, "loss": 0.5436062812805176, "step": 244260 }, { "epoch": 1.4519916067787744, "grad_norm": 1.5024436712265015, "learning_rate": 0.00013055328327161363, "loss": 0.5918038368225098, "step": 244270 }, { "epoch": 1.4520510488554428, "grad_norm": 1.794076919555664, "learning_rate": 0.00013054722294604691, "loss": 0.5802886486053467, "step": 244280 }, { "epoch": 1.4521104909321112, "grad_norm": 1.68169105052948, "learning_rate": 0.000130541162522189, "loss": 0.5877796173095703, "step": 244290 }, { "epoch": 1.4521699330087796, "grad_norm": 1.9681532382965088, "learning_rate": 0.00013053510200006888, "loss": 0.6531463146209717, "step": 244300 }, { "epoch": 1.452229375085448, "grad_norm": 1.6526744365692139, "learning_rate": 0.00013052904137971557, "loss": 0.5974247455596924, "step": 244310 }, { "epoch": 1.4522888171621164, "grad_norm": 1.353473424911499, "learning_rate": 0.00013052298066115801, "loss": 0.5865877151489258, "step": 244320 }, { "epoch": 1.4523482592387849, "grad_norm": 1.326605200767517, "learning_rate": 0.00013051691984442522, "loss": 0.568919038772583, "step": 244330 }, { "epoch": 1.4524077013154533, "grad_norm": 1.250534176826477, "learning_rate": 0.00013051085892954616, "loss": 0.6223862171173096, "step": 244340 }, { "epoch": 1.4524671433921217, "grad_norm": 1.5175731182098389, "learning_rate": 0.0001305047979165499, "loss": 0.5776402950286865, "step": 244350 }, { "epoch": 1.4525265854687899, "grad_norm": 1.504561424255371, "learning_rate": 0.0001304987368054654, "loss": 0.5476491451263428, "step": 244360 }, { "epoch": 1.4525860275454583, "grad_norm": 1.4760297536849976, "learning_rate": 0.0001304926755963216, "loss": 0.5738735675811768, "step": 244370 }, { "epoch": 1.4526454696221267, "grad_norm": 1.285112977027893, "learning_rate": 0.00013048661428914754, "loss": 0.5383667945861816, "step": 244380 }, { "epoch": 1.4527049116987951, "grad_norm": 1.4825403690338135, "learning_rate": 0.00013048055288397226, "loss": 0.5663609504699707, "step": 244390 }, { "epoch": 1.4527643537754635, "grad_norm": 1.7164589166641235, "learning_rate": 0.00013047449138082467, "loss": 0.5995260715484619, "step": 244400 }, { "epoch": 1.452823795852132, "grad_norm": 1.392678141593933, "learning_rate": 0.00013046842977973379, "loss": 0.6165767669677734, "step": 244410 }, { "epoch": 1.4528832379288001, "grad_norm": 1.3846560716629028, "learning_rate": 0.00013046236808072868, "loss": 0.5466744422912597, "step": 244420 }, { "epoch": 1.4529426800054686, "grad_norm": 1.345335841178894, "learning_rate": 0.00013045630628383823, "loss": 0.5359416961669922, "step": 244430 }, { "epoch": 1.453002122082137, "grad_norm": 1.4378756284713745, "learning_rate": 0.0001304502443890915, "loss": 0.5294389724731445, "step": 244440 }, { "epoch": 1.4530615641588054, "grad_norm": 1.5751467943191528, "learning_rate": 0.00013044418239651755, "loss": 0.5884160041809082, "step": 244450 }, { "epoch": 1.4531210062354738, "grad_norm": 1.7603659629821777, "learning_rate": 0.00013043812030614525, "loss": 0.5945249557495117, "step": 244460 }, { "epoch": 1.4531804483121422, "grad_norm": 1.3941274881362915, "learning_rate": 0.00013043205811800367, "loss": 0.6047866821289063, "step": 244470 }, { "epoch": 1.4532398903888106, "grad_norm": 1.6247690916061401, "learning_rate": 0.00013042599583212185, "loss": 0.5738956928253174, "step": 244480 }, { "epoch": 1.453299332465479, "grad_norm": 1.3454065322875977, "learning_rate": 0.00013041993344852868, "loss": 0.5949253082275391, "step": 244490 }, { "epoch": 1.4533587745421475, "grad_norm": 1.5030525922775269, "learning_rate": 0.00013041387096725325, "loss": 0.6137642383575439, "step": 244500 }, { "epoch": 1.4534182166188159, "grad_norm": 1.3507801294326782, "learning_rate": 0.00013040780838832454, "loss": 0.6353384494781494, "step": 244510 }, { "epoch": 1.4534776586954843, "grad_norm": 1.2604790925979614, "learning_rate": 0.0001304017457117715, "loss": 0.5683024406433106, "step": 244520 }, { "epoch": 1.4535371007721527, "grad_norm": 1.392372727394104, "learning_rate": 0.00013039568293762323, "loss": 0.5761024951934814, "step": 244530 }, { "epoch": 1.453596542848821, "grad_norm": 1.4957703351974487, "learning_rate": 0.00013038962006590868, "loss": 0.5885488033294678, "step": 244540 }, { "epoch": 1.4536559849254893, "grad_norm": 1.5430690050125122, "learning_rate": 0.0001303835570966568, "loss": 0.6201559543609619, "step": 244550 }, { "epoch": 1.4537154270021577, "grad_norm": 1.3448107242584229, "learning_rate": 0.00013037749402989668, "loss": 0.5960905075073242, "step": 244560 }, { "epoch": 1.4537748690788261, "grad_norm": 1.7873510122299194, "learning_rate": 0.00013037143086565728, "loss": 0.5745266437530517, "step": 244570 }, { "epoch": 1.4538343111554946, "grad_norm": 1.2293628454208374, "learning_rate": 0.0001303653676039676, "loss": 0.601577615737915, "step": 244580 }, { "epoch": 1.453893753232163, "grad_norm": 1.4240785837173462, "learning_rate": 0.00013035930424485666, "loss": 0.5902224540710449, "step": 244590 }, { "epoch": 1.4539531953088314, "grad_norm": 1.4476534128189087, "learning_rate": 0.0001303532407883535, "loss": 0.6134279251098633, "step": 244600 }, { "epoch": 1.4540126373854996, "grad_norm": 1.2563244104385376, "learning_rate": 0.00013034717723448707, "loss": 0.605647611618042, "step": 244610 }, { "epoch": 1.454072079462168, "grad_norm": 1.6598283052444458, "learning_rate": 0.00013034111358328635, "loss": 0.587893009185791, "step": 244620 }, { "epoch": 1.4541315215388364, "grad_norm": 1.6447237730026245, "learning_rate": 0.00013033504983478043, "loss": 0.5930583000183105, "step": 244630 }, { "epoch": 1.4541909636155048, "grad_norm": 1.520368218421936, "learning_rate": 0.00013032898598899827, "loss": 0.568961238861084, "step": 244640 }, { "epoch": 1.4542504056921732, "grad_norm": 1.3861500024795532, "learning_rate": 0.00013032292204596886, "loss": 0.6357686519622803, "step": 244650 }, { "epoch": 1.4543098477688416, "grad_norm": 1.73918879032135, "learning_rate": 0.0001303168580057213, "loss": 0.618780517578125, "step": 244660 }, { "epoch": 1.45436928984551, "grad_norm": 1.506772756576538, "learning_rate": 0.0001303107938682845, "loss": 0.5288032054901123, "step": 244670 }, { "epoch": 1.4544287319221785, "grad_norm": 1.7409111261367798, "learning_rate": 0.00013030472963368746, "loss": 0.6927630424499511, "step": 244680 }, { "epoch": 1.454488173998847, "grad_norm": 1.2632478475570679, "learning_rate": 0.00013029866530195924, "loss": 0.557157325744629, "step": 244690 }, { "epoch": 1.4545476160755153, "grad_norm": 1.5471235513687134, "learning_rate": 0.00013029260087312887, "loss": 0.6090714454650878, "step": 244700 }, { "epoch": 1.4546070581521837, "grad_norm": 1.3118828535079956, "learning_rate": 0.0001302865363472253, "loss": 0.5434925079345703, "step": 244710 }, { "epoch": 1.4546665002288521, "grad_norm": 1.7984539270401, "learning_rate": 0.0001302804717242776, "loss": 0.5900047779083252, "step": 244720 }, { "epoch": 1.4547259423055203, "grad_norm": 1.5062267780303955, "learning_rate": 0.00013027440700431474, "loss": 0.5745559692382812, "step": 244730 }, { "epoch": 1.4547853843821887, "grad_norm": 1.6627284288406372, "learning_rate": 0.00013026834218736574, "loss": 0.5438615322113037, "step": 244740 }, { "epoch": 1.4548448264588572, "grad_norm": 1.4130151271820068, "learning_rate": 0.00013026227727345958, "loss": 0.5999791145324707, "step": 244750 }, { "epoch": 1.4549042685355256, "grad_norm": 1.5953088998794556, "learning_rate": 0.00013025621226262537, "loss": 0.6122672080993652, "step": 244760 }, { "epoch": 1.454963710612194, "grad_norm": 1.5065374374389648, "learning_rate": 0.00013025014715489203, "loss": 0.5709261894226074, "step": 244770 }, { "epoch": 1.4550231526888624, "grad_norm": 1.3537909984588623, "learning_rate": 0.00013024408195028858, "loss": 0.5707159996032715, "step": 244780 }, { "epoch": 1.4550825947655306, "grad_norm": 1.5010900497436523, "learning_rate": 0.0001302380166488441, "loss": 0.630306339263916, "step": 244790 }, { "epoch": 1.455142036842199, "grad_norm": 1.3967759609222412, "learning_rate": 0.00013023195125058757, "loss": 0.573525333404541, "step": 244800 }, { "epoch": 1.4552014789188674, "grad_norm": 1.264130711555481, "learning_rate": 0.00013022588575554796, "loss": 0.6498292922973633, "step": 244810 }, { "epoch": 1.4552609209955358, "grad_norm": 1.569289207458496, "learning_rate": 0.00013021982016375432, "loss": 0.5867965698242188, "step": 244820 }, { "epoch": 1.4553203630722042, "grad_norm": 1.3694965839385986, "learning_rate": 0.00013021375447523566, "loss": 0.6254422187805175, "step": 244830 }, { "epoch": 1.4553798051488727, "grad_norm": 1.4751620292663574, "learning_rate": 0.00013020768869002105, "loss": 0.6141369819641114, "step": 244840 }, { "epoch": 1.455439247225541, "grad_norm": 1.3567925691604614, "learning_rate": 0.00013020162280813943, "loss": 0.5564784049987793, "step": 244850 }, { "epoch": 1.4554986893022095, "grad_norm": 1.7045577764511108, "learning_rate": 0.00013019555682961987, "loss": 0.6332785606384277, "step": 244860 }, { "epoch": 1.455558131378878, "grad_norm": 1.5702873468399048, "learning_rate": 0.00013018949075449134, "loss": 0.5796310424804687, "step": 244870 }, { "epoch": 1.4556175734555463, "grad_norm": 1.4565924406051636, "learning_rate": 0.0001301834245827829, "loss": 0.6211982727050781, "step": 244880 }, { "epoch": 1.4556770155322147, "grad_norm": 1.8843235969543457, "learning_rate": 0.00013017735831452354, "loss": 0.5446954727172851, "step": 244890 }, { "epoch": 1.4557364576088831, "grad_norm": 1.3958922624588013, "learning_rate": 0.0001301712919497423, "loss": 0.6037983417510986, "step": 244900 }, { "epoch": 1.4557958996855513, "grad_norm": 1.8029967546463013, "learning_rate": 0.00013016522548846824, "loss": 0.5398143768310547, "step": 244910 }, { "epoch": 1.4558553417622198, "grad_norm": 1.561282753944397, "learning_rate": 0.00013015915893073026, "loss": 0.5698527336120606, "step": 244920 }, { "epoch": 1.4559147838388882, "grad_norm": 1.5337181091308594, "learning_rate": 0.00013015309227655745, "loss": 0.5694564342498779, "step": 244930 }, { "epoch": 1.4559742259155566, "grad_norm": 1.1360198259353638, "learning_rate": 0.00013014702552597887, "loss": 0.5583847522735595, "step": 244940 }, { "epoch": 1.456033667992225, "grad_norm": 1.6434460878372192, "learning_rate": 0.0001301409586790235, "loss": 0.584917688369751, "step": 244950 }, { "epoch": 1.4560931100688934, "grad_norm": 1.3787226676940918, "learning_rate": 0.00013013489173572032, "loss": 0.5828258514404296, "step": 244960 }, { "epoch": 1.4561525521455618, "grad_norm": 1.9049731492996216, "learning_rate": 0.0001301288246960985, "loss": 0.6001475334167481, "step": 244970 }, { "epoch": 1.45621199422223, "grad_norm": 1.2901811599731445, "learning_rate": 0.00013012275756018688, "loss": 0.5481419086456298, "step": 244980 }, { "epoch": 1.4562714362988984, "grad_norm": 1.8498032093048096, "learning_rate": 0.00013011669032801456, "loss": 0.6615102767944336, "step": 244990 }, { "epoch": 1.4563308783755669, "grad_norm": 1.4041792154312134, "learning_rate": 0.0001301106229996106, "loss": 0.5463791847229004, "step": 245000 }, { "epoch": 1.4563903204522353, "grad_norm": 1.9599940776824951, "learning_rate": 0.00013010455557500397, "loss": 0.619199562072754, "step": 245010 }, { "epoch": 1.4564497625289037, "grad_norm": 1.4181896448135376, "learning_rate": 0.00013009848805422373, "loss": 0.585752296447754, "step": 245020 }, { "epoch": 1.456509204605572, "grad_norm": 1.450013518333435, "learning_rate": 0.0001300924204372989, "loss": 0.5760256767272949, "step": 245030 }, { "epoch": 1.4565686466822405, "grad_norm": 1.7910387516021729, "learning_rate": 0.0001300863527242585, "loss": 0.6400651454925537, "step": 245040 }, { "epoch": 1.456628088758909, "grad_norm": 1.3198387622833252, "learning_rate": 0.0001300802849151315, "loss": 0.5821139812469482, "step": 245050 }, { "epoch": 1.4566875308355773, "grad_norm": 1.3464279174804688, "learning_rate": 0.00013007421700994703, "loss": 0.5955679416656494, "step": 245060 }, { "epoch": 1.4567469729122458, "grad_norm": 1.2170555591583252, "learning_rate": 0.00013006814900873406, "loss": 0.6039692878723144, "step": 245070 }, { "epoch": 1.4568064149889142, "grad_norm": 1.7379664182662964, "learning_rate": 0.0001300620809115216, "loss": 0.5665688514709473, "step": 245080 }, { "epoch": 1.4568658570655826, "grad_norm": 1.282779574394226, "learning_rate": 0.00013005601271833873, "loss": 0.5672629356384278, "step": 245090 }, { "epoch": 1.4569252991422508, "grad_norm": 1.691491961479187, "learning_rate": 0.00013004994442921444, "loss": 0.5957682609558106, "step": 245100 }, { "epoch": 1.4569847412189192, "grad_norm": 1.5693994760513306, "learning_rate": 0.00013004387604417775, "loss": 0.546907615661621, "step": 245110 }, { "epoch": 1.4570441832955876, "grad_norm": 1.1332886219024658, "learning_rate": 0.00013003780756325775, "loss": 0.605256175994873, "step": 245120 }, { "epoch": 1.457103625372256, "grad_norm": 1.1119813919067383, "learning_rate": 0.00013003173898648338, "loss": 0.6343971252441406, "step": 245130 }, { "epoch": 1.4571630674489244, "grad_norm": 1.3504761457443237, "learning_rate": 0.00013002567031388372, "loss": 0.6152094841003418, "step": 245140 }, { "epoch": 1.4572225095255928, "grad_norm": 1.3566412925720215, "learning_rate": 0.00013001960154548784, "loss": 0.5857264041900635, "step": 245150 }, { "epoch": 1.457281951602261, "grad_norm": 1.4823918342590332, "learning_rate": 0.0001300135326813247, "loss": 0.5491465568542481, "step": 245160 }, { "epoch": 1.4573413936789295, "grad_norm": 1.6158605813980103, "learning_rate": 0.0001300074637214234, "loss": 0.5280389785766602, "step": 245170 }, { "epoch": 1.4574008357555979, "grad_norm": 1.3275681734085083, "learning_rate": 0.00013000139466581284, "loss": 0.6173741340637207, "step": 245180 }, { "epoch": 1.4574602778322663, "grad_norm": 1.7281055450439453, "learning_rate": 0.00012999532551452223, "loss": 0.6211791515350342, "step": 245190 }, { "epoch": 1.4575197199089347, "grad_norm": 1.4884241819381714, "learning_rate": 0.00012998925626758048, "loss": 0.5667206764221191, "step": 245200 }, { "epoch": 1.4575791619856031, "grad_norm": 1.2068672180175781, "learning_rate": 0.00012998318692501666, "loss": 0.6039330959320068, "step": 245210 }, { "epoch": 1.4576386040622715, "grad_norm": 1.6266967058181763, "learning_rate": 0.00012997711748685985, "loss": 0.5544971942901611, "step": 245220 }, { "epoch": 1.45769804613894, "grad_norm": 1.0759812593460083, "learning_rate": 0.00012997104795313898, "loss": 0.5919562816619873, "step": 245230 }, { "epoch": 1.4577574882156084, "grad_norm": 1.5560834407806396, "learning_rate": 0.00012996497832388316, "loss": 0.6288482666015625, "step": 245240 }, { "epoch": 1.4578169302922768, "grad_norm": 1.721286416053772, "learning_rate": 0.00012995890859912143, "loss": 0.6272643566131592, "step": 245250 }, { "epoch": 1.4578763723689452, "grad_norm": 1.3210880756378174, "learning_rate": 0.00012995283877888277, "loss": 0.5854324340820313, "step": 245260 }, { "epoch": 1.4579358144456136, "grad_norm": 1.2349040508270264, "learning_rate": 0.00012994676886319626, "loss": 0.5976838111877442, "step": 245270 }, { "epoch": 1.4579952565222818, "grad_norm": 1.6721338033676147, "learning_rate": 0.00012994069885209094, "loss": 0.5315534591674804, "step": 245280 }, { "epoch": 1.4580546985989502, "grad_norm": 1.7023301124572754, "learning_rate": 0.00012993462874559582, "loss": 0.5564986228942871, "step": 245290 }, { "epoch": 1.4581141406756186, "grad_norm": 1.7102248668670654, "learning_rate": 0.00012992855854373995, "loss": 0.5917792320251465, "step": 245300 }, { "epoch": 1.458173582752287, "grad_norm": 1.6355209350585938, "learning_rate": 0.0001299224882465524, "loss": 0.5816460132598877, "step": 245310 }, { "epoch": 1.4582330248289554, "grad_norm": 1.8227169513702393, "learning_rate": 0.00012991641785406214, "loss": 0.6467808723449707, "step": 245320 }, { "epoch": 1.4582924669056239, "grad_norm": 1.8622329235076904, "learning_rate": 0.00012991034736629828, "loss": 0.5783666610717774, "step": 245330 }, { "epoch": 1.4583519089822923, "grad_norm": 1.2535473108291626, "learning_rate": 0.0001299042767832898, "loss": 0.6206005096435547, "step": 245340 }, { "epoch": 1.4584113510589605, "grad_norm": 1.2696874141693115, "learning_rate": 0.00012989820610506575, "loss": 0.5743404388427734, "step": 245350 }, { "epoch": 1.4584707931356289, "grad_norm": 1.472887396812439, "learning_rate": 0.00012989213533165522, "loss": 0.5915170192718506, "step": 245360 }, { "epoch": 1.4585302352122973, "grad_norm": 1.3031848669052124, "learning_rate": 0.0001298860644630872, "loss": 0.5969231128692627, "step": 245370 }, { "epoch": 1.4585896772889657, "grad_norm": 1.2431838512420654, "learning_rate": 0.00012987999349939073, "loss": 0.606338357925415, "step": 245380 }, { "epoch": 1.4586491193656341, "grad_norm": 1.78584623336792, "learning_rate": 0.00012987392244059488, "loss": 0.607558298110962, "step": 245390 }, { "epoch": 1.4587085614423025, "grad_norm": 1.306854009628296, "learning_rate": 0.0001298678512867287, "loss": 0.5427912712097168, "step": 245400 }, { "epoch": 1.458768003518971, "grad_norm": 1.4234315156936646, "learning_rate": 0.0001298617800378212, "loss": 0.5743022918701172, "step": 245410 }, { "epoch": 1.4588274455956394, "grad_norm": 1.491769552230835, "learning_rate": 0.0001298557086939014, "loss": 0.587503719329834, "step": 245420 }, { "epoch": 1.4588868876723078, "grad_norm": 1.6491403579711914, "learning_rate": 0.00012984963725499841, "loss": 0.6109411239624023, "step": 245430 }, { "epoch": 1.4589463297489762, "grad_norm": 1.3545141220092773, "learning_rate": 0.00012984356572114125, "loss": 0.5791049003601074, "step": 245440 }, { "epoch": 1.4590057718256446, "grad_norm": 1.4917033910751343, "learning_rate": 0.00012983749409235893, "loss": 0.5555436134338378, "step": 245450 }, { "epoch": 1.459065213902313, "grad_norm": 1.7843434810638428, "learning_rate": 0.00012983142236868054, "loss": 0.5685639381408691, "step": 245460 }, { "epoch": 1.4591246559789812, "grad_norm": 1.2903149127960205, "learning_rate": 0.00012982535055013511, "loss": 0.5946718215942383, "step": 245470 }, { "epoch": 1.4591840980556496, "grad_norm": 1.1861565113067627, "learning_rate": 0.0001298192786367517, "loss": 0.5374304771423339, "step": 245480 }, { "epoch": 1.459243540132318, "grad_norm": 1.4075512886047363, "learning_rate": 0.00012981320662855929, "loss": 0.615534782409668, "step": 245490 }, { "epoch": 1.4593029822089865, "grad_norm": 1.7441641092300415, "learning_rate": 0.00012980713452558703, "loss": 0.6644767761230469, "step": 245500 }, { "epoch": 1.4593624242856549, "grad_norm": 1.618499755859375, "learning_rate": 0.0001298010623278639, "loss": 0.6055778503417969, "step": 245510 }, { "epoch": 1.4594218663623233, "grad_norm": 1.4002019166946411, "learning_rate": 0.0001297949900354189, "loss": 0.5246916770935058, "step": 245520 }, { "epoch": 1.4594813084389915, "grad_norm": 1.3147128820419312, "learning_rate": 0.0001297889176482812, "loss": 0.5816736221313477, "step": 245530 }, { "epoch": 1.45954075051566, "grad_norm": 1.4403153657913208, "learning_rate": 0.00012978284516647974, "loss": 0.5473114967346191, "step": 245540 }, { "epoch": 1.4596001925923283, "grad_norm": 1.3530149459838867, "learning_rate": 0.00012977677259004363, "loss": 0.5636565208435058, "step": 245550 }, { "epoch": 1.4596596346689967, "grad_norm": 1.7721482515335083, "learning_rate": 0.00012977069991900196, "loss": 0.6170164108276367, "step": 245560 }, { "epoch": 1.4597190767456651, "grad_norm": 1.4782956838607788, "learning_rate": 0.00012976462715338363, "loss": 0.6652994155883789, "step": 245570 }, { "epoch": 1.4597785188223336, "grad_norm": 1.954275369644165, "learning_rate": 0.00012975855429321782, "loss": 0.6654625415802002, "step": 245580 }, { "epoch": 1.459837960899002, "grad_norm": 1.357369065284729, "learning_rate": 0.00012975248133853355, "loss": 0.546147632598877, "step": 245590 }, { "epoch": 1.4598974029756704, "grad_norm": 1.690802812576294, "learning_rate": 0.00012974640828935987, "loss": 0.563063383102417, "step": 245600 }, { "epoch": 1.4599568450523388, "grad_norm": 1.371364951133728, "learning_rate": 0.0001297403351457258, "loss": 0.6119277477264404, "step": 245610 }, { "epoch": 1.4600162871290072, "grad_norm": 1.3253809213638306, "learning_rate": 0.00012973426190766046, "loss": 0.5572071075439453, "step": 245620 }, { "epoch": 1.4600757292056756, "grad_norm": 1.4045133590698242, "learning_rate": 0.00012972818857519283, "loss": 0.5307745933532715, "step": 245630 }, { "epoch": 1.460135171282344, "grad_norm": 1.6665186882019043, "learning_rate": 0.000129722115148352, "loss": 0.6478655815124512, "step": 245640 }, { "epoch": 1.4601946133590122, "grad_norm": 1.7471543550491333, "learning_rate": 0.000129716041627167, "loss": 0.579472017288208, "step": 245650 }, { "epoch": 1.4602540554356807, "grad_norm": 1.2799723148345947, "learning_rate": 0.00012970996801166696, "loss": 0.5361632347106934, "step": 245660 }, { "epoch": 1.460313497512349, "grad_norm": 1.3499913215637207, "learning_rate": 0.0001297038943018808, "loss": 0.5702944755554199, "step": 245670 }, { "epoch": 1.4603729395890175, "grad_norm": 2.2810471057891846, "learning_rate": 0.00012969782049783768, "loss": 0.6017364978790283, "step": 245680 }, { "epoch": 1.460432381665686, "grad_norm": 1.7864996194839478, "learning_rate": 0.00012969174659956665, "loss": 0.5838388919830322, "step": 245690 }, { "epoch": 1.4604918237423543, "grad_norm": 1.351200819015503, "learning_rate": 0.0001296856726070967, "loss": 0.5626345634460449, "step": 245700 }, { "epoch": 1.4605512658190227, "grad_norm": 1.5616666078567505, "learning_rate": 0.00012967959852045694, "loss": 0.6050459861755371, "step": 245710 }, { "epoch": 1.460610707895691, "grad_norm": 1.2357646226882935, "learning_rate": 0.0001296735243396764, "loss": 0.5897476673126221, "step": 245720 }, { "epoch": 1.4606701499723593, "grad_norm": 1.8285744190216064, "learning_rate": 0.00012966745006478416, "loss": 0.5708223342895508, "step": 245730 }, { "epoch": 1.4607295920490277, "grad_norm": 2.128871202468872, "learning_rate": 0.00012966137569580928, "loss": 0.6214184761047363, "step": 245740 }, { "epoch": 1.4607890341256962, "grad_norm": 1.398244023323059, "learning_rate": 0.00012965530123278078, "loss": 0.6154640674591064, "step": 245750 }, { "epoch": 1.4608484762023646, "grad_norm": 1.6883862018585205, "learning_rate": 0.00012964922667572777, "loss": 0.6081310272216797, "step": 245760 }, { "epoch": 1.460907918279033, "grad_norm": 1.5049296617507935, "learning_rate": 0.00012964315202467925, "loss": 0.517087459564209, "step": 245770 }, { "epoch": 1.4609673603557014, "grad_norm": 1.3246397972106934, "learning_rate": 0.0001296370772796643, "loss": 0.5686284065246582, "step": 245780 }, { "epoch": 1.4610268024323698, "grad_norm": 1.6865886449813843, "learning_rate": 0.00012963100244071203, "loss": 0.5568544387817382, "step": 245790 }, { "epoch": 1.4610862445090382, "grad_norm": 1.373576283454895, "learning_rate": 0.00012962492750785145, "loss": 0.5826116561889648, "step": 245800 }, { "epoch": 1.4611456865857066, "grad_norm": 1.267352819442749, "learning_rate": 0.0001296188524811116, "loss": 0.548613166809082, "step": 245810 }, { "epoch": 1.461205128662375, "grad_norm": 1.7470444440841675, "learning_rate": 0.0001296127773605216, "loss": 0.6316418647766113, "step": 245820 }, { "epoch": 1.4612645707390435, "grad_norm": 1.4639191627502441, "learning_rate": 0.00012960670214611048, "loss": 0.6187705039978028, "step": 245830 }, { "epoch": 1.4613240128157117, "grad_norm": 1.4191278219223022, "learning_rate": 0.0001296006268379073, "loss": 0.6076081275939942, "step": 245840 }, { "epoch": 1.46138345489238, "grad_norm": 1.9011796712875366, "learning_rate": 0.00012959455143594115, "loss": 0.5180899620056152, "step": 245850 }, { "epoch": 1.4614428969690485, "grad_norm": 1.4736390113830566, "learning_rate": 0.00012958847594024103, "loss": 0.514503288269043, "step": 245860 }, { "epoch": 1.461502339045717, "grad_norm": 1.9756577014923096, "learning_rate": 0.00012958240035083608, "loss": 0.5463451385498047, "step": 245870 }, { "epoch": 1.4615617811223853, "grad_norm": 1.4674378633499146, "learning_rate": 0.00012957632466775528, "loss": 0.5547277450561523, "step": 245880 }, { "epoch": 1.4616212231990537, "grad_norm": 1.6204081773757935, "learning_rate": 0.0001295702488910278, "loss": 0.5790774345397949, "step": 245890 }, { "epoch": 1.461680665275722, "grad_norm": 1.454936146736145, "learning_rate": 0.0001295641730206826, "loss": 0.6356830596923828, "step": 245900 }, { "epoch": 1.4617401073523903, "grad_norm": 2.048337459564209, "learning_rate": 0.00012955809705674878, "loss": 0.5921838760375977, "step": 245910 }, { "epoch": 1.4617995494290588, "grad_norm": 1.543506383895874, "learning_rate": 0.00012955202099925546, "loss": 0.5834306716918946, "step": 245920 }, { "epoch": 1.4618589915057272, "grad_norm": 1.4787331819534302, "learning_rate": 0.00012954594484823162, "loss": 0.5721753120422364, "step": 245930 }, { "epoch": 1.4619184335823956, "grad_norm": 1.464522123336792, "learning_rate": 0.00012953986860370642, "loss": 0.6152347564697266, "step": 245940 }, { "epoch": 1.461977875659064, "grad_norm": 1.7963595390319824, "learning_rate": 0.0001295337922657088, "loss": 0.6013269424438477, "step": 245950 }, { "epoch": 1.4620373177357324, "grad_norm": 1.8394737243652344, "learning_rate": 0.00012952771583426794, "loss": 0.625972318649292, "step": 245960 }, { "epoch": 1.4620967598124008, "grad_norm": 1.4612724781036377, "learning_rate": 0.0001295216393094129, "loss": 0.5979384422302246, "step": 245970 }, { "epoch": 1.4621562018890693, "grad_norm": 1.3299938440322876, "learning_rate": 0.00012951556269117268, "loss": 0.5566338062286377, "step": 245980 }, { "epoch": 1.4622156439657377, "grad_norm": 1.253775954246521, "learning_rate": 0.0001295094859795764, "loss": 0.6109885215759278, "step": 245990 }, { "epoch": 1.462275086042406, "grad_norm": 1.7500993013381958, "learning_rate": 0.00012950340917465311, "loss": 0.5783988952636718, "step": 246000 }, { "epoch": 1.4623345281190745, "grad_norm": 1.5186508893966675, "learning_rate": 0.00012949733227643186, "loss": 0.5699985027313232, "step": 246010 }, { "epoch": 1.4623939701957427, "grad_norm": 1.2854533195495605, "learning_rate": 0.00012949125528494178, "loss": 0.6128026008605957, "step": 246020 }, { "epoch": 1.462453412272411, "grad_norm": 1.394323706626892, "learning_rate": 0.00012948517820021192, "loss": 0.6551718711853027, "step": 246030 }, { "epoch": 1.4625128543490795, "grad_norm": 1.8348256349563599, "learning_rate": 0.00012947910102227128, "loss": 0.6611001014709472, "step": 246040 }, { "epoch": 1.462572296425748, "grad_norm": 1.2746080160140991, "learning_rate": 0.00012947302375114904, "loss": 0.5812842369079589, "step": 246050 }, { "epoch": 1.4626317385024163, "grad_norm": 1.5895130634307861, "learning_rate": 0.00012946694638687415, "loss": 0.6484689235687255, "step": 246060 }, { "epoch": 1.4626911805790848, "grad_norm": 1.5660663843154907, "learning_rate": 0.0001294608689294758, "loss": 0.6098230361938477, "step": 246070 }, { "epoch": 1.4627506226557532, "grad_norm": 1.1869081258773804, "learning_rate": 0.00012945479137898303, "loss": 0.5940955638885498, "step": 246080 }, { "epoch": 1.4628100647324214, "grad_norm": 1.5198018550872803, "learning_rate": 0.00012944871373542487, "loss": 0.5807378768920899, "step": 246090 }, { "epoch": 1.4628695068090898, "grad_norm": 1.6087597608566284, "learning_rate": 0.0001294426359988304, "loss": 0.5550469398498535, "step": 246100 }, { "epoch": 1.4629289488857582, "grad_norm": 1.4811192750930786, "learning_rate": 0.00012943655816922874, "loss": 0.6188537120819092, "step": 246110 }, { "epoch": 1.4629883909624266, "grad_norm": 1.563692331314087, "learning_rate": 0.0001294304802466489, "loss": 0.6018446922302246, "step": 246120 }, { "epoch": 1.463047833039095, "grad_norm": 1.571975827217102, "learning_rate": 0.00012942440223112007, "loss": 0.5863933563232422, "step": 246130 }, { "epoch": 1.4631072751157634, "grad_norm": 1.5990924835205078, "learning_rate": 0.0001294183241226712, "loss": 0.645451021194458, "step": 246140 }, { "epoch": 1.4631667171924319, "grad_norm": 1.324907898902893, "learning_rate": 0.00012941224592133142, "loss": 0.5429471492767334, "step": 246150 }, { "epoch": 1.4632261592691003, "grad_norm": 1.5138622522354126, "learning_rate": 0.00012940616762712977, "loss": 0.5907786369323731, "step": 246160 }, { "epoch": 1.4632856013457687, "grad_norm": 1.7118630409240723, "learning_rate": 0.0001294000892400954, "loss": 0.638283634185791, "step": 246170 }, { "epoch": 1.463345043422437, "grad_norm": 1.7677724361419678, "learning_rate": 0.0001293940107602573, "loss": 0.528986120223999, "step": 246180 }, { "epoch": 1.4634044854991055, "grad_norm": 1.5354242324829102, "learning_rate": 0.00012938793218764463, "loss": 0.6269987106323243, "step": 246190 }, { "epoch": 1.4634639275757737, "grad_norm": 1.2989128828048706, "learning_rate": 0.00012938185352228643, "loss": 0.5818567276000977, "step": 246200 }, { "epoch": 1.4635233696524421, "grad_norm": 1.4672411680221558, "learning_rate": 0.00012937577476421173, "loss": 0.5641633987426757, "step": 246210 }, { "epoch": 1.4635828117291105, "grad_norm": 1.602942943572998, "learning_rate": 0.0001293696959134497, "loss": 0.6029854774475097, "step": 246220 }, { "epoch": 1.463642253805779, "grad_norm": 1.5684503316879272, "learning_rate": 0.0001293636169700294, "loss": 0.6030837059020996, "step": 246230 }, { "epoch": 1.4637016958824474, "grad_norm": 1.4154937267303467, "learning_rate": 0.00012935753793397983, "loss": 0.607669448852539, "step": 246240 }, { "epoch": 1.4637611379591158, "grad_norm": 1.6637790203094482, "learning_rate": 0.00012935145880533012, "loss": 0.6509490966796875, "step": 246250 }, { "epoch": 1.4638205800357842, "grad_norm": 1.493850588798523, "learning_rate": 0.0001293453795841094, "loss": 0.5694750785827637, "step": 246260 }, { "epoch": 1.4638800221124524, "grad_norm": 1.2857962846755981, "learning_rate": 0.00012933930027034664, "loss": 0.6481438636779785, "step": 246270 }, { "epoch": 1.4639394641891208, "grad_norm": 1.39143705368042, "learning_rate": 0.00012933322086407104, "loss": 0.6072395801544189, "step": 246280 }, { "epoch": 1.4639989062657892, "grad_norm": 1.5985188484191895, "learning_rate": 0.00012932714136531165, "loss": 0.6187022686004638, "step": 246290 }, { "epoch": 1.4640583483424576, "grad_norm": 1.4632388353347778, "learning_rate": 0.00012932106177409745, "loss": 0.5706487655639648, "step": 246300 }, { "epoch": 1.464117790419126, "grad_norm": 1.5658200979232788, "learning_rate": 0.00012931498209045768, "loss": 0.5679763793945313, "step": 246310 }, { "epoch": 1.4641772324957945, "grad_norm": 1.8441548347473145, "learning_rate": 0.00012930890231442133, "loss": 0.6454527854919434, "step": 246320 }, { "epoch": 1.4642366745724629, "grad_norm": 1.730461835861206, "learning_rate": 0.0001293028224460175, "loss": 0.5959432601928711, "step": 246330 }, { "epoch": 1.4642961166491313, "grad_norm": 1.5324515104293823, "learning_rate": 0.00012929674248527527, "loss": 0.6183679580688477, "step": 246340 }, { "epoch": 1.4643555587257997, "grad_norm": 1.5394469499588013, "learning_rate": 0.00012929066243222372, "loss": 0.6033469200134277, "step": 246350 }, { "epoch": 1.4644150008024681, "grad_norm": 1.4175094366073608, "learning_rate": 0.00012928458228689195, "loss": 0.6336727619171143, "step": 246360 }, { "epoch": 1.4644744428791365, "grad_norm": 1.2875090837478638, "learning_rate": 0.00012927850204930906, "loss": 0.5458648204803467, "step": 246370 }, { "epoch": 1.464533884955805, "grad_norm": 1.4569426774978638, "learning_rate": 0.0001292724217195041, "loss": 0.6277149200439454, "step": 246380 }, { "epoch": 1.4645933270324731, "grad_norm": 1.1706321239471436, "learning_rate": 0.00012926634129750619, "loss": 0.5406584739685059, "step": 246390 }, { "epoch": 1.4646527691091416, "grad_norm": 1.2798320055007935, "learning_rate": 0.00012926026078334435, "loss": 0.5752211570739746, "step": 246400 }, { "epoch": 1.46471221118581, "grad_norm": 1.6581588983535767, "learning_rate": 0.00012925418017704777, "loss": 0.5068301200866699, "step": 246410 }, { "epoch": 1.4647716532624784, "grad_norm": 1.5638712644577026, "learning_rate": 0.00012924809947864547, "loss": 0.5980568885803222, "step": 246420 }, { "epoch": 1.4648310953391468, "grad_norm": 1.2171413898468018, "learning_rate": 0.00012924201868816655, "loss": 0.6237740516662598, "step": 246430 }, { "epoch": 1.4648905374158152, "grad_norm": 1.5888216495513916, "learning_rate": 0.00012923593780564006, "loss": 0.5685859680175781, "step": 246440 }, { "epoch": 1.4649499794924836, "grad_norm": 1.7769346237182617, "learning_rate": 0.0001292298568310952, "loss": 0.6336522102355957, "step": 246450 }, { "epoch": 1.4650094215691518, "grad_norm": 1.4779294729232788, "learning_rate": 0.00012922377576456094, "loss": 0.5817000389099121, "step": 246460 }, { "epoch": 1.4650688636458202, "grad_norm": 1.560966968536377, "learning_rate": 0.00012921769460606645, "loss": 0.6688947200775146, "step": 246470 }, { "epoch": 1.4651283057224886, "grad_norm": 1.306083083152771, "learning_rate": 0.00012921161335564078, "loss": 0.5385366439819336, "step": 246480 }, { "epoch": 1.465187747799157, "grad_norm": 1.2806825637817383, "learning_rate": 0.00012920553201331304, "loss": 0.5739172458648681, "step": 246490 }, { "epoch": 1.4652471898758255, "grad_norm": 1.3909779787063599, "learning_rate": 0.00012919945057911228, "loss": 0.5989433288574219, "step": 246500 }, { "epoch": 1.4653066319524939, "grad_norm": 1.574160099029541, "learning_rate": 0.00012919336905306764, "loss": 0.592760419845581, "step": 246510 }, { "epoch": 1.4653660740291623, "grad_norm": 1.8457976579666138, "learning_rate": 0.0001291872874352082, "loss": 0.57711763381958, "step": 246520 }, { "epoch": 1.4654255161058307, "grad_norm": 1.480624794960022, "learning_rate": 0.00012918120572556302, "loss": 0.5626651763916015, "step": 246530 }, { "epoch": 1.4654849581824991, "grad_norm": 1.590623378753662, "learning_rate": 0.00012917512392416128, "loss": 0.5510509967803955, "step": 246540 }, { "epoch": 1.4655444002591675, "grad_norm": 1.3125886917114258, "learning_rate": 0.00012916904203103194, "loss": 0.6116321086883545, "step": 246550 }, { "epoch": 1.465603842335836, "grad_norm": 1.4680640697479248, "learning_rate": 0.00012916296004620423, "loss": 0.6051517486572265, "step": 246560 }, { "epoch": 1.4656632844125042, "grad_norm": 1.6488584280014038, "learning_rate": 0.00012915687796970714, "loss": 0.5710641860961914, "step": 246570 }, { "epoch": 1.4657227264891726, "grad_norm": 1.8557785749435425, "learning_rate": 0.00012915079580156982, "loss": 0.5519813060760498, "step": 246580 }, { "epoch": 1.465782168565841, "grad_norm": 1.7122042179107666, "learning_rate": 0.00012914471354182137, "loss": 0.5540801048278808, "step": 246590 }, { "epoch": 1.4658416106425094, "grad_norm": 1.3887234926223755, "learning_rate": 0.00012913863119049085, "loss": 0.5966529846191406, "step": 246600 }, { "epoch": 1.4659010527191778, "grad_norm": 1.3096494674682617, "learning_rate": 0.0001291325487476074, "loss": 0.6048375606536865, "step": 246610 }, { "epoch": 1.4659604947958462, "grad_norm": 1.401296854019165, "learning_rate": 0.00012912646621320004, "loss": 0.6108362674713135, "step": 246620 }, { "epoch": 1.4660199368725146, "grad_norm": 1.3954780101776123, "learning_rate": 0.00012912038358729795, "loss": 0.5814803600311279, "step": 246630 }, { "epoch": 1.4660793789491828, "grad_norm": 1.209713339805603, "learning_rate": 0.00012911430086993018, "loss": 0.558740234375, "step": 246640 }, { "epoch": 1.4661388210258512, "grad_norm": 1.4341473579406738, "learning_rate": 0.00012910821806112586, "loss": 0.5606043815612793, "step": 246650 }, { "epoch": 1.4661982631025197, "grad_norm": 1.6558946371078491, "learning_rate": 0.00012910213516091403, "loss": 0.529283094406128, "step": 246660 }, { "epoch": 1.466257705179188, "grad_norm": 1.3257333040237427, "learning_rate": 0.00012909605216932389, "loss": 0.6366641998291016, "step": 246670 }, { "epoch": 1.4663171472558565, "grad_norm": 1.7804467678070068, "learning_rate": 0.0001290899690863844, "loss": 0.5737631797790528, "step": 246680 }, { "epoch": 1.466376589332525, "grad_norm": 1.4409939050674438, "learning_rate": 0.0001290838859121248, "loss": 0.6323710441589355, "step": 246690 }, { "epoch": 1.4664360314091933, "grad_norm": 1.50542414188385, "learning_rate": 0.0001290778026465741, "loss": 0.6533708095550537, "step": 246700 }, { "epoch": 1.4664954734858617, "grad_norm": 1.5709058046340942, "learning_rate": 0.0001290717192897614, "loss": 0.607116413116455, "step": 246710 }, { "epoch": 1.4665549155625301, "grad_norm": 1.324359655380249, "learning_rate": 0.00012906563584171588, "loss": 0.5602258205413818, "step": 246720 }, { "epoch": 1.4666143576391986, "grad_norm": 1.462475299835205, "learning_rate": 0.00012905955230246654, "loss": 0.5525561332702636, "step": 246730 }, { "epoch": 1.466673799715867, "grad_norm": 1.4445396661758423, "learning_rate": 0.00012905346867204257, "loss": 0.6285519599914551, "step": 246740 }, { "epoch": 1.4667332417925354, "grad_norm": 1.367083191871643, "learning_rate": 0.000129047384950473, "loss": 0.5791133403778076, "step": 246750 }, { "epoch": 1.4667926838692036, "grad_norm": 1.941697120666504, "learning_rate": 0.00012904130113778697, "loss": 0.6245877265930175, "step": 246760 }, { "epoch": 1.466852125945872, "grad_norm": 1.2649363279342651, "learning_rate": 0.00012903521723401363, "loss": 0.560162353515625, "step": 246770 }, { "epoch": 1.4669115680225404, "grad_norm": 1.7909355163574219, "learning_rate": 0.00012902913323918196, "loss": 0.6218095302581788, "step": 246780 }, { "epoch": 1.4669710100992088, "grad_norm": 1.8291093111038208, "learning_rate": 0.00012902304915332117, "loss": 0.6141592025756836, "step": 246790 }, { "epoch": 1.4670304521758772, "grad_norm": 1.2898013591766357, "learning_rate": 0.00012901696497646036, "loss": 0.5686063766479492, "step": 246800 }, { "epoch": 1.4670898942525457, "grad_norm": 1.9035950899124146, "learning_rate": 0.00012901088070862854, "loss": 0.6374611377716064, "step": 246810 }, { "epoch": 1.467149336329214, "grad_norm": 1.5983843803405762, "learning_rate": 0.00012900479634985493, "loss": 0.6119735717773438, "step": 246820 }, { "epoch": 1.4672087784058823, "grad_norm": 1.5221202373504639, "learning_rate": 0.00012899871190016858, "loss": 0.5855849266052247, "step": 246830 }, { "epoch": 1.4672682204825507, "grad_norm": 1.4902825355529785, "learning_rate": 0.00012899262735959857, "loss": 0.5585623264312745, "step": 246840 }, { "epoch": 1.467327662559219, "grad_norm": 1.4603904485702515, "learning_rate": 0.0001289865427281741, "loss": 0.5923275470733642, "step": 246850 }, { "epoch": 1.4673871046358875, "grad_norm": 1.5239490270614624, "learning_rate": 0.00012898045800592412, "loss": 0.5948696136474609, "step": 246860 }, { "epoch": 1.467446546712556, "grad_norm": 1.8094244003295898, "learning_rate": 0.0001289743731928779, "loss": 0.6056291580200195, "step": 246870 }, { "epoch": 1.4675059887892243, "grad_norm": 1.482872486114502, "learning_rate": 0.00012896828828906447, "loss": 0.6103637218475342, "step": 246880 }, { "epoch": 1.4675654308658928, "grad_norm": 1.7121535539627075, "learning_rate": 0.00012896220329451294, "loss": 0.622637128829956, "step": 246890 }, { "epoch": 1.4676248729425612, "grad_norm": 1.3110309839248657, "learning_rate": 0.00012895611820925242, "loss": 0.5789535522460938, "step": 246900 }, { "epoch": 1.4676843150192296, "grad_norm": 1.642298698425293, "learning_rate": 0.00012895003303331202, "loss": 0.6122090816497803, "step": 246910 }, { "epoch": 1.467743757095898, "grad_norm": 1.4643776416778564, "learning_rate": 0.0001289439477667209, "loss": 0.5828001022338867, "step": 246920 }, { "epoch": 1.4678031991725664, "grad_norm": 1.9371411800384521, "learning_rate": 0.00012893786240950807, "loss": 0.6432509422302246, "step": 246930 }, { "epoch": 1.4678626412492346, "grad_norm": 1.5108509063720703, "learning_rate": 0.0001289317769617027, "loss": 0.5465156555175781, "step": 246940 }, { "epoch": 1.467922083325903, "grad_norm": 1.676215648651123, "learning_rate": 0.00012892569142333393, "loss": 0.5789419174194336, "step": 246950 }, { "epoch": 1.4679815254025714, "grad_norm": 1.6190329790115356, "learning_rate": 0.0001289196057944308, "loss": 0.6765447616577148, "step": 246960 }, { "epoch": 1.4680409674792398, "grad_norm": 1.5386837720870972, "learning_rate": 0.0001289135200750225, "loss": 0.5936071872711182, "step": 246970 }, { "epoch": 1.4681004095559083, "grad_norm": 1.9495714902877808, "learning_rate": 0.00012890743426513808, "loss": 0.6228667259216308, "step": 246980 }, { "epoch": 1.4681598516325767, "grad_norm": 1.6276499032974243, "learning_rate": 0.00012890134836480665, "loss": 0.5833503723144531, "step": 246990 }, { "epoch": 1.468219293709245, "grad_norm": 1.6001931428909302, "learning_rate": 0.0001288952623740574, "loss": 0.5739994049072266, "step": 247000 }, { "epoch": 1.4682787357859133, "grad_norm": 1.5084282159805298, "learning_rate": 0.00012888917629291934, "loss": 0.621014404296875, "step": 247010 }, { "epoch": 1.4683381778625817, "grad_norm": 1.5135111808776855, "learning_rate": 0.00012888309012142166, "loss": 0.6325142860412598, "step": 247020 }, { "epoch": 1.46839761993925, "grad_norm": 1.66724693775177, "learning_rate": 0.00012887700385959345, "loss": 0.5356975555419922, "step": 247030 }, { "epoch": 1.4684570620159185, "grad_norm": 1.4852333068847656, "learning_rate": 0.0001288709175074638, "loss": 0.5883299827575683, "step": 247040 }, { "epoch": 1.468516504092587, "grad_norm": 1.7815020084381104, "learning_rate": 0.00012886483106506187, "loss": 0.5727350234985351, "step": 247050 }, { "epoch": 1.4685759461692554, "grad_norm": 1.6806286573410034, "learning_rate": 0.00012885874453241676, "loss": 0.5765576362609863, "step": 247060 }, { "epoch": 1.4686353882459238, "grad_norm": 1.4223663806915283, "learning_rate": 0.00012885265790955753, "loss": 0.5996372699737549, "step": 247070 }, { "epoch": 1.4686948303225922, "grad_norm": 2.428615093231201, "learning_rate": 0.0001288465711965134, "loss": 0.6121301651000977, "step": 247080 }, { "epoch": 1.4687542723992606, "grad_norm": 1.2623648643493652, "learning_rate": 0.0001288404843933134, "loss": 0.61527099609375, "step": 247090 }, { "epoch": 1.468813714475929, "grad_norm": 1.4169650077819824, "learning_rate": 0.0001288343974999867, "loss": 0.5179756641387939, "step": 247100 }, { "epoch": 1.4688731565525974, "grad_norm": 1.5150721073150635, "learning_rate": 0.00012882831051656238, "loss": 0.6211129188537597, "step": 247110 }, { "epoch": 1.4689325986292658, "grad_norm": 1.5346312522888184, "learning_rate": 0.0001288222234430696, "loss": 0.5460414409637451, "step": 247120 }, { "epoch": 1.468992040705934, "grad_norm": 1.9163941144943237, "learning_rate": 0.00012881613627953743, "loss": 0.5644173622131348, "step": 247130 }, { "epoch": 1.4690514827826024, "grad_norm": 1.3029135465621948, "learning_rate": 0.000128810049025995, "loss": 0.5963180541992188, "step": 247140 }, { "epoch": 1.4691109248592709, "grad_norm": 1.7080451250076294, "learning_rate": 0.00012880396168247148, "loss": 0.5643375873565674, "step": 247150 }, { "epoch": 1.4691703669359393, "grad_norm": 1.5329331159591675, "learning_rate": 0.00012879787424899597, "loss": 0.5697405815124512, "step": 247160 }, { "epoch": 1.4692298090126077, "grad_norm": 1.8731627464294434, "learning_rate": 0.00012879178672559752, "loss": 0.601518201828003, "step": 247170 }, { "epoch": 1.469289251089276, "grad_norm": 1.4287655353546143, "learning_rate": 0.0001287856991123053, "loss": 0.578211784362793, "step": 247180 }, { "epoch": 1.4693486931659445, "grad_norm": 1.663204550743103, "learning_rate": 0.00012877961140914847, "loss": 0.6139910697937012, "step": 247190 }, { "epoch": 1.4694081352426127, "grad_norm": 1.7610046863555908, "learning_rate": 0.0001287735236161561, "loss": 0.6192550659179688, "step": 247200 }, { "epoch": 1.4694675773192811, "grad_norm": 1.3031232357025146, "learning_rate": 0.00012876743573335734, "loss": 0.5689472675323486, "step": 247210 }, { "epoch": 1.4695270193959495, "grad_norm": 1.58433997631073, "learning_rate": 0.0001287613477607813, "loss": 0.6165437221527099, "step": 247220 }, { "epoch": 1.469586461472618, "grad_norm": 1.471068263053894, "learning_rate": 0.0001287552596984571, "loss": 0.5485766410827637, "step": 247230 }, { "epoch": 1.4696459035492864, "grad_norm": 1.6551661491394043, "learning_rate": 0.00012874917154641384, "loss": 0.5606509685516358, "step": 247240 }, { "epoch": 1.4697053456259548, "grad_norm": 1.4837535619735718, "learning_rate": 0.0001287430833046807, "loss": 0.5513636589050293, "step": 247250 }, { "epoch": 1.4697647877026232, "grad_norm": 1.280627727508545, "learning_rate": 0.0001287369949732868, "loss": 0.5908458709716797, "step": 247260 }, { "epoch": 1.4698242297792916, "grad_norm": 1.4715200662612915, "learning_rate": 0.00012873090655226118, "loss": 0.564179515838623, "step": 247270 }, { "epoch": 1.46988367185596, "grad_norm": 1.3800348043441772, "learning_rate": 0.00012872481804163309, "loss": 0.5832983016967773, "step": 247280 }, { "epoch": 1.4699431139326284, "grad_norm": 1.5892075300216675, "learning_rate": 0.00012871872944143152, "loss": 0.623403787612915, "step": 247290 }, { "epoch": 1.4700025560092969, "grad_norm": 1.4981470108032227, "learning_rate": 0.0001287126407516857, "loss": 0.6014694213867188, "step": 247300 }, { "epoch": 1.470061998085965, "grad_norm": 1.4603222608566284, "learning_rate": 0.00012870655197242474, "loss": 0.6214268684387207, "step": 247310 }, { "epoch": 1.4701214401626335, "grad_norm": 1.5845190286636353, "learning_rate": 0.0001287004631036777, "loss": 0.6248630046844482, "step": 247320 }, { "epoch": 1.4701808822393019, "grad_norm": 1.5292778015136719, "learning_rate": 0.0001286943741454738, "loss": 0.5850425720214844, "step": 247330 }, { "epoch": 1.4702403243159703, "grad_norm": 1.4046683311462402, "learning_rate": 0.00012868828509784213, "loss": 0.5937330722808838, "step": 247340 }, { "epoch": 1.4702997663926387, "grad_norm": 1.6844428777694702, "learning_rate": 0.00012868219596081176, "loss": 0.5496498107910156, "step": 247350 }, { "epoch": 1.4703592084693071, "grad_norm": 1.4396083354949951, "learning_rate": 0.00012867610673441193, "loss": 0.5388537883758545, "step": 247360 }, { "epoch": 1.4704186505459755, "grad_norm": 1.4947351217269897, "learning_rate": 0.00012867001741867168, "loss": 0.6067852020263672, "step": 247370 }, { "epoch": 1.4704780926226437, "grad_norm": 1.3368360996246338, "learning_rate": 0.00012866392801362016, "loss": 0.5766769409179687, "step": 247380 }, { "epoch": 1.4705375346993121, "grad_norm": 1.3384921550750732, "learning_rate": 0.00012865783851928652, "loss": 0.5607914447784423, "step": 247390 }, { "epoch": 1.4705969767759806, "grad_norm": 1.5616436004638672, "learning_rate": 0.00012865174893569986, "loss": 0.6050701141357422, "step": 247400 }, { "epoch": 1.470656418852649, "grad_norm": 1.2909990549087524, "learning_rate": 0.00012864565926288933, "loss": 0.5697011470794677, "step": 247410 }, { "epoch": 1.4707158609293174, "grad_norm": 1.6690608263015747, "learning_rate": 0.00012863956950088406, "loss": 0.6082756996154786, "step": 247420 }, { "epoch": 1.4707753030059858, "grad_norm": 1.4703713655471802, "learning_rate": 0.00012863347964971322, "loss": 0.6416119575500489, "step": 247430 }, { "epoch": 1.4708347450826542, "grad_norm": 1.7503485679626465, "learning_rate": 0.00012862738970940589, "loss": 0.6095409393310547, "step": 247440 }, { "epoch": 1.4708941871593226, "grad_norm": 1.429161787033081, "learning_rate": 0.00012862129967999118, "loss": 0.61485595703125, "step": 247450 }, { "epoch": 1.470953629235991, "grad_norm": 1.3905023336410522, "learning_rate": 0.00012861520956149828, "loss": 0.5875799655914307, "step": 247460 }, { "epoch": 1.4710130713126595, "grad_norm": 1.5900846719741821, "learning_rate": 0.0001286091193539563, "loss": 0.6420754432678223, "step": 247470 }, { "epoch": 1.4710725133893279, "grad_norm": 1.5470632314682007, "learning_rate": 0.00012860302905739438, "loss": 0.5540904045104981, "step": 247480 }, { "epoch": 1.4711319554659963, "grad_norm": 1.5807822942733765, "learning_rate": 0.00012859693867184162, "loss": 0.5767913341522217, "step": 247490 }, { "epoch": 1.4711913975426645, "grad_norm": 1.2779817581176758, "learning_rate": 0.00012859084819732722, "loss": 0.5692276954650879, "step": 247500 }, { "epoch": 1.471250839619333, "grad_norm": 1.2962579727172852, "learning_rate": 0.00012858475763388025, "loss": 0.5087207794189453, "step": 247510 }, { "epoch": 1.4713102816960013, "grad_norm": 1.8146989345550537, "learning_rate": 0.0001285786669815299, "loss": 0.6226264953613281, "step": 247520 }, { "epoch": 1.4713697237726697, "grad_norm": 1.550838589668274, "learning_rate": 0.00012857257624030526, "loss": 0.5513973236083984, "step": 247530 }, { "epoch": 1.4714291658493381, "grad_norm": 1.284699559211731, "learning_rate": 0.00012856648541023551, "loss": 0.5977195739746094, "step": 247540 }, { "epoch": 1.4714886079260066, "grad_norm": 1.342342734336853, "learning_rate": 0.00012856039449134972, "loss": 0.5987965106964112, "step": 247550 }, { "epoch": 1.471548050002675, "grad_norm": 1.7692574262619019, "learning_rate": 0.00012855430348367706, "loss": 0.6107704162597656, "step": 247560 }, { "epoch": 1.4716074920793432, "grad_norm": 2.043266534805298, "learning_rate": 0.00012854821238724674, "loss": 0.6140589714050293, "step": 247570 }, { "epoch": 1.4716669341560116, "grad_norm": 1.0015298128128052, "learning_rate": 0.0001285421212020878, "loss": 0.5806333541870117, "step": 247580 }, { "epoch": 1.47172637623268, "grad_norm": 1.1859687566757202, "learning_rate": 0.00012853602992822944, "loss": 0.620720386505127, "step": 247590 }, { "epoch": 1.4717858183093484, "grad_norm": 1.5561199188232422, "learning_rate": 0.0001285299385657007, "loss": 0.5782150745391845, "step": 247600 }, { "epoch": 1.4718452603860168, "grad_norm": 1.6634968519210815, "learning_rate": 0.00012852384711453085, "loss": 0.5552491188049317, "step": 247610 }, { "epoch": 1.4719047024626852, "grad_norm": 1.3478326797485352, "learning_rate": 0.00012851775557474896, "loss": 0.5542071342468262, "step": 247620 }, { "epoch": 1.4719641445393536, "grad_norm": 1.6429054737091064, "learning_rate": 0.00012851166394638414, "loss": 0.5617175102233887, "step": 247630 }, { "epoch": 1.472023586616022, "grad_norm": 1.3515456914901733, "learning_rate": 0.0001285055722294656, "loss": 0.591458797454834, "step": 247640 }, { "epoch": 1.4720830286926905, "grad_norm": 1.2991763353347778, "learning_rate": 0.00012849948042402247, "loss": 0.5638653755187988, "step": 247650 }, { "epoch": 1.472142470769359, "grad_norm": 1.22516930103302, "learning_rate": 0.00012849338853008382, "loss": 0.5511130809783935, "step": 247660 }, { "epoch": 1.4722019128460273, "grad_norm": 1.5608900785446167, "learning_rate": 0.00012848729654767887, "loss": 0.638424301147461, "step": 247670 }, { "epoch": 1.4722613549226955, "grad_norm": 1.6576025485992432, "learning_rate": 0.00012848120447683675, "loss": 0.5963692665100098, "step": 247680 }, { "epoch": 1.472320796999364, "grad_norm": 1.2676658630371094, "learning_rate": 0.00012847511231758657, "loss": 0.539877986907959, "step": 247690 }, { "epoch": 1.4723802390760323, "grad_norm": 1.3193689584732056, "learning_rate": 0.0001284690200699575, "loss": 0.5408303737640381, "step": 247700 }, { "epoch": 1.4724396811527007, "grad_norm": 1.950875163078308, "learning_rate": 0.00012846292773397867, "loss": 0.6356517314910889, "step": 247710 }, { "epoch": 1.4724991232293692, "grad_norm": 1.6175590753555298, "learning_rate": 0.00012845683530967925, "loss": 0.6313661575317383, "step": 247720 }, { "epoch": 1.4725585653060376, "grad_norm": 1.4465947151184082, "learning_rate": 0.0001284507427970883, "loss": 0.5602522850036621, "step": 247730 }, { "epoch": 1.472618007382706, "grad_norm": 1.6809171438217163, "learning_rate": 0.0001284446501962351, "loss": 0.5900453567504883, "step": 247740 }, { "epoch": 1.4726774494593742, "grad_norm": 1.6049659252166748, "learning_rate": 0.00012843855750714866, "loss": 0.621183967590332, "step": 247750 }, { "epoch": 1.4727368915360426, "grad_norm": 1.187485694885254, "learning_rate": 0.0001284324647298582, "loss": 0.5574797630310059, "step": 247760 }, { "epoch": 1.472796333612711, "grad_norm": 1.5668781995773315, "learning_rate": 0.0001284263718643929, "loss": 0.5597375869750977, "step": 247770 }, { "epoch": 1.4728557756893794, "grad_norm": 1.9202916622161865, "learning_rate": 0.0001284202789107818, "loss": 0.6599561691284179, "step": 247780 }, { "epoch": 1.4729152177660478, "grad_norm": 1.75749671459198, "learning_rate": 0.00012841418586905412, "loss": 0.5652607917785645, "step": 247790 }, { "epoch": 1.4729746598427162, "grad_norm": 1.4669432640075684, "learning_rate": 0.00012840809273923903, "loss": 0.564921522140503, "step": 247800 }, { "epoch": 1.4730341019193847, "grad_norm": 1.2233242988586426, "learning_rate": 0.0001284019995213656, "loss": 0.5668045520782471, "step": 247810 }, { "epoch": 1.473093543996053, "grad_norm": 1.671027421951294, "learning_rate": 0.000128395906215463, "loss": 0.5992316246032715, "step": 247820 }, { "epoch": 1.4731529860727215, "grad_norm": 1.4020581245422363, "learning_rate": 0.00012838981282156046, "loss": 0.6214814186096191, "step": 247830 }, { "epoch": 1.47321242814939, "grad_norm": 1.6743634939193726, "learning_rate": 0.00012838371933968703, "loss": 0.6082648277282715, "step": 247840 }, { "epoch": 1.4732718702260583, "grad_norm": 1.5304734706878662, "learning_rate": 0.0001283776257698719, "loss": 0.6075417041778565, "step": 247850 }, { "epoch": 1.4733313123027267, "grad_norm": 1.9734588861465454, "learning_rate": 0.0001283715321121442, "loss": 0.6261857986450196, "step": 247860 }, { "epoch": 1.473390754379395, "grad_norm": 1.3500006198883057, "learning_rate": 0.0001283654383665331, "loss": 0.6252681732177734, "step": 247870 }, { "epoch": 1.4734501964560633, "grad_norm": 1.407477855682373, "learning_rate": 0.00012835934453306775, "loss": 0.5399741649627685, "step": 247880 }, { "epoch": 1.4735096385327318, "grad_norm": 1.7363808155059814, "learning_rate": 0.0001283532506117773, "loss": 0.6092949867248535, "step": 247890 }, { "epoch": 1.4735690806094002, "grad_norm": 1.668837308883667, "learning_rate": 0.00012834715660269092, "loss": 0.5895257949829101, "step": 247900 }, { "epoch": 1.4736285226860686, "grad_norm": 1.263535737991333, "learning_rate": 0.0001283410625058377, "loss": 0.5220489501953125, "step": 247910 }, { "epoch": 1.473687964762737, "grad_norm": 1.4122145175933838, "learning_rate": 0.00012833496832124683, "loss": 0.5910804748535157, "step": 247920 }, { "epoch": 1.4737474068394054, "grad_norm": 1.692896842956543, "learning_rate": 0.00012832887404894746, "loss": 0.6278810024261474, "step": 247930 }, { "epoch": 1.4738068489160736, "grad_norm": 1.4747505187988281, "learning_rate": 0.00012832277968896877, "loss": 0.5853652954101562, "step": 247940 }, { "epoch": 1.473866290992742, "grad_norm": 1.5956794023513794, "learning_rate": 0.0001283166852413399, "loss": 0.5717761039733886, "step": 247950 }, { "epoch": 1.4739257330694104, "grad_norm": 1.4625622034072876, "learning_rate": 0.00012831059070608994, "loss": 0.5754482269287109, "step": 247960 }, { "epoch": 1.4739851751460789, "grad_norm": 1.470258116722107, "learning_rate": 0.00012830449608324814, "loss": 0.5347970485687256, "step": 247970 }, { "epoch": 1.4740446172227473, "grad_norm": 1.4102782011032104, "learning_rate": 0.00012829840137284362, "loss": 0.5931994438171386, "step": 247980 }, { "epoch": 1.4741040592994157, "grad_norm": 1.2143443822860718, "learning_rate": 0.00012829230657490553, "loss": 0.5971517086029052, "step": 247990 }, { "epoch": 1.474163501376084, "grad_norm": 1.5265588760375977, "learning_rate": 0.00012828621168946297, "loss": 0.5466951370239258, "step": 248000 }, { "epoch": 1.4742229434527525, "grad_norm": 1.582626461982727, "learning_rate": 0.0001282801167165452, "loss": 0.5479174613952636, "step": 248010 }, { "epoch": 1.474282385529421, "grad_norm": 1.8585284948349, "learning_rate": 0.00012827402165618132, "loss": 0.5977028846740723, "step": 248020 }, { "epoch": 1.4743418276060893, "grad_norm": 1.5644491910934448, "learning_rate": 0.0001282679265084005, "loss": 0.6152175903320313, "step": 248030 }, { "epoch": 1.4744012696827578, "grad_norm": 1.7379645109176636, "learning_rate": 0.00012826183127323185, "loss": 0.6066055297851562, "step": 248040 }, { "epoch": 1.474460711759426, "grad_norm": 1.6306020021438599, "learning_rate": 0.0001282557359507046, "loss": 0.6146388530731202, "step": 248050 }, { "epoch": 1.4745201538360944, "grad_norm": 1.6099658012390137, "learning_rate": 0.00012824964054084786, "loss": 0.532017707824707, "step": 248060 }, { "epoch": 1.4745795959127628, "grad_norm": 1.8431646823883057, "learning_rate": 0.00012824354504369082, "loss": 0.6195193290710449, "step": 248070 }, { "epoch": 1.4746390379894312, "grad_norm": 1.4953315258026123, "learning_rate": 0.00012823744945926263, "loss": 0.6112172126770019, "step": 248080 }, { "epoch": 1.4746984800660996, "grad_norm": 1.5946546792984009, "learning_rate": 0.0001282313537875924, "loss": 0.6178651809692383, "step": 248090 }, { "epoch": 1.474757922142768, "grad_norm": 1.1489661931991577, "learning_rate": 0.00012822525802870933, "loss": 0.6021482467651367, "step": 248100 }, { "epoch": 1.4748173642194364, "grad_norm": 1.9728854894638062, "learning_rate": 0.00012821916218264264, "loss": 0.6071992874145508, "step": 248110 }, { "epoch": 1.4748768062961046, "grad_norm": 1.4241139888763428, "learning_rate": 0.00012821306624942138, "loss": 0.5843608856201172, "step": 248120 }, { "epoch": 1.474936248372773, "grad_norm": 1.6085727214813232, "learning_rate": 0.00012820697022907483, "loss": 0.5880587100982666, "step": 248130 }, { "epoch": 1.4749956904494415, "grad_norm": 1.7079249620437622, "learning_rate": 0.000128200874121632, "loss": 0.6314566612243653, "step": 248140 }, { "epoch": 1.4750551325261099, "grad_norm": 1.378487229347229, "learning_rate": 0.00012819477792712217, "loss": 0.6329154014587403, "step": 248150 }, { "epoch": 1.4751145746027783, "grad_norm": 1.339822769165039, "learning_rate": 0.00012818868164557446, "loss": 0.631419563293457, "step": 248160 }, { "epoch": 1.4751740166794467, "grad_norm": 1.4449005126953125, "learning_rate": 0.00012818258527701808, "loss": 0.7065788269042969, "step": 248170 }, { "epoch": 1.4752334587561151, "grad_norm": 1.311876654624939, "learning_rate": 0.00012817648882148213, "loss": 0.5586077690124511, "step": 248180 }, { "epoch": 1.4752929008327835, "grad_norm": 1.5405596494674683, "learning_rate": 0.0001281703922789958, "loss": 0.5591329574584961, "step": 248190 }, { "epoch": 1.475352342909452, "grad_norm": 1.9282158613204956, "learning_rate": 0.00012816429564958825, "loss": 0.5611542701721192, "step": 248200 }, { "epoch": 1.4754117849861204, "grad_norm": 1.4128345251083374, "learning_rate": 0.00012815819893328864, "loss": 0.6055588722229004, "step": 248210 }, { "epoch": 1.4754712270627888, "grad_norm": 1.3250200748443604, "learning_rate": 0.00012815210213012614, "loss": 0.5709278583526611, "step": 248220 }, { "epoch": 1.4755306691394572, "grad_norm": 1.6369223594665527, "learning_rate": 0.0001281460052401299, "loss": 0.5706307888031006, "step": 248230 }, { "epoch": 1.4755901112161254, "grad_norm": 1.3781105279922485, "learning_rate": 0.00012813990826332914, "loss": 0.5927021503448486, "step": 248240 }, { "epoch": 1.4756495532927938, "grad_norm": 1.4468365907669067, "learning_rate": 0.00012813381119975296, "loss": 0.5813747406005859, "step": 248250 }, { "epoch": 1.4757089953694622, "grad_norm": 1.5971579551696777, "learning_rate": 0.00012812771404943055, "loss": 0.5623414039611816, "step": 248260 }, { "epoch": 1.4757684374461306, "grad_norm": 1.4714418649673462, "learning_rate": 0.0001281216168123911, "loss": 0.6579165458679199, "step": 248270 }, { "epoch": 1.475827879522799, "grad_norm": 1.3251895904541016, "learning_rate": 0.00012811551948866374, "loss": 0.6030136585235596, "step": 248280 }, { "epoch": 1.4758873215994674, "grad_norm": 1.4800022840499878, "learning_rate": 0.00012810942207827769, "loss": 0.6263177871704102, "step": 248290 }, { "epoch": 1.4759467636761359, "grad_norm": 1.5241200923919678, "learning_rate": 0.00012810332458126203, "loss": 0.5954625606536865, "step": 248300 }, { "epoch": 1.476006205752804, "grad_norm": 2.0087828636169434, "learning_rate": 0.000128097226997646, "loss": 0.5334862232208252, "step": 248310 }, { "epoch": 1.4760656478294725, "grad_norm": 1.7330831289291382, "learning_rate": 0.00012809112932745878, "loss": 0.5823522567749023, "step": 248320 }, { "epoch": 1.4761250899061409, "grad_norm": 1.33125901222229, "learning_rate": 0.0001280850315707295, "loss": 0.5591768741607666, "step": 248330 }, { "epoch": 1.4761845319828093, "grad_norm": 1.3619225025177002, "learning_rate": 0.0001280789337274873, "loss": 0.5792536735534668, "step": 248340 }, { "epoch": 1.4762439740594777, "grad_norm": 1.6372363567352295, "learning_rate": 0.00012807283579776145, "loss": 0.5984135627746582, "step": 248350 }, { "epoch": 1.4763034161361461, "grad_norm": 1.407811164855957, "learning_rate": 0.000128066737781581, "loss": 0.5851457595825196, "step": 248360 }, { "epoch": 1.4763628582128145, "grad_norm": 1.592789888381958, "learning_rate": 0.00012806063967897523, "loss": 0.6005195617675781, "step": 248370 }, { "epoch": 1.476422300289483, "grad_norm": 1.757205605506897, "learning_rate": 0.00012805454148997323, "loss": 0.5657258033752441, "step": 248380 }, { "epoch": 1.4764817423661514, "grad_norm": 1.4290101528167725, "learning_rate": 0.0001280484432146042, "loss": 0.5569924354553223, "step": 248390 }, { "epoch": 1.4765411844428198, "grad_norm": 1.7501637935638428, "learning_rate": 0.00012804234485289736, "loss": 0.6265471458435059, "step": 248400 }, { "epoch": 1.4766006265194882, "grad_norm": 1.698190689086914, "learning_rate": 0.00012803624640488176, "loss": 0.6002919197082519, "step": 248410 }, { "epoch": 1.4766600685961564, "grad_norm": 1.7660558223724365, "learning_rate": 0.0001280301478705867, "loss": 0.6029771327972412, "step": 248420 }, { "epoch": 1.4767195106728248, "grad_norm": 1.4052298069000244, "learning_rate": 0.0001280240492500413, "loss": 0.6081836700439454, "step": 248430 }, { "epoch": 1.4767789527494932, "grad_norm": 1.500475525856018, "learning_rate": 0.00012801795054327478, "loss": 0.5533377647399902, "step": 248440 }, { "epoch": 1.4768383948261616, "grad_norm": 1.1253607273101807, "learning_rate": 0.0001280118517503162, "loss": 0.5865337371826171, "step": 248450 }, { "epoch": 1.47689783690283, "grad_norm": 1.268776774406433, "learning_rate": 0.00012800575287119485, "loss": 0.604886245727539, "step": 248460 }, { "epoch": 1.4769572789794985, "grad_norm": 1.21562659740448, "learning_rate": 0.00012799965390593985, "loss": 0.5421009063720703, "step": 248470 }, { "epoch": 1.4770167210561669, "grad_norm": 1.7444651126861572, "learning_rate": 0.00012799355485458043, "loss": 0.5389714717864991, "step": 248480 }, { "epoch": 1.477076163132835, "grad_norm": 2.046015977859497, "learning_rate": 0.00012798745571714567, "loss": 0.546535587310791, "step": 248490 }, { "epoch": 1.4771356052095035, "grad_norm": 1.5679752826690674, "learning_rate": 0.0001279813564936648, "loss": 0.6029851913452149, "step": 248500 }, { "epoch": 1.477195047286172, "grad_norm": 1.7345598936080933, "learning_rate": 0.00012797525718416704, "loss": 0.6069523334503174, "step": 248510 }, { "epoch": 1.4772544893628403, "grad_norm": 1.5795406103134155, "learning_rate": 0.00012796915778868147, "loss": 0.5626543998718262, "step": 248520 }, { "epoch": 1.4773139314395087, "grad_norm": 1.662461519241333, "learning_rate": 0.00012796305830723736, "loss": 0.5936039924621582, "step": 248530 }, { "epoch": 1.4773733735161771, "grad_norm": 1.6706160306930542, "learning_rate": 0.00012795695873986385, "loss": 0.5931863784790039, "step": 248540 }, { "epoch": 1.4774328155928456, "grad_norm": 1.2749316692352295, "learning_rate": 0.0001279508590865901, "loss": 0.5374302387237548, "step": 248550 }, { "epoch": 1.477492257669514, "grad_norm": 1.3686295747756958, "learning_rate": 0.0001279447593474453, "loss": 0.6005568027496337, "step": 248560 }, { "epoch": 1.4775516997461824, "grad_norm": 1.513593077659607, "learning_rate": 0.00012793865952245867, "loss": 0.5736634731292725, "step": 248570 }, { "epoch": 1.4776111418228508, "grad_norm": 1.6483087539672852, "learning_rate": 0.00012793255961165932, "loss": 0.5359491348266602, "step": 248580 }, { "epoch": 1.4776705838995192, "grad_norm": 1.5884897708892822, "learning_rate": 0.0001279264596150765, "loss": 0.6205614089965821, "step": 248590 }, { "epoch": 1.4777300259761876, "grad_norm": 1.6515802145004272, "learning_rate": 0.00012792035953273934, "loss": 0.559663200378418, "step": 248600 }, { "epoch": 1.4777894680528558, "grad_norm": 1.291519284248352, "learning_rate": 0.000127914259364677, "loss": 0.6583191871643066, "step": 248610 }, { "epoch": 1.4778489101295242, "grad_norm": 1.7600075006484985, "learning_rate": 0.00012790815911091873, "loss": 0.5796120643615723, "step": 248620 }, { "epoch": 1.4779083522061927, "grad_norm": 1.9229776859283447, "learning_rate": 0.0001279020587714937, "loss": 0.6206657886505127, "step": 248630 }, { "epoch": 1.477967794282861, "grad_norm": 1.376442313194275, "learning_rate": 0.00012789595834643102, "loss": 0.6126761436462402, "step": 248640 }, { "epoch": 1.4780272363595295, "grad_norm": 1.4606444835662842, "learning_rate": 0.00012788985783575998, "loss": 0.5544416427612304, "step": 248650 }, { "epoch": 1.478086678436198, "grad_norm": 1.0921196937561035, "learning_rate": 0.00012788375723950967, "loss": 0.599283504486084, "step": 248660 }, { "epoch": 1.4781461205128663, "grad_norm": 1.5508174896240234, "learning_rate": 0.0001278776565577093, "loss": 0.592093563079834, "step": 248670 }, { "epoch": 1.4782055625895345, "grad_norm": 2.0224521160125732, "learning_rate": 0.0001278715557903881, "loss": 0.5988346099853515, "step": 248680 }, { "epoch": 1.478265004666203, "grad_norm": 1.3830839395523071, "learning_rate": 0.0001278654549375752, "loss": 0.5988987922668457, "step": 248690 }, { "epoch": 1.4783244467428713, "grad_norm": 1.2395154237747192, "learning_rate": 0.00012785935399929981, "loss": 0.567585563659668, "step": 248700 }, { "epoch": 1.4783838888195397, "grad_norm": 1.5837031602859497, "learning_rate": 0.0001278532529755911, "loss": 0.5311488151550293, "step": 248710 }, { "epoch": 1.4784433308962082, "grad_norm": 1.2676981687545776, "learning_rate": 0.00012784715186647827, "loss": 0.6084513187408447, "step": 248720 }, { "epoch": 1.4785027729728766, "grad_norm": 1.4503518342971802, "learning_rate": 0.0001278410506719905, "loss": 0.6049753189086914, "step": 248730 }, { "epoch": 1.478562215049545, "grad_norm": 1.6425913572311401, "learning_rate": 0.00012783494939215694, "loss": 0.5634310245513916, "step": 248740 }, { "epoch": 1.4786216571262134, "grad_norm": 1.2724608182907104, "learning_rate": 0.00012782884802700685, "loss": 0.5895412921905517, "step": 248750 }, { "epoch": 1.4786810992028818, "grad_norm": 1.9055827856063843, "learning_rate": 0.00012782274657656938, "loss": 0.610737419128418, "step": 248760 }, { "epoch": 1.4787405412795502, "grad_norm": 1.974750280380249, "learning_rate": 0.00012781664504087369, "loss": 0.5887481689453125, "step": 248770 }, { "epoch": 1.4787999833562187, "grad_norm": 1.4605532884597778, "learning_rate": 0.00012781054341994897, "loss": 0.6009373664855957, "step": 248780 }, { "epoch": 1.4788594254328868, "grad_norm": 1.4428666830062866, "learning_rate": 0.00012780444171382445, "loss": 0.60550537109375, "step": 248790 }, { "epoch": 1.4789188675095553, "grad_norm": 1.6630700826644897, "learning_rate": 0.00012779833992252935, "loss": 0.6076181411743165, "step": 248800 }, { "epoch": 1.4789783095862237, "grad_norm": 1.5522658824920654, "learning_rate": 0.00012779223804609274, "loss": 0.5745918273925781, "step": 248810 }, { "epoch": 1.479037751662892, "grad_norm": 2.017178535461426, "learning_rate": 0.00012778613608454393, "loss": 0.5965646743774414, "step": 248820 }, { "epoch": 1.4790971937395605, "grad_norm": 1.5610417127609253, "learning_rate": 0.00012778003403791203, "loss": 0.5926555156707763, "step": 248830 }, { "epoch": 1.479156635816229, "grad_norm": 1.4996602535247803, "learning_rate": 0.00012777393190622623, "loss": 0.5290534019470214, "step": 248840 }, { "epoch": 1.4792160778928973, "grad_norm": 1.1598222255706787, "learning_rate": 0.0001277678296895158, "loss": 0.5487212657928466, "step": 248850 }, { "epoch": 1.4792755199695655, "grad_norm": 1.4763790369033813, "learning_rate": 0.00012776172738780987, "loss": 0.5813543319702148, "step": 248860 }, { "epoch": 1.479334962046234, "grad_norm": 1.4159293174743652, "learning_rate": 0.00012775562500113764, "loss": 0.6026630401611328, "step": 248870 }, { "epoch": 1.4793944041229024, "grad_norm": 1.181475043296814, "learning_rate": 0.0001277495225295283, "loss": 0.6034260272979737, "step": 248880 }, { "epoch": 1.4794538461995708, "grad_norm": 1.4734388589859009, "learning_rate": 0.00012774341997301103, "loss": 0.5638153076171875, "step": 248890 }, { "epoch": 1.4795132882762392, "grad_norm": 1.211545705795288, "learning_rate": 0.00012773731733161503, "loss": 0.513951587677002, "step": 248900 }, { "epoch": 1.4795727303529076, "grad_norm": 1.620883822441101, "learning_rate": 0.00012773121460536954, "loss": 0.5484040260314942, "step": 248910 }, { "epoch": 1.479632172429576, "grad_norm": 1.4378634691238403, "learning_rate": 0.00012772511179430366, "loss": 0.5429612159729004, "step": 248920 }, { "epoch": 1.4796916145062444, "grad_norm": 1.6635594367980957, "learning_rate": 0.0001277190088984467, "loss": 0.6428977966308593, "step": 248930 }, { "epoch": 1.4797510565829128, "grad_norm": 1.207027554512024, "learning_rate": 0.00012771290591782775, "loss": 0.49103198051452634, "step": 248940 }, { "epoch": 1.4798104986595813, "grad_norm": 1.1490850448608398, "learning_rate": 0.00012770680285247602, "loss": 0.5714526653289795, "step": 248950 }, { "epoch": 1.4798699407362497, "grad_norm": 1.7973859310150146, "learning_rate": 0.0001277006997024208, "loss": 0.6019293785095214, "step": 248960 }, { "epoch": 1.479929382812918, "grad_norm": 1.4849568605422974, "learning_rate": 0.00012769459646769118, "loss": 0.5977828979492188, "step": 248970 }, { "epoch": 1.4799888248895863, "grad_norm": 1.6302599906921387, "learning_rate": 0.0001276884931483164, "loss": 0.6154202461242676, "step": 248980 }, { "epoch": 1.4800482669662547, "grad_norm": 2.0405492782592773, "learning_rate": 0.00012768238974432565, "loss": 0.6139788627624512, "step": 248990 }, { "epoch": 1.480107709042923, "grad_norm": 1.5206553936004639, "learning_rate": 0.00012767628625574812, "loss": 0.5467319488525391, "step": 249000 }, { "epoch": 1.4801671511195915, "grad_norm": 1.3941017389297485, "learning_rate": 0.00012767018268261302, "loss": 0.544278335571289, "step": 249010 }, { "epoch": 1.48022659319626, "grad_norm": 1.5696934461593628, "learning_rate": 0.00012766407902494952, "loss": 0.5960765838623047, "step": 249020 }, { "epoch": 1.4802860352729283, "grad_norm": 1.3240340948104858, "learning_rate": 0.00012765797528278686, "loss": 0.6129589080810547, "step": 249030 }, { "epoch": 1.4803454773495968, "grad_norm": 1.7231671810150146, "learning_rate": 0.00012765187145615423, "loss": 0.6377347946166992, "step": 249040 }, { "epoch": 1.480404919426265, "grad_norm": 1.2154231071472168, "learning_rate": 0.00012764576754508079, "loss": 0.5165311813354492, "step": 249050 }, { "epoch": 1.4804643615029334, "grad_norm": 1.5983004570007324, "learning_rate": 0.0001276396635495958, "loss": 0.5068274021148682, "step": 249060 }, { "epoch": 1.4805238035796018, "grad_norm": 1.3544509410858154, "learning_rate": 0.00012763355946972837, "loss": 0.5671005249023438, "step": 249070 }, { "epoch": 1.4805832456562702, "grad_norm": 1.527294635772705, "learning_rate": 0.00012762745530550776, "loss": 0.5971920013427734, "step": 249080 }, { "epoch": 1.4806426877329386, "grad_norm": 1.4398362636566162, "learning_rate": 0.00012762135105696325, "loss": 0.6151134490966796, "step": 249090 }, { "epoch": 1.480702129809607, "grad_norm": 1.8309892416000366, "learning_rate": 0.00012761524672412386, "loss": 0.5980957984924317, "step": 249100 }, { "epoch": 1.4807615718862754, "grad_norm": 1.3287546634674072, "learning_rate": 0.00012760914230701892, "loss": 0.6258614540100098, "step": 249110 }, { "epoch": 1.4808210139629439, "grad_norm": 1.6481977701187134, "learning_rate": 0.00012760303780567762, "loss": 0.5875654220581055, "step": 249120 }, { "epoch": 1.4808804560396123, "grad_norm": 1.6357685327529907, "learning_rate": 0.00012759693322012908, "loss": 0.5708459854125977, "step": 249130 }, { "epoch": 1.4809398981162807, "grad_norm": 1.674683928489685, "learning_rate": 0.00012759082855040262, "loss": 0.5907576560974122, "step": 249140 }, { "epoch": 1.480999340192949, "grad_norm": 1.548209547996521, "learning_rate": 0.00012758472379652738, "loss": 0.6136232376098633, "step": 249150 }, { "epoch": 1.4810587822696173, "grad_norm": 1.4550609588623047, "learning_rate": 0.0001275786189585325, "loss": 0.6020594120025635, "step": 249160 }, { "epoch": 1.4811182243462857, "grad_norm": 1.2319374084472656, "learning_rate": 0.0001275725140364473, "loss": 0.5806036949157715, "step": 249170 }, { "epoch": 1.4811776664229541, "grad_norm": 1.4591079950332642, "learning_rate": 0.00012756640903030097, "loss": 0.560380220413208, "step": 249180 }, { "epoch": 1.4812371084996225, "grad_norm": 1.168685793876648, "learning_rate": 0.00012756030394012267, "loss": 0.5707294464111328, "step": 249190 }, { "epoch": 1.481296550576291, "grad_norm": 1.7972830533981323, "learning_rate": 0.00012755419876594158, "loss": 0.5856282234191894, "step": 249200 }, { "epoch": 1.4813559926529594, "grad_norm": 1.719190239906311, "learning_rate": 0.00012754809350778697, "loss": 0.6183489799499512, "step": 249210 }, { "epoch": 1.4814154347296278, "grad_norm": 1.9852631092071533, "learning_rate": 0.00012754198816568798, "loss": 0.6431653499603271, "step": 249220 }, { "epoch": 1.481474876806296, "grad_norm": 1.4753321409225464, "learning_rate": 0.00012753588273967388, "loss": 0.5839596748352051, "step": 249230 }, { "epoch": 1.4815343188829644, "grad_norm": 1.5667158365249634, "learning_rate": 0.00012752977722977385, "loss": 0.6082930088043212, "step": 249240 }, { "epoch": 1.4815937609596328, "grad_norm": 1.6416181325912476, "learning_rate": 0.00012752367163601706, "loss": 0.5967069149017334, "step": 249250 }, { "epoch": 1.4816532030363012, "grad_norm": 1.5226237773895264, "learning_rate": 0.0001275175659584328, "loss": 0.5857943534851074, "step": 249260 }, { "epoch": 1.4817126451129696, "grad_norm": 1.5197645425796509, "learning_rate": 0.0001275114601970502, "loss": 0.5943773269653321, "step": 249270 }, { "epoch": 1.481772087189638, "grad_norm": 1.7845258712768555, "learning_rate": 0.00012750535435189847, "loss": 0.5682926654815674, "step": 249280 }, { "epoch": 1.4818315292663065, "grad_norm": 1.6923342943191528, "learning_rate": 0.0001274992484230069, "loss": 0.5463333129882812, "step": 249290 }, { "epoch": 1.4818909713429749, "grad_norm": 1.7126630544662476, "learning_rate": 0.0001274931424104046, "loss": 0.598333740234375, "step": 249300 }, { "epoch": 1.4819504134196433, "grad_norm": 1.3465784788131714, "learning_rate": 0.00012748703631412084, "loss": 0.5232418060302735, "step": 249310 }, { "epoch": 1.4820098554963117, "grad_norm": 1.5611399412155151, "learning_rate": 0.00012748093013418486, "loss": 0.637790584564209, "step": 249320 }, { "epoch": 1.4820692975729801, "grad_norm": 1.565563678741455, "learning_rate": 0.00012747482387062573, "loss": 0.5681808471679688, "step": 249330 }, { "epoch": 1.4821287396496485, "grad_norm": 1.6404743194580078, "learning_rate": 0.00012746871752347281, "loss": 0.6126015663146973, "step": 249340 }, { "epoch": 1.4821881817263167, "grad_norm": 1.4455187320709229, "learning_rate": 0.0001274626110927553, "loss": 0.530486011505127, "step": 249350 }, { "epoch": 1.4822476238029851, "grad_norm": 1.3592817783355713, "learning_rate": 0.00012745650457850227, "loss": 0.5957986831665039, "step": 249360 }, { "epoch": 1.4823070658796536, "grad_norm": 1.444158673286438, "learning_rate": 0.0001274503979807431, "loss": 0.551377820968628, "step": 249370 }, { "epoch": 1.482366507956322, "grad_norm": 1.6694550514221191, "learning_rate": 0.0001274442912995069, "loss": 0.5891283988952637, "step": 249380 }, { "epoch": 1.4824259500329904, "grad_norm": 1.372678518295288, "learning_rate": 0.00012743818453482287, "loss": 0.591489601135254, "step": 249390 }, { "epoch": 1.4824853921096588, "grad_norm": 1.5782252550125122, "learning_rate": 0.00012743207768672033, "loss": 0.5923379898071289, "step": 249400 }, { "epoch": 1.4825448341863272, "grad_norm": 1.3429757356643677, "learning_rate": 0.0001274259707552284, "loss": 0.5329891681671143, "step": 249410 }, { "epoch": 1.4826042762629954, "grad_norm": 1.6668769121170044, "learning_rate": 0.00012741986374037632, "loss": 0.5130552291870117, "step": 249420 }, { "epoch": 1.4826637183396638, "grad_norm": 1.5636954307556152, "learning_rate": 0.0001274137566421933, "loss": 0.5716980934143067, "step": 249430 }, { "epoch": 1.4827231604163322, "grad_norm": 1.422379493713379, "learning_rate": 0.00012740764946070856, "loss": 0.5718668937683106, "step": 249440 }, { "epoch": 1.4827826024930006, "grad_norm": 1.5806912183761597, "learning_rate": 0.00012740154219595133, "loss": 0.527485990524292, "step": 249450 }, { "epoch": 1.482842044569669, "grad_norm": 1.4820424318313599, "learning_rate": 0.0001273954348479508, "loss": 0.6336913108825684, "step": 249460 }, { "epoch": 1.4829014866463375, "grad_norm": 1.0937976837158203, "learning_rate": 0.00012738932741673622, "loss": 0.5697845458984375, "step": 249470 }, { "epoch": 1.4829609287230059, "grad_norm": 1.387062430381775, "learning_rate": 0.00012738321990233672, "loss": 0.6113790512084961, "step": 249480 }, { "epoch": 1.4830203707996743, "grad_norm": 1.5056133270263672, "learning_rate": 0.00012737711230478163, "loss": 0.5774231910705566, "step": 249490 }, { "epoch": 1.4830798128763427, "grad_norm": 1.4593912363052368, "learning_rate": 0.0001273710046241001, "loss": 0.5252964973449707, "step": 249500 }, { "epoch": 1.4831392549530111, "grad_norm": 1.4301345348358154, "learning_rate": 0.00012736489686032134, "loss": 0.5948345184326171, "step": 249510 }, { "epoch": 1.4831986970296795, "grad_norm": 1.9102705717086792, "learning_rate": 0.0001273587890134746, "loss": 0.6227708339691163, "step": 249520 }, { "epoch": 1.4832581391063477, "grad_norm": 1.6735118627548218, "learning_rate": 0.00012735268108358911, "loss": 0.6245683193206787, "step": 249530 }, { "epoch": 1.4833175811830162, "grad_norm": 1.286241054534912, "learning_rate": 0.00012734657307069403, "loss": 0.5956557750701904, "step": 249540 }, { "epoch": 1.4833770232596846, "grad_norm": 1.4317108392715454, "learning_rate": 0.00012734046497481861, "loss": 0.5721524715423584, "step": 249550 }, { "epoch": 1.483436465336353, "grad_norm": 1.6622406244277954, "learning_rate": 0.00012733435679599214, "loss": 0.6062692642211914, "step": 249560 }, { "epoch": 1.4834959074130214, "grad_norm": 1.432801365852356, "learning_rate": 0.00012732824853424368, "loss": 0.5827160835266113, "step": 249570 }, { "epoch": 1.4835553494896898, "grad_norm": 1.5196224451065063, "learning_rate": 0.0001273221401896026, "loss": 0.5404573917388916, "step": 249580 }, { "epoch": 1.4836147915663582, "grad_norm": 1.5135223865509033, "learning_rate": 0.00012731603176209806, "loss": 0.6440599441528321, "step": 249590 }, { "epoch": 1.4836742336430264, "grad_norm": 1.6997429132461548, "learning_rate": 0.0001273099232517593, "loss": 0.6273022651672363, "step": 249600 }, { "epoch": 1.4837336757196948, "grad_norm": 1.4077388048171997, "learning_rate": 0.00012730381465861544, "loss": 0.5344184875488281, "step": 249610 }, { "epoch": 1.4837931177963632, "grad_norm": 1.3124926090240479, "learning_rate": 0.00012729770598269587, "loss": 0.5927428245544434, "step": 249620 }, { "epoch": 1.4838525598730317, "grad_norm": 1.2817540168762207, "learning_rate": 0.00012729159722402967, "loss": 0.5813309669494628, "step": 249630 }, { "epoch": 1.4839120019497, "grad_norm": 1.3282294273376465, "learning_rate": 0.00012728548838264619, "loss": 0.6518322944641113, "step": 249640 }, { "epoch": 1.4839714440263685, "grad_norm": 1.667392611503601, "learning_rate": 0.00012727937945857453, "loss": 0.5932287216186524, "step": 249650 }, { "epoch": 1.484030886103037, "grad_norm": 1.5487884283065796, "learning_rate": 0.00012727327045184396, "loss": 0.6102353096008301, "step": 249660 }, { "epoch": 1.4840903281797053, "grad_norm": 1.6762089729309082, "learning_rate": 0.00012726716136248373, "loss": 0.62598557472229, "step": 249670 }, { "epoch": 1.4841497702563737, "grad_norm": 1.27946138381958, "learning_rate": 0.00012726105219052305, "loss": 0.609735107421875, "step": 249680 }, { "epoch": 1.4842092123330421, "grad_norm": 1.7818171977996826, "learning_rate": 0.0001272549429359911, "loss": 0.6082765579223632, "step": 249690 }, { "epoch": 1.4842686544097106, "grad_norm": 1.4579732418060303, "learning_rate": 0.0001272488335989172, "loss": 0.5902767181396484, "step": 249700 }, { "epoch": 1.484328096486379, "grad_norm": 1.4173122644424438, "learning_rate": 0.00012724272417933047, "loss": 0.6160077095031739, "step": 249710 }, { "epoch": 1.4843875385630472, "grad_norm": 1.507430076599121, "learning_rate": 0.00012723661467726018, "loss": 0.5473142147064209, "step": 249720 }, { "epoch": 1.4844469806397156, "grad_norm": 1.3122053146362305, "learning_rate": 0.00012723050509273558, "loss": 0.5459604263305664, "step": 249730 }, { "epoch": 1.484506422716384, "grad_norm": 1.6633543968200684, "learning_rate": 0.00012722439542578587, "loss": 0.5843441009521484, "step": 249740 }, { "epoch": 1.4845658647930524, "grad_norm": 1.394273281097412, "learning_rate": 0.00012721828567644028, "loss": 0.6445786476135253, "step": 249750 }, { "epoch": 1.4846253068697208, "grad_norm": 1.2720155715942383, "learning_rate": 0.00012721217584472805, "loss": 0.6093270301818847, "step": 249760 }, { "epoch": 1.4846847489463892, "grad_norm": 1.1538764238357544, "learning_rate": 0.00012720606593067836, "loss": 0.5302613258361817, "step": 249770 }, { "epoch": 1.4847441910230577, "grad_norm": 1.618076205253601, "learning_rate": 0.0001271999559343205, "loss": 0.5876418590545655, "step": 249780 }, { "epoch": 1.4848036330997259, "grad_norm": 1.3624262809753418, "learning_rate": 0.00012719384585568367, "loss": 0.5268608093261719, "step": 249790 }, { "epoch": 1.4848630751763943, "grad_norm": 1.4420580863952637, "learning_rate": 0.00012718773569479712, "loss": 0.5601900577545166, "step": 249800 }, { "epoch": 1.4849225172530627, "grad_norm": 1.624535083770752, "learning_rate": 0.00012718162545169006, "loss": 0.5968156337738038, "step": 249810 }, { "epoch": 1.484981959329731, "grad_norm": 1.3781672716140747, "learning_rate": 0.00012717551512639167, "loss": 0.552280855178833, "step": 249820 }, { "epoch": 1.4850414014063995, "grad_norm": 1.6790162324905396, "learning_rate": 0.00012716940471893125, "loss": 0.6028635978698731, "step": 249830 }, { "epoch": 1.485100843483068, "grad_norm": 1.2787069082260132, "learning_rate": 0.00012716329422933804, "loss": 0.5930452823638916, "step": 249840 }, { "epoch": 1.4851602855597363, "grad_norm": 1.4919135570526123, "learning_rate": 0.0001271571836576412, "loss": 0.6054564952850342, "step": 249850 }, { "epoch": 1.4852197276364048, "grad_norm": 1.4370875358581543, "learning_rate": 0.00012715107300387003, "loss": 0.5790517807006836, "step": 249860 }, { "epoch": 1.4852791697130732, "grad_norm": 1.6759600639343262, "learning_rate": 0.0001271449622680537, "loss": 0.5827738761901855, "step": 249870 }, { "epoch": 1.4853386117897416, "grad_norm": 1.4144713878631592, "learning_rate": 0.0001271388514502215, "loss": 0.5824532985687256, "step": 249880 }, { "epoch": 1.48539805386641, "grad_norm": 1.6416120529174805, "learning_rate": 0.00012713274055040265, "loss": 0.5763303756713867, "step": 249890 }, { "epoch": 1.4854574959430782, "grad_norm": 1.4660464525222778, "learning_rate": 0.00012712662956862632, "loss": 0.5729252815246582, "step": 249900 }, { "epoch": 1.4855169380197466, "grad_norm": 1.4630314111709595, "learning_rate": 0.00012712051850492185, "loss": 0.5829329490661621, "step": 249910 }, { "epoch": 1.485576380096415, "grad_norm": 1.862295389175415, "learning_rate": 0.00012711440735931837, "loss": 0.5497551918029785, "step": 249920 }, { "epoch": 1.4856358221730834, "grad_norm": 1.506075143814087, "learning_rate": 0.00012710829613184514, "loss": 0.5806448936462403, "step": 249930 }, { "epoch": 1.4856952642497518, "grad_norm": 1.6592903137207031, "learning_rate": 0.00012710218482253144, "loss": 0.5226557731628418, "step": 249940 }, { "epoch": 1.4857547063264203, "grad_norm": 1.7072302103042603, "learning_rate": 0.00012709607343140648, "loss": 0.5913460731506348, "step": 249950 }, { "epoch": 1.4858141484030887, "grad_norm": 1.3594393730163574, "learning_rate": 0.00012708996195849953, "loss": 0.6276612281799316, "step": 249960 }, { "epoch": 1.4858735904797569, "grad_norm": 1.5524685382843018, "learning_rate": 0.00012708385040383972, "loss": 0.5391912460327148, "step": 249970 }, { "epoch": 1.4859330325564253, "grad_norm": 1.5545276403427124, "learning_rate": 0.00012707773876745638, "loss": 0.5794166564941406, "step": 249980 }, { "epoch": 1.4859924746330937, "grad_norm": 1.1605020761489868, "learning_rate": 0.00012707162704937873, "loss": 0.5190371513366699, "step": 249990 }, { "epoch": 1.486051916709762, "grad_norm": 1.2581316232681274, "learning_rate": 0.00012706551524963597, "loss": 0.5653224945068359, "step": 250000 }, { "epoch": 1.4861113587864305, "grad_norm": 1.187929391860962, "learning_rate": 0.0001270594033682574, "loss": 0.568524169921875, "step": 250010 }, { "epoch": 1.486170800863099, "grad_norm": 1.4456276893615723, "learning_rate": 0.0001270532914052722, "loss": 0.5554444789886475, "step": 250020 }, { "epoch": 1.4862302429397674, "grad_norm": 1.7037620544433594, "learning_rate": 0.0001270471793607096, "loss": 0.6078469276428222, "step": 250030 }, { "epoch": 1.4862896850164358, "grad_norm": 1.471716284751892, "learning_rate": 0.00012704106723459888, "loss": 0.5531085014343262, "step": 250040 }, { "epoch": 1.4863491270931042, "grad_norm": 1.5508146286010742, "learning_rate": 0.00012703495502696928, "loss": 0.5732288837432862, "step": 250050 }, { "epoch": 1.4864085691697726, "grad_norm": 1.4472732543945312, "learning_rate": 0.00012702884273785, "loss": 0.620180606842041, "step": 250060 }, { "epoch": 1.486468011246441, "grad_norm": 1.7359362840652466, "learning_rate": 0.00012702273036727032, "loss": 0.5971058368682861, "step": 250070 }, { "epoch": 1.4865274533231094, "grad_norm": 1.2189691066741943, "learning_rate": 0.00012701661791525947, "loss": 0.5373537063598632, "step": 250080 }, { "epoch": 1.4865868953997776, "grad_norm": 1.0558539628982544, "learning_rate": 0.00012701050538184666, "loss": 0.5464931011199952, "step": 250090 }, { "epoch": 1.486646337476446, "grad_norm": 1.4732593297958374, "learning_rate": 0.00012700439276706118, "loss": 0.6087428092956543, "step": 250100 }, { "epoch": 1.4867057795531144, "grad_norm": 1.912426233291626, "learning_rate": 0.0001269982800709322, "loss": 0.640346097946167, "step": 250110 }, { "epoch": 1.4867652216297829, "grad_norm": 1.282023310661316, "learning_rate": 0.00012699216729348905, "loss": 0.5864250183105468, "step": 250120 }, { "epoch": 1.4868246637064513, "grad_norm": 1.5471653938293457, "learning_rate": 0.0001269860544347609, "loss": 0.5658520698547364, "step": 250130 }, { "epoch": 1.4868841057831197, "grad_norm": 1.880333423614502, "learning_rate": 0.00012697994149477702, "loss": 0.639834976196289, "step": 250140 }, { "epoch": 1.486943547859788, "grad_norm": 1.3918699026107788, "learning_rate": 0.00012697382847356664, "loss": 0.5617824554443359, "step": 250150 }, { "epoch": 1.4870029899364563, "grad_norm": 1.6052958965301514, "learning_rate": 0.00012696771537115898, "loss": 0.5754788398742676, "step": 250160 }, { "epoch": 1.4870624320131247, "grad_norm": 1.5386028289794922, "learning_rate": 0.00012696160218758336, "loss": 0.5682147979736328, "step": 250170 }, { "epoch": 1.4871218740897931, "grad_norm": 1.5816137790679932, "learning_rate": 0.00012695548892286898, "loss": 0.6573409080505371, "step": 250180 }, { "epoch": 1.4871813161664615, "grad_norm": 1.156826138496399, "learning_rate": 0.00012694937557704506, "loss": 0.5829449653625488, "step": 250190 }, { "epoch": 1.48724075824313, "grad_norm": 1.739732027053833, "learning_rate": 0.0001269432621501409, "loss": 0.6359936714172363, "step": 250200 }, { "epoch": 1.4873002003197984, "grad_norm": 1.3062560558319092, "learning_rate": 0.00012693714864218567, "loss": 0.5903800964355469, "step": 250210 }, { "epoch": 1.4873596423964668, "grad_norm": 1.4311383962631226, "learning_rate": 0.00012693103505320868, "loss": 0.627052640914917, "step": 250220 }, { "epoch": 1.4874190844731352, "grad_norm": 1.7832996845245361, "learning_rate": 0.00012692492138323915, "loss": 0.6247538566589356, "step": 250230 }, { "epoch": 1.4874785265498036, "grad_norm": 1.383182406425476, "learning_rate": 0.0001269188076323063, "loss": 0.5600645065307617, "step": 250240 }, { "epoch": 1.487537968626472, "grad_norm": 1.5976370573043823, "learning_rate": 0.00012691269380043943, "loss": 0.5864620208740234, "step": 250250 }, { "epoch": 1.4875974107031404, "grad_norm": 1.7084509134292603, "learning_rate": 0.00012690657988766776, "loss": 0.5360919952392578, "step": 250260 }, { "epoch": 1.4876568527798086, "grad_norm": 1.3463252782821655, "learning_rate": 0.00012690046589402057, "loss": 0.5519114971160889, "step": 250270 }, { "epoch": 1.487716294856477, "grad_norm": 1.3219397068023682, "learning_rate": 0.000126894351819527, "loss": 0.5970404624938965, "step": 250280 }, { "epoch": 1.4877757369331455, "grad_norm": 1.8418042659759521, "learning_rate": 0.00012688823766421643, "loss": 0.5989570617675781, "step": 250290 }, { "epoch": 1.4878351790098139, "grad_norm": 1.2530794143676758, "learning_rate": 0.00012688212342811802, "loss": 0.57032470703125, "step": 250300 }, { "epoch": 1.4878946210864823, "grad_norm": 1.4167959690093994, "learning_rate": 0.00012687600911126103, "loss": 0.5600823879241943, "step": 250310 }, { "epoch": 1.4879540631631507, "grad_norm": 1.4562863111495972, "learning_rate": 0.00012686989471367478, "loss": 0.5710243225097656, "step": 250320 }, { "epoch": 1.4880135052398191, "grad_norm": 1.573995590209961, "learning_rate": 0.00012686378023538846, "loss": 0.5805978775024414, "step": 250330 }, { "epoch": 1.4880729473164873, "grad_norm": 1.8256149291992188, "learning_rate": 0.0001268576656764313, "loss": 0.5430168628692627, "step": 250340 }, { "epoch": 1.4881323893931557, "grad_norm": 1.4877233505249023, "learning_rate": 0.0001268515510368326, "loss": 0.5522860527038574, "step": 250350 }, { "epoch": 1.4881918314698241, "grad_norm": 1.652282476425171, "learning_rate": 0.00012684543631662155, "loss": 0.6583672523498535, "step": 250360 }, { "epoch": 1.4882512735464926, "grad_norm": 1.5271798372268677, "learning_rate": 0.00012683932151582745, "loss": 0.6140580654144288, "step": 250370 }, { "epoch": 1.488310715623161, "grad_norm": 1.3703193664550781, "learning_rate": 0.00012683320663447957, "loss": 0.6172775268554688, "step": 250380 }, { "epoch": 1.4883701576998294, "grad_norm": 1.8945766687393188, "learning_rate": 0.0001268270916726071, "loss": 0.5951292514801025, "step": 250390 }, { "epoch": 1.4884295997764978, "grad_norm": 1.4691698551177979, "learning_rate": 0.00012682097663023936, "loss": 0.5202404975891113, "step": 250400 }, { "epoch": 1.4884890418531662, "grad_norm": 1.3312429189682007, "learning_rate": 0.0001268148615074055, "loss": 0.5736576557159424, "step": 250410 }, { "epoch": 1.4885484839298346, "grad_norm": 1.4554861783981323, "learning_rate": 0.0001268087463041349, "loss": 0.5260994911193848, "step": 250420 }, { "epoch": 1.488607926006503, "grad_norm": 1.4836640357971191, "learning_rate": 0.0001268026310204567, "loss": 0.5664454460144043, "step": 250430 }, { "epoch": 1.4886673680831715, "grad_norm": 1.3691338300704956, "learning_rate": 0.00012679651565640027, "loss": 0.5896857261657715, "step": 250440 }, { "epoch": 1.4887268101598399, "grad_norm": 1.210224986076355, "learning_rate": 0.00012679040021199475, "loss": 0.599358081817627, "step": 250450 }, { "epoch": 1.488786252236508, "grad_norm": 1.3592246770858765, "learning_rate": 0.00012678428468726943, "loss": 0.6105673789978028, "step": 250460 }, { "epoch": 1.4888456943131765, "grad_norm": 1.3656498193740845, "learning_rate": 0.00012677816908225362, "loss": 0.5845865726470947, "step": 250470 }, { "epoch": 1.488905136389845, "grad_norm": 1.515380620956421, "learning_rate": 0.0001267720533969765, "loss": 0.5469342708587647, "step": 250480 }, { "epoch": 1.4889645784665133, "grad_norm": 1.8165431022644043, "learning_rate": 0.00012676593763146738, "loss": 0.6024838924407959, "step": 250490 }, { "epoch": 1.4890240205431817, "grad_norm": 1.4150837659835815, "learning_rate": 0.00012675982178575546, "loss": 0.578972339630127, "step": 250500 }, { "epoch": 1.4890834626198501, "grad_norm": 1.509738564491272, "learning_rate": 0.00012675370585987008, "loss": 0.5514260768890381, "step": 250510 }, { "epoch": 1.4891429046965186, "grad_norm": 1.3149152994155884, "learning_rate": 0.00012674758985384038, "loss": 0.6452273368835449, "step": 250520 }, { "epoch": 1.4892023467731867, "grad_norm": 1.5985766649246216, "learning_rate": 0.00012674147376769574, "loss": 0.5642990112304688, "step": 250530 }, { "epoch": 1.4892617888498552, "grad_norm": 1.611054539680481, "learning_rate": 0.00012673535760146537, "loss": 0.5594630241394043, "step": 250540 }, { "epoch": 1.4893212309265236, "grad_norm": 1.2520570755004883, "learning_rate": 0.00012672924135517845, "loss": 0.5289706230163574, "step": 250550 }, { "epoch": 1.489380673003192, "grad_norm": 1.8627961874008179, "learning_rate": 0.00012672312502886438, "loss": 0.5921162605285645, "step": 250560 }, { "epoch": 1.4894401150798604, "grad_norm": 2.0275497436523438, "learning_rate": 0.00012671700862255228, "loss": 0.6705462455749511, "step": 250570 }, { "epoch": 1.4894995571565288, "grad_norm": 1.3471723794937134, "learning_rate": 0.00012671089213627155, "loss": 0.5691104412078858, "step": 250580 }, { "epoch": 1.4895589992331972, "grad_norm": 1.514885663986206, "learning_rate": 0.00012670477557005132, "loss": 0.5758142471313477, "step": 250590 }, { "epoch": 1.4896184413098656, "grad_norm": 1.4669158458709717, "learning_rate": 0.0001266986589239209, "loss": 0.5716921329498291, "step": 250600 }, { "epoch": 1.489677883386534, "grad_norm": 1.2740689516067505, "learning_rate": 0.0001266925421979096, "loss": 0.5698260307312012, "step": 250610 }, { "epoch": 1.4897373254632025, "grad_norm": 1.8291860818862915, "learning_rate": 0.00012668642539204655, "loss": 0.6212403774261475, "step": 250620 }, { "epoch": 1.489796767539871, "grad_norm": 1.0592668056488037, "learning_rate": 0.00012668030850636116, "loss": 0.55443115234375, "step": 250630 }, { "epoch": 1.489856209616539, "grad_norm": 1.3733530044555664, "learning_rate": 0.00012667419154088262, "loss": 0.5923308372497559, "step": 250640 }, { "epoch": 1.4899156516932075, "grad_norm": 2.061539649963379, "learning_rate": 0.00012666807449564015, "loss": 0.5778176784515381, "step": 250650 }, { "epoch": 1.489975093769876, "grad_norm": 1.7574235200881958, "learning_rate": 0.00012666195737066313, "loss": 0.5853668212890625, "step": 250660 }, { "epoch": 1.4900345358465443, "grad_norm": 1.2711457014083862, "learning_rate": 0.0001266558401659807, "loss": 0.5292940139770508, "step": 250670 }, { "epoch": 1.4900939779232127, "grad_norm": 1.6797678470611572, "learning_rate": 0.00012664972288162216, "loss": 0.5648260593414307, "step": 250680 }, { "epoch": 1.4901534199998812, "grad_norm": 1.9297946691513062, "learning_rate": 0.00012664360551761686, "loss": 0.6412567138671875, "step": 250690 }, { "epoch": 1.4902128620765496, "grad_norm": 1.6918599605560303, "learning_rate": 0.00012663748807399393, "loss": 0.6117029190063477, "step": 250700 }, { "epoch": 1.4902723041532178, "grad_norm": 1.9755988121032715, "learning_rate": 0.00012663137055078273, "loss": 0.6701786041259765, "step": 250710 }, { "epoch": 1.4903317462298862, "grad_norm": 1.3329813480377197, "learning_rate": 0.00012662525294801247, "loss": 0.5565364837646485, "step": 250720 }, { "epoch": 1.4903911883065546, "grad_norm": 1.3696554899215698, "learning_rate": 0.0001266191352657124, "loss": 0.6350652694702148, "step": 250730 }, { "epoch": 1.490450630383223, "grad_norm": 1.7244011163711548, "learning_rate": 0.00012661301750391187, "loss": 0.5945441246032714, "step": 250740 }, { "epoch": 1.4905100724598914, "grad_norm": 1.4324458837509155, "learning_rate": 0.00012660689966264007, "loss": 0.6117069244384765, "step": 250750 }, { "epoch": 1.4905695145365598, "grad_norm": 1.5648971796035767, "learning_rate": 0.00012660078174192628, "loss": 0.5703957557678223, "step": 250760 }, { "epoch": 1.4906289566132283, "grad_norm": 1.5482473373413086, "learning_rate": 0.00012659466374179978, "loss": 0.5742974758148194, "step": 250770 }, { "epoch": 1.4906883986898967, "grad_norm": 1.1402854919433594, "learning_rate": 0.00012658854566228986, "loss": 0.5470671653747559, "step": 250780 }, { "epoch": 1.490747840766565, "grad_norm": 1.686910629272461, "learning_rate": 0.00012658242750342576, "loss": 0.6033341407775878, "step": 250790 }, { "epoch": 1.4908072828432335, "grad_norm": 1.5019454956054688, "learning_rate": 0.0001265763092652367, "loss": 0.5990281105041504, "step": 250800 }, { "epoch": 1.490866724919902, "grad_norm": 1.392181158065796, "learning_rate": 0.00012657019094775202, "loss": 0.6026898384094238, "step": 250810 }, { "epoch": 1.4909261669965703, "grad_norm": 1.6195319890975952, "learning_rate": 0.00012656407255100095, "loss": 0.6340793609619141, "step": 250820 }, { "epoch": 1.4909856090732385, "grad_norm": 1.3901041746139526, "learning_rate": 0.00012655795407501277, "loss": 0.5662754058837891, "step": 250830 }, { "epoch": 1.491045051149907, "grad_norm": 1.3772528171539307, "learning_rate": 0.00012655183551981677, "loss": 0.5864686012268067, "step": 250840 }, { "epoch": 1.4911044932265753, "grad_norm": 1.4483178853988647, "learning_rate": 0.0001265457168854422, "loss": 0.6143042564392089, "step": 250850 }, { "epoch": 1.4911639353032438, "grad_norm": 1.3449009656906128, "learning_rate": 0.0001265395981719183, "loss": 0.507138442993164, "step": 250860 }, { "epoch": 1.4912233773799122, "grad_norm": 1.8776681423187256, "learning_rate": 0.00012653347937927438, "loss": 0.6273845672607422, "step": 250870 }, { "epoch": 1.4912828194565806, "grad_norm": 1.4842442274093628, "learning_rate": 0.0001265273605075397, "loss": 0.6101907253265381, "step": 250880 }, { "epoch": 1.491342261533249, "grad_norm": 1.431204915046692, "learning_rate": 0.00012652124155674354, "loss": 0.6021580219268798, "step": 250890 }, { "epoch": 1.4914017036099172, "grad_norm": 1.6989336013793945, "learning_rate": 0.00012651512252691513, "loss": 0.5638577938079834, "step": 250900 }, { "epoch": 1.4914611456865856, "grad_norm": 1.6331446170806885, "learning_rate": 0.00012650900341808381, "loss": 0.6317309379577637, "step": 250910 }, { "epoch": 1.491520587763254, "grad_norm": 1.8338472843170166, "learning_rate": 0.0001265028842302788, "loss": 0.5915971755981445, "step": 250920 }, { "epoch": 1.4915800298399224, "grad_norm": 1.637956142425537, "learning_rate": 0.00012649676496352935, "loss": 0.5682414054870606, "step": 250930 }, { "epoch": 1.4916394719165909, "grad_norm": 1.5427297353744507, "learning_rate": 0.00012649064561786482, "loss": 0.6077361106872559, "step": 250940 }, { "epoch": 1.4916989139932593, "grad_norm": 1.5141092538833618, "learning_rate": 0.0001264845261933144, "loss": 0.585904312133789, "step": 250950 }, { "epoch": 1.4917583560699277, "grad_norm": 1.092495083808899, "learning_rate": 0.0001264784066899074, "loss": 0.5181098937988281, "step": 250960 }, { "epoch": 1.491817798146596, "grad_norm": 1.5219825506210327, "learning_rate": 0.00012647228710767306, "loss": 0.6057671070098877, "step": 250970 }, { "epoch": 1.4918772402232645, "grad_norm": 1.587381362915039, "learning_rate": 0.00012646616744664072, "loss": 0.5993141174316406, "step": 250980 }, { "epoch": 1.491936682299933, "grad_norm": 1.3443224430084229, "learning_rate": 0.00012646004770683962, "loss": 0.5394124984741211, "step": 250990 }, { "epoch": 1.4919961243766013, "grad_norm": 1.4138884544372559, "learning_rate": 0.00012645392788829902, "loss": 0.5426921844482422, "step": 251000 }, { "epoch": 1.4920555664532695, "grad_norm": 1.4690022468566895, "learning_rate": 0.0001264478079910482, "loss": 0.616021728515625, "step": 251010 }, { "epoch": 1.492115008529938, "grad_norm": 1.8840062618255615, "learning_rate": 0.00012644168801511645, "loss": 0.5853785037994385, "step": 251020 }, { "epoch": 1.4921744506066064, "grad_norm": 1.4966297149658203, "learning_rate": 0.000126435567960533, "loss": 0.6001980304718018, "step": 251030 }, { "epoch": 1.4922338926832748, "grad_norm": 1.0875662565231323, "learning_rate": 0.0001264294478273272, "loss": 0.542087459564209, "step": 251040 }, { "epoch": 1.4922933347599432, "grad_norm": 1.7642505168914795, "learning_rate": 0.00012642332761552829, "loss": 0.5509645462036132, "step": 251050 }, { "epoch": 1.4923527768366116, "grad_norm": 1.3398176431655884, "learning_rate": 0.00012641720732516556, "loss": 0.5766401290893555, "step": 251060 }, { "epoch": 1.49241221891328, "grad_norm": 1.193118929862976, "learning_rate": 0.00012641108695626827, "loss": 0.5601722717285156, "step": 251070 }, { "epoch": 1.4924716609899482, "grad_norm": 1.3083401918411255, "learning_rate": 0.00012640496650886566, "loss": 0.5219480514526367, "step": 251080 }, { "epoch": 1.4925311030666166, "grad_norm": 1.492750883102417, "learning_rate": 0.0001263988459829871, "loss": 0.591612434387207, "step": 251090 }, { "epoch": 1.492590545143285, "grad_norm": 1.6977308988571167, "learning_rate": 0.00012639272537866183, "loss": 0.5926882743835449, "step": 251100 }, { "epoch": 1.4926499872199535, "grad_norm": 1.916841745376587, "learning_rate": 0.00012638660469591905, "loss": 0.6577608108520507, "step": 251110 }, { "epoch": 1.4927094292966219, "grad_norm": 1.7523193359375, "learning_rate": 0.00012638048393478818, "loss": 0.5756546020507812, "step": 251120 }, { "epoch": 1.4927688713732903, "grad_norm": 1.827582597732544, "learning_rate": 0.0001263743630952984, "loss": 0.5858479499816894, "step": 251130 }, { "epoch": 1.4928283134499587, "grad_norm": 1.6760979890823364, "learning_rate": 0.000126368242177479, "loss": 0.5851255893707276, "step": 251140 }, { "epoch": 1.4928877555266271, "grad_norm": 1.6042931079864502, "learning_rate": 0.0001263621211813593, "loss": 0.6348710060119629, "step": 251150 }, { "epoch": 1.4929471976032955, "grad_norm": 1.3657513856887817, "learning_rate": 0.00012635600010696855, "loss": 0.5656477928161621, "step": 251160 }, { "epoch": 1.493006639679964, "grad_norm": 1.7101821899414062, "learning_rate": 0.00012634987895433606, "loss": 0.59051513671875, "step": 251170 }, { "epoch": 1.4930660817566324, "grad_norm": 1.458425521850586, "learning_rate": 0.0001263437577234911, "loss": 0.6120643615722656, "step": 251180 }, { "epoch": 1.4931255238333008, "grad_norm": 1.2549606561660767, "learning_rate": 0.00012633763641446287, "loss": 0.5483306884765625, "step": 251190 }, { "epoch": 1.493184965909969, "grad_norm": 1.7235426902770996, "learning_rate": 0.0001263315150272808, "loss": 0.546195125579834, "step": 251200 }, { "epoch": 1.4932444079866374, "grad_norm": 1.4355058670043945, "learning_rate": 0.00012632539356197407, "loss": 0.5651389598846436, "step": 251210 }, { "epoch": 1.4933038500633058, "grad_norm": 1.49295175075531, "learning_rate": 0.000126319272018572, "loss": 0.594019079208374, "step": 251220 }, { "epoch": 1.4933632921399742, "grad_norm": 1.3076322078704834, "learning_rate": 0.00012631315039710386, "loss": 0.5867475509643555, "step": 251230 }, { "epoch": 1.4934227342166426, "grad_norm": 1.6706982851028442, "learning_rate": 0.000126307028697599, "loss": 0.6313111305236816, "step": 251240 }, { "epoch": 1.493482176293311, "grad_norm": 1.3963831663131714, "learning_rate": 0.00012630090692008656, "loss": 0.5838376522064209, "step": 251250 }, { "epoch": 1.4935416183699795, "grad_norm": 1.4084274768829346, "learning_rate": 0.00012629478506459593, "loss": 0.5975533485412597, "step": 251260 }, { "epoch": 1.4936010604466476, "grad_norm": 1.5077499151229858, "learning_rate": 0.00012628866313115639, "loss": 0.604105806350708, "step": 251270 }, { "epoch": 1.493660502523316, "grad_norm": 1.4082471132278442, "learning_rate": 0.0001262825411197972, "loss": 0.5929326057434082, "step": 251280 }, { "epoch": 1.4937199445999845, "grad_norm": 1.628949761390686, "learning_rate": 0.00012627641903054766, "loss": 0.5256957054138184, "step": 251290 }, { "epoch": 1.4937793866766529, "grad_norm": 1.7728540897369385, "learning_rate": 0.00012627029686343707, "loss": 0.5855475425720215, "step": 251300 }, { "epoch": 1.4938388287533213, "grad_norm": 1.3609801530838013, "learning_rate": 0.00012626417461849467, "loss": 0.6182963371276855, "step": 251310 }, { "epoch": 1.4938982708299897, "grad_norm": 1.4537322521209717, "learning_rate": 0.00012625805229574973, "loss": 0.5523015022277832, "step": 251320 }, { "epoch": 1.4939577129066581, "grad_norm": 1.2382218837738037, "learning_rate": 0.00012625192989523164, "loss": 0.6005857467651368, "step": 251330 }, { "epoch": 1.4940171549833265, "grad_norm": 1.7229161262512207, "learning_rate": 0.00012624580741696964, "loss": 0.5799407005310059, "step": 251340 }, { "epoch": 1.494076597059995, "grad_norm": 1.3973530530929565, "learning_rate": 0.00012623968486099294, "loss": 0.5783872604370117, "step": 251350 }, { "epoch": 1.4941360391366634, "grad_norm": 1.7702758312225342, "learning_rate": 0.00012623356222733097, "loss": 0.625079870223999, "step": 251360 }, { "epoch": 1.4941954812133318, "grad_norm": 1.3733432292938232, "learning_rate": 0.0001262274395160129, "loss": 0.5846243381500245, "step": 251370 }, { "epoch": 1.49425492329, "grad_norm": 1.749135971069336, "learning_rate": 0.00012622131672706809, "loss": 0.5778660774230957, "step": 251380 }, { "epoch": 1.4943143653666684, "grad_norm": 1.4397841691970825, "learning_rate": 0.00012621519386052575, "loss": 0.5883579254150391, "step": 251390 }, { "epoch": 1.4943738074433368, "grad_norm": 1.5149564743041992, "learning_rate": 0.0001262090709164153, "loss": 0.5710671424865723, "step": 251400 }, { "epoch": 1.4944332495200052, "grad_norm": 1.5069741010665894, "learning_rate": 0.00012620294789476592, "loss": 0.5910332679748536, "step": 251410 }, { "epoch": 1.4944926915966736, "grad_norm": 1.5764071941375732, "learning_rate": 0.0001261968247956069, "loss": 0.5004067420959473, "step": 251420 }, { "epoch": 1.494552133673342, "grad_norm": 1.9535235166549683, "learning_rate": 0.0001261907016189676, "loss": 0.6223265647888183, "step": 251430 }, { "epoch": 1.4946115757500105, "grad_norm": 1.1794716119766235, "learning_rate": 0.00012618457836487725, "loss": 0.5856379508972168, "step": 251440 }, { "epoch": 1.4946710178266787, "grad_norm": 1.9479056596755981, "learning_rate": 0.00012617845503336516, "loss": 0.5635825634002686, "step": 251450 }, { "epoch": 1.494730459903347, "grad_norm": 1.5532076358795166, "learning_rate": 0.00012617233162446066, "loss": 0.6136714458465576, "step": 251460 }, { "epoch": 1.4947899019800155, "grad_norm": 1.364589810371399, "learning_rate": 0.000126166208138193, "loss": 0.5912476539611816, "step": 251470 }, { "epoch": 1.494849344056684, "grad_norm": 1.637622356414795, "learning_rate": 0.0001261600845745915, "loss": 0.6063264846801758, "step": 251480 }, { "epoch": 1.4949087861333523, "grad_norm": 1.8779609203338623, "learning_rate": 0.00012615396093368538, "loss": 0.6356793403625488, "step": 251490 }, { "epoch": 1.4949682282100207, "grad_norm": 1.5790976285934448, "learning_rate": 0.00012614783721550402, "loss": 0.5431785106658935, "step": 251500 }, { "epoch": 1.4950276702866891, "grad_norm": 1.390573263168335, "learning_rate": 0.0001261417134200767, "loss": 0.5842283248901368, "step": 251510 }, { "epoch": 1.4950871123633576, "grad_norm": 1.5779696702957153, "learning_rate": 0.0001261355895474327, "loss": 0.6128564834594726, "step": 251520 }, { "epoch": 1.495146554440026, "grad_norm": 1.5337536334991455, "learning_rate": 0.00012612946559760127, "loss": 0.5740036010742188, "step": 251530 }, { "epoch": 1.4952059965166944, "grad_norm": 1.6858018636703491, "learning_rate": 0.00012612334157061179, "loss": 0.6167138099670411, "step": 251540 }, { "epoch": 1.4952654385933628, "grad_norm": 1.3789070844650269, "learning_rate": 0.0001261172174664935, "loss": 0.596074104309082, "step": 251550 }, { "epoch": 1.4953248806700312, "grad_norm": 1.464148759841919, "learning_rate": 0.00012611109328527576, "loss": 0.5497629642486572, "step": 251560 }, { "epoch": 1.4953843227466994, "grad_norm": 1.2691614627838135, "learning_rate": 0.00012610496902698773, "loss": 0.614152479171753, "step": 251570 }, { "epoch": 1.4954437648233678, "grad_norm": 1.6478564739227295, "learning_rate": 0.00012609884469165882, "loss": 0.5487200260162354, "step": 251580 }, { "epoch": 1.4955032069000362, "grad_norm": 1.2971384525299072, "learning_rate": 0.0001260927202793183, "loss": 0.571786642074585, "step": 251590 }, { "epoch": 1.4955626489767047, "grad_norm": 1.3934781551361084, "learning_rate": 0.00012608659578999546, "loss": 0.6246977806091308, "step": 251600 }, { "epoch": 1.495622091053373, "grad_norm": 1.6206815242767334, "learning_rate": 0.00012608047122371964, "loss": 0.5776089191436767, "step": 251610 }, { "epoch": 1.4956815331300415, "grad_norm": 1.5030518770217896, "learning_rate": 0.0001260743465805201, "loss": 0.5798556327819824, "step": 251620 }, { "epoch": 1.49574097520671, "grad_norm": 1.4473625421524048, "learning_rate": 0.00012606822186042607, "loss": 0.6252708911895752, "step": 251630 }, { "epoch": 1.495800417283378, "grad_norm": 1.8791780471801758, "learning_rate": 0.00012606209706346696, "loss": 0.6183688163757324, "step": 251640 }, { "epoch": 1.4958598593600465, "grad_norm": 1.5379407405853271, "learning_rate": 0.00012605597218967205, "loss": 0.5811939239501953, "step": 251650 }, { "epoch": 1.495919301436715, "grad_norm": 1.300391435623169, "learning_rate": 0.00012604984723907058, "loss": 0.5880622863769531, "step": 251660 }, { "epoch": 1.4959787435133833, "grad_norm": 1.3515710830688477, "learning_rate": 0.00012604372221169193, "loss": 0.6052659034729004, "step": 251670 }, { "epoch": 1.4960381855900518, "grad_norm": 1.6254936456680298, "learning_rate": 0.0001260375971075653, "loss": 0.5486745834350586, "step": 251680 }, { "epoch": 1.4960976276667202, "grad_norm": 1.6058918237686157, "learning_rate": 0.00012603147192672006, "loss": 0.6033092498779297, "step": 251690 }, { "epoch": 1.4961570697433886, "grad_norm": 1.6927188634872437, "learning_rate": 0.00012602534666918553, "loss": 0.6135228157043457, "step": 251700 }, { "epoch": 1.496216511820057, "grad_norm": 2.053797960281372, "learning_rate": 0.00012601922133499094, "loss": 0.6280234336853028, "step": 251710 }, { "epoch": 1.4962759538967254, "grad_norm": 1.3838839530944824, "learning_rate": 0.00012601309592416563, "loss": 0.564164686203003, "step": 251720 }, { "epoch": 1.4963353959733938, "grad_norm": 1.178531527519226, "learning_rate": 0.00012600697043673896, "loss": 0.57134108543396, "step": 251730 }, { "epoch": 1.4963948380500622, "grad_norm": 1.4802249670028687, "learning_rate": 0.00012600084487274013, "loss": 0.6400363922119141, "step": 251740 }, { "epoch": 1.4964542801267304, "grad_norm": 1.585694432258606, "learning_rate": 0.00012599471923219847, "loss": 0.5788775444030761, "step": 251750 }, { "epoch": 1.4965137222033988, "grad_norm": 1.7224587202072144, "learning_rate": 0.00012598859351514334, "loss": 0.5807672500610351, "step": 251760 }, { "epoch": 1.4965731642800673, "grad_norm": 1.285663366317749, "learning_rate": 0.000125982467721604, "loss": 0.6405248641967773, "step": 251770 }, { "epoch": 1.4966326063567357, "grad_norm": 1.7547051906585693, "learning_rate": 0.00012597634185160974, "loss": 0.5586248397827148, "step": 251780 }, { "epoch": 1.496692048433404, "grad_norm": 1.3745996952056885, "learning_rate": 0.00012597021590518987, "loss": 0.6066663265228271, "step": 251790 }, { "epoch": 1.4967514905100725, "grad_norm": 1.437363862991333, "learning_rate": 0.00012596408988237374, "loss": 0.6116912841796875, "step": 251800 }, { "epoch": 1.496810932586741, "grad_norm": 1.279121994972229, "learning_rate": 0.00012595796378319057, "loss": 0.5801724433898926, "step": 251810 }, { "epoch": 1.496870374663409, "grad_norm": 1.4046169519424438, "learning_rate": 0.0001259518376076698, "loss": 0.6078547477722168, "step": 251820 }, { "epoch": 1.4969298167400775, "grad_norm": 1.6753418445587158, "learning_rate": 0.00012594571135584058, "loss": 0.5917760848999023, "step": 251830 }, { "epoch": 1.496989258816746, "grad_norm": 1.761849284172058, "learning_rate": 0.0001259395850277323, "loss": 0.5630111694335938, "step": 251840 }, { "epoch": 1.4970487008934144, "grad_norm": 1.2834864854812622, "learning_rate": 0.00012593345862337428, "loss": 0.5848739624023438, "step": 251850 }, { "epoch": 1.4971081429700828, "grad_norm": 1.964132308959961, "learning_rate": 0.00012592733214279579, "loss": 0.6023944854736328, "step": 251860 }, { "epoch": 1.4971675850467512, "grad_norm": 1.4431543350219727, "learning_rate": 0.00012592120558602612, "loss": 0.6208442211151123, "step": 251870 }, { "epoch": 1.4972270271234196, "grad_norm": 1.3774938583374023, "learning_rate": 0.00012591507895309462, "loss": 0.5276662826538085, "step": 251880 }, { "epoch": 1.497286469200088, "grad_norm": 2.750746011734009, "learning_rate": 0.00012590895224403058, "loss": 0.5865987777709961, "step": 251890 }, { "epoch": 1.4973459112767564, "grad_norm": 1.518425464630127, "learning_rate": 0.00012590282545886335, "loss": 0.6046971321105957, "step": 251900 }, { "epoch": 1.4974053533534248, "grad_norm": 1.2515615224838257, "learning_rate": 0.00012589669859762218, "loss": 0.5789763450622558, "step": 251910 }, { "epoch": 1.4974647954300933, "grad_norm": 1.6124908924102783, "learning_rate": 0.0001258905716603364, "loss": 0.6057042121887207, "step": 251920 }, { "epoch": 1.4975242375067617, "grad_norm": 1.1000193357467651, "learning_rate": 0.0001258844446470353, "loss": 0.5963566303253174, "step": 251930 }, { "epoch": 1.4975836795834299, "grad_norm": 1.2559727430343628, "learning_rate": 0.00012587831755774822, "loss": 0.5561494827270508, "step": 251940 }, { "epoch": 1.4976431216600983, "grad_norm": 1.4263098239898682, "learning_rate": 0.00012587219039250446, "loss": 0.583436918258667, "step": 251950 }, { "epoch": 1.4977025637367667, "grad_norm": 1.661156177520752, "learning_rate": 0.00012586606315133332, "loss": 0.6056513786315918, "step": 251960 }, { "epoch": 1.497762005813435, "grad_norm": 1.4556951522827148, "learning_rate": 0.00012585993583426412, "loss": 0.536280632019043, "step": 251970 }, { "epoch": 1.4978214478901035, "grad_norm": 1.5736860036849976, "learning_rate": 0.0001258538084413262, "loss": 0.5745889186859131, "step": 251980 }, { "epoch": 1.497880889966772, "grad_norm": 1.603190302848816, "learning_rate": 0.00012584768097254878, "loss": 0.5427549839019775, "step": 251990 }, { "epoch": 1.4979403320434403, "grad_norm": 1.7035876512527466, "learning_rate": 0.0001258415534279613, "loss": 0.5789777278900147, "step": 252000 }, { "epoch": 1.4979997741201085, "grad_norm": 2.046569585800171, "learning_rate": 0.00012583542580759297, "loss": 0.6226578712463379, "step": 252010 }, { "epoch": 1.498059216196777, "grad_norm": 1.5262740850448608, "learning_rate": 0.00012582929811147313, "loss": 0.6047868251800537, "step": 252020 }, { "epoch": 1.4981186582734454, "grad_norm": 1.3651591539382935, "learning_rate": 0.0001258231703396311, "loss": 0.5521267890930176, "step": 252030 }, { "epoch": 1.4981781003501138, "grad_norm": 1.5346091985702515, "learning_rate": 0.0001258170424920962, "loss": 0.5890859603881836, "step": 252040 }, { "epoch": 1.4982375424267822, "grad_norm": 1.419865608215332, "learning_rate": 0.00012581091456889776, "loss": 0.5926651000976563, "step": 252050 }, { "epoch": 1.4982969845034506, "grad_norm": 1.6163098812103271, "learning_rate": 0.00012580478657006505, "loss": 0.5740031719207763, "step": 252060 }, { "epoch": 1.498356426580119, "grad_norm": 1.3527805805206299, "learning_rate": 0.00012579865849562743, "loss": 0.6194552898406982, "step": 252070 }, { "epoch": 1.4984158686567874, "grad_norm": 1.1775050163269043, "learning_rate": 0.0001257925303456142, "loss": 0.608470869064331, "step": 252080 }, { "epoch": 1.4984753107334559, "grad_norm": 1.762229323387146, "learning_rate": 0.00012578640212005459, "loss": 0.6373518943786621, "step": 252090 }, { "epoch": 1.4985347528101243, "grad_norm": 1.431300401687622, "learning_rate": 0.00012578027381897805, "loss": 0.5558503627777099, "step": 252100 }, { "epoch": 1.4985941948867927, "grad_norm": 1.7674121856689453, "learning_rate": 0.00012577414544241383, "loss": 0.589220380783081, "step": 252110 }, { "epoch": 1.4986536369634609, "grad_norm": 1.4484070539474487, "learning_rate": 0.00012576801699039125, "loss": 0.5688971519470215, "step": 252120 }, { "epoch": 1.4987130790401293, "grad_norm": 1.381243109703064, "learning_rate": 0.00012576188846293964, "loss": 0.5965347290039062, "step": 252130 }, { "epoch": 1.4987725211167977, "grad_norm": 1.4631885290145874, "learning_rate": 0.0001257557598600883, "loss": 0.6036301612854004, "step": 252140 }, { "epoch": 1.4988319631934661, "grad_norm": 1.429574728012085, "learning_rate": 0.00012574963118186654, "loss": 0.5990062713623047, "step": 252150 }, { "epoch": 1.4988914052701345, "grad_norm": 1.429465651512146, "learning_rate": 0.0001257435024283037, "loss": 0.542239761352539, "step": 252160 }, { "epoch": 1.498950847346803, "grad_norm": 1.4328019618988037, "learning_rate": 0.0001257373735994291, "loss": 0.5488112449645997, "step": 252170 }, { "epoch": 1.4990102894234714, "grad_norm": 1.5454792976379395, "learning_rate": 0.00012573124469527204, "loss": 0.6247324466705322, "step": 252180 }, { "epoch": 1.4990697315001396, "grad_norm": 1.6892008781433105, "learning_rate": 0.00012572511571586184, "loss": 0.6118923187255859, "step": 252190 }, { "epoch": 1.499129173576808, "grad_norm": 1.6101627349853516, "learning_rate": 0.00012571898666122782, "loss": 0.5773180484771728, "step": 252200 }, { "epoch": 1.4991886156534764, "grad_norm": 1.426503300666809, "learning_rate": 0.00012571285753139934, "loss": 0.5932397842407227, "step": 252210 }, { "epoch": 1.4992480577301448, "grad_norm": 1.540684461593628, "learning_rate": 0.00012570672832640565, "loss": 0.6003503322601318, "step": 252220 }, { "epoch": 1.4993074998068132, "grad_norm": 1.5998457670211792, "learning_rate": 0.00012570059904627615, "loss": 0.5883810997009278, "step": 252230 }, { "epoch": 1.4993669418834816, "grad_norm": 1.364426851272583, "learning_rate": 0.00012569446969104006, "loss": 0.5805823326110839, "step": 252240 }, { "epoch": 1.49942638396015, "grad_norm": 1.4935225248336792, "learning_rate": 0.00012568834026072676, "loss": 0.5979236125946045, "step": 252250 }, { "epoch": 1.4994858260368185, "grad_norm": 1.5781793594360352, "learning_rate": 0.00012568221075536559, "loss": 0.6276665687561035, "step": 252260 }, { "epoch": 1.4995452681134869, "grad_norm": 1.5688414573669434, "learning_rate": 0.00012567608117498586, "loss": 0.5319775581359864, "step": 252270 }, { "epoch": 1.4996047101901553, "grad_norm": 1.3173632621765137, "learning_rate": 0.00012566995151961683, "loss": 0.5670263767242432, "step": 252280 }, { "epoch": 1.4996641522668237, "grad_norm": 1.4451327323913574, "learning_rate": 0.00012566382178928794, "loss": 0.5975853443145752, "step": 252290 }, { "epoch": 1.4997235943434921, "grad_norm": 1.3331708908081055, "learning_rate": 0.0001256576919840284, "loss": 0.6183974266052246, "step": 252300 }, { "epoch": 1.4997830364201603, "grad_norm": 1.2703876495361328, "learning_rate": 0.00012565156210386758, "loss": 0.6171265125274659, "step": 252310 }, { "epoch": 1.4998424784968287, "grad_norm": 1.3764857053756714, "learning_rate": 0.00012564543214883483, "loss": 0.6117533683776856, "step": 252320 }, { "epoch": 1.4999019205734971, "grad_norm": 1.6006550788879395, "learning_rate": 0.00012563930211895942, "loss": 0.5787794589996338, "step": 252330 }, { "epoch": 1.4999613626501656, "grad_norm": 1.3432596921920776, "learning_rate": 0.00012563317201427071, "loss": 0.5636520385742188, "step": 252340 }, { "epoch": 1.500020804726834, "grad_norm": 1.4758923053741455, "learning_rate": 0.00012562704183479803, "loss": 0.5922713279724121, "step": 252350 }, { "epoch": 1.5000802468035024, "grad_norm": 1.5664170980453491, "learning_rate": 0.00012562091158057067, "loss": 0.5786588668823243, "step": 252360 }, { "epoch": 1.5001396888801706, "grad_norm": 1.5494384765625, "learning_rate": 0.00012561478125161797, "loss": 0.5968704223632812, "step": 252370 }, { "epoch": 1.500199130956839, "grad_norm": 1.5487580299377441, "learning_rate": 0.00012560865084796928, "loss": 0.5828907012939453, "step": 252380 }, { "epoch": 1.5002585730335074, "grad_norm": 1.484540343284607, "learning_rate": 0.00012560252036965388, "loss": 0.6457500457763672, "step": 252390 }, { "epoch": 1.5003180151101758, "grad_norm": 1.0983672142028809, "learning_rate": 0.00012559638981670112, "loss": 0.5642380714416504, "step": 252400 }, { "epoch": 1.5003774571868442, "grad_norm": 1.1657335758209229, "learning_rate": 0.0001255902591891404, "loss": 0.5746147632598877, "step": 252410 }, { "epoch": 1.5004368992635126, "grad_norm": 1.441650629043579, "learning_rate": 0.00012558412848700086, "loss": 0.6324511528015136, "step": 252420 }, { "epoch": 1.500496341340181, "grad_norm": 1.66779363155365, "learning_rate": 0.00012557799771031197, "loss": 0.562076187133789, "step": 252430 }, { "epoch": 1.5005557834168495, "grad_norm": 1.1592758893966675, "learning_rate": 0.0001255718668591031, "loss": 0.5567415237426758, "step": 252440 }, { "epoch": 1.500615225493518, "grad_norm": 1.660627841949463, "learning_rate": 0.00012556573593340347, "loss": 0.6375793933868408, "step": 252450 }, { "epoch": 1.5006746675701863, "grad_norm": 1.114259123802185, "learning_rate": 0.0001255596049332424, "loss": 0.5559423923492431, "step": 252460 }, { "epoch": 1.5007341096468547, "grad_norm": 1.5122934579849243, "learning_rate": 0.00012555347385864932, "loss": 0.5590867042541504, "step": 252470 }, { "epoch": 1.5007935517235231, "grad_norm": 1.4199020862579346, "learning_rate": 0.00012554734270965348, "loss": 0.5732706546783447, "step": 252480 }, { "epoch": 1.5008529938001915, "grad_norm": 1.2620849609375, "learning_rate": 0.00012554121148628425, "loss": 0.5642718315124512, "step": 252490 }, { "epoch": 1.5009124358768597, "grad_norm": 1.656266212463379, "learning_rate": 0.00012553508018857095, "loss": 0.558132266998291, "step": 252500 }, { "epoch": 1.5009718779535282, "grad_norm": 1.395115852355957, "learning_rate": 0.00012552894881654288, "loss": 0.5354921340942382, "step": 252510 }, { "epoch": 1.5010313200301966, "grad_norm": 1.7094868421554565, "learning_rate": 0.0001255228173702294, "loss": 0.5606637954711914, "step": 252520 }, { "epoch": 1.501090762106865, "grad_norm": 1.29044508934021, "learning_rate": 0.00012551668584965983, "loss": 0.6022284030914307, "step": 252530 }, { "epoch": 1.5011502041835334, "grad_norm": 2.0340585708618164, "learning_rate": 0.00012551055425486353, "loss": 0.5782722949981689, "step": 252540 }, { "epoch": 1.5012096462602016, "grad_norm": 1.2475680112838745, "learning_rate": 0.00012550442258586978, "loss": 0.5604311943054199, "step": 252550 }, { "epoch": 1.50126908833687, "grad_norm": 1.4311872720718384, "learning_rate": 0.00012549829084270795, "loss": 0.5946232318878174, "step": 252560 }, { "epoch": 1.5013285304135384, "grad_norm": 1.1887701749801636, "learning_rate": 0.0001254921590254074, "loss": 0.5693682670593262, "step": 252570 }, { "epoch": 1.5013879724902068, "grad_norm": 1.4308172464370728, "learning_rate": 0.00012548602713399734, "loss": 0.5654243946075439, "step": 252580 }, { "epoch": 1.5014474145668752, "grad_norm": 1.3548071384429932, "learning_rate": 0.00012547989516850725, "loss": 0.6143277645111084, "step": 252590 }, { "epoch": 1.5015068566435437, "grad_norm": 1.7264113426208496, "learning_rate": 0.0001254737631289664, "loss": 0.588387393951416, "step": 252600 }, { "epoch": 1.501566298720212, "grad_norm": 1.8842564821243286, "learning_rate": 0.00012546763101540408, "loss": 0.6065339565277099, "step": 252610 }, { "epoch": 1.5016257407968805, "grad_norm": 1.342729091644287, "learning_rate": 0.0001254614988278497, "loss": 0.556223726272583, "step": 252620 }, { "epoch": 1.501685182873549, "grad_norm": 1.6640876531600952, "learning_rate": 0.00012545536656633256, "loss": 0.5723220825195312, "step": 252630 }, { "epoch": 1.5017446249502173, "grad_norm": 1.8630410432815552, "learning_rate": 0.000125449234230882, "loss": 0.5569565773010254, "step": 252640 }, { "epoch": 1.5018040670268857, "grad_norm": 1.498193383216858, "learning_rate": 0.00012544310182152735, "loss": 0.567349624633789, "step": 252650 }, { "epoch": 1.5018635091035542, "grad_norm": 1.7918016910552979, "learning_rate": 0.00012543696933829793, "loss": 0.5500805854797364, "step": 252660 }, { "epoch": 1.5019229511802226, "grad_norm": 1.5568171739578247, "learning_rate": 0.0001254308367812231, "loss": 0.5130931854248046, "step": 252670 }, { "epoch": 1.501982393256891, "grad_norm": 1.5328214168548584, "learning_rate": 0.0001254247041503322, "loss": 0.6020070075988769, "step": 252680 }, { "epoch": 1.5020418353335592, "grad_norm": 1.2853351831436157, "learning_rate": 0.00012541857144565457, "loss": 0.5735694885253906, "step": 252690 }, { "epoch": 1.5021012774102276, "grad_norm": 1.608188509941101, "learning_rate": 0.00012541243866721953, "loss": 0.5862223625183105, "step": 252700 }, { "epoch": 1.502160719486896, "grad_norm": 1.7820645570755005, "learning_rate": 0.00012540630581505638, "loss": 0.6188289642333984, "step": 252710 }, { "epoch": 1.5022201615635644, "grad_norm": 1.3957608938217163, "learning_rate": 0.00012540017288919454, "loss": 0.6169796943664551, "step": 252720 }, { "epoch": 1.5022796036402328, "grad_norm": 1.693804383277893, "learning_rate": 0.00012539403988966332, "loss": 0.6337447166442871, "step": 252730 }, { "epoch": 1.502339045716901, "grad_norm": 1.5840822458267212, "learning_rate": 0.00012538790681649198, "loss": 0.605115270614624, "step": 252740 }, { "epoch": 1.5023984877935694, "grad_norm": 1.4390071630477905, "learning_rate": 0.00012538177366971, "loss": 0.6132642745971679, "step": 252750 }, { "epoch": 1.5024579298702379, "grad_norm": 1.6932415962219238, "learning_rate": 0.00012537564044934658, "loss": 0.639204740524292, "step": 252760 }, { "epoch": 1.5025173719469063, "grad_norm": 1.7672117948532104, "learning_rate": 0.00012536950715543113, "loss": 0.598600196838379, "step": 252770 }, { "epoch": 1.5025768140235747, "grad_norm": 1.2848972082138062, "learning_rate": 0.00012536337378799302, "loss": 0.5241690635681152, "step": 252780 }, { "epoch": 1.502636256100243, "grad_norm": 2.0075111389160156, "learning_rate": 0.0001253572403470615, "loss": 0.6409458160400391, "step": 252790 }, { "epoch": 1.5026956981769115, "grad_norm": 2.1612954139709473, "learning_rate": 0.00012535110683266598, "loss": 0.570985221862793, "step": 252800 }, { "epoch": 1.50275514025358, "grad_norm": 1.7593811750411987, "learning_rate": 0.0001253449732448358, "loss": 0.5795891284942627, "step": 252810 }, { "epoch": 1.5028145823302483, "grad_norm": 1.267594575881958, "learning_rate": 0.00012533883958360027, "loss": 0.5642836093902588, "step": 252820 }, { "epoch": 1.5028740244069168, "grad_norm": 1.3177776336669922, "learning_rate": 0.00012533270584898874, "loss": 0.6437783241271973, "step": 252830 }, { "epoch": 1.5029334664835852, "grad_norm": 1.1224898099899292, "learning_rate": 0.00012532657204103055, "loss": 0.550295352935791, "step": 252840 }, { "epoch": 1.5029929085602536, "grad_norm": 3.1339941024780273, "learning_rate": 0.00012532043815975506, "loss": 0.5853444576263428, "step": 252850 }, { "epoch": 1.503052350636922, "grad_norm": 1.5271400213241577, "learning_rate": 0.0001253143042051916, "loss": 0.5427415847778321, "step": 252860 }, { "epoch": 1.5031117927135902, "grad_norm": 1.8797954320907593, "learning_rate": 0.00012530817017736948, "loss": 0.5601848602294922, "step": 252870 }, { "epoch": 1.5031712347902586, "grad_norm": 1.4292563199996948, "learning_rate": 0.0001253020360763181, "loss": 0.5728896141052247, "step": 252880 }, { "epoch": 1.503230676866927, "grad_norm": 1.2974960803985596, "learning_rate": 0.0001252959019020668, "loss": 0.5468779563903808, "step": 252890 }, { "epoch": 1.5032901189435954, "grad_norm": 1.3422894477844238, "learning_rate": 0.0001252897676546449, "loss": 0.5778075695037842, "step": 252900 }, { "epoch": 1.5033495610202638, "grad_norm": 1.1811034679412842, "learning_rate": 0.00012528363333408175, "loss": 0.6278450012207031, "step": 252910 }, { "epoch": 1.503409003096932, "grad_norm": 1.3293262720108032, "learning_rate": 0.00012527749894040665, "loss": 0.5937268257141113, "step": 252920 }, { "epoch": 1.5034684451736005, "grad_norm": 1.604210376739502, "learning_rate": 0.00012527136447364903, "loss": 0.5858107566833496, "step": 252930 }, { "epoch": 1.5035278872502689, "grad_norm": 1.1974323987960815, "learning_rate": 0.0001252652299338382, "loss": 0.509333324432373, "step": 252940 }, { "epoch": 1.5035873293269373, "grad_norm": 2.0343105792999268, "learning_rate": 0.0001252590953210035, "loss": 0.5969978332519531, "step": 252950 }, { "epoch": 1.5036467714036057, "grad_norm": 1.8345290422439575, "learning_rate": 0.00012525296063517423, "loss": 0.5983962059020996, "step": 252960 }, { "epoch": 1.5037062134802741, "grad_norm": 1.1578330993652344, "learning_rate": 0.00012524682587637982, "loss": 0.6002346992492675, "step": 252970 }, { "epoch": 1.5037656555569425, "grad_norm": 1.353619933128357, "learning_rate": 0.00012524069104464955, "loss": 0.6619809150695801, "step": 252980 }, { "epoch": 1.503825097633611, "grad_norm": 1.2314801216125488, "learning_rate": 0.0001252345561400128, "loss": 0.6653691291809082, "step": 252990 }, { "epoch": 1.5038845397102794, "grad_norm": 1.3055304288864136, "learning_rate": 0.00012522842116249893, "loss": 0.4859612464904785, "step": 253000 }, { "epoch": 1.5039439817869478, "grad_norm": 1.82461416721344, "learning_rate": 0.00012522228611213727, "loss": 0.5877293586730957, "step": 253010 }, { "epoch": 1.5040034238636162, "grad_norm": 1.537089228630066, "learning_rate": 0.00012521615098895717, "loss": 0.524259376525879, "step": 253020 }, { "epoch": 1.5040628659402846, "grad_norm": 1.4735994338989258, "learning_rate": 0.00012521001579298796, "loss": 0.5355664253234863, "step": 253030 }, { "epoch": 1.504122308016953, "grad_norm": 1.2047628164291382, "learning_rate": 0.000125203880524259, "loss": 0.5930717468261719, "step": 253040 }, { "epoch": 1.5041817500936214, "grad_norm": 1.6886669397354126, "learning_rate": 0.00012519774518279968, "loss": 0.5783735275268554, "step": 253050 }, { "epoch": 1.5042411921702896, "grad_norm": 1.1053762435913086, "learning_rate": 0.00012519160976863928, "loss": 0.5378941535949707, "step": 253060 }, { "epoch": 1.504300634246958, "grad_norm": 1.3734674453735352, "learning_rate": 0.00012518547428180718, "loss": 0.6022767066955567, "step": 253070 }, { "epoch": 1.5043600763236264, "grad_norm": 1.998986005783081, "learning_rate": 0.00012517933872233274, "loss": 0.6115909099578858, "step": 253080 }, { "epoch": 1.5044195184002949, "grad_norm": 1.5415632724761963, "learning_rate": 0.00012517320309024532, "loss": 0.5982185363769531, "step": 253090 }, { "epoch": 1.5044789604769633, "grad_norm": 1.4366945028305054, "learning_rate": 0.00012516706738557426, "loss": 0.5760534763336181, "step": 253100 }, { "epoch": 1.5045384025536315, "grad_norm": 1.7266803979873657, "learning_rate": 0.00012516093160834887, "loss": 0.6532165050506592, "step": 253110 }, { "epoch": 1.5045978446302999, "grad_norm": 1.5329042673110962, "learning_rate": 0.0001251547957585986, "loss": 0.5824624061584472, "step": 253120 }, { "epoch": 1.5046572867069683, "grad_norm": 1.6825730800628662, "learning_rate": 0.00012514865983635269, "loss": 0.5857922077178955, "step": 253130 }, { "epoch": 1.5047167287836367, "grad_norm": 1.555315375328064, "learning_rate": 0.00012514252384164055, "loss": 0.5788510322570801, "step": 253140 }, { "epoch": 1.5047761708603051, "grad_norm": 1.5004737377166748, "learning_rate": 0.0001251363877744915, "loss": 0.5649454116821289, "step": 253150 }, { "epoch": 1.5048356129369735, "grad_norm": 1.3814994096755981, "learning_rate": 0.00012513025163493494, "loss": 0.6234694957733155, "step": 253160 }, { "epoch": 1.504895055013642, "grad_norm": 1.728758454322815, "learning_rate": 0.0001251241154230002, "loss": 0.6048422813415527, "step": 253170 }, { "epoch": 1.5049544970903104, "grad_norm": 1.3133430480957031, "learning_rate": 0.00012511797913871667, "loss": 0.514953899383545, "step": 253180 }, { "epoch": 1.5050139391669788, "grad_norm": 1.3047255277633667, "learning_rate": 0.00012511184278211362, "loss": 0.5969679355621338, "step": 253190 }, { "epoch": 1.5050733812436472, "grad_norm": 1.3622809648513794, "learning_rate": 0.00012510570635322046, "loss": 0.5830395221710205, "step": 253200 }, { "epoch": 1.5051328233203156, "grad_norm": 1.3565839529037476, "learning_rate": 0.00012509956985206657, "loss": 0.5992532730102539, "step": 253210 }, { "epoch": 1.505192265396984, "grad_norm": 1.612845540046692, "learning_rate": 0.00012509343327868125, "loss": 0.5728818893432617, "step": 253220 }, { "epoch": 1.5052517074736524, "grad_norm": 1.7666466236114502, "learning_rate": 0.00012508729663309384, "loss": 0.6463309288024902, "step": 253230 }, { "epoch": 1.5053111495503206, "grad_norm": 1.4008041620254517, "learning_rate": 0.00012508115991533383, "loss": 0.6488146781921387, "step": 253240 }, { "epoch": 1.505370591626989, "grad_norm": 1.824175477027893, "learning_rate": 0.00012507502312543038, "loss": 0.5798451900482178, "step": 253250 }, { "epoch": 1.5054300337036575, "grad_norm": 1.5311814546585083, "learning_rate": 0.000125068886263413, "loss": 0.5679967880249024, "step": 253260 }, { "epoch": 1.5054894757803259, "grad_norm": 1.233822226524353, "learning_rate": 0.00012506274932931098, "loss": 0.5509057998657226, "step": 253270 }, { "epoch": 1.5055489178569943, "grad_norm": 1.5977659225463867, "learning_rate": 0.00012505661232315368, "loss": 0.609162425994873, "step": 253280 }, { "epoch": 1.5056083599336625, "grad_norm": 1.0744932889938354, "learning_rate": 0.00012505047524497047, "loss": 0.587848711013794, "step": 253290 }, { "epoch": 1.505667802010331, "grad_norm": 1.2280218601226807, "learning_rate": 0.00012504433809479073, "loss": 0.585806131362915, "step": 253300 }, { "epoch": 1.5057272440869993, "grad_norm": 1.7309213876724243, "learning_rate": 0.00012503820087264377, "loss": 0.586129903793335, "step": 253310 }, { "epoch": 1.5057866861636677, "grad_norm": 1.999796986579895, "learning_rate": 0.00012503206357855897, "loss": 0.5885923862457275, "step": 253320 }, { "epoch": 1.5058461282403361, "grad_norm": 1.3790007829666138, "learning_rate": 0.0001250259262125657, "loss": 0.5585977554321289, "step": 253330 }, { "epoch": 1.5059055703170046, "grad_norm": 1.1737614870071411, "learning_rate": 0.00012501978877469332, "loss": 0.5474078178405761, "step": 253340 }, { "epoch": 1.505965012393673, "grad_norm": 1.4524494409561157, "learning_rate": 0.00012501365126497114, "loss": 0.5872049331665039, "step": 253350 }, { "epoch": 1.5060244544703414, "grad_norm": 1.3883405923843384, "learning_rate": 0.0001250075136834286, "loss": 0.5854269027709961, "step": 253360 }, { "epoch": 1.5060838965470098, "grad_norm": 1.4557005167007446, "learning_rate": 0.00012500137603009502, "loss": 0.615459394454956, "step": 253370 }, { "epoch": 1.5061433386236782, "grad_norm": 1.5031870603561401, "learning_rate": 0.0001249952383049997, "loss": 0.5548592567443847, "step": 253380 }, { "epoch": 1.5062027807003466, "grad_norm": 1.5469917058944702, "learning_rate": 0.00012498910050817212, "loss": 0.6453004360198975, "step": 253390 }, { "epoch": 1.506262222777015, "grad_norm": 1.4181612730026245, "learning_rate": 0.00012498296263964157, "loss": 0.5882838249206543, "step": 253400 }, { "epoch": 1.5063216648536835, "grad_norm": 1.3609836101531982, "learning_rate": 0.00012497682469943738, "loss": 0.6019916534423828, "step": 253410 }, { "epoch": 1.5063811069303519, "grad_norm": 1.3162546157836914, "learning_rate": 0.00012497068668758902, "loss": 0.6077499389648438, "step": 253420 }, { "epoch": 1.50644054900702, "grad_norm": 1.4012517929077148, "learning_rate": 0.00012496454860412576, "loss": 0.5635925769805908, "step": 253430 }, { "epoch": 1.5064999910836885, "grad_norm": 1.5269992351531982, "learning_rate": 0.000124958410449077, "loss": 0.48820886611938474, "step": 253440 }, { "epoch": 1.506559433160357, "grad_norm": 1.5140401124954224, "learning_rate": 0.00012495227222247205, "loss": 0.594118881225586, "step": 253450 }, { "epoch": 1.5066188752370253, "grad_norm": 1.1808785200119019, "learning_rate": 0.0001249461339243404, "loss": 0.5713954925537109, "step": 253460 }, { "epoch": 1.5066783173136935, "grad_norm": 1.4836459159851074, "learning_rate": 0.00012493999555471125, "loss": 0.5684603691101074, "step": 253470 }, { "epoch": 1.506737759390362, "grad_norm": 1.5084699392318726, "learning_rate": 0.00012493385711361408, "loss": 0.5616086483001709, "step": 253480 }, { "epoch": 1.5067972014670303, "grad_norm": 1.562948226928711, "learning_rate": 0.0001249277186010782, "loss": 0.5837370872497558, "step": 253490 }, { "epoch": 1.5068566435436987, "grad_norm": 1.963470220565796, "learning_rate": 0.00012492158001713302, "loss": 0.5840176582336426, "step": 253500 }, { "epoch": 1.5069160856203672, "grad_norm": 1.4176169633865356, "learning_rate": 0.00012491544136180785, "loss": 0.6332305908203125, "step": 253510 }, { "epoch": 1.5069755276970356, "grad_norm": 1.3485691547393799, "learning_rate": 0.00012490930263513213, "loss": 0.545511531829834, "step": 253520 }, { "epoch": 1.507034969773704, "grad_norm": 1.540794849395752, "learning_rate": 0.00012490316383713512, "loss": 0.5585201263427735, "step": 253530 }, { "epoch": 1.5070944118503724, "grad_norm": 1.5096019506454468, "learning_rate": 0.00012489702496784627, "loss": 0.5842532157897949, "step": 253540 }, { "epoch": 1.5071538539270408, "grad_norm": 1.8278273344039917, "learning_rate": 0.00012489088602729494, "loss": 0.6218430995941162, "step": 253550 }, { "epoch": 1.5072132960037092, "grad_norm": 1.3122965097427368, "learning_rate": 0.00012488474701551042, "loss": 0.5650525569915772, "step": 253560 }, { "epoch": 1.5072727380803776, "grad_norm": 1.4415799379348755, "learning_rate": 0.00012487860793252217, "loss": 0.608082389831543, "step": 253570 }, { "epoch": 1.507332180157046, "grad_norm": 1.47601318359375, "learning_rate": 0.00012487246877835952, "loss": 0.5897067070007325, "step": 253580 }, { "epoch": 1.5073916222337145, "grad_norm": 1.2638994455337524, "learning_rate": 0.00012486632955305185, "loss": 0.5857919692993164, "step": 253590 }, { "epoch": 1.507451064310383, "grad_norm": 1.422728180885315, "learning_rate": 0.0001248601902566285, "loss": 0.6090202331542969, "step": 253600 }, { "epoch": 1.507510506387051, "grad_norm": 1.509666085243225, "learning_rate": 0.00012485405088911888, "loss": 0.614450740814209, "step": 253610 }, { "epoch": 1.5075699484637195, "grad_norm": 1.5652495622634888, "learning_rate": 0.00012484791145055233, "loss": 0.5638136863708496, "step": 253620 }, { "epoch": 1.507629390540388, "grad_norm": 1.672521710395813, "learning_rate": 0.0001248417719409582, "loss": 0.603962516784668, "step": 253630 }, { "epoch": 1.5076888326170563, "grad_norm": 1.309185266494751, "learning_rate": 0.0001248356323603659, "loss": 0.5890148162841797, "step": 253640 }, { "epoch": 1.5077482746937247, "grad_norm": 1.7655400037765503, "learning_rate": 0.0001248294927088048, "loss": 0.58004732131958, "step": 253650 }, { "epoch": 1.507807716770393, "grad_norm": 1.7075915336608887, "learning_rate": 0.00012482335298630417, "loss": 0.663881492614746, "step": 253660 }, { "epoch": 1.5078671588470614, "grad_norm": 1.714881420135498, "learning_rate": 0.00012481721319289356, "loss": 0.5819090366363525, "step": 253670 }, { "epoch": 1.5079266009237298, "grad_norm": 1.901986837387085, "learning_rate": 0.00012481107332860223, "loss": 0.5925897598266602, "step": 253680 }, { "epoch": 1.5079860430003982, "grad_norm": 1.64566171169281, "learning_rate": 0.00012480493339345954, "loss": 0.5458365440368652, "step": 253690 }, { "epoch": 1.5080454850770666, "grad_norm": 1.7948873043060303, "learning_rate": 0.0001247987933874949, "loss": 0.5461965560913086, "step": 253700 }, { "epoch": 1.508104927153735, "grad_norm": 1.8066074848175049, "learning_rate": 0.00012479265331073766, "loss": 0.6395708084106445, "step": 253710 }, { "epoch": 1.5081643692304034, "grad_norm": 1.4467724561691284, "learning_rate": 0.00012478651316321718, "loss": 0.6108526229858399, "step": 253720 }, { "epoch": 1.5082238113070718, "grad_norm": 1.4852747917175293, "learning_rate": 0.00012478037294496292, "loss": 0.6044562816619873, "step": 253730 }, { "epoch": 1.5082832533837403, "grad_norm": 1.6156198978424072, "learning_rate": 0.00012477423265600413, "loss": 0.6513495445251465, "step": 253740 }, { "epoch": 1.5083426954604087, "grad_norm": 1.6462268829345703, "learning_rate": 0.00012476809229637026, "loss": 0.5705445766448974, "step": 253750 }, { "epoch": 1.508402137537077, "grad_norm": 1.6526806354522705, "learning_rate": 0.00012476195186609065, "loss": 0.5866358757019043, "step": 253760 }, { "epoch": 1.5084615796137455, "grad_norm": 1.3939107656478882, "learning_rate": 0.00012475581136519467, "loss": 0.5540695190429688, "step": 253770 }, { "epoch": 1.508521021690414, "grad_norm": 1.7840564250946045, "learning_rate": 0.00012474967079371176, "loss": 0.6440982341766357, "step": 253780 }, { "epoch": 1.5085804637670823, "grad_norm": 1.766501784324646, "learning_rate": 0.00012474353015167123, "loss": 0.5748022079467774, "step": 253790 }, { "epoch": 1.5086399058437505, "grad_norm": 1.3526010513305664, "learning_rate": 0.00012473738943910245, "loss": 0.548543643951416, "step": 253800 }, { "epoch": 1.508699347920419, "grad_norm": 1.6084076166152954, "learning_rate": 0.0001247312486560348, "loss": 0.6115731716156005, "step": 253810 }, { "epoch": 1.5087587899970873, "grad_norm": 1.7996654510498047, "learning_rate": 0.0001247251078024977, "loss": 0.5863447666168213, "step": 253820 }, { "epoch": 1.5088182320737558, "grad_norm": 1.3142129182815552, "learning_rate": 0.0001247189668785205, "loss": 0.5490785121917725, "step": 253830 }, { "epoch": 1.508877674150424, "grad_norm": 1.5286585092544556, "learning_rate": 0.00012471282588413256, "loss": 0.5758914947509766, "step": 253840 }, { "epoch": 1.5089371162270924, "grad_norm": 1.5572208166122437, "learning_rate": 0.00012470668481936328, "loss": 0.5777163505554199, "step": 253850 }, { "epoch": 1.5089965583037608, "grad_norm": 1.488695740699768, "learning_rate": 0.00012470054368424202, "loss": 0.596828031539917, "step": 253860 }, { "epoch": 1.5090560003804292, "grad_norm": 1.4919354915618896, "learning_rate": 0.00012469440247879816, "loss": 0.6021212577819824, "step": 253870 }, { "epoch": 1.5091154424570976, "grad_norm": 1.6140843629837036, "learning_rate": 0.00012468826120306108, "loss": 0.539923620223999, "step": 253880 }, { "epoch": 1.509174884533766, "grad_norm": 1.158700704574585, "learning_rate": 0.00012468211985706016, "loss": 0.5560585975646972, "step": 253890 }, { "epoch": 1.5092343266104344, "grad_norm": 1.5888813734054565, "learning_rate": 0.00012467597844082476, "loss": 0.5715499877929687, "step": 253900 }, { "epoch": 1.5092937686871029, "grad_norm": 1.5860249996185303, "learning_rate": 0.0001246698369543843, "loss": 0.5384217739105225, "step": 253910 }, { "epoch": 1.5093532107637713, "grad_norm": 2.578303098678589, "learning_rate": 0.00012466369539776813, "loss": 0.5833739280700684, "step": 253920 }, { "epoch": 1.5094126528404397, "grad_norm": 1.2205415964126587, "learning_rate": 0.00012465755377100564, "loss": 0.5708146572113038, "step": 253930 }, { "epoch": 1.509472094917108, "grad_norm": 1.5377007722854614, "learning_rate": 0.0001246514120741262, "loss": 0.567729377746582, "step": 253940 }, { "epoch": 1.5095315369937765, "grad_norm": 1.5275135040283203, "learning_rate": 0.00012464527030715917, "loss": 0.574491548538208, "step": 253950 }, { "epoch": 1.509590979070445, "grad_norm": 1.6773074865341187, "learning_rate": 0.00012463912847013398, "loss": 0.6113665580749512, "step": 253960 }, { "epoch": 1.5096504211471133, "grad_norm": 1.567893624305725, "learning_rate": 0.00012463298656308, "loss": 0.5476804733276367, "step": 253970 }, { "epoch": 1.5097098632237815, "grad_norm": 1.3698617219924927, "learning_rate": 0.00012462684458602655, "loss": 0.5986738681793213, "step": 253980 }, { "epoch": 1.50976930530045, "grad_norm": 0.9619067311286926, "learning_rate": 0.00012462070253900303, "loss": 0.5730969429016113, "step": 253990 }, { "epoch": 1.5098287473771184, "grad_norm": 1.6031893491744995, "learning_rate": 0.0001246145604220389, "loss": 0.6136719703674316, "step": 254000 }, { "epoch": 1.5098881894537868, "grad_norm": 1.7718846797943115, "learning_rate": 0.0001246084182351635, "loss": 0.5835296630859375, "step": 254010 }, { "epoch": 1.5099476315304552, "grad_norm": 1.3350032567977905, "learning_rate": 0.00012460227597840617, "loss": 0.645350980758667, "step": 254020 }, { "epoch": 1.5100070736071234, "grad_norm": 1.518782377243042, "learning_rate": 0.00012459613365179635, "loss": 0.5929507732391357, "step": 254030 }, { "epoch": 1.5100665156837918, "grad_norm": 1.3198213577270508, "learning_rate": 0.0001245899912553634, "loss": 0.5600423812866211, "step": 254040 }, { "epoch": 1.5101259577604602, "grad_norm": 1.3878165483474731, "learning_rate": 0.00012458384878913666, "loss": 0.5859813213348388, "step": 254050 }, { "epoch": 1.5101853998371286, "grad_norm": 1.3351361751556396, "learning_rate": 0.00012457770625314555, "loss": 0.5595520973205567, "step": 254060 }, { "epoch": 1.510244841913797, "grad_norm": 1.099174976348877, "learning_rate": 0.0001245715636474195, "loss": 0.576657485961914, "step": 254070 }, { "epoch": 1.5103042839904655, "grad_norm": 1.7720253467559814, "learning_rate": 0.00012456542097198783, "loss": 0.5646590232849121, "step": 254080 }, { "epoch": 1.5103637260671339, "grad_norm": 1.5378131866455078, "learning_rate": 0.00012455927822687996, "loss": 0.5604898452758789, "step": 254090 }, { "epoch": 1.5104231681438023, "grad_norm": 1.6443215608596802, "learning_rate": 0.00012455313541212526, "loss": 0.5911248207092286, "step": 254100 }, { "epoch": 1.5104826102204707, "grad_norm": 1.7660706043243408, "learning_rate": 0.0001245469925277531, "loss": 0.6080119609832764, "step": 254110 }, { "epoch": 1.5105420522971391, "grad_norm": 1.643181562423706, "learning_rate": 0.00012454084957379285, "loss": 0.5976269721984864, "step": 254120 }, { "epoch": 1.5106014943738075, "grad_norm": 1.489351511001587, "learning_rate": 0.000124534706550274, "loss": 0.5728320598602294, "step": 254130 }, { "epoch": 1.510660936450476, "grad_norm": 1.6470025777816772, "learning_rate": 0.00012452856345722583, "loss": 0.5760372161865235, "step": 254140 }, { "epoch": 1.5107203785271444, "grad_norm": 1.3048484325408936, "learning_rate": 0.00012452242029467773, "loss": 0.6565746784210205, "step": 254150 }, { "epoch": 1.5107798206038128, "grad_norm": 1.7769813537597656, "learning_rate": 0.0001245162770626592, "loss": 0.6033661842346192, "step": 254160 }, { "epoch": 1.510839262680481, "grad_norm": 1.7233612537384033, "learning_rate": 0.00012451013376119948, "loss": 0.5869418144226074, "step": 254170 }, { "epoch": 1.5108987047571494, "grad_norm": 1.5905627012252808, "learning_rate": 0.000124503990390328, "loss": 0.593049144744873, "step": 254180 }, { "epoch": 1.5109581468338178, "grad_norm": 1.5790941715240479, "learning_rate": 0.0001244978469500742, "loss": 0.6647976398468017, "step": 254190 }, { "epoch": 1.5110175889104862, "grad_norm": 1.4086310863494873, "learning_rate": 0.00012449170344046748, "loss": 0.6093113899230957, "step": 254200 }, { "epoch": 1.5110770309871544, "grad_norm": 1.223045825958252, "learning_rate": 0.00012448555986153715, "loss": 0.6200889587402344, "step": 254210 }, { "epoch": 1.5111364730638228, "grad_norm": 1.5025265216827393, "learning_rate": 0.0001244794162133126, "loss": 0.5865085601806641, "step": 254220 }, { "epoch": 1.5111959151404912, "grad_norm": 1.4617195129394531, "learning_rate": 0.0001244732724958233, "loss": 0.6136788368225098, "step": 254230 }, { "epoch": 1.5112553572171596, "grad_norm": 1.4332847595214844, "learning_rate": 0.0001244671287090986, "loss": 0.6540154933929443, "step": 254240 }, { "epoch": 1.511314799293828, "grad_norm": 1.7177916765213013, "learning_rate": 0.00012446098485316783, "loss": 0.6623873710632324, "step": 254250 }, { "epoch": 1.5113742413704965, "grad_norm": 1.9419645071029663, "learning_rate": 0.0001244548409280605, "loss": 0.566810417175293, "step": 254260 }, { "epoch": 1.5114336834471649, "grad_norm": 1.4597560167312622, "learning_rate": 0.0001244486969338059, "loss": 0.5737522125244141, "step": 254270 }, { "epoch": 1.5114931255238333, "grad_norm": 1.459263801574707, "learning_rate": 0.00012444255287043346, "loss": 0.5555394172668457, "step": 254280 }, { "epoch": 1.5115525676005017, "grad_norm": 1.3804296255111694, "learning_rate": 0.00012443640873797257, "loss": 0.5892298698425293, "step": 254290 }, { "epoch": 1.5116120096771701, "grad_norm": 1.1219819784164429, "learning_rate": 0.0001244302645364526, "loss": 0.6150016784667969, "step": 254300 }, { "epoch": 1.5116714517538385, "grad_norm": 1.6990338563919067, "learning_rate": 0.000124424120265903, "loss": 0.5805254936218261, "step": 254310 }, { "epoch": 1.511730893830507, "grad_norm": 1.3556369543075562, "learning_rate": 0.00012441797592635312, "loss": 0.5783339500427246, "step": 254320 }, { "epoch": 1.5117903359071754, "grad_norm": 1.4194811582565308, "learning_rate": 0.00012441183151783232, "loss": 0.6021595954895019, "step": 254330 }, { "epoch": 1.5118497779838438, "grad_norm": 1.4122371673583984, "learning_rate": 0.00012440568704037006, "loss": 0.580516004562378, "step": 254340 }, { "epoch": 1.511909220060512, "grad_norm": 1.863935947418213, "learning_rate": 0.0001243995424939957, "loss": 0.5839697837829589, "step": 254350 }, { "epoch": 1.5119686621371804, "grad_norm": 1.8957388401031494, "learning_rate": 0.00012439339787873857, "loss": 0.5784149169921875, "step": 254360 }, { "epoch": 1.5120281042138488, "grad_norm": 1.3945949077606201, "learning_rate": 0.00012438725319462821, "loss": 0.6059308052062988, "step": 254370 }, { "epoch": 1.5120875462905172, "grad_norm": 1.252851963043213, "learning_rate": 0.00012438110844169387, "loss": 0.6181858539581299, "step": 254380 }, { "epoch": 1.5121469883671856, "grad_norm": 1.6557832956314087, "learning_rate": 0.00012437496361996508, "loss": 0.5358982086181641, "step": 254390 }, { "epoch": 1.5122064304438538, "grad_norm": 1.2763769626617432, "learning_rate": 0.00012436881872947107, "loss": 0.5677525997161865, "step": 254400 }, { "epoch": 1.5122658725205222, "grad_norm": 1.4931211471557617, "learning_rate": 0.00012436267377024138, "loss": 0.5692821502685547, "step": 254410 }, { "epoch": 1.5123253145971907, "grad_norm": 1.4121601581573486, "learning_rate": 0.00012435652874230536, "loss": 0.5972959995269775, "step": 254420 }, { "epoch": 1.512384756673859, "grad_norm": 1.4087228775024414, "learning_rate": 0.00012435038364569238, "loss": 0.5913970947265625, "step": 254430 }, { "epoch": 1.5124441987505275, "grad_norm": 1.4575773477554321, "learning_rate": 0.00012434423848043185, "loss": 0.588820219039917, "step": 254440 }, { "epoch": 1.512503640827196, "grad_norm": 1.2673834562301636, "learning_rate": 0.0001243380932465532, "loss": 0.6092341423034668, "step": 254450 }, { "epoch": 1.5125630829038643, "grad_norm": 1.8898826837539673, "learning_rate": 0.0001243319479440858, "loss": 0.6329400062561035, "step": 254460 }, { "epoch": 1.5126225249805327, "grad_norm": 1.2896379232406616, "learning_rate": 0.000124325802573059, "loss": 0.6195955276489258, "step": 254470 }, { "epoch": 1.5126819670572011, "grad_norm": 1.5761996507644653, "learning_rate": 0.00012431965713350228, "loss": 0.5100956916809082, "step": 254480 }, { "epoch": 1.5127414091338696, "grad_norm": 1.3127682209014893, "learning_rate": 0.00012431351162544497, "loss": 0.6682461261749267, "step": 254490 }, { "epoch": 1.512800851210538, "grad_norm": 1.455904245376587, "learning_rate": 0.00012430736604891656, "loss": 0.5989889144897461, "step": 254500 }, { "epoch": 1.5128602932872064, "grad_norm": 1.4179753065109253, "learning_rate": 0.0001243012204039463, "loss": 0.5664655208587647, "step": 254510 }, { "epoch": 1.5129197353638748, "grad_norm": 1.2740912437438965, "learning_rate": 0.00012429507469056373, "loss": 0.6406159400939941, "step": 254520 }, { "epoch": 1.5129791774405432, "grad_norm": 1.2252562046051025, "learning_rate": 0.00012428892890879817, "loss": 0.509980583190918, "step": 254530 }, { "epoch": 1.5130386195172114, "grad_norm": 1.3557507991790771, "learning_rate": 0.00012428278305867904, "loss": 0.5579947471618653, "step": 254540 }, { "epoch": 1.5130980615938798, "grad_norm": 1.2636679410934448, "learning_rate": 0.0001242766371402358, "loss": 0.5791903972625733, "step": 254550 }, { "epoch": 1.5131575036705482, "grad_norm": 1.5919909477233887, "learning_rate": 0.00012427049115349773, "loss": 0.6252698421478271, "step": 254560 }, { "epoch": 1.5132169457472167, "grad_norm": 1.403640866279602, "learning_rate": 0.0001242643450984943, "loss": 0.5730687618255615, "step": 254570 }, { "epoch": 1.5132763878238848, "grad_norm": 1.4590668678283691, "learning_rate": 0.00012425819897525492, "loss": 0.6019737243652343, "step": 254580 }, { "epoch": 1.5133358299005533, "grad_norm": 1.3450424671173096, "learning_rate": 0.00012425205278380897, "loss": 0.5966053009033203, "step": 254590 }, { "epoch": 1.5133952719772217, "grad_norm": 1.4834926128387451, "learning_rate": 0.0001242459065241859, "loss": 0.6214348316192627, "step": 254600 }, { "epoch": 1.51345471405389, "grad_norm": 1.4224004745483398, "learning_rate": 0.000124239760196415, "loss": 0.6160934448242188, "step": 254610 }, { "epoch": 1.5135141561305585, "grad_norm": 2.005967617034912, "learning_rate": 0.00012423361380052577, "loss": 0.6231367111206054, "step": 254620 }, { "epoch": 1.513573598207227, "grad_norm": 1.462022304534912, "learning_rate": 0.0001242274673365476, "loss": 0.6352963447570801, "step": 254630 }, { "epoch": 1.5136330402838953, "grad_norm": 1.6755409240722656, "learning_rate": 0.00012422132080450984, "loss": 0.5554580688476562, "step": 254640 }, { "epoch": 1.5136924823605638, "grad_norm": 1.5421397686004639, "learning_rate": 0.00012421517420444197, "loss": 0.6488194465637207, "step": 254650 }, { "epoch": 1.5137519244372322, "grad_norm": 1.4994800090789795, "learning_rate": 0.00012420902753637334, "loss": 0.5797439575195312, "step": 254660 }, { "epoch": 1.5138113665139006, "grad_norm": 1.5053597688674927, "learning_rate": 0.00012420288080033335, "loss": 0.6003686904907226, "step": 254670 }, { "epoch": 1.513870808590569, "grad_norm": 1.7834229469299316, "learning_rate": 0.0001241967339963514, "loss": 0.5838017463684082, "step": 254680 }, { "epoch": 1.5139302506672374, "grad_norm": 1.5701056718826294, "learning_rate": 0.00012419058712445698, "loss": 0.6190340518951416, "step": 254690 }, { "epoch": 1.5139896927439058, "grad_norm": 1.8052613735198975, "learning_rate": 0.00012418444018467937, "loss": 0.5681678295135498, "step": 254700 }, { "epoch": 1.5140491348205742, "grad_norm": 1.5212703943252563, "learning_rate": 0.00012417829317704806, "loss": 0.5894498825073242, "step": 254710 }, { "epoch": 1.5141085768972424, "grad_norm": 1.4198726415634155, "learning_rate": 0.00012417214610159242, "loss": 0.5852726936340332, "step": 254720 }, { "epoch": 1.5141680189739108, "grad_norm": 1.4763717651367188, "learning_rate": 0.00012416599895834188, "loss": 0.6436763286590577, "step": 254730 }, { "epoch": 1.5142274610505793, "grad_norm": 1.6815506219863892, "learning_rate": 0.00012415985174732582, "loss": 0.5978851318359375, "step": 254740 }, { "epoch": 1.5142869031272477, "grad_norm": 1.438477873802185, "learning_rate": 0.00012415370446857367, "loss": 0.563580322265625, "step": 254750 }, { "epoch": 1.514346345203916, "grad_norm": 1.5482943058013916, "learning_rate": 0.00012414755712211481, "loss": 0.5894095420837402, "step": 254760 }, { "epoch": 1.5144057872805843, "grad_norm": 1.661812424659729, "learning_rate": 0.00012414140970797862, "loss": 0.5553807258605957, "step": 254770 }, { "epoch": 1.5144652293572527, "grad_norm": 1.223736047744751, "learning_rate": 0.00012413526222619463, "loss": 0.5609645843505859, "step": 254780 }, { "epoch": 1.514524671433921, "grad_norm": 1.4558289051055908, "learning_rate": 0.0001241291146767921, "loss": 0.5805428504943848, "step": 254790 }, { "epoch": 1.5145841135105895, "grad_norm": 1.7735545635223389, "learning_rate": 0.0001241229670598005, "loss": 0.5584748744964599, "step": 254800 }, { "epoch": 1.514643555587258, "grad_norm": 1.3689137697219849, "learning_rate": 0.0001241168193752493, "loss": 0.5597139358520508, "step": 254810 }, { "epoch": 1.5147029976639264, "grad_norm": 1.4087576866149902, "learning_rate": 0.0001241106716231678, "loss": 0.5612954139709473, "step": 254820 }, { "epoch": 1.5147624397405948, "grad_norm": 1.4863110780715942, "learning_rate": 0.00012410452380358548, "loss": 0.5635443210601807, "step": 254830 }, { "epoch": 1.5148218818172632, "grad_norm": 1.5591729879379272, "learning_rate": 0.00012409837591653174, "loss": 0.6017050743103027, "step": 254840 }, { "epoch": 1.5148813238939316, "grad_norm": 1.4765589237213135, "learning_rate": 0.00012409222796203593, "loss": 0.595662784576416, "step": 254850 }, { "epoch": 1.5149407659706, "grad_norm": 1.7141221761703491, "learning_rate": 0.00012408607994012752, "loss": 0.5947260856628418, "step": 254860 }, { "epoch": 1.5150002080472684, "grad_norm": 1.4422955513000488, "learning_rate": 0.00012407993185083594, "loss": 0.5902165412902832, "step": 254870 }, { "epoch": 1.5150596501239368, "grad_norm": 1.5405677556991577, "learning_rate": 0.0001240737836941906, "loss": 0.5555121421813964, "step": 254880 }, { "epoch": 1.5151190922006053, "grad_norm": 1.6821353435516357, "learning_rate": 0.00012406763547022077, "loss": 0.6174830436706543, "step": 254890 }, { "epoch": 1.5151785342772737, "grad_norm": 1.378151774406433, "learning_rate": 0.00012406148717895602, "loss": 0.6131942749023438, "step": 254900 }, { "epoch": 1.5152379763539419, "grad_norm": 1.4100029468536377, "learning_rate": 0.00012405533882042574, "loss": 0.5676611423492431, "step": 254910 }, { "epoch": 1.5152974184306103, "grad_norm": 1.2692502737045288, "learning_rate": 0.00012404919039465929, "loss": 0.5834600925445557, "step": 254920 }, { "epoch": 1.5153568605072787, "grad_norm": 1.8193633556365967, "learning_rate": 0.0001240430419016861, "loss": 0.5568051338195801, "step": 254930 }, { "epoch": 1.515416302583947, "grad_norm": 1.7889474630355835, "learning_rate": 0.0001240368933415356, "loss": 0.5374985694885254, "step": 254940 }, { "epoch": 1.5154757446606153, "grad_norm": 1.4354627132415771, "learning_rate": 0.00012403074471423718, "loss": 0.5779810905456543, "step": 254950 }, { "epoch": 1.5155351867372837, "grad_norm": 1.2857894897460938, "learning_rate": 0.00012402459601982025, "loss": 0.6183568000793457, "step": 254960 }, { "epoch": 1.5155946288139521, "grad_norm": 1.3881703615188599, "learning_rate": 0.00012401844725831425, "loss": 0.5504782199859619, "step": 254970 }, { "epoch": 1.5156540708906205, "grad_norm": 1.4579620361328125, "learning_rate": 0.00012401229842974858, "loss": 0.5872818946838378, "step": 254980 }, { "epoch": 1.515713512967289, "grad_norm": 1.209836721420288, "learning_rate": 0.00012400614953415266, "loss": 0.5269695281982422, "step": 254990 }, { "epoch": 1.5157729550439574, "grad_norm": 1.191706895828247, "learning_rate": 0.00012400000057155588, "loss": 0.6265602588653565, "step": 255000 }, { "epoch": 1.5158323971206258, "grad_norm": 1.427686095237732, "learning_rate": 0.00012399385154198767, "loss": 0.6142295837402344, "step": 255010 }, { "epoch": 1.5158918391972942, "grad_norm": 1.1573801040649414, "learning_rate": 0.00012398770244547745, "loss": 0.5626296043395996, "step": 255020 }, { "epoch": 1.5159512812739626, "grad_norm": 1.775431752204895, "learning_rate": 0.00012398155328205464, "loss": 0.5388334274291993, "step": 255030 }, { "epoch": 1.516010723350631, "grad_norm": 1.483249545097351, "learning_rate": 0.0001239754040517487, "loss": 0.6957984924316406, "step": 255040 }, { "epoch": 1.5160701654272994, "grad_norm": 1.048978567123413, "learning_rate": 0.00012396925475458893, "loss": 0.5191271305084229, "step": 255050 }, { "epoch": 1.5161296075039679, "grad_norm": 1.451094150543213, "learning_rate": 0.00012396310539060482, "loss": 0.5705113887786866, "step": 255060 }, { "epoch": 1.5161890495806363, "grad_norm": 1.7981833219528198, "learning_rate": 0.0001239569559598258, "loss": 0.6074622631072998, "step": 255070 }, { "epoch": 1.5162484916573047, "grad_norm": 1.605323076248169, "learning_rate": 0.00012395080646228124, "loss": 0.5392934799194335, "step": 255080 }, { "epoch": 1.5163079337339729, "grad_norm": 1.410457730293274, "learning_rate": 0.00012394465689800059, "loss": 0.610466718673706, "step": 255090 }, { "epoch": 1.5163673758106413, "grad_norm": 1.5829676389694214, "learning_rate": 0.00012393850726701323, "loss": 0.5923538208007812, "step": 255100 }, { "epoch": 1.5164268178873097, "grad_norm": 1.3905764818191528, "learning_rate": 0.00012393235756934863, "loss": 0.5376163482666015, "step": 255110 }, { "epoch": 1.5164862599639781, "grad_norm": 1.0018799304962158, "learning_rate": 0.0001239262078050362, "loss": 0.5368637084960938, "step": 255120 }, { "epoch": 1.5165457020406465, "grad_norm": 1.4841077327728271, "learning_rate": 0.00012392005797410533, "loss": 0.5831875801086426, "step": 255130 }, { "epoch": 1.5166051441173147, "grad_norm": 1.55747389793396, "learning_rate": 0.00012391390807658546, "loss": 0.5848846435546875, "step": 255140 }, { "epoch": 1.5166645861939831, "grad_norm": 1.6024912595748901, "learning_rate": 0.000123907758112506, "loss": 0.5666746616363525, "step": 255150 }, { "epoch": 1.5167240282706516, "grad_norm": 1.5822973251342773, "learning_rate": 0.00012390160808189635, "loss": 0.586048936843872, "step": 255160 }, { "epoch": 1.51678347034732, "grad_norm": 1.2341969013214111, "learning_rate": 0.00012389545798478598, "loss": 0.5705629825592041, "step": 255170 }, { "epoch": 1.5168429124239884, "grad_norm": 1.4200358390808105, "learning_rate": 0.00012388930782120426, "loss": 0.5897397518157959, "step": 255180 }, { "epoch": 1.5169023545006568, "grad_norm": 1.517014503479004, "learning_rate": 0.00012388315759118064, "loss": 0.5463244915008545, "step": 255190 }, { "epoch": 1.5169617965773252, "grad_norm": 1.505723237991333, "learning_rate": 0.0001238770072947445, "loss": 0.6065172672271728, "step": 255200 }, { "epoch": 1.5170212386539936, "grad_norm": 1.8448125123977661, "learning_rate": 0.00012387085693192534, "loss": 0.590960168838501, "step": 255210 }, { "epoch": 1.517080680730662, "grad_norm": 1.812074065208435, "learning_rate": 0.0001238647065027525, "loss": 0.595222282409668, "step": 255220 }, { "epoch": 1.5171401228073305, "grad_norm": 1.5676202774047852, "learning_rate": 0.00012385855600725542, "loss": 0.6055272102355957, "step": 255230 }, { "epoch": 1.5171995648839989, "grad_norm": 1.6895979642868042, "learning_rate": 0.00012385240544546359, "loss": 0.5882211208343506, "step": 255240 }, { "epoch": 1.5172590069606673, "grad_norm": 1.1949058771133423, "learning_rate": 0.00012384625481740634, "loss": 0.5770373821258545, "step": 255250 }, { "epoch": 1.5173184490373357, "grad_norm": 1.5234829187393188, "learning_rate": 0.00012384010412311313, "loss": 0.6509821891784668, "step": 255260 }, { "epoch": 1.5173778911140041, "grad_norm": 1.6003623008728027, "learning_rate": 0.00012383395336261344, "loss": 0.5864420890808105, "step": 255270 }, { "epoch": 1.5174373331906723, "grad_norm": 1.252565860748291, "learning_rate": 0.00012382780253593657, "loss": 0.5898670196533203, "step": 255280 }, { "epoch": 1.5174967752673407, "grad_norm": 1.5800130367279053, "learning_rate": 0.00012382165164311204, "loss": 0.6021721363067627, "step": 255290 }, { "epoch": 1.5175562173440091, "grad_norm": 1.9213528633117676, "learning_rate": 0.00012381550068416927, "loss": 0.5793881893157959, "step": 255300 }, { "epoch": 1.5176156594206776, "grad_norm": 1.465083122253418, "learning_rate": 0.0001238093496591376, "loss": 0.5577937126159668, "step": 255310 }, { "epoch": 1.5176751014973457, "grad_norm": 1.3443021774291992, "learning_rate": 0.00012380319856804655, "loss": 0.5168785572052002, "step": 255320 }, { "epoch": 1.5177345435740142, "grad_norm": 1.8246208429336548, "learning_rate": 0.00012379704741092553, "loss": 0.5508211612701416, "step": 255330 }, { "epoch": 1.5177939856506826, "grad_norm": 1.3445649147033691, "learning_rate": 0.0001237908961878039, "loss": 0.5836740493774414, "step": 255340 }, { "epoch": 1.517853427727351, "grad_norm": 1.9036128520965576, "learning_rate": 0.00012378474489871115, "loss": 0.5533875465393067, "step": 255350 }, { "epoch": 1.5179128698040194, "grad_norm": 1.5456594228744507, "learning_rate": 0.00012377859354367673, "loss": 0.5906464099884033, "step": 255360 }, { "epoch": 1.5179723118806878, "grad_norm": 2.136153221130371, "learning_rate": 0.00012377244212272994, "loss": 0.592258882522583, "step": 255370 }, { "epoch": 1.5180317539573562, "grad_norm": 1.6200335025787354, "learning_rate": 0.00012376629063590034, "loss": 0.5818044662475585, "step": 255380 }, { "epoch": 1.5180911960340246, "grad_norm": 1.3376039266586304, "learning_rate": 0.0001237601390832173, "loss": 0.5754298686981201, "step": 255390 }, { "epoch": 1.518150638110693, "grad_norm": 1.1698628664016724, "learning_rate": 0.0001237539874647102, "loss": 0.5667652130126953, "step": 255400 }, { "epoch": 1.5182100801873615, "grad_norm": 1.3312863111495972, "learning_rate": 0.0001237478357804086, "loss": 0.5713620185852051, "step": 255410 }, { "epoch": 1.51826952226403, "grad_norm": 1.3439526557922363, "learning_rate": 0.00012374168403034177, "loss": 0.5358709335327149, "step": 255420 }, { "epoch": 1.5183289643406983, "grad_norm": 1.7946670055389404, "learning_rate": 0.00012373553221453927, "loss": 0.5898087978363037, "step": 255430 }, { "epoch": 1.5183884064173667, "grad_norm": 1.3973463773727417, "learning_rate": 0.00012372938033303044, "loss": 0.5607827663421631, "step": 255440 }, { "epoch": 1.5184478484940351, "grad_norm": 1.4457426071166992, "learning_rate": 0.00012372322838584475, "loss": 0.5347609519958496, "step": 255450 }, { "epoch": 1.5185072905707033, "grad_norm": 1.7754164934158325, "learning_rate": 0.00012371707637301164, "loss": 0.585126543045044, "step": 255460 }, { "epoch": 1.5185667326473717, "grad_norm": 1.8226001262664795, "learning_rate": 0.00012371092429456048, "loss": 0.6420151710510253, "step": 255470 }, { "epoch": 1.5186261747240402, "grad_norm": 1.515670657157898, "learning_rate": 0.00012370477215052078, "loss": 0.6270196914672852, "step": 255480 }, { "epoch": 1.5186856168007086, "grad_norm": 1.4293901920318604, "learning_rate": 0.00012369861994092191, "loss": 0.5823801517486572, "step": 255490 }, { "epoch": 1.518745058877377, "grad_norm": 1.3208849430084229, "learning_rate": 0.00012369246766579333, "loss": 0.5910202503204346, "step": 255500 }, { "epoch": 1.5188045009540452, "grad_norm": 1.2625561952590942, "learning_rate": 0.00012368631532516444, "loss": 0.6192515850067138, "step": 255510 }, { "epoch": 1.5188639430307136, "grad_norm": 1.532170057296753, "learning_rate": 0.0001236801629190647, "loss": 0.6028998374938965, "step": 255520 }, { "epoch": 1.518923385107382, "grad_norm": 1.0777480602264404, "learning_rate": 0.00012367401044752354, "loss": 0.5648195266723632, "step": 255530 }, { "epoch": 1.5189828271840504, "grad_norm": 1.167524814605713, "learning_rate": 0.00012366785791057035, "loss": 0.5620670795440674, "step": 255540 }, { "epoch": 1.5190422692607188, "grad_norm": 1.2680720090866089, "learning_rate": 0.00012366170530823465, "loss": 0.5618146896362305, "step": 255550 }, { "epoch": 1.5191017113373873, "grad_norm": 1.7790557146072388, "learning_rate": 0.0001236555526405458, "loss": 0.5900664806365967, "step": 255560 }, { "epoch": 1.5191611534140557, "grad_norm": 1.4142076969146729, "learning_rate": 0.0001236493999075332, "loss": 0.5704782485961915, "step": 255570 }, { "epoch": 1.519220595490724, "grad_norm": 1.3589692115783691, "learning_rate": 0.0001236432471092264, "loss": 0.6138060569763184, "step": 255580 }, { "epoch": 1.5192800375673925, "grad_norm": 1.5007597208023071, "learning_rate": 0.0001236370942456547, "loss": 0.5807652473449707, "step": 255590 }, { "epoch": 1.519339479644061, "grad_norm": 1.070461392402649, "learning_rate": 0.00012363094131684764, "loss": 0.636119031906128, "step": 255600 }, { "epoch": 1.5193989217207293, "grad_norm": 1.1375982761383057, "learning_rate": 0.0001236247883228346, "loss": 0.5811815738677979, "step": 255610 }, { "epoch": 1.5194583637973977, "grad_norm": 1.6211612224578857, "learning_rate": 0.000123618635263645, "loss": 0.5651749610900879, "step": 255620 }, { "epoch": 1.5195178058740662, "grad_norm": 1.5518386363983154, "learning_rate": 0.00012361248213930834, "loss": 0.6200118064880371, "step": 255630 }, { "epoch": 1.5195772479507346, "grad_norm": 1.6025751829147339, "learning_rate": 0.000123606328949854, "loss": 0.6292760848999024, "step": 255640 }, { "epoch": 1.5196366900274028, "grad_norm": 1.6439188718795776, "learning_rate": 0.00012360017569531143, "loss": 0.5608769416809082, "step": 255650 }, { "epoch": 1.5196961321040712, "grad_norm": 1.8160344362258911, "learning_rate": 0.00012359402237571005, "loss": 0.5640645027160645, "step": 255660 }, { "epoch": 1.5197555741807396, "grad_norm": 1.354141116142273, "learning_rate": 0.00012358786899107935, "loss": 0.6081783294677734, "step": 255670 }, { "epoch": 1.519815016257408, "grad_norm": 1.5911345481872559, "learning_rate": 0.0001235817155414487, "loss": 0.5496073722839355, "step": 255680 }, { "epoch": 1.5198744583340762, "grad_norm": 1.9367042779922485, "learning_rate": 0.00012357556202684751, "loss": 0.5956207275390625, "step": 255690 }, { "epoch": 1.5199339004107446, "grad_norm": 2.0458896160125732, "learning_rate": 0.00012356940844730535, "loss": 0.5905416488647461, "step": 255700 }, { "epoch": 1.519993342487413, "grad_norm": 1.4505882263183594, "learning_rate": 0.00012356325480285157, "loss": 0.5654684066772461, "step": 255710 }, { "epoch": 1.5200527845640814, "grad_norm": 1.1041032075881958, "learning_rate": 0.00012355710109351555, "loss": 0.5573602676391601, "step": 255720 }, { "epoch": 1.5201122266407499, "grad_norm": 1.321462869644165, "learning_rate": 0.00012355094731932685, "loss": 0.5614517211914063, "step": 255730 }, { "epoch": 1.5201716687174183, "grad_norm": 1.317808747291565, "learning_rate": 0.0001235447934803148, "loss": 0.5555638313293457, "step": 255740 }, { "epoch": 1.5202311107940867, "grad_norm": 1.4380526542663574, "learning_rate": 0.00012353863957650888, "loss": 0.5649438381195069, "step": 255750 }, { "epoch": 1.520290552870755, "grad_norm": 1.5731791257858276, "learning_rate": 0.0001235324856079386, "loss": 0.6157278060913086, "step": 255760 }, { "epoch": 1.5203499949474235, "grad_norm": 1.7666008472442627, "learning_rate": 0.00012352633157463325, "loss": 0.6207260131835938, "step": 255770 }, { "epoch": 1.520409437024092, "grad_norm": 1.2270234823226929, "learning_rate": 0.00012352017747662236, "loss": 0.6123846054077149, "step": 255780 }, { "epoch": 1.5204688791007603, "grad_norm": 1.5410206317901611, "learning_rate": 0.00012351402331393541, "loss": 0.602896785736084, "step": 255790 }, { "epoch": 1.5205283211774288, "grad_norm": 1.2340470552444458, "learning_rate": 0.00012350786908660178, "loss": 0.5873928070068359, "step": 255800 }, { "epoch": 1.5205877632540972, "grad_norm": 1.70626962184906, "learning_rate": 0.0001235017147946509, "loss": 0.5662163257598877, "step": 255810 }, { "epoch": 1.5206472053307656, "grad_norm": 1.4579483270645142, "learning_rate": 0.0001234955604381122, "loss": 0.5971885681152344, "step": 255820 }, { "epoch": 1.5207066474074338, "grad_norm": 1.5527926683425903, "learning_rate": 0.00012348940601701518, "loss": 0.6631322383880616, "step": 255830 }, { "epoch": 1.5207660894841022, "grad_norm": 1.2145991325378418, "learning_rate": 0.0001234832515313893, "loss": 0.4926135063171387, "step": 255840 }, { "epoch": 1.5208255315607706, "grad_norm": 1.5058144330978394, "learning_rate": 0.00012347709698126388, "loss": 0.5986058235168457, "step": 255850 }, { "epoch": 1.520884973637439, "grad_norm": 1.6499121189117432, "learning_rate": 0.00012347094236666846, "loss": 0.5193269729614258, "step": 255860 }, { "epoch": 1.5209444157141074, "grad_norm": 1.7797948122024536, "learning_rate": 0.00012346478768763243, "loss": 0.602632713317871, "step": 255870 }, { "epoch": 1.5210038577907756, "grad_norm": 1.6202205419540405, "learning_rate": 0.0001234586329441853, "loss": 0.6048975467681885, "step": 255880 }, { "epoch": 1.521063299867444, "grad_norm": 1.3910765647888184, "learning_rate": 0.00012345247813635643, "loss": 0.5496543884277344, "step": 255890 }, { "epoch": 1.5211227419441125, "grad_norm": 1.4924628734588623, "learning_rate": 0.0001234463232641753, "loss": 0.5732454776763916, "step": 255900 }, { "epoch": 1.5211821840207809, "grad_norm": 1.5881381034851074, "learning_rate": 0.00012344016832767135, "loss": 0.5969460487365723, "step": 255910 }, { "epoch": 1.5212416260974493, "grad_norm": 1.4608672857284546, "learning_rate": 0.00012343401332687407, "loss": 0.5750668525695801, "step": 255920 }, { "epoch": 1.5213010681741177, "grad_norm": 1.3087654113769531, "learning_rate": 0.0001234278582618128, "loss": 0.6212047576904297, "step": 255930 }, { "epoch": 1.5213605102507861, "grad_norm": 1.5598981380462646, "learning_rate": 0.0001234217031325171, "loss": 0.6359542369842529, "step": 255940 }, { "epoch": 1.5214199523274545, "grad_norm": 1.160126805305481, "learning_rate": 0.00012341554793901635, "loss": 0.6100819110870361, "step": 255950 }, { "epoch": 1.521479394404123, "grad_norm": 1.3752977848052979, "learning_rate": 0.00012340939268133997, "loss": 0.5082125663757324, "step": 255960 }, { "epoch": 1.5215388364807914, "grad_norm": 1.6354550123214722, "learning_rate": 0.0001234032373595175, "loss": 0.5945643901824951, "step": 255970 }, { "epoch": 1.5215982785574598, "grad_norm": 1.3857457637786865, "learning_rate": 0.00012339708197357826, "loss": 0.5958156108856201, "step": 255980 }, { "epoch": 1.5216577206341282, "grad_norm": 1.1703215837478638, "learning_rate": 0.0001233909265235518, "loss": 0.5320789813995361, "step": 255990 }, { "epoch": 1.5217171627107966, "grad_norm": 1.2342060804367065, "learning_rate": 0.00012338477100946746, "loss": 0.5992259025573731, "step": 256000 }, { "epoch": 1.521776604787465, "grad_norm": 1.6149158477783203, "learning_rate": 0.0001233786154313548, "loss": 0.5328367233276368, "step": 256010 }, { "epoch": 1.5218360468641332, "grad_norm": 1.4409630298614502, "learning_rate": 0.00012337245978924323, "loss": 0.5447281837463379, "step": 256020 }, { "epoch": 1.5218954889408016, "grad_norm": 1.083330512046814, "learning_rate": 0.00012336630408316213, "loss": 0.576174545288086, "step": 256030 }, { "epoch": 1.52195493101747, "grad_norm": 1.672479510307312, "learning_rate": 0.00012336014831314108, "loss": 0.6064521789550781, "step": 256040 }, { "epoch": 1.5220143730941385, "grad_norm": 1.665000081062317, "learning_rate": 0.00012335399247920937, "loss": 0.538077449798584, "step": 256050 }, { "epoch": 1.5220738151708066, "grad_norm": 1.7943044900894165, "learning_rate": 0.00012334783658139655, "loss": 0.647126579284668, "step": 256060 }, { "epoch": 1.522133257247475, "grad_norm": 1.3714556694030762, "learning_rate": 0.00012334168061973205, "loss": 0.5965595245361328, "step": 256070 }, { "epoch": 1.5221926993241435, "grad_norm": 1.7371033430099487, "learning_rate": 0.0001233355245942453, "loss": 0.5715681076049804, "step": 256080 }, { "epoch": 1.5222521414008119, "grad_norm": 1.3146610260009766, "learning_rate": 0.00012332936850496576, "loss": 0.6028857231140137, "step": 256090 }, { "epoch": 1.5223115834774803, "grad_norm": 1.5548681020736694, "learning_rate": 0.00012332321235192288, "loss": 0.5144154071807862, "step": 256100 }, { "epoch": 1.5223710255541487, "grad_norm": 1.5861694812774658, "learning_rate": 0.0001233170561351461, "loss": 0.5795190811157227, "step": 256110 }, { "epoch": 1.5224304676308171, "grad_norm": 1.3036613464355469, "learning_rate": 0.00012331089985466489, "loss": 0.5805420875549316, "step": 256120 }, { "epoch": 1.5224899097074855, "grad_norm": 1.7547253370285034, "learning_rate": 0.00012330474351050866, "loss": 0.6685922145843506, "step": 256130 }, { "epoch": 1.522549351784154, "grad_norm": 1.3485915660858154, "learning_rate": 0.0001232985871027069, "loss": 0.5483110427856446, "step": 256140 }, { "epoch": 1.5226087938608224, "grad_norm": 1.8235349655151367, "learning_rate": 0.00012329243063128906, "loss": 0.5859431266784668, "step": 256150 }, { "epoch": 1.5226682359374908, "grad_norm": 1.5160727500915527, "learning_rate": 0.00012328627409628458, "loss": 0.5800364017486572, "step": 256160 }, { "epoch": 1.5227276780141592, "grad_norm": 1.018129825592041, "learning_rate": 0.00012328011749772287, "loss": 0.5229714870452881, "step": 256170 }, { "epoch": 1.5227871200908276, "grad_norm": 1.8030248880386353, "learning_rate": 0.00012327396083563344, "loss": 0.6036441326141357, "step": 256180 }, { "epoch": 1.522846562167496, "grad_norm": 1.429682970046997, "learning_rate": 0.00012326780411004573, "loss": 0.6021020889282227, "step": 256190 }, { "epoch": 1.5229060042441642, "grad_norm": 1.6614528894424438, "learning_rate": 0.00012326164732098918, "loss": 0.5055063247680665, "step": 256200 }, { "epoch": 1.5229654463208326, "grad_norm": 1.476755976676941, "learning_rate": 0.0001232554904684932, "loss": 0.5869784355163574, "step": 256210 }, { "epoch": 1.523024888397501, "grad_norm": 1.5766558647155762, "learning_rate": 0.00012324933355258732, "loss": 0.619875144958496, "step": 256220 }, { "epoch": 1.5230843304741695, "grad_norm": 2.031604528427124, "learning_rate": 0.00012324317657330097, "loss": 0.6225152969360351, "step": 256230 }, { "epoch": 1.5231437725508379, "grad_norm": 1.8560479879379272, "learning_rate": 0.00012323701953066354, "loss": 0.6012240886688233, "step": 256240 }, { "epoch": 1.523203214627506, "grad_norm": 1.6152278184890747, "learning_rate": 0.0001232308624247046, "loss": 0.5948861598968506, "step": 256250 }, { "epoch": 1.5232626567041745, "grad_norm": 1.6110988855361938, "learning_rate": 0.00012322470525545352, "loss": 0.5711566925048828, "step": 256260 }, { "epoch": 1.523322098780843, "grad_norm": 1.5739214420318604, "learning_rate": 0.00012321854802293972, "loss": 0.5380177021026611, "step": 256270 }, { "epoch": 1.5233815408575113, "grad_norm": 1.5979218482971191, "learning_rate": 0.00012321239072719275, "loss": 0.5885268211364746, "step": 256280 }, { "epoch": 1.5234409829341797, "grad_norm": 1.3720930814743042, "learning_rate": 0.00012320623336824202, "loss": 0.5441887855529786, "step": 256290 }, { "epoch": 1.5235004250108481, "grad_norm": 1.3979482650756836, "learning_rate": 0.00012320007594611698, "loss": 0.6077689170837403, "step": 256300 }, { "epoch": 1.5235598670875166, "grad_norm": 1.5876176357269287, "learning_rate": 0.0001231939184608471, "loss": 0.5981608390808105, "step": 256310 }, { "epoch": 1.523619309164185, "grad_norm": 1.7741327285766602, "learning_rate": 0.00012318776091246183, "loss": 0.5596096992492676, "step": 256320 }, { "epoch": 1.5236787512408534, "grad_norm": 1.2790443897247314, "learning_rate": 0.0001231816033009906, "loss": 0.5615633010864258, "step": 256330 }, { "epoch": 1.5237381933175218, "grad_norm": 1.5764764547348022, "learning_rate": 0.0001231754456264629, "loss": 0.595008659362793, "step": 256340 }, { "epoch": 1.5237976353941902, "grad_norm": 1.5588897466659546, "learning_rate": 0.00012316928788890817, "loss": 0.583751106262207, "step": 256350 }, { "epoch": 1.5238570774708586, "grad_norm": 1.1831669807434082, "learning_rate": 0.00012316313008835586, "loss": 0.5789036273956298, "step": 256360 }, { "epoch": 1.523916519547527, "grad_norm": 1.8883800506591797, "learning_rate": 0.00012315697222483547, "loss": 0.7041401863098145, "step": 256370 }, { "epoch": 1.5239759616241955, "grad_norm": 1.9464272260665894, "learning_rate": 0.00012315081429837638, "loss": 0.5921824932098388, "step": 256380 }, { "epoch": 1.5240354037008637, "grad_norm": 1.7767531871795654, "learning_rate": 0.00012314465630900814, "loss": 0.6061476707458496, "step": 256390 }, { "epoch": 1.524094845777532, "grad_norm": 1.3158609867095947, "learning_rate": 0.0001231384982567601, "loss": 0.5641092777252197, "step": 256400 }, { "epoch": 1.5241542878542005, "grad_norm": 1.4764496088027954, "learning_rate": 0.00012313234014166185, "loss": 0.5814272880554199, "step": 256410 }, { "epoch": 1.524213729930869, "grad_norm": 1.3750925064086914, "learning_rate": 0.00012312618196374273, "loss": 0.6497961044311523, "step": 256420 }, { "epoch": 1.524273172007537, "grad_norm": 1.338284969329834, "learning_rate": 0.00012312002372303225, "loss": 0.6314798831939697, "step": 256430 }, { "epoch": 1.5243326140842055, "grad_norm": 1.8811968564987183, "learning_rate": 0.00012311386541955988, "loss": 0.6033147811889649, "step": 256440 }, { "epoch": 1.524392056160874, "grad_norm": 1.837441325187683, "learning_rate": 0.00012310770705335503, "loss": 0.5362068176269531, "step": 256450 }, { "epoch": 1.5244514982375423, "grad_norm": 1.5070216655731201, "learning_rate": 0.00012310154862444722, "loss": 0.5980475425720215, "step": 256460 }, { "epoch": 1.5245109403142107, "grad_norm": 1.6468247175216675, "learning_rate": 0.00012309539013286589, "loss": 0.6183089256286621, "step": 256470 }, { "epoch": 1.5245703823908792, "grad_norm": 1.3829236030578613, "learning_rate": 0.0001230892315786405, "loss": 0.5921590805053711, "step": 256480 }, { "epoch": 1.5246298244675476, "grad_norm": 1.4482308626174927, "learning_rate": 0.00012308307296180046, "loss": 0.5956160068511963, "step": 256490 }, { "epoch": 1.524689266544216, "grad_norm": 1.7544658184051514, "learning_rate": 0.0001230769142823753, "loss": 0.5705672264099121, "step": 256500 }, { "epoch": 1.5247487086208844, "grad_norm": 1.7710591554641724, "learning_rate": 0.00012307075554039446, "loss": 0.6129250526428223, "step": 256510 }, { "epoch": 1.5248081506975528, "grad_norm": 1.5389785766601562, "learning_rate": 0.0001230645967358874, "loss": 0.6222134113311768, "step": 256520 }, { "epoch": 1.5248675927742212, "grad_norm": 1.2292158603668213, "learning_rate": 0.0001230584378688836, "loss": 0.5545355796813964, "step": 256530 }, { "epoch": 1.5249270348508897, "grad_norm": 1.653631567955017, "learning_rate": 0.00012305227893941243, "loss": 0.5774928092956543, "step": 256540 }, { "epoch": 1.524986476927558, "grad_norm": 1.6051663160324097, "learning_rate": 0.00012304611994750348, "loss": 0.5957771301269531, "step": 256550 }, { "epoch": 1.5250459190042265, "grad_norm": 1.5303020477294922, "learning_rate": 0.00012303996089318614, "loss": 0.6155617713928223, "step": 256560 }, { "epoch": 1.5251053610808947, "grad_norm": 1.138040542602539, "learning_rate": 0.00012303380177648989, "loss": 0.5601938247680665, "step": 256570 }, { "epoch": 1.525164803157563, "grad_norm": 1.371610164642334, "learning_rate": 0.00012302764259744422, "loss": 0.5283886909484863, "step": 256580 }, { "epoch": 1.5252242452342315, "grad_norm": 1.7201340198516846, "learning_rate": 0.00012302148335607854, "loss": 0.5655177116394043, "step": 256590 }, { "epoch": 1.5252836873109, "grad_norm": 1.650164008140564, "learning_rate": 0.00012301532405242232, "loss": 0.5005655288696289, "step": 256600 }, { "epoch": 1.5253431293875683, "grad_norm": 1.6218374967575073, "learning_rate": 0.00012300916468650506, "loss": 0.5491838455200195, "step": 256610 }, { "epoch": 1.5254025714642365, "grad_norm": 1.4794915914535522, "learning_rate": 0.00012300300525835622, "loss": 0.5970441818237304, "step": 256620 }, { "epoch": 1.525462013540905, "grad_norm": 1.546764612197876, "learning_rate": 0.00012299684576800522, "loss": 0.5940698146820068, "step": 256630 }, { "epoch": 1.5255214556175734, "grad_norm": 1.847381591796875, "learning_rate": 0.0001229906862154816, "loss": 0.5483862876892089, "step": 256640 }, { "epoch": 1.5255808976942418, "grad_norm": 1.4280985593795776, "learning_rate": 0.00012298452660081474, "loss": 0.6294213771820069, "step": 256650 }, { "epoch": 1.5256403397709102, "grad_norm": 1.4592623710632324, "learning_rate": 0.00012297836692403417, "loss": 0.5624827384948731, "step": 256660 }, { "epoch": 1.5256997818475786, "grad_norm": 1.5919755697250366, "learning_rate": 0.0001229722071851693, "loss": 0.5613485336303711, "step": 256670 }, { "epoch": 1.525759223924247, "grad_norm": 1.2378051280975342, "learning_rate": 0.0001229660473842497, "loss": 0.5797454833984375, "step": 256680 }, { "epoch": 1.5258186660009154, "grad_norm": 1.538846492767334, "learning_rate": 0.00012295988752130473, "loss": 0.5944397449493408, "step": 256690 }, { "epoch": 1.5258781080775838, "grad_norm": 1.2966079711914062, "learning_rate": 0.00012295372759636388, "loss": 0.6010924339294433, "step": 256700 }, { "epoch": 1.5259375501542523, "grad_norm": 1.6556309461593628, "learning_rate": 0.00012294756760945666, "loss": 0.5885263442993164, "step": 256710 }, { "epoch": 1.5259969922309207, "grad_norm": 1.4502010345458984, "learning_rate": 0.00012294140756061248, "loss": 0.572538185119629, "step": 256720 }, { "epoch": 1.526056434307589, "grad_norm": 1.1910094022750854, "learning_rate": 0.00012293524744986083, "loss": 0.5517816543579102, "step": 256730 }, { "epoch": 1.5261158763842575, "grad_norm": 1.3859285116195679, "learning_rate": 0.0001229290872772312, "loss": 0.5457413196563721, "step": 256740 }, { "epoch": 1.526175318460926, "grad_norm": 1.4240394830703735, "learning_rate": 0.00012292292704275306, "loss": 0.5874802112579346, "step": 256750 }, { "epoch": 1.526234760537594, "grad_norm": 1.4892816543579102, "learning_rate": 0.00012291676674645584, "loss": 0.5887082099914551, "step": 256760 }, { "epoch": 1.5262942026142625, "grad_norm": 1.6827545166015625, "learning_rate": 0.000122910606388369, "loss": 0.6195611476898193, "step": 256770 }, { "epoch": 1.526353644690931, "grad_norm": 1.4181632995605469, "learning_rate": 0.00012290444596852208, "loss": 0.5786931037902832, "step": 256780 }, { "epoch": 1.5264130867675993, "grad_norm": 1.568888783454895, "learning_rate": 0.0001228982854869445, "loss": 0.5732346534729004, "step": 256790 }, { "epoch": 1.5264725288442675, "grad_norm": 1.985121488571167, "learning_rate": 0.00012289212494366573, "loss": 0.5622568607330323, "step": 256800 }, { "epoch": 1.526531970920936, "grad_norm": 1.3408772945404053, "learning_rate": 0.00012288596433871523, "loss": 0.5810498237609864, "step": 256810 }, { "epoch": 1.5265914129976044, "grad_norm": 1.5139625072479248, "learning_rate": 0.00012287980367212253, "loss": 0.6483423709869385, "step": 256820 }, { "epoch": 1.5266508550742728, "grad_norm": 1.214058518409729, "learning_rate": 0.00012287364294391703, "loss": 0.5609536170959473, "step": 256830 }, { "epoch": 1.5267102971509412, "grad_norm": 1.188377857208252, "learning_rate": 0.00012286748215412826, "loss": 0.5402614593505859, "step": 256840 }, { "epoch": 1.5267697392276096, "grad_norm": 1.1062958240509033, "learning_rate": 0.00012286132130278564, "loss": 0.5665661811828613, "step": 256850 }, { "epoch": 1.526829181304278, "grad_norm": 1.5156939029693604, "learning_rate": 0.00012285516038991863, "loss": 0.5522601127624511, "step": 256860 }, { "epoch": 1.5268886233809464, "grad_norm": 2.032351493835449, "learning_rate": 0.0001228489994155568, "loss": 0.6360782146453857, "step": 256870 }, { "epoch": 1.5269480654576149, "grad_norm": 1.4806835651397705, "learning_rate": 0.0001228428383797295, "loss": 0.5850644111633301, "step": 256880 }, { "epoch": 1.5270075075342833, "grad_norm": 1.6447651386260986, "learning_rate": 0.00012283667728246628, "loss": 0.5576030731201171, "step": 256890 }, { "epoch": 1.5270669496109517, "grad_norm": 1.3795808553695679, "learning_rate": 0.0001228305161237966, "loss": 0.5482451438903808, "step": 256900 }, { "epoch": 1.52712639168762, "grad_norm": 1.522915005683899, "learning_rate": 0.0001228243549037499, "loss": 0.5766167640686035, "step": 256910 }, { "epoch": 1.5271858337642885, "grad_norm": 1.751316785812378, "learning_rate": 0.00012281819362235569, "loss": 0.6036101341247558, "step": 256920 }, { "epoch": 1.527245275840957, "grad_norm": 1.3080055713653564, "learning_rate": 0.00012281203227964345, "loss": 0.5267496585845948, "step": 256930 }, { "epoch": 1.5273047179176251, "grad_norm": 2.288076877593994, "learning_rate": 0.00012280587087564257, "loss": 0.6449820041656494, "step": 256940 }, { "epoch": 1.5273641599942935, "grad_norm": 1.8265546560287476, "learning_rate": 0.00012279970941038267, "loss": 0.6060997486114502, "step": 256950 }, { "epoch": 1.527423602070962, "grad_norm": 1.8253653049468994, "learning_rate": 0.0001227935478838931, "loss": 0.5722006797790528, "step": 256960 }, { "epoch": 1.5274830441476304, "grad_norm": 1.3877754211425781, "learning_rate": 0.0001227873862962034, "loss": 0.5291702270507812, "step": 256970 }, { "epoch": 1.5275424862242988, "grad_norm": 1.550815224647522, "learning_rate": 0.000122781224647343, "loss": 0.5750295639038085, "step": 256980 }, { "epoch": 1.527601928300967, "grad_norm": 1.4882646799087524, "learning_rate": 0.0001227750629373414, "loss": 0.5833463191986084, "step": 256990 }, { "epoch": 1.5276613703776354, "grad_norm": 1.70264732837677, "learning_rate": 0.00012276890116622808, "loss": 0.5757137298583984, "step": 257000 }, { "epoch": 1.5277208124543038, "grad_norm": 1.9522608518600464, "learning_rate": 0.00012276273933403247, "loss": 0.5954007148742676, "step": 257010 }, { "epoch": 1.5277802545309722, "grad_norm": 1.4656965732574463, "learning_rate": 0.00012275657744078414, "loss": 0.5944724082946777, "step": 257020 }, { "epoch": 1.5278396966076406, "grad_norm": 1.6883701086044312, "learning_rate": 0.00012275041548651252, "loss": 0.6143241882324219, "step": 257030 }, { "epoch": 1.527899138684309, "grad_norm": 1.5203213691711426, "learning_rate": 0.00012274425347124702, "loss": 0.5746527671813965, "step": 257040 }, { "epoch": 1.5279585807609775, "grad_norm": 1.253652811050415, "learning_rate": 0.00012273809139501724, "loss": 0.5736371040344238, "step": 257050 }, { "epoch": 1.5280180228376459, "grad_norm": 1.3454011678695679, "learning_rate": 0.00012273192925785258, "loss": 0.6152467727661133, "step": 257060 }, { "epoch": 1.5280774649143143, "grad_norm": 1.2132902145385742, "learning_rate": 0.00012272576705978254, "loss": 0.5976260662078857, "step": 257070 }, { "epoch": 1.5281369069909827, "grad_norm": 1.744828462600708, "learning_rate": 0.00012271960480083656, "loss": 0.5550201892852783, "step": 257080 }, { "epoch": 1.5281963490676511, "grad_norm": 1.7169740200042725, "learning_rate": 0.00012271344248104412, "loss": 0.5802218437194824, "step": 257090 }, { "epoch": 1.5282557911443195, "grad_norm": 1.4054512977600098, "learning_rate": 0.00012270728010043477, "loss": 0.5841959953308106, "step": 257100 }, { "epoch": 1.528315233220988, "grad_norm": 1.410365343093872, "learning_rate": 0.00012270111765903797, "loss": 0.5465850830078125, "step": 257110 }, { "epoch": 1.5283746752976564, "grad_norm": 1.5670121908187866, "learning_rate": 0.0001226949551568831, "loss": 0.5571834564208984, "step": 257120 }, { "epoch": 1.5284341173743246, "grad_norm": 1.665938377380371, "learning_rate": 0.00012268879259399977, "loss": 0.5929279327392578, "step": 257130 }, { "epoch": 1.528493559450993, "grad_norm": 1.435544729232788, "learning_rate": 0.0001226826299704174, "loss": 0.5919733047485352, "step": 257140 }, { "epoch": 1.5285530015276614, "grad_norm": 1.582341194152832, "learning_rate": 0.00012267646728616544, "loss": 0.5605712890625, "step": 257150 }, { "epoch": 1.5286124436043298, "grad_norm": 1.4584451913833618, "learning_rate": 0.00012267030454127343, "loss": 0.5199896812438964, "step": 257160 }, { "epoch": 1.528671885680998, "grad_norm": 1.1648293733596802, "learning_rate": 0.0001226641417357708, "loss": 0.5630301475524903, "step": 257170 }, { "epoch": 1.5287313277576664, "grad_norm": 1.6733266115188599, "learning_rate": 0.00012265797886968708, "loss": 0.6065079689025878, "step": 257180 }, { "epoch": 1.5287907698343348, "grad_norm": 2.0418968200683594, "learning_rate": 0.00012265181594305172, "loss": 0.5854936122894288, "step": 257190 }, { "epoch": 1.5288502119110032, "grad_norm": 1.428647518157959, "learning_rate": 0.0001226456529558942, "loss": 0.6173226356506347, "step": 257200 }, { "epoch": 1.5289096539876716, "grad_norm": 1.321897029876709, "learning_rate": 0.000122639489908244, "loss": 0.5906517505645752, "step": 257210 }, { "epoch": 1.52896909606434, "grad_norm": 1.3643497228622437, "learning_rate": 0.00012263332680013063, "loss": 0.5946246147155761, "step": 257220 }, { "epoch": 1.5290285381410085, "grad_norm": 1.3881114721298218, "learning_rate": 0.00012262716363158353, "loss": 0.6268361568450928, "step": 257230 }, { "epoch": 1.529087980217677, "grad_norm": 1.5018130540847778, "learning_rate": 0.00012262100040263225, "loss": 0.5705177307128906, "step": 257240 }, { "epoch": 1.5291474222943453, "grad_norm": 1.3241719007492065, "learning_rate": 0.0001226148371133062, "loss": 0.6050947189331055, "step": 257250 }, { "epoch": 1.5292068643710137, "grad_norm": 1.5412006378173828, "learning_rate": 0.00012260867376363488, "loss": 0.5776825904846191, "step": 257260 }, { "epoch": 1.5292663064476821, "grad_norm": 1.7926043272018433, "learning_rate": 0.00012260251035364777, "loss": 0.588258171081543, "step": 257270 }, { "epoch": 1.5293257485243505, "grad_norm": 1.3760249614715576, "learning_rate": 0.00012259634688337442, "loss": 0.5911806106567383, "step": 257280 }, { "epoch": 1.529385190601019, "grad_norm": 1.799842357635498, "learning_rate": 0.00012259018335284425, "loss": 0.5741652965545654, "step": 257290 }, { "epoch": 1.5294446326776874, "grad_norm": 1.5353480577468872, "learning_rate": 0.00012258401976208673, "loss": 0.6465848922729492, "step": 257300 }, { "epoch": 1.5295040747543556, "grad_norm": 1.4750070571899414, "learning_rate": 0.0001225778561111314, "loss": 0.520735216140747, "step": 257310 }, { "epoch": 1.529563516831024, "grad_norm": 1.5100727081298828, "learning_rate": 0.0001225716924000077, "loss": 0.5955623626708985, "step": 257320 }, { "epoch": 1.5296229589076924, "grad_norm": 1.3955334424972534, "learning_rate": 0.00012256552862874518, "loss": 0.5801742553710938, "step": 257330 }, { "epoch": 1.5296824009843608, "grad_norm": 1.1049184799194336, "learning_rate": 0.0001225593647973732, "loss": 0.5448231220245361, "step": 257340 }, { "epoch": 1.5297418430610292, "grad_norm": 1.3046424388885498, "learning_rate": 0.00012255320090592134, "loss": 0.5875709533691407, "step": 257350 }, { "epoch": 1.5298012851376974, "grad_norm": 1.502176284790039, "learning_rate": 0.0001225470369544191, "loss": 0.6134725093841553, "step": 257360 }, { "epoch": 1.5298607272143658, "grad_norm": 1.4903733730316162, "learning_rate": 0.00012254087294289592, "loss": 0.6174174308776855, "step": 257370 }, { "epoch": 1.5299201692910342, "grad_norm": 1.5569913387298584, "learning_rate": 0.00012253470887138132, "loss": 0.5920785903930664, "step": 257380 }, { "epoch": 1.5299796113677027, "grad_norm": 1.475525140762329, "learning_rate": 0.00012252854473990477, "loss": 0.5211956977844239, "step": 257390 }, { "epoch": 1.530039053444371, "grad_norm": 1.5978968143463135, "learning_rate": 0.00012252238054849573, "loss": 0.5891098499298095, "step": 257400 }, { "epoch": 1.5300984955210395, "grad_norm": 1.3872599601745605, "learning_rate": 0.0001225162162971837, "loss": 0.5511455059051513, "step": 257410 }, { "epoch": 1.530157937597708, "grad_norm": 1.359292984008789, "learning_rate": 0.00012251005198599823, "loss": 0.5838798522949219, "step": 257420 }, { "epoch": 1.5302173796743763, "grad_norm": 1.5054477453231812, "learning_rate": 0.00012250388761496874, "loss": 0.5541231632232666, "step": 257430 }, { "epoch": 1.5302768217510447, "grad_norm": 1.7023380994796753, "learning_rate": 0.00012249772318412473, "loss": 0.6238295555114746, "step": 257440 }, { "epoch": 1.5303362638277132, "grad_norm": 1.7102149724960327, "learning_rate": 0.0001224915586934957, "loss": 0.5890988826751709, "step": 257450 }, { "epoch": 1.5303957059043816, "grad_norm": 1.311452031135559, "learning_rate": 0.00012248539414311114, "loss": 0.627764892578125, "step": 257460 }, { "epoch": 1.53045514798105, "grad_norm": 1.1882637739181519, "learning_rate": 0.0001224792295330005, "loss": 0.5682726860046386, "step": 257470 }, { "epoch": 1.5305145900577184, "grad_norm": 1.502981185913086, "learning_rate": 0.00012247306486319335, "loss": 0.5796843528747558, "step": 257480 }, { "epoch": 1.5305740321343868, "grad_norm": 1.4676026105880737, "learning_rate": 0.00012246690013371914, "loss": 0.5772114276885987, "step": 257490 }, { "epoch": 1.530633474211055, "grad_norm": 1.709843397140503, "learning_rate": 0.00012246073534460733, "loss": 0.5912232398986816, "step": 257500 }, { "epoch": 1.5306929162877234, "grad_norm": 1.7675087451934814, "learning_rate": 0.00012245457049588743, "loss": 0.6342019081115723, "step": 257510 }, { "epoch": 1.5307523583643918, "grad_norm": 1.4115086793899536, "learning_rate": 0.00012244840558758895, "loss": 0.563897705078125, "step": 257520 }, { "epoch": 1.5308118004410602, "grad_norm": 1.8454900979995728, "learning_rate": 0.0001224422406197413, "loss": 0.5962784767150879, "step": 257530 }, { "epoch": 1.5308712425177284, "grad_norm": 1.5720442533493042, "learning_rate": 0.00012243607559237412, "loss": 0.644442367553711, "step": 257540 }, { "epoch": 1.5309306845943969, "grad_norm": 1.7151983976364136, "learning_rate": 0.0001224299105055168, "loss": 0.6343786239624023, "step": 257550 }, { "epoch": 1.5309901266710653, "grad_norm": 1.4837452173233032, "learning_rate": 0.00012242374535919887, "loss": 0.587384033203125, "step": 257560 }, { "epoch": 1.5310495687477337, "grad_norm": 1.4195090532302856, "learning_rate": 0.00012241758015344974, "loss": 0.6134533882141113, "step": 257570 }, { "epoch": 1.531109010824402, "grad_norm": 1.7324604988098145, "learning_rate": 0.00012241141488829904, "loss": 0.5871082305908203, "step": 257580 }, { "epoch": 1.5311684529010705, "grad_norm": 1.9563292264938354, "learning_rate": 0.00012240524956377616, "loss": 0.596869707107544, "step": 257590 }, { "epoch": 1.531227894977739, "grad_norm": 1.3964030742645264, "learning_rate": 0.00012239908417991058, "loss": 0.5894464015960693, "step": 257600 }, { "epoch": 1.5312873370544073, "grad_norm": 1.5602641105651855, "learning_rate": 0.00012239291873673188, "loss": 0.5738974571228027, "step": 257610 }, { "epoch": 1.5313467791310758, "grad_norm": 1.1862318515777588, "learning_rate": 0.0001223867532342695, "loss": 0.6172131538391114, "step": 257620 }, { "epoch": 1.5314062212077442, "grad_norm": 1.671122431755066, "learning_rate": 0.0001223805876725529, "loss": 0.5937090873718261, "step": 257630 }, { "epoch": 1.5314656632844126, "grad_norm": 1.4315425157546997, "learning_rate": 0.00012237442205161167, "loss": 0.5691427230834961, "step": 257640 }, { "epoch": 1.531525105361081, "grad_norm": 1.7016990184783936, "learning_rate": 0.0001223682563714752, "loss": 0.5503581047058106, "step": 257650 }, { "epoch": 1.5315845474377494, "grad_norm": 1.4714118242263794, "learning_rate": 0.00012236209063217304, "loss": 0.584718656539917, "step": 257660 }, { "epoch": 1.5316439895144178, "grad_norm": 1.5260859727859497, "learning_rate": 0.00012235592483373473, "loss": 0.6064677715301514, "step": 257670 }, { "epoch": 1.531703431591086, "grad_norm": 1.993792176246643, "learning_rate": 0.00012234975897618968, "loss": 0.5734321594238281, "step": 257680 }, { "epoch": 1.5317628736677544, "grad_norm": 1.0295097827911377, "learning_rate": 0.0001223435930595674, "loss": 0.5679776191711425, "step": 257690 }, { "epoch": 1.5318223157444228, "grad_norm": 1.767053484916687, "learning_rate": 0.0001223374270838974, "loss": 0.6072469711303711, "step": 257700 }, { "epoch": 1.5318817578210913, "grad_norm": 1.4309663772583008, "learning_rate": 0.00012233126104920923, "loss": 0.6305377006530761, "step": 257710 }, { "epoch": 1.5319411998977597, "grad_norm": 1.2748167514801025, "learning_rate": 0.0001223250949555323, "loss": 0.6042038917541503, "step": 257720 }, { "epoch": 1.5320006419744279, "grad_norm": 1.4163321256637573, "learning_rate": 0.00012231892880289617, "loss": 0.5984654426574707, "step": 257730 }, { "epoch": 1.5320600840510963, "grad_norm": 1.1524507999420166, "learning_rate": 0.0001223127625913303, "loss": 0.6130570411682129, "step": 257740 }, { "epoch": 1.5321195261277647, "grad_norm": 1.6534141302108765, "learning_rate": 0.0001223065963208642, "loss": 0.5907583236694336, "step": 257750 }, { "epoch": 1.5321789682044331, "grad_norm": 1.9999185800552368, "learning_rate": 0.00012230042999152732, "loss": 0.5852809906005859, "step": 257760 }, { "epoch": 1.5322384102811015, "grad_norm": 1.5697293281555176, "learning_rate": 0.00012229426360334925, "loss": 0.6359662055969239, "step": 257770 }, { "epoch": 1.53229785235777, "grad_norm": 1.7665510177612305, "learning_rate": 0.00012228809715635942, "loss": 0.6472373485565186, "step": 257780 }, { "epoch": 1.5323572944344384, "grad_norm": 1.534288763999939, "learning_rate": 0.00012228193065058735, "loss": 0.559481430053711, "step": 257790 }, { "epoch": 1.5324167365111068, "grad_norm": 1.5575168132781982, "learning_rate": 0.00012227576408606257, "loss": 0.5872255802154541, "step": 257800 }, { "epoch": 1.5324761785877752, "grad_norm": 1.3092399835586548, "learning_rate": 0.0001222695974628145, "loss": 0.6039093971252442, "step": 257810 }, { "epoch": 1.5325356206644436, "grad_norm": 1.5847697257995605, "learning_rate": 0.00012226343078087276, "loss": 0.6490849494934082, "step": 257820 }, { "epoch": 1.532595062741112, "grad_norm": 1.6843584775924683, "learning_rate": 0.0001222572640402667, "loss": 0.6132794380187988, "step": 257830 }, { "epoch": 1.5326545048177804, "grad_norm": 1.2877014875411987, "learning_rate": 0.0001222510972410259, "loss": 0.5386098861694336, "step": 257840 }, { "epoch": 1.5327139468944488, "grad_norm": 1.0568270683288574, "learning_rate": 0.0001222449303831799, "loss": 0.5595632553100586, "step": 257850 }, { "epoch": 1.5327733889711173, "grad_norm": 1.5998239517211914, "learning_rate": 0.00012223876346675812, "loss": 0.5322535991668701, "step": 257860 }, { "epoch": 1.5328328310477854, "grad_norm": 1.2918686866760254, "learning_rate": 0.0001222325964917901, "loss": 0.581693172454834, "step": 257870 }, { "epoch": 1.5328922731244539, "grad_norm": 1.5780197381973267, "learning_rate": 0.00012222642945830534, "loss": 0.5645949840545654, "step": 257880 }, { "epoch": 1.5329517152011223, "grad_norm": 1.9023902416229248, "learning_rate": 0.00012222026236633334, "loss": 0.5158989906311036, "step": 257890 }, { "epoch": 1.5330111572777907, "grad_norm": 1.2390284538269043, "learning_rate": 0.0001222140952159036, "loss": 0.61953706741333, "step": 257900 }, { "epoch": 1.5330705993544589, "grad_norm": 1.478623867034912, "learning_rate": 0.0001222079280070456, "loss": 0.6061731338500976, "step": 257910 }, { "epoch": 1.5331300414311273, "grad_norm": 1.3489367961883545, "learning_rate": 0.00012220176073978888, "loss": 0.6030695915222168, "step": 257920 }, { "epoch": 1.5331894835077957, "grad_norm": 1.524962306022644, "learning_rate": 0.0001221955934141629, "loss": 0.6066105842590332, "step": 257930 }, { "epoch": 1.5332489255844641, "grad_norm": 1.247529149055481, "learning_rate": 0.00012218942603019724, "loss": 0.6004562854766846, "step": 257940 }, { "epoch": 1.5333083676611325, "grad_norm": 1.505575180053711, "learning_rate": 0.0001221832585879213, "loss": 0.5855143547058106, "step": 257950 }, { "epoch": 1.533367809737801, "grad_norm": 1.6315442323684692, "learning_rate": 0.00012217709108736463, "loss": 0.5558152198791504, "step": 257960 }, { "epoch": 1.5334272518144694, "grad_norm": 1.7426193952560425, "learning_rate": 0.00012217092352855677, "loss": 0.5980703353881835, "step": 257970 }, { "epoch": 1.5334866938911378, "grad_norm": 1.2773152589797974, "learning_rate": 0.00012216475591152716, "loss": 0.6048067092895508, "step": 257980 }, { "epoch": 1.5335461359678062, "grad_norm": 1.6867576837539673, "learning_rate": 0.00012215858823630535, "loss": 0.5669117927551269, "step": 257990 }, { "epoch": 1.5336055780444746, "grad_norm": 2.157641887664795, "learning_rate": 0.00012215242050292083, "loss": 0.5931634902954102, "step": 258000 }, { "epoch": 1.533665020121143, "grad_norm": 1.6370543241500854, "learning_rate": 0.0001221462527114031, "loss": 0.6129298686981202, "step": 258010 }, { "epoch": 1.5337244621978114, "grad_norm": 1.2311865091323853, "learning_rate": 0.00012214008486178163, "loss": 0.5781919002532959, "step": 258020 }, { "epoch": 1.5337839042744799, "grad_norm": 1.1600611209869385, "learning_rate": 0.00012213391695408603, "loss": 0.5666188716888427, "step": 258030 }, { "epoch": 1.5338433463511483, "grad_norm": 1.3835487365722656, "learning_rate": 0.0001221277489883457, "loss": 0.5595606803894043, "step": 258040 }, { "epoch": 1.5339027884278165, "grad_norm": 1.4567149877548218, "learning_rate": 0.00012212158096459018, "loss": 0.5793293952941895, "step": 258050 }, { "epoch": 1.5339622305044849, "grad_norm": 1.4386074542999268, "learning_rate": 0.00012211541288284898, "loss": 0.5696436405181885, "step": 258060 }, { "epoch": 1.5340216725811533, "grad_norm": 1.4508744478225708, "learning_rate": 0.0001221092447431516, "loss": 0.5681313514709473, "step": 258070 }, { "epoch": 1.5340811146578217, "grad_norm": 1.4159742593765259, "learning_rate": 0.00012210307654552757, "loss": 0.5716985702514649, "step": 258080 }, { "epoch": 1.5341405567344901, "grad_norm": 1.217093586921692, "learning_rate": 0.00012209690829000634, "loss": 0.5726290702819824, "step": 258090 }, { "epoch": 1.5341999988111583, "grad_norm": 1.2234609127044678, "learning_rate": 0.00012209073997661752, "loss": 0.5719492912292481, "step": 258100 }, { "epoch": 1.5342594408878267, "grad_norm": 1.6650890111923218, "learning_rate": 0.0001220845716053905, "loss": 0.5627330780029297, "step": 258110 }, { "epoch": 1.5343188829644951, "grad_norm": 1.4109911918640137, "learning_rate": 0.00012207840317635482, "loss": 0.6212799072265625, "step": 258120 }, { "epoch": 1.5343783250411636, "grad_norm": 1.4517103433609009, "learning_rate": 0.00012207223468954005, "loss": 0.6019526481628418, "step": 258130 }, { "epoch": 1.534437767117832, "grad_norm": 1.5685498714447021, "learning_rate": 0.00012206606614497563, "loss": 0.5787203788757325, "step": 258140 }, { "epoch": 1.5344972091945004, "grad_norm": 1.543400764465332, "learning_rate": 0.00012205989754269107, "loss": 0.6329580783843994, "step": 258150 }, { "epoch": 1.5345566512711688, "grad_norm": 1.4620965719223022, "learning_rate": 0.00012205372888271598, "loss": 0.5630661010742187, "step": 258160 }, { "epoch": 1.5346160933478372, "grad_norm": 1.645439624786377, "learning_rate": 0.00012204756016507972, "loss": 0.5726609230041504, "step": 258170 }, { "epoch": 1.5346755354245056, "grad_norm": 1.5396932363510132, "learning_rate": 0.0001220413913898119, "loss": 0.5442427158355713, "step": 258180 }, { "epoch": 1.534734977501174, "grad_norm": 1.6966323852539062, "learning_rate": 0.000122035222556942, "loss": 0.5608243942260742, "step": 258190 }, { "epoch": 1.5347944195778425, "grad_norm": 1.282392978668213, "learning_rate": 0.0001220290536664995, "loss": 0.6315258979797364, "step": 258200 }, { "epoch": 1.5348538616545109, "grad_norm": 2.438568353652954, "learning_rate": 0.00012202288471851395, "loss": 0.5549616813659668, "step": 258210 }, { "epoch": 1.5349133037311793, "grad_norm": 1.4089934825897217, "learning_rate": 0.00012201671571301487, "loss": 0.5107677459716797, "step": 258220 }, { "epoch": 1.5349727458078477, "grad_norm": 1.3738378286361694, "learning_rate": 0.00012201054665003175, "loss": 0.5641520023345947, "step": 258230 }, { "epoch": 1.535032187884516, "grad_norm": 1.173058271408081, "learning_rate": 0.00012200437752959406, "loss": 0.5944386482238769, "step": 258240 }, { "epoch": 1.5350916299611843, "grad_norm": 1.5656384229660034, "learning_rate": 0.00012199820835173137, "loss": 0.5358740806579589, "step": 258250 }, { "epoch": 1.5351510720378527, "grad_norm": 1.1957582235336304, "learning_rate": 0.00012199203911647321, "loss": 0.5803980350494384, "step": 258260 }, { "epoch": 1.5352105141145211, "grad_norm": 1.3719847202301025, "learning_rate": 0.00012198586982384898, "loss": 0.5502069473266602, "step": 258270 }, { "epoch": 1.5352699561911893, "grad_norm": 1.3028894662857056, "learning_rate": 0.00012197970047388833, "loss": 0.6265981674194336, "step": 258280 }, { "epoch": 1.5353293982678577, "grad_norm": 1.4381203651428223, "learning_rate": 0.00012197353106662071, "loss": 0.6071950435638428, "step": 258290 }, { "epoch": 1.5353888403445262, "grad_norm": 1.2386422157287598, "learning_rate": 0.00012196736160207556, "loss": 0.5922544479370118, "step": 258300 }, { "epoch": 1.5354482824211946, "grad_norm": 1.8366392850875854, "learning_rate": 0.00012196119208028251, "loss": 0.5490022659301758, "step": 258310 }, { "epoch": 1.535507724497863, "grad_norm": 1.7965611219406128, "learning_rate": 0.00012195502250127105, "loss": 0.5445792198181152, "step": 258320 }, { "epoch": 1.5355671665745314, "grad_norm": 1.1373225450515747, "learning_rate": 0.00012194885286507063, "loss": 0.5778398990631104, "step": 258330 }, { "epoch": 1.5356266086511998, "grad_norm": 2.160416603088379, "learning_rate": 0.00012194268317171083, "loss": 0.5817770004272461, "step": 258340 }, { "epoch": 1.5356860507278682, "grad_norm": 1.7309156656265259, "learning_rate": 0.00012193651342122113, "loss": 0.5895164012908936, "step": 258350 }, { "epoch": 1.5357454928045366, "grad_norm": 1.916845440864563, "learning_rate": 0.00012193034361363104, "loss": 0.624347448348999, "step": 258360 }, { "epoch": 1.535804934881205, "grad_norm": 1.2733309268951416, "learning_rate": 0.00012192417374897007, "loss": 0.5736056327819824, "step": 258370 }, { "epoch": 1.5358643769578735, "grad_norm": 2.0188539028167725, "learning_rate": 0.00012191800382726779, "loss": 0.6680238723754883, "step": 258380 }, { "epoch": 1.535923819034542, "grad_norm": 1.3036335706710815, "learning_rate": 0.00012191183384855367, "loss": 0.6322072505950928, "step": 258390 }, { "epoch": 1.5359832611112103, "grad_norm": 1.4273782968521118, "learning_rate": 0.00012190566381285717, "loss": 0.5793718338012696, "step": 258400 }, { "epoch": 1.5360427031878787, "grad_norm": 1.6326838731765747, "learning_rate": 0.00012189949372020795, "loss": 0.5905121803283692, "step": 258410 }, { "epoch": 1.536102145264547, "grad_norm": 1.4176301956176758, "learning_rate": 0.0001218933235706354, "loss": 0.569594144821167, "step": 258420 }, { "epoch": 1.5361615873412153, "grad_norm": 1.4914562702178955, "learning_rate": 0.00012188715336416907, "loss": 0.6141021728515625, "step": 258430 }, { "epoch": 1.5362210294178837, "grad_norm": 1.414230227470398, "learning_rate": 0.00012188098310083848, "loss": 0.5502904891967774, "step": 258440 }, { "epoch": 1.5362804714945522, "grad_norm": 1.5878382921218872, "learning_rate": 0.00012187481278067316, "loss": 0.6205071449279785, "step": 258450 }, { "epoch": 1.5363399135712206, "grad_norm": 1.451975703239441, "learning_rate": 0.00012186864240370261, "loss": 0.5804174900054931, "step": 258460 }, { "epoch": 1.5363993556478888, "grad_norm": 1.2148326635360718, "learning_rate": 0.00012186247196995637, "loss": 0.5591023445129395, "step": 258470 }, { "epoch": 1.5364587977245572, "grad_norm": 1.6075701713562012, "learning_rate": 0.00012185630147946395, "loss": 0.5167532444000245, "step": 258480 }, { "epoch": 1.5365182398012256, "grad_norm": 1.3936643600463867, "learning_rate": 0.00012185013093225482, "loss": 0.5444618701934815, "step": 258490 }, { "epoch": 1.536577681877894, "grad_norm": 1.4074735641479492, "learning_rate": 0.00012184396032835855, "loss": 0.5879251480102539, "step": 258500 }, { "epoch": 1.5366371239545624, "grad_norm": 1.3445818424224854, "learning_rate": 0.00012183778966780464, "loss": 0.6079250812530518, "step": 258510 }, { "epoch": 1.5366965660312308, "grad_norm": 1.334792137145996, "learning_rate": 0.00012183161895062263, "loss": 0.6367444038391114, "step": 258520 }, { "epoch": 1.5367560081078993, "grad_norm": 1.8146991729736328, "learning_rate": 0.000121825448176842, "loss": 0.57563796043396, "step": 258530 }, { "epoch": 1.5368154501845677, "grad_norm": 1.1347750425338745, "learning_rate": 0.00012181927734649232, "loss": 0.5763402938842773, "step": 258540 }, { "epoch": 1.536874892261236, "grad_norm": 1.5536518096923828, "learning_rate": 0.00012181310645960305, "loss": 0.5488847732543946, "step": 258550 }, { "epoch": 1.5369343343379045, "grad_norm": 1.30717134475708, "learning_rate": 0.00012180693551620375, "loss": 0.5355040073394776, "step": 258560 }, { "epoch": 1.536993776414573, "grad_norm": 1.3441567420959473, "learning_rate": 0.00012180076451632397, "loss": 0.6135969638824463, "step": 258570 }, { "epoch": 1.5370532184912413, "grad_norm": 1.5038933753967285, "learning_rate": 0.00012179459345999311, "loss": 0.5510036468505859, "step": 258580 }, { "epoch": 1.5371126605679097, "grad_norm": 1.5743352174758911, "learning_rate": 0.00012178842234724086, "loss": 0.5556430816650391, "step": 258590 }, { "epoch": 1.5371721026445782, "grad_norm": 1.7831339836120605, "learning_rate": 0.00012178225117809659, "loss": 0.5932548522949219, "step": 258600 }, { "epoch": 1.5372315447212463, "grad_norm": 1.4417473077774048, "learning_rate": 0.00012177607995258986, "loss": 0.5737942218780517, "step": 258610 }, { "epoch": 1.5372909867979148, "grad_norm": 1.266237735748291, "learning_rate": 0.00012176990867075026, "loss": 0.5680706024169921, "step": 258620 }, { "epoch": 1.5373504288745832, "grad_norm": 1.8447147607803345, "learning_rate": 0.00012176373733260724, "loss": 0.615617322921753, "step": 258630 }, { "epoch": 1.5374098709512516, "grad_norm": 1.13424551486969, "learning_rate": 0.00012175756593819035, "loss": 0.5184502601623535, "step": 258640 }, { "epoch": 1.5374693130279198, "grad_norm": 1.450897455215454, "learning_rate": 0.0001217513944875291, "loss": 0.592807674407959, "step": 258650 }, { "epoch": 1.5375287551045882, "grad_norm": 1.905500054359436, "learning_rate": 0.00012174522298065303, "loss": 0.5670000076293945, "step": 258660 }, { "epoch": 1.5375881971812566, "grad_norm": 1.2686611413955688, "learning_rate": 0.00012173905141759165, "loss": 0.5409266471862793, "step": 258670 }, { "epoch": 1.537647639257925, "grad_norm": 1.3818647861480713, "learning_rate": 0.00012173287979837449, "loss": 0.5548703670501709, "step": 258680 }, { "epoch": 1.5377070813345934, "grad_norm": 1.4027856588363647, "learning_rate": 0.00012172670812303106, "loss": 0.6219278335571289, "step": 258690 }, { "epoch": 1.5377665234112619, "grad_norm": 1.0914654731750488, "learning_rate": 0.00012172053639159089, "loss": 0.5729419231414795, "step": 258700 }, { "epoch": 1.5378259654879303, "grad_norm": 1.2624999284744263, "learning_rate": 0.00012171436460408352, "loss": 0.5701916217803955, "step": 258710 }, { "epoch": 1.5378854075645987, "grad_norm": 1.3939621448516846, "learning_rate": 0.00012170819276053844, "loss": 0.5762737274169922, "step": 258720 }, { "epoch": 1.537944849641267, "grad_norm": 1.4306485652923584, "learning_rate": 0.00012170202086098519, "loss": 0.5583078384399414, "step": 258730 }, { "epoch": 1.5380042917179355, "grad_norm": 1.6948906183242798, "learning_rate": 0.00012169584890545332, "loss": 0.5688416004180908, "step": 258740 }, { "epoch": 1.538063733794604, "grad_norm": 1.1803162097930908, "learning_rate": 0.00012168967689397233, "loss": 0.600127124786377, "step": 258750 }, { "epoch": 1.5381231758712723, "grad_norm": 1.414537787437439, "learning_rate": 0.00012168350482657169, "loss": 0.5801926136016846, "step": 258760 }, { "epoch": 1.5381826179479408, "grad_norm": 1.2756223678588867, "learning_rate": 0.00012167733270328103, "loss": 0.5347333908081054, "step": 258770 }, { "epoch": 1.5382420600246092, "grad_norm": 1.201411485671997, "learning_rate": 0.00012167116052412982, "loss": 0.5231222629547119, "step": 258780 }, { "epoch": 1.5383015021012774, "grad_norm": 1.3719351291656494, "learning_rate": 0.00012166498828914759, "loss": 0.6223008155822753, "step": 258790 }, { "epoch": 1.5383609441779458, "grad_norm": 1.3158793449401855, "learning_rate": 0.00012165881599836386, "loss": 0.5526566505432129, "step": 258800 }, { "epoch": 1.5384203862546142, "grad_norm": 1.204394817352295, "learning_rate": 0.00012165264365180817, "loss": 0.5563958644866943, "step": 258810 }, { "epoch": 1.5384798283312826, "grad_norm": 1.6599807739257812, "learning_rate": 0.00012164647124951003, "loss": 0.5824345588684082, "step": 258820 }, { "epoch": 1.538539270407951, "grad_norm": 1.351577639579773, "learning_rate": 0.00012164029879149901, "loss": 0.6069919109344483, "step": 258830 }, { "epoch": 1.5385987124846192, "grad_norm": 1.6699572801589966, "learning_rate": 0.00012163412627780457, "loss": 0.572243595123291, "step": 258840 }, { "epoch": 1.5386581545612876, "grad_norm": 1.6627744436264038, "learning_rate": 0.0001216279537084563, "loss": 0.6192829608917236, "step": 258850 }, { "epoch": 1.538717596637956, "grad_norm": 1.6593164205551147, "learning_rate": 0.00012162178108348369, "loss": 0.5744110107421875, "step": 258860 }, { "epoch": 1.5387770387146245, "grad_norm": 2.381338596343994, "learning_rate": 0.00012161560840291626, "loss": 0.5741193771362305, "step": 258870 }, { "epoch": 1.5388364807912929, "grad_norm": 1.476783037185669, "learning_rate": 0.00012160943566678358, "loss": 0.595142936706543, "step": 258880 }, { "epoch": 1.5388959228679613, "grad_norm": 1.73978590965271, "learning_rate": 0.00012160326287511514, "loss": 0.6346863269805908, "step": 258890 }, { "epoch": 1.5389553649446297, "grad_norm": 1.6271814107894897, "learning_rate": 0.00012159709002794051, "loss": 0.6257269382476807, "step": 258900 }, { "epoch": 1.5390148070212981, "grad_norm": 1.5499173402786255, "learning_rate": 0.00012159091712528914, "loss": 0.5875625610351562, "step": 258910 }, { "epoch": 1.5390742490979665, "grad_norm": 1.2804874181747437, "learning_rate": 0.00012158474416719063, "loss": 0.5891413688659668, "step": 258920 }, { "epoch": 1.539133691174635, "grad_norm": 1.3908535242080688, "learning_rate": 0.00012157857115367452, "loss": 0.5878894805908204, "step": 258930 }, { "epoch": 1.5391931332513034, "grad_norm": 1.3890190124511719, "learning_rate": 0.00012157239808477027, "loss": 0.5161821365356445, "step": 258940 }, { "epoch": 1.5392525753279718, "grad_norm": 1.61272394657135, "learning_rate": 0.00012156622496050746, "loss": 0.6025549888610839, "step": 258950 }, { "epoch": 1.5393120174046402, "grad_norm": 1.41702401638031, "learning_rate": 0.00012156005178091562, "loss": 0.5450850009918213, "step": 258960 }, { "epoch": 1.5393714594813086, "grad_norm": 1.8450028896331787, "learning_rate": 0.0001215538785460243, "loss": 0.6077547073364258, "step": 258970 }, { "epoch": 1.5394309015579768, "grad_norm": 1.248320460319519, "learning_rate": 0.00012154770525586294, "loss": 0.6293153762817383, "step": 258980 }, { "epoch": 1.5394903436346452, "grad_norm": 1.3843413591384888, "learning_rate": 0.00012154153191046116, "loss": 0.6083484649658203, "step": 258990 }, { "epoch": 1.5395497857113136, "grad_norm": 1.1914225816726685, "learning_rate": 0.00012153535850984846, "loss": 0.5959379196166992, "step": 259000 }, { "epoch": 1.539609227787982, "grad_norm": 1.4348912239074707, "learning_rate": 0.00012152918505405438, "loss": 0.62997407913208, "step": 259010 }, { "epoch": 1.5396686698646502, "grad_norm": 1.6435856819152832, "learning_rate": 0.00012152301154310844, "loss": 0.5710065841674805, "step": 259020 }, { "epoch": 1.5397281119413186, "grad_norm": 1.5230070352554321, "learning_rate": 0.00012151683797704021, "loss": 0.6330862045288086, "step": 259030 }, { "epoch": 1.539787554017987, "grad_norm": 1.3125509023666382, "learning_rate": 0.00012151066435587914, "loss": 0.6248310565948486, "step": 259040 }, { "epoch": 1.5398469960946555, "grad_norm": 1.2983906269073486, "learning_rate": 0.00012150449067965483, "loss": 0.6207473754882813, "step": 259050 }, { "epoch": 1.5399064381713239, "grad_norm": 1.29435396194458, "learning_rate": 0.00012149831694839682, "loss": 0.5711565017700195, "step": 259060 }, { "epoch": 1.5399658802479923, "grad_norm": 1.2000761032104492, "learning_rate": 0.00012149214316213458, "loss": 0.5974301338195801, "step": 259070 }, { "epoch": 1.5400253223246607, "grad_norm": 1.2330454587936401, "learning_rate": 0.00012148596932089771, "loss": 0.5842954635620117, "step": 259080 }, { "epoch": 1.5400847644013291, "grad_norm": 1.5249500274658203, "learning_rate": 0.00012147979542471572, "loss": 0.5818964958190918, "step": 259090 }, { "epoch": 1.5401442064779975, "grad_norm": 1.3901170492172241, "learning_rate": 0.00012147362147361811, "loss": 0.6243979454040527, "step": 259100 }, { "epoch": 1.540203648554666, "grad_norm": 1.6849135160446167, "learning_rate": 0.00012146744746763447, "loss": 0.59193115234375, "step": 259110 }, { "epoch": 1.5402630906313344, "grad_norm": 1.5271896123886108, "learning_rate": 0.00012146127340679432, "loss": 0.6159756183624268, "step": 259120 }, { "epoch": 1.5403225327080028, "grad_norm": 1.7394442558288574, "learning_rate": 0.00012145509929112715, "loss": 0.5861623287200928, "step": 259130 }, { "epoch": 1.5403819747846712, "grad_norm": 1.1813629865646362, "learning_rate": 0.00012144892512066256, "loss": 0.5410679817199707, "step": 259140 }, { "epoch": 1.5404414168613396, "grad_norm": 1.3838192224502563, "learning_rate": 0.00012144275089543004, "loss": 0.5801658630371094, "step": 259150 }, { "epoch": 1.5405008589380078, "grad_norm": 1.3826771974563599, "learning_rate": 0.00012143657661545915, "loss": 0.5871628761291504, "step": 259160 }, { "epoch": 1.5405603010146762, "grad_norm": 1.5100873708724976, "learning_rate": 0.00012143040228077942, "loss": 0.5953510761260986, "step": 259170 }, { "epoch": 1.5406197430913446, "grad_norm": 1.304677128791809, "learning_rate": 0.00012142422789142034, "loss": 0.5864835739135742, "step": 259180 }, { "epoch": 1.540679185168013, "grad_norm": 1.6962947845458984, "learning_rate": 0.00012141805344741153, "loss": 0.578482723236084, "step": 259190 }, { "epoch": 1.5407386272446815, "grad_norm": 1.4257327318191528, "learning_rate": 0.00012141187894878246, "loss": 0.5562268257141113, "step": 259200 }, { "epoch": 1.5407980693213497, "grad_norm": 1.3694955110549927, "learning_rate": 0.00012140570439556269, "loss": 0.5944942474365235, "step": 259210 }, { "epoch": 1.540857511398018, "grad_norm": 1.552070140838623, "learning_rate": 0.00012139952978778177, "loss": 0.5518079280853272, "step": 259220 }, { "epoch": 1.5409169534746865, "grad_norm": 1.146283507347107, "learning_rate": 0.00012139335512546921, "loss": 0.5620110511779786, "step": 259230 }, { "epoch": 1.540976395551355, "grad_norm": 1.26029372215271, "learning_rate": 0.0001213871804086546, "loss": 0.6272737979888916, "step": 259240 }, { "epoch": 1.5410358376280233, "grad_norm": 1.898838996887207, "learning_rate": 0.00012138100563736741, "loss": 0.6102485656738281, "step": 259250 }, { "epoch": 1.5410952797046917, "grad_norm": 1.6487479209899902, "learning_rate": 0.00012137483081163721, "loss": 0.6359464645385742, "step": 259260 }, { "epoch": 1.5411547217813601, "grad_norm": 1.5612455606460571, "learning_rate": 0.00012136865593149354, "loss": 0.5042043685913086, "step": 259270 }, { "epoch": 1.5412141638580286, "grad_norm": 1.887488842010498, "learning_rate": 0.00012136248099696592, "loss": 0.564842414855957, "step": 259280 }, { "epoch": 1.541273605934697, "grad_norm": 1.1107254028320312, "learning_rate": 0.00012135630600808393, "loss": 0.5734581470489502, "step": 259290 }, { "epoch": 1.5413330480113654, "grad_norm": 1.5791387557983398, "learning_rate": 0.00012135013096487707, "loss": 0.5774389266967773, "step": 259300 }, { "epoch": 1.5413924900880338, "grad_norm": 1.7701376676559448, "learning_rate": 0.00012134395586737486, "loss": 0.6615967750549316, "step": 259310 }, { "epoch": 1.5414519321647022, "grad_norm": 1.5483686923980713, "learning_rate": 0.0001213377807156069, "loss": 0.6152918815612793, "step": 259320 }, { "epoch": 1.5415113742413706, "grad_norm": 1.6125438213348389, "learning_rate": 0.00012133160550960274, "loss": 0.587157917022705, "step": 259330 }, { "epoch": 1.541570816318039, "grad_norm": 1.228331208229065, "learning_rate": 0.00012132543024939184, "loss": 0.5652748584747315, "step": 259340 }, { "epoch": 1.5416302583947072, "grad_norm": 1.3696191310882568, "learning_rate": 0.00012131925493500378, "loss": 0.5382286548614502, "step": 259350 }, { "epoch": 1.5416897004713757, "grad_norm": 1.520151138305664, "learning_rate": 0.00012131307956646813, "loss": 0.6157550811767578, "step": 259360 }, { "epoch": 1.541749142548044, "grad_norm": 1.5240702629089355, "learning_rate": 0.0001213069041438144, "loss": 0.6087501525878907, "step": 259370 }, { "epoch": 1.5418085846247125, "grad_norm": 1.3723771572113037, "learning_rate": 0.00012130072866707212, "loss": 0.6000736236572266, "step": 259380 }, { "epoch": 1.5418680267013807, "grad_norm": 1.4209046363830566, "learning_rate": 0.00012129455313627087, "loss": 0.5602867603302002, "step": 259390 }, { "epoch": 1.541927468778049, "grad_norm": 1.58113431930542, "learning_rate": 0.00012128837755144014, "loss": 0.6136884689331055, "step": 259400 }, { "epoch": 1.5419869108547175, "grad_norm": 1.4625568389892578, "learning_rate": 0.00012128220191260951, "loss": 0.5777406692504883, "step": 259410 }, { "epoch": 1.542046352931386, "grad_norm": 1.2448650598526, "learning_rate": 0.00012127602621980853, "loss": 0.5414127349853516, "step": 259420 }, { "epoch": 1.5421057950080543, "grad_norm": 1.8443278074264526, "learning_rate": 0.0001212698504730667, "loss": 0.5974907875061035, "step": 259430 }, { "epoch": 1.5421652370847228, "grad_norm": 1.408410906791687, "learning_rate": 0.00012126367467241359, "loss": 0.6127769470214843, "step": 259440 }, { "epoch": 1.5422246791613912, "grad_norm": 1.5285284519195557, "learning_rate": 0.00012125749881787877, "loss": 0.6323314189910889, "step": 259450 }, { "epoch": 1.5422841212380596, "grad_norm": 1.498075008392334, "learning_rate": 0.00012125132290949173, "loss": 0.540340805053711, "step": 259460 }, { "epoch": 1.542343563314728, "grad_norm": 1.7281099557876587, "learning_rate": 0.00012124514694728206, "loss": 0.6023254871368409, "step": 259470 }, { "epoch": 1.5424030053913964, "grad_norm": 1.5143224000930786, "learning_rate": 0.00012123897093127927, "loss": 0.6561349868774414, "step": 259480 }, { "epoch": 1.5424624474680648, "grad_norm": 1.153611660003662, "learning_rate": 0.0001212327948615129, "loss": 0.5787084579467774, "step": 259490 }, { "epoch": 1.5425218895447332, "grad_norm": 1.4584234952926636, "learning_rate": 0.00012122661873801253, "loss": 0.5903915405273438, "step": 259500 }, { "epoch": 1.5425813316214017, "grad_norm": 1.374635100364685, "learning_rate": 0.00012122044256080768, "loss": 0.6149006843566894, "step": 259510 }, { "epoch": 1.54264077369807, "grad_norm": 1.4805182218551636, "learning_rate": 0.0001212142663299279, "loss": 0.5163050651550293, "step": 259520 }, { "epoch": 1.5427002157747383, "grad_norm": 1.292203426361084, "learning_rate": 0.00012120809004540272, "loss": 0.585236644744873, "step": 259530 }, { "epoch": 1.5427596578514067, "grad_norm": 2.529613494873047, "learning_rate": 0.0001212019137072617, "loss": 0.5695475101470947, "step": 259540 }, { "epoch": 1.542819099928075, "grad_norm": 1.7211557626724243, "learning_rate": 0.00012119573731553444, "loss": 0.6053696155548096, "step": 259550 }, { "epoch": 1.5428785420047435, "grad_norm": 1.1931277513504028, "learning_rate": 0.00012118956087025037, "loss": 0.5429455757141113, "step": 259560 }, { "epoch": 1.542937984081412, "grad_norm": 1.5312501192092896, "learning_rate": 0.00012118338437143912, "loss": 0.6098989009857178, "step": 259570 }, { "epoch": 1.54299742615808, "grad_norm": 1.151439905166626, "learning_rate": 0.0001211772078191302, "loss": 0.525869083404541, "step": 259580 }, { "epoch": 1.5430568682347485, "grad_norm": 1.7018102407455444, "learning_rate": 0.00012117103121335319, "loss": 0.5657771110534668, "step": 259590 }, { "epoch": 1.543116310311417, "grad_norm": 1.504158854484558, "learning_rate": 0.00012116485455413762, "loss": 0.6184207439422608, "step": 259600 }, { "epoch": 1.5431757523880854, "grad_norm": 1.419602870941162, "learning_rate": 0.00012115867784151303, "loss": 0.5790217399597168, "step": 259610 }, { "epoch": 1.5432351944647538, "grad_norm": 2.095255136489868, "learning_rate": 0.00012115250107550897, "loss": 0.5917797565460206, "step": 259620 }, { "epoch": 1.5432946365414222, "grad_norm": 1.8324074745178223, "learning_rate": 0.00012114632425615498, "loss": 0.6061239242553711, "step": 259630 }, { "epoch": 1.5433540786180906, "grad_norm": 1.6911611557006836, "learning_rate": 0.0001211401473834806, "loss": 0.5982532501220703, "step": 259640 }, { "epoch": 1.543413520694759, "grad_norm": 1.1623059511184692, "learning_rate": 0.00012113397045751542, "loss": 0.5703112125396729, "step": 259650 }, { "epoch": 1.5434729627714274, "grad_norm": 1.4635469913482666, "learning_rate": 0.00012112779347828898, "loss": 0.6186492919921875, "step": 259660 }, { "epoch": 1.5435324048480958, "grad_norm": 1.4224151372909546, "learning_rate": 0.00012112161644583078, "loss": 0.5718013286590576, "step": 259670 }, { "epoch": 1.5435918469247643, "grad_norm": 1.6108388900756836, "learning_rate": 0.00012111543936017042, "loss": 0.5486794471740722, "step": 259680 }, { "epoch": 1.5436512890014327, "grad_norm": 1.6145046949386597, "learning_rate": 0.00012110926222133743, "loss": 0.5757004737854003, "step": 259690 }, { "epoch": 1.543710731078101, "grad_norm": 1.0347611904144287, "learning_rate": 0.00012110308502936137, "loss": 0.5708873271942139, "step": 259700 }, { "epoch": 1.5437701731547695, "grad_norm": 1.2663129568099976, "learning_rate": 0.00012109690778427174, "loss": 0.5971696853637696, "step": 259710 }, { "epoch": 1.5438296152314377, "grad_norm": 1.4256528615951538, "learning_rate": 0.00012109073048609816, "loss": 0.5550538063049316, "step": 259720 }, { "epoch": 1.543889057308106, "grad_norm": 1.6276273727416992, "learning_rate": 0.00012108455313487018, "loss": 0.5437181949615478, "step": 259730 }, { "epoch": 1.5439484993847745, "grad_norm": 2.0319983959198, "learning_rate": 0.00012107837573061727, "loss": 0.5847541332244873, "step": 259740 }, { "epoch": 1.544007941461443, "grad_norm": 1.8506733179092407, "learning_rate": 0.00012107219827336905, "loss": 0.587211275100708, "step": 259750 }, { "epoch": 1.5440673835381111, "grad_norm": 1.314581036567688, "learning_rate": 0.00012106602076315505, "loss": 0.609303617477417, "step": 259760 }, { "epoch": 1.5441268256147795, "grad_norm": 1.408996343612671, "learning_rate": 0.00012105984320000481, "loss": 0.5817811012268066, "step": 259770 }, { "epoch": 1.544186267691448, "grad_norm": 1.4993561506271362, "learning_rate": 0.00012105366558394791, "loss": 0.5505466461181641, "step": 259780 }, { "epoch": 1.5442457097681164, "grad_norm": 1.2069405317306519, "learning_rate": 0.0001210474879150139, "loss": 0.5162282943725586, "step": 259790 }, { "epoch": 1.5443051518447848, "grad_norm": 1.659860610961914, "learning_rate": 0.00012104131019323229, "loss": 0.5882832050323487, "step": 259800 }, { "epoch": 1.5443645939214532, "grad_norm": 1.5748116970062256, "learning_rate": 0.00012103513241863267, "loss": 0.563228988647461, "step": 259810 }, { "epoch": 1.5444240359981216, "grad_norm": 1.1217553615570068, "learning_rate": 0.00012102895459124459, "loss": 0.561345100402832, "step": 259820 }, { "epoch": 1.54448347807479, "grad_norm": 1.657395362854004, "learning_rate": 0.00012102277671109759, "loss": 0.594028091430664, "step": 259830 }, { "epoch": 1.5445429201514584, "grad_norm": 1.41569185256958, "learning_rate": 0.00012101659877822123, "loss": 0.5615303993225098, "step": 259840 }, { "epoch": 1.5446023622281269, "grad_norm": 1.2874162197113037, "learning_rate": 0.00012101042079264507, "loss": 0.5592135906219482, "step": 259850 }, { "epoch": 1.5446618043047953, "grad_norm": 1.2329992055892944, "learning_rate": 0.00012100424275439864, "loss": 0.6084687232971191, "step": 259860 }, { "epoch": 1.5447212463814637, "grad_norm": 1.3458445072174072, "learning_rate": 0.0001209980646635115, "loss": 0.568962812423706, "step": 259870 }, { "epoch": 1.544780688458132, "grad_norm": 1.5114070177078247, "learning_rate": 0.00012099188652001328, "loss": 0.592340087890625, "step": 259880 }, { "epoch": 1.5448401305348005, "grad_norm": 1.643620252609253, "learning_rate": 0.00012098570832393337, "loss": 0.6128440856933594, "step": 259890 }, { "epoch": 1.5448995726114687, "grad_norm": 1.8066896200180054, "learning_rate": 0.00012097953007530145, "loss": 0.5596969127655029, "step": 259900 }, { "epoch": 1.5449590146881371, "grad_norm": 1.6088911294937134, "learning_rate": 0.0001209733517741471, "loss": 0.5523542404174805, "step": 259910 }, { "epoch": 1.5450184567648055, "grad_norm": 1.4465051889419556, "learning_rate": 0.00012096717342049977, "loss": 0.5900713920593261, "step": 259920 }, { "epoch": 1.545077898841474, "grad_norm": 1.3776497840881348, "learning_rate": 0.00012096099501438909, "loss": 0.6081417083740235, "step": 259930 }, { "epoch": 1.5451373409181424, "grad_norm": 1.569358468055725, "learning_rate": 0.00012095481655584457, "loss": 0.5501624584197998, "step": 259940 }, { "epoch": 1.5451967829948106, "grad_norm": 1.4604123830795288, "learning_rate": 0.0001209486380448958, "loss": 0.6139747619628906, "step": 259950 }, { "epoch": 1.545256225071479, "grad_norm": 1.5111018419265747, "learning_rate": 0.00012094245948157235, "loss": 0.5598445892333984, "step": 259960 }, { "epoch": 1.5453156671481474, "grad_norm": 1.6237398386001587, "learning_rate": 0.00012093628086590369, "loss": 0.5613332271575928, "step": 259970 }, { "epoch": 1.5453751092248158, "grad_norm": 1.487215518951416, "learning_rate": 0.00012093010219791948, "loss": 0.5846014976501465, "step": 259980 }, { "epoch": 1.5454345513014842, "grad_norm": 1.595255970954895, "learning_rate": 0.0001209239234776492, "loss": 0.6583012104034424, "step": 259990 }, { "epoch": 1.5454939933781526, "grad_norm": 1.695778250694275, "learning_rate": 0.00012091774470512249, "loss": 0.5423497200012207, "step": 260000 }, { "epoch": 1.545553435454821, "grad_norm": 1.5305242538452148, "learning_rate": 0.00012091156588036883, "loss": 0.6227612495422363, "step": 260010 }, { "epoch": 1.5456128775314895, "grad_norm": 1.4349100589752197, "learning_rate": 0.0001209053870034178, "loss": 0.606208324432373, "step": 260020 }, { "epoch": 1.5456723196081579, "grad_norm": 1.0782132148742676, "learning_rate": 0.00012089920807429897, "loss": 0.5362607002258301, "step": 260030 }, { "epoch": 1.5457317616848263, "grad_norm": 1.3944748640060425, "learning_rate": 0.0001208930290930419, "loss": 0.6041160106658936, "step": 260040 }, { "epoch": 1.5457912037614947, "grad_norm": 1.691041111946106, "learning_rate": 0.0001208868500596761, "loss": 0.5798386096954345, "step": 260050 }, { "epoch": 1.5458506458381631, "grad_norm": 1.4388915300369263, "learning_rate": 0.0001208806709742312, "loss": 0.5403939247131347, "step": 260060 }, { "epoch": 1.5459100879148315, "grad_norm": 1.3647485971450806, "learning_rate": 0.00012087449183673674, "loss": 0.6521970748901367, "step": 260070 }, { "epoch": 1.5459695299915, "grad_norm": 1.3120871782302856, "learning_rate": 0.00012086831264722221, "loss": 0.5347630500793457, "step": 260080 }, { "epoch": 1.5460289720681681, "grad_norm": 1.7784557342529297, "learning_rate": 0.00012086213340571728, "loss": 0.5401158332824707, "step": 260090 }, { "epoch": 1.5460884141448366, "grad_norm": 1.2575832605361938, "learning_rate": 0.00012085595411225144, "loss": 0.5506575584411622, "step": 260100 }, { "epoch": 1.546147856221505, "grad_norm": 1.4989595413208008, "learning_rate": 0.00012084977476685424, "loss": 0.5750305652618408, "step": 260110 }, { "epoch": 1.5462072982981734, "grad_norm": 1.156301736831665, "learning_rate": 0.00012084359536955527, "loss": 0.6164185047149658, "step": 260120 }, { "epoch": 1.5462667403748416, "grad_norm": 1.2004185914993286, "learning_rate": 0.00012083741592038411, "loss": 0.5153405666351318, "step": 260130 }, { "epoch": 1.54632618245151, "grad_norm": 1.3754966259002686, "learning_rate": 0.00012083123641937028, "loss": 0.6101322174072266, "step": 260140 }, { "epoch": 1.5463856245281784, "grad_norm": 1.5754194259643555, "learning_rate": 0.00012082505686654333, "loss": 0.5950958251953125, "step": 260150 }, { "epoch": 1.5464450666048468, "grad_norm": 1.5480128526687622, "learning_rate": 0.00012081887726193286, "loss": 0.5844493865966797, "step": 260160 }, { "epoch": 1.5465045086815152, "grad_norm": 1.3280324935913086, "learning_rate": 0.00012081269760556844, "loss": 0.5441179275512695, "step": 260170 }, { "epoch": 1.5465639507581836, "grad_norm": 1.5145158767700195, "learning_rate": 0.00012080651789747959, "loss": 0.5954296112060546, "step": 260180 }, { "epoch": 1.546623392834852, "grad_norm": 1.5348833799362183, "learning_rate": 0.00012080033813769591, "loss": 0.5398147106170654, "step": 260190 }, { "epoch": 1.5466828349115205, "grad_norm": 1.5340181589126587, "learning_rate": 0.0001207941583262469, "loss": 0.5969236373901368, "step": 260200 }, { "epoch": 1.546742276988189, "grad_norm": 1.5365355014801025, "learning_rate": 0.00012078797846316219, "loss": 0.6191300392150879, "step": 260210 }, { "epoch": 1.5468017190648573, "grad_norm": 1.5182149410247803, "learning_rate": 0.00012078179854847133, "loss": 0.6149863243103028, "step": 260220 }, { "epoch": 1.5468611611415257, "grad_norm": 1.0913068056106567, "learning_rate": 0.00012077561858220386, "loss": 0.578850269317627, "step": 260230 }, { "epoch": 1.5469206032181941, "grad_norm": 1.2938055992126465, "learning_rate": 0.00012076943856438934, "loss": 0.5473782539367675, "step": 260240 }, { "epoch": 1.5469800452948625, "grad_norm": 1.3433148860931396, "learning_rate": 0.00012076325849505735, "loss": 0.5685181617736816, "step": 260250 }, { "epoch": 1.547039487371531, "grad_norm": 1.5240068435668945, "learning_rate": 0.00012075707837423745, "loss": 0.5313446044921875, "step": 260260 }, { "epoch": 1.5470989294481992, "grad_norm": 1.3794727325439453, "learning_rate": 0.0001207508982019592, "loss": 0.5715807437896728, "step": 260270 }, { "epoch": 1.5471583715248676, "grad_norm": 1.2637465000152588, "learning_rate": 0.00012074471797825218, "loss": 0.5202876567840576, "step": 260280 }, { "epoch": 1.547217813601536, "grad_norm": 1.3936880826950073, "learning_rate": 0.00012073853770314593, "loss": 0.5747881889343261, "step": 260290 }, { "epoch": 1.5472772556782044, "grad_norm": 1.6311099529266357, "learning_rate": 0.00012073235737667001, "loss": 0.6041975975036621, "step": 260300 }, { "epoch": 1.5473366977548728, "grad_norm": 1.5180253982543945, "learning_rate": 0.00012072617699885402, "loss": 0.685253095626831, "step": 260310 }, { "epoch": 1.547396139831541, "grad_norm": 1.1545451879501343, "learning_rate": 0.0001207199965697275, "loss": 0.5801152229309082, "step": 260320 }, { "epoch": 1.5474555819082094, "grad_norm": 1.4922221899032593, "learning_rate": 0.00012071381608932, "loss": 0.566313362121582, "step": 260330 }, { "epoch": 1.5475150239848778, "grad_norm": 1.4533071517944336, "learning_rate": 0.00012070763555766114, "loss": 0.5776617050170898, "step": 260340 }, { "epoch": 1.5475744660615463, "grad_norm": 1.5383994579315186, "learning_rate": 0.00012070145497478042, "loss": 0.5736896991729736, "step": 260350 }, { "epoch": 1.5476339081382147, "grad_norm": 1.2004224061965942, "learning_rate": 0.00012069527434070747, "loss": 0.5474437236785888, "step": 260360 }, { "epoch": 1.547693350214883, "grad_norm": 1.3453572988510132, "learning_rate": 0.0001206890936554718, "loss": 0.5614899635314942, "step": 260370 }, { "epoch": 1.5477527922915515, "grad_norm": 1.3343645334243774, "learning_rate": 0.000120682912919103, "loss": 0.6060966491699219, "step": 260380 }, { "epoch": 1.54781223436822, "grad_norm": 1.2837364673614502, "learning_rate": 0.00012067673213163062, "loss": 0.5754368782043457, "step": 260390 }, { "epoch": 1.5478716764448883, "grad_norm": 1.485730528831482, "learning_rate": 0.00012067055129308428, "loss": 0.5774789810180664, "step": 260400 }, { "epoch": 1.5479311185215567, "grad_norm": 1.4378468990325928, "learning_rate": 0.0001206643704034935, "loss": 0.5907519340515137, "step": 260410 }, { "epoch": 1.5479905605982252, "grad_norm": 1.7940599918365479, "learning_rate": 0.00012065818946288785, "loss": 0.6313289642333985, "step": 260420 }, { "epoch": 1.5480500026748936, "grad_norm": 1.3762357234954834, "learning_rate": 0.0001206520084712969, "loss": 0.547121810913086, "step": 260430 }, { "epoch": 1.548109444751562, "grad_norm": 1.4043701887130737, "learning_rate": 0.00012064582742875021, "loss": 0.5642229557037354, "step": 260440 }, { "epoch": 1.5481688868282304, "grad_norm": 1.8943288326263428, "learning_rate": 0.0001206396463352774, "loss": 0.6083134651184082, "step": 260450 }, { "epoch": 1.5482283289048986, "grad_norm": 1.4976882934570312, "learning_rate": 0.00012063346519090797, "loss": 0.5846885681152344, "step": 260460 }, { "epoch": 1.548287770981567, "grad_norm": 1.6479791402816772, "learning_rate": 0.00012062728399567154, "loss": 0.5477863311767578, "step": 260470 }, { "epoch": 1.5483472130582354, "grad_norm": 1.7744518518447876, "learning_rate": 0.00012062110274959762, "loss": 0.5905096530914307, "step": 260480 }, { "epoch": 1.5484066551349038, "grad_norm": 1.1094378232955933, "learning_rate": 0.00012061492145271584, "loss": 0.527061653137207, "step": 260490 }, { "epoch": 1.548466097211572, "grad_norm": 1.2570891380310059, "learning_rate": 0.00012060874010505574, "loss": 0.584083080291748, "step": 260500 }, { "epoch": 1.5485255392882404, "grad_norm": 1.4872277975082397, "learning_rate": 0.00012060255870664687, "loss": 0.5495831489562988, "step": 260510 }, { "epoch": 1.5485849813649089, "grad_norm": 1.5188544988632202, "learning_rate": 0.00012059637725751887, "loss": 0.5783544540405273, "step": 260520 }, { "epoch": 1.5486444234415773, "grad_norm": 1.29604971408844, "learning_rate": 0.00012059019575770125, "loss": 0.5577720642089844, "step": 260530 }, { "epoch": 1.5487038655182457, "grad_norm": 1.367846131324768, "learning_rate": 0.00012058401420722358, "loss": 0.6045797348022461, "step": 260540 }, { "epoch": 1.548763307594914, "grad_norm": 1.502671241760254, "learning_rate": 0.00012057783260611544, "loss": 0.6127224922180176, "step": 260550 }, { "epoch": 1.5488227496715825, "grad_norm": 1.4130874872207642, "learning_rate": 0.00012057165095440643, "loss": 0.5442492485046386, "step": 260560 }, { "epoch": 1.548882191748251, "grad_norm": 1.3132864236831665, "learning_rate": 0.00012056546925212606, "loss": 0.5824587345123291, "step": 260570 }, { "epoch": 1.5489416338249193, "grad_norm": 1.701101541519165, "learning_rate": 0.00012055928749930398, "loss": 0.5627537727355957, "step": 260580 }, { "epoch": 1.5490010759015878, "grad_norm": 1.6753944158554077, "learning_rate": 0.00012055310569596971, "loss": 0.5774431228637695, "step": 260590 }, { "epoch": 1.5490605179782562, "grad_norm": 1.3438705205917358, "learning_rate": 0.00012054692384215282, "loss": 0.6053762435913086, "step": 260600 }, { "epoch": 1.5491199600549246, "grad_norm": 1.439003825187683, "learning_rate": 0.00012054074193788287, "loss": 0.5704729080200195, "step": 260610 }, { "epoch": 1.549179402131593, "grad_norm": 1.1346474885940552, "learning_rate": 0.00012053455998318949, "loss": 0.5647436141967773, "step": 260620 }, { "epoch": 1.5492388442082614, "grad_norm": 1.6619175672531128, "learning_rate": 0.00012052837797810224, "loss": 0.5351251602172852, "step": 260630 }, { "epoch": 1.5492982862849296, "grad_norm": 1.3297603130340576, "learning_rate": 0.00012052219592265062, "loss": 0.5515252113342285, "step": 260640 }, { "epoch": 1.549357728361598, "grad_norm": 1.3919340372085571, "learning_rate": 0.00012051601381686426, "loss": 0.5933525085449218, "step": 260650 }, { "epoch": 1.5494171704382664, "grad_norm": 1.4951659440994263, "learning_rate": 0.00012050983166077277, "loss": 0.6005191802978516, "step": 260660 }, { "epoch": 1.5494766125149348, "grad_norm": 1.2570898532867432, "learning_rate": 0.00012050364945440561, "loss": 0.5977005004882813, "step": 260670 }, { "epoch": 1.5495360545916033, "grad_norm": 1.540483832359314, "learning_rate": 0.00012049746719779249, "loss": 0.5273569583892822, "step": 260680 }, { "epoch": 1.5495954966682715, "grad_norm": 1.4912463426589966, "learning_rate": 0.00012049128489096288, "loss": 0.5598843574523926, "step": 260690 }, { "epoch": 1.5496549387449399, "grad_norm": 1.4199929237365723, "learning_rate": 0.0001204851025339464, "loss": 0.605589771270752, "step": 260700 }, { "epoch": 1.5497143808216083, "grad_norm": 1.290842056274414, "learning_rate": 0.00012047892012677265, "loss": 0.5198707580566406, "step": 260710 }, { "epoch": 1.5497738228982767, "grad_norm": 1.412285327911377, "learning_rate": 0.00012047273766947112, "loss": 0.5606040477752685, "step": 260720 }, { "epoch": 1.5498332649749451, "grad_norm": 1.2798691987991333, "learning_rate": 0.00012046655516207146, "loss": 0.5400629043579102, "step": 260730 }, { "epoch": 1.5498927070516135, "grad_norm": 1.6017491817474365, "learning_rate": 0.00012046037260460321, "loss": 0.6014645576477051, "step": 260740 }, { "epoch": 1.549952149128282, "grad_norm": 1.2697807550430298, "learning_rate": 0.00012045418999709595, "loss": 0.5403752803802491, "step": 260750 }, { "epoch": 1.5500115912049504, "grad_norm": 1.7176553010940552, "learning_rate": 0.00012044800733957926, "loss": 0.5600402355194092, "step": 260760 }, { "epoch": 1.5500710332816188, "grad_norm": 1.6729034185409546, "learning_rate": 0.00012044182463208276, "loss": 0.6016899108886719, "step": 260770 }, { "epoch": 1.5501304753582872, "grad_norm": 1.7293906211853027, "learning_rate": 0.00012043564187463594, "loss": 0.5925848484039307, "step": 260780 }, { "epoch": 1.5501899174349556, "grad_norm": 1.921810269355774, "learning_rate": 0.0001204294590672684, "loss": 0.5759649276733398, "step": 260790 }, { "epoch": 1.550249359511624, "grad_norm": 1.5612287521362305, "learning_rate": 0.00012042327621000982, "loss": 0.6379182815551758, "step": 260800 }, { "epoch": 1.5503088015882924, "grad_norm": 1.495323896408081, "learning_rate": 0.00012041709330288963, "loss": 0.6049304485321045, "step": 260810 }, { "epoch": 1.5503682436649608, "grad_norm": 1.4786921739578247, "learning_rate": 0.00012041091034593747, "loss": 0.6232295036315918, "step": 260820 }, { "epoch": 1.550427685741629, "grad_norm": 1.737809658050537, "learning_rate": 0.00012040472733918294, "loss": 0.5614630222320557, "step": 260830 }, { "epoch": 1.5504871278182975, "grad_norm": 1.563673734664917, "learning_rate": 0.00012039854428265558, "loss": 0.5771733283996582, "step": 260840 }, { "epoch": 1.5505465698949659, "grad_norm": 1.5045274496078491, "learning_rate": 0.00012039236117638496, "loss": 0.5987460136413574, "step": 260850 }, { "epoch": 1.5506060119716343, "grad_norm": 1.5651679039001465, "learning_rate": 0.00012038617802040073, "loss": 0.6542207717895507, "step": 260860 }, { "epoch": 1.5506654540483025, "grad_norm": 1.7108056545257568, "learning_rate": 0.00012037999481473242, "loss": 0.5724194526672364, "step": 260870 }, { "epoch": 1.5507248961249709, "grad_norm": 1.9188343286514282, "learning_rate": 0.00012037381155940954, "loss": 0.5369266986846923, "step": 260880 }, { "epoch": 1.5507843382016393, "grad_norm": 1.2593013048171997, "learning_rate": 0.0001203676282544618, "loss": 0.6017271041870117, "step": 260890 }, { "epoch": 1.5508437802783077, "grad_norm": 1.6031543016433716, "learning_rate": 0.0001203614448999187, "loss": 0.633237075805664, "step": 260900 }, { "epoch": 1.5509032223549761, "grad_norm": 1.4368765354156494, "learning_rate": 0.00012035526149580982, "loss": 0.6001489162445068, "step": 260910 }, { "epoch": 1.5509626644316445, "grad_norm": 1.359100103378296, "learning_rate": 0.00012034907804216475, "loss": 0.5583690643310547, "step": 260920 }, { "epoch": 1.551022106508313, "grad_norm": 1.2826142311096191, "learning_rate": 0.00012034289453901309, "loss": 0.5973424911499023, "step": 260930 }, { "epoch": 1.5510815485849814, "grad_norm": 1.3151795864105225, "learning_rate": 0.0001203367109863844, "loss": 0.6139455318450928, "step": 260940 }, { "epoch": 1.5511409906616498, "grad_norm": 1.2733627557754517, "learning_rate": 0.00012033052738430823, "loss": 0.5681931495666503, "step": 260950 }, { "epoch": 1.5512004327383182, "grad_norm": 1.008599877357483, "learning_rate": 0.00012032434373281427, "loss": 0.5184507369995117, "step": 260960 }, { "epoch": 1.5512598748149866, "grad_norm": 1.3388283252716064, "learning_rate": 0.00012031816003193194, "loss": 0.5918147087097168, "step": 260970 }, { "epoch": 1.551319316891655, "grad_norm": 1.5060532093048096, "learning_rate": 0.00012031197628169093, "loss": 0.5719517707824707, "step": 260980 }, { "epoch": 1.5513787589683234, "grad_norm": 1.7516800165176392, "learning_rate": 0.00012030579248212084, "loss": 0.591178035736084, "step": 260990 }, { "epoch": 1.5514382010449919, "grad_norm": 1.5030102729797363, "learning_rate": 0.00012029960863325113, "loss": 0.5715811729431153, "step": 261000 }, { "epoch": 1.55149764312166, "grad_norm": 1.3599138259887695, "learning_rate": 0.00012029342473511151, "loss": 0.5370320320129395, "step": 261010 }, { "epoch": 1.5515570851983285, "grad_norm": 1.7737984657287598, "learning_rate": 0.00012028724078773153, "loss": 0.6163962364196778, "step": 261020 }, { "epoch": 1.5516165272749969, "grad_norm": 1.1468487977981567, "learning_rate": 0.0001202810567911407, "loss": 0.5395769596099853, "step": 261030 }, { "epoch": 1.5516759693516653, "grad_norm": 1.4185426235198975, "learning_rate": 0.00012027487274536868, "loss": 0.5789005279541015, "step": 261040 }, { "epoch": 1.5517354114283337, "grad_norm": 1.8595209121704102, "learning_rate": 0.00012026868865044503, "loss": 0.630236005783081, "step": 261050 }, { "epoch": 1.551794853505002, "grad_norm": 1.3285784721374512, "learning_rate": 0.00012026250450639931, "loss": 0.582205867767334, "step": 261060 }, { "epoch": 1.5518542955816703, "grad_norm": 1.467163324356079, "learning_rate": 0.00012025632031326113, "loss": 0.5163196086883545, "step": 261070 }, { "epoch": 1.5519137376583387, "grad_norm": 1.862449288368225, "learning_rate": 0.00012025013607106005, "loss": 0.577000093460083, "step": 261080 }, { "epoch": 1.5519731797350071, "grad_norm": 1.1259077787399292, "learning_rate": 0.00012024395177982572, "loss": 0.5358498573303223, "step": 261090 }, { "epoch": 1.5520326218116756, "grad_norm": 1.226829171180725, "learning_rate": 0.00012023776743958761, "loss": 0.553072452545166, "step": 261100 }, { "epoch": 1.552092063888344, "grad_norm": 1.5252817869186401, "learning_rate": 0.00012023158305037543, "loss": 0.5787342071533204, "step": 261110 }, { "epoch": 1.5521515059650124, "grad_norm": 1.3748290538787842, "learning_rate": 0.00012022539861221867, "loss": 0.590464973449707, "step": 261120 }, { "epoch": 1.5522109480416808, "grad_norm": 1.155409812927246, "learning_rate": 0.00012021921412514692, "loss": 0.542399263381958, "step": 261130 }, { "epoch": 1.5522703901183492, "grad_norm": 1.215603232383728, "learning_rate": 0.00012021302958918983, "loss": 0.5977097511291504, "step": 261140 }, { "epoch": 1.5523298321950176, "grad_norm": 1.7285157442092896, "learning_rate": 0.00012020684500437692, "loss": 0.5790128707885742, "step": 261150 }, { "epoch": 1.552389274271686, "grad_norm": 1.6648545265197754, "learning_rate": 0.00012020066037073778, "loss": 0.5831924438476562, "step": 261160 }, { "epoch": 1.5524487163483545, "grad_norm": 1.7502391338348389, "learning_rate": 0.00012019447568830207, "loss": 0.5574891567230225, "step": 261170 }, { "epoch": 1.5525081584250229, "grad_norm": 1.423030138015747, "learning_rate": 0.00012018829095709927, "loss": 0.5463053703308105, "step": 261180 }, { "epoch": 1.5525676005016913, "grad_norm": 1.5505627393722534, "learning_rate": 0.00012018210617715903, "loss": 0.5730436325073243, "step": 261190 }, { "epoch": 1.5526270425783595, "grad_norm": 1.3617438077926636, "learning_rate": 0.00012017592134851095, "loss": 0.5948392868041992, "step": 261200 }, { "epoch": 1.552686484655028, "grad_norm": 1.4225728511810303, "learning_rate": 0.00012016973647118454, "loss": 0.567960548400879, "step": 261210 }, { "epoch": 1.5527459267316963, "grad_norm": 1.310940146446228, "learning_rate": 0.00012016355154520947, "loss": 0.5578327178955078, "step": 261220 }, { "epoch": 1.5528053688083647, "grad_norm": 1.0946894884109497, "learning_rate": 0.00012015736657061527, "loss": 0.540782356262207, "step": 261230 }, { "epoch": 1.552864810885033, "grad_norm": 1.6405482292175293, "learning_rate": 0.00012015118154743157, "loss": 0.5936394214630127, "step": 261240 }, { "epoch": 1.5529242529617013, "grad_norm": 0.931247353553772, "learning_rate": 0.00012014499647568791, "loss": 0.5567213535308838, "step": 261250 }, { "epoch": 1.5529836950383697, "grad_norm": 1.415631651878357, "learning_rate": 0.00012013881135541393, "loss": 0.590989065170288, "step": 261260 }, { "epoch": 1.5530431371150382, "grad_norm": 1.1143622398376465, "learning_rate": 0.00012013262618663918, "loss": 0.5420738220214844, "step": 261270 }, { "epoch": 1.5531025791917066, "grad_norm": 2.0319111347198486, "learning_rate": 0.00012012644096939322, "loss": 0.6199214935302735, "step": 261280 }, { "epoch": 1.553162021268375, "grad_norm": 1.450616478919983, "learning_rate": 0.00012012025570370574, "loss": 0.5981229782104492, "step": 261290 }, { "epoch": 1.5532214633450434, "grad_norm": 1.3563047647476196, "learning_rate": 0.00012011407038960622, "loss": 0.5587875366210937, "step": 261300 }, { "epoch": 1.5532809054217118, "grad_norm": 1.2758638858795166, "learning_rate": 0.0001201078850271243, "loss": 0.6175085067749023, "step": 261310 }, { "epoch": 1.5533403474983802, "grad_norm": 1.4477643966674805, "learning_rate": 0.00012010169961628956, "loss": 0.5617724895477295, "step": 261320 }, { "epoch": 1.5533997895750487, "grad_norm": 1.4788480997085571, "learning_rate": 0.0001200955141571316, "loss": 0.5709989547729493, "step": 261330 }, { "epoch": 1.553459231651717, "grad_norm": 1.6204612255096436, "learning_rate": 0.00012008932864967999, "loss": 0.5965682983398437, "step": 261340 }, { "epoch": 1.5535186737283855, "grad_norm": 1.851485013961792, "learning_rate": 0.00012008314309396434, "loss": 0.6037431716918945, "step": 261350 }, { "epoch": 1.553578115805054, "grad_norm": 1.6983622312545776, "learning_rate": 0.00012007695749001422, "loss": 0.5909725189208984, "step": 261360 }, { "epoch": 1.5536375578817223, "grad_norm": 1.5462336540222168, "learning_rate": 0.00012007077183785922, "loss": 0.564120101928711, "step": 261370 }, { "epoch": 1.5536969999583905, "grad_norm": 1.8552484512329102, "learning_rate": 0.00012006458613752896, "loss": 0.6050300121307373, "step": 261380 }, { "epoch": 1.553756442035059, "grad_norm": 1.4620048999786377, "learning_rate": 0.000120058400389053, "loss": 0.5258872032165527, "step": 261390 }, { "epoch": 1.5538158841117273, "grad_norm": 1.489277958869934, "learning_rate": 0.00012005221459246094, "loss": 0.5795641422271729, "step": 261400 }, { "epoch": 1.5538753261883957, "grad_norm": 1.7181177139282227, "learning_rate": 0.00012004602874778236, "loss": 0.5850178718566894, "step": 261410 }, { "epoch": 1.5539347682650642, "grad_norm": 1.5143975019454956, "learning_rate": 0.00012003984285504689, "loss": 0.5875742912292481, "step": 261420 }, { "epoch": 1.5539942103417324, "grad_norm": 1.8163563013076782, "learning_rate": 0.00012003365691428406, "loss": 0.6166796207427978, "step": 261430 }, { "epoch": 1.5540536524184008, "grad_norm": 1.5744231939315796, "learning_rate": 0.0001200274709255235, "loss": 0.5849774360656739, "step": 261440 }, { "epoch": 1.5541130944950692, "grad_norm": 1.8729970455169678, "learning_rate": 0.00012002128488879483, "loss": 0.5603920459747315, "step": 261450 }, { "epoch": 1.5541725365717376, "grad_norm": 1.564606785774231, "learning_rate": 0.00012001509880412755, "loss": 0.6156332492828369, "step": 261460 }, { "epoch": 1.554231978648406, "grad_norm": 2.1272735595703125, "learning_rate": 0.00012000891267155134, "loss": 0.576130485534668, "step": 261470 }, { "epoch": 1.5542914207250744, "grad_norm": 1.2136402130126953, "learning_rate": 0.00012000272649109579, "loss": 0.5687014102935791, "step": 261480 }, { "epoch": 1.5543508628017428, "grad_norm": 1.439782977104187, "learning_rate": 0.00011999654026279043, "loss": 0.5604893207550049, "step": 261490 }, { "epoch": 1.5544103048784113, "grad_norm": 1.4732451438903809, "learning_rate": 0.0001199903539866649, "loss": 0.5798823833465576, "step": 261500 }, { "epoch": 1.5544697469550797, "grad_norm": 1.8038973808288574, "learning_rate": 0.0001199841676627488, "loss": 0.6226273536682129, "step": 261510 }, { "epoch": 1.554529189031748, "grad_norm": 1.551527976989746, "learning_rate": 0.00011997798129107167, "loss": 0.5688629627227784, "step": 261520 }, { "epoch": 1.5545886311084165, "grad_norm": 1.2907705307006836, "learning_rate": 0.00011997179487166314, "loss": 0.6212737083435058, "step": 261530 }, { "epoch": 1.554648073185085, "grad_norm": 1.4897186756134033, "learning_rate": 0.00011996560840455285, "loss": 0.5847395420074463, "step": 261540 }, { "epoch": 1.5547075152617533, "grad_norm": 1.6032326221466064, "learning_rate": 0.00011995942188977028, "loss": 0.5663044452667236, "step": 261550 }, { "epoch": 1.5547669573384217, "grad_norm": 1.44796884059906, "learning_rate": 0.00011995323532734513, "loss": 0.5968403816223145, "step": 261560 }, { "epoch": 1.55482639941509, "grad_norm": 1.532078742980957, "learning_rate": 0.00011994704871730696, "loss": 0.4910069465637207, "step": 261570 }, { "epoch": 1.5548858414917583, "grad_norm": 1.3550363779067993, "learning_rate": 0.00011994086205968533, "loss": 0.5767516613006591, "step": 261580 }, { "epoch": 1.5549452835684268, "grad_norm": 1.4232151508331299, "learning_rate": 0.00011993467535450989, "loss": 0.5480917453765869, "step": 261590 }, { "epoch": 1.5550047256450952, "grad_norm": 1.557434320449829, "learning_rate": 0.00011992848860181018, "loss": 0.6036473274230957, "step": 261600 }, { "epoch": 1.5550641677217634, "grad_norm": 1.267322301864624, "learning_rate": 0.00011992230180161585, "loss": 0.5620844841003418, "step": 261610 }, { "epoch": 1.5551236097984318, "grad_norm": 1.4582959413528442, "learning_rate": 0.00011991611495395646, "loss": 0.5742815494537353, "step": 261620 }, { "epoch": 1.5551830518751002, "grad_norm": 1.3890775442123413, "learning_rate": 0.00011990992805886163, "loss": 0.5551506042480469, "step": 261630 }, { "epoch": 1.5552424939517686, "grad_norm": 1.301581621170044, "learning_rate": 0.00011990374111636096, "loss": 0.5632472991943359, "step": 261640 }, { "epoch": 1.555301936028437, "grad_norm": 1.3165770769119263, "learning_rate": 0.00011989755412648398, "loss": 0.5958669662475586, "step": 261650 }, { "epoch": 1.5553613781051054, "grad_norm": 1.433374047279358, "learning_rate": 0.00011989136708926036, "loss": 0.5649373531341553, "step": 261660 }, { "epoch": 1.5554208201817739, "grad_norm": 1.4342448711395264, "learning_rate": 0.00011988518000471969, "loss": 0.6010485172271729, "step": 261670 }, { "epoch": 1.5554802622584423, "grad_norm": 1.5770171880722046, "learning_rate": 0.00011987899287289152, "loss": 0.6028880596160888, "step": 261680 }, { "epoch": 1.5555397043351107, "grad_norm": 1.3028444051742554, "learning_rate": 0.00011987280569380548, "loss": 0.5014763832092285, "step": 261690 }, { "epoch": 1.555599146411779, "grad_norm": 1.7618019580841064, "learning_rate": 0.00011986661846749119, "loss": 0.6137588500976563, "step": 261700 }, { "epoch": 1.5556585884884475, "grad_norm": 1.3083105087280273, "learning_rate": 0.00011986043119397822, "loss": 0.5972400665283203, "step": 261710 }, { "epoch": 1.555718030565116, "grad_norm": 1.359286904335022, "learning_rate": 0.00011985424387329613, "loss": 0.5643369197845459, "step": 261720 }, { "epoch": 1.5557774726417843, "grad_norm": 1.3830010890960693, "learning_rate": 0.0001198480565054746, "loss": 0.5848390102386475, "step": 261730 }, { "epoch": 1.5558369147184528, "grad_norm": 1.344312310218811, "learning_rate": 0.00011984186909054316, "loss": 0.6141546249389649, "step": 261740 }, { "epoch": 1.555896356795121, "grad_norm": 1.5028027296066284, "learning_rate": 0.00011983568162853143, "loss": 0.6041818141937256, "step": 261750 }, { "epoch": 1.5559557988717894, "grad_norm": 1.4472596645355225, "learning_rate": 0.00011982949411946905, "loss": 0.5899163722991944, "step": 261760 }, { "epoch": 1.5560152409484578, "grad_norm": 1.531233310699463, "learning_rate": 0.00011982330656338554, "loss": 0.5867786884307862, "step": 261770 }, { "epoch": 1.5560746830251262, "grad_norm": 1.5218898057937622, "learning_rate": 0.00011981711896031056, "loss": 0.5719281196594238, "step": 261780 }, { "epoch": 1.5561341251017946, "grad_norm": 1.4984240531921387, "learning_rate": 0.0001198109313102737, "loss": 0.5470762252807617, "step": 261790 }, { "epoch": 1.5561935671784628, "grad_norm": 1.9269171953201294, "learning_rate": 0.00011980474361330454, "loss": 0.5770236015319824, "step": 261800 }, { "epoch": 1.5562530092551312, "grad_norm": 1.127581000328064, "learning_rate": 0.00011979855586943271, "loss": 0.5430838584899902, "step": 261810 }, { "epoch": 1.5563124513317996, "grad_norm": 1.5589951276779175, "learning_rate": 0.00011979236807868779, "loss": 0.5539702892303466, "step": 261820 }, { "epoch": 1.556371893408468, "grad_norm": 1.2058801651000977, "learning_rate": 0.00011978618024109933, "loss": 0.5899406433105469, "step": 261830 }, { "epoch": 1.5564313354851365, "grad_norm": 1.62465238571167, "learning_rate": 0.00011977999235669701, "loss": 0.5786625862121582, "step": 261840 }, { "epoch": 1.5564907775618049, "grad_norm": 1.275428056716919, "learning_rate": 0.00011977380442551042, "loss": 0.5639150619506836, "step": 261850 }, { "epoch": 1.5565502196384733, "grad_norm": 1.6625080108642578, "learning_rate": 0.00011976761644756913, "loss": 0.6220148086547852, "step": 261860 }, { "epoch": 1.5566096617151417, "grad_norm": 1.1107559204101562, "learning_rate": 0.00011976142842290277, "loss": 0.5833378791809082, "step": 261870 }, { "epoch": 1.5566691037918101, "grad_norm": 1.105262041091919, "learning_rate": 0.00011975524035154091, "loss": 0.5446661472320556, "step": 261880 }, { "epoch": 1.5567285458684785, "grad_norm": 1.7715001106262207, "learning_rate": 0.0001197490522335132, "loss": 0.5825847625732422, "step": 261890 }, { "epoch": 1.556787987945147, "grad_norm": 1.6026372909545898, "learning_rate": 0.00011974286406884917, "loss": 0.5596584796905517, "step": 261900 }, { "epoch": 1.5568474300218154, "grad_norm": 1.5090285539627075, "learning_rate": 0.00011973667585757846, "loss": 0.5585685729980469, "step": 261910 }, { "epoch": 1.5569068720984838, "grad_norm": 1.600711464881897, "learning_rate": 0.00011973048759973071, "loss": 0.5771908283233642, "step": 261920 }, { "epoch": 1.5569663141751522, "grad_norm": 1.1905401945114136, "learning_rate": 0.00011972429929533546, "loss": 0.5850913524627686, "step": 261930 }, { "epoch": 1.5570257562518204, "grad_norm": 1.502626895904541, "learning_rate": 0.00011971811094442239, "loss": 0.5328261375427246, "step": 261940 }, { "epoch": 1.5570851983284888, "grad_norm": 1.4990371465682983, "learning_rate": 0.00011971192254702097, "loss": 0.6008654117584229, "step": 261950 }, { "epoch": 1.5571446404051572, "grad_norm": 1.6084775924682617, "learning_rate": 0.00011970573410316093, "loss": 0.578092098236084, "step": 261960 }, { "epoch": 1.5572040824818256, "grad_norm": 1.8619632720947266, "learning_rate": 0.00011969954561287184, "loss": 0.5929109573364257, "step": 261970 }, { "epoch": 1.5572635245584938, "grad_norm": 2.528564453125, "learning_rate": 0.00011969335707618326, "loss": 0.565528678894043, "step": 261980 }, { "epoch": 1.5573229666351622, "grad_norm": 1.7182791233062744, "learning_rate": 0.00011968716849312487, "loss": 0.5502195358276367, "step": 261990 }, { "epoch": 1.5573824087118306, "grad_norm": 1.3230797052383423, "learning_rate": 0.00011968097986372622, "loss": 0.6526677131652832, "step": 262000 }, { "epoch": 1.557441850788499, "grad_norm": 1.3885055780410767, "learning_rate": 0.0001196747911880169, "loss": 0.5854814052581787, "step": 262010 }, { "epoch": 1.5575012928651675, "grad_norm": 1.1913915872573853, "learning_rate": 0.00011966860246602656, "loss": 0.5780317306518554, "step": 262020 }, { "epoch": 1.557560734941836, "grad_norm": 1.4449090957641602, "learning_rate": 0.00011966241369778479, "loss": 0.6153913974761963, "step": 262030 }, { "epoch": 1.5576201770185043, "grad_norm": 1.8407708406448364, "learning_rate": 0.00011965622488332116, "loss": 0.5798472404479981, "step": 262040 }, { "epoch": 1.5576796190951727, "grad_norm": 1.2493921518325806, "learning_rate": 0.00011965003602266535, "loss": 0.545479154586792, "step": 262050 }, { "epoch": 1.5577390611718411, "grad_norm": 1.259997010231018, "learning_rate": 0.0001196438471158469, "loss": 0.5751762390136719, "step": 262060 }, { "epoch": 1.5577985032485095, "grad_norm": 1.8533504009246826, "learning_rate": 0.00011963765816289543, "loss": 0.5651267051696778, "step": 262070 }, { "epoch": 1.557857945325178, "grad_norm": 1.4261184930801392, "learning_rate": 0.00011963146916384056, "loss": 0.5504230499267578, "step": 262080 }, { "epoch": 1.5579173874018464, "grad_norm": 1.5448909997940063, "learning_rate": 0.0001196252801187119, "loss": 0.5460405349731445, "step": 262090 }, { "epoch": 1.5579768294785148, "grad_norm": 1.4112513065338135, "learning_rate": 0.00011961909102753903, "loss": 0.572847557067871, "step": 262100 }, { "epoch": 1.5580362715551832, "grad_norm": 1.3768177032470703, "learning_rate": 0.00011961290189035156, "loss": 0.5236951828002929, "step": 262110 }, { "epoch": 1.5580957136318514, "grad_norm": 1.605310082435608, "learning_rate": 0.00011960671270717914, "loss": 0.5410032749176026, "step": 262120 }, { "epoch": 1.5581551557085198, "grad_norm": 1.1919951438903809, "learning_rate": 0.00011960052347805133, "loss": 0.5675954818725586, "step": 262130 }, { "epoch": 1.5582145977851882, "grad_norm": 1.502604365348816, "learning_rate": 0.00011959433420299775, "loss": 0.5911491394042969, "step": 262140 }, { "epoch": 1.5582740398618566, "grad_norm": 1.3552488088607788, "learning_rate": 0.00011958814488204803, "loss": 0.5272392272949219, "step": 262150 }, { "epoch": 1.558333481938525, "grad_norm": 1.3656399250030518, "learning_rate": 0.00011958195551523175, "loss": 0.6287888526916504, "step": 262160 }, { "epoch": 1.5583929240151932, "grad_norm": 1.3493314981460571, "learning_rate": 0.0001195757661025785, "loss": 0.5528769493103027, "step": 262170 }, { "epoch": 1.5584523660918617, "grad_norm": 1.5764745473861694, "learning_rate": 0.00011956957664411795, "loss": 0.6276601791381836, "step": 262180 }, { "epoch": 1.55851180816853, "grad_norm": 1.6381419897079468, "learning_rate": 0.00011956338713987966, "loss": 0.6161703586578369, "step": 262190 }, { "epoch": 1.5585712502451985, "grad_norm": 1.5530654191970825, "learning_rate": 0.00011955719758989325, "loss": 0.5823391914367676, "step": 262200 }, { "epoch": 1.558630692321867, "grad_norm": 1.6712545156478882, "learning_rate": 0.00011955100799418833, "loss": 0.5632189750671387, "step": 262210 }, { "epoch": 1.5586901343985353, "grad_norm": 1.841120958328247, "learning_rate": 0.0001195448183527945, "loss": 0.6080357551574707, "step": 262220 }, { "epoch": 1.5587495764752037, "grad_norm": 1.4888520240783691, "learning_rate": 0.00011953862866574139, "loss": 0.5363672733306885, "step": 262230 }, { "epoch": 1.5588090185518721, "grad_norm": 1.4328125715255737, "learning_rate": 0.0001195324389330586, "loss": 0.5617712020874024, "step": 262240 }, { "epoch": 1.5588684606285406, "grad_norm": 1.2995660305023193, "learning_rate": 0.00011952624915477573, "loss": 0.5970481872558594, "step": 262250 }, { "epoch": 1.558927902705209, "grad_norm": 1.3366869688034058, "learning_rate": 0.00011952005933092238, "loss": 0.6018770694732666, "step": 262260 }, { "epoch": 1.5589873447818774, "grad_norm": 1.133211612701416, "learning_rate": 0.00011951386946152821, "loss": 0.5397178649902343, "step": 262270 }, { "epoch": 1.5590467868585458, "grad_norm": 1.4750257730484009, "learning_rate": 0.00011950767954662278, "loss": 0.6068954467773438, "step": 262280 }, { "epoch": 1.5591062289352142, "grad_norm": 1.5735933780670166, "learning_rate": 0.00011950148958623571, "loss": 0.5648306369781494, "step": 262290 }, { "epoch": 1.5591656710118826, "grad_norm": 1.5798606872558594, "learning_rate": 0.00011949529958039664, "loss": 0.5555725574493409, "step": 262300 }, { "epoch": 1.5592251130885508, "grad_norm": 1.8421261310577393, "learning_rate": 0.00011948910952913517, "loss": 0.5652544975280762, "step": 262310 }, { "epoch": 1.5592845551652192, "grad_norm": 1.3335213661193848, "learning_rate": 0.00011948291943248087, "loss": 0.6081618309020996, "step": 262320 }, { "epoch": 1.5593439972418877, "grad_norm": 1.3523645401000977, "learning_rate": 0.0001194767292904634, "loss": 0.5606279850006104, "step": 262330 }, { "epoch": 1.559403439318556, "grad_norm": 1.4593778848648071, "learning_rate": 0.00011947053910311235, "loss": 0.564688777923584, "step": 262340 }, { "epoch": 1.5594628813952243, "grad_norm": 1.5368154048919678, "learning_rate": 0.00011946434887045732, "loss": 0.5387999534606933, "step": 262350 }, { "epoch": 1.5595223234718927, "grad_norm": 1.6311503648757935, "learning_rate": 0.00011945815859252795, "loss": 0.6489039421081543, "step": 262360 }, { "epoch": 1.559581765548561, "grad_norm": 1.4070618152618408, "learning_rate": 0.00011945196826935385, "loss": 0.6054335594177246, "step": 262370 }, { "epoch": 1.5596412076252295, "grad_norm": 1.2795318365097046, "learning_rate": 0.00011944577790096462, "loss": 0.5546103477478027, "step": 262380 }, { "epoch": 1.559700649701898, "grad_norm": 1.7694097757339478, "learning_rate": 0.00011943958748738986, "loss": 0.5508798122406006, "step": 262390 }, { "epoch": 1.5597600917785663, "grad_norm": 2.0569427013397217, "learning_rate": 0.00011943339702865921, "loss": 0.5896636486053467, "step": 262400 }, { "epoch": 1.5598195338552348, "grad_norm": 1.6925132274627686, "learning_rate": 0.00011942720652480229, "loss": 0.5794599533081055, "step": 262410 }, { "epoch": 1.5598789759319032, "grad_norm": 1.5358223915100098, "learning_rate": 0.00011942101597584868, "loss": 0.6330692291259765, "step": 262420 }, { "epoch": 1.5599384180085716, "grad_norm": 1.2886691093444824, "learning_rate": 0.00011941482538182798, "loss": 0.5687322616577148, "step": 262430 }, { "epoch": 1.55999786008524, "grad_norm": 1.6113301515579224, "learning_rate": 0.00011940863474276987, "loss": 0.5589933872222901, "step": 262440 }, { "epoch": 1.5600573021619084, "grad_norm": 1.8367420434951782, "learning_rate": 0.0001194024440587039, "loss": 0.5827924251556397, "step": 262450 }, { "epoch": 1.5601167442385768, "grad_norm": 1.6218739748001099, "learning_rate": 0.00011939625332965972, "loss": 0.5969607353210449, "step": 262460 }, { "epoch": 1.5601761863152452, "grad_norm": 1.0881627798080444, "learning_rate": 0.00011939006255566694, "loss": 0.5655629634857178, "step": 262470 }, { "epoch": 1.5602356283919137, "grad_norm": 1.7857059240341187, "learning_rate": 0.00011938387173675516, "loss": 0.6163773536682129, "step": 262480 }, { "epoch": 1.5602950704685818, "grad_norm": 1.6204736232757568, "learning_rate": 0.000119377680872954, "loss": 0.5869337558746338, "step": 262490 }, { "epoch": 1.5603545125452503, "grad_norm": 1.5963371992111206, "learning_rate": 0.0001193714899642931, "loss": 0.57548828125, "step": 262500 }, { "epoch": 1.5604139546219187, "grad_norm": 1.8866370916366577, "learning_rate": 0.00011936529901080207, "loss": 0.5998341560363769, "step": 262510 }, { "epoch": 1.560473396698587, "grad_norm": 1.1966112852096558, "learning_rate": 0.0001193591080125105, "loss": 0.5346901893615723, "step": 262520 }, { "epoch": 1.5605328387752555, "grad_norm": 1.435950756072998, "learning_rate": 0.00011935291696944797, "loss": 0.5469555377960205, "step": 262530 }, { "epoch": 1.5605922808519237, "grad_norm": 1.589127779006958, "learning_rate": 0.00011934672588164417, "loss": 0.6366546630859375, "step": 262540 }, { "epoch": 1.5606517229285921, "grad_norm": 1.164190649986267, "learning_rate": 0.00011934053474912869, "loss": 0.6396552085876465, "step": 262550 }, { "epoch": 1.5607111650052605, "grad_norm": 1.0767254829406738, "learning_rate": 0.00011933434357193117, "loss": 0.5411552906036377, "step": 262560 }, { "epoch": 1.560770607081929, "grad_norm": 1.6081584692001343, "learning_rate": 0.00011932815235008117, "loss": 0.6126428127288819, "step": 262570 }, { "epoch": 1.5608300491585974, "grad_norm": 1.3198864459991455, "learning_rate": 0.00011932196108360833, "loss": 0.5391412734985351, "step": 262580 }, { "epoch": 1.5608894912352658, "grad_norm": 1.7662688493728638, "learning_rate": 0.0001193157697725423, "loss": 0.5797472953796386, "step": 262590 }, { "epoch": 1.5609489333119342, "grad_norm": 1.6121243238449097, "learning_rate": 0.00011930957841691267, "loss": 0.5775736808776856, "step": 262600 }, { "epoch": 1.5610083753886026, "grad_norm": 1.610105037689209, "learning_rate": 0.00011930338701674903, "loss": 0.5821791648864746, "step": 262610 }, { "epoch": 1.561067817465271, "grad_norm": 2.5201096534729004, "learning_rate": 0.00011929719557208105, "loss": 0.6053057670593261, "step": 262620 }, { "epoch": 1.5611272595419394, "grad_norm": 1.1504380702972412, "learning_rate": 0.00011929100408293831, "loss": 0.5950970649719238, "step": 262630 }, { "epoch": 1.5611867016186078, "grad_norm": 1.838181734085083, "learning_rate": 0.00011928481254935047, "loss": 0.5952054977416992, "step": 262640 }, { "epoch": 1.5612461436952763, "grad_norm": 1.350453495979309, "learning_rate": 0.0001192786209713471, "loss": 0.6120966911315918, "step": 262650 }, { "epoch": 1.5613055857719447, "grad_norm": 1.7886403799057007, "learning_rate": 0.00011927242934895784, "loss": 0.5567915916442872, "step": 262660 }, { "epoch": 1.561365027848613, "grad_norm": 1.3115407228469849, "learning_rate": 0.00011926623768221232, "loss": 0.6024575233459473, "step": 262670 }, { "epoch": 1.5614244699252813, "grad_norm": 1.3611494302749634, "learning_rate": 0.00011926004597114014, "loss": 0.5483456134796143, "step": 262680 }, { "epoch": 1.5614839120019497, "grad_norm": 1.3970338106155396, "learning_rate": 0.00011925385421577093, "loss": 0.5675436019897461, "step": 262690 }, { "epoch": 1.561543354078618, "grad_norm": 1.5940804481506348, "learning_rate": 0.00011924766241613428, "loss": 0.5589860916137696, "step": 262700 }, { "epoch": 1.5616027961552865, "grad_norm": 1.426770806312561, "learning_rate": 0.00011924147057225988, "loss": 0.5231861114501953, "step": 262710 }, { "epoch": 1.5616622382319547, "grad_norm": 2.165163278579712, "learning_rate": 0.00011923527868417728, "loss": 0.5354409217834473, "step": 262720 }, { "epoch": 1.5617216803086231, "grad_norm": 1.4617615938186646, "learning_rate": 0.00011922908675191611, "loss": 0.6627604007720947, "step": 262730 }, { "epoch": 1.5617811223852915, "grad_norm": 1.6724969148635864, "learning_rate": 0.00011922289477550604, "loss": 0.5949259757995605, "step": 262740 }, { "epoch": 1.56184056446196, "grad_norm": 1.9452658891677856, "learning_rate": 0.00011921670275497663, "loss": 0.6034263610839844, "step": 262750 }, { "epoch": 1.5619000065386284, "grad_norm": 1.4261767864227295, "learning_rate": 0.00011921051069035751, "loss": 0.5666101455688477, "step": 262760 }, { "epoch": 1.5619594486152968, "grad_norm": 1.6862653493881226, "learning_rate": 0.00011920431858167838, "loss": 0.5762201309204101, "step": 262770 }, { "epoch": 1.5620188906919652, "grad_norm": 1.6944596767425537, "learning_rate": 0.00011919812642896873, "loss": 0.6054922103881836, "step": 262780 }, { "epoch": 1.5620783327686336, "grad_norm": 1.404046893119812, "learning_rate": 0.00011919193423225828, "loss": 0.5786317348480224, "step": 262790 }, { "epoch": 1.562137774845302, "grad_norm": 1.1166967153549194, "learning_rate": 0.00011918574199157664, "loss": 0.5588677406311036, "step": 262800 }, { "epoch": 1.5621972169219704, "grad_norm": 1.8244054317474365, "learning_rate": 0.00011917954970695337, "loss": 0.6147519111633301, "step": 262810 }, { "epoch": 1.5622566589986389, "grad_norm": 1.8699132204055786, "learning_rate": 0.00011917335737841816, "loss": 0.5876177787780762, "step": 262820 }, { "epoch": 1.5623161010753073, "grad_norm": 1.684047818183899, "learning_rate": 0.00011916716500600062, "loss": 0.5825637817382813, "step": 262830 }, { "epoch": 1.5623755431519757, "grad_norm": 1.5571426153182983, "learning_rate": 0.00011916097258973031, "loss": 0.5862692832946778, "step": 262840 }, { "epoch": 1.562434985228644, "grad_norm": 1.331791639328003, "learning_rate": 0.00011915478012963695, "loss": 0.5798767566680908, "step": 262850 }, { "epoch": 1.5624944273053123, "grad_norm": 1.8683439493179321, "learning_rate": 0.0001191485876257501, "loss": 0.5755849838256836, "step": 262860 }, { "epoch": 1.5625538693819807, "grad_norm": 1.0660922527313232, "learning_rate": 0.00011914239507809939, "loss": 0.4985672950744629, "step": 262870 }, { "epoch": 1.5626133114586491, "grad_norm": 1.4019478559494019, "learning_rate": 0.00011913620248671443, "loss": 0.5954888343811036, "step": 262880 }, { "epoch": 1.5626727535353175, "grad_norm": 1.4221621751785278, "learning_rate": 0.00011913000985162488, "loss": 0.5241406917572021, "step": 262890 }, { "epoch": 1.562732195611986, "grad_norm": 1.458507776260376, "learning_rate": 0.00011912381717286036, "loss": 0.5957672119140625, "step": 262900 }, { "epoch": 1.5627916376886541, "grad_norm": 1.9201021194458008, "learning_rate": 0.00011911762445045045, "loss": 0.5930315017700195, "step": 262910 }, { "epoch": 1.5628510797653226, "grad_norm": 1.581107497215271, "learning_rate": 0.00011911143168442482, "loss": 0.5658202648162842, "step": 262920 }, { "epoch": 1.562910521841991, "grad_norm": 1.4512699842453003, "learning_rate": 0.00011910523887481311, "loss": 0.5719199180603027, "step": 262930 }, { "epoch": 1.5629699639186594, "grad_norm": 1.5003931522369385, "learning_rate": 0.00011909904602164486, "loss": 0.5571177482604981, "step": 262940 }, { "epoch": 1.5630294059953278, "grad_norm": 1.2320793867111206, "learning_rate": 0.00011909285312494977, "loss": 0.5640817642211914, "step": 262950 }, { "epoch": 1.5630888480719962, "grad_norm": 1.501612901687622, "learning_rate": 0.00011908666018475747, "loss": 0.5395354270935059, "step": 262960 }, { "epoch": 1.5631482901486646, "grad_norm": 1.7003921270370483, "learning_rate": 0.00011908046720109753, "loss": 0.5950965881347656, "step": 262970 }, { "epoch": 1.563207732225333, "grad_norm": 1.5184072256088257, "learning_rate": 0.00011907427417399962, "loss": 0.536256217956543, "step": 262980 }, { "epoch": 1.5632671743020015, "grad_norm": 1.3100502490997314, "learning_rate": 0.0001190680811034933, "loss": 0.5736285209655761, "step": 262990 }, { "epoch": 1.5633266163786699, "grad_norm": 1.3631913661956787, "learning_rate": 0.00011906188798960831, "loss": 0.5939475059509277, "step": 263000 }, { "epoch": 1.5633860584553383, "grad_norm": 1.5249438285827637, "learning_rate": 0.00011905569483237415, "loss": 0.511278486251831, "step": 263010 }, { "epoch": 1.5634455005320067, "grad_norm": 1.4394959211349487, "learning_rate": 0.00011904950163182053, "loss": 0.5190947532653809, "step": 263020 }, { "epoch": 1.5635049426086751, "grad_norm": 1.407711148262024, "learning_rate": 0.00011904330838797707, "loss": 0.5992025852203369, "step": 263030 }, { "epoch": 1.5635643846853435, "grad_norm": 1.4516927003860474, "learning_rate": 0.00011903711510087334, "loss": 0.5905349731445313, "step": 263040 }, { "epoch": 1.5636238267620117, "grad_norm": 1.2789018154144287, "learning_rate": 0.00011903092177053905, "loss": 0.5247218132019043, "step": 263050 }, { "epoch": 1.5636832688386801, "grad_norm": 1.62654447555542, "learning_rate": 0.00011902472839700374, "loss": 0.6252418518066406, "step": 263060 }, { "epoch": 1.5637427109153486, "grad_norm": 1.6690094470977783, "learning_rate": 0.00011901853498029707, "loss": 0.5502421379089355, "step": 263070 }, { "epoch": 1.563802152992017, "grad_norm": 1.257717251777649, "learning_rate": 0.00011901234152044874, "loss": 0.6319882869720459, "step": 263080 }, { "epoch": 1.5638615950686852, "grad_norm": 1.2891972064971924, "learning_rate": 0.00011900614801748826, "loss": 0.60836763381958, "step": 263090 }, { "epoch": 1.5639210371453536, "grad_norm": 1.49537992477417, "learning_rate": 0.00011899995447144534, "loss": 0.5946565628051758, "step": 263100 }, { "epoch": 1.563980479222022, "grad_norm": 1.657764196395874, "learning_rate": 0.00011899376088234955, "loss": 0.5708501815795899, "step": 263110 }, { "epoch": 1.5640399212986904, "grad_norm": 1.5787700414657593, "learning_rate": 0.00011898756725023057, "loss": 0.5519792079925537, "step": 263120 }, { "epoch": 1.5640993633753588, "grad_norm": 1.6208631992340088, "learning_rate": 0.00011898137357511799, "loss": 0.6192001342773438, "step": 263130 }, { "epoch": 1.5641588054520272, "grad_norm": 1.1482559442520142, "learning_rate": 0.00011897517985704147, "loss": 0.5825231552124024, "step": 263140 }, { "epoch": 1.5642182475286956, "grad_norm": 1.5445983409881592, "learning_rate": 0.00011896898609603063, "loss": 0.5518597602844239, "step": 263150 }, { "epoch": 1.564277689605364, "grad_norm": 1.191357135772705, "learning_rate": 0.00011896279229211507, "loss": 0.581289005279541, "step": 263160 }, { "epoch": 1.5643371316820325, "grad_norm": 1.3266777992248535, "learning_rate": 0.00011895659844532445, "loss": 0.5465604782104492, "step": 263170 }, { "epoch": 1.564396573758701, "grad_norm": 1.2749788761138916, "learning_rate": 0.00011895040455568838, "loss": 0.5714482307434082, "step": 263180 }, { "epoch": 1.5644560158353693, "grad_norm": 1.526512861251831, "learning_rate": 0.00011894421062323651, "loss": 0.6309753894805908, "step": 263190 }, { "epoch": 1.5645154579120377, "grad_norm": 1.679578423500061, "learning_rate": 0.00011893801664799844, "loss": 0.6155329704284668, "step": 263200 }, { "epoch": 1.5645748999887061, "grad_norm": 1.3818556070327759, "learning_rate": 0.00011893182263000385, "loss": 0.5418192386627197, "step": 263210 }, { "epoch": 1.5646343420653746, "grad_norm": 1.2526054382324219, "learning_rate": 0.00011892562856928231, "loss": 0.6360039710998535, "step": 263220 }, { "epoch": 1.5646937841420427, "grad_norm": 1.7362087965011597, "learning_rate": 0.0001189194344658635, "loss": 0.556862735748291, "step": 263230 }, { "epoch": 1.5647532262187112, "grad_norm": 1.7117652893066406, "learning_rate": 0.00011891324031977702, "loss": 0.619810962677002, "step": 263240 }, { "epoch": 1.5648126682953796, "grad_norm": 1.3411575555801392, "learning_rate": 0.0001189070461310525, "loss": 0.5985209941864014, "step": 263250 }, { "epoch": 1.564872110372048, "grad_norm": 1.7806267738342285, "learning_rate": 0.00011890085189971962, "loss": 0.5708424568176269, "step": 263260 }, { "epoch": 1.5649315524487164, "grad_norm": 1.5824251174926758, "learning_rate": 0.00011889465762580795, "loss": 0.6164561748504639, "step": 263270 }, { "epoch": 1.5649909945253846, "grad_norm": 1.6219121217727661, "learning_rate": 0.00011888846330934715, "loss": 0.5963393211364746, "step": 263280 }, { "epoch": 1.565050436602053, "grad_norm": 1.5858970880508423, "learning_rate": 0.00011888226895036685, "loss": 0.6073930263519287, "step": 263290 }, { "epoch": 1.5651098786787214, "grad_norm": 1.6422985792160034, "learning_rate": 0.00011887607454889667, "loss": 0.6326179027557373, "step": 263300 }, { "epoch": 1.5651693207553898, "grad_norm": 1.519670844078064, "learning_rate": 0.00011886988010496624, "loss": 0.5676509857177734, "step": 263310 }, { "epoch": 1.5652287628320583, "grad_norm": 1.679842472076416, "learning_rate": 0.00011886368561860524, "loss": 0.5871612548828125, "step": 263320 }, { "epoch": 1.5652882049087267, "grad_norm": 1.761212944984436, "learning_rate": 0.00011885749108984323, "loss": 0.5904428482055664, "step": 263330 }, { "epoch": 1.565347646985395, "grad_norm": 1.401578664779663, "learning_rate": 0.00011885129651870987, "loss": 0.6181257724761963, "step": 263340 }, { "epoch": 1.5654070890620635, "grad_norm": 1.6276956796646118, "learning_rate": 0.00011884510190523481, "loss": 0.5736849784851075, "step": 263350 }, { "epoch": 1.565466531138732, "grad_norm": 1.4191619157791138, "learning_rate": 0.00011883890724944769, "loss": 0.5898200988769531, "step": 263360 }, { "epoch": 1.5655259732154003, "grad_norm": 1.7845007181167603, "learning_rate": 0.0001188327125513781, "loss": 0.5796645164489747, "step": 263370 }, { "epoch": 1.5655854152920687, "grad_norm": 1.5538995265960693, "learning_rate": 0.00011882651781105572, "loss": 0.5892171859741211, "step": 263380 }, { "epoch": 1.5656448573687372, "grad_norm": 1.228171467781067, "learning_rate": 0.00011882032302851015, "loss": 0.5768229484558105, "step": 263390 }, { "epoch": 1.5657042994454056, "grad_norm": 1.9358220100402832, "learning_rate": 0.00011881412820377105, "loss": 0.573024320602417, "step": 263400 }, { "epoch": 1.5657637415220738, "grad_norm": 1.60398530960083, "learning_rate": 0.00011880793333686804, "loss": 0.657460069656372, "step": 263410 }, { "epoch": 1.5658231835987422, "grad_norm": 1.2417572736740112, "learning_rate": 0.00011880173842783075, "loss": 0.6310039520263672, "step": 263420 }, { "epoch": 1.5658826256754106, "grad_norm": 1.3722238540649414, "learning_rate": 0.0001187955434766888, "loss": 0.5480087757110595, "step": 263430 }, { "epoch": 1.565942067752079, "grad_norm": 1.641265869140625, "learning_rate": 0.00011878934848347187, "loss": 0.6344974517822266, "step": 263440 }, { "epoch": 1.5660015098287474, "grad_norm": 1.583638072013855, "learning_rate": 0.00011878315344820959, "loss": 0.6405277729034424, "step": 263450 }, { "epoch": 1.5660609519054156, "grad_norm": 1.727416753768921, "learning_rate": 0.00011877695837093154, "loss": 0.5283829689025878, "step": 263460 }, { "epoch": 1.566120393982084, "grad_norm": 1.9853544235229492, "learning_rate": 0.00011877076325166741, "loss": 0.5905237197875977, "step": 263470 }, { "epoch": 1.5661798360587524, "grad_norm": 1.5478730201721191, "learning_rate": 0.0001187645680904468, "loss": 0.5508564949035645, "step": 263480 }, { "epoch": 1.5662392781354209, "grad_norm": 1.1761372089385986, "learning_rate": 0.00011875837288729934, "loss": 0.5785077571868896, "step": 263490 }, { "epoch": 1.5662987202120893, "grad_norm": 1.6495587825775146, "learning_rate": 0.00011875217764225472, "loss": 0.6225201606750488, "step": 263500 }, { "epoch": 1.5663581622887577, "grad_norm": 1.7815693616867065, "learning_rate": 0.00011874598235534255, "loss": 0.5981307983398437, "step": 263510 }, { "epoch": 1.566417604365426, "grad_norm": 1.5212438106536865, "learning_rate": 0.00011873978702659243, "loss": 0.5473871231079102, "step": 263520 }, { "epoch": 1.5664770464420945, "grad_norm": 1.3585076332092285, "learning_rate": 0.00011873359165603401, "loss": 0.6029387474060058, "step": 263530 }, { "epoch": 1.566536488518763, "grad_norm": 1.2350929975509644, "learning_rate": 0.000118727396243697, "loss": 0.5947338104248047, "step": 263540 }, { "epoch": 1.5665959305954313, "grad_norm": 3.0433220863342285, "learning_rate": 0.00011872120078961095, "loss": 0.5970730781555176, "step": 263550 }, { "epoch": 1.5666553726720998, "grad_norm": 1.1857630014419556, "learning_rate": 0.0001187150052938055, "loss": 0.5267499923706055, "step": 263560 }, { "epoch": 1.5667148147487682, "grad_norm": 1.3542903661727905, "learning_rate": 0.00011870880975631036, "loss": 0.5503609657287598, "step": 263570 }, { "epoch": 1.5667742568254366, "grad_norm": 1.6519968509674072, "learning_rate": 0.00011870261417715507, "loss": 0.6071211814880371, "step": 263580 }, { "epoch": 1.566833698902105, "grad_norm": 1.260644555091858, "learning_rate": 0.00011869641855636935, "loss": 0.5508119583129882, "step": 263590 }, { "epoch": 1.5668931409787732, "grad_norm": 1.641737699508667, "learning_rate": 0.00011869022289398282, "loss": 0.5522011756896973, "step": 263600 }, { "epoch": 1.5669525830554416, "grad_norm": 1.3876019716262817, "learning_rate": 0.00011868402719002504, "loss": 0.5677204132080078, "step": 263610 }, { "epoch": 1.56701202513211, "grad_norm": 1.879185438156128, "learning_rate": 0.00011867783144452578, "loss": 0.6013102531433105, "step": 263620 }, { "epoch": 1.5670714672087784, "grad_norm": 1.4536222219467163, "learning_rate": 0.00011867163565751458, "loss": 0.5488286972045898, "step": 263630 }, { "epoch": 1.5671309092854468, "grad_norm": 1.412465214729309, "learning_rate": 0.00011866543982902112, "loss": 0.556989336013794, "step": 263640 }, { "epoch": 1.567190351362115, "grad_norm": 1.737253189086914, "learning_rate": 0.00011865924395907502, "loss": 0.5543041229248047, "step": 263650 }, { "epoch": 1.5672497934387835, "grad_norm": 1.3883458375930786, "learning_rate": 0.00011865304804770594, "loss": 0.5691164493560791, "step": 263660 }, { "epoch": 1.5673092355154519, "grad_norm": 1.5313760042190552, "learning_rate": 0.00011864685209494349, "loss": 0.5641782760620118, "step": 263670 }, { "epoch": 1.5673686775921203, "grad_norm": 1.3876324892044067, "learning_rate": 0.00011864065610081731, "loss": 0.5926319122314453, "step": 263680 }, { "epoch": 1.5674281196687887, "grad_norm": 1.4116803407669067, "learning_rate": 0.00011863446006535708, "loss": 0.5850607395172119, "step": 263690 }, { "epoch": 1.5674875617454571, "grad_norm": 1.6949933767318726, "learning_rate": 0.00011862826398859241, "loss": 0.5899383068084717, "step": 263700 }, { "epoch": 1.5675470038221255, "grad_norm": 1.762041449546814, "learning_rate": 0.00011862206787055295, "loss": 0.5709811210632324, "step": 263710 }, { "epoch": 1.567606445898794, "grad_norm": 1.970760703086853, "learning_rate": 0.00011861587171126832, "loss": 0.5573507308959961, "step": 263720 }, { "epoch": 1.5676658879754624, "grad_norm": 1.3630318641662598, "learning_rate": 0.0001186096755107682, "loss": 0.5814215660095214, "step": 263730 }, { "epoch": 1.5677253300521308, "grad_norm": 1.7318389415740967, "learning_rate": 0.00011860347926908217, "loss": 0.5706522941589356, "step": 263740 }, { "epoch": 1.5677847721287992, "grad_norm": 1.6196255683898926, "learning_rate": 0.00011859728298623993, "loss": 0.6050874710083007, "step": 263750 }, { "epoch": 1.5678442142054676, "grad_norm": 1.3007246255874634, "learning_rate": 0.0001185910866622711, "loss": 0.5560907363891602, "step": 263760 }, { "epoch": 1.567903656282136, "grad_norm": 1.3584699630737305, "learning_rate": 0.00011858489029720532, "loss": 0.58780517578125, "step": 263770 }, { "epoch": 1.5679630983588042, "grad_norm": 1.6815381050109863, "learning_rate": 0.00011857869389107221, "loss": 0.657558822631836, "step": 263780 }, { "epoch": 1.5680225404354726, "grad_norm": 1.3794708251953125, "learning_rate": 0.00011857249744390146, "loss": 0.5824771881103515, "step": 263790 }, { "epoch": 1.568081982512141, "grad_norm": 1.6539111137390137, "learning_rate": 0.00011856630095572268, "loss": 0.5936189651489258, "step": 263800 }, { "epoch": 1.5681414245888095, "grad_norm": 2.1271870136260986, "learning_rate": 0.00011856010442656549, "loss": 0.49730987548828126, "step": 263810 }, { "epoch": 1.5682008666654779, "grad_norm": 1.313819408416748, "learning_rate": 0.00011855390785645959, "loss": 0.547944164276123, "step": 263820 }, { "epoch": 1.568260308742146, "grad_norm": 1.7909022569656372, "learning_rate": 0.00011854771124543455, "loss": 0.597815990447998, "step": 263830 }, { "epoch": 1.5683197508188145, "grad_norm": 1.0465755462646484, "learning_rate": 0.0001185415145935201, "loss": 0.5643758773803711, "step": 263840 }, { "epoch": 1.5683791928954829, "grad_norm": 1.404171347618103, "learning_rate": 0.00011853531790074581, "loss": 0.5855568408966064, "step": 263850 }, { "epoch": 1.5684386349721513, "grad_norm": 1.3096370697021484, "learning_rate": 0.00011852912116714132, "loss": 0.5713959217071534, "step": 263860 }, { "epoch": 1.5684980770488197, "grad_norm": 1.573909878730774, "learning_rate": 0.00011852292439273636, "loss": 0.6035950660705567, "step": 263870 }, { "epoch": 1.5685575191254881, "grad_norm": 1.3595407009124756, "learning_rate": 0.0001185167275775605, "loss": 0.5842571258544922, "step": 263880 }, { "epoch": 1.5686169612021565, "grad_norm": 1.0707371234893799, "learning_rate": 0.00011851053072164335, "loss": 0.5688852787017822, "step": 263890 }, { "epoch": 1.568676403278825, "grad_norm": 1.1562403440475464, "learning_rate": 0.00011850433382501464, "loss": 0.5553698539733887, "step": 263900 }, { "epoch": 1.5687358453554934, "grad_norm": 1.2811733484268188, "learning_rate": 0.00011849813688770399, "loss": 0.5072833061218261, "step": 263910 }, { "epoch": 1.5687952874321618, "grad_norm": 1.1777561902999878, "learning_rate": 0.00011849193990974101, "loss": 0.5511387825012207, "step": 263920 }, { "epoch": 1.5688547295088302, "grad_norm": 1.3174270391464233, "learning_rate": 0.00011848574289115537, "loss": 0.5616776466369628, "step": 263930 }, { "epoch": 1.5689141715854986, "grad_norm": 1.298081398010254, "learning_rate": 0.00011847954583197672, "loss": 0.5576015472412109, "step": 263940 }, { "epoch": 1.568973613662167, "grad_norm": 1.5598963499069214, "learning_rate": 0.0001184733487322347, "loss": 0.5809595584869385, "step": 263950 }, { "epoch": 1.5690330557388354, "grad_norm": 1.125503659248352, "learning_rate": 0.00011846715159195892, "loss": 0.5622827529907226, "step": 263960 }, { "epoch": 1.5690924978155036, "grad_norm": 1.599287509918213, "learning_rate": 0.00011846095441117906, "loss": 0.5852161407470703, "step": 263970 }, { "epoch": 1.569151939892172, "grad_norm": 1.4089585542678833, "learning_rate": 0.00011845475718992476, "loss": 0.5737716674804687, "step": 263980 }, { "epoch": 1.5692113819688405, "grad_norm": 1.4686733484268188, "learning_rate": 0.00011844855992822565, "loss": 0.5809924125671386, "step": 263990 }, { "epoch": 1.5692708240455089, "grad_norm": 1.2379096746444702, "learning_rate": 0.00011844236262611146, "loss": 0.538109016418457, "step": 264000 }, { "epoch": 1.5693302661221773, "grad_norm": 1.1967486143112183, "learning_rate": 0.0001184361652836117, "loss": 0.5723146438598633, "step": 264010 }, { "epoch": 1.5693897081988455, "grad_norm": 1.3131698369979858, "learning_rate": 0.00011842996790075607, "loss": 0.5296877861022949, "step": 264020 }, { "epoch": 1.569449150275514, "grad_norm": 1.677230715751648, "learning_rate": 0.00011842377047757429, "loss": 0.6119462966918945, "step": 264030 }, { "epoch": 1.5695085923521823, "grad_norm": 1.146478533744812, "learning_rate": 0.00011841757301409588, "loss": 0.5749445915222168, "step": 264040 }, { "epoch": 1.5695680344288507, "grad_norm": 1.6120728254318237, "learning_rate": 0.0001184113755103506, "loss": 0.5993564605712891, "step": 264050 }, { "epoch": 1.5696274765055191, "grad_norm": 1.8964799642562866, "learning_rate": 0.00011840517796636803, "loss": 0.6034788131713867, "step": 264060 }, { "epoch": 1.5696869185821876, "grad_norm": 1.5467692613601685, "learning_rate": 0.00011839898038217782, "loss": 0.637264633178711, "step": 264070 }, { "epoch": 1.569746360658856, "grad_norm": 1.4725819826126099, "learning_rate": 0.00011839278275780965, "loss": 0.6297726154327392, "step": 264080 }, { "epoch": 1.5698058027355244, "grad_norm": 1.763481855392456, "learning_rate": 0.00011838658509329317, "loss": 0.5684024333953858, "step": 264090 }, { "epoch": 1.5698652448121928, "grad_norm": 1.53968346118927, "learning_rate": 0.00011838038738865798, "loss": 0.5725401878356934, "step": 264100 }, { "epoch": 1.5699246868888612, "grad_norm": 1.4002877473831177, "learning_rate": 0.00011837418964393376, "loss": 0.5733904361724853, "step": 264110 }, { "epoch": 1.5699841289655296, "grad_norm": 1.6797893047332764, "learning_rate": 0.00011836799185915015, "loss": 0.57254638671875, "step": 264120 }, { "epoch": 1.570043571042198, "grad_norm": 1.9267985820770264, "learning_rate": 0.00011836179403433683, "loss": 0.5733946800231934, "step": 264130 }, { "epoch": 1.5701030131188665, "grad_norm": 1.5194510221481323, "learning_rate": 0.00011835559616952339, "loss": 0.5547585010528564, "step": 264140 }, { "epoch": 1.5701624551955347, "grad_norm": 1.4082415103912354, "learning_rate": 0.00011834939826473952, "loss": 0.5260315895080566, "step": 264150 }, { "epoch": 1.570221897272203, "grad_norm": 1.6532455682754517, "learning_rate": 0.00011834320032001486, "loss": 0.5615054130554199, "step": 264160 }, { "epoch": 1.5702813393488715, "grad_norm": 1.256425380706787, "learning_rate": 0.00011833700233537903, "loss": 0.5337453365325928, "step": 264170 }, { "epoch": 1.57034078142554, "grad_norm": 1.6211258172988892, "learning_rate": 0.00011833080431086174, "loss": 0.5976096153259277, "step": 264180 }, { "epoch": 1.5704002235022083, "grad_norm": 1.6564064025878906, "learning_rate": 0.0001183246062464926, "loss": 0.6024389266967773, "step": 264190 }, { "epoch": 1.5704596655788765, "grad_norm": 1.787575364112854, "learning_rate": 0.00011831840814230123, "loss": 0.5704747200012207, "step": 264200 }, { "epoch": 1.570519107655545, "grad_norm": 1.3403810262680054, "learning_rate": 0.00011831220999831733, "loss": 0.6348725318908691, "step": 264210 }, { "epoch": 1.5705785497322133, "grad_norm": 1.3063584566116333, "learning_rate": 0.00011830601181457058, "loss": 0.5656882286071777, "step": 264220 }, { "epoch": 1.5706379918088818, "grad_norm": 1.3824619054794312, "learning_rate": 0.00011829981359109052, "loss": 0.5275962352752686, "step": 264230 }, { "epoch": 1.5706974338855502, "grad_norm": 1.5544006824493408, "learning_rate": 0.00011829361532790689, "loss": 0.5667623519897461, "step": 264240 }, { "epoch": 1.5707568759622186, "grad_norm": 1.337190866470337, "learning_rate": 0.00011828741702504931, "loss": 0.5170422554016113, "step": 264250 }, { "epoch": 1.570816318038887, "grad_norm": 1.9865344762802124, "learning_rate": 0.00011828121868254744, "loss": 0.5691000938415527, "step": 264260 }, { "epoch": 1.5708757601155554, "grad_norm": 1.8839678764343262, "learning_rate": 0.00011827502030043093, "loss": 0.5666647911071777, "step": 264270 }, { "epoch": 1.5709352021922238, "grad_norm": 1.5524216890335083, "learning_rate": 0.00011826882187872943, "loss": 0.5652244567871094, "step": 264280 }, { "epoch": 1.5709946442688922, "grad_norm": 1.6918753385543823, "learning_rate": 0.00011826262341747258, "loss": 0.5706613540649415, "step": 264290 }, { "epoch": 1.5710540863455607, "grad_norm": 1.7647532224655151, "learning_rate": 0.00011825642491669002, "loss": 0.5650798320770264, "step": 264300 }, { "epoch": 1.571113528422229, "grad_norm": 1.511446475982666, "learning_rate": 0.0001182502263764115, "loss": 0.5938007831573486, "step": 264310 }, { "epoch": 1.5711729704988975, "grad_norm": 1.7396148443222046, "learning_rate": 0.0001182440277966665, "loss": 0.5633976936340332, "step": 264320 }, { "epoch": 1.571232412575566, "grad_norm": 1.7902488708496094, "learning_rate": 0.00011823782917748478, "loss": 0.606716251373291, "step": 264330 }, { "epoch": 1.571291854652234, "grad_norm": 1.8607759475708008, "learning_rate": 0.00011823163051889605, "loss": 0.6107256889343262, "step": 264340 }, { "epoch": 1.5713512967289025, "grad_norm": 1.6451423168182373, "learning_rate": 0.0001182254318209298, "loss": 0.587159252166748, "step": 264350 }, { "epoch": 1.571410738805571, "grad_norm": 1.2261343002319336, "learning_rate": 0.00011821923308361582, "loss": 0.5566061973571778, "step": 264360 }, { "epoch": 1.5714701808822393, "grad_norm": 1.2609058618545532, "learning_rate": 0.00011821303430698374, "loss": 0.5592179298400879, "step": 264370 }, { "epoch": 1.5715296229589077, "grad_norm": 1.5250868797302246, "learning_rate": 0.00011820683549106313, "loss": 0.6245538711547851, "step": 264380 }, { "epoch": 1.571589065035576, "grad_norm": 1.4559582471847534, "learning_rate": 0.00011820063663588373, "loss": 0.5866043090820312, "step": 264390 }, { "epoch": 1.5716485071122444, "grad_norm": 1.8250706195831299, "learning_rate": 0.00011819443774147516, "loss": 0.5391217231750488, "step": 264400 }, { "epoch": 1.5717079491889128, "grad_norm": 1.563665747642517, "learning_rate": 0.00011818823880786705, "loss": 0.5491763114929199, "step": 264410 }, { "epoch": 1.5717673912655812, "grad_norm": 1.3112196922302246, "learning_rate": 0.00011818203983508913, "loss": 0.5802197456359863, "step": 264420 }, { "epoch": 1.5718268333422496, "grad_norm": 1.4836941957473755, "learning_rate": 0.00011817584082317099, "loss": 0.5748127460479736, "step": 264430 }, { "epoch": 1.571886275418918, "grad_norm": 1.7332676649093628, "learning_rate": 0.00011816964177214229, "loss": 0.5929727554321289, "step": 264440 }, { "epoch": 1.5719457174955864, "grad_norm": 1.6744027137756348, "learning_rate": 0.0001181634426820327, "loss": 0.5705410957336425, "step": 264450 }, { "epoch": 1.5720051595722548, "grad_norm": 1.4762264490127563, "learning_rate": 0.00011815724355287185, "loss": 0.5957180976867675, "step": 264460 }, { "epoch": 1.5720646016489233, "grad_norm": 1.660271167755127, "learning_rate": 0.00011815104438468945, "loss": 0.603337574005127, "step": 264470 }, { "epoch": 1.5721240437255917, "grad_norm": 1.6412925720214844, "learning_rate": 0.00011814484517751508, "loss": 0.5871503353118896, "step": 264480 }, { "epoch": 1.57218348580226, "grad_norm": 1.6617029905319214, "learning_rate": 0.00011813864593137844, "loss": 0.6047496795654297, "step": 264490 }, { "epoch": 1.5722429278789285, "grad_norm": 1.7857666015625, "learning_rate": 0.0001181324466463092, "loss": 0.5543960571289063, "step": 264500 }, { "epoch": 1.572302369955597, "grad_norm": 1.5451072454452515, "learning_rate": 0.00011812624732233694, "loss": 0.5963541030883789, "step": 264510 }, { "epoch": 1.572361812032265, "grad_norm": 1.2960212230682373, "learning_rate": 0.00011812004795949145, "loss": 0.5580706119537353, "step": 264520 }, { "epoch": 1.5724212541089335, "grad_norm": 1.25669264793396, "learning_rate": 0.00011811384855780227, "loss": 0.5745989799499511, "step": 264530 }, { "epoch": 1.572480696185602, "grad_norm": 1.3915307521820068, "learning_rate": 0.00011810764911729906, "loss": 0.6077301025390625, "step": 264540 }, { "epoch": 1.5725401382622703, "grad_norm": 1.5636284351348877, "learning_rate": 0.00011810144963801156, "loss": 0.5920180320739746, "step": 264550 }, { "epoch": 1.5725995803389388, "grad_norm": 1.8383384943008423, "learning_rate": 0.00011809525011996932, "loss": 0.6055967807769775, "step": 264560 }, { "epoch": 1.572659022415607, "grad_norm": 1.3526718616485596, "learning_rate": 0.00011808905056320208, "loss": 0.5429876327514649, "step": 264570 }, { "epoch": 1.5727184644922754, "grad_norm": 1.5744266510009766, "learning_rate": 0.00011808285096773946, "loss": 0.6375248908996582, "step": 264580 }, { "epoch": 1.5727779065689438, "grad_norm": 1.3735427856445312, "learning_rate": 0.00011807665133361108, "loss": 0.5628176212310791, "step": 264590 }, { "epoch": 1.5728373486456122, "grad_norm": 1.1560070514678955, "learning_rate": 0.00011807045166084669, "loss": 0.5525991439819335, "step": 264600 }, { "epoch": 1.5728967907222806, "grad_norm": 1.2393563985824585, "learning_rate": 0.00011806425194947588, "loss": 0.4974726676940918, "step": 264610 }, { "epoch": 1.572956232798949, "grad_norm": 2.07108473777771, "learning_rate": 0.00011805805219952835, "loss": 0.604753828048706, "step": 264620 }, { "epoch": 1.5730156748756174, "grad_norm": 2.2930119037628174, "learning_rate": 0.0001180518524110337, "loss": 0.6159773826599121, "step": 264630 }, { "epoch": 1.5730751169522859, "grad_norm": 1.4922066926956177, "learning_rate": 0.00011804565258402162, "loss": 0.5612967491149903, "step": 264640 }, { "epoch": 1.5731345590289543, "grad_norm": 1.7710883617401123, "learning_rate": 0.0001180394527185218, "loss": 0.5805641651153565, "step": 264650 }, { "epoch": 1.5731940011056227, "grad_norm": 1.5761245489120483, "learning_rate": 0.00011803325281456381, "loss": 0.579470157623291, "step": 264660 }, { "epoch": 1.573253443182291, "grad_norm": 1.3233593702316284, "learning_rate": 0.0001180270528721774, "loss": 0.6147675514221191, "step": 264670 }, { "epoch": 1.5733128852589595, "grad_norm": 1.3956507444381714, "learning_rate": 0.0001180208528913922, "loss": 0.6418457984924316, "step": 264680 }, { "epoch": 1.573372327335628, "grad_norm": 1.4064515829086304, "learning_rate": 0.00011801465287223782, "loss": 0.5444370746612549, "step": 264690 }, { "epoch": 1.5734317694122963, "grad_norm": 1.7751909494400024, "learning_rate": 0.00011800845281474402, "loss": 0.6130399227142334, "step": 264700 }, { "epoch": 1.5734912114889645, "grad_norm": 2.035320997238159, "learning_rate": 0.00011800225271894034, "loss": 0.6000261306762695, "step": 264710 }, { "epoch": 1.573550653565633, "grad_norm": 1.5057158470153809, "learning_rate": 0.00011799605258485653, "loss": 0.5844471454620361, "step": 264720 }, { "epoch": 1.5736100956423014, "grad_norm": 1.5358757972717285, "learning_rate": 0.00011798985241252221, "loss": 0.6026177883148194, "step": 264730 }, { "epoch": 1.5736695377189698, "grad_norm": 1.5789916515350342, "learning_rate": 0.00011798365220196706, "loss": 0.5924489021301269, "step": 264740 }, { "epoch": 1.5737289797956382, "grad_norm": 1.5794612169265747, "learning_rate": 0.00011797745195322072, "loss": 0.5921850204467773, "step": 264750 }, { "epoch": 1.5737884218723064, "grad_norm": 1.7834899425506592, "learning_rate": 0.00011797125166631284, "loss": 0.560877513885498, "step": 264760 }, { "epoch": 1.5738478639489748, "grad_norm": 1.4303617477416992, "learning_rate": 0.00011796505134127311, "loss": 0.5140213012695313, "step": 264770 }, { "epoch": 1.5739073060256432, "grad_norm": 1.8369346857070923, "learning_rate": 0.0001179588509781312, "loss": 0.5735589027404785, "step": 264780 }, { "epoch": 1.5739667481023116, "grad_norm": 1.4563230276107788, "learning_rate": 0.00011795265057691672, "loss": 0.5561351776123047, "step": 264790 }, { "epoch": 1.57402619017898, "grad_norm": 1.3934192657470703, "learning_rate": 0.00011794645013765936, "loss": 0.5426169395446777, "step": 264800 }, { "epoch": 1.5740856322556485, "grad_norm": 1.4109256267547607, "learning_rate": 0.0001179402496603888, "loss": 0.5786157131195069, "step": 264810 }, { "epoch": 1.5741450743323169, "grad_norm": 1.3030380010604858, "learning_rate": 0.00011793404914513464, "loss": 0.5466583728790283, "step": 264820 }, { "epoch": 1.5742045164089853, "grad_norm": 1.8859326839447021, "learning_rate": 0.00011792784859192662, "loss": 0.5927824974060059, "step": 264830 }, { "epoch": 1.5742639584856537, "grad_norm": 1.6672991514205933, "learning_rate": 0.00011792164800079435, "loss": 0.6543027877807617, "step": 264840 }, { "epoch": 1.5743234005623221, "grad_norm": 1.5820000171661377, "learning_rate": 0.00011791544737176752, "loss": 0.5684892654418945, "step": 264850 }, { "epoch": 1.5743828426389905, "grad_norm": 1.632394790649414, "learning_rate": 0.00011790924670487575, "loss": 0.5617588043212891, "step": 264860 }, { "epoch": 1.574442284715659, "grad_norm": 1.476239800453186, "learning_rate": 0.00011790304600014874, "loss": 0.6033806800842285, "step": 264870 }, { "epoch": 1.5745017267923274, "grad_norm": 1.7312977313995361, "learning_rate": 0.00011789684525761614, "loss": 0.6255479335784913, "step": 264880 }, { "epoch": 1.5745611688689956, "grad_norm": 1.1013017892837524, "learning_rate": 0.00011789064447730762, "loss": 0.5626163482666016, "step": 264890 }, { "epoch": 1.574620610945664, "grad_norm": 1.176613450050354, "learning_rate": 0.00011788444365925282, "loss": 0.559340524673462, "step": 264900 }, { "epoch": 1.5746800530223324, "grad_norm": 1.2757271528244019, "learning_rate": 0.00011787824280348143, "loss": 0.6030173301696777, "step": 264910 }, { "epoch": 1.5747394950990008, "grad_norm": 1.6080703735351562, "learning_rate": 0.0001178720419100231, "loss": 0.5631602764129638, "step": 264920 }, { "epoch": 1.5747989371756692, "grad_norm": 1.9362733364105225, "learning_rate": 0.00011786584097890752, "loss": 0.5236638069152832, "step": 264930 }, { "epoch": 1.5748583792523374, "grad_norm": 1.273380994796753, "learning_rate": 0.00011785964001016425, "loss": 0.6144509792327881, "step": 264940 }, { "epoch": 1.5749178213290058, "grad_norm": 1.2058312892913818, "learning_rate": 0.0001178534390038231, "loss": 0.5434775352478027, "step": 264950 }, { "epoch": 1.5749772634056742, "grad_norm": 1.5628811120986938, "learning_rate": 0.00011784723795991365, "loss": 0.5857466220855713, "step": 264960 }, { "epoch": 1.5750367054823426, "grad_norm": 1.1549626588821411, "learning_rate": 0.00011784103687846554, "loss": 0.5241722583770752, "step": 264970 }, { "epoch": 1.575096147559011, "grad_norm": 1.4785414934158325, "learning_rate": 0.00011783483575950854, "loss": 0.5821666717529297, "step": 264980 }, { "epoch": 1.5751555896356795, "grad_norm": 1.7805817127227783, "learning_rate": 0.00011782863460307221, "loss": 0.5303310871124267, "step": 264990 }, { "epoch": 1.575215031712348, "grad_norm": 1.3851594924926758, "learning_rate": 0.00011782243340918624, "loss": 0.5622945785522461, "step": 265000 }, { "epoch": 1.5752744737890163, "grad_norm": 1.0289455652236938, "learning_rate": 0.00011781623217788031, "loss": 0.52399582862854, "step": 265010 }, { "epoch": 1.5753339158656847, "grad_norm": 1.3935836553573608, "learning_rate": 0.0001178100309091841, "loss": 0.6035755157470704, "step": 265020 }, { "epoch": 1.5753933579423531, "grad_norm": 1.15631902217865, "learning_rate": 0.00011780382960312724, "loss": 0.6053345680236817, "step": 265030 }, { "epoch": 1.5754528000190215, "grad_norm": 1.8156406879425049, "learning_rate": 0.00011779762825973941, "loss": 0.5409078598022461, "step": 265040 }, { "epoch": 1.57551224209569, "grad_norm": 1.5772470235824585, "learning_rate": 0.00011779142687905027, "loss": 0.568294906616211, "step": 265050 }, { "epoch": 1.5755716841723584, "grad_norm": 1.3353129625320435, "learning_rate": 0.0001177852254610895, "loss": 0.5783908367156982, "step": 265060 }, { "epoch": 1.5756311262490268, "grad_norm": 1.4964793920516968, "learning_rate": 0.00011777902400588674, "loss": 0.6212126731872558, "step": 265070 }, { "epoch": 1.575690568325695, "grad_norm": 1.456586241722107, "learning_rate": 0.0001177728225134717, "loss": 0.5948567390441895, "step": 265080 }, { "epoch": 1.5757500104023634, "grad_norm": 1.44109046459198, "learning_rate": 0.00011776662098387399, "loss": 0.5751112937927246, "step": 265090 }, { "epoch": 1.5758094524790318, "grad_norm": 1.495194911956787, "learning_rate": 0.0001177604194171233, "loss": 0.5783257961273194, "step": 265100 }, { "epoch": 1.5758688945557002, "grad_norm": 1.3357312679290771, "learning_rate": 0.00011775421781324934, "loss": 0.5522056102752686, "step": 265110 }, { "epoch": 1.5759283366323686, "grad_norm": 1.3912402391433716, "learning_rate": 0.0001177480161722817, "loss": 0.5988541603088379, "step": 265120 }, { "epoch": 1.5759877787090368, "grad_norm": 1.4791544675827026, "learning_rate": 0.00011774181449425006, "loss": 0.5409943580627441, "step": 265130 }, { "epoch": 1.5760472207857052, "grad_norm": 1.8517999649047852, "learning_rate": 0.00011773561277918416, "loss": 0.5705490112304688, "step": 265140 }, { "epoch": 1.5761066628623737, "grad_norm": 1.9438245296478271, "learning_rate": 0.00011772941102711361, "loss": 0.6105439186096191, "step": 265150 }, { "epoch": 1.576166104939042, "grad_norm": 1.4113540649414062, "learning_rate": 0.00011772320923806807, "loss": 0.5934745311737061, "step": 265160 }, { "epoch": 1.5762255470157105, "grad_norm": 1.1526457071304321, "learning_rate": 0.0001177170074120772, "loss": 0.5800623893737793, "step": 265170 }, { "epoch": 1.576284989092379, "grad_norm": 1.7514703273773193, "learning_rate": 0.00011771080554917073, "loss": 0.6258249282836914, "step": 265180 }, { "epoch": 1.5763444311690473, "grad_norm": 1.6209272146224976, "learning_rate": 0.00011770460364937826, "loss": 0.6016023635864258, "step": 265190 }, { "epoch": 1.5764038732457157, "grad_norm": 1.360116958618164, "learning_rate": 0.0001176984017127295, "loss": 0.5397247314453125, "step": 265200 }, { "epoch": 1.5764633153223842, "grad_norm": 1.4574477672576904, "learning_rate": 0.00011769219973925408, "loss": 0.6083215713500977, "step": 265210 }, { "epoch": 1.5765227573990526, "grad_norm": 1.4822297096252441, "learning_rate": 0.0001176859977289817, "loss": 0.6488836288452149, "step": 265220 }, { "epoch": 1.576582199475721, "grad_norm": 1.4690732955932617, "learning_rate": 0.00011767979568194203, "loss": 0.5549743175506592, "step": 265230 }, { "epoch": 1.5766416415523894, "grad_norm": 1.5586634874343872, "learning_rate": 0.00011767359359816475, "loss": 0.572684383392334, "step": 265240 }, { "epoch": 1.5767010836290578, "grad_norm": 1.1538898944854736, "learning_rate": 0.00011766739147767943, "loss": 0.5570655822753906, "step": 265250 }, { "epoch": 1.576760525705726, "grad_norm": 1.2884671688079834, "learning_rate": 0.00011766118932051589, "loss": 0.569558048248291, "step": 265260 }, { "epoch": 1.5768199677823944, "grad_norm": 1.13917875289917, "learning_rate": 0.00011765498712670368, "loss": 0.5348287582397461, "step": 265270 }, { "epoch": 1.5768794098590628, "grad_norm": 2.0159225463867188, "learning_rate": 0.00011764878489627251, "loss": 0.5698375701904297, "step": 265280 }, { "epoch": 1.5769388519357312, "grad_norm": 1.4523987770080566, "learning_rate": 0.00011764258262925209, "loss": 0.5733416557312012, "step": 265290 }, { "epoch": 1.5769982940123997, "grad_norm": 1.3107789754867554, "learning_rate": 0.00011763638032567203, "loss": 0.5740726470947266, "step": 265300 }, { "epoch": 1.5770577360890679, "grad_norm": 1.1960012912750244, "learning_rate": 0.000117630177985562, "loss": 0.5450314521789551, "step": 265310 }, { "epoch": 1.5771171781657363, "grad_norm": 1.6403815746307373, "learning_rate": 0.00011762397560895175, "loss": 0.575657844543457, "step": 265320 }, { "epoch": 1.5771766202424047, "grad_norm": 1.4744575023651123, "learning_rate": 0.00011761777319587084, "loss": 0.5599645614624024, "step": 265330 }, { "epoch": 1.577236062319073, "grad_norm": 1.5403517484664917, "learning_rate": 0.00011761157074634901, "loss": 0.6242307186126709, "step": 265340 }, { "epoch": 1.5772955043957415, "grad_norm": 1.6052215099334717, "learning_rate": 0.00011760536826041593, "loss": 0.5382826805114747, "step": 265350 }, { "epoch": 1.57735494647241, "grad_norm": 1.3874021768569946, "learning_rate": 0.00011759916573810123, "loss": 0.6092854499816894, "step": 265360 }, { "epoch": 1.5774143885490783, "grad_norm": 1.173157811164856, "learning_rate": 0.00011759296317943463, "loss": 0.5534884929656982, "step": 265370 }, { "epoch": 1.5774738306257468, "grad_norm": 1.3963805437088013, "learning_rate": 0.00011758676058444575, "loss": 0.5703823089599609, "step": 265380 }, { "epoch": 1.5775332727024152, "grad_norm": 1.6112555265426636, "learning_rate": 0.00011758055795316427, "loss": 0.5628912925720215, "step": 265390 }, { "epoch": 1.5775927147790836, "grad_norm": 2.060821294784546, "learning_rate": 0.0001175743552856199, "loss": 0.5714926719665527, "step": 265400 }, { "epoch": 1.577652156855752, "grad_norm": 1.2393611669540405, "learning_rate": 0.0001175681525818423, "loss": 0.602214765548706, "step": 265410 }, { "epoch": 1.5777115989324204, "grad_norm": 1.2764471769332886, "learning_rate": 0.00011756194984186115, "loss": 0.5479397773742676, "step": 265420 }, { "epoch": 1.5777710410090888, "grad_norm": 1.4561282396316528, "learning_rate": 0.00011755574706570607, "loss": 0.5880626201629638, "step": 265430 }, { "epoch": 1.5778304830857572, "grad_norm": 1.3429181575775146, "learning_rate": 0.00011754954425340677, "loss": 0.493845272064209, "step": 265440 }, { "epoch": 1.5778899251624254, "grad_norm": 1.8152459859848022, "learning_rate": 0.00011754334140499292, "loss": 0.597382640838623, "step": 265450 }, { "epoch": 1.5779493672390938, "grad_norm": 1.3068199157714844, "learning_rate": 0.00011753713852049417, "loss": 0.590866994857788, "step": 265460 }, { "epoch": 1.5780088093157623, "grad_norm": 1.363914132118225, "learning_rate": 0.00011753093559994024, "loss": 0.5777096271514892, "step": 265470 }, { "epoch": 1.5780682513924307, "grad_norm": 1.3327522277832031, "learning_rate": 0.00011752473264336077, "loss": 0.5618493556976318, "step": 265480 }, { "epoch": 1.578127693469099, "grad_norm": 1.874260663986206, "learning_rate": 0.00011751852965078542, "loss": 0.5994461059570313, "step": 265490 }, { "epoch": 1.5781871355457673, "grad_norm": 1.4803800582885742, "learning_rate": 0.00011751232662224392, "loss": 0.6334196090698242, "step": 265500 }, { "epoch": 1.5782465776224357, "grad_norm": 1.2460815906524658, "learning_rate": 0.00011750612355776589, "loss": 0.5667055606842041, "step": 265510 }, { "epoch": 1.5783060196991041, "grad_norm": 1.5194751024246216, "learning_rate": 0.000117499920457381, "loss": 0.5332084178924561, "step": 265520 }, { "epoch": 1.5783654617757725, "grad_norm": 1.6749950647354126, "learning_rate": 0.00011749371732111893, "loss": 0.6120524883270264, "step": 265530 }, { "epoch": 1.578424903852441, "grad_norm": 1.331191897392273, "learning_rate": 0.0001174875141490094, "loss": 0.5829981803894043, "step": 265540 }, { "epoch": 1.5784843459291094, "grad_norm": 1.5639185905456543, "learning_rate": 0.00011748131094108204, "loss": 0.5018190383911133, "step": 265550 }, { "epoch": 1.5785437880057778, "grad_norm": 1.4166313409805298, "learning_rate": 0.00011747510769736651, "loss": 0.5673413753509522, "step": 265560 }, { "epoch": 1.5786032300824462, "grad_norm": 1.9987471103668213, "learning_rate": 0.00011746890441789253, "loss": 0.5558584690093994, "step": 265570 }, { "epoch": 1.5786626721591146, "grad_norm": 1.3595343828201294, "learning_rate": 0.00011746270110268976, "loss": 0.6130275726318359, "step": 265580 }, { "epoch": 1.578722114235783, "grad_norm": 1.3849856853485107, "learning_rate": 0.00011745649775178785, "loss": 0.5514346122741699, "step": 265590 }, { "epoch": 1.5787815563124514, "grad_norm": 1.2445803880691528, "learning_rate": 0.00011745029436521651, "loss": 0.559569263458252, "step": 265600 }, { "epoch": 1.5788409983891198, "grad_norm": 1.7075408697128296, "learning_rate": 0.00011744409094300539, "loss": 0.5996345520019531, "step": 265610 }, { "epoch": 1.5789004404657883, "grad_norm": 1.396153450012207, "learning_rate": 0.00011743788748518415, "loss": 0.546202564239502, "step": 265620 }, { "epoch": 1.5789598825424564, "grad_norm": 1.3942173719406128, "learning_rate": 0.0001174316839917825, "loss": 0.6309632301330567, "step": 265630 }, { "epoch": 1.5790193246191249, "grad_norm": 1.4451016187667847, "learning_rate": 0.00011742548046283008, "loss": 0.5849670886993408, "step": 265640 }, { "epoch": 1.5790787666957933, "grad_norm": 1.6281051635742188, "learning_rate": 0.00011741927689835663, "loss": 0.5573368072509766, "step": 265650 }, { "epoch": 1.5791382087724617, "grad_norm": 1.187989592552185, "learning_rate": 0.00011741307329839179, "loss": 0.6012124061584473, "step": 265660 }, { "epoch": 1.57919765084913, "grad_norm": 1.404773235321045, "learning_rate": 0.0001174068696629652, "loss": 0.5642723083496094, "step": 265670 }, { "epoch": 1.5792570929257983, "grad_norm": 1.2911380529403687, "learning_rate": 0.00011740066599210658, "loss": 0.6031257152557373, "step": 265680 }, { "epoch": 1.5793165350024667, "grad_norm": 1.5842909812927246, "learning_rate": 0.00011739446228584556, "loss": 0.5859100341796875, "step": 265690 }, { "epoch": 1.5793759770791351, "grad_norm": 1.323936939239502, "learning_rate": 0.0001173882585442119, "loss": 0.5316543579101562, "step": 265700 }, { "epoch": 1.5794354191558035, "grad_norm": 1.548324465751648, "learning_rate": 0.00011738205476723519, "loss": 0.5492112159729003, "step": 265710 }, { "epoch": 1.579494861232472, "grad_norm": 1.693720817565918, "learning_rate": 0.00011737585095494515, "loss": 0.5638442993164062, "step": 265720 }, { "epoch": 1.5795543033091404, "grad_norm": 1.9395052194595337, "learning_rate": 0.00011736964710737147, "loss": 0.5936952114105225, "step": 265730 }, { "epoch": 1.5796137453858088, "grad_norm": 1.4949049949645996, "learning_rate": 0.00011736344322454376, "loss": 0.540336799621582, "step": 265740 }, { "epoch": 1.5796731874624772, "grad_norm": 1.2563185691833496, "learning_rate": 0.00011735723930649176, "loss": 0.5928915977478028, "step": 265750 }, { "epoch": 1.5797326295391456, "grad_norm": 1.5774433612823486, "learning_rate": 0.00011735103535324516, "loss": 0.5783043384552002, "step": 265760 }, { "epoch": 1.579792071615814, "grad_norm": 1.5013777017593384, "learning_rate": 0.00011734483136483359, "loss": 0.603154468536377, "step": 265770 }, { "epoch": 1.5798515136924824, "grad_norm": 1.2881211042404175, "learning_rate": 0.00011733862734128675, "loss": 0.5904475212097168, "step": 265780 }, { "epoch": 1.5799109557691509, "grad_norm": 1.1605000495910645, "learning_rate": 0.00011733242328263432, "loss": 0.5305206298828125, "step": 265790 }, { "epoch": 1.5799703978458193, "grad_norm": 1.5921076536178589, "learning_rate": 0.00011732621918890594, "loss": 0.5461615562438965, "step": 265800 }, { "epoch": 1.5800298399224877, "grad_norm": 1.4584070444107056, "learning_rate": 0.00011732001506013137, "loss": 0.5217401504516601, "step": 265810 }, { "epoch": 1.5800892819991559, "grad_norm": 1.271008849143982, "learning_rate": 0.00011731381089634023, "loss": 0.543824577331543, "step": 265820 }, { "epoch": 1.5801487240758243, "grad_norm": 1.6690369844436646, "learning_rate": 0.0001173076066975622, "loss": 0.5838510036468506, "step": 265830 }, { "epoch": 1.5802081661524927, "grad_norm": 1.7005186080932617, "learning_rate": 0.00011730140246382698, "loss": 0.5506046295166016, "step": 265840 }, { "epoch": 1.5802676082291611, "grad_norm": 1.7960785627365112, "learning_rate": 0.00011729519819516419, "loss": 0.5938625812530518, "step": 265850 }, { "epoch": 1.5803270503058295, "grad_norm": 1.2303080558776855, "learning_rate": 0.00011728899389160361, "loss": 0.5204410552978516, "step": 265860 }, { "epoch": 1.5803864923824977, "grad_norm": 1.4432141780853271, "learning_rate": 0.00011728278955317484, "loss": 0.5713497638702393, "step": 265870 }, { "epoch": 1.5804459344591661, "grad_norm": 1.462104082107544, "learning_rate": 0.0001172765851799076, "loss": 0.5681267738342285, "step": 265880 }, { "epoch": 1.5805053765358346, "grad_norm": 1.511595368385315, "learning_rate": 0.00011727038077183154, "loss": 0.5515630722045899, "step": 265890 }, { "epoch": 1.580564818612503, "grad_norm": 1.4642044305801392, "learning_rate": 0.00011726417632897634, "loss": 0.5583889007568359, "step": 265900 }, { "epoch": 1.5806242606891714, "grad_norm": 1.339834213256836, "learning_rate": 0.00011725797185137172, "loss": 0.5837303161621094, "step": 265910 }, { "epoch": 1.5806837027658398, "grad_norm": 1.5375350713729858, "learning_rate": 0.00011725176733904733, "loss": 0.5499236583709717, "step": 265920 }, { "epoch": 1.5807431448425082, "grad_norm": 1.3835543394088745, "learning_rate": 0.00011724556279203287, "loss": 0.616238021850586, "step": 265930 }, { "epoch": 1.5808025869191766, "grad_norm": 3.3133087158203125, "learning_rate": 0.00011723935821035799, "loss": 0.5458596229553223, "step": 265940 }, { "epoch": 1.580862028995845, "grad_norm": 1.5551910400390625, "learning_rate": 0.00011723315359405236, "loss": 0.6228067874908447, "step": 265950 }, { "epoch": 1.5809214710725135, "grad_norm": 1.3486990928649902, "learning_rate": 0.00011722694894314572, "loss": 0.5848029136657715, "step": 265960 }, { "epoch": 1.5809809131491819, "grad_norm": 1.7908639907836914, "learning_rate": 0.00011722074425766771, "loss": 0.5758854866027832, "step": 265970 }, { "epoch": 1.5810403552258503, "grad_norm": 1.2789158821105957, "learning_rate": 0.000117214539537648, "loss": 0.5431007385253906, "step": 265980 }, { "epoch": 1.5810997973025187, "grad_norm": 1.678256869316101, "learning_rate": 0.00011720833478311633, "loss": 0.6390200614929199, "step": 265990 }, { "epoch": 1.581159239379187, "grad_norm": 1.183632731437683, "learning_rate": 0.00011720212999410232, "loss": 0.5287910461425781, "step": 266000 }, { "epoch": 1.5812186814558553, "grad_norm": 1.225730538368225, "learning_rate": 0.00011719592517063569, "loss": 0.6312159538269043, "step": 266010 }, { "epoch": 1.5812781235325237, "grad_norm": 1.4979344606399536, "learning_rate": 0.00011718972031274606, "loss": 0.5875029563903809, "step": 266020 }, { "epoch": 1.5813375656091921, "grad_norm": 1.54586660861969, "learning_rate": 0.00011718351542046319, "loss": 0.5826550483703613, "step": 266030 }, { "epoch": 1.5813970076858606, "grad_norm": 1.9601106643676758, "learning_rate": 0.00011717731049381675, "loss": 0.6413786888122559, "step": 266040 }, { "epoch": 1.5814564497625287, "grad_norm": 1.660906434059143, "learning_rate": 0.00011717110553283634, "loss": 0.5551296234130859, "step": 266050 }, { "epoch": 1.5815158918391972, "grad_norm": 1.5526585578918457, "learning_rate": 0.00011716490053755176, "loss": 0.5300385475158691, "step": 266060 }, { "epoch": 1.5815753339158656, "grad_norm": 1.455923318862915, "learning_rate": 0.00011715869550799263, "loss": 0.5358059883117676, "step": 266070 }, { "epoch": 1.581634775992534, "grad_norm": 1.2803055047988892, "learning_rate": 0.00011715249044418862, "loss": 0.5703688144683838, "step": 266080 }, { "epoch": 1.5816942180692024, "grad_norm": 2.3570966720581055, "learning_rate": 0.00011714628534616947, "loss": 0.5570403099060058, "step": 266090 }, { "epoch": 1.5817536601458708, "grad_norm": 1.9228938817977905, "learning_rate": 0.00011714008021396479, "loss": 0.5990969657897949, "step": 266100 }, { "epoch": 1.5818131022225392, "grad_norm": 1.3859965801239014, "learning_rate": 0.00011713387504760431, "loss": 0.5684140205383301, "step": 266110 }, { "epoch": 1.5818725442992077, "grad_norm": 1.6836440563201904, "learning_rate": 0.00011712766984711773, "loss": 0.5922832489013672, "step": 266120 }, { "epoch": 1.581931986375876, "grad_norm": 1.5843433141708374, "learning_rate": 0.00011712146461253466, "loss": 0.6200673580169678, "step": 266130 }, { "epoch": 1.5819914284525445, "grad_norm": 1.134117841720581, "learning_rate": 0.00011711525934388487, "loss": 0.52659912109375, "step": 266140 }, { "epoch": 1.582050870529213, "grad_norm": 1.613964319229126, "learning_rate": 0.00011710905404119798, "loss": 0.5887109756469726, "step": 266150 }, { "epoch": 1.5821103126058813, "grad_norm": 1.8899445533752441, "learning_rate": 0.0001171028487045037, "loss": 0.5903336524963378, "step": 266160 }, { "epoch": 1.5821697546825497, "grad_norm": 1.47555673122406, "learning_rate": 0.00011709664333383173, "loss": 0.5647578716278077, "step": 266170 }, { "epoch": 1.5822291967592181, "grad_norm": 1.432845950126648, "learning_rate": 0.0001170904379292117, "loss": 0.626637315750122, "step": 266180 }, { "epoch": 1.5822886388358863, "grad_norm": 1.292384147644043, "learning_rate": 0.00011708423249067339, "loss": 0.6232640266418457, "step": 266190 }, { "epoch": 1.5823480809125547, "grad_norm": 1.388851523399353, "learning_rate": 0.00011707802701824637, "loss": 0.5727751731872559, "step": 266200 }, { "epoch": 1.5824075229892232, "grad_norm": 1.6776080131530762, "learning_rate": 0.0001170718215119604, "loss": 0.5901215553283692, "step": 266210 }, { "epoch": 1.5824669650658916, "grad_norm": 1.2652000188827515, "learning_rate": 0.00011706561597184518, "loss": 0.5410284042358399, "step": 266220 }, { "epoch": 1.58252640714256, "grad_norm": 1.525145411491394, "learning_rate": 0.00011705941039793031, "loss": 0.5842100143432617, "step": 266230 }, { "epoch": 1.5825858492192282, "grad_norm": 1.3004618883132935, "learning_rate": 0.00011705320479024557, "loss": 0.5726250648498535, "step": 266240 }, { "epoch": 1.5826452912958966, "grad_norm": 1.300825595855713, "learning_rate": 0.00011704699914882058, "loss": 0.5880903244018555, "step": 266250 }, { "epoch": 1.582704733372565, "grad_norm": 1.8772279024124146, "learning_rate": 0.00011704079347368504, "loss": 0.6760384559631347, "step": 266260 }, { "epoch": 1.5827641754492334, "grad_norm": 1.3391616344451904, "learning_rate": 0.00011703458776486868, "loss": 0.5657774448394776, "step": 266270 }, { "epoch": 1.5828236175259018, "grad_norm": 1.6939504146575928, "learning_rate": 0.00011702838202240114, "loss": 0.58558030128479, "step": 266280 }, { "epoch": 1.5828830596025703, "grad_norm": 1.2763447761535645, "learning_rate": 0.00011702217624631209, "loss": 0.5598291397094727, "step": 266290 }, { "epoch": 1.5829425016792387, "grad_norm": 1.6419155597686768, "learning_rate": 0.00011701597043663129, "loss": 0.5587860584259033, "step": 266300 }, { "epoch": 1.583001943755907, "grad_norm": 1.7558820247650146, "learning_rate": 0.00011700976459338835, "loss": 0.602041482925415, "step": 266310 }, { "epoch": 1.5830613858325755, "grad_norm": 1.8789721727371216, "learning_rate": 0.00011700355871661296, "loss": 0.6311137676239014, "step": 266320 }, { "epoch": 1.583120827909244, "grad_norm": 1.5612266063690186, "learning_rate": 0.00011699735280633488, "loss": 0.5874920845031738, "step": 266330 }, { "epoch": 1.5831802699859123, "grad_norm": 1.2274688482284546, "learning_rate": 0.00011699114686258374, "loss": 0.5659130096435547, "step": 266340 }, { "epoch": 1.5832397120625807, "grad_norm": 1.4677164554595947, "learning_rate": 0.00011698494088538924, "loss": 0.5697339057922364, "step": 266350 }, { "epoch": 1.5832991541392492, "grad_norm": 1.6567764282226562, "learning_rate": 0.00011697873487478104, "loss": 0.5539396286010743, "step": 266360 }, { "epoch": 1.5833585962159173, "grad_norm": 1.4683722257614136, "learning_rate": 0.00011697252883078891, "loss": 0.5929667472839355, "step": 266370 }, { "epoch": 1.5834180382925858, "grad_norm": 1.322710633277893, "learning_rate": 0.00011696632275344241, "loss": 0.5583495140075684, "step": 266380 }, { "epoch": 1.5834774803692542, "grad_norm": 1.3467496633529663, "learning_rate": 0.00011696011664277133, "loss": 0.6109362125396729, "step": 266390 }, { "epoch": 1.5835369224459226, "grad_norm": 1.5984827280044556, "learning_rate": 0.00011695391049880536, "loss": 0.6010991096496582, "step": 266400 }, { "epoch": 1.583596364522591, "grad_norm": 1.6451362371444702, "learning_rate": 0.00011694770432157409, "loss": 0.6158296585083007, "step": 266410 }, { "epoch": 1.5836558065992592, "grad_norm": 1.2979656457901, "learning_rate": 0.00011694149811110731, "loss": 0.5305801868438721, "step": 266420 }, { "epoch": 1.5837152486759276, "grad_norm": 1.9093064069747925, "learning_rate": 0.00011693529186743468, "loss": 0.6170763492584228, "step": 266430 }, { "epoch": 1.583774690752596, "grad_norm": 1.7222908735275269, "learning_rate": 0.00011692908559058587, "loss": 0.5702164649963379, "step": 266440 }, { "epoch": 1.5838341328292644, "grad_norm": 1.9458078145980835, "learning_rate": 0.00011692287928059057, "loss": 0.5329224586486816, "step": 266450 }, { "epoch": 1.5838935749059329, "grad_norm": 1.4385818243026733, "learning_rate": 0.0001169166729374785, "loss": 0.6055944919586181, "step": 266460 }, { "epoch": 1.5839530169826013, "grad_norm": 1.4602054357528687, "learning_rate": 0.00011691046656127928, "loss": 0.5550191879272461, "step": 266470 }, { "epoch": 1.5840124590592697, "grad_norm": 1.4943310022354126, "learning_rate": 0.00011690426015202268, "loss": 0.5459622383117676, "step": 266480 }, { "epoch": 1.584071901135938, "grad_norm": 1.8213056325912476, "learning_rate": 0.00011689805370973836, "loss": 0.6162835121154785, "step": 266490 }, { "epoch": 1.5841313432126065, "grad_norm": 1.253987193107605, "learning_rate": 0.000116891847234456, "loss": 0.5691564083099365, "step": 266500 }, { "epoch": 1.584190785289275, "grad_norm": 1.2548317909240723, "learning_rate": 0.00011688564072620529, "loss": 0.5151893615722656, "step": 266510 }, { "epoch": 1.5842502273659433, "grad_norm": 1.6486775875091553, "learning_rate": 0.00011687943418501592, "loss": 0.5634902954101563, "step": 266520 }, { "epoch": 1.5843096694426118, "grad_norm": 1.5927188396453857, "learning_rate": 0.00011687322761091761, "loss": 0.5856047630310058, "step": 266530 }, { "epoch": 1.5843691115192802, "grad_norm": 1.405676245689392, "learning_rate": 0.00011686702100394, "loss": 0.5577790260314941, "step": 266540 }, { "epoch": 1.5844285535959486, "grad_norm": 1.3800642490386963, "learning_rate": 0.00011686081436411281, "loss": 0.5833189010620117, "step": 266550 }, { "epoch": 1.5844879956726168, "grad_norm": 1.444976568222046, "learning_rate": 0.00011685460769146574, "loss": 0.5371494293212891, "step": 266560 }, { "epoch": 1.5845474377492852, "grad_norm": 1.4677025079727173, "learning_rate": 0.00011684840098602846, "loss": 0.6004948616027832, "step": 266570 }, { "epoch": 1.5846068798259536, "grad_norm": 1.3302501440048218, "learning_rate": 0.00011684219424783069, "loss": 0.5827694892883301, "step": 266580 }, { "epoch": 1.584666321902622, "grad_norm": 1.2718340158462524, "learning_rate": 0.00011683598747690205, "loss": 0.6051778793334961, "step": 266590 }, { "epoch": 1.5847257639792902, "grad_norm": 1.7524747848510742, "learning_rate": 0.00011682978067327229, "loss": 0.5587080001831055, "step": 266600 }, { "epoch": 1.5847852060559586, "grad_norm": 1.2906677722930908, "learning_rate": 0.00011682357383697113, "loss": 0.5853753089904785, "step": 266610 }, { "epoch": 1.584844648132627, "grad_norm": 1.4134269952774048, "learning_rate": 0.00011681736696802818, "loss": 0.5392638683319092, "step": 266620 }, { "epoch": 1.5849040902092955, "grad_norm": 1.7569607496261597, "learning_rate": 0.0001168111600664732, "loss": 0.5802980422973633, "step": 266630 }, { "epoch": 1.5849635322859639, "grad_norm": 1.2306519746780396, "learning_rate": 0.00011680495313233586, "loss": 0.5327152729034423, "step": 266640 }, { "epoch": 1.5850229743626323, "grad_norm": 1.5529358386993408, "learning_rate": 0.00011679874616564583, "loss": 0.5674238204956055, "step": 266650 }, { "epoch": 1.5850824164393007, "grad_norm": 1.3098018169403076, "learning_rate": 0.00011679253916643283, "loss": 0.5837528228759765, "step": 266660 }, { "epoch": 1.5851418585159691, "grad_norm": 1.1801880598068237, "learning_rate": 0.00011678633213472654, "loss": 0.5252285957336426, "step": 266670 }, { "epoch": 1.5852013005926375, "grad_norm": 1.4180301427841187, "learning_rate": 0.00011678012507055667, "loss": 0.5791111946105957, "step": 266680 }, { "epoch": 1.585260742669306, "grad_norm": 1.5933722257614136, "learning_rate": 0.00011677391797395288, "loss": 0.49594759941101074, "step": 266690 }, { "epoch": 1.5853201847459744, "grad_norm": 1.4901891946792603, "learning_rate": 0.00011676771084494487, "loss": 0.606605339050293, "step": 266700 }, { "epoch": 1.5853796268226428, "grad_norm": 1.60471773147583, "learning_rate": 0.00011676150368356236, "loss": 0.5814857959747315, "step": 266710 }, { "epoch": 1.5854390688993112, "grad_norm": 1.5071384906768799, "learning_rate": 0.000116755296489835, "loss": 0.532329797744751, "step": 266720 }, { "epoch": 1.5854985109759796, "grad_norm": 1.1093324422836304, "learning_rate": 0.00011674908926379253, "loss": 0.5621050834655762, "step": 266730 }, { "epoch": 1.5855579530526478, "grad_norm": 1.3497835397720337, "learning_rate": 0.00011674288200546464, "loss": 0.5565895080566406, "step": 266740 }, { "epoch": 1.5856173951293162, "grad_norm": 1.3240512609481812, "learning_rate": 0.00011673667471488099, "loss": 0.5417467594146729, "step": 266750 }, { "epoch": 1.5856768372059846, "grad_norm": 1.7906678915023804, "learning_rate": 0.00011673046739207127, "loss": 0.5700864315032959, "step": 266760 }, { "epoch": 1.585736279282653, "grad_norm": 1.4007865190505981, "learning_rate": 0.00011672426003706522, "loss": 0.5645414352416992, "step": 266770 }, { "epoch": 1.5857957213593215, "grad_norm": 1.467953085899353, "learning_rate": 0.0001167180526498925, "loss": 0.5554668426513671, "step": 266780 }, { "epoch": 1.5858551634359896, "grad_norm": 1.3885788917541504, "learning_rate": 0.0001167118452305828, "loss": 0.5937944412231445, "step": 266790 }, { "epoch": 1.585914605512658, "grad_norm": 1.6110138893127441, "learning_rate": 0.00011670563777916585, "loss": 0.5661707878112793, "step": 266800 }, { "epoch": 1.5859740475893265, "grad_norm": 1.7315930128097534, "learning_rate": 0.00011669943029567132, "loss": 0.5366433620452881, "step": 266810 }, { "epoch": 1.5860334896659949, "grad_norm": 1.552574634552002, "learning_rate": 0.00011669322278012889, "loss": 0.5756173133850098, "step": 266820 }, { "epoch": 1.5860929317426633, "grad_norm": 1.4352426528930664, "learning_rate": 0.00011668701523256829, "loss": 0.6150743961334229, "step": 266830 }, { "epoch": 1.5861523738193317, "grad_norm": 1.431077241897583, "learning_rate": 0.00011668080765301916, "loss": 0.5565330505371093, "step": 266840 }, { "epoch": 1.5862118158960001, "grad_norm": 1.416680932044983, "learning_rate": 0.00011667460004151124, "loss": 0.5968245506286621, "step": 266850 }, { "epoch": 1.5862712579726685, "grad_norm": 1.4891173839569092, "learning_rate": 0.00011666839239807423, "loss": 0.6251233577728271, "step": 266860 }, { "epoch": 1.586330700049337, "grad_norm": 1.1899648904800415, "learning_rate": 0.0001166621847227378, "loss": 0.5578145503997802, "step": 266870 }, { "epoch": 1.5863901421260054, "grad_norm": 1.2190165519714355, "learning_rate": 0.00011665597701553164, "loss": 0.6419398307800293, "step": 266880 }, { "epoch": 1.5864495842026738, "grad_norm": 1.1886507272720337, "learning_rate": 0.0001166497692764855, "loss": 0.5185511589050293, "step": 266890 }, { "epoch": 1.5865090262793422, "grad_norm": 1.476304292678833, "learning_rate": 0.00011664356150562901, "loss": 0.596097755432129, "step": 266900 }, { "epoch": 1.5865684683560106, "grad_norm": 1.9045485258102417, "learning_rate": 0.00011663735370299186, "loss": 0.6203710556030273, "step": 266910 }, { "epoch": 1.586627910432679, "grad_norm": 1.7548763751983643, "learning_rate": 0.00011663114586860386, "loss": 0.6023323059082031, "step": 266920 }, { "epoch": 1.5866873525093472, "grad_norm": 1.4488518238067627, "learning_rate": 0.00011662493800249457, "loss": 0.5896302700042725, "step": 266930 }, { "epoch": 1.5867467945860156, "grad_norm": 1.6981226205825806, "learning_rate": 0.00011661873010469376, "loss": 0.5653932571411133, "step": 266940 }, { "epoch": 1.586806236662684, "grad_norm": 1.353603720664978, "learning_rate": 0.00011661252217523109, "loss": 0.5427715301513671, "step": 266950 }, { "epoch": 1.5868656787393525, "grad_norm": 1.5807690620422363, "learning_rate": 0.00011660631421413628, "loss": 0.535715389251709, "step": 266960 }, { "epoch": 1.5869251208160207, "grad_norm": 1.544689655303955, "learning_rate": 0.00011660010622143905, "loss": 0.589515209197998, "step": 266970 }, { "epoch": 1.586984562892689, "grad_norm": 1.590371012687683, "learning_rate": 0.00011659389819716904, "loss": 0.5621392250061035, "step": 266980 }, { "epoch": 1.5870440049693575, "grad_norm": 1.4544875621795654, "learning_rate": 0.000116587690141356, "loss": 0.5595820426940918, "step": 266990 }, { "epoch": 1.587103447046026, "grad_norm": 1.434210181236267, "learning_rate": 0.00011658148205402956, "loss": 0.5595896720886231, "step": 267000 }, { "epoch": 1.5871628891226943, "grad_norm": 1.3374894857406616, "learning_rate": 0.0001165752739352195, "loss": 0.5402806758880615, "step": 267010 }, { "epoch": 1.5872223311993627, "grad_norm": 1.3431291580200195, "learning_rate": 0.00011656906578495546, "loss": 0.5419209480285645, "step": 267020 }, { "epoch": 1.5872817732760311, "grad_norm": 1.8788857460021973, "learning_rate": 0.00011656285760326716, "loss": 0.568182373046875, "step": 267030 }, { "epoch": 1.5873412153526996, "grad_norm": 1.2902196645736694, "learning_rate": 0.00011655664939018429, "loss": 0.5778793334960938, "step": 267040 }, { "epoch": 1.587400657429368, "grad_norm": 1.207931399345398, "learning_rate": 0.00011655044114573657, "loss": 0.6272048950195312, "step": 267050 }, { "epoch": 1.5874600995060364, "grad_norm": 1.6876672506332397, "learning_rate": 0.00011654423286995367, "loss": 0.5676415443420411, "step": 267060 }, { "epoch": 1.5875195415827048, "grad_norm": 1.2934610843658447, "learning_rate": 0.00011653802456286527, "loss": 0.5645341396331787, "step": 267070 }, { "epoch": 1.5875789836593732, "grad_norm": 1.276072382926941, "learning_rate": 0.00011653181622450113, "loss": 0.530474328994751, "step": 267080 }, { "epoch": 1.5876384257360416, "grad_norm": 1.741644024848938, "learning_rate": 0.0001165256078548909, "loss": 0.5709780693054199, "step": 267090 }, { "epoch": 1.58769786781271, "grad_norm": 1.2221760749816895, "learning_rate": 0.00011651939945406431, "loss": 0.5761205673217773, "step": 267100 }, { "epoch": 1.5877573098893782, "grad_norm": 1.1984906196594238, "learning_rate": 0.00011651319102205106, "loss": 0.5731435298919678, "step": 267110 }, { "epoch": 1.5878167519660467, "grad_norm": 1.4085296392440796, "learning_rate": 0.0001165069825588808, "loss": 0.5745707511901855, "step": 267120 }, { "epoch": 1.587876194042715, "grad_norm": 1.3205417394638062, "learning_rate": 0.00011650077406458326, "loss": 0.563794469833374, "step": 267130 }, { "epoch": 1.5879356361193835, "grad_norm": 1.363303303718567, "learning_rate": 0.00011649456553918817, "loss": 0.5334476470947266, "step": 267140 }, { "epoch": 1.587995078196052, "grad_norm": 1.1780978441238403, "learning_rate": 0.00011648835698272517, "loss": 0.5298651218414306, "step": 267150 }, { "epoch": 1.58805452027272, "grad_norm": 1.3492053747177124, "learning_rate": 0.00011648214839522402, "loss": 0.5856986522674561, "step": 267160 }, { "epoch": 1.5881139623493885, "grad_norm": 1.3226033449172974, "learning_rate": 0.00011647593977671439, "loss": 0.5978012084960938, "step": 267170 }, { "epoch": 1.588173404426057, "grad_norm": 1.2020361423492432, "learning_rate": 0.00011646973112722594, "loss": 0.5848577499389649, "step": 267180 }, { "epoch": 1.5882328465027253, "grad_norm": 1.789146900177002, "learning_rate": 0.00011646352244678844, "loss": 0.5725502967834473, "step": 267190 }, { "epoch": 1.5882922885793938, "grad_norm": 1.746023416519165, "learning_rate": 0.00011645731373543158, "loss": 0.5698459148406982, "step": 267200 }, { "epoch": 1.5883517306560622, "grad_norm": 1.2223142385482788, "learning_rate": 0.00011645110499318499, "loss": 0.6038913249969482, "step": 267210 }, { "epoch": 1.5884111727327306, "grad_norm": 1.2555999755859375, "learning_rate": 0.00011644489622007845, "loss": 0.5298113822937012, "step": 267220 }, { "epoch": 1.588470614809399, "grad_norm": 1.6286274194717407, "learning_rate": 0.00011643868741614165, "loss": 0.6206256866455078, "step": 267230 }, { "epoch": 1.5885300568860674, "grad_norm": 1.4613685607910156, "learning_rate": 0.00011643247858140424, "loss": 0.5734626770019531, "step": 267240 }, { "epoch": 1.5885894989627358, "grad_norm": 1.4205132722854614, "learning_rate": 0.00011642626971589598, "loss": 0.5816196441650391, "step": 267250 }, { "epoch": 1.5886489410394042, "grad_norm": 1.6648979187011719, "learning_rate": 0.00011642006081964653, "loss": 0.5828029632568359, "step": 267260 }, { "epoch": 1.5887083831160727, "grad_norm": 1.672494888305664, "learning_rate": 0.00011641385189268561, "loss": 0.6049854278564453, "step": 267270 }, { "epoch": 1.588767825192741, "grad_norm": 1.4050767421722412, "learning_rate": 0.00011640764293504293, "loss": 0.6371837615966797, "step": 267280 }, { "epoch": 1.5888272672694095, "grad_norm": 1.2498581409454346, "learning_rate": 0.00011640143394674819, "loss": 0.5614119529724121, "step": 267290 }, { "epoch": 1.5888867093460777, "grad_norm": 1.464360237121582, "learning_rate": 0.00011639522492783105, "loss": 0.5504907608032227, "step": 267300 }, { "epoch": 1.588946151422746, "grad_norm": 1.6599979400634766, "learning_rate": 0.00011638901587832125, "loss": 0.5361352920532226, "step": 267310 }, { "epoch": 1.5890055934994145, "grad_norm": 1.4435337781906128, "learning_rate": 0.00011638280679824851, "loss": 0.5865420341491699, "step": 267320 }, { "epoch": 1.589065035576083, "grad_norm": 1.3630776405334473, "learning_rate": 0.00011637659768764251, "loss": 0.5873774528503418, "step": 267330 }, { "epoch": 1.589124477652751, "grad_norm": 1.6562740802764893, "learning_rate": 0.00011637038854653293, "loss": 0.6113067626953125, "step": 267340 }, { "epoch": 1.5891839197294195, "grad_norm": 1.7128487825393677, "learning_rate": 0.0001163641793749495, "loss": 0.6865900993347168, "step": 267350 }, { "epoch": 1.589243361806088, "grad_norm": 1.8126505613327026, "learning_rate": 0.00011635797017292191, "loss": 0.6048968315124512, "step": 267360 }, { "epoch": 1.5893028038827564, "grad_norm": 1.333509087562561, "learning_rate": 0.00011635176094047985, "loss": 0.5562768936157226, "step": 267370 }, { "epoch": 1.5893622459594248, "grad_norm": 1.7046927213668823, "learning_rate": 0.00011634555167765309, "loss": 0.5584855079650879, "step": 267380 }, { "epoch": 1.5894216880360932, "grad_norm": 1.0159238576889038, "learning_rate": 0.00011633934238447124, "loss": 0.5770345211029053, "step": 267390 }, { "epoch": 1.5894811301127616, "grad_norm": 1.8177164793014526, "learning_rate": 0.00011633313306096407, "loss": 0.5847102165222168, "step": 267400 }, { "epoch": 1.58954057218943, "grad_norm": 1.3240848779678345, "learning_rate": 0.00011632692370716127, "loss": 0.5189750671386719, "step": 267410 }, { "epoch": 1.5896000142660984, "grad_norm": 1.4554314613342285, "learning_rate": 0.00011632071432309251, "loss": 0.5972767829895019, "step": 267420 }, { "epoch": 1.5896594563427668, "grad_norm": 1.4371427297592163, "learning_rate": 0.00011631450490878752, "loss": 0.6105729579925537, "step": 267430 }, { "epoch": 1.5897188984194353, "grad_norm": 1.1983652114868164, "learning_rate": 0.00011630829546427604, "loss": 0.5578348159790039, "step": 267440 }, { "epoch": 1.5897783404961037, "grad_norm": 1.363953948020935, "learning_rate": 0.00011630208598958767, "loss": 0.6177512168884277, "step": 267450 }, { "epoch": 1.589837782572772, "grad_norm": 1.6275403499603271, "learning_rate": 0.00011629587648475225, "loss": 0.5532639503479004, "step": 267460 }, { "epoch": 1.5898972246494405, "grad_norm": 1.47356379032135, "learning_rate": 0.00011628966694979937, "loss": 0.6120248317718506, "step": 267470 }, { "epoch": 1.5899566667261087, "grad_norm": 1.959168553352356, "learning_rate": 0.00011628345738475878, "loss": 0.5835577011108398, "step": 267480 }, { "epoch": 1.590016108802777, "grad_norm": 1.3719565868377686, "learning_rate": 0.00011627724778966021, "loss": 0.560636043548584, "step": 267490 }, { "epoch": 1.5900755508794455, "grad_norm": 1.416520357131958, "learning_rate": 0.00011627103816453331, "loss": 0.6106249809265136, "step": 267500 }, { "epoch": 1.590134992956114, "grad_norm": 1.4481512308120728, "learning_rate": 0.00011626482850940783, "loss": 0.5614691734313965, "step": 267510 }, { "epoch": 1.5901944350327823, "grad_norm": 0.9793647527694702, "learning_rate": 0.00011625861882431346, "loss": 0.6131546497344971, "step": 267520 }, { "epoch": 1.5902538771094505, "grad_norm": 1.2698081731796265, "learning_rate": 0.0001162524091092799, "loss": 0.5256337642669677, "step": 267530 }, { "epoch": 1.590313319186119, "grad_norm": 1.8112846612930298, "learning_rate": 0.00011624619936433685, "loss": 0.6491159439086914, "step": 267540 }, { "epoch": 1.5903727612627874, "grad_norm": 1.3973931074142456, "learning_rate": 0.00011623998958951401, "loss": 0.6073686122894287, "step": 267550 }, { "epoch": 1.5904322033394558, "grad_norm": 1.142691731452942, "learning_rate": 0.0001162337797848411, "loss": 0.5288530826568604, "step": 267560 }, { "epoch": 1.5904916454161242, "grad_norm": 1.3526710271835327, "learning_rate": 0.00011622756995034787, "loss": 0.573957872390747, "step": 267570 }, { "epoch": 1.5905510874927926, "grad_norm": 1.0835745334625244, "learning_rate": 0.00011622136008606392, "loss": 0.5498240947723388, "step": 267580 }, { "epoch": 1.590610529569461, "grad_norm": 1.8368769884109497, "learning_rate": 0.00011621515019201906, "loss": 0.5706133842468262, "step": 267590 }, { "epoch": 1.5906699716461294, "grad_norm": 1.340821623802185, "learning_rate": 0.00011620894026824295, "loss": 0.5697089195251465, "step": 267600 }, { "epoch": 1.5907294137227979, "grad_norm": 1.1815427541732788, "learning_rate": 0.0001162027303147653, "loss": 0.5266197204589844, "step": 267610 }, { "epoch": 1.5907888557994663, "grad_norm": 1.5919853448867798, "learning_rate": 0.00011619652033161579, "loss": 0.5595338821411133, "step": 267620 }, { "epoch": 1.5908482978761347, "grad_norm": 1.430480718612671, "learning_rate": 0.00011619031031882417, "loss": 0.5972546577453614, "step": 267630 }, { "epoch": 1.590907739952803, "grad_norm": 1.341246247291565, "learning_rate": 0.00011618410027642015, "loss": 0.6122739791870118, "step": 267640 }, { "epoch": 1.5909671820294715, "grad_norm": 1.5790923833847046, "learning_rate": 0.00011617789020443334, "loss": 0.550879955291748, "step": 267650 }, { "epoch": 1.59102662410614, "grad_norm": 1.7402321100234985, "learning_rate": 0.00011617168010289361, "loss": 0.602042293548584, "step": 267660 }, { "epoch": 1.5910860661828081, "grad_norm": 1.4519506692886353, "learning_rate": 0.00011616546997183053, "loss": 0.49188523292541503, "step": 267670 }, { "epoch": 1.5911455082594765, "grad_norm": 1.2027652263641357, "learning_rate": 0.00011615925981127386, "loss": 0.6112086296081543, "step": 267680 }, { "epoch": 1.591204950336145, "grad_norm": 1.9554389715194702, "learning_rate": 0.00011615304962125332, "loss": 0.5720295429229736, "step": 267690 }, { "epoch": 1.5912643924128134, "grad_norm": 1.243170976638794, "learning_rate": 0.00011614683940179861, "loss": 0.48157658576965334, "step": 267700 }, { "epoch": 1.5913238344894816, "grad_norm": 1.744663953781128, "learning_rate": 0.00011614062915293942, "loss": 0.5887192726135254, "step": 267710 }, { "epoch": 1.59138327656615, "grad_norm": 1.6874760389328003, "learning_rate": 0.00011613441887470544, "loss": 0.6678794860839844, "step": 267720 }, { "epoch": 1.5914427186428184, "grad_norm": 1.2458759546279907, "learning_rate": 0.0001161282085671264, "loss": 0.5243431091308594, "step": 267730 }, { "epoch": 1.5915021607194868, "grad_norm": 1.3527896404266357, "learning_rate": 0.00011612199823023207, "loss": 0.5952128410339356, "step": 267740 }, { "epoch": 1.5915616027961552, "grad_norm": 1.4773372411727905, "learning_rate": 0.00011611578786405206, "loss": 0.5591437816619873, "step": 267750 }, { "epoch": 1.5916210448728236, "grad_norm": 1.4231524467468262, "learning_rate": 0.00011610957746861612, "loss": 0.48633432388305664, "step": 267760 }, { "epoch": 1.591680486949492, "grad_norm": 1.5566316843032837, "learning_rate": 0.00011610336704395397, "loss": 0.4854398727416992, "step": 267770 }, { "epoch": 1.5917399290261605, "grad_norm": 1.4199464321136475, "learning_rate": 0.00011609715659009532, "loss": 0.6161339759826661, "step": 267780 }, { "epoch": 1.5917993711028289, "grad_norm": 1.3750680685043335, "learning_rate": 0.00011609094610706985, "loss": 0.5629572391510009, "step": 267790 }, { "epoch": 1.5918588131794973, "grad_norm": 1.2389936447143555, "learning_rate": 0.00011608473559490727, "loss": 0.558036470413208, "step": 267800 }, { "epoch": 1.5919182552561657, "grad_norm": 1.6101197004318237, "learning_rate": 0.00011607852505363732, "loss": 0.5704154014587403, "step": 267810 }, { "epoch": 1.5919776973328341, "grad_norm": 1.406723141670227, "learning_rate": 0.00011607231448328968, "loss": 0.5648469924926758, "step": 267820 }, { "epoch": 1.5920371394095025, "grad_norm": 1.4177823066711426, "learning_rate": 0.00011606610388389409, "loss": 0.5473301410675049, "step": 267830 }, { "epoch": 1.592096581486171, "grad_norm": 1.8645168542861938, "learning_rate": 0.00011605989325548024, "loss": 0.5667216300964355, "step": 267840 }, { "epoch": 1.5921560235628391, "grad_norm": 1.522503137588501, "learning_rate": 0.00011605368259807783, "loss": 0.6075691223144531, "step": 267850 }, { "epoch": 1.5922154656395076, "grad_norm": 1.4787439107894897, "learning_rate": 0.00011604747191171657, "loss": 0.553464412689209, "step": 267860 }, { "epoch": 1.592274907716176, "grad_norm": 1.3258343935012817, "learning_rate": 0.0001160412611964262, "loss": 0.5513500213623047, "step": 267870 }, { "epoch": 1.5923343497928444, "grad_norm": 1.620483636856079, "learning_rate": 0.00011603505045223642, "loss": 0.5872986793518067, "step": 267880 }, { "epoch": 1.5923937918695128, "grad_norm": 1.4061951637268066, "learning_rate": 0.00011602883967917693, "loss": 0.5609635353088379, "step": 267890 }, { "epoch": 1.592453233946181, "grad_norm": 1.292522668838501, "learning_rate": 0.0001160226288772774, "loss": 0.5698957443237305, "step": 267900 }, { "epoch": 1.5925126760228494, "grad_norm": 1.2859117984771729, "learning_rate": 0.00011601641804656763, "loss": 0.5930522918701172, "step": 267910 }, { "epoch": 1.5925721180995178, "grad_norm": 1.7541731595993042, "learning_rate": 0.00011601020718707725, "loss": 0.5460451126098633, "step": 267920 }, { "epoch": 1.5926315601761862, "grad_norm": 1.7782891988754272, "learning_rate": 0.00011600399629883603, "loss": 0.5899747848510742, "step": 267930 }, { "epoch": 1.5926910022528546, "grad_norm": 1.5827702283859253, "learning_rate": 0.0001159977853818736, "loss": 0.5489969253540039, "step": 267940 }, { "epoch": 1.592750444329523, "grad_norm": 1.5077903270721436, "learning_rate": 0.00011599157443621978, "loss": 0.6064376831054688, "step": 267950 }, { "epoch": 1.5928098864061915, "grad_norm": 1.451486587524414, "learning_rate": 0.00011598536346190423, "loss": 0.5747336387634278, "step": 267960 }, { "epoch": 1.59286932848286, "grad_norm": 1.6354767084121704, "learning_rate": 0.00011597915245895663, "loss": 0.5772045135498047, "step": 267970 }, { "epoch": 1.5929287705595283, "grad_norm": 1.426906704902649, "learning_rate": 0.00011597294142740671, "loss": 0.5771984100341797, "step": 267980 }, { "epoch": 1.5929882126361967, "grad_norm": 1.8572553396224976, "learning_rate": 0.00011596673036728422, "loss": 0.6032986640930176, "step": 267990 }, { "epoch": 1.5930476547128651, "grad_norm": 1.614742636680603, "learning_rate": 0.00011596051927861884, "loss": 0.5848546028137207, "step": 268000 }, { "epoch": 1.5931070967895335, "grad_norm": 1.435268521308899, "learning_rate": 0.00011595430816144024, "loss": 0.6015181541442871, "step": 268010 }, { "epoch": 1.593166538866202, "grad_norm": 1.0927175283432007, "learning_rate": 0.00011594809701577822, "loss": 0.5410048007965088, "step": 268020 }, { "epoch": 1.5932259809428704, "grad_norm": 1.5222489833831787, "learning_rate": 0.00011594188584166244, "loss": 0.6105446338653564, "step": 268030 }, { "epoch": 1.5932854230195386, "grad_norm": 1.606415867805481, "learning_rate": 0.00011593567463912258, "loss": 0.6364280223846436, "step": 268040 }, { "epoch": 1.593344865096207, "grad_norm": 1.4676250219345093, "learning_rate": 0.00011592946340818844, "loss": 0.5688714981079102, "step": 268050 }, { "epoch": 1.5934043071728754, "grad_norm": 1.575071096420288, "learning_rate": 0.00011592325214888968, "loss": 0.6315629959106446, "step": 268060 }, { "epoch": 1.5934637492495438, "grad_norm": 1.5044533014297485, "learning_rate": 0.00011591704086125604, "loss": 0.5696607112884522, "step": 268070 }, { "epoch": 1.593523191326212, "grad_norm": 1.5024666786193848, "learning_rate": 0.00011591082954531713, "loss": 0.573661994934082, "step": 268080 }, { "epoch": 1.5935826334028804, "grad_norm": 1.476402759552002, "learning_rate": 0.00011590461820110281, "loss": 0.5851357460021973, "step": 268090 }, { "epoch": 1.5936420754795488, "grad_norm": 1.2890241146087646, "learning_rate": 0.00011589840682864271, "loss": 0.570405387878418, "step": 268100 }, { "epoch": 1.5937015175562173, "grad_norm": 1.4125745296478271, "learning_rate": 0.00011589219542796654, "loss": 0.6275615692138672, "step": 268110 }, { "epoch": 1.5937609596328857, "grad_norm": 1.4865968227386475, "learning_rate": 0.00011588598399910406, "loss": 0.5527508735656739, "step": 268120 }, { "epoch": 1.593820401709554, "grad_norm": 1.179518699645996, "learning_rate": 0.00011587977254208496, "loss": 0.5944808006286622, "step": 268130 }, { "epoch": 1.5938798437862225, "grad_norm": 1.2723174095153809, "learning_rate": 0.00011587356105693891, "loss": 0.5678611755371094, "step": 268140 }, { "epoch": 1.593939285862891, "grad_norm": 1.4497201442718506, "learning_rate": 0.00011586734954369571, "loss": 0.5740171432495117, "step": 268150 }, { "epoch": 1.5939987279395593, "grad_norm": 1.3384153842926025, "learning_rate": 0.000115861138002385, "loss": 0.5689615726470947, "step": 268160 }, { "epoch": 1.5940581700162277, "grad_norm": 1.426112413406372, "learning_rate": 0.00011585492643303652, "loss": 0.5911697387695313, "step": 268170 }, { "epoch": 1.5941176120928962, "grad_norm": 1.497554898262024, "learning_rate": 0.00011584871483568002, "loss": 0.5985019683837891, "step": 268180 }, { "epoch": 1.5941770541695646, "grad_norm": 1.2525672912597656, "learning_rate": 0.00011584250321034516, "loss": 0.5244871139526367, "step": 268190 }, { "epoch": 1.594236496246233, "grad_norm": 1.253113031387329, "learning_rate": 0.00011583629155706164, "loss": 0.6183463096618652, "step": 268200 }, { "epoch": 1.5942959383229014, "grad_norm": 1.4164162874221802, "learning_rate": 0.00011583007987585923, "loss": 0.5570412158966065, "step": 268210 }, { "epoch": 1.5943553803995696, "grad_norm": 1.2836304903030396, "learning_rate": 0.00011582386816676765, "loss": 0.599370288848877, "step": 268220 }, { "epoch": 1.594414822476238, "grad_norm": 1.7471561431884766, "learning_rate": 0.00011581765642981654, "loss": 0.5772455215454102, "step": 268230 }, { "epoch": 1.5944742645529064, "grad_norm": 1.507949709892273, "learning_rate": 0.00011581144466503573, "loss": 0.6295231819152832, "step": 268240 }, { "epoch": 1.5945337066295748, "grad_norm": 1.6246728897094727, "learning_rate": 0.00011580523287245479, "loss": 0.5452869415283204, "step": 268250 }, { "epoch": 1.5945931487062432, "grad_norm": 1.313127040863037, "learning_rate": 0.00011579902105210356, "loss": 0.5457404613494873, "step": 268260 }, { "epoch": 1.5946525907829114, "grad_norm": 1.2907100915908813, "learning_rate": 0.00011579280920401169, "loss": 0.5821361541748047, "step": 268270 }, { "epoch": 1.5947120328595799, "grad_norm": 1.661414384841919, "learning_rate": 0.00011578659732820893, "loss": 0.5927978515625, "step": 268280 }, { "epoch": 1.5947714749362483, "grad_norm": 1.5267528295516968, "learning_rate": 0.00011578038542472498, "loss": 0.6011207580566407, "step": 268290 }, { "epoch": 1.5948309170129167, "grad_norm": 1.5831146240234375, "learning_rate": 0.00011577417349358954, "loss": 0.6155433654785156, "step": 268300 }, { "epoch": 1.594890359089585, "grad_norm": 1.2594075202941895, "learning_rate": 0.00011576796153483236, "loss": 0.6163895130157471, "step": 268310 }, { "epoch": 1.5949498011662535, "grad_norm": 1.1134270429611206, "learning_rate": 0.00011576174954848311, "loss": 0.564129114151001, "step": 268320 }, { "epoch": 1.595009243242922, "grad_norm": 1.360636830329895, "learning_rate": 0.00011575553753457156, "loss": 0.5809868812561035, "step": 268330 }, { "epoch": 1.5950686853195903, "grad_norm": 1.8848592042922974, "learning_rate": 0.0001157493254931274, "loss": 0.5759714126586915, "step": 268340 }, { "epoch": 1.5951281273962588, "grad_norm": 1.3159844875335693, "learning_rate": 0.00011574311342418032, "loss": 0.6083330154418946, "step": 268350 }, { "epoch": 1.5951875694729272, "grad_norm": 1.57338285446167, "learning_rate": 0.00011573690132776007, "loss": 0.5965848445892334, "step": 268360 }, { "epoch": 1.5952470115495956, "grad_norm": 1.8825347423553467, "learning_rate": 0.00011573068920389638, "loss": 0.5701255321502685, "step": 268370 }, { "epoch": 1.595306453626264, "grad_norm": 1.336599588394165, "learning_rate": 0.00011572447705261893, "loss": 0.5593539714813233, "step": 268380 }, { "epoch": 1.5953658957029324, "grad_norm": 1.60858154296875, "learning_rate": 0.00011571826487395745, "loss": 0.6474842548370361, "step": 268390 }, { "epoch": 1.5954253377796008, "grad_norm": 1.750661015510559, "learning_rate": 0.00011571205266794166, "loss": 0.6558170318603516, "step": 268400 }, { "epoch": 1.595484779856269, "grad_norm": 1.305867314338684, "learning_rate": 0.00011570584043460128, "loss": 0.5507508277893066, "step": 268410 }, { "epoch": 1.5955442219329374, "grad_norm": 1.512393832206726, "learning_rate": 0.00011569962817396603, "loss": 0.5359766006469726, "step": 268420 }, { "epoch": 1.5956036640096058, "grad_norm": 1.6206778287887573, "learning_rate": 0.0001156934158860656, "loss": 0.5698708057403564, "step": 268430 }, { "epoch": 1.5956631060862743, "grad_norm": 1.7644633054733276, "learning_rate": 0.00011568720357092974, "loss": 0.5959289073944092, "step": 268440 }, { "epoch": 1.5957225481629425, "grad_norm": 1.353602409362793, "learning_rate": 0.00011568099122858816, "loss": 0.5272054195404052, "step": 268450 }, { "epoch": 1.5957819902396109, "grad_norm": 1.338642954826355, "learning_rate": 0.00011567477885907061, "loss": 0.6268656253814697, "step": 268460 }, { "epoch": 1.5958414323162793, "grad_norm": 1.392009973526001, "learning_rate": 0.00011566856646240672, "loss": 0.5802748203277588, "step": 268470 }, { "epoch": 1.5959008743929477, "grad_norm": 1.2352776527404785, "learning_rate": 0.00011566235403862625, "loss": 0.49494643211364747, "step": 268480 }, { "epoch": 1.5959603164696161, "grad_norm": 1.7289378643035889, "learning_rate": 0.00011565614158775899, "loss": 0.6392336368560791, "step": 268490 }, { "epoch": 1.5960197585462845, "grad_norm": 1.565876841545105, "learning_rate": 0.00011564992910983456, "loss": 0.578414011001587, "step": 268500 }, { "epoch": 1.596079200622953, "grad_norm": 1.1913788318634033, "learning_rate": 0.00011564371660488271, "loss": 0.5859078407287598, "step": 268510 }, { "epoch": 1.5961386426996214, "grad_norm": 1.6262470483779907, "learning_rate": 0.00011563750407293319, "loss": 0.603825044631958, "step": 268520 }, { "epoch": 1.5961980847762898, "grad_norm": 1.6860042810440063, "learning_rate": 0.00011563129151401566, "loss": 0.6531516075134277, "step": 268530 }, { "epoch": 1.5962575268529582, "grad_norm": 1.252453088760376, "learning_rate": 0.0001156250789281599, "loss": 0.5202085018157959, "step": 268540 }, { "epoch": 1.5963169689296266, "grad_norm": 1.387825608253479, "learning_rate": 0.00011561886631539558, "loss": 0.5705210208892822, "step": 268550 }, { "epoch": 1.596376411006295, "grad_norm": 1.440042495727539, "learning_rate": 0.00011561265367575245, "loss": 0.6169528007507324, "step": 268560 }, { "epoch": 1.5964358530829634, "grad_norm": 1.4971604347229004, "learning_rate": 0.00011560644100926022, "loss": 0.5045867919921875, "step": 268570 }, { "epoch": 1.5964952951596318, "grad_norm": 1.6917767524719238, "learning_rate": 0.00011560022831594862, "loss": 0.6227957725524902, "step": 268580 }, { "epoch": 1.5965547372363, "grad_norm": 1.5582119226455688, "learning_rate": 0.00011559401559584735, "loss": 0.5809016227722168, "step": 268590 }, { "epoch": 1.5966141793129685, "grad_norm": 1.501726746559143, "learning_rate": 0.00011558780284898612, "loss": 0.5718982219696045, "step": 268600 }, { "epoch": 1.5966736213896369, "grad_norm": 1.879833459854126, "learning_rate": 0.00011558159007539466, "loss": 0.6283252716064454, "step": 268610 }, { "epoch": 1.5967330634663053, "grad_norm": 1.2787210941314697, "learning_rate": 0.00011557537727510275, "loss": 0.5444212913513183, "step": 268620 }, { "epoch": 1.5967925055429737, "grad_norm": 1.5623282194137573, "learning_rate": 0.00011556916444813999, "loss": 0.5807612419128418, "step": 268630 }, { "epoch": 1.5968519476196419, "grad_norm": 1.5252888202667236, "learning_rate": 0.00011556295159453623, "loss": 0.6107892990112305, "step": 268640 }, { "epoch": 1.5969113896963103, "grad_norm": 2.4432265758514404, "learning_rate": 0.0001155567387143211, "loss": 0.6110889434814453, "step": 268650 }, { "epoch": 1.5969708317729787, "grad_norm": 1.3156523704528809, "learning_rate": 0.00011555052580752433, "loss": 0.547177791595459, "step": 268660 }, { "epoch": 1.5970302738496471, "grad_norm": 1.643949270248413, "learning_rate": 0.00011554431287417568, "loss": 0.5555441856384278, "step": 268670 }, { "epoch": 1.5970897159263155, "grad_norm": 1.4687867164611816, "learning_rate": 0.00011553809991430482, "loss": 0.567164421081543, "step": 268680 }, { "epoch": 1.597149158002984, "grad_norm": 1.3328242301940918, "learning_rate": 0.00011553188692794155, "loss": 0.5934098243713379, "step": 268690 }, { "epoch": 1.5972086000796524, "grad_norm": 1.3770891427993774, "learning_rate": 0.0001155256739151155, "loss": 0.5563833236694335, "step": 268700 }, { "epoch": 1.5972680421563208, "grad_norm": 1.5887666940689087, "learning_rate": 0.00011551946087585646, "loss": 0.559672737121582, "step": 268710 }, { "epoch": 1.5973274842329892, "grad_norm": 1.5145752429962158, "learning_rate": 0.00011551324781019411, "loss": 0.5734774589538574, "step": 268720 }, { "epoch": 1.5973869263096576, "grad_norm": 1.2341452836990356, "learning_rate": 0.00011550703471815818, "loss": 0.5671751976013184, "step": 268730 }, { "epoch": 1.597446368386326, "grad_norm": 1.1389514207839966, "learning_rate": 0.0001155008215997784, "loss": 0.5521852493286132, "step": 268740 }, { "epoch": 1.5975058104629944, "grad_norm": 1.8853845596313477, "learning_rate": 0.00011549460845508447, "loss": 0.5957300662994385, "step": 268750 }, { "epoch": 1.5975652525396629, "grad_norm": 1.5166473388671875, "learning_rate": 0.00011548839528410615, "loss": 0.5882724761962891, "step": 268760 }, { "epoch": 1.5976246946163313, "grad_norm": 1.5171996355056763, "learning_rate": 0.00011548218208687316, "loss": 0.5867501258850097, "step": 268770 }, { "epoch": 1.5976841366929995, "grad_norm": 1.0278598070144653, "learning_rate": 0.00011547596886341516, "loss": 0.5013917922973633, "step": 268780 }, { "epoch": 1.5977435787696679, "grad_norm": 1.2453974485397339, "learning_rate": 0.00011546975561376192, "loss": 0.6391166687011719, "step": 268790 }, { "epoch": 1.5978030208463363, "grad_norm": 1.544489860534668, "learning_rate": 0.00011546354233794319, "loss": 0.5648706912994385, "step": 268800 }, { "epoch": 1.5978624629230047, "grad_norm": 1.6494417190551758, "learning_rate": 0.00011545732903598863, "loss": 0.598482084274292, "step": 268810 }, { "epoch": 1.597921904999673, "grad_norm": 1.285832166671753, "learning_rate": 0.000115451115707928, "loss": 0.4968269348144531, "step": 268820 }, { "epoch": 1.5979813470763413, "grad_norm": 1.2815649509429932, "learning_rate": 0.00011544490235379101, "loss": 0.5782666206359863, "step": 268830 }, { "epoch": 1.5980407891530097, "grad_norm": 1.738842487335205, "learning_rate": 0.00011543868897360739, "loss": 0.558779239654541, "step": 268840 }, { "epoch": 1.5981002312296781, "grad_norm": 1.3320889472961426, "learning_rate": 0.00011543247556740687, "loss": 0.5632681369781494, "step": 268850 }, { "epoch": 1.5981596733063466, "grad_norm": 1.4889603853225708, "learning_rate": 0.00011542626213521915, "loss": 0.5396668910980225, "step": 268860 }, { "epoch": 1.598219115383015, "grad_norm": 0.9119039177894592, "learning_rate": 0.00011542004867707397, "loss": 0.5728584289550781, "step": 268870 }, { "epoch": 1.5982785574596834, "grad_norm": 2.0840094089508057, "learning_rate": 0.00011541383519300104, "loss": 0.606110668182373, "step": 268880 }, { "epoch": 1.5983379995363518, "grad_norm": 1.3670436143875122, "learning_rate": 0.0001154076216830301, "loss": 0.6293125152587891, "step": 268890 }, { "epoch": 1.5983974416130202, "grad_norm": 1.8773574829101562, "learning_rate": 0.00011540140814719086, "loss": 0.552496337890625, "step": 268900 }, { "epoch": 1.5984568836896886, "grad_norm": 1.29633629322052, "learning_rate": 0.00011539519458551304, "loss": 0.5753958702087403, "step": 268910 }, { "epoch": 1.598516325766357, "grad_norm": 1.3021677732467651, "learning_rate": 0.0001153889809980264, "loss": 0.5466708183288574, "step": 268920 }, { "epoch": 1.5985757678430255, "grad_norm": 1.3482303619384766, "learning_rate": 0.00011538276738476061, "loss": 0.5101064682006836, "step": 268930 }, { "epoch": 1.5986352099196939, "grad_norm": 1.454696536064148, "learning_rate": 0.00011537655374574541, "loss": 0.548207950592041, "step": 268940 }, { "epoch": 1.5986946519963623, "grad_norm": 1.6310343742370605, "learning_rate": 0.0001153703400810106, "loss": 0.5657884120941162, "step": 268950 }, { "epoch": 1.5987540940730305, "grad_norm": 1.5520721673965454, "learning_rate": 0.00011536412639058576, "loss": 0.559428071975708, "step": 268960 }, { "epoch": 1.598813536149699, "grad_norm": 1.3878015279769897, "learning_rate": 0.00011535791267450071, "loss": 0.5473648071289062, "step": 268970 }, { "epoch": 1.5988729782263673, "grad_norm": 1.3529131412506104, "learning_rate": 0.00011535169893278518, "loss": 0.6009090900421142, "step": 268980 }, { "epoch": 1.5989324203030357, "grad_norm": 1.3816319704055786, "learning_rate": 0.00011534548516546886, "loss": 0.6168075561523437, "step": 268990 }, { "epoch": 1.5989918623797041, "grad_norm": 1.7697888612747192, "learning_rate": 0.0001153392713725815, "loss": 0.5784279346466065, "step": 269000 }, { "epoch": 1.5990513044563723, "grad_norm": 1.4082392454147339, "learning_rate": 0.0001153330575541528, "loss": 0.49689064025878904, "step": 269010 }, { "epoch": 1.5991107465330407, "grad_norm": 1.4520665407180786, "learning_rate": 0.00011532684371021247, "loss": 0.572331714630127, "step": 269020 }, { "epoch": 1.5991701886097092, "grad_norm": 1.6258759498596191, "learning_rate": 0.00011532062984079028, "loss": 0.5889621257781983, "step": 269030 }, { "epoch": 1.5992296306863776, "grad_norm": 1.248559832572937, "learning_rate": 0.00011531441594591596, "loss": 0.5302322387695313, "step": 269040 }, { "epoch": 1.599289072763046, "grad_norm": 1.5186283588409424, "learning_rate": 0.0001153082020256192, "loss": 0.5749810218811036, "step": 269050 }, { "epoch": 1.5993485148397144, "grad_norm": 1.858012080192566, "learning_rate": 0.00011530198807992971, "loss": 0.5749472618103028, "step": 269060 }, { "epoch": 1.5994079569163828, "grad_norm": 1.3325313329696655, "learning_rate": 0.00011529577410887726, "loss": 0.5776088237762451, "step": 269070 }, { "epoch": 1.5994673989930512, "grad_norm": 1.242577075958252, "learning_rate": 0.00011528956011249157, "loss": 0.6101273536682129, "step": 269080 }, { "epoch": 1.5995268410697197, "grad_norm": 1.6388258934020996, "learning_rate": 0.00011528334609080231, "loss": 0.6069775581359863, "step": 269090 }, { "epoch": 1.599586283146388, "grad_norm": 1.7752310037612915, "learning_rate": 0.0001152771320438393, "loss": 0.5883847236633301, "step": 269100 }, { "epoch": 1.5996457252230565, "grad_norm": 1.440637230873108, "learning_rate": 0.00011527091797163219, "loss": 0.5741712093353272, "step": 269110 }, { "epoch": 1.599705167299725, "grad_norm": 1.6233398914337158, "learning_rate": 0.00011526470387421071, "loss": 0.5565547943115234, "step": 269120 }, { "epoch": 1.5997646093763933, "grad_norm": 1.2897229194641113, "learning_rate": 0.00011525848975160465, "loss": 0.5555850028991699, "step": 269130 }, { "epoch": 1.5998240514530617, "grad_norm": 1.2918466329574585, "learning_rate": 0.00011525227560384369, "loss": 0.5592310905456543, "step": 269140 }, { "epoch": 1.59988349352973, "grad_norm": 1.1975302696228027, "learning_rate": 0.00011524606143095753, "loss": 0.6094844341278076, "step": 269150 }, { "epoch": 1.5999429356063983, "grad_norm": 1.9708024263381958, "learning_rate": 0.00011523984723297594, "loss": 0.5636528968811035, "step": 269160 }, { "epoch": 1.6000023776830667, "grad_norm": 1.6030937433242798, "learning_rate": 0.00011523363300992864, "loss": 0.5773256301879883, "step": 269170 }, { "epoch": 1.6000618197597352, "grad_norm": 1.688144326210022, "learning_rate": 0.00011522741876184535, "loss": 0.6389265060424805, "step": 269180 }, { "epoch": 1.6001212618364034, "grad_norm": 1.431348204612732, "learning_rate": 0.00011522120448875578, "loss": 0.562544298171997, "step": 269190 }, { "epoch": 1.6001807039130718, "grad_norm": 1.810767412185669, "learning_rate": 0.00011521499019068968, "loss": 0.5762789726257325, "step": 269200 }, { "epoch": 1.6002401459897402, "grad_norm": 1.4590065479278564, "learning_rate": 0.0001152087758676768, "loss": 0.5610620498657226, "step": 269210 }, { "epoch": 1.6002995880664086, "grad_norm": 1.5492440462112427, "learning_rate": 0.0001152025615197468, "loss": 0.6834197044372559, "step": 269220 }, { "epoch": 1.600359030143077, "grad_norm": 1.7712959051132202, "learning_rate": 0.00011519634714692949, "loss": 0.5524739265441895, "step": 269230 }, { "epoch": 1.6004184722197454, "grad_norm": 1.5123616456985474, "learning_rate": 0.0001151901327492545, "loss": 0.5624680519104004, "step": 269240 }, { "epoch": 1.6004779142964138, "grad_norm": 1.7247096300125122, "learning_rate": 0.00011518391832675162, "loss": 0.5525239944458008, "step": 269250 }, { "epoch": 1.6005373563730823, "grad_norm": 1.4414680004119873, "learning_rate": 0.00011517770387945061, "loss": 0.5792653083801269, "step": 269260 }, { "epoch": 1.6005967984497507, "grad_norm": 1.5353260040283203, "learning_rate": 0.00011517148940738112, "loss": 0.6235520362854003, "step": 269270 }, { "epoch": 1.600656240526419, "grad_norm": 1.2306195497512817, "learning_rate": 0.00011516527491057294, "loss": 0.5566857814788818, "step": 269280 }, { "epoch": 1.6007156826030875, "grad_norm": 1.340054988861084, "learning_rate": 0.00011515906038905575, "loss": 0.5665837287902832, "step": 269290 }, { "epoch": 1.600775124679756, "grad_norm": 1.3914796113967896, "learning_rate": 0.00011515284584285931, "loss": 0.5449188232421875, "step": 269300 }, { "epoch": 1.6008345667564243, "grad_norm": 1.5077203512191772, "learning_rate": 0.00011514663127201333, "loss": 0.5768970489501953, "step": 269310 }, { "epoch": 1.6008940088330927, "grad_norm": 1.5284712314605713, "learning_rate": 0.00011514041667654758, "loss": 0.5732364177703857, "step": 269320 }, { "epoch": 1.600953450909761, "grad_norm": 1.421959638595581, "learning_rate": 0.00011513420205649171, "loss": 0.6124500274658203, "step": 269330 }, { "epoch": 1.6010128929864293, "grad_norm": 1.3810962438583374, "learning_rate": 0.00011512798741187554, "loss": 0.574207878112793, "step": 269340 }, { "epoch": 1.6010723350630978, "grad_norm": 1.2370374202728271, "learning_rate": 0.00011512177274272873, "loss": 0.5577650547027588, "step": 269350 }, { "epoch": 1.6011317771397662, "grad_norm": 1.7000553607940674, "learning_rate": 0.00011511555804908102, "loss": 0.57032151222229, "step": 269360 }, { "epoch": 1.6011912192164346, "grad_norm": 1.2599633932113647, "learning_rate": 0.00011510934333096217, "loss": 0.5805363178253173, "step": 269370 }, { "epoch": 1.6012506612931028, "grad_norm": 1.8249095678329468, "learning_rate": 0.00011510312858840189, "loss": 0.5614410877227783, "step": 269380 }, { "epoch": 1.6013101033697712, "grad_norm": 1.3520210981369019, "learning_rate": 0.00011509691382142991, "loss": 0.6007068634033204, "step": 269390 }, { "epoch": 1.6013695454464396, "grad_norm": 1.6303842067718506, "learning_rate": 0.00011509069903007594, "loss": 0.5729524612426757, "step": 269400 }, { "epoch": 1.601428987523108, "grad_norm": 1.3540050983428955, "learning_rate": 0.0001150844842143698, "loss": 0.5586453914642334, "step": 269410 }, { "epoch": 1.6014884295997764, "grad_norm": 1.6453965902328491, "learning_rate": 0.00011507826937434107, "loss": 0.5569047451019287, "step": 269420 }, { "epoch": 1.6015478716764449, "grad_norm": 1.3493492603302002, "learning_rate": 0.00011507205451001958, "loss": 0.6161613464355469, "step": 269430 }, { "epoch": 1.6016073137531133, "grad_norm": 1.3800657987594604, "learning_rate": 0.00011506583962143506, "loss": 0.5394795417785645, "step": 269440 }, { "epoch": 1.6016667558297817, "grad_norm": 1.3395614624023438, "learning_rate": 0.0001150596247086172, "loss": 0.5550614356994629, "step": 269450 }, { "epoch": 1.60172619790645, "grad_norm": 1.2607463598251343, "learning_rate": 0.00011505340977159574, "loss": 0.5453434944152832, "step": 269460 }, { "epoch": 1.6017856399831185, "grad_norm": 1.2694755792617798, "learning_rate": 0.00011504719481040045, "loss": 0.6025725364685058, "step": 269470 }, { "epoch": 1.601845082059787, "grad_norm": 1.5585306882858276, "learning_rate": 0.000115040979825061, "loss": 0.5548473358154297, "step": 269480 }, { "epoch": 1.6019045241364553, "grad_norm": 1.5022499561309814, "learning_rate": 0.00011503476481560718, "loss": 0.5839178562164307, "step": 269490 }, { "epoch": 1.6019639662131238, "grad_norm": 1.3387281894683838, "learning_rate": 0.00011502854978206868, "loss": 0.570280647277832, "step": 269500 }, { "epoch": 1.6020234082897922, "grad_norm": 1.6811034679412842, "learning_rate": 0.00011502233472447521, "loss": 0.5982022285461426, "step": 269510 }, { "epoch": 1.6020828503664604, "grad_norm": 1.6267530918121338, "learning_rate": 0.00011501611964285657, "loss": 0.5792406082153321, "step": 269520 }, { "epoch": 1.6021422924431288, "grad_norm": 1.1586233377456665, "learning_rate": 0.00011500990453724243, "loss": 0.5167627334594727, "step": 269530 }, { "epoch": 1.6022017345197972, "grad_norm": 1.705630898475647, "learning_rate": 0.00011500368940766257, "loss": 0.5631430625915528, "step": 269540 }, { "epoch": 1.6022611765964656, "grad_norm": 1.6709659099578857, "learning_rate": 0.00011499747425414667, "loss": 0.567120361328125, "step": 269550 }, { "epoch": 1.6023206186731338, "grad_norm": 1.7241238355636597, "learning_rate": 0.00011499125907672448, "loss": 0.5374680995941162, "step": 269560 }, { "epoch": 1.6023800607498022, "grad_norm": 1.3585412502288818, "learning_rate": 0.00011498504387542576, "loss": 0.5847264289855957, "step": 269570 }, { "epoch": 1.6024395028264706, "grad_norm": 1.350997805595398, "learning_rate": 0.0001149788286502802, "loss": 0.5731851577758789, "step": 269580 }, { "epoch": 1.602498944903139, "grad_norm": 1.8226473331451416, "learning_rate": 0.00011497261340131757, "loss": 0.5348333358764649, "step": 269590 }, { "epoch": 1.6025583869798075, "grad_norm": 1.5811384916305542, "learning_rate": 0.00011496639812856757, "loss": 0.6244115829467773, "step": 269600 }, { "epoch": 1.6026178290564759, "grad_norm": 1.338624358177185, "learning_rate": 0.00011496018283205994, "loss": 0.5269283294677735, "step": 269610 }, { "epoch": 1.6026772711331443, "grad_norm": 1.4717179536819458, "learning_rate": 0.00011495396751182444, "loss": 0.6231392860412598, "step": 269620 }, { "epoch": 1.6027367132098127, "grad_norm": 1.3779878616333008, "learning_rate": 0.00011494775216789078, "loss": 0.5501879692077637, "step": 269630 }, { "epoch": 1.6027961552864811, "grad_norm": 1.7561750411987305, "learning_rate": 0.00011494153680028865, "loss": 0.5387844562530517, "step": 269640 }, { "epoch": 1.6028555973631495, "grad_norm": 1.542478322982788, "learning_rate": 0.00011493532140904786, "loss": 0.5919478416442872, "step": 269650 }, { "epoch": 1.602915039439818, "grad_norm": 1.732863187789917, "learning_rate": 0.00011492910599419809, "loss": 0.6490240097045898, "step": 269660 }, { "epoch": 1.6029744815164864, "grad_norm": 1.3285492658615112, "learning_rate": 0.00011492289055576908, "loss": 0.5590433120727539, "step": 269670 }, { "epoch": 1.6030339235931548, "grad_norm": 1.3182101249694824, "learning_rate": 0.00011491667509379058, "loss": 0.6127581596374512, "step": 269680 }, { "epoch": 1.6030933656698232, "grad_norm": 2.0000290870666504, "learning_rate": 0.00011491045960829232, "loss": 0.5378500461578369, "step": 269690 }, { "epoch": 1.6031528077464914, "grad_norm": 1.3219525814056396, "learning_rate": 0.00011490424409930403, "loss": 0.6094864845275879, "step": 269700 }, { "epoch": 1.6032122498231598, "grad_norm": 1.6705307960510254, "learning_rate": 0.00011489802856685543, "loss": 0.5814327716827392, "step": 269710 }, { "epoch": 1.6032716918998282, "grad_norm": 1.58998441696167, "learning_rate": 0.00011489181301097627, "loss": 0.571689224243164, "step": 269720 }, { "epoch": 1.6033311339764966, "grad_norm": 1.4611235857009888, "learning_rate": 0.00011488559743169625, "loss": 0.5300336837768554, "step": 269730 }, { "epoch": 1.603390576053165, "grad_norm": 1.2674734592437744, "learning_rate": 0.00011487938182904514, "loss": 0.5555392265319824, "step": 269740 }, { "epoch": 1.6034500181298332, "grad_norm": 1.6575387716293335, "learning_rate": 0.00011487316620305269, "loss": 0.529479694366455, "step": 269750 }, { "epoch": 1.6035094602065016, "grad_norm": 1.538326621055603, "learning_rate": 0.00011486695055374857, "loss": 0.5778241634368897, "step": 269760 }, { "epoch": 1.60356890228317, "grad_norm": 1.436274528503418, "learning_rate": 0.00011486073488116254, "loss": 0.6091192722320556, "step": 269770 }, { "epoch": 1.6036283443598385, "grad_norm": 1.3782973289489746, "learning_rate": 0.0001148545191853244, "loss": 0.5829973697662354, "step": 269780 }, { "epoch": 1.603687786436507, "grad_norm": 1.5271470546722412, "learning_rate": 0.00011484830346626376, "loss": 0.618776798248291, "step": 269790 }, { "epoch": 1.6037472285131753, "grad_norm": 1.4104325771331787, "learning_rate": 0.00011484208772401047, "loss": 0.5541925430297852, "step": 269800 }, { "epoch": 1.6038066705898437, "grad_norm": 1.4097920656204224, "learning_rate": 0.0001148358719585942, "loss": 0.549021577835083, "step": 269810 }, { "epoch": 1.6038661126665121, "grad_norm": 1.7026464939117432, "learning_rate": 0.00011482965617004466, "loss": 0.528325366973877, "step": 269820 }, { "epoch": 1.6039255547431805, "grad_norm": 1.1989712715148926, "learning_rate": 0.00011482344035839167, "loss": 0.5755301475524902, "step": 269830 }, { "epoch": 1.603984996819849, "grad_norm": 1.397814393043518, "learning_rate": 0.00011481722452366493, "loss": 0.5379285335540771, "step": 269840 }, { "epoch": 1.6040444388965174, "grad_norm": 1.8693790435791016, "learning_rate": 0.00011481100866589414, "loss": 0.634767723083496, "step": 269850 }, { "epoch": 1.6041038809731858, "grad_norm": 1.476995825767517, "learning_rate": 0.00011480479278510903, "loss": 0.605419111251831, "step": 269860 }, { "epoch": 1.6041633230498542, "grad_norm": 1.217883586883545, "learning_rate": 0.00011479857688133942, "loss": 0.6215585231781006, "step": 269870 }, { "epoch": 1.6042227651265226, "grad_norm": 1.4269654750823975, "learning_rate": 0.00011479236095461495, "loss": 0.6005020141601562, "step": 269880 }, { "epoch": 1.6042822072031908, "grad_norm": 1.4444736242294312, "learning_rate": 0.00011478614500496536, "loss": 0.5833436489105225, "step": 269890 }, { "epoch": 1.6043416492798592, "grad_norm": 1.90224289894104, "learning_rate": 0.00011477992903242046, "loss": 0.6457673072814941, "step": 269900 }, { "epoch": 1.6044010913565276, "grad_norm": 1.320420265197754, "learning_rate": 0.00011477371303700995, "loss": 0.5765951633453369, "step": 269910 }, { "epoch": 1.604460533433196, "grad_norm": 1.2393531799316406, "learning_rate": 0.0001147674970187635, "loss": 0.5477367401123047, "step": 269920 }, { "epoch": 1.6045199755098642, "grad_norm": 1.316045880317688, "learning_rate": 0.00011476128097771097, "loss": 0.5225183963775635, "step": 269930 }, { "epoch": 1.6045794175865327, "grad_norm": 1.3067405223846436, "learning_rate": 0.00011475506491388199, "loss": 0.5390902519226074, "step": 269940 }, { "epoch": 1.604638859663201, "grad_norm": 1.6467008590698242, "learning_rate": 0.00011474884882730634, "loss": 0.6118287563323974, "step": 269950 }, { "epoch": 1.6046983017398695, "grad_norm": 1.5715211629867554, "learning_rate": 0.00011474263271801377, "loss": 0.6083385467529296, "step": 269960 }, { "epoch": 1.604757743816538, "grad_norm": 1.6102147102355957, "learning_rate": 0.00011473641658603397, "loss": 0.6186636447906494, "step": 269970 }, { "epoch": 1.6048171858932063, "grad_norm": 1.865626335144043, "learning_rate": 0.00011473020043139671, "loss": 0.6205108165740967, "step": 269980 }, { "epoch": 1.6048766279698747, "grad_norm": 1.4041396379470825, "learning_rate": 0.00011472398425413171, "loss": 0.5459760665893555, "step": 269990 }, { "epoch": 1.6049360700465432, "grad_norm": 1.5050346851348877, "learning_rate": 0.00011471776805426872, "loss": 0.559116268157959, "step": 270000 }, { "epoch": 1.6049955121232116, "grad_norm": 1.6112909317016602, "learning_rate": 0.00011471155183183746, "loss": 0.5481141090393067, "step": 270010 }, { "epoch": 1.60505495419988, "grad_norm": 1.4608726501464844, "learning_rate": 0.0001147053355868677, "loss": 0.5797628879547119, "step": 270020 }, { "epoch": 1.6051143962765484, "grad_norm": 1.7639552354812622, "learning_rate": 0.00011469911931938912, "loss": 0.5896395683288574, "step": 270030 }, { "epoch": 1.6051738383532168, "grad_norm": 1.5759471654891968, "learning_rate": 0.0001146929030294315, "loss": 0.548943567276001, "step": 270040 }, { "epoch": 1.6052332804298852, "grad_norm": 1.4123499393463135, "learning_rate": 0.00011468668671702459, "loss": 0.5603384494781494, "step": 270050 }, { "epoch": 1.6052927225065536, "grad_norm": 1.373855710029602, "learning_rate": 0.0001146804703821981, "loss": 0.5955221652984619, "step": 270060 }, { "epoch": 1.6053521645832218, "grad_norm": 1.5402443408966064, "learning_rate": 0.00011467425402498173, "loss": 0.4919292449951172, "step": 270070 }, { "epoch": 1.6054116066598902, "grad_norm": 1.6391364336013794, "learning_rate": 0.00011466803764540526, "loss": 0.5729701519012451, "step": 270080 }, { "epoch": 1.6054710487365587, "grad_norm": 1.0681270360946655, "learning_rate": 0.00011466182124349845, "loss": 0.6143605232238769, "step": 270090 }, { "epoch": 1.605530490813227, "grad_norm": 1.6819640398025513, "learning_rate": 0.00011465560481929101, "loss": 0.5425048828125, "step": 270100 }, { "epoch": 1.6055899328898955, "grad_norm": 1.7651731967926025, "learning_rate": 0.00011464938837281265, "loss": 0.5758303642272949, "step": 270110 }, { "epoch": 1.6056493749665637, "grad_norm": 1.4209139347076416, "learning_rate": 0.00011464317190409317, "loss": 0.5970374584197998, "step": 270120 }, { "epoch": 1.605708817043232, "grad_norm": 1.5151045322418213, "learning_rate": 0.00011463695541316225, "loss": 0.5735198974609375, "step": 270130 }, { "epoch": 1.6057682591199005, "grad_norm": 1.6449005603790283, "learning_rate": 0.00011463073890004964, "loss": 0.5654293537139893, "step": 270140 }, { "epoch": 1.605827701196569, "grad_norm": 1.5637625455856323, "learning_rate": 0.00011462452236478514, "loss": 0.5316967487335205, "step": 270150 }, { "epoch": 1.6058871432732373, "grad_norm": 1.779601812362671, "learning_rate": 0.00011461830580739839, "loss": 0.5759997844696045, "step": 270160 }, { "epoch": 1.6059465853499058, "grad_norm": 1.7606977224349976, "learning_rate": 0.00011461208922791917, "loss": 0.6088344573974609, "step": 270170 }, { "epoch": 1.6060060274265742, "grad_norm": 1.8125492334365845, "learning_rate": 0.00011460587262637725, "loss": 0.5645495414733886, "step": 270180 }, { "epoch": 1.6060654695032426, "grad_norm": 1.4266775846481323, "learning_rate": 0.00011459965600280234, "loss": 0.5716044425964355, "step": 270190 }, { "epoch": 1.606124911579911, "grad_norm": 1.4048889875411987, "learning_rate": 0.00011459343935722418, "loss": 0.6048372268676758, "step": 270200 }, { "epoch": 1.6061843536565794, "grad_norm": 1.4396092891693115, "learning_rate": 0.00011458722268967251, "loss": 0.5804977416992188, "step": 270210 }, { "epoch": 1.6062437957332478, "grad_norm": 1.3744244575500488, "learning_rate": 0.00011458100600017705, "loss": 0.5602452278137207, "step": 270220 }, { "epoch": 1.6063032378099162, "grad_norm": 1.3868852853775024, "learning_rate": 0.00011457478928876753, "loss": 0.6138092041015625, "step": 270230 }, { "epoch": 1.6063626798865847, "grad_norm": 1.5080217123031616, "learning_rate": 0.00011456857255547378, "loss": 0.553803825378418, "step": 270240 }, { "epoch": 1.606422121963253, "grad_norm": 1.282784104347229, "learning_rate": 0.00011456235580032539, "loss": 0.5358301162719726, "step": 270250 }, { "epoch": 1.6064815640399213, "grad_norm": 1.2523581981658936, "learning_rate": 0.00011455613902335223, "loss": 0.6138456344604493, "step": 270260 }, { "epoch": 1.6065410061165897, "grad_norm": 1.6204323768615723, "learning_rate": 0.00011454992222458399, "loss": 0.5566327095031738, "step": 270270 }, { "epoch": 1.606600448193258, "grad_norm": 1.5831191539764404, "learning_rate": 0.00011454370540405039, "loss": 0.5121172904968262, "step": 270280 }, { "epoch": 1.6066598902699265, "grad_norm": 1.7140358686447144, "learning_rate": 0.00011453748856178122, "loss": 0.5522426128387451, "step": 270290 }, { "epoch": 1.6067193323465947, "grad_norm": 1.6490402221679688, "learning_rate": 0.00011453127169780617, "loss": 0.591773509979248, "step": 270300 }, { "epoch": 1.6067787744232631, "grad_norm": 1.773786187171936, "learning_rate": 0.00011452505481215497, "loss": 0.4968686580657959, "step": 270310 }, { "epoch": 1.6068382164999315, "grad_norm": 1.769067406654358, "learning_rate": 0.00011451883790485743, "loss": 0.6603592872619629, "step": 270320 }, { "epoch": 1.6068976585766, "grad_norm": 1.403012752532959, "learning_rate": 0.00011451262097594322, "loss": 0.5890486717224122, "step": 270330 }, { "epoch": 1.6069571006532684, "grad_norm": 1.5567317008972168, "learning_rate": 0.00011450640402544212, "loss": 0.5742431163787842, "step": 270340 }, { "epoch": 1.6070165427299368, "grad_norm": 1.5222629308700562, "learning_rate": 0.00011450018705338383, "loss": 0.5330592155456543, "step": 270350 }, { "epoch": 1.6070759848066052, "grad_norm": 1.3615398406982422, "learning_rate": 0.00011449397005979816, "loss": 0.5835416793823243, "step": 270360 }, { "epoch": 1.6071354268832736, "grad_norm": 1.4455751180648804, "learning_rate": 0.00011448775304471478, "loss": 0.5578341960906983, "step": 270370 }, { "epoch": 1.607194868959942, "grad_norm": 1.5737401247024536, "learning_rate": 0.00011448153600816345, "loss": 0.555732250213623, "step": 270380 }, { "epoch": 1.6072543110366104, "grad_norm": 1.4280176162719727, "learning_rate": 0.00011447531895017392, "loss": 0.5818925857543945, "step": 270390 }, { "epoch": 1.6073137531132788, "grad_norm": 1.2385036945343018, "learning_rate": 0.00011446910187077595, "loss": 0.5880783557891845, "step": 270400 }, { "epoch": 1.6073731951899473, "grad_norm": 1.1375350952148438, "learning_rate": 0.0001144628847699992, "loss": 0.5722044944763184, "step": 270410 }, { "epoch": 1.6074326372666157, "grad_norm": 1.2232754230499268, "learning_rate": 0.0001144566676478735, "loss": 0.6011706352233886, "step": 270420 }, { "epoch": 1.607492079343284, "grad_norm": 1.8133777379989624, "learning_rate": 0.00011445045050442859, "loss": 0.5830197334289551, "step": 270430 }, { "epoch": 1.6075515214199523, "grad_norm": 1.4823145866394043, "learning_rate": 0.00011444423333969417, "loss": 0.5924114227294922, "step": 270440 }, { "epoch": 1.6076109634966207, "grad_norm": 1.6459710597991943, "learning_rate": 0.00011443801615369994, "loss": 0.6045323371887207, "step": 270450 }, { "epoch": 1.607670405573289, "grad_norm": 1.2033061981201172, "learning_rate": 0.00011443179894647574, "loss": 0.611841869354248, "step": 270460 }, { "epoch": 1.6077298476499575, "grad_norm": 1.857446312904358, "learning_rate": 0.00011442558171805124, "loss": 0.5738888740539551, "step": 270470 }, { "epoch": 1.607789289726626, "grad_norm": 1.4634830951690674, "learning_rate": 0.0001144193644684562, "loss": 0.5603621482849122, "step": 270480 }, { "epoch": 1.6078487318032941, "grad_norm": 1.7159678936004639, "learning_rate": 0.00011441314719772038, "loss": 0.585193681716919, "step": 270490 }, { "epoch": 1.6079081738799625, "grad_norm": 1.68809974193573, "learning_rate": 0.0001144069299058735, "loss": 0.4791684150695801, "step": 270500 }, { "epoch": 1.607967615956631, "grad_norm": 1.7352319955825806, "learning_rate": 0.00011440071259294532, "loss": 0.5755430221557617, "step": 270510 }, { "epoch": 1.6080270580332994, "grad_norm": 1.4680849313735962, "learning_rate": 0.00011439449525896555, "loss": 0.5955591201782227, "step": 270520 }, { "epoch": 1.6080865001099678, "grad_norm": 1.380020022392273, "learning_rate": 0.00011438827790396396, "loss": 0.5547068595886231, "step": 270530 }, { "epoch": 1.6081459421866362, "grad_norm": 1.7101669311523438, "learning_rate": 0.00011438206052797025, "loss": 0.5564581871032714, "step": 270540 }, { "epoch": 1.6082053842633046, "grad_norm": 1.317746877670288, "learning_rate": 0.00011437584313101425, "loss": 0.5670226097106934, "step": 270550 }, { "epoch": 1.608264826339973, "grad_norm": 1.471566915512085, "learning_rate": 0.00011436962571312562, "loss": 0.5678060531616211, "step": 270560 }, { "epoch": 1.6083242684166414, "grad_norm": 1.6268844604492188, "learning_rate": 0.00011436340827433414, "loss": 0.6240436553955078, "step": 270570 }, { "epoch": 1.6083837104933099, "grad_norm": 1.451547622680664, "learning_rate": 0.00011435719081466953, "loss": 0.5491673469543457, "step": 270580 }, { "epoch": 1.6084431525699783, "grad_norm": 1.3046627044677734, "learning_rate": 0.00011435097333416153, "loss": 0.5843815803527832, "step": 270590 }, { "epoch": 1.6085025946466467, "grad_norm": 1.2211661338806152, "learning_rate": 0.00011434475583283992, "loss": 0.6156014442443848, "step": 270600 }, { "epoch": 1.608562036723315, "grad_norm": 1.2569018602371216, "learning_rate": 0.00011433853831073442, "loss": 0.6312214851379394, "step": 270610 }, { "epoch": 1.6086214787999835, "grad_norm": 1.3460954427719116, "learning_rate": 0.00011433232076787472, "loss": 0.565522575378418, "step": 270620 }, { "epoch": 1.6086809208766517, "grad_norm": 1.7895604372024536, "learning_rate": 0.00011432610320429067, "loss": 0.5808531761169433, "step": 270630 }, { "epoch": 1.6087403629533201, "grad_norm": 1.753920078277588, "learning_rate": 0.00011431988562001195, "loss": 0.6077986240386963, "step": 270640 }, { "epoch": 1.6087998050299885, "grad_norm": 1.5859768390655518, "learning_rate": 0.00011431366801506828, "loss": 0.6137810707092285, "step": 270650 }, { "epoch": 1.608859247106657, "grad_norm": 1.5885435342788696, "learning_rate": 0.00011430745038948945, "loss": 0.5945133209228516, "step": 270660 }, { "epoch": 1.6089186891833251, "grad_norm": 1.6520940065383911, "learning_rate": 0.0001143012327433052, "loss": 0.6226099014282227, "step": 270670 }, { "epoch": 1.6089781312599936, "grad_norm": 1.3518463373184204, "learning_rate": 0.00011429501507654523, "loss": 0.6068887710571289, "step": 270680 }, { "epoch": 1.609037573336662, "grad_norm": 1.0717206001281738, "learning_rate": 0.00011428879738923933, "loss": 0.5614695072174072, "step": 270690 }, { "epoch": 1.6090970154133304, "grad_norm": 1.588219165802002, "learning_rate": 0.00011428257968141722, "loss": 0.5453633785247802, "step": 270700 }, { "epoch": 1.6091564574899988, "grad_norm": 1.5855563879013062, "learning_rate": 0.00011427636195310864, "loss": 0.5574921607971192, "step": 270710 }, { "epoch": 1.6092158995666672, "grad_norm": 1.3408448696136475, "learning_rate": 0.00011427014420434332, "loss": 0.592856502532959, "step": 270720 }, { "epoch": 1.6092753416433356, "grad_norm": 1.447869062423706, "learning_rate": 0.00011426392643515109, "loss": 0.6205717563629151, "step": 270730 }, { "epoch": 1.609334783720004, "grad_norm": 1.1448986530303955, "learning_rate": 0.0001142577086455616, "loss": 0.5830079078674316, "step": 270740 }, { "epoch": 1.6093942257966725, "grad_norm": 1.6064528226852417, "learning_rate": 0.0001142514908356046, "loss": 0.5917245864868164, "step": 270750 }, { "epoch": 1.6094536678733409, "grad_norm": 1.594738483428955, "learning_rate": 0.00011424527300530987, "loss": 0.5580780029296875, "step": 270760 }, { "epoch": 1.6095131099500093, "grad_norm": 2.0142271518707275, "learning_rate": 0.00011423905515470714, "loss": 0.5606914520263672, "step": 270770 }, { "epoch": 1.6095725520266777, "grad_norm": 1.4014455080032349, "learning_rate": 0.00011423283728382616, "loss": 0.5723272323608398, "step": 270780 }, { "epoch": 1.6096319941033461, "grad_norm": 1.0674842596054077, "learning_rate": 0.00011422661939269669, "loss": 0.49007201194763184, "step": 270790 }, { "epoch": 1.6096914361800145, "grad_norm": 1.3467679023742676, "learning_rate": 0.00011422040148134843, "loss": 0.5531012535095214, "step": 270800 }, { "epoch": 1.6097508782566827, "grad_norm": 1.3805978298187256, "learning_rate": 0.00011421418354981115, "loss": 0.6076869487762451, "step": 270810 }, { "epoch": 1.6098103203333511, "grad_norm": 1.728714942932129, "learning_rate": 0.0001142079655981146, "loss": 0.5829255104064941, "step": 270820 }, { "epoch": 1.6098697624100196, "grad_norm": 1.6123130321502686, "learning_rate": 0.0001142017476262885, "loss": 0.6169182777404785, "step": 270830 }, { "epoch": 1.609929204486688, "grad_norm": 1.2063757181167603, "learning_rate": 0.00011419552963436261, "loss": 0.5128925800323486, "step": 270840 }, { "epoch": 1.6099886465633564, "grad_norm": 1.5767459869384766, "learning_rate": 0.0001141893116223667, "loss": 0.5908652782440186, "step": 270850 }, { "epoch": 1.6100480886400246, "grad_norm": 1.2987934350967407, "learning_rate": 0.0001141830935903305, "loss": 0.5675576210021973, "step": 270860 }, { "epoch": 1.610107530716693, "grad_norm": 1.335599660873413, "learning_rate": 0.00011417687553828372, "loss": 0.5448006629943848, "step": 270870 }, { "epoch": 1.6101669727933614, "grad_norm": 1.2225745916366577, "learning_rate": 0.00011417065746625615, "loss": 0.5793987274169922, "step": 270880 }, { "epoch": 1.6102264148700298, "grad_norm": 1.5760154724121094, "learning_rate": 0.00011416443937427752, "loss": 0.5950209617614746, "step": 270890 }, { "epoch": 1.6102858569466982, "grad_norm": 1.100799322128296, "learning_rate": 0.00011415822126237753, "loss": 0.5579095840454101, "step": 270900 }, { "epoch": 1.6103452990233666, "grad_norm": 1.192840814590454, "learning_rate": 0.00011415200313058606, "loss": 0.6145295143127442, "step": 270910 }, { "epoch": 1.610404741100035, "grad_norm": 1.7356966733932495, "learning_rate": 0.00011414578497893268, "loss": 0.5668241500854492, "step": 270920 }, { "epoch": 1.6104641831767035, "grad_norm": 1.6739201545715332, "learning_rate": 0.00011413956680744726, "loss": 0.552849292755127, "step": 270930 }, { "epoch": 1.610523625253372, "grad_norm": 1.05823814868927, "learning_rate": 0.0001141333486161595, "loss": 0.5819063186645508, "step": 270940 }, { "epoch": 1.6105830673300403, "grad_norm": 1.164890170097351, "learning_rate": 0.00011412713040509913, "loss": 0.5794227600097657, "step": 270950 }, { "epoch": 1.6106425094067087, "grad_norm": 2.0481069087982178, "learning_rate": 0.00011412091217429595, "loss": 0.6157933712005615, "step": 270960 }, { "epoch": 1.6107019514833771, "grad_norm": 1.3272454738616943, "learning_rate": 0.00011411469392377963, "loss": 0.5269901275634765, "step": 270970 }, { "epoch": 1.6107613935600456, "grad_norm": 1.2636643648147583, "learning_rate": 0.00011410847565357999, "loss": 0.5438992500305175, "step": 270980 }, { "epoch": 1.610820835636714, "grad_norm": 1.632466435432434, "learning_rate": 0.00011410225736372672, "loss": 0.5938988208770752, "step": 270990 }, { "epoch": 1.6108802777133822, "grad_norm": 2.1698262691497803, "learning_rate": 0.00011409603905424962, "loss": 0.5935041904449463, "step": 271000 }, { "epoch": 1.6109397197900506, "grad_norm": 2.0287938117980957, "learning_rate": 0.00011408982072517842, "loss": 0.5479836463928223, "step": 271010 }, { "epoch": 1.610999161866719, "grad_norm": 1.7182960510253906, "learning_rate": 0.00011408360237654284, "loss": 0.588529109954834, "step": 271020 }, { "epoch": 1.6110586039433874, "grad_norm": 1.8383530378341675, "learning_rate": 0.0001140773840083726, "loss": 0.6318660736083984, "step": 271030 }, { "epoch": 1.6111180460200556, "grad_norm": 1.361636757850647, "learning_rate": 0.00011407116562069754, "loss": 0.5514170169830322, "step": 271040 }, { "epoch": 1.611177488096724, "grad_norm": 1.5054548978805542, "learning_rate": 0.0001140649472135473, "loss": 0.5627903938293457, "step": 271050 }, { "epoch": 1.6112369301733924, "grad_norm": 1.435912013053894, "learning_rate": 0.00011405872878695174, "loss": 0.5301738739013672, "step": 271060 }, { "epoch": 1.6112963722500608, "grad_norm": 1.7433115243911743, "learning_rate": 0.00011405251034094053, "loss": 0.5678915023803711, "step": 271070 }, { "epoch": 1.6113558143267293, "grad_norm": 1.735219955444336, "learning_rate": 0.00011404629187554341, "loss": 0.5578643798828125, "step": 271080 }, { "epoch": 1.6114152564033977, "grad_norm": 1.5449694395065308, "learning_rate": 0.00011404007339079019, "loss": 0.6090594291687011, "step": 271090 }, { "epoch": 1.611474698480066, "grad_norm": 1.2635115385055542, "learning_rate": 0.00011403385488671055, "loss": 0.6655406475067138, "step": 271100 }, { "epoch": 1.6115341405567345, "grad_norm": 1.5361862182617188, "learning_rate": 0.00011402763636333429, "loss": 0.5904871940612793, "step": 271110 }, { "epoch": 1.611593582633403, "grad_norm": 1.264502763748169, "learning_rate": 0.00011402141782069109, "loss": 0.5467512607574463, "step": 271120 }, { "epoch": 1.6116530247100713, "grad_norm": 1.4098128080368042, "learning_rate": 0.00011401519925881078, "loss": 0.5320018291473388, "step": 271130 }, { "epoch": 1.6117124667867397, "grad_norm": 1.4011298418045044, "learning_rate": 0.00011400898067772308, "loss": 0.5351180553436279, "step": 271140 }, { "epoch": 1.6117719088634082, "grad_norm": 1.476401448249817, "learning_rate": 0.00011400276207745768, "loss": 0.5558317184448243, "step": 271150 }, { "epoch": 1.6118313509400766, "grad_norm": 1.2697882652282715, "learning_rate": 0.00011399654345804442, "loss": 0.5549699306488037, "step": 271160 }, { "epoch": 1.611890793016745, "grad_norm": 1.4306128025054932, "learning_rate": 0.00011399032481951297, "loss": 0.6337984085083008, "step": 271170 }, { "epoch": 1.6119502350934132, "grad_norm": 1.0807054042816162, "learning_rate": 0.0001139841061618931, "loss": 0.5520480155944825, "step": 271180 }, { "epoch": 1.6120096771700816, "grad_norm": 1.786177158355713, "learning_rate": 0.00011397788748521461, "loss": 0.6036481857299805, "step": 271190 }, { "epoch": 1.61206911924675, "grad_norm": 1.2980353832244873, "learning_rate": 0.0001139716687895072, "loss": 0.5868451118469238, "step": 271200 }, { "epoch": 1.6121285613234184, "grad_norm": 1.7190253734588623, "learning_rate": 0.0001139654500748006, "loss": 0.6308298110961914, "step": 271210 }, { "epoch": 1.6121880034000868, "grad_norm": 2.667419195175171, "learning_rate": 0.00011395923134112459, "loss": 0.6330067157745362, "step": 271220 }, { "epoch": 1.612247445476755, "grad_norm": 1.4585480690002441, "learning_rate": 0.00011395301258850893, "loss": 0.5694002628326416, "step": 271230 }, { "epoch": 1.6123068875534234, "grad_norm": 1.4561567306518555, "learning_rate": 0.00011394679381698332, "loss": 0.580804443359375, "step": 271240 }, { "epoch": 1.6123663296300919, "grad_norm": 1.3598051071166992, "learning_rate": 0.00011394057502657755, "loss": 0.5656644344329834, "step": 271250 }, { "epoch": 1.6124257717067603, "grad_norm": 1.4884551763534546, "learning_rate": 0.00011393435621732136, "loss": 0.6333230018615723, "step": 271260 }, { "epoch": 1.6124852137834287, "grad_norm": 1.3477306365966797, "learning_rate": 0.00011392813738924451, "loss": 0.5313921928405761, "step": 271270 }, { "epoch": 1.612544655860097, "grad_norm": 1.250144124031067, "learning_rate": 0.0001139219185423767, "loss": 0.5555830955505371, "step": 271280 }, { "epoch": 1.6126040979367655, "grad_norm": 1.2548199892044067, "learning_rate": 0.00011391569967674773, "loss": 0.5229255676269531, "step": 271290 }, { "epoch": 1.612663540013434, "grad_norm": 1.5167211294174194, "learning_rate": 0.00011390948079238737, "loss": 0.595980167388916, "step": 271300 }, { "epoch": 1.6127229820901023, "grad_norm": 1.548500657081604, "learning_rate": 0.00011390326188932527, "loss": 0.5647348403930664, "step": 271310 }, { "epoch": 1.6127824241667708, "grad_norm": 1.6500507593154907, "learning_rate": 0.00011389704296759129, "loss": 0.6262370109558105, "step": 271320 }, { "epoch": 1.6128418662434392, "grad_norm": 1.5428810119628906, "learning_rate": 0.0001138908240272151, "loss": 0.5546642780303955, "step": 271330 }, { "epoch": 1.6129013083201076, "grad_norm": 1.610947608947754, "learning_rate": 0.00011388460506822649, "loss": 0.5377403259277344, "step": 271340 }, { "epoch": 1.612960750396776, "grad_norm": 1.5897119045257568, "learning_rate": 0.0001138783860906552, "loss": 0.5764000892639161, "step": 271350 }, { "epoch": 1.6130201924734444, "grad_norm": 1.5602816343307495, "learning_rate": 0.00011387216709453097, "loss": 0.5583148956298828, "step": 271360 }, { "epoch": 1.6130796345501126, "grad_norm": 1.6990687847137451, "learning_rate": 0.00011386594807988358, "loss": 0.5751590728759766, "step": 271370 }, { "epoch": 1.613139076626781, "grad_norm": 1.362777590751648, "learning_rate": 0.00011385972904674273, "loss": 0.5570043563842774, "step": 271380 }, { "epoch": 1.6131985187034494, "grad_norm": 1.1710481643676758, "learning_rate": 0.0001138535099951382, "loss": 0.5702473640441894, "step": 271390 }, { "epoch": 1.6132579607801179, "grad_norm": 1.294326901435852, "learning_rate": 0.00011384729092509973, "loss": 0.5082901000976563, "step": 271400 }, { "epoch": 1.613317402856786, "grad_norm": 1.288691520690918, "learning_rate": 0.0001138410718366571, "loss": 0.5826708316802979, "step": 271410 }, { "epoch": 1.6133768449334545, "grad_norm": 1.385920763015747, "learning_rate": 0.00011383485272984005, "loss": 0.6119816303253174, "step": 271420 }, { "epoch": 1.6134362870101229, "grad_norm": 1.2892489433288574, "learning_rate": 0.00011382863360467828, "loss": 0.5624283790588379, "step": 271430 }, { "epoch": 1.6134957290867913, "grad_norm": 1.3294299840927124, "learning_rate": 0.00011382241446120161, "loss": 0.5975593566894531, "step": 271440 }, { "epoch": 1.6135551711634597, "grad_norm": 1.3007127046585083, "learning_rate": 0.00011381619529943974, "loss": 0.5813279151916504, "step": 271450 }, { "epoch": 1.6136146132401281, "grad_norm": 1.406748652458191, "learning_rate": 0.00011380997611942244, "loss": 0.5753957748413085, "step": 271460 }, { "epoch": 1.6136740553167965, "grad_norm": 1.623311996459961, "learning_rate": 0.00011380375692117946, "loss": 0.5845861434936523, "step": 271470 }, { "epoch": 1.613733497393465, "grad_norm": 1.6293447017669678, "learning_rate": 0.00011379753770474055, "loss": 0.5558387756347656, "step": 271480 }, { "epoch": 1.6137929394701334, "grad_norm": 1.6212589740753174, "learning_rate": 0.00011379131847013547, "loss": 0.5800540924072266, "step": 271490 }, { "epoch": 1.6138523815468018, "grad_norm": 1.6377776861190796, "learning_rate": 0.00011378509921739398, "loss": 0.5841237545013428, "step": 271500 }, { "epoch": 1.6139118236234702, "grad_norm": 1.451490879058838, "learning_rate": 0.00011377887994654577, "loss": 0.5433547973632813, "step": 271510 }, { "epoch": 1.6139712657001386, "grad_norm": 1.6288310289382935, "learning_rate": 0.00011377266065762062, "loss": 0.6003231525421142, "step": 271520 }, { "epoch": 1.614030707776807, "grad_norm": 1.693325400352478, "learning_rate": 0.00011376644135064838, "loss": 0.5405520439147949, "step": 271530 }, { "epoch": 1.6140901498534754, "grad_norm": 1.2459148168563843, "learning_rate": 0.00011376022202565864, "loss": 0.5132868766784668, "step": 271540 }, { "epoch": 1.6141495919301436, "grad_norm": 1.407623529434204, "learning_rate": 0.00011375400268268123, "loss": 0.5688831806182861, "step": 271550 }, { "epoch": 1.614209034006812, "grad_norm": 1.3335143327713013, "learning_rate": 0.00011374778332174593, "loss": 0.5619524002075196, "step": 271560 }, { "epoch": 1.6142684760834805, "grad_norm": 1.5749025344848633, "learning_rate": 0.00011374156394288244, "loss": 0.5642643928527832, "step": 271570 }, { "epoch": 1.6143279181601489, "grad_norm": 1.3835529088974, "learning_rate": 0.00011373534454612056, "loss": 0.5847368240356445, "step": 271580 }, { "epoch": 1.6143873602368173, "grad_norm": 1.4609286785125732, "learning_rate": 0.00011372912513148996, "loss": 0.6004130363464355, "step": 271590 }, { "epoch": 1.6144468023134855, "grad_norm": 1.691202163696289, "learning_rate": 0.0001137229056990205, "loss": 0.5892606735229492, "step": 271600 }, { "epoch": 1.6145062443901539, "grad_norm": 1.523755431175232, "learning_rate": 0.00011371668624874183, "loss": 0.5561294555664062, "step": 271610 }, { "epoch": 1.6145656864668223, "grad_norm": 1.366402268409729, "learning_rate": 0.00011371046678068377, "loss": 0.5743585586547851, "step": 271620 }, { "epoch": 1.6146251285434907, "grad_norm": 1.6629406213760376, "learning_rate": 0.00011370424729487606, "loss": 0.5767549037933349, "step": 271630 }, { "epoch": 1.6146845706201591, "grad_norm": 1.2624526023864746, "learning_rate": 0.0001136980277913484, "loss": 0.5212738513946533, "step": 271640 }, { "epoch": 1.6147440126968275, "grad_norm": 1.234937071800232, "learning_rate": 0.00011369180827013061, "loss": 0.5617033004760742, "step": 271650 }, { "epoch": 1.614803454773496, "grad_norm": 1.5736885070800781, "learning_rate": 0.00011368558873125244, "loss": 0.5765892028808594, "step": 271660 }, { "epoch": 1.6148628968501644, "grad_norm": 1.4463552236557007, "learning_rate": 0.00011367936917474356, "loss": 0.5932887077331543, "step": 271670 }, { "epoch": 1.6149223389268328, "grad_norm": 1.4109601974487305, "learning_rate": 0.00011367314960063382, "loss": 0.5956783771514893, "step": 271680 }, { "epoch": 1.6149817810035012, "grad_norm": 1.2583309412002563, "learning_rate": 0.00011366693000895294, "loss": 0.5580355644226074, "step": 271690 }, { "epoch": 1.6150412230801696, "grad_norm": 1.2842214107513428, "learning_rate": 0.00011366071039973065, "loss": 0.5781340599060059, "step": 271700 }, { "epoch": 1.615100665156838, "grad_norm": 1.2278857231140137, "learning_rate": 0.0001136544907729967, "loss": 0.5991531372070312, "step": 271710 }, { "epoch": 1.6151601072335064, "grad_norm": 1.4887534379959106, "learning_rate": 0.00011364827112878092, "loss": 0.5674689292907715, "step": 271720 }, { "epoch": 1.6152195493101749, "grad_norm": 1.9962503910064697, "learning_rate": 0.00011364205146711295, "loss": 0.5678617477416992, "step": 271730 }, { "epoch": 1.615278991386843, "grad_norm": 1.4440144300460815, "learning_rate": 0.00011363583178802259, "loss": 0.5731268882751465, "step": 271740 }, { "epoch": 1.6153384334635115, "grad_norm": 1.306386947631836, "learning_rate": 0.00011362961209153964, "loss": 0.5505521774291993, "step": 271750 }, { "epoch": 1.6153978755401799, "grad_norm": 1.6974422931671143, "learning_rate": 0.00011362339237769377, "loss": 0.5420255661010742, "step": 271760 }, { "epoch": 1.6154573176168483, "grad_norm": 1.9520092010498047, "learning_rate": 0.00011361717264651481, "loss": 0.5877646446228028, "step": 271770 }, { "epoch": 1.6155167596935165, "grad_norm": 1.5079593658447266, "learning_rate": 0.00011361095289803247, "loss": 0.6015466690063477, "step": 271780 }, { "epoch": 1.615576201770185, "grad_norm": 1.553341031074524, "learning_rate": 0.0001136047331322765, "loss": 0.5356030464172363, "step": 271790 }, { "epoch": 1.6156356438468533, "grad_norm": 1.4708629846572876, "learning_rate": 0.00011359851334927665, "loss": 0.5314000606536865, "step": 271800 }, { "epoch": 1.6156950859235217, "grad_norm": 1.1748803853988647, "learning_rate": 0.00011359229354906274, "loss": 0.5363078117370605, "step": 271810 }, { "epoch": 1.6157545280001901, "grad_norm": 1.7361427545547485, "learning_rate": 0.00011358607373166443, "loss": 0.5535982131958008, "step": 271820 }, { "epoch": 1.6158139700768586, "grad_norm": 1.7788687944412231, "learning_rate": 0.00011357985389711153, "loss": 0.5714098930358886, "step": 271830 }, { "epoch": 1.615873412153527, "grad_norm": 1.161429524421692, "learning_rate": 0.00011357363404543377, "loss": 0.5454440593719483, "step": 271840 }, { "epoch": 1.6159328542301954, "grad_norm": 1.9209247827529907, "learning_rate": 0.0001135674141766609, "loss": 0.5663084030151367, "step": 271850 }, { "epoch": 1.6159922963068638, "grad_norm": 1.8469043970108032, "learning_rate": 0.00011356119429082271, "loss": 0.5668452739715576, "step": 271860 }, { "epoch": 1.6160517383835322, "grad_norm": 1.7873443365097046, "learning_rate": 0.00011355497438794892, "loss": 0.5804056167602539, "step": 271870 }, { "epoch": 1.6161111804602006, "grad_norm": 1.402376651763916, "learning_rate": 0.0001135487544680693, "loss": 0.5122106552124024, "step": 271880 }, { "epoch": 1.616170622536869, "grad_norm": 1.4336035251617432, "learning_rate": 0.0001135425345312136, "loss": 0.5690964698791504, "step": 271890 }, { "epoch": 1.6162300646135375, "grad_norm": 1.6482869386672974, "learning_rate": 0.00011353631457741156, "loss": 0.5812395095825196, "step": 271900 }, { "epoch": 1.6162895066902059, "grad_norm": 1.5369417667388916, "learning_rate": 0.00011353009460669297, "loss": 0.5665432929992675, "step": 271910 }, { "epoch": 1.616348948766874, "grad_norm": 1.672645926475525, "learning_rate": 0.00011352387461908754, "loss": 0.5672873497009278, "step": 271920 }, { "epoch": 1.6164083908435425, "grad_norm": 1.0272386074066162, "learning_rate": 0.00011351765461462504, "loss": 0.5547369956970215, "step": 271930 }, { "epoch": 1.616467832920211, "grad_norm": 1.5000885725021362, "learning_rate": 0.00011351143459333527, "loss": 0.5399723529815674, "step": 271940 }, { "epoch": 1.6165272749968793, "grad_norm": 1.4758985042572021, "learning_rate": 0.0001135052145552479, "loss": 0.5930468559265136, "step": 271950 }, { "epoch": 1.6165867170735477, "grad_norm": 1.3860760927200317, "learning_rate": 0.00011349899450039274, "loss": 0.5436446189880371, "step": 271960 }, { "epoch": 1.616646159150216, "grad_norm": 0.973735511302948, "learning_rate": 0.00011349277442879955, "loss": 0.591419792175293, "step": 271970 }, { "epoch": 1.6167056012268843, "grad_norm": 1.6488138437271118, "learning_rate": 0.00011348655434049804, "loss": 0.6404376983642578, "step": 271980 }, { "epoch": 1.6167650433035528, "grad_norm": 1.4664112329483032, "learning_rate": 0.00011348033423551801, "loss": 0.6068756580352783, "step": 271990 }, { "epoch": 1.6168244853802212, "grad_norm": 1.1511057615280151, "learning_rate": 0.0001134741141138892, "loss": 0.6237847328186035, "step": 272000 }, { "epoch": 1.6168839274568896, "grad_norm": 1.923936367034912, "learning_rate": 0.00011346789397564135, "loss": 0.5358877658843995, "step": 272010 }, { "epoch": 1.616943369533558, "grad_norm": 1.4792819023132324, "learning_rate": 0.00011346167382080428, "loss": 0.6114691734313965, "step": 272020 }, { "epoch": 1.6170028116102264, "grad_norm": 1.3141090869903564, "learning_rate": 0.00011345545364940763, "loss": 0.64266357421875, "step": 272030 }, { "epoch": 1.6170622536868948, "grad_norm": 1.423924446105957, "learning_rate": 0.00011344923346148124, "loss": 0.6029418468475342, "step": 272040 }, { "epoch": 1.6171216957635632, "grad_norm": 1.3461593389511108, "learning_rate": 0.00011344301325705488, "loss": 0.5638043880462646, "step": 272050 }, { "epoch": 1.6171811378402317, "grad_norm": 1.5825971364974976, "learning_rate": 0.00011343679303615822, "loss": 0.662595558166504, "step": 272060 }, { "epoch": 1.6172405799169, "grad_norm": 1.34414541721344, "learning_rate": 0.0001134305727988211, "loss": 0.5732098579406738, "step": 272070 }, { "epoch": 1.6173000219935685, "grad_norm": 1.5675350427627563, "learning_rate": 0.00011342435254507322, "loss": 0.6275887489318848, "step": 272080 }, { "epoch": 1.617359464070237, "grad_norm": 1.5598161220550537, "learning_rate": 0.00011341813227494435, "loss": 0.5905030250549317, "step": 272090 }, { "epoch": 1.6174189061469053, "grad_norm": 1.3403773307800293, "learning_rate": 0.00011341191198846426, "loss": 0.5006867408752441, "step": 272100 }, { "epoch": 1.6174783482235735, "grad_norm": 1.1639755964279175, "learning_rate": 0.0001134056916856627, "loss": 0.6010958671569824, "step": 272110 }, { "epoch": 1.617537790300242, "grad_norm": 1.4284906387329102, "learning_rate": 0.00011339947136656944, "loss": 0.5874209403991699, "step": 272120 }, { "epoch": 1.6175972323769103, "grad_norm": 1.366591215133667, "learning_rate": 0.00011339325103121418, "loss": 0.5424322128295899, "step": 272130 }, { "epoch": 1.6176566744535787, "grad_norm": 1.5851154327392578, "learning_rate": 0.00011338703067962674, "loss": 0.5998870372772217, "step": 272140 }, { "epoch": 1.617716116530247, "grad_norm": 1.4030730724334717, "learning_rate": 0.00011338081031183688, "loss": 0.615910530090332, "step": 272150 }, { "epoch": 1.6177755586069154, "grad_norm": 1.4337533712387085, "learning_rate": 0.00011337458992787428, "loss": 0.5663675308227539, "step": 272160 }, { "epoch": 1.6178350006835838, "grad_norm": 1.6292972564697266, "learning_rate": 0.00011336836952776877, "loss": 0.599129581451416, "step": 272170 }, { "epoch": 1.6178944427602522, "grad_norm": 1.497513771057129, "learning_rate": 0.00011336214911155007, "loss": 0.5996012210845947, "step": 272180 }, { "epoch": 1.6179538848369206, "grad_norm": 1.5380827188491821, "learning_rate": 0.00011335592867924795, "loss": 0.5928664207458496, "step": 272190 }, { "epoch": 1.618013326913589, "grad_norm": 1.599030613899231, "learning_rate": 0.00011334970823089217, "loss": 0.5866923809051514, "step": 272200 }, { "epoch": 1.6180727689902574, "grad_norm": 1.4629143476486206, "learning_rate": 0.00011334348776651249, "loss": 0.5543888568878174, "step": 272210 }, { "epoch": 1.6181322110669258, "grad_norm": 1.1985657215118408, "learning_rate": 0.00011333726728613865, "loss": 0.5636663913726807, "step": 272220 }, { "epoch": 1.6181916531435943, "grad_norm": 1.4112120866775513, "learning_rate": 0.0001133310467898004, "loss": 0.5773047924041748, "step": 272230 }, { "epoch": 1.6182510952202627, "grad_norm": 1.6285507678985596, "learning_rate": 0.00011332482627752752, "loss": 0.6115419387817382, "step": 272240 }, { "epoch": 1.618310537296931, "grad_norm": 1.0408467054367065, "learning_rate": 0.00011331860574934976, "loss": 0.6183464050292968, "step": 272250 }, { "epoch": 1.6183699793735995, "grad_norm": 1.6668474674224854, "learning_rate": 0.00011331238520529686, "loss": 0.5350407600402832, "step": 272260 }, { "epoch": 1.618429421450268, "grad_norm": 1.7210633754730225, "learning_rate": 0.00011330616464539865, "loss": 0.6024562835693359, "step": 272270 }, { "epoch": 1.6184888635269363, "grad_norm": 1.3759679794311523, "learning_rate": 0.00011329994406968473, "loss": 0.5865060806274414, "step": 272280 }, { "epoch": 1.6185483056036045, "grad_norm": 2.056065559387207, "learning_rate": 0.00011329372347818501, "loss": 0.5800840854644775, "step": 272290 }, { "epoch": 1.618607747680273, "grad_norm": 1.1804401874542236, "learning_rate": 0.00011328750287092924, "loss": 0.5819439888000488, "step": 272300 }, { "epoch": 1.6186671897569413, "grad_norm": 1.4331636428833008, "learning_rate": 0.00011328128224794705, "loss": 0.618143892288208, "step": 272310 }, { "epoch": 1.6187266318336098, "grad_norm": 1.4837251901626587, "learning_rate": 0.00011327506160926831, "loss": 0.5675108909606934, "step": 272320 }, { "epoch": 1.6187860739102782, "grad_norm": 1.7883896827697754, "learning_rate": 0.00011326884095492278, "loss": 0.5672311782836914, "step": 272330 }, { "epoch": 1.6188455159869464, "grad_norm": 2.0188839435577393, "learning_rate": 0.00011326262028494013, "loss": 0.5348258018493652, "step": 272340 }, { "epoch": 1.6189049580636148, "grad_norm": 1.5919458866119385, "learning_rate": 0.00011325639959935019, "loss": 0.5762638092041016, "step": 272350 }, { "epoch": 1.6189644001402832, "grad_norm": 1.3379954099655151, "learning_rate": 0.0001132501788981827, "loss": 0.5723464488983154, "step": 272360 }, { "epoch": 1.6190238422169516, "grad_norm": 1.5454977750778198, "learning_rate": 0.0001132439581814674, "loss": 0.5431172370910644, "step": 272370 }, { "epoch": 1.61908328429362, "grad_norm": 1.7713170051574707, "learning_rate": 0.0001132377374492341, "loss": 0.5877381801605225, "step": 272380 }, { "epoch": 1.6191427263702884, "grad_norm": 1.4325684309005737, "learning_rate": 0.00011323151670151251, "loss": 0.5370539665222168, "step": 272390 }, { "epoch": 1.6192021684469569, "grad_norm": 1.5411099195480347, "learning_rate": 0.0001132252959383324, "loss": 0.590809440612793, "step": 272400 }, { "epoch": 1.6192616105236253, "grad_norm": 1.4627580642700195, "learning_rate": 0.0001132190751597235, "loss": 0.5949091911315918, "step": 272410 }, { "epoch": 1.6193210526002937, "grad_norm": 1.4194782972335815, "learning_rate": 0.00011321285436571563, "loss": 0.6119086265563964, "step": 272420 }, { "epoch": 1.619380494676962, "grad_norm": 1.7125447988510132, "learning_rate": 0.0001132066335563385, "loss": 0.6042742729187012, "step": 272430 }, { "epoch": 1.6194399367536305, "grad_norm": 1.5563960075378418, "learning_rate": 0.00011320041273162187, "loss": 0.5723803997039795, "step": 272440 }, { "epoch": 1.619499378830299, "grad_norm": 1.6870290040969849, "learning_rate": 0.00011319419189159552, "loss": 0.6438624382019043, "step": 272450 }, { "epoch": 1.6195588209069673, "grad_norm": 1.1103156805038452, "learning_rate": 0.00011318797103628922, "loss": 0.6382961273193359, "step": 272460 }, { "epoch": 1.6196182629836358, "grad_norm": 1.3958091735839844, "learning_rate": 0.00011318175016573267, "loss": 0.6100297451019288, "step": 272470 }, { "epoch": 1.619677705060304, "grad_norm": 1.7204086780548096, "learning_rate": 0.00011317552927995572, "loss": 0.567936897277832, "step": 272480 }, { "epoch": 1.6197371471369724, "grad_norm": 1.6563950777053833, "learning_rate": 0.00011316930837898802, "loss": 0.6464632987976074, "step": 272490 }, { "epoch": 1.6197965892136408, "grad_norm": 1.5012354850769043, "learning_rate": 0.00011316308746285942, "loss": 0.5820179939270019, "step": 272500 }, { "epoch": 1.6198560312903092, "grad_norm": 1.3764294385910034, "learning_rate": 0.00011315686653159962, "loss": 0.5663235664367676, "step": 272510 }, { "epoch": 1.6199154733669774, "grad_norm": 1.6307238340377808, "learning_rate": 0.00011315064558523842, "loss": 0.6026424407958985, "step": 272520 }, { "epoch": 1.6199749154436458, "grad_norm": 1.4540241956710815, "learning_rate": 0.00011314442462380559, "loss": 0.5876978874206543, "step": 272530 }, { "epoch": 1.6200343575203142, "grad_norm": 1.7191238403320312, "learning_rate": 0.00011313820364733081, "loss": 0.562522029876709, "step": 272540 }, { "epoch": 1.6200937995969826, "grad_norm": 1.2998239994049072, "learning_rate": 0.0001131319826558439, "loss": 0.5726972579956054, "step": 272550 }, { "epoch": 1.620153241673651, "grad_norm": 1.4154448509216309, "learning_rate": 0.00011312576164937463, "loss": 0.5480782508850097, "step": 272560 }, { "epoch": 1.6202126837503195, "grad_norm": 1.3984547853469849, "learning_rate": 0.00011311954062795271, "loss": 0.5368966102600098, "step": 272570 }, { "epoch": 1.6202721258269879, "grad_norm": 1.3319753408432007, "learning_rate": 0.00011311331959160798, "loss": 0.6241701126098633, "step": 272580 }, { "epoch": 1.6203315679036563, "grad_norm": 1.119107961654663, "learning_rate": 0.00011310709854037009, "loss": 0.5130339622497558, "step": 272590 }, { "epoch": 1.6203910099803247, "grad_norm": 1.5342097282409668, "learning_rate": 0.00011310087747426885, "loss": 0.5497055053710938, "step": 272600 }, { "epoch": 1.6204504520569931, "grad_norm": 1.4179050922393799, "learning_rate": 0.00011309465639333408, "loss": 0.6097421169281005, "step": 272610 }, { "epoch": 1.6205098941336615, "grad_norm": 1.4893497228622437, "learning_rate": 0.00011308843529759545, "loss": 0.5768573760986329, "step": 272620 }, { "epoch": 1.62056933621033, "grad_norm": 2.164555549621582, "learning_rate": 0.00011308221418708274, "loss": 0.5833734512329102, "step": 272630 }, { "epoch": 1.6206287782869984, "grad_norm": 1.5743924379348755, "learning_rate": 0.00011307599306182578, "loss": 0.5970849990844727, "step": 272640 }, { "epoch": 1.6206882203636668, "grad_norm": 1.7496765851974487, "learning_rate": 0.00011306977192185422, "loss": 0.6415652751922607, "step": 272650 }, { "epoch": 1.620747662440335, "grad_norm": 1.0074149370193481, "learning_rate": 0.00011306355076719788, "loss": 0.5392019271850585, "step": 272660 }, { "epoch": 1.6208071045170034, "grad_norm": 1.1746606826782227, "learning_rate": 0.00011305732959788653, "loss": 0.49296016693115235, "step": 272670 }, { "epoch": 1.6208665465936718, "grad_norm": 1.157817006111145, "learning_rate": 0.00011305110841394991, "loss": 0.49246892929077146, "step": 272680 }, { "epoch": 1.6209259886703402, "grad_norm": 1.679901123046875, "learning_rate": 0.00011304488721541778, "loss": 0.5749574184417725, "step": 272690 }, { "epoch": 1.6209854307470086, "grad_norm": 1.2370131015777588, "learning_rate": 0.00011303866600231991, "loss": 0.5330531120300293, "step": 272700 }, { "epoch": 1.6210448728236768, "grad_norm": 1.1385451555252075, "learning_rate": 0.00011303244477468606, "loss": 0.5546089172363281, "step": 272710 }, { "epoch": 1.6211043149003452, "grad_norm": 1.5043946504592896, "learning_rate": 0.00011302622353254597, "loss": 0.5951689720153809, "step": 272720 }, { "epoch": 1.6211637569770136, "grad_norm": 1.3561407327651978, "learning_rate": 0.00011302000227592944, "loss": 0.5560496330261231, "step": 272730 }, { "epoch": 1.621223199053682, "grad_norm": 1.7449618577957153, "learning_rate": 0.00011301378100486619, "loss": 0.613169002532959, "step": 272740 }, { "epoch": 1.6212826411303505, "grad_norm": 1.6621062755584717, "learning_rate": 0.00011300755971938599, "loss": 0.5918547153472901, "step": 272750 }, { "epoch": 1.621342083207019, "grad_norm": 1.5121653079986572, "learning_rate": 0.00011300133841951863, "loss": 0.5917101860046386, "step": 272760 }, { "epoch": 1.6214015252836873, "grad_norm": 1.415289044380188, "learning_rate": 0.00011299511710529383, "loss": 0.5494791030883789, "step": 272770 }, { "epoch": 1.6214609673603557, "grad_norm": 1.4839709997177124, "learning_rate": 0.00011298889577674137, "loss": 0.609952163696289, "step": 272780 }, { "epoch": 1.6215204094370241, "grad_norm": 1.2850245237350464, "learning_rate": 0.00011298267443389101, "loss": 0.5579897403717041, "step": 272790 }, { "epoch": 1.6215798515136925, "grad_norm": 1.3681755065917969, "learning_rate": 0.00011297645307677252, "loss": 0.6158009529113769, "step": 272800 }, { "epoch": 1.621639293590361, "grad_norm": 1.5192179679870605, "learning_rate": 0.00011297023170541561, "loss": 0.5542241096496582, "step": 272810 }, { "epoch": 1.6216987356670294, "grad_norm": 1.4115606546401978, "learning_rate": 0.00011296401031985016, "loss": 0.5664318084716797, "step": 272820 }, { "epoch": 1.6217581777436978, "grad_norm": 1.381696105003357, "learning_rate": 0.00011295778892010578, "loss": 0.5421152114868164, "step": 272830 }, { "epoch": 1.6218176198203662, "grad_norm": 1.843977928161621, "learning_rate": 0.00011295156750621234, "loss": 0.5998157024383545, "step": 272840 }, { "epoch": 1.6218770618970344, "grad_norm": 1.4562534093856812, "learning_rate": 0.00011294534607819958, "loss": 0.5679450511932373, "step": 272850 }, { "epoch": 1.6219365039737028, "grad_norm": 1.6378170251846313, "learning_rate": 0.00011293912463609719, "loss": 0.5495940208435058, "step": 272860 }, { "epoch": 1.6219959460503712, "grad_norm": 1.2510099411010742, "learning_rate": 0.00011293290317993504, "loss": 0.5824169158935547, "step": 272870 }, { "epoch": 1.6220553881270396, "grad_norm": 1.481327772140503, "learning_rate": 0.00011292668170974284, "loss": 0.5739678859710693, "step": 272880 }, { "epoch": 1.6221148302037078, "grad_norm": 1.3669142723083496, "learning_rate": 0.00011292046022555032, "loss": 0.5559433460235595, "step": 272890 }, { "epoch": 1.6221742722803763, "grad_norm": 1.9875195026397705, "learning_rate": 0.00011291423872738729, "loss": 0.5974220275878906, "step": 272900 }, { "epoch": 1.6222337143570447, "grad_norm": 1.5602892637252808, "learning_rate": 0.0001129080172152835, "loss": 0.5399215698242188, "step": 272910 }, { "epoch": 1.622293156433713, "grad_norm": 1.3203555345535278, "learning_rate": 0.00011290179568926871, "loss": 0.6069144248962403, "step": 272920 }, { "epoch": 1.6223525985103815, "grad_norm": 1.2321949005126953, "learning_rate": 0.00011289557414937264, "loss": 0.5766291141510009, "step": 272930 }, { "epoch": 1.62241204058705, "grad_norm": 1.6358903646469116, "learning_rate": 0.0001128893525956251, "loss": 0.5529427528381348, "step": 272940 }, { "epoch": 1.6224714826637183, "grad_norm": 1.5674465894699097, "learning_rate": 0.00011288313102805587, "loss": 0.5574217796325683, "step": 272950 }, { "epoch": 1.6225309247403867, "grad_norm": 1.2205854654312134, "learning_rate": 0.00011287690944669466, "loss": 0.5479618072509765, "step": 272960 }, { "epoch": 1.6225903668170552, "grad_norm": 1.2316884994506836, "learning_rate": 0.00011287068785157127, "loss": 0.5406260013580322, "step": 272970 }, { "epoch": 1.6226498088937236, "grad_norm": 1.674308180809021, "learning_rate": 0.00011286446624271545, "loss": 0.5824836254119873, "step": 272980 }, { "epoch": 1.622709250970392, "grad_norm": 1.6491141319274902, "learning_rate": 0.00011285824462015693, "loss": 0.5111224174499511, "step": 272990 }, { "epoch": 1.6227686930470604, "grad_norm": 1.5343250036239624, "learning_rate": 0.00011285202298392552, "loss": 0.5879396438598633, "step": 273000 }, { "epoch": 1.6228281351237288, "grad_norm": 1.4017881155014038, "learning_rate": 0.000112845801334051, "loss": 0.5557222366333008, "step": 273010 }, { "epoch": 1.6228875772003972, "grad_norm": 1.1915568113327026, "learning_rate": 0.00011283957967056306, "loss": 0.6183255195617676, "step": 273020 }, { "epoch": 1.6229470192770654, "grad_norm": 1.2585827112197876, "learning_rate": 0.00011283335799349148, "loss": 0.5474178791046143, "step": 273030 }, { "epoch": 1.6230064613537338, "grad_norm": 1.7270863056182861, "learning_rate": 0.00011282713630286607, "loss": 0.5732203483581543, "step": 273040 }, { "epoch": 1.6230659034304022, "grad_norm": 1.4093632698059082, "learning_rate": 0.00011282091459871658, "loss": 0.5723875999450684, "step": 273050 }, { "epoch": 1.6231253455070707, "grad_norm": 1.110708236694336, "learning_rate": 0.00011281469288107272, "loss": 0.5450033187866211, "step": 273060 }, { "epoch": 1.623184787583739, "grad_norm": 1.3084543943405151, "learning_rate": 0.0001128084711499643, "loss": 0.4872325897216797, "step": 273070 }, { "epoch": 1.6232442296604073, "grad_norm": 1.09203040599823, "learning_rate": 0.0001128022494054211, "loss": 0.501306676864624, "step": 273080 }, { "epoch": 1.6233036717370757, "grad_norm": 1.697087049484253, "learning_rate": 0.00011279602764747281, "loss": 0.5927037715911865, "step": 273090 }, { "epoch": 1.623363113813744, "grad_norm": 1.5425982475280762, "learning_rate": 0.0001127898058761493, "loss": 0.5246466636657715, "step": 273100 }, { "epoch": 1.6234225558904125, "grad_norm": 1.503541350364685, "learning_rate": 0.0001127835840914802, "loss": 0.5722573280334473, "step": 273110 }, { "epoch": 1.623481997967081, "grad_norm": 2.542598247528076, "learning_rate": 0.00011277736229349538, "loss": 0.5350591659545898, "step": 273120 }, { "epoch": 1.6235414400437493, "grad_norm": 1.7564340829849243, "learning_rate": 0.00011277114048222455, "loss": 0.6068338871002197, "step": 273130 }, { "epoch": 1.6236008821204178, "grad_norm": 1.2083381414413452, "learning_rate": 0.0001127649186576975, "loss": 0.5536081314086914, "step": 273140 }, { "epoch": 1.6236603241970862, "grad_norm": 1.4056001901626587, "learning_rate": 0.00011275869681994397, "loss": 0.5644589900970459, "step": 273150 }, { "epoch": 1.6237197662737546, "grad_norm": 1.323041558265686, "learning_rate": 0.00011275247496899375, "loss": 0.6157713413238526, "step": 273160 }, { "epoch": 1.623779208350423, "grad_norm": 1.3059965372085571, "learning_rate": 0.00011274625310487657, "loss": 0.5795735836029052, "step": 273170 }, { "epoch": 1.6238386504270914, "grad_norm": 1.2350163459777832, "learning_rate": 0.00011274003122762225, "loss": 0.5071061134338379, "step": 273180 }, { "epoch": 1.6238980925037598, "grad_norm": 1.369264006614685, "learning_rate": 0.00011273380933726049, "loss": 0.4978357791900635, "step": 273190 }, { "epoch": 1.6239575345804282, "grad_norm": 1.3853954076766968, "learning_rate": 0.0001127275874338211, "loss": 0.5878600597381591, "step": 273200 }, { "epoch": 1.6240169766570967, "grad_norm": 1.5355122089385986, "learning_rate": 0.00011272136551733379, "loss": 0.599066162109375, "step": 273210 }, { "epoch": 1.6240764187337648, "grad_norm": 1.4899972677230835, "learning_rate": 0.00011271514358782838, "loss": 0.5439086437225342, "step": 273220 }, { "epoch": 1.6241358608104333, "grad_norm": 1.3816741704940796, "learning_rate": 0.00011270892164533461, "loss": 0.5524740219116211, "step": 273230 }, { "epoch": 1.6241953028871017, "grad_norm": 1.2727986574172974, "learning_rate": 0.00011270269968988221, "loss": 0.5560225486755371, "step": 273240 }, { "epoch": 1.62425474496377, "grad_norm": 1.4665085077285767, "learning_rate": 0.00011269647772150102, "loss": 0.5314663887023926, "step": 273250 }, { "epoch": 1.6243141870404383, "grad_norm": 1.360097050666809, "learning_rate": 0.00011269025574022074, "loss": 0.5698960304260254, "step": 273260 }, { "epoch": 1.6243736291171067, "grad_norm": 1.6585819721221924, "learning_rate": 0.00011268403374607117, "loss": 0.5737883567810058, "step": 273270 }, { "epoch": 1.6244330711937751, "grad_norm": 1.5102871656417847, "learning_rate": 0.00011267781173908204, "loss": 0.5810688495635986, "step": 273280 }, { "epoch": 1.6244925132704435, "grad_norm": 1.3866328001022339, "learning_rate": 0.00011267158971928318, "loss": 0.549168872833252, "step": 273290 }, { "epoch": 1.624551955347112, "grad_norm": 1.540919542312622, "learning_rate": 0.00011266536768670426, "loss": 0.5360317230224609, "step": 273300 }, { "epoch": 1.6246113974237804, "grad_norm": 1.5704033374786377, "learning_rate": 0.00011265914564137509, "loss": 0.5995429039001465, "step": 273310 }, { "epoch": 1.6246708395004488, "grad_norm": 1.2973147630691528, "learning_rate": 0.00011265292358332546, "loss": 0.597010326385498, "step": 273320 }, { "epoch": 1.6247302815771172, "grad_norm": 1.461182713508606, "learning_rate": 0.00011264670151258511, "loss": 0.5663105964660644, "step": 273330 }, { "epoch": 1.6247897236537856, "grad_norm": 1.1344443559646606, "learning_rate": 0.0001126404794291838, "loss": 0.55072922706604, "step": 273340 }, { "epoch": 1.624849165730454, "grad_norm": 1.4640363454818726, "learning_rate": 0.00011263425733315132, "loss": 0.5223085880279541, "step": 273350 }, { "epoch": 1.6249086078071224, "grad_norm": 1.4822736978530884, "learning_rate": 0.00011262803522451739, "loss": 0.5970901012420654, "step": 273360 }, { "epoch": 1.6249680498837908, "grad_norm": 1.4928278923034668, "learning_rate": 0.00011262181310331179, "loss": 0.627461290359497, "step": 273370 }, { "epoch": 1.6250274919604593, "grad_norm": 1.6281298398971558, "learning_rate": 0.0001126155909695643, "loss": 0.5658834457397461, "step": 273380 }, { "epoch": 1.6250869340371277, "grad_norm": 1.4251654148101807, "learning_rate": 0.00011260936882330467, "loss": 0.5235177516937256, "step": 273390 }, { "epoch": 1.6251463761137959, "grad_norm": 1.5925897359848022, "learning_rate": 0.00011260314666456269, "loss": 0.5964596748352051, "step": 273400 }, { "epoch": 1.6252058181904643, "grad_norm": 1.458976149559021, "learning_rate": 0.00011259692449336812, "loss": 0.5321394920349121, "step": 273410 }, { "epoch": 1.6252652602671327, "grad_norm": 1.2454782724380493, "learning_rate": 0.00011259070230975066, "loss": 0.5650539875030518, "step": 273420 }, { "epoch": 1.625324702343801, "grad_norm": 1.5843071937561035, "learning_rate": 0.00011258448011374016, "loss": 0.5776059627532959, "step": 273430 }, { "epoch": 1.6253841444204695, "grad_norm": 1.302294373512268, "learning_rate": 0.00011257825790536638, "loss": 0.5518912315368653, "step": 273440 }, { "epoch": 1.6254435864971377, "grad_norm": 1.5904474258422852, "learning_rate": 0.000112572035684659, "loss": 0.5548862457275391, "step": 273450 }, { "epoch": 1.6255030285738061, "grad_norm": 1.2082165479660034, "learning_rate": 0.0001125658134516479, "loss": 0.6026179313659668, "step": 273460 }, { "epoch": 1.6255624706504745, "grad_norm": 1.590960144996643, "learning_rate": 0.00011255959120636272, "loss": 0.5778074741363526, "step": 273470 }, { "epoch": 1.625621912727143, "grad_norm": 1.8786917924880981, "learning_rate": 0.00011255336894883335, "loss": 0.5750236988067627, "step": 273480 }, { "epoch": 1.6256813548038114, "grad_norm": 1.275428056716919, "learning_rate": 0.00011254714667908945, "loss": 0.5435092926025391, "step": 273490 }, { "epoch": 1.6257407968804798, "grad_norm": 1.8247004747390747, "learning_rate": 0.00011254092439716089, "loss": 0.6098631381988525, "step": 273500 }, { "epoch": 1.6258002389571482, "grad_norm": 1.148453950881958, "learning_rate": 0.00011253470210307735, "loss": 0.526802396774292, "step": 273510 }, { "epoch": 1.6258596810338166, "grad_norm": 1.09772527217865, "learning_rate": 0.00011252847979686861, "loss": 0.5665080070495605, "step": 273520 }, { "epoch": 1.625919123110485, "grad_norm": 1.6632949113845825, "learning_rate": 0.00011252225747856446, "loss": 0.5679668426513672, "step": 273530 }, { "epoch": 1.6259785651871534, "grad_norm": 1.2318322658538818, "learning_rate": 0.00011251603514819466, "loss": 0.5981945514678955, "step": 273540 }, { "epoch": 1.6260380072638219, "grad_norm": 1.580607533454895, "learning_rate": 0.00011250981280578896, "loss": 0.5177148818969727, "step": 273550 }, { "epoch": 1.6260974493404903, "grad_norm": 1.4639720916748047, "learning_rate": 0.00011250359045137715, "loss": 0.570163345336914, "step": 273560 }, { "epoch": 1.6261568914171587, "grad_norm": 1.4625341892242432, "learning_rate": 0.00011249736808498894, "loss": 0.5773508071899414, "step": 273570 }, { "epoch": 1.626216333493827, "grad_norm": 1.473112940788269, "learning_rate": 0.00011249114570665416, "loss": 0.5703770637512207, "step": 273580 }, { "epoch": 1.6262757755704953, "grad_norm": 1.4671204090118408, "learning_rate": 0.00011248492331640259, "loss": 0.5585187435150146, "step": 273590 }, { "epoch": 1.6263352176471637, "grad_norm": 1.473787784576416, "learning_rate": 0.00011247870091426393, "loss": 0.6137338638305664, "step": 273600 }, { "epoch": 1.6263946597238321, "grad_norm": 1.3829262256622314, "learning_rate": 0.00011247247850026796, "loss": 0.6069411277770996, "step": 273610 }, { "epoch": 1.6264541018005005, "grad_norm": 1.6226176023483276, "learning_rate": 0.00011246625607444448, "loss": 0.5881107330322266, "step": 273620 }, { "epoch": 1.6265135438771687, "grad_norm": 1.3511494398117065, "learning_rate": 0.00011246003363682323, "loss": 0.5689383029937745, "step": 273630 }, { "epoch": 1.6265729859538371, "grad_norm": 1.113759160041809, "learning_rate": 0.00011245381118743399, "loss": 0.6157743453979492, "step": 273640 }, { "epoch": 1.6266324280305056, "grad_norm": 1.3052064180374146, "learning_rate": 0.00011244758872630652, "loss": 0.5286890029907226, "step": 273650 }, { "epoch": 1.626691870107174, "grad_norm": 1.4042621850967407, "learning_rate": 0.00011244136625347058, "loss": 0.518442440032959, "step": 273660 }, { "epoch": 1.6267513121838424, "grad_norm": 1.7106127738952637, "learning_rate": 0.00011243514376895595, "loss": 0.6059160232543945, "step": 273670 }, { "epoch": 1.6268107542605108, "grad_norm": 1.4174166917800903, "learning_rate": 0.00011242892127279239, "loss": 0.5573736190795898, "step": 273680 }, { "epoch": 1.6268701963371792, "grad_norm": 1.645131230354309, "learning_rate": 0.00011242269876500964, "loss": 0.582268238067627, "step": 273690 }, { "epoch": 1.6269296384138476, "grad_norm": 1.3950852155685425, "learning_rate": 0.00011241647624563749, "loss": 0.5564668655395508, "step": 273700 }, { "epoch": 1.626989080490516, "grad_norm": 1.3684287071228027, "learning_rate": 0.00011241025371470573, "loss": 0.6233045578002929, "step": 273710 }, { "epoch": 1.6270485225671845, "grad_norm": 1.1730715036392212, "learning_rate": 0.00011240403117224412, "loss": 0.5053034782409668, "step": 273720 }, { "epoch": 1.6271079646438529, "grad_norm": 1.3617820739746094, "learning_rate": 0.00011239780861828235, "loss": 0.5337589740753174, "step": 273730 }, { "epoch": 1.6271674067205213, "grad_norm": 1.3613557815551758, "learning_rate": 0.0001123915860528503, "loss": 0.5496695518493653, "step": 273740 }, { "epoch": 1.6272268487971897, "grad_norm": 1.3273258209228516, "learning_rate": 0.00011238536347597768, "loss": 0.5589570999145508, "step": 273750 }, { "epoch": 1.6272862908738581, "grad_norm": 1.3735520839691162, "learning_rate": 0.00011237914088769423, "loss": 0.5818275451660156, "step": 273760 }, { "epoch": 1.6273457329505263, "grad_norm": 1.4602551460266113, "learning_rate": 0.00011237291828802978, "loss": 0.5097043991088868, "step": 273770 }, { "epoch": 1.6274051750271947, "grad_norm": 1.1950198411941528, "learning_rate": 0.00011236669567701406, "loss": 0.5260995864868164, "step": 273780 }, { "epoch": 1.6274646171038631, "grad_norm": 1.5628687143325806, "learning_rate": 0.00011236047305467683, "loss": 0.5395586967468262, "step": 273790 }, { "epoch": 1.6275240591805316, "grad_norm": 1.2643402814865112, "learning_rate": 0.00011235425042104786, "loss": 0.5644276142120361, "step": 273800 }, { "epoch": 1.6275835012572, "grad_norm": 1.3166284561157227, "learning_rate": 0.00011234802777615693, "loss": 0.5323292255401612, "step": 273810 }, { "epoch": 1.6276429433338682, "grad_norm": 1.4585046768188477, "learning_rate": 0.00011234180512003382, "loss": 0.6272649765014648, "step": 273820 }, { "epoch": 1.6277023854105366, "grad_norm": 1.7266823053359985, "learning_rate": 0.00011233558245270823, "loss": 0.5784281730651856, "step": 273830 }, { "epoch": 1.627761827487205, "grad_norm": 1.3677045106887817, "learning_rate": 0.00011232935977421005, "loss": 0.5442814826965332, "step": 273840 }, { "epoch": 1.6278212695638734, "grad_norm": 1.449753761291504, "learning_rate": 0.00011232313708456895, "loss": 0.5862864494323731, "step": 273850 }, { "epoch": 1.6278807116405418, "grad_norm": 1.5660755634307861, "learning_rate": 0.00011231691438381469, "loss": 0.5509209632873535, "step": 273860 }, { "epoch": 1.6279401537172102, "grad_norm": 1.3033071756362915, "learning_rate": 0.0001123106916719771, "loss": 0.5463623046875, "step": 273870 }, { "epoch": 1.6279995957938787, "grad_norm": 1.2788068056106567, "learning_rate": 0.0001123044689490859, "loss": 0.6246508598327637, "step": 273880 }, { "epoch": 1.628059037870547, "grad_norm": 1.6697531938552856, "learning_rate": 0.00011229824621517087, "loss": 0.5993156433105469, "step": 273890 }, { "epoch": 1.6281184799472155, "grad_norm": 1.5961861610412598, "learning_rate": 0.00011229202347026181, "loss": 0.576911735534668, "step": 273900 }, { "epoch": 1.628177922023884, "grad_norm": 1.4493443965911865, "learning_rate": 0.00011228580071438843, "loss": 0.5567830085754395, "step": 273910 }, { "epoch": 1.6282373641005523, "grad_norm": 1.253419041633606, "learning_rate": 0.00011227957794758055, "loss": 0.5477661609649658, "step": 273920 }, { "epoch": 1.6282968061772207, "grad_norm": 1.2557694911956787, "learning_rate": 0.00011227335516986788, "loss": 0.5338564872741699, "step": 273930 }, { "epoch": 1.6283562482538891, "grad_norm": 1.3953580856323242, "learning_rate": 0.00011226713238128024, "loss": 0.6108023166656494, "step": 273940 }, { "epoch": 1.6284156903305576, "grad_norm": 2.0551841259002686, "learning_rate": 0.00011226090958184738, "loss": 0.5292876243591309, "step": 273950 }, { "epoch": 1.6284751324072257, "grad_norm": 1.60550856590271, "learning_rate": 0.00011225468677159908, "loss": 0.5357277870178223, "step": 273960 }, { "epoch": 1.6285345744838942, "grad_norm": 1.5045125484466553, "learning_rate": 0.0001122484639505651, "loss": 0.5606730461120606, "step": 273970 }, { "epoch": 1.6285940165605626, "grad_norm": 1.6641453504562378, "learning_rate": 0.00011224224111877515, "loss": 0.5945584297180175, "step": 273980 }, { "epoch": 1.628653458637231, "grad_norm": 1.0805253982543945, "learning_rate": 0.00011223601827625909, "loss": 0.49735136032104493, "step": 273990 }, { "epoch": 1.6287129007138992, "grad_norm": 1.3651468753814697, "learning_rate": 0.00011222979542304668, "loss": 0.5484797477722168, "step": 274000 }, { "epoch": 1.6287723427905676, "grad_norm": 1.630301833152771, "learning_rate": 0.0001122235725591676, "loss": 0.5468885421752929, "step": 274010 }, { "epoch": 1.628831784867236, "grad_norm": 1.3542563915252686, "learning_rate": 0.00011221734968465169, "loss": 0.5351493835449219, "step": 274020 }, { "epoch": 1.6288912269439044, "grad_norm": 1.37235426902771, "learning_rate": 0.00011221112679952872, "loss": 0.5899774551391601, "step": 274030 }, { "epoch": 1.6289506690205728, "grad_norm": 1.5156866312026978, "learning_rate": 0.00011220490390382843, "loss": 0.6017624378204346, "step": 274040 }, { "epoch": 1.6290101110972413, "grad_norm": 1.7112812995910645, "learning_rate": 0.00011219868099758062, "loss": 0.5725841522216797, "step": 274050 }, { "epoch": 1.6290695531739097, "grad_norm": 1.3840222358703613, "learning_rate": 0.00011219245808081502, "loss": 0.5625451087951661, "step": 274060 }, { "epoch": 1.629128995250578, "grad_norm": 1.6642119884490967, "learning_rate": 0.00011218623515356142, "loss": 0.5192497253417969, "step": 274070 }, { "epoch": 1.6291884373272465, "grad_norm": 1.4440529346466064, "learning_rate": 0.00011218001221584962, "loss": 0.6539460182189941, "step": 274080 }, { "epoch": 1.629247879403915, "grad_norm": 1.5157994031906128, "learning_rate": 0.00011217378926770929, "loss": 0.612505578994751, "step": 274090 }, { "epoch": 1.6293073214805833, "grad_norm": 1.2241414785385132, "learning_rate": 0.00011216756630917029, "loss": 0.5852830410003662, "step": 274100 }, { "epoch": 1.6293667635572517, "grad_norm": 1.327364206314087, "learning_rate": 0.00011216134334026237, "loss": 0.4896868705749512, "step": 274110 }, { "epoch": 1.6294262056339202, "grad_norm": 1.3785628080368042, "learning_rate": 0.0001121551203610153, "loss": 0.6027069091796875, "step": 274120 }, { "epoch": 1.6294856477105886, "grad_norm": 1.4877853393554688, "learning_rate": 0.00011214889737145882, "loss": 0.5288345336914062, "step": 274130 }, { "epoch": 1.6295450897872568, "grad_norm": 1.4433684349060059, "learning_rate": 0.00011214267437162271, "loss": 0.601891040802002, "step": 274140 }, { "epoch": 1.6296045318639252, "grad_norm": 1.5306683778762817, "learning_rate": 0.00011213645136153678, "loss": 0.5661349296569824, "step": 274150 }, { "epoch": 1.6296639739405936, "grad_norm": 1.3775966167449951, "learning_rate": 0.00011213022834123073, "loss": 0.540690279006958, "step": 274160 }, { "epoch": 1.629723416017262, "grad_norm": 1.9321260452270508, "learning_rate": 0.00011212400531073437, "loss": 0.6023166656494141, "step": 274170 }, { "epoch": 1.6297828580939304, "grad_norm": 1.3461560010910034, "learning_rate": 0.00011211778227007747, "loss": 0.5270486831665039, "step": 274180 }, { "epoch": 1.6298423001705986, "grad_norm": 1.7416048049926758, "learning_rate": 0.00011211155921928977, "loss": 0.5203584671020508, "step": 274190 }, { "epoch": 1.629901742247267, "grad_norm": 1.7769310474395752, "learning_rate": 0.00011210533615840111, "loss": 0.612397289276123, "step": 274200 }, { "epoch": 1.6299611843239354, "grad_norm": 1.4315444231033325, "learning_rate": 0.00011209911308744118, "loss": 0.616431713104248, "step": 274210 }, { "epoch": 1.6300206264006039, "grad_norm": 1.1866557598114014, "learning_rate": 0.00011209289000643975, "loss": 0.5804189682006836, "step": 274220 }, { "epoch": 1.6300800684772723, "grad_norm": 2.1101150512695312, "learning_rate": 0.00011208666691542666, "loss": 0.5615894317626953, "step": 274230 }, { "epoch": 1.6301395105539407, "grad_norm": 1.4631495475769043, "learning_rate": 0.00011208044381443164, "loss": 0.5251348495483399, "step": 274240 }, { "epoch": 1.630198952630609, "grad_norm": 1.1712102890014648, "learning_rate": 0.00011207422070348442, "loss": 0.5587945938110351, "step": 274250 }, { "epoch": 1.6302583947072775, "grad_norm": 1.3790442943572998, "learning_rate": 0.00011206799758261483, "loss": 0.5985795021057129, "step": 274260 }, { "epoch": 1.630317836783946, "grad_norm": 1.5777760744094849, "learning_rate": 0.00011206177445185262, "loss": 0.5944595336914062, "step": 274270 }, { "epoch": 1.6303772788606143, "grad_norm": 1.6068743467330933, "learning_rate": 0.00011205555131122756, "loss": 0.6012068271636963, "step": 274280 }, { "epoch": 1.6304367209372828, "grad_norm": 1.5333833694458008, "learning_rate": 0.00011204932816076939, "loss": 0.5776669979095459, "step": 274290 }, { "epoch": 1.6304961630139512, "grad_norm": 1.4902286529541016, "learning_rate": 0.00011204310500050792, "loss": 0.5591161727905274, "step": 274300 }, { "epoch": 1.6305556050906196, "grad_norm": 1.2747373580932617, "learning_rate": 0.0001120368818304729, "loss": 0.5897688865661621, "step": 274310 }, { "epoch": 1.630615047167288, "grad_norm": 1.5693923234939575, "learning_rate": 0.00011203065865069408, "loss": 0.5876330375671387, "step": 274320 }, { "epoch": 1.6306744892439562, "grad_norm": 1.4143174886703491, "learning_rate": 0.00011202443546120129, "loss": 0.5861360549926757, "step": 274330 }, { "epoch": 1.6307339313206246, "grad_norm": 1.4035413265228271, "learning_rate": 0.00011201821226202425, "loss": 0.5658237934112549, "step": 274340 }, { "epoch": 1.630793373397293, "grad_norm": 1.3939144611358643, "learning_rate": 0.00011201198905319272, "loss": 0.5114295959472657, "step": 274350 }, { "epoch": 1.6308528154739614, "grad_norm": 1.6181037425994873, "learning_rate": 0.00011200576583473654, "loss": 0.5702513694763184, "step": 274360 }, { "epoch": 1.6309122575506296, "grad_norm": 1.542501449584961, "learning_rate": 0.0001119995426066854, "loss": 0.6097200870513916, "step": 274370 }, { "epoch": 1.630971699627298, "grad_norm": 1.5240143537521362, "learning_rate": 0.0001119933193690691, "loss": 0.6081660747528076, "step": 274380 }, { "epoch": 1.6310311417039665, "grad_norm": 1.1752233505249023, "learning_rate": 0.00011198709612191743, "loss": 0.5368518829345703, "step": 274390 }, { "epoch": 1.6310905837806349, "grad_norm": 1.0078418254852295, "learning_rate": 0.00011198087286526011, "loss": 0.5540409088134766, "step": 274400 }, { "epoch": 1.6311500258573033, "grad_norm": 1.3344651460647583, "learning_rate": 0.00011197464959912695, "loss": 0.5564980983734131, "step": 274410 }, { "epoch": 1.6312094679339717, "grad_norm": 1.5991548299789429, "learning_rate": 0.00011196842632354774, "loss": 0.5984906196594239, "step": 274420 }, { "epoch": 1.6312689100106401, "grad_norm": 1.097224473953247, "learning_rate": 0.00011196220303855218, "loss": 0.5726735115051269, "step": 274430 }, { "epoch": 1.6313283520873085, "grad_norm": 1.5116934776306152, "learning_rate": 0.00011195597974417012, "loss": 0.5389316558837891, "step": 274440 }, { "epoch": 1.631387794163977, "grad_norm": 1.6704899072647095, "learning_rate": 0.00011194975644043128, "loss": 0.5648439407348633, "step": 274450 }, { "epoch": 1.6314472362406454, "grad_norm": 1.7088942527770996, "learning_rate": 0.00011194353312736545, "loss": 0.6221677780151367, "step": 274460 }, { "epoch": 1.6315066783173138, "grad_norm": 1.442936897277832, "learning_rate": 0.00011193730980500237, "loss": 0.6065278053283691, "step": 274470 }, { "epoch": 1.6315661203939822, "grad_norm": 1.2740769386291504, "learning_rate": 0.00011193108647337185, "loss": 0.5437653541564942, "step": 274480 }, { "epoch": 1.6316255624706506, "grad_norm": 1.7353816032409668, "learning_rate": 0.00011192486313250363, "loss": 0.6160869121551513, "step": 274490 }, { "epoch": 1.631685004547319, "grad_norm": 1.630056381225586, "learning_rate": 0.0001119186397824275, "loss": 0.50728759765625, "step": 274500 }, { "epoch": 1.6317444466239872, "grad_norm": 1.5858967304229736, "learning_rate": 0.00011191241642317323, "loss": 0.5593847751617431, "step": 274510 }, { "epoch": 1.6318038887006556, "grad_norm": 1.5206056833267212, "learning_rate": 0.0001119061930547706, "loss": 0.5111527442932129, "step": 274520 }, { "epoch": 1.631863330777324, "grad_norm": 1.4492965936660767, "learning_rate": 0.00011189996967724931, "loss": 0.5703423500061036, "step": 274530 }, { "epoch": 1.6319227728539925, "grad_norm": 1.2874677181243896, "learning_rate": 0.00011189374629063923, "loss": 0.5312202453613282, "step": 274540 }, { "epoch": 1.6319822149306609, "grad_norm": 1.5851407051086426, "learning_rate": 0.00011188752289497009, "loss": 0.5669307708740234, "step": 274550 }, { "epoch": 1.632041657007329, "grad_norm": 1.468334436416626, "learning_rate": 0.00011188129949027162, "loss": 0.5517606735229492, "step": 274560 }, { "epoch": 1.6321010990839975, "grad_norm": 1.633881688117981, "learning_rate": 0.00011187507607657368, "loss": 0.631648063659668, "step": 274570 }, { "epoch": 1.632160541160666, "grad_norm": 1.714605450630188, "learning_rate": 0.00011186885265390597, "loss": 0.6146794319152832, "step": 274580 }, { "epoch": 1.6322199832373343, "grad_norm": 1.4757614135742188, "learning_rate": 0.00011186262922229827, "loss": 0.5332444190979004, "step": 274590 }, { "epoch": 1.6322794253140027, "grad_norm": 1.7012457847595215, "learning_rate": 0.00011185640578178036, "loss": 0.612719202041626, "step": 274600 }, { "epoch": 1.6323388673906711, "grad_norm": 1.2826576232910156, "learning_rate": 0.000111850182332382, "loss": 0.5558301925659179, "step": 274610 }, { "epoch": 1.6323983094673395, "grad_norm": 1.956663966178894, "learning_rate": 0.00011184395887413301, "loss": 0.5623008728027343, "step": 274620 }, { "epoch": 1.632457751544008, "grad_norm": 1.187975287437439, "learning_rate": 0.00011183773540706308, "loss": 0.5457990169525146, "step": 274630 }, { "epoch": 1.6325171936206764, "grad_norm": 1.534785509109497, "learning_rate": 0.00011183151193120207, "loss": 0.5659345626831055, "step": 274640 }, { "epoch": 1.6325766356973448, "grad_norm": 1.4058135747909546, "learning_rate": 0.00011182528844657967, "loss": 0.5672856330871582, "step": 274650 }, { "epoch": 1.6326360777740132, "grad_norm": 1.5730234384536743, "learning_rate": 0.00011181906495322567, "loss": 0.5690231800079346, "step": 274660 }, { "epoch": 1.6326955198506816, "grad_norm": 1.3665027618408203, "learning_rate": 0.00011181284145116992, "loss": 0.5418907165527344, "step": 274670 }, { "epoch": 1.63275496192735, "grad_norm": 1.4196745157241821, "learning_rate": 0.0001118066179404421, "loss": 0.5237289428710937, "step": 274680 }, { "epoch": 1.6328144040040184, "grad_norm": 1.5350455045700073, "learning_rate": 0.000111800394421072, "loss": 0.5622900009155274, "step": 274690 }, { "epoch": 1.6328738460806866, "grad_norm": 1.3535609245300293, "learning_rate": 0.00011179417089308941, "loss": 0.5831480026245117, "step": 274700 }, { "epoch": 1.632933288157355, "grad_norm": 1.445884346961975, "learning_rate": 0.00011178794735652407, "loss": 0.5439365386962891, "step": 274710 }, { "epoch": 1.6329927302340235, "grad_norm": 2.0274534225463867, "learning_rate": 0.0001117817238114058, "loss": 0.5317329406738281, "step": 274720 }, { "epoch": 1.6330521723106919, "grad_norm": 1.4022319316864014, "learning_rate": 0.00011177550025776434, "loss": 0.5398628234863281, "step": 274730 }, { "epoch": 1.63311161438736, "grad_norm": 1.5570156574249268, "learning_rate": 0.00011176927669562947, "loss": 0.5540858745574951, "step": 274740 }, { "epoch": 1.6331710564640285, "grad_norm": 1.3903249502182007, "learning_rate": 0.00011176305312503095, "loss": 0.5263372898101807, "step": 274750 }, { "epoch": 1.633230498540697, "grad_norm": 1.3863272666931152, "learning_rate": 0.00011175682954599855, "loss": 0.6018265724182129, "step": 274760 }, { "epoch": 1.6332899406173653, "grad_norm": 1.453676700592041, "learning_rate": 0.00011175060595856206, "loss": 0.5611824035644531, "step": 274770 }, { "epoch": 1.6333493826940337, "grad_norm": 1.6506446599960327, "learning_rate": 0.00011174438236275125, "loss": 0.5841482162475586, "step": 274780 }, { "epoch": 1.6334088247707022, "grad_norm": 1.569978952407837, "learning_rate": 0.0001117381587585959, "loss": 0.5338542938232422, "step": 274790 }, { "epoch": 1.6334682668473706, "grad_norm": 1.2666743993759155, "learning_rate": 0.00011173193514612574, "loss": 0.61220703125, "step": 274800 }, { "epoch": 1.633527708924039, "grad_norm": 1.3517881631851196, "learning_rate": 0.00011172571152537057, "loss": 0.5913990497589111, "step": 274810 }, { "epoch": 1.6335871510007074, "grad_norm": 1.2122637033462524, "learning_rate": 0.0001117194878963602, "loss": 0.549527645111084, "step": 274820 }, { "epoch": 1.6336465930773758, "grad_norm": 1.4750092029571533, "learning_rate": 0.0001117132642591243, "loss": 0.6146489143371582, "step": 274830 }, { "epoch": 1.6337060351540442, "grad_norm": 1.7358464002609253, "learning_rate": 0.00011170704061369273, "loss": 0.6157102584838867, "step": 274840 }, { "epoch": 1.6337654772307126, "grad_norm": 1.4361276626586914, "learning_rate": 0.00011170081696009527, "loss": 0.5630142688751221, "step": 274850 }, { "epoch": 1.633824919307381, "grad_norm": 1.4598256349563599, "learning_rate": 0.0001116945932983616, "loss": 0.5983098030090332, "step": 274860 }, { "epoch": 1.6338843613840495, "grad_norm": 1.5278881788253784, "learning_rate": 0.00011168836962852156, "loss": 0.6171173095703125, "step": 274870 }, { "epoch": 1.6339438034607177, "grad_norm": 1.1204500198364258, "learning_rate": 0.00011168214595060496, "loss": 0.5479570865631104, "step": 274880 }, { "epoch": 1.634003245537386, "grad_norm": 1.6054396629333496, "learning_rate": 0.00011167592226464149, "loss": 0.5737313270568848, "step": 274890 }, { "epoch": 1.6340626876140545, "grad_norm": 1.2051175832748413, "learning_rate": 0.00011166969857066094, "loss": 0.5500125885009766, "step": 274900 }, { "epoch": 1.634122129690723, "grad_norm": 1.3389767408370972, "learning_rate": 0.00011166347486869313, "loss": 0.5447866916656494, "step": 274910 }, { "epoch": 1.6341815717673913, "grad_norm": 1.3199352025985718, "learning_rate": 0.00011165725115876778, "loss": 0.5642670154571533, "step": 274920 }, { "epoch": 1.6342410138440595, "grad_norm": 1.2931216955184937, "learning_rate": 0.00011165102744091467, "loss": 0.583920955657959, "step": 274930 }, { "epoch": 1.634300455920728, "grad_norm": 1.6942424774169922, "learning_rate": 0.00011164480371516361, "loss": 0.6151956558227539, "step": 274940 }, { "epoch": 1.6343598979973963, "grad_norm": 1.2745996713638306, "learning_rate": 0.00011163857998154436, "loss": 0.5537673950195312, "step": 274950 }, { "epoch": 1.6344193400740648, "grad_norm": 1.437251329421997, "learning_rate": 0.00011163235624008663, "loss": 0.5584274291992187, "step": 274960 }, { "epoch": 1.6344787821507332, "grad_norm": 1.4046491384506226, "learning_rate": 0.00011162613249082028, "loss": 0.5352830410003662, "step": 274970 }, { "epoch": 1.6345382242274016, "grad_norm": 1.5301942825317383, "learning_rate": 0.00011161990873377504, "loss": 0.6374558448791504, "step": 274980 }, { "epoch": 1.63459766630407, "grad_norm": 1.0703322887420654, "learning_rate": 0.00011161368496898065, "loss": 0.5246600151062012, "step": 274990 }, { "epoch": 1.6346571083807384, "grad_norm": 1.3950740098953247, "learning_rate": 0.00011160746119646697, "loss": 0.5982170104980469, "step": 275000 }, { "epoch": 1.6347165504574068, "grad_norm": 1.0426863431930542, "learning_rate": 0.0001116012374162637, "loss": 0.5301096916198731, "step": 275010 }, { "epoch": 1.6347759925340752, "grad_norm": 1.4243794679641724, "learning_rate": 0.00011159501362840059, "loss": 0.5548861503601075, "step": 275020 }, { "epoch": 1.6348354346107437, "grad_norm": 1.9798260927200317, "learning_rate": 0.00011158878983290752, "loss": 0.5420145034790039, "step": 275030 }, { "epoch": 1.634894876687412, "grad_norm": 1.4499070644378662, "learning_rate": 0.00011158256602981418, "loss": 0.603727149963379, "step": 275040 }, { "epoch": 1.6349543187640805, "grad_norm": 1.7585468292236328, "learning_rate": 0.00011157634221915035, "loss": 0.5911179542541504, "step": 275050 }, { "epoch": 1.635013760840749, "grad_norm": 1.491599202156067, "learning_rate": 0.0001115701184009458, "loss": 0.535216236114502, "step": 275060 }, { "epoch": 1.635073202917417, "grad_norm": 1.7606552839279175, "learning_rate": 0.00011156389457523036, "loss": 0.6021852016448974, "step": 275070 }, { "epoch": 1.6351326449940855, "grad_norm": 1.0132429599761963, "learning_rate": 0.00011155767074203374, "loss": 0.5308944702148437, "step": 275080 }, { "epoch": 1.635192087070754, "grad_norm": 1.381998896598816, "learning_rate": 0.00011155144690138572, "loss": 0.5636239051818848, "step": 275090 }, { "epoch": 1.6352515291474223, "grad_norm": 1.4213683605194092, "learning_rate": 0.00011154522305331607, "loss": 0.6187361240386963, "step": 275100 }, { "epoch": 1.6353109712240905, "grad_norm": 1.4864274263381958, "learning_rate": 0.00011153899919785463, "loss": 0.5919707298278809, "step": 275110 }, { "epoch": 1.635370413300759, "grad_norm": 1.736720323562622, "learning_rate": 0.00011153277533503108, "loss": 0.5728273391723633, "step": 275120 }, { "epoch": 1.6354298553774274, "grad_norm": 1.8347309827804565, "learning_rate": 0.00011152655146487525, "loss": 0.6060679912567138, "step": 275130 }, { "epoch": 1.6354892974540958, "grad_norm": 1.425560474395752, "learning_rate": 0.00011152032758741689, "loss": 0.5206497192382813, "step": 275140 }, { "epoch": 1.6355487395307642, "grad_norm": 1.68954336643219, "learning_rate": 0.00011151410370268578, "loss": 0.5340893745422364, "step": 275150 }, { "epoch": 1.6356081816074326, "grad_norm": 1.3717834949493408, "learning_rate": 0.00011150787981071171, "loss": 0.5730994701385498, "step": 275160 }, { "epoch": 1.635667623684101, "grad_norm": 1.4647530317306519, "learning_rate": 0.0001115016559115244, "loss": 0.6370857238769532, "step": 275170 }, { "epoch": 1.6357270657607694, "grad_norm": 1.5528054237365723, "learning_rate": 0.00011149543200515367, "loss": 0.5291689395904541, "step": 275180 }, { "epoch": 1.6357865078374378, "grad_norm": 1.9808963537216187, "learning_rate": 0.00011148920809162933, "loss": 0.5524172782897949, "step": 275190 }, { "epoch": 1.6358459499141063, "grad_norm": 1.0065549612045288, "learning_rate": 0.00011148298417098104, "loss": 0.620278787612915, "step": 275200 }, { "epoch": 1.6359053919907747, "grad_norm": 1.5408495664596558, "learning_rate": 0.00011147676024323867, "loss": 0.6026579856872558, "step": 275210 }, { "epoch": 1.635964834067443, "grad_norm": 1.5266848802566528, "learning_rate": 0.00011147053630843197, "loss": 0.614981746673584, "step": 275220 }, { "epoch": 1.6360242761441115, "grad_norm": 1.5709056854248047, "learning_rate": 0.00011146431236659064, "loss": 0.5665576457977295, "step": 275230 }, { "epoch": 1.63608371822078, "grad_norm": 1.4269675016403198, "learning_rate": 0.00011145808841774459, "loss": 0.5535685539245605, "step": 275240 }, { "epoch": 1.636143160297448, "grad_norm": 1.53366219997406, "learning_rate": 0.00011145186446192353, "loss": 0.5789623260498047, "step": 275250 }, { "epoch": 1.6362026023741165, "grad_norm": 1.577144980430603, "learning_rate": 0.0001114456404991572, "loss": 0.5782039642333985, "step": 275260 }, { "epoch": 1.636262044450785, "grad_norm": 1.3591734170913696, "learning_rate": 0.00011143941652947538, "loss": 0.5489643096923829, "step": 275270 }, { "epoch": 1.6363214865274534, "grad_norm": 2.0653674602508545, "learning_rate": 0.00011143319255290788, "loss": 0.5170114517211915, "step": 275280 }, { "epoch": 1.6363809286041218, "grad_norm": 1.4317626953125, "learning_rate": 0.00011142696856948445, "loss": 0.5436447143554688, "step": 275290 }, { "epoch": 1.63644037068079, "grad_norm": 1.7121418714523315, "learning_rate": 0.00011142074457923484, "loss": 0.6370935440063477, "step": 275300 }, { "epoch": 1.6364998127574584, "grad_norm": 0.9898949265480042, "learning_rate": 0.00011141452058218889, "loss": 0.5448001384735107, "step": 275310 }, { "epoch": 1.6365592548341268, "grad_norm": 1.2241809368133545, "learning_rate": 0.00011140829657837635, "loss": 0.543453311920166, "step": 275320 }, { "epoch": 1.6366186969107952, "grad_norm": 1.213626503944397, "learning_rate": 0.00011140207256782693, "loss": 0.5550817489624024, "step": 275330 }, { "epoch": 1.6366781389874636, "grad_norm": 1.750159502029419, "learning_rate": 0.00011139584855057048, "loss": 0.5658523559570312, "step": 275340 }, { "epoch": 1.636737581064132, "grad_norm": 1.4221142530441284, "learning_rate": 0.00011138962452663677, "loss": 0.5802350044250488, "step": 275350 }, { "epoch": 1.6367970231408004, "grad_norm": 1.4498974084854126, "learning_rate": 0.00011138340049605551, "loss": 0.5508293628692627, "step": 275360 }, { "epoch": 1.6368564652174689, "grad_norm": 1.4711936712265015, "learning_rate": 0.00011137717645885652, "loss": 0.5843409538269043, "step": 275370 }, { "epoch": 1.6369159072941373, "grad_norm": 1.2823960781097412, "learning_rate": 0.00011137095241506961, "loss": 0.5767024040222168, "step": 275380 }, { "epoch": 1.6369753493708057, "grad_norm": 1.4358830451965332, "learning_rate": 0.00011136472836472446, "loss": 0.574531078338623, "step": 275390 }, { "epoch": 1.637034791447474, "grad_norm": 1.5556427240371704, "learning_rate": 0.00011135850430785093, "loss": 0.5808518409729004, "step": 275400 }, { "epoch": 1.6370942335241425, "grad_norm": 1.065610408782959, "learning_rate": 0.00011135228024447875, "loss": 0.5682690620422364, "step": 275410 }, { "epoch": 1.637153675600811, "grad_norm": 1.7253000736236572, "learning_rate": 0.0001113460561746377, "loss": 0.5973284721374512, "step": 275420 }, { "epoch": 1.6372131176774793, "grad_norm": 1.12369966506958, "learning_rate": 0.00011133983209835757, "loss": 0.5659439563751221, "step": 275430 }, { "epoch": 1.6372725597541475, "grad_norm": 1.9071422815322876, "learning_rate": 0.0001113336080156681, "loss": 0.5378579139709473, "step": 275440 }, { "epoch": 1.637332001830816, "grad_norm": 1.2088780403137207, "learning_rate": 0.00011132738392659908, "loss": 0.5195647239685058, "step": 275450 }, { "epoch": 1.6373914439074844, "grad_norm": 1.380964994430542, "learning_rate": 0.0001113211598311803, "loss": 0.5633113861083985, "step": 275460 }, { "epoch": 1.6374508859841528, "grad_norm": 1.4198461771011353, "learning_rate": 0.00011131493572944153, "loss": 0.5301670074462891, "step": 275470 }, { "epoch": 1.637510328060821, "grad_norm": 1.3273175954818726, "learning_rate": 0.00011130871162141253, "loss": 0.5598255157470703, "step": 275480 }, { "epoch": 1.6375697701374894, "grad_norm": 1.3305962085723877, "learning_rate": 0.00011130248750712306, "loss": 0.575664758682251, "step": 275490 }, { "epoch": 1.6376292122141578, "grad_norm": 1.8174303770065308, "learning_rate": 0.00011129626338660297, "loss": 0.59312744140625, "step": 275500 }, { "epoch": 1.6376886542908262, "grad_norm": 1.7282003164291382, "learning_rate": 0.00011129003925988193, "loss": 0.5849728584289551, "step": 275510 }, { "epoch": 1.6377480963674946, "grad_norm": 1.5556339025497437, "learning_rate": 0.00011128381512698978, "loss": 0.5783826828002929, "step": 275520 }, { "epoch": 1.637807538444163, "grad_norm": 1.3672895431518555, "learning_rate": 0.0001112775909879563, "loss": 0.5742412567138672, "step": 275530 }, { "epoch": 1.6378669805208315, "grad_norm": 1.4870318174362183, "learning_rate": 0.00011127136684281119, "loss": 0.5973099708557129, "step": 275540 }, { "epoch": 1.6379264225974999, "grad_norm": 1.5415680408477783, "learning_rate": 0.00011126514269158432, "loss": 0.5689879417419433, "step": 275550 }, { "epoch": 1.6379858646741683, "grad_norm": 1.3624718189239502, "learning_rate": 0.00011125891853430542, "loss": 0.573218822479248, "step": 275560 }, { "epoch": 1.6380453067508367, "grad_norm": 1.1446995735168457, "learning_rate": 0.00011125269437100426, "loss": 0.5541468620300293, "step": 275570 }, { "epoch": 1.6381047488275051, "grad_norm": 0.9176053404808044, "learning_rate": 0.0001112464702017106, "loss": 0.5243264675140381, "step": 275580 }, { "epoch": 1.6381641909041735, "grad_norm": 1.514654517173767, "learning_rate": 0.00011124024602645424, "loss": 0.6274092674255372, "step": 275590 }, { "epoch": 1.638223632980842, "grad_norm": 1.0764570236206055, "learning_rate": 0.00011123402184526496, "loss": 0.5563704490661621, "step": 275600 }, { "epoch": 1.6382830750575104, "grad_norm": 1.7278705835342407, "learning_rate": 0.00011122779765817253, "loss": 0.5580915451049805, "step": 275610 }, { "epoch": 1.6383425171341786, "grad_norm": 1.152701735496521, "learning_rate": 0.00011122157346520672, "loss": 0.5375335216522217, "step": 275620 }, { "epoch": 1.638401959210847, "grad_norm": 1.5143836736679077, "learning_rate": 0.00011121534926639727, "loss": 0.5932379722595215, "step": 275630 }, { "epoch": 1.6384614012875154, "grad_norm": 1.4509798288345337, "learning_rate": 0.00011120912506177399, "loss": 0.5724179744720459, "step": 275640 }, { "epoch": 1.6385208433641838, "grad_norm": 1.2915458679199219, "learning_rate": 0.00011120290085136669, "loss": 0.5572739601135254, "step": 275650 }, { "epoch": 1.6385802854408522, "grad_norm": 1.605102777481079, "learning_rate": 0.00011119667663520507, "loss": 0.5622849464416504, "step": 275660 }, { "epoch": 1.6386397275175204, "grad_norm": 1.5656769275665283, "learning_rate": 0.00011119045241331896, "loss": 0.6052572727203369, "step": 275670 }, { "epoch": 1.6386991695941888, "grad_norm": 1.8579519987106323, "learning_rate": 0.00011118422818573813, "loss": 0.6130177497863769, "step": 275680 }, { "epoch": 1.6387586116708572, "grad_norm": 1.2569549083709717, "learning_rate": 0.00011117800395249229, "loss": 0.554310417175293, "step": 275690 }, { "epoch": 1.6388180537475256, "grad_norm": 1.5189368724822998, "learning_rate": 0.00011117177971361127, "loss": 0.5638606071472168, "step": 275700 }, { "epoch": 1.638877495824194, "grad_norm": 1.5460691452026367, "learning_rate": 0.00011116555546912488, "loss": 0.5689924240112305, "step": 275710 }, { "epoch": 1.6389369379008625, "grad_norm": 1.364617109298706, "learning_rate": 0.00011115933121906281, "loss": 0.60274338722229, "step": 275720 }, { "epoch": 1.638996379977531, "grad_norm": 1.605029821395874, "learning_rate": 0.00011115310696345491, "loss": 0.5857554912567139, "step": 275730 }, { "epoch": 1.6390558220541993, "grad_norm": 1.3606722354888916, "learning_rate": 0.00011114688270233092, "loss": 0.5937130451202393, "step": 275740 }, { "epoch": 1.6391152641308677, "grad_norm": 1.4508320093154907, "learning_rate": 0.00011114065843572062, "loss": 0.5520221710205078, "step": 275750 }, { "epoch": 1.6391747062075361, "grad_norm": 1.6080152988433838, "learning_rate": 0.00011113443416365374, "loss": 0.5824500560760498, "step": 275760 }, { "epoch": 1.6392341482842046, "grad_norm": 1.3873482942581177, "learning_rate": 0.00011112820988616015, "loss": 0.531820011138916, "step": 275770 }, { "epoch": 1.639293590360873, "grad_norm": 1.5584235191345215, "learning_rate": 0.00011112198560326957, "loss": 0.540252685546875, "step": 275780 }, { "epoch": 1.6393530324375414, "grad_norm": 1.1875476837158203, "learning_rate": 0.00011111576131501173, "loss": 0.5328542709350585, "step": 275790 }, { "epoch": 1.6394124745142098, "grad_norm": 1.770328402519226, "learning_rate": 0.00011110953702141648, "loss": 0.6456798553466797, "step": 275800 }, { "epoch": 1.639471916590878, "grad_norm": 1.4878294467926025, "learning_rate": 0.00011110331272251357, "loss": 0.4954660892486572, "step": 275810 }, { "epoch": 1.6395313586675464, "grad_norm": 1.6936367750167847, "learning_rate": 0.00011109708841833278, "loss": 0.48851618766784666, "step": 275820 }, { "epoch": 1.6395908007442148, "grad_norm": 1.4123687744140625, "learning_rate": 0.00011109086410890388, "loss": 0.5399685859680176, "step": 275830 }, { "epoch": 1.6396502428208832, "grad_norm": 1.654016137123108, "learning_rate": 0.00011108463979425663, "loss": 0.5743154525756836, "step": 275840 }, { "epoch": 1.6397096848975514, "grad_norm": 1.5931694507598877, "learning_rate": 0.00011107841547442084, "loss": 0.5238939762115479, "step": 275850 }, { "epoch": 1.6397691269742198, "grad_norm": 1.250974178314209, "learning_rate": 0.00011107219114942621, "loss": 0.5921375274658203, "step": 275860 }, { "epoch": 1.6398285690508883, "grad_norm": 1.4756790399551392, "learning_rate": 0.00011106596681930263, "loss": 0.5929091453552247, "step": 275870 }, { "epoch": 1.6398880111275567, "grad_norm": 1.5090821981430054, "learning_rate": 0.0001110597424840798, "loss": 0.5631296157836914, "step": 275880 }, { "epoch": 1.639947453204225, "grad_norm": 1.8524963855743408, "learning_rate": 0.00011105351814378746, "loss": 0.6172346591949462, "step": 275890 }, { "epoch": 1.6400068952808935, "grad_norm": 1.4122942686080933, "learning_rate": 0.00011104729379845549, "loss": 0.5915367126464843, "step": 275900 }, { "epoch": 1.640066337357562, "grad_norm": 1.1115105152130127, "learning_rate": 0.00011104106944811357, "loss": 0.5805742263793945, "step": 275910 }, { "epoch": 1.6401257794342303, "grad_norm": 1.604933500289917, "learning_rate": 0.00011103484509279154, "loss": 0.5523333549499512, "step": 275920 }, { "epoch": 1.6401852215108987, "grad_norm": 1.8578822612762451, "learning_rate": 0.00011102862073251916, "loss": 0.5946163654327392, "step": 275930 }, { "epoch": 1.6402446635875672, "grad_norm": 1.3306734561920166, "learning_rate": 0.00011102239636732614, "loss": 0.5934414863586426, "step": 275940 }, { "epoch": 1.6403041056642356, "grad_norm": 1.224488615989685, "learning_rate": 0.00011101617199724234, "loss": 0.5259724140167237, "step": 275950 }, { "epoch": 1.640363547740904, "grad_norm": 1.2175637483596802, "learning_rate": 0.00011100994762229753, "loss": 0.5498324394226074, "step": 275960 }, { "epoch": 1.6404229898175724, "grad_norm": 1.3461506366729736, "learning_rate": 0.00011100372324252144, "loss": 0.5487937927246094, "step": 275970 }, { "epoch": 1.6404824318942408, "grad_norm": 1.1586170196533203, "learning_rate": 0.00011099749885794387, "loss": 0.563258171081543, "step": 275980 }, { "epoch": 1.640541873970909, "grad_norm": 1.6130653619766235, "learning_rate": 0.00011099127446859459, "loss": 0.583890438079834, "step": 275990 }, { "epoch": 1.6406013160475774, "grad_norm": 1.7356717586517334, "learning_rate": 0.00011098505007450335, "loss": 0.5380438804626465, "step": 276000 }, { "epoch": 1.6406607581242458, "grad_norm": 1.438375473022461, "learning_rate": 0.00011097882567569999, "loss": 0.5896502494812011, "step": 276010 }, { "epoch": 1.6407202002009142, "grad_norm": 1.3212246894836426, "learning_rate": 0.00011097260127221425, "loss": 0.5148902893066406, "step": 276020 }, { "epoch": 1.6407796422775827, "grad_norm": 1.3730149269104004, "learning_rate": 0.00011096637686407584, "loss": 0.5906776428222656, "step": 276030 }, { "epoch": 1.6408390843542509, "grad_norm": 1.6416873931884766, "learning_rate": 0.00011096015245131468, "loss": 0.6141880035400391, "step": 276040 }, { "epoch": 1.6408985264309193, "grad_norm": 1.5007898807525635, "learning_rate": 0.00011095392803396041, "loss": 0.547600269317627, "step": 276050 }, { "epoch": 1.6409579685075877, "grad_norm": 1.3461896181106567, "learning_rate": 0.00011094770361204289, "loss": 0.5381853580474854, "step": 276060 }, { "epoch": 1.641017410584256, "grad_norm": 1.322670817375183, "learning_rate": 0.00011094147918559183, "loss": 0.5419872283935547, "step": 276070 }, { "epoch": 1.6410768526609245, "grad_norm": 1.4401593208312988, "learning_rate": 0.00011093525475463711, "loss": 0.5544413566589356, "step": 276080 }, { "epoch": 1.641136294737593, "grad_norm": 1.5866068601608276, "learning_rate": 0.00011092903031920839, "loss": 0.6005751609802246, "step": 276090 }, { "epoch": 1.6411957368142613, "grad_norm": 1.1705206632614136, "learning_rate": 0.00011092280587933548, "loss": 0.548495864868164, "step": 276100 }, { "epoch": 1.6412551788909298, "grad_norm": 1.1406714916229248, "learning_rate": 0.0001109165814350482, "loss": 0.5379368305206299, "step": 276110 }, { "epoch": 1.6413146209675982, "grad_norm": 1.6666522026062012, "learning_rate": 0.00011091035698637628, "loss": 0.564298677444458, "step": 276120 }, { "epoch": 1.6413740630442666, "grad_norm": 1.4265280961990356, "learning_rate": 0.00011090413253334948, "loss": 0.5522011756896973, "step": 276130 }, { "epoch": 1.641433505120935, "grad_norm": 1.4209749698638916, "learning_rate": 0.00011089790807599768, "loss": 0.5884711742401123, "step": 276140 }, { "epoch": 1.6414929471976034, "grad_norm": 1.844125747680664, "learning_rate": 0.00011089168361435052, "loss": 0.6203615188598632, "step": 276150 }, { "epoch": 1.6415523892742718, "grad_norm": 1.3549396991729736, "learning_rate": 0.00011088545914843786, "loss": 0.5764601707458497, "step": 276160 }, { "epoch": 1.6416118313509402, "grad_norm": 1.3649451732635498, "learning_rate": 0.00011087923467828945, "loss": 0.5955501556396484, "step": 276170 }, { "epoch": 1.6416712734276084, "grad_norm": 1.2415984869003296, "learning_rate": 0.00011087301020393506, "loss": 0.5386391162872315, "step": 276180 }, { "epoch": 1.6417307155042768, "grad_norm": 1.5279544591903687, "learning_rate": 0.00011086678572540448, "loss": 0.6032050132751465, "step": 276190 }, { "epoch": 1.6417901575809453, "grad_norm": 1.6125198602676392, "learning_rate": 0.00011086056124272748, "loss": 0.6064569473266601, "step": 276200 }, { "epoch": 1.6418495996576137, "grad_norm": 1.4196422100067139, "learning_rate": 0.0001108543367559338, "loss": 0.5864098072052002, "step": 276210 }, { "epoch": 1.6419090417342819, "grad_norm": 1.458310604095459, "learning_rate": 0.0001108481122650533, "loss": 0.5804649353027344, "step": 276220 }, { "epoch": 1.6419684838109503, "grad_norm": 1.591052770614624, "learning_rate": 0.0001108418877701157, "loss": 0.5575214385986328, "step": 276230 }, { "epoch": 1.6420279258876187, "grad_norm": 1.2870701551437378, "learning_rate": 0.00011083566327115078, "loss": 0.6257946014404296, "step": 276240 }, { "epoch": 1.6420873679642871, "grad_norm": 1.3277579545974731, "learning_rate": 0.00011082943876818832, "loss": 0.562154483795166, "step": 276250 }, { "epoch": 1.6421468100409555, "grad_norm": 1.680465817451477, "learning_rate": 0.0001108232142612581, "loss": 0.6090377807617188, "step": 276260 }, { "epoch": 1.642206252117624, "grad_norm": 1.4449213743209839, "learning_rate": 0.00011081698975038987, "loss": 0.557828140258789, "step": 276270 }, { "epoch": 1.6422656941942924, "grad_norm": 1.5116844177246094, "learning_rate": 0.00011081076523561345, "loss": 0.5778992176055908, "step": 276280 }, { "epoch": 1.6423251362709608, "grad_norm": 1.4217642545700073, "learning_rate": 0.0001108045407169586, "loss": 0.5904272079467774, "step": 276290 }, { "epoch": 1.6423845783476292, "grad_norm": 1.4483686685562134, "learning_rate": 0.00011079831619445509, "loss": 0.5654995441436768, "step": 276300 }, { "epoch": 1.6424440204242976, "grad_norm": 1.7617418766021729, "learning_rate": 0.00011079209166813267, "loss": 0.5874453544616699, "step": 276310 }, { "epoch": 1.642503462500966, "grad_norm": 1.6153812408447266, "learning_rate": 0.00011078586713802117, "loss": 0.5662247657775878, "step": 276320 }, { "epoch": 1.6425629045776344, "grad_norm": 1.54292631149292, "learning_rate": 0.00011077964260415033, "loss": 0.5765522003173829, "step": 276330 }, { "epoch": 1.6426223466543028, "grad_norm": 1.6072295904159546, "learning_rate": 0.00011077341806654993, "loss": 0.538529920578003, "step": 276340 }, { "epoch": 1.6426817887309713, "grad_norm": 1.4533395767211914, "learning_rate": 0.00011076719352524973, "loss": 0.557294225692749, "step": 276350 }, { "epoch": 1.6427412308076395, "grad_norm": 1.376768946647644, "learning_rate": 0.00011076096898027956, "loss": 0.5643686294555664, "step": 276360 }, { "epoch": 1.6428006728843079, "grad_norm": 1.8957853317260742, "learning_rate": 0.00011075474443166916, "loss": 0.541961669921875, "step": 276370 }, { "epoch": 1.6428601149609763, "grad_norm": 1.6047639846801758, "learning_rate": 0.00011074851987944828, "loss": 0.5517267227172852, "step": 276380 }, { "epoch": 1.6429195570376447, "grad_norm": 1.16178560256958, "learning_rate": 0.00011074229532364675, "loss": 0.6399234771728516, "step": 276390 }, { "epoch": 1.642978999114313, "grad_norm": 1.821085810661316, "learning_rate": 0.00011073607076429433, "loss": 0.5449093341827392, "step": 276400 }, { "epoch": 1.6430384411909813, "grad_norm": 1.536071538925171, "learning_rate": 0.00011072984620142077, "loss": 0.5572028160095215, "step": 276410 }, { "epoch": 1.6430978832676497, "grad_norm": 2.0347838401794434, "learning_rate": 0.0001107236216350559, "loss": 0.5875718116760253, "step": 276420 }, { "epoch": 1.6431573253443181, "grad_norm": 1.5062555074691772, "learning_rate": 0.00011071739706522941, "loss": 0.5367188453674316, "step": 276430 }, { "epoch": 1.6432167674209865, "grad_norm": 1.3923662900924683, "learning_rate": 0.00011071117249197114, "loss": 0.5372150421142579, "step": 276440 }, { "epoch": 1.643276209497655, "grad_norm": 1.2995840311050415, "learning_rate": 0.00011070494791531089, "loss": 0.6059849739074707, "step": 276450 }, { "epoch": 1.6433356515743234, "grad_norm": 1.2310540676116943, "learning_rate": 0.00011069872333527833, "loss": 0.561732292175293, "step": 276460 }, { "epoch": 1.6433950936509918, "grad_norm": 1.2924329042434692, "learning_rate": 0.00011069249875190337, "loss": 0.5637702465057373, "step": 276470 }, { "epoch": 1.6434545357276602, "grad_norm": 1.4118919372558594, "learning_rate": 0.00011068627416521571, "loss": 0.5688416004180908, "step": 276480 }, { "epoch": 1.6435139778043286, "grad_norm": 1.750231146812439, "learning_rate": 0.00011068004957524512, "loss": 0.5447588920593261, "step": 276490 }, { "epoch": 1.643573419880997, "grad_norm": 1.408875823020935, "learning_rate": 0.00011067382498202139, "loss": 0.5809832096099854, "step": 276500 }, { "epoch": 1.6436328619576654, "grad_norm": 1.323028326034546, "learning_rate": 0.00011066760038557433, "loss": 0.547602367401123, "step": 276510 }, { "epoch": 1.6436923040343339, "grad_norm": 1.6123912334442139, "learning_rate": 0.00011066137578593368, "loss": 0.639601182937622, "step": 276520 }, { "epoch": 1.6437517461110023, "grad_norm": 1.7729815244674683, "learning_rate": 0.0001106551511831292, "loss": 0.5247281074523926, "step": 276530 }, { "epoch": 1.6438111881876705, "grad_norm": 1.5322526693344116, "learning_rate": 0.00011064892657719071, "loss": 0.60881028175354, "step": 276540 }, { "epoch": 1.6438706302643389, "grad_norm": 1.5518356561660767, "learning_rate": 0.00011064270196814797, "loss": 0.5920703411102295, "step": 276550 }, { "epoch": 1.6439300723410073, "grad_norm": 1.3209617137908936, "learning_rate": 0.00011063647735603074, "loss": 0.6031042098999023, "step": 276560 }, { "epoch": 1.6439895144176757, "grad_norm": 1.267138123512268, "learning_rate": 0.00011063025274086882, "loss": 0.5399645328521728, "step": 276570 }, { "epoch": 1.6440489564943441, "grad_norm": 1.2620611190795898, "learning_rate": 0.00011062402812269199, "loss": 0.516363525390625, "step": 276580 }, { "epoch": 1.6441083985710123, "grad_norm": 1.6692990064620972, "learning_rate": 0.00011061780350152999, "loss": 0.5614775657653809, "step": 276590 }, { "epoch": 1.6441678406476807, "grad_norm": 1.7675708532333374, "learning_rate": 0.00011061157887741263, "loss": 0.575623893737793, "step": 276600 }, { "epoch": 1.6442272827243491, "grad_norm": 1.7770791053771973, "learning_rate": 0.00011060535425036967, "loss": 0.5857096672058105, "step": 276610 }, { "epoch": 1.6442867248010176, "grad_norm": 1.5952175855636597, "learning_rate": 0.00011059912962043089, "loss": 0.620300579071045, "step": 276620 }, { "epoch": 1.644346166877686, "grad_norm": 1.610098123550415, "learning_rate": 0.00011059290498762609, "loss": 0.5347396850585937, "step": 276630 }, { "epoch": 1.6444056089543544, "grad_norm": 1.5333538055419922, "learning_rate": 0.00011058668035198502, "loss": 0.5623720169067383, "step": 276640 }, { "epoch": 1.6444650510310228, "grad_norm": 1.2349421977996826, "learning_rate": 0.00011058045571353745, "loss": 0.596532154083252, "step": 276650 }, { "epoch": 1.6445244931076912, "grad_norm": 1.2915781736373901, "learning_rate": 0.00011057423107231317, "loss": 0.5433600425720215, "step": 276660 }, { "epoch": 1.6445839351843596, "grad_norm": 1.3619801998138428, "learning_rate": 0.00011056800642834198, "loss": 0.5864060878753662, "step": 276670 }, { "epoch": 1.644643377261028, "grad_norm": 1.926632046699524, "learning_rate": 0.00011056178178165362, "loss": 0.5555158615112304, "step": 276680 }, { "epoch": 1.6447028193376965, "grad_norm": 1.554801106452942, "learning_rate": 0.00011055555713227785, "loss": 0.5621824264526367, "step": 276690 }, { "epoch": 1.6447622614143649, "grad_norm": 1.3136895895004272, "learning_rate": 0.00011054933248024452, "loss": 0.5417580604553223, "step": 276700 }, { "epoch": 1.6448217034910333, "grad_norm": 1.1457568407058716, "learning_rate": 0.00011054310782558334, "loss": 0.5654296398162841, "step": 276710 }, { "epoch": 1.6448811455677017, "grad_norm": 1.505152940750122, "learning_rate": 0.00011053688316832412, "loss": 0.5414286613464355, "step": 276720 }, { "epoch": 1.64494058764437, "grad_norm": 1.701231837272644, "learning_rate": 0.00011053065850849665, "loss": 0.574530553817749, "step": 276730 }, { "epoch": 1.6450000297210383, "grad_norm": 1.4215883016586304, "learning_rate": 0.00011052443384613063, "loss": 0.545345401763916, "step": 276740 }, { "epoch": 1.6450594717977067, "grad_norm": 1.3632910251617432, "learning_rate": 0.00011051820918125592, "loss": 0.6289697170257569, "step": 276750 }, { "epoch": 1.6451189138743751, "grad_norm": 1.6966710090637207, "learning_rate": 0.00011051198451390226, "loss": 0.5844062805175781, "step": 276760 }, { "epoch": 1.6451783559510436, "grad_norm": 1.5203665494918823, "learning_rate": 0.00011050575984409941, "loss": 0.579372501373291, "step": 276770 }, { "epoch": 1.6452377980277118, "grad_norm": 1.4672996997833252, "learning_rate": 0.0001104995351718772, "loss": 0.5547025680541993, "step": 276780 }, { "epoch": 1.6452972401043802, "grad_norm": 1.5696879625320435, "learning_rate": 0.00011049331049726539, "loss": 0.5551276206970215, "step": 276790 }, { "epoch": 1.6453566821810486, "grad_norm": 1.3297632932662964, "learning_rate": 0.00011048708582029372, "loss": 0.5794810771942138, "step": 276800 }, { "epoch": 1.645416124257717, "grad_norm": 1.5431655645370483, "learning_rate": 0.00011048086114099198, "loss": 0.616606330871582, "step": 276810 }, { "epoch": 1.6454755663343854, "grad_norm": 1.6970406770706177, "learning_rate": 0.00011047463645938998, "loss": 0.49272842407226564, "step": 276820 }, { "epoch": 1.6455350084110538, "grad_norm": 1.3465332984924316, "learning_rate": 0.00011046841177551748, "loss": 0.5373208522796631, "step": 276830 }, { "epoch": 1.6455944504877222, "grad_norm": 1.4936003684997559, "learning_rate": 0.00011046218708940423, "loss": 0.5764317512512207, "step": 276840 }, { "epoch": 1.6456538925643907, "grad_norm": 1.297291874885559, "learning_rate": 0.00011045596240108005, "loss": 0.5830406188964844, "step": 276850 }, { "epoch": 1.645713334641059, "grad_norm": 1.19019615650177, "learning_rate": 0.00011044973771057467, "loss": 0.576259994506836, "step": 276860 }, { "epoch": 1.6457727767177275, "grad_norm": 1.4525132179260254, "learning_rate": 0.00011044351301791791, "loss": 0.579963207244873, "step": 276870 }, { "epoch": 1.645832218794396, "grad_norm": 1.375223159790039, "learning_rate": 0.0001104372883231395, "loss": 0.5655169486999512, "step": 276880 }, { "epoch": 1.6458916608710643, "grad_norm": 1.4618619680404663, "learning_rate": 0.00011043106362626929, "loss": 0.5707358360290528, "step": 276890 }, { "epoch": 1.6459511029477327, "grad_norm": 1.350365400314331, "learning_rate": 0.00011042483892733697, "loss": 0.513913345336914, "step": 276900 }, { "epoch": 1.646010545024401, "grad_norm": 1.3954182863235474, "learning_rate": 0.00011041861422637241, "loss": 0.5352930068969727, "step": 276910 }, { "epoch": 1.6460699871010693, "grad_norm": 1.2485820055007935, "learning_rate": 0.0001104123895234053, "loss": 0.6111276626586915, "step": 276920 }, { "epoch": 1.6461294291777377, "grad_norm": 1.134250283241272, "learning_rate": 0.00011040616481846543, "loss": 0.6158297538757325, "step": 276930 }, { "epoch": 1.6461888712544062, "grad_norm": 1.3318467140197754, "learning_rate": 0.00011039994011158265, "loss": 0.5649487018585205, "step": 276940 }, { "epoch": 1.6462483133310746, "grad_norm": 1.247066855430603, "learning_rate": 0.00011039371540278665, "loss": 0.5895149230957031, "step": 276950 }, { "epoch": 1.6463077554077428, "grad_norm": 1.6773412227630615, "learning_rate": 0.00011038749069210728, "loss": 0.573631477355957, "step": 276960 }, { "epoch": 1.6463671974844112, "grad_norm": 1.7892699241638184, "learning_rate": 0.00011038126597957427, "loss": 0.6482488632202148, "step": 276970 }, { "epoch": 1.6464266395610796, "grad_norm": 1.5015618801116943, "learning_rate": 0.00011037504126521738, "loss": 0.531673812866211, "step": 276980 }, { "epoch": 1.646486081637748, "grad_norm": 1.4163718223571777, "learning_rate": 0.00011036881654906644, "loss": 0.5673795700073242, "step": 276990 }, { "epoch": 1.6465455237144164, "grad_norm": 1.4677144289016724, "learning_rate": 0.00011036259183115121, "loss": 0.6027175426483155, "step": 277000 }, { "epoch": 1.6466049657910848, "grad_norm": 1.2827162742614746, "learning_rate": 0.00011035636711150146, "loss": 0.49942827224731445, "step": 277010 }, { "epoch": 1.6466644078677533, "grad_norm": 1.0883374214172363, "learning_rate": 0.00011035014239014694, "loss": 0.5688807010650635, "step": 277020 }, { "epoch": 1.6467238499444217, "grad_norm": 1.3940776586532593, "learning_rate": 0.00011034391766711746, "loss": 0.5731526851654053, "step": 277030 }, { "epoch": 1.64678329202109, "grad_norm": 1.1684050559997559, "learning_rate": 0.0001103376929424428, "loss": 0.5379708290100098, "step": 277040 }, { "epoch": 1.6468427340977585, "grad_norm": 1.6847742795944214, "learning_rate": 0.0001103314682161527, "loss": 0.5618887424468995, "step": 277050 }, { "epoch": 1.646902176174427, "grad_norm": 1.7506049871444702, "learning_rate": 0.000110325243488277, "loss": 0.611072301864624, "step": 277060 }, { "epoch": 1.6469616182510953, "grad_norm": 1.4529993534088135, "learning_rate": 0.00011031901875884543, "loss": 0.562591552734375, "step": 277070 }, { "epoch": 1.6470210603277637, "grad_norm": 1.0899461507797241, "learning_rate": 0.00011031279402788776, "loss": 0.5531449794769288, "step": 277080 }, { "epoch": 1.6470805024044322, "grad_norm": 2.6279828548431396, "learning_rate": 0.00011030656929543383, "loss": 0.5546344757080078, "step": 277090 }, { "epoch": 1.6471399444811003, "grad_norm": 1.8341583013534546, "learning_rate": 0.00011030034456151335, "loss": 0.5682871818542481, "step": 277100 }, { "epoch": 1.6471993865577688, "grad_norm": 1.553434133529663, "learning_rate": 0.00011029411982615609, "loss": 0.5881730079650879, "step": 277110 }, { "epoch": 1.6472588286344372, "grad_norm": 1.4498528242111206, "learning_rate": 0.0001102878950893919, "loss": 0.5526755809783935, "step": 277120 }, { "epoch": 1.6473182707111056, "grad_norm": 1.5587459802627563, "learning_rate": 0.0001102816703512505, "loss": 0.5622461318969727, "step": 277130 }, { "epoch": 1.647377712787774, "grad_norm": 1.2202826738357544, "learning_rate": 0.00011027544561176168, "loss": 0.5021018028259278, "step": 277140 }, { "epoch": 1.6474371548644422, "grad_norm": 1.4286655187606812, "learning_rate": 0.00011026922087095522, "loss": 0.5268435001373291, "step": 277150 }, { "epoch": 1.6474965969411106, "grad_norm": 1.4255599975585938, "learning_rate": 0.00011026299612886088, "loss": 0.6034140586853027, "step": 277160 }, { "epoch": 1.647556039017779, "grad_norm": 1.2609854936599731, "learning_rate": 0.00011025677138550847, "loss": 0.5530031681060791, "step": 277170 }, { "epoch": 1.6476154810944474, "grad_norm": 1.768614649772644, "learning_rate": 0.00011025054664092774, "loss": 0.5719242095947266, "step": 277180 }, { "epoch": 1.6476749231711159, "grad_norm": 1.4274412393569946, "learning_rate": 0.0001102443218951485, "loss": 0.6146974086761474, "step": 277190 }, { "epoch": 1.6477343652477843, "grad_norm": 1.337843894958496, "learning_rate": 0.00011023809714820048, "loss": 0.5644759178161621, "step": 277200 }, { "epoch": 1.6477938073244527, "grad_norm": 1.4694654941558838, "learning_rate": 0.00011023187240011346, "loss": 0.5451465606689453, "step": 277210 }, { "epoch": 1.647853249401121, "grad_norm": 1.3691902160644531, "learning_rate": 0.0001102256476509173, "loss": 0.6014822959899903, "step": 277220 }, { "epoch": 1.6479126914777895, "grad_norm": 1.4591491222381592, "learning_rate": 0.00011021942290064164, "loss": 0.5875850677490234, "step": 277230 }, { "epoch": 1.647972133554458, "grad_norm": 1.2999716997146606, "learning_rate": 0.00011021319814931638, "loss": 0.5547297477722168, "step": 277240 }, { "epoch": 1.6480315756311263, "grad_norm": 1.5854991674423218, "learning_rate": 0.00011020697339697126, "loss": 0.5722686767578125, "step": 277250 }, { "epoch": 1.6480910177077948, "grad_norm": 1.33655846118927, "learning_rate": 0.00011020074864363602, "loss": 0.5823952674865722, "step": 277260 }, { "epoch": 1.6481504597844632, "grad_norm": 1.2651787996292114, "learning_rate": 0.00011019452388934046, "loss": 0.5554853916168213, "step": 277270 }, { "epoch": 1.6482099018611314, "grad_norm": 1.2377588748931885, "learning_rate": 0.00011018829913411439, "loss": 0.5503117561340332, "step": 277280 }, { "epoch": 1.6482693439377998, "grad_norm": 1.1673946380615234, "learning_rate": 0.00011018207437798753, "loss": 0.5503070831298829, "step": 277290 }, { "epoch": 1.6483287860144682, "grad_norm": 1.487979531288147, "learning_rate": 0.0001101758496209897, "loss": 0.5905231475830078, "step": 277300 }, { "epoch": 1.6483882280911366, "grad_norm": 1.310217022895813, "learning_rate": 0.00011016962486315065, "loss": 0.5736057758331299, "step": 277310 }, { "epoch": 1.648447670167805, "grad_norm": 1.5138647556304932, "learning_rate": 0.00011016340010450021, "loss": 0.5945841789245605, "step": 277320 }, { "epoch": 1.6485071122444732, "grad_norm": 1.3618946075439453, "learning_rate": 0.00011015717534506806, "loss": 0.5202981948852539, "step": 277330 }, { "epoch": 1.6485665543211416, "grad_norm": 1.4765913486480713, "learning_rate": 0.00011015095058488408, "loss": 0.5559278011322022, "step": 277340 }, { "epoch": 1.64862599639781, "grad_norm": 1.1699934005737305, "learning_rate": 0.000110144725823978, "loss": 0.5719513893127441, "step": 277350 }, { "epoch": 1.6486854384744785, "grad_norm": 1.2383328676223755, "learning_rate": 0.00011013850106237956, "loss": 0.606206750869751, "step": 277360 }, { "epoch": 1.6487448805511469, "grad_norm": 1.4166851043701172, "learning_rate": 0.0001101322763001186, "loss": 0.5410222053527832, "step": 277370 }, { "epoch": 1.6488043226278153, "grad_norm": 1.3601312637329102, "learning_rate": 0.00011012605153722488, "loss": 0.5636051177978516, "step": 277380 }, { "epoch": 1.6488637647044837, "grad_norm": 1.5266722440719604, "learning_rate": 0.00011011982677372814, "loss": 0.5671913623809814, "step": 277390 }, { "epoch": 1.6489232067811521, "grad_norm": 1.5032724142074585, "learning_rate": 0.00011011360200965824, "loss": 0.5628632068634033, "step": 277400 }, { "epoch": 1.6489826488578205, "grad_norm": 1.779741644859314, "learning_rate": 0.00011010737724504488, "loss": 0.556026029586792, "step": 277410 }, { "epoch": 1.649042090934489, "grad_norm": 1.4843131303787231, "learning_rate": 0.0001101011524799178, "loss": 0.5851944923400879, "step": 277420 }, { "epoch": 1.6491015330111574, "grad_norm": 1.7527931928634644, "learning_rate": 0.00011009492771430697, "loss": 0.49245872497558596, "step": 277430 }, { "epoch": 1.6491609750878258, "grad_norm": 1.4615901708602905, "learning_rate": 0.00011008870294824194, "loss": 0.524786376953125, "step": 277440 }, { "epoch": 1.6492204171644942, "grad_norm": 1.4668289422988892, "learning_rate": 0.00011008247818175261, "loss": 0.5602015495300293, "step": 277450 }, { "epoch": 1.6492798592411626, "grad_norm": 1.4051626920700073, "learning_rate": 0.00011007625341486874, "loss": 0.6009103775024414, "step": 277460 }, { "epoch": 1.6493393013178308, "grad_norm": 1.4935423135757446, "learning_rate": 0.00011007002864762006, "loss": 0.5792448997497559, "step": 277470 }, { "epoch": 1.6493987433944992, "grad_norm": 1.3517175912857056, "learning_rate": 0.00011006380388003644, "loss": 0.59874267578125, "step": 277480 }, { "epoch": 1.6494581854711676, "grad_norm": 1.6919963359832764, "learning_rate": 0.00011005757911214758, "loss": 0.5970516204833984, "step": 277490 }, { "epoch": 1.649517627547836, "grad_norm": 1.4863386154174805, "learning_rate": 0.00011005135434398328, "loss": 0.6069777488708497, "step": 277500 }, { "epoch": 1.6495770696245045, "grad_norm": 1.2880041599273682, "learning_rate": 0.00011004512957557329, "loss": 0.5761062622070312, "step": 277510 }, { "epoch": 1.6496365117011726, "grad_norm": 1.2745202779769897, "learning_rate": 0.00011003890480694747, "loss": 0.5996500492095947, "step": 277520 }, { "epoch": 1.649695953777841, "grad_norm": 1.3732904195785522, "learning_rate": 0.0001100326800381355, "loss": 0.5577629566192627, "step": 277530 }, { "epoch": 1.6497553958545095, "grad_norm": 1.351544737815857, "learning_rate": 0.0001100264552691672, "loss": 0.6175459861755371, "step": 277540 }, { "epoch": 1.649814837931178, "grad_norm": 1.4884583950042725, "learning_rate": 0.00011002023050007238, "loss": 0.5648743152618408, "step": 277550 }, { "epoch": 1.6498742800078463, "grad_norm": 1.5251691341400146, "learning_rate": 0.00011001400573088077, "loss": 0.5570296287536621, "step": 277560 }, { "epoch": 1.6499337220845147, "grad_norm": 1.677712321281433, "learning_rate": 0.00011000778096162212, "loss": 0.5473331451416016, "step": 277570 }, { "epoch": 1.6499931641611831, "grad_norm": 1.6365469694137573, "learning_rate": 0.00011000155619232628, "loss": 0.6142608642578125, "step": 277580 }, { "epoch": 1.6500526062378515, "grad_norm": 1.6554046869277954, "learning_rate": 0.00010999533142302305, "loss": 0.5747788429260254, "step": 277590 }, { "epoch": 1.65011204831452, "grad_norm": 1.3010108470916748, "learning_rate": 0.00010998910665374205, "loss": 0.5787534236907959, "step": 277600 }, { "epoch": 1.6501714903911884, "grad_norm": 1.6130998134613037, "learning_rate": 0.00010998288188451323, "loss": 0.5547701358795166, "step": 277610 }, { "epoch": 1.6502309324678568, "grad_norm": 1.3929951190948486, "learning_rate": 0.00010997665711536632, "loss": 0.5759584426879882, "step": 277620 }, { "epoch": 1.6502903745445252, "grad_norm": 1.5971235036849976, "learning_rate": 0.00010997043234633097, "loss": 0.5685603141784668, "step": 277630 }, { "epoch": 1.6503498166211936, "grad_norm": 1.397855281829834, "learning_rate": 0.00010996420757743715, "loss": 0.5732288360595703, "step": 277640 }, { "epoch": 1.6504092586978618, "grad_norm": 1.1150081157684326, "learning_rate": 0.00010995798280871454, "loss": 0.5771299362182617, "step": 277650 }, { "epoch": 1.6504687007745302, "grad_norm": 1.1722177267074585, "learning_rate": 0.00010995175804019289, "loss": 0.5452316284179688, "step": 277660 }, { "epoch": 1.6505281428511986, "grad_norm": 1.3074142932891846, "learning_rate": 0.00010994553327190202, "loss": 0.5377104759216309, "step": 277670 }, { "epoch": 1.650587584927867, "grad_norm": 1.162361741065979, "learning_rate": 0.00010993930850387175, "loss": 0.5430672645568848, "step": 277680 }, { "epoch": 1.6506470270045355, "grad_norm": 1.3154634237289429, "learning_rate": 0.00010993308373613174, "loss": 0.5095135688781738, "step": 277690 }, { "epoch": 1.6507064690812037, "grad_norm": 1.1818927526474, "learning_rate": 0.00010992685896871189, "loss": 0.542358684539795, "step": 277700 }, { "epoch": 1.650765911157872, "grad_norm": 1.4086002111434937, "learning_rate": 0.00010992063420164192, "loss": 0.553412389755249, "step": 277710 }, { "epoch": 1.6508253532345405, "grad_norm": 1.4795325994491577, "learning_rate": 0.00010991440943495159, "loss": 0.5588749408721924, "step": 277720 }, { "epoch": 1.650884795311209, "grad_norm": 1.8298132419586182, "learning_rate": 0.00010990818466867067, "loss": 0.5424908638000489, "step": 277730 }, { "epoch": 1.6509442373878773, "grad_norm": 1.8570916652679443, "learning_rate": 0.00010990195990282903, "loss": 0.558804702758789, "step": 277740 }, { "epoch": 1.6510036794645457, "grad_norm": 1.2167695760726929, "learning_rate": 0.00010989573513745635, "loss": 0.5689465522766113, "step": 277750 }, { "epoch": 1.6510631215412142, "grad_norm": 1.6701048612594604, "learning_rate": 0.00010988951037258239, "loss": 0.5628051280975341, "step": 277760 }, { "epoch": 1.6511225636178826, "grad_norm": 1.6192370653152466, "learning_rate": 0.00010988328560823704, "loss": 0.6340165138244629, "step": 277770 }, { "epoch": 1.651182005694551, "grad_norm": 1.6854262351989746, "learning_rate": 0.00010987706084445002, "loss": 0.5397731781005859, "step": 277780 }, { "epoch": 1.6512414477712194, "grad_norm": 1.314486026763916, "learning_rate": 0.00010987083608125104, "loss": 0.5442573547363281, "step": 277790 }, { "epoch": 1.6513008898478878, "grad_norm": 1.7979174852371216, "learning_rate": 0.00010986461131866999, "loss": 0.5980063438415527, "step": 277800 }, { "epoch": 1.6513603319245562, "grad_norm": 1.4251904487609863, "learning_rate": 0.00010985838655673659, "loss": 0.5468598365783691, "step": 277810 }, { "epoch": 1.6514197740012246, "grad_norm": 1.4856443405151367, "learning_rate": 0.00010985216179548057, "loss": 0.6395852088928222, "step": 277820 }, { "epoch": 1.651479216077893, "grad_norm": 1.2735458612442017, "learning_rate": 0.00010984593703493183, "loss": 0.5490410804748536, "step": 277830 }, { "epoch": 1.6515386581545612, "grad_norm": 1.2858351469039917, "learning_rate": 0.00010983971227512006, "loss": 0.6090326309204102, "step": 277840 }, { "epoch": 1.6515981002312297, "grad_norm": 1.4943817853927612, "learning_rate": 0.00010983348751607505, "loss": 0.6013531684875488, "step": 277850 }, { "epoch": 1.651657542307898, "grad_norm": 1.3228389024734497, "learning_rate": 0.00010982726275782656, "loss": 0.5563840866088867, "step": 277860 }, { "epoch": 1.6517169843845665, "grad_norm": 1.8096380233764648, "learning_rate": 0.0001098210380004044, "loss": 0.5860557079315185, "step": 277870 }, { "epoch": 1.651776426461235, "grad_norm": 1.9663960933685303, "learning_rate": 0.00010981481324383834, "loss": 0.6037261009216308, "step": 277880 }, { "epoch": 1.651835868537903, "grad_norm": 1.3158512115478516, "learning_rate": 0.00010980858848815814, "loss": 0.5042176246643066, "step": 277890 }, { "epoch": 1.6518953106145715, "grad_norm": 1.3669002056121826, "learning_rate": 0.00010980236373339361, "loss": 0.5642345428466797, "step": 277900 }, { "epoch": 1.65195475269124, "grad_norm": 1.4233407974243164, "learning_rate": 0.0001097961389795745, "loss": 0.610011100769043, "step": 277910 }, { "epoch": 1.6520141947679083, "grad_norm": 1.5160248279571533, "learning_rate": 0.00010978991422673058, "loss": 0.5609280586242675, "step": 277920 }, { "epoch": 1.6520736368445768, "grad_norm": 1.3155361413955688, "learning_rate": 0.00010978368947489167, "loss": 0.5521743774414063, "step": 277930 }, { "epoch": 1.6521330789212452, "grad_norm": 1.9301934242248535, "learning_rate": 0.0001097774647240875, "loss": 0.6162209510803223, "step": 277940 }, { "epoch": 1.6521925209979136, "grad_norm": 1.3337682485580444, "learning_rate": 0.00010977123997434786, "loss": 0.5183979034423828, "step": 277950 }, { "epoch": 1.652251963074582, "grad_norm": 1.5674015283584595, "learning_rate": 0.00010976501522570252, "loss": 0.540297269821167, "step": 277960 }, { "epoch": 1.6523114051512504, "grad_norm": 1.3540034294128418, "learning_rate": 0.00010975879047818131, "loss": 0.6191987037658692, "step": 277970 }, { "epoch": 1.6523708472279188, "grad_norm": 1.604921817779541, "learning_rate": 0.00010975256573181396, "loss": 0.5334521770477295, "step": 277980 }, { "epoch": 1.6524302893045872, "grad_norm": 1.2568310499191284, "learning_rate": 0.00010974634098663024, "loss": 0.5982855796813965, "step": 277990 }, { "epoch": 1.6524897313812557, "grad_norm": 1.4135323762893677, "learning_rate": 0.00010974011624265994, "loss": 0.6098073959350586, "step": 278000 }, { "epoch": 1.652549173457924, "grad_norm": 1.3184200525283813, "learning_rate": 0.00010973389149993288, "loss": 0.5634759426116943, "step": 278010 }, { "epoch": 1.6526086155345923, "grad_norm": 1.4270193576812744, "learning_rate": 0.00010972766675847873, "loss": 0.5771039962768555, "step": 278020 }, { "epoch": 1.6526680576112607, "grad_norm": 1.161907434463501, "learning_rate": 0.00010972144201832736, "loss": 0.5491319179534913, "step": 278030 }, { "epoch": 1.652727499687929, "grad_norm": 1.6981767416000366, "learning_rate": 0.00010971521727950853, "loss": 0.6037525177001953, "step": 278040 }, { "epoch": 1.6527869417645975, "grad_norm": 1.5584890842437744, "learning_rate": 0.000109708992542052, "loss": 0.5293549537658692, "step": 278050 }, { "epoch": 1.652846383841266, "grad_norm": 1.8836253881454468, "learning_rate": 0.00010970276780598756, "loss": 0.5538018703460693, "step": 278060 }, { "epoch": 1.6529058259179341, "grad_norm": 1.0890998840332031, "learning_rate": 0.00010969654307134498, "loss": 0.5754347801208496, "step": 278070 }, { "epoch": 1.6529652679946025, "grad_norm": 1.462759017944336, "learning_rate": 0.00010969031833815406, "loss": 0.5773399829864502, "step": 278080 }, { "epoch": 1.653024710071271, "grad_norm": 1.2827074527740479, "learning_rate": 0.00010968409360644451, "loss": 0.5719649791717529, "step": 278090 }, { "epoch": 1.6530841521479394, "grad_norm": 1.0975311994552612, "learning_rate": 0.00010967786887624618, "loss": 0.5307394981384277, "step": 278100 }, { "epoch": 1.6531435942246078, "grad_norm": 1.6037578582763672, "learning_rate": 0.00010967164414758881, "loss": 0.563128662109375, "step": 278110 }, { "epoch": 1.6532030363012762, "grad_norm": 1.5953408479690552, "learning_rate": 0.0001096654194205022, "loss": 0.5772835731506347, "step": 278120 }, { "epoch": 1.6532624783779446, "grad_norm": 1.3978781700134277, "learning_rate": 0.0001096591946950161, "loss": 0.5485294342041016, "step": 278130 }, { "epoch": 1.653321920454613, "grad_norm": 1.2269020080566406, "learning_rate": 0.00010965296997116034, "loss": 0.5492093086242675, "step": 278140 }, { "epoch": 1.6533813625312814, "grad_norm": 1.8068408966064453, "learning_rate": 0.00010964674524896459, "loss": 0.5298044204711914, "step": 278150 }, { "epoch": 1.6534408046079498, "grad_norm": 1.624990463256836, "learning_rate": 0.00010964052052845874, "loss": 0.5960508823394776, "step": 278160 }, { "epoch": 1.6535002466846183, "grad_norm": 1.5308253765106201, "learning_rate": 0.00010963429580967255, "loss": 0.6071523666381836, "step": 278170 }, { "epoch": 1.6535596887612867, "grad_norm": 1.4145057201385498, "learning_rate": 0.00010962807109263569, "loss": 0.5802305221557618, "step": 278180 }, { "epoch": 1.653619130837955, "grad_norm": 1.179888129234314, "learning_rate": 0.00010962184637737807, "loss": 0.5179950714111328, "step": 278190 }, { "epoch": 1.6536785729146235, "grad_norm": 1.8649206161499023, "learning_rate": 0.00010961562166392943, "loss": 0.5948718070983887, "step": 278200 }, { "epoch": 1.6537380149912917, "grad_norm": 1.4892123937606812, "learning_rate": 0.00010960939695231951, "loss": 0.611816120147705, "step": 278210 }, { "epoch": 1.65379745706796, "grad_norm": 1.5612739324569702, "learning_rate": 0.00010960317224257806, "loss": 0.5611867904663086, "step": 278220 }, { "epoch": 1.6538568991446285, "grad_norm": 1.5118662118911743, "learning_rate": 0.00010959694753473497, "loss": 0.5533553123474121, "step": 278230 }, { "epoch": 1.653916341221297, "grad_norm": 1.8907874822616577, "learning_rate": 0.00010959072282881995, "loss": 0.5397092819213867, "step": 278240 }, { "epoch": 1.6539757832979654, "grad_norm": 2.0574302673339844, "learning_rate": 0.00010958449812486271, "loss": 0.5962944030761719, "step": 278250 }, { "epoch": 1.6540352253746335, "grad_norm": 1.4702483415603638, "learning_rate": 0.00010957827342289317, "loss": 0.5188340187072754, "step": 278260 }, { "epoch": 1.654094667451302, "grad_norm": 1.4087542295455933, "learning_rate": 0.000109572048722941, "loss": 0.5944078922271728, "step": 278270 }, { "epoch": 1.6541541095279704, "grad_norm": 1.7353142499923706, "learning_rate": 0.00010956582402503599, "loss": 0.5283706665039063, "step": 278280 }, { "epoch": 1.6542135516046388, "grad_norm": 1.3743191957473755, "learning_rate": 0.00010955959932920798, "loss": 0.5977741241455078, "step": 278290 }, { "epoch": 1.6542729936813072, "grad_norm": 1.3108062744140625, "learning_rate": 0.00010955337463548667, "loss": 0.5788199424743652, "step": 278300 }, { "epoch": 1.6543324357579756, "grad_norm": 1.3635305166244507, "learning_rate": 0.00010954714994390187, "loss": 0.5888204574584961, "step": 278310 }, { "epoch": 1.654391877834644, "grad_norm": 1.2292300462722778, "learning_rate": 0.00010954092525448338, "loss": 0.5980902671813965, "step": 278320 }, { "epoch": 1.6544513199113124, "grad_norm": 1.2390424013137817, "learning_rate": 0.00010953470056726094, "loss": 0.5887080669403076, "step": 278330 }, { "epoch": 1.6545107619879809, "grad_norm": 1.336991786956787, "learning_rate": 0.00010952847588226435, "loss": 0.5938824653625489, "step": 278340 }, { "epoch": 1.6545702040646493, "grad_norm": 1.1577026844024658, "learning_rate": 0.00010952225119952337, "loss": 0.5103491306304931, "step": 278350 }, { "epoch": 1.6546296461413177, "grad_norm": 1.4664692878723145, "learning_rate": 0.00010951602651906778, "loss": 0.5455343723297119, "step": 278360 }, { "epoch": 1.654689088217986, "grad_norm": 1.4720728397369385, "learning_rate": 0.00010950980184092737, "loss": 0.6066514015197754, "step": 278370 }, { "epoch": 1.6547485302946545, "grad_norm": 1.2111132144927979, "learning_rate": 0.00010950357716513189, "loss": 0.500999116897583, "step": 278380 }, { "epoch": 1.6548079723713227, "grad_norm": 1.3028678894042969, "learning_rate": 0.00010949735249171115, "loss": 0.6115773677825928, "step": 278390 }, { "epoch": 1.6548674144479911, "grad_norm": 1.257809042930603, "learning_rate": 0.0001094911278206949, "loss": 0.5552423000335693, "step": 278400 }, { "epoch": 1.6549268565246595, "grad_norm": 1.546828031539917, "learning_rate": 0.00010948490315211292, "loss": 0.6056474685668946, "step": 278410 }, { "epoch": 1.654986298601328, "grad_norm": 1.1849725246429443, "learning_rate": 0.00010947867848599502, "loss": 0.6159381866455078, "step": 278420 }, { "epoch": 1.6550457406779964, "grad_norm": 1.517554759979248, "learning_rate": 0.00010947245382237097, "loss": 0.5747228622436523, "step": 278430 }, { "epoch": 1.6551051827546646, "grad_norm": 1.349923014640808, "learning_rate": 0.0001094662291612705, "loss": 0.5909086704254151, "step": 278440 }, { "epoch": 1.655164624831333, "grad_norm": 1.1966166496276855, "learning_rate": 0.0001094600045027234, "loss": 0.5877552032470703, "step": 278450 }, { "epoch": 1.6552240669080014, "grad_norm": 1.838887095451355, "learning_rate": 0.00010945377984675949, "loss": 0.5267873287200928, "step": 278460 }, { "epoch": 1.6552835089846698, "grad_norm": 1.4038387537002563, "learning_rate": 0.0001094475551934085, "loss": 0.5451533317565918, "step": 278470 }, { "epoch": 1.6553429510613382, "grad_norm": 1.5458478927612305, "learning_rate": 0.00010944133054270021, "loss": 0.5642069816589356, "step": 278480 }, { "epoch": 1.6554023931380066, "grad_norm": 1.1339685916900635, "learning_rate": 0.00010943510589466445, "loss": 0.5500159740447998, "step": 278490 }, { "epoch": 1.655461835214675, "grad_norm": 1.3149614334106445, "learning_rate": 0.00010942888124933095, "loss": 0.55550217628479, "step": 278500 }, { "epoch": 1.6555212772913435, "grad_norm": 1.6436935663223267, "learning_rate": 0.00010942265660672947, "loss": 0.5316638946533203, "step": 278510 }, { "epoch": 1.6555807193680119, "grad_norm": 1.664334774017334, "learning_rate": 0.00010941643196688984, "loss": 0.6398321151733398, "step": 278520 }, { "epoch": 1.6556401614446803, "grad_norm": 1.7756404876708984, "learning_rate": 0.0001094102073298418, "loss": 0.54715895652771, "step": 278530 }, { "epoch": 1.6556996035213487, "grad_norm": 1.6130508184432983, "learning_rate": 0.00010940398269561512, "loss": 0.5761351108551025, "step": 278540 }, { "epoch": 1.6557590455980171, "grad_norm": 1.7811206579208374, "learning_rate": 0.00010939775806423962, "loss": 0.597181749343872, "step": 278550 }, { "epoch": 1.6558184876746855, "grad_norm": 2.465055465698242, "learning_rate": 0.00010939153343574504, "loss": 0.5339765548706055, "step": 278560 }, { "epoch": 1.655877929751354, "grad_norm": 1.804513931274414, "learning_rate": 0.00010938530881016116, "loss": 0.5235217094421387, "step": 278570 }, { "epoch": 1.6559373718280221, "grad_norm": 1.4851598739624023, "learning_rate": 0.00010937908418751774, "loss": 0.6269717693328858, "step": 278580 }, { "epoch": 1.6559968139046906, "grad_norm": 1.2218090295791626, "learning_rate": 0.00010937285956784462, "loss": 0.5268119812011719, "step": 278590 }, { "epoch": 1.656056255981359, "grad_norm": 1.706788420677185, "learning_rate": 0.00010936663495117153, "loss": 0.5727431297302246, "step": 278600 }, { "epoch": 1.6561156980580274, "grad_norm": 1.7525148391723633, "learning_rate": 0.00010936041033752822, "loss": 0.5926636695861817, "step": 278610 }, { "epoch": 1.6561751401346958, "grad_norm": 1.57240629196167, "learning_rate": 0.00010935418572694451, "loss": 0.5244421482086181, "step": 278620 }, { "epoch": 1.656234582211364, "grad_norm": 1.5766608715057373, "learning_rate": 0.00010934796111945018, "loss": 0.5575382709503174, "step": 278630 }, { "epoch": 1.6562940242880324, "grad_norm": 1.7868573665618896, "learning_rate": 0.00010934173651507496, "loss": 0.6302022933959961, "step": 278640 }, { "epoch": 1.6563534663647008, "grad_norm": 1.2835403680801392, "learning_rate": 0.0001093355119138487, "loss": 0.5596022129058837, "step": 278650 }, { "epoch": 1.6564129084413692, "grad_norm": 1.242863655090332, "learning_rate": 0.0001093292873158011, "loss": 0.5550179481506348, "step": 278660 }, { "epoch": 1.6564723505180377, "grad_norm": 1.2629050016403198, "learning_rate": 0.00010932306272096198, "loss": 0.5038510322570801, "step": 278670 }, { "epoch": 1.656531792594706, "grad_norm": 1.585067868232727, "learning_rate": 0.00010931683812936112, "loss": 0.5666060447692871, "step": 278680 }, { "epoch": 1.6565912346713745, "grad_norm": 1.5027766227722168, "learning_rate": 0.00010931061354102827, "loss": 0.6262825012207032, "step": 278690 }, { "epoch": 1.656650676748043, "grad_norm": 1.9115560054779053, "learning_rate": 0.00010930438895599324, "loss": 0.6175354957580567, "step": 278700 }, { "epoch": 1.6567101188247113, "grad_norm": 1.8925809860229492, "learning_rate": 0.00010929816437428573, "loss": 0.5895414829254151, "step": 278710 }, { "epoch": 1.6567695609013797, "grad_norm": 1.630815029144287, "learning_rate": 0.00010929193979593562, "loss": 0.5597868442535401, "step": 278720 }, { "epoch": 1.6568290029780481, "grad_norm": 1.32358717918396, "learning_rate": 0.00010928571522097264, "loss": 0.5211447715759278, "step": 278730 }, { "epoch": 1.6568884450547166, "grad_norm": 1.546946406364441, "learning_rate": 0.00010927949064942653, "loss": 0.5709831714630127, "step": 278740 }, { "epoch": 1.656947887131385, "grad_norm": 1.4129375219345093, "learning_rate": 0.00010927326608132713, "loss": 0.5825313568115235, "step": 278750 }, { "epoch": 1.6570073292080532, "grad_norm": 1.5252488851547241, "learning_rate": 0.00010926704151670421, "loss": 0.5708070755004883, "step": 278760 }, { "epoch": 1.6570667712847216, "grad_norm": 1.0984320640563965, "learning_rate": 0.00010926081695558746, "loss": 0.6025895118713379, "step": 278770 }, { "epoch": 1.65712621336139, "grad_norm": 1.4414174556732178, "learning_rate": 0.00010925459239800677, "loss": 0.5688557624816895, "step": 278780 }, { "epoch": 1.6571856554380584, "grad_norm": 1.3522433042526245, "learning_rate": 0.00010924836784399186, "loss": 0.6020923614501953, "step": 278790 }, { "epoch": 1.6572450975147268, "grad_norm": 1.450347661972046, "learning_rate": 0.00010924214329357252, "loss": 0.5914899826049804, "step": 278800 }, { "epoch": 1.657304539591395, "grad_norm": 1.5647971630096436, "learning_rate": 0.00010923591874677849, "loss": 0.5116777420043945, "step": 278810 }, { "epoch": 1.6573639816680634, "grad_norm": 1.810089111328125, "learning_rate": 0.0001092296942036396, "loss": 0.6112396240234375, "step": 278820 }, { "epoch": 1.6574234237447318, "grad_norm": 1.5798866748809814, "learning_rate": 0.0001092234696641856, "loss": 0.6287328720092773, "step": 278830 }, { "epoch": 1.6574828658214003, "grad_norm": 1.7163407802581787, "learning_rate": 0.00010921724512844622, "loss": 0.5835607528686524, "step": 278840 }, { "epoch": 1.6575423078980687, "grad_norm": 1.650593876838684, "learning_rate": 0.00010921102059645134, "loss": 0.6098423957824707, "step": 278850 }, { "epoch": 1.657601749974737, "grad_norm": 1.4723397493362427, "learning_rate": 0.00010920479606823067, "loss": 0.6235117435455322, "step": 278860 }, { "epoch": 1.6576611920514055, "grad_norm": 1.410407543182373, "learning_rate": 0.00010919857154381397, "loss": 0.5384405136108399, "step": 278870 }, { "epoch": 1.657720634128074, "grad_norm": 1.208950400352478, "learning_rate": 0.00010919234702323107, "loss": 0.5775432586669922, "step": 278880 }, { "epoch": 1.6577800762047423, "grad_norm": 1.614437222480774, "learning_rate": 0.0001091861225065117, "loss": 0.5203683376312256, "step": 278890 }, { "epoch": 1.6578395182814107, "grad_norm": 1.5420740842819214, "learning_rate": 0.00010917989799368564, "loss": 0.5573154926300049, "step": 278900 }, { "epoch": 1.6578989603580792, "grad_norm": 1.5794411897659302, "learning_rate": 0.0001091736734847827, "loss": 0.5745233535766602, "step": 278910 }, { "epoch": 1.6579584024347476, "grad_norm": 1.0481975078582764, "learning_rate": 0.00010916744897983265, "loss": 0.5849257946014405, "step": 278920 }, { "epoch": 1.658017844511416, "grad_norm": 1.3449113368988037, "learning_rate": 0.00010916122447886526, "loss": 0.5776969909667968, "step": 278930 }, { "epoch": 1.6580772865880844, "grad_norm": 1.7275521755218506, "learning_rate": 0.00010915499998191026, "loss": 0.5227964401245118, "step": 278940 }, { "epoch": 1.6581367286647526, "grad_norm": 1.1158990859985352, "learning_rate": 0.00010914877548899747, "loss": 0.5521292686462402, "step": 278950 }, { "epoch": 1.658196170741421, "grad_norm": 1.4149441719055176, "learning_rate": 0.00010914255100015667, "loss": 0.6060171127319336, "step": 278960 }, { "epoch": 1.6582556128180894, "grad_norm": 1.2983100414276123, "learning_rate": 0.0001091363265154176, "loss": 0.5290914535522461, "step": 278970 }, { "epoch": 1.6583150548947578, "grad_norm": 1.5826013088226318, "learning_rate": 0.0001091301020348101, "loss": 0.5692736148834229, "step": 278980 }, { "epoch": 1.6583744969714262, "grad_norm": 1.5291849374771118, "learning_rate": 0.00010912387755836391, "loss": 0.5307878494262696, "step": 278990 }, { "epoch": 1.6584339390480944, "grad_norm": 1.785465121269226, "learning_rate": 0.00010911765308610877, "loss": 0.5920895576477051, "step": 279000 }, { "epoch": 1.6584933811247629, "grad_norm": 1.286839485168457, "learning_rate": 0.00010911142861807451, "loss": 0.5455673217773438, "step": 279010 }, { "epoch": 1.6585528232014313, "grad_norm": 1.2612662315368652, "learning_rate": 0.00010910520415429089, "loss": 0.5423508644104004, "step": 279020 }, { "epoch": 1.6586122652780997, "grad_norm": 1.5318909883499146, "learning_rate": 0.00010909897969478766, "loss": 0.5668456077575683, "step": 279030 }, { "epoch": 1.658671707354768, "grad_norm": 1.5284152030944824, "learning_rate": 0.00010909275523959464, "loss": 0.5788047790527344, "step": 279040 }, { "epoch": 1.6587311494314365, "grad_norm": 1.5820155143737793, "learning_rate": 0.00010908653078874158, "loss": 0.5936442375183105, "step": 279050 }, { "epoch": 1.658790591508105, "grad_norm": 1.307141900062561, "learning_rate": 0.00010908030634225825, "loss": 0.5430726051330567, "step": 279060 }, { "epoch": 1.6588500335847733, "grad_norm": 1.4191232919692993, "learning_rate": 0.00010907408190017443, "loss": 0.5461416244506836, "step": 279070 }, { "epoch": 1.6589094756614418, "grad_norm": 1.1348092555999756, "learning_rate": 0.00010906785746251991, "loss": 0.5540926933288575, "step": 279080 }, { "epoch": 1.6589689177381102, "grad_norm": 1.5480315685272217, "learning_rate": 0.00010906163302932447, "loss": 0.568869686126709, "step": 279090 }, { "epoch": 1.6590283598147786, "grad_norm": 2.105516195297241, "learning_rate": 0.00010905540860061781, "loss": 0.5389863967895507, "step": 279100 }, { "epoch": 1.659087801891447, "grad_norm": 1.2219607830047607, "learning_rate": 0.00010904918417642982, "loss": 0.5562750816345214, "step": 279110 }, { "epoch": 1.6591472439681154, "grad_norm": 1.7544763088226318, "learning_rate": 0.00010904295975679021, "loss": 0.5014945030212402, "step": 279120 }, { "epoch": 1.6592066860447836, "grad_norm": 1.4622596502304077, "learning_rate": 0.00010903673534172876, "loss": 0.5951667785644531, "step": 279130 }, { "epoch": 1.659266128121452, "grad_norm": 1.6690510511398315, "learning_rate": 0.00010903051093127525, "loss": 0.5648352622985839, "step": 279140 }, { "epoch": 1.6593255701981204, "grad_norm": 1.7399251461029053, "learning_rate": 0.00010902428652545948, "loss": 0.6023627281188965, "step": 279150 }, { "epoch": 1.6593850122747889, "grad_norm": 1.4045543670654297, "learning_rate": 0.00010901806212431118, "loss": 0.6203176498413085, "step": 279160 }, { "epoch": 1.6594444543514573, "grad_norm": 1.1281776428222656, "learning_rate": 0.00010901183772786016, "loss": 0.5799312591552734, "step": 279170 }, { "epoch": 1.6595038964281255, "grad_norm": 1.4775909185409546, "learning_rate": 0.00010900561333613621, "loss": 0.535695743560791, "step": 279180 }, { "epoch": 1.6595633385047939, "grad_norm": 1.5643465518951416, "learning_rate": 0.00010899938894916907, "loss": 0.6245326042175293, "step": 279190 }, { "epoch": 1.6596227805814623, "grad_norm": 1.584793210029602, "learning_rate": 0.00010899316456698849, "loss": 0.5968211650848388, "step": 279200 }, { "epoch": 1.6596822226581307, "grad_norm": 1.5804182291030884, "learning_rate": 0.00010898694018962432, "loss": 0.5637531757354737, "step": 279210 }, { "epoch": 1.6597416647347991, "grad_norm": 1.1262925863265991, "learning_rate": 0.00010898071581710629, "loss": 0.5158180236816406, "step": 279220 }, { "epoch": 1.6598011068114675, "grad_norm": 1.38582181930542, "learning_rate": 0.00010897449144946415, "loss": 0.5405026435852051, "step": 279230 }, { "epoch": 1.659860548888136, "grad_norm": 1.2993900775909424, "learning_rate": 0.00010896826708672774, "loss": 0.5703446865081787, "step": 279240 }, { "epoch": 1.6599199909648044, "grad_norm": 1.6869838237762451, "learning_rate": 0.00010896204272892683, "loss": 0.5935393333435058, "step": 279250 }, { "epoch": 1.6599794330414728, "grad_norm": 1.3028568029403687, "learning_rate": 0.0001089558183760911, "loss": 0.6018061637878418, "step": 279260 }, { "epoch": 1.6600388751181412, "grad_norm": 1.3265433311462402, "learning_rate": 0.00010894959402825045, "loss": 0.5844409942626954, "step": 279270 }, { "epoch": 1.6600983171948096, "grad_norm": 1.019450306892395, "learning_rate": 0.0001089433696854346, "loss": 0.4923120975494385, "step": 279280 }, { "epoch": 1.660157759271478, "grad_norm": 1.1697927713394165, "learning_rate": 0.0001089371453476733, "loss": 0.5206765174865723, "step": 279290 }, { "epoch": 1.6602172013481464, "grad_norm": 1.3112519979476929, "learning_rate": 0.00010893092101499631, "loss": 0.5782809257507324, "step": 279300 }, { "epoch": 1.6602766434248148, "grad_norm": 1.6936612129211426, "learning_rate": 0.00010892469668743352, "loss": 0.5997125148773194, "step": 279310 }, { "epoch": 1.660336085501483, "grad_norm": 1.4104615449905396, "learning_rate": 0.0001089184723650146, "loss": 0.5791190147399903, "step": 279320 }, { "epoch": 1.6603955275781515, "grad_norm": 1.5746959447860718, "learning_rate": 0.00010891224804776931, "loss": 0.5528440952301026, "step": 279330 }, { "epoch": 1.6604549696548199, "grad_norm": 1.5100252628326416, "learning_rate": 0.00010890602373572755, "loss": 0.5535450458526612, "step": 279340 }, { "epoch": 1.6605144117314883, "grad_norm": 1.1870276927947998, "learning_rate": 0.00010889979942891897, "loss": 0.5807653427124023, "step": 279350 }, { "epoch": 1.6605738538081567, "grad_norm": 1.3930736780166626, "learning_rate": 0.00010889357512737337, "loss": 0.5384373664855957, "step": 279360 }, { "epoch": 1.660633295884825, "grad_norm": 1.7401849031448364, "learning_rate": 0.0001088873508311206, "loss": 0.5778342247009277, "step": 279370 }, { "epoch": 1.6606927379614933, "grad_norm": 1.6520487070083618, "learning_rate": 0.00010888112654019033, "loss": 0.6079622268676758, "step": 279380 }, { "epoch": 1.6607521800381617, "grad_norm": 1.7357066869735718, "learning_rate": 0.00010887490225461239, "loss": 0.5555706024169922, "step": 279390 }, { "epoch": 1.6608116221148301, "grad_norm": 1.3319791555404663, "learning_rate": 0.0001088686779744166, "loss": 0.575489616394043, "step": 279400 }, { "epoch": 1.6608710641914985, "grad_norm": 1.8117661476135254, "learning_rate": 0.00010886245369963266, "loss": 0.5811614513397216, "step": 279410 }, { "epoch": 1.660930506268167, "grad_norm": 1.4799944162368774, "learning_rate": 0.00010885622943029035, "loss": 0.6831497192382813, "step": 279420 }, { "epoch": 1.6609899483448354, "grad_norm": 1.6516271829605103, "learning_rate": 0.00010885000516641946, "loss": 0.5830827713012695, "step": 279430 }, { "epoch": 1.6610493904215038, "grad_norm": 1.4900004863739014, "learning_rate": 0.00010884378090804979, "loss": 0.5524394512176514, "step": 279440 }, { "epoch": 1.6611088324981722, "grad_norm": 1.4680863618850708, "learning_rate": 0.00010883755665521109, "loss": 0.5360531806945801, "step": 279450 }, { "epoch": 1.6611682745748406, "grad_norm": 1.537324070930481, "learning_rate": 0.00010883133240793313, "loss": 0.5494443893432617, "step": 279460 }, { "epoch": 1.661227716651509, "grad_norm": 1.6536328792572021, "learning_rate": 0.00010882510816624571, "loss": 0.5772027015686035, "step": 279470 }, { "epoch": 1.6612871587281774, "grad_norm": 1.3834021091461182, "learning_rate": 0.00010881888393017858, "loss": 0.6067855358123779, "step": 279480 }, { "epoch": 1.6613466008048459, "grad_norm": 1.5871669054031372, "learning_rate": 0.00010881265969976151, "loss": 0.5578806877136231, "step": 279490 }, { "epoch": 1.661406042881514, "grad_norm": 1.450716495513916, "learning_rate": 0.00010880643547502431, "loss": 0.6066924571990967, "step": 279500 }, { "epoch": 1.6614654849581825, "grad_norm": 1.455514669418335, "learning_rate": 0.00010880021125599673, "loss": 0.5887063503265381, "step": 279510 }, { "epoch": 1.6615249270348509, "grad_norm": 1.6521997451782227, "learning_rate": 0.00010879398704270854, "loss": 0.5519937515258789, "step": 279520 }, { "epoch": 1.6615843691115193, "grad_norm": 1.5222581624984741, "learning_rate": 0.00010878776283518952, "loss": 0.5418588161468506, "step": 279530 }, { "epoch": 1.6616438111881877, "grad_norm": 1.4624543190002441, "learning_rate": 0.00010878153863346945, "loss": 0.5471652984619141, "step": 279540 }, { "epoch": 1.661703253264856, "grad_norm": 1.535361886024475, "learning_rate": 0.00010877531443757811, "loss": 0.5481664657592773, "step": 279550 }, { "epoch": 1.6617626953415243, "grad_norm": 1.123234748840332, "learning_rate": 0.00010876909024754522, "loss": 0.5547882556915283, "step": 279560 }, { "epoch": 1.6618221374181927, "grad_norm": 1.727617621421814, "learning_rate": 0.00010876286606340064, "loss": 0.5763287544250488, "step": 279570 }, { "epoch": 1.6618815794948611, "grad_norm": 1.3585588932037354, "learning_rate": 0.00010875664188517411, "loss": 0.5729364871978759, "step": 279580 }, { "epoch": 1.6619410215715296, "grad_norm": 1.601891040802002, "learning_rate": 0.00010875041771289537, "loss": 0.5547043800354003, "step": 279590 }, { "epoch": 1.662000463648198, "grad_norm": 1.6992487907409668, "learning_rate": 0.00010874419354659427, "loss": 0.6139041900634765, "step": 279600 }, { "epoch": 1.6620599057248664, "grad_norm": 1.5134485960006714, "learning_rate": 0.00010873796938630052, "loss": 0.557462501525879, "step": 279610 }, { "epoch": 1.6621193478015348, "grad_norm": 1.32371985912323, "learning_rate": 0.00010873174523204388, "loss": 0.553078556060791, "step": 279620 }, { "epoch": 1.6621787898782032, "grad_norm": 1.4969621896743774, "learning_rate": 0.0001087255210838542, "loss": 0.5831457614898682, "step": 279630 }, { "epoch": 1.6622382319548716, "grad_norm": 1.4788860082626343, "learning_rate": 0.00010871929694176118, "loss": 0.5632871627807617, "step": 279640 }, { "epoch": 1.66229767403154, "grad_norm": 1.4280097484588623, "learning_rate": 0.00010871307280579465, "loss": 0.6445921897888184, "step": 279650 }, { "epoch": 1.6623571161082085, "grad_norm": 1.5338242053985596, "learning_rate": 0.00010870684867598433, "loss": 0.5917070865631103, "step": 279660 }, { "epoch": 1.6624165581848769, "grad_norm": 1.805713415145874, "learning_rate": 0.00010870062455236004, "loss": 0.563780689239502, "step": 279670 }, { "epoch": 1.6624760002615453, "grad_norm": 1.6101281642913818, "learning_rate": 0.00010869440043495155, "loss": 0.5654211044311523, "step": 279680 }, { "epoch": 1.6625354423382135, "grad_norm": 1.0808296203613281, "learning_rate": 0.00010868817632378858, "loss": 0.5776126861572266, "step": 279690 }, { "epoch": 1.662594884414882, "grad_norm": 1.4726673364639282, "learning_rate": 0.00010868195221890096, "loss": 0.617492961883545, "step": 279700 }, { "epoch": 1.6626543264915503, "grad_norm": 1.7129650115966797, "learning_rate": 0.0001086757281203185, "loss": 0.5812273979187011, "step": 279710 }, { "epoch": 1.6627137685682187, "grad_norm": 1.2807667255401611, "learning_rate": 0.00010866950402807085, "loss": 0.5804388999938965, "step": 279720 }, { "epoch": 1.6627732106448871, "grad_norm": 1.3678010702133179, "learning_rate": 0.0001086632799421879, "loss": 0.5679971694946289, "step": 279730 }, { "epoch": 1.6628326527215553, "grad_norm": 1.4772478342056274, "learning_rate": 0.00010865705586269941, "loss": 0.5876920700073243, "step": 279740 }, { "epoch": 1.6628920947982238, "grad_norm": 1.6999268531799316, "learning_rate": 0.00010865083178963504, "loss": 0.5972893714904786, "step": 279750 }, { "epoch": 1.6629515368748922, "grad_norm": 1.814002275466919, "learning_rate": 0.00010864460772302472, "loss": 0.519511604309082, "step": 279760 }, { "epoch": 1.6630109789515606, "grad_norm": 1.8812909126281738, "learning_rate": 0.00010863838366289816, "loss": 0.5502837657928467, "step": 279770 }, { "epoch": 1.663070421028229, "grad_norm": 1.4701255559921265, "learning_rate": 0.0001086321596092851, "loss": 0.5801664352416992, "step": 279780 }, { "epoch": 1.6631298631048974, "grad_norm": 1.3678359985351562, "learning_rate": 0.00010862593556221532, "loss": 0.5962188720703125, "step": 279790 }, { "epoch": 1.6631893051815658, "grad_norm": 1.298365831375122, "learning_rate": 0.00010861971152171863, "loss": 0.6233237266540528, "step": 279800 }, { "epoch": 1.6632487472582342, "grad_norm": 1.420857310295105, "learning_rate": 0.00010861348748782483, "loss": 0.5885510921478272, "step": 279810 }, { "epoch": 1.6633081893349027, "grad_norm": 1.4624122381210327, "learning_rate": 0.00010860726346056359, "loss": 0.6246657848358155, "step": 279820 }, { "epoch": 1.663367631411571, "grad_norm": 1.7045081853866577, "learning_rate": 0.00010860103943996478, "loss": 0.5322757244110108, "step": 279830 }, { "epoch": 1.6634270734882395, "grad_norm": 1.145020842552185, "learning_rate": 0.00010859481542605816, "loss": 0.4798413276672363, "step": 279840 }, { "epoch": 1.663486515564908, "grad_norm": 1.2786167860031128, "learning_rate": 0.00010858859141887343, "loss": 0.512332820892334, "step": 279850 }, { "epoch": 1.6635459576415763, "grad_norm": 2.2761430740356445, "learning_rate": 0.00010858236741844045, "loss": 0.5601336002349854, "step": 279860 }, { "epoch": 1.6636053997182445, "grad_norm": 1.4685817956924438, "learning_rate": 0.00010857614342478897, "loss": 0.6215837478637696, "step": 279870 }, { "epoch": 1.663664841794913, "grad_norm": 1.2891074419021606, "learning_rate": 0.00010856991943794872, "loss": 0.5878678798675537, "step": 279880 }, { "epoch": 1.6637242838715813, "grad_norm": 1.4976791143417358, "learning_rate": 0.00010856369545794955, "loss": 0.5586563110351562, "step": 279890 }, { "epoch": 1.6637837259482497, "grad_norm": 1.69147789478302, "learning_rate": 0.00010855747148482118, "loss": 0.5732710838317872, "step": 279900 }, { "epoch": 1.6638431680249182, "grad_norm": 1.7409679889678955, "learning_rate": 0.0001085512475185934, "loss": 0.6082745552062988, "step": 279910 }, { "epoch": 1.6639026101015864, "grad_norm": 1.9271801710128784, "learning_rate": 0.00010854502355929594, "loss": 0.5689617156982422, "step": 279920 }, { "epoch": 1.6639620521782548, "grad_norm": 1.4384492635726929, "learning_rate": 0.00010853879960695866, "loss": 0.5668479919433593, "step": 279930 }, { "epoch": 1.6640214942549232, "grad_norm": 1.5309404134750366, "learning_rate": 0.00010853257566161126, "loss": 0.558095645904541, "step": 279940 }, { "epoch": 1.6640809363315916, "grad_norm": 1.6012245416641235, "learning_rate": 0.00010852635172328354, "loss": 0.5598928451538085, "step": 279950 }, { "epoch": 1.66414037840826, "grad_norm": 1.4319475889205933, "learning_rate": 0.00010852012779200526, "loss": 0.5671122550964356, "step": 279960 }, { "epoch": 1.6641998204849284, "grad_norm": 1.2593843936920166, "learning_rate": 0.00010851390386780624, "loss": 0.49192056655883787, "step": 279970 }, { "epoch": 1.6642592625615968, "grad_norm": 1.8605109453201294, "learning_rate": 0.00010850767995071618, "loss": 0.5807433128356934, "step": 279980 }, { "epoch": 1.6643187046382653, "grad_norm": 1.3394726514816284, "learning_rate": 0.00010850145604076492, "loss": 0.571465253829956, "step": 279990 }, { "epoch": 1.6643781467149337, "grad_norm": 1.4188345670700073, "learning_rate": 0.0001084952321379822, "loss": 0.5365457534790039, "step": 280000 }, { "epoch": 1.664437588791602, "grad_norm": 1.1591835021972656, "learning_rate": 0.00010848900824239776, "loss": 0.5961931228637696, "step": 280010 }, { "epoch": 1.6644970308682705, "grad_norm": 1.5024020671844482, "learning_rate": 0.00010848278435404147, "loss": 0.6164307594299316, "step": 280020 }, { "epoch": 1.664556472944939, "grad_norm": 1.7504652738571167, "learning_rate": 0.00010847656047294301, "loss": 0.5625300407409668, "step": 280030 }, { "epoch": 1.6646159150216073, "grad_norm": 1.5180461406707764, "learning_rate": 0.00010847033659913219, "loss": 0.5168322563171387, "step": 280040 }, { "epoch": 1.6646753570982757, "grad_norm": 1.1878101825714111, "learning_rate": 0.00010846411273263877, "loss": 0.5368062019348144, "step": 280050 }, { "epoch": 1.664734799174944, "grad_norm": 1.6405658721923828, "learning_rate": 0.00010845788887349255, "loss": 0.5242897033691406, "step": 280060 }, { "epoch": 1.6647942412516124, "grad_norm": 1.5811177492141724, "learning_rate": 0.00010845166502172329, "loss": 0.5663257122039795, "step": 280070 }, { "epoch": 1.6648536833282808, "grad_norm": 1.2571909427642822, "learning_rate": 0.00010844544117736073, "loss": 0.5901165008544922, "step": 280080 }, { "epoch": 1.6649131254049492, "grad_norm": 1.5854769945144653, "learning_rate": 0.0001084392173404347, "loss": 0.5929080963134765, "step": 280090 }, { "epoch": 1.6649725674816174, "grad_norm": 1.3676047325134277, "learning_rate": 0.00010843299351097494, "loss": 0.5774278163909912, "step": 280100 }, { "epoch": 1.6650320095582858, "grad_norm": 1.4827793836593628, "learning_rate": 0.0001084267696890112, "loss": 0.5664561748504638, "step": 280110 }, { "epoch": 1.6650914516349542, "grad_norm": 1.3214399814605713, "learning_rate": 0.00010842054587457331, "loss": 0.534591817855835, "step": 280120 }, { "epoch": 1.6651508937116226, "grad_norm": 1.6980873346328735, "learning_rate": 0.00010841432206769102, "loss": 0.6180511474609375, "step": 280130 }, { "epoch": 1.665210335788291, "grad_norm": 1.7423555850982666, "learning_rate": 0.00010840809826839408, "loss": 0.5724008560180665, "step": 280140 }, { "epoch": 1.6652697778649594, "grad_norm": 1.2106502056121826, "learning_rate": 0.00010840187447671226, "loss": 0.5824049949645996, "step": 280150 }, { "epoch": 1.6653292199416279, "grad_norm": 1.4279296398162842, "learning_rate": 0.00010839565069267537, "loss": 0.5742938995361329, "step": 280160 }, { "epoch": 1.6653886620182963, "grad_norm": 1.1312587261199951, "learning_rate": 0.0001083894269163132, "loss": 0.5495107650756836, "step": 280170 }, { "epoch": 1.6654481040949647, "grad_norm": 1.5551079511642456, "learning_rate": 0.0001083832031476554, "loss": 0.5924467086791992, "step": 280180 }, { "epoch": 1.665507546171633, "grad_norm": 1.1159871816635132, "learning_rate": 0.00010837697938673188, "loss": 0.5878055572509766, "step": 280190 }, { "epoch": 1.6655669882483015, "grad_norm": 1.8840305805206299, "learning_rate": 0.00010837075563357238, "loss": 0.5681524753570557, "step": 280200 }, { "epoch": 1.66562643032497, "grad_norm": 1.1555737257003784, "learning_rate": 0.00010836453188820658, "loss": 0.5694855213165283, "step": 280210 }, { "epoch": 1.6656858724016383, "grad_norm": 1.7010914087295532, "learning_rate": 0.00010835830815066436, "loss": 0.5470927238464356, "step": 280220 }, { "epoch": 1.6657453144783068, "grad_norm": 1.8499534130096436, "learning_rate": 0.00010835208442097551, "loss": 0.5465115070343017, "step": 280230 }, { "epoch": 1.665804756554975, "grad_norm": 1.4631150960922241, "learning_rate": 0.00010834586069916967, "loss": 0.5447937965393066, "step": 280240 }, { "epoch": 1.6658641986316434, "grad_norm": 1.1692783832550049, "learning_rate": 0.00010833963698527673, "loss": 0.5229140758514405, "step": 280250 }, { "epoch": 1.6659236407083118, "grad_norm": 1.2569572925567627, "learning_rate": 0.00010833341327932647, "loss": 0.5818672180175781, "step": 280260 }, { "epoch": 1.6659830827849802, "grad_norm": 1.4632316827774048, "learning_rate": 0.00010832718958134855, "loss": 0.5852910995483398, "step": 280270 }, { "epoch": 1.6660425248616486, "grad_norm": 1.3418538570404053, "learning_rate": 0.00010832096589137282, "loss": 0.6064526081085205, "step": 280280 }, { "epoch": 1.6661019669383168, "grad_norm": 1.3496088981628418, "learning_rate": 0.00010831474220942906, "loss": 0.546562385559082, "step": 280290 }, { "epoch": 1.6661614090149852, "grad_norm": 1.3867987394332886, "learning_rate": 0.00010830851853554703, "loss": 0.5488804817199707, "step": 280300 }, { "epoch": 1.6662208510916536, "grad_norm": 1.2706576585769653, "learning_rate": 0.00010830229486975643, "loss": 0.5843082427978515, "step": 280310 }, { "epoch": 1.666280293168322, "grad_norm": 1.6124056577682495, "learning_rate": 0.00010829607121208715, "loss": 0.6154520511627197, "step": 280320 }, { "epoch": 1.6663397352449905, "grad_norm": 1.6267858743667603, "learning_rate": 0.00010828984756256892, "loss": 0.5516674518585205, "step": 280330 }, { "epoch": 1.6663991773216589, "grad_norm": 1.2687883377075195, "learning_rate": 0.00010828362392123143, "loss": 0.5753244400024414, "step": 280340 }, { "epoch": 1.6664586193983273, "grad_norm": 1.658835530281067, "learning_rate": 0.00010827740028810463, "loss": 0.5530735492706299, "step": 280350 }, { "epoch": 1.6665180614749957, "grad_norm": 1.6545809507369995, "learning_rate": 0.0001082711766632181, "loss": 0.5711089134216308, "step": 280360 }, { "epoch": 1.6665775035516641, "grad_norm": 1.407415747642517, "learning_rate": 0.00010826495304660171, "loss": 0.5933352470397949, "step": 280370 }, { "epoch": 1.6666369456283325, "grad_norm": 0.9984564185142517, "learning_rate": 0.00010825872943828525, "loss": 0.5297776222229004, "step": 280380 }, { "epoch": 1.666696387705001, "grad_norm": 1.9744805097579956, "learning_rate": 0.00010825250583829845, "loss": 0.5665106773376465, "step": 280390 }, { "epoch": 1.6667558297816694, "grad_norm": 1.4627289772033691, "learning_rate": 0.00010824628224667108, "loss": 0.5765362739562988, "step": 280400 }, { "epoch": 1.6668152718583378, "grad_norm": 1.547357201576233, "learning_rate": 0.00010824005866343292, "loss": 0.6168446063995361, "step": 280410 }, { "epoch": 1.6668747139350062, "grad_norm": 1.8722749948501587, "learning_rate": 0.00010823383508861373, "loss": 0.6414149284362793, "step": 280420 }, { "epoch": 1.6669341560116744, "grad_norm": 1.0038443803787231, "learning_rate": 0.00010822761152224332, "loss": 0.5031164169311524, "step": 280430 }, { "epoch": 1.6669935980883428, "grad_norm": 1.3385788202285767, "learning_rate": 0.00010822138796435143, "loss": 0.5358453750610351, "step": 280440 }, { "epoch": 1.6670530401650112, "grad_norm": 1.4192427396774292, "learning_rate": 0.00010821516441496784, "loss": 0.528824758529663, "step": 280450 }, { "epoch": 1.6671124822416796, "grad_norm": 1.2782231569290161, "learning_rate": 0.00010820894087412232, "loss": 0.5837221145629883, "step": 280460 }, { "epoch": 1.6671719243183478, "grad_norm": 1.7783825397491455, "learning_rate": 0.00010820271734184462, "loss": 0.5163298606872558, "step": 280470 }, { "epoch": 1.6672313663950162, "grad_norm": 1.2314237356185913, "learning_rate": 0.00010819649381816457, "loss": 0.5678431510925293, "step": 280480 }, { "epoch": 1.6672908084716846, "grad_norm": 1.745445966720581, "learning_rate": 0.00010819027030311189, "loss": 0.5685184955596924, "step": 280490 }, { "epoch": 1.667350250548353, "grad_norm": 1.573185682296753, "learning_rate": 0.00010818404679671634, "loss": 0.5389350891113281, "step": 280500 }, { "epoch": 1.6674096926250215, "grad_norm": 1.705202341079712, "learning_rate": 0.00010817782329900776, "loss": 0.5994264602661132, "step": 280510 }, { "epoch": 1.66746913470169, "grad_norm": 1.5600818395614624, "learning_rate": 0.00010817159981001586, "loss": 0.5219694137573242, "step": 280520 }, { "epoch": 1.6675285767783583, "grad_norm": 1.515002727508545, "learning_rate": 0.00010816537632977044, "loss": 0.5366580963134766, "step": 280530 }, { "epoch": 1.6675880188550267, "grad_norm": 1.379639983177185, "learning_rate": 0.00010815915285830123, "loss": 0.5644601821899414, "step": 280540 }, { "epoch": 1.6676474609316951, "grad_norm": 1.3484060764312744, "learning_rate": 0.00010815292939563806, "loss": 0.5940357208251953, "step": 280550 }, { "epoch": 1.6677069030083636, "grad_norm": 1.4593932628631592, "learning_rate": 0.00010814670594181064, "loss": 0.5390891075134278, "step": 280560 }, { "epoch": 1.667766345085032, "grad_norm": 1.5279723405838013, "learning_rate": 0.00010814048249684878, "loss": 0.5678939819335938, "step": 280570 }, { "epoch": 1.6678257871617004, "grad_norm": 1.301448941230774, "learning_rate": 0.00010813425906078227, "loss": 0.5308029174804687, "step": 280580 }, { "epoch": 1.6678852292383688, "grad_norm": 1.6291762590408325, "learning_rate": 0.00010812803563364085, "loss": 0.5491787910461425, "step": 280590 }, { "epoch": 1.6679446713150372, "grad_norm": 1.8815407752990723, "learning_rate": 0.00010812181221545428, "loss": 0.6415952682495117, "step": 280600 }, { "epoch": 1.6680041133917054, "grad_norm": 1.3891558647155762, "learning_rate": 0.00010811558880625235, "loss": 0.5389466285705566, "step": 280610 }, { "epoch": 1.6680635554683738, "grad_norm": 1.4783062934875488, "learning_rate": 0.00010810936540606484, "loss": 0.510328722000122, "step": 280620 }, { "epoch": 1.6681229975450422, "grad_norm": 1.174747347831726, "learning_rate": 0.00010810314201492152, "loss": 0.538479232788086, "step": 280630 }, { "epoch": 1.6681824396217106, "grad_norm": 1.6602331399917603, "learning_rate": 0.0001080969186328521, "loss": 0.5106712818145752, "step": 280640 }, { "epoch": 1.668241881698379, "grad_norm": 1.2906863689422607, "learning_rate": 0.00010809069525988644, "loss": 0.5420548915863037, "step": 280650 }, { "epoch": 1.6683013237750473, "grad_norm": 1.1656453609466553, "learning_rate": 0.00010808447189605426, "loss": 0.5802589893341065, "step": 280660 }, { "epoch": 1.6683607658517157, "grad_norm": 1.4299050569534302, "learning_rate": 0.00010807824854138533, "loss": 0.5789167404174804, "step": 280670 }, { "epoch": 1.668420207928384, "grad_norm": 1.5271282196044922, "learning_rate": 0.00010807202519590944, "loss": 0.551165246963501, "step": 280680 }, { "epoch": 1.6684796500050525, "grad_norm": 1.454136610031128, "learning_rate": 0.00010806580185965635, "loss": 0.5813803672790527, "step": 280690 }, { "epoch": 1.668539092081721, "grad_norm": 1.5153684616088867, "learning_rate": 0.00010805957853265583, "loss": 0.5963897705078125, "step": 280700 }, { "epoch": 1.6685985341583893, "grad_norm": 1.477729320526123, "learning_rate": 0.00010805335521493764, "loss": 0.5998908042907715, "step": 280710 }, { "epoch": 1.6686579762350577, "grad_norm": 1.5260848999023438, "learning_rate": 0.0001080471319065316, "loss": 0.5611167907714844, "step": 280720 }, { "epoch": 1.6687174183117262, "grad_norm": 1.3355010747909546, "learning_rate": 0.00010804090860746741, "loss": 0.6051195144653321, "step": 280730 }, { "epoch": 1.6687768603883946, "grad_norm": 1.2903834581375122, "learning_rate": 0.00010803468531777488, "loss": 0.5396174907684326, "step": 280740 }, { "epoch": 1.668836302465063, "grad_norm": 1.6319125890731812, "learning_rate": 0.00010802846203748378, "loss": 0.548749589920044, "step": 280750 }, { "epoch": 1.6688957445417314, "grad_norm": 1.57853102684021, "learning_rate": 0.0001080222387666239, "loss": 0.5484429359436035, "step": 280760 }, { "epoch": 1.6689551866183998, "grad_norm": 1.2566630840301514, "learning_rate": 0.00010801601550522492, "loss": 0.5432172775268554, "step": 280770 }, { "epoch": 1.6690146286950682, "grad_norm": 1.352304458618164, "learning_rate": 0.0001080097922533167, "loss": 0.5666826248168946, "step": 280780 }, { "epoch": 1.6690740707717366, "grad_norm": 1.3532222509384155, "learning_rate": 0.00010800356901092903, "loss": 0.5691374778747559, "step": 280790 }, { "epoch": 1.6691335128484048, "grad_norm": 1.2514748573303223, "learning_rate": 0.00010799734577809155, "loss": 0.57882080078125, "step": 280800 }, { "epoch": 1.6691929549250732, "grad_norm": 1.3464857339859009, "learning_rate": 0.00010799112255483416, "loss": 0.5633443832397461, "step": 280810 }, { "epoch": 1.6692523970017417, "grad_norm": 1.5396260023117065, "learning_rate": 0.0001079848993411866, "loss": 0.5666774272918701, "step": 280820 }, { "epoch": 1.66931183907841, "grad_norm": 1.598270297050476, "learning_rate": 0.00010797867613717856, "loss": 0.5533313751220703, "step": 280830 }, { "epoch": 1.6693712811550783, "grad_norm": 1.4368447065353394, "learning_rate": 0.00010797245294283995, "loss": 0.5354852676391602, "step": 280840 }, { "epoch": 1.6694307232317467, "grad_norm": 1.5124351978302002, "learning_rate": 0.00010796622975820044, "loss": 0.5929160118103027, "step": 280850 }, { "epoch": 1.669490165308415, "grad_norm": 1.5334259271621704, "learning_rate": 0.00010796000658328977, "loss": 0.6045852184295655, "step": 280860 }, { "epoch": 1.6695496073850835, "grad_norm": 1.5841408967971802, "learning_rate": 0.00010795378341813782, "loss": 0.5896754264831543, "step": 280870 }, { "epoch": 1.669609049461752, "grad_norm": 1.6895463466644287, "learning_rate": 0.00010794756026277429, "loss": 0.5511294364929199, "step": 280880 }, { "epoch": 1.6696684915384203, "grad_norm": 1.7663599252700806, "learning_rate": 0.00010794133711722896, "loss": 0.5743538856506347, "step": 280890 }, { "epoch": 1.6697279336150888, "grad_norm": 1.3512451648712158, "learning_rate": 0.00010793511398153157, "loss": 0.5939212799072265, "step": 280900 }, { "epoch": 1.6697873756917572, "grad_norm": 1.224240779876709, "learning_rate": 0.00010792889085571197, "loss": 0.5652740478515625, "step": 280910 }, { "epoch": 1.6698468177684256, "grad_norm": 1.1856590509414673, "learning_rate": 0.00010792266773979987, "loss": 0.5982345581054688, "step": 280920 }, { "epoch": 1.669906259845094, "grad_norm": 1.737214207649231, "learning_rate": 0.000107916444633825, "loss": 0.5781371116638183, "step": 280930 }, { "epoch": 1.6699657019217624, "grad_norm": 1.2730375528335571, "learning_rate": 0.00010791022153781723, "loss": 0.5605477333068848, "step": 280940 }, { "epoch": 1.6700251439984308, "grad_norm": 1.5850855112075806, "learning_rate": 0.00010790399845180626, "loss": 0.5344564914703369, "step": 280950 }, { "epoch": 1.6700845860750992, "grad_norm": 1.5302015542984009, "learning_rate": 0.00010789777537582184, "loss": 0.5704328060150147, "step": 280960 }, { "epoch": 1.6701440281517677, "grad_norm": 1.55866539478302, "learning_rate": 0.00010789155230989382, "loss": 0.5655773162841797, "step": 280970 }, { "epoch": 1.6702034702284358, "grad_norm": 1.4655040502548218, "learning_rate": 0.00010788532925405192, "loss": 0.5708778381347657, "step": 280980 }, { "epoch": 1.6702629123051043, "grad_norm": 1.3117057085037231, "learning_rate": 0.00010787910620832591, "loss": 0.5359627723693847, "step": 280990 }, { "epoch": 1.6703223543817727, "grad_norm": 1.2451696395874023, "learning_rate": 0.00010787288317274555, "loss": 0.5471940994262695, "step": 281000 }, { "epoch": 1.670381796458441, "grad_norm": 1.5930389165878296, "learning_rate": 0.00010786666014734064, "loss": 0.6151412010192872, "step": 281010 }, { "epoch": 1.6704412385351095, "grad_norm": 1.4012925624847412, "learning_rate": 0.00010786043713214094, "loss": 0.5655390739440918, "step": 281020 }, { "epoch": 1.6705006806117777, "grad_norm": 1.5386203527450562, "learning_rate": 0.00010785421412717618, "loss": 0.5862860679626465, "step": 281030 }, { "epoch": 1.6705601226884461, "grad_norm": 1.2971733808517456, "learning_rate": 0.00010784799113247617, "loss": 0.5729422092437744, "step": 281040 }, { "epoch": 1.6706195647651145, "grad_norm": 1.254915475845337, "learning_rate": 0.00010784176814807068, "loss": 0.582463550567627, "step": 281050 }, { "epoch": 1.670679006841783, "grad_norm": 1.4789890050888062, "learning_rate": 0.00010783554517398942, "loss": 0.5404597282409668, "step": 281060 }, { "epoch": 1.6707384489184514, "grad_norm": 1.3893296718597412, "learning_rate": 0.00010782932221026226, "loss": 0.6140554428100586, "step": 281070 }, { "epoch": 1.6707978909951198, "grad_norm": 1.656500220298767, "learning_rate": 0.00010782309925691889, "loss": 0.6158334732055664, "step": 281080 }, { "epoch": 1.6708573330717882, "grad_norm": 1.6221938133239746, "learning_rate": 0.00010781687631398909, "loss": 0.5506674766540527, "step": 281090 }, { "epoch": 1.6709167751484566, "grad_norm": 1.3400434255599976, "learning_rate": 0.00010781065338150267, "loss": 0.5693294525146484, "step": 281100 }, { "epoch": 1.670976217225125, "grad_norm": 1.3230775594711304, "learning_rate": 0.00010780443045948934, "loss": 0.5780538558959961, "step": 281110 }, { "epoch": 1.6710356593017934, "grad_norm": 1.293994426727295, "learning_rate": 0.00010779820754797891, "loss": 0.5406508445739746, "step": 281120 }, { "epoch": 1.6710951013784618, "grad_norm": 1.9700425863265991, "learning_rate": 0.00010779198464700113, "loss": 0.5723285675048828, "step": 281130 }, { "epoch": 1.6711545434551303, "grad_norm": 1.232735276222229, "learning_rate": 0.00010778576175658579, "loss": 0.5468614578247071, "step": 281140 }, { "epoch": 1.6712139855317987, "grad_norm": 1.159585952758789, "learning_rate": 0.00010777953887676264, "loss": 0.5253409385681153, "step": 281150 }, { "epoch": 1.671273427608467, "grad_norm": 1.493265151977539, "learning_rate": 0.00010777331600756143, "loss": 0.613124942779541, "step": 281160 }, { "epoch": 1.6713328696851353, "grad_norm": 1.2939579486846924, "learning_rate": 0.00010776709314901197, "loss": 0.579592227935791, "step": 281170 }, { "epoch": 1.6713923117618037, "grad_norm": 1.3664051294326782, "learning_rate": 0.00010776087030114399, "loss": 0.6172615051269531, "step": 281180 }, { "epoch": 1.671451753838472, "grad_norm": 1.305626630783081, "learning_rate": 0.00010775464746398726, "loss": 0.5237269401550293, "step": 281190 }, { "epoch": 1.6715111959151405, "grad_norm": 1.3957058191299438, "learning_rate": 0.0001077484246375716, "loss": 0.5744743347167969, "step": 281200 }, { "epoch": 1.6715706379918087, "grad_norm": 1.4148229360580444, "learning_rate": 0.00010774220182192671, "loss": 0.5408492088317871, "step": 281210 }, { "epoch": 1.6716300800684771, "grad_norm": 1.2121968269348145, "learning_rate": 0.00010773597901708241, "loss": 0.5925384998321533, "step": 281220 }, { "epoch": 1.6716895221451455, "grad_norm": 1.4069139957427979, "learning_rate": 0.00010772975622306844, "loss": 0.5723948001861572, "step": 281230 }, { "epoch": 1.671748964221814, "grad_norm": 1.599521279335022, "learning_rate": 0.00010772353343991457, "loss": 0.590701675415039, "step": 281240 }, { "epoch": 1.6718084062984824, "grad_norm": 1.756386637687683, "learning_rate": 0.00010771731066765061, "loss": 0.5524265766143799, "step": 281250 }, { "epoch": 1.6718678483751508, "grad_norm": 1.5630135536193848, "learning_rate": 0.00010771108790630622, "loss": 0.6019262313842774, "step": 281260 }, { "epoch": 1.6719272904518192, "grad_norm": 1.3386187553405762, "learning_rate": 0.00010770486515591129, "loss": 0.5516661643981934, "step": 281270 }, { "epoch": 1.6719867325284876, "grad_norm": 1.4492485523223877, "learning_rate": 0.00010769864241649554, "loss": 0.6697275161743164, "step": 281280 }, { "epoch": 1.672046174605156, "grad_norm": 1.2381223440170288, "learning_rate": 0.00010769241968808867, "loss": 0.6317500591278076, "step": 281290 }, { "epoch": 1.6721056166818244, "grad_norm": 1.8684844970703125, "learning_rate": 0.00010768619697072055, "loss": 0.5859395503997803, "step": 281300 }, { "epoch": 1.6721650587584929, "grad_norm": 1.5545737743377686, "learning_rate": 0.00010767997426442095, "loss": 0.5765830039978027, "step": 281310 }, { "epoch": 1.6722245008351613, "grad_norm": 1.4842100143432617, "learning_rate": 0.00010767375156921952, "loss": 0.5473679542541504, "step": 281320 }, { "epoch": 1.6722839429118297, "grad_norm": 1.4432708024978638, "learning_rate": 0.00010766752888514613, "loss": 0.46935243606567384, "step": 281330 }, { "epoch": 1.672343384988498, "grad_norm": 1.322898268699646, "learning_rate": 0.00010766130621223056, "loss": 0.5940913200378418, "step": 281340 }, { "epoch": 1.6724028270651663, "grad_norm": 1.6947479248046875, "learning_rate": 0.00010765508355050247, "loss": 0.5660222053527832, "step": 281350 }, { "epoch": 1.6724622691418347, "grad_norm": 1.1785142421722412, "learning_rate": 0.00010764886089999173, "loss": 0.5660730361938476, "step": 281360 }, { "epoch": 1.6725217112185031, "grad_norm": 1.3136827945709229, "learning_rate": 0.0001076426382607281, "loss": 0.4936237335205078, "step": 281370 }, { "epoch": 1.6725811532951715, "grad_norm": 1.5141774415969849, "learning_rate": 0.00010763641563274127, "loss": 0.5939810752868653, "step": 281380 }, { "epoch": 1.67264059537184, "grad_norm": 1.3210784196853638, "learning_rate": 0.00010763019301606106, "loss": 0.5893005847930908, "step": 281390 }, { "epoch": 1.6727000374485081, "grad_norm": 1.3187460899353027, "learning_rate": 0.00010762397041071726, "loss": 0.548456859588623, "step": 281400 }, { "epoch": 1.6727594795251766, "grad_norm": 1.8749278783798218, "learning_rate": 0.00010761774781673959, "loss": 0.6164456367492676, "step": 281410 }, { "epoch": 1.672818921601845, "grad_norm": 1.4235280752182007, "learning_rate": 0.00010761152523415781, "loss": 0.5091619491577148, "step": 281420 }, { "epoch": 1.6728783636785134, "grad_norm": 1.4306789636611938, "learning_rate": 0.00010760530266300177, "loss": 0.5327224731445312, "step": 281430 }, { "epoch": 1.6729378057551818, "grad_norm": 1.6301449537277222, "learning_rate": 0.00010759908010330115, "loss": 0.5889344215393066, "step": 281440 }, { "epoch": 1.6729972478318502, "grad_norm": 1.691443920135498, "learning_rate": 0.00010759285755508572, "loss": 0.6062365531921386, "step": 281450 }, { "epoch": 1.6730566899085186, "grad_norm": 1.2913886308670044, "learning_rate": 0.00010758663501838531, "loss": 0.5680342197418213, "step": 281460 }, { "epoch": 1.673116131985187, "grad_norm": 1.9102281332015991, "learning_rate": 0.00010758041249322966, "loss": 0.6341780662536621, "step": 281470 }, { "epoch": 1.6731755740618555, "grad_norm": 1.2658910751342773, "learning_rate": 0.00010757418997964849, "loss": 0.5292886257171631, "step": 281480 }, { "epoch": 1.6732350161385239, "grad_norm": 1.266208291053772, "learning_rate": 0.00010756796747767162, "loss": 0.6160202026367188, "step": 281490 }, { "epoch": 1.6732944582151923, "grad_norm": 1.4069207906723022, "learning_rate": 0.00010756174498732878, "loss": 0.5598240375518799, "step": 281500 }, { "epoch": 1.6733539002918607, "grad_norm": 1.130300521850586, "learning_rate": 0.0001075555225086498, "loss": 0.5747768402099609, "step": 281510 }, { "epoch": 1.6734133423685291, "grad_norm": 1.3762868642807007, "learning_rate": 0.00010754930004166435, "loss": 0.5405570030212402, "step": 281520 }, { "epoch": 1.6734727844451975, "grad_norm": 1.519043207168579, "learning_rate": 0.00010754307758640228, "loss": 0.5935030937194824, "step": 281530 }, { "epoch": 1.6735322265218657, "grad_norm": 1.2842202186584473, "learning_rate": 0.00010753685514289331, "loss": 0.5819319725036621, "step": 281540 }, { "epoch": 1.6735916685985341, "grad_norm": 1.9059933423995972, "learning_rate": 0.00010753063271116721, "loss": 0.5875693321228027, "step": 281550 }, { "epoch": 1.6736511106752026, "grad_norm": 1.2386623620986938, "learning_rate": 0.00010752441029125378, "loss": 0.6471295833587647, "step": 281560 }, { "epoch": 1.673710552751871, "grad_norm": 2.507430076599121, "learning_rate": 0.00010751818788318275, "loss": 0.5494190216064453, "step": 281570 }, { "epoch": 1.6737699948285392, "grad_norm": 1.4812579154968262, "learning_rate": 0.0001075119654869839, "loss": 0.5878342628479004, "step": 281580 }, { "epoch": 1.6738294369052076, "grad_norm": 1.4081913232803345, "learning_rate": 0.00010750574310268699, "loss": 0.524547529220581, "step": 281590 }, { "epoch": 1.673888878981876, "grad_norm": 2.128326892852783, "learning_rate": 0.00010749952073032181, "loss": 0.5919898509979248, "step": 281600 }, { "epoch": 1.6739483210585444, "grad_norm": 1.3586769104003906, "learning_rate": 0.00010749329836991808, "loss": 0.5615954875946045, "step": 281610 }, { "epoch": 1.6740077631352128, "grad_norm": 1.665276288986206, "learning_rate": 0.00010748707602150559, "loss": 0.5983587265014648, "step": 281620 }, { "epoch": 1.6740672052118812, "grad_norm": 1.3478857278823853, "learning_rate": 0.00010748085368511413, "loss": 0.5367843627929687, "step": 281630 }, { "epoch": 1.6741266472885497, "grad_norm": 1.5155106782913208, "learning_rate": 0.00010747463136077343, "loss": 0.555010461807251, "step": 281640 }, { "epoch": 1.674186089365218, "grad_norm": 1.2706149816513062, "learning_rate": 0.00010746840904851325, "loss": 0.6031844139099121, "step": 281650 }, { "epoch": 1.6742455314418865, "grad_norm": 1.264538049697876, "learning_rate": 0.00010746218674836339, "loss": 0.5268536567687988, "step": 281660 }, { "epoch": 1.674304973518555, "grad_norm": 1.2278969287872314, "learning_rate": 0.00010745596446035362, "loss": 0.6095802783966064, "step": 281670 }, { "epoch": 1.6743644155952233, "grad_norm": 1.5176866054534912, "learning_rate": 0.00010744974218451367, "loss": 0.5625833511352539, "step": 281680 }, { "epoch": 1.6744238576718917, "grad_norm": 1.4521777629852295, "learning_rate": 0.00010744351992087332, "loss": 0.5689934730529785, "step": 281690 }, { "epoch": 1.6744832997485601, "grad_norm": 1.660760521888733, "learning_rate": 0.00010743729766946233, "loss": 0.5374634742736817, "step": 281700 }, { "epoch": 1.6745427418252286, "grad_norm": 1.5570811033248901, "learning_rate": 0.00010743107543031046, "loss": 0.5394290447235107, "step": 281710 }, { "epoch": 1.6746021839018967, "grad_norm": 1.5169154405593872, "learning_rate": 0.0001074248532034475, "loss": 0.5631378650665283, "step": 281720 }, { "epoch": 1.6746616259785652, "grad_norm": 1.8706355094909668, "learning_rate": 0.00010741863098890318, "loss": 0.5531243324279785, "step": 281730 }, { "epoch": 1.6747210680552336, "grad_norm": 0.8917994499206543, "learning_rate": 0.00010741240878670735, "loss": 0.4983512878417969, "step": 281740 }, { "epoch": 1.674780510131902, "grad_norm": 1.7607932090759277, "learning_rate": 0.00010740618659688964, "loss": 0.5464105606079102, "step": 281750 }, { "epoch": 1.6748399522085704, "grad_norm": 1.5528546571731567, "learning_rate": 0.0001073999644194799, "loss": 0.5949232578277588, "step": 281760 }, { "epoch": 1.6748993942852386, "grad_norm": 1.7183524370193481, "learning_rate": 0.00010739374225450792, "loss": 0.6162332534790039, "step": 281770 }, { "epoch": 1.674958836361907, "grad_norm": 1.3183413743972778, "learning_rate": 0.00010738752010200337, "loss": 0.6000552177429199, "step": 281780 }, { "epoch": 1.6750182784385754, "grad_norm": 1.4713937044143677, "learning_rate": 0.0001073812979619961, "loss": 0.5895248413085937, "step": 281790 }, { "epoch": 1.6750777205152438, "grad_norm": 1.2421084642410278, "learning_rate": 0.00010737507583451587, "loss": 0.569646167755127, "step": 281800 }, { "epoch": 1.6751371625919123, "grad_norm": 1.4938846826553345, "learning_rate": 0.00010736885371959235, "loss": 0.5573112487792968, "step": 281810 }, { "epoch": 1.6751966046685807, "grad_norm": 1.484627604484558, "learning_rate": 0.00010736263161725541, "loss": 0.5780134677886963, "step": 281820 }, { "epoch": 1.675256046745249, "grad_norm": 1.619372010231018, "learning_rate": 0.00010735640952753483, "loss": 0.5383708953857422, "step": 281830 }, { "epoch": 1.6753154888219175, "grad_norm": 1.479050636291504, "learning_rate": 0.00010735018745046029, "loss": 0.5562804698944092, "step": 281840 }, { "epoch": 1.675374930898586, "grad_norm": 1.2825108766555786, "learning_rate": 0.00010734396538606153, "loss": 0.5091494560241699, "step": 281850 }, { "epoch": 1.6754343729752543, "grad_norm": 1.8816322088241577, "learning_rate": 0.00010733774333436843, "loss": 0.6141678333282471, "step": 281860 }, { "epoch": 1.6754938150519227, "grad_norm": 1.3690226078033447, "learning_rate": 0.00010733152129541068, "loss": 0.5055857181549073, "step": 281870 }, { "epoch": 1.6755532571285912, "grad_norm": 1.3972086906433105, "learning_rate": 0.00010732529926921804, "loss": 0.553611946105957, "step": 281880 }, { "epoch": 1.6756126992052596, "grad_norm": 1.7099781036376953, "learning_rate": 0.00010731907725582033, "loss": 0.6356776237487793, "step": 281890 }, { "epoch": 1.675672141281928, "grad_norm": 1.6323283910751343, "learning_rate": 0.00010731285525524728, "loss": 0.5884003639221191, "step": 281900 }, { "epoch": 1.6757315833585962, "grad_norm": 1.5228444337844849, "learning_rate": 0.00010730663326752862, "loss": 0.5118317604064941, "step": 281910 }, { "epoch": 1.6757910254352646, "grad_norm": 1.4799917936325073, "learning_rate": 0.00010730041129269416, "loss": 0.5680304527282715, "step": 281920 }, { "epoch": 1.675850467511933, "grad_norm": 1.2861998081207275, "learning_rate": 0.00010729418933077367, "loss": 0.6017725467681885, "step": 281930 }, { "epoch": 1.6759099095886014, "grad_norm": 1.5581387281417847, "learning_rate": 0.00010728796738179682, "loss": 0.5975507736206055, "step": 281940 }, { "epoch": 1.6759693516652696, "grad_norm": 1.216505765914917, "learning_rate": 0.00010728174544579354, "loss": 0.5617215156555175, "step": 281950 }, { "epoch": 1.676028793741938, "grad_norm": 1.330080270767212, "learning_rate": 0.00010727552352279348, "loss": 0.5845448493957519, "step": 281960 }, { "epoch": 1.6760882358186064, "grad_norm": 0.9947811365127563, "learning_rate": 0.0001072693016128264, "loss": 0.5427972793579101, "step": 281970 }, { "epoch": 1.6761476778952749, "grad_norm": 1.3319331407546997, "learning_rate": 0.00010726307971592209, "loss": 0.5263669967651368, "step": 281980 }, { "epoch": 1.6762071199719433, "grad_norm": 1.17546808719635, "learning_rate": 0.00010725685783211032, "loss": 0.5679863452911377, "step": 281990 }, { "epoch": 1.6762665620486117, "grad_norm": 1.4879294633865356, "learning_rate": 0.00010725063596142086, "loss": 0.5464444160461426, "step": 282000 }, { "epoch": 1.67632600412528, "grad_norm": 1.9000346660614014, "learning_rate": 0.00010724441410388345, "loss": 0.5436660289764405, "step": 282010 }, { "epoch": 1.6763854462019485, "grad_norm": 1.1982882022857666, "learning_rate": 0.00010723819225952784, "loss": 0.5723088264465332, "step": 282020 }, { "epoch": 1.676444888278617, "grad_norm": 1.3631078004837036, "learning_rate": 0.00010723197042838384, "loss": 0.5618619441986084, "step": 282030 }, { "epoch": 1.6765043303552853, "grad_norm": 1.894600510597229, "learning_rate": 0.00010722574861048119, "loss": 0.538691234588623, "step": 282040 }, { "epoch": 1.6765637724319538, "grad_norm": 1.0397701263427734, "learning_rate": 0.00010721952680584964, "loss": 0.5591423988342286, "step": 282050 }, { "epoch": 1.6766232145086222, "grad_norm": 1.3160864114761353, "learning_rate": 0.00010721330501451898, "loss": 0.5453398704528809, "step": 282060 }, { "epoch": 1.6766826565852906, "grad_norm": 1.414436936378479, "learning_rate": 0.0001072070832365189, "loss": 0.5679415702819824, "step": 282070 }, { "epoch": 1.676742098661959, "grad_norm": 1.2918606996536255, "learning_rate": 0.00010720086147187931, "loss": 0.5527329444885254, "step": 282080 }, { "epoch": 1.6768015407386272, "grad_norm": 1.2454590797424316, "learning_rate": 0.00010719463972062984, "loss": 0.5622316360473633, "step": 282090 }, { "epoch": 1.6768609828152956, "grad_norm": 1.2944746017456055, "learning_rate": 0.0001071884179828003, "loss": 0.5875876426696778, "step": 282100 }, { "epoch": 1.676920424891964, "grad_norm": 1.5064671039581299, "learning_rate": 0.00010718219625842044, "loss": 0.5618156433105469, "step": 282110 }, { "epoch": 1.6769798669686324, "grad_norm": 1.399903416633606, "learning_rate": 0.00010717597454752004, "loss": 0.6126906394958496, "step": 282120 }, { "epoch": 1.6770393090453009, "grad_norm": 1.3229451179504395, "learning_rate": 0.00010716975285012887, "loss": 0.5821486473083496, "step": 282130 }, { "epoch": 1.677098751121969, "grad_norm": 1.2424529790878296, "learning_rate": 0.00010716353116627664, "loss": 0.5350795745849609, "step": 282140 }, { "epoch": 1.6771581931986375, "grad_norm": 1.2925363779067993, "learning_rate": 0.00010715730949599318, "loss": 0.6432688236236572, "step": 282150 }, { "epoch": 1.6772176352753059, "grad_norm": 1.3598846197128296, "learning_rate": 0.00010715108783930823, "loss": 0.5692362785339355, "step": 282160 }, { "epoch": 1.6772770773519743, "grad_norm": 1.33573579788208, "learning_rate": 0.00010714486619625153, "loss": 0.5353057861328125, "step": 282170 }, { "epoch": 1.6773365194286427, "grad_norm": 1.5576132535934448, "learning_rate": 0.00010713864456685286, "loss": 0.5668789386749268, "step": 282180 }, { "epoch": 1.6773959615053111, "grad_norm": 1.9371905326843262, "learning_rate": 0.00010713242295114197, "loss": 0.6017359733581543, "step": 282190 }, { "epoch": 1.6774554035819795, "grad_norm": 1.7245646715164185, "learning_rate": 0.00010712620134914863, "loss": 0.5079034328460693, "step": 282200 }, { "epoch": 1.677514845658648, "grad_norm": 1.3938114643096924, "learning_rate": 0.00010711997976090262, "loss": 0.5547624111175538, "step": 282210 }, { "epoch": 1.6775742877353164, "grad_norm": 1.7157784700393677, "learning_rate": 0.00010711375818643368, "loss": 0.5204513549804688, "step": 282220 }, { "epoch": 1.6776337298119848, "grad_norm": 1.4498651027679443, "learning_rate": 0.0001071075366257716, "loss": 0.5763094425201416, "step": 282230 }, { "epoch": 1.6776931718886532, "grad_norm": 1.360694408416748, "learning_rate": 0.00010710131507894605, "loss": 0.5394690990447998, "step": 282240 }, { "epoch": 1.6777526139653216, "grad_norm": 1.3287732601165771, "learning_rate": 0.00010709509354598692, "loss": 0.5710795402526856, "step": 282250 }, { "epoch": 1.67781205604199, "grad_norm": 1.5781916379928589, "learning_rate": 0.00010708887202692393, "loss": 0.5756622791290283, "step": 282260 }, { "epoch": 1.6778714981186584, "grad_norm": 1.715951919555664, "learning_rate": 0.00010708265052178676, "loss": 0.5724751472473144, "step": 282270 }, { "epoch": 1.6779309401953266, "grad_norm": 1.3623889684677124, "learning_rate": 0.00010707642903060526, "loss": 0.5467715740203858, "step": 282280 }, { "epoch": 1.677990382271995, "grad_norm": 1.6750407218933105, "learning_rate": 0.00010707020755340922, "loss": 0.6172904014587403, "step": 282290 }, { "epoch": 1.6780498243486635, "grad_norm": 1.545866847038269, "learning_rate": 0.00010706398609022827, "loss": 0.5378536701202392, "step": 282300 }, { "epoch": 1.6781092664253319, "grad_norm": 1.5418184995651245, "learning_rate": 0.0001070577646410923, "loss": 0.5655012607574463, "step": 282310 }, { "epoch": 1.678168708502, "grad_norm": 1.3729312419891357, "learning_rate": 0.00010705154320603103, "loss": 0.6070115089416503, "step": 282320 }, { "epoch": 1.6782281505786685, "grad_norm": 1.2568936347961426, "learning_rate": 0.0001070453217850742, "loss": 0.5362992286682129, "step": 282330 }, { "epoch": 1.678287592655337, "grad_norm": 1.2215403318405151, "learning_rate": 0.00010703910037825156, "loss": 0.5505430221557617, "step": 282340 }, { "epoch": 1.6783470347320053, "grad_norm": 1.3778908252716064, "learning_rate": 0.00010703287898559293, "loss": 0.6138455867767334, "step": 282350 }, { "epoch": 1.6784064768086737, "grad_norm": 1.183112621307373, "learning_rate": 0.00010702665760712803, "loss": 0.5688623905181884, "step": 282360 }, { "epoch": 1.6784659188853421, "grad_norm": 1.468001365661621, "learning_rate": 0.0001070204362428866, "loss": 0.5425707817077636, "step": 282370 }, { "epoch": 1.6785253609620105, "grad_norm": 1.1283581256866455, "learning_rate": 0.00010701421489289847, "loss": 0.556523609161377, "step": 282380 }, { "epoch": 1.678584803038679, "grad_norm": 1.2643722295761108, "learning_rate": 0.00010700799355719335, "loss": 0.5915055751800538, "step": 282390 }, { "epoch": 1.6786442451153474, "grad_norm": 1.3187028169631958, "learning_rate": 0.00010700177223580097, "loss": 0.5635461330413818, "step": 282400 }, { "epoch": 1.6787036871920158, "grad_norm": 1.2834441661834717, "learning_rate": 0.00010699555092875118, "loss": 0.5258374214172363, "step": 282410 }, { "epoch": 1.6787631292686842, "grad_norm": 1.6288951635360718, "learning_rate": 0.00010698932963607369, "loss": 0.5234443664550781, "step": 282420 }, { "epoch": 1.6788225713453526, "grad_norm": 1.259903073310852, "learning_rate": 0.00010698310835779821, "loss": 0.6121598243713379, "step": 282430 }, { "epoch": 1.678882013422021, "grad_norm": 1.6914905309677124, "learning_rate": 0.00010697688709395461, "loss": 0.5809386730194092, "step": 282440 }, { "epoch": 1.6789414554986895, "grad_norm": 1.7769725322723389, "learning_rate": 0.00010697066584457261, "loss": 0.5672389507293701, "step": 282450 }, { "epoch": 1.6790008975753576, "grad_norm": 1.1377815008163452, "learning_rate": 0.00010696444460968192, "loss": 0.5374523639678955, "step": 282460 }, { "epoch": 1.679060339652026, "grad_norm": 1.5468014478683472, "learning_rate": 0.00010695822338931231, "loss": 0.5931105613708496, "step": 282470 }, { "epoch": 1.6791197817286945, "grad_norm": 1.5324609279632568, "learning_rate": 0.00010695200218349362, "loss": 0.5547447204589844, "step": 282480 }, { "epoch": 1.6791792238053629, "grad_norm": 1.522473931312561, "learning_rate": 0.00010694578099225551, "loss": 0.5884252548217773, "step": 282490 }, { "epoch": 1.6792386658820313, "grad_norm": 1.5142823457717896, "learning_rate": 0.0001069395598156278, "loss": 0.6005868911743164, "step": 282500 }, { "epoch": 1.6792981079586995, "grad_norm": 1.5493645668029785, "learning_rate": 0.00010693333865364026, "loss": 0.5621825218200683, "step": 282510 }, { "epoch": 1.679357550035368, "grad_norm": 1.5542529821395874, "learning_rate": 0.0001069271175063226, "loss": 0.5659379959106445, "step": 282520 }, { "epoch": 1.6794169921120363, "grad_norm": 1.3779748678207397, "learning_rate": 0.00010692089637370459, "loss": 0.5612366199493408, "step": 282530 }, { "epoch": 1.6794764341887047, "grad_norm": 1.4576530456542969, "learning_rate": 0.00010691467525581604, "loss": 0.6000030517578125, "step": 282540 }, { "epoch": 1.6795358762653732, "grad_norm": 1.2228189706802368, "learning_rate": 0.00010690845415268666, "loss": 0.5728963851928711, "step": 282550 }, { "epoch": 1.6795953183420416, "grad_norm": 1.3613371849060059, "learning_rate": 0.00010690223306434621, "loss": 0.5320344924926758, "step": 282560 }, { "epoch": 1.67965476041871, "grad_norm": 1.6921164989471436, "learning_rate": 0.00010689601199082449, "loss": 0.554959774017334, "step": 282570 }, { "epoch": 1.6797142024953784, "grad_norm": 1.5345999002456665, "learning_rate": 0.00010688979093215123, "loss": 0.6391826152801514, "step": 282580 }, { "epoch": 1.6797736445720468, "grad_norm": 1.6139624118804932, "learning_rate": 0.00010688356988835619, "loss": 0.5146788120269775, "step": 282590 }, { "epoch": 1.6798330866487152, "grad_norm": 1.3512076139450073, "learning_rate": 0.00010687734885946912, "loss": 0.4818528175354004, "step": 282600 }, { "epoch": 1.6798925287253836, "grad_norm": 1.4271143674850464, "learning_rate": 0.00010687112784551983, "loss": 0.5419993877410889, "step": 282610 }, { "epoch": 1.679951970802052, "grad_norm": 1.7325931787490845, "learning_rate": 0.000106864906846538, "loss": 0.5302788257598877, "step": 282620 }, { "epoch": 1.6800114128787205, "grad_norm": 1.6261301040649414, "learning_rate": 0.00010685868586255345, "loss": 0.5455243587493896, "step": 282630 }, { "epoch": 1.6800708549553889, "grad_norm": 1.583569049835205, "learning_rate": 0.00010685246489359592, "loss": 0.620232343673706, "step": 282640 }, { "epoch": 1.680130297032057, "grad_norm": 1.110569715499878, "learning_rate": 0.00010684624393969519, "loss": 0.567982292175293, "step": 282650 }, { "epoch": 1.6801897391087255, "grad_norm": 1.5935200452804565, "learning_rate": 0.00010684002300088094, "loss": 0.48945322036743166, "step": 282660 }, { "epoch": 1.680249181185394, "grad_norm": 1.413420557975769, "learning_rate": 0.00010683380207718303, "loss": 0.5505964279174804, "step": 282670 }, { "epoch": 1.6803086232620623, "grad_norm": 1.326248049736023, "learning_rate": 0.00010682758116863119, "loss": 0.5911970138549805, "step": 282680 }, { "epoch": 1.6803680653387305, "grad_norm": 1.354338526725769, "learning_rate": 0.00010682136027525513, "loss": 0.5780225276947022, "step": 282690 }, { "epoch": 1.680427507415399, "grad_norm": 1.4609884023666382, "learning_rate": 0.00010681513939708465, "loss": 0.5160147666931152, "step": 282700 }, { "epoch": 1.6804869494920673, "grad_norm": 1.3715473413467407, "learning_rate": 0.00010680891853414951, "loss": 0.5560748100280761, "step": 282710 }, { "epoch": 1.6805463915687358, "grad_norm": 1.36351478099823, "learning_rate": 0.00010680269768647948, "loss": 0.53630690574646, "step": 282720 }, { "epoch": 1.6806058336454042, "grad_norm": 1.5903327465057373, "learning_rate": 0.00010679647685410426, "loss": 0.5473962783813476, "step": 282730 }, { "epoch": 1.6806652757220726, "grad_norm": 1.682000756263733, "learning_rate": 0.00010679025603705369, "loss": 0.5107722282409668, "step": 282740 }, { "epoch": 1.680724717798741, "grad_norm": 1.4125908613204956, "learning_rate": 0.00010678403523535745, "loss": 0.6072728157043457, "step": 282750 }, { "epoch": 1.6807841598754094, "grad_norm": 1.9428716897964478, "learning_rate": 0.00010677781444904533, "loss": 0.58432035446167, "step": 282760 }, { "epoch": 1.6808436019520778, "grad_norm": 0.9939789175987244, "learning_rate": 0.00010677159367814713, "loss": 0.5729072570800782, "step": 282770 }, { "epoch": 1.6809030440287462, "grad_norm": 1.5693769454956055, "learning_rate": 0.00010676537292269255, "loss": 0.5722590923309326, "step": 282780 }, { "epoch": 1.6809624861054147, "grad_norm": 1.2188713550567627, "learning_rate": 0.00010675915218271135, "loss": 0.5512557029724121, "step": 282790 }, { "epoch": 1.681021928182083, "grad_norm": 1.5281203985214233, "learning_rate": 0.00010675293145823335, "loss": 0.5724674701690674, "step": 282800 }, { "epoch": 1.6810813702587515, "grad_norm": 1.6942182779312134, "learning_rate": 0.00010674671074928824, "loss": 0.6056511878967286, "step": 282810 }, { "epoch": 1.68114081233542, "grad_norm": 1.5829813480377197, "learning_rate": 0.00010674049005590583, "loss": 0.6559693336486816, "step": 282820 }, { "epoch": 1.681200254412088, "grad_norm": 1.3374916315078735, "learning_rate": 0.00010673426937811579, "loss": 0.5646038055419922, "step": 282830 }, { "epoch": 1.6812596964887565, "grad_norm": 1.4625898599624634, "learning_rate": 0.000106728048715948, "loss": 0.5690485954284668, "step": 282840 }, { "epoch": 1.681319138565425, "grad_norm": 1.7326771020889282, "learning_rate": 0.00010672182806943214, "loss": 0.5407781600952148, "step": 282850 }, { "epoch": 1.6813785806420933, "grad_norm": 1.5900089740753174, "learning_rate": 0.00010671560743859794, "loss": 0.6030771732330322, "step": 282860 }, { "epoch": 1.6814380227187617, "grad_norm": 1.582972526550293, "learning_rate": 0.00010670938682347527, "loss": 0.567460012435913, "step": 282870 }, { "epoch": 1.68149746479543, "grad_norm": 1.237214207649231, "learning_rate": 0.00010670316622409377, "loss": 0.5935426712036133, "step": 282880 }, { "epoch": 1.6815569068720984, "grad_norm": 1.3168072700500488, "learning_rate": 0.00010669694564048322, "loss": 0.536052131652832, "step": 282890 }, { "epoch": 1.6816163489487668, "grad_norm": 1.9850642681121826, "learning_rate": 0.00010669072507267348, "loss": 0.5688612461090088, "step": 282900 }, { "epoch": 1.6816757910254352, "grad_norm": 1.6609547138214111, "learning_rate": 0.00010668450452069418, "loss": 0.5132390975952148, "step": 282910 }, { "epoch": 1.6817352331021036, "grad_norm": 1.6041816473007202, "learning_rate": 0.00010667828398457511, "loss": 0.6014275550842285, "step": 282920 }, { "epoch": 1.681794675178772, "grad_norm": 1.258942723274231, "learning_rate": 0.00010667206346434611, "loss": 0.5095839977264405, "step": 282930 }, { "epoch": 1.6818541172554404, "grad_norm": 1.2918015718460083, "learning_rate": 0.00010666584296003684, "loss": 0.5254989624023437, "step": 282940 }, { "epoch": 1.6819135593321088, "grad_norm": 1.3690636157989502, "learning_rate": 0.00010665962247167706, "loss": 0.5497562885284424, "step": 282950 }, { "epoch": 1.6819730014087773, "grad_norm": 1.9437637329101562, "learning_rate": 0.00010665340199929656, "loss": 0.5718217849731445, "step": 282960 }, { "epoch": 1.6820324434854457, "grad_norm": 1.345693826675415, "learning_rate": 0.00010664718154292513, "loss": 0.5777305603027344, "step": 282970 }, { "epoch": 1.682091885562114, "grad_norm": 1.4143245220184326, "learning_rate": 0.00010664096110259245, "loss": 0.5729652404785156, "step": 282980 }, { "epoch": 1.6821513276387825, "grad_norm": 1.4447107315063477, "learning_rate": 0.00010663474067832833, "loss": 0.565395450592041, "step": 282990 }, { "epoch": 1.682210769715451, "grad_norm": 1.8273032903671265, "learning_rate": 0.0001066285202701625, "loss": 0.576968002319336, "step": 283000 }, { "epoch": 1.6822702117921193, "grad_norm": 1.359490990638733, "learning_rate": 0.00010662229987812473, "loss": 0.568148136138916, "step": 283010 }, { "epoch": 1.6823296538687875, "grad_norm": 1.150161862373352, "learning_rate": 0.00010661607950224476, "loss": 0.5330174446105957, "step": 283020 }, { "epoch": 1.682389095945456, "grad_norm": 1.3700920343399048, "learning_rate": 0.0001066098591425524, "loss": 0.5740066528320312, "step": 283030 }, { "epoch": 1.6824485380221244, "grad_norm": 1.467031717300415, "learning_rate": 0.00010660363879907734, "loss": 0.5476455211639404, "step": 283040 }, { "epoch": 1.6825079800987928, "grad_norm": 1.5415313243865967, "learning_rate": 0.00010659741847184935, "loss": 0.6147322177886962, "step": 283050 }, { "epoch": 1.682567422175461, "grad_norm": 1.3365858793258667, "learning_rate": 0.00010659119816089822, "loss": 0.5479425907135009, "step": 283060 }, { "epoch": 1.6826268642521294, "grad_norm": 2.111748218536377, "learning_rate": 0.00010658497786625368, "loss": 0.5722652435302734, "step": 283070 }, { "epoch": 1.6826863063287978, "grad_norm": 2.249211549758911, "learning_rate": 0.00010657875758794548, "loss": 0.5932740211486817, "step": 283080 }, { "epoch": 1.6827457484054662, "grad_norm": 1.2696740627288818, "learning_rate": 0.00010657253732600339, "loss": 0.5734108924865723, "step": 283090 }, { "epoch": 1.6828051904821346, "grad_norm": 1.4101896286010742, "learning_rate": 0.00010656631708045717, "loss": 0.6099004745483398, "step": 283100 }, { "epoch": 1.682864632558803, "grad_norm": 1.0866483449935913, "learning_rate": 0.00010656009685133657, "loss": 0.5259634017944336, "step": 283110 }, { "epoch": 1.6829240746354714, "grad_norm": 1.580344319343567, "learning_rate": 0.00010655387663867132, "loss": 0.5806254863739013, "step": 283120 }, { "epoch": 1.6829835167121399, "grad_norm": 1.3944096565246582, "learning_rate": 0.00010654765644249123, "loss": 0.5314244747161865, "step": 283130 }, { "epoch": 1.6830429587888083, "grad_norm": 1.5500460863113403, "learning_rate": 0.000106541436262826, "loss": 0.550234031677246, "step": 283140 }, { "epoch": 1.6831024008654767, "grad_norm": 1.1185225248336792, "learning_rate": 0.0001065352160997054, "loss": 0.6077167510986328, "step": 283150 }, { "epoch": 1.683161842942145, "grad_norm": 1.4378094673156738, "learning_rate": 0.00010652899595315921, "loss": 0.5700490474700928, "step": 283160 }, { "epoch": 1.6832212850188135, "grad_norm": 1.62911856174469, "learning_rate": 0.00010652277582321717, "loss": 0.5913496017456055, "step": 283170 }, { "epoch": 1.683280727095482, "grad_norm": 1.274996280670166, "learning_rate": 0.00010651655570990903, "loss": 0.5329402446746826, "step": 283180 }, { "epoch": 1.6833401691721503, "grad_norm": 1.2683945894241333, "learning_rate": 0.00010651033561326455, "loss": 0.5901846885681152, "step": 283190 }, { "epoch": 1.6833996112488185, "grad_norm": 1.6222574710845947, "learning_rate": 0.00010650411553331348, "loss": 0.5773556709289551, "step": 283200 }, { "epoch": 1.683459053325487, "grad_norm": 1.3773155212402344, "learning_rate": 0.0001064978954700856, "loss": 0.6348422527313232, "step": 283210 }, { "epoch": 1.6835184954021554, "grad_norm": 1.2696154117584229, "learning_rate": 0.0001064916754236106, "loss": 0.5415406703948975, "step": 283220 }, { "epoch": 1.6835779374788238, "grad_norm": 1.2999694347381592, "learning_rate": 0.00010648545539391832, "loss": 0.560121726989746, "step": 283230 }, { "epoch": 1.6836373795554922, "grad_norm": 1.7056528329849243, "learning_rate": 0.00010647923538103845, "loss": 0.6346481323242188, "step": 283240 }, { "epoch": 1.6836968216321604, "grad_norm": 1.2748825550079346, "learning_rate": 0.00010647301538500076, "loss": 0.5819445133209229, "step": 283250 }, { "epoch": 1.6837562637088288, "grad_norm": 1.6883463859558105, "learning_rate": 0.00010646679540583504, "loss": 0.6282084465026856, "step": 283260 }, { "epoch": 1.6838157057854972, "grad_norm": 1.0022552013397217, "learning_rate": 0.00010646057544357102, "loss": 0.5532282829284668, "step": 283270 }, { "epoch": 1.6838751478621656, "grad_norm": 1.553498387336731, "learning_rate": 0.00010645435549823841, "loss": 0.5504483222961426, "step": 283280 }, { "epoch": 1.683934589938834, "grad_norm": 1.400459885597229, "learning_rate": 0.00010644813556986704, "loss": 0.5329093933105469, "step": 283290 }, { "epoch": 1.6839940320155025, "grad_norm": 1.5222545862197876, "learning_rate": 0.00010644191565848662, "loss": 0.5431140899658203, "step": 283300 }, { "epoch": 1.6840534740921709, "grad_norm": 1.750196933746338, "learning_rate": 0.00010643569576412693, "loss": 0.5745128154754638, "step": 283310 }, { "epoch": 1.6841129161688393, "grad_norm": 1.245914340019226, "learning_rate": 0.00010642947588681764, "loss": 0.525859260559082, "step": 283320 }, { "epoch": 1.6841723582455077, "grad_norm": 1.3344814777374268, "learning_rate": 0.00010642325602658862, "loss": 0.5557984352111817, "step": 283330 }, { "epoch": 1.6842318003221761, "grad_norm": 1.68370521068573, "learning_rate": 0.00010641703618346961, "loss": 0.5518486022949218, "step": 283340 }, { "epoch": 1.6842912423988445, "grad_norm": 1.4245319366455078, "learning_rate": 0.00010641081635749024, "loss": 0.5453985214233399, "step": 283350 }, { "epoch": 1.684350684475513, "grad_norm": 1.1778948307037354, "learning_rate": 0.00010640459654868043, "loss": 0.5570023536682129, "step": 283360 }, { "epoch": 1.6844101265521814, "grad_norm": 1.8364267349243164, "learning_rate": 0.00010639837675706983, "loss": 0.6047844886779785, "step": 283370 }, { "epoch": 1.6844695686288498, "grad_norm": 1.520207166671753, "learning_rate": 0.00010639215698268818, "loss": 0.5552468299865723, "step": 283380 }, { "epoch": 1.684529010705518, "grad_norm": 1.4206805229187012, "learning_rate": 0.00010638593722556531, "loss": 0.5983626365661621, "step": 283390 }, { "epoch": 1.6845884527821864, "grad_norm": 1.4961401224136353, "learning_rate": 0.00010637971748573096, "loss": 0.6065733432769775, "step": 283400 }, { "epoch": 1.6846478948588548, "grad_norm": 1.272873878479004, "learning_rate": 0.0001063734977632148, "loss": 0.47173609733581545, "step": 283410 }, { "epoch": 1.6847073369355232, "grad_norm": 1.4399983882904053, "learning_rate": 0.00010636727805804667, "loss": 0.5457600593566895, "step": 283420 }, { "epoch": 1.6847667790121914, "grad_norm": 1.344909429550171, "learning_rate": 0.00010636105837025632, "loss": 0.5399511337280274, "step": 283430 }, { "epoch": 1.6848262210888598, "grad_norm": 1.3791254758834839, "learning_rate": 0.00010635483869987346, "loss": 0.5924122333526611, "step": 283440 }, { "epoch": 1.6848856631655282, "grad_norm": 1.3640602827072144, "learning_rate": 0.00010634861904692783, "loss": 0.55416259765625, "step": 283450 }, { "epoch": 1.6849451052421967, "grad_norm": 1.4762247800827026, "learning_rate": 0.00010634239941144926, "loss": 0.5676022529602051, "step": 283460 }, { "epoch": 1.685004547318865, "grad_norm": 1.1975077390670776, "learning_rate": 0.00010633617979346743, "loss": 0.528831958770752, "step": 283470 }, { "epoch": 1.6850639893955335, "grad_norm": 1.8201463222503662, "learning_rate": 0.00010632996019301209, "loss": 0.5808175086975098, "step": 283480 }, { "epoch": 1.685123431472202, "grad_norm": 1.3459111452102661, "learning_rate": 0.00010632374061011308, "loss": 0.5150993347167969, "step": 283490 }, { "epoch": 1.6851828735488703, "grad_norm": 1.6360291242599487, "learning_rate": 0.00010631752104480006, "loss": 0.5433302879333496, "step": 283500 }, { "epoch": 1.6852423156255387, "grad_norm": 1.2895933389663696, "learning_rate": 0.00010631130149710282, "loss": 0.5253281593322754, "step": 283510 }, { "epoch": 1.6853017577022071, "grad_norm": 1.1786879301071167, "learning_rate": 0.00010630508196705111, "loss": 0.5490678787231446, "step": 283520 }, { "epoch": 1.6853611997788756, "grad_norm": 1.5097559690475464, "learning_rate": 0.00010629886245467468, "loss": 0.5330606460571289, "step": 283530 }, { "epoch": 1.685420641855544, "grad_norm": 1.5725035667419434, "learning_rate": 0.00010629264296000328, "loss": 0.5426620483398438, "step": 283540 }, { "epoch": 1.6854800839322124, "grad_norm": 1.5361075401306152, "learning_rate": 0.00010628642348306665, "loss": 0.5539607048034668, "step": 283550 }, { "epoch": 1.6855395260088808, "grad_norm": 1.2584285736083984, "learning_rate": 0.00010628020402389459, "loss": 0.5385480880737304, "step": 283560 }, { "epoch": 1.685598968085549, "grad_norm": 1.577347993850708, "learning_rate": 0.00010627398458251681, "loss": 0.529170036315918, "step": 283570 }, { "epoch": 1.6856584101622174, "grad_norm": 1.3491920232772827, "learning_rate": 0.00010626776515896304, "loss": 0.5972852230072021, "step": 283580 }, { "epoch": 1.6857178522388858, "grad_norm": 1.45701265335083, "learning_rate": 0.0001062615457532631, "loss": 0.5197938919067383, "step": 283590 }, { "epoch": 1.6857772943155542, "grad_norm": 1.4697489738464355, "learning_rate": 0.00010625532636544669, "loss": 0.5871752738952637, "step": 283600 }, { "epoch": 1.6858367363922226, "grad_norm": 1.3670552968978882, "learning_rate": 0.00010624910699554356, "loss": 0.5749241828918457, "step": 283610 }, { "epoch": 1.6858961784688908, "grad_norm": 1.3330802917480469, "learning_rate": 0.00010624288764358348, "loss": 0.5775631904602051, "step": 283620 }, { "epoch": 1.6859556205455593, "grad_norm": 1.6695036888122559, "learning_rate": 0.00010623666830959623, "loss": 0.5526260375976563, "step": 283630 }, { "epoch": 1.6860150626222277, "grad_norm": 1.97911536693573, "learning_rate": 0.00010623044899361147, "loss": 0.6009580612182617, "step": 283640 }, { "epoch": 1.686074504698896, "grad_norm": 1.1315537691116333, "learning_rate": 0.00010622422969565906, "loss": 0.5233779907226562, "step": 283650 }, { "epoch": 1.6861339467755645, "grad_norm": 1.3719420433044434, "learning_rate": 0.00010621801041576869, "loss": 0.5669726371765137, "step": 283660 }, { "epoch": 1.686193388852233, "grad_norm": 1.0890614986419678, "learning_rate": 0.00010621179115397013, "loss": 0.5131096839904785, "step": 283670 }, { "epoch": 1.6862528309289013, "grad_norm": 1.4320341348648071, "learning_rate": 0.0001062055719102931, "loss": 0.5536081790924072, "step": 283680 }, { "epoch": 1.6863122730055697, "grad_norm": 1.6400030851364136, "learning_rate": 0.00010619935268476737, "loss": 0.5376447677612305, "step": 283690 }, { "epoch": 1.6863717150822382, "grad_norm": 1.768619418144226, "learning_rate": 0.00010619313347742272, "loss": 0.567837142944336, "step": 283700 }, { "epoch": 1.6864311571589066, "grad_norm": 1.844695806503296, "learning_rate": 0.00010618691428828887, "loss": 0.5840354919433594, "step": 283710 }, { "epoch": 1.686490599235575, "grad_norm": 1.5351768732070923, "learning_rate": 0.00010618069511739557, "loss": 0.6069360733032226, "step": 283720 }, { "epoch": 1.6865500413122434, "grad_norm": 1.6076312065124512, "learning_rate": 0.00010617447596477256, "loss": 0.5954309463500976, "step": 283730 }, { "epoch": 1.6866094833889118, "grad_norm": 1.6282321214675903, "learning_rate": 0.00010616825683044963, "loss": 0.5631169319152832, "step": 283740 }, { "epoch": 1.6866689254655802, "grad_norm": 1.2480542659759521, "learning_rate": 0.0001061620377144565, "loss": 0.574192476272583, "step": 283750 }, { "epoch": 1.6867283675422484, "grad_norm": 1.427718997001648, "learning_rate": 0.00010615581861682293, "loss": 0.5485416889190674, "step": 283760 }, { "epoch": 1.6867878096189168, "grad_norm": 1.4811277389526367, "learning_rate": 0.00010614959953757866, "loss": 0.5757204532623291, "step": 283770 }, { "epoch": 1.6868472516955852, "grad_norm": 1.2458525896072388, "learning_rate": 0.00010614338047675345, "loss": 0.5566542625427247, "step": 283780 }, { "epoch": 1.6869066937722537, "grad_norm": 1.4600588083267212, "learning_rate": 0.00010613716143437706, "loss": 0.5423516273498535, "step": 283790 }, { "epoch": 1.6869661358489219, "grad_norm": 1.3391668796539307, "learning_rate": 0.00010613094241047925, "loss": 0.5498542308807373, "step": 283800 }, { "epoch": 1.6870255779255903, "grad_norm": 1.4109281301498413, "learning_rate": 0.00010612472340508967, "loss": 0.5772741317749024, "step": 283810 }, { "epoch": 1.6870850200022587, "grad_norm": 1.4303131103515625, "learning_rate": 0.0001061185044182382, "loss": 0.49211583137512205, "step": 283820 }, { "epoch": 1.687144462078927, "grad_norm": 1.2006902694702148, "learning_rate": 0.00010611228544995456, "loss": 0.5304235458374024, "step": 283830 }, { "epoch": 1.6872039041555955, "grad_norm": 1.467810034751892, "learning_rate": 0.00010610606650026842, "loss": 0.595180606842041, "step": 283840 }, { "epoch": 1.687263346232264, "grad_norm": 1.6283695697784424, "learning_rate": 0.00010609984756920962, "loss": 0.5464684963226318, "step": 283850 }, { "epoch": 1.6873227883089323, "grad_norm": 1.684942603111267, "learning_rate": 0.00010609362865680787, "loss": 0.558186149597168, "step": 283860 }, { "epoch": 1.6873822303856008, "grad_norm": 1.8578517436981201, "learning_rate": 0.00010608740976309288, "loss": 0.6243502616882324, "step": 283870 }, { "epoch": 1.6874416724622692, "grad_norm": 1.4747047424316406, "learning_rate": 0.00010608119088809449, "loss": 0.5708138942718506, "step": 283880 }, { "epoch": 1.6875011145389376, "grad_norm": 1.4438633918762207, "learning_rate": 0.00010607497203184243, "loss": 0.5721930503845215, "step": 283890 }, { "epoch": 1.687560556615606, "grad_norm": 1.2082961797714233, "learning_rate": 0.00010606875319436636, "loss": 0.5465498924255371, "step": 283900 }, { "epoch": 1.6876199986922744, "grad_norm": 1.3280001878738403, "learning_rate": 0.0001060625343756961, "loss": 0.5563525199890137, "step": 283910 }, { "epoch": 1.6876794407689428, "grad_norm": 1.7553174495697021, "learning_rate": 0.00010605631557586144, "loss": 0.6384777069091797, "step": 283920 }, { "epoch": 1.6877388828456112, "grad_norm": 1.1028889417648315, "learning_rate": 0.00010605009679489204, "loss": 0.5652180194854737, "step": 283930 }, { "epoch": 1.6877983249222794, "grad_norm": 1.5991544723510742, "learning_rate": 0.00010604387803281765, "loss": 0.5349342823028564, "step": 283940 }, { "epoch": 1.6878577669989479, "grad_norm": 1.561063528060913, "learning_rate": 0.00010603765928966813, "loss": 0.5944108009338379, "step": 283950 }, { "epoch": 1.6879172090756163, "grad_norm": 1.444150447845459, "learning_rate": 0.00010603144056547312, "loss": 0.5449189186096192, "step": 283960 }, { "epoch": 1.6879766511522847, "grad_norm": 1.5142349004745483, "learning_rate": 0.00010602522186026236, "loss": 0.5906659126281738, "step": 283970 }, { "epoch": 1.688036093228953, "grad_norm": 1.2829248905181885, "learning_rate": 0.0001060190031740657, "loss": 0.5476871013641358, "step": 283980 }, { "epoch": 1.6880955353056213, "grad_norm": 1.7345302104949951, "learning_rate": 0.00010601278450691282, "loss": 0.5597342491149903, "step": 283990 }, { "epoch": 1.6881549773822897, "grad_norm": 1.4118380546569824, "learning_rate": 0.00010600656585883342, "loss": 0.5960543155670166, "step": 284000 }, { "epoch": 1.6882144194589581, "grad_norm": 1.2026710510253906, "learning_rate": 0.00010600034722985736, "loss": 0.51730375289917, "step": 284010 }, { "epoch": 1.6882738615356265, "grad_norm": 1.2808234691619873, "learning_rate": 0.00010599412862001433, "loss": 0.5805209159851075, "step": 284020 }, { "epoch": 1.688333303612295, "grad_norm": 1.260114312171936, "learning_rate": 0.00010598791002933406, "loss": 0.5236507415771484, "step": 284030 }, { "epoch": 1.6883927456889634, "grad_norm": 1.3038098812103271, "learning_rate": 0.00010598169145784629, "loss": 0.5489434242248535, "step": 284040 }, { "epoch": 1.6884521877656318, "grad_norm": 1.4959442615509033, "learning_rate": 0.00010597547290558085, "loss": 0.5587817192077636, "step": 284050 }, { "epoch": 1.6885116298423002, "grad_norm": 1.4347654581069946, "learning_rate": 0.00010596925437256742, "loss": 0.5748158454895019, "step": 284060 }, { "epoch": 1.6885710719189686, "grad_norm": 1.2487491369247437, "learning_rate": 0.00010596303585883572, "loss": 0.5221502304077148, "step": 284070 }, { "epoch": 1.688630513995637, "grad_norm": 1.3170217275619507, "learning_rate": 0.00010595681736441558, "loss": 0.5331693172454834, "step": 284080 }, { "epoch": 1.6886899560723054, "grad_norm": 1.519345760345459, "learning_rate": 0.0001059505988893367, "loss": 0.5633388519287109, "step": 284090 }, { "epoch": 1.6887493981489738, "grad_norm": 1.2865976095199585, "learning_rate": 0.0001059443804336288, "loss": 0.5432920455932617, "step": 284100 }, { "epoch": 1.6888088402256423, "grad_norm": 1.2683664560317993, "learning_rate": 0.00010593816199732167, "loss": 0.511699914932251, "step": 284110 }, { "epoch": 1.6888682823023107, "grad_norm": 1.204930305480957, "learning_rate": 0.00010593194358044507, "loss": 0.5532489776611328, "step": 284120 }, { "epoch": 1.6889277243789789, "grad_norm": 2.3018691539764404, "learning_rate": 0.0001059257251830287, "loss": 0.6386602401733399, "step": 284130 }, { "epoch": 1.6889871664556473, "grad_norm": 1.2130595445632935, "learning_rate": 0.00010591950680510235, "loss": 0.533912181854248, "step": 284140 }, { "epoch": 1.6890466085323157, "grad_norm": 1.3315621614456177, "learning_rate": 0.00010591328844669573, "loss": 0.5962541580200196, "step": 284150 }, { "epoch": 1.689106050608984, "grad_norm": 1.372069001197815, "learning_rate": 0.00010590707010783863, "loss": 0.549370002746582, "step": 284160 }, { "epoch": 1.6891654926856523, "grad_norm": 1.2919890880584717, "learning_rate": 0.0001059008517885607, "loss": 0.5995865345001221, "step": 284170 }, { "epoch": 1.6892249347623207, "grad_norm": 1.5448559522628784, "learning_rate": 0.00010589463348889181, "loss": 0.5816925048828125, "step": 284180 }, { "epoch": 1.6892843768389891, "grad_norm": 1.5416830778121948, "learning_rate": 0.00010588841520886166, "loss": 0.571451473236084, "step": 284190 }, { "epoch": 1.6893438189156575, "grad_norm": 1.427098035812378, "learning_rate": 0.00010588219694849996, "loss": 0.5025591850280762, "step": 284200 }, { "epoch": 1.689403260992326, "grad_norm": 1.0749984979629517, "learning_rate": 0.00010587597870783649, "loss": 0.5036385536193848, "step": 284210 }, { "epoch": 1.6894627030689944, "grad_norm": 1.4058465957641602, "learning_rate": 0.000105869760486901, "loss": 0.5822380542755127, "step": 284220 }, { "epoch": 1.6895221451456628, "grad_norm": 1.3121275901794434, "learning_rate": 0.00010586354228572322, "loss": 0.5715702056884766, "step": 284230 }, { "epoch": 1.6895815872223312, "grad_norm": 1.1159541606903076, "learning_rate": 0.00010585732410433289, "loss": 0.6103668212890625, "step": 284240 }, { "epoch": 1.6896410292989996, "grad_norm": 1.4152404069900513, "learning_rate": 0.0001058511059427598, "loss": 0.5628079891204834, "step": 284250 }, { "epoch": 1.689700471375668, "grad_norm": 1.475023627281189, "learning_rate": 0.00010584488780103363, "loss": 0.5894817352294922, "step": 284260 }, { "epoch": 1.6897599134523364, "grad_norm": 1.4360202550888062, "learning_rate": 0.00010583866967918416, "loss": 0.5518963813781739, "step": 284270 }, { "epoch": 1.6898193555290049, "grad_norm": 1.5222954750061035, "learning_rate": 0.00010583245157724115, "loss": 0.6126328468322754, "step": 284280 }, { "epoch": 1.6898787976056733, "grad_norm": 1.3111971616744995, "learning_rate": 0.00010582623349523438, "loss": 0.5654887676239013, "step": 284290 }, { "epoch": 1.6899382396823417, "grad_norm": 1.5330761671066284, "learning_rate": 0.00010582001543319345, "loss": 0.5766540050506592, "step": 284300 }, { "epoch": 1.6899976817590099, "grad_norm": 1.3437644243240356, "learning_rate": 0.00010581379739114823, "loss": 0.5236135482788086, "step": 284310 }, { "epoch": 1.6900571238356783, "grad_norm": 1.1395255327224731, "learning_rate": 0.00010580757936912849, "loss": 0.5181029319763184, "step": 284320 }, { "epoch": 1.6901165659123467, "grad_norm": 1.4798777103424072, "learning_rate": 0.00010580136136716383, "loss": 0.5823904991149902, "step": 284330 }, { "epoch": 1.6901760079890151, "grad_norm": 1.2505394220352173, "learning_rate": 0.00010579514338528414, "loss": 0.5001377105712891, "step": 284340 }, { "epoch": 1.6902354500656835, "grad_norm": 1.8072339296340942, "learning_rate": 0.00010578892542351913, "loss": 0.5765997886657714, "step": 284350 }, { "epoch": 1.6902948921423517, "grad_norm": 1.340050458908081, "learning_rate": 0.00010578270748189846, "loss": 0.5469926357269287, "step": 284360 }, { "epoch": 1.6903543342190201, "grad_norm": 1.716684341430664, "learning_rate": 0.00010577648956045199, "loss": 0.5326193809509278, "step": 284370 }, { "epoch": 1.6904137762956886, "grad_norm": 1.3113009929656982, "learning_rate": 0.00010577027165920941, "loss": 0.5458146095275879, "step": 284380 }, { "epoch": 1.690473218372357, "grad_norm": 1.1859468221664429, "learning_rate": 0.00010576405377820042, "loss": 0.5299933433532715, "step": 284390 }, { "epoch": 1.6905326604490254, "grad_norm": 1.4147334098815918, "learning_rate": 0.00010575783591745487, "loss": 0.6101806640625, "step": 284400 }, { "epoch": 1.6905921025256938, "grad_norm": 1.3366472721099854, "learning_rate": 0.00010575161807700245, "loss": 0.5744216442108154, "step": 284410 }, { "epoch": 1.6906515446023622, "grad_norm": 1.564911127090454, "learning_rate": 0.00010574540025687288, "loss": 0.5475884437561035, "step": 284420 }, { "epoch": 1.6907109866790306, "grad_norm": 1.1950188875198364, "learning_rate": 0.00010573918245709588, "loss": 0.6152808666229248, "step": 284430 }, { "epoch": 1.690770428755699, "grad_norm": 1.407675862312317, "learning_rate": 0.00010573296467770131, "loss": 0.5322688102722168, "step": 284440 }, { "epoch": 1.6908298708323675, "grad_norm": 1.2351363897323608, "learning_rate": 0.00010572674691871882, "loss": 0.5990582466125488, "step": 284450 }, { "epoch": 1.6908893129090359, "grad_norm": 1.533674955368042, "learning_rate": 0.00010572052918017814, "loss": 0.5865435600280762, "step": 284460 }, { "epoch": 1.6909487549857043, "grad_norm": 1.4783482551574707, "learning_rate": 0.0001057143114621091, "loss": 0.5753148555755615, "step": 284470 }, { "epoch": 1.6910081970623727, "grad_norm": 1.808478832244873, "learning_rate": 0.00010570809376454138, "loss": 0.6061280250549317, "step": 284480 }, { "epoch": 1.6910676391390411, "grad_norm": 1.497083067893982, "learning_rate": 0.0001057018760875047, "loss": 0.5406270503997803, "step": 284490 }, { "epoch": 1.6911270812157093, "grad_norm": 1.4355758428573608, "learning_rate": 0.0001056956584310289, "loss": 0.5599777221679687, "step": 284500 }, { "epoch": 1.6911865232923777, "grad_norm": 1.5021520853042603, "learning_rate": 0.00010568944079514363, "loss": 0.5697604179382324, "step": 284510 }, { "epoch": 1.6912459653690461, "grad_norm": 1.3827776908874512, "learning_rate": 0.00010568322317987867, "loss": 0.5918384552001953, "step": 284520 }, { "epoch": 1.6913054074457146, "grad_norm": 1.3776546716690063, "learning_rate": 0.00010567700558526375, "loss": 0.5604610443115234, "step": 284530 }, { "epoch": 1.6913648495223828, "grad_norm": 1.4491060972213745, "learning_rate": 0.00010567078801132863, "loss": 0.5731820106506348, "step": 284540 }, { "epoch": 1.6914242915990512, "grad_norm": 1.4395123720169067, "learning_rate": 0.00010566457045810305, "loss": 0.5747905731201172, "step": 284550 }, { "epoch": 1.6914837336757196, "grad_norm": 1.592936635017395, "learning_rate": 0.00010565835292561672, "loss": 0.5685959815979004, "step": 284560 }, { "epoch": 1.691543175752388, "grad_norm": 1.7138235569000244, "learning_rate": 0.00010565213541389944, "loss": 0.5135985374450683, "step": 284570 }, { "epoch": 1.6916026178290564, "grad_norm": 1.4305288791656494, "learning_rate": 0.00010564591792298093, "loss": 0.579454755783081, "step": 284580 }, { "epoch": 1.6916620599057248, "grad_norm": 1.7181799411773682, "learning_rate": 0.00010563970045289092, "loss": 0.5752486228942871, "step": 284590 }, { "epoch": 1.6917215019823932, "grad_norm": 1.9626140594482422, "learning_rate": 0.00010563348300365915, "loss": 0.6011774063110351, "step": 284600 }, { "epoch": 1.6917809440590617, "grad_norm": 1.1623640060424805, "learning_rate": 0.00010562726557531537, "loss": 0.5323690414428711, "step": 284610 }, { "epoch": 1.69184038613573, "grad_norm": 1.6052956581115723, "learning_rate": 0.00010562104816788931, "loss": 0.5964521408081055, "step": 284620 }, { "epoch": 1.6918998282123985, "grad_norm": 1.619355320930481, "learning_rate": 0.00010561483078141077, "loss": 0.5465831279754638, "step": 284630 }, { "epoch": 1.691959270289067, "grad_norm": 1.5554965734481812, "learning_rate": 0.00010560861341590941, "loss": 0.558988380432129, "step": 284640 }, { "epoch": 1.6920187123657353, "grad_norm": 1.255866527557373, "learning_rate": 0.00010560239607141503, "loss": 0.5625861644744873, "step": 284650 }, { "epoch": 1.6920781544424037, "grad_norm": 1.994306206703186, "learning_rate": 0.00010559617874795731, "loss": 0.5958840370178222, "step": 284660 }, { "epoch": 1.6921375965190721, "grad_norm": 1.0402038097381592, "learning_rate": 0.00010558996144556606, "loss": 0.5173946857452393, "step": 284670 }, { "epoch": 1.6921970385957403, "grad_norm": 1.32267427444458, "learning_rate": 0.000105583744164271, "loss": 0.5310515403747559, "step": 284680 }, { "epoch": 1.6922564806724087, "grad_norm": 1.257025957107544, "learning_rate": 0.00010557752690410183, "loss": 0.568575668334961, "step": 284690 }, { "epoch": 1.6923159227490772, "grad_norm": 1.906712293624878, "learning_rate": 0.00010557130966508837, "loss": 0.5480582237243652, "step": 284700 }, { "epoch": 1.6923753648257456, "grad_norm": 1.5800535678863525, "learning_rate": 0.00010556509244726029, "loss": 0.5695264339447021, "step": 284710 }, { "epoch": 1.692434806902414, "grad_norm": 1.583482027053833, "learning_rate": 0.00010555887525064736, "loss": 0.6103946685791015, "step": 284720 }, { "epoch": 1.6924942489790822, "grad_norm": 1.1566603183746338, "learning_rate": 0.00010555265807527932, "loss": 0.5020594596862793, "step": 284730 }, { "epoch": 1.6925536910557506, "grad_norm": 1.5276668071746826, "learning_rate": 0.00010554644092118592, "loss": 0.6376070022583008, "step": 284740 }, { "epoch": 1.692613133132419, "grad_norm": 1.208199381828308, "learning_rate": 0.00010554022378839688, "loss": 0.5902193069458008, "step": 284750 }, { "epoch": 1.6926725752090874, "grad_norm": 1.3664966821670532, "learning_rate": 0.00010553400667694198, "loss": 0.5869463920593262, "step": 284760 }, { "epoch": 1.6927320172857558, "grad_norm": 1.4908857345581055, "learning_rate": 0.00010552778958685091, "loss": 0.5900591850280762, "step": 284770 }, { "epoch": 1.6927914593624243, "grad_norm": 1.347809076309204, "learning_rate": 0.00010552157251815342, "loss": 0.5490671157836914, "step": 284780 }, { "epoch": 1.6928509014390927, "grad_norm": 1.2302815914154053, "learning_rate": 0.00010551535547087928, "loss": 0.5583498001098632, "step": 284790 }, { "epoch": 1.692910343515761, "grad_norm": 1.7201091051101685, "learning_rate": 0.00010550913844505822, "loss": 0.5258745193481446, "step": 284800 }, { "epoch": 1.6929697855924295, "grad_norm": 1.3613231182098389, "learning_rate": 0.00010550292144071996, "loss": 0.5266964912414551, "step": 284810 }, { "epoch": 1.693029227669098, "grad_norm": 0.9382036328315735, "learning_rate": 0.00010549670445789423, "loss": 0.4971647262573242, "step": 284820 }, { "epoch": 1.6930886697457663, "grad_norm": 1.4381182193756104, "learning_rate": 0.00010549048749661086, "loss": 0.5811882019042969, "step": 284830 }, { "epoch": 1.6931481118224347, "grad_norm": 1.0475462675094604, "learning_rate": 0.00010548427055689948, "loss": 0.5978156089782715, "step": 284840 }, { "epoch": 1.6932075538991032, "grad_norm": 1.4895193576812744, "learning_rate": 0.00010547805363878987, "loss": 0.5624959945678711, "step": 284850 }, { "epoch": 1.6932669959757716, "grad_norm": 1.2949974536895752, "learning_rate": 0.0001054718367423118, "loss": 0.5762382030487061, "step": 284860 }, { "epoch": 1.6933264380524398, "grad_norm": 1.3920987844467163, "learning_rate": 0.00010546561986749497, "loss": 0.6371088027954102, "step": 284870 }, { "epoch": 1.6933858801291082, "grad_norm": 1.4185765981674194, "learning_rate": 0.00010545940301436916, "loss": 0.568147087097168, "step": 284880 }, { "epoch": 1.6934453222057766, "grad_norm": 1.7430003881454468, "learning_rate": 0.000105453186182964, "loss": 0.5718199729919433, "step": 284890 }, { "epoch": 1.693504764282445, "grad_norm": 1.1163989305496216, "learning_rate": 0.0001054469693733094, "loss": 0.5638031959533691, "step": 284900 }, { "epoch": 1.6935642063591132, "grad_norm": 1.2225041389465332, "learning_rate": 0.00010544075258543498, "loss": 0.5775356292724609, "step": 284910 }, { "epoch": 1.6936236484357816, "grad_norm": 1.7198452949523926, "learning_rate": 0.00010543453581937049, "loss": 0.5843596458435059, "step": 284920 }, { "epoch": 1.69368309051245, "grad_norm": 1.3885624408721924, "learning_rate": 0.00010542831907514572, "loss": 0.5952234268188477, "step": 284930 }, { "epoch": 1.6937425325891184, "grad_norm": 1.3289815187454224, "learning_rate": 0.00010542210235279038, "loss": 0.6022600650787353, "step": 284940 }, { "epoch": 1.6938019746657869, "grad_norm": 1.7567604780197144, "learning_rate": 0.00010541588565233414, "loss": 0.5841172218322754, "step": 284950 }, { "epoch": 1.6938614167424553, "grad_norm": 1.454141616821289, "learning_rate": 0.00010540966897380689, "loss": 0.5500327587127686, "step": 284960 }, { "epoch": 1.6939208588191237, "grad_norm": 1.5899064540863037, "learning_rate": 0.00010540345231723822, "loss": 0.5606705665588378, "step": 284970 }, { "epoch": 1.693980300895792, "grad_norm": 1.1842602491378784, "learning_rate": 0.00010539723568265794, "loss": 0.5252754211425781, "step": 284980 }, { "epoch": 1.6940397429724605, "grad_norm": 1.5776256322860718, "learning_rate": 0.00010539101907009583, "loss": 0.5748814582824707, "step": 284990 }, { "epoch": 1.694099185049129, "grad_norm": 1.4159846305847168, "learning_rate": 0.00010538480247958156, "loss": 0.5946097850799561, "step": 285000 }, { "epoch": 1.6941586271257973, "grad_norm": 1.580676555633545, "learning_rate": 0.00010537858591114487, "loss": 0.579805850982666, "step": 285010 }, { "epoch": 1.6942180692024658, "grad_norm": 1.4837058782577515, "learning_rate": 0.00010537236936481549, "loss": 0.5700339317321778, "step": 285020 }, { "epoch": 1.6942775112791342, "grad_norm": 1.2257364988327026, "learning_rate": 0.00010536615284062324, "loss": 0.5387882709503173, "step": 285030 }, { "epoch": 1.6943369533558026, "grad_norm": 1.5056532621383667, "learning_rate": 0.00010535993633859778, "loss": 0.6321852207183838, "step": 285040 }, { "epoch": 1.6943963954324708, "grad_norm": 1.5127718448638916, "learning_rate": 0.00010535371985876883, "loss": 0.5810171127319336, "step": 285050 }, { "epoch": 1.6944558375091392, "grad_norm": 1.4734523296356201, "learning_rate": 0.00010534750340116619, "loss": 0.6266977310180664, "step": 285060 }, { "epoch": 1.6945152795858076, "grad_norm": 1.5316932201385498, "learning_rate": 0.0001053412869658196, "loss": 0.5467885971069336, "step": 285070 }, { "epoch": 1.694574721662476, "grad_norm": 1.3509465456008911, "learning_rate": 0.00010533507055275872, "loss": 0.5028748989105225, "step": 285080 }, { "epoch": 1.6946341637391444, "grad_norm": 1.4368687868118286, "learning_rate": 0.0001053288541620134, "loss": 0.5714674949645996, "step": 285090 }, { "epoch": 1.6946936058158126, "grad_norm": 1.2511147260665894, "learning_rate": 0.00010532263779361327, "loss": 0.57966628074646, "step": 285100 }, { "epoch": 1.694753047892481, "grad_norm": 1.5335016250610352, "learning_rate": 0.00010531642144758811, "loss": 0.5952237129211426, "step": 285110 }, { "epoch": 1.6948124899691495, "grad_norm": 1.4853745698928833, "learning_rate": 0.00010531020512396768, "loss": 0.5660533905029297, "step": 285120 }, { "epoch": 1.6948719320458179, "grad_norm": 1.5130703449249268, "learning_rate": 0.00010530398882278169, "loss": 0.5312314033508301, "step": 285130 }, { "epoch": 1.6949313741224863, "grad_norm": 1.2822718620300293, "learning_rate": 0.0001052977725440599, "loss": 0.5691602230072021, "step": 285140 }, { "epoch": 1.6949908161991547, "grad_norm": 1.5371522903442383, "learning_rate": 0.00010529155628783198, "loss": 0.5866746425628662, "step": 285150 }, { "epoch": 1.6950502582758231, "grad_norm": 1.4803670644760132, "learning_rate": 0.00010528534005412775, "loss": 0.5359624862670899, "step": 285160 }, { "epoch": 1.6951097003524915, "grad_norm": 1.3005856275558472, "learning_rate": 0.00010527912384297694, "loss": 0.5720944404602051, "step": 285170 }, { "epoch": 1.69516914242916, "grad_norm": 1.4234904050827026, "learning_rate": 0.0001052729076544092, "loss": 0.5566855430603027, "step": 285180 }, { "epoch": 1.6952285845058284, "grad_norm": 1.3513716459274292, "learning_rate": 0.00010526669148845436, "loss": 0.5480667114257812, "step": 285190 }, { "epoch": 1.6952880265824968, "grad_norm": 1.5797834396362305, "learning_rate": 0.00010526047534514212, "loss": 0.5516053676605225, "step": 285200 }, { "epoch": 1.6953474686591652, "grad_norm": 1.3803743124008179, "learning_rate": 0.00010525425922450221, "loss": 0.504778242111206, "step": 285210 }, { "epoch": 1.6954069107358336, "grad_norm": 1.677282452583313, "learning_rate": 0.00010524804312656438, "loss": 0.5554235935211181, "step": 285220 }, { "epoch": 1.695466352812502, "grad_norm": 1.227247953414917, "learning_rate": 0.00010524182705135834, "loss": 0.571556568145752, "step": 285230 }, { "epoch": 1.6955257948891702, "grad_norm": 1.496272087097168, "learning_rate": 0.00010523561099891386, "loss": 0.566733980178833, "step": 285240 }, { "epoch": 1.6955852369658386, "grad_norm": 1.0969818830490112, "learning_rate": 0.00010522939496926067, "loss": 0.547388744354248, "step": 285250 }, { "epoch": 1.695644679042507, "grad_norm": 1.0689505338668823, "learning_rate": 0.00010522317896242849, "loss": 0.6015982627868652, "step": 285260 }, { "epoch": 1.6957041211191755, "grad_norm": 1.4419035911560059, "learning_rate": 0.00010521696297844705, "loss": 0.5706457138061524, "step": 285270 }, { "epoch": 1.6957635631958436, "grad_norm": 1.421248197555542, "learning_rate": 0.0001052107470173461, "loss": 0.5905683517456055, "step": 285280 }, { "epoch": 1.695823005272512, "grad_norm": 1.3457396030426025, "learning_rate": 0.00010520453107915536, "loss": 0.5905019760131835, "step": 285290 }, { "epoch": 1.6958824473491805, "grad_norm": 1.4217411279678345, "learning_rate": 0.0001051983151639046, "loss": 0.5827902793884278, "step": 285300 }, { "epoch": 1.695941889425849, "grad_norm": 1.3071528673171997, "learning_rate": 0.0001051920992716235, "loss": 0.5212997436523438, "step": 285310 }, { "epoch": 1.6960013315025173, "grad_norm": 1.630354404449463, "learning_rate": 0.00010518588340234185, "loss": 0.6178828239440918, "step": 285320 }, { "epoch": 1.6960607735791857, "grad_norm": 1.4155535697937012, "learning_rate": 0.00010517966755608936, "loss": 0.5815265655517579, "step": 285330 }, { "epoch": 1.6961202156558541, "grad_norm": 1.3908451795578003, "learning_rate": 0.00010517345173289575, "loss": 0.6000093936920166, "step": 285340 }, { "epoch": 1.6961796577325225, "grad_norm": 1.3170591592788696, "learning_rate": 0.00010516723593279079, "loss": 0.5697590827941894, "step": 285350 }, { "epoch": 1.696239099809191, "grad_norm": 1.7209590673446655, "learning_rate": 0.00010516102015580418, "loss": 0.5838443756103515, "step": 285360 }, { "epoch": 1.6962985418858594, "grad_norm": 0.998649001121521, "learning_rate": 0.0001051548044019657, "loss": 0.5179179668426513, "step": 285370 }, { "epoch": 1.6963579839625278, "grad_norm": 1.9707372188568115, "learning_rate": 0.000105148588671305, "loss": 0.5866031646728516, "step": 285380 }, { "epoch": 1.6964174260391962, "grad_norm": 1.4829802513122559, "learning_rate": 0.0001051423729638519, "loss": 0.5531651973724365, "step": 285390 }, { "epoch": 1.6964768681158646, "grad_norm": 1.437252163887024, "learning_rate": 0.00010513615727963611, "loss": 0.6290216445922852, "step": 285400 }, { "epoch": 1.696536310192533, "grad_norm": 1.7705391645431519, "learning_rate": 0.0001051299416186873, "loss": 0.5477003574371337, "step": 285410 }, { "epoch": 1.6965957522692012, "grad_norm": 1.6296322345733643, "learning_rate": 0.0001051237259810353, "loss": 0.5854908466339112, "step": 285420 }, { "epoch": 1.6966551943458696, "grad_norm": 1.4488530158996582, "learning_rate": 0.00010511751036670982, "loss": 0.6000704765319824, "step": 285430 }, { "epoch": 1.696714636422538, "grad_norm": 1.506463885307312, "learning_rate": 0.00010511129477574051, "loss": 0.5326203346252442, "step": 285440 }, { "epoch": 1.6967740784992065, "grad_norm": 1.6631113290786743, "learning_rate": 0.0001051050792081572, "loss": 0.5516935348510742, "step": 285450 }, { "epoch": 1.6968335205758749, "grad_norm": 1.9219573736190796, "learning_rate": 0.00010509886366398964, "loss": 0.6316288948059082, "step": 285460 }, { "epoch": 1.696892962652543, "grad_norm": 1.8792901039123535, "learning_rate": 0.00010509264814326743, "loss": 0.5659097671508789, "step": 285470 }, { "epoch": 1.6969524047292115, "grad_norm": 0.8403619527816772, "learning_rate": 0.00010508643264602045, "loss": 0.5455270767211914, "step": 285480 }, { "epoch": 1.69701184680588, "grad_norm": 1.1108641624450684, "learning_rate": 0.00010508021717227836, "loss": 0.5580318450927735, "step": 285490 }, { "epoch": 1.6970712888825483, "grad_norm": 1.3555982112884521, "learning_rate": 0.00010507400172207091, "loss": 0.6241732597351074, "step": 285500 }, { "epoch": 1.6971307309592167, "grad_norm": 1.2127740383148193, "learning_rate": 0.00010506778629542778, "loss": 0.6101615905761719, "step": 285510 }, { "epoch": 1.6971901730358852, "grad_norm": 1.2991877794265747, "learning_rate": 0.0001050615708923788, "loss": 0.5391782760620117, "step": 285520 }, { "epoch": 1.6972496151125536, "grad_norm": 1.6256953477859497, "learning_rate": 0.00010505535551295362, "loss": 0.6231948852539062, "step": 285530 }, { "epoch": 1.697309057189222, "grad_norm": 1.180148720741272, "learning_rate": 0.00010504914015718202, "loss": 0.45958433151245115, "step": 285540 }, { "epoch": 1.6973684992658904, "grad_norm": 1.3711928129196167, "learning_rate": 0.0001050429248250937, "loss": 0.5293667316436768, "step": 285550 }, { "epoch": 1.6974279413425588, "grad_norm": 1.4928209781646729, "learning_rate": 0.00010503670951671842, "loss": 0.5218787670135498, "step": 285560 }, { "epoch": 1.6974873834192272, "grad_norm": 1.418027400970459, "learning_rate": 0.00010503049423208588, "loss": 0.49247150421142577, "step": 285570 }, { "epoch": 1.6975468254958956, "grad_norm": 1.3829665184020996, "learning_rate": 0.00010502427897122587, "loss": 0.5586078643798829, "step": 285580 }, { "epoch": 1.697606267572564, "grad_norm": 1.8447848558425903, "learning_rate": 0.00010501806373416805, "loss": 0.546635913848877, "step": 285590 }, { "epoch": 1.6976657096492325, "grad_norm": 1.6536192893981934, "learning_rate": 0.00010501184852094219, "loss": 0.580580472946167, "step": 285600 }, { "epoch": 1.6977251517259007, "grad_norm": 1.5290719270706177, "learning_rate": 0.00010500563333157802, "loss": 0.6192636489868164, "step": 285610 }, { "epoch": 1.697784593802569, "grad_norm": 1.340205430984497, "learning_rate": 0.00010499941816610527, "loss": 0.5828594207763672, "step": 285620 }, { "epoch": 1.6978440358792375, "grad_norm": 1.4064311981201172, "learning_rate": 0.00010499320302455369, "loss": 0.5265423774719238, "step": 285630 }, { "epoch": 1.697903477955906, "grad_norm": 1.4792351722717285, "learning_rate": 0.00010498698790695294, "loss": 0.6216075897216797, "step": 285640 }, { "epoch": 1.697962920032574, "grad_norm": 2.541679620742798, "learning_rate": 0.00010498077281333285, "loss": 0.5161314964294433, "step": 285650 }, { "epoch": 1.6980223621092425, "grad_norm": 1.637436866760254, "learning_rate": 0.00010497455774372309, "loss": 0.5318086624145508, "step": 285660 }, { "epoch": 1.698081804185911, "grad_norm": 1.330318808555603, "learning_rate": 0.00010496834269815339, "loss": 0.5837081909179688, "step": 285670 }, { "epoch": 1.6981412462625793, "grad_norm": 1.3413443565368652, "learning_rate": 0.0001049621276766535, "loss": 0.5461873054504395, "step": 285680 }, { "epoch": 1.6982006883392478, "grad_norm": 1.6891576051712036, "learning_rate": 0.00010495591267925315, "loss": 0.5712703227996826, "step": 285690 }, { "epoch": 1.6982601304159162, "grad_norm": 1.3196946382522583, "learning_rate": 0.00010494969770598205, "loss": 0.541346549987793, "step": 285700 }, { "epoch": 1.6983195724925846, "grad_norm": 1.604442834854126, "learning_rate": 0.00010494348275686996, "loss": 0.5629977226257324, "step": 285710 }, { "epoch": 1.698379014569253, "grad_norm": 1.5292167663574219, "learning_rate": 0.00010493726783194659, "loss": 0.6002835273742676, "step": 285720 }, { "epoch": 1.6984384566459214, "grad_norm": 1.8987082242965698, "learning_rate": 0.00010493105293124171, "loss": 0.5322382926940918, "step": 285730 }, { "epoch": 1.6984978987225898, "grad_norm": 1.4518483877182007, "learning_rate": 0.00010492483805478495, "loss": 0.5123908996582032, "step": 285740 }, { "epoch": 1.6985573407992582, "grad_norm": 1.557212233543396, "learning_rate": 0.00010491862320260615, "loss": 0.6065613746643066, "step": 285750 }, { "epoch": 1.6986167828759267, "grad_norm": 1.789670467376709, "learning_rate": 0.00010491240837473499, "loss": 0.6034634113311768, "step": 285760 }, { "epoch": 1.698676224952595, "grad_norm": 1.5432422161102295, "learning_rate": 0.0001049061935712012, "loss": 0.48882298469543456, "step": 285770 }, { "epoch": 1.6987356670292635, "grad_norm": 1.0668784379959106, "learning_rate": 0.00010489997879203452, "loss": 0.576947546005249, "step": 285780 }, { "epoch": 1.6987951091059317, "grad_norm": 1.3406200408935547, "learning_rate": 0.00010489376403726468, "loss": 0.5591328620910645, "step": 285790 }, { "epoch": 1.6988545511826, "grad_norm": 1.2500896453857422, "learning_rate": 0.00010488754930692137, "loss": 0.5413055896759034, "step": 285800 }, { "epoch": 1.6989139932592685, "grad_norm": 1.5691550970077515, "learning_rate": 0.0001048813346010344, "loss": 0.5363810539245606, "step": 285810 }, { "epoch": 1.698973435335937, "grad_norm": 1.3603324890136719, "learning_rate": 0.00010487511991963343, "loss": 0.5608602523803711, "step": 285820 }, { "epoch": 1.6990328774126053, "grad_norm": 1.402942180633545, "learning_rate": 0.00010486890526274821, "loss": 0.553812313079834, "step": 285830 }, { "epoch": 1.6990923194892735, "grad_norm": 1.2743284702301025, "learning_rate": 0.00010486269063040848, "loss": 0.5271842002868652, "step": 285840 }, { "epoch": 1.699151761565942, "grad_norm": 1.7835723161697388, "learning_rate": 0.00010485647602264396, "loss": 0.5856716156005859, "step": 285850 }, { "epoch": 1.6992112036426104, "grad_norm": 1.5757514238357544, "learning_rate": 0.0001048502614394844, "loss": 0.5877867698669433, "step": 285860 }, { "epoch": 1.6992706457192788, "grad_norm": 1.2585992813110352, "learning_rate": 0.00010484404688095943, "loss": 0.5156620025634766, "step": 285870 }, { "epoch": 1.6993300877959472, "grad_norm": 1.270187497138977, "learning_rate": 0.00010483783234709892, "loss": 0.5489299297332764, "step": 285880 }, { "epoch": 1.6993895298726156, "grad_norm": 1.3273968696594238, "learning_rate": 0.00010483161783793253, "loss": 0.5639817237854003, "step": 285890 }, { "epoch": 1.699448971949284, "grad_norm": 2.0386178493499756, "learning_rate": 0.00010482540335348996, "loss": 0.6094727993011475, "step": 285900 }, { "epoch": 1.6995084140259524, "grad_norm": 1.33210289478302, "learning_rate": 0.00010481918889380098, "loss": 0.5484296321868897, "step": 285910 }, { "epoch": 1.6995678561026208, "grad_norm": 1.614517331123352, "learning_rate": 0.00010481297445889536, "loss": 0.5069541454315185, "step": 285920 }, { "epoch": 1.6996272981792893, "grad_norm": 1.468069314956665, "learning_rate": 0.00010480676004880268, "loss": 0.5388764381408692, "step": 285930 }, { "epoch": 1.6996867402559577, "grad_norm": 1.5913244485855103, "learning_rate": 0.00010480054566355282, "loss": 0.6039319038391113, "step": 285940 }, { "epoch": 1.699746182332626, "grad_norm": 1.3325008153915405, "learning_rate": 0.00010479433130317546, "loss": 0.5603588581085205, "step": 285950 }, { "epoch": 1.6998056244092945, "grad_norm": 1.3817801475524902, "learning_rate": 0.00010478811696770028, "loss": 0.5906524658203125, "step": 285960 }, { "epoch": 1.699865066485963, "grad_norm": 1.1837565898895264, "learning_rate": 0.00010478190265715707, "loss": 0.626531457901001, "step": 285970 }, { "epoch": 1.699924508562631, "grad_norm": 1.064009666442871, "learning_rate": 0.00010477568837157555, "loss": 0.5596192836761474, "step": 285980 }, { "epoch": 1.6999839506392995, "grad_norm": 1.3902251720428467, "learning_rate": 0.00010476947411098542, "loss": 0.5607827186584473, "step": 285990 }, { "epoch": 1.700043392715968, "grad_norm": 1.4145946502685547, "learning_rate": 0.00010476325987541635, "loss": 0.6124362945556641, "step": 286000 }, { "epoch": 1.7001028347926364, "grad_norm": 1.5791441202163696, "learning_rate": 0.00010475704566489824, "loss": 0.5969013214111328, "step": 286010 }, { "epoch": 1.7001622768693045, "grad_norm": 1.3153353929519653, "learning_rate": 0.00010475083147946065, "loss": 0.5523251533508301, "step": 286020 }, { "epoch": 1.700221718945973, "grad_norm": 1.1584402322769165, "learning_rate": 0.00010474461731913334, "loss": 0.5860883235931397, "step": 286030 }, { "epoch": 1.7002811610226414, "grad_norm": 2.1778900623321533, "learning_rate": 0.00010473840318394612, "loss": 0.5699940204620362, "step": 286040 }, { "epoch": 1.7003406030993098, "grad_norm": 1.8017950057983398, "learning_rate": 0.00010473218907392863, "loss": 0.5603265762329102, "step": 286050 }, { "epoch": 1.7004000451759782, "grad_norm": 1.2747316360473633, "learning_rate": 0.0001047259749891106, "loss": 0.609871768951416, "step": 286060 }, { "epoch": 1.7004594872526466, "grad_norm": 1.613243579864502, "learning_rate": 0.00010471976092952185, "loss": 0.5903394222259521, "step": 286070 }, { "epoch": 1.700518929329315, "grad_norm": 1.7388081550598145, "learning_rate": 0.00010471354689519201, "loss": 0.5543113231658936, "step": 286080 }, { "epoch": 1.7005783714059834, "grad_norm": 1.5323818922042847, "learning_rate": 0.0001047073328861508, "loss": 0.592556381225586, "step": 286090 }, { "epoch": 1.7006378134826519, "grad_norm": 1.2557464838027954, "learning_rate": 0.00010470111890242802, "loss": 0.5093615055084229, "step": 286100 }, { "epoch": 1.7006972555593203, "grad_norm": 1.612612247467041, "learning_rate": 0.00010469490494405337, "loss": 0.5832057952880859, "step": 286110 }, { "epoch": 1.7007566976359887, "grad_norm": 1.6701374053955078, "learning_rate": 0.00010468869101105652, "loss": 0.5043271064758301, "step": 286120 }, { "epoch": 1.700816139712657, "grad_norm": 1.7606940269470215, "learning_rate": 0.00010468247710346723, "loss": 0.6421623229980469, "step": 286130 }, { "epoch": 1.7008755817893255, "grad_norm": 1.0380163192749023, "learning_rate": 0.00010467626322131528, "loss": 0.5324645042419434, "step": 286140 }, { "epoch": 1.700935023865994, "grad_norm": 1.6269140243530273, "learning_rate": 0.0001046700493646303, "loss": 0.49177045822143556, "step": 286150 }, { "epoch": 1.7009944659426621, "grad_norm": 1.4753292798995972, "learning_rate": 0.00010466383553344207, "loss": 0.544985580444336, "step": 286160 }, { "epoch": 1.7010539080193305, "grad_norm": 1.476811408996582, "learning_rate": 0.00010465762172778033, "loss": 0.5687168598175049, "step": 286170 }, { "epoch": 1.701113350095999, "grad_norm": 1.3963268995285034, "learning_rate": 0.00010465140794767476, "loss": 0.5774095535278321, "step": 286180 }, { "epoch": 1.7011727921726674, "grad_norm": 1.2996947765350342, "learning_rate": 0.0001046451941931551, "loss": 0.5490467548370361, "step": 286190 }, { "epoch": 1.7012322342493358, "grad_norm": 1.7265881299972534, "learning_rate": 0.00010463898046425111, "loss": 0.5443512916564941, "step": 286200 }, { "epoch": 1.701291676326004, "grad_norm": 1.3445112705230713, "learning_rate": 0.00010463276676099248, "loss": 0.5873727321624755, "step": 286210 }, { "epoch": 1.7013511184026724, "grad_norm": 1.6464709043502808, "learning_rate": 0.00010462655308340894, "loss": 0.6040044784545898, "step": 286220 }, { "epoch": 1.7014105604793408, "grad_norm": 1.280523419380188, "learning_rate": 0.00010462033943153018, "loss": 0.5580594062805175, "step": 286230 }, { "epoch": 1.7014700025560092, "grad_norm": 1.4111639261245728, "learning_rate": 0.00010461412580538599, "loss": 0.5835349082946777, "step": 286240 }, { "epoch": 1.7015294446326776, "grad_norm": 1.228737711906433, "learning_rate": 0.00010460791220500608, "loss": 0.5576143264770508, "step": 286250 }, { "epoch": 1.701588886709346, "grad_norm": 1.532132625579834, "learning_rate": 0.00010460169863042011, "loss": 0.5653856277465821, "step": 286260 }, { "epoch": 1.7016483287860145, "grad_norm": 1.5146353244781494, "learning_rate": 0.00010459548508165786, "loss": 0.5325755119323731, "step": 286270 }, { "epoch": 1.7017077708626829, "grad_norm": 1.7084035873413086, "learning_rate": 0.00010458927155874906, "loss": 0.517153549194336, "step": 286280 }, { "epoch": 1.7017672129393513, "grad_norm": 1.497312307357788, "learning_rate": 0.00010458305806172341, "loss": 0.6063613891601562, "step": 286290 }, { "epoch": 1.7018266550160197, "grad_norm": 1.3201056718826294, "learning_rate": 0.00010457684459061063, "loss": 0.5655526161193848, "step": 286300 }, { "epoch": 1.7018860970926881, "grad_norm": 1.2926133871078491, "learning_rate": 0.00010457063114544047, "loss": 0.5319406509399414, "step": 286310 }, { "epoch": 1.7019455391693565, "grad_norm": 1.6811453104019165, "learning_rate": 0.00010456441772624263, "loss": 0.6050788879394531, "step": 286320 }, { "epoch": 1.702004981246025, "grad_norm": 1.4008268117904663, "learning_rate": 0.00010455820433304686, "loss": 0.5774404048919678, "step": 286330 }, { "epoch": 1.7020644233226934, "grad_norm": 1.4033957719802856, "learning_rate": 0.00010455199096588283, "loss": 0.5381136417388916, "step": 286340 }, { "epoch": 1.7021238653993616, "grad_norm": 1.6299080848693848, "learning_rate": 0.00010454577762478035, "loss": 0.5895445823669434, "step": 286350 }, { "epoch": 1.70218330747603, "grad_norm": 1.5743787288665771, "learning_rate": 0.000104539564309769, "loss": 0.5746578693389892, "step": 286360 }, { "epoch": 1.7022427495526984, "grad_norm": 1.51107919216156, "learning_rate": 0.00010453335102087865, "loss": 0.5963454723358155, "step": 286370 }, { "epoch": 1.7023021916293668, "grad_norm": 1.063389778137207, "learning_rate": 0.00010452713775813896, "loss": 0.5670371532440186, "step": 286380 }, { "epoch": 1.702361633706035, "grad_norm": 1.4336057901382446, "learning_rate": 0.0001045209245215796, "loss": 0.5222176551818848, "step": 286390 }, { "epoch": 1.7024210757827034, "grad_norm": 1.4960421323776245, "learning_rate": 0.00010451471131123041, "loss": 0.6036464214324951, "step": 286400 }, { "epoch": 1.7024805178593718, "grad_norm": 1.512528896331787, "learning_rate": 0.00010450849812712105, "loss": 0.5175179481506348, "step": 286410 }, { "epoch": 1.7025399599360402, "grad_norm": 1.2264537811279297, "learning_rate": 0.00010450228496928119, "loss": 0.5623746871948242, "step": 286420 }, { "epoch": 1.7025994020127087, "grad_norm": 1.5862785577774048, "learning_rate": 0.00010449607183774061, "loss": 0.5662993431091309, "step": 286430 }, { "epoch": 1.702658844089377, "grad_norm": 1.1097280979156494, "learning_rate": 0.00010448985873252908, "loss": 0.5369333267211914, "step": 286440 }, { "epoch": 1.7027182861660455, "grad_norm": 1.4323831796646118, "learning_rate": 0.00010448364565367619, "loss": 0.5713403701782227, "step": 286450 }, { "epoch": 1.702777728242714, "grad_norm": 1.6698280572891235, "learning_rate": 0.00010447743260121177, "loss": 0.5928995132446289, "step": 286460 }, { "epoch": 1.7028371703193823, "grad_norm": 1.2776895761489868, "learning_rate": 0.00010447121957516554, "loss": 0.5226298332214355, "step": 286470 }, { "epoch": 1.7028966123960507, "grad_norm": 1.3704935312271118, "learning_rate": 0.00010446500657556715, "loss": 0.5832788467407226, "step": 286480 }, { "epoch": 1.7029560544727191, "grad_norm": 1.4959996938705444, "learning_rate": 0.00010445879360244635, "loss": 0.5947312355041504, "step": 286490 }, { "epoch": 1.7030154965493876, "grad_norm": 1.704429030418396, "learning_rate": 0.0001044525806558329, "loss": 0.5345742225646972, "step": 286500 }, { "epoch": 1.703074938626056, "grad_norm": 1.336931586265564, "learning_rate": 0.00010444636773575649, "loss": 0.5798954963684082, "step": 286510 }, { "epoch": 1.7031343807027244, "grad_norm": 1.3845937252044678, "learning_rate": 0.00010444015484224681, "loss": 0.5991555690765381, "step": 286520 }, { "epoch": 1.7031938227793926, "grad_norm": 2.706969738006592, "learning_rate": 0.00010443394197533365, "loss": 0.5607097625732422, "step": 286530 }, { "epoch": 1.703253264856061, "grad_norm": 1.435563325881958, "learning_rate": 0.00010442772913504669, "loss": 0.5268569469451905, "step": 286540 }, { "epoch": 1.7033127069327294, "grad_norm": 1.4018582105636597, "learning_rate": 0.00010442151632141559, "loss": 0.5646689891815185, "step": 286550 }, { "epoch": 1.7033721490093978, "grad_norm": 1.601449966430664, "learning_rate": 0.00010441530353447022, "loss": 0.5761903762817383, "step": 286560 }, { "epoch": 1.7034315910860662, "grad_norm": 1.7892245054244995, "learning_rate": 0.0001044090907742402, "loss": 0.5684457778930664, "step": 286570 }, { "epoch": 1.7034910331627344, "grad_norm": 1.4274616241455078, "learning_rate": 0.00010440287804075524, "loss": 0.5020628929138183, "step": 286580 }, { "epoch": 1.7035504752394028, "grad_norm": 1.462214469909668, "learning_rate": 0.00010439666533404507, "loss": 0.614738941192627, "step": 286590 }, { "epoch": 1.7036099173160713, "grad_norm": 1.4020886421203613, "learning_rate": 0.00010439045265413943, "loss": 0.5822430610656738, "step": 286600 }, { "epoch": 1.7036693593927397, "grad_norm": 1.0832383632659912, "learning_rate": 0.00010438424000106803, "loss": 0.5597463607788086, "step": 286610 }, { "epoch": 1.703728801469408, "grad_norm": 1.2978698015213013, "learning_rate": 0.00010437802737486058, "loss": 0.579339599609375, "step": 286620 }, { "epoch": 1.7037882435460765, "grad_norm": 1.1456339359283447, "learning_rate": 0.00010437181477554683, "loss": 0.5882610321044922, "step": 286630 }, { "epoch": 1.703847685622745, "grad_norm": 1.4552987813949585, "learning_rate": 0.00010436560220315648, "loss": 0.6173406600952148, "step": 286640 }, { "epoch": 1.7039071276994133, "grad_norm": 1.4512988328933716, "learning_rate": 0.00010435938965771923, "loss": 0.5581741333007812, "step": 286650 }, { "epoch": 1.7039665697760817, "grad_norm": 1.4028247594833374, "learning_rate": 0.00010435317713926483, "loss": 0.5759110927581788, "step": 286660 }, { "epoch": 1.7040260118527502, "grad_norm": 1.3720893859863281, "learning_rate": 0.00010434696464782299, "loss": 0.5645861148834228, "step": 286670 }, { "epoch": 1.7040854539294186, "grad_norm": 1.332614779472351, "learning_rate": 0.00010434075218342338, "loss": 0.519131851196289, "step": 286680 }, { "epoch": 1.704144896006087, "grad_norm": 1.997331142425537, "learning_rate": 0.00010433453974609582, "loss": 0.5202822685241699, "step": 286690 }, { "epoch": 1.7042043380827554, "grad_norm": 1.3904774188995361, "learning_rate": 0.00010432832733586995, "loss": 0.5944681167602539, "step": 286700 }, { "epoch": 1.7042637801594238, "grad_norm": 1.2660335302352905, "learning_rate": 0.00010432211495277552, "loss": 0.5652166366577148, "step": 286710 }, { "epoch": 1.704323222236092, "grad_norm": 1.4773685932159424, "learning_rate": 0.0001043159025968422, "loss": 0.5846471786499023, "step": 286720 }, { "epoch": 1.7043826643127604, "grad_norm": 1.691857933998108, "learning_rate": 0.00010430969026809978, "loss": 0.5627410888671875, "step": 286730 }, { "epoch": 1.7044421063894288, "grad_norm": 1.469363808631897, "learning_rate": 0.00010430347796657793, "loss": 0.5386536598205567, "step": 286740 }, { "epoch": 1.7045015484660972, "grad_norm": 1.4781900644302368, "learning_rate": 0.00010429726569230638, "loss": 0.5483055591583252, "step": 286750 }, { "epoch": 1.7045609905427654, "grad_norm": 1.5521658658981323, "learning_rate": 0.00010429105344531485, "loss": 0.5648955821990966, "step": 286760 }, { "epoch": 1.7046204326194339, "grad_norm": 1.2706713676452637, "learning_rate": 0.00010428484122563305, "loss": 0.5683923244476319, "step": 286770 }, { "epoch": 1.7046798746961023, "grad_norm": 1.6838667392730713, "learning_rate": 0.00010427862903329069, "loss": 0.5847629547119141, "step": 286780 }, { "epoch": 1.7047393167727707, "grad_norm": 1.7773680686950684, "learning_rate": 0.00010427241686831753, "loss": 0.5910329341888427, "step": 286790 }, { "epoch": 1.704798758849439, "grad_norm": 2.375354528427124, "learning_rate": 0.00010426620473074322, "loss": 0.5464204788208008, "step": 286800 }, { "epoch": 1.7048582009261075, "grad_norm": 1.3250231742858887, "learning_rate": 0.00010425999262059754, "loss": 0.5696652412414551, "step": 286810 }, { "epoch": 1.704917643002776, "grad_norm": 1.348767638206482, "learning_rate": 0.00010425378053791018, "loss": 0.5979135990142822, "step": 286820 }, { "epoch": 1.7049770850794443, "grad_norm": 1.3174000978469849, "learning_rate": 0.00010424756848271085, "loss": 0.5666662216186523, "step": 286830 }, { "epoch": 1.7050365271561128, "grad_norm": 1.5511033535003662, "learning_rate": 0.00010424135645502926, "loss": 0.629698371887207, "step": 286840 }, { "epoch": 1.7050959692327812, "grad_norm": 1.0919939279556274, "learning_rate": 0.00010423514445489513, "loss": 0.494505786895752, "step": 286850 }, { "epoch": 1.7051554113094496, "grad_norm": 1.4276010990142822, "learning_rate": 0.0001042289324823382, "loss": 0.5923259258270264, "step": 286860 }, { "epoch": 1.705214853386118, "grad_norm": 1.2057340145111084, "learning_rate": 0.0001042227205373882, "loss": 0.5643751144409179, "step": 286870 }, { "epoch": 1.7052742954627864, "grad_norm": 1.569467306137085, "learning_rate": 0.00010421650862007477, "loss": 0.578270435333252, "step": 286880 }, { "epoch": 1.7053337375394548, "grad_norm": 1.977066159248352, "learning_rate": 0.0001042102967304277, "loss": 0.5999794483184815, "step": 286890 }, { "epoch": 1.705393179616123, "grad_norm": 1.3439462184906006, "learning_rate": 0.00010420408486847669, "loss": 0.5529951095581055, "step": 286900 }, { "epoch": 1.7054526216927914, "grad_norm": 1.1242384910583496, "learning_rate": 0.0001041978730342514, "loss": 0.5949312686920166, "step": 286910 }, { "epoch": 1.7055120637694599, "grad_norm": 1.1669292449951172, "learning_rate": 0.00010419166122778161, "loss": 0.564391803741455, "step": 286920 }, { "epoch": 1.7055715058461283, "grad_norm": 1.2657370567321777, "learning_rate": 0.00010418544944909705, "loss": 0.5670504093170166, "step": 286930 }, { "epoch": 1.7056309479227967, "grad_norm": 1.757498025894165, "learning_rate": 0.00010417923769822733, "loss": 0.5899324417114258, "step": 286940 }, { "epoch": 1.7056903899994649, "grad_norm": 1.4061198234558105, "learning_rate": 0.00010417302597520229, "loss": 0.5799238204956054, "step": 286950 }, { "epoch": 1.7057498320761333, "grad_norm": 2.021660089492798, "learning_rate": 0.0001041668142800516, "loss": 0.5684399604797363, "step": 286960 }, { "epoch": 1.7058092741528017, "grad_norm": 1.05744469165802, "learning_rate": 0.00010416060261280493, "loss": 0.5868743419647217, "step": 286970 }, { "epoch": 1.7058687162294701, "grad_norm": 1.193933129310608, "learning_rate": 0.000104154390973492, "loss": 0.5328793048858642, "step": 286980 }, { "epoch": 1.7059281583061385, "grad_norm": 1.4879812002182007, "learning_rate": 0.00010414817936214263, "loss": 0.5944548606872558, "step": 286990 }, { "epoch": 1.705987600382807, "grad_norm": 1.3884655237197876, "learning_rate": 0.00010414196777878642, "loss": 0.5261017799377441, "step": 287000 }, { "epoch": 1.7060470424594754, "grad_norm": 1.3837926387786865, "learning_rate": 0.00010413575622345306, "loss": 0.5439236640930176, "step": 287010 }, { "epoch": 1.7061064845361438, "grad_norm": 1.1829372644424438, "learning_rate": 0.00010412954469617242, "loss": 0.5186532497406006, "step": 287020 }, { "epoch": 1.7061659266128122, "grad_norm": 1.459473729133606, "learning_rate": 0.0001041233331969741, "loss": 0.5922389984130859, "step": 287030 }, { "epoch": 1.7062253686894806, "grad_norm": 1.2950880527496338, "learning_rate": 0.00010411712172588777, "loss": 0.5558527946472168, "step": 287040 }, { "epoch": 1.706284810766149, "grad_norm": 1.5562540292739868, "learning_rate": 0.00010411091028294329, "loss": 0.565513801574707, "step": 287050 }, { "epoch": 1.7063442528428174, "grad_norm": 1.327959418296814, "learning_rate": 0.00010410469886817025, "loss": 0.5804412841796875, "step": 287060 }, { "epoch": 1.7064036949194858, "grad_norm": 1.5611176490783691, "learning_rate": 0.00010409848748159843, "loss": 0.555089282989502, "step": 287070 }, { "epoch": 1.7064631369961543, "grad_norm": 1.5333659648895264, "learning_rate": 0.00010409227612325747, "loss": 0.6028631687164306, "step": 287080 }, { "epoch": 1.7065225790728225, "grad_norm": 1.4340581893920898, "learning_rate": 0.00010408606479317718, "loss": 0.5625823497772217, "step": 287090 }, { "epoch": 1.7065820211494909, "grad_norm": 1.766898512840271, "learning_rate": 0.0001040798534913872, "loss": 0.5719993114471436, "step": 287100 }, { "epoch": 1.7066414632261593, "grad_norm": 1.4774025678634644, "learning_rate": 0.00010407364221791724, "loss": 0.5512934684753418, "step": 287110 }, { "epoch": 1.7067009053028277, "grad_norm": 1.1756840944290161, "learning_rate": 0.00010406743097279707, "loss": 0.4665172576904297, "step": 287120 }, { "epoch": 1.706760347379496, "grad_norm": 1.322050929069519, "learning_rate": 0.00010406121975605639, "loss": 0.4975303649902344, "step": 287130 }, { "epoch": 1.7068197894561643, "grad_norm": 1.516198992729187, "learning_rate": 0.00010405500856772484, "loss": 0.561312484741211, "step": 287140 }, { "epoch": 1.7068792315328327, "grad_norm": 1.5586084127426147, "learning_rate": 0.00010404879740783222, "loss": 0.563131856918335, "step": 287150 }, { "epoch": 1.7069386736095011, "grad_norm": 1.1710795164108276, "learning_rate": 0.00010404258627640822, "loss": 0.5711750030517578, "step": 287160 }, { "epoch": 1.7069981156861695, "grad_norm": 1.4885311126708984, "learning_rate": 0.00010403637517348251, "loss": 0.5446406841278076, "step": 287170 }, { "epoch": 1.707057557762838, "grad_norm": 1.415631651878357, "learning_rate": 0.00010403016409908483, "loss": 0.6302031517028809, "step": 287180 }, { "epoch": 1.7071169998395064, "grad_norm": 1.1652885675430298, "learning_rate": 0.00010402395305324496, "loss": 0.5656519412994385, "step": 287190 }, { "epoch": 1.7071764419161748, "grad_norm": 1.3139506578445435, "learning_rate": 0.00010401774203599248, "loss": 0.5734705448150634, "step": 287200 }, { "epoch": 1.7072358839928432, "grad_norm": 1.1422593593597412, "learning_rate": 0.00010401153104735717, "loss": 0.5227490425109863, "step": 287210 }, { "epoch": 1.7072953260695116, "grad_norm": 1.6976661682128906, "learning_rate": 0.00010400532008736876, "loss": 0.5746176719665528, "step": 287220 }, { "epoch": 1.70735476814618, "grad_norm": 1.4061599969863892, "learning_rate": 0.00010399910915605693, "loss": 0.5400321006774902, "step": 287230 }, { "epoch": 1.7074142102228484, "grad_norm": 1.3802145719528198, "learning_rate": 0.0001039928982534514, "loss": 0.5530494689941406, "step": 287240 }, { "epoch": 1.7074736522995169, "grad_norm": 1.4208064079284668, "learning_rate": 0.00010398668737958189, "loss": 0.5255301475524903, "step": 287250 }, { "epoch": 1.7075330943761853, "grad_norm": 1.3366034030914307, "learning_rate": 0.00010398047653447809, "loss": 0.5306647300720215, "step": 287260 }, { "epoch": 1.7075925364528535, "grad_norm": 1.5503604412078857, "learning_rate": 0.00010397426571816972, "loss": 0.554716968536377, "step": 287270 }, { "epoch": 1.7076519785295219, "grad_norm": 1.6378402709960938, "learning_rate": 0.00010396805493068651, "loss": 0.6127646446228028, "step": 287280 }, { "epoch": 1.7077114206061903, "grad_norm": 1.5736305713653564, "learning_rate": 0.00010396184417205815, "loss": 0.5618454933166503, "step": 287290 }, { "epoch": 1.7077708626828587, "grad_norm": 1.4469035863876343, "learning_rate": 0.00010395563344231434, "loss": 0.6080280780792237, "step": 287300 }, { "epoch": 1.7078303047595271, "grad_norm": 1.2404265403747559, "learning_rate": 0.00010394942274148482, "loss": 0.5044309616088867, "step": 287310 }, { "epoch": 1.7078897468361953, "grad_norm": 1.174444556236267, "learning_rate": 0.0001039432120695993, "loss": 0.5797468185424804, "step": 287320 }, { "epoch": 1.7079491889128637, "grad_norm": 1.809375524520874, "learning_rate": 0.00010393700142668745, "loss": 0.572852897644043, "step": 287330 }, { "epoch": 1.7080086309895322, "grad_norm": 1.8091984987258911, "learning_rate": 0.00010393079081277899, "loss": 0.5938383102416992, "step": 287340 }, { "epoch": 1.7080680730662006, "grad_norm": 1.5134209394454956, "learning_rate": 0.00010392458022790368, "loss": 0.5285784244537354, "step": 287350 }, { "epoch": 1.708127515142869, "grad_norm": 1.2011876106262207, "learning_rate": 0.00010391836967209116, "loss": 0.4985158920288086, "step": 287360 }, { "epoch": 1.7081869572195374, "grad_norm": 1.5934075117111206, "learning_rate": 0.00010391215914537117, "loss": 0.5844026565551758, "step": 287370 }, { "epoch": 1.7082463992962058, "grad_norm": 1.8161933422088623, "learning_rate": 0.00010390594864777346, "loss": 0.6275663375854492, "step": 287380 }, { "epoch": 1.7083058413728742, "grad_norm": 1.445643424987793, "learning_rate": 0.00010389973817932767, "loss": 0.5958464622497559, "step": 287390 }, { "epoch": 1.7083652834495426, "grad_norm": 1.281173586845398, "learning_rate": 0.00010389352774006354, "loss": 0.5438794136047364, "step": 287400 }, { "epoch": 1.708424725526211, "grad_norm": 1.5782991647720337, "learning_rate": 0.00010388731733001078, "loss": 0.5506195545196533, "step": 287410 }, { "epoch": 1.7084841676028795, "grad_norm": 1.5491174459457397, "learning_rate": 0.00010388110694919912, "loss": 0.5936477661132813, "step": 287420 }, { "epoch": 1.7085436096795479, "grad_norm": 1.397665023803711, "learning_rate": 0.00010387489659765821, "loss": 0.5465560913085937, "step": 287430 }, { "epoch": 1.7086030517562163, "grad_norm": 1.478024959564209, "learning_rate": 0.00010386868627541782, "loss": 0.5128307819366456, "step": 287440 }, { "epoch": 1.7086624938328847, "grad_norm": 1.5811846256256104, "learning_rate": 0.00010386247598250763, "loss": 0.5780802726745605, "step": 287450 }, { "epoch": 1.708721935909553, "grad_norm": 2.033742904663086, "learning_rate": 0.00010385626571895735, "loss": 0.5716945648193359, "step": 287460 }, { "epoch": 1.7087813779862213, "grad_norm": 1.378013014793396, "learning_rate": 0.00010385005548479662, "loss": 0.5487060070037841, "step": 287470 }, { "epoch": 1.7088408200628897, "grad_norm": 1.200072169303894, "learning_rate": 0.00010384384528005529, "loss": 0.573665189743042, "step": 287480 }, { "epoch": 1.7089002621395581, "grad_norm": 1.4414074420928955, "learning_rate": 0.00010383763510476301, "loss": 0.5369650840759277, "step": 287490 }, { "epoch": 1.7089597042162263, "grad_norm": 1.423690915107727, "learning_rate": 0.0001038314249589494, "loss": 0.522329044342041, "step": 287500 }, { "epoch": 1.7090191462928948, "grad_norm": 1.3985803127288818, "learning_rate": 0.00010382521484264425, "loss": 0.5244309425354003, "step": 287510 }, { "epoch": 1.7090785883695632, "grad_norm": 1.4284077882766724, "learning_rate": 0.00010381900475587731, "loss": 0.57443208694458, "step": 287520 }, { "epoch": 1.7091380304462316, "grad_norm": 1.2938891649246216, "learning_rate": 0.00010381279469867815, "loss": 0.6003149032592774, "step": 287530 }, { "epoch": 1.7091974725229, "grad_norm": 1.6984968185424805, "learning_rate": 0.00010380658467107662, "loss": 0.5211990356445313, "step": 287540 }, { "epoch": 1.7092569145995684, "grad_norm": 1.5585644245147705, "learning_rate": 0.00010380037467310237, "loss": 0.585585069656372, "step": 287550 }, { "epoch": 1.7093163566762368, "grad_norm": 1.1932275295257568, "learning_rate": 0.00010379416470478509, "loss": 0.5050074577331543, "step": 287560 }, { "epoch": 1.7093757987529052, "grad_norm": 1.4134904146194458, "learning_rate": 0.00010378795476615446, "loss": 0.5237175941467285, "step": 287570 }, { "epoch": 1.7094352408295737, "grad_norm": 2.1087121963500977, "learning_rate": 0.00010378174485724026, "loss": 0.5619102954864502, "step": 287580 }, { "epoch": 1.709494682906242, "grad_norm": 1.7423181533813477, "learning_rate": 0.00010377553497807218, "loss": 0.6019223213195801, "step": 287590 }, { "epoch": 1.7095541249829105, "grad_norm": 1.3346666097640991, "learning_rate": 0.00010376932512867985, "loss": 0.5649097919464111, "step": 287600 }, { "epoch": 1.709613567059579, "grad_norm": 1.1539701223373413, "learning_rate": 0.00010376311530909306, "loss": 0.6125472545623779, "step": 287610 }, { "epoch": 1.7096730091362473, "grad_norm": 1.5104143619537354, "learning_rate": 0.00010375690551934149, "loss": 0.5403817176818848, "step": 287620 }, { "epoch": 1.7097324512129157, "grad_norm": 1.2640552520751953, "learning_rate": 0.00010375069575945484, "loss": 0.5402544975280762, "step": 287630 }, { "epoch": 1.709791893289584, "grad_norm": 1.74552583694458, "learning_rate": 0.00010374448602946283, "loss": 0.594157600402832, "step": 287640 }, { "epoch": 1.7098513353662523, "grad_norm": 1.0825663805007935, "learning_rate": 0.00010373827632939515, "loss": 0.5575320243835449, "step": 287650 }, { "epoch": 1.7099107774429207, "grad_norm": 1.251617431640625, "learning_rate": 0.00010373206665928148, "loss": 0.5496084213256835, "step": 287660 }, { "epoch": 1.7099702195195892, "grad_norm": 1.5668402910232544, "learning_rate": 0.00010372585701915158, "loss": 0.5687664031982422, "step": 287670 }, { "epoch": 1.7100296615962576, "grad_norm": 1.672619104385376, "learning_rate": 0.00010371964740903514, "loss": 0.5755548477172852, "step": 287680 }, { "epoch": 1.7100891036729258, "grad_norm": 1.1646270751953125, "learning_rate": 0.00010371343782896186, "loss": 0.5262479305267334, "step": 287690 }, { "epoch": 1.7101485457495942, "grad_norm": 1.2021409273147583, "learning_rate": 0.0001037072282789614, "loss": 0.5215563774108887, "step": 287700 }, { "epoch": 1.7102079878262626, "grad_norm": 1.677130103111267, "learning_rate": 0.00010370101875906355, "loss": 0.506747055053711, "step": 287710 }, { "epoch": 1.710267429902931, "grad_norm": 1.4895998239517212, "learning_rate": 0.00010369480926929794, "loss": 0.5846967220306396, "step": 287720 }, { "epoch": 1.7103268719795994, "grad_norm": 1.2590752840042114, "learning_rate": 0.0001036885998096943, "loss": 0.5241056442260742, "step": 287730 }, { "epoch": 1.7103863140562678, "grad_norm": 1.3620258569717407, "learning_rate": 0.00010368239038028234, "loss": 0.5953120231628418, "step": 287740 }, { "epoch": 1.7104457561329363, "grad_norm": 1.3845125436782837, "learning_rate": 0.00010367618098109178, "loss": 0.5619793891906738, "step": 287750 }, { "epoch": 1.7105051982096047, "grad_norm": 1.5452924966812134, "learning_rate": 0.00010366997161215227, "loss": 0.5496807098388672, "step": 287760 }, { "epoch": 1.710564640286273, "grad_norm": 1.6551623344421387, "learning_rate": 0.00010366376227349355, "loss": 0.598721981048584, "step": 287770 }, { "epoch": 1.7106240823629415, "grad_norm": 1.4167743921279907, "learning_rate": 0.00010365755296514534, "loss": 0.5705932140350342, "step": 287780 }, { "epoch": 1.71068352443961, "grad_norm": 1.43869948387146, "learning_rate": 0.00010365134368713732, "loss": 0.5704222679138183, "step": 287790 }, { "epoch": 1.7107429665162783, "grad_norm": 1.17759370803833, "learning_rate": 0.0001036451344394992, "loss": 0.5686114311218262, "step": 287800 }, { "epoch": 1.7108024085929467, "grad_norm": 1.3262890577316284, "learning_rate": 0.00010363892522226066, "loss": 0.644619369506836, "step": 287810 }, { "epoch": 1.7108618506696152, "grad_norm": 1.4668399095535278, "learning_rate": 0.00010363271603545144, "loss": 0.5025251865386963, "step": 287820 }, { "epoch": 1.7109212927462834, "grad_norm": 1.3180508613586426, "learning_rate": 0.00010362650687910123, "loss": 0.5843966960906982, "step": 287830 }, { "epoch": 1.7109807348229518, "grad_norm": 1.203047275543213, "learning_rate": 0.00010362029775323971, "loss": 0.5454506874084473, "step": 287840 }, { "epoch": 1.7110401768996202, "grad_norm": 1.5773991346359253, "learning_rate": 0.00010361408865789662, "loss": 0.5713492870330811, "step": 287850 }, { "epoch": 1.7110996189762886, "grad_norm": 1.7468273639678955, "learning_rate": 0.00010360787959310163, "loss": 0.5839280128479004, "step": 287860 }, { "epoch": 1.7111590610529568, "grad_norm": 1.1373752355575562, "learning_rate": 0.00010360167055888446, "loss": 0.5836878776550293, "step": 287870 }, { "epoch": 1.7112185031296252, "grad_norm": 1.6685523986816406, "learning_rate": 0.00010359546155527482, "loss": 0.5511151313781738, "step": 287880 }, { "epoch": 1.7112779452062936, "grad_norm": 1.5200525522232056, "learning_rate": 0.00010358925258230236, "loss": 0.6078249454498291, "step": 287890 }, { "epoch": 1.711337387282962, "grad_norm": 1.3460949659347534, "learning_rate": 0.00010358304363999685, "loss": 0.5815043449401855, "step": 287900 }, { "epoch": 1.7113968293596304, "grad_norm": 1.5161385536193848, "learning_rate": 0.00010357683472838797, "loss": 0.5481374263763428, "step": 287910 }, { "epoch": 1.7114562714362989, "grad_norm": 1.7368905544281006, "learning_rate": 0.00010357062584750542, "loss": 0.5633640289306641, "step": 287920 }, { "epoch": 1.7115157135129673, "grad_norm": 1.347627878189087, "learning_rate": 0.00010356441699737885, "loss": 0.5159404754638672, "step": 287930 }, { "epoch": 1.7115751555896357, "grad_norm": 1.5223108530044556, "learning_rate": 0.00010355820817803803, "loss": 0.5498815536499023, "step": 287940 }, { "epoch": 1.711634597666304, "grad_norm": 1.3564658164978027, "learning_rate": 0.00010355199938951267, "loss": 0.5792804718017578, "step": 287950 }, { "epoch": 1.7116940397429725, "grad_norm": 1.3891996145248413, "learning_rate": 0.00010354579063183238, "loss": 0.5261235713958741, "step": 287960 }, { "epoch": 1.711753481819641, "grad_norm": 1.1679558753967285, "learning_rate": 0.00010353958190502694, "loss": 0.5918768405914306, "step": 287970 }, { "epoch": 1.7118129238963093, "grad_norm": 1.3961503505706787, "learning_rate": 0.00010353337320912606, "loss": 0.5821610927581787, "step": 287980 }, { "epoch": 1.7118723659729778, "grad_norm": 1.322274088859558, "learning_rate": 0.00010352716454415936, "loss": 0.5061600685119629, "step": 287990 }, { "epoch": 1.7119318080496462, "grad_norm": 1.746751070022583, "learning_rate": 0.0001035209559101566, "loss": 0.6046215534210205, "step": 288000 }, { "epoch": 1.7119912501263144, "grad_norm": 1.1432280540466309, "learning_rate": 0.00010351474730714752, "loss": 0.5363457202911377, "step": 288010 }, { "epoch": 1.7120506922029828, "grad_norm": 1.521577000617981, "learning_rate": 0.0001035085387351617, "loss": 0.5607211112976074, "step": 288020 }, { "epoch": 1.7121101342796512, "grad_norm": 2.129002094268799, "learning_rate": 0.00010350233019422895, "loss": 0.5481784820556641, "step": 288030 }, { "epoch": 1.7121695763563196, "grad_norm": 1.194502592086792, "learning_rate": 0.00010349612168437895, "loss": 0.5747323036193848, "step": 288040 }, { "epoch": 1.712229018432988, "grad_norm": 1.896576166152954, "learning_rate": 0.00010348991320564137, "loss": 0.568326759338379, "step": 288050 }, { "epoch": 1.7122884605096562, "grad_norm": 2.400402545928955, "learning_rate": 0.00010348370475804585, "loss": 0.5766895294189454, "step": 288060 }, { "epoch": 1.7123479025863246, "grad_norm": 1.410457730293274, "learning_rate": 0.00010347749634162222, "loss": 0.5018620014190673, "step": 288070 }, { "epoch": 1.712407344662993, "grad_norm": 1.4721084833145142, "learning_rate": 0.00010347128795640011, "loss": 0.5646069526672364, "step": 288080 }, { "epoch": 1.7124667867396615, "grad_norm": 3.2832493782043457, "learning_rate": 0.00010346507960240916, "loss": 0.530158281326294, "step": 288090 }, { "epoch": 1.7125262288163299, "grad_norm": 1.353115439414978, "learning_rate": 0.00010345887127967923, "loss": 0.5171942234039306, "step": 288100 }, { "epoch": 1.7125856708929983, "grad_norm": 1.7316484451293945, "learning_rate": 0.00010345266298823988, "loss": 0.5881117820739746, "step": 288110 }, { "epoch": 1.7126451129696667, "grad_norm": 1.2980875968933105, "learning_rate": 0.00010344645472812082, "loss": 0.5624466896057129, "step": 288120 }, { "epoch": 1.7127045550463351, "grad_norm": 1.239088535308838, "learning_rate": 0.00010344024649935184, "loss": 0.5804407596588135, "step": 288130 }, { "epoch": 1.7127639971230035, "grad_norm": 1.663461446762085, "learning_rate": 0.00010343403830196254, "loss": 0.5756837368011475, "step": 288140 }, { "epoch": 1.712823439199672, "grad_norm": 1.343237042427063, "learning_rate": 0.00010342783013598263, "loss": 0.573976993560791, "step": 288150 }, { "epoch": 1.7128828812763404, "grad_norm": 1.49491286277771, "learning_rate": 0.0001034216220014419, "loss": 0.5301363945007325, "step": 288160 }, { "epoch": 1.7129423233530088, "grad_norm": 1.3343864679336548, "learning_rate": 0.00010341541389836995, "loss": 0.613929557800293, "step": 288170 }, { "epoch": 1.7130017654296772, "grad_norm": 1.6083192825317383, "learning_rate": 0.0001034092058267965, "loss": 0.5767805099487304, "step": 288180 }, { "epoch": 1.7130612075063456, "grad_norm": 1.3342857360839844, "learning_rate": 0.00010340299778675125, "loss": 0.5711484909057617, "step": 288190 }, { "epoch": 1.7131206495830138, "grad_norm": 1.4840569496154785, "learning_rate": 0.00010339678977826393, "loss": 0.5649913311004638, "step": 288200 }, { "epoch": 1.7131800916596822, "grad_norm": 1.33495032787323, "learning_rate": 0.00010339058180136418, "loss": 0.5652633666992187, "step": 288210 }, { "epoch": 1.7132395337363506, "grad_norm": 1.6176382303237915, "learning_rate": 0.00010338437385608172, "loss": 0.5612666130065918, "step": 288220 }, { "epoch": 1.713298975813019, "grad_norm": 1.3641380071640015, "learning_rate": 0.00010337816594244627, "loss": 0.5845711708068848, "step": 288230 }, { "epoch": 1.7133584178896872, "grad_norm": 1.5356895923614502, "learning_rate": 0.00010337195806048753, "loss": 0.6221631050109864, "step": 288240 }, { "epoch": 1.7134178599663556, "grad_norm": 1.2320245504379272, "learning_rate": 0.00010336575021023513, "loss": 0.5938538074493408, "step": 288250 }, { "epoch": 1.713477302043024, "grad_norm": 1.5083682537078857, "learning_rate": 0.00010335954239171886, "loss": 0.5286961555480957, "step": 288260 }, { "epoch": 1.7135367441196925, "grad_norm": 1.6266896724700928, "learning_rate": 0.00010335333460496834, "loss": 0.5412407875061035, "step": 288270 }, { "epoch": 1.713596186196361, "grad_norm": 1.3117315769195557, "learning_rate": 0.00010334712685001331, "loss": 0.5380970001220703, "step": 288280 }, { "epoch": 1.7136556282730293, "grad_norm": 1.285382866859436, "learning_rate": 0.00010334091912688345, "loss": 0.5175729751586914, "step": 288290 }, { "epoch": 1.7137150703496977, "grad_norm": 1.3364567756652832, "learning_rate": 0.00010333471143560845, "loss": 0.5452640533447266, "step": 288300 }, { "epoch": 1.7137745124263661, "grad_norm": 1.8343290090560913, "learning_rate": 0.000103328503776218, "loss": 0.5648469448089599, "step": 288310 }, { "epoch": 1.7138339545030346, "grad_norm": 1.392366886138916, "learning_rate": 0.00010332229614874183, "loss": 0.5288138389587402, "step": 288320 }, { "epoch": 1.713893396579703, "grad_norm": 1.36837637424469, "learning_rate": 0.0001033160885532096, "loss": 0.5992781162261963, "step": 288330 }, { "epoch": 1.7139528386563714, "grad_norm": 1.228696346282959, "learning_rate": 0.00010330988098965102, "loss": 0.5374567985534668, "step": 288340 }, { "epoch": 1.7140122807330398, "grad_norm": 1.4696048498153687, "learning_rate": 0.00010330367345809579, "loss": 0.6251245498657226, "step": 288350 }, { "epoch": 1.7140717228097082, "grad_norm": 1.1995748281478882, "learning_rate": 0.00010329746595857359, "loss": 0.5402701377868653, "step": 288360 }, { "epoch": 1.7141311648863766, "grad_norm": 1.4826849699020386, "learning_rate": 0.00010329125849111414, "loss": 0.5515532493591309, "step": 288370 }, { "epoch": 1.7141906069630448, "grad_norm": 1.527867317199707, "learning_rate": 0.00010328505105574708, "loss": 0.5866223335266113, "step": 288380 }, { "epoch": 1.7142500490397132, "grad_norm": 1.70817232131958, "learning_rate": 0.00010327884365250218, "loss": 0.6097505569458008, "step": 288390 }, { "epoch": 1.7143094911163816, "grad_norm": 1.4425852298736572, "learning_rate": 0.00010327263628140908, "loss": 0.5252970695495606, "step": 288400 }, { "epoch": 1.71436893319305, "grad_norm": 1.7783410549163818, "learning_rate": 0.00010326642894249751, "loss": 0.5625528812408447, "step": 288410 }, { "epoch": 1.7144283752697185, "grad_norm": 1.3996937274932861, "learning_rate": 0.00010326022163579709, "loss": 0.5469871520996094, "step": 288420 }, { "epoch": 1.7144878173463867, "grad_norm": 1.6414945125579834, "learning_rate": 0.00010325401436133761, "loss": 0.5457414627075196, "step": 288430 }, { "epoch": 1.714547259423055, "grad_norm": 1.36955988407135, "learning_rate": 0.00010324780711914875, "loss": 0.5617784976959228, "step": 288440 }, { "epoch": 1.7146067014997235, "grad_norm": 0.9568883776664734, "learning_rate": 0.00010324159990926008, "loss": 0.5883986949920654, "step": 288450 }, { "epoch": 1.714666143576392, "grad_norm": 1.553225040435791, "learning_rate": 0.00010323539273170146, "loss": 0.5531230926513672, "step": 288460 }, { "epoch": 1.7147255856530603, "grad_norm": 1.3599178791046143, "learning_rate": 0.00010322918558650252, "loss": 0.5822079181671143, "step": 288470 }, { "epoch": 1.7147850277297287, "grad_norm": 1.4721224308013916, "learning_rate": 0.00010322297847369287, "loss": 0.5910841941833496, "step": 288480 }, { "epoch": 1.7148444698063972, "grad_norm": 1.5133979320526123, "learning_rate": 0.00010321677139330233, "loss": 0.6118369102478027, "step": 288490 }, { "epoch": 1.7149039118830656, "grad_norm": 1.5837550163269043, "learning_rate": 0.00010321056434536056, "loss": 0.6024615287780761, "step": 288500 }, { "epoch": 1.714963353959734, "grad_norm": 1.338873028755188, "learning_rate": 0.00010320435732989717, "loss": 0.49630093574523926, "step": 288510 }, { "epoch": 1.7150227960364024, "grad_norm": 1.6108664274215698, "learning_rate": 0.00010319815034694195, "loss": 0.5880752086639405, "step": 288520 }, { "epoch": 1.7150822381130708, "grad_norm": 1.4705897569656372, "learning_rate": 0.00010319194339652458, "loss": 0.615303373336792, "step": 288530 }, { "epoch": 1.7151416801897392, "grad_norm": 1.807260513305664, "learning_rate": 0.00010318573647867471, "loss": 0.5583386421203613, "step": 288540 }, { "epoch": 1.7152011222664076, "grad_norm": 1.4827351570129395, "learning_rate": 0.00010317952959342198, "loss": 0.5602994918823242, "step": 288550 }, { "epoch": 1.715260564343076, "grad_norm": 1.7243571281433105, "learning_rate": 0.00010317332274079626, "loss": 0.5426423072814941, "step": 288560 }, { "epoch": 1.7153200064197442, "grad_norm": 1.5346729755401611, "learning_rate": 0.00010316711592082708, "loss": 0.601046371459961, "step": 288570 }, { "epoch": 1.7153794484964127, "grad_norm": 1.255941390991211, "learning_rate": 0.00010316090913354414, "loss": 0.5600423812866211, "step": 288580 }, { "epoch": 1.715438890573081, "grad_norm": 1.7759902477264404, "learning_rate": 0.00010315470237897727, "loss": 0.5544574737548829, "step": 288590 }, { "epoch": 1.7154983326497495, "grad_norm": 1.299346923828125, "learning_rate": 0.00010314849565715603, "loss": 0.5724565505981445, "step": 288600 }, { "epoch": 1.7155577747264177, "grad_norm": 1.3411681652069092, "learning_rate": 0.00010314228896811008, "loss": 0.5229952335357666, "step": 288610 }, { "epoch": 1.715617216803086, "grad_norm": 1.8338451385498047, "learning_rate": 0.00010313608231186926, "loss": 0.5930636405944825, "step": 288620 }, { "epoch": 1.7156766588797545, "grad_norm": 1.4667296409606934, "learning_rate": 0.00010312987568846317, "loss": 0.5920426368713378, "step": 288630 }, { "epoch": 1.715736100956423, "grad_norm": 1.5611599683761597, "learning_rate": 0.00010312366909792146, "loss": 0.5855467796325684, "step": 288640 }, { "epoch": 1.7157955430330913, "grad_norm": 1.7711849212646484, "learning_rate": 0.00010311746254027394, "loss": 0.5541939735412598, "step": 288650 }, { "epoch": 1.7158549851097598, "grad_norm": 1.2061187028884888, "learning_rate": 0.0001031112560155502, "loss": 0.47536296844482423, "step": 288660 }, { "epoch": 1.7159144271864282, "grad_norm": 1.6015013456344604, "learning_rate": 0.00010310504952377996, "loss": 0.5778146266937256, "step": 288670 }, { "epoch": 1.7159738692630966, "grad_norm": 1.3024779558181763, "learning_rate": 0.00010309884306499289, "loss": 0.51126070022583, "step": 288680 }, { "epoch": 1.716033311339765, "grad_norm": 1.5237349271774292, "learning_rate": 0.00010309263663921871, "loss": 0.5301850795745849, "step": 288690 }, { "epoch": 1.7160927534164334, "grad_norm": 1.4710921049118042, "learning_rate": 0.00010308643024648711, "loss": 0.5844376087188721, "step": 288700 }, { "epoch": 1.7161521954931018, "grad_norm": 1.4757111072540283, "learning_rate": 0.00010308022388682776, "loss": 0.5576023101806641, "step": 288710 }, { "epoch": 1.7162116375697702, "grad_norm": 1.342349886894226, "learning_rate": 0.00010307401756027037, "loss": 0.5825975894927978, "step": 288720 }, { "epoch": 1.7162710796464387, "grad_norm": 1.7577389478683472, "learning_rate": 0.00010306781126684459, "loss": 0.5267492294311523, "step": 288730 }, { "epoch": 1.716330521723107, "grad_norm": 1.5236451625823975, "learning_rate": 0.00010306160500658015, "loss": 0.5917994976043701, "step": 288740 }, { "epoch": 1.7163899637997753, "grad_norm": 1.3103246688842773, "learning_rate": 0.00010305539877950674, "loss": 0.5635323524475098, "step": 288750 }, { "epoch": 1.7164494058764437, "grad_norm": 1.9708424806594849, "learning_rate": 0.00010304919258565402, "loss": 0.5528532505035401, "step": 288760 }, { "epoch": 1.716508847953112, "grad_norm": 1.602613925933838, "learning_rate": 0.00010304298642505167, "loss": 0.5612767219543457, "step": 288770 }, { "epoch": 1.7165682900297805, "grad_norm": 1.725314736366272, "learning_rate": 0.00010303678029772943, "loss": 0.567951774597168, "step": 288780 }, { "epoch": 1.716627732106449, "grad_norm": 1.5141353607177734, "learning_rate": 0.00010303057420371693, "loss": 0.5473181724548339, "step": 288790 }, { "epoch": 1.7166871741831171, "grad_norm": 1.5588481426239014, "learning_rate": 0.00010302436814304393, "loss": 0.6081299781799316, "step": 288800 }, { "epoch": 1.7167466162597855, "grad_norm": 1.332421898841858, "learning_rate": 0.00010301816211574003, "loss": 0.5796652793884277, "step": 288810 }, { "epoch": 1.716806058336454, "grad_norm": 1.4187695980072021, "learning_rate": 0.00010301195612183498, "loss": 0.5687841415405274, "step": 288820 }, { "epoch": 1.7168655004131224, "grad_norm": 1.217157244682312, "learning_rate": 0.00010300575016135845, "loss": 0.555707597732544, "step": 288830 }, { "epoch": 1.7169249424897908, "grad_norm": 1.640152096748352, "learning_rate": 0.00010299954423434011, "loss": 0.5931777954101562, "step": 288840 }, { "epoch": 1.7169843845664592, "grad_norm": 1.7247947454452515, "learning_rate": 0.00010299333834080967, "loss": 0.5557497024536133, "step": 288850 }, { "epoch": 1.7170438266431276, "grad_norm": 1.005751132965088, "learning_rate": 0.00010298713248079681, "loss": 0.5661547660827637, "step": 288860 }, { "epoch": 1.717103268719796, "grad_norm": 1.4192324876785278, "learning_rate": 0.00010298092665433121, "loss": 0.5560842037200928, "step": 288870 }, { "epoch": 1.7171627107964644, "grad_norm": 1.3269602060317993, "learning_rate": 0.00010297472086144258, "loss": 0.53800048828125, "step": 288880 }, { "epoch": 1.7172221528731328, "grad_norm": 1.7642877101898193, "learning_rate": 0.00010296851510216057, "loss": 0.5674302101135253, "step": 288890 }, { "epoch": 1.7172815949498013, "grad_norm": 1.3618189096450806, "learning_rate": 0.00010296230937651492, "loss": 0.5413132190704346, "step": 288900 }, { "epoch": 1.7173410370264697, "grad_norm": 1.583875060081482, "learning_rate": 0.00010295610368453524, "loss": 0.6408661365509033, "step": 288910 }, { "epoch": 1.717400479103138, "grad_norm": 1.6861451864242554, "learning_rate": 0.00010294989802625128, "loss": 0.5819724559783935, "step": 288920 }, { "epoch": 1.7174599211798065, "grad_norm": 1.4623565673828125, "learning_rate": 0.00010294369240169271, "loss": 0.5621049404144287, "step": 288930 }, { "epoch": 1.7175193632564747, "grad_norm": 1.2291607856750488, "learning_rate": 0.00010293748681088917, "loss": 0.5442000389099121, "step": 288940 }, { "epoch": 1.717578805333143, "grad_norm": 1.4652949571609497, "learning_rate": 0.00010293128125387043, "loss": 0.5663312911987305, "step": 288950 }, { "epoch": 1.7176382474098115, "grad_norm": 1.6025986671447754, "learning_rate": 0.00010292507573066612, "loss": 0.5591727733612061, "step": 288960 }, { "epoch": 1.71769768948648, "grad_norm": 1.6200734376907349, "learning_rate": 0.0001029188702413059, "loss": 0.6101878166198731, "step": 288970 }, { "epoch": 1.7177571315631481, "grad_norm": 1.5035902261734009, "learning_rate": 0.00010291266478581954, "loss": 0.5975028991699218, "step": 288980 }, { "epoch": 1.7178165736398165, "grad_norm": 1.41566801071167, "learning_rate": 0.00010290645936423668, "loss": 0.5400539398193359, "step": 288990 }, { "epoch": 1.717876015716485, "grad_norm": 1.3458991050720215, "learning_rate": 0.00010290025397658696, "loss": 0.5614238739013672, "step": 289000 }, { "epoch": 1.7179354577931534, "grad_norm": 1.404607892036438, "learning_rate": 0.00010289404862290011, "loss": 0.5516401290893554, "step": 289010 }, { "epoch": 1.7179948998698218, "grad_norm": 1.5091770887374878, "learning_rate": 0.00010288784330320585, "loss": 0.5625528812408447, "step": 289020 }, { "epoch": 1.7180543419464902, "grad_norm": 1.5781100988388062, "learning_rate": 0.00010288163801753379, "loss": 0.5423296928405762, "step": 289030 }, { "epoch": 1.7181137840231586, "grad_norm": 1.5218955278396606, "learning_rate": 0.00010287543276591362, "loss": 0.5707242965698243, "step": 289040 }, { "epoch": 1.718173226099827, "grad_norm": 1.3604742288589478, "learning_rate": 0.00010286922754837511, "loss": 0.5065655708312988, "step": 289050 }, { "epoch": 1.7182326681764954, "grad_norm": 1.3972280025482178, "learning_rate": 0.00010286302236494787, "loss": 0.573882007598877, "step": 289060 }, { "epoch": 1.7182921102531639, "grad_norm": 1.1465762853622437, "learning_rate": 0.00010285681721566156, "loss": 0.4822370529174805, "step": 289070 }, { "epoch": 1.7183515523298323, "grad_norm": 1.2579067945480347, "learning_rate": 0.00010285061210054594, "loss": 0.5398096561431884, "step": 289080 }, { "epoch": 1.7184109944065007, "grad_norm": 1.456984281539917, "learning_rate": 0.00010284440701963065, "loss": 0.5922400951385498, "step": 289090 }, { "epoch": 1.718470436483169, "grad_norm": 1.283337116241455, "learning_rate": 0.00010283820197294533, "loss": 0.5317754745483398, "step": 289100 }, { "epoch": 1.7185298785598375, "grad_norm": 1.4677586555480957, "learning_rate": 0.0001028319969605198, "loss": 0.5601601600646973, "step": 289110 }, { "epoch": 1.7185893206365057, "grad_norm": 1.485986590385437, "learning_rate": 0.0001028257919823836, "loss": 0.6003592491149903, "step": 289120 }, { "epoch": 1.7186487627131741, "grad_norm": 1.6251418590545654, "learning_rate": 0.00010281958703856645, "loss": 0.5839673042297363, "step": 289130 }, { "epoch": 1.7187082047898425, "grad_norm": 1.585422396659851, "learning_rate": 0.0001028133821290981, "loss": 0.5630223274230957, "step": 289140 }, { "epoch": 1.718767646866511, "grad_norm": 1.9252707958221436, "learning_rate": 0.00010280717725400815, "loss": 0.49848041534423826, "step": 289150 }, { "epoch": 1.7188270889431794, "grad_norm": 1.2902535200119019, "learning_rate": 0.00010280097241332631, "loss": 0.5707757949829102, "step": 289160 }, { "epoch": 1.7188865310198476, "grad_norm": 1.4754523038864136, "learning_rate": 0.00010279476760708226, "loss": 0.5304982185363769, "step": 289170 }, { "epoch": 1.718945973096516, "grad_norm": 1.5929492712020874, "learning_rate": 0.00010278856283530571, "loss": 0.5100617408752441, "step": 289180 }, { "epoch": 1.7190054151731844, "grad_norm": 2.0058555603027344, "learning_rate": 0.00010278235809802632, "loss": 0.5652518272399902, "step": 289190 }, { "epoch": 1.7190648572498528, "grad_norm": 1.9438072443008423, "learning_rate": 0.00010277615339527376, "loss": 0.560912036895752, "step": 289200 }, { "epoch": 1.7191242993265212, "grad_norm": 1.3149065971374512, "learning_rate": 0.00010276994872707772, "loss": 0.5695834159851074, "step": 289210 }, { "epoch": 1.7191837414031896, "grad_norm": 1.6536628007888794, "learning_rate": 0.00010276374409346788, "loss": 0.5885849952697754, "step": 289220 }, { "epoch": 1.719243183479858, "grad_norm": 1.5193977355957031, "learning_rate": 0.00010275753949447391, "loss": 0.5723846435546875, "step": 289230 }, { "epoch": 1.7193026255565265, "grad_norm": 1.3559709787368774, "learning_rate": 0.00010275133493012552, "loss": 0.5796119689941406, "step": 289240 }, { "epoch": 1.7193620676331949, "grad_norm": 1.3696709871292114, "learning_rate": 0.00010274513040045239, "loss": 0.5550159454345703, "step": 289250 }, { "epoch": 1.7194215097098633, "grad_norm": 1.2610169649124146, "learning_rate": 0.00010273892590548418, "loss": 0.5807745933532715, "step": 289260 }, { "epoch": 1.7194809517865317, "grad_norm": 1.3220933675765991, "learning_rate": 0.00010273272144525055, "loss": 0.5781571388244628, "step": 289270 }, { "epoch": 1.7195403938632001, "grad_norm": 1.2271698713302612, "learning_rate": 0.00010272651701978123, "loss": 0.5319218635559082, "step": 289280 }, { "epoch": 1.7195998359398685, "grad_norm": 1.3492958545684814, "learning_rate": 0.00010272031262910586, "loss": 0.527534294128418, "step": 289290 }, { "epoch": 1.719659278016537, "grad_norm": 1.290045976638794, "learning_rate": 0.00010271410827325414, "loss": 0.5170638084411621, "step": 289300 }, { "epoch": 1.7197187200932051, "grad_norm": 1.4589956998825073, "learning_rate": 0.00010270790395225576, "loss": 0.5322553634643554, "step": 289310 }, { "epoch": 1.7197781621698736, "grad_norm": 1.6700574159622192, "learning_rate": 0.00010270169966614036, "loss": 0.5731804847717286, "step": 289320 }, { "epoch": 1.719837604246542, "grad_norm": 1.4937289953231812, "learning_rate": 0.00010269549541493764, "loss": 0.5742005348205567, "step": 289330 }, { "epoch": 1.7198970463232104, "grad_norm": 1.2926535606384277, "learning_rate": 0.00010268929119867729, "loss": 0.5795953750610352, "step": 289340 }, { "epoch": 1.7199564883998786, "grad_norm": 1.2179526090621948, "learning_rate": 0.00010268308701738903, "loss": 0.5946832656860351, "step": 289350 }, { "epoch": 1.720015930476547, "grad_norm": 1.6667920351028442, "learning_rate": 0.00010267688287110242, "loss": 0.568753433227539, "step": 289360 }, { "epoch": 1.7200753725532154, "grad_norm": 1.5001615285873413, "learning_rate": 0.00010267067875984724, "loss": 0.477838134765625, "step": 289370 }, { "epoch": 1.7201348146298838, "grad_norm": 1.2750041484832764, "learning_rate": 0.00010266447468365315, "loss": 0.5343711376190186, "step": 289380 }, { "epoch": 1.7201942567065522, "grad_norm": 1.418062686920166, "learning_rate": 0.0001026582706425498, "loss": 0.5500340461730957, "step": 289390 }, { "epoch": 1.7202536987832207, "grad_norm": 1.7381839752197266, "learning_rate": 0.00010265206663656688, "loss": 0.5364461898803711, "step": 289400 }, { "epoch": 1.720313140859889, "grad_norm": 1.595118761062622, "learning_rate": 0.00010264586266573408, "loss": 0.5292012214660644, "step": 289410 }, { "epoch": 1.7203725829365575, "grad_norm": 1.452250599861145, "learning_rate": 0.00010263965873008108, "loss": 0.5376847743988037, "step": 289420 }, { "epoch": 1.720432025013226, "grad_norm": 1.7729499340057373, "learning_rate": 0.00010263345482963751, "loss": 0.561218547821045, "step": 289430 }, { "epoch": 1.7204914670898943, "grad_norm": 1.6273630857467651, "learning_rate": 0.00010262725096443313, "loss": 0.6138481140136719, "step": 289440 }, { "epoch": 1.7205509091665627, "grad_norm": 1.32160222530365, "learning_rate": 0.00010262104713449756, "loss": 0.532126522064209, "step": 289450 }, { "epoch": 1.7206103512432311, "grad_norm": 1.4013850688934326, "learning_rate": 0.00010261484333986046, "loss": 0.5588148593902588, "step": 289460 }, { "epoch": 1.7206697933198996, "grad_norm": 1.6057168245315552, "learning_rate": 0.00010260863958055156, "loss": 0.5395892143249512, "step": 289470 }, { "epoch": 1.720729235396568, "grad_norm": 1.4241043329238892, "learning_rate": 0.00010260243585660052, "loss": 0.5689023017883301, "step": 289480 }, { "epoch": 1.7207886774732362, "grad_norm": 1.6711500883102417, "learning_rate": 0.00010259623216803697, "loss": 0.5566023826599121, "step": 289490 }, { "epoch": 1.7208481195499046, "grad_norm": 1.459653615951538, "learning_rate": 0.00010259002851489068, "loss": 0.5925241470336914, "step": 289500 }, { "epoch": 1.720907561626573, "grad_norm": 1.4078563451766968, "learning_rate": 0.00010258382489719125, "loss": 0.5828082084655761, "step": 289510 }, { "epoch": 1.7209670037032414, "grad_norm": 1.371734857559204, "learning_rate": 0.00010257762131496839, "loss": 0.49378442764282227, "step": 289520 }, { "epoch": 1.7210264457799098, "grad_norm": 1.7556225061416626, "learning_rate": 0.00010257141776825172, "loss": 0.5850101947784424, "step": 289530 }, { "epoch": 1.721085887856578, "grad_norm": 1.3867955207824707, "learning_rate": 0.00010256521425707099, "loss": 0.5230295181274414, "step": 289540 }, { "epoch": 1.7211453299332464, "grad_norm": 1.3985440731048584, "learning_rate": 0.00010255901078145589, "loss": 0.5918730735778809, "step": 289550 }, { "epoch": 1.7212047720099148, "grad_norm": 1.4614059925079346, "learning_rate": 0.00010255280734143595, "loss": 0.5662224292755127, "step": 289560 }, { "epoch": 1.7212642140865833, "grad_norm": 1.2055079936981201, "learning_rate": 0.000102546603937041, "loss": 0.5437808513641358, "step": 289570 }, { "epoch": 1.7213236561632517, "grad_norm": 1.4479410648345947, "learning_rate": 0.0001025404005683007, "loss": 0.5704925537109375, "step": 289580 }, { "epoch": 1.72138309823992, "grad_norm": 1.6749770641326904, "learning_rate": 0.00010253419723524462, "loss": 0.5831228256225586, "step": 289590 }, { "epoch": 1.7214425403165885, "grad_norm": 1.5497304201126099, "learning_rate": 0.00010252799393790254, "loss": 0.5676943302154541, "step": 289600 }, { "epoch": 1.721501982393257, "grad_norm": 1.4432727098464966, "learning_rate": 0.0001025217906763041, "loss": 0.5361836910247803, "step": 289610 }, { "epoch": 1.7215614244699253, "grad_norm": 1.6860071420669556, "learning_rate": 0.00010251558745047896, "loss": 0.523681640625, "step": 289620 }, { "epoch": 1.7216208665465937, "grad_norm": 1.171522617340088, "learning_rate": 0.00010250938426045678, "loss": 0.5447809219360351, "step": 289630 }, { "epoch": 1.7216803086232622, "grad_norm": 1.5449780225753784, "learning_rate": 0.00010250318110626729, "loss": 0.5345396995544434, "step": 289640 }, { "epoch": 1.7217397506999306, "grad_norm": 1.7258104085922241, "learning_rate": 0.00010249697798794012, "loss": 0.5969673156738281, "step": 289650 }, { "epoch": 1.721799192776599, "grad_norm": 1.5026806592941284, "learning_rate": 0.00010249077490550492, "loss": 0.5369411468505859, "step": 289660 }, { "epoch": 1.7218586348532674, "grad_norm": 1.2727099657058716, "learning_rate": 0.00010248457185899142, "loss": 0.6125688552856445, "step": 289670 }, { "epoch": 1.7219180769299356, "grad_norm": 1.6574459075927734, "learning_rate": 0.00010247836884842932, "loss": 0.6270060539245605, "step": 289680 }, { "epoch": 1.721977519006604, "grad_norm": 1.099787950515747, "learning_rate": 0.00010247216587384818, "loss": 0.5210688591003418, "step": 289690 }, { "epoch": 1.7220369610832724, "grad_norm": 1.0835663080215454, "learning_rate": 0.00010246596293527777, "loss": 0.548013973236084, "step": 289700 }, { "epoch": 1.7220964031599408, "grad_norm": 1.4345369338989258, "learning_rate": 0.00010245976003274773, "loss": 0.523779296875, "step": 289710 }, { "epoch": 1.722155845236609, "grad_norm": 1.5057958364486694, "learning_rate": 0.00010245355716628773, "loss": 0.5996082305908204, "step": 289720 }, { "epoch": 1.7222152873132774, "grad_norm": 1.4873932600021362, "learning_rate": 0.00010244735433592745, "loss": 0.5496348381042481, "step": 289730 }, { "epoch": 1.7222747293899459, "grad_norm": 1.6302075386047363, "learning_rate": 0.00010244115154169655, "loss": 0.6496767997741699, "step": 289740 }, { "epoch": 1.7223341714666143, "grad_norm": 1.1491928100585938, "learning_rate": 0.00010243494878362472, "loss": 0.5616002082824707, "step": 289750 }, { "epoch": 1.7223936135432827, "grad_norm": 1.0617977380752563, "learning_rate": 0.0001024287460617416, "loss": 0.5236214637756348, "step": 289760 }, { "epoch": 1.722453055619951, "grad_norm": 1.7276965379714966, "learning_rate": 0.00010242254337607691, "loss": 0.5629536151885987, "step": 289770 }, { "epoch": 1.7225124976966195, "grad_norm": 1.3602958917617798, "learning_rate": 0.00010241634072666031, "loss": 0.5333639144897461, "step": 289780 }, { "epoch": 1.722571939773288, "grad_norm": 1.5097049474716187, "learning_rate": 0.00010241013811352142, "loss": 0.5929084777832031, "step": 289790 }, { "epoch": 1.7226313818499563, "grad_norm": 1.6510637998580933, "learning_rate": 0.00010240393553668996, "loss": 0.5806335926055908, "step": 289800 }, { "epoch": 1.7226908239266248, "grad_norm": 1.560805082321167, "learning_rate": 0.00010239773299619562, "loss": 0.5294488906860352, "step": 289810 }, { "epoch": 1.7227502660032932, "grad_norm": 1.5847419500350952, "learning_rate": 0.000102391530492068, "loss": 0.5654456138610839, "step": 289820 }, { "epoch": 1.7228097080799616, "grad_norm": 1.4152309894561768, "learning_rate": 0.00010238532802433682, "loss": 0.5789605617523194, "step": 289830 }, { "epoch": 1.72286915015663, "grad_norm": 1.3977348804473877, "learning_rate": 0.00010237912559303176, "loss": 0.5485274314880371, "step": 289840 }, { "epoch": 1.7229285922332984, "grad_norm": 1.2488291263580322, "learning_rate": 0.00010237292319818245, "loss": 0.48648724555969236, "step": 289850 }, { "epoch": 1.7229880343099666, "grad_norm": 1.4499828815460205, "learning_rate": 0.00010236672083981862, "loss": 0.5606475830078125, "step": 289860 }, { "epoch": 1.723047476386635, "grad_norm": 0.9993152618408203, "learning_rate": 0.00010236051851796988, "loss": 0.5374751091003418, "step": 289870 }, { "epoch": 1.7231069184633034, "grad_norm": 1.4760690927505493, "learning_rate": 0.00010235431623266591, "loss": 0.5949365139007569, "step": 289880 }, { "epoch": 1.7231663605399719, "grad_norm": 1.580061435699463, "learning_rate": 0.0001023481139839364, "loss": 0.599698543548584, "step": 289890 }, { "epoch": 1.7232258026166403, "grad_norm": 1.5720278024673462, "learning_rate": 0.00010234191177181102, "loss": 0.5343098640441895, "step": 289900 }, { "epoch": 1.7232852446933085, "grad_norm": 1.3355804681777954, "learning_rate": 0.00010233570959631944, "loss": 0.5426899433135987, "step": 289910 }, { "epoch": 1.7233446867699769, "grad_norm": 1.5849686861038208, "learning_rate": 0.00010232950745749129, "loss": 0.5277507781982422, "step": 289920 }, { "epoch": 1.7234041288466453, "grad_norm": 1.4807651042938232, "learning_rate": 0.0001023233053553563, "loss": 0.5307122230529785, "step": 289930 }, { "epoch": 1.7234635709233137, "grad_norm": 1.4183411598205566, "learning_rate": 0.0001023171032899441, "loss": 0.5276939868927002, "step": 289940 }, { "epoch": 1.7235230129999821, "grad_norm": 1.8127408027648926, "learning_rate": 0.00010231090126128435, "loss": 0.5358967781066895, "step": 289950 }, { "epoch": 1.7235824550766505, "grad_norm": 1.431102991104126, "learning_rate": 0.00010230469926940676, "loss": 0.5875300407409668, "step": 289960 }, { "epoch": 1.723641897153319, "grad_norm": 1.428247332572937, "learning_rate": 0.00010229849731434096, "loss": 0.5658431053161621, "step": 289970 }, { "epoch": 1.7237013392299874, "grad_norm": 1.8094309568405151, "learning_rate": 0.00010229229539611663, "loss": 0.5949348449707031, "step": 289980 }, { "epoch": 1.7237607813066558, "grad_norm": 1.678441047668457, "learning_rate": 0.00010228609351476344, "loss": 0.5481247901916504, "step": 289990 }, { "epoch": 1.7238202233833242, "grad_norm": 1.480528473854065, "learning_rate": 0.00010227989167031106, "loss": 0.4764425277709961, "step": 290000 }, { "epoch": 1.7238796654599926, "grad_norm": 1.3291736841201782, "learning_rate": 0.0001022736898627892, "loss": 0.5037030220031739, "step": 290010 }, { "epoch": 1.723939107536661, "grad_norm": 1.4412293434143066, "learning_rate": 0.00010226748809222739, "loss": 0.5480709075927734, "step": 290020 }, { "epoch": 1.7239985496133294, "grad_norm": 1.257818341255188, "learning_rate": 0.00010226128635865546, "loss": 0.5499821662902832, "step": 290030 }, { "epoch": 1.7240579916899976, "grad_norm": 1.3276243209838867, "learning_rate": 0.000102255084662103, "loss": 0.609900951385498, "step": 290040 }, { "epoch": 1.724117433766666, "grad_norm": 1.5714235305786133, "learning_rate": 0.00010224888300259966, "loss": 0.5989359855651856, "step": 290050 }, { "epoch": 1.7241768758433345, "grad_norm": 1.4087239503860474, "learning_rate": 0.00010224268138017514, "loss": 0.5088070392608642, "step": 290060 }, { "epoch": 1.7242363179200029, "grad_norm": 1.4032206535339355, "learning_rate": 0.00010223647979485913, "loss": 0.5639919757843017, "step": 290070 }, { "epoch": 1.7242957599966713, "grad_norm": 1.4497041702270508, "learning_rate": 0.00010223027824668119, "loss": 0.5978043556213379, "step": 290080 }, { "epoch": 1.7243552020733395, "grad_norm": 1.9284714460372925, "learning_rate": 0.00010222407673567111, "loss": 0.5938356399536133, "step": 290090 }, { "epoch": 1.724414644150008, "grad_norm": 1.3542914390563965, "learning_rate": 0.00010221787526185852, "loss": 0.5516731262207031, "step": 290100 }, { "epoch": 1.7244740862266763, "grad_norm": 1.152276635169983, "learning_rate": 0.00010221167382527306, "loss": 0.5663525581359863, "step": 290110 }, { "epoch": 1.7245335283033447, "grad_norm": 1.4520264863967896, "learning_rate": 0.00010220547242594435, "loss": 0.6189191818237305, "step": 290120 }, { "epoch": 1.7245929703800131, "grad_norm": 1.395892858505249, "learning_rate": 0.00010219927106390219, "loss": 0.5229764938354492, "step": 290130 }, { "epoch": 1.7246524124566815, "grad_norm": 1.3396711349487305, "learning_rate": 0.00010219306973917615, "loss": 0.59184250831604, "step": 290140 }, { "epoch": 1.72471185453335, "grad_norm": 1.3845206499099731, "learning_rate": 0.00010218686845179586, "loss": 0.5302558898925781, "step": 290150 }, { "epoch": 1.7247712966100184, "grad_norm": 1.5622590780258179, "learning_rate": 0.00010218066720179112, "loss": 0.5865026473999023, "step": 290160 }, { "epoch": 1.7248307386866868, "grad_norm": 1.5086472034454346, "learning_rate": 0.00010217446598919148, "loss": 0.5376842021942139, "step": 290170 }, { "epoch": 1.7248901807633552, "grad_norm": 1.3038115501403809, "learning_rate": 0.0001021682648140266, "loss": 0.6052799224853516, "step": 290180 }, { "epoch": 1.7249496228400236, "grad_norm": 1.9291068315505981, "learning_rate": 0.00010216206367632622, "loss": 0.5748035907745361, "step": 290190 }, { "epoch": 1.725009064916692, "grad_norm": 1.4528827667236328, "learning_rate": 0.00010215586257611996, "loss": 0.5713064193725585, "step": 290200 }, { "epoch": 1.7250685069933605, "grad_norm": 1.5674272775650024, "learning_rate": 0.00010214966151343745, "loss": 0.5432513236999512, "step": 290210 }, { "epoch": 1.7251279490700289, "grad_norm": 1.5886174440383911, "learning_rate": 0.00010214346048830846, "loss": 0.6378843784332275, "step": 290220 }, { "epoch": 1.725187391146697, "grad_norm": 1.7118960618972778, "learning_rate": 0.00010213725950076255, "loss": 0.563090705871582, "step": 290230 }, { "epoch": 1.7252468332233655, "grad_norm": 1.5576359033584595, "learning_rate": 0.00010213105855082946, "loss": 0.5661369800567627, "step": 290240 }, { "epoch": 1.7253062753000339, "grad_norm": 1.8275139331817627, "learning_rate": 0.00010212485763853875, "loss": 0.5891518592834473, "step": 290250 }, { "epoch": 1.7253657173767023, "grad_norm": 1.8126263618469238, "learning_rate": 0.00010211865676392019, "loss": 0.5722187042236329, "step": 290260 }, { "epoch": 1.7254251594533707, "grad_norm": 1.7130846977233887, "learning_rate": 0.00010211245592700339, "loss": 0.6273075103759765, "step": 290270 }, { "epoch": 1.725484601530039, "grad_norm": 1.7718257904052734, "learning_rate": 0.00010210625512781802, "loss": 0.5960814476013183, "step": 290280 }, { "epoch": 1.7255440436067073, "grad_norm": 1.2578531503677368, "learning_rate": 0.00010210005436639374, "loss": 0.5589015007019043, "step": 290290 }, { "epoch": 1.7256034856833757, "grad_norm": 1.6048617362976074, "learning_rate": 0.00010209385364276025, "loss": 0.5832004547119141, "step": 290300 }, { "epoch": 1.7256629277600442, "grad_norm": 1.4245197772979736, "learning_rate": 0.00010208765295694714, "loss": 0.604419469833374, "step": 290310 }, { "epoch": 1.7257223698367126, "grad_norm": 1.6061524152755737, "learning_rate": 0.00010208145230898413, "loss": 0.6237098217010498, "step": 290320 }, { "epoch": 1.725781811913381, "grad_norm": 1.2931126356124878, "learning_rate": 0.00010207525169890086, "loss": 0.5664312362670898, "step": 290330 }, { "epoch": 1.7258412539900494, "grad_norm": 1.4805152416229248, "learning_rate": 0.000102069051126727, "loss": 0.5288479804992676, "step": 290340 }, { "epoch": 1.7259006960667178, "grad_norm": 1.3879051208496094, "learning_rate": 0.0001020628505924922, "loss": 0.5932683944702148, "step": 290350 }, { "epoch": 1.7259601381433862, "grad_norm": 1.670810341835022, "learning_rate": 0.00010205665009622616, "loss": 0.5796514511108398, "step": 290360 }, { "epoch": 1.7260195802200546, "grad_norm": 1.4327290058135986, "learning_rate": 0.00010205044963795849, "loss": 0.5968297481536865, "step": 290370 }, { "epoch": 1.726079022296723, "grad_norm": 1.248680830001831, "learning_rate": 0.00010204424921771885, "loss": 0.5441262245178222, "step": 290380 }, { "epoch": 1.7261384643733915, "grad_norm": 1.145982265472412, "learning_rate": 0.00010203804883553696, "loss": 0.543582534790039, "step": 290390 }, { "epoch": 1.7261979064500599, "grad_norm": 1.1475269794464111, "learning_rate": 0.0001020318484914424, "loss": 0.5464543342590332, "step": 290400 }, { "epoch": 1.726257348526728, "grad_norm": 1.4729135036468506, "learning_rate": 0.0001020256481854649, "loss": 0.5738055229187011, "step": 290410 }, { "epoch": 1.7263167906033965, "grad_norm": 1.481217861175537, "learning_rate": 0.0001020194479176341, "loss": 0.5689051628112793, "step": 290420 }, { "epoch": 1.726376232680065, "grad_norm": 1.370164394378662, "learning_rate": 0.00010201324768797964, "loss": 0.5922565460205078, "step": 290430 }, { "epoch": 1.7264356747567333, "grad_norm": 1.4019752740859985, "learning_rate": 0.00010200704749653118, "loss": 0.5826625347137451, "step": 290440 }, { "epoch": 1.7264951168334017, "grad_norm": 1.6787601709365845, "learning_rate": 0.00010200084734331841, "loss": 0.5605890274047851, "step": 290450 }, { "epoch": 1.72655455891007, "grad_norm": 1.4113914966583252, "learning_rate": 0.00010199464722837098, "loss": 0.5603237152099609, "step": 290460 }, { "epoch": 1.7266140009867383, "grad_norm": 2.02062726020813, "learning_rate": 0.00010198844715171851, "loss": 0.5490052223205566, "step": 290470 }, { "epoch": 1.7266734430634068, "grad_norm": 1.2253516912460327, "learning_rate": 0.00010198224711339073, "loss": 0.5837438583374024, "step": 290480 }, { "epoch": 1.7267328851400752, "grad_norm": 1.6332449913024902, "learning_rate": 0.00010197604711341724, "loss": 0.5397358894348144, "step": 290490 }, { "epoch": 1.7267923272167436, "grad_norm": 2.150846242904663, "learning_rate": 0.00010196984715182773, "loss": 0.5719611167907714, "step": 290500 }, { "epoch": 1.726851769293412, "grad_norm": 1.4056942462921143, "learning_rate": 0.00010196364722865182, "loss": 0.555357837677002, "step": 290510 }, { "epoch": 1.7269112113700804, "grad_norm": 1.6184402704238892, "learning_rate": 0.0001019574473439192, "loss": 0.5659582138061523, "step": 290520 }, { "epoch": 1.7269706534467488, "grad_norm": 1.4670931100845337, "learning_rate": 0.00010195124749765956, "loss": 0.5687348365783691, "step": 290530 }, { "epoch": 1.7270300955234172, "grad_norm": 1.4902700185775757, "learning_rate": 0.00010194504768990247, "loss": 0.5766301155090332, "step": 290540 }, { "epoch": 1.7270895376000857, "grad_norm": 1.5435760021209717, "learning_rate": 0.00010193884792067767, "loss": 0.5582047462463379, "step": 290550 }, { "epoch": 1.727148979676754, "grad_norm": 1.240469217300415, "learning_rate": 0.00010193264819001482, "loss": 0.523583984375, "step": 290560 }, { "epoch": 1.7272084217534225, "grad_norm": 1.3741446733474731, "learning_rate": 0.00010192644849794345, "loss": 0.5196475505828857, "step": 290570 }, { "epoch": 1.727267863830091, "grad_norm": 1.4811712503433228, "learning_rate": 0.00010192024884449338, "loss": 0.5474475860595703, "step": 290580 }, { "epoch": 1.7273273059067593, "grad_norm": 1.3549176454544067, "learning_rate": 0.00010191404922969423, "loss": 0.51943998336792, "step": 290590 }, { "epoch": 1.7273867479834275, "grad_norm": 1.356103539466858, "learning_rate": 0.00010190784965357558, "loss": 0.5618531227111816, "step": 290600 }, { "epoch": 1.727446190060096, "grad_norm": 1.3760446310043335, "learning_rate": 0.0001019016501161671, "loss": 0.5869114875793457, "step": 290610 }, { "epoch": 1.7275056321367643, "grad_norm": 1.6249091625213623, "learning_rate": 0.00010189545061749854, "loss": 0.5937480926513672, "step": 290620 }, { "epoch": 1.7275650742134327, "grad_norm": 1.238906979560852, "learning_rate": 0.00010188925115759949, "loss": 0.5377524375915528, "step": 290630 }, { "epoch": 1.7276245162901012, "grad_norm": 1.2940592765808105, "learning_rate": 0.00010188305173649955, "loss": 0.5448100090026855, "step": 290640 }, { "epoch": 1.7276839583667694, "grad_norm": 1.077795147895813, "learning_rate": 0.0001018768523542285, "loss": 0.5660377025604248, "step": 290650 }, { "epoch": 1.7277434004434378, "grad_norm": 1.3905243873596191, "learning_rate": 0.00010187065301081592, "loss": 0.5662654876708985, "step": 290660 }, { "epoch": 1.7278028425201062, "grad_norm": 1.3553828001022339, "learning_rate": 0.00010186445370629145, "loss": 0.6064544200897217, "step": 290670 }, { "epoch": 1.7278622845967746, "grad_norm": 1.628373146057129, "learning_rate": 0.00010185825444068484, "loss": 0.5764793395996094, "step": 290680 }, { "epoch": 1.727921726673443, "grad_norm": 1.4261888265609741, "learning_rate": 0.00010185205521402563, "loss": 0.5946860313415527, "step": 290690 }, { "epoch": 1.7279811687501114, "grad_norm": 1.507235050201416, "learning_rate": 0.00010184585602634352, "loss": 0.6196523666381836, "step": 290700 }, { "epoch": 1.7280406108267798, "grad_norm": 1.5686968564987183, "learning_rate": 0.00010183965687766821, "loss": 0.6041346073150635, "step": 290710 }, { "epoch": 1.7281000529034483, "grad_norm": 1.3913965225219727, "learning_rate": 0.00010183345776802928, "loss": 0.5541847229003907, "step": 290720 }, { "epoch": 1.7281594949801167, "grad_norm": 1.3199820518493652, "learning_rate": 0.00010182725869745644, "loss": 0.5416349411010742, "step": 290730 }, { "epoch": 1.728218937056785, "grad_norm": 1.531967043876648, "learning_rate": 0.0001018210596659793, "loss": 0.5984649658203125, "step": 290740 }, { "epoch": 1.7282783791334535, "grad_norm": 1.4374423027038574, "learning_rate": 0.00010181486067362755, "loss": 0.5703953742980957, "step": 290750 }, { "epoch": 1.728337821210122, "grad_norm": 1.470119833946228, "learning_rate": 0.00010180866172043085, "loss": 0.5758055210113525, "step": 290760 }, { "epoch": 1.7283972632867903, "grad_norm": 1.1302059888839722, "learning_rate": 0.00010180246280641878, "loss": 0.5134378433227539, "step": 290770 }, { "epoch": 1.7284567053634585, "grad_norm": 1.3382713794708252, "learning_rate": 0.00010179626393162112, "loss": 0.5425224304199219, "step": 290780 }, { "epoch": 1.728516147440127, "grad_norm": 1.2157692909240723, "learning_rate": 0.00010179006509606741, "loss": 0.547301959991455, "step": 290790 }, { "epoch": 1.7285755895167954, "grad_norm": 1.4504892826080322, "learning_rate": 0.00010178386629978733, "loss": 0.5367141723632812, "step": 290800 }, { "epoch": 1.7286350315934638, "grad_norm": 1.2062335014343262, "learning_rate": 0.00010177766754281058, "loss": 0.5606393814086914, "step": 290810 }, { "epoch": 1.7286944736701322, "grad_norm": 1.42388117313385, "learning_rate": 0.0001017714688251668, "loss": 0.5489748954772949, "step": 290820 }, { "epoch": 1.7287539157468004, "grad_norm": 1.748607873916626, "learning_rate": 0.00010176527014688557, "loss": 0.5407594680786133, "step": 290830 }, { "epoch": 1.7288133578234688, "grad_norm": 1.7836805582046509, "learning_rate": 0.00010175907150799664, "loss": 0.5531630516052246, "step": 290840 }, { "epoch": 1.7288727999001372, "grad_norm": 1.2967032194137573, "learning_rate": 0.0001017528729085296, "loss": 0.554072380065918, "step": 290850 }, { "epoch": 1.7289322419768056, "grad_norm": 1.1861913204193115, "learning_rate": 0.00010174667434851412, "loss": 0.5577641487121582, "step": 290860 }, { "epoch": 1.728991684053474, "grad_norm": 1.7021594047546387, "learning_rate": 0.00010174047582797985, "loss": 0.5624080657958984, "step": 290870 }, { "epoch": 1.7290511261301424, "grad_norm": 1.210969090461731, "learning_rate": 0.00010173427734695646, "loss": 0.5942715644836426, "step": 290880 }, { "epoch": 1.7291105682068109, "grad_norm": 1.682306170463562, "learning_rate": 0.00010172807890547358, "loss": 0.5801391124725341, "step": 290890 }, { "epoch": 1.7291700102834793, "grad_norm": 1.375759243965149, "learning_rate": 0.00010172188050356083, "loss": 0.46052303314208987, "step": 290900 }, { "epoch": 1.7292294523601477, "grad_norm": 1.027687668800354, "learning_rate": 0.00010171568214124796, "loss": 0.5375441074371338, "step": 290910 }, { "epoch": 1.729288894436816, "grad_norm": 1.2270379066467285, "learning_rate": 0.00010170948381856453, "loss": 0.5309134960174561, "step": 290920 }, { "epoch": 1.7293483365134845, "grad_norm": 1.4605365991592407, "learning_rate": 0.00010170328553554021, "loss": 0.5493310451507568, "step": 290930 }, { "epoch": 1.729407778590153, "grad_norm": 1.5660430192947388, "learning_rate": 0.00010169708729220469, "loss": 0.6101502418518067, "step": 290940 }, { "epoch": 1.7294672206668213, "grad_norm": 1.3922791481018066, "learning_rate": 0.00010169088908858757, "loss": 0.57490234375, "step": 290950 }, { "epoch": 1.7295266627434898, "grad_norm": 1.4834502935409546, "learning_rate": 0.00010168469092471853, "loss": 0.5352607727050781, "step": 290960 }, { "epoch": 1.729586104820158, "grad_norm": 1.777021050453186, "learning_rate": 0.00010167849280062718, "loss": 0.5083492279052735, "step": 290970 }, { "epoch": 1.7296455468968264, "grad_norm": 1.77538001537323, "learning_rate": 0.00010167229471634323, "loss": 0.5592683792114258, "step": 290980 }, { "epoch": 1.7297049889734948, "grad_norm": 1.2963746786117554, "learning_rate": 0.0001016660966718963, "loss": 0.5333834648132324, "step": 290990 }, { "epoch": 1.7297644310501632, "grad_norm": 1.6362435817718506, "learning_rate": 0.00010165989866731603, "loss": 0.589594030380249, "step": 291000 }, { "epoch": 1.7298238731268316, "grad_norm": 1.2295842170715332, "learning_rate": 0.00010165370070263209, "loss": 0.583826732635498, "step": 291010 }, { "epoch": 1.7298833152034998, "grad_norm": 1.2631036043167114, "learning_rate": 0.00010164750277787414, "loss": 0.5773964881896972, "step": 291020 }, { "epoch": 1.7299427572801682, "grad_norm": 1.556792140007019, "learning_rate": 0.00010164130489307175, "loss": 0.516604995727539, "step": 291030 }, { "epoch": 1.7300021993568366, "grad_norm": 1.2162184715270996, "learning_rate": 0.00010163510704825467, "loss": 0.5389607429504395, "step": 291040 }, { "epoch": 1.730061641433505, "grad_norm": 1.3213080167770386, "learning_rate": 0.0001016289092434525, "loss": 0.5256776332855224, "step": 291050 }, { "epoch": 1.7301210835101735, "grad_norm": 1.5754444599151611, "learning_rate": 0.00010162271147869487, "loss": 0.5488110542297363, "step": 291060 }, { "epoch": 1.7301805255868419, "grad_norm": 1.6307569742202759, "learning_rate": 0.00010161651375401147, "loss": 0.5443963527679443, "step": 291070 }, { "epoch": 1.7302399676635103, "grad_norm": 1.0873438119888306, "learning_rate": 0.00010161031606943194, "loss": 0.5553456306457519, "step": 291080 }, { "epoch": 1.7302994097401787, "grad_norm": 1.2410845756530762, "learning_rate": 0.0001016041184249859, "loss": 0.5809371471405029, "step": 291090 }, { "epoch": 1.7303588518168471, "grad_norm": 1.0576403141021729, "learning_rate": 0.00010159792082070298, "loss": 0.528907585144043, "step": 291100 }, { "epoch": 1.7304182938935155, "grad_norm": 1.7274410724639893, "learning_rate": 0.00010159172325661292, "loss": 0.6089829444885254, "step": 291110 }, { "epoch": 1.730477735970184, "grad_norm": 1.5491796731948853, "learning_rate": 0.00010158552573274529, "loss": 0.5525569915771484, "step": 291120 }, { "epoch": 1.7305371780468524, "grad_norm": 1.630678415298462, "learning_rate": 0.00010157932824912973, "loss": 0.506625747680664, "step": 291130 }, { "epoch": 1.7305966201235208, "grad_norm": 1.5341488122940063, "learning_rate": 0.00010157313080579593, "loss": 0.5635058879852295, "step": 291140 }, { "epoch": 1.730656062200189, "grad_norm": 1.3294637203216553, "learning_rate": 0.00010156693340277353, "loss": 0.5025736808776855, "step": 291150 }, { "epoch": 1.7307155042768574, "grad_norm": 1.041943907737732, "learning_rate": 0.00010156073604009211, "loss": 0.556826114654541, "step": 291160 }, { "epoch": 1.7307749463535258, "grad_norm": 1.1590256690979004, "learning_rate": 0.00010155453871778144, "loss": 0.4922314643859863, "step": 291170 }, { "epoch": 1.7308343884301942, "grad_norm": 1.5881916284561157, "learning_rate": 0.00010154834143587108, "loss": 0.5928059577941894, "step": 291180 }, { "epoch": 1.7308938305068626, "grad_norm": 1.720529317855835, "learning_rate": 0.00010154214419439064, "loss": 0.5567265510559082, "step": 291190 }, { "epoch": 1.7309532725835308, "grad_norm": 1.526209831237793, "learning_rate": 0.00010153594699336988, "loss": 0.5565898895263672, "step": 291200 }, { "epoch": 1.7310127146601992, "grad_norm": 2.1905322074890137, "learning_rate": 0.00010152974983283838, "loss": 0.6042404174804688, "step": 291210 }, { "epoch": 1.7310721567368677, "grad_norm": 1.1469765901565552, "learning_rate": 0.00010152355271282578, "loss": 0.5454380512237549, "step": 291220 }, { "epoch": 1.731131598813536, "grad_norm": 1.0001834630966187, "learning_rate": 0.0001015173556333617, "loss": 0.5250759124755859, "step": 291230 }, { "epoch": 1.7311910408902045, "grad_norm": 1.4148820638656616, "learning_rate": 0.00010151115859447585, "loss": 0.5606250762939453, "step": 291240 }, { "epoch": 1.731250482966873, "grad_norm": 1.3805733919143677, "learning_rate": 0.00010150496159619785, "loss": 0.5884096145629882, "step": 291250 }, { "epoch": 1.7313099250435413, "grad_norm": 1.910954236984253, "learning_rate": 0.0001014987646385573, "loss": 0.5779829025268555, "step": 291260 }, { "epoch": 1.7313693671202097, "grad_norm": 1.3433125019073486, "learning_rate": 0.0001014925677215839, "loss": 0.5583775997161865, "step": 291270 }, { "epoch": 1.7314288091968781, "grad_norm": 1.2899459600448608, "learning_rate": 0.0001014863708453073, "loss": 0.5764144420623779, "step": 291280 }, { "epoch": 1.7314882512735466, "grad_norm": 1.2361778020858765, "learning_rate": 0.0001014801740097571, "loss": 0.5510557174682618, "step": 291290 }, { "epoch": 1.731547693350215, "grad_norm": 1.6158441305160522, "learning_rate": 0.00010147397721496297, "loss": 0.5489449501037598, "step": 291300 }, { "epoch": 1.7316071354268834, "grad_norm": 1.4326393604278564, "learning_rate": 0.00010146778046095455, "loss": 0.5628740310668945, "step": 291310 }, { "epoch": 1.7316665775035518, "grad_norm": 0.9570850729942322, "learning_rate": 0.00010146158374776144, "loss": 0.4912714958190918, "step": 291320 }, { "epoch": 1.7317260195802202, "grad_norm": 1.3759268522262573, "learning_rate": 0.00010145538707541337, "loss": 0.627906322479248, "step": 291330 }, { "epoch": 1.7317854616568884, "grad_norm": 1.5066949129104614, "learning_rate": 0.00010144919044393993, "loss": 0.5304606914520263, "step": 291340 }, { "epoch": 1.7318449037335568, "grad_norm": 1.095275640487671, "learning_rate": 0.00010144299385337074, "loss": 0.5106914520263672, "step": 291350 }, { "epoch": 1.7319043458102252, "grad_norm": 1.4454509019851685, "learning_rate": 0.0001014367973037355, "loss": 0.5305214405059815, "step": 291360 }, { "epoch": 1.7319637878868936, "grad_norm": 1.5185304880142212, "learning_rate": 0.00010143060079506381, "loss": 0.5342723846435546, "step": 291370 }, { "epoch": 1.732023229963562, "grad_norm": 1.5689146518707275, "learning_rate": 0.00010142440432738533, "loss": 0.5657928466796875, "step": 291380 }, { "epoch": 1.7320826720402303, "grad_norm": 1.7877415418624878, "learning_rate": 0.00010141820790072968, "loss": 0.5557567119598389, "step": 291390 }, { "epoch": 1.7321421141168987, "grad_norm": 1.5619854927062988, "learning_rate": 0.00010141201151512656, "loss": 0.5698092460632325, "step": 291400 }, { "epoch": 1.732201556193567, "grad_norm": 1.43379545211792, "learning_rate": 0.00010140581517060555, "loss": 0.5770079612731933, "step": 291410 }, { "epoch": 1.7322609982702355, "grad_norm": 1.3906333446502686, "learning_rate": 0.0001013996188671963, "loss": 0.4964326858520508, "step": 291420 }, { "epoch": 1.732320440346904, "grad_norm": 1.4339791536331177, "learning_rate": 0.00010139342260492845, "loss": 0.561644172668457, "step": 291430 }, { "epoch": 1.7323798824235723, "grad_norm": 1.2139934301376343, "learning_rate": 0.0001013872263838317, "loss": 0.5674813270568848, "step": 291440 }, { "epoch": 1.7324393245002407, "grad_norm": 1.2744640111923218, "learning_rate": 0.00010138103020393561, "loss": 0.6102577209472656, "step": 291450 }, { "epoch": 1.7324987665769092, "grad_norm": 1.1917425394058228, "learning_rate": 0.00010137483406526983, "loss": 0.5923624992370605, "step": 291460 }, { "epoch": 1.7325582086535776, "grad_norm": 1.6756800413131714, "learning_rate": 0.00010136863796786409, "loss": 0.5596931457519532, "step": 291470 }, { "epoch": 1.732617650730246, "grad_norm": 1.4415979385375977, "learning_rate": 0.00010136244191174793, "loss": 0.5673614501953125, "step": 291480 }, { "epoch": 1.7326770928069144, "grad_norm": 1.4896405935287476, "learning_rate": 0.000101356245896951, "loss": 0.5621870994567871, "step": 291490 }, { "epoch": 1.7327365348835828, "grad_norm": 1.6058242321014404, "learning_rate": 0.000101350049923503, "loss": 0.6008836269378662, "step": 291500 }, { "epoch": 1.7327959769602512, "grad_norm": 1.4347296953201294, "learning_rate": 0.00010134385399143354, "loss": 0.5438119888305664, "step": 291510 }, { "epoch": 1.7328554190369194, "grad_norm": 1.422494649887085, "learning_rate": 0.00010133765810077222, "loss": 0.525584602355957, "step": 291520 }, { "epoch": 1.7329148611135878, "grad_norm": 1.6962157487869263, "learning_rate": 0.00010133146225154875, "loss": 0.5831833839416504, "step": 291530 }, { "epoch": 1.7329743031902562, "grad_norm": 1.3994766473770142, "learning_rate": 0.0001013252664437927, "loss": 0.5256648063659668, "step": 291540 }, { "epoch": 1.7330337452669247, "grad_norm": 1.4083164930343628, "learning_rate": 0.00010131907067753374, "loss": 0.5742978096008301, "step": 291550 }, { "epoch": 1.733093187343593, "grad_norm": 1.6421825885772705, "learning_rate": 0.00010131287495280153, "loss": 0.5650426864624023, "step": 291560 }, { "epoch": 1.7331526294202613, "grad_norm": 1.8129726648330688, "learning_rate": 0.00010130667926962569, "loss": 0.5867693901062012, "step": 291570 }, { "epoch": 1.7332120714969297, "grad_norm": 1.2685801982879639, "learning_rate": 0.00010130048362803588, "loss": 0.5776100158691406, "step": 291580 }, { "epoch": 1.733271513573598, "grad_norm": 1.879331350326538, "learning_rate": 0.00010129428802806164, "loss": 0.49959564208984375, "step": 291590 }, { "epoch": 1.7333309556502665, "grad_norm": 1.4410878419876099, "learning_rate": 0.00010128809246973271, "loss": 0.5450478553771972, "step": 291600 }, { "epoch": 1.733390397726935, "grad_norm": 1.4305387735366821, "learning_rate": 0.00010128189695307875, "loss": 0.5417661666870117, "step": 291610 }, { "epoch": 1.7334498398036033, "grad_norm": 1.5161218643188477, "learning_rate": 0.00010127570147812928, "loss": 0.5347007751464844, "step": 291620 }, { "epoch": 1.7335092818802718, "grad_norm": 1.5474413633346558, "learning_rate": 0.00010126950604491403, "loss": 0.5557079315185547, "step": 291630 }, { "epoch": 1.7335687239569402, "grad_norm": 1.3570373058319092, "learning_rate": 0.00010126331065346261, "loss": 0.5543390274047851, "step": 291640 }, { "epoch": 1.7336281660336086, "grad_norm": 1.6991174221038818, "learning_rate": 0.00010125711530380464, "loss": 0.4932577133178711, "step": 291650 }, { "epoch": 1.733687608110277, "grad_norm": 1.4255590438842773, "learning_rate": 0.00010125091999596981, "loss": 0.6270806312561035, "step": 291660 }, { "epoch": 1.7337470501869454, "grad_norm": 1.3531726598739624, "learning_rate": 0.0001012447247299877, "loss": 0.5415515422821044, "step": 291670 }, { "epoch": 1.7338064922636138, "grad_norm": 1.6298271417617798, "learning_rate": 0.00010123852950588794, "loss": 0.5375959396362304, "step": 291680 }, { "epoch": 1.7338659343402822, "grad_norm": 1.4313523769378662, "learning_rate": 0.00010123233432370023, "loss": 0.5792768001556396, "step": 291690 }, { "epoch": 1.7339253764169507, "grad_norm": 1.4628936052322388, "learning_rate": 0.00010122613918345416, "loss": 0.5841598987579346, "step": 291700 }, { "epoch": 1.7339848184936189, "grad_norm": 1.6020452976226807, "learning_rate": 0.00010121994408517936, "loss": 0.5870667934417725, "step": 291710 }, { "epoch": 1.7340442605702873, "grad_norm": 1.254564881324768, "learning_rate": 0.00010121374902890548, "loss": 0.5319737911224365, "step": 291720 }, { "epoch": 1.7341037026469557, "grad_norm": 1.5243884325027466, "learning_rate": 0.00010120755401466216, "loss": 0.5664738178253174, "step": 291730 }, { "epoch": 1.734163144723624, "grad_norm": 1.6507691144943237, "learning_rate": 0.00010120135904247903, "loss": 0.5038403987884521, "step": 291740 }, { "epoch": 1.7342225868002925, "grad_norm": 1.4378405809402466, "learning_rate": 0.0001011951641123857, "loss": 0.647395133972168, "step": 291750 }, { "epoch": 1.7342820288769607, "grad_norm": 1.3934298753738403, "learning_rate": 0.00010118896922441185, "loss": 0.5282170295715332, "step": 291760 }, { "epoch": 1.7343414709536291, "grad_norm": 1.2316340208053589, "learning_rate": 0.0001011827743785871, "loss": 0.5543200969696045, "step": 291770 }, { "epoch": 1.7344009130302975, "grad_norm": 1.416003704071045, "learning_rate": 0.00010117657957494104, "loss": 0.5715744972229004, "step": 291780 }, { "epoch": 1.734460355106966, "grad_norm": 1.1967676877975464, "learning_rate": 0.00010117038481350336, "loss": 0.5746374607086182, "step": 291790 }, { "epoch": 1.7345197971836344, "grad_norm": 1.8297979831695557, "learning_rate": 0.00010116419009430368, "loss": 0.6048494815826416, "step": 291800 }, { "epoch": 1.7345792392603028, "grad_norm": 1.2724690437316895, "learning_rate": 0.00010115799541737162, "loss": 0.5371596336364746, "step": 291810 }, { "epoch": 1.7346386813369712, "grad_norm": 1.311034083366394, "learning_rate": 0.00010115180078273683, "loss": 0.5925644874572754, "step": 291820 }, { "epoch": 1.7346981234136396, "grad_norm": 1.625114917755127, "learning_rate": 0.00010114560619042892, "loss": 0.5699210643768311, "step": 291830 }, { "epoch": 1.734757565490308, "grad_norm": 1.8589102029800415, "learning_rate": 0.00010113941164047756, "loss": 0.5334743976593017, "step": 291840 }, { "epoch": 1.7348170075669764, "grad_norm": 1.5607879161834717, "learning_rate": 0.00010113321713291233, "loss": 0.5709226608276368, "step": 291850 }, { "epoch": 1.7348764496436448, "grad_norm": 1.6428985595703125, "learning_rate": 0.0001011270226677629, "loss": 0.5857836723327636, "step": 291860 }, { "epoch": 1.7349358917203133, "grad_norm": 1.5135527849197388, "learning_rate": 0.0001011208282450589, "loss": 0.553629207611084, "step": 291870 }, { "epoch": 1.7349953337969817, "grad_norm": 1.32084059715271, "learning_rate": 0.00010111463386482994, "loss": 0.5693730354309082, "step": 291880 }, { "epoch": 1.7350547758736499, "grad_norm": 1.6293374300003052, "learning_rate": 0.00010110843952710569, "loss": 0.5242344856262207, "step": 291890 }, { "epoch": 1.7351142179503183, "grad_norm": 1.3654388189315796, "learning_rate": 0.00010110224523191576, "loss": 0.578501558303833, "step": 291900 }, { "epoch": 1.7351736600269867, "grad_norm": 1.1985195875167847, "learning_rate": 0.00010109605097928975, "loss": 0.5199480056762695, "step": 291910 }, { "epoch": 1.7352331021036551, "grad_norm": 1.5109577178955078, "learning_rate": 0.00010108985676925735, "loss": 0.581700325012207, "step": 291920 }, { "epoch": 1.7352925441803235, "grad_norm": 1.7978081703186035, "learning_rate": 0.00010108366260184817, "loss": 0.5366254329681397, "step": 291930 }, { "epoch": 1.7353519862569917, "grad_norm": 1.456009030342102, "learning_rate": 0.00010107746847709183, "loss": 0.5351741790771485, "step": 291940 }, { "epoch": 1.7354114283336601, "grad_norm": 1.746873378753662, "learning_rate": 0.00010107127439501793, "loss": 0.5481643199920654, "step": 291950 }, { "epoch": 1.7354708704103285, "grad_norm": 1.3598144054412842, "learning_rate": 0.00010106508035565617, "loss": 0.5345361709594727, "step": 291960 }, { "epoch": 1.735530312486997, "grad_norm": 1.5409330129623413, "learning_rate": 0.00010105888635903613, "loss": 0.5521574020385742, "step": 291970 }, { "epoch": 1.7355897545636654, "grad_norm": 1.551612138748169, "learning_rate": 0.00010105269240518746, "loss": 0.6080584049224853, "step": 291980 }, { "epoch": 1.7356491966403338, "grad_norm": 1.3329737186431885, "learning_rate": 0.00010104649849413979, "loss": 0.5455459594726563, "step": 291990 }, { "epoch": 1.7357086387170022, "grad_norm": 1.4240710735321045, "learning_rate": 0.00010104030462592275, "loss": 0.5396407127380372, "step": 292000 }, { "epoch": 1.7357680807936706, "grad_norm": 1.3554168939590454, "learning_rate": 0.00010103411080056596, "loss": 0.5118401527404786, "step": 292010 }, { "epoch": 1.735827522870339, "grad_norm": 1.04993736743927, "learning_rate": 0.00010102791701809904, "loss": 0.6156883716583252, "step": 292020 }, { "epoch": 1.7358869649470074, "grad_norm": 1.3700790405273438, "learning_rate": 0.00010102172327855164, "loss": 0.5086167812347412, "step": 292030 }, { "epoch": 1.7359464070236759, "grad_norm": 1.737425684928894, "learning_rate": 0.00010101552958195337, "loss": 0.5585992813110352, "step": 292040 }, { "epoch": 1.7360058491003443, "grad_norm": 1.7672953605651855, "learning_rate": 0.0001010093359283339, "loss": 0.5210875034332275, "step": 292050 }, { "epoch": 1.7360652911770127, "grad_norm": 1.4417572021484375, "learning_rate": 0.00010100314231772283, "loss": 0.5551093101501465, "step": 292060 }, { "epoch": 1.736124733253681, "grad_norm": 1.39314866065979, "learning_rate": 0.0001009969487501498, "loss": 0.541721248626709, "step": 292070 }, { "epoch": 1.7361841753303493, "grad_norm": 2.0718278884887695, "learning_rate": 0.00010099075522564436, "loss": 0.5299528121948243, "step": 292080 }, { "epoch": 1.7362436174070177, "grad_norm": 1.9504950046539307, "learning_rate": 0.00010098456174423624, "loss": 0.5784126281738281, "step": 292090 }, { "epoch": 1.7363030594836861, "grad_norm": 1.7439976930618286, "learning_rate": 0.00010097836830595506, "loss": 0.5429635047912598, "step": 292100 }, { "epoch": 1.7363625015603545, "grad_norm": 1.3999578952789307, "learning_rate": 0.00010097217491083035, "loss": 0.5931724071502685, "step": 292110 }, { "epoch": 1.736421943637023, "grad_norm": 1.4358959197998047, "learning_rate": 0.00010096598155889186, "loss": 0.5966029644012452, "step": 292120 }, { "epoch": 1.7364813857136912, "grad_norm": 1.1828426122665405, "learning_rate": 0.00010095978825016916, "loss": 0.5531557559967041, "step": 292130 }, { "epoch": 1.7365408277903596, "grad_norm": 1.5590661764144897, "learning_rate": 0.00010095359498469184, "loss": 0.5799277305603028, "step": 292140 }, { "epoch": 1.736600269867028, "grad_norm": 1.8352863788604736, "learning_rate": 0.00010094740176248958, "loss": 0.5806078433990478, "step": 292150 }, { "epoch": 1.7366597119436964, "grad_norm": 1.2876296043395996, "learning_rate": 0.00010094120858359204, "loss": 0.5246223449707031, "step": 292160 }, { "epoch": 1.7367191540203648, "grad_norm": 1.5454998016357422, "learning_rate": 0.0001009350154480287, "loss": 0.5455354690551758, "step": 292170 }, { "epoch": 1.7367785960970332, "grad_norm": 1.5939371585845947, "learning_rate": 0.00010092882235582937, "loss": 0.6044432163238526, "step": 292180 }, { "epoch": 1.7368380381737016, "grad_norm": 1.3143038749694824, "learning_rate": 0.00010092262930702359, "loss": 0.5378841400146485, "step": 292190 }, { "epoch": 1.73689748025037, "grad_norm": 1.364790678024292, "learning_rate": 0.00010091643630164094, "loss": 0.4797947883605957, "step": 292200 }, { "epoch": 1.7369569223270385, "grad_norm": 1.9077136516571045, "learning_rate": 0.00010091024333971109, "loss": 0.6525527954101562, "step": 292210 }, { "epoch": 1.7370163644037069, "grad_norm": 1.459259271621704, "learning_rate": 0.00010090405042126369, "loss": 0.5127315998077393, "step": 292220 }, { "epoch": 1.7370758064803753, "grad_norm": 1.2090188264846802, "learning_rate": 0.00010089785754632835, "loss": 0.5432194232940674, "step": 292230 }, { "epoch": 1.7371352485570437, "grad_norm": 1.6960428953170776, "learning_rate": 0.00010089166471493463, "loss": 0.6031874179840088, "step": 292240 }, { "epoch": 1.7371946906337121, "grad_norm": 1.1378381252288818, "learning_rate": 0.00010088547192711226, "loss": 0.5696035861968994, "step": 292250 }, { "epoch": 1.7372541327103803, "grad_norm": 1.2926108837127686, "learning_rate": 0.00010087927918289082, "loss": 0.5175234794616699, "step": 292260 }, { "epoch": 1.7373135747870487, "grad_norm": 1.3402268886566162, "learning_rate": 0.00010087308648229985, "loss": 0.5387001991271972, "step": 292270 }, { "epoch": 1.7373730168637171, "grad_norm": 1.4270579814910889, "learning_rate": 0.00010086689382536914, "loss": 0.5405863285064697, "step": 292280 }, { "epoch": 1.7374324589403856, "grad_norm": 1.3438794612884521, "learning_rate": 0.0001008607012121282, "loss": 0.5776202201843261, "step": 292290 }, { "epoch": 1.737491901017054, "grad_norm": 1.3953748941421509, "learning_rate": 0.00010085450864260668, "loss": 0.5510281562805176, "step": 292300 }, { "epoch": 1.7375513430937222, "grad_norm": 1.4023478031158447, "learning_rate": 0.00010084831611683419, "loss": 0.5177350044250488, "step": 292310 }, { "epoch": 1.7376107851703906, "grad_norm": 1.3268299102783203, "learning_rate": 0.00010084212363484038, "loss": 0.5716902732849121, "step": 292320 }, { "epoch": 1.737670227247059, "grad_norm": 1.5068508386611938, "learning_rate": 0.00010083593119665484, "loss": 0.5656797885894775, "step": 292330 }, { "epoch": 1.7377296693237274, "grad_norm": 1.3027857542037964, "learning_rate": 0.0001008297388023072, "loss": 0.5395162582397461, "step": 292340 }, { "epoch": 1.7377891114003958, "grad_norm": 1.4128491878509521, "learning_rate": 0.00010082354645182713, "loss": 0.5220911026000976, "step": 292350 }, { "epoch": 1.7378485534770642, "grad_norm": 1.0972129106521606, "learning_rate": 0.00010081735414524418, "loss": 0.5457345962524414, "step": 292360 }, { "epoch": 1.7379079955537327, "grad_norm": 1.416009783744812, "learning_rate": 0.00010081116188258802, "loss": 0.603364372253418, "step": 292370 }, { "epoch": 1.737967437630401, "grad_norm": 1.2254014015197754, "learning_rate": 0.00010080496966388827, "loss": 0.5572694778442383, "step": 292380 }, { "epoch": 1.7380268797070695, "grad_norm": 1.8405121564865112, "learning_rate": 0.00010079877748917453, "loss": 0.5583247661590576, "step": 292390 }, { "epoch": 1.738086321783738, "grad_norm": 1.2525408267974854, "learning_rate": 0.00010079258535847642, "loss": 0.5204005718231202, "step": 292400 }, { "epoch": 1.7381457638604063, "grad_norm": 1.433855652809143, "learning_rate": 0.00010078639327182357, "loss": 0.5740439414978027, "step": 292410 }, { "epoch": 1.7382052059370747, "grad_norm": 1.1812381744384766, "learning_rate": 0.00010078020122924564, "loss": 0.5982023239135742, "step": 292420 }, { "epoch": 1.7382646480137431, "grad_norm": 1.5856633186340332, "learning_rate": 0.0001007740092307722, "loss": 0.5269579887390137, "step": 292430 }, { "epoch": 1.7383240900904116, "grad_norm": 1.5810109376907349, "learning_rate": 0.00010076781727643286, "loss": 0.5658050537109375, "step": 292440 }, { "epoch": 1.7383835321670797, "grad_norm": 1.5912030935287476, "learning_rate": 0.00010076162536625728, "loss": 0.5746294021606445, "step": 292450 }, { "epoch": 1.7384429742437482, "grad_norm": 1.3884670734405518, "learning_rate": 0.00010075543350027507, "loss": 0.5340536117553711, "step": 292460 }, { "epoch": 1.7385024163204166, "grad_norm": 1.898929476737976, "learning_rate": 0.00010074924167851583, "loss": 0.5555280685424805, "step": 292470 }, { "epoch": 1.738561858397085, "grad_norm": 1.3214759826660156, "learning_rate": 0.00010074304990100922, "loss": 0.5387080192565918, "step": 292480 }, { "epoch": 1.7386213004737534, "grad_norm": 1.5935642719268799, "learning_rate": 0.00010073685816778482, "loss": 0.5543344497680665, "step": 292490 }, { "epoch": 1.7386807425504216, "grad_norm": 1.4642298221588135, "learning_rate": 0.00010073066647887226, "loss": 0.5928927421569824, "step": 292500 }, { "epoch": 1.73874018462709, "grad_norm": 1.6810293197631836, "learning_rate": 0.00010072447483430116, "loss": 0.6186703205108642, "step": 292510 }, { "epoch": 1.7387996267037584, "grad_norm": 1.5501352548599243, "learning_rate": 0.00010071828323410118, "loss": 0.5712188720703125, "step": 292520 }, { "epoch": 1.7388590687804268, "grad_norm": 1.1171320676803589, "learning_rate": 0.00010071209167830183, "loss": 0.542418384552002, "step": 292530 }, { "epoch": 1.7389185108570953, "grad_norm": 1.4366087913513184, "learning_rate": 0.00010070590016693285, "loss": 0.5959155082702636, "step": 292540 }, { "epoch": 1.7389779529337637, "grad_norm": 1.5172570943832397, "learning_rate": 0.00010069970870002379, "loss": 0.507353687286377, "step": 292550 }, { "epoch": 1.739037395010432, "grad_norm": 1.656996250152588, "learning_rate": 0.00010069351727760432, "loss": 0.5566987991333008, "step": 292560 }, { "epoch": 1.7390968370871005, "grad_norm": 1.694576382637024, "learning_rate": 0.00010068732589970396, "loss": 0.6179285049438477, "step": 292570 }, { "epoch": 1.739156279163769, "grad_norm": 1.4634205102920532, "learning_rate": 0.00010068113456635243, "loss": 0.5181115150451661, "step": 292580 }, { "epoch": 1.7392157212404373, "grad_norm": 1.550399661064148, "learning_rate": 0.00010067494327757929, "loss": 0.5810558319091796, "step": 292590 }, { "epoch": 1.7392751633171057, "grad_norm": 1.2203611135482788, "learning_rate": 0.00010066875203341414, "loss": 0.5561969757080079, "step": 292600 }, { "epoch": 1.7393346053937742, "grad_norm": 1.5592639446258545, "learning_rate": 0.00010066256083388668, "loss": 0.5746198654174804, "step": 292610 }, { "epoch": 1.7393940474704426, "grad_norm": 1.1670665740966797, "learning_rate": 0.00010065636967902649, "loss": 0.5499567985534668, "step": 292620 }, { "epoch": 1.7394534895471108, "grad_norm": 1.2331793308258057, "learning_rate": 0.00010065017856886311, "loss": 0.5605872631072998, "step": 292630 }, { "epoch": 1.7395129316237792, "grad_norm": 1.2532941102981567, "learning_rate": 0.00010064398750342627, "loss": 0.5532725334167481, "step": 292640 }, { "epoch": 1.7395723737004476, "grad_norm": 1.5256129503250122, "learning_rate": 0.00010063779648274557, "loss": 0.5896131992340088, "step": 292650 }, { "epoch": 1.739631815777116, "grad_norm": 1.4435086250305176, "learning_rate": 0.00010063160550685053, "loss": 0.5392290115356445, "step": 292660 }, { "epoch": 1.7396912578537844, "grad_norm": 1.4615185260772705, "learning_rate": 0.00010062541457577081, "loss": 0.5736530303955079, "step": 292670 }, { "epoch": 1.7397506999304526, "grad_norm": 1.5132571458816528, "learning_rate": 0.00010061922368953614, "loss": 0.5194549560546875, "step": 292680 }, { "epoch": 1.739810142007121, "grad_norm": 1.4356770515441895, "learning_rate": 0.00010061303284817596, "loss": 0.5531467437744141, "step": 292690 }, { "epoch": 1.7398695840837894, "grad_norm": 1.5180224180221558, "learning_rate": 0.00010060684205171996, "loss": 0.5756836891174316, "step": 292700 }, { "epoch": 1.7399290261604579, "grad_norm": 1.171426773071289, "learning_rate": 0.00010060065130019781, "loss": 0.549308443069458, "step": 292710 }, { "epoch": 1.7399884682371263, "grad_norm": 1.3789961338043213, "learning_rate": 0.00010059446059363901, "loss": 0.5398088932037354, "step": 292720 }, { "epoch": 1.7400479103137947, "grad_norm": 1.3137891292572021, "learning_rate": 0.00010058826993207324, "loss": 0.5789033889770507, "step": 292730 }, { "epoch": 1.740107352390463, "grad_norm": 1.313056468963623, "learning_rate": 0.00010058207931553018, "loss": 0.6053616523742675, "step": 292740 }, { "epoch": 1.7401667944671315, "grad_norm": 1.3989746570587158, "learning_rate": 0.00010057588874403933, "loss": 0.5504180908203125, "step": 292750 }, { "epoch": 1.7402262365438, "grad_norm": 1.3867143392562866, "learning_rate": 0.00010056969821763034, "loss": 0.6328377723693848, "step": 292760 }, { "epoch": 1.7402856786204683, "grad_norm": 1.662373661994934, "learning_rate": 0.00010056350773633286, "loss": 0.5942032814025879, "step": 292770 }, { "epoch": 1.7403451206971368, "grad_norm": 1.6844319105148315, "learning_rate": 0.00010055731730017646, "loss": 0.5839732170104981, "step": 292780 }, { "epoch": 1.7404045627738052, "grad_norm": 1.7059179544448853, "learning_rate": 0.00010055112690919078, "loss": 0.5473516464233399, "step": 292790 }, { "epoch": 1.7404640048504736, "grad_norm": 1.1686946153640747, "learning_rate": 0.00010054493656340538, "loss": 0.5492586135864258, "step": 292800 }, { "epoch": 1.740523446927142, "grad_norm": 1.597246527671814, "learning_rate": 0.00010053874626284994, "loss": 0.542604637145996, "step": 292810 }, { "epoch": 1.7405828890038102, "grad_norm": 1.4738689661026, "learning_rate": 0.00010053255600755406, "loss": 0.5548552989959716, "step": 292820 }, { "epoch": 1.7406423310804786, "grad_norm": 1.199384093284607, "learning_rate": 0.0001005263657975473, "loss": 0.5851844787597656, "step": 292830 }, { "epoch": 1.740701773157147, "grad_norm": 1.3359744548797607, "learning_rate": 0.00010052017563285936, "loss": 0.5650043487548828, "step": 292840 }, { "epoch": 1.7407612152338154, "grad_norm": 1.2177660465240479, "learning_rate": 0.00010051398551351978, "loss": 0.548061752319336, "step": 292850 }, { "epoch": 1.7408206573104839, "grad_norm": 1.5772768259048462, "learning_rate": 0.00010050779543955817, "loss": 0.5516027450561524, "step": 292860 }, { "epoch": 1.740880099387152, "grad_norm": 1.2940542697906494, "learning_rate": 0.0001005016054110042, "loss": 0.5953093528747558, "step": 292870 }, { "epoch": 1.7409395414638205, "grad_norm": 1.7299799919128418, "learning_rate": 0.00010049541542788744, "loss": 0.5476818084716797, "step": 292880 }, { "epoch": 1.7409989835404889, "grad_norm": 1.3799653053283691, "learning_rate": 0.00010048922549023748, "loss": 0.612800407409668, "step": 292890 }, { "epoch": 1.7410584256171573, "grad_norm": 1.4454604387283325, "learning_rate": 0.00010048303559808396, "loss": 0.5049249649047851, "step": 292900 }, { "epoch": 1.7411178676938257, "grad_norm": 1.2720829248428345, "learning_rate": 0.0001004768457514565, "loss": 0.5866970539093017, "step": 292910 }, { "epoch": 1.7411773097704941, "grad_norm": 1.3247005939483643, "learning_rate": 0.00010047065595038471, "loss": 0.54937744140625, "step": 292920 }, { "epoch": 1.7412367518471625, "grad_norm": 1.437868356704712, "learning_rate": 0.00010046446619489818, "loss": 0.5956254959106445, "step": 292930 }, { "epoch": 1.741296193923831, "grad_norm": 1.707327961921692, "learning_rate": 0.00010045827648502653, "loss": 0.6151917457580567, "step": 292940 }, { "epoch": 1.7413556360004994, "grad_norm": 1.8857324123382568, "learning_rate": 0.00010045208682079936, "loss": 0.5401189804077149, "step": 292950 }, { "epoch": 1.7414150780771678, "grad_norm": 1.8688815832138062, "learning_rate": 0.00010044589720224629, "loss": 0.537546968460083, "step": 292960 }, { "epoch": 1.7414745201538362, "grad_norm": 1.2314562797546387, "learning_rate": 0.00010043970762939691, "loss": 0.5262701988220215, "step": 292970 }, { "epoch": 1.7415339622305046, "grad_norm": 1.5776524543762207, "learning_rate": 0.00010043351810228088, "loss": 0.5575127601623535, "step": 292980 }, { "epoch": 1.741593404307173, "grad_norm": 1.291347622871399, "learning_rate": 0.00010042732862092772, "loss": 0.5705755233764649, "step": 292990 }, { "epoch": 1.7416528463838412, "grad_norm": 1.481356143951416, "learning_rate": 0.00010042113918536714, "loss": 0.5726028919219971, "step": 293000 }, { "epoch": 1.7417122884605096, "grad_norm": 1.258271336555481, "learning_rate": 0.00010041494979562867, "loss": 0.5346471786499023, "step": 293010 }, { "epoch": 1.741771730537178, "grad_norm": 1.1781198978424072, "learning_rate": 0.00010040876045174195, "loss": 0.5831130981445313, "step": 293020 }, { "epoch": 1.7418311726138465, "grad_norm": 1.1827877759933472, "learning_rate": 0.00010040257115373662, "loss": 0.555604076385498, "step": 293030 }, { "epoch": 1.7418906146905149, "grad_norm": 1.339444875717163, "learning_rate": 0.00010039638190164222, "loss": 0.5707510471343994, "step": 293040 }, { "epoch": 1.741950056767183, "grad_norm": 2.4476349353790283, "learning_rate": 0.00010039019269548841, "loss": 0.5419943809509278, "step": 293050 }, { "epoch": 1.7420094988438515, "grad_norm": 1.4933838844299316, "learning_rate": 0.00010038400353530475, "loss": 0.5398253917694091, "step": 293060 }, { "epoch": 1.74206894092052, "grad_norm": 1.7473872900009155, "learning_rate": 0.00010037781442112088, "loss": 0.5829545974731445, "step": 293070 }, { "epoch": 1.7421283829971883, "grad_norm": 1.2509140968322754, "learning_rate": 0.00010037162535296645, "loss": 0.5965979099273682, "step": 293080 }, { "epoch": 1.7421878250738567, "grad_norm": 1.4653117656707764, "learning_rate": 0.00010036543633087095, "loss": 0.5451412200927734, "step": 293090 }, { "epoch": 1.7422472671505251, "grad_norm": 1.2844897508621216, "learning_rate": 0.00010035924735486408, "loss": 0.4884503841400146, "step": 293100 }, { "epoch": 1.7423067092271936, "grad_norm": 1.6457346677780151, "learning_rate": 0.00010035305842497546, "loss": 0.5927382469177246, "step": 293110 }, { "epoch": 1.742366151303862, "grad_norm": 1.6922798156738281, "learning_rate": 0.00010034686954123458, "loss": 0.5608357906341552, "step": 293120 }, { "epoch": 1.7424255933805304, "grad_norm": 1.5959035158157349, "learning_rate": 0.00010034068070367116, "loss": 0.587862205505371, "step": 293130 }, { "epoch": 1.7424850354571988, "grad_norm": 1.441529393196106, "learning_rate": 0.00010033449191231479, "loss": 0.537395429611206, "step": 293140 }, { "epoch": 1.7425444775338672, "grad_norm": 1.7201021909713745, "learning_rate": 0.00010032830316719504, "loss": 0.5729840755462646, "step": 293150 }, { "epoch": 1.7426039196105356, "grad_norm": 1.636149525642395, "learning_rate": 0.00010032211446834148, "loss": 0.5758471488952637, "step": 293160 }, { "epoch": 1.742663361687204, "grad_norm": 1.5534886121749878, "learning_rate": 0.00010031592581578382, "loss": 0.6062400817871094, "step": 293170 }, { "epoch": 1.7427228037638725, "grad_norm": 1.6037732362747192, "learning_rate": 0.00010030973720955159, "loss": 0.5830722332000733, "step": 293180 }, { "epoch": 1.7427822458405406, "grad_norm": 1.580209732055664, "learning_rate": 0.00010030354864967438, "loss": 0.5522984504699707, "step": 293190 }, { "epoch": 1.742841687917209, "grad_norm": 1.4629766941070557, "learning_rate": 0.00010029736013618187, "loss": 0.5273728370666504, "step": 293200 }, { "epoch": 1.7429011299938775, "grad_norm": 1.1312721967697144, "learning_rate": 0.00010029117166910361, "loss": 0.5126453399658203, "step": 293210 }, { "epoch": 1.7429605720705459, "grad_norm": 1.361707329750061, "learning_rate": 0.00010028498324846915, "loss": 0.5722191333770752, "step": 293220 }, { "epoch": 1.743020014147214, "grad_norm": 1.3622406721115112, "learning_rate": 0.00010027879487430825, "loss": 0.611809778213501, "step": 293230 }, { "epoch": 1.7430794562238825, "grad_norm": 1.7360754013061523, "learning_rate": 0.00010027260654665038, "loss": 0.5737939357757569, "step": 293240 }, { "epoch": 1.743138898300551, "grad_norm": 1.45633065700531, "learning_rate": 0.00010026641826552514, "loss": 0.5270289421081543, "step": 293250 }, { "epoch": 1.7431983403772193, "grad_norm": 1.5908726453781128, "learning_rate": 0.00010026023003096223, "loss": 0.5675592422485352, "step": 293260 }, { "epoch": 1.7432577824538877, "grad_norm": 1.8466612100601196, "learning_rate": 0.00010025404184299118, "loss": 0.5794605255126953, "step": 293270 }, { "epoch": 1.7433172245305562, "grad_norm": 1.5862963199615479, "learning_rate": 0.00010024785370164161, "loss": 0.5658313751220703, "step": 293280 }, { "epoch": 1.7433766666072246, "grad_norm": 1.391532301902771, "learning_rate": 0.0001002416656069431, "loss": 0.48071718215942383, "step": 293290 }, { "epoch": 1.743436108683893, "grad_norm": 1.3380650281906128, "learning_rate": 0.00010023547755892528, "loss": 0.6088833808898926, "step": 293300 }, { "epoch": 1.7434955507605614, "grad_norm": 1.363111138343811, "learning_rate": 0.00010022928955761777, "loss": 0.6018186569213867, "step": 293310 }, { "epoch": 1.7435549928372298, "grad_norm": 1.694442629814148, "learning_rate": 0.0001002231016030501, "loss": 0.5542031288146972, "step": 293320 }, { "epoch": 1.7436144349138982, "grad_norm": 1.369326114654541, "learning_rate": 0.00010021691369525196, "loss": 0.5480254650115967, "step": 293330 }, { "epoch": 1.7436738769905666, "grad_norm": 1.3703705072402954, "learning_rate": 0.00010021072583425288, "loss": 0.5470168113708496, "step": 293340 }, { "epoch": 1.743733319067235, "grad_norm": 1.268883466720581, "learning_rate": 0.00010020453802008251, "loss": 0.5485328674316406, "step": 293350 }, { "epoch": 1.7437927611439035, "grad_norm": 1.688999056816101, "learning_rate": 0.00010019835025277042, "loss": 0.528706693649292, "step": 293360 }, { "epoch": 1.7438522032205717, "grad_norm": 1.5562412738800049, "learning_rate": 0.00010019216253234622, "loss": 0.5832592964172363, "step": 293370 }, { "epoch": 1.74391164529724, "grad_norm": 1.6286921501159668, "learning_rate": 0.00010018597485883949, "loss": 0.5479086875915528, "step": 293380 }, { "epoch": 1.7439710873739085, "grad_norm": 1.4456787109375, "learning_rate": 0.00010017978723227987, "loss": 0.6208615779876709, "step": 293390 }, { "epoch": 1.744030529450577, "grad_norm": 1.2328897714614868, "learning_rate": 0.00010017359965269694, "loss": 0.5282970905303955, "step": 293400 }, { "epoch": 1.7440899715272453, "grad_norm": 1.4045889377593994, "learning_rate": 0.0001001674121201203, "loss": 0.6006814002990722, "step": 293410 }, { "epoch": 1.7441494136039135, "grad_norm": 1.3908692598342896, "learning_rate": 0.00010016122463457952, "loss": 0.5161869525909424, "step": 293420 }, { "epoch": 1.744208855680582, "grad_norm": 1.349945306777954, "learning_rate": 0.00010015503719610426, "loss": 0.4800971031188965, "step": 293430 }, { "epoch": 1.7442682977572503, "grad_norm": 1.775852918624878, "learning_rate": 0.00010014884980472407, "loss": 0.5508795738220215, "step": 293440 }, { "epoch": 1.7443277398339188, "grad_norm": 1.4344826936721802, "learning_rate": 0.00010014266246046855, "loss": 0.5480238914489746, "step": 293450 }, { "epoch": 1.7443871819105872, "grad_norm": 1.051461100578308, "learning_rate": 0.00010013647516336733, "loss": 0.5312054634094239, "step": 293460 }, { "epoch": 1.7444466239872556, "grad_norm": 1.1825612783432007, "learning_rate": 0.00010013028791345, "loss": 0.5589653968811035, "step": 293470 }, { "epoch": 1.744506066063924, "grad_norm": 1.968440294265747, "learning_rate": 0.00010012410071074612, "loss": 0.5915088653564453, "step": 293480 }, { "epoch": 1.7445655081405924, "grad_norm": 1.582351803779602, "learning_rate": 0.00010011791355528532, "loss": 0.5430583000183106, "step": 293490 }, { "epoch": 1.7446249502172608, "grad_norm": 1.7916761636734009, "learning_rate": 0.00010011172644709721, "loss": 0.5491400718688965, "step": 293500 }, { "epoch": 1.7446843922939292, "grad_norm": 1.91559636592865, "learning_rate": 0.00010010553938621135, "loss": 0.613231086730957, "step": 293510 }, { "epoch": 1.7447438343705977, "grad_norm": 1.3454644680023193, "learning_rate": 0.00010009935237265737, "loss": 0.5747923374176025, "step": 293520 }, { "epoch": 1.744803276447266, "grad_norm": 2.2282772064208984, "learning_rate": 0.00010009316540646486, "loss": 0.5390409469604492, "step": 293530 }, { "epoch": 1.7448627185239345, "grad_norm": 1.5663682222366333, "learning_rate": 0.0001000869784876634, "loss": 0.5805866718292236, "step": 293540 }, { "epoch": 1.744922160600603, "grad_norm": 1.1412460803985596, "learning_rate": 0.00010008079161628257, "loss": 0.5065447807312011, "step": 293550 }, { "epoch": 1.744981602677271, "grad_norm": 1.347736120223999, "learning_rate": 0.00010007460479235203, "loss": 0.5687557697296143, "step": 293560 }, { "epoch": 1.7450410447539395, "grad_norm": 1.3953591585159302, "learning_rate": 0.00010006841801590132, "loss": 0.5153662681579589, "step": 293570 }, { "epoch": 1.745100486830608, "grad_norm": 1.065000057220459, "learning_rate": 0.00010006223128696002, "loss": 0.5550553798675537, "step": 293580 }, { "epoch": 1.7451599289072763, "grad_norm": 1.3171135187149048, "learning_rate": 0.00010005604460555779, "loss": 0.5380328178405762, "step": 293590 }, { "epoch": 1.7452193709839445, "grad_norm": 1.7393828630447388, "learning_rate": 0.00010004985797172421, "loss": 0.5307969093322754, "step": 293600 }, { "epoch": 1.745278813060613, "grad_norm": 1.577770471572876, "learning_rate": 0.00010004367138548882, "loss": 0.6315348625183106, "step": 293610 }, { "epoch": 1.7453382551372814, "grad_norm": 1.5552616119384766, "learning_rate": 0.00010003748484688126, "loss": 0.6064387321472168, "step": 293620 }, { "epoch": 1.7453976972139498, "grad_norm": 1.4978561401367188, "learning_rate": 0.00010003129835593115, "loss": 0.5332994937896729, "step": 293630 }, { "epoch": 1.7454571392906182, "grad_norm": 1.4267158508300781, "learning_rate": 0.00010002511191266806, "loss": 0.5822594165802002, "step": 293640 }, { "epoch": 1.7455165813672866, "grad_norm": 1.6123744249343872, "learning_rate": 0.00010001892551712151, "loss": 0.5820829391479492, "step": 293650 }, { "epoch": 1.745576023443955, "grad_norm": 1.5309504270553589, "learning_rate": 0.00010001273916932121, "loss": 0.5192642688751221, "step": 293660 }, { "epoch": 1.7456354655206234, "grad_norm": 1.4200356006622314, "learning_rate": 0.0001000065528692967, "loss": 0.5195670127868652, "step": 293670 }, { "epoch": 1.7456949075972918, "grad_norm": 1.6436551809310913, "learning_rate": 0.00010000036661707752, "loss": 0.5490992546081543, "step": 293680 }, { "epoch": 1.7457543496739603, "grad_norm": 1.5670435428619385, "learning_rate": 9.999418041269338e-05, "loss": 0.6061117649078369, "step": 293690 }, { "epoch": 1.7458137917506287, "grad_norm": 1.3374383449554443, "learning_rate": 9.99879942561738e-05, "loss": 0.5318281173706054, "step": 293700 }, { "epoch": 1.745873233827297, "grad_norm": 1.8411082029342651, "learning_rate": 9.998180814754834e-05, "loss": 0.5578453540802002, "step": 293710 }, { "epoch": 1.7459326759039655, "grad_norm": 1.8147430419921875, "learning_rate": 9.99756220868467e-05, "loss": 0.5913807868957519, "step": 293720 }, { "epoch": 1.745992117980634, "grad_norm": 1.3083209991455078, "learning_rate": 9.996943607409839e-05, "loss": 0.5229106903076172, "step": 293730 }, { "epoch": 1.746051560057302, "grad_norm": 1.5502337217330933, "learning_rate": 9.996325010933296e-05, "loss": 0.5433302879333496, "step": 293740 }, { "epoch": 1.7461110021339705, "grad_norm": 1.2832555770874023, "learning_rate": 9.995706419258016e-05, "loss": 0.5153214931488037, "step": 293750 }, { "epoch": 1.746170444210639, "grad_norm": 1.6106781959533691, "learning_rate": 9.995087832386942e-05, "loss": 0.5783978462219238, "step": 293760 }, { "epoch": 1.7462298862873074, "grad_norm": 1.3440678119659424, "learning_rate": 9.99446925032304e-05, "loss": 0.5730726242065429, "step": 293770 }, { "epoch": 1.7462893283639758, "grad_norm": 1.5465342998504639, "learning_rate": 9.993850673069269e-05, "loss": 0.5890510082244873, "step": 293780 }, { "epoch": 1.746348770440644, "grad_norm": 1.270658016204834, "learning_rate": 9.993232100628589e-05, "loss": 0.58377103805542, "step": 293790 }, { "epoch": 1.7464082125173124, "grad_norm": 1.3344405889511108, "learning_rate": 9.992613533003957e-05, "loss": 0.5373759746551514, "step": 293800 }, { "epoch": 1.7464676545939808, "grad_norm": 1.35385262966156, "learning_rate": 9.991994970198329e-05, "loss": 0.5557716369628907, "step": 293810 }, { "epoch": 1.7465270966706492, "grad_norm": 1.8245607614517212, "learning_rate": 9.99137641221467e-05, "loss": 0.5875982761383056, "step": 293820 }, { "epoch": 1.7465865387473176, "grad_norm": 1.2903320789337158, "learning_rate": 9.990757859055939e-05, "loss": 0.5969825744628906, "step": 293830 }, { "epoch": 1.746645980823986, "grad_norm": 1.3818252086639404, "learning_rate": 9.990139310725088e-05, "loss": 0.5278307437896729, "step": 293840 }, { "epoch": 1.7467054229006544, "grad_norm": 1.6233824491500854, "learning_rate": 9.989520767225085e-05, "loss": 0.5545639991760254, "step": 293850 }, { "epoch": 1.7467648649773229, "grad_norm": 1.223672866821289, "learning_rate": 9.988902228558883e-05, "loss": 0.5606542587280273, "step": 293860 }, { "epoch": 1.7468243070539913, "grad_norm": 1.6235181093215942, "learning_rate": 9.988283694729439e-05, "loss": 0.5952147483825684, "step": 293870 }, { "epoch": 1.7468837491306597, "grad_norm": 1.1746031045913696, "learning_rate": 9.98766516573972e-05, "loss": 0.5499892234802246, "step": 293880 }, { "epoch": 1.746943191207328, "grad_norm": 1.1917794942855835, "learning_rate": 9.987046641592679e-05, "loss": 0.5475269794464112, "step": 293890 }, { "epoch": 1.7470026332839965, "grad_norm": 1.5298620462417603, "learning_rate": 9.986428122291276e-05, "loss": 0.5915074348449707, "step": 293900 }, { "epoch": 1.747062075360665, "grad_norm": 1.3016235828399658, "learning_rate": 9.985809607838466e-05, "loss": 0.4984899997711182, "step": 293910 }, { "epoch": 1.7471215174373333, "grad_norm": 1.3586260080337524, "learning_rate": 9.985191098237214e-05, "loss": 0.5786552429199219, "step": 293920 }, { "epoch": 1.7471809595140015, "grad_norm": 1.2637693881988525, "learning_rate": 9.984572593490475e-05, "loss": 0.5546343803405762, "step": 293930 }, { "epoch": 1.74724040159067, "grad_norm": 1.4781097173690796, "learning_rate": 9.98395409360121e-05, "loss": 0.5758048057556152, "step": 293940 }, { "epoch": 1.7472998436673384, "grad_norm": 1.5148729085922241, "learning_rate": 9.983335598572379e-05, "loss": 0.5763390064239502, "step": 293950 }, { "epoch": 1.7473592857440068, "grad_norm": 1.713042974472046, "learning_rate": 9.982717108406936e-05, "loss": 0.6415478706359863, "step": 293960 }, { "epoch": 1.747418727820675, "grad_norm": 1.3865076303482056, "learning_rate": 9.982098623107839e-05, "loss": 0.5739049434661865, "step": 293970 }, { "epoch": 1.7474781698973434, "grad_norm": 1.659555435180664, "learning_rate": 9.981480142678052e-05, "loss": 0.5590124607086182, "step": 293980 }, { "epoch": 1.7475376119740118, "grad_norm": 1.558647632598877, "learning_rate": 9.980861667120533e-05, "loss": 0.5583809852600098, "step": 293990 }, { "epoch": 1.7475970540506802, "grad_norm": 1.2763789892196655, "learning_rate": 9.980243196438237e-05, "loss": 0.5664623737335205, "step": 294000 }, { "epoch": 1.7476564961273486, "grad_norm": 1.285603642463684, "learning_rate": 9.979624730634122e-05, "loss": 0.5910255432128906, "step": 294010 }, { "epoch": 1.747715938204017, "grad_norm": 1.381920576095581, "learning_rate": 9.979006269711153e-05, "loss": 0.5558516502380371, "step": 294020 }, { "epoch": 1.7477753802806855, "grad_norm": 1.2185084819793701, "learning_rate": 9.978387813672283e-05, "loss": 0.5287635803222657, "step": 294030 }, { "epoch": 1.7478348223573539, "grad_norm": 1.3986845016479492, "learning_rate": 9.977769362520471e-05, "loss": 0.5939577102661133, "step": 294040 }, { "epoch": 1.7478942644340223, "grad_norm": 1.2804739475250244, "learning_rate": 9.977150916258677e-05, "loss": 0.5823519706726075, "step": 294050 }, { "epoch": 1.7479537065106907, "grad_norm": 1.7581088542938232, "learning_rate": 9.97653247488986e-05, "loss": 0.5511925697326661, "step": 294060 }, { "epoch": 1.7480131485873591, "grad_norm": 1.324038028717041, "learning_rate": 9.975914038416971e-05, "loss": 0.5329992294311523, "step": 294070 }, { "epoch": 1.7480725906640275, "grad_norm": 1.6116544008255005, "learning_rate": 9.97529560684298e-05, "loss": 0.5497775077819824, "step": 294080 }, { "epoch": 1.748132032740696, "grad_norm": 1.7353789806365967, "learning_rate": 9.974677180170839e-05, "loss": 0.5611746311187744, "step": 294090 }, { "epoch": 1.7481914748173644, "grad_norm": 1.4108836650848389, "learning_rate": 9.974058758403509e-05, "loss": 0.5916682720184326, "step": 294100 }, { "epoch": 1.7482509168940326, "grad_norm": 1.773256778717041, "learning_rate": 9.973440341543945e-05, "loss": 0.5988583564758301, "step": 294110 }, { "epoch": 1.748310358970701, "grad_norm": 1.4156781435012817, "learning_rate": 9.972821929595106e-05, "loss": 0.45285768508911134, "step": 294120 }, { "epoch": 1.7483698010473694, "grad_norm": 1.1470274925231934, "learning_rate": 9.972203522559956e-05, "loss": 0.5260756015777588, "step": 294130 }, { "epoch": 1.7484292431240378, "grad_norm": 1.4941741228103638, "learning_rate": 9.97158512044144e-05, "loss": 0.5221042633056641, "step": 294140 }, { "epoch": 1.7484886852007062, "grad_norm": 1.3357361555099487, "learning_rate": 9.97096672324253e-05, "loss": 0.6140121459960938, "step": 294150 }, { "epoch": 1.7485481272773744, "grad_norm": 1.2710542678833008, "learning_rate": 9.970348330966181e-05, "loss": 0.607002067565918, "step": 294160 }, { "epoch": 1.7486075693540428, "grad_norm": 1.4687751531600952, "learning_rate": 9.969729943615342e-05, "loss": 0.5603947639465332, "step": 294170 }, { "epoch": 1.7486670114307112, "grad_norm": 1.4526937007904053, "learning_rate": 9.969111561192982e-05, "loss": 0.5874337673187255, "step": 294180 }, { "epoch": 1.7487264535073797, "grad_norm": 1.329341173171997, "learning_rate": 9.96849318370206e-05, "loss": 0.5604151725769043, "step": 294190 }, { "epoch": 1.748785895584048, "grad_norm": 1.3343749046325684, "learning_rate": 9.967874811145523e-05, "loss": 0.5483276844024658, "step": 294200 }, { "epoch": 1.7488453376607165, "grad_norm": 1.3964859247207642, "learning_rate": 9.967256443526338e-05, "loss": 0.5615769386291504, "step": 294210 }, { "epoch": 1.748904779737385, "grad_norm": 1.1484295129776, "learning_rate": 9.966638080847463e-05, "loss": 0.5662704944610596, "step": 294220 }, { "epoch": 1.7489642218140533, "grad_norm": 1.6169496774673462, "learning_rate": 9.966019723111849e-05, "loss": 0.5126947879791259, "step": 294230 }, { "epoch": 1.7490236638907217, "grad_norm": 1.6233569383621216, "learning_rate": 9.965401370322461e-05, "loss": 0.5293291091918946, "step": 294240 }, { "epoch": 1.7490831059673901, "grad_norm": 1.33510422706604, "learning_rate": 9.964783022482255e-05, "loss": 0.5498343944549561, "step": 294250 }, { "epoch": 1.7491425480440586, "grad_norm": 1.1782407760620117, "learning_rate": 9.964164679594192e-05, "loss": 0.5658188819885254, "step": 294260 }, { "epoch": 1.749201990120727, "grad_norm": 1.4250519275665283, "learning_rate": 9.963546341661219e-05, "loss": 0.5494535446166993, "step": 294270 }, { "epoch": 1.7492614321973954, "grad_norm": 1.1342335939407349, "learning_rate": 9.962928008686308e-05, "loss": 0.5185907363891602, "step": 294280 }, { "epoch": 1.7493208742740638, "grad_norm": 1.2778346538543701, "learning_rate": 9.962309680672409e-05, "loss": 0.5744171142578125, "step": 294290 }, { "epoch": 1.749380316350732, "grad_norm": 1.3644938468933105, "learning_rate": 9.961691357622478e-05, "loss": 0.5225531101226807, "step": 294300 }, { "epoch": 1.7494397584274004, "grad_norm": 1.454012393951416, "learning_rate": 9.961073039539482e-05, "loss": 0.5911443710327149, "step": 294310 }, { "epoch": 1.7494992005040688, "grad_norm": 1.2497079372406006, "learning_rate": 9.96045472642637e-05, "loss": 0.5898848533630371, "step": 294320 }, { "epoch": 1.7495586425807372, "grad_norm": 1.5758124589920044, "learning_rate": 9.959836418286101e-05, "loss": 0.5647954940795898, "step": 294330 }, { "epoch": 1.7496180846574054, "grad_norm": 1.4599096775054932, "learning_rate": 9.959218115121636e-05, "loss": 0.5365418910980224, "step": 294340 }, { "epoch": 1.7496775267340738, "grad_norm": 1.657039999961853, "learning_rate": 9.958599816935934e-05, "loss": 0.4781486034393311, "step": 294350 }, { "epoch": 1.7497369688107423, "grad_norm": 1.1978962421417236, "learning_rate": 9.957981523731945e-05, "loss": 0.5701233863830566, "step": 294360 }, { "epoch": 1.7497964108874107, "grad_norm": 1.3202486038208008, "learning_rate": 9.957363235512635e-05, "loss": 0.5148361682891845, "step": 294370 }, { "epoch": 1.749855852964079, "grad_norm": 1.1900748014450073, "learning_rate": 9.95674495228096e-05, "loss": 0.5502576351165771, "step": 294380 }, { "epoch": 1.7499152950407475, "grad_norm": 1.2701283693313599, "learning_rate": 9.956126674039876e-05, "loss": 0.5482306003570556, "step": 294390 }, { "epoch": 1.749974737117416, "grad_norm": 1.2986226081848145, "learning_rate": 9.955508400792337e-05, "loss": 0.5723039627075195, "step": 294400 }, { "epoch": 1.7500341791940843, "grad_norm": 1.3561575412750244, "learning_rate": 9.954890132541308e-05, "loss": 0.5674299240112305, "step": 294410 }, { "epoch": 1.7500936212707527, "grad_norm": 1.5548310279846191, "learning_rate": 9.954271869289742e-05, "loss": 0.5475019454956055, "step": 294420 }, { "epoch": 1.7501530633474212, "grad_norm": 1.4200717210769653, "learning_rate": 9.953653611040596e-05, "loss": 0.5602422714233398, "step": 294430 }, { "epoch": 1.7502125054240896, "grad_norm": 1.8486316204071045, "learning_rate": 9.953035357796831e-05, "loss": 0.5578560352325439, "step": 294440 }, { "epoch": 1.750271947500758, "grad_norm": 1.1134159564971924, "learning_rate": 9.952417109561405e-05, "loss": 0.5019856452941894, "step": 294450 }, { "epoch": 1.7503313895774264, "grad_norm": 1.9250560998916626, "learning_rate": 9.95179886633727e-05, "loss": 0.5635298728942871, "step": 294460 }, { "epoch": 1.7503908316540948, "grad_norm": 1.3221070766448975, "learning_rate": 9.951180628127386e-05, "loss": 0.6031455039978028, "step": 294470 }, { "epoch": 1.750450273730763, "grad_norm": 0.9809606671333313, "learning_rate": 9.950562394934712e-05, "loss": 0.4904626846313477, "step": 294480 }, { "epoch": 1.7505097158074314, "grad_norm": 1.7705378532409668, "learning_rate": 9.949944166762206e-05, "loss": 0.5961647033691406, "step": 294490 }, { "epoch": 1.7505691578840998, "grad_norm": 1.464235782623291, "learning_rate": 9.949325943612821e-05, "loss": 0.5729430198669434, "step": 294500 }, { "epoch": 1.7506285999607683, "grad_norm": 1.463337779045105, "learning_rate": 9.948707725489521e-05, "loss": 0.6054566383361817, "step": 294510 }, { "epoch": 1.7506880420374367, "grad_norm": 1.6157575845718384, "learning_rate": 9.948089512395258e-05, "loss": 0.5648730278015137, "step": 294520 }, { "epoch": 1.7507474841141049, "grad_norm": 1.58334481716156, "learning_rate": 9.947471304332991e-05, "loss": 0.5085358619689941, "step": 294530 }, { "epoch": 1.7508069261907733, "grad_norm": 1.3957030773162842, "learning_rate": 9.946853101305677e-05, "loss": 0.5203232765197754, "step": 294540 }, { "epoch": 1.7508663682674417, "grad_norm": 1.423962950706482, "learning_rate": 9.946234903316274e-05, "loss": 0.5628225326538085, "step": 294550 }, { "epoch": 1.75092581034411, "grad_norm": 1.525610327720642, "learning_rate": 9.945616710367738e-05, "loss": 0.5985280990600585, "step": 294560 }, { "epoch": 1.7509852524207785, "grad_norm": 1.2504866123199463, "learning_rate": 9.944998522463028e-05, "loss": 0.514872694015503, "step": 294570 }, { "epoch": 1.751044694497447, "grad_norm": 1.32778000831604, "learning_rate": 9.944380339605101e-05, "loss": 0.5458451271057129, "step": 294580 }, { "epoch": 1.7511041365741153, "grad_norm": 1.0992248058319092, "learning_rate": 9.94376216179691e-05, "loss": 0.5902591705322265, "step": 294590 }, { "epoch": 1.7511635786507838, "grad_norm": 1.233918309211731, "learning_rate": 9.943143989041419e-05, "loss": 0.5776960372924804, "step": 294600 }, { "epoch": 1.7512230207274522, "grad_norm": 1.1980621814727783, "learning_rate": 9.942525821341582e-05, "loss": 0.5335407257080078, "step": 294610 }, { "epoch": 1.7512824628041206, "grad_norm": 1.525844931602478, "learning_rate": 9.941907658700358e-05, "loss": 0.6158831119537354, "step": 294620 }, { "epoch": 1.751341904880789, "grad_norm": 1.537821888923645, "learning_rate": 9.941289501120694e-05, "loss": 0.5316615581512452, "step": 294630 }, { "epoch": 1.7514013469574574, "grad_norm": 1.2790007591247559, "learning_rate": 9.940671348605561e-05, "loss": 0.5772452354431152, "step": 294640 }, { "epoch": 1.7514607890341258, "grad_norm": 1.6535922288894653, "learning_rate": 9.940053201157912e-05, "loss": 0.5751793384552002, "step": 294650 }, { "epoch": 1.7515202311107942, "grad_norm": 1.228219985961914, "learning_rate": 9.939435058780694e-05, "loss": 0.5129194259643555, "step": 294660 }, { "epoch": 1.7515796731874624, "grad_norm": 1.274929404258728, "learning_rate": 9.938816921476879e-05, "loss": 0.567569637298584, "step": 294670 }, { "epoch": 1.7516391152641309, "grad_norm": 1.336815357208252, "learning_rate": 9.938198789249417e-05, "loss": 0.6071746826171875, "step": 294680 }, { "epoch": 1.7516985573407993, "grad_norm": 1.2510524988174438, "learning_rate": 9.937580662101261e-05, "loss": 0.5073250293731689, "step": 294690 }, { "epoch": 1.7517579994174677, "grad_norm": 1.761604905128479, "learning_rate": 9.936962540035375e-05, "loss": 0.5621355056762696, "step": 294700 }, { "epoch": 1.7518174414941359, "grad_norm": 1.2261320352554321, "learning_rate": 9.936344423054713e-05, "loss": 0.5505949020385742, "step": 294710 }, { "epoch": 1.7518768835708043, "grad_norm": 2.4390792846679688, "learning_rate": 9.935726311162228e-05, "loss": 0.5260353565216065, "step": 294720 }, { "epoch": 1.7519363256474727, "grad_norm": 1.367885947227478, "learning_rate": 9.935108204360884e-05, "loss": 0.6103251457214356, "step": 294730 }, { "epoch": 1.7519957677241411, "grad_norm": 1.615888237953186, "learning_rate": 9.934490102653636e-05, "loss": 0.5049914360046387, "step": 294740 }, { "epoch": 1.7520552098008095, "grad_norm": 1.4706435203552246, "learning_rate": 9.933872006043436e-05, "loss": 0.5948327064514161, "step": 294750 }, { "epoch": 1.752114651877478, "grad_norm": 1.6380523443222046, "learning_rate": 9.93325391453324e-05, "loss": 0.5559526443481445, "step": 294760 }, { "epoch": 1.7521740939541464, "grad_norm": 1.744848608970642, "learning_rate": 9.932635828126016e-05, "loss": 0.5948720932006836, "step": 294770 }, { "epoch": 1.7522335360308148, "grad_norm": 1.6537209749221802, "learning_rate": 9.932017746824713e-05, "loss": 0.5398324012756348, "step": 294780 }, { "epoch": 1.7522929781074832, "grad_norm": 1.4132053852081299, "learning_rate": 9.931399670632282e-05, "loss": 0.5210366249084473, "step": 294790 }, { "epoch": 1.7523524201841516, "grad_norm": 1.6408030986785889, "learning_rate": 9.93078159955169e-05, "loss": 0.5783047676086426, "step": 294800 }, { "epoch": 1.75241186226082, "grad_norm": 2.004223108291626, "learning_rate": 9.93016353358589e-05, "loss": 0.6493571281433106, "step": 294810 }, { "epoch": 1.7524713043374884, "grad_norm": 1.0646476745605469, "learning_rate": 9.929545472737833e-05, "loss": 0.5433692932128906, "step": 294820 }, { "epoch": 1.7525307464141568, "grad_norm": 1.816754937171936, "learning_rate": 9.928927417010488e-05, "loss": 0.5696693420410156, "step": 294830 }, { "epoch": 1.7525901884908253, "grad_norm": 1.5424110889434814, "learning_rate": 9.9283093664068e-05, "loss": 0.6140948295593261, "step": 294840 }, { "epoch": 1.7526496305674935, "grad_norm": 1.941943645477295, "learning_rate": 9.927691320929733e-05, "loss": 0.5627180099487304, "step": 294850 }, { "epoch": 1.7527090726441619, "grad_norm": 1.487640142440796, "learning_rate": 9.927073280582233e-05, "loss": 0.5759606838226319, "step": 294860 }, { "epoch": 1.7527685147208303, "grad_norm": 1.5523654222488403, "learning_rate": 9.92645524536727e-05, "loss": 0.624736213684082, "step": 294870 }, { "epoch": 1.7528279567974987, "grad_norm": 1.4090807437896729, "learning_rate": 9.925837215287795e-05, "loss": 0.5581969261169434, "step": 294880 }, { "epoch": 1.7528873988741671, "grad_norm": 1.4070942401885986, "learning_rate": 9.92521919034676e-05, "loss": 0.5382256984710694, "step": 294890 }, { "epoch": 1.7529468409508353, "grad_norm": 1.4329478740692139, "learning_rate": 9.924601170547126e-05, "loss": 0.5488012313842774, "step": 294900 }, { "epoch": 1.7530062830275037, "grad_norm": 1.3780171871185303, "learning_rate": 9.923983155891849e-05, "loss": 0.5254167556762696, "step": 294910 }, { "epoch": 1.7530657251041721, "grad_norm": 1.5325604677200317, "learning_rate": 9.923365146383882e-05, "loss": 0.5057905197143555, "step": 294920 }, { "epoch": 1.7531251671808405, "grad_norm": 2.223440408706665, "learning_rate": 9.92274714202619e-05, "loss": 0.6163635730743409, "step": 294930 }, { "epoch": 1.753184609257509, "grad_norm": 1.4950363636016846, "learning_rate": 9.922129142821722e-05, "loss": 0.5725144386291504, "step": 294940 }, { "epoch": 1.7532440513341774, "grad_norm": 1.5062787532806396, "learning_rate": 9.921511148773432e-05, "loss": 0.5040936946868897, "step": 294950 }, { "epoch": 1.7533034934108458, "grad_norm": 1.1134321689605713, "learning_rate": 9.920893159884286e-05, "loss": 0.5858448028564454, "step": 294960 }, { "epoch": 1.7533629354875142, "grad_norm": 1.5882806777954102, "learning_rate": 9.92027517615723e-05, "loss": 0.5589266777038574, "step": 294970 }, { "epoch": 1.7534223775641826, "grad_norm": 1.3998302221298218, "learning_rate": 9.919657197595227e-05, "loss": 0.5635178089141846, "step": 294980 }, { "epoch": 1.753481819640851, "grad_norm": 1.346208095550537, "learning_rate": 9.91903922420123e-05, "loss": 0.5534910202026367, "step": 294990 }, { "epoch": 1.7535412617175195, "grad_norm": 1.5397047996520996, "learning_rate": 9.918421255978197e-05, "loss": 0.5770829200744629, "step": 295000 }, { "epoch": 1.7536007037941879, "grad_norm": 1.3696978092193604, "learning_rate": 9.917803292929082e-05, "loss": 0.5671605110168457, "step": 295010 }, { "epoch": 1.7536601458708563, "grad_norm": 1.537999153137207, "learning_rate": 9.917185335056842e-05, "loss": 0.551644229888916, "step": 295020 }, { "epoch": 1.7537195879475247, "grad_norm": 1.4752943515777588, "learning_rate": 9.916567382364435e-05, "loss": 0.5556320190429688, "step": 295030 }, { "epoch": 1.7537790300241929, "grad_norm": 1.6198670864105225, "learning_rate": 9.915949434854814e-05, "loss": 0.5901123046875, "step": 295040 }, { "epoch": 1.7538384721008613, "grad_norm": 1.3247929811477661, "learning_rate": 9.915331492530937e-05, "loss": 0.5598367691040039, "step": 295050 }, { "epoch": 1.7538979141775297, "grad_norm": 1.2971605062484741, "learning_rate": 9.91471355539576e-05, "loss": 0.5365026950836181, "step": 295060 }, { "epoch": 1.7539573562541981, "grad_norm": 1.3314054012298584, "learning_rate": 9.914095623452242e-05, "loss": 0.5724625587463379, "step": 295070 }, { "epoch": 1.7540167983308663, "grad_norm": 1.583392858505249, "learning_rate": 9.91347769670333e-05, "loss": 0.5732279777526855, "step": 295080 }, { "epoch": 1.7540762404075347, "grad_norm": 1.0415414571762085, "learning_rate": 9.912859775151988e-05, "loss": 0.4716142177581787, "step": 295090 }, { "epoch": 1.7541356824842032, "grad_norm": 1.5575629472732544, "learning_rate": 9.91224185880117e-05, "loss": 0.5308446407318115, "step": 295100 }, { "epoch": 1.7541951245608716, "grad_norm": 1.1101025342941284, "learning_rate": 9.911623947653834e-05, "loss": 0.5855231285095215, "step": 295110 }, { "epoch": 1.75425456663754, "grad_norm": 1.471156120300293, "learning_rate": 9.911006041712927e-05, "loss": 0.6036301612854004, "step": 295120 }, { "epoch": 1.7543140087142084, "grad_norm": 1.4188796281814575, "learning_rate": 9.910388140981414e-05, "loss": 0.5901309490203858, "step": 295130 }, { "epoch": 1.7543734507908768, "grad_norm": 1.463650107383728, "learning_rate": 9.909770245462254e-05, "loss": 0.5814667701721191, "step": 295140 }, { "epoch": 1.7544328928675452, "grad_norm": 1.4718283414840698, "learning_rate": 9.909152355158386e-05, "loss": 0.5971797943115235, "step": 295150 }, { "epoch": 1.7544923349442136, "grad_norm": 1.5677043199539185, "learning_rate": 9.908534470072786e-05, "loss": 0.5174162864685059, "step": 295160 }, { "epoch": 1.754551777020882, "grad_norm": 1.6501829624176025, "learning_rate": 9.907916590208397e-05, "loss": 0.6303062438964844, "step": 295170 }, { "epoch": 1.7546112190975505, "grad_norm": 1.3677667379379272, "learning_rate": 9.907298715568174e-05, "loss": 0.5572257518768311, "step": 295180 }, { "epoch": 1.7546706611742189, "grad_norm": 1.5602701902389526, "learning_rate": 9.906680846155083e-05, "loss": 0.5879326820373535, "step": 295190 }, { "epoch": 1.7547301032508873, "grad_norm": 1.9451042413711548, "learning_rate": 9.906062981972073e-05, "loss": 0.5417462825775147, "step": 295200 }, { "epoch": 1.7547895453275557, "grad_norm": 1.6718356609344482, "learning_rate": 9.905445123022094e-05, "loss": 0.5688544750213623, "step": 295210 }, { "epoch": 1.754848987404224, "grad_norm": 1.4948153495788574, "learning_rate": 9.904827269308115e-05, "loss": 0.6027517795562745, "step": 295220 }, { "epoch": 1.7549084294808923, "grad_norm": 1.2311155796051025, "learning_rate": 9.904209420833084e-05, "loss": 0.5186944007873535, "step": 295230 }, { "epoch": 1.7549678715575607, "grad_norm": 1.4122766256332397, "learning_rate": 9.903591577599954e-05, "loss": 0.5523226737976075, "step": 295240 }, { "epoch": 1.7550273136342291, "grad_norm": 1.482134461402893, "learning_rate": 9.90297373961168e-05, "loss": 0.5292916297912598, "step": 295250 }, { "epoch": 1.7550867557108976, "grad_norm": 1.3280748128890991, "learning_rate": 9.902355906871231e-05, "loss": 0.5761838912963867, "step": 295260 }, { "epoch": 1.7551461977875658, "grad_norm": 1.5289077758789062, "learning_rate": 9.901738079381546e-05, "loss": 0.5733660697937012, "step": 295270 }, { "epoch": 1.7552056398642342, "grad_norm": 1.8945518732070923, "learning_rate": 9.901120257145584e-05, "loss": 0.5602831840515137, "step": 295280 }, { "epoch": 1.7552650819409026, "grad_norm": 1.3475199937820435, "learning_rate": 9.900502440166311e-05, "loss": 0.5460773468017578, "step": 295290 }, { "epoch": 1.755324524017571, "grad_norm": 1.9612985849380493, "learning_rate": 9.899884628446672e-05, "loss": 0.5744839668273926, "step": 295300 }, { "epoch": 1.7553839660942394, "grad_norm": 1.791165828704834, "learning_rate": 9.899266821989621e-05, "loss": 0.5812336921691894, "step": 295310 }, { "epoch": 1.7554434081709078, "grad_norm": 1.3394956588745117, "learning_rate": 9.898649020798125e-05, "loss": 0.5940140724182129, "step": 295320 }, { "epoch": 1.7555028502475762, "grad_norm": 1.4297840595245361, "learning_rate": 9.89803122487513e-05, "loss": 0.5675361156463623, "step": 295330 }, { "epoch": 1.7555622923242447, "grad_norm": 1.4766980409622192, "learning_rate": 9.897413434223592e-05, "loss": 0.5809127807617187, "step": 295340 }, { "epoch": 1.755621734400913, "grad_norm": 1.6958277225494385, "learning_rate": 9.896795648846469e-05, "loss": 0.5390673160552979, "step": 295350 }, { "epoch": 1.7556811764775815, "grad_norm": 1.578879952430725, "learning_rate": 9.896177868746714e-05, "loss": 0.5576495170593262, "step": 295360 }, { "epoch": 1.75574061855425, "grad_norm": 1.3765296936035156, "learning_rate": 9.895560093927285e-05, "loss": 0.5481171607971191, "step": 295370 }, { "epoch": 1.7558000606309183, "grad_norm": 1.4486563205718994, "learning_rate": 9.894942324391132e-05, "loss": 0.5051774978637695, "step": 295380 }, { "epoch": 1.7558595027075867, "grad_norm": 1.6767164468765259, "learning_rate": 9.894324560141218e-05, "loss": 0.5437788963317871, "step": 295390 }, { "epoch": 1.7559189447842551, "grad_norm": 1.0750772953033447, "learning_rate": 9.89370680118049e-05, "loss": 0.5173012733459472, "step": 295400 }, { "epoch": 1.7559783868609233, "grad_norm": 1.0012311935424805, "learning_rate": 9.89308904751191e-05, "loss": 0.5588619232177734, "step": 295410 }, { "epoch": 1.7560378289375917, "grad_norm": 1.5674694776535034, "learning_rate": 9.89247129913843e-05, "loss": 0.5079977989196778, "step": 295420 }, { "epoch": 1.7560972710142602, "grad_norm": 1.7738449573516846, "learning_rate": 9.891853556063004e-05, "loss": 0.5814313888549805, "step": 295430 }, { "epoch": 1.7561567130909286, "grad_norm": 1.2069714069366455, "learning_rate": 9.891235818288589e-05, "loss": 0.5101962566375733, "step": 295440 }, { "epoch": 1.7562161551675968, "grad_norm": 1.2228807210922241, "learning_rate": 9.89061808581814e-05, "loss": 0.592162799835205, "step": 295450 }, { "epoch": 1.7562755972442652, "grad_norm": 1.4831477403640747, "learning_rate": 9.890000358654612e-05, "loss": 0.5286464691162109, "step": 295460 }, { "epoch": 1.7563350393209336, "grad_norm": 1.6912834644317627, "learning_rate": 9.889382636800959e-05, "loss": 0.5527315616607666, "step": 295470 }, { "epoch": 1.756394481397602, "grad_norm": 1.6856868267059326, "learning_rate": 9.888764920260136e-05, "loss": 0.600269079208374, "step": 295480 }, { "epoch": 1.7564539234742704, "grad_norm": 1.3663058280944824, "learning_rate": 9.888147209035099e-05, "loss": 0.5503660202026367, "step": 295490 }, { "epoch": 1.7565133655509388, "grad_norm": 1.1869736909866333, "learning_rate": 9.887529503128803e-05, "loss": 0.5232072830200195, "step": 295500 }, { "epoch": 1.7565728076276073, "grad_norm": 1.2508636713027954, "learning_rate": 9.886911802544199e-05, "loss": 0.583481740951538, "step": 295510 }, { "epoch": 1.7566322497042757, "grad_norm": 1.2399868965148926, "learning_rate": 9.886294107284249e-05, "loss": 0.5142937660217285, "step": 295520 }, { "epoch": 1.756691691780944, "grad_norm": 1.4569815397262573, "learning_rate": 9.885676417351904e-05, "loss": 0.5979964256286621, "step": 295530 }, { "epoch": 1.7567511338576125, "grad_norm": 1.5081177949905396, "learning_rate": 9.885058732750116e-05, "loss": 0.5191595554351807, "step": 295540 }, { "epoch": 1.756810575934281, "grad_norm": 1.2962454557418823, "learning_rate": 9.884441053481845e-05, "loss": 0.5516495704650879, "step": 295550 }, { "epoch": 1.7568700180109493, "grad_norm": 1.1132243871688843, "learning_rate": 9.883823379550043e-05, "loss": 0.542498779296875, "step": 295560 }, { "epoch": 1.7569294600876177, "grad_norm": 1.2711580991744995, "learning_rate": 9.883205710957664e-05, "loss": 0.5577131271362304, "step": 295570 }, { "epoch": 1.7569889021642862, "grad_norm": 1.2857578992843628, "learning_rate": 9.882588047707664e-05, "loss": 0.5455249786376953, "step": 295580 }, { "epoch": 1.7570483442409544, "grad_norm": 1.3408530950546265, "learning_rate": 9.881970389803e-05, "loss": 0.5498846054077149, "step": 295590 }, { "epoch": 1.7571077863176228, "grad_norm": 1.795919418334961, "learning_rate": 9.881352737246623e-05, "loss": 0.47022285461425783, "step": 295600 }, { "epoch": 1.7571672283942912, "grad_norm": 1.7480214834213257, "learning_rate": 9.880735090041486e-05, "loss": 0.5822793960571289, "step": 295610 }, { "epoch": 1.7572266704709596, "grad_norm": 1.3674542903900146, "learning_rate": 9.880117448190552e-05, "loss": 0.5536509037017823, "step": 295620 }, { "epoch": 1.757286112547628, "grad_norm": 1.6397908926010132, "learning_rate": 9.879499811696766e-05, "loss": 0.547752571105957, "step": 295630 }, { "epoch": 1.7573455546242962, "grad_norm": 1.4677972793579102, "learning_rate": 9.878882180563087e-05, "loss": 0.5537839412689209, "step": 295640 }, { "epoch": 1.7574049967009646, "grad_norm": 1.2042646408081055, "learning_rate": 9.878264554792472e-05, "loss": 0.5412262916564942, "step": 295650 }, { "epoch": 1.757464438777633, "grad_norm": 1.2058089971542358, "learning_rate": 9.877646934387872e-05, "loss": 0.4871506214141846, "step": 295660 }, { "epoch": 1.7575238808543014, "grad_norm": 1.1573582887649536, "learning_rate": 9.877029319352238e-05, "loss": 0.5481998443603515, "step": 295670 }, { "epoch": 1.7575833229309699, "grad_norm": 1.4072221517562866, "learning_rate": 9.876411709688533e-05, "loss": 0.5964279174804688, "step": 295680 }, { "epoch": 1.7576427650076383, "grad_norm": 1.4140843152999878, "learning_rate": 9.875794105399707e-05, "loss": 0.5652532577514648, "step": 295690 }, { "epoch": 1.7577022070843067, "grad_norm": 1.4012006521224976, "learning_rate": 9.875176506488717e-05, "loss": 0.5502376556396484, "step": 295700 }, { "epoch": 1.757761649160975, "grad_norm": 1.354750394821167, "learning_rate": 9.874558912958507e-05, "loss": 0.5778446197509766, "step": 295710 }, { "epoch": 1.7578210912376435, "grad_norm": 1.2957267761230469, "learning_rate": 9.873941324812046e-05, "loss": 0.5111492156982422, "step": 295720 }, { "epoch": 1.757880533314312, "grad_norm": 1.4217870235443115, "learning_rate": 9.873323742052282e-05, "loss": 0.5615572929382324, "step": 295730 }, { "epoch": 1.7579399753909803, "grad_norm": 1.5030540227890015, "learning_rate": 9.872706164682165e-05, "loss": 0.5996296405792236, "step": 295740 }, { "epoch": 1.7579994174676488, "grad_norm": 1.3653841018676758, "learning_rate": 9.872088592704656e-05, "loss": 0.5028916835784912, "step": 295750 }, { "epoch": 1.7580588595443172, "grad_norm": 1.292159914970398, "learning_rate": 9.871471026122707e-05, "loss": 0.5290745735168457, "step": 295760 }, { "epoch": 1.7581183016209856, "grad_norm": 1.2074120044708252, "learning_rate": 9.870853464939267e-05, "loss": 0.5267580509185791, "step": 295770 }, { "epoch": 1.7581777436976538, "grad_norm": 1.6718206405639648, "learning_rate": 9.870235909157301e-05, "loss": 0.5339145660400391, "step": 295780 }, { "epoch": 1.7582371857743222, "grad_norm": 1.8963035345077515, "learning_rate": 9.869618358779756e-05, "loss": 0.6071175098419189, "step": 295790 }, { "epoch": 1.7582966278509906, "grad_norm": 0.9793080687522888, "learning_rate": 9.869000813809581e-05, "loss": 0.5332427024841309, "step": 295800 }, { "epoch": 1.758356069927659, "grad_norm": 1.1810786724090576, "learning_rate": 9.868383274249747e-05, "loss": 0.5526795864105225, "step": 295810 }, { "epoch": 1.7584155120043272, "grad_norm": 1.6411477327346802, "learning_rate": 9.867765740103192e-05, "loss": 0.5800842761993408, "step": 295820 }, { "epoch": 1.7584749540809956, "grad_norm": 1.4803024530410767, "learning_rate": 9.867148211372876e-05, "loss": 0.6128569126129151, "step": 295830 }, { "epoch": 1.758534396157664, "grad_norm": 1.3128058910369873, "learning_rate": 9.866530688061751e-05, "loss": 0.5434948921203613, "step": 295840 }, { "epoch": 1.7585938382343325, "grad_norm": 1.6174659729003906, "learning_rate": 9.865913170172776e-05, "loss": 0.6180570602416993, "step": 295850 }, { "epoch": 1.7586532803110009, "grad_norm": 1.2580230236053467, "learning_rate": 9.8652956577089e-05, "loss": 0.5191996574401856, "step": 295860 }, { "epoch": 1.7587127223876693, "grad_norm": 1.5185209512710571, "learning_rate": 9.864678150673077e-05, "loss": 0.5569961547851563, "step": 295870 }, { "epoch": 1.7587721644643377, "grad_norm": 1.4374257326126099, "learning_rate": 9.864060649068266e-05, "loss": 0.5147315502166748, "step": 295880 }, { "epoch": 1.7588316065410061, "grad_norm": 1.476833701133728, "learning_rate": 9.863443152897415e-05, "loss": 0.5029424667358399, "step": 295890 }, { "epoch": 1.7588910486176745, "grad_norm": 1.4680157899856567, "learning_rate": 9.862825662163482e-05, "loss": 0.5231683731079102, "step": 295900 }, { "epoch": 1.758950490694343, "grad_norm": 1.6882244348526, "learning_rate": 9.862208176869421e-05, "loss": 0.5935364723205566, "step": 295910 }, { "epoch": 1.7590099327710114, "grad_norm": 1.523358702659607, "learning_rate": 9.861590697018181e-05, "loss": 0.5673500061035156, "step": 295920 }, { "epoch": 1.7590693748476798, "grad_norm": 1.4463592767715454, "learning_rate": 9.860973222612719e-05, "loss": 0.569088363647461, "step": 295930 }, { "epoch": 1.7591288169243482, "grad_norm": 1.5906707048416138, "learning_rate": 9.860355753655992e-05, "loss": 0.544735050201416, "step": 295940 }, { "epoch": 1.7591882590010166, "grad_norm": 1.5577356815338135, "learning_rate": 9.859738290150948e-05, "loss": 0.5324628829956055, "step": 295950 }, { "epoch": 1.7592477010776848, "grad_norm": 1.5155149698257446, "learning_rate": 9.859120832100548e-05, "loss": 0.5695663452148437, "step": 295960 }, { "epoch": 1.7593071431543532, "grad_norm": 1.2026691436767578, "learning_rate": 9.858503379507735e-05, "loss": 0.568285322189331, "step": 295970 }, { "epoch": 1.7593665852310216, "grad_norm": 1.5633199214935303, "learning_rate": 9.857885932375472e-05, "loss": 0.5494132995605469, "step": 295980 }, { "epoch": 1.75942602730769, "grad_norm": 1.5076937675476074, "learning_rate": 9.857268490706709e-05, "loss": 0.5685671329498291, "step": 295990 }, { "epoch": 1.7594854693843585, "grad_norm": 1.3504877090454102, "learning_rate": 9.856651054504398e-05, "loss": 0.579547643661499, "step": 296000 }, { "epoch": 1.7595449114610267, "grad_norm": 1.2800918817520142, "learning_rate": 9.856033623771496e-05, "loss": 0.5555778026580811, "step": 296010 }, { "epoch": 1.759604353537695, "grad_norm": 1.2517834901809692, "learning_rate": 9.855416198510959e-05, "loss": 0.5152627944946289, "step": 296020 }, { "epoch": 1.7596637956143635, "grad_norm": 1.5365593433380127, "learning_rate": 9.854798778725731e-05, "loss": 0.5592305183410644, "step": 296030 }, { "epoch": 1.759723237691032, "grad_norm": 1.4860278367996216, "learning_rate": 9.854181364418775e-05, "loss": 0.5403383255004883, "step": 296040 }, { "epoch": 1.7597826797677003, "grad_norm": 1.4519752264022827, "learning_rate": 9.85356395559304e-05, "loss": 0.5528836727142334, "step": 296050 }, { "epoch": 1.7598421218443687, "grad_norm": 1.4824597835540771, "learning_rate": 9.852946552251479e-05, "loss": 0.516194200515747, "step": 296060 }, { "epoch": 1.7599015639210371, "grad_norm": 1.647609829902649, "learning_rate": 9.852329154397049e-05, "loss": 0.6093590259552002, "step": 296070 }, { "epoch": 1.7599610059977056, "grad_norm": 1.3335953950881958, "learning_rate": 9.8517117620327e-05, "loss": 0.5283515930175782, "step": 296080 }, { "epoch": 1.760020448074374, "grad_norm": 1.569231390953064, "learning_rate": 9.851094375161389e-05, "loss": 0.5345707893371582, "step": 296090 }, { "epoch": 1.7600798901510424, "grad_norm": 1.578626036643982, "learning_rate": 9.850476993786064e-05, "loss": 0.574891185760498, "step": 296100 }, { "epoch": 1.7601393322277108, "grad_norm": 1.7028682231903076, "learning_rate": 9.849859617909683e-05, "loss": 0.5863924503326416, "step": 296110 }, { "epoch": 1.7601987743043792, "grad_norm": 1.616697907447815, "learning_rate": 9.849242247535198e-05, "loss": 0.5613067626953125, "step": 296120 }, { "epoch": 1.7602582163810476, "grad_norm": 1.6847028732299805, "learning_rate": 9.84862488266556e-05, "loss": 0.6432328224182129, "step": 296130 }, { "epoch": 1.760317658457716, "grad_norm": 1.2251492738723755, "learning_rate": 9.848007523303727e-05, "loss": 0.5283212184906005, "step": 296140 }, { "epoch": 1.7603771005343842, "grad_norm": 1.3967820405960083, "learning_rate": 9.847390169452648e-05, "loss": 0.5400909900665283, "step": 296150 }, { "epoch": 1.7604365426110526, "grad_norm": 1.4855490922927856, "learning_rate": 9.846772821115276e-05, "loss": 0.5756741046905518, "step": 296160 }, { "epoch": 1.760495984687721, "grad_norm": 1.3941504955291748, "learning_rate": 9.846155478294568e-05, "loss": 0.5957442283630371, "step": 296170 }, { "epoch": 1.7605554267643895, "grad_norm": 1.7033542394638062, "learning_rate": 9.845538140993475e-05, "loss": 0.536639404296875, "step": 296180 }, { "epoch": 1.7606148688410577, "grad_norm": 1.421489953994751, "learning_rate": 9.844920809214953e-05, "loss": 0.5701620578765869, "step": 296190 }, { "epoch": 1.760674310917726, "grad_norm": 1.0005427598953247, "learning_rate": 9.844303482961947e-05, "loss": 0.5526872634887695, "step": 296200 }, { "epoch": 1.7607337529943945, "grad_norm": 1.1307188272476196, "learning_rate": 9.843686162237417e-05, "loss": 0.5563636302947998, "step": 296210 }, { "epoch": 1.760793195071063, "grad_norm": 1.4984638690948486, "learning_rate": 9.843068847044319e-05, "loss": 0.5794722557067871, "step": 296220 }, { "epoch": 1.7608526371477313, "grad_norm": 1.4717495441436768, "learning_rate": 9.842451537385596e-05, "loss": 0.5503878593444824, "step": 296230 }, { "epoch": 1.7609120792243997, "grad_norm": 1.3659292459487915, "learning_rate": 9.841834233264207e-05, "loss": 0.6140771389007569, "step": 296240 }, { "epoch": 1.7609715213010682, "grad_norm": 1.36528742313385, "learning_rate": 9.841216934683108e-05, "loss": 0.5614676952362061, "step": 296250 }, { "epoch": 1.7610309633777366, "grad_norm": 1.2704498767852783, "learning_rate": 9.840599641645244e-05, "loss": 0.5492379188537597, "step": 296260 }, { "epoch": 1.761090405454405, "grad_norm": 1.4635740518569946, "learning_rate": 9.839982354153577e-05, "loss": 0.5905123710632324, "step": 296270 }, { "epoch": 1.7611498475310734, "grad_norm": 1.4746493101119995, "learning_rate": 9.839365072211056e-05, "loss": 0.5389194011688232, "step": 296280 }, { "epoch": 1.7612092896077418, "grad_norm": 1.5617811679840088, "learning_rate": 9.838747795820626e-05, "loss": 0.5787792205810547, "step": 296290 }, { "epoch": 1.7612687316844102, "grad_norm": 1.7727221250534058, "learning_rate": 9.838130524985251e-05, "loss": 0.5802449226379395, "step": 296300 }, { "epoch": 1.7613281737610786, "grad_norm": 1.726257562637329, "learning_rate": 9.837513259707884e-05, "loss": 0.5507853507995606, "step": 296310 }, { "epoch": 1.761387615837747, "grad_norm": 1.4217748641967773, "learning_rate": 9.836895999991472e-05, "loss": 0.5455827713012695, "step": 296320 }, { "epoch": 1.7614470579144152, "grad_norm": 1.4279042482376099, "learning_rate": 9.836278745838962e-05, "loss": 0.577863359451294, "step": 296330 }, { "epoch": 1.7615064999910837, "grad_norm": 1.356942892074585, "learning_rate": 9.835661497253323e-05, "loss": 0.560242748260498, "step": 296340 }, { "epoch": 1.761565942067752, "grad_norm": 1.3375169038772583, "learning_rate": 9.835044254237497e-05, "loss": 0.5120361328125, "step": 296350 }, { "epoch": 1.7616253841444205, "grad_norm": 1.1827062368392944, "learning_rate": 9.834427016794434e-05, "loss": 0.5282145023345948, "step": 296360 }, { "epoch": 1.761684826221089, "grad_norm": 1.1348929405212402, "learning_rate": 9.833809784927097e-05, "loss": 0.5150418758392334, "step": 296370 }, { "epoch": 1.761744268297757, "grad_norm": 1.1246298551559448, "learning_rate": 9.833192558638429e-05, "loss": 0.5523560523986817, "step": 296380 }, { "epoch": 1.7618037103744255, "grad_norm": 1.6254256963729858, "learning_rate": 9.832575337931387e-05, "loss": 0.548743724822998, "step": 296390 }, { "epoch": 1.761863152451094, "grad_norm": 1.3502671718597412, "learning_rate": 9.831958122808924e-05, "loss": 0.5681589603424072, "step": 296400 }, { "epoch": 1.7619225945277623, "grad_norm": 1.218932867050171, "learning_rate": 9.831340913273991e-05, "loss": 0.5258048057556153, "step": 296410 }, { "epoch": 1.7619820366044308, "grad_norm": 1.4406466484069824, "learning_rate": 9.830723709329541e-05, "loss": 0.5662343502044678, "step": 296420 }, { "epoch": 1.7620414786810992, "grad_norm": 1.6497793197631836, "learning_rate": 9.83010651097853e-05, "loss": 0.5448211193084717, "step": 296430 }, { "epoch": 1.7621009207577676, "grad_norm": 1.3015693426132202, "learning_rate": 9.829489318223903e-05, "loss": 0.49503650665283205, "step": 296440 }, { "epoch": 1.762160362834436, "grad_norm": 1.1319456100463867, "learning_rate": 9.828872131068621e-05, "loss": 0.5576067447662354, "step": 296450 }, { "epoch": 1.7622198049111044, "grad_norm": 1.148977279663086, "learning_rate": 9.828254949515625e-05, "loss": 0.5332945346832275, "step": 296460 }, { "epoch": 1.7622792469877728, "grad_norm": 1.494189977645874, "learning_rate": 9.827637773567879e-05, "loss": 0.5686298847198487, "step": 296470 }, { "epoch": 1.7623386890644412, "grad_norm": 1.5789448022842407, "learning_rate": 9.827020603228332e-05, "loss": 0.5236130237579346, "step": 296480 }, { "epoch": 1.7623981311411097, "grad_norm": 1.3297781944274902, "learning_rate": 9.826403438499932e-05, "loss": 0.5788781642913818, "step": 296490 }, { "epoch": 1.762457573217778, "grad_norm": 1.7119425535202026, "learning_rate": 9.825786279385636e-05, "loss": 0.5781184196472168, "step": 296500 }, { "epoch": 1.7625170152944465, "grad_norm": 1.4747110605239868, "learning_rate": 9.825169125888396e-05, "loss": 0.5756052017211915, "step": 296510 }, { "epoch": 1.7625764573711147, "grad_norm": 1.7310794591903687, "learning_rate": 9.824551978011159e-05, "loss": 0.5616363525390625, "step": 296520 }, { "epoch": 1.762635899447783, "grad_norm": 1.314477801322937, "learning_rate": 9.823934835756883e-05, "loss": 0.5649584770202637, "step": 296530 }, { "epoch": 1.7626953415244515, "grad_norm": 1.4073208570480347, "learning_rate": 9.82331769912852e-05, "loss": 0.5197075843811035, "step": 296540 }, { "epoch": 1.76275478360112, "grad_norm": 1.3906834125518799, "learning_rate": 9.822700568129018e-05, "loss": 0.565671157836914, "step": 296550 }, { "epoch": 1.7628142256777881, "grad_norm": 1.3668365478515625, "learning_rate": 9.822083442761334e-05, "loss": 0.5563724040985107, "step": 296560 }, { "epoch": 1.7628736677544565, "grad_norm": 1.5271462202072144, "learning_rate": 9.821466323028416e-05, "loss": 0.5633894443511963, "step": 296570 }, { "epoch": 1.762933109831125, "grad_norm": 1.397940993309021, "learning_rate": 9.820849208933223e-05, "loss": 0.5413137435913086, "step": 296580 }, { "epoch": 1.7629925519077934, "grad_norm": 1.4171295166015625, "learning_rate": 9.820232100478694e-05, "loss": 0.5178824901580811, "step": 296590 }, { "epoch": 1.7630519939844618, "grad_norm": 1.521142840385437, "learning_rate": 9.819614997667795e-05, "loss": 0.5899293422698975, "step": 296600 }, { "epoch": 1.7631114360611302, "grad_norm": 1.4937108755111694, "learning_rate": 9.81899790050347e-05, "loss": 0.6051107406616211, "step": 296610 }, { "epoch": 1.7631708781377986, "grad_norm": 1.402235984802246, "learning_rate": 9.818380808988672e-05, "loss": 0.5609403610229492, "step": 296620 }, { "epoch": 1.763230320214467, "grad_norm": 1.361687421798706, "learning_rate": 9.817763723126357e-05, "loss": 0.5628256320953369, "step": 296630 }, { "epoch": 1.7632897622911354, "grad_norm": 1.5711442232131958, "learning_rate": 9.817146642919473e-05, "loss": 0.5937470912933349, "step": 296640 }, { "epoch": 1.7633492043678038, "grad_norm": 1.409393310546875, "learning_rate": 9.816529568370969e-05, "loss": 0.5836322784423829, "step": 296650 }, { "epoch": 1.7634086464444723, "grad_norm": 1.911194920539856, "learning_rate": 9.815912499483805e-05, "loss": 0.5638850212097168, "step": 296660 }, { "epoch": 1.7634680885211407, "grad_norm": 1.5745184421539307, "learning_rate": 9.815295436260929e-05, "loss": 0.6226457595825196, "step": 296670 }, { "epoch": 1.763527530597809, "grad_norm": 1.139006495475769, "learning_rate": 9.814678378705293e-05, "loss": 0.5556427001953125, "step": 296680 }, { "epoch": 1.7635869726744775, "grad_norm": 1.666338562965393, "learning_rate": 9.814061326819844e-05, "loss": 0.5320823669433594, "step": 296690 }, { "epoch": 1.7636464147511457, "grad_norm": 1.362862229347229, "learning_rate": 9.81344428060754e-05, "loss": 0.5514431476593018, "step": 296700 }, { "epoch": 1.7637058568278141, "grad_norm": 1.608630657196045, "learning_rate": 9.812827240071333e-05, "loss": 0.5922981262207031, "step": 296710 }, { "epoch": 1.7637652989044825, "grad_norm": 1.4586524963378906, "learning_rate": 9.81221020521417e-05, "loss": 0.5556710243225098, "step": 296720 }, { "epoch": 1.763824740981151, "grad_norm": 1.8434832096099854, "learning_rate": 9.811593176039004e-05, "loss": 0.5364940643310547, "step": 296730 }, { "epoch": 1.7638841830578194, "grad_norm": 1.4145900011062622, "learning_rate": 9.810976152548794e-05, "loss": 0.5984089851379395, "step": 296740 }, { "epoch": 1.7639436251344875, "grad_norm": 1.3073220252990723, "learning_rate": 9.810359134746479e-05, "loss": 0.5239452362060547, "step": 296750 }, { "epoch": 1.764003067211156, "grad_norm": 1.1738560199737549, "learning_rate": 9.809742122635019e-05, "loss": 0.5498937606811524, "step": 296760 }, { "epoch": 1.7640625092878244, "grad_norm": 1.2569056749343872, "learning_rate": 9.809125116217365e-05, "loss": 0.5115838050842285, "step": 296770 }, { "epoch": 1.7641219513644928, "grad_norm": 1.7450788021087646, "learning_rate": 9.808508115496465e-05, "loss": 0.5636902809143066, "step": 296780 }, { "epoch": 1.7641813934411612, "grad_norm": 1.2353814840316772, "learning_rate": 9.807891120475274e-05, "loss": 0.5631879806518555, "step": 296790 }, { "epoch": 1.7642408355178296, "grad_norm": 1.4573781490325928, "learning_rate": 9.807274131156745e-05, "loss": 0.5759002685546875, "step": 296800 }, { "epoch": 1.764300277594498, "grad_norm": 1.3611862659454346, "learning_rate": 9.806657147543825e-05, "loss": 0.5704770565032959, "step": 296810 }, { "epoch": 1.7643597196711664, "grad_norm": 1.5857608318328857, "learning_rate": 9.806040169639463e-05, "loss": 0.5599052906036377, "step": 296820 }, { "epoch": 1.7644191617478349, "grad_norm": 1.4046556949615479, "learning_rate": 9.805423197446621e-05, "loss": 0.5180807113647461, "step": 296830 }, { "epoch": 1.7644786038245033, "grad_norm": 1.277309536933899, "learning_rate": 9.804806230968242e-05, "loss": 0.5395693302154541, "step": 296840 }, { "epoch": 1.7645380459011717, "grad_norm": 1.556117057800293, "learning_rate": 9.804189270207275e-05, "loss": 0.5853158473968506, "step": 296850 }, { "epoch": 1.76459748797784, "grad_norm": 1.4022040367126465, "learning_rate": 9.803572315166682e-05, "loss": 0.5677079200744629, "step": 296860 }, { "epoch": 1.7646569300545085, "grad_norm": 1.0774457454681396, "learning_rate": 9.802955365849407e-05, "loss": 0.5016337394714355, "step": 296870 }, { "epoch": 1.764716372131177, "grad_norm": 1.2693233489990234, "learning_rate": 9.802338422258397e-05, "loss": 0.5412539958953857, "step": 296880 }, { "epoch": 1.7647758142078451, "grad_norm": 1.3717907667160034, "learning_rate": 9.801721484396614e-05, "loss": 0.5667637825012207, "step": 296890 }, { "epoch": 1.7648352562845135, "grad_norm": 1.4178636074066162, "learning_rate": 9.801104552267002e-05, "loss": 0.5651496887207031, "step": 296900 }, { "epoch": 1.764894698361182, "grad_norm": 1.2548339366912842, "learning_rate": 9.800487625872512e-05, "loss": 0.5804997444152832, "step": 296910 }, { "epoch": 1.7649541404378504, "grad_norm": 1.2653728723526, "learning_rate": 9.799870705216101e-05, "loss": 0.5334890365600586, "step": 296920 }, { "epoch": 1.7650135825145186, "grad_norm": 1.2838754653930664, "learning_rate": 9.799253790300715e-05, "loss": 0.5306670665740967, "step": 296930 }, { "epoch": 1.765073024591187, "grad_norm": 1.5662226676940918, "learning_rate": 9.798636881129309e-05, "loss": 0.4964131832122803, "step": 296940 }, { "epoch": 1.7651324666678554, "grad_norm": 1.5573666095733643, "learning_rate": 9.798019977704824e-05, "loss": 0.605644702911377, "step": 296950 }, { "epoch": 1.7651919087445238, "grad_norm": 1.5236142873764038, "learning_rate": 9.797403080030226e-05, "loss": 0.5270344734191894, "step": 296960 }, { "epoch": 1.7652513508211922, "grad_norm": 1.3256193399429321, "learning_rate": 9.796786188108456e-05, "loss": 0.5344250679016114, "step": 296970 }, { "epoch": 1.7653107928978606, "grad_norm": 1.428344488143921, "learning_rate": 9.796169301942466e-05, "loss": 0.5673840522766114, "step": 296980 }, { "epoch": 1.765370234974529, "grad_norm": 1.3815994262695312, "learning_rate": 9.79555242153521e-05, "loss": 0.5377707481384277, "step": 296990 }, { "epoch": 1.7654296770511975, "grad_norm": 1.9400205612182617, "learning_rate": 9.794935546889639e-05, "loss": 0.5590104579925537, "step": 297000 }, { "epoch": 1.7654891191278659, "grad_norm": 1.3780221939086914, "learning_rate": 9.794318678008701e-05, "loss": 0.6248310565948486, "step": 297010 }, { "epoch": 1.7655485612045343, "grad_norm": 1.6459059715270996, "learning_rate": 9.793701814895348e-05, "loss": 0.5017021179199219, "step": 297020 }, { "epoch": 1.7656080032812027, "grad_norm": 0.9246625900268555, "learning_rate": 9.793084957552535e-05, "loss": 0.55067138671875, "step": 297030 }, { "epoch": 1.7656674453578711, "grad_norm": 1.384000539779663, "learning_rate": 9.792468105983206e-05, "loss": 0.5400428295135498, "step": 297040 }, { "epoch": 1.7657268874345395, "grad_norm": 1.453113079071045, "learning_rate": 9.791851260190312e-05, "loss": 0.5868800163269043, "step": 297050 }, { "epoch": 1.765786329511208, "grad_norm": 1.596763253211975, "learning_rate": 9.791234420176811e-05, "loss": 0.5134799003601074, "step": 297060 }, { "epoch": 1.7658457715878761, "grad_norm": 1.475618600845337, "learning_rate": 9.79061758594565e-05, "loss": 0.5084244728088378, "step": 297070 }, { "epoch": 1.7659052136645446, "grad_norm": 1.6911921501159668, "learning_rate": 9.790000757499775e-05, "loss": 0.5679238319396973, "step": 297080 }, { "epoch": 1.765964655741213, "grad_norm": 1.4823298454284668, "learning_rate": 9.789383934842145e-05, "loss": 0.545291805267334, "step": 297090 }, { "epoch": 1.7660240978178814, "grad_norm": 1.1928119659423828, "learning_rate": 9.788767117975706e-05, "loss": 0.5332681655883789, "step": 297100 }, { "epoch": 1.7660835398945498, "grad_norm": 1.2734893560409546, "learning_rate": 9.788150306903406e-05, "loss": 0.5487534523010253, "step": 297110 }, { "epoch": 1.766142981971218, "grad_norm": 1.2625336647033691, "learning_rate": 9.787533501628203e-05, "loss": 0.5234129905700684, "step": 297120 }, { "epoch": 1.7662024240478864, "grad_norm": 1.4539988040924072, "learning_rate": 9.786916702153042e-05, "loss": 0.5487894058227539, "step": 297130 }, { "epoch": 1.7662618661245548, "grad_norm": 1.2212566137313843, "learning_rate": 9.786299908480873e-05, "loss": 0.5063223838806152, "step": 297140 }, { "epoch": 1.7663213082012232, "grad_norm": 1.316544532775879, "learning_rate": 9.785683120614652e-05, "loss": 0.5359338283538818, "step": 297150 }, { "epoch": 1.7663807502778917, "grad_norm": 1.3602335453033447, "learning_rate": 9.785066338557325e-05, "loss": 0.5748286247253418, "step": 297160 }, { "epoch": 1.76644019235456, "grad_norm": 1.219343662261963, "learning_rate": 9.784449562311845e-05, "loss": 0.567991065979004, "step": 297170 }, { "epoch": 1.7664996344312285, "grad_norm": 1.190362811088562, "learning_rate": 9.783832791881155e-05, "loss": 0.5185327053070068, "step": 297180 }, { "epoch": 1.766559076507897, "grad_norm": 1.8240268230438232, "learning_rate": 9.783216027268218e-05, "loss": 0.5374407768249512, "step": 297190 }, { "epoch": 1.7666185185845653, "grad_norm": 1.0578778982162476, "learning_rate": 9.782599268475978e-05, "loss": 0.5743492126464844, "step": 297200 }, { "epoch": 1.7666779606612337, "grad_norm": 1.1751362085342407, "learning_rate": 9.781982515507379e-05, "loss": 0.6006763935089111, "step": 297210 }, { "epoch": 1.7667374027379021, "grad_norm": 1.2527217864990234, "learning_rate": 9.781365768365383e-05, "loss": 0.5979548454284668, "step": 297220 }, { "epoch": 1.7667968448145706, "grad_norm": 1.115471363067627, "learning_rate": 9.780749027052935e-05, "loss": 0.5058845520019531, "step": 297230 }, { "epoch": 1.766856286891239, "grad_norm": 1.6464380025863647, "learning_rate": 9.780132291572981e-05, "loss": 0.5752593040466308, "step": 297240 }, { "epoch": 1.7669157289679074, "grad_norm": 1.5992883443832397, "learning_rate": 9.779515561928479e-05, "loss": 0.5443444728851319, "step": 297250 }, { "epoch": 1.7669751710445756, "grad_norm": 1.3464239835739136, "learning_rate": 9.778898838122377e-05, "loss": 0.5296589851379394, "step": 297260 }, { "epoch": 1.767034613121244, "grad_norm": 1.4377644062042236, "learning_rate": 9.778282120157617e-05, "loss": 0.5284635543823242, "step": 297270 }, { "epoch": 1.7670940551979124, "grad_norm": 1.2035008668899536, "learning_rate": 9.777665408037162e-05, "loss": 0.5735588550567627, "step": 297280 }, { "epoch": 1.7671534972745808, "grad_norm": 1.5923935174942017, "learning_rate": 9.777048701763958e-05, "loss": 0.5339018821716308, "step": 297290 }, { "epoch": 1.767212939351249, "grad_norm": 1.170738935470581, "learning_rate": 9.77643200134095e-05, "loss": 0.5636921882629394, "step": 297300 }, { "epoch": 1.7672723814279174, "grad_norm": 1.3016339540481567, "learning_rate": 9.77581530677109e-05, "loss": 0.5466476440429687, "step": 297310 }, { "epoch": 1.7673318235045858, "grad_norm": 1.3350874185562134, "learning_rate": 9.775198618057333e-05, "loss": 0.5614465713500977, "step": 297320 }, { "epoch": 1.7673912655812543, "grad_norm": 1.254346251487732, "learning_rate": 9.774581935202623e-05, "loss": 0.5743708610534668, "step": 297330 }, { "epoch": 1.7674507076579227, "grad_norm": 1.3378950357437134, "learning_rate": 9.773965258209911e-05, "loss": 0.5596551895141602, "step": 297340 }, { "epoch": 1.767510149734591, "grad_norm": 1.1232386827468872, "learning_rate": 9.773348587082154e-05, "loss": 0.5195762157440186, "step": 297350 }, { "epoch": 1.7675695918112595, "grad_norm": 1.6465672254562378, "learning_rate": 9.772731921822294e-05, "loss": 0.5706242084503174, "step": 297360 }, { "epoch": 1.767629033887928, "grad_norm": 1.1166267395019531, "learning_rate": 9.772115262433279e-05, "loss": 0.5729501247406006, "step": 297370 }, { "epoch": 1.7676884759645963, "grad_norm": 1.3359160423278809, "learning_rate": 9.771498608918068e-05, "loss": 0.5602502822875977, "step": 297380 }, { "epoch": 1.7677479180412647, "grad_norm": 1.2358794212341309, "learning_rate": 9.770881961279608e-05, "loss": 0.5617437839508057, "step": 297390 }, { "epoch": 1.7678073601179332, "grad_norm": 1.371826410293579, "learning_rate": 9.770265319520839e-05, "loss": 0.5198543548583985, "step": 297400 }, { "epoch": 1.7678668021946016, "grad_norm": 1.6915740966796875, "learning_rate": 9.769648683644728e-05, "loss": 0.5386203765869141, "step": 297410 }, { "epoch": 1.76792624427127, "grad_norm": 1.2780479192733765, "learning_rate": 9.769032053654213e-05, "loss": 0.5588725090026856, "step": 297420 }, { "epoch": 1.7679856863479384, "grad_norm": 1.5237069129943848, "learning_rate": 9.768415429552244e-05, "loss": 0.5355065345764161, "step": 297430 }, { "epoch": 1.7680451284246066, "grad_norm": 1.4303027391433716, "learning_rate": 9.767798811341773e-05, "loss": 0.5309170722961426, "step": 297440 }, { "epoch": 1.768104570501275, "grad_norm": 1.2288089990615845, "learning_rate": 9.767182199025751e-05, "loss": 0.5473164558410645, "step": 297450 }, { "epoch": 1.7681640125779434, "grad_norm": 1.5935757160186768, "learning_rate": 9.766565592607126e-05, "loss": 0.4956332206726074, "step": 297460 }, { "epoch": 1.7682234546546118, "grad_norm": 1.0065674781799316, "learning_rate": 9.765948992088849e-05, "loss": 0.5103703498840332, "step": 297470 }, { "epoch": 1.7682828967312803, "grad_norm": 1.4560352563858032, "learning_rate": 9.765332397473867e-05, "loss": 0.5100619316101074, "step": 297480 }, { "epoch": 1.7683423388079484, "grad_norm": 1.3263028860092163, "learning_rate": 9.764715808765135e-05, "loss": 0.5373732566833496, "step": 297490 }, { "epoch": 1.7684017808846169, "grad_norm": 1.2723129987716675, "learning_rate": 9.764099225965594e-05, "loss": 0.5057900905609131, "step": 297500 }, { "epoch": 1.7684612229612853, "grad_norm": 1.295061707496643, "learning_rate": 9.763482649078202e-05, "loss": 0.5530385971069336, "step": 297510 }, { "epoch": 1.7685206650379537, "grad_norm": 1.0028425455093384, "learning_rate": 9.762866078105903e-05, "loss": 0.5743134021759033, "step": 297520 }, { "epoch": 1.768580107114622, "grad_norm": 1.6344918012619019, "learning_rate": 9.762249513051651e-05, "loss": 0.5939559936523438, "step": 297530 }, { "epoch": 1.7686395491912905, "grad_norm": 1.1537522077560425, "learning_rate": 9.761632953918389e-05, "loss": 0.5522500038146972, "step": 297540 }, { "epoch": 1.768698991267959, "grad_norm": 1.4450045824050903, "learning_rate": 9.761016400709073e-05, "loss": 0.5613597869873047, "step": 297550 }, { "epoch": 1.7687584333446273, "grad_norm": 1.521538257598877, "learning_rate": 9.76039985342665e-05, "loss": 0.5460353851318359, "step": 297560 }, { "epoch": 1.7688178754212958, "grad_norm": 1.4669058322906494, "learning_rate": 9.759783312074067e-05, "loss": 0.5494209289550781, "step": 297570 }, { "epoch": 1.7688773174979642, "grad_norm": 1.5980693101882935, "learning_rate": 9.759166776654277e-05, "loss": 0.5466838836669922, "step": 297580 }, { "epoch": 1.7689367595746326, "grad_norm": 1.616409182548523, "learning_rate": 9.758550247170226e-05, "loss": 0.5512410163879394, "step": 297590 }, { "epoch": 1.768996201651301, "grad_norm": 1.8005304336547852, "learning_rate": 9.757933723624863e-05, "loss": 0.5718364238739013, "step": 297600 }, { "epoch": 1.7690556437279694, "grad_norm": 1.582770824432373, "learning_rate": 9.757317206021147e-05, "loss": 0.52096586227417, "step": 297610 }, { "epoch": 1.7691150858046378, "grad_norm": 4.1600236892700195, "learning_rate": 9.756700694362011e-05, "loss": 0.5833381652832031, "step": 297620 }, { "epoch": 1.769174527881306, "grad_norm": 1.3389229774475098, "learning_rate": 9.756084188650416e-05, "loss": 0.5061105251312256, "step": 297630 }, { "epoch": 1.7692339699579744, "grad_norm": 1.2380777597427368, "learning_rate": 9.755467688889308e-05, "loss": 0.5321277618408203, "step": 297640 }, { "epoch": 1.7692934120346429, "grad_norm": 1.2868027687072754, "learning_rate": 9.754851195081636e-05, "loss": 0.6080267906188965, "step": 297650 }, { "epoch": 1.7693528541113113, "grad_norm": 1.7969597578048706, "learning_rate": 9.754234707230347e-05, "loss": 0.6309890747070312, "step": 297660 }, { "epoch": 1.7694122961879795, "grad_norm": 1.2065207958221436, "learning_rate": 9.753618225338392e-05, "loss": 0.49145803451538084, "step": 297670 }, { "epoch": 1.7694717382646479, "grad_norm": 1.6327177286148071, "learning_rate": 9.753001749408723e-05, "loss": 0.5570630073547364, "step": 297680 }, { "epoch": 1.7695311803413163, "grad_norm": 1.495962142944336, "learning_rate": 9.752385279444285e-05, "loss": 0.5023614883422851, "step": 297690 }, { "epoch": 1.7695906224179847, "grad_norm": 1.2415721416473389, "learning_rate": 9.751768815448028e-05, "loss": 0.5691972732543945, "step": 297700 }, { "epoch": 1.7696500644946531, "grad_norm": 1.2571253776550293, "learning_rate": 9.751152357422901e-05, "loss": 0.5230457305908203, "step": 297710 }, { "epoch": 1.7697095065713215, "grad_norm": 1.159988522529602, "learning_rate": 9.750535905371854e-05, "loss": 0.5295251846313477, "step": 297720 }, { "epoch": 1.76976894864799, "grad_norm": 1.4609936475753784, "learning_rate": 9.749919459297831e-05, "loss": 0.5472668647766114, "step": 297730 }, { "epoch": 1.7698283907246584, "grad_norm": 1.3270052671432495, "learning_rate": 9.749303019203789e-05, "loss": 0.580772066116333, "step": 297740 }, { "epoch": 1.7698878328013268, "grad_norm": 1.2516896724700928, "learning_rate": 9.74868658509267e-05, "loss": 0.5871447563171387, "step": 297750 }, { "epoch": 1.7699472748779952, "grad_norm": 1.2766032218933105, "learning_rate": 9.748070156967426e-05, "loss": 0.571925163269043, "step": 297760 }, { "epoch": 1.7700067169546636, "grad_norm": 1.466342568397522, "learning_rate": 9.747453734831006e-05, "loss": 0.4839020252227783, "step": 297770 }, { "epoch": 1.770066159031332, "grad_norm": 1.2943925857543945, "learning_rate": 9.74683731868636e-05, "loss": 0.5650990962982178, "step": 297780 }, { "epoch": 1.7701256011080004, "grad_norm": 1.2567986249923706, "learning_rate": 9.746220908536435e-05, "loss": 0.5804154396057128, "step": 297790 }, { "epoch": 1.7701850431846688, "grad_norm": 1.4668036699295044, "learning_rate": 9.745604504384171e-05, "loss": 0.606621265411377, "step": 297800 }, { "epoch": 1.770244485261337, "grad_norm": 1.2713203430175781, "learning_rate": 9.744988106232536e-05, "loss": 0.5875819206237793, "step": 297810 }, { "epoch": 1.7703039273380055, "grad_norm": 1.4777275323867798, "learning_rate": 9.744371714084461e-05, "loss": 0.5879665374755859, "step": 297820 }, { "epoch": 1.7703633694146739, "grad_norm": 1.4985253810882568, "learning_rate": 9.743755327942901e-05, "loss": 0.5828334331512451, "step": 297830 }, { "epoch": 1.7704228114913423, "grad_norm": 1.6707288026809692, "learning_rate": 9.74313894781081e-05, "loss": 0.567788553237915, "step": 297840 }, { "epoch": 1.7704822535680107, "grad_norm": 1.3062655925750732, "learning_rate": 9.742522573691128e-05, "loss": 0.5339926242828369, "step": 297850 }, { "epoch": 1.770541695644679, "grad_norm": 1.2224475145339966, "learning_rate": 9.741906205586804e-05, "loss": 0.561368465423584, "step": 297860 }, { "epoch": 1.7706011377213473, "grad_norm": 1.6464225053787231, "learning_rate": 9.741289843500796e-05, "loss": 0.5824495315551758, "step": 297870 }, { "epoch": 1.7706605797980157, "grad_norm": 1.4837411642074585, "learning_rate": 9.740673487436046e-05, "loss": 0.597964859008789, "step": 297880 }, { "epoch": 1.7707200218746841, "grad_norm": 1.2558485269546509, "learning_rate": 9.7400571373955e-05, "loss": 0.5812407016754151, "step": 297890 }, { "epoch": 1.7707794639513526, "grad_norm": 1.7370051145553589, "learning_rate": 9.739440793382106e-05, "loss": 0.4899128913879395, "step": 297900 }, { "epoch": 1.770838906028021, "grad_norm": 1.4547338485717773, "learning_rate": 9.738824455398818e-05, "loss": 0.5408531188964844, "step": 297910 }, { "epoch": 1.7708983481046894, "grad_norm": 1.4342403411865234, "learning_rate": 9.738208123448582e-05, "loss": 0.5403249740600586, "step": 297920 }, { "epoch": 1.7709577901813578, "grad_norm": 1.562153935432434, "learning_rate": 9.737591797534344e-05, "loss": 0.5431390285491944, "step": 297930 }, { "epoch": 1.7710172322580262, "grad_norm": 1.4183349609375, "learning_rate": 9.736975477659056e-05, "loss": 0.5732327938079834, "step": 297940 }, { "epoch": 1.7710766743346946, "grad_norm": 1.2255054712295532, "learning_rate": 9.736359163825665e-05, "loss": 0.5006129264831543, "step": 297950 }, { "epoch": 1.771136116411363, "grad_norm": 1.194173812866211, "learning_rate": 9.735742856037117e-05, "loss": 0.5497347831726074, "step": 297960 }, { "epoch": 1.7711955584880315, "grad_norm": 1.315453052520752, "learning_rate": 9.735126554296366e-05, "loss": 0.5715408325195312, "step": 297970 }, { "epoch": 1.7712550005646999, "grad_norm": 1.7157689332962036, "learning_rate": 9.734510258606353e-05, "loss": 0.5633701801300048, "step": 297980 }, { "epoch": 1.7713144426413683, "grad_norm": 1.5392067432403564, "learning_rate": 9.733893968970029e-05, "loss": 0.5294025897979736, "step": 297990 }, { "epoch": 1.7713738847180365, "grad_norm": 1.4762308597564697, "learning_rate": 9.733277685390343e-05, "loss": 0.579520320892334, "step": 298000 }, { "epoch": 1.7714333267947049, "grad_norm": 1.246138572692871, "learning_rate": 9.732661407870245e-05, "loss": 0.5250243663787841, "step": 298010 }, { "epoch": 1.7714927688713733, "grad_norm": 1.5110584497451782, "learning_rate": 9.732045136412678e-05, "loss": 0.5487260818481445, "step": 298020 }, { "epoch": 1.7715522109480417, "grad_norm": 1.1683087348937988, "learning_rate": 9.731428871020591e-05, "loss": 0.5970304489135743, "step": 298030 }, { "epoch": 1.77161165302471, "grad_norm": 1.6282178163528442, "learning_rate": 9.730812611696938e-05, "loss": 0.5465534687042236, "step": 298040 }, { "epoch": 1.7716710951013783, "grad_norm": 1.6539503335952759, "learning_rate": 9.73019635844466e-05, "loss": 0.5453031539916993, "step": 298050 }, { "epoch": 1.7717305371780467, "grad_norm": 1.8576089143753052, "learning_rate": 9.729580111266707e-05, "loss": 0.5453152656555176, "step": 298060 }, { "epoch": 1.7717899792547152, "grad_norm": 1.2421795129776, "learning_rate": 9.728963870166028e-05, "loss": 0.5912330627441407, "step": 298070 }, { "epoch": 1.7718494213313836, "grad_norm": 1.2611472606658936, "learning_rate": 9.728347635145574e-05, "loss": 0.5305717468261719, "step": 298080 }, { "epoch": 1.771908863408052, "grad_norm": 1.5900132656097412, "learning_rate": 9.727731406208284e-05, "loss": 0.5934095859527588, "step": 298090 }, { "epoch": 1.7719683054847204, "grad_norm": 1.161759614944458, "learning_rate": 9.727115183357114e-05, "loss": 0.5520175457000732, "step": 298100 }, { "epoch": 1.7720277475613888, "grad_norm": 1.6657545566558838, "learning_rate": 9.72649896659501e-05, "loss": 0.5071503162384033, "step": 298110 }, { "epoch": 1.7720871896380572, "grad_norm": 1.6051840782165527, "learning_rate": 9.725882755924915e-05, "loss": 0.5685205459594727, "step": 298120 }, { "epoch": 1.7721466317147256, "grad_norm": 1.5520944595336914, "learning_rate": 9.725266551349785e-05, "loss": 0.5867023944854737, "step": 298130 }, { "epoch": 1.772206073791394, "grad_norm": 1.2441962957382202, "learning_rate": 9.724650352872562e-05, "loss": 0.5204650402069092, "step": 298140 }, { "epoch": 1.7722655158680625, "grad_norm": 1.359496831893921, "learning_rate": 9.724034160496194e-05, "loss": 0.5364408493041992, "step": 298150 }, { "epoch": 1.7723249579447309, "grad_norm": 1.3681317567825317, "learning_rate": 9.723417974223627e-05, "loss": 0.5858107566833496, "step": 298160 }, { "epoch": 1.7723844000213993, "grad_norm": 1.331791877746582, "learning_rate": 9.722801794057817e-05, "loss": 0.5435053825378418, "step": 298170 }, { "epoch": 1.7724438420980675, "grad_norm": 1.2764272689819336, "learning_rate": 9.722185620001702e-05, "loss": 0.5559094429016114, "step": 298180 }, { "epoch": 1.772503284174736, "grad_norm": 1.163928508758545, "learning_rate": 9.721569452058234e-05, "loss": 0.5249800205230712, "step": 298190 }, { "epoch": 1.7725627262514043, "grad_norm": 1.4811592102050781, "learning_rate": 9.720953290230361e-05, "loss": 0.5313526630401612, "step": 298200 }, { "epoch": 1.7726221683280727, "grad_norm": 1.4915543794631958, "learning_rate": 9.720337134521029e-05, "loss": 0.5128193855285644, "step": 298210 }, { "epoch": 1.7726816104047411, "grad_norm": 1.3948606252670288, "learning_rate": 9.719720984933182e-05, "loss": 0.5710236549377441, "step": 298220 }, { "epoch": 1.7727410524814093, "grad_norm": 1.132550835609436, "learning_rate": 9.719104841469777e-05, "loss": 0.5874123096466064, "step": 298230 }, { "epoch": 1.7728004945580778, "grad_norm": 1.0397590398788452, "learning_rate": 9.718488704133754e-05, "loss": 0.5148715972900391, "step": 298240 }, { "epoch": 1.7728599366347462, "grad_norm": 1.4310030937194824, "learning_rate": 9.717872572928062e-05, "loss": 0.4968104362487793, "step": 298250 }, { "epoch": 1.7729193787114146, "grad_norm": 1.3820754289627075, "learning_rate": 9.717256447855648e-05, "loss": 0.5246439456939698, "step": 298260 }, { "epoch": 1.772978820788083, "grad_norm": 1.590747594833374, "learning_rate": 9.716640328919461e-05, "loss": 0.5568386077880859, "step": 298270 }, { "epoch": 1.7730382628647514, "grad_norm": 1.199408769607544, "learning_rate": 9.71602421612245e-05, "loss": 0.5655272006988525, "step": 298280 }, { "epoch": 1.7730977049414198, "grad_norm": 1.246566891670227, "learning_rate": 9.715408109467552e-05, "loss": 0.5826333045959473, "step": 298290 }, { "epoch": 1.7731571470180882, "grad_norm": 1.9711954593658447, "learning_rate": 9.714792008957729e-05, "loss": 0.513822364807129, "step": 298300 }, { "epoch": 1.7732165890947567, "grad_norm": 1.6919280290603638, "learning_rate": 9.71417591459592e-05, "loss": 0.5819747924804688, "step": 298310 }, { "epoch": 1.773276031171425, "grad_norm": 1.4949464797973633, "learning_rate": 9.713559826385068e-05, "loss": 0.5381096839904785, "step": 298320 }, { "epoch": 1.7733354732480935, "grad_norm": 1.7609318494796753, "learning_rate": 9.712943744328129e-05, "loss": 0.5391169548034668, "step": 298330 }, { "epoch": 1.773394915324762, "grad_norm": 1.7002638578414917, "learning_rate": 9.712327668428049e-05, "loss": 0.5655422210693359, "step": 298340 }, { "epoch": 1.7734543574014303, "grad_norm": 1.5616687536239624, "learning_rate": 9.711711598687767e-05, "loss": 0.49996347427368165, "step": 298350 }, { "epoch": 1.7735137994780987, "grad_norm": 1.4884454011917114, "learning_rate": 9.711095535110237e-05, "loss": 0.5379770278930665, "step": 298360 }, { "epoch": 1.773573241554767, "grad_norm": 1.4154154062271118, "learning_rate": 9.71047947769841e-05, "loss": 0.5867938041687012, "step": 298370 }, { "epoch": 1.7736326836314353, "grad_norm": 1.6665303707122803, "learning_rate": 9.709863426455225e-05, "loss": 0.6031498908996582, "step": 298380 }, { "epoch": 1.7736921257081038, "grad_norm": 1.5209085941314697, "learning_rate": 9.709247381383628e-05, "loss": 0.609837818145752, "step": 298390 }, { "epoch": 1.7737515677847722, "grad_norm": 1.110473394393921, "learning_rate": 9.708631342486574e-05, "loss": 0.553678560256958, "step": 298400 }, { "epoch": 1.7738110098614404, "grad_norm": 1.388977289199829, "learning_rate": 9.708015309767007e-05, "loss": 0.5831924438476562, "step": 298410 }, { "epoch": 1.7738704519381088, "grad_norm": 2.4175338745117188, "learning_rate": 9.707399283227867e-05, "loss": 0.5675538539886474, "step": 298420 }, { "epoch": 1.7739298940147772, "grad_norm": 1.5209065675735474, "learning_rate": 9.70678326287211e-05, "loss": 0.5867701530456543, "step": 298430 }, { "epoch": 1.7739893360914456, "grad_norm": 1.5368608236312866, "learning_rate": 9.706167248702678e-05, "loss": 0.5724965572357178, "step": 298440 }, { "epoch": 1.774048778168114, "grad_norm": 1.396412968635559, "learning_rate": 9.70555124072252e-05, "loss": 0.5979741096496582, "step": 298450 }, { "epoch": 1.7741082202447824, "grad_norm": 1.5693055391311646, "learning_rate": 9.704935238934581e-05, "loss": 0.5872638702392579, "step": 298460 }, { "epoch": 1.7741676623214508, "grad_norm": 1.3943980932235718, "learning_rate": 9.70431924334181e-05, "loss": 0.5978188514709473, "step": 298470 }, { "epoch": 1.7742271043981193, "grad_norm": 1.2627854347229004, "learning_rate": 9.70370325394715e-05, "loss": 0.6295401096343994, "step": 298480 }, { "epoch": 1.7742865464747877, "grad_norm": 1.2509913444519043, "learning_rate": 9.703087270753551e-05, "loss": 0.5297345161437989, "step": 298490 }, { "epoch": 1.774345988551456, "grad_norm": 1.364752173423767, "learning_rate": 9.70247129376396e-05, "loss": 0.5415076732635498, "step": 298500 }, { "epoch": 1.7744054306281245, "grad_norm": 1.506942868232727, "learning_rate": 9.701855322981321e-05, "loss": 0.644558048248291, "step": 298510 }, { "epoch": 1.774464872704793, "grad_norm": 1.2335079908370972, "learning_rate": 9.70123935840858e-05, "loss": 0.5949466705322266, "step": 298520 }, { "epoch": 1.7745243147814613, "grad_norm": 1.2668726444244385, "learning_rate": 9.70062340004869e-05, "loss": 0.581063175201416, "step": 298530 }, { "epoch": 1.7745837568581297, "grad_norm": 1.5684987306594849, "learning_rate": 9.700007447904591e-05, "loss": 0.5721913814544678, "step": 298540 }, { "epoch": 1.774643198934798, "grad_norm": 1.270039439201355, "learning_rate": 9.699391501979229e-05, "loss": 0.5564926147460938, "step": 298550 }, { "epoch": 1.7747026410114664, "grad_norm": 1.2181155681610107, "learning_rate": 9.698775562275555e-05, "loss": 0.5870765209197998, "step": 298560 }, { "epoch": 1.7747620830881348, "grad_norm": 1.582910180091858, "learning_rate": 9.698159628796514e-05, "loss": 0.5296257019042969, "step": 298570 }, { "epoch": 1.7748215251648032, "grad_norm": 1.1451083421707153, "learning_rate": 9.697543701545049e-05, "loss": 0.5317944526672364, "step": 298580 }, { "epoch": 1.7748809672414716, "grad_norm": 1.2020716667175293, "learning_rate": 9.696927780524112e-05, "loss": 0.5266249656677247, "step": 298590 }, { "epoch": 1.7749404093181398, "grad_norm": 1.5171211957931519, "learning_rate": 9.69631186573665e-05, "loss": 0.5836931228637695, "step": 298600 }, { "epoch": 1.7749998513948082, "grad_norm": 2.0581555366516113, "learning_rate": 9.6956959571856e-05, "loss": 0.561772346496582, "step": 298610 }, { "epoch": 1.7750592934714766, "grad_norm": 1.5311781167984009, "learning_rate": 9.695080054873917e-05, "loss": 0.6110489845275879, "step": 298620 }, { "epoch": 1.775118735548145, "grad_norm": 1.3722450733184814, "learning_rate": 9.694464158804544e-05, "loss": 0.5844121932983398, "step": 298630 }, { "epoch": 1.7751781776248134, "grad_norm": 1.3318907022476196, "learning_rate": 9.69384826898043e-05, "loss": 0.6110501289367676, "step": 298640 }, { "epoch": 1.7752376197014819, "grad_norm": 1.4041491746902466, "learning_rate": 9.693232385404516e-05, "loss": 0.5645848274230957, "step": 298650 }, { "epoch": 1.7752970617781503, "grad_norm": 1.6846262216567993, "learning_rate": 9.69261650807975e-05, "loss": 0.5063840866088867, "step": 298660 }, { "epoch": 1.7753565038548187, "grad_norm": 1.0836243629455566, "learning_rate": 9.692000637009084e-05, "loss": 0.5419753551483154, "step": 298670 }, { "epoch": 1.775415945931487, "grad_norm": 1.2705340385437012, "learning_rate": 9.691384772195455e-05, "loss": 0.5349665641784668, "step": 298680 }, { "epoch": 1.7754753880081555, "grad_norm": 1.3943023681640625, "learning_rate": 9.690768913641816e-05, "loss": 0.5471071720123291, "step": 298690 }, { "epoch": 1.775534830084824, "grad_norm": 1.3701404333114624, "learning_rate": 9.690153061351111e-05, "loss": 0.5544624328613281, "step": 298700 }, { "epoch": 1.7755942721614923, "grad_norm": 1.5248602628707886, "learning_rate": 9.689537215326284e-05, "loss": 0.5882827758789062, "step": 298710 }, { "epoch": 1.7756537142381608, "grad_norm": 1.6794439554214478, "learning_rate": 9.688921375570284e-05, "loss": 0.536014175415039, "step": 298720 }, { "epoch": 1.7757131563148292, "grad_norm": 1.391070008277893, "learning_rate": 9.688305542086056e-05, "loss": 0.5673394203186035, "step": 298730 }, { "epoch": 1.7757725983914974, "grad_norm": 1.1846710443496704, "learning_rate": 9.687689714876549e-05, "loss": 0.5792144298553467, "step": 298740 }, { "epoch": 1.7758320404681658, "grad_norm": 1.4484635591506958, "learning_rate": 9.687073893944698e-05, "loss": 0.5255199432373047, "step": 298750 }, { "epoch": 1.7758914825448342, "grad_norm": 1.4390426874160767, "learning_rate": 9.686458079293459e-05, "loss": 0.545559310913086, "step": 298760 }, { "epoch": 1.7759509246215026, "grad_norm": 1.4498341083526611, "learning_rate": 9.685842270925777e-05, "loss": 0.5953427314758301, "step": 298770 }, { "epoch": 1.7760103666981708, "grad_norm": 1.5629442930221558, "learning_rate": 9.685226468844595e-05, "loss": 0.4959095001220703, "step": 298780 }, { "epoch": 1.7760698087748392, "grad_norm": 1.457410454750061, "learning_rate": 9.68461067305286e-05, "loss": 0.6024982452392578, "step": 298790 }, { "epoch": 1.7761292508515076, "grad_norm": 1.48843252658844, "learning_rate": 9.68399488355352e-05, "loss": 0.5697534561157227, "step": 298800 }, { "epoch": 1.776188692928176, "grad_norm": 1.3040050268173218, "learning_rate": 9.683379100349513e-05, "loss": 0.5775396823883057, "step": 298810 }, { "epoch": 1.7762481350048445, "grad_norm": 1.1977838277816772, "learning_rate": 9.682763323443795e-05, "loss": 0.5286206722259521, "step": 298820 }, { "epoch": 1.7763075770815129, "grad_norm": 1.5103803873062134, "learning_rate": 9.682147552839307e-05, "loss": 0.5736019134521484, "step": 298830 }, { "epoch": 1.7763670191581813, "grad_norm": 1.5831445455551147, "learning_rate": 9.681531788538989e-05, "loss": 0.562779712677002, "step": 298840 }, { "epoch": 1.7764264612348497, "grad_norm": 1.4258382320404053, "learning_rate": 9.680916030545797e-05, "loss": 0.5593119621276855, "step": 298850 }, { "epoch": 1.7764859033115181, "grad_norm": 1.7892186641693115, "learning_rate": 9.680300278862673e-05, "loss": 0.5625074863433838, "step": 298860 }, { "epoch": 1.7765453453881865, "grad_norm": 1.3122800588607788, "learning_rate": 9.67968453349256e-05, "loss": 0.48429207801818847, "step": 298870 }, { "epoch": 1.776604787464855, "grad_norm": 1.5162712335586548, "learning_rate": 9.6790687944384e-05, "loss": 0.5728774547576905, "step": 298880 }, { "epoch": 1.7766642295415234, "grad_norm": 1.689721703529358, "learning_rate": 9.678453061703147e-05, "loss": 0.5535260200500488, "step": 298890 }, { "epoch": 1.7767236716181918, "grad_norm": 1.4612809419631958, "learning_rate": 9.677837335289743e-05, "loss": 0.565135145187378, "step": 298900 }, { "epoch": 1.7767831136948602, "grad_norm": 1.411363124847412, "learning_rate": 9.677221615201129e-05, "loss": 0.5280216217041016, "step": 298910 }, { "epoch": 1.7768425557715284, "grad_norm": 1.593037724494934, "learning_rate": 9.67660590144026e-05, "loss": 0.5815359115600586, "step": 298920 }, { "epoch": 1.7769019978481968, "grad_norm": 1.123266577720642, "learning_rate": 9.675990194010074e-05, "loss": 0.4963803291320801, "step": 298930 }, { "epoch": 1.7769614399248652, "grad_norm": 1.2877023220062256, "learning_rate": 9.675374492913515e-05, "loss": 0.5808714389801025, "step": 298940 }, { "epoch": 1.7770208820015336, "grad_norm": 1.414998173713684, "learning_rate": 9.674758798153535e-05, "loss": 0.6064261436462403, "step": 298950 }, { "epoch": 1.777080324078202, "grad_norm": 1.2896713018417358, "learning_rate": 9.674143109733075e-05, "loss": 0.5286881923675537, "step": 298960 }, { "epoch": 1.7771397661548702, "grad_norm": 1.4107059240341187, "learning_rate": 9.67352742765508e-05, "loss": 0.5091894149780274, "step": 298970 }, { "epoch": 1.7771992082315387, "grad_norm": 1.396863579750061, "learning_rate": 9.6729117519225e-05, "loss": 0.508180046081543, "step": 298980 }, { "epoch": 1.777258650308207, "grad_norm": 1.1830165386199951, "learning_rate": 9.672296082538274e-05, "loss": 0.516841983795166, "step": 298990 }, { "epoch": 1.7773180923848755, "grad_norm": 1.2581307888031006, "learning_rate": 9.671680419505351e-05, "loss": 0.5250453472137451, "step": 299000 }, { "epoch": 1.777377534461544, "grad_norm": 1.527955174446106, "learning_rate": 9.671064762826672e-05, "loss": 0.5590970516204834, "step": 299010 }, { "epoch": 1.7774369765382123, "grad_norm": 1.4569004774093628, "learning_rate": 9.670449112505187e-05, "loss": 0.5962125778198242, "step": 299020 }, { "epoch": 1.7774964186148807, "grad_norm": 1.0812351703643799, "learning_rate": 9.669833468543838e-05, "loss": 0.5868834495544434, "step": 299030 }, { "epoch": 1.7775558606915491, "grad_norm": 1.5054900646209717, "learning_rate": 9.669217830945569e-05, "loss": 0.5656225681304932, "step": 299040 }, { "epoch": 1.7776153027682176, "grad_norm": 0.9624967575073242, "learning_rate": 9.66860219971333e-05, "loss": 0.5302618980407715, "step": 299050 }, { "epoch": 1.777674744844886, "grad_norm": 1.4881163835525513, "learning_rate": 9.667986574850063e-05, "loss": 0.5248543739318847, "step": 299060 }, { "epoch": 1.7777341869215544, "grad_norm": 1.4346542358398438, "learning_rate": 9.667370956358713e-05, "loss": 0.5479472160339356, "step": 299070 }, { "epoch": 1.7777936289982228, "grad_norm": 1.5253328084945679, "learning_rate": 9.666755344242222e-05, "loss": 0.5230399608612061, "step": 299080 }, { "epoch": 1.7778530710748912, "grad_norm": 1.4780277013778687, "learning_rate": 9.666139738503542e-05, "loss": 0.5513033866882324, "step": 299090 }, { "epoch": 1.7779125131515596, "grad_norm": 2.3358850479125977, "learning_rate": 9.66552413914561e-05, "loss": 0.5871131896972657, "step": 299100 }, { "epoch": 1.7779719552282278, "grad_norm": 1.4884617328643799, "learning_rate": 9.664908546171376e-05, "loss": 0.5198990821838378, "step": 299110 }, { "epoch": 1.7780313973048962, "grad_norm": 1.2925575971603394, "learning_rate": 9.664292959583783e-05, "loss": 0.468814754486084, "step": 299120 }, { "epoch": 1.7780908393815646, "grad_norm": 1.7026692628860474, "learning_rate": 9.663677379385777e-05, "loss": 0.5862399101257324, "step": 299130 }, { "epoch": 1.778150281458233, "grad_norm": 1.198702335357666, "learning_rate": 9.663061805580298e-05, "loss": 0.5607260704040528, "step": 299140 }, { "epoch": 1.7782097235349013, "grad_norm": 1.2856225967407227, "learning_rate": 9.662446238170297e-05, "loss": 0.5547234058380127, "step": 299150 }, { "epoch": 1.7782691656115697, "grad_norm": 0.9716489911079407, "learning_rate": 9.661830677158717e-05, "loss": 0.5418968200683594, "step": 299160 }, { "epoch": 1.778328607688238, "grad_norm": 1.4507954120635986, "learning_rate": 9.661215122548499e-05, "loss": 0.546631908416748, "step": 299170 }, { "epoch": 1.7783880497649065, "grad_norm": 1.7568155527114868, "learning_rate": 9.660599574342592e-05, "loss": 0.565361213684082, "step": 299180 }, { "epoch": 1.778447491841575, "grad_norm": 1.4263759851455688, "learning_rate": 9.65998403254394e-05, "loss": 0.5473859310150146, "step": 299190 }, { "epoch": 1.7785069339182433, "grad_norm": 1.4775943756103516, "learning_rate": 9.659368497155483e-05, "loss": 0.5083907127380372, "step": 299200 }, { "epoch": 1.7785663759949117, "grad_norm": 1.4926488399505615, "learning_rate": 9.658752968180173e-05, "loss": 0.5424132347106934, "step": 299210 }, { "epoch": 1.7786258180715802, "grad_norm": 1.56308913230896, "learning_rate": 9.658137445620949e-05, "loss": 0.5637526512145996, "step": 299220 }, { "epoch": 1.7786852601482486, "grad_norm": 1.3589138984680176, "learning_rate": 9.657521929480759e-05, "loss": 0.577642297744751, "step": 299230 }, { "epoch": 1.778744702224917, "grad_norm": 1.8432968854904175, "learning_rate": 9.656906419762541e-05, "loss": 0.5837690830230713, "step": 299240 }, { "epoch": 1.7788041443015854, "grad_norm": 1.6149097681045532, "learning_rate": 9.656290916469248e-05, "loss": 0.5679061889648438, "step": 299250 }, { "epoch": 1.7788635863782538, "grad_norm": 1.834242820739746, "learning_rate": 9.65567541960382e-05, "loss": 0.5528871059417725, "step": 299260 }, { "epoch": 1.7789230284549222, "grad_norm": 1.4901131391525269, "learning_rate": 9.655059929169194e-05, "loss": 0.5551252365112305, "step": 299270 }, { "epoch": 1.7789824705315906, "grad_norm": 1.407739520072937, "learning_rate": 9.654444445168329e-05, "loss": 0.5307086944580078, "step": 299280 }, { "epoch": 1.7790419126082588, "grad_norm": 1.1972846984863281, "learning_rate": 9.653828967604163e-05, "loss": 0.5849527835845947, "step": 299290 }, { "epoch": 1.7791013546849272, "grad_norm": 1.3955661058425903, "learning_rate": 9.653213496479634e-05, "loss": 0.57000732421875, "step": 299300 }, { "epoch": 1.7791607967615957, "grad_norm": 1.661382794380188, "learning_rate": 9.652598031797694e-05, "loss": 0.5622151374816895, "step": 299310 }, { "epoch": 1.779220238838264, "grad_norm": 1.531307578086853, "learning_rate": 9.651982573561286e-05, "loss": 0.5475759983062745, "step": 299320 }, { "epoch": 1.7792796809149325, "grad_norm": 1.2533106803894043, "learning_rate": 9.65136712177335e-05, "loss": 0.5447842597961425, "step": 299330 }, { "epoch": 1.7793391229916007, "grad_norm": 1.5537428855895996, "learning_rate": 9.650751676436836e-05, "loss": 0.5655116081237793, "step": 299340 }, { "epoch": 1.779398565068269, "grad_norm": 1.0698509216308594, "learning_rate": 9.650136237554685e-05, "loss": 0.5435412406921387, "step": 299350 }, { "epoch": 1.7794580071449375, "grad_norm": 1.3454723358154297, "learning_rate": 9.649520805129839e-05, "loss": 0.5411996841430664, "step": 299360 }, { "epoch": 1.779517449221606, "grad_norm": 1.3716870546340942, "learning_rate": 9.648905379165242e-05, "loss": 0.530498456954956, "step": 299370 }, { "epoch": 1.7795768912982743, "grad_norm": 1.4688419103622437, "learning_rate": 9.648289959663845e-05, "loss": 0.5846696376800538, "step": 299380 }, { "epoch": 1.7796363333749428, "grad_norm": 1.739263892173767, "learning_rate": 9.647674546628587e-05, "loss": 0.5785324096679687, "step": 299390 }, { "epoch": 1.7796957754516112, "grad_norm": 1.5568022727966309, "learning_rate": 9.647059140062407e-05, "loss": 0.5021209239959716, "step": 299400 }, { "epoch": 1.7797552175282796, "grad_norm": 1.4440150260925293, "learning_rate": 9.646443739968258e-05, "loss": 0.5827167987823486, "step": 299410 }, { "epoch": 1.779814659604948, "grad_norm": 1.5327216386795044, "learning_rate": 9.645828346349079e-05, "loss": 0.5400914192199707, "step": 299420 }, { "epoch": 1.7798741016816164, "grad_norm": 1.4206974506378174, "learning_rate": 9.645212959207812e-05, "loss": 0.5591812133789062, "step": 299430 }, { "epoch": 1.7799335437582848, "grad_norm": 1.27266526222229, "learning_rate": 9.64459757854741e-05, "loss": 0.5651764869689941, "step": 299440 }, { "epoch": 1.7799929858349532, "grad_norm": 1.571569561958313, "learning_rate": 9.643982204370805e-05, "loss": 0.5390381336212158, "step": 299450 }, { "epoch": 1.7800524279116217, "grad_norm": 1.7743380069732666, "learning_rate": 9.643366836680945e-05, "loss": 0.5660293579101563, "step": 299460 }, { "epoch": 1.78011186998829, "grad_norm": 1.5072325468063354, "learning_rate": 9.642751475480778e-05, "loss": 0.5653530120849609, "step": 299470 }, { "epoch": 1.7801713120649583, "grad_norm": 1.441965937614441, "learning_rate": 9.642136120773244e-05, "loss": 0.5713561058044434, "step": 299480 }, { "epoch": 1.7802307541416267, "grad_norm": 2.0430781841278076, "learning_rate": 9.641520772561288e-05, "loss": 0.5393670082092286, "step": 299490 }, { "epoch": 1.780290196218295, "grad_norm": 1.2898154258728027, "learning_rate": 9.640905430847848e-05, "loss": 0.6233795166015625, "step": 299500 }, { "epoch": 1.7803496382949635, "grad_norm": 1.6001144647598267, "learning_rate": 9.640290095635878e-05, "loss": 0.5465001106262207, "step": 299510 }, { "epoch": 1.7804090803716317, "grad_norm": 1.418926477432251, "learning_rate": 9.639674766928312e-05, "loss": 0.5459355354309082, "step": 299520 }, { "epoch": 1.7804685224483001, "grad_norm": 1.460263729095459, "learning_rate": 9.639059444728098e-05, "loss": 0.584547472000122, "step": 299530 }, { "epoch": 1.7805279645249685, "grad_norm": 1.1277825832366943, "learning_rate": 9.63844412903818e-05, "loss": 0.5677836418151856, "step": 299540 }, { "epoch": 1.780587406601637, "grad_norm": 1.3081326484680176, "learning_rate": 9.637828819861499e-05, "loss": 0.5732393264770508, "step": 299550 }, { "epoch": 1.7806468486783054, "grad_norm": 1.848622441291809, "learning_rate": 9.637213517200998e-05, "loss": 0.5205783367156982, "step": 299560 }, { "epoch": 1.7807062907549738, "grad_norm": 1.347615122795105, "learning_rate": 9.636598221059627e-05, "loss": 0.5444302082061767, "step": 299570 }, { "epoch": 1.7807657328316422, "grad_norm": 1.574769377708435, "learning_rate": 9.635982931440322e-05, "loss": 0.5399235725402832, "step": 299580 }, { "epoch": 1.7808251749083106, "grad_norm": 1.3925440311431885, "learning_rate": 9.63536764834603e-05, "loss": 0.5211411476135254, "step": 299590 }, { "epoch": 1.780884616984979, "grad_norm": 1.2272894382476807, "learning_rate": 9.634752371779689e-05, "loss": 0.5077217578887939, "step": 299600 }, { "epoch": 1.7809440590616474, "grad_norm": 1.218180537223816, "learning_rate": 9.634137101744252e-05, "loss": 0.5644373893737793, "step": 299610 }, { "epoch": 1.7810035011383158, "grad_norm": 1.494935393333435, "learning_rate": 9.633521838242654e-05, "loss": 0.5087827205657959, "step": 299620 }, { "epoch": 1.7810629432149843, "grad_norm": 1.000961422920227, "learning_rate": 9.632906581277841e-05, "loss": 0.5686715602874756, "step": 299630 }, { "epoch": 1.7811223852916527, "grad_norm": 1.3755519390106201, "learning_rate": 9.632291330852756e-05, "loss": 0.5332250595092773, "step": 299640 }, { "epoch": 1.781181827368321, "grad_norm": 1.4710371494293213, "learning_rate": 9.631676086970343e-05, "loss": 0.6223443031311036, "step": 299650 }, { "epoch": 1.7812412694449893, "grad_norm": 1.0968960523605347, "learning_rate": 9.631060849633542e-05, "loss": 0.5056132316589356, "step": 299660 }, { "epoch": 1.7813007115216577, "grad_norm": 1.6127488613128662, "learning_rate": 9.630445618845303e-05, "loss": 0.5348719120025635, "step": 299670 }, { "epoch": 1.7813601535983261, "grad_norm": 1.16813063621521, "learning_rate": 9.62983039460856e-05, "loss": 0.5725699424743652, "step": 299680 }, { "epoch": 1.7814195956749945, "grad_norm": 1.507757306098938, "learning_rate": 9.629215176926262e-05, "loss": 0.5968924522399902, "step": 299690 }, { "epoch": 1.781479037751663, "grad_norm": 1.72369384765625, "learning_rate": 9.628599965801353e-05, "loss": 0.6383766174316406, "step": 299700 }, { "epoch": 1.7815384798283311, "grad_norm": 1.4700473546981812, "learning_rate": 9.627984761236775e-05, "loss": 0.543528413772583, "step": 299710 }, { "epoch": 1.7815979219049995, "grad_norm": 1.601921796798706, "learning_rate": 9.627369563235466e-05, "loss": 0.50895094871521, "step": 299720 }, { "epoch": 1.781657363981668, "grad_norm": 1.2825274467468262, "learning_rate": 9.62675437180037e-05, "loss": 0.5253604412078857, "step": 299730 }, { "epoch": 1.7817168060583364, "grad_norm": 1.2641867399215698, "learning_rate": 9.626139186934438e-05, "loss": 0.5868421077728272, "step": 299740 }, { "epoch": 1.7817762481350048, "grad_norm": 1.3175207376480103, "learning_rate": 9.625524008640606e-05, "loss": 0.5609341621398926, "step": 299750 }, { "epoch": 1.7818356902116732, "grad_norm": 1.3412392139434814, "learning_rate": 9.624908836921813e-05, "loss": 0.5858247756958008, "step": 299760 }, { "epoch": 1.7818951322883416, "grad_norm": 1.4890216588974, "learning_rate": 9.624293671781011e-05, "loss": 0.5816843986511231, "step": 299770 }, { "epoch": 1.78195457436501, "grad_norm": 1.2673664093017578, "learning_rate": 9.623678513221139e-05, "loss": 0.5617801666259765, "step": 299780 }, { "epoch": 1.7820140164416785, "grad_norm": 1.0964471101760864, "learning_rate": 9.623063361245137e-05, "loss": 0.5094966888427734, "step": 299790 }, { "epoch": 1.7820734585183469, "grad_norm": 1.2388492822647095, "learning_rate": 9.62244821585595e-05, "loss": 0.5613015174865723, "step": 299800 }, { "epoch": 1.7821329005950153, "grad_norm": 1.4538966417312622, "learning_rate": 9.621833077056524e-05, "loss": 0.5011609077453614, "step": 299810 }, { "epoch": 1.7821923426716837, "grad_norm": 1.4877004623413086, "learning_rate": 9.621217944849792e-05, "loss": 0.5534509181976318, "step": 299820 }, { "epoch": 1.782251784748352, "grad_norm": 1.647254228591919, "learning_rate": 9.620602819238707e-05, "loss": 0.6470983505249024, "step": 299830 }, { "epoch": 1.7823112268250205, "grad_norm": 1.2848154306411743, "learning_rate": 9.619987700226209e-05, "loss": 0.5689484596252441, "step": 299840 }, { "epoch": 1.7823706689016887, "grad_norm": 1.2510651350021362, "learning_rate": 9.619372587815236e-05, "loss": 0.5597344875335694, "step": 299850 }, { "epoch": 1.7824301109783571, "grad_norm": 1.369913101196289, "learning_rate": 9.618757482008731e-05, "loss": 0.556146240234375, "step": 299860 }, { "epoch": 1.7824895530550255, "grad_norm": 1.4779614210128784, "learning_rate": 9.618142382809644e-05, "loss": 0.5461103439331054, "step": 299870 }, { "epoch": 1.782548995131694, "grad_norm": 1.2862138748168945, "learning_rate": 9.617527290220911e-05, "loss": 0.5788346290588379, "step": 299880 }, { "epoch": 1.7826084372083622, "grad_norm": 1.5962334871292114, "learning_rate": 9.616912204245472e-05, "loss": 0.5134895324707032, "step": 299890 }, { "epoch": 1.7826678792850306, "grad_norm": 1.2113127708435059, "learning_rate": 9.616297124886278e-05, "loss": 0.6273312568664551, "step": 299900 }, { "epoch": 1.782727321361699, "grad_norm": 1.2316564321517944, "learning_rate": 9.615682052146264e-05, "loss": 0.5613731384277344, "step": 299910 }, { "epoch": 1.7827867634383674, "grad_norm": 1.1972230672836304, "learning_rate": 9.615066986028369e-05, "loss": 0.5632623195648193, "step": 299920 }, { "epoch": 1.7828462055150358, "grad_norm": 1.685408115386963, "learning_rate": 9.61445192653555e-05, "loss": 0.5818521022796631, "step": 299930 }, { "epoch": 1.7829056475917042, "grad_norm": 1.3059182167053223, "learning_rate": 9.613836873670738e-05, "loss": 0.5155163764953613, "step": 299940 }, { "epoch": 1.7829650896683726, "grad_norm": 1.4312539100646973, "learning_rate": 9.61322182743687e-05, "loss": 0.4985939025878906, "step": 299950 }, { "epoch": 1.783024531745041, "grad_norm": 1.5172563791275024, "learning_rate": 9.612606787836906e-05, "loss": 0.5366413593292236, "step": 299960 }, { "epoch": 1.7830839738217095, "grad_norm": 1.4708675146102905, "learning_rate": 9.611991754873775e-05, "loss": 0.529477596282959, "step": 299970 }, { "epoch": 1.7831434158983779, "grad_norm": 1.802283763885498, "learning_rate": 9.611376728550421e-05, "loss": 0.5906999588012696, "step": 299980 }, { "epoch": 1.7832028579750463, "grad_norm": 1.6834312677383423, "learning_rate": 9.610761708869784e-05, "loss": 0.6491504669189453, "step": 299990 }, { "epoch": 1.7832623000517147, "grad_norm": 1.8679077625274658, "learning_rate": 9.610146695834812e-05, "loss": 0.6015003204345704, "step": 300000 }, { "epoch": 1.7833217421283831, "grad_norm": 1.5962610244750977, "learning_rate": 9.609531689448443e-05, "loss": 0.5681244850158691, "step": 300010 }, { "epoch": 1.7833811842050515, "grad_norm": 1.4555529356002808, "learning_rate": 9.608916689713619e-05, "loss": 0.5642837047576904, "step": 300020 }, { "epoch": 1.7834406262817197, "grad_norm": 1.3277865648269653, "learning_rate": 9.608301696633283e-05, "loss": 0.5496213912963868, "step": 300030 }, { "epoch": 1.7835000683583881, "grad_norm": 1.3152978420257568, "learning_rate": 9.60768671021038e-05, "loss": 0.5428462028503418, "step": 300040 }, { "epoch": 1.7835595104350566, "grad_norm": 1.6052685976028442, "learning_rate": 9.607071730447845e-05, "loss": 0.5743446350097656, "step": 300050 }, { "epoch": 1.783618952511725, "grad_norm": 1.4389278888702393, "learning_rate": 9.606456757348625e-05, "loss": 0.5448325157165528, "step": 300060 }, { "epoch": 1.7836783945883934, "grad_norm": 1.2836127281188965, "learning_rate": 9.605841790915662e-05, "loss": 0.5550179481506348, "step": 300070 }, { "epoch": 1.7837378366650616, "grad_norm": 1.7753534317016602, "learning_rate": 9.605226831151897e-05, "loss": 0.5736117839813233, "step": 300080 }, { "epoch": 1.78379727874173, "grad_norm": 1.660054326057434, "learning_rate": 9.604611878060266e-05, "loss": 0.578102970123291, "step": 300090 }, { "epoch": 1.7838567208183984, "grad_norm": 1.4089868068695068, "learning_rate": 9.60399693164372e-05, "loss": 0.48770747184753416, "step": 300100 }, { "epoch": 1.7839161628950668, "grad_norm": 1.5039761066436768, "learning_rate": 9.603381991905196e-05, "loss": 0.5158346652984619, "step": 300110 }, { "epoch": 1.7839756049717352, "grad_norm": 1.6420010328292847, "learning_rate": 9.602767058847633e-05, "loss": 0.6199268341064453, "step": 300120 }, { "epoch": 1.7840350470484037, "grad_norm": 1.31698477268219, "learning_rate": 9.602152132473979e-05, "loss": 0.5591065406799316, "step": 300130 }, { "epoch": 1.784094489125072, "grad_norm": 1.3664116859436035, "learning_rate": 9.601537212787172e-05, "loss": 0.5326366424560547, "step": 300140 }, { "epoch": 1.7841539312017405, "grad_norm": 1.5659146308898926, "learning_rate": 9.600922299790151e-05, "loss": 0.5452781677246094, "step": 300150 }, { "epoch": 1.784213373278409, "grad_norm": 1.0712662935256958, "learning_rate": 9.600307393485865e-05, "loss": 0.5526972770690918, "step": 300160 }, { "epoch": 1.7842728153550773, "grad_norm": 1.2094504833221436, "learning_rate": 9.59969249387725e-05, "loss": 0.5287659645080567, "step": 300170 }, { "epoch": 1.7843322574317457, "grad_norm": 1.727512240409851, "learning_rate": 9.599077600967246e-05, "loss": 0.5201548576354981, "step": 300180 }, { "epoch": 1.7843916995084141, "grad_norm": 1.6041971445083618, "learning_rate": 9.598462714758798e-05, "loss": 0.65223388671875, "step": 300190 }, { "epoch": 1.7844511415850826, "grad_norm": 1.6420488357543945, "learning_rate": 9.597847835254847e-05, "loss": 0.5366810321807861, "step": 300200 }, { "epoch": 1.784510583661751, "grad_norm": 1.5504907369613647, "learning_rate": 9.597232962458333e-05, "loss": 0.5265735626220703, "step": 300210 }, { "epoch": 1.7845700257384192, "grad_norm": 1.6384367942810059, "learning_rate": 9.596618096372199e-05, "loss": 0.57386474609375, "step": 300220 }, { "epoch": 1.7846294678150876, "grad_norm": 1.201690912246704, "learning_rate": 9.596003236999385e-05, "loss": 0.5270082473754882, "step": 300230 }, { "epoch": 1.784688909891756, "grad_norm": 1.3253059387207031, "learning_rate": 9.595388384342834e-05, "loss": 0.515391731262207, "step": 300240 }, { "epoch": 1.7847483519684244, "grad_norm": 1.170188546180725, "learning_rate": 9.594773538405482e-05, "loss": 0.5053139686584472, "step": 300250 }, { "epoch": 1.7848077940450926, "grad_norm": 1.5925291776657104, "learning_rate": 9.594158699190277e-05, "loss": 0.5440252304077149, "step": 300260 }, { "epoch": 1.784867236121761, "grad_norm": 1.4434032440185547, "learning_rate": 9.593543866700159e-05, "loss": 0.5430560111999512, "step": 300270 }, { "epoch": 1.7849266781984294, "grad_norm": 1.0292173624038696, "learning_rate": 9.592929040938063e-05, "loss": 0.5337605476379395, "step": 300280 }, { "epoch": 1.7849861202750978, "grad_norm": 1.512534260749817, "learning_rate": 9.592314221906938e-05, "loss": 0.583369779586792, "step": 300290 }, { "epoch": 1.7850455623517663, "grad_norm": 1.569003939628601, "learning_rate": 9.591699409609722e-05, "loss": 0.5585705757141113, "step": 300300 }, { "epoch": 1.7851050044284347, "grad_norm": 1.2215818166732788, "learning_rate": 9.591084604049354e-05, "loss": 0.5558306694030761, "step": 300310 }, { "epoch": 1.785164446505103, "grad_norm": 1.5168853998184204, "learning_rate": 9.590469805228776e-05, "loss": 0.5506465911865235, "step": 300320 }, { "epoch": 1.7852238885817715, "grad_norm": 1.595482349395752, "learning_rate": 9.589855013150933e-05, "loss": 0.5815914630889892, "step": 300330 }, { "epoch": 1.78528333065844, "grad_norm": 1.3973561525344849, "learning_rate": 9.589240227818763e-05, "loss": 0.5085118293762207, "step": 300340 }, { "epoch": 1.7853427727351083, "grad_norm": 1.28758704662323, "learning_rate": 9.588625449235202e-05, "loss": 0.5435240268707275, "step": 300350 }, { "epoch": 1.7854022148117767, "grad_norm": 1.2179430723190308, "learning_rate": 9.588010677403198e-05, "loss": 0.5426631927490234, "step": 300360 }, { "epoch": 1.7854616568884452, "grad_norm": 1.242856740951538, "learning_rate": 9.587395912325694e-05, "loss": 0.5200140476226807, "step": 300370 }, { "epoch": 1.7855210989651136, "grad_norm": 1.3339667320251465, "learning_rate": 9.586781154005618e-05, "loss": 0.5465244293212891, "step": 300380 }, { "epoch": 1.785580541041782, "grad_norm": 1.5430576801300049, "learning_rate": 9.586166402445925e-05, "loss": 0.5574018478393554, "step": 300390 }, { "epoch": 1.7856399831184502, "grad_norm": 1.4538476467132568, "learning_rate": 9.58555165764955e-05, "loss": 0.5267162322998047, "step": 300400 }, { "epoch": 1.7856994251951186, "grad_norm": 1.238511085510254, "learning_rate": 9.58493691961943e-05, "loss": 0.5248920917510986, "step": 300410 }, { "epoch": 1.785758867271787, "grad_norm": 1.1970545053482056, "learning_rate": 9.58432218835851e-05, "loss": 0.564837646484375, "step": 300420 }, { "epoch": 1.7858183093484554, "grad_norm": 1.6323356628417969, "learning_rate": 9.583707463869733e-05, "loss": 0.5045464038848877, "step": 300430 }, { "epoch": 1.7858777514251238, "grad_norm": 1.4631626605987549, "learning_rate": 9.58309274615603e-05, "loss": 0.5003554344177246, "step": 300440 }, { "epoch": 1.785937193501792, "grad_norm": 1.052960753440857, "learning_rate": 9.582478035220357e-05, "loss": 0.5405117988586425, "step": 300450 }, { "epoch": 1.7859966355784604, "grad_norm": 1.4070770740509033, "learning_rate": 9.581863331065641e-05, "loss": 0.6003475189208984, "step": 300460 }, { "epoch": 1.7860560776551289, "grad_norm": 1.3228087425231934, "learning_rate": 9.58124863369483e-05, "loss": 0.4788508415222168, "step": 300470 }, { "epoch": 1.7861155197317973, "grad_norm": 1.324404239654541, "learning_rate": 9.58063394311086e-05, "loss": 0.534100866317749, "step": 300480 }, { "epoch": 1.7861749618084657, "grad_norm": 1.2091363668441772, "learning_rate": 9.580019259316673e-05, "loss": 0.5032752990722656, "step": 300490 }, { "epoch": 1.786234403885134, "grad_norm": 1.6688889265060425, "learning_rate": 9.57940458231521e-05, "loss": 0.5419189453125, "step": 300500 }, { "epoch": 1.7862938459618025, "grad_norm": 1.2440932989120483, "learning_rate": 9.578789912109412e-05, "loss": 0.5458780288696289, "step": 300510 }, { "epoch": 1.786353288038471, "grad_norm": 1.1350444555282593, "learning_rate": 9.578175248702217e-05, "loss": 0.5126165866851806, "step": 300520 }, { "epoch": 1.7864127301151393, "grad_norm": 1.3558355569839478, "learning_rate": 9.577560592096569e-05, "loss": 0.4738271713256836, "step": 300530 }, { "epoch": 1.7864721721918078, "grad_norm": 1.3994430303573608, "learning_rate": 9.576945942295404e-05, "loss": 0.5698700904846191, "step": 300540 }, { "epoch": 1.7865316142684762, "grad_norm": 1.1871403455734253, "learning_rate": 9.576331299301666e-05, "loss": 0.577329158782959, "step": 300550 }, { "epoch": 1.7865910563451446, "grad_norm": 1.2080997228622437, "learning_rate": 9.575716663118294e-05, "loss": 0.5695716381072998, "step": 300560 }, { "epoch": 1.786650498421813, "grad_norm": 1.51784348487854, "learning_rate": 9.57510203374823e-05, "loss": 0.5639503955841064, "step": 300570 }, { "epoch": 1.7867099404984814, "grad_norm": 1.2013976573944092, "learning_rate": 9.574487411194408e-05, "loss": 0.581218671798706, "step": 300580 }, { "epoch": 1.7867693825751496, "grad_norm": 2.202000379562378, "learning_rate": 9.573872795459775e-05, "loss": 0.5909456253051758, "step": 300590 }, { "epoch": 1.786828824651818, "grad_norm": 1.2104337215423584, "learning_rate": 9.57325818654727e-05, "loss": 0.5762785911560059, "step": 300600 }, { "epoch": 1.7868882667284864, "grad_norm": 1.9587996006011963, "learning_rate": 9.572643584459826e-05, "loss": 0.6344820499420166, "step": 300610 }, { "epoch": 1.7869477088051549, "grad_norm": 1.4280948638916016, "learning_rate": 9.572028989200393e-05, "loss": 0.558498477935791, "step": 300620 }, { "epoch": 1.787007150881823, "grad_norm": 1.3746657371520996, "learning_rate": 9.571414400771905e-05, "loss": 0.5793613433837891, "step": 300630 }, { "epoch": 1.7870665929584915, "grad_norm": 1.248482584953308, "learning_rate": 9.570799819177302e-05, "loss": 0.573945951461792, "step": 300640 }, { "epoch": 1.7871260350351599, "grad_norm": 1.5357673168182373, "learning_rate": 9.57018524441953e-05, "loss": 0.544757604598999, "step": 300650 }, { "epoch": 1.7871854771118283, "grad_norm": 1.2897870540618896, "learning_rate": 9.569570676501523e-05, "loss": 0.5724387168884277, "step": 300660 }, { "epoch": 1.7872449191884967, "grad_norm": 1.3999266624450684, "learning_rate": 9.56895611542622e-05, "loss": 0.5684492111206054, "step": 300670 }, { "epoch": 1.7873043612651651, "grad_norm": 1.365878939628601, "learning_rate": 9.568341561196566e-05, "loss": 0.5459578037261963, "step": 300680 }, { "epoch": 1.7873638033418335, "grad_norm": 1.4382191896438599, "learning_rate": 9.567727013815497e-05, "loss": 0.5861118316650391, "step": 300690 }, { "epoch": 1.787423245418502, "grad_norm": 1.7236818075180054, "learning_rate": 9.567112473285955e-05, "loss": 0.5718882560729981, "step": 300700 }, { "epoch": 1.7874826874951704, "grad_norm": 1.5817848443984985, "learning_rate": 9.566497939610877e-05, "loss": 0.5560431480407715, "step": 300710 }, { "epoch": 1.7875421295718388, "grad_norm": 1.0335495471954346, "learning_rate": 9.565883412793203e-05, "loss": 0.5323889255523682, "step": 300720 }, { "epoch": 1.7876015716485072, "grad_norm": 1.5879091024398804, "learning_rate": 9.565268892835879e-05, "loss": 0.5934245586395264, "step": 300730 }, { "epoch": 1.7876610137251756, "grad_norm": 1.7224750518798828, "learning_rate": 9.564654379741835e-05, "loss": 0.6218655586242676, "step": 300740 }, { "epoch": 1.787720455801844, "grad_norm": 1.5393989086151123, "learning_rate": 9.564039873514019e-05, "loss": 0.5865442276000976, "step": 300750 }, { "epoch": 1.7877798978785124, "grad_norm": 1.483422040939331, "learning_rate": 9.563425374155366e-05, "loss": 0.6046746730804443, "step": 300760 }, { "epoch": 1.7878393399551806, "grad_norm": 1.794610857963562, "learning_rate": 9.562810881668814e-05, "loss": 0.5521409511566162, "step": 300770 }, { "epoch": 1.787898782031849, "grad_norm": 1.3593993186950684, "learning_rate": 9.562196396057308e-05, "loss": 0.5690888404846192, "step": 300780 }, { "epoch": 1.7879582241085175, "grad_norm": 1.8932615518569946, "learning_rate": 9.561581917323783e-05, "loss": 0.5373982429504395, "step": 300790 }, { "epoch": 1.7880176661851859, "grad_norm": 1.422506332397461, "learning_rate": 9.560967445471178e-05, "loss": 0.5837890625, "step": 300800 }, { "epoch": 1.7880771082618543, "grad_norm": 1.4811145067214966, "learning_rate": 9.560352980502438e-05, "loss": 0.5444839000701904, "step": 300810 }, { "epoch": 1.7881365503385225, "grad_norm": 1.4584078788757324, "learning_rate": 9.559738522420498e-05, "loss": 0.6076640605926513, "step": 300820 }, { "epoch": 1.788195992415191, "grad_norm": 1.5090737342834473, "learning_rate": 9.5591240712283e-05, "loss": 0.5346467971801758, "step": 300830 }, { "epoch": 1.7882554344918593, "grad_norm": 1.4503253698349, "learning_rate": 9.558509626928778e-05, "loss": 0.5949066162109375, "step": 300840 }, { "epoch": 1.7883148765685277, "grad_norm": 1.5259984731674194, "learning_rate": 9.557895189524877e-05, "loss": 0.5803046226501465, "step": 300850 }, { "epoch": 1.7883743186451961, "grad_norm": 1.3400795459747314, "learning_rate": 9.557280759019536e-05, "loss": 0.5748908042907714, "step": 300860 }, { "epoch": 1.7884337607218646, "grad_norm": 1.3468782901763916, "learning_rate": 9.556666335415686e-05, "loss": 0.5431149482727051, "step": 300870 }, { "epoch": 1.788493202798533, "grad_norm": 1.4473190307617188, "learning_rate": 9.556051918716277e-05, "loss": 0.5080484390258789, "step": 300880 }, { "epoch": 1.7885526448752014, "grad_norm": 1.5875850915908813, "learning_rate": 9.555437508924245e-05, "loss": 0.5488451004028321, "step": 300890 }, { "epoch": 1.7886120869518698, "grad_norm": 1.1343587636947632, "learning_rate": 9.554823106042523e-05, "loss": 0.5130125999450683, "step": 300900 }, { "epoch": 1.7886715290285382, "grad_norm": 1.7447426319122314, "learning_rate": 9.55420871007406e-05, "loss": 0.5564990043640137, "step": 300910 }, { "epoch": 1.7887309711052066, "grad_norm": 1.4805656671524048, "learning_rate": 9.553594321021791e-05, "loss": 0.5482743740081787, "step": 300920 }, { "epoch": 1.788790413181875, "grad_norm": 1.564814567565918, "learning_rate": 9.55297993888865e-05, "loss": 0.6139123916625977, "step": 300930 }, { "epoch": 1.7888498552585435, "grad_norm": 1.1623713970184326, "learning_rate": 9.552365563677579e-05, "loss": 0.5225115299224854, "step": 300940 }, { "epoch": 1.7889092973352119, "grad_norm": 1.5068525075912476, "learning_rate": 9.551751195391523e-05, "loss": 0.5597507953643799, "step": 300950 }, { "epoch": 1.78896873941188, "grad_norm": 1.209303379058838, "learning_rate": 9.551136834033415e-05, "loss": 0.515898609161377, "step": 300960 }, { "epoch": 1.7890281814885485, "grad_norm": 1.833802342414856, "learning_rate": 9.550522479606188e-05, "loss": 0.5587031841278076, "step": 300970 }, { "epoch": 1.789087623565217, "grad_norm": 1.387607216835022, "learning_rate": 9.549908132112795e-05, "loss": 0.5524966716766357, "step": 300980 }, { "epoch": 1.7891470656418853, "grad_norm": 1.2761192321777344, "learning_rate": 9.549293791556166e-05, "loss": 0.5676714897155761, "step": 300990 }, { "epoch": 1.7892065077185535, "grad_norm": 1.557556390762329, "learning_rate": 9.548679457939238e-05, "loss": 0.5679847717285156, "step": 301000 }, { "epoch": 1.789265949795222, "grad_norm": 1.1750332117080688, "learning_rate": 9.548065131264958e-05, "loss": 0.5036953449249267, "step": 301010 }, { "epoch": 1.7893253918718903, "grad_norm": 1.1516618728637695, "learning_rate": 9.54745081153626e-05, "loss": 0.5265859603881836, "step": 301020 }, { "epoch": 1.7893848339485587, "grad_norm": 1.1596300601959229, "learning_rate": 9.546836498756075e-05, "loss": 0.5636557579040528, "step": 301030 }, { "epoch": 1.7894442760252272, "grad_norm": 1.585919737815857, "learning_rate": 9.546222192927358e-05, "loss": 0.5557346343994141, "step": 301040 }, { "epoch": 1.7895037181018956, "grad_norm": 1.555881142616272, "learning_rate": 9.545607894053037e-05, "loss": 0.5309715270996094, "step": 301050 }, { "epoch": 1.789563160178564, "grad_norm": 1.3446643352508545, "learning_rate": 9.544993602136052e-05, "loss": 0.5408439636230469, "step": 301060 }, { "epoch": 1.7896226022552324, "grad_norm": 1.4704136848449707, "learning_rate": 9.544379317179341e-05, "loss": 0.5379644393920898, "step": 301070 }, { "epoch": 1.7896820443319008, "grad_norm": 1.3535990715026855, "learning_rate": 9.543765039185844e-05, "loss": 0.5669111251831055, "step": 301080 }, { "epoch": 1.7897414864085692, "grad_norm": 1.4553571939468384, "learning_rate": 9.543150768158499e-05, "loss": 0.5562955856323242, "step": 301090 }, { "epoch": 1.7898009284852376, "grad_norm": 1.3310648202896118, "learning_rate": 9.542536504100246e-05, "loss": 0.5675308227539062, "step": 301100 }, { "epoch": 1.789860370561906, "grad_norm": 1.2756820917129517, "learning_rate": 9.541922247014019e-05, "loss": 0.5352627754211425, "step": 301110 }, { "epoch": 1.7899198126385745, "grad_norm": 1.0278189182281494, "learning_rate": 9.541307996902762e-05, "loss": 0.5096123695373536, "step": 301120 }, { "epoch": 1.7899792547152429, "grad_norm": 1.503532886505127, "learning_rate": 9.54069375376941e-05, "loss": 0.5463647365570068, "step": 301130 }, { "epoch": 1.790038696791911, "grad_norm": 1.6256847381591797, "learning_rate": 9.540079517616904e-05, "loss": 0.5786244392395019, "step": 301140 }, { "epoch": 1.7900981388685795, "grad_norm": 1.392095923423767, "learning_rate": 9.539465288448178e-05, "loss": 0.543823528289795, "step": 301150 }, { "epoch": 1.790157580945248, "grad_norm": 1.502661108970642, "learning_rate": 9.538851066266172e-05, "loss": 0.580086612701416, "step": 301160 }, { "epoch": 1.7902170230219163, "grad_norm": 1.4422365427017212, "learning_rate": 9.538236851073827e-05, "loss": 0.5713924407958985, "step": 301170 }, { "epoch": 1.7902764650985847, "grad_norm": 1.7202931642532349, "learning_rate": 9.53762264287408e-05, "loss": 0.5613401412963868, "step": 301180 }, { "epoch": 1.790335907175253, "grad_norm": 1.5185248851776123, "learning_rate": 9.537008441669868e-05, "loss": 0.4851344108581543, "step": 301190 }, { "epoch": 1.7903953492519213, "grad_norm": 1.3605883121490479, "learning_rate": 9.536394247464129e-05, "loss": 0.6165874004364014, "step": 301200 }, { "epoch": 1.7904547913285898, "grad_norm": 1.561892032623291, "learning_rate": 9.5357800602598e-05, "loss": 0.51951003074646, "step": 301210 }, { "epoch": 1.7905142334052582, "grad_norm": 1.2175737619400024, "learning_rate": 9.535165880059824e-05, "loss": 0.5610254764556885, "step": 301220 }, { "epoch": 1.7905736754819266, "grad_norm": 1.5696154832839966, "learning_rate": 9.534551706867132e-05, "loss": 0.5796130180358887, "step": 301230 }, { "epoch": 1.790633117558595, "grad_norm": 1.6874369382858276, "learning_rate": 9.533937540684667e-05, "loss": 0.52019362449646, "step": 301240 }, { "epoch": 1.7906925596352634, "grad_norm": 1.2302465438842773, "learning_rate": 9.533323381515367e-05, "loss": 0.581008005142212, "step": 301250 }, { "epoch": 1.7907520017119318, "grad_norm": 1.1637479066848755, "learning_rate": 9.532709229362167e-05, "loss": 0.5270655632019043, "step": 301260 }, { "epoch": 1.7908114437886002, "grad_norm": 1.093201994895935, "learning_rate": 9.532095084228008e-05, "loss": 0.5485950469970703, "step": 301270 }, { "epoch": 1.7908708858652687, "grad_norm": 1.361655354499817, "learning_rate": 9.531480946115827e-05, "loss": 0.5262548923492432, "step": 301280 }, { "epoch": 1.790930327941937, "grad_norm": 1.4926127195358276, "learning_rate": 9.530866815028559e-05, "loss": 0.5228463649749756, "step": 301290 }, { "epoch": 1.7909897700186055, "grad_norm": 1.233916997909546, "learning_rate": 9.530252690969143e-05, "loss": 0.5403810501098633, "step": 301300 }, { "epoch": 1.791049212095274, "grad_norm": 2.2283201217651367, "learning_rate": 9.529638573940522e-05, "loss": 0.517463493347168, "step": 301310 }, { "epoch": 1.7911086541719423, "grad_norm": 1.4967666864395142, "learning_rate": 9.529024463945631e-05, "loss": 0.5790231704711915, "step": 301320 }, { "epoch": 1.7911680962486105, "grad_norm": 1.39528489112854, "learning_rate": 9.528410360987398e-05, "loss": 0.5267850875854492, "step": 301330 }, { "epoch": 1.791227538325279, "grad_norm": 1.1884742975234985, "learning_rate": 9.527796265068774e-05, "loss": 0.5481989860534668, "step": 301340 }, { "epoch": 1.7912869804019473, "grad_norm": 1.2009881734848022, "learning_rate": 9.527182176192693e-05, "loss": 0.512544822692871, "step": 301350 }, { "epoch": 1.7913464224786158, "grad_norm": 1.4561119079589844, "learning_rate": 9.526568094362087e-05, "loss": 0.49973354339599607, "step": 301360 }, { "epoch": 1.791405864555284, "grad_norm": 1.4741814136505127, "learning_rate": 9.525954019579899e-05, "loss": 0.5436338424682617, "step": 301370 }, { "epoch": 1.7914653066319524, "grad_norm": 1.474108338356018, "learning_rate": 9.525339951849068e-05, "loss": 0.5695067882537842, "step": 301380 }, { "epoch": 1.7915247487086208, "grad_norm": 1.3826723098754883, "learning_rate": 9.524725891172526e-05, "loss": 0.5313538074493408, "step": 301390 }, { "epoch": 1.7915841907852892, "grad_norm": 1.3252426385879517, "learning_rate": 9.524111837553213e-05, "loss": 0.5681881427764892, "step": 301400 }, { "epoch": 1.7916436328619576, "grad_norm": 0.9494209289550781, "learning_rate": 9.523497790994072e-05, "loss": 0.5504086494445801, "step": 301410 }, { "epoch": 1.791703074938626, "grad_norm": 1.1686358451843262, "learning_rate": 9.52288375149803e-05, "loss": 0.564751672744751, "step": 301420 }, { "epoch": 1.7917625170152944, "grad_norm": 1.5479615926742554, "learning_rate": 9.522269719068026e-05, "loss": 0.5474260330200196, "step": 301430 }, { "epoch": 1.7918219590919628, "grad_norm": 1.1841378211975098, "learning_rate": 9.521655693707007e-05, "loss": 0.552769136428833, "step": 301440 }, { "epoch": 1.7918814011686313, "grad_norm": 1.3806413412094116, "learning_rate": 9.521041675417905e-05, "loss": 0.5411859512329101, "step": 301450 }, { "epoch": 1.7919408432452997, "grad_norm": 1.1988133192062378, "learning_rate": 9.520427664203649e-05, "loss": 0.506104850769043, "step": 301460 }, { "epoch": 1.792000285321968, "grad_norm": 1.2480647563934326, "learning_rate": 9.51981366006719e-05, "loss": 0.5990735054016113, "step": 301470 }, { "epoch": 1.7920597273986365, "grad_norm": 1.4461185932159424, "learning_rate": 9.519199663011458e-05, "loss": 0.5249166488647461, "step": 301480 }, { "epoch": 1.792119169475305, "grad_norm": 1.1836810111999512, "learning_rate": 9.518585673039384e-05, "loss": 0.5751856327056885, "step": 301490 }, { "epoch": 1.7921786115519733, "grad_norm": 1.4797520637512207, "learning_rate": 9.517971690153922e-05, "loss": 0.5515649318695068, "step": 301500 }, { "epoch": 1.7922380536286415, "grad_norm": 1.6732889413833618, "learning_rate": 9.517357714357995e-05, "loss": 0.5816795825958252, "step": 301510 }, { "epoch": 1.79229749570531, "grad_norm": 1.4690765142440796, "learning_rate": 9.51674374565454e-05, "loss": 0.637198543548584, "step": 301520 }, { "epoch": 1.7923569377819784, "grad_norm": 1.0745184421539307, "learning_rate": 9.516129784046505e-05, "loss": 0.5544770240783692, "step": 301530 }, { "epoch": 1.7924163798586468, "grad_norm": 1.3884236812591553, "learning_rate": 9.515515829536817e-05, "loss": 0.5722679615020752, "step": 301540 }, { "epoch": 1.7924758219353152, "grad_norm": 1.9850239753723145, "learning_rate": 9.514901882128418e-05, "loss": 0.5431882858276367, "step": 301550 }, { "epoch": 1.7925352640119834, "grad_norm": 1.9839171171188354, "learning_rate": 9.514287941824237e-05, "loss": 0.4954081535339355, "step": 301560 }, { "epoch": 1.7925947060886518, "grad_norm": 1.4129639863967896, "learning_rate": 9.513674008627222e-05, "loss": 0.5726645469665528, "step": 301570 }, { "epoch": 1.7926541481653202, "grad_norm": 1.4586478471755981, "learning_rate": 9.513060082540307e-05, "loss": 0.5659762382507324, "step": 301580 }, { "epoch": 1.7927135902419886, "grad_norm": 1.4058749675750732, "learning_rate": 9.512446163566422e-05, "loss": 0.5564420700073243, "step": 301590 }, { "epoch": 1.792773032318657, "grad_norm": 1.0238434076309204, "learning_rate": 9.511832251708511e-05, "loss": 0.5358673095703125, "step": 301600 }, { "epoch": 1.7928324743953254, "grad_norm": 1.3554770946502686, "learning_rate": 9.511218346969506e-05, "loss": 0.49450254440307617, "step": 301610 }, { "epoch": 1.7928919164719939, "grad_norm": 1.2900882959365845, "learning_rate": 9.510604449352347e-05, "loss": 0.5903561592102051, "step": 301620 }, { "epoch": 1.7929513585486623, "grad_norm": 1.9746204614639282, "learning_rate": 9.509990558859969e-05, "loss": 0.5594133377075196, "step": 301630 }, { "epoch": 1.7930108006253307, "grad_norm": 1.4416990280151367, "learning_rate": 9.509376675495311e-05, "loss": 0.5387245178222656, "step": 301640 }, { "epoch": 1.793070242701999, "grad_norm": 1.4345073699951172, "learning_rate": 9.508762799261306e-05, "loss": 0.5045708656311035, "step": 301650 }, { "epoch": 1.7931296847786675, "grad_norm": 1.2521847486495972, "learning_rate": 9.508148930160892e-05, "loss": 0.5580890655517579, "step": 301660 }, { "epoch": 1.793189126855336, "grad_norm": 1.4521844387054443, "learning_rate": 9.507535068197008e-05, "loss": 0.5300976753234863, "step": 301670 }, { "epoch": 1.7932485689320043, "grad_norm": 1.2909654378890991, "learning_rate": 9.506921213372588e-05, "loss": 0.5515243530273437, "step": 301680 }, { "epoch": 1.7933080110086728, "grad_norm": 1.3115895986557007, "learning_rate": 9.506307365690568e-05, "loss": 0.5032559394836426, "step": 301690 }, { "epoch": 1.793367453085341, "grad_norm": 1.3357353210449219, "learning_rate": 9.505693525153887e-05, "loss": 0.5396537780761719, "step": 301700 }, { "epoch": 1.7934268951620094, "grad_norm": 1.331139087677002, "learning_rate": 9.50507969176548e-05, "loss": 0.536498737335205, "step": 301710 }, { "epoch": 1.7934863372386778, "grad_norm": 1.672200083732605, "learning_rate": 9.50446586552828e-05, "loss": 0.6097658157348633, "step": 301720 }, { "epoch": 1.7935457793153462, "grad_norm": 1.7537779808044434, "learning_rate": 9.503852046445229e-05, "loss": 0.5520052909851074, "step": 301730 }, { "epoch": 1.7936052213920144, "grad_norm": 1.5794199705123901, "learning_rate": 9.503238234519261e-05, "loss": 0.5146066665649414, "step": 301740 }, { "epoch": 1.7936646634686828, "grad_norm": 1.1583566665649414, "learning_rate": 9.502624429753308e-05, "loss": 0.5718683719635009, "step": 301750 }, { "epoch": 1.7937241055453512, "grad_norm": 1.2909998893737793, "learning_rate": 9.502010632150315e-05, "loss": 0.5602993488311767, "step": 301760 }, { "epoch": 1.7937835476220196, "grad_norm": 1.643916130065918, "learning_rate": 9.501396841713215e-05, "loss": 0.533406114578247, "step": 301770 }, { "epoch": 1.793842989698688, "grad_norm": 1.2963876724243164, "learning_rate": 9.50078305844494e-05, "loss": 0.6038653373718261, "step": 301780 }, { "epoch": 1.7939024317753565, "grad_norm": 1.7934967279434204, "learning_rate": 9.50016928234843e-05, "loss": 0.6666682243347168, "step": 301790 }, { "epoch": 1.7939618738520249, "grad_norm": 1.1181761026382446, "learning_rate": 9.499555513426619e-05, "loss": 0.5285689353942871, "step": 301800 }, { "epoch": 1.7940213159286933, "grad_norm": 1.477190375328064, "learning_rate": 9.498941751682444e-05, "loss": 0.5368492126464843, "step": 301810 }, { "epoch": 1.7940807580053617, "grad_norm": 1.2374703884124756, "learning_rate": 9.498327997118841e-05, "loss": 0.5584920883178711, "step": 301820 }, { "epoch": 1.7941402000820301, "grad_norm": 1.156118392944336, "learning_rate": 9.497714249738745e-05, "loss": 0.4911623477935791, "step": 301830 }, { "epoch": 1.7941996421586985, "grad_norm": 1.2730766534805298, "learning_rate": 9.497100509545097e-05, "loss": 0.5328910827636719, "step": 301840 }, { "epoch": 1.794259084235367, "grad_norm": 1.5554146766662598, "learning_rate": 9.496486776540824e-05, "loss": 0.5465169906616211, "step": 301850 }, { "epoch": 1.7943185263120354, "grad_norm": 1.1760567426681519, "learning_rate": 9.49587305072887e-05, "loss": 0.5131219863891602, "step": 301860 }, { "epoch": 1.7943779683887038, "grad_norm": 1.431280493736267, "learning_rate": 9.495259332112172e-05, "loss": 0.5763083457946777, "step": 301870 }, { "epoch": 1.794437410465372, "grad_norm": 1.4117752313613892, "learning_rate": 9.494645620693652e-05, "loss": 0.5708180427551269, "step": 301880 }, { "epoch": 1.7944968525420404, "grad_norm": 1.8963136672973633, "learning_rate": 9.494031916476261e-05, "loss": 0.5626991271972657, "step": 301890 }, { "epoch": 1.7945562946187088, "grad_norm": 1.3462841510772705, "learning_rate": 9.493418219462931e-05, "loss": 0.5305059432983399, "step": 301900 }, { "epoch": 1.7946157366953772, "grad_norm": 1.4194388389587402, "learning_rate": 9.492804529656593e-05, "loss": 0.5538776874542236, "step": 301910 }, { "epoch": 1.7946751787720456, "grad_norm": 1.4844993352890015, "learning_rate": 9.492190847060183e-05, "loss": 0.558245038986206, "step": 301920 }, { "epoch": 1.7947346208487138, "grad_norm": 1.1892321109771729, "learning_rate": 9.491577171676644e-05, "loss": 0.5327279090881347, "step": 301930 }, { "epoch": 1.7947940629253822, "grad_norm": 1.3624951839447021, "learning_rate": 9.490963503508907e-05, "loss": 0.5519095420837402, "step": 301940 }, { "epoch": 1.7948535050020507, "grad_norm": 1.4251939058303833, "learning_rate": 9.490349842559902e-05, "loss": 0.5711390495300293, "step": 301950 }, { "epoch": 1.794912947078719, "grad_norm": 1.5838830471038818, "learning_rate": 9.489736188832574e-05, "loss": 0.5772566795349121, "step": 301960 }, { "epoch": 1.7949723891553875, "grad_norm": 1.6305713653564453, "learning_rate": 9.489122542329855e-05, "loss": 0.48990325927734374, "step": 301970 }, { "epoch": 1.795031831232056, "grad_norm": 1.2018872499465942, "learning_rate": 9.488508903054675e-05, "loss": 0.5000299453735352, "step": 301980 }, { "epoch": 1.7950912733087243, "grad_norm": 1.4174611568450928, "learning_rate": 9.487895271009984e-05, "loss": 0.5726899147033692, "step": 301990 }, { "epoch": 1.7951507153853927, "grad_norm": 1.6219334602355957, "learning_rate": 9.487281646198703e-05, "loss": 0.5789271831512451, "step": 302000 }, { "epoch": 1.7952101574620611, "grad_norm": 1.2573972940444946, "learning_rate": 9.486668028623766e-05, "loss": 0.4865557670593262, "step": 302010 }, { "epoch": 1.7952695995387296, "grad_norm": 1.6742122173309326, "learning_rate": 9.486054418288123e-05, "loss": 0.5817849636077881, "step": 302020 }, { "epoch": 1.795329041615398, "grad_norm": 1.333642601966858, "learning_rate": 9.4854408151947e-05, "loss": 0.49915132522583006, "step": 302030 }, { "epoch": 1.7953884836920664, "grad_norm": 1.6394283771514893, "learning_rate": 9.48482721934643e-05, "loss": 0.5836656093597412, "step": 302040 }, { "epoch": 1.7954479257687348, "grad_norm": 1.1050113439559937, "learning_rate": 9.484213630746252e-05, "loss": 0.5484354019165039, "step": 302050 }, { "epoch": 1.7955073678454032, "grad_norm": 1.2056907415390015, "learning_rate": 9.4836000493971e-05, "loss": 0.46866602897644044, "step": 302060 }, { "epoch": 1.7955668099220714, "grad_norm": 1.6039034128189087, "learning_rate": 9.482986475301913e-05, "loss": 0.5956624031066895, "step": 302070 }, { "epoch": 1.7956262519987398, "grad_norm": 1.1857826709747314, "learning_rate": 9.48237290846362e-05, "loss": 0.5824489593505859, "step": 302080 }, { "epoch": 1.7956856940754082, "grad_norm": 1.3692058324813843, "learning_rate": 9.48175934888516e-05, "loss": 0.5418444633483886, "step": 302090 }, { "epoch": 1.7957451361520766, "grad_norm": 1.5241672992706299, "learning_rate": 9.481145796569469e-05, "loss": 0.5536499500274659, "step": 302100 }, { "epoch": 1.7958045782287448, "grad_norm": 1.9494930505752563, "learning_rate": 9.480532251519476e-05, "loss": 0.5792999267578125, "step": 302110 }, { "epoch": 1.7958640203054133, "grad_norm": 1.2981215715408325, "learning_rate": 9.479918713738123e-05, "loss": 0.54920654296875, "step": 302120 }, { "epoch": 1.7959234623820817, "grad_norm": 1.2921398878097534, "learning_rate": 9.479305183228342e-05, "loss": 0.5891207695007324, "step": 302130 }, { "epoch": 1.79598290445875, "grad_norm": 1.4626368284225464, "learning_rate": 9.478691659993066e-05, "loss": 0.5833171844482422, "step": 302140 }, { "epoch": 1.7960423465354185, "grad_norm": 1.2391129732131958, "learning_rate": 9.478078144035234e-05, "loss": 0.5400018692016602, "step": 302150 }, { "epoch": 1.796101788612087, "grad_norm": 1.2614312171936035, "learning_rate": 9.477464635357778e-05, "loss": 0.5537287712097168, "step": 302160 }, { "epoch": 1.7961612306887553, "grad_norm": 1.247902750968933, "learning_rate": 9.476851133963636e-05, "loss": 0.5671811103820801, "step": 302170 }, { "epoch": 1.7962206727654237, "grad_norm": 1.7256706953048706, "learning_rate": 9.476237639855737e-05, "loss": 0.5787179946899415, "step": 302180 }, { "epoch": 1.7962801148420922, "grad_norm": 1.5376825332641602, "learning_rate": 9.475624153037019e-05, "loss": 0.5633249759674073, "step": 302190 }, { "epoch": 1.7963395569187606, "grad_norm": 1.3605693578720093, "learning_rate": 9.475010673510421e-05, "loss": 0.5740918159484864, "step": 302200 }, { "epoch": 1.796398998995429, "grad_norm": 1.3263561725616455, "learning_rate": 9.474397201278868e-05, "loss": 0.5953206539154052, "step": 302210 }, { "epoch": 1.7964584410720974, "grad_norm": 1.7447761297225952, "learning_rate": 9.473783736345303e-05, "loss": 0.5377323150634765, "step": 302220 }, { "epoch": 1.7965178831487658, "grad_norm": 1.2275770902633667, "learning_rate": 9.47317027871266e-05, "loss": 0.512706995010376, "step": 302230 }, { "epoch": 1.7965773252254342, "grad_norm": 1.27019202709198, "learning_rate": 9.472556828383867e-05, "loss": 0.579526710510254, "step": 302240 }, { "epoch": 1.7966367673021024, "grad_norm": 1.6101704835891724, "learning_rate": 9.471943385361865e-05, "loss": 0.5604715824127198, "step": 302250 }, { "epoch": 1.7966962093787708, "grad_norm": 1.6116164922714233, "learning_rate": 9.471329949649588e-05, "loss": 0.536495590209961, "step": 302260 }, { "epoch": 1.7967556514554393, "grad_norm": 1.115606665611267, "learning_rate": 9.470716521249967e-05, "loss": 0.5280033111572265, "step": 302270 }, { "epoch": 1.7968150935321077, "grad_norm": 1.2052769660949707, "learning_rate": 9.47010310016594e-05, "loss": 0.5053488254547119, "step": 302280 }, { "epoch": 1.796874535608776, "grad_norm": 1.1833850145339966, "learning_rate": 9.46948968640044e-05, "loss": 0.5079183578491211, "step": 302290 }, { "epoch": 1.7969339776854443, "grad_norm": 1.595197319984436, "learning_rate": 9.468876279956398e-05, "loss": 0.5407559871673584, "step": 302300 }, { "epoch": 1.7969934197621127, "grad_norm": 1.4844081401824951, "learning_rate": 9.468262880836753e-05, "loss": 0.5863875389099121, "step": 302310 }, { "epoch": 1.797052861838781, "grad_norm": 1.2569314241409302, "learning_rate": 9.467649489044439e-05, "loss": 0.589116096496582, "step": 302320 }, { "epoch": 1.7971123039154495, "grad_norm": 1.491831660270691, "learning_rate": 9.46703610458239e-05, "loss": 0.5160971641540527, "step": 302330 }, { "epoch": 1.797171745992118, "grad_norm": 1.3239139318466187, "learning_rate": 9.466422727453535e-05, "loss": 0.5665657997131348, "step": 302340 }, { "epoch": 1.7972311880687863, "grad_norm": 1.500440001487732, "learning_rate": 9.465809357660816e-05, "loss": 0.559749698638916, "step": 302350 }, { "epoch": 1.7972906301454548, "grad_norm": 1.463427186012268, "learning_rate": 9.465195995207164e-05, "loss": 0.5998779296875, "step": 302360 }, { "epoch": 1.7973500722221232, "grad_norm": 1.4870976209640503, "learning_rate": 9.46458264009551e-05, "loss": 0.5609880447387695, "step": 302370 }, { "epoch": 1.7974095142987916, "grad_norm": 1.3490688800811768, "learning_rate": 9.463969292328792e-05, "loss": 0.559288740158081, "step": 302380 }, { "epoch": 1.79746895637546, "grad_norm": 1.2982226610183716, "learning_rate": 9.463355951909944e-05, "loss": 0.5334240436553955, "step": 302390 }, { "epoch": 1.7975283984521284, "grad_norm": 1.4215980768203735, "learning_rate": 9.462742618841902e-05, "loss": 0.5546666145324707, "step": 302400 }, { "epoch": 1.7975878405287968, "grad_norm": 1.3755930662155151, "learning_rate": 9.462129293127589e-05, "loss": 0.6179717540740967, "step": 302410 }, { "epoch": 1.7976472826054652, "grad_norm": 1.3424646854400635, "learning_rate": 9.461515974769953e-05, "loss": 0.5275753974914551, "step": 302420 }, { "epoch": 1.7977067246821337, "grad_norm": 1.3106838464736938, "learning_rate": 9.460902663771923e-05, "loss": 0.4855335235595703, "step": 302430 }, { "epoch": 1.7977661667588019, "grad_norm": 1.6787961721420288, "learning_rate": 9.460289360136422e-05, "loss": 0.5664547920227051, "step": 302440 }, { "epoch": 1.7978256088354703, "grad_norm": 1.502236247062683, "learning_rate": 9.459676063866403e-05, "loss": 0.5647860527038574, "step": 302450 }, { "epoch": 1.7978850509121387, "grad_norm": 1.6185094118118286, "learning_rate": 9.459062774964789e-05, "loss": 0.5501819133758545, "step": 302460 }, { "epoch": 1.797944492988807, "grad_norm": 1.5236881971359253, "learning_rate": 9.458449493434511e-05, "loss": 0.6095378398895264, "step": 302470 }, { "epoch": 1.7980039350654753, "grad_norm": 1.4208978414535522, "learning_rate": 9.457836219278511e-05, "loss": 0.5278386116027832, "step": 302480 }, { "epoch": 1.7980633771421437, "grad_norm": 1.7767250537872314, "learning_rate": 9.457222952499718e-05, "loss": 0.5575881004333496, "step": 302490 }, { "epoch": 1.7981228192188121, "grad_norm": 1.0294690132141113, "learning_rate": 9.456609693101061e-05, "loss": 0.5747645378112793, "step": 302500 }, { "epoch": 1.7981822612954805, "grad_norm": 1.684644103050232, "learning_rate": 9.455996441085486e-05, "loss": 0.6015151023864747, "step": 302510 }, { "epoch": 1.798241703372149, "grad_norm": 1.2511956691741943, "learning_rate": 9.455383196455918e-05, "loss": 0.47714948654174805, "step": 302520 }, { "epoch": 1.7983011454488174, "grad_norm": 1.2707628011703491, "learning_rate": 9.45476995921529e-05, "loss": 0.5340142250061035, "step": 302530 }, { "epoch": 1.7983605875254858, "grad_norm": 1.2581559419631958, "learning_rate": 9.454156729366537e-05, "loss": 0.5782530784606934, "step": 302540 }, { "epoch": 1.7984200296021542, "grad_norm": 1.1127915382385254, "learning_rate": 9.453543506912596e-05, "loss": 0.5871200084686279, "step": 302550 }, { "epoch": 1.7984794716788226, "grad_norm": 1.3304224014282227, "learning_rate": 9.452930291856395e-05, "loss": 0.55560302734375, "step": 302560 }, { "epoch": 1.798538913755491, "grad_norm": 1.4572793245315552, "learning_rate": 9.45231708420087e-05, "loss": 0.567262840270996, "step": 302570 }, { "epoch": 1.7985983558321594, "grad_norm": 1.3366972208023071, "learning_rate": 9.451703883948954e-05, "loss": 0.4795330047607422, "step": 302580 }, { "epoch": 1.7986577979088278, "grad_norm": 1.5159695148468018, "learning_rate": 9.451090691103581e-05, "loss": 0.5383305549621582, "step": 302590 }, { "epoch": 1.7987172399854963, "grad_norm": 1.228102207183838, "learning_rate": 9.450477505667685e-05, "loss": 0.5672893047332763, "step": 302600 }, { "epoch": 1.7987766820621647, "grad_norm": 1.522539734840393, "learning_rate": 9.449864327644198e-05, "loss": 0.6365654945373536, "step": 302610 }, { "epoch": 1.7988361241388329, "grad_norm": 1.6360626220703125, "learning_rate": 9.449251157036052e-05, "loss": 0.5420949935913086, "step": 302620 }, { "epoch": 1.7988955662155013, "grad_norm": 1.5388660430908203, "learning_rate": 9.448637993846184e-05, "loss": 0.5959084510803223, "step": 302630 }, { "epoch": 1.7989550082921697, "grad_norm": 1.8012555837631226, "learning_rate": 9.448024838077523e-05, "loss": 0.582365608215332, "step": 302640 }, { "epoch": 1.7990144503688381, "grad_norm": 1.5680123567581177, "learning_rate": 9.447411689733004e-05, "loss": 0.513024377822876, "step": 302650 }, { "epoch": 1.7990738924455065, "grad_norm": 1.5129542350769043, "learning_rate": 9.446798548815561e-05, "loss": 0.5771666526794433, "step": 302660 }, { "epoch": 1.7991333345221747, "grad_norm": 1.5205912590026855, "learning_rate": 9.446185415328124e-05, "loss": 0.5501341819763184, "step": 302670 }, { "epoch": 1.7991927765988431, "grad_norm": 1.3961420059204102, "learning_rate": 9.44557228927363e-05, "loss": 0.5588107585906983, "step": 302680 }, { "epoch": 1.7992522186755115, "grad_norm": 1.3110275268554688, "learning_rate": 9.444959170655012e-05, "loss": 0.5073009014129639, "step": 302690 }, { "epoch": 1.79931166075218, "grad_norm": 1.5283459424972534, "learning_rate": 9.444346059475197e-05, "loss": 0.5651761531829834, "step": 302700 }, { "epoch": 1.7993711028288484, "grad_norm": 1.2712297439575195, "learning_rate": 9.443732955737124e-05, "loss": 0.6062442779541015, "step": 302710 }, { "epoch": 1.7994305449055168, "grad_norm": 1.4258722066879272, "learning_rate": 9.443119859443726e-05, "loss": 0.5489509582519532, "step": 302720 }, { "epoch": 1.7994899869821852, "grad_norm": 1.2733283042907715, "learning_rate": 9.44250677059793e-05, "loss": 0.5585426330566406, "step": 302730 }, { "epoch": 1.7995494290588536, "grad_norm": 1.343804955482483, "learning_rate": 9.441893689202674e-05, "loss": 0.4831382751464844, "step": 302740 }, { "epoch": 1.799608871135522, "grad_norm": 1.606312870979309, "learning_rate": 9.441280615260892e-05, "loss": 0.5644532203674316, "step": 302750 }, { "epoch": 1.7996683132121905, "grad_norm": 1.3427820205688477, "learning_rate": 9.440667548775513e-05, "loss": 0.5456464767456055, "step": 302760 }, { "epoch": 1.7997277552888589, "grad_norm": 1.890735387802124, "learning_rate": 9.440054489749468e-05, "loss": 0.6013043403625489, "step": 302770 }, { "epoch": 1.7997871973655273, "grad_norm": 1.3991401195526123, "learning_rate": 9.439441438185697e-05, "loss": 0.5632179260253907, "step": 302780 }, { "epoch": 1.7998466394421957, "grad_norm": 1.3498743772506714, "learning_rate": 9.438828394087124e-05, "loss": 0.5337349891662597, "step": 302790 }, { "epoch": 1.799906081518864, "grad_norm": 1.3758337497711182, "learning_rate": 9.438215357456686e-05, "loss": 0.5641579627990723, "step": 302800 }, { "epoch": 1.7999655235955323, "grad_norm": 1.2645037174224854, "learning_rate": 9.437602328297317e-05, "loss": 0.5464101791381836, "step": 302810 }, { "epoch": 1.8000249656722007, "grad_norm": 1.384462833404541, "learning_rate": 9.43698930661195e-05, "loss": 0.5951545715332032, "step": 302820 }, { "epoch": 1.8000844077488691, "grad_norm": 1.2851892709732056, "learning_rate": 9.436376292403511e-05, "loss": 0.5737056255340576, "step": 302830 }, { "epoch": 1.8001438498255375, "grad_norm": 1.440300464630127, "learning_rate": 9.435763285674939e-05, "loss": 0.5398773193359375, "step": 302840 }, { "epoch": 1.8002032919022057, "grad_norm": 1.071563720703125, "learning_rate": 9.435150286429163e-05, "loss": 0.5528968334197998, "step": 302850 }, { "epoch": 1.8002627339788742, "grad_norm": 1.2389661073684692, "learning_rate": 9.434537294669117e-05, "loss": 0.5480984210968017, "step": 302860 }, { "epoch": 1.8003221760555426, "grad_norm": 1.1102603673934937, "learning_rate": 9.433924310397734e-05, "loss": 0.46275968551635743, "step": 302870 }, { "epoch": 1.800381618132211, "grad_norm": 1.6809653043746948, "learning_rate": 9.433311333617946e-05, "loss": 0.5537120819091796, "step": 302880 }, { "epoch": 1.8004410602088794, "grad_norm": 1.147914171218872, "learning_rate": 9.432698364332686e-05, "loss": 0.5572720050811768, "step": 302890 }, { "epoch": 1.8005005022855478, "grad_norm": 1.2606555223464966, "learning_rate": 9.43208540254488e-05, "loss": 0.5182552337646484, "step": 302900 }, { "epoch": 1.8005599443622162, "grad_norm": 1.8697659969329834, "learning_rate": 9.431472448257467e-05, "loss": 0.5618637084960938, "step": 302910 }, { "epoch": 1.8006193864388846, "grad_norm": 1.3731484413146973, "learning_rate": 9.430859501473382e-05, "loss": 0.5700745582580566, "step": 302920 }, { "epoch": 1.800678828515553, "grad_norm": 1.287672758102417, "learning_rate": 9.430246562195544e-05, "loss": 0.6095528125762939, "step": 302930 }, { "epoch": 1.8007382705922215, "grad_norm": 1.7038038969039917, "learning_rate": 9.429633630426897e-05, "loss": 0.5993450164794922, "step": 302940 }, { "epoch": 1.8007977126688899, "grad_norm": 1.6593436002731323, "learning_rate": 9.429020706170373e-05, "loss": 0.5475207328796386, "step": 302950 }, { "epoch": 1.8008571547455583, "grad_norm": 1.1588181257247925, "learning_rate": 9.428407789428893e-05, "loss": 0.5397520542144776, "step": 302960 }, { "epoch": 1.8009165968222267, "grad_norm": 1.4789111614227295, "learning_rate": 9.427794880205403e-05, "loss": 0.5711138725280762, "step": 302970 }, { "epoch": 1.8009760388988951, "grad_norm": 1.2241802215576172, "learning_rate": 9.427181978502828e-05, "loss": 0.5611044883728027, "step": 302980 }, { "epoch": 1.8010354809755633, "grad_norm": 1.6803117990493774, "learning_rate": 9.426569084324095e-05, "loss": 0.5458238601684571, "step": 302990 }, { "epoch": 1.8010949230522317, "grad_norm": 1.388306975364685, "learning_rate": 9.425956197672146e-05, "loss": 0.5721311569213867, "step": 303000 }, { "epoch": 1.8011543651289001, "grad_norm": 1.029105544090271, "learning_rate": 9.42534331854991e-05, "loss": 0.5170088291168213, "step": 303010 }, { "epoch": 1.8012138072055686, "grad_norm": 1.588582992553711, "learning_rate": 9.424730446960314e-05, "loss": 0.5712133407592773, "step": 303020 }, { "epoch": 1.801273249282237, "grad_norm": 2.14359188079834, "learning_rate": 9.42411758290629e-05, "loss": 0.5755771160125732, "step": 303030 }, { "epoch": 1.8013326913589052, "grad_norm": 1.5907729864120483, "learning_rate": 9.423504726390779e-05, "loss": 0.5598457336425782, "step": 303040 }, { "epoch": 1.8013921334355736, "grad_norm": 1.536057710647583, "learning_rate": 9.422891877416702e-05, "loss": 0.5941375255584717, "step": 303050 }, { "epoch": 1.801451575512242, "grad_norm": 1.643040418624878, "learning_rate": 9.422279035986994e-05, "loss": 0.5065075874328613, "step": 303060 }, { "epoch": 1.8015110175889104, "grad_norm": 1.8586264848709106, "learning_rate": 9.421666202104591e-05, "loss": 0.5491640090942382, "step": 303070 }, { "epoch": 1.8015704596655788, "grad_norm": 1.6123565435409546, "learning_rate": 9.42105337577242e-05, "loss": 0.5792274475097656, "step": 303080 }, { "epoch": 1.8016299017422472, "grad_norm": 1.3533267974853516, "learning_rate": 9.420440556993409e-05, "loss": 0.5695186614990234, "step": 303090 }, { "epoch": 1.8016893438189157, "grad_norm": 1.5984381437301636, "learning_rate": 9.4198277457705e-05, "loss": 0.5267822742462158, "step": 303100 }, { "epoch": 1.801748785895584, "grad_norm": 1.631880521774292, "learning_rate": 9.419214942106617e-05, "loss": 0.5929388999938965, "step": 303110 }, { "epoch": 1.8018082279722525, "grad_norm": 1.5496845245361328, "learning_rate": 9.418602146004694e-05, "loss": 0.5598408222198487, "step": 303120 }, { "epoch": 1.801867670048921, "grad_norm": 1.7731726169586182, "learning_rate": 9.417989357467658e-05, "loss": 0.5757782936096192, "step": 303130 }, { "epoch": 1.8019271121255893, "grad_norm": 1.3822497129440308, "learning_rate": 9.417376576498447e-05, "loss": 0.617471981048584, "step": 303140 }, { "epoch": 1.8019865542022577, "grad_norm": 1.8241205215454102, "learning_rate": 9.416763803099988e-05, "loss": 0.596359395980835, "step": 303150 }, { "epoch": 1.8020459962789261, "grad_norm": 1.366674542427063, "learning_rate": 9.416151037275214e-05, "loss": 0.5563687801361084, "step": 303160 }, { "epoch": 1.8021054383555943, "grad_norm": 1.72287917137146, "learning_rate": 9.415538279027056e-05, "loss": 0.5922897815704345, "step": 303170 }, { "epoch": 1.8021648804322628, "grad_norm": 1.6009362936019897, "learning_rate": 9.414925528358444e-05, "loss": 0.5778591632843018, "step": 303180 }, { "epoch": 1.8022243225089312, "grad_norm": 1.249298095703125, "learning_rate": 9.41431278527231e-05, "loss": 0.5818287849426269, "step": 303190 }, { "epoch": 1.8022837645855996, "grad_norm": 1.5243932008743286, "learning_rate": 9.413700049771588e-05, "loss": 0.5409992694854736, "step": 303200 }, { "epoch": 1.802343206662268, "grad_norm": 2.4124553203582764, "learning_rate": 9.413087321859206e-05, "loss": 0.5182496070861816, "step": 303210 }, { "epoch": 1.8024026487389362, "grad_norm": 1.3337876796722412, "learning_rate": 9.412474601538092e-05, "loss": 0.5638219833374023, "step": 303220 }, { "epoch": 1.8024620908156046, "grad_norm": 1.5247564315795898, "learning_rate": 9.411861888811187e-05, "loss": 0.5752792358398438, "step": 303230 }, { "epoch": 1.802521532892273, "grad_norm": 1.004650354385376, "learning_rate": 9.41124918368141e-05, "loss": 0.5130294322967529, "step": 303240 }, { "epoch": 1.8025809749689414, "grad_norm": 1.2936921119689941, "learning_rate": 9.4106364861517e-05, "loss": 0.5954327583312988, "step": 303250 }, { "epoch": 1.8026404170456098, "grad_norm": 1.3487533330917358, "learning_rate": 9.410023796224985e-05, "loss": 0.5917046546936036, "step": 303260 }, { "epoch": 1.8026998591222783, "grad_norm": 1.316482424736023, "learning_rate": 9.409411113904199e-05, "loss": 0.558184289932251, "step": 303270 }, { "epoch": 1.8027593011989467, "grad_norm": 1.3786851167678833, "learning_rate": 9.408798439192268e-05, "loss": 0.5330995082855224, "step": 303280 }, { "epoch": 1.802818743275615, "grad_norm": 0.9598785638809204, "learning_rate": 9.408185772092123e-05, "loss": 0.5213490486145019, "step": 303290 }, { "epoch": 1.8028781853522835, "grad_norm": 1.3485697507858276, "learning_rate": 9.407573112606702e-05, "loss": 0.4967754364013672, "step": 303300 }, { "epoch": 1.802937627428952, "grad_norm": 1.1532436609268188, "learning_rate": 9.40696046073893e-05, "loss": 0.5016147136688233, "step": 303310 }, { "epoch": 1.8029970695056203, "grad_norm": 1.3898780345916748, "learning_rate": 9.406347816491734e-05, "loss": 0.5096593856811523, "step": 303320 }, { "epoch": 1.8030565115822887, "grad_norm": 1.472680687904358, "learning_rate": 9.405735179868054e-05, "loss": 0.5620316505432129, "step": 303330 }, { "epoch": 1.8031159536589572, "grad_norm": 1.405466914176941, "learning_rate": 9.405122550870815e-05, "loss": 0.5307300567626954, "step": 303340 }, { "epoch": 1.8031753957356256, "grad_norm": 1.428192138671875, "learning_rate": 9.404509929502945e-05, "loss": 0.5268570899963378, "step": 303350 }, { "epoch": 1.8032348378122938, "grad_norm": 1.1420849561691284, "learning_rate": 9.403897315767383e-05, "loss": 0.6166130065917969, "step": 303360 }, { "epoch": 1.8032942798889622, "grad_norm": 1.4567617177963257, "learning_rate": 9.403284709667053e-05, "loss": 0.5897004127502441, "step": 303370 }, { "epoch": 1.8033537219656306, "grad_norm": 1.4401839971542358, "learning_rate": 9.402672111204888e-05, "loss": 0.5372082710266113, "step": 303380 }, { "epoch": 1.803413164042299, "grad_norm": 1.477290153503418, "learning_rate": 9.402059520383812e-05, "loss": 0.552799129486084, "step": 303390 }, { "epoch": 1.8034726061189674, "grad_norm": 1.5729221105575562, "learning_rate": 9.401446937206766e-05, "loss": 0.6271584033966064, "step": 303400 }, { "epoch": 1.8035320481956356, "grad_norm": 1.2374780178070068, "learning_rate": 9.400834361676678e-05, "loss": 0.48376879692077634, "step": 303410 }, { "epoch": 1.803591490272304, "grad_norm": 1.7504652738571167, "learning_rate": 9.400221793796468e-05, "loss": 0.5763871669769287, "step": 303420 }, { "epoch": 1.8036509323489724, "grad_norm": 1.7954950332641602, "learning_rate": 9.39960923356908e-05, "loss": 0.5509349822998046, "step": 303430 }, { "epoch": 1.8037103744256409, "grad_norm": 0.9276940822601318, "learning_rate": 9.398996680997439e-05, "loss": 0.513211727142334, "step": 303440 }, { "epoch": 1.8037698165023093, "grad_norm": 1.6568244695663452, "learning_rate": 9.398384136084471e-05, "loss": 0.5905274868011474, "step": 303450 }, { "epoch": 1.8038292585789777, "grad_norm": 1.597590684890747, "learning_rate": 9.397771598833112e-05, "loss": 0.5351822376251221, "step": 303460 }, { "epoch": 1.803888700655646, "grad_norm": 1.5442756414413452, "learning_rate": 9.39715906924629e-05, "loss": 0.5553271293640136, "step": 303470 }, { "epoch": 1.8039481427323145, "grad_norm": 1.1848318576812744, "learning_rate": 9.396546547326932e-05, "loss": 0.5421070575714111, "step": 303480 }, { "epoch": 1.804007584808983, "grad_norm": 1.3343217372894287, "learning_rate": 9.395934033077975e-05, "loss": 0.5790365219116211, "step": 303490 }, { "epoch": 1.8040670268856513, "grad_norm": 1.6489146947860718, "learning_rate": 9.395321526502347e-05, "loss": 0.5078860759735108, "step": 303500 }, { "epoch": 1.8041264689623198, "grad_norm": 1.4757153987884521, "learning_rate": 9.394709027602975e-05, "loss": 0.5239032745361328, "step": 303510 }, { "epoch": 1.8041859110389882, "grad_norm": 1.7725635766983032, "learning_rate": 9.394096536382786e-05, "loss": 0.5734616756439209, "step": 303520 }, { "epoch": 1.8042453531156566, "grad_norm": 1.650883436203003, "learning_rate": 9.393484052844719e-05, "loss": 0.609478759765625, "step": 303530 }, { "epoch": 1.8043047951923248, "grad_norm": 1.735641360282898, "learning_rate": 9.3928715769917e-05, "loss": 0.5471631050109863, "step": 303540 }, { "epoch": 1.8043642372689932, "grad_norm": 1.3390140533447266, "learning_rate": 9.392259108826653e-05, "loss": 0.5684660911560059, "step": 303550 }, { "epoch": 1.8044236793456616, "grad_norm": 1.3518474102020264, "learning_rate": 9.391646648352519e-05, "loss": 0.56845703125, "step": 303560 }, { "epoch": 1.80448312142233, "grad_norm": 1.7376261949539185, "learning_rate": 9.391034195572219e-05, "loss": 0.6001924991607666, "step": 303570 }, { "epoch": 1.8045425634989984, "grad_norm": 1.5823241472244263, "learning_rate": 9.390421750488682e-05, "loss": 0.5717913627624511, "step": 303580 }, { "epoch": 1.8046020055756666, "grad_norm": 1.3221420049667358, "learning_rate": 9.389809313104847e-05, "loss": 0.5745023727416992, "step": 303590 }, { "epoch": 1.804661447652335, "grad_norm": 1.126617431640625, "learning_rate": 9.389196883423636e-05, "loss": 0.5330020427703858, "step": 303600 }, { "epoch": 1.8047208897290035, "grad_norm": 1.7395577430725098, "learning_rate": 9.38858446144798e-05, "loss": 0.5827743530273437, "step": 303610 }, { "epoch": 1.8047803318056719, "grad_norm": 1.1713517904281616, "learning_rate": 9.387972047180808e-05, "loss": 0.5565366744995117, "step": 303620 }, { "epoch": 1.8048397738823403, "grad_norm": 1.5621118545532227, "learning_rate": 9.387359640625056e-05, "loss": 0.5148579597473144, "step": 303630 }, { "epoch": 1.8048992159590087, "grad_norm": 1.3542066812515259, "learning_rate": 9.386747241783645e-05, "loss": 0.5580934047698974, "step": 303640 }, { "epoch": 1.8049586580356771, "grad_norm": 1.2452994585037231, "learning_rate": 9.386134850659507e-05, "loss": 0.533994483947754, "step": 303650 }, { "epoch": 1.8050181001123455, "grad_norm": 1.399221420288086, "learning_rate": 9.385522467255574e-05, "loss": 0.6136545181274414, "step": 303660 }, { "epoch": 1.805077542189014, "grad_norm": 1.5774997472763062, "learning_rate": 9.384910091574774e-05, "loss": 0.5502806186676026, "step": 303670 }, { "epoch": 1.8051369842656824, "grad_norm": 1.7311171293258667, "learning_rate": 9.384297723620034e-05, "loss": 0.5257543563842774, "step": 303680 }, { "epoch": 1.8051964263423508, "grad_norm": 1.0689592361450195, "learning_rate": 9.383685363394288e-05, "loss": 0.5336950302124024, "step": 303690 }, { "epoch": 1.8052558684190192, "grad_norm": 1.0583666563034058, "learning_rate": 9.383073010900465e-05, "loss": 0.5691698551177978, "step": 303700 }, { "epoch": 1.8053153104956876, "grad_norm": 1.2093229293823242, "learning_rate": 9.382460666141489e-05, "loss": 0.5483885288238526, "step": 303710 }, { "epoch": 1.805374752572356, "grad_norm": 1.8152190446853638, "learning_rate": 9.381848329120293e-05, "loss": 0.6351469993591309, "step": 303720 }, { "epoch": 1.8054341946490242, "grad_norm": 2.1312992572784424, "learning_rate": 9.381235999839806e-05, "loss": 0.5682674884796143, "step": 303730 }, { "epoch": 1.8054936367256926, "grad_norm": 4.152660369873047, "learning_rate": 9.380623678302957e-05, "loss": 0.5044230461120606, "step": 303740 }, { "epoch": 1.805553078802361, "grad_norm": 1.188145637512207, "learning_rate": 9.380011364512675e-05, "loss": 0.5595145225524902, "step": 303750 }, { "epoch": 1.8056125208790295, "grad_norm": 1.6771299839019775, "learning_rate": 9.37939905847189e-05, "loss": 0.5683166980743408, "step": 303760 }, { "epoch": 1.8056719629556979, "grad_norm": 1.1470404863357544, "learning_rate": 9.37878676018353e-05, "loss": 0.5546793460845947, "step": 303770 }, { "epoch": 1.805731405032366, "grad_norm": 1.5261894464492798, "learning_rate": 9.378174469650523e-05, "loss": 0.5665587425231934, "step": 303780 }, { "epoch": 1.8057908471090345, "grad_norm": 1.3580830097198486, "learning_rate": 9.377562186875802e-05, "loss": 0.5395751953125, "step": 303790 }, { "epoch": 1.805850289185703, "grad_norm": 1.5375380516052246, "learning_rate": 9.376949911862291e-05, "loss": 0.49927334785461425, "step": 303800 }, { "epoch": 1.8059097312623713, "grad_norm": 1.574672818183899, "learning_rate": 9.376337644612921e-05, "loss": 0.5440646171569824, "step": 303810 }, { "epoch": 1.8059691733390397, "grad_norm": 1.3086249828338623, "learning_rate": 9.375725385130623e-05, "loss": 0.4923198699951172, "step": 303820 }, { "epoch": 1.8060286154157081, "grad_norm": 1.5378150939941406, "learning_rate": 9.375113133418322e-05, "loss": 0.44668874740600584, "step": 303830 }, { "epoch": 1.8060880574923766, "grad_norm": 1.3868932723999023, "learning_rate": 9.374500889478948e-05, "loss": 0.5922906875610352, "step": 303840 }, { "epoch": 1.806147499569045, "grad_norm": 1.4500707387924194, "learning_rate": 9.373888653315433e-05, "loss": 0.5705698966979981, "step": 303850 }, { "epoch": 1.8062069416457134, "grad_norm": 1.7641074657440186, "learning_rate": 9.373276424930703e-05, "loss": 0.5402612686157227, "step": 303860 }, { "epoch": 1.8062663837223818, "grad_norm": 1.3918430805206299, "learning_rate": 9.372664204327688e-05, "loss": 0.5250050544738769, "step": 303870 }, { "epoch": 1.8063258257990502, "grad_norm": 1.542994499206543, "learning_rate": 9.372051991509312e-05, "loss": 0.5846592903137207, "step": 303880 }, { "epoch": 1.8063852678757186, "grad_norm": 1.7871131896972656, "learning_rate": 9.371439786478508e-05, "loss": 0.5260912895202636, "step": 303890 }, { "epoch": 1.806444709952387, "grad_norm": 1.5463436841964722, "learning_rate": 9.370827589238209e-05, "loss": 0.5546377182006836, "step": 303900 }, { "epoch": 1.8065041520290552, "grad_norm": 1.1708499193191528, "learning_rate": 9.370215399791332e-05, "loss": 0.5192583084106446, "step": 303910 }, { "epoch": 1.8065635941057236, "grad_norm": 1.2845605611801147, "learning_rate": 9.369603218140814e-05, "loss": 0.5319427013397217, "step": 303920 }, { "epoch": 1.806623036182392, "grad_norm": 1.5221898555755615, "learning_rate": 9.368991044289586e-05, "loss": 0.5570673942565918, "step": 303930 }, { "epoch": 1.8066824782590605, "grad_norm": 1.2455363273620605, "learning_rate": 9.368378878240565e-05, "loss": 0.5570060729980468, "step": 303940 }, { "epoch": 1.806741920335729, "grad_norm": 1.3748973608016968, "learning_rate": 9.367766719996688e-05, "loss": 0.5648821353912353, "step": 303950 }, { "epoch": 1.806801362412397, "grad_norm": 1.2711255550384521, "learning_rate": 9.367154569560885e-05, "loss": 0.5642570495605469, "step": 303960 }, { "epoch": 1.8068608044890655, "grad_norm": 1.3976044654846191, "learning_rate": 9.36654242693608e-05, "loss": 0.5760916709899903, "step": 303970 }, { "epoch": 1.806920246565734, "grad_norm": 1.42343008518219, "learning_rate": 9.365930292125196e-05, "loss": 0.5098026275634766, "step": 303980 }, { "epoch": 1.8069796886424023, "grad_norm": 1.4173911809921265, "learning_rate": 9.365318165131174e-05, "loss": 0.5500310897827149, "step": 303990 }, { "epoch": 1.8070391307190707, "grad_norm": 1.5669262409210205, "learning_rate": 9.364706045956935e-05, "loss": 0.5110610485076904, "step": 304000 }, { "epoch": 1.8070985727957392, "grad_norm": 1.6053493022918701, "learning_rate": 9.364093934605403e-05, "loss": 0.5664089679718017, "step": 304010 }, { "epoch": 1.8071580148724076, "grad_norm": 1.5845668315887451, "learning_rate": 9.363481831079517e-05, "loss": 0.5600983142852783, "step": 304020 }, { "epoch": 1.807217456949076, "grad_norm": 1.3701388835906982, "learning_rate": 9.362869735382198e-05, "loss": 0.585240650177002, "step": 304030 }, { "epoch": 1.8072768990257444, "grad_norm": 1.3974851369857788, "learning_rate": 9.36225764751637e-05, "loss": 0.5224967956542969, "step": 304040 }, { "epoch": 1.8073363411024128, "grad_norm": 1.185422420501709, "learning_rate": 9.36164556748497e-05, "loss": 0.502040433883667, "step": 304050 }, { "epoch": 1.8073957831790812, "grad_norm": 1.3464329242706299, "learning_rate": 9.361033495290925e-05, "loss": 0.5999836444854736, "step": 304060 }, { "epoch": 1.8074552252557496, "grad_norm": 1.3154937028884888, "learning_rate": 9.360421430937154e-05, "loss": 0.5602902889251709, "step": 304070 }, { "epoch": 1.807514667332418, "grad_norm": 1.370079755783081, "learning_rate": 9.359809374426595e-05, "loss": 0.5529438495635987, "step": 304080 }, { "epoch": 1.8075741094090865, "grad_norm": 1.259509801864624, "learning_rate": 9.359197325762174e-05, "loss": 0.5113211631774902, "step": 304090 }, { "epoch": 1.8076335514857547, "grad_norm": 1.505444049835205, "learning_rate": 9.358585284946815e-05, "loss": 0.5425421714782714, "step": 304100 }, { "epoch": 1.807692993562423, "grad_norm": 1.3321484327316284, "learning_rate": 9.357973251983446e-05, "loss": 0.5271074295043945, "step": 304110 }, { "epoch": 1.8077524356390915, "grad_norm": 1.4596366882324219, "learning_rate": 9.357361226874996e-05, "loss": 0.5207954406738281, "step": 304120 }, { "epoch": 1.80781187771576, "grad_norm": 1.2727633714675903, "learning_rate": 9.356749209624396e-05, "loss": 0.5330118179321289, "step": 304130 }, { "epoch": 1.8078713197924283, "grad_norm": 1.0891458988189697, "learning_rate": 9.356137200234567e-05, "loss": 0.5483638763427734, "step": 304140 }, { "epoch": 1.8079307618690965, "grad_norm": 1.7231953144073486, "learning_rate": 9.355525198708443e-05, "loss": 0.5473796844482421, "step": 304150 }, { "epoch": 1.807990203945765, "grad_norm": 1.5851176977157593, "learning_rate": 9.35491320504895e-05, "loss": 0.5658819198608398, "step": 304160 }, { "epoch": 1.8080496460224333, "grad_norm": 1.4080207347869873, "learning_rate": 9.35430121925901e-05, "loss": 0.5267913341522217, "step": 304170 }, { "epoch": 1.8081090880991018, "grad_norm": 1.7275289297103882, "learning_rate": 9.353689241341559e-05, "loss": 0.5407799243927002, "step": 304180 }, { "epoch": 1.8081685301757702, "grad_norm": 1.3516448736190796, "learning_rate": 9.35307727129952e-05, "loss": 0.5571098327636719, "step": 304190 }, { "epoch": 1.8082279722524386, "grad_norm": 1.3546311855316162, "learning_rate": 9.352465309135821e-05, "loss": 0.5578315734863282, "step": 304200 }, { "epoch": 1.808287414329107, "grad_norm": 1.5224155187606812, "learning_rate": 9.351853354853388e-05, "loss": 0.5198836326599121, "step": 304210 }, { "epoch": 1.8083468564057754, "grad_norm": 1.7508034706115723, "learning_rate": 9.351241408455151e-05, "loss": 0.5681764602661132, "step": 304220 }, { "epoch": 1.8084062984824438, "grad_norm": 1.2996617555618286, "learning_rate": 9.350629469944038e-05, "loss": 0.5544474601745606, "step": 304230 }, { "epoch": 1.8084657405591122, "grad_norm": 1.3172454833984375, "learning_rate": 9.350017539322972e-05, "loss": 0.5651229858398438, "step": 304240 }, { "epoch": 1.8085251826357807, "grad_norm": 1.3432470560073853, "learning_rate": 9.349405616594884e-05, "loss": 0.5907450199127198, "step": 304250 }, { "epoch": 1.808584624712449, "grad_norm": 1.4157869815826416, "learning_rate": 9.348793701762702e-05, "loss": 0.5150415420532226, "step": 304260 }, { "epoch": 1.8086440667891175, "grad_norm": 1.7147271633148193, "learning_rate": 9.348181794829347e-05, "loss": 0.5068069458007812, "step": 304270 }, { "epoch": 1.8087035088657857, "grad_norm": 1.629353642463684, "learning_rate": 9.347569895797754e-05, "loss": 0.4998586654663086, "step": 304280 }, { "epoch": 1.808762950942454, "grad_norm": 1.5375139713287354, "learning_rate": 9.346958004670847e-05, "loss": 0.5307944774627685, "step": 304290 }, { "epoch": 1.8088223930191225, "grad_norm": 1.9218751192092896, "learning_rate": 9.34634612145155e-05, "loss": 0.5463079929351806, "step": 304300 }, { "epoch": 1.808881835095791, "grad_norm": 1.4061827659606934, "learning_rate": 9.345734246142795e-05, "loss": 0.5341651916503907, "step": 304310 }, { "epoch": 1.8089412771724593, "grad_norm": 1.4568963050842285, "learning_rate": 9.345122378747507e-05, "loss": 0.5267420291900635, "step": 304320 }, { "epoch": 1.8090007192491275, "grad_norm": 1.412031650543213, "learning_rate": 9.344510519268607e-05, "loss": 0.5737988471984863, "step": 304330 }, { "epoch": 1.809060161325796, "grad_norm": 1.6961066722869873, "learning_rate": 9.343898667709034e-05, "loss": 0.5719658851623535, "step": 304340 }, { "epoch": 1.8091196034024644, "grad_norm": 1.280422329902649, "learning_rate": 9.343286824071707e-05, "loss": 0.5424276351928711, "step": 304350 }, { "epoch": 1.8091790454791328, "grad_norm": 1.3423404693603516, "learning_rate": 9.342674988359555e-05, "loss": 0.5980233192443848, "step": 304360 }, { "epoch": 1.8092384875558012, "grad_norm": 1.1797246932983398, "learning_rate": 9.342063160575503e-05, "loss": 0.5220160007476806, "step": 304370 }, { "epoch": 1.8092979296324696, "grad_norm": 1.1999268531799316, "learning_rate": 9.341451340722478e-05, "loss": 0.5724019050598145, "step": 304380 }, { "epoch": 1.809357371709138, "grad_norm": 1.456965684890747, "learning_rate": 9.340839528803409e-05, "loss": 0.5362836837768554, "step": 304390 }, { "epoch": 1.8094168137858064, "grad_norm": 1.4852629899978638, "learning_rate": 9.340227724821222e-05, "loss": 0.6122617244720459, "step": 304400 }, { "epoch": 1.8094762558624748, "grad_norm": 1.3348883390426636, "learning_rate": 9.339615928778842e-05, "loss": 0.5837773323059082, "step": 304410 }, { "epoch": 1.8095356979391433, "grad_norm": 1.208836555480957, "learning_rate": 9.339004140679197e-05, "loss": 0.5213173866271973, "step": 304420 }, { "epoch": 1.8095951400158117, "grad_norm": 1.3590515851974487, "learning_rate": 9.338392360525214e-05, "loss": 0.5507574558258057, "step": 304430 }, { "epoch": 1.80965458209248, "grad_norm": 1.3113305568695068, "learning_rate": 9.33778058831982e-05, "loss": 0.5718849658966064, "step": 304440 }, { "epoch": 1.8097140241691485, "grad_norm": 1.5319021940231323, "learning_rate": 9.337168824065938e-05, "loss": 0.573061466217041, "step": 304450 }, { "epoch": 1.809773466245817, "grad_norm": 1.4967283010482788, "learning_rate": 9.336557067766501e-05, "loss": 0.5918327331542969, "step": 304460 }, { "epoch": 1.8098329083224851, "grad_norm": 1.2956585884094238, "learning_rate": 9.335945319424426e-05, "loss": 0.538180160522461, "step": 304470 }, { "epoch": 1.8098923503991535, "grad_norm": 1.663519263267517, "learning_rate": 9.335333579042647e-05, "loss": 0.5553183078765869, "step": 304480 }, { "epoch": 1.809951792475822, "grad_norm": 1.538647174835205, "learning_rate": 9.334721846624093e-05, "loss": 0.5182652473449707, "step": 304490 }, { "epoch": 1.8100112345524904, "grad_norm": 1.1777846813201904, "learning_rate": 9.334110122171676e-05, "loss": 0.5436835289001465, "step": 304500 }, { "epoch": 1.8100706766291588, "grad_norm": 1.501201868057251, "learning_rate": 9.333498405688337e-05, "loss": 0.5668982028961181, "step": 304510 }, { "epoch": 1.810130118705827, "grad_norm": 1.3826169967651367, "learning_rate": 9.332886697177e-05, "loss": 0.5627391815185547, "step": 304520 }, { "epoch": 1.8101895607824954, "grad_norm": 1.2458137273788452, "learning_rate": 9.332274996640582e-05, "loss": 0.5219701290130615, "step": 304530 }, { "epoch": 1.8102490028591638, "grad_norm": 1.1080021858215332, "learning_rate": 9.331663304082022e-05, "loss": 0.581609582901001, "step": 304540 }, { "epoch": 1.8103084449358322, "grad_norm": 1.4262226819992065, "learning_rate": 9.331051619504234e-05, "loss": 0.5819165229797363, "step": 304550 }, { "epoch": 1.8103678870125006, "grad_norm": 1.4610694646835327, "learning_rate": 9.330439942910147e-05, "loss": 0.5449349403381347, "step": 304560 }, { "epoch": 1.810427329089169, "grad_norm": 1.3212162256240845, "learning_rate": 9.329828274302699e-05, "loss": 0.5874402046203613, "step": 304570 }, { "epoch": 1.8104867711658374, "grad_norm": 1.5428249835968018, "learning_rate": 9.329216613684801e-05, "loss": 0.5802062034606934, "step": 304580 }, { "epoch": 1.8105462132425059, "grad_norm": 1.3692034482955933, "learning_rate": 9.328604961059386e-05, "loss": 0.5985135078430176, "step": 304590 }, { "epoch": 1.8106056553191743, "grad_norm": 1.1711108684539795, "learning_rate": 9.327993316429377e-05, "loss": 0.5331021308898926, "step": 304600 }, { "epoch": 1.8106650973958427, "grad_norm": 1.4148215055465698, "learning_rate": 9.327381679797705e-05, "loss": 0.5337963581085206, "step": 304610 }, { "epoch": 1.810724539472511, "grad_norm": 1.483522653579712, "learning_rate": 9.32677005116729e-05, "loss": 0.561343002319336, "step": 304620 }, { "epoch": 1.8107839815491795, "grad_norm": 1.218745231628418, "learning_rate": 9.326158430541059e-05, "loss": 0.5171891212463379, "step": 304630 }, { "epoch": 1.810843423625848, "grad_norm": 1.7637698650360107, "learning_rate": 9.325546817921942e-05, "loss": 0.5828104019165039, "step": 304640 }, { "epoch": 1.8109028657025161, "grad_norm": 1.4582873582839966, "learning_rate": 9.324935213312859e-05, "loss": 0.6284732341766357, "step": 304650 }, { "epoch": 1.8109623077791845, "grad_norm": 1.4104955196380615, "learning_rate": 9.32432361671674e-05, "loss": 0.5261698722839355, "step": 304660 }, { "epoch": 1.811021749855853, "grad_norm": 1.70421302318573, "learning_rate": 9.323712028136508e-05, "loss": 0.5588658332824707, "step": 304670 }, { "epoch": 1.8110811919325214, "grad_norm": 1.5552915334701538, "learning_rate": 9.323100447575092e-05, "loss": 0.5312180519104004, "step": 304680 }, { "epoch": 1.8111406340091898, "grad_norm": 1.4655025005340576, "learning_rate": 9.322488875035413e-05, "loss": 0.5606211662292481, "step": 304690 }, { "epoch": 1.811200076085858, "grad_norm": 1.4113253355026245, "learning_rate": 9.321877310520401e-05, "loss": 0.5456775665283203, "step": 304700 }, { "epoch": 1.8112595181625264, "grad_norm": 1.3693151473999023, "learning_rate": 9.321265754032979e-05, "loss": 0.551545524597168, "step": 304710 }, { "epoch": 1.8113189602391948, "grad_norm": 1.645849347114563, "learning_rate": 9.320654205576074e-05, "loss": 0.5678120613098144, "step": 304720 }, { "epoch": 1.8113784023158632, "grad_norm": 1.2649624347686768, "learning_rate": 9.320042665152608e-05, "loss": 0.5732444763183594, "step": 304730 }, { "epoch": 1.8114378443925316, "grad_norm": 1.4017349481582642, "learning_rate": 9.31943113276551e-05, "loss": 0.5035558223724366, "step": 304740 }, { "epoch": 1.8114972864692, "grad_norm": 1.5775107145309448, "learning_rate": 9.318819608417706e-05, "loss": 0.5508987426757812, "step": 304750 }, { "epoch": 1.8115567285458685, "grad_norm": 1.410046935081482, "learning_rate": 9.318208092112118e-05, "loss": 0.5687360763549805, "step": 304760 }, { "epoch": 1.8116161706225369, "grad_norm": 1.176455020904541, "learning_rate": 9.317596583851671e-05, "loss": 0.5954729557037354, "step": 304770 }, { "epoch": 1.8116756126992053, "grad_norm": 1.4350879192352295, "learning_rate": 9.316985083639296e-05, "loss": 0.5464266300201416, "step": 304780 }, { "epoch": 1.8117350547758737, "grad_norm": 1.6794712543487549, "learning_rate": 9.31637359147791e-05, "loss": 0.581820011138916, "step": 304790 }, { "epoch": 1.8117944968525421, "grad_norm": 1.3493170738220215, "learning_rate": 9.315762107370447e-05, "loss": 0.5518394470214844, "step": 304800 }, { "epoch": 1.8118539389292105, "grad_norm": 1.5391457080841064, "learning_rate": 9.315150631319824e-05, "loss": 0.5505513191223145, "step": 304810 }, { "epoch": 1.811913381005879, "grad_norm": 1.3023697137832642, "learning_rate": 9.314539163328973e-05, "loss": 0.4972671031951904, "step": 304820 }, { "epoch": 1.8119728230825474, "grad_norm": 1.3098417520523071, "learning_rate": 9.313927703400814e-05, "loss": 0.5875035762786865, "step": 304830 }, { "epoch": 1.8120322651592156, "grad_norm": 1.2963902950286865, "learning_rate": 9.313316251538273e-05, "loss": 0.5224482536315918, "step": 304840 }, { "epoch": 1.812091707235884, "grad_norm": 1.4376335144042969, "learning_rate": 9.312704807744277e-05, "loss": 0.5556415557861328, "step": 304850 }, { "epoch": 1.8121511493125524, "grad_norm": 1.253353238105774, "learning_rate": 9.312093372021748e-05, "loss": 0.5405123710632325, "step": 304860 }, { "epoch": 1.8122105913892208, "grad_norm": 1.7596566677093506, "learning_rate": 9.311481944373615e-05, "loss": 0.5975803375244141, "step": 304870 }, { "epoch": 1.8122700334658892, "grad_norm": 1.7376023530960083, "learning_rate": 9.310870524802802e-05, "loss": 0.5471371650695801, "step": 304880 }, { "epoch": 1.8123294755425574, "grad_norm": 1.412233829498291, "learning_rate": 9.310259113312227e-05, "loss": 0.5930646896362305, "step": 304890 }, { "epoch": 1.8123889176192258, "grad_norm": 1.4056990146636963, "learning_rate": 9.309647709904825e-05, "loss": 0.5420005798339844, "step": 304900 }, { "epoch": 1.8124483596958942, "grad_norm": 1.2187786102294922, "learning_rate": 9.309036314583514e-05, "loss": 0.5544820785522461, "step": 304910 }, { "epoch": 1.8125078017725627, "grad_norm": 1.1636167764663696, "learning_rate": 9.30842492735122e-05, "loss": 0.5473045349121094, "step": 304920 }, { "epoch": 1.812567243849231, "grad_norm": 1.3584140539169312, "learning_rate": 9.30781354821087e-05, "loss": 0.5068120002746582, "step": 304930 }, { "epoch": 1.8126266859258995, "grad_norm": 1.268437385559082, "learning_rate": 9.307202177165389e-05, "loss": 0.5141199111938477, "step": 304940 }, { "epoch": 1.812686128002568, "grad_norm": 1.0954787731170654, "learning_rate": 9.306590814217697e-05, "loss": 0.5548690795898438, "step": 304950 }, { "epoch": 1.8127455700792363, "grad_norm": 1.2488933801651, "learning_rate": 9.305979459370719e-05, "loss": 0.5436625003814697, "step": 304960 }, { "epoch": 1.8128050121559047, "grad_norm": 1.177937388420105, "learning_rate": 9.305368112627384e-05, "loss": 0.49640703201293945, "step": 304970 }, { "epoch": 1.8128644542325731, "grad_norm": 1.111630916595459, "learning_rate": 9.304756773990617e-05, "loss": 0.548740005493164, "step": 304980 }, { "epoch": 1.8129238963092416, "grad_norm": 1.5475085973739624, "learning_rate": 9.304145443463332e-05, "loss": 0.568968677520752, "step": 304990 }, { "epoch": 1.81298333838591, "grad_norm": 1.3657991886138916, "learning_rate": 9.303534121048468e-05, "loss": 0.5805462837219239, "step": 305000 }, { "epoch": 1.8130427804625784, "grad_norm": 1.4155408143997192, "learning_rate": 9.302922806748942e-05, "loss": 0.6339465141296386, "step": 305010 }, { "epoch": 1.8131022225392466, "grad_norm": 1.5037798881530762, "learning_rate": 9.302311500567673e-05, "loss": 0.5319366455078125, "step": 305020 }, { "epoch": 1.813161664615915, "grad_norm": 1.2591543197631836, "learning_rate": 9.301700202507593e-05, "loss": 0.5009894371032715, "step": 305030 }, { "epoch": 1.8132211066925834, "grad_norm": 1.6405781507492065, "learning_rate": 9.30108891257163e-05, "loss": 0.5605116844177246, "step": 305040 }, { "epoch": 1.8132805487692518, "grad_norm": 1.432464361190796, "learning_rate": 9.300477630762694e-05, "loss": 0.544101333618164, "step": 305050 }, { "epoch": 1.8133399908459202, "grad_norm": 1.3029768466949463, "learning_rate": 9.299866357083721e-05, "loss": 0.5792897701263428, "step": 305060 }, { "epoch": 1.8133994329225884, "grad_norm": 1.1586545705795288, "learning_rate": 9.299255091537635e-05, "loss": 0.5766305923461914, "step": 305070 }, { "epoch": 1.8134588749992568, "grad_norm": 1.6850947141647339, "learning_rate": 9.298643834127356e-05, "loss": 0.5792135238647461, "step": 305080 }, { "epoch": 1.8135183170759253, "grad_norm": 1.1927573680877686, "learning_rate": 9.298032584855802e-05, "loss": 0.5618138313293457, "step": 305090 }, { "epoch": 1.8135777591525937, "grad_norm": 1.7968860864639282, "learning_rate": 9.297421343725914e-05, "loss": 0.5649723052978516, "step": 305100 }, { "epoch": 1.813637201229262, "grad_norm": 1.4375592470169067, "learning_rate": 9.296810110740601e-05, "loss": 0.4879135608673096, "step": 305110 }, { "epoch": 1.8136966433059305, "grad_norm": 1.648154377937317, "learning_rate": 9.29619888590279e-05, "loss": 0.5820471763610839, "step": 305120 }, { "epoch": 1.813756085382599, "grad_norm": 1.6619776487350464, "learning_rate": 9.295587669215409e-05, "loss": 0.5953267097473145, "step": 305130 }, { "epoch": 1.8138155274592673, "grad_norm": 1.1164723634719849, "learning_rate": 9.29497646068138e-05, "loss": 0.5990520477294922, "step": 305140 }, { "epoch": 1.8138749695359357, "grad_norm": 1.673763632774353, "learning_rate": 9.294365260303623e-05, "loss": 0.6170331954956054, "step": 305150 }, { "epoch": 1.8139344116126042, "grad_norm": 1.5942134857177734, "learning_rate": 9.29375406808507e-05, "loss": 0.5731358528137207, "step": 305160 }, { "epoch": 1.8139938536892726, "grad_norm": 1.1439839601516724, "learning_rate": 9.293142884028638e-05, "loss": 0.5786430358886718, "step": 305170 }, { "epoch": 1.814053295765941, "grad_norm": 1.9810651540756226, "learning_rate": 9.29253170813725e-05, "loss": 0.535339069366455, "step": 305180 }, { "epoch": 1.8141127378426094, "grad_norm": 1.342635989189148, "learning_rate": 9.291920540413837e-05, "loss": 0.48544769287109374, "step": 305190 }, { "epoch": 1.8141721799192778, "grad_norm": 1.419639229774475, "learning_rate": 9.291309380861315e-05, "loss": 0.5001041412353515, "step": 305200 }, { "epoch": 1.814231621995946, "grad_norm": 1.2297073602676392, "learning_rate": 9.290698229482611e-05, "loss": 0.5257083892822265, "step": 305210 }, { "epoch": 1.8142910640726144, "grad_norm": 1.8801593780517578, "learning_rate": 9.290087086280645e-05, "loss": 0.530855655670166, "step": 305220 }, { "epoch": 1.8143505061492828, "grad_norm": 1.4736157655715942, "learning_rate": 9.289475951258349e-05, "loss": 0.5398528099060058, "step": 305230 }, { "epoch": 1.8144099482259513, "grad_norm": 1.186097502708435, "learning_rate": 9.28886482441864e-05, "loss": 0.4915966033935547, "step": 305240 }, { "epoch": 1.8144693903026197, "grad_norm": 1.1143114566802979, "learning_rate": 9.288253705764438e-05, "loss": 0.5442355155944825, "step": 305250 }, { "epoch": 1.8145288323792879, "grad_norm": 1.7456642389297485, "learning_rate": 9.287642595298676e-05, "loss": 0.5642849922180175, "step": 305260 }, { "epoch": 1.8145882744559563, "grad_norm": 1.2573466300964355, "learning_rate": 9.28703149302427e-05, "loss": 0.5522371292114258, "step": 305270 }, { "epoch": 1.8146477165326247, "grad_norm": 1.0719801187515259, "learning_rate": 9.286420398944145e-05, "loss": 0.5023739814758301, "step": 305280 }, { "epoch": 1.814707158609293, "grad_norm": 1.4804973602294922, "learning_rate": 9.285809313061227e-05, "loss": 0.5176375389099122, "step": 305290 }, { "epoch": 1.8147666006859615, "grad_norm": 1.7602335214614868, "learning_rate": 9.285198235378433e-05, "loss": 0.5786114692687988, "step": 305300 }, { "epoch": 1.81482604276263, "grad_norm": 1.395340085029602, "learning_rate": 9.284587165898694e-05, "loss": 0.5291557788848877, "step": 305310 }, { "epoch": 1.8148854848392983, "grad_norm": 1.6974835395812988, "learning_rate": 9.283976104624928e-05, "loss": 0.6026116371154785, "step": 305320 }, { "epoch": 1.8149449269159668, "grad_norm": 1.3199020624160767, "learning_rate": 9.28336505156006e-05, "loss": 0.5716867446899414, "step": 305330 }, { "epoch": 1.8150043689926352, "grad_norm": 1.537473440170288, "learning_rate": 9.282754006707012e-05, "loss": 0.5087099075317383, "step": 305340 }, { "epoch": 1.8150638110693036, "grad_norm": 1.624895453453064, "learning_rate": 9.282142970068709e-05, "loss": 0.5615268230438233, "step": 305350 }, { "epoch": 1.815123253145972, "grad_norm": 1.2505931854248047, "learning_rate": 9.281531941648072e-05, "loss": 0.5230300903320313, "step": 305360 }, { "epoch": 1.8151826952226404, "grad_norm": 1.5190380811691284, "learning_rate": 9.280920921448024e-05, "loss": 0.6122973918914795, "step": 305370 }, { "epoch": 1.8152421372993088, "grad_norm": 1.549842357635498, "learning_rate": 9.280309909471487e-05, "loss": 0.5423819541931152, "step": 305380 }, { "epoch": 1.815301579375977, "grad_norm": 1.005653738975525, "learning_rate": 9.279698905721388e-05, "loss": 0.5405391693115235, "step": 305390 }, { "epoch": 1.8153610214526454, "grad_norm": 1.4374018907546997, "learning_rate": 9.279087910200645e-05, "loss": 0.5003656864166259, "step": 305400 }, { "epoch": 1.8154204635293139, "grad_norm": 1.4154753684997559, "learning_rate": 9.278476922912184e-05, "loss": 0.5315459251403809, "step": 305410 }, { "epoch": 1.8154799056059823, "grad_norm": 1.4905041456222534, "learning_rate": 9.277865943858928e-05, "loss": 0.5800656795501709, "step": 305420 }, { "epoch": 1.8155393476826507, "grad_norm": 1.2556649446487427, "learning_rate": 9.277254973043798e-05, "loss": 0.5178290367126465, "step": 305430 }, { "epoch": 1.8155987897593189, "grad_norm": 1.4157710075378418, "learning_rate": 9.276644010469719e-05, "loss": 0.49922609329223633, "step": 305440 }, { "epoch": 1.8156582318359873, "grad_norm": 1.2930383682250977, "learning_rate": 9.276033056139609e-05, "loss": 0.5850827693939209, "step": 305450 }, { "epoch": 1.8157176739126557, "grad_norm": 1.5147676467895508, "learning_rate": 9.275422110056394e-05, "loss": 0.549705696105957, "step": 305460 }, { "epoch": 1.8157771159893241, "grad_norm": 1.1809377670288086, "learning_rate": 9.274811172222999e-05, "loss": 0.49930477142333984, "step": 305470 }, { "epoch": 1.8158365580659925, "grad_norm": 1.5694350004196167, "learning_rate": 9.274200242642338e-05, "loss": 0.559898042678833, "step": 305480 }, { "epoch": 1.815896000142661, "grad_norm": 1.233158826828003, "learning_rate": 9.27358932131734e-05, "loss": 0.5672924995422364, "step": 305490 }, { "epoch": 1.8159554422193294, "grad_norm": 1.2172484397888184, "learning_rate": 9.272978408250931e-05, "loss": 0.5321832180023194, "step": 305500 }, { "epoch": 1.8160148842959978, "grad_norm": 1.3101856708526611, "learning_rate": 9.272367503446024e-05, "loss": 0.5255876541137695, "step": 305510 }, { "epoch": 1.8160743263726662, "grad_norm": 1.2226136922836304, "learning_rate": 9.271756606905548e-05, "loss": 0.5795226097106934, "step": 305520 }, { "epoch": 1.8161337684493346, "grad_norm": 1.1898057460784912, "learning_rate": 9.271145718632428e-05, "loss": 0.537467098236084, "step": 305530 }, { "epoch": 1.816193210526003, "grad_norm": 1.3182168006896973, "learning_rate": 9.270534838629574e-05, "loss": 0.5732074737548828, "step": 305540 }, { "epoch": 1.8162526526026714, "grad_norm": 1.3891521692276, "learning_rate": 9.269923966899921e-05, "loss": 0.5814804077148438, "step": 305550 }, { "epoch": 1.8163120946793399, "grad_norm": 1.5231034755706787, "learning_rate": 9.269313103446387e-05, "loss": 0.5143612861633301, "step": 305560 }, { "epoch": 1.8163715367560083, "grad_norm": 1.5104806423187256, "learning_rate": 9.268702248271892e-05, "loss": 0.5675471305847168, "step": 305570 }, { "epoch": 1.8164309788326765, "grad_norm": 0.8560467958450317, "learning_rate": 9.268091401379358e-05, "loss": 0.5024697303771972, "step": 305580 }, { "epoch": 1.8164904209093449, "grad_norm": 1.376670002937317, "learning_rate": 9.267480562771711e-05, "loss": 0.5340532779693603, "step": 305590 }, { "epoch": 1.8165498629860133, "grad_norm": 1.3120046854019165, "learning_rate": 9.266869732451873e-05, "loss": 0.5480624198913574, "step": 305600 }, { "epoch": 1.8166093050626817, "grad_norm": 1.3678057193756104, "learning_rate": 9.266258910422756e-05, "loss": 0.532742977142334, "step": 305610 }, { "epoch": 1.8166687471393501, "grad_norm": 1.259293556213379, "learning_rate": 9.265648096687298e-05, "loss": 0.5702025413513183, "step": 305620 }, { "epoch": 1.8167281892160183, "grad_norm": 1.170049786567688, "learning_rate": 9.265037291248408e-05, "loss": 0.6074361801147461, "step": 305630 }, { "epoch": 1.8167876312926867, "grad_norm": 1.5587927103042603, "learning_rate": 9.264426494109013e-05, "loss": 0.5518021583557129, "step": 305640 }, { "epoch": 1.8168470733693551, "grad_norm": 1.208770513534546, "learning_rate": 9.263815705272036e-05, "loss": 0.5173856735229492, "step": 305650 }, { "epoch": 1.8169065154460236, "grad_norm": 1.1133075952529907, "learning_rate": 9.263204924740398e-05, "loss": 0.5573871612548829, "step": 305660 }, { "epoch": 1.816965957522692, "grad_norm": 1.3237911462783813, "learning_rate": 9.26259415251702e-05, "loss": 0.5804244041442871, "step": 305670 }, { "epoch": 1.8170253995993604, "grad_norm": 1.4339348077774048, "learning_rate": 9.26198338860482e-05, "loss": 0.5663812160491943, "step": 305680 }, { "epoch": 1.8170848416760288, "grad_norm": 1.3211486339569092, "learning_rate": 9.261372633006729e-05, "loss": 0.5474203586578369, "step": 305690 }, { "epoch": 1.8171442837526972, "grad_norm": 1.5144110918045044, "learning_rate": 9.26076188572566e-05, "loss": 0.5540552139282227, "step": 305700 }, { "epoch": 1.8172037258293656, "grad_norm": 1.5090124607086182, "learning_rate": 9.260151146764538e-05, "loss": 0.5655687808990478, "step": 305710 }, { "epoch": 1.817263167906034, "grad_norm": 1.3897374868392944, "learning_rate": 9.259540416126285e-05, "loss": 0.5499987602233887, "step": 305720 }, { "epoch": 1.8173226099827025, "grad_norm": 1.2957546710968018, "learning_rate": 9.25892969381382e-05, "loss": 0.5280488967895508, "step": 305730 }, { "epoch": 1.8173820520593709, "grad_norm": 1.4283905029296875, "learning_rate": 9.258318979830067e-05, "loss": 0.5229908943176269, "step": 305740 }, { "epoch": 1.8174414941360393, "grad_norm": 1.452252984046936, "learning_rate": 9.257708274177947e-05, "loss": 0.5727390766143798, "step": 305750 }, { "epoch": 1.8175009362127075, "grad_norm": 0.9939872622489929, "learning_rate": 9.257097576860383e-05, "loss": 0.5291830539703369, "step": 305760 }, { "epoch": 1.8175603782893759, "grad_norm": 1.3226349353790283, "learning_rate": 9.256486887880291e-05, "loss": 0.6032651901245117, "step": 305770 }, { "epoch": 1.8176198203660443, "grad_norm": 1.4660917520523071, "learning_rate": 9.2558762072406e-05, "loss": 0.568422508239746, "step": 305780 }, { "epoch": 1.8176792624427127, "grad_norm": 1.4077723026275635, "learning_rate": 9.255265534944224e-05, "loss": 0.5314295768737793, "step": 305790 }, { "epoch": 1.8177387045193811, "grad_norm": 1.377702236175537, "learning_rate": 9.25465487099409e-05, "loss": 0.5237107276916504, "step": 305800 }, { "epoch": 1.8177981465960493, "grad_norm": 1.293377161026001, "learning_rate": 9.254044215393114e-05, "loss": 0.5490273475646973, "step": 305810 }, { "epoch": 1.8178575886727177, "grad_norm": 1.5284206867218018, "learning_rate": 9.253433568144223e-05, "loss": 0.5922376155853272, "step": 305820 }, { "epoch": 1.8179170307493862, "grad_norm": 1.4819048643112183, "learning_rate": 9.252822929250334e-05, "loss": 0.5193207740783692, "step": 305830 }, { "epoch": 1.8179764728260546, "grad_norm": 1.4355329275131226, "learning_rate": 9.252212298714367e-05, "loss": 0.5377005577087403, "step": 305840 }, { "epoch": 1.818035914902723, "grad_norm": 1.3307796716690063, "learning_rate": 9.251601676539248e-05, "loss": 0.49558510780334475, "step": 305850 }, { "epoch": 1.8180953569793914, "grad_norm": 1.2149378061294556, "learning_rate": 9.250991062727894e-05, "loss": 0.5161499500274658, "step": 305860 }, { "epoch": 1.8181547990560598, "grad_norm": 1.3667559623718262, "learning_rate": 9.250380457283226e-05, "loss": 0.52425537109375, "step": 305870 }, { "epoch": 1.8182142411327282, "grad_norm": 1.1300987005233765, "learning_rate": 9.249769860208168e-05, "loss": 0.5812828063964843, "step": 305880 }, { "epoch": 1.8182736832093966, "grad_norm": 1.3450751304626465, "learning_rate": 9.249159271505639e-05, "loss": 0.5485505104064942, "step": 305890 }, { "epoch": 1.818333125286065, "grad_norm": 1.403306484222412, "learning_rate": 9.248548691178558e-05, "loss": 0.574734115600586, "step": 305900 }, { "epoch": 1.8183925673627335, "grad_norm": 1.0012571811676025, "learning_rate": 9.247938119229849e-05, "loss": 0.5290447235107422, "step": 305910 }, { "epoch": 1.8184520094394019, "grad_norm": 1.2811243534088135, "learning_rate": 9.24732755566243e-05, "loss": 0.5380344390869141, "step": 305920 }, { "epoch": 1.8185114515160703, "grad_norm": 1.3704016208648682, "learning_rate": 9.246717000479226e-05, "loss": 0.5065464973449707, "step": 305930 }, { "epoch": 1.8185708935927387, "grad_norm": 1.2979381084442139, "learning_rate": 9.246106453683152e-05, "loss": 0.5807616233825683, "step": 305940 }, { "epoch": 1.818630335669407, "grad_norm": 1.3275854587554932, "learning_rate": 9.245495915277133e-05, "loss": 0.5598811149597168, "step": 305950 }, { "epoch": 1.8186897777460753, "grad_norm": 1.133934497833252, "learning_rate": 9.24488538526409e-05, "loss": 0.5396242141723633, "step": 305960 }, { "epoch": 1.8187492198227437, "grad_norm": 1.3717217445373535, "learning_rate": 9.244274863646938e-05, "loss": 0.5591899871826171, "step": 305970 }, { "epoch": 1.8188086618994121, "grad_norm": 1.2793793678283691, "learning_rate": 9.243664350428605e-05, "loss": 0.5119789123535157, "step": 305980 }, { "epoch": 1.8188681039760806, "grad_norm": 1.4259370565414429, "learning_rate": 9.243053845612006e-05, "loss": 0.5742347717285157, "step": 305990 }, { "epoch": 1.8189275460527488, "grad_norm": 1.4709045886993408, "learning_rate": 9.24244334920006e-05, "loss": 0.5585458755493165, "step": 306000 }, { "epoch": 1.8189869881294172, "grad_norm": 1.4504894018173218, "learning_rate": 9.241832861195694e-05, "loss": 0.5184996604919434, "step": 306010 }, { "epoch": 1.8190464302060856, "grad_norm": 1.4800633192062378, "learning_rate": 9.241222381601829e-05, "loss": 0.6129364013671875, "step": 306020 }, { "epoch": 1.819105872282754, "grad_norm": 1.2210521697998047, "learning_rate": 9.240611910421372e-05, "loss": 0.5325323104858398, "step": 306030 }, { "epoch": 1.8191653143594224, "grad_norm": 1.328399896621704, "learning_rate": 9.24000144765726e-05, "loss": 0.5445747375488281, "step": 306040 }, { "epoch": 1.8192247564360908, "grad_norm": 1.1516891717910767, "learning_rate": 9.239390993312407e-05, "loss": 0.5617453575134277, "step": 306050 }, { "epoch": 1.8192841985127592, "grad_norm": 1.2380706071853638, "learning_rate": 9.238780547389727e-05, "loss": 0.5506989479064941, "step": 306060 }, { "epoch": 1.8193436405894277, "grad_norm": 1.5032248497009277, "learning_rate": 9.238170109892145e-05, "loss": 0.5254032135009765, "step": 306070 }, { "epoch": 1.819403082666096, "grad_norm": 1.5119922161102295, "learning_rate": 9.237559680822585e-05, "loss": 0.5726475238800048, "step": 306080 }, { "epoch": 1.8194625247427645, "grad_norm": 1.2140120267868042, "learning_rate": 9.236949260183962e-05, "loss": 0.5236620903015137, "step": 306090 }, { "epoch": 1.819521966819433, "grad_norm": 1.5279923677444458, "learning_rate": 9.236338847979195e-05, "loss": 0.5785671234130859, "step": 306100 }, { "epoch": 1.8195814088961013, "grad_norm": 1.2357101440429688, "learning_rate": 9.235728444211211e-05, "loss": 0.5687925338745117, "step": 306110 }, { "epoch": 1.8196408509727697, "grad_norm": 1.1912949085235596, "learning_rate": 9.235118048882924e-05, "loss": 0.5074496269226074, "step": 306120 }, { "epoch": 1.819700293049438, "grad_norm": 1.5673037767410278, "learning_rate": 9.234507661997253e-05, "loss": 0.5780789375305175, "step": 306130 }, { "epoch": 1.8197597351261063, "grad_norm": 1.0751959085464478, "learning_rate": 9.233897283557125e-05, "loss": 0.5839000701904297, "step": 306140 }, { "epoch": 1.8198191772027748, "grad_norm": 1.441515564918518, "learning_rate": 9.233286913565453e-05, "loss": 0.58567795753479, "step": 306150 }, { "epoch": 1.8198786192794432, "grad_norm": 1.4608652591705322, "learning_rate": 9.23267655202516e-05, "loss": 0.5360437393188476, "step": 306160 }, { "epoch": 1.8199380613561116, "grad_norm": 1.6123207807540894, "learning_rate": 9.232066198939162e-05, "loss": 0.5701667785644531, "step": 306170 }, { "epoch": 1.8199975034327798, "grad_norm": 2.4571454524993896, "learning_rate": 9.231455854310384e-05, "loss": 0.5649948120117188, "step": 306180 }, { "epoch": 1.8200569455094482, "grad_norm": 1.4508169889450073, "learning_rate": 9.230845518141742e-05, "loss": 0.5721050262451172, "step": 306190 }, { "epoch": 1.8201163875861166, "grad_norm": 1.4399656057357788, "learning_rate": 9.230235190436157e-05, "loss": 0.5342159271240234, "step": 306200 }, { "epoch": 1.820175829662785, "grad_norm": 1.6825107336044312, "learning_rate": 9.229624871196549e-05, "loss": 0.5702350616455079, "step": 306210 }, { "epoch": 1.8202352717394534, "grad_norm": 1.2273558378219604, "learning_rate": 9.229014560425837e-05, "loss": 0.4862259864807129, "step": 306220 }, { "epoch": 1.8202947138161218, "grad_norm": 1.2704702615737915, "learning_rate": 9.228404258126939e-05, "loss": 0.5449173927307129, "step": 306230 }, { "epoch": 1.8203541558927903, "grad_norm": 1.4807175397872925, "learning_rate": 9.227793964302777e-05, "loss": 0.5113587856292725, "step": 306240 }, { "epoch": 1.8204135979694587, "grad_norm": 1.4733201265335083, "learning_rate": 9.227183678956273e-05, "loss": 0.5145786285400391, "step": 306250 }, { "epoch": 1.820473040046127, "grad_norm": 1.3153791427612305, "learning_rate": 9.226573402090337e-05, "loss": 0.5087338924407959, "step": 306260 }, { "epoch": 1.8205324821227955, "grad_norm": 1.3393040895462036, "learning_rate": 9.225963133707898e-05, "loss": 0.5474198341369629, "step": 306270 }, { "epoch": 1.820591924199464, "grad_norm": 1.5137864351272583, "learning_rate": 9.22535287381187e-05, "loss": 0.5672789573669433, "step": 306280 }, { "epoch": 1.8206513662761323, "grad_norm": 1.4550025463104248, "learning_rate": 9.224742622405175e-05, "loss": 0.5660083770751954, "step": 306290 }, { "epoch": 1.8207108083528007, "grad_norm": 1.264190435409546, "learning_rate": 9.224132379490731e-05, "loss": 0.5440412521362304, "step": 306300 }, { "epoch": 1.8207702504294692, "grad_norm": 1.5740525722503662, "learning_rate": 9.223522145071456e-05, "loss": 0.5230654716491699, "step": 306310 }, { "epoch": 1.8208296925061374, "grad_norm": 1.4218525886535645, "learning_rate": 9.222911919150274e-05, "loss": 0.5673218250274659, "step": 306320 }, { "epoch": 1.8208891345828058, "grad_norm": 1.9027223587036133, "learning_rate": 9.222301701730097e-05, "loss": 0.5497435092926025, "step": 306330 }, { "epoch": 1.8209485766594742, "grad_norm": 1.270524501800537, "learning_rate": 9.221691492813849e-05, "loss": 0.5394703865051269, "step": 306340 }, { "epoch": 1.8210080187361426, "grad_norm": 1.6191883087158203, "learning_rate": 9.221081292404447e-05, "loss": 0.5610523223876953, "step": 306350 }, { "epoch": 1.8210674608128108, "grad_norm": 1.4924529790878296, "learning_rate": 9.22047110050481e-05, "loss": 0.5471766471862793, "step": 306360 }, { "epoch": 1.8211269028894792, "grad_norm": 1.6360013484954834, "learning_rate": 9.219860917117862e-05, "loss": 0.5506978988647461, "step": 306370 }, { "epoch": 1.8211863449661476, "grad_norm": 1.5324137210845947, "learning_rate": 9.219250742246514e-05, "loss": 0.5333376407623291, "step": 306380 }, { "epoch": 1.821245787042816, "grad_norm": 1.6842550039291382, "learning_rate": 9.21864057589369e-05, "loss": 0.5708448410034179, "step": 306390 }, { "epoch": 1.8213052291194844, "grad_norm": 1.3254015445709229, "learning_rate": 9.218030418062305e-05, "loss": 0.5263567924499511, "step": 306400 }, { "epoch": 1.8213646711961529, "grad_norm": 0.9705412983894348, "learning_rate": 9.217420268755282e-05, "loss": 0.5651005268096924, "step": 306410 }, { "epoch": 1.8214241132728213, "grad_norm": 1.3140469789505005, "learning_rate": 9.216810127975539e-05, "loss": 0.5319377899169921, "step": 306420 }, { "epoch": 1.8214835553494897, "grad_norm": 1.7841874361038208, "learning_rate": 9.216199995725989e-05, "loss": 0.602688217163086, "step": 306430 }, { "epoch": 1.821542997426158, "grad_norm": 1.5103187561035156, "learning_rate": 9.21558987200956e-05, "loss": 0.5340017318725586, "step": 306440 }, { "epoch": 1.8216024395028265, "grad_norm": 1.667533040046692, "learning_rate": 9.214979756829164e-05, "loss": 0.5155394554138184, "step": 306450 }, { "epoch": 1.821661881579495, "grad_norm": 1.2609938383102417, "learning_rate": 9.214369650187723e-05, "loss": 0.5324769496917725, "step": 306460 }, { "epoch": 1.8217213236561633, "grad_norm": 1.1837551593780518, "learning_rate": 9.213759552088153e-05, "loss": 0.577024507522583, "step": 306470 }, { "epoch": 1.8217807657328318, "grad_norm": 1.5900992155075073, "learning_rate": 9.213149462533372e-05, "loss": 0.514704704284668, "step": 306480 }, { "epoch": 1.8218402078095002, "grad_norm": 1.4841614961624146, "learning_rate": 9.212539381526302e-05, "loss": 0.49228858947753906, "step": 306490 }, { "epoch": 1.8218996498861684, "grad_norm": 1.3413434028625488, "learning_rate": 9.211929309069858e-05, "loss": 0.5414077758789062, "step": 306500 }, { "epoch": 1.8219590919628368, "grad_norm": 1.3153961896896362, "learning_rate": 9.211319245166961e-05, "loss": 0.5565037727355957, "step": 306510 }, { "epoch": 1.8220185340395052, "grad_norm": 1.3688910007476807, "learning_rate": 9.210709189820528e-05, "loss": 0.5498924255371094, "step": 306520 }, { "epoch": 1.8220779761161736, "grad_norm": 1.3953651189804077, "learning_rate": 9.210099143033478e-05, "loss": 0.5428292751312256, "step": 306530 }, { "epoch": 1.822137418192842, "grad_norm": 1.46930730342865, "learning_rate": 9.209489104808729e-05, "loss": 0.5415294647216797, "step": 306540 }, { "epoch": 1.8221968602695102, "grad_norm": 1.4514447450637817, "learning_rate": 9.2088790751492e-05, "loss": 0.5598176002502442, "step": 306550 }, { "epoch": 1.8222563023461786, "grad_norm": 1.8071833848953247, "learning_rate": 9.208269054057804e-05, "loss": 0.5659080982208252, "step": 306560 }, { "epoch": 1.822315744422847, "grad_norm": 1.3119392395019531, "learning_rate": 9.207659041537464e-05, "loss": 0.5805776596069336, "step": 306570 }, { "epoch": 1.8223751864995155, "grad_norm": 1.395157814025879, "learning_rate": 9.207049037591102e-05, "loss": 0.5672686576843262, "step": 306580 }, { "epoch": 1.8224346285761839, "grad_norm": 2.0423202514648438, "learning_rate": 9.206439042221624e-05, "loss": 0.6170596599578857, "step": 306590 }, { "epoch": 1.8224940706528523, "grad_norm": 1.4802716970443726, "learning_rate": 9.205829055431962e-05, "loss": 0.5198845386505127, "step": 306600 }, { "epoch": 1.8225535127295207, "grad_norm": 1.3529887199401855, "learning_rate": 9.205219077225027e-05, "loss": 0.5527481079101563, "step": 306610 }, { "epoch": 1.8226129548061891, "grad_norm": 1.6020854711532593, "learning_rate": 9.204609107603732e-05, "loss": 0.5979634761810303, "step": 306620 }, { "epoch": 1.8226723968828575, "grad_norm": 1.462152361869812, "learning_rate": 9.203999146571007e-05, "loss": 0.5928138732910156, "step": 306630 }, { "epoch": 1.822731838959526, "grad_norm": 1.357677698135376, "learning_rate": 9.203389194129761e-05, "loss": 0.5225866794586181, "step": 306640 }, { "epoch": 1.8227912810361944, "grad_norm": 1.1046783924102783, "learning_rate": 9.202779250282914e-05, "loss": 0.536879014968872, "step": 306650 }, { "epoch": 1.8228507231128628, "grad_norm": 1.3858578205108643, "learning_rate": 9.202169315033382e-05, "loss": 0.5473029136657714, "step": 306660 }, { "epoch": 1.8229101651895312, "grad_norm": 1.436192274093628, "learning_rate": 9.201559388384085e-05, "loss": 0.5068280220031738, "step": 306670 }, { "epoch": 1.8229696072661996, "grad_norm": 1.294836401939392, "learning_rate": 9.200949470337941e-05, "loss": 0.5181966781616211, "step": 306680 }, { "epoch": 1.8230290493428678, "grad_norm": 1.788809895515442, "learning_rate": 9.200339560897866e-05, "loss": 0.627684497833252, "step": 306690 }, { "epoch": 1.8230884914195362, "grad_norm": 1.5702571868896484, "learning_rate": 9.199729660066778e-05, "loss": 0.5390255928039551, "step": 306700 }, { "epoch": 1.8231479334962046, "grad_norm": 1.2892122268676758, "learning_rate": 9.199119767847597e-05, "loss": 0.5494771003723145, "step": 306710 }, { "epoch": 1.823207375572873, "grad_norm": 1.6812355518341064, "learning_rate": 9.198509884243236e-05, "loss": 0.5860646724700928, "step": 306720 }, { "epoch": 1.8232668176495412, "grad_norm": 1.615878939628601, "learning_rate": 9.197900009256617e-05, "loss": 0.5877942562103271, "step": 306730 }, { "epoch": 1.8233262597262097, "grad_norm": 1.5925415754318237, "learning_rate": 9.197290142890656e-05, "loss": 0.5545839309692383, "step": 306740 }, { "epoch": 1.823385701802878, "grad_norm": 1.0741955041885376, "learning_rate": 9.196680285148268e-05, "loss": 0.5357365608215332, "step": 306750 }, { "epoch": 1.8234451438795465, "grad_norm": 1.4041798114776611, "learning_rate": 9.196070436032371e-05, "loss": 0.5487468719482422, "step": 306760 }, { "epoch": 1.823504585956215, "grad_norm": 1.1926486492156982, "learning_rate": 9.195460595545886e-05, "loss": 0.5177644729614258, "step": 306770 }, { "epoch": 1.8235640280328833, "grad_norm": 1.7796329259872437, "learning_rate": 9.194850763691726e-05, "loss": 0.5156834125518799, "step": 306780 }, { "epoch": 1.8236234701095517, "grad_norm": 1.4162452220916748, "learning_rate": 9.194240940472812e-05, "loss": 0.5201943397521973, "step": 306790 }, { "epoch": 1.8236829121862201, "grad_norm": 1.2606070041656494, "learning_rate": 9.193631125892057e-05, "loss": 0.49413418769836426, "step": 306800 }, { "epoch": 1.8237423542628886, "grad_norm": 1.3154865503311157, "learning_rate": 9.193021319952381e-05, "loss": 0.5808938026428223, "step": 306810 }, { "epoch": 1.823801796339557, "grad_norm": 1.5104767084121704, "learning_rate": 9.192411522656701e-05, "loss": 0.5418447017669678, "step": 306820 }, { "epoch": 1.8238612384162254, "grad_norm": 1.648544192314148, "learning_rate": 9.191801734007935e-05, "loss": 0.5537165641784668, "step": 306830 }, { "epoch": 1.8239206804928938, "grad_norm": 2.436737537384033, "learning_rate": 9.191191954008995e-05, "loss": 0.5213691234588623, "step": 306840 }, { "epoch": 1.8239801225695622, "grad_norm": 1.4066301584243774, "learning_rate": 9.190582182662804e-05, "loss": 0.5349530696868896, "step": 306850 }, { "epoch": 1.8240395646462306, "grad_norm": 1.747025728225708, "learning_rate": 9.189972419972277e-05, "loss": 0.6057238578796387, "step": 306860 }, { "epoch": 1.8240990067228988, "grad_norm": 1.3106184005737305, "learning_rate": 9.18936266594033e-05, "loss": 0.5528493881225586, "step": 306870 }, { "epoch": 1.8241584487995672, "grad_norm": 1.769999384880066, "learning_rate": 9.188752920569879e-05, "loss": 0.5773120403289795, "step": 306880 }, { "epoch": 1.8242178908762356, "grad_norm": 1.4123823642730713, "learning_rate": 9.188143183863843e-05, "loss": 0.5545764923095703, "step": 306890 }, { "epoch": 1.824277332952904, "grad_norm": 1.657487392425537, "learning_rate": 9.187533455825137e-05, "loss": 0.4759946346282959, "step": 306900 }, { "epoch": 1.8243367750295725, "grad_norm": 1.2040519714355469, "learning_rate": 9.18692373645668e-05, "loss": 0.5536631584167481, "step": 306910 }, { "epoch": 1.8243962171062407, "grad_norm": 1.594874620437622, "learning_rate": 9.186314025761387e-05, "loss": 0.5371115684509278, "step": 306920 }, { "epoch": 1.824455659182909, "grad_norm": 1.5581015348434448, "learning_rate": 9.185704323742175e-05, "loss": 0.5834812164306641, "step": 306930 }, { "epoch": 1.8245151012595775, "grad_norm": 1.4458383321762085, "learning_rate": 9.18509463040196e-05, "loss": 0.49727940559387207, "step": 306940 }, { "epoch": 1.824574543336246, "grad_norm": 1.4593127965927124, "learning_rate": 9.184484945743658e-05, "loss": 0.5789632797241211, "step": 306950 }, { "epoch": 1.8246339854129143, "grad_norm": 1.3724397420883179, "learning_rate": 9.183875269770191e-05, "loss": 0.5445877075195312, "step": 306960 }, { "epoch": 1.8246934274895827, "grad_norm": 1.4554657936096191, "learning_rate": 9.183265602484467e-05, "loss": 0.5564483642578125, "step": 306970 }, { "epoch": 1.8247528695662512, "grad_norm": 1.6224604845046997, "learning_rate": 9.182655943889407e-05, "loss": 0.5230812549591064, "step": 306980 }, { "epoch": 1.8248123116429196, "grad_norm": 1.4031150341033936, "learning_rate": 9.182046293987929e-05, "loss": 0.5667957305908203, "step": 306990 }, { "epoch": 1.824871753719588, "grad_norm": 1.7575653791427612, "learning_rate": 9.181436652782946e-05, "loss": 0.5608685970306396, "step": 307000 }, { "epoch": 1.8249311957962564, "grad_norm": 1.5983455181121826, "learning_rate": 9.180827020277381e-05, "loss": 0.5493910789489747, "step": 307010 }, { "epoch": 1.8249906378729248, "grad_norm": 1.765191912651062, "learning_rate": 9.180217396474136e-05, "loss": 0.5858871459960937, "step": 307020 }, { "epoch": 1.8250500799495932, "grad_norm": 1.7030036449432373, "learning_rate": 9.17960778137614e-05, "loss": 0.5199380874633789, "step": 307030 }, { "epoch": 1.8251095220262616, "grad_norm": 1.524170160293579, "learning_rate": 9.178998174986308e-05, "loss": 0.6559634208679199, "step": 307040 }, { "epoch": 1.82516896410293, "grad_norm": 1.2576810121536255, "learning_rate": 9.17838857730755e-05, "loss": 0.5191863059997559, "step": 307050 }, { "epoch": 1.8252284061795983, "grad_norm": 1.343747615814209, "learning_rate": 9.177778988342787e-05, "loss": 0.5572825908660889, "step": 307060 }, { "epoch": 1.8252878482562667, "grad_norm": 1.8212734460830688, "learning_rate": 9.177169408094937e-05, "loss": 0.5592625617980957, "step": 307070 }, { "epoch": 1.825347290332935, "grad_norm": 1.2781001329421997, "learning_rate": 9.176559836566907e-05, "loss": 0.5947688579559326, "step": 307080 }, { "epoch": 1.8254067324096035, "grad_norm": 1.6013422012329102, "learning_rate": 9.175950273761623e-05, "loss": 0.5109230041503906, "step": 307090 }, { "epoch": 1.8254661744862717, "grad_norm": 1.4208825826644897, "learning_rate": 9.175340719681998e-05, "loss": 0.5352577209472656, "step": 307100 }, { "epoch": 1.82552561656294, "grad_norm": 1.6025364398956299, "learning_rate": 9.174731174330942e-05, "loss": 0.5504478454589844, "step": 307110 }, { "epoch": 1.8255850586396085, "grad_norm": 1.5625516176223755, "learning_rate": 9.174121637711376e-05, "loss": 0.5259061813354492, "step": 307120 }, { "epoch": 1.825644500716277, "grad_norm": 1.4639627933502197, "learning_rate": 9.173512109826221e-05, "loss": 0.5692131042480468, "step": 307130 }, { "epoch": 1.8257039427929453, "grad_norm": 1.040420651435852, "learning_rate": 9.172902590678385e-05, "loss": 0.536589527130127, "step": 307140 }, { "epoch": 1.8257633848696138, "grad_norm": 1.115642786026001, "learning_rate": 9.172293080270779e-05, "loss": 0.5241325378417969, "step": 307150 }, { "epoch": 1.8258228269462822, "grad_norm": 1.452785611152649, "learning_rate": 9.171683578606334e-05, "loss": 0.5593595981597901, "step": 307160 }, { "epoch": 1.8258822690229506, "grad_norm": 1.871640920639038, "learning_rate": 9.171074085687956e-05, "loss": 0.6409719467163086, "step": 307170 }, { "epoch": 1.825941711099619, "grad_norm": 1.3825613260269165, "learning_rate": 9.170464601518556e-05, "loss": 0.5282079696655273, "step": 307180 }, { "epoch": 1.8260011531762874, "grad_norm": 1.6103785037994385, "learning_rate": 9.169855126101064e-05, "loss": 0.5547386169433594, "step": 307190 }, { "epoch": 1.8260605952529558, "grad_norm": 1.2316880226135254, "learning_rate": 9.169245659438382e-05, "loss": 0.5329963684082031, "step": 307200 }, { "epoch": 1.8261200373296242, "grad_norm": 1.2392858266830444, "learning_rate": 9.168636201533427e-05, "loss": 0.5750245571136474, "step": 307210 }, { "epoch": 1.8261794794062927, "grad_norm": 1.110192894935608, "learning_rate": 9.168026752389125e-05, "loss": 0.5221151351928711, "step": 307220 }, { "epoch": 1.826238921482961, "grad_norm": 1.3666613101959229, "learning_rate": 9.167417312008382e-05, "loss": 0.5557290077209472, "step": 307230 }, { "epoch": 1.8262983635596293, "grad_norm": 1.0754762887954712, "learning_rate": 9.166807880394113e-05, "loss": 0.5385637283325195, "step": 307240 }, { "epoch": 1.8263578056362977, "grad_norm": 1.3781155347824097, "learning_rate": 9.166198457549237e-05, "loss": 0.564731216430664, "step": 307250 }, { "epoch": 1.826417247712966, "grad_norm": 1.244282603263855, "learning_rate": 9.16558904347667e-05, "loss": 0.5260331153869628, "step": 307260 }, { "epoch": 1.8264766897896345, "grad_norm": 1.2266287803649902, "learning_rate": 9.164979638179325e-05, "loss": 0.5465830326080322, "step": 307270 }, { "epoch": 1.826536131866303, "grad_norm": 1.4589862823486328, "learning_rate": 9.164370241660118e-05, "loss": 0.5454434394836426, "step": 307280 }, { "epoch": 1.8265955739429711, "grad_norm": 1.154876470565796, "learning_rate": 9.163760853921963e-05, "loss": 0.531381893157959, "step": 307290 }, { "epoch": 1.8266550160196395, "grad_norm": 1.379888653755188, "learning_rate": 9.163151474967777e-05, "loss": 0.5549867630004883, "step": 307300 }, { "epoch": 1.826714458096308, "grad_norm": 1.4501087665557861, "learning_rate": 9.162542104800473e-05, "loss": 0.5535185813903809, "step": 307310 }, { "epoch": 1.8267739001729764, "grad_norm": 1.7309247255325317, "learning_rate": 9.161932743422968e-05, "loss": 0.5780137062072754, "step": 307320 }, { "epoch": 1.8268333422496448, "grad_norm": 1.8212802410125732, "learning_rate": 9.161323390838176e-05, "loss": 0.5173139572143555, "step": 307330 }, { "epoch": 1.8268927843263132, "grad_norm": 1.1628375053405762, "learning_rate": 9.16071404704901e-05, "loss": 0.4932899475097656, "step": 307340 }, { "epoch": 1.8269522264029816, "grad_norm": 1.2884420156478882, "learning_rate": 9.160104712058389e-05, "loss": 0.625779390335083, "step": 307350 }, { "epoch": 1.82701166847965, "grad_norm": 1.311460018157959, "learning_rate": 9.159495385869226e-05, "loss": 0.563126516342163, "step": 307360 }, { "epoch": 1.8270711105563184, "grad_norm": 1.4056528806686401, "learning_rate": 9.158886068484434e-05, "loss": 0.5465458869934082, "step": 307370 }, { "epoch": 1.8271305526329868, "grad_norm": 1.589642882347107, "learning_rate": 9.15827675990693e-05, "loss": 0.5707929611206055, "step": 307380 }, { "epoch": 1.8271899947096553, "grad_norm": 1.1945165395736694, "learning_rate": 9.157667460139629e-05, "loss": 0.5455555438995361, "step": 307390 }, { "epoch": 1.8272494367863237, "grad_norm": 1.981232762336731, "learning_rate": 9.157058169185444e-05, "loss": 0.5561008453369141, "step": 307400 }, { "epoch": 1.827308878862992, "grad_norm": 1.4193581342697144, "learning_rate": 9.156448887047289e-05, "loss": 0.5171113014221191, "step": 307410 }, { "epoch": 1.8273683209396605, "grad_norm": 1.2038213014602661, "learning_rate": 9.155839613728084e-05, "loss": 0.5349418640136718, "step": 307420 }, { "epoch": 1.8274277630163287, "grad_norm": 1.2210984230041504, "learning_rate": 9.155230349230737e-05, "loss": 0.5493175506591796, "step": 307430 }, { "epoch": 1.8274872050929971, "grad_norm": 1.4098644256591797, "learning_rate": 9.154621093558164e-05, "loss": 0.5519850730895997, "step": 307440 }, { "epoch": 1.8275466471696655, "grad_norm": 1.8118135929107666, "learning_rate": 9.154011846713281e-05, "loss": 0.5960482597351074, "step": 307450 }, { "epoch": 1.827606089246334, "grad_norm": 1.4967948198318481, "learning_rate": 9.153402608699004e-05, "loss": 0.5246655464172363, "step": 307460 }, { "epoch": 1.8276655313230021, "grad_norm": 1.6676033735275269, "learning_rate": 9.152793379518243e-05, "loss": 0.5133255958557129, "step": 307470 }, { "epoch": 1.8277249733996705, "grad_norm": 1.3479361534118652, "learning_rate": 9.152184159173918e-05, "loss": 0.547940731048584, "step": 307480 }, { "epoch": 1.827784415476339, "grad_norm": 1.3666049242019653, "learning_rate": 9.151574947668938e-05, "loss": 0.589214563369751, "step": 307490 }, { "epoch": 1.8278438575530074, "grad_norm": 1.5904324054718018, "learning_rate": 9.150965745006221e-05, "loss": 0.5214151859283447, "step": 307500 }, { "epoch": 1.8279032996296758, "grad_norm": 1.372914433479309, "learning_rate": 9.150356551188677e-05, "loss": 0.5440092563629151, "step": 307510 }, { "epoch": 1.8279627417063442, "grad_norm": 1.3305107355117798, "learning_rate": 9.149747366219224e-05, "loss": 0.5509307861328125, "step": 307520 }, { "epoch": 1.8280221837830126, "grad_norm": 1.3429486751556396, "learning_rate": 9.149138190100776e-05, "loss": 0.5680171966552734, "step": 307530 }, { "epoch": 1.828081625859681, "grad_norm": 1.302599549293518, "learning_rate": 9.148529022836243e-05, "loss": 0.5707714080810546, "step": 307540 }, { "epoch": 1.8281410679363495, "grad_norm": 1.5364789962768555, "learning_rate": 9.147919864428545e-05, "loss": 0.5601982116699219, "step": 307550 }, { "epoch": 1.8282005100130179, "grad_norm": 1.6117743253707886, "learning_rate": 9.147310714880595e-05, "loss": 0.5964918613433838, "step": 307560 }, { "epoch": 1.8282599520896863, "grad_norm": 1.9016209840774536, "learning_rate": 9.146701574195297e-05, "loss": 0.614683198928833, "step": 307570 }, { "epoch": 1.8283193941663547, "grad_norm": 1.6445177793502808, "learning_rate": 9.14609244237558e-05, "loss": 0.5477253913879394, "step": 307580 }, { "epoch": 1.828378836243023, "grad_norm": 1.076629877090454, "learning_rate": 9.145483319424353e-05, "loss": 0.5498065948486328, "step": 307590 }, { "epoch": 1.8284382783196915, "grad_norm": 1.3938374519348145, "learning_rate": 9.14487420534452e-05, "loss": 0.6151310443878174, "step": 307600 }, { "epoch": 1.8284977203963597, "grad_norm": 1.573121428489685, "learning_rate": 9.144265100139007e-05, "loss": 0.5360690116882324, "step": 307610 }, { "epoch": 1.8285571624730281, "grad_norm": 1.2829091548919678, "learning_rate": 9.143656003810723e-05, "loss": 0.5756824970245361, "step": 307620 }, { "epoch": 1.8286166045496965, "grad_norm": 1.4097766876220703, "learning_rate": 9.143046916362585e-05, "loss": 0.5758265972137451, "step": 307630 }, { "epoch": 1.828676046626365, "grad_norm": 1.496392011642456, "learning_rate": 9.142437837797497e-05, "loss": 0.5339232444763183, "step": 307640 }, { "epoch": 1.8287354887030334, "grad_norm": 1.4790374040603638, "learning_rate": 9.141828768118386e-05, "loss": 0.6011991500854492, "step": 307650 }, { "epoch": 1.8287949307797016, "grad_norm": 1.354835033416748, "learning_rate": 9.141219707328155e-05, "loss": 0.5361952781677246, "step": 307660 }, { "epoch": 1.82885437285637, "grad_norm": 0.9826128482818604, "learning_rate": 9.140610655429718e-05, "loss": 0.4776618957519531, "step": 307670 }, { "epoch": 1.8289138149330384, "grad_norm": 1.402296543121338, "learning_rate": 9.140001612426e-05, "loss": 0.5447193145751953, "step": 307680 }, { "epoch": 1.8289732570097068, "grad_norm": 1.4054124355316162, "learning_rate": 9.139392578319903e-05, "loss": 0.5449654579162597, "step": 307690 }, { "epoch": 1.8290326990863752, "grad_norm": 1.39351487159729, "learning_rate": 9.138783553114339e-05, "loss": 0.5248287200927735, "step": 307700 }, { "epoch": 1.8290921411630436, "grad_norm": 1.4867981672286987, "learning_rate": 9.138174536812234e-05, "loss": 0.5349431037902832, "step": 307710 }, { "epoch": 1.829151583239712, "grad_norm": 1.6060785055160522, "learning_rate": 9.13756552941649e-05, "loss": 0.5089271545410157, "step": 307720 }, { "epoch": 1.8292110253163805, "grad_norm": 1.5973215103149414, "learning_rate": 9.136956530930021e-05, "loss": 0.5567584991455078, "step": 307730 }, { "epoch": 1.8292704673930489, "grad_norm": 1.5280619859695435, "learning_rate": 9.136347541355749e-05, "loss": 0.5324803352355957, "step": 307740 }, { "epoch": 1.8293299094697173, "grad_norm": 1.480610966682434, "learning_rate": 9.135738560696578e-05, "loss": 0.5809444427490235, "step": 307750 }, { "epoch": 1.8293893515463857, "grad_norm": 1.2332205772399902, "learning_rate": 9.135129588955427e-05, "loss": 0.5251653671264649, "step": 307760 }, { "epoch": 1.8294487936230541, "grad_norm": 1.3787450790405273, "learning_rate": 9.134520626135203e-05, "loss": 0.576688814163208, "step": 307770 }, { "epoch": 1.8295082356997225, "grad_norm": 1.5319243669509888, "learning_rate": 9.133911672238827e-05, "loss": 0.5455000400543213, "step": 307780 }, { "epoch": 1.829567677776391, "grad_norm": 1.6284481287002563, "learning_rate": 9.133302727269204e-05, "loss": 0.5999933242797851, "step": 307790 }, { "epoch": 1.8296271198530591, "grad_norm": 1.2251908779144287, "learning_rate": 9.13269379122925e-05, "loss": 0.5444634437561036, "step": 307800 }, { "epoch": 1.8296865619297276, "grad_norm": 1.1318461894989014, "learning_rate": 9.132084864121882e-05, "loss": 0.6228902339935303, "step": 307810 }, { "epoch": 1.829746004006396, "grad_norm": 1.5128052234649658, "learning_rate": 9.131475945950008e-05, "loss": 0.5214720249176026, "step": 307820 }, { "epoch": 1.8298054460830644, "grad_norm": 1.2113146781921387, "learning_rate": 9.13086703671654e-05, "loss": 0.5339139461517334, "step": 307830 }, { "epoch": 1.8298648881597326, "grad_norm": 1.5980138778686523, "learning_rate": 9.130258136424396e-05, "loss": 0.5299782752990723, "step": 307840 }, { "epoch": 1.829924330236401, "grad_norm": 1.4184740781784058, "learning_rate": 9.129649245076486e-05, "loss": 0.5526103973388672, "step": 307850 }, { "epoch": 1.8299837723130694, "grad_norm": 1.457438588142395, "learning_rate": 9.129040362675722e-05, "loss": 0.53297119140625, "step": 307860 }, { "epoch": 1.8300432143897378, "grad_norm": 1.2808781862258911, "learning_rate": 9.128431489225018e-05, "loss": 0.5710843086242676, "step": 307870 }, { "epoch": 1.8301026564664062, "grad_norm": 1.1108391284942627, "learning_rate": 9.127822624727287e-05, "loss": 0.5486706733703614, "step": 307880 }, { "epoch": 1.8301620985430747, "grad_norm": 1.3684052228927612, "learning_rate": 9.127213769185438e-05, "loss": 0.5358392715454101, "step": 307890 }, { "epoch": 1.830221540619743, "grad_norm": 1.4043432474136353, "learning_rate": 9.126604922602388e-05, "loss": 0.5918696403503418, "step": 307900 }, { "epoch": 1.8302809826964115, "grad_norm": 1.7662336826324463, "learning_rate": 9.12599608498105e-05, "loss": 0.5112479209899903, "step": 307910 }, { "epoch": 1.83034042477308, "grad_norm": 1.3794970512390137, "learning_rate": 9.125387256324331e-05, "loss": 0.5425763130187988, "step": 307920 }, { "epoch": 1.8303998668497483, "grad_norm": 1.295785903930664, "learning_rate": 9.124778436635147e-05, "loss": 0.5430099487304687, "step": 307930 }, { "epoch": 1.8304593089264167, "grad_norm": 1.3047317266464233, "learning_rate": 9.124169625916412e-05, "loss": 0.5109533309936524, "step": 307940 }, { "epoch": 1.8305187510030851, "grad_norm": 2.0988211631774902, "learning_rate": 9.123560824171035e-05, "loss": 0.5480348587036132, "step": 307950 }, { "epoch": 1.8305781930797536, "grad_norm": 1.2671902179718018, "learning_rate": 9.12295203140193e-05, "loss": 0.5532999515533448, "step": 307960 }, { "epoch": 1.830637635156422, "grad_norm": 1.5078372955322266, "learning_rate": 9.12234324761201e-05, "loss": 0.5781373977661133, "step": 307970 }, { "epoch": 1.8306970772330902, "grad_norm": 1.406212329864502, "learning_rate": 9.121734472804187e-05, "loss": 0.5404083251953125, "step": 307980 }, { "epoch": 1.8307565193097586, "grad_norm": 1.4069961309432983, "learning_rate": 9.121125706981372e-05, "loss": 0.46149892807006837, "step": 307990 }, { "epoch": 1.830815961386427, "grad_norm": 1.4149142503738403, "learning_rate": 9.120516950146474e-05, "loss": 0.5139621734619141, "step": 308000 }, { "epoch": 1.8308754034630954, "grad_norm": 1.2220083475112915, "learning_rate": 9.119908202302412e-05, "loss": 0.5609954357147217, "step": 308010 }, { "epoch": 1.8309348455397638, "grad_norm": 1.7403842210769653, "learning_rate": 9.119299463452098e-05, "loss": 0.5464208126068115, "step": 308020 }, { "epoch": 1.830994287616432, "grad_norm": 1.5388407707214355, "learning_rate": 9.118690733598432e-05, "loss": 0.5888049125671386, "step": 308030 }, { "epoch": 1.8310537296931004, "grad_norm": 1.439518928527832, "learning_rate": 9.11808201274434e-05, "loss": 0.5458858489990235, "step": 308040 }, { "epoch": 1.8311131717697688, "grad_norm": 1.5675855875015259, "learning_rate": 9.117473300892731e-05, "loss": 0.539248275756836, "step": 308050 }, { "epoch": 1.8311726138464373, "grad_norm": 1.2627224922180176, "learning_rate": 9.116864598046509e-05, "loss": 0.5055134773254395, "step": 308060 }, { "epoch": 1.8312320559231057, "grad_norm": 1.4160267114639282, "learning_rate": 9.116255904208594e-05, "loss": 0.5418015480041504, "step": 308070 }, { "epoch": 1.831291497999774, "grad_norm": 1.4018495082855225, "learning_rate": 9.115647219381898e-05, "loss": 0.5403491973876953, "step": 308080 }, { "epoch": 1.8313509400764425, "grad_norm": 1.5958937406539917, "learning_rate": 9.115038543569323e-05, "loss": 0.5818790435791016, "step": 308090 }, { "epoch": 1.831410382153111, "grad_norm": 1.7643455266952515, "learning_rate": 9.114429876773793e-05, "loss": 0.6062119483947754, "step": 308100 }, { "epoch": 1.8314698242297793, "grad_norm": 1.5359278917312622, "learning_rate": 9.113821218998216e-05, "loss": 0.5588449478149414, "step": 308110 }, { "epoch": 1.8315292663064477, "grad_norm": 1.5406018495559692, "learning_rate": 9.113212570245499e-05, "loss": 0.530008602142334, "step": 308120 }, { "epoch": 1.8315887083831162, "grad_norm": 1.224499225616455, "learning_rate": 9.112603930518553e-05, "loss": 0.5071337223052979, "step": 308130 }, { "epoch": 1.8316481504597846, "grad_norm": 1.3207591772079468, "learning_rate": 9.1119952998203e-05, "loss": 0.5415627956390381, "step": 308140 }, { "epoch": 1.831707592536453, "grad_norm": 1.2152303457260132, "learning_rate": 9.111386678153639e-05, "loss": 0.5557333469390869, "step": 308150 }, { "epoch": 1.8317670346131214, "grad_norm": 2.00854754447937, "learning_rate": 9.110778065521486e-05, "loss": 0.5860536575317383, "step": 308160 }, { "epoch": 1.8318264766897896, "grad_norm": 1.391134262084961, "learning_rate": 9.110169461926759e-05, "loss": 0.5247431755065918, "step": 308170 }, { "epoch": 1.831885918766458, "grad_norm": 1.7594692707061768, "learning_rate": 9.109560867372361e-05, "loss": 0.5406868934631348, "step": 308180 }, { "epoch": 1.8319453608431264, "grad_norm": 1.5410287380218506, "learning_rate": 9.108952281861203e-05, "loss": 0.5876909255981445, "step": 308190 }, { "epoch": 1.8320048029197948, "grad_norm": 1.3544808626174927, "learning_rate": 9.108343705396205e-05, "loss": 0.5890236377716065, "step": 308200 }, { "epoch": 1.832064244996463, "grad_norm": 1.4087198972702026, "learning_rate": 9.107735137980269e-05, "loss": 0.5104796409606933, "step": 308210 }, { "epoch": 1.8321236870731314, "grad_norm": 1.1249436140060425, "learning_rate": 9.107126579616307e-05, "loss": 0.5369128227233887, "step": 308220 }, { "epoch": 1.8321831291497999, "grad_norm": 1.5084699392318726, "learning_rate": 9.106518030307238e-05, "loss": 0.5555883407592773, "step": 308230 }, { "epoch": 1.8322425712264683, "grad_norm": 1.3713843822479248, "learning_rate": 9.105909490055968e-05, "loss": 0.4987644195556641, "step": 308240 }, { "epoch": 1.8323020133031367, "grad_norm": 1.7301390171051025, "learning_rate": 9.105300958865406e-05, "loss": 0.5624915599822998, "step": 308250 }, { "epoch": 1.832361455379805, "grad_norm": 1.1885998249053955, "learning_rate": 9.104692436738462e-05, "loss": 0.5711594104766846, "step": 308260 }, { "epoch": 1.8324208974564735, "grad_norm": 1.292506456375122, "learning_rate": 9.104083923678056e-05, "loss": 0.4979253768920898, "step": 308270 }, { "epoch": 1.832480339533142, "grad_norm": 1.2498865127563477, "learning_rate": 9.103475419687089e-05, "loss": 0.5562135219573975, "step": 308280 }, { "epoch": 1.8325397816098103, "grad_norm": 1.563881516456604, "learning_rate": 9.102866924768473e-05, "loss": 0.5496511459350586, "step": 308290 }, { "epoch": 1.8325992236864788, "grad_norm": 1.393968939781189, "learning_rate": 9.102258438925129e-05, "loss": 0.5331942558288574, "step": 308300 }, { "epoch": 1.8326586657631472, "grad_norm": 1.6980667114257812, "learning_rate": 9.101649962159957e-05, "loss": 0.6214739799499511, "step": 308310 }, { "epoch": 1.8327181078398156, "grad_norm": 1.289724349975586, "learning_rate": 9.10104149447587e-05, "loss": 0.5449236869812012, "step": 308320 }, { "epoch": 1.832777549916484, "grad_norm": 1.648949146270752, "learning_rate": 9.100433035875782e-05, "loss": 0.5917404174804688, "step": 308330 }, { "epoch": 1.8328369919931524, "grad_norm": 1.6993778944015503, "learning_rate": 9.099824586362599e-05, "loss": 0.5511541843414307, "step": 308340 }, { "epoch": 1.8328964340698206, "grad_norm": 1.3862364292144775, "learning_rate": 9.099216145939238e-05, "loss": 0.5285686492919922, "step": 308350 }, { "epoch": 1.832955876146489, "grad_norm": 1.2677644491195679, "learning_rate": 9.0986077146086e-05, "loss": 0.5858426570892334, "step": 308360 }, { "epoch": 1.8330153182231574, "grad_norm": 1.5230485200881958, "learning_rate": 9.097999292373607e-05, "loss": 0.5210762977600097, "step": 308370 }, { "epoch": 1.8330747602998259, "grad_norm": 1.4642587900161743, "learning_rate": 9.097390879237162e-05, "loss": 0.5321822166442871, "step": 308380 }, { "epoch": 1.8331342023764943, "grad_norm": 1.3785409927368164, "learning_rate": 9.096782475202175e-05, "loss": 0.6138716697692871, "step": 308390 }, { "epoch": 1.8331936444531625, "grad_norm": 1.5035858154296875, "learning_rate": 9.09617408027156e-05, "loss": 0.5664666175842286, "step": 308400 }, { "epoch": 1.8332530865298309, "grad_norm": 1.3412526845932007, "learning_rate": 9.095565694448229e-05, "loss": 0.5998114585876465, "step": 308410 }, { "epoch": 1.8333125286064993, "grad_norm": 1.6182434558868408, "learning_rate": 9.094957317735085e-05, "loss": 0.5867298126220704, "step": 308420 }, { "epoch": 1.8333719706831677, "grad_norm": 1.40326726436615, "learning_rate": 9.094348950135045e-05, "loss": 0.6186293601989746, "step": 308430 }, { "epoch": 1.8334314127598361, "grad_norm": 1.6888548135757446, "learning_rate": 9.093740591651016e-05, "loss": 0.548245906829834, "step": 308440 }, { "epoch": 1.8334908548365045, "grad_norm": 1.1159085035324097, "learning_rate": 9.093132242285908e-05, "loss": 0.5029245376586914, "step": 308450 }, { "epoch": 1.833550296913173, "grad_norm": 1.5445295572280884, "learning_rate": 9.092523902042634e-05, "loss": 0.589070177078247, "step": 308460 }, { "epoch": 1.8336097389898414, "grad_norm": 1.3992023468017578, "learning_rate": 9.091915570924103e-05, "loss": 0.5935291290283203, "step": 308470 }, { "epoch": 1.8336691810665098, "grad_norm": 1.6204980611801147, "learning_rate": 9.091307248933223e-05, "loss": 0.5602257728576661, "step": 308480 }, { "epoch": 1.8337286231431782, "grad_norm": 1.436199426651001, "learning_rate": 9.090698936072903e-05, "loss": 0.5042038917541504, "step": 308490 }, { "epoch": 1.8337880652198466, "grad_norm": 1.5008546113967896, "learning_rate": 9.09009063234606e-05, "loss": 0.5603617668151856, "step": 308500 }, { "epoch": 1.833847507296515, "grad_norm": 1.0885509252548218, "learning_rate": 9.089482337755597e-05, "loss": 0.5244177341461181, "step": 308510 }, { "epoch": 1.8339069493731834, "grad_norm": 1.3390644788742065, "learning_rate": 9.088874052304425e-05, "loss": 0.5541417121887207, "step": 308520 }, { "epoch": 1.8339663914498519, "grad_norm": 1.2183852195739746, "learning_rate": 9.088265775995456e-05, "loss": 0.48863492012023924, "step": 308530 }, { "epoch": 1.83402583352652, "grad_norm": 1.5184566974639893, "learning_rate": 9.087657508831601e-05, "loss": 0.6277225494384766, "step": 308540 }, { "epoch": 1.8340852756031885, "grad_norm": 1.5742329359054565, "learning_rate": 9.087049250815765e-05, "loss": 0.5095473289489746, "step": 308550 }, { "epoch": 1.8341447176798569, "grad_norm": 1.4209260940551758, "learning_rate": 9.086441001950861e-05, "loss": 0.513425874710083, "step": 308560 }, { "epoch": 1.8342041597565253, "grad_norm": 1.4226957559585571, "learning_rate": 9.085832762239796e-05, "loss": 0.5602824211120605, "step": 308570 }, { "epoch": 1.8342636018331935, "grad_norm": 1.3181517124176025, "learning_rate": 9.085224531685483e-05, "loss": 0.5261548042297364, "step": 308580 }, { "epoch": 1.834323043909862, "grad_norm": 1.680849313735962, "learning_rate": 9.08461631029083e-05, "loss": 0.5663530349731445, "step": 308590 }, { "epoch": 1.8343824859865303, "grad_norm": 1.2963073253631592, "learning_rate": 9.084008098058747e-05, "loss": 0.5379558086395264, "step": 308600 }, { "epoch": 1.8344419280631987, "grad_norm": 1.3153761625289917, "learning_rate": 9.083399894992146e-05, "loss": 0.5233516693115234, "step": 308610 }, { "epoch": 1.8345013701398671, "grad_norm": 1.3006796836853027, "learning_rate": 9.082791701093927e-05, "loss": 0.5207572937011719, "step": 308620 }, { "epoch": 1.8345608122165356, "grad_norm": 1.2064541578292847, "learning_rate": 9.082183516367013e-05, "loss": 0.495394229888916, "step": 308630 }, { "epoch": 1.834620254293204, "grad_norm": 1.049546718597412, "learning_rate": 9.081575340814303e-05, "loss": 0.5219568252563477, "step": 308640 }, { "epoch": 1.8346796963698724, "grad_norm": 1.7395684719085693, "learning_rate": 9.080967174438706e-05, "loss": 0.5724915504455567, "step": 308650 }, { "epoch": 1.8347391384465408, "grad_norm": 1.358994483947754, "learning_rate": 9.080359017243141e-05, "loss": 0.531112813949585, "step": 308660 }, { "epoch": 1.8347985805232092, "grad_norm": 1.479658842086792, "learning_rate": 9.079750869230508e-05, "loss": 0.570194673538208, "step": 308670 }, { "epoch": 1.8348580225998776, "grad_norm": 1.225661039352417, "learning_rate": 9.079142730403716e-05, "loss": 0.5350664138793946, "step": 308680 }, { "epoch": 1.834917464676546, "grad_norm": 1.6325174570083618, "learning_rate": 9.078534600765684e-05, "loss": 0.5442623138427735, "step": 308690 }, { "epoch": 1.8349769067532145, "grad_norm": 1.2646114826202393, "learning_rate": 9.077926480319312e-05, "loss": 0.5489896774291992, "step": 308700 }, { "epoch": 1.8350363488298829, "grad_norm": 1.1726596355438232, "learning_rate": 9.077318369067512e-05, "loss": 0.5219292640686035, "step": 308710 }, { "epoch": 1.835095790906551, "grad_norm": 1.3093795776367188, "learning_rate": 9.076710267013191e-05, "loss": 0.5647598266601562, "step": 308720 }, { "epoch": 1.8351552329832195, "grad_norm": 1.4030518531799316, "learning_rate": 9.07610217415926e-05, "loss": 0.5407784461975098, "step": 308730 }, { "epoch": 1.835214675059888, "grad_norm": 1.3970729112625122, "learning_rate": 9.07549409050863e-05, "loss": 0.5063816547393799, "step": 308740 }, { "epoch": 1.8352741171365563, "grad_norm": 1.2395983934402466, "learning_rate": 9.074886016064202e-05, "loss": 0.5517080307006836, "step": 308750 }, { "epoch": 1.8353335592132247, "grad_norm": 1.1882240772247314, "learning_rate": 9.074277950828894e-05, "loss": 0.5562763690948487, "step": 308760 }, { "epoch": 1.835393001289893, "grad_norm": 1.2104498147964478, "learning_rate": 9.07366989480561e-05, "loss": 0.5399939537048339, "step": 308770 }, { "epoch": 1.8354524433665613, "grad_norm": 1.899678111076355, "learning_rate": 9.073061847997259e-05, "loss": 0.6090151786804199, "step": 308780 }, { "epoch": 1.8355118854432297, "grad_norm": 1.273658275604248, "learning_rate": 9.072453810406751e-05, "loss": 0.591786003112793, "step": 308790 }, { "epoch": 1.8355713275198982, "grad_norm": 1.711590051651001, "learning_rate": 9.071845782036996e-05, "loss": 0.5576365470886231, "step": 308800 }, { "epoch": 1.8356307695965666, "grad_norm": 1.2126741409301758, "learning_rate": 9.071237762890896e-05, "loss": 0.5760164260864258, "step": 308810 }, { "epoch": 1.835690211673235, "grad_norm": 0.928899347782135, "learning_rate": 9.070629752971368e-05, "loss": 0.5002140998840332, "step": 308820 }, { "epoch": 1.8357496537499034, "grad_norm": 1.5363705158233643, "learning_rate": 9.070021752281317e-05, "loss": 0.5472921848297119, "step": 308830 }, { "epoch": 1.8358090958265718, "grad_norm": 1.4263614416122437, "learning_rate": 9.06941376082365e-05, "loss": 0.544059944152832, "step": 308840 }, { "epoch": 1.8358685379032402, "grad_norm": 1.3816677331924438, "learning_rate": 9.068805778601277e-05, "loss": 0.5678693294525147, "step": 308850 }, { "epoch": 1.8359279799799086, "grad_norm": 1.395591139793396, "learning_rate": 9.068197805617107e-05, "loss": 0.5389270305633544, "step": 308860 }, { "epoch": 1.835987422056577, "grad_norm": 1.3096814155578613, "learning_rate": 9.067589841874047e-05, "loss": 0.4978497982025146, "step": 308870 }, { "epoch": 1.8360468641332455, "grad_norm": 1.4140026569366455, "learning_rate": 9.066981887375001e-05, "loss": 0.5650528907775879, "step": 308880 }, { "epoch": 1.8361063062099139, "grad_norm": 1.3495962619781494, "learning_rate": 9.066373942122887e-05, "loss": 0.533571720123291, "step": 308890 }, { "epoch": 1.8361657482865823, "grad_norm": 1.358783483505249, "learning_rate": 9.065766006120609e-05, "loss": 0.5301095962524414, "step": 308900 }, { "epoch": 1.8362251903632505, "grad_norm": 1.3509957790374756, "learning_rate": 9.06515807937107e-05, "loss": 0.552674388885498, "step": 308910 }, { "epoch": 1.836284632439919, "grad_norm": 1.4101954698562622, "learning_rate": 9.064550161877185e-05, "loss": 0.5455501556396485, "step": 308920 }, { "epoch": 1.8363440745165873, "grad_norm": 2.008521556854248, "learning_rate": 9.06394225364186e-05, "loss": 0.5797513961791992, "step": 308930 }, { "epoch": 1.8364035165932557, "grad_norm": 1.1775727272033691, "learning_rate": 9.063334354668001e-05, "loss": 0.537373399734497, "step": 308940 }, { "epoch": 1.836462958669924, "grad_norm": 1.4528603553771973, "learning_rate": 9.062726464958518e-05, "loss": 0.5570435047149658, "step": 308950 }, { "epoch": 1.8365224007465923, "grad_norm": 1.3110427856445312, "learning_rate": 9.062118584516319e-05, "loss": 0.5954395294189453, "step": 308960 }, { "epoch": 1.8365818428232608, "grad_norm": 1.2567312717437744, "learning_rate": 9.061510713344312e-05, "loss": 0.5285653591156005, "step": 308970 }, { "epoch": 1.8366412848999292, "grad_norm": 1.7222929000854492, "learning_rate": 9.060902851445404e-05, "loss": 0.5703640937805176, "step": 308980 }, { "epoch": 1.8367007269765976, "grad_norm": 1.728713870048523, "learning_rate": 9.060294998822503e-05, "loss": 0.5685261726379395, "step": 308990 }, { "epoch": 1.836760169053266, "grad_norm": 1.375693917274475, "learning_rate": 9.059687155478515e-05, "loss": 0.5061631679534913, "step": 309000 }, { "epoch": 1.8368196111299344, "grad_norm": 1.4795374870300293, "learning_rate": 9.05907932141635e-05, "loss": 0.5966526985168457, "step": 309010 }, { "epoch": 1.8368790532066028, "grad_norm": 1.3830894231796265, "learning_rate": 9.058471496638916e-05, "loss": 0.5635495185852051, "step": 309020 }, { "epoch": 1.8369384952832712, "grad_norm": 1.447787880897522, "learning_rate": 9.05786368114912e-05, "loss": 0.49829511642456054, "step": 309030 }, { "epoch": 1.8369979373599397, "grad_norm": 1.5251200199127197, "learning_rate": 9.057255874949871e-05, "loss": 0.5314714431762695, "step": 309040 }, { "epoch": 1.837057379436608, "grad_norm": 1.2908538579940796, "learning_rate": 9.056648078044073e-05, "loss": 0.5444219589233399, "step": 309050 }, { "epoch": 1.8371168215132765, "grad_norm": 1.6865471601486206, "learning_rate": 9.056040290434635e-05, "loss": 0.5637101173400879, "step": 309060 }, { "epoch": 1.837176263589945, "grad_norm": 1.638740062713623, "learning_rate": 9.055432512124464e-05, "loss": 0.5748969554901123, "step": 309070 }, { "epoch": 1.8372357056666133, "grad_norm": 1.1713227033615112, "learning_rate": 9.054824743116472e-05, "loss": 0.654116153717041, "step": 309080 }, { "epoch": 1.8372951477432815, "grad_norm": 1.711635947227478, "learning_rate": 9.054216983413562e-05, "loss": 0.5131523609161377, "step": 309090 }, { "epoch": 1.83735458981995, "grad_norm": 1.4271754026412964, "learning_rate": 9.053609233018643e-05, "loss": 0.5287901878356933, "step": 309100 }, { "epoch": 1.8374140318966183, "grad_norm": 1.2620043754577637, "learning_rate": 9.053001491934616e-05, "loss": 0.5358970642089844, "step": 309110 }, { "epoch": 1.8374734739732868, "grad_norm": 2.563744306564331, "learning_rate": 9.052393760164398e-05, "loss": 0.5468374252319336, "step": 309120 }, { "epoch": 1.8375329160499552, "grad_norm": 1.4267317056655884, "learning_rate": 9.051786037710891e-05, "loss": 0.5477773189544678, "step": 309130 }, { "epoch": 1.8375923581266234, "grad_norm": 1.4601573944091797, "learning_rate": 9.051178324577001e-05, "loss": 0.5089803695678711, "step": 309140 }, { "epoch": 1.8376518002032918, "grad_norm": 1.291541576385498, "learning_rate": 9.050570620765639e-05, "loss": 0.5251069068908691, "step": 309150 }, { "epoch": 1.8377112422799602, "grad_norm": 1.5877039432525635, "learning_rate": 9.049962926279712e-05, "loss": 0.5331707954406738, "step": 309160 }, { "epoch": 1.8377706843566286, "grad_norm": 1.3876609802246094, "learning_rate": 9.049355241122119e-05, "loss": 0.5828153610229492, "step": 309170 }, { "epoch": 1.837830126433297, "grad_norm": 1.411560297012329, "learning_rate": 9.048747565295779e-05, "loss": 0.5506782531738281, "step": 309180 }, { "epoch": 1.8378895685099654, "grad_norm": 1.2873867750167847, "learning_rate": 9.048139898803592e-05, "loss": 0.5490650177001953, "step": 309190 }, { "epoch": 1.8379490105866338, "grad_norm": 1.51024329662323, "learning_rate": 9.047532241648464e-05, "loss": 0.5947818756103516, "step": 309200 }, { "epoch": 1.8380084526633023, "grad_norm": 1.2888119220733643, "learning_rate": 9.046924593833302e-05, "loss": 0.5367166519165039, "step": 309210 }, { "epoch": 1.8380678947399707, "grad_norm": 1.2754839658737183, "learning_rate": 9.046316955361021e-05, "loss": 0.5587543964385986, "step": 309220 }, { "epoch": 1.838127336816639, "grad_norm": 1.651525855064392, "learning_rate": 9.045709326234517e-05, "loss": 0.5607716560363769, "step": 309230 }, { "epoch": 1.8381867788933075, "grad_norm": 1.307879090309143, "learning_rate": 9.045101706456698e-05, "loss": 0.5883434772491455, "step": 309240 }, { "epoch": 1.838246220969976, "grad_norm": 1.479605793952942, "learning_rate": 9.044494096030478e-05, "loss": 0.511957836151123, "step": 309250 }, { "epoch": 1.8383056630466443, "grad_norm": 1.5422089099884033, "learning_rate": 9.043886494958757e-05, "loss": 0.5682218551635743, "step": 309260 }, { "epoch": 1.8383651051233127, "grad_norm": 1.3291206359863281, "learning_rate": 9.043278903244443e-05, "loss": 0.5457810401916504, "step": 309270 }, { "epoch": 1.838424547199981, "grad_norm": 0.9435238838195801, "learning_rate": 9.042671320890446e-05, "loss": 0.5360753536224365, "step": 309280 }, { "epoch": 1.8384839892766494, "grad_norm": 1.5245487689971924, "learning_rate": 9.042063747899669e-05, "loss": 0.576384162902832, "step": 309290 }, { "epoch": 1.8385434313533178, "grad_norm": 1.5119459629058838, "learning_rate": 9.041456184275017e-05, "loss": 0.5219335556030273, "step": 309300 }, { "epoch": 1.8386028734299862, "grad_norm": 1.3056272268295288, "learning_rate": 9.040848630019401e-05, "loss": 0.5552515029907227, "step": 309310 }, { "epoch": 1.8386623155066544, "grad_norm": 1.3881055116653442, "learning_rate": 9.040241085135725e-05, "loss": 0.5449082374572753, "step": 309320 }, { "epoch": 1.8387217575833228, "grad_norm": 1.7522876262664795, "learning_rate": 9.039633549626893e-05, "loss": 0.5225655555725097, "step": 309330 }, { "epoch": 1.8387811996599912, "grad_norm": 1.4125410318374634, "learning_rate": 9.039026023495816e-05, "loss": 0.5705069541931153, "step": 309340 }, { "epoch": 1.8388406417366596, "grad_norm": 1.2074599266052246, "learning_rate": 9.038418506745396e-05, "loss": 0.5304847240447998, "step": 309350 }, { "epoch": 1.838900083813328, "grad_norm": 1.4449752569198608, "learning_rate": 9.037810999378542e-05, "loss": 0.5265171527862549, "step": 309360 }, { "epoch": 1.8389595258899964, "grad_norm": 1.891911268234253, "learning_rate": 9.037203501398158e-05, "loss": 0.5745703697204589, "step": 309370 }, { "epoch": 1.8390189679666649, "grad_norm": 1.256363034248352, "learning_rate": 9.036596012807151e-05, "loss": 0.6022771835327149, "step": 309380 }, { "epoch": 1.8390784100433333, "grad_norm": 1.2101484537124634, "learning_rate": 9.035988533608426e-05, "loss": 0.5813080787658691, "step": 309390 }, { "epoch": 1.8391378521200017, "grad_norm": 1.2619885206222534, "learning_rate": 9.035381063804891e-05, "loss": 0.5099242687225342, "step": 309400 }, { "epoch": 1.83919729419667, "grad_norm": 1.2182440757751465, "learning_rate": 9.034773603399452e-05, "loss": 0.5108894824981689, "step": 309410 }, { "epoch": 1.8392567362733385, "grad_norm": 1.42595636844635, "learning_rate": 9.034166152395011e-05, "loss": 0.5466748237609863, "step": 309420 }, { "epoch": 1.839316178350007, "grad_norm": 1.3213037252426147, "learning_rate": 9.033558710794479e-05, "loss": 0.6154451370239258, "step": 309430 }, { "epoch": 1.8393756204266754, "grad_norm": 1.1131831407546997, "learning_rate": 9.032951278600758e-05, "loss": 0.5173774719238281, "step": 309440 }, { "epoch": 1.8394350625033438, "grad_norm": 1.6808207035064697, "learning_rate": 9.032343855816759e-05, "loss": 0.5273462295532226, "step": 309450 }, { "epoch": 1.839494504580012, "grad_norm": 1.180261254310608, "learning_rate": 9.031736442445383e-05, "loss": 0.5489483833312988, "step": 309460 }, { "epoch": 1.8395539466566804, "grad_norm": 1.3876361846923828, "learning_rate": 9.03112903848953e-05, "loss": 0.6065744400024414, "step": 309470 }, { "epoch": 1.8396133887333488, "grad_norm": 1.3909891843795776, "learning_rate": 9.03052164395212e-05, "loss": 0.5109045028686523, "step": 309480 }, { "epoch": 1.8396728308100172, "grad_norm": 1.7781645059585571, "learning_rate": 9.029914258836047e-05, "loss": 0.6144997596740722, "step": 309490 }, { "epoch": 1.8397322728866856, "grad_norm": 1.484361171722412, "learning_rate": 9.02930688314422e-05, "loss": 0.5220744609832764, "step": 309500 }, { "epoch": 1.8397917149633538, "grad_norm": 1.6121320724487305, "learning_rate": 9.028699516879546e-05, "loss": 0.6428308963775635, "step": 309510 }, { "epoch": 1.8398511570400222, "grad_norm": 1.809133768081665, "learning_rate": 9.028092160044933e-05, "loss": 0.4789740562438965, "step": 309520 }, { "epoch": 1.8399105991166906, "grad_norm": 1.3374392986297607, "learning_rate": 9.027484812643277e-05, "loss": 0.5327332496643067, "step": 309530 }, { "epoch": 1.839970041193359, "grad_norm": 1.3693511486053467, "learning_rate": 9.026877474677491e-05, "loss": 0.5284732818603516, "step": 309540 }, { "epoch": 1.8400294832700275, "grad_norm": 1.4150556325912476, "learning_rate": 9.026270146150478e-05, "loss": 0.6230618000030518, "step": 309550 }, { "epoch": 1.8400889253466959, "grad_norm": 1.498744010925293, "learning_rate": 9.025662827065147e-05, "loss": 0.5345996379852295, "step": 309560 }, { "epoch": 1.8401483674233643, "grad_norm": 1.5334142446517944, "learning_rate": 9.025055517424395e-05, "loss": 0.5202764511108399, "step": 309570 }, { "epoch": 1.8402078095000327, "grad_norm": 1.3538734912872314, "learning_rate": 9.024448217231131e-05, "loss": 0.5954829216003418, "step": 309580 }, { "epoch": 1.8402672515767011, "grad_norm": 1.4351255893707275, "learning_rate": 9.023840926488267e-05, "loss": 0.5106199264526368, "step": 309590 }, { "epoch": 1.8403266936533695, "grad_norm": 1.1600315570831299, "learning_rate": 9.023233645198697e-05, "loss": 0.5917614936828614, "step": 309600 }, { "epoch": 1.840386135730038, "grad_norm": 1.2182972431182861, "learning_rate": 9.022626373365335e-05, "loss": 0.5292541980743408, "step": 309610 }, { "epoch": 1.8404455778067064, "grad_norm": 1.4176002740859985, "learning_rate": 9.022019110991083e-05, "loss": 0.5552789688110351, "step": 309620 }, { "epoch": 1.8405050198833748, "grad_norm": 1.4355508089065552, "learning_rate": 9.021411858078839e-05, "loss": 0.5234518051147461, "step": 309630 }, { "epoch": 1.8405644619600432, "grad_norm": 1.471057415008545, "learning_rate": 9.020804614631518e-05, "loss": 0.5804052352905273, "step": 309640 }, { "epoch": 1.8406239040367114, "grad_norm": 1.6268678903579712, "learning_rate": 9.020197380652024e-05, "loss": 0.5478286743164062, "step": 309650 }, { "epoch": 1.8406833461133798, "grad_norm": 1.2790336608886719, "learning_rate": 9.019590156143251e-05, "loss": 0.47300004959106445, "step": 309660 }, { "epoch": 1.8407427881900482, "grad_norm": 1.5987350940704346, "learning_rate": 9.018982941108118e-05, "loss": 0.567662525177002, "step": 309670 }, { "epoch": 1.8408022302667166, "grad_norm": 1.8476026058197021, "learning_rate": 9.018375735549523e-05, "loss": 0.5129969596862793, "step": 309680 }, { "epoch": 1.8408616723433848, "grad_norm": 1.229180097579956, "learning_rate": 9.017768539470368e-05, "loss": 0.610440731048584, "step": 309690 }, { "epoch": 1.8409211144200532, "grad_norm": 0.9586611986160278, "learning_rate": 9.01716135287356e-05, "loss": 0.5484807014465332, "step": 309700 }, { "epoch": 1.8409805564967217, "grad_norm": 1.2565988302230835, "learning_rate": 9.016554175762009e-05, "loss": 0.5710062980651855, "step": 309710 }, { "epoch": 1.84103999857339, "grad_norm": 1.3700191974639893, "learning_rate": 9.01594700813861e-05, "loss": 0.5297520637512207, "step": 309720 }, { "epoch": 1.8410994406500585, "grad_norm": 1.569945216178894, "learning_rate": 9.01533985000627e-05, "loss": 0.5139117240905762, "step": 309730 }, { "epoch": 1.841158882726727, "grad_norm": 1.6495097875595093, "learning_rate": 9.014732701367902e-05, "loss": 0.5468546867370605, "step": 309740 }, { "epoch": 1.8412183248033953, "grad_norm": 1.411313533782959, "learning_rate": 9.014125562226401e-05, "loss": 0.5228757858276367, "step": 309750 }, { "epoch": 1.8412777668800637, "grad_norm": 1.4942514896392822, "learning_rate": 9.013518432584672e-05, "loss": 0.5701858520507812, "step": 309760 }, { "epoch": 1.8413372089567321, "grad_norm": 1.5771671533584595, "learning_rate": 9.012911312445627e-05, "loss": 0.5963926792144776, "step": 309770 }, { "epoch": 1.8413966510334006, "grad_norm": 1.427171230316162, "learning_rate": 9.012304201812161e-05, "loss": 0.5784226894378662, "step": 309780 }, { "epoch": 1.841456093110069, "grad_norm": 1.4849172830581665, "learning_rate": 9.01169710068718e-05, "loss": 0.5696710109710693, "step": 309790 }, { "epoch": 1.8415155351867374, "grad_norm": 1.4284852743148804, "learning_rate": 9.011090009073596e-05, "loss": 0.555333137512207, "step": 309800 }, { "epoch": 1.8415749772634058, "grad_norm": 1.4627362489700317, "learning_rate": 9.010482926974305e-05, "loss": 0.6010890007019043, "step": 309810 }, { "epoch": 1.8416344193400742, "grad_norm": 1.3845977783203125, "learning_rate": 9.009875854392214e-05, "loss": 0.5583301544189453, "step": 309820 }, { "epoch": 1.8416938614167424, "grad_norm": 1.3226248025894165, "learning_rate": 9.009268791330223e-05, "loss": 0.5421332359313965, "step": 309830 }, { "epoch": 1.8417533034934108, "grad_norm": 1.270717740058899, "learning_rate": 9.008661737791244e-05, "loss": 0.562721061706543, "step": 309840 }, { "epoch": 1.8418127455700792, "grad_norm": 1.2054662704467773, "learning_rate": 9.008054693778174e-05, "loss": 0.5559781551361084, "step": 309850 }, { "epoch": 1.8418721876467476, "grad_norm": 1.810530424118042, "learning_rate": 9.007447659293919e-05, "loss": 0.5481932163238525, "step": 309860 }, { "epoch": 1.841931629723416, "grad_norm": 1.1964865922927856, "learning_rate": 9.006840634341385e-05, "loss": 0.554817008972168, "step": 309870 }, { "epoch": 1.8419910718000843, "grad_norm": 1.496801733970642, "learning_rate": 9.006233618923474e-05, "loss": 0.5729206085205079, "step": 309880 }, { "epoch": 1.8420505138767527, "grad_norm": 1.5859477519989014, "learning_rate": 9.005626613043088e-05, "loss": 0.5884025573730469, "step": 309890 }, { "epoch": 1.842109955953421, "grad_norm": 0.9846258163452148, "learning_rate": 9.005019616703134e-05, "loss": 0.49418487548828127, "step": 309900 }, { "epoch": 1.8421693980300895, "grad_norm": 1.2393739223480225, "learning_rate": 9.004412629906514e-05, "loss": 0.5833717823028565, "step": 309910 }, { "epoch": 1.842228840106758, "grad_norm": 1.3849116563796997, "learning_rate": 9.00380565265613e-05, "loss": 0.5396992683410644, "step": 309920 }, { "epoch": 1.8422882821834263, "grad_norm": 1.236388087272644, "learning_rate": 9.00319868495489e-05, "loss": 0.508674144744873, "step": 309930 }, { "epoch": 1.8423477242600947, "grad_norm": 1.5628767013549805, "learning_rate": 9.002591726805694e-05, "loss": 0.5657161712646485, "step": 309940 }, { "epoch": 1.8424071663367632, "grad_norm": 1.326419711112976, "learning_rate": 9.001984778211446e-05, "loss": 0.5678923606872559, "step": 309950 }, { "epoch": 1.8424666084134316, "grad_norm": 1.6211118698120117, "learning_rate": 9.001377839175049e-05, "loss": 0.5011570930480957, "step": 309960 }, { "epoch": 1.8425260504901, "grad_norm": 1.1493628025054932, "learning_rate": 9.00077090969941e-05, "loss": 0.5333281040191651, "step": 309970 }, { "epoch": 1.8425854925667684, "grad_norm": 1.1455810070037842, "learning_rate": 9.000163989787427e-05, "loss": 0.5666687965393067, "step": 309980 }, { "epoch": 1.8426449346434368, "grad_norm": 1.324716329574585, "learning_rate": 8.999557079442007e-05, "loss": 0.5450302124023437, "step": 309990 }, { "epoch": 1.8427043767201052, "grad_norm": 1.250004768371582, "learning_rate": 8.998950178666053e-05, "loss": 0.5539510250091553, "step": 310000 }, { "epoch": 1.8427638187967736, "grad_norm": 1.1938444375991821, "learning_rate": 8.998343287462465e-05, "loss": 0.5494184494018555, "step": 310010 }, { "epoch": 1.8428232608734418, "grad_norm": 1.252049446105957, "learning_rate": 8.997736405834149e-05, "loss": 0.5247591018676758, "step": 310020 }, { "epoch": 1.8428827029501103, "grad_norm": 1.7442892789840698, "learning_rate": 8.99712953378401e-05, "loss": 0.5691389083862305, "step": 310030 }, { "epoch": 1.8429421450267787, "grad_norm": 1.4158587455749512, "learning_rate": 8.996522671314948e-05, "loss": 0.5778560638427734, "step": 310040 }, { "epoch": 1.843001587103447, "grad_norm": 1.2527356147766113, "learning_rate": 8.995915818429869e-05, "loss": 0.4998169898986816, "step": 310050 }, { "epoch": 1.8430610291801153, "grad_norm": 1.4535956382751465, "learning_rate": 8.995308975131669e-05, "loss": 0.5355566024780274, "step": 310060 }, { "epoch": 1.8431204712567837, "grad_norm": 1.5547879934310913, "learning_rate": 8.994702141423257e-05, "loss": 0.4925710678100586, "step": 310070 }, { "epoch": 1.843179913333452, "grad_norm": 1.2819149494171143, "learning_rate": 8.994095317307538e-05, "loss": 0.5179463386535644, "step": 310080 }, { "epoch": 1.8432393554101205, "grad_norm": 1.4438400268554688, "learning_rate": 8.993488502787406e-05, "loss": 0.5183472156524658, "step": 310090 }, { "epoch": 1.843298797486789, "grad_norm": 1.4525327682495117, "learning_rate": 8.992881697865771e-05, "loss": 0.54873046875, "step": 310100 }, { "epoch": 1.8433582395634573, "grad_norm": 1.5466071367263794, "learning_rate": 8.992274902545539e-05, "loss": 0.5785037994384765, "step": 310110 }, { "epoch": 1.8434176816401258, "grad_norm": 1.1112686395645142, "learning_rate": 8.991668116829601e-05, "loss": 0.5437531471252441, "step": 310120 }, { "epoch": 1.8434771237167942, "grad_norm": 1.4987236261367798, "learning_rate": 8.99106134072087e-05, "loss": 0.5678038597106934, "step": 310130 }, { "epoch": 1.8435365657934626, "grad_norm": 1.5250436067581177, "learning_rate": 8.990454574222246e-05, "loss": 0.554314136505127, "step": 310140 }, { "epoch": 1.843596007870131, "grad_norm": 1.2439254522323608, "learning_rate": 8.989847817336626e-05, "loss": 0.49511351585388186, "step": 310150 }, { "epoch": 1.8436554499467994, "grad_norm": 1.5694841146469116, "learning_rate": 8.98924107006692e-05, "loss": 0.5212113380432128, "step": 310160 }, { "epoch": 1.8437148920234678, "grad_norm": 1.8089210987091064, "learning_rate": 8.98863433241603e-05, "loss": 0.6152462005615235, "step": 310170 }, { "epoch": 1.8437743341001362, "grad_norm": 1.159259557723999, "learning_rate": 8.988027604386855e-05, "loss": 0.5278339385986328, "step": 310180 }, { "epoch": 1.8438337761768047, "grad_norm": 1.5636537075042725, "learning_rate": 8.987420885982294e-05, "loss": 0.5340458869934082, "step": 310190 }, { "epoch": 1.8438932182534729, "grad_norm": 1.5324060916900635, "learning_rate": 8.986814177205258e-05, "loss": 0.5240878105163574, "step": 310200 }, { "epoch": 1.8439526603301413, "grad_norm": 1.8569844961166382, "learning_rate": 8.986207478058646e-05, "loss": 0.5922506809234619, "step": 310210 }, { "epoch": 1.8440121024068097, "grad_norm": 1.3980196714401245, "learning_rate": 8.985600788545354e-05, "loss": 0.5655091285705567, "step": 310220 }, { "epoch": 1.844071544483478, "grad_norm": 1.7940789461135864, "learning_rate": 8.984994108668295e-05, "loss": 0.5635861396789551, "step": 310230 }, { "epoch": 1.8441309865601465, "grad_norm": 1.0796347856521606, "learning_rate": 8.984387438430364e-05, "loss": 0.5388443946838379, "step": 310240 }, { "epoch": 1.8441904286368147, "grad_norm": 1.5087157487869263, "learning_rate": 8.983780777834461e-05, "loss": 0.6093463897705078, "step": 310250 }, { "epoch": 1.8442498707134831, "grad_norm": 1.4465285539627075, "learning_rate": 8.983174126883498e-05, "loss": 0.5964672088623046, "step": 310260 }, { "epoch": 1.8443093127901515, "grad_norm": 1.1889381408691406, "learning_rate": 8.982567485580369e-05, "loss": 0.5641892433166504, "step": 310270 }, { "epoch": 1.84436875486682, "grad_norm": 1.2909343242645264, "learning_rate": 8.98196085392797e-05, "loss": 0.5743585586547851, "step": 310280 }, { "epoch": 1.8444281969434884, "grad_norm": 1.1874624490737915, "learning_rate": 8.981354231929222e-05, "loss": 0.5538531303405761, "step": 310290 }, { "epoch": 1.8444876390201568, "grad_norm": 1.2014788389205933, "learning_rate": 8.98074761958701e-05, "loss": 0.5427578926086426, "step": 310300 }, { "epoch": 1.8445470810968252, "grad_norm": 1.6004741191864014, "learning_rate": 8.980141016904244e-05, "loss": 0.5594034194946289, "step": 310310 }, { "epoch": 1.8446065231734936, "grad_norm": 1.7108443975448608, "learning_rate": 8.979534423883822e-05, "loss": 0.5593808174133301, "step": 310320 }, { "epoch": 1.844665965250162, "grad_norm": 1.3267529010772705, "learning_rate": 8.978927840528649e-05, "loss": 0.5247539520263672, "step": 310330 }, { "epoch": 1.8447254073268304, "grad_norm": 1.7858328819274902, "learning_rate": 8.978321266841623e-05, "loss": 0.5791215896606445, "step": 310340 }, { "epoch": 1.8447848494034988, "grad_norm": 1.8447710275650024, "learning_rate": 8.977714702825644e-05, "loss": 0.4978206634521484, "step": 310350 }, { "epoch": 1.8448442914801673, "grad_norm": 1.3969978094100952, "learning_rate": 8.977108148483622e-05, "loss": 0.612706184387207, "step": 310360 }, { "epoch": 1.8449037335568357, "grad_norm": 2.0040197372436523, "learning_rate": 8.976501603818453e-05, "loss": 0.5187870025634765, "step": 310370 }, { "epoch": 1.844963175633504, "grad_norm": 1.6375017166137695, "learning_rate": 8.975895068833036e-05, "loss": 0.5807280540466309, "step": 310380 }, { "epoch": 1.8450226177101723, "grad_norm": 1.2641066312789917, "learning_rate": 8.975288543530276e-05, "loss": 0.5651639461517334, "step": 310390 }, { "epoch": 1.8450820597868407, "grad_norm": 1.610639214515686, "learning_rate": 8.974682027913077e-05, "loss": 0.5311720848083497, "step": 310400 }, { "epoch": 1.8451415018635091, "grad_norm": 1.2352226972579956, "learning_rate": 8.974075521984333e-05, "loss": 0.5349977016448975, "step": 310410 }, { "epoch": 1.8452009439401775, "grad_norm": 1.2276875972747803, "learning_rate": 8.973469025746953e-05, "loss": 0.5832760810852051, "step": 310420 }, { "epoch": 1.8452603860168457, "grad_norm": 1.359618902206421, "learning_rate": 8.972862539203835e-05, "loss": 0.5743997097015381, "step": 310430 }, { "epoch": 1.8453198280935141, "grad_norm": 1.2432746887207031, "learning_rate": 8.972256062357878e-05, "loss": 0.5715325832366943, "step": 310440 }, { "epoch": 1.8453792701701826, "grad_norm": 1.3889414072036743, "learning_rate": 8.971649595211983e-05, "loss": 0.519597053527832, "step": 310450 }, { "epoch": 1.845438712246851, "grad_norm": 1.4370856285095215, "learning_rate": 8.97104313776906e-05, "loss": 0.5231548309326172, "step": 310460 }, { "epoch": 1.8454981543235194, "grad_norm": 1.0557829141616821, "learning_rate": 8.970436690032e-05, "loss": 0.5046632766723633, "step": 310470 }, { "epoch": 1.8455575964001878, "grad_norm": 1.2352105379104614, "learning_rate": 8.969830252003706e-05, "loss": 0.5657013893127442, "step": 310480 }, { "epoch": 1.8456170384768562, "grad_norm": 1.6654114723205566, "learning_rate": 8.969223823687084e-05, "loss": 0.5166789054870605, "step": 310490 }, { "epoch": 1.8456764805535246, "grad_norm": 1.229722261428833, "learning_rate": 8.968617405085032e-05, "loss": 0.564694881439209, "step": 310500 }, { "epoch": 1.845735922630193, "grad_norm": 1.8019939661026, "learning_rate": 8.968010996200446e-05, "loss": 0.5161144733428955, "step": 310510 }, { "epoch": 1.8457953647068615, "grad_norm": 1.0594371557235718, "learning_rate": 8.967404597036235e-05, "loss": 0.5673036575317383, "step": 310520 }, { "epoch": 1.8458548067835299, "grad_norm": 1.362303376197815, "learning_rate": 8.966798207595296e-05, "loss": 0.5737567901611328, "step": 310530 }, { "epoch": 1.8459142488601983, "grad_norm": 1.6484401226043701, "learning_rate": 8.96619182788053e-05, "loss": 0.5571056842803955, "step": 310540 }, { "epoch": 1.8459736909368667, "grad_norm": 1.6155273914337158, "learning_rate": 8.965585457894834e-05, "loss": 0.530904483795166, "step": 310550 }, { "epoch": 1.846033133013535, "grad_norm": 1.0348095893859863, "learning_rate": 8.964979097641115e-05, "loss": 0.54525785446167, "step": 310560 }, { "epoch": 1.8460925750902033, "grad_norm": 1.4512757062911987, "learning_rate": 8.964372747122272e-05, "loss": 0.5476794719696045, "step": 310570 }, { "epoch": 1.8461520171668717, "grad_norm": 2.05076003074646, "learning_rate": 8.9637664063412e-05, "loss": 0.5286710262298584, "step": 310580 }, { "epoch": 1.8462114592435401, "grad_norm": 1.2888944149017334, "learning_rate": 8.96316007530081e-05, "loss": 0.539913558959961, "step": 310590 }, { "epoch": 1.8462709013202085, "grad_norm": 1.084317922592163, "learning_rate": 8.962553754003996e-05, "loss": 0.5368828773498535, "step": 310600 }, { "epoch": 1.846330343396877, "grad_norm": 1.6667746305465698, "learning_rate": 8.961947442453656e-05, "loss": 0.5503205299377442, "step": 310610 }, { "epoch": 1.8463897854735452, "grad_norm": 1.2080744504928589, "learning_rate": 8.961341140652693e-05, "loss": 0.5205600738525391, "step": 310620 }, { "epoch": 1.8464492275502136, "grad_norm": 1.2496957778930664, "learning_rate": 8.960734848604011e-05, "loss": 0.5290360927581788, "step": 310630 }, { "epoch": 1.846508669626882, "grad_norm": 1.2316313982009888, "learning_rate": 8.960128566310504e-05, "loss": 0.5272538185119628, "step": 310640 }, { "epoch": 1.8465681117035504, "grad_norm": 1.3102824687957764, "learning_rate": 8.959522293775075e-05, "loss": 0.5402588844299316, "step": 310650 }, { "epoch": 1.8466275537802188, "grad_norm": 1.866064429283142, "learning_rate": 8.958916031000628e-05, "loss": 0.5806246280670166, "step": 310660 }, { "epoch": 1.8466869958568872, "grad_norm": 1.2723053693771362, "learning_rate": 8.958309777990059e-05, "loss": 0.5069502830505371, "step": 310670 }, { "epoch": 1.8467464379335556, "grad_norm": 1.3430588245391846, "learning_rate": 8.957703534746264e-05, "loss": 0.5427919387817383, "step": 310680 }, { "epoch": 1.846805880010224, "grad_norm": 1.3460195064544678, "learning_rate": 8.957097301272155e-05, "loss": 0.5178943634033203, "step": 310690 }, { "epoch": 1.8468653220868925, "grad_norm": 1.3884754180908203, "learning_rate": 8.956491077570621e-05, "loss": 0.5527289867401123, "step": 310700 }, { "epoch": 1.8469247641635609, "grad_norm": 1.443304181098938, "learning_rate": 8.955884863644563e-05, "loss": 0.5519525527954101, "step": 310710 }, { "epoch": 1.8469842062402293, "grad_norm": 1.0973632335662842, "learning_rate": 8.95527865949689e-05, "loss": 0.5145042419433594, "step": 310720 }, { "epoch": 1.8470436483168977, "grad_norm": 1.4320530891418457, "learning_rate": 8.954672465130493e-05, "loss": 0.558382511138916, "step": 310730 }, { "epoch": 1.8471030903935661, "grad_norm": 1.4543064832687378, "learning_rate": 8.95406628054827e-05, "loss": 0.5669381141662597, "step": 310740 }, { "epoch": 1.8471625324702345, "grad_norm": 1.2551788091659546, "learning_rate": 8.953460105753133e-05, "loss": 0.529224443435669, "step": 310750 }, { "epoch": 1.8472219745469027, "grad_norm": 1.6426657438278198, "learning_rate": 8.952853940747972e-05, "loss": 0.5509626388549804, "step": 310760 }, { "epoch": 1.8472814166235711, "grad_norm": 1.178465485572815, "learning_rate": 8.952247785535683e-05, "loss": 0.5102695941925048, "step": 310770 }, { "epoch": 1.8473408587002396, "grad_norm": 1.4389753341674805, "learning_rate": 8.951641640119177e-05, "loss": 0.5136004447937011, "step": 310780 }, { "epoch": 1.847400300776908, "grad_norm": 1.3051549196243286, "learning_rate": 8.951035504501348e-05, "loss": 0.5469460487365723, "step": 310790 }, { "epoch": 1.8474597428535762, "grad_norm": 1.604062557220459, "learning_rate": 8.950429378685094e-05, "loss": 0.533501672744751, "step": 310800 }, { "epoch": 1.8475191849302446, "grad_norm": 1.4935331344604492, "learning_rate": 8.949823262673316e-05, "loss": 0.48816442489624023, "step": 310810 }, { "epoch": 1.847578627006913, "grad_norm": 1.3301115036010742, "learning_rate": 8.949217156468915e-05, "loss": 0.5095079421997071, "step": 310820 }, { "epoch": 1.8476380690835814, "grad_norm": 1.3790290355682373, "learning_rate": 8.948611060074787e-05, "loss": 0.5713459968566894, "step": 310830 }, { "epoch": 1.8476975111602498, "grad_norm": 1.2784751653671265, "learning_rate": 8.948004973493831e-05, "loss": 0.575084924697876, "step": 310840 }, { "epoch": 1.8477569532369182, "grad_norm": 1.3562967777252197, "learning_rate": 8.947398896728953e-05, "loss": 0.5484226703643799, "step": 310850 }, { "epoch": 1.8478163953135867, "grad_norm": 1.419358730316162, "learning_rate": 8.946792829783047e-05, "loss": 0.5614571094512939, "step": 310860 }, { "epoch": 1.847875837390255, "grad_norm": 1.1583629846572876, "learning_rate": 8.946186772659011e-05, "loss": 0.5790131092071533, "step": 310870 }, { "epoch": 1.8479352794669235, "grad_norm": 1.7791430950164795, "learning_rate": 8.945580725359748e-05, "loss": 0.584907054901123, "step": 310880 }, { "epoch": 1.847994721543592, "grad_norm": 1.4336702823638916, "learning_rate": 8.944974687888154e-05, "loss": 0.5776915550231934, "step": 310890 }, { "epoch": 1.8480541636202603, "grad_norm": 1.5106217861175537, "learning_rate": 8.944368660247133e-05, "loss": 0.5792321681976318, "step": 310900 }, { "epoch": 1.8481136056969287, "grad_norm": 1.6823920011520386, "learning_rate": 8.943762642439577e-05, "loss": 0.5532033443450928, "step": 310910 }, { "epoch": 1.8481730477735971, "grad_norm": 1.5254385471343994, "learning_rate": 8.943156634468391e-05, "loss": 0.5465120315551758, "step": 310920 }, { "epoch": 1.8482324898502656, "grad_norm": 1.1232951879501343, "learning_rate": 8.942550636336468e-05, "loss": 0.5443913459777832, "step": 310930 }, { "epoch": 1.8482919319269338, "grad_norm": 1.0929189920425415, "learning_rate": 8.941944648046712e-05, "loss": 0.5491250038146973, "step": 310940 }, { "epoch": 1.8483513740036022, "grad_norm": 1.8108673095703125, "learning_rate": 8.941338669602022e-05, "loss": 0.5659966468811035, "step": 310950 }, { "epoch": 1.8484108160802706, "grad_norm": 1.1158757209777832, "learning_rate": 8.940732701005294e-05, "loss": 0.5653026580810547, "step": 310960 }, { "epoch": 1.848470258156939, "grad_norm": 2.0692760944366455, "learning_rate": 8.940126742259428e-05, "loss": 0.613518238067627, "step": 310970 }, { "epoch": 1.8485297002336074, "grad_norm": 1.2677048444747925, "learning_rate": 8.939520793367322e-05, "loss": 0.5233065128326416, "step": 310980 }, { "epoch": 1.8485891423102756, "grad_norm": 1.2540431022644043, "learning_rate": 8.938914854331874e-05, "loss": 0.5217589378356934, "step": 310990 }, { "epoch": 1.848648584386944, "grad_norm": 1.1282198429107666, "learning_rate": 8.938308925155983e-05, "loss": 0.5282614231109619, "step": 311000 }, { "epoch": 1.8487080264636124, "grad_norm": 1.345863699913025, "learning_rate": 8.937703005842552e-05, "loss": 0.5216914653778076, "step": 311010 }, { "epoch": 1.8487674685402808, "grad_norm": 1.5853080749511719, "learning_rate": 8.937097096394474e-05, "loss": 0.5368705272674561, "step": 311020 }, { "epoch": 1.8488269106169493, "grad_norm": 1.6148796081542969, "learning_rate": 8.936491196814651e-05, "loss": 0.5703270435333252, "step": 311030 }, { "epoch": 1.8488863526936177, "grad_norm": 1.2425000667572021, "learning_rate": 8.935885307105975e-05, "loss": 0.5584383964538574, "step": 311040 }, { "epoch": 1.848945794770286, "grad_norm": 1.3268661499023438, "learning_rate": 8.935279427271355e-05, "loss": 0.5771276950836182, "step": 311050 }, { "epoch": 1.8490052368469545, "grad_norm": 1.208325982093811, "learning_rate": 8.934673557313682e-05, "loss": 0.5305294036865235, "step": 311060 }, { "epoch": 1.849064678923623, "grad_norm": 1.548039197921753, "learning_rate": 8.934067697235852e-05, "loss": 0.5328532218933105, "step": 311070 }, { "epoch": 1.8491241210002913, "grad_norm": 0.9561798572540283, "learning_rate": 8.93346184704077e-05, "loss": 0.5436978340148926, "step": 311080 }, { "epoch": 1.8491835630769597, "grad_norm": 1.4397084712982178, "learning_rate": 8.932856006731331e-05, "loss": 0.5833487987518311, "step": 311090 }, { "epoch": 1.8492430051536282, "grad_norm": 1.7334004640579224, "learning_rate": 8.932250176310433e-05, "loss": 0.5333571434020996, "step": 311100 }, { "epoch": 1.8493024472302966, "grad_norm": 1.4456257820129395, "learning_rate": 8.931644355780973e-05, "loss": 0.5551023483276367, "step": 311110 }, { "epoch": 1.849361889306965, "grad_norm": 1.1527961492538452, "learning_rate": 8.931038545145854e-05, "loss": 0.5313376426696778, "step": 311120 }, { "epoch": 1.8494213313836332, "grad_norm": 1.1508466005325317, "learning_rate": 8.930432744407966e-05, "loss": 0.5278868675231934, "step": 311130 }, { "epoch": 1.8494807734603016, "grad_norm": 1.4708194732666016, "learning_rate": 8.929826953570215e-05, "loss": 0.5553960800170898, "step": 311140 }, { "epoch": 1.84954021553697, "grad_norm": 1.2949515581130981, "learning_rate": 8.929221172635494e-05, "loss": 0.5740612506866455, "step": 311150 }, { "epoch": 1.8495996576136384, "grad_norm": 1.136574387550354, "learning_rate": 8.928615401606706e-05, "loss": 0.5472754001617431, "step": 311160 }, { "epoch": 1.8496590996903066, "grad_norm": 1.2273515462875366, "learning_rate": 8.928009640486736e-05, "loss": 0.553416395187378, "step": 311170 }, { "epoch": 1.849718541766975, "grad_norm": 1.2560579776763916, "learning_rate": 8.927403889278499e-05, "loss": 0.4938084602355957, "step": 311180 }, { "epoch": 1.8497779838436434, "grad_norm": 1.4904649257659912, "learning_rate": 8.926798147984882e-05, "loss": 0.49533767700195314, "step": 311190 }, { "epoch": 1.8498374259203119, "grad_norm": 1.3792724609375, "learning_rate": 8.926192416608783e-05, "loss": 0.5363018989562989, "step": 311200 }, { "epoch": 1.8498968679969803, "grad_norm": 1.7349799871444702, "learning_rate": 8.925586695153103e-05, "loss": 0.5554260730743408, "step": 311210 }, { "epoch": 1.8499563100736487, "grad_norm": 1.41167151927948, "learning_rate": 8.924980983620741e-05, "loss": 0.5734138011932373, "step": 311220 }, { "epoch": 1.850015752150317, "grad_norm": 1.3542392253875732, "learning_rate": 8.924375282014585e-05, "loss": 0.5506514072418213, "step": 311230 }, { "epoch": 1.8500751942269855, "grad_norm": 1.2695283889770508, "learning_rate": 8.923769590337545e-05, "loss": 0.545830488204956, "step": 311240 }, { "epoch": 1.850134636303654, "grad_norm": 1.5200434923171997, "learning_rate": 8.923163908592516e-05, "loss": 0.5800467967987061, "step": 311250 }, { "epoch": 1.8501940783803223, "grad_norm": 1.1641044616699219, "learning_rate": 8.922558236782383e-05, "loss": 0.5892534732818604, "step": 311260 }, { "epoch": 1.8502535204569908, "grad_norm": 1.5779746770858765, "learning_rate": 8.921952574910057e-05, "loss": 0.6128314018249512, "step": 311270 }, { "epoch": 1.8503129625336592, "grad_norm": 2.028604507446289, "learning_rate": 8.921346922978436e-05, "loss": 0.5622751235961914, "step": 311280 }, { "epoch": 1.8503724046103276, "grad_norm": 1.2871812582015991, "learning_rate": 8.920741280990406e-05, "loss": 0.5874924659729004, "step": 311290 }, { "epoch": 1.850431846686996, "grad_norm": 1.5279232263565063, "learning_rate": 8.92013564894887e-05, "loss": 0.5580822944641113, "step": 311300 }, { "epoch": 1.8504912887636642, "grad_norm": 1.3517484664916992, "learning_rate": 8.919530026856726e-05, "loss": 0.5619040489196777, "step": 311310 }, { "epoch": 1.8505507308403326, "grad_norm": 1.6066936254501343, "learning_rate": 8.918924414716871e-05, "loss": 0.5106791496276856, "step": 311320 }, { "epoch": 1.850610172917001, "grad_norm": 1.6526597738265991, "learning_rate": 8.9183188125322e-05, "loss": 0.6242448806762695, "step": 311330 }, { "epoch": 1.8506696149936694, "grad_norm": 1.3177576065063477, "learning_rate": 8.917713220305615e-05, "loss": 0.5577484130859375, "step": 311340 }, { "epoch": 1.8507290570703379, "grad_norm": 1.4264079332351685, "learning_rate": 8.917107638040008e-05, "loss": 0.5808591842651367, "step": 311350 }, { "epoch": 1.850788499147006, "grad_norm": 1.3896961212158203, "learning_rate": 8.916502065738275e-05, "loss": 0.5847468376159668, "step": 311360 }, { "epoch": 1.8508479412236745, "grad_norm": 1.4875259399414062, "learning_rate": 8.915896503403318e-05, "loss": 0.48136210441589355, "step": 311370 }, { "epoch": 1.8509073833003429, "grad_norm": 1.3437213897705078, "learning_rate": 8.915290951038032e-05, "loss": 0.5319591522216797, "step": 311380 }, { "epoch": 1.8509668253770113, "grad_norm": 0.8822553753852844, "learning_rate": 8.91468540864531e-05, "loss": 0.5171324253082276, "step": 311390 }, { "epoch": 1.8510262674536797, "grad_norm": 1.257463812828064, "learning_rate": 8.91407987622805e-05, "loss": 0.5204815864562988, "step": 311400 }, { "epoch": 1.8510857095303481, "grad_norm": 1.3560471534729004, "learning_rate": 8.913474353789153e-05, "loss": 0.570896053314209, "step": 311410 }, { "epoch": 1.8511451516070165, "grad_norm": 1.4811103343963623, "learning_rate": 8.912868841331514e-05, "loss": 0.5649507522583008, "step": 311420 }, { "epoch": 1.851204593683685, "grad_norm": 1.4492822885513306, "learning_rate": 8.912263338858025e-05, "loss": 0.5491347312927246, "step": 311430 }, { "epoch": 1.8512640357603534, "grad_norm": 1.2748873233795166, "learning_rate": 8.911657846371588e-05, "loss": 0.5896946907043457, "step": 311440 }, { "epoch": 1.8513234778370218, "grad_norm": 1.646687388420105, "learning_rate": 8.911052363875099e-05, "loss": 0.5730628967285156, "step": 311450 }, { "epoch": 1.8513829199136902, "grad_norm": 1.3380626440048218, "learning_rate": 8.910446891371449e-05, "loss": 0.5235704898834228, "step": 311460 }, { "epoch": 1.8514423619903586, "grad_norm": 1.6003464460372925, "learning_rate": 8.909841428863541e-05, "loss": 0.5796406745910645, "step": 311470 }, { "epoch": 1.851501804067027, "grad_norm": 1.348222255706787, "learning_rate": 8.909235976354267e-05, "loss": 0.5767488479614258, "step": 311480 }, { "epoch": 1.8515612461436954, "grad_norm": 1.6383459568023682, "learning_rate": 8.908630533846525e-05, "loss": 0.5779393196105957, "step": 311490 }, { "epoch": 1.8516206882203636, "grad_norm": 1.7443749904632568, "learning_rate": 8.908025101343212e-05, "loss": 0.5183220863342285, "step": 311500 }, { "epoch": 1.851680130297032, "grad_norm": 1.3512580394744873, "learning_rate": 8.907419678847222e-05, "loss": 0.5663363456726074, "step": 311510 }, { "epoch": 1.8517395723737005, "grad_norm": 1.5566142797470093, "learning_rate": 8.906814266361455e-05, "loss": 0.5177535057067871, "step": 311520 }, { "epoch": 1.8517990144503689, "grad_norm": 1.506357192993164, "learning_rate": 8.906208863888801e-05, "loss": 0.5367813110351562, "step": 311530 }, { "epoch": 1.851858456527037, "grad_norm": 1.6033958196640015, "learning_rate": 8.905603471432162e-05, "loss": 0.5164776802062988, "step": 311540 }, { "epoch": 1.8519178986037055, "grad_norm": 1.5649003982543945, "learning_rate": 8.904998088994432e-05, "loss": 0.5694615364074707, "step": 311550 }, { "epoch": 1.851977340680374, "grad_norm": 1.5055787563323975, "learning_rate": 8.904392716578502e-05, "loss": 0.5432591438293457, "step": 311560 }, { "epoch": 1.8520367827570423, "grad_norm": 1.3485419750213623, "learning_rate": 8.903787354187276e-05, "loss": 0.5730547904968262, "step": 311570 }, { "epoch": 1.8520962248337107, "grad_norm": 1.4250892400741577, "learning_rate": 8.903182001823647e-05, "loss": 0.5337633609771728, "step": 311580 }, { "epoch": 1.8521556669103791, "grad_norm": 1.7077192068099976, "learning_rate": 8.902576659490506e-05, "loss": 0.6000834465026855, "step": 311590 }, { "epoch": 1.8522151089870476, "grad_norm": 1.1189875602722168, "learning_rate": 8.901971327190757e-05, "loss": 0.5054702758789062, "step": 311600 }, { "epoch": 1.852274551063716, "grad_norm": 1.3389595746994019, "learning_rate": 8.901366004927291e-05, "loss": 0.5537665367126465, "step": 311610 }, { "epoch": 1.8523339931403844, "grad_norm": 1.236205816268921, "learning_rate": 8.900760692703003e-05, "loss": 0.5129132270812988, "step": 311620 }, { "epoch": 1.8523934352170528, "grad_norm": 1.6743518114089966, "learning_rate": 8.90015539052079e-05, "loss": 0.5086405277252197, "step": 311630 }, { "epoch": 1.8524528772937212, "grad_norm": 1.6851333379745483, "learning_rate": 8.89955009838355e-05, "loss": 0.5551775455474853, "step": 311640 }, { "epoch": 1.8525123193703896, "grad_norm": 1.545931100845337, "learning_rate": 8.898944816294175e-05, "loss": 0.5065725326538086, "step": 311650 }, { "epoch": 1.852571761447058, "grad_norm": 1.3803690671920776, "learning_rate": 8.898339544255556e-05, "loss": 0.5562305927276612, "step": 311660 }, { "epoch": 1.8526312035237265, "grad_norm": 1.3702908754348755, "learning_rate": 8.897734282270597e-05, "loss": 0.5200588226318359, "step": 311670 }, { "epoch": 1.8526906456003946, "grad_norm": 1.1913741827011108, "learning_rate": 8.897129030342195e-05, "loss": 0.5342817306518555, "step": 311680 }, { "epoch": 1.852750087677063, "grad_norm": 1.74068284034729, "learning_rate": 8.896523788473232e-05, "loss": 0.5986566543579102, "step": 311690 }, { "epoch": 1.8528095297537315, "grad_norm": 1.1320698261260986, "learning_rate": 8.895918556666616e-05, "loss": 0.4587701797485352, "step": 311700 }, { "epoch": 1.8528689718304, "grad_norm": 1.4061942100524902, "learning_rate": 8.895313334925242e-05, "loss": 0.5281608581542969, "step": 311710 }, { "epoch": 1.8529284139070683, "grad_norm": 1.4377487897872925, "learning_rate": 8.894708123251994e-05, "loss": 0.5894761562347413, "step": 311720 }, { "epoch": 1.8529878559837365, "grad_norm": 1.4404915571212769, "learning_rate": 8.894102921649778e-05, "loss": 0.5337384700775146, "step": 311730 }, { "epoch": 1.853047298060405, "grad_norm": 1.360679030418396, "learning_rate": 8.893497730121488e-05, "loss": 0.5264079093933105, "step": 311740 }, { "epoch": 1.8531067401370733, "grad_norm": 1.4833520650863647, "learning_rate": 8.892892548670013e-05, "loss": 0.5447006702423096, "step": 311750 }, { "epoch": 1.8531661822137417, "grad_norm": 1.4568336009979248, "learning_rate": 8.892287377298248e-05, "loss": 0.5719069480895996, "step": 311760 }, { "epoch": 1.8532256242904102, "grad_norm": 1.1119688749313354, "learning_rate": 8.891682216009098e-05, "loss": 0.5513052940368652, "step": 311770 }, { "epoch": 1.8532850663670786, "grad_norm": 1.431381106376648, "learning_rate": 8.891077064805449e-05, "loss": 0.5727136611938477, "step": 311780 }, { "epoch": 1.853344508443747, "grad_norm": 0.9990550875663757, "learning_rate": 8.890471923690196e-05, "loss": 0.541085958480835, "step": 311790 }, { "epoch": 1.8534039505204154, "grad_norm": 1.456352710723877, "learning_rate": 8.889866792666237e-05, "loss": 0.6114563941955566, "step": 311800 }, { "epoch": 1.8534633925970838, "grad_norm": 1.3710063695907593, "learning_rate": 8.889261671736468e-05, "loss": 0.5008920192718506, "step": 311810 }, { "epoch": 1.8535228346737522, "grad_norm": 1.4847242832183838, "learning_rate": 8.888656560903776e-05, "loss": 0.5118056774139405, "step": 311820 }, { "epoch": 1.8535822767504206, "grad_norm": 1.4741337299346924, "learning_rate": 8.888051460171068e-05, "loss": 0.5375096321105957, "step": 311830 }, { "epoch": 1.853641718827089, "grad_norm": 1.3025480508804321, "learning_rate": 8.887446369541228e-05, "loss": 0.49700336456298827, "step": 311840 }, { "epoch": 1.8537011609037575, "grad_norm": 1.1983392238616943, "learning_rate": 8.886841289017152e-05, "loss": 0.6103209972381591, "step": 311850 }, { "epoch": 1.8537606029804259, "grad_norm": 1.2853569984436035, "learning_rate": 8.886236218601743e-05, "loss": 0.5464158058166504, "step": 311860 }, { "epoch": 1.853820045057094, "grad_norm": 1.4287797212600708, "learning_rate": 8.885631158297885e-05, "loss": 0.5541357040405274, "step": 311870 }, { "epoch": 1.8538794871337625, "grad_norm": 1.2908382415771484, "learning_rate": 8.885026108108476e-05, "loss": 0.579743766784668, "step": 311880 }, { "epoch": 1.853938929210431, "grad_norm": 1.599584937095642, "learning_rate": 8.884421068036411e-05, "loss": 0.5717865943908691, "step": 311890 }, { "epoch": 1.8539983712870993, "grad_norm": 1.2375849485397339, "learning_rate": 8.883816038084584e-05, "loss": 0.5554320335388183, "step": 311900 }, { "epoch": 1.8540578133637675, "grad_norm": 1.4046354293823242, "learning_rate": 8.883211018255892e-05, "loss": 0.5738555908203125, "step": 311910 }, { "epoch": 1.854117255440436, "grad_norm": 1.4436790943145752, "learning_rate": 8.882606008553225e-05, "loss": 0.5548860549926757, "step": 311920 }, { "epoch": 1.8541766975171043, "grad_norm": 1.3341119289398193, "learning_rate": 8.88200100897948e-05, "loss": 0.5426188945770264, "step": 311930 }, { "epoch": 1.8542361395937728, "grad_norm": 1.3870540857315063, "learning_rate": 8.881396019537547e-05, "loss": 0.5363964080810547, "step": 311940 }, { "epoch": 1.8542955816704412, "grad_norm": 1.2285261154174805, "learning_rate": 8.880791040230325e-05, "loss": 0.5755440711975097, "step": 311950 }, { "epoch": 1.8543550237471096, "grad_norm": 0.9983900189399719, "learning_rate": 8.880186071060705e-05, "loss": 0.5399192810058594, "step": 311960 }, { "epoch": 1.854414465823778, "grad_norm": 1.3965773582458496, "learning_rate": 8.879581112031586e-05, "loss": 0.5734489440917969, "step": 311970 }, { "epoch": 1.8544739079004464, "grad_norm": 1.713666558265686, "learning_rate": 8.878976163145854e-05, "loss": 0.6331867694854736, "step": 311980 }, { "epoch": 1.8545333499771148, "grad_norm": 1.198723316192627, "learning_rate": 8.878371224406408e-05, "loss": 0.5437825202941895, "step": 311990 }, { "epoch": 1.8545927920537832, "grad_norm": 1.3847177028656006, "learning_rate": 8.877766295816141e-05, "loss": 0.5454748153686524, "step": 312000 }, { "epoch": 1.8546522341304517, "grad_norm": 1.2354087829589844, "learning_rate": 8.877161377377948e-05, "loss": 0.5243574142456054, "step": 312010 }, { "epoch": 1.85471167620712, "grad_norm": 1.3414965867996216, "learning_rate": 8.876556469094717e-05, "loss": 0.5162135601043701, "step": 312020 }, { "epoch": 1.8547711182837885, "grad_norm": 1.6184780597686768, "learning_rate": 8.875951570969349e-05, "loss": 0.5367615699768067, "step": 312030 }, { "epoch": 1.854830560360457, "grad_norm": 1.0159651041030884, "learning_rate": 8.875346683004735e-05, "loss": 0.48560643196105957, "step": 312040 }, { "epoch": 1.854890002437125, "grad_norm": 1.7170791625976562, "learning_rate": 8.874741805203766e-05, "loss": 0.5758688926696778, "step": 312050 }, { "epoch": 1.8549494445137935, "grad_norm": 1.0374460220336914, "learning_rate": 8.87413693756934e-05, "loss": 0.5552496433258056, "step": 312060 }, { "epoch": 1.855008886590462, "grad_norm": 1.5016579627990723, "learning_rate": 8.873532080104345e-05, "loss": 0.5068694591522217, "step": 312070 }, { "epoch": 1.8550683286671303, "grad_norm": 1.741090178489685, "learning_rate": 8.872927232811681e-05, "loss": 0.5898260593414306, "step": 312080 }, { "epoch": 1.8551277707437988, "grad_norm": 1.1364761590957642, "learning_rate": 8.872322395694234e-05, "loss": 0.5427604675292969, "step": 312090 }, { "epoch": 1.855187212820467, "grad_norm": 1.228346586227417, "learning_rate": 8.871717568754905e-05, "loss": 0.591913890838623, "step": 312100 }, { "epoch": 1.8552466548971354, "grad_norm": 1.5128803253173828, "learning_rate": 8.871112751996582e-05, "loss": 0.5367694854736328, "step": 312110 }, { "epoch": 1.8553060969738038, "grad_norm": 1.861114501953125, "learning_rate": 8.870507945422162e-05, "loss": 0.5220220565795899, "step": 312120 }, { "epoch": 1.8553655390504722, "grad_norm": 1.116549015045166, "learning_rate": 8.869903149034532e-05, "loss": 0.5079615592956543, "step": 312130 }, { "epoch": 1.8554249811271406, "grad_norm": 1.1995640993118286, "learning_rate": 8.869298362836596e-05, "loss": 0.5591462135314942, "step": 312140 }, { "epoch": 1.855484423203809, "grad_norm": 1.4463764429092407, "learning_rate": 8.868693586831234e-05, "loss": 0.4946261405944824, "step": 312150 }, { "epoch": 1.8555438652804774, "grad_norm": 1.2189122438430786, "learning_rate": 8.868088821021345e-05, "loss": 0.5248043537139893, "step": 312160 }, { "epoch": 1.8556033073571458, "grad_norm": 1.2632641792297363, "learning_rate": 8.867484065409828e-05, "loss": 0.5526739120483398, "step": 312170 }, { "epoch": 1.8556627494338143, "grad_norm": 1.1944435834884644, "learning_rate": 8.866879319999563e-05, "loss": 0.5333450317382813, "step": 312180 }, { "epoch": 1.8557221915104827, "grad_norm": 1.481163740158081, "learning_rate": 8.866274584793457e-05, "loss": 0.553570556640625, "step": 312190 }, { "epoch": 1.855781633587151, "grad_norm": 1.3755515813827515, "learning_rate": 8.865669859794394e-05, "loss": 0.5224028110504151, "step": 312200 }, { "epoch": 1.8558410756638195, "grad_norm": 1.2946053743362427, "learning_rate": 8.865065145005267e-05, "loss": 0.5314041137695312, "step": 312210 }, { "epoch": 1.855900517740488, "grad_norm": 1.3287262916564941, "learning_rate": 8.86446044042897e-05, "loss": 0.5410741329193115, "step": 312220 }, { "epoch": 1.8559599598171563, "grad_norm": 1.4265254735946655, "learning_rate": 8.863855746068402e-05, "loss": 0.5120169162750244, "step": 312230 }, { "epoch": 1.8560194018938245, "grad_norm": 1.935890793800354, "learning_rate": 8.863251061926446e-05, "loss": 0.5464722156524658, "step": 312240 }, { "epoch": 1.856078843970493, "grad_norm": 1.2990802526474, "learning_rate": 8.862646388005995e-05, "loss": 0.5612895965576172, "step": 312250 }, { "epoch": 1.8561382860471614, "grad_norm": 1.6574183702468872, "learning_rate": 8.862041724309953e-05, "loss": 0.5231080532073975, "step": 312260 }, { "epoch": 1.8561977281238298, "grad_norm": 1.623025894165039, "learning_rate": 8.861437070841201e-05, "loss": 0.4905247211456299, "step": 312270 }, { "epoch": 1.856257170200498, "grad_norm": 1.2095268964767456, "learning_rate": 8.86083242760263e-05, "loss": 0.49858994483947755, "step": 312280 }, { "epoch": 1.8563166122771664, "grad_norm": 1.2692530155181885, "learning_rate": 8.860227794597144e-05, "loss": 0.5067171096801758, "step": 312290 }, { "epoch": 1.8563760543538348, "grad_norm": 1.1060595512390137, "learning_rate": 8.859623171827628e-05, "loss": 0.5139184951782226, "step": 312300 }, { "epoch": 1.8564354964305032, "grad_norm": 1.3758772611618042, "learning_rate": 8.859018559296972e-05, "loss": 0.5546142578125, "step": 312310 }, { "epoch": 1.8564949385071716, "grad_norm": 1.1526567935943604, "learning_rate": 8.858413957008078e-05, "loss": 0.5183291435241699, "step": 312320 }, { "epoch": 1.85655438058384, "grad_norm": 1.4966872930526733, "learning_rate": 8.857809364963827e-05, "loss": 0.5150509357452393, "step": 312330 }, { "epoch": 1.8566138226605085, "grad_norm": 1.088498592376709, "learning_rate": 8.857204783167115e-05, "loss": 0.543956995010376, "step": 312340 }, { "epoch": 1.8566732647371769, "grad_norm": 1.361947774887085, "learning_rate": 8.856600211620838e-05, "loss": 0.5297460556030273, "step": 312350 }, { "epoch": 1.8567327068138453, "grad_norm": 1.6452269554138184, "learning_rate": 8.855995650327886e-05, "loss": 0.5918878555297852, "step": 312360 }, { "epoch": 1.8567921488905137, "grad_norm": 1.5110315084457397, "learning_rate": 8.855391099291148e-05, "loss": 0.5870028495788574, "step": 312370 }, { "epoch": 1.856851590967182, "grad_norm": 1.6614669561386108, "learning_rate": 8.854786558513518e-05, "loss": 0.5375166893005371, "step": 312380 }, { "epoch": 1.8569110330438505, "grad_norm": 1.1508619785308838, "learning_rate": 8.854182027997889e-05, "loss": 0.5004807472229004, "step": 312390 }, { "epoch": 1.856970475120519, "grad_norm": 1.2045996189117432, "learning_rate": 8.85357750774715e-05, "loss": 0.5811398029327393, "step": 312400 }, { "epoch": 1.8570299171971874, "grad_norm": 1.3994061946868896, "learning_rate": 8.852972997764195e-05, "loss": 0.4977468490600586, "step": 312410 }, { "epoch": 1.8570893592738555, "grad_norm": 1.3133323192596436, "learning_rate": 8.852368498051917e-05, "loss": 0.5611025810241699, "step": 312420 }, { "epoch": 1.857148801350524, "grad_norm": 1.7061351537704468, "learning_rate": 8.851764008613205e-05, "loss": 0.5937756538391114, "step": 312430 }, { "epoch": 1.8572082434271924, "grad_norm": 1.2749797105789185, "learning_rate": 8.851159529450952e-05, "loss": 0.5650098323822021, "step": 312440 }, { "epoch": 1.8572676855038608, "grad_norm": 1.367530107498169, "learning_rate": 8.850555060568051e-05, "loss": 0.5576271533966064, "step": 312450 }, { "epoch": 1.8573271275805292, "grad_norm": 1.4905792474746704, "learning_rate": 8.849950601967391e-05, "loss": 0.6077768325805664, "step": 312460 }, { "epoch": 1.8573865696571974, "grad_norm": 1.587568998336792, "learning_rate": 8.849346153651865e-05, "loss": 0.5624545097351075, "step": 312470 }, { "epoch": 1.8574460117338658, "grad_norm": 1.895362138748169, "learning_rate": 8.848741715624365e-05, "loss": 0.534694766998291, "step": 312480 }, { "epoch": 1.8575054538105342, "grad_norm": 0.9162097573280334, "learning_rate": 8.848137287887781e-05, "loss": 0.5064446449279785, "step": 312490 }, { "epoch": 1.8575648958872026, "grad_norm": 1.3832156658172607, "learning_rate": 8.847532870445006e-05, "loss": 0.49889345169067384, "step": 312500 }, { "epoch": 1.857624337963871, "grad_norm": 1.5288722515106201, "learning_rate": 8.846928463298927e-05, "loss": 0.5257328987121582, "step": 312510 }, { "epoch": 1.8576837800405395, "grad_norm": 1.4128780364990234, "learning_rate": 8.846324066452441e-05, "loss": 0.5293583393096923, "step": 312520 }, { "epoch": 1.8577432221172079, "grad_norm": 1.0022146701812744, "learning_rate": 8.845719679908438e-05, "loss": 0.49436302185058595, "step": 312530 }, { "epoch": 1.8578026641938763, "grad_norm": 1.3453025817871094, "learning_rate": 8.845115303669804e-05, "loss": 0.5196140289306641, "step": 312540 }, { "epoch": 1.8578621062705447, "grad_norm": 1.519844889640808, "learning_rate": 8.844510937739436e-05, "loss": 0.5755832672119141, "step": 312550 }, { "epoch": 1.8579215483472131, "grad_norm": 1.7914940118789673, "learning_rate": 8.843906582120225e-05, "loss": 0.5965344429016113, "step": 312560 }, { "epoch": 1.8579809904238815, "grad_norm": 1.7464200258255005, "learning_rate": 8.843302236815058e-05, "loss": 0.49611616134643555, "step": 312570 }, { "epoch": 1.85804043250055, "grad_norm": 1.3937032222747803, "learning_rate": 8.84269790182683e-05, "loss": 0.5919125080108643, "step": 312580 }, { "epoch": 1.8580998745772184, "grad_norm": 1.542851209640503, "learning_rate": 8.84209357715843e-05, "loss": 0.5666160583496094, "step": 312590 }, { "epoch": 1.8581593166538868, "grad_norm": 1.4467828273773193, "learning_rate": 8.84148926281275e-05, "loss": 0.5659745216369629, "step": 312600 }, { "epoch": 1.858218758730555, "grad_norm": 1.3736233711242676, "learning_rate": 8.84088495879268e-05, "loss": 0.5463788032531738, "step": 312610 }, { "epoch": 1.8582782008072234, "grad_norm": 1.314658284187317, "learning_rate": 8.840280665101108e-05, "loss": 0.546367073059082, "step": 312620 }, { "epoch": 1.8583376428838918, "grad_norm": 1.488956332206726, "learning_rate": 8.839676381740929e-05, "loss": 0.5301673889160157, "step": 312630 }, { "epoch": 1.8583970849605602, "grad_norm": 1.515223741531372, "learning_rate": 8.839072108715032e-05, "loss": 0.5549792289733887, "step": 312640 }, { "epoch": 1.8584565270372284, "grad_norm": 1.2367358207702637, "learning_rate": 8.838467846026308e-05, "loss": 0.5591764450073242, "step": 312650 }, { "epoch": 1.8585159691138968, "grad_norm": 1.1654211282730103, "learning_rate": 8.837863593677649e-05, "loss": 0.5389381408691406, "step": 312660 }, { "epoch": 1.8585754111905652, "grad_norm": 1.2968140840530396, "learning_rate": 8.83725935167194e-05, "loss": 0.5734390258789063, "step": 312670 }, { "epoch": 1.8586348532672337, "grad_norm": 1.0202867984771729, "learning_rate": 8.836655120012078e-05, "loss": 0.5536260604858398, "step": 312680 }, { "epoch": 1.858694295343902, "grad_norm": 1.5147541761398315, "learning_rate": 8.836050898700951e-05, "loss": 0.5964774131774903, "step": 312690 }, { "epoch": 1.8587537374205705, "grad_norm": 1.263930320739746, "learning_rate": 8.835446687741448e-05, "loss": 0.5274665832519532, "step": 312700 }, { "epoch": 1.858813179497239, "grad_norm": 1.2104103565216064, "learning_rate": 8.834842487136463e-05, "loss": 0.4981938362121582, "step": 312710 }, { "epoch": 1.8588726215739073, "grad_norm": 1.4356162548065186, "learning_rate": 8.834238296888886e-05, "loss": 0.5418251991271973, "step": 312720 }, { "epoch": 1.8589320636505757, "grad_norm": 1.2526979446411133, "learning_rate": 8.833634117001603e-05, "loss": 0.5672888278961181, "step": 312730 }, { "epoch": 1.8589915057272441, "grad_norm": 1.2915308475494385, "learning_rate": 8.8330299474775e-05, "loss": 0.5689002990722656, "step": 312740 }, { "epoch": 1.8590509478039126, "grad_norm": 1.2039729356765747, "learning_rate": 8.832425788319482e-05, "loss": 0.5551208019256592, "step": 312750 }, { "epoch": 1.859110389880581, "grad_norm": 1.4865126609802246, "learning_rate": 8.831821639530428e-05, "loss": 0.5544661998748779, "step": 312760 }, { "epoch": 1.8591698319572494, "grad_norm": 1.4666792154312134, "learning_rate": 8.831217501113227e-05, "loss": 0.5650740623474121, "step": 312770 }, { "epoch": 1.8592292740339178, "grad_norm": 1.5689525604248047, "learning_rate": 8.83061337307078e-05, "loss": 0.5356040477752686, "step": 312780 }, { "epoch": 1.859288716110586, "grad_norm": 1.5155705213546753, "learning_rate": 8.830009255405966e-05, "loss": 0.5319299697875977, "step": 312790 }, { "epoch": 1.8593481581872544, "grad_norm": 1.2383383512496948, "learning_rate": 8.829405148121674e-05, "loss": 0.5574947357177734, "step": 312800 }, { "epoch": 1.8594076002639228, "grad_norm": 1.6743963956832886, "learning_rate": 8.828801051220805e-05, "loss": 0.568484115600586, "step": 312810 }, { "epoch": 1.8594670423405912, "grad_norm": 1.4092196226119995, "learning_rate": 8.828196964706241e-05, "loss": 0.5868836402893066, "step": 312820 }, { "epoch": 1.8595264844172597, "grad_norm": 1.498643159866333, "learning_rate": 8.827592888580869e-05, "loss": 0.545527172088623, "step": 312830 }, { "epoch": 1.8595859264939278, "grad_norm": 1.3970967531204224, "learning_rate": 8.826988822847588e-05, "loss": 0.5008282661437988, "step": 312840 }, { "epoch": 1.8596453685705963, "grad_norm": 1.6070224046707153, "learning_rate": 8.826384767509279e-05, "loss": 0.5331242561340332, "step": 312850 }, { "epoch": 1.8597048106472647, "grad_norm": 1.415360927581787, "learning_rate": 8.825780722568837e-05, "loss": 0.5376343250274658, "step": 312860 }, { "epoch": 1.859764252723933, "grad_norm": 1.384412169456482, "learning_rate": 8.825176688029148e-05, "loss": 0.5234677791595459, "step": 312870 }, { "epoch": 1.8598236948006015, "grad_norm": 1.2658782005310059, "learning_rate": 8.824572663893105e-05, "loss": 0.5711066246032714, "step": 312880 }, { "epoch": 1.85988313687727, "grad_norm": 1.0937981605529785, "learning_rate": 8.823968650163593e-05, "loss": 0.5007558822631836, "step": 312890 }, { "epoch": 1.8599425789539383, "grad_norm": 1.560051441192627, "learning_rate": 8.823364646843501e-05, "loss": 0.5064540386199952, "step": 312900 }, { "epoch": 1.8600020210306067, "grad_norm": 1.2944413423538208, "learning_rate": 8.822760653935727e-05, "loss": 0.5113224983215332, "step": 312910 }, { "epoch": 1.8600614631072752, "grad_norm": 1.2990756034851074, "learning_rate": 8.822156671443153e-05, "loss": 0.5532089233398437, "step": 312920 }, { "epoch": 1.8601209051839436, "grad_norm": 1.0276381969451904, "learning_rate": 8.821552699368667e-05, "loss": 0.5806421279907227, "step": 312930 }, { "epoch": 1.860180347260612, "grad_norm": 1.0915954113006592, "learning_rate": 8.820948737715163e-05, "loss": 0.5797887325286866, "step": 312940 }, { "epoch": 1.8602397893372804, "grad_norm": 1.3476693630218506, "learning_rate": 8.82034478648553e-05, "loss": 0.5259197235107422, "step": 312950 }, { "epoch": 1.8602992314139488, "grad_norm": 1.5330442190170288, "learning_rate": 8.819740845682652e-05, "loss": 0.5465986251831054, "step": 312960 }, { "epoch": 1.8603586734906172, "grad_norm": 1.4608871936798096, "learning_rate": 8.819136915309422e-05, "loss": 0.5628010749816894, "step": 312970 }, { "epoch": 1.8604181155672854, "grad_norm": 1.551604151725769, "learning_rate": 8.81853299536873e-05, "loss": 0.5331235885620117, "step": 312980 }, { "epoch": 1.8604775576439538, "grad_norm": 1.0375117063522339, "learning_rate": 8.817929085863463e-05, "loss": 0.5178759098052979, "step": 312990 }, { "epoch": 1.8605369997206223, "grad_norm": 1.2208346128463745, "learning_rate": 8.817325186796508e-05, "loss": 0.5558769226074218, "step": 313000 }, { "epoch": 1.8605964417972907, "grad_norm": 1.0748931169509888, "learning_rate": 8.816721298170759e-05, "loss": 0.5636015892028808, "step": 313010 }, { "epoch": 1.8606558838739589, "grad_norm": 1.5084582567214966, "learning_rate": 8.816117419989099e-05, "loss": 0.5588407993316651, "step": 313020 }, { "epoch": 1.8607153259506273, "grad_norm": 1.317017912864685, "learning_rate": 8.81551355225442e-05, "loss": 0.5544799327850342, "step": 313030 }, { "epoch": 1.8607747680272957, "grad_norm": 1.3762941360473633, "learning_rate": 8.814909694969611e-05, "loss": 0.5292058944702148, "step": 313040 }, { "epoch": 1.860834210103964, "grad_norm": 2.438122272491455, "learning_rate": 8.814305848137558e-05, "loss": 0.5334881782531739, "step": 313050 }, { "epoch": 1.8608936521806325, "grad_norm": 1.8883588314056396, "learning_rate": 8.813702011761153e-05, "loss": 0.5653192520141601, "step": 313060 }, { "epoch": 1.860953094257301, "grad_norm": 1.7587177753448486, "learning_rate": 8.813098185843285e-05, "loss": 0.5350878238677979, "step": 313070 }, { "epoch": 1.8610125363339693, "grad_norm": 1.4579098224639893, "learning_rate": 8.812494370386839e-05, "loss": 0.5180005073547364, "step": 313080 }, { "epoch": 1.8610719784106378, "grad_norm": 1.4123653173446655, "learning_rate": 8.811890565394704e-05, "loss": 0.5624983787536622, "step": 313090 }, { "epoch": 1.8611314204873062, "grad_norm": 1.6867127418518066, "learning_rate": 8.811286770869771e-05, "loss": 0.5909216403961182, "step": 313100 }, { "epoch": 1.8611908625639746, "grad_norm": 1.687396764755249, "learning_rate": 8.810682986814927e-05, "loss": 0.6048468112945556, "step": 313110 }, { "epoch": 1.861250304640643, "grad_norm": 1.339333415031433, "learning_rate": 8.81007921323306e-05, "loss": 0.5917468070983887, "step": 313120 }, { "epoch": 1.8613097467173114, "grad_norm": 1.57756769657135, "learning_rate": 8.809475450127056e-05, "loss": 0.5393133163452148, "step": 313130 }, { "epoch": 1.8613691887939798, "grad_norm": 1.298189640045166, "learning_rate": 8.808871697499808e-05, "loss": 0.6014580726623535, "step": 313140 }, { "epoch": 1.8614286308706482, "grad_norm": 1.6675090789794922, "learning_rate": 8.808267955354202e-05, "loss": 0.5436141967773438, "step": 313150 }, { "epoch": 1.8614880729473164, "grad_norm": 1.6409965753555298, "learning_rate": 8.807664223693124e-05, "loss": 0.5425511837005615, "step": 313160 }, { "epoch": 1.8615475150239849, "grad_norm": 1.4983441829681396, "learning_rate": 8.807060502519465e-05, "loss": 0.5968537330627441, "step": 313170 }, { "epoch": 1.8616069571006533, "grad_norm": 1.518542766571045, "learning_rate": 8.806456791836113e-05, "loss": 0.5567740440368653, "step": 313180 }, { "epoch": 1.8616663991773217, "grad_norm": 1.485796332359314, "learning_rate": 8.805853091645951e-05, "loss": 0.5871702194213867, "step": 313190 }, { "epoch": 1.86172584125399, "grad_norm": 1.3679965734481812, "learning_rate": 8.805249401951874e-05, "loss": 0.5461760520935058, "step": 313200 }, { "epoch": 1.8617852833306583, "grad_norm": 1.4410611391067505, "learning_rate": 8.804645722756766e-05, "loss": 0.50276198387146, "step": 313210 }, { "epoch": 1.8618447254073267, "grad_norm": 1.562215805053711, "learning_rate": 8.80404205406352e-05, "loss": 0.5245563507080078, "step": 313220 }, { "epoch": 1.8619041674839951, "grad_norm": 1.4440547227859497, "learning_rate": 8.80343839587501e-05, "loss": 0.5541435241699219, "step": 313230 }, { "epoch": 1.8619636095606635, "grad_norm": 1.4110500812530518, "learning_rate": 8.802834748194138e-05, "loss": 0.4974645137786865, "step": 313240 }, { "epoch": 1.862023051637332, "grad_norm": 1.7290033102035522, "learning_rate": 8.802231111023789e-05, "loss": 0.5757686138153076, "step": 313250 }, { "epoch": 1.8620824937140004, "grad_norm": 1.827327847480774, "learning_rate": 8.80162748436684e-05, "loss": 0.5630389213562011, "step": 313260 }, { "epoch": 1.8621419357906688, "grad_norm": 1.423435926437378, "learning_rate": 8.801023868226192e-05, "loss": 0.5035572528839112, "step": 313270 }, { "epoch": 1.8622013778673372, "grad_norm": 1.9120656251907349, "learning_rate": 8.80042026260473e-05, "loss": 0.5542545318603516, "step": 313280 }, { "epoch": 1.8622608199440056, "grad_norm": 1.495159387588501, "learning_rate": 8.799816667505332e-05, "loss": 0.5258954524993896, "step": 313290 }, { "epoch": 1.862320262020674, "grad_norm": 1.5789161920547485, "learning_rate": 8.799213082930896e-05, "loss": 0.5710999488830566, "step": 313300 }, { "epoch": 1.8623797040973424, "grad_norm": 1.1939913034439087, "learning_rate": 8.798609508884308e-05, "loss": 0.6021169662475586, "step": 313310 }, { "epoch": 1.8624391461740109, "grad_norm": 1.4953447580337524, "learning_rate": 8.798005945368446e-05, "loss": 0.5269358634948731, "step": 313320 }, { "epoch": 1.8624985882506793, "grad_norm": 1.1220479011535645, "learning_rate": 8.797402392386209e-05, "loss": 0.46448230743408203, "step": 313330 }, { "epoch": 1.8625580303273477, "grad_norm": 1.7806035280227661, "learning_rate": 8.79679884994048e-05, "loss": 0.5207643508911133, "step": 313340 }, { "epoch": 1.8626174724040159, "grad_norm": 1.4266430139541626, "learning_rate": 8.796195318034141e-05, "loss": 0.6216781616210938, "step": 313350 }, { "epoch": 1.8626769144806843, "grad_norm": 1.1683982610702515, "learning_rate": 8.795591796670086e-05, "loss": 0.5308760643005371, "step": 313360 }, { "epoch": 1.8627363565573527, "grad_norm": 1.5212631225585938, "learning_rate": 8.7949882858512e-05, "loss": 0.5445472717285156, "step": 313370 }, { "epoch": 1.8627957986340211, "grad_norm": 1.3710505962371826, "learning_rate": 8.794384785580368e-05, "loss": 0.5230138778686524, "step": 313380 }, { "epoch": 1.8628552407106893, "grad_norm": 1.478884220123291, "learning_rate": 8.793781295860477e-05, "loss": 0.5730424880981445, "step": 313390 }, { "epoch": 1.8629146827873577, "grad_norm": 1.4606398344039917, "learning_rate": 8.793177816694418e-05, "loss": 0.594810152053833, "step": 313400 }, { "epoch": 1.8629741248640261, "grad_norm": 1.7665413618087769, "learning_rate": 8.792574348085075e-05, "loss": 0.5460296630859375, "step": 313410 }, { "epoch": 1.8630335669406946, "grad_norm": 1.3600720167160034, "learning_rate": 8.791970890035333e-05, "loss": 0.5345160007476807, "step": 313420 }, { "epoch": 1.863093009017363, "grad_norm": 1.0158318281173706, "learning_rate": 8.791367442548082e-05, "loss": 0.4939417839050293, "step": 313430 }, { "epoch": 1.8631524510940314, "grad_norm": 1.390943169593811, "learning_rate": 8.790764005626206e-05, "loss": 0.5632390975952148, "step": 313440 }, { "epoch": 1.8632118931706998, "grad_norm": 1.1746220588684082, "learning_rate": 8.790160579272594e-05, "loss": 0.5125651359558105, "step": 313450 }, { "epoch": 1.8632713352473682, "grad_norm": 1.2929877042770386, "learning_rate": 8.789557163490132e-05, "loss": 0.5417134284973144, "step": 313460 }, { "epoch": 1.8633307773240366, "grad_norm": 1.3835728168487549, "learning_rate": 8.788953758281706e-05, "loss": 0.5400221347808838, "step": 313470 }, { "epoch": 1.863390219400705, "grad_norm": 1.368277907371521, "learning_rate": 8.788350363650204e-05, "loss": 0.5293965339660645, "step": 313480 }, { "epoch": 1.8634496614773735, "grad_norm": 1.688417911529541, "learning_rate": 8.787746979598509e-05, "loss": 0.5608823776245118, "step": 313490 }, { "epoch": 1.8635091035540419, "grad_norm": 1.4273695945739746, "learning_rate": 8.787143606129509e-05, "loss": 0.5299967765808106, "step": 313500 }, { "epoch": 1.8635685456307103, "grad_norm": 1.7516677379608154, "learning_rate": 8.78654024324609e-05, "loss": 0.5517659664154053, "step": 313510 }, { "epoch": 1.8636279877073787, "grad_norm": 1.3370949029922485, "learning_rate": 8.785936890951143e-05, "loss": 0.5344990730285645, "step": 313520 }, { "epoch": 1.863687429784047, "grad_norm": 1.3228771686553955, "learning_rate": 8.785333549247548e-05, "loss": 0.545521354675293, "step": 313530 }, { "epoch": 1.8637468718607153, "grad_norm": 1.7471610307693481, "learning_rate": 8.784730218138193e-05, "loss": 0.5550564765930176, "step": 313540 }, { "epoch": 1.8638063139373837, "grad_norm": 1.244376301765442, "learning_rate": 8.784126897625964e-05, "loss": 0.5446601867675781, "step": 313550 }, { "epoch": 1.8638657560140521, "grad_norm": 1.2701423168182373, "learning_rate": 8.783523587713751e-05, "loss": 0.5185300350189209, "step": 313560 }, { "epoch": 1.8639251980907205, "grad_norm": 1.5072554349899292, "learning_rate": 8.782920288404435e-05, "loss": 0.551610279083252, "step": 313570 }, { "epoch": 1.8639846401673887, "grad_norm": 1.227164387702942, "learning_rate": 8.782316999700904e-05, "loss": 0.5404624462127685, "step": 313580 }, { "epoch": 1.8640440822440572, "grad_norm": 1.315919280052185, "learning_rate": 8.781713721606042e-05, "loss": 0.5507583141326904, "step": 313590 }, { "epoch": 1.8641035243207256, "grad_norm": 1.146009922027588, "learning_rate": 8.781110454122739e-05, "loss": 0.5420955657958985, "step": 313600 }, { "epoch": 1.864162966397394, "grad_norm": 1.2560393810272217, "learning_rate": 8.780507197253877e-05, "loss": 0.5246415138244629, "step": 313610 }, { "epoch": 1.8642224084740624, "grad_norm": 1.3777436017990112, "learning_rate": 8.779903951002344e-05, "loss": 0.5035182476043701, "step": 313620 }, { "epoch": 1.8642818505507308, "grad_norm": 1.621246576309204, "learning_rate": 8.779300715371026e-05, "loss": 0.5663679599761963, "step": 313630 }, { "epoch": 1.8643412926273992, "grad_norm": 1.366029977798462, "learning_rate": 8.778697490362806e-05, "loss": 0.5484122276306153, "step": 313640 }, { "epoch": 1.8644007347040676, "grad_norm": 1.5301895141601562, "learning_rate": 8.77809427598057e-05, "loss": 0.6127470970153809, "step": 313650 }, { "epoch": 1.864460176780736, "grad_norm": 1.103658676147461, "learning_rate": 8.777491072227208e-05, "loss": 0.530651330947876, "step": 313660 }, { "epoch": 1.8645196188574045, "grad_norm": 1.1684921979904175, "learning_rate": 8.776887879105602e-05, "loss": 0.5818615913391113, "step": 313670 }, { "epoch": 1.8645790609340729, "grad_norm": 1.3025530576705933, "learning_rate": 8.776284696618636e-05, "loss": 0.565767478942871, "step": 313680 }, { "epoch": 1.8646385030107413, "grad_norm": 1.5974901914596558, "learning_rate": 8.775681524769196e-05, "loss": 0.5634930610656739, "step": 313690 }, { "epoch": 1.8646979450874097, "grad_norm": 1.1762391328811646, "learning_rate": 8.775078363560171e-05, "loss": 0.5477480888366699, "step": 313700 }, { "epoch": 1.8647573871640781, "grad_norm": 1.6467167139053345, "learning_rate": 8.774475212994449e-05, "loss": 0.5291168212890625, "step": 313710 }, { "epoch": 1.8648168292407463, "grad_norm": 1.0513513088226318, "learning_rate": 8.7738720730749e-05, "loss": 0.5228317260742188, "step": 313720 }, { "epoch": 1.8648762713174147, "grad_norm": 1.8494441509246826, "learning_rate": 8.773268943804427e-05, "loss": 0.504279613494873, "step": 313730 }, { "epoch": 1.8649357133940831, "grad_norm": 0.9849303364753723, "learning_rate": 8.772665825185906e-05, "loss": 0.5220955848693848, "step": 313740 }, { "epoch": 1.8649951554707516, "grad_norm": 1.243518590927124, "learning_rate": 8.77206271722222e-05, "loss": 0.5256680488586426, "step": 313750 }, { "epoch": 1.8650545975474198, "grad_norm": 1.259883165359497, "learning_rate": 8.771459619916262e-05, "loss": 0.583293104171753, "step": 313760 }, { "epoch": 1.8651140396240882, "grad_norm": 1.2036635875701904, "learning_rate": 8.770856533270915e-05, "loss": 0.5426787376403809, "step": 313770 }, { "epoch": 1.8651734817007566, "grad_norm": 1.2730305194854736, "learning_rate": 8.770253457289055e-05, "loss": 0.517198133468628, "step": 313780 }, { "epoch": 1.865232923777425, "grad_norm": 1.2661246061325073, "learning_rate": 8.769650391973577e-05, "loss": 0.5647058486938477, "step": 313790 }, { "epoch": 1.8652923658540934, "grad_norm": 1.2271836996078491, "learning_rate": 8.769047337327365e-05, "loss": 0.519285011291504, "step": 313800 }, { "epoch": 1.8653518079307618, "grad_norm": 1.1174983978271484, "learning_rate": 8.768444293353297e-05, "loss": 0.5019304275512695, "step": 313810 }, { "epoch": 1.8654112500074302, "grad_norm": 1.1037122011184692, "learning_rate": 8.767841260054266e-05, "loss": 0.5464382171630859, "step": 313820 }, { "epoch": 1.8654706920840987, "grad_norm": 1.688684105873108, "learning_rate": 8.767238237433154e-05, "loss": 0.5476465225219727, "step": 313830 }, { "epoch": 1.865530134160767, "grad_norm": 1.1587425470352173, "learning_rate": 8.766635225492843e-05, "loss": 0.5466852188110352, "step": 313840 }, { "epoch": 1.8655895762374355, "grad_norm": 1.567940354347229, "learning_rate": 8.766032224236216e-05, "loss": 0.5566900730133056, "step": 313850 }, { "epoch": 1.865649018314104, "grad_norm": 1.2324259281158447, "learning_rate": 8.765429233666164e-05, "loss": 0.48424196243286133, "step": 313860 }, { "epoch": 1.8657084603907723, "grad_norm": 1.8085970878601074, "learning_rate": 8.764826253785567e-05, "loss": 0.49676666259765623, "step": 313870 }, { "epoch": 1.8657679024674407, "grad_norm": 0.9832847714424133, "learning_rate": 8.764223284597308e-05, "loss": 0.4844703674316406, "step": 313880 }, { "epoch": 1.8658273445441091, "grad_norm": 1.6939446926116943, "learning_rate": 8.763620326104283e-05, "loss": 0.5617596626281738, "step": 313890 }, { "epoch": 1.8658867866207773, "grad_norm": 1.3682115077972412, "learning_rate": 8.76301737830936e-05, "loss": 0.5033958911895752, "step": 313900 }, { "epoch": 1.8659462286974458, "grad_norm": 1.2109179496765137, "learning_rate": 8.76241444121543e-05, "loss": 0.5117528438568115, "step": 313910 }, { "epoch": 1.8660056707741142, "grad_norm": 1.1895567178726196, "learning_rate": 8.761811514825385e-05, "loss": 0.5052965164184571, "step": 313920 }, { "epoch": 1.8660651128507826, "grad_norm": 1.5096657276153564, "learning_rate": 8.761208599142096e-05, "loss": 0.531721830368042, "step": 313930 }, { "epoch": 1.866124554927451, "grad_norm": 1.5546940565109253, "learning_rate": 8.760605694168458e-05, "loss": 0.5877686500549316, "step": 313940 }, { "epoch": 1.8661839970041192, "grad_norm": 1.8369873762130737, "learning_rate": 8.760002799907345e-05, "loss": 0.519627046585083, "step": 313950 }, { "epoch": 1.8662434390807876, "grad_norm": 1.3377801179885864, "learning_rate": 8.759399916361651e-05, "loss": 0.5150635719299317, "step": 313960 }, { "epoch": 1.866302881157456, "grad_norm": 1.6306902170181274, "learning_rate": 8.758797043534254e-05, "loss": 0.5585918426513672, "step": 313970 }, { "epoch": 1.8663623232341244, "grad_norm": 1.4911549091339111, "learning_rate": 8.758194181428039e-05, "loss": 0.5567773818969727, "step": 313980 }, { "epoch": 1.8664217653107928, "grad_norm": 1.3169403076171875, "learning_rate": 8.757591330045892e-05, "loss": 0.5429695129394532, "step": 313990 }, { "epoch": 1.8664812073874613, "grad_norm": 1.565433144569397, "learning_rate": 8.756988489390694e-05, "loss": 0.5163224697113037, "step": 314000 }, { "epoch": 1.8665406494641297, "grad_norm": 1.4736933708190918, "learning_rate": 8.75638565946533e-05, "loss": 0.5220009803771972, "step": 314010 }, { "epoch": 1.866600091540798, "grad_norm": 1.4553446769714355, "learning_rate": 8.755782840272684e-05, "loss": 0.5460208892822266, "step": 314020 }, { "epoch": 1.8666595336174665, "grad_norm": 0.9997037053108215, "learning_rate": 8.75518003181564e-05, "loss": 0.5617160797119141, "step": 314030 }, { "epoch": 1.866718975694135, "grad_norm": 1.0172723531723022, "learning_rate": 8.754577234097079e-05, "loss": 0.4877618789672852, "step": 314040 }, { "epoch": 1.8667784177708033, "grad_norm": 1.388437032699585, "learning_rate": 8.753974447119888e-05, "loss": 0.6069372177124024, "step": 314050 }, { "epoch": 1.8668378598474717, "grad_norm": 1.6539661884307861, "learning_rate": 8.753371670886949e-05, "loss": 0.547592306137085, "step": 314060 }, { "epoch": 1.8668973019241402, "grad_norm": 1.4579671621322632, "learning_rate": 8.752768905401147e-05, "loss": 0.5483967781066894, "step": 314070 }, { "epoch": 1.8669567440008086, "grad_norm": 1.8368319272994995, "learning_rate": 8.752166150665364e-05, "loss": 0.5309564590454101, "step": 314080 }, { "epoch": 1.8670161860774768, "grad_norm": 1.5614882707595825, "learning_rate": 8.751563406682483e-05, "loss": 0.5753488540649414, "step": 314090 }, { "epoch": 1.8670756281541452, "grad_norm": 1.506946325302124, "learning_rate": 8.750960673455388e-05, "loss": 0.5247782707214356, "step": 314100 }, { "epoch": 1.8671350702308136, "grad_norm": 1.6008009910583496, "learning_rate": 8.750357950986961e-05, "loss": 0.5786550045013428, "step": 314110 }, { "epoch": 1.867194512307482, "grad_norm": 1.6691642999649048, "learning_rate": 8.749755239280089e-05, "loss": 0.5557346343994141, "step": 314120 }, { "epoch": 1.8672539543841502, "grad_norm": 1.3379756212234497, "learning_rate": 8.74915253833765e-05, "loss": 0.5559041500091553, "step": 314130 }, { "epoch": 1.8673133964608186, "grad_norm": 1.4046339988708496, "learning_rate": 8.74854984816253e-05, "loss": 0.5197118759155274, "step": 314140 }, { "epoch": 1.867372838537487, "grad_norm": 1.9482115507125854, "learning_rate": 8.747947168757613e-05, "loss": 0.6206577301025391, "step": 314150 }, { "epoch": 1.8674322806141554, "grad_norm": 1.3623900413513184, "learning_rate": 8.74734450012578e-05, "loss": 0.5504301071166993, "step": 314160 }, { "epoch": 1.8674917226908239, "grad_norm": 1.5067102909088135, "learning_rate": 8.746741842269914e-05, "loss": 0.5317303657531738, "step": 314170 }, { "epoch": 1.8675511647674923, "grad_norm": 1.2763806581497192, "learning_rate": 8.7461391951929e-05, "loss": 0.5359315395355224, "step": 314180 }, { "epoch": 1.8676106068441607, "grad_norm": 1.4338281154632568, "learning_rate": 8.74553655889762e-05, "loss": 0.5308757781982422, "step": 314190 }, { "epoch": 1.867670048920829, "grad_norm": 1.6948308944702148, "learning_rate": 8.744933933386958e-05, "loss": 0.5206740379333497, "step": 314200 }, { "epoch": 1.8677294909974975, "grad_norm": 1.5598036050796509, "learning_rate": 8.744331318663787e-05, "loss": 0.5495528221130371, "step": 314210 }, { "epoch": 1.867788933074166, "grad_norm": 1.2692718505859375, "learning_rate": 8.743728714731005e-05, "loss": 0.5284677028656006, "step": 314220 }, { "epoch": 1.8678483751508344, "grad_norm": 1.2565054893493652, "learning_rate": 8.743126121591488e-05, "loss": 0.5236921787261963, "step": 314230 }, { "epoch": 1.8679078172275028, "grad_norm": 1.1487395763397217, "learning_rate": 8.742523539248113e-05, "loss": 0.5644468307495117, "step": 314240 }, { "epoch": 1.8679672593041712, "grad_norm": 1.3500304222106934, "learning_rate": 8.741920967703772e-05, "loss": 0.5788546562194824, "step": 314250 }, { "epoch": 1.8680267013808396, "grad_norm": 1.4126253128051758, "learning_rate": 8.741318406961343e-05, "loss": 0.5159573554992676, "step": 314260 }, { "epoch": 1.8680861434575078, "grad_norm": 1.0839498043060303, "learning_rate": 8.740715857023704e-05, "loss": 0.525084114074707, "step": 314270 }, { "epoch": 1.8681455855341762, "grad_norm": 1.5750480890274048, "learning_rate": 8.740113317893745e-05, "loss": 0.5718554019927978, "step": 314280 }, { "epoch": 1.8682050276108446, "grad_norm": 1.3885257244110107, "learning_rate": 8.739510789574347e-05, "loss": 0.5277812004089355, "step": 314290 }, { "epoch": 1.868264469687513, "grad_norm": 1.50142240524292, "learning_rate": 8.738908272068389e-05, "loss": 0.5492593765258789, "step": 314300 }, { "epoch": 1.8683239117641814, "grad_norm": 1.653164029121399, "learning_rate": 8.738305765378753e-05, "loss": 0.5613057613372803, "step": 314310 }, { "epoch": 1.8683833538408496, "grad_norm": 1.5416054725646973, "learning_rate": 8.737703269508328e-05, "loss": 0.5390623092651368, "step": 314320 }, { "epoch": 1.868442795917518, "grad_norm": 1.355611801147461, "learning_rate": 8.73710078445999e-05, "loss": 0.5170114517211915, "step": 314330 }, { "epoch": 1.8685022379941865, "grad_norm": 1.3228230476379395, "learning_rate": 8.736498310236616e-05, "loss": 0.5710327625274658, "step": 314340 }, { "epoch": 1.8685616800708549, "grad_norm": 1.5207257270812988, "learning_rate": 8.735895846841104e-05, "loss": 0.48462514877319335, "step": 314350 }, { "epoch": 1.8686211221475233, "grad_norm": 1.0878382921218872, "learning_rate": 8.73529339427632e-05, "loss": 0.5438052654266358, "step": 314360 }, { "epoch": 1.8686805642241917, "grad_norm": 1.4327646493911743, "learning_rate": 8.734690952545151e-05, "loss": 0.5542325496673584, "step": 314370 }, { "epoch": 1.8687400063008601, "grad_norm": 1.2241848707199097, "learning_rate": 8.734088521650485e-05, "loss": 0.5421709060668946, "step": 314380 }, { "epoch": 1.8687994483775285, "grad_norm": 1.2851811647415161, "learning_rate": 8.733486101595199e-05, "loss": 0.5944109916687011, "step": 314390 }, { "epoch": 1.868858890454197, "grad_norm": 1.4446303844451904, "learning_rate": 8.732883692382168e-05, "loss": 0.5388508796691894, "step": 314400 }, { "epoch": 1.8689183325308654, "grad_norm": 1.457929015159607, "learning_rate": 8.732281294014288e-05, "loss": 0.5053557395935059, "step": 314410 }, { "epoch": 1.8689777746075338, "grad_norm": 1.6444770097732544, "learning_rate": 8.731678906494431e-05, "loss": 0.5533729553222656, "step": 314420 }, { "epoch": 1.8690372166842022, "grad_norm": 1.496428370475769, "learning_rate": 8.731076529825481e-05, "loss": 0.5948814392089844, "step": 314430 }, { "epoch": 1.8690966587608706, "grad_norm": 1.7439876794815063, "learning_rate": 8.730474164010319e-05, "loss": 0.5998573780059815, "step": 314440 }, { "epoch": 1.869156100837539, "grad_norm": 1.45953369140625, "learning_rate": 8.729871809051826e-05, "loss": 0.5824409008026123, "step": 314450 }, { "epoch": 1.8692155429142072, "grad_norm": 1.7373778820037842, "learning_rate": 8.729269464952885e-05, "loss": 0.555302906036377, "step": 314460 }, { "epoch": 1.8692749849908756, "grad_norm": 1.5338332653045654, "learning_rate": 8.728667131716376e-05, "loss": 0.5296721458435059, "step": 314470 }, { "epoch": 1.869334427067544, "grad_norm": 1.801216721534729, "learning_rate": 8.72806480934518e-05, "loss": 0.5632346153259278, "step": 314480 }, { "epoch": 1.8693938691442125, "grad_norm": 1.2894630432128906, "learning_rate": 8.727462497842184e-05, "loss": 0.5407458782196045, "step": 314490 }, { "epoch": 1.8694533112208807, "grad_norm": 1.4898693561553955, "learning_rate": 8.726860197210261e-05, "loss": 0.5480835914611817, "step": 314500 }, { "epoch": 1.869512753297549, "grad_norm": 1.4690014123916626, "learning_rate": 8.726257907452296e-05, "loss": 0.5158400535583496, "step": 314510 }, { "epoch": 1.8695721953742175, "grad_norm": 1.3979930877685547, "learning_rate": 8.725655628571171e-05, "loss": 0.5689130783081054, "step": 314520 }, { "epoch": 1.869631637450886, "grad_norm": 1.4153391122817993, "learning_rate": 8.725053360569767e-05, "loss": 0.5024464130401611, "step": 314530 }, { "epoch": 1.8696910795275543, "grad_norm": 1.3949106931686401, "learning_rate": 8.724451103450964e-05, "loss": 0.5392035961151123, "step": 314540 }, { "epoch": 1.8697505216042227, "grad_norm": 1.6949259042739868, "learning_rate": 8.723848857217643e-05, "loss": 0.5633868217468262, "step": 314550 }, { "epoch": 1.8698099636808911, "grad_norm": 1.392170786857605, "learning_rate": 8.723246621872685e-05, "loss": 0.5032478332519531, "step": 314560 }, { "epoch": 1.8698694057575596, "grad_norm": 1.2041237354278564, "learning_rate": 8.722644397418971e-05, "loss": 0.5930917739868165, "step": 314570 }, { "epoch": 1.869928847834228, "grad_norm": 1.906419038772583, "learning_rate": 8.722042183859382e-05, "loss": 0.5544804573059082, "step": 314580 }, { "epoch": 1.8699882899108964, "grad_norm": 1.4335827827453613, "learning_rate": 8.721439981196799e-05, "loss": 0.5574295997619629, "step": 314590 }, { "epoch": 1.8700477319875648, "grad_norm": 1.387982964515686, "learning_rate": 8.720837789434102e-05, "loss": 0.5558055400848388, "step": 314600 }, { "epoch": 1.8701071740642332, "grad_norm": 1.242679476737976, "learning_rate": 8.720235608574173e-05, "loss": 0.44962139129638673, "step": 314610 }, { "epoch": 1.8701666161409016, "grad_norm": 1.2676814794540405, "learning_rate": 8.71963343861989e-05, "loss": 0.5861848831176758, "step": 314620 }, { "epoch": 1.87022605821757, "grad_norm": 1.3660447597503662, "learning_rate": 8.719031279574137e-05, "loss": 0.5824050426483154, "step": 314630 }, { "epoch": 1.8702855002942382, "grad_norm": 1.5687639713287354, "learning_rate": 8.718429131439794e-05, "loss": 0.5828472137451172, "step": 314640 }, { "epoch": 1.8703449423709066, "grad_norm": 1.4746750593185425, "learning_rate": 8.71782699421974e-05, "loss": 0.5377824783325196, "step": 314650 }, { "epoch": 1.870404384447575, "grad_norm": 1.0508860349655151, "learning_rate": 8.717224867916851e-05, "loss": 0.5098757743835449, "step": 314660 }, { "epoch": 1.8704638265242435, "grad_norm": 1.2662547826766968, "learning_rate": 8.716622752534019e-05, "loss": 0.5355660438537597, "step": 314670 }, { "epoch": 1.870523268600912, "grad_norm": 1.197790265083313, "learning_rate": 8.716020648074114e-05, "loss": 0.5885440826416015, "step": 314680 }, { "epoch": 1.87058271067758, "grad_norm": 1.4022672176361084, "learning_rate": 8.71541855454002e-05, "loss": 0.5753978729248047, "step": 314690 }, { "epoch": 1.8706421527542485, "grad_norm": 1.4912384748458862, "learning_rate": 8.714816471934617e-05, "loss": 0.5196763038635254, "step": 314700 }, { "epoch": 1.870701594830917, "grad_norm": 1.375925064086914, "learning_rate": 8.714214400260785e-05, "loss": 0.5250082969665527, "step": 314710 }, { "epoch": 1.8707610369075853, "grad_norm": 1.3701937198638916, "learning_rate": 8.713612339521406e-05, "loss": 0.5366766929626465, "step": 314720 }, { "epoch": 1.8708204789842537, "grad_norm": 1.339697003364563, "learning_rate": 8.713010289719356e-05, "loss": 0.5522482872009278, "step": 314730 }, { "epoch": 1.8708799210609222, "grad_norm": 1.4386563301086426, "learning_rate": 8.71240825085752e-05, "loss": 0.5577672958374024, "step": 314740 }, { "epoch": 1.8709393631375906, "grad_norm": 2.028388738632202, "learning_rate": 8.711806222938777e-05, "loss": 0.5203115463256835, "step": 314750 }, { "epoch": 1.870998805214259, "grad_norm": 1.4748934507369995, "learning_rate": 8.711204205966e-05, "loss": 0.5479655742645264, "step": 314760 }, { "epoch": 1.8710582472909274, "grad_norm": 1.6516375541687012, "learning_rate": 8.710602199942075e-05, "loss": 0.5372496128082276, "step": 314770 }, { "epoch": 1.8711176893675958, "grad_norm": 1.3255363702774048, "learning_rate": 8.710000204869886e-05, "loss": 0.529545783996582, "step": 314780 }, { "epoch": 1.8711771314442642, "grad_norm": 1.596751093864441, "learning_rate": 8.709398220752303e-05, "loss": 0.5799068450927735, "step": 314790 }, { "epoch": 1.8712365735209326, "grad_norm": 1.7975831031799316, "learning_rate": 8.708796247592208e-05, "loss": 0.5579296112060547, "step": 314800 }, { "epoch": 1.871296015597601, "grad_norm": 1.6909412145614624, "learning_rate": 8.70819428539249e-05, "loss": 0.498063850402832, "step": 314810 }, { "epoch": 1.8713554576742695, "grad_norm": 1.7182910442352295, "learning_rate": 8.707592334156018e-05, "loss": 0.5625438213348388, "step": 314820 }, { "epoch": 1.8714148997509377, "grad_norm": 1.276228904724121, "learning_rate": 8.706990393885673e-05, "loss": 0.5783598899841309, "step": 314830 }, { "epoch": 1.871474341827606, "grad_norm": 1.458316683769226, "learning_rate": 8.706388464584341e-05, "loss": 0.517142391204834, "step": 314840 }, { "epoch": 1.8715337839042745, "grad_norm": 1.3635811805725098, "learning_rate": 8.705786546254895e-05, "loss": 0.5648690223693847, "step": 314850 }, { "epoch": 1.871593225980943, "grad_norm": 1.7168166637420654, "learning_rate": 8.70518463890021e-05, "loss": 0.5620282649993896, "step": 314860 }, { "epoch": 1.871652668057611, "grad_norm": 1.3838355541229248, "learning_rate": 8.704582742523182e-05, "loss": 0.5283494472503663, "step": 314870 }, { "epoch": 1.8717121101342795, "grad_norm": 1.6914297342300415, "learning_rate": 8.703980857126675e-05, "loss": 0.5232665538787842, "step": 314880 }, { "epoch": 1.871771552210948, "grad_norm": 1.3358755111694336, "learning_rate": 8.703378982713572e-05, "loss": 0.530211353302002, "step": 314890 }, { "epoch": 1.8718309942876163, "grad_norm": 1.5213617086410522, "learning_rate": 8.702777119286757e-05, "loss": 0.5848456382751465, "step": 314900 }, { "epoch": 1.8718904363642848, "grad_norm": 1.5101467370986938, "learning_rate": 8.702175266849104e-05, "loss": 0.5074196815490722, "step": 314910 }, { "epoch": 1.8719498784409532, "grad_norm": 1.3459103107452393, "learning_rate": 8.701573425403493e-05, "loss": 0.5160452365875244, "step": 314920 }, { "epoch": 1.8720093205176216, "grad_norm": 1.368329405784607, "learning_rate": 8.700971594952805e-05, "loss": 0.5414178848266602, "step": 314930 }, { "epoch": 1.87206876259429, "grad_norm": 1.9498902559280396, "learning_rate": 8.700369775499917e-05, "loss": 0.5117685317993164, "step": 314940 }, { "epoch": 1.8721282046709584, "grad_norm": 1.4994823932647705, "learning_rate": 8.699767967047707e-05, "loss": 0.5562950134277344, "step": 314950 }, { "epoch": 1.8721876467476268, "grad_norm": 1.2670539617538452, "learning_rate": 8.699166169599056e-05, "loss": 0.5097482204437256, "step": 314960 }, { "epoch": 1.8722470888242952, "grad_norm": 1.2320003509521484, "learning_rate": 8.698564383156842e-05, "loss": 0.5808621406555176, "step": 314970 }, { "epoch": 1.8723065309009637, "grad_norm": 1.2304632663726807, "learning_rate": 8.697962607723946e-05, "loss": 0.5806901454925537, "step": 314980 }, { "epoch": 1.872365972977632, "grad_norm": 1.8307178020477295, "learning_rate": 8.697360843303241e-05, "loss": 0.6073213577270508, "step": 314990 }, { "epoch": 1.8724254150543005, "grad_norm": 1.2108395099639893, "learning_rate": 8.696759089897612e-05, "loss": 0.5604456901550293, "step": 315000 }, { "epoch": 1.8724848571309687, "grad_norm": 1.1485971212387085, "learning_rate": 8.696157347509934e-05, "loss": 0.5111312866210938, "step": 315010 }, { "epoch": 1.872544299207637, "grad_norm": 1.7510647773742676, "learning_rate": 8.695555616143087e-05, "loss": 0.5578341007232666, "step": 315020 }, { "epoch": 1.8726037412843055, "grad_norm": 1.5884723663330078, "learning_rate": 8.694953895799947e-05, "loss": 0.5101879596710205, "step": 315030 }, { "epoch": 1.872663183360974, "grad_norm": 1.3087116479873657, "learning_rate": 8.694352186483396e-05, "loss": 0.5378361225128174, "step": 315040 }, { "epoch": 1.8727226254376423, "grad_norm": 1.485791802406311, "learning_rate": 8.693750488196311e-05, "loss": 0.4485316276550293, "step": 315050 }, { "epoch": 1.8727820675143105, "grad_norm": 1.706279993057251, "learning_rate": 8.693148800941569e-05, "loss": 0.5195966243743897, "step": 315060 }, { "epoch": 1.872841509590979, "grad_norm": 1.5490596294403076, "learning_rate": 8.692547124722048e-05, "loss": 0.5223191261291504, "step": 315070 }, { "epoch": 1.8729009516676474, "grad_norm": 1.1369980573654175, "learning_rate": 8.69194545954063e-05, "loss": 0.4869264602661133, "step": 315080 }, { "epoch": 1.8729603937443158, "grad_norm": 1.6937044858932495, "learning_rate": 8.691343805400187e-05, "loss": 0.5332900524139405, "step": 315090 }, { "epoch": 1.8730198358209842, "grad_norm": 1.1523418426513672, "learning_rate": 8.690742162303604e-05, "loss": 0.5126923561096192, "step": 315100 }, { "epoch": 1.8730792778976526, "grad_norm": 1.1558854579925537, "learning_rate": 8.690140530253756e-05, "loss": 0.5309207439422607, "step": 315110 }, { "epoch": 1.873138719974321, "grad_norm": 1.3744555711746216, "learning_rate": 8.689538909253518e-05, "loss": 0.5479505062103271, "step": 315120 }, { "epoch": 1.8731981620509894, "grad_norm": 1.5665003061294556, "learning_rate": 8.688937299305775e-05, "loss": 0.5546106815338134, "step": 315130 }, { "epoch": 1.8732576041276578, "grad_norm": 0.9916151762008667, "learning_rate": 8.688335700413397e-05, "loss": 0.5354560852050781, "step": 315140 }, { "epoch": 1.8733170462043263, "grad_norm": 1.2596153020858765, "learning_rate": 8.687734112579267e-05, "loss": 0.5427788734436035, "step": 315150 }, { "epoch": 1.8733764882809947, "grad_norm": 1.4728139638900757, "learning_rate": 8.687132535806261e-05, "loss": 0.5101790428161621, "step": 315160 }, { "epoch": 1.873435930357663, "grad_norm": 1.3063560724258423, "learning_rate": 8.686530970097258e-05, "loss": 0.580266284942627, "step": 315170 }, { "epoch": 1.8734953724343315, "grad_norm": 1.5715783834457397, "learning_rate": 8.685929415455135e-05, "loss": 0.5584806442260742, "step": 315180 }, { "epoch": 1.873554814511, "grad_norm": 1.212079405784607, "learning_rate": 8.685327871882767e-05, "loss": 0.4981998443603516, "step": 315190 }, { "epoch": 1.8736142565876681, "grad_norm": 1.7736890316009521, "learning_rate": 8.684726339383036e-05, "loss": 0.5742500782012939, "step": 315200 }, { "epoch": 1.8736736986643365, "grad_norm": 1.700699806213379, "learning_rate": 8.684124817958816e-05, "loss": 0.6130049228668213, "step": 315210 }, { "epoch": 1.873733140741005, "grad_norm": 1.6153380870819092, "learning_rate": 8.683523307612987e-05, "loss": 0.5917044162750245, "step": 315220 }, { "epoch": 1.8737925828176734, "grad_norm": 1.50175940990448, "learning_rate": 8.682921808348426e-05, "loss": 0.5814779281616211, "step": 315230 }, { "epoch": 1.8738520248943416, "grad_norm": 1.2983976602554321, "learning_rate": 8.68232032016801e-05, "loss": 0.5059018135070801, "step": 315240 }, { "epoch": 1.87391146697101, "grad_norm": 1.2797365188598633, "learning_rate": 8.681718843074614e-05, "loss": 0.5433332443237304, "step": 315250 }, { "epoch": 1.8739709090476784, "grad_norm": 1.2307380437850952, "learning_rate": 8.681117377071119e-05, "loss": 0.5250359535217285, "step": 315260 }, { "epoch": 1.8740303511243468, "grad_norm": 1.389890432357788, "learning_rate": 8.680515922160402e-05, "loss": 0.5066890716552734, "step": 315270 }, { "epoch": 1.8740897932010152, "grad_norm": 1.4597716331481934, "learning_rate": 8.67991447834534e-05, "loss": 0.5635015487670898, "step": 315280 }, { "epoch": 1.8741492352776836, "grad_norm": 1.5660922527313232, "learning_rate": 8.679313045628803e-05, "loss": 0.542650556564331, "step": 315290 }, { "epoch": 1.874208677354352, "grad_norm": 1.5353862047195435, "learning_rate": 8.678711624013677e-05, "loss": 0.5223559379577637, "step": 315300 }, { "epoch": 1.8742681194310205, "grad_norm": 1.2902839183807373, "learning_rate": 8.678110213502839e-05, "loss": 0.5280547142028809, "step": 315310 }, { "epoch": 1.8743275615076889, "grad_norm": 1.3539656400680542, "learning_rate": 8.677508814099158e-05, "loss": 0.5321042537689209, "step": 315320 }, { "epoch": 1.8743870035843573, "grad_norm": 1.7802560329437256, "learning_rate": 8.676907425805519e-05, "loss": 0.5493329048156739, "step": 315330 }, { "epoch": 1.8744464456610257, "grad_norm": 1.4779188632965088, "learning_rate": 8.676306048624796e-05, "loss": 0.5453527450561524, "step": 315340 }, { "epoch": 1.874505887737694, "grad_norm": 1.5988763570785522, "learning_rate": 8.675704682559862e-05, "loss": 0.5865164756774902, "step": 315350 }, { "epoch": 1.8745653298143625, "grad_norm": 1.3311556577682495, "learning_rate": 8.675103327613601e-05, "loss": 0.4945270538330078, "step": 315360 }, { "epoch": 1.874624771891031, "grad_norm": 1.3882883787155151, "learning_rate": 8.674501983788886e-05, "loss": 0.5074680328369141, "step": 315370 }, { "epoch": 1.8746842139676991, "grad_norm": 1.6976299285888672, "learning_rate": 8.673900651088589e-05, "loss": 0.5376962184906006, "step": 315380 }, { "epoch": 1.8747436560443675, "grad_norm": 0.9847677946090698, "learning_rate": 8.673299329515596e-05, "loss": 0.5403036594390869, "step": 315390 }, { "epoch": 1.874803098121036, "grad_norm": 2.0547869205474854, "learning_rate": 8.672698019072777e-05, "loss": 0.6175178527832031, "step": 315400 }, { "epoch": 1.8748625401977044, "grad_norm": 1.311341643333435, "learning_rate": 8.67209671976301e-05, "loss": 0.4984915733337402, "step": 315410 }, { "epoch": 1.8749219822743728, "grad_norm": 1.3646926879882812, "learning_rate": 8.671495431589169e-05, "loss": 0.5656214714050293, "step": 315420 }, { "epoch": 1.874981424351041, "grad_norm": 1.463118076324463, "learning_rate": 8.670894154554137e-05, "loss": 0.4783310890197754, "step": 315430 }, { "epoch": 1.8750408664277094, "grad_norm": 1.7514244318008423, "learning_rate": 8.670292888660785e-05, "loss": 0.5178280830383301, "step": 315440 }, { "epoch": 1.8751003085043778, "grad_norm": 1.6031975746154785, "learning_rate": 8.669691633911987e-05, "loss": 0.5602826118469239, "step": 315450 }, { "epoch": 1.8751597505810462, "grad_norm": 1.337404489517212, "learning_rate": 8.669090390310628e-05, "loss": 0.5045754909515381, "step": 315460 }, { "epoch": 1.8752191926577146, "grad_norm": 1.1128215789794922, "learning_rate": 8.668489157859577e-05, "loss": 0.5554528713226319, "step": 315470 }, { "epoch": 1.875278634734383, "grad_norm": 1.6293184757232666, "learning_rate": 8.667887936561709e-05, "loss": 0.5241463661193848, "step": 315480 }, { "epoch": 1.8753380768110515, "grad_norm": 1.2495787143707275, "learning_rate": 8.667286726419905e-05, "loss": 0.5623893737792969, "step": 315490 }, { "epoch": 1.8753975188877199, "grad_norm": 1.4103375673294067, "learning_rate": 8.66668552743704e-05, "loss": 0.5890701293945313, "step": 315500 }, { "epoch": 1.8754569609643883, "grad_norm": 1.4714549779891968, "learning_rate": 8.666084339615988e-05, "loss": 0.5464850425720215, "step": 315510 }, { "epoch": 1.8755164030410567, "grad_norm": 1.5711565017700195, "learning_rate": 8.665483162959627e-05, "loss": 0.5193675994873047, "step": 315520 }, { "epoch": 1.8755758451177251, "grad_norm": 1.4163587093353271, "learning_rate": 8.664881997470828e-05, "loss": 0.5543611526489258, "step": 315530 }, { "epoch": 1.8756352871943935, "grad_norm": 1.6108276844024658, "learning_rate": 8.664280843152474e-05, "loss": 0.5261058807373047, "step": 315540 }, { "epoch": 1.875694729271062, "grad_norm": 1.5846827030181885, "learning_rate": 8.663679700007436e-05, "loss": 0.5823328495025635, "step": 315550 }, { "epoch": 1.8757541713477304, "grad_norm": 1.6209007501602173, "learning_rate": 8.663078568038592e-05, "loss": 0.5962756156921387, "step": 315560 }, { "epoch": 1.8758136134243986, "grad_norm": 1.2792956829071045, "learning_rate": 8.662477447248815e-05, "loss": 0.5369988918304444, "step": 315570 }, { "epoch": 1.875873055501067, "grad_norm": 1.5596563816070557, "learning_rate": 8.661876337640982e-05, "loss": 0.5588222503662109, "step": 315580 }, { "epoch": 1.8759324975777354, "grad_norm": 1.4063531160354614, "learning_rate": 8.661275239217968e-05, "loss": 0.4878506660461426, "step": 315590 }, { "epoch": 1.8759919396544038, "grad_norm": 1.6531256437301636, "learning_rate": 8.66067415198265e-05, "loss": 0.5605542182922363, "step": 315600 }, { "epoch": 1.876051381731072, "grad_norm": 1.162711501121521, "learning_rate": 8.660073075937902e-05, "loss": 0.5762710571289062, "step": 315610 }, { "epoch": 1.8761108238077404, "grad_norm": 1.6383095979690552, "learning_rate": 8.6594720110866e-05, "loss": 0.5509128570556641, "step": 315620 }, { "epoch": 1.8761702658844088, "grad_norm": 1.5040405988693237, "learning_rate": 8.65887095743162e-05, "loss": 0.55128493309021, "step": 315630 }, { "epoch": 1.8762297079610772, "grad_norm": 1.2309436798095703, "learning_rate": 8.658269914975834e-05, "loss": 0.5756878852844238, "step": 315640 }, { "epoch": 1.8762891500377457, "grad_norm": 1.2991706132888794, "learning_rate": 8.657668883722118e-05, "loss": 0.5455764293670654, "step": 315650 }, { "epoch": 1.876348592114414, "grad_norm": 1.4098384380340576, "learning_rate": 8.657067863673354e-05, "loss": 0.5141368389129639, "step": 315660 }, { "epoch": 1.8764080341910825, "grad_norm": 1.2924846410751343, "learning_rate": 8.656466854832408e-05, "loss": 0.5467370986938477, "step": 315670 }, { "epoch": 1.876467476267751, "grad_norm": 1.2365421056747437, "learning_rate": 8.655865857202159e-05, "loss": 0.5500918388366699, "step": 315680 }, { "epoch": 1.8765269183444193, "grad_norm": 1.4242784976959229, "learning_rate": 8.655264870785482e-05, "loss": 0.5036118984222412, "step": 315690 }, { "epoch": 1.8765863604210877, "grad_norm": 1.5950515270233154, "learning_rate": 8.654663895585251e-05, "loss": 0.5444416999816895, "step": 315700 }, { "epoch": 1.8766458024977561, "grad_norm": 1.2441741228103638, "learning_rate": 8.65406293160434e-05, "loss": 0.5572663307189941, "step": 315710 }, { "epoch": 1.8767052445744246, "grad_norm": 1.4805347919464111, "learning_rate": 8.65346197884563e-05, "loss": 0.5573266506195068, "step": 315720 }, { "epoch": 1.876764686651093, "grad_norm": 1.1364504098892212, "learning_rate": 8.652861037311988e-05, "loss": 0.539719820022583, "step": 315730 }, { "epoch": 1.8768241287277614, "grad_norm": 1.7538261413574219, "learning_rate": 8.652260107006291e-05, "loss": 0.5881686210632324, "step": 315740 }, { "epoch": 1.8768835708044296, "grad_norm": 1.4478269815444946, "learning_rate": 8.651659187931415e-05, "loss": 0.5689518451690674, "step": 315750 }, { "epoch": 1.876943012881098, "grad_norm": 1.1618849039077759, "learning_rate": 8.651058280090236e-05, "loss": 0.5652687549591064, "step": 315760 }, { "epoch": 1.8770024549577664, "grad_norm": 1.0553176403045654, "learning_rate": 8.650457383485628e-05, "loss": 0.4605320930480957, "step": 315770 }, { "epoch": 1.8770618970344348, "grad_norm": 1.4933900833129883, "learning_rate": 8.649856498120459e-05, "loss": 0.5439887523651123, "step": 315780 }, { "epoch": 1.8771213391111032, "grad_norm": 1.4144513607025146, "learning_rate": 8.64925562399761e-05, "loss": 0.5138792991638184, "step": 315790 }, { "epoch": 1.8771807811877714, "grad_norm": 1.3456565141677856, "learning_rate": 8.648654761119956e-05, "loss": 0.5499786853790283, "step": 315800 }, { "epoch": 1.8772402232644398, "grad_norm": 1.6734561920166016, "learning_rate": 8.648053909490366e-05, "loss": 0.5777980804443359, "step": 315810 }, { "epoch": 1.8772996653411083, "grad_norm": 1.6089987754821777, "learning_rate": 8.647453069111719e-05, "loss": 0.5826149940490722, "step": 315820 }, { "epoch": 1.8773591074177767, "grad_norm": 1.499813437461853, "learning_rate": 8.646852239986891e-05, "loss": 0.5658674716949463, "step": 315830 }, { "epoch": 1.877418549494445, "grad_norm": 1.577825665473938, "learning_rate": 8.646251422118745e-05, "loss": 0.521726417541504, "step": 315840 }, { "epoch": 1.8774779915711135, "grad_norm": 1.5283564329147339, "learning_rate": 8.64565061551017e-05, "loss": 0.4887984275817871, "step": 315850 }, { "epoch": 1.877537433647782, "grad_norm": 1.6151525974273682, "learning_rate": 8.645049820164033e-05, "loss": 0.5835864067077636, "step": 315860 }, { "epoch": 1.8775968757244503, "grad_norm": 1.5241955518722534, "learning_rate": 8.644449036083202e-05, "loss": 0.5567276477813721, "step": 315870 }, { "epoch": 1.8776563178011187, "grad_norm": 1.473742127418518, "learning_rate": 8.64384826327056e-05, "loss": 0.5446646690368653, "step": 315880 }, { "epoch": 1.8777157598777872, "grad_norm": 1.8293678760528564, "learning_rate": 8.643247501728981e-05, "loss": 0.5601072311401367, "step": 315890 }, { "epoch": 1.8777752019544556, "grad_norm": 1.5521578788757324, "learning_rate": 8.642646751461334e-05, "loss": 0.5841072082519532, "step": 315900 }, { "epoch": 1.877834644031124, "grad_norm": 1.8805761337280273, "learning_rate": 8.64204601247049e-05, "loss": 0.48229589462280276, "step": 315910 }, { "epoch": 1.8778940861077924, "grad_norm": 1.2760978937149048, "learning_rate": 8.641445284759336e-05, "loss": 0.5445420265197753, "step": 315920 }, { "epoch": 1.8779535281844608, "grad_norm": 1.4586482048034668, "learning_rate": 8.640844568330732e-05, "loss": 0.5475260734558105, "step": 315930 }, { "epoch": 1.878012970261129, "grad_norm": 1.529388189315796, "learning_rate": 8.640243863187554e-05, "loss": 0.5680477142333984, "step": 315940 }, { "epoch": 1.8780724123377974, "grad_norm": 1.3802919387817383, "learning_rate": 8.639643169332683e-05, "loss": 0.54891357421875, "step": 315950 }, { "epoch": 1.8781318544144658, "grad_norm": 1.3759249448776245, "learning_rate": 8.639042486768986e-05, "loss": 0.5237212181091309, "step": 315960 }, { "epoch": 1.8781912964911343, "grad_norm": 1.3749321699142456, "learning_rate": 8.638441815499334e-05, "loss": 0.5767273902893066, "step": 315970 }, { "epoch": 1.8782507385678024, "grad_norm": 1.4207509756088257, "learning_rate": 8.637841155526611e-05, "loss": 0.535219144821167, "step": 315980 }, { "epoch": 1.8783101806444709, "grad_norm": 1.1516424417495728, "learning_rate": 8.637240506853684e-05, "loss": 0.5330698013305664, "step": 315990 }, { "epoch": 1.8783696227211393, "grad_norm": 1.305195689201355, "learning_rate": 8.63663986948342e-05, "loss": 0.5868498325347901, "step": 316000 }, { "epoch": 1.8784290647978077, "grad_norm": 1.4830371141433716, "learning_rate": 8.636039243418703e-05, "loss": 0.5904563426971435, "step": 316010 }, { "epoch": 1.878488506874476, "grad_norm": 1.3013354539871216, "learning_rate": 8.635438628662402e-05, "loss": 0.5228829383850098, "step": 316020 }, { "epoch": 1.8785479489511445, "grad_norm": 1.1789665222167969, "learning_rate": 8.634838025217391e-05, "loss": 0.5819082260131836, "step": 316030 }, { "epoch": 1.878607391027813, "grad_norm": 1.170630693435669, "learning_rate": 8.634237433086538e-05, "loss": 0.5547295570373535, "step": 316040 }, { "epoch": 1.8786668331044813, "grad_norm": 1.548179030418396, "learning_rate": 8.633636852272722e-05, "loss": 0.5150232791900635, "step": 316050 }, { "epoch": 1.8787262751811498, "grad_norm": 1.1830170154571533, "learning_rate": 8.633036282778814e-05, "loss": 0.47393016815185546, "step": 316060 }, { "epoch": 1.8787857172578182, "grad_norm": 1.3499226570129395, "learning_rate": 8.632435724607686e-05, "loss": 0.5088804721832275, "step": 316070 }, { "epoch": 1.8788451593344866, "grad_norm": 1.329241394996643, "learning_rate": 8.631835177762211e-05, "loss": 0.5395800590515136, "step": 316080 }, { "epoch": 1.878904601411155, "grad_norm": 1.9149143695831299, "learning_rate": 8.631234642245265e-05, "loss": 0.5278215408325195, "step": 316090 }, { "epoch": 1.8789640434878234, "grad_norm": 1.1843456029891968, "learning_rate": 8.630634118059717e-05, "loss": 0.5544225692749023, "step": 316100 }, { "epoch": 1.8790234855644918, "grad_norm": 1.5008809566497803, "learning_rate": 8.630033605208443e-05, "loss": 0.5761123657226562, "step": 316110 }, { "epoch": 1.87908292764116, "grad_norm": 1.4907163381576538, "learning_rate": 8.629433103694311e-05, "loss": 0.5674920558929444, "step": 316120 }, { "epoch": 1.8791423697178284, "grad_norm": 1.276352047920227, "learning_rate": 8.628832613520197e-05, "loss": 0.49842400550842286, "step": 316130 }, { "epoch": 1.8792018117944969, "grad_norm": 1.5429725646972656, "learning_rate": 8.628232134688972e-05, "loss": 0.5348769187927246, "step": 316140 }, { "epoch": 1.8792612538711653, "grad_norm": 1.1437658071517944, "learning_rate": 8.627631667203511e-05, "loss": 0.5323994159698486, "step": 316150 }, { "epoch": 1.8793206959478337, "grad_norm": 1.635490894317627, "learning_rate": 8.627031211066685e-05, "loss": 0.5365440368652343, "step": 316160 }, { "epoch": 1.8793801380245019, "grad_norm": 1.4245667457580566, "learning_rate": 8.626430766281365e-05, "loss": 0.5660670280456543, "step": 316170 }, { "epoch": 1.8794395801011703, "grad_norm": 1.4359279870986938, "learning_rate": 8.625830332850427e-05, "loss": 0.5566066265106201, "step": 316180 }, { "epoch": 1.8794990221778387, "grad_norm": 1.6569056510925293, "learning_rate": 8.625229910776738e-05, "loss": 0.5793575763702392, "step": 316190 }, { "epoch": 1.8795584642545071, "grad_norm": 1.271155595779419, "learning_rate": 8.624629500063172e-05, "loss": 0.49445037841796874, "step": 316200 }, { "epoch": 1.8796179063311755, "grad_norm": 1.40348482131958, "learning_rate": 8.624029100712604e-05, "loss": 0.5881426334381104, "step": 316210 }, { "epoch": 1.879677348407844, "grad_norm": 1.582195520401001, "learning_rate": 8.623428712727905e-05, "loss": 0.5410961151123047, "step": 316220 }, { "epoch": 1.8797367904845124, "grad_norm": 0.9417012333869934, "learning_rate": 8.622828336111946e-05, "loss": 0.551723861694336, "step": 316230 }, { "epoch": 1.8797962325611808, "grad_norm": 1.8942945003509521, "learning_rate": 8.622227970867598e-05, "loss": 0.5703552722930908, "step": 316240 }, { "epoch": 1.8798556746378492, "grad_norm": 1.206883192062378, "learning_rate": 8.621627616997738e-05, "loss": 0.5436897277832031, "step": 316250 }, { "epoch": 1.8799151167145176, "grad_norm": 1.3146631717681885, "learning_rate": 8.621027274505234e-05, "loss": 0.5691287994384766, "step": 316260 }, { "epoch": 1.879974558791186, "grad_norm": 1.4427815675735474, "learning_rate": 8.620426943392952e-05, "loss": 0.5668505668640137, "step": 316270 }, { "epoch": 1.8800340008678544, "grad_norm": 1.5912933349609375, "learning_rate": 8.619826623663773e-05, "loss": 0.5110691070556641, "step": 316280 }, { "epoch": 1.8800934429445229, "grad_norm": 1.3591941595077515, "learning_rate": 8.61922631532057e-05, "loss": 0.5713423728942871, "step": 316290 }, { "epoch": 1.880152885021191, "grad_norm": 1.3128981590270996, "learning_rate": 8.618626018366203e-05, "loss": 0.5313440799713135, "step": 316300 }, { "epoch": 1.8802123270978595, "grad_norm": 1.2022911310195923, "learning_rate": 8.618025732803557e-05, "loss": 0.5206851005554199, "step": 316310 }, { "epoch": 1.8802717691745279, "grad_norm": 1.2523044347763062, "learning_rate": 8.617425458635495e-05, "loss": 0.5633570671081543, "step": 316320 }, { "epoch": 1.8803312112511963, "grad_norm": 1.380601406097412, "learning_rate": 8.616825195864888e-05, "loss": 0.5662351131439209, "step": 316330 }, { "epoch": 1.8803906533278647, "grad_norm": 1.3680459260940552, "learning_rate": 8.616224944494614e-05, "loss": 0.4949795722961426, "step": 316340 }, { "epoch": 1.880450095404533, "grad_norm": 1.7126500606536865, "learning_rate": 8.615624704527542e-05, "loss": 0.5498377799987793, "step": 316350 }, { "epoch": 1.8805095374812013, "grad_norm": 1.207709550857544, "learning_rate": 8.615024475966538e-05, "loss": 0.547659969329834, "step": 316360 }, { "epoch": 1.8805689795578697, "grad_norm": 1.4972258806228638, "learning_rate": 8.61442425881448e-05, "loss": 0.5184072017669678, "step": 316370 }, { "epoch": 1.8806284216345381, "grad_norm": 1.7718337774276733, "learning_rate": 8.613824053074237e-05, "loss": 0.5854991436004638, "step": 316380 }, { "epoch": 1.8806878637112066, "grad_norm": 1.5996434688568115, "learning_rate": 8.613223858748682e-05, "loss": 0.5302528858184814, "step": 316390 }, { "epoch": 1.880747305787875, "grad_norm": 1.4811735153198242, "learning_rate": 8.612623675840679e-05, "loss": 0.5773131370544433, "step": 316400 }, { "epoch": 1.8808067478645434, "grad_norm": 1.4918886423110962, "learning_rate": 8.612023504353109e-05, "loss": 0.5696567535400391, "step": 316410 }, { "epoch": 1.8808661899412118, "grad_norm": 1.1285964250564575, "learning_rate": 8.611423344288836e-05, "loss": 0.5575544357299804, "step": 316420 }, { "epoch": 1.8809256320178802, "grad_norm": 1.7605746984481812, "learning_rate": 8.610823195650727e-05, "loss": 0.6130866050720215, "step": 316430 }, { "epoch": 1.8809850740945486, "grad_norm": 1.356455683708191, "learning_rate": 8.610223058441668e-05, "loss": 0.5430433273315429, "step": 316440 }, { "epoch": 1.881044516171217, "grad_norm": 1.639417052268982, "learning_rate": 8.609622932664521e-05, "loss": 0.5487731456756592, "step": 316450 }, { "epoch": 1.8811039582478855, "grad_norm": 1.148615837097168, "learning_rate": 8.609022818322147e-05, "loss": 0.5348445415496826, "step": 316460 }, { "epoch": 1.8811634003245539, "grad_norm": 1.2979573011398315, "learning_rate": 8.608422715417437e-05, "loss": 0.5766132354736329, "step": 316470 }, { "epoch": 1.8812228424012223, "grad_norm": 1.675032138824463, "learning_rate": 8.607822623953248e-05, "loss": 0.5567255973815918, "step": 316480 }, { "epoch": 1.8812822844778905, "grad_norm": 1.2760404348373413, "learning_rate": 8.607222543932449e-05, "loss": 0.5220485687255859, "step": 316490 }, { "epoch": 1.881341726554559, "grad_norm": 1.3978221416473389, "learning_rate": 8.606622475357922e-05, "loss": 0.5622218132019043, "step": 316500 }, { "epoch": 1.8814011686312273, "grad_norm": 1.273987889289856, "learning_rate": 8.606022418232529e-05, "loss": 0.6148992061614991, "step": 316510 }, { "epoch": 1.8814606107078957, "grad_norm": 1.2193987369537354, "learning_rate": 8.605422372559142e-05, "loss": 0.4973857879638672, "step": 316520 }, { "epoch": 1.8815200527845641, "grad_norm": 1.3482210636138916, "learning_rate": 8.60482233834063e-05, "loss": 0.5518269538879395, "step": 316530 }, { "epoch": 1.8815794948612323, "grad_norm": 1.5263280868530273, "learning_rate": 8.604222315579866e-05, "loss": 0.583499813079834, "step": 316540 }, { "epoch": 1.8816389369379007, "grad_norm": 1.3917452096939087, "learning_rate": 8.603622304279722e-05, "loss": 0.5813149452209473, "step": 316550 }, { "epoch": 1.8816983790145692, "grad_norm": 1.3312276601791382, "learning_rate": 8.603022304443062e-05, "loss": 0.5445400238037109, "step": 316560 }, { "epoch": 1.8817578210912376, "grad_norm": 1.2471970319747925, "learning_rate": 8.602422316072762e-05, "loss": 0.5115859031677246, "step": 316570 }, { "epoch": 1.881817263167906, "grad_norm": 1.29099702835083, "learning_rate": 8.601822339171692e-05, "loss": 0.562895679473877, "step": 316580 }, { "epoch": 1.8818767052445744, "grad_norm": 1.249747395515442, "learning_rate": 8.601222373742716e-05, "loss": 0.5501582145690918, "step": 316590 }, { "epoch": 1.8819361473212428, "grad_norm": 1.4481842517852783, "learning_rate": 8.60062241978871e-05, "loss": 0.5799779891967773, "step": 316600 }, { "epoch": 1.8819955893979112, "grad_norm": 1.3070188760757446, "learning_rate": 8.600022477312544e-05, "loss": 0.5189628601074219, "step": 316610 }, { "epoch": 1.8820550314745796, "grad_norm": 1.125784158706665, "learning_rate": 8.599422546317084e-05, "loss": 0.48534107208251953, "step": 316620 }, { "epoch": 1.882114473551248, "grad_norm": 1.2169221639633179, "learning_rate": 8.598822626805203e-05, "loss": 0.5135358810424805, "step": 316630 }, { "epoch": 1.8821739156279165, "grad_norm": 1.3699698448181152, "learning_rate": 8.598222718779769e-05, "loss": 0.5641853332519531, "step": 316640 }, { "epoch": 1.8822333577045849, "grad_norm": 1.5112364292144775, "learning_rate": 8.597622822243653e-05, "loss": 0.5466158390045166, "step": 316650 }, { "epoch": 1.8822927997812533, "grad_norm": 1.3814799785614014, "learning_rate": 8.597022937199723e-05, "loss": 0.5805587291717529, "step": 316660 }, { "epoch": 1.8823522418579215, "grad_norm": 1.3462578058242798, "learning_rate": 8.596423063650854e-05, "loss": 0.5555523872375489, "step": 316670 }, { "epoch": 1.88241168393459, "grad_norm": 1.1478071212768555, "learning_rate": 8.595823201599908e-05, "loss": 0.5261665344238281, "step": 316680 }, { "epoch": 1.8824711260112583, "grad_norm": 1.3008191585540771, "learning_rate": 8.595223351049759e-05, "loss": 0.5379035472869873, "step": 316690 }, { "epoch": 1.8825305680879267, "grad_norm": 1.0790352821350098, "learning_rate": 8.594623512003277e-05, "loss": 0.5315863132476807, "step": 316700 }, { "epoch": 1.8825900101645952, "grad_norm": 1.2752952575683594, "learning_rate": 8.594023684463328e-05, "loss": 0.5438201904296875, "step": 316710 }, { "epoch": 1.8826494522412633, "grad_norm": 1.3824384212493896, "learning_rate": 8.593423868432782e-05, "loss": 0.5316004753112793, "step": 316720 }, { "epoch": 1.8827088943179318, "grad_norm": 1.5386252403259277, "learning_rate": 8.592824063914513e-05, "loss": 0.6275249004364014, "step": 316730 }, { "epoch": 1.8827683363946002, "grad_norm": 1.540482521057129, "learning_rate": 8.592224270911387e-05, "loss": 0.5141544818878174, "step": 316740 }, { "epoch": 1.8828277784712686, "grad_norm": 1.16660737991333, "learning_rate": 8.591624489426273e-05, "loss": 0.5688154220581054, "step": 316750 }, { "epoch": 1.882887220547937, "grad_norm": 1.4553202390670776, "learning_rate": 8.591024719462037e-05, "loss": 0.5786715984344483, "step": 316760 }, { "epoch": 1.8829466626246054, "grad_norm": 1.3973020315170288, "learning_rate": 8.590424961021555e-05, "loss": 0.5108483314514161, "step": 316770 }, { "epoch": 1.8830061047012738, "grad_norm": 1.8484373092651367, "learning_rate": 8.589825214107692e-05, "loss": 0.4976794242858887, "step": 316780 }, { "epoch": 1.8830655467779422, "grad_norm": 1.1017788648605347, "learning_rate": 8.589225478723315e-05, "loss": 0.5714217185974121, "step": 316790 }, { "epoch": 1.8831249888546107, "grad_norm": 1.176771640777588, "learning_rate": 8.588625754871299e-05, "loss": 0.5617727279663086, "step": 316800 }, { "epoch": 1.883184430931279, "grad_norm": 1.5976910591125488, "learning_rate": 8.588026042554509e-05, "loss": 0.5971243858337403, "step": 316810 }, { "epoch": 1.8832438730079475, "grad_norm": 1.627112865447998, "learning_rate": 8.58742634177581e-05, "loss": 0.5958426475524903, "step": 316820 }, { "epoch": 1.883303315084616, "grad_norm": 1.576909065246582, "learning_rate": 8.58682665253808e-05, "loss": 0.5563000679016114, "step": 316830 }, { "epoch": 1.8833627571612843, "grad_norm": 1.2057262659072876, "learning_rate": 8.586226974844183e-05, "loss": 0.5244578838348388, "step": 316840 }, { "epoch": 1.8834221992379527, "grad_norm": 1.2252634763717651, "learning_rate": 8.58562730869698e-05, "loss": 0.5755208969116211, "step": 316850 }, { "epoch": 1.883481641314621, "grad_norm": 1.933998703956604, "learning_rate": 8.585027654099354e-05, "loss": 0.5448294162750245, "step": 316860 }, { "epoch": 1.8835410833912893, "grad_norm": 1.413539171218872, "learning_rate": 8.584428011054167e-05, "loss": 0.5581310749053955, "step": 316870 }, { "epoch": 1.8836005254679578, "grad_norm": 1.2116166353225708, "learning_rate": 8.583828379564283e-05, "loss": 0.5201092720031738, "step": 316880 }, { "epoch": 1.8836599675446262, "grad_norm": 1.70745050907135, "learning_rate": 8.583228759632573e-05, "loss": 0.5200863838195801, "step": 316890 }, { "epoch": 1.8837194096212946, "grad_norm": 1.466510534286499, "learning_rate": 8.582629151261911e-05, "loss": 0.5759437561035157, "step": 316900 }, { "epoch": 1.8837788516979628, "grad_norm": 1.2576603889465332, "learning_rate": 8.582029554455162e-05, "loss": 0.5283509254455566, "step": 316910 }, { "epoch": 1.8838382937746312, "grad_norm": 1.6340620517730713, "learning_rate": 8.581429969215186e-05, "loss": 0.5340259552001954, "step": 316920 }, { "epoch": 1.8838977358512996, "grad_norm": 1.353834867477417, "learning_rate": 8.580830395544868e-05, "loss": 0.5884917736053467, "step": 316930 }, { "epoch": 1.883957177927968, "grad_norm": 1.5491396188735962, "learning_rate": 8.580230833447063e-05, "loss": 0.5270730018615722, "step": 316940 }, { "epoch": 1.8840166200046364, "grad_norm": 1.367527723312378, "learning_rate": 8.579631282924638e-05, "loss": 0.507025146484375, "step": 316950 }, { "epoch": 1.8840760620813048, "grad_norm": 1.2379268407821655, "learning_rate": 8.579031743980475e-05, "loss": 0.5076917171478271, "step": 316960 }, { "epoch": 1.8841355041579733, "grad_norm": 1.4363625049591064, "learning_rate": 8.578432216617426e-05, "loss": 0.5306944847106934, "step": 316970 }, { "epoch": 1.8841949462346417, "grad_norm": 1.7190390825271606, "learning_rate": 8.577832700838371e-05, "loss": 0.5989775657653809, "step": 316980 }, { "epoch": 1.88425438831131, "grad_norm": 1.5813302993774414, "learning_rate": 8.577233196646169e-05, "loss": 0.5541131973266602, "step": 316990 }, { "epoch": 1.8843138303879785, "grad_norm": 1.6396757364273071, "learning_rate": 8.576633704043693e-05, "loss": 0.5773353576660156, "step": 317000 }, { "epoch": 1.884373272464647, "grad_norm": 1.2905375957489014, "learning_rate": 8.576034223033808e-05, "loss": 0.48250432014465333, "step": 317010 }, { "epoch": 1.8844327145413153, "grad_norm": 1.3960413932800293, "learning_rate": 8.575434753619383e-05, "loss": 0.6248457908630372, "step": 317020 }, { "epoch": 1.8844921566179837, "grad_norm": 1.181795597076416, "learning_rate": 8.574835295803287e-05, "loss": 0.5440062522888184, "step": 317030 }, { "epoch": 1.884551598694652, "grad_norm": 1.521367073059082, "learning_rate": 8.574235849588388e-05, "loss": 0.5577811241149903, "step": 317040 }, { "epoch": 1.8846110407713204, "grad_norm": 1.677643895149231, "learning_rate": 8.573636414977549e-05, "loss": 0.5898509979248047, "step": 317050 }, { "epoch": 1.8846704828479888, "grad_norm": 1.2450217008590698, "learning_rate": 8.573036991973642e-05, "loss": 0.5237948417663574, "step": 317060 }, { "epoch": 1.8847299249246572, "grad_norm": 1.0682650804519653, "learning_rate": 8.572437580579533e-05, "loss": 0.5021632194519043, "step": 317070 }, { "epoch": 1.8847893670013256, "grad_norm": 1.46441650390625, "learning_rate": 8.571838180798088e-05, "loss": 0.5111308574676514, "step": 317080 }, { "epoch": 1.8848488090779938, "grad_norm": 1.2589702606201172, "learning_rate": 8.571238792632177e-05, "loss": 0.5631453990936279, "step": 317090 }, { "epoch": 1.8849082511546622, "grad_norm": 1.18987238407135, "learning_rate": 8.570639416084664e-05, "loss": 0.5517137527465821, "step": 317100 }, { "epoch": 1.8849676932313306, "grad_norm": 1.471928596496582, "learning_rate": 8.570040051158421e-05, "loss": 0.5238118648529053, "step": 317110 }, { "epoch": 1.885027135307999, "grad_norm": 1.4415653944015503, "learning_rate": 8.56944069785631e-05, "loss": 0.5167623996734619, "step": 317120 }, { "epoch": 1.8850865773846675, "grad_norm": 1.3469053506851196, "learning_rate": 8.568841356181203e-05, "loss": 0.5775859832763672, "step": 317130 }, { "epoch": 1.8851460194613359, "grad_norm": 1.3150919675827026, "learning_rate": 8.568242026135962e-05, "loss": 0.5578414916992187, "step": 317140 }, { "epoch": 1.8852054615380043, "grad_norm": 1.4080047607421875, "learning_rate": 8.567642707723455e-05, "loss": 0.6065337181091308, "step": 317150 }, { "epoch": 1.8852649036146727, "grad_norm": 1.4772300720214844, "learning_rate": 8.567043400946553e-05, "loss": 0.5718331336975098, "step": 317160 }, { "epoch": 1.885324345691341, "grad_norm": 1.3561326265335083, "learning_rate": 8.56644410580812e-05, "loss": 0.5446505069732666, "step": 317170 }, { "epoch": 1.8853837877680095, "grad_norm": 1.4511040449142456, "learning_rate": 8.565844822311022e-05, "loss": 0.5573012351989746, "step": 317180 }, { "epoch": 1.885443229844678, "grad_norm": 1.3189886808395386, "learning_rate": 8.565245550458128e-05, "loss": 0.5282127380371093, "step": 317190 }, { "epoch": 1.8855026719213464, "grad_norm": 1.5744508504867554, "learning_rate": 8.564646290252305e-05, "loss": 0.5133690357208252, "step": 317200 }, { "epoch": 1.8855621139980148, "grad_norm": 1.2261260747909546, "learning_rate": 8.564047041696413e-05, "loss": 0.5166699409484863, "step": 317210 }, { "epoch": 1.8856215560746832, "grad_norm": 1.157414436340332, "learning_rate": 8.56344780479333e-05, "loss": 0.5368380546569824, "step": 317220 }, { "epoch": 1.8856809981513514, "grad_norm": 1.3589776754379272, "learning_rate": 8.562848579545912e-05, "loss": 0.5201751708984375, "step": 317230 }, { "epoch": 1.8857404402280198, "grad_norm": 1.145572543144226, "learning_rate": 8.562249365957034e-05, "loss": 0.5597896099090576, "step": 317240 }, { "epoch": 1.8857998823046882, "grad_norm": 1.2233672142028809, "learning_rate": 8.561650164029555e-05, "loss": 0.5809768199920654, "step": 317250 }, { "epoch": 1.8858593243813566, "grad_norm": 1.5033059120178223, "learning_rate": 8.561050973766344e-05, "loss": 0.5088714599609375, "step": 317260 }, { "epoch": 1.885918766458025, "grad_norm": 1.2272922992706299, "learning_rate": 8.560451795170273e-05, "loss": 0.540184497833252, "step": 317270 }, { "epoch": 1.8859782085346932, "grad_norm": 1.4980480670928955, "learning_rate": 8.559852628244199e-05, "loss": 0.538941478729248, "step": 317280 }, { "epoch": 1.8860376506113616, "grad_norm": 1.3559201955795288, "learning_rate": 8.559253472990993e-05, "loss": 0.548641300201416, "step": 317290 }, { "epoch": 1.88609709268803, "grad_norm": 1.610990285873413, "learning_rate": 8.558654329413523e-05, "loss": 0.5483053207397461, "step": 317300 }, { "epoch": 1.8861565347646985, "grad_norm": 1.5913561582565308, "learning_rate": 8.558055197514649e-05, "loss": 0.5030533313751221, "step": 317310 }, { "epoch": 1.8862159768413669, "grad_norm": 1.2487872838974, "learning_rate": 8.557456077297245e-05, "loss": 0.5674260139465332, "step": 317320 }, { "epoch": 1.8862754189180353, "grad_norm": 1.1481367349624634, "learning_rate": 8.556856968764174e-05, "loss": 0.5190173149108886, "step": 317330 }, { "epoch": 1.8863348609947037, "grad_norm": 1.3481804132461548, "learning_rate": 8.556257871918295e-05, "loss": 0.5223189353942871, "step": 317340 }, { "epoch": 1.8863943030713721, "grad_norm": 1.53547203540802, "learning_rate": 8.555658786762484e-05, "loss": 0.5898170948028565, "step": 317350 }, { "epoch": 1.8864537451480405, "grad_norm": 1.3919392824172974, "learning_rate": 8.5550597132996e-05, "loss": 0.5527139663696289, "step": 317360 }, { "epoch": 1.886513187224709, "grad_norm": 1.9899483919143677, "learning_rate": 8.554460651532517e-05, "loss": 0.5371253967285157, "step": 317370 }, { "epoch": 1.8865726293013774, "grad_norm": 1.4903243780136108, "learning_rate": 8.553861601464086e-05, "loss": 0.5594508171081543, "step": 317380 }, { "epoch": 1.8866320713780458, "grad_norm": 1.4900513887405396, "learning_rate": 8.553262563097187e-05, "loss": 0.5187601089477539, "step": 317390 }, { "epoch": 1.8866915134547142, "grad_norm": 1.4089950323104858, "learning_rate": 8.552663536434682e-05, "loss": 0.4901817798614502, "step": 317400 }, { "epoch": 1.8867509555313824, "grad_norm": 1.060760498046875, "learning_rate": 8.55206452147943e-05, "loss": 0.5297492980957031, "step": 317410 }, { "epoch": 1.8868103976080508, "grad_norm": 1.274743914604187, "learning_rate": 8.551465518234305e-05, "loss": 0.5534462928771973, "step": 317420 }, { "epoch": 1.8868698396847192, "grad_norm": 1.147180199623108, "learning_rate": 8.550866526702171e-05, "loss": 0.5156051635742187, "step": 317430 }, { "epoch": 1.8869292817613876, "grad_norm": 1.3797246217727661, "learning_rate": 8.550267546885883e-05, "loss": 0.6312739372253418, "step": 317440 }, { "epoch": 1.886988723838056, "grad_norm": 1.1059895753860474, "learning_rate": 8.549668578788321e-05, "loss": 0.5064147472381592, "step": 317450 }, { "epoch": 1.8870481659147242, "grad_norm": 1.9003360271453857, "learning_rate": 8.549069622412342e-05, "loss": 0.5040830612182617, "step": 317460 }, { "epoch": 1.8871076079913927, "grad_norm": 1.5035426616668701, "learning_rate": 8.548470677760816e-05, "loss": 0.6283920764923095, "step": 317470 }, { "epoch": 1.887167050068061, "grad_norm": 1.6547651290893555, "learning_rate": 8.5478717448366e-05, "loss": 0.5437701225280762, "step": 317480 }, { "epoch": 1.8872264921447295, "grad_norm": 1.6231764554977417, "learning_rate": 8.547272823642567e-05, "loss": 0.5817506790161133, "step": 317490 }, { "epoch": 1.887285934221398, "grad_norm": 1.518148422241211, "learning_rate": 8.546673914181577e-05, "loss": 0.533881425857544, "step": 317500 }, { "epoch": 1.8873453762980663, "grad_norm": 1.6743576526641846, "learning_rate": 8.546075016456499e-05, "loss": 0.5991703033447265, "step": 317510 }, { "epoch": 1.8874048183747347, "grad_norm": 1.2005549669265747, "learning_rate": 8.545476130470196e-05, "loss": 0.5343425750732422, "step": 317520 }, { "epoch": 1.8874642604514031, "grad_norm": 1.483888864517212, "learning_rate": 8.544877256225534e-05, "loss": 0.5261973381042481, "step": 317530 }, { "epoch": 1.8875237025280716, "grad_norm": 1.3691582679748535, "learning_rate": 8.544278393725376e-05, "loss": 0.5440481185913086, "step": 317540 }, { "epoch": 1.88758314460474, "grad_norm": 1.074414849281311, "learning_rate": 8.543679542972587e-05, "loss": 0.5314475059509277, "step": 317550 }, { "epoch": 1.8876425866814084, "grad_norm": 1.4713678359985352, "learning_rate": 8.543080703970033e-05, "loss": 0.4998342514038086, "step": 317560 }, { "epoch": 1.8877020287580768, "grad_norm": 1.3954287767410278, "learning_rate": 8.542481876720576e-05, "loss": 0.5163214683532715, "step": 317570 }, { "epoch": 1.8877614708347452, "grad_norm": 1.5849037170410156, "learning_rate": 8.541883061227085e-05, "loss": 0.5679746627807617, "step": 317580 }, { "epoch": 1.8878209129114136, "grad_norm": 1.3652279376983643, "learning_rate": 8.541284257492421e-05, "loss": 0.5744589805603028, "step": 317590 }, { "epoch": 1.8878803549880818, "grad_norm": 1.466874361038208, "learning_rate": 8.540685465519452e-05, "loss": 0.5690402030944824, "step": 317600 }, { "epoch": 1.8879397970647502, "grad_norm": 1.236380934715271, "learning_rate": 8.540086685311037e-05, "loss": 0.5072859764099121, "step": 317610 }, { "epoch": 1.8879992391414187, "grad_norm": 1.1982204914093018, "learning_rate": 8.539487916870044e-05, "loss": 0.493181848526001, "step": 317620 }, { "epoch": 1.888058681218087, "grad_norm": 1.1963989734649658, "learning_rate": 8.538889160199337e-05, "loss": 0.5080156803131104, "step": 317630 }, { "epoch": 1.8881181232947555, "grad_norm": 1.6208027601242065, "learning_rate": 8.53829041530178e-05, "loss": 0.49655799865722655, "step": 317640 }, { "epoch": 1.8881775653714237, "grad_norm": 1.3909480571746826, "learning_rate": 8.537691682180237e-05, "loss": 0.49846467971801756, "step": 317650 }, { "epoch": 1.888237007448092, "grad_norm": 1.0381473302841187, "learning_rate": 8.537092960837574e-05, "loss": 0.4863129615783691, "step": 317660 }, { "epoch": 1.8882964495247605, "grad_norm": 1.1261756420135498, "learning_rate": 8.53649425127665e-05, "loss": 0.5284379005432129, "step": 317670 }, { "epoch": 1.888355891601429, "grad_norm": 1.3165102005004883, "learning_rate": 8.535895553500335e-05, "loss": 0.5321331024169922, "step": 317680 }, { "epoch": 1.8884153336780973, "grad_norm": 0.8657124638557434, "learning_rate": 8.535296867511491e-05, "loss": 0.5285831928253174, "step": 317690 }, { "epoch": 1.8884747757547657, "grad_norm": 1.5067923069000244, "learning_rate": 8.53469819331298e-05, "loss": 0.5390776634216309, "step": 317700 }, { "epoch": 1.8885342178314342, "grad_norm": 1.3179253339767456, "learning_rate": 8.534099530907667e-05, "loss": 0.5464447021484375, "step": 317710 }, { "epoch": 1.8885936599081026, "grad_norm": 1.273453950881958, "learning_rate": 8.533500880298418e-05, "loss": 0.49526729583740237, "step": 317720 }, { "epoch": 1.888653101984771, "grad_norm": 1.3759245872497559, "learning_rate": 8.532902241488093e-05, "loss": 0.5339578628540039, "step": 317730 }, { "epoch": 1.8887125440614394, "grad_norm": 1.3352912664413452, "learning_rate": 8.532303614479555e-05, "loss": 0.5568994522094727, "step": 317740 }, { "epoch": 1.8887719861381078, "grad_norm": 1.0999268293380737, "learning_rate": 8.531704999275674e-05, "loss": 0.506925106048584, "step": 317750 }, { "epoch": 1.8888314282147762, "grad_norm": 1.5170615911483765, "learning_rate": 8.531106395879307e-05, "loss": 0.5527415752410889, "step": 317760 }, { "epoch": 1.8888908702914446, "grad_norm": 1.400963306427002, "learning_rate": 8.530507804293322e-05, "loss": 0.5740459442138672, "step": 317770 }, { "epoch": 1.8889503123681128, "grad_norm": 1.5137975215911865, "learning_rate": 8.529909224520577e-05, "loss": 0.5426104545593262, "step": 317780 }, { "epoch": 1.8890097544447813, "grad_norm": 1.6872905492782593, "learning_rate": 8.529310656563945e-05, "loss": 0.569735336303711, "step": 317790 }, { "epoch": 1.8890691965214497, "grad_norm": 1.3026058673858643, "learning_rate": 8.528712100426279e-05, "loss": 0.48856453895568847, "step": 317800 }, { "epoch": 1.889128638598118, "grad_norm": 1.6862586736679077, "learning_rate": 8.528113556110448e-05, "loss": 0.5078160762786865, "step": 317810 }, { "epoch": 1.8891880806747865, "grad_norm": 1.604258418083191, "learning_rate": 8.527515023619314e-05, "loss": 0.5455194473266601, "step": 317820 }, { "epoch": 1.8892475227514547, "grad_norm": 1.5292937755584717, "learning_rate": 8.526916502955742e-05, "loss": 0.5298614501953125, "step": 317830 }, { "epoch": 1.889306964828123, "grad_norm": 1.334567904472351, "learning_rate": 8.526317994122587e-05, "loss": 0.5066003799438477, "step": 317840 }, { "epoch": 1.8893664069047915, "grad_norm": 1.6726278066635132, "learning_rate": 8.525719497122723e-05, "loss": 0.5513837814331055, "step": 317850 }, { "epoch": 1.88942584898146, "grad_norm": 2.072324514389038, "learning_rate": 8.525121011959012e-05, "loss": 0.5257404327392579, "step": 317860 }, { "epoch": 1.8894852910581283, "grad_norm": 1.1429765224456787, "learning_rate": 8.524522538634308e-05, "loss": 0.5780067443847656, "step": 317870 }, { "epoch": 1.8895447331347968, "grad_norm": 1.6635167598724365, "learning_rate": 8.523924077151479e-05, "loss": 0.4971430778503418, "step": 317880 }, { "epoch": 1.8896041752114652, "grad_norm": 1.6208561658859253, "learning_rate": 8.523325627513392e-05, "loss": 0.5381750106811524, "step": 317890 }, { "epoch": 1.8896636172881336, "grad_norm": 1.3336330652236938, "learning_rate": 8.522727189722899e-05, "loss": 0.5630799770355225, "step": 317900 }, { "epoch": 1.889723059364802, "grad_norm": 1.1339231729507446, "learning_rate": 8.522128763782875e-05, "loss": 0.5368907928466797, "step": 317910 }, { "epoch": 1.8897825014414704, "grad_norm": 1.2953306436538696, "learning_rate": 8.521530349696179e-05, "loss": 0.5435119152069092, "step": 317920 }, { "epoch": 1.8898419435181388, "grad_norm": 1.5963042974472046, "learning_rate": 8.520931947465664e-05, "loss": 0.5136905670166015, "step": 317930 }, { "epoch": 1.8899013855948072, "grad_norm": 1.7607957124710083, "learning_rate": 8.520333557094206e-05, "loss": 0.58251953125, "step": 317940 }, { "epoch": 1.8899608276714757, "grad_norm": 1.4069745540618896, "learning_rate": 8.519735178584665e-05, "loss": 0.550900936126709, "step": 317950 }, { "epoch": 1.890020269748144, "grad_norm": 1.5808748006820679, "learning_rate": 8.519136811939897e-05, "loss": 0.5566519737243653, "step": 317960 }, { "epoch": 1.8900797118248123, "grad_norm": 1.273362398147583, "learning_rate": 8.518538457162764e-05, "loss": 0.5338597297668457, "step": 317970 }, { "epoch": 1.8901391539014807, "grad_norm": 1.2071458101272583, "learning_rate": 8.517940114256138e-05, "loss": 0.5652604579925538, "step": 317980 }, { "epoch": 1.890198595978149, "grad_norm": 1.178940773010254, "learning_rate": 8.517341783222872e-05, "loss": 0.5000306129455566, "step": 317990 }, { "epoch": 1.8902580380548175, "grad_norm": 1.504908800125122, "learning_rate": 8.516743464065831e-05, "loss": 0.5275316715240479, "step": 318000 }, { "epoch": 1.890317480131486, "grad_norm": 1.72868013381958, "learning_rate": 8.51614515678788e-05, "loss": 0.5158966541290283, "step": 318010 }, { "epoch": 1.8903769222081541, "grad_norm": 1.2546460628509521, "learning_rate": 8.515546861391878e-05, "loss": 0.5400253295898437, "step": 318020 }, { "epoch": 1.8904363642848225, "grad_norm": 1.3311060667037964, "learning_rate": 8.514948577880684e-05, "loss": 0.47103471755981446, "step": 318030 }, { "epoch": 1.890495806361491, "grad_norm": 1.3914564847946167, "learning_rate": 8.514350306257171e-05, "loss": 0.5829883098602295, "step": 318040 }, { "epoch": 1.8905552484381594, "grad_norm": 1.4532926082611084, "learning_rate": 8.51375204652419e-05, "loss": 0.5776516914367675, "step": 318050 }, { "epoch": 1.8906146905148278, "grad_norm": 1.8247016668319702, "learning_rate": 8.513153798684604e-05, "loss": 0.5286928176879883, "step": 318060 }, { "epoch": 1.8906741325914962, "grad_norm": 1.369027853012085, "learning_rate": 8.512555562741282e-05, "loss": 0.5264499664306641, "step": 318070 }, { "epoch": 1.8907335746681646, "grad_norm": 0.9948063492774963, "learning_rate": 8.511957338697081e-05, "loss": 0.533457088470459, "step": 318080 }, { "epoch": 1.890793016744833, "grad_norm": 1.631904125213623, "learning_rate": 8.51135912655486e-05, "loss": 0.5268666267395019, "step": 318090 }, { "epoch": 1.8908524588215014, "grad_norm": 1.5781265497207642, "learning_rate": 8.510760926317487e-05, "loss": 0.5636012554168701, "step": 318100 }, { "epoch": 1.8909119008981699, "grad_norm": 1.611411690711975, "learning_rate": 8.510162737987819e-05, "loss": 0.5757633209228515, "step": 318110 }, { "epoch": 1.8909713429748383, "grad_norm": 1.427550196647644, "learning_rate": 8.50956456156872e-05, "loss": 0.5367965698242188, "step": 318120 }, { "epoch": 1.8910307850515067, "grad_norm": 1.270081639289856, "learning_rate": 8.508966397063045e-05, "loss": 0.5156658172607422, "step": 318130 }, { "epoch": 1.891090227128175, "grad_norm": 1.2979140281677246, "learning_rate": 8.508368244473665e-05, "loss": 0.49022645950317384, "step": 318140 }, { "epoch": 1.8911496692048433, "grad_norm": 1.561704158782959, "learning_rate": 8.507770103803438e-05, "loss": 0.5309593677520752, "step": 318150 }, { "epoch": 1.8912091112815117, "grad_norm": 1.4480531215667725, "learning_rate": 8.507171975055222e-05, "loss": 0.5060180187225342, "step": 318160 }, { "epoch": 1.8912685533581801, "grad_norm": 1.6075786352157593, "learning_rate": 8.506573858231881e-05, "loss": 0.5623337745666503, "step": 318170 }, { "epoch": 1.8913279954348485, "grad_norm": 1.798566222190857, "learning_rate": 8.505975753336277e-05, "loss": 0.5954421997070313, "step": 318180 }, { "epoch": 1.891387437511517, "grad_norm": 1.458784818649292, "learning_rate": 8.505377660371268e-05, "loss": 0.5765525817871093, "step": 318190 }, { "epoch": 1.8914468795881851, "grad_norm": 1.7706483602523804, "learning_rate": 8.504779579339719e-05, "loss": 0.5368321418762207, "step": 318200 }, { "epoch": 1.8915063216648536, "grad_norm": 1.752560019493103, "learning_rate": 8.504181510244489e-05, "loss": 0.5593662738800049, "step": 318210 }, { "epoch": 1.891565763741522, "grad_norm": 1.266588807106018, "learning_rate": 8.503583453088437e-05, "loss": 0.5629351139068604, "step": 318220 }, { "epoch": 1.8916252058181904, "grad_norm": 1.402281403541565, "learning_rate": 8.502985407874427e-05, "loss": 0.5551430702209472, "step": 318230 }, { "epoch": 1.8916846478948588, "grad_norm": 1.3651829957962036, "learning_rate": 8.50238737460532e-05, "loss": 0.533130407333374, "step": 318240 }, { "epoch": 1.8917440899715272, "grad_norm": 1.1147397756576538, "learning_rate": 8.501789353283975e-05, "loss": 0.5781402111053466, "step": 318250 }, { "epoch": 1.8918035320481956, "grad_norm": 1.2524369955062866, "learning_rate": 8.501191343913251e-05, "loss": 0.5473214149475097, "step": 318260 }, { "epoch": 1.891862974124864, "grad_norm": 1.6574136018753052, "learning_rate": 8.500593346496013e-05, "loss": 0.5506596565246582, "step": 318270 }, { "epoch": 1.8919224162015325, "grad_norm": 1.4039270877838135, "learning_rate": 8.49999536103512e-05, "loss": 0.5215582847595215, "step": 318280 }, { "epoch": 1.8919818582782009, "grad_norm": 1.545254111289978, "learning_rate": 8.49939738753343e-05, "loss": 0.5229334831237793, "step": 318290 }, { "epoch": 1.8920413003548693, "grad_norm": 1.7814884185791016, "learning_rate": 8.498799425993806e-05, "loss": 0.5174968242645264, "step": 318300 }, { "epoch": 1.8921007424315377, "grad_norm": 1.2036319971084595, "learning_rate": 8.498201476419112e-05, "loss": 0.49842376708984376, "step": 318310 }, { "epoch": 1.8921601845082061, "grad_norm": 1.576649785041809, "learning_rate": 8.497603538812205e-05, "loss": 0.4930687427520752, "step": 318320 }, { "epoch": 1.8922196265848745, "grad_norm": 1.3784663677215576, "learning_rate": 8.497005613175939e-05, "loss": 0.5329488277435303, "step": 318330 }, { "epoch": 1.8922790686615427, "grad_norm": 1.218812346458435, "learning_rate": 8.496407699513182e-05, "loss": 0.5368306159973144, "step": 318340 }, { "epoch": 1.8923385107382111, "grad_norm": 1.2067651748657227, "learning_rate": 8.495809797826796e-05, "loss": 0.4822816848754883, "step": 318350 }, { "epoch": 1.8923979528148795, "grad_norm": 1.3834081888198853, "learning_rate": 8.495211908119632e-05, "loss": 0.5800268173217773, "step": 318360 }, { "epoch": 1.892457394891548, "grad_norm": 1.3749895095825195, "learning_rate": 8.494614030394558e-05, "loss": 0.5830868721008301, "step": 318370 }, { "epoch": 1.8925168369682164, "grad_norm": 1.748009204864502, "learning_rate": 8.494016164654435e-05, "loss": 0.5095174789428711, "step": 318380 }, { "epoch": 1.8925762790448846, "grad_norm": 1.2537202835083008, "learning_rate": 8.493418310902115e-05, "loss": 0.5910651206970214, "step": 318390 }, { "epoch": 1.892635721121553, "grad_norm": 1.217387080192566, "learning_rate": 8.492820469140465e-05, "loss": 0.5176676750183106, "step": 318400 }, { "epoch": 1.8926951631982214, "grad_norm": 1.6207079887390137, "learning_rate": 8.492222639372344e-05, "loss": 0.5718238830566407, "step": 318410 }, { "epoch": 1.8927546052748898, "grad_norm": 1.5815930366516113, "learning_rate": 8.491624821600606e-05, "loss": 0.5571324348449707, "step": 318420 }, { "epoch": 1.8928140473515582, "grad_norm": 1.3156542778015137, "learning_rate": 8.491027015828117e-05, "loss": 0.5076776504516601, "step": 318430 }, { "epoch": 1.8928734894282266, "grad_norm": 1.0426429510116577, "learning_rate": 8.490429222057739e-05, "loss": 0.5254773616790771, "step": 318440 }, { "epoch": 1.892932931504895, "grad_norm": 1.591917872428894, "learning_rate": 8.489831440292324e-05, "loss": 0.5498859405517578, "step": 318450 }, { "epoch": 1.8929923735815635, "grad_norm": 1.1584407091140747, "learning_rate": 8.48923367053473e-05, "loss": 0.5340316295623779, "step": 318460 }, { "epoch": 1.8930518156582319, "grad_norm": 1.5005728006362915, "learning_rate": 8.48863591278783e-05, "loss": 0.5171006679534912, "step": 318470 }, { "epoch": 1.8931112577349003, "grad_norm": 1.656074047088623, "learning_rate": 8.488038167054472e-05, "loss": 0.6027368545532227, "step": 318480 }, { "epoch": 1.8931706998115687, "grad_norm": 1.4435086250305176, "learning_rate": 8.487440433337515e-05, "loss": 0.5209258079528809, "step": 318490 }, { "epoch": 1.8932301418882371, "grad_norm": 1.314180850982666, "learning_rate": 8.486842711639828e-05, "loss": 0.5597042083740235, "step": 318500 }, { "epoch": 1.8932895839649055, "grad_norm": 1.387161135673523, "learning_rate": 8.486245001964262e-05, "loss": 0.5466715335845947, "step": 318510 }, { "epoch": 1.8933490260415737, "grad_norm": 1.491864800453186, "learning_rate": 8.485647304313673e-05, "loss": 0.5634019374847412, "step": 318520 }, { "epoch": 1.8934084681182421, "grad_norm": 1.6316444873809814, "learning_rate": 8.485049618690933e-05, "loss": 0.5733477592468261, "step": 318530 }, { "epoch": 1.8934679101949106, "grad_norm": 1.231715440750122, "learning_rate": 8.484451945098893e-05, "loss": 0.5168511390686035, "step": 318540 }, { "epoch": 1.893527352271579, "grad_norm": 1.3301132917404175, "learning_rate": 8.483854283540407e-05, "loss": 0.508885669708252, "step": 318550 }, { "epoch": 1.8935867943482474, "grad_norm": 1.3601195812225342, "learning_rate": 8.483256634018344e-05, "loss": 0.5194327354431152, "step": 318560 }, { "epoch": 1.8936462364249156, "grad_norm": 1.2476201057434082, "learning_rate": 8.48265899653556e-05, "loss": 0.503951120376587, "step": 318570 }, { "epoch": 1.893705678501584, "grad_norm": 1.9586721658706665, "learning_rate": 8.482061371094912e-05, "loss": 0.5152590274810791, "step": 318580 }, { "epoch": 1.8937651205782524, "grad_norm": 1.34526789188385, "learning_rate": 8.481463757699255e-05, "loss": 0.513682746887207, "step": 318590 }, { "epoch": 1.8938245626549208, "grad_norm": 1.6562696695327759, "learning_rate": 8.480866156351457e-05, "loss": 0.5218626976013183, "step": 318600 }, { "epoch": 1.8938840047315892, "grad_norm": 1.9324196577072144, "learning_rate": 8.480268567054372e-05, "loss": 0.6180820941925049, "step": 318610 }, { "epoch": 1.8939434468082577, "grad_norm": 1.081810712814331, "learning_rate": 8.479670989810855e-05, "loss": 0.5341694355010986, "step": 318620 }, { "epoch": 1.894002888884926, "grad_norm": 1.3221981525421143, "learning_rate": 8.479073424623774e-05, "loss": 0.4745838165283203, "step": 318630 }, { "epoch": 1.8940623309615945, "grad_norm": 1.5180490016937256, "learning_rate": 8.478475871495979e-05, "loss": 0.5467901706695557, "step": 318640 }, { "epoch": 1.894121773038263, "grad_norm": 1.7086373567581177, "learning_rate": 8.477878330430329e-05, "loss": 0.5676463603973388, "step": 318650 }, { "epoch": 1.8941812151149313, "grad_norm": 1.8691045045852661, "learning_rate": 8.477280801429688e-05, "loss": 0.5766035079956054, "step": 318660 }, { "epoch": 1.8942406571915997, "grad_norm": 1.4223427772521973, "learning_rate": 8.476683284496909e-05, "loss": 0.5515012741088867, "step": 318670 }, { "epoch": 1.8943000992682681, "grad_norm": 1.7618495225906372, "learning_rate": 8.476085779634854e-05, "loss": 0.5606040000915528, "step": 318680 }, { "epoch": 1.8943595413449366, "grad_norm": 1.5613014698028564, "learning_rate": 8.475488286846378e-05, "loss": 0.5561177253723144, "step": 318690 }, { "epoch": 1.894418983421605, "grad_norm": 1.543939471244812, "learning_rate": 8.474890806134344e-05, "loss": 0.5684097290039063, "step": 318700 }, { "epoch": 1.8944784254982732, "grad_norm": 1.4267867803573608, "learning_rate": 8.474293337501607e-05, "loss": 0.5606542587280273, "step": 318710 }, { "epoch": 1.8945378675749416, "grad_norm": 1.489318609237671, "learning_rate": 8.473695880951023e-05, "loss": 0.5120161056518555, "step": 318720 }, { "epoch": 1.89459730965161, "grad_norm": 1.4676666259765625, "learning_rate": 8.473098436485453e-05, "loss": 0.5645544052124023, "step": 318730 }, { "epoch": 1.8946567517282784, "grad_norm": 1.2833428382873535, "learning_rate": 8.472501004107756e-05, "loss": 0.5230451583862304, "step": 318740 }, { "epoch": 1.8947161938049468, "grad_norm": 1.0654911994934082, "learning_rate": 8.471903583820784e-05, "loss": 0.5341661930084228, "step": 318750 }, { "epoch": 1.894775635881615, "grad_norm": 1.201694130897522, "learning_rate": 8.471306175627403e-05, "loss": 0.5341121196746826, "step": 318760 }, { "epoch": 1.8948350779582834, "grad_norm": 1.3325285911560059, "learning_rate": 8.470708779530465e-05, "loss": 0.538877010345459, "step": 318770 }, { "epoch": 1.8948945200349518, "grad_norm": 1.584953784942627, "learning_rate": 8.470111395532829e-05, "loss": 0.5681980133056641, "step": 318780 }, { "epoch": 1.8949539621116203, "grad_norm": 1.1768845319747925, "learning_rate": 8.469514023637355e-05, "loss": 0.5112689018249512, "step": 318790 }, { "epoch": 1.8950134041882887, "grad_norm": 1.4351364374160767, "learning_rate": 8.4689166638469e-05, "loss": 0.593951416015625, "step": 318800 }, { "epoch": 1.895072846264957, "grad_norm": 1.4045313596725464, "learning_rate": 8.468319316164319e-05, "loss": 0.5473055839538574, "step": 318810 }, { "epoch": 1.8951322883416255, "grad_norm": 1.1022289991378784, "learning_rate": 8.467721980592468e-05, "loss": 0.5284496307373047, "step": 318820 }, { "epoch": 1.895191730418294, "grad_norm": 1.0677425861358643, "learning_rate": 8.467124657134214e-05, "loss": 0.5487012386322021, "step": 318830 }, { "epoch": 1.8952511724949623, "grad_norm": 1.3676767349243164, "learning_rate": 8.466527345792406e-05, "loss": 0.4810951232910156, "step": 318840 }, { "epoch": 1.8953106145716307, "grad_norm": 1.125301480293274, "learning_rate": 8.465930046569898e-05, "loss": 0.5678164005279541, "step": 318850 }, { "epoch": 1.8953700566482992, "grad_norm": 1.576816439628601, "learning_rate": 8.465332759469557e-05, "loss": 0.503357219696045, "step": 318860 }, { "epoch": 1.8954294987249676, "grad_norm": 1.694453239440918, "learning_rate": 8.464735484494237e-05, "loss": 0.5350313663482666, "step": 318870 }, { "epoch": 1.895488940801636, "grad_norm": 1.2854057550430298, "learning_rate": 8.464138221646789e-05, "loss": 0.5662128448486328, "step": 318880 }, { "epoch": 1.8955483828783042, "grad_norm": 1.393107295036316, "learning_rate": 8.463540970930079e-05, "loss": 0.5809825420379638, "step": 318890 }, { "epoch": 1.8956078249549726, "grad_norm": 1.2594075202941895, "learning_rate": 8.462943732346961e-05, "loss": 0.5478413581848145, "step": 318900 }, { "epoch": 1.895667267031641, "grad_norm": 1.2944080829620361, "learning_rate": 8.462346505900287e-05, "loss": 0.5082192420959473, "step": 318910 }, { "epoch": 1.8957267091083094, "grad_norm": 1.179915189743042, "learning_rate": 8.46174929159292e-05, "loss": 0.53681640625, "step": 318920 }, { "epoch": 1.8957861511849778, "grad_norm": 1.6464064121246338, "learning_rate": 8.461152089427717e-05, "loss": 0.5071380138397217, "step": 318930 }, { "epoch": 1.895845593261646, "grad_norm": 1.1562378406524658, "learning_rate": 8.460554899407532e-05, "loss": 0.5464314460754395, "step": 318940 }, { "epoch": 1.8959050353383144, "grad_norm": 1.408653974533081, "learning_rate": 8.459957721535217e-05, "loss": 0.6015853404998779, "step": 318950 }, { "epoch": 1.8959644774149829, "grad_norm": 1.2033246755599976, "learning_rate": 8.45936055581364e-05, "loss": 0.5419415473937989, "step": 318960 }, { "epoch": 1.8960239194916513, "grad_norm": 1.5273866653442383, "learning_rate": 8.45876340224565e-05, "loss": 0.5686066627502442, "step": 318970 }, { "epoch": 1.8960833615683197, "grad_norm": 1.1771314144134521, "learning_rate": 8.458166260834103e-05, "loss": 0.5408418655395508, "step": 318980 }, { "epoch": 1.896142803644988, "grad_norm": 1.274444341659546, "learning_rate": 8.457569131581863e-05, "loss": 0.5482405185699463, "step": 318990 }, { "epoch": 1.8962022457216565, "grad_norm": 1.3555835485458374, "learning_rate": 8.45697201449178e-05, "loss": 0.5665476799011231, "step": 319000 }, { "epoch": 1.896261687798325, "grad_norm": 1.5571640729904175, "learning_rate": 8.456374909566707e-05, "loss": 0.48885498046875, "step": 319010 }, { "epoch": 1.8963211298749933, "grad_norm": 1.313443899154663, "learning_rate": 8.455777816809512e-05, "loss": 0.5138925552368164, "step": 319020 }, { "epoch": 1.8963805719516618, "grad_norm": 1.282212257385254, "learning_rate": 8.455180736223041e-05, "loss": 0.48288869857788086, "step": 319030 }, { "epoch": 1.8964400140283302, "grad_norm": 1.1301854848861694, "learning_rate": 8.45458366781015e-05, "loss": 0.5938586235046387, "step": 319040 }, { "epoch": 1.8964994561049986, "grad_norm": 1.8934683799743652, "learning_rate": 8.453986611573706e-05, "loss": 0.5378042221069336, "step": 319050 }, { "epoch": 1.896558898181667, "grad_norm": 1.028233528137207, "learning_rate": 8.453389567516554e-05, "loss": 0.5347169876098633, "step": 319060 }, { "epoch": 1.8966183402583354, "grad_norm": 1.4099136590957642, "learning_rate": 8.452792535641556e-05, "loss": 0.5560359477996826, "step": 319070 }, { "epoch": 1.8966777823350036, "grad_norm": 1.5750483274459839, "learning_rate": 8.452195515951565e-05, "loss": 0.5565709114074707, "step": 319080 }, { "epoch": 1.896737224411672, "grad_norm": 1.3416085243225098, "learning_rate": 8.451598508449436e-05, "loss": 0.5201492309570312, "step": 319090 }, { "epoch": 1.8967966664883404, "grad_norm": 1.3368782997131348, "learning_rate": 8.451001513138031e-05, "loss": 0.5606611251831055, "step": 319100 }, { "epoch": 1.8968561085650089, "grad_norm": 1.3315403461456299, "learning_rate": 8.450404530020197e-05, "loss": 0.5264446258544921, "step": 319110 }, { "epoch": 1.8969155506416773, "grad_norm": 1.2883778810501099, "learning_rate": 8.4498075590988e-05, "loss": 0.5200261116027832, "step": 319120 }, { "epoch": 1.8969749927183455, "grad_norm": 1.2186473608016968, "learning_rate": 8.449210600376687e-05, "loss": 0.5215713500976562, "step": 319130 }, { "epoch": 1.8970344347950139, "grad_norm": 1.463240146636963, "learning_rate": 8.448613653856716e-05, "loss": 0.6113858699798584, "step": 319140 }, { "epoch": 1.8970938768716823, "grad_norm": 1.8003231287002563, "learning_rate": 8.448016719541745e-05, "loss": 0.5645305156707764, "step": 319150 }, { "epoch": 1.8971533189483507, "grad_norm": 1.4186522960662842, "learning_rate": 8.447419797434629e-05, "loss": 0.5382469177246094, "step": 319160 }, { "epoch": 1.8972127610250191, "grad_norm": 1.196837067604065, "learning_rate": 8.446822887538222e-05, "loss": 0.5441060543060303, "step": 319170 }, { "epoch": 1.8972722031016875, "grad_norm": 1.6113077402114868, "learning_rate": 8.446225989855376e-05, "loss": 0.5693592548370361, "step": 319180 }, { "epoch": 1.897331645178356, "grad_norm": 1.4352260828018188, "learning_rate": 8.445629104388954e-05, "loss": 0.5870959281921386, "step": 319190 }, { "epoch": 1.8973910872550244, "grad_norm": 1.1779333353042603, "learning_rate": 8.44503223114181e-05, "loss": 0.5353049755096435, "step": 319200 }, { "epoch": 1.8974505293316928, "grad_norm": 1.3001028299331665, "learning_rate": 8.44443537011679e-05, "loss": 0.5653140068054199, "step": 319210 }, { "epoch": 1.8975099714083612, "grad_norm": 1.7191953659057617, "learning_rate": 8.443838521316763e-05, "loss": 0.5106957435607911, "step": 319220 }, { "epoch": 1.8975694134850296, "grad_norm": 1.6745575666427612, "learning_rate": 8.443241684744572e-05, "loss": 0.6086328506469727, "step": 319230 }, { "epoch": 1.897628855561698, "grad_norm": 1.3663936853408813, "learning_rate": 8.442644860403079e-05, "loss": 0.5423146247863769, "step": 319240 }, { "epoch": 1.8976882976383664, "grad_norm": 1.2332454919815063, "learning_rate": 8.442048048295137e-05, "loss": 0.5585506916046142, "step": 319250 }, { "epoch": 1.8977477397150346, "grad_norm": 1.5953139066696167, "learning_rate": 8.441451248423602e-05, "loss": 0.5883056640625, "step": 319260 }, { "epoch": 1.897807181791703, "grad_norm": 1.4620444774627686, "learning_rate": 8.440854460791327e-05, "loss": 0.5660863876342773, "step": 319270 }, { "epoch": 1.8978666238683715, "grad_norm": 1.5889899730682373, "learning_rate": 8.44025768540117e-05, "loss": 0.5444656372070312, "step": 319280 }, { "epoch": 1.8979260659450399, "grad_norm": 1.5926510095596313, "learning_rate": 8.43966092225598e-05, "loss": 0.5592741012573242, "step": 319290 }, { "epoch": 1.8979855080217083, "grad_norm": 1.4708024263381958, "learning_rate": 8.439064171358621e-05, "loss": 0.5569726467132569, "step": 319300 }, { "epoch": 1.8980449500983765, "grad_norm": 1.2672181129455566, "learning_rate": 8.438467432711937e-05, "loss": 0.5234521865844727, "step": 319310 }, { "epoch": 1.898104392175045, "grad_norm": 1.26986563205719, "learning_rate": 8.437870706318789e-05, "loss": 0.5593631744384766, "step": 319320 }, { "epoch": 1.8981638342517133, "grad_norm": 1.2936139106750488, "learning_rate": 8.437273992182033e-05, "loss": 0.5131387710571289, "step": 319330 }, { "epoch": 1.8982232763283817, "grad_norm": 1.6142276525497437, "learning_rate": 8.436677290304515e-05, "loss": 0.6325416564941406, "step": 319340 }, { "epoch": 1.8982827184050501, "grad_norm": 1.2158647775650024, "learning_rate": 8.4360806006891e-05, "loss": 0.5243166923522949, "step": 319350 }, { "epoch": 1.8983421604817186, "grad_norm": 1.245910406112671, "learning_rate": 8.435483923338636e-05, "loss": 0.5205569267272949, "step": 319360 }, { "epoch": 1.898401602558387, "grad_norm": 1.5151375532150269, "learning_rate": 8.43488725825598e-05, "loss": 0.5505936622619629, "step": 319370 }, { "epoch": 1.8984610446350554, "grad_norm": 1.3600664138793945, "learning_rate": 8.434290605443984e-05, "loss": 0.5467086791992187, "step": 319380 }, { "epoch": 1.8985204867117238, "grad_norm": 1.282409906387329, "learning_rate": 8.433693964905503e-05, "loss": 0.549113130569458, "step": 319390 }, { "epoch": 1.8985799287883922, "grad_norm": 1.6242599487304688, "learning_rate": 8.43309733664339e-05, "loss": 0.5355509757995606, "step": 319400 }, { "epoch": 1.8986393708650606, "grad_norm": 1.298585057258606, "learning_rate": 8.432500720660504e-05, "loss": 0.5330459594726562, "step": 319410 }, { "epoch": 1.898698812941729, "grad_norm": 1.5699915885925293, "learning_rate": 8.431904116959692e-05, "loss": 0.6353413581848144, "step": 319420 }, { "epoch": 1.8987582550183975, "grad_norm": 1.463545322418213, "learning_rate": 8.431307525543817e-05, "loss": 0.5201068878173828, "step": 319430 }, { "epoch": 1.8988176970950659, "grad_norm": 1.088609218597412, "learning_rate": 8.430710946415718e-05, "loss": 0.5134410858154297, "step": 319440 }, { "epoch": 1.898877139171734, "grad_norm": 0.9328030943870544, "learning_rate": 8.430114379578265e-05, "loss": 0.5438002586364746, "step": 319450 }, { "epoch": 1.8989365812484025, "grad_norm": 1.2203428745269775, "learning_rate": 8.429517825034308e-05, "loss": 0.5677248001098633, "step": 319460 }, { "epoch": 1.898996023325071, "grad_norm": 1.1046671867370605, "learning_rate": 8.428921282786688e-05, "loss": 0.5225375175476075, "step": 319470 }, { "epoch": 1.8990554654017393, "grad_norm": 1.0251396894454956, "learning_rate": 8.428324752838277e-05, "loss": 0.5193143367767334, "step": 319480 }, { "epoch": 1.8991149074784077, "grad_norm": 1.223426342010498, "learning_rate": 8.427728235191917e-05, "loss": 0.5626665115356445, "step": 319490 }, { "epoch": 1.899174349555076, "grad_norm": 1.3361690044403076, "learning_rate": 8.427131729850462e-05, "loss": 0.5245204925537109, "step": 319500 }, { "epoch": 1.8992337916317443, "grad_norm": 1.3487907648086548, "learning_rate": 8.42653523681677e-05, "loss": 0.5524600982666016, "step": 319510 }, { "epoch": 1.8992932337084127, "grad_norm": 1.3764896392822266, "learning_rate": 8.425938756093694e-05, "loss": 0.5150397777557373, "step": 319520 }, { "epoch": 1.8993526757850812, "grad_norm": 1.2038228511810303, "learning_rate": 8.425342287684084e-05, "loss": 0.49086456298828124, "step": 319530 }, { "epoch": 1.8994121178617496, "grad_norm": 1.5170314311981201, "learning_rate": 8.424745831590795e-05, "loss": 0.5408263206481934, "step": 319540 }, { "epoch": 1.899471559938418, "grad_norm": 1.0990796089172363, "learning_rate": 8.42414938781668e-05, "loss": 0.560050106048584, "step": 319550 }, { "epoch": 1.8995310020150864, "grad_norm": 1.1945244073867798, "learning_rate": 8.423552956364595e-05, "loss": 0.5265498161315918, "step": 319560 }, { "epoch": 1.8995904440917548, "grad_norm": 1.4283828735351562, "learning_rate": 8.422956537237387e-05, "loss": 0.5391126155853272, "step": 319570 }, { "epoch": 1.8996498861684232, "grad_norm": 1.6036691665649414, "learning_rate": 8.422360130437914e-05, "loss": 0.5619640350341797, "step": 319580 }, { "epoch": 1.8997093282450916, "grad_norm": 1.4353337287902832, "learning_rate": 8.42176373596903e-05, "loss": 0.5665551662445069, "step": 319590 }, { "epoch": 1.89976877032176, "grad_norm": 1.3494850397109985, "learning_rate": 8.421167353833583e-05, "loss": 0.5420687198638916, "step": 319600 }, { "epoch": 1.8998282123984285, "grad_norm": 1.3019566535949707, "learning_rate": 8.42057098403443e-05, "loss": 0.5757998466491699, "step": 319610 }, { "epoch": 1.8998876544750969, "grad_norm": 0.9752857089042664, "learning_rate": 8.419974626574423e-05, "loss": 0.5298415660858155, "step": 319620 }, { "epoch": 1.899947096551765, "grad_norm": 1.0534842014312744, "learning_rate": 8.419378281456412e-05, "loss": 0.5050033569335938, "step": 319630 }, { "epoch": 1.9000065386284335, "grad_norm": 1.5431429147720337, "learning_rate": 8.418781948683252e-05, "loss": 0.5376877784729004, "step": 319640 }, { "epoch": 1.900065980705102, "grad_norm": 1.0242667198181152, "learning_rate": 8.418185628257799e-05, "loss": 0.5555302619934082, "step": 319650 }, { "epoch": 1.9001254227817703, "grad_norm": 1.5598087310791016, "learning_rate": 8.417589320182901e-05, "loss": 0.568686580657959, "step": 319660 }, { "epoch": 1.9001848648584387, "grad_norm": 1.6332316398620605, "learning_rate": 8.416993024461409e-05, "loss": 0.5521683692932129, "step": 319670 }, { "epoch": 1.900244306935107, "grad_norm": 1.4211959838867188, "learning_rate": 8.416396741096179e-05, "loss": 0.5256701946258545, "step": 319680 }, { "epoch": 1.9003037490117753, "grad_norm": 1.3165053129196167, "learning_rate": 8.415800470090066e-05, "loss": 0.5273491859436035, "step": 319690 }, { "epoch": 1.9003631910884438, "grad_norm": 1.3421955108642578, "learning_rate": 8.415204211445915e-05, "loss": 0.5518549919128418, "step": 319700 }, { "epoch": 1.9004226331651122, "grad_norm": 1.8214248418807983, "learning_rate": 8.414607965166583e-05, "loss": 0.5574158191680908, "step": 319710 }, { "epoch": 1.9004820752417806, "grad_norm": 1.393141508102417, "learning_rate": 8.414011731254925e-05, "loss": 0.5105160713195801, "step": 319720 }, { "epoch": 1.900541517318449, "grad_norm": 1.478435754776001, "learning_rate": 8.413415509713784e-05, "loss": 0.5490993976593017, "step": 319730 }, { "epoch": 1.9006009593951174, "grad_norm": 1.623343825340271, "learning_rate": 8.412819300546024e-05, "loss": 0.48435153961181643, "step": 319740 }, { "epoch": 1.9006604014717858, "grad_norm": 1.3236640691757202, "learning_rate": 8.412223103754488e-05, "loss": 0.49572553634643557, "step": 319750 }, { "epoch": 1.9007198435484542, "grad_norm": 1.6347638368606567, "learning_rate": 8.41162691934203e-05, "loss": 0.5731039047241211, "step": 319760 }, { "epoch": 1.9007792856251227, "grad_norm": 1.5029761791229248, "learning_rate": 8.411030747311506e-05, "loss": 0.49439687728881837, "step": 319770 }, { "epoch": 1.900838727701791, "grad_norm": 1.5218714475631714, "learning_rate": 8.41043458766576e-05, "loss": 0.5591330528259277, "step": 319780 }, { "epoch": 1.9008981697784595, "grad_norm": 2.1893765926361084, "learning_rate": 8.409838440407653e-05, "loss": 0.5462335109710693, "step": 319790 }, { "epoch": 1.900957611855128, "grad_norm": 1.5046684741973877, "learning_rate": 8.40924230554003e-05, "loss": 0.5780413627624512, "step": 319800 }, { "epoch": 1.9010170539317963, "grad_norm": 1.3496439456939697, "learning_rate": 8.408646183065746e-05, "loss": 0.5701842308044434, "step": 319810 }, { "epoch": 1.9010764960084645, "grad_norm": 1.1677476167678833, "learning_rate": 8.408050072987654e-05, "loss": 0.5035711288452148, "step": 319820 }, { "epoch": 1.901135938085133, "grad_norm": 1.3628883361816406, "learning_rate": 8.407453975308598e-05, "loss": 0.5912389755249023, "step": 319830 }, { "epoch": 1.9011953801618013, "grad_norm": 1.5130032300949097, "learning_rate": 8.406857890031441e-05, "loss": 0.5111232757568359, "step": 319840 }, { "epoch": 1.9012548222384698, "grad_norm": 1.413096308708191, "learning_rate": 8.406261817159027e-05, "loss": 0.5410089492797852, "step": 319850 }, { "epoch": 1.901314264315138, "grad_norm": 1.3532265424728394, "learning_rate": 8.405665756694206e-05, "loss": 0.5621446132659912, "step": 319860 }, { "epoch": 1.9013737063918064, "grad_norm": 1.2185076475143433, "learning_rate": 8.405069708639833e-05, "loss": 0.5546290874481201, "step": 319870 }, { "epoch": 1.9014331484684748, "grad_norm": 1.5826900005340576, "learning_rate": 8.40447367299876e-05, "loss": 0.6007661819458008, "step": 319880 }, { "epoch": 1.9014925905451432, "grad_norm": 1.5435835123062134, "learning_rate": 8.403877649773835e-05, "loss": 0.5619280815124512, "step": 319890 }, { "epoch": 1.9015520326218116, "grad_norm": 1.1732761859893799, "learning_rate": 8.403281638967912e-05, "loss": 0.5829448223114013, "step": 319900 }, { "epoch": 1.90161147469848, "grad_norm": 1.2887780666351318, "learning_rate": 8.40268564058384e-05, "loss": 0.5577050685882569, "step": 319910 }, { "epoch": 1.9016709167751484, "grad_norm": 1.2293258905410767, "learning_rate": 8.402089654624477e-05, "loss": 0.5157939910888671, "step": 319920 }, { "epoch": 1.9017303588518168, "grad_norm": 1.4743627309799194, "learning_rate": 8.401493681092657e-05, "loss": 0.5640070915222168, "step": 319930 }, { "epoch": 1.9017898009284853, "grad_norm": 1.4049303531646729, "learning_rate": 8.40089771999125e-05, "loss": 0.5365920543670655, "step": 319940 }, { "epoch": 1.9018492430051537, "grad_norm": 1.3681373596191406, "learning_rate": 8.4003017713231e-05, "loss": 0.531973123550415, "step": 319950 }, { "epoch": 1.901908685081822, "grad_norm": 1.4151195287704468, "learning_rate": 8.399705835091049e-05, "loss": 0.5248604774475097, "step": 319960 }, { "epoch": 1.9019681271584905, "grad_norm": 1.302486538887024, "learning_rate": 8.399109911297963e-05, "loss": 0.545046329498291, "step": 319970 }, { "epoch": 1.902027569235159, "grad_norm": 1.3842498064041138, "learning_rate": 8.398513999946684e-05, "loss": 0.5495696067810059, "step": 319980 }, { "epoch": 1.9020870113118273, "grad_norm": 1.5906912088394165, "learning_rate": 8.397918101040059e-05, "loss": 0.5728204727172852, "step": 319990 }, { "epoch": 1.9021464533884955, "grad_norm": 1.4603996276855469, "learning_rate": 8.397322214580947e-05, "loss": 0.5462994575500488, "step": 320000 }, { "epoch": 1.902205895465164, "grad_norm": 2.344526529312134, "learning_rate": 8.396726340572199e-05, "loss": 0.5378560066223145, "step": 320010 }, { "epoch": 1.9022653375418324, "grad_norm": 1.1200008392333984, "learning_rate": 8.396130479016655e-05, "loss": 0.5342390537261963, "step": 320020 }, { "epoch": 1.9023247796185008, "grad_norm": 1.2647087574005127, "learning_rate": 8.395534629917172e-05, "loss": 0.5507706642150879, "step": 320030 }, { "epoch": 1.9023842216951692, "grad_norm": 1.4812469482421875, "learning_rate": 8.394938793276603e-05, "loss": 0.589444637298584, "step": 320040 }, { "epoch": 1.9024436637718374, "grad_norm": 1.456588864326477, "learning_rate": 8.394342969097797e-05, "loss": 0.5866449356079102, "step": 320050 }, { "epoch": 1.9025031058485058, "grad_norm": 1.569639801979065, "learning_rate": 8.393747157383596e-05, "loss": 0.5323127746582031, "step": 320060 }, { "epoch": 1.9025625479251742, "grad_norm": 1.2843133211135864, "learning_rate": 8.393151358136864e-05, "loss": 0.5584567070007325, "step": 320070 }, { "epoch": 1.9026219900018426, "grad_norm": 1.6424187421798706, "learning_rate": 8.392555571360443e-05, "loss": 0.5680034637451172, "step": 320080 }, { "epoch": 1.902681432078511, "grad_norm": 1.3078256845474243, "learning_rate": 8.391959797057179e-05, "loss": 0.5207447052001953, "step": 320090 }, { "epoch": 1.9027408741551795, "grad_norm": 1.3128843307495117, "learning_rate": 8.391364035229931e-05, "loss": 0.505046796798706, "step": 320100 }, { "epoch": 1.9028003162318479, "grad_norm": 1.4047820568084717, "learning_rate": 8.390768285881545e-05, "loss": 0.5535419940948486, "step": 320110 }, { "epoch": 1.9028597583085163, "grad_norm": 1.270052194595337, "learning_rate": 8.390172549014869e-05, "loss": 0.5535161018371582, "step": 320120 }, { "epoch": 1.9029192003851847, "grad_norm": 1.413989782333374, "learning_rate": 8.389576824632754e-05, "loss": 0.5716165065765381, "step": 320130 }, { "epoch": 1.902978642461853, "grad_norm": 2.003304958343506, "learning_rate": 8.388981112738052e-05, "loss": 0.5688667297363281, "step": 320140 }, { "epoch": 1.9030380845385215, "grad_norm": 1.9198992252349854, "learning_rate": 8.388385413333613e-05, "loss": 0.5405708312988281, "step": 320150 }, { "epoch": 1.90309752661519, "grad_norm": 1.400087594985962, "learning_rate": 8.387789726422281e-05, "loss": 0.531529712677002, "step": 320160 }, { "epoch": 1.9031569686918584, "grad_norm": 1.60178804397583, "learning_rate": 8.387194052006913e-05, "loss": 0.5100319862365723, "step": 320170 }, { "epoch": 1.9032164107685268, "grad_norm": 1.6951160430908203, "learning_rate": 8.386598390090352e-05, "loss": 0.5197263717651367, "step": 320180 }, { "epoch": 1.903275852845195, "grad_norm": 1.3319580554962158, "learning_rate": 8.386002740675449e-05, "loss": 0.5096536159515381, "step": 320190 }, { "epoch": 1.9033352949218634, "grad_norm": 1.585167407989502, "learning_rate": 8.385407103765059e-05, "loss": 0.5586968421936035, "step": 320200 }, { "epoch": 1.9033947369985318, "grad_norm": 1.3491202592849731, "learning_rate": 8.384811479362025e-05, "loss": 0.4944730758666992, "step": 320210 }, { "epoch": 1.9034541790752002, "grad_norm": 1.8605902194976807, "learning_rate": 8.384215867469194e-05, "loss": 0.5686301231384278, "step": 320220 }, { "epoch": 1.9035136211518684, "grad_norm": 1.87362802028656, "learning_rate": 8.383620268089425e-05, "loss": 0.5581887245178223, "step": 320230 }, { "epoch": 1.9035730632285368, "grad_norm": 1.281894564628601, "learning_rate": 8.38302468122556e-05, "loss": 0.5796133041381836, "step": 320240 }, { "epoch": 1.9036325053052052, "grad_norm": 1.1941157579421997, "learning_rate": 8.382429106880449e-05, "loss": 0.5084262371063233, "step": 320250 }, { "epoch": 1.9036919473818736, "grad_norm": 1.6800217628479004, "learning_rate": 8.381833545056942e-05, "loss": 0.528067684173584, "step": 320260 }, { "epoch": 1.903751389458542, "grad_norm": 1.3736555576324463, "learning_rate": 8.381237995757889e-05, "loss": 0.5172970771789551, "step": 320270 }, { "epoch": 1.9038108315352105, "grad_norm": 1.5846995115280151, "learning_rate": 8.380642458986136e-05, "loss": 0.5806924819946289, "step": 320280 }, { "epoch": 1.9038702736118789, "grad_norm": 1.3443095684051514, "learning_rate": 8.380046934744534e-05, "loss": 0.5875478744506836, "step": 320290 }, { "epoch": 1.9039297156885473, "grad_norm": 1.2350791692733765, "learning_rate": 8.379451423035931e-05, "loss": 0.516862154006958, "step": 320300 }, { "epoch": 1.9039891577652157, "grad_norm": 1.3685003519058228, "learning_rate": 8.378855923863178e-05, "loss": 0.5592494964599609, "step": 320310 }, { "epoch": 1.9040485998418841, "grad_norm": 1.7711634635925293, "learning_rate": 8.378260437229118e-05, "loss": 0.5613463401794434, "step": 320320 }, { "epoch": 1.9041080419185525, "grad_norm": 1.3783971071243286, "learning_rate": 8.377664963136604e-05, "loss": 0.5633147239685059, "step": 320330 }, { "epoch": 1.904167483995221, "grad_norm": 1.597640872001648, "learning_rate": 8.377069501588486e-05, "loss": 0.5545766830444336, "step": 320340 }, { "epoch": 1.9042269260718894, "grad_norm": 1.4260997772216797, "learning_rate": 8.376474052587609e-05, "loss": 0.5502423286437989, "step": 320350 }, { "epoch": 1.9042863681485578, "grad_norm": 1.3750336170196533, "learning_rate": 8.375878616136823e-05, "loss": 0.598453426361084, "step": 320360 }, { "epoch": 1.904345810225226, "grad_norm": 1.4027634859085083, "learning_rate": 8.375283192238976e-05, "loss": 0.5268041610717773, "step": 320370 }, { "epoch": 1.9044052523018944, "grad_norm": 1.2081292867660522, "learning_rate": 8.374687780896917e-05, "loss": 0.513486099243164, "step": 320380 }, { "epoch": 1.9044646943785628, "grad_norm": 1.5909658670425415, "learning_rate": 8.374092382113491e-05, "loss": 0.5803908824920654, "step": 320390 }, { "epoch": 1.9045241364552312, "grad_norm": 1.250974178314209, "learning_rate": 8.373496995891555e-05, "loss": 0.4641998291015625, "step": 320400 }, { "epoch": 1.9045835785318996, "grad_norm": 1.6204091310501099, "learning_rate": 8.372901622233948e-05, "loss": 0.5197418212890625, "step": 320410 }, { "epoch": 1.9046430206085678, "grad_norm": 1.2657990455627441, "learning_rate": 8.372306261143519e-05, "loss": 0.5212163925170898, "step": 320420 }, { "epoch": 1.9047024626852362, "grad_norm": 1.801203966140747, "learning_rate": 8.371710912623119e-05, "loss": 0.5922487258911133, "step": 320430 }, { "epoch": 1.9047619047619047, "grad_norm": 1.0002557039260864, "learning_rate": 8.371115576675599e-05, "loss": 0.5397072792053222, "step": 320440 }, { "epoch": 1.904821346838573, "grad_norm": 1.700331211090088, "learning_rate": 8.370520253303795e-05, "loss": 0.5833377838134766, "step": 320450 }, { "epoch": 1.9048807889152415, "grad_norm": 1.4767462015151978, "learning_rate": 8.369924942510568e-05, "loss": 0.5940574645996094, "step": 320460 }, { "epoch": 1.90494023099191, "grad_norm": 1.525837779045105, "learning_rate": 8.369329644298763e-05, "loss": 0.5740833759307862, "step": 320470 }, { "epoch": 1.9049996730685783, "grad_norm": 1.5683627128601074, "learning_rate": 8.368734358671217e-05, "loss": 0.5767770767211914, "step": 320480 }, { "epoch": 1.9050591151452467, "grad_norm": 1.1013309955596924, "learning_rate": 8.36813908563079e-05, "loss": 0.531177282333374, "step": 320490 }, { "epoch": 1.9051185572219151, "grad_norm": 1.6087568998336792, "learning_rate": 8.367543825180331e-05, "loss": 0.5508611679077149, "step": 320500 }, { "epoch": 1.9051779992985836, "grad_norm": 1.3977470397949219, "learning_rate": 8.366948577322678e-05, "loss": 0.5456465244293213, "step": 320510 }, { "epoch": 1.905237441375252, "grad_norm": 1.2147256135940552, "learning_rate": 8.366353342060677e-05, "loss": 0.4969057559967041, "step": 320520 }, { "epoch": 1.9052968834519204, "grad_norm": 1.4576787948608398, "learning_rate": 8.365758119397188e-05, "loss": 0.499615478515625, "step": 320530 }, { "epoch": 1.9053563255285888, "grad_norm": 1.5283459424972534, "learning_rate": 8.365162909335051e-05, "loss": 0.5160954475402832, "step": 320540 }, { "epoch": 1.9054157676052572, "grad_norm": 1.359725832939148, "learning_rate": 8.364567711877109e-05, "loss": 0.5476555347442627, "step": 320550 }, { "epoch": 1.9054752096819254, "grad_norm": 1.1813808679580688, "learning_rate": 8.36397252702622e-05, "loss": 0.5084898471832275, "step": 320560 }, { "epoch": 1.9055346517585938, "grad_norm": 1.2110766172409058, "learning_rate": 8.363377354785223e-05, "loss": 0.5104406356811524, "step": 320570 }, { "epoch": 1.9055940938352622, "grad_norm": 1.2180473804473877, "learning_rate": 8.36278219515696e-05, "loss": 0.5208935737609863, "step": 320580 }, { "epoch": 1.9056535359119307, "grad_norm": 1.327547550201416, "learning_rate": 8.362187048144294e-05, "loss": 0.5376216411590576, "step": 320590 }, { "epoch": 1.9057129779885988, "grad_norm": 1.5580549240112305, "learning_rate": 8.36159191375006e-05, "loss": 0.5302991390228271, "step": 320600 }, { "epoch": 1.9057724200652673, "grad_norm": 1.0490384101867676, "learning_rate": 8.360996791977104e-05, "loss": 0.5026525974273681, "step": 320610 }, { "epoch": 1.9058318621419357, "grad_norm": 1.3271236419677734, "learning_rate": 8.360401682828285e-05, "loss": 0.4939701080322266, "step": 320620 }, { "epoch": 1.905891304218604, "grad_norm": 1.2312620878219604, "learning_rate": 8.359806586306437e-05, "loss": 0.5624630451202393, "step": 320630 }, { "epoch": 1.9059507462952725, "grad_norm": 1.1863676309585571, "learning_rate": 8.359211502414412e-05, "loss": 0.5171592235565186, "step": 320640 }, { "epoch": 1.906010188371941, "grad_norm": 1.547471046447754, "learning_rate": 8.358616431155055e-05, "loss": 0.5153794765472413, "step": 320650 }, { "epoch": 1.9060696304486093, "grad_norm": 1.5577319860458374, "learning_rate": 8.358021372531217e-05, "loss": 0.532276725769043, "step": 320660 }, { "epoch": 1.9061290725252777, "grad_norm": 1.9039006233215332, "learning_rate": 8.357426326545739e-05, "loss": 0.5311058044433594, "step": 320670 }, { "epoch": 1.9061885146019462, "grad_norm": 1.1786472797393799, "learning_rate": 8.356831293201468e-05, "loss": 0.5953183174133301, "step": 320680 }, { "epoch": 1.9062479566786146, "grad_norm": 1.5706688165664673, "learning_rate": 8.356236272501254e-05, "loss": 0.560432243347168, "step": 320690 }, { "epoch": 1.906307398755283, "grad_norm": 1.7042933702468872, "learning_rate": 8.355641264447944e-05, "loss": 0.4655769348144531, "step": 320700 }, { "epoch": 1.9063668408319514, "grad_norm": 1.391550064086914, "learning_rate": 8.35504626904438e-05, "loss": 0.5469412803649902, "step": 320710 }, { "epoch": 1.9064262829086198, "grad_norm": 1.231582522392273, "learning_rate": 8.354451286293413e-05, "loss": 0.5540687561035156, "step": 320720 }, { "epoch": 1.9064857249852882, "grad_norm": 1.236783742904663, "learning_rate": 8.353856316197881e-05, "loss": 0.516887092590332, "step": 320730 }, { "epoch": 1.9065451670619564, "grad_norm": 1.699577808380127, "learning_rate": 8.353261358760638e-05, "loss": 0.5197024345397949, "step": 320740 }, { "epoch": 1.9066046091386248, "grad_norm": 1.6521540880203247, "learning_rate": 8.352666413984529e-05, "loss": 0.5197416305541992, "step": 320750 }, { "epoch": 1.9066640512152933, "grad_norm": 1.089462161064148, "learning_rate": 8.352071481872399e-05, "loss": 0.582064437866211, "step": 320760 }, { "epoch": 1.9067234932919617, "grad_norm": 1.4138067960739136, "learning_rate": 8.351476562427092e-05, "loss": 0.5394184112548828, "step": 320770 }, { "epoch": 1.90678293536863, "grad_norm": 1.6601066589355469, "learning_rate": 8.350881655651454e-05, "loss": 0.5320479869842529, "step": 320780 }, { "epoch": 1.9068423774452983, "grad_norm": 1.3693385124206543, "learning_rate": 8.350286761548336e-05, "loss": 0.5534390449523926, "step": 320790 }, { "epoch": 1.9069018195219667, "grad_norm": 1.0255322456359863, "learning_rate": 8.34969188012058e-05, "loss": 0.5196186065673828, "step": 320800 }, { "epoch": 1.906961261598635, "grad_norm": 1.6530166864395142, "learning_rate": 8.34909701137103e-05, "loss": 0.5703322887420654, "step": 320810 }, { "epoch": 1.9070207036753035, "grad_norm": 1.7985045909881592, "learning_rate": 8.348502155302533e-05, "loss": 0.5570863723754883, "step": 320820 }, { "epoch": 1.907080145751972, "grad_norm": 1.3737919330596924, "learning_rate": 8.347907311917938e-05, "loss": 0.5828147888183594, "step": 320830 }, { "epoch": 1.9071395878286403, "grad_norm": 1.420427680015564, "learning_rate": 8.347312481220084e-05, "loss": 0.5296296596527099, "step": 320840 }, { "epoch": 1.9071990299053088, "grad_norm": 1.5542628765106201, "learning_rate": 8.346717663211823e-05, "loss": 0.5580947875976563, "step": 320850 }, { "epoch": 1.9072584719819772, "grad_norm": 1.3957016468048096, "learning_rate": 8.346122857895997e-05, "loss": 0.5477144241333007, "step": 320860 }, { "epoch": 1.9073179140586456, "grad_norm": 2.252683401107788, "learning_rate": 8.345528065275454e-05, "loss": 0.5646191596984863, "step": 320870 }, { "epoch": 1.907377356135314, "grad_norm": 1.4747676849365234, "learning_rate": 8.344933285353032e-05, "loss": 0.6102778434753418, "step": 320880 }, { "epoch": 1.9074367982119824, "grad_norm": 1.086072325706482, "learning_rate": 8.344338518131587e-05, "loss": 0.5573920249938965, "step": 320890 }, { "epoch": 1.9074962402886508, "grad_norm": 1.297800898551941, "learning_rate": 8.343743763613957e-05, "loss": 0.5599939346313476, "step": 320900 }, { "epoch": 1.9075556823653192, "grad_norm": 1.255926251411438, "learning_rate": 8.343149021802985e-05, "loss": 0.5131378173828125, "step": 320910 }, { "epoch": 1.9076151244419877, "grad_norm": 1.4754858016967773, "learning_rate": 8.342554292701523e-05, "loss": 0.5256316661834717, "step": 320920 }, { "epoch": 1.9076745665186559, "grad_norm": 1.5290679931640625, "learning_rate": 8.341959576312417e-05, "loss": 0.5648364067077637, "step": 320930 }, { "epoch": 1.9077340085953243, "grad_norm": 1.2351980209350586, "learning_rate": 8.3413648726385e-05, "loss": 0.5577127456665039, "step": 320940 }, { "epoch": 1.9077934506719927, "grad_norm": 1.376055359840393, "learning_rate": 8.340770181682626e-05, "loss": 0.48869986534118653, "step": 320950 }, { "epoch": 1.907852892748661, "grad_norm": 1.1761269569396973, "learning_rate": 8.340175503447645e-05, "loss": 0.5016475677490234, "step": 320960 }, { "epoch": 1.9079123348253293, "grad_norm": 1.4099572896957397, "learning_rate": 8.339580837936387e-05, "loss": 0.5165723323822021, "step": 320970 }, { "epoch": 1.9079717769019977, "grad_norm": 1.3821948766708374, "learning_rate": 8.33898618515171e-05, "loss": 0.5455411911010742, "step": 320980 }, { "epoch": 1.9080312189786661, "grad_norm": 1.6380661725997925, "learning_rate": 8.338391545096453e-05, "loss": 0.6395569324493409, "step": 320990 }, { "epoch": 1.9080906610553345, "grad_norm": 1.6991081237792969, "learning_rate": 8.337796917773459e-05, "loss": 0.5744717597961426, "step": 321000 }, { "epoch": 1.908150103132003, "grad_norm": 1.1543254852294922, "learning_rate": 8.337202303185572e-05, "loss": 0.5438783645629883, "step": 321010 }, { "epoch": 1.9082095452086714, "grad_norm": 1.7849687337875366, "learning_rate": 8.336607701335645e-05, "loss": 0.5262551784515381, "step": 321020 }, { "epoch": 1.9082689872853398, "grad_norm": 1.714562177658081, "learning_rate": 8.336013112226515e-05, "loss": 0.5793286323547363, "step": 321030 }, { "epoch": 1.9083284293620082, "grad_norm": 1.1007306575775146, "learning_rate": 8.335418535861022e-05, "loss": 0.49790444374084475, "step": 321040 }, { "epoch": 1.9083878714386766, "grad_norm": 1.4389137029647827, "learning_rate": 8.334823972242023e-05, "loss": 0.5574224472045899, "step": 321050 }, { "epoch": 1.908447313515345, "grad_norm": 1.4567041397094727, "learning_rate": 8.334229421372355e-05, "loss": 0.5644125938415527, "step": 321060 }, { "epoch": 1.9085067555920134, "grad_norm": 1.7186222076416016, "learning_rate": 8.333634883254854e-05, "loss": 0.5353841781616211, "step": 321070 }, { "epoch": 1.9085661976686819, "grad_norm": 1.4578768014907837, "learning_rate": 8.333040357892381e-05, "loss": 0.4836718082427979, "step": 321080 }, { "epoch": 1.9086256397453503, "grad_norm": 1.8078014850616455, "learning_rate": 8.332445845287769e-05, "loss": 0.5528656959533691, "step": 321090 }, { "epoch": 1.9086850818220187, "grad_norm": 1.2772085666656494, "learning_rate": 8.331851345443861e-05, "loss": 0.5580256938934326, "step": 321100 }, { "epoch": 1.9087445238986869, "grad_norm": 1.3876800537109375, "learning_rate": 8.33125685836351e-05, "loss": 0.5631259918212891, "step": 321110 }, { "epoch": 1.9088039659753553, "grad_norm": 1.3014217615127563, "learning_rate": 8.33066238404955e-05, "loss": 0.5677367210388183, "step": 321120 }, { "epoch": 1.9088634080520237, "grad_norm": 1.466807246208191, "learning_rate": 8.330067922504832e-05, "loss": 0.5429568290710449, "step": 321130 }, { "epoch": 1.9089228501286921, "grad_norm": 1.4233050346374512, "learning_rate": 8.329473473732192e-05, "loss": 0.5350823879241944, "step": 321140 }, { "epoch": 1.9089822922053605, "grad_norm": 1.2454222440719604, "learning_rate": 8.328879037734481e-05, "loss": 0.5293479442596436, "step": 321150 }, { "epoch": 1.9090417342820287, "grad_norm": 1.5174860954284668, "learning_rate": 8.328284614514538e-05, "loss": 0.537699031829834, "step": 321160 }, { "epoch": 1.9091011763586971, "grad_norm": 1.6349639892578125, "learning_rate": 8.327690204075209e-05, "loss": 0.5463114261627198, "step": 321170 }, { "epoch": 1.9091606184353656, "grad_norm": 1.1644840240478516, "learning_rate": 8.327095806419339e-05, "loss": 0.5402023315429687, "step": 321180 }, { "epoch": 1.909220060512034, "grad_norm": 1.3212369680404663, "learning_rate": 8.326501421549766e-05, "loss": 0.5281380653381348, "step": 321190 }, { "epoch": 1.9092795025887024, "grad_norm": 1.2409555912017822, "learning_rate": 8.325907049469337e-05, "loss": 0.5202806949615478, "step": 321200 }, { "epoch": 1.9093389446653708, "grad_norm": 1.1646751165390015, "learning_rate": 8.325312690180895e-05, "loss": 0.5793265342712403, "step": 321210 }, { "epoch": 1.9093983867420392, "grad_norm": 1.111945390701294, "learning_rate": 8.324718343687285e-05, "loss": 0.5192995071411133, "step": 321220 }, { "epoch": 1.9094578288187076, "grad_norm": 1.2922877073287964, "learning_rate": 8.324124009991346e-05, "loss": 0.5390036106109619, "step": 321230 }, { "epoch": 1.909517270895376, "grad_norm": 1.398921251296997, "learning_rate": 8.323529689095923e-05, "loss": 0.494049596786499, "step": 321240 }, { "epoch": 1.9095767129720445, "grad_norm": 1.204727292060852, "learning_rate": 8.322935381003863e-05, "loss": 0.5178416252136231, "step": 321250 }, { "epoch": 1.9096361550487129, "grad_norm": 1.360719084739685, "learning_rate": 8.322341085718002e-05, "loss": 0.5747538566589355, "step": 321260 }, { "epoch": 1.9096955971253813, "grad_norm": 1.2053792476654053, "learning_rate": 8.321746803241186e-05, "loss": 0.49039134979248045, "step": 321270 }, { "epoch": 1.9097550392020497, "grad_norm": 1.4376153945922852, "learning_rate": 8.32115253357626e-05, "loss": 0.5161930084228515, "step": 321280 }, { "epoch": 1.9098144812787181, "grad_norm": 1.2912975549697876, "learning_rate": 8.320558276726062e-05, "loss": 0.49225363731384275, "step": 321290 }, { "epoch": 1.9098739233553863, "grad_norm": 1.3352662324905396, "learning_rate": 8.31996403269344e-05, "loss": 0.5010732650756836, "step": 321300 }, { "epoch": 1.9099333654320547, "grad_norm": 1.0773532390594482, "learning_rate": 8.319369801481233e-05, "loss": 0.5938504219055176, "step": 321310 }, { "epoch": 1.9099928075087231, "grad_norm": 1.2465347051620483, "learning_rate": 8.318775583092286e-05, "loss": 0.5003517150878907, "step": 321320 }, { "epoch": 1.9100522495853915, "grad_norm": 1.4160771369934082, "learning_rate": 8.318181377529437e-05, "loss": 0.5158652305603028, "step": 321330 }, { "epoch": 1.9101116916620597, "grad_norm": 1.5205292701721191, "learning_rate": 8.317587184795536e-05, "loss": 0.5601036071777343, "step": 321340 }, { "epoch": 1.9101711337387282, "grad_norm": 1.5375336408615112, "learning_rate": 8.31699300489342e-05, "loss": 0.5421864509582519, "step": 321350 }, { "epoch": 1.9102305758153966, "grad_norm": 1.4264421463012695, "learning_rate": 8.316398837825934e-05, "loss": 0.526374340057373, "step": 321360 }, { "epoch": 1.910290017892065, "grad_norm": 1.0757933855056763, "learning_rate": 8.315804683595916e-05, "loss": 0.5163154602050781, "step": 321370 }, { "epoch": 1.9103494599687334, "grad_norm": 1.3669705390930176, "learning_rate": 8.31521054220621e-05, "loss": 0.5441530227661133, "step": 321380 }, { "epoch": 1.9104089020454018, "grad_norm": 1.6144598722457886, "learning_rate": 8.314616413659664e-05, "loss": 0.5552401542663574, "step": 321390 }, { "epoch": 1.9104683441220702, "grad_norm": 1.3463082313537598, "learning_rate": 8.314022297959112e-05, "loss": 0.5510271072387696, "step": 321400 }, { "epoch": 1.9105277861987386, "grad_norm": 1.4387589693069458, "learning_rate": 8.3134281951074e-05, "loss": 0.6053751945495606, "step": 321410 }, { "epoch": 1.910587228275407, "grad_norm": 1.3556442260742188, "learning_rate": 8.312834105107372e-05, "loss": 0.5565315246582031, "step": 321420 }, { "epoch": 1.9106466703520755, "grad_norm": 1.6309881210327148, "learning_rate": 8.312240027961866e-05, "loss": 0.5063494682312012, "step": 321430 }, { "epoch": 1.9107061124287439, "grad_norm": 1.189048409461975, "learning_rate": 8.311645963673725e-05, "loss": 0.5541629791259766, "step": 321440 }, { "epoch": 1.9107655545054123, "grad_norm": 1.7322889566421509, "learning_rate": 8.31105191224579e-05, "loss": 0.5052225112915039, "step": 321450 }, { "epoch": 1.9108249965820807, "grad_norm": 1.3468780517578125, "learning_rate": 8.310457873680905e-05, "loss": 0.5082620620727539, "step": 321460 }, { "epoch": 1.9108844386587491, "grad_norm": 1.9185429811477661, "learning_rate": 8.309863847981911e-05, "loss": 0.5421957969665527, "step": 321470 }, { "epoch": 1.9109438807354173, "grad_norm": 1.5930901765823364, "learning_rate": 8.309269835151649e-05, "loss": 0.5318828105926514, "step": 321480 }, { "epoch": 1.9110033228120857, "grad_norm": 1.3794162273406982, "learning_rate": 8.308675835192964e-05, "loss": 0.5341511726379394, "step": 321490 }, { "epoch": 1.9110627648887542, "grad_norm": 1.5061455965042114, "learning_rate": 8.308081848108686e-05, "loss": 0.5475123405456543, "step": 321500 }, { "epoch": 1.9111222069654226, "grad_norm": 1.7018241882324219, "learning_rate": 8.307487873901673e-05, "loss": 0.5623920917510986, "step": 321510 }, { "epoch": 1.911181649042091, "grad_norm": 1.6826529502868652, "learning_rate": 8.306893912574756e-05, "loss": 0.5274455547332764, "step": 321520 }, { "epoch": 1.9112410911187592, "grad_norm": 1.47339928150177, "learning_rate": 8.306299964130774e-05, "loss": 0.5501877784729003, "step": 321530 }, { "epoch": 1.9113005331954276, "grad_norm": 1.1448999643325806, "learning_rate": 8.30570602857258e-05, "loss": 0.5218218803405762, "step": 321540 }, { "epoch": 1.911359975272096, "grad_norm": 1.2012999057769775, "learning_rate": 8.305112105903003e-05, "loss": 0.5231698036193848, "step": 321550 }, { "epoch": 1.9114194173487644, "grad_norm": 1.5716029405593872, "learning_rate": 8.304518196124886e-05, "loss": 0.5586941719055176, "step": 321560 }, { "epoch": 1.9114788594254328, "grad_norm": 1.150010108947754, "learning_rate": 8.30392429924108e-05, "loss": 0.4800546646118164, "step": 321570 }, { "epoch": 1.9115383015021012, "grad_norm": 1.4571365118026733, "learning_rate": 8.303330415254418e-05, "loss": 0.5631083488464356, "step": 321580 }, { "epoch": 1.9115977435787697, "grad_norm": 1.4410866498947144, "learning_rate": 8.302736544167736e-05, "loss": 0.5791232109069824, "step": 321590 }, { "epoch": 1.911657185655438, "grad_norm": 1.514281153678894, "learning_rate": 8.302142685983887e-05, "loss": 0.5416189193725586, "step": 321600 }, { "epoch": 1.9117166277321065, "grad_norm": 1.5972281694412231, "learning_rate": 8.301548840705704e-05, "loss": 0.5498505592346191, "step": 321610 }, { "epoch": 1.911776069808775, "grad_norm": 1.4605768918991089, "learning_rate": 8.300955008336028e-05, "loss": 0.5435688018798828, "step": 321620 }, { "epoch": 1.9118355118854433, "grad_norm": 1.5469001531600952, "learning_rate": 8.300361188877701e-05, "loss": 0.5193537712097168, "step": 321630 }, { "epoch": 1.9118949539621117, "grad_norm": 1.2583519220352173, "learning_rate": 8.299767382333565e-05, "loss": 0.5248859405517579, "step": 321640 }, { "epoch": 1.9119543960387801, "grad_norm": 1.6036875247955322, "learning_rate": 8.299173588706461e-05, "loss": 0.4967185974121094, "step": 321650 }, { "epoch": 1.9120138381154486, "grad_norm": 1.7401823997497559, "learning_rate": 8.298579807999225e-05, "loss": 0.5659548759460449, "step": 321660 }, { "epoch": 1.9120732801921168, "grad_norm": 1.2804198265075684, "learning_rate": 8.297986040214702e-05, "loss": 0.5461910247802735, "step": 321670 }, { "epoch": 1.9121327222687852, "grad_norm": 1.3018180131912231, "learning_rate": 8.297392285355732e-05, "loss": 0.5621431350708008, "step": 321680 }, { "epoch": 1.9121921643454536, "grad_norm": 1.6291307210922241, "learning_rate": 8.29679854342515e-05, "loss": 0.529716682434082, "step": 321690 }, { "epoch": 1.912251606422122, "grad_norm": 1.6148440837860107, "learning_rate": 8.296204814425803e-05, "loss": 0.5635956764221192, "step": 321700 }, { "epoch": 1.9123110484987902, "grad_norm": 1.46254563331604, "learning_rate": 8.295611098360529e-05, "loss": 0.5484603881835938, "step": 321710 }, { "epoch": 1.9123704905754586, "grad_norm": 1.3477674722671509, "learning_rate": 8.295017395232167e-05, "loss": 0.5575457096099854, "step": 321720 }, { "epoch": 1.912429932652127, "grad_norm": 1.3439546823501587, "learning_rate": 8.294423705043557e-05, "loss": 0.5655030727386474, "step": 321730 }, { "epoch": 1.9124893747287954, "grad_norm": 1.3578712940216064, "learning_rate": 8.293830027797543e-05, "loss": 0.5358874797821045, "step": 321740 }, { "epoch": 1.9125488168054638, "grad_norm": 1.5921385288238525, "learning_rate": 8.293236363496959e-05, "loss": 0.5133681774139405, "step": 321750 }, { "epoch": 1.9126082588821323, "grad_norm": 1.5170443058013916, "learning_rate": 8.292642712144647e-05, "loss": 0.5432574272155761, "step": 321760 }, { "epoch": 1.9126677009588007, "grad_norm": 1.7022043466567993, "learning_rate": 8.292049073743449e-05, "loss": 0.5430037021636963, "step": 321770 }, { "epoch": 1.912727143035469, "grad_norm": 0.9434725046157837, "learning_rate": 8.291455448296204e-05, "loss": 0.5674750328063964, "step": 321780 }, { "epoch": 1.9127865851121375, "grad_norm": 1.5240309238433838, "learning_rate": 8.290861835805748e-05, "loss": 0.6089587211608887, "step": 321790 }, { "epoch": 1.912846027188806, "grad_norm": 1.6716278791427612, "learning_rate": 8.290268236274927e-05, "loss": 0.5839634895324707, "step": 321800 }, { "epoch": 1.9129054692654743, "grad_norm": 1.1834766864776611, "learning_rate": 8.289674649706576e-05, "loss": 0.5986619472503663, "step": 321810 }, { "epoch": 1.9129649113421427, "grad_norm": 1.4837688207626343, "learning_rate": 8.289081076103534e-05, "loss": 0.5356353759765625, "step": 321820 }, { "epoch": 1.9130243534188112, "grad_norm": 1.0396884679794312, "learning_rate": 8.288487515468643e-05, "loss": 0.5179545402526855, "step": 321830 }, { "epoch": 1.9130837954954796, "grad_norm": 1.1183143854141235, "learning_rate": 8.287893967804742e-05, "loss": 0.5348448753356934, "step": 321840 }, { "epoch": 1.9131432375721478, "grad_norm": 1.7453330755233765, "learning_rate": 8.287300433114673e-05, "loss": 0.5280357360839844, "step": 321850 }, { "epoch": 1.9132026796488162, "grad_norm": 1.0710986852645874, "learning_rate": 8.286706911401267e-05, "loss": 0.5198816776275634, "step": 321860 }, { "epoch": 1.9132621217254846, "grad_norm": 1.3361341953277588, "learning_rate": 8.28611340266737e-05, "loss": 0.5786675930023193, "step": 321870 }, { "epoch": 1.913321563802153, "grad_norm": 1.1827619075775146, "learning_rate": 8.285519906915822e-05, "loss": 0.5698708534240723, "step": 321880 }, { "epoch": 1.9133810058788214, "grad_norm": 1.0836780071258545, "learning_rate": 8.284926424149458e-05, "loss": 0.5163206100463867, "step": 321890 }, { "epoch": 1.9134404479554896, "grad_norm": 1.2966363430023193, "learning_rate": 8.284332954371119e-05, "loss": 0.5423711776733399, "step": 321900 }, { "epoch": 1.913499890032158, "grad_norm": 1.3977383375167847, "learning_rate": 8.283739497583643e-05, "loss": 0.5284573078155518, "step": 321910 }, { "epoch": 1.9135593321088264, "grad_norm": 1.1821261644363403, "learning_rate": 8.28314605378987e-05, "loss": 0.530291748046875, "step": 321920 }, { "epoch": 1.9136187741854949, "grad_norm": 1.4764785766601562, "learning_rate": 8.282552622992637e-05, "loss": 0.523862648010254, "step": 321930 }, { "epoch": 1.9136782162621633, "grad_norm": 1.12796151638031, "learning_rate": 8.281959205194787e-05, "loss": 0.5103973388671875, "step": 321940 }, { "epoch": 1.9137376583388317, "grad_norm": 1.8473591804504395, "learning_rate": 8.281365800399153e-05, "loss": 0.5558029174804687, "step": 321950 }, { "epoch": 1.9137971004155, "grad_norm": 1.6600151062011719, "learning_rate": 8.280772408608576e-05, "loss": 0.5329765796661377, "step": 321960 }, { "epoch": 1.9138565424921685, "grad_norm": 1.1125082969665527, "learning_rate": 8.280179029825899e-05, "loss": 0.5096145629882812, "step": 321970 }, { "epoch": 1.913915984568837, "grad_norm": 1.4618771076202393, "learning_rate": 8.279585664053959e-05, "loss": 0.5048633575439453, "step": 321980 }, { "epoch": 1.9139754266455054, "grad_norm": 1.6673201322555542, "learning_rate": 8.278992311295584e-05, "loss": 0.5066493034362793, "step": 321990 }, { "epoch": 1.9140348687221738, "grad_norm": 1.102085828781128, "learning_rate": 8.278398971553625e-05, "loss": 0.545347785949707, "step": 322000 }, { "epoch": 1.9140943107988422, "grad_norm": 1.4562209844589233, "learning_rate": 8.277805644830919e-05, "loss": 0.5297647953033447, "step": 322010 }, { "epoch": 1.9141537528755106, "grad_norm": 1.465692162513733, "learning_rate": 8.277212331130291e-05, "loss": 0.5213834762573242, "step": 322020 }, { "epoch": 1.914213194952179, "grad_norm": 1.120741605758667, "learning_rate": 8.276619030454598e-05, "loss": 0.5692148685455323, "step": 322030 }, { "epoch": 1.9142726370288472, "grad_norm": 1.4501945972442627, "learning_rate": 8.27602574280667e-05, "loss": 0.5342914581298828, "step": 322040 }, { "epoch": 1.9143320791055156, "grad_norm": 1.4364876747131348, "learning_rate": 8.275432468189339e-05, "loss": 0.5837449550628662, "step": 322050 }, { "epoch": 1.914391521182184, "grad_norm": 1.0693005323410034, "learning_rate": 8.274839206605451e-05, "loss": 0.5327693939208984, "step": 322060 }, { "epoch": 1.9144509632588524, "grad_norm": 2.0907211303710938, "learning_rate": 8.274245958057844e-05, "loss": 0.5884735107421875, "step": 322070 }, { "epoch": 1.9145104053355206, "grad_norm": 1.4201875925064087, "learning_rate": 8.27365272254935e-05, "loss": 0.5138384819030761, "step": 322080 }, { "epoch": 1.914569847412189, "grad_norm": 1.258758544921875, "learning_rate": 8.273059500082814e-05, "loss": 0.5471667766571044, "step": 322090 }, { "epoch": 1.9146292894888575, "grad_norm": 1.0996286869049072, "learning_rate": 8.27246629066107e-05, "loss": 0.52975435256958, "step": 322100 }, { "epoch": 1.9146887315655259, "grad_norm": 1.1616778373718262, "learning_rate": 8.271873094286955e-05, "loss": 0.49705052375793457, "step": 322110 }, { "epoch": 1.9147481736421943, "grad_norm": 1.3903207778930664, "learning_rate": 8.271279910963303e-05, "loss": 0.5365120887756347, "step": 322120 }, { "epoch": 1.9148076157188627, "grad_norm": 1.810788869857788, "learning_rate": 8.270686740692964e-05, "loss": 0.5318887233734131, "step": 322130 }, { "epoch": 1.9148670577955311, "grad_norm": 1.55863356590271, "learning_rate": 8.270093583478764e-05, "loss": 0.5081852912902832, "step": 322140 }, { "epoch": 1.9149264998721995, "grad_norm": 1.8721492290496826, "learning_rate": 8.26950043932354e-05, "loss": 0.5484529972076416, "step": 322150 }, { "epoch": 1.914985941948868, "grad_norm": 1.4982374906539917, "learning_rate": 8.268907308230141e-05, "loss": 0.5039937496185303, "step": 322160 }, { "epoch": 1.9150453840255364, "grad_norm": 1.3146833181381226, "learning_rate": 8.268314190201394e-05, "loss": 0.5683075428009033, "step": 322170 }, { "epoch": 1.9151048261022048, "grad_norm": 1.4297744035720825, "learning_rate": 8.267721085240137e-05, "loss": 0.490401029586792, "step": 322180 }, { "epoch": 1.9151642681788732, "grad_norm": 1.4122822284698486, "learning_rate": 8.267127993349211e-05, "loss": 0.5659977436065674, "step": 322190 }, { "epoch": 1.9152237102555416, "grad_norm": 1.6414920091629028, "learning_rate": 8.266534914531452e-05, "loss": 0.5856922626495361, "step": 322200 }, { "epoch": 1.91528315233221, "grad_norm": 1.5889579057693481, "learning_rate": 8.265941848789697e-05, "loss": 0.5582942008972168, "step": 322210 }, { "epoch": 1.9153425944088782, "grad_norm": 1.3644723892211914, "learning_rate": 8.265348796126781e-05, "loss": 0.5160629272460937, "step": 322220 }, { "epoch": 1.9154020364855466, "grad_norm": 1.5060640573501587, "learning_rate": 8.264755756545543e-05, "loss": 0.5435914039611817, "step": 322230 }, { "epoch": 1.915461478562215, "grad_norm": 1.425414800643921, "learning_rate": 8.264162730048823e-05, "loss": 0.5782541275024414, "step": 322240 }, { "epoch": 1.9155209206388835, "grad_norm": 1.337283730506897, "learning_rate": 8.263569716639448e-05, "loss": 0.5730055809020996, "step": 322250 }, { "epoch": 1.9155803627155519, "grad_norm": 1.3359335660934448, "learning_rate": 8.262976716320266e-05, "loss": 0.5201470375061035, "step": 322260 }, { "epoch": 1.91563980479222, "grad_norm": 1.282943844795227, "learning_rate": 8.26238372909411e-05, "loss": 0.5590899467468262, "step": 322270 }, { "epoch": 1.9156992468688885, "grad_norm": 1.3537167310714722, "learning_rate": 8.261790754963811e-05, "loss": 0.588005256652832, "step": 322280 }, { "epoch": 1.915758688945557, "grad_norm": 1.2916382551193237, "learning_rate": 8.261197793932212e-05, "loss": 0.5619514465332032, "step": 322290 }, { "epoch": 1.9158181310222253, "grad_norm": 0.9574856162071228, "learning_rate": 8.260604846002149e-05, "loss": 0.6109678268432617, "step": 322300 }, { "epoch": 1.9158775730988937, "grad_norm": 1.5126198530197144, "learning_rate": 8.260011911176455e-05, "loss": 0.5747546195983887, "step": 322310 }, { "epoch": 1.9159370151755621, "grad_norm": 1.371701717376709, "learning_rate": 8.25941898945797e-05, "loss": 0.5376143455505371, "step": 322320 }, { "epoch": 1.9159964572522306, "grad_norm": 1.5938217639923096, "learning_rate": 8.258826080849531e-05, "loss": 0.5614530563354492, "step": 322330 }, { "epoch": 1.916055899328899, "grad_norm": 1.350127935409546, "learning_rate": 8.25823318535397e-05, "loss": 0.5097361087799073, "step": 322340 }, { "epoch": 1.9161153414055674, "grad_norm": 1.6821725368499756, "learning_rate": 8.257640302974123e-05, "loss": 0.5598621368408203, "step": 322350 }, { "epoch": 1.9161747834822358, "grad_norm": 1.5527392625808716, "learning_rate": 8.257047433712832e-05, "loss": 0.5526660919189453, "step": 322360 }, { "epoch": 1.9162342255589042, "grad_norm": 1.6162171363830566, "learning_rate": 8.25645457757293e-05, "loss": 0.5129611968994141, "step": 322370 }, { "epoch": 1.9162936676355726, "grad_norm": 1.0608798265457153, "learning_rate": 8.255861734557248e-05, "loss": 0.5141525268554688, "step": 322380 }, { "epoch": 1.916353109712241, "grad_norm": 1.8773342370986938, "learning_rate": 8.255268904668632e-05, "loss": 0.5644135475158691, "step": 322390 }, { "epoch": 1.9164125517889095, "grad_norm": 1.7855467796325684, "learning_rate": 8.254676087909911e-05, "loss": 0.6065946578979492, "step": 322400 }, { "epoch": 1.9164719938655776, "grad_norm": 1.3458961248397827, "learning_rate": 8.254083284283923e-05, "loss": 0.48684191703796387, "step": 322410 }, { "epoch": 1.916531435942246, "grad_norm": 1.4095202684402466, "learning_rate": 8.2534904937935e-05, "loss": 0.5319849491119385, "step": 322420 }, { "epoch": 1.9165908780189145, "grad_norm": 1.2538962364196777, "learning_rate": 8.252897716441486e-05, "loss": 0.5365155220031739, "step": 322430 }, { "epoch": 1.916650320095583, "grad_norm": 1.1149942874908447, "learning_rate": 8.252304952230707e-05, "loss": 0.5561393737792969, "step": 322440 }, { "epoch": 1.916709762172251, "grad_norm": 1.414351463317871, "learning_rate": 8.251712201164006e-05, "loss": 0.5129037380218506, "step": 322450 }, { "epoch": 1.9167692042489195, "grad_norm": 1.4218165874481201, "learning_rate": 8.251119463244214e-05, "loss": 0.5846413612365723, "step": 322460 }, { "epoch": 1.916828646325588, "grad_norm": 1.2436786890029907, "learning_rate": 8.250526738474172e-05, "loss": 0.5033249855041504, "step": 322470 }, { "epoch": 1.9168880884022563, "grad_norm": 1.3768078088760376, "learning_rate": 8.249934026856705e-05, "loss": 0.571631908416748, "step": 322480 }, { "epoch": 1.9169475304789247, "grad_norm": 1.2128536701202393, "learning_rate": 8.249341328394657e-05, "loss": 0.5322541236877442, "step": 322490 }, { "epoch": 1.9170069725555932, "grad_norm": 1.4504170417785645, "learning_rate": 8.248748643090864e-05, "loss": 0.5393082141876221, "step": 322500 }, { "epoch": 1.9170664146322616, "grad_norm": 1.4830378293991089, "learning_rate": 8.248155970948155e-05, "loss": 0.5480334281921386, "step": 322510 }, { "epoch": 1.91712585670893, "grad_norm": 1.5396571159362793, "learning_rate": 8.24756331196937e-05, "loss": 0.546565055847168, "step": 322520 }, { "epoch": 1.9171852987855984, "grad_norm": 1.6001147031784058, "learning_rate": 8.246970666157345e-05, "loss": 0.5715274333953857, "step": 322530 }, { "epoch": 1.9172447408622668, "grad_norm": 1.153360366821289, "learning_rate": 8.246378033514908e-05, "loss": 0.5093017578125, "step": 322540 }, { "epoch": 1.9173041829389352, "grad_norm": 1.2803698778152466, "learning_rate": 8.245785414044902e-05, "loss": 0.5545292854309082, "step": 322550 }, { "epoch": 1.9173636250156036, "grad_norm": 1.0631606578826904, "learning_rate": 8.24519280775016e-05, "loss": 0.5560412406921387, "step": 322560 }, { "epoch": 1.917423067092272, "grad_norm": 1.2808457612991333, "learning_rate": 8.244600214633513e-05, "loss": 0.5204689025878906, "step": 322570 }, { "epoch": 1.9174825091689405, "grad_norm": 1.0313631296157837, "learning_rate": 8.244007634697795e-05, "loss": 0.5092292785644531, "step": 322580 }, { "epoch": 1.9175419512456087, "grad_norm": 1.5175124406814575, "learning_rate": 8.24341506794585e-05, "loss": 0.6296700477600098, "step": 322590 }, { "epoch": 1.917601393322277, "grad_norm": 1.6707333326339722, "learning_rate": 8.242822514380504e-05, "loss": 0.5569282531738281, "step": 322600 }, { "epoch": 1.9176608353989455, "grad_norm": 1.2955683469772339, "learning_rate": 8.24222997400459e-05, "loss": 0.5065211296081543, "step": 322610 }, { "epoch": 1.917720277475614, "grad_norm": 1.1130032539367676, "learning_rate": 8.241637446820951e-05, "loss": 0.535129451751709, "step": 322620 }, { "epoch": 1.9177797195522823, "grad_norm": 1.5829894542694092, "learning_rate": 8.241044932832416e-05, "loss": 0.5257376670837403, "step": 322630 }, { "epoch": 1.9178391616289505, "grad_norm": 1.6923680305480957, "learning_rate": 8.240452432041818e-05, "loss": 0.5679245948791504, "step": 322640 }, { "epoch": 1.917898603705619, "grad_norm": 1.1248974800109863, "learning_rate": 8.239859944451997e-05, "loss": 0.5409358024597168, "step": 322650 }, { "epoch": 1.9179580457822873, "grad_norm": 1.434827446937561, "learning_rate": 8.239267470065783e-05, "loss": 0.495195198059082, "step": 322660 }, { "epoch": 1.9180174878589558, "grad_norm": 1.3305466175079346, "learning_rate": 8.23867500888601e-05, "loss": 0.5714277267456055, "step": 322670 }, { "epoch": 1.9180769299356242, "grad_norm": 1.5227952003479004, "learning_rate": 8.238082560915516e-05, "loss": 0.49396495819091796, "step": 322680 }, { "epoch": 1.9181363720122926, "grad_norm": 1.3360613584518433, "learning_rate": 8.237490126157131e-05, "loss": 0.5806398391723633, "step": 322690 }, { "epoch": 1.918195814088961, "grad_norm": 1.3301923274993896, "learning_rate": 8.23689770461369e-05, "loss": 0.5260957717895508, "step": 322700 }, { "epoch": 1.9182552561656294, "grad_norm": 1.3524694442749023, "learning_rate": 8.23630529628803e-05, "loss": 0.5332856178283691, "step": 322710 }, { "epoch": 1.9183146982422978, "grad_norm": 1.5479711294174194, "learning_rate": 8.23571290118298e-05, "loss": 0.5633597373962402, "step": 322720 }, { "epoch": 1.9183741403189662, "grad_norm": 1.329269528388977, "learning_rate": 8.235120519301376e-05, "loss": 0.5670366764068604, "step": 322730 }, { "epoch": 1.9184335823956347, "grad_norm": 1.7130950689315796, "learning_rate": 8.23452815064605e-05, "loss": 0.5615322113037109, "step": 322740 }, { "epoch": 1.918493024472303, "grad_norm": 1.1574296951293945, "learning_rate": 8.23393579521984e-05, "loss": 0.5577002048492432, "step": 322750 }, { "epoch": 1.9185524665489715, "grad_norm": 1.2104946374893188, "learning_rate": 8.233343453025577e-05, "loss": 0.5274305820465088, "step": 322760 }, { "epoch": 1.91861190862564, "grad_norm": 1.5830758810043335, "learning_rate": 8.232751124066094e-05, "loss": 0.547937536239624, "step": 322770 }, { "epoch": 1.918671350702308, "grad_norm": 1.1104779243469238, "learning_rate": 8.232158808344225e-05, "loss": 0.6084259033203125, "step": 322780 }, { "epoch": 1.9187307927789765, "grad_norm": 1.5478651523590088, "learning_rate": 8.231566505862807e-05, "loss": 0.5234623432159424, "step": 322790 }, { "epoch": 1.918790234855645, "grad_norm": 1.4196404218673706, "learning_rate": 8.230974216624665e-05, "loss": 0.472017765045166, "step": 322800 }, { "epoch": 1.9188496769323133, "grad_norm": 1.556421160697937, "learning_rate": 8.230381940632642e-05, "loss": 0.571960735321045, "step": 322810 }, { "epoch": 1.9189091190089815, "grad_norm": 1.3924899101257324, "learning_rate": 8.229789677889564e-05, "loss": 0.5426712989807129, "step": 322820 }, { "epoch": 1.91896856108565, "grad_norm": 1.544183611869812, "learning_rate": 8.229197428398268e-05, "loss": 0.5367954254150391, "step": 322830 }, { "epoch": 1.9190280031623184, "grad_norm": 1.535697102546692, "learning_rate": 8.228605192161584e-05, "loss": 0.5470522403717041, "step": 322840 }, { "epoch": 1.9190874452389868, "grad_norm": 1.2125478982925415, "learning_rate": 8.22801296918235e-05, "loss": 0.5201502323150635, "step": 322850 }, { "epoch": 1.9191468873156552, "grad_norm": 1.370539903640747, "learning_rate": 8.227420759463395e-05, "loss": 0.5429969787597656, "step": 322860 }, { "epoch": 1.9192063293923236, "grad_norm": 1.3923166990280151, "learning_rate": 8.226828563007552e-05, "loss": 0.5813905715942382, "step": 322870 }, { "epoch": 1.919265771468992, "grad_norm": 1.3377043008804321, "learning_rate": 8.226236379817655e-05, "loss": 0.5548021793365479, "step": 322880 }, { "epoch": 1.9193252135456604, "grad_norm": 1.5484217405319214, "learning_rate": 8.22564420989654e-05, "loss": 0.533182430267334, "step": 322890 }, { "epoch": 1.9193846556223289, "grad_norm": 0.9496123790740967, "learning_rate": 8.225052053247031e-05, "loss": 0.49509243965148925, "step": 322900 }, { "epoch": 1.9194440976989973, "grad_norm": 1.3922518491744995, "learning_rate": 8.224459909871968e-05, "loss": 0.5345105171203614, "step": 322910 }, { "epoch": 1.9195035397756657, "grad_norm": 1.4369970560073853, "learning_rate": 8.223867779774184e-05, "loss": 0.5328512191772461, "step": 322920 }, { "epoch": 1.919562981852334, "grad_norm": 1.6683388948440552, "learning_rate": 8.223275662956507e-05, "loss": 0.5437801837921142, "step": 322930 }, { "epoch": 1.9196224239290025, "grad_norm": 1.2780358791351318, "learning_rate": 8.222683559421773e-05, "loss": 0.6014659404754639, "step": 322940 }, { "epoch": 1.919681866005671, "grad_norm": 1.4402815103530884, "learning_rate": 8.222091469172812e-05, "loss": 0.5079696178436279, "step": 322950 }, { "epoch": 1.9197413080823391, "grad_norm": 1.495012640953064, "learning_rate": 8.221499392212461e-05, "loss": 0.5137763977050781, "step": 322960 }, { "epoch": 1.9198007501590075, "grad_norm": 1.3525031805038452, "learning_rate": 8.220907328543543e-05, "loss": 0.5301566123962402, "step": 322970 }, { "epoch": 1.919860192235676, "grad_norm": 1.5587528944015503, "learning_rate": 8.220315278168899e-05, "loss": 0.5452227115631103, "step": 322980 }, { "epoch": 1.9199196343123444, "grad_norm": 1.1997332572937012, "learning_rate": 8.219723241091363e-05, "loss": 0.5354745864868165, "step": 322990 }, { "epoch": 1.9199790763890128, "grad_norm": 1.308671236038208, "learning_rate": 8.219131217313756e-05, "loss": 0.6013003349304199, "step": 323000 }, { "epoch": 1.920038518465681, "grad_norm": 2.1508138179779053, "learning_rate": 8.218539206838917e-05, "loss": 0.5625591278076172, "step": 323010 }, { "epoch": 1.9200979605423494, "grad_norm": 1.4812220335006714, "learning_rate": 8.217947209669683e-05, "loss": 0.6043404579162598, "step": 323020 }, { "epoch": 1.9201574026190178, "grad_norm": 1.4170260429382324, "learning_rate": 8.217355225808872e-05, "loss": 0.5766811370849609, "step": 323030 }, { "epoch": 1.9202168446956862, "grad_norm": 1.4250096082687378, "learning_rate": 8.21676325525933e-05, "loss": 0.5546219825744629, "step": 323040 }, { "epoch": 1.9202762867723546, "grad_norm": 1.2221968173980713, "learning_rate": 8.216171298023884e-05, "loss": 0.5332509994506835, "step": 323050 }, { "epoch": 1.920335728849023, "grad_norm": 1.3233973979949951, "learning_rate": 8.215579354105363e-05, "loss": 0.532684326171875, "step": 323060 }, { "epoch": 1.9203951709256915, "grad_norm": 1.7729021310806274, "learning_rate": 8.214987423506597e-05, "loss": 0.5486117362976074, "step": 323070 }, { "epoch": 1.9204546130023599, "grad_norm": 0.9350858926773071, "learning_rate": 8.214395506230426e-05, "loss": 0.542569923400879, "step": 323080 }, { "epoch": 1.9205140550790283, "grad_norm": 1.491786241531372, "learning_rate": 8.213803602279673e-05, "loss": 0.5025924682617188, "step": 323090 }, { "epoch": 1.9205734971556967, "grad_norm": 1.317546010017395, "learning_rate": 8.213211711657174e-05, "loss": 0.5582515716552734, "step": 323100 }, { "epoch": 1.920632939232365, "grad_norm": 1.6554718017578125, "learning_rate": 8.21261983436576e-05, "loss": 0.5372897148132324, "step": 323110 }, { "epoch": 1.9206923813090335, "grad_norm": 1.4197394847869873, "learning_rate": 8.212027970408263e-05, "loss": 0.5571401596069336, "step": 323120 }, { "epoch": 1.920751823385702, "grad_norm": 1.3030339479446411, "learning_rate": 8.211436119787508e-05, "loss": 0.5281707286834717, "step": 323130 }, { "epoch": 1.9208112654623704, "grad_norm": 1.4340994358062744, "learning_rate": 8.210844282506338e-05, "loss": 0.4813815116882324, "step": 323140 }, { "epoch": 1.9208707075390385, "grad_norm": 1.2119816541671753, "learning_rate": 8.210252458567576e-05, "loss": 0.5267938613891602, "step": 323150 }, { "epoch": 1.920930149615707, "grad_norm": 1.0052471160888672, "learning_rate": 8.209660647974049e-05, "loss": 0.4683688163757324, "step": 323160 }, { "epoch": 1.9209895916923754, "grad_norm": 1.4220784902572632, "learning_rate": 8.209068850728601e-05, "loss": 0.5336369037628174, "step": 323170 }, { "epoch": 1.9210490337690438, "grad_norm": 1.3795106410980225, "learning_rate": 8.20847706683405e-05, "loss": 0.5021197319030761, "step": 323180 }, { "epoch": 1.921108475845712, "grad_norm": 1.3153005838394165, "learning_rate": 8.207885296293236e-05, "loss": 0.5228058815002441, "step": 323190 }, { "epoch": 1.9211679179223804, "grad_norm": 1.2774653434753418, "learning_rate": 8.207293539108982e-05, "loss": 0.48591814041137693, "step": 323200 }, { "epoch": 1.9212273599990488, "grad_norm": 1.247030258178711, "learning_rate": 8.206701795284128e-05, "loss": 0.5400117874145508, "step": 323210 }, { "epoch": 1.9212868020757172, "grad_norm": 1.6897966861724854, "learning_rate": 8.206110064821497e-05, "loss": 0.5658602714538574, "step": 323220 }, { "epoch": 1.9213462441523856, "grad_norm": 1.3158453702926636, "learning_rate": 8.205518347723923e-05, "loss": 0.5445484161376953, "step": 323230 }, { "epoch": 1.921405686229054, "grad_norm": 1.631949543952942, "learning_rate": 8.204926643994235e-05, "loss": 0.5747273921966553, "step": 323240 }, { "epoch": 1.9214651283057225, "grad_norm": 1.5923150777816772, "learning_rate": 8.204334953635266e-05, "loss": 0.5386865615844727, "step": 323250 }, { "epoch": 1.9215245703823909, "grad_norm": 1.5626821517944336, "learning_rate": 8.203743276649845e-05, "loss": 0.5800820827484131, "step": 323260 }, { "epoch": 1.9215840124590593, "grad_norm": 1.3451186418533325, "learning_rate": 8.2031516130408e-05, "loss": 0.49573965072631837, "step": 323270 }, { "epoch": 1.9216434545357277, "grad_norm": 1.7108798027038574, "learning_rate": 8.202559962810967e-05, "loss": 0.5693234443664551, "step": 323280 }, { "epoch": 1.9217028966123961, "grad_norm": 1.1231802701950073, "learning_rate": 8.20196832596317e-05, "loss": 0.5513782024383544, "step": 323290 }, { "epoch": 1.9217623386890645, "grad_norm": 1.1365435123443604, "learning_rate": 8.201376702500245e-05, "loss": 0.5853680610656739, "step": 323300 }, { "epoch": 1.921821780765733, "grad_norm": 1.7113343477249146, "learning_rate": 8.200785092425019e-05, "loss": 0.5223217964172363, "step": 323310 }, { "epoch": 1.9218812228424014, "grad_norm": 1.5986554622650146, "learning_rate": 8.200193495740318e-05, "loss": 0.5385607719421387, "step": 323320 }, { "epoch": 1.9219406649190696, "grad_norm": 1.8035017251968384, "learning_rate": 8.19960191244898e-05, "loss": 0.5746330261230469, "step": 323330 }, { "epoch": 1.922000106995738, "grad_norm": 1.0513437986373901, "learning_rate": 8.19901034255383e-05, "loss": 0.5163107872009277, "step": 323340 }, { "epoch": 1.9220595490724064, "grad_norm": 1.3840817213058472, "learning_rate": 8.198418786057702e-05, "loss": 0.48804759979248047, "step": 323350 }, { "epoch": 1.9221189911490748, "grad_norm": 1.4415509700775146, "learning_rate": 8.197827242963418e-05, "loss": 0.507169771194458, "step": 323360 }, { "epoch": 1.9221784332257432, "grad_norm": 1.2636547088623047, "learning_rate": 8.197235713273817e-05, "loss": 0.6196801662445068, "step": 323370 }, { "epoch": 1.9222378753024114, "grad_norm": 1.3931454420089722, "learning_rate": 8.196644196991723e-05, "loss": 0.5392598628997802, "step": 323380 }, { "epoch": 1.9222973173790798, "grad_norm": 1.2223570346832275, "learning_rate": 8.196052694119964e-05, "loss": 0.5047118186950683, "step": 323390 }, { "epoch": 1.9223567594557482, "grad_norm": 1.5490459203720093, "learning_rate": 8.195461204661377e-05, "loss": 0.5591477394104004, "step": 323400 }, { "epoch": 1.9224162015324167, "grad_norm": 1.3227354288101196, "learning_rate": 8.194869728618786e-05, "loss": 0.5395345687866211, "step": 323410 }, { "epoch": 1.922475643609085, "grad_norm": 1.5011653900146484, "learning_rate": 8.194278265995019e-05, "loss": 0.5653035640716553, "step": 323420 }, { "epoch": 1.9225350856857535, "grad_norm": 1.3050073385238647, "learning_rate": 8.193686816792912e-05, "loss": 0.5277975082397461, "step": 323430 }, { "epoch": 1.922594527762422, "grad_norm": 1.4646271467208862, "learning_rate": 8.193095381015287e-05, "loss": 0.58779935836792, "step": 323440 }, { "epoch": 1.9226539698390903, "grad_norm": 1.3035565614700317, "learning_rate": 8.19250395866498e-05, "loss": 0.5412895202636718, "step": 323450 }, { "epoch": 1.9227134119157587, "grad_norm": 1.2749806642532349, "learning_rate": 8.191912549744811e-05, "loss": 0.48889727592468263, "step": 323460 }, { "epoch": 1.9227728539924271, "grad_norm": 1.384688377380371, "learning_rate": 8.191321154257617e-05, "loss": 0.5169407367706299, "step": 323470 }, { "epoch": 1.9228322960690956, "grad_norm": 1.17671799659729, "learning_rate": 8.190729772206227e-05, "loss": 0.5433677673339844, "step": 323480 }, { "epoch": 1.922891738145764, "grad_norm": 1.1764743328094482, "learning_rate": 8.190138403593463e-05, "loss": 0.5141595840454102, "step": 323490 }, { "epoch": 1.9229511802224324, "grad_norm": 1.3210824728012085, "learning_rate": 8.189547048422164e-05, "loss": 0.5304289340972901, "step": 323500 }, { "epoch": 1.9230106222991008, "grad_norm": 1.1029802560806274, "learning_rate": 8.188955706695152e-05, "loss": 0.5207148551940918, "step": 323510 }, { "epoch": 1.923070064375769, "grad_norm": 0.9483521580696106, "learning_rate": 8.188364378415254e-05, "loss": 0.5890241146087647, "step": 323520 }, { "epoch": 1.9231295064524374, "grad_norm": 1.399810791015625, "learning_rate": 8.187773063585305e-05, "loss": 0.5505022048950196, "step": 323530 }, { "epoch": 1.9231889485291058, "grad_norm": 1.4666067361831665, "learning_rate": 8.187181762208129e-05, "loss": 0.5145548820495606, "step": 323540 }, { "epoch": 1.9232483906057742, "grad_norm": 1.502866268157959, "learning_rate": 8.186590474286562e-05, "loss": 0.5313484191894531, "step": 323550 }, { "epoch": 1.9233078326824424, "grad_norm": 1.3207184076309204, "learning_rate": 8.185999199823417e-05, "loss": 0.5650762557983399, "step": 323560 }, { "epoch": 1.9233672747591108, "grad_norm": 1.315933108329773, "learning_rate": 8.185407938821538e-05, "loss": 0.5483242511749268, "step": 323570 }, { "epoch": 1.9234267168357793, "grad_norm": 1.375685214996338, "learning_rate": 8.184816691283748e-05, "loss": 0.5172520637512207, "step": 323580 }, { "epoch": 1.9234861589124477, "grad_norm": 1.3747807741165161, "learning_rate": 8.184225457212871e-05, "loss": 0.5315857887268066, "step": 323590 }, { "epoch": 1.923545600989116, "grad_norm": 1.2436542510986328, "learning_rate": 8.183634236611745e-05, "loss": 0.5709212303161622, "step": 323600 }, { "epoch": 1.9236050430657845, "grad_norm": 1.5040537118911743, "learning_rate": 8.183043029483188e-05, "loss": 0.5662016868591309, "step": 323610 }, { "epoch": 1.923664485142453, "grad_norm": 1.3615626096725464, "learning_rate": 8.182451835830032e-05, "loss": 0.5206829071044922, "step": 323620 }, { "epoch": 1.9237239272191213, "grad_norm": 1.689404010772705, "learning_rate": 8.181860655655109e-05, "loss": 0.5884079456329345, "step": 323630 }, { "epoch": 1.9237833692957897, "grad_norm": 1.2392239570617676, "learning_rate": 8.181269488961243e-05, "loss": 0.5018141746520997, "step": 323640 }, { "epoch": 1.9238428113724582, "grad_norm": 1.335350513458252, "learning_rate": 8.180678335751257e-05, "loss": 0.5445386886596679, "step": 323650 }, { "epoch": 1.9239022534491266, "grad_norm": 1.4438284635543823, "learning_rate": 8.180087196027992e-05, "loss": 0.5556107521057129, "step": 323660 }, { "epoch": 1.923961695525795, "grad_norm": 1.2689439058303833, "learning_rate": 8.179496069794266e-05, "loss": 0.5013575553894043, "step": 323670 }, { "epoch": 1.9240211376024634, "grad_norm": 1.7188178300857544, "learning_rate": 8.178904957052909e-05, "loss": 0.6082139492034913, "step": 323680 }, { "epoch": 1.9240805796791318, "grad_norm": 1.595197081565857, "learning_rate": 8.178313857806748e-05, "loss": 0.5719061374664307, "step": 323690 }, { "epoch": 1.9241400217558, "grad_norm": 1.4681369066238403, "learning_rate": 8.177722772058611e-05, "loss": 0.5364676952362061, "step": 323700 }, { "epoch": 1.9241994638324684, "grad_norm": 1.5386326313018799, "learning_rate": 8.177131699811327e-05, "loss": 0.5324328422546387, "step": 323710 }, { "epoch": 1.9242589059091368, "grad_norm": 1.5612330436706543, "learning_rate": 8.176540641067721e-05, "loss": 0.5121861934661865, "step": 323720 }, { "epoch": 1.9243183479858053, "grad_norm": 1.4411081075668335, "learning_rate": 8.175949595830623e-05, "loss": 0.561518669128418, "step": 323730 }, { "epoch": 1.9243777900624737, "grad_norm": 1.347112774848938, "learning_rate": 8.17535856410286e-05, "loss": 0.47925806045532227, "step": 323740 }, { "epoch": 1.9244372321391419, "grad_norm": 1.309526801109314, "learning_rate": 8.174767545887257e-05, "loss": 0.5412393569946289, "step": 323750 }, { "epoch": 1.9244966742158103, "grad_norm": 1.3687713146209717, "learning_rate": 8.174176541186642e-05, "loss": 0.5487501621246338, "step": 323760 }, { "epoch": 1.9245561162924787, "grad_norm": 1.7456741333007812, "learning_rate": 8.173585550003843e-05, "loss": 0.5467406272888183, "step": 323770 }, { "epoch": 1.924615558369147, "grad_norm": 1.3763949871063232, "learning_rate": 8.172994572341687e-05, "loss": 0.5212504386901855, "step": 323780 }, { "epoch": 1.9246750004458155, "grad_norm": 1.57952880859375, "learning_rate": 8.172403608203003e-05, "loss": 0.5293274879455566, "step": 323790 }, { "epoch": 1.924734442522484, "grad_norm": 1.4798024892807007, "learning_rate": 8.171812657590619e-05, "loss": 0.5370491981506348, "step": 323800 }, { "epoch": 1.9247938845991523, "grad_norm": 1.0852879285812378, "learning_rate": 8.171221720507354e-05, "loss": 0.496766471862793, "step": 323810 }, { "epoch": 1.9248533266758208, "grad_norm": 1.0616263151168823, "learning_rate": 8.17063079695604e-05, "loss": 0.5148762226104736, "step": 323820 }, { "epoch": 1.9249127687524892, "grad_norm": 1.6895530223846436, "learning_rate": 8.170039886939504e-05, "loss": 0.5246830940246582, "step": 323830 }, { "epoch": 1.9249722108291576, "grad_norm": 1.2398350238800049, "learning_rate": 8.169448990460575e-05, "loss": 0.5418299674987793, "step": 323840 }, { "epoch": 1.925031652905826, "grad_norm": 1.7194240093231201, "learning_rate": 8.168858107522074e-05, "loss": 0.501123046875, "step": 323850 }, { "epoch": 1.9250910949824944, "grad_norm": 1.3364298343658447, "learning_rate": 8.168267238126832e-05, "loss": 0.48851728439331055, "step": 323860 }, { "epoch": 1.9251505370591628, "grad_norm": 1.4282920360565186, "learning_rate": 8.167676382277675e-05, "loss": 0.5436242580413818, "step": 323870 }, { "epoch": 1.9252099791358313, "grad_norm": 1.705328345298767, "learning_rate": 8.167085539977426e-05, "loss": 0.5774467468261719, "step": 323880 }, { "epoch": 1.9252694212124994, "grad_norm": 1.5590134859085083, "learning_rate": 8.166494711228916e-05, "loss": 0.5405930519104004, "step": 323890 }, { "epoch": 1.9253288632891679, "grad_norm": 1.4190771579742432, "learning_rate": 8.16590389603497e-05, "loss": 0.5398072719573974, "step": 323900 }, { "epoch": 1.9253883053658363, "grad_norm": 1.0371731519699097, "learning_rate": 8.165313094398413e-05, "loss": 0.5203642845153809, "step": 323910 }, { "epoch": 1.9254477474425047, "grad_norm": 2.003331422805786, "learning_rate": 8.164722306322069e-05, "loss": 0.48743305206298826, "step": 323920 }, { "epoch": 1.9255071895191729, "grad_norm": 1.7382782697677612, "learning_rate": 8.16413153180877e-05, "loss": 0.5621705532073975, "step": 323930 }, { "epoch": 1.9255666315958413, "grad_norm": 1.172716498374939, "learning_rate": 8.163540770861337e-05, "loss": 0.5312528133392334, "step": 323940 }, { "epoch": 1.9256260736725097, "grad_norm": 1.2613465785980225, "learning_rate": 8.162950023482599e-05, "loss": 0.501154613494873, "step": 323950 }, { "epoch": 1.9256855157491781, "grad_norm": 1.5535609722137451, "learning_rate": 8.162359289675382e-05, "loss": 0.5585898399353028, "step": 323960 }, { "epoch": 1.9257449578258465, "grad_norm": 1.2825990915298462, "learning_rate": 8.16176856944251e-05, "loss": 0.5736087322235107, "step": 323970 }, { "epoch": 1.925804399902515, "grad_norm": 1.140542984008789, "learning_rate": 8.161177862786806e-05, "loss": 0.4935967445373535, "step": 323980 }, { "epoch": 1.9258638419791834, "grad_norm": 1.2451504468917847, "learning_rate": 8.160587169711105e-05, "loss": 0.5032936096191406, "step": 323990 }, { "epoch": 1.9259232840558518, "grad_norm": 1.589860439300537, "learning_rate": 8.159996490218225e-05, "loss": 0.5274033546447754, "step": 324000 }, { "epoch": 1.9259827261325202, "grad_norm": 1.565442442893982, "learning_rate": 8.159405824310993e-05, "loss": 0.531820821762085, "step": 324010 }, { "epoch": 1.9260421682091886, "grad_norm": 1.5678516626358032, "learning_rate": 8.158815171992236e-05, "loss": 0.571111536026001, "step": 324020 }, { "epoch": 1.926101610285857, "grad_norm": 1.1942189931869507, "learning_rate": 8.158224533264777e-05, "loss": 0.4663810729980469, "step": 324030 }, { "epoch": 1.9261610523625254, "grad_norm": 1.3107638359069824, "learning_rate": 8.157633908131448e-05, "loss": 0.5720390319824219, "step": 324040 }, { "epoch": 1.9262204944391939, "grad_norm": 1.3995287418365479, "learning_rate": 8.157043296595061e-05, "loss": 0.5382984161376954, "step": 324050 }, { "epoch": 1.9262799365158623, "grad_norm": 1.1994147300720215, "learning_rate": 8.156452698658457e-05, "loss": 0.4916022300720215, "step": 324060 }, { "epoch": 1.9263393785925305, "grad_norm": 1.4015445709228516, "learning_rate": 8.155862114324453e-05, "loss": 0.6043430805206299, "step": 324070 }, { "epoch": 1.9263988206691989, "grad_norm": 1.3685740232467651, "learning_rate": 8.155271543595871e-05, "loss": 0.5350040435791016, "step": 324080 }, { "epoch": 1.9264582627458673, "grad_norm": 1.1308454275131226, "learning_rate": 8.154680986475543e-05, "loss": 0.5086528778076171, "step": 324090 }, { "epoch": 1.9265177048225357, "grad_norm": 1.562011957168579, "learning_rate": 8.154090442966294e-05, "loss": 0.5837616443634033, "step": 324100 }, { "epoch": 1.9265771468992041, "grad_norm": 1.4479708671569824, "learning_rate": 8.153499913070941e-05, "loss": 0.5831632614135742, "step": 324110 }, { "epoch": 1.9266365889758723, "grad_norm": 1.564978837966919, "learning_rate": 8.152909396792316e-05, "loss": 0.5102705478668212, "step": 324120 }, { "epoch": 1.9266960310525407, "grad_norm": 1.5453307628631592, "learning_rate": 8.152318894133247e-05, "loss": 0.5751314163208008, "step": 324130 }, { "epoch": 1.9267554731292091, "grad_norm": 1.4156441688537598, "learning_rate": 8.151728405096546e-05, "loss": 0.5911648750305176, "step": 324140 }, { "epoch": 1.9268149152058776, "grad_norm": 1.8841493129730225, "learning_rate": 8.151137929685049e-05, "loss": 0.5727081775665284, "step": 324150 }, { "epoch": 1.926874357282546, "grad_norm": 1.2988604307174683, "learning_rate": 8.150547467901579e-05, "loss": 0.5682915687561035, "step": 324160 }, { "epoch": 1.9269337993592144, "grad_norm": 1.2689069509506226, "learning_rate": 8.14995701974896e-05, "loss": 0.5524081230163574, "step": 324170 }, { "epoch": 1.9269932414358828, "grad_norm": 1.1544075012207031, "learning_rate": 8.149366585230007e-05, "loss": 0.5272971153259277, "step": 324180 }, { "epoch": 1.9270526835125512, "grad_norm": 1.2509896755218506, "learning_rate": 8.14877616434756e-05, "loss": 0.5136384963989258, "step": 324190 }, { "epoch": 1.9271121255892196, "grad_norm": 1.4238554239273071, "learning_rate": 8.148185757104434e-05, "loss": 0.5263391017913819, "step": 324200 }, { "epoch": 1.927171567665888, "grad_norm": 1.2309690713882446, "learning_rate": 8.147595363503455e-05, "loss": 0.556663990020752, "step": 324210 }, { "epoch": 1.9272310097425565, "grad_norm": 1.330880880355835, "learning_rate": 8.147004983547448e-05, "loss": 0.5490286827087403, "step": 324220 }, { "epoch": 1.9272904518192249, "grad_norm": 1.4197652339935303, "learning_rate": 8.146414617239238e-05, "loss": 0.5642358779907226, "step": 324230 }, { "epoch": 1.9273498938958933, "grad_norm": 1.5449614524841309, "learning_rate": 8.145824264581645e-05, "loss": 0.5497634410858154, "step": 324240 }, { "epoch": 1.9274093359725617, "grad_norm": 1.7867971658706665, "learning_rate": 8.145233925577498e-05, "loss": 0.6018733978271484, "step": 324250 }, { "epoch": 1.92746877804923, "grad_norm": 1.3201582431793213, "learning_rate": 8.144643600229618e-05, "loss": 0.550448226928711, "step": 324260 }, { "epoch": 1.9275282201258983, "grad_norm": 1.5870392322540283, "learning_rate": 8.144053288540829e-05, "loss": 0.5950743675231933, "step": 324270 }, { "epoch": 1.9275876622025667, "grad_norm": 1.3253154754638672, "learning_rate": 8.14346299051396e-05, "loss": 0.5295815467834473, "step": 324280 }, { "epoch": 1.9276471042792351, "grad_norm": 1.278685212135315, "learning_rate": 8.142872706151827e-05, "loss": 0.49614534378051756, "step": 324290 }, { "epoch": 1.9277065463559033, "grad_norm": 1.6394398212432861, "learning_rate": 8.142282435457258e-05, "loss": 0.5840959548950195, "step": 324300 }, { "epoch": 1.9277659884325717, "grad_norm": 1.1970030069351196, "learning_rate": 8.141692178433073e-05, "loss": 0.5134363174438477, "step": 324310 }, { "epoch": 1.9278254305092402, "grad_norm": 1.5115749835968018, "learning_rate": 8.141101935082103e-05, "loss": 0.5116277694702148, "step": 324320 }, { "epoch": 1.9278848725859086, "grad_norm": 1.5885424613952637, "learning_rate": 8.140511705407166e-05, "loss": 0.51205472946167, "step": 324330 }, { "epoch": 1.927944314662577, "grad_norm": 1.212867021560669, "learning_rate": 8.139921489411085e-05, "loss": 0.5864060401916504, "step": 324340 }, { "epoch": 1.9280037567392454, "grad_norm": 1.4046491384506226, "learning_rate": 8.139331287096686e-05, "loss": 0.5344367504119873, "step": 324350 }, { "epoch": 1.9280631988159138, "grad_norm": 1.809536099433899, "learning_rate": 8.138741098466791e-05, "loss": 0.5863512516021728, "step": 324360 }, { "epoch": 1.9281226408925822, "grad_norm": 1.4250738620758057, "learning_rate": 8.138150923524222e-05, "loss": 0.5807172775268554, "step": 324370 }, { "epoch": 1.9281820829692506, "grad_norm": 1.342034101486206, "learning_rate": 8.137560762271805e-05, "loss": 0.5360067367553711, "step": 324380 }, { "epoch": 1.928241525045919, "grad_norm": 1.4658819437026978, "learning_rate": 8.136970614712364e-05, "loss": 0.5664056301116943, "step": 324390 }, { "epoch": 1.9283009671225875, "grad_norm": 1.2815213203430176, "learning_rate": 8.136380480848717e-05, "loss": 0.5101786613464355, "step": 324400 }, { "epoch": 1.9283604091992559, "grad_norm": 1.3515511751174927, "learning_rate": 8.135790360683691e-05, "loss": 0.5367325782775879, "step": 324410 }, { "epoch": 1.9284198512759243, "grad_norm": 1.5951249599456787, "learning_rate": 8.135200254220107e-05, "loss": 0.5742502689361573, "step": 324420 }, { "epoch": 1.9284792933525927, "grad_norm": 1.317752718925476, "learning_rate": 8.134610161460791e-05, "loss": 0.4953753471374512, "step": 324430 }, { "epoch": 1.928538735429261, "grad_norm": 0.8588008284568787, "learning_rate": 8.13402008240856e-05, "loss": 0.4943242073059082, "step": 324440 }, { "epoch": 1.9285981775059293, "grad_norm": 1.2742671966552734, "learning_rate": 8.133430017066243e-05, "loss": 0.5621979713439942, "step": 324450 }, { "epoch": 1.9286576195825977, "grad_norm": 1.4797295331954956, "learning_rate": 8.13283996543666e-05, "loss": 0.5294816970825196, "step": 324460 }, { "epoch": 1.9287170616592662, "grad_norm": 1.1605244874954224, "learning_rate": 8.132249927522632e-05, "loss": 0.5151271343231201, "step": 324470 }, { "epoch": 1.9287765037359346, "grad_norm": 1.1869573593139648, "learning_rate": 8.131659903326985e-05, "loss": 0.4851815223693848, "step": 324480 }, { "epoch": 1.9288359458126028, "grad_norm": 1.8488216400146484, "learning_rate": 8.131069892852541e-05, "loss": 0.5743391990661622, "step": 324490 }, { "epoch": 1.9288953878892712, "grad_norm": 1.5823806524276733, "learning_rate": 8.130479896102117e-05, "loss": 0.4771549701690674, "step": 324500 }, { "epoch": 1.9289548299659396, "grad_norm": 1.3376257419586182, "learning_rate": 8.129889913078542e-05, "loss": 0.562443208694458, "step": 324510 }, { "epoch": 1.929014272042608, "grad_norm": 1.003283977508545, "learning_rate": 8.129299943784635e-05, "loss": 0.5062530517578125, "step": 324520 }, { "epoch": 1.9290737141192764, "grad_norm": 1.1612577438354492, "learning_rate": 8.128709988223221e-05, "loss": 0.5325675964355469, "step": 324530 }, { "epoch": 1.9291331561959448, "grad_norm": 1.3365960121154785, "learning_rate": 8.128120046397116e-05, "loss": 0.5150779724121094, "step": 324540 }, { "epoch": 1.9291925982726132, "grad_norm": 1.3791158199310303, "learning_rate": 8.127530118309148e-05, "loss": 0.5843117713928223, "step": 324550 }, { "epoch": 1.9292520403492817, "grad_norm": 1.6286333799362183, "learning_rate": 8.126940203962139e-05, "loss": 0.5531641960144043, "step": 324560 }, { "epoch": 1.92931148242595, "grad_norm": 0.9305241107940674, "learning_rate": 8.126350303358905e-05, "loss": 0.5227389335632324, "step": 324570 }, { "epoch": 1.9293709245026185, "grad_norm": 1.5215452909469604, "learning_rate": 8.125760416502275e-05, "loss": 0.5383244514465332, "step": 324580 }, { "epoch": 1.929430366579287, "grad_norm": 1.608272910118103, "learning_rate": 8.125170543395069e-05, "loss": 0.5391261100769043, "step": 324590 }, { "epoch": 1.9294898086559553, "grad_norm": 1.257825255393982, "learning_rate": 8.124580684040102e-05, "loss": 0.4993151664733887, "step": 324600 }, { "epoch": 1.9295492507326237, "grad_norm": 1.4703218936920166, "learning_rate": 8.123990838440208e-05, "loss": 0.5348453521728516, "step": 324610 }, { "epoch": 1.9296086928092921, "grad_norm": 1.3499562740325928, "learning_rate": 8.123401006598201e-05, "loss": 0.5643692016601562, "step": 324620 }, { "epoch": 1.9296681348859603, "grad_norm": 1.0817774534225464, "learning_rate": 8.122811188516899e-05, "loss": 0.5224818229675293, "step": 324630 }, { "epoch": 1.9297275769626288, "grad_norm": 1.1448427438735962, "learning_rate": 8.122221384199129e-05, "loss": 0.5131452560424805, "step": 324640 }, { "epoch": 1.9297870190392972, "grad_norm": 1.0959354639053345, "learning_rate": 8.121631593647716e-05, "loss": 0.5375895977020264, "step": 324650 }, { "epoch": 1.9298464611159656, "grad_norm": 1.5516340732574463, "learning_rate": 8.121041816865475e-05, "loss": 0.5461376667022705, "step": 324660 }, { "epoch": 1.9299059031926338, "grad_norm": 1.5567071437835693, "learning_rate": 8.120452053855225e-05, "loss": 0.5349925994873047, "step": 324670 }, { "epoch": 1.9299653452693022, "grad_norm": 1.3480894565582275, "learning_rate": 8.119862304619796e-05, "loss": 0.513373851776123, "step": 324680 }, { "epoch": 1.9300247873459706, "grad_norm": 1.4912283420562744, "learning_rate": 8.119272569162004e-05, "loss": 0.5277891635894776, "step": 324690 }, { "epoch": 1.930084229422639, "grad_norm": 1.439680814743042, "learning_rate": 8.118682847484666e-05, "loss": 0.5453844547271729, "step": 324700 }, { "epoch": 1.9301436714993074, "grad_norm": 1.1500937938690186, "learning_rate": 8.118093139590614e-05, "loss": 0.5074607372283936, "step": 324710 }, { "epoch": 1.9302031135759758, "grad_norm": 1.6142443418502808, "learning_rate": 8.117503445482661e-05, "loss": 0.5372726440429687, "step": 324720 }, { "epoch": 1.9302625556526443, "grad_norm": 1.2665624618530273, "learning_rate": 8.116913765163625e-05, "loss": 0.5155073165893554, "step": 324730 }, { "epoch": 1.9303219977293127, "grad_norm": 1.7089823484420776, "learning_rate": 8.116324098636336e-05, "loss": 0.5159907817840577, "step": 324740 }, { "epoch": 1.930381439805981, "grad_norm": 1.2839090824127197, "learning_rate": 8.115734445903609e-05, "loss": 0.5962631702423096, "step": 324750 }, { "epoch": 1.9304408818826495, "grad_norm": 1.6765223741531372, "learning_rate": 8.115144806968267e-05, "loss": 0.5520429134368896, "step": 324760 }, { "epoch": 1.930500323959318, "grad_norm": 1.6340965032577515, "learning_rate": 8.114555181833126e-05, "loss": 0.5042387008666992, "step": 324770 }, { "epoch": 1.9305597660359863, "grad_norm": 1.2876291275024414, "learning_rate": 8.113965570501012e-05, "loss": 0.5116917610168457, "step": 324780 }, { "epoch": 1.9306192081126547, "grad_norm": 1.5357941389083862, "learning_rate": 8.113375972974747e-05, "loss": 0.5227904796600342, "step": 324790 }, { "epoch": 1.9306786501893232, "grad_norm": 1.5778220891952515, "learning_rate": 8.112786389257141e-05, "loss": 0.5299795627593994, "step": 324800 }, { "epoch": 1.9307380922659914, "grad_norm": 1.574427843093872, "learning_rate": 8.112196819351025e-05, "loss": 0.538204288482666, "step": 324810 }, { "epoch": 1.9307975343426598, "grad_norm": 1.5551143884658813, "learning_rate": 8.111607263259217e-05, "loss": 0.49402055740356443, "step": 324820 }, { "epoch": 1.9308569764193282, "grad_norm": 1.1570770740509033, "learning_rate": 8.111017720984532e-05, "loss": 0.5130558013916016, "step": 324830 }, { "epoch": 1.9309164184959966, "grad_norm": 1.600555419921875, "learning_rate": 8.110428192529798e-05, "loss": 0.5727591514587402, "step": 324840 }, { "epoch": 1.930975860572665, "grad_norm": 1.2788944244384766, "learning_rate": 8.10983867789783e-05, "loss": 0.4791240692138672, "step": 324850 }, { "epoch": 1.9310353026493332, "grad_norm": 1.2832239866256714, "learning_rate": 8.109249177091449e-05, "loss": 0.5207842350006103, "step": 324860 }, { "epoch": 1.9310947447260016, "grad_norm": 1.3118406534194946, "learning_rate": 8.108659690113474e-05, "loss": 0.5840106964111328, "step": 324870 }, { "epoch": 1.93115418680267, "grad_norm": 1.5249537229537964, "learning_rate": 8.108070216966728e-05, "loss": 0.5488977432250977, "step": 324880 }, { "epoch": 1.9312136288793385, "grad_norm": 1.2937142848968506, "learning_rate": 8.107480757654028e-05, "loss": 0.5421109199523926, "step": 324890 }, { "epoch": 1.9312730709560069, "grad_norm": 1.410556435585022, "learning_rate": 8.106891312178195e-05, "loss": 0.5340234756469726, "step": 324900 }, { "epoch": 1.9313325130326753, "grad_norm": 1.7434064149856567, "learning_rate": 8.106301880542048e-05, "loss": 0.4828804016113281, "step": 324910 }, { "epoch": 1.9313919551093437, "grad_norm": 1.5807603597640991, "learning_rate": 8.10571246274841e-05, "loss": 0.5599113464355469, "step": 324920 }, { "epoch": 1.931451397186012, "grad_norm": 1.4454680681228638, "learning_rate": 8.105123058800094e-05, "loss": 0.5756077766418457, "step": 324930 }, { "epoch": 1.9315108392626805, "grad_norm": 1.3645763397216797, "learning_rate": 8.104533668699925e-05, "loss": 0.5437468528747559, "step": 324940 }, { "epoch": 1.931570281339349, "grad_norm": 1.4035576581954956, "learning_rate": 8.10394429245072e-05, "loss": 0.5601984024047851, "step": 324950 }, { "epoch": 1.9316297234160174, "grad_norm": 1.4691728353500366, "learning_rate": 8.103354930055298e-05, "loss": 0.5227621078491211, "step": 324960 }, { "epoch": 1.9316891654926858, "grad_norm": 1.0131945610046387, "learning_rate": 8.102765581516482e-05, "loss": 0.5184946060180664, "step": 324970 }, { "epoch": 1.9317486075693542, "grad_norm": 1.1266642808914185, "learning_rate": 8.10217624683709e-05, "loss": 0.47673234939575193, "step": 324980 }, { "epoch": 1.9318080496460226, "grad_norm": 1.1300065517425537, "learning_rate": 8.101586926019933e-05, "loss": 0.5443281173706055, "step": 324990 }, { "epoch": 1.9318674917226908, "grad_norm": 1.3188613653182983, "learning_rate": 8.100997619067843e-05, "loss": 0.4951189994812012, "step": 325000 }, { "epoch": 1.9319269337993592, "grad_norm": 1.564516544342041, "learning_rate": 8.100408325983632e-05, "loss": 0.5586483955383301, "step": 325010 }, { "epoch": 1.9319863758760276, "grad_norm": 1.3760613203048706, "learning_rate": 8.099819046770121e-05, "loss": 0.567741870880127, "step": 325020 }, { "epoch": 1.932045817952696, "grad_norm": 1.3348628282546997, "learning_rate": 8.099229781430121e-05, "loss": 0.5422370910644532, "step": 325030 }, { "epoch": 1.9321052600293642, "grad_norm": 1.1512445211410522, "learning_rate": 8.098640529966465e-05, "loss": 0.528305959701538, "step": 325040 }, { "epoch": 1.9321647021060326, "grad_norm": 1.3147207498550415, "learning_rate": 8.098051292381966e-05, "loss": 0.5443508148193359, "step": 325050 }, { "epoch": 1.932224144182701, "grad_norm": 1.417395830154419, "learning_rate": 8.097462068679433e-05, "loss": 0.545330810546875, "step": 325060 }, { "epoch": 1.9322835862593695, "grad_norm": 1.0994598865509033, "learning_rate": 8.096872858861697e-05, "loss": 0.5007906913757324, "step": 325070 }, { "epoch": 1.9323430283360379, "grad_norm": 1.2032294273376465, "learning_rate": 8.096283662931577e-05, "loss": 0.5227254867553711, "step": 325080 }, { "epoch": 1.9324024704127063, "grad_norm": 0.9968100190162659, "learning_rate": 8.09569448089188e-05, "loss": 0.5613388061523438, "step": 325090 }, { "epoch": 1.9324619124893747, "grad_norm": 1.5014652013778687, "learning_rate": 8.095105312745434e-05, "loss": 0.4997835159301758, "step": 325100 }, { "epoch": 1.9325213545660431, "grad_norm": 1.4036773443222046, "learning_rate": 8.094516158495058e-05, "loss": 0.5735514640808106, "step": 325110 }, { "epoch": 1.9325807966427115, "grad_norm": 1.5948407649993896, "learning_rate": 8.09392701814356e-05, "loss": 0.5199492931365967, "step": 325120 }, { "epoch": 1.93264023871938, "grad_norm": 1.1107168197631836, "learning_rate": 8.093337891693771e-05, "loss": 0.539084529876709, "step": 325130 }, { "epoch": 1.9326996807960484, "grad_norm": 1.8471781015396118, "learning_rate": 8.092748779148504e-05, "loss": 0.5086670398712159, "step": 325140 }, { "epoch": 1.9327591228727168, "grad_norm": 1.2351529598236084, "learning_rate": 8.092159680510578e-05, "loss": 0.5893669605255127, "step": 325150 }, { "epoch": 1.9328185649493852, "grad_norm": 1.3201868534088135, "learning_rate": 8.091570595782802e-05, "loss": 0.5516816139221191, "step": 325160 }, { "epoch": 1.9328780070260536, "grad_norm": 1.2212872505187988, "learning_rate": 8.090981524968011e-05, "loss": 0.5237953186035156, "step": 325170 }, { "epoch": 1.9329374491027218, "grad_norm": 1.3886278867721558, "learning_rate": 8.09039246806901e-05, "loss": 0.5409304141998291, "step": 325180 }, { "epoch": 1.9329968911793902, "grad_norm": 1.6927763223648071, "learning_rate": 8.089803425088618e-05, "loss": 0.6023035049438477, "step": 325190 }, { "epoch": 1.9330563332560586, "grad_norm": 1.4614540338516235, "learning_rate": 8.089214396029659e-05, "loss": 0.5673225879669189, "step": 325200 }, { "epoch": 1.933115775332727, "grad_norm": 1.6057145595550537, "learning_rate": 8.088625380894945e-05, "loss": 0.5688677787780761, "step": 325210 }, { "epoch": 1.9331752174093955, "grad_norm": 1.3297713994979858, "learning_rate": 8.088036379687294e-05, "loss": 0.5094661235809326, "step": 325220 }, { "epoch": 1.9332346594860637, "grad_norm": 1.609660029411316, "learning_rate": 8.087447392409528e-05, "loss": 0.5102041244506836, "step": 325230 }, { "epoch": 1.933294101562732, "grad_norm": 1.5291883945465088, "learning_rate": 8.086858419064464e-05, "loss": 0.5060773849487304, "step": 325240 }, { "epoch": 1.9333535436394005, "grad_norm": 1.3653388023376465, "learning_rate": 8.086269459654914e-05, "loss": 0.5257012367248535, "step": 325250 }, { "epoch": 1.933412985716069, "grad_norm": 1.5875931978225708, "learning_rate": 8.085680514183698e-05, "loss": 0.515441608428955, "step": 325260 }, { "epoch": 1.9334724277927373, "grad_norm": 1.5705270767211914, "learning_rate": 8.085091582653637e-05, "loss": 0.5546219348907471, "step": 325270 }, { "epoch": 1.9335318698694057, "grad_norm": 1.4817793369293213, "learning_rate": 8.084502665067544e-05, "loss": 0.5073866844177246, "step": 325280 }, { "epoch": 1.9335913119460741, "grad_norm": 1.5537831783294678, "learning_rate": 8.083913761428237e-05, "loss": 0.5616649627685547, "step": 325290 }, { "epoch": 1.9336507540227426, "grad_norm": 1.957851529121399, "learning_rate": 8.083324871738534e-05, "loss": 0.5984631538391113, "step": 325300 }, { "epoch": 1.933710196099411, "grad_norm": 1.3018219470977783, "learning_rate": 8.082735996001251e-05, "loss": 0.49329137802124023, "step": 325310 }, { "epoch": 1.9337696381760794, "grad_norm": 1.2809805870056152, "learning_rate": 8.082147134219205e-05, "loss": 0.5098479747772217, "step": 325320 }, { "epoch": 1.9338290802527478, "grad_norm": 1.8735098838806152, "learning_rate": 8.081558286395215e-05, "loss": 0.5455146789550781, "step": 325330 }, { "epoch": 1.9338885223294162, "grad_norm": 1.2291795015335083, "learning_rate": 8.080969452532097e-05, "loss": 0.542960786819458, "step": 325340 }, { "epoch": 1.9339479644060846, "grad_norm": 1.4016658067703247, "learning_rate": 8.080380632632665e-05, "loss": 0.5663891315460206, "step": 325350 }, { "epoch": 1.934007406482753, "grad_norm": 1.1715104579925537, "learning_rate": 8.079791826699739e-05, "loss": 0.5005769252777099, "step": 325360 }, { "epoch": 1.9340668485594212, "grad_norm": 1.162645936012268, "learning_rate": 8.079203034736136e-05, "loss": 0.5714326858520508, "step": 325370 }, { "epoch": 1.9341262906360897, "grad_norm": 1.3555852174758911, "learning_rate": 8.07861425674467e-05, "loss": 0.5826097011566163, "step": 325380 }, { "epoch": 1.934185732712758, "grad_norm": 1.2321890592575073, "learning_rate": 8.078025492728156e-05, "loss": 0.5377384662628174, "step": 325390 }, { "epoch": 1.9342451747894265, "grad_norm": 1.2168381214141846, "learning_rate": 8.077436742689415e-05, "loss": 0.4884509086608887, "step": 325400 }, { "epoch": 1.9343046168660947, "grad_norm": 1.275911569595337, "learning_rate": 8.076848006631264e-05, "loss": 0.5769793510437011, "step": 325410 }, { "epoch": 1.934364058942763, "grad_norm": 1.702289342880249, "learning_rate": 8.076259284556513e-05, "loss": 0.532992935180664, "step": 325420 }, { "epoch": 1.9344235010194315, "grad_norm": 1.395743727684021, "learning_rate": 8.075670576467984e-05, "loss": 0.5289339065551758, "step": 325430 }, { "epoch": 1.9344829430961, "grad_norm": 2.170532703399658, "learning_rate": 8.075081882368493e-05, "loss": 0.567402458190918, "step": 325440 }, { "epoch": 1.9345423851727683, "grad_norm": 1.584825038909912, "learning_rate": 8.074493202260852e-05, "loss": 0.548682689666748, "step": 325450 }, { "epoch": 1.9346018272494367, "grad_norm": 1.673152208328247, "learning_rate": 8.073904536147879e-05, "loss": 0.5552037239074707, "step": 325460 }, { "epoch": 1.9346612693261052, "grad_norm": 1.5789504051208496, "learning_rate": 8.073315884032392e-05, "loss": 0.5555194854736328, "step": 325470 }, { "epoch": 1.9347207114027736, "grad_norm": 1.8600040674209595, "learning_rate": 8.072727245917205e-05, "loss": 0.5407367706298828, "step": 325480 }, { "epoch": 1.934780153479442, "grad_norm": 1.4131470918655396, "learning_rate": 8.072138621805134e-05, "loss": 0.5214802742004394, "step": 325490 }, { "epoch": 1.9348395955561104, "grad_norm": 1.5638961791992188, "learning_rate": 8.071550011698996e-05, "loss": 0.4723834037780762, "step": 325500 }, { "epoch": 1.9348990376327788, "grad_norm": 1.4797770977020264, "learning_rate": 8.070961415601606e-05, "loss": 0.5033467292785645, "step": 325510 }, { "epoch": 1.9349584797094472, "grad_norm": 1.262932300567627, "learning_rate": 8.070372833515776e-05, "loss": 0.523037338256836, "step": 325520 }, { "epoch": 1.9350179217861156, "grad_norm": 1.0221493244171143, "learning_rate": 8.06978426544433e-05, "loss": 0.48874382972717284, "step": 325530 }, { "epoch": 1.935077363862784, "grad_norm": 1.3755041360855103, "learning_rate": 8.069195711390074e-05, "loss": 0.6092972755432129, "step": 325540 }, { "epoch": 1.9351368059394523, "grad_norm": 1.3069018125534058, "learning_rate": 8.068607171355829e-05, "loss": 0.5414305686950683, "step": 325550 }, { "epoch": 1.9351962480161207, "grad_norm": 1.1947256326675415, "learning_rate": 8.068018645344411e-05, "loss": 0.5635923385620117, "step": 325560 }, { "epoch": 1.935255690092789, "grad_norm": 1.8100268840789795, "learning_rate": 8.06743013335863e-05, "loss": 0.5583860397338867, "step": 325570 }, { "epoch": 1.9353151321694575, "grad_norm": 1.3228397369384766, "learning_rate": 8.066841635401308e-05, "loss": 0.5086756706237793, "step": 325580 }, { "epoch": 1.935374574246126, "grad_norm": 1.25885808467865, "learning_rate": 8.066253151475256e-05, "loss": 0.5074033737182617, "step": 325590 }, { "epoch": 1.935434016322794, "grad_norm": 1.1586244106292725, "learning_rate": 8.065664681583293e-05, "loss": 0.5255274772644043, "step": 325600 }, { "epoch": 1.9354934583994625, "grad_norm": 1.3449883460998535, "learning_rate": 8.06507622572823e-05, "loss": 0.5297934532165527, "step": 325610 }, { "epoch": 1.935552900476131, "grad_norm": 1.1456844806671143, "learning_rate": 8.064487783912878e-05, "loss": 0.4998188018798828, "step": 325620 }, { "epoch": 1.9356123425527993, "grad_norm": 1.368236780166626, "learning_rate": 8.063899356140066e-05, "loss": 0.519158124923706, "step": 325630 }, { "epoch": 1.9356717846294678, "grad_norm": 1.1294194459915161, "learning_rate": 8.063310942412594e-05, "loss": 0.4697521686553955, "step": 325640 }, { "epoch": 1.9357312267061362, "grad_norm": 1.652356743812561, "learning_rate": 8.06272254273328e-05, "loss": 0.5347714424133301, "step": 325650 }, { "epoch": 1.9357906687828046, "grad_norm": 1.4314427375793457, "learning_rate": 8.062134157104948e-05, "loss": 0.5536646842956543, "step": 325660 }, { "epoch": 1.935850110859473, "grad_norm": 1.3737916946411133, "learning_rate": 8.061545785530404e-05, "loss": 0.529056167602539, "step": 325670 }, { "epoch": 1.9359095529361414, "grad_norm": 1.32239830493927, "learning_rate": 8.060957428012461e-05, "loss": 0.5001621723175049, "step": 325680 }, { "epoch": 1.9359689950128098, "grad_norm": 1.386010766029358, "learning_rate": 8.060369084553943e-05, "loss": 0.48737730979919436, "step": 325690 }, { "epoch": 1.9360284370894782, "grad_norm": 1.681268572807312, "learning_rate": 8.059780755157655e-05, "loss": 0.592305040359497, "step": 325700 }, { "epoch": 1.9360878791661467, "grad_norm": 0.9886994361877441, "learning_rate": 8.059192439826413e-05, "loss": 0.5439404964447021, "step": 325710 }, { "epoch": 1.936147321242815, "grad_norm": 1.193311095237732, "learning_rate": 8.058604138563037e-05, "loss": 0.5601095199584961, "step": 325720 }, { "epoch": 1.9362067633194835, "grad_norm": 1.3816794157028198, "learning_rate": 8.058015851370337e-05, "loss": 0.49028596878051756, "step": 325730 }, { "epoch": 1.9362662053961517, "grad_norm": 1.3990371227264404, "learning_rate": 8.05742757825113e-05, "loss": 0.5814383029937744, "step": 325740 }, { "epoch": 1.93632564747282, "grad_norm": 1.4759303331375122, "learning_rate": 8.056839319208222e-05, "loss": 0.5083234310150146, "step": 325750 }, { "epoch": 1.9363850895494885, "grad_norm": 1.4303525686264038, "learning_rate": 8.056251074244438e-05, "loss": 0.5584958553314209, "step": 325760 }, { "epoch": 1.936444531626157, "grad_norm": 1.0923240184783936, "learning_rate": 8.055662843362586e-05, "loss": 0.5708292484283447, "step": 325770 }, { "epoch": 1.9365039737028251, "grad_norm": 1.55046546459198, "learning_rate": 8.055074626565477e-05, "loss": 0.5225555419921875, "step": 325780 }, { "epoch": 1.9365634157794935, "grad_norm": 1.58120858669281, "learning_rate": 8.054486423855932e-05, "loss": 0.5365688323974609, "step": 325790 }, { "epoch": 1.936622857856162, "grad_norm": 1.7121564149856567, "learning_rate": 8.05389823523676e-05, "loss": 0.5195225715637207, "step": 325800 }, { "epoch": 1.9366822999328304, "grad_norm": 1.210943579673767, "learning_rate": 8.053310060710776e-05, "loss": 0.5337650299072265, "step": 325810 }, { "epoch": 1.9367417420094988, "grad_norm": 1.615440845489502, "learning_rate": 8.052721900280795e-05, "loss": 0.5961532592773438, "step": 325820 }, { "epoch": 1.9368011840861672, "grad_norm": 1.1571367979049683, "learning_rate": 8.052133753949628e-05, "loss": 0.5375873565673828, "step": 325830 }, { "epoch": 1.9368606261628356, "grad_norm": 1.0145152807235718, "learning_rate": 8.05154562172009e-05, "loss": 0.5201771259307861, "step": 325840 }, { "epoch": 1.936920068239504, "grad_norm": 1.2709569931030273, "learning_rate": 8.050957503594995e-05, "loss": 0.5206066131591797, "step": 325850 }, { "epoch": 1.9369795103161724, "grad_norm": 1.089534878730774, "learning_rate": 8.050369399577156e-05, "loss": 0.4950991630554199, "step": 325860 }, { "epoch": 1.9370389523928409, "grad_norm": 1.604912519454956, "learning_rate": 8.049781309669384e-05, "loss": 0.5480355262756348, "step": 325870 }, { "epoch": 1.9370983944695093, "grad_norm": 1.4121500253677368, "learning_rate": 8.049193233874494e-05, "loss": 0.5595977306365967, "step": 325880 }, { "epoch": 1.9371578365461777, "grad_norm": 1.102505087852478, "learning_rate": 8.0486051721953e-05, "loss": 0.5107711791992188, "step": 325890 }, { "epoch": 1.937217278622846, "grad_norm": 1.4376331567764282, "learning_rate": 8.048017124634615e-05, "loss": 0.5463460445404053, "step": 325900 }, { "epoch": 1.9372767206995145, "grad_norm": 1.1018792390823364, "learning_rate": 8.047429091195249e-05, "loss": 0.47299847602844236, "step": 325910 }, { "epoch": 1.9373361627761827, "grad_norm": 1.2326173782348633, "learning_rate": 8.04684107188002e-05, "loss": 0.5644360542297363, "step": 325920 }, { "epoch": 1.9373956048528511, "grad_norm": 1.1842033863067627, "learning_rate": 8.046253066691741e-05, "loss": 0.5645617485046387, "step": 325930 }, { "epoch": 1.9374550469295195, "grad_norm": 1.443619728088379, "learning_rate": 8.045665075633215e-05, "loss": 0.5270187854766846, "step": 325940 }, { "epoch": 1.937514489006188, "grad_norm": 1.346711277961731, "learning_rate": 8.045077098707265e-05, "loss": 0.5584665775299072, "step": 325950 }, { "epoch": 1.9375739310828564, "grad_norm": 0.9659562706947327, "learning_rate": 8.044489135916702e-05, "loss": 0.5150300979614257, "step": 325960 }, { "epoch": 1.9376333731595246, "grad_norm": 1.329733967781067, "learning_rate": 8.043901187264334e-05, "loss": 0.5441993713378906, "step": 325970 }, { "epoch": 1.937692815236193, "grad_norm": 1.5752779245376587, "learning_rate": 8.043313252752977e-05, "loss": 0.5344356536865235, "step": 325980 }, { "epoch": 1.9377522573128614, "grad_norm": 1.4493327140808105, "learning_rate": 8.042725332385445e-05, "loss": 0.5739928245544433, "step": 325990 }, { "epoch": 1.9378116993895298, "grad_norm": 1.3246805667877197, "learning_rate": 8.042137426164549e-05, "loss": 0.5067694664001465, "step": 326000 }, { "epoch": 1.9378711414661982, "grad_norm": 1.4262853860855103, "learning_rate": 8.0415495340931e-05, "loss": 0.525333023071289, "step": 326010 }, { "epoch": 1.9379305835428666, "grad_norm": 1.2667083740234375, "learning_rate": 8.04096165617391e-05, "loss": 0.541677188873291, "step": 326020 }, { "epoch": 1.937990025619535, "grad_norm": 1.5449327230453491, "learning_rate": 8.040373792409796e-05, "loss": 0.5884013175964355, "step": 326030 }, { "epoch": 1.9380494676962035, "grad_norm": 1.4033933877944946, "learning_rate": 8.039785942803561e-05, "loss": 0.5836336135864257, "step": 326040 }, { "epoch": 1.9381089097728719, "grad_norm": 1.1497045755386353, "learning_rate": 8.039198107358028e-05, "loss": 0.575705623626709, "step": 326050 }, { "epoch": 1.9381683518495403, "grad_norm": 1.4697695970535278, "learning_rate": 8.038610286076e-05, "loss": 0.544584321975708, "step": 326060 }, { "epoch": 1.9382277939262087, "grad_norm": 1.3277431726455688, "learning_rate": 8.038022478960295e-05, "loss": 0.5997193336486817, "step": 326070 }, { "epoch": 1.9382872360028771, "grad_norm": 1.7415120601654053, "learning_rate": 8.037434686013722e-05, "loss": 0.49918394088745116, "step": 326080 }, { "epoch": 1.9383466780795455, "grad_norm": 1.3641427755355835, "learning_rate": 8.036846907239093e-05, "loss": 0.5527275562286377, "step": 326090 }, { "epoch": 1.938406120156214, "grad_norm": 1.3025949001312256, "learning_rate": 8.036259142639222e-05, "loss": 0.5122771739959717, "step": 326100 }, { "epoch": 1.9384655622328821, "grad_norm": 1.639696478843689, "learning_rate": 8.035671392216912e-05, "loss": 0.5912179946899414, "step": 326110 }, { "epoch": 1.9385250043095505, "grad_norm": 1.6494678258895874, "learning_rate": 8.035083655974989e-05, "loss": 0.5474565505981446, "step": 326120 }, { "epoch": 1.938584446386219, "grad_norm": 1.3292900323867798, "learning_rate": 8.034495933916255e-05, "loss": 0.46981172561645507, "step": 326130 }, { "epoch": 1.9386438884628874, "grad_norm": 1.46686851978302, "learning_rate": 8.033908226043519e-05, "loss": 0.558963680267334, "step": 326140 }, { "epoch": 1.9387033305395556, "grad_norm": 0.9774187207221985, "learning_rate": 8.033320532359601e-05, "loss": 0.4872842788696289, "step": 326150 }, { "epoch": 1.938762772616224, "grad_norm": 1.4525145292282104, "learning_rate": 8.032732852867309e-05, "loss": 0.5896079063415527, "step": 326160 }, { "epoch": 1.9388222146928924, "grad_norm": 1.5263131856918335, "learning_rate": 8.032145187569446e-05, "loss": 0.5887506008148193, "step": 326170 }, { "epoch": 1.9388816567695608, "grad_norm": 1.3702582120895386, "learning_rate": 8.031557536468837e-05, "loss": 0.6081891536712647, "step": 326180 }, { "epoch": 1.9389410988462292, "grad_norm": 1.6816105842590332, "learning_rate": 8.030969899568287e-05, "loss": 0.5032983779907226, "step": 326190 }, { "epoch": 1.9390005409228976, "grad_norm": 1.4962645769119263, "learning_rate": 8.030382276870602e-05, "loss": 0.4903870582580566, "step": 326200 }, { "epoch": 1.939059982999566, "grad_norm": 1.4653372764587402, "learning_rate": 8.0297946683786e-05, "loss": 0.4559901237487793, "step": 326210 }, { "epoch": 1.9391194250762345, "grad_norm": 1.3919683694839478, "learning_rate": 8.029207074095095e-05, "loss": 0.5007050514221192, "step": 326220 }, { "epoch": 1.9391788671529029, "grad_norm": 1.374314308166504, "learning_rate": 8.028619494022886e-05, "loss": 0.49194488525390623, "step": 326230 }, { "epoch": 1.9392383092295713, "grad_norm": 1.5802439451217651, "learning_rate": 8.028031928164792e-05, "loss": 0.5726452350616456, "step": 326240 }, { "epoch": 1.9392977513062397, "grad_norm": 1.498474359512329, "learning_rate": 8.027444376523623e-05, "loss": 0.5097773551940918, "step": 326250 }, { "epoch": 1.9393571933829081, "grad_norm": 1.57673180103302, "learning_rate": 8.026856839102188e-05, "loss": 0.5228117942810059, "step": 326260 }, { "epoch": 1.9394166354595765, "grad_norm": 1.16965913772583, "learning_rate": 8.026269315903296e-05, "loss": 0.4942787647247314, "step": 326270 }, { "epoch": 1.939476077536245, "grad_norm": 1.0655227899551392, "learning_rate": 8.025681806929763e-05, "loss": 0.5063376426696777, "step": 326280 }, { "epoch": 1.9395355196129132, "grad_norm": 1.6412370204925537, "learning_rate": 8.025094312184395e-05, "loss": 0.502074909210205, "step": 326290 }, { "epoch": 1.9395949616895816, "grad_norm": 1.3160514831542969, "learning_rate": 8.024506831670002e-05, "loss": 0.5062557220458984, "step": 326300 }, { "epoch": 1.93965440376625, "grad_norm": 1.3758283853530884, "learning_rate": 8.023919365389399e-05, "loss": 0.525356674194336, "step": 326310 }, { "epoch": 1.9397138458429184, "grad_norm": 1.360366702079773, "learning_rate": 8.023331913345393e-05, "loss": 0.5674281120300293, "step": 326320 }, { "epoch": 1.9397732879195868, "grad_norm": 1.3383170366287231, "learning_rate": 8.02274447554079e-05, "loss": 0.5084240436553955, "step": 326330 }, { "epoch": 1.939832729996255, "grad_norm": 1.5486490726470947, "learning_rate": 8.022157051978407e-05, "loss": 0.597780704498291, "step": 326340 }, { "epoch": 1.9398921720729234, "grad_norm": 1.3652840852737427, "learning_rate": 8.021569642661056e-05, "loss": 0.591109323501587, "step": 326350 }, { "epoch": 1.9399516141495918, "grad_norm": 1.5644574165344238, "learning_rate": 8.020982247591538e-05, "loss": 0.5626702308654785, "step": 326360 }, { "epoch": 1.9400110562262602, "grad_norm": 1.1675387620925903, "learning_rate": 8.020394866772667e-05, "loss": 0.4964385986328125, "step": 326370 }, { "epoch": 1.9400704983029287, "grad_norm": 1.3615175485610962, "learning_rate": 8.019807500207253e-05, "loss": 0.5435537815093994, "step": 326380 }, { "epoch": 1.940129940379597, "grad_norm": 0.9622455835342407, "learning_rate": 8.019220147898108e-05, "loss": 0.5594379425048828, "step": 326390 }, { "epoch": 1.9401893824562655, "grad_norm": 0.9584774971008301, "learning_rate": 8.018632809848037e-05, "loss": 0.5546779632568359, "step": 326400 }, { "epoch": 1.940248824532934, "grad_norm": 1.4597870111465454, "learning_rate": 8.018045486059854e-05, "loss": 0.5013880729675293, "step": 326410 }, { "epoch": 1.9403082666096023, "grad_norm": 1.2633888721466064, "learning_rate": 8.017458176536367e-05, "loss": 0.5660808563232422, "step": 326420 }, { "epoch": 1.9403677086862707, "grad_norm": 1.586209774017334, "learning_rate": 8.016870881280384e-05, "loss": 0.49654207229614256, "step": 326430 }, { "epoch": 1.9404271507629391, "grad_norm": 1.6581214666366577, "learning_rate": 8.016283600294719e-05, "loss": 0.5459088325500489, "step": 326440 }, { "epoch": 1.9404865928396076, "grad_norm": 1.524851679801941, "learning_rate": 8.015696333582174e-05, "loss": 0.5675289630889893, "step": 326450 }, { "epoch": 1.940546034916276, "grad_norm": 1.3833967447280884, "learning_rate": 8.015109081145564e-05, "loss": 0.566032886505127, "step": 326460 }, { "epoch": 1.9406054769929444, "grad_norm": 1.2330764532089233, "learning_rate": 8.0145218429877e-05, "loss": 0.49858675003051756, "step": 326470 }, { "epoch": 1.9406649190696126, "grad_norm": 1.213110327720642, "learning_rate": 8.013934619111385e-05, "loss": 0.5153008460998535, "step": 326480 }, { "epoch": 1.940724361146281, "grad_norm": 1.6828240156173706, "learning_rate": 8.013347409519432e-05, "loss": 0.49141407012939453, "step": 326490 }, { "epoch": 1.9407838032229494, "grad_norm": 1.445970892906189, "learning_rate": 8.012760214214645e-05, "loss": 0.49988436698913574, "step": 326500 }, { "epoch": 1.9408432452996178, "grad_norm": 1.144758939743042, "learning_rate": 8.012173033199841e-05, "loss": 0.4994304656982422, "step": 326510 }, { "epoch": 1.940902687376286, "grad_norm": 1.3181469440460205, "learning_rate": 8.011585866477824e-05, "loss": 0.5844980239868164, "step": 326520 }, { "epoch": 1.9409621294529544, "grad_norm": 1.9182898998260498, "learning_rate": 8.010998714051401e-05, "loss": 0.5247835159301758, "step": 326530 }, { "epoch": 1.9410215715296228, "grad_norm": 1.5654891729354858, "learning_rate": 8.010411575923387e-05, "loss": 0.5665318965911865, "step": 326540 }, { "epoch": 1.9410810136062913, "grad_norm": 1.5391151905059814, "learning_rate": 8.009824452096588e-05, "loss": 0.5755651950836181, "step": 326550 }, { "epoch": 1.9411404556829597, "grad_norm": 1.2912250757217407, "learning_rate": 8.009237342573808e-05, "loss": 0.5570985794067382, "step": 326560 }, { "epoch": 1.941199897759628, "grad_norm": 1.2359648942947388, "learning_rate": 8.00865024735786e-05, "loss": 0.49121904373168945, "step": 326570 }, { "epoch": 1.9412593398362965, "grad_norm": 1.3791110515594482, "learning_rate": 8.008063166451551e-05, "loss": 0.5442116737365723, "step": 326580 }, { "epoch": 1.941318781912965, "grad_norm": 1.4495679140090942, "learning_rate": 8.007476099857696e-05, "loss": 0.5151727676391602, "step": 326590 }, { "epoch": 1.9413782239896333, "grad_norm": 1.5247077941894531, "learning_rate": 8.006889047579089e-05, "loss": 0.5083399295806885, "step": 326600 }, { "epoch": 1.9414376660663017, "grad_norm": 1.0222469568252563, "learning_rate": 8.00630200961855e-05, "loss": 0.5866754531860352, "step": 326610 }, { "epoch": 1.9414971081429702, "grad_norm": 1.3977138996124268, "learning_rate": 8.005714985978887e-05, "loss": 0.5599492073059082, "step": 326620 }, { "epoch": 1.9415565502196386, "grad_norm": 1.3611129522323608, "learning_rate": 8.005127976662897e-05, "loss": 0.5239312171936035, "step": 326630 }, { "epoch": 1.941615992296307, "grad_norm": 1.7002129554748535, "learning_rate": 8.004540981673401e-05, "loss": 0.5638219833374023, "step": 326640 }, { "epoch": 1.9416754343729754, "grad_norm": 1.645541787147522, "learning_rate": 8.003954001013205e-05, "loss": 0.5525720119476318, "step": 326650 }, { "epoch": 1.9417348764496436, "grad_norm": 1.395748257637024, "learning_rate": 8.003367034685108e-05, "loss": 0.5321987628936767, "step": 326660 }, { "epoch": 1.941794318526312, "grad_norm": 1.5141416788101196, "learning_rate": 8.002780082691928e-05, "loss": 0.5194123268127442, "step": 326670 }, { "epoch": 1.9418537606029804, "grad_norm": 1.0855413675308228, "learning_rate": 8.00219314503647e-05, "loss": 0.534703540802002, "step": 326680 }, { "epoch": 1.9419132026796488, "grad_norm": 1.599788784980774, "learning_rate": 8.001606221721534e-05, "loss": 0.5515250205993653, "step": 326690 }, { "epoch": 1.9419726447563173, "grad_norm": 1.4708189964294434, "learning_rate": 8.001019312749937e-05, "loss": 0.5041255950927734, "step": 326700 }, { "epoch": 1.9420320868329854, "grad_norm": 1.7217241525650024, "learning_rate": 8.000432418124487e-05, "loss": 0.5779299736022949, "step": 326710 }, { "epoch": 1.9420915289096539, "grad_norm": 1.209398627281189, "learning_rate": 7.999845537847985e-05, "loss": 0.564460277557373, "step": 326720 }, { "epoch": 1.9421509709863223, "grad_norm": 1.456493616104126, "learning_rate": 7.99925867192324e-05, "loss": 0.5334552764892578, "step": 326730 }, { "epoch": 1.9422104130629907, "grad_norm": 1.5450302362442017, "learning_rate": 7.998671820353063e-05, "loss": 0.5623385906219482, "step": 326740 }, { "epoch": 1.942269855139659, "grad_norm": 1.0532714128494263, "learning_rate": 7.99808498314026e-05, "loss": 0.5254242897033692, "step": 326750 }, { "epoch": 1.9423292972163275, "grad_norm": 1.457572340965271, "learning_rate": 7.997498160287634e-05, "loss": 0.5005424976348877, "step": 326760 }, { "epoch": 1.942388739292996, "grad_norm": 1.347151279449463, "learning_rate": 7.996911351797998e-05, "loss": 0.5764048576354981, "step": 326770 }, { "epoch": 1.9424481813696644, "grad_norm": 1.0505293607711792, "learning_rate": 7.996324557674158e-05, "loss": 0.5095256805419922, "step": 326780 }, { "epoch": 1.9425076234463328, "grad_norm": 1.69704270362854, "learning_rate": 7.995737777918915e-05, "loss": 0.554731035232544, "step": 326790 }, { "epoch": 1.9425670655230012, "grad_norm": 1.5366896390914917, "learning_rate": 7.995151012535085e-05, "loss": 0.47757625579833984, "step": 326800 }, { "epoch": 1.9426265075996696, "grad_norm": 1.4822746515274048, "learning_rate": 7.99456426152547e-05, "loss": 0.5588974952697754, "step": 326810 }, { "epoch": 1.942685949676338, "grad_norm": 1.5312062501907349, "learning_rate": 7.993977524892873e-05, "loss": 0.5130880355834961, "step": 326820 }, { "epoch": 1.9427453917530064, "grad_norm": 1.4260315895080566, "learning_rate": 7.993390802640111e-05, "loss": 0.5387703895568847, "step": 326830 }, { "epoch": 1.9428048338296748, "grad_norm": 1.5739952325820923, "learning_rate": 7.992804094769983e-05, "loss": 0.5509124755859375, "step": 326840 }, { "epoch": 1.942864275906343, "grad_norm": 1.2761411666870117, "learning_rate": 7.992217401285298e-05, "loss": 0.5442696571350097, "step": 326850 }, { "epoch": 1.9429237179830114, "grad_norm": 1.5474902391433716, "learning_rate": 7.99163072218886e-05, "loss": 0.5215940475463867, "step": 326860 }, { "epoch": 1.9429831600596799, "grad_norm": 1.5831137895584106, "learning_rate": 7.991044057483479e-05, "loss": 0.5651500701904297, "step": 326870 }, { "epoch": 1.9430426021363483, "grad_norm": 1.4214032888412476, "learning_rate": 7.990457407171959e-05, "loss": 0.4831872463226318, "step": 326880 }, { "epoch": 1.9431020442130165, "grad_norm": 1.3145983219146729, "learning_rate": 7.989870771257107e-05, "loss": 0.44596061706542967, "step": 326890 }, { "epoch": 1.9431614862896849, "grad_norm": 1.508419394493103, "learning_rate": 7.98928414974173e-05, "loss": 0.5678823947906494, "step": 326900 }, { "epoch": 1.9432209283663533, "grad_norm": 1.459241509437561, "learning_rate": 7.988697542628636e-05, "loss": 0.500145149230957, "step": 326910 }, { "epoch": 1.9432803704430217, "grad_norm": 1.2433459758758545, "learning_rate": 7.988110949920624e-05, "loss": 0.5733979225158692, "step": 326920 }, { "epoch": 1.9433398125196901, "grad_norm": 1.8700684309005737, "learning_rate": 7.987524371620507e-05, "loss": 0.5419989585876465, "step": 326930 }, { "epoch": 1.9433992545963585, "grad_norm": 1.1253896951675415, "learning_rate": 7.986937807731092e-05, "loss": 0.5521751403808594, "step": 326940 }, { "epoch": 1.943458696673027, "grad_norm": 1.6196409463882446, "learning_rate": 7.986351258255178e-05, "loss": 0.49844789505004883, "step": 326950 }, { "epoch": 1.9435181387496954, "grad_norm": 1.6500582695007324, "learning_rate": 7.985764723195575e-05, "loss": 0.5467276096343994, "step": 326960 }, { "epoch": 1.9435775808263638, "grad_norm": 1.214626431465149, "learning_rate": 7.98517820255509e-05, "loss": 0.5140547752380371, "step": 326970 }, { "epoch": 1.9436370229030322, "grad_norm": 1.2578705549240112, "learning_rate": 7.984591696336527e-05, "loss": 0.47415504455566404, "step": 326980 }, { "epoch": 1.9436964649797006, "grad_norm": 1.3138208389282227, "learning_rate": 7.984005204542691e-05, "loss": 0.5334603309631347, "step": 326990 }, { "epoch": 1.943755907056369, "grad_norm": 1.4938108921051025, "learning_rate": 7.98341872717639e-05, "loss": 0.5332879066467285, "step": 327000 }, { "epoch": 1.9438153491330374, "grad_norm": 1.4211746454238892, "learning_rate": 7.982832264240427e-05, "loss": 0.5934086322784424, "step": 327010 }, { "epoch": 1.9438747912097059, "grad_norm": 1.132790446281433, "learning_rate": 7.982245815737607e-05, "loss": 0.519223403930664, "step": 327020 }, { "epoch": 1.943934233286374, "grad_norm": 1.2981417179107666, "learning_rate": 7.981659381670739e-05, "loss": 0.5588543891906739, "step": 327030 }, { "epoch": 1.9439936753630425, "grad_norm": 1.3873192071914673, "learning_rate": 7.981072962042626e-05, "loss": 0.5279464721679688, "step": 327040 }, { "epoch": 1.9440531174397109, "grad_norm": 1.3141664266586304, "learning_rate": 7.980486556856072e-05, "loss": 0.5327387809753418, "step": 327050 }, { "epoch": 1.9441125595163793, "grad_norm": 1.4574525356292725, "learning_rate": 7.979900166113885e-05, "loss": 0.5656185150146484, "step": 327060 }, { "epoch": 1.9441720015930477, "grad_norm": 1.4185477495193481, "learning_rate": 7.979313789818868e-05, "loss": 0.5713423728942871, "step": 327070 }, { "epoch": 1.944231443669716, "grad_norm": 1.2624703645706177, "learning_rate": 7.978727427973829e-05, "loss": 0.58810453414917, "step": 327080 }, { "epoch": 1.9442908857463843, "grad_norm": 1.5093188285827637, "learning_rate": 7.978141080581568e-05, "loss": 0.5553218841552734, "step": 327090 }, { "epoch": 1.9443503278230527, "grad_norm": 1.3680397272109985, "learning_rate": 7.977554747644892e-05, "loss": 0.5779137134552002, "step": 327100 }, { "epoch": 1.9444097698997211, "grad_norm": 1.468700647354126, "learning_rate": 7.97696842916661e-05, "loss": 0.5139849185943604, "step": 327110 }, { "epoch": 1.9444692119763896, "grad_norm": 1.5444639921188354, "learning_rate": 7.976382125149516e-05, "loss": 0.5459732055664063, "step": 327120 }, { "epoch": 1.944528654053058, "grad_norm": 2.1397175788879395, "learning_rate": 7.975795835596426e-05, "loss": 0.6018279075622559, "step": 327130 }, { "epoch": 1.9445880961297264, "grad_norm": 1.50395667552948, "learning_rate": 7.975209560510142e-05, "loss": 0.5584018707275391, "step": 327140 }, { "epoch": 1.9446475382063948, "grad_norm": 1.4970334768295288, "learning_rate": 7.974623299893465e-05, "loss": 0.5166071891784668, "step": 327150 }, { "epoch": 1.9447069802830632, "grad_norm": 1.045419692993164, "learning_rate": 7.9740370537492e-05, "loss": 0.5045040130615235, "step": 327160 }, { "epoch": 1.9447664223597316, "grad_norm": 1.4869468212127686, "learning_rate": 7.973450822080158e-05, "loss": 0.554908275604248, "step": 327170 }, { "epoch": 1.9448258644364, "grad_norm": 1.236493706703186, "learning_rate": 7.972864604889132e-05, "loss": 0.510936975479126, "step": 327180 }, { "epoch": 1.9448853065130685, "grad_norm": 1.8303687572479248, "learning_rate": 7.972278402178934e-05, "loss": 0.5621635437011718, "step": 327190 }, { "epoch": 1.9449447485897369, "grad_norm": 1.308046579360962, "learning_rate": 7.971692213952371e-05, "loss": 0.5102355003356933, "step": 327200 }, { "epoch": 1.9450041906664053, "grad_norm": 1.492668867111206, "learning_rate": 7.97110604021224e-05, "loss": 0.551564359664917, "step": 327210 }, { "epoch": 1.9450636327430735, "grad_norm": 1.3127268552780151, "learning_rate": 7.970519880961345e-05, "loss": 0.5241947174072266, "step": 327220 }, { "epoch": 1.945123074819742, "grad_norm": 1.7197047472000122, "learning_rate": 7.969933736202498e-05, "loss": 0.5496434211730957, "step": 327230 }, { "epoch": 1.9451825168964103, "grad_norm": 1.383620262145996, "learning_rate": 7.969347605938496e-05, "loss": 0.5368259429931641, "step": 327240 }, { "epoch": 1.9452419589730787, "grad_norm": 1.1436160802841187, "learning_rate": 7.968761490172139e-05, "loss": 0.499650764465332, "step": 327250 }, { "epoch": 1.945301401049747, "grad_norm": 1.392866611480713, "learning_rate": 7.968175388906245e-05, "loss": 0.5098631381988525, "step": 327260 }, { "epoch": 1.9453608431264153, "grad_norm": 1.3420166969299316, "learning_rate": 7.967589302143603e-05, "loss": 0.5727896690368652, "step": 327270 }, { "epoch": 1.9454202852030837, "grad_norm": 1.545861840248108, "learning_rate": 7.967003229887022e-05, "loss": 0.5210598945617676, "step": 327280 }, { "epoch": 1.9454797272797522, "grad_norm": 1.1373443603515625, "learning_rate": 7.966417172139313e-05, "loss": 0.5213700294494629, "step": 327290 }, { "epoch": 1.9455391693564206, "grad_norm": 1.7630470991134644, "learning_rate": 7.965831128903269e-05, "loss": 0.5843187808990479, "step": 327300 }, { "epoch": 1.945598611433089, "grad_norm": 1.1514707803726196, "learning_rate": 7.965245100181695e-05, "loss": 0.4957186222076416, "step": 327310 }, { "epoch": 1.9456580535097574, "grad_norm": 1.304366946220398, "learning_rate": 7.964659085977402e-05, "loss": 0.4936398506164551, "step": 327320 }, { "epoch": 1.9457174955864258, "grad_norm": 1.2488515377044678, "learning_rate": 7.964073086293186e-05, "loss": 0.5837666988372803, "step": 327330 }, { "epoch": 1.9457769376630942, "grad_norm": 1.1207776069641113, "learning_rate": 7.963487101131852e-05, "loss": 0.49536838531494143, "step": 327340 }, { "epoch": 1.9458363797397626, "grad_norm": 1.5985509157180786, "learning_rate": 7.9629011304962e-05, "loss": 0.5540640830993653, "step": 327350 }, { "epoch": 1.945895821816431, "grad_norm": 1.2423133850097656, "learning_rate": 7.962315174389041e-05, "loss": 0.5219346523284912, "step": 327360 }, { "epoch": 1.9459552638930995, "grad_norm": 1.3133070468902588, "learning_rate": 7.961729232813173e-05, "loss": 0.5409703731536866, "step": 327370 }, { "epoch": 1.9460147059697679, "grad_norm": 1.6520345211029053, "learning_rate": 7.961143305771396e-05, "loss": 0.5464988231658936, "step": 327380 }, { "epoch": 1.9460741480464363, "grad_norm": 1.447454571723938, "learning_rate": 7.96055739326652e-05, "loss": 0.5288900375366211, "step": 327390 }, { "epoch": 1.9461335901231045, "grad_norm": 1.737207055091858, "learning_rate": 7.959971495301341e-05, "loss": 0.5928923606872558, "step": 327400 }, { "epoch": 1.946193032199773, "grad_norm": 1.0913727283477783, "learning_rate": 7.959385611878667e-05, "loss": 0.5130554676055908, "step": 327410 }, { "epoch": 1.9462524742764413, "grad_norm": 1.6258680820465088, "learning_rate": 7.958799743001297e-05, "loss": 0.5547585964202881, "step": 327420 }, { "epoch": 1.9463119163531097, "grad_norm": 1.5623114109039307, "learning_rate": 7.958213888672037e-05, "loss": 0.5465363979339599, "step": 327430 }, { "epoch": 1.9463713584297782, "grad_norm": 1.4931201934814453, "learning_rate": 7.957628048893688e-05, "loss": 0.5434072494506836, "step": 327440 }, { "epoch": 1.9464308005064463, "grad_norm": 1.8611376285552979, "learning_rate": 7.957042223669052e-05, "loss": 0.5514308452606201, "step": 327450 }, { "epoch": 1.9464902425831148, "grad_norm": 1.8005763292312622, "learning_rate": 7.956456413000931e-05, "loss": 0.5468071937561035, "step": 327460 }, { "epoch": 1.9465496846597832, "grad_norm": 1.5973105430603027, "learning_rate": 7.955870616892124e-05, "loss": 0.5224361896514893, "step": 327470 }, { "epoch": 1.9466091267364516, "grad_norm": 1.3519723415374756, "learning_rate": 7.955284835345441e-05, "loss": 0.5505453109741211, "step": 327480 }, { "epoch": 1.94666856881312, "grad_norm": 1.2474852800369263, "learning_rate": 7.95469906836368e-05, "loss": 0.5043657302856446, "step": 327490 }, { "epoch": 1.9467280108897884, "grad_norm": 1.9263229370117188, "learning_rate": 7.954113315949645e-05, "loss": 0.5684592723846436, "step": 327500 }, { "epoch": 1.9467874529664568, "grad_norm": 1.4123291969299316, "learning_rate": 7.953527578106132e-05, "loss": 0.5019224643707275, "step": 327510 }, { "epoch": 1.9468468950431252, "grad_norm": 1.4303430318832397, "learning_rate": 7.952941854835951e-05, "loss": 0.5486618518829346, "step": 327520 }, { "epoch": 1.9469063371197937, "grad_norm": 1.3793830871582031, "learning_rate": 7.952356146141901e-05, "loss": 0.5103875160217285, "step": 327530 }, { "epoch": 1.946965779196462, "grad_norm": 1.3599201440811157, "learning_rate": 7.951770452026781e-05, "loss": 0.5088809490203857, "step": 327540 }, { "epoch": 1.9470252212731305, "grad_norm": 1.361406922340393, "learning_rate": 7.951184772493397e-05, "loss": 0.5780833244323731, "step": 327550 }, { "epoch": 1.947084663349799, "grad_norm": 0.9853834509849548, "learning_rate": 7.950599107544547e-05, "loss": 0.5342319011688232, "step": 327560 }, { "epoch": 1.9471441054264673, "grad_norm": 1.4949766397476196, "learning_rate": 7.950013457183036e-05, "loss": 0.5672390937805176, "step": 327570 }, { "epoch": 1.9472035475031357, "grad_norm": 1.3271026611328125, "learning_rate": 7.949427821411662e-05, "loss": 0.5414034843444824, "step": 327580 }, { "epoch": 1.947262989579804, "grad_norm": 1.179153561592102, "learning_rate": 7.948842200233228e-05, "loss": 0.5785978317260743, "step": 327590 }, { "epoch": 1.9473224316564723, "grad_norm": 1.1224197149276733, "learning_rate": 7.948256593650538e-05, "loss": 0.5773172855377198, "step": 327600 }, { "epoch": 1.9473818737331408, "grad_norm": 1.271694302558899, "learning_rate": 7.947671001666388e-05, "loss": 0.544666862487793, "step": 327610 }, { "epoch": 1.9474413158098092, "grad_norm": 1.4664051532745361, "learning_rate": 7.947085424283587e-05, "loss": 0.5597078323364257, "step": 327620 }, { "epoch": 1.9475007578864774, "grad_norm": 1.2276909351348877, "learning_rate": 7.94649986150493e-05, "loss": 0.4803337097167969, "step": 327630 }, { "epoch": 1.9475601999631458, "grad_norm": 1.2315881252288818, "learning_rate": 7.945914313333216e-05, "loss": 0.5689412117004394, "step": 327640 }, { "epoch": 1.9476196420398142, "grad_norm": 1.4215039014816284, "learning_rate": 7.945328779771253e-05, "loss": 0.5419200897216797, "step": 327650 }, { "epoch": 1.9476790841164826, "grad_norm": 1.6201640367507935, "learning_rate": 7.944743260821841e-05, "loss": 0.545299482345581, "step": 327660 }, { "epoch": 1.947738526193151, "grad_norm": 1.0542807579040527, "learning_rate": 7.944157756487773e-05, "loss": 0.4665972709655762, "step": 327670 }, { "epoch": 1.9477979682698194, "grad_norm": 1.3991119861602783, "learning_rate": 7.94357226677186e-05, "loss": 0.5722918510437012, "step": 327680 }, { "epoch": 1.9478574103464878, "grad_norm": 1.21820867061615, "learning_rate": 7.942986791676901e-05, "loss": 0.5548967361450196, "step": 327690 }, { "epoch": 1.9479168524231563, "grad_norm": 1.4007971286773682, "learning_rate": 7.942401331205689e-05, "loss": 0.6049939632415772, "step": 327700 }, { "epoch": 1.9479762944998247, "grad_norm": 1.3003225326538086, "learning_rate": 7.941815885361028e-05, "loss": 0.5256169319152832, "step": 327710 }, { "epoch": 1.948035736576493, "grad_norm": 1.4821207523345947, "learning_rate": 7.941230454145727e-05, "loss": 0.5277949810028076, "step": 327720 }, { "epoch": 1.9480951786531615, "grad_norm": 1.6571508646011353, "learning_rate": 7.940645037562577e-05, "loss": 0.5674731254577636, "step": 327730 }, { "epoch": 1.94815462072983, "grad_norm": 1.573442816734314, "learning_rate": 7.940059635614378e-05, "loss": 0.5256542205810547, "step": 327740 }, { "epoch": 1.9482140628064983, "grad_norm": 1.323967695236206, "learning_rate": 7.93947424830394e-05, "loss": 0.5378973960876465, "step": 327750 }, { "epoch": 1.9482735048831668, "grad_norm": 1.1088250875473022, "learning_rate": 7.938888875634054e-05, "loss": 0.5182956695556641, "step": 327760 }, { "epoch": 1.948332946959835, "grad_norm": 1.339615821838379, "learning_rate": 7.93830351760752e-05, "loss": 0.5463615417480469, "step": 327770 }, { "epoch": 1.9483923890365034, "grad_norm": 1.5045042037963867, "learning_rate": 7.937718174227147e-05, "loss": 0.5545945167541504, "step": 327780 }, { "epoch": 1.9484518311131718, "grad_norm": 1.490560531616211, "learning_rate": 7.937132845495727e-05, "loss": 0.5203768253326416, "step": 327790 }, { "epoch": 1.9485112731898402, "grad_norm": 1.4473947286605835, "learning_rate": 7.936547531416063e-05, "loss": 0.5317420959472656, "step": 327800 }, { "epoch": 1.9485707152665086, "grad_norm": 1.3127161264419556, "learning_rate": 7.935962231990952e-05, "loss": 0.5711270332336426, "step": 327810 }, { "epoch": 1.9486301573431768, "grad_norm": 1.4898837804794312, "learning_rate": 7.935376947223198e-05, "loss": 0.4928293228149414, "step": 327820 }, { "epoch": 1.9486895994198452, "grad_norm": 1.5619184970855713, "learning_rate": 7.934791677115599e-05, "loss": 0.5119653701782226, "step": 327830 }, { "epoch": 1.9487490414965136, "grad_norm": 1.0007723569869995, "learning_rate": 7.934206421670956e-05, "loss": 0.5023887157440186, "step": 327840 }, { "epoch": 1.948808483573182, "grad_norm": 1.2627649307250977, "learning_rate": 7.933621180892066e-05, "loss": 0.5425264358520507, "step": 327850 }, { "epoch": 1.9488679256498505, "grad_norm": 0.9883961081504822, "learning_rate": 7.933035954781731e-05, "loss": 0.48513317108154297, "step": 327860 }, { "epoch": 1.9489273677265189, "grad_norm": 1.2761216163635254, "learning_rate": 7.932450743342747e-05, "loss": 0.5785060405731202, "step": 327870 }, { "epoch": 1.9489868098031873, "grad_norm": 1.495449185371399, "learning_rate": 7.931865546577919e-05, "loss": 0.5261722564697265, "step": 327880 }, { "epoch": 1.9490462518798557, "grad_norm": 1.3588844537734985, "learning_rate": 7.931280364490045e-05, "loss": 0.5864301204681397, "step": 327890 }, { "epoch": 1.949105693956524, "grad_norm": 1.5472065210342407, "learning_rate": 7.93069519708192e-05, "loss": 0.5098694324493408, "step": 327900 }, { "epoch": 1.9491651360331925, "grad_norm": 1.3732060194015503, "learning_rate": 7.930110044356347e-05, "loss": 0.5226744651794434, "step": 327910 }, { "epoch": 1.949224578109861, "grad_norm": 1.2408231496810913, "learning_rate": 7.929524906316125e-05, "loss": 0.5093821525573731, "step": 327920 }, { "epoch": 1.9492840201865294, "grad_norm": 0.9168959259986877, "learning_rate": 7.928939782964053e-05, "loss": 0.5597975730895997, "step": 327930 }, { "epoch": 1.9493434622631978, "grad_norm": 1.4025928974151611, "learning_rate": 7.928354674302927e-05, "loss": 0.5111577033996582, "step": 327940 }, { "epoch": 1.9494029043398662, "grad_norm": 1.6163060665130615, "learning_rate": 7.927769580335552e-05, "loss": 0.5308370590209961, "step": 327950 }, { "epoch": 1.9494623464165344, "grad_norm": 1.131744384765625, "learning_rate": 7.927184501064722e-05, "loss": 0.5562568187713623, "step": 327960 }, { "epoch": 1.9495217884932028, "grad_norm": 1.3239091634750366, "learning_rate": 7.926599436493233e-05, "loss": 0.5225486755371094, "step": 327970 }, { "epoch": 1.9495812305698712, "grad_norm": 1.4484496116638184, "learning_rate": 7.926014386623892e-05, "loss": 0.5525067329406739, "step": 327980 }, { "epoch": 1.9496406726465396, "grad_norm": 1.2936913967132568, "learning_rate": 7.925429351459492e-05, "loss": 0.5460921287536621, "step": 327990 }, { "epoch": 1.9497001147232078, "grad_norm": 1.881797432899475, "learning_rate": 7.924844331002832e-05, "loss": 0.5413235664367676, "step": 328000 }, { "epoch": 1.9497595567998762, "grad_norm": 1.2854801416397095, "learning_rate": 7.924259325256716e-05, "loss": 0.5762612819671631, "step": 328010 }, { "epoch": 1.9498189988765446, "grad_norm": 1.5718226432800293, "learning_rate": 7.923674334223936e-05, "loss": 0.6217633247375488, "step": 328020 }, { "epoch": 1.949878440953213, "grad_norm": 1.2561691999435425, "learning_rate": 7.923089357907292e-05, "loss": 0.5099655628204346, "step": 328030 }, { "epoch": 1.9499378830298815, "grad_norm": 1.452454686164856, "learning_rate": 7.922504396309585e-05, "loss": 0.47628164291381836, "step": 328040 }, { "epoch": 1.9499973251065499, "grad_norm": 1.1452823877334595, "learning_rate": 7.921919449433608e-05, "loss": 0.504633092880249, "step": 328050 }, { "epoch": 1.9500567671832183, "grad_norm": 1.6255120038986206, "learning_rate": 7.921334517282166e-05, "loss": 0.5735864639282227, "step": 328060 }, { "epoch": 1.9501162092598867, "grad_norm": 1.463857889175415, "learning_rate": 7.920749599858051e-05, "loss": 0.48593864440917967, "step": 328070 }, { "epoch": 1.9501756513365551, "grad_norm": 1.0764589309692383, "learning_rate": 7.920164697164062e-05, "loss": 0.5384486198425293, "step": 328080 }, { "epoch": 1.9502350934132235, "grad_norm": 1.2317652702331543, "learning_rate": 7.919579809203003e-05, "loss": 0.5152164459228515, "step": 328090 }, { "epoch": 1.950294535489892, "grad_norm": 1.5039923191070557, "learning_rate": 7.918994935977664e-05, "loss": 0.5939334869384766, "step": 328100 }, { "epoch": 1.9503539775665604, "grad_norm": 1.1821702718734741, "learning_rate": 7.918410077490847e-05, "loss": 0.5322186946868896, "step": 328110 }, { "epoch": 1.9504134196432288, "grad_norm": 1.4727636575698853, "learning_rate": 7.917825233745351e-05, "loss": 0.5180058479309082, "step": 328120 }, { "epoch": 1.9504728617198972, "grad_norm": 1.1720901727676392, "learning_rate": 7.91724040474397e-05, "loss": 0.557619857788086, "step": 328130 }, { "epoch": 1.9505323037965654, "grad_norm": 1.7278496026992798, "learning_rate": 7.916655590489505e-05, "loss": 0.5696008205413818, "step": 328140 }, { "epoch": 1.9505917458732338, "grad_norm": 1.4787269830703735, "learning_rate": 7.91607079098475e-05, "loss": 0.5460493087768554, "step": 328150 }, { "epoch": 1.9506511879499022, "grad_norm": 1.153781771659851, "learning_rate": 7.915486006232506e-05, "loss": 0.5423609733581543, "step": 328160 }, { "epoch": 1.9507106300265706, "grad_norm": 1.383310079574585, "learning_rate": 7.91490123623557e-05, "loss": 0.5387297630310058, "step": 328170 }, { "epoch": 1.950770072103239, "grad_norm": 1.3002880811691284, "learning_rate": 7.914316480996737e-05, "loss": 0.49393062591552733, "step": 328180 }, { "epoch": 1.9508295141799072, "grad_norm": 1.1649956703186035, "learning_rate": 7.913731740518805e-05, "loss": 0.5355082988739014, "step": 328190 }, { "epoch": 1.9508889562565757, "grad_norm": 1.2907685041427612, "learning_rate": 7.913147014804571e-05, "loss": 0.5506473541259765, "step": 328200 }, { "epoch": 1.950948398333244, "grad_norm": 1.75031578540802, "learning_rate": 7.912562303856834e-05, "loss": 0.48520355224609374, "step": 328210 }, { "epoch": 1.9510078404099125, "grad_norm": 1.4637823104858398, "learning_rate": 7.911977607678393e-05, "loss": 0.5010141849517822, "step": 328220 }, { "epoch": 1.951067282486581, "grad_norm": 1.4043315649032593, "learning_rate": 7.911392926272035e-05, "loss": 0.546477222442627, "step": 328230 }, { "epoch": 1.9511267245632493, "grad_norm": 1.291430950164795, "learning_rate": 7.91080825964057e-05, "loss": 0.525968074798584, "step": 328240 }, { "epoch": 1.9511861666399177, "grad_norm": 1.2889634370803833, "learning_rate": 7.910223607786788e-05, "loss": 0.6051934242248536, "step": 328250 }, { "epoch": 1.9512456087165861, "grad_norm": 1.5212304592132568, "learning_rate": 7.90963897071348e-05, "loss": 0.5625495433807373, "step": 328260 }, { "epoch": 1.9513050507932546, "grad_norm": 1.2514469623565674, "learning_rate": 7.909054348423459e-05, "loss": 0.5312849998474121, "step": 328270 }, { "epoch": 1.951364492869923, "grad_norm": 1.4453933238983154, "learning_rate": 7.908469740919507e-05, "loss": 0.5660489082336426, "step": 328280 }, { "epoch": 1.9514239349465914, "grad_norm": 1.3211873769760132, "learning_rate": 7.907885148204426e-05, "loss": 0.5561769962310791, "step": 328290 }, { "epoch": 1.9514833770232598, "grad_norm": 1.4019060134887695, "learning_rate": 7.907300570281011e-05, "loss": 0.5533408164978028, "step": 328300 }, { "epoch": 1.9515428190999282, "grad_norm": 1.4617552757263184, "learning_rate": 7.90671600715206e-05, "loss": 0.5132071018218994, "step": 328310 }, { "epoch": 1.9516022611765966, "grad_norm": 1.389436960220337, "learning_rate": 7.90613145882037e-05, "loss": 0.5577297210693359, "step": 328320 }, { "epoch": 1.9516617032532648, "grad_norm": 1.4449735879898071, "learning_rate": 7.905546925288731e-05, "loss": 0.5216944694519043, "step": 328330 }, { "epoch": 1.9517211453299332, "grad_norm": 1.5880450010299683, "learning_rate": 7.90496240655995e-05, "loss": 0.5634041786193847, "step": 328340 }, { "epoch": 1.9517805874066017, "grad_norm": 1.6369459629058838, "learning_rate": 7.904377902636815e-05, "loss": 0.5437643527984619, "step": 328350 }, { "epoch": 1.95184002948327, "grad_norm": 1.5353295803070068, "learning_rate": 7.903793413522122e-05, "loss": 0.5317925453186035, "step": 328360 }, { "epoch": 1.9518994715599383, "grad_norm": 1.7094290256500244, "learning_rate": 7.903208939218674e-05, "loss": 0.585823917388916, "step": 328370 }, { "epoch": 1.9519589136366067, "grad_norm": 1.3009051084518433, "learning_rate": 7.902624479729261e-05, "loss": 0.5025769233703613, "step": 328380 }, { "epoch": 1.952018355713275, "grad_norm": 1.3525311946868896, "learning_rate": 7.90204003505668e-05, "loss": 0.5328645229339599, "step": 328390 }, { "epoch": 1.9520777977899435, "grad_norm": 1.282650351524353, "learning_rate": 7.901455605203725e-05, "loss": 0.4752391815185547, "step": 328400 }, { "epoch": 1.952137239866612, "grad_norm": 1.6409122943878174, "learning_rate": 7.900871190173195e-05, "loss": 0.5536742687225342, "step": 328410 }, { "epoch": 1.9521966819432803, "grad_norm": 1.5204836130142212, "learning_rate": 7.900286789967888e-05, "loss": 0.5733224868774414, "step": 328420 }, { "epoch": 1.9522561240199487, "grad_norm": 1.2685836553573608, "learning_rate": 7.89970240459059e-05, "loss": 0.4760533332824707, "step": 328430 }, { "epoch": 1.9523155660966172, "grad_norm": 1.4736336469650269, "learning_rate": 7.899118034044106e-05, "loss": 0.5467446327209473, "step": 328440 }, { "epoch": 1.9523750081732856, "grad_norm": 1.3803369998931885, "learning_rate": 7.898533678331227e-05, "loss": 0.5114423274993897, "step": 328450 }, { "epoch": 1.952434450249954, "grad_norm": 1.5469554662704468, "learning_rate": 7.897949337454749e-05, "loss": 0.5222500801086426, "step": 328460 }, { "epoch": 1.9524938923266224, "grad_norm": 1.311794638633728, "learning_rate": 7.89736501141747e-05, "loss": 0.5187102317810058, "step": 328470 }, { "epoch": 1.9525533344032908, "grad_norm": 1.297560214996338, "learning_rate": 7.896780700222182e-05, "loss": 0.5947179794311523, "step": 328480 }, { "epoch": 1.9526127764799592, "grad_norm": 1.3056304454803467, "learning_rate": 7.896196403871678e-05, "loss": 0.5470745086669921, "step": 328490 }, { "epoch": 1.9526722185566276, "grad_norm": 1.3749083280563354, "learning_rate": 7.89561212236876e-05, "loss": 0.47280025482177734, "step": 328500 }, { "epoch": 1.9527316606332958, "grad_norm": 1.211778998374939, "learning_rate": 7.895027855716217e-05, "loss": 0.5261668682098388, "step": 328510 }, { "epoch": 1.9527911027099643, "grad_norm": 1.4471180438995361, "learning_rate": 7.894443603916843e-05, "loss": 0.5697550773620605, "step": 328520 }, { "epoch": 1.9528505447866327, "grad_norm": 1.3050576448440552, "learning_rate": 7.893859366973442e-05, "loss": 0.5261745929718018, "step": 328530 }, { "epoch": 1.952909986863301, "grad_norm": 1.168912649154663, "learning_rate": 7.893275144888801e-05, "loss": 0.5327383995056152, "step": 328540 }, { "epoch": 1.9529694289399695, "grad_norm": 1.093586802482605, "learning_rate": 7.892690937665714e-05, "loss": 0.5027308464050293, "step": 328550 }, { "epoch": 1.9530288710166377, "grad_norm": 1.339840054512024, "learning_rate": 7.89210674530698e-05, "loss": 0.5674895286560059, "step": 328560 }, { "epoch": 1.953088313093306, "grad_norm": 1.2119959592819214, "learning_rate": 7.89152256781539e-05, "loss": 0.5444260597229004, "step": 328570 }, { "epoch": 1.9531477551699745, "grad_norm": 1.2764605283737183, "learning_rate": 7.890938405193741e-05, "loss": 0.5045347213745117, "step": 328580 }, { "epoch": 1.953207197246643, "grad_norm": 1.353216290473938, "learning_rate": 7.890354257444827e-05, "loss": 0.5083452224731445, "step": 328590 }, { "epoch": 1.9532666393233113, "grad_norm": 1.3031458854675293, "learning_rate": 7.889770124571442e-05, "loss": 0.5448279857635498, "step": 328600 }, { "epoch": 1.9533260813999798, "grad_norm": 1.2492278814315796, "learning_rate": 7.889186006576381e-05, "loss": 0.4920334815979004, "step": 328610 }, { "epoch": 1.9533855234766482, "grad_norm": 1.4988285303115845, "learning_rate": 7.888601903462436e-05, "loss": 0.5831107139587403, "step": 328620 }, { "epoch": 1.9534449655533166, "grad_norm": 1.5707050561904907, "learning_rate": 7.888017815232402e-05, "loss": 0.5449621200561523, "step": 328630 }, { "epoch": 1.953504407629985, "grad_norm": 1.1641355752944946, "learning_rate": 7.887433741889076e-05, "loss": 0.5443906784057617, "step": 328640 }, { "epoch": 1.9535638497066534, "grad_norm": 1.1478149890899658, "learning_rate": 7.886849683435251e-05, "loss": 0.5304327964782715, "step": 328650 }, { "epoch": 1.9536232917833218, "grad_norm": 1.439326286315918, "learning_rate": 7.886265639873715e-05, "loss": 0.5004191398620605, "step": 328660 }, { "epoch": 1.9536827338599903, "grad_norm": 1.5851973295211792, "learning_rate": 7.88568161120727e-05, "loss": 0.5332305431365967, "step": 328670 }, { "epoch": 1.9537421759366587, "grad_norm": 1.3113247156143188, "learning_rate": 7.885097597438709e-05, "loss": 0.5259446144104004, "step": 328680 }, { "epoch": 1.953801618013327, "grad_norm": 1.4250679016113281, "learning_rate": 7.884513598570815e-05, "loss": 0.5555633068084717, "step": 328690 }, { "epoch": 1.9538610600899953, "grad_norm": 1.444913625717163, "learning_rate": 7.883929614606395e-05, "loss": 0.5347799301147461, "step": 328700 }, { "epoch": 1.9539205021666637, "grad_norm": 1.1101516485214233, "learning_rate": 7.883345645548242e-05, "loss": 0.5534575939178467, "step": 328710 }, { "epoch": 1.953979944243332, "grad_norm": 1.6532062292099, "learning_rate": 7.882761691399136e-05, "loss": 0.5324625015258789, "step": 328720 }, { "epoch": 1.9540393863200005, "grad_norm": 1.1277940273284912, "learning_rate": 7.882177752161884e-05, "loss": 0.5843245506286621, "step": 328730 }, { "epoch": 1.9540988283966687, "grad_norm": 1.613645076751709, "learning_rate": 7.881593827839275e-05, "loss": 0.5510001182556152, "step": 328740 }, { "epoch": 1.9541582704733371, "grad_norm": 1.4159072637557983, "learning_rate": 7.881009918434097e-05, "loss": 0.5300776958465576, "step": 328750 }, { "epoch": 1.9542177125500055, "grad_norm": 1.3078222274780273, "learning_rate": 7.880426023949152e-05, "loss": 0.5453535079956054, "step": 328760 }, { "epoch": 1.954277154626674, "grad_norm": 1.331091046333313, "learning_rate": 7.879842144387233e-05, "loss": 0.5389703750610352, "step": 328770 }, { "epoch": 1.9543365967033424, "grad_norm": 1.5396244525909424, "learning_rate": 7.879258279751127e-05, "loss": 0.5028450012207031, "step": 328780 }, { "epoch": 1.9543960387800108, "grad_norm": 1.406785011291504, "learning_rate": 7.878674430043627e-05, "loss": 0.5868368148803711, "step": 328790 }, { "epoch": 1.9544554808566792, "grad_norm": 1.5289907455444336, "learning_rate": 7.87809059526753e-05, "loss": 0.5476634502410889, "step": 328800 }, { "epoch": 1.9545149229333476, "grad_norm": 2.672090768814087, "learning_rate": 7.87750677542563e-05, "loss": 0.5730019569396972, "step": 328810 }, { "epoch": 1.954574365010016, "grad_norm": 1.5063154697418213, "learning_rate": 7.87692297052071e-05, "loss": 0.5477127075195313, "step": 328820 }, { "epoch": 1.9546338070866844, "grad_norm": 1.2020564079284668, "learning_rate": 7.876339180555576e-05, "loss": 0.5198267459869385, "step": 328830 }, { "epoch": 1.9546932491633529, "grad_norm": 1.2745589017868042, "learning_rate": 7.875755405533014e-05, "loss": 0.5226206302642822, "step": 328840 }, { "epoch": 1.9547526912400213, "grad_norm": 1.4352030754089355, "learning_rate": 7.875171645455812e-05, "loss": 0.5117274761199951, "step": 328850 }, { "epoch": 1.9548121333166897, "grad_norm": 1.5138908624649048, "learning_rate": 7.874587900326775e-05, "loss": 0.5202443122863769, "step": 328860 }, { "epoch": 1.954871575393358, "grad_norm": 1.3756071329116821, "learning_rate": 7.874004170148685e-05, "loss": 0.5801379680633545, "step": 328870 }, { "epoch": 1.9549310174700263, "grad_norm": 1.2671194076538086, "learning_rate": 7.873420454924334e-05, "loss": 0.5044963359832764, "step": 328880 }, { "epoch": 1.9549904595466947, "grad_norm": 1.0364922285079956, "learning_rate": 7.872836754656523e-05, "loss": 0.4852592468261719, "step": 328890 }, { "epoch": 1.9550499016233631, "grad_norm": 1.2063570022583008, "learning_rate": 7.87225306934804e-05, "loss": 0.5274179458618165, "step": 328900 }, { "epoch": 1.9551093437000315, "grad_norm": 1.6334439516067505, "learning_rate": 7.871669399001674e-05, "loss": 0.5988816261291504, "step": 328910 }, { "epoch": 1.9551687857767, "grad_norm": 1.525749921798706, "learning_rate": 7.871085743620214e-05, "loss": 0.5225100517272949, "step": 328920 }, { "epoch": 1.9552282278533681, "grad_norm": 1.2698028087615967, "learning_rate": 7.870502103206463e-05, "loss": 0.5173232078552246, "step": 328930 }, { "epoch": 1.9552876699300366, "grad_norm": 1.413569450378418, "learning_rate": 7.869918477763208e-05, "loss": 0.5100039005279541, "step": 328940 }, { "epoch": 1.955347112006705, "grad_norm": 1.187566876411438, "learning_rate": 7.869334867293234e-05, "loss": 0.5780272960662842, "step": 328950 }, { "epoch": 1.9554065540833734, "grad_norm": 1.6411290168762207, "learning_rate": 7.868751271799344e-05, "loss": 0.5514491081237793, "step": 328960 }, { "epoch": 1.9554659961600418, "grad_norm": 1.1264287233352661, "learning_rate": 7.868167691284324e-05, "loss": 0.5025876045227051, "step": 328970 }, { "epoch": 1.9555254382367102, "grad_norm": 1.3914635181427002, "learning_rate": 7.867584125750966e-05, "loss": 0.49689550399780275, "step": 328980 }, { "epoch": 1.9555848803133786, "grad_norm": 1.365586519241333, "learning_rate": 7.867000575202061e-05, "loss": 0.5482906341552735, "step": 328990 }, { "epoch": 1.955644322390047, "grad_norm": 1.339614987373352, "learning_rate": 7.866417039640404e-05, "loss": 0.5420355796813965, "step": 329000 }, { "epoch": 1.9557037644667155, "grad_norm": 1.674376368522644, "learning_rate": 7.865833519068779e-05, "loss": 0.5459585189819336, "step": 329010 }, { "epoch": 1.9557632065433839, "grad_norm": 1.456011176109314, "learning_rate": 7.865250013489986e-05, "loss": 0.5547020912170411, "step": 329020 }, { "epoch": 1.9558226486200523, "grad_norm": 1.2810081243515015, "learning_rate": 7.864666522906811e-05, "loss": 0.5415471076965332, "step": 329030 }, { "epoch": 1.9558820906967207, "grad_norm": 1.3193607330322266, "learning_rate": 7.864083047322049e-05, "loss": 0.5577607154846191, "step": 329040 }, { "epoch": 1.9559415327733891, "grad_norm": 1.367685317993164, "learning_rate": 7.863499586738485e-05, "loss": 0.5325445652008056, "step": 329050 }, { "epoch": 1.9560009748500575, "grad_norm": 1.3815689086914062, "learning_rate": 7.862916141158915e-05, "loss": 0.5426873207092285, "step": 329060 }, { "epoch": 1.9560604169267257, "grad_norm": 1.7099519968032837, "learning_rate": 7.862332710586133e-05, "loss": 0.5417325973510743, "step": 329070 }, { "epoch": 1.9561198590033941, "grad_norm": 1.5461065769195557, "learning_rate": 7.861749295022922e-05, "loss": 0.5368940353393554, "step": 329080 }, { "epoch": 1.9561793010800625, "grad_norm": 1.3755346536636353, "learning_rate": 7.861165894472078e-05, "loss": 0.5215405464172364, "step": 329090 }, { "epoch": 1.956238743156731, "grad_norm": 1.3534951210021973, "learning_rate": 7.86058250893639e-05, "loss": 0.5588565826416015, "step": 329100 }, { "epoch": 1.9562981852333992, "grad_norm": 1.5652410984039307, "learning_rate": 7.85999913841865e-05, "loss": 0.5191771030426026, "step": 329110 }, { "epoch": 1.9563576273100676, "grad_norm": 1.347360372543335, "learning_rate": 7.859415782921647e-05, "loss": 0.539348554611206, "step": 329120 }, { "epoch": 1.956417069386736, "grad_norm": 1.2377358675003052, "learning_rate": 7.858832442448175e-05, "loss": 0.5459731101989747, "step": 329130 }, { "epoch": 1.9564765114634044, "grad_norm": 1.2529184818267822, "learning_rate": 7.85824911700102e-05, "loss": 0.47784037590026857, "step": 329140 }, { "epoch": 1.9565359535400728, "grad_norm": 1.2487144470214844, "learning_rate": 7.857665806582972e-05, "loss": 0.5189441204071045, "step": 329150 }, { "epoch": 1.9565953956167412, "grad_norm": 1.8762856721878052, "learning_rate": 7.857082511196827e-05, "loss": 0.5518649101257325, "step": 329160 }, { "epoch": 1.9566548376934096, "grad_norm": 1.3595390319824219, "learning_rate": 7.856499230845375e-05, "loss": 0.5446486473083496, "step": 329170 }, { "epoch": 1.956714279770078, "grad_norm": 1.6799077987670898, "learning_rate": 7.855915965531396e-05, "loss": 0.5325789451599121, "step": 329180 }, { "epoch": 1.9567737218467465, "grad_norm": 1.3460040092468262, "learning_rate": 7.855332715257691e-05, "loss": 0.48969316482543945, "step": 329190 }, { "epoch": 1.9568331639234149, "grad_norm": 1.1104968786239624, "learning_rate": 7.85474948002705e-05, "loss": 0.5017213821411133, "step": 329200 }, { "epoch": 1.9568926060000833, "grad_norm": 1.7631064653396606, "learning_rate": 7.854166259842253e-05, "loss": 0.5466089248657227, "step": 329210 }, { "epoch": 1.9569520480767517, "grad_norm": 1.1417467594146729, "learning_rate": 7.853583054706102e-05, "loss": 0.5171272277832031, "step": 329220 }, { "epoch": 1.9570114901534201, "grad_norm": 1.3841075897216797, "learning_rate": 7.852999864621383e-05, "loss": 0.5311516761779785, "step": 329230 }, { "epoch": 1.9570709322300885, "grad_norm": 1.3799724578857422, "learning_rate": 7.852416689590878e-05, "loss": 0.5592103004455566, "step": 329240 }, { "epoch": 1.9571303743067567, "grad_norm": 1.4567879438400269, "learning_rate": 7.851833529617385e-05, "loss": 0.5261937141418457, "step": 329250 }, { "epoch": 1.9571898163834252, "grad_norm": 1.533789873123169, "learning_rate": 7.851250384703695e-05, "loss": 0.5428102970123291, "step": 329260 }, { "epoch": 1.9572492584600936, "grad_norm": 1.5007648468017578, "learning_rate": 7.85066725485259e-05, "loss": 0.5382452011108398, "step": 329270 }, { "epoch": 1.957308700536762, "grad_norm": 1.4950628280639648, "learning_rate": 7.850084140066865e-05, "loss": 0.5817556858062745, "step": 329280 }, { "epoch": 1.9573681426134304, "grad_norm": 1.341086745262146, "learning_rate": 7.84950104034931e-05, "loss": 0.49616570472717286, "step": 329290 }, { "epoch": 1.9574275846900986, "grad_norm": 1.3764004707336426, "learning_rate": 7.84891795570271e-05, "loss": 0.5162454605102539, "step": 329300 }, { "epoch": 1.957487026766767, "grad_norm": 0.923785388469696, "learning_rate": 7.848334886129853e-05, "loss": 0.5234591484069824, "step": 329310 }, { "epoch": 1.9575464688434354, "grad_norm": 1.5832874774932861, "learning_rate": 7.847751831633541e-05, "loss": 0.5312446117401123, "step": 329320 }, { "epoch": 1.9576059109201038, "grad_norm": 1.381698727607727, "learning_rate": 7.847168792216548e-05, "loss": 0.5242094993591309, "step": 329330 }, { "epoch": 1.9576653529967722, "grad_norm": 1.3299014568328857, "learning_rate": 7.846585767881667e-05, "loss": 0.5402198791503906, "step": 329340 }, { "epoch": 1.9577247950734407, "grad_norm": 1.3261022567749023, "learning_rate": 7.846002758631697e-05, "loss": 0.5271184921264649, "step": 329350 }, { "epoch": 1.957784237150109, "grad_norm": 1.6584129333496094, "learning_rate": 7.845419764469413e-05, "loss": 0.5559862613677978, "step": 329360 }, { "epoch": 1.9578436792267775, "grad_norm": 1.5331730842590332, "learning_rate": 7.844836785397609e-05, "loss": 0.5232741355895996, "step": 329370 }, { "epoch": 1.957903121303446, "grad_norm": 1.4246876239776611, "learning_rate": 7.84425382141908e-05, "loss": 0.5346382141113282, "step": 329380 }, { "epoch": 1.9579625633801143, "grad_norm": 1.516488790512085, "learning_rate": 7.843670872536608e-05, "loss": 0.5121864795684814, "step": 329390 }, { "epoch": 1.9580220054567827, "grad_norm": 1.443346381187439, "learning_rate": 7.843087938752982e-05, "loss": 0.6010685443878174, "step": 329400 }, { "epoch": 1.9580814475334511, "grad_norm": 1.7358887195587158, "learning_rate": 7.842505020070989e-05, "loss": 0.5300592422485352, "step": 329410 }, { "epoch": 1.9581408896101196, "grad_norm": 1.4373314380645752, "learning_rate": 7.841922116493424e-05, "loss": 0.5762953281402587, "step": 329420 }, { "epoch": 1.958200331686788, "grad_norm": 1.2008756399154663, "learning_rate": 7.84133922802307e-05, "loss": 0.46834187507629393, "step": 329430 }, { "epoch": 1.9582597737634562, "grad_norm": 1.7991633415222168, "learning_rate": 7.840756354662715e-05, "loss": 0.507074499130249, "step": 329440 }, { "epoch": 1.9583192158401246, "grad_norm": 1.6312072277069092, "learning_rate": 7.840173496415153e-05, "loss": 0.5112484931945801, "step": 329450 }, { "epoch": 1.958378657916793, "grad_norm": 1.532599925994873, "learning_rate": 7.839590653283167e-05, "loss": 0.6344060897827148, "step": 329460 }, { "epoch": 1.9584380999934614, "grad_norm": 1.098035216331482, "learning_rate": 7.839007825269545e-05, "loss": 0.5437123298645019, "step": 329470 }, { "epoch": 1.9584975420701296, "grad_norm": 1.8722761869430542, "learning_rate": 7.838425012377075e-05, "loss": 0.5133833885192871, "step": 329480 }, { "epoch": 1.958556984146798, "grad_norm": 1.3631908893585205, "learning_rate": 7.83784221460855e-05, "loss": 0.5817461967468261, "step": 329490 }, { "epoch": 1.9586164262234664, "grad_norm": 1.2276874780654907, "learning_rate": 7.837259431966755e-05, "loss": 0.4959290027618408, "step": 329500 }, { "epoch": 1.9586758683001348, "grad_norm": 1.4032375812530518, "learning_rate": 7.836676664454474e-05, "loss": 0.5756026268005371, "step": 329510 }, { "epoch": 1.9587353103768033, "grad_norm": 1.2659357786178589, "learning_rate": 7.8360939120745e-05, "loss": 0.5032790660858154, "step": 329520 }, { "epoch": 1.9587947524534717, "grad_norm": 1.148880124092102, "learning_rate": 7.83551117482962e-05, "loss": 0.545588493347168, "step": 329530 }, { "epoch": 1.95885419453014, "grad_norm": 1.3113067150115967, "learning_rate": 7.834928452722617e-05, "loss": 0.5095151424407959, "step": 329540 }, { "epoch": 1.9589136366068085, "grad_norm": 1.3921434879302979, "learning_rate": 7.834345745756284e-05, "loss": 0.5598465442657471, "step": 329550 }, { "epoch": 1.958973078683477, "grad_norm": 1.585821270942688, "learning_rate": 7.833763053933408e-05, "loss": 0.5073963642120362, "step": 329560 }, { "epoch": 1.9590325207601453, "grad_norm": 0.9840797185897827, "learning_rate": 7.83318037725677e-05, "loss": 0.5208004951477051, "step": 329570 }, { "epoch": 1.9590919628368137, "grad_norm": 1.4010156393051147, "learning_rate": 7.832597715729167e-05, "loss": 0.5151032447814942, "step": 329580 }, { "epoch": 1.9591514049134822, "grad_norm": 1.2337075471878052, "learning_rate": 7.83201506935338e-05, "loss": 0.5311907768249512, "step": 329590 }, { "epoch": 1.9592108469901506, "grad_norm": 1.4291259050369263, "learning_rate": 7.831432438132193e-05, "loss": 0.5443391799926758, "step": 329600 }, { "epoch": 1.959270289066819, "grad_norm": 1.3224139213562012, "learning_rate": 7.830849822068405e-05, "loss": 0.5728744983673095, "step": 329610 }, { "epoch": 1.9593297311434872, "grad_norm": 1.7171434164047241, "learning_rate": 7.830267221164793e-05, "loss": 0.5910902500152588, "step": 329620 }, { "epoch": 1.9593891732201556, "grad_norm": 1.3035855293273926, "learning_rate": 7.829684635424146e-05, "loss": 0.5480538368225097, "step": 329630 }, { "epoch": 1.959448615296824, "grad_norm": 1.216231107711792, "learning_rate": 7.829102064849249e-05, "loss": 0.5593530654907226, "step": 329640 }, { "epoch": 1.9595080573734924, "grad_norm": 1.400352954864502, "learning_rate": 7.828519509442895e-05, "loss": 0.5781474113464355, "step": 329650 }, { "epoch": 1.9595674994501608, "grad_norm": 1.2096956968307495, "learning_rate": 7.827936969207868e-05, "loss": 0.4972642421722412, "step": 329660 }, { "epoch": 1.959626941526829, "grad_norm": 1.2141374349594116, "learning_rate": 7.827354444146953e-05, "loss": 0.5335143089294434, "step": 329670 }, { "epoch": 1.9596863836034975, "grad_norm": 1.5740455389022827, "learning_rate": 7.826771934262936e-05, "loss": 0.5659945011138916, "step": 329680 }, { "epoch": 1.9597458256801659, "grad_norm": 1.2251911163330078, "learning_rate": 7.826189439558609e-05, "loss": 0.5206785202026367, "step": 329690 }, { "epoch": 1.9598052677568343, "grad_norm": 1.8274015188217163, "learning_rate": 7.825606960036749e-05, "loss": 0.552174186706543, "step": 329700 }, { "epoch": 1.9598647098335027, "grad_norm": 1.2827420234680176, "learning_rate": 7.82502449570015e-05, "loss": 0.5335653781890869, "step": 329710 }, { "epoch": 1.959924151910171, "grad_norm": 1.2991222143173218, "learning_rate": 7.824442046551599e-05, "loss": 0.49234886169433595, "step": 329720 }, { "epoch": 1.9599835939868395, "grad_norm": 0.9516255855560303, "learning_rate": 7.823859612593874e-05, "loss": 0.45038795471191406, "step": 329730 }, { "epoch": 1.960043036063508, "grad_norm": 1.4646432399749756, "learning_rate": 7.82327719382977e-05, "loss": 0.5258345603942871, "step": 329740 }, { "epoch": 1.9601024781401764, "grad_norm": 1.7002204656600952, "learning_rate": 7.822694790262073e-05, "loss": 0.5783220291137695, "step": 329750 }, { "epoch": 1.9601619202168448, "grad_norm": 1.6047658920288086, "learning_rate": 7.822112401893562e-05, "loss": 0.5447083950042725, "step": 329760 }, { "epoch": 1.9602213622935132, "grad_norm": 1.4828211069107056, "learning_rate": 7.821530028727024e-05, "loss": 0.5716611862182617, "step": 329770 }, { "epoch": 1.9602808043701816, "grad_norm": 1.7562414407730103, "learning_rate": 7.820947670765253e-05, "loss": 0.5690860748291016, "step": 329780 }, { "epoch": 1.96034024644685, "grad_norm": 1.5730793476104736, "learning_rate": 7.820365328011027e-05, "loss": 0.5701556205749512, "step": 329790 }, { "epoch": 1.9603996885235182, "grad_norm": 1.2850850820541382, "learning_rate": 7.819783000467131e-05, "loss": 0.5792783737182617, "step": 329800 }, { "epoch": 1.9604591306001866, "grad_norm": 1.3610950708389282, "learning_rate": 7.819200688136359e-05, "loss": 0.5015412330627441, "step": 329810 }, { "epoch": 1.960518572676855, "grad_norm": 1.3818211555480957, "learning_rate": 7.818618391021492e-05, "loss": 0.4994500160217285, "step": 329820 }, { "epoch": 1.9605780147535234, "grad_norm": 1.7184960842132568, "learning_rate": 7.818036109125309e-05, "loss": 0.5290534973144532, "step": 329830 }, { "epoch": 1.9606374568301919, "grad_norm": 1.1763417720794678, "learning_rate": 7.817453842450606e-05, "loss": 0.49398202896118165, "step": 329840 }, { "epoch": 1.96069689890686, "grad_norm": 1.6465306282043457, "learning_rate": 7.816871591000164e-05, "loss": 0.5046313285827637, "step": 329850 }, { "epoch": 1.9607563409835285, "grad_norm": 1.591517448425293, "learning_rate": 7.816289354776763e-05, "loss": 0.56607084274292, "step": 329860 }, { "epoch": 1.9608157830601969, "grad_norm": 1.846394419670105, "learning_rate": 7.8157071337832e-05, "loss": 0.5022662162780762, "step": 329870 }, { "epoch": 1.9608752251368653, "grad_norm": 1.5800262689590454, "learning_rate": 7.81512492802225e-05, "loss": 0.5459603309631348, "step": 329880 }, { "epoch": 1.9609346672135337, "grad_norm": 1.0324835777282715, "learning_rate": 7.814542737496702e-05, "loss": 0.5460695743560791, "step": 329890 }, { "epoch": 1.9609941092902021, "grad_norm": 1.4221545457839966, "learning_rate": 7.813960562209339e-05, "loss": 0.5042451858520508, "step": 329900 }, { "epoch": 1.9610535513668705, "grad_norm": 1.671573519706726, "learning_rate": 7.81337840216295e-05, "loss": 0.5983170509338379, "step": 329910 }, { "epoch": 1.961112993443539, "grad_norm": 1.56017005443573, "learning_rate": 7.812796257360315e-05, "loss": 0.5372823715209961, "step": 329920 }, { "epoch": 1.9611724355202074, "grad_norm": 1.575473427772522, "learning_rate": 7.812214127804222e-05, "loss": 0.5294236183166504, "step": 329930 }, { "epoch": 1.9612318775968758, "grad_norm": 1.4166570901870728, "learning_rate": 7.811632013497454e-05, "loss": 0.579801082611084, "step": 329940 }, { "epoch": 1.9612913196735442, "grad_norm": 1.3497650623321533, "learning_rate": 7.811049914442799e-05, "loss": 0.5746460437774659, "step": 329950 }, { "epoch": 1.9613507617502126, "grad_norm": 1.2292546033859253, "learning_rate": 7.810467830643036e-05, "loss": 0.5152403831481933, "step": 329960 }, { "epoch": 1.961410203826881, "grad_norm": 1.8071260452270508, "learning_rate": 7.809885762100955e-05, "loss": 0.5138709068298339, "step": 329970 }, { "epoch": 1.9614696459035494, "grad_norm": 1.2459570169448853, "learning_rate": 7.809303708819338e-05, "loss": 0.4796761512756348, "step": 329980 }, { "epoch": 1.9615290879802176, "grad_norm": 1.5471445322036743, "learning_rate": 7.808721670800969e-05, "loss": 0.5132313728332519, "step": 329990 }, { "epoch": 1.961588530056886, "grad_norm": 1.4353370666503906, "learning_rate": 7.808139648048631e-05, "loss": 0.5454663276672364, "step": 330000 }, { "epoch": 1.9616479721335545, "grad_norm": 1.198459506034851, "learning_rate": 7.80755764056511e-05, "loss": 0.5257553100585938, "step": 330010 }, { "epoch": 1.9617074142102229, "grad_norm": 1.180540680885315, "learning_rate": 7.806975648353192e-05, "loss": 0.5573602676391601, "step": 330020 }, { "epoch": 1.9617668562868913, "grad_norm": 1.4091402292251587, "learning_rate": 7.806393671415657e-05, "loss": 0.5457308292388916, "step": 330030 }, { "epoch": 1.9618262983635595, "grad_norm": 1.252028226852417, "learning_rate": 7.80581170975529e-05, "loss": 0.5066873550415039, "step": 330040 }, { "epoch": 1.961885740440228, "grad_norm": 1.4735034704208374, "learning_rate": 7.80522976337488e-05, "loss": 0.5338536739349365, "step": 330050 }, { "epoch": 1.9619451825168963, "grad_norm": 1.658265471458435, "learning_rate": 7.804647832277203e-05, "loss": 0.5300117015838623, "step": 330060 }, { "epoch": 1.9620046245935647, "grad_norm": 1.154440999031067, "learning_rate": 7.80406591646505e-05, "loss": 0.4925394058227539, "step": 330070 }, { "epoch": 1.9620640666702331, "grad_norm": 1.209382176399231, "learning_rate": 7.803484015941198e-05, "loss": 0.5477417945861817, "step": 330080 }, { "epoch": 1.9621235087469016, "grad_norm": 1.5192320346832275, "learning_rate": 7.802902130708433e-05, "loss": 0.5601188659667968, "step": 330090 }, { "epoch": 1.96218295082357, "grad_norm": 1.2971770763397217, "learning_rate": 7.802320260769543e-05, "loss": 0.5489385604858399, "step": 330100 }, { "epoch": 1.9622423929002384, "grad_norm": 1.2717844247817993, "learning_rate": 7.801738406127305e-05, "loss": 0.5405675411224365, "step": 330110 }, { "epoch": 1.9623018349769068, "grad_norm": 1.1813424825668335, "learning_rate": 7.80115656678451e-05, "loss": 0.5033262729644775, "step": 330120 }, { "epoch": 1.9623612770535752, "grad_norm": 1.3422588109970093, "learning_rate": 7.800574742743931e-05, "loss": 0.5624405860900878, "step": 330130 }, { "epoch": 1.9624207191302436, "grad_norm": 1.425791621208191, "learning_rate": 7.799992934008358e-05, "loss": 0.5712275505065918, "step": 330140 }, { "epoch": 1.962480161206912, "grad_norm": 1.4347597360610962, "learning_rate": 7.799411140580575e-05, "loss": 0.5537670135498047, "step": 330150 }, { "epoch": 1.9625396032835805, "grad_norm": 1.5819569826126099, "learning_rate": 7.79882936246336e-05, "loss": 0.5956038951873779, "step": 330160 }, { "epoch": 1.9625990453602487, "grad_norm": 1.8938490152359009, "learning_rate": 7.798247599659503e-05, "loss": 0.5190036773681641, "step": 330170 }, { "epoch": 1.962658487436917, "grad_norm": 1.4873805046081543, "learning_rate": 7.797665852171783e-05, "loss": 0.5334356784820556, "step": 330180 }, { "epoch": 1.9627179295135855, "grad_norm": 1.2815297842025757, "learning_rate": 7.79708412000298e-05, "loss": 0.5235018730163574, "step": 330190 }, { "epoch": 1.962777371590254, "grad_norm": 1.4543920755386353, "learning_rate": 7.796502403155881e-05, "loss": 0.4901434421539307, "step": 330200 }, { "epoch": 1.9628368136669223, "grad_norm": 1.269789695739746, "learning_rate": 7.795920701633268e-05, "loss": 0.5368660926818848, "step": 330210 }, { "epoch": 1.9628962557435905, "grad_norm": 0.9296259880065918, "learning_rate": 7.795339015437921e-05, "loss": 0.5137193202972412, "step": 330220 }, { "epoch": 1.962955697820259, "grad_norm": 1.135541558265686, "learning_rate": 7.794757344572629e-05, "loss": 0.5417310237884522, "step": 330230 }, { "epoch": 1.9630151398969273, "grad_norm": 1.2246357202529907, "learning_rate": 7.794175689040169e-05, "loss": 0.5217749595642089, "step": 330240 }, { "epoch": 1.9630745819735957, "grad_norm": 1.3735777139663696, "learning_rate": 7.793594048843327e-05, "loss": 0.5169357299804688, "step": 330250 }, { "epoch": 1.9631340240502642, "grad_norm": 1.4161099195480347, "learning_rate": 7.793012423984878e-05, "loss": 0.5494909286499023, "step": 330260 }, { "epoch": 1.9631934661269326, "grad_norm": 1.403324007987976, "learning_rate": 7.792430814467611e-05, "loss": 0.5039945602416992, "step": 330270 }, { "epoch": 1.963252908203601, "grad_norm": 1.4757159948349, "learning_rate": 7.79184922029431e-05, "loss": 0.5325215339660645, "step": 330280 }, { "epoch": 1.9633123502802694, "grad_norm": 1.2947330474853516, "learning_rate": 7.791267641467748e-05, "loss": 0.48946828842163087, "step": 330290 }, { "epoch": 1.9633717923569378, "grad_norm": 1.3801705837249756, "learning_rate": 7.790686077990719e-05, "loss": 0.555167818069458, "step": 330300 }, { "epoch": 1.9634312344336062, "grad_norm": 1.4047367572784424, "learning_rate": 7.790104529865998e-05, "loss": 0.5881773948669433, "step": 330310 }, { "epoch": 1.9634906765102746, "grad_norm": 1.2565052509307861, "learning_rate": 7.789522997096363e-05, "loss": 0.5176514625549317, "step": 330320 }, { "epoch": 1.963550118586943, "grad_norm": 1.223934292793274, "learning_rate": 7.788941479684607e-05, "loss": 0.5054072380065918, "step": 330330 }, { "epoch": 1.9636095606636115, "grad_norm": 1.6197487115859985, "learning_rate": 7.788359977633502e-05, "loss": 0.5758226394653321, "step": 330340 }, { "epoch": 1.96366900274028, "grad_norm": 1.3919438123703003, "learning_rate": 7.787778490945831e-05, "loss": 0.542735242843628, "step": 330350 }, { "epoch": 1.963728444816948, "grad_norm": 1.3745864629745483, "learning_rate": 7.787197019624383e-05, "loss": 0.5110862255096436, "step": 330360 }, { "epoch": 1.9637878868936165, "grad_norm": 1.204128384590149, "learning_rate": 7.786615563671934e-05, "loss": 0.49850988388061523, "step": 330370 }, { "epoch": 1.963847328970285, "grad_norm": 1.2435752153396606, "learning_rate": 7.786034123091266e-05, "loss": 0.5295856952667236, "step": 330380 }, { "epoch": 1.9639067710469533, "grad_norm": 1.3525488376617432, "learning_rate": 7.785452697885156e-05, "loss": 0.5136809825897217, "step": 330390 }, { "epoch": 1.9639662131236217, "grad_norm": 1.5462161302566528, "learning_rate": 7.784871288056392e-05, "loss": 0.5211648941040039, "step": 330400 }, { "epoch": 1.96402565520029, "grad_norm": 1.2297756671905518, "learning_rate": 7.784289893607757e-05, "loss": 0.5785664081573486, "step": 330410 }, { "epoch": 1.9640850972769583, "grad_norm": 1.3804093599319458, "learning_rate": 7.783708514542024e-05, "loss": 0.49962778091430665, "step": 330420 }, { "epoch": 1.9641445393536268, "grad_norm": 1.0501935482025146, "learning_rate": 7.783127150861978e-05, "loss": 0.5006941795349121, "step": 330430 }, { "epoch": 1.9642039814302952, "grad_norm": 1.1383371353149414, "learning_rate": 7.782545802570403e-05, "loss": 0.5425998210906983, "step": 330440 }, { "epoch": 1.9642634235069636, "grad_norm": 1.2099729776382446, "learning_rate": 7.781964469670075e-05, "loss": 0.5123340129852295, "step": 330450 }, { "epoch": 1.964322865583632, "grad_norm": 1.7228795289993286, "learning_rate": 7.781383152163777e-05, "loss": 0.535113525390625, "step": 330460 }, { "epoch": 1.9643823076603004, "grad_norm": 1.482787013053894, "learning_rate": 7.780801850054293e-05, "loss": 0.4996640682220459, "step": 330470 }, { "epoch": 1.9644417497369688, "grad_norm": 1.7586702108383179, "learning_rate": 7.780220563344403e-05, "loss": 0.5205683708190918, "step": 330480 }, { "epoch": 1.9645011918136372, "grad_norm": 1.5319100618362427, "learning_rate": 7.779639292036878e-05, "loss": 0.48784728050231935, "step": 330490 }, { "epoch": 1.9645606338903057, "grad_norm": 1.4595271348953247, "learning_rate": 7.779058036134512e-05, "loss": 0.5547019004821777, "step": 330500 }, { "epoch": 1.964620075966974, "grad_norm": 1.3451263904571533, "learning_rate": 7.778476795640077e-05, "loss": 0.5038496017456054, "step": 330510 }, { "epoch": 1.9646795180436425, "grad_norm": 1.3176525831222534, "learning_rate": 7.777895570556357e-05, "loss": 0.4970973491668701, "step": 330520 }, { "epoch": 1.964738960120311, "grad_norm": 1.2766897678375244, "learning_rate": 7.777314360886132e-05, "loss": 0.4524738311767578, "step": 330530 }, { "epoch": 1.964798402196979, "grad_norm": 1.335898518562317, "learning_rate": 7.776733166632182e-05, "loss": 0.5284862041473388, "step": 330540 }, { "epoch": 1.9648578442736475, "grad_norm": 1.4409338235855103, "learning_rate": 7.776151987797287e-05, "loss": 0.5047650337219238, "step": 330550 }, { "epoch": 1.964917286350316, "grad_norm": 1.300045132637024, "learning_rate": 7.775570824384227e-05, "loss": 0.5037316799163818, "step": 330560 }, { "epoch": 1.9649767284269843, "grad_norm": 1.2519004344940186, "learning_rate": 7.774989676395783e-05, "loss": 0.5289441585540772, "step": 330570 }, { "epoch": 1.9650361705036528, "grad_norm": 1.2486616373062134, "learning_rate": 7.774408543834735e-05, "loss": 0.5348186492919922, "step": 330580 }, { "epoch": 1.965095612580321, "grad_norm": 1.1380517482757568, "learning_rate": 7.773827426703861e-05, "loss": 0.5216485023498535, "step": 330590 }, { "epoch": 1.9651550546569894, "grad_norm": 1.2756297588348389, "learning_rate": 7.773246325005943e-05, "loss": 0.5170934677124024, "step": 330600 }, { "epoch": 1.9652144967336578, "grad_norm": 1.6157238483428955, "learning_rate": 7.772665238743759e-05, "loss": 0.5689141273498535, "step": 330610 }, { "epoch": 1.9652739388103262, "grad_norm": 1.299771785736084, "learning_rate": 7.772084167920091e-05, "loss": 0.5485960960388183, "step": 330620 }, { "epoch": 1.9653333808869946, "grad_norm": 1.2277350425720215, "learning_rate": 7.771503112537718e-05, "loss": 0.521912670135498, "step": 330630 }, { "epoch": 1.965392822963663, "grad_norm": 1.0610136985778809, "learning_rate": 7.770922072599417e-05, "loss": 0.5353501319885254, "step": 330640 }, { "epoch": 1.9654522650403314, "grad_norm": 1.4258933067321777, "learning_rate": 7.77034104810797e-05, "loss": 0.5788206100463867, "step": 330650 }, { "epoch": 1.9655117071169999, "grad_norm": 1.360813856124878, "learning_rate": 7.769760039066156e-05, "loss": 0.5322957038879395, "step": 330660 }, { "epoch": 1.9655711491936683, "grad_norm": 1.4351975917816162, "learning_rate": 7.769179045476757e-05, "loss": 0.5048972129821777, "step": 330670 }, { "epoch": 1.9656305912703367, "grad_norm": 1.3663139343261719, "learning_rate": 7.768598067342545e-05, "loss": 0.539422607421875, "step": 330680 }, { "epoch": 1.965690033347005, "grad_norm": 1.303114891052246, "learning_rate": 7.768017104666308e-05, "loss": 0.5497146129608155, "step": 330690 }, { "epoch": 1.9657494754236735, "grad_norm": 1.2937883138656616, "learning_rate": 7.76743615745082e-05, "loss": 0.522215747833252, "step": 330700 }, { "epoch": 1.965808917500342, "grad_norm": 1.2446997165679932, "learning_rate": 7.76685522569886e-05, "loss": 0.5615026473999023, "step": 330710 }, { "epoch": 1.9658683595770103, "grad_norm": 1.586456537246704, "learning_rate": 7.766274309413206e-05, "loss": 0.5095956802368165, "step": 330720 }, { "epoch": 1.9659278016536785, "grad_norm": 1.237710952758789, "learning_rate": 7.765693408596644e-05, "loss": 0.548581600189209, "step": 330730 }, { "epoch": 1.965987243730347, "grad_norm": 1.3085616827011108, "learning_rate": 7.765112523251947e-05, "loss": 0.49022526741027833, "step": 330740 }, { "epoch": 1.9660466858070154, "grad_norm": 1.077734112739563, "learning_rate": 7.764531653381888e-05, "loss": 0.54341139793396, "step": 330750 }, { "epoch": 1.9661061278836838, "grad_norm": 1.1624691486358643, "learning_rate": 7.763950798989259e-05, "loss": 0.5231553077697754, "step": 330760 }, { "epoch": 1.9661655699603522, "grad_norm": 1.1040058135986328, "learning_rate": 7.763369960076832e-05, "loss": 0.5519578456878662, "step": 330770 }, { "epoch": 1.9662250120370204, "grad_norm": 1.3758569955825806, "learning_rate": 7.762789136647379e-05, "loss": 0.5063553333282471, "step": 330780 }, { "epoch": 1.9662844541136888, "grad_norm": 1.2928191423416138, "learning_rate": 7.762208328703689e-05, "loss": 0.5305801391601562, "step": 330790 }, { "epoch": 1.9663438961903572, "grad_norm": 1.662103295326233, "learning_rate": 7.761627536248539e-05, "loss": 0.5741448402404785, "step": 330800 }, { "epoch": 1.9664033382670256, "grad_norm": 1.513872742652893, "learning_rate": 7.761046759284698e-05, "loss": 0.5090812683105469, "step": 330810 }, { "epoch": 1.966462780343694, "grad_norm": 1.4619907140731812, "learning_rate": 7.760465997814953e-05, "loss": 0.4932600975036621, "step": 330820 }, { "epoch": 1.9665222224203625, "grad_norm": 2.070673704147339, "learning_rate": 7.759885251842085e-05, "loss": 0.5700925827026367, "step": 330830 }, { "epoch": 1.9665816644970309, "grad_norm": 1.3466202020645142, "learning_rate": 7.759304521368864e-05, "loss": 0.5258877277374268, "step": 330840 }, { "epoch": 1.9666411065736993, "grad_norm": 1.690440058708191, "learning_rate": 7.758723806398067e-05, "loss": 0.5461990833282471, "step": 330850 }, { "epoch": 1.9667005486503677, "grad_norm": 1.8039202690124512, "learning_rate": 7.758143106932482e-05, "loss": 0.5529924392700195, "step": 330860 }, { "epoch": 1.9667599907270361, "grad_norm": 1.4291759729385376, "learning_rate": 7.75756242297488e-05, "loss": 0.5776052951812745, "step": 330870 }, { "epoch": 1.9668194328037045, "grad_norm": 1.444082498550415, "learning_rate": 7.756981754528034e-05, "loss": 0.5242300987243652, "step": 330880 }, { "epoch": 1.966878874880373, "grad_norm": 1.6016614437103271, "learning_rate": 7.756401101594734e-05, "loss": 0.5254134178161621, "step": 330890 }, { "epoch": 1.9669383169570414, "grad_norm": 1.1593281030654907, "learning_rate": 7.75582046417775e-05, "loss": 0.550198745727539, "step": 330900 }, { "epoch": 1.9669977590337095, "grad_norm": 1.3479331731796265, "learning_rate": 7.755239842279856e-05, "loss": 0.5363131523132324, "step": 330910 }, { "epoch": 1.967057201110378, "grad_norm": 1.644354224205017, "learning_rate": 7.75465923590384e-05, "loss": 0.5317916870117188, "step": 330920 }, { "epoch": 1.9671166431870464, "grad_norm": 1.5222032070159912, "learning_rate": 7.754078645052472e-05, "loss": 0.5255282402038575, "step": 330930 }, { "epoch": 1.9671760852637148, "grad_norm": 1.2712559700012207, "learning_rate": 7.753498069728527e-05, "loss": 0.4574864864349365, "step": 330940 }, { "epoch": 1.9672355273403832, "grad_norm": 1.2550479173660278, "learning_rate": 7.752917509934791e-05, "loss": 0.48191466331481936, "step": 330950 }, { "epoch": 1.9672949694170514, "grad_norm": 1.2741827964782715, "learning_rate": 7.752336965674037e-05, "loss": 0.4850801467895508, "step": 330960 }, { "epoch": 1.9673544114937198, "grad_norm": 1.362862229347229, "learning_rate": 7.75175643694904e-05, "loss": 0.5463836669921875, "step": 330970 }, { "epoch": 1.9674138535703882, "grad_norm": 1.3619707822799683, "learning_rate": 7.751175923762577e-05, "loss": 0.4883278846740723, "step": 330980 }, { "epoch": 1.9674732956470566, "grad_norm": 1.357236385345459, "learning_rate": 7.750595426117428e-05, "loss": 0.5209255218505859, "step": 330990 }, { "epoch": 1.967532737723725, "grad_norm": 1.6149542331695557, "learning_rate": 7.750014944016368e-05, "loss": 0.523654556274414, "step": 331000 }, { "epoch": 1.9675921798003935, "grad_norm": 1.3427587747573853, "learning_rate": 7.749434477462174e-05, "loss": 0.542598819732666, "step": 331010 }, { "epoch": 1.9676516218770619, "grad_norm": 1.8333678245544434, "learning_rate": 7.748854026457624e-05, "loss": 0.5535638809204102, "step": 331020 }, { "epoch": 1.9677110639537303, "grad_norm": 1.3061047792434692, "learning_rate": 7.748273591005495e-05, "loss": 0.5318380355834961, "step": 331030 }, { "epoch": 1.9677705060303987, "grad_norm": 1.4313302040100098, "learning_rate": 7.747693171108559e-05, "loss": 0.49505815505981443, "step": 331040 }, { "epoch": 1.9678299481070671, "grad_norm": 1.3274266719818115, "learning_rate": 7.7471127667696e-05, "loss": 0.5567549705505371, "step": 331050 }, { "epoch": 1.9678893901837355, "grad_norm": 2.1366734504699707, "learning_rate": 7.74653237799139e-05, "loss": 0.5549010753631591, "step": 331060 }, { "epoch": 1.967948832260404, "grad_norm": 1.3825205564498901, "learning_rate": 7.745952004776702e-05, "loss": 0.5684190273284913, "step": 331070 }, { "epoch": 1.9680082743370724, "grad_norm": 1.4536347389221191, "learning_rate": 7.745371647128319e-05, "loss": 0.5496588230133057, "step": 331080 }, { "epoch": 1.9680677164137408, "grad_norm": 1.4469091892242432, "learning_rate": 7.744791305049015e-05, "loss": 0.5642067909240722, "step": 331090 }, { "epoch": 1.968127158490409, "grad_norm": 1.289290189743042, "learning_rate": 7.744210978541566e-05, "loss": 0.5262502670288086, "step": 331100 }, { "epoch": 1.9681866005670774, "grad_norm": 1.1694022417068481, "learning_rate": 7.743630667608746e-05, "loss": 0.5374957084655761, "step": 331110 }, { "epoch": 1.9682460426437458, "grad_norm": 1.1263082027435303, "learning_rate": 7.743050372253333e-05, "loss": 0.538414716720581, "step": 331120 }, { "epoch": 1.9683054847204142, "grad_norm": 1.1736911535263062, "learning_rate": 7.742470092478105e-05, "loss": 0.4539764404296875, "step": 331130 }, { "epoch": 1.9683649267970826, "grad_norm": 1.3845367431640625, "learning_rate": 7.74188982828583e-05, "loss": 0.511589527130127, "step": 331140 }, { "epoch": 1.9684243688737508, "grad_norm": 1.0051777362823486, "learning_rate": 7.741309579679293e-05, "loss": 0.5187188148498535, "step": 331150 }, { "epoch": 1.9684838109504192, "grad_norm": 1.7581136226654053, "learning_rate": 7.740729346661266e-05, "loss": 0.5797815322875977, "step": 331160 }, { "epoch": 1.9685432530270877, "grad_norm": 1.1826759576797485, "learning_rate": 7.740149129234524e-05, "loss": 0.5613295555114746, "step": 331170 }, { "epoch": 1.968602695103756, "grad_norm": 1.2221925258636475, "learning_rate": 7.739568927401844e-05, "loss": 0.5315944671630859, "step": 331180 }, { "epoch": 1.9686621371804245, "grad_norm": 1.3927867412567139, "learning_rate": 7.738988741166e-05, "loss": 0.5481135368347168, "step": 331190 }, { "epoch": 1.968721579257093, "grad_norm": 1.533226490020752, "learning_rate": 7.738408570529767e-05, "loss": 0.5974073886871338, "step": 331200 }, { "epoch": 1.9687810213337613, "grad_norm": 1.4624922275543213, "learning_rate": 7.737828415495925e-05, "loss": 0.5555825233459473, "step": 331210 }, { "epoch": 1.9688404634104297, "grad_norm": 1.2422184944152832, "learning_rate": 7.737248276067244e-05, "loss": 0.5250069618225097, "step": 331220 }, { "epoch": 1.9688999054870981, "grad_norm": 1.2808493375778198, "learning_rate": 7.736668152246503e-05, "loss": 0.5581853866577149, "step": 331230 }, { "epoch": 1.9689593475637666, "grad_norm": 1.11445951461792, "learning_rate": 7.736088044036469e-05, "loss": 0.5659761428833008, "step": 331240 }, { "epoch": 1.969018789640435, "grad_norm": 1.2594361305236816, "learning_rate": 7.735507951439929e-05, "loss": 0.5297691345214843, "step": 331250 }, { "epoch": 1.9690782317171034, "grad_norm": 1.3482768535614014, "learning_rate": 7.734927874459652e-05, "loss": 0.5587663650512695, "step": 331260 }, { "epoch": 1.9691376737937718, "grad_norm": 1.092398762702942, "learning_rate": 7.734347813098406e-05, "loss": 0.5820562362670898, "step": 331270 }, { "epoch": 1.96919711587044, "grad_norm": 1.5859858989715576, "learning_rate": 7.733767767358979e-05, "loss": 0.5749046325683593, "step": 331280 }, { "epoch": 1.9692565579471084, "grad_norm": 1.5383373498916626, "learning_rate": 7.73318773724414e-05, "loss": 0.5447915077209473, "step": 331290 }, { "epoch": 1.9693160000237768, "grad_norm": 1.3668268918991089, "learning_rate": 7.73260772275666e-05, "loss": 0.529813003540039, "step": 331300 }, { "epoch": 1.9693754421004452, "grad_norm": 1.7585502862930298, "learning_rate": 7.732027723899318e-05, "loss": 0.5685298919677735, "step": 331310 }, { "epoch": 1.9694348841771137, "grad_norm": 1.644274353981018, "learning_rate": 7.731447740674891e-05, "loss": 0.5734519481658935, "step": 331320 }, { "epoch": 1.9694943262537818, "grad_norm": 1.318197250366211, "learning_rate": 7.730867773086147e-05, "loss": 0.5046194076538086, "step": 331330 }, { "epoch": 1.9695537683304503, "grad_norm": 1.356305718421936, "learning_rate": 7.73028782113586e-05, "loss": 0.5918150901794433, "step": 331340 }, { "epoch": 1.9696132104071187, "grad_norm": 1.4776372909545898, "learning_rate": 7.729707884826814e-05, "loss": 0.5222455978393554, "step": 331350 }, { "epoch": 1.969672652483787, "grad_norm": 1.370024561882019, "learning_rate": 7.729127964161773e-05, "loss": 0.5475831508636475, "step": 331360 }, { "epoch": 1.9697320945604555, "grad_norm": 1.5417757034301758, "learning_rate": 7.728548059143513e-05, "loss": 0.5093041896820069, "step": 331370 }, { "epoch": 1.969791536637124, "grad_norm": 1.593489646911621, "learning_rate": 7.727968169774813e-05, "loss": 0.5523725032806397, "step": 331380 }, { "epoch": 1.9698509787137923, "grad_norm": 1.4732494354248047, "learning_rate": 7.727388296058444e-05, "loss": 0.565761947631836, "step": 331390 }, { "epoch": 1.9699104207904607, "grad_norm": 1.569810152053833, "learning_rate": 7.726808437997175e-05, "loss": 0.5218039512634277, "step": 331400 }, { "epoch": 1.9699698628671292, "grad_norm": 1.3544940948486328, "learning_rate": 7.726228595593792e-05, "loss": 0.5095078468322753, "step": 331410 }, { "epoch": 1.9700293049437976, "grad_norm": 1.192935824394226, "learning_rate": 7.72564876885106e-05, "loss": 0.5728443622589111, "step": 331420 }, { "epoch": 1.970088747020466, "grad_norm": 1.2793909311294556, "learning_rate": 7.725068957771749e-05, "loss": 0.5073025703430176, "step": 331430 }, { "epoch": 1.9701481890971344, "grad_norm": 1.447278618812561, "learning_rate": 7.724489162358644e-05, "loss": 0.5904383659362793, "step": 331440 }, { "epoch": 1.9702076311738028, "grad_norm": 1.2426490783691406, "learning_rate": 7.723909382614509e-05, "loss": 0.5743735313415528, "step": 331450 }, { "epoch": 1.9702670732504712, "grad_norm": 1.1704649925231934, "learning_rate": 7.723329618542121e-05, "loss": 0.526881742477417, "step": 331460 }, { "epoch": 1.9703265153271394, "grad_norm": 1.3614081144332886, "learning_rate": 7.722749870144253e-05, "loss": 0.4850581645965576, "step": 331470 }, { "epoch": 1.9703859574038078, "grad_norm": 1.211200475692749, "learning_rate": 7.72217013742368e-05, "loss": 0.4906303405761719, "step": 331480 }, { "epoch": 1.9704453994804763, "grad_norm": 1.3949600458145142, "learning_rate": 7.721590420383173e-05, "loss": 0.5492902278900147, "step": 331490 }, { "epoch": 1.9705048415571447, "grad_norm": 1.2845940589904785, "learning_rate": 7.721010719025506e-05, "loss": 0.5377049446105957, "step": 331500 }, { "epoch": 1.970564283633813, "grad_norm": 1.3117690086364746, "learning_rate": 7.720431033353452e-05, "loss": 0.6289453983306885, "step": 331510 }, { "epoch": 1.9706237257104813, "grad_norm": 1.2304178476333618, "learning_rate": 7.719851363369786e-05, "loss": 0.5507346153259277, "step": 331520 }, { "epoch": 1.9706831677871497, "grad_norm": 1.6334842443466187, "learning_rate": 7.719271709077276e-05, "loss": 0.5546943664550781, "step": 331530 }, { "epoch": 1.970742609863818, "grad_norm": 1.0598065853118896, "learning_rate": 7.718692070478702e-05, "loss": 0.49376707077026366, "step": 331540 }, { "epoch": 1.9708020519404865, "grad_norm": 1.6909000873565674, "learning_rate": 7.718112447576831e-05, "loss": 0.5548521041870117, "step": 331550 }, { "epoch": 1.970861494017155, "grad_norm": 1.5564589500427246, "learning_rate": 7.717532840374435e-05, "loss": 0.5662436008453369, "step": 331560 }, { "epoch": 1.9709209360938234, "grad_norm": 1.280013918876648, "learning_rate": 7.71695324887429e-05, "loss": 0.4944723129272461, "step": 331570 }, { "epoch": 1.9709803781704918, "grad_norm": 1.148202896118164, "learning_rate": 7.716373673079171e-05, "loss": 0.5325652122497558, "step": 331580 }, { "epoch": 1.9710398202471602, "grad_norm": 1.491689920425415, "learning_rate": 7.715794112991846e-05, "loss": 0.5366219520568848, "step": 331590 }, { "epoch": 1.9710992623238286, "grad_norm": 1.2680734395980835, "learning_rate": 7.715214568615086e-05, "loss": 0.4682905197143555, "step": 331600 }, { "epoch": 1.971158704400497, "grad_norm": 1.5081982612609863, "learning_rate": 7.714635039951668e-05, "loss": 0.5173784732818604, "step": 331610 }, { "epoch": 1.9712181464771654, "grad_norm": 1.2080811262130737, "learning_rate": 7.714055527004362e-05, "loss": 0.5166650772094726, "step": 331620 }, { "epoch": 1.9712775885538338, "grad_norm": 1.4118046760559082, "learning_rate": 7.713476029775941e-05, "loss": 0.5318902015686036, "step": 331630 }, { "epoch": 1.9713370306305023, "grad_norm": 1.2892273664474487, "learning_rate": 7.712896548269177e-05, "loss": 0.5063400745391846, "step": 331640 }, { "epoch": 1.9713964727071704, "grad_norm": 1.198819875717163, "learning_rate": 7.712317082486842e-05, "loss": 0.5402998447418212, "step": 331650 }, { "epoch": 1.9714559147838389, "grad_norm": 1.3427375555038452, "learning_rate": 7.711737632431703e-05, "loss": 0.532340145111084, "step": 331660 }, { "epoch": 1.9715153568605073, "grad_norm": 1.4276118278503418, "learning_rate": 7.711158198106543e-05, "loss": 0.5779845714569092, "step": 331670 }, { "epoch": 1.9715747989371757, "grad_norm": 1.6026737689971924, "learning_rate": 7.710578779514124e-05, "loss": 0.5065487384796142, "step": 331680 }, { "epoch": 1.971634241013844, "grad_norm": 1.3498637676239014, "learning_rate": 7.709999376657222e-05, "loss": 0.6077921867370606, "step": 331690 }, { "epoch": 1.9716936830905123, "grad_norm": 1.227038860321045, "learning_rate": 7.709419989538607e-05, "loss": 0.5113569736480713, "step": 331700 }, { "epoch": 1.9717531251671807, "grad_norm": 1.4587870836257935, "learning_rate": 7.708840618161053e-05, "loss": 0.5340403556823731, "step": 331710 }, { "epoch": 1.9718125672438491, "grad_norm": 2.028792142868042, "learning_rate": 7.70826126252733e-05, "loss": 0.5602592468261719, "step": 331720 }, { "epoch": 1.9718720093205175, "grad_norm": 1.3013209104537964, "learning_rate": 7.707681922640207e-05, "loss": 0.525985860824585, "step": 331730 }, { "epoch": 1.971931451397186, "grad_norm": 1.1150466203689575, "learning_rate": 7.707102598502458e-05, "loss": 0.4748800754547119, "step": 331740 }, { "epoch": 1.9719908934738544, "grad_norm": 1.6364549398422241, "learning_rate": 7.706523290116856e-05, "loss": 0.5574366569519043, "step": 331750 }, { "epoch": 1.9720503355505228, "grad_norm": 1.4621453285217285, "learning_rate": 7.705943997486167e-05, "loss": 0.5578371047973633, "step": 331760 }, { "epoch": 1.9721097776271912, "grad_norm": 1.019181728363037, "learning_rate": 7.705364720613169e-05, "loss": 0.511568546295166, "step": 331770 }, { "epoch": 1.9721692197038596, "grad_norm": 1.151463270187378, "learning_rate": 7.70478545950063e-05, "loss": 0.5279936790466309, "step": 331780 }, { "epoch": 1.972228661780528, "grad_norm": 1.2659069299697876, "learning_rate": 7.704206214151315e-05, "loss": 0.485045051574707, "step": 331790 }, { "epoch": 1.9722881038571964, "grad_norm": 0.9376118779182434, "learning_rate": 7.703626984568005e-05, "loss": 0.5424599647521973, "step": 331800 }, { "epoch": 1.9723475459338649, "grad_norm": 1.1471755504608154, "learning_rate": 7.703047770753466e-05, "loss": 0.538044786453247, "step": 331810 }, { "epoch": 1.9724069880105333, "grad_norm": 1.6374597549438477, "learning_rate": 7.702468572710471e-05, "loss": 0.5968281745910644, "step": 331820 }, { "epoch": 1.9724664300872017, "grad_norm": 1.1694707870483398, "learning_rate": 7.701889390441781e-05, "loss": 0.4994699478149414, "step": 331830 }, { "epoch": 1.9725258721638699, "grad_norm": 1.4877901077270508, "learning_rate": 7.701310223950182e-05, "loss": 0.5575111389160157, "step": 331840 }, { "epoch": 1.9725853142405383, "grad_norm": 1.3576754331588745, "learning_rate": 7.700731073238437e-05, "loss": 0.5477148056030273, "step": 331850 }, { "epoch": 1.9726447563172067, "grad_norm": 1.4061756134033203, "learning_rate": 7.700151938309308e-05, "loss": 0.4950401782989502, "step": 331860 }, { "epoch": 1.9727041983938751, "grad_norm": 1.3155156373977661, "learning_rate": 7.699572819165584e-05, "loss": 0.48398661613464355, "step": 331870 }, { "epoch": 1.9727636404705435, "grad_norm": 1.7964147329330444, "learning_rate": 7.698993715810019e-05, "loss": 0.5413488388061524, "step": 331880 }, { "epoch": 1.9728230825472117, "grad_norm": 1.3768378496170044, "learning_rate": 7.698414628245388e-05, "loss": 0.5636198997497559, "step": 331890 }, { "epoch": 1.9728825246238801, "grad_norm": 1.4528281688690186, "learning_rate": 7.697835556474466e-05, "loss": 0.5029129028320313, "step": 331900 }, { "epoch": 1.9729419667005486, "grad_norm": 1.3942488431930542, "learning_rate": 7.697256500500019e-05, "loss": 0.6041724681854248, "step": 331910 }, { "epoch": 1.973001408777217, "grad_norm": 1.1176165342330933, "learning_rate": 7.696677460324814e-05, "loss": 0.5041571617126465, "step": 331920 }, { "epoch": 1.9730608508538854, "grad_norm": 1.333724856376648, "learning_rate": 7.696098435951631e-05, "loss": 0.5716598987579345, "step": 331930 }, { "epoch": 1.9731202929305538, "grad_norm": 1.2126811742782593, "learning_rate": 7.695519427383229e-05, "loss": 0.5374209403991699, "step": 331940 }, { "epoch": 1.9731797350072222, "grad_norm": 1.3274003267288208, "learning_rate": 7.694940434622385e-05, "loss": 0.4858292579650879, "step": 331950 }, { "epoch": 1.9732391770838906, "grad_norm": 1.2076187133789062, "learning_rate": 7.694361457671862e-05, "loss": 0.5719107627868653, "step": 331960 }, { "epoch": 1.973298619160559, "grad_norm": 1.601099967956543, "learning_rate": 7.693782496534434e-05, "loss": 0.46924653053283694, "step": 331970 }, { "epoch": 1.9733580612372275, "grad_norm": 1.3277051448822021, "learning_rate": 7.693203551212873e-05, "loss": 0.5575831413269043, "step": 331980 }, { "epoch": 1.9734175033138959, "grad_norm": 1.5507653951644897, "learning_rate": 7.692624621709943e-05, "loss": 0.5206892013549804, "step": 331990 }, { "epoch": 1.9734769453905643, "grad_norm": 1.229952335357666, "learning_rate": 7.692045708028419e-05, "loss": 0.5334143161773681, "step": 332000 }, { "epoch": 1.9735363874672327, "grad_norm": 1.4218798875808716, "learning_rate": 7.691466810171064e-05, "loss": 0.5461829662322998, "step": 332010 }, { "epoch": 1.973595829543901, "grad_norm": 1.6345347166061401, "learning_rate": 7.69088792814065e-05, "loss": 0.4942976474761963, "step": 332020 }, { "epoch": 1.9736552716205693, "grad_norm": 1.815661907196045, "learning_rate": 7.690309061939948e-05, "loss": 0.6027550220489502, "step": 332030 }, { "epoch": 1.9737147136972377, "grad_norm": 1.5695462226867676, "learning_rate": 7.689730211571728e-05, "loss": 0.5221417427062989, "step": 332040 }, { "epoch": 1.9737741557739061, "grad_norm": 1.1462111473083496, "learning_rate": 7.689151377038754e-05, "loss": 0.5374936103820801, "step": 332050 }, { "epoch": 1.9738335978505746, "grad_norm": 1.2826639413833618, "learning_rate": 7.688572558343801e-05, "loss": 0.5078816413879395, "step": 332060 }, { "epoch": 1.9738930399272427, "grad_norm": 1.3840898275375366, "learning_rate": 7.687993755489632e-05, "loss": 0.5533162117004394, "step": 332070 }, { "epoch": 1.9739524820039112, "grad_norm": 1.459139108657837, "learning_rate": 7.687414968479021e-05, "loss": 0.5639577865600586, "step": 332080 }, { "epoch": 1.9740119240805796, "grad_norm": 1.3916935920715332, "learning_rate": 7.686836197314728e-05, "loss": 0.5126565933227539, "step": 332090 }, { "epoch": 1.974071366157248, "grad_norm": 1.689756989479065, "learning_rate": 7.686257441999536e-05, "loss": 0.5574478149414063, "step": 332100 }, { "epoch": 1.9741308082339164, "grad_norm": 1.473370909690857, "learning_rate": 7.6856787025362e-05, "loss": 0.5659480094909668, "step": 332110 }, { "epoch": 1.9741902503105848, "grad_norm": 1.4643547534942627, "learning_rate": 7.685099978927494e-05, "loss": 0.5431093692779541, "step": 332120 }, { "epoch": 1.9742496923872532, "grad_norm": 1.5075039863586426, "learning_rate": 7.684521271176189e-05, "loss": 0.592259693145752, "step": 332130 }, { "epoch": 1.9743091344639216, "grad_norm": 1.467057466506958, "learning_rate": 7.683942579285051e-05, "loss": 0.5444059848785401, "step": 332140 }, { "epoch": 1.97436857654059, "grad_norm": 1.1206607818603516, "learning_rate": 7.683363903256847e-05, "loss": 0.5022518634796143, "step": 332150 }, { "epoch": 1.9744280186172585, "grad_norm": 1.2854080200195312, "learning_rate": 7.682785243094343e-05, "loss": 0.5684935569763183, "step": 332160 }, { "epoch": 1.9744874606939269, "grad_norm": 1.2733488082885742, "learning_rate": 7.682206598800317e-05, "loss": 0.5535691261291504, "step": 332170 }, { "epoch": 1.9745469027705953, "grad_norm": 1.1420131921768188, "learning_rate": 7.681627970377526e-05, "loss": 0.5274153709411621, "step": 332180 }, { "epoch": 1.9746063448472637, "grad_norm": 1.5782331228256226, "learning_rate": 7.681049357828742e-05, "loss": 0.5663018703460694, "step": 332190 }, { "epoch": 1.9746657869239321, "grad_norm": 1.098819375038147, "learning_rate": 7.680470761156736e-05, "loss": 0.5072849273681641, "step": 332200 }, { "epoch": 1.9747252290006003, "grad_norm": 1.5395965576171875, "learning_rate": 7.67989218036427e-05, "loss": 0.6246189117431641, "step": 332210 }, { "epoch": 1.9747846710772687, "grad_norm": 1.5357376337051392, "learning_rate": 7.679313615454115e-05, "loss": 0.5592206954956055, "step": 332220 }, { "epoch": 1.9748441131539372, "grad_norm": 1.2175934314727783, "learning_rate": 7.678735066429039e-05, "loss": 0.508372688293457, "step": 332230 }, { "epoch": 1.9749035552306056, "grad_norm": 1.5643738508224487, "learning_rate": 7.678156533291812e-05, "loss": 0.5418784141540527, "step": 332240 }, { "epoch": 1.974962997307274, "grad_norm": 1.366879940032959, "learning_rate": 7.677578016045193e-05, "loss": 0.5480135917663574, "step": 332250 }, { "epoch": 1.9750224393839422, "grad_norm": 1.250271201133728, "learning_rate": 7.676999514691958e-05, "loss": 0.5331621170043945, "step": 332260 }, { "epoch": 1.9750818814606106, "grad_norm": 1.9550081491470337, "learning_rate": 7.676421029234873e-05, "loss": 0.5352682113647461, "step": 332270 }, { "epoch": 1.975141323537279, "grad_norm": 1.6647909879684448, "learning_rate": 7.6758425596767e-05, "loss": 0.5034309387207031, "step": 332280 }, { "epoch": 1.9752007656139474, "grad_norm": 1.335439682006836, "learning_rate": 7.675264106020213e-05, "loss": 0.5193346023559571, "step": 332290 }, { "epoch": 1.9752602076906158, "grad_norm": 1.023151159286499, "learning_rate": 7.674685668268176e-05, "loss": 0.5338663101196289, "step": 332300 }, { "epoch": 1.9753196497672842, "grad_norm": 1.2491213083267212, "learning_rate": 7.674107246423356e-05, "loss": 0.5471212863922119, "step": 332310 }, { "epoch": 1.9753790918439527, "grad_norm": 1.5925801992416382, "learning_rate": 7.673528840488515e-05, "loss": 0.5764140129089356, "step": 332320 }, { "epoch": 1.975438533920621, "grad_norm": 1.3167448043823242, "learning_rate": 7.672950450466431e-05, "loss": 0.4720633029937744, "step": 332330 }, { "epoch": 1.9754979759972895, "grad_norm": 1.2130781412124634, "learning_rate": 7.672372076359866e-05, "loss": 0.5505263328552246, "step": 332340 }, { "epoch": 1.975557418073958, "grad_norm": 1.5457513332366943, "learning_rate": 7.671793718171578e-05, "loss": 0.5297977447509765, "step": 332350 }, { "epoch": 1.9756168601506263, "grad_norm": 1.5408607721328735, "learning_rate": 7.671215375904348e-05, "loss": 0.4598038673400879, "step": 332360 }, { "epoch": 1.9756763022272947, "grad_norm": 1.2907322645187378, "learning_rate": 7.670637049560934e-05, "loss": 0.5275321960449219, "step": 332370 }, { "epoch": 1.9757357443039631, "grad_norm": 1.462300419807434, "learning_rate": 7.6700587391441e-05, "loss": 0.4839335441589355, "step": 332380 }, { "epoch": 1.9757951863806313, "grad_norm": 1.2212822437286377, "learning_rate": 7.669480444656623e-05, "loss": 0.5026001453399658, "step": 332390 }, { "epoch": 1.9758546284572998, "grad_norm": 1.3607112169265747, "learning_rate": 7.66890216610126e-05, "loss": 0.5591839790344239, "step": 332400 }, { "epoch": 1.9759140705339682, "grad_norm": 1.1177194118499756, "learning_rate": 7.668323903480776e-05, "loss": 0.4918262004852295, "step": 332410 }, { "epoch": 1.9759735126106366, "grad_norm": 1.5400224924087524, "learning_rate": 7.66774565679795e-05, "loss": 0.5404530048370362, "step": 332420 }, { "epoch": 1.976032954687305, "grad_norm": 1.41117262840271, "learning_rate": 7.667167426055537e-05, "loss": 0.5680965900421142, "step": 332430 }, { "epoch": 1.9760923967639732, "grad_norm": 1.6024426221847534, "learning_rate": 7.666589211256305e-05, "loss": 0.5954020500183106, "step": 332440 }, { "epoch": 1.9761518388406416, "grad_norm": 1.432314395904541, "learning_rate": 7.66601101240302e-05, "loss": 0.5529672145843506, "step": 332450 }, { "epoch": 1.97621128091731, "grad_norm": 1.1780507564544678, "learning_rate": 7.665432829498451e-05, "loss": 0.5457130432128906, "step": 332460 }, { "epoch": 1.9762707229939784, "grad_norm": 1.6151872873306274, "learning_rate": 7.66485466254536e-05, "loss": 0.591666316986084, "step": 332470 }, { "epoch": 1.9763301650706468, "grad_norm": 0.6604659557342529, "learning_rate": 7.664276511546513e-05, "loss": 0.5001390933990478, "step": 332480 }, { "epoch": 1.9763896071473153, "grad_norm": 1.6369014978408813, "learning_rate": 7.66369837650468e-05, "loss": 0.5523836135864257, "step": 332490 }, { "epoch": 1.9764490492239837, "grad_norm": 1.562677264213562, "learning_rate": 7.663120257422622e-05, "loss": 0.566308069229126, "step": 332500 }, { "epoch": 1.976508491300652, "grad_norm": 1.5638163089752197, "learning_rate": 7.662542154303105e-05, "loss": 0.5538636207580566, "step": 332510 }, { "epoch": 1.9765679333773205, "grad_norm": 1.1450985670089722, "learning_rate": 7.661964067148897e-05, "loss": 0.5449857234954834, "step": 332520 }, { "epoch": 1.976627375453989, "grad_norm": 1.870851755142212, "learning_rate": 7.661385995962764e-05, "loss": 0.5375612258911133, "step": 332530 }, { "epoch": 1.9766868175306573, "grad_norm": 0.9846851229667664, "learning_rate": 7.660807940747468e-05, "loss": 0.4912566184997559, "step": 332540 }, { "epoch": 1.9767462596073258, "grad_norm": 1.5108071565628052, "learning_rate": 7.660229901505773e-05, "loss": 0.5258710861206055, "step": 332550 }, { "epoch": 1.9768057016839942, "grad_norm": 1.1640321016311646, "learning_rate": 7.659651878240448e-05, "loss": 0.5395123481750488, "step": 332560 }, { "epoch": 1.9768651437606626, "grad_norm": 1.0055854320526123, "learning_rate": 7.659073870954259e-05, "loss": 0.4946931838989258, "step": 332570 }, { "epoch": 1.9769245858373308, "grad_norm": 1.178764820098877, "learning_rate": 7.658495879649966e-05, "loss": 0.5521633148193359, "step": 332580 }, { "epoch": 1.9769840279139992, "grad_norm": 1.2470743656158447, "learning_rate": 7.657917904330339e-05, "loss": 0.4725661277770996, "step": 332590 }, { "epoch": 1.9770434699906676, "grad_norm": 1.4737753868103027, "learning_rate": 7.657339944998139e-05, "loss": 0.5931427001953125, "step": 332600 }, { "epoch": 1.977102912067336, "grad_norm": 1.3856061697006226, "learning_rate": 7.656762001656133e-05, "loss": 0.5699562072753906, "step": 332610 }, { "epoch": 1.9771623541440044, "grad_norm": 1.2324919700622559, "learning_rate": 7.656184074307084e-05, "loss": 0.5923779010772705, "step": 332620 }, { "epoch": 1.9772217962206726, "grad_norm": 1.3317688703536987, "learning_rate": 7.655606162953759e-05, "loss": 0.5357718467712402, "step": 332630 }, { "epoch": 1.977281238297341, "grad_norm": 1.444608449935913, "learning_rate": 7.655028267598919e-05, "loss": 0.4992358684539795, "step": 332640 }, { "epoch": 1.9773406803740095, "grad_norm": 1.30461847782135, "learning_rate": 7.654450388245333e-05, "loss": 0.5171268463134766, "step": 332650 }, { "epoch": 1.9774001224506779, "grad_norm": 1.3775429725646973, "learning_rate": 7.653872524895761e-05, "loss": 0.5476040840148926, "step": 332660 }, { "epoch": 1.9774595645273463, "grad_norm": 1.7282313108444214, "learning_rate": 7.653294677552974e-05, "loss": 0.5324152946472168, "step": 332670 }, { "epoch": 1.9775190066040147, "grad_norm": 1.3425161838531494, "learning_rate": 7.652716846219726e-05, "loss": 0.49776639938354494, "step": 332680 }, { "epoch": 1.977578448680683, "grad_norm": 1.21480131149292, "learning_rate": 7.652139030898788e-05, "loss": 0.5020467281341553, "step": 332690 }, { "epoch": 1.9776378907573515, "grad_norm": 1.3614789247512817, "learning_rate": 7.651561231592925e-05, "loss": 0.5420732975006104, "step": 332700 }, { "epoch": 1.97769733283402, "grad_norm": 1.0667849779129028, "learning_rate": 7.650983448304895e-05, "loss": 0.5288963317871094, "step": 332710 }, { "epoch": 1.9777567749106884, "grad_norm": 1.081028699874878, "learning_rate": 7.65040568103747e-05, "loss": 0.5226439476013184, "step": 332720 }, { "epoch": 1.9778162169873568, "grad_norm": 1.5077697038650513, "learning_rate": 7.649827929793408e-05, "loss": 0.5548118591308594, "step": 332730 }, { "epoch": 1.9778756590640252, "grad_norm": 1.6193249225616455, "learning_rate": 7.649250194575472e-05, "loss": 0.5948746204376221, "step": 332740 }, { "epoch": 1.9779351011406936, "grad_norm": 1.110459804534912, "learning_rate": 7.648672475386429e-05, "loss": 0.544029426574707, "step": 332750 }, { "epoch": 1.9779945432173618, "grad_norm": 1.6715548038482666, "learning_rate": 7.648094772229044e-05, "loss": 0.4951038360595703, "step": 332760 }, { "epoch": 1.9780539852940302, "grad_norm": 1.3932350873947144, "learning_rate": 7.647517085106075e-05, "loss": 0.5178762435913086, "step": 332770 }, { "epoch": 1.9781134273706986, "grad_norm": 1.5893542766571045, "learning_rate": 7.646939414020291e-05, "loss": 0.5284050941467285, "step": 332780 }, { "epoch": 1.978172869447367, "grad_norm": 1.6284611225128174, "learning_rate": 7.646361758974454e-05, "loss": 0.4914389133453369, "step": 332790 }, { "epoch": 1.9782323115240354, "grad_norm": 1.1252145767211914, "learning_rate": 7.645784119971327e-05, "loss": 0.5295627593994141, "step": 332800 }, { "epoch": 1.9782917536007036, "grad_norm": 1.53708016872406, "learning_rate": 7.645206497013666e-05, "loss": 0.5295573234558105, "step": 332810 }, { "epoch": 1.978351195677372, "grad_norm": 1.524530291557312, "learning_rate": 7.644628890104246e-05, "loss": 0.5356340408325195, "step": 332820 }, { "epoch": 1.9784106377540405, "grad_norm": 1.0376098155975342, "learning_rate": 7.644051299245827e-05, "loss": 0.5669547557830811, "step": 332830 }, { "epoch": 1.9784700798307089, "grad_norm": 1.053889513015747, "learning_rate": 7.643473724441163e-05, "loss": 0.49142799377441404, "step": 332840 }, { "epoch": 1.9785295219073773, "grad_norm": 1.2684682607650757, "learning_rate": 7.64289616569303e-05, "loss": 0.5023253440856934, "step": 332850 }, { "epoch": 1.9785889639840457, "grad_norm": 1.296011209487915, "learning_rate": 7.642318623004183e-05, "loss": 0.5197216987609863, "step": 332860 }, { "epoch": 1.9786484060607141, "grad_norm": 1.0370813608169556, "learning_rate": 7.641741096377385e-05, "loss": 0.5509854793548584, "step": 332870 }, { "epoch": 1.9787078481373825, "grad_norm": 1.1890079975128174, "learning_rate": 7.641163585815398e-05, "loss": 0.5302004814147949, "step": 332880 }, { "epoch": 1.978767290214051, "grad_norm": 1.3854900598526, "learning_rate": 7.640586091320994e-05, "loss": 0.5545451164245605, "step": 332890 }, { "epoch": 1.9788267322907194, "grad_norm": 1.327093482017517, "learning_rate": 7.64000861289692e-05, "loss": 0.5027840614318848, "step": 332900 }, { "epoch": 1.9788861743673878, "grad_norm": 1.5146350860595703, "learning_rate": 7.639431150545953e-05, "loss": 0.5572182655334472, "step": 332910 }, { "epoch": 1.9789456164440562, "grad_norm": 1.5739561319351196, "learning_rate": 7.638853704270847e-05, "loss": 0.47985410690307617, "step": 332920 }, { "epoch": 1.9790050585207246, "grad_norm": 1.7560038566589355, "learning_rate": 7.638276274074367e-05, "loss": 0.5360657691955566, "step": 332930 }, { "epoch": 1.979064500597393, "grad_norm": 1.3898544311523438, "learning_rate": 7.637698859959271e-05, "loss": 0.5213886737823487, "step": 332940 }, { "epoch": 1.9791239426740612, "grad_norm": 1.4008368253707886, "learning_rate": 7.637121461928331e-05, "loss": 0.5673483848571778, "step": 332950 }, { "epoch": 1.9791833847507296, "grad_norm": 1.2350411415100098, "learning_rate": 7.636544079984297e-05, "loss": 0.5629210472106934, "step": 332960 }, { "epoch": 1.979242826827398, "grad_norm": 1.0424786806106567, "learning_rate": 7.635966714129939e-05, "loss": 0.5357837677001953, "step": 332970 }, { "epoch": 1.9793022689040665, "grad_norm": 1.5955098867416382, "learning_rate": 7.635389364368019e-05, "loss": 0.5737105369567871, "step": 332980 }, { "epoch": 1.9793617109807347, "grad_norm": 1.3980544805526733, "learning_rate": 7.634812030701298e-05, "loss": 0.5671457290649414, "step": 332990 }, { "epoch": 1.979421153057403, "grad_norm": 1.4429253339767456, "learning_rate": 7.63423471313253e-05, "loss": 0.5506897926330566, "step": 333000 }, { "epoch": 1.9794805951340715, "grad_norm": 1.6128454208374023, "learning_rate": 7.633657411664487e-05, "loss": 0.5282833099365234, "step": 333010 }, { "epoch": 1.97954003721074, "grad_norm": 1.347493290901184, "learning_rate": 7.633080126299928e-05, "loss": 0.46411590576171874, "step": 333020 }, { "epoch": 1.9795994792874083, "grad_norm": 1.1303367614746094, "learning_rate": 7.632502857041612e-05, "loss": 0.5178332328796387, "step": 333030 }, { "epoch": 1.9796589213640767, "grad_norm": 1.6397531032562256, "learning_rate": 7.6319256038923e-05, "loss": 0.5274796485900879, "step": 333040 }, { "epoch": 1.9797183634407451, "grad_norm": 1.422999382019043, "learning_rate": 7.631348366854758e-05, "loss": 0.567198371887207, "step": 333050 }, { "epoch": 1.9797778055174136, "grad_norm": 1.1309802532196045, "learning_rate": 7.630771145931743e-05, "loss": 0.5828029155731201, "step": 333060 }, { "epoch": 1.979837247594082, "grad_norm": 1.3323744535446167, "learning_rate": 7.630193941126018e-05, "loss": 0.5275659561157227, "step": 333070 }, { "epoch": 1.9798966896707504, "grad_norm": 1.359861135482788, "learning_rate": 7.629616752440345e-05, "loss": 0.5383270740509033, "step": 333080 }, { "epoch": 1.9799561317474188, "grad_norm": 1.5232560634613037, "learning_rate": 7.629039579877483e-05, "loss": 0.5110711097717285, "step": 333090 }, { "epoch": 1.9800155738240872, "grad_norm": 1.8309814929962158, "learning_rate": 7.628462423440192e-05, "loss": 0.544270658493042, "step": 333100 }, { "epoch": 1.9800750159007556, "grad_norm": 1.2939270734786987, "learning_rate": 7.627885283131237e-05, "loss": 0.5681182861328125, "step": 333110 }, { "epoch": 1.980134457977424, "grad_norm": 1.1913971900939941, "learning_rate": 7.627308158953379e-05, "loss": 0.581813907623291, "step": 333120 }, { "epoch": 1.9801939000540922, "grad_norm": 1.5479644536972046, "learning_rate": 7.626731050909373e-05, "loss": 0.47192087173461916, "step": 333130 }, { "epoch": 1.9802533421307607, "grad_norm": 1.6082652807235718, "learning_rate": 7.626153959001985e-05, "loss": 0.5448858261108398, "step": 333140 }, { "epoch": 1.980312784207429, "grad_norm": 1.1628626585006714, "learning_rate": 7.625576883233976e-05, "loss": 0.537678337097168, "step": 333150 }, { "epoch": 1.9803722262840975, "grad_norm": 1.551128625869751, "learning_rate": 7.624999823608102e-05, "loss": 0.5600977897644043, "step": 333160 }, { "epoch": 1.980431668360766, "grad_norm": 1.4200105667114258, "learning_rate": 7.624422780127122e-05, "loss": 0.5046175956726074, "step": 333170 }, { "epoch": 1.980491110437434, "grad_norm": 1.2985605001449585, "learning_rate": 7.623845752793806e-05, "loss": 0.5055986404418945, "step": 333180 }, { "epoch": 1.9805505525141025, "grad_norm": 1.320804238319397, "learning_rate": 7.62326874161091e-05, "loss": 0.5125194072723389, "step": 333190 }, { "epoch": 1.980609994590771, "grad_norm": 1.281712532043457, "learning_rate": 7.622691746581186e-05, "loss": 0.5478336334228515, "step": 333200 }, { "epoch": 1.9806694366674393, "grad_norm": 1.3829655647277832, "learning_rate": 7.622114767707405e-05, "loss": 0.5481973648071289, "step": 333210 }, { "epoch": 1.9807288787441077, "grad_norm": 1.7346514463424683, "learning_rate": 7.621537804992322e-05, "loss": 0.5788207054138184, "step": 333220 }, { "epoch": 1.9807883208207762, "grad_norm": 1.1116116046905518, "learning_rate": 7.620960858438699e-05, "loss": 0.4956368446350098, "step": 333230 }, { "epoch": 1.9808477628974446, "grad_norm": 1.5394809246063232, "learning_rate": 7.620383928049295e-05, "loss": 0.5299843788146973, "step": 333240 }, { "epoch": 1.980907204974113, "grad_norm": 1.3817009925842285, "learning_rate": 7.619807013826869e-05, "loss": 0.5351568222045898, "step": 333250 }, { "epoch": 1.9809666470507814, "grad_norm": 1.461728572845459, "learning_rate": 7.61923011577418e-05, "loss": 0.5504133224487304, "step": 333260 }, { "epoch": 1.9810260891274498, "grad_norm": 1.535845398902893, "learning_rate": 7.618653233893993e-05, "loss": 0.5071852207183838, "step": 333270 }, { "epoch": 1.9810855312041182, "grad_norm": 1.4367973804473877, "learning_rate": 7.618076368189064e-05, "loss": 0.5096149444580078, "step": 333280 }, { "epoch": 1.9811449732807866, "grad_norm": 1.5532994270324707, "learning_rate": 7.617499518662153e-05, "loss": 0.5066818237304688, "step": 333290 }, { "epoch": 1.981204415357455, "grad_norm": 1.3152828216552734, "learning_rate": 7.61692268531601e-05, "loss": 0.5390283584594726, "step": 333300 }, { "epoch": 1.9812638574341235, "grad_norm": 1.8314987421035767, "learning_rate": 7.616345868153412e-05, "loss": 0.5457484722137451, "step": 333310 }, { "epoch": 1.9813232995107917, "grad_norm": 1.180422306060791, "learning_rate": 7.61576906717711e-05, "loss": 0.5429475784301758, "step": 333320 }, { "epoch": 1.98138274158746, "grad_norm": 1.6889965534210205, "learning_rate": 7.615192282389858e-05, "loss": 0.5329435348510743, "step": 333330 }, { "epoch": 1.9814421836641285, "grad_norm": 1.4688007831573486, "learning_rate": 7.614615513794421e-05, "loss": 0.5587703704833984, "step": 333340 }, { "epoch": 1.981501625740797, "grad_norm": 1.8983027935028076, "learning_rate": 7.61403876139356e-05, "loss": 0.5753933906555175, "step": 333350 }, { "epoch": 1.981561067817465, "grad_norm": 1.44717538356781, "learning_rate": 7.613462025190026e-05, "loss": 0.587125301361084, "step": 333360 }, { "epoch": 1.9816205098941335, "grad_norm": 1.280748724937439, "learning_rate": 7.612885305186588e-05, "loss": 0.5265149593353271, "step": 333370 }, { "epoch": 1.981679951970802, "grad_norm": 1.5297393798828125, "learning_rate": 7.612308601386e-05, "loss": 0.5561587810516357, "step": 333380 }, { "epoch": 1.9817393940474703, "grad_norm": 1.183583378791809, "learning_rate": 7.611731913791015e-05, "loss": 0.5612264156341553, "step": 333390 }, { "epoch": 1.9817988361241388, "grad_norm": 1.3792932033538818, "learning_rate": 7.6111552424044e-05, "loss": 0.5238970756530762, "step": 333400 }, { "epoch": 1.9818582782008072, "grad_norm": 1.3833646774291992, "learning_rate": 7.610578587228916e-05, "loss": 0.5470174312591553, "step": 333410 }, { "epoch": 1.9819177202774756, "grad_norm": 1.5422126054763794, "learning_rate": 7.610001948267312e-05, "loss": 0.518547773361206, "step": 333420 }, { "epoch": 1.981977162354144, "grad_norm": 1.2905964851379395, "learning_rate": 7.609425325522345e-05, "loss": 0.5151826858520507, "step": 333430 }, { "epoch": 1.9820366044308124, "grad_norm": 1.0530240535736084, "learning_rate": 7.608848718996789e-05, "loss": 0.4555346488952637, "step": 333440 }, { "epoch": 1.9820960465074808, "grad_norm": 1.7020580768585205, "learning_rate": 7.608272128693387e-05, "loss": 0.5184554100036621, "step": 333450 }, { "epoch": 1.9821554885841492, "grad_norm": 1.0289791822433472, "learning_rate": 7.607695554614904e-05, "loss": 0.5541234016418457, "step": 333460 }, { "epoch": 1.9822149306608177, "grad_norm": 1.1588159799575806, "learning_rate": 7.607118996764098e-05, "loss": 0.5799618721008301, "step": 333470 }, { "epoch": 1.982274372737486, "grad_norm": 1.1500203609466553, "learning_rate": 7.606542455143726e-05, "loss": 0.48987407684326173, "step": 333480 }, { "epoch": 1.9823338148141545, "grad_norm": 1.4631578922271729, "learning_rate": 7.60596592975654e-05, "loss": 0.6076132774353027, "step": 333490 }, { "epoch": 1.9823932568908227, "grad_norm": 1.3770010471343994, "learning_rate": 7.605389420605311e-05, "loss": 0.5536497116088868, "step": 333500 }, { "epoch": 1.982452698967491, "grad_norm": 1.3384720087051392, "learning_rate": 7.604812927692788e-05, "loss": 0.4876728057861328, "step": 333510 }, { "epoch": 1.9825121410441595, "grad_norm": 1.5947930812835693, "learning_rate": 7.604236451021731e-05, "loss": 0.5349011898040772, "step": 333520 }, { "epoch": 1.982571583120828, "grad_norm": 1.2917217016220093, "learning_rate": 7.603659990594893e-05, "loss": 0.5399412155151367, "step": 333530 }, { "epoch": 1.9826310251974963, "grad_norm": 1.8246393203735352, "learning_rate": 7.603083546415039e-05, "loss": 0.5427715301513671, "step": 333540 }, { "epoch": 1.9826904672741645, "grad_norm": 1.7575892210006714, "learning_rate": 7.602507118484923e-05, "loss": 0.5115821838378907, "step": 333550 }, { "epoch": 1.982749909350833, "grad_norm": 1.5299627780914307, "learning_rate": 7.601930706807301e-05, "loss": 0.6018741130828857, "step": 333560 }, { "epoch": 1.9828093514275014, "grad_norm": 1.6690858602523804, "learning_rate": 7.601354311384934e-05, "loss": 0.5354689598083496, "step": 333570 }, { "epoch": 1.9828687935041698, "grad_norm": 1.4604301452636719, "learning_rate": 7.600777932220575e-05, "loss": 0.509381628036499, "step": 333580 }, { "epoch": 1.9829282355808382, "grad_norm": 1.2426038980484009, "learning_rate": 7.600201569316985e-05, "loss": 0.493912410736084, "step": 333590 }, { "epoch": 1.9829876776575066, "grad_norm": 1.2988665103912354, "learning_rate": 7.599625222676921e-05, "loss": 0.5197830200195312, "step": 333600 }, { "epoch": 1.983047119734175, "grad_norm": 1.349126935005188, "learning_rate": 7.599048892303136e-05, "loss": 0.508312463760376, "step": 333610 }, { "epoch": 1.9831065618108434, "grad_norm": 1.5857850313186646, "learning_rate": 7.59847257819839e-05, "loss": 0.531587028503418, "step": 333620 }, { "epoch": 1.9831660038875119, "grad_norm": 1.2170038223266602, "learning_rate": 7.59789628036544e-05, "loss": 0.524253511428833, "step": 333630 }, { "epoch": 1.9832254459641803, "grad_norm": 1.3256012201309204, "learning_rate": 7.597319998807044e-05, "loss": 0.504733657836914, "step": 333640 }, { "epoch": 1.9832848880408487, "grad_norm": 1.543007731437683, "learning_rate": 7.596743733525957e-05, "loss": 0.5479413032531738, "step": 333650 }, { "epoch": 1.983344330117517, "grad_norm": 1.1406503915786743, "learning_rate": 7.596167484524934e-05, "loss": 0.5808059692382812, "step": 333660 }, { "epoch": 1.9834037721941855, "grad_norm": 1.2193702459335327, "learning_rate": 7.595591251806735e-05, "loss": 0.526338768005371, "step": 333670 }, { "epoch": 1.983463214270854, "grad_norm": 1.5090280771255493, "learning_rate": 7.595015035374114e-05, "loss": 0.5147539138793945, "step": 333680 }, { "epoch": 1.9835226563475221, "grad_norm": 1.2255021333694458, "learning_rate": 7.594438835229827e-05, "loss": 0.5406692504882813, "step": 333690 }, { "epoch": 1.9835820984241905, "grad_norm": 1.5767797231674194, "learning_rate": 7.593862651376633e-05, "loss": 0.5990010261535644, "step": 333700 }, { "epoch": 1.983641540500859, "grad_norm": 1.035746693611145, "learning_rate": 7.593286483817285e-05, "loss": 0.527506160736084, "step": 333710 }, { "epoch": 1.9837009825775274, "grad_norm": 1.315382719039917, "learning_rate": 7.592710332554542e-05, "loss": 0.5335623741149902, "step": 333720 }, { "epoch": 1.9837604246541956, "grad_norm": 1.5490944385528564, "learning_rate": 7.592134197591161e-05, "loss": 0.5168599128723145, "step": 333730 }, { "epoch": 1.983819866730864, "grad_norm": 1.2970515489578247, "learning_rate": 7.591558078929897e-05, "loss": 0.5056755065917968, "step": 333740 }, { "epoch": 1.9838793088075324, "grad_norm": 1.7186641693115234, "learning_rate": 7.590981976573504e-05, "loss": 0.5221364021301269, "step": 333750 }, { "epoch": 1.9839387508842008, "grad_norm": 1.5771394968032837, "learning_rate": 7.590405890524739e-05, "loss": 0.5319961071014404, "step": 333760 }, { "epoch": 1.9839981929608692, "grad_norm": 1.5206525325775146, "learning_rate": 7.589829820786358e-05, "loss": 0.5345130920410156, "step": 333770 }, { "epoch": 1.9840576350375376, "grad_norm": 1.5750125646591187, "learning_rate": 7.589253767361117e-05, "loss": 0.5317746639251709, "step": 333780 }, { "epoch": 1.984117077114206, "grad_norm": 1.1666814088821411, "learning_rate": 7.588677730251769e-05, "loss": 0.5306811332702637, "step": 333790 }, { "epoch": 1.9841765191908745, "grad_norm": 1.2922481298446655, "learning_rate": 7.588101709461075e-05, "loss": 0.5597461700439453, "step": 333800 }, { "epoch": 1.9842359612675429, "grad_norm": 1.544646978378296, "learning_rate": 7.587525704991786e-05, "loss": 0.5353262901306153, "step": 333810 }, { "epoch": 1.9842954033442113, "grad_norm": 1.145289421081543, "learning_rate": 7.586949716846658e-05, "loss": 0.5360903263092041, "step": 333820 }, { "epoch": 1.9843548454208797, "grad_norm": 0.8868001699447632, "learning_rate": 7.586373745028447e-05, "loss": 0.5332110404968262, "step": 333830 }, { "epoch": 1.9844142874975481, "grad_norm": 1.1332871913909912, "learning_rate": 7.585797789539913e-05, "loss": 0.5506913661956787, "step": 333840 }, { "epoch": 1.9844737295742165, "grad_norm": 1.4111523628234863, "learning_rate": 7.5852218503838e-05, "loss": 0.541373348236084, "step": 333850 }, { "epoch": 1.984533171650885, "grad_norm": 1.3681824207305908, "learning_rate": 7.584645927562875e-05, "loss": 0.5220505714416503, "step": 333860 }, { "epoch": 1.9845926137275531, "grad_norm": 1.4844486713409424, "learning_rate": 7.584070021079885e-05, "loss": 0.5606556892395019, "step": 333870 }, { "epoch": 1.9846520558042215, "grad_norm": 1.6864248514175415, "learning_rate": 7.58349413093759e-05, "loss": 0.4960988998413086, "step": 333880 }, { "epoch": 1.98471149788089, "grad_norm": 1.195915937423706, "learning_rate": 7.582918257138738e-05, "loss": 0.6116692543029785, "step": 333890 }, { "epoch": 1.9847709399575584, "grad_norm": 1.0268114805221558, "learning_rate": 7.582342399686093e-05, "loss": 0.510213565826416, "step": 333900 }, { "epoch": 1.9848303820342268, "grad_norm": 1.2373085021972656, "learning_rate": 7.581766558582404e-05, "loss": 0.5781155586242676, "step": 333910 }, { "epoch": 1.984889824110895, "grad_norm": 1.136842966079712, "learning_rate": 7.581190733830423e-05, "loss": 0.5723111152648925, "step": 333920 }, { "epoch": 1.9849492661875634, "grad_norm": 1.3863736391067505, "learning_rate": 7.580614925432914e-05, "loss": 0.538877296447754, "step": 333930 }, { "epoch": 1.9850087082642318, "grad_norm": 1.417974591255188, "learning_rate": 7.580039133392624e-05, "loss": 0.5125277519226075, "step": 333940 }, { "epoch": 1.9850681503409002, "grad_norm": 1.8371236324310303, "learning_rate": 7.579463357712304e-05, "loss": 0.5274861812591553, "step": 333950 }, { "epoch": 1.9851275924175686, "grad_norm": 1.4885016679763794, "learning_rate": 7.578887598394719e-05, "loss": 0.5255899429321289, "step": 333960 }, { "epoch": 1.985187034494237, "grad_norm": 1.4341403245925903, "learning_rate": 7.57831185544262e-05, "loss": 0.5381321907043457, "step": 333970 }, { "epoch": 1.9852464765709055, "grad_norm": 1.219753384590149, "learning_rate": 7.57773612885875e-05, "loss": 0.5717196464538574, "step": 333980 }, { "epoch": 1.9853059186475739, "grad_norm": 1.3463788032531738, "learning_rate": 7.577160418645879e-05, "loss": 0.5212165832519531, "step": 333990 }, { "epoch": 1.9853653607242423, "grad_norm": 1.2859820127487183, "learning_rate": 7.576584724806752e-05, "loss": 0.5024051189422607, "step": 334000 }, { "epoch": 1.9854248028009107, "grad_norm": 1.7480095624923706, "learning_rate": 7.576009047344126e-05, "loss": 0.6224353790283204, "step": 334010 }, { "epoch": 1.9854842448775791, "grad_norm": 1.1037931442260742, "learning_rate": 7.57543338626075e-05, "loss": 0.5178877830505371, "step": 334020 }, { "epoch": 1.9855436869542475, "grad_norm": 1.1739282608032227, "learning_rate": 7.574857741559385e-05, "loss": 0.5435480594635009, "step": 334030 }, { "epoch": 1.985603129030916, "grad_norm": 1.47505521774292, "learning_rate": 7.574282113242781e-05, "loss": 0.5541591644287109, "step": 334040 }, { "epoch": 1.9856625711075844, "grad_norm": 1.4225956201553345, "learning_rate": 7.57370650131369e-05, "loss": 0.5392201900482178, "step": 334050 }, { "epoch": 1.9857220131842526, "grad_norm": 1.190006136894226, "learning_rate": 7.57313090577487e-05, "loss": 0.5218311786651612, "step": 334060 }, { "epoch": 1.985781455260921, "grad_norm": 1.1695750951766968, "learning_rate": 7.572555326629072e-05, "loss": 0.5287919044494629, "step": 334070 }, { "epoch": 1.9858408973375894, "grad_norm": 1.1949211359024048, "learning_rate": 7.571979763879045e-05, "loss": 0.5030033588409424, "step": 334080 }, { "epoch": 1.9859003394142578, "grad_norm": 1.4422142505645752, "learning_rate": 7.571404217527549e-05, "loss": 0.5341489791870118, "step": 334090 }, { "epoch": 1.985959781490926, "grad_norm": 0.9740732312202454, "learning_rate": 7.570828687577335e-05, "loss": 0.5789454460144043, "step": 334100 }, { "epoch": 1.9860192235675944, "grad_norm": 1.5705186128616333, "learning_rate": 7.570253174031156e-05, "loss": 0.4963979244232178, "step": 334110 }, { "epoch": 1.9860786656442628, "grad_norm": 1.3296093940734863, "learning_rate": 7.569677676891765e-05, "loss": 0.5552448272705078, "step": 334120 }, { "epoch": 1.9861381077209312, "grad_norm": 1.7052147388458252, "learning_rate": 7.569102196161915e-05, "loss": 0.6063125610351563, "step": 334130 }, { "epoch": 1.9861975497975997, "grad_norm": 1.8639246225357056, "learning_rate": 7.568526731844359e-05, "loss": 0.5548748016357422, "step": 334140 }, { "epoch": 1.986256991874268, "grad_norm": 1.1617482900619507, "learning_rate": 7.567951283941848e-05, "loss": 0.5145962715148926, "step": 334150 }, { "epoch": 1.9863164339509365, "grad_norm": 1.0616518259048462, "learning_rate": 7.567375852457137e-05, "loss": 0.49701542854309083, "step": 334160 }, { "epoch": 1.986375876027605, "grad_norm": 1.3970437049865723, "learning_rate": 7.56680043739298e-05, "loss": 0.5097849845886231, "step": 334170 }, { "epoch": 1.9864353181042733, "grad_norm": 1.8570306301116943, "learning_rate": 7.566225038752124e-05, "loss": 0.5105363368988037, "step": 334180 }, { "epoch": 1.9864947601809417, "grad_norm": 1.5957742929458618, "learning_rate": 7.56564965653733e-05, "loss": 0.559026050567627, "step": 334190 }, { "epoch": 1.9865542022576101, "grad_norm": 1.3957412242889404, "learning_rate": 7.565074290751344e-05, "loss": 0.5679167747497559, "step": 334200 }, { "epoch": 1.9866136443342786, "grad_norm": 1.6801204681396484, "learning_rate": 7.564498941396918e-05, "loss": 0.4939168930053711, "step": 334210 }, { "epoch": 1.986673086410947, "grad_norm": 1.4049310684204102, "learning_rate": 7.563923608476808e-05, "loss": 0.5360962867736816, "step": 334220 }, { "epoch": 1.9867325284876154, "grad_norm": 1.399871826171875, "learning_rate": 7.563348291993765e-05, "loss": 0.5205107688903808, "step": 334230 }, { "epoch": 1.9867919705642836, "grad_norm": 1.3080929517745972, "learning_rate": 7.56277299195054e-05, "loss": 0.5395030021667481, "step": 334240 }, { "epoch": 1.986851412640952, "grad_norm": 1.4594981670379639, "learning_rate": 7.562197708349885e-05, "loss": 0.5580827236175537, "step": 334250 }, { "epoch": 1.9869108547176204, "grad_norm": 1.609499454498291, "learning_rate": 7.561622441194553e-05, "loss": 0.5187744140625, "step": 334260 }, { "epoch": 1.9869702967942888, "grad_norm": 0.8056827783584595, "learning_rate": 7.561047190487296e-05, "loss": 0.5076231956481934, "step": 334270 }, { "epoch": 1.9870297388709572, "grad_norm": 1.5806515216827393, "learning_rate": 7.560471956230865e-05, "loss": 0.522706127166748, "step": 334280 }, { "epoch": 1.9870891809476254, "grad_norm": 1.0696614980697632, "learning_rate": 7.559896738428013e-05, "loss": 0.5220743179321289, "step": 334290 }, { "epoch": 1.9871486230242938, "grad_norm": 1.637848138809204, "learning_rate": 7.559321537081492e-05, "loss": 0.5722987174987793, "step": 334300 }, { "epoch": 1.9872080651009623, "grad_norm": 1.5086172819137573, "learning_rate": 7.558746352194048e-05, "loss": 0.5293077945709228, "step": 334310 }, { "epoch": 1.9872675071776307, "grad_norm": 1.078163981437683, "learning_rate": 7.558171183768441e-05, "loss": 0.5335315704345703, "step": 334320 }, { "epoch": 1.987326949254299, "grad_norm": 0.9081912636756897, "learning_rate": 7.557596031807417e-05, "loss": 0.5191375732421875, "step": 334330 }, { "epoch": 1.9873863913309675, "grad_norm": 1.2527345418930054, "learning_rate": 7.557020896313726e-05, "loss": 0.5289559841156006, "step": 334340 }, { "epoch": 1.987445833407636, "grad_norm": 1.3372211456298828, "learning_rate": 7.556445777290126e-05, "loss": 0.5497709274291992, "step": 334350 }, { "epoch": 1.9875052754843043, "grad_norm": 1.6066168546676636, "learning_rate": 7.555870674739362e-05, "loss": 0.5108176708221436, "step": 334360 }, { "epoch": 1.9875647175609727, "grad_norm": 1.6027591228485107, "learning_rate": 7.555295588664189e-05, "loss": 0.553927993774414, "step": 334370 }, { "epoch": 1.9876241596376412, "grad_norm": 1.4081796407699585, "learning_rate": 7.554720519067351e-05, "loss": 0.48256592750549315, "step": 334380 }, { "epoch": 1.9876836017143096, "grad_norm": 1.644767165184021, "learning_rate": 7.554145465951609e-05, "loss": 0.5322892189025878, "step": 334390 }, { "epoch": 1.987743043790978, "grad_norm": 1.5872647762298584, "learning_rate": 7.55357042931971e-05, "loss": 0.5233629703521728, "step": 334400 }, { "epoch": 1.9878024858676464, "grad_norm": 1.2449204921722412, "learning_rate": 7.552995409174397e-05, "loss": 0.5022920608520508, "step": 334410 }, { "epoch": 1.9878619279443148, "grad_norm": 1.3962687253952026, "learning_rate": 7.552420405518436e-05, "loss": 0.501500129699707, "step": 334420 }, { "epoch": 1.987921370020983, "grad_norm": 1.4136031866073608, "learning_rate": 7.551845418354564e-05, "loss": 0.5353380680084229, "step": 334430 }, { "epoch": 1.9879808120976514, "grad_norm": 1.8208719491958618, "learning_rate": 7.551270447685534e-05, "loss": 0.6060628890991211, "step": 334440 }, { "epoch": 1.9880402541743198, "grad_norm": 1.6949902772903442, "learning_rate": 7.550695493514106e-05, "loss": 0.5141514301300049, "step": 334450 }, { "epoch": 1.9880996962509883, "grad_norm": 1.2814486026763916, "learning_rate": 7.550120555843022e-05, "loss": 0.5061276435852051, "step": 334460 }, { "epoch": 1.9881591383276564, "grad_norm": 1.258272409439087, "learning_rate": 7.549545634675029e-05, "loss": 0.5754361152648926, "step": 334470 }, { "epoch": 1.9882185804043249, "grad_norm": 1.5058046579360962, "learning_rate": 7.548970730012885e-05, "loss": 0.5469257354736328, "step": 334480 }, { "epoch": 1.9882780224809933, "grad_norm": 1.3297080993652344, "learning_rate": 7.54839584185934e-05, "loss": 0.511769962310791, "step": 334490 }, { "epoch": 1.9883374645576617, "grad_norm": 1.3311527967453003, "learning_rate": 7.547820970217137e-05, "loss": 0.5110269069671631, "step": 334500 }, { "epoch": 1.98839690663433, "grad_norm": 1.5754427909851074, "learning_rate": 7.547246115089033e-05, "loss": 0.5127599716186524, "step": 334510 }, { "epoch": 1.9884563487109985, "grad_norm": 1.6370606422424316, "learning_rate": 7.546671276477773e-05, "loss": 0.5228716373443604, "step": 334520 }, { "epoch": 1.988515790787667, "grad_norm": 1.453169345855713, "learning_rate": 7.546096454386111e-05, "loss": 0.5585278511047364, "step": 334530 }, { "epoch": 1.9885752328643354, "grad_norm": 1.229732871055603, "learning_rate": 7.545521648816793e-05, "loss": 0.5109365463256836, "step": 334540 }, { "epoch": 1.9886346749410038, "grad_norm": 1.2367647886276245, "learning_rate": 7.544946859772573e-05, "loss": 0.5139376640319824, "step": 334550 }, { "epoch": 1.9886941170176722, "grad_norm": 1.7082675695419312, "learning_rate": 7.544372087256195e-05, "loss": 0.5374020576477051, "step": 334560 }, { "epoch": 1.9887535590943406, "grad_norm": 1.2294530868530273, "learning_rate": 7.543797331270412e-05, "loss": 0.5460597038269043, "step": 334570 }, { "epoch": 1.988813001171009, "grad_norm": 1.6247568130493164, "learning_rate": 7.543222591817976e-05, "loss": 0.5121816635131836, "step": 334580 }, { "epoch": 1.9888724432476774, "grad_norm": 1.7310490608215332, "learning_rate": 7.542647868901632e-05, "loss": 0.5792089462280273, "step": 334590 }, { "epoch": 1.9889318853243458, "grad_norm": 1.2839897871017456, "learning_rate": 7.542073162524129e-05, "loss": 0.5175970554351806, "step": 334600 }, { "epoch": 1.988991327401014, "grad_norm": 1.4519286155700684, "learning_rate": 7.541498472688218e-05, "loss": 0.5307085514068604, "step": 334610 }, { "epoch": 1.9890507694776824, "grad_norm": 1.4572926759719849, "learning_rate": 7.54092379939665e-05, "loss": 0.5017073631286622, "step": 334620 }, { "epoch": 1.9891102115543509, "grad_norm": 1.3108575344085693, "learning_rate": 7.540349142652172e-05, "loss": 0.5306650161743164, "step": 334630 }, { "epoch": 1.9891696536310193, "grad_norm": 1.5257264375686646, "learning_rate": 7.53977450245753e-05, "loss": 0.5968961715698242, "step": 334640 }, { "epoch": 1.9892290957076877, "grad_norm": 1.241764783859253, "learning_rate": 7.539199878815481e-05, "loss": 0.5095879077911377, "step": 334650 }, { "epoch": 1.9892885377843559, "grad_norm": 1.276380181312561, "learning_rate": 7.538625271728767e-05, "loss": 0.5290050506591797, "step": 334660 }, { "epoch": 1.9893479798610243, "grad_norm": 1.1643306016921997, "learning_rate": 7.538050681200137e-05, "loss": 0.5119781494140625, "step": 334670 }, { "epoch": 1.9894074219376927, "grad_norm": 1.3345202207565308, "learning_rate": 7.537476107232342e-05, "loss": 0.5018982410430908, "step": 334680 }, { "epoch": 1.9894668640143611, "grad_norm": 1.391852617263794, "learning_rate": 7.53690154982813e-05, "loss": 0.49894123077392577, "step": 334690 }, { "epoch": 1.9895263060910295, "grad_norm": 1.3177404403686523, "learning_rate": 7.536327008990247e-05, "loss": 0.5427743911743164, "step": 334700 }, { "epoch": 1.989585748167698, "grad_norm": 1.5858291387557983, "learning_rate": 7.535752484721445e-05, "loss": 0.5478665828704834, "step": 334710 }, { "epoch": 1.9896451902443664, "grad_norm": 1.3875653743743896, "learning_rate": 7.535177977024474e-05, "loss": 0.553837776184082, "step": 334720 }, { "epoch": 1.9897046323210348, "grad_norm": 1.7352770566940308, "learning_rate": 7.534603485902076e-05, "loss": 0.5066944122314453, "step": 334730 }, { "epoch": 1.9897640743977032, "grad_norm": 1.131704330444336, "learning_rate": 7.534029011357003e-05, "loss": 0.5902694702148438, "step": 334740 }, { "epoch": 1.9898235164743716, "grad_norm": 1.2766203880310059, "learning_rate": 7.533454553392003e-05, "loss": 0.544551944732666, "step": 334750 }, { "epoch": 1.98988295855104, "grad_norm": 1.5928096771240234, "learning_rate": 7.532880112009823e-05, "loss": 0.5275733947753907, "step": 334760 }, { "epoch": 1.9899424006277084, "grad_norm": 1.41859769821167, "learning_rate": 7.532305687213211e-05, "loss": 0.5032083511352539, "step": 334770 }, { "epoch": 1.9900018427043769, "grad_norm": 1.5127917528152466, "learning_rate": 7.531731279004916e-05, "loss": 0.5692304611206055, "step": 334780 }, { "epoch": 1.9900612847810453, "grad_norm": 1.3983235359191895, "learning_rate": 7.531156887387688e-05, "loss": 0.5362989425659179, "step": 334790 }, { "epoch": 1.9901207268577135, "grad_norm": 1.0973594188690186, "learning_rate": 7.530582512364265e-05, "loss": 0.5256590843200684, "step": 334800 }, { "epoch": 1.9901801689343819, "grad_norm": 1.3628668785095215, "learning_rate": 7.530008153937406e-05, "loss": 0.5399895668029785, "step": 334810 }, { "epoch": 1.9902396110110503, "grad_norm": 1.1478687524795532, "learning_rate": 7.529433812109856e-05, "loss": 0.6066900253295898, "step": 334820 }, { "epoch": 1.9902990530877187, "grad_norm": 1.4524708986282349, "learning_rate": 7.528859486884357e-05, "loss": 0.5319359779357911, "step": 334830 }, { "epoch": 1.990358495164387, "grad_norm": 1.5134997367858887, "learning_rate": 7.528285178263661e-05, "loss": 0.5555564880371093, "step": 334840 }, { "epoch": 1.9904179372410553, "grad_norm": 1.4389770030975342, "learning_rate": 7.527710886250514e-05, "loss": 0.5504868507385254, "step": 334850 }, { "epoch": 1.9904773793177237, "grad_norm": 1.3327769041061401, "learning_rate": 7.527136610847664e-05, "loss": 0.5194166660308838, "step": 334860 }, { "epoch": 1.9905368213943921, "grad_norm": 1.5929999351501465, "learning_rate": 7.526562352057856e-05, "loss": 0.5501211643218994, "step": 334870 }, { "epoch": 1.9905962634710606, "grad_norm": 1.3582974672317505, "learning_rate": 7.525988109883837e-05, "loss": 0.5808784008026123, "step": 334880 }, { "epoch": 1.990655705547729, "grad_norm": 1.3876854181289673, "learning_rate": 7.525413884328361e-05, "loss": 0.5648011684417724, "step": 334890 }, { "epoch": 1.9907151476243974, "grad_norm": 1.675361156463623, "learning_rate": 7.524839675394164e-05, "loss": 0.5526605606079101, "step": 334900 }, { "epoch": 1.9907745897010658, "grad_norm": 1.2409565448760986, "learning_rate": 7.524265483084e-05, "loss": 0.5398985862731933, "step": 334910 }, { "epoch": 1.9908340317777342, "grad_norm": 1.1332038640975952, "learning_rate": 7.523691307400617e-05, "loss": 0.4871069431304932, "step": 334920 }, { "epoch": 1.9908934738544026, "grad_norm": 1.4647225141525269, "learning_rate": 7.523117148346755e-05, "loss": 0.5042081832885742, "step": 334930 }, { "epoch": 1.990952915931071, "grad_norm": 1.2359144687652588, "learning_rate": 7.522543005925166e-05, "loss": 0.5339868545532227, "step": 334940 }, { "epoch": 1.9910123580077395, "grad_norm": 1.3771235942840576, "learning_rate": 7.521968880138596e-05, "loss": 0.5470726013183593, "step": 334950 }, { "epoch": 1.9910718000844079, "grad_norm": 1.2431601285934448, "learning_rate": 7.521394770989788e-05, "loss": 0.49277071952819823, "step": 334960 }, { "epoch": 1.9911312421610763, "grad_norm": 1.5569828748703003, "learning_rate": 7.52082067848149e-05, "loss": 0.5200382232666015, "step": 334970 }, { "epoch": 1.9911906842377445, "grad_norm": 1.4203580617904663, "learning_rate": 7.520246602616455e-05, "loss": 0.5378806114196777, "step": 334980 }, { "epoch": 1.991250126314413, "grad_norm": 1.501078724861145, "learning_rate": 7.519672543397415e-05, "loss": 0.5578762531280518, "step": 334990 }, { "epoch": 1.9913095683910813, "grad_norm": 1.3875993490219116, "learning_rate": 7.519098500827127e-05, "loss": 0.5658749580383301, "step": 335000 }, { "epoch": 1.9913690104677497, "grad_norm": 1.2907190322875977, "learning_rate": 7.518524474908338e-05, "loss": 0.510793924331665, "step": 335010 }, { "epoch": 1.9914284525444181, "grad_norm": 1.56894850730896, "learning_rate": 7.517950465643786e-05, "loss": 0.46085481643676757, "step": 335020 }, { "epoch": 1.9914878946210863, "grad_norm": 1.2766424417495728, "learning_rate": 7.517376473036217e-05, "loss": 0.5586038589477539, "step": 335030 }, { "epoch": 1.9915473366977547, "grad_norm": 1.5155733823776245, "learning_rate": 7.516802497088389e-05, "loss": 0.5138010501861572, "step": 335040 }, { "epoch": 1.9916067787744232, "grad_norm": 1.7422782182693481, "learning_rate": 7.516228537803037e-05, "loss": 0.5272125244140625, "step": 335050 }, { "epoch": 1.9916662208510916, "grad_norm": 1.3021806478500366, "learning_rate": 7.515654595182906e-05, "loss": 0.5374176025390625, "step": 335060 }, { "epoch": 1.99172566292776, "grad_norm": 1.2651410102844238, "learning_rate": 7.51508066923075e-05, "loss": 0.5277697563171386, "step": 335070 }, { "epoch": 1.9917851050044284, "grad_norm": 1.1215670108795166, "learning_rate": 7.514506759949305e-05, "loss": 0.5033886432647705, "step": 335080 }, { "epoch": 1.9918445470810968, "grad_norm": 1.3675243854522705, "learning_rate": 7.51393286734132e-05, "loss": 0.518796157836914, "step": 335090 }, { "epoch": 1.9919039891577652, "grad_norm": 1.3352197408676147, "learning_rate": 7.513358991409542e-05, "loss": 0.5379570007324219, "step": 335100 }, { "epoch": 1.9919634312344336, "grad_norm": 1.6120269298553467, "learning_rate": 7.512785132156718e-05, "loss": 0.5625933647155762, "step": 335110 }, { "epoch": 1.992022873311102, "grad_norm": 1.098507285118103, "learning_rate": 7.512211289585589e-05, "loss": 0.5338566780090332, "step": 335120 }, { "epoch": 1.9920823153877705, "grad_norm": 1.0586532354354858, "learning_rate": 7.5116374636989e-05, "loss": 0.5333188533782959, "step": 335130 }, { "epoch": 1.992141757464439, "grad_norm": 1.3659714460372925, "learning_rate": 7.511063654499398e-05, "loss": 0.5213624954223632, "step": 335140 }, { "epoch": 1.9922011995411073, "grad_norm": 1.486211895942688, "learning_rate": 7.510489861989826e-05, "loss": 0.5602736473083496, "step": 335150 }, { "epoch": 1.9922606416177757, "grad_norm": 1.2856502532958984, "learning_rate": 7.509916086172933e-05, "loss": 0.5370718955993652, "step": 335160 }, { "epoch": 1.992320083694444, "grad_norm": 1.3437259197235107, "learning_rate": 7.509342327051458e-05, "loss": 0.5531711578369141, "step": 335170 }, { "epoch": 1.9923795257711123, "grad_norm": 1.7566108703613281, "learning_rate": 7.508768584628152e-05, "loss": 0.5673741340637207, "step": 335180 }, { "epoch": 1.9924389678477807, "grad_norm": 1.6260632276535034, "learning_rate": 7.50819485890575e-05, "loss": 0.5450722694396972, "step": 335190 }, { "epoch": 1.9924984099244492, "grad_norm": 1.3188427686691284, "learning_rate": 7.507621149887009e-05, "loss": 0.5947730541229248, "step": 335200 }, { "epoch": 1.9925578520011173, "grad_norm": 1.4493788480758667, "learning_rate": 7.507047457574663e-05, "loss": 0.5549139022827149, "step": 335210 }, { "epoch": 1.9926172940777858, "grad_norm": 1.4633203744888306, "learning_rate": 7.506473781971464e-05, "loss": 0.5339563369750977, "step": 335220 }, { "epoch": 1.9926767361544542, "grad_norm": 1.3899445533752441, "learning_rate": 7.50590012308015e-05, "loss": 0.5314278125762939, "step": 335230 }, { "epoch": 1.9927361782311226, "grad_norm": 1.2557473182678223, "learning_rate": 7.505326480903467e-05, "loss": 0.4995457649230957, "step": 335240 }, { "epoch": 1.992795620307791, "grad_norm": 1.3370994329452515, "learning_rate": 7.504752855444164e-05, "loss": 0.5910308837890625, "step": 335250 }, { "epoch": 1.9928550623844594, "grad_norm": 1.6424633264541626, "learning_rate": 7.504179246704979e-05, "loss": 0.5327531814575195, "step": 335260 }, { "epoch": 1.9929145044611278, "grad_norm": 1.8285640478134155, "learning_rate": 7.503605654688656e-05, "loss": 0.5632535934448242, "step": 335270 }, { "epoch": 1.9929739465377962, "grad_norm": 1.5701807737350464, "learning_rate": 7.503032079397945e-05, "loss": 0.5356148719787598, "step": 335280 }, { "epoch": 1.9930333886144647, "grad_norm": 1.324694275856018, "learning_rate": 7.50245852083558e-05, "loss": 0.5324282646179199, "step": 335290 }, { "epoch": 1.993092830691133, "grad_norm": 1.3016149997711182, "learning_rate": 7.501884979004316e-05, "loss": 0.5270586013793945, "step": 335300 }, { "epoch": 1.9931522727678015, "grad_norm": 1.7830504179000854, "learning_rate": 7.50131145390689e-05, "loss": 0.5836671829223633, "step": 335310 }, { "epoch": 1.99321171484447, "grad_norm": 1.3096340894699097, "learning_rate": 7.500737945546043e-05, "loss": 0.5288564682006835, "step": 335320 }, { "epoch": 1.9932711569211383, "grad_norm": 1.3133071660995483, "learning_rate": 7.500164453924525e-05, "loss": 0.5388676643371582, "step": 335330 }, { "epoch": 1.9933305989978067, "grad_norm": 1.7517871856689453, "learning_rate": 7.499590979045076e-05, "loss": 0.5118112564086914, "step": 335340 }, { "epoch": 1.993390041074475, "grad_norm": 1.1077868938446045, "learning_rate": 7.499017520910445e-05, "loss": 0.484116792678833, "step": 335350 }, { "epoch": 1.9934494831511433, "grad_norm": 1.4809012413024902, "learning_rate": 7.498444079523362e-05, "loss": 0.5658769607543945, "step": 335360 }, { "epoch": 1.9935089252278118, "grad_norm": 1.3672422170639038, "learning_rate": 7.49787065488658e-05, "loss": 0.5356563091278076, "step": 335370 }, { "epoch": 1.9935683673044802, "grad_norm": 1.6665159463882446, "learning_rate": 7.497297247002845e-05, "loss": 0.4816590309143066, "step": 335380 }, { "epoch": 1.9936278093811486, "grad_norm": 1.4981001615524292, "learning_rate": 7.49672385587489e-05, "loss": 0.5142424583435059, "step": 335390 }, { "epoch": 1.9936872514578168, "grad_norm": 2.0182414054870605, "learning_rate": 7.496150481505464e-05, "loss": 0.4815999984741211, "step": 335400 }, { "epoch": 1.9937466935344852, "grad_norm": 1.1900041103363037, "learning_rate": 7.495577123897313e-05, "loss": 0.5204809188842774, "step": 335410 }, { "epoch": 1.9938061356111536, "grad_norm": 1.1822935342788696, "learning_rate": 7.49500378305317e-05, "loss": 0.45444068908691404, "step": 335420 }, { "epoch": 1.993865577687822, "grad_norm": 1.4547016620635986, "learning_rate": 7.494430458975785e-05, "loss": 0.5275999546051026, "step": 335430 }, { "epoch": 1.9939250197644904, "grad_norm": 1.2634624242782593, "learning_rate": 7.493857151667904e-05, "loss": 0.5620050430297852, "step": 335440 }, { "epoch": 1.9939844618411589, "grad_norm": 1.031490683555603, "learning_rate": 7.493283861132259e-05, "loss": 0.5025424480438232, "step": 335450 }, { "epoch": 1.9940439039178273, "grad_norm": 1.474727988243103, "learning_rate": 7.492710587371599e-05, "loss": 0.49440832138061525, "step": 335460 }, { "epoch": 1.9941033459944957, "grad_norm": 1.5869418382644653, "learning_rate": 7.492137330388669e-05, "loss": 0.5531455039978027, "step": 335470 }, { "epoch": 1.994162788071164, "grad_norm": 1.305790901184082, "learning_rate": 7.491564090186205e-05, "loss": 0.5122846126556396, "step": 335480 }, { "epoch": 1.9942222301478325, "grad_norm": 1.304518461227417, "learning_rate": 7.49099086676695e-05, "loss": 0.4686144828796387, "step": 335490 }, { "epoch": 1.994281672224501, "grad_norm": 1.564048409461975, "learning_rate": 7.49041766013365e-05, "loss": 0.49599494934082033, "step": 335500 }, { "epoch": 1.9943411143011693, "grad_norm": 1.3336302042007446, "learning_rate": 7.489844470289045e-05, "loss": 0.570952033996582, "step": 335510 }, { "epoch": 1.9944005563778378, "grad_norm": 1.165657877922058, "learning_rate": 7.489271297235874e-05, "loss": 0.5387619018554688, "step": 335520 }, { "epoch": 1.9944599984545062, "grad_norm": 1.4428259134292603, "learning_rate": 7.488698140976888e-05, "loss": 0.5005715370178223, "step": 335530 }, { "epoch": 1.9945194405311744, "grad_norm": 1.2478177547454834, "learning_rate": 7.488125001514818e-05, "loss": 0.5235376834869385, "step": 335540 }, { "epoch": 1.9945788826078428, "grad_norm": 1.6167081594467163, "learning_rate": 7.48755187885241e-05, "loss": 0.5748961448669434, "step": 335550 }, { "epoch": 1.9946383246845112, "grad_norm": 1.355644941329956, "learning_rate": 7.486978772992407e-05, "loss": 0.5602832317352295, "step": 335560 }, { "epoch": 1.9946977667611796, "grad_norm": 1.1754498481750488, "learning_rate": 7.486405683937551e-05, "loss": 0.4983402729034424, "step": 335570 }, { "epoch": 1.9947572088378478, "grad_norm": 1.548175573348999, "learning_rate": 7.485832611690581e-05, "loss": 0.5489449501037598, "step": 335580 }, { "epoch": 1.9948166509145162, "grad_norm": 1.3462778329849243, "learning_rate": 7.485259556254238e-05, "loss": 0.5388979911804199, "step": 335590 }, { "epoch": 1.9948760929911846, "grad_norm": 1.6828019618988037, "learning_rate": 7.484686517631265e-05, "loss": 0.5534278392791748, "step": 335600 }, { "epoch": 1.994935535067853, "grad_norm": 1.4062285423278809, "learning_rate": 7.484113495824405e-05, "loss": 0.5588649272918701, "step": 335610 }, { "epoch": 1.9949949771445215, "grad_norm": 1.2298065423965454, "learning_rate": 7.483540490836394e-05, "loss": 0.49741134643554685, "step": 335620 }, { "epoch": 1.9950544192211899, "grad_norm": 1.090970516204834, "learning_rate": 7.482967502669979e-05, "loss": 0.5465806007385254, "step": 335630 }, { "epoch": 1.9951138612978583, "grad_norm": 1.3717763423919678, "learning_rate": 7.482394531327896e-05, "loss": 0.5321246147155761, "step": 335640 }, { "epoch": 1.9951733033745267, "grad_norm": 1.656912922859192, "learning_rate": 7.481821576812888e-05, "loss": 0.5298114776611328, "step": 335650 }, { "epoch": 1.9952327454511951, "grad_norm": 1.256867527961731, "learning_rate": 7.481248639127699e-05, "loss": 0.5536136627197266, "step": 335660 }, { "epoch": 1.9952921875278635, "grad_norm": 1.0156534910202026, "learning_rate": 7.480675718275064e-05, "loss": 0.48395843505859376, "step": 335670 }, { "epoch": 1.995351629604532, "grad_norm": 1.3804105520248413, "learning_rate": 7.480102814257724e-05, "loss": 0.5199277877807618, "step": 335680 }, { "epoch": 1.9954110716812004, "grad_norm": 1.11857271194458, "learning_rate": 7.479529927078424e-05, "loss": 0.4980952262878418, "step": 335690 }, { "epoch": 1.9954705137578688, "grad_norm": 1.4377477169036865, "learning_rate": 7.478957056739904e-05, "loss": 0.5621963024139405, "step": 335700 }, { "epoch": 1.9955299558345372, "grad_norm": 1.5380537509918213, "learning_rate": 7.478384203244901e-05, "loss": 0.5630608081817627, "step": 335710 }, { "epoch": 1.9955893979112054, "grad_norm": 1.0614820718765259, "learning_rate": 7.477811366596157e-05, "loss": 0.5509557723999023, "step": 335720 }, { "epoch": 1.9956488399878738, "grad_norm": 1.1840078830718994, "learning_rate": 7.477238546796413e-05, "loss": 0.47542295455932615, "step": 335730 }, { "epoch": 1.9957082820645422, "grad_norm": 1.1703236103057861, "learning_rate": 7.47666574384841e-05, "loss": 0.5944293975830078, "step": 335740 }, { "epoch": 1.9957677241412106, "grad_norm": 1.5935896635055542, "learning_rate": 7.476092957754882e-05, "loss": 0.49401092529296875, "step": 335750 }, { "epoch": 1.995827166217879, "grad_norm": 1.097939133644104, "learning_rate": 7.475520188518577e-05, "loss": 0.5245106220245361, "step": 335760 }, { "epoch": 1.9958866082945472, "grad_norm": 1.6546719074249268, "learning_rate": 7.474947436142232e-05, "loss": 0.5617140293121338, "step": 335770 }, { "epoch": 1.9959460503712156, "grad_norm": 1.3449276685714722, "learning_rate": 7.474374700628583e-05, "loss": 0.49233622550964357, "step": 335780 }, { "epoch": 1.996005492447884, "grad_norm": 1.492209553718567, "learning_rate": 7.473801981980377e-05, "loss": 0.5221259593963623, "step": 335790 }, { "epoch": 1.9960649345245525, "grad_norm": 1.2770369052886963, "learning_rate": 7.473229280200348e-05, "loss": 0.5304782867431641, "step": 335800 }, { "epoch": 1.9961243766012209, "grad_norm": 1.4146915674209595, "learning_rate": 7.472656595291239e-05, "loss": 0.47428040504455565, "step": 335810 }, { "epoch": 1.9961838186778893, "grad_norm": 1.517531394958496, "learning_rate": 7.472083927255788e-05, "loss": 0.5740871906280518, "step": 335820 }, { "epoch": 1.9962432607545577, "grad_norm": 0.9775515794754028, "learning_rate": 7.471511276096734e-05, "loss": 0.5333430290222168, "step": 335830 }, { "epoch": 1.9963027028312261, "grad_norm": 1.199798583984375, "learning_rate": 7.470938641816818e-05, "loss": 0.5773561477661133, "step": 335840 }, { "epoch": 1.9963621449078945, "grad_norm": 1.2471295595169067, "learning_rate": 7.470366024418775e-05, "loss": 0.5263551712036133, "step": 335850 }, { "epoch": 1.996421586984563, "grad_norm": 1.035498023033142, "learning_rate": 7.469793423905352e-05, "loss": 0.513064193725586, "step": 335860 }, { "epoch": 1.9964810290612314, "grad_norm": 1.4802155494689941, "learning_rate": 7.469220840279281e-05, "loss": 0.5229611396789551, "step": 335870 }, { "epoch": 1.9965404711378998, "grad_norm": 1.3284425735473633, "learning_rate": 7.468648273543302e-05, "loss": 0.479356575012207, "step": 335880 }, { "epoch": 1.9965999132145682, "grad_norm": 1.4511960744857788, "learning_rate": 7.468075723700159e-05, "loss": 0.49749250411987306, "step": 335890 }, { "epoch": 1.9966593552912366, "grad_norm": 1.676121473312378, "learning_rate": 7.467503190752587e-05, "loss": 0.5433163166046142, "step": 335900 }, { "epoch": 1.9967187973679048, "grad_norm": 1.0320042371749878, "learning_rate": 7.466930674703321e-05, "loss": 0.5181959629058838, "step": 335910 }, { "epoch": 1.9967782394445732, "grad_norm": 1.162452220916748, "learning_rate": 7.466358175555108e-05, "loss": 0.5219416141510009, "step": 335920 }, { "epoch": 1.9968376815212416, "grad_norm": 1.2487908601760864, "learning_rate": 7.465785693310683e-05, "loss": 0.5249842166900635, "step": 335930 }, { "epoch": 1.99689712359791, "grad_norm": 0.9131135940551758, "learning_rate": 7.465213227972781e-05, "loss": 0.5132806777954102, "step": 335940 }, { "epoch": 1.9969565656745782, "grad_norm": 1.432795524597168, "learning_rate": 7.464640779544147e-05, "loss": 0.4912724494934082, "step": 335950 }, { "epoch": 1.9970160077512467, "grad_norm": 1.3387696743011475, "learning_rate": 7.464068348027517e-05, "loss": 0.5053672790527344, "step": 335960 }, { "epoch": 1.997075449827915, "grad_norm": 1.2204275131225586, "learning_rate": 7.463495933425626e-05, "loss": 0.6276817321777344, "step": 335970 }, { "epoch": 1.9971348919045835, "grad_norm": 1.121727466583252, "learning_rate": 7.462923535741213e-05, "loss": 0.5441551208496094, "step": 335980 }, { "epoch": 1.997194333981252, "grad_norm": 1.2554408311843872, "learning_rate": 7.462351154977023e-05, "loss": 0.5001786231994629, "step": 335990 }, { "epoch": 1.9972537760579203, "grad_norm": 1.3543639183044434, "learning_rate": 7.461778791135786e-05, "loss": 0.5190944194793701, "step": 336000 }, { "epoch": 1.9973132181345887, "grad_norm": 1.407342791557312, "learning_rate": 7.461206444220241e-05, "loss": 0.5005283355712891, "step": 336010 }, { "epoch": 1.9973726602112571, "grad_norm": 1.2849235534667969, "learning_rate": 7.460634114233131e-05, "loss": 0.49347820281982424, "step": 336020 }, { "epoch": 1.9974321022879256, "grad_norm": 0.9823288321495056, "learning_rate": 7.460061801177192e-05, "loss": 0.5135699272155761, "step": 336030 }, { "epoch": 1.997491544364594, "grad_norm": 1.57353675365448, "learning_rate": 7.459489505055152e-05, "loss": 0.4913674831390381, "step": 336040 }, { "epoch": 1.9975509864412624, "grad_norm": 1.6898523569107056, "learning_rate": 7.458917225869766e-05, "loss": 0.5650170326232911, "step": 336050 }, { "epoch": 1.9976104285179308, "grad_norm": 1.3472013473510742, "learning_rate": 7.458344963623763e-05, "loss": 0.4902195930480957, "step": 336060 }, { "epoch": 1.9976698705945992, "grad_norm": 1.7051069736480713, "learning_rate": 7.457772718319875e-05, "loss": 0.5022300720214844, "step": 336070 }, { "epoch": 1.9977293126712676, "grad_norm": 1.3218318223953247, "learning_rate": 7.457200489960847e-05, "loss": 0.5385180473327636, "step": 336080 }, { "epoch": 1.9977887547479358, "grad_norm": 1.7527813911437988, "learning_rate": 7.456628278549416e-05, "loss": 0.5414670467376709, "step": 336090 }, { "epoch": 1.9978481968246042, "grad_norm": 1.576457142829895, "learning_rate": 7.456056084088314e-05, "loss": 0.5616369724273682, "step": 336100 }, { "epoch": 1.9979076389012727, "grad_norm": 1.4050133228302002, "learning_rate": 7.455483906580283e-05, "loss": 0.4762944221496582, "step": 336110 }, { "epoch": 1.997967080977941, "grad_norm": 1.3693493604660034, "learning_rate": 7.454911746028058e-05, "loss": 0.5093212127685547, "step": 336120 }, { "epoch": 1.9980265230546095, "grad_norm": 1.0964598655700684, "learning_rate": 7.454339602434377e-05, "loss": 0.4869087219238281, "step": 336130 }, { "epoch": 1.9980859651312777, "grad_norm": 1.458220362663269, "learning_rate": 7.453767475801976e-05, "loss": 0.5138659954071045, "step": 336140 }, { "epoch": 1.998145407207946, "grad_norm": 1.2922604084014893, "learning_rate": 7.453195366133594e-05, "loss": 0.5517148017883301, "step": 336150 }, { "epoch": 1.9982048492846145, "grad_norm": 1.582867980003357, "learning_rate": 7.452623273431966e-05, "loss": 0.5180248260498047, "step": 336160 }, { "epoch": 1.998264291361283, "grad_norm": 1.4025006294250488, "learning_rate": 7.452051197699827e-05, "loss": 0.5915017127990723, "step": 336170 }, { "epoch": 1.9983237334379513, "grad_norm": 1.5906472206115723, "learning_rate": 7.451479138939919e-05, "loss": 0.5103545665740967, "step": 336180 }, { "epoch": 1.9983831755146197, "grad_norm": 1.097900629043579, "learning_rate": 7.450907097154974e-05, "loss": 0.53187255859375, "step": 336190 }, { "epoch": 1.9984426175912882, "grad_norm": 1.1933165788650513, "learning_rate": 7.450335072347727e-05, "loss": 0.4801743507385254, "step": 336200 }, { "epoch": 1.9985020596679566, "grad_norm": 1.8029885292053223, "learning_rate": 7.449763064520918e-05, "loss": 0.5405363082885742, "step": 336210 }, { "epoch": 1.998561501744625, "grad_norm": 1.3155021667480469, "learning_rate": 7.449191073677284e-05, "loss": 0.5413028717041015, "step": 336220 }, { "epoch": 1.9986209438212934, "grad_norm": 1.4073596000671387, "learning_rate": 7.448619099819558e-05, "loss": 0.5415582180023193, "step": 336230 }, { "epoch": 1.9986803858979618, "grad_norm": 1.3409638404846191, "learning_rate": 7.448047142950479e-05, "loss": 0.5291177749633789, "step": 336240 }, { "epoch": 1.9987398279746302, "grad_norm": 1.1752021312713623, "learning_rate": 7.44747520307278e-05, "loss": 0.5176158905029297, "step": 336250 }, { "epoch": 1.9987992700512986, "grad_norm": 1.621862769126892, "learning_rate": 7.446903280189199e-05, "loss": 0.5591555595397949, "step": 336260 }, { "epoch": 1.998858712127967, "grad_norm": 1.2907634973526, "learning_rate": 7.44633137430247e-05, "loss": 0.5408253192901611, "step": 336270 }, { "epoch": 1.9989181542046353, "grad_norm": 1.1061166524887085, "learning_rate": 7.445759485415336e-05, "loss": 0.4628256320953369, "step": 336280 }, { "epoch": 1.9989775962813037, "grad_norm": 1.3216454982757568, "learning_rate": 7.445187613530522e-05, "loss": 0.5099797248840332, "step": 336290 }, { "epoch": 1.999037038357972, "grad_norm": 1.402190089225769, "learning_rate": 7.444615758650768e-05, "loss": 0.5811744689941406, "step": 336300 }, { "epoch": 1.9990964804346405, "grad_norm": 1.550298810005188, "learning_rate": 7.444043920778814e-05, "loss": 0.5288383483886718, "step": 336310 }, { "epoch": 1.9991559225113087, "grad_norm": 1.6885161399841309, "learning_rate": 7.443472099917392e-05, "loss": 0.532846736907959, "step": 336320 }, { "epoch": 1.999215364587977, "grad_norm": 0.9584691524505615, "learning_rate": 7.442900296069235e-05, "loss": 0.5377188682556152, "step": 336330 }, { "epoch": 1.9992748066646455, "grad_norm": 1.5447973012924194, "learning_rate": 7.44232850923708e-05, "loss": 0.5946531295776367, "step": 336340 }, { "epoch": 1.999334248741314, "grad_norm": 0.9338932633399963, "learning_rate": 7.441756739423665e-05, "loss": 0.5056261539459228, "step": 336350 }, { "epoch": 1.9993936908179823, "grad_norm": 1.4860097169876099, "learning_rate": 7.441184986631722e-05, "loss": 0.5251261711120605, "step": 336360 }, { "epoch": 1.9994531328946508, "grad_norm": 1.4625681638717651, "learning_rate": 7.440613250863984e-05, "loss": 0.524385643005371, "step": 336370 }, { "epoch": 1.9995125749713192, "grad_norm": 1.225986361503601, "learning_rate": 7.440041532123192e-05, "loss": 0.5181825637817383, "step": 336380 }, { "epoch": 1.9995720170479876, "grad_norm": 1.4968684911727905, "learning_rate": 7.439469830412078e-05, "loss": 0.5084304332733154, "step": 336390 }, { "epoch": 1.999631459124656, "grad_norm": 1.2685916423797607, "learning_rate": 7.438898145733377e-05, "loss": 0.4917311668395996, "step": 336400 }, { "epoch": 1.9996909012013244, "grad_norm": 1.3663285970687866, "learning_rate": 7.438326478089821e-05, "loss": 0.5347004890441894, "step": 336410 }, { "epoch": 1.9997503432779928, "grad_norm": 1.6448293924331665, "learning_rate": 7.437754827484151e-05, "loss": 0.5676054000854492, "step": 336420 }, { "epoch": 1.9998097853546613, "grad_norm": 1.3420275449752808, "learning_rate": 7.437183193919093e-05, "loss": 0.5100805759429932, "step": 336430 }, { "epoch": 1.9998692274313297, "grad_norm": 1.4235692024230957, "learning_rate": 7.43661157739739e-05, "loss": 0.549515676498413, "step": 336440 }, { "epoch": 1.999928669507998, "grad_norm": 1.4718506336212158, "learning_rate": 7.436039977921773e-05, "loss": 0.5141899108886718, "step": 336450 }, { "epoch": 1.9999881115846663, "grad_norm": 1.3431490659713745, "learning_rate": 7.435468395494975e-05, "loss": 0.5830705642700196, "step": 336460 }, { "epoch": 2.000047553661335, "grad_norm": 1.240832805633545, "learning_rate": 7.434896830119728e-05, "loss": 0.4717129707336426, "step": 336470 }, { "epoch": 2.0001069957380033, "grad_norm": 1.1415599584579468, "learning_rate": 7.434325281798775e-05, "loss": 0.46955175399780275, "step": 336480 }, { "epoch": 2.0001664378146713, "grad_norm": 1.2797815799713135, "learning_rate": 7.433753750534845e-05, "loss": 0.5177649021148681, "step": 336490 }, { "epoch": 2.0002258798913397, "grad_norm": 1.5171982049942017, "learning_rate": 7.433182236330665e-05, "loss": 0.5564816951751709, "step": 336500 }, { "epoch": 2.000285321968008, "grad_norm": 1.3046849966049194, "learning_rate": 7.43261073918898e-05, "loss": 0.5255565643310547, "step": 336510 }, { "epoch": 2.0003447640446765, "grad_norm": 1.6743742227554321, "learning_rate": 7.432039259112517e-05, "loss": 0.5322941303253174, "step": 336520 }, { "epoch": 2.000404206121345, "grad_norm": 1.2476743459701538, "learning_rate": 7.431467796104012e-05, "loss": 0.5251481056213378, "step": 336530 }, { "epoch": 2.0004636481980134, "grad_norm": 1.5534415245056152, "learning_rate": 7.430896350166203e-05, "loss": 0.4832131385803223, "step": 336540 }, { "epoch": 2.000523090274682, "grad_norm": 1.0203534364700317, "learning_rate": 7.430324921301819e-05, "loss": 0.49518117904663084, "step": 336550 }, { "epoch": 2.00058253235135, "grad_norm": 1.250198245048523, "learning_rate": 7.429753509513591e-05, "loss": 0.49499073028564455, "step": 336560 }, { "epoch": 2.0006419744280186, "grad_norm": 1.191204309463501, "learning_rate": 7.429182114804256e-05, "loss": 0.4960172653198242, "step": 336570 }, { "epoch": 2.000701416504687, "grad_norm": 1.4246752262115479, "learning_rate": 7.428610737176546e-05, "loss": 0.5190665245056152, "step": 336580 }, { "epoch": 2.0007608585813554, "grad_norm": 1.188950538635254, "learning_rate": 7.428039376633197e-05, "loss": 0.46298809051513673, "step": 336590 }, { "epoch": 2.000820300658024, "grad_norm": 1.2265396118164062, "learning_rate": 7.427468033176938e-05, "loss": 0.5489338874816895, "step": 336600 }, { "epoch": 2.0008797427346923, "grad_norm": 1.245102047920227, "learning_rate": 7.426896706810507e-05, "loss": 0.5122419357299804, "step": 336610 }, { "epoch": 2.0009391848113607, "grad_norm": 1.1892905235290527, "learning_rate": 7.426325397536635e-05, "loss": 0.5274369239807128, "step": 336620 }, { "epoch": 2.000998626888029, "grad_norm": 1.3558568954467773, "learning_rate": 7.425754105358051e-05, "loss": 0.5072524070739746, "step": 336630 }, { "epoch": 2.0010580689646975, "grad_norm": 1.3331342935562134, "learning_rate": 7.425182830277492e-05, "loss": 0.5143697261810303, "step": 336640 }, { "epoch": 2.001117511041366, "grad_norm": 1.3419103622436523, "learning_rate": 7.424611572297693e-05, "loss": 0.5497548103332519, "step": 336650 }, { "epoch": 2.0011769531180343, "grad_norm": 1.3244701623916626, "learning_rate": 7.424040331421382e-05, "loss": 0.4939152240753174, "step": 336660 }, { "epoch": 2.0012363951947023, "grad_norm": 1.2764674425125122, "learning_rate": 7.423469107651293e-05, "loss": 0.47400288581848143, "step": 336670 }, { "epoch": 2.0012958372713707, "grad_norm": 1.3461402654647827, "learning_rate": 7.42289790099016e-05, "loss": 0.5072474479675293, "step": 336680 }, { "epoch": 2.001355279348039, "grad_norm": 1.4738820791244507, "learning_rate": 7.422326711440714e-05, "loss": 0.5287899017333985, "step": 336690 }, { "epoch": 2.0014147214247076, "grad_norm": 1.349208116531372, "learning_rate": 7.421755539005686e-05, "loss": 0.5210254669189454, "step": 336700 }, { "epoch": 2.001474163501376, "grad_norm": 1.7249510288238525, "learning_rate": 7.421184383687814e-05, "loss": 0.4705784320831299, "step": 336710 }, { "epoch": 2.0015336055780444, "grad_norm": 1.4563037157058716, "learning_rate": 7.420613245489822e-05, "loss": 0.4689915180206299, "step": 336720 }, { "epoch": 2.001593047654713, "grad_norm": 1.1463247537612915, "learning_rate": 7.420042124414451e-05, "loss": 0.4661843776702881, "step": 336730 }, { "epoch": 2.001652489731381, "grad_norm": 1.4635169506072998, "learning_rate": 7.419471020464424e-05, "loss": 0.4958005905151367, "step": 336740 }, { "epoch": 2.0017119318080496, "grad_norm": 1.204885721206665, "learning_rate": 7.41889993364248e-05, "loss": 0.5351468086242676, "step": 336750 }, { "epoch": 2.001771373884718, "grad_norm": 1.0735396146774292, "learning_rate": 7.418328863951347e-05, "loss": 0.4358816146850586, "step": 336760 }, { "epoch": 2.0018308159613865, "grad_norm": 1.4937744140625, "learning_rate": 7.41775781139376e-05, "loss": 0.5129388809204102, "step": 336770 }, { "epoch": 2.001890258038055, "grad_norm": 1.052006721496582, "learning_rate": 7.417186775972449e-05, "loss": 0.46508026123046875, "step": 336780 }, { "epoch": 2.0019497001147233, "grad_norm": 1.2898435592651367, "learning_rate": 7.416615757690145e-05, "loss": 0.5000336647033692, "step": 336790 }, { "epoch": 2.0020091421913917, "grad_norm": 1.4120697975158691, "learning_rate": 7.416044756549578e-05, "loss": 0.5211735725402832, "step": 336800 }, { "epoch": 2.00206858426806, "grad_norm": 1.445305347442627, "learning_rate": 7.415473772553484e-05, "loss": 0.44467744827270506, "step": 336810 }, { "epoch": 2.0021280263447285, "grad_norm": 1.4265519380569458, "learning_rate": 7.414902805704593e-05, "loss": 0.5136792182922363, "step": 336820 }, { "epoch": 2.002187468421397, "grad_norm": 1.2772856950759888, "learning_rate": 7.414331856005632e-05, "loss": 0.5039840698242187, "step": 336830 }, { "epoch": 2.0022469104980654, "grad_norm": 1.174554705619812, "learning_rate": 7.413760923459338e-05, "loss": 0.485365104675293, "step": 336840 }, { "epoch": 2.0023063525747338, "grad_norm": 1.2606853246688843, "learning_rate": 7.413190008068441e-05, "loss": 0.5272524356842041, "step": 336850 }, { "epoch": 2.0023657946514017, "grad_norm": 1.238234519958496, "learning_rate": 7.412619109835668e-05, "loss": 0.5247186660766602, "step": 336860 }, { "epoch": 2.00242523672807, "grad_norm": 1.1926788091659546, "learning_rate": 7.412048228763752e-05, "loss": 0.49589967727661133, "step": 336870 }, { "epoch": 2.0024846788047386, "grad_norm": 1.7662618160247803, "learning_rate": 7.411477364855428e-05, "loss": 0.5020335197448731, "step": 336880 }, { "epoch": 2.002544120881407, "grad_norm": 1.1522634029388428, "learning_rate": 7.410906518113423e-05, "loss": 0.5358174324035645, "step": 336890 }, { "epoch": 2.0026035629580754, "grad_norm": 1.2908940315246582, "learning_rate": 7.410335688540466e-05, "loss": 0.5454248905181884, "step": 336900 }, { "epoch": 2.002663005034744, "grad_norm": 1.2040449380874634, "learning_rate": 7.40976487613929e-05, "loss": 0.4744229316711426, "step": 336910 }, { "epoch": 2.0027224471114122, "grad_norm": 1.1854687929153442, "learning_rate": 7.409194080912632e-05, "loss": 0.49651002883911133, "step": 336920 }, { "epoch": 2.0027818891880806, "grad_norm": 1.2931437492370605, "learning_rate": 7.408623302863207e-05, "loss": 0.5556576728820801, "step": 336930 }, { "epoch": 2.002841331264749, "grad_norm": 1.393036961555481, "learning_rate": 7.40805254199376e-05, "loss": 0.5014466285705567, "step": 336940 }, { "epoch": 2.0029007733414175, "grad_norm": 1.2737852334976196, "learning_rate": 7.407481798307016e-05, "loss": 0.5000467777252198, "step": 336950 }, { "epoch": 2.002960215418086, "grad_norm": 1.6940168142318726, "learning_rate": 7.4069110718057e-05, "loss": 0.5805352687835693, "step": 336960 }, { "epoch": 2.0030196574947543, "grad_norm": 1.3161991834640503, "learning_rate": 7.406340362492551e-05, "loss": 0.476669979095459, "step": 336970 }, { "epoch": 2.0030790995714227, "grad_norm": 1.693402647972107, "learning_rate": 7.405769670370298e-05, "loss": 0.5613361835479737, "step": 336980 }, { "epoch": 2.003138541648091, "grad_norm": 1.520289659500122, "learning_rate": 7.40519899544166e-05, "loss": 0.519681167602539, "step": 336990 }, { "epoch": 2.0031979837247595, "grad_norm": 1.2597867250442505, "learning_rate": 7.40462833770938e-05, "loss": 0.4883512020111084, "step": 337000 }, { "epoch": 2.003257425801428, "grad_norm": 1.3779512643814087, "learning_rate": 7.404057697176186e-05, "loss": 0.5032237052917481, "step": 337010 }, { "epoch": 2.0033168678780964, "grad_norm": 1.5520141124725342, "learning_rate": 7.4034870738448e-05, "loss": 0.5461426734924316, "step": 337020 }, { "epoch": 2.003376309954765, "grad_norm": 1.3314305543899536, "learning_rate": 7.40291646771796e-05, "loss": 0.5459997177124023, "step": 337030 }, { "epoch": 2.0034357520314328, "grad_norm": 1.2743326425552368, "learning_rate": 7.402345878798391e-05, "loss": 0.5745223045349122, "step": 337040 }, { "epoch": 2.003495194108101, "grad_norm": 1.7471967935562134, "learning_rate": 7.401775307088825e-05, "loss": 0.5606141090393066, "step": 337050 }, { "epoch": 2.0035546361847696, "grad_norm": 1.2588733434677124, "learning_rate": 7.401204752591985e-05, "loss": 0.5135130882263184, "step": 337060 }, { "epoch": 2.003614078261438, "grad_norm": 1.7146656513214111, "learning_rate": 7.400634215310611e-05, "loss": 0.5498044967651368, "step": 337070 }, { "epoch": 2.0036735203381064, "grad_norm": 1.2394812107086182, "learning_rate": 7.400063695247424e-05, "loss": 0.5294028282165527, "step": 337080 }, { "epoch": 2.003732962414775, "grad_norm": 1.2642936706542969, "learning_rate": 7.399493192405156e-05, "loss": 0.5355147361755371, "step": 337090 }, { "epoch": 2.0037924044914432, "grad_norm": 1.0293127298355103, "learning_rate": 7.398922706786535e-05, "loss": 0.4466146469116211, "step": 337100 }, { "epoch": 2.0038518465681117, "grad_norm": 1.5379314422607422, "learning_rate": 7.398352238394293e-05, "loss": 0.5217984199523926, "step": 337110 }, { "epoch": 2.00391128864478, "grad_norm": 1.4676841497421265, "learning_rate": 7.397781787231156e-05, "loss": 0.562445592880249, "step": 337120 }, { "epoch": 2.0039707307214485, "grad_norm": 1.2637999057769775, "learning_rate": 7.397211353299853e-05, "loss": 0.5254415512084961, "step": 337130 }, { "epoch": 2.004030172798117, "grad_norm": 1.3673145771026611, "learning_rate": 7.396640936603115e-05, "loss": 0.48580198287963866, "step": 337140 }, { "epoch": 2.0040896148747853, "grad_norm": 1.3478927612304688, "learning_rate": 7.396070537143665e-05, "loss": 0.4755545139312744, "step": 337150 }, { "epoch": 2.0041490569514537, "grad_norm": 1.6649152040481567, "learning_rate": 7.39550015492424e-05, "loss": 0.5447830200195313, "step": 337160 }, { "epoch": 2.004208499028122, "grad_norm": 1.433264970779419, "learning_rate": 7.394929789947564e-05, "loss": 0.4653714656829834, "step": 337170 }, { "epoch": 2.0042679411047906, "grad_norm": 1.3878602981567383, "learning_rate": 7.394359442216365e-05, "loss": 0.5281208038330079, "step": 337180 }, { "epoch": 2.004327383181459, "grad_norm": 1.1405802965164185, "learning_rate": 7.393789111733371e-05, "loss": 0.49593091011047363, "step": 337190 }, { "epoch": 2.0043868252581274, "grad_norm": 1.358713150024414, "learning_rate": 7.393218798501313e-05, "loss": 0.5017484664916992, "step": 337200 }, { "epoch": 2.004446267334796, "grad_norm": 1.6239506006240845, "learning_rate": 7.392648502522916e-05, "loss": 0.5283361911773682, "step": 337210 }, { "epoch": 2.004505709411464, "grad_norm": 1.1930086612701416, "learning_rate": 7.392078223800909e-05, "loss": 0.5080249786376954, "step": 337220 }, { "epoch": 2.004565151488132, "grad_norm": 1.546614646911621, "learning_rate": 7.391507962338025e-05, "loss": 0.49309210777282714, "step": 337230 }, { "epoch": 2.0046245935648006, "grad_norm": 1.6869596242904663, "learning_rate": 7.390937718136985e-05, "loss": 0.5388439655303955, "step": 337240 }, { "epoch": 2.004684035641469, "grad_norm": 0.9643711447715759, "learning_rate": 7.390367491200519e-05, "loss": 0.5241832256317138, "step": 337250 }, { "epoch": 2.0047434777181374, "grad_norm": 1.6454095840454102, "learning_rate": 7.389797281531355e-05, "loss": 0.5330694198608399, "step": 337260 }, { "epoch": 2.004802919794806, "grad_norm": 1.2299494743347168, "learning_rate": 7.389227089132222e-05, "loss": 0.5074223518371582, "step": 337270 }, { "epoch": 2.0048623618714743, "grad_norm": 1.2557564973831177, "learning_rate": 7.388656914005845e-05, "loss": 0.5741422653198243, "step": 337280 }, { "epoch": 2.0049218039481427, "grad_norm": 1.4288427829742432, "learning_rate": 7.388086756154955e-05, "loss": 0.5086198806762695, "step": 337290 }, { "epoch": 2.004981246024811, "grad_norm": 1.3672658205032349, "learning_rate": 7.387516615582278e-05, "loss": 0.4960916519165039, "step": 337300 }, { "epoch": 2.0050406881014795, "grad_norm": 1.4826194047927856, "learning_rate": 7.386946492290541e-05, "loss": 0.5446734428405762, "step": 337310 }, { "epoch": 2.005100130178148, "grad_norm": 0.9427372813224792, "learning_rate": 7.386376386282467e-05, "loss": 0.48455076217651366, "step": 337320 }, { "epoch": 2.0051595722548163, "grad_norm": 1.4609308242797852, "learning_rate": 7.38580629756079e-05, "loss": 0.5251795768737793, "step": 337330 }, { "epoch": 2.0052190143314848, "grad_norm": 1.2635576725006104, "learning_rate": 7.385236226128238e-05, "loss": 0.49438066482543946, "step": 337340 }, { "epoch": 2.005278456408153, "grad_norm": 1.5987873077392578, "learning_rate": 7.38466617198753e-05, "loss": 0.5238154411315918, "step": 337350 }, { "epoch": 2.0053378984848216, "grad_norm": 1.3360002040863037, "learning_rate": 7.3840961351414e-05, "loss": 0.5015650749206543, "step": 337360 }, { "epoch": 2.00539734056149, "grad_norm": 1.1551915407180786, "learning_rate": 7.383526115592572e-05, "loss": 0.4699728012084961, "step": 337370 }, { "epoch": 2.0054567826381584, "grad_norm": 1.2740750312805176, "learning_rate": 7.38295611334377e-05, "loss": 0.5491398334503174, "step": 337380 }, { "epoch": 2.005516224714827, "grad_norm": 1.4761204719543457, "learning_rate": 7.382386128397729e-05, "loss": 0.5661306858062745, "step": 337390 }, { "epoch": 2.0055756667914952, "grad_norm": 1.1290401220321655, "learning_rate": 7.381816160757166e-05, "loss": 0.5020568370819092, "step": 337400 }, { "epoch": 2.005635108868163, "grad_norm": 1.224644660949707, "learning_rate": 7.38124621042482e-05, "loss": 0.5226788520812988, "step": 337410 }, { "epoch": 2.0056945509448316, "grad_norm": 1.3114759922027588, "learning_rate": 7.380676277403398e-05, "loss": 0.489589786529541, "step": 337420 }, { "epoch": 2.0057539930215, "grad_norm": 1.2525714635849, "learning_rate": 7.380106361695645e-05, "loss": 0.5178412437438965, "step": 337430 }, { "epoch": 2.0058134350981685, "grad_norm": 1.712584376335144, "learning_rate": 7.379536463304282e-05, "loss": 0.5090060234069824, "step": 337440 }, { "epoch": 2.005872877174837, "grad_norm": 1.5971652269363403, "learning_rate": 7.378966582232027e-05, "loss": 0.5423921585083008, "step": 337450 }, { "epoch": 2.0059323192515053, "grad_norm": 1.5642348527908325, "learning_rate": 7.378396718481614e-05, "loss": 0.5164649486541748, "step": 337460 }, { "epoch": 2.0059917613281737, "grad_norm": 1.4655600786209106, "learning_rate": 7.377826872055773e-05, "loss": 0.49644904136657714, "step": 337470 }, { "epoch": 2.006051203404842, "grad_norm": 1.3333083391189575, "learning_rate": 7.377257042957217e-05, "loss": 0.49771642684936523, "step": 337480 }, { "epoch": 2.0061106454815105, "grad_norm": 1.420432209968567, "learning_rate": 7.376687231188684e-05, "loss": 0.4798592567443848, "step": 337490 }, { "epoch": 2.006170087558179, "grad_norm": 1.4244884252548218, "learning_rate": 7.376117436752896e-05, "loss": 0.5202450275421142, "step": 337500 }, { "epoch": 2.0062295296348474, "grad_norm": 1.3920953273773193, "learning_rate": 7.375547659652573e-05, "loss": 0.5267374992370606, "step": 337510 }, { "epoch": 2.0062889717115158, "grad_norm": 1.1798115968704224, "learning_rate": 7.37497789989045e-05, "loss": 0.5137112617492676, "step": 337520 }, { "epoch": 2.006348413788184, "grad_norm": 1.2322537899017334, "learning_rate": 7.374408157469251e-05, "loss": 0.5066801548004151, "step": 337530 }, { "epoch": 2.0064078558648526, "grad_norm": 1.7684324979782104, "learning_rate": 7.373838432391693e-05, "loss": 0.4987003326416016, "step": 337540 }, { "epoch": 2.006467297941521, "grad_norm": 1.6515799760818481, "learning_rate": 7.373268724660505e-05, "loss": 0.5552617073059082, "step": 337550 }, { "epoch": 2.0065267400181894, "grad_norm": 1.3103779554367065, "learning_rate": 7.372699034278421e-05, "loss": 0.55805983543396, "step": 337560 }, { "epoch": 2.006586182094858, "grad_norm": 1.0453975200653076, "learning_rate": 7.372129361248154e-05, "loss": 0.5039313316345215, "step": 337570 }, { "epoch": 2.0066456241715263, "grad_norm": 1.439194679260254, "learning_rate": 7.371559705572435e-05, "loss": 0.5433950424194336, "step": 337580 }, { "epoch": 2.0067050662481947, "grad_norm": 1.3168095350265503, "learning_rate": 7.370990067253991e-05, "loss": 0.4788163185119629, "step": 337590 }, { "epoch": 2.0067645083248626, "grad_norm": 1.626093864440918, "learning_rate": 7.370420446295545e-05, "loss": 0.5163113594055175, "step": 337600 }, { "epoch": 2.006823950401531, "grad_norm": 1.336524486541748, "learning_rate": 7.369850842699815e-05, "loss": 0.5135364532470703, "step": 337610 }, { "epoch": 2.0068833924781995, "grad_norm": 1.2739012241363525, "learning_rate": 7.36928125646954e-05, "loss": 0.4725017547607422, "step": 337620 }, { "epoch": 2.006942834554868, "grad_norm": 1.5949722528457642, "learning_rate": 7.368711687607434e-05, "loss": 0.49382004737854, "step": 337630 }, { "epoch": 2.0070022766315363, "grad_norm": 1.157294511795044, "learning_rate": 7.368142136116223e-05, "loss": 0.5027238845825195, "step": 337640 }, { "epoch": 2.0070617187082047, "grad_norm": 1.0851045846939087, "learning_rate": 7.367572601998636e-05, "loss": 0.5117867469787598, "step": 337650 }, { "epoch": 2.007121160784873, "grad_norm": 1.774052619934082, "learning_rate": 7.367003085257393e-05, "loss": 0.46526899337768557, "step": 337660 }, { "epoch": 2.0071806028615415, "grad_norm": 1.245664358139038, "learning_rate": 7.366433585895223e-05, "loss": 0.5071207523345947, "step": 337670 }, { "epoch": 2.00724004493821, "grad_norm": 1.2280874252319336, "learning_rate": 7.365864103914842e-05, "loss": 0.5125260353088379, "step": 337680 }, { "epoch": 2.0072994870148784, "grad_norm": 1.3708730936050415, "learning_rate": 7.365294639318983e-05, "loss": 0.5451647758483886, "step": 337690 }, { "epoch": 2.007358929091547, "grad_norm": 1.3221737146377563, "learning_rate": 7.364725192110367e-05, "loss": 0.5169875621795654, "step": 337700 }, { "epoch": 2.007418371168215, "grad_norm": 1.5339900255203247, "learning_rate": 7.364155762291713e-05, "loss": 0.48311710357666016, "step": 337710 }, { "epoch": 2.0074778132448836, "grad_norm": 1.2639086246490479, "learning_rate": 7.363586349865754e-05, "loss": 0.48992280960083007, "step": 337720 }, { "epoch": 2.007537255321552, "grad_norm": 1.4796346426010132, "learning_rate": 7.36301695483521e-05, "loss": 0.5143292903900146, "step": 337730 }, { "epoch": 2.0075966973982204, "grad_norm": 1.465958595275879, "learning_rate": 7.3624475772028e-05, "loss": 0.4926325798034668, "step": 337740 }, { "epoch": 2.007656139474889, "grad_norm": 1.5947463512420654, "learning_rate": 7.361878216971254e-05, "loss": 0.5366460800170898, "step": 337750 }, { "epoch": 2.0077155815515573, "grad_norm": 1.305790901184082, "learning_rate": 7.361308874143296e-05, "loss": 0.5344823837280274, "step": 337760 }, { "epoch": 2.0077750236282257, "grad_norm": 1.4157371520996094, "learning_rate": 7.360739548721645e-05, "loss": 0.5036334991455078, "step": 337770 }, { "epoch": 2.0078344657048937, "grad_norm": 1.7631850242614746, "learning_rate": 7.360170240709028e-05, "loss": 0.555838680267334, "step": 337780 }, { "epoch": 2.007893907781562, "grad_norm": 1.597348690032959, "learning_rate": 7.359600950108165e-05, "loss": 0.49448361396789553, "step": 337790 }, { "epoch": 2.0079533498582305, "grad_norm": 1.4353996515274048, "learning_rate": 7.359031676921784e-05, "loss": 0.5286683082580567, "step": 337800 }, { "epoch": 2.008012791934899, "grad_norm": 1.3320584297180176, "learning_rate": 7.358462421152603e-05, "loss": 0.4971649646759033, "step": 337810 }, { "epoch": 2.0080722340115673, "grad_norm": 1.2023296356201172, "learning_rate": 7.357893182803348e-05, "loss": 0.5131530284881591, "step": 337820 }, { "epoch": 2.0081316760882357, "grad_norm": 1.1842074394226074, "learning_rate": 7.357323961876745e-05, "loss": 0.4790019989013672, "step": 337830 }, { "epoch": 2.008191118164904, "grad_norm": 1.3174772262573242, "learning_rate": 7.356754758375511e-05, "loss": 0.5009456634521484, "step": 337840 }, { "epoch": 2.0082505602415726, "grad_norm": 1.125778079032898, "learning_rate": 7.356185572302373e-05, "loss": 0.5256648063659668, "step": 337850 }, { "epoch": 2.008310002318241, "grad_norm": 1.4811124801635742, "learning_rate": 7.35561640366005e-05, "loss": 0.5002835273742676, "step": 337860 }, { "epoch": 2.0083694443949094, "grad_norm": 1.1864421367645264, "learning_rate": 7.355047252451268e-05, "loss": 0.4575685501098633, "step": 337870 }, { "epoch": 2.008428886471578, "grad_norm": 1.3034255504608154, "learning_rate": 7.35447811867875e-05, "loss": 0.46204214096069335, "step": 337880 }, { "epoch": 2.008488328548246, "grad_norm": 1.5158582925796509, "learning_rate": 7.353909002345217e-05, "loss": 0.548580265045166, "step": 337890 }, { "epoch": 2.0085477706249146, "grad_norm": 1.4618202447891235, "learning_rate": 7.353339903453393e-05, "loss": 0.5600543022155762, "step": 337900 }, { "epoch": 2.008607212701583, "grad_norm": 1.7449357509613037, "learning_rate": 7.352770822005994e-05, "loss": 0.5108002662658692, "step": 337910 }, { "epoch": 2.0086666547782515, "grad_norm": 1.7467912435531616, "learning_rate": 7.352201758005752e-05, "loss": 0.5187562942504883, "step": 337920 }, { "epoch": 2.00872609685492, "grad_norm": 0.957855761051178, "learning_rate": 7.351632711455387e-05, "loss": 0.4640494823455811, "step": 337930 }, { "epoch": 2.0087855389315883, "grad_norm": 1.6716848611831665, "learning_rate": 7.351063682357611e-05, "loss": 0.5304116249084473, "step": 337940 }, { "epoch": 2.0088449810082567, "grad_norm": 1.2026371955871582, "learning_rate": 7.35049467071516e-05, "loss": 0.5140686988830566, "step": 337950 }, { "epoch": 2.0089044230849247, "grad_norm": 1.2660279273986816, "learning_rate": 7.349925676530751e-05, "loss": 0.45122699737548827, "step": 337960 }, { "epoch": 2.008963865161593, "grad_norm": 1.1271133422851562, "learning_rate": 7.3493566998071e-05, "loss": 0.5659865856170654, "step": 337970 }, { "epoch": 2.0090233072382615, "grad_norm": 1.5054317712783813, "learning_rate": 7.348787740546933e-05, "loss": 0.47806406021118164, "step": 337980 }, { "epoch": 2.00908274931493, "grad_norm": 1.5079997777938843, "learning_rate": 7.348218798752977e-05, "loss": 0.5414527893066406, "step": 337990 }, { "epoch": 2.0091421913915983, "grad_norm": 1.444274663925171, "learning_rate": 7.347649874427944e-05, "loss": 0.44985618591308596, "step": 338000 }, { "epoch": 2.0092016334682667, "grad_norm": 1.2054017782211304, "learning_rate": 7.347080967574563e-05, "loss": 0.4657400131225586, "step": 338010 }, { "epoch": 2.009261075544935, "grad_norm": 1.3454575538635254, "learning_rate": 7.346512078195555e-05, "loss": 0.481770658493042, "step": 338020 }, { "epoch": 2.0093205176216036, "grad_norm": 1.3511847257614136, "learning_rate": 7.345943206293638e-05, "loss": 0.5379692554473877, "step": 338030 }, { "epoch": 2.009379959698272, "grad_norm": 1.087100625038147, "learning_rate": 7.34537435187153e-05, "loss": 0.5019264221191406, "step": 338040 }, { "epoch": 2.0094394017749404, "grad_norm": 1.3792144060134888, "learning_rate": 7.344805514931963e-05, "loss": 0.4260107040405273, "step": 338050 }, { "epoch": 2.009498843851609, "grad_norm": 1.2878777980804443, "learning_rate": 7.344236695477651e-05, "loss": 0.4836392402648926, "step": 338060 }, { "epoch": 2.0095582859282772, "grad_norm": 1.511917233467102, "learning_rate": 7.34366789351131e-05, "loss": 0.5488617420196533, "step": 338070 }, { "epoch": 2.0096177280049456, "grad_norm": 1.569523811340332, "learning_rate": 7.343099109035674e-05, "loss": 0.5466760158538818, "step": 338080 }, { "epoch": 2.009677170081614, "grad_norm": 1.1545875072479248, "learning_rate": 7.342530342053456e-05, "loss": 0.5377274513244629, "step": 338090 }, { "epoch": 2.0097366121582825, "grad_norm": 1.4414266347885132, "learning_rate": 7.34196159256737e-05, "loss": 0.566144609451294, "step": 338100 }, { "epoch": 2.009796054234951, "grad_norm": 1.488086462020874, "learning_rate": 7.341392860580152e-05, "loss": 0.5047368049621582, "step": 338110 }, { "epoch": 2.0098554963116193, "grad_norm": 1.4537336826324463, "learning_rate": 7.340824146094514e-05, "loss": 0.5360142707824707, "step": 338120 }, { "epoch": 2.0099149383882877, "grad_norm": 1.3785208463668823, "learning_rate": 7.340255449113172e-05, "loss": 0.44855303764343263, "step": 338130 }, { "epoch": 2.009974380464956, "grad_norm": 1.1925489902496338, "learning_rate": 7.339686769638858e-05, "loss": 0.4781804084777832, "step": 338140 }, { "epoch": 2.010033822541624, "grad_norm": 1.4868329763412476, "learning_rate": 7.339118107674284e-05, "loss": 0.5467675209045411, "step": 338150 }, { "epoch": 2.0100932646182925, "grad_norm": 1.4408900737762451, "learning_rate": 7.338549463222175e-05, "loss": 0.4830196380615234, "step": 338160 }, { "epoch": 2.010152706694961, "grad_norm": 1.3744659423828125, "learning_rate": 7.337980836285243e-05, "loss": 0.5425889968872071, "step": 338170 }, { "epoch": 2.0102121487716293, "grad_norm": 1.1123251914978027, "learning_rate": 7.33741222686622e-05, "loss": 0.5041854381561279, "step": 338180 }, { "epoch": 2.0102715908482978, "grad_norm": 1.3204916715621948, "learning_rate": 7.336843634967818e-05, "loss": 0.5484981536865234, "step": 338190 }, { "epoch": 2.010331032924966, "grad_norm": 1.2988367080688477, "learning_rate": 7.336275060592757e-05, "loss": 0.4561290740966797, "step": 338200 }, { "epoch": 2.0103904750016346, "grad_norm": 1.521175503730774, "learning_rate": 7.33570650374376e-05, "loss": 0.5214074134826661, "step": 338210 }, { "epoch": 2.010449917078303, "grad_norm": 1.288141131401062, "learning_rate": 7.335137964423546e-05, "loss": 0.48268942832946776, "step": 338220 }, { "epoch": 2.0105093591549714, "grad_norm": 1.476582646369934, "learning_rate": 7.334569442634833e-05, "loss": 0.49838976860046386, "step": 338230 }, { "epoch": 2.01056880123164, "grad_norm": 1.46299147605896, "learning_rate": 7.334000938380343e-05, "loss": 0.5329190731048584, "step": 338240 }, { "epoch": 2.0106282433083082, "grad_norm": 1.5624080896377563, "learning_rate": 7.333432451662797e-05, "loss": 0.5134441375732421, "step": 338250 }, { "epoch": 2.0106876853849767, "grad_norm": 1.3410066366195679, "learning_rate": 7.332863982484908e-05, "loss": 0.5046780109405518, "step": 338260 }, { "epoch": 2.010747127461645, "grad_norm": 1.2783468961715698, "learning_rate": 7.3322955308494e-05, "loss": 0.5162901878356934, "step": 338270 }, { "epoch": 2.0108065695383135, "grad_norm": 1.318509817123413, "learning_rate": 7.331727096758991e-05, "loss": 0.585080909729004, "step": 338280 }, { "epoch": 2.010866011614982, "grad_norm": 1.2725415229797363, "learning_rate": 7.331158680216403e-05, "loss": 0.5176169395446777, "step": 338290 }, { "epoch": 2.0109254536916503, "grad_norm": 1.47678542137146, "learning_rate": 7.330590281224352e-05, "loss": 0.5553726196289063, "step": 338300 }, { "epoch": 2.0109848957683187, "grad_norm": 1.1523357629776, "learning_rate": 7.330021899785557e-05, "loss": 0.4726727962493896, "step": 338310 }, { "epoch": 2.011044337844987, "grad_norm": 1.3104618787765503, "learning_rate": 7.32945353590274e-05, "loss": 0.46187291145324705, "step": 338320 }, { "epoch": 2.0111037799216556, "grad_norm": 1.5636273622512817, "learning_rate": 7.328885189578614e-05, "loss": 0.43193645477294923, "step": 338330 }, { "epoch": 2.0111632219983235, "grad_norm": 1.3483009338378906, "learning_rate": 7.328316860815905e-05, "loss": 0.5166869640350342, "step": 338340 }, { "epoch": 2.011222664074992, "grad_norm": 1.4152401685714722, "learning_rate": 7.327748549617328e-05, "loss": 0.5572337150573731, "step": 338350 }, { "epoch": 2.0112821061516604, "grad_norm": 1.4845612049102783, "learning_rate": 7.3271802559856e-05, "loss": 0.48514976501464846, "step": 338360 }, { "epoch": 2.011341548228329, "grad_norm": 1.5185461044311523, "learning_rate": 7.326611979923442e-05, "loss": 0.5373610019683838, "step": 338370 }, { "epoch": 2.011400990304997, "grad_norm": 1.2897213697433472, "learning_rate": 7.326043721433571e-05, "loss": 0.5087909698486328, "step": 338380 }, { "epoch": 2.0114604323816656, "grad_norm": 1.9710651636123657, "learning_rate": 7.325475480518709e-05, "loss": 0.5450185775756836, "step": 338390 }, { "epoch": 2.011519874458334, "grad_norm": 1.2441799640655518, "learning_rate": 7.324907257181568e-05, "loss": 0.4566351890563965, "step": 338400 }, { "epoch": 2.0115793165350024, "grad_norm": 1.0486972332000732, "learning_rate": 7.324339051424874e-05, "loss": 0.534607219696045, "step": 338410 }, { "epoch": 2.011638758611671, "grad_norm": 1.3953289985656738, "learning_rate": 7.323770863251336e-05, "loss": 0.5390247821807861, "step": 338420 }, { "epoch": 2.0116982006883393, "grad_norm": 1.3385789394378662, "learning_rate": 7.323202692663678e-05, "loss": 0.482590389251709, "step": 338430 }, { "epoch": 2.0117576427650077, "grad_norm": 1.4197883605957031, "learning_rate": 7.322634539664619e-05, "loss": 0.5527092933654785, "step": 338440 }, { "epoch": 2.011817084841676, "grad_norm": 1.0158121585845947, "learning_rate": 7.322066404256873e-05, "loss": 0.47895402908325196, "step": 338450 }, { "epoch": 2.0118765269183445, "grad_norm": 1.0079787969589233, "learning_rate": 7.321498286443159e-05, "loss": 0.4751708507537842, "step": 338460 }, { "epoch": 2.011935968995013, "grad_norm": 1.5263081789016724, "learning_rate": 7.320930186226196e-05, "loss": 0.5296815395355224, "step": 338470 }, { "epoch": 2.0119954110716813, "grad_norm": 1.8876293897628784, "learning_rate": 7.320362103608703e-05, "loss": 0.510765552520752, "step": 338480 }, { "epoch": 2.0120548531483498, "grad_norm": 1.11403489112854, "learning_rate": 7.319794038593389e-05, "loss": 0.500623083114624, "step": 338490 }, { "epoch": 2.012114295225018, "grad_norm": 1.7032983303070068, "learning_rate": 7.319225991182981e-05, "loss": 0.5063882827758789, "step": 338500 }, { "epoch": 2.0121737373016866, "grad_norm": 1.7329555749893188, "learning_rate": 7.318657961380196e-05, "loss": 0.5293848037719726, "step": 338510 }, { "epoch": 2.0122331793783546, "grad_norm": 1.5829256772994995, "learning_rate": 7.318089949187745e-05, "loss": 0.47744083404541016, "step": 338520 }, { "epoch": 2.012292621455023, "grad_norm": 1.5223737955093384, "learning_rate": 7.317521954608346e-05, "loss": 0.5249133110046387, "step": 338530 }, { "epoch": 2.0123520635316914, "grad_norm": 1.5516856908798218, "learning_rate": 7.316953977644723e-05, "loss": 0.5501331806182861, "step": 338540 }, { "epoch": 2.01241150560836, "grad_norm": 1.4897522926330566, "learning_rate": 7.316386018299588e-05, "loss": 0.428403902053833, "step": 338550 }, { "epoch": 2.012470947685028, "grad_norm": 1.0160006284713745, "learning_rate": 7.315818076575654e-05, "loss": 0.4357825756072998, "step": 338560 }, { "epoch": 2.0125303897616966, "grad_norm": 1.2956719398498535, "learning_rate": 7.315250152475648e-05, "loss": 0.508115816116333, "step": 338570 }, { "epoch": 2.012589831838365, "grad_norm": 1.7857264280319214, "learning_rate": 7.314682246002278e-05, "loss": 0.5287470817565918, "step": 338580 }, { "epoch": 2.0126492739150335, "grad_norm": 1.3963724374771118, "learning_rate": 7.314114357158261e-05, "loss": 0.5060256004333497, "step": 338590 }, { "epoch": 2.012708715991702, "grad_norm": 1.3523410558700562, "learning_rate": 7.313546485946323e-05, "loss": 0.5287431716918946, "step": 338600 }, { "epoch": 2.0127681580683703, "grad_norm": 1.1247929334640503, "learning_rate": 7.312978632369169e-05, "loss": 0.4757511615753174, "step": 338610 }, { "epoch": 2.0128276001450387, "grad_norm": 1.415764570236206, "learning_rate": 7.312410796429525e-05, "loss": 0.5360841751098633, "step": 338620 }, { "epoch": 2.012887042221707, "grad_norm": 1.2800451517105103, "learning_rate": 7.311842978130099e-05, "loss": 0.524134349822998, "step": 338630 }, { "epoch": 2.0129464842983755, "grad_norm": 1.580341100692749, "learning_rate": 7.31127517747361e-05, "loss": 0.507811164855957, "step": 338640 }, { "epoch": 2.013005926375044, "grad_norm": 1.262467861175537, "learning_rate": 7.31070739446278e-05, "loss": 0.5028762340545654, "step": 338650 }, { "epoch": 2.0130653684517124, "grad_norm": 1.3902140855789185, "learning_rate": 7.310139629100315e-05, "loss": 0.47832612991333007, "step": 338660 }, { "epoch": 2.0131248105283808, "grad_norm": 1.2963708639144897, "learning_rate": 7.309571881388934e-05, "loss": 0.49588441848754883, "step": 338670 }, { "epoch": 2.013184252605049, "grad_norm": 1.2705633640289307, "learning_rate": 7.309004151331363e-05, "loss": 0.5324114322662353, "step": 338680 }, { "epoch": 2.0132436946817176, "grad_norm": 1.464056372642517, "learning_rate": 7.308436438930301e-05, "loss": 0.5215564727783203, "step": 338690 }, { "epoch": 2.0133031367583856, "grad_norm": 1.9176560640335083, "learning_rate": 7.30786874418848e-05, "loss": 0.5539015293121338, "step": 338700 }, { "epoch": 2.013362578835054, "grad_norm": 1.807604432106018, "learning_rate": 7.307301067108605e-05, "loss": 0.4829387664794922, "step": 338710 }, { "epoch": 2.0134220209117224, "grad_norm": 1.0794808864593506, "learning_rate": 7.306733407693396e-05, "loss": 0.4879015922546387, "step": 338720 }, { "epoch": 2.013481462988391, "grad_norm": 1.309391736984253, "learning_rate": 7.306165765945567e-05, "loss": 0.5152329444885254, "step": 338730 }, { "epoch": 2.0135409050650592, "grad_norm": 1.3957490921020508, "learning_rate": 7.305598141867835e-05, "loss": 0.5341163635253906, "step": 338740 }, { "epoch": 2.0136003471417276, "grad_norm": 1.4269403219223022, "learning_rate": 7.305030535462913e-05, "loss": 0.5317177772521973, "step": 338750 }, { "epoch": 2.013659789218396, "grad_norm": 1.4317615032196045, "learning_rate": 7.304462946733516e-05, "loss": 0.5262273788452149, "step": 338760 }, { "epoch": 2.0137192312950645, "grad_norm": 1.3684287071228027, "learning_rate": 7.303895375682364e-05, "loss": 0.5092012405395507, "step": 338770 }, { "epoch": 2.013778673371733, "grad_norm": 1.4460020065307617, "learning_rate": 7.303327822312164e-05, "loss": 0.48476371765136717, "step": 338780 }, { "epoch": 2.0138381154484013, "grad_norm": 1.063733696937561, "learning_rate": 7.302760286625638e-05, "loss": 0.4801796913146973, "step": 338790 }, { "epoch": 2.0138975575250697, "grad_norm": 1.4831151962280273, "learning_rate": 7.3021927686255e-05, "loss": 0.5225670814514161, "step": 338800 }, { "epoch": 2.013956999601738, "grad_norm": 1.4644732475280762, "learning_rate": 7.301625268314462e-05, "loss": 0.5021224975585937, "step": 338810 }, { "epoch": 2.0140164416784065, "grad_norm": 1.0768773555755615, "learning_rate": 7.30105778569524e-05, "loss": 0.5048125267028809, "step": 338820 }, { "epoch": 2.014075883755075, "grad_norm": 1.4326404333114624, "learning_rate": 7.300490320770548e-05, "loss": 0.4801319599151611, "step": 338830 }, { "epoch": 2.0141353258317434, "grad_norm": 1.845579743385315, "learning_rate": 7.299922873543104e-05, "loss": 0.5180234909057617, "step": 338840 }, { "epoch": 2.014194767908412, "grad_norm": 1.2391979694366455, "learning_rate": 7.299355444015616e-05, "loss": 0.4844694137573242, "step": 338850 }, { "epoch": 2.01425420998508, "grad_norm": 1.7122704982757568, "learning_rate": 7.298788032190805e-05, "loss": 0.5362709999084473, "step": 338860 }, { "epoch": 2.0143136520617486, "grad_norm": 1.5060734748840332, "learning_rate": 7.29822063807138e-05, "loss": 0.5371987819671631, "step": 338870 }, { "epoch": 2.014373094138417, "grad_norm": 1.4385418891906738, "learning_rate": 7.29765326166006e-05, "loss": 0.5407265186309814, "step": 338880 }, { "epoch": 2.014432536215085, "grad_norm": 1.3199775218963623, "learning_rate": 7.297085902959555e-05, "loss": 0.5662672519683838, "step": 338890 }, { "epoch": 2.0144919782917534, "grad_norm": 1.6868232488632202, "learning_rate": 7.296518561972582e-05, "loss": 0.5428210258483886, "step": 338900 }, { "epoch": 2.014551420368422, "grad_norm": 1.689124584197998, "learning_rate": 7.295951238701855e-05, "loss": 0.5267057418823242, "step": 338910 }, { "epoch": 2.0146108624450902, "grad_norm": 1.052588701248169, "learning_rate": 7.295383933150086e-05, "loss": 0.4664469718933105, "step": 338920 }, { "epoch": 2.0146703045217587, "grad_norm": 1.5882068872451782, "learning_rate": 7.294816645319989e-05, "loss": 0.5121673583984375, "step": 338930 }, { "epoch": 2.014729746598427, "grad_norm": 1.2870466709136963, "learning_rate": 7.294249375214279e-05, "loss": 0.5051019191741943, "step": 338940 }, { "epoch": 2.0147891886750955, "grad_norm": 1.2741889953613281, "learning_rate": 7.293682122835667e-05, "loss": 0.522862434387207, "step": 338950 }, { "epoch": 2.014848630751764, "grad_norm": 1.3744161128997803, "learning_rate": 7.293114888186869e-05, "loss": 0.5152566432952881, "step": 338960 }, { "epoch": 2.0149080728284323, "grad_norm": 1.196021318435669, "learning_rate": 7.292547671270602e-05, "loss": 0.4836899280548096, "step": 338970 }, { "epoch": 2.0149675149051007, "grad_norm": 1.281924843788147, "learning_rate": 7.29198047208957e-05, "loss": 0.4818118095397949, "step": 338980 }, { "epoch": 2.015026956981769, "grad_norm": 1.2547106742858887, "learning_rate": 7.291413290646494e-05, "loss": 0.49524993896484376, "step": 338990 }, { "epoch": 2.0150863990584376, "grad_norm": 1.614478349685669, "learning_rate": 7.290846126944087e-05, "loss": 0.5735987663269043, "step": 339000 }, { "epoch": 2.015145841135106, "grad_norm": 1.2428362369537354, "learning_rate": 7.290278980985059e-05, "loss": 0.5177560806274414, "step": 339010 }, { "epoch": 2.0152052832117744, "grad_norm": 1.2784677743911743, "learning_rate": 7.289711852772121e-05, "loss": 0.47150468826293945, "step": 339020 }, { "epoch": 2.015264725288443, "grad_norm": 1.3284412622451782, "learning_rate": 7.28914474230799e-05, "loss": 0.5350196838378907, "step": 339030 }, { "epoch": 2.015324167365111, "grad_norm": 1.458487629890442, "learning_rate": 7.28857764959538e-05, "loss": 0.4870412349700928, "step": 339040 }, { "epoch": 2.0153836094417796, "grad_norm": 1.5342867374420166, "learning_rate": 7.288010574636996e-05, "loss": 0.4988428592681885, "step": 339050 }, { "epoch": 2.015443051518448, "grad_norm": 1.427587628364563, "learning_rate": 7.287443517435561e-05, "loss": 0.5424892425537109, "step": 339060 }, { "epoch": 2.015502493595116, "grad_norm": 1.0656343698501587, "learning_rate": 7.286876477993787e-05, "loss": 0.46492319107055663, "step": 339070 }, { "epoch": 2.0155619356717844, "grad_norm": 1.7974809408187866, "learning_rate": 7.286309456314373e-05, "loss": 0.5427491664886475, "step": 339080 }, { "epoch": 2.015621377748453, "grad_norm": 1.3440593481063843, "learning_rate": 7.285742452400048e-05, "loss": 0.5438530445098877, "step": 339090 }, { "epoch": 2.0156808198251213, "grad_norm": 1.4230047464370728, "learning_rate": 7.285175466253515e-05, "loss": 0.48825626373291015, "step": 339100 }, { "epoch": 2.0157402619017897, "grad_norm": 1.337012767791748, "learning_rate": 7.28460849787749e-05, "loss": 0.48142991065979, "step": 339110 }, { "epoch": 2.015799703978458, "grad_norm": 1.0104937553405762, "learning_rate": 7.284041547274682e-05, "loss": 0.4963965892791748, "step": 339120 }, { "epoch": 2.0158591460551265, "grad_norm": 1.1959351301193237, "learning_rate": 7.283474614447805e-05, "loss": 0.46089825630187986, "step": 339130 }, { "epoch": 2.015918588131795, "grad_norm": 1.5300229787826538, "learning_rate": 7.282907699399572e-05, "loss": 0.5258079528808594, "step": 339140 }, { "epoch": 2.0159780302084633, "grad_norm": 1.3533352613449097, "learning_rate": 7.282340802132692e-05, "loss": 0.4950107574462891, "step": 339150 }, { "epoch": 2.0160374722851317, "grad_norm": 1.5752266645431519, "learning_rate": 7.28177392264988e-05, "loss": 0.530186653137207, "step": 339160 }, { "epoch": 2.0160969143618, "grad_norm": 1.6489686965942383, "learning_rate": 7.281207060953845e-05, "loss": 0.46700348854064944, "step": 339170 }, { "epoch": 2.0161563564384686, "grad_norm": 1.418204665184021, "learning_rate": 7.280640217047301e-05, "loss": 0.47339458465576173, "step": 339180 }, { "epoch": 2.016215798515137, "grad_norm": 1.6012526750564575, "learning_rate": 7.28007339093296e-05, "loss": 0.5391253471374512, "step": 339190 }, { "epoch": 2.0162752405918054, "grad_norm": 1.2469030618667603, "learning_rate": 7.279506582613531e-05, "loss": 0.5100112915039062, "step": 339200 }, { "epoch": 2.016334682668474, "grad_norm": 1.3420685529708862, "learning_rate": 7.278939792091726e-05, "loss": 0.513270092010498, "step": 339210 }, { "epoch": 2.0163941247451422, "grad_norm": 1.32395339012146, "learning_rate": 7.278373019370257e-05, "loss": 0.530578327178955, "step": 339220 }, { "epoch": 2.0164535668218107, "grad_norm": 1.737230658531189, "learning_rate": 7.277806264451836e-05, "loss": 0.48170485496521, "step": 339230 }, { "epoch": 2.016513008898479, "grad_norm": 1.2441922426223755, "learning_rate": 7.277239527339175e-05, "loss": 0.49131069183349607, "step": 339240 }, { "epoch": 2.0165724509751475, "grad_norm": 1.2634377479553223, "learning_rate": 7.27667280803498e-05, "loss": 0.5110543727874756, "step": 339250 }, { "epoch": 2.0166318930518154, "grad_norm": 0.9743744730949402, "learning_rate": 7.276106106541967e-05, "loss": 0.5061255931854248, "step": 339260 }, { "epoch": 2.016691335128484, "grad_norm": 1.2126996517181396, "learning_rate": 7.275539422862846e-05, "loss": 0.5315311431884766, "step": 339270 }, { "epoch": 2.0167507772051523, "grad_norm": 1.5637109279632568, "learning_rate": 7.274972757000327e-05, "loss": 0.5135434150695801, "step": 339280 }, { "epoch": 2.0168102192818207, "grad_norm": 1.3395910263061523, "learning_rate": 7.27440610895712e-05, "loss": 0.5317830085754395, "step": 339290 }, { "epoch": 2.016869661358489, "grad_norm": 1.2169101238250732, "learning_rate": 7.273839478735937e-05, "loss": 0.4560244560241699, "step": 339300 }, { "epoch": 2.0169291034351575, "grad_norm": 1.3440980911254883, "learning_rate": 7.273272866339489e-05, "loss": 0.5452436447143555, "step": 339310 }, { "epoch": 2.016988545511826, "grad_norm": 1.250717282295227, "learning_rate": 7.272706271770486e-05, "loss": 0.5418473720550537, "step": 339320 }, { "epoch": 2.0170479875884944, "grad_norm": 1.4940568208694458, "learning_rate": 7.272139695031636e-05, "loss": 0.5238876342773438, "step": 339330 }, { "epoch": 2.0171074296651628, "grad_norm": 0.9724358916282654, "learning_rate": 7.271573136125653e-05, "loss": 0.4671795845031738, "step": 339340 }, { "epoch": 2.017166871741831, "grad_norm": 1.1763657331466675, "learning_rate": 7.271006595055245e-05, "loss": 0.5104202270507813, "step": 339350 }, { "epoch": 2.0172263138184996, "grad_norm": 1.1509103775024414, "learning_rate": 7.270440071823126e-05, "loss": 0.47068233489990235, "step": 339360 }, { "epoch": 2.017285755895168, "grad_norm": 1.338592767715454, "learning_rate": 7.269873566431999e-05, "loss": 0.5120850563049316, "step": 339370 }, { "epoch": 2.0173451979718364, "grad_norm": 1.6816611289978027, "learning_rate": 7.269307078884579e-05, "loss": 0.45911555290222167, "step": 339380 }, { "epoch": 2.017404640048505, "grad_norm": 1.4882142543792725, "learning_rate": 7.268740609183575e-05, "loss": 0.5144760131835937, "step": 339390 }, { "epoch": 2.0174640821251733, "grad_norm": 1.176379919052124, "learning_rate": 7.268174157331696e-05, "loss": 0.5083673477172852, "step": 339400 }, { "epoch": 2.0175235242018417, "grad_norm": 1.510022521018982, "learning_rate": 7.267607723331651e-05, "loss": 0.5105644226074219, "step": 339410 }, { "epoch": 2.01758296627851, "grad_norm": 1.7826992273330688, "learning_rate": 7.267041307186153e-05, "loss": 0.5283929824829101, "step": 339420 }, { "epoch": 2.0176424083551785, "grad_norm": 1.2382947206497192, "learning_rate": 7.266474908897911e-05, "loss": 0.5041187763214111, "step": 339430 }, { "epoch": 2.0177018504318465, "grad_norm": 1.4086037874221802, "learning_rate": 7.26590852846963e-05, "loss": 0.5238850116729736, "step": 339440 }, { "epoch": 2.017761292508515, "grad_norm": 1.0230218172073364, "learning_rate": 7.265342165904023e-05, "loss": 0.5203548908233643, "step": 339450 }, { "epoch": 2.0178207345851833, "grad_norm": 1.2505229711532593, "learning_rate": 7.264775821203798e-05, "loss": 0.4720085620880127, "step": 339460 }, { "epoch": 2.0178801766618517, "grad_norm": 1.2670509815216064, "learning_rate": 7.264209494371663e-05, "loss": 0.5271677494049072, "step": 339470 }, { "epoch": 2.01793961873852, "grad_norm": 1.0899889469146729, "learning_rate": 7.263643185410334e-05, "loss": 0.5331489086151123, "step": 339480 }, { "epoch": 2.0179990608151885, "grad_norm": 1.7914506196975708, "learning_rate": 7.263076894322513e-05, "loss": 0.5508595943450928, "step": 339490 }, { "epoch": 2.018058502891857, "grad_norm": 1.3931587934494019, "learning_rate": 7.262510621110911e-05, "loss": 0.506375503540039, "step": 339500 }, { "epoch": 2.0181179449685254, "grad_norm": 1.4025583267211914, "learning_rate": 7.261944365778232e-05, "loss": 0.5114760398864746, "step": 339510 }, { "epoch": 2.018177387045194, "grad_norm": 1.3459640741348267, "learning_rate": 7.261378128327197e-05, "loss": 0.5164834022521972, "step": 339520 }, { "epoch": 2.018236829121862, "grad_norm": 1.046102523803711, "learning_rate": 7.260811908760506e-05, "loss": 0.5083855628967285, "step": 339530 }, { "epoch": 2.0182962711985306, "grad_norm": 1.5244348049163818, "learning_rate": 7.260245707080864e-05, "loss": 0.5152452468872071, "step": 339540 }, { "epoch": 2.018355713275199, "grad_norm": 1.533610463142395, "learning_rate": 7.259679523290986e-05, "loss": 0.5521516323089599, "step": 339550 }, { "epoch": 2.0184151553518674, "grad_norm": 1.1026982069015503, "learning_rate": 7.25911335739358e-05, "loss": 0.4794479846954346, "step": 339560 }, { "epoch": 2.018474597428536, "grad_norm": 1.5729058980941772, "learning_rate": 7.25854720939135e-05, "loss": 0.47679991722106935, "step": 339570 }, { "epoch": 2.0185340395052043, "grad_norm": 1.638014793395996, "learning_rate": 7.257981079287012e-05, "loss": 0.5035700798034668, "step": 339580 }, { "epoch": 2.0185934815818727, "grad_norm": 1.392258644104004, "learning_rate": 7.257414967083271e-05, "loss": 0.5308663368225097, "step": 339590 }, { "epoch": 2.018652923658541, "grad_norm": 1.5712560415267944, "learning_rate": 7.256848872782831e-05, "loss": 0.5770510673522949, "step": 339600 }, { "epoch": 2.0187123657352095, "grad_norm": 1.6293895244598389, "learning_rate": 7.2562827963884e-05, "loss": 0.5567984104156494, "step": 339610 }, { "epoch": 2.018771807811878, "grad_norm": 1.2659375667572021, "learning_rate": 7.255716737902694e-05, "loss": 0.5190377235412598, "step": 339620 }, { "epoch": 2.018831249888546, "grad_norm": 1.238253116607666, "learning_rate": 7.255150697328412e-05, "loss": 0.4811453342437744, "step": 339630 }, { "epoch": 2.0188906919652143, "grad_norm": 1.2131385803222656, "learning_rate": 7.254584674668266e-05, "loss": 0.4517331600189209, "step": 339640 }, { "epoch": 2.0189501340418827, "grad_norm": 1.2637748718261719, "learning_rate": 7.254018669924963e-05, "loss": 0.49965734481811525, "step": 339650 }, { "epoch": 2.019009576118551, "grad_norm": 0.9729093909263611, "learning_rate": 7.253452683101209e-05, "loss": 0.4859346389770508, "step": 339660 }, { "epoch": 2.0190690181952196, "grad_norm": 1.3702861070632935, "learning_rate": 7.252886714199712e-05, "loss": 0.49113736152648924, "step": 339670 }, { "epoch": 2.019128460271888, "grad_norm": 1.3021085262298584, "learning_rate": 7.252320763223181e-05, "loss": 0.5124080657958985, "step": 339680 }, { "epoch": 2.0191879023485564, "grad_norm": 1.3565384149551392, "learning_rate": 7.251754830174327e-05, "loss": 0.5725776672363281, "step": 339690 }, { "epoch": 2.019247344425225, "grad_norm": 1.2012450695037842, "learning_rate": 7.251188915055849e-05, "loss": 0.5015519142150879, "step": 339700 }, { "epoch": 2.019306786501893, "grad_norm": 1.446192979812622, "learning_rate": 7.250623017870461e-05, "loss": 0.49117136001586914, "step": 339710 }, { "epoch": 2.0193662285785616, "grad_norm": 1.2433444261550903, "learning_rate": 7.250057138620865e-05, "loss": 0.5495514869689941, "step": 339720 }, { "epoch": 2.01942567065523, "grad_norm": 1.7297825813293457, "learning_rate": 7.249491277309772e-05, "loss": 0.5209895133972168, "step": 339730 }, { "epoch": 2.0194851127318985, "grad_norm": 1.059078335762024, "learning_rate": 7.248925433939884e-05, "loss": 0.4747634410858154, "step": 339740 }, { "epoch": 2.019544554808567, "grad_norm": 1.4493647813796997, "learning_rate": 7.248359608513912e-05, "loss": 0.554085636138916, "step": 339750 }, { "epoch": 2.0196039968852353, "grad_norm": 1.485973834991455, "learning_rate": 7.247793801034566e-05, "loss": 0.5424470901489258, "step": 339760 }, { "epoch": 2.0196634389619037, "grad_norm": 1.2280998229980469, "learning_rate": 7.247228011504541e-05, "loss": 0.5383248805999756, "step": 339770 }, { "epoch": 2.019722881038572, "grad_norm": 1.7502250671386719, "learning_rate": 7.246662239926554e-05, "loss": 0.538709020614624, "step": 339780 }, { "epoch": 2.0197823231152405, "grad_norm": 1.4402213096618652, "learning_rate": 7.246096486303309e-05, "loss": 0.4930574417114258, "step": 339790 }, { "epoch": 2.019841765191909, "grad_norm": 1.7470804452896118, "learning_rate": 7.245530750637508e-05, "loss": 0.5640649795532227, "step": 339800 }, { "epoch": 2.019901207268577, "grad_norm": 1.5872408151626587, "learning_rate": 7.244965032931865e-05, "loss": 0.5099527359008789, "step": 339810 }, { "epoch": 2.0199606493452453, "grad_norm": 1.2840473651885986, "learning_rate": 7.244399333189085e-05, "loss": 0.524479866027832, "step": 339820 }, { "epoch": 2.0200200914219137, "grad_norm": 1.0803433656692505, "learning_rate": 7.243833651411864e-05, "loss": 0.5559620380401611, "step": 339830 }, { "epoch": 2.020079533498582, "grad_norm": 1.4827948808670044, "learning_rate": 7.24326798760292e-05, "loss": 0.5225883483886719, "step": 339840 }, { "epoch": 2.0201389755752506, "grad_norm": 1.1929599046707153, "learning_rate": 7.242702341764954e-05, "loss": 0.4985652446746826, "step": 339850 }, { "epoch": 2.020198417651919, "grad_norm": 1.157333254814148, "learning_rate": 7.242136713900669e-05, "loss": 0.5097075462341308, "step": 339860 }, { "epoch": 2.0202578597285874, "grad_norm": 1.4206463098526, "learning_rate": 7.241571104012774e-05, "loss": 0.49080514907836914, "step": 339870 }, { "epoch": 2.020317301805256, "grad_norm": 1.364823818206787, "learning_rate": 7.24100551210398e-05, "loss": 0.44812636375427245, "step": 339880 }, { "epoch": 2.0203767438819242, "grad_norm": 1.3900868892669678, "learning_rate": 7.240439938176984e-05, "loss": 0.5057790756225586, "step": 339890 }, { "epoch": 2.0204361859585926, "grad_norm": 1.641231656074524, "learning_rate": 7.239874382234491e-05, "loss": 0.5398699283599854, "step": 339900 }, { "epoch": 2.020495628035261, "grad_norm": 1.374995231628418, "learning_rate": 7.239308844279214e-05, "loss": 0.5024226188659668, "step": 339910 }, { "epoch": 2.0205550701119295, "grad_norm": 1.1948164701461792, "learning_rate": 7.238743324313855e-05, "loss": 0.5079707145690918, "step": 339920 }, { "epoch": 2.020614512188598, "grad_norm": 1.4777333736419678, "learning_rate": 7.238177822341113e-05, "loss": 0.5264856338500976, "step": 339930 }, { "epoch": 2.0206739542652663, "grad_norm": 1.601874828338623, "learning_rate": 7.237612338363709e-05, "loss": 0.4735245704650879, "step": 339940 }, { "epoch": 2.0207333963419347, "grad_norm": 1.4596141576766968, "learning_rate": 7.237046872384332e-05, "loss": 0.4931753158569336, "step": 339950 }, { "epoch": 2.020792838418603, "grad_norm": 1.4504555463790894, "learning_rate": 7.236481424405695e-05, "loss": 0.5116307258605957, "step": 339960 }, { "epoch": 2.0208522804952715, "grad_norm": 1.4981144666671753, "learning_rate": 7.235915994430496e-05, "loss": 0.48464536666870117, "step": 339970 }, { "epoch": 2.02091172257194, "grad_norm": 1.4607654809951782, "learning_rate": 7.235350582461448e-05, "loss": 0.5354739189147949, "step": 339980 }, { "epoch": 2.0209711646486084, "grad_norm": 1.3685381412506104, "learning_rate": 7.234785188501251e-05, "loss": 0.5244486808776856, "step": 339990 }, { "epoch": 2.0210306067252763, "grad_norm": 1.1722867488861084, "learning_rate": 7.234219812552616e-05, "loss": 0.4894308567047119, "step": 340000 }, { "epoch": 2.0210900488019448, "grad_norm": 1.4044145345687866, "learning_rate": 7.233654454618239e-05, "loss": 0.48102617263793945, "step": 340010 }, { "epoch": 2.021149490878613, "grad_norm": 1.3232078552246094, "learning_rate": 7.233089114700831e-05, "loss": 0.4738008499145508, "step": 340020 }, { "epoch": 2.0212089329552816, "grad_norm": 1.5580745935440063, "learning_rate": 7.232523792803087e-05, "loss": 0.5007548332214355, "step": 340030 }, { "epoch": 2.02126837503195, "grad_norm": 1.427700400352478, "learning_rate": 7.231958488927724e-05, "loss": 0.5216132640838623, "step": 340040 }, { "epoch": 2.0213278171086184, "grad_norm": 1.2674391269683838, "learning_rate": 7.231393203077439e-05, "loss": 0.5334117889404297, "step": 340050 }, { "epoch": 2.021387259185287, "grad_norm": 1.1356011629104614, "learning_rate": 7.230827935254938e-05, "loss": 0.4698194980621338, "step": 340060 }, { "epoch": 2.0214467012619552, "grad_norm": 1.3641327619552612, "learning_rate": 7.230262685462923e-05, "loss": 0.5337330818176269, "step": 340070 }, { "epoch": 2.0215061433386237, "grad_norm": 1.3734692335128784, "learning_rate": 7.2296974537041e-05, "loss": 0.4784087181091309, "step": 340080 }, { "epoch": 2.021565585415292, "grad_norm": 1.25911545753479, "learning_rate": 7.229132239981174e-05, "loss": 0.46667070388793946, "step": 340090 }, { "epoch": 2.0216250274919605, "grad_norm": 1.340418815612793, "learning_rate": 7.228567044296841e-05, "loss": 0.5164803504943848, "step": 340100 }, { "epoch": 2.021684469568629, "grad_norm": 1.4535926580429077, "learning_rate": 7.228001866653816e-05, "loss": 0.47273836135864256, "step": 340110 }, { "epoch": 2.0217439116452973, "grad_norm": 1.3106896877288818, "learning_rate": 7.227436707054795e-05, "loss": 0.5155324935913086, "step": 340120 }, { "epoch": 2.0218033537219657, "grad_norm": 1.2275856733322144, "learning_rate": 7.226871565502487e-05, "loss": 0.5065106391906739, "step": 340130 }, { "epoch": 2.021862795798634, "grad_norm": 1.4450242519378662, "learning_rate": 7.226306441999589e-05, "loss": 0.5549726486206055, "step": 340140 }, { "epoch": 2.0219222378753026, "grad_norm": 1.2499418258666992, "learning_rate": 7.22574133654881e-05, "loss": 0.4762753486633301, "step": 340150 }, { "epoch": 2.021981679951971, "grad_norm": 1.3997761011123657, "learning_rate": 7.225176249152848e-05, "loss": 0.48054041862487795, "step": 340160 }, { "epoch": 2.0220411220286394, "grad_norm": 1.43839430809021, "learning_rate": 7.22461117981441e-05, "loss": 0.45937676429748536, "step": 340170 }, { "epoch": 2.0221005641053074, "grad_norm": 1.4808478355407715, "learning_rate": 7.2240461285362e-05, "loss": 0.5612300872802735, "step": 340180 }, { "epoch": 2.0221600061819758, "grad_norm": 1.12637197971344, "learning_rate": 7.223481095320921e-05, "loss": 0.4770638942718506, "step": 340190 }, { "epoch": 2.022219448258644, "grad_norm": 1.5835717916488647, "learning_rate": 7.222916080171271e-05, "loss": 0.4962925910949707, "step": 340200 }, { "epoch": 2.0222788903353126, "grad_norm": 1.2369571924209595, "learning_rate": 7.222351083089958e-05, "loss": 0.5403323173522949, "step": 340210 }, { "epoch": 2.022338332411981, "grad_norm": 1.4621247053146362, "learning_rate": 7.221786104079683e-05, "loss": 0.5264113426208497, "step": 340220 }, { "epoch": 2.0223977744886494, "grad_norm": 1.0862598419189453, "learning_rate": 7.221221143143146e-05, "loss": 0.5276544094085693, "step": 340230 }, { "epoch": 2.022457216565318, "grad_norm": 1.2926640510559082, "learning_rate": 7.220656200283054e-05, "loss": 0.5151692390441894, "step": 340240 }, { "epoch": 2.0225166586419863, "grad_norm": 1.1687865257263184, "learning_rate": 7.22009127550211e-05, "loss": 0.5150161266326905, "step": 340250 }, { "epoch": 2.0225761007186547, "grad_norm": 1.6355366706848145, "learning_rate": 7.219526368803009e-05, "loss": 0.49809608459472654, "step": 340260 }, { "epoch": 2.022635542795323, "grad_norm": 1.2818686962127686, "learning_rate": 7.218961480188462e-05, "loss": 0.5127294063568115, "step": 340270 }, { "epoch": 2.0226949848719915, "grad_norm": 1.382229208946228, "learning_rate": 7.218396609661167e-05, "loss": 0.49515867233276367, "step": 340280 }, { "epoch": 2.02275442694866, "grad_norm": 1.1478056907653809, "learning_rate": 7.217831757223823e-05, "loss": 0.5360673427581787, "step": 340290 }, { "epoch": 2.0228138690253283, "grad_norm": 1.125065803527832, "learning_rate": 7.21726692287914e-05, "loss": 0.5374106407165528, "step": 340300 }, { "epoch": 2.0228733111019968, "grad_norm": 1.1679942607879639, "learning_rate": 7.216702106629818e-05, "loss": 0.44384403228759767, "step": 340310 }, { "epoch": 2.022932753178665, "grad_norm": 1.4043785333633423, "learning_rate": 7.21613730847855e-05, "loss": 0.49257717132568357, "step": 340320 }, { "epoch": 2.0229921952553336, "grad_norm": 1.6595579385757446, "learning_rate": 7.21557252842805e-05, "loss": 0.5293215751647949, "step": 340330 }, { "epoch": 2.023051637332002, "grad_norm": 1.2651386260986328, "learning_rate": 7.215007766481012e-05, "loss": 0.4989017009735107, "step": 340340 }, { "epoch": 2.0231110794086704, "grad_norm": 1.337662935256958, "learning_rate": 7.21444302264014e-05, "loss": 0.49642333984375, "step": 340350 }, { "epoch": 2.023170521485339, "grad_norm": 1.5148829221725464, "learning_rate": 7.213878296908134e-05, "loss": 0.44926090240478517, "step": 340360 }, { "epoch": 2.023229963562007, "grad_norm": 1.313024878501892, "learning_rate": 7.213313589287702e-05, "loss": 0.5166889667510987, "step": 340370 }, { "epoch": 2.023289405638675, "grad_norm": 1.272755742073059, "learning_rate": 7.212748899781538e-05, "loss": 0.5268009185791016, "step": 340380 }, { "epoch": 2.0233488477153436, "grad_norm": 1.7671841382980347, "learning_rate": 7.212184228392343e-05, "loss": 0.5186020851135253, "step": 340390 }, { "epoch": 2.023408289792012, "grad_norm": 1.6329436302185059, "learning_rate": 7.211619575122821e-05, "loss": 0.49895401000976564, "step": 340400 }, { "epoch": 2.0234677318686805, "grad_norm": 1.6487526893615723, "learning_rate": 7.211054939975674e-05, "loss": 0.5550560474395752, "step": 340410 }, { "epoch": 2.023527173945349, "grad_norm": 1.7587083578109741, "learning_rate": 7.2104903229536e-05, "loss": 0.4947781562805176, "step": 340420 }, { "epoch": 2.0235866160220173, "grad_norm": 1.2371169328689575, "learning_rate": 7.209925724059307e-05, "loss": 0.5006631374359131, "step": 340430 }, { "epoch": 2.0236460580986857, "grad_norm": 1.2605276107788086, "learning_rate": 7.20936114329549e-05, "loss": 0.4727943420410156, "step": 340440 }, { "epoch": 2.023705500175354, "grad_norm": 1.8397151231765747, "learning_rate": 7.20879658066485e-05, "loss": 0.49691100120544435, "step": 340450 }, { "epoch": 2.0237649422520225, "grad_norm": 1.814008116722107, "learning_rate": 7.208232036170082e-05, "loss": 0.4987095832824707, "step": 340460 }, { "epoch": 2.023824384328691, "grad_norm": 1.4957956075668335, "learning_rate": 7.207667509813898e-05, "loss": 0.5190853118896485, "step": 340470 }, { "epoch": 2.0238838264053594, "grad_norm": 1.4263932704925537, "learning_rate": 7.207103001598992e-05, "loss": 0.4926289081573486, "step": 340480 }, { "epoch": 2.0239432684820278, "grad_norm": 1.2327916622161865, "learning_rate": 7.206538511528067e-05, "loss": 0.47093782424926756, "step": 340490 }, { "epoch": 2.024002710558696, "grad_norm": 1.2536827325820923, "learning_rate": 7.205974039603822e-05, "loss": 0.5336641788482666, "step": 340500 }, { "epoch": 2.0240621526353646, "grad_norm": 1.1860625743865967, "learning_rate": 7.205409585828957e-05, "loss": 0.5152348518371582, "step": 340510 }, { "epoch": 2.024121594712033, "grad_norm": 1.2824020385742188, "learning_rate": 7.20484515020617e-05, "loss": 0.4847285270690918, "step": 340520 }, { "epoch": 2.0241810367887014, "grad_norm": 1.5495527982711792, "learning_rate": 7.204280732738165e-05, "loss": 0.4629453182220459, "step": 340530 }, { "epoch": 2.02424047886537, "grad_norm": 1.4706741571426392, "learning_rate": 7.203716333427642e-05, "loss": 0.570813798904419, "step": 340540 }, { "epoch": 2.024299920942038, "grad_norm": 1.1210325956344604, "learning_rate": 7.203151952277299e-05, "loss": 0.5080118179321289, "step": 340550 }, { "epoch": 2.0243593630187062, "grad_norm": 1.4118633270263672, "learning_rate": 7.202587589289835e-05, "loss": 0.46004428863525393, "step": 340560 }, { "epoch": 2.0244188050953746, "grad_norm": 1.797934651374817, "learning_rate": 7.202023244467954e-05, "loss": 0.5028881072998047, "step": 340570 }, { "epoch": 2.024478247172043, "grad_norm": 1.4019495248794556, "learning_rate": 7.20145891781435e-05, "loss": 0.49018087387084963, "step": 340580 }, { "epoch": 2.0245376892487115, "grad_norm": 1.4836127758026123, "learning_rate": 7.200894609331723e-05, "loss": 0.5637588500976562, "step": 340590 }, { "epoch": 2.02459713132538, "grad_norm": 1.1088390350341797, "learning_rate": 7.200330319022776e-05, "loss": 0.500669002532959, "step": 340600 }, { "epoch": 2.0246565734020483, "grad_norm": 1.0741908550262451, "learning_rate": 7.199766046890209e-05, "loss": 0.47755002975463867, "step": 340610 }, { "epoch": 2.0247160154787167, "grad_norm": 1.3973902463912964, "learning_rate": 7.19920179293672e-05, "loss": 0.5113675594329834, "step": 340620 }, { "epoch": 2.024775457555385, "grad_norm": 1.434523344039917, "learning_rate": 7.198637557165007e-05, "loss": 0.5720248699188233, "step": 340630 }, { "epoch": 2.0248348996320535, "grad_norm": 1.0917389392852783, "learning_rate": 7.198073339577769e-05, "loss": 0.49976887702941897, "step": 340640 }, { "epoch": 2.024894341708722, "grad_norm": 1.1600435972213745, "learning_rate": 7.1975091401777e-05, "loss": 0.48276662826538086, "step": 340650 }, { "epoch": 2.0249537837853904, "grad_norm": 1.3224899768829346, "learning_rate": 7.196944958967512e-05, "loss": 0.4711151599884033, "step": 340660 }, { "epoch": 2.025013225862059, "grad_norm": 1.6936718225479126, "learning_rate": 7.196380795949895e-05, "loss": 0.5382464408874512, "step": 340670 }, { "epoch": 2.025072667938727, "grad_norm": 1.2725396156311035, "learning_rate": 7.195816651127548e-05, "loss": 0.5306860923767089, "step": 340680 }, { "epoch": 2.0251321100153956, "grad_norm": 1.4560236930847168, "learning_rate": 7.19525252450317e-05, "loss": 0.5022439956665039, "step": 340690 }, { "epoch": 2.025191552092064, "grad_norm": 1.6897367238998413, "learning_rate": 7.194688416079465e-05, "loss": 0.5118522644042969, "step": 340700 }, { "epoch": 2.0252509941687324, "grad_norm": 1.1760635375976562, "learning_rate": 7.194124325859124e-05, "loss": 0.5261575698852539, "step": 340710 }, { "epoch": 2.025310436245401, "grad_norm": 0.9298125505447388, "learning_rate": 7.193560253844844e-05, "loss": 0.4957400321960449, "step": 340720 }, { "epoch": 2.0253698783220693, "grad_norm": 1.5416678190231323, "learning_rate": 7.192996200039335e-05, "loss": 0.5207535743713378, "step": 340730 }, { "epoch": 2.0254293203987372, "grad_norm": 1.827988862991333, "learning_rate": 7.192432164445284e-05, "loss": 0.5580965995788574, "step": 340740 }, { "epoch": 2.0254887624754057, "grad_norm": 1.0462898015975952, "learning_rate": 7.191868147065395e-05, "loss": 0.4850670337677002, "step": 340750 }, { "epoch": 2.025548204552074, "grad_norm": 1.3336127996444702, "learning_rate": 7.191304147902364e-05, "loss": 0.5042324066162109, "step": 340760 }, { "epoch": 2.0256076466287425, "grad_norm": 1.0657280683517456, "learning_rate": 7.19074016695889e-05, "loss": 0.5033892154693603, "step": 340770 }, { "epoch": 2.025667088705411, "grad_norm": 1.1941044330596924, "learning_rate": 7.190176204237666e-05, "loss": 0.5540282249450683, "step": 340780 }, { "epoch": 2.0257265307820793, "grad_norm": 1.6249531507492065, "learning_rate": 7.189612259741398e-05, "loss": 0.5112442016601563, "step": 340790 }, { "epoch": 2.0257859728587477, "grad_norm": 1.6256626844406128, "learning_rate": 7.189048333472778e-05, "loss": 0.49144730567932127, "step": 340800 }, { "epoch": 2.025845414935416, "grad_norm": 1.2466795444488525, "learning_rate": 7.188484425434512e-05, "loss": 0.4925539970397949, "step": 340810 }, { "epoch": 2.0259048570120846, "grad_norm": 1.4049190282821655, "learning_rate": 7.18792053562928e-05, "loss": 0.5273454666137696, "step": 340820 }, { "epoch": 2.025964299088753, "grad_norm": 1.4831290245056152, "learning_rate": 7.187356664059796e-05, "loss": 0.5258149147033692, "step": 340830 }, { "epoch": 2.0260237411654214, "grad_norm": 1.3853484392166138, "learning_rate": 7.186792810728752e-05, "loss": 0.5622867584228516, "step": 340840 }, { "epoch": 2.02608318324209, "grad_norm": 0.9391028881072998, "learning_rate": 7.186228975638842e-05, "loss": 0.48555550575256345, "step": 340850 }, { "epoch": 2.026142625318758, "grad_norm": 1.2793058156967163, "learning_rate": 7.185665158792771e-05, "loss": 0.5033078193664551, "step": 340860 }, { "epoch": 2.0262020673954266, "grad_norm": 1.1991325616836548, "learning_rate": 7.185101360193231e-05, "loss": 0.5302829742431641, "step": 340870 }, { "epoch": 2.026261509472095, "grad_norm": 1.014574646949768, "learning_rate": 7.184537579842913e-05, "loss": 0.5144224643707276, "step": 340880 }, { "epoch": 2.0263209515487635, "grad_norm": 1.4922475814819336, "learning_rate": 7.183973817744525e-05, "loss": 0.5359861850738525, "step": 340890 }, { "epoch": 2.026380393625432, "grad_norm": 1.487585425376892, "learning_rate": 7.183410073900758e-05, "loss": 0.5100454330444336, "step": 340900 }, { "epoch": 2.0264398357021003, "grad_norm": 1.4034258127212524, "learning_rate": 7.182846348314308e-05, "loss": 0.49431819915771485, "step": 340910 }, { "epoch": 2.0264992777787683, "grad_norm": 1.4178402423858643, "learning_rate": 7.18228264098788e-05, "loss": 0.5563318252563476, "step": 340920 }, { "epoch": 2.0265587198554367, "grad_norm": 1.6122913360595703, "learning_rate": 7.181718951924162e-05, "loss": 0.5379368305206299, "step": 340930 }, { "epoch": 2.026618161932105, "grad_norm": 1.1405792236328125, "learning_rate": 7.181155281125851e-05, "loss": 0.45515899658203124, "step": 340940 }, { "epoch": 2.0266776040087735, "grad_norm": 1.4431244134902954, "learning_rate": 7.180591628595643e-05, "loss": 0.5279587745666504, "step": 340950 }, { "epoch": 2.026737046085442, "grad_norm": 1.4823676347732544, "learning_rate": 7.180027994336238e-05, "loss": 0.469577693939209, "step": 340960 }, { "epoch": 2.0267964881621103, "grad_norm": 1.3274368047714233, "learning_rate": 7.179464378350331e-05, "loss": 0.49862470626831057, "step": 340970 }, { "epoch": 2.0268559302387787, "grad_norm": 1.5548819303512573, "learning_rate": 7.178900780640621e-05, "loss": 0.5037178516387939, "step": 340980 }, { "epoch": 2.026915372315447, "grad_norm": 1.4511326551437378, "learning_rate": 7.178337201209797e-05, "loss": 0.49727492332458495, "step": 340990 }, { "epoch": 2.0269748143921156, "grad_norm": 1.5442218780517578, "learning_rate": 7.177773640060562e-05, "loss": 0.5339833259582519, "step": 341000 }, { "epoch": 2.027034256468784, "grad_norm": 1.3975259065628052, "learning_rate": 7.177210097195602e-05, "loss": 0.5000022411346435, "step": 341010 }, { "epoch": 2.0270936985454524, "grad_norm": 1.4379520416259766, "learning_rate": 7.176646572617624e-05, "loss": 0.48940334320068357, "step": 341020 }, { "epoch": 2.027153140622121, "grad_norm": 1.3028621673583984, "learning_rate": 7.176083066329323e-05, "loss": 0.5356513500213623, "step": 341030 }, { "epoch": 2.0272125826987892, "grad_norm": 1.2705397605895996, "learning_rate": 7.175519578333385e-05, "loss": 0.511649227142334, "step": 341040 }, { "epoch": 2.0272720247754576, "grad_norm": 1.1405229568481445, "learning_rate": 7.174956108632515e-05, "loss": 0.5204007625579834, "step": 341050 }, { "epoch": 2.027331466852126, "grad_norm": 0.9889219403266907, "learning_rate": 7.174392657229405e-05, "loss": 0.5035345077514648, "step": 341060 }, { "epoch": 2.0273909089287945, "grad_norm": 1.4521881341934204, "learning_rate": 7.173829224126749e-05, "loss": 0.5179673671722412, "step": 341070 }, { "epoch": 2.027450351005463, "grad_norm": 1.6414554119110107, "learning_rate": 7.173265809327243e-05, "loss": 0.5305670261383056, "step": 341080 }, { "epoch": 2.0275097930821313, "grad_norm": 1.2326372861862183, "learning_rate": 7.172702412833583e-05, "loss": 0.5395675659179687, "step": 341090 }, { "epoch": 2.0275692351587997, "grad_norm": 1.5711183547973633, "learning_rate": 7.172139034648464e-05, "loss": 0.5248713016510009, "step": 341100 }, { "epoch": 2.0276286772354677, "grad_norm": 1.4494571685791016, "learning_rate": 7.171575674774582e-05, "loss": 0.555274486541748, "step": 341110 }, { "epoch": 2.027688119312136, "grad_norm": 2.108902931213379, "learning_rate": 7.171012333214631e-05, "loss": 0.5044778347015381, "step": 341120 }, { "epoch": 2.0277475613888045, "grad_norm": 1.2746622562408447, "learning_rate": 7.170449009971307e-05, "loss": 0.5207865715026856, "step": 341130 }, { "epoch": 2.027807003465473, "grad_norm": 1.2577672004699707, "learning_rate": 7.169885705047297e-05, "loss": 0.4965547561645508, "step": 341140 }, { "epoch": 2.0278664455421413, "grad_norm": 1.2002556324005127, "learning_rate": 7.169322418445307e-05, "loss": 0.5187758445739746, "step": 341150 }, { "epoch": 2.0279258876188098, "grad_norm": 1.5717766284942627, "learning_rate": 7.168759150168027e-05, "loss": 0.5201996803283692, "step": 341160 }, { "epoch": 2.027985329695478, "grad_norm": 1.4306809902191162, "learning_rate": 7.16819590021815e-05, "loss": 0.5148849964141846, "step": 341170 }, { "epoch": 2.0280447717721466, "grad_norm": 1.5610671043395996, "learning_rate": 7.167632668598374e-05, "loss": 0.47363967895507814, "step": 341180 }, { "epoch": 2.028104213848815, "grad_norm": 1.3049083948135376, "learning_rate": 7.167069455311389e-05, "loss": 0.4937565326690674, "step": 341190 }, { "epoch": 2.0281636559254834, "grad_norm": 0.974528968334198, "learning_rate": 7.166506260359891e-05, "loss": 0.45642800331115724, "step": 341200 }, { "epoch": 2.028223098002152, "grad_norm": 1.144926905632019, "learning_rate": 7.165943083746572e-05, "loss": 0.48188128471374514, "step": 341210 }, { "epoch": 2.0282825400788203, "grad_norm": 1.2952487468719482, "learning_rate": 7.165379925474129e-05, "loss": 0.49438161849975587, "step": 341220 }, { "epoch": 2.0283419821554887, "grad_norm": 1.3291093111038208, "learning_rate": 7.164816785545256e-05, "loss": 0.5302264213562011, "step": 341230 }, { "epoch": 2.028401424232157, "grad_norm": 1.378535509109497, "learning_rate": 7.16425366396265e-05, "loss": 0.5031826019287109, "step": 341240 }, { "epoch": 2.0284608663088255, "grad_norm": 1.3463647365570068, "learning_rate": 7.163690560728997e-05, "loss": 0.5139377593994141, "step": 341250 }, { "epoch": 2.028520308385494, "grad_norm": 1.5411726236343384, "learning_rate": 7.163127475846996e-05, "loss": 0.5329289913177491, "step": 341260 }, { "epoch": 2.0285797504621623, "grad_norm": 1.216032862663269, "learning_rate": 7.162564409319336e-05, "loss": 0.48290243148803713, "step": 341270 }, { "epoch": 2.0286391925388307, "grad_norm": 1.5583869218826294, "learning_rate": 7.162001361148716e-05, "loss": 0.4883068084716797, "step": 341280 }, { "epoch": 2.0286986346154987, "grad_norm": 1.3896517753601074, "learning_rate": 7.161438331337828e-05, "loss": 0.5133697509765625, "step": 341290 }, { "epoch": 2.028758076692167, "grad_norm": 1.2984880208969116, "learning_rate": 7.160875319889369e-05, "loss": 0.5213478088378907, "step": 341300 }, { "epoch": 2.0288175187688355, "grad_norm": 1.3589720726013184, "learning_rate": 7.16031232680602e-05, "loss": 0.5633797645568848, "step": 341310 }, { "epoch": 2.028876960845504, "grad_norm": 1.4805257320404053, "learning_rate": 7.159749352090486e-05, "loss": 0.5299167633056641, "step": 341320 }, { "epoch": 2.0289364029221724, "grad_norm": 1.8126555681228638, "learning_rate": 7.159186395745457e-05, "loss": 0.5377131938934326, "step": 341330 }, { "epoch": 2.028995844998841, "grad_norm": 1.289429783821106, "learning_rate": 7.158623457773618e-05, "loss": 0.5505998134613037, "step": 341340 }, { "epoch": 2.029055287075509, "grad_norm": 1.2560408115386963, "learning_rate": 7.158060538177676e-05, "loss": 0.46868457794189455, "step": 341350 }, { "epoch": 2.0291147291521776, "grad_norm": 1.6511547565460205, "learning_rate": 7.157497636960317e-05, "loss": 0.586445951461792, "step": 341360 }, { "epoch": 2.029174171228846, "grad_norm": 1.933294415473938, "learning_rate": 7.156934754124229e-05, "loss": 0.4965981006622314, "step": 341370 }, { "epoch": 2.0292336133055144, "grad_norm": 1.1568773984909058, "learning_rate": 7.156371889672113e-05, "loss": 0.4997738838195801, "step": 341380 }, { "epoch": 2.029293055382183, "grad_norm": 1.2093168497085571, "learning_rate": 7.155809043606659e-05, "loss": 0.4621185302734375, "step": 341390 }, { "epoch": 2.0293524974588513, "grad_norm": 1.369809865951538, "learning_rate": 7.155246215930552e-05, "loss": 0.5125473499298095, "step": 341400 }, { "epoch": 2.0294119395355197, "grad_norm": 1.4514305591583252, "learning_rate": 7.154683406646494e-05, "loss": 0.5197424411773681, "step": 341410 }, { "epoch": 2.029471381612188, "grad_norm": 1.5288100242614746, "learning_rate": 7.154120615757178e-05, "loss": 0.517891788482666, "step": 341420 }, { "epoch": 2.0295308236888565, "grad_norm": 1.3402442932128906, "learning_rate": 7.153557843265289e-05, "loss": 0.5223531723022461, "step": 341430 }, { "epoch": 2.029590265765525, "grad_norm": 1.1687443256378174, "learning_rate": 7.152995089173517e-05, "loss": 0.4716193199157715, "step": 341440 }, { "epoch": 2.0296497078421933, "grad_norm": 1.2286838293075562, "learning_rate": 7.152432353484566e-05, "loss": 0.544669246673584, "step": 341450 }, { "epoch": 2.0297091499188618, "grad_norm": 1.5021275281906128, "learning_rate": 7.15186963620112e-05, "loss": 0.5063080310821533, "step": 341460 }, { "epoch": 2.02976859199553, "grad_norm": 1.0797479152679443, "learning_rate": 7.151306937325867e-05, "loss": 0.48009233474731444, "step": 341470 }, { "epoch": 2.029828034072198, "grad_norm": 1.5334049463272095, "learning_rate": 7.150744256861514e-05, "loss": 0.554628849029541, "step": 341480 }, { "epoch": 2.0298874761488666, "grad_norm": 1.2406280040740967, "learning_rate": 7.150181594810737e-05, "loss": 0.47023763656616213, "step": 341490 }, { "epoch": 2.029946918225535, "grad_norm": 1.5061410665512085, "learning_rate": 7.149618951176229e-05, "loss": 0.5331998348236084, "step": 341500 }, { "epoch": 2.0300063603022034, "grad_norm": 1.2125279903411865, "learning_rate": 7.14905632596069e-05, "loss": 0.5039553642272949, "step": 341510 }, { "epoch": 2.030065802378872, "grad_norm": 1.4579370021820068, "learning_rate": 7.148493719166807e-05, "loss": 0.49757704734802244, "step": 341520 }, { "epoch": 2.03012524445554, "grad_norm": 1.6357460021972656, "learning_rate": 7.147931130797272e-05, "loss": 0.5171574115753174, "step": 341530 }, { "epoch": 2.0301846865322086, "grad_norm": 1.5379836559295654, "learning_rate": 7.147368560854774e-05, "loss": 0.5197589874267579, "step": 341540 }, { "epoch": 2.030244128608877, "grad_norm": 1.6894354820251465, "learning_rate": 7.146806009342007e-05, "loss": 0.5030760765075684, "step": 341550 }, { "epoch": 2.0303035706855455, "grad_norm": 1.2562203407287598, "learning_rate": 7.14624347626166e-05, "loss": 0.5430601119995118, "step": 341560 }, { "epoch": 2.030363012762214, "grad_norm": 1.4584964513778687, "learning_rate": 7.145680961616423e-05, "loss": 0.5767767906188965, "step": 341570 }, { "epoch": 2.0304224548388823, "grad_norm": 1.5621867179870605, "learning_rate": 7.145118465408992e-05, "loss": 0.45222954750061034, "step": 341580 }, { "epoch": 2.0304818969155507, "grad_norm": 1.4143635034561157, "learning_rate": 7.144555987642053e-05, "loss": 0.48313155174255373, "step": 341590 }, { "epoch": 2.030541338992219, "grad_norm": 1.4818404912948608, "learning_rate": 7.143993528318298e-05, "loss": 0.5274275779724121, "step": 341600 }, { "epoch": 2.0306007810688875, "grad_norm": 1.3544172048568726, "learning_rate": 7.143431087440418e-05, "loss": 0.5129153728485107, "step": 341610 }, { "epoch": 2.030660223145556, "grad_norm": 1.4975653886795044, "learning_rate": 7.142868665011105e-05, "loss": 0.4570178508758545, "step": 341620 }, { "epoch": 2.0307196652222244, "grad_norm": 1.478163719177246, "learning_rate": 7.142306261033042e-05, "loss": 0.4800689220428467, "step": 341630 }, { "epoch": 2.0307791072988928, "grad_norm": 1.4209823608398438, "learning_rate": 7.14174387550893e-05, "loss": 0.4816927909851074, "step": 341640 }, { "epoch": 2.030838549375561, "grad_norm": 1.5801527500152588, "learning_rate": 7.141181508441452e-05, "loss": 0.5291291236877441, "step": 341650 }, { "epoch": 2.030897991452229, "grad_norm": 1.3738747835159302, "learning_rate": 7.140619159833304e-05, "loss": 0.5197910308837891, "step": 341660 }, { "epoch": 2.0309574335288976, "grad_norm": 1.3581663370132446, "learning_rate": 7.140056829687172e-05, "loss": 0.5486098289489746, "step": 341670 }, { "epoch": 2.031016875605566, "grad_norm": 1.2859801054000854, "learning_rate": 7.139494518005745e-05, "loss": 0.45545406341552735, "step": 341680 }, { "epoch": 2.0310763176822344, "grad_norm": 1.7330068349838257, "learning_rate": 7.138932224791717e-05, "loss": 0.5263640403747558, "step": 341690 }, { "epoch": 2.031135759758903, "grad_norm": 1.409026026725769, "learning_rate": 7.13836995004777e-05, "loss": 0.5283118724822998, "step": 341700 }, { "epoch": 2.0311952018355712, "grad_norm": 1.5253303050994873, "learning_rate": 7.137807693776602e-05, "loss": 0.4989304542541504, "step": 341710 }, { "epoch": 2.0312546439122396, "grad_norm": 1.2867780923843384, "learning_rate": 7.1372454559809e-05, "loss": 0.4744093894958496, "step": 341720 }, { "epoch": 2.031314085988908, "grad_norm": 1.9590495824813843, "learning_rate": 7.136683236663358e-05, "loss": 0.5273666381835938, "step": 341730 }, { "epoch": 2.0313735280655765, "grad_norm": 1.3829572200775146, "learning_rate": 7.136121035826656e-05, "loss": 0.517051362991333, "step": 341740 }, { "epoch": 2.031432970142245, "grad_norm": 1.44865882396698, "learning_rate": 7.13555885347349e-05, "loss": 0.5155418395996094, "step": 341750 }, { "epoch": 2.0314924122189133, "grad_norm": 1.3327504396438599, "learning_rate": 7.134996689606543e-05, "loss": 0.550789737701416, "step": 341760 }, { "epoch": 2.0315518542955817, "grad_norm": 1.2239845991134644, "learning_rate": 7.134434544228511e-05, "loss": 0.4970663547515869, "step": 341770 }, { "epoch": 2.03161129637225, "grad_norm": 1.1578729152679443, "learning_rate": 7.133872417342083e-05, "loss": 0.5211627960205079, "step": 341780 }, { "epoch": 2.0316707384489185, "grad_norm": 1.9405193328857422, "learning_rate": 7.133310308949949e-05, "loss": 0.46517462730407716, "step": 341790 }, { "epoch": 2.031730180525587, "grad_norm": 1.5729455947875977, "learning_rate": 7.132748219054788e-05, "loss": 0.5124190330505372, "step": 341800 }, { "epoch": 2.0317896226022554, "grad_norm": 1.5210771560668945, "learning_rate": 7.132186147659299e-05, "loss": 0.49455647468566893, "step": 341810 }, { "epoch": 2.031849064678924, "grad_norm": 0.721842348575592, "learning_rate": 7.131624094766168e-05, "loss": 0.5131117820739746, "step": 341820 }, { "epoch": 2.031908506755592, "grad_norm": 1.3151969909667969, "learning_rate": 7.131062060378077e-05, "loss": 0.4884998321533203, "step": 341830 }, { "epoch": 2.0319679488322606, "grad_norm": 1.387929081916809, "learning_rate": 7.130500044497728e-05, "loss": 0.4730836868286133, "step": 341840 }, { "epoch": 2.0320273909089286, "grad_norm": 1.2944077253341675, "learning_rate": 7.129938047127804e-05, "loss": 0.5053685665130615, "step": 341850 }, { "epoch": 2.032086832985597, "grad_norm": 1.445970058441162, "learning_rate": 7.129376068270985e-05, "loss": 0.4894918441772461, "step": 341860 }, { "epoch": 2.0321462750622654, "grad_norm": 1.3407022953033447, "learning_rate": 7.128814107929969e-05, "loss": 0.5046669006347656, "step": 341870 }, { "epoch": 2.032205717138934, "grad_norm": 1.3356977701187134, "learning_rate": 7.12825216610744e-05, "loss": 0.4696627140045166, "step": 341880 }, { "epoch": 2.0322651592156022, "grad_norm": 1.2822531461715698, "learning_rate": 7.127690242806087e-05, "loss": 0.5596587657928467, "step": 341890 }, { "epoch": 2.0323246012922707, "grad_norm": 1.4668775796890259, "learning_rate": 7.1271283380286e-05, "loss": 0.5219779968261719, "step": 341900 }, { "epoch": 2.032384043368939, "grad_norm": 1.182692527770996, "learning_rate": 7.126566451777669e-05, "loss": 0.5130405426025391, "step": 341910 }, { "epoch": 2.0324434854456075, "grad_norm": 1.2213770151138306, "learning_rate": 7.126004584055975e-05, "loss": 0.5113118171691895, "step": 341920 }, { "epoch": 2.032502927522276, "grad_norm": 1.919138789176941, "learning_rate": 7.125442734866205e-05, "loss": 0.4998666763305664, "step": 341930 }, { "epoch": 2.0325623695989443, "grad_norm": 1.2919795513153076, "learning_rate": 7.124880904211053e-05, "loss": 0.5202396392822266, "step": 341940 }, { "epoch": 2.0326218116756127, "grad_norm": 1.272895097732544, "learning_rate": 7.124319092093205e-05, "loss": 0.5125222206115723, "step": 341950 }, { "epoch": 2.032681253752281, "grad_norm": 1.506033182144165, "learning_rate": 7.123757298515346e-05, "loss": 0.47844362258911133, "step": 341960 }, { "epoch": 2.0327406958289496, "grad_norm": 1.1907086372375488, "learning_rate": 7.123195523480172e-05, "loss": 0.5115309715270996, "step": 341970 }, { "epoch": 2.032800137905618, "grad_norm": 1.3966559171676636, "learning_rate": 7.12263376699036e-05, "loss": 0.4932561874389648, "step": 341980 }, { "epoch": 2.0328595799822864, "grad_norm": 1.2706533670425415, "learning_rate": 7.122072029048596e-05, "loss": 0.4685549736022949, "step": 341990 }, { "epoch": 2.032919022058955, "grad_norm": 1.6190502643585205, "learning_rate": 7.121510309657578e-05, "loss": 0.5467666625976563, "step": 342000 }, { "epoch": 2.032978464135623, "grad_norm": 1.6017565727233887, "learning_rate": 7.120948608819986e-05, "loss": 0.5033496856689453, "step": 342010 }, { "epoch": 2.0330379062122916, "grad_norm": 1.3683193922042847, "learning_rate": 7.120386926538504e-05, "loss": 0.5176537036895752, "step": 342020 }, { "epoch": 2.0330973482889596, "grad_norm": 1.1830894947052002, "learning_rate": 7.11982526281583e-05, "loss": 0.5085922241210937, "step": 342030 }, { "epoch": 2.033156790365628, "grad_norm": 1.1611523628234863, "learning_rate": 7.119263617654641e-05, "loss": 0.4594565391540527, "step": 342040 }, { "epoch": 2.0332162324422964, "grad_norm": 1.736646056175232, "learning_rate": 7.118701991057626e-05, "loss": 0.5124251842498779, "step": 342050 }, { "epoch": 2.033275674518965, "grad_norm": 0.6815798878669739, "learning_rate": 7.118140383027469e-05, "loss": 0.49439082145690916, "step": 342060 }, { "epoch": 2.0333351165956333, "grad_norm": 1.2425471544265747, "learning_rate": 7.117578793566864e-05, "loss": 0.5039668083190918, "step": 342070 }, { "epoch": 2.0333945586723017, "grad_norm": 1.837854266166687, "learning_rate": 7.117017222678493e-05, "loss": 0.5573141574859619, "step": 342080 }, { "epoch": 2.03345400074897, "grad_norm": 1.4215941429138184, "learning_rate": 7.116455670365043e-05, "loss": 0.493726110458374, "step": 342090 }, { "epoch": 2.0335134428256385, "grad_norm": 1.633538842201233, "learning_rate": 7.1158941366292e-05, "loss": 0.5375095844268799, "step": 342100 }, { "epoch": 2.033572884902307, "grad_norm": 1.0334267616271973, "learning_rate": 7.11533262147365e-05, "loss": 0.46814737319946287, "step": 342110 }, { "epoch": 2.0336323269789753, "grad_norm": 1.6541588306427002, "learning_rate": 7.114771124901074e-05, "loss": 0.4994958400726318, "step": 342120 }, { "epoch": 2.0336917690556437, "grad_norm": 1.4664613008499146, "learning_rate": 7.11420964691417e-05, "loss": 0.5509331703186036, "step": 342130 }, { "epoch": 2.033751211132312, "grad_norm": 1.3104877471923828, "learning_rate": 7.113648187515614e-05, "loss": 0.524156904220581, "step": 342140 }, { "epoch": 2.0338106532089806, "grad_norm": 1.2505152225494385, "learning_rate": 7.113086746708097e-05, "loss": 0.5310561656951904, "step": 342150 }, { "epoch": 2.033870095285649, "grad_norm": 1.5581551790237427, "learning_rate": 7.1125253244943e-05, "loss": 0.5273036003112793, "step": 342160 }, { "epoch": 2.0339295373623174, "grad_norm": 1.3542041778564453, "learning_rate": 7.111963920876913e-05, "loss": 0.49491324424743655, "step": 342170 }, { "epoch": 2.033988979438986, "grad_norm": 1.144593358039856, "learning_rate": 7.111402535858623e-05, "loss": 0.5030679702758789, "step": 342180 }, { "epoch": 2.0340484215156542, "grad_norm": 1.519370675086975, "learning_rate": 7.110841169442104e-05, "loss": 0.549371337890625, "step": 342190 }, { "epoch": 2.0341078635923227, "grad_norm": 1.1570931673049927, "learning_rate": 7.110279821630056e-05, "loss": 0.5330736637115479, "step": 342200 }, { "epoch": 2.034167305668991, "grad_norm": 1.6425172090530396, "learning_rate": 7.109718492425157e-05, "loss": 0.5673116683959961, "step": 342210 }, { "epoch": 2.034226747745659, "grad_norm": 1.3927891254425049, "learning_rate": 7.109157181830095e-05, "loss": 0.5169822692871093, "step": 342220 }, { "epoch": 2.0342861898223275, "grad_norm": 1.5276728868484497, "learning_rate": 7.108595889847553e-05, "loss": 0.5164856433868408, "step": 342230 }, { "epoch": 2.034345631898996, "grad_norm": 1.2734808921813965, "learning_rate": 7.108034616480215e-05, "loss": 0.4815535545349121, "step": 342240 }, { "epoch": 2.0344050739756643, "grad_norm": 1.1013740301132202, "learning_rate": 7.107473361730765e-05, "loss": 0.4728252410888672, "step": 342250 }, { "epoch": 2.0344645160523327, "grad_norm": 1.3820807933807373, "learning_rate": 7.106912125601895e-05, "loss": 0.4789145469665527, "step": 342260 }, { "epoch": 2.034523958129001, "grad_norm": 1.6610432863235474, "learning_rate": 7.106350908096284e-05, "loss": 0.49611492156982423, "step": 342270 }, { "epoch": 2.0345834002056695, "grad_norm": 1.36044442653656, "learning_rate": 7.105789709216621e-05, "loss": 0.5307823657989502, "step": 342280 }, { "epoch": 2.034642842282338, "grad_norm": 2.038682699203491, "learning_rate": 7.10522852896558e-05, "loss": 0.5388138771057129, "step": 342290 }, { "epoch": 2.0347022843590064, "grad_norm": 1.4891105890274048, "learning_rate": 7.104667367345858e-05, "loss": 0.45743460655212403, "step": 342300 }, { "epoch": 2.0347617264356748, "grad_norm": 1.3837740421295166, "learning_rate": 7.104106224360135e-05, "loss": 0.48694143295288084, "step": 342310 }, { "epoch": 2.034821168512343, "grad_norm": 1.438511610031128, "learning_rate": 7.103545100011089e-05, "loss": 0.5704217910766601, "step": 342320 }, { "epoch": 2.0348806105890116, "grad_norm": 1.8016796112060547, "learning_rate": 7.102983994301414e-05, "loss": 0.497922945022583, "step": 342330 }, { "epoch": 2.03494005266568, "grad_norm": 1.2968004941940308, "learning_rate": 7.102422907233792e-05, "loss": 0.49759554862976074, "step": 342340 }, { "epoch": 2.0349994947423484, "grad_norm": 2.0134692192077637, "learning_rate": 7.101861838810899e-05, "loss": 0.5203448295593261, "step": 342350 }, { "epoch": 2.035058936819017, "grad_norm": 1.1598355770111084, "learning_rate": 7.10130078903543e-05, "loss": 0.5257599353790283, "step": 342360 }, { "epoch": 2.0351183788956853, "grad_norm": 1.3060559034347534, "learning_rate": 7.100739757910064e-05, "loss": 0.5235584735870361, "step": 342370 }, { "epoch": 2.0351778209723537, "grad_norm": 1.2414146661758423, "learning_rate": 7.10017874543748e-05, "loss": 0.45981440544128416, "step": 342380 }, { "epoch": 2.035237263049022, "grad_norm": 1.5557781457901, "learning_rate": 7.099617751620369e-05, "loss": 0.5842451095581055, "step": 342390 }, { "epoch": 2.03529670512569, "grad_norm": 1.050969123840332, "learning_rate": 7.09905677646142e-05, "loss": 0.49451069831848143, "step": 342400 }, { "epoch": 2.0353561472023585, "grad_norm": 1.5340633392333984, "learning_rate": 7.0984958199633e-05, "loss": 0.5563621520996094, "step": 342410 }, { "epoch": 2.035415589279027, "grad_norm": 1.5273075103759766, "learning_rate": 7.097934882128699e-05, "loss": 0.5332061767578125, "step": 342420 }, { "epoch": 2.0354750313556953, "grad_norm": 1.5332374572753906, "learning_rate": 7.097373962960305e-05, "loss": 0.5257997512817383, "step": 342430 }, { "epoch": 2.0355344734323637, "grad_norm": 1.3220993280410767, "learning_rate": 7.096813062460802e-05, "loss": 0.5071331977844238, "step": 342440 }, { "epoch": 2.035593915509032, "grad_norm": 1.60194993019104, "learning_rate": 7.096252180632863e-05, "loss": 0.5219295501708985, "step": 342450 }, { "epoch": 2.0356533575857005, "grad_norm": 1.2207443714141846, "learning_rate": 7.095691317479185e-05, "loss": 0.46692590713500975, "step": 342460 }, { "epoch": 2.035712799662369, "grad_norm": 1.2487549781799316, "learning_rate": 7.095130473002441e-05, "loss": 0.5071118831634521, "step": 342470 }, { "epoch": 2.0357722417390374, "grad_norm": 1.4162157773971558, "learning_rate": 7.094569647205312e-05, "loss": 0.5374801635742188, "step": 342480 }, { "epoch": 2.035831683815706, "grad_norm": 1.528140902519226, "learning_rate": 7.094008840090492e-05, "loss": 0.4848529815673828, "step": 342490 }, { "epoch": 2.035891125892374, "grad_norm": 1.521636962890625, "learning_rate": 7.093448051660653e-05, "loss": 0.518856143951416, "step": 342500 }, { "epoch": 2.0359505679690426, "grad_norm": 1.3014029264450073, "learning_rate": 7.092887281918486e-05, "loss": 0.46331086158752444, "step": 342510 }, { "epoch": 2.036010010045711, "grad_norm": 1.3736127614974976, "learning_rate": 7.092326530866666e-05, "loss": 0.4447540283203125, "step": 342520 }, { "epoch": 2.0360694521223794, "grad_norm": 1.2395867109298706, "learning_rate": 7.091765798507882e-05, "loss": 0.5537859916687011, "step": 342530 }, { "epoch": 2.036128894199048, "grad_norm": 1.0506882667541504, "learning_rate": 7.09120508484481e-05, "loss": 0.5320466518402099, "step": 342540 }, { "epoch": 2.0361883362757163, "grad_norm": 1.2475255727767944, "learning_rate": 7.090644389880134e-05, "loss": 0.4672553062438965, "step": 342550 }, { "epoch": 2.0362477783523847, "grad_norm": 1.4793944358825684, "learning_rate": 7.09008371361654e-05, "loss": 0.5323076248168945, "step": 342560 }, { "epoch": 2.036307220429053, "grad_norm": 1.2247577905654907, "learning_rate": 7.08952305605671e-05, "loss": 0.46074981689453126, "step": 342570 }, { "epoch": 2.0363666625057215, "grad_norm": 1.1384910345077515, "learning_rate": 7.088962417203322e-05, "loss": 0.5318612098693848, "step": 342580 }, { "epoch": 2.0364261045823895, "grad_norm": 1.0707134008407593, "learning_rate": 7.088401797059059e-05, "loss": 0.4600632667541504, "step": 342590 }, { "epoch": 2.036485546659058, "grad_norm": 1.4772391319274902, "learning_rate": 7.087841195626605e-05, "loss": 0.5108142375946045, "step": 342600 }, { "epoch": 2.0365449887357263, "grad_norm": 1.4495066404342651, "learning_rate": 7.087280612908636e-05, "loss": 0.47854199409484866, "step": 342610 }, { "epoch": 2.0366044308123947, "grad_norm": 1.261805534362793, "learning_rate": 7.08672004890784e-05, "loss": 0.48059954643249514, "step": 342620 }, { "epoch": 2.036663872889063, "grad_norm": 1.2373136281967163, "learning_rate": 7.0861595036269e-05, "loss": 0.5816824436187744, "step": 342630 }, { "epoch": 2.0367233149657316, "grad_norm": 1.8827252388000488, "learning_rate": 7.085598977068491e-05, "loss": 0.492924165725708, "step": 342640 }, { "epoch": 2.0367827570424, "grad_norm": 1.5845588445663452, "learning_rate": 7.085038469235297e-05, "loss": 0.5302799224853516, "step": 342650 }, { "epoch": 2.0368421991190684, "grad_norm": 1.2027884721755981, "learning_rate": 7.08447798013e-05, "loss": 0.49329099655151365, "step": 342660 }, { "epoch": 2.036901641195737, "grad_norm": 1.6071224212646484, "learning_rate": 7.083917509755281e-05, "loss": 0.5382816791534424, "step": 342670 }, { "epoch": 2.036961083272405, "grad_norm": 1.4414814710617065, "learning_rate": 7.083357058113818e-05, "loss": 0.5114767551422119, "step": 342680 }, { "epoch": 2.0370205253490736, "grad_norm": 1.213965892791748, "learning_rate": 7.082796625208296e-05, "loss": 0.4298060417175293, "step": 342690 }, { "epoch": 2.037079967425742, "grad_norm": 1.3706419467926025, "learning_rate": 7.082236211041398e-05, "loss": 0.5269687175750732, "step": 342700 }, { "epoch": 2.0371394095024105, "grad_norm": 1.4937419891357422, "learning_rate": 7.0816758156158e-05, "loss": 0.503672456741333, "step": 342710 }, { "epoch": 2.037198851579079, "grad_norm": 1.3191341161727905, "learning_rate": 7.081115438934184e-05, "loss": 0.47163238525390627, "step": 342720 }, { "epoch": 2.0372582936557473, "grad_norm": 1.5665805339813232, "learning_rate": 7.080555080999231e-05, "loss": 0.5185987472534179, "step": 342730 }, { "epoch": 2.0373177357324157, "grad_norm": 1.0229188203811646, "learning_rate": 7.079994741813621e-05, "loss": 0.5162687301635742, "step": 342740 }, { "epoch": 2.037377177809084, "grad_norm": 1.2577320337295532, "learning_rate": 7.079434421380035e-05, "loss": 0.5270828247070313, "step": 342750 }, { "epoch": 2.0374366198857525, "grad_norm": 1.7474172115325928, "learning_rate": 7.078874119701155e-05, "loss": 0.49346675872802737, "step": 342760 }, { "epoch": 2.0374960619624205, "grad_norm": 1.5218696594238281, "learning_rate": 7.07831383677966e-05, "loss": 0.4687471866607666, "step": 342770 }, { "epoch": 2.037555504039089, "grad_norm": 1.0300506353378296, "learning_rate": 7.07775357261823e-05, "loss": 0.4735712051391602, "step": 342780 }, { "epoch": 2.0376149461157573, "grad_norm": 1.2151352167129517, "learning_rate": 7.077193327219545e-05, "loss": 0.5431134700775146, "step": 342790 }, { "epoch": 2.0376743881924257, "grad_norm": 1.4924269914627075, "learning_rate": 7.076633100586285e-05, "loss": 0.4568051338195801, "step": 342800 }, { "epoch": 2.037733830269094, "grad_norm": 1.4567910432815552, "learning_rate": 7.076072892721127e-05, "loss": 0.5197191715240479, "step": 342810 }, { "epoch": 2.0377932723457626, "grad_norm": 1.248548984527588, "learning_rate": 7.075512703626757e-05, "loss": 0.4838475227355957, "step": 342820 }, { "epoch": 2.037852714422431, "grad_norm": 1.3834834098815918, "learning_rate": 7.07495253330585e-05, "loss": 0.5020119667053222, "step": 342830 }, { "epoch": 2.0379121564990994, "grad_norm": 1.3297995328903198, "learning_rate": 7.074392381761088e-05, "loss": 0.4726576805114746, "step": 342840 }, { "epoch": 2.037971598575768, "grad_norm": 1.0937323570251465, "learning_rate": 7.073832248995153e-05, "loss": 0.5265941619873047, "step": 342850 }, { "epoch": 2.0380310406524362, "grad_norm": 1.221862554550171, "learning_rate": 7.073272135010718e-05, "loss": 0.490716552734375, "step": 342860 }, { "epoch": 2.0380904827291046, "grad_norm": 1.3710488080978394, "learning_rate": 7.072712039810466e-05, "loss": 0.43213891983032227, "step": 342870 }, { "epoch": 2.038149924805773, "grad_norm": 1.5164926052093506, "learning_rate": 7.072151963397076e-05, "loss": 0.5371719360351562, "step": 342880 }, { "epoch": 2.0382093668824415, "grad_norm": 0.9493893384933472, "learning_rate": 7.071591905773232e-05, "loss": 0.4843426704406738, "step": 342890 }, { "epoch": 2.03826880895911, "grad_norm": 1.3082947731018066, "learning_rate": 7.071031866941604e-05, "loss": 0.49372358322143556, "step": 342900 }, { "epoch": 2.0383282510357783, "grad_norm": 1.1599211692810059, "learning_rate": 7.070471846904873e-05, "loss": 0.4788471221923828, "step": 342910 }, { "epoch": 2.0383876931124467, "grad_norm": 1.116690754890442, "learning_rate": 7.069911845665727e-05, "loss": 0.4745209217071533, "step": 342920 }, { "epoch": 2.038447135189115, "grad_norm": 1.1107347011566162, "learning_rate": 7.069351863226834e-05, "loss": 0.49593820571899416, "step": 342930 }, { "epoch": 2.0385065772657835, "grad_norm": 1.7867417335510254, "learning_rate": 7.068791899590875e-05, "loss": 0.46396942138671876, "step": 342940 }, { "epoch": 2.038566019342452, "grad_norm": 1.307771921157837, "learning_rate": 7.068231954760538e-05, "loss": 0.536468505859375, "step": 342950 }, { "epoch": 2.03862546141912, "grad_norm": 1.7679380178451538, "learning_rate": 7.06767202873849e-05, "loss": 0.53154296875, "step": 342960 }, { "epoch": 2.0386849034957883, "grad_norm": 1.0858311653137207, "learning_rate": 7.067112121527413e-05, "loss": 0.49938507080078126, "step": 342970 }, { "epoch": 2.0387443455724568, "grad_norm": 1.2216304540634155, "learning_rate": 7.066552233129988e-05, "loss": 0.45155925750732423, "step": 342980 }, { "epoch": 2.038803787649125, "grad_norm": 1.1393934488296509, "learning_rate": 7.06599236354889e-05, "loss": 0.5200793266296386, "step": 342990 }, { "epoch": 2.0388632297257936, "grad_norm": 1.1746262311935425, "learning_rate": 7.065432512786802e-05, "loss": 0.4868763446807861, "step": 343000 }, { "epoch": 2.038922671802462, "grad_norm": 1.3748763799667358, "learning_rate": 7.064872680846398e-05, "loss": 0.4899913311004639, "step": 343010 }, { "epoch": 2.0389821138791304, "grad_norm": 1.5525449514389038, "learning_rate": 7.064312867730356e-05, "loss": 0.4776612281799316, "step": 343020 }, { "epoch": 2.039041555955799, "grad_norm": 0.9648895263671875, "learning_rate": 7.063753073441357e-05, "loss": 0.4927321434020996, "step": 343030 }, { "epoch": 2.0391009980324672, "grad_norm": 1.0616375207901, "learning_rate": 7.063193297982071e-05, "loss": 0.50687255859375, "step": 343040 }, { "epoch": 2.0391604401091357, "grad_norm": 1.1697325706481934, "learning_rate": 7.062633541355186e-05, "loss": 0.5316210746765136, "step": 343050 }, { "epoch": 2.039219882185804, "grad_norm": 1.3116523027420044, "learning_rate": 7.062073803563376e-05, "loss": 0.5468261241912842, "step": 343060 }, { "epoch": 2.0392793242624725, "grad_norm": 1.1344835758209229, "learning_rate": 7.06151408460932e-05, "loss": 0.4848785877227783, "step": 343070 }, { "epoch": 2.039338766339141, "grad_norm": 1.3182696104049683, "learning_rate": 7.06095438449569e-05, "loss": 0.46149282455444335, "step": 343080 }, { "epoch": 2.0393982084158093, "grad_norm": 1.353606939315796, "learning_rate": 7.060394703225168e-05, "loss": 0.5134934425354004, "step": 343090 }, { "epoch": 2.0394576504924777, "grad_norm": 1.2300626039505005, "learning_rate": 7.059835040800429e-05, "loss": 0.4845111846923828, "step": 343100 }, { "epoch": 2.039517092569146, "grad_norm": 1.3397222757339478, "learning_rate": 7.059275397224152e-05, "loss": 0.5504514694213867, "step": 343110 }, { "epoch": 2.0395765346458146, "grad_norm": 1.588305950164795, "learning_rate": 7.058715772499014e-05, "loss": 0.5498757362365723, "step": 343120 }, { "epoch": 2.039635976722483, "grad_norm": 1.5844289064407349, "learning_rate": 7.058156166627692e-05, "loss": 0.5120892524719238, "step": 343130 }, { "epoch": 2.039695418799151, "grad_norm": 1.0688908100128174, "learning_rate": 7.057596579612864e-05, "loss": 0.5200757503509521, "step": 343140 }, { "epoch": 2.0397548608758194, "grad_norm": 1.8235056400299072, "learning_rate": 7.057037011457204e-05, "loss": 0.43318653106689453, "step": 343150 }, { "epoch": 2.039814302952488, "grad_norm": 1.4121452569961548, "learning_rate": 7.056477462163394e-05, "loss": 0.5451812744140625, "step": 343160 }, { "epoch": 2.039873745029156, "grad_norm": 1.355009913444519, "learning_rate": 7.055917931734099e-05, "loss": 0.5373190879821778, "step": 343170 }, { "epoch": 2.0399331871058246, "grad_norm": 1.648102045059204, "learning_rate": 7.055358420172007e-05, "loss": 0.5192863941192627, "step": 343180 }, { "epoch": 2.039992629182493, "grad_norm": 1.6280779838562012, "learning_rate": 7.054798927479793e-05, "loss": 0.5242783546447753, "step": 343190 }, { "epoch": 2.0400520712591614, "grad_norm": 1.4283685684204102, "learning_rate": 7.054239453660134e-05, "loss": 0.5358823776245117, "step": 343200 }, { "epoch": 2.04011151333583, "grad_norm": 1.4489248991012573, "learning_rate": 7.053679998715701e-05, "loss": 0.5259143829345703, "step": 343210 }, { "epoch": 2.0401709554124983, "grad_norm": 1.2764087915420532, "learning_rate": 7.053120562649174e-05, "loss": 0.4932692050933838, "step": 343220 }, { "epoch": 2.0402303974891667, "grad_norm": 1.7698800563812256, "learning_rate": 7.052561145463224e-05, "loss": 0.5349226951599121, "step": 343230 }, { "epoch": 2.040289839565835, "grad_norm": 1.0758086442947388, "learning_rate": 7.052001747160538e-05, "loss": 0.4889705181121826, "step": 343240 }, { "epoch": 2.0403492816425035, "grad_norm": 2.746142864227295, "learning_rate": 7.051442367743781e-05, "loss": 0.49932146072387695, "step": 343250 }, { "epoch": 2.040408723719172, "grad_norm": 1.5664981603622437, "learning_rate": 7.050883007215634e-05, "loss": 0.5236865997314453, "step": 343260 }, { "epoch": 2.0404681657958403, "grad_norm": 1.335955262184143, "learning_rate": 7.050323665578775e-05, "loss": 0.5006907463073731, "step": 343270 }, { "epoch": 2.0405276078725088, "grad_norm": 1.4533077478408813, "learning_rate": 7.049764342835874e-05, "loss": 0.48385162353515626, "step": 343280 }, { "epoch": 2.040587049949177, "grad_norm": 1.2169804573059082, "learning_rate": 7.04920503898961e-05, "loss": 0.5228726387023925, "step": 343290 }, { "epoch": 2.0406464920258456, "grad_norm": 1.6117042303085327, "learning_rate": 7.048645754042656e-05, "loss": 0.5263434410095215, "step": 343300 }, { "epoch": 2.040705934102514, "grad_norm": 1.5783048868179321, "learning_rate": 7.048086487997694e-05, "loss": 0.5721931457519531, "step": 343310 }, { "epoch": 2.0407653761791824, "grad_norm": 1.5367861986160278, "learning_rate": 7.04752724085739e-05, "loss": 0.46698546409606934, "step": 343320 }, { "epoch": 2.0408248182558504, "grad_norm": 1.322928547859192, "learning_rate": 7.046968012624428e-05, "loss": 0.5171140670776367, "step": 343330 }, { "epoch": 2.040884260332519, "grad_norm": 1.652986764907837, "learning_rate": 7.046408803301479e-05, "loss": 0.5046547889709473, "step": 343340 }, { "epoch": 2.040943702409187, "grad_norm": 1.3406391143798828, "learning_rate": 7.045849612891216e-05, "loss": 0.5332194328308105, "step": 343350 }, { "epoch": 2.0410031444858556, "grad_norm": 1.403516411781311, "learning_rate": 7.045290441396315e-05, "loss": 0.48475494384765627, "step": 343360 }, { "epoch": 2.041062586562524, "grad_norm": 1.195542812347412, "learning_rate": 7.044731288819453e-05, "loss": 0.48120594024658203, "step": 343370 }, { "epoch": 2.0411220286391925, "grad_norm": 1.4051098823547363, "learning_rate": 7.044172155163307e-05, "loss": 0.47504358291625975, "step": 343380 }, { "epoch": 2.041181470715861, "grad_norm": 1.277282476425171, "learning_rate": 7.04361304043055e-05, "loss": 0.4799449920654297, "step": 343390 }, { "epoch": 2.0412409127925293, "grad_norm": 1.353559970855713, "learning_rate": 7.04305394462385e-05, "loss": 0.44037203788757323, "step": 343400 }, { "epoch": 2.0413003548691977, "grad_norm": 1.531484603881836, "learning_rate": 7.042494867745888e-05, "loss": 0.5364317893981934, "step": 343410 }, { "epoch": 2.041359796945866, "grad_norm": 1.6398484706878662, "learning_rate": 7.041935809799339e-05, "loss": 0.5145387649536133, "step": 343420 }, { "epoch": 2.0414192390225345, "grad_norm": 1.5128332376480103, "learning_rate": 7.041376770786869e-05, "loss": 0.5600791454315186, "step": 343430 }, { "epoch": 2.041478681099203, "grad_norm": 1.741436243057251, "learning_rate": 7.040817750711166e-05, "loss": 0.5734482765197754, "step": 343440 }, { "epoch": 2.0415381231758714, "grad_norm": 1.0736901760101318, "learning_rate": 7.0402587495749e-05, "loss": 0.5242899894714356, "step": 343450 }, { "epoch": 2.0415975652525398, "grad_norm": 1.1842920780181885, "learning_rate": 7.039699767380735e-05, "loss": 0.49180827140808103, "step": 343460 }, { "epoch": 2.041657007329208, "grad_norm": 1.2855759859085083, "learning_rate": 7.039140804131354e-05, "loss": 0.5309681415557861, "step": 343470 }, { "epoch": 2.0417164494058766, "grad_norm": 1.2902683019638062, "learning_rate": 7.038581859829429e-05, "loss": 0.49228801727294924, "step": 343480 }, { "epoch": 2.041775891482545, "grad_norm": 1.6351268291473389, "learning_rate": 7.038022934477635e-05, "loss": 0.5384465217590332, "step": 343490 }, { "epoch": 2.0418353335592134, "grad_norm": 1.4861090183258057, "learning_rate": 7.037464028078641e-05, "loss": 0.5135602951049805, "step": 343500 }, { "epoch": 2.0418947756358814, "grad_norm": 1.2724758386611938, "learning_rate": 7.03690514063513e-05, "loss": 0.5220817565917969, "step": 343510 }, { "epoch": 2.04195421771255, "grad_norm": 1.3630017042160034, "learning_rate": 7.036346272149768e-05, "loss": 0.4652904510498047, "step": 343520 }, { "epoch": 2.0420136597892182, "grad_norm": 1.6479743719100952, "learning_rate": 7.035787422625227e-05, "loss": 0.49874100685119627, "step": 343530 }, { "epoch": 2.0420731018658866, "grad_norm": 1.3112165927886963, "learning_rate": 7.035228592064185e-05, "loss": 0.5255311489105224, "step": 343540 }, { "epoch": 2.042132543942555, "grad_norm": 1.392130732536316, "learning_rate": 7.034669780469312e-05, "loss": 0.45605077743530276, "step": 343550 }, { "epoch": 2.0421919860192235, "grad_norm": 1.771206259727478, "learning_rate": 7.034110987843286e-05, "loss": 0.5368255615234375, "step": 343560 }, { "epoch": 2.042251428095892, "grad_norm": 1.556995153427124, "learning_rate": 7.033552214188776e-05, "loss": 0.49019627571105956, "step": 343570 }, { "epoch": 2.0423108701725603, "grad_norm": 1.539504051208496, "learning_rate": 7.032993459508457e-05, "loss": 0.5240177631378173, "step": 343580 }, { "epoch": 2.0423703122492287, "grad_norm": 1.4279494285583496, "learning_rate": 7.032434723804995e-05, "loss": 0.5109035968780518, "step": 343590 }, { "epoch": 2.042429754325897, "grad_norm": 1.455167293548584, "learning_rate": 7.031876007081075e-05, "loss": 0.5382345199584961, "step": 343600 }, { "epoch": 2.0424891964025655, "grad_norm": 1.4536147117614746, "learning_rate": 7.03131730933936e-05, "loss": 0.49186859130859373, "step": 343610 }, { "epoch": 2.042548638479234, "grad_norm": 1.0453656911849976, "learning_rate": 7.03075863058253e-05, "loss": 0.437226390838623, "step": 343620 }, { "epoch": 2.0426080805559024, "grad_norm": 1.4939334392547607, "learning_rate": 7.03019997081325e-05, "loss": 0.5611303329467774, "step": 343630 }, { "epoch": 2.042667522632571, "grad_norm": 1.4369276762008667, "learning_rate": 7.029641330034198e-05, "loss": 0.5537727355957032, "step": 343640 }, { "epoch": 2.042726964709239, "grad_norm": 1.2705401182174683, "learning_rate": 7.029082708248043e-05, "loss": 0.5364134788513184, "step": 343650 }, { "epoch": 2.0427864067859076, "grad_norm": 1.4572986364364624, "learning_rate": 7.028524105457457e-05, "loss": 0.4857471942901611, "step": 343660 }, { "epoch": 2.042845848862576, "grad_norm": 1.5765666961669922, "learning_rate": 7.027965521665117e-05, "loss": 0.5259820938110351, "step": 343670 }, { "epoch": 2.0429052909392444, "grad_norm": 1.410989761352539, "learning_rate": 7.02740695687369e-05, "loss": 0.5460511684417725, "step": 343680 }, { "epoch": 2.042964733015913, "grad_norm": 1.5197248458862305, "learning_rate": 7.026848411085851e-05, "loss": 0.4746553897857666, "step": 343690 }, { "epoch": 2.043024175092581, "grad_norm": 1.1830507516860962, "learning_rate": 7.02628988430427e-05, "loss": 0.42452588081359866, "step": 343700 }, { "epoch": 2.0430836171692492, "grad_norm": 1.252895712852478, "learning_rate": 7.025731376531621e-05, "loss": 0.49330816268920896, "step": 343710 }, { "epoch": 2.0431430592459177, "grad_norm": 1.4591771364212036, "learning_rate": 7.02517288777057e-05, "loss": 0.4893810749053955, "step": 343720 }, { "epoch": 2.043202501322586, "grad_norm": 1.0931365489959717, "learning_rate": 7.024614418023796e-05, "loss": 0.45734944343566897, "step": 343730 }, { "epoch": 2.0432619433992545, "grad_norm": 1.1824965476989746, "learning_rate": 7.024055967293967e-05, "loss": 0.4691937446594238, "step": 343740 }, { "epoch": 2.043321385475923, "grad_norm": 1.1712397336959839, "learning_rate": 7.023497535583758e-05, "loss": 0.46726169586181643, "step": 343750 }, { "epoch": 2.0433808275525913, "grad_norm": 1.2923811674118042, "learning_rate": 7.022939122895834e-05, "loss": 0.5140407085418701, "step": 343760 }, { "epoch": 2.0434402696292597, "grad_norm": 1.242518663406372, "learning_rate": 7.022380729232871e-05, "loss": 0.4993377685546875, "step": 343770 }, { "epoch": 2.043499711705928, "grad_norm": 1.3138047456741333, "learning_rate": 7.021822354597538e-05, "loss": 0.5042264461517334, "step": 343780 }, { "epoch": 2.0435591537825966, "grad_norm": 1.6588085889816284, "learning_rate": 7.021263998992504e-05, "loss": 0.5062684059143067, "step": 343790 }, { "epoch": 2.043618595859265, "grad_norm": 1.527428150177002, "learning_rate": 7.020705662420446e-05, "loss": 0.495403528213501, "step": 343800 }, { "epoch": 2.0436780379359334, "grad_norm": 1.0882070064544678, "learning_rate": 7.020147344884031e-05, "loss": 0.45121335983276367, "step": 343810 }, { "epoch": 2.043737480012602, "grad_norm": 1.488481044769287, "learning_rate": 7.019589046385932e-05, "loss": 0.5339438438415527, "step": 343820 }, { "epoch": 2.04379692208927, "grad_norm": 1.4134864807128906, "learning_rate": 7.019030766928816e-05, "loss": 0.5468342781066895, "step": 343830 }, { "epoch": 2.0438563641659386, "grad_norm": 1.0247445106506348, "learning_rate": 7.018472506515357e-05, "loss": 0.48091540336608884, "step": 343840 }, { "epoch": 2.043915806242607, "grad_norm": 1.3834627866744995, "learning_rate": 7.017914265148224e-05, "loss": 0.5235469341278076, "step": 343850 }, { "epoch": 2.0439752483192755, "grad_norm": 1.5692732334136963, "learning_rate": 7.017356042830086e-05, "loss": 0.44965457916259766, "step": 343860 }, { "epoch": 2.044034690395944, "grad_norm": 1.690658688545227, "learning_rate": 7.016797839563618e-05, "loss": 0.5132643222808838, "step": 343870 }, { "epoch": 2.044094132472612, "grad_norm": 1.1934635639190674, "learning_rate": 7.016239655351489e-05, "loss": 0.5004631042480469, "step": 343880 }, { "epoch": 2.0441535745492803, "grad_norm": 1.1587425470352173, "learning_rate": 7.015681490196361e-05, "loss": 0.4562129020690918, "step": 343890 }, { "epoch": 2.0442130166259487, "grad_norm": 1.17429518699646, "learning_rate": 7.015123344100916e-05, "loss": 0.45256357192993163, "step": 343900 }, { "epoch": 2.044272458702617, "grad_norm": 1.3679943084716797, "learning_rate": 7.014565217067817e-05, "loss": 0.5098611354827881, "step": 343910 }, { "epoch": 2.0443319007792855, "grad_norm": 1.7524628639221191, "learning_rate": 7.014007109099732e-05, "loss": 0.5123327255249024, "step": 343920 }, { "epoch": 2.044391342855954, "grad_norm": 1.2945637702941895, "learning_rate": 7.013449020199338e-05, "loss": 0.5479211807250977, "step": 343930 }, { "epoch": 2.0444507849326223, "grad_norm": 0.9966519474983215, "learning_rate": 7.012890950369307e-05, "loss": 0.4877976417541504, "step": 343940 }, { "epoch": 2.0445102270092907, "grad_norm": 1.4639798402786255, "learning_rate": 7.012332899612293e-05, "loss": 0.5295848846435547, "step": 343950 }, { "epoch": 2.044569669085959, "grad_norm": 1.3305639028549194, "learning_rate": 7.01177486793098e-05, "loss": 0.5046987056732177, "step": 343960 }, { "epoch": 2.0446291111626276, "grad_norm": 1.5589929819107056, "learning_rate": 7.011216855328031e-05, "loss": 0.49828033447265624, "step": 343970 }, { "epoch": 2.044688553239296, "grad_norm": 1.5181294679641724, "learning_rate": 7.010658861806119e-05, "loss": 0.5459794998168945, "step": 343980 }, { "epoch": 2.0447479953159644, "grad_norm": 1.2183244228363037, "learning_rate": 7.010100887367905e-05, "loss": 0.5024793148040771, "step": 343990 }, { "epoch": 2.044807437392633, "grad_norm": 1.0977855920791626, "learning_rate": 7.009542932016076e-05, "loss": 0.48937835693359377, "step": 344000 }, { "epoch": 2.0448668794693012, "grad_norm": 1.675666093826294, "learning_rate": 7.008984995753282e-05, "loss": 0.4972433567047119, "step": 344010 }, { "epoch": 2.0449263215459696, "grad_norm": 1.5319764614105225, "learning_rate": 7.008427078582198e-05, "loss": 0.47048392295837405, "step": 344020 }, { "epoch": 2.044985763622638, "grad_norm": 0.9105742573738098, "learning_rate": 7.007869180505498e-05, "loss": 0.47809610366821287, "step": 344030 }, { "epoch": 2.0450452056993065, "grad_norm": 1.6894919872283936, "learning_rate": 7.007311301525845e-05, "loss": 0.5431914329528809, "step": 344040 }, { "epoch": 2.045104647775975, "grad_norm": 1.5119022130966187, "learning_rate": 7.006753441645908e-05, "loss": 0.5246136665344239, "step": 344050 }, { "epoch": 2.0451640898526433, "grad_norm": 1.1688472032546997, "learning_rate": 7.006195600868364e-05, "loss": 0.4575646877288818, "step": 344060 }, { "epoch": 2.0452235319293113, "grad_norm": 1.0777347087860107, "learning_rate": 7.005637779195872e-05, "loss": 0.46729249954223634, "step": 344070 }, { "epoch": 2.0452829740059797, "grad_norm": 1.4106380939483643, "learning_rate": 7.005079976631102e-05, "loss": 0.47553057670593263, "step": 344080 }, { "epoch": 2.045342416082648, "grad_norm": 1.4620442390441895, "learning_rate": 7.004522193176726e-05, "loss": 0.4649256706237793, "step": 344090 }, { "epoch": 2.0454018581593165, "grad_norm": 1.2546312808990479, "learning_rate": 7.003964428835408e-05, "loss": 0.511442756652832, "step": 344100 }, { "epoch": 2.045461300235985, "grad_norm": 1.1953647136688232, "learning_rate": 7.00340668360982e-05, "loss": 0.5153308391571045, "step": 344110 }, { "epoch": 2.0455207423126534, "grad_norm": 1.2875680923461914, "learning_rate": 7.002848957502629e-05, "loss": 0.49717016220092775, "step": 344120 }, { "epoch": 2.0455801843893218, "grad_norm": 1.4425981044769287, "learning_rate": 7.002291250516499e-05, "loss": 0.5147886276245117, "step": 344130 }, { "epoch": 2.04563962646599, "grad_norm": 0.9683640599250793, "learning_rate": 7.001733562654105e-05, "loss": 0.4838740348815918, "step": 344140 }, { "epoch": 2.0456990685426586, "grad_norm": 1.025211215019226, "learning_rate": 7.001175893918104e-05, "loss": 0.49715323448181153, "step": 344150 }, { "epoch": 2.045758510619327, "grad_norm": 1.4107915163040161, "learning_rate": 7.000618244311177e-05, "loss": 0.5511327743530273, "step": 344160 }, { "epoch": 2.0458179526959954, "grad_norm": 1.4563392400741577, "learning_rate": 7.000060613835984e-05, "loss": 0.490750789642334, "step": 344170 }, { "epoch": 2.045877394772664, "grad_norm": 1.7588554620742798, "learning_rate": 6.999503002495194e-05, "loss": 0.48322200775146484, "step": 344180 }, { "epoch": 2.0459368368493323, "grad_norm": 1.3786073923110962, "learning_rate": 6.998945410291476e-05, "loss": 0.5613306045532227, "step": 344190 }, { "epoch": 2.0459962789260007, "grad_norm": 1.410449743270874, "learning_rate": 6.998387837227494e-05, "loss": 0.44974584579467775, "step": 344200 }, { "epoch": 2.046055721002669, "grad_norm": 1.322272539138794, "learning_rate": 6.997830283305913e-05, "loss": 0.5021837711334228, "step": 344210 }, { "epoch": 2.0461151630793375, "grad_norm": 1.6398426294326782, "learning_rate": 6.997272748529406e-05, "loss": 0.51359543800354, "step": 344220 }, { "epoch": 2.046174605156006, "grad_norm": 1.2902559041976929, "learning_rate": 6.996715232900641e-05, "loss": 0.5355489730834961, "step": 344230 }, { "epoch": 2.0462340472326743, "grad_norm": 1.2746002674102783, "learning_rate": 6.996157736422281e-05, "loss": 0.48314723968505857, "step": 344240 }, { "epoch": 2.0462934893093423, "grad_norm": 1.4173897504806519, "learning_rate": 6.995600259096995e-05, "loss": 0.529916524887085, "step": 344250 }, { "epoch": 2.0463529313860107, "grad_norm": 1.1914997100830078, "learning_rate": 6.995042800927449e-05, "loss": 0.5517083168029785, "step": 344260 }, { "epoch": 2.046412373462679, "grad_norm": 1.4804712533950806, "learning_rate": 6.994485361916306e-05, "loss": 0.49764056205749513, "step": 344270 }, { "epoch": 2.0464718155393475, "grad_norm": 1.4166045188903809, "learning_rate": 6.993927942066236e-05, "loss": 0.5248154640197754, "step": 344280 }, { "epoch": 2.046531257616016, "grad_norm": 2.074655532836914, "learning_rate": 6.993370541379907e-05, "loss": 0.5866563320159912, "step": 344290 }, { "epoch": 2.0465906996926844, "grad_norm": 0.9389705657958984, "learning_rate": 6.992813159859985e-05, "loss": 0.4529440879821777, "step": 344300 }, { "epoch": 2.046650141769353, "grad_norm": 1.6648292541503906, "learning_rate": 6.992255797509136e-05, "loss": 0.49676008224487306, "step": 344310 }, { "epoch": 2.046709583846021, "grad_norm": 1.5805654525756836, "learning_rate": 6.991698454330023e-05, "loss": 0.5257265567779541, "step": 344320 }, { "epoch": 2.0467690259226896, "grad_norm": 1.2175973653793335, "learning_rate": 6.991141130325316e-05, "loss": 0.48253483772277833, "step": 344330 }, { "epoch": 2.046828467999358, "grad_norm": 1.4095418453216553, "learning_rate": 6.99058382549768e-05, "loss": 0.4867513656616211, "step": 344340 }, { "epoch": 2.0468879100760264, "grad_norm": 1.1881141662597656, "learning_rate": 6.990026539849777e-05, "loss": 0.47385263442993164, "step": 344350 }, { "epoch": 2.046947352152695, "grad_norm": 1.3750696182250977, "learning_rate": 6.98946927338428e-05, "loss": 0.5304458141326904, "step": 344360 }, { "epoch": 2.0470067942293633, "grad_norm": 1.1364343166351318, "learning_rate": 6.988912026103855e-05, "loss": 0.4746138095855713, "step": 344370 }, { "epoch": 2.0470662363060317, "grad_norm": 1.2004570960998535, "learning_rate": 6.988354798011156e-05, "loss": 0.49944534301757815, "step": 344380 }, { "epoch": 2.0471256783827, "grad_norm": 1.1683954000473022, "learning_rate": 6.987797589108862e-05, "loss": 0.5390625476837159, "step": 344390 }, { "epoch": 2.0471851204593685, "grad_norm": 1.1316472291946411, "learning_rate": 6.987240399399632e-05, "loss": 0.5508895874023437, "step": 344400 }, { "epoch": 2.047244562536037, "grad_norm": 1.3025519847869873, "learning_rate": 6.986683228886128e-05, "loss": 0.5166041374206543, "step": 344410 }, { "epoch": 2.0473040046127053, "grad_norm": 1.1692200899124146, "learning_rate": 6.986126077571027e-05, "loss": 0.550838565826416, "step": 344420 }, { "epoch": 2.0473634466893738, "grad_norm": 1.4363915920257568, "learning_rate": 6.985568945456987e-05, "loss": 0.5201510906219482, "step": 344430 }, { "epoch": 2.0474228887660417, "grad_norm": 1.239120602607727, "learning_rate": 6.985011832546666e-05, "loss": 0.561473274230957, "step": 344440 }, { "epoch": 2.04748233084271, "grad_norm": 1.1022640466690063, "learning_rate": 6.984454738842742e-05, "loss": 0.5011137008666993, "step": 344450 }, { "epoch": 2.0475417729193786, "grad_norm": 1.419161319732666, "learning_rate": 6.983897664347874e-05, "loss": 0.4952082633972168, "step": 344460 }, { "epoch": 2.047601214996047, "grad_norm": 1.7221698760986328, "learning_rate": 6.983340609064725e-05, "loss": 0.5327639102935791, "step": 344470 }, { "epoch": 2.0476606570727154, "grad_norm": 1.6942046880722046, "learning_rate": 6.982783572995961e-05, "loss": 0.5368154525756836, "step": 344480 }, { "epoch": 2.047720099149384, "grad_norm": 1.613303542137146, "learning_rate": 6.982226556144253e-05, "loss": 0.546014928817749, "step": 344490 }, { "epoch": 2.047779541226052, "grad_norm": 1.1707720756530762, "learning_rate": 6.981669558512258e-05, "loss": 0.42794222831726075, "step": 344500 }, { "epoch": 2.0478389833027206, "grad_norm": 1.4463633298873901, "learning_rate": 6.981112580102637e-05, "loss": 0.5289016723632812, "step": 344510 }, { "epoch": 2.047898425379389, "grad_norm": 1.1893469095230103, "learning_rate": 6.980555620918066e-05, "loss": 0.4899266719818115, "step": 344520 }, { "epoch": 2.0479578674560575, "grad_norm": 1.3058656454086304, "learning_rate": 6.979998680961201e-05, "loss": 0.5396640777587891, "step": 344530 }, { "epoch": 2.048017309532726, "grad_norm": 1.9014064073562622, "learning_rate": 6.979441760234706e-05, "loss": 0.5622823715209961, "step": 344540 }, { "epoch": 2.0480767516093943, "grad_norm": 1.259634017944336, "learning_rate": 6.978884858741255e-05, "loss": 0.45813760757446287, "step": 344550 }, { "epoch": 2.0481361936860627, "grad_norm": 1.247818112373352, "learning_rate": 6.978327976483503e-05, "loss": 0.5017759799957275, "step": 344560 }, { "epoch": 2.048195635762731, "grad_norm": 1.0908844470977783, "learning_rate": 6.977771113464109e-05, "loss": 0.47566661834716795, "step": 344570 }, { "epoch": 2.0482550778393995, "grad_norm": 1.0604454278945923, "learning_rate": 6.977214269685747e-05, "loss": 0.4935410499572754, "step": 344580 }, { "epoch": 2.048314519916068, "grad_norm": 1.490410327911377, "learning_rate": 6.97665744515108e-05, "loss": 0.5001959800720215, "step": 344590 }, { "epoch": 2.0483739619927364, "grad_norm": 1.4978301525115967, "learning_rate": 6.976100639862767e-05, "loss": 0.5167869567871094, "step": 344600 }, { "epoch": 2.0484334040694048, "grad_norm": 1.423950433731079, "learning_rate": 6.975543853823474e-05, "loss": 0.48689045906066897, "step": 344610 }, { "epoch": 2.0484928461460727, "grad_norm": 1.4705846309661865, "learning_rate": 6.974987087035864e-05, "loss": 0.5029429435729981, "step": 344620 }, { "epoch": 2.048552288222741, "grad_norm": 1.6476596593856812, "learning_rate": 6.9744303395026e-05, "loss": 0.5061779975891113, "step": 344630 }, { "epoch": 2.0486117302994096, "grad_norm": 1.316820740699768, "learning_rate": 6.973873611226343e-05, "loss": 0.5322749137878418, "step": 344640 }, { "epoch": 2.048671172376078, "grad_norm": 1.2211552858352661, "learning_rate": 6.97331690220976e-05, "loss": 0.5100406169891357, "step": 344650 }, { "epoch": 2.0487306144527464, "grad_norm": 1.3603445291519165, "learning_rate": 6.972760212455516e-05, "loss": 0.4415302753448486, "step": 344660 }, { "epoch": 2.048790056529415, "grad_norm": 1.3251087665557861, "learning_rate": 6.972203541966271e-05, "loss": 0.4920241355895996, "step": 344670 }, { "epoch": 2.0488494986060832, "grad_norm": 1.0313090085983276, "learning_rate": 6.971646890744686e-05, "loss": 0.5153308868408203, "step": 344680 }, { "epoch": 2.0489089406827516, "grad_norm": 1.1809768676757812, "learning_rate": 6.971090258793427e-05, "loss": 0.48898115158081057, "step": 344690 }, { "epoch": 2.04896838275942, "grad_norm": 1.4418294429779053, "learning_rate": 6.970533646115155e-05, "loss": 0.4804880142211914, "step": 344700 }, { "epoch": 2.0490278248360885, "grad_norm": 1.2216272354125977, "learning_rate": 6.96997705271253e-05, "loss": 0.5437365531921386, "step": 344710 }, { "epoch": 2.049087266912757, "grad_norm": 1.407569169998169, "learning_rate": 6.969420478588221e-05, "loss": 0.5485153198242188, "step": 344720 }, { "epoch": 2.0491467089894253, "grad_norm": 1.3041398525238037, "learning_rate": 6.968863923744888e-05, "loss": 0.5706045150756835, "step": 344730 }, { "epoch": 2.0492061510660937, "grad_norm": 1.5846409797668457, "learning_rate": 6.96830738818519e-05, "loss": 0.5317665576934815, "step": 344740 }, { "epoch": 2.049265593142762, "grad_norm": 0.9995574951171875, "learning_rate": 6.967750871911796e-05, "loss": 0.5051277160644532, "step": 344750 }, { "epoch": 2.0493250352194305, "grad_norm": 1.0034210681915283, "learning_rate": 6.967194374927361e-05, "loss": 0.49113893508911133, "step": 344760 }, { "epoch": 2.049384477296099, "grad_norm": 1.3568440675735474, "learning_rate": 6.966637897234548e-05, "loss": 0.5606632232666016, "step": 344770 }, { "epoch": 2.0494439193727674, "grad_norm": 1.8091241121292114, "learning_rate": 6.966081438836025e-05, "loss": 0.49869556427001954, "step": 344780 }, { "epoch": 2.049503361449436, "grad_norm": 1.5747442245483398, "learning_rate": 6.965524999734449e-05, "loss": 0.5164517402648926, "step": 344790 }, { "epoch": 2.049562803526104, "grad_norm": 1.2628452777862549, "learning_rate": 6.964968579932484e-05, "loss": 0.49803962707519533, "step": 344800 }, { "epoch": 2.049622245602772, "grad_norm": 1.4113625288009644, "learning_rate": 6.96441217943279e-05, "loss": 0.4688393592834473, "step": 344810 }, { "epoch": 2.0496816876794406, "grad_norm": 1.3761887550354004, "learning_rate": 6.963855798238028e-05, "loss": 0.4565893650054932, "step": 344820 }, { "epoch": 2.049741129756109, "grad_norm": 1.2803852558135986, "learning_rate": 6.963299436350863e-05, "loss": 0.47715034484863283, "step": 344830 }, { "epoch": 2.0498005718327774, "grad_norm": 1.4237192869186401, "learning_rate": 6.962743093773949e-05, "loss": 0.5167501449584961, "step": 344840 }, { "epoch": 2.049860013909446, "grad_norm": 0.9929883480072021, "learning_rate": 6.962186770509957e-05, "loss": 0.5071372509002685, "step": 344850 }, { "epoch": 2.0499194559861142, "grad_norm": 1.0207273960113525, "learning_rate": 6.961630466561544e-05, "loss": 0.46175804138183596, "step": 344860 }, { "epoch": 2.0499788980627827, "grad_norm": 1.2229305505752563, "learning_rate": 6.96107418193137e-05, "loss": 0.43696908950805663, "step": 344870 }, { "epoch": 2.050038340139451, "grad_norm": 1.312996506690979, "learning_rate": 6.9605179166221e-05, "loss": 0.56737380027771, "step": 344880 }, { "epoch": 2.0500977822161195, "grad_norm": 2.4158990383148193, "learning_rate": 6.95996167063639e-05, "loss": 0.5002319812774658, "step": 344890 }, { "epoch": 2.050157224292788, "grad_norm": 1.6911983489990234, "learning_rate": 6.9594054439769e-05, "loss": 0.5102208137512207, "step": 344900 }, { "epoch": 2.0502166663694563, "grad_norm": 1.655686855316162, "learning_rate": 6.958849236646296e-05, "loss": 0.5359115123748779, "step": 344910 }, { "epoch": 2.0502761084461247, "grad_norm": 1.069225788116455, "learning_rate": 6.95829304864724e-05, "loss": 0.5234410285949707, "step": 344920 }, { "epoch": 2.050335550522793, "grad_norm": 1.987337350845337, "learning_rate": 6.957736879982387e-05, "loss": 0.49201555252075196, "step": 344930 }, { "epoch": 2.0503949925994616, "grad_norm": 1.109023094177246, "learning_rate": 6.957180730654399e-05, "loss": 0.5446587562561035, "step": 344940 }, { "epoch": 2.05045443467613, "grad_norm": 1.1729834079742432, "learning_rate": 6.956624600665938e-05, "loss": 0.4880208015441895, "step": 344950 }, { "epoch": 2.0505138767527984, "grad_norm": 1.212043046951294, "learning_rate": 6.956068490019663e-05, "loss": 0.487872314453125, "step": 344960 }, { "epoch": 2.050573318829467, "grad_norm": 1.3863465785980225, "learning_rate": 6.955512398718233e-05, "loss": 0.4893298625946045, "step": 344970 }, { "epoch": 2.050632760906135, "grad_norm": 1.2149819135665894, "learning_rate": 6.954956326764316e-05, "loss": 0.5072625160217286, "step": 344980 }, { "epoch": 2.050692202982803, "grad_norm": 1.4839165210723877, "learning_rate": 6.954400274160562e-05, "loss": 0.4695584297180176, "step": 344990 }, { "epoch": 2.0507516450594716, "grad_norm": 1.547752857208252, "learning_rate": 6.953844240909632e-05, "loss": 0.5030569076538086, "step": 345000 }, { "epoch": 2.05081108713614, "grad_norm": 1.4739376306533813, "learning_rate": 6.953288227014192e-05, "loss": 0.5063521385192871, "step": 345010 }, { "epoch": 2.0508705292128084, "grad_norm": 1.4351495504379272, "learning_rate": 6.952732232476898e-05, "loss": 0.4822195053100586, "step": 345020 }, { "epoch": 2.050929971289477, "grad_norm": 1.4479494094848633, "learning_rate": 6.952176257300408e-05, "loss": 0.4975587368011475, "step": 345030 }, { "epoch": 2.0509894133661453, "grad_norm": 1.3375065326690674, "learning_rate": 6.95162030148739e-05, "loss": 0.4775243759155273, "step": 345040 }, { "epoch": 2.0510488554428137, "grad_norm": 1.4361287355422974, "learning_rate": 6.951064365040495e-05, "loss": 0.5302898406982421, "step": 345050 }, { "epoch": 2.051108297519482, "grad_norm": 1.6924537420272827, "learning_rate": 6.950508447962381e-05, "loss": 0.4893612861633301, "step": 345060 }, { "epoch": 2.0511677395961505, "grad_norm": 1.439505934715271, "learning_rate": 6.949952550255714e-05, "loss": 0.5530443668365479, "step": 345070 }, { "epoch": 2.051227181672819, "grad_norm": 1.378265142440796, "learning_rate": 6.94939667192315e-05, "loss": 0.48433623313903806, "step": 345080 }, { "epoch": 2.0512866237494873, "grad_norm": 0.8966063857078552, "learning_rate": 6.948840812967351e-05, "loss": 0.4783762454986572, "step": 345090 }, { "epoch": 2.0513460658261558, "grad_norm": 2.185974359512329, "learning_rate": 6.948284973390972e-05, "loss": 0.5183083057403565, "step": 345100 }, { "epoch": 2.051405507902824, "grad_norm": 1.4208617210388184, "learning_rate": 6.947729153196674e-05, "loss": 0.5146193504333496, "step": 345110 }, { "epoch": 2.0514649499794926, "grad_norm": 1.1438525915145874, "learning_rate": 6.947173352387115e-05, "loss": 0.5143678188323975, "step": 345120 }, { "epoch": 2.051524392056161, "grad_norm": 1.1110306978225708, "learning_rate": 6.946617570964951e-05, "loss": 0.47396373748779297, "step": 345130 }, { "epoch": 2.0515838341328294, "grad_norm": 1.0750129222869873, "learning_rate": 6.946061808932846e-05, "loss": 0.5517351627349854, "step": 345140 }, { "epoch": 2.051643276209498, "grad_norm": 1.0765681266784668, "learning_rate": 6.945506066293459e-05, "loss": 0.4775885581970215, "step": 345150 }, { "epoch": 2.0517027182861662, "grad_norm": 1.4059475660324097, "learning_rate": 6.944950343049444e-05, "loss": 0.5238991737365722, "step": 345160 }, { "epoch": 2.0517621603628347, "grad_norm": 1.304032325744629, "learning_rate": 6.944394639203462e-05, "loss": 0.4867886543273926, "step": 345170 }, { "epoch": 2.0518216024395026, "grad_norm": 1.2040616273880005, "learning_rate": 6.943838954758171e-05, "loss": 0.5057313919067383, "step": 345180 }, { "epoch": 2.051881044516171, "grad_norm": 1.3308894634246826, "learning_rate": 6.943283289716229e-05, "loss": 0.51600661277771, "step": 345190 }, { "epoch": 2.0519404865928395, "grad_norm": 1.5338503122329712, "learning_rate": 6.94272764408029e-05, "loss": 0.5007171630859375, "step": 345200 }, { "epoch": 2.051999928669508, "grad_norm": 1.1137735843658447, "learning_rate": 6.942172017853019e-05, "loss": 0.49141383171081543, "step": 345210 }, { "epoch": 2.0520593707461763, "grad_norm": 1.30951988697052, "learning_rate": 6.94161641103707e-05, "loss": 0.5665898323059082, "step": 345220 }, { "epoch": 2.0521188128228447, "grad_norm": 1.2462095022201538, "learning_rate": 6.941060823635104e-05, "loss": 0.503365421295166, "step": 345230 }, { "epoch": 2.052178254899513, "grad_norm": 1.3148839473724365, "learning_rate": 6.940505255649776e-05, "loss": 0.5589809417724609, "step": 345240 }, { "epoch": 2.0522376969761815, "grad_norm": 1.2798041105270386, "learning_rate": 6.939949707083744e-05, "loss": 0.5264633178710938, "step": 345250 }, { "epoch": 2.05229713905285, "grad_norm": 1.7742269039154053, "learning_rate": 6.939394177939665e-05, "loss": 0.5058247089385987, "step": 345260 }, { "epoch": 2.0523565811295184, "grad_norm": 1.0820876359939575, "learning_rate": 6.938838668220196e-05, "loss": 0.5169869422912597, "step": 345270 }, { "epoch": 2.0524160232061868, "grad_norm": 1.3945293426513672, "learning_rate": 6.938283177927998e-05, "loss": 0.5132973194122314, "step": 345280 }, { "epoch": 2.052475465282855, "grad_norm": 1.4025866985321045, "learning_rate": 6.937727707065727e-05, "loss": 0.48903894424438477, "step": 345290 }, { "epoch": 2.0525349073595236, "grad_norm": 1.9373866319656372, "learning_rate": 6.937172255636038e-05, "loss": 0.5109736919403076, "step": 345300 }, { "epoch": 2.052594349436192, "grad_norm": 1.4014662504196167, "learning_rate": 6.936616823641586e-05, "loss": 0.4980497360229492, "step": 345310 }, { "epoch": 2.0526537915128604, "grad_norm": 1.612177848815918, "learning_rate": 6.936061411085035e-05, "loss": 0.5054637908935546, "step": 345320 }, { "epoch": 2.052713233589529, "grad_norm": 1.4057555198669434, "learning_rate": 6.935506017969034e-05, "loss": 0.4869023323059082, "step": 345330 }, { "epoch": 2.0527726756661973, "grad_norm": 1.4936484098434448, "learning_rate": 6.934950644296247e-05, "loss": 0.5162741661071777, "step": 345340 }, { "epoch": 2.0528321177428657, "grad_norm": 1.626789927482605, "learning_rate": 6.934395290069326e-05, "loss": 0.5255335807800293, "step": 345350 }, { "epoch": 2.0528915598195336, "grad_norm": 1.5637338161468506, "learning_rate": 6.933839955290933e-05, "loss": 0.481840991973877, "step": 345360 }, { "epoch": 2.052951001896202, "grad_norm": 1.122491478919983, "learning_rate": 6.933284639963719e-05, "loss": 0.486528205871582, "step": 345370 }, { "epoch": 2.0530104439728705, "grad_norm": 1.431323766708374, "learning_rate": 6.932729344090341e-05, "loss": 0.4692185401916504, "step": 345380 }, { "epoch": 2.053069886049539, "grad_norm": 1.315394401550293, "learning_rate": 6.932174067673454e-05, "loss": 0.5175354957580567, "step": 345390 }, { "epoch": 2.0531293281262073, "grad_norm": 1.7840980291366577, "learning_rate": 6.931618810715721e-05, "loss": 0.5466912269592286, "step": 345400 }, { "epoch": 2.0531887702028757, "grad_norm": 1.600035548210144, "learning_rate": 6.931063573219792e-05, "loss": 0.5153797149658204, "step": 345410 }, { "epoch": 2.053248212279544, "grad_norm": 1.5262086391448975, "learning_rate": 6.930508355188328e-05, "loss": 0.522744083404541, "step": 345420 }, { "epoch": 2.0533076543562125, "grad_norm": 1.0384855270385742, "learning_rate": 6.929953156623981e-05, "loss": 0.5037216186523438, "step": 345430 }, { "epoch": 2.053367096432881, "grad_norm": 1.6900103092193604, "learning_rate": 6.929397977529409e-05, "loss": 0.5610835552215576, "step": 345440 }, { "epoch": 2.0534265385095494, "grad_norm": 1.2469418048858643, "learning_rate": 6.928842817907263e-05, "loss": 0.5294348239898682, "step": 345450 }, { "epoch": 2.053485980586218, "grad_norm": 1.5037868022918701, "learning_rate": 6.928287677760202e-05, "loss": 0.5670270919799805, "step": 345460 }, { "epoch": 2.053545422662886, "grad_norm": 1.4072213172912598, "learning_rate": 6.927732557090886e-05, "loss": 0.5002717971801758, "step": 345470 }, { "epoch": 2.0536048647395546, "grad_norm": 1.0550600290298462, "learning_rate": 6.92717745590197e-05, "loss": 0.49022607803344725, "step": 345480 }, { "epoch": 2.053664306816223, "grad_norm": 1.681488037109375, "learning_rate": 6.926622374196096e-05, "loss": 0.4661426544189453, "step": 345490 }, { "epoch": 2.0537237488928914, "grad_norm": 1.3329747915267944, "learning_rate": 6.926067311975936e-05, "loss": 0.517490291595459, "step": 345500 }, { "epoch": 2.05378319096956, "grad_norm": 1.0009278059005737, "learning_rate": 6.925512269244138e-05, "loss": 0.41785249710083006, "step": 345510 }, { "epoch": 2.0538426330462283, "grad_norm": 1.3179837465286255, "learning_rate": 6.924957246003355e-05, "loss": 0.5035099983215332, "step": 345520 }, { "epoch": 2.0539020751228967, "grad_norm": 1.3074951171875, "learning_rate": 6.924402242256247e-05, "loss": 0.4990811347961426, "step": 345530 }, { "epoch": 2.053961517199565, "grad_norm": 1.3811308145523071, "learning_rate": 6.923847258005471e-05, "loss": 0.5648107528686523, "step": 345540 }, { "epoch": 2.054020959276233, "grad_norm": 1.6093190908432007, "learning_rate": 6.923292293253673e-05, "loss": 0.5065844535827637, "step": 345550 }, { "epoch": 2.0540804013529015, "grad_norm": 1.4808006286621094, "learning_rate": 6.92273734800351e-05, "loss": 0.5108167171478272, "step": 345560 }, { "epoch": 2.05413984342957, "grad_norm": 1.5221666097640991, "learning_rate": 6.922182422257641e-05, "loss": 0.5064189910888672, "step": 345570 }, { "epoch": 2.0541992855062383, "grad_norm": 1.657412052154541, "learning_rate": 6.92162751601872e-05, "loss": 0.4948431491851807, "step": 345580 }, { "epoch": 2.0542587275829067, "grad_norm": 1.5662257671356201, "learning_rate": 6.921072629289401e-05, "loss": 0.5323777198791504, "step": 345590 }, { "epoch": 2.054318169659575, "grad_norm": 1.2441333532333374, "learning_rate": 6.920517762072336e-05, "loss": 0.4898055553436279, "step": 345600 }, { "epoch": 2.0543776117362436, "grad_norm": 1.2261000871658325, "learning_rate": 6.919962914370182e-05, "loss": 0.517499589920044, "step": 345610 }, { "epoch": 2.054437053812912, "grad_norm": 1.324291706085205, "learning_rate": 6.919408086185588e-05, "loss": 0.5376256942749024, "step": 345620 }, { "epoch": 2.0544964958895804, "grad_norm": 1.3757492303848267, "learning_rate": 6.918853277521216e-05, "loss": 0.5380536079406738, "step": 345630 }, { "epoch": 2.054555937966249, "grad_norm": 1.3037457466125488, "learning_rate": 6.918298488379715e-05, "loss": 0.4997109413146973, "step": 345640 }, { "epoch": 2.054615380042917, "grad_norm": 1.1166566610336304, "learning_rate": 6.91774371876374e-05, "loss": 0.48910017013549806, "step": 345650 }, { "epoch": 2.0546748221195856, "grad_norm": 1.3114093542099, "learning_rate": 6.917188968675945e-05, "loss": 0.5038352489471436, "step": 345660 }, { "epoch": 2.054734264196254, "grad_norm": 1.160571813583374, "learning_rate": 6.916634238118987e-05, "loss": 0.5337470531463623, "step": 345670 }, { "epoch": 2.0547937062729225, "grad_norm": 1.3188284635543823, "learning_rate": 6.916079527095514e-05, "loss": 0.5366062164306641, "step": 345680 }, { "epoch": 2.054853148349591, "grad_norm": 1.302415132522583, "learning_rate": 6.915524835608176e-05, "loss": 0.4855926513671875, "step": 345690 }, { "epoch": 2.0549125904262593, "grad_norm": 1.4092497825622559, "learning_rate": 6.91497016365964e-05, "loss": 0.4529071807861328, "step": 345700 }, { "epoch": 2.0549720325029277, "grad_norm": 1.4969161748886108, "learning_rate": 6.914415511252549e-05, "loss": 0.4931628227233887, "step": 345710 }, { "epoch": 2.055031474579596, "grad_norm": 1.4661650657653809, "learning_rate": 6.91386087838956e-05, "loss": 0.46747827529907227, "step": 345720 }, { "epoch": 2.055090916656264, "grad_norm": 1.4552435874938965, "learning_rate": 6.913306265073325e-05, "loss": 0.48218417167663574, "step": 345730 }, { "epoch": 2.0551503587329325, "grad_norm": 1.4576208591461182, "learning_rate": 6.912751671306497e-05, "loss": 0.5282738685607911, "step": 345740 }, { "epoch": 2.055209800809601, "grad_norm": 1.908015251159668, "learning_rate": 6.912197097091727e-05, "loss": 0.5487034797668457, "step": 345750 }, { "epoch": 2.0552692428862693, "grad_norm": 1.7414666414260864, "learning_rate": 6.911642542431671e-05, "loss": 0.4999698638916016, "step": 345760 }, { "epoch": 2.0553286849629377, "grad_norm": 1.2265561819076538, "learning_rate": 6.911088007328983e-05, "loss": 0.5125198364257812, "step": 345770 }, { "epoch": 2.055388127039606, "grad_norm": 1.4310591220855713, "learning_rate": 6.910533491786315e-05, "loss": 0.5093013286590576, "step": 345780 }, { "epoch": 2.0554475691162746, "grad_norm": 1.0707368850708008, "learning_rate": 6.909978995806317e-05, "loss": 0.5311933040618897, "step": 345790 }, { "epoch": 2.055507011192943, "grad_norm": 1.052483320236206, "learning_rate": 6.909424519391641e-05, "loss": 0.46364765167236327, "step": 345800 }, { "epoch": 2.0555664532696114, "grad_norm": 1.4553223848342896, "learning_rate": 6.908870062544943e-05, "loss": 0.5429973125457763, "step": 345810 }, { "epoch": 2.05562589534628, "grad_norm": 1.1003363132476807, "learning_rate": 6.90831562526887e-05, "loss": 0.4395054817199707, "step": 345820 }, { "epoch": 2.0556853374229482, "grad_norm": 1.4901291131973267, "learning_rate": 6.907761207566082e-05, "loss": 0.4805782318115234, "step": 345830 }, { "epoch": 2.0557447794996166, "grad_norm": 1.3662729263305664, "learning_rate": 6.907206809439226e-05, "loss": 0.4637126922607422, "step": 345840 }, { "epoch": 2.055804221576285, "grad_norm": 1.1861600875854492, "learning_rate": 6.906652430890955e-05, "loss": 0.528761339187622, "step": 345850 }, { "epoch": 2.0558636636529535, "grad_norm": 1.2432316541671753, "learning_rate": 6.906098071923922e-05, "loss": 0.5536580085754395, "step": 345860 }, { "epoch": 2.055923105729622, "grad_norm": 1.6778239011764526, "learning_rate": 6.905543732540778e-05, "loss": 0.5072908401489258, "step": 345870 }, { "epoch": 2.0559825478062903, "grad_norm": 1.3173052072525024, "learning_rate": 6.904989412744169e-05, "loss": 0.5173042297363282, "step": 345880 }, { "epoch": 2.0560419898829587, "grad_norm": 1.3493059873580933, "learning_rate": 6.904435112536759e-05, "loss": 0.5006655693054199, "step": 345890 }, { "epoch": 2.056101431959627, "grad_norm": 1.6461036205291748, "learning_rate": 6.903880831921192e-05, "loss": 0.5124162197113037, "step": 345900 }, { "epoch": 2.0561608740362955, "grad_norm": 1.377898097038269, "learning_rate": 6.903326570900119e-05, "loss": 0.49564809799194337, "step": 345910 }, { "epoch": 2.0562203161129635, "grad_norm": 1.356976866722107, "learning_rate": 6.902772329476195e-05, "loss": 0.5193836212158203, "step": 345920 }, { "epoch": 2.056279758189632, "grad_norm": 1.1941711902618408, "learning_rate": 6.902218107652067e-05, "loss": 0.4986430644989014, "step": 345930 }, { "epoch": 2.0563392002663003, "grad_norm": 1.3884313106536865, "learning_rate": 6.90166390543039e-05, "loss": 0.5004324913024902, "step": 345940 }, { "epoch": 2.0563986423429688, "grad_norm": 1.1504852771759033, "learning_rate": 6.90110972281381e-05, "loss": 0.44722542762756345, "step": 345950 }, { "epoch": 2.056458084419637, "grad_norm": 1.4353766441345215, "learning_rate": 6.900555559804985e-05, "loss": 0.5007802009582519, "step": 345960 }, { "epoch": 2.0565175264963056, "grad_norm": 1.4085099697113037, "learning_rate": 6.900001416406566e-05, "loss": 0.5074031829833985, "step": 345970 }, { "epoch": 2.056576968572974, "grad_norm": 1.7342469692230225, "learning_rate": 6.89944729262119e-05, "loss": 0.5825481414794922, "step": 345980 }, { "epoch": 2.0566364106496424, "grad_norm": 1.1821945905685425, "learning_rate": 6.898893188451527e-05, "loss": 0.4845921516418457, "step": 345990 }, { "epoch": 2.056695852726311, "grad_norm": 1.201410174369812, "learning_rate": 6.898339103900215e-05, "loss": 0.46277198791503904, "step": 346000 }, { "epoch": 2.0567552948029793, "grad_norm": 0.9987305998802185, "learning_rate": 6.897785038969906e-05, "loss": 0.47308931350708006, "step": 346010 }, { "epoch": 2.0568147368796477, "grad_norm": 1.592998743057251, "learning_rate": 6.897230993663257e-05, "loss": 0.5303413391113281, "step": 346020 }, { "epoch": 2.056874178956316, "grad_norm": 1.2360438108444214, "learning_rate": 6.896676967982915e-05, "loss": 0.5330877304077148, "step": 346030 }, { "epoch": 2.0569336210329845, "grad_norm": 1.491380214691162, "learning_rate": 6.896122961931531e-05, "loss": 0.5281063079833984, "step": 346040 }, { "epoch": 2.056993063109653, "grad_norm": 1.4939829111099243, "learning_rate": 6.895568975511745e-05, "loss": 0.614501667022705, "step": 346050 }, { "epoch": 2.0570525051863213, "grad_norm": 1.4420268535614014, "learning_rate": 6.895015008726221e-05, "loss": 0.5132514953613281, "step": 346060 }, { "epoch": 2.0571119472629897, "grad_norm": 1.296330451965332, "learning_rate": 6.894461061577604e-05, "loss": 0.489731502532959, "step": 346070 }, { "epoch": 2.057171389339658, "grad_norm": 1.3221687078475952, "learning_rate": 6.893907134068539e-05, "loss": 0.5539114952087403, "step": 346080 }, { "epoch": 2.0572308314163266, "grad_norm": 1.6627440452575684, "learning_rate": 6.893353226201689e-05, "loss": 0.46189346313476565, "step": 346090 }, { "epoch": 2.0572902734929945, "grad_norm": 1.4360029697418213, "learning_rate": 6.892799337979689e-05, "loss": 0.49754962921142576, "step": 346100 }, { "epoch": 2.057349715569663, "grad_norm": 1.3527826070785522, "learning_rate": 6.892245469405196e-05, "loss": 0.4816450595855713, "step": 346110 }, { "epoch": 2.0574091576463314, "grad_norm": 1.5591341257095337, "learning_rate": 6.891691620480858e-05, "loss": 0.5682179450988769, "step": 346120 }, { "epoch": 2.057468599723, "grad_norm": 1.4441241025924683, "learning_rate": 6.891137791209324e-05, "loss": 0.5503651142120362, "step": 346130 }, { "epoch": 2.057528041799668, "grad_norm": 1.1196932792663574, "learning_rate": 6.890583981593243e-05, "loss": 0.45181875228881835, "step": 346140 }, { "epoch": 2.0575874838763366, "grad_norm": 2.003915309906006, "learning_rate": 6.890030191635271e-05, "loss": 0.5282951354980469, "step": 346150 }, { "epoch": 2.057646925953005, "grad_norm": 1.6262279748916626, "learning_rate": 6.889476421338048e-05, "loss": 0.5049551486968994, "step": 346160 }, { "epoch": 2.0577063680296734, "grad_norm": 1.5035429000854492, "learning_rate": 6.888922670704227e-05, "loss": 0.4754513740539551, "step": 346170 }, { "epoch": 2.057765810106342, "grad_norm": 1.5644075870513916, "learning_rate": 6.888368939736451e-05, "loss": 0.5088828086853028, "step": 346180 }, { "epoch": 2.0578252521830103, "grad_norm": 1.4031013250350952, "learning_rate": 6.887815228437379e-05, "loss": 0.5146414756774902, "step": 346190 }, { "epoch": 2.0578846942596787, "grad_norm": 1.2495344877243042, "learning_rate": 6.887261536809657e-05, "loss": 0.4994443416595459, "step": 346200 }, { "epoch": 2.057944136336347, "grad_norm": 1.543439269065857, "learning_rate": 6.886707864855931e-05, "loss": 0.48476357460021974, "step": 346210 }, { "epoch": 2.0580035784130155, "grad_norm": 1.4610545635223389, "learning_rate": 6.886154212578848e-05, "loss": 0.5604063987731933, "step": 346220 }, { "epoch": 2.058063020489684, "grad_norm": 1.1639493703842163, "learning_rate": 6.88560057998106e-05, "loss": 0.5157313346862793, "step": 346230 }, { "epoch": 2.0581224625663523, "grad_norm": 1.6589505672454834, "learning_rate": 6.885046967065212e-05, "loss": 0.5131651401519776, "step": 346240 }, { "epoch": 2.0581819046430208, "grad_norm": 1.1373512744903564, "learning_rate": 6.884493373833956e-05, "loss": 0.49725971221923826, "step": 346250 }, { "epoch": 2.058241346719689, "grad_norm": 1.3200170993804932, "learning_rate": 6.883939800289939e-05, "loss": 0.5011796951293945, "step": 346260 }, { "epoch": 2.0583007887963576, "grad_norm": 1.2960140705108643, "learning_rate": 6.88338624643581e-05, "loss": 0.47478222846984863, "step": 346270 }, { "epoch": 2.058360230873026, "grad_norm": 1.6475495100021362, "learning_rate": 6.882832712274217e-05, "loss": 0.4846169471740723, "step": 346280 }, { "epoch": 2.058419672949694, "grad_norm": 1.5376616716384888, "learning_rate": 6.882279197807803e-05, "loss": 0.5095355033874511, "step": 346290 }, { "epoch": 2.0584791150263624, "grad_norm": 1.414940357208252, "learning_rate": 6.881725703039224e-05, "loss": 0.46324901580810546, "step": 346300 }, { "epoch": 2.058538557103031, "grad_norm": 0.9794275164604187, "learning_rate": 6.881172227971118e-05, "loss": 0.4753389358520508, "step": 346310 }, { "epoch": 2.058597999179699, "grad_norm": 1.5639824867248535, "learning_rate": 6.88061877260614e-05, "loss": 0.5342375278472901, "step": 346320 }, { "epoch": 2.0586574412563676, "grad_norm": 1.9029556512832642, "learning_rate": 6.880065336946937e-05, "loss": 0.5216439247131348, "step": 346330 }, { "epoch": 2.058716883333036, "grad_norm": 1.4070792198181152, "learning_rate": 6.879511920996156e-05, "loss": 0.508448314666748, "step": 346340 }, { "epoch": 2.0587763254097045, "grad_norm": 1.6700940132141113, "learning_rate": 6.878958524756442e-05, "loss": 0.49938035011291504, "step": 346350 }, { "epoch": 2.058835767486373, "grad_norm": 1.750943899154663, "learning_rate": 6.878405148230443e-05, "loss": 0.5028227806091309, "step": 346360 }, { "epoch": 2.0588952095630413, "grad_norm": 1.442342758178711, "learning_rate": 6.877851791420805e-05, "loss": 0.5489839076995849, "step": 346370 }, { "epoch": 2.0589546516397097, "grad_norm": 1.2456821203231812, "learning_rate": 6.877298454330178e-05, "loss": 0.5272984504699707, "step": 346380 }, { "epoch": 2.059014093716378, "grad_norm": 1.2247358560562134, "learning_rate": 6.876745136961211e-05, "loss": 0.5006307601928711, "step": 346390 }, { "epoch": 2.0590735357930465, "grad_norm": 1.3454043865203857, "learning_rate": 6.876191839316546e-05, "loss": 0.576483154296875, "step": 346400 }, { "epoch": 2.059132977869715, "grad_norm": 1.502812147140503, "learning_rate": 6.875638561398832e-05, "loss": 0.5370874404907227, "step": 346410 }, { "epoch": 2.0591924199463834, "grad_norm": 1.330849528312683, "learning_rate": 6.875085303210714e-05, "loss": 0.5149873733520508, "step": 346420 }, { "epoch": 2.0592518620230518, "grad_norm": 1.7586021423339844, "learning_rate": 6.874532064754842e-05, "loss": 0.4505134582519531, "step": 346430 }, { "epoch": 2.05931130409972, "grad_norm": 1.2754874229431152, "learning_rate": 6.873978846033856e-05, "loss": 0.4858360290527344, "step": 346440 }, { "epoch": 2.0593707461763886, "grad_norm": 1.681097388267517, "learning_rate": 6.87342564705041e-05, "loss": 0.4873509407043457, "step": 346450 }, { "epoch": 2.059430188253057, "grad_norm": 1.3277033567428589, "learning_rate": 6.872872467807151e-05, "loss": 0.523678207397461, "step": 346460 }, { "epoch": 2.059489630329725, "grad_norm": 1.85535728931427, "learning_rate": 6.872319308306714e-05, "loss": 0.5318531036376953, "step": 346470 }, { "epoch": 2.0595490724063934, "grad_norm": 1.343698263168335, "learning_rate": 6.871766168551755e-05, "loss": 0.4775416374206543, "step": 346480 }, { "epoch": 2.059608514483062, "grad_norm": 1.573776125907898, "learning_rate": 6.87121304854492e-05, "loss": 0.5200146198272705, "step": 346490 }, { "epoch": 2.0596679565597302, "grad_norm": 1.1646733283996582, "learning_rate": 6.870659948288846e-05, "loss": 0.5035299301147461, "step": 346500 }, { "epoch": 2.0597273986363986, "grad_norm": 1.3898475170135498, "learning_rate": 6.870106867786192e-05, "loss": 0.5117945671081543, "step": 346510 }, { "epoch": 2.059786840713067, "grad_norm": 1.228691577911377, "learning_rate": 6.8695538070396e-05, "loss": 0.5229375839233399, "step": 346520 }, { "epoch": 2.0598462827897355, "grad_norm": 1.463731288909912, "learning_rate": 6.869000766051707e-05, "loss": 0.5321325302124024, "step": 346530 }, { "epoch": 2.059905724866404, "grad_norm": 1.3335448503494263, "learning_rate": 6.868447744825161e-05, "loss": 0.5066135883331299, "step": 346540 }, { "epoch": 2.0599651669430723, "grad_norm": 1.1221932172775269, "learning_rate": 6.867894743362618e-05, "loss": 0.5190589904785157, "step": 346550 }, { "epoch": 2.0600246090197407, "grad_norm": 1.2478022575378418, "learning_rate": 6.867341761666712e-05, "loss": 0.49666609764099123, "step": 346560 }, { "epoch": 2.060084051096409, "grad_norm": 1.3730109930038452, "learning_rate": 6.86678879974009e-05, "loss": 0.4858811378479004, "step": 346570 }, { "epoch": 2.0601434931730775, "grad_norm": 1.3682194948196411, "learning_rate": 6.866235857585408e-05, "loss": 0.4773849964141846, "step": 346580 }, { "epoch": 2.060202935249746, "grad_norm": 1.4693666696548462, "learning_rate": 6.865682935205298e-05, "loss": 0.5239010810852051, "step": 346590 }, { "epoch": 2.0602623773264144, "grad_norm": 1.1473004817962646, "learning_rate": 6.865130032602408e-05, "loss": 0.523466157913208, "step": 346600 }, { "epoch": 2.060321819403083, "grad_norm": 1.6794657707214355, "learning_rate": 6.864577149779385e-05, "loss": 0.5536458969116211, "step": 346610 }, { "epoch": 2.060381261479751, "grad_norm": 1.5352126359939575, "learning_rate": 6.864024286738875e-05, "loss": 0.4639717102050781, "step": 346620 }, { "epoch": 2.0604407035564196, "grad_norm": 1.1613727807998657, "learning_rate": 6.863471443483518e-05, "loss": 0.4776917934417725, "step": 346630 }, { "epoch": 2.060500145633088, "grad_norm": 1.8624331951141357, "learning_rate": 6.862918620015968e-05, "loss": 0.5162217140197753, "step": 346640 }, { "epoch": 2.0605595877097564, "grad_norm": 1.5387159585952759, "learning_rate": 6.86236581633886e-05, "loss": 0.4519293785095215, "step": 346650 }, { "epoch": 2.0606190297864244, "grad_norm": 1.5633963346481323, "learning_rate": 6.861813032454845e-05, "loss": 0.5040741920471191, "step": 346660 }, { "epoch": 2.060678471863093, "grad_norm": 1.2775442600250244, "learning_rate": 6.861260268366556e-05, "loss": 0.5564507961273193, "step": 346670 }, { "epoch": 2.0607379139397612, "grad_norm": 1.2087817192077637, "learning_rate": 6.86070752407665e-05, "loss": 0.5067963123321533, "step": 346680 }, { "epoch": 2.0607973560164297, "grad_norm": 1.5153603553771973, "learning_rate": 6.860154799587767e-05, "loss": 0.5328206062316895, "step": 346690 }, { "epoch": 2.060856798093098, "grad_norm": 1.8279978036880493, "learning_rate": 6.859602094902552e-05, "loss": 0.4794417381286621, "step": 346700 }, { "epoch": 2.0609162401697665, "grad_norm": 1.8712037801742554, "learning_rate": 6.859049410023645e-05, "loss": 0.5648533821105957, "step": 346710 }, { "epoch": 2.060975682246435, "grad_norm": 1.7166779041290283, "learning_rate": 6.858496744953692e-05, "loss": 0.5066633224487305, "step": 346720 }, { "epoch": 2.0610351243231033, "grad_norm": 1.322925329208374, "learning_rate": 6.857944099695337e-05, "loss": 0.5467133522033691, "step": 346730 }, { "epoch": 2.0610945663997717, "grad_norm": 1.0749919414520264, "learning_rate": 6.857391474251224e-05, "loss": 0.49749345779418946, "step": 346740 }, { "epoch": 2.06115400847644, "grad_norm": 1.5836296081542969, "learning_rate": 6.856838868623998e-05, "loss": 0.528172779083252, "step": 346750 }, { "epoch": 2.0612134505531086, "grad_norm": 1.3262674808502197, "learning_rate": 6.8562862828163e-05, "loss": 0.46239185333251953, "step": 346760 }, { "epoch": 2.061272892629777, "grad_norm": 1.1838542222976685, "learning_rate": 6.855733716830776e-05, "loss": 0.5267477989196777, "step": 346770 }, { "epoch": 2.0613323347064454, "grad_norm": 1.261686086654663, "learning_rate": 6.855181170670066e-05, "loss": 0.4767104148864746, "step": 346780 }, { "epoch": 2.061391776783114, "grad_norm": 1.7247344255447388, "learning_rate": 6.854628644336816e-05, "loss": 0.5393214702606202, "step": 346790 }, { "epoch": 2.061451218859782, "grad_norm": 1.292519211769104, "learning_rate": 6.854076137833663e-05, "loss": 0.5325428009033203, "step": 346800 }, { "epoch": 2.0615106609364506, "grad_norm": 1.533693790435791, "learning_rate": 6.853523651163258e-05, "loss": 0.544529390335083, "step": 346810 }, { "epoch": 2.061570103013119, "grad_norm": 1.065883994102478, "learning_rate": 6.85297118432824e-05, "loss": 0.4759822368621826, "step": 346820 }, { "epoch": 2.0616295450897875, "grad_norm": 1.4808905124664307, "learning_rate": 6.852418737331255e-05, "loss": 0.5009024143218994, "step": 346830 }, { "epoch": 2.0616889871664554, "grad_norm": 1.7626856565475464, "learning_rate": 6.851866310174941e-05, "loss": 0.5256853103637695, "step": 346840 }, { "epoch": 2.061748429243124, "grad_norm": 1.5827518701553345, "learning_rate": 6.851313902861945e-05, "loss": 0.5630673408508301, "step": 346850 }, { "epoch": 2.0618078713197923, "grad_norm": 1.3112294673919678, "learning_rate": 6.850761515394903e-05, "loss": 0.46486215591430663, "step": 346860 }, { "epoch": 2.0618673133964607, "grad_norm": 1.8264312744140625, "learning_rate": 6.850209147776467e-05, "loss": 0.5168896198272706, "step": 346870 }, { "epoch": 2.061926755473129, "grad_norm": 1.6017184257507324, "learning_rate": 6.849656800009272e-05, "loss": 0.49901561737060546, "step": 346880 }, { "epoch": 2.0619861975497975, "grad_norm": 1.554067850112915, "learning_rate": 6.849104472095965e-05, "loss": 0.5296453475952149, "step": 346890 }, { "epoch": 2.062045639626466, "grad_norm": 1.4900721311569214, "learning_rate": 6.848552164039183e-05, "loss": 0.4901705741882324, "step": 346900 }, { "epoch": 2.0621050817031343, "grad_norm": 1.1641768217086792, "learning_rate": 6.847999875841573e-05, "loss": 0.5126096725463867, "step": 346910 }, { "epoch": 2.0621645237798027, "grad_norm": 1.7933053970336914, "learning_rate": 6.847447607505773e-05, "loss": 0.5184975147247315, "step": 346920 }, { "epoch": 2.062223965856471, "grad_norm": 1.2425605058670044, "learning_rate": 6.846895359034424e-05, "loss": 0.4920839309692383, "step": 346930 }, { "epoch": 2.0622834079331396, "grad_norm": 1.8637466430664062, "learning_rate": 6.846343130430173e-05, "loss": 0.5251888275146485, "step": 346940 }, { "epoch": 2.062342850009808, "grad_norm": 1.4947247505187988, "learning_rate": 6.845790921695659e-05, "loss": 0.5072609901428222, "step": 346950 }, { "epoch": 2.0624022920864764, "grad_norm": 1.3305312395095825, "learning_rate": 6.845238732833526e-05, "loss": 0.47434296607971194, "step": 346960 }, { "epoch": 2.062461734163145, "grad_norm": 1.336633324623108, "learning_rate": 6.844686563846411e-05, "loss": 0.49566149711608887, "step": 346970 }, { "epoch": 2.0625211762398132, "grad_norm": 1.136025071144104, "learning_rate": 6.844134414736957e-05, "loss": 0.5175214290618897, "step": 346980 }, { "epoch": 2.0625806183164817, "grad_norm": 1.1609914302825928, "learning_rate": 6.843582285507804e-05, "loss": 0.4708672523498535, "step": 346990 }, { "epoch": 2.06264006039315, "grad_norm": 1.1920028924942017, "learning_rate": 6.843030176161597e-05, "loss": 0.5057437896728516, "step": 347000 }, { "epoch": 2.0626995024698185, "grad_norm": 1.3155282735824585, "learning_rate": 6.84247808670098e-05, "loss": 0.483624267578125, "step": 347010 }, { "epoch": 2.062758944546487, "grad_norm": 1.4326484203338623, "learning_rate": 6.841926017128585e-05, "loss": 0.492723274230957, "step": 347020 }, { "epoch": 2.062818386623155, "grad_norm": 1.3100855350494385, "learning_rate": 6.841373967447053e-05, "loss": 0.5138067245483399, "step": 347030 }, { "epoch": 2.0628778286998233, "grad_norm": 1.3237547874450684, "learning_rate": 6.840821937659033e-05, "loss": 0.510244083404541, "step": 347040 }, { "epoch": 2.0629372707764917, "grad_norm": 1.597112774848938, "learning_rate": 6.840269927767163e-05, "loss": 0.46387014389038084, "step": 347050 }, { "epoch": 2.06299671285316, "grad_norm": 1.4460508823394775, "learning_rate": 6.839717937774076e-05, "loss": 0.44304866790771485, "step": 347060 }, { "epoch": 2.0630561549298285, "grad_norm": 1.398262619972229, "learning_rate": 6.839165967682426e-05, "loss": 0.5116640090942383, "step": 347070 }, { "epoch": 2.063115597006497, "grad_norm": 1.1003103256225586, "learning_rate": 6.838614017494844e-05, "loss": 0.4775865077972412, "step": 347080 }, { "epoch": 2.0631750390831654, "grad_norm": 1.1439871788024902, "learning_rate": 6.838062087213969e-05, "loss": 0.4992481231689453, "step": 347090 }, { "epoch": 2.0632344811598338, "grad_norm": 1.4644585847854614, "learning_rate": 6.837510176842448e-05, "loss": 0.5205373764038086, "step": 347100 }, { "epoch": 2.063293923236502, "grad_norm": 1.4605990648269653, "learning_rate": 6.836958286382919e-05, "loss": 0.48742876052856443, "step": 347110 }, { "epoch": 2.0633533653131706, "grad_norm": 1.370385766029358, "learning_rate": 6.836406415838017e-05, "loss": 0.5068423271179199, "step": 347120 }, { "epoch": 2.063412807389839, "grad_norm": 1.213326096534729, "learning_rate": 6.835854565210392e-05, "loss": 0.4897589206695557, "step": 347130 }, { "epoch": 2.0634722494665074, "grad_norm": 1.5139553546905518, "learning_rate": 6.835302734502676e-05, "loss": 0.5272859096527099, "step": 347140 }, { "epoch": 2.063531691543176, "grad_norm": 1.423705816268921, "learning_rate": 6.83475092371751e-05, "loss": 0.5091904640197754, "step": 347150 }, { "epoch": 2.0635911336198443, "grad_norm": 1.3468455076217651, "learning_rate": 6.83419913285753e-05, "loss": 0.49790124893188475, "step": 347160 }, { "epoch": 2.0636505756965127, "grad_norm": 1.5790636539459229, "learning_rate": 6.833647361925383e-05, "loss": 0.5359047889709473, "step": 347170 }, { "epoch": 2.063710017773181, "grad_norm": 1.473490595817566, "learning_rate": 6.833095610923708e-05, "loss": 0.5101313591003418, "step": 347180 }, { "epoch": 2.0637694598498495, "grad_norm": 2.362827777862549, "learning_rate": 6.83254387985514e-05, "loss": 0.5128014564514161, "step": 347190 }, { "epoch": 2.063828901926518, "grad_norm": 1.1357554197311401, "learning_rate": 6.831992168722321e-05, "loss": 0.4893194198608398, "step": 347200 }, { "epoch": 2.063888344003186, "grad_norm": 1.6092438697814941, "learning_rate": 6.831440477527888e-05, "loss": 0.5221401214599609, "step": 347210 }, { "epoch": 2.0639477860798543, "grad_norm": 1.4031288623809814, "learning_rate": 6.83088880627448e-05, "loss": 0.5472118854522705, "step": 347220 }, { "epoch": 2.0640072281565227, "grad_norm": 1.288987398147583, "learning_rate": 6.830337154964739e-05, "loss": 0.5045958042144776, "step": 347230 }, { "epoch": 2.064066670233191, "grad_norm": 1.418376088142395, "learning_rate": 6.829785523601303e-05, "loss": 0.5175709247589111, "step": 347240 }, { "epoch": 2.0641261123098595, "grad_norm": 1.5353094339370728, "learning_rate": 6.829233912186812e-05, "loss": 0.5552412986755371, "step": 347250 }, { "epoch": 2.064185554386528, "grad_norm": 1.3255842924118042, "learning_rate": 6.8286823207239e-05, "loss": 0.5182630538940429, "step": 347260 }, { "epoch": 2.0642449964631964, "grad_norm": 1.526421070098877, "learning_rate": 6.82813074921521e-05, "loss": 0.5024764537811279, "step": 347270 }, { "epoch": 2.064304438539865, "grad_norm": 1.3661646842956543, "learning_rate": 6.827579197663379e-05, "loss": 0.4802964687347412, "step": 347280 }, { "epoch": 2.064363880616533, "grad_norm": 1.4776852130889893, "learning_rate": 6.827027666071042e-05, "loss": 0.49199872016906737, "step": 347290 }, { "epoch": 2.0644233226932016, "grad_norm": 1.5429145097732544, "learning_rate": 6.826476154440845e-05, "loss": 0.4671992301940918, "step": 347300 }, { "epoch": 2.06448276476987, "grad_norm": 1.3886539936065674, "learning_rate": 6.825924662775421e-05, "loss": 0.5179081916809082, "step": 347310 }, { "epoch": 2.0645422068465384, "grad_norm": 1.4309242963790894, "learning_rate": 6.825373191077409e-05, "loss": 0.5387483596801758, "step": 347320 }, { "epoch": 2.064601648923207, "grad_norm": 1.9082975387573242, "learning_rate": 6.824821739349451e-05, "loss": 0.5339070320129394, "step": 347330 }, { "epoch": 2.0646610909998753, "grad_norm": 1.3122392892837524, "learning_rate": 6.824270307594179e-05, "loss": 0.5052197933197021, "step": 347340 }, { "epoch": 2.0647205330765437, "grad_norm": 1.0640625953674316, "learning_rate": 6.823718895814228e-05, "loss": 0.48938469886779784, "step": 347350 }, { "epoch": 2.064779975153212, "grad_norm": 1.0574135780334473, "learning_rate": 6.823167504012246e-05, "loss": 0.492965030670166, "step": 347360 }, { "epoch": 2.0648394172298805, "grad_norm": 1.487390398979187, "learning_rate": 6.822616132190867e-05, "loss": 0.5279570102691651, "step": 347370 }, { "epoch": 2.064898859306549, "grad_norm": 1.15875244140625, "learning_rate": 6.822064780352725e-05, "loss": 0.5055489540100098, "step": 347380 }, { "epoch": 2.064958301383217, "grad_norm": 1.2147477865219116, "learning_rate": 6.821513448500459e-05, "loss": 0.49608449935913085, "step": 347390 }, { "epoch": 2.0650177434598853, "grad_norm": 1.6987625360488892, "learning_rate": 6.82096213663671e-05, "loss": 0.5276907920837403, "step": 347400 }, { "epoch": 2.0650771855365537, "grad_norm": 1.3656383752822876, "learning_rate": 6.820410844764111e-05, "loss": 0.5775869846343994, "step": 347410 }, { "epoch": 2.065136627613222, "grad_norm": 1.3488266468048096, "learning_rate": 6.819859572885297e-05, "loss": 0.5516983985900878, "step": 347420 }, { "epoch": 2.0651960696898906, "grad_norm": 1.35293710231781, "learning_rate": 6.819308321002913e-05, "loss": 0.5419817447662354, "step": 347430 }, { "epoch": 2.065255511766559, "grad_norm": 1.3719674348831177, "learning_rate": 6.818757089119589e-05, "loss": 0.4981266975402832, "step": 347440 }, { "epoch": 2.0653149538432274, "grad_norm": 1.315316915512085, "learning_rate": 6.818205877237968e-05, "loss": 0.5296670913696289, "step": 347450 }, { "epoch": 2.065374395919896, "grad_norm": 1.2485840320587158, "learning_rate": 6.817654685360682e-05, "loss": 0.48685684204101565, "step": 347460 }, { "epoch": 2.065433837996564, "grad_norm": 1.5177291631698608, "learning_rate": 6.81710351349037e-05, "loss": 0.5370706558227539, "step": 347470 }, { "epoch": 2.0654932800732326, "grad_norm": 1.4488919973373413, "learning_rate": 6.816552361629664e-05, "loss": 0.5140811920166015, "step": 347480 }, { "epoch": 2.065552722149901, "grad_norm": 1.2487186193466187, "learning_rate": 6.816001229781207e-05, "loss": 0.5010943412780762, "step": 347490 }, { "epoch": 2.0656121642265695, "grad_norm": 1.026619791984558, "learning_rate": 6.815450117947632e-05, "loss": 0.517568302154541, "step": 347500 }, { "epoch": 2.065671606303238, "grad_norm": 1.3360196352005005, "learning_rate": 6.814899026131583e-05, "loss": 0.5269148826599122, "step": 347510 }, { "epoch": 2.0657310483799063, "grad_norm": 1.1740461587905884, "learning_rate": 6.814347954335681e-05, "loss": 0.5169055938720704, "step": 347520 }, { "epoch": 2.0657904904565747, "grad_norm": 1.506295084953308, "learning_rate": 6.813796902562572e-05, "loss": 0.522836971282959, "step": 347530 }, { "epoch": 2.065849932533243, "grad_norm": 1.2862640619277954, "learning_rate": 6.813245870814892e-05, "loss": 0.4841106414794922, "step": 347540 }, { "epoch": 2.0659093746099115, "grad_norm": 1.4232820272445679, "learning_rate": 6.812694859095271e-05, "loss": 0.4919546604156494, "step": 347550 }, { "epoch": 2.06596881668658, "grad_norm": 1.2943949699401855, "learning_rate": 6.812143867406354e-05, "loss": 0.5281798362731933, "step": 347560 }, { "epoch": 2.0660282587632484, "grad_norm": 1.3252614736557007, "learning_rate": 6.811592895750775e-05, "loss": 0.48111858367919924, "step": 347570 }, { "epoch": 2.0660877008399163, "grad_norm": 1.2724679708480835, "learning_rate": 6.81104194413116e-05, "loss": 0.45517120361328123, "step": 347580 }, { "epoch": 2.0661471429165847, "grad_norm": 1.3189985752105713, "learning_rate": 6.810491012550156e-05, "loss": 0.47884349822998046, "step": 347590 }, { "epoch": 2.066206584993253, "grad_norm": 1.1811318397521973, "learning_rate": 6.809940101010392e-05, "loss": 0.49611601829528806, "step": 347600 }, { "epoch": 2.0662660270699216, "grad_norm": 1.3961739540100098, "learning_rate": 6.809389209514503e-05, "loss": 0.51644868850708, "step": 347610 }, { "epoch": 2.06632546914659, "grad_norm": 1.548214316368103, "learning_rate": 6.808838338065134e-05, "loss": 0.4874439239501953, "step": 347620 }, { "epoch": 2.0663849112232584, "grad_norm": 1.2858548164367676, "learning_rate": 6.808287486664909e-05, "loss": 0.530545425415039, "step": 347630 }, { "epoch": 2.066444353299927, "grad_norm": 1.7609716653823853, "learning_rate": 6.807736655316463e-05, "loss": 0.4774310111999512, "step": 347640 }, { "epoch": 2.0665037953765952, "grad_norm": 1.4807754755020142, "learning_rate": 6.807185844022436e-05, "loss": 0.4622373580932617, "step": 347650 }, { "epoch": 2.0665632374532636, "grad_norm": 1.130947470664978, "learning_rate": 6.806635052785462e-05, "loss": 0.5175701141357422, "step": 347660 }, { "epoch": 2.066622679529932, "grad_norm": 1.1557210683822632, "learning_rate": 6.80608428160818e-05, "loss": 0.46199564933776854, "step": 347670 }, { "epoch": 2.0666821216066005, "grad_norm": 1.9698234796524048, "learning_rate": 6.805533530493216e-05, "loss": 0.5592844963073731, "step": 347680 }, { "epoch": 2.066741563683269, "grad_norm": 1.442577838897705, "learning_rate": 6.804982799443209e-05, "loss": 0.486011266708374, "step": 347690 }, { "epoch": 2.0668010057599373, "grad_norm": 1.1451194286346436, "learning_rate": 6.804432088460795e-05, "loss": 0.4940945148468018, "step": 347700 }, { "epoch": 2.0668604478366057, "grad_norm": 1.6348121166229248, "learning_rate": 6.803881397548604e-05, "loss": 0.5337515830993652, "step": 347710 }, { "epoch": 2.066919889913274, "grad_norm": 1.188503384590149, "learning_rate": 6.803330726709274e-05, "loss": 0.4974983215332031, "step": 347720 }, { "epoch": 2.0669793319899425, "grad_norm": 1.4876999855041504, "learning_rate": 6.80278007594544e-05, "loss": 0.5011127471923829, "step": 347730 }, { "epoch": 2.067038774066611, "grad_norm": 1.5875989198684692, "learning_rate": 6.802229445259735e-05, "loss": 0.5341537475585938, "step": 347740 }, { "epoch": 2.0670982161432794, "grad_norm": 1.3476437330245972, "learning_rate": 6.80167883465479e-05, "loss": 0.48987793922424316, "step": 347750 }, { "epoch": 2.067157658219948, "grad_norm": 1.0464820861816406, "learning_rate": 6.801128244133243e-05, "loss": 0.5181648254394531, "step": 347760 }, { "epoch": 2.0672171002966158, "grad_norm": 1.5370930433273315, "learning_rate": 6.800577673697726e-05, "loss": 0.46502056121826174, "step": 347770 }, { "epoch": 2.067276542373284, "grad_norm": 1.3340113162994385, "learning_rate": 6.80002712335087e-05, "loss": 0.5136010646820068, "step": 347780 }, { "epoch": 2.0673359844499526, "grad_norm": 0.9812209010124207, "learning_rate": 6.799476593095316e-05, "loss": 0.5240347862243653, "step": 347790 }, { "epoch": 2.067395426526621, "grad_norm": 2.2529187202453613, "learning_rate": 6.798926082933692e-05, "loss": 0.5424001693725586, "step": 347800 }, { "epoch": 2.0674548686032894, "grad_norm": 1.480589747428894, "learning_rate": 6.798375592868634e-05, "loss": 0.5180869102478027, "step": 347810 }, { "epoch": 2.067514310679958, "grad_norm": 1.645952582359314, "learning_rate": 6.797825122902771e-05, "loss": 0.47264604568481444, "step": 347820 }, { "epoch": 2.0675737527566262, "grad_norm": 1.5675030946731567, "learning_rate": 6.797274673038741e-05, "loss": 0.5403307437896728, "step": 347830 }, { "epoch": 2.0676331948332947, "grad_norm": 1.3633451461791992, "learning_rate": 6.796724243279173e-05, "loss": 0.5211055755615235, "step": 347840 }, { "epoch": 2.067692636909963, "grad_norm": 1.6503602266311646, "learning_rate": 6.796173833626707e-05, "loss": 0.5567957401275635, "step": 347850 }, { "epoch": 2.0677520789866315, "grad_norm": 1.4148434400558472, "learning_rate": 6.795623444083969e-05, "loss": 0.5031897544860839, "step": 347860 }, { "epoch": 2.0678115210633, "grad_norm": 0.9704044461250305, "learning_rate": 6.795073074653595e-05, "loss": 0.5604086875915527, "step": 347870 }, { "epoch": 2.0678709631399683, "grad_norm": 1.5481321811676025, "learning_rate": 6.794522725338217e-05, "loss": 0.5315382480621338, "step": 347880 }, { "epoch": 2.0679304052166367, "grad_norm": 1.601033091545105, "learning_rate": 6.793972396140469e-05, "loss": 0.5323457717895508, "step": 347890 }, { "epoch": 2.067989847293305, "grad_norm": 1.3072435855865479, "learning_rate": 6.793422087062981e-05, "loss": 0.5019612789154053, "step": 347900 }, { "epoch": 2.0680492893699736, "grad_norm": 1.471948266029358, "learning_rate": 6.792871798108384e-05, "loss": 0.4852293968200684, "step": 347910 }, { "epoch": 2.068108731446642, "grad_norm": 1.5297553539276123, "learning_rate": 6.792321529279319e-05, "loss": 0.48043508529663087, "step": 347920 }, { "epoch": 2.0681681735233104, "grad_norm": 1.3187578916549683, "learning_rate": 6.79177128057841e-05, "loss": 0.47324771881103517, "step": 347930 }, { "epoch": 2.068227615599979, "grad_norm": 1.2119561433792114, "learning_rate": 6.791221052008294e-05, "loss": 0.46221127510070803, "step": 347940 }, { "epoch": 2.068287057676647, "grad_norm": 1.0135469436645508, "learning_rate": 6.7906708435716e-05, "loss": 0.4685211181640625, "step": 347950 }, { "epoch": 2.068346499753315, "grad_norm": 1.3146708011627197, "learning_rate": 6.790120655270961e-05, "loss": 0.5080599308013916, "step": 347960 }, { "epoch": 2.0684059418299836, "grad_norm": 1.0226106643676758, "learning_rate": 6.789570487109006e-05, "loss": 0.5329305171966553, "step": 347970 }, { "epoch": 2.068465383906652, "grad_norm": 1.3225375413894653, "learning_rate": 6.789020339088373e-05, "loss": 0.5115663051605225, "step": 347980 }, { "epoch": 2.0685248259833204, "grad_norm": 1.6398066282272339, "learning_rate": 6.78847021121169e-05, "loss": 0.46865124702453614, "step": 347990 }, { "epoch": 2.068584268059989, "grad_norm": 1.7170697450637817, "learning_rate": 6.787920103481593e-05, "loss": 0.5458335876464844, "step": 348000 }, { "epoch": 2.0686437101366573, "grad_norm": 1.3646198511123657, "learning_rate": 6.787370015900703e-05, "loss": 0.4888165950775146, "step": 348010 }, { "epoch": 2.0687031522133257, "grad_norm": 1.0798643827438354, "learning_rate": 6.786819948471661e-05, "loss": 0.47949934005737305, "step": 348020 }, { "epoch": 2.068762594289994, "grad_norm": 1.3545998334884644, "learning_rate": 6.786269901197098e-05, "loss": 0.5057002067565918, "step": 348030 }, { "epoch": 2.0688220363666625, "grad_norm": 1.4318033456802368, "learning_rate": 6.785719874079636e-05, "loss": 0.4497998237609863, "step": 348040 }, { "epoch": 2.068881478443331, "grad_norm": 1.6129800081253052, "learning_rate": 6.785169867121917e-05, "loss": 0.5136631011962891, "step": 348050 }, { "epoch": 2.0689409205199993, "grad_norm": 1.176506757736206, "learning_rate": 6.784619880326573e-05, "loss": 0.4840378284454346, "step": 348060 }, { "epoch": 2.0690003625966678, "grad_norm": 1.9003703594207764, "learning_rate": 6.784069913696223e-05, "loss": 0.5994531631469726, "step": 348070 }, { "epoch": 2.069059804673336, "grad_norm": 1.328871250152588, "learning_rate": 6.783519967233505e-05, "loss": 0.5262641906738281, "step": 348080 }, { "epoch": 2.0691192467500046, "grad_norm": 1.3908363580703735, "learning_rate": 6.782970040941053e-05, "loss": 0.5254496574401856, "step": 348090 }, { "epoch": 2.069178688826673, "grad_norm": 1.646676778793335, "learning_rate": 6.782420134821488e-05, "loss": 0.47955522537231443, "step": 348100 }, { "epoch": 2.0692381309033414, "grad_norm": 1.4404641389846802, "learning_rate": 6.781870248877453e-05, "loss": 0.4994077682495117, "step": 348110 }, { "epoch": 2.06929757298001, "grad_norm": 1.334900975227356, "learning_rate": 6.781320383111573e-05, "loss": 0.4632591247558594, "step": 348120 }, { "epoch": 2.069357015056678, "grad_norm": 1.4226187467575073, "learning_rate": 6.780770537526477e-05, "loss": 0.4916386604309082, "step": 348130 }, { "epoch": 2.069416457133346, "grad_norm": 1.5415709018707275, "learning_rate": 6.780220712124791e-05, "loss": 0.48919038772583007, "step": 348140 }, { "epoch": 2.0694758992100146, "grad_norm": 1.610541582107544, "learning_rate": 6.779670906909153e-05, "loss": 0.5661272525787353, "step": 348150 }, { "epoch": 2.069535341286683, "grad_norm": 1.6542719602584839, "learning_rate": 6.779121121882191e-05, "loss": 0.5065448760986329, "step": 348160 }, { "epoch": 2.0695947833633515, "grad_norm": 1.2687785625457764, "learning_rate": 6.77857135704653e-05, "loss": 0.5190959930419922, "step": 348170 }, { "epoch": 2.06965422544002, "grad_norm": 1.3940757513046265, "learning_rate": 6.77802161240481e-05, "loss": 0.47054166793823243, "step": 348180 }, { "epoch": 2.0697136675166883, "grad_norm": 1.3379086256027222, "learning_rate": 6.777471887959654e-05, "loss": 0.48929595947265625, "step": 348190 }, { "epoch": 2.0697731095933567, "grad_norm": 1.4337321519851685, "learning_rate": 6.776922183713687e-05, "loss": 0.5468055725097656, "step": 348200 }, { "epoch": 2.069832551670025, "grad_norm": 1.5343502759933472, "learning_rate": 6.776372499669547e-05, "loss": 0.5258880138397217, "step": 348210 }, { "epoch": 2.0698919937466935, "grad_norm": 1.234840750694275, "learning_rate": 6.775822835829863e-05, "loss": 0.49500484466552735, "step": 348220 }, { "epoch": 2.069951435823362, "grad_norm": 1.8276921510696411, "learning_rate": 6.775273192197263e-05, "loss": 0.5183667659759521, "step": 348230 }, { "epoch": 2.0700108779000304, "grad_norm": 1.3903671503067017, "learning_rate": 6.774723568774371e-05, "loss": 0.5490468978881836, "step": 348240 }, { "epoch": 2.0700703199766988, "grad_norm": 1.361922025680542, "learning_rate": 6.774173965563824e-05, "loss": 0.4503644943237305, "step": 348250 }, { "epoch": 2.070129762053367, "grad_norm": 1.2790712118148804, "learning_rate": 6.773624382568247e-05, "loss": 0.5197573661804199, "step": 348260 }, { "epoch": 2.0701892041300356, "grad_norm": 1.4062119722366333, "learning_rate": 6.773074819790266e-05, "loss": 0.4880612850189209, "step": 348270 }, { "epoch": 2.070248646206704, "grad_norm": 1.2644431591033936, "learning_rate": 6.772525277232517e-05, "loss": 0.5191318035125733, "step": 348280 }, { "epoch": 2.0703080882833724, "grad_norm": 1.3817869424819946, "learning_rate": 6.771975754897626e-05, "loss": 0.5173789024353027, "step": 348290 }, { "epoch": 2.070367530360041, "grad_norm": 1.3972065448760986, "learning_rate": 6.771426252788221e-05, "loss": 0.5201659202575684, "step": 348300 }, { "epoch": 2.0704269724367093, "grad_norm": 1.445631504058838, "learning_rate": 6.770876770906931e-05, "loss": 0.5542963027954102, "step": 348310 }, { "epoch": 2.0704864145133772, "grad_norm": 1.398438572883606, "learning_rate": 6.770327309256386e-05, "loss": 0.45720672607421875, "step": 348320 }, { "epoch": 2.0705458565900456, "grad_norm": 1.8247785568237305, "learning_rate": 6.769777867839206e-05, "loss": 0.5184794425964355, "step": 348330 }, { "epoch": 2.070605298666714, "grad_norm": 1.222737193107605, "learning_rate": 6.769228446658031e-05, "loss": 0.5124939918518067, "step": 348340 }, { "epoch": 2.0706647407433825, "grad_norm": 1.4765609502792358, "learning_rate": 6.768679045715485e-05, "loss": 0.5909751415252685, "step": 348350 }, { "epoch": 2.070724182820051, "grad_norm": 1.334729552268982, "learning_rate": 6.768129665014196e-05, "loss": 0.5282834053039551, "step": 348360 }, { "epoch": 2.0707836248967193, "grad_norm": 1.3747918605804443, "learning_rate": 6.767580304556791e-05, "loss": 0.48656134605407714, "step": 348370 }, { "epoch": 2.0708430669733877, "grad_norm": 1.6492438316345215, "learning_rate": 6.767030964345899e-05, "loss": 0.5893381118774415, "step": 348380 }, { "epoch": 2.070902509050056, "grad_norm": 1.3796182870864868, "learning_rate": 6.766481644384148e-05, "loss": 0.5707313537597656, "step": 348390 }, { "epoch": 2.0709619511267245, "grad_norm": 1.3837902545928955, "learning_rate": 6.765932344674161e-05, "loss": 0.5222894668579101, "step": 348400 }, { "epoch": 2.071021393203393, "grad_norm": 1.2573111057281494, "learning_rate": 6.765383065218573e-05, "loss": 0.47900819778442383, "step": 348410 }, { "epoch": 2.0710808352800614, "grad_norm": 1.1024593114852905, "learning_rate": 6.76483380602001e-05, "loss": 0.5078004837036133, "step": 348420 }, { "epoch": 2.07114027735673, "grad_norm": 1.7024747133255005, "learning_rate": 6.764284567081097e-05, "loss": 0.517393970489502, "step": 348430 }, { "epoch": 2.071199719433398, "grad_norm": 1.1900380849838257, "learning_rate": 6.763735348404462e-05, "loss": 0.5080013751983643, "step": 348440 }, { "epoch": 2.0712591615100666, "grad_norm": 1.0958588123321533, "learning_rate": 6.763186149992733e-05, "loss": 0.4978916168212891, "step": 348450 }, { "epoch": 2.071318603586735, "grad_norm": 1.60427725315094, "learning_rate": 6.762636971848535e-05, "loss": 0.5027215480804443, "step": 348460 }, { "epoch": 2.0713780456634034, "grad_norm": 1.5626060962677002, "learning_rate": 6.762087813974498e-05, "loss": 0.5376301765441894, "step": 348470 }, { "epoch": 2.071437487740072, "grad_norm": 1.7012931108474731, "learning_rate": 6.76153867637325e-05, "loss": 0.514646339416504, "step": 348480 }, { "epoch": 2.0714969298167403, "grad_norm": 1.6292601823806763, "learning_rate": 6.760989559047419e-05, "loss": 0.5279458522796631, "step": 348490 }, { "epoch": 2.0715563718934087, "grad_norm": 1.3044942617416382, "learning_rate": 6.760440461999621e-05, "loss": 0.4920825004577637, "step": 348500 }, { "epoch": 2.0716158139700767, "grad_norm": 1.3027584552764893, "learning_rate": 6.759891385232493e-05, "loss": 0.5075185298919678, "step": 348510 }, { "epoch": 2.071675256046745, "grad_norm": 1.399667501449585, "learning_rate": 6.759342328748659e-05, "loss": 0.5164657592773437, "step": 348520 }, { "epoch": 2.0717346981234135, "grad_norm": 1.3450301885604858, "learning_rate": 6.758793292550744e-05, "loss": 0.4766689300537109, "step": 348530 }, { "epoch": 2.071794140200082, "grad_norm": 1.5552881956100464, "learning_rate": 6.758244276641376e-05, "loss": 0.5301073074340821, "step": 348540 }, { "epoch": 2.0718535822767503, "grad_norm": 1.1207633018493652, "learning_rate": 6.757695281023188e-05, "loss": 0.4619927883148193, "step": 348550 }, { "epoch": 2.0719130243534187, "grad_norm": 1.2136831283569336, "learning_rate": 6.757146305698792e-05, "loss": 0.5075456142425537, "step": 348560 }, { "epoch": 2.071972466430087, "grad_norm": 1.1010935306549072, "learning_rate": 6.756597350670824e-05, "loss": 0.43911089897155764, "step": 348570 }, { "epoch": 2.0720319085067556, "grad_norm": 0.8075504899024963, "learning_rate": 6.756048415941907e-05, "loss": 0.4903458595275879, "step": 348580 }, { "epoch": 2.072091350583424, "grad_norm": 1.7761889696121216, "learning_rate": 6.755499501514668e-05, "loss": 0.4678477764129639, "step": 348590 }, { "epoch": 2.0721507926600924, "grad_norm": 1.5517278909683228, "learning_rate": 6.75495060739173e-05, "loss": 0.49028491973876953, "step": 348600 }, { "epoch": 2.072210234736761, "grad_norm": 1.3816777467727661, "learning_rate": 6.754401733575726e-05, "loss": 0.5663818359375, "step": 348610 }, { "epoch": 2.072269676813429, "grad_norm": 1.3837741613388062, "learning_rate": 6.753852880069273e-05, "loss": 0.49869441986083984, "step": 348620 }, { "epoch": 2.0723291188900976, "grad_norm": 1.4304730892181396, "learning_rate": 6.753304046874998e-05, "loss": 0.5263002872467041, "step": 348630 }, { "epoch": 2.072388560966766, "grad_norm": 1.780968189239502, "learning_rate": 6.752755233995531e-05, "loss": 0.4771073818206787, "step": 348640 }, { "epoch": 2.0724480030434345, "grad_norm": 1.4343055486679077, "learning_rate": 6.752206441433494e-05, "loss": 0.5197368621826172, "step": 348650 }, { "epoch": 2.072507445120103, "grad_norm": 1.2879878282546997, "learning_rate": 6.751657669191512e-05, "loss": 0.5210787296295166, "step": 348660 }, { "epoch": 2.0725668871967713, "grad_norm": 1.5759071111679077, "learning_rate": 6.751108917272218e-05, "loss": 0.4933664321899414, "step": 348670 }, { "epoch": 2.0726263292734397, "grad_norm": 1.4510360956192017, "learning_rate": 6.750560185678228e-05, "loss": 0.5274552345275879, "step": 348680 }, { "epoch": 2.0726857713501077, "grad_norm": 1.2514386177062988, "learning_rate": 6.750011474412164e-05, "loss": 0.4855035305023193, "step": 348690 }, { "epoch": 2.072745213426776, "grad_norm": 1.6015080213546753, "learning_rate": 6.749462783476659e-05, "loss": 0.5535669326782227, "step": 348700 }, { "epoch": 2.0728046555034445, "grad_norm": 1.420810341835022, "learning_rate": 6.748914112874337e-05, "loss": 0.49904775619506836, "step": 348710 }, { "epoch": 2.072864097580113, "grad_norm": 1.1663978099822998, "learning_rate": 6.74836546260782e-05, "loss": 0.48822479248046874, "step": 348720 }, { "epoch": 2.0729235396567813, "grad_norm": 1.4307241439819336, "learning_rate": 6.747816832679732e-05, "loss": 0.5684866905212402, "step": 348730 }, { "epoch": 2.0729829817334497, "grad_norm": 1.4008567333221436, "learning_rate": 6.747268223092699e-05, "loss": 0.507063913345337, "step": 348740 }, { "epoch": 2.073042423810118, "grad_norm": 1.4937028884887695, "learning_rate": 6.746719633849346e-05, "loss": 0.4657398223876953, "step": 348750 }, { "epoch": 2.0731018658867866, "grad_norm": 1.6877542734146118, "learning_rate": 6.746171064952291e-05, "loss": 0.5255631923675537, "step": 348760 }, { "epoch": 2.073161307963455, "grad_norm": 1.6385750770568848, "learning_rate": 6.745622516404168e-05, "loss": 0.4950232982635498, "step": 348770 }, { "epoch": 2.0732207500401234, "grad_norm": 1.9232221841812134, "learning_rate": 6.745073988207598e-05, "loss": 0.5501770496368408, "step": 348780 }, { "epoch": 2.073280192116792, "grad_norm": 1.0453284978866577, "learning_rate": 6.744525480365202e-05, "loss": 0.5191163063049317, "step": 348790 }, { "epoch": 2.0733396341934602, "grad_norm": 1.6249498128890991, "learning_rate": 6.743976992879605e-05, "loss": 0.518176794052124, "step": 348800 }, { "epoch": 2.0733990762701286, "grad_norm": 1.0775678157806396, "learning_rate": 6.743428525753433e-05, "loss": 0.5288681030273438, "step": 348810 }, { "epoch": 2.073458518346797, "grad_norm": 1.269078016281128, "learning_rate": 6.742880078989302e-05, "loss": 0.4931290626525879, "step": 348820 }, { "epoch": 2.0735179604234655, "grad_norm": 1.2467418909072876, "learning_rate": 6.742331652589846e-05, "loss": 0.4994350433349609, "step": 348830 }, { "epoch": 2.073577402500134, "grad_norm": 1.3440918922424316, "learning_rate": 6.741783246557684e-05, "loss": 0.5228906631469726, "step": 348840 }, { "epoch": 2.0736368445768023, "grad_norm": 1.0404280424118042, "learning_rate": 6.74123486089544e-05, "loss": 0.49028606414794923, "step": 348850 }, { "epoch": 2.0736962866534707, "grad_norm": 1.5832195281982422, "learning_rate": 6.740686495605736e-05, "loss": 0.5106825828552246, "step": 348860 }, { "epoch": 2.0737557287301387, "grad_norm": 1.5085771083831787, "learning_rate": 6.740138150691197e-05, "loss": 0.5544999122619629, "step": 348870 }, { "epoch": 2.073815170806807, "grad_norm": 1.2984483242034912, "learning_rate": 6.739589826154444e-05, "loss": 0.5004997730255127, "step": 348880 }, { "epoch": 2.0738746128834755, "grad_norm": 1.4957261085510254, "learning_rate": 6.739041521998096e-05, "loss": 0.45244174003601073, "step": 348890 }, { "epoch": 2.073934054960144, "grad_norm": 1.449472427368164, "learning_rate": 6.738493238224787e-05, "loss": 0.4793813705444336, "step": 348900 }, { "epoch": 2.0739934970368124, "grad_norm": 1.3430862426757812, "learning_rate": 6.737944974837131e-05, "loss": 0.5176129817962647, "step": 348910 }, { "epoch": 2.0740529391134808, "grad_norm": 1.4678194522857666, "learning_rate": 6.737396731837755e-05, "loss": 0.4593538761138916, "step": 348920 }, { "epoch": 2.074112381190149, "grad_norm": 1.4913740158081055, "learning_rate": 6.736848509229281e-05, "loss": 0.5249561786651611, "step": 348930 }, { "epoch": 2.0741718232668176, "grad_norm": 1.6316654682159424, "learning_rate": 6.736300307014327e-05, "loss": 0.48411073684692385, "step": 348940 }, { "epoch": 2.074231265343486, "grad_norm": 1.562607765197754, "learning_rate": 6.73575212519552e-05, "loss": 0.5051104545593261, "step": 348950 }, { "epoch": 2.0742907074201544, "grad_norm": 1.5086778402328491, "learning_rate": 6.735203963775482e-05, "loss": 0.5296185493469239, "step": 348960 }, { "epoch": 2.074350149496823, "grad_norm": 1.40691077709198, "learning_rate": 6.734655822756835e-05, "loss": 0.5265268325805664, "step": 348970 }, { "epoch": 2.0744095915734913, "grad_norm": 1.5283485651016235, "learning_rate": 6.7341077021422e-05, "loss": 0.5489720821380615, "step": 348980 }, { "epoch": 2.0744690336501597, "grad_norm": 1.4812321662902832, "learning_rate": 6.733559601934201e-05, "loss": 0.49145970344543455, "step": 348990 }, { "epoch": 2.074528475726828, "grad_norm": 1.2598791122436523, "learning_rate": 6.733011522135457e-05, "loss": 0.5010222434997559, "step": 349000 }, { "epoch": 2.0745879178034965, "grad_norm": 1.788985013961792, "learning_rate": 6.732463462748593e-05, "loss": 0.47137084007263186, "step": 349010 }, { "epoch": 2.074647359880165, "grad_norm": 1.271772861480713, "learning_rate": 6.731915423776225e-05, "loss": 0.4805009841918945, "step": 349020 }, { "epoch": 2.0747068019568333, "grad_norm": 1.281859040260315, "learning_rate": 6.731367405220982e-05, "loss": 0.508550500869751, "step": 349030 }, { "epoch": 2.0747662440335017, "grad_norm": 1.4495939016342163, "learning_rate": 6.730819407085485e-05, "loss": 0.5270472526550293, "step": 349040 }, { "epoch": 2.07482568611017, "grad_norm": 1.1671326160430908, "learning_rate": 6.730271429372347e-05, "loss": 0.44312896728515627, "step": 349050 }, { "epoch": 2.074885128186838, "grad_norm": 1.5818504095077515, "learning_rate": 6.7297234720842e-05, "loss": 0.5229200839996337, "step": 349060 }, { "epoch": 2.0749445702635065, "grad_norm": 1.4524930715560913, "learning_rate": 6.729175535223656e-05, "loss": 0.49631538391113283, "step": 349070 }, { "epoch": 2.075004012340175, "grad_norm": 1.3407907485961914, "learning_rate": 6.728627618793344e-05, "loss": 0.5485817909240722, "step": 349080 }, { "epoch": 2.0750634544168434, "grad_norm": 1.1923493146896362, "learning_rate": 6.728079722795879e-05, "loss": 0.5012980461120605, "step": 349090 }, { "epoch": 2.075122896493512, "grad_norm": 1.2063323259353638, "learning_rate": 6.727531847233888e-05, "loss": 0.4973772048950195, "step": 349100 }, { "epoch": 2.07518233857018, "grad_norm": 1.5157331228256226, "learning_rate": 6.726983992109987e-05, "loss": 0.45346484184265134, "step": 349110 }, { "epoch": 2.0752417806468486, "grad_norm": 1.480832576751709, "learning_rate": 6.726436157426795e-05, "loss": 0.5222839832305908, "step": 349120 }, { "epoch": 2.075301222723517, "grad_norm": 1.0600457191467285, "learning_rate": 6.725888343186939e-05, "loss": 0.48165283203125, "step": 349130 }, { "epoch": 2.0753606648001854, "grad_norm": 1.4769879579544067, "learning_rate": 6.725340549393036e-05, "loss": 0.5127823829650879, "step": 349140 }, { "epoch": 2.075420106876854, "grad_norm": 1.6502262353897095, "learning_rate": 6.724792776047703e-05, "loss": 0.4931607246398926, "step": 349150 }, { "epoch": 2.0754795489535223, "grad_norm": 1.2227082252502441, "learning_rate": 6.724245023153572e-05, "loss": 0.5212737560272217, "step": 349160 }, { "epoch": 2.0755389910301907, "grad_norm": 1.660240650177002, "learning_rate": 6.72369729071325e-05, "loss": 0.4779313087463379, "step": 349170 }, { "epoch": 2.075598433106859, "grad_norm": 1.324196219444275, "learning_rate": 6.723149578729362e-05, "loss": 0.537874984741211, "step": 349180 }, { "epoch": 2.0756578751835275, "grad_norm": 1.469103455543518, "learning_rate": 6.722601887204531e-05, "loss": 0.5416638851165771, "step": 349190 }, { "epoch": 2.075717317260196, "grad_norm": 1.6530734300613403, "learning_rate": 6.722054216141374e-05, "loss": 0.5095415115356445, "step": 349200 }, { "epoch": 2.0757767593368643, "grad_norm": 1.3209552764892578, "learning_rate": 6.721506565542512e-05, "loss": 0.4573319435119629, "step": 349210 }, { "epoch": 2.0758362014135328, "grad_norm": 1.5231633186340332, "learning_rate": 6.720958935410564e-05, "loss": 0.5460063934326171, "step": 349220 }, { "epoch": 2.075895643490201, "grad_norm": 1.364884853363037, "learning_rate": 6.720411325748152e-05, "loss": 0.5188502311706543, "step": 349230 }, { "epoch": 2.0759550855668696, "grad_norm": 1.4825223684310913, "learning_rate": 6.719863736557892e-05, "loss": 0.435414981842041, "step": 349240 }, { "epoch": 2.0760145276435376, "grad_norm": 1.8049980401992798, "learning_rate": 6.7193161678424e-05, "loss": 0.4948250770568848, "step": 349250 }, { "epoch": 2.076073969720206, "grad_norm": 1.419603943824768, "learning_rate": 6.718768619604308e-05, "loss": 0.5674779891967774, "step": 349260 }, { "epoch": 2.0761334117968744, "grad_norm": 1.135574221611023, "learning_rate": 6.718221091846227e-05, "loss": 0.5189462661743164, "step": 349270 }, { "epoch": 2.076192853873543, "grad_norm": 1.215583324432373, "learning_rate": 6.717673584570774e-05, "loss": 0.47091169357299806, "step": 349280 }, { "epoch": 2.076252295950211, "grad_norm": 1.488936185836792, "learning_rate": 6.717126097780573e-05, "loss": 0.512112045288086, "step": 349290 }, { "epoch": 2.0763117380268796, "grad_norm": 1.5315170288085938, "learning_rate": 6.716578631478241e-05, "loss": 0.4965670108795166, "step": 349300 }, { "epoch": 2.076371180103548, "grad_norm": 1.5585204362869263, "learning_rate": 6.716031185666393e-05, "loss": 0.5574202537536621, "step": 349310 }, { "epoch": 2.0764306221802165, "grad_norm": 1.4126496315002441, "learning_rate": 6.715483760347656e-05, "loss": 0.48454532623291013, "step": 349320 }, { "epoch": 2.076490064256885, "grad_norm": 1.420242428779602, "learning_rate": 6.714936355524643e-05, "loss": 0.46984148025512695, "step": 349330 }, { "epoch": 2.0765495063335533, "grad_norm": 1.2068872451782227, "learning_rate": 6.714388971199976e-05, "loss": 0.5049080848693848, "step": 349340 }, { "epoch": 2.0766089484102217, "grad_norm": 1.505869746208191, "learning_rate": 6.71384160737627e-05, "loss": 0.5577343940734864, "step": 349350 }, { "epoch": 2.07666839048689, "grad_norm": 1.3792951107025146, "learning_rate": 6.713294264056147e-05, "loss": 0.5282391548156739, "step": 349360 }, { "epoch": 2.0767278325635585, "grad_norm": 0.8946281671524048, "learning_rate": 6.712746941242223e-05, "loss": 0.5384073257446289, "step": 349370 }, { "epoch": 2.076787274640227, "grad_norm": 1.4669277667999268, "learning_rate": 6.712199638937113e-05, "loss": 0.501029634475708, "step": 349380 }, { "epoch": 2.0768467167168954, "grad_norm": 1.2640502452850342, "learning_rate": 6.71165235714344e-05, "loss": 0.511012601852417, "step": 349390 }, { "epoch": 2.0769061587935638, "grad_norm": 1.0479440689086914, "learning_rate": 6.711105095863822e-05, "loss": 0.5152657985687256, "step": 349400 }, { "epoch": 2.076965600870232, "grad_norm": 1.7371138334274292, "learning_rate": 6.710557855100877e-05, "loss": 0.5180424690246582, "step": 349410 }, { "epoch": 2.0770250429469006, "grad_norm": 1.3282438516616821, "learning_rate": 6.71001063485722e-05, "loss": 0.5342729568481446, "step": 349420 }, { "epoch": 2.0770844850235686, "grad_norm": 1.4004333019256592, "learning_rate": 6.709463435135471e-05, "loss": 0.47640399932861327, "step": 349430 }, { "epoch": 2.077143927100237, "grad_norm": 1.4821608066558838, "learning_rate": 6.70891625593824e-05, "loss": 0.5003116607666016, "step": 349440 }, { "epoch": 2.0772033691769054, "grad_norm": 0.9162044525146484, "learning_rate": 6.708369097268157e-05, "loss": 0.4964765548706055, "step": 349450 }, { "epoch": 2.077262811253574, "grad_norm": 1.3334250450134277, "learning_rate": 6.707821959127836e-05, "loss": 0.5174959182739258, "step": 349460 }, { "epoch": 2.0773222533302422, "grad_norm": 1.7109476327896118, "learning_rate": 6.707274841519888e-05, "loss": 0.5084919452667236, "step": 349470 }, { "epoch": 2.0773816954069106, "grad_norm": 1.0334100723266602, "learning_rate": 6.706727744446938e-05, "loss": 0.5152988433837891, "step": 349480 }, { "epoch": 2.077441137483579, "grad_norm": 1.0818836688995361, "learning_rate": 6.706180667911596e-05, "loss": 0.4886465549468994, "step": 349490 }, { "epoch": 2.0775005795602475, "grad_norm": 1.395716667175293, "learning_rate": 6.705633611916487e-05, "loss": 0.5253998279571533, "step": 349500 }, { "epoch": 2.077560021636916, "grad_norm": 1.4408559799194336, "learning_rate": 6.705086576464215e-05, "loss": 0.5128026008605957, "step": 349510 }, { "epoch": 2.0776194637135843, "grad_norm": 1.203094720840454, "learning_rate": 6.704539561557412e-05, "loss": 0.49825382232666016, "step": 349520 }, { "epoch": 2.0776789057902527, "grad_norm": 1.6223671436309814, "learning_rate": 6.703992567198686e-05, "loss": 0.5895136833190918, "step": 349530 }, { "epoch": 2.077738347866921, "grad_norm": 1.4296926259994507, "learning_rate": 6.703445593390656e-05, "loss": 0.5316855430603027, "step": 349540 }, { "epoch": 2.0777977899435895, "grad_norm": 1.3739712238311768, "learning_rate": 6.702898640135939e-05, "loss": 0.4779913902282715, "step": 349550 }, { "epoch": 2.077857232020258, "grad_norm": 1.295488953590393, "learning_rate": 6.70235170743715e-05, "loss": 0.4907715320587158, "step": 349560 }, { "epoch": 2.0779166740969264, "grad_norm": 1.339224100112915, "learning_rate": 6.701804795296907e-05, "loss": 0.5217942237854004, "step": 349570 }, { "epoch": 2.077976116173595, "grad_norm": 1.513317346572876, "learning_rate": 6.70125790371782e-05, "loss": 0.49775543212890627, "step": 349580 }, { "epoch": 2.078035558250263, "grad_norm": 1.047661542892456, "learning_rate": 6.700711032702516e-05, "loss": 0.4814760208129883, "step": 349590 }, { "epoch": 2.0780950003269316, "grad_norm": 1.3117060661315918, "learning_rate": 6.700164182253607e-05, "loss": 0.5840948104858399, "step": 349600 }, { "epoch": 2.0781544424035996, "grad_norm": 1.1832265853881836, "learning_rate": 6.6996173523737e-05, "loss": 0.4859927654266357, "step": 349610 }, { "epoch": 2.078213884480268, "grad_norm": 1.6341419219970703, "learning_rate": 6.699070543065422e-05, "loss": 0.5000435829162597, "step": 349620 }, { "epoch": 2.0782733265569364, "grad_norm": 1.5173438787460327, "learning_rate": 6.698523754331386e-05, "loss": 0.5131396293640137, "step": 349630 }, { "epoch": 2.078332768633605, "grad_norm": 1.408633828163147, "learning_rate": 6.697976986174203e-05, "loss": 0.5605792999267578, "step": 349640 }, { "epoch": 2.0783922107102732, "grad_norm": 1.6871341466903687, "learning_rate": 6.697430238596498e-05, "loss": 0.49837579727172854, "step": 349650 }, { "epoch": 2.0784516527869417, "grad_norm": 1.3538905382156372, "learning_rate": 6.69688351160088e-05, "loss": 0.4673638820648193, "step": 349660 }, { "epoch": 2.07851109486361, "grad_norm": 1.2644749879837036, "learning_rate": 6.696336805189957e-05, "loss": 0.5134398460388183, "step": 349670 }, { "epoch": 2.0785705369402785, "grad_norm": 1.617370367050171, "learning_rate": 6.695790119366359e-05, "loss": 0.4774049758911133, "step": 349680 }, { "epoch": 2.078629979016947, "grad_norm": 1.215064525604248, "learning_rate": 6.695243454132694e-05, "loss": 0.503847074508667, "step": 349690 }, { "epoch": 2.0786894210936153, "grad_norm": 1.2598965167999268, "learning_rate": 6.694696809491577e-05, "loss": 0.4945328712463379, "step": 349700 }, { "epoch": 2.0787488631702837, "grad_norm": 1.3665709495544434, "learning_rate": 6.694150185445625e-05, "loss": 0.5141079902648926, "step": 349710 }, { "epoch": 2.078808305246952, "grad_norm": 0.9782350659370422, "learning_rate": 6.693603581997448e-05, "loss": 0.4769174575805664, "step": 349720 }, { "epoch": 2.0788677473236206, "grad_norm": 1.6450399160385132, "learning_rate": 6.693056999149667e-05, "loss": 0.5454352378845215, "step": 349730 }, { "epoch": 2.078927189400289, "grad_norm": 1.2951233386993408, "learning_rate": 6.692510436904889e-05, "loss": 0.4891463279724121, "step": 349740 }, { "epoch": 2.0789866314769574, "grad_norm": 1.6187174320220947, "learning_rate": 6.691963895265739e-05, "loss": 0.5330154895782471, "step": 349750 }, { "epoch": 2.079046073553626, "grad_norm": 1.3375660181045532, "learning_rate": 6.691417374234823e-05, "loss": 0.4678350448608398, "step": 349760 }, { "epoch": 2.079105515630294, "grad_norm": 1.0557756423950195, "learning_rate": 6.69087087381476e-05, "loss": 0.514667272567749, "step": 349770 }, { "epoch": 2.0791649577069626, "grad_norm": 1.6785242557525635, "learning_rate": 6.690324394008161e-05, "loss": 0.5310177326202392, "step": 349780 }, { "epoch": 2.079224399783631, "grad_norm": 2.0320382118225098, "learning_rate": 6.689777934817643e-05, "loss": 0.472809886932373, "step": 349790 }, { "epoch": 2.079283841860299, "grad_norm": 1.8501793146133423, "learning_rate": 6.689231496245814e-05, "loss": 0.5511530876159668, "step": 349800 }, { "epoch": 2.0793432839369674, "grad_norm": 1.0360888242721558, "learning_rate": 6.688685078295298e-05, "loss": 0.5085696220397949, "step": 349810 }, { "epoch": 2.079402726013636, "grad_norm": 1.6394426822662354, "learning_rate": 6.688138680968702e-05, "loss": 0.49759554862976074, "step": 349820 }, { "epoch": 2.0794621680903043, "grad_norm": 1.2358744144439697, "learning_rate": 6.687592304268642e-05, "loss": 0.5274120330810547, "step": 349830 }, { "epoch": 2.0795216101669727, "grad_norm": 1.3661656379699707, "learning_rate": 6.687045948197732e-05, "loss": 0.5507085800170899, "step": 349840 }, { "epoch": 2.079581052243641, "grad_norm": 1.2486512660980225, "learning_rate": 6.686499612758584e-05, "loss": 0.49604477882385256, "step": 349850 }, { "epoch": 2.0796404943203095, "grad_norm": 1.4701594114303589, "learning_rate": 6.685953297953813e-05, "loss": 0.45169711112976074, "step": 349860 }, { "epoch": 2.079699936396978, "grad_norm": 0.6580329537391663, "learning_rate": 6.685407003786026e-05, "loss": 0.5072674751281738, "step": 349870 }, { "epoch": 2.0797593784736463, "grad_norm": 1.0930368900299072, "learning_rate": 6.684860730257847e-05, "loss": 0.4980011940002441, "step": 349880 }, { "epoch": 2.0798188205503148, "grad_norm": 1.4571051597595215, "learning_rate": 6.684314477371882e-05, "loss": 0.5365124702453613, "step": 349890 }, { "epoch": 2.079878262626983, "grad_norm": 1.878377079963684, "learning_rate": 6.68376824513075e-05, "loss": 0.47534704208374023, "step": 349900 }, { "epoch": 2.0799377047036516, "grad_norm": 1.2014919519424438, "learning_rate": 6.683222033537057e-05, "loss": 0.5238398551940918, "step": 349910 }, { "epoch": 2.07999714678032, "grad_norm": 1.2158130407333374, "learning_rate": 6.68267584259342e-05, "loss": 0.5528688430786133, "step": 349920 }, { "epoch": 2.0800565888569884, "grad_norm": 1.4712553024291992, "learning_rate": 6.68212967230245e-05, "loss": 0.48953952789306643, "step": 349930 }, { "epoch": 2.080116030933657, "grad_norm": 1.1579995155334473, "learning_rate": 6.681583522666759e-05, "loss": 0.5234491348266601, "step": 349940 }, { "epoch": 2.0801754730103252, "grad_norm": 1.2439824342727661, "learning_rate": 6.681037393688962e-05, "loss": 0.5448831558227539, "step": 349950 }, { "epoch": 2.0802349150869937, "grad_norm": 1.502657175064087, "learning_rate": 6.680491285371672e-05, "loss": 0.5088543891906738, "step": 349960 }, { "epoch": 2.080294357163662, "grad_norm": 1.2260428667068481, "learning_rate": 6.679945197717502e-05, "loss": 0.47478561401367186, "step": 349970 }, { "epoch": 2.0803537992403305, "grad_norm": 1.6045979261398315, "learning_rate": 6.679399130729059e-05, "loss": 0.5409952163696289, "step": 349980 }, { "epoch": 2.0804132413169985, "grad_norm": 1.7774752378463745, "learning_rate": 6.678853084408962e-05, "loss": 0.4792987823486328, "step": 349990 }, { "epoch": 2.080472683393667, "grad_norm": 1.6289457082748413, "learning_rate": 6.678307058759815e-05, "loss": 0.5384091377258301, "step": 350000 }, { "epoch": 2.0805321254703353, "grad_norm": 1.5011874437332153, "learning_rate": 6.677761053784236e-05, "loss": 0.514784860610962, "step": 350010 }, { "epoch": 2.0805915675470037, "grad_norm": 1.4393553733825684, "learning_rate": 6.677215069484837e-05, "loss": 0.497233247756958, "step": 350020 }, { "epoch": 2.080651009623672, "grad_norm": 1.664010763168335, "learning_rate": 6.67666910586423e-05, "loss": 0.5053205013275146, "step": 350030 }, { "epoch": 2.0807104517003405, "grad_norm": 1.157052755355835, "learning_rate": 6.676123162925024e-05, "loss": 0.4850290298461914, "step": 350040 }, { "epoch": 2.080769893777009, "grad_norm": 1.3589287996292114, "learning_rate": 6.675577240669829e-05, "loss": 0.5053313255310059, "step": 350050 }, { "epoch": 2.0808293358536774, "grad_norm": 1.175209879875183, "learning_rate": 6.675031339101261e-05, "loss": 0.4972373962402344, "step": 350060 }, { "epoch": 2.0808887779303458, "grad_norm": 1.4555076360702515, "learning_rate": 6.674485458221929e-05, "loss": 0.49649248123168943, "step": 350070 }, { "epoch": 2.080948220007014, "grad_norm": 1.1946346759796143, "learning_rate": 6.673939598034446e-05, "loss": 0.4854898452758789, "step": 350080 }, { "epoch": 2.0810076620836826, "grad_norm": 1.3078203201293945, "learning_rate": 6.673393758541425e-05, "loss": 0.4858080863952637, "step": 350090 }, { "epoch": 2.081067104160351, "grad_norm": 1.4374958276748657, "learning_rate": 6.672847939745469e-05, "loss": 0.5154812335968018, "step": 350100 }, { "epoch": 2.0811265462370194, "grad_norm": 1.283104658126831, "learning_rate": 6.672302141649196e-05, "loss": 0.48369412422180175, "step": 350110 }, { "epoch": 2.081185988313688, "grad_norm": 1.5327353477478027, "learning_rate": 6.671756364255218e-05, "loss": 0.5204954147338867, "step": 350120 }, { "epoch": 2.0812454303903563, "grad_norm": 1.1871143579483032, "learning_rate": 6.671210607566136e-05, "loss": 0.49110755920410154, "step": 350130 }, { "epoch": 2.0813048724670247, "grad_norm": 1.45819890499115, "learning_rate": 6.670664871584574e-05, "loss": 0.45338850021362304, "step": 350140 }, { "epoch": 2.081364314543693, "grad_norm": 1.6217541694641113, "learning_rate": 6.670119156313139e-05, "loss": 0.5261765480041504, "step": 350150 }, { "epoch": 2.0814237566203615, "grad_norm": 1.500015139579773, "learning_rate": 6.669573461754432e-05, "loss": 0.517334270477295, "step": 350160 }, { "epoch": 2.0814831986970295, "grad_norm": 1.4188480377197266, "learning_rate": 6.669027787911075e-05, "loss": 0.4740314960479736, "step": 350170 }, { "epoch": 2.081542640773698, "grad_norm": 1.0621778964996338, "learning_rate": 6.668482134785671e-05, "loss": 0.5107363224029541, "step": 350180 }, { "epoch": 2.0816020828503663, "grad_norm": 1.2300755977630615, "learning_rate": 6.667936502380836e-05, "loss": 0.5040132999420166, "step": 350190 }, { "epoch": 2.0816615249270347, "grad_norm": 1.6021771430969238, "learning_rate": 6.667390890699172e-05, "loss": 0.4949474334716797, "step": 350200 }, { "epoch": 2.081720967003703, "grad_norm": 1.496563196182251, "learning_rate": 6.6668452997433e-05, "loss": 0.5274657726287841, "step": 350210 }, { "epoch": 2.0817804090803715, "grad_norm": 1.6015081405639648, "learning_rate": 6.666299729515822e-05, "loss": 0.5202432155609131, "step": 350220 }, { "epoch": 2.08183985115704, "grad_norm": 1.4376705884933472, "learning_rate": 6.665754180019345e-05, "loss": 0.5345033645629883, "step": 350230 }, { "epoch": 2.0818992932337084, "grad_norm": 1.776809573173523, "learning_rate": 6.665208651256489e-05, "loss": 0.5478286743164062, "step": 350240 }, { "epoch": 2.081958735310377, "grad_norm": 1.4599483013153076, "learning_rate": 6.664663143229856e-05, "loss": 0.49133949279785155, "step": 350250 }, { "epoch": 2.082018177387045, "grad_norm": 1.0995975732803345, "learning_rate": 6.664117655942057e-05, "loss": 0.5179322719573974, "step": 350260 }, { "epoch": 2.0820776194637136, "grad_norm": 1.5467772483825684, "learning_rate": 6.663572189395708e-05, "loss": 0.47343902587890624, "step": 350270 }, { "epoch": 2.082137061540382, "grad_norm": 1.18056321144104, "learning_rate": 6.663026743593408e-05, "loss": 0.48424386978149414, "step": 350280 }, { "epoch": 2.0821965036170504, "grad_norm": 1.0526244640350342, "learning_rate": 6.662481318537768e-05, "loss": 0.567673635482788, "step": 350290 }, { "epoch": 2.082255945693719, "grad_norm": 1.334551453590393, "learning_rate": 6.661935914231403e-05, "loss": 0.4954686164855957, "step": 350300 }, { "epoch": 2.0823153877703873, "grad_norm": 1.3165901899337769, "learning_rate": 6.661390530676919e-05, "loss": 0.5279115200042724, "step": 350310 }, { "epoch": 2.0823748298470557, "grad_norm": 1.2007780075073242, "learning_rate": 6.660845167876924e-05, "loss": 0.5035277366638183, "step": 350320 }, { "epoch": 2.082434271923724, "grad_norm": 1.2151280641555786, "learning_rate": 6.660299825834029e-05, "loss": 0.5208974838256836, "step": 350330 }, { "epoch": 2.0824937140003925, "grad_norm": 1.8749333620071411, "learning_rate": 6.65975450455084e-05, "loss": 0.5489231586456299, "step": 350340 }, { "epoch": 2.0825531560770605, "grad_norm": 1.216098666191101, "learning_rate": 6.659209204029969e-05, "loss": 0.5139463424682618, "step": 350350 }, { "epoch": 2.082612598153729, "grad_norm": 1.4145419597625732, "learning_rate": 6.658663924274018e-05, "loss": 0.4254439353942871, "step": 350360 }, { "epoch": 2.0826720402303973, "grad_norm": 1.4972249269485474, "learning_rate": 6.658118665285603e-05, "loss": 0.4982148170471191, "step": 350370 }, { "epoch": 2.0827314823070657, "grad_norm": 1.2102619409561157, "learning_rate": 6.65757342706733e-05, "loss": 0.48405933380126953, "step": 350380 }, { "epoch": 2.082790924383734, "grad_norm": 1.5395689010620117, "learning_rate": 6.657028209621806e-05, "loss": 0.5028434753417969, "step": 350390 }, { "epoch": 2.0828503664604026, "grad_norm": 1.6537760496139526, "learning_rate": 6.65648301295164e-05, "loss": 0.5193209648132324, "step": 350400 }, { "epoch": 2.082909808537071, "grad_norm": 1.2356377840042114, "learning_rate": 6.65593783705944e-05, "loss": 0.5213685512542725, "step": 350410 }, { "epoch": 2.0829692506137394, "grad_norm": 1.9263957738876343, "learning_rate": 6.655392681947815e-05, "loss": 0.513252067565918, "step": 350420 }, { "epoch": 2.083028692690408, "grad_norm": 1.2966017723083496, "learning_rate": 6.654847547619367e-05, "loss": 0.5597920894622803, "step": 350430 }, { "epoch": 2.083088134767076, "grad_norm": 1.2436026334762573, "learning_rate": 6.654302434076712e-05, "loss": 0.4251706123352051, "step": 350440 }, { "epoch": 2.0831475768437446, "grad_norm": 1.2273930311203003, "learning_rate": 6.653757341322453e-05, "loss": 0.5301761627197266, "step": 350450 }, { "epoch": 2.083207018920413, "grad_norm": 1.45745050907135, "learning_rate": 6.653212269359199e-05, "loss": 0.5288887977600097, "step": 350460 }, { "epoch": 2.0832664609970815, "grad_norm": 1.7744181156158447, "learning_rate": 6.652667218189557e-05, "loss": 0.5098941802978516, "step": 350470 }, { "epoch": 2.08332590307375, "grad_norm": 1.3744617700576782, "learning_rate": 6.652122187816135e-05, "loss": 0.4758313179016113, "step": 350480 }, { "epoch": 2.0833853451504183, "grad_norm": 1.4084223508834839, "learning_rate": 6.651577178241534e-05, "loss": 0.48343896865844727, "step": 350490 }, { "epoch": 2.0834447872270867, "grad_norm": 1.0781059265136719, "learning_rate": 6.651032189468373e-05, "loss": 0.5279637336730957, "step": 350500 }, { "epoch": 2.083504229303755, "grad_norm": 1.2965662479400635, "learning_rate": 6.650487221499252e-05, "loss": 0.445832347869873, "step": 350510 }, { "epoch": 2.0835636713804235, "grad_norm": 1.6066162586212158, "learning_rate": 6.649942274336777e-05, "loss": 0.4937427520751953, "step": 350520 }, { "epoch": 2.083623113457092, "grad_norm": 1.089335322380066, "learning_rate": 6.649397347983558e-05, "loss": 0.5095108032226563, "step": 350530 }, { "epoch": 2.08368255553376, "grad_norm": 1.3085359334945679, "learning_rate": 6.6488524424422e-05, "loss": 0.4955195426940918, "step": 350540 }, { "epoch": 2.0837419976104283, "grad_norm": 1.4295482635498047, "learning_rate": 6.64830755771531e-05, "loss": 0.5415160179138183, "step": 350550 }, { "epoch": 2.0838014396870967, "grad_norm": 1.0787872076034546, "learning_rate": 6.64776269380549e-05, "loss": 0.47684431076049805, "step": 350560 }, { "epoch": 2.083860881763765, "grad_norm": 1.4898422956466675, "learning_rate": 6.647217850715355e-05, "loss": 0.5072202682495117, "step": 350570 }, { "epoch": 2.0839203238404336, "grad_norm": 1.6137197017669678, "learning_rate": 6.646673028447511e-05, "loss": 0.5297418594360351, "step": 350580 }, { "epoch": 2.083979765917102, "grad_norm": 1.519642949104309, "learning_rate": 6.646128227004554e-05, "loss": 0.520414924621582, "step": 350590 }, { "epoch": 2.0840392079937704, "grad_norm": 1.08986234664917, "learning_rate": 6.645583446389101e-05, "loss": 0.5149948120117187, "step": 350600 }, { "epoch": 2.084098650070439, "grad_norm": 1.6171985864639282, "learning_rate": 6.645038686603751e-05, "loss": 0.510219669342041, "step": 350610 }, { "epoch": 2.0841580921471072, "grad_norm": 1.2687286138534546, "learning_rate": 6.644493947651112e-05, "loss": 0.49158611297607424, "step": 350620 }, { "epoch": 2.0842175342237756, "grad_norm": 1.3838132619857788, "learning_rate": 6.643949229533794e-05, "loss": 0.5163478374481201, "step": 350630 }, { "epoch": 2.084276976300444, "grad_norm": 1.4270879030227661, "learning_rate": 6.6434045322544e-05, "loss": 0.5231301784515381, "step": 350640 }, { "epoch": 2.0843364183771125, "grad_norm": 1.6496648788452148, "learning_rate": 6.64285985581553e-05, "loss": 0.5225105285644531, "step": 350650 }, { "epoch": 2.084395860453781, "grad_norm": 1.1311063766479492, "learning_rate": 6.642315200219799e-05, "loss": 0.45230660438537595, "step": 350660 }, { "epoch": 2.0844553025304493, "grad_norm": 1.556760311126709, "learning_rate": 6.641770565469804e-05, "loss": 0.49768962860107424, "step": 350670 }, { "epoch": 2.0845147446071177, "grad_norm": 1.5976999998092651, "learning_rate": 6.641225951568158e-05, "loss": 0.4891819000244141, "step": 350680 }, { "epoch": 2.084574186683786, "grad_norm": 1.5997904539108276, "learning_rate": 6.64068135851746e-05, "loss": 0.5079441547393799, "step": 350690 }, { "epoch": 2.0846336287604545, "grad_norm": 1.303863286972046, "learning_rate": 6.640136786320321e-05, "loss": 0.503334903717041, "step": 350700 }, { "epoch": 2.084693070837123, "grad_norm": 1.3648121356964111, "learning_rate": 6.639592234979342e-05, "loss": 0.4699543952941895, "step": 350710 }, { "epoch": 2.0847525129137914, "grad_norm": 1.5009208917617798, "learning_rate": 6.639047704497124e-05, "loss": 0.49605417251586914, "step": 350720 }, { "epoch": 2.0848119549904593, "grad_norm": 1.2555978298187256, "learning_rate": 6.63850319487628e-05, "loss": 0.5076885223388672, "step": 350730 }, { "epoch": 2.0848713970671278, "grad_norm": 1.4071900844573975, "learning_rate": 6.637958706119413e-05, "loss": 0.49666776657104494, "step": 350740 }, { "epoch": 2.084930839143796, "grad_norm": 1.5839532613754272, "learning_rate": 6.63741423822912e-05, "loss": 0.5361478805541993, "step": 350750 }, { "epoch": 2.0849902812204646, "grad_norm": 1.1683173179626465, "learning_rate": 6.63686979120802e-05, "loss": 0.5122473239898682, "step": 350760 }, { "epoch": 2.085049723297133, "grad_norm": 1.5142402648925781, "learning_rate": 6.636325365058705e-05, "loss": 0.4813650608062744, "step": 350770 }, { "epoch": 2.0851091653738014, "grad_norm": 1.2743901014328003, "learning_rate": 6.635780959783785e-05, "loss": 0.5830743312835693, "step": 350780 }, { "epoch": 2.08516860745047, "grad_norm": 1.3579356670379639, "learning_rate": 6.635236575385859e-05, "loss": 0.507799768447876, "step": 350790 }, { "epoch": 2.0852280495271382, "grad_norm": 1.4878114461898804, "learning_rate": 6.634692211867537e-05, "loss": 0.5219020843505859, "step": 350800 }, { "epoch": 2.0852874916038067, "grad_norm": 1.37794828414917, "learning_rate": 6.63414786923142e-05, "loss": 0.47435832023620605, "step": 350810 }, { "epoch": 2.085346933680475, "grad_norm": 1.1463932991027832, "learning_rate": 6.633603547480114e-05, "loss": 0.45281553268432617, "step": 350820 }, { "epoch": 2.0854063757571435, "grad_norm": 1.4645190238952637, "learning_rate": 6.633059246616223e-05, "loss": 0.5197796821594238, "step": 350830 }, { "epoch": 2.085465817833812, "grad_norm": 1.2282397747039795, "learning_rate": 6.632514966642347e-05, "loss": 0.4709977149963379, "step": 350840 }, { "epoch": 2.0855252599104803, "grad_norm": 1.1654889583587646, "learning_rate": 6.63197070756109e-05, "loss": 0.4631791591644287, "step": 350850 }, { "epoch": 2.0855847019871487, "grad_norm": 1.1303459405899048, "learning_rate": 6.631426469375059e-05, "loss": 0.4975302219390869, "step": 350860 }, { "epoch": 2.085644144063817, "grad_norm": 1.2540971040725708, "learning_rate": 6.63088225208686e-05, "loss": 0.5228088855743408, "step": 350870 }, { "epoch": 2.0857035861404856, "grad_norm": 1.2987335920333862, "learning_rate": 6.63033805569909e-05, "loss": 0.4390315055847168, "step": 350880 }, { "epoch": 2.085763028217154, "grad_norm": 1.327312707901001, "learning_rate": 6.629793880214356e-05, "loss": 0.4722001075744629, "step": 350890 }, { "epoch": 2.0858224702938224, "grad_norm": 1.244136929512024, "learning_rate": 6.629249725635258e-05, "loss": 0.48195462226867675, "step": 350900 }, { "epoch": 2.0858819123704904, "grad_norm": 1.3831582069396973, "learning_rate": 6.628705591964401e-05, "loss": 0.4992522239685059, "step": 350910 }, { "epoch": 2.085941354447159, "grad_norm": 1.625598669052124, "learning_rate": 6.628161479204385e-05, "loss": 0.5458124160766602, "step": 350920 }, { "epoch": 2.086000796523827, "grad_norm": 1.1178394556045532, "learning_rate": 6.62761738735782e-05, "loss": 0.4701509475708008, "step": 350930 }, { "epoch": 2.0860602386004956, "grad_norm": 1.117055058479309, "learning_rate": 6.627073316427304e-05, "loss": 0.5184701919555664, "step": 350940 }, { "epoch": 2.086119680677164, "grad_norm": 1.3352866172790527, "learning_rate": 6.626529266415442e-05, "loss": 0.4989293575286865, "step": 350950 }, { "epoch": 2.0861791227538324, "grad_norm": 1.4967344999313354, "learning_rate": 6.625985237324832e-05, "loss": 0.5485365867614747, "step": 350960 }, { "epoch": 2.086238564830501, "grad_norm": 1.5299609899520874, "learning_rate": 6.62544122915808e-05, "loss": 0.5142711639404297, "step": 350970 }, { "epoch": 2.0862980069071693, "grad_norm": 1.2092829942703247, "learning_rate": 6.624897241917785e-05, "loss": 0.49863290786743164, "step": 350980 }, { "epoch": 2.0863574489838377, "grad_norm": 1.6019102334976196, "learning_rate": 6.624353275606554e-05, "loss": 0.5086315631866455, "step": 350990 }, { "epoch": 2.086416891060506, "grad_norm": 1.4413644075393677, "learning_rate": 6.623809330226987e-05, "loss": 0.5046907424926758, "step": 351000 }, { "epoch": 2.0864763331371745, "grad_norm": 1.1442402601242065, "learning_rate": 6.623265405781687e-05, "loss": 0.5216734409332275, "step": 351010 }, { "epoch": 2.086535775213843, "grad_norm": 1.5141828060150146, "learning_rate": 6.622721502273254e-05, "loss": 0.5569624900817871, "step": 351020 }, { "epoch": 2.0865952172905113, "grad_norm": 1.1658028364181519, "learning_rate": 6.622177619704291e-05, "loss": 0.5108773708343506, "step": 351030 }, { "epoch": 2.0866546593671798, "grad_norm": 1.088815450668335, "learning_rate": 6.621633758077401e-05, "loss": 0.5371123313903808, "step": 351040 }, { "epoch": 2.086714101443848, "grad_norm": 1.107772707939148, "learning_rate": 6.621089917395179e-05, "loss": 0.5243714332580567, "step": 351050 }, { "epoch": 2.0867735435205166, "grad_norm": 1.1790543794631958, "learning_rate": 6.620546097660236e-05, "loss": 0.46121630668640134, "step": 351060 }, { "epoch": 2.086832985597185, "grad_norm": 1.1418251991271973, "learning_rate": 6.620002298875171e-05, "loss": 0.47673587799072265, "step": 351070 }, { "epoch": 2.0868924276738534, "grad_norm": 1.561790943145752, "learning_rate": 6.619458521042578e-05, "loss": 0.5207520961761475, "step": 351080 }, { "epoch": 2.0869518697505214, "grad_norm": 1.039811611175537, "learning_rate": 6.618914764165068e-05, "loss": 0.48983240127563477, "step": 351090 }, { "epoch": 2.08701131182719, "grad_norm": 1.3103224039077759, "learning_rate": 6.618371028245239e-05, "loss": 0.47941160202026367, "step": 351100 }, { "epoch": 2.087070753903858, "grad_norm": 1.3092349767684937, "learning_rate": 6.617827313285686e-05, "loss": 0.5398199081420898, "step": 351110 }, { "epoch": 2.0871301959805266, "grad_norm": 1.0417072772979736, "learning_rate": 6.617283619289019e-05, "loss": 0.4397578716278076, "step": 351120 }, { "epoch": 2.087189638057195, "grad_norm": 1.1706181764602661, "learning_rate": 6.616739946257838e-05, "loss": 0.45575995445251466, "step": 351130 }, { "epoch": 2.0872490801338635, "grad_norm": 1.2596677541732788, "learning_rate": 6.616196294194732e-05, "loss": 0.45008220672607424, "step": 351140 }, { "epoch": 2.087308522210532, "grad_norm": 1.4829812049865723, "learning_rate": 6.615652663102317e-05, "loss": 0.48287668228149416, "step": 351150 }, { "epoch": 2.0873679642872003, "grad_norm": 1.5541980266571045, "learning_rate": 6.615109052983184e-05, "loss": 0.52932710647583, "step": 351160 }, { "epoch": 2.0874274063638687, "grad_norm": 1.5849107503890991, "learning_rate": 6.614565463839938e-05, "loss": 0.5080750942230224, "step": 351170 }, { "epoch": 2.087486848440537, "grad_norm": 1.531209945678711, "learning_rate": 6.614021895675174e-05, "loss": 0.5543913841247559, "step": 351180 }, { "epoch": 2.0875462905172055, "grad_norm": 1.8702428340911865, "learning_rate": 6.613478348491502e-05, "loss": 0.5321693897247315, "step": 351190 }, { "epoch": 2.087605732593874, "grad_norm": 1.2462847232818604, "learning_rate": 6.612934822291513e-05, "loss": 0.5111908435821533, "step": 351200 }, { "epoch": 2.0876651746705424, "grad_norm": 1.3719022274017334, "learning_rate": 6.612391317077808e-05, "loss": 0.5197288513183593, "step": 351210 }, { "epoch": 2.0877246167472108, "grad_norm": 1.5835130214691162, "learning_rate": 6.61184783285299e-05, "loss": 0.4829852104187012, "step": 351220 }, { "epoch": 2.087784058823879, "grad_norm": 1.6920034885406494, "learning_rate": 6.61130436961966e-05, "loss": 0.5021944046020508, "step": 351230 }, { "epoch": 2.0878435009005476, "grad_norm": 1.5797683000564575, "learning_rate": 6.61076092738041e-05, "loss": 0.4621211051940918, "step": 351240 }, { "epoch": 2.087902942977216, "grad_norm": 1.5215027332305908, "learning_rate": 6.610217506137855e-05, "loss": 0.5280123710632324, "step": 351250 }, { "epoch": 2.0879623850538844, "grad_norm": 1.6444967985153198, "learning_rate": 6.60967410589458e-05, "loss": 0.5148046493530274, "step": 351260 }, { "epoch": 2.088021827130553, "grad_norm": 1.2618542909622192, "learning_rate": 6.60913072665319e-05, "loss": 0.49882116317749026, "step": 351270 }, { "epoch": 2.088081269207221, "grad_norm": 1.09793221950531, "learning_rate": 6.608587368416279e-05, "loss": 0.46806926727294923, "step": 351280 }, { "epoch": 2.0881407112838892, "grad_norm": 1.609251856803894, "learning_rate": 6.608044031186454e-05, "loss": 0.5229513645172119, "step": 351290 }, { "epoch": 2.0882001533605576, "grad_norm": 1.5752161741256714, "learning_rate": 6.607500714966312e-05, "loss": 0.517767333984375, "step": 351300 }, { "epoch": 2.088259595437226, "grad_norm": 1.5297605991363525, "learning_rate": 6.606957419758452e-05, "loss": 0.4813824653625488, "step": 351310 }, { "epoch": 2.0883190375138945, "grad_norm": 1.7068074941635132, "learning_rate": 6.606414145565472e-05, "loss": 0.48368988037109373, "step": 351320 }, { "epoch": 2.088378479590563, "grad_norm": 1.306152105331421, "learning_rate": 6.60587089238997e-05, "loss": 0.47326231002807617, "step": 351330 }, { "epoch": 2.0884379216672313, "grad_norm": 1.7175449132919312, "learning_rate": 6.605327660234541e-05, "loss": 0.5296950340270996, "step": 351340 }, { "epoch": 2.0884973637438997, "grad_norm": 1.0933767557144165, "learning_rate": 6.604784449101793e-05, "loss": 0.5324362277984619, "step": 351350 }, { "epoch": 2.088556805820568, "grad_norm": 1.2794839143753052, "learning_rate": 6.60424125899432e-05, "loss": 0.4636012077331543, "step": 351360 }, { "epoch": 2.0886162478972365, "grad_norm": 1.6478333473205566, "learning_rate": 6.603698089914719e-05, "loss": 0.4584792137145996, "step": 351370 }, { "epoch": 2.088675689973905, "grad_norm": 1.3196309804916382, "learning_rate": 6.603154941865591e-05, "loss": 0.4886623382568359, "step": 351380 }, { "epoch": 2.0887351320505734, "grad_norm": 1.5157749652862549, "learning_rate": 6.602611814849532e-05, "loss": 0.49382858276367186, "step": 351390 }, { "epoch": 2.088794574127242, "grad_norm": 1.3015985488891602, "learning_rate": 6.602068708869141e-05, "loss": 0.4762737274169922, "step": 351400 }, { "epoch": 2.08885401620391, "grad_norm": 1.2610766887664795, "learning_rate": 6.601525623927014e-05, "loss": 0.5150181770324707, "step": 351410 }, { "epoch": 2.0889134582805786, "grad_norm": 1.3529185056686401, "learning_rate": 6.600982560025752e-05, "loss": 0.5433743953704834, "step": 351420 }, { "epoch": 2.088972900357247, "grad_norm": 1.3274301290512085, "learning_rate": 6.600439517167955e-05, "loss": 0.5215409278869629, "step": 351430 }, { "epoch": 2.0890323424339154, "grad_norm": 1.5001627206802368, "learning_rate": 6.599896495356215e-05, "loss": 0.551240348815918, "step": 351440 }, { "epoch": 2.089091784510584, "grad_norm": 1.96494722366333, "learning_rate": 6.599353494593132e-05, "loss": 0.5442876815795898, "step": 351450 }, { "epoch": 2.0891512265872523, "grad_norm": 1.0632046461105347, "learning_rate": 6.598810514881306e-05, "loss": 0.4758608818054199, "step": 351460 }, { "epoch": 2.0892106686639202, "grad_norm": 1.4787853956222534, "learning_rate": 6.598267556223328e-05, "loss": 0.5048117637634277, "step": 351470 }, { "epoch": 2.0892701107405887, "grad_norm": 1.2946195602416992, "learning_rate": 6.597724618621803e-05, "loss": 0.4699858665466309, "step": 351480 }, { "epoch": 2.089329552817257, "grad_norm": 1.6347880363464355, "learning_rate": 6.597181702079322e-05, "loss": 0.5188426494598388, "step": 351490 }, { "epoch": 2.0893889948939255, "grad_norm": 1.1909301280975342, "learning_rate": 6.596638806598489e-05, "loss": 0.49248361587524414, "step": 351500 }, { "epoch": 2.089448436970594, "grad_norm": 1.3910729885101318, "learning_rate": 6.596095932181894e-05, "loss": 0.47710561752319336, "step": 351510 }, { "epoch": 2.0895078790472623, "grad_norm": 1.3391891717910767, "learning_rate": 6.595553078832138e-05, "loss": 0.48883848190307616, "step": 351520 }, { "epoch": 2.0895673211239307, "grad_norm": 1.4304869174957275, "learning_rate": 6.595010246551816e-05, "loss": 0.4569045066833496, "step": 351530 }, { "epoch": 2.089626763200599, "grad_norm": 1.2947413921356201, "learning_rate": 6.594467435343523e-05, "loss": 0.44022274017333984, "step": 351540 }, { "epoch": 2.0896862052772676, "grad_norm": 1.2336899042129517, "learning_rate": 6.593924645209862e-05, "loss": 0.535975980758667, "step": 351550 }, { "epoch": 2.089745647353936, "grad_norm": 1.571404218673706, "learning_rate": 6.593381876153423e-05, "loss": 0.4997689247131348, "step": 351560 }, { "epoch": 2.0898050894306044, "grad_norm": 1.0984824895858765, "learning_rate": 6.592839128176808e-05, "loss": 0.5120511531829834, "step": 351570 }, { "epoch": 2.089864531507273, "grad_norm": 1.5831701755523682, "learning_rate": 6.592296401282608e-05, "loss": 0.5903905868530274, "step": 351580 }, { "epoch": 2.089923973583941, "grad_norm": 1.5218868255615234, "learning_rate": 6.591753695473422e-05, "loss": 0.4853981018066406, "step": 351590 }, { "epoch": 2.0899834156606096, "grad_norm": 1.4763834476470947, "learning_rate": 6.591211010751843e-05, "loss": 0.47237844467163087, "step": 351600 }, { "epoch": 2.090042857737278, "grad_norm": 1.793419361114502, "learning_rate": 6.590668347120472e-05, "loss": 0.5024641036987305, "step": 351610 }, { "epoch": 2.0901022998139465, "grad_norm": 1.2791194915771484, "learning_rate": 6.590125704581904e-05, "loss": 0.5041473388671875, "step": 351620 }, { "epoch": 2.090161741890615, "grad_norm": 1.1778082847595215, "learning_rate": 6.589583083138736e-05, "loss": 0.5291809558868408, "step": 351630 }, { "epoch": 2.0902211839672833, "grad_norm": 1.391908049583435, "learning_rate": 6.589040482793556e-05, "loss": 0.5191641807556152, "step": 351640 }, { "epoch": 2.0902806260439513, "grad_norm": 1.1715445518493652, "learning_rate": 6.588497903548966e-05, "loss": 0.48337297439575194, "step": 351650 }, { "epoch": 2.0903400681206197, "grad_norm": 1.5111584663391113, "learning_rate": 6.587955345407562e-05, "loss": 0.5248744487762451, "step": 351660 }, { "epoch": 2.090399510197288, "grad_norm": 1.0362604856491089, "learning_rate": 6.587412808371933e-05, "loss": 0.47567138671875, "step": 351670 }, { "epoch": 2.0904589522739565, "grad_norm": 1.6290481090545654, "learning_rate": 6.586870292444683e-05, "loss": 0.4776153087615967, "step": 351680 }, { "epoch": 2.090518394350625, "grad_norm": 1.4179582595825195, "learning_rate": 6.586327797628407e-05, "loss": 0.5105106353759765, "step": 351690 }, { "epoch": 2.0905778364272933, "grad_norm": 1.5067487955093384, "learning_rate": 6.58578532392569e-05, "loss": 0.4884359359741211, "step": 351700 }, { "epoch": 2.0906372785039617, "grad_norm": 1.264330506324768, "learning_rate": 6.585242871339136e-05, "loss": 0.5034768581390381, "step": 351710 }, { "epoch": 2.09069672058063, "grad_norm": 1.5824496746063232, "learning_rate": 6.584700439871338e-05, "loss": 0.4676083564758301, "step": 351720 }, { "epoch": 2.0907561626572986, "grad_norm": 1.5245860815048218, "learning_rate": 6.584158029524885e-05, "loss": 0.5164902687072754, "step": 351730 }, { "epoch": 2.090815604733967, "grad_norm": 1.6891391277313232, "learning_rate": 6.583615640302386e-05, "loss": 0.5599267959594727, "step": 351740 }, { "epoch": 2.0908750468106354, "grad_norm": 1.505174160003662, "learning_rate": 6.583073272206421e-05, "loss": 0.5037294864654541, "step": 351750 }, { "epoch": 2.090934488887304, "grad_norm": 1.5830495357513428, "learning_rate": 6.582530925239592e-05, "loss": 0.5265209674835205, "step": 351760 }, { "epoch": 2.0909939309639722, "grad_norm": 1.2529058456420898, "learning_rate": 6.581988599404487e-05, "loss": 0.521973991394043, "step": 351770 }, { "epoch": 2.0910533730406407, "grad_norm": 1.6137115955352783, "learning_rate": 6.581446294703709e-05, "loss": 0.5018043994903565, "step": 351780 }, { "epoch": 2.091112815117309, "grad_norm": 1.354370355606079, "learning_rate": 6.580904011139846e-05, "loss": 0.5338424682617188, "step": 351790 }, { "epoch": 2.0911722571939775, "grad_norm": 1.5113856792449951, "learning_rate": 6.580361748715496e-05, "loss": 0.5139701843261719, "step": 351800 }, { "epoch": 2.091231699270646, "grad_norm": 1.0374833345413208, "learning_rate": 6.57981950743325e-05, "loss": 0.4779416561126709, "step": 351810 }, { "epoch": 2.0912911413473143, "grad_norm": 1.0811110734939575, "learning_rate": 6.579277287295704e-05, "loss": 0.46421327590942385, "step": 351820 }, { "epoch": 2.0913505834239823, "grad_norm": 1.5358176231384277, "learning_rate": 6.578735088305445e-05, "loss": 0.4846446990966797, "step": 351830 }, { "epoch": 2.0914100255006507, "grad_norm": 1.5210156440734863, "learning_rate": 6.578192910465077e-05, "loss": 0.4936734676361084, "step": 351840 }, { "epoch": 2.091469467577319, "grad_norm": 1.3876053094863892, "learning_rate": 6.57765075377719e-05, "loss": 0.5522091865539551, "step": 351850 }, { "epoch": 2.0915289096539875, "grad_norm": 1.2371723651885986, "learning_rate": 6.577108618244377e-05, "loss": 0.4791396617889404, "step": 351860 }, { "epoch": 2.091588351730656, "grad_norm": 1.2982456684112549, "learning_rate": 6.57656650386923e-05, "loss": 0.48880882263183595, "step": 351870 }, { "epoch": 2.0916477938073244, "grad_norm": 1.3150564432144165, "learning_rate": 6.576024410654342e-05, "loss": 0.5077863693237304, "step": 351880 }, { "epoch": 2.0917072358839928, "grad_norm": 1.5021880865097046, "learning_rate": 6.57548233860231e-05, "loss": 0.5174732208251953, "step": 351890 }, { "epoch": 2.091766677960661, "grad_norm": 1.0850626230239868, "learning_rate": 6.574940287715718e-05, "loss": 0.49143095016479493, "step": 351900 }, { "epoch": 2.0918261200373296, "grad_norm": 1.1787853240966797, "learning_rate": 6.574398257997172e-05, "loss": 0.48578414916992185, "step": 351910 }, { "epoch": 2.091885562113998, "grad_norm": 1.3595925569534302, "learning_rate": 6.573856249449257e-05, "loss": 0.5172002792358399, "step": 351920 }, { "epoch": 2.0919450041906664, "grad_norm": 1.658090591430664, "learning_rate": 6.573314262074566e-05, "loss": 0.4763801097869873, "step": 351930 }, { "epoch": 2.092004446267335, "grad_norm": 1.1625113487243652, "learning_rate": 6.572772295875695e-05, "loss": 0.5634302616119384, "step": 351940 }, { "epoch": 2.0920638883440033, "grad_norm": 1.3948345184326172, "learning_rate": 6.572230350855233e-05, "loss": 0.509120512008667, "step": 351950 }, { "epoch": 2.0921233304206717, "grad_norm": 1.3126007318496704, "learning_rate": 6.571688427015771e-05, "loss": 0.5473875999450684, "step": 351960 }, { "epoch": 2.09218277249734, "grad_norm": 1.720278024673462, "learning_rate": 6.571146524359909e-05, "loss": 0.5512206077575683, "step": 351970 }, { "epoch": 2.0922422145740085, "grad_norm": 1.6092230081558228, "learning_rate": 6.570604642890233e-05, "loss": 0.4980906963348389, "step": 351980 }, { "epoch": 2.092301656650677, "grad_norm": 1.2248711585998535, "learning_rate": 6.570062782609338e-05, "loss": 0.5206188678741455, "step": 351990 }, { "epoch": 2.0923610987273453, "grad_norm": 1.0767443180084229, "learning_rate": 6.569520943519816e-05, "loss": 0.4658353328704834, "step": 352000 }, { "epoch": 2.0924205408040137, "grad_norm": 1.2774704694747925, "learning_rate": 6.568979125624256e-05, "loss": 0.5006994724273681, "step": 352010 }, { "epoch": 2.0924799828806817, "grad_norm": 1.4282498359680176, "learning_rate": 6.568437328925253e-05, "loss": 0.4889404296875, "step": 352020 }, { "epoch": 2.09253942495735, "grad_norm": 1.0646698474884033, "learning_rate": 6.567895553425394e-05, "loss": 0.43906440734863283, "step": 352030 }, { "epoch": 2.0925988670340185, "grad_norm": 1.4301791191101074, "learning_rate": 6.567353799127277e-05, "loss": 0.44762840270996096, "step": 352040 }, { "epoch": 2.092658309110687, "grad_norm": 1.7197571992874146, "learning_rate": 6.56681206603349e-05, "loss": 0.5055082321166993, "step": 352050 }, { "epoch": 2.0927177511873554, "grad_norm": 1.8850822448730469, "learning_rate": 6.566270354146626e-05, "loss": 0.5575974464416504, "step": 352060 }, { "epoch": 2.092777193264024, "grad_norm": 1.1523852348327637, "learning_rate": 6.565728663469275e-05, "loss": 0.5085205078125, "step": 352070 }, { "epoch": 2.092836635340692, "grad_norm": 1.227439284324646, "learning_rate": 6.56518699400403e-05, "loss": 0.5070192337036132, "step": 352080 }, { "epoch": 2.0928960774173606, "grad_norm": 1.462833285331726, "learning_rate": 6.564645345753479e-05, "loss": 0.5498163223266601, "step": 352090 }, { "epoch": 2.092955519494029, "grad_norm": 1.6366312503814697, "learning_rate": 6.564103718720216e-05, "loss": 0.5327713966369629, "step": 352100 }, { "epoch": 2.0930149615706974, "grad_norm": 1.3578846454620361, "learning_rate": 6.563562112906832e-05, "loss": 0.4664919853210449, "step": 352110 }, { "epoch": 2.093074403647366, "grad_norm": 1.0267661809921265, "learning_rate": 6.563020528315921e-05, "loss": 0.46423907279968263, "step": 352120 }, { "epoch": 2.0931338457240343, "grad_norm": 1.676376461982727, "learning_rate": 6.562478964950063e-05, "loss": 0.5190267562866211, "step": 352130 }, { "epoch": 2.0931932878007027, "grad_norm": 1.0335469245910645, "learning_rate": 6.56193742281186e-05, "loss": 0.46405367851257323, "step": 352140 }, { "epoch": 2.093252729877371, "grad_norm": 1.0516225099563599, "learning_rate": 6.561395901903896e-05, "loss": 0.47852420806884766, "step": 352150 }, { "epoch": 2.0933121719540395, "grad_norm": 1.241193413734436, "learning_rate": 6.560854402228759e-05, "loss": 0.4798410892486572, "step": 352160 }, { "epoch": 2.093371614030708, "grad_norm": 1.1125664710998535, "learning_rate": 6.560312923789049e-05, "loss": 0.49383020401000977, "step": 352170 }, { "epoch": 2.0934310561073763, "grad_norm": 1.235703945159912, "learning_rate": 6.559771466587355e-05, "loss": 0.48347764015197753, "step": 352180 }, { "epoch": 2.0934904981840448, "grad_norm": 1.1240670680999756, "learning_rate": 6.559230030626254e-05, "loss": 0.5640310287475586, "step": 352190 }, { "epoch": 2.093549940260713, "grad_norm": 1.1086761951446533, "learning_rate": 6.558688615908351e-05, "loss": 0.5365085601806641, "step": 352200 }, { "epoch": 2.093609382337381, "grad_norm": 1.4352340698242188, "learning_rate": 6.558147222436231e-05, "loss": 0.4843508243560791, "step": 352210 }, { "epoch": 2.0936688244140496, "grad_norm": 1.5484998226165771, "learning_rate": 6.557605850212476e-05, "loss": 0.4967047691345215, "step": 352220 }, { "epoch": 2.093728266490718, "grad_norm": 0.8792082667350769, "learning_rate": 6.557064499239689e-05, "loss": 0.4927126407623291, "step": 352230 }, { "epoch": 2.0937877085673864, "grad_norm": 1.2205755710601807, "learning_rate": 6.556523169520457e-05, "loss": 0.5426512718200683, "step": 352240 }, { "epoch": 2.093847150644055, "grad_norm": 1.3745231628417969, "learning_rate": 6.555981861057361e-05, "loss": 0.5398512840270996, "step": 352250 }, { "epoch": 2.093906592720723, "grad_norm": 1.4714274406433105, "learning_rate": 6.555440573852993e-05, "loss": 0.49031686782836914, "step": 352260 }, { "epoch": 2.0939660347973916, "grad_norm": 1.1719924211502075, "learning_rate": 6.55489930790995e-05, "loss": 0.5612636089324952, "step": 352270 }, { "epoch": 2.09402547687406, "grad_norm": 1.1925159692764282, "learning_rate": 6.554358063230812e-05, "loss": 0.5109870910644532, "step": 352280 }, { "epoch": 2.0940849189507285, "grad_norm": 1.5447072982788086, "learning_rate": 6.55381683981817e-05, "loss": 0.5232362747192383, "step": 352290 }, { "epoch": 2.094144361027397, "grad_norm": 1.7732467651367188, "learning_rate": 6.553275637674625e-05, "loss": 0.48838367462158205, "step": 352300 }, { "epoch": 2.0942038031040653, "grad_norm": 1.3523552417755127, "learning_rate": 6.552734456802751e-05, "loss": 0.4993980884552002, "step": 352310 }, { "epoch": 2.0942632451807337, "grad_norm": 1.4134304523468018, "learning_rate": 6.552193297205138e-05, "loss": 0.5132755756378173, "step": 352320 }, { "epoch": 2.094322687257402, "grad_norm": 1.4192211627960205, "learning_rate": 6.551652158884383e-05, "loss": 0.5451977252960205, "step": 352330 }, { "epoch": 2.0943821293340705, "grad_norm": 1.4184280633926392, "learning_rate": 6.55111104184307e-05, "loss": 0.4989789485931396, "step": 352340 }, { "epoch": 2.094441571410739, "grad_norm": 1.5755641460418701, "learning_rate": 6.550569946083787e-05, "loss": 0.5757426261901856, "step": 352350 }, { "epoch": 2.0945010134874074, "grad_norm": 1.6046468019485474, "learning_rate": 6.550028871609124e-05, "loss": 0.5411833763122559, "step": 352360 }, { "epoch": 2.0945604555640758, "grad_norm": 1.2917450666427612, "learning_rate": 6.549487818421666e-05, "loss": 0.48107094764709474, "step": 352370 }, { "epoch": 2.094619897640744, "grad_norm": 1.4857850074768066, "learning_rate": 6.548946786524009e-05, "loss": 0.47708778381347655, "step": 352380 }, { "epoch": 2.094679339717412, "grad_norm": 1.3611118793487549, "learning_rate": 6.548405775918728e-05, "loss": 0.4808654308319092, "step": 352390 }, { "epoch": 2.0947387817940806, "grad_norm": 1.671360731124878, "learning_rate": 6.547864786608424e-05, "loss": 0.514506721496582, "step": 352400 }, { "epoch": 2.094798223870749, "grad_norm": 1.2804063558578491, "learning_rate": 6.547323818595681e-05, "loss": 0.5422361373901368, "step": 352410 }, { "epoch": 2.0948576659474174, "grad_norm": 1.5248268842697144, "learning_rate": 6.546782871883085e-05, "loss": 0.514411735534668, "step": 352420 }, { "epoch": 2.094917108024086, "grad_norm": 1.4906731843948364, "learning_rate": 6.546241946473224e-05, "loss": 0.52926025390625, "step": 352430 }, { "epoch": 2.0949765501007542, "grad_norm": 1.091304898262024, "learning_rate": 6.545701042368686e-05, "loss": 0.48096637725830077, "step": 352440 }, { "epoch": 2.0950359921774226, "grad_norm": 1.9022620916366577, "learning_rate": 6.545160159572057e-05, "loss": 0.5673806190490722, "step": 352450 }, { "epoch": 2.095095434254091, "grad_norm": 1.0794917345046997, "learning_rate": 6.544619298085926e-05, "loss": 0.5019531726837159, "step": 352460 }, { "epoch": 2.0951548763307595, "grad_norm": 1.2989959716796875, "learning_rate": 6.544078457912883e-05, "loss": 0.5311929225921631, "step": 352470 }, { "epoch": 2.095214318407428, "grad_norm": 1.5991504192352295, "learning_rate": 6.54353763905551e-05, "loss": 0.538853645324707, "step": 352480 }, { "epoch": 2.0952737604840963, "grad_norm": 1.494213581085205, "learning_rate": 6.5429968415164e-05, "loss": 0.5167850971221923, "step": 352490 }, { "epoch": 2.0953332025607647, "grad_norm": 1.4563803672790527, "learning_rate": 6.542456065298133e-05, "loss": 0.491497802734375, "step": 352500 }, { "epoch": 2.095392644637433, "grad_norm": 1.07389235496521, "learning_rate": 6.541915310403301e-05, "loss": 0.4563302040100098, "step": 352510 }, { "epoch": 2.0954520867141015, "grad_norm": 1.4002797603607178, "learning_rate": 6.541374576834487e-05, "loss": 0.48914422988891604, "step": 352520 }, { "epoch": 2.09551152879077, "grad_norm": 1.639468789100647, "learning_rate": 6.54083386459428e-05, "loss": 0.5084725379943847, "step": 352530 }, { "epoch": 2.0955709708674384, "grad_norm": 1.4501780271530151, "learning_rate": 6.54029317368527e-05, "loss": 0.49807281494140626, "step": 352540 }, { "epoch": 2.095630412944107, "grad_norm": 1.239680290222168, "learning_rate": 6.539752504110038e-05, "loss": 0.4351200103759766, "step": 352550 }, { "epoch": 2.095689855020775, "grad_norm": 1.434679627418518, "learning_rate": 6.539211855871174e-05, "loss": 0.5448641777038574, "step": 352560 }, { "epoch": 2.095749297097443, "grad_norm": 1.0498219728469849, "learning_rate": 6.53867122897126e-05, "loss": 0.4475216865539551, "step": 352570 }, { "epoch": 2.0958087391741116, "grad_norm": 1.4794217348098755, "learning_rate": 6.538130623412885e-05, "loss": 0.484401798248291, "step": 352580 }, { "epoch": 2.09586818125078, "grad_norm": 1.4043020009994507, "learning_rate": 6.537590039198636e-05, "loss": 0.4946502685546875, "step": 352590 }, { "epoch": 2.0959276233274484, "grad_norm": 1.2086493968963623, "learning_rate": 6.537049476331099e-05, "loss": 0.483905553817749, "step": 352600 }, { "epoch": 2.095987065404117, "grad_norm": 1.4948605298995972, "learning_rate": 6.536508934812862e-05, "loss": 0.4748240947723389, "step": 352610 }, { "epoch": 2.0960465074807852, "grad_norm": 1.6337956190109253, "learning_rate": 6.535968414646501e-05, "loss": 0.4713008880615234, "step": 352620 }, { "epoch": 2.0961059495574537, "grad_norm": 1.2546021938323975, "learning_rate": 6.535427915834611e-05, "loss": 0.5442595481872559, "step": 352630 }, { "epoch": 2.096165391634122, "grad_norm": 1.4615232944488525, "learning_rate": 6.534887438379773e-05, "loss": 0.4847916603088379, "step": 352640 }, { "epoch": 2.0962248337107905, "grad_norm": 1.6224393844604492, "learning_rate": 6.534346982284574e-05, "loss": 0.4899244785308838, "step": 352650 }, { "epoch": 2.096284275787459, "grad_norm": 1.3038755655288696, "learning_rate": 6.5338065475516e-05, "loss": 0.5205151557922363, "step": 352660 }, { "epoch": 2.0963437178641273, "grad_norm": 1.2898889780044556, "learning_rate": 6.533266134183442e-05, "loss": 0.5028488159179687, "step": 352670 }, { "epoch": 2.0964031599407957, "grad_norm": 1.3109943866729736, "learning_rate": 6.532725742182673e-05, "loss": 0.513752794265747, "step": 352680 }, { "epoch": 2.096462602017464, "grad_norm": 1.466064453125, "learning_rate": 6.532185371551884e-05, "loss": 0.48371591567993166, "step": 352690 }, { "epoch": 2.0965220440941326, "grad_norm": 1.353420615196228, "learning_rate": 6.531645022293663e-05, "loss": 0.4668854236602783, "step": 352700 }, { "epoch": 2.096581486170801, "grad_norm": 1.1209672689437866, "learning_rate": 6.531104694410587e-05, "loss": 0.47432670593261717, "step": 352710 }, { "epoch": 2.0966409282474694, "grad_norm": 1.2360862493515015, "learning_rate": 6.53056438790525e-05, "loss": 0.48560247421264646, "step": 352720 }, { "epoch": 2.096700370324138, "grad_norm": 1.1711643934249878, "learning_rate": 6.530024102780235e-05, "loss": 0.4780296325683594, "step": 352730 }, { "epoch": 2.0967598124008062, "grad_norm": 1.2120252847671509, "learning_rate": 6.529483839038122e-05, "loss": 0.49759531021118164, "step": 352740 }, { "epoch": 2.0968192544774746, "grad_norm": 1.825088381767273, "learning_rate": 6.528943596681491e-05, "loss": 0.5380597114562988, "step": 352750 }, { "epoch": 2.0968786965541426, "grad_norm": 1.3789172172546387, "learning_rate": 6.52840337571294e-05, "loss": 0.49300451278686525, "step": 352760 }, { "epoch": 2.096938138630811, "grad_norm": 1.7007941007614136, "learning_rate": 6.527863176135042e-05, "loss": 0.47793054580688477, "step": 352770 }, { "epoch": 2.0969975807074794, "grad_norm": 1.3372803926467896, "learning_rate": 6.527322997950383e-05, "loss": 0.5016277313232422, "step": 352780 }, { "epoch": 2.097057022784148, "grad_norm": 1.630663275718689, "learning_rate": 6.526782841161557e-05, "loss": 0.5223814010620117, "step": 352790 }, { "epoch": 2.0971164648608163, "grad_norm": 1.268969178199768, "learning_rate": 6.526242705771135e-05, "loss": 0.45591168403625487, "step": 352800 }, { "epoch": 2.0971759069374847, "grad_norm": 1.5504060983657837, "learning_rate": 6.525702591781703e-05, "loss": 0.5075054168701172, "step": 352810 }, { "epoch": 2.097235349014153, "grad_norm": 1.2081986665725708, "learning_rate": 6.525162499195853e-05, "loss": 0.4844350814819336, "step": 352820 }, { "epoch": 2.0972947910908215, "grad_norm": 1.6460543870925903, "learning_rate": 6.524622428016163e-05, "loss": 0.5711491584777832, "step": 352830 }, { "epoch": 2.09735423316749, "grad_norm": 1.5246905088424683, "learning_rate": 6.524082378245212e-05, "loss": 0.4662171363830566, "step": 352840 }, { "epoch": 2.0974136752441583, "grad_norm": 1.461531639099121, "learning_rate": 6.523542349885593e-05, "loss": 0.48514699935913086, "step": 352850 }, { "epoch": 2.0974731173208268, "grad_norm": 1.4515093564987183, "learning_rate": 6.523002342939884e-05, "loss": 0.48104143142700195, "step": 352860 }, { "epoch": 2.097532559397495, "grad_norm": 1.3770838975906372, "learning_rate": 6.522462357410665e-05, "loss": 0.5188129901885986, "step": 352870 }, { "epoch": 2.0975920014741636, "grad_norm": 1.7654787302017212, "learning_rate": 6.521922393300524e-05, "loss": 0.5484895229339599, "step": 352880 }, { "epoch": 2.097651443550832, "grad_norm": 1.5057748556137085, "learning_rate": 6.521382450612043e-05, "loss": 0.5531457901000977, "step": 352890 }, { "epoch": 2.0977108856275004, "grad_norm": 1.1380451917648315, "learning_rate": 6.520842529347808e-05, "loss": 0.505390739440918, "step": 352900 }, { "epoch": 2.097770327704169, "grad_norm": 1.1888344287872314, "learning_rate": 6.520302629510396e-05, "loss": 0.5140265941619873, "step": 352910 }, { "epoch": 2.0978297697808372, "grad_norm": 1.6014167070388794, "learning_rate": 6.519762751102392e-05, "loss": 0.5127675056457519, "step": 352920 }, { "epoch": 2.0978892118575057, "grad_norm": 1.6637517213821411, "learning_rate": 6.51922289412638e-05, "loss": 0.5294221878051758, "step": 352930 }, { "epoch": 2.097948653934174, "grad_norm": 2.8680498600006104, "learning_rate": 6.518683058584938e-05, "loss": 0.5712464332580567, "step": 352940 }, { "epoch": 2.098008096010842, "grad_norm": 0.9204350113868713, "learning_rate": 6.518143244480654e-05, "loss": 0.46573171615600584, "step": 352950 }, { "epoch": 2.0980675380875105, "grad_norm": 1.543975591659546, "learning_rate": 6.517603451816109e-05, "loss": 0.4533530712127686, "step": 352960 }, { "epoch": 2.098126980164179, "grad_norm": 1.0007067918777466, "learning_rate": 6.517063680593885e-05, "loss": 0.5293918132781983, "step": 352970 }, { "epoch": 2.0981864222408473, "grad_norm": 1.4697972536087036, "learning_rate": 6.51652393081656e-05, "loss": 0.5200912475585937, "step": 352980 }, { "epoch": 2.0982458643175157, "grad_norm": 1.160353422164917, "learning_rate": 6.515984202486722e-05, "loss": 0.4572721481323242, "step": 352990 }, { "epoch": 2.098305306394184, "grad_norm": 1.1392228603363037, "learning_rate": 6.51544449560695e-05, "loss": 0.4929827690124512, "step": 353000 }, { "epoch": 2.0983647484708525, "grad_norm": 1.3437689542770386, "learning_rate": 6.514904810179823e-05, "loss": 0.5133296966552734, "step": 353010 }, { "epoch": 2.098424190547521, "grad_norm": 1.2421797513961792, "learning_rate": 6.514365146207928e-05, "loss": 0.5345235347747803, "step": 353020 }, { "epoch": 2.0984836326241894, "grad_norm": 1.4512062072753906, "learning_rate": 6.513825503693845e-05, "loss": 0.5758392333984375, "step": 353030 }, { "epoch": 2.0985430747008578, "grad_norm": 1.0628809928894043, "learning_rate": 6.513285882640154e-05, "loss": 0.5253558158874512, "step": 353040 }, { "epoch": 2.098602516777526, "grad_norm": 1.582882046699524, "learning_rate": 6.512746283049438e-05, "loss": 0.5578889369964599, "step": 353050 }, { "epoch": 2.0986619588541946, "grad_norm": 1.0226799249649048, "learning_rate": 6.512206704924276e-05, "loss": 0.445604133605957, "step": 353060 }, { "epoch": 2.098721400930863, "grad_norm": 1.4720655679702759, "learning_rate": 6.511667148267249e-05, "loss": 0.48183622360229494, "step": 353070 }, { "epoch": 2.0987808430075314, "grad_norm": 1.2848093509674072, "learning_rate": 6.51112761308094e-05, "loss": 0.4793311595916748, "step": 353080 }, { "epoch": 2.0988402850842, "grad_norm": 2.816598653793335, "learning_rate": 6.510588099367933e-05, "loss": 0.5419151782989502, "step": 353090 }, { "epoch": 2.0988997271608683, "grad_norm": 1.510194182395935, "learning_rate": 6.510048607130806e-05, "loss": 0.5697813034057617, "step": 353100 }, { "epoch": 2.0989591692375367, "grad_norm": 1.3026134967803955, "learning_rate": 6.509509136372134e-05, "loss": 0.4701094627380371, "step": 353110 }, { "epoch": 2.099018611314205, "grad_norm": 1.3069289922714233, "learning_rate": 6.508969687094505e-05, "loss": 0.49211878776550294, "step": 353120 }, { "epoch": 2.099078053390873, "grad_norm": 1.5286284685134888, "learning_rate": 6.508430259300498e-05, "loss": 0.49927549362182616, "step": 353130 }, { "epoch": 2.0991374954675415, "grad_norm": 1.6040838956832886, "learning_rate": 6.507890852992688e-05, "loss": 0.48692903518676756, "step": 353140 }, { "epoch": 2.09919693754421, "grad_norm": 1.6654443740844727, "learning_rate": 6.507351468173666e-05, "loss": 0.5605822563171386, "step": 353150 }, { "epoch": 2.0992563796208783, "grad_norm": 1.0868232250213623, "learning_rate": 6.506812104846008e-05, "loss": 0.5228541851043701, "step": 353160 }, { "epoch": 2.0993158216975467, "grad_norm": 1.0886917114257812, "learning_rate": 6.506272763012287e-05, "loss": 0.4671849250793457, "step": 353170 }, { "epoch": 2.099375263774215, "grad_norm": 1.3597832918167114, "learning_rate": 6.505733442675091e-05, "loss": 0.5232158660888672, "step": 353180 }, { "epoch": 2.0994347058508835, "grad_norm": 1.2043043375015259, "learning_rate": 6.505194143836997e-05, "loss": 0.48557190895080565, "step": 353190 }, { "epoch": 2.099494147927552, "grad_norm": 1.2848644256591797, "learning_rate": 6.504654866500583e-05, "loss": 0.5024172306060791, "step": 353200 }, { "epoch": 2.0995535900042204, "grad_norm": 1.2278075218200684, "learning_rate": 6.504115610668433e-05, "loss": 0.513175630569458, "step": 353210 }, { "epoch": 2.099613032080889, "grad_norm": 1.5010936260223389, "learning_rate": 6.50357637634313e-05, "loss": 0.48840951919555664, "step": 353220 }, { "epoch": 2.099672474157557, "grad_norm": 1.4693236351013184, "learning_rate": 6.503037163527243e-05, "loss": 0.5000349998474121, "step": 353230 }, { "epoch": 2.0997319162342256, "grad_norm": 1.3711538314819336, "learning_rate": 6.502497972223354e-05, "loss": 0.461974048614502, "step": 353240 }, { "epoch": 2.099791358310894, "grad_norm": 1.1919227838516235, "learning_rate": 6.501958802434049e-05, "loss": 0.5048361778259277, "step": 353250 }, { "epoch": 2.0998508003875624, "grad_norm": 1.084745168685913, "learning_rate": 6.501419654161902e-05, "loss": 0.5267258644104004, "step": 353260 }, { "epoch": 2.099910242464231, "grad_norm": 1.7139639854431152, "learning_rate": 6.50088052740949e-05, "loss": 0.5258345603942871, "step": 353270 }, { "epoch": 2.0999696845408993, "grad_norm": 1.9017589092254639, "learning_rate": 6.500341422179403e-05, "loss": 0.5581783771514892, "step": 353280 }, { "epoch": 2.1000291266175677, "grad_norm": 1.0697863101959229, "learning_rate": 6.499802338474208e-05, "loss": 0.46354165077209475, "step": 353290 }, { "epoch": 2.100088568694236, "grad_norm": 1.3889495134353638, "learning_rate": 6.499263276296483e-05, "loss": 0.4854267120361328, "step": 353300 }, { "epoch": 2.100148010770904, "grad_norm": 1.3382879495620728, "learning_rate": 6.498724235648817e-05, "loss": 0.524870777130127, "step": 353310 }, { "epoch": 2.1002074528475725, "grad_norm": 1.366176724433899, "learning_rate": 6.498185216533783e-05, "loss": 0.5515079498291016, "step": 353320 }, { "epoch": 2.100266894924241, "grad_norm": 1.2062432765960693, "learning_rate": 6.497646218953957e-05, "loss": 0.5293896198272705, "step": 353330 }, { "epoch": 2.1003263370009093, "grad_norm": 1.0480929613113403, "learning_rate": 6.497107242911925e-05, "loss": 0.5155672073364258, "step": 353340 }, { "epoch": 2.1003857790775777, "grad_norm": 1.337878704071045, "learning_rate": 6.496568288410259e-05, "loss": 0.5059651851654052, "step": 353350 }, { "epoch": 2.100445221154246, "grad_norm": 1.5444384813308716, "learning_rate": 6.496029355451536e-05, "loss": 0.4530994415283203, "step": 353360 }, { "epoch": 2.1005046632309146, "grad_norm": 1.7777056694030762, "learning_rate": 6.495490444038335e-05, "loss": 0.5213915348052979, "step": 353370 }, { "epoch": 2.100564105307583, "grad_norm": 1.3963611125946045, "learning_rate": 6.49495155417324e-05, "loss": 0.45676231384277344, "step": 353380 }, { "epoch": 2.1006235473842514, "grad_norm": 1.1160968542099, "learning_rate": 6.494412685858822e-05, "loss": 0.5123720169067383, "step": 353390 }, { "epoch": 2.10068298946092, "grad_norm": 1.5887305736541748, "learning_rate": 6.493873839097664e-05, "loss": 0.5212852954864502, "step": 353400 }, { "epoch": 2.100742431537588, "grad_norm": 1.6701533794403076, "learning_rate": 6.493335013892339e-05, "loss": 0.5203166484832764, "step": 353410 }, { "epoch": 2.1008018736142566, "grad_norm": 1.4163036346435547, "learning_rate": 6.492796210245426e-05, "loss": 0.49831175804138184, "step": 353420 }, { "epoch": 2.100861315690925, "grad_norm": 1.246747374534607, "learning_rate": 6.4922574281595e-05, "loss": 0.5198323726654053, "step": 353430 }, { "epoch": 2.1009207577675935, "grad_norm": 1.1702998876571655, "learning_rate": 6.491718667637145e-05, "loss": 0.4657240867614746, "step": 353440 }, { "epoch": 2.100980199844262, "grad_norm": 1.4920717477798462, "learning_rate": 6.491179928680936e-05, "loss": 0.551937198638916, "step": 353450 }, { "epoch": 2.1010396419209303, "grad_norm": 1.733928918838501, "learning_rate": 6.490641211293448e-05, "loss": 0.5386417388916016, "step": 353460 }, { "epoch": 2.1010990839975987, "grad_norm": 1.0522669553756714, "learning_rate": 6.490102515477259e-05, "loss": 0.5235515594482422, "step": 353470 }, { "epoch": 2.101158526074267, "grad_norm": 1.327253818511963, "learning_rate": 6.489563841234944e-05, "loss": 0.49063782691955565, "step": 353480 }, { "epoch": 2.1012179681509355, "grad_norm": 1.2064294815063477, "learning_rate": 6.489025188569082e-05, "loss": 0.5460598945617676, "step": 353490 }, { "epoch": 2.1012774102276035, "grad_norm": 0.839165210723877, "learning_rate": 6.488486557482247e-05, "loss": 0.5075142860412598, "step": 353500 }, { "epoch": 2.101336852304272, "grad_norm": 1.4844106435775757, "learning_rate": 6.48794794797702e-05, "loss": 0.49390645027160646, "step": 353510 }, { "epoch": 2.1013962943809403, "grad_norm": 1.0688124895095825, "learning_rate": 6.487409360055977e-05, "loss": 0.5510421752929687, "step": 353520 }, { "epoch": 2.1014557364576087, "grad_norm": 1.6001321077346802, "learning_rate": 6.486870793721691e-05, "loss": 0.49724416732788085, "step": 353530 }, { "epoch": 2.101515178534277, "grad_norm": 1.6656378507614136, "learning_rate": 6.486332248976743e-05, "loss": 0.5163683891296387, "step": 353540 }, { "epoch": 2.1015746206109456, "grad_norm": 1.166591763496399, "learning_rate": 6.485793725823705e-05, "loss": 0.48109006881713867, "step": 353550 }, { "epoch": 2.101634062687614, "grad_norm": 1.2901873588562012, "learning_rate": 6.485255224265149e-05, "loss": 0.5150741100311279, "step": 353560 }, { "epoch": 2.1016935047642824, "grad_norm": 1.4894598722457886, "learning_rate": 6.484716744303663e-05, "loss": 0.5142726898193359, "step": 353570 }, { "epoch": 2.101752946840951, "grad_norm": 1.8538718223571777, "learning_rate": 6.484178285941816e-05, "loss": 0.44987783432006834, "step": 353580 }, { "epoch": 2.1018123889176192, "grad_norm": 1.6547666788101196, "learning_rate": 6.483639849182184e-05, "loss": 0.5296137809753418, "step": 353590 }, { "epoch": 2.1018718309942876, "grad_norm": 1.688981056213379, "learning_rate": 6.483101434027344e-05, "loss": 0.5016526222229004, "step": 353600 }, { "epoch": 2.101931273070956, "grad_norm": 1.4057453870773315, "learning_rate": 6.482563040479868e-05, "loss": 0.48221750259399415, "step": 353610 }, { "epoch": 2.1019907151476245, "grad_norm": 1.3155542612075806, "learning_rate": 6.482024668542334e-05, "loss": 0.4967007637023926, "step": 353620 }, { "epoch": 2.102050157224293, "grad_norm": 1.1668509244918823, "learning_rate": 6.481486318217315e-05, "loss": 0.5648736000061035, "step": 353630 }, { "epoch": 2.1021095993009613, "grad_norm": 1.2647697925567627, "learning_rate": 6.480947989507394e-05, "loss": 0.4872765064239502, "step": 353640 }, { "epoch": 2.1021690413776297, "grad_norm": 1.572027325630188, "learning_rate": 6.48040968241514e-05, "loss": 0.5675287246704102, "step": 353650 }, { "epoch": 2.102228483454298, "grad_norm": 1.853886604309082, "learning_rate": 6.479871396943129e-05, "loss": 0.6035929679870605, "step": 353660 }, { "epoch": 2.1022879255309666, "grad_norm": 1.0736733675003052, "learning_rate": 6.479333133093936e-05, "loss": 0.4719700813293457, "step": 353670 }, { "epoch": 2.102347367607635, "grad_norm": 1.3829319477081299, "learning_rate": 6.478794890870135e-05, "loss": 0.5221474170684814, "step": 353680 }, { "epoch": 2.102406809684303, "grad_norm": 1.5609885454177856, "learning_rate": 6.478256670274299e-05, "loss": 0.599337100982666, "step": 353690 }, { "epoch": 2.1024662517609713, "grad_norm": 1.9346445798873901, "learning_rate": 6.477718471309009e-05, "loss": 0.5021088123321533, "step": 353700 }, { "epoch": 2.1025256938376398, "grad_norm": 1.3824249505996704, "learning_rate": 6.477180293976835e-05, "loss": 0.5154289245605469, "step": 353710 }, { "epoch": 2.102585135914308, "grad_norm": 2.0650289058685303, "learning_rate": 6.476642138280358e-05, "loss": 0.5761744499206543, "step": 353720 }, { "epoch": 2.1026445779909766, "grad_norm": 1.1711807250976562, "learning_rate": 6.476104004222138e-05, "loss": 0.48343586921691895, "step": 353730 }, { "epoch": 2.102704020067645, "grad_norm": 1.478264331817627, "learning_rate": 6.47556589180476e-05, "loss": 0.5218481063842774, "step": 353740 }, { "epoch": 2.1027634621443134, "grad_norm": 1.0798300504684448, "learning_rate": 6.4750278010308e-05, "loss": 0.45621910095214846, "step": 353750 }, { "epoch": 2.102822904220982, "grad_norm": 1.4888064861297607, "learning_rate": 6.474489731902823e-05, "loss": 0.5170671463012695, "step": 353760 }, { "epoch": 2.1028823462976503, "grad_norm": 1.2211719751358032, "learning_rate": 6.473951684423414e-05, "loss": 0.4897798538208008, "step": 353770 }, { "epoch": 2.1029417883743187, "grad_norm": 1.4746698141098022, "learning_rate": 6.473413658595139e-05, "loss": 0.5193513870239258, "step": 353780 }, { "epoch": 2.103001230450987, "grad_norm": 1.7177369594573975, "learning_rate": 6.47287565442057e-05, "loss": 0.5167730331420899, "step": 353790 }, { "epoch": 2.1030606725276555, "grad_norm": 1.3497322797775269, "learning_rate": 6.472337671902288e-05, "loss": 0.4977579593658447, "step": 353800 }, { "epoch": 2.103120114604324, "grad_norm": 1.2820378541946411, "learning_rate": 6.47179971104286e-05, "loss": 0.48866920471191405, "step": 353810 }, { "epoch": 2.1031795566809923, "grad_norm": 1.4153987169265747, "learning_rate": 6.471261771844867e-05, "loss": 0.4633941650390625, "step": 353820 }, { "epoch": 2.1032389987576607, "grad_norm": 1.270532488822937, "learning_rate": 6.470723854310874e-05, "loss": 0.4794475078582764, "step": 353830 }, { "epoch": 2.103298440834329, "grad_norm": 1.3738105297088623, "learning_rate": 6.47018595844346e-05, "loss": 0.4328746795654297, "step": 353840 }, { "epoch": 2.1033578829109976, "grad_norm": 1.9636908769607544, "learning_rate": 6.469648084245196e-05, "loss": 0.5252972602844238, "step": 353850 }, { "epoch": 2.103417324987666, "grad_norm": 1.3482083082199097, "learning_rate": 6.469110231718651e-05, "loss": 0.4880057334899902, "step": 353860 }, { "epoch": 2.103476767064334, "grad_norm": 1.4950973987579346, "learning_rate": 6.468572400866406e-05, "loss": 0.478926944732666, "step": 353870 }, { "epoch": 2.1035362091410024, "grad_norm": 1.0949342250823975, "learning_rate": 6.468034591691031e-05, "loss": 0.5202376842498779, "step": 353880 }, { "epoch": 2.103595651217671, "grad_norm": 1.1273956298828125, "learning_rate": 6.467496804195095e-05, "loss": 0.5101146697998047, "step": 353890 }, { "epoch": 2.103655093294339, "grad_norm": 1.2938669919967651, "learning_rate": 6.466959038381173e-05, "loss": 0.5114550590515137, "step": 353900 }, { "epoch": 2.1037145353710076, "grad_norm": 1.113196611404419, "learning_rate": 6.466421294251837e-05, "loss": 0.5013011932373047, "step": 353910 }, { "epoch": 2.103773977447676, "grad_norm": 1.1397415399551392, "learning_rate": 6.465883571809658e-05, "loss": 0.4798462390899658, "step": 353920 }, { "epoch": 2.1038334195243444, "grad_norm": 1.7083944082260132, "learning_rate": 6.465345871057214e-05, "loss": 0.5825819492340087, "step": 353930 }, { "epoch": 2.103892861601013, "grad_norm": 1.4840309619903564, "learning_rate": 6.464808191997072e-05, "loss": 0.49803957939147947, "step": 353940 }, { "epoch": 2.1039523036776813, "grad_norm": 1.4557888507843018, "learning_rate": 6.464270534631806e-05, "loss": 0.5436639308929443, "step": 353950 }, { "epoch": 2.1040117457543497, "grad_norm": 1.1041293144226074, "learning_rate": 6.463732898963988e-05, "loss": 0.5157377243041992, "step": 353960 }, { "epoch": 2.104071187831018, "grad_norm": 1.7084298133850098, "learning_rate": 6.46319528499619e-05, "loss": 0.5656489372253418, "step": 353970 }, { "epoch": 2.1041306299076865, "grad_norm": 1.7725645303726196, "learning_rate": 6.462657692730983e-05, "loss": 0.48451838493347166, "step": 353980 }, { "epoch": 2.104190071984355, "grad_norm": 1.1325329542160034, "learning_rate": 6.462120122170934e-05, "loss": 0.4718174934387207, "step": 353990 }, { "epoch": 2.1042495140610233, "grad_norm": 1.446252465248108, "learning_rate": 6.461582573318623e-05, "loss": 0.5245375156402587, "step": 354000 }, { "epoch": 2.1043089561376918, "grad_norm": 1.2693339586257935, "learning_rate": 6.461045046176617e-05, "loss": 0.5297749996185303, "step": 354010 }, { "epoch": 2.10436839821436, "grad_norm": 1.5468173027038574, "learning_rate": 6.46050754074749e-05, "loss": 0.5243414878845215, "step": 354020 }, { "epoch": 2.1044278402910286, "grad_norm": 1.4363949298858643, "learning_rate": 6.45997005703381e-05, "loss": 0.5101464748382568, "step": 354030 }, { "epoch": 2.104487282367697, "grad_norm": 1.1484473943710327, "learning_rate": 6.459432595038151e-05, "loss": 0.5128674507141113, "step": 354040 }, { "epoch": 2.104546724444365, "grad_norm": 1.6151319742202759, "learning_rate": 6.458895154763078e-05, "loss": 0.49739952087402345, "step": 354050 }, { "epoch": 2.1046061665210334, "grad_norm": 1.0835349559783936, "learning_rate": 6.458357736211171e-05, "loss": 0.48945040702819825, "step": 354060 }, { "epoch": 2.104665608597702, "grad_norm": 1.3211549520492554, "learning_rate": 6.457820339384997e-05, "loss": 0.5087313652038574, "step": 354070 }, { "epoch": 2.10472505067437, "grad_norm": 1.3416156768798828, "learning_rate": 6.457282964287124e-05, "loss": 0.4820090770721436, "step": 354080 }, { "epoch": 2.1047844927510386, "grad_norm": 1.6557632684707642, "learning_rate": 6.456745610920125e-05, "loss": 0.5260143280029297, "step": 354090 }, { "epoch": 2.104843934827707, "grad_norm": 1.2045592069625854, "learning_rate": 6.456208279286571e-05, "loss": 0.5100738048553467, "step": 354100 }, { "epoch": 2.1049033769043755, "grad_norm": 1.492100477218628, "learning_rate": 6.455670969389032e-05, "loss": 0.5089705944061279, "step": 354110 }, { "epoch": 2.104962818981044, "grad_norm": 1.516803503036499, "learning_rate": 6.455133681230073e-05, "loss": 0.5727312088012695, "step": 354120 }, { "epoch": 2.1050222610577123, "grad_norm": 1.642458438873291, "learning_rate": 6.454596414812274e-05, "loss": 0.4966908931732178, "step": 354130 }, { "epoch": 2.1050817031343807, "grad_norm": 1.7582662105560303, "learning_rate": 6.4540591701382e-05, "loss": 0.4820060729980469, "step": 354140 }, { "epoch": 2.105141145211049, "grad_norm": 1.4500436782836914, "learning_rate": 6.453521947210422e-05, "loss": 0.47711029052734377, "step": 354150 }, { "epoch": 2.1052005872877175, "grad_norm": 1.3116395473480225, "learning_rate": 6.452984746031508e-05, "loss": 0.4732646942138672, "step": 354160 }, { "epoch": 2.105260029364386, "grad_norm": 1.3947077989578247, "learning_rate": 6.45244756660403e-05, "loss": 0.4837466239929199, "step": 354170 }, { "epoch": 2.1053194714410544, "grad_norm": 1.237766146659851, "learning_rate": 6.451910408930552e-05, "loss": 0.49565792083740234, "step": 354180 }, { "epoch": 2.1053789135177228, "grad_norm": 1.198007583618164, "learning_rate": 6.451373273013652e-05, "loss": 0.5035535812377929, "step": 354190 }, { "epoch": 2.105438355594391, "grad_norm": 1.2237815856933594, "learning_rate": 6.450836158855897e-05, "loss": 0.5033379554748535, "step": 354200 }, { "epoch": 2.1054977976710596, "grad_norm": 1.3220142126083374, "learning_rate": 6.450299066459857e-05, "loss": 0.4878826141357422, "step": 354210 }, { "epoch": 2.105557239747728, "grad_norm": 1.4841704368591309, "learning_rate": 6.449761995828094e-05, "loss": 0.525173568725586, "step": 354220 }, { "epoch": 2.1056166818243964, "grad_norm": 1.113814353942871, "learning_rate": 6.449224946963185e-05, "loss": 0.47522540092468263, "step": 354230 }, { "epoch": 2.1056761239010644, "grad_norm": 1.431073546409607, "learning_rate": 6.448687919867695e-05, "loss": 0.5077643394470215, "step": 354240 }, { "epoch": 2.105735565977733, "grad_norm": 1.319839596748352, "learning_rate": 6.448150914544193e-05, "loss": 0.4813204765319824, "step": 354250 }, { "epoch": 2.1057950080544012, "grad_norm": 1.2432492971420288, "learning_rate": 6.447613930995254e-05, "loss": 0.4910222053527832, "step": 354260 }, { "epoch": 2.1058544501310696, "grad_norm": 1.6111458539962769, "learning_rate": 6.447076969223444e-05, "loss": 0.4991455078125, "step": 354270 }, { "epoch": 2.105913892207738, "grad_norm": 1.61814284324646, "learning_rate": 6.446540029231325e-05, "loss": 0.5292551040649414, "step": 354280 }, { "epoch": 2.1059733342844065, "grad_norm": 1.6508997678756714, "learning_rate": 6.446003111021472e-05, "loss": 0.4930133819580078, "step": 354290 }, { "epoch": 2.106032776361075, "grad_norm": 1.4108998775482178, "learning_rate": 6.445466214596451e-05, "loss": 0.5192628860473633, "step": 354300 }, { "epoch": 2.1060922184377433, "grad_norm": 1.3907350301742554, "learning_rate": 6.444929339958834e-05, "loss": 0.4509239196777344, "step": 354310 }, { "epoch": 2.1061516605144117, "grad_norm": 1.666365623474121, "learning_rate": 6.444392487111182e-05, "loss": 0.555484390258789, "step": 354320 }, { "epoch": 2.10621110259108, "grad_norm": 1.3199537992477417, "learning_rate": 6.443855656056072e-05, "loss": 0.5571932315826416, "step": 354330 }, { "epoch": 2.1062705446677485, "grad_norm": 1.3926432132720947, "learning_rate": 6.443318846796066e-05, "loss": 0.5463823318481446, "step": 354340 }, { "epoch": 2.106329986744417, "grad_norm": 1.752935528755188, "learning_rate": 6.442782059333731e-05, "loss": 0.5312992095947265, "step": 354350 }, { "epoch": 2.1063894288210854, "grad_norm": 1.5752555131912231, "learning_rate": 6.44224529367164e-05, "loss": 0.4915493965148926, "step": 354360 }, { "epoch": 2.106448870897754, "grad_norm": 1.139190912246704, "learning_rate": 6.441708549812359e-05, "loss": 0.545045280456543, "step": 354370 }, { "epoch": 2.106508312974422, "grad_norm": 1.4544650316238403, "learning_rate": 6.441171827758452e-05, "loss": 0.5173022270202636, "step": 354380 }, { "epoch": 2.1065677550510906, "grad_norm": 1.0884596109390259, "learning_rate": 6.440635127512491e-05, "loss": 0.44292759895324707, "step": 354390 }, { "epoch": 2.106627197127759, "grad_norm": 1.2897752523422241, "learning_rate": 6.440098449077041e-05, "loss": 0.5139759063720704, "step": 354400 }, { "epoch": 2.1066866392044274, "grad_norm": 1.3588815927505493, "learning_rate": 6.439561792454666e-05, "loss": 0.5062819957733155, "step": 354410 }, { "epoch": 2.106746081281096, "grad_norm": 1.0347667932510376, "learning_rate": 6.439025157647943e-05, "loss": 0.53317289352417, "step": 354420 }, { "epoch": 2.106805523357764, "grad_norm": 1.6003679037094116, "learning_rate": 6.43848854465943e-05, "loss": 0.5352536201477051, "step": 354430 }, { "epoch": 2.1068649654344322, "grad_norm": 1.3379340171813965, "learning_rate": 6.437951953491699e-05, "loss": 0.5328357696533204, "step": 354440 }, { "epoch": 2.1069244075111007, "grad_norm": 1.3572636842727661, "learning_rate": 6.437415384147313e-05, "loss": 0.5036740303039551, "step": 354450 }, { "epoch": 2.106983849587769, "grad_norm": 1.050750494003296, "learning_rate": 6.436878836628842e-05, "loss": 0.47877254486083987, "step": 354460 }, { "epoch": 2.1070432916644375, "grad_norm": 1.1710444688796997, "learning_rate": 6.436342310938852e-05, "loss": 0.5036484718322753, "step": 354470 }, { "epoch": 2.107102733741106, "grad_norm": 2.428908586502075, "learning_rate": 6.435805807079905e-05, "loss": 0.5090539455413818, "step": 354480 }, { "epoch": 2.1071621758177743, "grad_norm": 1.3580200672149658, "learning_rate": 6.435269325054575e-05, "loss": 0.520485258102417, "step": 354490 }, { "epoch": 2.1072216178944427, "grad_norm": 1.1826953887939453, "learning_rate": 6.434732864865424e-05, "loss": 0.5082803726196289, "step": 354500 }, { "epoch": 2.107281059971111, "grad_norm": 1.232033371925354, "learning_rate": 6.434196426515019e-05, "loss": 0.5576976776123047, "step": 354510 }, { "epoch": 2.1073405020477796, "grad_norm": 1.5936483144760132, "learning_rate": 6.433660010005927e-05, "loss": 0.5125058174133301, "step": 354520 }, { "epoch": 2.107399944124448, "grad_norm": 1.2198127508163452, "learning_rate": 6.433123615340712e-05, "loss": 0.49640693664550783, "step": 354530 }, { "epoch": 2.1074593862011164, "grad_norm": 1.0963343381881714, "learning_rate": 6.432587242521939e-05, "loss": 0.48502264022827146, "step": 354540 }, { "epoch": 2.107518828277785, "grad_norm": 1.6285263299942017, "learning_rate": 6.432050891552179e-05, "loss": 0.5081392765045166, "step": 354550 }, { "epoch": 2.107578270354453, "grad_norm": 1.7829468250274658, "learning_rate": 6.431514562433996e-05, "loss": 0.5058941841125488, "step": 354560 }, { "epoch": 2.1076377124311216, "grad_norm": 1.048352837562561, "learning_rate": 6.430978255169953e-05, "loss": 0.45711779594421387, "step": 354570 }, { "epoch": 2.10769715450779, "grad_norm": 1.9127665758132935, "learning_rate": 6.430441969762617e-05, "loss": 0.47595062255859377, "step": 354580 }, { "epoch": 2.1077565965844585, "grad_norm": 1.4935611486434937, "learning_rate": 6.429905706214552e-05, "loss": 0.5105561256408692, "step": 354590 }, { "epoch": 2.107816038661127, "grad_norm": 1.123091220855713, "learning_rate": 6.429369464528326e-05, "loss": 0.48023247718811035, "step": 354600 }, { "epoch": 2.107875480737795, "grad_norm": 1.3569432497024536, "learning_rate": 6.428833244706499e-05, "loss": 0.49158458709716796, "step": 354610 }, { "epoch": 2.1079349228144633, "grad_norm": 1.0494502782821655, "learning_rate": 6.428297046751644e-05, "loss": 0.44639902114868163, "step": 354620 }, { "epoch": 2.1079943648911317, "grad_norm": 1.7949525117874146, "learning_rate": 6.427760870666322e-05, "loss": 0.5432267189025879, "step": 354630 }, { "epoch": 2.1080538069678, "grad_norm": 1.4782600402832031, "learning_rate": 6.427224716453096e-05, "loss": 0.447862434387207, "step": 354640 }, { "epoch": 2.1081132490444685, "grad_norm": 1.6449487209320068, "learning_rate": 6.426688584114533e-05, "loss": 0.4970833778381348, "step": 354650 }, { "epoch": 2.108172691121137, "grad_norm": 1.4717471599578857, "learning_rate": 6.4261524736532e-05, "loss": 0.5069672584533691, "step": 354660 }, { "epoch": 2.1082321331978053, "grad_norm": 1.3677994012832642, "learning_rate": 6.425616385071655e-05, "loss": 0.5735936164855957, "step": 354670 }, { "epoch": 2.1082915752744738, "grad_norm": 1.3165138959884644, "learning_rate": 6.425080318372465e-05, "loss": 0.5466774463653564, "step": 354680 }, { "epoch": 2.108351017351142, "grad_norm": 1.2004907131195068, "learning_rate": 6.4245442735582e-05, "loss": 0.4840262413024902, "step": 354690 }, { "epoch": 2.1084104594278106, "grad_norm": 1.6650183200836182, "learning_rate": 6.424008250631421e-05, "loss": 0.5011297225952148, "step": 354700 }, { "epoch": 2.108469901504479, "grad_norm": 1.6252802610397339, "learning_rate": 6.423472249594685e-05, "loss": 0.5321230411529541, "step": 354710 }, { "epoch": 2.1085293435811474, "grad_norm": 1.2607444524765015, "learning_rate": 6.422936270450566e-05, "loss": 0.4936357021331787, "step": 354720 }, { "epoch": 2.108588785657816, "grad_norm": 1.4618247747421265, "learning_rate": 6.422400313201624e-05, "loss": 0.5486184120178222, "step": 354730 }, { "epoch": 2.1086482277344842, "grad_norm": 1.4507421255111694, "learning_rate": 6.42186437785042e-05, "loss": 0.506153917312622, "step": 354740 }, { "epoch": 2.1087076698111527, "grad_norm": 1.221604585647583, "learning_rate": 6.421328464399523e-05, "loss": 0.45974173545837405, "step": 354750 }, { "epoch": 2.108767111887821, "grad_norm": 1.33415949344635, "learning_rate": 6.420792572851497e-05, "loss": 0.5034597396850586, "step": 354760 }, { "epoch": 2.1088265539644895, "grad_norm": 1.4605106115341187, "learning_rate": 6.420256703208897e-05, "loss": 0.4787324905395508, "step": 354770 }, { "epoch": 2.108885996041158, "grad_norm": 1.428215503692627, "learning_rate": 6.419720855474298e-05, "loss": 0.5429859638214112, "step": 354780 }, { "epoch": 2.108945438117826, "grad_norm": 1.595292091369629, "learning_rate": 6.419185029650254e-05, "loss": 0.4930551528930664, "step": 354790 }, { "epoch": 2.1090048801944943, "grad_norm": 1.4219454526901245, "learning_rate": 6.418649225739333e-05, "loss": 0.5050178527832031, "step": 354800 }, { "epoch": 2.1090643222711627, "grad_norm": 1.077434778213501, "learning_rate": 6.418113443744094e-05, "loss": 0.5509516716003418, "step": 354810 }, { "epoch": 2.109123764347831, "grad_norm": 1.4490796327590942, "learning_rate": 6.41757768366711e-05, "loss": 0.511358118057251, "step": 354820 }, { "epoch": 2.1091832064244995, "grad_norm": 1.1108382940292358, "learning_rate": 6.417041945510934e-05, "loss": 0.4766093254089355, "step": 354830 }, { "epoch": 2.109242648501168, "grad_norm": 1.272368311882019, "learning_rate": 6.416506229278125e-05, "loss": 0.4919434547424316, "step": 354840 }, { "epoch": 2.1093020905778364, "grad_norm": 1.5649853944778442, "learning_rate": 6.415970534971259e-05, "loss": 0.4589116096496582, "step": 354850 }, { "epoch": 2.1093615326545048, "grad_norm": 1.3419380187988281, "learning_rate": 6.41543486259289e-05, "loss": 0.5234869956970215, "step": 354860 }, { "epoch": 2.109420974731173, "grad_norm": 1.124455451965332, "learning_rate": 6.41489921214558e-05, "loss": 0.5280675888061523, "step": 354870 }, { "epoch": 2.1094804168078416, "grad_norm": 1.26585853099823, "learning_rate": 6.4143635836319e-05, "loss": 0.5019058227539063, "step": 354880 }, { "epoch": 2.10953985888451, "grad_norm": 1.2736635208129883, "learning_rate": 6.413827977054403e-05, "loss": 0.5136072158813476, "step": 354890 }, { "epoch": 2.1095993009611784, "grad_norm": 1.1202802658081055, "learning_rate": 6.41329239241565e-05, "loss": 0.4660823822021484, "step": 354900 }, { "epoch": 2.109658743037847, "grad_norm": 1.3017914295196533, "learning_rate": 6.412756829718212e-05, "loss": 0.533962631225586, "step": 354910 }, { "epoch": 2.1097181851145153, "grad_norm": 1.5154452323913574, "learning_rate": 6.412221288964644e-05, "loss": 0.5674890995025634, "step": 354920 }, { "epoch": 2.1097776271911837, "grad_norm": 1.4495866298675537, "learning_rate": 6.411685770157512e-05, "loss": 0.5274292945861816, "step": 354930 }, { "epoch": 2.109837069267852, "grad_norm": 1.1581120491027832, "learning_rate": 6.411150273299375e-05, "loss": 0.4677927494049072, "step": 354940 }, { "epoch": 2.1098965113445205, "grad_norm": 1.235451340675354, "learning_rate": 6.410614798392795e-05, "loss": 0.49279012680053713, "step": 354950 }, { "epoch": 2.109955953421189, "grad_norm": 1.4563281536102295, "learning_rate": 6.410079345440336e-05, "loss": 0.5127387046813965, "step": 354960 }, { "epoch": 2.1100153954978573, "grad_norm": 1.3829429149627686, "learning_rate": 6.409543914444551e-05, "loss": 0.46903576850891116, "step": 354970 }, { "epoch": 2.1100748375745253, "grad_norm": 1.3195725679397583, "learning_rate": 6.409008505408014e-05, "loss": 0.44364094734191895, "step": 354980 }, { "epoch": 2.1101342796511937, "grad_norm": 1.4586838483810425, "learning_rate": 6.408473118333278e-05, "loss": 0.4890285968780518, "step": 354990 }, { "epoch": 2.110193721727862, "grad_norm": 1.141487717628479, "learning_rate": 6.407937753222908e-05, "loss": 0.4743068695068359, "step": 355000 }, { "epoch": 2.1102531638045305, "grad_norm": 1.499139428138733, "learning_rate": 6.407402410079461e-05, "loss": 0.5302436351776123, "step": 355010 }, { "epoch": 2.110312605881199, "grad_norm": 1.1827006340026855, "learning_rate": 6.406867088905501e-05, "loss": 0.4893465995788574, "step": 355020 }, { "epoch": 2.1103720479578674, "grad_norm": 1.0555490255355835, "learning_rate": 6.406331789703584e-05, "loss": 0.43005976676940916, "step": 355030 }, { "epoch": 2.110431490034536, "grad_norm": 1.5945990085601807, "learning_rate": 6.405796512476278e-05, "loss": 0.47455596923828125, "step": 355040 }, { "epoch": 2.110490932111204, "grad_norm": 1.353628158569336, "learning_rate": 6.40526125722614e-05, "loss": 0.49074182510375974, "step": 355050 }, { "epoch": 2.1105503741878726, "grad_norm": 1.0722613334655762, "learning_rate": 6.404726023955731e-05, "loss": 0.4286344528198242, "step": 355060 }, { "epoch": 2.110609816264541, "grad_norm": 1.6140201091766357, "learning_rate": 6.404190812667612e-05, "loss": 0.49527683258056643, "step": 355070 }, { "epoch": 2.1106692583412094, "grad_norm": 1.3705987930297852, "learning_rate": 6.403655623364341e-05, "loss": 0.5322654724121094, "step": 355080 }, { "epoch": 2.110728700417878, "grad_norm": 1.5062808990478516, "learning_rate": 6.403120456048479e-05, "loss": 0.5079526901245117, "step": 355090 }, { "epoch": 2.1107881424945463, "grad_norm": 1.3174784183502197, "learning_rate": 6.402585310722584e-05, "loss": 0.5029615879058837, "step": 355100 }, { "epoch": 2.1108475845712147, "grad_norm": 1.319886326789856, "learning_rate": 6.40205018738922e-05, "loss": 0.5029659271240234, "step": 355110 }, { "epoch": 2.110907026647883, "grad_norm": 1.4419572353363037, "learning_rate": 6.401515086050947e-05, "loss": 0.478636646270752, "step": 355120 }, { "epoch": 2.1109664687245515, "grad_norm": 1.227391242980957, "learning_rate": 6.400980006710322e-05, "loss": 0.49551897048950194, "step": 355130 }, { "epoch": 2.11102591080122, "grad_norm": 1.2077795267105103, "learning_rate": 6.400444949369906e-05, "loss": 0.5160869598388672, "step": 355140 }, { "epoch": 2.1110853528778883, "grad_norm": 1.236958384513855, "learning_rate": 6.399909914032259e-05, "loss": 0.4942279815673828, "step": 355150 }, { "epoch": 2.1111447949545568, "grad_norm": 1.4552351236343384, "learning_rate": 6.399374900699939e-05, "loss": 0.5078781604766845, "step": 355160 }, { "epoch": 2.1112042370312247, "grad_norm": 1.2783496379852295, "learning_rate": 6.398839909375503e-05, "loss": 0.5187394618988037, "step": 355170 }, { "epoch": 2.111263679107893, "grad_norm": 1.4928443431854248, "learning_rate": 6.398304940061516e-05, "loss": 0.5004142761230469, "step": 355180 }, { "epoch": 2.1113231211845616, "grad_norm": 1.4151670932769775, "learning_rate": 6.397769992760538e-05, "loss": 0.5416601181030274, "step": 355190 }, { "epoch": 2.11138256326123, "grad_norm": 1.2328720092773438, "learning_rate": 6.397235067475118e-05, "loss": 0.486740779876709, "step": 355200 }, { "epoch": 2.1114420053378984, "grad_norm": 1.2794783115386963, "learning_rate": 6.396700164207824e-05, "loss": 0.4709341049194336, "step": 355210 }, { "epoch": 2.111501447414567, "grad_norm": 1.4226676225662231, "learning_rate": 6.396165282961213e-05, "loss": 0.5584903240203858, "step": 355220 }, { "epoch": 2.111560889491235, "grad_norm": 1.4140064716339111, "learning_rate": 6.395630423737837e-05, "loss": 0.49051389694213865, "step": 355230 }, { "epoch": 2.1116203315679036, "grad_norm": 1.0656646490097046, "learning_rate": 6.395095586540267e-05, "loss": 0.4359996795654297, "step": 355240 }, { "epoch": 2.111679773644572, "grad_norm": 1.4796173572540283, "learning_rate": 6.394560771371056e-05, "loss": 0.5255278587341309, "step": 355250 }, { "epoch": 2.1117392157212405, "grad_norm": 1.1176388263702393, "learning_rate": 6.394025978232754e-05, "loss": 0.49164466857910155, "step": 355260 }, { "epoch": 2.111798657797909, "grad_norm": 1.2415211200714111, "learning_rate": 6.39349120712793e-05, "loss": 0.4982107162475586, "step": 355270 }, { "epoch": 2.1118580998745773, "grad_norm": 1.2979235649108887, "learning_rate": 6.39295645805914e-05, "loss": 0.5008824825286865, "step": 355280 }, { "epoch": 2.1119175419512457, "grad_norm": 1.0397758483886719, "learning_rate": 6.39242173102894e-05, "loss": 0.453204345703125, "step": 355290 }, { "epoch": 2.111976984027914, "grad_norm": 1.2405472993850708, "learning_rate": 6.391887026039885e-05, "loss": 0.5347072601318359, "step": 355300 }, { "epoch": 2.1120364261045825, "grad_norm": 1.4190237522125244, "learning_rate": 6.391352343094545e-05, "loss": 0.4403711795806885, "step": 355310 }, { "epoch": 2.112095868181251, "grad_norm": 1.2155845165252686, "learning_rate": 6.390817682195465e-05, "loss": 0.4489619255065918, "step": 355320 }, { "epoch": 2.1121553102579194, "grad_norm": 1.3928637504577637, "learning_rate": 6.390283043345202e-05, "loss": 0.5462767601013183, "step": 355330 }, { "epoch": 2.1122147523345878, "grad_norm": 1.6550121307373047, "learning_rate": 6.389748426546322e-05, "loss": 0.5091030120849609, "step": 355340 }, { "epoch": 2.1122741944112557, "grad_norm": 1.5087738037109375, "learning_rate": 6.389213831801381e-05, "loss": 0.4675088882446289, "step": 355350 }, { "epoch": 2.112333636487924, "grad_norm": 1.761217474937439, "learning_rate": 6.38867925911293e-05, "loss": 0.5648554801940918, "step": 355360 }, { "epoch": 2.1123930785645926, "grad_norm": 1.5100873708724976, "learning_rate": 6.388144708483536e-05, "loss": 0.46984386444091797, "step": 355370 }, { "epoch": 2.112452520641261, "grad_norm": 1.090943694114685, "learning_rate": 6.387610179915748e-05, "loss": 0.515507173538208, "step": 355380 }, { "epoch": 2.1125119627179294, "grad_norm": 1.5179424285888672, "learning_rate": 6.387075673412122e-05, "loss": 0.5174660682678223, "step": 355390 }, { "epoch": 2.112571404794598, "grad_norm": 1.2020167112350464, "learning_rate": 6.386541188975223e-05, "loss": 0.4132668972015381, "step": 355400 }, { "epoch": 2.1126308468712662, "grad_norm": 1.4879695177078247, "learning_rate": 6.386006726607601e-05, "loss": 0.5031432628631591, "step": 355410 }, { "epoch": 2.1126902889479346, "grad_norm": 1.2880972623825073, "learning_rate": 6.385472286311816e-05, "loss": 0.5161446571350098, "step": 355420 }, { "epoch": 2.112749731024603, "grad_norm": 1.1092997789382935, "learning_rate": 6.384937868090424e-05, "loss": 0.5079643249511718, "step": 355430 }, { "epoch": 2.1128091731012715, "grad_norm": 1.2121611833572388, "learning_rate": 6.38440347194598e-05, "loss": 0.47205157279968263, "step": 355440 }, { "epoch": 2.11286861517794, "grad_norm": 1.6429035663604736, "learning_rate": 6.383869097881043e-05, "loss": 0.4991626739501953, "step": 355450 }, { "epoch": 2.1129280572546083, "grad_norm": 1.3804932832717896, "learning_rate": 6.383334745898164e-05, "loss": 0.5141577243804931, "step": 355460 }, { "epoch": 2.1129874993312767, "grad_norm": 1.3429338932037354, "learning_rate": 6.382800415999906e-05, "loss": 0.47968235015869143, "step": 355470 }, { "epoch": 2.113046941407945, "grad_norm": 1.299558162689209, "learning_rate": 6.382266108188822e-05, "loss": 0.5006946086883545, "step": 355480 }, { "epoch": 2.1131063834846135, "grad_norm": 1.57901132106781, "learning_rate": 6.381731822467465e-05, "loss": 0.5540682792663574, "step": 355490 }, { "epoch": 2.113165825561282, "grad_norm": 1.2694867849349976, "learning_rate": 6.381197558838398e-05, "loss": 0.5039322376251221, "step": 355500 }, { "epoch": 2.1132252676379504, "grad_norm": 1.1945894956588745, "learning_rate": 6.38066331730417e-05, "loss": 0.5190223217010498, "step": 355510 }, { "epoch": 2.113284709714619, "grad_norm": 1.7192376852035522, "learning_rate": 6.380129097867339e-05, "loss": 0.5400679588317872, "step": 355520 }, { "epoch": 2.1133441517912868, "grad_norm": 0.9592568278312683, "learning_rate": 6.379594900530459e-05, "loss": 0.44592914581298826, "step": 355530 }, { "epoch": 2.113403593867955, "grad_norm": 1.4547019004821777, "learning_rate": 6.379060725296089e-05, "loss": 0.5188058376312256, "step": 355540 }, { "epoch": 2.1134630359446236, "grad_norm": 1.197397232055664, "learning_rate": 6.378526572166781e-05, "loss": 0.5501106262207032, "step": 355550 }, { "epoch": 2.113522478021292, "grad_norm": 1.2961994409561157, "learning_rate": 6.377992441145095e-05, "loss": 0.5485928535461426, "step": 355560 }, { "epoch": 2.1135819200979604, "grad_norm": 1.3755146265029907, "learning_rate": 6.37745833223358e-05, "loss": 0.5034933090209961, "step": 355570 }, { "epoch": 2.113641362174629, "grad_norm": 1.4114573001861572, "learning_rate": 6.376924245434795e-05, "loss": 0.5001954078674317, "step": 355580 }, { "epoch": 2.1137008042512972, "grad_norm": 1.4835412502288818, "learning_rate": 6.376390180751288e-05, "loss": 0.46028881072998046, "step": 355590 }, { "epoch": 2.1137602463279657, "grad_norm": 1.7258580923080444, "learning_rate": 6.375856138185625e-05, "loss": 0.5179546356201172, "step": 355600 }, { "epoch": 2.113819688404634, "grad_norm": 1.2217576503753662, "learning_rate": 6.375322117740354e-05, "loss": 0.49968781471252444, "step": 355610 }, { "epoch": 2.1138791304813025, "grad_norm": 1.2610281705856323, "learning_rate": 6.374788119418033e-05, "loss": 0.5400903701782227, "step": 355620 }, { "epoch": 2.113938572557971, "grad_norm": 1.4047352075576782, "learning_rate": 6.374254143221211e-05, "loss": 0.4930723190307617, "step": 355630 }, { "epoch": 2.1139980146346393, "grad_norm": 1.1644569635391235, "learning_rate": 6.373720189152448e-05, "loss": 0.538570785522461, "step": 355640 }, { "epoch": 2.1140574567113077, "grad_norm": 1.2165383100509644, "learning_rate": 6.373186257214295e-05, "loss": 0.5130472183227539, "step": 355650 }, { "epoch": 2.114116898787976, "grad_norm": 1.316757321357727, "learning_rate": 6.372652347409302e-05, "loss": 0.532679271697998, "step": 355660 }, { "epoch": 2.1141763408646446, "grad_norm": 1.3592416048049927, "learning_rate": 6.372118459740031e-05, "loss": 0.49900045394897463, "step": 355670 }, { "epoch": 2.114235782941313, "grad_norm": 1.6132653951644897, "learning_rate": 6.371584594209035e-05, "loss": 0.49288120269775393, "step": 355680 }, { "epoch": 2.1142952250179814, "grad_norm": 0.9592468738555908, "learning_rate": 6.371050750818864e-05, "loss": 0.4850612640380859, "step": 355690 }, { "epoch": 2.11435466709465, "grad_norm": 1.7024059295654297, "learning_rate": 6.370516929572074e-05, "loss": 0.5472275257110596, "step": 355700 }, { "epoch": 2.1144141091713182, "grad_norm": 1.4716191291809082, "learning_rate": 6.36998313047122e-05, "loss": 0.5293267250061036, "step": 355710 }, { "epoch": 2.114473551247986, "grad_norm": 1.5854541063308716, "learning_rate": 6.369449353518847e-05, "loss": 0.5221163749694824, "step": 355720 }, { "epoch": 2.1145329933246546, "grad_norm": 1.1386237144470215, "learning_rate": 6.368915598717521e-05, "loss": 0.5313569068908691, "step": 355730 }, { "epoch": 2.114592435401323, "grad_norm": 1.3090825080871582, "learning_rate": 6.368381866069789e-05, "loss": 0.503383731842041, "step": 355740 }, { "epoch": 2.1146518774779914, "grad_norm": 1.4884201288223267, "learning_rate": 6.367848155578202e-05, "loss": 0.5003024101257324, "step": 355750 }, { "epoch": 2.11471131955466, "grad_norm": 1.471338152885437, "learning_rate": 6.367314467245317e-05, "loss": 0.5142453193664551, "step": 355760 }, { "epoch": 2.1147707616313283, "grad_norm": 1.549803614616394, "learning_rate": 6.366780801073686e-05, "loss": 0.49396581649780275, "step": 355770 }, { "epoch": 2.1148302037079967, "grad_norm": 1.3019753694534302, "learning_rate": 6.366247157065864e-05, "loss": 0.47830734252929685, "step": 355780 }, { "epoch": 2.114889645784665, "grad_norm": 1.2422735691070557, "learning_rate": 6.365713535224393e-05, "loss": 0.5072959899902344, "step": 355790 }, { "epoch": 2.1149490878613335, "grad_norm": 1.0270264148712158, "learning_rate": 6.365179935551844e-05, "loss": 0.46217641830444334, "step": 355800 }, { "epoch": 2.115008529938002, "grad_norm": 1.071227788925171, "learning_rate": 6.364646358050754e-05, "loss": 0.5044784545898438, "step": 355810 }, { "epoch": 2.1150679720146703, "grad_norm": 1.7966907024383545, "learning_rate": 6.36411280272368e-05, "loss": 0.4987054347991943, "step": 355820 }, { "epoch": 2.1151274140913388, "grad_norm": 1.4649035930633545, "learning_rate": 6.363579269573176e-05, "loss": 0.49285364151000977, "step": 355830 }, { "epoch": 2.115186856168007, "grad_norm": 1.5701361894607544, "learning_rate": 6.363045758601797e-05, "loss": 0.5418464660644531, "step": 355840 }, { "epoch": 2.1152462982446756, "grad_norm": 1.4503746032714844, "learning_rate": 6.362512269812087e-05, "loss": 0.5048776626586914, "step": 355850 }, { "epoch": 2.115305740321344, "grad_norm": 1.2094817161560059, "learning_rate": 6.361978803206608e-05, "loss": 0.4752813816070557, "step": 355860 }, { "epoch": 2.1153651823980124, "grad_norm": 1.1664201021194458, "learning_rate": 6.361445358787905e-05, "loss": 0.47266159057617185, "step": 355870 }, { "epoch": 2.115424624474681, "grad_norm": 1.2234307527542114, "learning_rate": 6.360911936558527e-05, "loss": 0.5174224376678467, "step": 355880 }, { "epoch": 2.1154840665513492, "grad_norm": 1.4412676095962524, "learning_rate": 6.360378536521033e-05, "loss": 0.49480395317077636, "step": 355890 }, { "epoch": 2.1155435086280177, "grad_norm": 1.1320072412490845, "learning_rate": 6.359845158677973e-05, "loss": 0.5217636108398438, "step": 355900 }, { "epoch": 2.1156029507046856, "grad_norm": 1.2634893655776978, "learning_rate": 6.359311803031897e-05, "loss": 0.49535403251647947, "step": 355910 }, { "epoch": 2.115662392781354, "grad_norm": 1.2688076496124268, "learning_rate": 6.358778469585358e-05, "loss": 0.48995485305786135, "step": 355920 }, { "epoch": 2.1157218348580225, "grad_norm": 1.451261043548584, "learning_rate": 6.358245158340906e-05, "loss": 0.4919316291809082, "step": 355930 }, { "epoch": 2.115781276934691, "grad_norm": 1.1109249591827393, "learning_rate": 6.35771186930109e-05, "loss": 0.47100372314453126, "step": 355940 }, { "epoch": 2.1158407190113593, "grad_norm": 1.4149906635284424, "learning_rate": 6.357178602468461e-05, "loss": 0.48043217658996584, "step": 355950 }, { "epoch": 2.1159001610880277, "grad_norm": 1.070888638496399, "learning_rate": 6.356645357845577e-05, "loss": 0.5064801216125489, "step": 355960 }, { "epoch": 2.115959603164696, "grad_norm": 1.4731669425964355, "learning_rate": 6.356112135434981e-05, "loss": 0.5446250438690186, "step": 355970 }, { "epoch": 2.1160190452413645, "grad_norm": 1.2418838739395142, "learning_rate": 6.35557893523923e-05, "loss": 0.5041211605072021, "step": 355980 }, { "epoch": 2.116078487318033, "grad_norm": 1.2917661666870117, "learning_rate": 6.35504575726087e-05, "loss": 0.518887710571289, "step": 355990 }, { "epoch": 2.1161379293947014, "grad_norm": 1.6768791675567627, "learning_rate": 6.354512601502454e-05, "loss": 0.4761871337890625, "step": 356000 }, { "epoch": 2.1161973714713698, "grad_norm": 1.328932285308838, "learning_rate": 6.35397946796653e-05, "loss": 0.5206449508666993, "step": 356010 }, { "epoch": 2.116256813548038, "grad_norm": 1.3573195934295654, "learning_rate": 6.353446356655648e-05, "loss": 0.497102165222168, "step": 356020 }, { "epoch": 2.1163162556247066, "grad_norm": 1.3428332805633545, "learning_rate": 6.352913267572362e-05, "loss": 0.46259775161743166, "step": 356030 }, { "epoch": 2.116375697701375, "grad_norm": 1.3795686960220337, "learning_rate": 6.35238020071922e-05, "loss": 0.5087413787841797, "step": 356040 }, { "epoch": 2.1164351397780434, "grad_norm": 1.2339386940002441, "learning_rate": 6.351847156098775e-05, "loss": 0.5189435958862305, "step": 356050 }, { "epoch": 2.116494581854712, "grad_norm": 1.0120229721069336, "learning_rate": 6.351314133713573e-05, "loss": 0.44833669662475584, "step": 356060 }, { "epoch": 2.1165540239313803, "grad_norm": 1.1414555311203003, "learning_rate": 6.350781133566165e-05, "loss": 0.4995570182800293, "step": 356070 }, { "epoch": 2.1166134660080487, "grad_norm": 1.1891019344329834, "learning_rate": 6.350248155659097e-05, "loss": 0.5680253028869628, "step": 356080 }, { "epoch": 2.1166729080847166, "grad_norm": 1.4583874940872192, "learning_rate": 6.349715199994925e-05, "loss": 0.46166701316833497, "step": 356090 }, { "epoch": 2.116732350161385, "grad_norm": 1.4115371704101562, "learning_rate": 6.349182266576198e-05, "loss": 0.512279462814331, "step": 356100 }, { "epoch": 2.1167917922380535, "grad_norm": 1.3259762525558472, "learning_rate": 6.348649355405461e-05, "loss": 0.4743372917175293, "step": 356110 }, { "epoch": 2.116851234314722, "grad_norm": 1.5466843843460083, "learning_rate": 6.348116466485266e-05, "loss": 0.5035686492919922, "step": 356120 }, { "epoch": 2.1169106763913903, "grad_norm": 1.305401086807251, "learning_rate": 6.347583599818161e-05, "loss": 0.5293007850646972, "step": 356130 }, { "epoch": 2.1169701184680587, "grad_norm": 1.104448914527893, "learning_rate": 6.347050755406696e-05, "loss": 0.46613368988037107, "step": 356140 }, { "epoch": 2.117029560544727, "grad_norm": 1.5449352264404297, "learning_rate": 6.346517933253416e-05, "loss": 0.5265548706054688, "step": 356150 }, { "epoch": 2.1170890026213955, "grad_norm": 1.644301414489746, "learning_rate": 6.345985133360877e-05, "loss": 0.5197368621826172, "step": 356160 }, { "epoch": 2.117148444698064, "grad_norm": 0.9564315676689148, "learning_rate": 6.345452355731625e-05, "loss": 0.48396501541137693, "step": 356170 }, { "epoch": 2.1172078867747324, "grad_norm": 1.2928553819656372, "learning_rate": 6.344919600368207e-05, "loss": 0.5040711402893067, "step": 356180 }, { "epoch": 2.117267328851401, "grad_norm": 1.8500301837921143, "learning_rate": 6.344386867273172e-05, "loss": 0.520481014251709, "step": 356190 }, { "epoch": 2.117326770928069, "grad_norm": 1.5887258052825928, "learning_rate": 6.343854156449069e-05, "loss": 0.5204286575317383, "step": 356200 }, { "epoch": 2.1173862130047376, "grad_norm": 1.2942640781402588, "learning_rate": 6.343321467898443e-05, "loss": 0.46642189025878905, "step": 356210 }, { "epoch": 2.117445655081406, "grad_norm": 1.461983323097229, "learning_rate": 6.342788801623849e-05, "loss": 0.49736199378967283, "step": 356220 }, { "epoch": 2.1175050971580744, "grad_norm": 1.2820136547088623, "learning_rate": 6.342256157627831e-05, "loss": 0.4683095455169678, "step": 356230 }, { "epoch": 2.117564539234743, "grad_norm": 1.3750003576278687, "learning_rate": 6.341723535912938e-05, "loss": 0.47807536125183103, "step": 356240 }, { "epoch": 2.1176239813114113, "grad_norm": 1.1906954050064087, "learning_rate": 6.341190936481715e-05, "loss": 0.5042068958282471, "step": 356250 }, { "epoch": 2.1176834233880797, "grad_norm": 1.1761382818222046, "learning_rate": 6.340658359336715e-05, "loss": 0.5068440437316895, "step": 356260 }, { "epoch": 2.1177428654647477, "grad_norm": 1.342292308807373, "learning_rate": 6.340125804480481e-05, "loss": 0.5306767463684082, "step": 356270 }, { "epoch": 2.117802307541416, "grad_norm": 1.64128839969635, "learning_rate": 6.339593271915559e-05, "loss": 0.522456169128418, "step": 356280 }, { "epoch": 2.1178617496180845, "grad_norm": 1.1582087278366089, "learning_rate": 6.339060761644503e-05, "loss": 0.46346235275268555, "step": 356290 }, { "epoch": 2.117921191694753, "grad_norm": 1.2520923614501953, "learning_rate": 6.338528273669861e-05, "loss": 0.4756310939788818, "step": 356300 }, { "epoch": 2.1179806337714213, "grad_norm": 1.0424233675003052, "learning_rate": 6.337995807994171e-05, "loss": 0.484926176071167, "step": 356310 }, { "epoch": 2.1180400758480897, "grad_norm": 1.525579810142517, "learning_rate": 6.337463364619985e-05, "loss": 0.5107891082763671, "step": 356320 }, { "epoch": 2.118099517924758, "grad_norm": 1.577802062034607, "learning_rate": 6.336930943549854e-05, "loss": 0.5039814949035645, "step": 356330 }, { "epoch": 2.1181589600014266, "grad_norm": 1.1371119022369385, "learning_rate": 6.336398544786316e-05, "loss": 0.5080582618713378, "step": 356340 }, { "epoch": 2.118218402078095, "grad_norm": 1.3964999914169312, "learning_rate": 6.335866168331929e-05, "loss": 0.4957447052001953, "step": 356350 }, { "epoch": 2.1182778441547634, "grad_norm": 1.3702349662780762, "learning_rate": 6.335333814189235e-05, "loss": 0.5057193279266358, "step": 356360 }, { "epoch": 2.118337286231432, "grad_norm": 1.0886179208755493, "learning_rate": 6.334801482360773e-05, "loss": 0.49811925888061526, "step": 356370 }, { "epoch": 2.1183967283081, "grad_norm": 1.4487375020980835, "learning_rate": 6.3342691728491e-05, "loss": 0.48580183982849123, "step": 356380 }, { "epoch": 2.1184561703847686, "grad_norm": 1.079209804534912, "learning_rate": 6.33373688565676e-05, "loss": 0.4786074638366699, "step": 356390 }, { "epoch": 2.118515612461437, "grad_norm": 1.3187049627304077, "learning_rate": 6.333204620786297e-05, "loss": 0.45389766693115235, "step": 356400 }, { "epoch": 2.1185750545381055, "grad_norm": 1.0300605297088623, "learning_rate": 6.332672378240257e-05, "loss": 0.4643708229064941, "step": 356410 }, { "epoch": 2.118634496614774, "grad_norm": 1.1927940845489502, "learning_rate": 6.332140158021189e-05, "loss": 0.48571176528930665, "step": 356420 }, { "epoch": 2.1186939386914423, "grad_norm": 1.1067594289779663, "learning_rate": 6.331607960131633e-05, "loss": 0.48149929046630857, "step": 356430 }, { "epoch": 2.1187533807681107, "grad_norm": 1.369338870048523, "learning_rate": 6.331075784574139e-05, "loss": 0.548346757888794, "step": 356440 }, { "epoch": 2.118812822844779, "grad_norm": 1.2764534950256348, "learning_rate": 6.330543631351256e-05, "loss": 0.5378132820129394, "step": 356450 }, { "epoch": 2.118872264921447, "grad_norm": 1.3240903615951538, "learning_rate": 6.330011500465525e-05, "loss": 0.5107161045074463, "step": 356460 }, { "epoch": 2.1189317069981155, "grad_norm": 1.7709362506866455, "learning_rate": 6.329479391919493e-05, "loss": 0.5128127098083496, "step": 356470 }, { "epoch": 2.118991149074784, "grad_norm": 1.5340306758880615, "learning_rate": 6.328947305715706e-05, "loss": 0.4653223991394043, "step": 356480 }, { "epoch": 2.1190505911514523, "grad_norm": 1.3642983436584473, "learning_rate": 6.328415241856707e-05, "loss": 0.5243225574493409, "step": 356490 }, { "epoch": 2.1191100332281207, "grad_norm": 1.3541232347488403, "learning_rate": 6.327883200345044e-05, "loss": 0.4711743354797363, "step": 356500 }, { "epoch": 2.119169475304789, "grad_norm": 1.682224988937378, "learning_rate": 6.327351181183257e-05, "loss": 0.5445111274719239, "step": 356510 }, { "epoch": 2.1192289173814576, "grad_norm": 0.9926389455795288, "learning_rate": 6.3268191843739e-05, "loss": 0.5498997211456299, "step": 356520 }, { "epoch": 2.119288359458126, "grad_norm": 1.0719358921051025, "learning_rate": 6.32628720991951e-05, "loss": 0.5099356651306153, "step": 356530 }, { "epoch": 2.1193478015347944, "grad_norm": 1.7650234699249268, "learning_rate": 6.325755257822636e-05, "loss": 0.5721072196960449, "step": 356540 }, { "epoch": 2.119407243611463, "grad_norm": 1.3979160785675049, "learning_rate": 6.325223328085821e-05, "loss": 0.5556694030761719, "step": 356550 }, { "epoch": 2.1194666856881312, "grad_norm": 1.354902744293213, "learning_rate": 6.324691420711612e-05, "loss": 0.5143286228179932, "step": 356560 }, { "epoch": 2.1195261277647997, "grad_norm": 1.3518285751342773, "learning_rate": 6.324159535702545e-05, "loss": 0.5008170127868652, "step": 356570 }, { "epoch": 2.119585569841468, "grad_norm": 1.3597570657730103, "learning_rate": 6.323627673061175e-05, "loss": 0.4707827091217041, "step": 356580 }, { "epoch": 2.1196450119181365, "grad_norm": 1.4934110641479492, "learning_rate": 6.323095832790042e-05, "loss": 0.4964646816253662, "step": 356590 }, { "epoch": 2.119704453994805, "grad_norm": 1.2350953817367554, "learning_rate": 6.322564014891693e-05, "loss": 0.48120551109313964, "step": 356600 }, { "epoch": 2.1197638960714733, "grad_norm": 1.304490327835083, "learning_rate": 6.322032219368664e-05, "loss": 0.4764653205871582, "step": 356610 }, { "epoch": 2.1198233381481417, "grad_norm": 1.2557761669158936, "learning_rate": 6.321500446223508e-05, "loss": 0.47427687644958494, "step": 356620 }, { "epoch": 2.11988278022481, "grad_norm": 1.2069072723388672, "learning_rate": 6.320968695458763e-05, "loss": 0.5214697837829589, "step": 356630 }, { "epoch": 2.1199422223014786, "grad_norm": 1.541138768196106, "learning_rate": 6.32043696707697e-05, "loss": 0.5251004219055175, "step": 356640 }, { "epoch": 2.1200016643781465, "grad_norm": 2.069434881210327, "learning_rate": 6.319905261080683e-05, "loss": 0.5194314479827881, "step": 356650 }, { "epoch": 2.120061106454815, "grad_norm": 1.4942594766616821, "learning_rate": 6.31937357747244e-05, "loss": 0.5174143314361572, "step": 356660 }, { "epoch": 2.1201205485314834, "grad_norm": 1.3015702962875366, "learning_rate": 6.318841916254783e-05, "loss": 0.5286384582519531, "step": 356670 }, { "epoch": 2.1201799906081518, "grad_norm": 1.6582062244415283, "learning_rate": 6.318310277430256e-05, "loss": 0.5529589653015137, "step": 356680 }, { "epoch": 2.12023943268482, "grad_norm": 1.464137077331543, "learning_rate": 6.317778661001403e-05, "loss": 0.5346854209899903, "step": 356690 }, { "epoch": 2.1202988747614886, "grad_norm": 1.4146918058395386, "learning_rate": 6.317247066970763e-05, "loss": 0.5150151252746582, "step": 356700 }, { "epoch": 2.120358316838157, "grad_norm": 1.3674490451812744, "learning_rate": 6.316715495340888e-05, "loss": 0.5173904895782471, "step": 356710 }, { "epoch": 2.1204177589148254, "grad_norm": 1.0057992935180664, "learning_rate": 6.316183946114315e-05, "loss": 0.5150413990020752, "step": 356720 }, { "epoch": 2.120477200991494, "grad_norm": 1.3949741125106812, "learning_rate": 6.315652419293586e-05, "loss": 0.5247544288635254, "step": 356730 }, { "epoch": 2.1205366430681623, "grad_norm": 1.3297511339187622, "learning_rate": 6.315120914881245e-05, "loss": 0.5566801071166992, "step": 356740 }, { "epoch": 2.1205960851448307, "grad_norm": 1.2971687316894531, "learning_rate": 6.314589432879835e-05, "loss": 0.4945899486541748, "step": 356750 }, { "epoch": 2.120655527221499, "grad_norm": 1.5600634813308716, "learning_rate": 6.314057973291899e-05, "loss": 0.5545185089111329, "step": 356760 }, { "epoch": 2.1207149692981675, "grad_norm": 1.3881641626358032, "learning_rate": 6.313526536119974e-05, "loss": 0.5323873043060303, "step": 356770 }, { "epoch": 2.120774411374836, "grad_norm": 1.3944838047027588, "learning_rate": 6.31299512136661e-05, "loss": 0.5032134056091309, "step": 356780 }, { "epoch": 2.1208338534515043, "grad_norm": 1.2320339679718018, "learning_rate": 6.312463729034348e-05, "loss": 0.5343256950378418, "step": 356790 }, { "epoch": 2.1208932955281727, "grad_norm": 1.228188157081604, "learning_rate": 6.31193235912572e-05, "loss": 0.48306026458740237, "step": 356800 }, { "epoch": 2.120952737604841, "grad_norm": 1.283804178237915, "learning_rate": 6.311401011643282e-05, "loss": 0.5075764656066895, "step": 356810 }, { "epoch": 2.121012179681509, "grad_norm": 1.4027563333511353, "learning_rate": 6.310869686589568e-05, "loss": 0.47085909843444823, "step": 356820 }, { "epoch": 2.1210716217581775, "grad_norm": 1.4112261533737183, "learning_rate": 6.310338383967118e-05, "loss": 0.4933070182800293, "step": 356830 }, { "epoch": 2.121131063834846, "grad_norm": 1.3116905689239502, "learning_rate": 6.309807103778478e-05, "loss": 0.5459444522857666, "step": 356840 }, { "epoch": 2.1211905059115144, "grad_norm": 1.389711856842041, "learning_rate": 6.309275846026192e-05, "loss": 0.5179187774658203, "step": 356850 }, { "epoch": 2.121249947988183, "grad_norm": 1.6078100204467773, "learning_rate": 6.308744610712795e-05, "loss": 0.49110074043273927, "step": 356860 }, { "epoch": 2.121309390064851, "grad_norm": 1.2072221040725708, "learning_rate": 6.308213397840829e-05, "loss": 0.47946977615356445, "step": 356870 }, { "epoch": 2.1213688321415196, "grad_norm": 1.0903300046920776, "learning_rate": 6.307682207412838e-05, "loss": 0.5124281883239746, "step": 356880 }, { "epoch": 2.121428274218188, "grad_norm": 1.2418733835220337, "learning_rate": 6.307151039431363e-05, "loss": 0.5068658828735352, "step": 356890 }, { "epoch": 2.1214877162948564, "grad_norm": 1.4632982015609741, "learning_rate": 6.306619893898938e-05, "loss": 0.5013539791107178, "step": 356900 }, { "epoch": 2.121547158371525, "grad_norm": 1.546829342842102, "learning_rate": 6.30608877081812e-05, "loss": 0.5309375762939453, "step": 356910 }, { "epoch": 2.1216066004481933, "grad_norm": 1.3309648036956787, "learning_rate": 6.305557670191433e-05, "loss": 0.47438993453979494, "step": 356920 }, { "epoch": 2.1216660425248617, "grad_norm": 1.492043375968933, "learning_rate": 6.305026592021421e-05, "loss": 0.4703707695007324, "step": 356930 }, { "epoch": 2.12172548460153, "grad_norm": 1.0132859945297241, "learning_rate": 6.304495536310632e-05, "loss": 0.5117324829101563, "step": 356940 }, { "epoch": 2.1217849266781985, "grad_norm": 1.0961105823516846, "learning_rate": 6.303964503061601e-05, "loss": 0.47361316680908205, "step": 356950 }, { "epoch": 2.121844368754867, "grad_norm": 1.4538064002990723, "learning_rate": 6.303433492276866e-05, "loss": 0.5065538883209229, "step": 356960 }, { "epoch": 2.1219038108315353, "grad_norm": 1.5508469343185425, "learning_rate": 6.302902503958977e-05, "loss": 0.5026015281677246, "step": 356970 }, { "epoch": 2.1219632529082038, "grad_norm": 1.4787235260009766, "learning_rate": 6.302371538110462e-05, "loss": 0.50250244140625, "step": 356980 }, { "epoch": 2.122022694984872, "grad_norm": 1.116641879081726, "learning_rate": 6.30184059473387e-05, "loss": 0.4872828483581543, "step": 356990 }, { "epoch": 2.1220821370615406, "grad_norm": 1.338891625404358, "learning_rate": 6.301309673831732e-05, "loss": 0.5070320129394531, "step": 357000 }, { "epoch": 2.1221415791382086, "grad_norm": 1.4550954103469849, "learning_rate": 6.300778775406597e-05, "loss": 0.5022139549255371, "step": 357010 }, { "epoch": 2.122201021214877, "grad_norm": 2.2579891681671143, "learning_rate": 6.300247899461e-05, "loss": 0.5079607009887696, "step": 357020 }, { "epoch": 2.1222604632915454, "grad_norm": 1.4766231775283813, "learning_rate": 6.299717045997481e-05, "loss": 0.5146126270294189, "step": 357030 }, { "epoch": 2.122319905368214, "grad_norm": 1.4209437370300293, "learning_rate": 6.29918621501858e-05, "loss": 0.5239524841308594, "step": 357040 }, { "epoch": 2.122379347444882, "grad_norm": 1.468650460243225, "learning_rate": 6.298655406526835e-05, "loss": 0.5355749130249023, "step": 357050 }, { "epoch": 2.1224387895215506, "grad_norm": 2.0456106662750244, "learning_rate": 6.298124620524785e-05, "loss": 0.49381608963012696, "step": 357060 }, { "epoch": 2.122498231598219, "grad_norm": 1.440236210823059, "learning_rate": 6.297593857014971e-05, "loss": 0.49937734603881834, "step": 357070 }, { "epoch": 2.1225576736748875, "grad_norm": 1.7654987573623657, "learning_rate": 6.297063115999932e-05, "loss": 0.6060618877410888, "step": 357080 }, { "epoch": 2.122617115751556, "grad_norm": 1.539641261100769, "learning_rate": 6.296532397482207e-05, "loss": 0.5091627597808838, "step": 357090 }, { "epoch": 2.1226765578282243, "grad_norm": 1.259968638420105, "learning_rate": 6.296001701464334e-05, "loss": 0.4830453872680664, "step": 357100 }, { "epoch": 2.1227359999048927, "grad_norm": 1.5549030303955078, "learning_rate": 6.29547102794885e-05, "loss": 0.46230926513671877, "step": 357110 }, { "epoch": 2.122795441981561, "grad_norm": 1.0765682458877563, "learning_rate": 6.294940376938297e-05, "loss": 0.4786327362060547, "step": 357120 }, { "epoch": 2.1228548840582295, "grad_norm": 1.4695125818252563, "learning_rate": 6.294409748435208e-05, "loss": 0.5160318851470947, "step": 357130 }, { "epoch": 2.122914326134898, "grad_norm": 1.5063576698303223, "learning_rate": 6.293879142442126e-05, "loss": 0.5072641849517823, "step": 357140 }, { "epoch": 2.1229737682115664, "grad_norm": 1.162436604499817, "learning_rate": 6.293348558961591e-05, "loss": 0.4593989372253418, "step": 357150 }, { "epoch": 2.1230332102882348, "grad_norm": 1.2439539432525635, "learning_rate": 6.292817997996137e-05, "loss": 0.5024318218231201, "step": 357160 }, { "epoch": 2.123092652364903, "grad_norm": 1.0422194004058838, "learning_rate": 6.292287459548304e-05, "loss": 0.4975489616394043, "step": 357170 }, { "epoch": 2.1231520944415716, "grad_norm": 1.5298653841018677, "learning_rate": 6.291756943620628e-05, "loss": 0.5067785739898681, "step": 357180 }, { "epoch": 2.12321153651824, "grad_norm": 1.0578755140304565, "learning_rate": 6.291226450215646e-05, "loss": 0.5402642250061035, "step": 357190 }, { "epoch": 2.123270978594908, "grad_norm": 1.333689570426941, "learning_rate": 6.2906959793359e-05, "loss": 0.4916365623474121, "step": 357200 }, { "epoch": 2.1233304206715764, "grad_norm": 1.5858094692230225, "learning_rate": 6.290165530983927e-05, "loss": 0.4841665267944336, "step": 357210 }, { "epoch": 2.123389862748245, "grad_norm": 1.8251914978027344, "learning_rate": 6.289635105162262e-05, "loss": 0.49962377548217773, "step": 357220 }, { "epoch": 2.1234493048249132, "grad_norm": 1.2473891973495483, "learning_rate": 6.289104701873442e-05, "loss": 0.5333511352539062, "step": 357230 }, { "epoch": 2.1235087469015816, "grad_norm": 1.3850951194763184, "learning_rate": 6.28857432112001e-05, "loss": 0.5430661201477051, "step": 357240 }, { "epoch": 2.12356818897825, "grad_norm": 1.5192545652389526, "learning_rate": 6.288043962904495e-05, "loss": 0.4962409019470215, "step": 357250 }, { "epoch": 2.1236276310549185, "grad_norm": 1.4906175136566162, "learning_rate": 6.287513627229435e-05, "loss": 0.46138429641723633, "step": 357260 }, { "epoch": 2.123687073131587, "grad_norm": 1.1480038166046143, "learning_rate": 6.286983314097373e-05, "loss": 0.4594737529754639, "step": 357270 }, { "epoch": 2.1237465152082553, "grad_norm": 1.5331172943115234, "learning_rate": 6.286453023510845e-05, "loss": 0.5395101547241211, "step": 357280 }, { "epoch": 2.1238059572849237, "grad_norm": 1.268670916557312, "learning_rate": 6.28592275547238e-05, "loss": 0.5447381973266602, "step": 357290 }, { "epoch": 2.123865399361592, "grad_norm": 1.308032751083374, "learning_rate": 6.285392509984524e-05, "loss": 0.5216639995574951, "step": 357300 }, { "epoch": 2.1239248414382605, "grad_norm": 1.453548550605774, "learning_rate": 6.284862287049809e-05, "loss": 0.4860179901123047, "step": 357310 }, { "epoch": 2.123984283514929, "grad_norm": 1.294303059577942, "learning_rate": 6.284332086670768e-05, "loss": 0.4828780174255371, "step": 357320 }, { "epoch": 2.1240437255915974, "grad_norm": 2.3355371952056885, "learning_rate": 6.283801908849944e-05, "loss": 0.49987258911132815, "step": 357330 }, { "epoch": 2.124103167668266, "grad_norm": 1.3856353759765625, "learning_rate": 6.283271753589876e-05, "loss": 0.49283556938171386, "step": 357340 }, { "epoch": 2.124162609744934, "grad_norm": 1.3996996879577637, "learning_rate": 6.282741620893089e-05, "loss": 0.454915714263916, "step": 357350 }, { "epoch": 2.1242220518216026, "grad_norm": 1.270677924156189, "learning_rate": 6.282211510762122e-05, "loss": 0.5186249732971191, "step": 357360 }, { "epoch": 2.124281493898271, "grad_norm": 1.759641408920288, "learning_rate": 6.281681423199517e-05, "loss": 0.4949062347412109, "step": 357370 }, { "epoch": 2.1243409359749394, "grad_norm": 1.241162657737732, "learning_rate": 6.281151358207803e-05, "loss": 0.4638986587524414, "step": 357380 }, { "epoch": 2.1244003780516074, "grad_norm": 1.6218698024749756, "learning_rate": 6.280621315789519e-05, "loss": 0.5417948722839355, "step": 357390 }, { "epoch": 2.124459820128276, "grad_norm": 1.3951364755630493, "learning_rate": 6.280091295947208e-05, "loss": 0.5382184982299805, "step": 357400 }, { "epoch": 2.1245192622049442, "grad_norm": 1.0914320945739746, "learning_rate": 6.279561298683392e-05, "loss": 0.5056038856506347, "step": 357410 }, { "epoch": 2.1245787042816127, "grad_norm": 1.4218965768814087, "learning_rate": 6.279031324000608e-05, "loss": 0.48516035079956055, "step": 357420 }, { "epoch": 2.124638146358281, "grad_norm": 1.3203785419464111, "learning_rate": 6.278501371901399e-05, "loss": 0.532811975479126, "step": 357430 }, { "epoch": 2.1246975884349495, "grad_norm": 1.7196086645126343, "learning_rate": 6.277971442388298e-05, "loss": 0.5539535522460938, "step": 357440 }, { "epoch": 2.124757030511618, "grad_norm": 1.460242748260498, "learning_rate": 6.277441535463834e-05, "loss": 0.42073512077331543, "step": 357450 }, { "epoch": 2.1248164725882863, "grad_norm": 1.7909185886383057, "learning_rate": 6.276911651130555e-05, "loss": 0.5329057216644287, "step": 357460 }, { "epoch": 2.1248759146649547, "grad_norm": 1.3080143928527832, "learning_rate": 6.276381789390982e-05, "loss": 0.5491456508636474, "step": 357470 }, { "epoch": 2.124935356741623, "grad_norm": 1.3273581266403198, "learning_rate": 6.275851950247654e-05, "loss": 0.5037428855895996, "step": 357480 }, { "epoch": 2.1249947988182916, "grad_norm": 1.4493261575698853, "learning_rate": 6.275322133703106e-05, "loss": 0.5060734272003173, "step": 357490 }, { "epoch": 2.12505424089496, "grad_norm": 1.4195573329925537, "learning_rate": 6.274792339759873e-05, "loss": 0.53487548828125, "step": 357500 }, { "epoch": 2.1251136829716284, "grad_norm": 1.430699110031128, "learning_rate": 6.27426256842049e-05, "loss": 0.4772050857543945, "step": 357510 }, { "epoch": 2.125173125048297, "grad_norm": 1.4340649843215942, "learning_rate": 6.273732819687493e-05, "loss": 0.4884360313415527, "step": 357520 }, { "epoch": 2.125232567124965, "grad_norm": 1.5791373252868652, "learning_rate": 6.27320309356341e-05, "loss": 0.5202896118164062, "step": 357530 }, { "epoch": 2.1252920092016336, "grad_norm": 1.1962881088256836, "learning_rate": 6.272673390050781e-05, "loss": 0.4872750282287598, "step": 357540 }, { "epoch": 2.125351451278302, "grad_norm": 1.463557481765747, "learning_rate": 6.272143709152131e-05, "loss": 0.4911855697631836, "step": 357550 }, { "epoch": 2.12541089335497, "grad_norm": 1.0773409605026245, "learning_rate": 6.271614050870007e-05, "loss": 0.5071709632873536, "step": 357560 }, { "epoch": 2.1254703354316384, "grad_norm": 1.3432880640029907, "learning_rate": 6.271084415206936e-05, "loss": 0.49070014953613283, "step": 357570 }, { "epoch": 2.125529777508307, "grad_norm": 1.1106590032577515, "learning_rate": 6.270554802165451e-05, "loss": 0.5102278709411621, "step": 357580 }, { "epoch": 2.1255892195849753, "grad_norm": 1.5063555240631104, "learning_rate": 6.270025211748087e-05, "loss": 0.5469787120819092, "step": 357590 }, { "epoch": 2.1256486616616437, "grad_norm": 1.4215267896652222, "learning_rate": 6.269495643957375e-05, "loss": 0.5309747695922852, "step": 357600 }, { "epoch": 2.125708103738312, "grad_norm": 1.4470378160476685, "learning_rate": 6.268966098795851e-05, "loss": 0.48119258880615234, "step": 357610 }, { "epoch": 2.1257675458149805, "grad_norm": 1.3185869455337524, "learning_rate": 6.268436576266043e-05, "loss": 0.5106576442718506, "step": 357620 }, { "epoch": 2.125826987891649, "grad_norm": 1.182715654373169, "learning_rate": 6.267907076370494e-05, "loss": 0.514404582977295, "step": 357630 }, { "epoch": 2.1258864299683173, "grad_norm": 1.0726981163024902, "learning_rate": 6.267377599111728e-05, "loss": 0.4940818786621094, "step": 357640 }, { "epoch": 2.1259458720449858, "grad_norm": 1.5259404182434082, "learning_rate": 6.266848144492282e-05, "loss": 0.5268324851989746, "step": 357650 }, { "epoch": 2.126005314121654, "grad_norm": 1.241700291633606, "learning_rate": 6.266318712514689e-05, "loss": 0.4809277057647705, "step": 357660 }, { "epoch": 2.1260647561983226, "grad_norm": 1.0883369445800781, "learning_rate": 6.265789303181478e-05, "loss": 0.48417129516601565, "step": 357670 }, { "epoch": 2.126124198274991, "grad_norm": 1.2449588775634766, "learning_rate": 6.265259916495181e-05, "loss": 0.49060564041137694, "step": 357680 }, { "epoch": 2.1261836403516594, "grad_norm": 1.6930713653564453, "learning_rate": 6.264730552458337e-05, "loss": 0.5369570255279541, "step": 357690 }, { "epoch": 2.126243082428328, "grad_norm": 1.6916472911834717, "learning_rate": 6.264201211073475e-05, "loss": 0.4977756977081299, "step": 357700 }, { "epoch": 2.1263025245049962, "grad_norm": 1.621077537536621, "learning_rate": 6.263671892343126e-05, "loss": 0.5019792079925537, "step": 357710 }, { "epoch": 2.1263619665816647, "grad_norm": 1.6150627136230469, "learning_rate": 6.263142596269824e-05, "loss": 0.554532814025879, "step": 357720 }, { "epoch": 2.126421408658333, "grad_norm": 1.195858120918274, "learning_rate": 6.262613322856099e-05, "loss": 0.5248449325561524, "step": 357730 }, { "epoch": 2.1264808507350015, "grad_norm": 1.2427961826324463, "learning_rate": 6.262084072104484e-05, "loss": 0.5042361259460449, "step": 357740 }, { "epoch": 2.1265402928116695, "grad_norm": 1.5104553699493408, "learning_rate": 6.261554844017507e-05, "loss": 0.4886808395385742, "step": 357750 }, { "epoch": 2.126599734888338, "grad_norm": 1.6490505933761597, "learning_rate": 6.261025638597706e-05, "loss": 0.5302739143371582, "step": 357760 }, { "epoch": 2.1266591769650063, "grad_norm": 1.2957850694656372, "learning_rate": 6.260496455847609e-05, "loss": 0.5453543663024902, "step": 357770 }, { "epoch": 2.1267186190416747, "grad_norm": 1.090035319328308, "learning_rate": 6.259967295769749e-05, "loss": 0.5032191276550293, "step": 357780 }, { "epoch": 2.126778061118343, "grad_norm": 1.8745379447937012, "learning_rate": 6.259438158366658e-05, "loss": 0.45911035537719724, "step": 357790 }, { "epoch": 2.1268375031950115, "grad_norm": 1.3875716924667358, "learning_rate": 6.258909043640861e-05, "loss": 0.543663501739502, "step": 357800 }, { "epoch": 2.12689694527168, "grad_norm": 1.5079612731933594, "learning_rate": 6.258379951594895e-05, "loss": 0.46179962158203125, "step": 357810 }, { "epoch": 2.1269563873483484, "grad_norm": 1.0522388219833374, "learning_rate": 6.25785088223129e-05, "loss": 0.5021567821502686, "step": 357820 }, { "epoch": 2.1270158294250168, "grad_norm": 1.1940337419509888, "learning_rate": 6.257321835552583e-05, "loss": 0.5260591030120849, "step": 357830 }, { "epoch": 2.127075271501685, "grad_norm": 1.1811977624893188, "learning_rate": 6.256792811561293e-05, "loss": 0.4972991466522217, "step": 357840 }, { "epoch": 2.1271347135783536, "grad_norm": 1.346812129020691, "learning_rate": 6.256263810259953e-05, "loss": 0.4914381980895996, "step": 357850 }, { "epoch": 2.127194155655022, "grad_norm": 1.4505151510238647, "learning_rate": 6.255734831651099e-05, "loss": 0.4908498764038086, "step": 357860 }, { "epoch": 2.1272535977316904, "grad_norm": 1.5359126329421997, "learning_rate": 6.255205875737262e-05, "loss": 0.4951017379760742, "step": 357870 }, { "epoch": 2.127313039808359, "grad_norm": 1.711011528968811, "learning_rate": 6.254676942520963e-05, "loss": 0.4986692428588867, "step": 357880 }, { "epoch": 2.1273724818850273, "grad_norm": 1.8950504064559937, "learning_rate": 6.254148032004747e-05, "loss": 0.5286531448364258, "step": 357890 }, { "epoch": 2.1274319239616957, "grad_norm": 1.6190506219863892, "learning_rate": 6.253619144191131e-05, "loss": 0.5361450672149658, "step": 357900 }, { "epoch": 2.127491366038364, "grad_norm": 1.467629075050354, "learning_rate": 6.253090279082648e-05, "loss": 0.49200735092163084, "step": 357910 }, { "epoch": 2.1275508081150325, "grad_norm": 1.3417929410934448, "learning_rate": 6.252561436681834e-05, "loss": 0.48363552093505857, "step": 357920 }, { "epoch": 2.127610250191701, "grad_norm": 1.433659553527832, "learning_rate": 6.252032616991214e-05, "loss": 0.5149093627929687, "step": 357930 }, { "epoch": 2.127669692268369, "grad_norm": 1.727099061012268, "learning_rate": 6.251503820013314e-05, "loss": 0.5142306327819824, "step": 357940 }, { "epoch": 2.1277291343450373, "grad_norm": 1.3079032897949219, "learning_rate": 6.250975045750676e-05, "loss": 0.5107248306274415, "step": 357950 }, { "epoch": 2.1277885764217057, "grad_norm": 1.377753734588623, "learning_rate": 6.250446294205817e-05, "loss": 0.5247247695922852, "step": 357960 }, { "epoch": 2.127848018498374, "grad_norm": 1.198852300643921, "learning_rate": 6.24991756538127e-05, "loss": 0.49259557723999026, "step": 357970 }, { "epoch": 2.1279074605750425, "grad_norm": 1.1714140176773071, "learning_rate": 6.249388859279563e-05, "loss": 0.4854989528656006, "step": 357980 }, { "epoch": 2.127966902651711, "grad_norm": 1.1055160760879517, "learning_rate": 6.248860175903231e-05, "loss": 0.48985891342163085, "step": 357990 }, { "epoch": 2.1280263447283794, "grad_norm": 1.2266112565994263, "learning_rate": 6.248331515254797e-05, "loss": 0.5218829154968262, "step": 358000 }, { "epoch": 2.128085786805048, "grad_norm": 1.3001708984375, "learning_rate": 6.247802877336793e-05, "loss": 0.5061018943786622, "step": 358010 }, { "epoch": 2.128145228881716, "grad_norm": 1.489243745803833, "learning_rate": 6.247274262151748e-05, "loss": 0.4788051128387451, "step": 358020 }, { "epoch": 2.1282046709583846, "grad_norm": 1.2583059072494507, "learning_rate": 6.24674566970219e-05, "loss": 0.5483686923980713, "step": 358030 }, { "epoch": 2.128264113035053, "grad_norm": 1.1828639507293701, "learning_rate": 6.246217099990643e-05, "loss": 0.4872447967529297, "step": 358040 }, { "epoch": 2.1283235551117214, "grad_norm": 1.533259391784668, "learning_rate": 6.245688553019644e-05, "loss": 0.5208674430847168, "step": 358050 }, { "epoch": 2.12838299718839, "grad_norm": 1.1589308977127075, "learning_rate": 6.245160028791715e-05, "loss": 0.5068474292755127, "step": 358060 }, { "epoch": 2.1284424392650583, "grad_norm": 1.022672176361084, "learning_rate": 6.244631527309389e-05, "loss": 0.49155092239379883, "step": 358070 }, { "epoch": 2.1285018813417267, "grad_norm": 1.0683826208114624, "learning_rate": 6.244103048575191e-05, "loss": 0.47278823852539065, "step": 358080 }, { "epoch": 2.128561323418395, "grad_norm": 1.5614668130874634, "learning_rate": 6.24357459259165e-05, "loss": 0.5099018096923829, "step": 358090 }, { "epoch": 2.1286207654950635, "grad_norm": 1.3111401796340942, "learning_rate": 6.243046159361293e-05, "loss": 0.49262180328369143, "step": 358100 }, { "epoch": 2.128680207571732, "grad_norm": 1.0777479410171509, "learning_rate": 6.242517748886644e-05, "loss": 0.4833353042602539, "step": 358110 }, { "epoch": 2.1287396496484003, "grad_norm": 1.543825626373291, "learning_rate": 6.241989361170242e-05, "loss": 0.4619187355041504, "step": 358120 }, { "epoch": 2.1287990917250683, "grad_norm": 1.5782067775726318, "learning_rate": 6.241460996214606e-05, "loss": 0.508424949645996, "step": 358130 }, { "epoch": 2.1288585338017367, "grad_norm": 1.4177824258804321, "learning_rate": 6.240932654022266e-05, "loss": 0.538025188446045, "step": 358140 }, { "epoch": 2.128917975878405, "grad_norm": 1.1375625133514404, "learning_rate": 6.240404334595749e-05, "loss": 0.5058460712432862, "step": 358150 }, { "epoch": 2.1289774179550736, "grad_norm": 1.9001604318618774, "learning_rate": 6.23987603793758e-05, "loss": 0.48597092628479005, "step": 358160 }, { "epoch": 2.129036860031742, "grad_norm": 1.6725798845291138, "learning_rate": 6.239347764050288e-05, "loss": 0.5543056488037109, "step": 358170 }, { "epoch": 2.1290963021084104, "grad_norm": 1.1996923685073853, "learning_rate": 6.238819512936403e-05, "loss": 0.5084031105041504, "step": 358180 }, { "epoch": 2.129155744185079, "grad_norm": 1.5514373779296875, "learning_rate": 6.23829128459845e-05, "loss": 0.4953312873840332, "step": 358190 }, { "epoch": 2.129215186261747, "grad_norm": 1.0191750526428223, "learning_rate": 6.237763079038954e-05, "loss": 0.5023176670074463, "step": 358200 }, { "epoch": 2.1292746283384156, "grad_norm": 1.3723653554916382, "learning_rate": 6.237234896260444e-05, "loss": 0.5316482543945312, "step": 358210 }, { "epoch": 2.129334070415084, "grad_norm": 1.70853590965271, "learning_rate": 6.236706736265446e-05, "loss": 0.49643354415893554, "step": 358220 }, { "epoch": 2.1293935124917525, "grad_norm": 1.765578031539917, "learning_rate": 6.236178599056485e-05, "loss": 0.5214154243469238, "step": 358230 }, { "epoch": 2.129452954568421, "grad_norm": 1.4501445293426514, "learning_rate": 6.235650484636087e-05, "loss": 0.4638517379760742, "step": 358240 }, { "epoch": 2.1295123966450893, "grad_norm": 1.0963618755340576, "learning_rate": 6.235122393006782e-05, "loss": 0.4755260944366455, "step": 358250 }, { "epoch": 2.1295718387217577, "grad_norm": 1.3525137901306152, "learning_rate": 6.234594324171095e-05, "loss": 0.4934722900390625, "step": 358260 }, { "epoch": 2.129631280798426, "grad_norm": 1.2606332302093506, "learning_rate": 6.234066278131551e-05, "loss": 0.47733297348022463, "step": 358270 }, { "epoch": 2.1296907228750945, "grad_norm": 1.2409639358520508, "learning_rate": 6.233538254890676e-05, "loss": 0.4996635437011719, "step": 358280 }, { "epoch": 2.129750164951763, "grad_norm": 1.273929238319397, "learning_rate": 6.233010254450997e-05, "loss": 0.49351892471313474, "step": 358290 }, { "epoch": 2.129809607028431, "grad_norm": 2.0272068977355957, "learning_rate": 6.232482276815036e-05, "loss": 0.5046542167663575, "step": 358300 }, { "epoch": 2.1298690491050993, "grad_norm": 1.5156333446502686, "learning_rate": 6.231954321985325e-05, "loss": 0.467070484161377, "step": 358310 }, { "epoch": 2.1299284911817677, "grad_norm": 1.2585840225219727, "learning_rate": 6.231426389964385e-05, "loss": 0.5052550315856934, "step": 358320 }, { "epoch": 2.129987933258436, "grad_norm": 1.24330472946167, "learning_rate": 6.230898480754748e-05, "loss": 0.5186112880706787, "step": 358330 }, { "epoch": 2.1300473753351046, "grad_norm": 1.5255253314971924, "learning_rate": 6.230370594358927e-05, "loss": 0.5058189392089844, "step": 358340 }, { "epoch": 2.130106817411773, "grad_norm": 1.5900049209594727, "learning_rate": 6.229842730779458e-05, "loss": 0.4972053050994873, "step": 358350 }, { "epoch": 2.1301662594884414, "grad_norm": 1.3217206001281738, "learning_rate": 6.229314890018861e-05, "loss": 0.5504020690917969, "step": 358360 }, { "epoch": 2.13022570156511, "grad_norm": 1.092713713645935, "learning_rate": 6.22878707207966e-05, "loss": 0.44562253952026365, "step": 358370 }, { "epoch": 2.1302851436417782, "grad_norm": 1.6605794429779053, "learning_rate": 6.228259276964386e-05, "loss": 0.5269547462463379, "step": 358380 }, { "epoch": 2.1303445857184466, "grad_norm": 1.1978819370269775, "learning_rate": 6.227731504675562e-05, "loss": 0.5036481857299805, "step": 358390 }, { "epoch": 2.130404027795115, "grad_norm": 1.7137916088104248, "learning_rate": 6.227203755215707e-05, "loss": 0.5123356819152832, "step": 358400 }, { "epoch": 2.1304634698717835, "grad_norm": 1.5883405208587646, "learning_rate": 6.22667602858735e-05, "loss": 0.46491231918334963, "step": 358410 }, { "epoch": 2.130522911948452, "grad_norm": 1.4174658060073853, "learning_rate": 6.226148324793018e-05, "loss": 0.5164656639099121, "step": 358420 }, { "epoch": 2.1305823540251203, "grad_norm": 1.367242455482483, "learning_rate": 6.225620643835226e-05, "loss": 0.4881139755249023, "step": 358430 }, { "epoch": 2.1306417961017887, "grad_norm": 1.8075101375579834, "learning_rate": 6.22509298571651e-05, "loss": 0.5419732570648194, "step": 358440 }, { "epoch": 2.130701238178457, "grad_norm": 1.3247218132019043, "learning_rate": 6.224565350439391e-05, "loss": 0.5013696193695069, "step": 358450 }, { "epoch": 2.1307606802551255, "grad_norm": 1.5953783988952637, "learning_rate": 6.224037738006387e-05, "loss": 0.49672656059265136, "step": 358460 }, { "epoch": 2.130820122331794, "grad_norm": 1.658075213432312, "learning_rate": 6.223510148420022e-05, "loss": 0.51611328125, "step": 358470 }, { "epoch": 2.1308795644084624, "grad_norm": 1.5490622520446777, "learning_rate": 6.222982581682828e-05, "loss": 0.5163888454437255, "step": 358480 }, { "epoch": 2.1309390064851303, "grad_norm": 1.1874386072158813, "learning_rate": 6.222455037797324e-05, "loss": 0.502932071685791, "step": 358490 }, { "epoch": 2.1309984485617988, "grad_norm": 1.4373915195465088, "learning_rate": 6.221927516766033e-05, "loss": 0.46361870765686036, "step": 358500 }, { "epoch": 2.131057890638467, "grad_norm": 1.2201040983200073, "learning_rate": 6.22140001859148e-05, "loss": 0.5523425579071045, "step": 358510 }, { "epoch": 2.1311173327151356, "grad_norm": 1.3153272867202759, "learning_rate": 6.220872543276189e-05, "loss": 0.5043387413024902, "step": 358520 }, { "epoch": 2.131176774791804, "grad_norm": 1.1208040714263916, "learning_rate": 6.220345090822675e-05, "loss": 0.5073929309844971, "step": 358530 }, { "epoch": 2.1312362168684724, "grad_norm": 1.0785361528396606, "learning_rate": 6.219817661233473e-05, "loss": 0.48006086349487304, "step": 358540 }, { "epoch": 2.131295658945141, "grad_norm": 0.9506767988204956, "learning_rate": 6.219290254511103e-05, "loss": 0.526703929901123, "step": 358550 }, { "epoch": 2.1313551010218093, "grad_norm": 1.1749948263168335, "learning_rate": 6.218762870658085e-05, "loss": 0.47592735290527344, "step": 358560 }, { "epoch": 2.1314145430984777, "grad_norm": 1.4422165155410767, "learning_rate": 6.218235509676942e-05, "loss": 0.5026476860046387, "step": 358570 }, { "epoch": 2.131473985175146, "grad_norm": 1.4329754114151, "learning_rate": 6.217708171570198e-05, "loss": 0.5150867462158203, "step": 358580 }, { "epoch": 2.1315334272518145, "grad_norm": 1.5028945207595825, "learning_rate": 6.217180856340377e-05, "loss": 0.5195156097412109, "step": 358590 }, { "epoch": 2.131592869328483, "grad_norm": 1.7069240808486938, "learning_rate": 6.216653563989993e-05, "loss": 0.5225292205810547, "step": 358600 }, { "epoch": 2.1316523114051513, "grad_norm": 1.1822528839111328, "learning_rate": 6.216126294521582e-05, "loss": 0.5030779838562012, "step": 358610 }, { "epoch": 2.1317117534818197, "grad_norm": 1.3953418731689453, "learning_rate": 6.215599047937657e-05, "loss": 0.4802116870880127, "step": 358620 }, { "epoch": 2.131771195558488, "grad_norm": 1.6015892028808594, "learning_rate": 6.215071824240744e-05, "loss": 0.5748533248901367, "step": 358630 }, { "epoch": 2.1318306376351566, "grad_norm": 1.2719801664352417, "learning_rate": 6.214544623433363e-05, "loss": 0.4699394702911377, "step": 358640 }, { "epoch": 2.131890079711825, "grad_norm": 1.4095478057861328, "learning_rate": 6.214017445518036e-05, "loss": 0.47287211418151853, "step": 358650 }, { "epoch": 2.1319495217884934, "grad_norm": 1.284764289855957, "learning_rate": 6.213490290497282e-05, "loss": 0.5093019485473633, "step": 358660 }, { "epoch": 2.132008963865162, "grad_norm": 1.2389883995056152, "learning_rate": 6.21296315837363e-05, "loss": 0.5061709403991699, "step": 358670 }, { "epoch": 2.13206840594183, "grad_norm": 1.2788736820220947, "learning_rate": 6.212436049149598e-05, "loss": 0.48361783027648925, "step": 358680 }, { "epoch": 2.132127848018498, "grad_norm": 1.2931662797927856, "learning_rate": 6.211908962827708e-05, "loss": 0.450242805480957, "step": 358690 }, { "epoch": 2.1321872900951666, "grad_norm": 1.2050381898880005, "learning_rate": 6.21138189941048e-05, "loss": 0.5551799297332763, "step": 358700 }, { "epoch": 2.132246732171835, "grad_norm": 1.8376976251602173, "learning_rate": 6.210854858900436e-05, "loss": 0.46880254745483396, "step": 358710 }, { "epoch": 2.1323061742485034, "grad_norm": 1.5882724523544312, "learning_rate": 6.210327841300099e-05, "loss": 0.5182974338531494, "step": 358720 }, { "epoch": 2.132365616325172, "grad_norm": 1.7683809995651245, "learning_rate": 6.209800846611981e-05, "loss": 0.5296806335449219, "step": 358730 }, { "epoch": 2.1324250584018403, "grad_norm": 1.519058108329773, "learning_rate": 6.209273874838617e-05, "loss": 0.5474782943725586, "step": 358740 }, { "epoch": 2.1324845004785087, "grad_norm": 1.1473662853240967, "learning_rate": 6.208746925982522e-05, "loss": 0.48000564575195315, "step": 358750 }, { "epoch": 2.132543942555177, "grad_norm": 1.538053035736084, "learning_rate": 6.208220000046215e-05, "loss": 0.49527850151062014, "step": 358760 }, { "epoch": 2.1326033846318455, "grad_norm": 1.1504484415054321, "learning_rate": 6.207693097032215e-05, "loss": 0.5430690765380859, "step": 358770 }, { "epoch": 2.132662826708514, "grad_norm": 1.2903246879577637, "learning_rate": 6.207166216943046e-05, "loss": 0.4686562538146973, "step": 358780 }, { "epoch": 2.1327222687851823, "grad_norm": 1.2571741342544556, "learning_rate": 6.206639359781226e-05, "loss": 0.48975439071655275, "step": 358790 }, { "epoch": 2.1327817108618508, "grad_norm": 1.3868200778961182, "learning_rate": 6.206112525549279e-05, "loss": 0.5462002754211426, "step": 358800 }, { "epoch": 2.132841152938519, "grad_norm": 1.1928608417510986, "learning_rate": 6.205585714249723e-05, "loss": 0.4941540718078613, "step": 358810 }, { "epoch": 2.1329005950151876, "grad_norm": 1.2686718702316284, "learning_rate": 6.205058925885081e-05, "loss": 0.4567634105682373, "step": 358820 }, { "epoch": 2.132960037091856, "grad_norm": 1.250152349472046, "learning_rate": 6.204532160457865e-05, "loss": 0.5020161151885987, "step": 358830 }, { "epoch": 2.1330194791685244, "grad_norm": 1.0837165117263794, "learning_rate": 6.204005417970602e-05, "loss": 0.45644550323486327, "step": 358840 }, { "epoch": 2.133078921245193, "grad_norm": 1.6045366525650024, "learning_rate": 6.20347869842581e-05, "loss": 0.5330058097839355, "step": 358850 }, { "epoch": 2.1331383633218612, "grad_norm": 1.5503714084625244, "learning_rate": 6.202952001826006e-05, "loss": 0.5385990142822266, "step": 358860 }, { "epoch": 2.133197805398529, "grad_norm": 1.5391337871551514, "learning_rate": 6.202425328173714e-05, "loss": 0.5402346134185791, "step": 358870 }, { "epoch": 2.1332572474751976, "grad_norm": 1.4865357875823975, "learning_rate": 6.201898677471454e-05, "loss": 0.5135510444641114, "step": 358880 }, { "epoch": 2.133316689551866, "grad_norm": 1.3171840906143188, "learning_rate": 6.20137204972174e-05, "loss": 0.4473093032836914, "step": 358890 }, { "epoch": 2.1333761316285345, "grad_norm": 1.2488384246826172, "learning_rate": 6.200845444927092e-05, "loss": 0.5105849266052246, "step": 358900 }, { "epoch": 2.133435573705203, "grad_norm": 1.456449031829834, "learning_rate": 6.200318863090034e-05, "loss": 0.4852729797363281, "step": 358910 }, { "epoch": 2.1334950157818713, "grad_norm": 1.1933170557022095, "learning_rate": 6.199792304213076e-05, "loss": 0.5193626403808593, "step": 358920 }, { "epoch": 2.1335544578585397, "grad_norm": 1.7804875373840332, "learning_rate": 6.19926576829875e-05, "loss": 0.5116562366485595, "step": 358930 }, { "epoch": 2.133613899935208, "grad_norm": 1.0149788856506348, "learning_rate": 6.198739255349568e-05, "loss": 0.4881437301635742, "step": 358940 }, { "epoch": 2.1336733420118765, "grad_norm": 1.6088870763778687, "learning_rate": 6.198212765368048e-05, "loss": 0.5054364204406738, "step": 358950 }, { "epoch": 2.133732784088545, "grad_norm": 1.079156517982483, "learning_rate": 6.197686298356702e-05, "loss": 0.44108238220214846, "step": 358960 }, { "epoch": 2.1337922261652134, "grad_norm": 1.075031042098999, "learning_rate": 6.197159854318062e-05, "loss": 0.4608006477355957, "step": 358970 }, { "epoch": 2.1338516682418818, "grad_norm": 1.2285035848617554, "learning_rate": 6.196633433254637e-05, "loss": 0.4819663047790527, "step": 358980 }, { "epoch": 2.13391111031855, "grad_norm": 1.3190724849700928, "learning_rate": 6.196107035168947e-05, "loss": 0.5468829154968262, "step": 358990 }, { "epoch": 2.1339705523952186, "grad_norm": 1.8732718229293823, "learning_rate": 6.195580660063516e-05, "loss": 0.5119499683380127, "step": 359000 }, { "epoch": 2.134029994471887, "grad_norm": 1.4549881219863892, "learning_rate": 6.195054307940854e-05, "loss": 0.5123972415924072, "step": 359010 }, { "epoch": 2.1340894365485554, "grad_norm": 1.199751853942871, "learning_rate": 6.19452797880348e-05, "loss": 0.47840003967285155, "step": 359020 }, { "epoch": 2.134148878625224, "grad_norm": 1.5385476350784302, "learning_rate": 6.194001672653913e-05, "loss": 0.44325270652771, "step": 359030 }, { "epoch": 2.134208320701892, "grad_norm": 0.9489364624023438, "learning_rate": 6.193475389494675e-05, "loss": 0.4454642295837402, "step": 359040 }, { "epoch": 2.1342677627785602, "grad_norm": 1.5871225595474243, "learning_rate": 6.19294912932828e-05, "loss": 0.4932085514068604, "step": 359050 }, { "epoch": 2.1343272048552286, "grad_norm": 1.5326869487762451, "learning_rate": 6.192422892157244e-05, "loss": 0.4826094150543213, "step": 359060 }, { "epoch": 2.134386646931897, "grad_norm": 1.331054925918579, "learning_rate": 6.191896677984086e-05, "loss": 0.5241713047027587, "step": 359070 }, { "epoch": 2.1344460890085655, "grad_norm": 1.1430405378341675, "learning_rate": 6.191370486811323e-05, "loss": 0.5077963829040527, "step": 359080 }, { "epoch": 2.134505531085234, "grad_norm": 1.3937124013900757, "learning_rate": 6.19084431864147e-05, "loss": 0.511815357208252, "step": 359090 }, { "epoch": 2.1345649731619023, "grad_norm": 1.3295059204101562, "learning_rate": 6.190318173477048e-05, "loss": 0.4491428852081299, "step": 359100 }, { "epoch": 2.1346244152385707, "grad_norm": 1.4488245248794556, "learning_rate": 6.189792051320572e-05, "loss": 0.5172082901000976, "step": 359110 }, { "epoch": 2.134683857315239, "grad_norm": 1.386947512626648, "learning_rate": 6.189265952174559e-05, "loss": 0.5139379501342773, "step": 359120 }, { "epoch": 2.1347432993919075, "grad_norm": 1.5574718713760376, "learning_rate": 6.188739876041526e-05, "loss": 0.5067360877990723, "step": 359130 }, { "epoch": 2.134802741468576, "grad_norm": 1.397917628288269, "learning_rate": 6.188213822923989e-05, "loss": 0.49779653549194336, "step": 359140 }, { "epoch": 2.1348621835452444, "grad_norm": 1.8392126560211182, "learning_rate": 6.18768779282446e-05, "loss": 0.49583067893981936, "step": 359150 }, { "epoch": 2.134921625621913, "grad_norm": 1.6458120346069336, "learning_rate": 6.187161785745466e-05, "loss": 0.5030621528625489, "step": 359160 }, { "epoch": 2.134981067698581, "grad_norm": 1.2148398160934448, "learning_rate": 6.186635801689515e-05, "loss": 0.5041861534118652, "step": 359170 }, { "epoch": 2.1350405097752496, "grad_norm": 1.4444547891616821, "learning_rate": 6.186109840659126e-05, "loss": 0.5097728729248047, "step": 359180 }, { "epoch": 2.135099951851918, "grad_norm": 1.55653715133667, "learning_rate": 6.185583902656814e-05, "loss": 0.440610408782959, "step": 359190 }, { "epoch": 2.1351593939285864, "grad_norm": 1.3941376209259033, "learning_rate": 6.185057987685095e-05, "loss": 0.4644766807556152, "step": 359200 }, { "epoch": 2.135218836005255, "grad_norm": 1.5075477361679077, "learning_rate": 6.184532095746484e-05, "loss": 0.6235862731933594, "step": 359210 }, { "epoch": 2.1352782780819233, "grad_norm": 1.1182574033737183, "learning_rate": 6.184006226843497e-05, "loss": 0.4840632438659668, "step": 359220 }, { "epoch": 2.1353377201585912, "grad_norm": 1.4333211183547974, "learning_rate": 6.183480380978652e-05, "loss": 0.4448265075683594, "step": 359230 }, { "epoch": 2.1353971622352597, "grad_norm": 1.1973012685775757, "learning_rate": 6.182954558154464e-05, "loss": 0.4742823600769043, "step": 359240 }, { "epoch": 2.135456604311928, "grad_norm": 1.3281465768814087, "learning_rate": 6.182428758373446e-05, "loss": 0.4829118728637695, "step": 359250 }, { "epoch": 2.1355160463885965, "grad_norm": 1.1356093883514404, "learning_rate": 6.181902981638115e-05, "loss": 0.475538444519043, "step": 359260 }, { "epoch": 2.135575488465265, "grad_norm": 1.3496826887130737, "learning_rate": 6.181377227950986e-05, "loss": 0.46793508529663086, "step": 359270 }, { "epoch": 2.1356349305419333, "grad_norm": 1.4796150922775269, "learning_rate": 6.18085149731457e-05, "loss": 0.4720907211303711, "step": 359280 }, { "epoch": 2.1356943726186017, "grad_norm": 1.4813225269317627, "learning_rate": 6.180325789731389e-05, "loss": 0.459168815612793, "step": 359290 }, { "epoch": 2.13575381469527, "grad_norm": 1.3439167737960815, "learning_rate": 6.179800105203954e-05, "loss": 0.5006700038909913, "step": 359300 }, { "epoch": 2.1358132567719386, "grad_norm": 1.2144927978515625, "learning_rate": 6.179274443734783e-05, "loss": 0.5001688957214355, "step": 359310 }, { "epoch": 2.135872698848607, "grad_norm": 1.5979998111724854, "learning_rate": 6.178748805326382e-05, "loss": 0.5224793910980224, "step": 359320 }, { "epoch": 2.1359321409252754, "grad_norm": 1.3919368982315063, "learning_rate": 6.178223189981273e-05, "loss": 0.5094445705413818, "step": 359330 }, { "epoch": 2.135991583001944, "grad_norm": 1.223510980606079, "learning_rate": 6.177697597701969e-05, "loss": 0.5187028884887696, "step": 359340 }, { "epoch": 2.136051025078612, "grad_norm": 1.442955732345581, "learning_rate": 6.17717202849098e-05, "loss": 0.5016358852386474, "step": 359350 }, { "epoch": 2.1361104671552806, "grad_norm": 1.323563575744629, "learning_rate": 6.176646482350829e-05, "loss": 0.5084827899932861, "step": 359360 }, { "epoch": 2.136169909231949, "grad_norm": 1.2132272720336914, "learning_rate": 6.176120959284027e-05, "loss": 0.5420601844787598, "step": 359370 }, { "epoch": 2.1362293513086175, "grad_norm": 1.2085734605789185, "learning_rate": 6.175595459293079e-05, "loss": 0.47492804527282717, "step": 359380 }, { "epoch": 2.136288793385286, "grad_norm": 1.0408979654312134, "learning_rate": 6.175069982380509e-05, "loss": 0.5305048942565918, "step": 359390 }, { "epoch": 2.1363482354619543, "grad_norm": 1.6496741771697998, "learning_rate": 6.174544528548826e-05, "loss": 0.4534099578857422, "step": 359400 }, { "epoch": 2.1364076775386227, "grad_norm": 1.632442831993103, "learning_rate": 6.174019097800545e-05, "loss": 0.527883768081665, "step": 359410 }, { "epoch": 2.1364671196152907, "grad_norm": 1.6791019439697266, "learning_rate": 6.173493690138181e-05, "loss": 0.4629235744476318, "step": 359420 }, { "epoch": 2.136526561691959, "grad_norm": 1.48440682888031, "learning_rate": 6.17296830556425e-05, "loss": 0.5781189441680908, "step": 359430 }, { "epoch": 2.1365860037686275, "grad_norm": 1.1063019037246704, "learning_rate": 6.172442944081256e-05, "loss": 0.4852943420410156, "step": 359440 }, { "epoch": 2.136645445845296, "grad_norm": 1.659981608390808, "learning_rate": 6.171917605691716e-05, "loss": 0.5753439903259278, "step": 359450 }, { "epoch": 2.1367048879219643, "grad_norm": 2.093722343444824, "learning_rate": 6.171392290398146e-05, "loss": 0.5227261543273926, "step": 359460 }, { "epoch": 2.1367643299986327, "grad_norm": 1.3085633516311646, "learning_rate": 6.17086699820306e-05, "loss": 0.5092341899871826, "step": 359470 }, { "epoch": 2.136823772075301, "grad_norm": 1.4080798625946045, "learning_rate": 6.170341729108961e-05, "loss": 0.500715684890747, "step": 359480 }, { "epoch": 2.1368832141519696, "grad_norm": 1.6139723062515259, "learning_rate": 6.169816483118378e-05, "loss": 0.5048386573791503, "step": 359490 }, { "epoch": 2.136942656228638, "grad_norm": 1.5457403659820557, "learning_rate": 6.16929126023381e-05, "loss": 0.5064330101013184, "step": 359500 }, { "epoch": 2.1370020983053064, "grad_norm": 1.4104806184768677, "learning_rate": 6.168766060457772e-05, "loss": 0.5292594909667969, "step": 359510 }, { "epoch": 2.137061540381975, "grad_norm": 1.1933517456054688, "learning_rate": 6.16824088379278e-05, "loss": 0.5172000885009765, "step": 359520 }, { "epoch": 2.1371209824586432, "grad_norm": 1.5755990743637085, "learning_rate": 6.167715730241346e-05, "loss": 0.5325644493103028, "step": 359530 }, { "epoch": 2.1371804245353117, "grad_norm": 1.1560297012329102, "learning_rate": 6.16719059980598e-05, "loss": 0.44052829742431643, "step": 359540 }, { "epoch": 2.13723986661198, "grad_norm": 1.4218634366989136, "learning_rate": 6.166665492489194e-05, "loss": 0.5131752967834473, "step": 359550 }, { "epoch": 2.1372993086886485, "grad_norm": 1.4144822359085083, "learning_rate": 6.166140408293503e-05, "loss": 0.515986156463623, "step": 359560 }, { "epoch": 2.137358750765317, "grad_norm": 1.3734686374664307, "learning_rate": 6.165615347221414e-05, "loss": 0.5153759956359864, "step": 359570 }, { "epoch": 2.1374181928419853, "grad_norm": 1.3240914344787598, "learning_rate": 6.165090309275438e-05, "loss": 0.504335880279541, "step": 359580 }, { "epoch": 2.1374776349186537, "grad_norm": 1.6915032863616943, "learning_rate": 6.164565294458095e-05, "loss": 0.5281346321105957, "step": 359590 }, { "epoch": 2.137537076995322, "grad_norm": 1.65500807762146, "learning_rate": 6.164040302771892e-05, "loss": 0.5074682712554932, "step": 359600 }, { "epoch": 2.13759651907199, "grad_norm": 1.0023332834243774, "learning_rate": 6.163515334219337e-05, "loss": 0.4653157234191895, "step": 359610 }, { "epoch": 2.1376559611486585, "grad_norm": 1.2891929149627686, "learning_rate": 6.162990388802948e-05, "loss": 0.5396088600158692, "step": 359620 }, { "epoch": 2.137715403225327, "grad_norm": 1.4803721904754639, "learning_rate": 6.162465466525228e-05, "loss": 0.41270928382873534, "step": 359630 }, { "epoch": 2.1377748453019954, "grad_norm": 1.1331106424331665, "learning_rate": 6.16194056738869e-05, "loss": 0.5088899612426758, "step": 359640 }, { "epoch": 2.1378342873786638, "grad_norm": 1.1723062992095947, "learning_rate": 6.161415691395852e-05, "loss": 0.521664810180664, "step": 359650 }, { "epoch": 2.137893729455332, "grad_norm": 1.3584771156311035, "learning_rate": 6.160890838549219e-05, "loss": 0.48171195983886717, "step": 359660 }, { "epoch": 2.1379531715320006, "grad_norm": 1.4614800214767456, "learning_rate": 6.160366008851304e-05, "loss": 0.49677438735961915, "step": 359670 }, { "epoch": 2.138012613608669, "grad_norm": 1.2863816022872925, "learning_rate": 6.159841202304615e-05, "loss": 0.5185723304748535, "step": 359680 }, { "epoch": 2.1380720556853374, "grad_norm": 1.4088561534881592, "learning_rate": 6.159316418911665e-05, "loss": 0.4796799659729004, "step": 359690 }, { "epoch": 2.138131497762006, "grad_norm": 1.1870681047439575, "learning_rate": 6.158791658674962e-05, "loss": 0.49743804931640623, "step": 359700 }, { "epoch": 2.1381909398386743, "grad_norm": 1.4396946430206299, "learning_rate": 6.158266921597016e-05, "loss": 0.5318953037261963, "step": 359710 }, { "epoch": 2.1382503819153427, "grad_norm": 1.367634654045105, "learning_rate": 6.15774220768034e-05, "loss": 0.468015718460083, "step": 359720 }, { "epoch": 2.138309823992011, "grad_norm": 1.1008281707763672, "learning_rate": 6.157217516927444e-05, "loss": 0.4756145000457764, "step": 359730 }, { "epoch": 2.1383692660686795, "grad_norm": 1.3524104356765747, "learning_rate": 6.156692849340837e-05, "loss": 0.43817806243896484, "step": 359740 }, { "epoch": 2.138428708145348, "grad_norm": 1.1676241159439087, "learning_rate": 6.156168204923027e-05, "loss": 0.5545412063598633, "step": 359750 }, { "epoch": 2.1384881502220163, "grad_norm": 1.7557717561721802, "learning_rate": 6.155643583676527e-05, "loss": 0.5198943138122558, "step": 359760 }, { "epoch": 2.1385475922986847, "grad_norm": 1.4090629816055298, "learning_rate": 6.155118985603841e-05, "loss": 0.49799289703369143, "step": 359770 }, { "epoch": 2.1386070343753527, "grad_norm": 1.3076133728027344, "learning_rate": 6.154594410707486e-05, "loss": 0.49883236885070803, "step": 359780 }, { "epoch": 2.138666476452021, "grad_norm": 1.655086874961853, "learning_rate": 6.154069858989968e-05, "loss": 0.545166015625, "step": 359790 }, { "epoch": 2.1387259185286895, "grad_norm": 1.594573736190796, "learning_rate": 6.153545330453796e-05, "loss": 0.5150314331054687, "step": 359800 }, { "epoch": 2.138785360605358, "grad_norm": 0.9922125935554504, "learning_rate": 6.15302082510148e-05, "loss": 0.49343013763427734, "step": 359810 }, { "epoch": 2.1388448026820264, "grad_norm": 1.6646889448165894, "learning_rate": 6.152496342935527e-05, "loss": 0.49586191177368166, "step": 359820 }, { "epoch": 2.138904244758695, "grad_norm": 1.6719648838043213, "learning_rate": 6.151971883958447e-05, "loss": 0.49425954818725587, "step": 359830 }, { "epoch": 2.138963686835363, "grad_norm": 1.4084033966064453, "learning_rate": 6.151447448172748e-05, "loss": 0.4834050178527832, "step": 359840 }, { "epoch": 2.1390231289120316, "grad_norm": 1.2782957553863525, "learning_rate": 6.150923035580942e-05, "loss": 0.4947258949279785, "step": 359850 }, { "epoch": 2.1390825709887, "grad_norm": 1.5123851299285889, "learning_rate": 6.150398646185538e-05, "loss": 0.5366327285766601, "step": 359860 }, { "epoch": 2.1391420130653684, "grad_norm": 1.6252363920211792, "learning_rate": 6.149874279989036e-05, "loss": 0.5301472187042237, "step": 359870 }, { "epoch": 2.139201455142037, "grad_norm": 1.4532450437545776, "learning_rate": 6.149349936993954e-05, "loss": 0.4438161849975586, "step": 359880 }, { "epoch": 2.1392608972187053, "grad_norm": 1.7549301385879517, "learning_rate": 6.148825617202797e-05, "loss": 0.5027998924255371, "step": 359890 }, { "epoch": 2.1393203392953737, "grad_norm": 1.286525011062622, "learning_rate": 6.148301320618073e-05, "loss": 0.48015737533569336, "step": 359900 }, { "epoch": 2.139379781372042, "grad_norm": 1.3603814840316772, "learning_rate": 6.147777047242285e-05, "loss": 0.5065068244934082, "step": 359910 }, { "epoch": 2.1394392234487105, "grad_norm": 1.494964599609375, "learning_rate": 6.147252797077953e-05, "loss": 0.49989709854125974, "step": 359920 }, { "epoch": 2.139498665525379, "grad_norm": 1.6578514575958252, "learning_rate": 6.146728570127576e-05, "loss": 0.4744311809539795, "step": 359930 }, { "epoch": 2.1395581076020473, "grad_norm": 1.5344245433807373, "learning_rate": 6.146204366393659e-05, "loss": 0.48827352523803713, "step": 359940 }, { "epoch": 2.1396175496787158, "grad_norm": 1.1706278324127197, "learning_rate": 6.145680185878718e-05, "loss": 0.4713200569152832, "step": 359950 }, { "epoch": 2.139676991755384, "grad_norm": 1.1842483282089233, "learning_rate": 6.145156028585255e-05, "loss": 0.5939231872558594, "step": 359960 }, { "epoch": 2.139736433832052, "grad_norm": 1.2676541805267334, "learning_rate": 6.144631894515777e-05, "loss": 0.49863319396972655, "step": 359970 }, { "epoch": 2.1397958759087206, "grad_norm": 2.0614798069000244, "learning_rate": 6.144107783672799e-05, "loss": 0.5060172080993652, "step": 359980 }, { "epoch": 2.139855317985389, "grad_norm": 1.207301139831543, "learning_rate": 6.14358369605882e-05, "loss": 0.5012300968170166, "step": 359990 }, { "epoch": 2.1399147600620574, "grad_norm": 1.2765408754348755, "learning_rate": 6.143059631676345e-05, "loss": 0.5059230327606201, "step": 360000 }, { "epoch": 2.139974202138726, "grad_norm": 1.1498264074325562, "learning_rate": 6.14253559052789e-05, "loss": 0.46227827072143557, "step": 360010 }, { "epoch": 2.140033644215394, "grad_norm": 1.15883469581604, "learning_rate": 6.142011572615958e-05, "loss": 0.4641148567199707, "step": 360020 }, { "epoch": 2.1400930862920626, "grad_norm": 1.1479824781417847, "learning_rate": 6.141487577943055e-05, "loss": 0.4465456962585449, "step": 360030 }, { "epoch": 2.140152528368731, "grad_norm": 1.571890115737915, "learning_rate": 6.140963606511686e-05, "loss": 0.4807243824005127, "step": 360040 }, { "epoch": 2.1402119704453995, "grad_norm": 1.23499596118927, "learning_rate": 6.140439658324359e-05, "loss": 0.4810896396636963, "step": 360050 }, { "epoch": 2.140271412522068, "grad_norm": 1.1752692461013794, "learning_rate": 6.13991573338358e-05, "loss": 0.48592638969421387, "step": 360060 }, { "epoch": 2.1403308545987363, "grad_norm": 1.2192310094833374, "learning_rate": 6.139391831691855e-05, "loss": 0.5368195056915284, "step": 360070 }, { "epoch": 2.1403902966754047, "grad_norm": 1.0847644805908203, "learning_rate": 6.138867953251694e-05, "loss": 0.4763450622558594, "step": 360080 }, { "epoch": 2.140449738752073, "grad_norm": 1.4537460803985596, "learning_rate": 6.1383440980656e-05, "loss": 0.48599944114685056, "step": 360090 }, { "epoch": 2.1405091808287415, "grad_norm": 1.4009854793548584, "learning_rate": 6.137820266136078e-05, "loss": 0.45830535888671875, "step": 360100 }, { "epoch": 2.14056862290541, "grad_norm": 1.259299874305725, "learning_rate": 6.137296457465635e-05, "loss": 0.46854400634765625, "step": 360110 }, { "epoch": 2.1406280649820784, "grad_norm": 1.432191252708435, "learning_rate": 6.136772672056777e-05, "loss": 0.48834915161132814, "step": 360120 }, { "epoch": 2.1406875070587468, "grad_norm": 1.072452425956726, "learning_rate": 6.136248909912005e-05, "loss": 0.4546497344970703, "step": 360130 }, { "epoch": 2.140746949135415, "grad_norm": 1.242485761642456, "learning_rate": 6.135725171033833e-05, "loss": 0.46817641258239745, "step": 360140 }, { "epoch": 2.1408063912120836, "grad_norm": 1.3271201848983765, "learning_rate": 6.135201455424762e-05, "loss": 0.49228553771972655, "step": 360150 }, { "epoch": 2.1408658332887516, "grad_norm": 1.5295199155807495, "learning_rate": 6.134677763087296e-05, "loss": 0.5238851547241211, "step": 360160 }, { "epoch": 2.14092527536542, "grad_norm": 1.803100824356079, "learning_rate": 6.134154094023944e-05, "loss": 0.5611499786376953, "step": 360170 }, { "epoch": 2.1409847174420884, "grad_norm": 1.3017925024032593, "learning_rate": 6.133630448237207e-05, "loss": 0.5479761600494385, "step": 360180 }, { "epoch": 2.141044159518757, "grad_norm": 1.6098262071609497, "learning_rate": 6.13310682572959e-05, "loss": 0.5008743286132813, "step": 360190 }, { "epoch": 2.1411036015954252, "grad_norm": 1.3513232469558716, "learning_rate": 6.1325832265036e-05, "loss": 0.5188182830810547, "step": 360200 }, { "epoch": 2.1411630436720936, "grad_norm": 1.139231562614441, "learning_rate": 6.132059650561743e-05, "loss": 0.4616887092590332, "step": 360210 }, { "epoch": 2.141222485748762, "grad_norm": 1.2071352005004883, "learning_rate": 6.131536097906521e-05, "loss": 0.4485724449157715, "step": 360220 }, { "epoch": 2.1412819278254305, "grad_norm": 1.4146344661712646, "learning_rate": 6.131012568540439e-05, "loss": 0.45264286994934083, "step": 360230 }, { "epoch": 2.141341369902099, "grad_norm": 1.642774224281311, "learning_rate": 6.130489062466002e-05, "loss": 0.5207834720611573, "step": 360240 }, { "epoch": 2.1414008119787673, "grad_norm": 1.269331932067871, "learning_rate": 6.129965579685716e-05, "loss": 0.4812792778015137, "step": 360250 }, { "epoch": 2.1414602540554357, "grad_norm": 1.4442003965377808, "learning_rate": 6.129442120202078e-05, "loss": 0.46621065139770507, "step": 360260 }, { "epoch": 2.141519696132104, "grad_norm": 1.5016249418258667, "learning_rate": 6.128918684017601e-05, "loss": 0.4671661853790283, "step": 360270 }, { "epoch": 2.1415791382087725, "grad_norm": 1.426310420036316, "learning_rate": 6.128395271134783e-05, "loss": 0.5249892234802246, "step": 360280 }, { "epoch": 2.141638580285441, "grad_norm": 1.6297931671142578, "learning_rate": 6.127871881556133e-05, "loss": 0.5305051803588867, "step": 360290 }, { "epoch": 2.1416980223621094, "grad_norm": 1.40041983127594, "learning_rate": 6.12734851528415e-05, "loss": 0.5033141136169433, "step": 360300 }, { "epoch": 2.141757464438778, "grad_norm": 1.3492968082427979, "learning_rate": 6.12682517232134e-05, "loss": 0.548970365524292, "step": 360310 }, { "epoch": 2.141816906515446, "grad_norm": 1.5839860439300537, "learning_rate": 6.126301852670205e-05, "loss": 0.5496132850646973, "step": 360320 }, { "epoch": 2.1418763485921146, "grad_norm": 1.547392725944519, "learning_rate": 6.125778556333247e-05, "loss": 0.5638057708740234, "step": 360330 }, { "epoch": 2.141935790668783, "grad_norm": 1.2514574527740479, "learning_rate": 6.125255283312974e-05, "loss": 0.5135369300842285, "step": 360340 }, { "epoch": 2.141995232745451, "grad_norm": 1.263252854347229, "learning_rate": 6.124732033611887e-05, "loss": 0.5269952774047851, "step": 360350 }, { "epoch": 2.1420546748221194, "grad_norm": 1.067948341369629, "learning_rate": 6.124208807232487e-05, "loss": 0.4846039295196533, "step": 360360 }, { "epoch": 2.142114116898788, "grad_norm": 1.5704578161239624, "learning_rate": 6.123685604177282e-05, "loss": 0.5139597892761231, "step": 360370 }, { "epoch": 2.1421735589754562, "grad_norm": 1.3357266187667847, "learning_rate": 6.123162424448768e-05, "loss": 0.43978300094604494, "step": 360380 }, { "epoch": 2.1422330010521247, "grad_norm": 1.6505194902420044, "learning_rate": 6.122639268049453e-05, "loss": 0.48011341094970705, "step": 360390 }, { "epoch": 2.142292443128793, "grad_norm": 1.102211356163025, "learning_rate": 6.122116134981834e-05, "loss": 0.49056253433227537, "step": 360400 }, { "epoch": 2.1423518852054615, "grad_norm": 1.1349709033966064, "learning_rate": 6.12159302524842e-05, "loss": 0.4730860710144043, "step": 360410 }, { "epoch": 2.14241132728213, "grad_norm": 1.2068288326263428, "learning_rate": 6.121069938851717e-05, "loss": 0.5021333217620849, "step": 360420 }, { "epoch": 2.1424707693587983, "grad_norm": 1.251434326171875, "learning_rate": 6.120546875794211e-05, "loss": 0.5054286003112793, "step": 360430 }, { "epoch": 2.1425302114354667, "grad_norm": 1.250335931777954, "learning_rate": 6.120023836078419e-05, "loss": 0.5241457939147949, "step": 360440 }, { "epoch": 2.142589653512135, "grad_norm": 1.1276874542236328, "learning_rate": 6.119500819706838e-05, "loss": 0.4808927536010742, "step": 360450 }, { "epoch": 2.1426490955888036, "grad_norm": 1.325458288192749, "learning_rate": 6.118977826681967e-05, "loss": 0.48880572319030763, "step": 360460 }, { "epoch": 2.142708537665472, "grad_norm": 1.6101174354553223, "learning_rate": 6.118454857006314e-05, "loss": 0.5332182884216309, "step": 360470 }, { "epoch": 2.1427679797421404, "grad_norm": 1.3696184158325195, "learning_rate": 6.11793191068238e-05, "loss": 0.5050764560699463, "step": 360480 }, { "epoch": 2.142827421818809, "grad_norm": 1.5101264715194702, "learning_rate": 6.117408987712658e-05, "loss": 0.45568218231201174, "step": 360490 }, { "epoch": 2.1428868638954772, "grad_norm": 1.3252140283584595, "learning_rate": 6.11688608809966e-05, "loss": 0.4812454700469971, "step": 360500 }, { "epoch": 2.1429463059721456, "grad_norm": 1.156423807144165, "learning_rate": 6.116363211845884e-05, "loss": 0.4949501037597656, "step": 360510 }, { "epoch": 2.1430057480488136, "grad_norm": 2.1851627826690674, "learning_rate": 6.115840358953828e-05, "loss": 0.47145442962646483, "step": 360520 }, { "epoch": 2.143065190125482, "grad_norm": 1.6825934648513794, "learning_rate": 6.115317529425997e-05, "loss": 0.5164341926574707, "step": 360530 }, { "epoch": 2.1431246322021504, "grad_norm": 1.265248417854309, "learning_rate": 6.114794723264892e-05, "loss": 0.5290691375732421, "step": 360540 }, { "epoch": 2.143184074278819, "grad_norm": 1.441085934638977, "learning_rate": 6.11427194047301e-05, "loss": 0.49785518646240234, "step": 360550 }, { "epoch": 2.1432435163554873, "grad_norm": 1.5479165315628052, "learning_rate": 6.113749181052851e-05, "loss": 0.5077048778533936, "step": 360560 }, { "epoch": 2.1433029584321557, "grad_norm": 1.4294681549072266, "learning_rate": 6.113226445006923e-05, "loss": 0.5345173835754394, "step": 360570 }, { "epoch": 2.143362400508824, "grad_norm": 1.4582207202911377, "learning_rate": 6.112703732337723e-05, "loss": 0.4614212989807129, "step": 360580 }, { "epoch": 2.1434218425854925, "grad_norm": 1.511925220489502, "learning_rate": 6.112181043047753e-05, "loss": 0.5313974380493164, "step": 360590 }, { "epoch": 2.143481284662161, "grad_norm": 1.2025933265686035, "learning_rate": 6.111658377139509e-05, "loss": 0.4888327598571777, "step": 360600 }, { "epoch": 2.1435407267388293, "grad_norm": 1.4568274021148682, "learning_rate": 6.111135734615494e-05, "loss": 0.4962264060974121, "step": 360610 }, { "epoch": 2.1436001688154978, "grad_norm": 1.7065753936767578, "learning_rate": 6.110613115478206e-05, "loss": 0.5185483932495117, "step": 360620 }, { "epoch": 2.143659610892166, "grad_norm": 1.2588496208190918, "learning_rate": 6.110090519730147e-05, "loss": 0.4931607246398926, "step": 360630 }, { "epoch": 2.1437190529688346, "grad_norm": 1.2026196718215942, "learning_rate": 6.10956794737382e-05, "loss": 0.44041967391967773, "step": 360640 }, { "epoch": 2.143778495045503, "grad_norm": 1.1138118505477905, "learning_rate": 6.109045398411721e-05, "loss": 0.46483378410339354, "step": 360650 }, { "epoch": 2.1438379371221714, "grad_norm": 1.2009003162384033, "learning_rate": 6.108522872846351e-05, "loss": 0.49459543228149416, "step": 360660 }, { "epoch": 2.14389737919884, "grad_norm": 1.1028331518173218, "learning_rate": 6.108000370680208e-05, "loss": 0.5585356712341308, "step": 360670 }, { "epoch": 2.1439568212755082, "grad_norm": 1.740857720375061, "learning_rate": 6.107477891915794e-05, "loss": 0.5012569427490234, "step": 360680 }, { "epoch": 2.1440162633521767, "grad_norm": 1.3901982307434082, "learning_rate": 6.106955436555602e-05, "loss": 0.49689712524414065, "step": 360690 }, { "epoch": 2.144075705428845, "grad_norm": 1.406336784362793, "learning_rate": 6.106433004602141e-05, "loss": 0.5051734924316407, "step": 360700 }, { "epoch": 2.144135147505513, "grad_norm": 1.1254585981369019, "learning_rate": 6.105910596057903e-05, "loss": 0.49848480224609376, "step": 360710 }, { "epoch": 2.1441945895821815, "grad_norm": 1.3988862037658691, "learning_rate": 6.105388210925391e-05, "loss": 0.5042276859283448, "step": 360720 }, { "epoch": 2.14425403165885, "grad_norm": 1.3343909978866577, "learning_rate": 6.104865849207103e-05, "loss": 0.485296630859375, "step": 360730 }, { "epoch": 2.1443134737355183, "grad_norm": 1.8113657236099243, "learning_rate": 6.104343510905533e-05, "loss": 0.5320385456085205, "step": 360740 }, { "epoch": 2.1443729158121867, "grad_norm": 1.7104105949401855, "learning_rate": 6.103821196023187e-05, "loss": 0.5161609172821044, "step": 360750 }, { "epoch": 2.144432357888855, "grad_norm": 1.1948014497756958, "learning_rate": 6.1032989045625565e-05, "loss": 0.5099354743957519, "step": 360760 }, { "epoch": 2.1444917999655235, "grad_norm": 1.430456280708313, "learning_rate": 6.1027766365261484e-05, "loss": 0.49600982666015625, "step": 360770 }, { "epoch": 2.144551242042192, "grad_norm": 1.3530876636505127, "learning_rate": 6.102254391916454e-05, "loss": 0.5015972137451172, "step": 360780 }, { "epoch": 2.1446106841188604, "grad_norm": 1.3854994773864746, "learning_rate": 6.1017321707359756e-05, "loss": 0.4720188617706299, "step": 360790 }, { "epoch": 2.1446701261955288, "grad_norm": 1.673317790031433, "learning_rate": 6.10120997298721e-05, "loss": 0.47428102493286134, "step": 360800 }, { "epoch": 2.144729568272197, "grad_norm": 1.7055485248565674, "learning_rate": 6.1006877986726526e-05, "loss": 0.494818115234375, "step": 360810 }, { "epoch": 2.1447890103488656, "grad_norm": 1.9920603036880493, "learning_rate": 6.100165647794802e-05, "loss": 0.4691967010498047, "step": 360820 }, { "epoch": 2.144848452425534, "grad_norm": 0.8581933379173279, "learning_rate": 6.099643520356162e-05, "loss": 0.5015164852142334, "step": 360830 }, { "epoch": 2.1449078945022024, "grad_norm": 1.1197333335876465, "learning_rate": 6.0991214163592235e-05, "loss": 0.45024895668029785, "step": 360840 }, { "epoch": 2.144967336578871, "grad_norm": 0.9990007281303406, "learning_rate": 6.0985993358064885e-05, "loss": 0.5453104496002197, "step": 360850 }, { "epoch": 2.1450267786555393, "grad_norm": 1.4355541467666626, "learning_rate": 6.098077278700452e-05, "loss": 0.5007006645202636, "step": 360860 }, { "epoch": 2.1450862207322077, "grad_norm": 1.4588018655776978, "learning_rate": 6.0975552450436124e-05, "loss": 0.4879655361175537, "step": 360870 }, { "epoch": 2.145145662808876, "grad_norm": 1.7508585453033447, "learning_rate": 6.0970332348384653e-05, "loss": 0.5233317375183105, "step": 360880 }, { "epoch": 2.1452051048855445, "grad_norm": 1.5998191833496094, "learning_rate": 6.0965112480875054e-05, "loss": 0.5207450866699219, "step": 360890 }, { "epoch": 2.1452645469622125, "grad_norm": 1.098711609840393, "learning_rate": 6.095989284793238e-05, "loss": 0.5333974361419678, "step": 360900 }, { "epoch": 2.145323989038881, "grad_norm": 1.6060792207717896, "learning_rate": 6.095467344958157e-05, "loss": 0.48485660552978516, "step": 360910 }, { "epoch": 2.1453834311155493, "grad_norm": 1.2171213626861572, "learning_rate": 6.094945428584751e-05, "loss": 0.4769573211669922, "step": 360920 }, { "epoch": 2.1454428731922177, "grad_norm": 1.3991303443908691, "learning_rate": 6.0944235356755276e-05, "loss": 0.47151765823364256, "step": 360930 }, { "epoch": 2.145502315268886, "grad_norm": 1.2958203554153442, "learning_rate": 6.0939016662329774e-05, "loss": 0.5074379920959473, "step": 360940 }, { "epoch": 2.1455617573455545, "grad_norm": 1.4848226308822632, "learning_rate": 6.093379820259596e-05, "loss": 0.5326340675354004, "step": 360950 }, { "epoch": 2.145621199422223, "grad_norm": 1.2806416749954224, "learning_rate": 6.0928579977578845e-05, "loss": 0.5143766403198242, "step": 360960 }, { "epoch": 2.1456806414988914, "grad_norm": 1.3910025358200073, "learning_rate": 6.0923361987303406e-05, "loss": 0.46107139587402346, "step": 360970 }, { "epoch": 2.14574008357556, "grad_norm": 1.3380602598190308, "learning_rate": 6.091814423179449e-05, "loss": 0.46579203605651853, "step": 360980 }, { "epoch": 2.145799525652228, "grad_norm": 1.572367548942566, "learning_rate": 6.091292671107718e-05, "loss": 0.5164955615997314, "step": 360990 }, { "epoch": 2.1458589677288966, "grad_norm": 1.1091638803482056, "learning_rate": 6.090770942517637e-05, "loss": 0.467180061340332, "step": 361000 }, { "epoch": 2.145918409805565, "grad_norm": 1.3379303216934204, "learning_rate": 6.090249237411705e-05, "loss": 0.5198763847351074, "step": 361010 }, { "epoch": 2.1459778518822334, "grad_norm": 1.6769993305206299, "learning_rate": 6.0897275557924125e-05, "loss": 0.5357790946960449, "step": 361020 }, { "epoch": 2.146037293958902, "grad_norm": 1.1429548263549805, "learning_rate": 6.089205897662264e-05, "loss": 0.48851890563964845, "step": 361030 }, { "epoch": 2.1460967360355703, "grad_norm": 1.2629884481430054, "learning_rate": 6.0886842630237476e-05, "loss": 0.4596105575561523, "step": 361040 }, { "epoch": 2.1461561781122387, "grad_norm": 1.2257616519927979, "learning_rate": 6.0881626518793566e-05, "loss": 0.5004018306732178, "step": 361050 }, { "epoch": 2.146215620188907, "grad_norm": 1.197316288948059, "learning_rate": 6.087641064231595e-05, "loss": 0.4870366096496582, "step": 361060 }, { "epoch": 2.1462750622655755, "grad_norm": 1.5917640924453735, "learning_rate": 6.087119500082952e-05, "loss": 0.49835901260375975, "step": 361070 }, { "epoch": 2.146334504342244, "grad_norm": 1.725507140159607, "learning_rate": 6.08659795943592e-05, "loss": 0.5351961135864258, "step": 361080 }, { "epoch": 2.146393946418912, "grad_norm": 1.4771614074707031, "learning_rate": 6.086076442293005e-05, "loss": 0.4974623680114746, "step": 361090 }, { "epoch": 2.1464533884955803, "grad_norm": 1.1915010213851929, "learning_rate": 6.085554948656691e-05, "loss": 0.5353801727294922, "step": 361100 }, { "epoch": 2.1465128305722487, "grad_norm": 1.1031866073608398, "learning_rate": 6.085033478529474e-05, "loss": 0.47179012298583983, "step": 361110 }, { "epoch": 2.146572272648917, "grad_norm": 1.3461716175079346, "learning_rate": 6.0845120319138514e-05, "loss": 0.5564980506896973, "step": 361120 }, { "epoch": 2.1466317147255856, "grad_norm": 1.591207504272461, "learning_rate": 6.0839906088123176e-05, "loss": 0.4990013599395752, "step": 361130 }, { "epoch": 2.146691156802254, "grad_norm": 1.4152917861938477, "learning_rate": 6.083469209227367e-05, "loss": 0.5254655838012695, "step": 361140 }, { "epoch": 2.1467505988789224, "grad_norm": 1.3647918701171875, "learning_rate": 6.082947833161492e-05, "loss": 0.5012121200561523, "step": 361150 }, { "epoch": 2.146810040955591, "grad_norm": 0.9531689286231995, "learning_rate": 6.0824264806171896e-05, "loss": 0.4829707145690918, "step": 361160 }, { "epoch": 2.146869483032259, "grad_norm": 1.293532371520996, "learning_rate": 6.0819051515969504e-05, "loss": 0.5550312042236328, "step": 361170 }, { "epoch": 2.1469289251089276, "grad_norm": 1.5862491130828857, "learning_rate": 6.0813838461032655e-05, "loss": 0.47954273223876953, "step": 361180 }, { "epoch": 2.146988367185596, "grad_norm": 1.064586877822876, "learning_rate": 6.0808625641386386e-05, "loss": 0.5183312892913818, "step": 361190 }, { "epoch": 2.1470478092622645, "grad_norm": 1.10419762134552, "learning_rate": 6.0803413057055547e-05, "loss": 0.4749723434448242, "step": 361200 }, { "epoch": 2.147107251338933, "grad_norm": 1.145704746246338, "learning_rate": 6.079820070806512e-05, "loss": 0.4669647216796875, "step": 361210 }, { "epoch": 2.1471666934156013, "grad_norm": 1.3070536851882935, "learning_rate": 6.079298859444002e-05, "loss": 0.5363892555236817, "step": 361220 }, { "epoch": 2.1472261354922697, "grad_norm": 1.4747793674468994, "learning_rate": 6.0787776716205167e-05, "loss": 0.5599040508270263, "step": 361230 }, { "epoch": 2.147285577568938, "grad_norm": 1.3145426511764526, "learning_rate": 6.078256507338553e-05, "loss": 0.48431782722473143, "step": 361240 }, { "epoch": 2.1473450196456065, "grad_norm": 1.1835252046585083, "learning_rate": 6.077735366600598e-05, "loss": 0.47161216735839845, "step": 361250 }, { "epoch": 2.1474044617222745, "grad_norm": 1.437861442565918, "learning_rate": 6.077214249409151e-05, "loss": 0.5079095840454102, "step": 361260 }, { "epoch": 2.147463903798943, "grad_norm": 1.1618784666061401, "learning_rate": 6.076693155766702e-05, "loss": 0.5360430717468262, "step": 361270 }, { "epoch": 2.1475233458756113, "grad_norm": 1.5190738439559937, "learning_rate": 6.076172085675744e-05, "loss": 0.4823301792144775, "step": 361280 }, { "epoch": 2.1475827879522797, "grad_norm": 0.9607123136520386, "learning_rate": 6.07565103913877e-05, "loss": 0.45974388122558596, "step": 361290 }, { "epoch": 2.147642230028948, "grad_norm": 1.668071985244751, "learning_rate": 6.0751300161582725e-05, "loss": 0.5087977886199951, "step": 361300 }, { "epoch": 2.1477016721056166, "grad_norm": 1.3934067487716675, "learning_rate": 6.07460901673674e-05, "loss": 0.5010271072387695, "step": 361310 }, { "epoch": 2.147761114182285, "grad_norm": 1.5990912914276123, "learning_rate": 6.074088040876671e-05, "loss": 0.4641840934753418, "step": 361320 }, { "epoch": 2.1478205562589534, "grad_norm": 1.354920506477356, "learning_rate": 6.073567088580556e-05, "loss": 0.5447022438049316, "step": 361330 }, { "epoch": 2.147879998335622, "grad_norm": 1.4965064525604248, "learning_rate": 6.0730461598508856e-05, "loss": 0.4781494140625, "step": 361340 }, { "epoch": 2.1479394404122902, "grad_norm": 1.3233304023742676, "learning_rate": 6.0725252546901535e-05, "loss": 0.5166834831237793, "step": 361350 }, { "epoch": 2.1479988824889586, "grad_norm": 1.2417916059494019, "learning_rate": 6.072004373100848e-05, "loss": 0.5012966156005859, "step": 361360 }, { "epoch": 2.148058324565627, "grad_norm": 0.9296091198921204, "learning_rate": 6.071483515085463e-05, "loss": 0.5236897468566895, "step": 361370 }, { "epoch": 2.1481177666422955, "grad_norm": 1.4795600175857544, "learning_rate": 6.0709626806464884e-05, "loss": 0.5439599514007568, "step": 361380 }, { "epoch": 2.148177208718964, "grad_norm": 1.3330178260803223, "learning_rate": 6.070441869786421e-05, "loss": 0.5678521156311035, "step": 361390 }, { "epoch": 2.1482366507956323, "grad_norm": 1.304311990737915, "learning_rate": 6.069921082507751e-05, "loss": 0.4671778678894043, "step": 361400 }, { "epoch": 2.1482960928723007, "grad_norm": 1.2615567445755005, "learning_rate": 6.069400318812961e-05, "loss": 0.5148334503173828, "step": 361410 }, { "epoch": 2.148355534948969, "grad_norm": 1.7879098653793335, "learning_rate": 6.068879578704552e-05, "loss": 0.4720724105834961, "step": 361420 }, { "epoch": 2.1484149770256376, "grad_norm": 1.353274941444397, "learning_rate": 6.068358862185011e-05, "loss": 0.5293331623077393, "step": 361430 }, { "epoch": 2.148474419102306, "grad_norm": 1.325992226600647, "learning_rate": 6.0678381692568276e-05, "loss": 0.5230906963348388, "step": 361440 }, { "epoch": 2.148533861178974, "grad_norm": 1.358437418937683, "learning_rate": 6.067317499922497e-05, "loss": 0.5346080303192139, "step": 361450 }, { "epoch": 2.1485933032556424, "grad_norm": 1.9168660640716553, "learning_rate": 6.066796854184511e-05, "loss": 0.5020987510681152, "step": 361460 }, { "epoch": 2.1486527453323108, "grad_norm": 1.62967050075531, "learning_rate": 6.066276232045349e-05, "loss": 0.49235687255859373, "step": 361470 }, { "epoch": 2.148712187408979, "grad_norm": 1.1638911962509155, "learning_rate": 6.065755633507514e-05, "loss": 0.4538261413574219, "step": 361480 }, { "epoch": 2.1487716294856476, "grad_norm": 1.425641417503357, "learning_rate": 6.065235058573491e-05, "loss": 0.5259968280792237, "step": 361490 }, { "epoch": 2.148831071562316, "grad_norm": 1.1892035007476807, "learning_rate": 6.06471450724577e-05, "loss": 0.5022140502929687, "step": 361500 }, { "epoch": 2.1488905136389844, "grad_norm": 1.1925663948059082, "learning_rate": 6.06419397952684e-05, "loss": 0.4534619331359863, "step": 361510 }, { "epoch": 2.148949955715653, "grad_norm": 1.51023530960083, "learning_rate": 6.0636734754191985e-05, "loss": 0.5423898696899414, "step": 361520 }, { "epoch": 2.1490093977923213, "grad_norm": 1.327500581741333, "learning_rate": 6.063152994925327e-05, "loss": 0.4843013763427734, "step": 361530 }, { "epoch": 2.1490688398689897, "grad_norm": 1.587395191192627, "learning_rate": 6.0626325380477145e-05, "loss": 0.5107902526855469, "step": 361540 }, { "epoch": 2.149128281945658, "grad_norm": 1.1572715044021606, "learning_rate": 6.062112104788857e-05, "loss": 0.5088545799255371, "step": 361550 }, { "epoch": 2.1491877240223265, "grad_norm": 1.4275741577148438, "learning_rate": 6.061591695151243e-05, "loss": 0.4654065132141113, "step": 361560 }, { "epoch": 2.149247166098995, "grad_norm": 1.135841965675354, "learning_rate": 6.061071309137357e-05, "loss": 0.4855799674987793, "step": 361570 }, { "epoch": 2.1493066081756633, "grad_norm": 1.068442940711975, "learning_rate": 6.060550946749698e-05, "loss": 0.5046780109405518, "step": 361580 }, { "epoch": 2.1493660502523317, "grad_norm": 1.5557358264923096, "learning_rate": 6.0600306079907455e-05, "loss": 0.5365316867828369, "step": 361590 }, { "epoch": 2.149425492329, "grad_norm": 1.3376551866531372, "learning_rate": 6.059510292862992e-05, "loss": 0.4609514236450195, "step": 361600 }, { "epoch": 2.1494849344056686, "grad_norm": 1.2478948831558228, "learning_rate": 6.058990001368924e-05, "loss": 0.47039947509765623, "step": 361610 }, { "epoch": 2.149544376482337, "grad_norm": 1.2147376537322998, "learning_rate": 6.0584697335110366e-05, "loss": 0.516331148147583, "step": 361620 }, { "epoch": 2.1496038185590054, "grad_norm": 1.3619333505630493, "learning_rate": 6.057949489291814e-05, "loss": 0.5080916881561279, "step": 361630 }, { "epoch": 2.1496632606356734, "grad_norm": 1.2630313634872437, "learning_rate": 6.057429268713748e-05, "loss": 0.43493165969848635, "step": 361640 }, { "epoch": 2.149722702712342, "grad_norm": 1.571751594543457, "learning_rate": 6.056909071779323e-05, "loss": 0.5144286155700684, "step": 361650 }, { "epoch": 2.14978214478901, "grad_norm": 1.6627169847488403, "learning_rate": 6.05638889849103e-05, "loss": 0.5417306900024415, "step": 361660 }, { "epoch": 2.1498415868656786, "grad_norm": 1.4926121234893799, "learning_rate": 6.0558687488513545e-05, "loss": 0.5022648334503174, "step": 361670 }, { "epoch": 2.149901028942347, "grad_norm": 1.2682325839996338, "learning_rate": 6.05534862286279e-05, "loss": 0.561826753616333, "step": 361680 }, { "epoch": 2.1499604710190154, "grad_norm": 1.7269989252090454, "learning_rate": 6.054828520527821e-05, "loss": 0.5369772911071777, "step": 361690 }, { "epoch": 2.150019913095684, "grad_norm": 1.2732363939285278, "learning_rate": 6.054308441848937e-05, "loss": 0.5206286430358886, "step": 361700 }, { "epoch": 2.1500793551723523, "grad_norm": 1.3926398754119873, "learning_rate": 6.0537883868286246e-05, "loss": 0.4908146858215332, "step": 361710 }, { "epoch": 2.1501387972490207, "grad_norm": 1.4037268161773682, "learning_rate": 6.0532683554693726e-05, "loss": 0.5233755588531495, "step": 361720 }, { "epoch": 2.150198239325689, "grad_norm": 1.5587000846862793, "learning_rate": 6.052748347773669e-05, "loss": 0.49201264381408694, "step": 361730 }, { "epoch": 2.1502576814023575, "grad_norm": 1.3898966312408447, "learning_rate": 6.052228363743996e-05, "loss": 0.46229162216186526, "step": 361740 }, { "epoch": 2.150317123479026, "grad_norm": 1.426844596862793, "learning_rate": 6.05170840338285e-05, "loss": 0.4690749168395996, "step": 361750 }, { "epoch": 2.1503765655556943, "grad_norm": 1.5153415203094482, "learning_rate": 6.051188466692712e-05, "loss": 0.504481315612793, "step": 361760 }, { "epoch": 2.1504360076323628, "grad_norm": 1.1068073511123657, "learning_rate": 6.0506685536760733e-05, "loss": 0.48323917388916016, "step": 361770 }, { "epoch": 2.150495449709031, "grad_norm": 1.3397026062011719, "learning_rate": 6.050148664335418e-05, "loss": 0.4878800392150879, "step": 361780 }, { "epoch": 2.1505548917856996, "grad_norm": 1.5112767219543457, "learning_rate": 6.0496287986732326e-05, "loss": 0.5111666679382324, "step": 361790 }, { "epoch": 2.150614333862368, "grad_norm": 1.3053936958312988, "learning_rate": 6.049108956692004e-05, "loss": 0.5365021228790283, "step": 361800 }, { "epoch": 2.1506737759390364, "grad_norm": 1.3592833280563354, "learning_rate": 6.0485891383942205e-05, "loss": 0.5012636661529541, "step": 361810 }, { "epoch": 2.150733218015705, "grad_norm": 1.3488802909851074, "learning_rate": 6.048069343782371e-05, "loss": 0.45240259170532227, "step": 361820 }, { "epoch": 2.150792660092373, "grad_norm": 1.2791664600372314, "learning_rate": 6.0475495728589396e-05, "loss": 0.5293572425842286, "step": 361830 }, { "epoch": 2.150852102169041, "grad_norm": 1.2225205898284912, "learning_rate": 6.047029825626411e-05, "loss": 0.46700482368469237, "step": 361840 }, { "epoch": 2.1509115442457096, "grad_norm": 1.329588770866394, "learning_rate": 6.0465101020872736e-05, "loss": 0.5056386947631836, "step": 361850 }, { "epoch": 2.150970986322378, "grad_norm": 1.3800268173217773, "learning_rate": 6.045990402244013e-05, "loss": 0.4665241241455078, "step": 361860 }, { "epoch": 2.1510304283990465, "grad_norm": 2.1643528938293457, "learning_rate": 6.0454707260991114e-05, "loss": 0.505791425704956, "step": 361870 }, { "epoch": 2.151089870475715, "grad_norm": 1.8673063516616821, "learning_rate": 6.0449510736550644e-05, "loss": 0.4813981533050537, "step": 361880 }, { "epoch": 2.1511493125523833, "grad_norm": 1.360613226890564, "learning_rate": 6.0444314449143494e-05, "loss": 0.4746538162231445, "step": 361890 }, { "epoch": 2.1512087546290517, "grad_norm": 1.335218906402588, "learning_rate": 6.043911839879457e-05, "loss": 0.4777048110961914, "step": 361900 }, { "epoch": 2.15126819670572, "grad_norm": 1.375441074371338, "learning_rate": 6.0433922585528694e-05, "loss": 0.537172269821167, "step": 361910 }, { "epoch": 2.1513276387823885, "grad_norm": 1.0702836513519287, "learning_rate": 6.042872700937073e-05, "loss": 0.5254367828369141, "step": 361920 }, { "epoch": 2.151387080859057, "grad_norm": 1.0857031345367432, "learning_rate": 6.042353167034551e-05, "loss": 0.536988639831543, "step": 361930 }, { "epoch": 2.1514465229357254, "grad_norm": 1.2449452877044678, "learning_rate": 6.041833656847795e-05, "loss": 0.4636249542236328, "step": 361940 }, { "epoch": 2.1515059650123938, "grad_norm": 1.1899749040603638, "learning_rate": 6.0413141703792884e-05, "loss": 0.5098710060119629, "step": 361950 }, { "epoch": 2.151565407089062, "grad_norm": 1.373478889465332, "learning_rate": 6.04079470763151e-05, "loss": 0.5206694602966309, "step": 361960 }, { "epoch": 2.1516248491657306, "grad_norm": 1.4602289199829102, "learning_rate": 6.040275268606951e-05, "loss": 0.48308792114257815, "step": 361970 }, { "epoch": 2.151684291242399, "grad_norm": 1.38568115234375, "learning_rate": 6.0397558533080935e-05, "loss": 0.5044745445251465, "step": 361980 }, { "epoch": 2.1517437333190674, "grad_norm": 1.3408317565917969, "learning_rate": 6.039236461737423e-05, "loss": 0.4696939945220947, "step": 361990 }, { "epoch": 2.1518031753957354, "grad_norm": 1.5427972078323364, "learning_rate": 6.038717093897422e-05, "loss": 0.5711595058441162, "step": 362000 }, { "epoch": 2.151862617472404, "grad_norm": 1.00469172000885, "learning_rate": 6.038197749790584e-05, "loss": 0.5055393695831298, "step": 362010 }, { "epoch": 2.1519220595490722, "grad_norm": 1.4286261796951294, "learning_rate": 6.0376784294193825e-05, "loss": 0.5273673057556152, "step": 362020 }, { "epoch": 2.1519815016257406, "grad_norm": 1.5489497184753418, "learning_rate": 6.0371591327863006e-05, "loss": 0.5094562530517578, "step": 362030 }, { "epoch": 2.152040943702409, "grad_norm": 1.2685987949371338, "learning_rate": 6.036639859893833e-05, "loss": 0.5008125305175781, "step": 362040 }, { "epoch": 2.1521003857790775, "grad_norm": 1.1169992685317993, "learning_rate": 6.036120610744458e-05, "loss": 0.49783172607421877, "step": 362050 }, { "epoch": 2.152159827855746, "grad_norm": 1.683527946472168, "learning_rate": 6.035601385340656e-05, "loss": 0.5555893898010253, "step": 362060 }, { "epoch": 2.1522192699324143, "grad_norm": 1.2806442975997925, "learning_rate": 6.0350821836849215e-05, "loss": 0.502139949798584, "step": 362070 }, { "epoch": 2.1522787120090827, "grad_norm": 1.0167055130004883, "learning_rate": 6.0345630057797275e-05, "loss": 0.4974808216094971, "step": 362080 }, { "epoch": 2.152338154085751, "grad_norm": 1.3770555257797241, "learning_rate": 6.034043851627562e-05, "loss": 0.4992538928985596, "step": 362090 }, { "epoch": 2.1523975961624195, "grad_norm": 1.5271857976913452, "learning_rate": 6.033524721230903e-05, "loss": 0.5525405883789063, "step": 362100 }, { "epoch": 2.152457038239088, "grad_norm": 1.2246817350387573, "learning_rate": 6.0330056145922445e-05, "loss": 0.5690322399139405, "step": 362110 }, { "epoch": 2.1525164803157564, "grad_norm": 1.1573925018310547, "learning_rate": 6.032486531714061e-05, "loss": 0.5619789600372315, "step": 362120 }, { "epoch": 2.152575922392425, "grad_norm": 1.7918531894683838, "learning_rate": 6.031967472598841e-05, "loss": 0.5175857543945312, "step": 362130 }, { "epoch": 2.152635364469093, "grad_norm": 1.27053701877594, "learning_rate": 6.031448437249063e-05, "loss": 0.4841193675994873, "step": 362140 }, { "epoch": 2.1526948065457616, "grad_norm": 1.4901260137557983, "learning_rate": 6.030929425667213e-05, "loss": 0.5287873268127441, "step": 362150 }, { "epoch": 2.15275424862243, "grad_norm": 1.1880707740783691, "learning_rate": 6.03041043785577e-05, "loss": 0.45662784576416016, "step": 362160 }, { "epoch": 2.1528136906990984, "grad_norm": 1.4230457544326782, "learning_rate": 6.0298914738172217e-05, "loss": 0.4759626865386963, "step": 362170 }, { "epoch": 2.152873132775767, "grad_norm": 1.185315728187561, "learning_rate": 6.02937253355405e-05, "loss": 0.4951439380645752, "step": 362180 }, { "epoch": 2.152932574852435, "grad_norm": 1.3499975204467773, "learning_rate": 6.028853617068734e-05, "loss": 0.4835838317871094, "step": 362190 }, { "epoch": 2.1529920169291032, "grad_norm": 1.2809202671051025, "learning_rate": 6.028334724363758e-05, "loss": 0.5222620964050293, "step": 362200 }, { "epoch": 2.1530514590057717, "grad_norm": 1.1834564208984375, "learning_rate": 6.0278158554416044e-05, "loss": 0.5133602142333984, "step": 362210 }, { "epoch": 2.15311090108244, "grad_norm": 1.298130989074707, "learning_rate": 6.027297010304756e-05, "loss": 0.45471854209899903, "step": 362220 }, { "epoch": 2.1531703431591085, "grad_norm": 1.097497820854187, "learning_rate": 6.0267781889556875e-05, "loss": 0.4761027812957764, "step": 362230 }, { "epoch": 2.153229785235777, "grad_norm": 1.4672982692718506, "learning_rate": 6.0262593913968915e-05, "loss": 0.5202579021453857, "step": 362240 }, { "epoch": 2.1532892273124453, "grad_norm": 1.4338146448135376, "learning_rate": 6.025740617630844e-05, "loss": 0.5133888244628906, "step": 362250 }, { "epoch": 2.1533486693891137, "grad_norm": 1.7796152830123901, "learning_rate": 6.025221867660029e-05, "loss": 0.530039119720459, "step": 362260 }, { "epoch": 2.153408111465782, "grad_norm": 1.6481326818466187, "learning_rate": 6.024703141486927e-05, "loss": 0.5214777946472168, "step": 362270 }, { "epoch": 2.1534675535424506, "grad_norm": 1.0901516675949097, "learning_rate": 6.024184439114019e-05, "loss": 0.5198923587799072, "step": 362280 }, { "epoch": 2.153526995619119, "grad_norm": 1.499590516090393, "learning_rate": 6.023665760543784e-05, "loss": 0.5050406455993652, "step": 362290 }, { "epoch": 2.1535864376957874, "grad_norm": 1.3015578985214233, "learning_rate": 6.023147105778708e-05, "loss": 0.5194137096405029, "step": 362300 }, { "epoch": 2.153645879772456, "grad_norm": 0.9402355551719666, "learning_rate": 6.022628474821269e-05, "loss": 0.5137510776519776, "step": 362310 }, { "epoch": 2.153705321849124, "grad_norm": 1.5474435091018677, "learning_rate": 6.022109867673951e-05, "loss": 0.5544568061828613, "step": 362320 }, { "epoch": 2.1537647639257926, "grad_norm": 1.0485740900039673, "learning_rate": 6.0215912843392305e-05, "loss": 0.5075047492980957, "step": 362330 }, { "epoch": 2.153824206002461, "grad_norm": 1.3582689762115479, "learning_rate": 6.021072724819592e-05, "loss": 0.4818722724914551, "step": 362340 }, { "epoch": 2.1538836480791295, "grad_norm": 1.4374161958694458, "learning_rate": 6.020554189117513e-05, "loss": 0.4426994323730469, "step": 362350 }, { "epoch": 2.153943090155798, "grad_norm": 1.4400174617767334, "learning_rate": 6.0200356772354714e-05, "loss": 0.44995269775390623, "step": 362360 }, { "epoch": 2.1540025322324663, "grad_norm": 1.1436326503753662, "learning_rate": 6.0195171891759583e-05, "loss": 0.4829537391662598, "step": 362370 }, { "epoch": 2.1540619743091343, "grad_norm": 1.2027385234832764, "learning_rate": 6.018998724941445e-05, "loss": 0.5150196075439453, "step": 362380 }, { "epoch": 2.1541214163858027, "grad_norm": 2.175523519515991, "learning_rate": 6.0184802845344145e-05, "loss": 0.515120267868042, "step": 362390 }, { "epoch": 2.154180858462471, "grad_norm": 1.3734569549560547, "learning_rate": 6.0179618679573454e-05, "loss": 0.47474122047424316, "step": 362400 }, { "epoch": 2.1542403005391395, "grad_norm": 1.2404347658157349, "learning_rate": 6.0174434752127206e-05, "loss": 0.45346622467041015, "step": 362410 }, { "epoch": 2.154299742615808, "grad_norm": 1.7272462844848633, "learning_rate": 6.0169251063030127e-05, "loss": 0.4782224655151367, "step": 362420 }, { "epoch": 2.1543591846924763, "grad_norm": 1.2700977325439453, "learning_rate": 6.0164067612307106e-05, "loss": 0.4983715534210205, "step": 362430 }, { "epoch": 2.1544186267691448, "grad_norm": 1.6065058708190918, "learning_rate": 6.01588843999829e-05, "loss": 0.4482781410217285, "step": 362440 }, { "epoch": 2.154478068845813, "grad_norm": 1.3885536193847656, "learning_rate": 6.015370142608233e-05, "loss": 0.4873790740966797, "step": 362450 }, { "epoch": 2.1545375109224816, "grad_norm": 1.7155086994171143, "learning_rate": 6.0148518690630093e-05, "loss": 0.5148802757263183, "step": 362460 }, { "epoch": 2.15459695299915, "grad_norm": 1.5531927347183228, "learning_rate": 6.01433361936511e-05, "loss": 0.5177151679992675, "step": 362470 }, { "epoch": 2.1546563950758184, "grad_norm": 1.6475878953933716, "learning_rate": 6.0138153935170084e-05, "loss": 0.5152253150939942, "step": 362480 }, { "epoch": 2.154715837152487, "grad_norm": 1.2034826278686523, "learning_rate": 6.013297191521181e-05, "loss": 0.477934455871582, "step": 362490 }, { "epoch": 2.1547752792291552, "grad_norm": 1.5671887397766113, "learning_rate": 6.012779013380114e-05, "loss": 0.500020694732666, "step": 362500 }, { "epoch": 2.1548347213058237, "grad_norm": 1.3568360805511475, "learning_rate": 6.012260859096286e-05, "loss": 0.4830209732055664, "step": 362510 }, { "epoch": 2.154894163382492, "grad_norm": 1.0888839960098267, "learning_rate": 6.011742728672165e-05, "loss": 0.4860318660736084, "step": 362520 }, { "epoch": 2.1549536054591605, "grad_norm": 1.1183792352676392, "learning_rate": 6.011224622110239e-05, "loss": 0.42470455169677734, "step": 362530 }, { "epoch": 2.155013047535829, "grad_norm": 1.7150380611419678, "learning_rate": 6.010706539412985e-05, "loss": 0.46296138763427735, "step": 362540 }, { "epoch": 2.155072489612497, "grad_norm": 1.2365045547485352, "learning_rate": 6.010188480582877e-05, "loss": 0.47815237045288084, "step": 362550 }, { "epoch": 2.1551319316891657, "grad_norm": 1.2764315605163574, "learning_rate": 6.009670445622403e-05, "loss": 0.5165714740753173, "step": 362560 }, { "epoch": 2.1551913737658337, "grad_norm": 2.0435101985931396, "learning_rate": 6.009152434534031e-05, "loss": 0.5045858383178711, "step": 362570 }, { "epoch": 2.155250815842502, "grad_norm": 1.1794698238372803, "learning_rate": 6.008634447320244e-05, "loss": 0.47911911010742186, "step": 362580 }, { "epoch": 2.1553102579191705, "grad_norm": 1.428174376487732, "learning_rate": 6.0081164839835144e-05, "loss": 0.46736440658569334, "step": 362590 }, { "epoch": 2.155369699995839, "grad_norm": 1.1593716144561768, "learning_rate": 6.007598544526327e-05, "loss": 0.48471927642822266, "step": 362600 }, { "epoch": 2.1554291420725074, "grad_norm": 1.5088491439819336, "learning_rate": 6.007080628951158e-05, "loss": 0.5035215854644776, "step": 362610 }, { "epoch": 2.1554885841491758, "grad_norm": 1.2762341499328613, "learning_rate": 6.006562737260483e-05, "loss": 0.4968263626098633, "step": 362620 }, { "epoch": 2.155548026225844, "grad_norm": 1.3415586948394775, "learning_rate": 6.006044869456779e-05, "loss": 0.5101409435272217, "step": 362630 }, { "epoch": 2.1556074683025126, "grad_norm": 1.2435884475708008, "learning_rate": 6.005527025542526e-05, "loss": 0.49392175674438477, "step": 362640 }, { "epoch": 2.155666910379181, "grad_norm": 1.6579560041427612, "learning_rate": 6.005009205520196e-05, "loss": 0.4752333641052246, "step": 362650 }, { "epoch": 2.1557263524558494, "grad_norm": 1.2822704315185547, "learning_rate": 6.00449140939227e-05, "loss": 0.503017807006836, "step": 362660 }, { "epoch": 2.155785794532518, "grad_norm": 1.3336138725280762, "learning_rate": 6.003973637161228e-05, "loss": 0.5197376251220703, "step": 362670 }, { "epoch": 2.1558452366091863, "grad_norm": 1.2570480108261108, "learning_rate": 6.003455888829541e-05, "loss": 0.4538418769836426, "step": 362680 }, { "epoch": 2.1559046786858547, "grad_norm": 1.3293927907943726, "learning_rate": 6.002938164399689e-05, "loss": 0.5060392379760742, "step": 362690 }, { "epoch": 2.155964120762523, "grad_norm": 1.370285153388977, "learning_rate": 6.00242046387415e-05, "loss": 0.5599992752075196, "step": 362700 }, { "epoch": 2.1560235628391915, "grad_norm": 1.2397210597991943, "learning_rate": 6.001902787255396e-05, "loss": 0.47916498184204104, "step": 362710 }, { "epoch": 2.15608300491586, "grad_norm": 1.2936683893203735, "learning_rate": 6.001385134545902e-05, "loss": 0.5162222862243653, "step": 362720 }, { "epoch": 2.1561424469925283, "grad_norm": 1.1036169528961182, "learning_rate": 6.000867505748151e-05, "loss": 0.46027498245239257, "step": 362730 }, { "epoch": 2.1562018890691963, "grad_norm": 1.4807462692260742, "learning_rate": 6.0003499008646193e-05, "loss": 0.5131447315216064, "step": 362740 }, { "epoch": 2.1562613311458647, "grad_norm": 1.4908840656280518, "learning_rate": 5.999832319897776e-05, "loss": 0.5077858448028565, "step": 362750 }, { "epoch": 2.156320773222533, "grad_norm": 1.7325468063354492, "learning_rate": 5.999314762850104e-05, "loss": 0.5302061557769775, "step": 362760 }, { "epoch": 2.1563802152992015, "grad_norm": 1.5739115476608276, "learning_rate": 5.998797229724073e-05, "loss": 0.5838338375091553, "step": 362770 }, { "epoch": 2.15643965737587, "grad_norm": 1.2919381856918335, "learning_rate": 5.99827972052216e-05, "loss": 0.5479118347167968, "step": 362780 }, { "epoch": 2.1564990994525384, "grad_norm": 1.0175095796585083, "learning_rate": 5.9977622352468455e-05, "loss": 0.5049101352691651, "step": 362790 }, { "epoch": 2.156558541529207, "grad_norm": 1.270839810371399, "learning_rate": 5.997244773900601e-05, "loss": 0.5166674613952636, "step": 362800 }, { "epoch": 2.156617983605875, "grad_norm": 0.9227744340896606, "learning_rate": 5.996727336485903e-05, "loss": 0.4542209625244141, "step": 362810 }, { "epoch": 2.1566774256825436, "grad_norm": 1.6460058689117432, "learning_rate": 5.996209923005226e-05, "loss": 0.4952824592590332, "step": 362820 }, { "epoch": 2.156736867759212, "grad_norm": 1.578418254852295, "learning_rate": 5.9956925334610456e-05, "loss": 0.5389278888702392, "step": 362830 }, { "epoch": 2.1567963098358804, "grad_norm": 1.4556665420532227, "learning_rate": 5.9951751678558375e-05, "loss": 0.5017457962036133, "step": 362840 }, { "epoch": 2.156855751912549, "grad_norm": 1.5011523962020874, "learning_rate": 5.994657826192071e-05, "loss": 0.5484784126281739, "step": 362850 }, { "epoch": 2.1569151939892173, "grad_norm": 1.413880705833435, "learning_rate": 5.9941405084722304e-05, "loss": 0.5101134300231933, "step": 362860 }, { "epoch": 2.1569746360658857, "grad_norm": 1.2740387916564941, "learning_rate": 5.993623214698785e-05, "loss": 0.5051734924316407, "step": 362870 }, { "epoch": 2.157034078142554, "grad_norm": 1.0800098180770874, "learning_rate": 5.99310594487421e-05, "loss": 0.5220066547393799, "step": 362880 }, { "epoch": 2.1570935202192225, "grad_norm": 1.5470144748687744, "learning_rate": 5.992588699000981e-05, "loss": 0.5062606811523438, "step": 362890 }, { "epoch": 2.157152962295891, "grad_norm": 1.4210222959518433, "learning_rate": 5.992071477081569e-05, "loss": 0.5326550483703614, "step": 362900 }, { "epoch": 2.1572124043725593, "grad_norm": 1.1615307331085205, "learning_rate": 5.991554279118449e-05, "loss": 0.5133190155029297, "step": 362910 }, { "epoch": 2.1572718464492278, "grad_norm": 1.4896901845932007, "learning_rate": 5.991037105114099e-05, "loss": 0.491317081451416, "step": 362920 }, { "epoch": 2.1573312885258957, "grad_norm": 1.3165687322616577, "learning_rate": 5.99051995507099e-05, "loss": 0.4832622528076172, "step": 362930 }, { "epoch": 2.157390730602564, "grad_norm": 1.4951109886169434, "learning_rate": 5.990002828991601e-05, "loss": 0.47756447792053225, "step": 362940 }, { "epoch": 2.1574501726792326, "grad_norm": 1.3045196533203125, "learning_rate": 5.989485726878394e-05, "loss": 0.5137365341186524, "step": 362950 }, { "epoch": 2.157509614755901, "grad_norm": 1.3560435771942139, "learning_rate": 5.988968648733855e-05, "loss": 0.47239322662353517, "step": 362960 }, { "epoch": 2.1575690568325694, "grad_norm": 1.147538661956787, "learning_rate": 5.988451594560449e-05, "loss": 0.512841272354126, "step": 362970 }, { "epoch": 2.157628498909238, "grad_norm": 1.3735010623931885, "learning_rate": 5.987934564360651e-05, "loss": 0.4677602767944336, "step": 362980 }, { "epoch": 2.157687940985906, "grad_norm": 1.147325038909912, "learning_rate": 5.987417558136941e-05, "loss": 0.4673933029174805, "step": 362990 }, { "epoch": 2.1577473830625746, "grad_norm": 1.1302136182785034, "learning_rate": 5.986900575891787e-05, "loss": 0.5310920715332031, "step": 363000 }, { "epoch": 2.157806825139243, "grad_norm": 1.4819083213806152, "learning_rate": 5.9863836176276575e-05, "loss": 0.5065599918365479, "step": 363010 }, { "epoch": 2.1578662672159115, "grad_norm": 1.5856115818023682, "learning_rate": 5.9858666833470354e-05, "loss": 0.48891000747680663, "step": 363020 }, { "epoch": 2.15792570929258, "grad_norm": 1.3721694946289062, "learning_rate": 5.985349773052387e-05, "loss": 0.4790452003479004, "step": 363030 }, { "epoch": 2.1579851513692483, "grad_norm": 1.3717057704925537, "learning_rate": 5.9848328867461834e-05, "loss": 0.4972956657409668, "step": 363040 }, { "epoch": 2.1580445934459167, "grad_norm": 1.812435269355774, "learning_rate": 5.984316024430903e-05, "loss": 0.5229092121124268, "step": 363050 }, { "epoch": 2.158104035522585, "grad_norm": 1.5725868940353394, "learning_rate": 5.983799186109019e-05, "loss": 0.48495144844055177, "step": 363060 }, { "epoch": 2.1581634775992535, "grad_norm": 1.394351601600647, "learning_rate": 5.983282371782998e-05, "loss": 0.5142196178436279, "step": 363070 }, { "epoch": 2.158222919675922, "grad_norm": 1.3171635866165161, "learning_rate": 5.9827655814553096e-05, "loss": 0.4989638328552246, "step": 363080 }, { "epoch": 2.1582823617525904, "grad_norm": 1.4950226545333862, "learning_rate": 5.982248815128436e-05, "loss": 0.5208368301391602, "step": 363090 }, { "epoch": 2.1583418038292588, "grad_norm": 1.3918006420135498, "learning_rate": 5.981732072804843e-05, "loss": 0.4545596599578857, "step": 363100 }, { "epoch": 2.158401245905927, "grad_norm": 1.264025092124939, "learning_rate": 5.981215354487002e-05, "loss": 0.4943399429321289, "step": 363110 }, { "epoch": 2.158460687982595, "grad_norm": 1.6124541759490967, "learning_rate": 5.980698660177392e-05, "loss": 0.530894660949707, "step": 363120 }, { "epoch": 2.1585201300592636, "grad_norm": 1.5487418174743652, "learning_rate": 5.980181989878476e-05, "loss": 0.5279070854187011, "step": 363130 }, { "epoch": 2.158579572135932, "grad_norm": 1.2594150304794312, "learning_rate": 5.979665343592726e-05, "loss": 0.4974794387817383, "step": 363140 }, { "epoch": 2.1586390142126004, "grad_norm": 1.1875966787338257, "learning_rate": 5.9791487213226195e-05, "loss": 0.4834102153778076, "step": 363150 }, { "epoch": 2.158698456289269, "grad_norm": 1.4340898990631104, "learning_rate": 5.9786321230706247e-05, "loss": 0.48744959831237794, "step": 363160 }, { "epoch": 2.1587578983659372, "grad_norm": 1.3669390678405762, "learning_rate": 5.978115548839213e-05, "loss": 0.4871185302734375, "step": 363170 }, { "epoch": 2.1588173404426056, "grad_norm": 1.1104472875595093, "learning_rate": 5.977598998630856e-05, "loss": 0.49889817237854006, "step": 363180 }, { "epoch": 2.158876782519274, "grad_norm": 1.3485784530639648, "learning_rate": 5.9770824724480215e-05, "loss": 0.5415279388427734, "step": 363190 }, { "epoch": 2.1589362245959425, "grad_norm": 1.6283103227615356, "learning_rate": 5.9765659702931844e-05, "loss": 0.5024175643920898, "step": 363200 }, { "epoch": 2.158995666672611, "grad_norm": 1.2241863012313843, "learning_rate": 5.9760494921688116e-05, "loss": 0.5038397789001465, "step": 363210 }, { "epoch": 2.1590551087492793, "grad_norm": 1.0657916069030762, "learning_rate": 5.975533038077379e-05, "loss": 0.4948244094848633, "step": 363220 }, { "epoch": 2.1591145508259477, "grad_norm": 1.2079824209213257, "learning_rate": 5.9750166080213535e-05, "loss": 0.4566180229187012, "step": 363230 }, { "epoch": 2.159173992902616, "grad_norm": 1.3315664529800415, "learning_rate": 5.974500202003207e-05, "loss": 0.4741631031036377, "step": 363240 }, { "epoch": 2.1592334349792845, "grad_norm": 1.3834108114242554, "learning_rate": 5.97398382002541e-05, "loss": 0.5164630889892579, "step": 363250 }, { "epoch": 2.159292877055953, "grad_norm": 1.141323447227478, "learning_rate": 5.973467462090431e-05, "loss": 0.5157258987426758, "step": 363260 }, { "epoch": 2.1593523191326214, "grad_norm": 1.3081026077270508, "learning_rate": 5.972951128200737e-05, "loss": 0.5077590942382812, "step": 363270 }, { "epoch": 2.15941176120929, "grad_norm": 1.4564145803451538, "learning_rate": 5.972434818358806e-05, "loss": 0.49280705451965334, "step": 363280 }, { "epoch": 2.1594712032859578, "grad_norm": 1.2986485958099365, "learning_rate": 5.9719185325671044e-05, "loss": 0.5575767517089844, "step": 363290 }, { "epoch": 2.1595306453626266, "grad_norm": 1.293687343597412, "learning_rate": 5.9714022708281e-05, "loss": 0.4657301902770996, "step": 363300 }, { "epoch": 2.1595900874392946, "grad_norm": 1.2226239442825317, "learning_rate": 5.970886033144265e-05, "loss": 0.4662936687469482, "step": 363310 }, { "epoch": 2.159649529515963, "grad_norm": 1.3900409936904907, "learning_rate": 5.970369819518067e-05, "loss": 0.47544307708740235, "step": 363320 }, { "epoch": 2.1597089715926314, "grad_norm": 0.9819406270980835, "learning_rate": 5.969853629951976e-05, "loss": 0.44588165283203124, "step": 363330 }, { "epoch": 2.1597684136693, "grad_norm": 1.5255088806152344, "learning_rate": 5.969337464448459e-05, "loss": 0.4801973342895508, "step": 363340 }, { "epoch": 2.1598278557459683, "grad_norm": 0.9309197068214417, "learning_rate": 5.96882132300999e-05, "loss": 0.5047802448272705, "step": 363350 }, { "epoch": 2.1598872978226367, "grad_norm": 1.4960354566574097, "learning_rate": 5.968305205639035e-05, "loss": 0.5234162330627441, "step": 363360 }, { "epoch": 2.159946739899305, "grad_norm": 1.3247706890106201, "learning_rate": 5.9677891123380644e-05, "loss": 0.5182737827301025, "step": 363370 }, { "epoch": 2.1600061819759735, "grad_norm": 1.9095193147659302, "learning_rate": 5.967273043109546e-05, "loss": 0.5464589118957519, "step": 363380 }, { "epoch": 2.160065624052642, "grad_norm": 1.0977861881256104, "learning_rate": 5.966756997955949e-05, "loss": 0.4886812210083008, "step": 363390 }, { "epoch": 2.1601250661293103, "grad_norm": 1.1827595233917236, "learning_rate": 5.966240976879738e-05, "loss": 0.513681697845459, "step": 363400 }, { "epoch": 2.1601845082059787, "grad_norm": 1.0481202602386475, "learning_rate": 5.965724979883388e-05, "loss": 0.5092594623565674, "step": 363410 }, { "epoch": 2.160243950282647, "grad_norm": 1.4843990802764893, "learning_rate": 5.965209006969366e-05, "loss": 0.519792890548706, "step": 363420 }, { "epoch": 2.1603033923593156, "grad_norm": 1.3209584951400757, "learning_rate": 5.9646930581401404e-05, "loss": 0.4895143508911133, "step": 363430 }, { "epoch": 2.160362834435984, "grad_norm": 1.2964096069335938, "learning_rate": 5.964177133398172e-05, "loss": 0.5093239307403564, "step": 363440 }, { "epoch": 2.1604222765126524, "grad_norm": 1.206679105758667, "learning_rate": 5.963661232745936e-05, "loss": 0.5131474494934082, "step": 363450 }, { "epoch": 2.160481718589321, "grad_norm": 1.1988664865493774, "learning_rate": 5.9631453561858995e-05, "loss": 0.46608738899230956, "step": 363460 }, { "epoch": 2.1605411606659892, "grad_norm": 1.1961897611618042, "learning_rate": 5.962629503720527e-05, "loss": 0.5430287837982177, "step": 363470 }, { "epoch": 2.160600602742657, "grad_norm": 1.3717907667160034, "learning_rate": 5.962113675352293e-05, "loss": 0.45749378204345703, "step": 363480 }, { "epoch": 2.1606600448193256, "grad_norm": 1.4845914840698242, "learning_rate": 5.961597871083664e-05, "loss": 0.504914665222168, "step": 363490 }, { "epoch": 2.160719486895994, "grad_norm": 1.407348394393921, "learning_rate": 5.961082090917096e-05, "loss": 0.4972052574157715, "step": 363500 }, { "epoch": 2.1607789289726624, "grad_norm": 1.1203763484954834, "learning_rate": 5.9605663348550686e-05, "loss": 0.5509414196014404, "step": 363510 }, { "epoch": 2.160838371049331, "grad_norm": 1.0570961236953735, "learning_rate": 5.9600506029000446e-05, "loss": 0.48614025115966797, "step": 363520 }, { "epoch": 2.1608978131259993, "grad_norm": 0.9863552451133728, "learning_rate": 5.959534895054488e-05, "loss": 0.47937631607055664, "step": 363530 }, { "epoch": 2.1609572552026677, "grad_norm": 1.3186882734298706, "learning_rate": 5.9590192113208734e-05, "loss": 0.4920774459838867, "step": 363540 }, { "epoch": 2.161016697279336, "grad_norm": 1.3665008544921875, "learning_rate": 5.9585035517016655e-05, "loss": 0.5101837158203125, "step": 363550 }, { "epoch": 2.1610761393560045, "grad_norm": 1.601986289024353, "learning_rate": 5.957987916199327e-05, "loss": 0.4351454734802246, "step": 363560 }, { "epoch": 2.161135581432673, "grad_norm": 1.3931914567947388, "learning_rate": 5.957472304816323e-05, "loss": 0.4958344459533691, "step": 363570 }, { "epoch": 2.1611950235093413, "grad_norm": 1.318846344947815, "learning_rate": 5.956956717555125e-05, "loss": 0.4898539543151855, "step": 363580 }, { "epoch": 2.1612544655860098, "grad_norm": 1.1474573612213135, "learning_rate": 5.9564411544181994e-05, "loss": 0.5185205936431885, "step": 363590 }, { "epoch": 2.161313907662678, "grad_norm": 1.363223671913147, "learning_rate": 5.955925615408009e-05, "loss": 0.48609156608581544, "step": 363600 }, { "epoch": 2.1613733497393466, "grad_norm": 1.4726485013961792, "learning_rate": 5.955410100527028e-05, "loss": 0.5941770553588868, "step": 363610 }, { "epoch": 2.161432791816015, "grad_norm": 1.5854076147079468, "learning_rate": 5.954894609777713e-05, "loss": 0.5034243583679199, "step": 363620 }, { "epoch": 2.1614922338926834, "grad_norm": 1.1999707221984863, "learning_rate": 5.9543791431625296e-05, "loss": 0.41971912384033205, "step": 363630 }, { "epoch": 2.161551675969352, "grad_norm": 1.7114849090576172, "learning_rate": 5.953863700683951e-05, "loss": 0.5116289615631103, "step": 363640 }, { "epoch": 2.1616111180460202, "grad_norm": 1.28245210647583, "learning_rate": 5.953348282344439e-05, "loss": 0.4883531093597412, "step": 363650 }, { "epoch": 2.1616705601226887, "grad_norm": 1.5262531042099, "learning_rate": 5.952832888146456e-05, "loss": 0.4960306644439697, "step": 363660 }, { "epoch": 2.1617300021993566, "grad_norm": 1.3338887691497803, "learning_rate": 5.9523175180924785e-05, "loss": 0.4864225387573242, "step": 363670 }, { "epoch": 2.161789444276025, "grad_norm": 1.5276110172271729, "learning_rate": 5.9518021721849615e-05, "loss": 0.46485462188720705, "step": 363680 }, { "epoch": 2.1618488863526935, "grad_norm": 1.319382905960083, "learning_rate": 5.951286850426372e-05, "loss": 0.5056298255920411, "step": 363690 }, { "epoch": 2.161908328429362, "grad_norm": 0.9189172983169556, "learning_rate": 5.950771552819174e-05, "loss": 0.47919530868530275, "step": 363700 }, { "epoch": 2.1619677705060303, "grad_norm": 1.4092364311218262, "learning_rate": 5.950256279365838e-05, "loss": 0.4973318099975586, "step": 363710 }, { "epoch": 2.1620272125826987, "grad_norm": 1.3517972230911255, "learning_rate": 5.949741030068824e-05, "loss": 0.4999823570251465, "step": 363720 }, { "epoch": 2.162086654659367, "grad_norm": 1.6653974056243896, "learning_rate": 5.9492258049305996e-05, "loss": 0.5526967525482178, "step": 363730 }, { "epoch": 2.1621460967360355, "grad_norm": 1.2919307947158813, "learning_rate": 5.948710603953629e-05, "loss": 0.5036710739135742, "step": 363740 }, { "epoch": 2.162205538812704, "grad_norm": 1.450340747833252, "learning_rate": 5.948195427140375e-05, "loss": 0.5092478275299073, "step": 363750 }, { "epoch": 2.1622649808893724, "grad_norm": 1.0771746635437012, "learning_rate": 5.9476802744933004e-05, "loss": 0.5121724605560303, "step": 363760 }, { "epoch": 2.1623244229660408, "grad_norm": 1.3631396293640137, "learning_rate": 5.947165146014876e-05, "loss": 0.4961713790893555, "step": 363770 }, { "epoch": 2.162383865042709, "grad_norm": 1.1088029146194458, "learning_rate": 5.946650041707562e-05, "loss": 0.4526475429534912, "step": 363780 }, { "epoch": 2.1624433071193776, "grad_norm": 1.1845401525497437, "learning_rate": 5.9461349615738214e-05, "loss": 0.5336448669433593, "step": 363790 }, { "epoch": 2.162502749196046, "grad_norm": 1.2675868272781372, "learning_rate": 5.945619905616121e-05, "loss": 0.4821339130401611, "step": 363800 }, { "epoch": 2.1625621912727144, "grad_norm": 1.0673540830612183, "learning_rate": 5.945104873836924e-05, "loss": 0.500285530090332, "step": 363810 }, { "epoch": 2.162621633349383, "grad_norm": 1.270734429359436, "learning_rate": 5.9445898662386914e-05, "loss": 0.4821974754333496, "step": 363820 }, { "epoch": 2.1626810754260513, "grad_norm": 1.7124727964401245, "learning_rate": 5.944074882823886e-05, "loss": 0.4361717224121094, "step": 363830 }, { "epoch": 2.1627405175027197, "grad_norm": 1.1884788274765015, "learning_rate": 5.943559923594978e-05, "loss": 0.49699716567993163, "step": 363840 }, { "epoch": 2.162799959579388, "grad_norm": 1.5390843152999878, "learning_rate": 5.943044988554427e-05, "loss": 0.477753210067749, "step": 363850 }, { "epoch": 2.162859401656056, "grad_norm": 1.2141021490097046, "learning_rate": 5.9425300777046947e-05, "loss": 0.4872593879699707, "step": 363860 }, { "epoch": 2.1629188437327245, "grad_norm": 1.5589929819107056, "learning_rate": 5.942015191048247e-05, "loss": 0.4633979797363281, "step": 363870 }, { "epoch": 2.162978285809393, "grad_norm": 1.9755970239639282, "learning_rate": 5.941500328587545e-05, "loss": 0.5548659324645996, "step": 363880 }, { "epoch": 2.1630377278860613, "grad_norm": 1.3281116485595703, "learning_rate": 5.9409854903250486e-05, "loss": 0.5232194900512696, "step": 363890 }, { "epoch": 2.1630971699627297, "grad_norm": 1.1903631687164307, "learning_rate": 5.940470676263228e-05, "loss": 0.5001684188842773, "step": 363900 }, { "epoch": 2.163156612039398, "grad_norm": 1.417398452758789, "learning_rate": 5.939955886404543e-05, "loss": 0.5521991729736329, "step": 363910 }, { "epoch": 2.1632160541160665, "grad_norm": 1.2128239870071411, "learning_rate": 5.9394411207514546e-05, "loss": 0.44802045822143555, "step": 363920 }, { "epoch": 2.163275496192735, "grad_norm": 1.304818868637085, "learning_rate": 5.9389263793064266e-05, "loss": 0.5002768039703369, "step": 363930 }, { "epoch": 2.1633349382694034, "grad_norm": 1.7990390062332153, "learning_rate": 5.938411662071921e-05, "loss": 0.5079349517822266, "step": 363940 }, { "epoch": 2.163394380346072, "grad_norm": 1.3591541051864624, "learning_rate": 5.937896969050398e-05, "loss": 0.5034132480621338, "step": 363950 }, { "epoch": 2.16345382242274, "grad_norm": 1.3517104387283325, "learning_rate": 5.937382300244321e-05, "loss": 0.5127989292144776, "step": 363960 }, { "epoch": 2.1635132644994086, "grad_norm": 1.4559928178787231, "learning_rate": 5.9368676556561545e-05, "loss": 0.5069562911987304, "step": 363970 }, { "epoch": 2.163572706576077, "grad_norm": 1.4442265033721924, "learning_rate": 5.936353035288362e-05, "loss": 0.4729135513305664, "step": 363980 }, { "epoch": 2.1636321486527454, "grad_norm": 1.0068320035934448, "learning_rate": 5.935838439143395e-05, "loss": 0.4347567558288574, "step": 363990 }, { "epoch": 2.163691590729414, "grad_norm": 1.650381326675415, "learning_rate": 5.9353238672237246e-05, "loss": 0.504222297668457, "step": 364000 }, { "epoch": 2.1637510328060823, "grad_norm": 1.2129523754119873, "learning_rate": 5.934809319531811e-05, "loss": 0.46727657318115234, "step": 364010 }, { "epoch": 2.1638104748827507, "grad_norm": 1.5283726453781128, "learning_rate": 5.93429479607011e-05, "loss": 0.5371753692626953, "step": 364020 }, { "epoch": 2.1638699169594187, "grad_norm": 1.6214611530303955, "learning_rate": 5.933780296841092e-05, "loss": 0.5458698272705078, "step": 364030 }, { "epoch": 2.1639293590360875, "grad_norm": 1.161733865737915, "learning_rate": 5.933265821847214e-05, "loss": 0.43190417289733884, "step": 364040 }, { "epoch": 2.1639888011127555, "grad_norm": 1.0705314874649048, "learning_rate": 5.9327513710909345e-05, "loss": 0.544291877746582, "step": 364050 }, { "epoch": 2.164048243189424, "grad_norm": 1.6185044050216675, "learning_rate": 5.932236944574714e-05, "loss": 0.48049287796020507, "step": 364060 }, { "epoch": 2.1641076852660923, "grad_norm": 1.5750724077224731, "learning_rate": 5.931722542301018e-05, "loss": 0.5128027439117432, "step": 364070 }, { "epoch": 2.1641671273427607, "grad_norm": 1.315268635749817, "learning_rate": 5.931208164272306e-05, "loss": 0.5272043704986572, "step": 364080 }, { "epoch": 2.164226569419429, "grad_norm": 1.2092320919036865, "learning_rate": 5.930693810491034e-05, "loss": 0.5295625686645508, "step": 364090 }, { "epoch": 2.1642860114960976, "grad_norm": 1.4858598709106445, "learning_rate": 5.930179480959672e-05, "loss": 0.5164286613464355, "step": 364100 }, { "epoch": 2.164345453572766, "grad_norm": 1.5782803297042847, "learning_rate": 5.9296651756806724e-05, "loss": 0.5129041194915771, "step": 364110 }, { "epoch": 2.1644048956494344, "grad_norm": 1.062375545501709, "learning_rate": 5.9291508946564924e-05, "loss": 0.46341633796691895, "step": 364120 }, { "epoch": 2.164464337726103, "grad_norm": 1.2292999029159546, "learning_rate": 5.928636637889602e-05, "loss": 0.4686861038208008, "step": 364130 }, { "epoch": 2.164523779802771, "grad_norm": 1.419006586074829, "learning_rate": 5.928122405382457e-05, "loss": 0.4701695442199707, "step": 364140 }, { "epoch": 2.1645832218794396, "grad_norm": 1.359086275100708, "learning_rate": 5.927608197137513e-05, "loss": 0.5324189186096191, "step": 364150 }, { "epoch": 2.164642663956108, "grad_norm": 1.151175618171692, "learning_rate": 5.9270940131572404e-05, "loss": 0.4818690299987793, "step": 364160 }, { "epoch": 2.1647021060327765, "grad_norm": 1.2953821420669556, "learning_rate": 5.92657985344409e-05, "loss": 0.49546194076538086, "step": 364170 }, { "epoch": 2.164761548109445, "grad_norm": 1.2632408142089844, "learning_rate": 5.926065718000522e-05, "loss": 0.49220733642578124, "step": 364180 }, { "epoch": 2.1648209901861133, "grad_norm": 1.5870447158813477, "learning_rate": 5.9255516068289943e-05, "loss": 0.5149277687072754, "step": 364190 }, { "epoch": 2.1648804322627817, "grad_norm": 0.9979559779167175, "learning_rate": 5.925037519931973e-05, "loss": 0.4917912483215332, "step": 364200 }, { "epoch": 2.16493987433945, "grad_norm": 1.280859351158142, "learning_rate": 5.924523457311915e-05, "loss": 0.49129109382629393, "step": 364210 }, { "epoch": 2.164999316416118, "grad_norm": 1.487991452217102, "learning_rate": 5.924009418971276e-05, "loss": 0.4571648597717285, "step": 364220 }, { "epoch": 2.1650587584927865, "grad_norm": 1.4002021551132202, "learning_rate": 5.923495404912518e-05, "loss": 0.4817215919494629, "step": 364230 }, { "epoch": 2.165118200569455, "grad_norm": 1.1734603643417358, "learning_rate": 5.922981415138098e-05, "loss": 0.5227523803710937, "step": 364240 }, { "epoch": 2.1651776426461233, "grad_norm": 1.426970362663269, "learning_rate": 5.922467449650473e-05, "loss": 0.5120750427246094, "step": 364250 }, { "epoch": 2.1652370847227917, "grad_norm": 1.386175513267517, "learning_rate": 5.921953508452108e-05, "loss": 0.49936800003051757, "step": 364260 }, { "epoch": 2.16529652679946, "grad_norm": 1.466475486755371, "learning_rate": 5.921439591545458e-05, "loss": 0.5136741161346435, "step": 364270 }, { "epoch": 2.1653559688761286, "grad_norm": 1.6656513214111328, "learning_rate": 5.920925698932982e-05, "loss": 0.5181518077850342, "step": 364280 }, { "epoch": 2.165415410952797, "grad_norm": 1.5184552669525146, "learning_rate": 5.9204118306171355e-05, "loss": 0.5019277572631836, "step": 364290 }, { "epoch": 2.1654748530294654, "grad_norm": 1.5920742750167847, "learning_rate": 5.91989798660038e-05, "loss": 0.5132902145385743, "step": 364300 }, { "epoch": 2.165534295106134, "grad_norm": 1.2527103424072266, "learning_rate": 5.919384166885172e-05, "loss": 0.4712215423583984, "step": 364310 }, { "epoch": 2.1655937371828022, "grad_norm": 1.326709508895874, "learning_rate": 5.918870371473967e-05, "loss": 0.5182413578033447, "step": 364320 }, { "epoch": 2.1656531792594707, "grad_norm": 1.4974830150604248, "learning_rate": 5.918356600369229e-05, "loss": 0.5149792671203614, "step": 364330 }, { "epoch": 2.165712621336139, "grad_norm": 1.3401100635528564, "learning_rate": 5.917842853573412e-05, "loss": 0.4927212715148926, "step": 364340 }, { "epoch": 2.1657720634128075, "grad_norm": 1.653908371925354, "learning_rate": 5.9173291310889735e-05, "loss": 0.5272449493408203, "step": 364350 }, { "epoch": 2.165831505489476, "grad_norm": 1.461586594581604, "learning_rate": 5.9168154329183723e-05, "loss": 0.4632361888885498, "step": 364360 }, { "epoch": 2.1658909475661443, "grad_norm": 1.4979910850524902, "learning_rate": 5.9163017590640644e-05, "loss": 0.5229968070983887, "step": 364370 }, { "epoch": 2.1659503896428127, "grad_norm": 1.3639609813690186, "learning_rate": 5.915788109528504e-05, "loss": 0.4721003532409668, "step": 364380 }, { "epoch": 2.166009831719481, "grad_norm": 1.5747179985046387, "learning_rate": 5.915274484314155e-05, "loss": 0.5166630268096923, "step": 364390 }, { "epoch": 2.1660692737961496, "grad_norm": 1.121509075164795, "learning_rate": 5.914760883423471e-05, "loss": 0.47655296325683594, "step": 364400 }, { "epoch": 2.1661287158728175, "grad_norm": 1.5179790258407593, "learning_rate": 5.914247306858911e-05, "loss": 0.4944146156311035, "step": 364410 }, { "epoch": 2.166188157949486, "grad_norm": 1.4857852458953857, "learning_rate": 5.9137337546229276e-05, "loss": 0.5619626998901367, "step": 364420 }, { "epoch": 2.1662476000261544, "grad_norm": 1.468148946762085, "learning_rate": 5.9132202267179814e-05, "loss": 0.5207592010498047, "step": 364430 }, { "epoch": 2.1663070421028228, "grad_norm": 1.5369174480438232, "learning_rate": 5.912706723146526e-05, "loss": 0.5256757736206055, "step": 364440 }, { "epoch": 2.166366484179491, "grad_norm": 1.2297512292861938, "learning_rate": 5.912193243911015e-05, "loss": 0.5216394424438476, "step": 364450 }, { "epoch": 2.1664259262561596, "grad_norm": 1.1573580503463745, "learning_rate": 5.911679789013913e-05, "loss": 0.5005358695983887, "step": 364460 }, { "epoch": 2.166485368332828, "grad_norm": 1.4593392610549927, "learning_rate": 5.9111663584576737e-05, "loss": 0.5438315391540527, "step": 364470 }, { "epoch": 2.1665448104094964, "grad_norm": 1.3415923118591309, "learning_rate": 5.910652952244748e-05, "loss": 0.5217350959777832, "step": 364480 }, { "epoch": 2.166604252486165, "grad_norm": 1.1792383193969727, "learning_rate": 5.910139570377599e-05, "loss": 0.49523158073425294, "step": 364490 }, { "epoch": 2.1666636945628333, "grad_norm": 1.2301265001296997, "learning_rate": 5.9096262128586765e-05, "loss": 0.5127016067504883, "step": 364500 }, { "epoch": 2.1667231366395017, "grad_norm": 1.1841620206832886, "learning_rate": 5.909112879690437e-05, "loss": 0.5003359317779541, "step": 364510 }, { "epoch": 2.16678257871617, "grad_norm": 1.4051799774169922, "learning_rate": 5.908599570875339e-05, "loss": 0.550262451171875, "step": 364520 }, { "epoch": 2.1668420207928385, "grad_norm": 1.187525987625122, "learning_rate": 5.908086286415839e-05, "loss": 0.5164802551269532, "step": 364530 }, { "epoch": 2.166901462869507, "grad_norm": 1.2852729558944702, "learning_rate": 5.907573026314393e-05, "loss": 0.46137118339538574, "step": 364540 }, { "epoch": 2.1669609049461753, "grad_norm": 1.3734638690948486, "learning_rate": 5.9070597905734446e-05, "loss": 0.5008400917053223, "step": 364550 }, { "epoch": 2.1670203470228437, "grad_norm": 1.3978172540664673, "learning_rate": 5.906546579195462e-05, "loss": 0.5469471931457519, "step": 364560 }, { "epoch": 2.167079789099512, "grad_norm": 1.1943384408950806, "learning_rate": 5.906033392182897e-05, "loss": 0.4906017303466797, "step": 364570 }, { "epoch": 2.1671392311761806, "grad_norm": 1.484432339668274, "learning_rate": 5.9055202295382014e-05, "loss": 0.4921278476715088, "step": 364580 }, { "epoch": 2.167198673252849, "grad_norm": 1.445090889930725, "learning_rate": 5.905007091263837e-05, "loss": 0.5223306655883789, "step": 364590 }, { "epoch": 2.167258115329517, "grad_norm": 1.3466928005218506, "learning_rate": 5.904493977362251e-05, "loss": 0.5623437881469726, "step": 364600 }, { "epoch": 2.1673175574061854, "grad_norm": 1.3816405534744263, "learning_rate": 5.903980887835896e-05, "loss": 0.4734355449676514, "step": 364610 }, { "epoch": 2.167376999482854, "grad_norm": 1.6248730421066284, "learning_rate": 5.903467822687235e-05, "loss": 0.5713826179504394, "step": 364620 }, { "epoch": 2.167436441559522, "grad_norm": 1.1163986921310425, "learning_rate": 5.902954781918719e-05, "loss": 0.4748199462890625, "step": 364630 }, { "epoch": 2.1674958836361906, "grad_norm": 1.4199109077453613, "learning_rate": 5.9024417655328e-05, "loss": 0.5104311943054199, "step": 364640 }, { "epoch": 2.167555325712859, "grad_norm": 1.5725091695785522, "learning_rate": 5.901928773531935e-05, "loss": 0.48604135513305663, "step": 364650 }, { "epoch": 2.1676147677895274, "grad_norm": 1.1342192888259888, "learning_rate": 5.901415805918578e-05, "loss": 0.501387643814087, "step": 364660 }, { "epoch": 2.167674209866196, "grad_norm": 1.3442939519882202, "learning_rate": 5.900902862695179e-05, "loss": 0.4937619686126709, "step": 364670 }, { "epoch": 2.1677336519428643, "grad_norm": 1.2008270025253296, "learning_rate": 5.900389943864193e-05, "loss": 0.49602336883544923, "step": 364680 }, { "epoch": 2.1677930940195327, "grad_norm": 1.681907296180725, "learning_rate": 5.899877049428075e-05, "loss": 0.46725759506225584, "step": 364690 }, { "epoch": 2.167852536096201, "grad_norm": 1.362404227256775, "learning_rate": 5.899364179389282e-05, "loss": 0.4686558246612549, "step": 364700 }, { "epoch": 2.1679119781728695, "grad_norm": 1.6093508005142212, "learning_rate": 5.898851333750262e-05, "loss": 0.538824987411499, "step": 364710 }, { "epoch": 2.167971420249538, "grad_norm": 1.5095657110214233, "learning_rate": 5.898338512513472e-05, "loss": 0.4909174919128418, "step": 364720 }, { "epoch": 2.1680308623262063, "grad_norm": 1.4197094440460205, "learning_rate": 5.897825715681362e-05, "loss": 0.535545015335083, "step": 364730 }, { "epoch": 2.1680903044028748, "grad_norm": 1.8873777389526367, "learning_rate": 5.8973129432563835e-05, "loss": 0.4940845489501953, "step": 364740 }, { "epoch": 2.168149746479543, "grad_norm": 1.8175265789031982, "learning_rate": 5.896800195240995e-05, "loss": 0.5307156562805175, "step": 364750 }, { "epoch": 2.1682091885562116, "grad_norm": 1.297039270401001, "learning_rate": 5.896287471637647e-05, "loss": 0.5241022109985352, "step": 364760 }, { "epoch": 2.1682686306328796, "grad_norm": 1.218363881111145, "learning_rate": 5.895774772448791e-05, "loss": 0.490118408203125, "step": 364770 }, { "epoch": 2.1683280727095484, "grad_norm": 1.2270216941833496, "learning_rate": 5.895262097676881e-05, "loss": 0.48807077407836913, "step": 364780 }, { "epoch": 2.1683875147862164, "grad_norm": 1.4612025022506714, "learning_rate": 5.894749447324369e-05, "loss": 0.5054137229919433, "step": 364790 }, { "epoch": 2.168446956862885, "grad_norm": 1.4291081428527832, "learning_rate": 5.894236821393708e-05, "loss": 0.5058660984039307, "step": 364800 }, { "epoch": 2.168506398939553, "grad_norm": 1.2246170043945312, "learning_rate": 5.8937242198873446e-05, "loss": 0.5007564544677734, "step": 364810 }, { "epoch": 2.1685658410162216, "grad_norm": 1.2874805927276611, "learning_rate": 5.89321164280774e-05, "loss": 0.47063407897949217, "step": 364820 }, { "epoch": 2.16862528309289, "grad_norm": 1.2551586627960205, "learning_rate": 5.892699090157341e-05, "loss": 0.5112158775329589, "step": 364830 }, { "epoch": 2.1686847251695585, "grad_norm": 0.9100023508071899, "learning_rate": 5.892186561938602e-05, "loss": 0.4909069061279297, "step": 364840 }, { "epoch": 2.168744167246227, "grad_norm": 1.4898115396499634, "learning_rate": 5.8916740581539734e-05, "loss": 0.47289600372314455, "step": 364850 }, { "epoch": 2.1688036093228953, "grad_norm": 1.2027302980422974, "learning_rate": 5.891161578805905e-05, "loss": 0.5073144912719727, "step": 364860 }, { "epoch": 2.1688630513995637, "grad_norm": 1.2589702606201172, "learning_rate": 5.890649123896848e-05, "loss": 0.49538450241088866, "step": 364870 }, { "epoch": 2.168922493476232, "grad_norm": 1.207401156425476, "learning_rate": 5.890136693429258e-05, "loss": 0.4440752983093262, "step": 364880 }, { "epoch": 2.1689819355529005, "grad_norm": 1.2838865518569946, "learning_rate": 5.889624287405585e-05, "loss": 0.4884310722351074, "step": 364890 }, { "epoch": 2.169041377629569, "grad_norm": 1.2201555967330933, "learning_rate": 5.8891119058282793e-05, "loss": 0.48024463653564453, "step": 364900 }, { "epoch": 2.1691008197062374, "grad_norm": 0.9838793277740479, "learning_rate": 5.888599548699791e-05, "loss": 0.5093823432922363, "step": 364910 }, { "epoch": 2.1691602617829058, "grad_norm": 1.2964895963668823, "learning_rate": 5.888087216022573e-05, "loss": 0.4930079460144043, "step": 364920 }, { "epoch": 2.169219703859574, "grad_norm": 1.2217752933502197, "learning_rate": 5.887574907799076e-05, "loss": 0.5071684360504151, "step": 364930 }, { "epoch": 2.1692791459362426, "grad_norm": 1.4636608362197876, "learning_rate": 5.887062624031745e-05, "loss": 0.528485918045044, "step": 364940 }, { "epoch": 2.169338588012911, "grad_norm": 1.3391348123550415, "learning_rate": 5.886550364723039e-05, "loss": 0.5097208023071289, "step": 364950 }, { "epoch": 2.169398030089579, "grad_norm": 0.939213216304779, "learning_rate": 5.886038129875406e-05, "loss": 0.5012840747833252, "step": 364960 }, { "epoch": 2.1694574721662474, "grad_norm": 1.5974957942962646, "learning_rate": 5.885525919491295e-05, "loss": 0.4646891117095947, "step": 364970 }, { "epoch": 2.169516914242916, "grad_norm": 1.7488127946853638, "learning_rate": 5.885013733573156e-05, "loss": 0.5443187236785889, "step": 364980 }, { "epoch": 2.1695763563195842, "grad_norm": 0.9843550324440002, "learning_rate": 5.8845015721234397e-05, "loss": 0.49152522087097167, "step": 364990 }, { "epoch": 2.1696357983962526, "grad_norm": 1.2151672840118408, "learning_rate": 5.883989435144593e-05, "loss": 0.5092765331268311, "step": 365000 }, { "epoch": 2.169695240472921, "grad_norm": 1.4778673648834229, "learning_rate": 5.8834773226390725e-05, "loss": 0.5018840789794922, "step": 365010 }, { "epoch": 2.1697546825495895, "grad_norm": 1.0485552549362183, "learning_rate": 5.8829652346093236e-05, "loss": 0.5134527206420898, "step": 365020 }, { "epoch": 2.169814124626258, "grad_norm": 1.1418380737304688, "learning_rate": 5.8824531710578e-05, "loss": 0.5462329387664795, "step": 365030 }, { "epoch": 2.1698735667029263, "grad_norm": 1.2156345844268799, "learning_rate": 5.881941131986942e-05, "loss": 0.4845468521118164, "step": 365040 }, { "epoch": 2.1699330087795947, "grad_norm": 1.2889842987060547, "learning_rate": 5.8814291173992086e-05, "loss": 0.48889837265014646, "step": 365050 }, { "epoch": 2.169992450856263, "grad_norm": 1.4966633319854736, "learning_rate": 5.8809171272970455e-05, "loss": 0.46060881614685056, "step": 365060 }, { "epoch": 2.1700518929329315, "grad_norm": 1.2473113536834717, "learning_rate": 5.880405161682899e-05, "loss": 0.5292962074279786, "step": 365070 }, { "epoch": 2.1701113350096, "grad_norm": 1.2117611169815063, "learning_rate": 5.879893220559223e-05, "loss": 0.5112442016601563, "step": 365080 }, { "epoch": 2.1701707770862684, "grad_norm": 1.1245054006576538, "learning_rate": 5.87938130392847e-05, "loss": 0.4412276268005371, "step": 365090 }, { "epoch": 2.170230219162937, "grad_norm": 1.3168623447418213, "learning_rate": 5.8788694117930756e-05, "loss": 0.46047205924987794, "step": 365100 }, { "epoch": 2.170289661239605, "grad_norm": 1.2800558805465698, "learning_rate": 5.878357544155499e-05, "loss": 0.49417948722839355, "step": 365110 }, { "epoch": 2.1703491033162736, "grad_norm": 0.963485836982727, "learning_rate": 5.877845701018185e-05, "loss": 0.4765613079071045, "step": 365120 }, { "epoch": 2.170408545392942, "grad_norm": 1.1687053442001343, "learning_rate": 5.877333882383586e-05, "loss": 0.5169648647308349, "step": 365130 }, { "epoch": 2.1704679874696104, "grad_norm": 1.5111451148986816, "learning_rate": 5.8768220882541435e-05, "loss": 0.4811086654663086, "step": 365140 }, { "epoch": 2.1705274295462784, "grad_norm": 1.3200390338897705, "learning_rate": 5.876310318632317e-05, "loss": 0.5006994724273681, "step": 365150 }, { "epoch": 2.170586871622947, "grad_norm": 1.5880988836288452, "learning_rate": 5.875798573520542e-05, "loss": 0.47733421325683595, "step": 365160 }, { "epoch": 2.1706463136996152, "grad_norm": 1.5003442764282227, "learning_rate": 5.8752868529212704e-05, "loss": 0.5341193199157714, "step": 365170 }, { "epoch": 2.1707057557762837, "grad_norm": 1.516180157661438, "learning_rate": 5.874775156836955e-05, "loss": 0.5212785243988037, "step": 365180 }, { "epoch": 2.170765197852952, "grad_norm": 1.439281702041626, "learning_rate": 5.874263485270039e-05, "loss": 0.4825717926025391, "step": 365190 }, { "epoch": 2.1708246399296205, "grad_norm": 1.395655870437622, "learning_rate": 5.8737518382229696e-05, "loss": 0.46924076080322263, "step": 365200 }, { "epoch": 2.170884082006289, "grad_norm": 1.7032599449157715, "learning_rate": 5.873240215698201e-05, "loss": 0.49396162033081054, "step": 365210 }, { "epoch": 2.1709435240829573, "grad_norm": 1.4883980751037598, "learning_rate": 5.872728617698175e-05, "loss": 0.48664054870605467, "step": 365220 }, { "epoch": 2.1710029661596257, "grad_norm": 1.157373070716858, "learning_rate": 5.872217044225335e-05, "loss": 0.5159877300262451, "step": 365230 }, { "epoch": 2.171062408236294, "grad_norm": 1.066037654876709, "learning_rate": 5.871705495282136e-05, "loss": 0.47933182716369627, "step": 365240 }, { "epoch": 2.1711218503129626, "grad_norm": 1.286062240600586, "learning_rate": 5.871193970871022e-05, "loss": 0.48690147399902345, "step": 365250 }, { "epoch": 2.171181292389631, "grad_norm": 1.5119677782058716, "learning_rate": 5.8706824709944396e-05, "loss": 0.5015585899353028, "step": 365260 }, { "epoch": 2.1712407344662994, "grad_norm": 1.3536406755447388, "learning_rate": 5.870170995654837e-05, "loss": 0.48158464431762693, "step": 365270 }, { "epoch": 2.171300176542968, "grad_norm": 1.407891035079956, "learning_rate": 5.86965954485466e-05, "loss": 0.47412929534912107, "step": 365280 }, { "epoch": 2.1713596186196362, "grad_norm": 1.6069988012313843, "learning_rate": 5.8691481185963536e-05, "loss": 0.5226762771606446, "step": 365290 }, { "epoch": 2.1714190606963046, "grad_norm": 1.7809685468673706, "learning_rate": 5.868636716882363e-05, "loss": 0.5541683197021484, "step": 365300 }, { "epoch": 2.171478502772973, "grad_norm": 1.4763416051864624, "learning_rate": 5.8681253397151416e-05, "loss": 0.5186904907226563, "step": 365310 }, { "epoch": 2.1715379448496415, "grad_norm": 1.2850451469421387, "learning_rate": 5.867613987097132e-05, "loss": 0.47124929428100587, "step": 365320 }, { "epoch": 2.17159738692631, "grad_norm": 1.2199664115905762, "learning_rate": 5.867102659030778e-05, "loss": 0.5011665344238281, "step": 365330 }, { "epoch": 2.171656829002978, "grad_norm": 1.6905320882797241, "learning_rate": 5.8665913555185285e-05, "loss": 0.5415932655334472, "step": 365340 }, { "epoch": 2.1717162710796463, "grad_norm": 1.1385605335235596, "learning_rate": 5.8660800765628276e-05, "loss": 0.5122742652893066, "step": 365350 }, { "epoch": 2.1717757131563147, "grad_norm": 1.3071486949920654, "learning_rate": 5.8655688221661186e-05, "loss": 0.5032920837402344, "step": 365360 }, { "epoch": 2.171835155232983, "grad_norm": 1.630208134651184, "learning_rate": 5.865057592330854e-05, "loss": 0.5591535568237305, "step": 365370 }, { "epoch": 2.1718945973096515, "grad_norm": 1.0704243183135986, "learning_rate": 5.8645463870594766e-05, "loss": 0.49188756942749023, "step": 365380 }, { "epoch": 2.17195403938632, "grad_norm": 1.1698235273361206, "learning_rate": 5.86403520635443e-05, "loss": 0.44922266006469724, "step": 365390 }, { "epoch": 2.1720134814629883, "grad_norm": 1.7860101461410522, "learning_rate": 5.863524050218161e-05, "loss": 0.5114878177642822, "step": 365400 }, { "epoch": 2.1720729235396568, "grad_norm": 2.5009751319885254, "learning_rate": 5.863012918653115e-05, "loss": 0.5017683029174804, "step": 365410 }, { "epoch": 2.172132365616325, "grad_norm": 1.2258548736572266, "learning_rate": 5.862501811661734e-05, "loss": 0.49406919479370115, "step": 365420 }, { "epoch": 2.1721918076929936, "grad_norm": 1.6709905862808228, "learning_rate": 5.861990729246464e-05, "loss": 0.5634188652038574, "step": 365430 }, { "epoch": 2.172251249769662, "grad_norm": 1.1265802383422852, "learning_rate": 5.861479671409754e-05, "loss": 0.4873805046081543, "step": 365440 }, { "epoch": 2.1723106918463304, "grad_norm": 1.3824604749679565, "learning_rate": 5.860968638154045e-05, "loss": 0.5047817230224609, "step": 365450 }, { "epoch": 2.172370133922999, "grad_norm": 1.554726004600525, "learning_rate": 5.8604576294817846e-05, "loss": 0.4844955921173096, "step": 365460 }, { "epoch": 2.1724295759996672, "grad_norm": 1.2524676322937012, "learning_rate": 5.8599466453954156e-05, "loss": 0.49949893951416013, "step": 365470 }, { "epoch": 2.1724890180763357, "grad_norm": 1.53901207447052, "learning_rate": 5.8594356858973797e-05, "loss": 0.5806726455688477, "step": 365480 }, { "epoch": 2.172548460153004, "grad_norm": 1.6123872995376587, "learning_rate": 5.8589247509901244e-05, "loss": 0.4857933044433594, "step": 365490 }, { "epoch": 2.1726079022296725, "grad_norm": 1.5858098268508911, "learning_rate": 5.85841384067609e-05, "loss": 0.4865240573883057, "step": 365500 }, { "epoch": 2.1726673443063405, "grad_norm": 1.293344497680664, "learning_rate": 5.857902954957727e-05, "loss": 0.5100708484649659, "step": 365510 }, { "epoch": 2.1727267863830093, "grad_norm": 1.3742324113845825, "learning_rate": 5.857392093837479e-05, "loss": 0.46520099639892576, "step": 365520 }, { "epoch": 2.1727862284596773, "grad_norm": 1.3652502298355103, "learning_rate": 5.8568812573177804e-05, "loss": 0.47326269149780276, "step": 365530 }, { "epoch": 2.1728456705363457, "grad_norm": 1.3491216897964478, "learning_rate": 5.8563704454010826e-05, "loss": 0.4886167526245117, "step": 365540 }, { "epoch": 2.172905112613014, "grad_norm": 1.433834433555603, "learning_rate": 5.8558596580898286e-05, "loss": 0.5511364459991455, "step": 365550 }, { "epoch": 2.1729645546896825, "grad_norm": 1.0919514894485474, "learning_rate": 5.8553488953864586e-05, "loss": 0.4844337463378906, "step": 365560 }, { "epoch": 2.173023996766351, "grad_norm": 1.2690249681472778, "learning_rate": 5.854838157293421e-05, "loss": 0.43085432052612305, "step": 365570 }, { "epoch": 2.1730834388430194, "grad_norm": 1.1517599821090698, "learning_rate": 5.854327443813158e-05, "loss": 0.45827493667602537, "step": 365580 }, { "epoch": 2.1731428809196878, "grad_norm": 1.3584673404693604, "learning_rate": 5.853816754948105e-05, "loss": 0.4558448791503906, "step": 365590 }, { "epoch": 2.173202322996356, "grad_norm": 1.3601906299591064, "learning_rate": 5.853306090700716e-05, "loss": 0.5111645698547364, "step": 365600 }, { "epoch": 2.1732617650730246, "grad_norm": 1.1128257513046265, "learning_rate": 5.852795451073427e-05, "loss": 0.45250511169433594, "step": 365610 }, { "epoch": 2.173321207149693, "grad_norm": 1.3939893245697021, "learning_rate": 5.852284836068682e-05, "loss": 0.48110208511352537, "step": 365620 }, { "epoch": 2.1733806492263614, "grad_norm": 1.5138298273086548, "learning_rate": 5.851774245688921e-05, "loss": 0.49825034141540525, "step": 365630 }, { "epoch": 2.17344009130303, "grad_norm": 1.1299527883529663, "learning_rate": 5.851263679936598e-05, "loss": 0.47232847213745116, "step": 365640 }, { "epoch": 2.1734995333796983, "grad_norm": 1.1527799367904663, "learning_rate": 5.850753138814142e-05, "loss": 0.4913946151733398, "step": 365650 }, { "epoch": 2.1735589754563667, "grad_norm": 1.6458938121795654, "learning_rate": 5.850242622323998e-05, "loss": 0.4950282096862793, "step": 365660 }, { "epoch": 2.173618417533035, "grad_norm": 1.368607759475708, "learning_rate": 5.849732130468612e-05, "loss": 0.4974095344543457, "step": 365670 }, { "epoch": 2.1736778596097035, "grad_norm": 1.3055524826049805, "learning_rate": 5.849221663250425e-05, "loss": 0.4963409423828125, "step": 365680 }, { "epoch": 2.173737301686372, "grad_norm": 1.7265509366989136, "learning_rate": 5.848711220671874e-05, "loss": 0.5040628433227539, "step": 365690 }, { "epoch": 2.17379674376304, "grad_norm": 1.0322409868240356, "learning_rate": 5.848200802735414e-05, "loss": 0.5140727043151856, "step": 365700 }, { "epoch": 2.1738561858397083, "grad_norm": 1.4943969249725342, "learning_rate": 5.8476904094434734e-05, "loss": 0.5192195892333984, "step": 365710 }, { "epoch": 2.1739156279163767, "grad_norm": 1.515329122543335, "learning_rate": 5.8471800407984944e-05, "loss": 0.5439239501953125, "step": 365720 }, { "epoch": 2.173975069993045, "grad_norm": 1.1937791109085083, "learning_rate": 5.8466696968029255e-05, "loss": 0.5023032188415527, "step": 365730 }, { "epoch": 2.1740345120697135, "grad_norm": 1.3482006788253784, "learning_rate": 5.846159377459205e-05, "loss": 0.49735469818115235, "step": 365740 }, { "epoch": 2.174093954146382, "grad_norm": 1.2476933002471924, "learning_rate": 5.845649082769773e-05, "loss": 0.49300575256347656, "step": 365750 }, { "epoch": 2.1741533962230504, "grad_norm": 1.3048150539398193, "learning_rate": 5.8451388127370724e-05, "loss": 0.5191424369812012, "step": 365760 }, { "epoch": 2.174212838299719, "grad_norm": 1.3103057146072388, "learning_rate": 5.844628567363541e-05, "loss": 0.45787844657897947, "step": 365770 }, { "epoch": 2.174272280376387, "grad_norm": 1.327507734298706, "learning_rate": 5.8441183466516256e-05, "loss": 0.5084069252014161, "step": 365780 }, { "epoch": 2.1743317224530556, "grad_norm": 1.26099693775177, "learning_rate": 5.843608150603756e-05, "loss": 0.5532350540161133, "step": 365790 }, { "epoch": 2.174391164529724, "grad_norm": 1.5928934812545776, "learning_rate": 5.843097979222385e-05, "loss": 0.5245804786682129, "step": 365800 }, { "epoch": 2.1744506066063924, "grad_norm": 1.3962123394012451, "learning_rate": 5.842587832509947e-05, "loss": 0.5333844184875488, "step": 365810 }, { "epoch": 2.174510048683061, "grad_norm": 1.0955781936645508, "learning_rate": 5.842077710468885e-05, "loss": 0.43925819396972654, "step": 365820 }, { "epoch": 2.1745694907597293, "grad_norm": 1.2949581146240234, "learning_rate": 5.841567613101637e-05, "loss": 0.5454325199127197, "step": 365830 }, { "epoch": 2.1746289328363977, "grad_norm": 0.9408130645751953, "learning_rate": 5.841057540410644e-05, "loss": 0.44869794845581057, "step": 365840 }, { "epoch": 2.174688374913066, "grad_norm": 1.5420336723327637, "learning_rate": 5.840547492398341e-05, "loss": 0.4486259460449219, "step": 365850 }, { "epoch": 2.1747478169897345, "grad_norm": 1.4591574668884277, "learning_rate": 5.840037469067177e-05, "loss": 0.5240722179412842, "step": 365860 }, { "epoch": 2.174807259066403, "grad_norm": 1.6169897317886353, "learning_rate": 5.8395274704195866e-05, "loss": 0.5451737403869629, "step": 365870 }, { "epoch": 2.1748667011430713, "grad_norm": 1.5482665300369263, "learning_rate": 5.839017496458011e-05, "loss": 0.4798402786254883, "step": 365880 }, { "epoch": 2.1749261432197393, "grad_norm": 1.2552579641342163, "learning_rate": 5.838507547184888e-05, "loss": 0.5548467636108398, "step": 365890 }, { "epoch": 2.1749855852964077, "grad_norm": 1.5451560020446777, "learning_rate": 5.83799762260266e-05, "loss": 0.4542102813720703, "step": 365900 }, { "epoch": 2.175045027373076, "grad_norm": 1.3560971021652222, "learning_rate": 5.837487722713764e-05, "loss": 0.4950854301452637, "step": 365910 }, { "epoch": 2.1751044694497446, "grad_norm": 1.3419188261032104, "learning_rate": 5.836977847520635e-05, "loss": 0.45839848518371584, "step": 365920 }, { "epoch": 2.175163911526413, "grad_norm": 1.0126591920852661, "learning_rate": 5.836467997025721e-05, "loss": 0.5220132350921631, "step": 365930 }, { "epoch": 2.1752233536030814, "grad_norm": 1.4795050621032715, "learning_rate": 5.835958171231456e-05, "loss": 0.49492769241333007, "step": 365940 }, { "epoch": 2.17528279567975, "grad_norm": 1.7657722234725952, "learning_rate": 5.8354483701402795e-05, "loss": 0.47298831939697267, "step": 365950 }, { "epoch": 2.175342237756418, "grad_norm": 1.249157190322876, "learning_rate": 5.834938593754632e-05, "loss": 0.5285763740539551, "step": 365960 }, { "epoch": 2.1754016798330866, "grad_norm": 1.3013670444488525, "learning_rate": 5.834428842076949e-05, "loss": 0.49045743942260744, "step": 365970 }, { "epoch": 2.175461121909755, "grad_norm": 1.946320652961731, "learning_rate": 5.833919115109669e-05, "loss": 0.48661031723022463, "step": 365980 }, { "epoch": 2.1755205639864235, "grad_norm": 1.1949596405029297, "learning_rate": 5.8334094128552305e-05, "loss": 0.5013359069824219, "step": 365990 }, { "epoch": 2.175580006063092, "grad_norm": 1.4961051940917969, "learning_rate": 5.8328997353160753e-05, "loss": 0.4798985481262207, "step": 366000 }, { "epoch": 2.1756394481397603, "grad_norm": 1.1961357593536377, "learning_rate": 5.8323900824946433e-05, "loss": 0.49353318214416503, "step": 366010 }, { "epoch": 2.1756988902164287, "grad_norm": 1.22756826877594, "learning_rate": 5.831880454393359e-05, "loss": 0.4829885482788086, "step": 366020 }, { "epoch": 2.175758332293097, "grad_norm": 2.054016351699829, "learning_rate": 5.831370851014675e-05, "loss": 0.517619514465332, "step": 366030 }, { "epoch": 2.1758177743697655, "grad_norm": 1.3236491680145264, "learning_rate": 5.830861272361024e-05, "loss": 0.527737808227539, "step": 366040 }, { "epoch": 2.175877216446434, "grad_norm": 1.3652702569961548, "learning_rate": 5.830351718434839e-05, "loss": 0.5192971229553223, "step": 366050 }, { "epoch": 2.1759366585231024, "grad_norm": 1.4452881813049316, "learning_rate": 5.829842189238567e-05, "loss": 0.5549384593963623, "step": 366060 }, { "epoch": 2.1759961005997708, "grad_norm": 1.644267201423645, "learning_rate": 5.8293326847746424e-05, "loss": 0.5101494789123535, "step": 366070 }, { "epoch": 2.1760555426764387, "grad_norm": 1.5194236040115356, "learning_rate": 5.828823205045494e-05, "loss": 0.5072246074676514, "step": 366080 }, { "epoch": 2.176114984753107, "grad_norm": 1.3774749040603638, "learning_rate": 5.828313750053569e-05, "loss": 0.4894881248474121, "step": 366090 }, { "epoch": 2.1761744268297756, "grad_norm": 1.3245447874069214, "learning_rate": 5.8278043198013e-05, "loss": 0.4678779602050781, "step": 366100 }, { "epoch": 2.176233868906444, "grad_norm": 1.1358329057693481, "learning_rate": 5.8272949142911246e-05, "loss": 0.47755126953125, "step": 366110 }, { "epoch": 2.1762933109831124, "grad_norm": 1.6269656419754028, "learning_rate": 5.826785533525478e-05, "loss": 0.5118058204650879, "step": 366120 }, { "epoch": 2.176352753059781, "grad_norm": 1.3356441259384155, "learning_rate": 5.826276177506804e-05, "loss": 0.43297348022460935, "step": 366130 }, { "epoch": 2.1764121951364492, "grad_norm": 1.3046119213104248, "learning_rate": 5.8257668462375325e-05, "loss": 0.5053502559661865, "step": 366140 }, { "epoch": 2.1764716372131176, "grad_norm": 0.7975491881370544, "learning_rate": 5.825257539720097e-05, "loss": 0.5019977569580079, "step": 366150 }, { "epoch": 2.176531079289786, "grad_norm": 1.1695083379745483, "learning_rate": 5.824748257956941e-05, "loss": 0.5058037757873535, "step": 366160 }, { "epoch": 2.1765905213664545, "grad_norm": 1.1483442783355713, "learning_rate": 5.8242390009504986e-05, "loss": 0.49961042404174805, "step": 366170 }, { "epoch": 2.176649963443123, "grad_norm": 1.5491424798965454, "learning_rate": 5.823729768703203e-05, "loss": 0.5127226352691651, "step": 366180 }, { "epoch": 2.1767094055197913, "grad_norm": 1.5325034856796265, "learning_rate": 5.823220561217497e-05, "loss": 0.49248700141906737, "step": 366190 }, { "epoch": 2.1767688475964597, "grad_norm": 1.339833378791809, "learning_rate": 5.822711378495811e-05, "loss": 0.4613028526306152, "step": 366200 }, { "epoch": 2.176828289673128, "grad_norm": 1.4056533575057983, "learning_rate": 5.822202220540578e-05, "loss": 0.5056899070739747, "step": 366210 }, { "epoch": 2.1768877317497966, "grad_norm": 1.3417049646377563, "learning_rate": 5.8216930873542406e-05, "loss": 0.4997260093688965, "step": 366220 }, { "epoch": 2.176947173826465, "grad_norm": 1.4993995428085327, "learning_rate": 5.82118397893923e-05, "loss": 0.5059274196624756, "step": 366230 }, { "epoch": 2.1770066159031334, "grad_norm": 1.3423665761947632, "learning_rate": 5.820674895297984e-05, "loss": 0.4921910285949707, "step": 366240 }, { "epoch": 2.1770660579798014, "grad_norm": 1.4225993156433105, "learning_rate": 5.8201658364329356e-05, "loss": 0.4740764141082764, "step": 366250 }, { "epoch": 2.17712550005647, "grad_norm": 1.2477673292160034, "learning_rate": 5.819656802346523e-05, "loss": 0.49772071838378906, "step": 366260 }, { "epoch": 2.177184942133138, "grad_norm": 1.5912185907363892, "learning_rate": 5.819147793041178e-05, "loss": 0.49311676025390627, "step": 366270 }, { "epoch": 2.1772443842098066, "grad_norm": 1.4539318084716797, "learning_rate": 5.818638808519333e-05, "loss": 0.566248607635498, "step": 366280 }, { "epoch": 2.177303826286475, "grad_norm": 1.4919846057891846, "learning_rate": 5.8181298487834314e-05, "loss": 0.487736177444458, "step": 366290 }, { "epoch": 2.1773632683631434, "grad_norm": 1.2896982431411743, "learning_rate": 5.8176209138359015e-05, "loss": 0.4778531551361084, "step": 366300 }, { "epoch": 2.177422710439812, "grad_norm": 1.4346824884414673, "learning_rate": 5.8171120036791815e-05, "loss": 0.4993770599365234, "step": 366310 }, { "epoch": 2.1774821525164803, "grad_norm": 1.305588960647583, "learning_rate": 5.816603118315702e-05, "loss": 0.5062203407287598, "step": 366320 }, { "epoch": 2.1775415945931487, "grad_norm": 1.6050562858581543, "learning_rate": 5.8160942577479005e-05, "loss": 0.49727640151977537, "step": 366330 }, { "epoch": 2.177601036669817, "grad_norm": 1.169381856918335, "learning_rate": 5.815585421978207e-05, "loss": 0.4595067501068115, "step": 366340 }, { "epoch": 2.1776604787464855, "grad_norm": 1.0703366994857788, "learning_rate": 5.8150766110090606e-05, "loss": 0.5052632331848145, "step": 366350 }, { "epoch": 2.177719920823154, "grad_norm": 1.2073277235031128, "learning_rate": 5.814567824842894e-05, "loss": 0.4796391487121582, "step": 366360 }, { "epoch": 2.1777793628998223, "grad_norm": 1.2713524103164673, "learning_rate": 5.814059063482139e-05, "loss": 0.4773129940032959, "step": 366370 }, { "epoch": 2.1778388049764907, "grad_norm": 1.2524406909942627, "learning_rate": 5.8135503269292314e-05, "loss": 0.4894832134246826, "step": 366380 }, { "epoch": 2.177898247053159, "grad_norm": 1.3764228820800781, "learning_rate": 5.8130416151866054e-05, "loss": 0.4620372772216797, "step": 366390 }, { "epoch": 2.1779576891298276, "grad_norm": 1.239142894744873, "learning_rate": 5.812532928256691e-05, "loss": 0.5039444923400879, "step": 366400 }, { "epoch": 2.178017131206496, "grad_norm": 1.5204018354415894, "learning_rate": 5.8120242661419224e-05, "loss": 0.5351785659790039, "step": 366410 }, { "epoch": 2.1780765732831644, "grad_norm": 1.1579357385635376, "learning_rate": 5.811515628844737e-05, "loss": 0.5510354042053223, "step": 366420 }, { "epoch": 2.178136015359833, "grad_norm": 1.3374950885772705, "learning_rate": 5.811007016367565e-05, "loss": 0.5500849723815918, "step": 366430 }, { "epoch": 2.178195457436501, "grad_norm": 1.4402053356170654, "learning_rate": 5.81049842871284e-05, "loss": 0.5751014709472656, "step": 366440 }, { "epoch": 2.178254899513169, "grad_norm": 1.3810358047485352, "learning_rate": 5.8099898658829935e-05, "loss": 0.5166982650756836, "step": 366450 }, { "epoch": 2.1783143415898376, "grad_norm": 1.2987329959869385, "learning_rate": 5.8094813278804595e-05, "loss": 0.49382834434509276, "step": 366460 }, { "epoch": 2.178373783666506, "grad_norm": 1.2879937887191772, "learning_rate": 5.808972814707672e-05, "loss": 0.4206706047058105, "step": 366470 }, { "epoch": 2.1784332257431744, "grad_norm": 1.4187889099121094, "learning_rate": 5.808464326367057e-05, "loss": 0.5282878875732422, "step": 366480 }, { "epoch": 2.178492667819843, "grad_norm": 1.641139030456543, "learning_rate": 5.8079558628610564e-05, "loss": 0.5434650421142578, "step": 366490 }, { "epoch": 2.1785521098965113, "grad_norm": 1.2340441942214966, "learning_rate": 5.807447424192098e-05, "loss": 0.5234847068786621, "step": 366500 }, { "epoch": 2.1786115519731797, "grad_norm": 1.128875732421875, "learning_rate": 5.806939010362614e-05, "loss": 0.48672142028808596, "step": 366510 }, { "epoch": 2.178670994049848, "grad_norm": 1.1741282939910889, "learning_rate": 5.806430621375037e-05, "loss": 0.4580334186553955, "step": 366520 }, { "epoch": 2.1787304361265165, "grad_norm": 1.1019281148910522, "learning_rate": 5.805922257231799e-05, "loss": 0.4941575050354004, "step": 366530 }, { "epoch": 2.178789878203185, "grad_norm": 1.6142441034317017, "learning_rate": 5.8054139179353274e-05, "loss": 0.5245795249938965, "step": 366540 }, { "epoch": 2.1788493202798533, "grad_norm": 1.5620801448822021, "learning_rate": 5.804905603488062e-05, "loss": 0.5632489681243896, "step": 366550 }, { "epoch": 2.1789087623565218, "grad_norm": 1.210615873336792, "learning_rate": 5.8043973138924315e-05, "loss": 0.513760757446289, "step": 366560 }, { "epoch": 2.17896820443319, "grad_norm": 1.4808131456375122, "learning_rate": 5.803889049150863e-05, "loss": 0.49381771087646487, "step": 366570 }, { "epoch": 2.1790276465098586, "grad_norm": 1.334355115890503, "learning_rate": 5.803380809265794e-05, "loss": 0.5741866111755372, "step": 366580 }, { "epoch": 2.179087088586527, "grad_norm": 1.4036051034927368, "learning_rate": 5.802872594239651e-05, "loss": 0.5008262634277344, "step": 366590 }, { "epoch": 2.1791465306631954, "grad_norm": 1.3877543210983276, "learning_rate": 5.802364404074868e-05, "loss": 0.47469511032104494, "step": 366600 }, { "epoch": 2.179205972739864, "grad_norm": 1.479604721069336, "learning_rate": 5.801856238773873e-05, "loss": 0.49053306579589845, "step": 366610 }, { "epoch": 2.1792654148165322, "grad_norm": 1.223588466644287, "learning_rate": 5.801348098339103e-05, "loss": 0.48551340103149415, "step": 366620 }, { "epoch": 2.1793248568932, "grad_norm": 1.328141689300537, "learning_rate": 5.8008399827729835e-05, "loss": 0.4771472930908203, "step": 366630 }, { "epoch": 2.1793842989698686, "grad_norm": 1.4519338607788086, "learning_rate": 5.800331892077943e-05, "loss": 0.5191658496856689, "step": 366640 }, { "epoch": 2.179443741046537, "grad_norm": 1.0597074031829834, "learning_rate": 5.7998238262564175e-05, "loss": 0.4505454063415527, "step": 366650 }, { "epoch": 2.1795031831232055, "grad_norm": 1.3188220262527466, "learning_rate": 5.799315785310836e-05, "loss": 0.5250722408294678, "step": 366660 }, { "epoch": 2.179562625199874, "grad_norm": 1.1423325538635254, "learning_rate": 5.798807769243626e-05, "loss": 0.4396969318389893, "step": 366670 }, { "epoch": 2.1796220672765423, "grad_norm": 1.840593934059143, "learning_rate": 5.7982997780572244e-05, "loss": 0.5322851181030274, "step": 366680 }, { "epoch": 2.1796815093532107, "grad_norm": 1.335129976272583, "learning_rate": 5.797791811754054e-05, "loss": 0.4906808853149414, "step": 366690 }, { "epoch": 2.179740951429879, "grad_norm": 1.741503119468689, "learning_rate": 5.797283870336545e-05, "loss": 0.5121000289916993, "step": 366700 }, { "epoch": 2.1798003935065475, "grad_norm": 1.4060078859329224, "learning_rate": 5.796775953807133e-05, "loss": 0.5237088680267334, "step": 366710 }, { "epoch": 2.179859835583216, "grad_norm": 1.3583112955093384, "learning_rate": 5.796268062168244e-05, "loss": 0.5595149040222168, "step": 366720 }, { "epoch": 2.1799192776598844, "grad_norm": 1.384761095046997, "learning_rate": 5.795760195422308e-05, "loss": 0.4451460838317871, "step": 366730 }, { "epoch": 2.1799787197365528, "grad_norm": 1.4010084867477417, "learning_rate": 5.795252353571754e-05, "loss": 0.4984462738037109, "step": 366740 }, { "epoch": 2.180038161813221, "grad_norm": 1.2456328868865967, "learning_rate": 5.794744536619012e-05, "loss": 0.47610864639282224, "step": 366750 }, { "epoch": 2.1800976038898896, "grad_norm": 1.5507090091705322, "learning_rate": 5.7942367445665124e-05, "loss": 0.4896566390991211, "step": 366760 }, { "epoch": 2.180157045966558, "grad_norm": 1.3122929334640503, "learning_rate": 5.793728977416679e-05, "loss": 0.4314753532409668, "step": 366770 }, { "epoch": 2.1802164880432264, "grad_norm": 1.563651442527771, "learning_rate": 5.7932212351719474e-05, "loss": 0.5005263328552246, "step": 366780 }, { "epoch": 2.180275930119895, "grad_norm": 1.379996418952942, "learning_rate": 5.7927135178347434e-05, "loss": 0.5676731586456298, "step": 366790 }, { "epoch": 2.1803353721965633, "grad_norm": 1.4834519624710083, "learning_rate": 5.792205825407497e-05, "loss": 0.45227584838867185, "step": 366800 }, { "epoch": 2.1803948142732317, "grad_norm": 1.2753993272781372, "learning_rate": 5.7916981578926355e-05, "loss": 0.5043705463409424, "step": 366810 }, { "epoch": 2.1804542563498996, "grad_norm": 1.0718357563018799, "learning_rate": 5.791190515292588e-05, "loss": 0.4770810604095459, "step": 366820 }, { "epoch": 2.180513698426568, "grad_norm": 1.2692067623138428, "learning_rate": 5.790682897609784e-05, "loss": 0.5077876567840576, "step": 366830 }, { "epoch": 2.1805731405032365, "grad_norm": 1.3211928606033325, "learning_rate": 5.7901753048466466e-05, "loss": 0.46782989501953126, "step": 366840 }, { "epoch": 2.180632582579905, "grad_norm": 1.0885330438613892, "learning_rate": 5.7896677370056106e-05, "loss": 0.4925814628601074, "step": 366850 }, { "epoch": 2.1806920246565733, "grad_norm": 1.3921406269073486, "learning_rate": 5.789160194089102e-05, "loss": 0.48750791549682615, "step": 366860 }, { "epoch": 2.1807514667332417, "grad_norm": 1.5082471370697021, "learning_rate": 5.7886526760995474e-05, "loss": 0.5292539596557617, "step": 366870 }, { "epoch": 2.18081090880991, "grad_norm": 1.4459564685821533, "learning_rate": 5.7881451830393755e-05, "loss": 0.5077890396118164, "step": 366880 }, { "epoch": 2.1808703508865785, "grad_norm": 1.185420274734497, "learning_rate": 5.787637714911015e-05, "loss": 0.5153403759002686, "step": 366890 }, { "epoch": 2.180929792963247, "grad_norm": 1.351976752281189, "learning_rate": 5.787130271716887e-05, "loss": 0.5061149597167969, "step": 366900 }, { "epoch": 2.1809892350399154, "grad_norm": 1.8450309038162231, "learning_rate": 5.78662285345943e-05, "loss": 0.541291332244873, "step": 366910 }, { "epoch": 2.181048677116584, "grad_norm": 1.3883419036865234, "learning_rate": 5.786115460141064e-05, "loss": 0.5357574462890625, "step": 366920 }, { "epoch": 2.181108119193252, "grad_norm": 1.6750797033309937, "learning_rate": 5.785608091764218e-05, "loss": 0.48947725296020506, "step": 366930 }, { "epoch": 2.1811675612699206, "grad_norm": 1.2507522106170654, "learning_rate": 5.785100748331318e-05, "loss": 0.513765525817871, "step": 366940 }, { "epoch": 2.181227003346589, "grad_norm": 1.323988676071167, "learning_rate": 5.7845934298447926e-05, "loss": 0.5070191383361816, "step": 366950 }, { "epoch": 2.1812864454232574, "grad_norm": 1.5119431018829346, "learning_rate": 5.7840861363070675e-05, "loss": 0.5168684005737305, "step": 366960 }, { "epoch": 2.181345887499926, "grad_norm": 0.9478439688682556, "learning_rate": 5.7835788677205674e-05, "loss": 0.500759220123291, "step": 366970 }, { "epoch": 2.1814053295765943, "grad_norm": 1.5955095291137695, "learning_rate": 5.7830716240877236e-05, "loss": 0.48081235885620116, "step": 366980 }, { "epoch": 2.1814647716532622, "grad_norm": 1.2642160654067993, "learning_rate": 5.7825644054109594e-05, "loss": 0.45117826461791993, "step": 366990 }, { "epoch": 2.1815242137299307, "grad_norm": 1.7173116207122803, "learning_rate": 5.782057211692704e-05, "loss": 0.4590627670288086, "step": 367000 }, { "epoch": 2.181583655806599, "grad_norm": 1.458533763885498, "learning_rate": 5.78155004293538e-05, "loss": 0.499864387512207, "step": 367010 }, { "epoch": 2.1816430978832675, "grad_norm": 1.163780927658081, "learning_rate": 5.781042899141415e-05, "loss": 0.4938714027404785, "step": 367020 }, { "epoch": 2.181702539959936, "grad_norm": 1.5867329835891724, "learning_rate": 5.780535780313233e-05, "loss": 0.5252083778381348, "step": 367030 }, { "epoch": 2.1817619820366043, "grad_norm": 1.2413278818130493, "learning_rate": 5.7800286864532646e-05, "loss": 0.5027740955352783, "step": 367040 }, { "epoch": 2.1818214241132727, "grad_norm": 1.4426488876342773, "learning_rate": 5.7795216175639345e-05, "loss": 0.5452402114868165, "step": 367050 }, { "epoch": 2.181880866189941, "grad_norm": 1.3459926843643188, "learning_rate": 5.779014573647665e-05, "loss": 0.49723234176635744, "step": 367060 }, { "epoch": 2.1819403082666096, "grad_norm": 1.5280510187149048, "learning_rate": 5.778507554706885e-05, "loss": 0.4795367240905762, "step": 367070 }, { "epoch": 2.181999750343278, "grad_norm": 1.4805694818496704, "learning_rate": 5.778000560744018e-05, "loss": 0.5500497817993164, "step": 367080 }, { "epoch": 2.1820591924199464, "grad_norm": 1.3713600635528564, "learning_rate": 5.777493591761489e-05, "loss": 0.4876082897186279, "step": 367090 }, { "epoch": 2.182118634496615, "grad_norm": 1.294288158416748, "learning_rate": 5.776986647761722e-05, "loss": 0.4704739570617676, "step": 367100 }, { "epoch": 2.182178076573283, "grad_norm": 1.6066460609436035, "learning_rate": 5.776479728747146e-05, "loss": 0.523841667175293, "step": 367110 }, { "epoch": 2.1822375186499516, "grad_norm": 1.3342022895812988, "learning_rate": 5.7759728347201894e-05, "loss": 0.5060160636901856, "step": 367120 }, { "epoch": 2.18229696072662, "grad_norm": 1.7385363578796387, "learning_rate": 5.775465965683262e-05, "loss": 0.4951801300048828, "step": 367130 }, { "epoch": 2.1823564028032885, "grad_norm": 1.410617470741272, "learning_rate": 5.774959121638803e-05, "loss": 0.5252534866333007, "step": 367140 }, { "epoch": 2.182415844879957, "grad_norm": 1.3777061700820923, "learning_rate": 5.774452302589232e-05, "loss": 0.503484058380127, "step": 367150 }, { "epoch": 2.1824752869566253, "grad_norm": 1.244735836982727, "learning_rate": 5.7739455085369695e-05, "loss": 0.48580150604248046, "step": 367160 }, { "epoch": 2.1825347290332937, "grad_norm": 1.1950325965881348, "learning_rate": 5.773438739484448e-05, "loss": 0.5017871379852294, "step": 367170 }, { "epoch": 2.1825941711099617, "grad_norm": 1.3411403894424438, "learning_rate": 5.77293199543409e-05, "loss": 0.4673173904418945, "step": 367180 }, { "epoch": 2.18265361318663, "grad_norm": 1.47638738155365, "learning_rate": 5.7724252763883105e-05, "loss": 0.5101397514343262, "step": 367190 }, { "epoch": 2.1827130552632985, "grad_norm": 1.4880564212799072, "learning_rate": 5.771918582349543e-05, "loss": 0.45676326751708984, "step": 367200 }, { "epoch": 2.182772497339967, "grad_norm": 1.184053897857666, "learning_rate": 5.7714119133202106e-05, "loss": 0.5084638118743896, "step": 367210 }, { "epoch": 2.1828319394166353, "grad_norm": 1.59113347530365, "learning_rate": 5.770905269302732e-05, "loss": 0.4643682956695557, "step": 367220 }, { "epoch": 2.1828913814933038, "grad_norm": 1.004907250404358, "learning_rate": 5.7703986502995334e-05, "loss": 0.45122537612915037, "step": 367230 }, { "epoch": 2.182950823569972, "grad_norm": 1.6059415340423584, "learning_rate": 5.769892056313042e-05, "loss": 0.45217304229736327, "step": 367240 }, { "epoch": 2.1830102656466406, "grad_norm": 2.0881881713867188, "learning_rate": 5.769385487345675e-05, "loss": 0.49343295097351075, "step": 367250 }, { "epoch": 2.183069707723309, "grad_norm": 1.3755967617034912, "learning_rate": 5.768878943399858e-05, "loss": 0.5017091274261475, "step": 367260 }, { "epoch": 2.1831291497999774, "grad_norm": 1.4219244718551636, "learning_rate": 5.768372424478016e-05, "loss": 0.4643050193786621, "step": 367270 }, { "epoch": 2.183188591876646, "grad_norm": 1.2774797677993774, "learning_rate": 5.76786593058257e-05, "loss": 0.4880537509918213, "step": 367280 }, { "epoch": 2.1832480339533142, "grad_norm": 1.3243688344955444, "learning_rate": 5.767359461715944e-05, "loss": 0.508213996887207, "step": 367290 }, { "epoch": 2.1833074760299827, "grad_norm": 1.3088334798812866, "learning_rate": 5.766853017880561e-05, "loss": 0.47928905487060547, "step": 367300 }, { "epoch": 2.183366918106651, "grad_norm": 1.5405739545822144, "learning_rate": 5.766346599078842e-05, "loss": 0.5548421382904053, "step": 367310 }, { "epoch": 2.1834263601833195, "grad_norm": 1.1233528852462769, "learning_rate": 5.765840205313211e-05, "loss": 0.4725620269775391, "step": 367320 }, { "epoch": 2.183485802259988, "grad_norm": 1.5677372217178345, "learning_rate": 5.7653338365860875e-05, "loss": 0.47716073989868163, "step": 367330 }, { "epoch": 2.1835452443366563, "grad_norm": 1.6558294296264648, "learning_rate": 5.764827492899898e-05, "loss": 0.5550121307373047, "step": 367340 }, { "epoch": 2.1836046864133247, "grad_norm": 1.4014315605163574, "learning_rate": 5.764321174257064e-05, "loss": 0.4962776184082031, "step": 367350 }, { "epoch": 2.183664128489993, "grad_norm": 1.4223554134368896, "learning_rate": 5.763814880660006e-05, "loss": 0.5096516132354736, "step": 367360 }, { "epoch": 2.183723570566661, "grad_norm": 1.4475877285003662, "learning_rate": 5.763308612111146e-05, "loss": 0.5041861534118652, "step": 367370 }, { "epoch": 2.1837830126433295, "grad_norm": 1.3662452697753906, "learning_rate": 5.762802368612907e-05, "loss": 0.49670162200927737, "step": 367380 }, { "epoch": 2.183842454719998, "grad_norm": 1.4304581880569458, "learning_rate": 5.7622961501677056e-05, "loss": 0.5197704792022705, "step": 367390 }, { "epoch": 2.1839018967966664, "grad_norm": 1.116371989250183, "learning_rate": 5.7617899567779724e-05, "loss": 0.47930269241333007, "step": 367400 }, { "epoch": 2.1839613388733348, "grad_norm": 1.2153244018554688, "learning_rate": 5.761283788446123e-05, "loss": 0.4604329109191895, "step": 367410 }, { "epoch": 2.184020780950003, "grad_norm": 1.3219844102859497, "learning_rate": 5.76077764517458e-05, "loss": 0.5434030532836914, "step": 367420 }, { "epoch": 2.1840802230266716, "grad_norm": 1.4206135272979736, "learning_rate": 5.760271526965764e-05, "loss": 0.48776912689208984, "step": 367430 }, { "epoch": 2.18413966510334, "grad_norm": 1.0252043008804321, "learning_rate": 5.759765433822099e-05, "loss": 0.5060807228088379, "step": 367440 }, { "epoch": 2.1841991071800084, "grad_norm": 1.0016350746154785, "learning_rate": 5.759259365746002e-05, "loss": 0.5205965995788574, "step": 367450 }, { "epoch": 2.184258549256677, "grad_norm": 0.969764769077301, "learning_rate": 5.758753322739892e-05, "loss": 0.47205286026000975, "step": 367460 }, { "epoch": 2.1843179913333453, "grad_norm": 1.3594697713851929, "learning_rate": 5.758247304806197e-05, "loss": 0.5034963607788085, "step": 367470 }, { "epoch": 2.1843774334100137, "grad_norm": 1.7920200824737549, "learning_rate": 5.757741311947333e-05, "loss": 0.5634829998016357, "step": 367480 }, { "epoch": 2.184436875486682, "grad_norm": 1.2549102306365967, "learning_rate": 5.7572353441657225e-05, "loss": 0.5165984153747558, "step": 367490 }, { "epoch": 2.1844963175633505, "grad_norm": 1.4926632642745972, "learning_rate": 5.756729401463785e-05, "loss": 0.5180295944213867, "step": 367500 }, { "epoch": 2.184555759640019, "grad_norm": 1.429729700088501, "learning_rate": 5.756223483843939e-05, "loss": 0.5213774681091309, "step": 367510 }, { "epoch": 2.1846152017166873, "grad_norm": 1.3775317668914795, "learning_rate": 5.755717591308605e-05, "loss": 0.48450555801391604, "step": 367520 }, { "epoch": 2.1846746437933557, "grad_norm": 1.3904399871826172, "learning_rate": 5.755211723860205e-05, "loss": 0.47134981155395506, "step": 367530 }, { "epoch": 2.184734085870024, "grad_norm": 1.469433069229126, "learning_rate": 5.75470588150116e-05, "loss": 0.5042441368103028, "step": 367540 }, { "epoch": 2.1847935279466926, "grad_norm": 1.6070668697357178, "learning_rate": 5.754200064233887e-05, "loss": 0.45737743377685547, "step": 367550 }, { "epoch": 2.1848529700233605, "grad_norm": 1.5841947793960571, "learning_rate": 5.753694272060808e-05, "loss": 0.4933279037475586, "step": 367560 }, { "epoch": 2.184912412100029, "grad_norm": 1.2086131572723389, "learning_rate": 5.753188504984339e-05, "loss": 0.5919736862182617, "step": 367570 }, { "epoch": 2.1849718541766974, "grad_norm": 1.0735297203063965, "learning_rate": 5.752682763006902e-05, "loss": 0.4861907005310059, "step": 367580 }, { "epoch": 2.185031296253366, "grad_norm": 1.2178274393081665, "learning_rate": 5.752177046130913e-05, "loss": 0.43787784576416017, "step": 367590 }, { "epoch": 2.185090738330034, "grad_norm": 1.6202973127365112, "learning_rate": 5.7516713543587975e-05, "loss": 0.4897614479064941, "step": 367600 }, { "epoch": 2.1851501804067026, "grad_norm": 1.1578558683395386, "learning_rate": 5.751165687692974e-05, "loss": 0.5213437557220459, "step": 367610 }, { "epoch": 2.185209622483371, "grad_norm": 1.984939694404602, "learning_rate": 5.750660046135853e-05, "loss": 0.5194576263427735, "step": 367620 }, { "epoch": 2.1852690645600394, "grad_norm": 1.1830557584762573, "learning_rate": 5.75015442968986e-05, "loss": 0.5305144309997558, "step": 367630 }, { "epoch": 2.185328506636708, "grad_norm": 1.4346946477890015, "learning_rate": 5.7496488383574135e-05, "loss": 0.4614285469055176, "step": 367640 }, { "epoch": 2.1853879487133763, "grad_norm": 1.0789223909378052, "learning_rate": 5.749143272140929e-05, "loss": 0.49315319061279295, "step": 367650 }, { "epoch": 2.1854473907900447, "grad_norm": 1.1125515699386597, "learning_rate": 5.7486377310428295e-05, "loss": 0.45139198303222655, "step": 367660 }, { "epoch": 2.185506832866713, "grad_norm": 1.1312928199768066, "learning_rate": 5.7481322150655335e-05, "loss": 0.44729185104370117, "step": 367670 }, { "epoch": 2.1855662749433815, "grad_norm": 1.4065932035446167, "learning_rate": 5.747626724211454e-05, "loss": 0.5742976188659668, "step": 367680 }, { "epoch": 2.18562571702005, "grad_norm": 1.4143263101577759, "learning_rate": 5.747121258483008e-05, "loss": 0.48499250411987305, "step": 367690 }, { "epoch": 2.1856851590967183, "grad_norm": 1.2862108945846558, "learning_rate": 5.746615817882621e-05, "loss": 0.46305017471313475, "step": 367700 }, { "epoch": 2.1857446011733868, "grad_norm": 1.4744938611984253, "learning_rate": 5.746110402412708e-05, "loss": 0.5319587707519531, "step": 367710 }, { "epoch": 2.185804043250055, "grad_norm": 1.0542036294937134, "learning_rate": 5.745605012075681e-05, "loss": 0.526570463180542, "step": 367720 }, { "epoch": 2.185863485326723, "grad_norm": 1.2421739101409912, "learning_rate": 5.74509964687397e-05, "loss": 0.4777080059051514, "step": 367730 }, { "epoch": 2.1859229274033916, "grad_norm": 1.4000324010849, "learning_rate": 5.7445943068099805e-05, "loss": 0.48573808670043944, "step": 367740 }, { "epoch": 2.18598236948006, "grad_norm": 1.6542521715164185, "learning_rate": 5.744088991886133e-05, "loss": 0.5359131336212158, "step": 367750 }, { "epoch": 2.1860418115567284, "grad_norm": 1.6213102340698242, "learning_rate": 5.7435837021048475e-05, "loss": 0.4695699691772461, "step": 367760 }, { "epoch": 2.186101253633397, "grad_norm": 1.2958043813705444, "learning_rate": 5.7430784374685406e-05, "loss": 0.47057366371154785, "step": 367770 }, { "epoch": 2.186160695710065, "grad_norm": 1.7406425476074219, "learning_rate": 5.742573197979626e-05, "loss": 0.46297149658203124, "step": 367780 }, { "epoch": 2.1862201377867336, "grad_norm": 1.2894115447998047, "learning_rate": 5.7420679836405286e-05, "loss": 0.5085517883300781, "step": 367790 }, { "epoch": 2.186279579863402, "grad_norm": 1.4163771867752075, "learning_rate": 5.741562794453656e-05, "loss": 0.5389157295227051, "step": 367800 }, { "epoch": 2.1863390219400705, "grad_norm": 1.3941844701766968, "learning_rate": 5.741057630421429e-05, "loss": 0.48579654693603513, "step": 367810 }, { "epoch": 2.186398464016739, "grad_norm": 1.4830663204193115, "learning_rate": 5.7405524915462615e-05, "loss": 0.511143970489502, "step": 367820 }, { "epoch": 2.1864579060934073, "grad_norm": 1.3448541164398193, "learning_rate": 5.7400473778305744e-05, "loss": 0.5017927646636963, "step": 367830 }, { "epoch": 2.1865173481700757, "grad_norm": 1.538927674293518, "learning_rate": 5.73954228927678e-05, "loss": 0.4492490768432617, "step": 367840 }, { "epoch": 2.186576790246744, "grad_norm": 1.334906816482544, "learning_rate": 5.739037225887298e-05, "loss": 0.47754459381103515, "step": 367850 }, { "epoch": 2.1866362323234125, "grad_norm": 1.5127942562103271, "learning_rate": 5.7385321876645434e-05, "loss": 0.4826554298400879, "step": 367860 }, { "epoch": 2.186695674400081, "grad_norm": 1.7574304342269897, "learning_rate": 5.7380271746109294e-05, "loss": 0.5147678852081299, "step": 367870 }, { "epoch": 2.1867551164767494, "grad_norm": 1.3620836734771729, "learning_rate": 5.737522186728872e-05, "loss": 0.502926254272461, "step": 367880 }, { "epoch": 2.1868145585534178, "grad_norm": 1.4388285875320435, "learning_rate": 5.737017224020791e-05, "loss": 0.49964303970336915, "step": 367890 }, { "epoch": 2.186874000630086, "grad_norm": 1.4344682693481445, "learning_rate": 5.736512286489101e-05, "loss": 0.525428581237793, "step": 367900 }, { "epoch": 2.1869334427067546, "grad_norm": 1.6250431537628174, "learning_rate": 5.736007374136215e-05, "loss": 0.4858290195465088, "step": 367910 }, { "epoch": 2.1869928847834226, "grad_norm": 1.3761391639709473, "learning_rate": 5.73550248696455e-05, "loss": 0.5693564891815186, "step": 367920 }, { "epoch": 2.187052326860091, "grad_norm": 1.5710456371307373, "learning_rate": 5.7349976249765194e-05, "loss": 0.4738147735595703, "step": 367930 }, { "epoch": 2.1871117689367594, "grad_norm": 1.413985252380371, "learning_rate": 5.734492788174539e-05, "loss": 0.48818264007568357, "step": 367940 }, { "epoch": 2.187171211013428, "grad_norm": 1.878332257270813, "learning_rate": 5.733987976561024e-05, "loss": 0.5553367614746094, "step": 367950 }, { "epoch": 2.1872306530900962, "grad_norm": 1.322283148765564, "learning_rate": 5.7334831901383904e-05, "loss": 0.49993181228637695, "step": 367960 }, { "epoch": 2.1872900951667646, "grad_norm": 1.0588489770889282, "learning_rate": 5.7329784289090526e-05, "loss": 0.45427188873291013, "step": 367970 }, { "epoch": 2.187349537243433, "grad_norm": 1.223732352256775, "learning_rate": 5.732473692875426e-05, "loss": 0.443618631362915, "step": 367980 }, { "epoch": 2.1874089793201015, "grad_norm": 1.5468344688415527, "learning_rate": 5.7319689820399225e-05, "loss": 0.5391910076141357, "step": 367990 }, { "epoch": 2.18746842139677, "grad_norm": 1.4189977645874023, "learning_rate": 5.731464296404958e-05, "loss": 0.497450065612793, "step": 368000 }, { "epoch": 2.1875278634734383, "grad_norm": 1.2385121583938599, "learning_rate": 5.730959635972943e-05, "loss": 0.48388671875, "step": 368010 }, { "epoch": 2.1875873055501067, "grad_norm": 1.1868016719818115, "learning_rate": 5.7304550007463e-05, "loss": 0.48683772087097166, "step": 368020 }, { "epoch": 2.187646747626775, "grad_norm": 1.2968075275421143, "learning_rate": 5.729950390727437e-05, "loss": 0.4904629707336426, "step": 368030 }, { "epoch": 2.1877061897034435, "grad_norm": 1.4876154661178589, "learning_rate": 5.7294458059187684e-05, "loss": 0.48757405281066896, "step": 368040 }, { "epoch": 2.187765631780112, "grad_norm": 1.357027530670166, "learning_rate": 5.72894124632271e-05, "loss": 0.5104595184326172, "step": 368050 }, { "epoch": 2.1878250738567804, "grad_norm": 1.3354567289352417, "learning_rate": 5.728436711941672e-05, "loss": 0.48898563385009763, "step": 368060 }, { "epoch": 2.187884515933449, "grad_norm": 1.4963200092315674, "learning_rate": 5.7279322027780715e-05, "loss": 0.46704583168029784, "step": 368070 }, { "epoch": 2.187943958010117, "grad_norm": 1.4092451333999634, "learning_rate": 5.7274277188343175e-05, "loss": 0.4500920295715332, "step": 368080 }, { "epoch": 2.1880034000867856, "grad_norm": 1.033417820930481, "learning_rate": 5.726923260112829e-05, "loss": 0.5383955955505371, "step": 368090 }, { "epoch": 2.188062842163454, "grad_norm": 1.3094443082809448, "learning_rate": 5.726418826616018e-05, "loss": 0.48266029357910156, "step": 368100 }, { "epoch": 2.188122284240122, "grad_norm": 1.421587347984314, "learning_rate": 5.725914418346292e-05, "loss": 0.49254150390625, "step": 368110 }, { "epoch": 2.1881817263167904, "grad_norm": 1.3700658082962036, "learning_rate": 5.7254100353060705e-05, "loss": 0.5219149589538574, "step": 368120 }, { "epoch": 2.188241168393459, "grad_norm": 1.3987399339675903, "learning_rate": 5.724905677497763e-05, "loss": 0.5222591876983642, "step": 368130 }, { "epoch": 2.1883006104701272, "grad_norm": 1.553045630455017, "learning_rate": 5.7244013449237786e-05, "loss": 0.4833993434906006, "step": 368140 }, { "epoch": 2.1883600525467957, "grad_norm": 1.1069999933242798, "learning_rate": 5.7238970375865385e-05, "loss": 0.45777077674865724, "step": 368150 }, { "epoch": 2.188419494623464, "grad_norm": 1.0970789194107056, "learning_rate": 5.723392755488455e-05, "loss": 0.5061407089233398, "step": 368160 }, { "epoch": 2.1884789367001325, "grad_norm": 1.5984926223754883, "learning_rate": 5.722888498631931e-05, "loss": 0.5047893524169922, "step": 368170 }, { "epoch": 2.188538378776801, "grad_norm": 1.2948821783065796, "learning_rate": 5.7223842670193814e-05, "loss": 0.4517655372619629, "step": 368180 }, { "epoch": 2.1885978208534693, "grad_norm": 1.278082013130188, "learning_rate": 5.721880060653224e-05, "loss": 0.5182939529418945, "step": 368190 }, { "epoch": 2.1886572629301377, "grad_norm": 1.289113163948059, "learning_rate": 5.7213758795358675e-05, "loss": 0.5121745586395263, "step": 368200 }, { "epoch": 2.188716705006806, "grad_norm": 1.5515881776809692, "learning_rate": 5.7208717236697204e-05, "loss": 0.4942080020904541, "step": 368210 }, { "epoch": 2.1887761470834746, "grad_norm": 1.696707010269165, "learning_rate": 5.720367593057203e-05, "loss": 0.5077900886535645, "step": 368220 }, { "epoch": 2.188835589160143, "grad_norm": 1.5079162120819092, "learning_rate": 5.7198634877007205e-05, "loss": 0.5210020065307617, "step": 368230 }, { "epoch": 2.1888950312368114, "grad_norm": 1.3788213729858398, "learning_rate": 5.719359407602682e-05, "loss": 0.4702497959136963, "step": 368240 }, { "epoch": 2.18895447331348, "grad_norm": 1.4613010883331299, "learning_rate": 5.718855352765504e-05, "loss": 0.520391845703125, "step": 368250 }, { "epoch": 2.1890139153901482, "grad_norm": 0.9773206114768982, "learning_rate": 5.7183513231915976e-05, "loss": 0.48802852630615234, "step": 368260 }, { "epoch": 2.1890733574668166, "grad_norm": 1.2818000316619873, "learning_rate": 5.717847318883369e-05, "loss": 0.5430676460266113, "step": 368270 }, { "epoch": 2.189132799543485, "grad_norm": 1.3609230518341064, "learning_rate": 5.71734333984324e-05, "loss": 0.491532039642334, "step": 368280 }, { "epoch": 2.1891922416201535, "grad_norm": 1.358866810798645, "learning_rate": 5.716839386073608e-05, "loss": 0.48810205459594724, "step": 368290 }, { "epoch": 2.1892516836968214, "grad_norm": 1.3553906679153442, "learning_rate": 5.7163354575768914e-05, "loss": 0.4567918300628662, "step": 368300 }, { "epoch": 2.18931112577349, "grad_norm": 1.025341510772705, "learning_rate": 5.7158315543554966e-05, "loss": 0.4925048828125, "step": 368310 }, { "epoch": 2.1893705678501583, "grad_norm": 1.3863130807876587, "learning_rate": 5.715327676411839e-05, "loss": 0.5127150535583496, "step": 368320 }, { "epoch": 2.1894300099268267, "grad_norm": 1.2540253400802612, "learning_rate": 5.714823823748328e-05, "loss": 0.48059840202331544, "step": 368330 }, { "epoch": 2.189489452003495, "grad_norm": 1.2263072729110718, "learning_rate": 5.714319996367371e-05, "loss": 0.468264102935791, "step": 368340 }, { "epoch": 2.1895488940801635, "grad_norm": 1.3676763772964478, "learning_rate": 5.713816194271381e-05, "loss": 0.539019775390625, "step": 368350 }, { "epoch": 2.189608336156832, "grad_norm": 1.098617672920227, "learning_rate": 5.713312417462766e-05, "loss": 0.4692983150482178, "step": 368360 }, { "epoch": 2.1896677782335003, "grad_norm": 1.6214839220046997, "learning_rate": 5.712808665943934e-05, "loss": 0.5178628444671631, "step": 368370 }, { "epoch": 2.1897272203101688, "grad_norm": 1.1682229042053223, "learning_rate": 5.7123049397173e-05, "loss": 0.5030398845672608, "step": 368380 }, { "epoch": 2.189786662386837, "grad_norm": 1.1955724954605103, "learning_rate": 5.7118012387852724e-05, "loss": 0.5173686981201172, "step": 368390 }, { "epoch": 2.1898461044635056, "grad_norm": 1.365031123161316, "learning_rate": 5.7112975631502587e-05, "loss": 0.5225997924804687, "step": 368400 }, { "epoch": 2.189905546540174, "grad_norm": 1.1160380840301514, "learning_rate": 5.710793912814668e-05, "loss": 0.5044038772583008, "step": 368410 }, { "epoch": 2.1899649886168424, "grad_norm": 1.3220173120498657, "learning_rate": 5.7102902877809114e-05, "loss": 0.5335478782653809, "step": 368420 }, { "epoch": 2.190024430693511, "grad_norm": 1.2061554193496704, "learning_rate": 5.7097866880513986e-05, "loss": 0.454502010345459, "step": 368430 }, { "epoch": 2.1900838727701792, "grad_norm": 1.2073215246200562, "learning_rate": 5.709283113628533e-05, "loss": 0.49203147888183596, "step": 368440 }, { "epoch": 2.1901433148468477, "grad_norm": 1.5133498907089233, "learning_rate": 5.7087795645147325e-05, "loss": 0.5427582263946533, "step": 368450 }, { "epoch": 2.190202756923516, "grad_norm": 1.4456303119659424, "learning_rate": 5.708276040712399e-05, "loss": 0.5181482315063477, "step": 368460 }, { "epoch": 2.190262199000184, "grad_norm": 1.5236154794692993, "learning_rate": 5.707772542223946e-05, "loss": 0.556754207611084, "step": 368470 }, { "epoch": 2.1903216410768525, "grad_norm": 1.356061339378357, "learning_rate": 5.7072690690517785e-05, "loss": 0.5435178279876709, "step": 368480 }, { "epoch": 2.190381083153521, "grad_norm": 1.1522918939590454, "learning_rate": 5.7067656211983055e-05, "loss": 0.4623931884765625, "step": 368490 }, { "epoch": 2.1904405252301893, "grad_norm": 1.2802534103393555, "learning_rate": 5.706262198665934e-05, "loss": 0.5037008285522461, "step": 368500 }, { "epoch": 2.1904999673068577, "grad_norm": 1.1763379573822021, "learning_rate": 5.7057588014570764e-05, "loss": 0.4239473819732666, "step": 368510 }, { "epoch": 2.190559409383526, "grad_norm": 1.2291784286499023, "learning_rate": 5.705255429574139e-05, "loss": 0.5160585880279541, "step": 368520 }, { "epoch": 2.1906188514601945, "grad_norm": 1.291732668876648, "learning_rate": 5.704752083019529e-05, "loss": 0.484482479095459, "step": 368530 }, { "epoch": 2.190678293536863, "grad_norm": 1.375891089439392, "learning_rate": 5.704248761795654e-05, "loss": 0.47779250144958496, "step": 368540 }, { "epoch": 2.1907377356135314, "grad_norm": 1.4374476671218872, "learning_rate": 5.7037454659049236e-05, "loss": 0.47367105484008787, "step": 368550 }, { "epoch": 2.1907971776901998, "grad_norm": 1.212113857269287, "learning_rate": 5.703242195349743e-05, "loss": 0.46625585556030275, "step": 368560 }, { "epoch": 2.190856619766868, "grad_norm": 1.3794922828674316, "learning_rate": 5.7027389501325176e-05, "loss": 0.47937736511230467, "step": 368570 }, { "epoch": 2.1909160618435366, "grad_norm": 1.4940418004989624, "learning_rate": 5.702235730255662e-05, "loss": 0.5063144207000733, "step": 368580 }, { "epoch": 2.190975503920205, "grad_norm": 1.0227642059326172, "learning_rate": 5.701732535721578e-05, "loss": 0.4823010444641113, "step": 368590 }, { "epoch": 2.1910349459968734, "grad_norm": 1.7503669261932373, "learning_rate": 5.7012293665326766e-05, "loss": 0.5242499351501465, "step": 368600 }, { "epoch": 2.191094388073542, "grad_norm": 1.4672859907150269, "learning_rate": 5.7007262226913596e-05, "loss": 0.49809913635253905, "step": 368610 }, { "epoch": 2.1911538301502103, "grad_norm": 1.300780177116394, "learning_rate": 5.700223104200038e-05, "loss": 0.4623905658721924, "step": 368620 }, { "epoch": 2.1912132722268787, "grad_norm": 1.3332054615020752, "learning_rate": 5.699720011061113e-05, "loss": 0.5265520095825196, "step": 368630 }, { "epoch": 2.191272714303547, "grad_norm": 1.1048983335494995, "learning_rate": 5.699216943276999e-05, "loss": 0.533478832244873, "step": 368640 }, { "epoch": 2.1913321563802155, "grad_norm": 1.3595103025436401, "learning_rate": 5.698713900850098e-05, "loss": 0.47247090339660647, "step": 368650 }, { "epoch": 2.1913915984568835, "grad_norm": 1.5044224262237549, "learning_rate": 5.6982108837828206e-05, "loss": 0.5069936752319336, "step": 368660 }, { "epoch": 2.191451040533552, "grad_norm": 1.1472959518432617, "learning_rate": 5.697707892077564e-05, "loss": 0.4482434272766113, "step": 368670 }, { "epoch": 2.1915104826102203, "grad_norm": 1.476897954940796, "learning_rate": 5.6972049257367434e-05, "loss": 0.4954212665557861, "step": 368680 }, { "epoch": 2.1915699246868887, "grad_norm": 1.4219404458999634, "learning_rate": 5.69670198476276e-05, "loss": 0.5464234352111816, "step": 368690 }, { "epoch": 2.191629366763557, "grad_norm": 1.3350895643234253, "learning_rate": 5.696199069158019e-05, "loss": 0.5020302772521973, "step": 368700 }, { "epoch": 2.1916888088402255, "grad_norm": 1.7119929790496826, "learning_rate": 5.695696178924934e-05, "loss": 0.4865883827209473, "step": 368710 }, { "epoch": 2.191748250916894, "grad_norm": 1.156362771987915, "learning_rate": 5.695193314065903e-05, "loss": 0.5120672225952149, "step": 368720 }, { "epoch": 2.1918076929935624, "grad_norm": 1.4755760431289673, "learning_rate": 5.6946904745833306e-05, "loss": 0.569737720489502, "step": 368730 }, { "epoch": 2.191867135070231, "grad_norm": 1.4797743558883667, "learning_rate": 5.694187660479628e-05, "loss": 0.48198485374450684, "step": 368740 }, { "epoch": 2.191926577146899, "grad_norm": 1.3987735509872437, "learning_rate": 5.693684871757197e-05, "loss": 0.46346220970153806, "step": 368750 }, { "epoch": 2.1919860192235676, "grad_norm": 1.7193934917449951, "learning_rate": 5.69318210841844e-05, "loss": 0.521245288848877, "step": 368760 }, { "epoch": 2.192045461300236, "grad_norm": 1.2827255725860596, "learning_rate": 5.692679370465772e-05, "loss": 0.49647274017333987, "step": 368770 }, { "epoch": 2.1921049033769044, "grad_norm": 1.1457726955413818, "learning_rate": 5.69217665790159e-05, "loss": 0.4480596542358398, "step": 368780 }, { "epoch": 2.192164345453573, "grad_norm": 1.7010445594787598, "learning_rate": 5.6916739707283e-05, "loss": 0.47861690521240235, "step": 368790 }, { "epoch": 2.1922237875302413, "grad_norm": 1.186628818511963, "learning_rate": 5.691171308948301e-05, "loss": 0.4717857360839844, "step": 368800 }, { "epoch": 2.1922832296069097, "grad_norm": 1.339262843132019, "learning_rate": 5.690668672564009e-05, "loss": 0.4905651569366455, "step": 368810 }, { "epoch": 2.192342671683578, "grad_norm": 1.4624778032302856, "learning_rate": 5.6901660615778216e-05, "loss": 0.5326456069946289, "step": 368820 }, { "epoch": 2.1924021137602465, "grad_norm": 1.1028246879577637, "learning_rate": 5.689663475992146e-05, "loss": 0.5032052040100098, "step": 368830 }, { "epoch": 2.192461555836915, "grad_norm": 1.469925880432129, "learning_rate": 5.689160915809384e-05, "loss": 0.570915699005127, "step": 368840 }, { "epoch": 2.192520997913583, "grad_norm": 1.5395948886871338, "learning_rate": 5.688658381031941e-05, "loss": 0.4695722579956055, "step": 368850 }, { "epoch": 2.1925804399902513, "grad_norm": 0.8368380069732666, "learning_rate": 5.6881558716622175e-05, "loss": 0.43907938003540037, "step": 368860 }, { "epoch": 2.1926398820669197, "grad_norm": 0.8441169261932373, "learning_rate": 5.687653387702623e-05, "loss": 0.44876651763916015, "step": 368870 }, { "epoch": 2.192699324143588, "grad_norm": 1.3021420240402222, "learning_rate": 5.687150929155558e-05, "loss": 0.4872457504272461, "step": 368880 }, { "epoch": 2.1927587662202566, "grad_norm": 1.3437018394470215, "learning_rate": 5.686648496023428e-05, "loss": 0.5316025733947753, "step": 368890 }, { "epoch": 2.192818208296925, "grad_norm": 1.4754400253295898, "learning_rate": 5.686146088308635e-05, "loss": 0.4326763153076172, "step": 368900 }, { "epoch": 2.1928776503735934, "grad_norm": 1.2749611139297485, "learning_rate": 5.685643706013582e-05, "loss": 0.4947463035583496, "step": 368910 }, { "epoch": 2.192937092450262, "grad_norm": 1.256848931312561, "learning_rate": 5.6851413491406725e-05, "loss": 0.516413402557373, "step": 368920 }, { "epoch": 2.19299653452693, "grad_norm": 1.0944470167160034, "learning_rate": 5.684639017692308e-05, "loss": 0.43643951416015625, "step": 368930 }, { "epoch": 2.1930559766035986, "grad_norm": 1.5966726541519165, "learning_rate": 5.684136711670894e-05, "loss": 0.5624508857727051, "step": 368940 }, { "epoch": 2.193115418680267, "grad_norm": 1.1999850273132324, "learning_rate": 5.6836344310788345e-05, "loss": 0.536298131942749, "step": 368950 }, { "epoch": 2.1931748607569355, "grad_norm": 1.2289515733718872, "learning_rate": 5.683132175918531e-05, "loss": 0.4611072540283203, "step": 368960 }, { "epoch": 2.193234302833604, "grad_norm": 1.1635724306106567, "learning_rate": 5.682629946192385e-05, "loss": 0.4578110218048096, "step": 368970 }, { "epoch": 2.1932937449102723, "grad_norm": 0.9601874351501465, "learning_rate": 5.682127741902801e-05, "loss": 0.46662101745605467, "step": 368980 }, { "epoch": 2.1933531869869407, "grad_norm": 1.6918002367019653, "learning_rate": 5.681625563052173e-05, "loss": 0.5006560325622559, "step": 368990 }, { "epoch": 2.193412629063609, "grad_norm": 1.5954108238220215, "learning_rate": 5.681123409642917e-05, "loss": 0.518532657623291, "step": 369000 }, { "epoch": 2.1934720711402775, "grad_norm": 0.796751856803894, "learning_rate": 5.6806212816774265e-05, "loss": 0.5097699165344238, "step": 369010 }, { "epoch": 2.193531513216946, "grad_norm": 1.2399133443832397, "learning_rate": 5.6801191791581064e-05, "loss": 0.4974356174468994, "step": 369020 }, { "epoch": 2.1935909552936144, "grad_norm": 1.4066184759140015, "learning_rate": 5.679617102087358e-05, "loss": 0.45783653259277346, "step": 369030 }, { "epoch": 2.1936503973702823, "grad_norm": 1.31000816822052, "learning_rate": 5.679115050467582e-05, "loss": 0.45586719512939455, "step": 369040 }, { "epoch": 2.1937098394469507, "grad_norm": 1.3034766912460327, "learning_rate": 5.6786130243011805e-05, "loss": 0.43570404052734374, "step": 369050 }, { "epoch": 2.193769281523619, "grad_norm": 1.3731406927108765, "learning_rate": 5.678111023590551e-05, "loss": 0.5021280288696289, "step": 369060 }, { "epoch": 2.1938287236002876, "grad_norm": 1.4047616720199585, "learning_rate": 5.677609048338104e-05, "loss": 0.467406177520752, "step": 369070 }, { "epoch": 2.193888165676956, "grad_norm": 1.520992398262024, "learning_rate": 5.677107098546236e-05, "loss": 0.4624842643737793, "step": 369080 }, { "epoch": 2.1939476077536244, "grad_norm": 1.1737502813339233, "learning_rate": 5.676605174217348e-05, "loss": 0.5174805164337158, "step": 369090 }, { "epoch": 2.194007049830293, "grad_norm": 1.4773788452148438, "learning_rate": 5.676103275353839e-05, "loss": 0.5337057113647461, "step": 369100 }, { "epoch": 2.1940664919069612, "grad_norm": 1.4984502792358398, "learning_rate": 5.675601401958115e-05, "loss": 0.5321362018585205, "step": 369110 }, { "epoch": 2.1941259339836297, "grad_norm": 1.2801941633224487, "learning_rate": 5.675099554032569e-05, "loss": 0.5163296699523926, "step": 369120 }, { "epoch": 2.194185376060298, "grad_norm": 1.316986322402954, "learning_rate": 5.6745977315796094e-05, "loss": 0.47643585205078126, "step": 369130 }, { "epoch": 2.1942448181369665, "grad_norm": 1.2300517559051514, "learning_rate": 5.674095934601635e-05, "loss": 0.4820239543914795, "step": 369140 }, { "epoch": 2.194304260213635, "grad_norm": 1.3129324913024902, "learning_rate": 5.673594163101048e-05, "loss": 0.479604434967041, "step": 369150 }, { "epoch": 2.1943637022903033, "grad_norm": 0.9503487944602966, "learning_rate": 5.673092417080239e-05, "loss": 0.47066240310668944, "step": 369160 }, { "epoch": 2.1944231443669717, "grad_norm": 1.2843729257583618, "learning_rate": 5.67259069654162e-05, "loss": 0.5224151611328125, "step": 369170 }, { "epoch": 2.19448258644364, "grad_norm": 0.9967237710952759, "learning_rate": 5.672089001487584e-05, "loss": 0.5393266201019287, "step": 369180 }, { "epoch": 2.1945420285203086, "grad_norm": 1.2499454021453857, "learning_rate": 5.671587331920532e-05, "loss": 0.5042479038238525, "step": 369190 }, { "epoch": 2.194601470596977, "grad_norm": 1.381230115890503, "learning_rate": 5.6710856878428656e-05, "loss": 0.4871072292327881, "step": 369200 }, { "epoch": 2.194660912673645, "grad_norm": 1.5659165382385254, "learning_rate": 5.670584069256988e-05, "loss": 0.521752405166626, "step": 369210 }, { "epoch": 2.1947203547503134, "grad_norm": 1.2947349548339844, "learning_rate": 5.670082476165288e-05, "loss": 0.4868321418762207, "step": 369220 }, { "epoch": 2.1947797968269818, "grad_norm": 1.5579237937927246, "learning_rate": 5.6695809085701755e-05, "loss": 0.5277134895324707, "step": 369230 }, { "epoch": 2.19483923890365, "grad_norm": 1.327337384223938, "learning_rate": 5.669079366474045e-05, "loss": 0.5305218696594238, "step": 369240 }, { "epoch": 2.1948986809803186, "grad_norm": 1.2890430688858032, "learning_rate": 5.668577849879294e-05, "loss": 0.5261672019958497, "step": 369250 }, { "epoch": 2.194958123056987, "grad_norm": 1.5799216032028198, "learning_rate": 5.6680763587883264e-05, "loss": 0.4951325416564941, "step": 369260 }, { "epoch": 2.1950175651336554, "grad_norm": 1.379253625869751, "learning_rate": 5.667574893203544e-05, "loss": 0.4962216854095459, "step": 369270 }, { "epoch": 2.195077007210324, "grad_norm": 1.2477591037750244, "learning_rate": 5.667073453127336e-05, "loss": 0.5197533130645752, "step": 369280 }, { "epoch": 2.1951364492869923, "grad_norm": 1.1044846773147583, "learning_rate": 5.6665720385621036e-05, "loss": 0.49590530395507815, "step": 369290 }, { "epoch": 2.1951958913636607, "grad_norm": 1.251152515411377, "learning_rate": 5.666070649510249e-05, "loss": 0.4824239253997803, "step": 369300 }, { "epoch": 2.195255333440329, "grad_norm": 0.9807125329971313, "learning_rate": 5.6655692859741706e-05, "loss": 0.4878899097442627, "step": 369310 }, { "epoch": 2.1953147755169975, "grad_norm": 1.41002357006073, "learning_rate": 5.6650679479562664e-05, "loss": 0.4694055557250977, "step": 369320 }, { "epoch": 2.195374217593666, "grad_norm": 1.0671495199203491, "learning_rate": 5.664566635458932e-05, "loss": 0.5032525062561035, "step": 369330 }, { "epoch": 2.1954336596703343, "grad_norm": 1.6274415254592896, "learning_rate": 5.6640653484845684e-05, "loss": 0.47736048698425293, "step": 369340 }, { "epoch": 2.1954931017470027, "grad_norm": 1.6342366933822632, "learning_rate": 5.663564087035569e-05, "loss": 0.4937347412109375, "step": 369350 }, { "epoch": 2.195552543823671, "grad_norm": 1.3444284200668335, "learning_rate": 5.663062851114337e-05, "loss": 0.45894269943237304, "step": 369360 }, { "epoch": 2.1956119859003396, "grad_norm": 1.468635082244873, "learning_rate": 5.66256164072327e-05, "loss": 0.5093688011169434, "step": 369370 }, { "epoch": 2.195671427977008, "grad_norm": 1.2905857563018799, "learning_rate": 5.662060455864762e-05, "loss": 0.44797444343566895, "step": 369380 }, { "epoch": 2.1957308700536764, "grad_norm": 1.5045453310012817, "learning_rate": 5.661559296541212e-05, "loss": 0.5667380332946778, "step": 369390 }, { "epoch": 2.1957903121303444, "grad_norm": 1.4517759084701538, "learning_rate": 5.6610581627550195e-05, "loss": 0.4787330150604248, "step": 369400 }, { "epoch": 2.195849754207013, "grad_norm": 1.6299983263015747, "learning_rate": 5.66055705450858e-05, "loss": 0.5662569999694824, "step": 369410 }, { "epoch": 2.195909196283681, "grad_norm": 1.0289267301559448, "learning_rate": 5.660055971804287e-05, "loss": 0.5188597202301025, "step": 369420 }, { "epoch": 2.1959686383603496, "grad_norm": 1.3087108135223389, "learning_rate": 5.6595549146445435e-05, "loss": 0.49547252655029295, "step": 369430 }, { "epoch": 2.196028080437018, "grad_norm": 1.8612680435180664, "learning_rate": 5.6590538830317454e-05, "loss": 0.486985969543457, "step": 369440 }, { "epoch": 2.1960875225136864, "grad_norm": 1.2634131908416748, "learning_rate": 5.658552876968286e-05, "loss": 0.47209882736206055, "step": 369450 }, { "epoch": 2.196146964590355, "grad_norm": 1.5568562746047974, "learning_rate": 5.658051896456567e-05, "loss": 0.524540901184082, "step": 369460 }, { "epoch": 2.1962064066670233, "grad_norm": 1.3111392259597778, "learning_rate": 5.657550941498979e-05, "loss": 0.5018723487854004, "step": 369470 }, { "epoch": 2.1962658487436917, "grad_norm": 1.219765305519104, "learning_rate": 5.65705001209792e-05, "loss": 0.49332370758056643, "step": 369480 }, { "epoch": 2.19632529082036, "grad_norm": 1.413242220878601, "learning_rate": 5.65654910825579e-05, "loss": 0.523690128326416, "step": 369490 }, { "epoch": 2.1963847328970285, "grad_norm": 1.2062321901321411, "learning_rate": 5.656048229974983e-05, "loss": 0.48957099914550783, "step": 369500 }, { "epoch": 2.196444174973697, "grad_norm": 1.012756586074829, "learning_rate": 5.655547377257895e-05, "loss": 0.4560297966003418, "step": 369510 }, { "epoch": 2.1965036170503653, "grad_norm": 1.188840389251709, "learning_rate": 5.6550465501069215e-05, "loss": 0.45458269119262695, "step": 369520 }, { "epoch": 2.1965630591270338, "grad_norm": 1.39102303981781, "learning_rate": 5.654545748524458e-05, "loss": 0.45282230377197263, "step": 369530 }, { "epoch": 2.196622501203702, "grad_norm": 1.232094645500183, "learning_rate": 5.654044972512902e-05, "loss": 0.5112825393676758, "step": 369540 }, { "epoch": 2.1966819432803706, "grad_norm": 1.5817844867706299, "learning_rate": 5.653544222074644e-05, "loss": 0.5300412178039551, "step": 369550 }, { "epoch": 2.196741385357039, "grad_norm": 1.8274717330932617, "learning_rate": 5.653043497212087e-05, "loss": 0.5634794712066651, "step": 369560 }, { "epoch": 2.1968008274337074, "grad_norm": 1.4677833318710327, "learning_rate": 5.65254279792762e-05, "loss": 0.5153186321258545, "step": 369570 }, { "epoch": 2.196860269510376, "grad_norm": 1.4557946920394897, "learning_rate": 5.652042124223644e-05, "loss": 0.5178629875183105, "step": 369580 }, { "epoch": 2.196919711587044, "grad_norm": 1.6082700490951538, "learning_rate": 5.651541476102549e-05, "loss": 0.4851123332977295, "step": 369590 }, { "epoch": 2.196979153663712, "grad_norm": 1.320406436920166, "learning_rate": 5.651040853566731e-05, "loss": 0.4653205871582031, "step": 369600 }, { "epoch": 2.1970385957403806, "grad_norm": 1.091825008392334, "learning_rate": 5.650540256618584e-05, "loss": 0.47895183563232424, "step": 369610 }, { "epoch": 2.197098037817049, "grad_norm": 1.3006535768508911, "learning_rate": 5.650039685260508e-05, "loss": 0.46106486320495604, "step": 369620 }, { "epoch": 2.1971574798937175, "grad_norm": 1.7349213361740112, "learning_rate": 5.6495391394948915e-05, "loss": 0.4775893211364746, "step": 369630 }, { "epoch": 2.197216921970386, "grad_norm": 1.1729816198349, "learning_rate": 5.6490386193241364e-05, "loss": 0.5147529125213623, "step": 369640 }, { "epoch": 2.1972763640470543, "grad_norm": 1.2728345394134521, "learning_rate": 5.648538124750623e-05, "loss": 0.47594680786132815, "step": 369650 }, { "epoch": 2.1973358061237227, "grad_norm": 1.0407902002334595, "learning_rate": 5.648037655776759e-05, "loss": 0.45888938903808596, "step": 369660 }, { "epoch": 2.197395248200391, "grad_norm": 1.349239706993103, "learning_rate": 5.647537212404934e-05, "loss": 0.5422861099243164, "step": 369670 }, { "epoch": 2.1974546902770595, "grad_norm": 1.0542409420013428, "learning_rate": 5.6470367946375394e-05, "loss": 0.46008639335632323, "step": 369680 }, { "epoch": 2.197514132353728, "grad_norm": 1.3986371755599976, "learning_rate": 5.6465364024769715e-05, "loss": 0.4964281558990479, "step": 369690 }, { "epoch": 2.1975735744303964, "grad_norm": 1.338794231414795, "learning_rate": 5.64603603592563e-05, "loss": 0.516296100616455, "step": 369700 }, { "epoch": 2.1976330165070648, "grad_norm": 1.5731850862503052, "learning_rate": 5.6455356949858954e-05, "loss": 0.49712352752685546, "step": 369710 }, { "epoch": 2.197692458583733, "grad_norm": 1.4918571710586548, "learning_rate": 5.6450353796601706e-05, "loss": 0.49385814666748046, "step": 369720 }, { "epoch": 2.1977519006604016, "grad_norm": 1.2742893695831299, "learning_rate": 5.644535089950848e-05, "loss": 0.43788509368896483, "step": 369730 }, { "epoch": 2.19781134273707, "grad_norm": 1.421486735343933, "learning_rate": 5.644034825860315e-05, "loss": 0.5266983985900879, "step": 369740 }, { "epoch": 2.1978707848137384, "grad_norm": 1.0600279569625854, "learning_rate": 5.643534587390973e-05, "loss": 0.5063351631164551, "step": 369750 }, { "epoch": 2.197930226890407, "grad_norm": 1.2749292850494385, "learning_rate": 5.643034374545213e-05, "loss": 0.47090697288513184, "step": 369760 }, { "epoch": 2.1979896689670753, "grad_norm": 1.311495304107666, "learning_rate": 5.642534187325424e-05, "loss": 0.5023112773895264, "step": 369770 }, { "epoch": 2.1980491110437432, "grad_norm": 1.5472544431686401, "learning_rate": 5.6420340257339955e-05, "loss": 0.4889021396636963, "step": 369780 }, { "epoch": 2.1981085531204116, "grad_norm": 1.54495108127594, "learning_rate": 5.6415338897733296e-05, "loss": 0.5375056266784668, "step": 369790 }, { "epoch": 2.19816799519708, "grad_norm": 0.9821726083755493, "learning_rate": 5.6410337794458146e-05, "loss": 0.43497657775878906, "step": 369800 }, { "epoch": 2.1982274372737485, "grad_norm": 1.3240466117858887, "learning_rate": 5.64053369475384e-05, "loss": 0.5028307914733887, "step": 369810 }, { "epoch": 2.198286879350417, "grad_norm": 1.0540509223937988, "learning_rate": 5.640033635699806e-05, "loss": 0.5003679275512696, "step": 369820 }, { "epoch": 2.1983463214270853, "grad_norm": 1.1734278202056885, "learning_rate": 5.6395336022860955e-05, "loss": 0.4754836082458496, "step": 369830 }, { "epoch": 2.1984057635037537, "grad_norm": 1.429062008857727, "learning_rate": 5.639033594515103e-05, "loss": 0.5111599445343018, "step": 369840 }, { "epoch": 2.198465205580422, "grad_norm": 1.4033327102661133, "learning_rate": 5.638533612389225e-05, "loss": 0.5506282806396484, "step": 369850 }, { "epoch": 2.1985246476570905, "grad_norm": 1.4453240633010864, "learning_rate": 5.6380336559108496e-05, "loss": 0.46899900436401365, "step": 369860 }, { "epoch": 2.198584089733759, "grad_norm": 1.4761180877685547, "learning_rate": 5.637533725082369e-05, "loss": 0.475559139251709, "step": 369870 }, { "epoch": 2.1986435318104274, "grad_norm": 1.2355765104293823, "learning_rate": 5.6370338199061743e-05, "loss": 0.5100939273834229, "step": 369880 }, { "epoch": 2.198702973887096, "grad_norm": 1.3836333751678467, "learning_rate": 5.636533940384656e-05, "loss": 0.48108701705932616, "step": 369890 }, { "epoch": 2.198762415963764, "grad_norm": 1.1988731622695923, "learning_rate": 5.6360340865202074e-05, "loss": 0.4944277763366699, "step": 369900 }, { "epoch": 2.1988218580404326, "grad_norm": 1.427937626838684, "learning_rate": 5.635534258315217e-05, "loss": 0.46286497116088865, "step": 369910 }, { "epoch": 2.198881300117101, "grad_norm": 1.2440340518951416, "learning_rate": 5.635034455772079e-05, "loss": 0.5066900253295898, "step": 369920 }, { "epoch": 2.1989407421937694, "grad_norm": 1.5608274936676025, "learning_rate": 5.6345346788931844e-05, "loss": 0.514101219177246, "step": 369930 }, { "epoch": 2.199000184270438, "grad_norm": 1.1271826028823853, "learning_rate": 5.634034927680921e-05, "loss": 0.46434998512268066, "step": 369940 }, { "epoch": 2.199059626347106, "grad_norm": 1.3287439346313477, "learning_rate": 5.633535202137682e-05, "loss": 0.4909733772277832, "step": 369950 }, { "epoch": 2.1991190684237742, "grad_norm": 1.3618601560592651, "learning_rate": 5.6330355022658554e-05, "loss": 0.506895923614502, "step": 369960 }, { "epoch": 2.1991785105004427, "grad_norm": 1.4240456819534302, "learning_rate": 5.6325358280678305e-05, "loss": 0.49321837425231935, "step": 369970 }, { "epoch": 2.199237952577111, "grad_norm": 1.298563838005066, "learning_rate": 5.6320361795460056e-05, "loss": 0.4935322284698486, "step": 369980 }, { "epoch": 2.1992973946537795, "grad_norm": 1.2735003232955933, "learning_rate": 5.631536556702762e-05, "loss": 0.5357451438903809, "step": 369990 }, { "epoch": 2.199356836730448, "grad_norm": 1.3379803895950317, "learning_rate": 5.631036959540494e-05, "loss": 0.459873628616333, "step": 370000 }, { "epoch": 2.1994162788071163, "grad_norm": 1.4262816905975342, "learning_rate": 5.630537388061592e-05, "loss": 0.5192901611328125, "step": 370010 }, { "epoch": 2.1994757208837847, "grad_norm": 1.4665088653564453, "learning_rate": 5.630037842268443e-05, "loss": 0.516818618774414, "step": 370020 }, { "epoch": 2.199535162960453, "grad_norm": 1.4882322549819946, "learning_rate": 5.629538322163438e-05, "loss": 0.46014909744262694, "step": 370030 }, { "epoch": 2.1995946050371216, "grad_norm": 1.6115792989730835, "learning_rate": 5.629038827748964e-05, "loss": 0.4882380485534668, "step": 370040 }, { "epoch": 2.19965404711379, "grad_norm": 1.286759376525879, "learning_rate": 5.628539359027416e-05, "loss": 0.5282596111297607, "step": 370050 }, { "epoch": 2.1997134891904584, "grad_norm": 1.6189175844192505, "learning_rate": 5.6280399160011796e-05, "loss": 0.5108428955078125, "step": 370060 }, { "epoch": 2.199772931267127, "grad_norm": 1.0395468473434448, "learning_rate": 5.627540498672645e-05, "loss": 0.4645477294921875, "step": 370070 }, { "epoch": 2.1998323733437952, "grad_norm": 1.2337220907211304, "learning_rate": 5.627041107044202e-05, "loss": 0.4727898597717285, "step": 370080 }, { "epoch": 2.1998918154204636, "grad_norm": 1.6396832466125488, "learning_rate": 5.626541741118238e-05, "loss": 0.5114076614379883, "step": 370090 }, { "epoch": 2.199951257497132, "grad_norm": 1.4199920892715454, "learning_rate": 5.626042400897138e-05, "loss": 0.5080170631408691, "step": 370100 }, { "epoch": 2.2000106995738005, "grad_norm": 1.6417745351791382, "learning_rate": 5.625543086383299e-05, "loss": 0.47375192642211916, "step": 370110 }, { "epoch": 2.200070141650469, "grad_norm": 1.577776551246643, "learning_rate": 5.625043797579105e-05, "loss": 0.49857273101806643, "step": 370120 }, { "epoch": 2.2001295837271373, "grad_norm": 1.1256548166275024, "learning_rate": 5.624544534486948e-05, "loss": 0.46755223274230956, "step": 370130 }, { "epoch": 2.2001890258038053, "grad_norm": 1.530942440032959, "learning_rate": 5.624045297109208e-05, "loss": 0.5411290168762207, "step": 370140 }, { "epoch": 2.2002484678804737, "grad_norm": 1.0797330141067505, "learning_rate": 5.62354608544828e-05, "loss": 0.5008046150207519, "step": 370150 }, { "epoch": 2.200307909957142, "grad_norm": 1.141694188117981, "learning_rate": 5.623046899506552e-05, "loss": 0.5371269702911377, "step": 370160 }, { "epoch": 2.2003673520338105, "grad_norm": 0.9921367168426514, "learning_rate": 5.6225477392864055e-05, "loss": 0.4944169521331787, "step": 370170 }, { "epoch": 2.200426794110479, "grad_norm": 1.324318289756775, "learning_rate": 5.6220486047902386e-05, "loss": 0.5120053291320801, "step": 370180 }, { "epoch": 2.2004862361871473, "grad_norm": 1.4081553220748901, "learning_rate": 5.621549496020435e-05, "loss": 0.5055906772613525, "step": 370190 }, { "epoch": 2.2005456782638158, "grad_norm": 1.47953462600708, "learning_rate": 5.621050412979376e-05, "loss": 0.5349127769470214, "step": 370200 }, { "epoch": 2.200605120340484, "grad_norm": 1.4964178800582886, "learning_rate": 5.620551355669457e-05, "loss": 0.4583484649658203, "step": 370210 }, { "epoch": 2.2006645624171526, "grad_norm": 1.3201791048049927, "learning_rate": 5.6200523240930615e-05, "loss": 0.5141862392425537, "step": 370220 }, { "epoch": 2.200724004493821, "grad_norm": 1.3137727975845337, "learning_rate": 5.6195533182525725e-05, "loss": 0.47940797805786134, "step": 370230 }, { "epoch": 2.2007834465704894, "grad_norm": 1.4336438179016113, "learning_rate": 5.619054338150389e-05, "loss": 0.5262625694274903, "step": 370240 }, { "epoch": 2.200842888647158, "grad_norm": 1.2825595140457153, "learning_rate": 5.6185553837888926e-05, "loss": 0.46196718215942384, "step": 370250 }, { "epoch": 2.2009023307238262, "grad_norm": 1.2699254751205444, "learning_rate": 5.618056455170464e-05, "loss": 0.4523932456970215, "step": 370260 }, { "epoch": 2.2009617728004947, "grad_norm": 1.2063909769058228, "learning_rate": 5.617557552297493e-05, "loss": 0.48816561698913574, "step": 370270 }, { "epoch": 2.201021214877163, "grad_norm": 1.4378770589828491, "learning_rate": 5.617058675172371e-05, "loss": 0.4886582374572754, "step": 370280 }, { "epoch": 2.2010806569538315, "grad_norm": 1.1189217567443848, "learning_rate": 5.6165598237974805e-05, "loss": 0.49709348678588866, "step": 370290 }, { "epoch": 2.2011400990305, "grad_norm": 1.5482864379882812, "learning_rate": 5.616060998175206e-05, "loss": 0.4606175899505615, "step": 370300 }, { "epoch": 2.2011995411071683, "grad_norm": 1.5718852281570435, "learning_rate": 5.615562198307942e-05, "loss": 0.49901537895202636, "step": 370310 }, { "epoch": 2.2012589831838367, "grad_norm": 1.4922130107879639, "learning_rate": 5.615063424198064e-05, "loss": 0.47394542694091796, "step": 370320 }, { "epoch": 2.2013184252605047, "grad_norm": 1.1703693866729736, "learning_rate": 5.614564675847962e-05, "loss": 0.46862030029296875, "step": 370330 }, { "epoch": 2.201377867337173, "grad_norm": 1.1775197982788086, "learning_rate": 5.614065953260025e-05, "loss": 0.4752370834350586, "step": 370340 }, { "epoch": 2.2014373094138415, "grad_norm": 1.5595988035202026, "learning_rate": 5.613567256436636e-05, "loss": 0.5580658912658691, "step": 370350 }, { "epoch": 2.20149675149051, "grad_norm": 1.253542423248291, "learning_rate": 5.613068585380181e-05, "loss": 0.4730380058288574, "step": 370360 }, { "epoch": 2.2015561935671784, "grad_norm": 0.9975476861000061, "learning_rate": 5.612569940093046e-05, "loss": 0.5377717018127441, "step": 370370 }, { "epoch": 2.2016156356438468, "grad_norm": 1.202646255493164, "learning_rate": 5.6120713205776146e-05, "loss": 0.5177427291870117, "step": 370380 }, { "epoch": 2.201675077720515, "grad_norm": 1.4334995746612549, "learning_rate": 5.611572726836274e-05, "loss": 0.5346922397613525, "step": 370390 }, { "epoch": 2.2017345197971836, "grad_norm": 1.5538700819015503, "learning_rate": 5.611074158871406e-05, "loss": 0.5145299911499024, "step": 370400 }, { "epoch": 2.201793961873852, "grad_norm": 1.0314112901687622, "learning_rate": 5.6105756166854e-05, "loss": 0.45552854537963866, "step": 370410 }, { "epoch": 2.2018534039505204, "grad_norm": 1.3586857318878174, "learning_rate": 5.6100771002806394e-05, "loss": 0.509112024307251, "step": 370420 }, { "epoch": 2.201912846027189, "grad_norm": 1.669227957725525, "learning_rate": 5.6095786096595096e-05, "loss": 0.5270529747009277, "step": 370430 }, { "epoch": 2.2019722881038573, "grad_norm": 1.313562273979187, "learning_rate": 5.6090801448243925e-05, "loss": 0.5342864990234375, "step": 370440 }, { "epoch": 2.2020317301805257, "grad_norm": 1.0762803554534912, "learning_rate": 5.608581705777676e-05, "loss": 0.49577507972717283, "step": 370450 }, { "epoch": 2.202091172257194, "grad_norm": 1.8565326929092407, "learning_rate": 5.6080832925217376e-05, "loss": 0.47585287094116213, "step": 370460 }, { "epoch": 2.2021506143338625, "grad_norm": 1.3221060037612915, "learning_rate": 5.6075849050589704e-05, "loss": 0.48745098114013674, "step": 370470 }, { "epoch": 2.202210056410531, "grad_norm": 1.3724486827850342, "learning_rate": 5.6070865433917553e-05, "loss": 0.47725515365600585, "step": 370480 }, { "epoch": 2.2022694984871993, "grad_norm": 1.6846450567245483, "learning_rate": 5.606588207522474e-05, "loss": 0.5182687759399414, "step": 370490 }, { "epoch": 2.2023289405638677, "grad_norm": 1.1427394151687622, "learning_rate": 5.606089897453515e-05, "loss": 0.44645094871520996, "step": 370500 }, { "epoch": 2.202388382640536, "grad_norm": 1.04484224319458, "learning_rate": 5.605591613187258e-05, "loss": 0.47960643768310546, "step": 370510 }, { "epoch": 2.202447824717204, "grad_norm": 1.7611145973205566, "learning_rate": 5.605093354726088e-05, "loss": 0.47884039878845214, "step": 370520 }, { "epoch": 2.2025072667938725, "grad_norm": 1.289702296257019, "learning_rate": 5.604595122072383e-05, "loss": 0.4986750602722168, "step": 370530 }, { "epoch": 2.202566708870541, "grad_norm": 1.5292364358901978, "learning_rate": 5.604096915228536e-05, "loss": 0.5144780158996582, "step": 370540 }, { "epoch": 2.2026261509472094, "grad_norm": 1.478635311126709, "learning_rate": 5.6035987341969266e-05, "loss": 0.49571905136108396, "step": 370550 }, { "epoch": 2.202685593023878, "grad_norm": 1.531803011894226, "learning_rate": 5.6031005789799385e-05, "loss": 0.5212449073791504, "step": 370560 }, { "epoch": 2.202745035100546, "grad_norm": 1.1658285856246948, "learning_rate": 5.602602449579952e-05, "loss": 0.4581589221954346, "step": 370570 }, { "epoch": 2.2028044771772146, "grad_norm": 1.2660548686981201, "learning_rate": 5.60210434599935e-05, "loss": 0.45651817321777344, "step": 370580 }, { "epoch": 2.202863919253883, "grad_norm": 1.7335931062698364, "learning_rate": 5.6016062682405165e-05, "loss": 0.488651180267334, "step": 370590 }, { "epoch": 2.2029233613305514, "grad_norm": 1.0326930284500122, "learning_rate": 5.601108216305837e-05, "loss": 0.45107035636901854, "step": 370600 }, { "epoch": 2.20298280340722, "grad_norm": 1.4759478569030762, "learning_rate": 5.600610190197691e-05, "loss": 0.5300890445709229, "step": 370610 }, { "epoch": 2.2030422454838883, "grad_norm": 1.0627589225769043, "learning_rate": 5.60011218991846e-05, "loss": 0.4769566535949707, "step": 370620 }, { "epoch": 2.2031016875605567, "grad_norm": 1.1601330041885376, "learning_rate": 5.599614215470529e-05, "loss": 0.4928700923919678, "step": 370630 }, { "epoch": 2.203161129637225, "grad_norm": 1.554733395576477, "learning_rate": 5.599116266856279e-05, "loss": 0.516145133972168, "step": 370640 }, { "epoch": 2.2032205717138935, "grad_norm": 1.3799784183502197, "learning_rate": 5.5986183440780905e-05, "loss": 0.5294718742370605, "step": 370650 }, { "epoch": 2.203280013790562, "grad_norm": 1.458417534828186, "learning_rate": 5.598120447138344e-05, "loss": 0.5460627555847168, "step": 370660 }, { "epoch": 2.2033394558672303, "grad_norm": 1.5354728698730469, "learning_rate": 5.597622576039427e-05, "loss": 0.47777667045593264, "step": 370670 }, { "epoch": 2.2033988979438988, "grad_norm": 1.54351806640625, "learning_rate": 5.597124730783718e-05, "loss": 0.4880842208862305, "step": 370680 }, { "epoch": 2.2034583400205667, "grad_norm": 1.7328380346298218, "learning_rate": 5.5966269113735994e-05, "loss": 0.5473089218139648, "step": 370690 }, { "epoch": 2.203517782097235, "grad_norm": 1.250887393951416, "learning_rate": 5.5961291178114506e-05, "loss": 0.5265541076660156, "step": 370700 }, { "epoch": 2.2035772241739036, "grad_norm": 1.2342429161071777, "learning_rate": 5.595631350099655e-05, "loss": 0.5052495479583741, "step": 370710 }, { "epoch": 2.203636666250572, "grad_norm": 1.3464369773864746, "learning_rate": 5.5951336082405924e-05, "loss": 0.45300731658935545, "step": 370720 }, { "epoch": 2.2036961083272404, "grad_norm": 1.1298953294754028, "learning_rate": 5.594635892236641e-05, "loss": 0.44094252586364746, "step": 370730 }, { "epoch": 2.203755550403909, "grad_norm": 1.3283568620681763, "learning_rate": 5.594138202090193e-05, "loss": 0.5137673377990722, "step": 370740 }, { "epoch": 2.203814992480577, "grad_norm": 2.058868885040283, "learning_rate": 5.5936405378036174e-05, "loss": 0.5317558288574219, "step": 370750 }, { "epoch": 2.2038744345572456, "grad_norm": 1.121714472770691, "learning_rate": 5.5931428993792946e-05, "loss": 0.465891170501709, "step": 370760 }, { "epoch": 2.203933876633914, "grad_norm": 1.234585165977478, "learning_rate": 5.592645286819611e-05, "loss": 0.4909368515014648, "step": 370770 }, { "epoch": 2.2039933187105825, "grad_norm": 1.4770315885543823, "learning_rate": 5.5921477001269486e-05, "loss": 0.5207468032836914, "step": 370780 }, { "epoch": 2.204052760787251, "grad_norm": 1.4309828281402588, "learning_rate": 5.591650139303679e-05, "loss": 0.4665863513946533, "step": 370790 }, { "epoch": 2.2041122028639193, "grad_norm": 1.4115029573440552, "learning_rate": 5.5911526043521935e-05, "loss": 0.5177145004272461, "step": 370800 }, { "epoch": 2.2041716449405877, "grad_norm": 1.0741605758666992, "learning_rate": 5.590655095274864e-05, "loss": 0.4813982009887695, "step": 370810 }, { "epoch": 2.204231087017256, "grad_norm": 1.7072855234146118, "learning_rate": 5.590157612074069e-05, "loss": 0.5383203506469727, "step": 370820 }, { "epoch": 2.2042905290939245, "grad_norm": 1.7489583492279053, "learning_rate": 5.589660154752197e-05, "loss": 0.5057077407836914, "step": 370830 }, { "epoch": 2.204349971170593, "grad_norm": 0.9842336773872375, "learning_rate": 5.5891627233116206e-05, "loss": 0.49254584312438965, "step": 370840 }, { "epoch": 2.2044094132472614, "grad_norm": 1.6263775825500488, "learning_rate": 5.588665317754722e-05, "loss": 0.5068164348602295, "step": 370850 }, { "epoch": 2.2044688553239298, "grad_norm": 0.8944374918937683, "learning_rate": 5.588167938083881e-05, "loss": 0.48026461601257325, "step": 370860 }, { "epoch": 2.204528297400598, "grad_norm": 1.390944242477417, "learning_rate": 5.5876705843014745e-05, "loss": 0.49390735626220705, "step": 370870 }, { "epoch": 2.204587739477266, "grad_norm": 1.194930911064148, "learning_rate": 5.587173256409885e-05, "loss": 0.44342989921569825, "step": 370880 }, { "epoch": 2.2046471815539346, "grad_norm": 1.5955917835235596, "learning_rate": 5.586675954411484e-05, "loss": 0.5221817970275879, "step": 370890 }, { "epoch": 2.204706623630603, "grad_norm": 1.2234245538711548, "learning_rate": 5.5861786783086625e-05, "loss": 0.5696266174316407, "step": 370900 }, { "epoch": 2.2047660657072714, "grad_norm": 1.4462194442749023, "learning_rate": 5.5856814281037904e-05, "loss": 0.49951581954956054, "step": 370910 }, { "epoch": 2.20482550778394, "grad_norm": 1.626431941986084, "learning_rate": 5.58518420379925e-05, "loss": 0.4538140296936035, "step": 370920 }, { "epoch": 2.2048849498606082, "grad_norm": 1.4254719018936157, "learning_rate": 5.584687005397418e-05, "loss": 0.44997224807739256, "step": 370930 }, { "epoch": 2.2049443919372766, "grad_norm": 1.5525338649749756, "learning_rate": 5.5841898329006746e-05, "loss": 0.524053955078125, "step": 370940 }, { "epoch": 2.205003834013945, "grad_norm": 1.1626092195510864, "learning_rate": 5.583692686311395e-05, "loss": 0.5045354843139649, "step": 370950 }, { "epoch": 2.2050632760906135, "grad_norm": 1.7290688753128052, "learning_rate": 5.5831955656319603e-05, "loss": 0.5433917999267578, "step": 370960 }, { "epoch": 2.205122718167282, "grad_norm": 1.4274054765701294, "learning_rate": 5.582698470864749e-05, "loss": 0.5066168785095215, "step": 370970 }, { "epoch": 2.2051821602439503, "grad_norm": 1.4732733964920044, "learning_rate": 5.582201402012137e-05, "loss": 0.4421850204467773, "step": 370980 }, { "epoch": 2.2052416023206187, "grad_norm": 1.4333614110946655, "learning_rate": 5.581704359076503e-05, "loss": 0.5122249603271485, "step": 370990 }, { "epoch": 2.205301044397287, "grad_norm": 1.5852702856063843, "learning_rate": 5.581207342060226e-05, "loss": 0.5006171226501465, "step": 371000 }, { "epoch": 2.2053604864739556, "grad_norm": 1.4988809823989868, "learning_rate": 5.580710350965681e-05, "loss": 0.4906907081604004, "step": 371010 }, { "epoch": 2.205419928550624, "grad_norm": 0.9569265842437744, "learning_rate": 5.5802133857952445e-05, "loss": 0.44991841316223147, "step": 371020 }, { "epoch": 2.2054793706272924, "grad_norm": 1.0814539194107056, "learning_rate": 5.5797164465512973e-05, "loss": 0.5108010292053222, "step": 371030 }, { "epoch": 2.205538812703961, "grad_norm": 1.272796630859375, "learning_rate": 5.579219533236217e-05, "loss": 0.5075471878051758, "step": 371040 }, { "epoch": 2.205598254780629, "grad_norm": 1.5045939683914185, "learning_rate": 5.578722645852379e-05, "loss": 0.5308583736419678, "step": 371050 }, { "epoch": 2.2056576968572976, "grad_norm": 1.4825552701950073, "learning_rate": 5.578225784402158e-05, "loss": 0.49566221237182617, "step": 371060 }, { "epoch": 2.2057171389339656, "grad_norm": 1.256378173828125, "learning_rate": 5.5777289488879345e-05, "loss": 0.458695125579834, "step": 371070 }, { "epoch": 2.205776581010634, "grad_norm": 0.9198039770126343, "learning_rate": 5.577232139312081e-05, "loss": 0.47011265754699705, "step": 371080 }, { "epoch": 2.2058360230873024, "grad_norm": 1.0331889390945435, "learning_rate": 5.576735355676979e-05, "loss": 0.470532751083374, "step": 371090 }, { "epoch": 2.205895465163971, "grad_norm": 1.4766926765441895, "learning_rate": 5.576238597985004e-05, "loss": 0.49532480239868165, "step": 371100 }, { "epoch": 2.2059549072406393, "grad_norm": 2.475550651550293, "learning_rate": 5.5757418662385286e-05, "loss": 0.5240020275115966, "step": 371110 }, { "epoch": 2.2060143493173077, "grad_norm": 1.1091755628585815, "learning_rate": 5.5752451604399334e-05, "loss": 0.5080139636993408, "step": 371120 }, { "epoch": 2.206073791393976, "grad_norm": 1.475278377532959, "learning_rate": 5.5747484805915926e-05, "loss": 0.5148860454559326, "step": 371130 }, { "epoch": 2.2061332334706445, "grad_norm": 1.4590699672698975, "learning_rate": 5.574251826695882e-05, "loss": 0.48223209381103516, "step": 371140 }, { "epoch": 2.206192675547313, "grad_norm": 1.3976705074310303, "learning_rate": 5.573755198755174e-05, "loss": 0.481303071975708, "step": 371150 }, { "epoch": 2.2062521176239813, "grad_norm": 1.1594440937042236, "learning_rate": 5.573258596771851e-05, "loss": 0.49629859924316405, "step": 371160 }, { "epoch": 2.2063115597006497, "grad_norm": 1.5224273204803467, "learning_rate": 5.5727620207482855e-05, "loss": 0.48452119827270507, "step": 371170 }, { "epoch": 2.206371001777318, "grad_norm": 1.6188160181045532, "learning_rate": 5.5722654706868526e-05, "loss": 0.49883184432983396, "step": 371180 }, { "epoch": 2.2064304438539866, "grad_norm": 1.5211213827133179, "learning_rate": 5.571768946589928e-05, "loss": 0.5091156959533691, "step": 371190 }, { "epoch": 2.206489885930655, "grad_norm": 1.494699239730835, "learning_rate": 5.571272448459886e-05, "loss": 0.5432682514190674, "step": 371200 }, { "epoch": 2.2065493280073234, "grad_norm": 1.3085886240005493, "learning_rate": 5.570775976299103e-05, "loss": 0.4832120418548584, "step": 371210 }, { "epoch": 2.206608770083992, "grad_norm": 1.099788784980774, "learning_rate": 5.570279530109951e-05, "loss": 0.4652690887451172, "step": 371220 }, { "epoch": 2.2066682121606602, "grad_norm": 1.743334174156189, "learning_rate": 5.5697831098948104e-05, "loss": 0.524718952178955, "step": 371230 }, { "epoch": 2.2067276542373286, "grad_norm": 1.6985249519348145, "learning_rate": 5.5692867156560555e-05, "loss": 0.4858144760131836, "step": 371240 }, { "epoch": 2.206787096313997, "grad_norm": 1.1429904699325562, "learning_rate": 5.568790347396051e-05, "loss": 0.4418465614318848, "step": 371250 }, { "epoch": 2.206846538390665, "grad_norm": 1.1533385515213013, "learning_rate": 5.5682940051171826e-05, "loss": 0.5450314998626709, "step": 371260 }, { "epoch": 2.2069059804673334, "grad_norm": 1.2604308128356934, "learning_rate": 5.567797688821821e-05, "loss": 0.5484525680541992, "step": 371270 }, { "epoch": 2.206965422544002, "grad_norm": 1.302534580230713, "learning_rate": 5.567301398512337e-05, "loss": 0.5096533298492432, "step": 371280 }, { "epoch": 2.2070248646206703, "grad_norm": 1.9203927516937256, "learning_rate": 5.5668051341911086e-05, "loss": 0.5727985382080079, "step": 371290 }, { "epoch": 2.2070843066973387, "grad_norm": 1.6054686307907104, "learning_rate": 5.566308895860515e-05, "loss": 0.4798318862915039, "step": 371300 }, { "epoch": 2.207143748774007, "grad_norm": 1.5889238119125366, "learning_rate": 5.565812683522915e-05, "loss": 0.509460735321045, "step": 371310 }, { "epoch": 2.2072031908506755, "grad_norm": 1.2126885652542114, "learning_rate": 5.565316497180696e-05, "loss": 0.4984092712402344, "step": 371320 }, { "epoch": 2.207262632927344, "grad_norm": 1.1961623430252075, "learning_rate": 5.564820336836227e-05, "loss": 0.4781291961669922, "step": 371330 }, { "epoch": 2.2073220750040123, "grad_norm": 1.4676145315170288, "learning_rate": 5.56432420249188e-05, "loss": 0.4911014556884766, "step": 371340 }, { "epoch": 2.2073815170806808, "grad_norm": 1.36918044090271, "learning_rate": 5.563828094150031e-05, "loss": 0.4790172576904297, "step": 371350 }, { "epoch": 2.207440959157349, "grad_norm": 1.5220935344696045, "learning_rate": 5.5633320118130504e-05, "loss": 0.5361128330230713, "step": 371360 }, { "epoch": 2.2075004012340176, "grad_norm": 1.0275166034698486, "learning_rate": 5.562835955483314e-05, "loss": 0.5231274604797364, "step": 371370 }, { "epoch": 2.207559843310686, "grad_norm": 1.432562232017517, "learning_rate": 5.562339925163189e-05, "loss": 0.5380607604980469, "step": 371380 }, { "epoch": 2.2076192853873544, "grad_norm": 1.5595932006835938, "learning_rate": 5.5618439208550566e-05, "loss": 0.5306303024291992, "step": 371390 }, { "epoch": 2.207678727464023, "grad_norm": 1.8543270826339722, "learning_rate": 5.5613479425612854e-05, "loss": 0.4896102428436279, "step": 371400 }, { "epoch": 2.2077381695406912, "grad_norm": 1.1107807159423828, "learning_rate": 5.560851990284249e-05, "loss": 0.45272417068481446, "step": 371410 }, { "epoch": 2.2077976116173597, "grad_norm": 1.0928895473480225, "learning_rate": 5.560356064026319e-05, "loss": 0.48071794509887694, "step": 371420 }, { "epoch": 2.2078570536940276, "grad_norm": 1.0993199348449707, "learning_rate": 5.5598601637898686e-05, "loss": 0.4546513557434082, "step": 371430 }, { "epoch": 2.207916495770696, "grad_norm": 1.644456148147583, "learning_rate": 5.559364289577264e-05, "loss": 0.538443660736084, "step": 371440 }, { "epoch": 2.2079759378473645, "grad_norm": 1.3494428396224976, "learning_rate": 5.558868441390888e-05, "loss": 0.47993764877319334, "step": 371450 }, { "epoch": 2.208035379924033, "grad_norm": 1.4191863536834717, "learning_rate": 5.5583726192331054e-05, "loss": 0.5199833393096924, "step": 371460 }, { "epoch": 2.2080948220007013, "grad_norm": 1.342748999595642, "learning_rate": 5.557876823106291e-05, "loss": 0.5254387378692627, "step": 371470 }, { "epoch": 2.2081542640773697, "grad_norm": 1.1519814729690552, "learning_rate": 5.5573810530128154e-05, "loss": 0.44117107391357424, "step": 371480 }, { "epoch": 2.208213706154038, "grad_norm": 1.21950364112854, "learning_rate": 5.5568853089550485e-05, "loss": 0.48943290710449217, "step": 371490 }, { "epoch": 2.2082731482307065, "grad_norm": 1.5774720907211304, "learning_rate": 5.556389590935366e-05, "loss": 0.45673885345458987, "step": 371500 }, { "epoch": 2.208332590307375, "grad_norm": 1.3131223917007446, "learning_rate": 5.5558938989561316e-05, "loss": 0.4736508369445801, "step": 371510 }, { "epoch": 2.2083920323840434, "grad_norm": 1.355973243713379, "learning_rate": 5.555398233019725e-05, "loss": 0.5238624572753906, "step": 371520 }, { "epoch": 2.2084514744607118, "grad_norm": 1.0134243965148926, "learning_rate": 5.554902593128515e-05, "loss": 0.5262445449829102, "step": 371530 }, { "epoch": 2.20851091653738, "grad_norm": 1.410987377166748, "learning_rate": 5.554406979284871e-05, "loss": 0.547864580154419, "step": 371540 }, { "epoch": 2.2085703586140486, "grad_norm": 1.4407349824905396, "learning_rate": 5.553911391491165e-05, "loss": 0.5132619857788085, "step": 371550 }, { "epoch": 2.208629800690717, "grad_norm": 1.3850500583648682, "learning_rate": 5.553415829749765e-05, "loss": 0.5139243125915527, "step": 371560 }, { "epoch": 2.2086892427673854, "grad_norm": 1.4808183908462524, "learning_rate": 5.552920294063046e-05, "loss": 0.4829393863677979, "step": 371570 }, { "epoch": 2.208748684844054, "grad_norm": 1.3253371715545654, "learning_rate": 5.552424784433372e-05, "loss": 0.5131784915924072, "step": 371580 }, { "epoch": 2.2088081269207223, "grad_norm": 1.4698057174682617, "learning_rate": 5.5519293008631215e-05, "loss": 0.5240476608276368, "step": 371590 }, { "epoch": 2.2088675689973907, "grad_norm": 1.306395173072815, "learning_rate": 5.55143384335466e-05, "loss": 0.4834113121032715, "step": 371600 }, { "epoch": 2.208927011074059, "grad_norm": 1.4289170503616333, "learning_rate": 5.550938411910358e-05, "loss": 0.5402896881103516, "step": 371610 }, { "epoch": 2.208986453150727, "grad_norm": 1.3554320335388184, "learning_rate": 5.550443006532586e-05, "loss": 0.49043979644775393, "step": 371620 }, { "epoch": 2.2090458952273955, "grad_norm": 1.701781988143921, "learning_rate": 5.549947627223714e-05, "loss": 0.54019193649292, "step": 371630 }, { "epoch": 2.209105337304064, "grad_norm": 1.4376955032348633, "learning_rate": 5.549452273986109e-05, "loss": 0.5476532936096191, "step": 371640 }, { "epoch": 2.2091647793807323, "grad_norm": 1.1323339939117432, "learning_rate": 5.5489569468221456e-05, "loss": 0.497076416015625, "step": 371650 }, { "epoch": 2.2092242214574007, "grad_norm": 1.3596253395080566, "learning_rate": 5.548461645734191e-05, "loss": 0.5907234191894531, "step": 371660 }, { "epoch": 2.209283663534069, "grad_norm": 1.425262212753296, "learning_rate": 5.547966370724613e-05, "loss": 0.4976752758026123, "step": 371670 }, { "epoch": 2.2093431056107375, "grad_norm": 1.1407768726348877, "learning_rate": 5.547471121795784e-05, "loss": 0.4948162078857422, "step": 371680 }, { "epoch": 2.209402547687406, "grad_norm": 1.5360876321792603, "learning_rate": 5.546975898950071e-05, "loss": 0.4632271766662598, "step": 371690 }, { "epoch": 2.2094619897640744, "grad_norm": 1.077924370765686, "learning_rate": 5.546480702189842e-05, "loss": 0.49740943908691404, "step": 371700 }, { "epoch": 2.209521431840743, "grad_norm": 1.3634936809539795, "learning_rate": 5.545985531517465e-05, "loss": 0.5198892116546631, "step": 371710 }, { "epoch": 2.209580873917411, "grad_norm": 1.3033603429794312, "learning_rate": 5.5454903869353124e-05, "loss": 0.50069580078125, "step": 371720 }, { "epoch": 2.2096403159940796, "grad_norm": 1.4459000825881958, "learning_rate": 5.5449952684457565e-05, "loss": 0.5083556652069092, "step": 371730 }, { "epoch": 2.209699758070748, "grad_norm": 1.5979228019714355, "learning_rate": 5.5445001760511525e-05, "loss": 0.5264739036560059, "step": 371740 }, { "epoch": 2.2097592001474164, "grad_norm": 1.6623919010162354, "learning_rate": 5.5440051097538816e-05, "loss": 0.46022677421569824, "step": 371750 }, { "epoch": 2.209818642224085, "grad_norm": 1.0991607904434204, "learning_rate": 5.543510069556306e-05, "loss": 0.4920970439910889, "step": 371760 }, { "epoch": 2.2098780843007533, "grad_norm": 1.3446546792984009, "learning_rate": 5.543015055460792e-05, "loss": 0.5054844856262207, "step": 371770 }, { "epoch": 2.2099375263774217, "grad_norm": 1.1130191087722778, "learning_rate": 5.542520067469714e-05, "loss": 0.44862003326416017, "step": 371780 }, { "epoch": 2.20999696845409, "grad_norm": 1.1980513334274292, "learning_rate": 5.54202510558544e-05, "loss": 0.48728103637695314, "step": 371790 }, { "epoch": 2.2100564105307585, "grad_norm": 1.4443033933639526, "learning_rate": 5.541530169810327e-05, "loss": 0.5433046340942382, "step": 371800 }, { "epoch": 2.2101158526074265, "grad_norm": 1.2206177711486816, "learning_rate": 5.541035260146753e-05, "loss": 0.5285704612731934, "step": 371810 }, { "epoch": 2.210175294684095, "grad_norm": 1.4919203519821167, "learning_rate": 5.540540376597083e-05, "loss": 0.5207428455352783, "step": 371820 }, { "epoch": 2.2102347367607633, "grad_norm": 1.2846946716308594, "learning_rate": 5.5400455191636836e-05, "loss": 0.45244565010070803, "step": 371830 }, { "epoch": 2.2102941788374317, "grad_norm": 1.586925983428955, "learning_rate": 5.539550687848919e-05, "loss": 0.5499953269958496, "step": 371840 }, { "epoch": 2.2103536209141, "grad_norm": 1.001990556716919, "learning_rate": 5.539055882655165e-05, "loss": 0.48464193344116213, "step": 371850 }, { "epoch": 2.2104130629907686, "grad_norm": 1.557916283607483, "learning_rate": 5.538561103584781e-05, "loss": 0.5213890552520752, "step": 371860 }, { "epoch": 2.210472505067437, "grad_norm": 1.1983540058135986, "learning_rate": 5.538066350640132e-05, "loss": 0.44632883071899415, "step": 371870 }, { "epoch": 2.2105319471441054, "grad_norm": 1.1676764488220215, "learning_rate": 5.537571623823592e-05, "loss": 0.4438614368438721, "step": 371880 }, { "epoch": 2.210591389220774, "grad_norm": 1.3803796768188477, "learning_rate": 5.537076923137523e-05, "loss": 0.4779604434967041, "step": 371890 }, { "epoch": 2.210650831297442, "grad_norm": 1.6470935344696045, "learning_rate": 5.5365822485842924e-05, "loss": 0.5059800624847413, "step": 371900 }, { "epoch": 2.2107102733741106, "grad_norm": 1.2685575485229492, "learning_rate": 5.53608760016627e-05, "loss": 0.46966142654418946, "step": 371910 }, { "epoch": 2.210769715450779, "grad_norm": 1.5524235963821411, "learning_rate": 5.5355929778858175e-05, "loss": 0.5020761489868164, "step": 371920 }, { "epoch": 2.2108291575274475, "grad_norm": 1.376106858253479, "learning_rate": 5.5350983817452984e-05, "loss": 0.5037555694580078, "step": 371930 }, { "epoch": 2.210888599604116, "grad_norm": 1.0955089330673218, "learning_rate": 5.5346038117470865e-05, "loss": 0.49784255027770996, "step": 371940 }, { "epoch": 2.2109480416807843, "grad_norm": 1.6180005073547363, "learning_rate": 5.534109267893543e-05, "loss": 0.48831539154052733, "step": 371950 }, { "epoch": 2.2110074837574527, "grad_norm": 1.1908705234527588, "learning_rate": 5.5336147501870364e-05, "loss": 0.49983906745910645, "step": 371960 }, { "epoch": 2.211066925834121, "grad_norm": 1.4931145906448364, "learning_rate": 5.5331202586299294e-05, "loss": 0.49233245849609375, "step": 371970 }, { "epoch": 2.2111263679107895, "grad_norm": 0.9365255236625671, "learning_rate": 5.5326257932245886e-05, "loss": 0.4666910171508789, "step": 371980 }, { "epoch": 2.211185809987458, "grad_norm": 1.2083927392959595, "learning_rate": 5.5321313539733775e-05, "loss": 0.45966806411743166, "step": 371990 }, { "epoch": 2.211245252064126, "grad_norm": 1.3768465518951416, "learning_rate": 5.531636940878662e-05, "loss": 0.46740427017211916, "step": 372000 }, { "epoch": 2.2113046941407943, "grad_norm": 1.452029824256897, "learning_rate": 5.5311425539428096e-05, "loss": 0.4577178478240967, "step": 372010 }, { "epoch": 2.2113641362174628, "grad_norm": 1.3685722351074219, "learning_rate": 5.530648193168187e-05, "loss": 0.520195198059082, "step": 372020 }, { "epoch": 2.211423578294131, "grad_norm": 1.1085838079452515, "learning_rate": 5.5301538585571525e-05, "loss": 0.528232192993164, "step": 372030 }, { "epoch": 2.2114830203707996, "grad_norm": 1.1435081958770752, "learning_rate": 5.529659550112076e-05, "loss": 0.5313972473144531, "step": 372040 }, { "epoch": 2.211542462447468, "grad_norm": 1.0993773937225342, "learning_rate": 5.5291652678353214e-05, "loss": 0.5037917613983154, "step": 372050 }, { "epoch": 2.2116019045241364, "grad_norm": 1.6546066999435425, "learning_rate": 5.5286710117292516e-05, "loss": 0.5215750217437745, "step": 372060 }, { "epoch": 2.211661346600805, "grad_norm": 1.1937471628189087, "learning_rate": 5.528176781796227e-05, "loss": 0.5299260139465332, "step": 372070 }, { "epoch": 2.2117207886774732, "grad_norm": 1.5724842548370361, "learning_rate": 5.527682578038622e-05, "loss": 0.4499004364013672, "step": 372080 }, { "epoch": 2.2117802307541417, "grad_norm": 1.4992830753326416, "learning_rate": 5.5271884004587935e-05, "loss": 0.46919403076171873, "step": 372090 }, { "epoch": 2.21183967283081, "grad_norm": 1.6217461824417114, "learning_rate": 5.526694249059108e-05, "loss": 0.5019541263580323, "step": 372100 }, { "epoch": 2.2118991149074785, "grad_norm": 1.2367746829986572, "learning_rate": 5.526200123841929e-05, "loss": 0.48571052551269533, "step": 372110 }, { "epoch": 2.211958556984147, "grad_norm": 1.1738715171813965, "learning_rate": 5.525706024809618e-05, "loss": 0.4904674530029297, "step": 372120 }, { "epoch": 2.2120179990608153, "grad_norm": 1.230960726737976, "learning_rate": 5.525211951964539e-05, "loss": 0.4685244083404541, "step": 372130 }, { "epoch": 2.2120774411374837, "grad_norm": 1.3109856843948364, "learning_rate": 5.524717905309058e-05, "loss": 0.5678618431091309, "step": 372140 }, { "epoch": 2.212136883214152, "grad_norm": 1.1855953931808472, "learning_rate": 5.524223884845539e-05, "loss": 0.5381037712097168, "step": 372150 }, { "epoch": 2.2121963252908206, "grad_norm": 1.362164855003357, "learning_rate": 5.523729890576342e-05, "loss": 0.48656768798828126, "step": 372160 }, { "epoch": 2.2122557673674885, "grad_norm": 1.1745742559432983, "learning_rate": 5.5232359225038336e-05, "loss": 0.4719845771789551, "step": 372170 }, { "epoch": 2.212315209444157, "grad_norm": 1.3020824193954468, "learning_rate": 5.5227419806303725e-05, "loss": 0.4670696258544922, "step": 372180 }, { "epoch": 2.2123746515208254, "grad_norm": 1.8830567598342896, "learning_rate": 5.522248064958325e-05, "loss": 0.48421525955200195, "step": 372190 }, { "epoch": 2.2124340935974938, "grad_norm": 1.1759569644927979, "learning_rate": 5.521754175490049e-05, "loss": 0.5302628993988037, "step": 372200 }, { "epoch": 2.212493535674162, "grad_norm": 1.6594016551971436, "learning_rate": 5.5212603122279135e-05, "loss": 0.4924166679382324, "step": 372210 }, { "epoch": 2.2125529777508306, "grad_norm": 1.2237216234207153, "learning_rate": 5.520766475174283e-05, "loss": 0.46956558227539064, "step": 372220 }, { "epoch": 2.212612419827499, "grad_norm": 1.5540179014205933, "learning_rate": 5.520272664331507e-05, "loss": 0.49897046089172364, "step": 372230 }, { "epoch": 2.2126718619041674, "grad_norm": 1.3780748844146729, "learning_rate": 5.51977887970196e-05, "loss": 0.48189849853515626, "step": 372240 }, { "epoch": 2.212731303980836, "grad_norm": 1.4843517541885376, "learning_rate": 5.519285121287999e-05, "loss": 0.48113317489624025, "step": 372250 }, { "epoch": 2.2127907460575043, "grad_norm": 1.890601396560669, "learning_rate": 5.518791389091984e-05, "loss": 0.47932281494140627, "step": 372260 }, { "epoch": 2.2128501881341727, "grad_norm": 1.3477411270141602, "learning_rate": 5.518297683116285e-05, "loss": 0.48125104904174804, "step": 372270 }, { "epoch": 2.212909630210841, "grad_norm": 1.3839951753616333, "learning_rate": 5.5178040033632584e-05, "loss": 0.5052501678466796, "step": 372280 }, { "epoch": 2.2129690722875095, "grad_norm": 1.6208744049072266, "learning_rate": 5.517310349835261e-05, "loss": 0.5468294620513916, "step": 372290 }, { "epoch": 2.213028514364178, "grad_norm": 1.537330985069275, "learning_rate": 5.5168167225346625e-05, "loss": 0.5154232025146485, "step": 372300 }, { "epoch": 2.2130879564408463, "grad_norm": 1.5734883546829224, "learning_rate": 5.51632312146382e-05, "loss": 0.48399782180786133, "step": 372310 }, { "epoch": 2.2131473985175147, "grad_norm": 1.5640850067138672, "learning_rate": 5.515829546625096e-05, "loss": 0.502105712890625, "step": 372320 }, { "epoch": 2.213206840594183, "grad_norm": 1.1219046115875244, "learning_rate": 5.5153359980208476e-05, "loss": 0.4445630073547363, "step": 372330 }, { "epoch": 2.2132662826708516, "grad_norm": 1.204175591468811, "learning_rate": 5.5148424756534464e-05, "loss": 0.48902645111083987, "step": 372340 }, { "epoch": 2.21332572474752, "grad_norm": 1.3610938787460327, "learning_rate": 5.5143489795252435e-05, "loss": 0.5616926193237305, "step": 372350 }, { "epoch": 2.213385166824188, "grad_norm": 1.4809691905975342, "learning_rate": 5.513855509638598e-05, "loss": 0.49327778816223145, "step": 372360 }, { "epoch": 2.2134446089008564, "grad_norm": 1.0159651041030884, "learning_rate": 5.5133620659958794e-05, "loss": 0.4762229919433594, "step": 372370 }, { "epoch": 2.213504050977525, "grad_norm": 1.5209163427352905, "learning_rate": 5.512868648599442e-05, "loss": 0.5164172172546386, "step": 372380 }, { "epoch": 2.213563493054193, "grad_norm": 1.6471487283706665, "learning_rate": 5.512375257451645e-05, "loss": 0.48624091148376464, "step": 372390 }, { "epoch": 2.2136229351308616, "grad_norm": 1.249976396560669, "learning_rate": 5.5118818925548586e-05, "loss": 0.4646474838256836, "step": 372400 }, { "epoch": 2.21368237720753, "grad_norm": 1.4490489959716797, "learning_rate": 5.511388553911432e-05, "loss": 0.46474542617797854, "step": 372410 }, { "epoch": 2.2137418192841984, "grad_norm": 1.2241381406784058, "learning_rate": 5.510895241523726e-05, "loss": 0.45999650955200194, "step": 372420 }, { "epoch": 2.213801261360867, "grad_norm": 1.3602638244628906, "learning_rate": 5.510401955394107e-05, "loss": 0.492045259475708, "step": 372430 }, { "epoch": 2.2138607034375353, "grad_norm": 1.3941892385482788, "learning_rate": 5.509908695524929e-05, "loss": 0.5020083427429199, "step": 372440 }, { "epoch": 2.2139201455142037, "grad_norm": 1.1471785306930542, "learning_rate": 5.509415461918554e-05, "loss": 0.5004071235656739, "step": 372450 }, { "epoch": 2.213979587590872, "grad_norm": 1.7397119998931885, "learning_rate": 5.5089222545773436e-05, "loss": 0.5015443325042724, "step": 372460 }, { "epoch": 2.2140390296675405, "grad_norm": 1.093862533569336, "learning_rate": 5.5084290735036526e-05, "loss": 0.48106727600097654, "step": 372470 }, { "epoch": 2.214098471744209, "grad_norm": 1.0849376916885376, "learning_rate": 5.507935918699843e-05, "loss": 0.5087804317474365, "step": 372480 }, { "epoch": 2.2141579138208773, "grad_norm": 1.4862669706344604, "learning_rate": 5.507442790168269e-05, "loss": 0.4611999034881592, "step": 372490 }, { "epoch": 2.2142173558975458, "grad_norm": 1.1068658828735352, "learning_rate": 5.506949687911298e-05, "loss": 0.494122314453125, "step": 372500 }, { "epoch": 2.214276797974214, "grad_norm": 0.9660475254058838, "learning_rate": 5.506456611931283e-05, "loss": 0.4418368339538574, "step": 372510 }, { "epoch": 2.2143362400508826, "grad_norm": 1.1715487241744995, "learning_rate": 5.505963562230585e-05, "loss": 0.48679652214050295, "step": 372520 }, { "epoch": 2.214395682127551, "grad_norm": 1.3660178184509277, "learning_rate": 5.5054705388115626e-05, "loss": 0.5055557727813721, "step": 372530 }, { "epoch": 2.2144551242042194, "grad_norm": 1.6747586727142334, "learning_rate": 5.5049775416765724e-05, "loss": 0.4814134120941162, "step": 372540 }, { "epoch": 2.2145145662808874, "grad_norm": 1.5076179504394531, "learning_rate": 5.504484570827976e-05, "loss": 0.49729552268981936, "step": 372550 }, { "epoch": 2.214574008357556, "grad_norm": 1.2464178800582886, "learning_rate": 5.503991626268123e-05, "loss": 0.5013381004333496, "step": 372560 }, { "epoch": 2.214633450434224, "grad_norm": 1.375054121017456, "learning_rate": 5.503498707999384e-05, "loss": 0.5080718517303466, "step": 372570 }, { "epoch": 2.2146928925108926, "grad_norm": 1.3431000709533691, "learning_rate": 5.5030058160241095e-05, "loss": 0.5323570251464844, "step": 372580 }, { "epoch": 2.214752334587561, "grad_norm": 1.506095290184021, "learning_rate": 5.502512950344659e-05, "loss": 0.4727327823638916, "step": 372590 }, { "epoch": 2.2148117766642295, "grad_norm": 1.4392362833023071, "learning_rate": 5.5020201109633895e-05, "loss": 0.5279871940612793, "step": 372600 }, { "epoch": 2.214871218740898, "grad_norm": 1.7040694952011108, "learning_rate": 5.50152729788266e-05, "loss": 0.48261632919311526, "step": 372610 }, { "epoch": 2.2149306608175663, "grad_norm": 1.7385536432266235, "learning_rate": 5.5010345111048236e-05, "loss": 0.46317663192749026, "step": 372620 }, { "epoch": 2.2149901028942347, "grad_norm": 1.5975041389465332, "learning_rate": 5.500541750632244e-05, "loss": 0.5447201728820801, "step": 372630 }, { "epoch": 2.215049544970903, "grad_norm": 1.192908525466919, "learning_rate": 5.500049016467275e-05, "loss": 0.4649648666381836, "step": 372640 }, { "epoch": 2.2151089870475715, "grad_norm": 1.6430374383926392, "learning_rate": 5.499556308612275e-05, "loss": 0.48998432159423827, "step": 372650 }, { "epoch": 2.21516842912424, "grad_norm": 1.113778829574585, "learning_rate": 5.499063627069598e-05, "loss": 0.5061777591705322, "step": 372660 }, { "epoch": 2.2152278712009084, "grad_norm": 1.314826250076294, "learning_rate": 5.498570971841606e-05, "loss": 0.4973580837249756, "step": 372670 }, { "epoch": 2.2152873132775768, "grad_norm": 1.3662769794464111, "learning_rate": 5.498078342930651e-05, "loss": 0.4657693862915039, "step": 372680 }, { "epoch": 2.215346755354245, "grad_norm": 1.294160008430481, "learning_rate": 5.4975857403390875e-05, "loss": 0.49787173271179197, "step": 372690 }, { "epoch": 2.2154061974309136, "grad_norm": 0.9146773815155029, "learning_rate": 5.497093164069278e-05, "loss": 0.40885171890258787, "step": 372700 }, { "epoch": 2.215465639507582, "grad_norm": 1.3466013669967651, "learning_rate": 5.496600614123577e-05, "loss": 0.5232025146484375, "step": 372710 }, { "epoch": 2.2155250815842504, "grad_norm": 1.6064859628677368, "learning_rate": 5.496108090504342e-05, "loss": 0.42440476417541506, "step": 372720 }, { "epoch": 2.215584523660919, "grad_norm": 1.3991308212280273, "learning_rate": 5.4956155932139265e-05, "loss": 0.4826019763946533, "step": 372730 }, { "epoch": 2.215643965737587, "grad_norm": 1.5362967252731323, "learning_rate": 5.495123122254686e-05, "loss": 0.5268530368804931, "step": 372740 }, { "epoch": 2.2157034078142552, "grad_norm": 1.325323224067688, "learning_rate": 5.494630677628975e-05, "loss": 0.5090072631835938, "step": 372750 }, { "epoch": 2.2157628498909236, "grad_norm": 1.3149054050445557, "learning_rate": 5.4941382593391546e-05, "loss": 0.4709580421447754, "step": 372760 }, { "epoch": 2.215822291967592, "grad_norm": 1.5093289613723755, "learning_rate": 5.4936458673875815e-05, "loss": 0.4678623676300049, "step": 372770 }, { "epoch": 2.2158817340442605, "grad_norm": 1.2103986740112305, "learning_rate": 5.493153501776599e-05, "loss": 0.5450751304626464, "step": 372780 }, { "epoch": 2.215941176120929, "grad_norm": 0.7841774225234985, "learning_rate": 5.492661162508576e-05, "loss": 0.43614020347595217, "step": 372790 }, { "epoch": 2.2160006181975973, "grad_norm": 1.1278947591781616, "learning_rate": 5.492168849585859e-05, "loss": 0.5183844566345215, "step": 372800 }, { "epoch": 2.2160600602742657, "grad_norm": 1.1256388425827026, "learning_rate": 5.4916765630108094e-05, "loss": 0.5005624294281006, "step": 372810 }, { "epoch": 2.216119502350934, "grad_norm": 1.4038177728652954, "learning_rate": 5.4911843027857744e-05, "loss": 0.4767588138580322, "step": 372820 }, { "epoch": 2.2161789444276025, "grad_norm": 1.2264623641967773, "learning_rate": 5.490692068913119e-05, "loss": 0.5120304107666016, "step": 372830 }, { "epoch": 2.216238386504271, "grad_norm": 1.3832676410675049, "learning_rate": 5.49019986139519e-05, "loss": 0.5117904663085937, "step": 372840 }, { "epoch": 2.2162978285809394, "grad_norm": 1.3392308950424194, "learning_rate": 5.4897076802343415e-05, "loss": 0.49702887535095214, "step": 372850 }, { "epoch": 2.216357270657608, "grad_norm": 1.2451833486557007, "learning_rate": 5.489215525432933e-05, "loss": 0.4666475296020508, "step": 372860 }, { "epoch": 2.216416712734276, "grad_norm": 1.5039783716201782, "learning_rate": 5.488723396993316e-05, "loss": 0.5296710968017578, "step": 372870 }, { "epoch": 2.2164761548109446, "grad_norm": 1.5962413549423218, "learning_rate": 5.488231294917844e-05, "loss": 0.4644496440887451, "step": 372880 }, { "epoch": 2.216535596887613, "grad_norm": 1.3530466556549072, "learning_rate": 5.487739219208876e-05, "loss": 0.5680150985717773, "step": 372890 }, { "epoch": 2.2165950389642814, "grad_norm": 1.630667805671692, "learning_rate": 5.487247169868761e-05, "loss": 0.525944709777832, "step": 372900 }, { "epoch": 2.2166544810409494, "grad_norm": 1.4689542055130005, "learning_rate": 5.4867551468998533e-05, "loss": 0.48532743453979493, "step": 372910 }, { "epoch": 2.216713923117618, "grad_norm": 1.1754432916641235, "learning_rate": 5.4862631503045045e-05, "loss": 0.528605318069458, "step": 372920 }, { "epoch": 2.2167733651942862, "grad_norm": 1.520755410194397, "learning_rate": 5.485771180085073e-05, "loss": 0.4956979751586914, "step": 372930 }, { "epoch": 2.2168328072709547, "grad_norm": 1.1483430862426758, "learning_rate": 5.485279236243911e-05, "loss": 0.5015527725219726, "step": 372940 }, { "epoch": 2.216892249347623, "grad_norm": 1.4755783081054688, "learning_rate": 5.484787318783371e-05, "loss": 0.4714957237243652, "step": 372950 }, { "epoch": 2.2169516914242915, "grad_norm": 1.3848848342895508, "learning_rate": 5.484295427705806e-05, "loss": 0.5403368473052979, "step": 372960 }, { "epoch": 2.21701113350096, "grad_norm": 1.144173502922058, "learning_rate": 5.4838035630135675e-05, "loss": 0.48147239685058596, "step": 372970 }, { "epoch": 2.2170705755776283, "grad_norm": 1.5850156545639038, "learning_rate": 5.483311724709009e-05, "loss": 0.5288506031036377, "step": 372980 }, { "epoch": 2.2171300176542967, "grad_norm": 1.310638189315796, "learning_rate": 5.482819912794487e-05, "loss": 0.5029621124267578, "step": 372990 }, { "epoch": 2.217189459730965, "grad_norm": 1.1761902570724487, "learning_rate": 5.482328127272352e-05, "loss": 0.5136181354522705, "step": 373000 }, { "epoch": 2.2172489018076336, "grad_norm": 1.1234863996505737, "learning_rate": 5.481836368144955e-05, "loss": 0.5029358863830566, "step": 373010 }, { "epoch": 2.217308343884302, "grad_norm": 1.391794204711914, "learning_rate": 5.481344635414649e-05, "loss": 0.49978065490722656, "step": 373020 }, { "epoch": 2.2173677859609704, "grad_norm": 1.7251840829849243, "learning_rate": 5.4808529290837864e-05, "loss": 0.5551810264587402, "step": 373030 }, { "epoch": 2.217427228037639, "grad_norm": 1.5912131071090698, "learning_rate": 5.480361249154722e-05, "loss": 0.45766148567199705, "step": 373040 }, { "epoch": 2.2174866701143072, "grad_norm": 1.4542195796966553, "learning_rate": 5.479869595629801e-05, "loss": 0.5111759662628174, "step": 373050 }, { "epoch": 2.2175461121909756, "grad_norm": 1.1149612665176392, "learning_rate": 5.479377968511383e-05, "loss": 0.47296934127807616, "step": 373060 }, { "epoch": 2.217605554267644, "grad_norm": 1.52115797996521, "learning_rate": 5.478886367801817e-05, "loss": 0.4695894718170166, "step": 373070 }, { "epoch": 2.2176649963443125, "grad_norm": 1.5817981958389282, "learning_rate": 5.478394793503454e-05, "loss": 0.5335215568542481, "step": 373080 }, { "epoch": 2.217724438420981, "grad_norm": 1.468666434288025, "learning_rate": 5.477903245618645e-05, "loss": 0.4293327808380127, "step": 373090 }, { "epoch": 2.217783880497649, "grad_norm": 1.4513490200042725, "learning_rate": 5.4774117241497436e-05, "loss": 0.46483402252197265, "step": 373100 }, { "epoch": 2.2178433225743173, "grad_norm": 1.3436795473098755, "learning_rate": 5.476920229099096e-05, "loss": 0.49797849655151366, "step": 373110 }, { "epoch": 2.2179027646509857, "grad_norm": 1.3643687963485718, "learning_rate": 5.476428760469061e-05, "loss": 0.4668154716491699, "step": 373120 }, { "epoch": 2.217962206727654, "grad_norm": 1.376061201095581, "learning_rate": 5.4759373182619845e-05, "loss": 0.49679136276245117, "step": 373130 }, { "epoch": 2.2180216488043225, "grad_norm": 1.6982223987579346, "learning_rate": 5.4754459024802196e-05, "loss": 0.5497412204742431, "step": 373140 }, { "epoch": 2.218081090880991, "grad_norm": 2.0053398609161377, "learning_rate": 5.4749545131261157e-05, "loss": 0.46701850891113283, "step": 373150 }, { "epoch": 2.2181405329576593, "grad_norm": 1.162076473236084, "learning_rate": 5.474463150202023e-05, "loss": 0.539860725402832, "step": 373160 }, { "epoch": 2.2181999750343278, "grad_norm": 1.1965309381484985, "learning_rate": 5.473971813710294e-05, "loss": 0.49170856475830077, "step": 373170 }, { "epoch": 2.218259417110996, "grad_norm": 1.5422718524932861, "learning_rate": 5.4734805036532745e-05, "loss": 0.48958115577697753, "step": 373180 }, { "epoch": 2.2183188591876646, "grad_norm": 1.7698180675506592, "learning_rate": 5.4729892200333196e-05, "loss": 0.4997669219970703, "step": 373190 }, { "epoch": 2.218378301264333, "grad_norm": 1.270300030708313, "learning_rate": 5.4724979628527806e-05, "loss": 0.49373369216918944, "step": 373200 }, { "epoch": 2.2184377433410014, "grad_norm": 1.2924598455429077, "learning_rate": 5.4720067321140034e-05, "loss": 0.5344978332519531, "step": 373210 }, { "epoch": 2.21849718541767, "grad_norm": 1.4272621870040894, "learning_rate": 5.47151552781934e-05, "loss": 0.47902956008911135, "step": 373220 }, { "epoch": 2.2185566274943382, "grad_norm": 1.2458525896072388, "learning_rate": 5.471024349971139e-05, "loss": 0.4569414138793945, "step": 373230 }, { "epoch": 2.2186160695710067, "grad_norm": 1.4727071523666382, "learning_rate": 5.470533198571748e-05, "loss": 0.4941843032836914, "step": 373240 }, { "epoch": 2.218675511647675, "grad_norm": 1.3984397649765015, "learning_rate": 5.470042073623523e-05, "loss": 0.4421542644500732, "step": 373250 }, { "epoch": 2.2187349537243435, "grad_norm": 1.029950737953186, "learning_rate": 5.469550975128808e-05, "loss": 0.4552800178527832, "step": 373260 }, { "epoch": 2.218794395801012, "grad_norm": 1.0995105504989624, "learning_rate": 5.469059903089955e-05, "loss": 0.5039541721343994, "step": 373270 }, { "epoch": 2.2188538378776803, "grad_norm": 1.051168441772461, "learning_rate": 5.4685688575093105e-05, "loss": 0.49101905822753905, "step": 373280 }, { "epoch": 2.2189132799543483, "grad_norm": 1.8582526445388794, "learning_rate": 5.468077838389226e-05, "loss": 0.46826372146606443, "step": 373290 }, { "epoch": 2.2189727220310167, "grad_norm": 1.2874857187271118, "learning_rate": 5.467586845732049e-05, "loss": 0.4720598697662354, "step": 373300 }, { "epoch": 2.219032164107685, "grad_norm": 1.2396864891052246, "learning_rate": 5.467095879540126e-05, "loss": 0.5214859485626221, "step": 373310 }, { "epoch": 2.2190916061843535, "grad_norm": 1.2925933599472046, "learning_rate": 5.4666049398158105e-05, "loss": 0.5148927688598632, "step": 373320 }, { "epoch": 2.219151048261022, "grad_norm": 1.1795454025268555, "learning_rate": 5.4661140265614516e-05, "loss": 0.4835484027862549, "step": 373330 }, { "epoch": 2.2192104903376904, "grad_norm": 1.0779166221618652, "learning_rate": 5.465623139779389e-05, "loss": 0.43286566734313964, "step": 373340 }, { "epoch": 2.2192699324143588, "grad_norm": 1.3623770475387573, "learning_rate": 5.4651322794719796e-05, "loss": 0.5091655254364014, "step": 373350 }, { "epoch": 2.219329374491027, "grad_norm": 1.0765509605407715, "learning_rate": 5.4646414456415685e-05, "loss": 0.5289492607116699, "step": 373360 }, { "epoch": 2.2193888165676956, "grad_norm": 1.4417080879211426, "learning_rate": 5.4641506382905016e-05, "loss": 0.4520289897918701, "step": 373370 }, { "epoch": 2.219448258644364, "grad_norm": 1.271548867225647, "learning_rate": 5.463659857421134e-05, "loss": 0.5122320175170898, "step": 373380 }, { "epoch": 2.2195077007210324, "grad_norm": 1.5334991216659546, "learning_rate": 5.463169103035806e-05, "loss": 0.49955596923828127, "step": 373390 }, { "epoch": 2.219567142797701, "grad_norm": 1.2503278255462646, "learning_rate": 5.462678375136867e-05, "loss": 0.4872619152069092, "step": 373400 }, { "epoch": 2.2196265848743693, "grad_norm": 0.9155694842338562, "learning_rate": 5.462187673726662e-05, "loss": 0.5004798412322998, "step": 373410 }, { "epoch": 2.2196860269510377, "grad_norm": 1.274411678314209, "learning_rate": 5.4616969988075437e-05, "loss": 0.49207363128662107, "step": 373420 }, { "epoch": 2.219745469027706, "grad_norm": 1.3764225244522095, "learning_rate": 5.4612063503818576e-05, "loss": 0.48447132110595703, "step": 373430 }, { "epoch": 2.2198049111043745, "grad_norm": 1.2306616306304932, "learning_rate": 5.46071572845195e-05, "loss": 0.4805936336517334, "step": 373440 }, { "epoch": 2.219864353181043, "grad_norm": 1.422140121459961, "learning_rate": 5.460225133020169e-05, "loss": 0.48220257759094237, "step": 373450 }, { "epoch": 2.2199237952577113, "grad_norm": 1.3622443675994873, "learning_rate": 5.45973456408886e-05, "loss": 0.5216690063476562, "step": 373460 }, { "epoch": 2.2199832373343797, "grad_norm": 1.0784181356430054, "learning_rate": 5.459244021660366e-05, "loss": 0.4870475769042969, "step": 373470 }, { "epoch": 2.2200426794110477, "grad_norm": 1.5885735750198364, "learning_rate": 5.458753505737043e-05, "loss": 0.46001324653625486, "step": 373480 }, { "epoch": 2.220102121487716, "grad_norm": 1.3021296262741089, "learning_rate": 5.458263016321231e-05, "loss": 0.5237374305725098, "step": 373490 }, { "epoch": 2.2201615635643845, "grad_norm": 1.9345251321792603, "learning_rate": 5.457772553415279e-05, "loss": 0.49729442596435547, "step": 373500 }, { "epoch": 2.220221005641053, "grad_norm": 1.2525815963745117, "learning_rate": 5.4572821170215314e-05, "loss": 0.503684139251709, "step": 373510 }, { "epoch": 2.2202804477177214, "grad_norm": 1.4853843450546265, "learning_rate": 5.4567917071423325e-05, "loss": 0.4855006217956543, "step": 373520 }, { "epoch": 2.22033988979439, "grad_norm": 1.1678314208984375, "learning_rate": 5.4563013237800334e-05, "loss": 0.4861167907714844, "step": 373530 }, { "epoch": 2.220399331871058, "grad_norm": 1.6659519672393799, "learning_rate": 5.455810966936973e-05, "loss": 0.48929033279418943, "step": 373540 }, { "epoch": 2.2204587739477266, "grad_norm": 1.3229966163635254, "learning_rate": 5.455320636615504e-05, "loss": 0.4538003921508789, "step": 373550 }, { "epoch": 2.220518216024395, "grad_norm": 1.1851997375488281, "learning_rate": 5.4548303328179686e-05, "loss": 0.5189341545104981, "step": 373560 }, { "epoch": 2.2205776581010634, "grad_norm": 1.3968998193740845, "learning_rate": 5.454340055546714e-05, "loss": 0.49540276527404786, "step": 373570 }, { "epoch": 2.220637100177732, "grad_norm": 1.492828607559204, "learning_rate": 5.453849804804084e-05, "loss": 0.49364571571350097, "step": 373580 }, { "epoch": 2.2206965422544003, "grad_norm": 1.4372981786727905, "learning_rate": 5.453359580592423e-05, "loss": 0.5243428230285645, "step": 373590 }, { "epoch": 2.2207559843310687, "grad_norm": 1.4022797346115112, "learning_rate": 5.4528693829140744e-05, "loss": 0.4567257881164551, "step": 373600 }, { "epoch": 2.220815426407737, "grad_norm": 1.5713931322097778, "learning_rate": 5.45237921177139e-05, "loss": 0.5189944267272949, "step": 373610 }, { "epoch": 2.2208748684844055, "grad_norm": 1.7151002883911133, "learning_rate": 5.451889067166709e-05, "loss": 0.5062040328979492, "step": 373620 }, { "epoch": 2.220934310561074, "grad_norm": 1.0619758367538452, "learning_rate": 5.451398949102379e-05, "loss": 0.47623319625854493, "step": 373630 }, { "epoch": 2.2209937526377423, "grad_norm": 1.4771794080734253, "learning_rate": 5.4509088575807424e-05, "loss": 0.5096035957336426, "step": 373640 }, { "epoch": 2.2210531947144103, "grad_norm": 1.3097385168075562, "learning_rate": 5.450418792604144e-05, "loss": 0.4882507801055908, "step": 373650 }, { "epoch": 2.2211126367910787, "grad_norm": 1.2328623533248901, "learning_rate": 5.449928754174929e-05, "loss": 0.4984025001525879, "step": 373660 }, { "epoch": 2.221172078867747, "grad_norm": 1.36807382106781, "learning_rate": 5.4494387422954365e-05, "loss": 0.4696925163269043, "step": 373670 }, { "epoch": 2.2212315209444156, "grad_norm": 1.1853281259536743, "learning_rate": 5.44894875696802e-05, "loss": 0.44716591835021974, "step": 373680 }, { "epoch": 2.221290963021084, "grad_norm": 1.3399710655212402, "learning_rate": 5.448458798195017e-05, "loss": 0.5165055274963379, "step": 373690 }, { "epoch": 2.2213504050977524, "grad_norm": 1.434317708015442, "learning_rate": 5.447968865978774e-05, "loss": 0.5337528228759766, "step": 373700 }, { "epoch": 2.221409847174421, "grad_norm": 1.2913174629211426, "learning_rate": 5.447478960321633e-05, "loss": 0.48404364585876464, "step": 373710 }, { "epoch": 2.221469289251089, "grad_norm": 1.402650237083435, "learning_rate": 5.4469890812259396e-05, "loss": 0.5129335880279541, "step": 373720 }, { "epoch": 2.2215287313277576, "grad_norm": 1.2186522483825684, "learning_rate": 5.446499228694031e-05, "loss": 0.48987317085266113, "step": 373730 }, { "epoch": 2.221588173404426, "grad_norm": 1.2913527488708496, "learning_rate": 5.446009402728258e-05, "loss": 0.44864959716796876, "step": 373740 }, { "epoch": 2.2216476154810945, "grad_norm": 1.384804606437683, "learning_rate": 5.445519603330962e-05, "loss": 0.5257052421569824, "step": 373750 }, { "epoch": 2.221707057557763, "grad_norm": 1.2905691862106323, "learning_rate": 5.445029830504488e-05, "loss": 0.4932094573974609, "step": 373760 }, { "epoch": 2.2217664996344313, "grad_norm": 1.131592035293579, "learning_rate": 5.4445400842511694e-05, "loss": 0.5166371822357178, "step": 373770 }, { "epoch": 2.2218259417110997, "grad_norm": 1.3676272630691528, "learning_rate": 5.4440503645733585e-05, "loss": 0.4645079612731934, "step": 373780 }, { "epoch": 2.221885383787768, "grad_norm": 1.4316426515579224, "learning_rate": 5.443560671473396e-05, "loss": 0.5015051364898682, "step": 373790 }, { "epoch": 2.2219448258644365, "grad_norm": 1.2719224691390991, "learning_rate": 5.443071004953618e-05, "loss": 0.510069751739502, "step": 373800 }, { "epoch": 2.222004267941105, "grad_norm": 1.578324556350708, "learning_rate": 5.442581365016377e-05, "loss": 0.505129623413086, "step": 373810 }, { "epoch": 2.2220637100177734, "grad_norm": 1.3232934474945068, "learning_rate": 5.4420917516640136e-05, "loss": 0.5138479709625244, "step": 373820 }, { "epoch": 2.222123152094442, "grad_norm": 1.1005915403366089, "learning_rate": 5.44160216489886e-05, "loss": 0.4918989181518555, "step": 373830 }, { "epoch": 2.2221825941711097, "grad_norm": 1.252812147140503, "learning_rate": 5.441112604723269e-05, "loss": 0.5021958351135254, "step": 373840 }, { "epoch": 2.222242036247778, "grad_norm": 1.2825602293014526, "learning_rate": 5.440623071139579e-05, "loss": 0.489980411529541, "step": 373850 }, { "epoch": 2.2223014783244466, "grad_norm": 1.142571210861206, "learning_rate": 5.440133564150127e-05, "loss": 0.46810455322265626, "step": 373860 }, { "epoch": 2.222360920401115, "grad_norm": 1.1656008958816528, "learning_rate": 5.439644083757263e-05, "loss": 0.5108604431152344, "step": 373870 }, { "epoch": 2.2224203624777834, "grad_norm": 1.4756700992584229, "learning_rate": 5.439154629963328e-05, "loss": 0.5639621257781983, "step": 373880 }, { "epoch": 2.222479804554452, "grad_norm": 1.3576580286026, "learning_rate": 5.438665202770655e-05, "loss": 0.48958559036254884, "step": 373890 }, { "epoch": 2.2225392466311202, "grad_norm": 1.0596009492874146, "learning_rate": 5.438175802181589e-05, "loss": 0.49418277740478517, "step": 373900 }, { "epoch": 2.2225986887077887, "grad_norm": 1.4746261835098267, "learning_rate": 5.4376864281984755e-05, "loss": 0.544919776916504, "step": 373910 }, { "epoch": 2.222658130784457, "grad_norm": 1.666565179824829, "learning_rate": 5.4371970808236506e-05, "loss": 0.5403359413146973, "step": 373920 }, { "epoch": 2.2227175728611255, "grad_norm": 1.466351866722107, "learning_rate": 5.436707760059455e-05, "loss": 0.53627028465271, "step": 373930 }, { "epoch": 2.222777014937794, "grad_norm": 1.3650492429733276, "learning_rate": 5.436218465908238e-05, "loss": 0.524476432800293, "step": 373940 }, { "epoch": 2.2228364570144623, "grad_norm": 0.9495025277137756, "learning_rate": 5.43572919837233e-05, "loss": 0.47341175079345704, "step": 373950 }, { "epoch": 2.2228958990911307, "grad_norm": 1.0915971994400024, "learning_rate": 5.435239957454072e-05, "loss": 0.4512836456298828, "step": 373960 }, { "epoch": 2.222955341167799, "grad_norm": 1.1225191354751587, "learning_rate": 5.4347507431558096e-05, "loss": 0.4846993923187256, "step": 373970 }, { "epoch": 2.2230147832444676, "grad_norm": 1.2169241905212402, "learning_rate": 5.4342615554798826e-05, "loss": 0.47255549430847166, "step": 373980 }, { "epoch": 2.223074225321136, "grad_norm": 1.3274463415145874, "learning_rate": 5.4337723944286244e-05, "loss": 0.47849669456481936, "step": 373990 }, { "epoch": 2.2231336673978044, "grad_norm": 1.5968700647354126, "learning_rate": 5.433283260004389e-05, "loss": 0.44179706573486327, "step": 374000 }, { "epoch": 2.223193109474473, "grad_norm": 1.3120349645614624, "learning_rate": 5.4327941522095026e-05, "loss": 0.4856692314147949, "step": 374010 }, { "epoch": 2.223252551551141, "grad_norm": 1.4753230810165405, "learning_rate": 5.4323050710463086e-05, "loss": 0.4472076416015625, "step": 374020 }, { "epoch": 2.223311993627809, "grad_norm": 1.0885515213012695, "learning_rate": 5.431816016517146e-05, "loss": 0.4806406021118164, "step": 374030 }, { "epoch": 2.2233714357044776, "grad_norm": 1.3702526092529297, "learning_rate": 5.4313269886243575e-05, "loss": 0.4723158836364746, "step": 374040 }, { "epoch": 2.223430877781146, "grad_norm": 1.410050392150879, "learning_rate": 5.430837987370283e-05, "loss": 0.489200496673584, "step": 374050 }, { "epoch": 2.2234903198578144, "grad_norm": 1.622787594795227, "learning_rate": 5.430349012757257e-05, "loss": 0.45978922843933107, "step": 374060 }, { "epoch": 2.223549761934483, "grad_norm": 1.1221258640289307, "learning_rate": 5.429860064787624e-05, "loss": 0.464462423324585, "step": 374070 }, { "epoch": 2.2236092040111513, "grad_norm": 1.6448168754577637, "learning_rate": 5.429371143463717e-05, "loss": 0.4876725196838379, "step": 374080 }, { "epoch": 2.2236686460878197, "grad_norm": 1.2558280229568481, "learning_rate": 5.428882248787877e-05, "loss": 0.49293270111083987, "step": 374090 }, { "epoch": 2.223728088164488, "grad_norm": 1.4400466680526733, "learning_rate": 5.428393380762446e-05, "loss": 0.46291418075561525, "step": 374100 }, { "epoch": 2.2237875302411565, "grad_norm": 1.3397622108459473, "learning_rate": 5.427904539389761e-05, "loss": 0.48658275604248047, "step": 374110 }, { "epoch": 2.223846972317825, "grad_norm": 1.566764235496521, "learning_rate": 5.427415724672158e-05, "loss": 0.5054347038269043, "step": 374120 }, { "epoch": 2.2239064143944933, "grad_norm": 1.1931875944137573, "learning_rate": 5.426926936611978e-05, "loss": 0.47760848999023436, "step": 374130 }, { "epoch": 2.2239658564711617, "grad_norm": 1.266187310218811, "learning_rate": 5.426438175211559e-05, "loss": 0.5348317146301269, "step": 374140 }, { "epoch": 2.22402529854783, "grad_norm": 1.490214228630066, "learning_rate": 5.425949440473237e-05, "loss": 0.524408483505249, "step": 374150 }, { "epoch": 2.2240847406244986, "grad_norm": 0.9614057540893555, "learning_rate": 5.4254607323993504e-05, "loss": 0.491959285736084, "step": 374160 }, { "epoch": 2.224144182701167, "grad_norm": 1.1493163108825684, "learning_rate": 5.4249720509922384e-05, "loss": 0.5101804733276367, "step": 374170 }, { "epoch": 2.2242036247778354, "grad_norm": 1.258998155593872, "learning_rate": 5.4244833962542386e-05, "loss": 0.4974544525146484, "step": 374180 }, { "epoch": 2.224263066854504, "grad_norm": 1.3457010984420776, "learning_rate": 5.42399476818769e-05, "loss": 0.4298579216003418, "step": 374190 }, { "epoch": 2.2243225089311722, "grad_norm": 3.3239150047302246, "learning_rate": 5.423506166794926e-05, "loss": 0.5059481620788574, "step": 374200 }, { "epoch": 2.2243819510078406, "grad_norm": 1.4214388132095337, "learning_rate": 5.423017592078288e-05, "loss": 0.4989025592803955, "step": 374210 }, { "epoch": 2.2244413930845086, "grad_norm": 1.1774340867996216, "learning_rate": 5.4225290440401056e-05, "loss": 0.5050724983215332, "step": 374220 }, { "epoch": 2.224500835161177, "grad_norm": 1.2935230731964111, "learning_rate": 5.422040522682728e-05, "loss": 0.5183402061462402, "step": 374230 }, { "epoch": 2.2245602772378454, "grad_norm": 1.129866600036621, "learning_rate": 5.421552028008483e-05, "loss": 0.48251914978027344, "step": 374240 }, { "epoch": 2.224619719314514, "grad_norm": 1.1967419385910034, "learning_rate": 5.421063560019713e-05, "loss": 0.47623066902160643, "step": 374250 }, { "epoch": 2.2246791613911823, "grad_norm": 1.3463923931121826, "learning_rate": 5.420575118718747e-05, "loss": 0.49596371650695803, "step": 374260 }, { "epoch": 2.2247386034678507, "grad_norm": 1.451719880104065, "learning_rate": 5.4200867041079297e-05, "loss": 0.4939891815185547, "step": 374270 }, { "epoch": 2.224798045544519, "grad_norm": 1.2781962156295776, "learning_rate": 5.4195983161895915e-05, "loss": 0.5146242618560791, "step": 374280 }, { "epoch": 2.2248574876211875, "grad_norm": 1.2235163450241089, "learning_rate": 5.419109954966071e-05, "loss": 0.45402822494506834, "step": 374290 }, { "epoch": 2.224916929697856, "grad_norm": 1.3514844179153442, "learning_rate": 5.4186216204397056e-05, "loss": 0.4869718074798584, "step": 374300 }, { "epoch": 2.2249763717745243, "grad_norm": 1.0766748189926147, "learning_rate": 5.418133312612834e-05, "loss": 0.486798620223999, "step": 374310 }, { "epoch": 2.2250358138511928, "grad_norm": 1.335897445678711, "learning_rate": 5.417645031487784e-05, "loss": 0.44549970626831054, "step": 374320 }, { "epoch": 2.225095255927861, "grad_norm": 1.4431185722351074, "learning_rate": 5.417156777066896e-05, "loss": 0.5735785961151123, "step": 374330 }, { "epoch": 2.2251546980045296, "grad_norm": 1.4173158407211304, "learning_rate": 5.4166685493525085e-05, "loss": 0.5407358169555664, "step": 374340 }, { "epoch": 2.225214140081198, "grad_norm": 1.4010207653045654, "learning_rate": 5.416180348346949e-05, "loss": 0.459687614440918, "step": 374350 }, { "epoch": 2.2252735821578664, "grad_norm": 1.2918617725372314, "learning_rate": 5.4156921740525616e-05, "loss": 0.5301694869995117, "step": 374360 }, { "epoch": 2.225333024234535, "grad_norm": 1.333466649055481, "learning_rate": 5.4152040264716805e-05, "loss": 0.47030105590820315, "step": 374370 }, { "epoch": 2.2253924663112032, "grad_norm": 1.383155107498169, "learning_rate": 5.4147159056066354e-05, "loss": 0.45030865669250486, "step": 374380 }, { "epoch": 2.225451908387871, "grad_norm": 1.5729469060897827, "learning_rate": 5.41422781145976e-05, "loss": 0.48160638809204104, "step": 374390 }, { "epoch": 2.2255113504645396, "grad_norm": 1.3369722366333008, "learning_rate": 5.4137397440333994e-05, "loss": 0.5119272232055664, "step": 374400 }, { "epoch": 2.225570792541208, "grad_norm": 1.4317498207092285, "learning_rate": 5.41325170332988e-05, "loss": 0.5411504745483399, "step": 374410 }, { "epoch": 2.2256302346178765, "grad_norm": 1.269826054573059, "learning_rate": 5.4127636893515356e-05, "loss": 0.490385913848877, "step": 374420 }, { "epoch": 2.225689676694545, "grad_norm": 1.3608839511871338, "learning_rate": 5.4122757021007087e-05, "loss": 0.47619428634643557, "step": 374430 }, { "epoch": 2.2257491187712133, "grad_norm": 1.315281629562378, "learning_rate": 5.411787741579728e-05, "loss": 0.5161861419677735, "step": 374440 }, { "epoch": 2.2258085608478817, "grad_norm": 1.4554814100265503, "learning_rate": 5.4112998077909246e-05, "loss": 0.4702493667602539, "step": 374450 }, { "epoch": 2.22586800292455, "grad_norm": 1.1509031057357788, "learning_rate": 5.4108119007366385e-05, "loss": 0.4845571517944336, "step": 374460 }, { "epoch": 2.2259274450012185, "grad_norm": 1.2878602743148804, "learning_rate": 5.410324020419204e-05, "loss": 0.4934206008911133, "step": 374470 }, { "epoch": 2.225986887077887, "grad_norm": 1.2825852632522583, "learning_rate": 5.409836166840949e-05, "loss": 0.4912628173828125, "step": 374480 }, { "epoch": 2.2260463291545554, "grad_norm": 1.8226406574249268, "learning_rate": 5.409348340004217e-05, "loss": 0.5660060405731201, "step": 374490 }, { "epoch": 2.2261057712312238, "grad_norm": 1.3679136037826538, "learning_rate": 5.4088605399113315e-05, "loss": 0.500142765045166, "step": 374500 }, { "epoch": 2.226165213307892, "grad_norm": 1.227265477180481, "learning_rate": 5.408372766564629e-05, "loss": 0.4986475944519043, "step": 374510 }, { "epoch": 2.2262246553845606, "grad_norm": 1.5711702108383179, "learning_rate": 5.4078850199664434e-05, "loss": 0.5235503196716309, "step": 374520 }, { "epoch": 2.226284097461229, "grad_norm": 1.1902751922607422, "learning_rate": 5.4073973001191095e-05, "loss": 0.5235270023345947, "step": 374530 }, { "epoch": 2.2263435395378974, "grad_norm": 1.5253236293792725, "learning_rate": 5.4069096070249595e-05, "loss": 0.45947933197021484, "step": 374540 }, { "epoch": 2.226402981614566, "grad_norm": 1.2597261667251587, "learning_rate": 5.406421940686326e-05, "loss": 0.4998845100402832, "step": 374550 }, { "epoch": 2.2264624236912343, "grad_norm": 1.1527575254440308, "learning_rate": 5.405934301105543e-05, "loss": 0.5107431411743164, "step": 374560 }, { "epoch": 2.2265218657679027, "grad_norm": 1.3607673645019531, "learning_rate": 5.405446688284942e-05, "loss": 0.5237935066223145, "step": 374570 }, { "epoch": 2.2265813078445706, "grad_norm": 1.3187313079833984, "learning_rate": 5.404959102226851e-05, "loss": 0.45973634719848633, "step": 374580 }, { "epoch": 2.226640749921239, "grad_norm": 1.1830648183822632, "learning_rate": 5.4044715429336114e-05, "loss": 0.5734653472900391, "step": 374590 }, { "epoch": 2.2267001919979075, "grad_norm": 1.4725879430770874, "learning_rate": 5.403984010407552e-05, "loss": 0.5190326690673828, "step": 374600 }, { "epoch": 2.226759634074576, "grad_norm": 1.2874040603637695, "learning_rate": 5.4034965046510035e-05, "loss": 0.4643576622009277, "step": 374610 }, { "epoch": 2.2268190761512443, "grad_norm": 1.5639431476593018, "learning_rate": 5.403009025666299e-05, "loss": 0.48696227073669435, "step": 374620 }, { "epoch": 2.2268785182279127, "grad_norm": 1.580784559249878, "learning_rate": 5.40252157345577e-05, "loss": 0.5057868957519531, "step": 374630 }, { "epoch": 2.226937960304581, "grad_norm": 1.175153136253357, "learning_rate": 5.402034148021748e-05, "loss": 0.458997917175293, "step": 374640 }, { "epoch": 2.2269974023812495, "grad_norm": 1.2962092161178589, "learning_rate": 5.4015467493665636e-05, "loss": 0.46039433479309083, "step": 374650 }, { "epoch": 2.227056844457918, "grad_norm": 1.257664442062378, "learning_rate": 5.401059377492552e-05, "loss": 0.46465473175048827, "step": 374660 }, { "epoch": 2.2271162865345864, "grad_norm": 1.072411298751831, "learning_rate": 5.4005720324020424e-05, "loss": 0.5273765563964844, "step": 374670 }, { "epoch": 2.227175728611255, "grad_norm": 1.0796767473220825, "learning_rate": 5.400084714097367e-05, "loss": 0.4481643199920654, "step": 374680 }, { "epoch": 2.227235170687923, "grad_norm": 1.7817208766937256, "learning_rate": 5.399597422580855e-05, "loss": 0.5339232921600342, "step": 374690 }, { "epoch": 2.2272946127645916, "grad_norm": 0.8661503195762634, "learning_rate": 5.39911015785484e-05, "loss": 0.5012104988098145, "step": 374700 }, { "epoch": 2.22735405484126, "grad_norm": 1.3062922954559326, "learning_rate": 5.398622919921648e-05, "loss": 0.5282148361206055, "step": 374710 }, { "epoch": 2.2274134969179284, "grad_norm": 1.3297454118728638, "learning_rate": 5.398135708783617e-05, "loss": 0.4587702751159668, "step": 374720 }, { "epoch": 2.227472938994597, "grad_norm": 1.0834211111068726, "learning_rate": 5.397648524443073e-05, "loss": 0.47583374977111814, "step": 374730 }, { "epoch": 2.2275323810712653, "grad_norm": 1.246778130531311, "learning_rate": 5.397161366902349e-05, "loss": 0.5149046897888183, "step": 374740 }, { "epoch": 2.2275918231479337, "grad_norm": 1.3695019483566284, "learning_rate": 5.3966742361637736e-05, "loss": 0.5452211380004883, "step": 374750 }, { "epoch": 2.227651265224602, "grad_norm": 1.231986403465271, "learning_rate": 5.3961871322296765e-05, "loss": 0.5307816505432129, "step": 374760 }, { "epoch": 2.22771070730127, "grad_norm": 1.4308621883392334, "learning_rate": 5.3957000551023886e-05, "loss": 0.48341822624206543, "step": 374770 }, { "epoch": 2.2277701493779385, "grad_norm": 1.2752984762191772, "learning_rate": 5.395213004784239e-05, "loss": 0.5114681243896484, "step": 374780 }, { "epoch": 2.227829591454607, "grad_norm": 0.9677090644836426, "learning_rate": 5.39472598127756e-05, "loss": 0.4976936340332031, "step": 374790 }, { "epoch": 2.2278890335312753, "grad_norm": 1.1031190156936646, "learning_rate": 5.394238984584683e-05, "loss": 0.46006274223327637, "step": 374800 }, { "epoch": 2.2279484756079437, "grad_norm": 1.2570703029632568, "learning_rate": 5.39375201470793e-05, "loss": 0.5419720649719239, "step": 374810 }, { "epoch": 2.228007917684612, "grad_norm": 1.706545114517212, "learning_rate": 5.393265071649638e-05, "loss": 0.5281192779541015, "step": 374820 }, { "epoch": 2.2280673597612806, "grad_norm": 1.3339756727218628, "learning_rate": 5.3927781554121334e-05, "loss": 0.5523828506469727, "step": 374830 }, { "epoch": 2.228126801837949, "grad_norm": 1.2028942108154297, "learning_rate": 5.392291265997742e-05, "loss": 0.5067998886108398, "step": 374840 }, { "epoch": 2.2281862439146174, "grad_norm": 1.4543334245681763, "learning_rate": 5.3918044034088e-05, "loss": 0.48549623489379884, "step": 374850 }, { "epoch": 2.228245685991286, "grad_norm": 1.3544425964355469, "learning_rate": 5.391317567647636e-05, "loss": 0.5408160209655761, "step": 374860 }, { "epoch": 2.228305128067954, "grad_norm": 1.2222031354904175, "learning_rate": 5.390830758716573e-05, "loss": 0.5049603939056396, "step": 374870 }, { "epoch": 2.2283645701446226, "grad_norm": 1.0550670623779297, "learning_rate": 5.39034397661794e-05, "loss": 0.5128405570983887, "step": 374880 }, { "epoch": 2.228424012221291, "grad_norm": 1.25816810131073, "learning_rate": 5.389857221354071e-05, "loss": 0.42850894927978517, "step": 374890 }, { "epoch": 2.2284834542979595, "grad_norm": 1.2997525930404663, "learning_rate": 5.38937049292729e-05, "loss": 0.44016590118408205, "step": 374900 }, { "epoch": 2.228542896374628, "grad_norm": 1.2135449647903442, "learning_rate": 5.3888837913399245e-05, "loss": 0.5237980842590332, "step": 374910 }, { "epoch": 2.2286023384512963, "grad_norm": 1.4692310094833374, "learning_rate": 5.388397116594313e-05, "loss": 0.4948403835296631, "step": 374920 }, { "epoch": 2.2286617805279647, "grad_norm": 1.3678338527679443, "learning_rate": 5.3879104686927716e-05, "loss": 0.4773989677429199, "step": 374930 }, { "epoch": 2.228721222604633, "grad_norm": 1.3004509210586548, "learning_rate": 5.3874238476376294e-05, "loss": 0.5491289138793946, "step": 374940 }, { "epoch": 2.2287806646813015, "grad_norm": 1.4069440364837646, "learning_rate": 5.3869372534312205e-05, "loss": 0.496367073059082, "step": 374950 }, { "epoch": 2.2288401067579695, "grad_norm": 1.5763570070266724, "learning_rate": 5.38645068607587e-05, "loss": 0.5148102760314941, "step": 374960 }, { "epoch": 2.228899548834638, "grad_norm": 1.257738709449768, "learning_rate": 5.385964145573901e-05, "loss": 0.4570927619934082, "step": 374970 }, { "epoch": 2.2289589909113063, "grad_norm": 1.1086634397506714, "learning_rate": 5.385477631927651e-05, "loss": 0.5168725967407226, "step": 374980 }, { "epoch": 2.2290184329879748, "grad_norm": 1.2234715223312378, "learning_rate": 5.384991145139437e-05, "loss": 0.483916187286377, "step": 374990 }, { "epoch": 2.229077875064643, "grad_norm": 1.2692914009094238, "learning_rate": 5.3845046852115934e-05, "loss": 0.5072108268737793, "step": 375000 }, { "epoch": 2.2291373171413116, "grad_norm": 1.2129172086715698, "learning_rate": 5.3840182521464386e-05, "loss": 0.47774786949157716, "step": 375010 }, { "epoch": 2.22919675921798, "grad_norm": 1.350456714630127, "learning_rate": 5.3835318459463094e-05, "loss": 0.4309369087219238, "step": 375020 }, { "epoch": 2.2292562012946484, "grad_norm": 1.2601271867752075, "learning_rate": 5.383045466613528e-05, "loss": 0.5132176399230957, "step": 375030 }, { "epoch": 2.229315643371317, "grad_norm": 1.1370023488998413, "learning_rate": 5.38255911415042e-05, "loss": 0.49073052406311035, "step": 375040 }, { "epoch": 2.2293750854479852, "grad_norm": 1.0003235340118408, "learning_rate": 5.382072788559316e-05, "loss": 0.48427839279174806, "step": 375050 }, { "epoch": 2.2294345275246537, "grad_norm": 1.5029716491699219, "learning_rate": 5.3815864898425386e-05, "loss": 0.4710291862487793, "step": 375060 }, { "epoch": 2.229493969601322, "grad_norm": 1.3252753019332886, "learning_rate": 5.3811002180024116e-05, "loss": 0.47772769927978515, "step": 375070 }, { "epoch": 2.2295534116779905, "grad_norm": 1.4336011409759521, "learning_rate": 5.3806139730412685e-05, "loss": 0.4884478569030762, "step": 375080 }, { "epoch": 2.229612853754659, "grad_norm": 1.362215518951416, "learning_rate": 5.380127754961433e-05, "loss": 0.48256921768188477, "step": 375090 }, { "epoch": 2.2296722958313273, "grad_norm": 1.4725261926651, "learning_rate": 5.379641563765228e-05, "loss": 0.5043666362762451, "step": 375100 }, { "epoch": 2.2297317379079957, "grad_norm": 1.2054224014282227, "learning_rate": 5.379155399454983e-05, "loss": 0.547054386138916, "step": 375110 }, { "epoch": 2.229791179984664, "grad_norm": 1.5208144187927246, "learning_rate": 5.378669262033019e-05, "loss": 0.47552061080932617, "step": 375120 }, { "epoch": 2.229850622061332, "grad_norm": 1.5653281211853027, "learning_rate": 5.378183151501666e-05, "loss": 0.46572141647338866, "step": 375130 }, { "epoch": 2.2299100641380005, "grad_norm": 1.157009243965149, "learning_rate": 5.377697067863243e-05, "loss": 0.47853622436523435, "step": 375140 }, { "epoch": 2.229969506214669, "grad_norm": 1.4841259717941284, "learning_rate": 5.377211011120084e-05, "loss": 0.47266378402709963, "step": 375150 }, { "epoch": 2.2300289482913374, "grad_norm": 1.4482498168945312, "learning_rate": 5.3767249812745104e-05, "loss": 0.484774112701416, "step": 375160 }, { "epoch": 2.2300883903680058, "grad_norm": 1.7011228799819946, "learning_rate": 5.3762389783288455e-05, "loss": 0.47692155838012695, "step": 375170 }, { "epoch": 2.230147832444674, "grad_norm": 1.022972583770752, "learning_rate": 5.375753002285415e-05, "loss": 0.45464611053466797, "step": 375180 }, { "epoch": 2.2302072745213426, "grad_norm": 1.8431975841522217, "learning_rate": 5.3752670531465465e-05, "loss": 0.5164519309997558, "step": 375190 }, { "epoch": 2.230266716598011, "grad_norm": 1.4068405628204346, "learning_rate": 5.3747811309145576e-05, "loss": 0.49443750381469725, "step": 375200 }, { "epoch": 2.2303261586746794, "grad_norm": 1.1001595258712769, "learning_rate": 5.374295235591781e-05, "loss": 0.47683305740356446, "step": 375210 }, { "epoch": 2.230385600751348, "grad_norm": 1.3471769094467163, "learning_rate": 5.373809367180538e-05, "loss": 0.5237069129943848, "step": 375220 }, { "epoch": 2.2304450428280163, "grad_norm": 0.8283272385597229, "learning_rate": 5.3733235256831514e-05, "loss": 0.46892361640930175, "step": 375230 }, { "epoch": 2.2305044849046847, "grad_norm": 1.3557323217391968, "learning_rate": 5.372837711101946e-05, "loss": 0.5210485458374023, "step": 375240 }, { "epoch": 2.230563926981353, "grad_norm": 1.5935858488082886, "learning_rate": 5.3723519234392475e-05, "loss": 0.4971335411071777, "step": 375250 }, { "epoch": 2.2306233690580215, "grad_norm": 1.1410928964614868, "learning_rate": 5.3718661626973765e-05, "loss": 0.4824833869934082, "step": 375260 }, { "epoch": 2.23068281113469, "grad_norm": 1.2547972202301025, "learning_rate": 5.3713804288786564e-05, "loss": 0.47868757247924804, "step": 375270 }, { "epoch": 2.2307422532113583, "grad_norm": 1.2504923343658447, "learning_rate": 5.3708947219854156e-05, "loss": 0.522822904586792, "step": 375280 }, { "epoch": 2.2308016952880267, "grad_norm": 1.3241385221481323, "learning_rate": 5.370409042019975e-05, "loss": 0.49928936958312986, "step": 375290 }, { "epoch": 2.230861137364695, "grad_norm": 1.2208970785140991, "learning_rate": 5.3699233889846566e-05, "loss": 0.4957146644592285, "step": 375300 }, { "epoch": 2.2309205794413636, "grad_norm": 1.44965660572052, "learning_rate": 5.369437762881786e-05, "loss": 0.4938077926635742, "step": 375310 }, { "epoch": 2.2309800215180315, "grad_norm": 1.1989240646362305, "learning_rate": 5.3689521637136854e-05, "loss": 0.47229747772216796, "step": 375320 }, { "epoch": 2.2310394635947, "grad_norm": 1.2823216915130615, "learning_rate": 5.368466591482675e-05, "loss": 0.49489917755126955, "step": 375330 }, { "epoch": 2.2310989056713684, "grad_norm": 1.2186598777770996, "learning_rate": 5.367981046191082e-05, "loss": 0.451450252532959, "step": 375340 }, { "epoch": 2.231158347748037, "grad_norm": 1.164451241493225, "learning_rate": 5.367495527841226e-05, "loss": 0.44859676361083983, "step": 375350 }, { "epoch": 2.231217789824705, "grad_norm": 1.7335443496704102, "learning_rate": 5.3670100364354346e-05, "loss": 0.49481902122497556, "step": 375360 }, { "epoch": 2.2312772319013736, "grad_norm": 1.1030263900756836, "learning_rate": 5.36652457197602e-05, "loss": 0.4866476058959961, "step": 375370 }, { "epoch": 2.231336673978042, "grad_norm": 1.2073007822036743, "learning_rate": 5.366039134465315e-05, "loss": 0.48125381469726564, "step": 375380 }, { "epoch": 2.2313961160547104, "grad_norm": 1.3413758277893066, "learning_rate": 5.365553723905636e-05, "loss": 0.5049249649047851, "step": 375390 }, { "epoch": 2.231455558131379, "grad_norm": 1.1680399179458618, "learning_rate": 5.365068340299306e-05, "loss": 0.48760156631469725, "step": 375400 }, { "epoch": 2.2315150002080473, "grad_norm": 1.454138159751892, "learning_rate": 5.3645829836486486e-05, "loss": 0.560500955581665, "step": 375410 }, { "epoch": 2.2315744422847157, "grad_norm": 1.4545525312423706, "learning_rate": 5.3640976539559884e-05, "loss": 0.5041253566741943, "step": 375420 }, { "epoch": 2.231633884361384, "grad_norm": 1.3090142011642456, "learning_rate": 5.363612351223636e-05, "loss": 0.46153011322021487, "step": 375430 }, { "epoch": 2.2316933264380525, "grad_norm": 1.3202710151672363, "learning_rate": 5.3631270754539234e-05, "loss": 0.4779681205749512, "step": 375440 }, { "epoch": 2.231752768514721, "grad_norm": 1.652665138244629, "learning_rate": 5.36264182664917e-05, "loss": 0.4557077407836914, "step": 375450 }, { "epoch": 2.2318122105913893, "grad_norm": 1.5298057794570923, "learning_rate": 5.362156604811694e-05, "loss": 0.579013729095459, "step": 375460 }, { "epoch": 2.2318716526680578, "grad_norm": 1.4653065204620361, "learning_rate": 5.36167140994382e-05, "loss": 0.5316777229309082, "step": 375470 }, { "epoch": 2.231931094744726, "grad_norm": 1.1361355781555176, "learning_rate": 5.3611862420478665e-05, "loss": 0.4881135940551758, "step": 375480 }, { "epoch": 2.2319905368213946, "grad_norm": 1.6538605690002441, "learning_rate": 5.3607011011261554e-05, "loss": 0.5323593139648437, "step": 375490 }, { "epoch": 2.232049978898063, "grad_norm": 1.3327454328536987, "learning_rate": 5.3602159871810044e-05, "loss": 0.5029391765594482, "step": 375500 }, { "epoch": 2.232109420974731, "grad_norm": 1.226306438446045, "learning_rate": 5.35973090021474e-05, "loss": 0.4690735340118408, "step": 375510 }, { "epoch": 2.2321688630513994, "grad_norm": 1.359006404876709, "learning_rate": 5.3592458402296785e-05, "loss": 0.47170424461364746, "step": 375520 }, { "epoch": 2.232228305128068, "grad_norm": 1.2556073665618896, "learning_rate": 5.3587608072281425e-05, "loss": 0.5080258846282959, "step": 375530 }, { "epoch": 2.232287747204736, "grad_norm": 1.302052617073059, "learning_rate": 5.358275801212452e-05, "loss": 0.5557186126708984, "step": 375540 }, { "epoch": 2.2323471892814046, "grad_norm": 1.2003602981567383, "learning_rate": 5.357790822184926e-05, "loss": 0.4989813804626465, "step": 375550 }, { "epoch": 2.232406631358073, "grad_norm": 1.4391485452651978, "learning_rate": 5.3573058701478815e-05, "loss": 0.5536113739013672, "step": 375560 }, { "epoch": 2.2324660734347415, "grad_norm": 1.3779832124710083, "learning_rate": 5.356820945103644e-05, "loss": 0.5274083137512207, "step": 375570 }, { "epoch": 2.23252551551141, "grad_norm": 1.58040452003479, "learning_rate": 5.356336047054532e-05, "loss": 0.5605168342590332, "step": 375580 }, { "epoch": 2.2325849575880783, "grad_norm": 1.6587949991226196, "learning_rate": 5.355851176002863e-05, "loss": 0.4805948257446289, "step": 375590 }, { "epoch": 2.2326443996647467, "grad_norm": 1.5873254537582397, "learning_rate": 5.355366331950958e-05, "loss": 0.5205683708190918, "step": 375600 }, { "epoch": 2.232703841741415, "grad_norm": 1.305021047592163, "learning_rate": 5.3548815149011356e-05, "loss": 0.4878836631774902, "step": 375610 }, { "epoch": 2.2327632838180835, "grad_norm": 1.5280756950378418, "learning_rate": 5.354396724855716e-05, "loss": 0.5411770820617676, "step": 375620 }, { "epoch": 2.232822725894752, "grad_norm": 1.2426798343658447, "learning_rate": 5.353911961817013e-05, "loss": 0.5038913726806641, "step": 375630 }, { "epoch": 2.2328821679714204, "grad_norm": 1.2752279043197632, "learning_rate": 5.353427225787355e-05, "loss": 0.509035062789917, "step": 375640 }, { "epoch": 2.2329416100480888, "grad_norm": 1.5982184410095215, "learning_rate": 5.352942516769054e-05, "loss": 0.4942673683166504, "step": 375650 }, { "epoch": 2.233001052124757, "grad_norm": 1.3177043199539185, "learning_rate": 5.35245783476443e-05, "loss": 0.45135769844055174, "step": 375660 }, { "epoch": 2.2330604942014256, "grad_norm": 1.7819005250930786, "learning_rate": 5.3519731797758046e-05, "loss": 0.48166685104370116, "step": 375670 }, { "epoch": 2.2331199362780936, "grad_norm": 1.2302221059799194, "learning_rate": 5.351488551805492e-05, "loss": 0.5214097023010253, "step": 375680 }, { "epoch": 2.2331793783547624, "grad_norm": 1.355590581893921, "learning_rate": 5.3510039508558095e-05, "loss": 0.49527902603149415, "step": 375690 }, { "epoch": 2.2332388204314304, "grad_norm": 1.4045368432998657, "learning_rate": 5.350519376929082e-05, "loss": 0.5046108722686767, "step": 375700 }, { "epoch": 2.233298262508099, "grad_norm": 1.3917678594589233, "learning_rate": 5.3500348300276214e-05, "loss": 0.5264287471771241, "step": 375710 }, { "epoch": 2.2333577045847672, "grad_norm": 1.4935451745986938, "learning_rate": 5.349550310153749e-05, "loss": 0.45777273178100586, "step": 375720 }, { "epoch": 2.2334171466614356, "grad_norm": 1.068907618522644, "learning_rate": 5.349065817309782e-05, "loss": 0.5128249168395996, "step": 375730 }, { "epoch": 2.233476588738104, "grad_norm": 1.2962839603424072, "learning_rate": 5.348581351498036e-05, "loss": 0.4878753662109375, "step": 375740 }, { "epoch": 2.2335360308147725, "grad_norm": 1.5143523216247559, "learning_rate": 5.34809691272083e-05, "loss": 0.5022382736206055, "step": 375750 }, { "epoch": 2.233595472891441, "grad_norm": 1.063485026359558, "learning_rate": 5.347612500980479e-05, "loss": 0.4840414524078369, "step": 375760 }, { "epoch": 2.2336549149681093, "grad_norm": 1.3602138757705688, "learning_rate": 5.347128116279305e-05, "loss": 0.46120452880859375, "step": 375770 }, { "epoch": 2.2337143570447777, "grad_norm": 1.3140119314193726, "learning_rate": 5.346643758619623e-05, "loss": 0.47618875503540037, "step": 375780 }, { "epoch": 2.233773799121446, "grad_norm": 1.6776022911071777, "learning_rate": 5.3461594280037495e-05, "loss": 0.4898355484008789, "step": 375790 }, { "epoch": 2.2338332411981145, "grad_norm": 1.3593968152999878, "learning_rate": 5.345675124434002e-05, "loss": 0.5121652603149414, "step": 375800 }, { "epoch": 2.233892683274783, "grad_norm": 1.5949082374572754, "learning_rate": 5.3451908479126976e-05, "loss": 0.465147066116333, "step": 375810 }, { "epoch": 2.2339521253514514, "grad_norm": 1.3206262588500977, "learning_rate": 5.3447065984421484e-05, "loss": 0.4800732612609863, "step": 375820 }, { "epoch": 2.23401156742812, "grad_norm": 1.583086371421814, "learning_rate": 5.3442223760246776e-05, "loss": 0.47339587211608886, "step": 375830 }, { "epoch": 2.234071009504788, "grad_norm": 1.5961495637893677, "learning_rate": 5.3437381806625985e-05, "loss": 0.4807520866394043, "step": 375840 }, { "epoch": 2.2341304515814566, "grad_norm": 1.386109471321106, "learning_rate": 5.343254012358231e-05, "loss": 0.5628090381622315, "step": 375850 }, { "epoch": 2.234189893658125, "grad_norm": 1.1556445360183716, "learning_rate": 5.342769871113882e-05, "loss": 0.4859030723571777, "step": 375860 }, { "epoch": 2.234249335734793, "grad_norm": 1.3474787473678589, "learning_rate": 5.3422857569318744e-05, "loss": 0.500162410736084, "step": 375870 }, { "epoch": 2.2343087778114614, "grad_norm": 1.195847988128662, "learning_rate": 5.3418016698145236e-05, "loss": 0.4649227142333984, "step": 375880 }, { "epoch": 2.23436821988813, "grad_norm": 1.166178584098816, "learning_rate": 5.341317609764142e-05, "loss": 0.4620049476623535, "step": 375890 }, { "epoch": 2.2344276619647983, "grad_norm": 1.4971486330032349, "learning_rate": 5.3408335767830505e-05, "loss": 0.5215176582336426, "step": 375900 }, { "epoch": 2.2344871040414667, "grad_norm": 1.3062548637390137, "learning_rate": 5.340349570873564e-05, "loss": 0.4792026996612549, "step": 375910 }, { "epoch": 2.234546546118135, "grad_norm": 1.1933479309082031, "learning_rate": 5.339865592037989e-05, "loss": 0.4883383274078369, "step": 375920 }, { "epoch": 2.2346059881948035, "grad_norm": 1.2724486589431763, "learning_rate": 5.3393816402786536e-05, "loss": 0.511233139038086, "step": 375930 }, { "epoch": 2.234665430271472, "grad_norm": 1.5368666648864746, "learning_rate": 5.3388977155978634e-05, "loss": 0.4749161720275879, "step": 375940 }, { "epoch": 2.2347248723481403, "grad_norm": 1.4972859621047974, "learning_rate": 5.3384138179979383e-05, "loss": 0.5208708763122558, "step": 375950 }, { "epoch": 2.2347843144248087, "grad_norm": 1.4105267524719238, "learning_rate": 5.3379299474811864e-05, "loss": 0.4721287727355957, "step": 375960 }, { "epoch": 2.234843756501477, "grad_norm": 1.7459924221038818, "learning_rate": 5.337446104049934e-05, "loss": 0.5360257148742675, "step": 375970 }, { "epoch": 2.2349031985781456, "grad_norm": 1.269298791885376, "learning_rate": 5.3369622877064865e-05, "loss": 0.5006633758544922, "step": 375980 }, { "epoch": 2.234962640654814, "grad_norm": 1.5654041767120361, "learning_rate": 5.3364784984531566e-05, "loss": 0.5253722190856933, "step": 375990 }, { "epoch": 2.2350220827314824, "grad_norm": 1.0839946269989014, "learning_rate": 5.335994736292267e-05, "loss": 0.5013359546661377, "step": 376000 }, { "epoch": 2.235081524808151, "grad_norm": 1.7165265083312988, "learning_rate": 5.3355110012261264e-05, "loss": 0.44809417724609374, "step": 376010 }, { "epoch": 2.2351409668848192, "grad_norm": 1.2745524644851685, "learning_rate": 5.3350272932570474e-05, "loss": 0.5132937908172608, "step": 376020 }, { "epoch": 2.2352004089614876, "grad_norm": 1.0040626525878906, "learning_rate": 5.3345436123873525e-05, "loss": 0.4815608024597168, "step": 376030 }, { "epoch": 2.235259851038156, "grad_norm": 1.5499786138534546, "learning_rate": 5.3340599586193474e-05, "loss": 0.4551023006439209, "step": 376040 }, { "epoch": 2.2353192931148245, "grad_norm": 1.4370723962783813, "learning_rate": 5.3335763319553436e-05, "loss": 0.4868125915527344, "step": 376050 }, { "epoch": 2.2353787351914924, "grad_norm": 1.2991161346435547, "learning_rate": 5.333092732397662e-05, "loss": 0.5109773635864258, "step": 376060 }, { "epoch": 2.235438177268161, "grad_norm": 1.6097419261932373, "learning_rate": 5.332609159948614e-05, "loss": 0.5280013084411621, "step": 376070 }, { "epoch": 2.2354976193448293, "grad_norm": 1.443074107170105, "learning_rate": 5.3321256146105106e-05, "loss": 0.5060467720031738, "step": 376080 }, { "epoch": 2.2355570614214977, "grad_norm": 1.5037351846694946, "learning_rate": 5.331642096385665e-05, "loss": 0.514168643951416, "step": 376090 }, { "epoch": 2.235616503498166, "grad_norm": 1.1466295719146729, "learning_rate": 5.331158605276394e-05, "loss": 0.4652012825012207, "step": 376100 }, { "epoch": 2.2356759455748345, "grad_norm": 1.447198748588562, "learning_rate": 5.330675141285004e-05, "loss": 0.5305785179138184, "step": 376110 }, { "epoch": 2.235735387651503, "grad_norm": 1.5411252975463867, "learning_rate": 5.3301917044138106e-05, "loss": 0.5447126388549804, "step": 376120 }, { "epoch": 2.2357948297281713, "grad_norm": 1.317764401435852, "learning_rate": 5.32970829466513e-05, "loss": 0.4864058494567871, "step": 376130 }, { "epoch": 2.2358542718048398, "grad_norm": 1.0966510772705078, "learning_rate": 5.329224912041272e-05, "loss": 0.4964115142822266, "step": 376140 }, { "epoch": 2.235913713881508, "grad_norm": 1.5693963766098022, "learning_rate": 5.3287415565445485e-05, "loss": 0.47985038757324217, "step": 376150 }, { "epoch": 2.2359731559581766, "grad_norm": 1.5997718572616577, "learning_rate": 5.328258228177272e-05, "loss": 0.5260604858398438, "step": 376160 }, { "epoch": 2.236032598034845, "grad_norm": 1.4031310081481934, "learning_rate": 5.3277749269417545e-05, "loss": 0.4913956165313721, "step": 376170 }, { "epoch": 2.2360920401115134, "grad_norm": 1.634394884109497, "learning_rate": 5.327291652840305e-05, "loss": 0.5455957412719726, "step": 376180 }, { "epoch": 2.236151482188182, "grad_norm": 1.5022639036178589, "learning_rate": 5.326808405875241e-05, "loss": 0.4487356662750244, "step": 376190 }, { "epoch": 2.2362109242648502, "grad_norm": 1.7156448364257812, "learning_rate": 5.3263251860488724e-05, "loss": 0.5219773292541504, "step": 376200 }, { "epoch": 2.2362703663415187, "grad_norm": 1.393918514251709, "learning_rate": 5.32584199336351e-05, "loss": 0.5067618370056153, "step": 376210 }, { "epoch": 2.236329808418187, "grad_norm": 1.3404597043991089, "learning_rate": 5.325358827821465e-05, "loss": 0.46543254852294924, "step": 376220 }, { "epoch": 2.2363892504948555, "grad_norm": 1.256171464920044, "learning_rate": 5.3248756894250484e-05, "loss": 0.4822213649749756, "step": 376230 }, { "epoch": 2.236448692571524, "grad_norm": 1.5761730670928955, "learning_rate": 5.324392578176571e-05, "loss": 0.5214035987854004, "step": 376240 }, { "epoch": 2.236508134648192, "grad_norm": 1.6867340803146362, "learning_rate": 5.323909494078343e-05, "loss": 0.4722311496734619, "step": 376250 }, { "epoch": 2.2365675767248603, "grad_norm": 1.5496470928192139, "learning_rate": 5.3234264371326804e-05, "loss": 0.5015248775482177, "step": 376260 }, { "epoch": 2.2366270188015287, "grad_norm": 1.0455502271652222, "learning_rate": 5.3229434073418893e-05, "loss": 0.5051414012908936, "step": 376270 }, { "epoch": 2.236686460878197, "grad_norm": 1.2237132787704468, "learning_rate": 5.3224604047082824e-05, "loss": 0.5419393539428711, "step": 376280 }, { "epoch": 2.2367459029548655, "grad_norm": 1.2593623399734497, "learning_rate": 5.3219774292341696e-05, "loss": 0.5070338249206543, "step": 376290 }, { "epoch": 2.236805345031534, "grad_norm": 1.3313212394714355, "learning_rate": 5.3214944809218616e-05, "loss": 0.45932512283325194, "step": 376300 }, { "epoch": 2.2368647871082024, "grad_norm": 1.320703387260437, "learning_rate": 5.321011559773665e-05, "loss": 0.4613668918609619, "step": 376310 }, { "epoch": 2.2369242291848708, "grad_norm": 1.5796526670455933, "learning_rate": 5.320528665791895e-05, "loss": 0.4861569404602051, "step": 376320 }, { "epoch": 2.236983671261539, "grad_norm": 1.1900910139083862, "learning_rate": 5.320045798978861e-05, "loss": 0.5004255294799804, "step": 376330 }, { "epoch": 2.2370431133382076, "grad_norm": 1.207238793373108, "learning_rate": 5.319562959336875e-05, "loss": 0.4975642204284668, "step": 376340 }, { "epoch": 2.237102555414876, "grad_norm": 1.2276325225830078, "learning_rate": 5.319080146868236e-05, "loss": 0.47141094207763673, "step": 376350 }, { "epoch": 2.2371619974915444, "grad_norm": 1.1901627779006958, "learning_rate": 5.3185973615752635e-05, "loss": 0.4980947971343994, "step": 376360 }, { "epoch": 2.237221439568213, "grad_norm": 1.5241179466247559, "learning_rate": 5.318114603460267e-05, "loss": 0.5781336784362793, "step": 376370 }, { "epoch": 2.2372808816448813, "grad_norm": 1.3629018068313599, "learning_rate": 5.317631872525549e-05, "loss": 0.5130468368530273, "step": 376380 }, { "epoch": 2.2373403237215497, "grad_norm": 1.7284272909164429, "learning_rate": 5.317149168773425e-05, "loss": 0.49926466941833497, "step": 376390 }, { "epoch": 2.237399765798218, "grad_norm": 1.7165405750274658, "learning_rate": 5.3166664922062084e-05, "loss": 0.49806976318359375, "step": 376400 }, { "epoch": 2.2374592078748865, "grad_norm": 1.5370051860809326, "learning_rate": 5.3161838428261925e-05, "loss": 0.49892821311950686, "step": 376410 }, { "epoch": 2.2375186499515545, "grad_norm": 1.648551344871521, "learning_rate": 5.3157012206357005e-05, "loss": 0.5202658653259278, "step": 376420 }, { "epoch": 2.2375780920282233, "grad_norm": 1.1546545028686523, "learning_rate": 5.315218625637036e-05, "loss": 0.45848665237426756, "step": 376430 }, { "epoch": 2.2376375341048913, "grad_norm": 1.4668914079666138, "learning_rate": 5.3147360578325076e-05, "loss": 0.5013309478759765, "step": 376440 }, { "epoch": 2.2376969761815597, "grad_norm": 1.2485893964767456, "learning_rate": 5.3142535172244215e-05, "loss": 0.47498502731323244, "step": 376450 }, { "epoch": 2.237756418258228, "grad_norm": 1.3142316341400146, "learning_rate": 5.313771003815093e-05, "loss": 0.4623931884765625, "step": 376460 }, { "epoch": 2.2378158603348965, "grad_norm": 1.3946771621704102, "learning_rate": 5.313288517606824e-05, "loss": 0.4797687530517578, "step": 376470 }, { "epoch": 2.237875302411565, "grad_norm": 1.4521574974060059, "learning_rate": 5.3128060586019203e-05, "loss": 0.5180375576019287, "step": 376480 }, { "epoch": 2.2379347444882334, "grad_norm": 1.4250805377960205, "learning_rate": 5.312323626802698e-05, "loss": 0.4339808464050293, "step": 376490 }, { "epoch": 2.237994186564902, "grad_norm": 1.3886616230010986, "learning_rate": 5.31184122221146e-05, "loss": 0.5108654499053955, "step": 376500 }, { "epoch": 2.23805362864157, "grad_norm": 1.34791100025177, "learning_rate": 5.3113588448305116e-05, "loss": 0.5200828552246094, "step": 376510 }, { "epoch": 2.2381130707182386, "grad_norm": 1.151449203491211, "learning_rate": 5.3108764946621705e-05, "loss": 0.4803003311157227, "step": 376520 }, { "epoch": 2.238172512794907, "grad_norm": 1.2190420627593994, "learning_rate": 5.310394171708732e-05, "loss": 0.5296214103698731, "step": 376530 }, { "epoch": 2.2382319548715754, "grad_norm": 1.4155157804489136, "learning_rate": 5.3099118759725064e-05, "loss": 0.5049654006958008, "step": 376540 }, { "epoch": 2.238291396948244, "grad_norm": 1.5016332864761353, "learning_rate": 5.309429607455807e-05, "loss": 0.5313242912292481, "step": 376550 }, { "epoch": 2.2383508390249123, "grad_norm": 1.4702818393707275, "learning_rate": 5.308947366160936e-05, "loss": 0.48290233612060546, "step": 376560 }, { "epoch": 2.2384102811015807, "grad_norm": 1.3304386138916016, "learning_rate": 5.308465152090201e-05, "loss": 0.49696006774902346, "step": 376570 }, { "epoch": 2.238469723178249, "grad_norm": 1.4122430086135864, "learning_rate": 5.3079829652459077e-05, "loss": 0.4930851936340332, "step": 376580 }, { "epoch": 2.2385291652549175, "grad_norm": 1.1888819932937622, "learning_rate": 5.3075008056303647e-05, "loss": 0.5087008476257324, "step": 376590 }, { "epoch": 2.238588607331586, "grad_norm": 1.4415887594223022, "learning_rate": 5.307018673245877e-05, "loss": 0.44933147430419923, "step": 376600 }, { "epoch": 2.238648049408254, "grad_norm": 1.276848316192627, "learning_rate": 5.3065365680947485e-05, "loss": 0.4981494903564453, "step": 376610 }, { "epoch": 2.2387074914849223, "grad_norm": 2.5276198387145996, "learning_rate": 5.306054490179292e-05, "loss": 0.5205799579620362, "step": 376620 }, { "epoch": 2.2387669335615907, "grad_norm": 1.488519310951233, "learning_rate": 5.305572439501809e-05, "loss": 0.5733274936676025, "step": 376630 }, { "epoch": 2.238826375638259, "grad_norm": 1.0055458545684814, "learning_rate": 5.305090416064606e-05, "loss": 0.49003915786743163, "step": 376640 }, { "epoch": 2.2388858177149276, "grad_norm": 0.9840962290763855, "learning_rate": 5.304608419869992e-05, "loss": 0.4730170249938965, "step": 376650 }, { "epoch": 2.238945259791596, "grad_norm": 1.290502905845642, "learning_rate": 5.3041264509202684e-05, "loss": 0.44448347091674806, "step": 376660 }, { "epoch": 2.2390047018682644, "grad_norm": 1.46794855594635, "learning_rate": 5.303644509217739e-05, "loss": 0.4987905025482178, "step": 376670 }, { "epoch": 2.239064143944933, "grad_norm": 1.44822359085083, "learning_rate": 5.303162594764716e-05, "loss": 0.5047703742980957, "step": 376680 }, { "epoch": 2.239123586021601, "grad_norm": 1.452110767364502, "learning_rate": 5.302680707563501e-05, "loss": 0.4564478397369385, "step": 376690 }, { "epoch": 2.2391830280982696, "grad_norm": 1.5726828575134277, "learning_rate": 5.3021988476164005e-05, "loss": 0.4880989074707031, "step": 376700 }, { "epoch": 2.239242470174938, "grad_norm": 1.6724046468734741, "learning_rate": 5.3017170149257176e-05, "loss": 0.5164155006408692, "step": 376710 }, { "epoch": 2.2393019122516065, "grad_norm": 1.1026790142059326, "learning_rate": 5.3012352094937604e-05, "loss": 0.492669677734375, "step": 376720 }, { "epoch": 2.239361354328275, "grad_norm": 1.505190134048462, "learning_rate": 5.300753431322829e-05, "loss": 0.47548933029174806, "step": 376730 }, { "epoch": 2.2394207964049433, "grad_norm": 1.3622103929519653, "learning_rate": 5.3002716804152294e-05, "loss": 0.4653076171875, "step": 376740 }, { "epoch": 2.2394802384816117, "grad_norm": 1.3646687269210815, "learning_rate": 5.29978995677327e-05, "loss": 0.5202094554901123, "step": 376750 }, { "epoch": 2.23953968055828, "grad_norm": 1.0513185262680054, "learning_rate": 5.299308260399252e-05, "loss": 0.4767775058746338, "step": 376760 }, { "epoch": 2.2395991226349485, "grad_norm": 1.116662621498108, "learning_rate": 5.2988265912954804e-05, "loss": 0.48087921142578127, "step": 376770 }, { "epoch": 2.239658564711617, "grad_norm": 1.0009300708770752, "learning_rate": 5.29834494946426e-05, "loss": 0.49877352714538575, "step": 376780 }, { "epoch": 2.2397180067882854, "grad_norm": 1.5674843788146973, "learning_rate": 5.297863334907893e-05, "loss": 0.5278010368347168, "step": 376790 }, { "epoch": 2.2397774488649533, "grad_norm": 1.5061978101730347, "learning_rate": 5.297381747628685e-05, "loss": 0.5463762760162354, "step": 376800 }, { "epoch": 2.2398368909416217, "grad_norm": 1.7676591873168945, "learning_rate": 5.296900187628936e-05, "loss": 0.5048229694366455, "step": 376810 }, { "epoch": 2.23989633301829, "grad_norm": 1.1294429302215576, "learning_rate": 5.2964186549109564e-05, "loss": 0.5013552188873291, "step": 376820 }, { "epoch": 2.2399557750949586, "grad_norm": 1.1019452810287476, "learning_rate": 5.2959371494770485e-05, "loss": 0.49827985763549804, "step": 376830 }, { "epoch": 2.240015217171627, "grad_norm": 1.4745957851409912, "learning_rate": 5.295455671329505e-05, "loss": 0.5062670707702637, "step": 376840 }, { "epoch": 2.2400746592482954, "grad_norm": 1.2807402610778809, "learning_rate": 5.294974220470643e-05, "loss": 0.48834967613220215, "step": 376850 }, { "epoch": 2.240134101324964, "grad_norm": 1.2748311758041382, "learning_rate": 5.294492796902759e-05, "loss": 0.49155483245849607, "step": 376860 }, { "epoch": 2.2401935434016322, "grad_norm": 1.3376517295837402, "learning_rate": 5.294011400628154e-05, "loss": 0.5672010898590087, "step": 376870 }, { "epoch": 2.2402529854783007, "grad_norm": 1.1942625045776367, "learning_rate": 5.2935300316491375e-05, "loss": 0.5123050689697266, "step": 376880 }, { "epoch": 2.240312427554969, "grad_norm": 1.4041022062301636, "learning_rate": 5.2930486899680096e-05, "loss": 0.5396011352539063, "step": 376890 }, { "epoch": 2.2403718696316375, "grad_norm": 1.499661922454834, "learning_rate": 5.2925673755870674e-05, "loss": 0.5509202003479003, "step": 376900 }, { "epoch": 2.240431311708306, "grad_norm": 1.4766122102737427, "learning_rate": 5.29208608850862e-05, "loss": 0.497434139251709, "step": 376910 }, { "epoch": 2.2404907537849743, "grad_norm": 1.2965959310531616, "learning_rate": 5.291604828734967e-05, "loss": 0.48749871253967286, "step": 376920 }, { "epoch": 2.2405501958616427, "grad_norm": 1.2899341583251953, "learning_rate": 5.2911235962684114e-05, "loss": 0.48473501205444336, "step": 376930 }, { "epoch": 2.240609637938311, "grad_norm": 1.4263522624969482, "learning_rate": 5.290642391111252e-05, "loss": 0.4809422969818115, "step": 376940 }, { "epoch": 2.2406690800149796, "grad_norm": 1.2508735656738281, "learning_rate": 5.2901612132658005e-05, "loss": 0.4664773464202881, "step": 376950 }, { "epoch": 2.240728522091648, "grad_norm": 1.386162519454956, "learning_rate": 5.2896800627343465e-05, "loss": 0.48081493377685547, "step": 376960 }, { "epoch": 2.2407879641683164, "grad_norm": 1.5484825372695923, "learning_rate": 5.2891989395191954e-05, "loss": 0.4478731632232666, "step": 376970 }, { "epoch": 2.240847406244985, "grad_norm": 0.9645424485206604, "learning_rate": 5.2887178436226525e-05, "loss": 0.4720315933227539, "step": 376980 }, { "epoch": 2.2409068483216528, "grad_norm": 1.7588169574737549, "learning_rate": 5.288236775047017e-05, "loss": 0.4857147216796875, "step": 376990 }, { "epoch": 2.240966290398321, "grad_norm": 1.543732762336731, "learning_rate": 5.2877557337945884e-05, "loss": 0.4438186168670654, "step": 377000 }, { "epoch": 2.2410257324749896, "grad_norm": 1.4451546669006348, "learning_rate": 5.287274719867674e-05, "loss": 0.48499317169189454, "step": 377010 }, { "epoch": 2.241085174551658, "grad_norm": 1.2711642980575562, "learning_rate": 5.286793733268569e-05, "loss": 0.462862491607666, "step": 377020 }, { "epoch": 2.2411446166283264, "grad_norm": 1.3153421878814697, "learning_rate": 5.2863127739995724e-05, "loss": 0.47795901298522947, "step": 377030 }, { "epoch": 2.241204058704995, "grad_norm": 1.3247346878051758, "learning_rate": 5.285831842062989e-05, "loss": 0.5609783172607422, "step": 377040 }, { "epoch": 2.2412635007816633, "grad_norm": 1.1052082777023315, "learning_rate": 5.285350937461122e-05, "loss": 0.4638021469116211, "step": 377050 }, { "epoch": 2.2413229428583317, "grad_norm": 1.2868432998657227, "learning_rate": 5.284870060196266e-05, "loss": 0.49028525352478025, "step": 377060 }, { "epoch": 2.241382384935, "grad_norm": 1.327746033668518, "learning_rate": 5.284389210270726e-05, "loss": 0.49042654037475586, "step": 377070 }, { "epoch": 2.2414418270116685, "grad_norm": 1.5852230787277222, "learning_rate": 5.2839083876867976e-05, "loss": 0.5525594711303711, "step": 377080 }, { "epoch": 2.241501269088337, "grad_norm": 1.5274375677108765, "learning_rate": 5.283427592446786e-05, "loss": 0.4763959884643555, "step": 377090 }, { "epoch": 2.2415607111650053, "grad_norm": 1.2009085416793823, "learning_rate": 5.282946824552983e-05, "loss": 0.49445037841796874, "step": 377100 }, { "epoch": 2.2416201532416737, "grad_norm": 1.4304094314575195, "learning_rate": 5.282466084007698e-05, "loss": 0.49851245880126954, "step": 377110 }, { "epoch": 2.241679595318342, "grad_norm": 1.503504753112793, "learning_rate": 5.2819853708132273e-05, "loss": 0.5065593719482422, "step": 377120 }, { "epoch": 2.2417390373950106, "grad_norm": 1.4627764225006104, "learning_rate": 5.281504684971871e-05, "loss": 0.5394516944885254, "step": 377130 }, { "epoch": 2.241798479471679, "grad_norm": 1.3965528011322021, "learning_rate": 5.2810240264859255e-05, "loss": 0.46609249114990237, "step": 377140 }, { "epoch": 2.2418579215483474, "grad_norm": 1.42180597782135, "learning_rate": 5.280543395357693e-05, "loss": 0.46526370048522947, "step": 377150 }, { "epoch": 2.2419173636250154, "grad_norm": 1.2112568616867065, "learning_rate": 5.2800627915894684e-05, "loss": 0.46491804122924807, "step": 377160 }, { "epoch": 2.2419768057016842, "grad_norm": 1.5613371133804321, "learning_rate": 5.279582215183557e-05, "loss": 0.5086396217346192, "step": 377170 }, { "epoch": 2.242036247778352, "grad_norm": 1.4260035753250122, "learning_rate": 5.279101666142254e-05, "loss": 0.5108885765075684, "step": 377180 }, { "epoch": 2.2420956898550206, "grad_norm": 1.3037458658218384, "learning_rate": 5.278621144467861e-05, "loss": 0.5065223693847656, "step": 377190 }, { "epoch": 2.242155131931689, "grad_norm": 1.2862683534622192, "learning_rate": 5.278140650162674e-05, "loss": 0.48076772689819336, "step": 377200 }, { "epoch": 2.2422145740083574, "grad_norm": 1.4365724325180054, "learning_rate": 5.277660183228992e-05, "loss": 0.5036510467529297, "step": 377210 }, { "epoch": 2.242274016085026, "grad_norm": 1.6300690174102783, "learning_rate": 5.2771797436691136e-05, "loss": 0.48747873306274414, "step": 377220 }, { "epoch": 2.2423334581616943, "grad_norm": 1.4334827661514282, "learning_rate": 5.276699331485334e-05, "loss": 0.4716278076171875, "step": 377230 }, { "epoch": 2.2423929002383627, "grad_norm": 1.2628580331802368, "learning_rate": 5.2762189466799584e-05, "loss": 0.5084015846252441, "step": 377240 }, { "epoch": 2.242452342315031, "grad_norm": 1.3430426120758057, "learning_rate": 5.275738589255279e-05, "loss": 0.5068711280822754, "step": 377250 }, { "epoch": 2.2425117843916995, "grad_norm": 1.4685622453689575, "learning_rate": 5.275258259213596e-05, "loss": 0.47875471115112306, "step": 377260 }, { "epoch": 2.242571226468368, "grad_norm": 1.5323258638381958, "learning_rate": 5.274777956557208e-05, "loss": 0.5059713363647461, "step": 377270 }, { "epoch": 2.2426306685450363, "grad_norm": 1.3781399726867676, "learning_rate": 5.274297681288409e-05, "loss": 0.4845722198486328, "step": 377280 }, { "epoch": 2.2426901106217048, "grad_norm": 1.1730172634124756, "learning_rate": 5.2738174334095e-05, "loss": 0.4617833137512207, "step": 377290 }, { "epoch": 2.242749552698373, "grad_norm": 1.6300742626190186, "learning_rate": 5.2733372129227753e-05, "loss": 0.44228343963623046, "step": 377300 }, { "epoch": 2.2428089947750416, "grad_norm": 1.4982060194015503, "learning_rate": 5.272857019830535e-05, "loss": 0.4836078643798828, "step": 377310 }, { "epoch": 2.24286843685171, "grad_norm": 1.2672677040100098, "learning_rate": 5.272376854135075e-05, "loss": 0.5060239315032959, "step": 377320 }, { "epoch": 2.2429278789283784, "grad_norm": 1.4152631759643555, "learning_rate": 5.271896715838693e-05, "loss": 0.4695423126220703, "step": 377330 }, { "epoch": 2.242987321005047, "grad_norm": 1.4040783643722534, "learning_rate": 5.271416604943685e-05, "loss": 0.4891382694244385, "step": 377340 }, { "epoch": 2.243046763081715, "grad_norm": 1.3114981651306152, "learning_rate": 5.270936521452348e-05, "loss": 0.5431499004364013, "step": 377350 }, { "epoch": 2.243106205158383, "grad_norm": 1.9043256044387817, "learning_rate": 5.270456465366975e-05, "loss": 0.4741353034973145, "step": 377360 }, { "epoch": 2.2431656472350516, "grad_norm": 1.4474354982376099, "learning_rate": 5.26997643668987e-05, "loss": 0.5416645050048828, "step": 377370 }, { "epoch": 2.24322508931172, "grad_norm": 1.7911332845687866, "learning_rate": 5.269496435423324e-05, "loss": 0.47838573455810546, "step": 377380 }, { "epoch": 2.2432845313883885, "grad_norm": 1.5829112529754639, "learning_rate": 5.2690164615696344e-05, "loss": 0.5023700714111328, "step": 377390 }, { "epoch": 2.243343973465057, "grad_norm": 1.1574320793151855, "learning_rate": 5.268536515131097e-05, "loss": 0.45908756256103517, "step": 377400 }, { "epoch": 2.2434034155417253, "grad_norm": 1.7532719373703003, "learning_rate": 5.268056596110009e-05, "loss": 0.5604685783386231, "step": 377410 }, { "epoch": 2.2434628576183937, "grad_norm": 1.5571690797805786, "learning_rate": 5.267576704508665e-05, "loss": 0.5215414047241211, "step": 377420 }, { "epoch": 2.243522299695062, "grad_norm": 1.192612648010254, "learning_rate": 5.267096840329355e-05, "loss": 0.5178705215454101, "step": 377430 }, { "epoch": 2.2435817417717305, "grad_norm": 1.5693222284317017, "learning_rate": 5.2666170035743854e-05, "loss": 0.4725058078765869, "step": 377440 }, { "epoch": 2.243641183848399, "grad_norm": 1.4756015539169312, "learning_rate": 5.2661371942460503e-05, "loss": 0.4848275661468506, "step": 377450 }, { "epoch": 2.2437006259250674, "grad_norm": 1.5703949928283691, "learning_rate": 5.265657412346633e-05, "loss": 0.5120059967041015, "step": 377460 }, { "epoch": 2.2437600680017358, "grad_norm": 1.3906621932983398, "learning_rate": 5.265177657878441e-05, "loss": 0.4551679611206055, "step": 377470 }, { "epoch": 2.243819510078404, "grad_norm": 1.4145424365997314, "learning_rate": 5.264697930843764e-05, "loss": 0.5206083297729492, "step": 377480 }, { "epoch": 2.2438789521550726, "grad_norm": 1.5662935972213745, "learning_rate": 5.264218231244895e-05, "loss": 0.49962401390075684, "step": 377490 }, { "epoch": 2.243938394231741, "grad_norm": 1.388550877571106, "learning_rate": 5.263738559084137e-05, "loss": 0.5342501163482666, "step": 377500 }, { "epoch": 2.2439978363084094, "grad_norm": 1.1863301992416382, "learning_rate": 5.2632589143637765e-05, "loss": 0.49464983940124513, "step": 377510 }, { "epoch": 2.244057278385078, "grad_norm": 1.2646806240081787, "learning_rate": 5.262779297086109e-05, "loss": 0.4984284400939941, "step": 377520 }, { "epoch": 2.2441167204617463, "grad_norm": 1.3911399841308594, "learning_rate": 5.262299707253431e-05, "loss": 0.5008331298828125, "step": 377530 }, { "epoch": 2.2441761625384142, "grad_norm": 1.2380099296569824, "learning_rate": 5.261820144868038e-05, "loss": 0.4966167449951172, "step": 377540 }, { "epoch": 2.2442356046150826, "grad_norm": 1.3047834634780884, "learning_rate": 5.261340609932221e-05, "loss": 0.5112431049346924, "step": 377550 }, { "epoch": 2.244295046691751, "grad_norm": 1.1921055316925049, "learning_rate": 5.2608611024482755e-05, "loss": 0.513986873626709, "step": 377560 }, { "epoch": 2.2443544887684195, "grad_norm": 1.284899115562439, "learning_rate": 5.260381622418495e-05, "loss": 0.4962165832519531, "step": 377570 }, { "epoch": 2.244413930845088, "grad_norm": 1.107558012008667, "learning_rate": 5.259902169845173e-05, "loss": 0.4559304237365723, "step": 377580 }, { "epoch": 2.2444733729217563, "grad_norm": 1.183080792427063, "learning_rate": 5.2594227447305996e-05, "loss": 0.5055773735046387, "step": 377590 }, { "epoch": 2.2445328149984247, "grad_norm": 1.2575314044952393, "learning_rate": 5.2589433470770767e-05, "loss": 0.47646055221557615, "step": 377600 }, { "epoch": 2.244592257075093, "grad_norm": 1.4813733100891113, "learning_rate": 5.25846397688689e-05, "loss": 0.4877325534820557, "step": 377610 }, { "epoch": 2.2446516991517615, "grad_norm": 1.4085705280303955, "learning_rate": 5.257984634162337e-05, "loss": 0.4808343887329102, "step": 377620 }, { "epoch": 2.24471114122843, "grad_norm": 1.4605306386947632, "learning_rate": 5.2575053189057085e-05, "loss": 0.47209949493408204, "step": 377630 }, { "epoch": 2.2447705833050984, "grad_norm": 1.167158842086792, "learning_rate": 5.2570260311192984e-05, "loss": 0.4624505043029785, "step": 377640 }, { "epoch": 2.244830025381767, "grad_norm": 1.3850207328796387, "learning_rate": 5.2565467708053983e-05, "loss": 0.4562563896179199, "step": 377650 }, { "epoch": 2.244889467458435, "grad_norm": 1.3520807027816772, "learning_rate": 5.256067537966298e-05, "loss": 0.4449657917022705, "step": 377660 }, { "epoch": 2.2449489095351036, "grad_norm": 1.2402421236038208, "learning_rate": 5.2555883326042974e-05, "loss": 0.5069133758544921, "step": 377670 }, { "epoch": 2.245008351611772, "grad_norm": 1.9548860788345337, "learning_rate": 5.255109154721685e-05, "loss": 0.47428083419799805, "step": 377680 }, { "epoch": 2.2450677936884404, "grad_norm": 1.2313531637191772, "learning_rate": 5.254630004320752e-05, "loss": 0.44751429557800293, "step": 377690 }, { "epoch": 2.245127235765109, "grad_norm": 1.4462721347808838, "learning_rate": 5.254150881403792e-05, "loss": 0.5128326416015625, "step": 377700 }, { "epoch": 2.2451866778417773, "grad_norm": 1.3773248195648193, "learning_rate": 5.253671785973097e-05, "loss": 0.44391617774963377, "step": 377710 }, { "epoch": 2.2452461199184457, "grad_norm": 1.6740108728408813, "learning_rate": 5.253192718030955e-05, "loss": 0.4867849349975586, "step": 377720 }, { "epoch": 2.2453055619951137, "grad_norm": 1.658851146697998, "learning_rate": 5.252713677579663e-05, "loss": 0.4976834297180176, "step": 377730 }, { "epoch": 2.245365004071782, "grad_norm": 1.4583311080932617, "learning_rate": 5.2522346646215106e-05, "loss": 0.45303778648376464, "step": 377740 }, { "epoch": 2.2454244461484505, "grad_norm": 1.1553925275802612, "learning_rate": 5.2517556791587905e-05, "loss": 0.4804357051849365, "step": 377750 }, { "epoch": 2.245483888225119, "grad_norm": 1.0085771083831787, "learning_rate": 5.2512767211937916e-05, "loss": 0.5039513587951661, "step": 377760 }, { "epoch": 2.2455433303017873, "grad_norm": 1.4854472875595093, "learning_rate": 5.250797790728806e-05, "loss": 0.5339468479156494, "step": 377770 }, { "epoch": 2.2456027723784557, "grad_norm": 1.4085835218429565, "learning_rate": 5.2503188877661255e-05, "loss": 0.5046148777008057, "step": 377780 }, { "epoch": 2.245662214455124, "grad_norm": 1.6193363666534424, "learning_rate": 5.2498400123080384e-05, "loss": 0.4845362663269043, "step": 377790 }, { "epoch": 2.2457216565317926, "grad_norm": 1.4787569046020508, "learning_rate": 5.249361164356839e-05, "loss": 0.5304996967315674, "step": 377800 }, { "epoch": 2.245781098608461, "grad_norm": 1.1266703605651855, "learning_rate": 5.248882343914816e-05, "loss": 0.4772846221923828, "step": 377810 }, { "epoch": 2.2458405406851294, "grad_norm": 1.510332703590393, "learning_rate": 5.248403550984262e-05, "loss": 0.4660510063171387, "step": 377820 }, { "epoch": 2.245899982761798, "grad_norm": 1.4548875093460083, "learning_rate": 5.247924785567464e-05, "loss": 0.4871350288391113, "step": 377830 }, { "epoch": 2.2459594248384662, "grad_norm": 1.4238039255142212, "learning_rate": 5.2474460476667165e-05, "loss": 0.5062761306762695, "step": 377840 }, { "epoch": 2.2460188669151346, "grad_norm": 1.4104362726211548, "learning_rate": 5.246967337284302e-05, "loss": 0.4771106243133545, "step": 377850 }, { "epoch": 2.246078308991803, "grad_norm": 1.1871894598007202, "learning_rate": 5.246488654422519e-05, "loss": 0.48810415267944335, "step": 377860 }, { "epoch": 2.2461377510684715, "grad_norm": 1.4535558223724365, "learning_rate": 5.246009999083654e-05, "loss": 0.47714862823486326, "step": 377870 }, { "epoch": 2.24619719314514, "grad_norm": 1.2024257183074951, "learning_rate": 5.245531371269998e-05, "loss": 0.4867546081542969, "step": 377880 }, { "epoch": 2.2462566352218083, "grad_norm": 1.1948966979980469, "learning_rate": 5.245052770983838e-05, "loss": 0.43818273544311526, "step": 377890 }, { "epoch": 2.2463160772984763, "grad_norm": 1.0724081993103027, "learning_rate": 5.2445741982274656e-05, "loss": 0.5250607490539551, "step": 377900 }, { "epoch": 2.246375519375145, "grad_norm": 1.0835903882980347, "learning_rate": 5.2440956530031695e-05, "loss": 0.4330587387084961, "step": 377910 }, { "epoch": 2.246434961451813, "grad_norm": 1.7449994087219238, "learning_rate": 5.2436171353132344e-05, "loss": 0.4955177307128906, "step": 377920 }, { "epoch": 2.2464944035284815, "grad_norm": 1.0801365375518799, "learning_rate": 5.2431386451599576e-05, "loss": 0.4593297004699707, "step": 377930 }, { "epoch": 2.24655384560515, "grad_norm": 1.5555304288864136, "learning_rate": 5.242660182545627e-05, "loss": 0.5086719512939453, "step": 377940 }, { "epoch": 2.2466132876818183, "grad_norm": 1.415004014968872, "learning_rate": 5.242181747472523e-05, "loss": 0.5408731937408447, "step": 377950 }, { "epoch": 2.2466727297584868, "grad_norm": 1.6648625135421753, "learning_rate": 5.2417033399429425e-05, "loss": 0.5009317874908448, "step": 377960 }, { "epoch": 2.246732171835155, "grad_norm": 1.4054052829742432, "learning_rate": 5.241224959959172e-05, "loss": 0.5342333793640137, "step": 377970 }, { "epoch": 2.2467916139118236, "grad_norm": 1.3723297119140625, "learning_rate": 5.240746607523495e-05, "loss": 0.49816341400146485, "step": 377980 }, { "epoch": 2.246851055988492, "grad_norm": 1.200104832649231, "learning_rate": 5.240268282638208e-05, "loss": 0.5015316009521484, "step": 377990 }, { "epoch": 2.2469104980651604, "grad_norm": 1.1303551197052002, "learning_rate": 5.239789985305599e-05, "loss": 0.4872929573059082, "step": 378000 }, { "epoch": 2.246969940141829, "grad_norm": 1.1309162378311157, "learning_rate": 5.239311715527945e-05, "loss": 0.5112199783325195, "step": 378010 }, { "epoch": 2.2470293822184972, "grad_norm": 1.505868911743164, "learning_rate": 5.238833473307545e-05, "loss": 0.46802425384521484, "step": 378020 }, { "epoch": 2.2470888242951657, "grad_norm": 1.837032675743103, "learning_rate": 5.238355258646681e-05, "loss": 0.5560524940490723, "step": 378030 }, { "epoch": 2.247148266371834, "grad_norm": 1.2539091110229492, "learning_rate": 5.237877071547646e-05, "loss": 0.5381071090698242, "step": 378040 }, { "epoch": 2.2472077084485025, "grad_norm": 1.7039371728897095, "learning_rate": 5.237398912012716e-05, "loss": 0.5036865711212158, "step": 378050 }, { "epoch": 2.247267150525171, "grad_norm": 1.5420095920562744, "learning_rate": 5.236920780044197e-05, "loss": 0.5043810844421387, "step": 378060 }, { "epoch": 2.2473265926018393, "grad_norm": 1.2048143148422241, "learning_rate": 5.2364426756443594e-05, "loss": 0.45628948211669923, "step": 378070 }, { "epoch": 2.2473860346785077, "grad_norm": 1.4924792051315308, "learning_rate": 5.235964598815497e-05, "loss": 0.45347986221313474, "step": 378080 }, { "epoch": 2.2474454767551757, "grad_norm": 1.408489465713501, "learning_rate": 5.235486549559896e-05, "loss": 0.4500901222229004, "step": 378090 }, { "epoch": 2.247504918831844, "grad_norm": 1.4422314167022705, "learning_rate": 5.235008527879845e-05, "loss": 0.5097952842712402, "step": 378100 }, { "epoch": 2.2475643609085125, "grad_norm": 1.1512407064437866, "learning_rate": 5.2345305337776284e-05, "loss": 0.4836703300476074, "step": 378110 }, { "epoch": 2.247623802985181, "grad_norm": 1.2802435159683228, "learning_rate": 5.234052567255534e-05, "loss": 0.5078901767730712, "step": 378120 }, { "epoch": 2.2476832450618494, "grad_norm": 1.2286230325698853, "learning_rate": 5.233574628315847e-05, "loss": 0.5263032913208008, "step": 378130 }, { "epoch": 2.2477426871385178, "grad_norm": 1.3378809690475464, "learning_rate": 5.233096716960857e-05, "loss": 0.46253280639648436, "step": 378140 }, { "epoch": 2.247802129215186, "grad_norm": 1.7104512453079224, "learning_rate": 5.2326188331928415e-05, "loss": 0.4754194259643555, "step": 378150 }, { "epoch": 2.2478615712918546, "grad_norm": 1.2865878343582153, "learning_rate": 5.232140977014097e-05, "loss": 0.48998098373413085, "step": 378160 }, { "epoch": 2.247921013368523, "grad_norm": 1.4379026889801025, "learning_rate": 5.231663148426906e-05, "loss": 0.5239136219024658, "step": 378170 }, { "epoch": 2.2479804554451914, "grad_norm": 1.371466875076294, "learning_rate": 5.2311853474335524e-05, "loss": 0.5034780502319336, "step": 378180 }, { "epoch": 2.24803989752186, "grad_norm": 1.6932204961776733, "learning_rate": 5.230707574036324e-05, "loss": 0.5048582553863525, "step": 378190 }, { "epoch": 2.2480993395985283, "grad_norm": 1.5639649629592896, "learning_rate": 5.230229828237503e-05, "loss": 0.5008708953857421, "step": 378200 }, { "epoch": 2.2481587816751967, "grad_norm": 1.3463090658187866, "learning_rate": 5.2297521100393756e-05, "loss": 0.5138888359069824, "step": 378210 }, { "epoch": 2.248218223751865, "grad_norm": 1.2603429555892944, "learning_rate": 5.22927441944423e-05, "loss": 0.4438976287841797, "step": 378220 }, { "epoch": 2.2482776658285335, "grad_norm": 1.6271713972091675, "learning_rate": 5.22879675645435e-05, "loss": 0.4891524314880371, "step": 378230 }, { "epoch": 2.248337107905202, "grad_norm": 1.1049671173095703, "learning_rate": 5.2283191210720225e-05, "loss": 0.4804637908935547, "step": 378240 }, { "epoch": 2.2483965499818703, "grad_norm": 1.2607792615890503, "learning_rate": 5.2278415132995284e-05, "loss": 0.5755871772766114, "step": 378250 }, { "epoch": 2.2484559920585387, "grad_norm": 1.0630956888198853, "learning_rate": 5.227363933139153e-05, "loss": 0.520808219909668, "step": 378260 }, { "epoch": 2.248515434135207, "grad_norm": 1.6848024129867554, "learning_rate": 5.2268863805931835e-05, "loss": 0.5101703643798828, "step": 378270 }, { "epoch": 2.248574876211875, "grad_norm": 1.5578283071517944, "learning_rate": 5.2264088556639005e-05, "loss": 0.48233933448791505, "step": 378280 }, { "epoch": 2.2486343182885435, "grad_norm": 1.2999792098999023, "learning_rate": 5.225931358353593e-05, "loss": 0.5194228172302247, "step": 378290 }, { "epoch": 2.248693760365212, "grad_norm": 1.5193110704421997, "learning_rate": 5.225453888664542e-05, "loss": 0.4896883964538574, "step": 378300 }, { "epoch": 2.2487532024418804, "grad_norm": 1.0985774993896484, "learning_rate": 5.2249764465990335e-05, "loss": 0.49216570854187014, "step": 378310 }, { "epoch": 2.248812644518549, "grad_norm": 1.3376843929290771, "learning_rate": 5.224499032159349e-05, "loss": 0.4795189380645752, "step": 378320 }, { "epoch": 2.248872086595217, "grad_norm": 1.3039454221725464, "learning_rate": 5.224021645347776e-05, "loss": 0.457472038269043, "step": 378330 }, { "epoch": 2.2489315286718856, "grad_norm": 1.065422773361206, "learning_rate": 5.223544286166591e-05, "loss": 0.47930059432983396, "step": 378340 }, { "epoch": 2.248990970748554, "grad_norm": 1.2466663122177124, "learning_rate": 5.2230669546180854e-05, "loss": 0.5162380695343017, "step": 378350 }, { "epoch": 2.2490504128252224, "grad_norm": 1.4157922267913818, "learning_rate": 5.2225896507045415e-05, "loss": 0.5376045227050781, "step": 378360 }, { "epoch": 2.249109854901891, "grad_norm": 1.4316641092300415, "learning_rate": 5.2221123744282386e-05, "loss": 0.48505678176879885, "step": 378370 }, { "epoch": 2.2491692969785593, "grad_norm": 1.3767361640930176, "learning_rate": 5.221635125791462e-05, "loss": 0.4859572410583496, "step": 378380 }, { "epoch": 2.2492287390552277, "grad_norm": 1.8673745393753052, "learning_rate": 5.221157904796495e-05, "loss": 0.5360589981079101, "step": 378390 }, { "epoch": 2.249288181131896, "grad_norm": 1.4177862405776978, "learning_rate": 5.22068071144562e-05, "loss": 0.5359716415405273, "step": 378400 }, { "epoch": 2.2493476232085645, "grad_norm": 1.3432785272598267, "learning_rate": 5.2202035457411156e-05, "loss": 0.46625232696533203, "step": 378410 }, { "epoch": 2.249407065285233, "grad_norm": 1.3129526376724243, "learning_rate": 5.219726407685274e-05, "loss": 0.465320348739624, "step": 378420 }, { "epoch": 2.2494665073619013, "grad_norm": 1.5017006397247314, "learning_rate": 5.219249297280373e-05, "loss": 0.48349580764770506, "step": 378430 }, { "epoch": 2.2495259494385698, "grad_norm": 1.2450664043426514, "learning_rate": 5.218772214528691e-05, "loss": 0.4820101261138916, "step": 378440 }, { "epoch": 2.249585391515238, "grad_norm": 1.2689343690872192, "learning_rate": 5.218295159432514e-05, "loss": 0.516217041015625, "step": 378450 }, { "epoch": 2.2496448335919066, "grad_norm": 1.3254098892211914, "learning_rate": 5.217818131994123e-05, "loss": 0.4985218048095703, "step": 378460 }, { "epoch": 2.2497042756685746, "grad_norm": 1.2570767402648926, "learning_rate": 5.2173411322158005e-05, "loss": 0.48882007598876953, "step": 378470 }, { "epoch": 2.249763717745243, "grad_norm": 1.2575492858886719, "learning_rate": 5.216864160099828e-05, "loss": 0.4764594078063965, "step": 378480 }, { "epoch": 2.2498231598219114, "grad_norm": 1.5692877769470215, "learning_rate": 5.2163872156484926e-05, "loss": 0.49034719467163085, "step": 378490 }, { "epoch": 2.24988260189858, "grad_norm": 1.493868350982666, "learning_rate": 5.215910298864066e-05, "loss": 0.42854809761047363, "step": 378500 }, { "epoch": 2.249942043975248, "grad_norm": 1.2541050910949707, "learning_rate": 5.215433409748833e-05, "loss": 0.4925842761993408, "step": 378510 }, { "epoch": 2.2500014860519166, "grad_norm": 1.3280420303344727, "learning_rate": 5.2149565483050764e-05, "loss": 0.4868152618408203, "step": 378520 }, { "epoch": 2.250060928128585, "grad_norm": 1.2448500394821167, "learning_rate": 5.214479714535081e-05, "loss": 0.5155277252197266, "step": 378530 }, { "epoch": 2.2501203702052535, "grad_norm": 1.4013887643814087, "learning_rate": 5.214002908441118e-05, "loss": 0.4799070358276367, "step": 378540 }, { "epoch": 2.250179812281922, "grad_norm": 1.3940539360046387, "learning_rate": 5.213526130025481e-05, "loss": 0.4426259994506836, "step": 378550 }, { "epoch": 2.2502392543585903, "grad_norm": 1.3281506299972534, "learning_rate": 5.213049379290441e-05, "loss": 0.43741207122802733, "step": 378560 }, { "epoch": 2.2502986964352587, "grad_norm": 1.7015204429626465, "learning_rate": 5.212572656238277e-05, "loss": 0.5118905067443847, "step": 378570 }, { "epoch": 2.250358138511927, "grad_norm": 1.2359941005706787, "learning_rate": 5.212095960871279e-05, "loss": 0.4949198722839355, "step": 378580 }, { "epoch": 2.2504175805885955, "grad_norm": 1.2864543199539185, "learning_rate": 5.211619293191723e-05, "loss": 0.4464818000793457, "step": 378590 }, { "epoch": 2.250477022665264, "grad_norm": 1.5418095588684082, "learning_rate": 5.2111426532018834e-05, "loss": 0.5163615703582763, "step": 378600 }, { "epoch": 2.2505364647419324, "grad_norm": 1.1939117908477783, "learning_rate": 5.210666040904054e-05, "loss": 0.463893461227417, "step": 378610 }, { "epoch": 2.2505959068186008, "grad_norm": 1.2947418689727783, "learning_rate": 5.210189456300501e-05, "loss": 0.474276065826416, "step": 378620 }, { "epoch": 2.250655348895269, "grad_norm": 1.4007433652877808, "learning_rate": 5.209712899393511e-05, "loss": 0.4646409511566162, "step": 378630 }, { "epoch": 2.250714790971937, "grad_norm": 1.4718754291534424, "learning_rate": 5.209236370185359e-05, "loss": 0.5049538612365723, "step": 378640 }, { "epoch": 2.250774233048606, "grad_norm": 1.5032482147216797, "learning_rate": 5.20875986867833e-05, "loss": 0.4304826736450195, "step": 378650 }, { "epoch": 2.250833675125274, "grad_norm": 2.116191864013672, "learning_rate": 5.208283394874702e-05, "loss": 0.5162440299987793, "step": 378660 }, { "epoch": 2.2508931172019424, "grad_norm": 1.6774598360061646, "learning_rate": 5.2078069487767535e-05, "loss": 0.5311178207397461, "step": 378670 }, { "epoch": 2.250952559278611, "grad_norm": 1.3397811651229858, "learning_rate": 5.2073305303867624e-05, "loss": 0.4600590705871582, "step": 378680 }, { "epoch": 2.2510120013552792, "grad_norm": 1.4013323783874512, "learning_rate": 5.20685413970701e-05, "loss": 0.5210401535034179, "step": 378690 }, { "epoch": 2.2510714434319476, "grad_norm": 1.3009809255599976, "learning_rate": 5.206377776739773e-05, "loss": 0.5320217609405518, "step": 378700 }, { "epoch": 2.251130885508616, "grad_norm": 1.4521771669387817, "learning_rate": 5.205901441487331e-05, "loss": 0.48001980781555176, "step": 378710 }, { "epoch": 2.2511903275852845, "grad_norm": 1.2651777267456055, "learning_rate": 5.2054251339519645e-05, "loss": 0.537770938873291, "step": 378720 }, { "epoch": 2.251249769661953, "grad_norm": 1.3019320964813232, "learning_rate": 5.204948854135949e-05, "loss": 0.47031121253967284, "step": 378730 }, { "epoch": 2.2513092117386213, "grad_norm": 1.0678033828735352, "learning_rate": 5.204472602041567e-05, "loss": 0.4907256603240967, "step": 378740 }, { "epoch": 2.2513686538152897, "grad_norm": 1.3083350658416748, "learning_rate": 5.203996377671092e-05, "loss": 0.5091493606567383, "step": 378750 }, { "epoch": 2.251428095891958, "grad_norm": 1.3012038469314575, "learning_rate": 5.203520181026807e-05, "loss": 0.47277045249938965, "step": 378760 }, { "epoch": 2.2514875379686266, "grad_norm": 1.1412872076034546, "learning_rate": 5.20304401211098e-05, "loss": 0.5080910682678222, "step": 378770 }, { "epoch": 2.251546980045295, "grad_norm": 1.4032366275787354, "learning_rate": 5.202567870925902e-05, "loss": 0.49039487838745116, "step": 378780 }, { "epoch": 2.2516064221219634, "grad_norm": 1.069501519203186, "learning_rate": 5.202091757473844e-05, "loss": 0.49338245391845703, "step": 378790 }, { "epoch": 2.251665864198632, "grad_norm": 1.0072758197784424, "learning_rate": 5.201615671757083e-05, "loss": 0.4567223072052002, "step": 378800 }, { "epoch": 2.2517253062753, "grad_norm": 1.3205223083496094, "learning_rate": 5.2011396137778986e-05, "loss": 0.44142894744873046, "step": 378810 }, { "epoch": 2.2517847483519686, "grad_norm": 0.9111112952232361, "learning_rate": 5.2006635835385675e-05, "loss": 0.47077789306640627, "step": 378820 }, { "epoch": 2.2518441904286366, "grad_norm": 1.4838168621063232, "learning_rate": 5.2001875810413645e-05, "loss": 0.46651325225830076, "step": 378830 }, { "epoch": 2.2519036325053055, "grad_norm": 1.5220495462417603, "learning_rate": 5.1997116062885706e-05, "loss": 0.49637541770935056, "step": 378840 }, { "epoch": 2.2519630745819734, "grad_norm": 1.372778058052063, "learning_rate": 5.199235659282461e-05, "loss": 0.4746382236480713, "step": 378850 }, { "epoch": 2.252022516658642, "grad_norm": 1.5743168592453003, "learning_rate": 5.1987597400253115e-05, "loss": 0.5067785739898681, "step": 378860 }, { "epoch": 2.2520819587353103, "grad_norm": 1.3162530660629272, "learning_rate": 5.198283848519401e-05, "loss": 0.5136367797851562, "step": 378870 }, { "epoch": 2.2521414008119787, "grad_norm": 1.4851038455963135, "learning_rate": 5.197807984767002e-05, "loss": 0.5039949893951416, "step": 378880 }, { "epoch": 2.252200842888647, "grad_norm": 1.3600729703903198, "learning_rate": 5.197332148770396e-05, "loss": 0.5113414764404297, "step": 378890 }, { "epoch": 2.2522602849653155, "grad_norm": 1.2103333473205566, "learning_rate": 5.196856340531853e-05, "loss": 0.5072122097015381, "step": 378900 }, { "epoch": 2.252319727041984, "grad_norm": 1.5864490270614624, "learning_rate": 5.1963805600536553e-05, "loss": 0.5376031875610352, "step": 378910 }, { "epoch": 2.2523791691186523, "grad_norm": 1.0564347505569458, "learning_rate": 5.19590480733808e-05, "loss": 0.4573019027709961, "step": 378920 }, { "epoch": 2.2524386111953207, "grad_norm": 1.4830728769302368, "learning_rate": 5.195429082387393e-05, "loss": 0.5047749519348145, "step": 378930 }, { "epoch": 2.252498053271989, "grad_norm": 1.6324771642684937, "learning_rate": 5.194953385203878e-05, "loss": 0.4556908130645752, "step": 378940 }, { "epoch": 2.2525574953486576, "grad_norm": 1.4103950262069702, "learning_rate": 5.194477715789812e-05, "loss": 0.5133790969848633, "step": 378950 }, { "epoch": 2.252616937425326, "grad_norm": 1.6511616706848145, "learning_rate": 5.194002074147461e-05, "loss": 0.46218137741088866, "step": 378960 }, { "epoch": 2.2526763795019944, "grad_norm": 0.9430492520332336, "learning_rate": 5.193526460279111e-05, "loss": 0.5241888999938965, "step": 378970 }, { "epoch": 2.252735821578663, "grad_norm": 1.3651043176651, "learning_rate": 5.193050874187037e-05, "loss": 0.5040530681610107, "step": 378980 }, { "epoch": 2.2527952636553312, "grad_norm": 1.4635581970214844, "learning_rate": 5.1925753158735047e-05, "loss": 0.44375128746032716, "step": 378990 }, { "epoch": 2.2528547057319996, "grad_norm": 1.0967596769332886, "learning_rate": 5.1920997853407925e-05, "loss": 0.4633178234100342, "step": 379000 }, { "epoch": 2.252914147808668, "grad_norm": 1.5412428379058838, "learning_rate": 5.19162428259118e-05, "loss": 0.46050825119018557, "step": 379010 }, { "epoch": 2.252973589885336, "grad_norm": 1.3227438926696777, "learning_rate": 5.191148807626939e-05, "loss": 0.505474853515625, "step": 379020 }, { "epoch": 2.2530330319620044, "grad_norm": 1.1113836765289307, "learning_rate": 5.19067336045034e-05, "loss": 0.4624089241027832, "step": 379030 }, { "epoch": 2.253092474038673, "grad_norm": 2.224731922149658, "learning_rate": 5.190197941063668e-05, "loss": 0.5054201126098633, "step": 379040 }, { "epoch": 2.2531519161153413, "grad_norm": 1.399326205253601, "learning_rate": 5.189722549469185e-05, "loss": 0.48621387481689454, "step": 379050 }, { "epoch": 2.2532113581920097, "grad_norm": 1.2275749444961548, "learning_rate": 5.1892471856691704e-05, "loss": 0.512787914276123, "step": 379060 }, { "epoch": 2.253270800268678, "grad_norm": 1.677578330039978, "learning_rate": 5.1887718496659e-05, "loss": 0.5472039699554443, "step": 379070 }, { "epoch": 2.2533302423453465, "grad_norm": 0.9970449209213257, "learning_rate": 5.1882965414616457e-05, "loss": 0.4504550933837891, "step": 379080 }, { "epoch": 2.253389684422015, "grad_norm": 1.4268275499343872, "learning_rate": 5.1878212610586783e-05, "loss": 0.5321897506713867, "step": 379090 }, { "epoch": 2.2534491264986833, "grad_norm": 1.2149255275726318, "learning_rate": 5.1873460084592816e-05, "loss": 0.48790922164916994, "step": 379100 }, { "epoch": 2.2535085685753518, "grad_norm": 1.3727375268936157, "learning_rate": 5.186870783665718e-05, "loss": 0.46351985931396483, "step": 379110 }, { "epoch": 2.25356801065202, "grad_norm": 1.8725967407226562, "learning_rate": 5.186395586680266e-05, "loss": 0.5051836013793946, "step": 379120 }, { "epoch": 2.2536274527286886, "grad_norm": 1.6358473300933838, "learning_rate": 5.1859204175051946e-05, "loss": 0.5183240413665772, "step": 379130 }, { "epoch": 2.253686894805357, "grad_norm": 1.5402014255523682, "learning_rate": 5.185445276142782e-05, "loss": 0.5038615226745605, "step": 379140 }, { "epoch": 2.2537463368820254, "grad_norm": 1.4776467084884644, "learning_rate": 5.184970162595299e-05, "loss": 0.4835999011993408, "step": 379150 }, { "epoch": 2.253805778958694, "grad_norm": 1.1666021347045898, "learning_rate": 5.184495076865018e-05, "loss": 0.4593662738800049, "step": 379160 }, { "epoch": 2.2538652210353622, "grad_norm": 1.4381135702133179, "learning_rate": 5.184020018954212e-05, "loss": 0.4827691078186035, "step": 379170 }, { "epoch": 2.2539246631120307, "grad_norm": 1.4014173746109009, "learning_rate": 5.183544988865154e-05, "loss": 0.45649542808532717, "step": 379180 }, { "epoch": 2.2539841051886986, "grad_norm": 1.8742852210998535, "learning_rate": 5.1830699866001134e-05, "loss": 0.5060557842254638, "step": 379190 }, { "epoch": 2.2540435472653675, "grad_norm": 1.5766046047210693, "learning_rate": 5.182595012161369e-05, "loss": 0.4718631744384766, "step": 379200 }, { "epoch": 2.2541029893420355, "grad_norm": 1.5044435262680054, "learning_rate": 5.182120065551186e-05, "loss": 0.5197409629821778, "step": 379210 }, { "epoch": 2.254162431418704, "grad_norm": 1.5522829294204712, "learning_rate": 5.181645146771841e-05, "loss": 0.5007363319396972, "step": 379220 }, { "epoch": 2.2542218734953723, "grad_norm": 1.291306495666504, "learning_rate": 5.181170255825605e-05, "loss": 0.47542400360107423, "step": 379230 }, { "epoch": 2.2542813155720407, "grad_norm": 1.2728571891784668, "learning_rate": 5.180695392714747e-05, "loss": 0.4728271484375, "step": 379240 }, { "epoch": 2.254340757648709, "grad_norm": 1.5898314714431763, "learning_rate": 5.180220557441542e-05, "loss": 0.5317874908447265, "step": 379250 }, { "epoch": 2.2544001997253775, "grad_norm": 1.2079042196273804, "learning_rate": 5.1797457500082556e-05, "loss": 0.46874179840087893, "step": 379260 }, { "epoch": 2.254459641802046, "grad_norm": 1.0321420431137085, "learning_rate": 5.179270970417167e-05, "loss": 0.5121009349822998, "step": 379270 }, { "epoch": 2.2545190838787144, "grad_norm": 1.2994767427444458, "learning_rate": 5.178796218670543e-05, "loss": 0.5512346267700196, "step": 379280 }, { "epoch": 2.2545785259553828, "grad_norm": 1.2979487180709839, "learning_rate": 5.178321494770657e-05, "loss": 0.4952253341674805, "step": 379290 }, { "epoch": 2.254637968032051, "grad_norm": 1.3859039545059204, "learning_rate": 5.1778467987197786e-05, "loss": 0.5205802917480469, "step": 379300 }, { "epoch": 2.2546974101087196, "grad_norm": 1.231858491897583, "learning_rate": 5.177372130520177e-05, "loss": 0.5157696723937988, "step": 379310 }, { "epoch": 2.254756852185388, "grad_norm": 1.0062763690948486, "learning_rate": 5.176897490174122e-05, "loss": 0.4903275966644287, "step": 379320 }, { "epoch": 2.2548162942620564, "grad_norm": 1.2010095119476318, "learning_rate": 5.17642287768389e-05, "loss": 0.4610104560852051, "step": 379330 }, { "epoch": 2.254875736338725, "grad_norm": 1.442306399345398, "learning_rate": 5.1759482930517465e-05, "loss": 0.5258547306060791, "step": 379340 }, { "epoch": 2.2549351784153933, "grad_norm": 1.3987034559249878, "learning_rate": 5.175473736279963e-05, "loss": 0.5271097660064697, "step": 379350 }, { "epoch": 2.2549946204920617, "grad_norm": 1.1747044324874878, "learning_rate": 5.174999207370812e-05, "loss": 0.46689939498901367, "step": 379360 }, { "epoch": 2.25505406256873, "grad_norm": 1.0613716840744019, "learning_rate": 5.17452470632656e-05, "loss": 0.4604348182678223, "step": 379370 }, { "epoch": 2.255113504645398, "grad_norm": 1.3260178565979004, "learning_rate": 5.174050233149477e-05, "loss": 0.5172954082489014, "step": 379380 }, { "epoch": 2.255172946722067, "grad_norm": 0.9836302399635315, "learning_rate": 5.173575787841831e-05, "loss": 0.4572652816772461, "step": 379390 }, { "epoch": 2.255232388798735, "grad_norm": 1.5121732950210571, "learning_rate": 5.1731013704058975e-05, "loss": 0.5091093063354493, "step": 379400 }, { "epoch": 2.2552918308754033, "grad_norm": 1.4128620624542236, "learning_rate": 5.172626980843942e-05, "loss": 0.4631324768066406, "step": 379410 }, { "epoch": 2.2553512729520717, "grad_norm": 1.0351154804229736, "learning_rate": 5.172152619158237e-05, "loss": 0.45996909141540526, "step": 379420 }, { "epoch": 2.25541071502874, "grad_norm": 1.4438985586166382, "learning_rate": 5.171678285351047e-05, "loss": 0.5223899841308594, "step": 379430 }, { "epoch": 2.2554701571054085, "grad_norm": 1.1294748783111572, "learning_rate": 5.171203979424644e-05, "loss": 0.46373577117919923, "step": 379440 }, { "epoch": 2.255529599182077, "grad_norm": 1.3227566480636597, "learning_rate": 5.1707297013812936e-05, "loss": 0.5005193710327148, "step": 379450 }, { "epoch": 2.2555890412587454, "grad_norm": 1.2843540906906128, "learning_rate": 5.1702554512232715e-05, "loss": 0.48727941513061523, "step": 379460 }, { "epoch": 2.255648483335414, "grad_norm": 1.4557044506072998, "learning_rate": 5.169781228952839e-05, "loss": 0.5118764877319336, "step": 379470 }, { "epoch": 2.255707925412082, "grad_norm": 1.2416623830795288, "learning_rate": 5.1693070345722724e-05, "loss": 0.46396121978759763, "step": 379480 }, { "epoch": 2.2557673674887506, "grad_norm": 1.28556489944458, "learning_rate": 5.168832868083831e-05, "loss": 0.4752506256103516, "step": 379490 }, { "epoch": 2.255826809565419, "grad_norm": 1.5449447631835938, "learning_rate": 5.168358729489789e-05, "loss": 0.5012178897857666, "step": 379500 }, { "epoch": 2.2558862516420874, "grad_norm": 1.2120256423950195, "learning_rate": 5.1678846187924136e-05, "loss": 0.45738515853881834, "step": 379510 }, { "epoch": 2.255945693718756, "grad_norm": 1.4284793138504028, "learning_rate": 5.1674105359939686e-05, "loss": 0.5458128929138184, "step": 379520 }, { "epoch": 2.2560051357954243, "grad_norm": 1.3464020490646362, "learning_rate": 5.166936481096731e-05, "loss": 0.4942750930786133, "step": 379530 }, { "epoch": 2.2560645778720927, "grad_norm": 1.3269184827804565, "learning_rate": 5.16646245410296e-05, "loss": 0.4922776222229004, "step": 379540 }, { "epoch": 2.256124019948761, "grad_norm": 1.3658397197723389, "learning_rate": 5.1659884550149254e-05, "loss": 0.46021242141723634, "step": 379550 }, { "epoch": 2.2561834620254295, "grad_norm": 1.0829339027404785, "learning_rate": 5.165514483834897e-05, "loss": 0.46380224227905276, "step": 379560 }, { "epoch": 2.2562429041020975, "grad_norm": 1.3135097026824951, "learning_rate": 5.16504054056514e-05, "loss": 0.5327853202819824, "step": 379570 }, { "epoch": 2.2563023461787663, "grad_norm": 1.4670137166976929, "learning_rate": 5.164566625207921e-05, "loss": 0.439715051651001, "step": 379580 }, { "epoch": 2.2563617882554343, "grad_norm": 1.1511410474777222, "learning_rate": 5.164092737765511e-05, "loss": 0.5455041885375976, "step": 379590 }, { "epoch": 2.2564212303321027, "grad_norm": 1.4913465976715088, "learning_rate": 5.163618878240173e-05, "loss": 0.45058484077453614, "step": 379600 }, { "epoch": 2.256480672408771, "grad_norm": 1.356777548789978, "learning_rate": 5.163145046634176e-05, "loss": 0.4868281841278076, "step": 379610 }, { "epoch": 2.2565401144854396, "grad_norm": 1.8336660861968994, "learning_rate": 5.162671242949781e-05, "loss": 0.4937891006469727, "step": 379620 }, { "epoch": 2.256599556562108, "grad_norm": 1.4658286571502686, "learning_rate": 5.1621974671892626e-05, "loss": 0.47224082946777346, "step": 379630 }, { "epoch": 2.2566589986387764, "grad_norm": 1.2593320608139038, "learning_rate": 5.161723719354884e-05, "loss": 0.49575300216674806, "step": 379640 }, { "epoch": 2.256718440715445, "grad_norm": 1.2959952354431152, "learning_rate": 5.1612499994489116e-05, "loss": 0.4922971725463867, "step": 379650 }, { "epoch": 2.256777882792113, "grad_norm": 1.2070152759552002, "learning_rate": 5.1607763074736105e-05, "loss": 0.4649677753448486, "step": 379660 }, { "epoch": 2.2568373248687816, "grad_norm": 1.4870178699493408, "learning_rate": 5.1603026434312476e-05, "loss": 0.5127877235412598, "step": 379670 }, { "epoch": 2.25689676694545, "grad_norm": 1.1174802780151367, "learning_rate": 5.159829007324084e-05, "loss": 0.5313526153564453, "step": 379680 }, { "epoch": 2.2569562090221185, "grad_norm": 1.585142970085144, "learning_rate": 5.159355399154394e-05, "loss": 0.4520680904388428, "step": 379690 }, { "epoch": 2.257015651098787, "grad_norm": 1.3990697860717773, "learning_rate": 5.158881818924439e-05, "loss": 0.4569122314453125, "step": 379700 }, { "epoch": 2.2570750931754553, "grad_norm": 1.2819432020187378, "learning_rate": 5.1584082666364855e-05, "loss": 0.4880247116088867, "step": 379710 }, { "epoch": 2.2571345352521237, "grad_norm": 1.4747432470321655, "learning_rate": 5.157934742292796e-05, "loss": 0.4898704528808594, "step": 379720 }, { "epoch": 2.257193977328792, "grad_norm": 1.336483120918274, "learning_rate": 5.1574612458956385e-05, "loss": 0.5079471588134765, "step": 379730 }, { "epoch": 2.2572534194054605, "grad_norm": 1.1661962270736694, "learning_rate": 5.1569877774472764e-05, "loss": 0.5332126617431641, "step": 379740 }, { "epoch": 2.257312861482129, "grad_norm": 1.2366554737091064, "learning_rate": 5.1565143369499715e-05, "loss": 0.49683356285095215, "step": 379750 }, { "epoch": 2.257372303558797, "grad_norm": 1.434592604637146, "learning_rate": 5.156040924405996e-05, "loss": 0.515545654296875, "step": 379760 }, { "epoch": 2.2574317456354653, "grad_norm": 1.2954294681549072, "learning_rate": 5.155567539817612e-05, "loss": 0.5150959014892578, "step": 379770 }, { "epoch": 2.2574911877121338, "grad_norm": 1.6416834592819214, "learning_rate": 5.155094183187083e-05, "loss": 0.4459968566894531, "step": 379780 }, { "epoch": 2.257550629788802, "grad_norm": 1.3953843116760254, "learning_rate": 5.154620854516672e-05, "loss": 0.463043212890625, "step": 379790 }, { "epoch": 2.2576100718654706, "grad_norm": 1.275551199913025, "learning_rate": 5.154147553808645e-05, "loss": 0.5012305736541748, "step": 379800 }, { "epoch": 2.257669513942139, "grad_norm": 1.4952105283737183, "learning_rate": 5.153674281065263e-05, "loss": 0.49038944244384763, "step": 379810 }, { "epoch": 2.2577289560188074, "grad_norm": 1.284142017364502, "learning_rate": 5.153201036288795e-05, "loss": 0.477354621887207, "step": 379820 }, { "epoch": 2.257788398095476, "grad_norm": 1.046802043914795, "learning_rate": 5.152727819481502e-05, "loss": 0.47936697006225587, "step": 379830 }, { "epoch": 2.2578478401721442, "grad_norm": 1.5336905717849731, "learning_rate": 5.15225463064565e-05, "loss": 0.5055565357208252, "step": 379840 }, { "epoch": 2.2579072822488127, "grad_norm": 1.0840229988098145, "learning_rate": 5.1517814697835e-05, "loss": 0.47081289291381834, "step": 379850 }, { "epoch": 2.257966724325481, "grad_norm": 1.1134179830551147, "learning_rate": 5.1513083368973156e-05, "loss": 0.5025462627410888, "step": 379860 }, { "epoch": 2.2580261664021495, "grad_norm": 1.4142589569091797, "learning_rate": 5.150835231989362e-05, "loss": 0.4729414463043213, "step": 379870 }, { "epoch": 2.258085608478818, "grad_norm": 1.1792529821395874, "learning_rate": 5.150362155061896e-05, "loss": 0.5407504081726074, "step": 379880 }, { "epoch": 2.2581450505554863, "grad_norm": 1.3003573417663574, "learning_rate": 5.1498891061171904e-05, "loss": 0.5341029167175293, "step": 379890 }, { "epoch": 2.2582044926321547, "grad_norm": 1.1896321773529053, "learning_rate": 5.149416085157503e-05, "loss": 0.4729767799377441, "step": 379900 }, { "epoch": 2.258263934708823, "grad_norm": 1.3415210247039795, "learning_rate": 5.1489430921850965e-05, "loss": 0.5147274494171142, "step": 379910 }, { "epoch": 2.2583233767854916, "grad_norm": 1.3033947944641113, "learning_rate": 5.148470127202236e-05, "loss": 0.5042019367218018, "step": 379920 }, { "epoch": 2.2583828188621595, "grad_norm": 1.5587960481643677, "learning_rate": 5.14799719021118e-05, "loss": 0.5091529369354248, "step": 379930 }, { "epoch": 2.2584422609388284, "grad_norm": 1.8710839748382568, "learning_rate": 5.147524281214191e-05, "loss": 0.5198579788208008, "step": 379940 }, { "epoch": 2.2585017030154964, "grad_norm": 1.6107245683670044, "learning_rate": 5.147051400213537e-05, "loss": 0.49791440963745115, "step": 379950 }, { "epoch": 2.2585611450921648, "grad_norm": 1.262053370475769, "learning_rate": 5.1465785472114755e-05, "loss": 0.4718867301940918, "step": 379960 }, { "epoch": 2.258620587168833, "grad_norm": 1.1700986623764038, "learning_rate": 5.146105722210273e-05, "loss": 0.49337544441223147, "step": 379970 }, { "epoch": 2.2586800292455016, "grad_norm": 1.314699411392212, "learning_rate": 5.1456329252121806e-05, "loss": 0.5304513454437256, "step": 379980 }, { "epoch": 2.25873947132217, "grad_norm": 1.3851526975631714, "learning_rate": 5.145160156219471e-05, "loss": 0.48775901794433596, "step": 379990 }, { "epoch": 2.2587989133988384, "grad_norm": 1.4421247243881226, "learning_rate": 5.144687415234399e-05, "loss": 0.5217489242553711, "step": 380000 }, { "epoch": 2.258858355475507, "grad_norm": 1.3052208423614502, "learning_rate": 5.144214702259229e-05, "loss": 0.5636063098907471, "step": 380010 }, { "epoch": 2.2589177975521753, "grad_norm": 1.329857349395752, "learning_rate": 5.143742017296225e-05, "loss": 0.5442373275756835, "step": 380020 }, { "epoch": 2.2589772396288437, "grad_norm": 1.3841743469238281, "learning_rate": 5.1432693603476464e-05, "loss": 0.5238106727600098, "step": 380030 }, { "epoch": 2.259036681705512, "grad_norm": 1.422343134880066, "learning_rate": 5.1427967314157486e-05, "loss": 0.4940251350402832, "step": 380040 }, { "epoch": 2.2590961237821805, "grad_norm": 1.126602053642273, "learning_rate": 5.1423241305028e-05, "loss": 0.5280208587646484, "step": 380050 }, { "epoch": 2.259155565858849, "grad_norm": 0.8745457530021667, "learning_rate": 5.141851557611058e-05, "loss": 0.47557849884033204, "step": 380060 }, { "epoch": 2.2592150079355173, "grad_norm": 1.4120008945465088, "learning_rate": 5.141379012742781e-05, "loss": 0.4807765483856201, "step": 380070 }, { "epoch": 2.2592744500121857, "grad_norm": 1.516624093055725, "learning_rate": 5.140906495900235e-05, "loss": 0.5047418117523194, "step": 380080 }, { "epoch": 2.259333892088854, "grad_norm": 1.4037559032440186, "learning_rate": 5.1404340070856814e-05, "loss": 0.49853153228759767, "step": 380090 }, { "epoch": 2.2593933341655226, "grad_norm": 1.636867642402649, "learning_rate": 5.139961546301373e-05, "loss": 0.5078789710998535, "step": 380100 }, { "epoch": 2.259452776242191, "grad_norm": 1.1387507915496826, "learning_rate": 5.139489113549571e-05, "loss": 0.4806813716888428, "step": 380110 }, { "epoch": 2.259512218318859, "grad_norm": 1.307016134262085, "learning_rate": 5.139016708832538e-05, "loss": 0.5301366806030273, "step": 380120 }, { "epoch": 2.259571660395528, "grad_norm": 1.7126384973526, "learning_rate": 5.1385443321525374e-05, "loss": 0.5060419082641602, "step": 380130 }, { "epoch": 2.259631102472196, "grad_norm": 2.015624523162842, "learning_rate": 5.138071983511823e-05, "loss": 0.48870220184326174, "step": 380140 }, { "epoch": 2.259690544548864, "grad_norm": 1.1753259897232056, "learning_rate": 5.137599662912658e-05, "loss": 0.49855942726135255, "step": 380150 }, { "epoch": 2.2597499866255326, "grad_norm": 1.1955476999282837, "learning_rate": 5.1371273703572996e-05, "loss": 0.4911334991455078, "step": 380160 }, { "epoch": 2.259809428702201, "grad_norm": 1.1669920682907104, "learning_rate": 5.136655105848004e-05, "loss": 0.4956169605255127, "step": 380170 }, { "epoch": 2.2598688707788694, "grad_norm": 1.4888392686843872, "learning_rate": 5.1361828693870386e-05, "loss": 0.5421199321746826, "step": 380180 }, { "epoch": 2.259928312855538, "grad_norm": 1.0687006711959839, "learning_rate": 5.135710660976657e-05, "loss": 0.5271481037139892, "step": 380190 }, { "epoch": 2.2599877549322063, "grad_norm": 1.1664040088653564, "learning_rate": 5.13523848061912e-05, "loss": 0.48109097480773927, "step": 380200 }, { "epoch": 2.2600471970088747, "grad_norm": 1.5962433815002441, "learning_rate": 5.134766328316685e-05, "loss": 0.5046164989471436, "step": 380210 }, { "epoch": 2.260106639085543, "grad_norm": 1.2119587659835815, "learning_rate": 5.1342942040716116e-05, "loss": 0.455076789855957, "step": 380220 }, { "epoch": 2.2601660811622115, "grad_norm": 1.275151252746582, "learning_rate": 5.133822107886157e-05, "loss": 0.4929961204528809, "step": 380230 }, { "epoch": 2.26022552323888, "grad_norm": 1.1445646286010742, "learning_rate": 5.1333500397625765e-05, "loss": 0.48827152252197265, "step": 380240 }, { "epoch": 2.2602849653155483, "grad_norm": 1.202481985092163, "learning_rate": 5.132877999703136e-05, "loss": 0.5153825759887696, "step": 380250 }, { "epoch": 2.2603444073922168, "grad_norm": 1.415616750717163, "learning_rate": 5.1324059877100916e-05, "loss": 0.45774288177490235, "step": 380260 }, { "epoch": 2.260403849468885, "grad_norm": 1.4461698532104492, "learning_rate": 5.131934003785698e-05, "loss": 0.513045072555542, "step": 380270 }, { "epoch": 2.2604632915455536, "grad_norm": 1.2714180946350098, "learning_rate": 5.131462047932214e-05, "loss": 0.4806044101715088, "step": 380280 }, { "epoch": 2.260522733622222, "grad_norm": 1.3184123039245605, "learning_rate": 5.1309901201518975e-05, "loss": 0.4593788146972656, "step": 380290 }, { "epoch": 2.2605821756988904, "grad_norm": 0.9599728584289551, "learning_rate": 5.130518220447005e-05, "loss": 0.4571844100952148, "step": 380300 }, { "epoch": 2.2606416177755584, "grad_norm": 1.4308993816375732, "learning_rate": 5.130046348819797e-05, "loss": 0.5223016738891602, "step": 380310 }, { "epoch": 2.2607010598522272, "grad_norm": 1.456802487373352, "learning_rate": 5.129574505272529e-05, "loss": 0.4944176197052002, "step": 380320 }, { "epoch": 2.260760501928895, "grad_norm": 1.4785596132278442, "learning_rate": 5.129102689807458e-05, "loss": 0.4641932487487793, "step": 380330 }, { "epoch": 2.2608199440055636, "grad_norm": 1.187516212463379, "learning_rate": 5.128630902426841e-05, "loss": 0.506839656829834, "step": 380340 }, { "epoch": 2.260879386082232, "grad_norm": 1.3655638694763184, "learning_rate": 5.1281591431329345e-05, "loss": 0.5018115520477295, "step": 380350 }, { "epoch": 2.2609388281589005, "grad_norm": 1.4153831005096436, "learning_rate": 5.127687411927996e-05, "loss": 0.43456377983093264, "step": 380360 }, { "epoch": 2.260998270235569, "grad_norm": 1.723811149597168, "learning_rate": 5.12721570881428e-05, "loss": 0.5151642799377442, "step": 380370 }, { "epoch": 2.2610577123122373, "grad_norm": 1.4044549465179443, "learning_rate": 5.126744033794046e-05, "loss": 0.5670673370361328, "step": 380380 }, { "epoch": 2.2611171543889057, "grad_norm": 1.6092607975006104, "learning_rate": 5.1262723868695506e-05, "loss": 0.47031192779541015, "step": 380390 }, { "epoch": 2.261176596465574, "grad_norm": 1.4585952758789062, "learning_rate": 5.125800768043047e-05, "loss": 0.5222569465637207, "step": 380400 }, { "epoch": 2.2612360385422425, "grad_norm": 1.3926644325256348, "learning_rate": 5.1253291773167956e-05, "loss": 0.5218537807464599, "step": 380410 }, { "epoch": 2.261295480618911, "grad_norm": 1.0848731994628906, "learning_rate": 5.1248576146930486e-05, "loss": 0.4908901214599609, "step": 380420 }, { "epoch": 2.2613549226955794, "grad_norm": 1.7006484270095825, "learning_rate": 5.1243860801740574e-05, "loss": 0.5119247436523438, "step": 380430 }, { "epoch": 2.2614143647722478, "grad_norm": 1.449796199798584, "learning_rate": 5.123914573762087e-05, "loss": 0.5292165756225586, "step": 380440 }, { "epoch": 2.261473806848916, "grad_norm": 1.5795347690582275, "learning_rate": 5.12344309545939e-05, "loss": 0.5143620491027832, "step": 380450 }, { "epoch": 2.2615332489255846, "grad_norm": 1.3209202289581299, "learning_rate": 5.122971645268224e-05, "loss": 0.5556350708007812, "step": 380460 }, { "epoch": 2.261592691002253, "grad_norm": 1.577301025390625, "learning_rate": 5.1225002231908335e-05, "loss": 0.4599002838134766, "step": 380470 }, { "epoch": 2.2616521330789214, "grad_norm": 1.4248043298721313, "learning_rate": 5.122028829229486e-05, "loss": 0.5213996887207031, "step": 380480 }, { "epoch": 2.26171157515559, "grad_norm": 1.4502700567245483, "learning_rate": 5.121557463386429e-05, "loss": 0.5000616073608398, "step": 380490 }, { "epoch": 2.261771017232258, "grad_norm": 1.2732099294662476, "learning_rate": 5.12108612566392e-05, "loss": 0.5466612815856934, "step": 380500 }, { "epoch": 2.2618304593089262, "grad_norm": 1.4897478818893433, "learning_rate": 5.120614816064215e-05, "loss": 0.4827445030212402, "step": 380510 }, { "epoch": 2.2618899013855946, "grad_norm": 1.3397066593170166, "learning_rate": 5.12014353458957e-05, "loss": 0.49319796562194823, "step": 380520 }, { "epoch": 2.261949343462263, "grad_norm": 1.3166319131851196, "learning_rate": 5.119672281242232e-05, "loss": 0.51619873046875, "step": 380530 }, { "epoch": 2.2620087855389315, "grad_norm": 1.3043651580810547, "learning_rate": 5.119201056024463e-05, "loss": 0.5074790954589844, "step": 380540 }, { "epoch": 2.2620682276156, "grad_norm": 1.2397592067718506, "learning_rate": 5.118729858938513e-05, "loss": 0.4637470245361328, "step": 380550 }, { "epoch": 2.2621276696922683, "grad_norm": 1.3865708112716675, "learning_rate": 5.1182586899866345e-05, "loss": 0.4571687698364258, "step": 380560 }, { "epoch": 2.2621871117689367, "grad_norm": 1.5445308685302734, "learning_rate": 5.117787549171088e-05, "loss": 0.5020073413848877, "step": 380570 }, { "epoch": 2.262246553845605, "grad_norm": 1.048064112663269, "learning_rate": 5.117316436494126e-05, "loss": 0.502357006072998, "step": 380580 }, { "epoch": 2.2623059959222735, "grad_norm": 1.3841760158538818, "learning_rate": 5.116845351957997e-05, "loss": 0.5465551376342773, "step": 380590 }, { "epoch": 2.262365437998942, "grad_norm": 1.1098933219909668, "learning_rate": 5.116374295564956e-05, "loss": 0.48301000595092775, "step": 380600 }, { "epoch": 2.2624248800756104, "grad_norm": 1.4150797128677368, "learning_rate": 5.1159032673172594e-05, "loss": 0.488979434967041, "step": 380610 }, { "epoch": 2.262484322152279, "grad_norm": 1.748908281326294, "learning_rate": 5.115432267217157e-05, "loss": 0.5032268524169922, "step": 380620 }, { "epoch": 2.262543764228947, "grad_norm": 1.3200637102127075, "learning_rate": 5.114961295266901e-05, "loss": 0.5045589447021485, "step": 380630 }, { "epoch": 2.2626032063056156, "grad_norm": 1.2233941555023193, "learning_rate": 5.1144903514687536e-05, "loss": 0.4675590991973877, "step": 380640 }, { "epoch": 2.262662648382284, "grad_norm": 1.1361972093582153, "learning_rate": 5.1140194358249596e-05, "loss": 0.49166069030761717, "step": 380650 }, { "epoch": 2.2627220904589525, "grad_norm": 1.448905348777771, "learning_rate": 5.113548548337768e-05, "loss": 0.45534572601318357, "step": 380660 }, { "epoch": 2.2627815325356204, "grad_norm": 1.5465595722198486, "learning_rate": 5.113077689009438e-05, "loss": 0.4775334358215332, "step": 380670 }, { "epoch": 2.2628409746122893, "grad_norm": 1.2158654928207397, "learning_rate": 5.1126068578422236e-05, "loss": 0.49244985580444334, "step": 380680 }, { "epoch": 2.2629004166889573, "grad_norm": 1.3496685028076172, "learning_rate": 5.1121360548383725e-05, "loss": 0.44285025596618655, "step": 380690 }, { "epoch": 2.2629598587656257, "grad_norm": 1.6056585311889648, "learning_rate": 5.1116652800001375e-05, "loss": 0.5206553936004639, "step": 380700 }, { "epoch": 2.263019300842294, "grad_norm": 1.4810200929641724, "learning_rate": 5.111194533329773e-05, "loss": 0.47160024642944337, "step": 380710 }, { "epoch": 2.2630787429189625, "grad_norm": 1.3874118328094482, "learning_rate": 5.110723814829529e-05, "loss": 0.5107297897338867, "step": 380720 }, { "epoch": 2.263138184995631, "grad_norm": 1.4346296787261963, "learning_rate": 5.110253124501654e-05, "loss": 0.4588637351989746, "step": 380730 }, { "epoch": 2.2631976270722993, "grad_norm": 1.3793632984161377, "learning_rate": 5.109782462348407e-05, "loss": 0.5114222526550293, "step": 380740 }, { "epoch": 2.2632570691489677, "grad_norm": 1.374213695526123, "learning_rate": 5.1093118283720357e-05, "loss": 0.47409281730651853, "step": 380750 }, { "epoch": 2.263316511225636, "grad_norm": 1.161394715309143, "learning_rate": 5.1088412225747904e-05, "loss": 0.5020232677459717, "step": 380760 }, { "epoch": 2.2633759533023046, "grad_norm": 1.4100944995880127, "learning_rate": 5.108370644958924e-05, "loss": 0.5315122604370117, "step": 380770 }, { "epoch": 2.263435395378973, "grad_norm": 1.21153724193573, "learning_rate": 5.1079000955266875e-05, "loss": 0.4976065635681152, "step": 380780 }, { "epoch": 2.2634948374556414, "grad_norm": 1.5671724081039429, "learning_rate": 5.107429574280329e-05, "loss": 0.49352073669433594, "step": 380790 }, { "epoch": 2.26355427953231, "grad_norm": 1.2973854541778564, "learning_rate": 5.1069590812221034e-05, "loss": 0.4772289276123047, "step": 380800 }, { "epoch": 2.2636137216089782, "grad_norm": 1.4743729829788208, "learning_rate": 5.10648861635426e-05, "loss": 0.5235989570617676, "step": 380810 }, { "epoch": 2.2636731636856466, "grad_norm": 1.6919840574264526, "learning_rate": 5.106018179679051e-05, "loss": 0.49318714141845704, "step": 380820 }, { "epoch": 2.263732605762315, "grad_norm": 1.5955513715744019, "learning_rate": 5.105547771198722e-05, "loss": 0.4658318519592285, "step": 380830 }, { "epoch": 2.2637920478389835, "grad_norm": 1.1337947845458984, "learning_rate": 5.105077390915527e-05, "loss": 0.4940475940704346, "step": 380840 }, { "epoch": 2.263851489915652, "grad_norm": 1.629672646522522, "learning_rate": 5.104607038831715e-05, "loss": 0.5099664688110351, "step": 380850 }, { "epoch": 2.26391093199232, "grad_norm": 1.4715412855148315, "learning_rate": 5.1041367149495344e-05, "loss": 0.4728433132171631, "step": 380860 }, { "epoch": 2.2639703740689887, "grad_norm": 1.716274619102478, "learning_rate": 5.103666419271239e-05, "loss": 0.5706218719482422, "step": 380870 }, { "epoch": 2.2640298161456567, "grad_norm": 1.418387532234192, "learning_rate": 5.103196151799077e-05, "loss": 0.46852450370788573, "step": 380880 }, { "epoch": 2.264089258222325, "grad_norm": 1.2442939281463623, "learning_rate": 5.1027259125352975e-05, "loss": 0.4798140525817871, "step": 380890 }, { "epoch": 2.2641487002989935, "grad_norm": 1.3269606828689575, "learning_rate": 5.10225570148215e-05, "loss": 0.46791834831237794, "step": 380900 }, { "epoch": 2.264208142375662, "grad_norm": 1.3458768129348755, "learning_rate": 5.101785518641884e-05, "loss": 0.5267242908477783, "step": 380910 }, { "epoch": 2.2642675844523303, "grad_norm": 1.38895583152771, "learning_rate": 5.101315364016746e-05, "loss": 0.43779869079589845, "step": 380920 }, { "epoch": 2.2643270265289988, "grad_norm": 1.3769482374191284, "learning_rate": 5.1008452376089886e-05, "loss": 0.4920483589172363, "step": 380930 }, { "epoch": 2.264386468605667, "grad_norm": 1.4529584646224976, "learning_rate": 5.100375139420861e-05, "loss": 0.5407093048095704, "step": 380940 }, { "epoch": 2.2644459106823356, "grad_norm": 1.2826896905899048, "learning_rate": 5.099905069454613e-05, "loss": 0.5166625499725341, "step": 380950 }, { "epoch": 2.264505352759004, "grad_norm": 1.7493826150894165, "learning_rate": 5.099435027712486e-05, "loss": 0.52024827003479, "step": 380960 }, { "epoch": 2.2645647948356724, "grad_norm": 1.4478487968444824, "learning_rate": 5.098965014196737e-05, "loss": 0.4884350776672363, "step": 380970 }, { "epoch": 2.264624236912341, "grad_norm": 1.362664818763733, "learning_rate": 5.098495028909609e-05, "loss": 0.5593262672424316, "step": 380980 }, { "epoch": 2.2646836789890092, "grad_norm": 1.4227346181869507, "learning_rate": 5.0980250718533496e-05, "loss": 0.5290361881256104, "step": 380990 }, { "epoch": 2.2647431210656777, "grad_norm": 1.0259393453598022, "learning_rate": 5.097555143030213e-05, "loss": 0.47152981758117674, "step": 381000 }, { "epoch": 2.264802563142346, "grad_norm": 1.4090648889541626, "learning_rate": 5.097085242442448e-05, "loss": 0.546113920211792, "step": 381010 }, { "epoch": 2.2648620052190145, "grad_norm": 1.0966472625732422, "learning_rate": 5.0966153700922906e-05, "loss": 0.4464890480041504, "step": 381020 }, { "epoch": 2.264921447295683, "grad_norm": 1.823678731918335, "learning_rate": 5.096145525981998e-05, "loss": 0.4883277893066406, "step": 381030 }, { "epoch": 2.2649808893723513, "grad_norm": 1.3201799392700195, "learning_rate": 5.095675710113819e-05, "loss": 0.5084764957427979, "step": 381040 }, { "epoch": 2.2650403314490193, "grad_norm": 0.9550818800926208, "learning_rate": 5.0952059224899917e-05, "loss": 0.5064135551452636, "step": 381050 }, { "epoch": 2.265099773525688, "grad_norm": 1.4971399307250977, "learning_rate": 5.094736163112773e-05, "loss": 0.4967830181121826, "step": 381060 }, { "epoch": 2.265159215602356, "grad_norm": 1.4357436895370483, "learning_rate": 5.094266431984411e-05, "loss": 0.49877476692199707, "step": 381070 }, { "epoch": 2.2652186576790245, "grad_norm": 1.437342882156372, "learning_rate": 5.093796729107144e-05, "loss": 0.5254695892333985, "step": 381080 }, { "epoch": 2.265278099755693, "grad_norm": 1.3385851383209229, "learning_rate": 5.093327054483221e-05, "loss": 0.5016636848449707, "step": 381090 }, { "epoch": 2.2653375418323614, "grad_norm": 1.486604928970337, "learning_rate": 5.0928574081148936e-05, "loss": 0.5053213119506836, "step": 381100 }, { "epoch": 2.2653969839090298, "grad_norm": 1.4222288131713867, "learning_rate": 5.092387790004407e-05, "loss": 0.46800837516784666, "step": 381110 }, { "epoch": 2.265456425985698, "grad_norm": 1.0010933876037598, "learning_rate": 5.091918200154003e-05, "loss": 0.4753415107727051, "step": 381120 }, { "epoch": 2.2655158680623666, "grad_norm": 1.5029025077819824, "learning_rate": 5.0914486385659376e-05, "loss": 0.537821102142334, "step": 381130 }, { "epoch": 2.265575310139035, "grad_norm": 1.5861170291900635, "learning_rate": 5.090979105242448e-05, "loss": 0.5522052764892578, "step": 381140 }, { "epoch": 2.2656347522157034, "grad_norm": 1.3943599462509155, "learning_rate": 5.09050960018578e-05, "loss": 0.49149556159973146, "step": 381150 }, { "epoch": 2.265694194292372, "grad_norm": 1.411756992340088, "learning_rate": 5.0900401233981855e-05, "loss": 0.4890717029571533, "step": 381160 }, { "epoch": 2.2657536363690403, "grad_norm": 1.2055848836898804, "learning_rate": 5.089570674881908e-05, "loss": 0.4671438217163086, "step": 381170 }, { "epoch": 2.2658130784457087, "grad_norm": 1.4025053977966309, "learning_rate": 5.0891012546391936e-05, "loss": 0.505317497253418, "step": 381180 }, { "epoch": 2.265872520522377, "grad_norm": 1.5512481927871704, "learning_rate": 5.088631862672286e-05, "loss": 0.4997755527496338, "step": 381190 }, { "epoch": 2.2659319625990455, "grad_norm": 1.1535848379135132, "learning_rate": 5.088162498983432e-05, "loss": 0.4840510845184326, "step": 381200 }, { "epoch": 2.265991404675714, "grad_norm": 1.575139045715332, "learning_rate": 5.087693163574877e-05, "loss": 0.4804693222045898, "step": 381210 }, { "epoch": 2.2660508467523823, "grad_norm": 1.1530687808990479, "learning_rate": 5.087223856448863e-05, "loss": 0.4734773635864258, "step": 381220 }, { "epoch": 2.2661102888290507, "grad_norm": 1.554700493812561, "learning_rate": 5.08675457760764e-05, "loss": 0.5066825866699218, "step": 381230 }, { "epoch": 2.2661697309057187, "grad_norm": 1.1790475845336914, "learning_rate": 5.0862853270534506e-05, "loss": 0.4372109889984131, "step": 381240 }, { "epoch": 2.266229172982387, "grad_norm": 1.5379482507705688, "learning_rate": 5.08581610478854e-05, "loss": 0.5166201114654541, "step": 381250 }, { "epoch": 2.2662886150590555, "grad_norm": 1.3941205739974976, "learning_rate": 5.085346910815152e-05, "loss": 0.4874577522277832, "step": 381260 }, { "epoch": 2.266348057135724, "grad_norm": 1.3302205801010132, "learning_rate": 5.084877745135532e-05, "loss": 0.5078357696533203, "step": 381270 }, { "epoch": 2.2664074992123924, "grad_norm": 1.305937647819519, "learning_rate": 5.084408607751921e-05, "loss": 0.440114688873291, "step": 381280 }, { "epoch": 2.266466941289061, "grad_norm": 1.8357306718826294, "learning_rate": 5.083939498666568e-05, "loss": 0.523319149017334, "step": 381290 }, { "epoch": 2.266526383365729, "grad_norm": 1.781785488128662, "learning_rate": 5.0834704178817146e-05, "loss": 0.48542938232421873, "step": 381300 }, { "epoch": 2.2665858254423976, "grad_norm": 1.0819698572158813, "learning_rate": 5.0830013653996065e-05, "loss": 0.5184603214263916, "step": 381310 }, { "epoch": 2.266645267519066, "grad_norm": 1.2054295539855957, "learning_rate": 5.082532341222486e-05, "loss": 0.47890243530273435, "step": 381320 }, { "epoch": 2.2667047095957344, "grad_norm": 1.487341046333313, "learning_rate": 5.0820633453525966e-05, "loss": 0.49340238571166994, "step": 381330 }, { "epoch": 2.266764151672403, "grad_norm": 1.2668169736862183, "learning_rate": 5.081594377792183e-05, "loss": 0.4557366371154785, "step": 381340 }, { "epoch": 2.2668235937490713, "grad_norm": 1.7070268392562866, "learning_rate": 5.0811254385434835e-05, "loss": 0.4916705131530762, "step": 381350 }, { "epoch": 2.2668830358257397, "grad_norm": 1.2992511987686157, "learning_rate": 5.080656527608748e-05, "loss": 0.509853458404541, "step": 381360 }, { "epoch": 2.266942477902408, "grad_norm": 1.469649314880371, "learning_rate": 5.080187644990219e-05, "loss": 0.48426270484924316, "step": 381370 }, { "epoch": 2.2670019199790765, "grad_norm": 1.3831043243408203, "learning_rate": 5.079718790690138e-05, "loss": 0.4880875587463379, "step": 381380 }, { "epoch": 2.267061362055745, "grad_norm": 1.5480188131332397, "learning_rate": 5.079249964710745e-05, "loss": 0.44515371322631836, "step": 381390 }, { "epoch": 2.2671208041324133, "grad_norm": 1.4610321521759033, "learning_rate": 5.078781167054287e-05, "loss": 0.4956252098083496, "step": 381400 }, { "epoch": 2.2671802462090813, "grad_norm": 1.420473337173462, "learning_rate": 5.078312397723002e-05, "loss": 0.5348336696624756, "step": 381410 }, { "epoch": 2.26723968828575, "grad_norm": 1.6537319421768188, "learning_rate": 5.077843656719138e-05, "loss": 0.5052567481994629, "step": 381420 }, { "epoch": 2.267299130362418, "grad_norm": 1.4414997100830078, "learning_rate": 5.077374944044934e-05, "loss": 0.5013554096221924, "step": 381430 }, { "epoch": 2.2673585724390866, "grad_norm": 1.1472275257110596, "learning_rate": 5.076906259702634e-05, "loss": 0.48064556121826174, "step": 381440 }, { "epoch": 2.267418014515755, "grad_norm": 1.373178482055664, "learning_rate": 5.076437603694477e-05, "loss": 0.5086359977722168, "step": 381450 }, { "epoch": 2.2674774565924234, "grad_norm": 0.860413134098053, "learning_rate": 5.075968976022707e-05, "loss": 0.5098129272460937, "step": 381460 }, { "epoch": 2.267536898669092, "grad_norm": 1.2682273387908936, "learning_rate": 5.075500376689566e-05, "loss": 0.4859154224395752, "step": 381470 }, { "epoch": 2.26759634074576, "grad_norm": 1.162623405456543, "learning_rate": 5.0750318056972924e-05, "loss": 0.4919825553894043, "step": 381480 }, { "epoch": 2.2676557828224286, "grad_norm": 1.3250764608383179, "learning_rate": 5.074563263048132e-05, "loss": 0.44870481491088865, "step": 381490 }, { "epoch": 2.267715224899097, "grad_norm": 1.6846754550933838, "learning_rate": 5.0740947487443266e-05, "loss": 0.5447952270507812, "step": 381500 }, { "epoch": 2.2677746669757655, "grad_norm": 1.1083309650421143, "learning_rate": 5.0736262627881136e-05, "loss": 0.4598828315734863, "step": 381510 }, { "epoch": 2.267834109052434, "grad_norm": 1.6231130361557007, "learning_rate": 5.073157805181736e-05, "loss": 0.5479442596435546, "step": 381520 }, { "epoch": 2.2678935511291023, "grad_norm": 1.457672119140625, "learning_rate": 5.0726893759274355e-05, "loss": 0.46007614135742186, "step": 381530 }, { "epoch": 2.2679529932057707, "grad_norm": 1.45039701461792, "learning_rate": 5.072220975027451e-05, "loss": 0.4893660545349121, "step": 381540 }, { "epoch": 2.268012435282439, "grad_norm": 1.801125407218933, "learning_rate": 5.071752602484021e-05, "loss": 0.5157917976379395, "step": 381550 }, { "epoch": 2.2680718773591075, "grad_norm": 1.360987901687622, "learning_rate": 5.0712842582993955e-05, "loss": 0.5066013336181641, "step": 381560 }, { "epoch": 2.268131319435776, "grad_norm": 1.1983768939971924, "learning_rate": 5.070815942475806e-05, "loss": 0.4569104194641113, "step": 381570 }, { "epoch": 2.2681907615124444, "grad_norm": 1.1526230573654175, "learning_rate": 5.070347655015493e-05, "loss": 0.4615316867828369, "step": 381580 }, { "epoch": 2.268250203589113, "grad_norm": 1.5012911558151245, "learning_rate": 5.0698793959207e-05, "loss": 0.48053154945373533, "step": 381590 }, { "epoch": 2.2683096456657807, "grad_norm": 1.2488012313842773, "learning_rate": 5.069411165193667e-05, "loss": 0.47558016777038575, "step": 381600 }, { "epoch": 2.2683690877424496, "grad_norm": 1.7467694282531738, "learning_rate": 5.068942962836631e-05, "loss": 0.5210328102111816, "step": 381610 }, { "epoch": 2.2684285298191176, "grad_norm": 1.3890446424484253, "learning_rate": 5.068474788851838e-05, "loss": 0.47348842620849607, "step": 381620 }, { "epoch": 2.268487971895786, "grad_norm": 1.2467366456985474, "learning_rate": 5.068006643241521e-05, "loss": 0.5219691276550293, "step": 381630 }, { "epoch": 2.2685474139724544, "grad_norm": 1.3617682456970215, "learning_rate": 5.067538526007918e-05, "loss": 0.4921399116516113, "step": 381640 }, { "epoch": 2.268606856049123, "grad_norm": 1.8833945989608765, "learning_rate": 5.0670704371532754e-05, "loss": 0.4902845859527588, "step": 381650 }, { "epoch": 2.2686662981257912, "grad_norm": 1.390203833580017, "learning_rate": 5.0666023766798275e-05, "loss": 0.494091796875, "step": 381660 }, { "epoch": 2.2687257402024597, "grad_norm": 1.7049024105072021, "learning_rate": 5.066134344589817e-05, "loss": 0.49911746978759763, "step": 381670 }, { "epoch": 2.268785182279128, "grad_norm": 1.5426744222640991, "learning_rate": 5.06566634088548e-05, "loss": 0.5239312648773193, "step": 381680 }, { "epoch": 2.2688446243557965, "grad_norm": 1.150413155555725, "learning_rate": 5.065198365569055e-05, "loss": 0.4701862335205078, "step": 381690 }, { "epoch": 2.268904066432465, "grad_norm": 1.743659496307373, "learning_rate": 5.064730418642782e-05, "loss": 0.5108315944671631, "step": 381700 }, { "epoch": 2.2689635085091333, "grad_norm": 1.5345064401626587, "learning_rate": 5.064262500108896e-05, "loss": 0.49326581954956056, "step": 381710 }, { "epoch": 2.2690229505858017, "grad_norm": 1.4530826807022095, "learning_rate": 5.063794609969642e-05, "loss": 0.5089110374450684, "step": 381720 }, { "epoch": 2.26908239266247, "grad_norm": 1.0639735460281372, "learning_rate": 5.063326748227254e-05, "loss": 0.4819894790649414, "step": 381730 }, { "epoch": 2.2691418347391386, "grad_norm": 1.3103803396224976, "learning_rate": 5.06285891488397e-05, "loss": 0.48348569869995117, "step": 381740 }, { "epoch": 2.269201276815807, "grad_norm": 1.2526710033416748, "learning_rate": 5.062391109942031e-05, "loss": 0.447882080078125, "step": 381750 }, { "epoch": 2.2692607188924754, "grad_norm": 1.379228949546814, "learning_rate": 5.06192333340367e-05, "loss": 0.5012650489807129, "step": 381760 }, { "epoch": 2.269320160969144, "grad_norm": 1.4177740812301636, "learning_rate": 5.0614555852711244e-05, "loss": 0.471506929397583, "step": 381770 }, { "epoch": 2.269379603045812, "grad_norm": 1.3830846548080444, "learning_rate": 5.060987865546638e-05, "loss": 0.49506254196166993, "step": 381780 }, { "epoch": 2.26943904512248, "grad_norm": 1.3494929075241089, "learning_rate": 5.0605201742324446e-05, "loss": 0.46890888214111326, "step": 381790 }, { "epoch": 2.2694984871991486, "grad_norm": 1.3710837364196777, "learning_rate": 5.060052511330783e-05, "loss": 0.5329379081726074, "step": 381800 }, { "epoch": 2.269557929275817, "grad_norm": 1.2644704580307007, "learning_rate": 5.059584876843888e-05, "loss": 0.47192840576171874, "step": 381810 }, { "epoch": 2.2696173713524854, "grad_norm": 1.2697982788085938, "learning_rate": 5.0591172707739966e-05, "loss": 0.48262624740600585, "step": 381820 }, { "epoch": 2.269676813429154, "grad_norm": 1.4246326684951782, "learning_rate": 5.058649693123349e-05, "loss": 0.5051206111907959, "step": 381830 }, { "epoch": 2.2697362555058223, "grad_norm": 1.3296878337860107, "learning_rate": 5.0581821438941745e-05, "loss": 0.4774660587310791, "step": 381840 }, { "epoch": 2.2697956975824907, "grad_norm": 1.5325545072555542, "learning_rate": 5.057714623088718e-05, "loss": 0.5095778465270996, "step": 381850 }, { "epoch": 2.269855139659159, "grad_norm": 1.27812659740448, "learning_rate": 5.057247130709214e-05, "loss": 0.50455322265625, "step": 381860 }, { "epoch": 2.2699145817358275, "grad_norm": 1.3397654294967651, "learning_rate": 5.056779666757897e-05, "loss": 0.4821147441864014, "step": 381870 }, { "epoch": 2.269974023812496, "grad_norm": 1.3543814420700073, "learning_rate": 5.0563122312370034e-05, "loss": 0.45126953125, "step": 381880 }, { "epoch": 2.2700334658891643, "grad_norm": 1.0240693092346191, "learning_rate": 5.05584482414877e-05, "loss": 0.4900557518005371, "step": 381890 }, { "epoch": 2.2700929079658327, "grad_norm": 1.225738525390625, "learning_rate": 5.0553774454954304e-05, "loss": 0.44240469932556153, "step": 381900 }, { "epoch": 2.270152350042501, "grad_norm": 1.3778190612792969, "learning_rate": 5.054910095279224e-05, "loss": 0.4917330741882324, "step": 381910 }, { "epoch": 2.2702117921191696, "grad_norm": 1.37183678150177, "learning_rate": 5.0544427735023855e-05, "loss": 0.47397537231445314, "step": 381920 }, { "epoch": 2.270271234195838, "grad_norm": 1.4105678796768188, "learning_rate": 5.053975480167148e-05, "loss": 0.545848274230957, "step": 381930 }, { "epoch": 2.2703306762725064, "grad_norm": 1.2787748575210571, "learning_rate": 5.053508215275751e-05, "loss": 0.46582937240600586, "step": 381940 }, { "epoch": 2.270390118349175, "grad_norm": 1.127446174621582, "learning_rate": 5.0530409788304275e-05, "loss": 0.4691301345825195, "step": 381950 }, { "epoch": 2.2704495604258432, "grad_norm": 1.854317545890808, "learning_rate": 5.052573770833411e-05, "loss": 0.47934465408325194, "step": 381960 }, { "epoch": 2.2705090025025116, "grad_norm": 1.304229974746704, "learning_rate": 5.052106591286936e-05, "loss": 0.49421119689941406, "step": 381970 }, { "epoch": 2.2705684445791796, "grad_norm": 1.1616207361221313, "learning_rate": 5.051639440193241e-05, "loss": 0.4543889045715332, "step": 381980 }, { "epoch": 2.270627886655848, "grad_norm": 1.3262540102005005, "learning_rate": 5.05117231755456e-05, "loss": 0.4968526840209961, "step": 381990 }, { "epoch": 2.2706873287325164, "grad_norm": 1.1944923400878906, "learning_rate": 5.0507052233731246e-05, "loss": 0.4386446952819824, "step": 382000 }, { "epoch": 2.270746770809185, "grad_norm": 1.276300072669983, "learning_rate": 5.050238157651174e-05, "loss": 0.5101038455963135, "step": 382010 }, { "epoch": 2.2708062128858533, "grad_norm": 1.3782461881637573, "learning_rate": 5.049771120390938e-05, "loss": 0.48291959762573244, "step": 382020 }, { "epoch": 2.2708656549625217, "grad_norm": 1.1250219345092773, "learning_rate": 5.049304111594653e-05, "loss": 0.4826303005218506, "step": 382030 }, { "epoch": 2.27092509703919, "grad_norm": 1.1890677213668823, "learning_rate": 5.048837131264549e-05, "loss": 0.5082282543182373, "step": 382040 }, { "epoch": 2.2709845391158585, "grad_norm": 1.113612413406372, "learning_rate": 5.0483701794028656e-05, "loss": 0.46306495666503905, "step": 382050 }, { "epoch": 2.271043981192527, "grad_norm": 1.1238038539886475, "learning_rate": 5.047903256011839e-05, "loss": 0.49073195457458496, "step": 382060 }, { "epoch": 2.2711034232691953, "grad_norm": 1.3875795602798462, "learning_rate": 5.047436361093692e-05, "loss": 0.44880127906799316, "step": 382070 }, { "epoch": 2.2711628653458638, "grad_norm": 1.5680341720581055, "learning_rate": 5.046969494650665e-05, "loss": 0.4566371917724609, "step": 382080 }, { "epoch": 2.271222307422532, "grad_norm": 1.3470460176467896, "learning_rate": 5.046502656684993e-05, "loss": 0.4852339744567871, "step": 382090 }, { "epoch": 2.2712817494992006, "grad_norm": 1.1088249683380127, "learning_rate": 5.046035847198902e-05, "loss": 0.42330217361450195, "step": 382100 }, { "epoch": 2.271341191575869, "grad_norm": 1.2484525442123413, "learning_rate": 5.045569066194633e-05, "loss": 0.4733593940734863, "step": 382110 }, { "epoch": 2.2714006336525374, "grad_norm": 1.091896653175354, "learning_rate": 5.045102313674419e-05, "loss": 0.46460638046264646, "step": 382120 }, { "epoch": 2.271460075729206, "grad_norm": 1.419091820716858, "learning_rate": 5.0446355896404826e-05, "loss": 0.4577943801879883, "step": 382130 }, { "epoch": 2.2715195178058742, "grad_norm": 1.0936774015426636, "learning_rate": 5.044168894095067e-05, "loss": 0.48242483139038084, "step": 382140 }, { "epoch": 2.271578959882542, "grad_norm": 1.3747363090515137, "learning_rate": 5.043702227040401e-05, "loss": 0.481612491607666, "step": 382150 }, { "epoch": 2.271638401959211, "grad_norm": 1.448743224143982, "learning_rate": 5.043235588478718e-05, "loss": 0.532962703704834, "step": 382160 }, { "epoch": 2.271697844035879, "grad_norm": 1.1105005741119385, "learning_rate": 5.042768978412244e-05, "loss": 0.47711610794067383, "step": 382170 }, { "epoch": 2.2717572861125475, "grad_norm": 1.2611567974090576, "learning_rate": 5.042302396843225e-05, "loss": 0.458601188659668, "step": 382180 }, { "epoch": 2.271816728189216, "grad_norm": 1.3105725049972534, "learning_rate": 5.04183584377388e-05, "loss": 0.4561809539794922, "step": 382190 }, { "epoch": 2.2718761702658843, "grad_norm": 1.4777623414993286, "learning_rate": 5.041369319206442e-05, "loss": 0.5152857780456543, "step": 382200 }, { "epoch": 2.2719356123425527, "grad_norm": 1.1217182874679565, "learning_rate": 5.04090282314315e-05, "loss": 0.4575168609619141, "step": 382210 }, { "epoch": 2.271995054419221, "grad_norm": 1.4388865232467651, "learning_rate": 5.040436355586229e-05, "loss": 0.45154056549072263, "step": 382220 }, { "epoch": 2.2720544964958895, "grad_norm": 1.339232087135315, "learning_rate": 5.0399699165379146e-05, "loss": 0.5102561473846435, "step": 382230 }, { "epoch": 2.272113938572558, "grad_norm": 1.0430642366409302, "learning_rate": 5.0395035060004366e-05, "loss": 0.5084583759307861, "step": 382240 }, { "epoch": 2.2721733806492264, "grad_norm": 1.2647054195404053, "learning_rate": 5.039037123976025e-05, "loss": 0.49608888626098635, "step": 382250 }, { "epoch": 2.2722328227258948, "grad_norm": 1.2638850212097168, "learning_rate": 5.0385707704669084e-05, "loss": 0.5008967399597168, "step": 382260 }, { "epoch": 2.272292264802563, "grad_norm": 1.3749547004699707, "learning_rate": 5.038104445475326e-05, "loss": 0.5404096603393554, "step": 382270 }, { "epoch": 2.2723517068792316, "grad_norm": 1.8090227842330933, "learning_rate": 5.037638149003503e-05, "loss": 0.48575725555419924, "step": 382280 }, { "epoch": 2.2724111489559, "grad_norm": 1.6031230688095093, "learning_rate": 5.0371718810536696e-05, "loss": 0.44132037162780763, "step": 382290 }, { "epoch": 2.2724705910325684, "grad_norm": 1.5907624959945679, "learning_rate": 5.036705641628057e-05, "loss": 0.49472794532775877, "step": 382300 }, { "epoch": 2.272530033109237, "grad_norm": 1.4043899774551392, "learning_rate": 5.0362394307288965e-05, "loss": 0.506850290298462, "step": 382310 }, { "epoch": 2.2725894751859053, "grad_norm": 1.5890358686447144, "learning_rate": 5.0357732483584176e-05, "loss": 0.5520639419555664, "step": 382320 }, { "epoch": 2.2726489172625737, "grad_norm": 1.5785225629806519, "learning_rate": 5.035307094518846e-05, "loss": 0.49425663948059084, "step": 382330 }, { "epoch": 2.2727083593392416, "grad_norm": 1.579917550086975, "learning_rate": 5.03484096921242e-05, "loss": 0.4601408004760742, "step": 382340 }, { "epoch": 2.2727678014159105, "grad_norm": 1.415687084197998, "learning_rate": 5.034374872441366e-05, "loss": 0.49227027893066405, "step": 382350 }, { "epoch": 2.2728272434925785, "grad_norm": 1.1335513591766357, "learning_rate": 5.033908804207913e-05, "loss": 0.46530847549438475, "step": 382360 }, { "epoch": 2.272886685569247, "grad_norm": 1.4600807428359985, "learning_rate": 5.033442764514291e-05, "loss": 0.46323256492614745, "step": 382370 }, { "epoch": 2.2729461276459153, "grad_norm": 1.7543052434921265, "learning_rate": 5.032976753362727e-05, "loss": 0.5230566978454589, "step": 382380 }, { "epoch": 2.2730055697225837, "grad_norm": 1.6605961322784424, "learning_rate": 5.0325107707554494e-05, "loss": 0.48232412338256836, "step": 382390 }, { "epoch": 2.273065011799252, "grad_norm": 1.2573925256729126, "learning_rate": 5.0320448166946946e-05, "loss": 0.44287734031677245, "step": 382400 }, { "epoch": 2.2731244538759205, "grad_norm": 1.2415798902511597, "learning_rate": 5.0315788911826865e-05, "loss": 0.4862081050872803, "step": 382410 }, { "epoch": 2.273183895952589, "grad_norm": 1.658144474029541, "learning_rate": 5.031112994221654e-05, "loss": 0.5085824966430664, "step": 382420 }, { "epoch": 2.2732433380292574, "grad_norm": 1.4096648693084717, "learning_rate": 5.030647125813827e-05, "loss": 0.5049957752227783, "step": 382430 }, { "epoch": 2.273302780105926, "grad_norm": 0.8179811835289001, "learning_rate": 5.030181285961433e-05, "loss": 0.4899315357208252, "step": 382440 }, { "epoch": 2.273362222182594, "grad_norm": 1.137985110282898, "learning_rate": 5.029715474666701e-05, "loss": 0.4798304080963135, "step": 382450 }, { "epoch": 2.2734216642592626, "grad_norm": 1.3152648210525513, "learning_rate": 5.029249691931855e-05, "loss": 0.5005978584289551, "step": 382460 }, { "epoch": 2.273481106335931, "grad_norm": 1.404004693031311, "learning_rate": 5.028783937759132e-05, "loss": 0.5233926773071289, "step": 382470 }, { "epoch": 2.2735405484125994, "grad_norm": 1.1386843919754028, "learning_rate": 5.028318212150753e-05, "loss": 0.4775324821472168, "step": 382480 }, { "epoch": 2.273599990489268, "grad_norm": 2.183143138885498, "learning_rate": 5.027852515108949e-05, "loss": 0.514653205871582, "step": 382490 }, { "epoch": 2.2736594325659363, "grad_norm": 1.2940051555633545, "learning_rate": 5.0273868466359474e-05, "loss": 0.5130647659301758, "step": 382500 }, { "epoch": 2.2737188746426047, "grad_norm": 1.6827353239059448, "learning_rate": 5.0269212067339745e-05, "loss": 0.45644502639770507, "step": 382510 }, { "epoch": 2.273778316719273, "grad_norm": 1.235789179801941, "learning_rate": 5.0264555954052596e-05, "loss": 0.45781536102294923, "step": 382520 }, { "epoch": 2.273837758795941, "grad_norm": 1.2428714036941528, "learning_rate": 5.025990012652026e-05, "loss": 0.5119954109191894, "step": 382530 }, { "epoch": 2.2738972008726095, "grad_norm": 1.1404297351837158, "learning_rate": 5.025524458476506e-05, "loss": 0.4581584930419922, "step": 382540 }, { "epoch": 2.273956642949278, "grad_norm": 1.5716873407363892, "learning_rate": 5.025058932880927e-05, "loss": 0.4752164363861084, "step": 382550 }, { "epoch": 2.2740160850259463, "grad_norm": 1.4845035076141357, "learning_rate": 5.0245934358675084e-05, "loss": 0.5515424728393554, "step": 382560 }, { "epoch": 2.2740755271026147, "grad_norm": 1.084108829498291, "learning_rate": 5.0241279674384856e-05, "loss": 0.499358081817627, "step": 382570 }, { "epoch": 2.274134969179283, "grad_norm": 1.471876621246338, "learning_rate": 5.02366252759608e-05, "loss": 0.5288526535034179, "step": 382580 }, { "epoch": 2.2741944112559516, "grad_norm": 1.5097769498825073, "learning_rate": 5.023197116342517e-05, "loss": 0.47843289375305176, "step": 382590 }, { "epoch": 2.27425385333262, "grad_norm": 1.5051987171173096, "learning_rate": 5.02273173368003e-05, "loss": 0.48499631881713867, "step": 382600 }, { "epoch": 2.2743132954092884, "grad_norm": 1.3621172904968262, "learning_rate": 5.022266379610843e-05, "loss": 0.5023755550384521, "step": 382610 }, { "epoch": 2.274372737485957, "grad_norm": 1.5212130546569824, "learning_rate": 5.021801054137175e-05, "loss": 0.5610487937927247, "step": 382620 }, { "epoch": 2.2744321795626252, "grad_norm": 1.8717739582061768, "learning_rate": 5.0213357572612594e-05, "loss": 0.46534204483032227, "step": 382630 }, { "epoch": 2.2744916216392936, "grad_norm": 1.4399807453155518, "learning_rate": 5.02087048898532e-05, "loss": 0.5600498199462891, "step": 382640 }, { "epoch": 2.274551063715962, "grad_norm": 1.2032623291015625, "learning_rate": 5.0204052493115814e-05, "loss": 0.5031143665313721, "step": 382650 }, { "epoch": 2.2746105057926305, "grad_norm": 1.079576015472412, "learning_rate": 5.0199400382422676e-05, "loss": 0.48917474746704104, "step": 382660 }, { "epoch": 2.274669947869299, "grad_norm": 1.4190491437911987, "learning_rate": 5.019474855779613e-05, "loss": 0.48032665252685547, "step": 382670 }, { "epoch": 2.2747293899459673, "grad_norm": 1.5622860193252563, "learning_rate": 5.019009701925832e-05, "loss": 0.4779177188873291, "step": 382680 }, { "epoch": 2.2747888320226357, "grad_norm": 1.5535383224487305, "learning_rate": 5.0185445766831516e-05, "loss": 0.5482999801635742, "step": 382690 }, { "epoch": 2.274848274099304, "grad_norm": 1.2398980855941772, "learning_rate": 5.0180794800538024e-05, "loss": 0.43948822021484374, "step": 382700 }, { "epoch": 2.2749077161759725, "grad_norm": 1.2924518585205078, "learning_rate": 5.017614412040006e-05, "loss": 0.5185585021972656, "step": 382710 }, { "epoch": 2.2749671582526405, "grad_norm": 1.2266039848327637, "learning_rate": 5.0171493726439836e-05, "loss": 0.5275956630706787, "step": 382720 }, { "epoch": 2.275026600329309, "grad_norm": 1.5289822816848755, "learning_rate": 5.0166843618679695e-05, "loss": 0.4531810760498047, "step": 382730 }, { "epoch": 2.2750860424059773, "grad_norm": 1.1568878889083862, "learning_rate": 5.01621937971418e-05, "loss": 0.540522289276123, "step": 382740 }, { "epoch": 2.2751454844826458, "grad_norm": 1.647331953048706, "learning_rate": 5.0157544261848366e-05, "loss": 0.5067176818847656, "step": 382750 }, { "epoch": 2.275204926559314, "grad_norm": 1.2995836734771729, "learning_rate": 5.015289501282173e-05, "loss": 0.503085994720459, "step": 382760 }, { "epoch": 2.2752643686359826, "grad_norm": 1.2106419801712036, "learning_rate": 5.014824605008408e-05, "loss": 0.4827458381652832, "step": 382770 }, { "epoch": 2.275323810712651, "grad_norm": 1.3408883810043335, "learning_rate": 5.014359737365766e-05, "loss": 0.5434916496276856, "step": 382780 }, { "epoch": 2.2753832527893194, "grad_norm": 1.3685508966445923, "learning_rate": 5.013894898356472e-05, "loss": 0.4713452339172363, "step": 382790 }, { "epoch": 2.275442694865988, "grad_norm": 1.126514196395874, "learning_rate": 5.0134300879827466e-05, "loss": 0.4865365505218506, "step": 382800 }, { "epoch": 2.2755021369426562, "grad_norm": 1.0441921949386597, "learning_rate": 5.012965306246817e-05, "loss": 0.4508212089538574, "step": 382810 }, { "epoch": 2.2755615790193247, "grad_norm": 1.500923991203308, "learning_rate": 5.0125005531509006e-05, "loss": 0.501369571685791, "step": 382820 }, { "epoch": 2.275621021095993, "grad_norm": 1.1490967273712158, "learning_rate": 5.012035828697228e-05, "loss": 0.4549994468688965, "step": 382830 }, { "epoch": 2.2756804631726615, "grad_norm": 1.665168046951294, "learning_rate": 5.011571132888019e-05, "loss": 0.48552637100219725, "step": 382840 }, { "epoch": 2.27573990524933, "grad_norm": 1.5408076047897339, "learning_rate": 5.011106465725497e-05, "loss": 0.4928079128265381, "step": 382850 }, { "epoch": 2.2757993473259983, "grad_norm": 1.1121459007263184, "learning_rate": 5.0106418272118836e-05, "loss": 0.4703974723815918, "step": 382860 }, { "epoch": 2.2758587894026667, "grad_norm": 1.8578689098358154, "learning_rate": 5.0101772173494044e-05, "loss": 0.47617197036743164, "step": 382870 }, { "epoch": 2.275918231479335, "grad_norm": 1.1446794271469116, "learning_rate": 5.009712636140278e-05, "loss": 0.4717005729675293, "step": 382880 }, { "epoch": 2.275977673556003, "grad_norm": 2.394787311553955, "learning_rate": 5.009248083586727e-05, "loss": 0.49957866668701173, "step": 382890 }, { "epoch": 2.276037115632672, "grad_norm": 1.2106516361236572, "learning_rate": 5.008783559690977e-05, "loss": 0.5030876159667969, "step": 382900 }, { "epoch": 2.27609655770934, "grad_norm": 1.2809100151062012, "learning_rate": 5.0083190644552494e-05, "loss": 0.4781781196594238, "step": 382910 }, { "epoch": 2.2761559997860084, "grad_norm": 1.6689480543136597, "learning_rate": 5.007854597881765e-05, "loss": 0.48708515167236327, "step": 382920 }, { "epoch": 2.2762154418626768, "grad_norm": 1.4839372634887695, "learning_rate": 5.0073901599727466e-05, "loss": 0.512093448638916, "step": 382930 }, { "epoch": 2.276274883939345, "grad_norm": 3.000436305999756, "learning_rate": 5.0069257507304154e-05, "loss": 0.5565272808074951, "step": 382940 }, { "epoch": 2.2763343260160136, "grad_norm": 1.3710774183273315, "learning_rate": 5.0064613701569896e-05, "loss": 0.5252270698547363, "step": 382950 }, { "epoch": 2.276393768092682, "grad_norm": 1.295804738998413, "learning_rate": 5.0059970182546953e-05, "loss": 0.5139808654785156, "step": 382960 }, { "epoch": 2.2764532101693504, "grad_norm": 1.6616743803024292, "learning_rate": 5.005532695025754e-05, "loss": 0.550289535522461, "step": 382970 }, { "epoch": 2.276512652246019, "grad_norm": 0.8251461386680603, "learning_rate": 5.005068400472386e-05, "loss": 0.46524553298950194, "step": 382980 }, { "epoch": 2.2765720943226873, "grad_norm": 1.6214021444320679, "learning_rate": 5.00460413459681e-05, "loss": 0.4846308708190918, "step": 382990 }, { "epoch": 2.2766315363993557, "grad_norm": 1.2032268047332764, "learning_rate": 5.0041398974012476e-05, "loss": 0.4940066337585449, "step": 383000 }, { "epoch": 2.276690978476024, "grad_norm": 1.3466116189956665, "learning_rate": 5.0036756888879236e-05, "loss": 0.479038667678833, "step": 383010 }, { "epoch": 2.2767504205526925, "grad_norm": 1.3188432455062866, "learning_rate": 5.0032115090590505e-05, "loss": 0.4704470157623291, "step": 383020 }, { "epoch": 2.276809862629361, "grad_norm": 1.5041358470916748, "learning_rate": 5.002747357916857e-05, "loss": 0.5048943519592285, "step": 383030 }, { "epoch": 2.2768693047060293, "grad_norm": 1.3972030878067017, "learning_rate": 5.002283235463563e-05, "loss": 0.5273843765258789, "step": 383040 }, { "epoch": 2.2769287467826977, "grad_norm": 1.4729132652282715, "learning_rate": 5.0018191417013805e-05, "loss": 0.46337118148803713, "step": 383050 }, { "epoch": 2.276988188859366, "grad_norm": 1.2938297986984253, "learning_rate": 5.0013550766325366e-05, "loss": 0.48104381561279297, "step": 383060 }, { "epoch": 2.2770476309360346, "grad_norm": 1.1144464015960693, "learning_rate": 5.000891040259251e-05, "loss": 0.476041316986084, "step": 383070 }, { "epoch": 2.2771070730127025, "grad_norm": 1.2035181522369385, "learning_rate": 5.000427032583739e-05, "loss": 0.4730253219604492, "step": 383080 }, { "epoch": 2.2771665150893714, "grad_norm": 1.0964939594268799, "learning_rate": 4.999963053608227e-05, "loss": 0.4986018180847168, "step": 383090 }, { "epoch": 2.2772259571660394, "grad_norm": 1.3100478649139404, "learning_rate": 4.999499103334933e-05, "loss": 0.44118423461914064, "step": 383100 }, { "epoch": 2.277285399242708, "grad_norm": 1.4155384302139282, "learning_rate": 4.999035181766067e-05, "loss": 0.5052292346954346, "step": 383110 }, { "epoch": 2.277344841319376, "grad_norm": 1.533673644065857, "learning_rate": 4.998571288903861e-05, "loss": 0.4663113594055176, "step": 383120 }, { "epoch": 2.2774042833960446, "grad_norm": 1.3613362312316895, "learning_rate": 4.9981074247505274e-05, "loss": 0.5245774745941162, "step": 383130 }, { "epoch": 2.277463725472713, "grad_norm": 1.1322555541992188, "learning_rate": 4.997643589308287e-05, "loss": 0.5033355236053467, "step": 383140 }, { "epoch": 2.2775231675493814, "grad_norm": 1.5198748111724854, "learning_rate": 4.997179782579355e-05, "loss": 0.5094589233398438, "step": 383150 }, { "epoch": 2.27758260962605, "grad_norm": 1.0603364706039429, "learning_rate": 4.996716004565959e-05, "loss": 0.46835575103759763, "step": 383160 }, { "epoch": 2.2776420517027183, "grad_norm": 1.3150572776794434, "learning_rate": 4.996252255270309e-05, "loss": 0.46640801429748535, "step": 383170 }, { "epoch": 2.2777014937793867, "grad_norm": 1.1826097965240479, "learning_rate": 4.9957885346946224e-05, "loss": 0.4641746997833252, "step": 383180 }, { "epoch": 2.277760935856055, "grad_norm": 1.364102840423584, "learning_rate": 4.995324842841125e-05, "loss": 0.43731322288513186, "step": 383190 }, { "epoch": 2.2778203779327235, "grad_norm": 1.3345568180084229, "learning_rate": 4.994861179712031e-05, "loss": 0.4534759521484375, "step": 383200 }, { "epoch": 2.277879820009392, "grad_norm": 1.3665152788162231, "learning_rate": 4.9943975453095555e-05, "loss": 0.4638822078704834, "step": 383210 }, { "epoch": 2.2779392620860603, "grad_norm": 1.2673345804214478, "learning_rate": 4.9939339396359254e-05, "loss": 0.5004961013793945, "step": 383220 }, { "epoch": 2.2779987041627288, "grad_norm": 1.3163102865219116, "learning_rate": 4.993470362693349e-05, "loss": 0.48493146896362305, "step": 383230 }, { "epoch": 2.278058146239397, "grad_norm": 1.0812532901763916, "learning_rate": 4.9930068144840456e-05, "loss": 0.52967529296875, "step": 383240 }, { "epoch": 2.2781175883160656, "grad_norm": 1.194856882095337, "learning_rate": 4.992543295010237e-05, "loss": 0.4858579635620117, "step": 383250 }, { "epoch": 2.278177030392734, "grad_norm": 1.5124831199645996, "learning_rate": 4.9920798042741384e-05, "loss": 0.48145523071289065, "step": 383260 }, { "epoch": 2.278236472469402, "grad_norm": 1.4076412916183472, "learning_rate": 4.991616342277966e-05, "loss": 0.45476369857788085, "step": 383270 }, { "epoch": 2.2782959145460704, "grad_norm": 1.1029167175292969, "learning_rate": 4.991152909023937e-05, "loss": 0.48447751998901367, "step": 383280 }, { "epoch": 2.278355356622739, "grad_norm": 1.5268630981445312, "learning_rate": 4.9906895045142703e-05, "loss": 0.4889556407928467, "step": 383290 }, { "epoch": 2.278414798699407, "grad_norm": 1.2549129724502563, "learning_rate": 4.990226128751181e-05, "loss": 0.5143596649169921, "step": 383300 }, { "epoch": 2.2784742407760756, "grad_norm": 1.306660532951355, "learning_rate": 4.989762781736881e-05, "loss": 0.4622507095336914, "step": 383310 }, { "epoch": 2.278533682852744, "grad_norm": 1.6393754482269287, "learning_rate": 4.9892994634735965e-05, "loss": 0.49413456916809084, "step": 383320 }, { "epoch": 2.2785931249294125, "grad_norm": 1.4066601991653442, "learning_rate": 4.988836173963538e-05, "loss": 0.49025449752807615, "step": 383330 }, { "epoch": 2.278652567006081, "grad_norm": 1.2950819730758667, "learning_rate": 4.988372913208922e-05, "loss": 0.48134584426879884, "step": 383340 }, { "epoch": 2.2787120090827493, "grad_norm": 1.3112759590148926, "learning_rate": 4.9879096812119676e-05, "loss": 0.4873534679412842, "step": 383350 }, { "epoch": 2.2787714511594177, "grad_norm": 1.2689565420150757, "learning_rate": 4.987446477974887e-05, "loss": 0.454595947265625, "step": 383360 }, { "epoch": 2.278830893236086, "grad_norm": 1.1446717977523804, "learning_rate": 4.986983303499898e-05, "loss": 0.4803112030029297, "step": 383370 }, { "epoch": 2.2788903353127545, "grad_norm": 1.1161185503005981, "learning_rate": 4.9865201577892126e-05, "loss": 0.5177525520324707, "step": 383380 }, { "epoch": 2.278949777389423, "grad_norm": 1.189512848854065, "learning_rate": 4.9860570408450535e-05, "loss": 0.4146100997924805, "step": 383390 }, { "epoch": 2.2790092194660914, "grad_norm": 1.0839203596115112, "learning_rate": 4.985593952669631e-05, "loss": 0.45440311431884767, "step": 383400 }, { "epoch": 2.2790686615427598, "grad_norm": 1.3040193319320679, "learning_rate": 4.985130893265162e-05, "loss": 0.5015904903411865, "step": 383410 }, { "epoch": 2.279128103619428, "grad_norm": 1.1209957599639893, "learning_rate": 4.984667862633861e-05, "loss": 0.4703218460083008, "step": 383420 }, { "epoch": 2.2791875456960966, "grad_norm": 1.3056035041809082, "learning_rate": 4.984204860777944e-05, "loss": 0.504283332824707, "step": 383430 }, { "epoch": 2.279246987772765, "grad_norm": 1.188325047492981, "learning_rate": 4.98374188769962e-05, "loss": 0.458147668838501, "step": 383440 }, { "epoch": 2.2793064298494334, "grad_norm": 1.0918283462524414, "learning_rate": 4.983278943401113e-05, "loss": 0.44457664489746096, "step": 383450 }, { "epoch": 2.2793658719261014, "grad_norm": 1.5799965858459473, "learning_rate": 4.9828160278846325e-05, "loss": 0.5042241096496582, "step": 383460 }, { "epoch": 2.27942531400277, "grad_norm": 1.0188542604446411, "learning_rate": 4.9823531411523944e-05, "loss": 0.4325109481811523, "step": 383470 }, { "epoch": 2.2794847560794382, "grad_norm": 1.6249985694885254, "learning_rate": 4.981890283206612e-05, "loss": 0.4362895965576172, "step": 383480 }, { "epoch": 2.2795441981561066, "grad_norm": 1.275904655456543, "learning_rate": 4.9814274540495e-05, "loss": 0.502005672454834, "step": 383490 }, { "epoch": 2.279603640232775, "grad_norm": 1.056073546409607, "learning_rate": 4.9809646536832715e-05, "loss": 0.44052419662475584, "step": 383500 }, { "epoch": 2.2796630823094435, "grad_norm": 1.4233490228652954, "learning_rate": 4.9805018821101383e-05, "loss": 0.4585367202758789, "step": 383510 }, { "epoch": 2.279722524386112, "grad_norm": 1.532559871673584, "learning_rate": 4.980039139332321e-05, "loss": 0.48391008377075195, "step": 383520 }, { "epoch": 2.2797819664627803, "grad_norm": 1.6268025636672974, "learning_rate": 4.9795764253520285e-05, "loss": 0.5216556549072265, "step": 383530 }, { "epoch": 2.2798414085394487, "grad_norm": 0.9768624901771545, "learning_rate": 4.9791137401714746e-05, "loss": 0.47855043411254883, "step": 383540 }, { "epoch": 2.279900850616117, "grad_norm": 1.7165124416351318, "learning_rate": 4.978651083792872e-05, "loss": 0.5204378128051758, "step": 383550 }, { "epoch": 2.2799602926927856, "grad_norm": 1.4731202125549316, "learning_rate": 4.978188456218436e-05, "loss": 0.5000443935394288, "step": 383560 }, { "epoch": 2.280019734769454, "grad_norm": 1.165216326713562, "learning_rate": 4.9777258574503756e-05, "loss": 0.5251440048217774, "step": 383570 }, { "epoch": 2.2800791768461224, "grad_norm": 1.8971924781799316, "learning_rate": 4.977263287490909e-05, "loss": 0.5505584716796875, "step": 383580 }, { "epoch": 2.280138618922791, "grad_norm": 1.0171715021133423, "learning_rate": 4.9768007463422494e-05, "loss": 0.5071749687194824, "step": 383590 }, { "epoch": 2.280198060999459, "grad_norm": 1.44634211063385, "learning_rate": 4.976338234006601e-05, "loss": 0.496213960647583, "step": 383600 }, { "epoch": 2.2802575030761276, "grad_norm": 1.4647438526153564, "learning_rate": 4.9758757504861856e-05, "loss": 0.4538568496704102, "step": 383610 }, { "epoch": 2.280316945152796, "grad_norm": 1.6028860807418823, "learning_rate": 4.9754132957832114e-05, "loss": 0.4797350883483887, "step": 383620 }, { "epoch": 2.280376387229464, "grad_norm": 1.1425036191940308, "learning_rate": 4.974950869899891e-05, "loss": 0.4982443809509277, "step": 383630 }, { "epoch": 2.280435829306133, "grad_norm": 1.1121797561645508, "learning_rate": 4.9744884728384334e-05, "loss": 0.5210637092590332, "step": 383640 }, { "epoch": 2.280495271382801, "grad_norm": 1.639362096786499, "learning_rate": 4.97402610460106e-05, "loss": 0.46365013122558596, "step": 383650 }, { "epoch": 2.2805547134594693, "grad_norm": 1.3381363153457642, "learning_rate": 4.973563765189973e-05, "loss": 0.48056869506835936, "step": 383660 }, { "epoch": 2.2806141555361377, "grad_norm": 1.4834774732589722, "learning_rate": 4.9731014546073854e-05, "loss": 0.5546384811401367, "step": 383670 }, { "epoch": 2.280673597612806, "grad_norm": 1.172849416732788, "learning_rate": 4.9726391728555136e-05, "loss": 0.48123760223388673, "step": 383680 }, { "epoch": 2.2807330396894745, "grad_norm": 1.148323893547058, "learning_rate": 4.9721769199365654e-05, "loss": 0.41145687103271483, "step": 383690 }, { "epoch": 2.280792481766143, "grad_norm": 1.2907729148864746, "learning_rate": 4.971714695852751e-05, "loss": 0.5037639617919922, "step": 383700 }, { "epoch": 2.2808519238428113, "grad_norm": 1.5884346961975098, "learning_rate": 4.971252500606288e-05, "loss": 0.5346711158752442, "step": 383710 }, { "epoch": 2.2809113659194797, "grad_norm": 1.4059876203536987, "learning_rate": 4.9707903341993815e-05, "loss": 0.491152286529541, "step": 383720 }, { "epoch": 2.280970807996148, "grad_norm": 1.5240468978881836, "learning_rate": 4.970328196634243e-05, "loss": 0.5146202564239502, "step": 383730 }, { "epoch": 2.2810302500728166, "grad_norm": 1.471673846244812, "learning_rate": 4.969866087913081e-05, "loss": 0.5114276885986329, "step": 383740 }, { "epoch": 2.281089692149485, "grad_norm": 1.6590901613235474, "learning_rate": 4.9694040080381114e-05, "loss": 0.5544737339019775, "step": 383750 }, { "epoch": 2.2811491342261534, "grad_norm": 1.5562502145767212, "learning_rate": 4.968941957011542e-05, "loss": 0.48821706771850587, "step": 383760 }, { "epoch": 2.281208576302822, "grad_norm": 1.1112247705459595, "learning_rate": 4.9684799348355845e-05, "loss": 0.48715734481811523, "step": 383770 }, { "epoch": 2.2812680183794902, "grad_norm": 1.3763757944107056, "learning_rate": 4.9680179415124466e-05, "loss": 0.5574588775634766, "step": 383780 }, { "epoch": 2.2813274604561586, "grad_norm": 1.1587153673171997, "learning_rate": 4.9675559770443405e-05, "loss": 0.46686420440673826, "step": 383790 }, { "epoch": 2.281386902532827, "grad_norm": 1.713405966758728, "learning_rate": 4.967094041433472e-05, "loss": 0.48206520080566406, "step": 383800 }, { "epoch": 2.2814463446094955, "grad_norm": 1.4601216316223145, "learning_rate": 4.9666321346820574e-05, "loss": 0.4698200702667236, "step": 383810 }, { "epoch": 2.2815057866861634, "grad_norm": 1.5099189281463623, "learning_rate": 4.966170256792301e-05, "loss": 0.446116304397583, "step": 383820 }, { "epoch": 2.2815652287628323, "grad_norm": 1.3121531009674072, "learning_rate": 4.9657084077664165e-05, "loss": 0.460178804397583, "step": 383830 }, { "epoch": 2.2816246708395003, "grad_norm": 0.9678823947906494, "learning_rate": 4.96524658760661e-05, "loss": 0.45169706344604493, "step": 383840 }, { "epoch": 2.2816841129161687, "grad_norm": 1.3522149324417114, "learning_rate": 4.9647847963150916e-05, "loss": 0.5097490310668945, "step": 383850 }, { "epoch": 2.281743554992837, "grad_norm": 1.5023149251937866, "learning_rate": 4.964323033894071e-05, "loss": 0.5114607334136962, "step": 383860 }, { "epoch": 2.2818029970695055, "grad_norm": 1.6449788808822632, "learning_rate": 4.963861300345753e-05, "loss": 0.47719831466674806, "step": 383870 }, { "epoch": 2.281862439146174, "grad_norm": 1.4805351495742798, "learning_rate": 4.963399595672354e-05, "loss": 0.4903536796569824, "step": 383880 }, { "epoch": 2.2819218812228423, "grad_norm": 1.4415910243988037, "learning_rate": 4.9629379198760766e-05, "loss": 0.4671809673309326, "step": 383890 }, { "epoch": 2.2819813232995108, "grad_norm": 1.1327264308929443, "learning_rate": 4.9624762729591317e-05, "loss": 0.4924907684326172, "step": 383900 }, { "epoch": 2.282040765376179, "grad_norm": 1.6212612390518188, "learning_rate": 4.962014654923729e-05, "loss": 0.4809884071350098, "step": 383910 }, { "epoch": 2.2821002074528476, "grad_norm": 1.0760581493377686, "learning_rate": 4.9615530657720726e-05, "loss": 0.465914249420166, "step": 383920 }, { "epoch": 2.282159649529516, "grad_norm": 1.2945257425308228, "learning_rate": 4.961091505506371e-05, "loss": 0.49025788307189944, "step": 383930 }, { "epoch": 2.2822190916061844, "grad_norm": 1.351518154144287, "learning_rate": 4.9606299741288375e-05, "loss": 0.5164520740509033, "step": 383940 }, { "epoch": 2.282278533682853, "grad_norm": 1.6810288429260254, "learning_rate": 4.9601684716416766e-05, "loss": 0.5006184577941895, "step": 383950 }, { "epoch": 2.2823379757595212, "grad_norm": 1.1344075202941895, "learning_rate": 4.9597069980470955e-05, "loss": 0.45817813873291013, "step": 383960 }, { "epoch": 2.2823974178361897, "grad_norm": 1.239294409751892, "learning_rate": 4.959245553347301e-05, "loss": 0.5148568630218506, "step": 383970 }, { "epoch": 2.282456859912858, "grad_norm": 1.292320966720581, "learning_rate": 4.9587841375445035e-05, "loss": 0.4585252285003662, "step": 383980 }, { "epoch": 2.2825163019895265, "grad_norm": 1.5183933973312378, "learning_rate": 4.958322750640907e-05, "loss": 0.4814910888671875, "step": 383990 }, { "epoch": 2.282575744066195, "grad_norm": 1.4267390966415405, "learning_rate": 4.957861392638719e-05, "loss": 0.5142730712890625, "step": 384000 }, { "epoch": 2.282635186142863, "grad_norm": 1.3872721195220947, "learning_rate": 4.9574000635401484e-05, "loss": 0.5495495319366455, "step": 384010 }, { "epoch": 2.2826946282195313, "grad_norm": 1.4833751916885376, "learning_rate": 4.9569387633474025e-05, "loss": 0.46368207931518557, "step": 384020 }, { "epoch": 2.2827540702961997, "grad_norm": 1.3812803030014038, "learning_rate": 4.9564774920626855e-05, "loss": 0.42733187675476075, "step": 384030 }, { "epoch": 2.282813512372868, "grad_norm": 1.9049735069274902, "learning_rate": 4.956016249688205e-05, "loss": 0.5266973972320557, "step": 384040 }, { "epoch": 2.2828729544495365, "grad_norm": 1.2975066900253296, "learning_rate": 4.9555550362261694e-05, "loss": 0.4846382141113281, "step": 384050 }, { "epoch": 2.282932396526205, "grad_norm": 1.3761026859283447, "learning_rate": 4.955093851678778e-05, "loss": 0.5034289360046387, "step": 384060 }, { "epoch": 2.2829918386028734, "grad_norm": 1.4301965236663818, "learning_rate": 4.954632696048247e-05, "loss": 0.46217732429504393, "step": 384070 }, { "epoch": 2.2830512806795418, "grad_norm": 1.3585240840911865, "learning_rate": 4.954171569336777e-05, "loss": 0.46849689483642576, "step": 384080 }, { "epoch": 2.28311072275621, "grad_norm": 1.499725580215454, "learning_rate": 4.953710471546574e-05, "loss": 0.47370247840881347, "step": 384090 }, { "epoch": 2.2831701648328786, "grad_norm": 1.2653207778930664, "learning_rate": 4.953249402679844e-05, "loss": 0.5131192207336426, "step": 384100 }, { "epoch": 2.283229606909547, "grad_norm": 0.9633221626281738, "learning_rate": 4.952788362738793e-05, "loss": 0.4517373561859131, "step": 384110 }, { "epoch": 2.2832890489862154, "grad_norm": 1.3840490579605103, "learning_rate": 4.952327351725626e-05, "loss": 0.5089831352233887, "step": 384120 }, { "epoch": 2.283348491062884, "grad_norm": 1.1992154121398926, "learning_rate": 4.951866369642546e-05, "loss": 0.4934087753295898, "step": 384130 }, { "epoch": 2.2834079331395523, "grad_norm": 1.1447583436965942, "learning_rate": 4.9514054164917635e-05, "loss": 0.459482479095459, "step": 384140 }, { "epoch": 2.2834673752162207, "grad_norm": 1.8979617357254028, "learning_rate": 4.950944492275484e-05, "loss": 0.4540074825286865, "step": 384150 }, { "epoch": 2.283526817292889, "grad_norm": 1.0604745149612427, "learning_rate": 4.950483596995902e-05, "loss": 0.47992782592773436, "step": 384160 }, { "epoch": 2.2835862593695575, "grad_norm": 1.140856146812439, "learning_rate": 4.950022730655234e-05, "loss": 0.4583621025085449, "step": 384170 }, { "epoch": 2.283645701446226, "grad_norm": 1.381779432296753, "learning_rate": 4.949561893255679e-05, "loss": 0.46433534622192385, "step": 384180 }, { "epoch": 2.2837051435228943, "grad_norm": 1.1497782468795776, "learning_rate": 4.94910108479944e-05, "loss": 0.511159086227417, "step": 384190 }, { "epoch": 2.2837645855995623, "grad_norm": 1.3941320180892944, "learning_rate": 4.948640305288728e-05, "loss": 0.4678949356079102, "step": 384200 }, { "epoch": 2.2838240276762307, "grad_norm": 1.3418612480163574, "learning_rate": 4.9481795547257454e-05, "loss": 0.4587134838104248, "step": 384210 }, { "epoch": 2.283883469752899, "grad_norm": 1.0983678102493286, "learning_rate": 4.94771883311269e-05, "loss": 0.4901732921600342, "step": 384220 }, { "epoch": 2.2839429118295675, "grad_norm": 1.2827308177947998, "learning_rate": 4.9472581404517687e-05, "loss": 0.47040772438049316, "step": 384230 }, { "epoch": 2.284002353906236, "grad_norm": 1.7855702638626099, "learning_rate": 4.946797476745188e-05, "loss": 0.5315479278564453, "step": 384240 }, { "epoch": 2.2840617959829044, "grad_norm": 2.171969413757324, "learning_rate": 4.9463368419951506e-05, "loss": 0.5227030277252197, "step": 384250 }, { "epoch": 2.284121238059573, "grad_norm": 1.091659665107727, "learning_rate": 4.945876236203859e-05, "loss": 0.4624283790588379, "step": 384260 }, { "epoch": 2.284180680136241, "grad_norm": 1.216330647468567, "learning_rate": 4.9454156593735176e-05, "loss": 0.4942084789276123, "step": 384270 }, { "epoch": 2.2842401222129096, "grad_norm": 1.4821231365203857, "learning_rate": 4.944955111506328e-05, "loss": 0.49902892112731934, "step": 384280 }, { "epoch": 2.284299564289578, "grad_norm": 1.3176387548446655, "learning_rate": 4.944494592604493e-05, "loss": 0.4740752220153809, "step": 384290 }, { "epoch": 2.2843590063662464, "grad_norm": 1.5111336708068848, "learning_rate": 4.9440341026702186e-05, "loss": 0.4675501823425293, "step": 384300 }, { "epoch": 2.284418448442915, "grad_norm": 1.373286247253418, "learning_rate": 4.943573641705706e-05, "loss": 0.5164113998413086, "step": 384310 }, { "epoch": 2.2844778905195833, "grad_norm": 1.418214201927185, "learning_rate": 4.943113209713158e-05, "loss": 0.44787025451660156, "step": 384320 }, { "epoch": 2.2845373325962517, "grad_norm": 1.4734352827072144, "learning_rate": 4.9426528066947765e-05, "loss": 0.4494637489318848, "step": 384330 }, { "epoch": 2.28459677467292, "grad_norm": 1.1983330249786377, "learning_rate": 4.942192432652765e-05, "loss": 0.4981718063354492, "step": 384340 }, { "epoch": 2.2846562167495885, "grad_norm": 1.414618730545044, "learning_rate": 4.941732087589325e-05, "loss": 0.5582365036010742, "step": 384350 }, { "epoch": 2.284715658826257, "grad_norm": 1.3586431741714478, "learning_rate": 4.941271771506656e-05, "loss": 0.5483744144439697, "step": 384360 }, { "epoch": 2.284775100902925, "grad_norm": 1.2864748239517212, "learning_rate": 4.940811484406966e-05, "loss": 0.4869532585144043, "step": 384370 }, { "epoch": 2.2848345429795938, "grad_norm": 1.2785241603851318, "learning_rate": 4.940351226292453e-05, "loss": 0.49300732612609866, "step": 384380 }, { "epoch": 2.2848939850562617, "grad_norm": 1.465188980102539, "learning_rate": 4.93989099716532e-05, "loss": 0.5088204383850098, "step": 384390 }, { "epoch": 2.28495342713293, "grad_norm": 1.0914205312728882, "learning_rate": 4.9394307970277686e-05, "loss": 0.5050296306610107, "step": 384400 }, { "epoch": 2.2850128692095986, "grad_norm": 1.409882664680481, "learning_rate": 4.938970625881998e-05, "loss": 0.5054592609405517, "step": 384410 }, { "epoch": 2.285072311286267, "grad_norm": 1.6687179803848267, "learning_rate": 4.938510483730209e-05, "loss": 0.5312932968139649, "step": 384420 }, { "epoch": 2.2851317533629354, "grad_norm": 1.2492021322250366, "learning_rate": 4.9380503705746084e-05, "loss": 0.4453926086425781, "step": 384430 }, { "epoch": 2.285191195439604, "grad_norm": 1.4528241157531738, "learning_rate": 4.9375902864173934e-05, "loss": 0.49684867858886717, "step": 384440 }, { "epoch": 2.285250637516272, "grad_norm": 1.581982970237732, "learning_rate": 4.937130231260765e-05, "loss": 0.47303180694580077, "step": 384450 }, { "epoch": 2.2853100795929406, "grad_norm": 1.0303692817687988, "learning_rate": 4.936670205106925e-05, "loss": 0.49070425033569337, "step": 384460 }, { "epoch": 2.285369521669609, "grad_norm": 1.1480576992034912, "learning_rate": 4.936210207958072e-05, "loss": 0.5350452423095703, "step": 384470 }, { "epoch": 2.2854289637462775, "grad_norm": 1.548524260520935, "learning_rate": 4.935750239816409e-05, "loss": 0.4987483024597168, "step": 384480 }, { "epoch": 2.285488405822946, "grad_norm": 1.4295661449432373, "learning_rate": 4.935290300684131e-05, "loss": 0.4841350555419922, "step": 384490 }, { "epoch": 2.2855478478996143, "grad_norm": 1.5832462310791016, "learning_rate": 4.9348303905634466e-05, "loss": 0.43545103073120117, "step": 384500 }, { "epoch": 2.2856072899762827, "grad_norm": 1.3867706060409546, "learning_rate": 4.9343705094565496e-05, "loss": 0.49777374267578123, "step": 384510 }, { "epoch": 2.285666732052951, "grad_norm": 1.4872078895568848, "learning_rate": 4.9339106573656424e-05, "loss": 0.5258675575256347, "step": 384520 }, { "epoch": 2.2857261741296195, "grad_norm": 1.5391128063201904, "learning_rate": 4.933450834292925e-05, "loss": 0.5253747940063477, "step": 384530 }, { "epoch": 2.285785616206288, "grad_norm": 1.4962315559387207, "learning_rate": 4.932991040240595e-05, "loss": 0.5068801403045654, "step": 384540 }, { "epoch": 2.2858450582829564, "grad_norm": 1.459924578666687, "learning_rate": 4.932531275210851e-05, "loss": 0.49570589065551757, "step": 384550 }, { "epoch": 2.2859045003596243, "grad_norm": 1.3367124795913696, "learning_rate": 4.932071539205898e-05, "loss": 0.505060338973999, "step": 384560 }, { "epoch": 2.285963942436293, "grad_norm": 1.1567341089248657, "learning_rate": 4.931611832227931e-05, "loss": 0.45038394927978515, "step": 384570 }, { "epoch": 2.286023384512961, "grad_norm": 1.2830382585525513, "learning_rate": 4.931152154279152e-05, "loss": 0.45324029922485354, "step": 384580 }, { "epoch": 2.2860828265896296, "grad_norm": 1.4632688760757446, "learning_rate": 4.9306925053617533e-05, "loss": 0.5247669219970703, "step": 384590 }, { "epoch": 2.286142268666298, "grad_norm": 1.4259474277496338, "learning_rate": 4.930232885477941e-05, "loss": 0.485323429107666, "step": 384600 }, { "epoch": 2.2862017107429664, "grad_norm": 1.2081218957901, "learning_rate": 4.9297732946299105e-05, "loss": 0.4948712348937988, "step": 384610 }, { "epoch": 2.286261152819635, "grad_norm": 1.3400518894195557, "learning_rate": 4.9293137328198574e-05, "loss": 0.5369339942932129, "step": 384620 }, { "epoch": 2.2863205948963032, "grad_norm": 1.378617763519287, "learning_rate": 4.9288542000499874e-05, "loss": 0.5150502681732178, "step": 384630 }, { "epoch": 2.2863800369729717, "grad_norm": 1.744444727897644, "learning_rate": 4.9283946963224966e-05, "loss": 0.5042226314544678, "step": 384640 }, { "epoch": 2.28643947904964, "grad_norm": 1.5488022565841675, "learning_rate": 4.9279352216395766e-05, "loss": 0.47008647918701174, "step": 384650 }, { "epoch": 2.2864989211263085, "grad_norm": 1.9030345678329468, "learning_rate": 4.927475776003433e-05, "loss": 0.5312929153442383, "step": 384660 }, { "epoch": 2.286558363202977, "grad_norm": 1.5467532873153687, "learning_rate": 4.927016359416261e-05, "loss": 0.4458888530731201, "step": 384670 }, { "epoch": 2.2866178052796453, "grad_norm": 1.6320443153381348, "learning_rate": 4.926556971880255e-05, "loss": 0.4961374282836914, "step": 384680 }, { "epoch": 2.2866772473563137, "grad_norm": 1.5507769584655762, "learning_rate": 4.9260976133976166e-05, "loss": 0.5039290904998779, "step": 384690 }, { "epoch": 2.286736689432982, "grad_norm": 1.067941665649414, "learning_rate": 4.9256382839705464e-05, "loss": 0.4821596145629883, "step": 384700 }, { "epoch": 2.2867961315096506, "grad_norm": 1.1463124752044678, "learning_rate": 4.925178983601235e-05, "loss": 0.4725026607513428, "step": 384710 }, { "epoch": 2.286855573586319, "grad_norm": 1.141984462738037, "learning_rate": 4.9247197122918796e-05, "loss": 0.4695412635803223, "step": 384720 }, { "epoch": 2.2869150156629874, "grad_norm": 1.4368281364440918, "learning_rate": 4.9242604700446814e-05, "loss": 0.5260595321655274, "step": 384730 }, { "epoch": 2.286974457739656, "grad_norm": 1.6235597133636475, "learning_rate": 4.923801256861837e-05, "loss": 0.4510478973388672, "step": 384740 }, { "epoch": 2.2870338998163238, "grad_norm": 1.5802183151245117, "learning_rate": 4.923342072745538e-05, "loss": 0.5434688568115235, "step": 384750 }, { "epoch": 2.287093341892992, "grad_norm": 1.3377643823623657, "learning_rate": 4.92288291769799e-05, "loss": 0.4772735595703125, "step": 384760 }, { "epoch": 2.2871527839696606, "grad_norm": 1.4366458654403687, "learning_rate": 4.922423791721381e-05, "loss": 0.4951735496520996, "step": 384770 }, { "epoch": 2.287212226046329, "grad_norm": 1.1602650880813599, "learning_rate": 4.921964694817909e-05, "loss": 0.46583032608032227, "step": 384780 }, { "epoch": 2.2872716681229974, "grad_norm": 1.570085883140564, "learning_rate": 4.9215056269897733e-05, "loss": 0.5060383796691894, "step": 384790 }, { "epoch": 2.287331110199666, "grad_norm": 1.5827059745788574, "learning_rate": 4.9210465882391684e-05, "loss": 0.4951939105987549, "step": 384800 }, { "epoch": 2.2873905522763343, "grad_norm": 1.3912819623947144, "learning_rate": 4.920587578568287e-05, "loss": 0.520931339263916, "step": 384810 }, { "epoch": 2.2874499943530027, "grad_norm": 1.5100001096725464, "learning_rate": 4.920128597979334e-05, "loss": 0.48709897994995116, "step": 384820 }, { "epoch": 2.287509436429671, "grad_norm": 1.5297006368637085, "learning_rate": 4.9196696464744954e-05, "loss": 0.5095550537109375, "step": 384830 }, { "epoch": 2.2875688785063395, "grad_norm": 1.4132527112960815, "learning_rate": 4.919210724055971e-05, "loss": 0.4787753582000732, "step": 384840 }, { "epoch": 2.287628320583008, "grad_norm": 1.3377431631088257, "learning_rate": 4.918751830725951e-05, "loss": 0.5086890697479248, "step": 384850 }, { "epoch": 2.2876877626596763, "grad_norm": 1.448837399482727, "learning_rate": 4.9182929664866395e-05, "loss": 0.5069526672363281, "step": 384860 }, { "epoch": 2.2877472047363447, "grad_norm": 1.3558155298233032, "learning_rate": 4.917834131340226e-05, "loss": 0.5117111206054688, "step": 384870 }, { "epoch": 2.287806646813013, "grad_norm": 1.0898478031158447, "learning_rate": 4.917375325288906e-05, "loss": 0.46183147430419924, "step": 384880 }, { "epoch": 2.2878660888896816, "grad_norm": 1.473005771636963, "learning_rate": 4.9169165483348754e-05, "loss": 0.4532024383544922, "step": 384890 }, { "epoch": 2.28792553096635, "grad_norm": 1.476704478263855, "learning_rate": 4.916457800480327e-05, "loss": 0.5056042671203613, "step": 384900 }, { "epoch": 2.2879849730430184, "grad_norm": 1.3228297233581543, "learning_rate": 4.915999081727454e-05, "loss": 0.45967912673950195, "step": 384910 }, { "epoch": 2.288044415119687, "grad_norm": 1.263622522354126, "learning_rate": 4.915540392078456e-05, "loss": 0.47431421279907227, "step": 384920 }, { "epoch": 2.2881038571963552, "grad_norm": 1.3599432706832886, "learning_rate": 4.915081731535525e-05, "loss": 0.4685464859008789, "step": 384930 }, { "epoch": 2.288163299273023, "grad_norm": 1.2858343124389648, "learning_rate": 4.9146231001008544e-05, "loss": 0.46009464263916017, "step": 384940 }, { "epoch": 2.2882227413496916, "grad_norm": 1.3748751878738403, "learning_rate": 4.914164497776637e-05, "loss": 0.5193902969360351, "step": 384950 }, { "epoch": 2.28828218342636, "grad_norm": 1.234083652496338, "learning_rate": 4.9137059245650683e-05, "loss": 0.5305200576782226, "step": 384960 }, { "epoch": 2.2883416255030284, "grad_norm": 1.2842445373535156, "learning_rate": 4.913247380468342e-05, "loss": 0.5242690086364746, "step": 384970 }, { "epoch": 2.288401067579697, "grad_norm": 1.2353975772857666, "learning_rate": 4.912788865488647e-05, "loss": 0.47433815002441404, "step": 384980 }, { "epoch": 2.2884605096563653, "grad_norm": 1.4561078548431396, "learning_rate": 4.912330379628185e-05, "loss": 0.5405170440673828, "step": 384990 }, { "epoch": 2.2885199517330337, "grad_norm": 1.1487476825714111, "learning_rate": 4.911871922889144e-05, "loss": 0.4351661682128906, "step": 385000 }, { "epoch": 2.288579393809702, "grad_norm": 1.2212426662445068, "learning_rate": 4.911413495273718e-05, "loss": 0.45191073417663574, "step": 385010 }, { "epoch": 2.2886388358863705, "grad_norm": 0.9257256388664246, "learning_rate": 4.910955096784102e-05, "loss": 0.4999855995178223, "step": 385020 }, { "epoch": 2.288698277963039, "grad_norm": 1.3579654693603516, "learning_rate": 4.910496727422485e-05, "loss": 0.5146091461181641, "step": 385030 }, { "epoch": 2.2887577200397073, "grad_norm": 1.4436476230621338, "learning_rate": 4.9100383871910585e-05, "loss": 0.4850164413452148, "step": 385040 }, { "epoch": 2.2888171621163758, "grad_norm": 1.249203085899353, "learning_rate": 4.909580076092022e-05, "loss": 0.4943696022033691, "step": 385050 }, { "epoch": 2.288876604193044, "grad_norm": 1.4064399003982544, "learning_rate": 4.909121794127564e-05, "loss": 0.4322312831878662, "step": 385060 }, { "epoch": 2.2889360462697126, "grad_norm": 1.3058245182037354, "learning_rate": 4.908663541299879e-05, "loss": 0.438431978225708, "step": 385070 }, { "epoch": 2.288995488346381, "grad_norm": 1.5640325546264648, "learning_rate": 4.908205317611151e-05, "loss": 0.4878455638885498, "step": 385080 }, { "epoch": 2.2890549304230494, "grad_norm": 1.154841423034668, "learning_rate": 4.9077471230635816e-05, "loss": 0.4758609771728516, "step": 385090 }, { "epoch": 2.289114372499718, "grad_norm": 1.3019726276397705, "learning_rate": 4.907288957659359e-05, "loss": 0.4789179801940918, "step": 385100 }, { "epoch": 2.289173814576386, "grad_norm": 1.0437113046646118, "learning_rate": 4.9068308214006724e-05, "loss": 0.5234525203704834, "step": 385110 }, { "epoch": 2.2892332566530547, "grad_norm": 1.3645037412643433, "learning_rate": 4.906372714289718e-05, "loss": 0.5022109031677247, "step": 385120 }, { "epoch": 2.2892926987297226, "grad_norm": 1.501354694366455, "learning_rate": 4.905914636328688e-05, "loss": 0.5210388660430908, "step": 385130 }, { "epoch": 2.289352140806391, "grad_norm": 1.0737208127975464, "learning_rate": 4.9054565875197654e-05, "loss": 0.45690078735351564, "step": 385140 }, { "epoch": 2.2894115828830595, "grad_norm": 0.8870537281036377, "learning_rate": 4.90499856786515e-05, "loss": 0.460772180557251, "step": 385150 }, { "epoch": 2.289471024959728, "grad_norm": 1.4692656993865967, "learning_rate": 4.904540577367028e-05, "loss": 0.46893882751464844, "step": 385160 }, { "epoch": 2.2895304670363963, "grad_norm": 0.9336267709732056, "learning_rate": 4.9040826160275904e-05, "loss": 0.491367244720459, "step": 385170 }, { "epoch": 2.2895899091130647, "grad_norm": 1.488545298576355, "learning_rate": 4.9036246838490324e-05, "loss": 0.5179451942443848, "step": 385180 }, { "epoch": 2.289649351189733, "grad_norm": 0.9540513157844543, "learning_rate": 4.903166780833544e-05, "loss": 0.44080386161804197, "step": 385190 }, { "epoch": 2.2897087932664015, "grad_norm": 1.3592945337295532, "learning_rate": 4.9027089069833096e-05, "loss": 0.4927516460418701, "step": 385200 }, { "epoch": 2.28976823534307, "grad_norm": 1.0984379053115845, "learning_rate": 4.9022510623005216e-05, "loss": 0.5309817314147949, "step": 385210 }, { "epoch": 2.2898276774197384, "grad_norm": 1.2778648138046265, "learning_rate": 4.901793246787374e-05, "loss": 0.46027679443359376, "step": 385220 }, { "epoch": 2.2898871194964068, "grad_norm": 1.498401165008545, "learning_rate": 4.901335460446054e-05, "loss": 0.49437479972839354, "step": 385230 }, { "epoch": 2.289946561573075, "grad_norm": 1.6822158098220825, "learning_rate": 4.900877703278751e-05, "loss": 0.51917724609375, "step": 385240 }, { "epoch": 2.2900060036497436, "grad_norm": 1.4140607118606567, "learning_rate": 4.9004199752876594e-05, "loss": 0.4403373241424561, "step": 385250 }, { "epoch": 2.290065445726412, "grad_norm": 1.6809812784194946, "learning_rate": 4.8999622764749644e-05, "loss": 0.5090568542480469, "step": 385260 }, { "epoch": 2.2901248878030804, "grad_norm": 1.3489435911178589, "learning_rate": 4.899504606842852e-05, "loss": 0.5160194396972656, "step": 385270 }, { "epoch": 2.290184329879749, "grad_norm": 1.3550430536270142, "learning_rate": 4.89904696639352e-05, "loss": 0.5351790904998779, "step": 385280 }, { "epoch": 2.2902437719564173, "grad_norm": 1.482818603515625, "learning_rate": 4.8985893551291525e-05, "loss": 0.5040874481201172, "step": 385290 }, { "epoch": 2.2903032140330852, "grad_norm": 1.1451345682144165, "learning_rate": 4.898131773051937e-05, "loss": 0.4481037139892578, "step": 385300 }, { "epoch": 2.290362656109754, "grad_norm": 1.5072263479232788, "learning_rate": 4.8976742201640716e-05, "loss": 0.5113560676574707, "step": 385310 }, { "epoch": 2.290422098186422, "grad_norm": 0.8773506879806519, "learning_rate": 4.897216696467734e-05, "loss": 0.4705638885498047, "step": 385320 }, { "epoch": 2.2904815402630905, "grad_norm": 1.1200993061065674, "learning_rate": 4.896759201965118e-05, "loss": 0.48697528839111326, "step": 385330 }, { "epoch": 2.290540982339759, "grad_norm": 1.1165508031845093, "learning_rate": 4.896301736658409e-05, "loss": 0.49979186058044434, "step": 385340 }, { "epoch": 2.2906004244164273, "grad_norm": 1.3530402183532715, "learning_rate": 4.8958443005498e-05, "loss": 0.48691234588623045, "step": 385350 }, { "epoch": 2.2906598664930957, "grad_norm": 1.594547152519226, "learning_rate": 4.8953868936414776e-05, "loss": 0.5210165023803711, "step": 385360 }, { "epoch": 2.290719308569764, "grad_norm": 1.500584602355957, "learning_rate": 4.894929515935628e-05, "loss": 0.5400148391723633, "step": 385370 }, { "epoch": 2.2907787506464325, "grad_norm": 1.055577039718628, "learning_rate": 4.894472167434442e-05, "loss": 0.4826972961425781, "step": 385380 }, { "epoch": 2.290838192723101, "grad_norm": 1.5227484703063965, "learning_rate": 4.894014848140105e-05, "loss": 0.49285736083984377, "step": 385390 }, { "epoch": 2.2908976347997694, "grad_norm": 1.2042174339294434, "learning_rate": 4.8935575580548025e-05, "loss": 0.4821482181549072, "step": 385400 }, { "epoch": 2.290957076876438, "grad_norm": 0.9703124761581421, "learning_rate": 4.8931002971807285e-05, "loss": 0.45662851333618165, "step": 385410 }, { "epoch": 2.291016518953106, "grad_norm": 0.9487505555152893, "learning_rate": 4.892643065520067e-05, "loss": 0.49968528747558594, "step": 385420 }, { "epoch": 2.2910759610297746, "grad_norm": 1.1460949182510376, "learning_rate": 4.892185863075006e-05, "loss": 0.5164665699005127, "step": 385430 }, { "epoch": 2.291135403106443, "grad_norm": 1.367775559425354, "learning_rate": 4.891728689847729e-05, "loss": 0.4679676055908203, "step": 385440 }, { "epoch": 2.2911948451831115, "grad_norm": 1.5200225114822388, "learning_rate": 4.8912715458404275e-05, "loss": 0.49294452667236327, "step": 385450 }, { "epoch": 2.29125428725978, "grad_norm": 1.1006947755813599, "learning_rate": 4.890814431055287e-05, "loss": 0.4452953338623047, "step": 385460 }, { "epoch": 2.2913137293364483, "grad_norm": 1.2207551002502441, "learning_rate": 4.890357345494491e-05, "loss": 0.4862220764160156, "step": 385470 }, { "epoch": 2.2913731714131167, "grad_norm": 1.4353554248809814, "learning_rate": 4.889900289160231e-05, "loss": 0.5350690841674804, "step": 385480 }, { "epoch": 2.2914326134897847, "grad_norm": 1.185720682144165, "learning_rate": 4.8894432620546906e-05, "loss": 0.49383039474487306, "step": 385490 }, { "epoch": 2.291492055566453, "grad_norm": 1.3302149772644043, "learning_rate": 4.8889862641800574e-05, "loss": 0.493745231628418, "step": 385500 }, { "epoch": 2.2915514976431215, "grad_norm": 1.2963777780532837, "learning_rate": 4.888529295538517e-05, "loss": 0.49996633529663087, "step": 385510 }, { "epoch": 2.29161093971979, "grad_norm": 1.303818702697754, "learning_rate": 4.8880723561322545e-05, "loss": 0.47310581207275393, "step": 385520 }, { "epoch": 2.2916703817964583, "grad_norm": 1.8181219100952148, "learning_rate": 4.887615445963454e-05, "loss": 0.508111572265625, "step": 385530 }, { "epoch": 2.2917298238731267, "grad_norm": 1.2434585094451904, "learning_rate": 4.887158565034307e-05, "loss": 0.4905360698699951, "step": 385540 }, { "epoch": 2.291789265949795, "grad_norm": 1.2060089111328125, "learning_rate": 4.886701713346995e-05, "loss": 0.4629809379577637, "step": 385550 }, { "epoch": 2.2918487080264636, "grad_norm": 1.4143941402435303, "learning_rate": 4.886244890903704e-05, "loss": 0.47774486541748046, "step": 385560 }, { "epoch": 2.291908150103132, "grad_norm": 1.593080997467041, "learning_rate": 4.8857880977066203e-05, "loss": 0.4925844192504883, "step": 385570 }, { "epoch": 2.2919675921798004, "grad_norm": 1.5177497863769531, "learning_rate": 4.885331333757928e-05, "loss": 0.4938366889953613, "step": 385580 }, { "epoch": 2.292027034256469, "grad_norm": 1.4438691139221191, "learning_rate": 4.884874599059812e-05, "loss": 0.5009798049926758, "step": 385590 }, { "epoch": 2.2920864763331372, "grad_norm": 1.3292630910873413, "learning_rate": 4.884417893614454e-05, "loss": 0.45198421478271483, "step": 385600 }, { "epoch": 2.2921459184098056, "grad_norm": 1.7237275838851929, "learning_rate": 4.8839612174240456e-05, "loss": 0.48827733993530276, "step": 385610 }, { "epoch": 2.292205360486474, "grad_norm": 1.3548126220703125, "learning_rate": 4.883504570490769e-05, "loss": 0.47491025924682617, "step": 385620 }, { "epoch": 2.2922648025631425, "grad_norm": 1.2410653829574585, "learning_rate": 4.883047952816806e-05, "loss": 0.47846670150756837, "step": 385630 }, { "epoch": 2.292324244639811, "grad_norm": 1.3184387683868408, "learning_rate": 4.882591364404344e-05, "loss": 0.49741902351379397, "step": 385640 }, { "epoch": 2.2923836867164793, "grad_norm": 1.363198161125183, "learning_rate": 4.882134805255564e-05, "loss": 0.4574584007263184, "step": 385650 }, { "epoch": 2.2924431287931477, "grad_norm": 1.296316146850586, "learning_rate": 4.881678275372651e-05, "loss": 0.46308116912841796, "step": 385660 }, { "epoch": 2.292502570869816, "grad_norm": 1.2238900661468506, "learning_rate": 4.881221774757791e-05, "loss": 0.44255666732788085, "step": 385670 }, { "epoch": 2.292562012946484, "grad_norm": 0.8307507038116455, "learning_rate": 4.8807653034131696e-05, "loss": 0.5161984443664551, "step": 385680 }, { "epoch": 2.2926214550231525, "grad_norm": 1.2197895050048828, "learning_rate": 4.880308861340965e-05, "loss": 0.49907522201538085, "step": 385690 }, { "epoch": 2.292680897099821, "grad_norm": 1.633499026298523, "learning_rate": 4.879852448543359e-05, "loss": 0.5237180709838867, "step": 385700 }, { "epoch": 2.2927403391764893, "grad_norm": 1.4196234941482544, "learning_rate": 4.879396065022542e-05, "loss": 0.501401138305664, "step": 385710 }, { "epoch": 2.2927997812531578, "grad_norm": 1.4958767890930176, "learning_rate": 4.878939710780695e-05, "loss": 0.46174049377441406, "step": 385720 }, { "epoch": 2.292859223329826, "grad_norm": 1.1985108852386475, "learning_rate": 4.878483385819995e-05, "loss": 0.43786230087280276, "step": 385730 }, { "epoch": 2.2929186654064946, "grad_norm": 1.3081114292144775, "learning_rate": 4.878027090142637e-05, "loss": 0.48627943992614747, "step": 385740 }, { "epoch": 2.292978107483163, "grad_norm": 1.4533647298812866, "learning_rate": 4.877570823750795e-05, "loss": 0.47213144302368165, "step": 385750 }, { "epoch": 2.2930375495598314, "grad_norm": 1.4421261548995972, "learning_rate": 4.8771145866466486e-05, "loss": 0.4988839149475098, "step": 385760 }, { "epoch": 2.2930969916365, "grad_norm": 1.2016469240188599, "learning_rate": 4.876658378832389e-05, "loss": 0.4714048862457275, "step": 385770 }, { "epoch": 2.2931564337131682, "grad_norm": 0.9529743790626526, "learning_rate": 4.876202200310194e-05, "loss": 0.4678933143615723, "step": 385780 }, { "epoch": 2.2932158757898367, "grad_norm": 1.4080986976623535, "learning_rate": 4.8757460510822436e-05, "loss": 0.4733733654022217, "step": 385790 }, { "epoch": 2.293275317866505, "grad_norm": 1.3968619108200073, "learning_rate": 4.875289931150728e-05, "loss": 0.49691066741943357, "step": 385800 }, { "epoch": 2.2933347599431735, "grad_norm": 1.0145643949508667, "learning_rate": 4.8748338405178216e-05, "loss": 0.48515024185180666, "step": 385810 }, { "epoch": 2.293394202019842, "grad_norm": 1.2902787923812866, "learning_rate": 4.874377779185709e-05, "loss": 0.5105090141296387, "step": 385820 }, { "epoch": 2.2934536440965103, "grad_norm": 1.352948784828186, "learning_rate": 4.873921747156567e-05, "loss": 0.4662175178527832, "step": 385830 }, { "epoch": 2.2935130861731787, "grad_norm": 1.2765834331512451, "learning_rate": 4.8734657444325846e-05, "loss": 0.49833040237426757, "step": 385840 }, { "epoch": 2.2935725282498467, "grad_norm": 1.3242051601409912, "learning_rate": 4.8730097710159404e-05, "loss": 0.48587260246276853, "step": 385850 }, { "epoch": 2.2936319703265156, "grad_norm": 1.547992467880249, "learning_rate": 4.872553826908814e-05, "loss": 0.5001374244689941, "step": 385860 }, { "epoch": 2.2936914124031835, "grad_norm": 1.4364219903945923, "learning_rate": 4.872097912113389e-05, "loss": 0.49398603439331057, "step": 385870 }, { "epoch": 2.293750854479852, "grad_norm": 1.2816039323806763, "learning_rate": 4.871642026631845e-05, "loss": 0.4582804203033447, "step": 385880 }, { "epoch": 2.2938102965565204, "grad_norm": 1.0862904787063599, "learning_rate": 4.871186170466358e-05, "loss": 0.43567934036254885, "step": 385890 }, { "epoch": 2.2938697386331888, "grad_norm": 1.4794628620147705, "learning_rate": 4.870730343619118e-05, "loss": 0.5051428794860839, "step": 385900 }, { "epoch": 2.293929180709857, "grad_norm": 1.2554594278335571, "learning_rate": 4.870274546092301e-05, "loss": 0.4801839828491211, "step": 385910 }, { "epoch": 2.2939886227865256, "grad_norm": 1.591955304145813, "learning_rate": 4.8698187778880865e-05, "loss": 0.5112441539764404, "step": 385920 }, { "epoch": 2.294048064863194, "grad_norm": 1.7488667964935303, "learning_rate": 4.8693630390086556e-05, "loss": 0.48502402305603026, "step": 385930 }, { "epoch": 2.2941075069398624, "grad_norm": 1.2439080476760864, "learning_rate": 4.8689073294561895e-05, "loss": 0.45425214767456057, "step": 385940 }, { "epoch": 2.294166949016531, "grad_norm": 1.0769113302230835, "learning_rate": 4.8684516492328666e-05, "loss": 0.4267420768737793, "step": 385950 }, { "epoch": 2.2942263910931993, "grad_norm": 1.5499697923660278, "learning_rate": 4.867995998340864e-05, "loss": 0.4805776596069336, "step": 385960 }, { "epoch": 2.2942858331698677, "grad_norm": 1.3433985710144043, "learning_rate": 4.867540376782368e-05, "loss": 0.4666471481323242, "step": 385970 }, { "epoch": 2.294345275246536, "grad_norm": 1.2810249328613281, "learning_rate": 4.867084784559554e-05, "loss": 0.4527581691741943, "step": 385980 }, { "epoch": 2.2944047173232045, "grad_norm": 1.3318533897399902, "learning_rate": 4.8666292216746024e-05, "loss": 0.46577816009521483, "step": 385990 }, { "epoch": 2.294464159399873, "grad_norm": 1.356941819190979, "learning_rate": 4.866173688129692e-05, "loss": 0.5148082733154297, "step": 386000 }, { "epoch": 2.2945236014765413, "grad_norm": 1.218329668045044, "learning_rate": 4.865718183927002e-05, "loss": 0.4389129638671875, "step": 386010 }, { "epoch": 2.2945830435532097, "grad_norm": 2.3840811252593994, "learning_rate": 4.86526270906871e-05, "loss": 0.513448429107666, "step": 386020 }, { "epoch": 2.294642485629878, "grad_norm": 1.4592390060424805, "learning_rate": 4.8648072635569975e-05, "loss": 0.524929141998291, "step": 386030 }, { "epoch": 2.294701927706546, "grad_norm": 1.613126516342163, "learning_rate": 4.864351847394043e-05, "loss": 0.45920677185058595, "step": 386040 }, { "epoch": 2.294761369783215, "grad_norm": 1.1830819845199585, "learning_rate": 4.863896460582024e-05, "loss": 0.4790003776550293, "step": 386050 }, { "epoch": 2.294820811859883, "grad_norm": 1.2504627704620361, "learning_rate": 4.863441103123118e-05, "loss": 0.5033038139343262, "step": 386060 }, { "epoch": 2.2948802539365514, "grad_norm": 1.181518793106079, "learning_rate": 4.862985775019506e-05, "loss": 0.529986572265625, "step": 386070 }, { "epoch": 2.29493969601322, "grad_norm": 1.2656537294387817, "learning_rate": 4.8625304762733634e-05, "loss": 0.4690864562988281, "step": 386080 }, { "epoch": 2.294999138089888, "grad_norm": 1.3332557678222656, "learning_rate": 4.862075206886867e-05, "loss": 0.48475146293640137, "step": 386090 }, { "epoch": 2.2950585801665566, "grad_norm": 1.8135753870010376, "learning_rate": 4.861619966862199e-05, "loss": 0.5045450687408447, "step": 386100 }, { "epoch": 2.295118022243225, "grad_norm": 1.4148763418197632, "learning_rate": 4.861164756201536e-05, "loss": 0.4523333549499512, "step": 386110 }, { "epoch": 2.2951774643198934, "grad_norm": 1.1379351615905762, "learning_rate": 4.8607095749070535e-05, "loss": 0.4911667346954346, "step": 386120 }, { "epoch": 2.295236906396562, "grad_norm": 1.3495166301727295, "learning_rate": 4.860254422980931e-05, "loss": 0.5091409683227539, "step": 386130 }, { "epoch": 2.2952963484732303, "grad_norm": 1.4091006517410278, "learning_rate": 4.8597993004253446e-05, "loss": 0.49118738174438475, "step": 386140 }, { "epoch": 2.2953557905498987, "grad_norm": 1.247302770614624, "learning_rate": 4.8593442072424674e-05, "loss": 0.5070993423461914, "step": 386150 }, { "epoch": 2.295415232626567, "grad_norm": 1.152037501335144, "learning_rate": 4.858889143434486e-05, "loss": 0.44251112937927245, "step": 386160 }, { "epoch": 2.2954746747032355, "grad_norm": 1.0989381074905396, "learning_rate": 4.858434109003571e-05, "loss": 0.48115739822387693, "step": 386170 }, { "epoch": 2.295534116779904, "grad_norm": 1.4577940702438354, "learning_rate": 4.857979103951903e-05, "loss": 0.42539043426513673, "step": 386180 }, { "epoch": 2.2955935588565723, "grad_norm": 1.383792757987976, "learning_rate": 4.85752412828165e-05, "loss": 0.5101128578186035, "step": 386190 }, { "epoch": 2.2956530009332408, "grad_norm": 1.1750459671020508, "learning_rate": 4.857069181994997e-05, "loss": 0.4818134307861328, "step": 386200 }, { "epoch": 2.295712443009909, "grad_norm": 1.4720851182937622, "learning_rate": 4.856614265094118e-05, "loss": 0.5076521873474121, "step": 386210 }, { "epoch": 2.2957718850865776, "grad_norm": 1.1390066146850586, "learning_rate": 4.856159377581184e-05, "loss": 0.4490001678466797, "step": 386220 }, { "epoch": 2.2958313271632456, "grad_norm": 1.2865233421325684, "learning_rate": 4.85570451945838e-05, "loss": 0.48690013885498046, "step": 386230 }, { "epoch": 2.295890769239914, "grad_norm": 1.244154930114746, "learning_rate": 4.855249690727881e-05, "loss": 0.516682243347168, "step": 386240 }, { "epoch": 2.2959502113165824, "grad_norm": 1.7497671842575073, "learning_rate": 4.8547948913918526e-05, "loss": 0.5164327621459961, "step": 386250 }, { "epoch": 2.296009653393251, "grad_norm": 1.3224411010742188, "learning_rate": 4.85434012145248e-05, "loss": 0.5036496162414551, "step": 386260 }, { "epoch": 2.296069095469919, "grad_norm": 1.3651288747787476, "learning_rate": 4.853885380911937e-05, "loss": 0.5219353675842285, "step": 386270 }, { "epoch": 2.2961285375465876, "grad_norm": 1.3317432403564453, "learning_rate": 4.853430669772393e-05, "loss": 0.4318870544433594, "step": 386280 }, { "epoch": 2.296187979623256, "grad_norm": 1.4818798303604126, "learning_rate": 4.852975988036036e-05, "loss": 0.5398774147033691, "step": 386290 }, { "epoch": 2.2962474216999245, "grad_norm": 1.1206793785095215, "learning_rate": 4.852521335705029e-05, "loss": 0.5221563339233398, "step": 386300 }, { "epoch": 2.296306863776593, "grad_norm": 1.346901297569275, "learning_rate": 4.8520667127815504e-05, "loss": 0.5340877056121827, "step": 386310 }, { "epoch": 2.2963663058532613, "grad_norm": 1.5041604042053223, "learning_rate": 4.8516121192677734e-05, "loss": 0.49918560981750487, "step": 386320 }, { "epoch": 2.2964257479299297, "grad_norm": 1.2840297222137451, "learning_rate": 4.8511575551658765e-05, "loss": 0.49156503677368163, "step": 386330 }, { "epoch": 2.296485190006598, "grad_norm": 1.447363257408142, "learning_rate": 4.8507030204780336e-05, "loss": 0.5372208595275879, "step": 386340 }, { "epoch": 2.2965446320832665, "grad_norm": 1.493382215499878, "learning_rate": 4.850248515206417e-05, "loss": 0.4757219314575195, "step": 386350 }, { "epoch": 2.296604074159935, "grad_norm": 1.4503778219223022, "learning_rate": 4.849794039353202e-05, "loss": 0.5225313663482666, "step": 386360 }, { "epoch": 2.2966635162366034, "grad_norm": 1.3252898454666138, "learning_rate": 4.8493395929205625e-05, "loss": 0.5183961391448975, "step": 386370 }, { "epoch": 2.296722958313272, "grad_norm": 1.0806808471679688, "learning_rate": 4.84888517591067e-05, "loss": 0.46413822174072267, "step": 386380 }, { "epoch": 2.29678240038994, "grad_norm": 1.060586929321289, "learning_rate": 4.848430788325703e-05, "loss": 0.46342763900756834, "step": 386390 }, { "epoch": 2.2968418424666086, "grad_norm": 1.497188687324524, "learning_rate": 4.8479764301678324e-05, "loss": 0.5033444404602051, "step": 386400 }, { "epoch": 2.296901284543277, "grad_norm": 1.26638662815094, "learning_rate": 4.847522101439233e-05, "loss": 0.44537911415100095, "step": 386410 }, { "epoch": 2.296960726619945, "grad_norm": 1.4217877388000488, "learning_rate": 4.8470678021420755e-05, "loss": 0.5118298530578613, "step": 386420 }, { "epoch": 2.2970201686966134, "grad_norm": 1.2676942348480225, "learning_rate": 4.846613532278535e-05, "loss": 0.48097810745239256, "step": 386430 }, { "epoch": 2.297079610773282, "grad_norm": 1.4948984384536743, "learning_rate": 4.846159291850787e-05, "loss": 0.5715245246887207, "step": 386440 }, { "epoch": 2.2971390528499502, "grad_norm": 1.2241376638412476, "learning_rate": 4.845705080860997e-05, "loss": 0.4740301132202148, "step": 386450 }, { "epoch": 2.2971984949266187, "grad_norm": 1.4780389070510864, "learning_rate": 4.8452508993113455e-05, "loss": 0.478001070022583, "step": 386460 }, { "epoch": 2.297257937003287, "grad_norm": 1.4885430335998535, "learning_rate": 4.844796747204003e-05, "loss": 0.45145506858825685, "step": 386470 }, { "epoch": 2.2973173790799555, "grad_norm": 1.6061346530914307, "learning_rate": 4.844342624541141e-05, "loss": 0.509740161895752, "step": 386480 }, { "epoch": 2.297376821156624, "grad_norm": 1.4927661418914795, "learning_rate": 4.843888531324932e-05, "loss": 0.48508200645446775, "step": 386490 }, { "epoch": 2.2974362632332923, "grad_norm": 1.5411217212677002, "learning_rate": 4.843434467557548e-05, "loss": 0.4981240749359131, "step": 386500 }, { "epoch": 2.2974957053099607, "grad_norm": 1.3971216678619385, "learning_rate": 4.8429804332411595e-05, "loss": 0.4852243423461914, "step": 386510 }, { "epoch": 2.297555147386629, "grad_norm": 1.283158540725708, "learning_rate": 4.842526428377943e-05, "loss": 0.5092306137084961, "step": 386520 }, { "epoch": 2.2976145894632976, "grad_norm": 1.3030669689178467, "learning_rate": 4.842072452970068e-05, "loss": 0.437907075881958, "step": 386530 }, { "epoch": 2.297674031539966, "grad_norm": 1.1826320886611938, "learning_rate": 4.841618507019706e-05, "loss": 0.41286425590515136, "step": 386540 }, { "epoch": 2.2977334736166344, "grad_norm": 1.2948436737060547, "learning_rate": 4.841164590529028e-05, "loss": 0.5709468841552734, "step": 386550 }, { "epoch": 2.297792915693303, "grad_norm": 0.9144877195358276, "learning_rate": 4.840710703500206e-05, "loss": 0.4614901542663574, "step": 386560 }, { "epoch": 2.297852357769971, "grad_norm": 1.0465985536575317, "learning_rate": 4.840256845935411e-05, "loss": 0.4637563705444336, "step": 386570 }, { "epoch": 2.2979117998466396, "grad_norm": 1.355980634689331, "learning_rate": 4.839803017836812e-05, "loss": 0.47601957321166993, "step": 386580 }, { "epoch": 2.2979712419233076, "grad_norm": 1.116126298904419, "learning_rate": 4.839349219206585e-05, "loss": 0.5005300998687744, "step": 386590 }, { "epoch": 2.2980306839999765, "grad_norm": 1.1713050603866577, "learning_rate": 4.838895450046898e-05, "loss": 0.5264365196228027, "step": 386600 }, { "epoch": 2.2980901260766444, "grad_norm": 1.5249271392822266, "learning_rate": 4.83844171035992e-05, "loss": 0.5378806114196777, "step": 386610 }, { "epoch": 2.298149568153313, "grad_norm": 1.507272720336914, "learning_rate": 4.8379880001478255e-05, "loss": 0.4950162410736084, "step": 386620 }, { "epoch": 2.2982090102299813, "grad_norm": 1.319868803024292, "learning_rate": 4.837534319412781e-05, "loss": 0.49915475845336915, "step": 386630 }, { "epoch": 2.2982684523066497, "grad_norm": 1.306183934211731, "learning_rate": 4.8370806681569565e-05, "loss": 0.49211602210998534, "step": 386640 }, { "epoch": 2.298327894383318, "grad_norm": 1.2631793022155762, "learning_rate": 4.836627046382527e-05, "loss": 0.4921463966369629, "step": 386650 }, { "epoch": 2.2983873364599865, "grad_norm": 1.6307764053344727, "learning_rate": 4.836173454091659e-05, "loss": 0.5032211303710937, "step": 386660 }, { "epoch": 2.298446778536655, "grad_norm": 1.4481452703475952, "learning_rate": 4.8357198912865256e-05, "loss": 0.527040433883667, "step": 386670 }, { "epoch": 2.2985062206133233, "grad_norm": 1.4199614524841309, "learning_rate": 4.8352663579692884e-05, "loss": 0.5088709831237793, "step": 386680 }, { "epoch": 2.2985656626899917, "grad_norm": 1.387128472328186, "learning_rate": 4.834812854142125e-05, "loss": 0.5011293888092041, "step": 386690 }, { "epoch": 2.29862510476666, "grad_norm": 1.093887209892273, "learning_rate": 4.834359379807203e-05, "loss": 0.49266939163208007, "step": 386700 }, { "epoch": 2.2986845468433286, "grad_norm": 1.1096512079238892, "learning_rate": 4.833905934966686e-05, "loss": 0.47608227729797364, "step": 386710 }, { "epoch": 2.298743988919997, "grad_norm": 1.5871484279632568, "learning_rate": 4.833452519622752e-05, "loss": 0.4956964492797852, "step": 386720 }, { "epoch": 2.2988034309966654, "grad_norm": 1.3972301483154297, "learning_rate": 4.8329991337775694e-05, "loss": 0.5015530109405517, "step": 386730 }, { "epoch": 2.298862873073334, "grad_norm": 1.685302734375, "learning_rate": 4.832545777433297e-05, "loss": 0.45169963836669924, "step": 386740 }, { "epoch": 2.2989223151500022, "grad_norm": 1.1863915920257568, "learning_rate": 4.832092450592112e-05, "loss": 0.4301140308380127, "step": 386750 }, { "epoch": 2.2989817572266706, "grad_norm": 1.3088858127593994, "learning_rate": 4.8316391532561814e-05, "loss": 0.482866096496582, "step": 386760 }, { "epoch": 2.299041199303339, "grad_norm": 1.2060918807983398, "learning_rate": 4.8311858854276745e-05, "loss": 0.5038323402404785, "step": 386770 }, { "epoch": 2.299100641380007, "grad_norm": 1.3528640270233154, "learning_rate": 4.830732647108755e-05, "loss": 0.5006422996520996, "step": 386780 }, { "epoch": 2.299160083456676, "grad_norm": 1.4210456609725952, "learning_rate": 4.830279438301599e-05, "loss": 0.47115411758422854, "step": 386790 }, { "epoch": 2.299219525533344, "grad_norm": 1.4930781126022339, "learning_rate": 4.829826259008369e-05, "loss": 0.46899709701538084, "step": 386800 }, { "epoch": 2.2992789676100123, "grad_norm": 1.009004831314087, "learning_rate": 4.8293731092312286e-05, "loss": 0.4913307189941406, "step": 386810 }, { "epoch": 2.2993384096866807, "grad_norm": 1.2333571910858154, "learning_rate": 4.828919988972355e-05, "loss": 0.4961728096008301, "step": 386820 }, { "epoch": 2.299397851763349, "grad_norm": 1.0976604223251343, "learning_rate": 4.828466898233911e-05, "loss": 0.49411764144897463, "step": 386830 }, { "epoch": 2.2994572938400175, "grad_norm": 1.3273566961288452, "learning_rate": 4.8280138370180614e-05, "loss": 0.5073184967041016, "step": 386840 }, { "epoch": 2.299516735916686, "grad_norm": 0.8182185292243958, "learning_rate": 4.827560805326983e-05, "loss": 0.46900405883789065, "step": 386850 }, { "epoch": 2.2995761779933543, "grad_norm": 1.2742857933044434, "learning_rate": 4.827107803162833e-05, "loss": 0.4362905025482178, "step": 386860 }, { "epoch": 2.2996356200700228, "grad_norm": 1.402748465538025, "learning_rate": 4.82665483052778e-05, "loss": 0.47937211990356443, "step": 386870 }, { "epoch": 2.299695062146691, "grad_norm": 1.0010478496551514, "learning_rate": 4.8262018874239946e-05, "loss": 0.5074506759643554, "step": 386880 }, { "epoch": 2.2997545042233596, "grad_norm": 1.3321188688278198, "learning_rate": 4.825748973853643e-05, "loss": 0.4634398937225342, "step": 386890 }, { "epoch": 2.299813946300028, "grad_norm": 1.5753271579742432, "learning_rate": 4.825296089818889e-05, "loss": 0.5106900215148926, "step": 386900 }, { "epoch": 2.2998733883766964, "grad_norm": 2.6895368099212646, "learning_rate": 4.824843235321902e-05, "loss": 0.4752248764038086, "step": 386910 }, { "epoch": 2.299932830453365, "grad_norm": 1.3192538022994995, "learning_rate": 4.824390410364846e-05, "loss": 0.47587146759033205, "step": 386920 }, { "epoch": 2.2999922725300332, "grad_norm": 1.618516206741333, "learning_rate": 4.823937614949888e-05, "loss": 0.5506148338317871, "step": 386930 }, { "epoch": 2.3000517146067017, "grad_norm": 1.407307744026184, "learning_rate": 4.8234848490791915e-05, "loss": 0.47336688041687014, "step": 386940 }, { "epoch": 2.30011115668337, "grad_norm": 1.442527174949646, "learning_rate": 4.823032112754928e-05, "loss": 0.49942550659179685, "step": 386950 }, { "epoch": 2.3001705987600385, "grad_norm": 1.252029299736023, "learning_rate": 4.82257940597926e-05, "loss": 0.5322067260742187, "step": 386960 }, { "epoch": 2.3002300408367065, "grad_norm": 1.6699570417404175, "learning_rate": 4.822126728754353e-05, "loss": 0.4847043514251709, "step": 386970 }, { "epoch": 2.300289482913375, "grad_norm": 1.2259244918823242, "learning_rate": 4.821674081082374e-05, "loss": 0.518235731124878, "step": 386980 }, { "epoch": 2.3003489249900433, "grad_norm": 1.538956880569458, "learning_rate": 4.8212214629654854e-05, "loss": 0.49420366287231443, "step": 386990 }, { "epoch": 2.3004083670667117, "grad_norm": 1.4093985557556152, "learning_rate": 4.8207688744058525e-05, "loss": 0.43790740966796876, "step": 387000 }, { "epoch": 2.30046780914338, "grad_norm": 1.326237678527832, "learning_rate": 4.820316315405644e-05, "loss": 0.48700656890869143, "step": 387010 }, { "epoch": 2.3005272512200485, "grad_norm": 1.2452366352081299, "learning_rate": 4.8198637859670236e-05, "loss": 0.43135852813720704, "step": 387020 }, { "epoch": 2.300586693296717, "grad_norm": 1.5732548236846924, "learning_rate": 4.819411286092155e-05, "loss": 0.4977607727050781, "step": 387030 }, { "epoch": 2.3006461353733854, "grad_norm": 1.8745288848876953, "learning_rate": 4.8189588157832024e-05, "loss": 0.5212128639221192, "step": 387040 }, { "epoch": 2.3007055774500538, "grad_norm": 1.4069103002548218, "learning_rate": 4.818506375042331e-05, "loss": 0.5533621788024903, "step": 387050 }, { "epoch": 2.300765019526722, "grad_norm": 1.2691730260849, "learning_rate": 4.818053963871705e-05, "loss": 0.4813492774963379, "step": 387060 }, { "epoch": 2.3008244616033906, "grad_norm": 1.3998124599456787, "learning_rate": 4.817601582273485e-05, "loss": 0.5407202243804932, "step": 387070 }, { "epoch": 2.300883903680059, "grad_norm": 1.320691466331482, "learning_rate": 4.817149230249842e-05, "loss": 0.4482592582702637, "step": 387080 }, { "epoch": 2.3009433457567274, "grad_norm": 1.4770219326019287, "learning_rate": 4.816696907802937e-05, "loss": 0.4803332328796387, "step": 387090 }, { "epoch": 2.301002787833396, "grad_norm": 1.4311292171478271, "learning_rate": 4.8162446149349334e-05, "loss": 0.4961682319641113, "step": 387100 }, { "epoch": 2.3010622299100643, "grad_norm": 1.0300458669662476, "learning_rate": 4.815792351647994e-05, "loss": 0.5043430805206299, "step": 387110 }, { "epoch": 2.3011216719867327, "grad_norm": 1.3166491985321045, "learning_rate": 4.815340117944283e-05, "loss": 0.4803779602050781, "step": 387120 }, { "epoch": 2.301181114063401, "grad_norm": 1.4340298175811768, "learning_rate": 4.814887913825961e-05, "loss": 0.5231595993041992, "step": 387130 }, { "epoch": 2.301240556140069, "grad_norm": 1.0945844650268555, "learning_rate": 4.814435739295196e-05, "loss": 0.47934913635253906, "step": 387140 }, { "epoch": 2.301299998216738, "grad_norm": 1.4559983015060425, "learning_rate": 4.813983594354151e-05, "loss": 0.48597049713134766, "step": 387150 }, { "epoch": 2.301359440293406, "grad_norm": 1.6163121461868286, "learning_rate": 4.813531479004988e-05, "loss": 0.4955131530761719, "step": 387160 }, { "epoch": 2.3014188823700743, "grad_norm": 1.095403790473938, "learning_rate": 4.813079393249863e-05, "loss": 0.48996744155883787, "step": 387170 }, { "epoch": 2.3014783244467427, "grad_norm": 1.4258548021316528, "learning_rate": 4.812627337090948e-05, "loss": 0.5306488513946533, "step": 387180 }, { "epoch": 2.301537766523411, "grad_norm": 1.2122894525527954, "learning_rate": 4.8121753105304005e-05, "loss": 0.4800978183746338, "step": 387190 }, { "epoch": 2.3015972086000795, "grad_norm": 1.0581986904144287, "learning_rate": 4.8117233135703824e-05, "loss": 0.47933454513549806, "step": 387200 }, { "epoch": 2.301656650676748, "grad_norm": 0.9930753111839294, "learning_rate": 4.8112713462130605e-05, "loss": 0.46357574462890627, "step": 387210 }, { "epoch": 2.3017160927534164, "grad_norm": 1.2549972534179688, "learning_rate": 4.810819408460596e-05, "loss": 0.5416078567504883, "step": 387220 }, { "epoch": 2.301775534830085, "grad_norm": 1.5780166387557983, "learning_rate": 4.810367500315143e-05, "loss": 0.48287081718444824, "step": 387230 }, { "epoch": 2.301834976906753, "grad_norm": 1.6137462854385376, "learning_rate": 4.809915621778873e-05, "loss": 0.46268930435180666, "step": 387240 }, { "epoch": 2.3018944189834216, "grad_norm": 1.7736822366714478, "learning_rate": 4.8094637728539435e-05, "loss": 0.5158318996429443, "step": 387250 }, { "epoch": 2.30195386106009, "grad_norm": 1.1038645505905151, "learning_rate": 4.8090119535425166e-05, "loss": 0.43926315307617186, "step": 387260 }, { "epoch": 2.3020133031367584, "grad_norm": 1.2054795026779175, "learning_rate": 4.8085601638467485e-05, "loss": 0.46795654296875, "step": 387270 }, { "epoch": 2.302072745213427, "grad_norm": 1.403393268585205, "learning_rate": 4.808108403768812e-05, "loss": 0.4783721923828125, "step": 387280 }, { "epoch": 2.3021321872900953, "grad_norm": 1.3931530714035034, "learning_rate": 4.8076566733108595e-05, "loss": 0.5061286926269531, "step": 387290 }, { "epoch": 2.3021916293667637, "grad_norm": 1.5066492557525635, "learning_rate": 4.8072049724750504e-05, "loss": 0.5053487777709961, "step": 387300 }, { "epoch": 2.302251071443432, "grad_norm": 1.2423142194747925, "learning_rate": 4.806753301263551e-05, "loss": 0.5228917598724365, "step": 387310 }, { "epoch": 2.3023105135201005, "grad_norm": 1.2546135187149048, "learning_rate": 4.80630165967852e-05, "loss": 0.4843276500701904, "step": 387320 }, { "epoch": 2.3023699555967685, "grad_norm": 0.9996050596237183, "learning_rate": 4.8058500477221155e-05, "loss": 0.4855800151824951, "step": 387330 }, { "epoch": 2.3024293976734374, "grad_norm": 1.082934021949768, "learning_rate": 4.8053984653965055e-05, "loss": 0.5483391284942627, "step": 387340 }, { "epoch": 2.3024888397501053, "grad_norm": 1.7005395889282227, "learning_rate": 4.804946912703842e-05, "loss": 0.5058123588562011, "step": 387350 }, { "epoch": 2.3025482818267737, "grad_norm": 1.4502463340759277, "learning_rate": 4.804495389646285e-05, "loss": 0.49406728744506834, "step": 387360 }, { "epoch": 2.302607723903442, "grad_norm": 1.2504907846450806, "learning_rate": 4.804043896226e-05, "loss": 0.4689678192138672, "step": 387370 }, { "epoch": 2.3026671659801106, "grad_norm": 1.7968597412109375, "learning_rate": 4.803592432445144e-05, "loss": 0.5071735382080078, "step": 387380 }, { "epoch": 2.302726608056779, "grad_norm": 1.6076973676681519, "learning_rate": 4.8031409983058775e-05, "loss": 0.5442829132080078, "step": 387390 }, { "epoch": 2.3027860501334474, "grad_norm": 1.3235915899276733, "learning_rate": 4.80268959381036e-05, "loss": 0.4981637954711914, "step": 387400 }, { "epoch": 2.302845492210116, "grad_norm": 1.3769696950912476, "learning_rate": 4.802238218960748e-05, "loss": 0.5702601909637451, "step": 387410 }, { "epoch": 2.3029049342867842, "grad_norm": 1.3040868043899536, "learning_rate": 4.801786873759204e-05, "loss": 0.5173569679260254, "step": 387420 }, { "epoch": 2.3029643763634526, "grad_norm": 1.172218680381775, "learning_rate": 4.801335558207883e-05, "loss": 0.5009702682495117, "step": 387430 }, { "epoch": 2.303023818440121, "grad_norm": 1.5152288675308228, "learning_rate": 4.80088427230895e-05, "loss": 0.5385764598846435, "step": 387440 }, { "epoch": 2.3030832605167895, "grad_norm": 1.5207195281982422, "learning_rate": 4.8004330160645605e-05, "loss": 0.5140965461730957, "step": 387450 }, { "epoch": 2.303142702593458, "grad_norm": 1.1265922784805298, "learning_rate": 4.7999817894768736e-05, "loss": 0.47798547744750974, "step": 387460 }, { "epoch": 2.3032021446701263, "grad_norm": 1.6712572574615479, "learning_rate": 4.799530592548048e-05, "loss": 0.5157115936279297, "step": 387470 }, { "epoch": 2.3032615867467947, "grad_norm": 1.391255259513855, "learning_rate": 4.7990794252802416e-05, "loss": 0.4805310249328613, "step": 387480 }, { "epoch": 2.303321028823463, "grad_norm": 1.1922402381896973, "learning_rate": 4.7986282876756095e-05, "loss": 0.5085600852966309, "step": 387490 }, { "epoch": 2.3033804709001315, "grad_norm": 1.1017606258392334, "learning_rate": 4.798177179736316e-05, "loss": 0.4915922164916992, "step": 387500 }, { "epoch": 2.3034399129768, "grad_norm": 1.2391310930252075, "learning_rate": 4.7977261014645165e-05, "loss": 0.523099422454834, "step": 387510 }, { "epoch": 2.303499355053468, "grad_norm": 1.240139126777649, "learning_rate": 4.797275052862367e-05, "loss": 0.4619626045227051, "step": 387520 }, { "epoch": 2.303558797130137, "grad_norm": 1.3008935451507568, "learning_rate": 4.796824033932028e-05, "loss": 0.45304527282714846, "step": 387530 }, { "epoch": 2.3036182392068048, "grad_norm": 1.0957773923873901, "learning_rate": 4.7963730446756556e-05, "loss": 0.49189052581787107, "step": 387540 }, { "epoch": 2.303677681283473, "grad_norm": 1.5046391487121582, "learning_rate": 4.795922085095406e-05, "loss": 0.4617506980895996, "step": 387550 }, { "epoch": 2.3037371233601416, "grad_norm": 1.4231115579605103, "learning_rate": 4.795471155193435e-05, "loss": 0.5034062385559082, "step": 387560 }, { "epoch": 2.30379656543681, "grad_norm": 1.8414281606674194, "learning_rate": 4.795020254971906e-05, "loss": 0.5115679264068603, "step": 387570 }, { "epoch": 2.3038560075134784, "grad_norm": 1.2821617126464844, "learning_rate": 4.7945693844329725e-05, "loss": 0.49272971153259276, "step": 387580 }, { "epoch": 2.303915449590147, "grad_norm": 1.0034767389297485, "learning_rate": 4.7941185435787914e-05, "loss": 0.4947670936584473, "step": 387590 }, { "epoch": 2.3039748916668152, "grad_norm": 1.0144261121749878, "learning_rate": 4.793667732411518e-05, "loss": 0.4797274112701416, "step": 387600 }, { "epoch": 2.3040343337434837, "grad_norm": 1.4354394674301147, "learning_rate": 4.79321695093331e-05, "loss": 0.5054662704467774, "step": 387610 }, { "epoch": 2.304093775820152, "grad_norm": 1.4665030241012573, "learning_rate": 4.7927661991463244e-05, "loss": 0.4696968555450439, "step": 387620 }, { "epoch": 2.3041532178968205, "grad_norm": 1.2826805114746094, "learning_rate": 4.792315477052713e-05, "loss": 0.4382350921630859, "step": 387630 }, { "epoch": 2.304212659973489, "grad_norm": 1.395779013633728, "learning_rate": 4.791864784654639e-05, "loss": 0.4998451232910156, "step": 387640 }, { "epoch": 2.3042721020501573, "grad_norm": 1.5865473747253418, "learning_rate": 4.791414121954255e-05, "loss": 0.5495213508605957, "step": 387650 }, { "epoch": 2.3043315441268257, "grad_norm": 1.6856411695480347, "learning_rate": 4.790963488953717e-05, "loss": 0.46070065498352053, "step": 387660 }, { "epoch": 2.304390986203494, "grad_norm": 1.3868846893310547, "learning_rate": 4.7905128856551815e-05, "loss": 0.5336442470550538, "step": 387670 }, { "epoch": 2.3044504282801626, "grad_norm": 1.373793125152588, "learning_rate": 4.7900623120608015e-05, "loss": 0.50167875289917, "step": 387680 }, { "epoch": 2.304509870356831, "grad_norm": 1.4521008729934692, "learning_rate": 4.7896117681727315e-05, "loss": 0.47729029655456545, "step": 387690 }, { "epoch": 2.3045693124334994, "grad_norm": 1.4726512432098389, "learning_rate": 4.789161253993132e-05, "loss": 0.5549566268920898, "step": 387700 }, { "epoch": 2.3046287545101674, "grad_norm": 1.5706372261047363, "learning_rate": 4.788710769524158e-05, "loss": 0.5212698459625245, "step": 387710 }, { "epoch": 2.3046881965868358, "grad_norm": 1.3459078073501587, "learning_rate": 4.788260314767956e-05, "loss": 0.5076451301574707, "step": 387720 }, { "epoch": 2.304747638663504, "grad_norm": 1.4496456384658813, "learning_rate": 4.78780988972669e-05, "loss": 0.488498592376709, "step": 387730 }, { "epoch": 2.3048070807401726, "grad_norm": 1.155949354171753, "learning_rate": 4.787359494402512e-05, "loss": 0.4425464630126953, "step": 387740 }, { "epoch": 2.304866522816841, "grad_norm": 1.404592752456665, "learning_rate": 4.786909128797575e-05, "loss": 0.466306209564209, "step": 387750 }, { "epoch": 2.3049259648935094, "grad_norm": 1.369107961654663, "learning_rate": 4.7864587929140317e-05, "loss": 0.505579662322998, "step": 387760 }, { "epoch": 2.304985406970178, "grad_norm": 1.2282590866088867, "learning_rate": 4.7860084867540444e-05, "loss": 0.49020042419433596, "step": 387770 }, { "epoch": 2.3050448490468463, "grad_norm": 1.3347853422164917, "learning_rate": 4.785558210319759e-05, "loss": 0.4700034141540527, "step": 387780 }, { "epoch": 2.3051042911235147, "grad_norm": 1.3083240985870361, "learning_rate": 4.785107963613329e-05, "loss": 0.49268083572387694, "step": 387790 }, { "epoch": 2.305163733200183, "grad_norm": 1.1309212446212769, "learning_rate": 4.7846577466369145e-05, "loss": 0.5444048404693603, "step": 387800 }, { "epoch": 2.3052231752768515, "grad_norm": 1.2224431037902832, "learning_rate": 4.784207559392667e-05, "loss": 0.5044004440307617, "step": 387810 }, { "epoch": 2.30528261735352, "grad_norm": 1.2074919939041138, "learning_rate": 4.783757401882736e-05, "loss": 0.4715723514556885, "step": 387820 }, { "epoch": 2.3053420594301883, "grad_norm": 1.319541096687317, "learning_rate": 4.783307274109283e-05, "loss": 0.44620256423950194, "step": 387830 }, { "epoch": 2.3054015015068567, "grad_norm": 1.5484488010406494, "learning_rate": 4.782857176074454e-05, "loss": 0.5079525470733642, "step": 387840 }, { "epoch": 2.305460943583525, "grad_norm": 2.045748233795166, "learning_rate": 4.782407107780401e-05, "loss": 0.5033180713653564, "step": 387850 }, { "epoch": 2.3055203856601936, "grad_norm": 1.3303226232528687, "learning_rate": 4.7819570692292845e-05, "loss": 0.49682464599609377, "step": 387860 }, { "epoch": 2.305579827736862, "grad_norm": 1.496118426322937, "learning_rate": 4.781507060423252e-05, "loss": 0.4900692939758301, "step": 387870 }, { "epoch": 2.30563926981353, "grad_norm": 1.3055429458618164, "learning_rate": 4.781057081364458e-05, "loss": 0.4785026550292969, "step": 387880 }, { "epoch": 2.305698711890199, "grad_norm": 1.1643242835998535, "learning_rate": 4.780607132055055e-05, "loss": 0.4649174690246582, "step": 387890 }, { "epoch": 2.305758153966867, "grad_norm": 0.9318024516105652, "learning_rate": 4.780157212497195e-05, "loss": 0.47884340286254884, "step": 387900 }, { "epoch": 2.305817596043535, "grad_norm": 1.1076569557189941, "learning_rate": 4.7797073226930294e-05, "loss": 0.47806663513183595, "step": 387910 }, { "epoch": 2.3058770381202036, "grad_norm": 1.3469289541244507, "learning_rate": 4.77925746264471e-05, "loss": 0.49117727279663087, "step": 387920 }, { "epoch": 2.305936480196872, "grad_norm": 1.226500153541565, "learning_rate": 4.778807632354391e-05, "loss": 0.4900386333465576, "step": 387930 }, { "epoch": 2.3059959222735404, "grad_norm": 1.3142367601394653, "learning_rate": 4.778357831824224e-05, "loss": 0.5000144004821777, "step": 387940 }, { "epoch": 2.306055364350209, "grad_norm": 1.3184523582458496, "learning_rate": 4.777908061056359e-05, "loss": 0.47275447845458984, "step": 387950 }, { "epoch": 2.3061148064268773, "grad_norm": 1.5620033740997314, "learning_rate": 4.7774583200529496e-05, "loss": 0.42465386390686033, "step": 387960 }, { "epoch": 2.3061742485035457, "grad_norm": 1.5389100313186646, "learning_rate": 4.777008608816146e-05, "loss": 0.534060001373291, "step": 387970 }, { "epoch": 2.306233690580214, "grad_norm": 1.4832382202148438, "learning_rate": 4.776558927348096e-05, "loss": 0.4586495876312256, "step": 387980 }, { "epoch": 2.3062931326568825, "grad_norm": 1.1703540086746216, "learning_rate": 4.776109275650957e-05, "loss": 0.484445858001709, "step": 387990 }, { "epoch": 2.306352574733551, "grad_norm": 1.5599418878555298, "learning_rate": 4.7756596537268775e-05, "loss": 0.520236873626709, "step": 388000 }, { "epoch": 2.3064120168102193, "grad_norm": 1.2322113513946533, "learning_rate": 4.775210061578008e-05, "loss": 0.4463484764099121, "step": 388010 }, { "epoch": 2.3064714588868878, "grad_norm": 1.338610291481018, "learning_rate": 4.774760499206499e-05, "loss": 0.45377097129821775, "step": 388020 }, { "epoch": 2.306530900963556, "grad_norm": 1.5235551595687866, "learning_rate": 4.774310966614503e-05, "loss": 0.510092830657959, "step": 388030 }, { "epoch": 2.3065903430402246, "grad_norm": 1.1043033599853516, "learning_rate": 4.7738614638041664e-05, "loss": 0.45378265380859373, "step": 388040 }, { "epoch": 2.306649785116893, "grad_norm": 1.765886902809143, "learning_rate": 4.773411990777641e-05, "loss": 0.5421856880187989, "step": 388050 }, { "epoch": 2.3067092271935614, "grad_norm": 1.3804913759231567, "learning_rate": 4.7729625475370793e-05, "loss": 0.4471400260925293, "step": 388060 }, { "epoch": 2.3067686692702294, "grad_norm": 1.3939021825790405, "learning_rate": 4.77251313408463e-05, "loss": 0.532269287109375, "step": 388070 }, { "epoch": 2.3068281113468982, "grad_norm": 1.1846065521240234, "learning_rate": 4.772063750422443e-05, "loss": 0.458038330078125, "step": 388080 }, { "epoch": 2.306887553423566, "grad_norm": 1.1347485780715942, "learning_rate": 4.771614396552667e-05, "loss": 0.4583949089050293, "step": 388090 }, { "epoch": 2.3069469955002346, "grad_norm": 1.7450404167175293, "learning_rate": 4.771165072477454e-05, "loss": 0.4852560520172119, "step": 388100 }, { "epoch": 2.307006437576903, "grad_norm": 1.1906989812850952, "learning_rate": 4.7707157781989496e-05, "loss": 0.4642582893371582, "step": 388110 }, { "epoch": 2.3070658796535715, "grad_norm": 1.3946036100387573, "learning_rate": 4.7702665137193036e-05, "loss": 0.49491100311279296, "step": 388120 }, { "epoch": 2.30712532173024, "grad_norm": 1.4333114624023438, "learning_rate": 4.769817279040669e-05, "loss": 0.44893560409545896, "step": 388130 }, { "epoch": 2.3071847638069083, "grad_norm": 1.2092722654342651, "learning_rate": 4.769368074165193e-05, "loss": 0.5308289527893066, "step": 388140 }, { "epoch": 2.3072442058835767, "grad_norm": 1.2526745796203613, "learning_rate": 4.768918899095023e-05, "loss": 0.46646890640258787, "step": 388150 }, { "epoch": 2.307303647960245, "grad_norm": 1.4670466184616089, "learning_rate": 4.7684697538323095e-05, "loss": 0.5482695579528809, "step": 388160 }, { "epoch": 2.3073630900369135, "grad_norm": 1.2251265048980713, "learning_rate": 4.7680206383792005e-05, "loss": 0.4947329044342041, "step": 388170 }, { "epoch": 2.307422532113582, "grad_norm": 1.2816261053085327, "learning_rate": 4.76757155273784e-05, "loss": 0.4890140056610107, "step": 388180 }, { "epoch": 2.3074819741902504, "grad_norm": 1.2573001384735107, "learning_rate": 4.767122496910384e-05, "loss": 0.4937178611755371, "step": 388190 }, { "epoch": 2.3075414162669188, "grad_norm": 1.1032302379608154, "learning_rate": 4.7666734708989774e-05, "loss": 0.44516544342041015, "step": 388200 }, { "epoch": 2.307600858343587, "grad_norm": 1.4610679149627686, "learning_rate": 4.7662244747057675e-05, "loss": 0.5015244960784913, "step": 388210 }, { "epoch": 2.3076603004202556, "grad_norm": 1.2826642990112305, "learning_rate": 4.765775508332903e-05, "loss": 0.4622159004211426, "step": 388220 }, { "epoch": 2.307719742496924, "grad_norm": 1.1231729984283447, "learning_rate": 4.76532657178253e-05, "loss": 0.5306770324707031, "step": 388230 }, { "epoch": 2.3077791845735924, "grad_norm": 1.3483080863952637, "learning_rate": 4.764877665056798e-05, "loss": 0.45364532470703123, "step": 388240 }, { "epoch": 2.307838626650261, "grad_norm": 1.5258057117462158, "learning_rate": 4.764428788157851e-05, "loss": 0.5021832466125489, "step": 388250 }, { "epoch": 2.307898068726929, "grad_norm": 1.405218482017517, "learning_rate": 4.763979941087841e-05, "loss": 0.5444892406463623, "step": 388260 }, { "epoch": 2.3079575108035977, "grad_norm": 1.3565737009048462, "learning_rate": 4.763531123848916e-05, "loss": 0.47872748374938967, "step": 388270 }, { "epoch": 2.3080169528802656, "grad_norm": 1.2932813167572021, "learning_rate": 4.7630823364432145e-05, "loss": 0.5541128158569336, "step": 388280 }, { "epoch": 2.308076394956934, "grad_norm": 1.2426828145980835, "learning_rate": 4.7626335788728916e-05, "loss": 0.5145969390869141, "step": 388290 }, { "epoch": 2.3081358370336025, "grad_norm": 1.1411585807800293, "learning_rate": 4.7621848511400916e-05, "loss": 0.48445816040039064, "step": 388300 }, { "epoch": 2.308195279110271, "grad_norm": 1.4602373838424683, "learning_rate": 4.7617361532469565e-05, "loss": 0.5158082008361816, "step": 388310 }, { "epoch": 2.3082547211869393, "grad_norm": 1.7145129442214966, "learning_rate": 4.761287485195644e-05, "loss": 0.47741427421569826, "step": 388320 }, { "epoch": 2.3083141632636077, "grad_norm": 1.5262253284454346, "learning_rate": 4.760838846988291e-05, "loss": 0.4585288047790527, "step": 388330 }, { "epoch": 2.308373605340276, "grad_norm": 1.3038575649261475, "learning_rate": 4.760390238627042e-05, "loss": 0.5052126884460449, "step": 388340 }, { "epoch": 2.3084330474169446, "grad_norm": 1.4124187231063843, "learning_rate": 4.75994166011405e-05, "loss": 0.4739036560058594, "step": 388350 }, { "epoch": 2.308492489493613, "grad_norm": 1.1018990278244019, "learning_rate": 4.759493111451457e-05, "loss": 0.48446035385131836, "step": 388360 }, { "epoch": 2.3085519315702814, "grad_norm": 1.514032244682312, "learning_rate": 4.759044592641411e-05, "loss": 0.5100839138031006, "step": 388370 }, { "epoch": 2.30861137364695, "grad_norm": 1.4247702360153198, "learning_rate": 4.758596103686056e-05, "loss": 0.5067166328430176, "step": 388380 }, { "epoch": 2.308670815723618, "grad_norm": 1.42317795753479, "learning_rate": 4.758147644587537e-05, "loss": 0.49939913749694825, "step": 388390 }, { "epoch": 2.3087302578002866, "grad_norm": 1.5869773626327515, "learning_rate": 4.757699215348e-05, "loss": 0.5246282577514648, "step": 388400 }, { "epoch": 2.308789699876955, "grad_norm": 1.389646291732788, "learning_rate": 4.757250815969587e-05, "loss": 0.5204564094543457, "step": 388410 }, { "epoch": 2.3088491419536235, "grad_norm": 1.3511654138565063, "learning_rate": 4.7568024464544495e-05, "loss": 0.4788069725036621, "step": 388420 }, { "epoch": 2.308908584030292, "grad_norm": 1.696823239326477, "learning_rate": 4.756354106804727e-05, "loss": 0.47437849044799807, "step": 388430 }, { "epoch": 2.3089680261069603, "grad_norm": 1.3280937671661377, "learning_rate": 4.7559057970225676e-05, "loss": 0.4892094135284424, "step": 388440 }, { "epoch": 2.3090274681836283, "grad_norm": 1.7112528085708618, "learning_rate": 4.755457517110114e-05, "loss": 0.5491168022155761, "step": 388450 }, { "epoch": 2.3090869102602967, "grad_norm": 1.398905634880066, "learning_rate": 4.75500926706951e-05, "loss": 0.5088651657104493, "step": 388460 }, { "epoch": 2.309146352336965, "grad_norm": 1.4489269256591797, "learning_rate": 4.754561046902902e-05, "loss": 0.5054607391357422, "step": 388470 }, { "epoch": 2.3092057944136335, "grad_norm": 1.789307951927185, "learning_rate": 4.754112856612429e-05, "loss": 0.5590826034545898, "step": 388480 }, { "epoch": 2.309265236490302, "grad_norm": 1.299446940422058, "learning_rate": 4.753664696200244e-05, "loss": 0.46177167892456056, "step": 388490 }, { "epoch": 2.3093246785669703, "grad_norm": 1.316120982170105, "learning_rate": 4.7532165656684826e-05, "loss": 0.49374828338623045, "step": 388500 }, { "epoch": 2.3093841206436387, "grad_norm": 1.2742565870285034, "learning_rate": 4.752768465019293e-05, "loss": 0.5323532581329345, "step": 388510 }, { "epoch": 2.309443562720307, "grad_norm": 1.8311727046966553, "learning_rate": 4.752320394254818e-05, "loss": 0.4766105651855469, "step": 388520 }, { "epoch": 2.3095030047969756, "grad_norm": 1.2704603672027588, "learning_rate": 4.7518723533772e-05, "loss": 0.49251432418823243, "step": 388530 }, { "epoch": 2.309562446873644, "grad_norm": 1.3062556982040405, "learning_rate": 4.75142434238858e-05, "loss": 0.5050778388977051, "step": 388540 }, { "epoch": 2.3096218889503124, "grad_norm": 1.0965585708618164, "learning_rate": 4.750976361291107e-05, "loss": 0.5168246269226074, "step": 388550 }, { "epoch": 2.309681331026981, "grad_norm": 1.6202811002731323, "learning_rate": 4.750528410086921e-05, "loss": 0.581545639038086, "step": 388560 }, { "epoch": 2.3097407731036492, "grad_norm": 1.5290858745574951, "learning_rate": 4.7500804887781644e-05, "loss": 0.4929662704467773, "step": 388570 }, { "epoch": 2.3098002151803176, "grad_norm": 1.1854157447814941, "learning_rate": 4.74963259736698e-05, "loss": 0.4869236946105957, "step": 388580 }, { "epoch": 2.309859657256986, "grad_norm": 1.0657356977462769, "learning_rate": 4.7491847358555105e-05, "loss": 0.5015133857727051, "step": 388590 }, { "epoch": 2.3099190993336545, "grad_norm": 1.5567657947540283, "learning_rate": 4.748736904245899e-05, "loss": 0.4985808372497559, "step": 388600 }, { "epoch": 2.309978541410323, "grad_norm": 1.229243516921997, "learning_rate": 4.748289102540284e-05, "loss": 0.48294386863708494, "step": 388610 }, { "epoch": 2.310037983486991, "grad_norm": 1.1925163269042969, "learning_rate": 4.747841330740813e-05, "loss": 0.4798755168914795, "step": 388620 }, { "epoch": 2.3100974255636597, "grad_norm": 1.5945465564727783, "learning_rate": 4.747393588849627e-05, "loss": 0.5127475738525391, "step": 388630 }, { "epoch": 2.3101568676403277, "grad_norm": 1.6605429649353027, "learning_rate": 4.746945876868866e-05, "loss": 0.49897308349609376, "step": 388640 }, { "epoch": 2.310216309716996, "grad_norm": 1.1755855083465576, "learning_rate": 4.746498194800674e-05, "loss": 0.4723622798919678, "step": 388650 }, { "epoch": 2.3102757517936645, "grad_norm": 1.2843056917190552, "learning_rate": 4.746050542647189e-05, "loss": 0.5147170066833496, "step": 388660 }, { "epoch": 2.310335193870333, "grad_norm": 1.5932296514511108, "learning_rate": 4.7456029204105525e-05, "loss": 0.44655547142028806, "step": 388670 }, { "epoch": 2.3103946359470013, "grad_norm": 1.2642215490341187, "learning_rate": 4.74515532809291e-05, "loss": 0.49745979309082033, "step": 388680 }, { "epoch": 2.3104540780236698, "grad_norm": 1.3078252077102661, "learning_rate": 4.7447077656964004e-05, "loss": 0.5139459133148193, "step": 388690 }, { "epoch": 2.310513520100338, "grad_norm": 1.3067677021026611, "learning_rate": 4.744260233223165e-05, "loss": 0.5536473274230957, "step": 388700 }, { "epoch": 2.3105729621770066, "grad_norm": 1.5656260251998901, "learning_rate": 4.743812730675344e-05, "loss": 0.4862844467163086, "step": 388710 }, { "epoch": 2.310632404253675, "grad_norm": 1.2975101470947266, "learning_rate": 4.7433652580550786e-05, "loss": 0.476324462890625, "step": 388720 }, { "epoch": 2.3106918463303434, "grad_norm": 1.0407136678695679, "learning_rate": 4.7429178153645085e-05, "loss": 0.470291805267334, "step": 388730 }, { "epoch": 2.310751288407012, "grad_norm": 1.3518365621566772, "learning_rate": 4.742470402605772e-05, "loss": 0.5236886024475098, "step": 388740 }, { "epoch": 2.3108107304836802, "grad_norm": 1.1657078266143799, "learning_rate": 4.742023019781016e-05, "loss": 0.5082552433013916, "step": 388750 }, { "epoch": 2.3108701725603487, "grad_norm": 1.14093017578125, "learning_rate": 4.7415756668923786e-05, "loss": 0.44483160972595215, "step": 388760 }, { "epoch": 2.310929614637017, "grad_norm": 1.3307225704193115, "learning_rate": 4.741128343941993e-05, "loss": 0.4637006759643555, "step": 388770 }, { "epoch": 2.3109890567136855, "grad_norm": 1.4115182161331177, "learning_rate": 4.740681050932006e-05, "loss": 0.5599532127380371, "step": 388780 }, { "epoch": 2.311048498790354, "grad_norm": 1.4396672248840332, "learning_rate": 4.740233787864556e-05, "loss": 0.47906064987182617, "step": 388790 }, { "epoch": 2.3111079408670223, "grad_norm": 1.6764723062515259, "learning_rate": 4.739786554741778e-05, "loss": 0.5104726791381836, "step": 388800 }, { "epoch": 2.3111673829436903, "grad_norm": 1.200627088546753, "learning_rate": 4.739339351565819e-05, "loss": 0.4851863861083984, "step": 388810 }, { "epoch": 2.311226825020359, "grad_norm": 1.1510114669799805, "learning_rate": 4.7388921783388166e-05, "loss": 0.4601305961608887, "step": 388820 }, { "epoch": 2.311286267097027, "grad_norm": 1.473217487335205, "learning_rate": 4.738445035062902e-05, "loss": 0.5184750556945801, "step": 388830 }, { "epoch": 2.3113457091736955, "grad_norm": 1.3496155738830566, "learning_rate": 4.737997921740224e-05, "loss": 0.4943958282470703, "step": 388840 }, { "epoch": 2.311405151250364, "grad_norm": 1.214726209640503, "learning_rate": 4.737550838372917e-05, "loss": 0.48154706954956056, "step": 388850 }, { "epoch": 2.3114645933270324, "grad_norm": 1.3126795291900635, "learning_rate": 4.73710378496312e-05, "loss": 0.5379196166992187, "step": 388860 }, { "epoch": 2.3115240354037008, "grad_norm": 1.397519826889038, "learning_rate": 4.7366567615129697e-05, "loss": 0.5019056320190429, "step": 388870 }, { "epoch": 2.311583477480369, "grad_norm": 1.2211509943008423, "learning_rate": 4.736209768024611e-05, "loss": 0.5134324073791504, "step": 388880 }, { "epoch": 2.3116429195570376, "grad_norm": 1.3210970163345337, "learning_rate": 4.735762804500176e-05, "loss": 0.5161223411560059, "step": 388890 }, { "epoch": 2.311702361633706, "grad_norm": 1.247090458869934, "learning_rate": 4.735315870941801e-05, "loss": 0.5109829425811767, "step": 388900 }, { "epoch": 2.3117618037103744, "grad_norm": 1.5491902828216553, "learning_rate": 4.73486896735163e-05, "loss": 0.5127599716186524, "step": 388910 }, { "epoch": 2.311821245787043, "grad_norm": 1.3711462020874023, "learning_rate": 4.734422093731801e-05, "loss": 0.49649934768676757, "step": 388920 }, { "epoch": 2.3118806878637113, "grad_norm": 1.3180886507034302, "learning_rate": 4.7339752500844435e-05, "loss": 0.5097599029541016, "step": 388930 }, { "epoch": 2.3119401299403797, "grad_norm": 1.289995551109314, "learning_rate": 4.7335284364117065e-05, "loss": 0.5084968566894531, "step": 388940 }, { "epoch": 2.311999572017048, "grad_norm": 1.2699857950210571, "learning_rate": 4.7330816527157204e-05, "loss": 0.41491289138793946, "step": 388950 }, { "epoch": 2.3120590140937165, "grad_norm": 1.3168818950653076, "learning_rate": 4.732634898998622e-05, "loss": 0.5049198150634766, "step": 388960 }, { "epoch": 2.312118456170385, "grad_norm": 1.239776849746704, "learning_rate": 4.732188175262548e-05, "loss": 0.43875913619995116, "step": 388970 }, { "epoch": 2.3121778982470533, "grad_norm": 1.3552948236465454, "learning_rate": 4.73174148150964e-05, "loss": 0.4453581809997559, "step": 388980 }, { "epoch": 2.3122373403237217, "grad_norm": 1.5333595275878906, "learning_rate": 4.7312948177420324e-05, "loss": 0.44931964874267577, "step": 388990 }, { "epoch": 2.3122967824003897, "grad_norm": 1.3349876403808594, "learning_rate": 4.730848183961862e-05, "loss": 0.5323260307312012, "step": 389000 }, { "epoch": 2.3123562244770586, "grad_norm": 1.4489115476608276, "learning_rate": 4.730401580171265e-05, "loss": 0.5089052200317383, "step": 389010 }, { "epoch": 2.3124156665537265, "grad_norm": 1.4932705163955688, "learning_rate": 4.729955006372378e-05, "loss": 0.5117781639099122, "step": 389020 }, { "epoch": 2.312475108630395, "grad_norm": 1.3194160461425781, "learning_rate": 4.729508462567333e-05, "loss": 0.5030829429626464, "step": 389030 }, { "epoch": 2.3125345507070634, "grad_norm": 1.539101481437683, "learning_rate": 4.729061948758275e-05, "loss": 0.5044055938720703, "step": 389040 }, { "epoch": 2.312593992783732, "grad_norm": 1.391409993171692, "learning_rate": 4.728615464947334e-05, "loss": 0.5157369136810303, "step": 389050 }, { "epoch": 2.3126534348604, "grad_norm": 1.5177773237228394, "learning_rate": 4.728169011136647e-05, "loss": 0.5150054931640625, "step": 389060 }, { "epoch": 2.3127128769370686, "grad_norm": 1.4583383798599243, "learning_rate": 4.727722587328351e-05, "loss": 0.5198862075805664, "step": 389070 }, { "epoch": 2.312772319013737, "grad_norm": 1.2138605117797852, "learning_rate": 4.72727619352458e-05, "loss": 0.4975555896759033, "step": 389080 }, { "epoch": 2.3128317610904054, "grad_norm": 1.3561561107635498, "learning_rate": 4.72682982972747e-05, "loss": 0.46813039779663085, "step": 389090 }, { "epoch": 2.312891203167074, "grad_norm": 1.1532790660858154, "learning_rate": 4.7263834959391515e-05, "loss": 0.5115603446960449, "step": 389100 }, { "epoch": 2.3129506452437423, "grad_norm": 1.006757140159607, "learning_rate": 4.725937192161768e-05, "loss": 0.43836655616760256, "step": 389110 }, { "epoch": 2.3130100873204107, "grad_norm": 1.674513816833496, "learning_rate": 4.725490918397451e-05, "loss": 0.5100915908813477, "step": 389120 }, { "epoch": 2.313069529397079, "grad_norm": 1.632430076599121, "learning_rate": 4.725044674648334e-05, "loss": 0.5034220695495606, "step": 389130 }, { "epoch": 2.3131289714737475, "grad_norm": 1.2524176836013794, "learning_rate": 4.7245984609165534e-05, "loss": 0.5035640239715576, "step": 389140 }, { "epoch": 2.313188413550416, "grad_norm": 0.8415185809135437, "learning_rate": 4.7241522772042435e-05, "loss": 0.5245570182800293, "step": 389150 }, { "epoch": 2.3132478556270843, "grad_norm": 0.9425079822540283, "learning_rate": 4.7237061235135345e-05, "loss": 0.4973623275756836, "step": 389160 }, { "epoch": 2.3133072977037528, "grad_norm": 1.3694394826889038, "learning_rate": 4.723259999846567e-05, "loss": 0.45047931671142577, "step": 389170 }, { "epoch": 2.313366739780421, "grad_norm": 1.565497636795044, "learning_rate": 4.722813906205473e-05, "loss": 0.5062851428985595, "step": 389180 }, { "epoch": 2.313426181857089, "grad_norm": 1.348291277885437, "learning_rate": 4.722367842592385e-05, "loss": 0.5102849483489991, "step": 389190 }, { "epoch": 2.3134856239337576, "grad_norm": 1.4113800525665283, "learning_rate": 4.721921809009438e-05, "loss": 0.507679557800293, "step": 389200 }, { "epoch": 2.313545066010426, "grad_norm": 1.5636656284332275, "learning_rate": 4.7214758054587654e-05, "loss": 0.46329708099365235, "step": 389210 }, { "epoch": 2.3136045080870944, "grad_norm": 1.2218331098556519, "learning_rate": 4.721029831942501e-05, "loss": 0.4996007442474365, "step": 389220 }, { "epoch": 2.313663950163763, "grad_norm": 1.474419355392456, "learning_rate": 4.7205838884627744e-05, "loss": 0.5617411613464356, "step": 389230 }, { "epoch": 2.313723392240431, "grad_norm": 1.232932448387146, "learning_rate": 4.720137975021726e-05, "loss": 0.4457968235015869, "step": 389240 }, { "epoch": 2.3137828343170996, "grad_norm": 1.1423157453536987, "learning_rate": 4.719692091621487e-05, "loss": 0.488297176361084, "step": 389250 }, { "epoch": 2.313842276393768, "grad_norm": 1.4051072597503662, "learning_rate": 4.7192462382641844e-05, "loss": 0.47181406021118166, "step": 389260 }, { "epoch": 2.3139017184704365, "grad_norm": 1.287891149520874, "learning_rate": 4.718800414951957e-05, "loss": 0.5399278163909912, "step": 389270 }, { "epoch": 2.313961160547105, "grad_norm": 1.294805884361267, "learning_rate": 4.718354621686935e-05, "loss": 0.5140261650085449, "step": 389280 }, { "epoch": 2.3140206026237733, "grad_norm": 1.3085442781448364, "learning_rate": 4.7179088584712506e-05, "loss": 0.4980312824249268, "step": 389290 }, { "epoch": 2.3140800447004417, "grad_norm": 1.6133809089660645, "learning_rate": 4.7174631253070384e-05, "loss": 0.5451818466186523, "step": 389300 }, { "epoch": 2.31413948677711, "grad_norm": 1.3666309118270874, "learning_rate": 4.717017422196433e-05, "loss": 0.536153507232666, "step": 389310 }, { "epoch": 2.3141989288537785, "grad_norm": 1.2228784561157227, "learning_rate": 4.716571749141558e-05, "loss": 0.4833521366119385, "step": 389320 }, { "epoch": 2.314258370930447, "grad_norm": 1.5168436765670776, "learning_rate": 4.716126106144553e-05, "loss": 0.5099630355834961, "step": 389330 }, { "epoch": 2.3143178130071154, "grad_norm": 1.014416217803955, "learning_rate": 4.715680493207547e-05, "loss": 0.49770393371582033, "step": 389340 }, { "epoch": 2.314377255083784, "grad_norm": 1.7106938362121582, "learning_rate": 4.71523491033267e-05, "loss": 0.45884056091308595, "step": 389350 }, { "epoch": 2.3144366971604518, "grad_norm": 1.471298336982727, "learning_rate": 4.714789357522054e-05, "loss": 0.5056954383850097, "step": 389360 }, { "epoch": 2.3144961392371206, "grad_norm": 1.3418197631835938, "learning_rate": 4.7143438347778376e-05, "loss": 0.46861581802368163, "step": 389370 }, { "epoch": 2.3145555813137886, "grad_norm": 1.2592732906341553, "learning_rate": 4.713898342102143e-05, "loss": 0.47292795181274416, "step": 389380 }, { "epoch": 2.314615023390457, "grad_norm": 0.9397314190864563, "learning_rate": 4.713452879497102e-05, "loss": 0.47660102844238283, "step": 389390 }, { "epoch": 2.3146744654671254, "grad_norm": 1.5578091144561768, "learning_rate": 4.71300744696485e-05, "loss": 0.45906691551208495, "step": 389400 }, { "epoch": 2.314733907543794, "grad_norm": 1.232983112335205, "learning_rate": 4.712562044507515e-05, "loss": 0.524258041381836, "step": 389410 }, { "epoch": 2.3147933496204622, "grad_norm": 1.5363357067108154, "learning_rate": 4.712116672127227e-05, "loss": 0.5169559001922608, "step": 389420 }, { "epoch": 2.3148527916971307, "grad_norm": 1.4487210512161255, "learning_rate": 4.711671329826123e-05, "loss": 0.5245123386383057, "step": 389430 }, { "epoch": 2.314912233773799, "grad_norm": 1.3699480295181274, "learning_rate": 4.711226017606327e-05, "loss": 0.4922518253326416, "step": 389440 }, { "epoch": 2.3149716758504675, "grad_norm": 1.02055823802948, "learning_rate": 4.7107807354699684e-05, "loss": 0.4722156524658203, "step": 389450 }, { "epoch": 2.315031117927136, "grad_norm": 1.3413643836975098, "learning_rate": 4.710335483419177e-05, "loss": 0.43822102546691893, "step": 389460 }, { "epoch": 2.3150905600038043, "grad_norm": 1.4144043922424316, "learning_rate": 4.709890261456089e-05, "loss": 0.4785576343536377, "step": 389470 }, { "epoch": 2.3151500020804727, "grad_norm": 1.406082272529602, "learning_rate": 4.709445069582829e-05, "loss": 0.4925394058227539, "step": 389480 }, { "epoch": 2.315209444157141, "grad_norm": 1.036768913269043, "learning_rate": 4.70899990780153e-05, "loss": 0.4580497741699219, "step": 389490 }, { "epoch": 2.3152688862338096, "grad_norm": 1.8137398958206177, "learning_rate": 4.708554776114318e-05, "loss": 0.5542707443237305, "step": 389500 }, { "epoch": 2.315328328310478, "grad_norm": 1.2544851303100586, "learning_rate": 4.708109674523324e-05, "loss": 0.4759983539581299, "step": 389510 }, { "epoch": 2.3153877703871464, "grad_norm": 1.4555435180664062, "learning_rate": 4.7076646030306746e-05, "loss": 0.49234676361083984, "step": 389520 }, { "epoch": 2.315447212463815, "grad_norm": 1.5622854232788086, "learning_rate": 4.707219561638504e-05, "loss": 0.47062907218933103, "step": 389530 }, { "epoch": 2.315506654540483, "grad_norm": 1.442408800125122, "learning_rate": 4.7067745503489394e-05, "loss": 0.5057294845581055, "step": 389540 }, { "epoch": 2.315566096617151, "grad_norm": 1.1000006198883057, "learning_rate": 4.7063295691641074e-05, "loss": 0.4818121433258057, "step": 389550 }, { "epoch": 2.31562553869382, "grad_norm": 1.387961983680725, "learning_rate": 4.705884618086138e-05, "loss": 0.5395411014556885, "step": 389560 }, { "epoch": 2.315684980770488, "grad_norm": 1.5076431035995483, "learning_rate": 4.7054396971171606e-05, "loss": 0.4862508296966553, "step": 389570 }, { "epoch": 2.3157444228471564, "grad_norm": 1.3355571031570435, "learning_rate": 4.704994806259302e-05, "loss": 0.49195380210876466, "step": 389580 }, { "epoch": 2.315803864923825, "grad_norm": 1.4442121982574463, "learning_rate": 4.7045499455146886e-05, "loss": 0.4733761787414551, "step": 389590 }, { "epoch": 2.3158633070004933, "grad_norm": 1.3394920825958252, "learning_rate": 4.704105114885453e-05, "loss": 0.4900372505187988, "step": 389600 }, { "epoch": 2.3159227490771617, "grad_norm": 1.1580382585525513, "learning_rate": 4.7036603143737206e-05, "loss": 0.44891972541809083, "step": 389610 }, { "epoch": 2.31598219115383, "grad_norm": 1.4203085899353027, "learning_rate": 4.7032155439816203e-05, "loss": 0.4927103519439697, "step": 389620 }, { "epoch": 2.3160416332304985, "grad_norm": 1.357926607131958, "learning_rate": 4.7027708037112795e-05, "loss": 0.49795141220092776, "step": 389630 }, { "epoch": 2.316101075307167, "grad_norm": 1.359092116355896, "learning_rate": 4.702326093564825e-05, "loss": 0.45349998474121095, "step": 389640 }, { "epoch": 2.3161605173838353, "grad_norm": 1.230348825454712, "learning_rate": 4.701881413544382e-05, "loss": 0.50386643409729, "step": 389650 }, { "epoch": 2.3162199594605037, "grad_norm": 1.1698402166366577, "learning_rate": 4.7014367636520816e-05, "loss": 0.502256202697754, "step": 389660 }, { "epoch": 2.316279401537172, "grad_norm": 1.5602346658706665, "learning_rate": 4.70099214389005e-05, "loss": 0.48708815574645997, "step": 389670 }, { "epoch": 2.3163388436138406, "grad_norm": 1.1858148574829102, "learning_rate": 4.7005475542604136e-05, "loss": 0.43799219131469724, "step": 389680 }, { "epoch": 2.316398285690509, "grad_norm": 1.6921637058258057, "learning_rate": 4.700102994765299e-05, "loss": 0.5119494438171387, "step": 389690 }, { "epoch": 2.3164577277671774, "grad_norm": 1.3741055727005005, "learning_rate": 4.699658465406833e-05, "loss": 0.5136637687683105, "step": 389700 }, { "epoch": 2.316517169843846, "grad_norm": 1.3445651531219482, "learning_rate": 4.6992139661871416e-05, "loss": 0.5048685073852539, "step": 389710 }, { "epoch": 2.3165766119205142, "grad_norm": 1.3093098402023315, "learning_rate": 4.6987694971083485e-05, "loss": 0.5382734298706054, "step": 389720 }, { "epoch": 2.3166360539971826, "grad_norm": 1.3925541639328003, "learning_rate": 4.6983250581725855e-05, "loss": 0.4759506702423096, "step": 389730 }, { "epoch": 2.3166954960738506, "grad_norm": 1.4088257551193237, "learning_rate": 4.6978806493819796e-05, "loss": 0.541436767578125, "step": 389740 }, { "epoch": 2.3167549381505195, "grad_norm": 1.27256441116333, "learning_rate": 4.697436270738647e-05, "loss": 0.47986583709716796, "step": 389750 }, { "epoch": 2.3168143802271874, "grad_norm": 1.5688432455062866, "learning_rate": 4.696991922244722e-05, "loss": 0.5051528930664062, "step": 389760 }, { "epoch": 2.316873822303856, "grad_norm": 1.0316526889801025, "learning_rate": 4.6965476039023286e-05, "loss": 0.4777503967285156, "step": 389770 }, { "epoch": 2.3169332643805243, "grad_norm": 0.9897937774658203, "learning_rate": 4.6961033157135884e-05, "loss": 0.4277900218963623, "step": 389780 }, { "epoch": 2.3169927064571927, "grad_norm": 1.1323856115341187, "learning_rate": 4.695659057680633e-05, "loss": 0.49313969612121583, "step": 389790 }, { "epoch": 2.317052148533861, "grad_norm": 1.5351991653442383, "learning_rate": 4.6952148298055856e-05, "loss": 0.48457841873168944, "step": 389800 }, { "epoch": 2.3171115906105295, "grad_norm": 1.2772072553634644, "learning_rate": 4.694770632090569e-05, "loss": 0.5056384563446045, "step": 389810 }, { "epoch": 2.317171032687198, "grad_norm": 1.3226855993270874, "learning_rate": 4.694326464537705e-05, "loss": 0.45058307647705076, "step": 389820 }, { "epoch": 2.3172304747638663, "grad_norm": 1.2972297668457031, "learning_rate": 4.693882327149127e-05, "loss": 0.4842409133911133, "step": 389830 }, { "epoch": 2.3172899168405348, "grad_norm": 1.3499276638031006, "learning_rate": 4.6934382199269535e-05, "loss": 0.46801605224609377, "step": 389840 }, { "epoch": 2.317349358917203, "grad_norm": 1.1777691841125488, "learning_rate": 4.6929941428733083e-05, "loss": 0.46413049697875974, "step": 389850 }, { "epoch": 2.3174088009938716, "grad_norm": 1.1638720035552979, "learning_rate": 4.6925500959903235e-05, "loss": 0.513183307647705, "step": 389860 }, { "epoch": 2.31746824307054, "grad_norm": 1.272364854812622, "learning_rate": 4.692106079280115e-05, "loss": 0.4990711688995361, "step": 389870 }, { "epoch": 2.3175276851472084, "grad_norm": 1.2706143856048584, "learning_rate": 4.6916620927448065e-05, "loss": 0.5109572410583496, "step": 389880 }, { "epoch": 2.317587127223877, "grad_norm": 0.9653189778327942, "learning_rate": 4.6912181363865285e-05, "loss": 0.4787459850311279, "step": 389890 }, { "epoch": 2.3176465693005452, "grad_norm": 1.1990853548049927, "learning_rate": 4.690774210207401e-05, "loss": 0.5512449264526367, "step": 389900 }, { "epoch": 2.3177060113772137, "grad_norm": 1.303741455078125, "learning_rate": 4.690330314209545e-05, "loss": 0.5066514492034913, "step": 389910 }, { "epoch": 2.317765453453882, "grad_norm": 1.7436563968658447, "learning_rate": 4.689886448395091e-05, "loss": 0.5293822288513184, "step": 389920 }, { "epoch": 2.31782489553055, "grad_norm": 1.455386996269226, "learning_rate": 4.6894426127661574e-05, "loss": 0.5013723373413086, "step": 389930 }, { "epoch": 2.3178843376072185, "grad_norm": 1.3683793544769287, "learning_rate": 4.688998807324867e-05, "loss": 0.5042413711547852, "step": 389940 }, { "epoch": 2.317943779683887, "grad_norm": 1.3823975324630737, "learning_rate": 4.688555032073341e-05, "loss": 0.5392735958099365, "step": 389950 }, { "epoch": 2.3180032217605553, "grad_norm": 1.547302484512329, "learning_rate": 4.688111287013707e-05, "loss": 0.5340052604675293, "step": 389960 }, { "epoch": 2.3180626638372237, "grad_norm": 0.9977364540100098, "learning_rate": 4.6876675721480875e-05, "loss": 0.4528923034667969, "step": 389970 }, { "epoch": 2.318122105913892, "grad_norm": 1.186911940574646, "learning_rate": 4.687223887478603e-05, "loss": 0.48069000244140625, "step": 389980 }, { "epoch": 2.3181815479905605, "grad_norm": 1.5471343994140625, "learning_rate": 4.6867802330073755e-05, "loss": 0.5267258644104004, "step": 389990 }, { "epoch": 2.318240990067229, "grad_norm": 1.6618077754974365, "learning_rate": 4.686336608736529e-05, "loss": 0.4784651756286621, "step": 390000 }, { "epoch": 2.3183004321438974, "grad_norm": 1.3586254119873047, "learning_rate": 4.685893014668182e-05, "loss": 0.4899118423461914, "step": 390010 }, { "epoch": 2.3183598742205658, "grad_norm": 0.9394367337226868, "learning_rate": 4.685449450804462e-05, "loss": 0.5240151882171631, "step": 390020 }, { "epoch": 2.318419316297234, "grad_norm": 1.2316808700561523, "learning_rate": 4.685005917147488e-05, "loss": 0.4677728652954102, "step": 390030 }, { "epoch": 2.3184787583739026, "grad_norm": 1.147639274597168, "learning_rate": 4.684562413699382e-05, "loss": 0.5113446235656738, "step": 390040 }, { "epoch": 2.318538200450571, "grad_norm": 1.3136812448501587, "learning_rate": 4.6841189404622656e-05, "loss": 0.5676302433013916, "step": 390050 }, { "epoch": 2.3185976425272394, "grad_norm": 1.2912176847457886, "learning_rate": 4.68367549743826e-05, "loss": 0.5770701408386231, "step": 390060 }, { "epoch": 2.318657084603908, "grad_norm": 1.2152957916259766, "learning_rate": 4.683232084629488e-05, "loss": 0.43765974044799805, "step": 390070 }, { "epoch": 2.3187165266805763, "grad_norm": 1.7176944017410278, "learning_rate": 4.682788702038065e-05, "loss": 0.4895498275756836, "step": 390080 }, { "epoch": 2.3187759687572447, "grad_norm": 1.414993405342102, "learning_rate": 4.682345349666119e-05, "loss": 0.5440635681152344, "step": 390090 }, { "epoch": 2.3188354108339126, "grad_norm": 1.5557305812835693, "learning_rate": 4.681902027515769e-05, "loss": 0.512156343460083, "step": 390100 }, { "epoch": 2.3188948529105815, "grad_norm": 1.2815897464752197, "learning_rate": 4.6814587355891344e-05, "loss": 0.4552153587341309, "step": 390110 }, { "epoch": 2.3189542949872495, "grad_norm": 1.3829636573791504, "learning_rate": 4.681015473888337e-05, "loss": 0.5051959991455078, "step": 390120 }, { "epoch": 2.319013737063918, "grad_norm": 1.4078162908554077, "learning_rate": 4.680572242415496e-05, "loss": 0.5299746990203857, "step": 390130 }, { "epoch": 2.3190731791405863, "grad_norm": 1.303463339805603, "learning_rate": 4.680129041172729e-05, "loss": 0.5476672172546386, "step": 390140 }, { "epoch": 2.3191326212172547, "grad_norm": 1.4645931720733643, "learning_rate": 4.679685870162163e-05, "loss": 0.47362771034240725, "step": 390150 }, { "epoch": 2.319192063293923, "grad_norm": 1.736006736755371, "learning_rate": 4.6792427293859145e-05, "loss": 0.5096759796142578, "step": 390160 }, { "epoch": 2.3192515053705915, "grad_norm": 1.6532784700393677, "learning_rate": 4.678799618846101e-05, "loss": 0.5456947326660156, "step": 390170 }, { "epoch": 2.31931094744726, "grad_norm": 1.2812341451644897, "learning_rate": 4.678356538544846e-05, "loss": 0.48055295944213866, "step": 390180 }, { "epoch": 2.3193703895239284, "grad_norm": 1.3532963991165161, "learning_rate": 4.6779134884842676e-05, "loss": 0.49163451194763186, "step": 390190 }, { "epoch": 2.319429831600597, "grad_norm": 1.0455149412155151, "learning_rate": 4.677470468666485e-05, "loss": 0.4831097602844238, "step": 390200 }, { "epoch": 2.319489273677265, "grad_norm": 1.1413078308105469, "learning_rate": 4.6770274790936134e-05, "loss": 0.46805672645568847, "step": 390210 }, { "epoch": 2.3195487157539336, "grad_norm": 1.9430028200149536, "learning_rate": 4.676584519767781e-05, "loss": 0.5003940105438233, "step": 390220 }, { "epoch": 2.319608157830602, "grad_norm": 0.9778146147727966, "learning_rate": 4.676141590691099e-05, "loss": 0.41426401138305663, "step": 390230 }, { "epoch": 2.3196675999072704, "grad_norm": 1.2798752784729004, "learning_rate": 4.675698691865691e-05, "loss": 0.48064279556274414, "step": 390240 }, { "epoch": 2.319727041983939, "grad_norm": 1.282810091972351, "learning_rate": 4.6752558232936726e-05, "loss": 0.48406095504760743, "step": 390250 }, { "epoch": 2.3197864840606073, "grad_norm": 1.4479365348815918, "learning_rate": 4.674812984977164e-05, "loss": 0.4576150894165039, "step": 390260 }, { "epoch": 2.3198459261372757, "grad_norm": 1.3560154438018799, "learning_rate": 4.674370176918279e-05, "loss": 0.5335460662841797, "step": 390270 }, { "epoch": 2.319905368213944, "grad_norm": 1.3970391750335693, "learning_rate": 4.673927399119144e-05, "loss": 0.4677377223968506, "step": 390280 }, { "epoch": 2.319964810290612, "grad_norm": 1.4450676441192627, "learning_rate": 4.673484651581872e-05, "loss": 0.4670106887817383, "step": 390290 }, { "epoch": 2.320024252367281, "grad_norm": 1.3881431818008423, "learning_rate": 4.6730419343085865e-05, "loss": 0.4788824081420898, "step": 390300 }, { "epoch": 2.320083694443949, "grad_norm": 1.2574000358581543, "learning_rate": 4.672599247301393e-05, "loss": 0.5008667469024658, "step": 390310 }, { "epoch": 2.3201431365206173, "grad_norm": 1.2603516578674316, "learning_rate": 4.672156590562421e-05, "loss": 0.47658143043518064, "step": 390320 }, { "epoch": 2.3202025785972857, "grad_norm": 1.75922429561615, "learning_rate": 4.671713964093784e-05, "loss": 0.513304615020752, "step": 390330 }, { "epoch": 2.320262020673954, "grad_norm": 1.554684042930603, "learning_rate": 4.671271367897596e-05, "loss": 0.5371088981628418, "step": 390340 }, { "epoch": 2.3203214627506226, "grad_norm": 1.527463436126709, "learning_rate": 4.670828801975983e-05, "loss": 0.504815673828125, "step": 390350 }, { "epoch": 2.320380904827291, "grad_norm": 1.1556034088134766, "learning_rate": 4.670386266331054e-05, "loss": 0.4807710647583008, "step": 390360 }, { "epoch": 2.3204403469039594, "grad_norm": 1.3617924451828003, "learning_rate": 4.669943760964926e-05, "loss": 0.4700795650482178, "step": 390370 }, { "epoch": 2.320499788980628, "grad_norm": 1.263108730316162, "learning_rate": 4.66950128587972e-05, "loss": 0.49492921829223635, "step": 390380 }, { "epoch": 2.3205592310572962, "grad_norm": 1.7146321535110474, "learning_rate": 4.669058841077552e-05, "loss": 0.49201235771179197, "step": 390390 }, { "epoch": 2.3206186731339646, "grad_norm": 1.2165639400482178, "learning_rate": 4.6686164265605336e-05, "loss": 0.4695903778076172, "step": 390400 }, { "epoch": 2.320678115210633, "grad_norm": 1.222902774810791, "learning_rate": 4.668174042330792e-05, "loss": 0.4807180404663086, "step": 390410 }, { "epoch": 2.3207375572873015, "grad_norm": 1.3803311586380005, "learning_rate": 4.667731688390434e-05, "loss": 0.46786980628967284, "step": 390420 }, { "epoch": 2.32079699936397, "grad_norm": 1.3439021110534668, "learning_rate": 4.6672893647415775e-05, "loss": 0.4468400955200195, "step": 390430 }, { "epoch": 2.3208564414406383, "grad_norm": 1.1529968976974487, "learning_rate": 4.666847071386336e-05, "loss": 0.5060123443603516, "step": 390440 }, { "epoch": 2.3209158835173067, "grad_norm": 1.3317856788635254, "learning_rate": 4.6664048083268316e-05, "loss": 0.552680778503418, "step": 390450 }, { "epoch": 2.320975325593975, "grad_norm": 1.441374659538269, "learning_rate": 4.665962575565177e-05, "loss": 0.4538121700286865, "step": 390460 }, { "epoch": 2.3210347676706435, "grad_norm": 1.2307711839675903, "learning_rate": 4.665520373103487e-05, "loss": 0.49161877632141116, "step": 390470 }, { "epoch": 2.3210942097473115, "grad_norm": 1.4720555543899536, "learning_rate": 4.6650782009438774e-05, "loss": 0.5140995025634766, "step": 390480 }, { "epoch": 2.3211536518239804, "grad_norm": 1.3463788032531738, "learning_rate": 4.664636059088464e-05, "loss": 0.48478035926818847, "step": 390490 }, { "epoch": 2.3212130939006483, "grad_norm": 1.0195645093917847, "learning_rate": 4.6641939475393574e-05, "loss": 0.45961480140686034, "step": 390500 }, { "epoch": 2.3212725359773168, "grad_norm": 1.541998267173767, "learning_rate": 4.6637518662986794e-05, "loss": 0.5091933250427246, "step": 390510 }, { "epoch": 2.321331978053985, "grad_norm": 1.9560011625289917, "learning_rate": 4.6633098153685435e-05, "loss": 0.5161539077758789, "step": 390520 }, { "epoch": 2.3213914201306536, "grad_norm": 1.5480647087097168, "learning_rate": 4.6628677947510604e-05, "loss": 0.5191356658935546, "step": 390530 }, { "epoch": 2.321450862207322, "grad_norm": 1.7061026096343994, "learning_rate": 4.662425804448348e-05, "loss": 0.5066029071807862, "step": 390540 }, { "epoch": 2.3215103042839904, "grad_norm": 1.2125139236450195, "learning_rate": 4.661983844462519e-05, "loss": 0.4607421398162842, "step": 390550 }, { "epoch": 2.321569746360659, "grad_norm": 1.5631166696548462, "learning_rate": 4.661541914795688e-05, "loss": 0.4708101749420166, "step": 390560 }, { "epoch": 2.3216291884373272, "grad_norm": 1.7237251996994019, "learning_rate": 4.6611000154499675e-05, "loss": 0.5278996467590332, "step": 390570 }, { "epoch": 2.3216886305139957, "grad_norm": 1.8967170715332031, "learning_rate": 4.6606581464274733e-05, "loss": 0.4740130424499512, "step": 390580 }, { "epoch": 2.321748072590664, "grad_norm": 1.3436856269836426, "learning_rate": 4.660216307730321e-05, "loss": 0.5078944206237793, "step": 390590 }, { "epoch": 2.3218075146673325, "grad_norm": 1.2662564516067505, "learning_rate": 4.6597744993606215e-05, "loss": 0.5165467262268066, "step": 390600 }, { "epoch": 2.321866956744001, "grad_norm": 1.334271788597107, "learning_rate": 4.659332721320488e-05, "loss": 0.4996494293212891, "step": 390610 }, { "epoch": 2.3219263988206693, "grad_norm": 1.3006302118301392, "learning_rate": 4.658890973612035e-05, "loss": 0.518359375, "step": 390620 }, { "epoch": 2.3219858408973377, "grad_norm": 1.3709309101104736, "learning_rate": 4.658449256237372e-05, "loss": 0.49287004470825196, "step": 390630 }, { "epoch": 2.322045282974006, "grad_norm": 1.709731936454773, "learning_rate": 4.6580075691986185e-05, "loss": 0.49596128463745115, "step": 390640 }, { "epoch": 2.3221047250506746, "grad_norm": 1.2058675289154053, "learning_rate": 4.657565912497885e-05, "loss": 0.4957246780395508, "step": 390650 }, { "epoch": 2.322164167127343, "grad_norm": 1.5144613981246948, "learning_rate": 4.657124286137283e-05, "loss": 0.5443428516387939, "step": 390660 }, { "epoch": 2.322223609204011, "grad_norm": 1.1220473051071167, "learning_rate": 4.656682690118924e-05, "loss": 0.49721899032592776, "step": 390670 }, { "epoch": 2.3222830512806794, "grad_norm": 1.0929827690124512, "learning_rate": 4.656241124444924e-05, "loss": 0.45049662590026857, "step": 390680 }, { "epoch": 2.3223424933573478, "grad_norm": 1.0567625761032104, "learning_rate": 4.655799589117393e-05, "loss": 0.4458774566650391, "step": 390690 }, { "epoch": 2.322401935434016, "grad_norm": 0.9809131026268005, "learning_rate": 4.6553580841384396e-05, "loss": 0.48608713150024413, "step": 390700 }, { "epoch": 2.3224613775106846, "grad_norm": 1.2649673223495483, "learning_rate": 4.654916609510183e-05, "loss": 0.4335624694824219, "step": 390710 }, { "epoch": 2.322520819587353, "grad_norm": 1.1734837293624878, "learning_rate": 4.6544751652347325e-05, "loss": 0.4257508277893066, "step": 390720 }, { "epoch": 2.3225802616640214, "grad_norm": 1.4831147193908691, "learning_rate": 4.6540337513141985e-05, "loss": 0.46605443954467773, "step": 390730 }, { "epoch": 2.32263970374069, "grad_norm": 1.2778637409210205, "learning_rate": 4.653592367750693e-05, "loss": 0.44961118698120117, "step": 390740 }, { "epoch": 2.3226991458173583, "grad_norm": 1.5705138444900513, "learning_rate": 4.653151014546327e-05, "loss": 0.5279327392578125, "step": 390750 }, { "epoch": 2.3227585878940267, "grad_norm": 1.370172381401062, "learning_rate": 4.652709691703211e-05, "loss": 0.4499471187591553, "step": 390760 }, { "epoch": 2.322818029970695, "grad_norm": 1.86936354637146, "learning_rate": 4.6522683992234596e-05, "loss": 0.4942923545837402, "step": 390770 }, { "epoch": 2.3228774720473635, "grad_norm": 1.2452200651168823, "learning_rate": 4.6518271371091814e-05, "loss": 0.45996780395507814, "step": 390780 }, { "epoch": 2.322936914124032, "grad_norm": 1.2876100540161133, "learning_rate": 4.651385905362491e-05, "loss": 0.4998870849609375, "step": 390790 }, { "epoch": 2.3229963562007003, "grad_norm": 0.9732417464256287, "learning_rate": 4.650944703985489e-05, "loss": 0.4808948993682861, "step": 390800 }, { "epoch": 2.3230557982773687, "grad_norm": 1.3368799686431885, "learning_rate": 4.650503532980296e-05, "loss": 0.515553092956543, "step": 390810 }, { "epoch": 2.323115240354037, "grad_norm": 1.7276428937911987, "learning_rate": 4.65006239234902e-05, "loss": 0.5076597690582275, "step": 390820 }, { "epoch": 2.3231746824307056, "grad_norm": 1.15303373336792, "learning_rate": 4.649621282093767e-05, "loss": 0.5052280426025391, "step": 390830 }, { "epoch": 2.3232341245073735, "grad_norm": 1.3169076442718506, "learning_rate": 4.6491802022166534e-05, "loss": 0.4953449249267578, "step": 390840 }, { "epoch": 2.3232935665840424, "grad_norm": 1.4852285385131836, "learning_rate": 4.6487391527197874e-05, "loss": 0.48068714141845703, "step": 390850 }, { "epoch": 2.3233530086607104, "grad_norm": 1.3358783721923828, "learning_rate": 4.6482981336052736e-05, "loss": 0.5074083805084229, "step": 390860 }, { "epoch": 2.323412450737379, "grad_norm": 1.3542964458465576, "learning_rate": 4.647857144875228e-05, "loss": 0.47147631645202637, "step": 390870 }, { "epoch": 2.323471892814047, "grad_norm": 1.2266783714294434, "learning_rate": 4.6474161865317586e-05, "loss": 0.4454976558685303, "step": 390880 }, { "epoch": 2.3235313348907156, "grad_norm": 1.1544208526611328, "learning_rate": 4.646975258576971e-05, "loss": 0.4665684700012207, "step": 390890 }, { "epoch": 2.323590776967384, "grad_norm": 1.4493824243545532, "learning_rate": 4.64653436101298e-05, "loss": 0.48624696731567385, "step": 390900 }, { "epoch": 2.3236502190440524, "grad_norm": 1.3577675819396973, "learning_rate": 4.646093493841896e-05, "loss": 0.5462604522705078, "step": 390910 }, { "epoch": 2.323709661120721, "grad_norm": 1.2688157558441162, "learning_rate": 4.645652657065821e-05, "loss": 0.5050700664520263, "step": 390920 }, { "epoch": 2.3237691031973893, "grad_norm": 1.3423658609390259, "learning_rate": 4.645211850686864e-05, "loss": 0.5054419994354248, "step": 390930 }, { "epoch": 2.3238285452740577, "grad_norm": 1.5849100351333618, "learning_rate": 4.64477107470714e-05, "loss": 0.5165014266967773, "step": 390940 }, { "epoch": 2.323887987350726, "grad_norm": 1.4436535835266113, "learning_rate": 4.6443303291287534e-05, "loss": 0.4829879283905029, "step": 390950 }, { "epoch": 2.3239474294273945, "grad_norm": 1.4694812297821045, "learning_rate": 4.643889613953811e-05, "loss": 0.49239168167114256, "step": 390960 }, { "epoch": 2.324006871504063, "grad_norm": 1.1293314695358276, "learning_rate": 4.6434489291844295e-05, "loss": 0.4759818077087402, "step": 390970 }, { "epoch": 2.3240663135807313, "grad_norm": 1.0104211568832397, "learning_rate": 4.643008274822708e-05, "loss": 0.45829029083251954, "step": 390980 }, { "epoch": 2.3241257556573998, "grad_norm": 0.7988414168357849, "learning_rate": 4.6425676508707544e-05, "loss": 0.4644596576690674, "step": 390990 }, { "epoch": 2.324185197734068, "grad_norm": 1.5780842304229736, "learning_rate": 4.6421270573306824e-05, "loss": 0.5280014991760253, "step": 391000 }, { "epoch": 2.3242446398107366, "grad_norm": 1.2246112823486328, "learning_rate": 4.641686494204597e-05, "loss": 0.5228639602661133, "step": 391010 }, { "epoch": 2.324304081887405, "grad_norm": 1.429275393486023, "learning_rate": 4.641245961494606e-05, "loss": 0.47643437385559084, "step": 391020 }, { "epoch": 2.324363523964073, "grad_norm": 1.7969125509262085, "learning_rate": 4.640805459202816e-05, "loss": 0.488499116897583, "step": 391030 }, { "epoch": 2.324422966040742, "grad_norm": 1.0687096118927002, "learning_rate": 4.640364987331333e-05, "loss": 0.45204830169677734, "step": 391040 }, { "epoch": 2.32448240811741, "grad_norm": 1.2409991025924683, "learning_rate": 4.639924545882267e-05, "loss": 0.5251628875732421, "step": 391050 }, { "epoch": 2.324541850194078, "grad_norm": 1.0784615278244019, "learning_rate": 4.63948413485772e-05, "loss": 0.49031720161437986, "step": 391060 }, { "epoch": 2.3246012922707466, "grad_norm": 1.186280608177185, "learning_rate": 4.6390437542598054e-05, "loss": 0.48399744033813474, "step": 391070 }, { "epoch": 2.324660734347415, "grad_norm": 1.2130061388015747, "learning_rate": 4.638603404090627e-05, "loss": 0.4815534114837646, "step": 391080 }, { "epoch": 2.3247201764240835, "grad_norm": 1.078100562095642, "learning_rate": 4.63816308435229e-05, "loss": 0.49642229080200195, "step": 391090 }, { "epoch": 2.324779618500752, "grad_norm": 1.1555181741714478, "learning_rate": 4.637722795046903e-05, "loss": 0.5113979339599609, "step": 391100 }, { "epoch": 2.3248390605774203, "grad_norm": 1.3896375894546509, "learning_rate": 4.6372825361765704e-05, "loss": 0.502621841430664, "step": 391110 }, { "epoch": 2.3248985026540887, "grad_norm": 1.449749231338501, "learning_rate": 4.6368423077433954e-05, "loss": 0.5426983833312988, "step": 391120 }, { "epoch": 2.324957944730757, "grad_norm": 1.0501269102096558, "learning_rate": 4.636402109749491e-05, "loss": 0.46556243896484373, "step": 391130 }, { "epoch": 2.3250173868074255, "grad_norm": 1.2343850135803223, "learning_rate": 4.635961942196958e-05, "loss": 0.5028334140777588, "step": 391140 }, { "epoch": 2.325076828884094, "grad_norm": 1.4650044441223145, "learning_rate": 4.635521805087905e-05, "loss": 0.5401771545410157, "step": 391150 }, { "epoch": 2.3251362709607624, "grad_norm": 1.2630926370620728, "learning_rate": 4.6350816984244344e-05, "loss": 0.47014541625976564, "step": 391160 }, { "epoch": 2.325195713037431, "grad_norm": 1.4639720916748047, "learning_rate": 4.6346416222086534e-05, "loss": 0.4672991752624512, "step": 391170 }, { "epoch": 2.325255155114099, "grad_norm": 1.3804842233657837, "learning_rate": 4.634201576442667e-05, "loss": 0.5284725189208984, "step": 391180 }, { "epoch": 2.3253145971907676, "grad_norm": 1.0866572856903076, "learning_rate": 4.6337615611285764e-05, "loss": 0.5118003845214844, "step": 391190 }, { "epoch": 2.325374039267436, "grad_norm": 1.2198196649551392, "learning_rate": 4.633321576268493e-05, "loss": 0.491405725479126, "step": 391200 }, { "epoch": 2.3254334813441044, "grad_norm": 1.2685716152191162, "learning_rate": 4.632881621864519e-05, "loss": 0.48521924018859863, "step": 391210 }, { "epoch": 2.3254929234207724, "grad_norm": 2.1315319538116455, "learning_rate": 4.632441697918759e-05, "loss": 0.5089824676513672, "step": 391220 }, { "epoch": 2.3255523654974413, "grad_norm": 1.0872951745986938, "learning_rate": 4.6320018044333155e-05, "loss": 0.5104948997497558, "step": 391230 }, { "epoch": 2.3256118075741092, "grad_norm": 1.2092499732971191, "learning_rate": 4.631561941410295e-05, "loss": 0.5107974052429199, "step": 391240 }, { "epoch": 2.3256712496507776, "grad_norm": 1.3428717851638794, "learning_rate": 4.6311221088517974e-05, "loss": 0.5249882698059082, "step": 391250 }, { "epoch": 2.325730691727446, "grad_norm": 1.6437290906906128, "learning_rate": 4.630682306759934e-05, "loss": 0.5267962455749512, "step": 391260 }, { "epoch": 2.3257901338041145, "grad_norm": 1.447796106338501, "learning_rate": 4.630242535136805e-05, "loss": 0.4512608528137207, "step": 391270 }, { "epoch": 2.325849575880783, "grad_norm": 1.5158036947250366, "learning_rate": 4.629802793984516e-05, "loss": 0.5111739158630371, "step": 391280 }, { "epoch": 2.3259090179574513, "grad_norm": 1.8900983333587646, "learning_rate": 4.629363083305164e-05, "loss": 0.48345203399658204, "step": 391290 }, { "epoch": 2.3259684600341197, "grad_norm": 1.59102463722229, "learning_rate": 4.6289234031008586e-05, "loss": 0.5156570911407471, "step": 391300 }, { "epoch": 2.326027902110788, "grad_norm": 1.3415179252624512, "learning_rate": 4.628483753373703e-05, "loss": 0.4546632766723633, "step": 391310 }, { "epoch": 2.3260873441874566, "grad_norm": 1.2487609386444092, "learning_rate": 4.628044134125796e-05, "loss": 0.4775548934936523, "step": 391320 }, { "epoch": 2.326146786264125, "grad_norm": 1.4085354804992676, "learning_rate": 4.627604545359245e-05, "loss": 0.5234564304351806, "step": 391330 }, { "epoch": 2.3262062283407934, "grad_norm": 1.1754451990127563, "learning_rate": 4.627164987076155e-05, "loss": 0.4685389518737793, "step": 391340 }, { "epoch": 2.326265670417462, "grad_norm": 1.1866785287857056, "learning_rate": 4.6267254592786194e-05, "loss": 0.5080500602722168, "step": 391350 }, { "epoch": 2.32632511249413, "grad_norm": 1.310783863067627, "learning_rate": 4.626285961968749e-05, "loss": 0.4487966537475586, "step": 391360 }, { "epoch": 2.3263845545707986, "grad_norm": 1.308397889137268, "learning_rate": 4.6258464951486434e-05, "loss": 0.5063374519348145, "step": 391370 }, { "epoch": 2.326443996647467, "grad_norm": 0.9799545407295227, "learning_rate": 4.625407058820403e-05, "loss": 0.5049879074096679, "step": 391380 }, { "epoch": 2.3265034387241355, "grad_norm": 1.519874930381775, "learning_rate": 4.624967652986134e-05, "loss": 0.48849334716796877, "step": 391390 }, { "epoch": 2.326562880800804, "grad_norm": 1.683678388595581, "learning_rate": 4.624528277647939e-05, "loss": 0.4979378700256348, "step": 391400 }, { "epoch": 2.326622322877472, "grad_norm": 1.1913167238235474, "learning_rate": 4.6240889328079153e-05, "loss": 0.44089927673339846, "step": 391410 }, { "epoch": 2.3266817649541403, "grad_norm": 1.1663717031478882, "learning_rate": 4.6236496184681635e-05, "loss": 0.4548636436462402, "step": 391420 }, { "epoch": 2.3267412070308087, "grad_norm": 1.1026380062103271, "learning_rate": 4.6232103346307905e-05, "loss": 0.46474289894104004, "step": 391430 }, { "epoch": 2.326800649107477, "grad_norm": 1.4676929712295532, "learning_rate": 4.6227710812978955e-05, "loss": 0.4974799156188965, "step": 391440 }, { "epoch": 2.3268600911841455, "grad_norm": 1.3565735816955566, "learning_rate": 4.622331858471577e-05, "loss": 0.5140082359313964, "step": 391450 }, { "epoch": 2.326919533260814, "grad_norm": 1.300968885421753, "learning_rate": 4.621892666153944e-05, "loss": 0.459743070602417, "step": 391460 }, { "epoch": 2.3269789753374823, "grad_norm": 1.1047980785369873, "learning_rate": 4.621453504347089e-05, "loss": 0.4716205596923828, "step": 391470 }, { "epoch": 2.3270384174141507, "grad_norm": 1.572050929069519, "learning_rate": 4.621014373053114e-05, "loss": 0.4551243782043457, "step": 391480 }, { "epoch": 2.327097859490819, "grad_norm": 1.3595331907272339, "learning_rate": 4.6205752722741236e-05, "loss": 0.4453920841217041, "step": 391490 }, { "epoch": 2.3271573015674876, "grad_norm": 1.2998390197753906, "learning_rate": 4.620136202012216e-05, "loss": 0.5046141624450684, "step": 391500 }, { "epoch": 2.327216743644156, "grad_norm": 1.217922568321228, "learning_rate": 4.6196971622694915e-05, "loss": 0.47967729568481443, "step": 391510 }, { "epoch": 2.3272761857208244, "grad_norm": 1.4179569482803345, "learning_rate": 4.619258153048052e-05, "loss": 0.470395565032959, "step": 391520 }, { "epoch": 2.327335627797493, "grad_norm": 1.2494181394577026, "learning_rate": 4.618819174349996e-05, "loss": 0.46779646873474123, "step": 391530 }, { "epoch": 2.3273950698741612, "grad_norm": 1.8611036539077759, "learning_rate": 4.618380226177423e-05, "loss": 0.5179917335510253, "step": 391540 }, { "epoch": 2.3274545119508296, "grad_norm": 1.1204668283462524, "learning_rate": 4.6179413085324315e-05, "loss": 0.4663426399230957, "step": 391550 }, { "epoch": 2.327513954027498, "grad_norm": 1.1554259061813354, "learning_rate": 4.617502421417125e-05, "loss": 0.4631033420562744, "step": 391560 }, { "epoch": 2.3275733961041665, "grad_norm": 1.4526461362838745, "learning_rate": 4.6170635648336017e-05, "loss": 0.48107166290283204, "step": 391570 }, { "epoch": 2.3276328381808344, "grad_norm": 1.553922414779663, "learning_rate": 4.616624738783961e-05, "loss": 0.4722540855407715, "step": 391580 }, { "epoch": 2.3276922802575033, "grad_norm": 1.0682817697525024, "learning_rate": 4.616185943270299e-05, "loss": 0.5264113426208497, "step": 391590 }, { "epoch": 2.3277517223341713, "grad_norm": 1.3473329544067383, "learning_rate": 4.6157471782947194e-05, "loss": 0.443693733215332, "step": 391600 }, { "epoch": 2.3278111644108397, "grad_norm": 1.3653899431228638, "learning_rate": 4.615308443859315e-05, "loss": 0.4589503288269043, "step": 391610 }, { "epoch": 2.327870606487508, "grad_norm": 1.2557733058929443, "learning_rate": 4.6148697399661924e-05, "loss": 0.4471926212310791, "step": 391620 }, { "epoch": 2.3279300485641765, "grad_norm": 1.2583794593811035, "learning_rate": 4.614431066617445e-05, "loss": 0.4580531120300293, "step": 391630 }, { "epoch": 2.327989490640845, "grad_norm": 1.2499462366104126, "learning_rate": 4.613992423815173e-05, "loss": 0.49971494674682615, "step": 391640 }, { "epoch": 2.3280489327175133, "grad_norm": 1.1249059438705444, "learning_rate": 4.6135538115614755e-05, "loss": 0.44199647903442385, "step": 391650 }, { "epoch": 2.3281083747941818, "grad_norm": 1.4247568845748901, "learning_rate": 4.6131152298584486e-05, "loss": 0.4912728786468506, "step": 391660 }, { "epoch": 2.32816781687085, "grad_norm": 1.3225992918014526, "learning_rate": 4.612676678708191e-05, "loss": 0.49196610450744627, "step": 391670 }, { "epoch": 2.3282272589475186, "grad_norm": 1.3795467615127563, "learning_rate": 4.612238158112798e-05, "loss": 0.48396992683410645, "step": 391680 }, { "epoch": 2.328286701024187, "grad_norm": 1.2435911893844604, "learning_rate": 4.611799668074373e-05, "loss": 0.5191655158996582, "step": 391690 }, { "epoch": 2.3283461431008554, "grad_norm": 1.281943917274475, "learning_rate": 4.61136120859501e-05, "loss": 0.5092003822326661, "step": 391700 }, { "epoch": 2.328405585177524, "grad_norm": 1.302616000175476, "learning_rate": 4.610922779676807e-05, "loss": 0.4623687744140625, "step": 391710 }, { "epoch": 2.3284650272541922, "grad_norm": 1.2732051610946655, "learning_rate": 4.610484381321862e-05, "loss": 0.497437572479248, "step": 391720 }, { "epoch": 2.3285244693308607, "grad_norm": 1.4542080163955688, "learning_rate": 4.610046013532272e-05, "loss": 0.4983816146850586, "step": 391730 }, { "epoch": 2.328583911407529, "grad_norm": 1.2522625923156738, "learning_rate": 4.609607676310131e-05, "loss": 0.4788663864135742, "step": 391740 }, { "epoch": 2.3286433534841975, "grad_norm": 1.433806300163269, "learning_rate": 4.609169369657541e-05, "loss": 0.515885877609253, "step": 391750 }, { "epoch": 2.328702795560866, "grad_norm": 1.280454158782959, "learning_rate": 4.608731093576596e-05, "loss": 0.45727243423461916, "step": 391760 }, { "epoch": 2.328762237637534, "grad_norm": 0.848400890827179, "learning_rate": 4.608292848069396e-05, "loss": 0.4788625240325928, "step": 391770 }, { "epoch": 2.3288216797142027, "grad_norm": 1.071469783782959, "learning_rate": 4.607854633138028e-05, "loss": 0.4528306007385254, "step": 391780 }, { "epoch": 2.3288811217908707, "grad_norm": 1.472182035446167, "learning_rate": 4.607416448784597e-05, "loss": 0.47423553466796875, "step": 391790 }, { "epoch": 2.328940563867539, "grad_norm": 0.944243311882019, "learning_rate": 4.6069782950111966e-05, "loss": 0.43747725486755373, "step": 391800 }, { "epoch": 2.3290000059442075, "grad_norm": 1.94049072265625, "learning_rate": 4.606540171819921e-05, "loss": 0.47687640190124514, "step": 391810 }, { "epoch": 2.329059448020876, "grad_norm": 0.9375802278518677, "learning_rate": 4.60610207921287e-05, "loss": 0.44725589752197265, "step": 391820 }, { "epoch": 2.3291188900975444, "grad_norm": 1.1762076616287231, "learning_rate": 4.60566401719214e-05, "loss": 0.47821292877197263, "step": 391830 }, { "epoch": 2.3291783321742128, "grad_norm": 1.5237866640090942, "learning_rate": 4.6052259857598186e-05, "loss": 0.5053009510040283, "step": 391840 }, { "epoch": 2.329237774250881, "grad_norm": 1.4479634761810303, "learning_rate": 4.604787984918007e-05, "loss": 0.44745216369628904, "step": 391850 }, { "epoch": 2.3292972163275496, "grad_norm": 1.5095648765563965, "learning_rate": 4.604350014668802e-05, "loss": 0.4517975807189941, "step": 391860 }, { "epoch": 2.329356658404218, "grad_norm": 1.3911948204040527, "learning_rate": 4.603912075014292e-05, "loss": 0.5076926231384278, "step": 391870 }, { "epoch": 2.3294161004808864, "grad_norm": 1.157751441001892, "learning_rate": 4.6034741659565806e-05, "loss": 0.5040832996368408, "step": 391880 }, { "epoch": 2.329475542557555, "grad_norm": 1.4307892322540283, "learning_rate": 4.603036287497761e-05, "loss": 0.4995583534240723, "step": 391890 }, { "epoch": 2.3295349846342233, "grad_norm": 1.2230159044265747, "learning_rate": 4.6025984396399214e-05, "loss": 0.49098544120788573, "step": 391900 }, { "epoch": 2.3295944267108917, "grad_norm": 1.4874542951583862, "learning_rate": 4.602160622385157e-05, "loss": 0.5071278572082519, "step": 391910 }, { "epoch": 2.32965386878756, "grad_norm": 1.3349055051803589, "learning_rate": 4.60172283573557e-05, "loss": 0.49578123092651366, "step": 391920 }, { "epoch": 2.3297133108642285, "grad_norm": 1.5339916944503784, "learning_rate": 4.601285079693249e-05, "loss": 0.5074164390563964, "step": 391930 }, { "epoch": 2.329772752940897, "grad_norm": 1.1331217288970947, "learning_rate": 4.6008473542602866e-05, "loss": 0.44804811477661133, "step": 391940 }, { "epoch": 2.3298321950175653, "grad_norm": 2.473323106765747, "learning_rate": 4.600409659438784e-05, "loss": 0.5333184242248535, "step": 391950 }, { "epoch": 2.3298916370942333, "grad_norm": 1.2312719821929932, "learning_rate": 4.599971995230827e-05, "loss": 0.4922788619995117, "step": 391960 }, { "epoch": 2.329951079170902, "grad_norm": 1.273963212966919, "learning_rate": 4.599534361638512e-05, "loss": 0.550822114944458, "step": 391970 }, { "epoch": 2.33001052124757, "grad_norm": 1.3062710762023926, "learning_rate": 4.5990967586639336e-05, "loss": 0.4562201499938965, "step": 391980 }, { "epoch": 2.3300699633242385, "grad_norm": 1.2848231792449951, "learning_rate": 4.598659186309185e-05, "loss": 0.508309268951416, "step": 391990 }, { "epoch": 2.330129405400907, "grad_norm": 1.3413816690444946, "learning_rate": 4.598221644576359e-05, "loss": 0.518583869934082, "step": 392000 }, { "epoch": 2.3301888474775754, "grad_norm": 1.3345168828964233, "learning_rate": 4.597784133467548e-05, "loss": 0.4488933563232422, "step": 392010 }, { "epoch": 2.330248289554244, "grad_norm": 1.4595866203308105, "learning_rate": 4.597346652984846e-05, "loss": 0.5041393280029297, "step": 392020 }, { "epoch": 2.330307731630912, "grad_norm": 1.7445284128189087, "learning_rate": 4.5969092031303456e-05, "loss": 0.4787877082824707, "step": 392030 }, { "epoch": 2.3303671737075806, "grad_norm": 1.84306001663208, "learning_rate": 4.596471783906135e-05, "loss": 0.48927888870239256, "step": 392040 }, { "epoch": 2.330426615784249, "grad_norm": 1.261744499206543, "learning_rate": 4.596034395314315e-05, "loss": 0.4566041946411133, "step": 392050 }, { "epoch": 2.3304860578609174, "grad_norm": 1.324953556060791, "learning_rate": 4.595597037356972e-05, "loss": 0.45120854377746583, "step": 392060 }, { "epoch": 2.330545499937586, "grad_norm": 1.9120850563049316, "learning_rate": 4.5951597100362e-05, "loss": 0.5483311653137207, "step": 392070 }, { "epoch": 2.3306049420142543, "grad_norm": 2.049924612045288, "learning_rate": 4.594722413354092e-05, "loss": 0.5595053672790528, "step": 392080 }, { "epoch": 2.3306643840909227, "grad_norm": 1.3605300188064575, "learning_rate": 4.5942851473127386e-05, "loss": 0.5065283298492431, "step": 392090 }, { "epoch": 2.330723826167591, "grad_norm": 0.9751570224761963, "learning_rate": 4.593847911914229e-05, "loss": 0.46832914352416993, "step": 392100 }, { "epoch": 2.3307832682442595, "grad_norm": 1.5526790618896484, "learning_rate": 4.593410707160659e-05, "loss": 0.4942500114440918, "step": 392110 }, { "epoch": 2.330842710320928, "grad_norm": 2.103562831878662, "learning_rate": 4.5929735330541195e-05, "loss": 0.47486371994018556, "step": 392120 }, { "epoch": 2.3309021523975963, "grad_norm": 1.159430742263794, "learning_rate": 4.5925363895967e-05, "loss": 0.5101994037628174, "step": 392130 }, { "epoch": 2.3309615944742648, "grad_norm": 1.3123202323913574, "learning_rate": 4.592099276790493e-05, "loss": 0.47269439697265625, "step": 392140 }, { "epoch": 2.3310210365509327, "grad_norm": 1.2706843614578247, "learning_rate": 4.591662194637588e-05, "loss": 0.5069474220275879, "step": 392150 }, { "epoch": 2.331080478627601, "grad_norm": 1.24900484085083, "learning_rate": 4.5912251431400775e-05, "loss": 0.5199978828430176, "step": 392160 }, { "epoch": 2.3311399207042696, "grad_norm": 1.1062911748886108, "learning_rate": 4.5907881223000495e-05, "loss": 0.5038390159606934, "step": 392170 }, { "epoch": 2.331199362780938, "grad_norm": 1.3817825317382812, "learning_rate": 4.590351132119598e-05, "loss": 0.5051050186157227, "step": 392180 }, { "epoch": 2.3312588048576064, "grad_norm": 1.1854634284973145, "learning_rate": 4.589914172600813e-05, "loss": 0.4677407264709473, "step": 392190 }, { "epoch": 2.331318246934275, "grad_norm": 1.3844977617263794, "learning_rate": 4.589477243745783e-05, "loss": 0.4892845630645752, "step": 392200 }, { "epoch": 2.331377689010943, "grad_norm": 1.0378493070602417, "learning_rate": 4.5890403455565997e-05, "loss": 0.3925048351287842, "step": 392210 }, { "epoch": 2.3314371310876116, "grad_norm": 1.3332124948501587, "learning_rate": 4.588603478035351e-05, "loss": 0.4916564464569092, "step": 392220 }, { "epoch": 2.33149657316428, "grad_norm": 1.4442626237869263, "learning_rate": 4.588166641184126e-05, "loss": 0.4880228996276855, "step": 392230 }, { "epoch": 2.3315560152409485, "grad_norm": 1.0226941108703613, "learning_rate": 4.58772983500502e-05, "loss": 0.4812270164489746, "step": 392240 }, { "epoch": 2.331615457317617, "grad_norm": 1.1650011539459229, "learning_rate": 4.587293059500118e-05, "loss": 0.47322607040405273, "step": 392250 }, { "epoch": 2.3316748993942853, "grad_norm": 1.3237295150756836, "learning_rate": 4.58685631467151e-05, "loss": 0.5025969505310058, "step": 392260 }, { "epoch": 2.3317343414709537, "grad_norm": 1.0612674951553345, "learning_rate": 4.586419600521286e-05, "loss": 0.530705451965332, "step": 392270 }, { "epoch": 2.331793783547622, "grad_norm": 1.3396358489990234, "learning_rate": 4.5859829170515346e-05, "loss": 0.4984868049621582, "step": 392280 }, { "epoch": 2.3318532256242905, "grad_norm": 1.7759339809417725, "learning_rate": 4.585546264264345e-05, "loss": 0.5431526184082032, "step": 392290 }, { "epoch": 2.331912667700959, "grad_norm": 1.389548897743225, "learning_rate": 4.585109642161802e-05, "loss": 0.45427770614624025, "step": 392300 }, { "epoch": 2.3319721097776274, "grad_norm": 1.441049575805664, "learning_rate": 4.5846730507460025e-05, "loss": 0.4942138671875, "step": 392310 }, { "epoch": 2.3320315518542953, "grad_norm": 1.2339961528778076, "learning_rate": 4.58423649001903e-05, "loss": 0.4868668556213379, "step": 392320 }, { "epoch": 2.332090993930964, "grad_norm": 1.0892256498336792, "learning_rate": 4.5837999599829723e-05, "loss": 0.4769423961639404, "step": 392330 }, { "epoch": 2.332150436007632, "grad_norm": 1.279281497001648, "learning_rate": 4.5833634606399195e-05, "loss": 0.4970771312713623, "step": 392340 }, { "epoch": 2.3322098780843006, "grad_norm": 1.6171029806137085, "learning_rate": 4.58292699199196e-05, "loss": 0.515532398223877, "step": 392350 }, { "epoch": 2.332269320160969, "grad_norm": 1.5326796770095825, "learning_rate": 4.582490554041176e-05, "loss": 0.41225180625915525, "step": 392360 }, { "epoch": 2.3323287622376374, "grad_norm": 1.3827861547470093, "learning_rate": 4.582054146789664e-05, "loss": 0.4670108318328857, "step": 392370 }, { "epoch": 2.332388204314306, "grad_norm": 1.190634846687317, "learning_rate": 4.581617770239507e-05, "loss": 0.5267326354980468, "step": 392380 }, { "epoch": 2.3324476463909742, "grad_norm": 1.331356167793274, "learning_rate": 4.5811814243927964e-05, "loss": 0.44929141998291017, "step": 392390 }, { "epoch": 2.3325070884676427, "grad_norm": 1.3188157081604004, "learning_rate": 4.5807451092516094e-05, "loss": 0.49390034675598143, "step": 392400 }, { "epoch": 2.332566530544311, "grad_norm": 1.4358311891555786, "learning_rate": 4.580308824818044e-05, "loss": 0.4114975929260254, "step": 392410 }, { "epoch": 2.3326259726209795, "grad_norm": 1.4175710678100586, "learning_rate": 4.5798725710941825e-05, "loss": 0.48441143035888673, "step": 392420 }, { "epoch": 2.332685414697648, "grad_norm": 0.9866064786911011, "learning_rate": 4.57943634808211e-05, "loss": 0.4833074569702148, "step": 392430 }, { "epoch": 2.3327448567743163, "grad_norm": 1.4587063789367676, "learning_rate": 4.579000155783921e-05, "loss": 0.468384838104248, "step": 392440 }, { "epoch": 2.3328042988509847, "grad_norm": 1.3713544607162476, "learning_rate": 4.578563994201695e-05, "loss": 0.5571311950683594, "step": 392450 }, { "epoch": 2.332863740927653, "grad_norm": 1.5950486660003662, "learning_rate": 4.578127863337517e-05, "loss": 0.5057556629180908, "step": 392460 }, { "epoch": 2.3329231830043216, "grad_norm": 1.4072051048278809, "learning_rate": 4.577691763193479e-05, "loss": 0.5048332214355469, "step": 392470 }, { "epoch": 2.33298262508099, "grad_norm": 1.5316886901855469, "learning_rate": 4.5772556937716656e-05, "loss": 0.46666631698608396, "step": 392480 }, { "epoch": 2.3330420671576584, "grad_norm": 1.0623540878295898, "learning_rate": 4.576819655074162e-05, "loss": 0.4578911781311035, "step": 392490 }, { "epoch": 2.333101509234327, "grad_norm": 1.7714816331863403, "learning_rate": 4.576383647103053e-05, "loss": 0.4780618190765381, "step": 392500 }, { "epoch": 2.3331609513109948, "grad_norm": 1.3427807092666626, "learning_rate": 4.5759476698604256e-05, "loss": 0.44263172149658203, "step": 392510 }, { "epoch": 2.3332203933876636, "grad_norm": 1.1968361139297485, "learning_rate": 4.575511723348365e-05, "loss": 0.5354499340057373, "step": 392520 }, { "epoch": 2.3332798354643316, "grad_norm": 1.0599005222320557, "learning_rate": 4.5750758075689544e-05, "loss": 0.45550832748413084, "step": 392530 }, { "epoch": 2.333339277541, "grad_norm": 1.5250385999679565, "learning_rate": 4.574639922524284e-05, "loss": 0.4652132034301758, "step": 392540 }, { "epoch": 2.3333987196176684, "grad_norm": 1.1559520959854126, "learning_rate": 4.574204068216437e-05, "loss": 0.42707123756408694, "step": 392550 }, { "epoch": 2.333458161694337, "grad_norm": 1.339674949645996, "learning_rate": 4.573768244647497e-05, "loss": 0.4969362258911133, "step": 392560 }, { "epoch": 2.3335176037710053, "grad_norm": 1.1123403310775757, "learning_rate": 4.5733324518195496e-05, "loss": 0.4618133544921875, "step": 392570 }, { "epoch": 2.3335770458476737, "grad_norm": 1.3442715406417847, "learning_rate": 4.572896689734681e-05, "loss": 0.4977234363555908, "step": 392580 }, { "epoch": 2.333636487924342, "grad_norm": 1.2507754564285278, "learning_rate": 4.57246095839497e-05, "loss": 0.47314791679382323, "step": 392590 }, { "epoch": 2.3336959300010105, "grad_norm": 1.328408122062683, "learning_rate": 4.572025257802508e-05, "loss": 0.534454345703125, "step": 392600 }, { "epoch": 2.333755372077679, "grad_norm": 1.62931489944458, "learning_rate": 4.571589587959376e-05, "loss": 0.4989990234375, "step": 392610 }, { "epoch": 2.3338148141543473, "grad_norm": 1.4447909593582153, "learning_rate": 4.5711539488676595e-05, "loss": 0.45737323760986326, "step": 392620 }, { "epoch": 2.3338742562310157, "grad_norm": 1.4226664304733276, "learning_rate": 4.5707183405294425e-05, "loss": 0.5368914604187012, "step": 392630 }, { "epoch": 2.333933698307684, "grad_norm": 1.2230125665664673, "learning_rate": 4.570282762946806e-05, "loss": 0.49552335739135744, "step": 392640 }, { "epoch": 2.3339931403843526, "grad_norm": 1.173240303993225, "learning_rate": 4.569847216121836e-05, "loss": 0.48785977363586425, "step": 392650 }, { "epoch": 2.334052582461021, "grad_norm": 1.5800666809082031, "learning_rate": 4.5694117000566136e-05, "loss": 0.5106900215148926, "step": 392660 }, { "epoch": 2.3341120245376894, "grad_norm": 1.2133420705795288, "learning_rate": 4.5689762147532255e-05, "loss": 0.526416826248169, "step": 392670 }, { "epoch": 2.334171466614358, "grad_norm": 1.6145849227905273, "learning_rate": 4.568540760213755e-05, "loss": 0.5216457366943359, "step": 392680 }, { "epoch": 2.3342309086910262, "grad_norm": 1.2067893743515015, "learning_rate": 4.568105336440283e-05, "loss": 0.4651303291320801, "step": 392690 }, { "epoch": 2.334290350767694, "grad_norm": 1.1585791110992432, "learning_rate": 4.567669943434893e-05, "loss": 0.5083335876464844, "step": 392700 }, { "epoch": 2.334349792844363, "grad_norm": 1.1795603036880493, "learning_rate": 4.567234581199668e-05, "loss": 0.4425039291381836, "step": 392710 }, { "epoch": 2.334409234921031, "grad_norm": 1.2179747819900513, "learning_rate": 4.566799249736688e-05, "loss": 0.48607726097106935, "step": 392720 }, { "epoch": 2.3344686769976994, "grad_norm": 1.6197810173034668, "learning_rate": 4.5663639490480406e-05, "loss": 0.48311419486999513, "step": 392730 }, { "epoch": 2.334528119074368, "grad_norm": 1.406507968902588, "learning_rate": 4.565928679135805e-05, "loss": 0.4649775981903076, "step": 392740 }, { "epoch": 2.3345875611510363, "grad_norm": 0.9765585660934448, "learning_rate": 4.565493440002064e-05, "loss": 0.4927406311035156, "step": 392750 }, { "epoch": 2.3346470032277047, "grad_norm": 1.5850194692611694, "learning_rate": 4.565058231648899e-05, "loss": 0.5170372009277344, "step": 392760 }, { "epoch": 2.334706445304373, "grad_norm": 1.7144445180892944, "learning_rate": 4.564623054078395e-05, "loss": 0.43909502029418945, "step": 392770 }, { "epoch": 2.3347658873810415, "grad_norm": 1.2760392427444458, "learning_rate": 4.5641879072926294e-05, "loss": 0.4808341503143311, "step": 392780 }, { "epoch": 2.33482532945771, "grad_norm": 1.3308055400848389, "learning_rate": 4.5637527912936825e-05, "loss": 0.44722347259521483, "step": 392790 }, { "epoch": 2.3348847715343783, "grad_norm": 1.4617440700531006, "learning_rate": 4.563317706083642e-05, "loss": 0.55948805809021, "step": 392800 }, { "epoch": 2.3349442136110468, "grad_norm": 1.4181251525878906, "learning_rate": 4.562882651664586e-05, "loss": 0.502439308166504, "step": 392810 }, { "epoch": 2.335003655687715, "grad_norm": 1.629504680633545, "learning_rate": 4.5624476280385955e-05, "loss": 0.5049777507781983, "step": 392820 }, { "epoch": 2.3350630977643836, "grad_norm": 1.2692869901657104, "learning_rate": 4.5620126352077517e-05, "loss": 0.4786959648132324, "step": 392830 }, { "epoch": 2.335122539841052, "grad_norm": 1.0872350931167603, "learning_rate": 4.561577673174136e-05, "loss": 0.45213851928710935, "step": 392840 }, { "epoch": 2.3351819819177204, "grad_norm": 1.2457650899887085, "learning_rate": 4.5611427419398297e-05, "loss": 0.497224235534668, "step": 392850 }, { "epoch": 2.335241423994389, "grad_norm": 1.517226219177246, "learning_rate": 4.560707841506908e-05, "loss": 0.5092726230621338, "step": 392860 }, { "epoch": 2.3353008660710572, "grad_norm": 1.2336349487304688, "learning_rate": 4.560272971877459e-05, "loss": 0.45315074920654297, "step": 392870 }, { "epoch": 2.3353603081477257, "grad_norm": 1.1935701370239258, "learning_rate": 4.5598381330535616e-05, "loss": 0.44909820556640623, "step": 392880 }, { "epoch": 2.3354197502243936, "grad_norm": 1.4097791910171509, "learning_rate": 4.5594033250372884e-05, "loss": 0.4853233337402344, "step": 392890 }, { "epoch": 2.335479192301062, "grad_norm": 1.372708797454834, "learning_rate": 4.558968547830728e-05, "loss": 0.48349895477294924, "step": 392900 }, { "epoch": 2.3355386343777305, "grad_norm": 1.5973986387252808, "learning_rate": 4.5585338014359576e-05, "loss": 0.4862028121948242, "step": 392910 }, { "epoch": 2.335598076454399, "grad_norm": 1.5838676691055298, "learning_rate": 4.5580990858550524e-05, "loss": 0.5166333198547364, "step": 392920 }, { "epoch": 2.3356575185310673, "grad_norm": 1.4808460474014282, "learning_rate": 4.5576644010900996e-05, "loss": 0.478773307800293, "step": 392930 }, { "epoch": 2.3357169606077357, "grad_norm": 1.3734177350997925, "learning_rate": 4.557229747143179e-05, "loss": 0.5127790451049805, "step": 392940 }, { "epoch": 2.335776402684404, "grad_norm": 1.320914387702942, "learning_rate": 4.556795124016358e-05, "loss": 0.5380584239959717, "step": 392950 }, { "epoch": 2.3358358447610725, "grad_norm": 0.984691321849823, "learning_rate": 4.5563605317117276e-05, "loss": 0.5299086570739746, "step": 392960 }, { "epoch": 2.335895286837741, "grad_norm": 1.5759446620941162, "learning_rate": 4.555925970231362e-05, "loss": 0.46670989990234374, "step": 392970 }, { "epoch": 2.3359547289144094, "grad_norm": 1.1457960605621338, "learning_rate": 4.5554914395773405e-05, "loss": 0.4940972805023193, "step": 392980 }, { "epoch": 2.3360141709910778, "grad_norm": 1.5717217922210693, "learning_rate": 4.555056939751739e-05, "loss": 0.5141375541687012, "step": 392990 }, { "epoch": 2.336073613067746, "grad_norm": 1.4402432441711426, "learning_rate": 4.5546224707566445e-05, "loss": 0.5300077438354492, "step": 393000 }, { "epoch": 2.3361330551444146, "grad_norm": 1.4134527444839478, "learning_rate": 4.554188032594128e-05, "loss": 0.463106632232666, "step": 393010 }, { "epoch": 2.336192497221083, "grad_norm": 1.2619507312774658, "learning_rate": 4.553753625266265e-05, "loss": 0.4764899253845215, "step": 393020 }, { "epoch": 2.3362519392977514, "grad_norm": 1.2836791276931763, "learning_rate": 4.553319248775142e-05, "loss": 0.48111906051635744, "step": 393030 }, { "epoch": 2.33631138137442, "grad_norm": 1.3917909860610962, "learning_rate": 4.552884903122832e-05, "loss": 0.4438652038574219, "step": 393040 }, { "epoch": 2.3363708234510883, "grad_norm": 1.5194686651229858, "learning_rate": 4.5524505883114147e-05, "loss": 0.4757711410522461, "step": 393050 }, { "epoch": 2.3364302655277562, "grad_norm": 2.002274990081787, "learning_rate": 4.552016304342967e-05, "loss": 0.5622701168060302, "step": 393060 }, { "epoch": 2.336489707604425, "grad_norm": 1.3156310319900513, "learning_rate": 4.5515820512195636e-05, "loss": 0.48426151275634766, "step": 393070 }, { "epoch": 2.336549149681093, "grad_norm": 1.127363681793213, "learning_rate": 4.551147828943284e-05, "loss": 0.5221169948577881, "step": 393080 }, { "epoch": 2.3366085917577615, "grad_norm": 1.7607593536376953, "learning_rate": 4.5507136375162075e-05, "loss": 0.5055305004119873, "step": 393090 }, { "epoch": 2.33666803383443, "grad_norm": 1.3238643407821655, "learning_rate": 4.5502794769404096e-05, "loss": 0.5168240070343018, "step": 393100 }, { "epoch": 2.3367274759110983, "grad_norm": 1.6586909294128418, "learning_rate": 4.549845347217967e-05, "loss": 0.5167313575744629, "step": 393110 }, { "epoch": 2.3367869179877667, "grad_norm": 1.4550269842147827, "learning_rate": 4.549411248350956e-05, "loss": 0.5095522403717041, "step": 393120 }, { "epoch": 2.336846360064435, "grad_norm": 1.2783492803573608, "learning_rate": 4.548977180341453e-05, "loss": 0.4881477355957031, "step": 393130 }, { "epoch": 2.3369058021411035, "grad_norm": 1.4022467136383057, "learning_rate": 4.548543143191536e-05, "loss": 0.5298489570617676, "step": 393140 }, { "epoch": 2.336965244217772, "grad_norm": 1.5816227197647095, "learning_rate": 4.548109136903277e-05, "loss": 0.5046243667602539, "step": 393150 }, { "epoch": 2.3370246862944404, "grad_norm": 1.1591334342956543, "learning_rate": 4.547675161478758e-05, "loss": 0.5091643810272217, "step": 393160 }, { "epoch": 2.337084128371109, "grad_norm": 1.2354410886764526, "learning_rate": 4.547241216920053e-05, "loss": 0.4542263984680176, "step": 393170 }, { "epoch": 2.337143570447777, "grad_norm": 1.632338523864746, "learning_rate": 4.546807303229237e-05, "loss": 0.464799690246582, "step": 393180 }, { "epoch": 2.3372030125244456, "grad_norm": 1.3702120780944824, "learning_rate": 4.546373420408385e-05, "loss": 0.47591333389282225, "step": 393190 }, { "epoch": 2.337262454601114, "grad_norm": 1.720647931098938, "learning_rate": 4.5459395684595745e-05, "loss": 0.5175276756286621, "step": 393200 }, { "epoch": 2.3373218966777825, "grad_norm": 1.205383062362671, "learning_rate": 4.5455057473848764e-05, "loss": 0.5169484138488769, "step": 393210 }, { "epoch": 2.337381338754451, "grad_norm": 1.2891371250152588, "learning_rate": 4.545071957186373e-05, "loss": 0.47653374671936033, "step": 393220 }, { "epoch": 2.3374407808311193, "grad_norm": 1.1234177350997925, "learning_rate": 4.544638197866135e-05, "loss": 0.4968315601348877, "step": 393230 }, { "epoch": 2.3375002229077877, "grad_norm": 1.4463868141174316, "learning_rate": 4.544204469426239e-05, "loss": 0.5029913425445557, "step": 393240 }, { "epoch": 2.3375596649844557, "grad_norm": 1.4494818449020386, "learning_rate": 4.543770771868758e-05, "loss": 0.4798769950866699, "step": 393250 }, { "epoch": 2.3376191070611245, "grad_norm": 1.1135084629058838, "learning_rate": 4.54333710519577e-05, "loss": 0.4911444664001465, "step": 393260 }, { "epoch": 2.3376785491377925, "grad_norm": 1.4729024171829224, "learning_rate": 4.5429034694093445e-05, "loss": 0.484941291809082, "step": 393270 }, { "epoch": 2.337737991214461, "grad_norm": 1.3683736324310303, "learning_rate": 4.542469864511557e-05, "loss": 0.49401402473449707, "step": 393280 }, { "epoch": 2.3377974332911293, "grad_norm": 1.6877384185791016, "learning_rate": 4.5420362905044864e-05, "loss": 0.510581111907959, "step": 393290 }, { "epoch": 2.3378568753677977, "grad_norm": 1.2616606950759888, "learning_rate": 4.541602747390203e-05, "loss": 0.5250606536865234, "step": 393300 }, { "epoch": 2.337916317444466, "grad_norm": 1.4952319860458374, "learning_rate": 4.541169235170782e-05, "loss": 0.4736030101776123, "step": 393310 }, { "epoch": 2.3379757595211346, "grad_norm": 1.4010130167007446, "learning_rate": 4.540735753848297e-05, "loss": 0.5022092819213867, "step": 393320 }, { "epoch": 2.338035201597803, "grad_norm": 1.5279325246810913, "learning_rate": 4.540302303424821e-05, "loss": 0.4926875114440918, "step": 393330 }, { "epoch": 2.3380946436744714, "grad_norm": 1.878414273262024, "learning_rate": 4.539868883902428e-05, "loss": 0.4870606422424316, "step": 393340 }, { "epoch": 2.33815408575114, "grad_norm": 1.6029012203216553, "learning_rate": 4.539435495283186e-05, "loss": 0.4927652359008789, "step": 393350 }, { "epoch": 2.3382135278278082, "grad_norm": 1.4609252214431763, "learning_rate": 4.539002137569179e-05, "loss": 0.5337962150573731, "step": 393360 }, { "epoch": 2.3382729699044766, "grad_norm": 1.087310791015625, "learning_rate": 4.538568810762476e-05, "loss": 0.46648855209350587, "step": 393370 }, { "epoch": 2.338332411981145, "grad_norm": 1.086398720741272, "learning_rate": 4.5381355148651425e-05, "loss": 0.5331937789916992, "step": 393380 }, { "epoch": 2.3383918540578135, "grad_norm": 1.4536134004592896, "learning_rate": 4.53770224987926e-05, "loss": 0.5054954051971435, "step": 393390 }, { "epoch": 2.338451296134482, "grad_norm": 1.5760157108306885, "learning_rate": 4.537269015806897e-05, "loss": 0.5289364337921143, "step": 393400 }, { "epoch": 2.3385107382111503, "grad_norm": 1.0512973070144653, "learning_rate": 4.5368358126501256e-05, "loss": 0.4603642463684082, "step": 393410 }, { "epoch": 2.3385701802878187, "grad_norm": 1.5104433298110962, "learning_rate": 4.536402640411021e-05, "loss": 0.5005835056304931, "step": 393420 }, { "epoch": 2.338629622364487, "grad_norm": 1.4684418439865112, "learning_rate": 4.535969499091657e-05, "loss": 0.47884702682495117, "step": 393430 }, { "epoch": 2.338689064441155, "grad_norm": 1.1300387382507324, "learning_rate": 4.5355363886940974e-05, "loss": 0.46657276153564453, "step": 393440 }, { "epoch": 2.338748506517824, "grad_norm": 1.5065734386444092, "learning_rate": 4.5351033092204216e-05, "loss": 0.5015336513519287, "step": 393450 }, { "epoch": 2.338807948594492, "grad_norm": 1.398898720741272, "learning_rate": 4.534670260672698e-05, "loss": 0.47149834632873533, "step": 393460 }, { "epoch": 2.3388673906711603, "grad_norm": 1.596303939819336, "learning_rate": 4.5342372430530006e-05, "loss": 0.4875363826751709, "step": 393470 }, { "epoch": 2.3389268327478288, "grad_norm": 1.315126657485962, "learning_rate": 4.533804256363396e-05, "loss": 0.5133700847625733, "step": 393480 }, { "epoch": 2.338986274824497, "grad_norm": 1.3471041917800903, "learning_rate": 4.533371300605963e-05, "loss": 0.4734035968780518, "step": 393490 }, { "epoch": 2.3390457169011656, "grad_norm": 1.203601598739624, "learning_rate": 4.532938375782767e-05, "loss": 0.49602155685424804, "step": 393500 }, { "epoch": 2.339105158977834, "grad_norm": 1.5087239742279053, "learning_rate": 4.532505481895877e-05, "loss": 0.502412223815918, "step": 393510 }, { "epoch": 2.3391646010545024, "grad_norm": 1.3305152654647827, "learning_rate": 4.53207261894737e-05, "loss": 0.48388218879699707, "step": 393520 }, { "epoch": 2.339224043131171, "grad_norm": 1.4727718830108643, "learning_rate": 4.531639786939314e-05, "loss": 0.4783022880554199, "step": 393530 }, { "epoch": 2.3392834852078392, "grad_norm": 1.4457820653915405, "learning_rate": 4.5312069858737755e-05, "loss": 0.5047567367553711, "step": 393540 }, { "epoch": 2.3393429272845077, "grad_norm": 1.5775011777877808, "learning_rate": 4.530774215752835e-05, "loss": 0.4877281665802002, "step": 393550 }, { "epoch": 2.339402369361176, "grad_norm": 1.260304570198059, "learning_rate": 4.530341476578555e-05, "loss": 0.49205722808837893, "step": 393560 }, { "epoch": 2.3394618114378445, "grad_norm": 1.5325576066970825, "learning_rate": 4.529908768353002e-05, "loss": 0.48251819610595703, "step": 393570 }, { "epoch": 2.339521253514513, "grad_norm": 1.3408427238464355, "learning_rate": 4.529476091078256e-05, "loss": 0.5341809272766114, "step": 393580 }, { "epoch": 2.3395806955911813, "grad_norm": 1.54402494430542, "learning_rate": 4.52904344475638e-05, "loss": 0.5026782989501953, "step": 393590 }, { "epoch": 2.3396401376678497, "grad_norm": 1.8144928216934204, "learning_rate": 4.528610829389446e-05, "loss": 0.5434838771820069, "step": 393600 }, { "epoch": 2.339699579744518, "grad_norm": 1.2862507104873657, "learning_rate": 4.528178244979523e-05, "loss": 0.4502875328063965, "step": 393610 }, { "epoch": 2.3397590218211866, "grad_norm": 1.2010319232940674, "learning_rate": 4.527745691528681e-05, "loss": 0.4580587387084961, "step": 393620 }, { "epoch": 2.3398184638978545, "grad_norm": 1.3190574645996094, "learning_rate": 4.527313169038988e-05, "loss": 0.5217193603515625, "step": 393630 }, { "epoch": 2.339877905974523, "grad_norm": 0.7975968718528748, "learning_rate": 4.5268806775125114e-05, "loss": 0.44614014625549314, "step": 393640 }, { "epoch": 2.3399373480511914, "grad_norm": 1.2818617820739746, "learning_rate": 4.526448216951323e-05, "loss": 0.4736198902130127, "step": 393650 }, { "epoch": 2.3399967901278598, "grad_norm": 1.383392333984375, "learning_rate": 4.526015787357492e-05, "loss": 0.4114853858947754, "step": 393660 }, { "epoch": 2.340056232204528, "grad_norm": 0.9593554735183716, "learning_rate": 4.5255833887330856e-05, "loss": 0.4943422794342041, "step": 393670 }, { "epoch": 2.3401156742811966, "grad_norm": 1.6841546297073364, "learning_rate": 4.5251510210801726e-05, "loss": 0.49646387100219724, "step": 393680 }, { "epoch": 2.340175116357865, "grad_norm": 1.2744497060775757, "learning_rate": 4.524718684400821e-05, "loss": 0.4323410987854004, "step": 393690 }, { "epoch": 2.3402345584345334, "grad_norm": 1.6390773057937622, "learning_rate": 4.524286378697099e-05, "loss": 0.5302884101867675, "step": 393700 }, { "epoch": 2.340294000511202, "grad_norm": 1.4805395603179932, "learning_rate": 4.523854103971072e-05, "loss": 0.4891242027282715, "step": 393710 }, { "epoch": 2.3403534425878703, "grad_norm": 1.6014761924743652, "learning_rate": 4.5234218602248134e-05, "loss": 0.45714526176452636, "step": 393720 }, { "epoch": 2.3404128846645387, "grad_norm": 1.1665682792663574, "learning_rate": 4.522989647460388e-05, "loss": 0.4925638198852539, "step": 393730 }, { "epoch": 2.340472326741207, "grad_norm": 1.5350064039230347, "learning_rate": 4.522557465679862e-05, "loss": 0.4920992851257324, "step": 393740 }, { "epoch": 2.3405317688178755, "grad_norm": 1.242845058441162, "learning_rate": 4.522125314885306e-05, "loss": 0.47238950729370116, "step": 393750 }, { "epoch": 2.340591210894544, "grad_norm": 1.3742218017578125, "learning_rate": 4.521693195078786e-05, "loss": 0.49725046157836916, "step": 393760 }, { "epoch": 2.3406506529712123, "grad_norm": 1.633650541305542, "learning_rate": 4.5212611062623644e-05, "loss": 0.49125213623046876, "step": 393770 }, { "epoch": 2.3407100950478807, "grad_norm": 1.028506875038147, "learning_rate": 4.520829048438116e-05, "loss": 0.42082815170288085, "step": 393780 }, { "epoch": 2.340769537124549, "grad_norm": 1.0992882251739502, "learning_rate": 4.520397021608103e-05, "loss": 0.490916109085083, "step": 393790 }, { "epoch": 2.340828979201217, "grad_norm": 1.1920994520187378, "learning_rate": 4.5199650257743944e-05, "loss": 0.46238460540771487, "step": 393800 }, { "epoch": 2.340888421277886, "grad_norm": 1.2509686946868896, "learning_rate": 4.519533060939055e-05, "loss": 0.4901000499725342, "step": 393810 }, { "epoch": 2.340947863354554, "grad_norm": 1.420142650604248, "learning_rate": 4.519101127104151e-05, "loss": 0.4275308609008789, "step": 393820 }, { "epoch": 2.3410073054312224, "grad_norm": 1.0300776958465576, "learning_rate": 4.518669224271749e-05, "loss": 0.48600025177001954, "step": 393830 }, { "epoch": 2.341066747507891, "grad_norm": 1.4231206178665161, "learning_rate": 4.518237352443914e-05, "loss": 0.48120770454406736, "step": 393840 }, { "epoch": 2.341126189584559, "grad_norm": 1.0809005498886108, "learning_rate": 4.517805511622715e-05, "loss": 0.5186072826385498, "step": 393850 }, { "epoch": 2.3411856316612276, "grad_norm": 1.4403703212738037, "learning_rate": 4.5173737018102184e-05, "loss": 0.44383773803710935, "step": 393860 }, { "epoch": 2.341245073737896, "grad_norm": 1.2418838739395142, "learning_rate": 4.516941923008483e-05, "loss": 0.5363829612731934, "step": 393870 }, { "epoch": 2.3413045158145644, "grad_norm": 1.087978720664978, "learning_rate": 4.5165101752195806e-05, "loss": 0.4809407711029053, "step": 393880 }, { "epoch": 2.341363957891233, "grad_norm": 1.3908565044403076, "learning_rate": 4.5160784584455755e-05, "loss": 0.47417821884155276, "step": 393890 }, { "epoch": 2.3414233999679013, "grad_norm": 1.124449610710144, "learning_rate": 4.515646772688529e-05, "loss": 0.4582667350769043, "step": 393900 }, { "epoch": 2.3414828420445697, "grad_norm": 1.6479321718215942, "learning_rate": 4.5152151179505117e-05, "loss": 0.5081045627593994, "step": 393910 }, { "epoch": 2.341542284121238, "grad_norm": 1.2548118829727173, "learning_rate": 4.5147834942335885e-05, "loss": 0.47186479568481443, "step": 393920 }, { "epoch": 2.3416017261979065, "grad_norm": 1.5011574029922485, "learning_rate": 4.5143519015398176e-05, "loss": 0.45800004005432127, "step": 393930 }, { "epoch": 2.341661168274575, "grad_norm": 1.333749532699585, "learning_rate": 4.513920339871269e-05, "loss": 0.48940563201904297, "step": 393940 }, { "epoch": 2.3417206103512433, "grad_norm": 1.2449982166290283, "learning_rate": 4.513488809230006e-05, "loss": 0.4924917697906494, "step": 393950 }, { "epoch": 2.3417800524279118, "grad_norm": 1.2920836210250854, "learning_rate": 4.513057309618093e-05, "loss": 0.4207624435424805, "step": 393960 }, { "epoch": 2.34183949450458, "grad_norm": 1.2110905647277832, "learning_rate": 4.512625841037592e-05, "loss": 0.4753842353820801, "step": 393970 }, { "epoch": 2.3418989365812486, "grad_norm": 1.1558414697647095, "learning_rate": 4.5121944034905726e-05, "loss": 0.4739087104797363, "step": 393980 }, { "epoch": 2.3419583786579166, "grad_norm": 1.2441260814666748, "learning_rate": 4.5117629969790934e-05, "loss": 0.47100677490234377, "step": 393990 }, { "epoch": 2.3420178207345854, "grad_norm": 1.439186930656433, "learning_rate": 4.511331621505217e-05, "loss": 0.48709926605224607, "step": 394000 }, { "epoch": 2.3420772628112534, "grad_norm": 1.280094861984253, "learning_rate": 4.5109002770710125e-05, "loss": 0.43587846755981446, "step": 394010 }, { "epoch": 2.342136704887922, "grad_norm": 1.5085091590881348, "learning_rate": 4.5104689636785396e-05, "loss": 0.5350624084472656, "step": 394020 }, { "epoch": 2.34219614696459, "grad_norm": 1.3935377597808838, "learning_rate": 4.510037681329859e-05, "loss": 0.486005973815918, "step": 394030 }, { "epoch": 2.3422555890412586, "grad_norm": 1.404287576675415, "learning_rate": 4.509606430027044e-05, "loss": 0.4816178321838379, "step": 394040 }, { "epoch": 2.342315031117927, "grad_norm": 1.2756712436676025, "learning_rate": 4.5091752097721476e-05, "loss": 0.48064708709716797, "step": 394050 }, { "epoch": 2.3423744731945955, "grad_norm": 1.179448127746582, "learning_rate": 4.508744020567233e-05, "loss": 0.4925984859466553, "step": 394060 }, { "epoch": 2.342433915271264, "grad_norm": 1.3146249055862427, "learning_rate": 4.5083128624143686e-05, "loss": 0.43831691741943357, "step": 394070 }, { "epoch": 2.3424933573479323, "grad_norm": 0.8696951866149902, "learning_rate": 4.5078817353156136e-05, "loss": 0.5284450054168701, "step": 394080 }, { "epoch": 2.3425527994246007, "grad_norm": 1.4068056344985962, "learning_rate": 4.507450639273031e-05, "loss": 0.49236607551574707, "step": 394090 }, { "epoch": 2.342612241501269, "grad_norm": 1.5379399061203003, "learning_rate": 4.5070195742886825e-05, "loss": 0.45107059478759765, "step": 394100 }, { "epoch": 2.3426716835779375, "grad_norm": 1.2003319263458252, "learning_rate": 4.5065885403646304e-05, "loss": 0.4885751247406006, "step": 394110 }, { "epoch": 2.342731125654606, "grad_norm": 1.354144811630249, "learning_rate": 4.506157537502937e-05, "loss": 0.5203977108001709, "step": 394120 }, { "epoch": 2.3427905677312744, "grad_norm": 1.1375621557235718, "learning_rate": 4.50572656570566e-05, "loss": 0.4512015342712402, "step": 394130 }, { "epoch": 2.342850009807943, "grad_norm": 1.462701439857483, "learning_rate": 4.505295624974869e-05, "loss": 0.5221670150756836, "step": 394140 }, { "epoch": 2.342909451884611, "grad_norm": 1.4376389980316162, "learning_rate": 4.5048647153126206e-05, "loss": 0.47438793182373046, "step": 394150 }, { "epoch": 2.3429688939612796, "grad_norm": 1.1911823749542236, "learning_rate": 4.5044338367209764e-05, "loss": 0.4883736610412598, "step": 394160 }, { "epoch": 2.343028336037948, "grad_norm": 1.382609248161316, "learning_rate": 4.504002989201999e-05, "loss": 0.5386228561401367, "step": 394170 }, { "epoch": 2.343087778114616, "grad_norm": 0.9042197465896606, "learning_rate": 4.503572172757747e-05, "loss": 0.48761801719665526, "step": 394180 }, { "epoch": 2.343147220191285, "grad_norm": 1.2270643711090088, "learning_rate": 4.503141387390284e-05, "loss": 0.4740035057067871, "step": 394190 }, { "epoch": 2.343206662267953, "grad_norm": 1.0756489038467407, "learning_rate": 4.502710633101666e-05, "loss": 0.46126604080200195, "step": 394200 }, { "epoch": 2.3432661043446212, "grad_norm": 1.634110689163208, "learning_rate": 4.502279909893959e-05, "loss": 0.4663362503051758, "step": 394210 }, { "epoch": 2.3433255464212897, "grad_norm": 1.3227390050888062, "learning_rate": 4.5018492177692226e-05, "loss": 0.4774138927459717, "step": 394220 }, { "epoch": 2.343384988497958, "grad_norm": 1.5431853532791138, "learning_rate": 4.5014185567295145e-05, "loss": 0.49706716537475587, "step": 394230 }, { "epoch": 2.3434444305746265, "grad_norm": 1.2847161293029785, "learning_rate": 4.500987926776898e-05, "loss": 0.5112294673919677, "step": 394240 }, { "epoch": 2.343503872651295, "grad_norm": 1.1751729249954224, "learning_rate": 4.50055732791343e-05, "loss": 0.48319435119628906, "step": 394250 }, { "epoch": 2.3435633147279633, "grad_norm": 1.2654846906661987, "learning_rate": 4.5001267601411704e-05, "loss": 0.48024768829345704, "step": 394260 }, { "epoch": 2.3436227568046317, "grad_norm": 1.3064028024673462, "learning_rate": 4.499696223462181e-05, "loss": 0.4831717491149902, "step": 394270 }, { "epoch": 2.3436821988813, "grad_norm": 1.3860729932785034, "learning_rate": 4.4992657178785226e-05, "loss": 0.4728857040405273, "step": 394280 }, { "epoch": 2.3437416409579686, "grad_norm": 1.552127480506897, "learning_rate": 4.498835243392251e-05, "loss": 0.5029982089996338, "step": 394290 }, { "epoch": 2.343801083034637, "grad_norm": 1.3954499959945679, "learning_rate": 4.498404800005428e-05, "loss": 0.49792914390563964, "step": 394300 }, { "epoch": 2.3438605251113054, "grad_norm": 1.1689614057540894, "learning_rate": 4.497974387720111e-05, "loss": 0.4484115123748779, "step": 394310 }, { "epoch": 2.343919967187974, "grad_norm": 1.1290090084075928, "learning_rate": 4.49754400653836e-05, "loss": 0.48832025527954104, "step": 394320 }, { "epoch": 2.343979409264642, "grad_norm": 1.3484045267105103, "learning_rate": 4.497113656462231e-05, "loss": 0.48067150115966795, "step": 394330 }, { "epoch": 2.3440388513413106, "grad_norm": 1.6864395141601562, "learning_rate": 4.496683337493787e-05, "loss": 0.5069828033447266, "step": 394340 }, { "epoch": 2.344098293417979, "grad_norm": 1.593753457069397, "learning_rate": 4.4962530496350855e-05, "loss": 0.48360323905944824, "step": 394350 }, { "epoch": 2.3441577354946475, "grad_norm": 1.5407828092575073, "learning_rate": 4.495822792888182e-05, "loss": 0.4748836517333984, "step": 394360 }, { "epoch": 2.3442171775713154, "grad_norm": 1.085028052330017, "learning_rate": 4.495392567255139e-05, "loss": 0.4826552391052246, "step": 394370 }, { "epoch": 2.344276619647984, "grad_norm": 1.6662791967391968, "learning_rate": 4.494962372738012e-05, "loss": 0.4981392860412598, "step": 394380 }, { "epoch": 2.3443360617246523, "grad_norm": 1.2623926401138306, "learning_rate": 4.494532209338855e-05, "loss": 0.5326226234436036, "step": 394390 }, { "epoch": 2.3443955038013207, "grad_norm": 0.9845829010009766, "learning_rate": 4.494102077059734e-05, "loss": 0.4632375240325928, "step": 394400 }, { "epoch": 2.344454945877989, "grad_norm": 1.2991325855255127, "learning_rate": 4.4936719759027015e-05, "loss": 0.5067710876464844, "step": 394410 }, { "epoch": 2.3445143879546575, "grad_norm": 1.1242647171020508, "learning_rate": 4.493241905869817e-05, "loss": 0.47670297622680663, "step": 394420 }, { "epoch": 2.344573830031326, "grad_norm": 1.0467936992645264, "learning_rate": 4.4928118669631367e-05, "loss": 0.47837009429931643, "step": 394430 }, { "epoch": 2.3446332721079943, "grad_norm": 1.4025895595550537, "learning_rate": 4.492381859184717e-05, "loss": 0.514039421081543, "step": 394440 }, { "epoch": 2.3446927141846627, "grad_norm": 1.4076097011566162, "learning_rate": 4.491951882536616e-05, "loss": 0.49573640823364257, "step": 394450 }, { "epoch": 2.344752156261331, "grad_norm": 1.2922685146331787, "learning_rate": 4.4915219370208874e-05, "loss": 0.42045230865478517, "step": 394460 }, { "epoch": 2.3448115983379996, "grad_norm": 1.2857232093811035, "learning_rate": 4.491092022639597e-05, "loss": 0.48343667984008787, "step": 394470 }, { "epoch": 2.344871040414668, "grad_norm": 1.4421840906143188, "learning_rate": 4.490662139394792e-05, "loss": 0.5353198051452637, "step": 394480 }, { "epoch": 2.3449304824913364, "grad_norm": 1.1795848608016968, "learning_rate": 4.49023228728853e-05, "loss": 0.48203339576721194, "step": 394490 }, { "epoch": 2.344989924568005, "grad_norm": 1.094395637512207, "learning_rate": 4.489802466322872e-05, "loss": 0.4592618942260742, "step": 394500 }, { "epoch": 2.3450493666446732, "grad_norm": 1.1376127004623413, "learning_rate": 4.4893726764998705e-05, "loss": 0.4400952339172363, "step": 394510 }, { "epoch": 2.3451088087213416, "grad_norm": 1.4244861602783203, "learning_rate": 4.4889429178215803e-05, "loss": 0.4320201396942139, "step": 394520 }, { "epoch": 2.34516825079801, "grad_norm": 1.4145756959915161, "learning_rate": 4.4885131902900645e-05, "loss": 0.5278860569000244, "step": 394530 }, { "epoch": 2.345227692874678, "grad_norm": 1.4438793659210205, "learning_rate": 4.488083493907371e-05, "loss": 0.4866611480712891, "step": 394540 }, { "epoch": 2.345287134951347, "grad_norm": 1.4374825954437256, "learning_rate": 4.4876538286755585e-05, "loss": 0.5494246482849121, "step": 394550 }, { "epoch": 2.345346577028015, "grad_norm": 1.3571271896362305, "learning_rate": 4.4872241945966774e-05, "loss": 0.454069995880127, "step": 394560 }, { "epoch": 2.3454060191046833, "grad_norm": 1.4651851654052734, "learning_rate": 4.486794591672792e-05, "loss": 0.49137129783630373, "step": 394570 }, { "epoch": 2.3454654611813517, "grad_norm": 1.4101262092590332, "learning_rate": 4.486365019905952e-05, "loss": 0.5266108512878418, "step": 394580 }, { "epoch": 2.34552490325802, "grad_norm": 1.2395198345184326, "learning_rate": 4.4859354792982135e-05, "loss": 0.5172201156616211, "step": 394590 }, { "epoch": 2.3455843453346885, "grad_norm": 1.6029077768325806, "learning_rate": 4.48550596985163e-05, "loss": 0.5280220031738281, "step": 394600 }, { "epoch": 2.345643787411357, "grad_norm": 1.223751425743103, "learning_rate": 4.485076491568258e-05, "loss": 0.4402979850769043, "step": 394610 }, { "epoch": 2.3457032294880253, "grad_norm": 1.3808479309082031, "learning_rate": 4.484647044450147e-05, "loss": 0.5092983245849609, "step": 394620 }, { "epoch": 2.3457626715646938, "grad_norm": 1.421217441558838, "learning_rate": 4.484217628499359e-05, "loss": 0.5032890319824219, "step": 394630 }, { "epoch": 2.345822113641362, "grad_norm": 1.0273857116699219, "learning_rate": 4.4837882437179444e-05, "loss": 0.5465438842773438, "step": 394640 }, { "epoch": 2.3458815557180306, "grad_norm": 1.3476359844207764, "learning_rate": 4.483358890107957e-05, "loss": 0.45839757919311525, "step": 394650 }, { "epoch": 2.345940997794699, "grad_norm": 1.0817762613296509, "learning_rate": 4.4829295676714504e-05, "loss": 0.49687509536743163, "step": 394660 }, { "epoch": 2.3460004398713674, "grad_norm": 1.4357028007507324, "learning_rate": 4.482500276410481e-05, "loss": 0.4613471031188965, "step": 394670 }, { "epoch": 2.346059881948036, "grad_norm": 1.0410895347595215, "learning_rate": 4.4820710163270984e-05, "loss": 0.4838247299194336, "step": 394680 }, { "epoch": 2.3461193240247042, "grad_norm": 1.3790644407272339, "learning_rate": 4.4816417874233554e-05, "loss": 0.5047814846038818, "step": 394690 }, { "epoch": 2.3461787661013727, "grad_norm": 1.2890195846557617, "learning_rate": 4.481212589701311e-05, "loss": 0.4812185287475586, "step": 394700 }, { "epoch": 2.346238208178041, "grad_norm": 1.511674165725708, "learning_rate": 4.480783423163015e-05, "loss": 0.5388459205627442, "step": 394710 }, { "epoch": 2.3462976502547095, "grad_norm": 1.3364160060882568, "learning_rate": 4.4803542878105206e-05, "loss": 0.4707980155944824, "step": 394720 }, { "epoch": 2.3463570923313775, "grad_norm": 0.9527862071990967, "learning_rate": 4.4799251836458814e-05, "loss": 0.48806066513061525, "step": 394730 }, { "epoch": 2.3464165344080463, "grad_norm": 1.4877527952194214, "learning_rate": 4.4794961106711495e-05, "loss": 0.49117412567138674, "step": 394740 }, { "epoch": 2.3464759764847143, "grad_norm": 1.196467399597168, "learning_rate": 4.479067068888374e-05, "loss": 0.47973976135253904, "step": 394750 }, { "epoch": 2.3465354185613827, "grad_norm": 1.0575350522994995, "learning_rate": 4.478638058299613e-05, "loss": 0.47526016235351565, "step": 394760 }, { "epoch": 2.346594860638051, "grad_norm": 1.364964246749878, "learning_rate": 4.478209078906916e-05, "loss": 0.45354499816894533, "step": 394770 }, { "epoch": 2.3466543027147195, "grad_norm": 1.47404944896698, "learning_rate": 4.477780130712336e-05, "loss": 0.49103870391845705, "step": 394780 }, { "epoch": 2.346713744791388, "grad_norm": 1.3734266757965088, "learning_rate": 4.477351213717924e-05, "loss": 0.5069903373718262, "step": 394790 }, { "epoch": 2.3467731868680564, "grad_norm": 1.3437485694885254, "learning_rate": 4.4769223279257325e-05, "loss": 0.4463996410369873, "step": 394800 }, { "epoch": 2.3468326289447248, "grad_norm": 1.4181907176971436, "learning_rate": 4.476493473337813e-05, "loss": 0.4752227306365967, "step": 394810 }, { "epoch": 2.346892071021393, "grad_norm": 1.2201772928237915, "learning_rate": 4.4760646499562135e-05, "loss": 0.5043440341949463, "step": 394820 }, { "epoch": 2.3469515130980616, "grad_norm": 1.5724170207977295, "learning_rate": 4.475635857782993e-05, "loss": 0.48163485527038574, "step": 394830 }, { "epoch": 2.34701095517473, "grad_norm": 1.492133617401123, "learning_rate": 4.4752070968201965e-05, "loss": 0.48558969497680665, "step": 394840 }, { "epoch": 2.3470703972513984, "grad_norm": 1.1669687032699585, "learning_rate": 4.474778367069877e-05, "loss": 0.4712811470031738, "step": 394850 }, { "epoch": 2.347129839328067, "grad_norm": 1.3931307792663574, "learning_rate": 4.474349668534087e-05, "loss": 0.5194763660430908, "step": 394860 }, { "epoch": 2.3471892814047353, "grad_norm": 1.0292671918869019, "learning_rate": 4.473921001214874e-05, "loss": 0.48346891403198244, "step": 394870 }, { "epoch": 2.3472487234814037, "grad_norm": 1.9602564573287964, "learning_rate": 4.473492365114288e-05, "loss": 0.4980187892913818, "step": 394880 }, { "epoch": 2.347308165558072, "grad_norm": 1.3750028610229492, "learning_rate": 4.473063760234384e-05, "loss": 0.43962631225585935, "step": 394890 }, { "epoch": 2.3473676076347405, "grad_norm": 1.29640531539917, "learning_rate": 4.47263518657721e-05, "loss": 0.500156831741333, "step": 394900 }, { "epoch": 2.347427049711409, "grad_norm": 1.081963062286377, "learning_rate": 4.4722066441448165e-05, "loss": 0.5346831321716309, "step": 394910 }, { "epoch": 2.347486491788077, "grad_norm": 1.4961098432540894, "learning_rate": 4.471778132939254e-05, "loss": 0.501441764831543, "step": 394920 }, { "epoch": 2.3475459338647453, "grad_norm": 1.4954365491867065, "learning_rate": 4.47134965296257e-05, "loss": 0.4904168128967285, "step": 394930 }, { "epoch": 2.3476053759414137, "grad_norm": 1.399618148803711, "learning_rate": 4.470921204216815e-05, "loss": 0.4887363433837891, "step": 394940 }, { "epoch": 2.347664818018082, "grad_norm": 0.7988556027412415, "learning_rate": 4.470492786704039e-05, "loss": 0.42861237525939944, "step": 394950 }, { "epoch": 2.3477242600947505, "grad_norm": 1.3764634132385254, "learning_rate": 4.4700644004262924e-05, "loss": 0.48284244537353516, "step": 394960 }, { "epoch": 2.347783702171419, "grad_norm": 1.2211698293685913, "learning_rate": 4.469636045385627e-05, "loss": 0.45307159423828125, "step": 394970 }, { "epoch": 2.3478431442480874, "grad_norm": 1.51656174659729, "learning_rate": 4.469207721584083e-05, "loss": 0.47032732963562013, "step": 394980 }, { "epoch": 2.347902586324756, "grad_norm": 1.3151743412017822, "learning_rate": 4.4687794290237174e-05, "loss": 0.4450244903564453, "step": 394990 }, { "epoch": 2.347962028401424, "grad_norm": 1.5846478939056396, "learning_rate": 4.468351167706577e-05, "loss": 0.4968697547912598, "step": 395000 }, { "epoch": 2.3480214704780926, "grad_norm": 1.189886212348938, "learning_rate": 4.4679229376347076e-05, "loss": 0.47693424224853515, "step": 395010 }, { "epoch": 2.348080912554761, "grad_norm": 1.2693578004837036, "learning_rate": 4.467494738810163e-05, "loss": 0.47685809135437013, "step": 395020 }, { "epoch": 2.3481403546314294, "grad_norm": 1.2651524543762207, "learning_rate": 4.467066571234991e-05, "loss": 0.4801449775695801, "step": 395030 }, { "epoch": 2.348199796708098, "grad_norm": 1.4077712297439575, "learning_rate": 4.4666384349112354e-05, "loss": 0.5354215621948242, "step": 395040 }, { "epoch": 2.3482592387847663, "grad_norm": 1.5701870918273926, "learning_rate": 4.4662103298409425e-05, "loss": 0.5153361320495605, "step": 395050 }, { "epoch": 2.3483186808614347, "grad_norm": 1.2784194946289062, "learning_rate": 4.465782256026167e-05, "loss": 0.4888180732727051, "step": 395060 }, { "epoch": 2.348378122938103, "grad_norm": 1.318124532699585, "learning_rate": 4.465354213468955e-05, "loss": 0.5325440883636474, "step": 395070 }, { "epoch": 2.3484375650147715, "grad_norm": 1.3866336345672607, "learning_rate": 4.464926202171352e-05, "loss": 0.4773847579956055, "step": 395080 }, { "epoch": 2.34849700709144, "grad_norm": 1.5675660371780396, "learning_rate": 4.464498222135406e-05, "loss": 0.49821624755859373, "step": 395090 }, { "epoch": 2.3485564491681084, "grad_norm": 1.2717527151107788, "learning_rate": 4.4640702733631654e-05, "loss": 0.5041567802429199, "step": 395100 }, { "epoch": 2.3486158912447763, "grad_norm": 1.5797712802886963, "learning_rate": 4.4636423558566744e-05, "loss": 0.49967474937438966, "step": 395110 }, { "epoch": 2.3486753333214447, "grad_norm": 1.5481069087982178, "learning_rate": 4.463214469617984e-05, "loss": 0.5088540077209472, "step": 395120 }, { "epoch": 2.348734775398113, "grad_norm": 0.9131312370300293, "learning_rate": 4.46278661464914e-05, "loss": 0.38306641578674316, "step": 395130 }, { "epoch": 2.3487942174747816, "grad_norm": 1.6306571960449219, "learning_rate": 4.462358790952188e-05, "loss": 0.45963611602783205, "step": 395140 }, { "epoch": 2.34885365955145, "grad_norm": 1.7734873294830322, "learning_rate": 4.461930998529175e-05, "loss": 0.5027346134185791, "step": 395150 }, { "epoch": 2.3489131016281184, "grad_norm": 1.3856298923492432, "learning_rate": 4.461503237382148e-05, "loss": 0.47862634658813474, "step": 395160 }, { "epoch": 2.348972543704787, "grad_norm": 1.3301678895950317, "learning_rate": 4.461075507513152e-05, "loss": 0.450545597076416, "step": 395170 }, { "epoch": 2.3490319857814552, "grad_norm": 1.2085793018341064, "learning_rate": 4.460647808924232e-05, "loss": 0.4936363220214844, "step": 395180 }, { "epoch": 2.3490914278581236, "grad_norm": 1.1521259546279907, "learning_rate": 4.460220141617437e-05, "loss": 0.4315633773803711, "step": 395190 }, { "epoch": 2.349150869934792, "grad_norm": 1.2319942712783813, "learning_rate": 4.459792505594812e-05, "loss": 0.5045178890228271, "step": 395200 }, { "epoch": 2.3492103120114605, "grad_norm": 1.1394976377487183, "learning_rate": 4.4593649008584035e-05, "loss": 0.45887117385864257, "step": 395210 }, { "epoch": 2.349269754088129, "grad_norm": 1.1535860300064087, "learning_rate": 4.4589373274102555e-05, "loss": 0.48106884956359863, "step": 395220 }, { "epoch": 2.3493291961647973, "grad_norm": 1.5023045539855957, "learning_rate": 4.4585097852524126e-05, "loss": 0.4448094367980957, "step": 395230 }, { "epoch": 2.3493886382414657, "grad_norm": 1.0643304586410522, "learning_rate": 4.458082274386919e-05, "loss": 0.47043299674987793, "step": 395240 }, { "epoch": 2.349448080318134, "grad_norm": 1.2718429565429688, "learning_rate": 4.457654794815826e-05, "loss": 0.5093569278717041, "step": 395250 }, { "epoch": 2.3495075223948025, "grad_norm": 1.177809476852417, "learning_rate": 4.4572273465411726e-05, "loss": 0.44469966888427737, "step": 395260 }, { "epoch": 2.349566964471471, "grad_norm": 1.1937788724899292, "learning_rate": 4.4567999295650055e-05, "loss": 0.4263929843902588, "step": 395270 }, { "epoch": 2.349626406548139, "grad_norm": 1.1298391819000244, "learning_rate": 4.45637254388937e-05, "loss": 0.4858811378479004, "step": 395280 }, { "epoch": 2.349685848624808, "grad_norm": 1.4930964708328247, "learning_rate": 4.455945189516309e-05, "loss": 0.4510857582092285, "step": 395290 }, { "epoch": 2.3497452907014758, "grad_norm": 1.0801723003387451, "learning_rate": 4.455517866447868e-05, "loss": 0.5055044174194336, "step": 395300 }, { "epoch": 2.349804732778144, "grad_norm": 1.394963026046753, "learning_rate": 4.455090574686088e-05, "loss": 0.5359824180603028, "step": 395310 }, { "epoch": 2.3498641748548126, "grad_norm": 1.3756849765777588, "learning_rate": 4.454663314233019e-05, "loss": 0.4906309604644775, "step": 395320 }, { "epoch": 2.349923616931481, "grad_norm": 1.4925448894500732, "learning_rate": 4.4542360850907004e-05, "loss": 0.5210729598999023, "step": 395330 }, { "epoch": 2.3499830590081494, "grad_norm": 1.442920446395874, "learning_rate": 4.4538088872611784e-05, "loss": 0.5141965866088867, "step": 395340 }, { "epoch": 2.350042501084818, "grad_norm": 1.9674752950668335, "learning_rate": 4.453381720746495e-05, "loss": 0.4830615997314453, "step": 395350 }, { "epoch": 2.3501019431614862, "grad_norm": 1.2286499738693237, "learning_rate": 4.452954585548694e-05, "loss": 0.48795428276062014, "step": 395360 }, { "epoch": 2.3501613852381547, "grad_norm": 1.308547854423523, "learning_rate": 4.452527481669816e-05, "loss": 0.5324055671691894, "step": 395370 }, { "epoch": 2.350220827314823, "grad_norm": 1.3560153245925903, "learning_rate": 4.452100409111909e-05, "loss": 0.5509031295776368, "step": 395380 }, { "epoch": 2.3502802693914915, "grad_norm": 1.8247426748275757, "learning_rate": 4.451673367877014e-05, "loss": 0.5141016483306885, "step": 395390 }, { "epoch": 2.35033971146816, "grad_norm": 1.1255093812942505, "learning_rate": 4.4512463579671764e-05, "loss": 0.4810725212097168, "step": 395400 }, { "epoch": 2.3503991535448283, "grad_norm": 1.224725365638733, "learning_rate": 4.450819379384431e-05, "loss": 0.4926469802856445, "step": 395410 }, { "epoch": 2.3504585956214967, "grad_norm": 1.5303928852081299, "learning_rate": 4.450392432130828e-05, "loss": 0.4811700344085693, "step": 395420 }, { "epoch": 2.350518037698165, "grad_norm": 1.2978606224060059, "learning_rate": 4.4499655162084065e-05, "loss": 0.4715547561645508, "step": 395430 }, { "epoch": 2.3505774797748336, "grad_norm": 1.373354434967041, "learning_rate": 4.449538631619207e-05, "loss": 0.49908957481384275, "step": 395440 }, { "epoch": 2.350636921851502, "grad_norm": 1.2963584661483765, "learning_rate": 4.449111778365277e-05, "loss": 0.44651069641113283, "step": 395450 }, { "epoch": 2.3506963639281704, "grad_norm": 1.351902723312378, "learning_rate": 4.448684956448658e-05, "loss": 0.4954843521118164, "step": 395460 }, { "epoch": 2.3507558060048384, "grad_norm": 1.1277830600738525, "learning_rate": 4.448258165871383e-05, "loss": 0.47171292304992674, "step": 395470 }, { "epoch": 2.350815248081507, "grad_norm": 1.2880350351333618, "learning_rate": 4.447831406635503e-05, "loss": 0.4707639694213867, "step": 395480 }, { "epoch": 2.350874690158175, "grad_norm": 1.023719310760498, "learning_rate": 4.4474046787430566e-05, "loss": 0.4693330764770508, "step": 395490 }, { "epoch": 2.3509341322348436, "grad_norm": 1.2730618715286255, "learning_rate": 4.4469779821960835e-05, "loss": 0.49948573112487793, "step": 395500 }, { "epoch": 2.350993574311512, "grad_norm": 1.4573943614959717, "learning_rate": 4.446551316996625e-05, "loss": 0.4701545715332031, "step": 395510 }, { "epoch": 2.3510530163881804, "grad_norm": 1.3692412376403809, "learning_rate": 4.4461246831467293e-05, "loss": 0.4934248924255371, "step": 395520 }, { "epoch": 2.351112458464849, "grad_norm": 1.1221927404403687, "learning_rate": 4.445698080648428e-05, "loss": 0.48470287322998046, "step": 395530 }, { "epoch": 2.3511719005415173, "grad_norm": 1.2809957265853882, "learning_rate": 4.4452715095037615e-05, "loss": 0.47381105422973635, "step": 395540 }, { "epoch": 2.3512313426181857, "grad_norm": 1.374049425125122, "learning_rate": 4.444844969714778e-05, "loss": 0.46571621894836424, "step": 395550 }, { "epoch": 2.351290784694854, "grad_norm": 1.7208813428878784, "learning_rate": 4.444418461283513e-05, "loss": 0.5067484378814697, "step": 395560 }, { "epoch": 2.3513502267715225, "grad_norm": 1.312304139137268, "learning_rate": 4.443991984212005e-05, "loss": 0.4871987342834473, "step": 395570 }, { "epoch": 2.351409668848191, "grad_norm": 1.4760000705718994, "learning_rate": 4.443565538502302e-05, "loss": 0.4532774925231934, "step": 395580 }, { "epoch": 2.3514691109248593, "grad_norm": 0.9999834299087524, "learning_rate": 4.443139124156437e-05, "loss": 0.43466663360595703, "step": 395590 }, { "epoch": 2.3515285530015277, "grad_norm": 1.4112870693206787, "learning_rate": 4.442712741176449e-05, "loss": 0.48251638412475584, "step": 395600 }, { "epoch": 2.351587995078196, "grad_norm": 0.9704769849777222, "learning_rate": 4.442286389564382e-05, "loss": 0.4728595733642578, "step": 395610 }, { "epoch": 2.3516474371548646, "grad_norm": 1.3622766733169556, "learning_rate": 4.4418600693222744e-05, "loss": 0.506252670288086, "step": 395620 }, { "epoch": 2.351706879231533, "grad_norm": 1.3599600791931152, "learning_rate": 4.4414337804521625e-05, "loss": 0.49301767349243164, "step": 395630 }, { "epoch": 2.3517663213082014, "grad_norm": 1.1410719156265259, "learning_rate": 4.4410075229560926e-05, "loss": 0.494922399520874, "step": 395640 }, { "epoch": 2.35182576338487, "grad_norm": 1.22763192653656, "learning_rate": 4.440581296836096e-05, "loss": 0.47826223373413085, "step": 395650 }, { "epoch": 2.351885205461538, "grad_norm": 1.3811132907867432, "learning_rate": 4.440155102094216e-05, "loss": 0.5355011463165283, "step": 395660 }, { "epoch": 2.351944647538206, "grad_norm": 1.261802077293396, "learning_rate": 4.4397289387324876e-05, "loss": 0.5178362369537354, "step": 395670 }, { "epoch": 2.3520040896148746, "grad_norm": 1.537021279335022, "learning_rate": 4.439302806752955e-05, "loss": 0.5345295906066895, "step": 395680 }, { "epoch": 2.352063531691543, "grad_norm": 1.3970345258712769, "learning_rate": 4.438876706157653e-05, "loss": 0.4781162261962891, "step": 395690 }, { "epoch": 2.3521229737682114, "grad_norm": 1.1003029346466064, "learning_rate": 4.438450636948621e-05, "loss": 0.44542083740234373, "step": 395700 }, { "epoch": 2.35218241584488, "grad_norm": 1.5305670499801636, "learning_rate": 4.438024599127897e-05, "loss": 0.4529123783111572, "step": 395710 }, { "epoch": 2.3522418579215483, "grad_norm": 1.3870755434036255, "learning_rate": 4.437598592697518e-05, "loss": 0.5225360870361329, "step": 395720 }, { "epoch": 2.3523012999982167, "grad_norm": 1.443768858909607, "learning_rate": 4.4371726176595194e-05, "loss": 0.4975475788116455, "step": 395730 }, { "epoch": 2.352360742074885, "grad_norm": 1.1458184719085693, "learning_rate": 4.436746674015947e-05, "loss": 0.5116887569427491, "step": 395740 }, { "epoch": 2.3524201841515535, "grad_norm": 1.3894342184066772, "learning_rate": 4.4363207617688316e-05, "loss": 0.564897108078003, "step": 395750 }, { "epoch": 2.352479626228222, "grad_norm": 1.1796506643295288, "learning_rate": 4.4358948809202136e-05, "loss": 0.4885146141052246, "step": 395760 }, { "epoch": 2.3525390683048903, "grad_norm": 0.906187117099762, "learning_rate": 4.43546903147213e-05, "loss": 0.5196186065673828, "step": 395770 }, { "epoch": 2.3525985103815588, "grad_norm": 1.2082223892211914, "learning_rate": 4.435043213426616e-05, "loss": 0.43879313468933107, "step": 395780 }, { "epoch": 2.352657952458227, "grad_norm": 1.2381491661071777, "learning_rate": 4.434617426785711e-05, "loss": 0.48299856185913087, "step": 395790 }, { "epoch": 2.3527173945348956, "grad_norm": 1.527910590171814, "learning_rate": 4.4341916715514474e-05, "loss": 0.5115745544433594, "step": 395800 }, { "epoch": 2.352776836611564, "grad_norm": 1.2848469018936157, "learning_rate": 4.433765947725868e-05, "loss": 0.48262829780578614, "step": 395810 }, { "epoch": 2.3528362786882324, "grad_norm": 1.2083070278167725, "learning_rate": 4.433340255311006e-05, "loss": 0.5244955062866211, "step": 395820 }, { "epoch": 2.352895720764901, "grad_norm": 1.5547335147857666, "learning_rate": 4.432914594308899e-05, "loss": 0.48077392578125, "step": 395830 }, { "epoch": 2.3529551628415692, "grad_norm": 1.3797791004180908, "learning_rate": 4.432488964721582e-05, "loss": 0.46022605895996094, "step": 395840 }, { "epoch": 2.353014604918237, "grad_norm": 1.4270249605178833, "learning_rate": 4.4320633665510914e-05, "loss": 0.49599523544311525, "step": 395850 }, { "epoch": 2.3530740469949056, "grad_norm": 1.1409363746643066, "learning_rate": 4.431637799799461e-05, "loss": 0.46876869201660154, "step": 395860 }, { "epoch": 2.353133489071574, "grad_norm": 1.1338632106781006, "learning_rate": 4.4312122644687305e-05, "loss": 0.4604806900024414, "step": 395870 }, { "epoch": 2.3531929311482425, "grad_norm": 1.4596537351608276, "learning_rate": 4.430786760560934e-05, "loss": 0.4111928939819336, "step": 395880 }, { "epoch": 2.353252373224911, "grad_norm": 1.2781791687011719, "learning_rate": 4.43036128807811e-05, "loss": 0.4914722442626953, "step": 395890 }, { "epoch": 2.3533118153015793, "grad_norm": 1.0269138813018799, "learning_rate": 4.429935847022284e-05, "loss": 0.4836433410644531, "step": 395900 }, { "epoch": 2.3533712573782477, "grad_norm": 1.5167573690414429, "learning_rate": 4.4295104373955024e-05, "loss": 0.48430442810058594, "step": 395910 }, { "epoch": 2.353430699454916, "grad_norm": 1.801733136177063, "learning_rate": 4.4290850591997943e-05, "loss": 0.5078372001647949, "step": 395920 }, { "epoch": 2.3534901415315845, "grad_norm": 1.3609448671340942, "learning_rate": 4.4286597124371944e-05, "loss": 0.48847002983093263, "step": 395930 }, { "epoch": 2.353549583608253, "grad_norm": 1.503760814666748, "learning_rate": 4.428234397109741e-05, "loss": 0.535345458984375, "step": 395940 }, { "epoch": 2.3536090256849214, "grad_norm": 1.178644061088562, "learning_rate": 4.4278091132194685e-05, "loss": 0.5071362972259521, "step": 395950 }, { "epoch": 2.3536684677615898, "grad_norm": 1.2026088237762451, "learning_rate": 4.427383860768404e-05, "loss": 0.4736617088317871, "step": 395960 }, { "epoch": 2.353727909838258, "grad_norm": 1.3667702674865723, "learning_rate": 4.426958639758591e-05, "loss": 0.47971582412719727, "step": 395970 }, { "epoch": 2.3537873519149266, "grad_norm": 1.392798662185669, "learning_rate": 4.4265334501920585e-05, "loss": 0.45868444442749023, "step": 395980 }, { "epoch": 2.353846793991595, "grad_norm": 1.3888492584228516, "learning_rate": 4.4261082920708394e-05, "loss": 0.466440486907959, "step": 395990 }, { "epoch": 2.3539062360682634, "grad_norm": 1.277265191078186, "learning_rate": 4.4256831653969735e-05, "loss": 0.46844959259033203, "step": 396000 }, { "epoch": 2.353965678144932, "grad_norm": 1.5313071012496948, "learning_rate": 4.4252580701724936e-05, "loss": 0.5354211807250977, "step": 396010 }, { "epoch": 2.3540251202216, "grad_norm": 1.2918410301208496, "learning_rate": 4.424833006399427e-05, "loss": 0.5086607933044434, "step": 396020 }, { "epoch": 2.3540845622982687, "grad_norm": 1.397393822669983, "learning_rate": 4.424407974079807e-05, "loss": 0.4832746505737305, "step": 396030 }, { "epoch": 2.3541440043749366, "grad_norm": 1.4220407009124756, "learning_rate": 4.423982973215675e-05, "loss": 0.44754552841186523, "step": 396040 }, { "epoch": 2.354203446451605, "grad_norm": 1.1036456823349, "learning_rate": 4.4235580038090576e-05, "loss": 0.4705205917358398, "step": 396050 }, { "epoch": 2.3542628885282735, "grad_norm": 1.4410195350646973, "learning_rate": 4.4231330658619874e-05, "loss": 0.47767324447631837, "step": 396060 }, { "epoch": 2.354322330604942, "grad_norm": 1.2668864727020264, "learning_rate": 4.422708159376505e-05, "loss": 0.5303667068481446, "step": 396070 }, { "epoch": 2.3543817726816103, "grad_norm": 1.3530133962631226, "learning_rate": 4.422283284354634e-05, "loss": 0.4827426910400391, "step": 396080 }, { "epoch": 2.3544412147582787, "grad_norm": 1.2703025341033936, "learning_rate": 4.4218584407984085e-05, "loss": 0.4856210708618164, "step": 396090 }, { "epoch": 2.354500656834947, "grad_norm": 1.4582362174987793, "learning_rate": 4.421433628709864e-05, "loss": 0.546131181716919, "step": 396100 }, { "epoch": 2.3545600989116156, "grad_norm": 1.1679435968399048, "learning_rate": 4.4210088480910314e-05, "loss": 0.49251418113708495, "step": 396110 }, { "epoch": 2.354619540988284, "grad_norm": 1.1999574899673462, "learning_rate": 4.42058409894394e-05, "loss": 0.49133949279785155, "step": 396120 }, { "epoch": 2.3546789830649524, "grad_norm": 1.3220100402832031, "learning_rate": 4.42015938127063e-05, "loss": 0.48727855682373045, "step": 396130 }, { "epoch": 2.354738425141621, "grad_norm": 1.106499433517456, "learning_rate": 4.419734695073123e-05, "loss": 0.47537994384765625, "step": 396140 }, { "epoch": 2.354797867218289, "grad_norm": 1.191613793373108, "learning_rate": 4.419310040353456e-05, "loss": 0.5039972305297852, "step": 396150 }, { "epoch": 2.3548573092949576, "grad_norm": 1.3113067150115967, "learning_rate": 4.418885417113656e-05, "loss": 0.4371990203857422, "step": 396160 }, { "epoch": 2.354916751371626, "grad_norm": 1.1179144382476807, "learning_rate": 4.4184608253557604e-05, "loss": 0.5105751991271973, "step": 396170 }, { "epoch": 2.3549761934482945, "grad_norm": 1.6057480573654175, "learning_rate": 4.418036265081797e-05, "loss": 0.47248249053955077, "step": 396180 }, { "epoch": 2.355035635524963, "grad_norm": 1.401376485824585, "learning_rate": 4.417611736293798e-05, "loss": 0.49690613746643064, "step": 396190 }, { "epoch": 2.3550950776016313, "grad_norm": 1.04927659034729, "learning_rate": 4.417187238993793e-05, "loss": 0.45438218116760254, "step": 396200 }, { "epoch": 2.3551545196782993, "grad_norm": 1.342079997062683, "learning_rate": 4.416762773183812e-05, "loss": 0.5291461944580078, "step": 396210 }, { "epoch": 2.355213961754968, "grad_norm": 1.550441861152649, "learning_rate": 4.4163383388658843e-05, "loss": 0.4654085159301758, "step": 396220 }, { "epoch": 2.355273403831636, "grad_norm": 1.1058897972106934, "learning_rate": 4.4159139360420456e-05, "loss": 0.46674270629882814, "step": 396230 }, { "epoch": 2.3553328459083045, "grad_norm": 1.309491515159607, "learning_rate": 4.415489564714322e-05, "loss": 0.46869335174560545, "step": 396240 }, { "epoch": 2.355392287984973, "grad_norm": 1.1881181001663208, "learning_rate": 4.415065224884746e-05, "loss": 0.48981781005859376, "step": 396250 }, { "epoch": 2.3554517300616413, "grad_norm": 1.3331104516983032, "learning_rate": 4.414640916555345e-05, "loss": 0.5081154346466065, "step": 396260 }, { "epoch": 2.3555111721383097, "grad_norm": 1.1277554035186768, "learning_rate": 4.414216639728149e-05, "loss": 0.5055590629577636, "step": 396270 }, { "epoch": 2.355570614214978, "grad_norm": 1.1352028846740723, "learning_rate": 4.41379239440519e-05, "loss": 0.4931847095489502, "step": 396280 }, { "epoch": 2.3556300562916466, "grad_norm": 1.4146760702133179, "learning_rate": 4.413368180588491e-05, "loss": 0.505453634262085, "step": 396290 }, { "epoch": 2.355689498368315, "grad_norm": 0.9879881739616394, "learning_rate": 4.4129439982800895e-05, "loss": 0.4746557235717773, "step": 396300 }, { "epoch": 2.3557489404449834, "grad_norm": 1.652153730392456, "learning_rate": 4.412519847482012e-05, "loss": 0.5171086311340332, "step": 396310 }, { "epoch": 2.355808382521652, "grad_norm": 1.3124574422836304, "learning_rate": 4.412095728196286e-05, "loss": 0.41539525985717773, "step": 396320 }, { "epoch": 2.3558678245983202, "grad_norm": 1.3056674003601074, "learning_rate": 4.411671640424942e-05, "loss": 0.4477597713470459, "step": 396330 }, { "epoch": 2.3559272666749886, "grad_norm": 1.3147094249725342, "learning_rate": 4.4112475841700075e-05, "loss": 0.4960176467895508, "step": 396340 }, { "epoch": 2.355986708751657, "grad_norm": 1.583646297454834, "learning_rate": 4.410823559433508e-05, "loss": 0.4991201400756836, "step": 396350 }, { "epoch": 2.3560461508283255, "grad_norm": 1.138183832168579, "learning_rate": 4.410399566217478e-05, "loss": 0.4869040012359619, "step": 396360 }, { "epoch": 2.356105592904994, "grad_norm": 1.6206144094467163, "learning_rate": 4.409975604523944e-05, "loss": 0.4911752700805664, "step": 396370 }, { "epoch": 2.3561650349816623, "grad_norm": 1.4942935705184937, "learning_rate": 4.409551674354933e-05, "loss": 0.4875323295593262, "step": 396380 }, { "epoch": 2.3562244770583307, "grad_norm": 1.2553181648254395, "learning_rate": 4.4091277757124716e-05, "loss": 0.48393878936767576, "step": 396390 }, { "epoch": 2.3562839191349987, "grad_norm": 1.3557007312774658, "learning_rate": 4.408703908598589e-05, "loss": 0.5318759441375732, "step": 396400 }, { "epoch": 2.356343361211667, "grad_norm": 1.0862318277359009, "learning_rate": 4.408280073015314e-05, "loss": 0.4577538013458252, "step": 396410 }, { "epoch": 2.3564028032883355, "grad_norm": 1.3532252311706543, "learning_rate": 4.4078562689646695e-05, "loss": 0.5280391216278076, "step": 396420 }, { "epoch": 2.356462245365004, "grad_norm": 1.3270306587219238, "learning_rate": 4.407432496448689e-05, "loss": 0.4713314056396484, "step": 396430 }, { "epoch": 2.3565216874416723, "grad_norm": 1.1160932779312134, "learning_rate": 4.407008755469399e-05, "loss": 0.4598647117614746, "step": 396440 }, { "epoch": 2.3565811295183408, "grad_norm": 1.2163463830947876, "learning_rate": 4.406585046028822e-05, "loss": 0.45305376052856444, "step": 396450 }, { "epoch": 2.356640571595009, "grad_norm": 1.323405146598816, "learning_rate": 4.4061613681289884e-05, "loss": 0.5131783485412598, "step": 396460 }, { "epoch": 2.3567000136716776, "grad_norm": 1.2443674802780151, "learning_rate": 4.4057377217719234e-05, "loss": 0.440522289276123, "step": 396470 }, { "epoch": 2.356759455748346, "grad_norm": 1.1346157789230347, "learning_rate": 4.405314106959652e-05, "loss": 0.4821768760681152, "step": 396480 }, { "epoch": 2.3568188978250144, "grad_norm": 1.4949935674667358, "learning_rate": 4.404890523694205e-05, "loss": 0.5098860263824463, "step": 396490 }, { "epoch": 2.356878339901683, "grad_norm": 1.6062859296798706, "learning_rate": 4.40446697197761e-05, "loss": 0.529294776916504, "step": 396500 }, { "epoch": 2.3569377819783512, "grad_norm": 1.249261736869812, "learning_rate": 4.4040434518118845e-05, "loss": 0.49869279861450194, "step": 396510 }, { "epoch": 2.3569972240550197, "grad_norm": 1.3111870288848877, "learning_rate": 4.4036199631990595e-05, "loss": 0.46968393325805663, "step": 396520 }, { "epoch": 2.357056666131688, "grad_norm": 1.6244343519210815, "learning_rate": 4.403196506141163e-05, "loss": 0.46448240280151365, "step": 396530 }, { "epoch": 2.3571161082083565, "grad_norm": 1.4803545475006104, "learning_rate": 4.402773080640217e-05, "loss": 0.4648478031158447, "step": 396540 }, { "epoch": 2.357175550285025, "grad_norm": 1.2603811025619507, "learning_rate": 4.402349686698247e-05, "loss": 0.5227588653564453, "step": 396550 }, { "epoch": 2.3572349923616933, "grad_norm": 1.3480401039123535, "learning_rate": 4.401926324317285e-05, "loss": 0.4977245330810547, "step": 396560 }, { "epoch": 2.3572944344383617, "grad_norm": 1.1631320714950562, "learning_rate": 4.401502993499349e-05, "loss": 0.46019792556762695, "step": 396570 }, { "epoch": 2.35735387651503, "grad_norm": 1.4152100086212158, "learning_rate": 4.401079694246464e-05, "loss": 0.5322924613952636, "step": 396580 }, { "epoch": 2.357413318591698, "grad_norm": 1.601635456085205, "learning_rate": 4.400656426560659e-05, "loss": 0.5028185844421387, "step": 396590 }, { "epoch": 2.3574727606683665, "grad_norm": 1.6153606176376343, "learning_rate": 4.400233190443958e-05, "loss": 0.5418656349182129, "step": 396600 }, { "epoch": 2.357532202745035, "grad_norm": 1.581407904624939, "learning_rate": 4.399809985898381e-05, "loss": 0.4699605941772461, "step": 396610 }, { "epoch": 2.3575916448217034, "grad_norm": 1.3386967182159424, "learning_rate": 4.399386812925961e-05, "loss": 0.4540553569793701, "step": 396620 }, { "epoch": 2.3576510868983718, "grad_norm": 1.3959120512008667, "learning_rate": 4.398963671528715e-05, "loss": 0.47767138481140137, "step": 396630 }, { "epoch": 2.35771052897504, "grad_norm": 1.4735007286071777, "learning_rate": 4.398540561708669e-05, "loss": 0.4679385185241699, "step": 396640 }, { "epoch": 2.3577699710517086, "grad_norm": 1.6226317882537842, "learning_rate": 4.398117483467847e-05, "loss": 0.47866597175598147, "step": 396650 }, { "epoch": 2.357829413128377, "grad_norm": 1.6637327671051025, "learning_rate": 4.3976944368082744e-05, "loss": 0.522184419631958, "step": 396660 }, { "epoch": 2.3578888552050454, "grad_norm": 1.4726941585540771, "learning_rate": 4.397271421731975e-05, "loss": 0.5261188983917237, "step": 396670 }, { "epoch": 2.357948297281714, "grad_norm": 1.1766586303710938, "learning_rate": 4.39684843824097e-05, "loss": 0.46573805809020996, "step": 396680 }, { "epoch": 2.3580077393583823, "grad_norm": 1.4247105121612549, "learning_rate": 4.396425486337285e-05, "loss": 0.4693127155303955, "step": 396690 }, { "epoch": 2.3580671814350507, "grad_norm": 1.3606618642807007, "learning_rate": 4.3960025660229434e-05, "loss": 0.47842798233032224, "step": 396700 }, { "epoch": 2.358126623511719, "grad_norm": 1.1415940523147583, "learning_rate": 4.395579677299964e-05, "loss": 0.45932779312133787, "step": 396710 }, { "epoch": 2.3581860655883875, "grad_norm": 1.5961041450500488, "learning_rate": 4.395156820170374e-05, "loss": 0.49554834365844724, "step": 396720 }, { "epoch": 2.358245507665056, "grad_norm": 1.3519197702407837, "learning_rate": 4.3947339946361965e-05, "loss": 0.5022292613983155, "step": 396730 }, { "epoch": 2.3583049497417243, "grad_norm": 1.2652277946472168, "learning_rate": 4.3943112006994536e-05, "loss": 0.43953981399536135, "step": 396740 }, { "epoch": 2.3583643918183927, "grad_norm": 1.4909493923187256, "learning_rate": 4.393888438362166e-05, "loss": 0.47213311195373536, "step": 396750 }, { "epoch": 2.3584238338950607, "grad_norm": 0.9668764472007751, "learning_rate": 4.3934657076263574e-05, "loss": 0.4616520881652832, "step": 396760 }, { "epoch": 2.3584832759717296, "grad_norm": 1.1664389371871948, "learning_rate": 4.39304300849405e-05, "loss": 0.5205987930297852, "step": 396770 }, { "epoch": 2.3585427180483975, "grad_norm": 0.8746479749679565, "learning_rate": 4.3926203409672636e-05, "loss": 0.42612333297729493, "step": 396780 }, { "epoch": 2.358602160125066, "grad_norm": 1.2891076803207397, "learning_rate": 4.3921977050480244e-05, "loss": 0.4883540153503418, "step": 396790 }, { "epoch": 2.3586616022017344, "grad_norm": 1.018781304359436, "learning_rate": 4.391775100738351e-05, "loss": 0.5005340576171875, "step": 396800 }, { "epoch": 2.358721044278403, "grad_norm": 1.5832843780517578, "learning_rate": 4.391352528040268e-05, "loss": 0.4418461799621582, "step": 396810 }, { "epoch": 2.358780486355071, "grad_norm": 1.064721703529358, "learning_rate": 4.390929986955794e-05, "loss": 0.4632104873657227, "step": 396820 }, { "epoch": 2.3588399284317396, "grad_norm": 0.9908429980278015, "learning_rate": 4.3905074774869504e-05, "loss": 0.4676091194152832, "step": 396830 }, { "epoch": 2.358899370508408, "grad_norm": 0.9811649322509766, "learning_rate": 4.3900849996357563e-05, "loss": 0.4665332794189453, "step": 396840 }, { "epoch": 2.3589588125850764, "grad_norm": 2.359999179840088, "learning_rate": 4.389662553404239e-05, "loss": 0.49404163360595704, "step": 396850 }, { "epoch": 2.359018254661745, "grad_norm": 1.3359265327453613, "learning_rate": 4.389240138794415e-05, "loss": 0.4828354358673096, "step": 396860 }, { "epoch": 2.3590776967384133, "grad_norm": 1.3894145488739014, "learning_rate": 4.388817755808306e-05, "loss": 0.463482141494751, "step": 396870 }, { "epoch": 2.3591371388150817, "grad_norm": 1.6742693185806274, "learning_rate": 4.388395404447932e-05, "loss": 0.505410099029541, "step": 396880 }, { "epoch": 2.35919658089175, "grad_norm": 1.4694644212722778, "learning_rate": 4.3879730847153146e-05, "loss": 0.5103823184967041, "step": 396890 }, { "epoch": 2.3592560229684185, "grad_norm": 1.2592668533325195, "learning_rate": 4.387550796612472e-05, "loss": 0.4526559829711914, "step": 396900 }, { "epoch": 2.359315465045087, "grad_norm": 1.5617742538452148, "learning_rate": 4.387128540141423e-05, "loss": 0.4477910041809082, "step": 396910 }, { "epoch": 2.3593749071217553, "grad_norm": 1.1992461681365967, "learning_rate": 4.386706315304193e-05, "loss": 0.49784293174743655, "step": 396920 }, { "epoch": 2.3594343491984238, "grad_norm": 1.3563822507858276, "learning_rate": 4.386284122102799e-05, "loss": 0.4678781986236572, "step": 396930 }, { "epoch": 2.359493791275092, "grad_norm": 1.1790529489517212, "learning_rate": 4.38586196053926e-05, "loss": 0.5451380729675293, "step": 396940 }, { "epoch": 2.35955323335176, "grad_norm": 1.2615031003952026, "learning_rate": 4.385439830615596e-05, "loss": 0.47313432693481444, "step": 396950 }, { "epoch": 2.359612675428429, "grad_norm": 1.2688556909561157, "learning_rate": 4.385017732333826e-05, "loss": 0.5116481781005859, "step": 396960 }, { "epoch": 2.359672117505097, "grad_norm": 1.3557285070419312, "learning_rate": 4.384595665695966e-05, "loss": 0.523552942276001, "step": 396970 }, { "epoch": 2.3597315595817654, "grad_norm": 1.206825613975525, "learning_rate": 4.384173630704043e-05, "loss": 0.48447341918945314, "step": 396980 }, { "epoch": 2.359791001658434, "grad_norm": 1.2001264095306396, "learning_rate": 4.383751627360069e-05, "loss": 0.5036022186279296, "step": 396990 }, { "epoch": 2.359850443735102, "grad_norm": 1.3293081521987915, "learning_rate": 4.383329655666069e-05, "loss": 0.4645254135131836, "step": 397000 }, { "epoch": 2.3599098858117706, "grad_norm": 1.4371256828308105, "learning_rate": 4.382907715624052e-05, "loss": 0.4750481605529785, "step": 397010 }, { "epoch": 2.359969327888439, "grad_norm": 1.7516568899154663, "learning_rate": 4.382485807236044e-05, "loss": 0.5055339813232422, "step": 397020 }, { "epoch": 2.3600287699651075, "grad_norm": 1.364571213722229, "learning_rate": 4.3820639305040625e-05, "loss": 0.45516490936279297, "step": 397030 }, { "epoch": 2.360088212041776, "grad_norm": 1.1437970399856567, "learning_rate": 4.381642085430121e-05, "loss": 0.47079715728759763, "step": 397040 }, { "epoch": 2.3601476541184443, "grad_norm": 1.1740919351577759, "learning_rate": 4.3812202720162434e-05, "loss": 0.4826016426086426, "step": 397050 }, { "epoch": 2.3602070961951127, "grad_norm": 1.535228967666626, "learning_rate": 4.380798490264448e-05, "loss": 0.4738619327545166, "step": 397060 }, { "epoch": 2.360266538271781, "grad_norm": 1.501442551612854, "learning_rate": 4.380376740176744e-05, "loss": 0.5340006828308106, "step": 397070 }, { "epoch": 2.3603259803484495, "grad_norm": 1.2126855850219727, "learning_rate": 4.379955021755157e-05, "loss": 0.4722477436065674, "step": 397080 }, { "epoch": 2.360385422425118, "grad_norm": 1.4089736938476562, "learning_rate": 4.379533335001701e-05, "loss": 0.4916670799255371, "step": 397090 }, { "epoch": 2.3604448645017864, "grad_norm": 1.4505456686019897, "learning_rate": 4.3791116799183926e-05, "loss": 0.47008304595947265, "step": 397100 }, { "epoch": 2.360504306578455, "grad_norm": 1.6044764518737793, "learning_rate": 4.378690056507255e-05, "loss": 0.5404854774475097, "step": 397110 }, { "epoch": 2.360563748655123, "grad_norm": 1.2468940019607544, "learning_rate": 4.3782684647702974e-05, "loss": 0.4997245311737061, "step": 397120 }, { "epoch": 2.3606231907317916, "grad_norm": 1.3236584663391113, "learning_rate": 4.3778469047095394e-05, "loss": 0.44502010345458987, "step": 397130 }, { "epoch": 2.3606826328084596, "grad_norm": 1.4432164430618286, "learning_rate": 4.377425376326996e-05, "loss": 0.4676527976989746, "step": 397140 }, { "epoch": 2.360742074885128, "grad_norm": 1.260218858718872, "learning_rate": 4.377003879624688e-05, "loss": 0.4912175178527832, "step": 397150 }, { "epoch": 2.3608015169617964, "grad_norm": 1.7430450916290283, "learning_rate": 4.3765824146046274e-05, "loss": 0.4852665901184082, "step": 397160 }, { "epoch": 2.360860959038465, "grad_norm": 1.4896702766418457, "learning_rate": 4.376160981268833e-05, "loss": 0.48995265960693357, "step": 397170 }, { "epoch": 2.3609204011151332, "grad_norm": 1.4690203666687012, "learning_rate": 4.37573957961932e-05, "loss": 0.4699875831604004, "step": 397180 }, { "epoch": 2.3609798431918017, "grad_norm": 1.515944242477417, "learning_rate": 4.375318209658104e-05, "loss": 0.508678388595581, "step": 397190 }, { "epoch": 2.36103928526847, "grad_norm": 1.3019893169403076, "learning_rate": 4.3748968713871965e-05, "loss": 0.5001105785369873, "step": 397200 }, { "epoch": 2.3610987273451385, "grad_norm": 1.2751001119613647, "learning_rate": 4.374475564808621e-05, "loss": 0.4693248748779297, "step": 397210 }, { "epoch": 2.361158169421807, "grad_norm": 1.4987733364105225, "learning_rate": 4.3740542899243896e-05, "loss": 0.516594123840332, "step": 397220 }, { "epoch": 2.3612176114984753, "grad_norm": 1.70633864402771, "learning_rate": 4.373633046736516e-05, "loss": 0.48447360992431643, "step": 397230 }, { "epoch": 2.3612770535751437, "grad_norm": 0.8761933445930481, "learning_rate": 4.373211835247017e-05, "loss": 0.46865644454956057, "step": 397240 }, { "epoch": 2.361336495651812, "grad_norm": 1.0895060300827026, "learning_rate": 4.3727906554579076e-05, "loss": 0.47257232666015625, "step": 397250 }, { "epoch": 2.3613959377284806, "grad_norm": 1.165604591369629, "learning_rate": 4.3723695073712015e-05, "loss": 0.44948515892028806, "step": 397260 }, { "epoch": 2.361455379805149, "grad_norm": 1.259468674659729, "learning_rate": 4.37194839098891e-05, "loss": 0.46534223556518556, "step": 397270 }, { "epoch": 2.3615148218818174, "grad_norm": 1.3863950967788696, "learning_rate": 4.3715273063130556e-05, "loss": 0.4404780864715576, "step": 397280 }, { "epoch": 2.361574263958486, "grad_norm": 0.9924473762512207, "learning_rate": 4.3711062533456476e-05, "loss": 0.48393831253051756, "step": 397290 }, { "epoch": 2.361633706035154, "grad_norm": 1.2082269191741943, "learning_rate": 4.370685232088701e-05, "loss": 0.5221036434173584, "step": 397300 }, { "epoch": 2.3616931481118226, "grad_norm": 1.325639247894287, "learning_rate": 4.37026424254423e-05, "loss": 0.4664128303527832, "step": 397310 }, { "epoch": 2.361752590188491, "grad_norm": 1.2359906435012817, "learning_rate": 4.369843284714248e-05, "loss": 0.47820148468017576, "step": 397320 }, { "epoch": 2.361812032265159, "grad_norm": 1.1023869514465332, "learning_rate": 4.369422358600766e-05, "loss": 0.4837764263153076, "step": 397330 }, { "epoch": 2.3618714743418274, "grad_norm": 1.3729976415634155, "learning_rate": 4.3690014642058043e-05, "loss": 0.49156980514526366, "step": 397340 }, { "epoch": 2.361930916418496, "grad_norm": 1.4622738361358643, "learning_rate": 4.368580601531371e-05, "loss": 0.4821326732635498, "step": 397350 }, { "epoch": 2.3619903584951643, "grad_norm": 1.4740091562271118, "learning_rate": 4.368159770579482e-05, "loss": 0.5047216415405273, "step": 397360 }, { "epoch": 2.3620498005718327, "grad_norm": 1.1821482181549072, "learning_rate": 4.367738971352149e-05, "loss": 0.4407795906066895, "step": 397370 }, { "epoch": 2.362109242648501, "grad_norm": 1.4816033840179443, "learning_rate": 4.367318203851386e-05, "loss": 0.5076990127563477, "step": 397380 }, { "epoch": 2.3621686847251695, "grad_norm": 1.514746069908142, "learning_rate": 4.366897468079204e-05, "loss": 0.5117969512939453, "step": 397390 }, { "epoch": 2.362228126801838, "grad_norm": 1.9021574258804321, "learning_rate": 4.366476764037614e-05, "loss": 0.5145853996276856, "step": 397400 }, { "epoch": 2.3622875688785063, "grad_norm": 1.321483850479126, "learning_rate": 4.3660560917286345e-05, "loss": 0.5348947048187256, "step": 397410 }, { "epoch": 2.3623470109551747, "grad_norm": 1.2968521118164062, "learning_rate": 4.365635451154275e-05, "loss": 0.42512941360473633, "step": 397420 }, { "epoch": 2.362406453031843, "grad_norm": 1.2892789840698242, "learning_rate": 4.3652148423165476e-05, "loss": 0.5075668811798095, "step": 397430 }, { "epoch": 2.3624658951085116, "grad_norm": 1.3446776866912842, "learning_rate": 4.364794265217463e-05, "loss": 0.4958141326904297, "step": 397440 }, { "epoch": 2.36252533718518, "grad_norm": 1.9095855951309204, "learning_rate": 4.364373719859035e-05, "loss": 0.49192209243774415, "step": 397450 }, { "epoch": 2.3625847792618484, "grad_norm": 1.2843329906463623, "learning_rate": 4.363953206243272e-05, "loss": 0.5109565734863282, "step": 397460 }, { "epoch": 2.362644221338517, "grad_norm": 1.3128001689910889, "learning_rate": 4.36353272437219e-05, "loss": 0.508013391494751, "step": 397470 }, { "epoch": 2.3627036634151852, "grad_norm": 1.4317290782928467, "learning_rate": 4.3631122742478e-05, "loss": 0.48145856857299807, "step": 397480 }, { "epoch": 2.3627631054918536, "grad_norm": 1.2185064554214478, "learning_rate": 4.362691855872114e-05, "loss": 0.44919443130493164, "step": 397490 }, { "epoch": 2.3628225475685216, "grad_norm": 1.344788670539856, "learning_rate": 4.362271469247136e-05, "loss": 0.44495620727539065, "step": 397500 }, { "epoch": 2.3628819896451905, "grad_norm": 1.1869741678237915, "learning_rate": 4.361851114374884e-05, "loss": 0.4716972351074219, "step": 397510 }, { "epoch": 2.3629414317218584, "grad_norm": 1.3372570276260376, "learning_rate": 4.3614307912573666e-05, "loss": 0.48905372619628906, "step": 397520 }, { "epoch": 2.363000873798527, "grad_norm": 1.9045846462249756, "learning_rate": 4.3610104998965933e-05, "loss": 0.5399840354919434, "step": 397530 }, { "epoch": 2.3630603158751953, "grad_norm": 1.558410882949829, "learning_rate": 4.360590240294578e-05, "loss": 0.5304390907287597, "step": 397540 }, { "epoch": 2.3631197579518637, "grad_norm": 1.0806541442871094, "learning_rate": 4.360170012453332e-05, "loss": 0.44631381034851075, "step": 397550 }, { "epoch": 2.363179200028532, "grad_norm": 1.4357069730758667, "learning_rate": 4.359749816374858e-05, "loss": 0.4917901992797852, "step": 397560 }, { "epoch": 2.3632386421052005, "grad_norm": 1.2467097043991089, "learning_rate": 4.359329652061173e-05, "loss": 0.44586610794067383, "step": 397570 }, { "epoch": 2.363298084181869, "grad_norm": 1.1914533376693726, "learning_rate": 4.3589095195142844e-05, "loss": 0.4619548797607422, "step": 397580 }, { "epoch": 2.3633575262585373, "grad_norm": 0.9803727269172668, "learning_rate": 4.358489418736202e-05, "loss": 0.47336521148681643, "step": 397590 }, { "epoch": 2.3634169683352058, "grad_norm": 1.3853563070297241, "learning_rate": 4.358069349728934e-05, "loss": 0.45461606979370117, "step": 397600 }, { "epoch": 2.363476410411874, "grad_norm": 1.2262130975723267, "learning_rate": 4.357649312494497e-05, "loss": 0.5086534976959228, "step": 397610 }, { "epoch": 2.3635358524885426, "grad_norm": 1.5316635370254517, "learning_rate": 4.357229307034892e-05, "loss": 0.4966423511505127, "step": 397620 }, { "epoch": 2.363595294565211, "grad_norm": 1.5101248025894165, "learning_rate": 4.356809333352128e-05, "loss": 0.4834609031677246, "step": 397630 }, { "epoch": 2.3636547366418794, "grad_norm": 1.398202657699585, "learning_rate": 4.35638939144822e-05, "loss": 0.471882963180542, "step": 397640 }, { "epoch": 2.363714178718548, "grad_norm": 1.573649287223816, "learning_rate": 4.355969481325174e-05, "loss": 0.4597020626068115, "step": 397650 }, { "epoch": 2.3637736207952162, "grad_norm": 1.0664230585098267, "learning_rate": 4.3555496029849965e-05, "loss": 0.4741697311401367, "step": 397660 }, { "epoch": 2.3638330628718847, "grad_norm": 1.4680204391479492, "learning_rate": 4.355129756429703e-05, "loss": 0.5367178916931152, "step": 397670 }, { "epoch": 2.363892504948553, "grad_norm": 1.4303780794143677, "learning_rate": 4.3547099416612944e-05, "loss": 0.5363783836364746, "step": 397680 }, { "epoch": 2.363951947025221, "grad_norm": 1.1004550457000732, "learning_rate": 4.354290158681781e-05, "loss": 0.4603894233703613, "step": 397690 }, { "epoch": 2.36401138910189, "grad_norm": 1.567478060722351, "learning_rate": 4.353870407493173e-05, "loss": 0.5361542224884033, "step": 397700 }, { "epoch": 2.364070831178558, "grad_norm": 1.3594543933868408, "learning_rate": 4.353450688097477e-05, "loss": 0.4984453201293945, "step": 397710 }, { "epoch": 2.3641302732552263, "grad_norm": 1.1720224618911743, "learning_rate": 4.353031000496699e-05, "loss": 0.5279303550720215, "step": 397720 }, { "epoch": 2.3641897153318947, "grad_norm": 1.252498984336853, "learning_rate": 4.352611344692851e-05, "loss": 0.5140758991241455, "step": 397730 }, { "epoch": 2.364249157408563, "grad_norm": 1.409842848777771, "learning_rate": 4.352191720687936e-05, "loss": 0.47235960960388185, "step": 397740 }, { "epoch": 2.3643085994852315, "grad_norm": 1.2363768815994263, "learning_rate": 4.3517721284839646e-05, "loss": 0.5348925590515137, "step": 397750 }, { "epoch": 2.3643680415619, "grad_norm": 1.2830820083618164, "learning_rate": 4.35135256808294e-05, "loss": 0.5146636009216309, "step": 397760 }, { "epoch": 2.3644274836385684, "grad_norm": 1.767288088798523, "learning_rate": 4.3509330394868744e-05, "loss": 0.4447762489318848, "step": 397770 }, { "epoch": 2.3644869257152368, "grad_norm": 1.5826404094696045, "learning_rate": 4.350513542697773e-05, "loss": 0.5257586479187012, "step": 397780 }, { "epoch": 2.364546367791905, "grad_norm": 1.2103191614151, "learning_rate": 4.3500940777176404e-05, "loss": 0.4774728775024414, "step": 397790 }, { "epoch": 2.3646058098685736, "grad_norm": 1.4017630815505981, "learning_rate": 4.349674644548485e-05, "loss": 0.49005556106567383, "step": 397800 }, { "epoch": 2.364665251945242, "grad_norm": 0.8605320453643799, "learning_rate": 4.3492552431923126e-05, "loss": 0.42198734283447265, "step": 397810 }, { "epoch": 2.3647246940219104, "grad_norm": 1.0015207529067993, "learning_rate": 4.348835873651127e-05, "loss": 0.5163105487823486, "step": 397820 }, { "epoch": 2.364784136098579, "grad_norm": 1.5736652612686157, "learning_rate": 4.3484165359269394e-05, "loss": 0.49396114349365233, "step": 397830 }, { "epoch": 2.3648435781752473, "grad_norm": 1.1480112075805664, "learning_rate": 4.3479972300217534e-05, "loss": 0.481765604019165, "step": 397840 }, { "epoch": 2.3649030202519157, "grad_norm": 0.7897409796714783, "learning_rate": 4.347577955937575e-05, "loss": 0.46982803344726565, "step": 397850 }, { "epoch": 2.364962462328584, "grad_norm": 1.8509395122528076, "learning_rate": 4.34715871367641e-05, "loss": 0.5221219539642334, "step": 397860 }, { "epoch": 2.3650219044052525, "grad_norm": 1.358723521232605, "learning_rate": 4.3467395032402625e-05, "loss": 0.48288803100585936, "step": 397870 }, { "epoch": 2.3650813464819205, "grad_norm": 1.289841890335083, "learning_rate": 4.34632032463114e-05, "loss": 0.4649263858795166, "step": 397880 }, { "epoch": 2.365140788558589, "grad_norm": 1.3878177404403687, "learning_rate": 4.345901177851043e-05, "loss": 0.49669804573059084, "step": 397890 }, { "epoch": 2.3652002306352573, "grad_norm": 1.0644657611846924, "learning_rate": 4.3454820629019824e-05, "loss": 0.4707171440124512, "step": 397900 }, { "epoch": 2.3652596727119257, "grad_norm": 1.4732048511505127, "learning_rate": 4.345062979785963e-05, "loss": 0.4914194107055664, "step": 397910 }, { "epoch": 2.365319114788594, "grad_norm": 1.269865870475769, "learning_rate": 4.344643928504986e-05, "loss": 0.5142125129699707, "step": 397920 }, { "epoch": 2.3653785568652625, "grad_norm": 1.1815871000289917, "learning_rate": 4.344224909061057e-05, "loss": 0.4933218002319336, "step": 397930 }, { "epoch": 2.365437998941931, "grad_norm": 1.6587300300598145, "learning_rate": 4.343805921456182e-05, "loss": 0.4675806999206543, "step": 397940 }, { "epoch": 2.3654974410185994, "grad_norm": 1.466073751449585, "learning_rate": 4.343386965692361e-05, "loss": 0.4991630554199219, "step": 397950 }, { "epoch": 2.365556883095268, "grad_norm": 1.2726835012435913, "learning_rate": 4.342968041771605e-05, "loss": 0.4930730819702148, "step": 397960 }, { "epoch": 2.365616325171936, "grad_norm": 1.474545955657959, "learning_rate": 4.342549149695913e-05, "loss": 0.4522669315338135, "step": 397970 }, { "epoch": 2.3656757672486046, "grad_norm": 0.9561994075775146, "learning_rate": 4.3421302894672936e-05, "loss": 0.43555798530578616, "step": 397980 }, { "epoch": 2.365735209325273, "grad_norm": 1.2278987169265747, "learning_rate": 4.341711461087742e-05, "loss": 0.49542675018310545, "step": 397990 }, { "epoch": 2.3657946514019415, "grad_norm": 1.2065032720565796, "learning_rate": 4.341292664559268e-05, "loss": 0.49038944244384763, "step": 398000 }, { "epoch": 2.36585409347861, "grad_norm": 1.3256055116653442, "learning_rate": 4.340873899883875e-05, "loss": 0.49182848930358886, "step": 398010 }, { "epoch": 2.3659135355552783, "grad_norm": 1.5808115005493164, "learning_rate": 4.340455167063562e-05, "loss": 0.5621545791625977, "step": 398020 }, { "epoch": 2.3659729776319467, "grad_norm": 1.1331549882888794, "learning_rate": 4.340036466100338e-05, "loss": 0.48438525199890137, "step": 398030 }, { "epoch": 2.366032419708615, "grad_norm": 1.3175907135009766, "learning_rate": 4.339617796996206e-05, "loss": 0.5201728820800782, "step": 398040 }, { "epoch": 2.3660918617852835, "grad_norm": 1.2750500440597534, "learning_rate": 4.33919915975316e-05, "loss": 0.47484188079833983, "step": 398050 }, { "epoch": 2.366151303861952, "grad_norm": 1.050260305404663, "learning_rate": 4.3387805543732104e-05, "loss": 0.4992558002471924, "step": 398060 }, { "epoch": 2.36621074593862, "grad_norm": 1.1902248859405518, "learning_rate": 4.338361980858359e-05, "loss": 0.4504560470581055, "step": 398070 }, { "epoch": 2.3662701880152883, "grad_norm": 1.2301913499832153, "learning_rate": 4.3379434392106066e-05, "loss": 0.48789501190185547, "step": 398080 }, { "epoch": 2.3663296300919567, "grad_norm": 1.641709566116333, "learning_rate": 4.337524929431953e-05, "loss": 0.5113600730895996, "step": 398090 }, { "epoch": 2.366389072168625, "grad_norm": 1.485743522644043, "learning_rate": 4.3371064515244074e-05, "loss": 0.4444561004638672, "step": 398100 }, { "epoch": 2.3664485142452936, "grad_norm": 1.1512166261672974, "learning_rate": 4.336688005489965e-05, "loss": 0.48751158714294435, "step": 398110 }, { "epoch": 2.366507956321962, "grad_norm": 1.3953667879104614, "learning_rate": 4.3362695913306266e-05, "loss": 0.48044404983520506, "step": 398120 }, { "epoch": 2.3665673983986304, "grad_norm": 1.807921290397644, "learning_rate": 4.335851209048399e-05, "loss": 0.5002931594848633, "step": 398130 }, { "epoch": 2.366626840475299, "grad_norm": 1.3737760782241821, "learning_rate": 4.335432858645283e-05, "loss": 0.48133258819580077, "step": 398140 }, { "epoch": 2.3666862825519672, "grad_norm": 1.3036178350448608, "learning_rate": 4.3350145401232744e-05, "loss": 0.5278654575347901, "step": 398150 }, { "epoch": 2.3667457246286356, "grad_norm": 1.2007416486740112, "learning_rate": 4.3345962534843834e-05, "loss": 0.4891646385192871, "step": 398160 }, { "epoch": 2.366805166705304, "grad_norm": 1.355189323425293, "learning_rate": 4.334177998730603e-05, "loss": 0.47365331649780273, "step": 398170 }, { "epoch": 2.3668646087819725, "grad_norm": 2.0946836471557617, "learning_rate": 4.3337597758639335e-05, "loss": 0.5287188529968262, "step": 398180 }, { "epoch": 2.366924050858641, "grad_norm": 1.4690443277359009, "learning_rate": 4.333341584886383e-05, "loss": 0.5620304584503174, "step": 398190 }, { "epoch": 2.3669834929353093, "grad_norm": 1.4650427103042603, "learning_rate": 4.332923425799947e-05, "loss": 0.48876094818115234, "step": 398200 }, { "epoch": 2.3670429350119777, "grad_norm": 1.3228508234024048, "learning_rate": 4.332505298606626e-05, "loss": 0.46048460006713865, "step": 398210 }, { "epoch": 2.367102377088646, "grad_norm": 1.2945443391799927, "learning_rate": 4.33208720330842e-05, "loss": 0.5310324668884278, "step": 398220 }, { "epoch": 2.3671618191653145, "grad_norm": 1.3223737478256226, "learning_rate": 4.3316691399073305e-05, "loss": 0.46933460235595703, "step": 398230 }, { "epoch": 2.3672212612419825, "grad_norm": 1.5494338274002075, "learning_rate": 4.3312511084053565e-05, "loss": 0.5271014213562012, "step": 398240 }, { "epoch": 2.3672807033186514, "grad_norm": 1.3007560968399048, "learning_rate": 4.330833108804495e-05, "loss": 0.5547927379608154, "step": 398250 }, { "epoch": 2.3673401453953193, "grad_norm": 1.0816919803619385, "learning_rate": 4.330415141106752e-05, "loss": 0.47092623710632325, "step": 398260 }, { "epoch": 2.3673995874719878, "grad_norm": 1.2321693897247314, "learning_rate": 4.3299972053141226e-05, "loss": 0.5348631858825683, "step": 398270 }, { "epoch": 2.367459029548656, "grad_norm": 1.2668126821517944, "learning_rate": 4.329579301428607e-05, "loss": 0.5231646060943603, "step": 398280 }, { "epoch": 2.3675184716253246, "grad_norm": 1.2527340650558472, "learning_rate": 4.3291614294522045e-05, "loss": 0.5470282554626464, "step": 398290 }, { "epoch": 2.367577913701993, "grad_norm": 1.3939985036849976, "learning_rate": 4.328743589386912e-05, "loss": 0.4937331199645996, "step": 398300 }, { "epoch": 2.3676373557786614, "grad_norm": 1.3576850891113281, "learning_rate": 4.328325781234729e-05, "loss": 0.46047086715698243, "step": 398310 }, { "epoch": 2.36769679785533, "grad_norm": 1.040946125984192, "learning_rate": 4.327908004997657e-05, "loss": 0.4567592620849609, "step": 398320 }, { "epoch": 2.3677562399319982, "grad_norm": 1.4148046970367432, "learning_rate": 4.327490260677693e-05, "loss": 0.49164762496948244, "step": 398330 }, { "epoch": 2.3678156820086667, "grad_norm": 1.0872678756713867, "learning_rate": 4.327072548276835e-05, "loss": 0.44330949783325196, "step": 398340 }, { "epoch": 2.367875124085335, "grad_norm": 1.3625807762145996, "learning_rate": 4.326654867797082e-05, "loss": 0.4774190902709961, "step": 398350 }, { "epoch": 2.3679345661620035, "grad_norm": 1.2956631183624268, "learning_rate": 4.32623721924043e-05, "loss": 0.4813380241394043, "step": 398360 }, { "epoch": 2.367994008238672, "grad_norm": 1.2845115661621094, "learning_rate": 4.325819602608877e-05, "loss": 0.5060573101043702, "step": 398370 }, { "epoch": 2.3680534503153403, "grad_norm": 1.0036489963531494, "learning_rate": 4.3254020179044216e-05, "loss": 0.4355757713317871, "step": 398380 }, { "epoch": 2.3681128923920087, "grad_norm": 1.4256770610809326, "learning_rate": 4.324984465129064e-05, "loss": 0.5297902584075928, "step": 398390 }, { "epoch": 2.368172334468677, "grad_norm": 0.9174437522888184, "learning_rate": 4.324566944284798e-05, "loss": 0.5130282402038574, "step": 398400 }, { "epoch": 2.3682317765453456, "grad_norm": 1.5028374195098877, "learning_rate": 4.324149455373623e-05, "loss": 0.47232661247253416, "step": 398410 }, { "epoch": 2.368291218622014, "grad_norm": 1.454149603843689, "learning_rate": 4.323731998397536e-05, "loss": 0.5198101997375488, "step": 398420 }, { "epoch": 2.368350660698682, "grad_norm": 1.5068773031234741, "learning_rate": 4.3233145733585326e-05, "loss": 0.5223301410675049, "step": 398430 }, { "epoch": 2.368410102775351, "grad_norm": 1.2703275680541992, "learning_rate": 4.3228971802586096e-05, "loss": 0.5083806991577149, "step": 398440 }, { "epoch": 2.3684695448520188, "grad_norm": 0.8529168367385864, "learning_rate": 4.3224798190997616e-05, "loss": 0.44750323295593264, "step": 398450 }, { "epoch": 2.368528986928687, "grad_norm": 1.4971774816513062, "learning_rate": 4.322062489883992e-05, "loss": 0.5222850322723389, "step": 398460 }, { "epoch": 2.3685884290053556, "grad_norm": 1.6871917247772217, "learning_rate": 4.321645192613292e-05, "loss": 0.5250130653381347, "step": 398470 }, { "epoch": 2.368647871082024, "grad_norm": 1.4593299627304077, "learning_rate": 4.3212279272896596e-05, "loss": 0.5099035263061523, "step": 398480 }, { "epoch": 2.3687073131586924, "grad_norm": 1.5535552501678467, "learning_rate": 4.320810693915089e-05, "loss": 0.4557779312133789, "step": 398490 }, { "epoch": 2.368766755235361, "grad_norm": 1.2433384656906128, "learning_rate": 4.320393492491578e-05, "loss": 0.45904932022094724, "step": 398500 }, { "epoch": 2.3688261973120293, "grad_norm": 1.4519243240356445, "learning_rate": 4.3199763230211186e-05, "loss": 0.5032468795776367, "step": 398510 }, { "epoch": 2.3688856393886977, "grad_norm": 1.5026895999908447, "learning_rate": 4.319559185505714e-05, "loss": 0.5339945793151856, "step": 398520 }, { "epoch": 2.368945081465366, "grad_norm": 1.6265723705291748, "learning_rate": 4.319142079947355e-05, "loss": 0.49189443588256837, "step": 398530 }, { "epoch": 2.3690045235420345, "grad_norm": 1.2724469900131226, "learning_rate": 4.318725006348033e-05, "loss": 0.46426095962524416, "step": 398540 }, { "epoch": 2.369063965618703, "grad_norm": 1.4653042554855347, "learning_rate": 4.31830796470975e-05, "loss": 0.4686314582824707, "step": 398550 }, { "epoch": 2.3691234076953713, "grad_norm": 1.2462451457977295, "learning_rate": 4.317890955034497e-05, "loss": 0.4836014747619629, "step": 398560 }, { "epoch": 2.3691828497720397, "grad_norm": 1.3522216081619263, "learning_rate": 4.317473977324271e-05, "loss": 0.4781165599822998, "step": 398570 }, { "epoch": 2.369242291848708, "grad_norm": 1.1510794162750244, "learning_rate": 4.317057031581062e-05, "loss": 0.483205509185791, "step": 398580 }, { "epoch": 2.3693017339253766, "grad_norm": 1.2475682497024536, "learning_rate": 4.316640117806875e-05, "loss": 0.4593395233154297, "step": 398590 }, { "epoch": 2.369361176002045, "grad_norm": 1.255079746246338, "learning_rate": 4.316223236003694e-05, "loss": 0.4685169219970703, "step": 398600 }, { "epoch": 2.3694206180787134, "grad_norm": 1.404516577720642, "learning_rate": 4.315806386173514e-05, "loss": 0.49002599716186523, "step": 398610 }, { "epoch": 2.3694800601553814, "grad_norm": 1.3646492958068848, "learning_rate": 4.315389568318334e-05, "loss": 0.4985334396362305, "step": 398620 }, { "epoch": 2.36953950223205, "grad_norm": 1.3712780475616455, "learning_rate": 4.3149727824401465e-05, "loss": 0.5509294986724853, "step": 398630 }, { "epoch": 2.369598944308718, "grad_norm": 1.3263070583343506, "learning_rate": 4.314556028540942e-05, "loss": 0.5271543502807617, "step": 398640 }, { "epoch": 2.3696583863853866, "grad_norm": 1.0795049667358398, "learning_rate": 4.314139306622721e-05, "loss": 0.49741363525390625, "step": 398650 }, { "epoch": 2.369717828462055, "grad_norm": 1.4351626634597778, "learning_rate": 4.313722616687471e-05, "loss": 0.5489921569824219, "step": 398660 }, { "epoch": 2.3697772705387234, "grad_norm": 1.2603892087936401, "learning_rate": 4.313305958737183e-05, "loss": 0.4434617519378662, "step": 398670 }, { "epoch": 2.369836712615392, "grad_norm": 1.7195391654968262, "learning_rate": 4.312889332773858e-05, "loss": 0.5198259353637695, "step": 398680 }, { "epoch": 2.3698961546920603, "grad_norm": 0.8542175889015198, "learning_rate": 4.3124727387994844e-05, "loss": 0.48343791961669924, "step": 398690 }, { "epoch": 2.3699555967687287, "grad_norm": 1.4461365938186646, "learning_rate": 4.312056176816056e-05, "loss": 0.5223703384399414, "step": 398700 }, { "epoch": 2.370015038845397, "grad_norm": 1.4175587892532349, "learning_rate": 4.311639646825565e-05, "loss": 0.5057478904724121, "step": 398710 }, { "epoch": 2.3700744809220655, "grad_norm": 1.0823472738265991, "learning_rate": 4.311223148830005e-05, "loss": 0.4901895523071289, "step": 398720 }, { "epoch": 2.370133922998734, "grad_norm": 1.165889859199524, "learning_rate": 4.310806682831366e-05, "loss": 0.46782970428466797, "step": 398730 }, { "epoch": 2.3701933650754023, "grad_norm": 1.2988204956054688, "learning_rate": 4.3103902488316396e-05, "loss": 0.43337421417236327, "step": 398740 }, { "epoch": 2.3702528071520708, "grad_norm": 1.3480721712112427, "learning_rate": 4.309973846832823e-05, "loss": 0.5545434951782227, "step": 398750 }, { "epoch": 2.370312249228739, "grad_norm": 1.478358507156372, "learning_rate": 4.309557476836905e-05, "loss": 0.5532065391540527, "step": 398760 }, { "epoch": 2.3703716913054076, "grad_norm": 1.311410665512085, "learning_rate": 4.309141138845878e-05, "loss": 0.44040212631225584, "step": 398770 }, { "epoch": 2.370431133382076, "grad_norm": 1.4199942350387573, "learning_rate": 4.3087248328617336e-05, "loss": 0.41083440780639646, "step": 398780 }, { "epoch": 2.3704905754587444, "grad_norm": 1.568447470664978, "learning_rate": 4.3083085588864616e-05, "loss": 0.48166913986206056, "step": 398790 }, { "epoch": 2.370550017535413, "grad_norm": 1.661266565322876, "learning_rate": 4.307892316922052e-05, "loss": 0.4843608856201172, "step": 398800 }, { "epoch": 2.370609459612081, "grad_norm": 1.1930183172225952, "learning_rate": 4.307476106970503e-05, "loss": 0.4911170482635498, "step": 398810 }, { "epoch": 2.370668901688749, "grad_norm": 1.7138745784759521, "learning_rate": 4.3070599290337996e-05, "loss": 0.4985833168029785, "step": 398820 }, { "epoch": 2.3707283437654176, "grad_norm": 1.4690382480621338, "learning_rate": 4.306643783113934e-05, "loss": 0.5305334091186523, "step": 398830 }, { "epoch": 2.370787785842086, "grad_norm": 1.3365041017532349, "learning_rate": 4.3062276692128975e-05, "loss": 0.5029073715209961, "step": 398840 }, { "epoch": 2.3708472279187545, "grad_norm": 1.246687650680542, "learning_rate": 4.305811587332681e-05, "loss": 0.4670711517333984, "step": 398850 }, { "epoch": 2.370906669995423, "grad_norm": 1.3129445314407349, "learning_rate": 4.305395537475273e-05, "loss": 0.5118616104125977, "step": 398860 }, { "epoch": 2.3709661120720913, "grad_norm": 1.872711420059204, "learning_rate": 4.304979519642663e-05, "loss": 0.4936841487884521, "step": 398870 }, { "epoch": 2.3710255541487597, "grad_norm": 1.6188416481018066, "learning_rate": 4.304563533836845e-05, "loss": 0.4601741313934326, "step": 398880 }, { "epoch": 2.371084996225428, "grad_norm": 1.0317028760910034, "learning_rate": 4.304147580059809e-05, "loss": 0.5218146800994873, "step": 398890 }, { "epoch": 2.3711444383020965, "grad_norm": 1.3812335729599, "learning_rate": 4.30373165831354e-05, "loss": 0.4845314025878906, "step": 398900 }, { "epoch": 2.371203880378765, "grad_norm": 1.246088981628418, "learning_rate": 4.3033157686000324e-05, "loss": 0.5244124412536622, "step": 398910 }, { "epoch": 2.3712633224554334, "grad_norm": 1.2659558057785034, "learning_rate": 4.302899910921273e-05, "loss": 0.46493959426879883, "step": 398920 }, { "epoch": 2.371322764532102, "grad_norm": 1.1578067541122437, "learning_rate": 4.302484085279251e-05, "loss": 0.48063955307006834, "step": 398930 }, { "epoch": 2.37138220660877, "grad_norm": 1.3777185678482056, "learning_rate": 4.3020682916759545e-05, "loss": 0.4806666851043701, "step": 398940 }, { "epoch": 2.3714416486854386, "grad_norm": 1.07133150100708, "learning_rate": 4.301652530113377e-05, "loss": 0.47920451164245603, "step": 398950 }, { "epoch": 2.371501090762107, "grad_norm": 1.3758394718170166, "learning_rate": 4.3012368005935046e-05, "loss": 0.46702232360839846, "step": 398960 }, { "epoch": 2.3715605328387754, "grad_norm": 1.037186861038208, "learning_rate": 4.300821103118326e-05, "loss": 0.46438064575195315, "step": 398970 }, { "epoch": 2.3716199749154434, "grad_norm": 1.0605227947235107, "learning_rate": 4.300405437689831e-05, "loss": 0.47916488647460936, "step": 398980 }, { "epoch": 2.3716794169921123, "grad_norm": 1.7225666046142578, "learning_rate": 4.299989804310006e-05, "loss": 0.4502202033996582, "step": 398990 }, { "epoch": 2.3717388590687802, "grad_norm": 1.0389513969421387, "learning_rate": 4.299574202980838e-05, "loss": 0.4490067481994629, "step": 399000 }, { "epoch": 2.3717983011454487, "grad_norm": 1.302586317062378, "learning_rate": 4.299158633704319e-05, "loss": 0.40677628517150877, "step": 399010 }, { "epoch": 2.371857743222117, "grad_norm": 1.5258594751358032, "learning_rate": 4.298743096482436e-05, "loss": 0.46914281845092776, "step": 399020 }, { "epoch": 2.3719171852987855, "grad_norm": 1.269224762916565, "learning_rate": 4.2983275913171764e-05, "loss": 0.48784470558166504, "step": 399030 }, { "epoch": 2.371976627375454, "grad_norm": 1.3653135299682617, "learning_rate": 4.297912118210527e-05, "loss": 0.47255716323852537, "step": 399040 }, { "epoch": 2.3720360694521223, "grad_norm": 1.529405117034912, "learning_rate": 4.297496677164475e-05, "loss": 0.510224723815918, "step": 399050 }, { "epoch": 2.3720955115287907, "grad_norm": 1.5846508741378784, "learning_rate": 4.297081268181009e-05, "loss": 0.519097900390625, "step": 399060 }, { "epoch": 2.372154953605459, "grad_norm": 1.0529849529266357, "learning_rate": 4.2966658912621136e-05, "loss": 0.4873359680175781, "step": 399070 }, { "epoch": 2.3722143956821276, "grad_norm": 1.3462564945220947, "learning_rate": 4.29625054640978e-05, "loss": 0.4985696315765381, "step": 399080 }, { "epoch": 2.372273837758796, "grad_norm": 0.8635188937187195, "learning_rate": 4.2958352336259965e-05, "loss": 0.4762713432312012, "step": 399090 }, { "epoch": 2.3723332798354644, "grad_norm": 1.5120733976364136, "learning_rate": 4.29541995291274e-05, "loss": 0.5110535621643066, "step": 399100 }, { "epoch": 2.372392721912133, "grad_norm": 1.2093557119369507, "learning_rate": 4.295004704272007e-05, "loss": 0.4809411525726318, "step": 399110 }, { "epoch": 2.372452163988801, "grad_norm": 1.5092815160751343, "learning_rate": 4.2945894877057794e-05, "loss": 0.46288042068481444, "step": 399120 }, { "epoch": 2.3725116060654696, "grad_norm": 1.5057350397109985, "learning_rate": 4.294174303216041e-05, "loss": 0.46031885147094725, "step": 399130 }, { "epoch": 2.372571048142138, "grad_norm": 0.8708327412605286, "learning_rate": 4.293759150804785e-05, "loss": 0.49238033294677735, "step": 399140 }, { "epoch": 2.3726304902188065, "grad_norm": 0.9604241251945496, "learning_rate": 4.293344030473996e-05, "loss": 0.4253390789031982, "step": 399150 }, { "epoch": 2.372689932295475, "grad_norm": 1.2650651931762695, "learning_rate": 4.2929289422256515e-05, "loss": 0.4964003562927246, "step": 399160 }, { "epoch": 2.372749374372143, "grad_norm": 1.582754135131836, "learning_rate": 4.292513886061746e-05, "loss": 0.5128712177276611, "step": 399170 }, { "epoch": 2.3728088164488117, "grad_norm": 1.4878180027008057, "learning_rate": 4.2920988619842636e-05, "loss": 0.45172863006591796, "step": 399180 }, { "epoch": 2.3728682585254797, "grad_norm": 0.9717755317687988, "learning_rate": 4.291683869995187e-05, "loss": 0.45591001510620116, "step": 399190 }, { "epoch": 2.372927700602148, "grad_norm": 1.1775249242782593, "learning_rate": 4.2912689100965016e-05, "loss": 0.4692279815673828, "step": 399200 }, { "epoch": 2.3729871426788165, "grad_norm": 1.4045392274856567, "learning_rate": 4.290853982290194e-05, "loss": 0.48922953605651853, "step": 399210 }, { "epoch": 2.373046584755485, "grad_norm": 1.5013097524642944, "learning_rate": 4.2904390865782484e-05, "loss": 0.49877290725708007, "step": 399220 }, { "epoch": 2.3731060268321533, "grad_norm": 1.2912715673446655, "learning_rate": 4.290024222962647e-05, "loss": 0.4303112030029297, "step": 399230 }, { "epoch": 2.3731654689088217, "grad_norm": 1.2718392610549927, "learning_rate": 4.2896093914453793e-05, "loss": 0.4617560386657715, "step": 399240 }, { "epoch": 2.37322491098549, "grad_norm": 1.2611743211746216, "learning_rate": 4.289194592028428e-05, "loss": 0.4848897933959961, "step": 399250 }, { "epoch": 2.3732843530621586, "grad_norm": 1.3196921348571777, "learning_rate": 4.2887798247137753e-05, "loss": 0.46456212997436525, "step": 399260 }, { "epoch": 2.373343795138827, "grad_norm": 1.3945388793945312, "learning_rate": 4.2883650895034075e-05, "loss": 0.4535384178161621, "step": 399270 }, { "epoch": 2.3734032372154954, "grad_norm": 1.2402883768081665, "learning_rate": 4.287950386399308e-05, "loss": 0.44138708114624026, "step": 399280 }, { "epoch": 2.373462679292164, "grad_norm": 1.2806463241577148, "learning_rate": 4.287535715403457e-05, "loss": 0.45307254791259766, "step": 399290 }, { "epoch": 2.3735221213688322, "grad_norm": 1.509509801864624, "learning_rate": 4.2871210765178446e-05, "loss": 0.5025759220123291, "step": 399300 }, { "epoch": 2.3735815634455006, "grad_norm": 1.2318211793899536, "learning_rate": 4.2867064697444506e-05, "loss": 0.452561092376709, "step": 399310 }, { "epoch": 2.373641005522169, "grad_norm": 2.0670197010040283, "learning_rate": 4.286291895085259e-05, "loss": 0.514738655090332, "step": 399320 }, { "epoch": 2.3737004475988375, "grad_norm": 1.3039696216583252, "learning_rate": 4.2858773525422536e-05, "loss": 0.46282062530517576, "step": 399330 }, { "epoch": 2.373759889675506, "grad_norm": 1.4840487241744995, "learning_rate": 4.285462842117416e-05, "loss": 0.5094796657562256, "step": 399340 }, { "epoch": 2.3738193317521743, "grad_norm": 1.456386923789978, "learning_rate": 4.285048363812731e-05, "loss": 0.4731167793273926, "step": 399350 }, { "epoch": 2.3738787738288423, "grad_norm": 1.1925461292266846, "learning_rate": 4.284633917630175e-05, "loss": 0.48069915771484373, "step": 399360 }, { "epoch": 2.3739382159055107, "grad_norm": 1.430338740348816, "learning_rate": 4.2842195035717415e-05, "loss": 0.4698625087738037, "step": 399370 }, { "epoch": 2.373997657982179, "grad_norm": 1.4160516262054443, "learning_rate": 4.283805121639406e-05, "loss": 0.5409005165100098, "step": 399380 }, { "epoch": 2.3740571000588475, "grad_norm": 1.5504646301269531, "learning_rate": 4.283390771835151e-05, "loss": 0.4735581398010254, "step": 399390 }, { "epoch": 2.374116542135516, "grad_norm": 1.1388717889785767, "learning_rate": 4.28297645416096e-05, "loss": 0.4297992706298828, "step": 399400 }, { "epoch": 2.3741759842121843, "grad_norm": 1.2364357709884644, "learning_rate": 4.2825621686188156e-05, "loss": 0.5678550243377686, "step": 399410 }, { "epoch": 2.3742354262888528, "grad_norm": 1.2734172344207764, "learning_rate": 4.282147915210697e-05, "loss": 0.49602770805358887, "step": 399420 }, { "epoch": 2.374294868365521, "grad_norm": 1.2664849758148193, "learning_rate": 4.281733693938586e-05, "loss": 0.48392200469970703, "step": 399430 }, { "epoch": 2.3743543104421896, "grad_norm": 1.24934720993042, "learning_rate": 4.281319504804466e-05, "loss": 0.45902338027954104, "step": 399440 }, { "epoch": 2.374413752518858, "grad_norm": 1.3012657165527344, "learning_rate": 4.2809053478103195e-05, "loss": 0.49082236289978026, "step": 399450 }, { "epoch": 2.3744731945955264, "grad_norm": 0.9736838936805725, "learning_rate": 4.280491222958126e-05, "loss": 0.45400028228759765, "step": 399460 }, { "epoch": 2.374532636672195, "grad_norm": 1.1787139177322388, "learning_rate": 4.280077130249866e-05, "loss": 0.4594071865081787, "step": 399470 }, { "epoch": 2.3745920787488632, "grad_norm": 1.3643697500228882, "learning_rate": 4.279663069687521e-05, "loss": 0.5032400131225586, "step": 399480 }, { "epoch": 2.3746515208255317, "grad_norm": 1.4606634378433228, "learning_rate": 4.279249041273069e-05, "loss": 0.46475791931152344, "step": 399490 }, { "epoch": 2.3747109629022, "grad_norm": 1.4844424724578857, "learning_rate": 4.2788350450084965e-05, "loss": 0.47960615158081055, "step": 399500 }, { "epoch": 2.3747704049788685, "grad_norm": 1.136956810951233, "learning_rate": 4.278421080895779e-05, "loss": 0.42702760696411135, "step": 399510 }, { "epoch": 2.374829847055537, "grad_norm": 1.734648585319519, "learning_rate": 4.2780071489369e-05, "loss": 0.508098030090332, "step": 399520 }, { "epoch": 2.3748892891322053, "grad_norm": 1.268245816230774, "learning_rate": 4.277593249133838e-05, "loss": 0.47991056442260743, "step": 399530 }, { "epoch": 2.3749487312088737, "grad_norm": 1.992973804473877, "learning_rate": 4.2771793814885726e-05, "loss": 0.47848219871520997, "step": 399540 }, { "epoch": 2.3750081732855417, "grad_norm": 1.51185142993927, "learning_rate": 4.2767655460030835e-05, "loss": 0.48301382064819337, "step": 399550 }, { "epoch": 2.37506761536221, "grad_norm": 1.344572901725769, "learning_rate": 4.2763517426793486e-05, "loss": 0.4938960075378418, "step": 399560 }, { "epoch": 2.3751270574388785, "grad_norm": 1.0452055931091309, "learning_rate": 4.275937971519353e-05, "loss": 0.48695621490478513, "step": 399570 }, { "epoch": 2.375186499515547, "grad_norm": 1.1365457773208618, "learning_rate": 4.275524232525075e-05, "loss": 0.5173077583312988, "step": 399580 }, { "epoch": 2.3752459415922154, "grad_norm": 1.538928508758545, "learning_rate": 4.2751105256984855e-05, "loss": 0.48004932403564454, "step": 399590 }, { "epoch": 2.3753053836688838, "grad_norm": 1.2602921724319458, "learning_rate": 4.274696851041572e-05, "loss": 0.494569730758667, "step": 399600 }, { "epoch": 2.375364825745552, "grad_norm": 1.5214531421661377, "learning_rate": 4.274283208556312e-05, "loss": 0.5350688934326172, "step": 399610 }, { "epoch": 2.3754242678222206, "grad_norm": 1.4626177549362183, "learning_rate": 4.2738695982446794e-05, "loss": 0.5227376461029053, "step": 399620 }, { "epoch": 2.375483709898889, "grad_norm": 1.1400699615478516, "learning_rate": 4.2734560201086604e-05, "loss": 0.45122766494750977, "step": 399630 }, { "epoch": 2.3755431519755574, "grad_norm": 1.3862277269363403, "learning_rate": 4.273042474150231e-05, "loss": 0.46887912750244143, "step": 399640 }, { "epoch": 2.375602594052226, "grad_norm": 1.2254894971847534, "learning_rate": 4.2726289603713634e-05, "loss": 0.5140985965728759, "step": 399650 }, { "epoch": 2.3756620361288943, "grad_norm": 1.220646858215332, "learning_rate": 4.2722154787740434e-05, "loss": 0.4621546268463135, "step": 399660 }, { "epoch": 2.3757214782055627, "grad_norm": 1.2537590265274048, "learning_rate": 4.271802029360245e-05, "loss": 0.5253244876861572, "step": 399670 }, { "epoch": 2.375780920282231, "grad_norm": 1.3832727670669556, "learning_rate": 4.271388612131947e-05, "loss": 0.5246932029724121, "step": 399680 }, { "epoch": 2.3758403623588995, "grad_norm": 1.625367283821106, "learning_rate": 4.2709752270911255e-05, "loss": 0.5234245300292969, "step": 399690 }, { "epoch": 2.375899804435568, "grad_norm": 1.3343760967254639, "learning_rate": 4.270561874239762e-05, "loss": 0.5184307098388672, "step": 399700 }, { "epoch": 2.3759592465122363, "grad_norm": 1.2644038200378418, "learning_rate": 4.270148553579831e-05, "loss": 0.4356393814086914, "step": 399710 }, { "epoch": 2.3760186885889043, "grad_norm": 1.2194783687591553, "learning_rate": 4.269735265113307e-05, "loss": 0.49601039886474607, "step": 399720 }, { "epoch": 2.376078130665573, "grad_norm": 0.9679664969444275, "learning_rate": 4.269322008842172e-05, "loss": 0.44896302223205564, "step": 399730 }, { "epoch": 2.376137572742241, "grad_norm": 1.3067140579223633, "learning_rate": 4.268908784768402e-05, "loss": 0.5129422187805176, "step": 399740 }, { "epoch": 2.3761970148189095, "grad_norm": 1.3900991678237915, "learning_rate": 4.2684955928939684e-05, "loss": 0.4663177490234375, "step": 399750 }, { "epoch": 2.376256456895578, "grad_norm": 1.753965973854065, "learning_rate": 4.268082433220859e-05, "loss": 0.5457021236419678, "step": 399760 }, { "epoch": 2.3763158989722464, "grad_norm": 1.1469976902008057, "learning_rate": 4.2676693057510385e-05, "loss": 0.4840878486633301, "step": 399770 }, { "epoch": 2.376375341048915, "grad_norm": 1.142958402633667, "learning_rate": 4.26725621048649e-05, "loss": 0.46932163238525393, "step": 399780 }, { "epoch": 2.376434783125583, "grad_norm": 1.053467035293579, "learning_rate": 4.2668431474291834e-05, "loss": 0.45551271438598634, "step": 399790 }, { "epoch": 2.3764942252022516, "grad_norm": 1.1207430362701416, "learning_rate": 4.266430116581103e-05, "loss": 0.47150135040283203, "step": 399800 }, { "epoch": 2.37655366727892, "grad_norm": 1.7550054788589478, "learning_rate": 4.266017117944219e-05, "loss": 0.539852523803711, "step": 399810 }, { "epoch": 2.3766131093555884, "grad_norm": 1.1160950660705566, "learning_rate": 4.265604151520509e-05, "loss": 0.5098689079284668, "step": 399820 }, { "epoch": 2.376672551432257, "grad_norm": 1.529868245124817, "learning_rate": 4.265191217311947e-05, "loss": 0.48067522048950195, "step": 399830 }, { "epoch": 2.3767319935089253, "grad_norm": 1.1604852676391602, "learning_rate": 4.26477831532051e-05, "loss": 0.47445454597473147, "step": 399840 }, { "epoch": 2.3767914355855937, "grad_norm": 1.5715489387512207, "learning_rate": 4.2643654455481695e-05, "loss": 0.49757089614868166, "step": 399850 }, { "epoch": 2.376850877662262, "grad_norm": 1.3949183225631714, "learning_rate": 4.2639526079969073e-05, "loss": 0.5005917549133301, "step": 399860 }, { "epoch": 2.3769103197389305, "grad_norm": 1.3199251890182495, "learning_rate": 4.263539802668693e-05, "loss": 0.4902693748474121, "step": 399870 }, { "epoch": 2.376969761815599, "grad_norm": 1.39756178855896, "learning_rate": 4.263127029565503e-05, "loss": 0.4626492500305176, "step": 399880 }, { "epoch": 2.3770292038922674, "grad_norm": 1.0413306951522827, "learning_rate": 4.2627142886893124e-05, "loss": 0.4990388870239258, "step": 399890 }, { "epoch": 2.3770886459689358, "grad_norm": 1.3386059999465942, "learning_rate": 4.262301580042094e-05, "loss": 0.5047374725341797, "step": 399900 }, { "epoch": 2.3771480880456037, "grad_norm": 1.2532895803451538, "learning_rate": 4.261888903625824e-05, "loss": 0.4827588558197021, "step": 399910 }, { "epoch": 2.3772075301222726, "grad_norm": 1.2941040992736816, "learning_rate": 4.261476259442472e-05, "loss": 0.4798128604888916, "step": 399920 }, { "epoch": 2.3772669721989406, "grad_norm": 1.203428864479065, "learning_rate": 4.261063647494018e-05, "loss": 0.4705232620239258, "step": 399930 }, { "epoch": 2.377326414275609, "grad_norm": 1.185256004333496, "learning_rate": 4.260651067782434e-05, "loss": 0.49855546951293944, "step": 399940 }, { "epoch": 2.3773858563522774, "grad_norm": 1.3379679918289185, "learning_rate": 4.260238520309692e-05, "loss": 0.5198147773742676, "step": 399950 }, { "epoch": 2.377445298428946, "grad_norm": 1.6922647953033447, "learning_rate": 4.259826005077767e-05, "loss": 0.49173593521118164, "step": 399960 }, { "epoch": 2.3775047405056142, "grad_norm": 1.2073748111724854, "learning_rate": 4.259413522088631e-05, "loss": 0.45895700454711913, "step": 399970 }, { "epoch": 2.3775641825822826, "grad_norm": 1.0665923357009888, "learning_rate": 4.259001071344255e-05, "loss": 0.5032763004302978, "step": 399980 }, { "epoch": 2.377623624658951, "grad_norm": 1.5760401487350464, "learning_rate": 4.258588652846618e-05, "loss": 0.5241320610046387, "step": 399990 }, { "epoch": 2.3776830667356195, "grad_norm": 1.470171570777893, "learning_rate": 4.25817626659769e-05, "loss": 0.4879913806915283, "step": 400000 }, { "epoch": 2.377742508812288, "grad_norm": 1.9200897216796875, "learning_rate": 4.257763912599444e-05, "loss": 0.4709610939025879, "step": 400010 }, { "epoch": 2.3778019508889563, "grad_norm": 1.6382849216461182, "learning_rate": 4.2573515908538506e-05, "loss": 0.4425931930541992, "step": 400020 }, { "epoch": 2.3778613929656247, "grad_norm": 1.1893203258514404, "learning_rate": 4.256939301362884e-05, "loss": 0.3939927339553833, "step": 400030 }, { "epoch": 2.377920835042293, "grad_norm": 1.3264650106430054, "learning_rate": 4.256527044128517e-05, "loss": 0.5594432830810547, "step": 400040 }, { "epoch": 2.3779802771189615, "grad_norm": 1.3050446510314941, "learning_rate": 4.256114819152717e-05, "loss": 0.486282205581665, "step": 400050 }, { "epoch": 2.37803971919563, "grad_norm": 1.318762183189392, "learning_rate": 4.2557026264374647e-05, "loss": 0.4677415370941162, "step": 400060 }, { "epoch": 2.3780991612722984, "grad_norm": 1.5396935939788818, "learning_rate": 4.255290465984727e-05, "loss": 0.4819046974182129, "step": 400070 }, { "epoch": 2.378158603348967, "grad_norm": 1.4082547426223755, "learning_rate": 4.254878337796472e-05, "loss": 0.4675187110900879, "step": 400080 }, { "epoch": 2.378218045425635, "grad_norm": 1.3369743824005127, "learning_rate": 4.254466241874676e-05, "loss": 0.5034074783325195, "step": 400090 }, { "epoch": 2.378277487502303, "grad_norm": 1.5860873460769653, "learning_rate": 4.2540541782213096e-05, "loss": 0.4839749336242676, "step": 400100 }, { "epoch": 2.3783369295789716, "grad_norm": 1.4782640933990479, "learning_rate": 4.2536421468383415e-05, "loss": 0.5382741451263428, "step": 400110 }, { "epoch": 2.37839637165564, "grad_norm": 1.248680591583252, "learning_rate": 4.253230147727747e-05, "loss": 0.4587958335876465, "step": 400120 }, { "epoch": 2.3784558137323084, "grad_norm": 1.4707335233688354, "learning_rate": 4.252818180891496e-05, "loss": 0.5285728931427002, "step": 400130 }, { "epoch": 2.378515255808977, "grad_norm": 1.4796923398971558, "learning_rate": 4.252406246331553e-05, "loss": 0.4585587501525879, "step": 400140 }, { "epoch": 2.3785746978856452, "grad_norm": 1.2669000625610352, "learning_rate": 4.251994344049897e-05, "loss": 0.4608929634094238, "step": 400150 }, { "epoch": 2.3786341399623137, "grad_norm": 1.3732959032058716, "learning_rate": 4.251582474048494e-05, "loss": 0.48245830535888673, "step": 400160 }, { "epoch": 2.378693582038982, "grad_norm": 1.6533628702163696, "learning_rate": 4.2511706363293154e-05, "loss": 0.4879324913024902, "step": 400170 }, { "epoch": 2.3787530241156505, "grad_norm": 1.464098334312439, "learning_rate": 4.250758830894328e-05, "loss": 0.4739199161529541, "step": 400180 }, { "epoch": 2.378812466192319, "grad_norm": 1.053810477256775, "learning_rate": 4.2503470577455105e-05, "loss": 0.5027382850646973, "step": 400190 }, { "epoch": 2.3788719082689873, "grad_norm": 1.38636314868927, "learning_rate": 4.249935316884823e-05, "loss": 0.4918359756469727, "step": 400200 }, { "epoch": 2.3789313503456557, "grad_norm": 1.196096420288086, "learning_rate": 4.2495236083142373e-05, "loss": 0.5108501434326171, "step": 400210 }, { "epoch": 2.378990792422324, "grad_norm": 1.6792922019958496, "learning_rate": 4.2491119320357275e-05, "loss": 0.5166869163513184, "step": 400220 }, { "epoch": 2.3790502344989926, "grad_norm": 1.3761922121047974, "learning_rate": 4.2487002880512596e-05, "loss": 0.4403075218200684, "step": 400230 }, { "epoch": 2.379109676575661, "grad_norm": 1.5532057285308838, "learning_rate": 4.2482886763628006e-05, "loss": 0.4657658576965332, "step": 400240 }, { "epoch": 2.3791691186523294, "grad_norm": 1.4017581939697266, "learning_rate": 4.247877096972327e-05, "loss": 0.4617669105529785, "step": 400250 }, { "epoch": 2.379228560728998, "grad_norm": 1.422798752784729, "learning_rate": 4.2474655498818006e-05, "loss": 0.4421121597290039, "step": 400260 }, { "epoch": 2.3792880028056658, "grad_norm": 1.1451152563095093, "learning_rate": 4.247054035093192e-05, "loss": 0.5555194854736328, "step": 400270 }, { "epoch": 2.3793474448823346, "grad_norm": 1.3594377040863037, "learning_rate": 4.246642552608468e-05, "loss": 0.46094532012939454, "step": 400280 }, { "epoch": 2.3794068869590026, "grad_norm": 1.6662254333496094, "learning_rate": 4.2462311024296e-05, "loss": 0.4724597930908203, "step": 400290 }, { "epoch": 2.379466329035671, "grad_norm": 1.4786765575408936, "learning_rate": 4.245819684558557e-05, "loss": 0.4714314937591553, "step": 400300 }, { "epoch": 2.3795257711123394, "grad_norm": 1.2698678970336914, "learning_rate": 4.2454082989973045e-05, "loss": 0.4935948848724365, "step": 400310 }, { "epoch": 2.379585213189008, "grad_norm": 1.092215657234192, "learning_rate": 4.2449969457478114e-05, "loss": 0.4859904766082764, "step": 400320 }, { "epoch": 2.3796446552656763, "grad_norm": 1.89388906955719, "learning_rate": 4.2445856248120466e-05, "loss": 0.5026707649230957, "step": 400330 }, { "epoch": 2.3797040973423447, "grad_norm": 1.2687608003616333, "learning_rate": 4.244174336191972e-05, "loss": 0.4436457633972168, "step": 400340 }, { "epoch": 2.379763539419013, "grad_norm": 1.146504521369934, "learning_rate": 4.243763079889563e-05, "loss": 0.49114170074462893, "step": 400350 }, { "epoch": 2.3798229814956815, "grad_norm": 1.698127031326294, "learning_rate": 4.243351855906783e-05, "loss": 0.4952105522155762, "step": 400360 }, { "epoch": 2.37988242357235, "grad_norm": 1.2418184280395508, "learning_rate": 4.242940664245599e-05, "loss": 0.49540348052978517, "step": 400370 }, { "epoch": 2.3799418656490183, "grad_norm": 1.6210495233535767, "learning_rate": 4.24252950490798e-05, "loss": 0.4268655776977539, "step": 400380 }, { "epoch": 2.3800013077256867, "grad_norm": 1.1631537675857544, "learning_rate": 4.242118377895891e-05, "loss": 0.5035606384277344, "step": 400390 }, { "epoch": 2.380060749802355, "grad_norm": 1.103678584098816, "learning_rate": 4.241707283211299e-05, "loss": 0.49250063896179197, "step": 400400 }, { "epoch": 2.3801201918790236, "grad_norm": 1.4350368976593018, "learning_rate": 4.241296220856169e-05, "loss": 0.5175222396850586, "step": 400410 }, { "epoch": 2.380179633955692, "grad_norm": 0.9744088053703308, "learning_rate": 4.2408851908324704e-05, "loss": 0.4812030792236328, "step": 400420 }, { "epoch": 2.3802390760323604, "grad_norm": 1.5709692239761353, "learning_rate": 4.240474193142169e-05, "loss": 0.4715142250061035, "step": 400430 }, { "epoch": 2.380298518109029, "grad_norm": 1.5355913639068604, "learning_rate": 4.24006322778723e-05, "loss": 0.4954668045043945, "step": 400440 }, { "epoch": 2.3803579601856972, "grad_norm": 1.5439138412475586, "learning_rate": 4.2396522947696186e-05, "loss": 0.5468296051025391, "step": 400450 }, { "epoch": 2.380417402262365, "grad_norm": 1.22515070438385, "learning_rate": 4.2392413940913024e-05, "loss": 0.46514143943786623, "step": 400460 }, { "epoch": 2.380476844339034, "grad_norm": 1.6440759897232056, "learning_rate": 4.238830525754243e-05, "loss": 0.5116375923156739, "step": 400470 }, { "epoch": 2.380536286415702, "grad_norm": 1.5977727174758911, "learning_rate": 4.23841968976041e-05, "loss": 0.5040668964385986, "step": 400480 }, { "epoch": 2.3805957284923704, "grad_norm": 1.2652391195297241, "learning_rate": 4.2380088861117694e-05, "loss": 0.4844656944274902, "step": 400490 }, { "epoch": 2.380655170569039, "grad_norm": 1.3747437000274658, "learning_rate": 4.237598114810284e-05, "loss": 0.4535671710968018, "step": 400500 }, { "epoch": 2.3807146126457073, "grad_norm": 1.1179059743881226, "learning_rate": 4.2371873758579187e-05, "loss": 0.5193455696105957, "step": 400510 }, { "epoch": 2.3807740547223757, "grad_norm": 1.4356106519699097, "learning_rate": 4.23677666925664e-05, "loss": 0.45393195152282717, "step": 400520 }, { "epoch": 2.380833496799044, "grad_norm": 1.4507263898849487, "learning_rate": 4.23636599500841e-05, "loss": 0.44228239059448243, "step": 400530 }, { "epoch": 2.3808929388757125, "grad_norm": 1.4398634433746338, "learning_rate": 4.235955353115192e-05, "loss": 0.540471363067627, "step": 400540 }, { "epoch": 2.380952380952381, "grad_norm": 1.392069935798645, "learning_rate": 4.2355447435789574e-05, "loss": 0.48520774841308595, "step": 400550 }, { "epoch": 2.3810118230290493, "grad_norm": 1.5681824684143066, "learning_rate": 4.2351341664016674e-05, "loss": 0.4995072364807129, "step": 400560 }, { "epoch": 2.3810712651057178, "grad_norm": 1.1417039632797241, "learning_rate": 4.23472362158528e-05, "loss": 0.4982608318328857, "step": 400570 }, { "epoch": 2.381130707182386, "grad_norm": 1.354711651802063, "learning_rate": 4.2343131091317656e-05, "loss": 0.4646977424621582, "step": 400580 }, { "epoch": 2.3811901492590546, "grad_norm": 1.3474431037902832, "learning_rate": 4.2339026290430874e-05, "loss": 0.47481861114501955, "step": 400590 }, { "epoch": 2.381249591335723, "grad_norm": 1.3555281162261963, "learning_rate": 4.2334921813212044e-05, "loss": 0.5088435173034668, "step": 400600 }, { "epoch": 2.3813090334123914, "grad_norm": 1.0768376588821411, "learning_rate": 4.233081765968087e-05, "loss": 0.4853058815002441, "step": 400610 }, { "epoch": 2.38136847548906, "grad_norm": 1.5272490978240967, "learning_rate": 4.232671382985697e-05, "loss": 0.48230276107788084, "step": 400620 }, { "epoch": 2.3814279175657282, "grad_norm": 1.2240734100341797, "learning_rate": 4.232261032375993e-05, "loss": 0.5192915916442871, "step": 400630 }, { "epoch": 2.3814873596423967, "grad_norm": 1.2686994075775146, "learning_rate": 4.231850714140938e-05, "loss": 0.49698925018310547, "step": 400640 }, { "epoch": 2.3815468017190646, "grad_norm": 1.0103391408920288, "learning_rate": 4.231440428282499e-05, "loss": 0.49332461357116697, "step": 400650 }, { "epoch": 2.3816062437957335, "grad_norm": 1.098193883895874, "learning_rate": 4.231030174802638e-05, "loss": 0.4775123596191406, "step": 400660 }, { "epoch": 2.3816656858724015, "grad_norm": 1.4735779762268066, "learning_rate": 4.230619953703314e-05, "loss": 0.4816592216491699, "step": 400670 }, { "epoch": 2.38172512794907, "grad_norm": 1.2433058023452759, "learning_rate": 4.230209764986497e-05, "loss": 0.43012042045593263, "step": 400680 }, { "epoch": 2.3817845700257383, "grad_norm": 1.2009167671203613, "learning_rate": 4.2297996086541413e-05, "loss": 0.46482219696044924, "step": 400690 }, { "epoch": 2.3818440121024067, "grad_norm": 1.552129864692688, "learning_rate": 4.229389484708209e-05, "loss": 0.43273067474365234, "step": 400700 }, { "epoch": 2.381903454179075, "grad_norm": 1.269890546798706, "learning_rate": 4.228979393150668e-05, "loss": 0.4824213027954102, "step": 400710 }, { "epoch": 2.3819628962557435, "grad_norm": 1.1413114070892334, "learning_rate": 4.2285693339834756e-05, "loss": 0.43947925567626955, "step": 400720 }, { "epoch": 2.382022338332412, "grad_norm": 1.7123968601226807, "learning_rate": 4.228159307208593e-05, "loss": 0.460631799697876, "step": 400730 }, { "epoch": 2.3820817804090804, "grad_norm": 1.417494535446167, "learning_rate": 4.2277493128279884e-05, "loss": 0.4603006362915039, "step": 400740 }, { "epoch": 2.3821412224857488, "grad_norm": 1.4996449947357178, "learning_rate": 4.227339350843614e-05, "loss": 0.48543100357055663, "step": 400750 }, { "epoch": 2.382200664562417, "grad_norm": 1.413064956665039, "learning_rate": 4.226929421257436e-05, "loss": 0.4719856262207031, "step": 400760 }, { "epoch": 2.3822601066390856, "grad_norm": 1.7845536470413208, "learning_rate": 4.2265195240714115e-05, "loss": 0.4670368194580078, "step": 400770 }, { "epoch": 2.382319548715754, "grad_norm": 1.2584487199783325, "learning_rate": 4.2261096592875063e-05, "loss": 0.4360959053039551, "step": 400780 }, { "epoch": 2.3823789907924224, "grad_norm": 1.918540596961975, "learning_rate": 4.22569982690768e-05, "loss": 0.5034812927246094, "step": 400790 }, { "epoch": 2.382438432869091, "grad_norm": 0.7845382690429688, "learning_rate": 4.22529002693389e-05, "loss": 0.5115534782409668, "step": 400800 }, { "epoch": 2.3824978749457593, "grad_norm": 1.7668089866638184, "learning_rate": 4.2248802593680995e-05, "loss": 0.5095959663391113, "step": 400810 }, { "epoch": 2.3825573170224277, "grad_norm": 1.486116647720337, "learning_rate": 4.224470524212267e-05, "loss": 0.47743473052978513, "step": 400820 }, { "epoch": 2.382616759099096, "grad_norm": 0.9559458494186401, "learning_rate": 4.224060821468352e-05, "loss": 0.46788911819458007, "step": 400830 }, { "epoch": 2.382676201175764, "grad_norm": 1.2535396814346313, "learning_rate": 4.223651151138317e-05, "loss": 0.4812191009521484, "step": 400840 }, { "epoch": 2.3827356432524325, "grad_norm": 1.5950326919555664, "learning_rate": 4.223241513224121e-05, "loss": 0.4883108615875244, "step": 400850 }, { "epoch": 2.382795085329101, "grad_norm": 1.3101001977920532, "learning_rate": 4.2228319077277224e-05, "loss": 0.45896053314208984, "step": 400860 }, { "epoch": 2.3828545274057693, "grad_norm": 1.0668774843215942, "learning_rate": 4.222422334651081e-05, "loss": 0.5142322540283203, "step": 400870 }, { "epoch": 2.3829139694824377, "grad_norm": 1.4071743488311768, "learning_rate": 4.2220127939961575e-05, "loss": 0.502668809890747, "step": 400880 }, { "epoch": 2.382973411559106, "grad_norm": 1.1553294658660889, "learning_rate": 4.221603285764908e-05, "loss": 0.45647668838500977, "step": 400890 }, { "epoch": 2.3830328536357746, "grad_norm": 1.3158279657363892, "learning_rate": 4.221193809959292e-05, "loss": 0.47536468505859375, "step": 400900 }, { "epoch": 2.383092295712443, "grad_norm": 1.2408881187438965, "learning_rate": 4.220784366581271e-05, "loss": 0.4954653263092041, "step": 400910 }, { "epoch": 2.3831517377891114, "grad_norm": 0.9806431531906128, "learning_rate": 4.220374955632803e-05, "loss": 0.49095821380615234, "step": 400920 }, { "epoch": 2.38321117986578, "grad_norm": 1.3294111490249634, "learning_rate": 4.219965577115845e-05, "loss": 0.49605503082275393, "step": 400930 }, { "epoch": 2.383270621942448, "grad_norm": 1.489576816558838, "learning_rate": 4.2195562310323553e-05, "loss": 0.49590167999267576, "step": 400940 }, { "epoch": 2.3833300640191166, "grad_norm": 0.9763783812522888, "learning_rate": 4.219146917384295e-05, "loss": 0.4741276741027832, "step": 400950 }, { "epoch": 2.383389506095785, "grad_norm": 1.479859709739685, "learning_rate": 4.218737636173616e-05, "loss": 0.4473154544830322, "step": 400960 }, { "epoch": 2.3834489481724535, "grad_norm": 1.5336365699768066, "learning_rate": 4.218328387402282e-05, "loss": 0.5264098644256592, "step": 400970 }, { "epoch": 2.383508390249122, "grad_norm": 1.3504751920700073, "learning_rate": 4.217919171072249e-05, "loss": 0.48403615951538087, "step": 400980 }, { "epoch": 2.3835678323257903, "grad_norm": 1.328344464302063, "learning_rate": 4.217509987185474e-05, "loss": 0.47057533264160156, "step": 400990 }, { "epoch": 2.3836272744024587, "grad_norm": 1.1164147853851318, "learning_rate": 4.217100835743916e-05, "loss": 0.5172910213470459, "step": 401000 }, { "epoch": 2.3836867164791267, "grad_norm": 1.179766058921814, "learning_rate": 4.2166917167495294e-05, "loss": 0.45855417251586916, "step": 401010 }, { "epoch": 2.3837461585557955, "grad_norm": 1.1133384704589844, "learning_rate": 4.216282630204273e-05, "loss": 0.5058610916137696, "step": 401020 }, { "epoch": 2.3838056006324635, "grad_norm": 1.3676776885986328, "learning_rate": 4.2158735761101024e-05, "loss": 0.5066964149475097, "step": 401030 }, { "epoch": 2.383865042709132, "grad_norm": 1.588555932044983, "learning_rate": 4.215464554468977e-05, "loss": 0.5344034671783447, "step": 401040 }, { "epoch": 2.3839244847858003, "grad_norm": 1.573240876197815, "learning_rate": 4.215055565282852e-05, "loss": 0.5185768127441406, "step": 401050 }, { "epoch": 2.3839839268624687, "grad_norm": 1.243569016456604, "learning_rate": 4.214646608553684e-05, "loss": 0.5003370761871337, "step": 401060 }, { "epoch": 2.384043368939137, "grad_norm": 1.5146021842956543, "learning_rate": 4.2142376842834285e-05, "loss": 0.5193560600280762, "step": 401070 }, { "epoch": 2.3841028110158056, "grad_norm": 1.3011221885681152, "learning_rate": 4.213828792474043e-05, "loss": 0.5337576866149902, "step": 401080 }, { "epoch": 2.384162253092474, "grad_norm": 1.2395445108413696, "learning_rate": 4.213419933127481e-05, "loss": 0.4514127731323242, "step": 401090 }, { "epoch": 2.3842216951691424, "grad_norm": 1.612558364868164, "learning_rate": 4.213011106245701e-05, "loss": 0.472045373916626, "step": 401100 }, { "epoch": 2.384281137245811, "grad_norm": 1.2425215244293213, "learning_rate": 4.212602311830659e-05, "loss": 0.47006897926330565, "step": 401110 }, { "epoch": 2.3843405793224792, "grad_norm": 1.260635495185852, "learning_rate": 4.2121935498843124e-05, "loss": 0.4621402740478516, "step": 401120 }, { "epoch": 2.3844000213991476, "grad_norm": 0.9929125308990479, "learning_rate": 4.211784820408607e-05, "loss": 0.482133674621582, "step": 401130 }, { "epoch": 2.384459463475816, "grad_norm": 0.9471064209938049, "learning_rate": 4.2113761234055075e-05, "loss": 0.46530909538269044, "step": 401140 }, { "epoch": 2.3845189055524845, "grad_norm": 1.3048374652862549, "learning_rate": 4.2109674588769664e-05, "loss": 0.4637326240539551, "step": 401150 }, { "epoch": 2.384578347629153, "grad_norm": 1.1848835945129395, "learning_rate": 4.210558826824936e-05, "loss": 0.4970292091369629, "step": 401160 }, { "epoch": 2.3846377897058213, "grad_norm": 1.7244702577590942, "learning_rate": 4.210150227251376e-05, "loss": 0.4516884803771973, "step": 401170 }, { "epoch": 2.3846972317824897, "grad_norm": 1.2274601459503174, "learning_rate": 4.209741660158241e-05, "loss": 0.4653327941894531, "step": 401180 }, { "epoch": 2.384756673859158, "grad_norm": 1.8319406509399414, "learning_rate": 4.209333125547476e-05, "loss": 0.5168285846710206, "step": 401190 }, { "epoch": 2.384816115935826, "grad_norm": 1.2596436738967896, "learning_rate": 4.208924623421047e-05, "loss": 0.472459602355957, "step": 401200 }, { "epoch": 2.384875558012495, "grad_norm": 1.7328770160675049, "learning_rate": 4.208516153780902e-05, "loss": 0.5155284881591797, "step": 401210 }, { "epoch": 2.384935000089163, "grad_norm": 1.5542722940444946, "learning_rate": 4.2081077166289945e-05, "loss": 0.4856221675872803, "step": 401220 }, { "epoch": 2.3849944421658313, "grad_norm": 1.429532527923584, "learning_rate": 4.2076993119672845e-05, "loss": 0.491269588470459, "step": 401230 }, { "epoch": 2.3850538842424998, "grad_norm": 1.2523689270019531, "learning_rate": 4.207290939797719e-05, "loss": 0.469187068939209, "step": 401240 }, { "epoch": 2.385113326319168, "grad_norm": 1.4436259269714355, "learning_rate": 4.206882600122253e-05, "loss": 0.49562606811523435, "step": 401250 }, { "epoch": 2.3851727683958366, "grad_norm": 1.3616455793380737, "learning_rate": 4.206474292942838e-05, "loss": 0.44733424186706544, "step": 401260 }, { "epoch": 2.385232210472505, "grad_norm": 1.8279552459716797, "learning_rate": 4.206066018261433e-05, "loss": 0.5413401603698731, "step": 401270 }, { "epoch": 2.3852916525491734, "grad_norm": 1.2493276596069336, "learning_rate": 4.205657776079989e-05, "loss": 0.4575371742248535, "step": 401280 }, { "epoch": 2.385351094625842, "grad_norm": 1.3709460496902466, "learning_rate": 4.205249566400457e-05, "loss": 0.45737543106079104, "step": 401290 }, { "epoch": 2.3854105367025102, "grad_norm": 1.8508495092391968, "learning_rate": 4.2048413892247896e-05, "loss": 0.47843232154846194, "step": 401300 }, { "epoch": 2.3854699787791787, "grad_norm": 1.6229875087738037, "learning_rate": 4.2044332445549414e-05, "loss": 0.4814423084259033, "step": 401310 }, { "epoch": 2.385529420855847, "grad_norm": 1.3573623895645142, "learning_rate": 4.2040251323928605e-05, "loss": 0.5232808113098144, "step": 401320 }, { "epoch": 2.3855888629325155, "grad_norm": 1.3141571283340454, "learning_rate": 4.203617052740505e-05, "loss": 0.4532798767089844, "step": 401330 }, { "epoch": 2.385648305009184, "grad_norm": 1.281179666519165, "learning_rate": 4.203209005599824e-05, "loss": 0.46547298431396483, "step": 401340 }, { "epoch": 2.3857077470858523, "grad_norm": 1.2014130353927612, "learning_rate": 4.2028009909727706e-05, "loss": 0.48442821502685546, "step": 401350 }, { "epoch": 2.3857671891625207, "grad_norm": 1.4132053852081299, "learning_rate": 4.202393008861296e-05, "loss": 0.4810295104980469, "step": 401360 }, { "epoch": 2.385826631239189, "grad_norm": 1.3156534433364868, "learning_rate": 4.201985059267352e-05, "loss": 0.4775521278381348, "step": 401370 }, { "epoch": 2.3858860733158576, "grad_norm": 1.4123421907424927, "learning_rate": 4.2015771421928896e-05, "loss": 0.46931209564208987, "step": 401380 }, { "epoch": 2.3859455153925255, "grad_norm": 1.9797329902648926, "learning_rate": 4.2011692576398576e-05, "loss": 0.5067156791687012, "step": 401390 }, { "epoch": 2.3860049574691944, "grad_norm": 1.1139485836029053, "learning_rate": 4.200761405610213e-05, "loss": 0.49443759918212893, "step": 401400 }, { "epoch": 2.3860643995458624, "grad_norm": 1.480121374130249, "learning_rate": 4.200353586105903e-05, "loss": 0.45866856575012205, "step": 401410 }, { "epoch": 2.3861238416225308, "grad_norm": 1.0754894018173218, "learning_rate": 4.19994579912888e-05, "loss": 0.44983673095703125, "step": 401420 }, { "epoch": 2.386183283699199, "grad_norm": 1.5838595628738403, "learning_rate": 4.1995380446810937e-05, "loss": 0.5255646705627441, "step": 401430 }, { "epoch": 2.3862427257758676, "grad_norm": 1.9469565153121948, "learning_rate": 4.199130322764495e-05, "loss": 0.5076453208923339, "step": 401440 }, { "epoch": 2.386302167852536, "grad_norm": 1.2493188381195068, "learning_rate": 4.1987226333810326e-05, "loss": 0.5090620040893554, "step": 401450 }, { "epoch": 2.3863616099292044, "grad_norm": 1.3465815782546997, "learning_rate": 4.198314976532659e-05, "loss": 0.49246015548706057, "step": 401460 }, { "epoch": 2.386421052005873, "grad_norm": 1.6912331581115723, "learning_rate": 4.197907352221325e-05, "loss": 0.444688606262207, "step": 401470 }, { "epoch": 2.3864804940825413, "grad_norm": 1.2008070945739746, "learning_rate": 4.19749976044898e-05, "loss": 0.49645347595214845, "step": 401480 }, { "epoch": 2.3865399361592097, "grad_norm": 1.532515048980713, "learning_rate": 4.1970922012175714e-05, "loss": 0.5208266258239747, "step": 401490 }, { "epoch": 2.386599378235878, "grad_norm": 1.6128005981445312, "learning_rate": 4.196684674529052e-05, "loss": 0.5126401901245117, "step": 401500 }, { "epoch": 2.3866588203125465, "grad_norm": 1.15873384475708, "learning_rate": 4.196277180385369e-05, "loss": 0.45209331512451173, "step": 401510 }, { "epoch": 2.386718262389215, "grad_norm": 1.3855522871017456, "learning_rate": 4.19586971878847e-05, "loss": 0.5014567375183105, "step": 401520 }, { "epoch": 2.3867777044658833, "grad_norm": 1.2701138257980347, "learning_rate": 4.1954622897403096e-05, "loss": 0.4753448486328125, "step": 401530 }, { "epoch": 2.3868371465425517, "grad_norm": 1.068023681640625, "learning_rate": 4.195054893242833e-05, "loss": 0.4607213020324707, "step": 401540 }, { "epoch": 2.38689658861922, "grad_norm": 1.5163304805755615, "learning_rate": 4.19464752929799e-05, "loss": 0.5046030044555664, "step": 401550 }, { "epoch": 2.3869560306958886, "grad_norm": 0.9219764471054077, "learning_rate": 4.194240197907731e-05, "loss": 0.469774866104126, "step": 401560 }, { "epoch": 2.387015472772557, "grad_norm": 1.3109793663024902, "learning_rate": 4.193832899074e-05, "loss": 0.5341404914855957, "step": 401570 }, { "epoch": 2.387074914849225, "grad_norm": 1.4910998344421387, "learning_rate": 4.193425632798748e-05, "loss": 0.46788730621337893, "step": 401580 }, { "epoch": 2.3871343569258934, "grad_norm": 1.543469786643982, "learning_rate": 4.193018399083925e-05, "loss": 0.4828483581542969, "step": 401590 }, { "epoch": 2.387193799002562, "grad_norm": 1.2355951070785522, "learning_rate": 4.1926111979314776e-05, "loss": 0.4585434913635254, "step": 401600 }, { "epoch": 2.38725324107923, "grad_norm": 1.182566523551941, "learning_rate": 4.192204029343355e-05, "loss": 0.46581087112426756, "step": 401610 }, { "epoch": 2.3873126831558986, "grad_norm": 1.543957233428955, "learning_rate": 4.191796893321499e-05, "loss": 0.48788747787475584, "step": 401620 }, { "epoch": 2.387372125232567, "grad_norm": 1.3958722352981567, "learning_rate": 4.191389789867866e-05, "loss": 0.5134827613830566, "step": 401630 }, { "epoch": 2.3874315673092354, "grad_norm": 1.5454131364822388, "learning_rate": 4.190982718984397e-05, "loss": 0.47035675048828124, "step": 401640 }, { "epoch": 2.387491009385904, "grad_norm": 1.4769738912582397, "learning_rate": 4.19057568067304e-05, "loss": 0.5005281448364258, "step": 401650 }, { "epoch": 2.3875504514625723, "grad_norm": 1.0594604015350342, "learning_rate": 4.190168674935745e-05, "loss": 0.4351567268371582, "step": 401660 }, { "epoch": 2.3876098935392407, "grad_norm": 1.4692084789276123, "learning_rate": 4.1897617017744605e-05, "loss": 0.5215059757232666, "step": 401670 }, { "epoch": 2.387669335615909, "grad_norm": 1.151430606842041, "learning_rate": 4.189354761191126e-05, "loss": 0.49147562980651854, "step": 401680 }, { "epoch": 2.3877287776925775, "grad_norm": 1.7059252262115479, "learning_rate": 4.188947853187695e-05, "loss": 0.46735806465148927, "step": 401690 }, { "epoch": 2.387788219769246, "grad_norm": 1.5502936840057373, "learning_rate": 4.188540977766111e-05, "loss": 0.48665652275085447, "step": 401700 }, { "epoch": 2.3878476618459143, "grad_norm": 1.4219354391098022, "learning_rate": 4.18813413492832e-05, "loss": 0.4426436424255371, "step": 401710 }, { "epoch": 2.3879071039225828, "grad_norm": 1.2251527309417725, "learning_rate": 4.187727324676269e-05, "loss": 0.5345461368560791, "step": 401720 }, { "epoch": 2.387966545999251, "grad_norm": 1.4372788667678833, "learning_rate": 4.187320547011909e-05, "loss": 0.48384628295898435, "step": 401730 }, { "epoch": 2.3880259880759196, "grad_norm": 1.1897011995315552, "learning_rate": 4.186913801937178e-05, "loss": 0.4698652267456055, "step": 401740 }, { "epoch": 2.3880854301525876, "grad_norm": 1.024760365486145, "learning_rate": 4.186507089454022e-05, "loss": 0.4352066993713379, "step": 401750 }, { "epoch": 2.3881448722292564, "grad_norm": 1.3998419046401978, "learning_rate": 4.186100409564392e-05, "loss": 0.5239300727844238, "step": 401760 }, { "epoch": 2.3882043143059244, "grad_norm": 1.120776891708374, "learning_rate": 4.1856937622702306e-05, "loss": 0.4418912887573242, "step": 401770 }, { "epoch": 2.388263756382593, "grad_norm": 1.2500221729278564, "learning_rate": 4.185287147573481e-05, "loss": 0.44681477546691895, "step": 401780 }, { "epoch": 2.388323198459261, "grad_norm": 1.6392637491226196, "learning_rate": 4.184880565476095e-05, "loss": 0.5046542167663575, "step": 401790 }, { "epoch": 2.3883826405359296, "grad_norm": 1.2244564294815063, "learning_rate": 4.184474015980012e-05, "loss": 0.48274903297424315, "step": 401800 }, { "epoch": 2.388442082612598, "grad_norm": 1.2213586568832397, "learning_rate": 4.1840674990871755e-05, "loss": 0.4689746379852295, "step": 401810 }, { "epoch": 2.3885015246892665, "grad_norm": 0.9787343144416809, "learning_rate": 4.183661014799534e-05, "loss": 0.44517006874084475, "step": 401820 }, { "epoch": 2.388560966765935, "grad_norm": 1.1472915410995483, "learning_rate": 4.183254563119031e-05, "loss": 0.4599287986755371, "step": 401830 }, { "epoch": 2.3886204088426033, "grad_norm": 1.2749340534210205, "learning_rate": 4.18284814404761e-05, "loss": 0.4785965919494629, "step": 401840 }, { "epoch": 2.3886798509192717, "grad_norm": 1.4605907201766968, "learning_rate": 4.1824417575872167e-05, "loss": 0.5207994937896728, "step": 401850 }, { "epoch": 2.38873929299594, "grad_norm": 1.4254744052886963, "learning_rate": 4.182035403739793e-05, "loss": 0.47262277603149416, "step": 401860 }, { "epoch": 2.3887987350726085, "grad_norm": 1.3144962787628174, "learning_rate": 4.1816290825072846e-05, "loss": 0.48100767135620115, "step": 401870 }, { "epoch": 2.388858177149277, "grad_norm": 1.7484595775604248, "learning_rate": 4.1812227938916316e-05, "loss": 0.4746333122253418, "step": 401880 }, { "epoch": 2.3889176192259454, "grad_norm": 1.1624912023544312, "learning_rate": 4.1808165378947824e-05, "loss": 0.48664178848266604, "step": 401890 }, { "epoch": 2.388977061302614, "grad_norm": 1.3784079551696777, "learning_rate": 4.180410314518679e-05, "loss": 0.5024570465087891, "step": 401900 }, { "epoch": 2.389036503379282, "grad_norm": 1.779130220413208, "learning_rate": 4.1800041237652635e-05, "loss": 0.4773563861846924, "step": 401910 }, { "epoch": 2.3890959454559506, "grad_norm": 1.405656337738037, "learning_rate": 4.1795979656364794e-05, "loss": 0.4730812072753906, "step": 401920 }, { "epoch": 2.389155387532619, "grad_norm": 1.3342089653015137, "learning_rate": 4.17919184013427e-05, "loss": 0.528541088104248, "step": 401930 }, { "epoch": 2.389214829609287, "grad_norm": 1.4096934795379639, "learning_rate": 4.178785747260575e-05, "loss": 0.5150234222412109, "step": 401940 }, { "epoch": 2.389274271685956, "grad_norm": 1.3636846542358398, "learning_rate": 4.1783796870173434e-05, "loss": 0.49581151008605956, "step": 401950 }, { "epoch": 2.389333713762624, "grad_norm": 1.0334947109222412, "learning_rate": 4.1779736594065136e-05, "loss": 0.479279899597168, "step": 401960 }, { "epoch": 2.3893931558392922, "grad_norm": 1.4733623266220093, "learning_rate": 4.177567664430027e-05, "loss": 0.5273008346557617, "step": 401970 }, { "epoch": 2.3894525979159607, "grad_norm": 1.2675492763519287, "learning_rate": 4.177161702089828e-05, "loss": 0.47236042022705077, "step": 401980 }, { "epoch": 2.389512039992629, "grad_norm": 1.2723355293273926, "learning_rate": 4.1767557723878584e-05, "loss": 0.4476675033569336, "step": 401990 }, { "epoch": 2.3895714820692975, "grad_norm": 1.5495854616165161, "learning_rate": 4.176349875326058e-05, "loss": 0.459096622467041, "step": 402000 }, { "epoch": 2.389630924145966, "grad_norm": 1.10465669631958, "learning_rate": 4.175944010906367e-05, "loss": 0.4399237632751465, "step": 402010 }, { "epoch": 2.3896903662226343, "grad_norm": 1.496561884880066, "learning_rate": 4.175538179130733e-05, "loss": 0.5343729972839355, "step": 402020 }, { "epoch": 2.3897498082993027, "grad_norm": 1.413898229598999, "learning_rate": 4.1751323800010954e-05, "loss": 0.521085548400879, "step": 402030 }, { "epoch": 2.389809250375971, "grad_norm": 1.2818742990493774, "learning_rate": 4.174726613519393e-05, "loss": 0.49880666732788087, "step": 402040 }, { "epoch": 2.3898686924526396, "grad_norm": 1.4091469049453735, "learning_rate": 4.174320879687568e-05, "loss": 0.47501001358032224, "step": 402050 }, { "epoch": 2.389928134529308, "grad_norm": 1.0229283571243286, "learning_rate": 4.173915178507561e-05, "loss": 0.4581271171569824, "step": 402060 }, { "epoch": 2.3899875766059764, "grad_norm": 1.0911270380020142, "learning_rate": 4.17350950998131e-05, "loss": 0.4660990238189697, "step": 402070 }, { "epoch": 2.390047018682645, "grad_norm": 1.0336629152297974, "learning_rate": 4.173103874110762e-05, "loss": 0.4439555168151855, "step": 402080 }, { "epoch": 2.390106460759313, "grad_norm": 1.4869942665100098, "learning_rate": 4.172698270897854e-05, "loss": 0.4487449169158936, "step": 402090 }, { "epoch": 2.3901659028359816, "grad_norm": 1.2702959775924683, "learning_rate": 4.172292700344529e-05, "loss": 0.477645206451416, "step": 402100 }, { "epoch": 2.39022534491265, "grad_norm": 1.1911535263061523, "learning_rate": 4.1718871624527176e-05, "loss": 0.513527774810791, "step": 402110 }, { "epoch": 2.3902847869893185, "grad_norm": 1.2219618558883667, "learning_rate": 4.171481657224371e-05, "loss": 0.4919763088226318, "step": 402120 }, { "epoch": 2.3903442290659864, "grad_norm": 1.1598553657531738, "learning_rate": 4.171076184661425e-05, "loss": 0.4603420734405518, "step": 402130 }, { "epoch": 2.3904036711426553, "grad_norm": 1.1073774099349976, "learning_rate": 4.170670744765814e-05, "loss": 0.409682559967041, "step": 402140 }, { "epoch": 2.3904631132193233, "grad_norm": 1.0911535024642944, "learning_rate": 4.170265337539487e-05, "loss": 0.47434797286987307, "step": 402150 }, { "epoch": 2.3905225552959917, "grad_norm": 1.496098279953003, "learning_rate": 4.1698599629843804e-05, "loss": 0.48673300743103026, "step": 402160 }, { "epoch": 2.39058199737266, "grad_norm": 1.3493496179580688, "learning_rate": 4.169454621102426e-05, "loss": 0.513393783569336, "step": 402170 }, { "epoch": 2.3906414394493285, "grad_norm": 1.3923332691192627, "learning_rate": 4.169049311895571e-05, "loss": 0.4596094608306885, "step": 402180 }, { "epoch": 2.390700881525997, "grad_norm": 1.4700486660003662, "learning_rate": 4.1686440353657523e-05, "loss": 0.4896402359008789, "step": 402190 }, { "epoch": 2.3907603236026653, "grad_norm": 1.512846827507019, "learning_rate": 4.168238791514906e-05, "loss": 0.4896805763244629, "step": 402200 }, { "epoch": 2.3908197656793337, "grad_norm": 1.2381342649459839, "learning_rate": 4.167833580344974e-05, "loss": 0.48756017684936526, "step": 402210 }, { "epoch": 2.390879207756002, "grad_norm": 1.297819972038269, "learning_rate": 4.167428401857896e-05, "loss": 0.4608296394348145, "step": 402220 }, { "epoch": 2.3909386498326706, "grad_norm": 1.7034677267074585, "learning_rate": 4.1670232560556064e-05, "loss": 0.4812149524688721, "step": 402230 }, { "epoch": 2.390998091909339, "grad_norm": 1.0622403621673584, "learning_rate": 4.166618142940041e-05, "loss": 0.4916438102722168, "step": 402240 }, { "epoch": 2.3910575339860074, "grad_norm": 1.315234899520874, "learning_rate": 4.166213062513144e-05, "loss": 0.44940915107727053, "step": 402250 }, { "epoch": 2.391116976062676, "grad_norm": 1.8493280410766602, "learning_rate": 4.1658080147768495e-05, "loss": 0.499724006652832, "step": 402260 }, { "epoch": 2.3911764181393442, "grad_norm": 1.066503643989563, "learning_rate": 4.1654029997330945e-05, "loss": 0.46618313789367677, "step": 402270 }, { "epoch": 2.3912358602160126, "grad_norm": 1.1771315336227417, "learning_rate": 4.164998017383823e-05, "loss": 0.47850236892700193, "step": 402280 }, { "epoch": 2.391295302292681, "grad_norm": 1.4770914316177368, "learning_rate": 4.1645930677309645e-05, "loss": 0.44981861114501953, "step": 402290 }, { "epoch": 2.3913547443693495, "grad_norm": 1.178323745727539, "learning_rate": 4.1641881507764566e-05, "loss": 0.48946552276611327, "step": 402300 }, { "epoch": 2.391414186446018, "grad_norm": 1.2359468936920166, "learning_rate": 4.163783266522241e-05, "loss": 0.45592432022094725, "step": 402310 }, { "epoch": 2.391473628522686, "grad_norm": 1.3621513843536377, "learning_rate": 4.163378414970252e-05, "loss": 0.5036356449127197, "step": 402320 }, { "epoch": 2.3915330705993543, "grad_norm": 0.9474068880081177, "learning_rate": 4.162973596122424e-05, "loss": 0.4768305778503418, "step": 402330 }, { "epoch": 2.3915925126760227, "grad_norm": 1.479269027709961, "learning_rate": 4.1625688099807014e-05, "loss": 0.5040294647216796, "step": 402340 }, { "epoch": 2.391651954752691, "grad_norm": 1.8748940229415894, "learning_rate": 4.162164056547012e-05, "loss": 0.4671319961547852, "step": 402350 }, { "epoch": 2.3917113968293595, "grad_norm": 1.249764323234558, "learning_rate": 4.1617593358232955e-05, "loss": 0.48580360412597656, "step": 402360 }, { "epoch": 2.391770838906028, "grad_norm": 1.3744302988052368, "learning_rate": 4.161354647811485e-05, "loss": 0.4871645927429199, "step": 402370 }, { "epoch": 2.3918302809826963, "grad_norm": 1.338853359222412, "learning_rate": 4.160949992513521e-05, "loss": 0.4793818473815918, "step": 402380 }, { "epoch": 2.3918897230593648, "grad_norm": 1.5670665502548218, "learning_rate": 4.1605453699313374e-05, "loss": 0.43233652114868165, "step": 402390 }, { "epoch": 2.391949165136033, "grad_norm": 1.592536449432373, "learning_rate": 4.16014078006687e-05, "loss": 0.5109639644622803, "step": 402400 }, { "epoch": 2.3920086072127016, "grad_norm": 1.0644694566726685, "learning_rate": 4.159736222922053e-05, "loss": 0.45039663314819334, "step": 402410 }, { "epoch": 2.39206804928937, "grad_norm": 1.6582287549972534, "learning_rate": 4.159331698498823e-05, "loss": 0.4764516830444336, "step": 402420 }, { "epoch": 2.3921274913660384, "grad_norm": 1.5338728427886963, "learning_rate": 4.1589272067991126e-05, "loss": 0.4864786148071289, "step": 402430 }, { "epoch": 2.392186933442707, "grad_norm": 1.2890136241912842, "learning_rate": 4.158522747824861e-05, "loss": 0.5164855480194092, "step": 402440 }, { "epoch": 2.3922463755193752, "grad_norm": 1.2969045639038086, "learning_rate": 4.1581183215780005e-05, "loss": 0.47006983757019044, "step": 402450 }, { "epoch": 2.3923058175960437, "grad_norm": 1.4020599126815796, "learning_rate": 4.157713928060466e-05, "loss": 0.465608024597168, "step": 402460 }, { "epoch": 2.392365259672712, "grad_norm": 1.416710376739502, "learning_rate": 4.157309567274192e-05, "loss": 0.43053302764892576, "step": 402470 }, { "epoch": 2.3924247017493805, "grad_norm": 1.539898157119751, "learning_rate": 4.156905239221113e-05, "loss": 0.46998062133789065, "step": 402480 }, { "epoch": 2.3924841438260485, "grad_norm": 1.4330229759216309, "learning_rate": 4.1565009439031634e-05, "loss": 0.48050532341003416, "step": 402490 }, { "epoch": 2.3925435859027173, "grad_norm": 1.3290317058563232, "learning_rate": 4.156096681322274e-05, "loss": 0.45754108428955076, "step": 402500 }, { "epoch": 2.3926030279793853, "grad_norm": 0.9934317469596863, "learning_rate": 4.155692451480383e-05, "loss": 0.45427885055541994, "step": 402510 }, { "epoch": 2.3926624700560537, "grad_norm": 1.3315080404281616, "learning_rate": 4.1552882543794235e-05, "loss": 0.5141081809997559, "step": 402520 }, { "epoch": 2.392721912132722, "grad_norm": 1.2204755544662476, "learning_rate": 4.154884090021328e-05, "loss": 0.478059196472168, "step": 402530 }, { "epoch": 2.3927813542093905, "grad_norm": 1.2862759828567505, "learning_rate": 4.15447995840803e-05, "loss": 0.47145986557006836, "step": 402540 }, { "epoch": 2.392840796286059, "grad_norm": 1.2594568729400635, "learning_rate": 4.1540758595414626e-05, "loss": 0.45331335067749023, "step": 402550 }, { "epoch": 2.3929002383627274, "grad_norm": 1.2979302406311035, "learning_rate": 4.153671793423556e-05, "loss": 0.44130759239196776, "step": 402560 }, { "epoch": 2.3929596804393958, "grad_norm": 1.5426998138427734, "learning_rate": 4.15326776005625e-05, "loss": 0.4951458930969238, "step": 402570 }, { "epoch": 2.393019122516064, "grad_norm": 0.931714653968811, "learning_rate": 4.1528637594414724e-05, "loss": 0.49941039085388184, "step": 402580 }, { "epoch": 2.3930785645927326, "grad_norm": 1.4246201515197754, "learning_rate": 4.152459791581158e-05, "loss": 0.49122257232666017, "step": 402590 }, { "epoch": 2.393138006669401, "grad_norm": 1.2358698844909668, "learning_rate": 4.152055856477236e-05, "loss": 0.4465346336364746, "step": 402600 }, { "epoch": 2.3931974487460694, "grad_norm": 1.0484925508499146, "learning_rate": 4.1516519541316436e-05, "loss": 0.4633613586425781, "step": 402610 }, { "epoch": 2.393256890822738, "grad_norm": 1.1208348274230957, "learning_rate": 4.151248084546309e-05, "loss": 0.4617720603942871, "step": 402620 }, { "epoch": 2.3933163328994063, "grad_norm": 1.360445499420166, "learning_rate": 4.1508442477231616e-05, "loss": 0.48615002632141113, "step": 402630 }, { "epoch": 2.3933757749760747, "grad_norm": 2.0420799255371094, "learning_rate": 4.150440443664141e-05, "loss": 0.5392858505249023, "step": 402640 }, { "epoch": 2.393435217052743, "grad_norm": 1.2729212045669556, "learning_rate": 4.150036672371177e-05, "loss": 0.4738104820251465, "step": 402650 }, { "epoch": 2.3934946591294115, "grad_norm": 1.5404026508331299, "learning_rate": 4.149632933846194e-05, "loss": 0.5004525184631348, "step": 402660 }, { "epoch": 2.39355410120608, "grad_norm": 1.1748085021972656, "learning_rate": 4.14922922809113e-05, "loss": 0.5298359394073486, "step": 402670 }, { "epoch": 2.393613543282748, "grad_norm": 1.545093059539795, "learning_rate": 4.148825555107916e-05, "loss": 0.4785916328430176, "step": 402680 }, { "epoch": 2.3936729853594167, "grad_norm": 1.0767618417739868, "learning_rate": 4.1484219148984785e-05, "loss": 0.4479884147644043, "step": 402690 }, { "epoch": 2.3937324274360847, "grad_norm": 1.9215041399002075, "learning_rate": 4.148018307464754e-05, "loss": 0.4378718376159668, "step": 402700 }, { "epoch": 2.393791869512753, "grad_norm": 1.4567017555236816, "learning_rate": 4.147614732808672e-05, "loss": 0.5104361534118652, "step": 402710 }, { "epoch": 2.3938513115894215, "grad_norm": 1.3685287237167358, "learning_rate": 4.1472111909321604e-05, "loss": 0.4501060485839844, "step": 402720 }, { "epoch": 2.39391075366609, "grad_norm": 1.1033823490142822, "learning_rate": 4.1468076818371485e-05, "loss": 0.5223616600036621, "step": 402730 }, { "epoch": 2.3939701957427584, "grad_norm": 1.4510998725891113, "learning_rate": 4.146404205525571e-05, "loss": 0.4887107849121094, "step": 402740 }, { "epoch": 2.394029637819427, "grad_norm": 1.006969690322876, "learning_rate": 4.146000761999356e-05, "loss": 0.46604080200195314, "step": 402750 }, { "epoch": 2.394089079896095, "grad_norm": 1.4864349365234375, "learning_rate": 4.145597351260431e-05, "loss": 0.5152090072631836, "step": 402760 }, { "epoch": 2.3941485219727636, "grad_norm": 1.3704490661621094, "learning_rate": 4.1451939733107336e-05, "loss": 0.4697715759277344, "step": 402770 }, { "epoch": 2.394207964049432, "grad_norm": 1.3852864503860474, "learning_rate": 4.1447906281521845e-05, "loss": 0.4725775718688965, "step": 402780 }, { "epoch": 2.3942674061261005, "grad_norm": 1.2262403964996338, "learning_rate": 4.144387315786715e-05, "loss": 0.4407858371734619, "step": 402790 }, { "epoch": 2.394326848202769, "grad_norm": 1.4560331106185913, "learning_rate": 4.1439840362162596e-05, "loss": 0.5147593975067138, "step": 402800 }, { "epoch": 2.3943862902794373, "grad_norm": 1.4490619897842407, "learning_rate": 4.143580789442742e-05, "loss": 0.5420380592346191, "step": 402810 }, { "epoch": 2.3944457323561057, "grad_norm": 1.0793954133987427, "learning_rate": 4.1431775754680955e-05, "loss": 0.4536109924316406, "step": 402820 }, { "epoch": 2.394505174432774, "grad_norm": 1.3730159997940063, "learning_rate": 4.142774394294245e-05, "loss": 0.48391194343566896, "step": 402830 }, { "epoch": 2.3945646165094425, "grad_norm": 1.2870862483978271, "learning_rate": 4.142371245923121e-05, "loss": 0.487824821472168, "step": 402840 }, { "epoch": 2.394624058586111, "grad_norm": 1.5476692914962769, "learning_rate": 4.1419681303566526e-05, "loss": 0.52042236328125, "step": 402850 }, { "epoch": 2.3946835006627794, "grad_norm": 1.404860258102417, "learning_rate": 4.141565047596764e-05, "loss": 0.5146044731140137, "step": 402860 }, { "epoch": 2.3947429427394473, "grad_norm": 1.4363106489181519, "learning_rate": 4.14116199764539e-05, "loss": 0.538451099395752, "step": 402870 }, { "epoch": 2.394802384816116, "grad_norm": 1.3770798444747925, "learning_rate": 4.140758980504456e-05, "loss": 0.5144854068756104, "step": 402880 }, { "epoch": 2.394861826892784, "grad_norm": 1.3185826539993286, "learning_rate": 4.140355996175888e-05, "loss": 0.5062492847442627, "step": 402890 }, { "epoch": 2.3949212689694526, "grad_norm": 1.3342361450195312, "learning_rate": 4.1399530446616164e-05, "loss": 0.46930389404296874, "step": 402900 }, { "epoch": 2.394980711046121, "grad_norm": 1.3485842943191528, "learning_rate": 4.139550125963567e-05, "loss": 0.4765490531921387, "step": 402910 }, { "epoch": 2.3950401531227894, "grad_norm": 1.2819875478744507, "learning_rate": 4.139147240083665e-05, "loss": 0.46992969512939453, "step": 402920 }, { "epoch": 2.395099595199458, "grad_norm": 1.4744404554367065, "learning_rate": 4.138744387023843e-05, "loss": 0.5099375724792481, "step": 402930 }, { "epoch": 2.3951590372761262, "grad_norm": 1.3066784143447876, "learning_rate": 4.138341566786026e-05, "loss": 0.47431144714355467, "step": 402940 }, { "epoch": 2.3952184793527946, "grad_norm": 1.026558518409729, "learning_rate": 4.137938779372141e-05, "loss": 0.46837806701660156, "step": 402950 }, { "epoch": 2.395277921429463, "grad_norm": 1.4883942604064941, "learning_rate": 4.137536024784113e-05, "loss": 0.49089775085449217, "step": 402960 }, { "epoch": 2.3953373635061315, "grad_norm": 1.5769766569137573, "learning_rate": 4.137133303023871e-05, "loss": 0.5410300254821777, "step": 402970 }, { "epoch": 2.3953968055828, "grad_norm": 1.3513027429580688, "learning_rate": 4.1367306140933397e-05, "loss": 0.535486888885498, "step": 402980 }, { "epoch": 2.3954562476594683, "grad_norm": 1.2416335344314575, "learning_rate": 4.1363279579944445e-05, "loss": 0.4583857536315918, "step": 402990 }, { "epoch": 2.3955156897361367, "grad_norm": 1.3168855905532837, "learning_rate": 4.135925334729116e-05, "loss": 0.48629050254821776, "step": 403000 }, { "epoch": 2.395575131812805, "grad_norm": 1.1697826385498047, "learning_rate": 4.1355227442992764e-05, "loss": 0.45386757850646975, "step": 403010 }, { "epoch": 2.3956345738894735, "grad_norm": 1.099134087562561, "learning_rate": 4.135120186706854e-05, "loss": 0.4810667037963867, "step": 403020 }, { "epoch": 2.395694015966142, "grad_norm": 1.4430838823318481, "learning_rate": 4.134717661953772e-05, "loss": 0.5072572708129883, "step": 403030 }, { "epoch": 2.3957534580428104, "grad_norm": 1.234229326248169, "learning_rate": 4.1343151700419574e-05, "loss": 0.4775062561035156, "step": 403040 }, { "epoch": 2.395812900119479, "grad_norm": 1.1272257566452026, "learning_rate": 4.133912710973332e-05, "loss": 0.5441486835479736, "step": 403050 }, { "epoch": 2.3958723421961468, "grad_norm": 0.9211217761039734, "learning_rate": 4.133510284749829e-05, "loss": 0.4420504570007324, "step": 403060 }, { "epoch": 2.395931784272815, "grad_norm": 1.2667032480239868, "learning_rate": 4.133107891373367e-05, "loss": 0.4649111270904541, "step": 403070 }, { "epoch": 2.3959912263494836, "grad_norm": 1.1956446170806885, "learning_rate": 4.1327055308458726e-05, "loss": 0.5586543083190918, "step": 403080 }, { "epoch": 2.396050668426152, "grad_norm": 1.4737783670425415, "learning_rate": 4.132303203169272e-05, "loss": 0.4806809425354004, "step": 403090 }, { "epoch": 2.3961101105028204, "grad_norm": 1.498158574104309, "learning_rate": 4.131900908345487e-05, "loss": 0.5225092887878418, "step": 403100 }, { "epoch": 2.396169552579489, "grad_norm": 1.2764638662338257, "learning_rate": 4.131498646376444e-05, "loss": 0.5003640174865722, "step": 403110 }, { "epoch": 2.3962289946561572, "grad_norm": 1.2205055952072144, "learning_rate": 4.131096417264065e-05, "loss": 0.46325178146362306, "step": 403120 }, { "epoch": 2.3962884367328257, "grad_norm": 1.2860699892044067, "learning_rate": 4.1306942210102786e-05, "loss": 0.45871696472167967, "step": 403130 }, { "epoch": 2.396347878809494, "grad_norm": 1.7819005250930786, "learning_rate": 4.1302920576170054e-05, "loss": 0.4218484401702881, "step": 403140 }, { "epoch": 2.3964073208861625, "grad_norm": 1.2697070837020874, "learning_rate": 4.1298899270861705e-05, "loss": 0.44426546096801756, "step": 403150 }, { "epoch": 2.396466762962831, "grad_norm": 1.3617777824401855, "learning_rate": 4.129487829419696e-05, "loss": 0.4838878631591797, "step": 403160 }, { "epoch": 2.3965262050394993, "grad_norm": 1.34756600856781, "learning_rate": 4.129085764619507e-05, "loss": 0.48941702842712403, "step": 403170 }, { "epoch": 2.3965856471161677, "grad_norm": 1.366446852684021, "learning_rate": 4.128683732687524e-05, "loss": 0.44837088584899903, "step": 403180 }, { "epoch": 2.396645089192836, "grad_norm": 1.4122501611709595, "learning_rate": 4.128281733625674e-05, "loss": 0.5043329715728759, "step": 403190 }, { "epoch": 2.3967045312695046, "grad_norm": 1.7391507625579834, "learning_rate": 4.1278797674358796e-05, "loss": 0.510735034942627, "step": 403200 }, { "epoch": 2.396763973346173, "grad_norm": 1.4333125352859497, "learning_rate": 4.127477834120066e-05, "loss": 0.5196735382080078, "step": 403210 }, { "epoch": 2.3968234154228414, "grad_norm": 1.0778872966766357, "learning_rate": 4.1270759336801454e-05, "loss": 0.4514266014099121, "step": 403220 }, { "epoch": 2.3968828574995094, "grad_norm": 1.238311529159546, "learning_rate": 4.1266740661180514e-05, "loss": 0.493544864654541, "step": 403230 }, { "epoch": 2.396942299576178, "grad_norm": 1.6076875925064087, "learning_rate": 4.1262722314357014e-05, "loss": 0.4867896556854248, "step": 403240 }, { "epoch": 2.397001741652846, "grad_norm": 1.2533680200576782, "learning_rate": 4.125870429635016e-05, "loss": 0.4866188049316406, "step": 403250 }, { "epoch": 2.3970611837295146, "grad_norm": 1.2332316637039185, "learning_rate": 4.125468660717926e-05, "loss": 0.4811521530151367, "step": 403260 }, { "epoch": 2.397120625806183, "grad_norm": 1.3306553363800049, "learning_rate": 4.1250669246863446e-05, "loss": 0.4658858299255371, "step": 403270 }, { "epoch": 2.3971800678828514, "grad_norm": 1.0462219715118408, "learning_rate": 4.1246652215421934e-05, "loss": 0.43139076232910156, "step": 403280 }, { "epoch": 2.39723950995952, "grad_norm": 1.5141305923461914, "learning_rate": 4.1242635512874e-05, "loss": 0.48199663162231443, "step": 403290 }, { "epoch": 2.3972989520361883, "grad_norm": 1.3668009042739868, "learning_rate": 4.123861913923882e-05, "loss": 0.4759253978729248, "step": 403300 }, { "epoch": 2.3973583941128567, "grad_norm": 1.213754415512085, "learning_rate": 4.123460309453562e-05, "loss": 0.5263056278228759, "step": 403310 }, { "epoch": 2.397417836189525, "grad_norm": 1.4559122323989868, "learning_rate": 4.12305873787836e-05, "loss": 0.5376540184020996, "step": 403320 }, { "epoch": 2.3974772782661935, "grad_norm": 1.2363003492355347, "learning_rate": 4.1226571992001975e-05, "loss": 0.48403115272521974, "step": 403330 }, { "epoch": 2.397536720342862, "grad_norm": 1.6171236038208008, "learning_rate": 4.1222556934209965e-05, "loss": 0.4479090690612793, "step": 403340 }, { "epoch": 2.3975961624195303, "grad_norm": 1.5380650758743286, "learning_rate": 4.1218542205426727e-05, "loss": 0.42751102447509765, "step": 403350 }, { "epoch": 2.3976556044961987, "grad_norm": 0.9215621948242188, "learning_rate": 4.1214527805671546e-05, "loss": 0.4857501029968262, "step": 403360 }, { "epoch": 2.397715046572867, "grad_norm": 1.095331072807312, "learning_rate": 4.121051373496357e-05, "loss": 0.4919009208679199, "step": 403370 }, { "epoch": 2.3977744886495356, "grad_norm": 0.9534929990768433, "learning_rate": 4.1206499993322025e-05, "loss": 0.48015379905700684, "step": 403380 }, { "epoch": 2.397833930726204, "grad_norm": 1.2615705728530884, "learning_rate": 4.120248658076609e-05, "loss": 0.5021574974060059, "step": 403390 }, { "epoch": 2.3978933728028724, "grad_norm": 1.4437161684036255, "learning_rate": 4.119847349731499e-05, "loss": 0.46007184982299804, "step": 403400 }, { "epoch": 2.397952814879541, "grad_norm": 1.3460606336593628, "learning_rate": 4.119446074298788e-05, "loss": 0.5160613059997559, "step": 403410 }, { "epoch": 2.398012256956209, "grad_norm": 1.2831391096115112, "learning_rate": 4.1190448317804006e-05, "loss": 0.45768122673034667, "step": 403420 }, { "epoch": 2.3980716990328776, "grad_norm": 1.5153512954711914, "learning_rate": 4.118643622178254e-05, "loss": 0.5111275672912597, "step": 403430 }, { "epoch": 2.3981311411095456, "grad_norm": 1.5252671241760254, "learning_rate": 4.1182424454942676e-05, "loss": 0.4650256156921387, "step": 403440 }, { "epoch": 2.398190583186214, "grad_norm": 1.3778660297393799, "learning_rate": 4.117841301730361e-05, "loss": 0.5075043678283692, "step": 403450 }, { "epoch": 2.3982500252628824, "grad_norm": 1.0351595878601074, "learning_rate": 4.117440190888451e-05, "loss": 0.4264000415802002, "step": 403460 }, { "epoch": 2.398309467339551, "grad_norm": 1.7393264770507812, "learning_rate": 4.117039112970459e-05, "loss": 0.5281107425689697, "step": 403470 }, { "epoch": 2.3983689094162193, "grad_norm": 1.399524450302124, "learning_rate": 4.116638067978299e-05, "loss": 0.4901466369628906, "step": 403480 }, { "epoch": 2.3984283514928877, "grad_norm": 1.3741061687469482, "learning_rate": 4.1162370559138966e-05, "loss": 0.5184449195861817, "step": 403490 }, { "epoch": 2.398487793569556, "grad_norm": 1.1948152780532837, "learning_rate": 4.1158360767791666e-05, "loss": 0.47577829360961915, "step": 403500 }, { "epoch": 2.3985472356462245, "grad_norm": 1.0635994672775269, "learning_rate": 4.1154351305760266e-05, "loss": 0.48125710487365725, "step": 403510 }, { "epoch": 2.398606677722893, "grad_norm": 0.9159187078475952, "learning_rate": 4.115034217306395e-05, "loss": 0.518468189239502, "step": 403520 }, { "epoch": 2.3986661197995613, "grad_norm": 1.1726635694503784, "learning_rate": 4.114633336972189e-05, "loss": 0.48982796669006345, "step": 403530 }, { "epoch": 2.3987255618762298, "grad_norm": 1.8261858224868774, "learning_rate": 4.1142324895753245e-05, "loss": 0.4816166400909424, "step": 403540 }, { "epoch": 2.398785003952898, "grad_norm": 1.2452034950256348, "learning_rate": 4.1138316751177253e-05, "loss": 0.47531757354736326, "step": 403550 }, { "epoch": 2.3988444460295666, "grad_norm": 1.1987378597259521, "learning_rate": 4.113430893601304e-05, "loss": 0.488887882232666, "step": 403560 }, { "epoch": 2.398903888106235, "grad_norm": 1.1102159023284912, "learning_rate": 4.113030145027979e-05, "loss": 0.48934102058410645, "step": 403570 }, { "epoch": 2.3989633301829034, "grad_norm": 1.1817848682403564, "learning_rate": 4.112629429399667e-05, "loss": 0.4404646873474121, "step": 403580 }, { "epoch": 2.399022772259572, "grad_norm": 1.5546480417251587, "learning_rate": 4.112228746718285e-05, "loss": 0.5219717979431152, "step": 403590 }, { "epoch": 2.3990822143362402, "grad_norm": 1.5585063695907593, "learning_rate": 4.111828096985749e-05, "loss": 0.4576733589172363, "step": 403600 }, { "epoch": 2.399141656412908, "grad_norm": 1.6475495100021362, "learning_rate": 4.111427480203975e-05, "loss": 0.45693387985229494, "step": 403610 }, { "epoch": 2.399201098489577, "grad_norm": 1.4747300148010254, "learning_rate": 4.111026896374883e-05, "loss": 0.4903592109680176, "step": 403620 }, { "epoch": 2.399260540566245, "grad_norm": 1.084877848625183, "learning_rate": 4.110626345500387e-05, "loss": 0.43449039459228517, "step": 403630 }, { "epoch": 2.3993199826429135, "grad_norm": 1.5868359804153442, "learning_rate": 4.110225827582402e-05, "loss": 0.5358898162841796, "step": 403640 }, { "epoch": 2.399379424719582, "grad_norm": 1.3789710998535156, "learning_rate": 4.109825342622846e-05, "loss": 0.507877254486084, "step": 403650 }, { "epoch": 2.3994388667962503, "grad_norm": 1.1699084043502808, "learning_rate": 4.1094248906236344e-05, "loss": 0.4798630714416504, "step": 403660 }, { "epoch": 2.3994983088729187, "grad_norm": 1.5401431322097778, "learning_rate": 4.109024471586682e-05, "loss": 0.4664423942565918, "step": 403670 }, { "epoch": 2.399557750949587, "grad_norm": 1.4172111749649048, "learning_rate": 4.1086240855139e-05, "loss": 0.49228487014770506, "step": 403680 }, { "epoch": 2.3996171930262555, "grad_norm": 1.6026467084884644, "learning_rate": 4.1082237324072135e-05, "loss": 0.4668060302734375, "step": 403690 }, { "epoch": 2.399676635102924, "grad_norm": 1.3021248579025269, "learning_rate": 4.107823412268534e-05, "loss": 0.4736173629760742, "step": 403700 }, { "epoch": 2.3997360771795924, "grad_norm": 1.5371172428131104, "learning_rate": 4.1074231250997694e-05, "loss": 0.5557879447937012, "step": 403710 }, { "epoch": 2.399795519256261, "grad_norm": 1.0977743864059448, "learning_rate": 4.1070228709028426e-05, "loss": 0.4422603607177734, "step": 403720 }, { "epoch": 2.399854961332929, "grad_norm": 1.452107548713684, "learning_rate": 4.1066226496796656e-05, "loss": 0.5009825706481934, "step": 403730 }, { "epoch": 2.3999144034095976, "grad_norm": 1.2562881708145142, "learning_rate": 4.106222461432152e-05, "loss": 0.45747690200805663, "step": 403740 }, { "epoch": 2.399973845486266, "grad_norm": 1.366981029510498, "learning_rate": 4.105822306162218e-05, "loss": 0.4801501274108887, "step": 403750 }, { "epoch": 2.4000332875629344, "grad_norm": 1.5602918863296509, "learning_rate": 4.1054221838717796e-05, "loss": 0.4981819152832031, "step": 403760 }, { "epoch": 2.400092729639603, "grad_norm": 1.2960938215255737, "learning_rate": 4.105022094562745e-05, "loss": 0.481688404083252, "step": 403770 }, { "epoch": 2.4001521717162713, "grad_norm": 1.2337180376052856, "learning_rate": 4.1046220382370325e-05, "loss": 0.47682762145996094, "step": 403780 }, { "epoch": 2.4002116137929397, "grad_norm": 0.930031418800354, "learning_rate": 4.104222014896555e-05, "loss": 0.5095831871032714, "step": 403790 }, { "epoch": 2.4002710558696077, "grad_norm": 1.4088414907455444, "learning_rate": 4.103822024543226e-05, "loss": 0.50029296875, "step": 403800 }, { "epoch": 2.400330497946276, "grad_norm": 1.1101120710372925, "learning_rate": 4.103422067178955e-05, "loss": 0.48212828636169436, "step": 403810 }, { "epoch": 2.4003899400229445, "grad_norm": 1.1228564977645874, "learning_rate": 4.103022142805666e-05, "loss": 0.4698497772216797, "step": 403820 }, { "epoch": 2.400449382099613, "grad_norm": 1.18419349193573, "learning_rate": 4.102622251425261e-05, "loss": 0.4608715534210205, "step": 403830 }, { "epoch": 2.4005088241762813, "grad_norm": 1.0667698383331299, "learning_rate": 4.102222393039656e-05, "loss": 0.44021196365356446, "step": 403840 }, { "epoch": 2.4005682662529497, "grad_norm": 1.3777426481246948, "learning_rate": 4.101822567650767e-05, "loss": 0.4622939109802246, "step": 403850 }, { "epoch": 2.400627708329618, "grad_norm": 1.972853660583496, "learning_rate": 4.101422775260504e-05, "loss": 0.47368478775024414, "step": 403860 }, { "epoch": 2.4006871504062866, "grad_norm": 1.6343014240264893, "learning_rate": 4.1010230158707795e-05, "loss": 0.48579750061035154, "step": 403870 }, { "epoch": 2.400746592482955, "grad_norm": 1.5192517042160034, "learning_rate": 4.100623289483506e-05, "loss": 0.4646047592163086, "step": 403880 }, { "epoch": 2.4008060345596234, "grad_norm": 1.3999766111373901, "learning_rate": 4.1002235961005975e-05, "loss": 0.5014774322509765, "step": 403890 }, { "epoch": 2.400865476636292, "grad_norm": 1.127751350402832, "learning_rate": 4.099823935723962e-05, "loss": 0.5006561279296875, "step": 403900 }, { "epoch": 2.40092491871296, "grad_norm": 1.1562105417251587, "learning_rate": 4.099424308355515e-05, "loss": 0.47707176208496094, "step": 403910 }, { "epoch": 2.4009843607896286, "grad_norm": 1.3989570140838623, "learning_rate": 4.0990247139971674e-05, "loss": 0.4471610069274902, "step": 403920 }, { "epoch": 2.401043802866297, "grad_norm": 1.2226253747940063, "learning_rate": 4.098625152650831e-05, "loss": 0.482651424407959, "step": 403930 }, { "epoch": 2.4011032449429655, "grad_norm": 1.356224775314331, "learning_rate": 4.098225624318415e-05, "loss": 0.4795860290527344, "step": 403940 }, { "epoch": 2.401162687019634, "grad_norm": 1.5236643552780151, "learning_rate": 4.0978261290018335e-05, "loss": 0.4656215667724609, "step": 403950 }, { "epoch": 2.4012221290963023, "grad_norm": 1.0055526494979858, "learning_rate": 4.097426666702996e-05, "loss": 0.4735729217529297, "step": 403960 }, { "epoch": 2.4012815711729703, "grad_norm": 1.0938841104507446, "learning_rate": 4.0970272374238096e-05, "loss": 0.43233389854431153, "step": 403970 }, { "epoch": 2.401341013249639, "grad_norm": 1.379818081855774, "learning_rate": 4.096627841166193e-05, "loss": 0.4987363815307617, "step": 403980 }, { "epoch": 2.401400455326307, "grad_norm": 1.3502275943756104, "learning_rate": 4.0962284779320526e-05, "loss": 0.5104187965393067, "step": 403990 }, { "epoch": 2.4014598974029755, "grad_norm": 1.1976264715194702, "learning_rate": 4.095829147723298e-05, "loss": 0.5169430732727051, "step": 404000 }, { "epoch": 2.401519339479644, "grad_norm": 1.167834758758545, "learning_rate": 4.095429850541841e-05, "loss": 0.46320600509643556, "step": 404010 }, { "epoch": 2.4015787815563123, "grad_norm": 1.373191475868225, "learning_rate": 4.095030586389592e-05, "loss": 0.47936248779296875, "step": 404020 }, { "epoch": 2.4016382236329807, "grad_norm": 1.3753308057785034, "learning_rate": 4.094631355268456e-05, "loss": 0.42508721351623535, "step": 404030 }, { "epoch": 2.401697665709649, "grad_norm": 1.1052229404449463, "learning_rate": 4.09423215718035e-05, "loss": 0.5271705627441406, "step": 404040 }, { "epoch": 2.4017571077863176, "grad_norm": 1.7867292165756226, "learning_rate": 4.0938329921271814e-05, "loss": 0.49893689155578613, "step": 404050 }, { "epoch": 2.401816549862986, "grad_norm": 1.2459067106246948, "learning_rate": 4.093433860110859e-05, "loss": 0.49456300735473635, "step": 404060 }, { "epoch": 2.4018759919396544, "grad_norm": 1.158615231513977, "learning_rate": 4.093034761133291e-05, "loss": 0.44937524795532224, "step": 404070 }, { "epoch": 2.401935434016323, "grad_norm": 1.2838521003723145, "learning_rate": 4.092635695196387e-05, "loss": 0.4685041427612305, "step": 404080 }, { "epoch": 2.4019948760929912, "grad_norm": 1.174981713294983, "learning_rate": 4.092236662302057e-05, "loss": 0.44849286079406736, "step": 404090 }, { "epoch": 2.4020543181696596, "grad_norm": 1.4426697492599487, "learning_rate": 4.091837662452207e-05, "loss": 0.4880323886871338, "step": 404100 }, { "epoch": 2.402113760246328, "grad_norm": 1.3332353830337524, "learning_rate": 4.0914386956487504e-05, "loss": 0.4756413459777832, "step": 404110 }, { "epoch": 2.4021732023229965, "grad_norm": 1.388792872428894, "learning_rate": 4.091039761893594e-05, "loss": 0.5141537666320801, "step": 404120 }, { "epoch": 2.402232644399665, "grad_norm": 1.159893274307251, "learning_rate": 4.090640861188645e-05, "loss": 0.5095930576324463, "step": 404130 }, { "epoch": 2.4022920864763333, "grad_norm": 1.463074803352356, "learning_rate": 4.0902419935358116e-05, "loss": 0.4798081398010254, "step": 404140 }, { "epoch": 2.4023515285530017, "grad_norm": 1.0723967552185059, "learning_rate": 4.0898431589370024e-05, "loss": 0.5097666263580323, "step": 404150 }, { "epoch": 2.4024109706296697, "grad_norm": 1.6305146217346191, "learning_rate": 4.089444357394127e-05, "loss": 0.544520378112793, "step": 404160 }, { "epoch": 2.4024704127063385, "grad_norm": 1.3085992336273193, "learning_rate": 4.0890455889090865e-05, "loss": 0.4566293239593506, "step": 404170 }, { "epoch": 2.4025298547830065, "grad_norm": 1.1061897277832031, "learning_rate": 4.088646853483797e-05, "loss": 0.46371750831604003, "step": 404180 }, { "epoch": 2.402589296859675, "grad_norm": 1.7793022394180298, "learning_rate": 4.0882481511201645e-05, "loss": 0.4713716506958008, "step": 404190 }, { "epoch": 2.4026487389363433, "grad_norm": 1.6552326679229736, "learning_rate": 4.0878494818200896e-05, "loss": 0.5015801906585693, "step": 404200 }, { "epoch": 2.4027081810130118, "grad_norm": 1.3483829498291016, "learning_rate": 4.087450845585487e-05, "loss": 0.511574125289917, "step": 404210 }, { "epoch": 2.40276762308968, "grad_norm": 1.2903218269348145, "learning_rate": 4.0870522424182575e-05, "loss": 0.5119115829467773, "step": 404220 }, { "epoch": 2.4028270651663486, "grad_norm": 1.4838422536849976, "learning_rate": 4.086653672320311e-05, "loss": 0.5321010112762451, "step": 404230 }, { "epoch": 2.402886507243017, "grad_norm": 1.1695556640625, "learning_rate": 4.0862551352935566e-05, "loss": 0.4776580810546875, "step": 404240 }, { "epoch": 2.4029459493196854, "grad_norm": 1.1356558799743652, "learning_rate": 4.0858566313398995e-05, "loss": 0.5058268547058106, "step": 404250 }, { "epoch": 2.403005391396354, "grad_norm": 1.3011318445205688, "learning_rate": 4.0854581604612404e-05, "loss": 0.5214553356170655, "step": 404260 }, { "epoch": 2.4030648334730222, "grad_norm": 1.3446825742721558, "learning_rate": 4.0850597226594923e-05, "loss": 0.5075827598571777, "step": 404270 }, { "epoch": 2.4031242755496907, "grad_norm": 1.2725228071212769, "learning_rate": 4.084661317936558e-05, "loss": 0.44982070922851564, "step": 404280 }, { "epoch": 2.403183717626359, "grad_norm": 1.9149256944656372, "learning_rate": 4.084262946294345e-05, "loss": 0.55117769241333, "step": 404290 }, { "epoch": 2.4032431597030275, "grad_norm": 1.4197660684585571, "learning_rate": 4.083864607734755e-05, "loss": 0.48316302299499514, "step": 404300 }, { "epoch": 2.403302601779696, "grad_norm": 1.2557390928268433, "learning_rate": 4.083466302259702e-05, "loss": 0.4900599479675293, "step": 404310 }, { "epoch": 2.4033620438563643, "grad_norm": 1.291162371635437, "learning_rate": 4.0830680298710825e-05, "loss": 0.4754302978515625, "step": 404320 }, { "epoch": 2.4034214859330327, "grad_norm": 1.5562642812728882, "learning_rate": 4.082669790570802e-05, "loss": 0.48607673645019533, "step": 404330 }, { "epoch": 2.403480928009701, "grad_norm": 1.2643322944641113, "learning_rate": 4.082271584360772e-05, "loss": 0.44737701416015624, "step": 404340 }, { "epoch": 2.403540370086369, "grad_norm": 1.2757422924041748, "learning_rate": 4.081873411242894e-05, "loss": 0.4453102111816406, "step": 404350 }, { "epoch": 2.403599812163038, "grad_norm": 1.3471544981002808, "learning_rate": 4.0814752712190706e-05, "loss": 0.46104135513305666, "step": 404360 }, { "epoch": 2.403659254239706, "grad_norm": 1.3827446699142456, "learning_rate": 4.081077164291213e-05, "loss": 0.4796576976776123, "step": 404370 }, { "epoch": 2.4037186963163744, "grad_norm": 1.2055461406707764, "learning_rate": 4.080679090461219e-05, "loss": 0.5035559654235839, "step": 404380 }, { "epoch": 2.4037781383930428, "grad_norm": 1.49040949344635, "learning_rate": 4.080281049730992e-05, "loss": 0.5170304298400878, "step": 404390 }, { "epoch": 2.403837580469711, "grad_norm": 1.1452243328094482, "learning_rate": 4.079883042102442e-05, "loss": 0.47390069961547854, "step": 404400 }, { "epoch": 2.4038970225463796, "grad_norm": 1.4851312637329102, "learning_rate": 4.07948506757747e-05, "loss": 0.4729503631591797, "step": 404410 }, { "epoch": 2.403956464623048, "grad_norm": 1.0400229692459106, "learning_rate": 4.07908712615798e-05, "loss": 0.49151129722595216, "step": 404420 }, { "epoch": 2.4040159066997164, "grad_norm": 1.7141797542572021, "learning_rate": 4.078689217845875e-05, "loss": 0.5560356616973877, "step": 404430 }, { "epoch": 2.404075348776385, "grad_norm": 1.3485803604125977, "learning_rate": 4.078291342643058e-05, "loss": 0.48785905838012694, "step": 404440 }, { "epoch": 2.4041347908530533, "grad_norm": 1.69357430934906, "learning_rate": 4.0778935005514346e-05, "loss": 0.5089966773986816, "step": 404450 }, { "epoch": 2.4041942329297217, "grad_norm": 1.257969617843628, "learning_rate": 4.0774956915729035e-05, "loss": 0.47327494621276855, "step": 404460 }, { "epoch": 2.40425367500639, "grad_norm": 1.4725472927093506, "learning_rate": 4.077097915709373e-05, "loss": 0.5308378219604493, "step": 404470 }, { "epoch": 2.4043131170830585, "grad_norm": 0.9477583169937134, "learning_rate": 4.076700172962743e-05, "loss": 0.4847283363342285, "step": 404480 }, { "epoch": 2.404372559159727, "grad_norm": 1.3362317085266113, "learning_rate": 4.076302463334919e-05, "loss": 0.469964599609375, "step": 404490 }, { "epoch": 2.4044320012363953, "grad_norm": 1.4099562168121338, "learning_rate": 4.0759047868277986e-05, "loss": 0.5333742141723633, "step": 404500 }, { "epoch": 2.4044914433130637, "grad_norm": 1.1113899946212769, "learning_rate": 4.075507143443289e-05, "loss": 0.44860496520996096, "step": 404510 }, { "epoch": 2.404550885389732, "grad_norm": 1.363573670387268, "learning_rate": 4.075109533183289e-05, "loss": 0.4757661819458008, "step": 404520 }, { "epoch": 2.4046103274664006, "grad_norm": 1.4635050296783447, "learning_rate": 4.0747119560497e-05, "loss": 0.43367843627929686, "step": 404530 }, { "epoch": 2.4046697695430685, "grad_norm": 1.0341882705688477, "learning_rate": 4.0743144120444284e-05, "loss": 0.4967036247253418, "step": 404540 }, { "epoch": 2.404729211619737, "grad_norm": 0.951530933380127, "learning_rate": 4.073916901169373e-05, "loss": 0.4825295925140381, "step": 404550 }, { "epoch": 2.4047886536964054, "grad_norm": 1.071609377861023, "learning_rate": 4.073519423426436e-05, "loss": 0.44219064712524414, "step": 404560 }, { "epoch": 2.404848095773074, "grad_norm": 1.2833263874053955, "learning_rate": 4.073121978817518e-05, "loss": 0.5159645557403565, "step": 404570 }, { "epoch": 2.404907537849742, "grad_norm": 1.4304122924804688, "learning_rate": 4.0727245673445215e-05, "loss": 0.4599794864654541, "step": 404580 }, { "epoch": 2.4049669799264106, "grad_norm": 1.2429490089416504, "learning_rate": 4.072327189009343e-05, "loss": 0.4976691246032715, "step": 404590 }, { "epoch": 2.405026422003079, "grad_norm": 1.2194839715957642, "learning_rate": 4.071929843813891e-05, "loss": 0.4580105781555176, "step": 404600 }, { "epoch": 2.4050858640797474, "grad_norm": 1.4112491607666016, "learning_rate": 4.0715325317600616e-05, "loss": 0.5385992527008057, "step": 404610 }, { "epoch": 2.405145306156416, "grad_norm": 1.8013273477554321, "learning_rate": 4.071135252849758e-05, "loss": 0.5216273784637451, "step": 404620 }, { "epoch": 2.4052047482330843, "grad_norm": 1.2441245317459106, "learning_rate": 4.070738007084877e-05, "loss": 0.5210360527038574, "step": 404630 }, { "epoch": 2.4052641903097527, "grad_norm": 1.0266934633255005, "learning_rate": 4.070340794467322e-05, "loss": 0.47165517807006835, "step": 404640 }, { "epoch": 2.405323632386421, "grad_norm": 1.3262884616851807, "learning_rate": 4.069943614998992e-05, "loss": 0.4341677188873291, "step": 404650 }, { "epoch": 2.4053830744630895, "grad_norm": 1.8280894756317139, "learning_rate": 4.069546468681783e-05, "loss": 0.49580631256103513, "step": 404660 }, { "epoch": 2.405442516539758, "grad_norm": 1.602610468864441, "learning_rate": 4.069149355517603e-05, "loss": 0.5219632625579834, "step": 404670 }, { "epoch": 2.4055019586164264, "grad_norm": 1.0506161451339722, "learning_rate": 4.0687522755083496e-05, "loss": 0.4347853660583496, "step": 404680 }, { "epoch": 2.4055614006930948, "grad_norm": 1.3218302726745605, "learning_rate": 4.068355228655915e-05, "loss": 0.46210365295410155, "step": 404690 }, { "epoch": 2.405620842769763, "grad_norm": 1.2251062393188477, "learning_rate": 4.067958214962206e-05, "loss": 0.49431581497192384, "step": 404700 }, { "epoch": 2.405680284846431, "grad_norm": 1.6208194494247437, "learning_rate": 4.067561234429119e-05, "loss": 0.4976818561553955, "step": 404710 }, { "epoch": 2.4057397269231, "grad_norm": 1.4850789308547974, "learning_rate": 4.067164287058551e-05, "loss": 0.5645853042602539, "step": 404720 }, { "epoch": 2.405799168999768, "grad_norm": 1.9005494117736816, "learning_rate": 4.0667673728524076e-05, "loss": 0.44673986434936525, "step": 404730 }, { "epoch": 2.4058586110764364, "grad_norm": 1.1774932146072388, "learning_rate": 4.066370491812585e-05, "loss": 0.5417315483093261, "step": 404740 }, { "epoch": 2.405918053153105, "grad_norm": 1.136759877204895, "learning_rate": 4.0659736439409744e-05, "loss": 0.45816679000854493, "step": 404750 }, { "epoch": 2.405977495229773, "grad_norm": 1.5875438451766968, "learning_rate": 4.065576829239483e-05, "loss": 0.4719993591308594, "step": 404760 }, { "epoch": 2.4060369373064416, "grad_norm": 1.3782740831375122, "learning_rate": 4.065180047710005e-05, "loss": 0.4273951530456543, "step": 404770 }, { "epoch": 2.40609637938311, "grad_norm": 1.513800024986267, "learning_rate": 4.06478329935444e-05, "loss": 0.46896872520446775, "step": 404780 }, { "epoch": 2.4061558214597785, "grad_norm": 1.1309956312179565, "learning_rate": 4.064386584174683e-05, "loss": 0.5017309188842773, "step": 404790 }, { "epoch": 2.406215263536447, "grad_norm": 1.5056955814361572, "learning_rate": 4.063989902172638e-05, "loss": 0.5339925765991211, "step": 404800 }, { "epoch": 2.4062747056131153, "grad_norm": 1.127624750137329, "learning_rate": 4.063593253350196e-05, "loss": 0.427175235748291, "step": 404810 }, { "epoch": 2.4063341476897837, "grad_norm": 1.3122256994247437, "learning_rate": 4.0631966377092556e-05, "loss": 0.44154982566833495, "step": 404820 }, { "epoch": 2.406393589766452, "grad_norm": 1.2820429801940918, "learning_rate": 4.0628000552517184e-05, "loss": 0.45807657241821287, "step": 404830 }, { "epoch": 2.4064530318431205, "grad_norm": 1.0055029392242432, "learning_rate": 4.062403505979477e-05, "loss": 0.4835217475891113, "step": 404840 }, { "epoch": 2.406512473919789, "grad_norm": 1.8744882345199585, "learning_rate": 4.062006989894428e-05, "loss": 0.5019110679626465, "step": 404850 }, { "epoch": 2.4065719159964574, "grad_norm": 1.8652399778366089, "learning_rate": 4.061610506998477e-05, "loss": 0.4818138599395752, "step": 404860 }, { "epoch": 2.406631358073126, "grad_norm": 1.69294011592865, "learning_rate": 4.0612140572935084e-05, "loss": 0.47237339019775393, "step": 404870 }, { "epoch": 2.406690800149794, "grad_norm": 0.9845913648605347, "learning_rate": 4.0608176407814234e-05, "loss": 0.4893824577331543, "step": 404880 }, { "epoch": 2.4067502422264626, "grad_norm": 1.5304477214813232, "learning_rate": 4.060421257464121e-05, "loss": 0.4726954460144043, "step": 404890 }, { "epoch": 2.4068096843031306, "grad_norm": 1.2041058540344238, "learning_rate": 4.060024907343496e-05, "loss": 0.46071386337280273, "step": 404900 }, { "epoch": 2.4068691263797994, "grad_norm": 1.534515380859375, "learning_rate": 4.0596285904214436e-05, "loss": 0.46883134841918944, "step": 404910 }, { "epoch": 2.4069285684564674, "grad_norm": 1.3656038045883179, "learning_rate": 4.0592323066998596e-05, "loss": 0.458074951171875, "step": 404920 }, { "epoch": 2.406988010533136, "grad_norm": 1.2318902015686035, "learning_rate": 4.0588360561806396e-05, "loss": 0.4537976264953613, "step": 404930 }, { "epoch": 2.4070474526098042, "grad_norm": 1.2707244157791138, "learning_rate": 4.058439838865681e-05, "loss": 0.5362646102905273, "step": 404940 }, { "epoch": 2.4071068946864727, "grad_norm": 1.7471915483474731, "learning_rate": 4.058043654756874e-05, "loss": 0.527677345275879, "step": 404950 }, { "epoch": 2.407166336763141, "grad_norm": 1.503200650215149, "learning_rate": 4.057647503856121e-05, "loss": 0.5080923080444336, "step": 404960 }, { "epoch": 2.4072257788398095, "grad_norm": 0.9867216348648071, "learning_rate": 4.057251386165312e-05, "loss": 0.5358783721923828, "step": 404970 }, { "epoch": 2.407285220916478, "grad_norm": 1.3113338947296143, "learning_rate": 4.056855301686345e-05, "loss": 0.4922035217285156, "step": 404980 }, { "epoch": 2.4073446629931463, "grad_norm": 1.353538155555725, "learning_rate": 4.056459250421112e-05, "loss": 0.4738301753997803, "step": 404990 }, { "epoch": 2.4074041050698147, "grad_norm": 1.2830406427383423, "learning_rate": 4.0560632323715095e-05, "loss": 0.5364457607269287, "step": 405000 }, { "epoch": 2.407463547146483, "grad_norm": 1.3111387491226196, "learning_rate": 4.055667247539431e-05, "loss": 0.5029168128967285, "step": 405010 }, { "epoch": 2.4075229892231516, "grad_norm": 1.2497835159301758, "learning_rate": 4.0552712959267674e-05, "loss": 0.525771951675415, "step": 405020 }, { "epoch": 2.40758243129982, "grad_norm": 1.3233691453933716, "learning_rate": 4.05487537753542e-05, "loss": 0.43776540756225585, "step": 405030 }, { "epoch": 2.4076418733764884, "grad_norm": 0.9216242432594299, "learning_rate": 4.0544794923672795e-05, "loss": 0.42302989959716797, "step": 405040 }, { "epoch": 2.407701315453157, "grad_norm": 1.9114830493927002, "learning_rate": 4.054083640424239e-05, "loss": 0.49813523292541506, "step": 405050 }, { "epoch": 2.407760757529825, "grad_norm": 0.9765128493309021, "learning_rate": 4.0536878217081915e-05, "loss": 0.4773555278778076, "step": 405060 }, { "epoch": 2.4078201996064936, "grad_norm": 1.3978168964385986, "learning_rate": 4.0532920362210324e-05, "loss": 0.49250593185424807, "step": 405070 }, { "epoch": 2.407879641683162, "grad_norm": 1.312135100364685, "learning_rate": 4.052896283964651e-05, "loss": 0.4850933074951172, "step": 405080 }, { "epoch": 2.40793908375983, "grad_norm": 1.6375322341918945, "learning_rate": 4.0525005649409464e-05, "loss": 0.46353397369384763, "step": 405090 }, { "epoch": 2.407998525836499, "grad_norm": 1.5293233394622803, "learning_rate": 4.0521048791518074e-05, "loss": 0.5133743286132812, "step": 405100 }, { "epoch": 2.408057967913167, "grad_norm": 1.1609795093536377, "learning_rate": 4.0517092265991293e-05, "loss": 0.5606060981750488, "step": 405110 }, { "epoch": 2.4081174099898353, "grad_norm": 1.167144536972046, "learning_rate": 4.0513136072848034e-05, "loss": 0.4524789810180664, "step": 405120 }, { "epoch": 2.4081768520665037, "grad_norm": 1.245678424835205, "learning_rate": 4.0509180212107215e-05, "loss": 0.46915736198425295, "step": 405130 }, { "epoch": 2.408236294143172, "grad_norm": 1.6970984935760498, "learning_rate": 4.0505224683787776e-05, "loss": 0.5201295852661133, "step": 405140 }, { "epoch": 2.4082957362198405, "grad_norm": 1.4789317846298218, "learning_rate": 4.05012694879086e-05, "loss": 0.49442195892333984, "step": 405150 }, { "epoch": 2.408355178296509, "grad_norm": 1.3071271181106567, "learning_rate": 4.049731462448867e-05, "loss": 0.45165214538574217, "step": 405160 }, { "epoch": 2.4084146203731773, "grad_norm": 1.346088171005249, "learning_rate": 4.049336009354687e-05, "loss": 0.4792478561401367, "step": 405170 }, { "epoch": 2.4084740624498457, "grad_norm": 1.2748686075210571, "learning_rate": 4.048940589510213e-05, "loss": 0.5219927310943604, "step": 405180 }, { "epoch": 2.408533504526514, "grad_norm": 0.988740861415863, "learning_rate": 4.0485452029173345e-05, "loss": 0.506625747680664, "step": 405190 }, { "epoch": 2.4085929466031826, "grad_norm": 1.440490484237671, "learning_rate": 4.048149849577944e-05, "loss": 0.44643001556396483, "step": 405200 }, { "epoch": 2.408652388679851, "grad_norm": 1.2588036060333252, "learning_rate": 4.04775452949393e-05, "loss": 0.4727029323577881, "step": 405210 }, { "epoch": 2.4087118307565194, "grad_norm": 1.3805339336395264, "learning_rate": 4.047359242667189e-05, "loss": 0.4713721752166748, "step": 405220 }, { "epoch": 2.408771272833188, "grad_norm": 1.4167941808700562, "learning_rate": 4.0469639890996095e-05, "loss": 0.43596649169921875, "step": 405230 }, { "epoch": 2.4088307149098562, "grad_norm": 0.9131602644920349, "learning_rate": 4.046568768793082e-05, "loss": 0.5149647712707519, "step": 405240 }, { "epoch": 2.4088901569865246, "grad_norm": 1.2436048984527588, "learning_rate": 4.0461735817494986e-05, "loss": 0.4786219596862793, "step": 405250 }, { "epoch": 2.408949599063193, "grad_norm": 1.554704189300537, "learning_rate": 4.045778427970746e-05, "loss": 0.47214317321777344, "step": 405260 }, { "epoch": 2.4090090411398615, "grad_norm": 1.404549479484558, "learning_rate": 4.0453833074587166e-05, "loss": 0.4956986427307129, "step": 405270 }, { "epoch": 2.4090684832165294, "grad_norm": 1.0939955711364746, "learning_rate": 4.0449882202153e-05, "loss": 0.494738245010376, "step": 405280 }, { "epoch": 2.409127925293198, "grad_norm": 1.1591393947601318, "learning_rate": 4.044593166242391e-05, "loss": 0.5269672393798828, "step": 405290 }, { "epoch": 2.4091873673698663, "grad_norm": 1.611762523651123, "learning_rate": 4.044198145541872e-05, "loss": 0.45926675796508787, "step": 405300 }, { "epoch": 2.4092468094465347, "grad_norm": 1.289391040802002, "learning_rate": 4.043803158115633e-05, "loss": 0.4885112762451172, "step": 405310 }, { "epoch": 2.409306251523203, "grad_norm": 1.213680386543274, "learning_rate": 4.043408203965571e-05, "loss": 0.44685516357421873, "step": 405320 }, { "epoch": 2.4093656935998715, "grad_norm": 1.5543882846832275, "learning_rate": 4.0430132830935695e-05, "loss": 0.5476359367370606, "step": 405330 }, { "epoch": 2.40942513567654, "grad_norm": 1.275556206703186, "learning_rate": 4.042618395501516e-05, "loss": 0.4944622039794922, "step": 405340 }, { "epoch": 2.4094845777532083, "grad_norm": 1.2734801769256592, "learning_rate": 4.042223541191308e-05, "loss": 0.48662338256835935, "step": 405350 }, { "epoch": 2.4095440198298768, "grad_norm": 1.335425853729248, "learning_rate": 4.0418287201648265e-05, "loss": 0.4765786170959473, "step": 405360 }, { "epoch": 2.409603461906545, "grad_norm": 1.1582903861999512, "learning_rate": 4.0414339324239615e-05, "loss": 0.524761962890625, "step": 405370 }, { "epoch": 2.4096629039832136, "grad_norm": 1.2846715450286865, "learning_rate": 4.041039177970601e-05, "loss": 0.43613319396972655, "step": 405380 }, { "epoch": 2.409722346059882, "grad_norm": 1.4499022960662842, "learning_rate": 4.0406444568066367e-05, "loss": 0.49437246322631834, "step": 405390 }, { "epoch": 2.4097817881365504, "grad_norm": 1.2634062767028809, "learning_rate": 4.0402497689339546e-05, "loss": 0.5237043380737305, "step": 405400 }, { "epoch": 2.409841230213219, "grad_norm": 1.457013487815857, "learning_rate": 4.039855114354445e-05, "loss": 0.487930965423584, "step": 405410 }, { "epoch": 2.4099006722898872, "grad_norm": 1.514591097831726, "learning_rate": 4.039460493069992e-05, "loss": 0.5049367904663086, "step": 405420 }, { "epoch": 2.4099601143665557, "grad_norm": 1.4608190059661865, "learning_rate": 4.039065905082485e-05, "loss": 0.5269041061401367, "step": 405430 }, { "epoch": 2.410019556443224, "grad_norm": 1.1784483194351196, "learning_rate": 4.0386713503938105e-05, "loss": 0.48522210121154785, "step": 405440 }, { "epoch": 2.410078998519892, "grad_norm": 1.8228498697280884, "learning_rate": 4.03827682900586e-05, "loss": 0.48336544036865237, "step": 405450 }, { "epoch": 2.410138440596561, "grad_norm": 1.1377276182174683, "learning_rate": 4.037882340920517e-05, "loss": 0.4792978286743164, "step": 405460 }, { "epoch": 2.410197882673229, "grad_norm": 1.2226098775863647, "learning_rate": 4.03748788613967e-05, "loss": 0.46663589477539064, "step": 405470 }, { "epoch": 2.4102573247498973, "grad_norm": 1.494338035583496, "learning_rate": 4.037093464665206e-05, "loss": 0.5090262413024902, "step": 405480 }, { "epoch": 2.4103167668265657, "grad_norm": 1.4286859035491943, "learning_rate": 4.036699076499011e-05, "loss": 0.492132568359375, "step": 405490 }, { "epoch": 2.410376208903234, "grad_norm": 1.4685437679290771, "learning_rate": 4.036304721642973e-05, "loss": 0.46919002532958987, "step": 405500 }, { "epoch": 2.4104356509799025, "grad_norm": 1.7501143217086792, "learning_rate": 4.0359104000989736e-05, "loss": 0.5065159797668457, "step": 405510 }, { "epoch": 2.410495093056571, "grad_norm": 1.6199884414672852, "learning_rate": 4.035516111868906e-05, "loss": 0.49413442611694336, "step": 405520 }, { "epoch": 2.4105545351332394, "grad_norm": 1.241115927696228, "learning_rate": 4.0351218569546536e-05, "loss": 0.4641077995300293, "step": 405530 }, { "epoch": 2.4106139772099078, "grad_norm": 1.26188063621521, "learning_rate": 4.034727635358102e-05, "loss": 0.4934562683105469, "step": 405540 }, { "epoch": 2.410673419286576, "grad_norm": 1.4977390766143799, "learning_rate": 4.0343334470811355e-05, "loss": 0.5155281066894531, "step": 405550 }, { "epoch": 2.4107328613632446, "grad_norm": 1.2894043922424316, "learning_rate": 4.033939292125644e-05, "loss": 0.48230810165405275, "step": 405560 }, { "epoch": 2.410792303439913, "grad_norm": 1.2868572473526, "learning_rate": 4.033545170493506e-05, "loss": 0.4487485885620117, "step": 405570 }, { "epoch": 2.4108517455165814, "grad_norm": 1.781610369682312, "learning_rate": 4.0331510821866134e-05, "loss": 0.4853950023651123, "step": 405580 }, { "epoch": 2.41091118759325, "grad_norm": 1.7967134714126587, "learning_rate": 4.0327570272068515e-05, "loss": 0.4936131477355957, "step": 405590 }, { "epoch": 2.4109706296699183, "grad_norm": 1.355861783027649, "learning_rate": 4.0323630055561014e-05, "loss": 0.4900862693786621, "step": 405600 }, { "epoch": 2.4110300717465867, "grad_norm": 1.1473325490951538, "learning_rate": 4.0319690172362496e-05, "loss": 0.4716617584228516, "step": 405610 }, { "epoch": 2.411089513823255, "grad_norm": 1.47019624710083, "learning_rate": 4.031575062249181e-05, "loss": 0.5491790771484375, "step": 405620 }, { "epoch": 2.4111489558999235, "grad_norm": 1.34261155128479, "learning_rate": 4.03118114059678e-05, "loss": 0.47728862762451174, "step": 405630 }, { "epoch": 2.4112083979765915, "grad_norm": 1.5086753368377686, "learning_rate": 4.03078725228093e-05, "loss": 0.47077083587646484, "step": 405640 }, { "epoch": 2.4112678400532603, "grad_norm": 1.2366726398468018, "learning_rate": 4.0303933973035165e-05, "loss": 0.47026524543762205, "step": 405650 }, { "epoch": 2.4113272821299283, "grad_norm": 1.5491530895233154, "learning_rate": 4.0299995756664246e-05, "loss": 0.5189635753631592, "step": 405660 }, { "epoch": 2.4113867242065967, "grad_norm": 1.4332523345947266, "learning_rate": 4.0296057873715364e-05, "loss": 0.4694795608520508, "step": 405670 }, { "epoch": 2.411446166283265, "grad_norm": 1.2444580793380737, "learning_rate": 4.029212032420736e-05, "loss": 0.43811817169189454, "step": 405680 }, { "epoch": 2.4115056083599336, "grad_norm": 1.7151501178741455, "learning_rate": 4.028818310815907e-05, "loss": 0.48623456954956057, "step": 405690 }, { "epoch": 2.411565050436602, "grad_norm": 1.2975616455078125, "learning_rate": 4.0284246225589325e-05, "loss": 0.4773383140563965, "step": 405700 }, { "epoch": 2.4116244925132704, "grad_norm": 1.4522701501846313, "learning_rate": 4.028030967651697e-05, "loss": 0.4825597286224365, "step": 405710 }, { "epoch": 2.411683934589939, "grad_norm": 1.1038484573364258, "learning_rate": 4.0276373460960824e-05, "loss": 0.48776988983154296, "step": 405720 }, { "epoch": 2.411743376666607, "grad_norm": 1.4428383111953735, "learning_rate": 4.027243757893973e-05, "loss": 0.4548338890075684, "step": 405730 }, { "epoch": 2.4118028187432756, "grad_norm": 1.4100925922393799, "learning_rate": 4.02685020304725e-05, "loss": 0.4815055370330811, "step": 405740 }, { "epoch": 2.411862260819944, "grad_norm": 1.4328131675720215, "learning_rate": 4.026456681557797e-05, "loss": 0.4771851062774658, "step": 405750 }, { "epoch": 2.4119217028966125, "grad_norm": 1.1170154809951782, "learning_rate": 4.026063193427497e-05, "loss": 0.43302669525146487, "step": 405760 }, { "epoch": 2.411981144973281, "grad_norm": 1.227794885635376, "learning_rate": 4.0256697386582295e-05, "loss": 0.450361442565918, "step": 405770 }, { "epoch": 2.4120405870499493, "grad_norm": 1.7703301906585693, "learning_rate": 4.0252763172518806e-05, "loss": 0.5106322288513183, "step": 405780 }, { "epoch": 2.4121000291266177, "grad_norm": 1.4223241806030273, "learning_rate": 4.024882929210333e-05, "loss": 0.47806649208068847, "step": 405790 }, { "epoch": 2.412159471203286, "grad_norm": 1.344969630241394, "learning_rate": 4.02448957453546e-05, "loss": 0.4766207695007324, "step": 405800 }, { "epoch": 2.4122189132799545, "grad_norm": 1.1629204750061035, "learning_rate": 4.024096253229153e-05, "loss": 0.4887077808380127, "step": 405810 }, { "epoch": 2.412278355356623, "grad_norm": 1.2587615251541138, "learning_rate": 4.023702965293289e-05, "loss": 0.4615456581115723, "step": 405820 }, { "epoch": 2.412337797433291, "grad_norm": 1.2873146533966064, "learning_rate": 4.0233097107297476e-05, "loss": 0.5283313751220703, "step": 405830 }, { "epoch": 2.4123972395099598, "grad_norm": 1.3499919176101685, "learning_rate": 4.022916489540416e-05, "loss": 0.5108567237854004, "step": 405840 }, { "epoch": 2.4124566815866277, "grad_norm": 1.1298342943191528, "learning_rate": 4.0225233017271726e-05, "loss": 0.4569068908691406, "step": 405850 }, { "epoch": 2.412516123663296, "grad_norm": 1.4009259939193726, "learning_rate": 4.022130147291896e-05, "loss": 0.4587101459503174, "step": 405860 }, { "epoch": 2.4125755657399646, "grad_norm": 1.4376217126846313, "learning_rate": 4.0217370262364664e-05, "loss": 0.4713231086730957, "step": 405870 }, { "epoch": 2.412635007816633, "grad_norm": 1.3339734077453613, "learning_rate": 4.0213439385627684e-05, "loss": 0.5193902492523194, "step": 405880 }, { "epoch": 2.4126944498933014, "grad_norm": 1.4454047679901123, "learning_rate": 4.02095088427268e-05, "loss": 0.5032523155212403, "step": 405890 }, { "epoch": 2.41275389196997, "grad_norm": 1.285570740699768, "learning_rate": 4.02055786336808e-05, "loss": 0.44417943954467776, "step": 405900 }, { "epoch": 2.4128133340466382, "grad_norm": 1.266597867012024, "learning_rate": 4.020164875850855e-05, "loss": 0.47640314102172854, "step": 405910 }, { "epoch": 2.4128727761233066, "grad_norm": 1.3289376497268677, "learning_rate": 4.019771921722877e-05, "loss": 0.4557488918304443, "step": 405920 }, { "epoch": 2.412932218199975, "grad_norm": 1.4754664897918701, "learning_rate": 4.0193790009860264e-05, "loss": 0.4640355587005615, "step": 405930 }, { "epoch": 2.4129916602766435, "grad_norm": 1.1060049533843994, "learning_rate": 4.018986113642189e-05, "loss": 0.4343897342681885, "step": 405940 }, { "epoch": 2.413051102353312, "grad_norm": 1.310182809829712, "learning_rate": 4.0185932596932394e-05, "loss": 0.48403520584106446, "step": 405950 }, { "epoch": 2.4131105444299803, "grad_norm": 1.1110813617706299, "learning_rate": 4.018200439141059e-05, "loss": 0.4668003559112549, "step": 405960 }, { "epoch": 2.4131699865066487, "grad_norm": 1.4261605739593506, "learning_rate": 4.017807651987525e-05, "loss": 0.5038900375366211, "step": 405970 }, { "epoch": 2.413229428583317, "grad_norm": 1.370509147644043, "learning_rate": 4.01741489823452e-05, "loss": 0.45896081924438475, "step": 405980 }, { "epoch": 2.4132888706599855, "grad_norm": 1.5421286821365356, "learning_rate": 4.0170221778839166e-05, "loss": 0.5194345474243164, "step": 405990 }, { "epoch": 2.413348312736654, "grad_norm": 1.4763389825820923, "learning_rate": 4.016629490937597e-05, "loss": 0.4988718032836914, "step": 406000 }, { "epoch": 2.4134077548133224, "grad_norm": 1.5630475282669067, "learning_rate": 4.016236837397442e-05, "loss": 0.5130638122558594, "step": 406010 }, { "epoch": 2.4134671968899903, "grad_norm": 1.4731030464172363, "learning_rate": 4.015844217265327e-05, "loss": 0.48815321922302246, "step": 406020 }, { "epoch": 2.4135266389666588, "grad_norm": 1.2835886478424072, "learning_rate": 4.015451630543131e-05, "loss": 0.49115891456604005, "step": 406030 }, { "epoch": 2.413586081043327, "grad_norm": 1.4565132856369019, "learning_rate": 4.015059077232731e-05, "loss": 0.4183177947998047, "step": 406040 }, { "epoch": 2.4136455231199956, "grad_norm": 1.2833878993988037, "learning_rate": 4.014666557336006e-05, "loss": 0.483231258392334, "step": 406050 }, { "epoch": 2.413704965196664, "grad_norm": 1.5918827056884766, "learning_rate": 4.014274070854832e-05, "loss": 0.4922363758087158, "step": 406060 }, { "epoch": 2.4137644072733324, "grad_norm": 1.3198877573013306, "learning_rate": 4.01388161779109e-05, "loss": 0.46323528289794924, "step": 406070 }, { "epoch": 2.413823849350001, "grad_norm": 1.5499539375305176, "learning_rate": 4.013489198146655e-05, "loss": 0.5030612468719482, "step": 406080 }, { "epoch": 2.4138832914266692, "grad_norm": 1.2373288869857788, "learning_rate": 4.013096811923405e-05, "loss": 0.445966911315918, "step": 406090 }, { "epoch": 2.4139427335033377, "grad_norm": 1.4111002683639526, "learning_rate": 4.012704459123215e-05, "loss": 0.4755441665649414, "step": 406100 }, { "epoch": 2.414002175580006, "grad_norm": 1.2449383735656738, "learning_rate": 4.012312139747965e-05, "loss": 0.4249244689941406, "step": 406110 }, { "epoch": 2.4140616176566745, "grad_norm": 1.782547950744629, "learning_rate": 4.011919853799528e-05, "loss": 0.49938321113586426, "step": 406120 }, { "epoch": 2.414121059733343, "grad_norm": 1.4439375400543213, "learning_rate": 4.011527601279782e-05, "loss": 0.49517126083374025, "step": 406130 }, { "epoch": 2.4141805018100113, "grad_norm": 1.216476321220398, "learning_rate": 4.011135382190606e-05, "loss": 0.49004554748535156, "step": 406140 }, { "epoch": 2.4142399438866797, "grad_norm": 1.4356111288070679, "learning_rate": 4.010743196533875e-05, "loss": 0.48730716705322263, "step": 406150 }, { "epoch": 2.414299385963348, "grad_norm": 1.0588340759277344, "learning_rate": 4.010351044311464e-05, "loss": 0.4892601013183594, "step": 406160 }, { "epoch": 2.4143588280400166, "grad_norm": 1.5194158554077148, "learning_rate": 4.009958925525249e-05, "loss": 0.5653277397155761, "step": 406170 }, { "epoch": 2.414418270116685, "grad_norm": 1.7498035430908203, "learning_rate": 4.009566840177108e-05, "loss": 0.4966271877288818, "step": 406180 }, { "epoch": 2.414477712193353, "grad_norm": 1.1833575963974, "learning_rate": 4.00917478826891e-05, "loss": 0.44990148544311526, "step": 406190 }, { "epoch": 2.414537154270022, "grad_norm": 1.477818489074707, "learning_rate": 4.0087827698025384e-05, "loss": 0.5324618816375732, "step": 406200 }, { "epoch": 2.4145965963466898, "grad_norm": 1.2171659469604492, "learning_rate": 4.0083907847798655e-05, "loss": 0.5087384223937989, "step": 406210 }, { "epoch": 2.414656038423358, "grad_norm": 1.1256718635559082, "learning_rate": 4.007998833202766e-05, "loss": 0.423679256439209, "step": 406220 }, { "epoch": 2.4147154805000266, "grad_norm": 1.279315710067749, "learning_rate": 4.0076069150731155e-05, "loss": 0.5140319347381592, "step": 406230 }, { "epoch": 2.414774922576695, "grad_norm": 1.3441380262374878, "learning_rate": 4.007215030392788e-05, "loss": 0.47459936141967773, "step": 406240 }, { "epoch": 2.4148343646533634, "grad_norm": 1.5750796794891357, "learning_rate": 4.006823179163658e-05, "loss": 0.5143115997314454, "step": 406250 }, { "epoch": 2.414893806730032, "grad_norm": 1.281705379486084, "learning_rate": 4.006431361387598e-05, "loss": 0.4362459182739258, "step": 406260 }, { "epoch": 2.4149532488067003, "grad_norm": 1.0230484008789062, "learning_rate": 4.0060395770664883e-05, "loss": 0.4788207054138184, "step": 406270 }, { "epoch": 2.4150126908833687, "grad_norm": 1.466023325920105, "learning_rate": 4.005647826202201e-05, "loss": 0.5094766616821289, "step": 406280 }, { "epoch": 2.415072132960037, "grad_norm": 1.1455364227294922, "learning_rate": 4.0052561087966055e-05, "loss": 0.4627561569213867, "step": 406290 }, { "epoch": 2.4151315750367055, "grad_norm": 1.5505229234695435, "learning_rate": 4.0048644248515796e-05, "loss": 0.48740625381469727, "step": 406300 }, { "epoch": 2.415191017113374, "grad_norm": 1.2787914276123047, "learning_rate": 4.004472774368997e-05, "loss": 0.4438755035400391, "step": 406310 }, { "epoch": 2.4152504591900423, "grad_norm": 1.9172000885009766, "learning_rate": 4.004081157350729e-05, "loss": 0.46509222984313964, "step": 406320 }, { "epoch": 2.4153099012667107, "grad_norm": 1.6452759504318237, "learning_rate": 4.0036895737986504e-05, "loss": 0.4985956192016602, "step": 406330 }, { "epoch": 2.415369343343379, "grad_norm": 1.2923994064331055, "learning_rate": 4.003298023714639e-05, "loss": 0.4677420616149902, "step": 406340 }, { "epoch": 2.4154287854200476, "grad_norm": 1.0223233699798584, "learning_rate": 4.00290650710056e-05, "loss": 0.4689894676208496, "step": 406350 }, { "epoch": 2.415488227496716, "grad_norm": 1.526374101638794, "learning_rate": 4.002515023958287e-05, "loss": 0.480635929107666, "step": 406360 }, { "epoch": 2.4155476695733844, "grad_norm": 1.053215503692627, "learning_rate": 4.002123574289699e-05, "loss": 0.4275707244873047, "step": 406370 }, { "epoch": 2.4156071116500524, "grad_norm": 1.1597340106964111, "learning_rate": 4.001732158096663e-05, "loss": 0.45620880126953123, "step": 406380 }, { "epoch": 2.4156665537267212, "grad_norm": 1.5818132162094116, "learning_rate": 4.0013407753810525e-05, "loss": 0.49222412109375, "step": 406390 }, { "epoch": 2.415725995803389, "grad_norm": 1.4416102170944214, "learning_rate": 4.000949426144745e-05, "loss": 0.4527097702026367, "step": 406400 }, { "epoch": 2.4157854378800576, "grad_norm": 1.366558313369751, "learning_rate": 4.000558110389605e-05, "loss": 0.4994607448577881, "step": 406410 }, { "epoch": 2.415844879956726, "grad_norm": 1.1997185945510864, "learning_rate": 4.000166828117505e-05, "loss": 0.46123814582824707, "step": 406420 }, { "epoch": 2.4159043220333944, "grad_norm": 1.1458286046981812, "learning_rate": 3.9997755793303224e-05, "loss": 0.4313218116760254, "step": 406430 }, { "epoch": 2.415963764110063, "grad_norm": 1.3620309829711914, "learning_rate": 3.9993843640299256e-05, "loss": 0.47335023880004884, "step": 406440 }, { "epoch": 2.4160232061867313, "grad_norm": 1.1836154460906982, "learning_rate": 3.998993182218185e-05, "loss": 0.45139241218566895, "step": 406450 }, { "epoch": 2.4160826482633997, "grad_norm": 1.0976225137710571, "learning_rate": 3.998602033896976e-05, "loss": 0.5182862281799316, "step": 406460 }, { "epoch": 2.416142090340068, "grad_norm": 1.0437923669815063, "learning_rate": 3.998210919068165e-05, "loss": 0.5033048152923584, "step": 406470 }, { "epoch": 2.4162015324167365, "grad_norm": 1.1894571781158447, "learning_rate": 3.997819837733625e-05, "loss": 0.48511757850646975, "step": 406480 }, { "epoch": 2.416260974493405, "grad_norm": 1.275378704071045, "learning_rate": 3.997428789895224e-05, "loss": 0.5525467395782471, "step": 406490 }, { "epoch": 2.4163204165700733, "grad_norm": 1.119855284690857, "learning_rate": 3.997037775554838e-05, "loss": 0.45160717964172364, "step": 406500 }, { "epoch": 2.4163798586467418, "grad_norm": 1.0413190126419067, "learning_rate": 3.996646794714334e-05, "loss": 0.5036168575286866, "step": 406510 }, { "epoch": 2.41643930072341, "grad_norm": 1.1896696090698242, "learning_rate": 3.9962558473755835e-05, "loss": 0.48798017501831054, "step": 406520 }, { "epoch": 2.4164987428000786, "grad_norm": 1.764486312866211, "learning_rate": 3.995864933540455e-05, "loss": 0.5055909156799316, "step": 406530 }, { "epoch": 2.416558184876747, "grad_norm": 1.4203872680664062, "learning_rate": 3.995474053210821e-05, "loss": 0.4614540100097656, "step": 406540 }, { "epoch": 2.4166176269534154, "grad_norm": 1.560721516609192, "learning_rate": 3.995083206388548e-05, "loss": 0.48606386184692385, "step": 406550 }, { "epoch": 2.416677069030084, "grad_norm": 1.390350103378296, "learning_rate": 3.994692393075509e-05, "loss": 0.5115394115447998, "step": 406560 }, { "epoch": 2.416736511106752, "grad_norm": 1.3134394884109497, "learning_rate": 3.9943016132735725e-05, "loss": 0.47340784072875974, "step": 406570 }, { "epoch": 2.4167959531834207, "grad_norm": 1.1788140535354614, "learning_rate": 3.993910866984607e-05, "loss": 0.43627176284790037, "step": 406580 }, { "epoch": 2.4168553952600886, "grad_norm": 1.2869914770126343, "learning_rate": 3.993520154210484e-05, "loss": 0.48322267532348634, "step": 406590 }, { "epoch": 2.416914837336757, "grad_norm": 1.1471165418624878, "learning_rate": 3.993129474953069e-05, "loss": 0.48595800399780276, "step": 406600 }, { "epoch": 2.4169742794134255, "grad_norm": 1.1015278100967407, "learning_rate": 3.992738829214234e-05, "loss": 0.46384434700012206, "step": 406610 }, { "epoch": 2.417033721490094, "grad_norm": 2.0305545330047607, "learning_rate": 3.992348216995844e-05, "loss": 0.44644827842712403, "step": 406620 }, { "epoch": 2.4170931635667623, "grad_norm": 1.231020212173462, "learning_rate": 3.991957638299773e-05, "loss": 0.49040722846984863, "step": 406630 }, { "epoch": 2.4171526056434307, "grad_norm": 1.1754810810089111, "learning_rate": 3.991567093127884e-05, "loss": 0.4605718612670898, "step": 406640 }, { "epoch": 2.417212047720099, "grad_norm": 1.0302006006240845, "learning_rate": 3.99117658148205e-05, "loss": 0.49565372467041013, "step": 406650 }, { "epoch": 2.4172714897967675, "grad_norm": 1.4734538793563843, "learning_rate": 3.990786103364135e-05, "loss": 0.498483943939209, "step": 406660 }, { "epoch": 2.417330931873436, "grad_norm": 1.5326848030090332, "learning_rate": 3.99039565877601e-05, "loss": 0.5050358772277832, "step": 406670 }, { "epoch": 2.4173903739501044, "grad_norm": 1.191542387008667, "learning_rate": 3.9900052477195374e-05, "loss": 0.5035896301269531, "step": 406680 }, { "epoch": 2.417449816026773, "grad_norm": 1.625120759010315, "learning_rate": 3.989614870196593e-05, "loss": 0.4957578659057617, "step": 406690 }, { "epoch": 2.417509258103441, "grad_norm": 1.0671558380126953, "learning_rate": 3.989224526209039e-05, "loss": 0.4907063007354736, "step": 406700 }, { "epoch": 2.4175687001801096, "grad_norm": 1.2487317323684692, "learning_rate": 3.988834215758747e-05, "loss": 0.4898810386657715, "step": 406710 }, { "epoch": 2.417628142256778, "grad_norm": 1.5519678592681885, "learning_rate": 3.9884439388475744e-05, "loss": 0.5359632968902588, "step": 406720 }, { "epoch": 2.4176875843334464, "grad_norm": 1.3096668720245361, "learning_rate": 3.988053695477399e-05, "loss": 0.4350618362426758, "step": 406730 }, { "epoch": 2.417747026410115, "grad_norm": 1.2795664072036743, "learning_rate": 3.9876634856500814e-05, "loss": 0.5022883415222168, "step": 406740 }, { "epoch": 2.4178064684867833, "grad_norm": 1.3162773847579956, "learning_rate": 3.9872733093674884e-05, "loss": 0.4969340324401855, "step": 406750 }, { "epoch": 2.4178659105634512, "grad_norm": 1.1123040914535522, "learning_rate": 3.986883166631491e-05, "loss": 0.4520726203918457, "step": 406760 }, { "epoch": 2.4179253526401197, "grad_norm": 1.038057804107666, "learning_rate": 3.9864930574439544e-05, "loss": 0.44966802597045896, "step": 406770 }, { "epoch": 2.417984794716788, "grad_norm": 1.3406511545181274, "learning_rate": 3.9861029818067384e-05, "loss": 0.4318796157836914, "step": 406780 }, { "epoch": 2.4180442367934565, "grad_norm": 1.5456126928329468, "learning_rate": 3.9857129397217165e-05, "loss": 0.4782561302185059, "step": 406790 }, { "epoch": 2.418103678870125, "grad_norm": 1.3756647109985352, "learning_rate": 3.9853229311907515e-05, "loss": 0.4736842155456543, "step": 406800 }, { "epoch": 2.4181631209467933, "grad_norm": 1.6388241052627563, "learning_rate": 3.9849329562157055e-05, "loss": 0.4659588813781738, "step": 406810 }, { "epoch": 2.4182225630234617, "grad_norm": 1.1707111597061157, "learning_rate": 3.984543014798451e-05, "loss": 0.4719153881072998, "step": 406820 }, { "epoch": 2.41828200510013, "grad_norm": 1.64951491355896, "learning_rate": 3.984153106940852e-05, "loss": 0.5215154170989991, "step": 406830 }, { "epoch": 2.4183414471767986, "grad_norm": 1.3694539070129395, "learning_rate": 3.983763232644769e-05, "loss": 0.4671815872192383, "step": 406840 }, { "epoch": 2.418400889253467, "grad_norm": 1.150329828262329, "learning_rate": 3.98337339191207e-05, "loss": 0.4518918037414551, "step": 406850 }, { "epoch": 2.4184603313301354, "grad_norm": 1.3744816780090332, "learning_rate": 3.982983584744618e-05, "loss": 0.48323583602905273, "step": 406860 }, { "epoch": 2.418519773406804, "grad_norm": 1.4310013055801392, "learning_rate": 3.982593811144282e-05, "loss": 0.528018856048584, "step": 406870 }, { "epoch": 2.418579215483472, "grad_norm": 1.0617376565933228, "learning_rate": 3.9822040711129217e-05, "loss": 0.47957944869995117, "step": 406880 }, { "epoch": 2.4186386575601406, "grad_norm": 1.1718868017196655, "learning_rate": 3.9818143646524076e-05, "loss": 0.5062811851501465, "step": 406890 }, { "epoch": 2.418698099636809, "grad_norm": 1.3282506465911865, "learning_rate": 3.981424691764597e-05, "loss": 0.4724289894104004, "step": 406900 }, { "epoch": 2.4187575417134775, "grad_norm": 1.2996515035629272, "learning_rate": 3.981035052451356e-05, "loss": 0.44540929794311523, "step": 406910 }, { "epoch": 2.418816983790146, "grad_norm": 1.590505838394165, "learning_rate": 3.98064544671455e-05, "loss": 0.5063193321228028, "step": 406920 }, { "epoch": 2.418876425866814, "grad_norm": 1.326450228691101, "learning_rate": 3.980255874556045e-05, "loss": 0.460523796081543, "step": 406930 }, { "epoch": 2.4189358679434827, "grad_norm": 1.1334295272827148, "learning_rate": 3.979866335977697e-05, "loss": 0.43602333068847654, "step": 406940 }, { "epoch": 2.4189953100201507, "grad_norm": 1.2691149711608887, "learning_rate": 3.97947683098138e-05, "loss": 0.4841309547424316, "step": 406950 }, { "epoch": 2.419054752096819, "grad_norm": 1.5576765537261963, "learning_rate": 3.979087359568949e-05, "loss": 0.4977270126342773, "step": 406960 }, { "epoch": 2.4191141941734875, "grad_norm": 1.6875489950180054, "learning_rate": 3.978697921742269e-05, "loss": 0.49656357765197756, "step": 406970 }, { "epoch": 2.419173636250156, "grad_norm": 1.54110586643219, "learning_rate": 3.9783085175032034e-05, "loss": 0.43393640518188475, "step": 406980 }, { "epoch": 2.4192330783268243, "grad_norm": 1.404412031173706, "learning_rate": 3.977919146853615e-05, "loss": 0.49804120063781737, "step": 406990 }, { "epoch": 2.4192925204034927, "grad_norm": 1.3598041534423828, "learning_rate": 3.9775298097953675e-05, "loss": 0.46848554611206056, "step": 407000 }, { "epoch": 2.419351962480161, "grad_norm": 1.3327661752700806, "learning_rate": 3.977140506330322e-05, "loss": 0.45608863830566404, "step": 407010 }, { "epoch": 2.4194114045568296, "grad_norm": 1.5522456169128418, "learning_rate": 3.976751236460342e-05, "loss": 0.45998420715332033, "step": 407020 }, { "epoch": 2.419470846633498, "grad_norm": 1.049358606338501, "learning_rate": 3.976362000187288e-05, "loss": 0.4837480545043945, "step": 407030 }, { "epoch": 2.4195302887101664, "grad_norm": 1.4565150737762451, "learning_rate": 3.975972797513021e-05, "loss": 0.488768196105957, "step": 407040 }, { "epoch": 2.419589730786835, "grad_norm": 1.1436028480529785, "learning_rate": 3.975583628439407e-05, "loss": 0.4774327278137207, "step": 407050 }, { "epoch": 2.4196491728635032, "grad_norm": 1.2548253536224365, "learning_rate": 3.975194492968305e-05, "loss": 0.46326384544372556, "step": 407060 }, { "epoch": 2.4197086149401716, "grad_norm": 1.25234055519104, "learning_rate": 3.974805391101577e-05, "loss": 0.45224642753601074, "step": 407070 }, { "epoch": 2.41976805701684, "grad_norm": 1.1509666442871094, "learning_rate": 3.974416322841084e-05, "loss": 0.4408577919006348, "step": 407080 }, { "epoch": 2.4198274990935085, "grad_norm": 1.0979681015014648, "learning_rate": 3.9740272881886876e-05, "loss": 0.4686923027038574, "step": 407090 }, { "epoch": 2.419886941170177, "grad_norm": 1.0871758460998535, "learning_rate": 3.973638287146249e-05, "loss": 0.5100133419036865, "step": 407100 }, { "epoch": 2.4199463832468453, "grad_norm": 1.2866801023483276, "learning_rate": 3.973249319715625e-05, "loss": 0.47173357009887695, "step": 407110 }, { "epoch": 2.4200058253235133, "grad_norm": 1.195428490638733, "learning_rate": 3.972860385898684e-05, "loss": 0.47109346389770507, "step": 407120 }, { "epoch": 2.420065267400182, "grad_norm": 1.1999446153640747, "learning_rate": 3.972471485697281e-05, "loss": 0.4649944305419922, "step": 407130 }, { "epoch": 2.42012470947685, "grad_norm": 0.9061934351921082, "learning_rate": 3.972082619113279e-05, "loss": 0.4593463897705078, "step": 407140 }, { "epoch": 2.4201841515535185, "grad_norm": 1.2985414266586304, "learning_rate": 3.9716937861485356e-05, "loss": 0.5076463699340821, "step": 407150 }, { "epoch": 2.420243593630187, "grad_norm": 1.2399287223815918, "learning_rate": 3.971304986804912e-05, "loss": 0.49726500511169436, "step": 407160 }, { "epoch": 2.4203030357068553, "grad_norm": 1.563044786453247, "learning_rate": 3.9709162210842674e-05, "loss": 0.48610568046569824, "step": 407170 }, { "epoch": 2.4203624777835238, "grad_norm": 1.6290538311004639, "learning_rate": 3.9705274889884645e-05, "loss": 0.4916093826293945, "step": 407180 }, { "epoch": 2.420421919860192, "grad_norm": 1.2621068954467773, "learning_rate": 3.97013879051936e-05, "loss": 0.5157026290893555, "step": 407190 }, { "epoch": 2.4204813619368606, "grad_norm": 1.3697139024734497, "learning_rate": 3.969750125678815e-05, "loss": 0.4731163501739502, "step": 407200 }, { "epoch": 2.420540804013529, "grad_norm": 1.492871642112732, "learning_rate": 3.9693614944686875e-05, "loss": 0.5332382202148438, "step": 407210 }, { "epoch": 2.4206002460901974, "grad_norm": 1.2993559837341309, "learning_rate": 3.968972896890837e-05, "loss": 0.48950958251953125, "step": 407220 }, { "epoch": 2.420659688166866, "grad_norm": 1.2489348649978638, "learning_rate": 3.968584332947122e-05, "loss": 0.49378376007080077, "step": 407230 }, { "epoch": 2.4207191302435342, "grad_norm": 0.9984546899795532, "learning_rate": 3.9681958026393996e-05, "loss": 0.5063748359680176, "step": 407240 }, { "epoch": 2.4207785723202027, "grad_norm": 1.2637214660644531, "learning_rate": 3.967807305969533e-05, "loss": 0.5008777618408203, "step": 407250 }, { "epoch": 2.420838014396871, "grad_norm": 1.2058130502700806, "learning_rate": 3.9674188429393785e-05, "loss": 0.43912830352783205, "step": 407260 }, { "epoch": 2.4208974564735395, "grad_norm": 1.446571707725525, "learning_rate": 3.967030413550794e-05, "loss": 0.4823304176330566, "step": 407270 }, { "epoch": 2.420956898550208, "grad_norm": 1.2272495031356812, "learning_rate": 3.966642017805637e-05, "loss": 0.4835169315338135, "step": 407280 }, { "epoch": 2.4210163406268763, "grad_norm": 1.190398097038269, "learning_rate": 3.966253655705766e-05, "loss": 0.47188873291015626, "step": 407290 }, { "epoch": 2.4210757827035447, "grad_norm": 1.3677921295166016, "learning_rate": 3.965865327253037e-05, "loss": 0.4995423793792725, "step": 407300 }, { "epoch": 2.4211352247802127, "grad_norm": 1.2244373559951782, "learning_rate": 3.965477032449312e-05, "loss": 0.45505390167236326, "step": 407310 }, { "epoch": 2.4211946668568816, "grad_norm": 1.4763319492340088, "learning_rate": 3.965088771296447e-05, "loss": 0.45143561363220214, "step": 407320 }, { "epoch": 2.4212541089335495, "grad_norm": 1.2272372245788574, "learning_rate": 3.964700543796297e-05, "loss": 0.4877312183380127, "step": 407330 }, { "epoch": 2.421313551010218, "grad_norm": 1.0360246896743774, "learning_rate": 3.9643123499507184e-05, "loss": 0.4900666236877441, "step": 407340 }, { "epoch": 2.4213729930868864, "grad_norm": 1.420737385749817, "learning_rate": 3.963924189761571e-05, "loss": 0.4742580413818359, "step": 407350 }, { "epoch": 2.4214324351635548, "grad_norm": 1.2378009557724, "learning_rate": 3.963536063230713e-05, "loss": 0.5087643623352051, "step": 407360 }, { "epoch": 2.421491877240223, "grad_norm": 1.2059868574142456, "learning_rate": 3.9631479703599957e-05, "loss": 0.4612330436706543, "step": 407370 }, { "epoch": 2.4215513193168916, "grad_norm": 1.3967772722244263, "learning_rate": 3.9627599111512826e-05, "loss": 0.5178224563598632, "step": 407380 }, { "epoch": 2.42161076139356, "grad_norm": 1.3528212308883667, "learning_rate": 3.962371885606425e-05, "loss": 0.44478483200073243, "step": 407390 }, { "epoch": 2.4216702034702284, "grad_norm": 1.2897626161575317, "learning_rate": 3.961983893727278e-05, "loss": 0.4724876403808594, "step": 407400 }, { "epoch": 2.421729645546897, "grad_norm": 1.4069017171859741, "learning_rate": 3.961595935515702e-05, "loss": 0.4686625003814697, "step": 407410 }, { "epoch": 2.4217890876235653, "grad_norm": 1.797971248626709, "learning_rate": 3.961208010973551e-05, "loss": 0.5169253349304199, "step": 407420 }, { "epoch": 2.4218485297002337, "grad_norm": 1.0027543306350708, "learning_rate": 3.9608201201026784e-05, "loss": 0.45951337814331056, "step": 407430 }, { "epoch": 2.421907971776902, "grad_norm": 1.4761425256729126, "learning_rate": 3.960432262904946e-05, "loss": 0.4646498203277588, "step": 407440 }, { "epoch": 2.4219674138535705, "grad_norm": 0.9341731071472168, "learning_rate": 3.9600444393822034e-05, "loss": 0.48706827163696287, "step": 407450 }, { "epoch": 2.422026855930239, "grad_norm": 1.1719883680343628, "learning_rate": 3.9596566495363075e-05, "loss": 0.43304786682128904, "step": 407460 }, { "epoch": 2.4220862980069073, "grad_norm": 1.2388019561767578, "learning_rate": 3.9592688933691104e-05, "loss": 0.44689321517944336, "step": 407470 }, { "epoch": 2.4221457400835757, "grad_norm": 1.6026691198349, "learning_rate": 3.958881170882472e-05, "loss": 0.44251060485839844, "step": 407480 }, { "epoch": 2.422205182160244, "grad_norm": 1.4122344255447388, "learning_rate": 3.958493482078247e-05, "loss": 0.47994003295898435, "step": 407490 }, { "epoch": 2.422264624236912, "grad_norm": 1.3126235008239746, "learning_rate": 3.958105826958286e-05, "loss": 0.46401262283325195, "step": 407500 }, { "epoch": 2.4223240663135805, "grad_norm": 1.5458539724349976, "learning_rate": 3.9577182055244467e-05, "loss": 0.46964397430419924, "step": 407510 }, { "epoch": 2.422383508390249, "grad_norm": 1.442017912864685, "learning_rate": 3.9573306177785804e-05, "loss": 0.46648263931274414, "step": 407520 }, { "epoch": 2.4224429504669174, "grad_norm": 1.4231144189834595, "learning_rate": 3.9569430637225424e-05, "loss": 0.5021376609802246, "step": 407530 }, { "epoch": 2.422502392543586, "grad_norm": 1.514729380607605, "learning_rate": 3.956555543358189e-05, "loss": 0.4619881629943848, "step": 407540 }, { "epoch": 2.422561834620254, "grad_norm": 1.4328633546829224, "learning_rate": 3.956168056687371e-05, "loss": 0.460215425491333, "step": 407550 }, { "epoch": 2.4226212766969226, "grad_norm": 1.2074986696243286, "learning_rate": 3.9557806037119436e-05, "loss": 0.41649503707885743, "step": 407560 }, { "epoch": 2.422680718773591, "grad_norm": 1.4754308462142944, "learning_rate": 3.9553931844337606e-05, "loss": 0.4881406784057617, "step": 407570 }, { "epoch": 2.4227401608502594, "grad_norm": 1.300437092781067, "learning_rate": 3.9550057988546743e-05, "loss": 0.48139204978942873, "step": 407580 }, { "epoch": 2.422799602926928, "grad_norm": 1.504508137702942, "learning_rate": 3.954618446976537e-05, "loss": 0.4970503807067871, "step": 407590 }, { "epoch": 2.4228590450035963, "grad_norm": 1.6405975818634033, "learning_rate": 3.9542311288012e-05, "loss": 0.4976038932800293, "step": 407600 }, { "epoch": 2.4229184870802647, "grad_norm": 1.2957895994186401, "learning_rate": 3.9538438443305215e-05, "loss": 0.5161134719848632, "step": 407610 }, { "epoch": 2.422977929156933, "grad_norm": 1.3410050868988037, "learning_rate": 3.953456593566352e-05, "loss": 0.4707308769226074, "step": 407620 }, { "epoch": 2.4230373712336015, "grad_norm": 1.3994578123092651, "learning_rate": 3.9530693765105425e-05, "loss": 0.4593240737915039, "step": 407630 }, { "epoch": 2.42309681331027, "grad_norm": 1.3448195457458496, "learning_rate": 3.9526821931649465e-05, "loss": 0.4538626194000244, "step": 407640 }, { "epoch": 2.4231562553869384, "grad_norm": 1.4106556177139282, "learning_rate": 3.952295043531416e-05, "loss": 0.45330243110656737, "step": 407650 }, { "epoch": 2.4232156974636068, "grad_norm": 1.5527688264846802, "learning_rate": 3.9519079276118e-05, "loss": 0.49807162284851075, "step": 407660 }, { "epoch": 2.4232751395402747, "grad_norm": 1.3791049718856812, "learning_rate": 3.951520845407955e-05, "loss": 0.5074292182922363, "step": 407670 }, { "epoch": 2.4233345816169436, "grad_norm": 1.3125144243240356, "learning_rate": 3.9511337969217325e-05, "loss": 0.5002097606658935, "step": 407680 }, { "epoch": 2.4233940236936116, "grad_norm": 1.2386361360549927, "learning_rate": 3.950746782154981e-05, "loss": 0.5255715847015381, "step": 407690 }, { "epoch": 2.42345346577028, "grad_norm": 1.3452335596084595, "learning_rate": 3.950359801109553e-05, "loss": 0.4708362579345703, "step": 407700 }, { "epoch": 2.4235129078469484, "grad_norm": 1.3151819705963135, "learning_rate": 3.9499728537873e-05, "loss": 0.4783933639526367, "step": 407710 }, { "epoch": 2.423572349923617, "grad_norm": 1.3327500820159912, "learning_rate": 3.949585940190074e-05, "loss": 0.4885688781738281, "step": 407720 }, { "epoch": 2.4236317920002852, "grad_norm": 1.2708163261413574, "learning_rate": 3.949199060319721e-05, "loss": 0.47943649291992185, "step": 407730 }, { "epoch": 2.4236912340769536, "grad_norm": 1.7143632173538208, "learning_rate": 3.948812214178098e-05, "loss": 0.5090510845184326, "step": 407740 }, { "epoch": 2.423750676153622, "grad_norm": 1.2102524042129517, "learning_rate": 3.948425401767054e-05, "loss": 0.47090420722961424, "step": 407750 }, { "epoch": 2.4238101182302905, "grad_norm": 1.2564750909805298, "learning_rate": 3.948038623088438e-05, "loss": 0.4968820571899414, "step": 407760 }, { "epoch": 2.423869560306959, "grad_norm": 1.298761010169983, "learning_rate": 3.9476518781441e-05, "loss": 0.4898689270019531, "step": 407770 }, { "epoch": 2.4239290023836273, "grad_norm": 1.3950624465942383, "learning_rate": 3.9472651669358915e-05, "loss": 0.4202129364013672, "step": 407780 }, { "epoch": 2.4239884444602957, "grad_norm": 1.2969295978546143, "learning_rate": 3.946878489465658e-05, "loss": 0.434641170501709, "step": 407790 }, { "epoch": 2.424047886536964, "grad_norm": 1.5294400453567505, "learning_rate": 3.946491845735257e-05, "loss": 0.4172471046447754, "step": 407800 }, { "epoch": 2.4241073286136325, "grad_norm": 1.5092921257019043, "learning_rate": 3.946105235746532e-05, "loss": 0.4600072860717773, "step": 407810 }, { "epoch": 2.424166770690301, "grad_norm": 1.3319987058639526, "learning_rate": 3.9457186595013385e-05, "loss": 0.5013959884643555, "step": 407820 }, { "epoch": 2.4242262127669694, "grad_norm": 1.4606289863586426, "learning_rate": 3.9453321170015153e-05, "loss": 0.47333130836486814, "step": 407830 }, { "epoch": 2.424285654843638, "grad_norm": 1.2489972114562988, "learning_rate": 3.9449456082489214e-05, "loss": 0.5106148719787598, "step": 407840 }, { "epoch": 2.424345096920306, "grad_norm": 1.337201714515686, "learning_rate": 3.944559133245401e-05, "loss": 0.5266159057617188, "step": 407850 }, { "epoch": 2.424404538996974, "grad_norm": 1.1775048971176147, "learning_rate": 3.9441726919928016e-05, "loss": 0.42926864624023436, "step": 407860 }, { "epoch": 2.424463981073643, "grad_norm": 1.1792194843292236, "learning_rate": 3.943786284492977e-05, "loss": 0.5269716262817383, "step": 407870 }, { "epoch": 2.424523423150311, "grad_norm": 0.9681718349456787, "learning_rate": 3.943399910747777e-05, "loss": 0.4783296585083008, "step": 407880 }, { "epoch": 2.4245828652269794, "grad_norm": 1.068273663520813, "learning_rate": 3.9430135707590375e-05, "loss": 0.4578911781311035, "step": 407890 }, { "epoch": 2.424642307303648, "grad_norm": 1.042455792427063, "learning_rate": 3.94262726452862e-05, "loss": 0.5266796112060547, "step": 407900 }, { "epoch": 2.4247017493803162, "grad_norm": 1.2845968008041382, "learning_rate": 3.942240992058366e-05, "loss": 0.47853717803955076, "step": 407910 }, { "epoch": 2.4247611914569847, "grad_norm": 1.3412591218948364, "learning_rate": 3.941854753350121e-05, "loss": 0.47470769882202146, "step": 407920 }, { "epoch": 2.424820633533653, "grad_norm": 1.2512775659561157, "learning_rate": 3.941468548405741e-05, "loss": 0.42560806274414065, "step": 407930 }, { "epoch": 2.4248800756103215, "grad_norm": 1.4673842191696167, "learning_rate": 3.94108237722707e-05, "loss": 0.5195765018463134, "step": 407940 }, { "epoch": 2.42493951768699, "grad_norm": 1.3216309547424316, "learning_rate": 3.940696239815952e-05, "loss": 0.4809162139892578, "step": 407950 }, { "epoch": 2.4249989597636583, "grad_norm": 1.31138014793396, "learning_rate": 3.940310136174233e-05, "loss": 0.4490815162658691, "step": 407960 }, { "epoch": 2.4250584018403267, "grad_norm": 1.344875454902649, "learning_rate": 3.939924066303766e-05, "loss": 0.5274636268615722, "step": 407970 }, { "epoch": 2.425117843916995, "grad_norm": 1.499836802482605, "learning_rate": 3.9395380302063954e-05, "loss": 0.46659250259399415, "step": 407980 }, { "epoch": 2.4251772859936636, "grad_norm": 1.3635857105255127, "learning_rate": 3.939152027883967e-05, "loss": 0.4871523857116699, "step": 407990 }, { "epoch": 2.425236728070332, "grad_norm": 1.2258306741714478, "learning_rate": 3.938766059338328e-05, "loss": 0.5017947196960449, "step": 408000 }, { "epoch": 2.4252961701470004, "grad_norm": 1.1444363594055176, "learning_rate": 3.938380124571325e-05, "loss": 0.4601407527923584, "step": 408010 }, { "epoch": 2.425355612223669, "grad_norm": 1.3315513134002686, "learning_rate": 3.9379942235848e-05, "loss": 0.4998181819915771, "step": 408020 }, { "epoch": 2.425415054300337, "grad_norm": 1.8999720811843872, "learning_rate": 3.9376083563806066e-05, "loss": 0.553221321105957, "step": 408030 }, { "epoch": 2.4254744963770056, "grad_norm": 1.3081939220428467, "learning_rate": 3.937222522960586e-05, "loss": 0.469594669342041, "step": 408040 }, { "epoch": 2.4255339384536736, "grad_norm": 1.208778977394104, "learning_rate": 3.9368367233265844e-05, "loss": 0.43750991821289065, "step": 408050 }, { "epoch": 2.4255933805303425, "grad_norm": 1.475806474685669, "learning_rate": 3.936450957480449e-05, "loss": 0.527297067642212, "step": 408060 }, { "epoch": 2.4256528226070104, "grad_norm": 0.8686472773551941, "learning_rate": 3.9360652254240225e-05, "loss": 0.4487194061279297, "step": 408070 }, { "epoch": 2.425712264683679, "grad_norm": 1.571790337562561, "learning_rate": 3.9356795271591515e-05, "loss": 0.49030070304870604, "step": 408080 }, { "epoch": 2.4257717067603473, "grad_norm": 1.0897594690322876, "learning_rate": 3.9352938626876804e-05, "loss": 0.5147405624389648, "step": 408090 }, { "epoch": 2.4258311488370157, "grad_norm": 1.4470603466033936, "learning_rate": 3.934908232011455e-05, "loss": 0.4769341468811035, "step": 408100 }, { "epoch": 2.425890590913684, "grad_norm": 1.3166106939315796, "learning_rate": 3.934522635132321e-05, "loss": 0.48011932373046873, "step": 408110 }, { "epoch": 2.4259500329903525, "grad_norm": 1.3096418380737305, "learning_rate": 3.9341370720521204e-05, "loss": 0.46977667808532714, "step": 408120 }, { "epoch": 2.426009475067021, "grad_norm": 1.21260404586792, "learning_rate": 3.9337515427726995e-05, "loss": 0.5103646278381347, "step": 408130 }, { "epoch": 2.4260689171436893, "grad_norm": 1.434653878211975, "learning_rate": 3.933366047295902e-05, "loss": 0.503373670578003, "step": 408140 }, { "epoch": 2.4261283592203577, "grad_norm": 1.4197838306427002, "learning_rate": 3.9329805856235694e-05, "loss": 0.526353120803833, "step": 408150 }, { "epoch": 2.426187801297026, "grad_norm": 1.3846793174743652, "learning_rate": 3.932595157757551e-05, "loss": 0.5008665561676026, "step": 408160 }, { "epoch": 2.4262472433736946, "grad_norm": 1.1595622301101685, "learning_rate": 3.932209763699688e-05, "loss": 0.49103827476501466, "step": 408170 }, { "epoch": 2.426306685450363, "grad_norm": 1.4025912284851074, "learning_rate": 3.9318244034518225e-05, "loss": 0.4251716613769531, "step": 408180 }, { "epoch": 2.4263661275270314, "grad_norm": 1.6256924867630005, "learning_rate": 3.9314390770157996e-05, "loss": 0.4615875244140625, "step": 408190 }, { "epoch": 2.4264255696037, "grad_norm": 1.5435224771499634, "learning_rate": 3.9310537843934626e-05, "loss": 0.48647022247314453, "step": 408200 }, { "epoch": 2.4264850116803682, "grad_norm": 1.488526701927185, "learning_rate": 3.9306685255866536e-05, "loss": 0.4691436767578125, "step": 408210 }, { "epoch": 2.4265444537570366, "grad_norm": 1.72270929813385, "learning_rate": 3.930283300597214e-05, "loss": 0.4970371246337891, "step": 408220 }, { "epoch": 2.426603895833705, "grad_norm": 1.1367076635360718, "learning_rate": 3.9298981094269914e-05, "loss": 0.5202860832214355, "step": 408230 }, { "epoch": 2.426663337910373, "grad_norm": 0.9117431044578552, "learning_rate": 3.9295129520778253e-05, "loss": 0.45278110504150393, "step": 408240 }, { "epoch": 2.4267227799870414, "grad_norm": 1.3842846155166626, "learning_rate": 3.929127828551559e-05, "loss": 0.4670257568359375, "step": 408250 }, { "epoch": 2.42678222206371, "grad_norm": 1.4270319938659668, "learning_rate": 3.928742738850033e-05, "loss": 0.48192248344421384, "step": 408260 }, { "epoch": 2.4268416641403783, "grad_norm": 1.157596230506897, "learning_rate": 3.928357682975091e-05, "loss": 0.49698677062988283, "step": 408270 }, { "epoch": 2.4269011062170467, "grad_norm": 1.3190420866012573, "learning_rate": 3.927972660928574e-05, "loss": 0.47687878608703616, "step": 408280 }, { "epoch": 2.426960548293715, "grad_norm": 1.423598051071167, "learning_rate": 3.927587672712327e-05, "loss": 0.4547414779663086, "step": 408290 }, { "epoch": 2.4270199903703835, "grad_norm": 1.4645463228225708, "learning_rate": 3.9272027183281884e-05, "loss": 0.5120314121246338, "step": 408300 }, { "epoch": 2.427079432447052, "grad_norm": 1.3041107654571533, "learning_rate": 3.9268177977780026e-05, "loss": 0.46817493438720703, "step": 408310 }, { "epoch": 2.4271388745237203, "grad_norm": 1.4882203340530396, "learning_rate": 3.926432911063605e-05, "loss": 0.46074914932250977, "step": 408320 }, { "epoch": 2.4271983166003888, "grad_norm": 1.1377793550491333, "learning_rate": 3.926048058186842e-05, "loss": 0.4815349578857422, "step": 408330 }, { "epoch": 2.427257758677057, "grad_norm": 1.7053043842315674, "learning_rate": 3.925663239149554e-05, "loss": 0.45131874084472656, "step": 408340 }, { "epoch": 2.4273172007537256, "grad_norm": 1.3571126461029053, "learning_rate": 3.925278453953579e-05, "loss": 0.4758729934692383, "step": 408350 }, { "epoch": 2.427376642830394, "grad_norm": 1.109222650527954, "learning_rate": 3.9248937026007616e-05, "loss": 0.5079649448394775, "step": 408360 }, { "epoch": 2.4274360849070624, "grad_norm": 1.3444042205810547, "learning_rate": 3.924508985092944e-05, "loss": 0.4488205909729004, "step": 408370 }, { "epoch": 2.427495526983731, "grad_norm": 1.5949369668960571, "learning_rate": 3.924124301431957e-05, "loss": 0.4667018413543701, "step": 408380 }, { "epoch": 2.4275549690603992, "grad_norm": 1.624483585357666, "learning_rate": 3.923739651619651e-05, "loss": 0.47031683921813966, "step": 408390 }, { "epoch": 2.4276144111370677, "grad_norm": 1.3589993715286255, "learning_rate": 3.923355035657861e-05, "loss": 0.4672404766082764, "step": 408400 }, { "epoch": 2.4276738532137356, "grad_norm": 0.9883851408958435, "learning_rate": 3.922970453548427e-05, "loss": 0.52217116355896, "step": 408410 }, { "epoch": 2.4277332952904045, "grad_norm": 1.3627393245697021, "learning_rate": 3.9225859052931876e-05, "loss": 0.46504840850830076, "step": 408420 }, { "epoch": 2.4277927373670725, "grad_norm": 1.711722731590271, "learning_rate": 3.92220139089399e-05, "loss": 0.47678632736206056, "step": 408430 }, { "epoch": 2.427852179443741, "grad_norm": 1.1940544843673706, "learning_rate": 3.921816910352665e-05, "loss": 0.47432842254638674, "step": 408440 }, { "epoch": 2.4279116215204093, "grad_norm": 1.1464037895202637, "learning_rate": 3.921432463671052e-05, "loss": 0.4494197368621826, "step": 408450 }, { "epoch": 2.4279710635970777, "grad_norm": 1.2427846193313599, "learning_rate": 3.921048050850995e-05, "loss": 0.49265012741088865, "step": 408460 }, { "epoch": 2.428030505673746, "grad_norm": 1.2790354490280151, "learning_rate": 3.9206636718943314e-05, "loss": 0.48070669174194336, "step": 408470 }, { "epoch": 2.4280899477504145, "grad_norm": 1.1897335052490234, "learning_rate": 3.9202793268028964e-05, "loss": 0.48322277069091796, "step": 408480 }, { "epoch": 2.428149389827083, "grad_norm": 1.3617517948150635, "learning_rate": 3.919895015578536e-05, "loss": 0.4824169158935547, "step": 408490 }, { "epoch": 2.4282088319037514, "grad_norm": 1.4362305402755737, "learning_rate": 3.9195107382230833e-05, "loss": 0.4746638298034668, "step": 408500 }, { "epoch": 2.42826827398042, "grad_norm": 1.2349060773849487, "learning_rate": 3.919126494738373e-05, "loss": 0.5017933368682861, "step": 408510 }, { "epoch": 2.428327716057088, "grad_norm": 1.5589956045150757, "learning_rate": 3.9187422851262505e-05, "loss": 0.4328606605529785, "step": 408520 }, { "epoch": 2.4283871581337566, "grad_norm": 1.3968528509140015, "learning_rate": 3.91835810938855e-05, "loss": 0.5163383960723877, "step": 408530 }, { "epoch": 2.428446600210425, "grad_norm": 1.186471939086914, "learning_rate": 3.917973967527112e-05, "loss": 0.4754115104675293, "step": 408540 }, { "epoch": 2.4285060422870934, "grad_norm": 1.57330322265625, "learning_rate": 3.91758985954377e-05, "loss": 0.4950541973114014, "step": 408550 }, { "epoch": 2.428565484363762, "grad_norm": 1.3775545358657837, "learning_rate": 3.917205785440365e-05, "loss": 0.4846597194671631, "step": 408560 }, { "epoch": 2.4286249264404303, "grad_norm": 1.4346630573272705, "learning_rate": 3.916821745218733e-05, "loss": 0.5279376983642579, "step": 408570 }, { "epoch": 2.4286843685170987, "grad_norm": 1.1435552835464478, "learning_rate": 3.9164377388807074e-05, "loss": 0.527769660949707, "step": 408580 }, { "epoch": 2.428743810593767, "grad_norm": 1.5817278623580933, "learning_rate": 3.916053766428131e-05, "loss": 0.5082954406738281, "step": 408590 }, { "epoch": 2.428803252670435, "grad_norm": 1.3665361404418945, "learning_rate": 3.915669827862839e-05, "loss": 0.509931993484497, "step": 408600 }, { "epoch": 2.428862694747104, "grad_norm": 1.3210996389389038, "learning_rate": 3.915285923186668e-05, "loss": 0.5321603298187256, "step": 408610 }, { "epoch": 2.428922136823772, "grad_norm": 1.3501027822494507, "learning_rate": 3.914902052401452e-05, "loss": 0.4569377422332764, "step": 408620 }, { "epoch": 2.4289815789004403, "grad_norm": 1.5910159349441528, "learning_rate": 3.914518215509031e-05, "loss": 0.4682962417602539, "step": 408630 }, { "epoch": 2.4290410209771087, "grad_norm": 1.2036821842193604, "learning_rate": 3.9141344125112355e-05, "loss": 0.5240160942077636, "step": 408640 }, { "epoch": 2.429100463053777, "grad_norm": 1.3683464527130127, "learning_rate": 3.913750643409908e-05, "loss": 0.4578455924987793, "step": 408650 }, { "epoch": 2.4291599051304456, "grad_norm": 1.1534796953201294, "learning_rate": 3.913366908206882e-05, "loss": 0.511817455291748, "step": 408660 }, { "epoch": 2.429219347207114, "grad_norm": 1.6817436218261719, "learning_rate": 3.912983206903993e-05, "loss": 0.5196304798126221, "step": 408670 }, { "epoch": 2.4292787892837824, "grad_norm": 1.2044193744659424, "learning_rate": 3.912599539503076e-05, "loss": 0.5141258239746094, "step": 408680 }, { "epoch": 2.429338231360451, "grad_norm": 1.4053438901901245, "learning_rate": 3.912215906005967e-05, "loss": 0.46513876914978025, "step": 408690 }, { "epoch": 2.429397673437119, "grad_norm": 1.6293463706970215, "learning_rate": 3.9118323064144996e-05, "loss": 0.5184112071990967, "step": 408700 }, { "epoch": 2.4294571155137876, "grad_norm": 1.5462002754211426, "learning_rate": 3.911448740730509e-05, "loss": 0.466873025894165, "step": 408710 }, { "epoch": 2.429516557590456, "grad_norm": 1.320188045501709, "learning_rate": 3.911065208955833e-05, "loss": 0.5049553871154785, "step": 408720 }, { "epoch": 2.4295759996671245, "grad_norm": 1.127974510192871, "learning_rate": 3.910681711092303e-05, "loss": 0.47560915946960447, "step": 408730 }, { "epoch": 2.429635441743793, "grad_norm": 1.4874367713928223, "learning_rate": 3.910298247141757e-05, "loss": 0.4957103252410889, "step": 408740 }, { "epoch": 2.4296948838204613, "grad_norm": 1.4604166746139526, "learning_rate": 3.909914817106026e-05, "loss": 0.46453156471252444, "step": 408750 }, { "epoch": 2.4297543258971297, "grad_norm": 1.6154757738113403, "learning_rate": 3.909531420986946e-05, "loss": 0.48042001724243166, "step": 408760 }, { "epoch": 2.429813767973798, "grad_norm": 1.3691916465759277, "learning_rate": 3.909148058786348e-05, "loss": 0.4807013511657715, "step": 408770 }, { "epoch": 2.4298732100504665, "grad_norm": 1.191325068473816, "learning_rate": 3.90876473050607e-05, "loss": 0.4894845485687256, "step": 408780 }, { "epoch": 2.4299326521271345, "grad_norm": 1.5517430305480957, "learning_rate": 3.9083814361479454e-05, "loss": 0.5337408542633056, "step": 408790 }, { "epoch": 2.429992094203803, "grad_norm": 1.276501178741455, "learning_rate": 3.907998175713808e-05, "loss": 0.4171931266784668, "step": 408800 }, { "epoch": 2.4300515362804713, "grad_norm": 1.80497407913208, "learning_rate": 3.907614949205485e-05, "loss": 0.525997257232666, "step": 408810 }, { "epoch": 2.4301109783571397, "grad_norm": 1.3737285137176514, "learning_rate": 3.907231756624816e-05, "loss": 0.4918947696685791, "step": 408820 }, { "epoch": 2.430170420433808, "grad_norm": 0.9921528100967407, "learning_rate": 3.906848597973634e-05, "loss": 0.4962922096252441, "step": 408830 }, { "epoch": 2.4302298625104766, "grad_norm": 1.121476411819458, "learning_rate": 3.906465473253767e-05, "loss": 0.4390530586242676, "step": 408840 }, { "epoch": 2.430289304587145, "grad_norm": 2.1530539989471436, "learning_rate": 3.9060823824670525e-05, "loss": 0.521169376373291, "step": 408850 }, { "epoch": 2.4303487466638134, "grad_norm": 1.3928929567337036, "learning_rate": 3.905699325615325e-05, "loss": 0.4903294086456299, "step": 408860 }, { "epoch": 2.430408188740482, "grad_norm": 1.5528531074523926, "learning_rate": 3.905316302700408e-05, "loss": 0.4429995059967041, "step": 408870 }, { "epoch": 2.4304676308171502, "grad_norm": 0.9147382974624634, "learning_rate": 3.904933313724142e-05, "loss": 0.42528371810913085, "step": 408880 }, { "epoch": 2.4305270728938186, "grad_norm": 1.5093568563461304, "learning_rate": 3.904550358688356e-05, "loss": 0.4689091682434082, "step": 408890 }, { "epoch": 2.430586514970487, "grad_norm": 1.6710578203201294, "learning_rate": 3.904167437594883e-05, "loss": 0.5387807846069336, "step": 408900 }, { "epoch": 2.4306459570471555, "grad_norm": 1.2467432022094727, "learning_rate": 3.9037845504455504e-05, "loss": 0.5289892196655274, "step": 408910 }, { "epoch": 2.430705399123824, "grad_norm": 1.1974828243255615, "learning_rate": 3.9034016972421996e-05, "loss": 0.4589097499847412, "step": 408920 }, { "epoch": 2.4307648412004923, "grad_norm": 1.534870982170105, "learning_rate": 3.9030188779866526e-05, "loss": 0.5355682373046875, "step": 408930 }, { "epoch": 2.4308242832771607, "grad_norm": 1.4582270383834839, "learning_rate": 3.902636092680741e-05, "loss": 0.5013117313385009, "step": 408940 }, { "epoch": 2.430883725353829, "grad_norm": 1.0044173002243042, "learning_rate": 3.902253341326303e-05, "loss": 0.46944341659545896, "step": 408950 }, { "epoch": 2.4309431674304975, "grad_norm": 1.4046251773834229, "learning_rate": 3.9018706239251655e-05, "loss": 0.5070712089538574, "step": 408960 }, { "epoch": 2.431002609507166, "grad_norm": 1.085138201713562, "learning_rate": 3.901487940479156e-05, "loss": 0.4444253921508789, "step": 408970 }, { "epoch": 2.431062051583834, "grad_norm": 1.2407410144805908, "learning_rate": 3.901105290990113e-05, "loss": 0.4827853202819824, "step": 408980 }, { "epoch": 2.4311214936605023, "grad_norm": 1.2779029607772827, "learning_rate": 3.9007226754598606e-05, "loss": 0.4594737529754639, "step": 408990 }, { "epoch": 2.4311809357371708, "grad_norm": 0.97962886095047, "learning_rate": 3.9003400938902276e-05, "loss": 0.43563251495361327, "step": 409000 }, { "epoch": 2.431240377813839, "grad_norm": 1.5046532154083252, "learning_rate": 3.8999575462830495e-05, "loss": 0.5049421787261963, "step": 409010 }, { "epoch": 2.4312998198905076, "grad_norm": 1.06650710105896, "learning_rate": 3.899575032640155e-05, "loss": 0.49306302070617675, "step": 409020 }, { "epoch": 2.431359261967176, "grad_norm": 1.3600608110427856, "learning_rate": 3.8991925529633734e-05, "loss": 0.49989805221557615, "step": 409030 }, { "epoch": 2.4314187040438444, "grad_norm": 1.587424397468567, "learning_rate": 3.898810107254533e-05, "loss": 0.5140777587890625, "step": 409040 }, { "epoch": 2.431478146120513, "grad_norm": 1.3703269958496094, "learning_rate": 3.898427695515465e-05, "loss": 0.5126954078674316, "step": 409050 }, { "epoch": 2.4315375881971812, "grad_norm": 1.2035882472991943, "learning_rate": 3.898045317747998e-05, "loss": 0.5030786514282226, "step": 409060 }, { "epoch": 2.4315970302738497, "grad_norm": 0.9821857213973999, "learning_rate": 3.8976629739539596e-05, "loss": 0.4920493125915527, "step": 409070 }, { "epoch": 2.431656472350518, "grad_norm": 1.1130552291870117, "learning_rate": 3.8972806641351816e-05, "loss": 0.5112208843231201, "step": 409080 }, { "epoch": 2.4317159144271865, "grad_norm": 1.351333737373352, "learning_rate": 3.896898388293492e-05, "loss": 0.4845593929290771, "step": 409090 }, { "epoch": 2.431775356503855, "grad_norm": 1.1559830904006958, "learning_rate": 3.89651614643072e-05, "loss": 0.4535031318664551, "step": 409100 }, { "epoch": 2.4318347985805233, "grad_norm": 1.3567191362380981, "learning_rate": 3.8961339385486926e-05, "loss": 0.5034124374389648, "step": 409110 }, { "epoch": 2.4318942406571917, "grad_norm": 1.502915859222412, "learning_rate": 3.895751764649238e-05, "loss": 0.49089851379394533, "step": 409120 }, { "epoch": 2.43195368273386, "grad_norm": 1.488358974456787, "learning_rate": 3.895369624734185e-05, "loss": 0.49654207229614256, "step": 409130 }, { "epoch": 2.4320131248105286, "grad_norm": 1.7292041778564453, "learning_rate": 3.894987518805363e-05, "loss": 0.47722711563110354, "step": 409140 }, { "epoch": 2.4320725668871965, "grad_norm": 1.0772581100463867, "learning_rate": 3.8946054468645986e-05, "loss": 0.41357979774475095, "step": 409150 }, { "epoch": 2.4321320089638654, "grad_norm": 1.6485493183135986, "learning_rate": 3.8942234089137195e-05, "loss": 0.506291675567627, "step": 409160 }, { "epoch": 2.4321914510405334, "grad_norm": 0.8903767466545105, "learning_rate": 3.8938414049545544e-05, "loss": 0.44893994331359866, "step": 409170 }, { "epoch": 2.4322508931172018, "grad_norm": 1.2818562984466553, "learning_rate": 3.8934594349889295e-05, "loss": 0.4841574192047119, "step": 409180 }, { "epoch": 2.43231033519387, "grad_norm": 1.3135523796081543, "learning_rate": 3.8930774990186725e-05, "loss": 0.5412817001342773, "step": 409190 }, { "epoch": 2.4323697772705386, "grad_norm": 1.176409125328064, "learning_rate": 3.892695597045607e-05, "loss": 0.43685297966003417, "step": 409200 }, { "epoch": 2.432429219347207, "grad_norm": 1.3743231296539307, "learning_rate": 3.892313729071566e-05, "loss": 0.46590266227722166, "step": 409210 }, { "epoch": 2.4324886614238754, "grad_norm": 1.3635709285736084, "learning_rate": 3.891931895098373e-05, "loss": 0.5502549171447754, "step": 409220 }, { "epoch": 2.432548103500544, "grad_norm": 1.068851113319397, "learning_rate": 3.891550095127855e-05, "loss": 0.4634376525878906, "step": 409230 }, { "epoch": 2.4326075455772123, "grad_norm": 1.2155227661132812, "learning_rate": 3.8911683291618376e-05, "loss": 0.46712145805358884, "step": 409240 }, { "epoch": 2.4326669876538807, "grad_norm": 0.946640133857727, "learning_rate": 3.890786597202147e-05, "loss": 0.4010912418365479, "step": 409250 }, { "epoch": 2.432726429730549, "grad_norm": 1.520450472831726, "learning_rate": 3.8904048992506096e-05, "loss": 0.5132922649383544, "step": 409260 }, { "epoch": 2.4327858718072175, "grad_norm": 1.1487849950790405, "learning_rate": 3.890023235309054e-05, "loss": 0.48535852432250975, "step": 409270 }, { "epoch": 2.432845313883886, "grad_norm": 1.2775886058807373, "learning_rate": 3.889641605379303e-05, "loss": 0.43420071601867677, "step": 409280 }, { "epoch": 2.4329047559605543, "grad_norm": 1.252456545829773, "learning_rate": 3.889260009463182e-05, "loss": 0.5147924423217773, "step": 409290 }, { "epoch": 2.4329641980372227, "grad_norm": 1.3779717683792114, "learning_rate": 3.88887844756252e-05, "loss": 0.4881115913391113, "step": 409300 }, { "epoch": 2.433023640113891, "grad_norm": 1.3139973878860474, "learning_rate": 3.888496919679137e-05, "loss": 0.5355410575866699, "step": 409310 }, { "epoch": 2.4330830821905596, "grad_norm": 1.1163922548294067, "learning_rate": 3.888115425814861e-05, "loss": 0.5042407512664795, "step": 409320 }, { "epoch": 2.433142524267228, "grad_norm": 1.7233357429504395, "learning_rate": 3.887733965971515e-05, "loss": 0.5143217086791992, "step": 409330 }, { "epoch": 2.433201966343896, "grad_norm": 1.3846505880355835, "learning_rate": 3.887352540150927e-05, "loss": 0.502690601348877, "step": 409340 }, { "epoch": 2.433261408420565, "grad_norm": 1.727036714553833, "learning_rate": 3.886971148354921e-05, "loss": 0.48911705017089846, "step": 409350 }, { "epoch": 2.433320850497233, "grad_norm": 1.5192009210586548, "learning_rate": 3.88658979058532e-05, "loss": 0.4685770034790039, "step": 409360 }, { "epoch": 2.433380292573901, "grad_norm": 1.3217922449111938, "learning_rate": 3.886208466843949e-05, "loss": 0.4791067600250244, "step": 409370 }, { "epoch": 2.4334397346505696, "grad_norm": 1.0692601203918457, "learning_rate": 3.8858271771326316e-05, "loss": 0.43944101333618163, "step": 409380 }, { "epoch": 2.433499176727238, "grad_norm": 1.3203212022781372, "learning_rate": 3.885445921453192e-05, "loss": 0.43033757209777834, "step": 409390 }, { "epoch": 2.4335586188039064, "grad_norm": 1.394531488418579, "learning_rate": 3.885064699807452e-05, "loss": 0.5026233673095704, "step": 409400 }, { "epoch": 2.433618060880575, "grad_norm": 1.295097827911377, "learning_rate": 3.884683512197241e-05, "loss": 0.49990501403808596, "step": 409410 }, { "epoch": 2.4336775029572433, "grad_norm": 1.2758352756500244, "learning_rate": 3.884302358624378e-05, "loss": 0.4913076400756836, "step": 409420 }, { "epoch": 2.4337369450339117, "grad_norm": 1.2310676574707031, "learning_rate": 3.883921239090683e-05, "loss": 0.46448287963867185, "step": 409430 }, { "epoch": 2.43379638711058, "grad_norm": 1.2368888854980469, "learning_rate": 3.883540153597987e-05, "loss": 0.45941991806030275, "step": 409440 }, { "epoch": 2.4338558291872485, "grad_norm": 1.2611926794052124, "learning_rate": 3.8831591021481086e-05, "loss": 0.4938515663146973, "step": 409450 }, { "epoch": 2.433915271263917, "grad_norm": 1.0113544464111328, "learning_rate": 3.882778084742869e-05, "loss": 0.45667099952697754, "step": 409460 }, { "epoch": 2.4339747133405853, "grad_norm": 1.2914912700653076, "learning_rate": 3.882397101384098e-05, "loss": 0.45591249465942385, "step": 409470 }, { "epoch": 2.4340341554172538, "grad_norm": 1.0565327405929565, "learning_rate": 3.88201615207361e-05, "loss": 0.4739692211151123, "step": 409480 }, { "epoch": 2.434093597493922, "grad_norm": 1.165137767791748, "learning_rate": 3.8816352368132295e-05, "loss": 0.4535063743591309, "step": 409490 }, { "epoch": 2.4341530395705906, "grad_norm": 1.505815863609314, "learning_rate": 3.881254355604781e-05, "loss": 0.47317800521850584, "step": 409500 }, { "epoch": 2.434212481647259, "grad_norm": 1.5384200811386108, "learning_rate": 3.8808735084500856e-05, "loss": 0.4603584766387939, "step": 409510 }, { "epoch": 2.4342719237239274, "grad_norm": 1.42914617061615, "learning_rate": 3.8804926953509654e-05, "loss": 0.4986860752105713, "step": 409520 }, { "epoch": 2.4343313658005954, "grad_norm": 1.2742067575454712, "learning_rate": 3.88011191630924e-05, "loss": 0.41994223594665525, "step": 409530 }, { "epoch": 2.434390807877264, "grad_norm": 1.2026103734970093, "learning_rate": 3.8797311713267335e-05, "loss": 0.4707025051116943, "step": 409540 }, { "epoch": 2.434450249953932, "grad_norm": 1.0086640119552612, "learning_rate": 3.879350460405266e-05, "loss": 0.4566792964935303, "step": 409550 }, { "epoch": 2.4345096920306006, "grad_norm": 1.1734637022018433, "learning_rate": 3.878969783546657e-05, "loss": 0.5281872272491455, "step": 409560 }, { "epoch": 2.434569134107269, "grad_norm": 1.158632755279541, "learning_rate": 3.878589140752731e-05, "loss": 0.47582192420959474, "step": 409570 }, { "epoch": 2.4346285761839375, "grad_norm": 1.1913048028945923, "learning_rate": 3.878208532025307e-05, "loss": 0.48000245094299315, "step": 409580 }, { "epoch": 2.434688018260606, "grad_norm": 1.1943248510360718, "learning_rate": 3.877827957366206e-05, "loss": 0.4886932373046875, "step": 409590 }, { "epoch": 2.4347474603372743, "grad_norm": 1.1652601957321167, "learning_rate": 3.877447416777249e-05, "loss": 0.46408634185791015, "step": 409600 }, { "epoch": 2.4348069024139427, "grad_norm": 1.2445313930511475, "learning_rate": 3.8770669102602564e-05, "loss": 0.5431288719177246, "step": 409610 }, { "epoch": 2.434866344490611, "grad_norm": 1.4552427530288696, "learning_rate": 3.876686437817044e-05, "loss": 0.4901733875274658, "step": 409620 }, { "epoch": 2.4349257865672795, "grad_norm": 1.232810616493225, "learning_rate": 3.876305999449439e-05, "loss": 0.46914987564086913, "step": 409630 }, { "epoch": 2.434985228643948, "grad_norm": 1.02027428150177, "learning_rate": 3.875925595159259e-05, "loss": 0.4448415279388428, "step": 409640 }, { "epoch": 2.4350446707206164, "grad_norm": 1.2196892499923706, "learning_rate": 3.8755452249483215e-05, "loss": 0.48929781913757325, "step": 409650 }, { "epoch": 2.435104112797285, "grad_norm": 1.1206570863723755, "learning_rate": 3.8751648888184466e-05, "loss": 0.4827530860900879, "step": 409660 }, { "epoch": 2.435163554873953, "grad_norm": 1.0876374244689941, "learning_rate": 3.874784586771456e-05, "loss": 0.4496123790740967, "step": 409670 }, { "epoch": 2.4352229969506216, "grad_norm": 1.1957365274429321, "learning_rate": 3.8744043188091673e-05, "loss": 0.4948904991149902, "step": 409680 }, { "epoch": 2.43528243902729, "grad_norm": 1.093130350112915, "learning_rate": 3.8740240849333965e-05, "loss": 0.4989307880401611, "step": 409690 }, { "epoch": 2.4353418811039584, "grad_norm": 1.1393437385559082, "learning_rate": 3.873643885145969e-05, "loss": 0.49005541801452634, "step": 409700 }, { "epoch": 2.435401323180627, "grad_norm": 1.2701810598373413, "learning_rate": 3.8732637194486995e-05, "loss": 0.5115875720977783, "step": 409710 }, { "epoch": 2.435460765257295, "grad_norm": 1.5907963514328003, "learning_rate": 3.8728835878434075e-05, "loss": 0.4744675636291504, "step": 409720 }, { "epoch": 2.4355202073339632, "grad_norm": 1.0503063201904297, "learning_rate": 3.8725034903319106e-05, "loss": 0.48029603958129885, "step": 409730 }, { "epoch": 2.4355796494106317, "grad_norm": 1.2404170036315918, "learning_rate": 3.872123426916029e-05, "loss": 0.4805863857269287, "step": 409740 }, { "epoch": 2.4356390914873, "grad_norm": 1.2602347135543823, "learning_rate": 3.8717433975975783e-05, "loss": 0.44306278228759766, "step": 409750 }, { "epoch": 2.4356985335639685, "grad_norm": 1.2514240741729736, "learning_rate": 3.8713634023783765e-05, "loss": 0.515510892868042, "step": 409760 }, { "epoch": 2.435757975640637, "grad_norm": 1.0060075521469116, "learning_rate": 3.870983441260244e-05, "loss": 0.43415155410766604, "step": 409770 }, { "epoch": 2.4358174177173053, "grad_norm": 1.4091086387634277, "learning_rate": 3.870603514244997e-05, "loss": 0.4817265510559082, "step": 409780 }, { "epoch": 2.4358768597939737, "grad_norm": 1.6571675539016724, "learning_rate": 3.8702236213344535e-05, "loss": 0.4393932342529297, "step": 409790 }, { "epoch": 2.435936301870642, "grad_norm": 1.6467114686965942, "learning_rate": 3.869843762530429e-05, "loss": 0.4882619380950928, "step": 409800 }, { "epoch": 2.4359957439473106, "grad_norm": 1.3743844032287598, "learning_rate": 3.869463937834743e-05, "loss": 0.4654412269592285, "step": 409810 }, { "epoch": 2.436055186023979, "grad_norm": 1.1662557125091553, "learning_rate": 3.869084147249208e-05, "loss": 0.4736656188964844, "step": 409820 }, { "epoch": 2.4361146281006474, "grad_norm": 1.0528323650360107, "learning_rate": 3.868704390775646e-05, "loss": 0.49849529266357423, "step": 409830 }, { "epoch": 2.436174070177316, "grad_norm": 1.319084644317627, "learning_rate": 3.868324668415874e-05, "loss": 0.4666279792785645, "step": 409840 }, { "epoch": 2.436233512253984, "grad_norm": 1.3576939105987549, "learning_rate": 3.867944980171704e-05, "loss": 0.5311876773834229, "step": 409850 }, { "epoch": 2.4362929543306526, "grad_norm": 1.3813226222991943, "learning_rate": 3.867565326044955e-05, "loss": 0.48056535720825194, "step": 409860 }, { "epoch": 2.436352396407321, "grad_norm": 1.431024193763733, "learning_rate": 3.8671857060374415e-05, "loss": 0.442763614654541, "step": 409870 }, { "epoch": 2.4364118384839895, "grad_norm": 1.338766098022461, "learning_rate": 3.866806120150983e-05, "loss": 0.4966286182403564, "step": 409880 }, { "epoch": 2.4364712805606574, "grad_norm": 1.3715420961380005, "learning_rate": 3.866426568387388e-05, "loss": 0.5247287750244141, "step": 409890 }, { "epoch": 2.4365307226373263, "grad_norm": 1.2873573303222656, "learning_rate": 3.866047050748481e-05, "loss": 0.5315649032592773, "step": 409900 }, { "epoch": 2.4365901647139943, "grad_norm": 1.1224302053451538, "learning_rate": 3.865667567236075e-05, "loss": 0.5089574813842773, "step": 409910 }, { "epoch": 2.4366496067906627, "grad_norm": 1.2387001514434814, "learning_rate": 3.8652881178519795e-05, "loss": 0.4712655067443848, "step": 409920 }, { "epoch": 2.436709048867331, "grad_norm": 1.2890913486480713, "learning_rate": 3.864908702598017e-05, "loss": 0.4918648719787598, "step": 409930 }, { "epoch": 2.4367684909439995, "grad_norm": 1.281599521636963, "learning_rate": 3.8645293214759995e-05, "loss": 0.43045930862426757, "step": 409940 }, { "epoch": 2.436827933020668, "grad_norm": 1.260635256767273, "learning_rate": 3.864149974487738e-05, "loss": 0.4375021934509277, "step": 409950 }, { "epoch": 2.4368873750973363, "grad_norm": 1.3063617944717407, "learning_rate": 3.863770661635054e-05, "loss": 0.47928452491760254, "step": 409960 }, { "epoch": 2.4369468171740047, "grad_norm": 1.3324826955795288, "learning_rate": 3.863391382919761e-05, "loss": 0.5246358871459961, "step": 409970 }, { "epoch": 2.437006259250673, "grad_norm": 1.203017234802246, "learning_rate": 3.863012138343667e-05, "loss": 0.4454542636871338, "step": 409980 }, { "epoch": 2.4370657013273416, "grad_norm": 1.3949521780014038, "learning_rate": 3.862632927908594e-05, "loss": 0.4491427421569824, "step": 409990 }, { "epoch": 2.43712514340401, "grad_norm": 1.3721027374267578, "learning_rate": 3.8622537516163514e-05, "loss": 0.48068809509277344, "step": 410000 }, { "epoch": 2.4371845854806784, "grad_norm": 1.4670640230178833, "learning_rate": 3.861874609468754e-05, "loss": 0.516166877746582, "step": 410010 }, { "epoch": 2.437244027557347, "grad_norm": 1.1904820203781128, "learning_rate": 3.8614955014676166e-05, "loss": 0.46686630249023436, "step": 410020 }, { "epoch": 2.4373034696340152, "grad_norm": 1.088866114616394, "learning_rate": 3.861116427614751e-05, "loss": 0.44301409721374513, "step": 410030 }, { "epoch": 2.4373629117106836, "grad_norm": 1.7492470741271973, "learning_rate": 3.8607373879119726e-05, "loss": 0.5528915405273438, "step": 410040 }, { "epoch": 2.437422353787352, "grad_norm": 1.1825554370880127, "learning_rate": 3.86035838236109e-05, "loss": 0.4436167240142822, "step": 410050 }, { "epoch": 2.4374817958640205, "grad_norm": 1.4219743013381958, "learning_rate": 3.859979410963921e-05, "loss": 0.4419704914093018, "step": 410060 }, { "epoch": 2.437541237940689, "grad_norm": 1.2927467823028564, "learning_rate": 3.859600473722279e-05, "loss": 0.4340197563171387, "step": 410070 }, { "epoch": 2.437600680017357, "grad_norm": 1.10919988155365, "learning_rate": 3.859221570637974e-05, "loss": 0.5017284393310547, "step": 410080 }, { "epoch": 2.4376601220940257, "grad_norm": 1.4164098501205444, "learning_rate": 3.858842701712819e-05, "loss": 0.4157381057739258, "step": 410090 }, { "epoch": 2.4377195641706937, "grad_norm": 1.3602492809295654, "learning_rate": 3.858463866948627e-05, "loss": 0.4983724594116211, "step": 410100 }, { "epoch": 2.437779006247362, "grad_norm": 1.5325689315795898, "learning_rate": 3.858085066347208e-05, "loss": 0.5334543228149414, "step": 410110 }, { "epoch": 2.4378384483240305, "grad_norm": 1.661468505859375, "learning_rate": 3.8577062999103784e-05, "loss": 0.5412954807281494, "step": 410120 }, { "epoch": 2.437897890400699, "grad_norm": 1.3486191034317017, "learning_rate": 3.8573275676399485e-05, "loss": 0.48860511779785154, "step": 410130 }, { "epoch": 2.4379573324773673, "grad_norm": 1.8090325593948364, "learning_rate": 3.856948869537727e-05, "loss": 0.499410343170166, "step": 410140 }, { "epoch": 2.4380167745540358, "grad_norm": 1.2314954996109009, "learning_rate": 3.856570205605531e-05, "loss": 0.45123000144958497, "step": 410150 }, { "epoch": 2.438076216630704, "grad_norm": 1.4769902229309082, "learning_rate": 3.856191575845166e-05, "loss": 0.5057861328125, "step": 410160 }, { "epoch": 2.4381356587073726, "grad_norm": 1.2516191005706787, "learning_rate": 3.855812980258447e-05, "loss": 0.4631982326507568, "step": 410170 }, { "epoch": 2.438195100784041, "grad_norm": 1.366145372390747, "learning_rate": 3.85543441884718e-05, "loss": 0.4673024654388428, "step": 410180 }, { "epoch": 2.4382545428607094, "grad_norm": 1.087649941444397, "learning_rate": 3.8550558916131844e-05, "loss": 0.4652748107910156, "step": 410190 }, { "epoch": 2.438313984937378, "grad_norm": 1.0825992822647095, "learning_rate": 3.854677398558265e-05, "loss": 0.4594019889831543, "step": 410200 }, { "epoch": 2.4383734270140462, "grad_norm": 1.099207878112793, "learning_rate": 3.8542989396842346e-05, "loss": 0.45482568740844725, "step": 410210 }, { "epoch": 2.4384328690907147, "grad_norm": 1.7822397947311401, "learning_rate": 3.8539205149929025e-05, "loss": 0.5187240600585937, "step": 410220 }, { "epoch": 2.438492311167383, "grad_norm": 1.4142286777496338, "learning_rate": 3.8535421244860794e-05, "loss": 0.5040376663208008, "step": 410230 }, { "epoch": 2.4385517532440515, "grad_norm": 1.441356897354126, "learning_rate": 3.853163768165575e-05, "loss": 0.5119683265686035, "step": 410240 }, { "epoch": 2.43861119532072, "grad_norm": 1.4374008178710938, "learning_rate": 3.8527854460331976e-05, "loss": 0.48804850578308107, "step": 410250 }, { "epoch": 2.4386706373973883, "grad_norm": 1.5048332214355469, "learning_rate": 3.85240715809076e-05, "loss": 0.48486127853393557, "step": 410260 }, { "epoch": 2.4387300794740563, "grad_norm": 1.138656497001648, "learning_rate": 3.852028904340072e-05, "loss": 0.4424448490142822, "step": 410270 }, { "epoch": 2.4387895215507247, "grad_norm": 1.5043402910232544, "learning_rate": 3.851650684782942e-05, "loss": 0.4774762153625488, "step": 410280 }, { "epoch": 2.438848963627393, "grad_norm": 1.2960150241851807, "learning_rate": 3.851272499421178e-05, "loss": 0.519141149520874, "step": 410290 }, { "epoch": 2.4389084057040615, "grad_norm": 1.0137741565704346, "learning_rate": 3.850894348256591e-05, "loss": 0.5039134979248047, "step": 410300 }, { "epoch": 2.43896784778073, "grad_norm": 1.112730622291565, "learning_rate": 3.850516231290986e-05, "loss": 0.537540054321289, "step": 410310 }, { "epoch": 2.4390272898573984, "grad_norm": 1.2070471048355103, "learning_rate": 3.850138148526178e-05, "loss": 0.46595149040222167, "step": 410320 }, { "epoch": 2.4390867319340668, "grad_norm": 1.145981788635254, "learning_rate": 3.849760099963972e-05, "loss": 0.497296142578125, "step": 410330 }, { "epoch": 2.439146174010735, "grad_norm": 1.3130464553833008, "learning_rate": 3.849382085606177e-05, "loss": 0.47239341735839846, "step": 410340 }, { "epoch": 2.4392056160874036, "grad_norm": 1.4384310245513916, "learning_rate": 3.8490041054546006e-05, "loss": 0.4798428058624268, "step": 410350 }, { "epoch": 2.439265058164072, "grad_norm": 1.8429806232452393, "learning_rate": 3.848626159511053e-05, "loss": 0.48417253494262696, "step": 410360 }, { "epoch": 2.4393245002407404, "grad_norm": 1.1827239990234375, "learning_rate": 3.848248247777339e-05, "loss": 0.47960314750671384, "step": 410370 }, { "epoch": 2.439383942317409, "grad_norm": 1.3737214803695679, "learning_rate": 3.847870370255268e-05, "loss": 0.4454507350921631, "step": 410380 }, { "epoch": 2.4394433843940773, "grad_norm": 1.5635849237442017, "learning_rate": 3.8474925269466485e-05, "loss": 0.49887962341308595, "step": 410390 }, { "epoch": 2.4395028264707457, "grad_norm": 0.8958925008773804, "learning_rate": 3.8471147178532895e-05, "loss": 0.49379668235778806, "step": 410400 }, { "epoch": 2.439562268547414, "grad_norm": 1.2120475769042969, "learning_rate": 3.846736942976993e-05, "loss": 0.46596474647521974, "step": 410410 }, { "epoch": 2.4396217106240825, "grad_norm": 1.1710267066955566, "learning_rate": 3.8463592023195706e-05, "loss": 0.463704776763916, "step": 410420 }, { "epoch": 2.439681152700751, "grad_norm": 1.2322614192962646, "learning_rate": 3.8459814958828264e-05, "loss": 0.49188480377197263, "step": 410430 }, { "epoch": 2.4397405947774193, "grad_norm": 1.6560399532318115, "learning_rate": 3.845603823668569e-05, "loss": 0.4808391571044922, "step": 410440 }, { "epoch": 2.4398000368540878, "grad_norm": 1.009093165397644, "learning_rate": 3.8452261856786055e-05, "loss": 0.47307605743408204, "step": 410450 }, { "epoch": 2.4398594789307557, "grad_norm": 1.4777579307556152, "learning_rate": 3.844848581914746e-05, "loss": 0.4811504364013672, "step": 410460 }, { "epoch": 2.439918921007424, "grad_norm": 1.3961049318313599, "learning_rate": 3.844471012378785e-05, "loss": 0.45502076148986814, "step": 410470 }, { "epoch": 2.4399783630840925, "grad_norm": 1.266446828842163, "learning_rate": 3.844093477072541e-05, "loss": 0.45168514251708985, "step": 410480 }, { "epoch": 2.440037805160761, "grad_norm": 1.6242789030075073, "learning_rate": 3.843715975997814e-05, "loss": 0.49905853271484374, "step": 410490 }, { "epoch": 2.4400972472374294, "grad_norm": 1.6075702905654907, "learning_rate": 3.843338509156411e-05, "loss": 0.5191179275512695, "step": 410500 }, { "epoch": 2.440156689314098, "grad_norm": 1.5660440921783447, "learning_rate": 3.842961076550137e-05, "loss": 0.5147673606872558, "step": 410510 }, { "epoch": 2.440216131390766, "grad_norm": 1.1519838571548462, "learning_rate": 3.8425836781808014e-05, "loss": 0.4499034881591797, "step": 410520 }, { "epoch": 2.4402755734674346, "grad_norm": 1.386283040046692, "learning_rate": 3.842206314050204e-05, "loss": 0.46430292129516604, "step": 410530 }, { "epoch": 2.440335015544103, "grad_norm": 1.1752070188522339, "learning_rate": 3.841828984160151e-05, "loss": 0.5003110885620117, "step": 410540 }, { "epoch": 2.4403944576207715, "grad_norm": 1.040464997291565, "learning_rate": 3.841451688512451e-05, "loss": 0.4749699592590332, "step": 410550 }, { "epoch": 2.44045389969744, "grad_norm": 1.0373203754425049, "learning_rate": 3.841074427108906e-05, "loss": 0.4996819496154785, "step": 410560 }, { "epoch": 2.4405133417741083, "grad_norm": 1.0638463497161865, "learning_rate": 3.840697199951318e-05, "loss": 0.46700410842895507, "step": 410570 }, { "epoch": 2.4405727838507767, "grad_norm": 1.140342116355896, "learning_rate": 3.8403200070415026e-05, "loss": 0.4778390884399414, "step": 410580 }, { "epoch": 2.440632225927445, "grad_norm": 1.4734476804733276, "learning_rate": 3.839942848381253e-05, "loss": 0.4367704391479492, "step": 410590 }, { "epoch": 2.4406916680041135, "grad_norm": 1.4886291027069092, "learning_rate": 3.839565723972375e-05, "loss": 0.5052735805511475, "step": 410600 }, { "epoch": 2.440751110080782, "grad_norm": 1.4152450561523438, "learning_rate": 3.8391886338166746e-05, "loss": 0.5116158485412597, "step": 410610 }, { "epoch": 2.4408105521574504, "grad_norm": 1.5046306848526, "learning_rate": 3.838811577915956e-05, "loss": 0.46879849433898924, "step": 410620 }, { "epoch": 2.4408699942341183, "grad_norm": 1.632396936416626, "learning_rate": 3.8384345562720234e-05, "loss": 0.49637880325317385, "step": 410630 }, { "epoch": 2.440929436310787, "grad_norm": 1.3131396770477295, "learning_rate": 3.83805756888668e-05, "loss": 0.47953362464904786, "step": 410640 }, { "epoch": 2.440988878387455, "grad_norm": 1.5580267906188965, "learning_rate": 3.8376806157617285e-05, "loss": 0.42033867835998534, "step": 410650 }, { "epoch": 2.4410483204641236, "grad_norm": 1.151045799255371, "learning_rate": 3.837303696898972e-05, "loss": 0.489958381652832, "step": 410660 }, { "epoch": 2.441107762540792, "grad_norm": 1.3948301076889038, "learning_rate": 3.836926812300211e-05, "loss": 0.4976933479309082, "step": 410670 }, { "epoch": 2.4411672046174604, "grad_norm": 1.2333110570907593, "learning_rate": 3.836549961967254e-05, "loss": 0.4900071620941162, "step": 410680 }, { "epoch": 2.441226646694129, "grad_norm": 1.6186891794204712, "learning_rate": 3.836173145901901e-05, "loss": 0.48368988037109373, "step": 410690 }, { "epoch": 2.4412860887707972, "grad_norm": 1.950560212135315, "learning_rate": 3.835796364105954e-05, "loss": 0.49938006401062013, "step": 410700 }, { "epoch": 2.4413455308474656, "grad_norm": 1.0780389308929443, "learning_rate": 3.835419616581216e-05, "loss": 0.4817910671234131, "step": 410710 }, { "epoch": 2.441404972924134, "grad_norm": 1.5323256254196167, "learning_rate": 3.83504290332949e-05, "loss": 0.5062180995941162, "step": 410720 }, { "epoch": 2.4414644150008025, "grad_norm": 1.6289093494415283, "learning_rate": 3.8346662243525766e-05, "loss": 0.5373710632324219, "step": 410730 }, { "epoch": 2.441523857077471, "grad_norm": 1.4833550453186035, "learning_rate": 3.834289579652276e-05, "loss": 0.4817922115325928, "step": 410740 }, { "epoch": 2.4415832991541393, "grad_norm": 1.4274332523345947, "learning_rate": 3.833912969230395e-05, "loss": 0.4893346786499023, "step": 410750 }, { "epoch": 2.4416427412308077, "grad_norm": 1.085692286491394, "learning_rate": 3.833536393088732e-05, "loss": 0.4929615020751953, "step": 410760 }, { "epoch": 2.441702183307476, "grad_norm": 1.4821125268936157, "learning_rate": 3.833159851229089e-05, "loss": 0.45962066650390626, "step": 410770 }, { "epoch": 2.4417616253841445, "grad_norm": 1.3706103563308716, "learning_rate": 3.8327833436532666e-05, "loss": 0.4932234764099121, "step": 410780 }, { "epoch": 2.441821067460813, "grad_norm": 1.480094075202942, "learning_rate": 3.832406870363067e-05, "loss": 0.5057641506195069, "step": 410790 }, { "epoch": 2.4418805095374814, "grad_norm": 1.6585358381271362, "learning_rate": 3.832030431360289e-05, "loss": 0.5283655166625977, "step": 410800 }, { "epoch": 2.44193995161415, "grad_norm": 1.5561786890029907, "learning_rate": 3.831654026646736e-05, "loss": 0.4977989196777344, "step": 410810 }, { "epoch": 2.4419993936908178, "grad_norm": 1.578796148300171, "learning_rate": 3.831277656224208e-05, "loss": 0.5167739868164063, "step": 410820 }, { "epoch": 2.4420588357674866, "grad_norm": 1.550084114074707, "learning_rate": 3.8309013200945046e-05, "loss": 0.5000311851501464, "step": 410830 }, { "epoch": 2.4421182778441546, "grad_norm": 1.3046932220458984, "learning_rate": 3.830525018259426e-05, "loss": 0.45873308181762695, "step": 410840 }, { "epoch": 2.442177719920823, "grad_norm": 1.4967167377471924, "learning_rate": 3.830148750720774e-05, "loss": 0.4741353034973145, "step": 410850 }, { "epoch": 2.4422371619974914, "grad_norm": 1.4775243997573853, "learning_rate": 3.8297725174803456e-05, "loss": 0.4811966896057129, "step": 410860 }, { "epoch": 2.44229660407416, "grad_norm": 1.0268803834915161, "learning_rate": 3.829396318539941e-05, "loss": 0.4286396026611328, "step": 410870 }, { "epoch": 2.4423560461508282, "grad_norm": 1.6437753438949585, "learning_rate": 3.829020153901363e-05, "loss": 0.4912604808807373, "step": 410880 }, { "epoch": 2.4424154882274967, "grad_norm": 1.0996730327606201, "learning_rate": 3.828644023566412e-05, "loss": 0.487382698059082, "step": 410890 }, { "epoch": 2.442474930304165, "grad_norm": 1.6411927938461304, "learning_rate": 3.828267927536879e-05, "loss": 0.45761713981628416, "step": 410900 }, { "epoch": 2.4425343723808335, "grad_norm": 1.0087544918060303, "learning_rate": 3.8278918658145704e-05, "loss": 0.46616926193237307, "step": 410910 }, { "epoch": 2.442593814457502, "grad_norm": 1.260380506515503, "learning_rate": 3.827515838401284e-05, "loss": 0.5460096836090088, "step": 410920 }, { "epoch": 2.4426532565341703, "grad_norm": 1.3876852989196777, "learning_rate": 3.827139845298816e-05, "loss": 0.485047721862793, "step": 410930 }, { "epoch": 2.4427126986108387, "grad_norm": 1.2841603755950928, "learning_rate": 3.826763886508968e-05, "loss": 0.45624237060546874, "step": 410940 }, { "epoch": 2.442772140687507, "grad_norm": 1.069791555404663, "learning_rate": 3.826387962033541e-05, "loss": 0.4849945068359375, "step": 410950 }, { "epoch": 2.4428315827641756, "grad_norm": 1.3332319259643555, "learning_rate": 3.826012071874324e-05, "loss": 0.5375545978546142, "step": 410960 }, { "epoch": 2.442891024840844, "grad_norm": 1.1451385021209717, "learning_rate": 3.825636216033123e-05, "loss": 0.4846898078918457, "step": 410970 }, { "epoch": 2.4429504669175124, "grad_norm": 1.3110779523849487, "learning_rate": 3.825260394511735e-05, "loss": 0.42380266189575194, "step": 410980 }, { "epoch": 2.443009908994181, "grad_norm": 1.028267502784729, "learning_rate": 3.824884607311955e-05, "loss": 0.4869977951049805, "step": 410990 }, { "epoch": 2.443069351070849, "grad_norm": 1.4782638549804688, "learning_rate": 3.82450885443558e-05, "loss": 0.46329822540283205, "step": 411000 }, { "epoch": 2.443128793147517, "grad_norm": 1.2540082931518555, "learning_rate": 3.8241331358844154e-05, "loss": 0.4870725154876709, "step": 411010 }, { "epoch": 2.4431882352241856, "grad_norm": 1.114284873008728, "learning_rate": 3.823757451660249e-05, "loss": 0.5177906036376954, "step": 411020 }, { "epoch": 2.443247677300854, "grad_norm": 1.2025401592254639, "learning_rate": 3.82338180176488e-05, "loss": 0.45343494415283203, "step": 411030 }, { "epoch": 2.4433071193775224, "grad_norm": 1.3413044214248657, "learning_rate": 3.823006186200111e-05, "loss": 0.47927398681640626, "step": 411040 }, { "epoch": 2.443366561454191, "grad_norm": 1.7298206090927124, "learning_rate": 3.822630604967733e-05, "loss": 0.5250245094299316, "step": 411050 }, { "epoch": 2.4434260035308593, "grad_norm": 1.3047760725021362, "learning_rate": 3.822255058069543e-05, "loss": 0.48711957931518557, "step": 411060 }, { "epoch": 2.4434854456075277, "grad_norm": 1.5119508504867554, "learning_rate": 3.821879545507344e-05, "loss": 0.4868666648864746, "step": 411070 }, { "epoch": 2.443544887684196, "grad_norm": 1.4716475009918213, "learning_rate": 3.8215040672829246e-05, "loss": 0.47417707443237306, "step": 411080 }, { "epoch": 2.4436043297608645, "grad_norm": 1.0837047100067139, "learning_rate": 3.821128623398084e-05, "loss": 0.5006862640380859, "step": 411090 }, { "epoch": 2.443663771837533, "grad_norm": 0.956529974937439, "learning_rate": 3.8207532138546154e-05, "loss": 0.45377488136291505, "step": 411100 }, { "epoch": 2.4437232139142013, "grad_norm": 1.5133264064788818, "learning_rate": 3.8203778386543196e-05, "loss": 0.4576863288879395, "step": 411110 }, { "epoch": 2.4437826559908697, "grad_norm": 1.0436326265335083, "learning_rate": 3.82000249779899e-05, "loss": 0.49630088806152345, "step": 411120 }, { "epoch": 2.443842098067538, "grad_norm": 1.5029871463775635, "learning_rate": 3.8196271912904226e-05, "loss": 0.4587098121643066, "step": 411130 }, { "epoch": 2.4439015401442066, "grad_norm": 0.9933716654777527, "learning_rate": 3.819251919130411e-05, "loss": 0.48181638717651365, "step": 411140 }, { "epoch": 2.443960982220875, "grad_norm": 1.0642725229263306, "learning_rate": 3.818876681320752e-05, "loss": 0.4840824604034424, "step": 411150 }, { "epoch": 2.4440204242975434, "grad_norm": 1.565322995185852, "learning_rate": 3.818501477863238e-05, "loss": 0.48052005767822265, "step": 411160 }, { "epoch": 2.444079866374212, "grad_norm": 1.3868978023529053, "learning_rate": 3.818126308759668e-05, "loss": 0.4940143585205078, "step": 411170 }, { "epoch": 2.4441393084508802, "grad_norm": 1.2206993103027344, "learning_rate": 3.8177511740118357e-05, "loss": 0.45081262588500975, "step": 411180 }, { "epoch": 2.4441987505275486, "grad_norm": 1.2675098180770874, "learning_rate": 3.8173760736215336e-05, "loss": 0.4311640739440918, "step": 411190 }, { "epoch": 2.4442581926042166, "grad_norm": 1.1694494485855103, "learning_rate": 3.817001007590557e-05, "loss": 0.4827157974243164, "step": 411200 }, { "epoch": 2.444317634680885, "grad_norm": 1.3292174339294434, "learning_rate": 3.8166259759207e-05, "loss": 0.4993463039398193, "step": 411210 }, { "epoch": 2.4443770767575534, "grad_norm": 1.1733976602554321, "learning_rate": 3.816250978613758e-05, "loss": 0.5298521518707275, "step": 411220 }, { "epoch": 2.444436518834222, "grad_norm": 1.3735663890838623, "learning_rate": 3.81587601567152e-05, "loss": 0.45282983779907227, "step": 411230 }, { "epoch": 2.4444959609108903, "grad_norm": 1.4044229984283447, "learning_rate": 3.8155010870957864e-05, "loss": 0.5169054985046386, "step": 411240 }, { "epoch": 2.4445554029875587, "grad_norm": 1.2912781238555908, "learning_rate": 3.815126192888348e-05, "loss": 0.4201493263244629, "step": 411250 }, { "epoch": 2.444614845064227, "grad_norm": 1.425933599472046, "learning_rate": 3.814751333050997e-05, "loss": 0.5045326232910157, "step": 411260 }, { "epoch": 2.4446742871408955, "grad_norm": 1.3982592821121216, "learning_rate": 3.814376507585527e-05, "loss": 0.5617556571960449, "step": 411270 }, { "epoch": 2.444733729217564, "grad_norm": 1.2434148788452148, "learning_rate": 3.814001716493732e-05, "loss": 0.45701904296875, "step": 411280 }, { "epoch": 2.4447931712942323, "grad_norm": 1.6508897542953491, "learning_rate": 3.8136269597774025e-05, "loss": 0.518674087524414, "step": 411290 }, { "epoch": 2.4448526133709008, "grad_norm": 1.4579232931137085, "learning_rate": 3.813252237438335e-05, "loss": 0.5322734832763671, "step": 411300 }, { "epoch": 2.444912055447569, "grad_norm": 1.1019270420074463, "learning_rate": 3.812877549478321e-05, "loss": 0.5013139724731446, "step": 411310 }, { "epoch": 2.4449714975242376, "grad_norm": 1.3203388452529907, "learning_rate": 3.8125028958991514e-05, "loss": 0.5673595428466797, "step": 411320 }, { "epoch": 2.445030939600906, "grad_norm": 1.316633701324463, "learning_rate": 3.812128276702619e-05, "loss": 0.4284168243408203, "step": 411330 }, { "epoch": 2.4450903816775744, "grad_norm": 1.5886019468307495, "learning_rate": 3.8117536918905164e-05, "loss": 0.4486320972442627, "step": 411340 }, { "epoch": 2.445149823754243, "grad_norm": 1.2330578565597534, "learning_rate": 3.811379141464634e-05, "loss": 0.5012610912322998, "step": 411350 }, { "epoch": 2.4452092658309112, "grad_norm": 1.0418691635131836, "learning_rate": 3.811004625426763e-05, "loss": 0.4696375846862793, "step": 411360 }, { "epoch": 2.445268707907579, "grad_norm": 1.7410714626312256, "learning_rate": 3.810630143778699e-05, "loss": 0.45108752250671386, "step": 411370 }, { "epoch": 2.445328149984248, "grad_norm": 1.4457849264144897, "learning_rate": 3.810255696522229e-05, "loss": 0.4961820602416992, "step": 411380 }, { "epoch": 2.445387592060916, "grad_norm": 1.219781517982483, "learning_rate": 3.809881283659148e-05, "loss": 0.4508659362792969, "step": 411390 }, { "epoch": 2.4454470341375845, "grad_norm": 1.4788672924041748, "learning_rate": 3.809506905191245e-05, "loss": 0.4937342643737793, "step": 411400 }, { "epoch": 2.445506476214253, "grad_norm": 1.059137225151062, "learning_rate": 3.809132561120311e-05, "loss": 0.42632293701171875, "step": 411410 }, { "epoch": 2.4455659182909213, "grad_norm": 1.4608349800109863, "learning_rate": 3.808758251448134e-05, "loss": 0.48203401565551757, "step": 411420 }, { "epoch": 2.4456253603675897, "grad_norm": 1.3649450540542603, "learning_rate": 3.80838397617651e-05, "loss": 0.4935063362121582, "step": 411430 }, { "epoch": 2.445684802444258, "grad_norm": 1.1128140687942505, "learning_rate": 3.808009735307229e-05, "loss": 0.48137426376342773, "step": 411440 }, { "epoch": 2.4457442445209265, "grad_norm": 0.9600226283073425, "learning_rate": 3.8076355288420774e-05, "loss": 0.47630672454833983, "step": 411450 }, { "epoch": 2.445803686597595, "grad_norm": 1.4425479173660278, "learning_rate": 3.807261356782844e-05, "loss": 0.5022953987121582, "step": 411460 }, { "epoch": 2.4458631286742634, "grad_norm": 1.4085299968719482, "learning_rate": 3.806887219131324e-05, "loss": 0.46413259506225585, "step": 411470 }, { "epoch": 2.445922570750932, "grad_norm": 1.3728185892105103, "learning_rate": 3.806513115889304e-05, "loss": 0.43933835029602053, "step": 411480 }, { "epoch": 2.4459820128276, "grad_norm": 1.0336092710494995, "learning_rate": 3.8061390470585736e-05, "loss": 0.4117135524749756, "step": 411490 }, { "epoch": 2.4460414549042686, "grad_norm": 1.18049955368042, "learning_rate": 3.805765012640927e-05, "loss": 0.5093485355377197, "step": 411500 }, { "epoch": 2.446100896980937, "grad_norm": 1.3619647026062012, "learning_rate": 3.805391012638146e-05, "loss": 0.5257374286651612, "step": 411510 }, { "epoch": 2.4461603390576054, "grad_norm": 1.1237276792526245, "learning_rate": 3.805017047052023e-05, "loss": 0.4794649124145508, "step": 411520 }, { "epoch": 2.446219781134274, "grad_norm": 1.0844906568527222, "learning_rate": 3.8046431158843486e-05, "loss": 0.5297882556915283, "step": 411530 }, { "epoch": 2.4462792232109423, "grad_norm": 1.42829167842865, "learning_rate": 3.80426921913691e-05, "loss": 0.5240906715393067, "step": 411540 }, { "epoch": 2.4463386652876107, "grad_norm": 1.3900413513183594, "learning_rate": 3.803895356811493e-05, "loss": 0.4837104320526123, "step": 411550 }, { "epoch": 2.4463981073642787, "grad_norm": 1.1407221555709839, "learning_rate": 3.8035215289098944e-05, "loss": 0.4931635856628418, "step": 411560 }, { "epoch": 2.4464575494409475, "grad_norm": 1.6942106485366821, "learning_rate": 3.803147735433894e-05, "loss": 0.5303251266479492, "step": 411570 }, { "epoch": 2.4465169915176155, "grad_norm": 1.2571308612823486, "learning_rate": 3.802773976385283e-05, "loss": 0.45961642265319824, "step": 411580 }, { "epoch": 2.446576433594284, "grad_norm": 1.6236497163772583, "learning_rate": 3.8024002517658466e-05, "loss": 0.4980771541595459, "step": 411590 }, { "epoch": 2.4466358756709523, "grad_norm": 1.3544623851776123, "learning_rate": 3.8020265615773786e-05, "loss": 0.4391777992248535, "step": 411600 }, { "epoch": 2.4466953177476207, "grad_norm": 1.2278298139572144, "learning_rate": 3.801652905821663e-05, "loss": 0.4845137596130371, "step": 411610 }, { "epoch": 2.446754759824289, "grad_norm": 1.2995011806488037, "learning_rate": 3.801279284500486e-05, "loss": 0.5043682098388672, "step": 411620 }, { "epoch": 2.4468142019009576, "grad_norm": 1.7028486728668213, "learning_rate": 3.800905697615638e-05, "loss": 0.4904360771179199, "step": 411630 }, { "epoch": 2.446873643977626, "grad_norm": 1.3272089958190918, "learning_rate": 3.800532145168904e-05, "loss": 0.484361457824707, "step": 411640 }, { "epoch": 2.4469330860542944, "grad_norm": 1.1387791633605957, "learning_rate": 3.8001586271620685e-05, "loss": 0.43984084129333495, "step": 411650 }, { "epoch": 2.446992528130963, "grad_norm": 1.565377116203308, "learning_rate": 3.799785143596924e-05, "loss": 0.44836015701293946, "step": 411660 }, { "epoch": 2.447051970207631, "grad_norm": 1.3342045545578003, "learning_rate": 3.799411694475254e-05, "loss": 0.4631758689880371, "step": 411670 }, { "epoch": 2.4471114122842996, "grad_norm": 1.0860884189605713, "learning_rate": 3.799038279798846e-05, "loss": 0.47935709953308103, "step": 411680 }, { "epoch": 2.447170854360968, "grad_norm": 1.2182749509811401, "learning_rate": 3.798664899569484e-05, "loss": 0.4567460060119629, "step": 411690 }, { "epoch": 2.4472302964376365, "grad_norm": 1.4685331583023071, "learning_rate": 3.798291553788958e-05, "loss": 0.4519390106201172, "step": 411700 }, { "epoch": 2.447289738514305, "grad_norm": 1.1740574836730957, "learning_rate": 3.79791824245905e-05, "loss": 0.48037042617797854, "step": 411710 }, { "epoch": 2.4473491805909733, "grad_norm": 2.168637275695801, "learning_rate": 3.797544965581545e-05, "loss": 0.5545002937316894, "step": 411720 }, { "epoch": 2.4474086226676417, "grad_norm": 1.3338059186935425, "learning_rate": 3.7971717231582346e-05, "loss": 0.4823896408081055, "step": 411730 }, { "epoch": 2.44746806474431, "grad_norm": 1.4076217412948608, "learning_rate": 3.796798515190899e-05, "loss": 0.4577642917633057, "step": 411740 }, { "epoch": 2.447527506820978, "grad_norm": 1.4336323738098145, "learning_rate": 3.796425341681327e-05, "loss": 0.4547395706176758, "step": 411750 }, { "epoch": 2.4475869488976465, "grad_norm": 1.3937722444534302, "learning_rate": 3.7960522026313014e-05, "loss": 0.49237818717956544, "step": 411760 }, { "epoch": 2.447646390974315, "grad_norm": 1.3160892724990845, "learning_rate": 3.795679098042608e-05, "loss": 0.52273530960083, "step": 411770 }, { "epoch": 2.4477058330509833, "grad_norm": 1.2098993062973022, "learning_rate": 3.795306027917028e-05, "loss": 0.5156849384307861, "step": 411780 }, { "epoch": 2.4477652751276517, "grad_norm": 1.6512655019760132, "learning_rate": 3.794932992256354e-05, "loss": 0.49885053634643556, "step": 411790 }, { "epoch": 2.44782471720432, "grad_norm": 1.1775790452957153, "learning_rate": 3.7945599910623636e-05, "loss": 0.4394291877746582, "step": 411800 }, { "epoch": 2.4478841592809886, "grad_norm": 1.4308257102966309, "learning_rate": 3.794187024336845e-05, "loss": 0.5040816307067871, "step": 411810 }, { "epoch": 2.447943601357657, "grad_norm": 1.907467246055603, "learning_rate": 3.79381409208158e-05, "loss": 0.49553794860839845, "step": 411820 }, { "epoch": 2.4480030434343254, "grad_norm": 1.3989993333816528, "learning_rate": 3.793441194298353e-05, "loss": 0.4875663757324219, "step": 411830 }, { "epoch": 2.448062485510994, "grad_norm": 1.2615854740142822, "learning_rate": 3.793068330988949e-05, "loss": 0.4949148178100586, "step": 411840 }, { "epoch": 2.4481219275876622, "grad_norm": 1.3088438510894775, "learning_rate": 3.792695502155149e-05, "loss": 0.45619940757751465, "step": 411850 }, { "epoch": 2.4481813696643306, "grad_norm": 1.469310998916626, "learning_rate": 3.79232270779874e-05, "loss": 0.5277144432067871, "step": 411860 }, { "epoch": 2.448240811740999, "grad_norm": 1.300592064857483, "learning_rate": 3.7919499479215035e-05, "loss": 0.4774054527282715, "step": 411870 }, { "epoch": 2.4483002538176675, "grad_norm": 1.391758918762207, "learning_rate": 3.791577222525222e-05, "loss": 0.533788013458252, "step": 411880 }, { "epoch": 2.448359695894336, "grad_norm": 1.4307812452316284, "learning_rate": 3.791204531611681e-05, "loss": 0.5001972675323486, "step": 411890 }, { "epoch": 2.4484191379710043, "grad_norm": 1.4288058280944824, "learning_rate": 3.7908318751826614e-05, "loss": 0.4613369941711426, "step": 411900 }, { "epoch": 2.4484785800476727, "grad_norm": 1.271296739578247, "learning_rate": 3.790459253239943e-05, "loss": 0.47905640602111815, "step": 411910 }, { "epoch": 2.448538022124341, "grad_norm": 1.316441297531128, "learning_rate": 3.790086665785314e-05, "loss": 0.4423555374145508, "step": 411920 }, { "epoch": 2.4485974642010095, "grad_norm": 1.324284315109253, "learning_rate": 3.789714112820555e-05, "loss": 0.45122346878051756, "step": 411930 }, { "epoch": 2.4486569062776775, "grad_norm": 1.3980318307876587, "learning_rate": 3.789341594347448e-05, "loss": 0.47805514335632326, "step": 411940 }, { "epoch": 2.448716348354346, "grad_norm": 1.3727171421051025, "learning_rate": 3.7889691103677706e-05, "loss": 0.48908424377441406, "step": 411950 }, { "epoch": 2.4487757904310143, "grad_norm": 1.5380845069885254, "learning_rate": 3.788596660883311e-05, "loss": 0.4963984966278076, "step": 411960 }, { "epoch": 2.4488352325076828, "grad_norm": 1.5399435758590698, "learning_rate": 3.788224245895847e-05, "loss": 0.47464542388916015, "step": 411970 }, { "epoch": 2.448894674584351, "grad_norm": 1.1877808570861816, "learning_rate": 3.787851865407161e-05, "loss": 0.49673948287963865, "step": 411980 }, { "epoch": 2.4489541166610196, "grad_norm": 1.1614649295806885, "learning_rate": 3.787479519419036e-05, "loss": 0.4627851963043213, "step": 411990 }, { "epoch": 2.449013558737688, "grad_norm": 1.317256212234497, "learning_rate": 3.787107207933255e-05, "loss": 0.47558088302612306, "step": 412000 }, { "epoch": 2.4490730008143564, "grad_norm": 1.2573648691177368, "learning_rate": 3.78673493095159e-05, "loss": 0.48929615020751954, "step": 412010 }, { "epoch": 2.449132442891025, "grad_norm": 1.2175941467285156, "learning_rate": 3.786362688475831e-05, "loss": 0.47067766189575194, "step": 412020 }, { "epoch": 2.4491918849676932, "grad_norm": 1.9708799123764038, "learning_rate": 3.785990480507755e-05, "loss": 0.5384328365325928, "step": 412030 }, { "epoch": 2.4492513270443617, "grad_norm": 1.4915595054626465, "learning_rate": 3.78561830704914e-05, "loss": 0.5336545944213867, "step": 412040 }, { "epoch": 2.44931076912103, "grad_norm": 1.2235584259033203, "learning_rate": 3.785246168101776e-05, "loss": 0.4848299503326416, "step": 412050 }, { "epoch": 2.4493702111976985, "grad_norm": 1.6027318239212036, "learning_rate": 3.7848740636674326e-05, "loss": 0.47434797286987307, "step": 412060 }, { "epoch": 2.449429653274367, "grad_norm": 1.2722816467285156, "learning_rate": 3.784501993747894e-05, "loss": 0.4724236488342285, "step": 412070 }, { "epoch": 2.4494890953510353, "grad_norm": 1.8028852939605713, "learning_rate": 3.7841299583449376e-05, "loss": 0.47956142425537107, "step": 412080 }, { "epoch": 2.4495485374277037, "grad_norm": 1.604382872581482, "learning_rate": 3.783757957460347e-05, "loss": 0.49203052520751955, "step": 412090 }, { "epoch": 2.449607979504372, "grad_norm": 1.4038584232330322, "learning_rate": 3.783385991095901e-05, "loss": 0.4998340606689453, "step": 412100 }, { "epoch": 2.44966742158104, "grad_norm": 1.6173025369644165, "learning_rate": 3.783014059253378e-05, "loss": 0.45090689659118655, "step": 412110 }, { "epoch": 2.449726863657709, "grad_norm": 1.083127498626709, "learning_rate": 3.782642161934556e-05, "loss": 0.4893342971801758, "step": 412120 }, { "epoch": 2.449786305734377, "grad_norm": 1.2454866170883179, "learning_rate": 3.7822702991412164e-05, "loss": 0.49584197998046875, "step": 412130 }, { "epoch": 2.4498457478110454, "grad_norm": 1.2693266868591309, "learning_rate": 3.781898470875135e-05, "loss": 0.47838191986083983, "step": 412140 }, { "epoch": 2.4499051898877138, "grad_norm": 1.2182620763778687, "learning_rate": 3.781526677138093e-05, "loss": 0.5084240436553955, "step": 412150 }, { "epoch": 2.449964631964382, "grad_norm": 1.4601761102676392, "learning_rate": 3.78115491793187e-05, "loss": 0.501120662689209, "step": 412160 }, { "epoch": 2.4500240740410506, "grad_norm": 1.3800729513168335, "learning_rate": 3.780783193258241e-05, "loss": 0.47357945442199706, "step": 412170 }, { "epoch": 2.450083516117719, "grad_norm": 1.014821171760559, "learning_rate": 3.780411503118989e-05, "loss": 0.44307384490966795, "step": 412180 }, { "epoch": 2.4501429581943874, "grad_norm": 1.5276936292648315, "learning_rate": 3.780039847515887e-05, "loss": 0.4598033905029297, "step": 412190 }, { "epoch": 2.450202400271056, "grad_norm": 1.1457343101501465, "learning_rate": 3.779668226450715e-05, "loss": 0.46891069412231445, "step": 412200 }, { "epoch": 2.4502618423477243, "grad_norm": 1.3662502765655518, "learning_rate": 3.779296639925248e-05, "loss": 0.44902820587158204, "step": 412210 }, { "epoch": 2.4503212844243927, "grad_norm": 1.603132963180542, "learning_rate": 3.778925087941268e-05, "loss": 0.502657127380371, "step": 412220 }, { "epoch": 2.450380726501061, "grad_norm": 1.2801958322525024, "learning_rate": 3.7785535705005514e-05, "loss": 0.46726675033569337, "step": 412230 }, { "epoch": 2.4504401685777295, "grad_norm": 1.4836775064468384, "learning_rate": 3.778182087604874e-05, "loss": 0.5246588230133057, "step": 412240 }, { "epoch": 2.450499610654398, "grad_norm": 1.1244432926177979, "learning_rate": 3.7778106392560136e-05, "loss": 0.4235495090484619, "step": 412250 }, { "epoch": 2.4505590527310663, "grad_norm": 1.0864205360412598, "learning_rate": 3.777439225455747e-05, "loss": 0.47040233612060545, "step": 412260 }, { "epoch": 2.4506184948077347, "grad_norm": 1.5556035041809082, "learning_rate": 3.777067846205847e-05, "loss": 0.4984593391418457, "step": 412270 }, { "epoch": 2.450677936884403, "grad_norm": 0.9250590801239014, "learning_rate": 3.776696501508099e-05, "loss": 0.4798842430114746, "step": 412280 }, { "epoch": 2.4507373789610716, "grad_norm": 1.0396076440811157, "learning_rate": 3.776325191364272e-05, "loss": 0.4422619819641113, "step": 412290 }, { "epoch": 2.4507968210377395, "grad_norm": 1.248207688331604, "learning_rate": 3.775953915776146e-05, "loss": 0.5035987854003906, "step": 412300 }, { "epoch": 2.4508562631144084, "grad_norm": 1.5085290670394897, "learning_rate": 3.775582674745495e-05, "loss": 0.4883111953735352, "step": 412310 }, { "epoch": 2.4509157051910764, "grad_norm": 1.3692340850830078, "learning_rate": 3.775211468274096e-05, "loss": 0.5056973457336426, "step": 412320 }, { "epoch": 2.450975147267745, "grad_norm": 1.268315076828003, "learning_rate": 3.7748402963637236e-05, "loss": 0.4549733638763428, "step": 412330 }, { "epoch": 2.451034589344413, "grad_norm": 1.0230144262313843, "learning_rate": 3.774469159016152e-05, "loss": 0.4870615005493164, "step": 412340 }, { "epoch": 2.4510940314210816, "grad_norm": 1.2848974466323853, "learning_rate": 3.774098056233161e-05, "loss": 0.4768059253692627, "step": 412350 }, { "epoch": 2.45115347349775, "grad_norm": 1.018563985824585, "learning_rate": 3.773726988016523e-05, "loss": 0.4962736129760742, "step": 412360 }, { "epoch": 2.4512129155744184, "grad_norm": 1.1989805698394775, "learning_rate": 3.773355954368014e-05, "loss": 0.45307464599609376, "step": 412370 }, { "epoch": 2.451272357651087, "grad_norm": 1.4487465620040894, "learning_rate": 3.772984955289409e-05, "loss": 0.45231924057006834, "step": 412380 }, { "epoch": 2.4513317997277553, "grad_norm": 1.568182110786438, "learning_rate": 3.772613990782481e-05, "loss": 0.45444412231445314, "step": 412390 }, { "epoch": 2.4513912418044237, "grad_norm": 1.257490634918213, "learning_rate": 3.772243060849004e-05, "loss": 0.48511390686035155, "step": 412400 }, { "epoch": 2.451450683881092, "grad_norm": 1.047101378440857, "learning_rate": 3.7718721654907565e-05, "loss": 0.48946533203125, "step": 412410 }, { "epoch": 2.4515101259577605, "grad_norm": 1.2284282445907593, "learning_rate": 3.7715013047095096e-05, "loss": 0.4628903388977051, "step": 412420 }, { "epoch": 2.451569568034429, "grad_norm": 1.5679281949996948, "learning_rate": 3.771130478507042e-05, "loss": 0.47090516090393064, "step": 412430 }, { "epoch": 2.4516290101110974, "grad_norm": 1.286389708518982, "learning_rate": 3.770759686885117e-05, "loss": 0.4548488616943359, "step": 412440 }, { "epoch": 2.4516884521877658, "grad_norm": 1.2783852815628052, "learning_rate": 3.770388929845519e-05, "loss": 0.47300872802734373, "step": 412450 }, { "epoch": 2.451747894264434, "grad_norm": 1.3347138166427612, "learning_rate": 3.770018207390018e-05, "loss": 0.4450821399688721, "step": 412460 }, { "epoch": 2.4518073363411026, "grad_norm": 1.4803825616836548, "learning_rate": 3.769647519520383e-05, "loss": 0.46961402893066406, "step": 412470 }, { "epoch": 2.451866778417771, "grad_norm": 1.3321014642715454, "learning_rate": 3.769276866238395e-05, "loss": 0.5083864212036133, "step": 412480 }, { "epoch": 2.451926220494439, "grad_norm": 1.4556634426116943, "learning_rate": 3.7689062475458256e-05, "loss": 0.5103405952453614, "step": 412490 }, { "epoch": 2.4519856625711074, "grad_norm": 1.3877787590026855, "learning_rate": 3.768535663444441e-05, "loss": 0.4616540908813477, "step": 412500 }, { "epoch": 2.452045104647776, "grad_norm": 1.533790946006775, "learning_rate": 3.768165113936021e-05, "loss": 0.5464255332946777, "step": 412510 }, { "epoch": 2.4521045467244442, "grad_norm": 0.8811782002449036, "learning_rate": 3.7677945990223356e-05, "loss": 0.4490347385406494, "step": 412520 }, { "epoch": 2.4521639888011126, "grad_norm": 1.1451176404953003, "learning_rate": 3.767424118705155e-05, "loss": 0.4418509006500244, "step": 412530 }, { "epoch": 2.452223430877781, "grad_norm": 1.238416314125061, "learning_rate": 3.767053672986256e-05, "loss": 0.4473409652709961, "step": 412540 }, { "epoch": 2.4522828729544495, "grad_norm": 1.2145520448684692, "learning_rate": 3.766683261867411e-05, "loss": 0.504789400100708, "step": 412550 }, { "epoch": 2.452342315031118, "grad_norm": 1.1513079404830933, "learning_rate": 3.766312885350387e-05, "loss": 0.5006793975830078, "step": 412560 }, { "epoch": 2.4524017571077863, "grad_norm": 1.307232141494751, "learning_rate": 3.765942543436954e-05, "loss": 0.45947465896606443, "step": 412570 }, { "epoch": 2.4524611991844547, "grad_norm": 1.3373669385910034, "learning_rate": 3.765572236128893e-05, "loss": 0.4634396076202393, "step": 412580 }, { "epoch": 2.452520641261123, "grad_norm": 1.4729853868484497, "learning_rate": 3.765201963427969e-05, "loss": 0.45467491149902345, "step": 412590 }, { "epoch": 2.4525800833377915, "grad_norm": 1.2219234704971313, "learning_rate": 3.764831725335951e-05, "loss": 0.47402248382568357, "step": 412600 }, { "epoch": 2.45263952541446, "grad_norm": 1.3279308080673218, "learning_rate": 3.7644615218546206e-05, "loss": 0.44075260162353513, "step": 412610 }, { "epoch": 2.4526989674911284, "grad_norm": 1.5429227352142334, "learning_rate": 3.764091352985738e-05, "loss": 0.5029281616210938, "step": 412620 }, { "epoch": 2.452758409567797, "grad_norm": 1.4785295724868774, "learning_rate": 3.763721218731076e-05, "loss": 0.5047740459442138, "step": 412630 }, { "epoch": 2.452817851644465, "grad_norm": 1.3469995260238647, "learning_rate": 3.7633511190924074e-05, "loss": 0.4289548873901367, "step": 412640 }, { "epoch": 2.4528772937211336, "grad_norm": 1.3679693937301636, "learning_rate": 3.762981054071503e-05, "loss": 0.5023208618164062, "step": 412650 }, { "epoch": 2.452936735797802, "grad_norm": 1.5832111835479736, "learning_rate": 3.762611023670131e-05, "loss": 0.49429945945739745, "step": 412660 }, { "epoch": 2.4529961778744704, "grad_norm": 1.563447117805481, "learning_rate": 3.7622410278900656e-05, "loss": 0.45918688774108884, "step": 412670 }, { "epoch": 2.4530556199511384, "grad_norm": 1.6239832639694214, "learning_rate": 3.761871066733071e-05, "loss": 0.448989200592041, "step": 412680 }, { "epoch": 2.453115062027807, "grad_norm": 1.4457021951675415, "learning_rate": 3.7615011402009225e-05, "loss": 0.5251935958862305, "step": 412690 }, { "epoch": 2.4531745041044752, "grad_norm": 0.8936637043952942, "learning_rate": 3.761131248295383e-05, "loss": 0.4361137390136719, "step": 412700 }, { "epoch": 2.4532339461811437, "grad_norm": 1.1156949996948242, "learning_rate": 3.760761391018228e-05, "loss": 0.5040712356567383, "step": 412710 }, { "epoch": 2.453293388257812, "grad_norm": 1.4020227193832397, "learning_rate": 3.760391568371225e-05, "loss": 0.4871476173400879, "step": 412720 }, { "epoch": 2.4533528303344805, "grad_norm": 1.3383032083511353, "learning_rate": 3.7600217803561434e-05, "loss": 0.4360435962677002, "step": 412730 }, { "epoch": 2.453412272411149, "grad_norm": 1.6826937198638916, "learning_rate": 3.75965202697475e-05, "loss": 0.48119144439697265, "step": 412740 }, { "epoch": 2.4534717144878173, "grad_norm": 1.1044968366622925, "learning_rate": 3.759282308228817e-05, "loss": 0.538739538192749, "step": 412750 }, { "epoch": 2.4535311565644857, "grad_norm": 1.4588686227798462, "learning_rate": 3.7589126241201075e-05, "loss": 0.5049867630004883, "step": 412760 }, { "epoch": 2.453590598641154, "grad_norm": 1.2778936624526978, "learning_rate": 3.7585429746503974e-05, "loss": 0.4767786502838135, "step": 412770 }, { "epoch": 2.4536500407178226, "grad_norm": 1.0220457315444946, "learning_rate": 3.7581733598214495e-05, "loss": 0.4730998992919922, "step": 412780 }, { "epoch": 2.453709482794491, "grad_norm": 1.1337836980819702, "learning_rate": 3.757803779635034e-05, "loss": 0.44205570220947266, "step": 412790 }, { "epoch": 2.4537689248711594, "grad_norm": 1.5097261667251587, "learning_rate": 3.7574342340929195e-05, "loss": 0.44760546684265134, "step": 412800 }, { "epoch": 2.453828366947828, "grad_norm": 1.58484947681427, "learning_rate": 3.757064723196871e-05, "loss": 0.4835531234741211, "step": 412810 }, { "epoch": 2.453887809024496, "grad_norm": 1.266538143157959, "learning_rate": 3.7566952469486595e-05, "loss": 0.4577049732208252, "step": 412820 }, { "epoch": 2.4539472511011646, "grad_norm": 1.4204190969467163, "learning_rate": 3.756325805350047e-05, "loss": 0.47704105377197265, "step": 412830 }, { "epoch": 2.454006693177833, "grad_norm": 1.3159492015838623, "learning_rate": 3.7559563984028076e-05, "loss": 0.506889820098877, "step": 412840 }, { "epoch": 2.454066135254501, "grad_norm": 1.7135435342788696, "learning_rate": 3.755587026108706e-05, "loss": 0.484451961517334, "step": 412850 }, { "epoch": 2.45412557733117, "grad_norm": 1.1819549798965454, "learning_rate": 3.7552176884695085e-05, "loss": 0.46098756790161133, "step": 412860 }, { "epoch": 2.454185019407838, "grad_norm": 1.3231362104415894, "learning_rate": 3.7548483854869806e-05, "loss": 0.4028994083404541, "step": 412870 }, { "epoch": 2.4542444614845063, "grad_norm": 1.5663789510726929, "learning_rate": 3.754479117162892e-05, "loss": 0.525083351135254, "step": 412880 }, { "epoch": 2.4543039035611747, "grad_norm": 1.0827608108520508, "learning_rate": 3.754109883499004e-05, "loss": 0.4246387481689453, "step": 412890 }, { "epoch": 2.454363345637843, "grad_norm": 1.1404967308044434, "learning_rate": 3.753740684497089e-05, "loss": 0.45689687728881834, "step": 412900 }, { "epoch": 2.4544227877145115, "grad_norm": 1.4289276599884033, "learning_rate": 3.75337152015891e-05, "loss": 0.471802806854248, "step": 412910 }, { "epoch": 2.45448222979118, "grad_norm": 1.430039882659912, "learning_rate": 3.7530023904862364e-05, "loss": 0.4816403865814209, "step": 412920 }, { "epoch": 2.4545416718678483, "grad_norm": 1.3510959148406982, "learning_rate": 3.752633295480826e-05, "loss": 0.45336432456970216, "step": 412930 }, { "epoch": 2.4546011139445167, "grad_norm": 1.3822849988937378, "learning_rate": 3.752264235144452e-05, "loss": 0.505281400680542, "step": 412940 }, { "epoch": 2.454660556021185, "grad_norm": 1.5971109867095947, "learning_rate": 3.751895209478878e-05, "loss": 0.48728246688842775, "step": 412950 }, { "epoch": 2.4547199980978536, "grad_norm": 1.4950997829437256, "learning_rate": 3.751526218485866e-05, "loss": 0.4679865837097168, "step": 412960 }, { "epoch": 2.454779440174522, "grad_norm": 1.7656629085540771, "learning_rate": 3.751157262167184e-05, "loss": 0.5638984680175781, "step": 412970 }, { "epoch": 2.4548388822511904, "grad_norm": 1.2898954153060913, "learning_rate": 3.7507883405246014e-05, "loss": 0.4721780776977539, "step": 412980 }, { "epoch": 2.454898324327859, "grad_norm": 1.2745118141174316, "learning_rate": 3.750419453559872e-05, "loss": 0.480500602722168, "step": 412990 }, { "epoch": 2.4549577664045272, "grad_norm": 1.3505884408950806, "learning_rate": 3.7500506012747704e-05, "loss": 0.4676796913146973, "step": 413000 }, { "epoch": 2.4550172084811956, "grad_norm": 1.25664222240448, "learning_rate": 3.7496817836710566e-05, "loss": 0.48027834892272947, "step": 413010 }, { "epoch": 2.455076650557864, "grad_norm": 1.4136945009231567, "learning_rate": 3.749313000750494e-05, "loss": 0.4299591064453125, "step": 413020 }, { "epoch": 2.4551360926345325, "grad_norm": 1.2587106227874756, "learning_rate": 3.74894425251485e-05, "loss": 0.5167603492736816, "step": 413030 }, { "epoch": 2.4551955347112004, "grad_norm": 1.4142602682113647, "learning_rate": 3.74857553896589e-05, "loss": 0.4456671714782715, "step": 413040 }, { "epoch": 2.4552549767878693, "grad_norm": 1.2434474229812622, "learning_rate": 3.748206860105373e-05, "loss": 0.44817509651184084, "step": 413050 }, { "epoch": 2.4553144188645373, "grad_norm": 1.204725980758667, "learning_rate": 3.747838215935061e-05, "loss": 0.4527854919433594, "step": 413060 }, { "epoch": 2.4553738609412057, "grad_norm": 1.2857311964035034, "learning_rate": 3.747469606456725e-05, "loss": 0.4772518157958984, "step": 413070 }, { "epoch": 2.455433303017874, "grad_norm": 1.4724020957946777, "learning_rate": 3.7471010316721226e-05, "loss": 0.4897665023803711, "step": 413080 }, { "epoch": 2.4554927450945425, "grad_norm": 1.3752435445785522, "learning_rate": 3.746732491583017e-05, "loss": 0.5201165199279785, "step": 413090 }, { "epoch": 2.455552187171211, "grad_norm": 1.6400604248046875, "learning_rate": 3.7463639861911764e-05, "loss": 0.4537508010864258, "step": 413100 }, { "epoch": 2.4556116292478793, "grad_norm": 1.4775900840759277, "learning_rate": 3.745995515498359e-05, "loss": 0.42859554290771484, "step": 413110 }, { "epoch": 2.4556710713245478, "grad_norm": 1.128489375114441, "learning_rate": 3.745627079506324e-05, "loss": 0.4722439765930176, "step": 413120 }, { "epoch": 2.455730513401216, "grad_norm": 1.3275022506713867, "learning_rate": 3.745258678216843e-05, "loss": 0.48172550201416015, "step": 413130 }, { "epoch": 2.4557899554778846, "grad_norm": 1.3648757934570312, "learning_rate": 3.744890311631673e-05, "loss": 0.488328742980957, "step": 413140 }, { "epoch": 2.455849397554553, "grad_norm": 1.34529447555542, "learning_rate": 3.7445219797525746e-05, "loss": 0.4768227577209473, "step": 413150 }, { "epoch": 2.4559088396312214, "grad_norm": 1.3899643421173096, "learning_rate": 3.7441536825813155e-05, "loss": 0.46412339210510256, "step": 413160 }, { "epoch": 2.45596828170789, "grad_norm": 1.2576053142547607, "learning_rate": 3.743785420119652e-05, "loss": 0.499959659576416, "step": 413170 }, { "epoch": 2.4560277237845582, "grad_norm": 1.303968071937561, "learning_rate": 3.743417192369348e-05, "loss": 0.465117073059082, "step": 413180 }, { "epoch": 2.4560871658612267, "grad_norm": 1.5735055208206177, "learning_rate": 3.743048999332162e-05, "loss": 0.5263506889343261, "step": 413190 }, { "epoch": 2.456146607937895, "grad_norm": 1.0758635997772217, "learning_rate": 3.742680841009861e-05, "loss": 0.51054368019104, "step": 413200 }, { "epoch": 2.4562060500145635, "grad_norm": 1.7125595808029175, "learning_rate": 3.7423127174042026e-05, "loss": 0.4772998809814453, "step": 413210 }, { "epoch": 2.456265492091232, "grad_norm": 1.8993768692016602, "learning_rate": 3.7419446285169493e-05, "loss": 0.48340959548950196, "step": 413220 }, { "epoch": 2.4563249341679, "grad_norm": 1.5375407934188843, "learning_rate": 3.741576574349859e-05, "loss": 0.49574456214904783, "step": 413230 }, { "epoch": 2.4563843762445683, "grad_norm": 0.996300220489502, "learning_rate": 3.741208554904696e-05, "loss": 0.4307579040527344, "step": 413240 }, { "epoch": 2.4564438183212367, "grad_norm": 1.2393122911453247, "learning_rate": 3.740840570183216e-05, "loss": 0.46616311073303224, "step": 413250 }, { "epoch": 2.456503260397905, "grad_norm": 1.1933196783065796, "learning_rate": 3.740472620187185e-05, "loss": 0.5011762619018555, "step": 413260 }, { "epoch": 2.4565627024745735, "grad_norm": 1.3677048683166504, "learning_rate": 3.7401047049183603e-05, "loss": 0.4445240020751953, "step": 413270 }, { "epoch": 2.456622144551242, "grad_norm": 1.3863543272018433, "learning_rate": 3.739736824378503e-05, "loss": 0.494382381439209, "step": 413280 }, { "epoch": 2.4566815866279104, "grad_norm": 1.4147396087646484, "learning_rate": 3.7393689785693705e-05, "loss": 0.5364680290222168, "step": 413290 }, { "epoch": 2.4567410287045788, "grad_norm": 1.2380937337875366, "learning_rate": 3.7390011674927246e-05, "loss": 0.4352607727050781, "step": 413300 }, { "epoch": 2.456800470781247, "grad_norm": 0.6969350576400757, "learning_rate": 3.738633391150324e-05, "loss": 0.44086418151855467, "step": 413310 }, { "epoch": 2.4568599128579156, "grad_norm": 1.2700698375701904, "learning_rate": 3.738265649543927e-05, "loss": 0.4574841022491455, "step": 413320 }, { "epoch": 2.456919354934584, "grad_norm": 1.052019476890564, "learning_rate": 3.737897942675295e-05, "loss": 0.49379544258117675, "step": 413330 }, { "epoch": 2.4569787970112524, "grad_norm": 1.4594507217407227, "learning_rate": 3.7375302705461866e-05, "loss": 0.47787065505981446, "step": 413340 }, { "epoch": 2.457038239087921, "grad_norm": 1.316657543182373, "learning_rate": 3.73716263315836e-05, "loss": 0.504028606414795, "step": 413350 }, { "epoch": 2.4570976811645893, "grad_norm": 1.4374799728393555, "learning_rate": 3.7367950305135734e-05, "loss": 0.4873197555541992, "step": 413360 }, { "epoch": 2.4571571232412577, "grad_norm": 1.272719383239746, "learning_rate": 3.736427462613586e-05, "loss": 0.5202786445617675, "step": 413370 }, { "epoch": 2.457216565317926, "grad_norm": 1.4126896858215332, "learning_rate": 3.736059929460154e-05, "loss": 0.4729128837585449, "step": 413380 }, { "epoch": 2.4572760073945945, "grad_norm": 1.3130353689193726, "learning_rate": 3.7356924310550394e-05, "loss": 0.4867580413818359, "step": 413390 }, { "epoch": 2.4573354494712625, "grad_norm": 1.191426396369934, "learning_rate": 3.735324967399998e-05, "loss": 0.4740774154663086, "step": 413400 }, { "epoch": 2.4573948915479313, "grad_norm": 1.4362362623214722, "learning_rate": 3.7349575384967886e-05, "loss": 0.48022890090942383, "step": 413410 }, { "epoch": 2.4574543336245993, "grad_norm": 1.2411161661148071, "learning_rate": 3.7345901443471676e-05, "loss": 0.44754843711853026, "step": 413420 }, { "epoch": 2.4575137757012677, "grad_norm": 1.6990571022033691, "learning_rate": 3.734222784952892e-05, "loss": 0.4992362499237061, "step": 413430 }, { "epoch": 2.457573217777936, "grad_norm": 1.161172866821289, "learning_rate": 3.73385546031572e-05, "loss": 0.46148042678833007, "step": 413440 }, { "epoch": 2.4576326598546046, "grad_norm": 1.2065409421920776, "learning_rate": 3.733488170437408e-05, "loss": 0.5028154373168945, "step": 413450 }, { "epoch": 2.457692101931273, "grad_norm": 1.5468921661376953, "learning_rate": 3.733120915319717e-05, "loss": 0.5142120361328125, "step": 413460 }, { "epoch": 2.4577515440079414, "grad_norm": 1.2120068073272705, "learning_rate": 3.732753694964401e-05, "loss": 0.4383729934692383, "step": 413470 }, { "epoch": 2.45781098608461, "grad_norm": 1.348783016204834, "learning_rate": 3.732386509373213e-05, "loss": 0.49435696601867674, "step": 413480 }, { "epoch": 2.457870428161278, "grad_norm": 1.393479585647583, "learning_rate": 3.732019358547914e-05, "loss": 0.4820765495300293, "step": 413490 }, { "epoch": 2.4579298702379466, "grad_norm": 1.2104943990707397, "learning_rate": 3.73165224249026e-05, "loss": 0.4575929641723633, "step": 413500 }, { "epoch": 2.457989312314615, "grad_norm": 0.9992854595184326, "learning_rate": 3.7312851612020037e-05, "loss": 0.4504690170288086, "step": 413510 }, { "epoch": 2.4580487543912835, "grad_norm": 1.6066474914550781, "learning_rate": 3.730918114684906e-05, "loss": 0.4641597270965576, "step": 413520 }, { "epoch": 2.458108196467952, "grad_norm": 1.408667802810669, "learning_rate": 3.7305511029407236e-05, "loss": 0.49516749382019043, "step": 413530 }, { "epoch": 2.4581676385446203, "grad_norm": 1.1541415452957153, "learning_rate": 3.730184125971205e-05, "loss": 0.41834516525268556, "step": 413540 }, { "epoch": 2.4582270806212887, "grad_norm": 1.6140483617782593, "learning_rate": 3.729817183778109e-05, "loss": 0.5432970523834229, "step": 413550 }, { "epoch": 2.458286522697957, "grad_norm": 1.3927369117736816, "learning_rate": 3.7294502763631934e-05, "loss": 0.5093228340148925, "step": 413560 }, { "epoch": 2.4583459647746255, "grad_norm": 1.3869048357009888, "learning_rate": 3.729083403728212e-05, "loss": 0.49619479179382325, "step": 413570 }, { "epoch": 2.458405406851294, "grad_norm": 1.1137053966522217, "learning_rate": 3.7287165658749173e-05, "loss": 0.4777683258056641, "step": 413580 }, { "epoch": 2.458464848927962, "grad_norm": 1.5696520805358887, "learning_rate": 3.72834976280507e-05, "loss": 0.4938239097595215, "step": 413590 }, { "epoch": 2.4585242910046308, "grad_norm": 1.4243934154510498, "learning_rate": 3.727982994520419e-05, "loss": 0.5081234455108643, "step": 413600 }, { "epoch": 2.4585837330812987, "grad_norm": 1.366949439048767, "learning_rate": 3.72761626102272e-05, "loss": 0.5047157287597657, "step": 413610 }, { "epoch": 2.458643175157967, "grad_norm": 1.2668259143829346, "learning_rate": 3.727249562313729e-05, "loss": 0.4726001262664795, "step": 413620 }, { "epoch": 2.4587026172346356, "grad_norm": 1.197045922279358, "learning_rate": 3.7268828983951996e-05, "loss": 0.4617631435394287, "step": 413630 }, { "epoch": 2.458762059311304, "grad_norm": 1.5499286651611328, "learning_rate": 3.7265162692688846e-05, "loss": 0.4646895408630371, "step": 413640 }, { "epoch": 2.4588215013879724, "grad_norm": 1.6403701305389404, "learning_rate": 3.726149674936541e-05, "loss": 0.43082246780395506, "step": 413650 }, { "epoch": 2.458880943464641, "grad_norm": 1.4443358182907104, "learning_rate": 3.725783115399918e-05, "loss": 0.5209285259246826, "step": 413660 }, { "epoch": 2.4589403855413092, "grad_norm": 1.6011286973953247, "learning_rate": 3.725416590660772e-05, "loss": 0.4414843559265137, "step": 413670 }, { "epoch": 2.4589998276179776, "grad_norm": 1.4532850980758667, "learning_rate": 3.7250501007208536e-05, "loss": 0.4762433052062988, "step": 413680 }, { "epoch": 2.459059269694646, "grad_norm": 1.4250518083572388, "learning_rate": 3.72468364558192e-05, "loss": 0.46408872604370116, "step": 413690 }, { "epoch": 2.4591187117713145, "grad_norm": 1.7353994846343994, "learning_rate": 3.7243172252457234e-05, "loss": 0.5286526679992676, "step": 413700 }, { "epoch": 2.459178153847983, "grad_norm": 1.3912593126296997, "learning_rate": 3.723950839714014e-05, "loss": 0.44398984909057615, "step": 413710 }, { "epoch": 2.4592375959246513, "grad_norm": 1.2101541757583618, "learning_rate": 3.723584488988547e-05, "loss": 0.4967621326446533, "step": 413720 }, { "epoch": 2.4592970380013197, "grad_norm": 1.0183041095733643, "learning_rate": 3.723218173071073e-05, "loss": 0.5084105014801026, "step": 413730 }, { "epoch": 2.459356480077988, "grad_norm": 1.6343598365783691, "learning_rate": 3.7228518919633436e-05, "loss": 0.5091135025024414, "step": 413740 }, { "epoch": 2.4594159221546565, "grad_norm": 1.5341358184814453, "learning_rate": 3.722485645667114e-05, "loss": 0.4278520107269287, "step": 413750 }, { "epoch": 2.459475364231325, "grad_norm": 1.2616684436798096, "learning_rate": 3.722119434184136e-05, "loss": 0.45598297119140624, "step": 413760 }, { "epoch": 2.4595348063079934, "grad_norm": 1.3426753282546997, "learning_rate": 3.72175325751616e-05, "loss": 0.48030567169189453, "step": 413770 }, { "epoch": 2.4595942483846613, "grad_norm": 1.3326716423034668, "learning_rate": 3.721387115664937e-05, "loss": 0.4735990524291992, "step": 413780 }, { "epoch": 2.45965369046133, "grad_norm": 1.1458266973495483, "learning_rate": 3.72102100863222e-05, "loss": 0.5064926147460938, "step": 413790 }, { "epoch": 2.459713132537998, "grad_norm": 1.8631943464279175, "learning_rate": 3.7206549364197595e-05, "loss": 0.48777313232421876, "step": 413800 }, { "epoch": 2.4597725746146666, "grad_norm": 1.6392322778701782, "learning_rate": 3.720288899029304e-05, "loss": 0.5003525733947753, "step": 413810 }, { "epoch": 2.459832016691335, "grad_norm": 1.3156087398529053, "learning_rate": 3.719922896462611e-05, "loss": 0.4864052295684814, "step": 413820 }, { "epoch": 2.4598914587680034, "grad_norm": 1.2575006484985352, "learning_rate": 3.719556928721426e-05, "loss": 0.45185213088989257, "step": 413830 }, { "epoch": 2.459950900844672, "grad_norm": 1.2297046184539795, "learning_rate": 3.719190995807502e-05, "loss": 0.47368531227111815, "step": 413840 }, { "epoch": 2.4600103429213402, "grad_norm": 1.3979281187057495, "learning_rate": 3.71882509772259e-05, "loss": 0.49895715713500977, "step": 413850 }, { "epoch": 2.4600697849980087, "grad_norm": 1.272573709487915, "learning_rate": 3.7184592344684386e-05, "loss": 0.4844652652740479, "step": 413860 }, { "epoch": 2.460129227074677, "grad_norm": 1.7568976879119873, "learning_rate": 3.7180934060467956e-05, "loss": 0.5059669494628907, "step": 413870 }, { "epoch": 2.4601886691513455, "grad_norm": 1.4305527210235596, "learning_rate": 3.7177276124594164e-05, "loss": 0.5193388938903809, "step": 413880 }, { "epoch": 2.460248111228014, "grad_norm": 1.2221577167510986, "learning_rate": 3.7173618537080493e-05, "loss": 0.47821874618530275, "step": 413890 }, { "epoch": 2.4603075533046823, "grad_norm": 1.2111315727233887, "learning_rate": 3.716996129794441e-05, "loss": 0.5055625438690186, "step": 413900 }, { "epoch": 2.4603669953813507, "grad_norm": 1.281810998916626, "learning_rate": 3.7166304407203454e-05, "loss": 0.4723653793334961, "step": 413910 }, { "epoch": 2.460426437458019, "grad_norm": 1.2560518980026245, "learning_rate": 3.716264786487509e-05, "loss": 0.4470676422119141, "step": 413920 }, { "epoch": 2.4604858795346876, "grad_norm": 1.2768969535827637, "learning_rate": 3.715899167097682e-05, "loss": 0.46489405632019043, "step": 413930 }, { "epoch": 2.460545321611356, "grad_norm": 1.1034386157989502, "learning_rate": 3.715533582552609e-05, "loss": 0.4679816722869873, "step": 413940 }, { "epoch": 2.4606047636880244, "grad_norm": 1.2677181959152222, "learning_rate": 3.715168032854047e-05, "loss": 0.41772851943969724, "step": 413950 }, { "epoch": 2.460664205764693, "grad_norm": 1.175270438194275, "learning_rate": 3.714802518003739e-05, "loss": 0.4649660587310791, "step": 413960 }, { "epoch": 2.4607236478413608, "grad_norm": 1.678650140762329, "learning_rate": 3.714437038003435e-05, "loss": 0.4937752723693848, "step": 413970 }, { "epoch": 2.460783089918029, "grad_norm": 1.121274471282959, "learning_rate": 3.714071592854883e-05, "loss": 0.49969873428344724, "step": 413980 }, { "epoch": 2.4608425319946976, "grad_norm": 1.501863956451416, "learning_rate": 3.713706182559833e-05, "loss": 0.5622208595275879, "step": 413990 }, { "epoch": 2.460901974071366, "grad_norm": 1.0467426776885986, "learning_rate": 3.7133408071200276e-05, "loss": 0.5102458953857422, "step": 414000 }, { "epoch": 2.4609614161480344, "grad_norm": 1.1063250303268433, "learning_rate": 3.7129754665372216e-05, "loss": 0.47040705680847167, "step": 414010 }, { "epoch": 2.461020858224703, "grad_norm": 1.3262784481048584, "learning_rate": 3.71261016081316e-05, "loss": 0.4865267276763916, "step": 414020 }, { "epoch": 2.4610803003013713, "grad_norm": 1.268498182296753, "learning_rate": 3.712244889949591e-05, "loss": 0.5013946056365967, "step": 414030 }, { "epoch": 2.4611397423780397, "grad_norm": 1.3229377269744873, "learning_rate": 3.711879653948256e-05, "loss": 0.4623116493225098, "step": 414040 }, { "epoch": 2.461199184454708, "grad_norm": 1.2768888473510742, "learning_rate": 3.7115144528109105e-05, "loss": 0.4786726951599121, "step": 414050 }, { "epoch": 2.4612586265313765, "grad_norm": 1.2383350133895874, "learning_rate": 3.711149286539297e-05, "loss": 0.46112651824951173, "step": 414060 }, { "epoch": 2.461318068608045, "grad_norm": 1.849568247795105, "learning_rate": 3.710784155135161e-05, "loss": 0.5147429466247558, "step": 414070 }, { "epoch": 2.4613775106847133, "grad_norm": 1.4426714181900024, "learning_rate": 3.710419058600256e-05, "loss": 0.46119394302368166, "step": 414080 }, { "epoch": 2.4614369527613817, "grad_norm": 1.4350240230560303, "learning_rate": 3.7100539969363236e-05, "loss": 0.5153470516204834, "step": 414090 }, { "epoch": 2.46149639483805, "grad_norm": 1.5127211809158325, "learning_rate": 3.7096889701451054e-05, "loss": 0.4873626232147217, "step": 414100 }, { "epoch": 2.4615558369147186, "grad_norm": 1.2894892692565918, "learning_rate": 3.709323978228356e-05, "loss": 0.4667226791381836, "step": 414110 }, { "epoch": 2.461615278991387, "grad_norm": 1.3980146646499634, "learning_rate": 3.708959021187819e-05, "loss": 0.5179171562194824, "step": 414120 }, { "epoch": 2.4616747210680554, "grad_norm": 0.9805454611778259, "learning_rate": 3.7085940990252374e-05, "loss": 0.5010148048400879, "step": 414130 }, { "epoch": 2.4617341631447234, "grad_norm": 1.3232039213180542, "learning_rate": 3.708229211742361e-05, "loss": 0.47433900833129883, "step": 414140 }, { "epoch": 2.4617936052213922, "grad_norm": 1.1604830026626587, "learning_rate": 3.7078643593409326e-05, "loss": 0.5257553100585938, "step": 414150 }, { "epoch": 2.46185304729806, "grad_norm": 0.989645779132843, "learning_rate": 3.707499541822696e-05, "loss": 0.46542844772338865, "step": 414160 }, { "epoch": 2.4619124893747286, "grad_norm": 1.5303927659988403, "learning_rate": 3.707134759189399e-05, "loss": 0.45480971336364745, "step": 414170 }, { "epoch": 2.461971931451397, "grad_norm": 1.1710163354873657, "learning_rate": 3.7067700114427854e-05, "loss": 0.5008678436279297, "step": 414180 }, { "epoch": 2.4620313735280654, "grad_norm": 1.3920482397079468, "learning_rate": 3.706405298584602e-05, "loss": 0.49175729751586916, "step": 414190 }, { "epoch": 2.462090815604734, "grad_norm": 1.3495033979415894, "learning_rate": 3.7060406206165934e-05, "loss": 0.4606379508972168, "step": 414200 }, { "epoch": 2.4621502576814023, "grad_norm": 1.1320852041244507, "learning_rate": 3.705675977540502e-05, "loss": 0.4500528335571289, "step": 414210 }, { "epoch": 2.4622096997580707, "grad_norm": 1.4318928718566895, "learning_rate": 3.705311369358071e-05, "loss": 0.5039963245391845, "step": 414220 }, { "epoch": 2.462269141834739, "grad_norm": 1.2340800762176514, "learning_rate": 3.704946796071046e-05, "loss": 0.5509707927703857, "step": 414230 }, { "epoch": 2.4623285839114075, "grad_norm": 1.068100929260254, "learning_rate": 3.704582257681172e-05, "loss": 0.4401749610900879, "step": 414240 }, { "epoch": 2.462388025988076, "grad_norm": 1.0983209609985352, "learning_rate": 3.704217754190193e-05, "loss": 0.5177115440368653, "step": 414250 }, { "epoch": 2.4624474680647443, "grad_norm": 1.3226392269134521, "learning_rate": 3.7038532855998536e-05, "loss": 0.5061066627502442, "step": 414260 }, { "epoch": 2.4625069101414128, "grad_norm": 1.5883005857467651, "learning_rate": 3.703488851911895e-05, "loss": 0.4923757553100586, "step": 414270 }, { "epoch": 2.462566352218081, "grad_norm": 1.4909831285476685, "learning_rate": 3.7031244531280605e-05, "loss": 0.5026793479919434, "step": 414280 }, { "epoch": 2.4626257942947496, "grad_norm": 1.1729111671447754, "learning_rate": 3.702760089250095e-05, "loss": 0.4430218696594238, "step": 414290 }, { "epoch": 2.462685236371418, "grad_norm": 1.4341912269592285, "learning_rate": 3.702395760279737e-05, "loss": 0.4778872489929199, "step": 414300 }, { "epoch": 2.4627446784480864, "grad_norm": 1.4385839700698853, "learning_rate": 3.702031466218736e-05, "loss": 0.48058338165283204, "step": 414310 }, { "epoch": 2.462804120524755, "grad_norm": 1.3586971759796143, "learning_rate": 3.7016672070688305e-05, "loss": 0.4575822830200195, "step": 414320 }, { "epoch": 2.462863562601423, "grad_norm": 1.26069176197052, "learning_rate": 3.7013029828317645e-05, "loss": 0.4496580123901367, "step": 414330 }, { "epoch": 2.4629230046780917, "grad_norm": 0.9935894012451172, "learning_rate": 3.70093879350928e-05, "loss": 0.4633171558380127, "step": 414340 }, { "epoch": 2.4629824467547596, "grad_norm": 1.267503261566162, "learning_rate": 3.7005746391031184e-05, "loss": 0.48825960159301757, "step": 414350 }, { "epoch": 2.463041888831428, "grad_norm": 1.2604219913482666, "learning_rate": 3.700210519615021e-05, "loss": 0.4623607635498047, "step": 414360 }, { "epoch": 2.4631013309080965, "grad_norm": 1.2787647247314453, "learning_rate": 3.6998464350467325e-05, "loss": 0.4884469985961914, "step": 414370 }, { "epoch": 2.463160772984765, "grad_norm": 1.1135473251342773, "learning_rate": 3.6994823853999925e-05, "loss": 0.48204660415649414, "step": 414380 }, { "epoch": 2.4632202150614333, "grad_norm": 1.428075909614563, "learning_rate": 3.699118370676543e-05, "loss": 0.4741621494293213, "step": 414390 }, { "epoch": 2.4632796571381017, "grad_norm": 1.5065219402313232, "learning_rate": 3.6987543908781265e-05, "loss": 0.4359307289123535, "step": 414400 }, { "epoch": 2.46333909921477, "grad_norm": 1.6753402948379517, "learning_rate": 3.698390446006481e-05, "loss": 0.471754264831543, "step": 414410 }, { "epoch": 2.4633985412914385, "grad_norm": 1.2688772678375244, "learning_rate": 3.6980265360633506e-05, "loss": 0.4718030452728271, "step": 414420 }, { "epoch": 2.463457983368107, "grad_norm": 1.7890183925628662, "learning_rate": 3.697662661050473e-05, "loss": 0.5542057037353516, "step": 414430 }, { "epoch": 2.4635174254447754, "grad_norm": 1.2427008152008057, "learning_rate": 3.697298820969592e-05, "loss": 0.4559197425842285, "step": 414440 }, { "epoch": 2.463576867521444, "grad_norm": 1.2529778480529785, "learning_rate": 3.696935015822449e-05, "loss": 0.48457794189453124, "step": 414450 }, { "epoch": 2.463636309598112, "grad_norm": 0.9458956122398376, "learning_rate": 3.6965712456107805e-05, "loss": 0.4530062198638916, "step": 414460 }, { "epoch": 2.4636957516747806, "grad_norm": 1.0062711238861084, "learning_rate": 3.696207510336328e-05, "loss": 0.5050844192504883, "step": 414470 }, { "epoch": 2.463755193751449, "grad_norm": 1.3723077774047852, "learning_rate": 3.695843810000833e-05, "loss": 0.5035941123962402, "step": 414480 }, { "epoch": 2.4638146358281174, "grad_norm": 1.2575980424880981, "learning_rate": 3.695480144606033e-05, "loss": 0.47634105682373046, "step": 414490 }, { "epoch": 2.463874077904786, "grad_norm": 1.228489875793457, "learning_rate": 3.695116514153668e-05, "loss": 0.4785101890563965, "step": 414500 }, { "epoch": 2.4639335199814543, "grad_norm": 1.3235255479812622, "learning_rate": 3.6947529186454785e-05, "loss": 0.48923563957214355, "step": 414510 }, { "epoch": 2.4639929620581222, "grad_norm": 1.1169530153274536, "learning_rate": 3.694389358083208e-05, "loss": 0.44954695701599123, "step": 414520 }, { "epoch": 2.464052404134791, "grad_norm": 1.5158494710922241, "learning_rate": 3.694025832468586e-05, "loss": 0.4725313663482666, "step": 414530 }, { "epoch": 2.464111846211459, "grad_norm": 1.2811638116836548, "learning_rate": 3.6936623418033586e-05, "loss": 0.4739401817321777, "step": 414540 }, { "epoch": 2.4641712882881275, "grad_norm": 1.0367214679718018, "learning_rate": 3.6932988860892636e-05, "loss": 0.4440114974975586, "step": 414550 }, { "epoch": 2.464230730364796, "grad_norm": 1.666882872581482, "learning_rate": 3.6929354653280354e-05, "loss": 0.5018151760101318, "step": 414560 }, { "epoch": 2.4642901724414643, "grad_norm": 1.2101048231124878, "learning_rate": 3.6925720795214195e-05, "loss": 0.5366251945495606, "step": 414570 }, { "epoch": 2.4643496145181327, "grad_norm": 1.3106927871704102, "learning_rate": 3.6922087286711526e-05, "loss": 0.45580034255981444, "step": 414580 }, { "epoch": 2.464409056594801, "grad_norm": 1.4121025800704956, "learning_rate": 3.691845412778967e-05, "loss": 0.5201297283172608, "step": 414590 }, { "epoch": 2.4644684986714696, "grad_norm": 1.4649274349212646, "learning_rate": 3.691482131846605e-05, "loss": 0.49480977058410647, "step": 414600 }, { "epoch": 2.464527940748138, "grad_norm": 1.389723777770996, "learning_rate": 3.691118885875806e-05, "loss": 0.46909198760986326, "step": 414610 }, { "epoch": 2.4645873828248064, "grad_norm": 1.0722800493240356, "learning_rate": 3.690755674868305e-05, "loss": 0.44544034004211425, "step": 414620 }, { "epoch": 2.464646824901475, "grad_norm": 1.054391860961914, "learning_rate": 3.690392498825839e-05, "loss": 0.5187644004821778, "step": 414630 }, { "epoch": 2.464706266978143, "grad_norm": 1.1743366718292236, "learning_rate": 3.690029357750149e-05, "loss": 0.4962893486022949, "step": 414640 }, { "epoch": 2.4647657090548116, "grad_norm": 1.290679931640625, "learning_rate": 3.6896662516429684e-05, "loss": 0.5287511825561524, "step": 414650 }, { "epoch": 2.46482515113148, "grad_norm": 1.02936851978302, "learning_rate": 3.689303180506033e-05, "loss": 0.49186029434204104, "step": 414660 }, { "epoch": 2.4648845932081485, "grad_norm": 1.3682057857513428, "learning_rate": 3.688940144341084e-05, "loss": 0.476865291595459, "step": 414670 }, { "epoch": 2.464944035284817, "grad_norm": 1.222984790802002, "learning_rate": 3.688577143149856e-05, "loss": 0.42443552017211916, "step": 414680 }, { "epoch": 2.4650034773614853, "grad_norm": 1.5041643381118774, "learning_rate": 3.688214176934084e-05, "loss": 0.45502510070800783, "step": 414690 }, { "epoch": 2.4650629194381537, "grad_norm": 1.4133254289627075, "learning_rate": 3.687851245695511e-05, "loss": 0.4669215202331543, "step": 414700 }, { "epoch": 2.4651223615148217, "grad_norm": 1.1800172328948975, "learning_rate": 3.687488349435864e-05, "loss": 0.4826772689819336, "step": 414710 }, { "epoch": 2.46518180359149, "grad_norm": 1.509596824645996, "learning_rate": 3.6871254881568806e-05, "loss": 0.4960781097412109, "step": 414720 }, { "epoch": 2.4652412456681585, "grad_norm": 1.2018320560455322, "learning_rate": 3.6867626618603025e-05, "loss": 0.4846000671386719, "step": 414730 }, { "epoch": 2.465300687744827, "grad_norm": 1.382436752319336, "learning_rate": 3.6863998705478616e-05, "loss": 0.48225693702697753, "step": 414740 }, { "epoch": 2.4653601298214953, "grad_norm": 1.0546956062316895, "learning_rate": 3.686037114221293e-05, "loss": 0.46425628662109375, "step": 414750 }, { "epoch": 2.4654195718981637, "grad_norm": 1.2090638875961304, "learning_rate": 3.6856743928823336e-05, "loss": 0.4624135971069336, "step": 414760 }, { "epoch": 2.465479013974832, "grad_norm": 1.4385044574737549, "learning_rate": 3.6853117065327166e-05, "loss": 0.48929648399353026, "step": 414770 }, { "epoch": 2.4655384560515006, "grad_norm": 1.4230549335479736, "learning_rate": 3.684949055174179e-05, "loss": 0.5194106578826905, "step": 414780 }, { "epoch": 2.465597898128169, "grad_norm": 1.4037024974822998, "learning_rate": 3.684586438808452e-05, "loss": 0.4970378875732422, "step": 414790 }, { "epoch": 2.4656573402048374, "grad_norm": 1.3880305290222168, "learning_rate": 3.6842238574372745e-05, "loss": 0.5276878833770752, "step": 414800 }, { "epoch": 2.465716782281506, "grad_norm": 1.246803641319275, "learning_rate": 3.683861311062379e-05, "loss": 0.49169073104858396, "step": 414810 }, { "epoch": 2.4657762243581742, "grad_norm": 1.2531483173370361, "learning_rate": 3.6834987996855e-05, "loss": 0.484804630279541, "step": 414820 }, { "epoch": 2.4658356664348426, "grad_norm": 1.6989907026290894, "learning_rate": 3.683136323308373e-05, "loss": 0.5102249622344971, "step": 414830 }, { "epoch": 2.465895108511511, "grad_norm": 1.6398547887802124, "learning_rate": 3.6827738819327296e-05, "loss": 0.4731252670288086, "step": 414840 }, { "epoch": 2.4659545505881795, "grad_norm": 1.4405510425567627, "learning_rate": 3.682411475560302e-05, "loss": 0.4923738479614258, "step": 414850 }, { "epoch": 2.466013992664848, "grad_norm": 1.534593105316162, "learning_rate": 3.682049104192829e-05, "loss": 0.493881368637085, "step": 414860 }, { "epoch": 2.4660734347415163, "grad_norm": 1.5521905422210693, "learning_rate": 3.681686767832042e-05, "loss": 0.47994723320007326, "step": 414870 }, { "epoch": 2.4661328768181843, "grad_norm": 1.0853298902511597, "learning_rate": 3.6813244664796745e-05, "loss": 0.4930868148803711, "step": 414880 }, { "epoch": 2.466192318894853, "grad_norm": 1.02219557762146, "learning_rate": 3.680962200137458e-05, "loss": 0.43264617919921877, "step": 414890 }, { "epoch": 2.466251760971521, "grad_norm": 1.3899104595184326, "learning_rate": 3.680599968807127e-05, "loss": 0.46998019218444825, "step": 414900 }, { "epoch": 2.4663112030481895, "grad_norm": 1.4751988649368286, "learning_rate": 3.680237772490413e-05, "loss": 0.4652960777282715, "step": 414910 }, { "epoch": 2.466370645124858, "grad_norm": 1.3892672061920166, "learning_rate": 3.6798756111890474e-05, "loss": 0.5135022163391113, "step": 414920 }, { "epoch": 2.4664300872015263, "grad_norm": 1.528680443763733, "learning_rate": 3.679513484904766e-05, "loss": 0.4786137580871582, "step": 414930 }, { "epoch": 2.4664895292781948, "grad_norm": 1.396706461906433, "learning_rate": 3.6791513936393016e-05, "loss": 0.47460641860961916, "step": 414940 }, { "epoch": 2.466548971354863, "grad_norm": 1.4356657266616821, "learning_rate": 3.678789337394384e-05, "loss": 0.4980793476104736, "step": 414950 }, { "epoch": 2.4666084134315316, "grad_norm": 1.412231683731079, "learning_rate": 3.6784273161717454e-05, "loss": 0.4754620552062988, "step": 414960 }, { "epoch": 2.4666678555082, "grad_norm": 1.2707445621490479, "learning_rate": 3.678065329973117e-05, "loss": 0.49611506462097166, "step": 414970 }, { "epoch": 2.4667272975848684, "grad_norm": 1.1382970809936523, "learning_rate": 3.6777033788002314e-05, "loss": 0.4869701862335205, "step": 414980 }, { "epoch": 2.466786739661537, "grad_norm": 1.320590615272522, "learning_rate": 3.6773414626548185e-05, "loss": 0.4640390396118164, "step": 414990 }, { "epoch": 2.4668461817382052, "grad_norm": 1.484294056892395, "learning_rate": 3.676979581538613e-05, "loss": 0.5166388511657715, "step": 415000 }, { "epoch": 2.4669056238148737, "grad_norm": 1.750380516052246, "learning_rate": 3.676617735453346e-05, "loss": 0.4562861442565918, "step": 415010 }, { "epoch": 2.466965065891542, "grad_norm": 1.645745873451233, "learning_rate": 3.676255924400742e-05, "loss": 0.48320908546447755, "step": 415020 }, { "epoch": 2.4670245079682105, "grad_norm": 1.1712182760238647, "learning_rate": 3.6758941483825386e-05, "loss": 0.43712196350097654, "step": 415030 }, { "epoch": 2.467083950044879, "grad_norm": 1.094875454902649, "learning_rate": 3.675532407400464e-05, "loss": 0.45708541870117186, "step": 415040 }, { "epoch": 2.4671433921215473, "grad_norm": 1.0633889436721802, "learning_rate": 3.6751707014562456e-05, "loss": 0.5101018428802491, "step": 415050 }, { "epoch": 2.4672028341982157, "grad_norm": 1.1396178007125854, "learning_rate": 3.6748090305516206e-05, "loss": 0.42038793563842775, "step": 415060 }, { "epoch": 2.4672622762748837, "grad_norm": 1.1993802785873413, "learning_rate": 3.674447394688316e-05, "loss": 0.5113160133361816, "step": 415070 }, { "epoch": 2.4673217183515526, "grad_norm": 1.35116708278656, "learning_rate": 3.674085793868057e-05, "loss": 0.4736050605773926, "step": 415080 }, { "epoch": 2.4673811604282205, "grad_norm": 1.3121919631958008, "learning_rate": 3.67372422809258e-05, "loss": 0.47618951797485354, "step": 415090 }, { "epoch": 2.467440602504889, "grad_norm": 1.4291518926620483, "learning_rate": 3.673362697363612e-05, "loss": 0.49894008636474607, "step": 415100 }, { "epoch": 2.4675000445815574, "grad_norm": 1.3002431392669678, "learning_rate": 3.673001201682883e-05, "loss": 0.5037202835083008, "step": 415110 }, { "epoch": 2.4675594866582258, "grad_norm": 1.3141117095947266, "learning_rate": 3.6726397410521185e-05, "loss": 0.5153404712677002, "step": 415120 }, { "epoch": 2.467618928734894, "grad_norm": 1.1918854713439941, "learning_rate": 3.6722783154730565e-05, "loss": 0.4576424598693848, "step": 415130 }, { "epoch": 2.4676783708115626, "grad_norm": 1.2309328317642212, "learning_rate": 3.6719169249474175e-05, "loss": 0.487578010559082, "step": 415140 }, { "epoch": 2.467737812888231, "grad_norm": 1.2400939464569092, "learning_rate": 3.67155556947693e-05, "loss": 0.46461262702941897, "step": 415150 }, { "epoch": 2.4677972549648994, "grad_norm": 1.3590576648712158, "learning_rate": 3.67119424906333e-05, "loss": 0.48120923042297364, "step": 415160 }, { "epoch": 2.467856697041568, "grad_norm": 1.6479706764221191, "learning_rate": 3.670832963708339e-05, "loss": 0.5233093738555908, "step": 415170 }, { "epoch": 2.4679161391182363, "grad_norm": 0.954919695854187, "learning_rate": 3.670471713413688e-05, "loss": 0.4696483135223389, "step": 415180 }, { "epoch": 2.4679755811949047, "grad_norm": 1.0703047513961792, "learning_rate": 3.670110498181107e-05, "loss": 0.4465658187866211, "step": 415190 }, { "epoch": 2.468035023271573, "grad_norm": 1.4395884275436401, "learning_rate": 3.669749318012323e-05, "loss": 0.48000326156616213, "step": 415200 }, { "epoch": 2.4680944653482415, "grad_norm": 1.1100099086761475, "learning_rate": 3.669388172909058e-05, "loss": 0.47737722396850585, "step": 415210 }, { "epoch": 2.46815390742491, "grad_norm": 1.4381433725357056, "learning_rate": 3.669027062873047e-05, "loss": 0.4550042629241943, "step": 415220 }, { "epoch": 2.4682133495015783, "grad_norm": 1.282314658164978, "learning_rate": 3.668665987906015e-05, "loss": 0.48682026863098143, "step": 415230 }, { "epoch": 2.4682727915782467, "grad_norm": 1.4349312782287598, "learning_rate": 3.66830494800969e-05, "loss": 0.4635136604309082, "step": 415240 }, { "epoch": 2.468332233654915, "grad_norm": 1.171521544456482, "learning_rate": 3.667943943185796e-05, "loss": 0.49320616722106936, "step": 415250 }, { "epoch": 2.468391675731583, "grad_norm": 1.5433884859085083, "learning_rate": 3.6675829734360636e-05, "loss": 0.49628705978393556, "step": 415260 }, { "epoch": 2.468451117808252, "grad_norm": 1.5430498123168945, "learning_rate": 3.667222038762218e-05, "loss": 0.4680290222167969, "step": 415270 }, { "epoch": 2.46851055988492, "grad_norm": 1.5886518955230713, "learning_rate": 3.6668611391659815e-05, "loss": 0.5406570911407471, "step": 415280 }, { "epoch": 2.4685700019615884, "grad_norm": 1.147093415260315, "learning_rate": 3.6665002746490896e-05, "loss": 0.46034717559814453, "step": 415290 }, { "epoch": 2.468629444038257, "grad_norm": 1.354609489440918, "learning_rate": 3.6661394452132626e-05, "loss": 0.4799003601074219, "step": 415300 }, { "epoch": 2.468688886114925, "grad_norm": 1.3172199726104736, "learning_rate": 3.6657786508602277e-05, "loss": 0.488063383102417, "step": 415310 }, { "epoch": 2.4687483281915936, "grad_norm": 1.488863468170166, "learning_rate": 3.66541789159171e-05, "loss": 0.47992630004882814, "step": 415320 }, { "epoch": 2.468807770268262, "grad_norm": 0.8965017199516296, "learning_rate": 3.665057167409438e-05, "loss": 0.48634090423583987, "step": 415330 }, { "epoch": 2.4688672123449305, "grad_norm": 1.3233784437179565, "learning_rate": 3.6646964783151326e-05, "loss": 0.5094061851501465, "step": 415340 }, { "epoch": 2.468926654421599, "grad_norm": 0.9285074472427368, "learning_rate": 3.664335824310524e-05, "loss": 0.45876240730285645, "step": 415350 }, { "epoch": 2.4689860964982673, "grad_norm": 1.2561215162277222, "learning_rate": 3.663975205397336e-05, "loss": 0.5046778678894043, "step": 415360 }, { "epoch": 2.4690455385749357, "grad_norm": 0.9297573566436768, "learning_rate": 3.663614621577293e-05, "loss": 0.46005778312683104, "step": 415370 }, { "epoch": 2.469104980651604, "grad_norm": 1.0899568796157837, "learning_rate": 3.66325407285212e-05, "loss": 0.46576876640319825, "step": 415380 }, { "epoch": 2.4691644227282725, "grad_norm": 1.4593374729156494, "learning_rate": 3.662893559223541e-05, "loss": 0.48901777267456054, "step": 415390 }, { "epoch": 2.469223864804941, "grad_norm": 1.4047043323516846, "learning_rate": 3.662533080693282e-05, "loss": 0.48233208656311033, "step": 415400 }, { "epoch": 2.4692833068816094, "grad_norm": 1.3254860639572144, "learning_rate": 3.662172637263065e-05, "loss": 0.47257304191589355, "step": 415410 }, { "epoch": 2.4693427489582778, "grad_norm": 0.9737789034843445, "learning_rate": 3.661812228934618e-05, "loss": 0.4984743118286133, "step": 415420 }, { "epoch": 2.469402191034946, "grad_norm": 1.2065573930740356, "learning_rate": 3.6614518557096635e-05, "loss": 0.43685197830200195, "step": 415430 }, { "epoch": 2.4694616331116146, "grad_norm": 1.3560518026351929, "learning_rate": 3.661091517589925e-05, "loss": 0.5246162414550781, "step": 415440 }, { "epoch": 2.4695210751882826, "grad_norm": 1.0636537075042725, "learning_rate": 3.660731214577126e-05, "loss": 0.49552011489868164, "step": 415450 }, { "epoch": 2.469580517264951, "grad_norm": 1.2552838325500488, "learning_rate": 3.660370946672991e-05, "loss": 0.458342456817627, "step": 415460 }, { "epoch": 2.4696399593416194, "grad_norm": 1.2067195177078247, "learning_rate": 3.6600107138792414e-05, "loss": 0.5043504714965821, "step": 415470 }, { "epoch": 2.469699401418288, "grad_norm": 1.452080488204956, "learning_rate": 3.6596505161976004e-05, "loss": 0.45139074325561523, "step": 415480 }, { "epoch": 2.4697588434949562, "grad_norm": 1.144032597541809, "learning_rate": 3.659290353629795e-05, "loss": 0.4940230369567871, "step": 415490 }, { "epoch": 2.4698182855716246, "grad_norm": 1.0652331113815308, "learning_rate": 3.658930226177547e-05, "loss": 0.4659935474395752, "step": 415500 }, { "epoch": 2.469877727648293, "grad_norm": 1.169287085533142, "learning_rate": 3.658570133842574e-05, "loss": 0.4832633972167969, "step": 415510 }, { "epoch": 2.4699371697249615, "grad_norm": 1.3189586400985718, "learning_rate": 3.658210076626605e-05, "loss": 0.5164239883422852, "step": 415520 }, { "epoch": 2.46999661180163, "grad_norm": 1.4080613851547241, "learning_rate": 3.6578500545313586e-05, "loss": 0.48686766624450684, "step": 415530 }, { "epoch": 2.4700560538782983, "grad_norm": 1.2727571725845337, "learning_rate": 3.657490067558555e-05, "loss": 0.4794827938079834, "step": 415540 }, { "epoch": 2.4701154959549667, "grad_norm": 1.5465059280395508, "learning_rate": 3.6571301157099224e-05, "loss": 0.4944192886352539, "step": 415550 }, { "epoch": 2.470174938031635, "grad_norm": 1.5245873928070068, "learning_rate": 3.656770198987184e-05, "loss": 0.49339799880981444, "step": 415560 }, { "epoch": 2.4702343801083035, "grad_norm": 1.37492036819458, "learning_rate": 3.656410317392051e-05, "loss": 0.5662528038024902, "step": 415570 }, { "epoch": 2.470293822184972, "grad_norm": 1.7323168516159058, "learning_rate": 3.6560504709262524e-05, "loss": 0.44577274322509763, "step": 415580 }, { "epoch": 2.4703532642616404, "grad_norm": 0.9832668900489807, "learning_rate": 3.6556906595915094e-05, "loss": 0.4512115478515625, "step": 415590 }, { "epoch": 2.470412706338309, "grad_norm": 1.315148949623108, "learning_rate": 3.6553308833895415e-05, "loss": 0.5087138652801514, "step": 415600 }, { "epoch": 2.470472148414977, "grad_norm": 1.206032156944275, "learning_rate": 3.6549711423220686e-05, "loss": 0.4795994281768799, "step": 415610 }, { "epoch": 2.470531590491645, "grad_norm": 1.1175638437271118, "learning_rate": 3.654611436390818e-05, "loss": 0.44807777404785154, "step": 415620 }, { "epoch": 2.470591032568314, "grad_norm": 1.3199886083602905, "learning_rate": 3.654251765597504e-05, "loss": 0.48421573638916016, "step": 415630 }, { "epoch": 2.470650474644982, "grad_norm": 1.5472670793533325, "learning_rate": 3.653892129943847e-05, "loss": 0.5149043083190918, "step": 415640 }, { "epoch": 2.4707099167216504, "grad_norm": 1.4324795007705688, "learning_rate": 3.6535325294315696e-05, "loss": 0.45307626724243166, "step": 415650 }, { "epoch": 2.470769358798319, "grad_norm": 0.8447032570838928, "learning_rate": 3.653172964062393e-05, "loss": 0.47398743629455564, "step": 415660 }, { "epoch": 2.4708288008749872, "grad_norm": 1.6296552419662476, "learning_rate": 3.6528134338380325e-05, "loss": 0.4763181686401367, "step": 415670 }, { "epoch": 2.4708882429516557, "grad_norm": 1.4934206008911133, "learning_rate": 3.6524539387602174e-05, "loss": 0.5314848899841309, "step": 415680 }, { "epoch": 2.470947685028324, "grad_norm": 1.5034908056259155, "learning_rate": 3.65209447883066e-05, "loss": 0.4791379451751709, "step": 415690 }, { "epoch": 2.4710071271049925, "grad_norm": 1.293180227279663, "learning_rate": 3.6517350540510765e-05, "loss": 0.5061029911041259, "step": 415700 }, { "epoch": 2.471066569181661, "grad_norm": 1.4779325723648071, "learning_rate": 3.651375664423195e-05, "loss": 0.4617734909057617, "step": 415710 }, { "epoch": 2.4711260112583293, "grad_norm": 1.2696583271026611, "learning_rate": 3.6510163099487306e-05, "loss": 0.5241269588470459, "step": 415720 }, { "epoch": 2.4711854533349977, "grad_norm": 1.2592189311981201, "learning_rate": 3.650656990629402e-05, "loss": 0.44733471870422364, "step": 415730 }, { "epoch": 2.471244895411666, "grad_norm": 1.3289599418640137, "learning_rate": 3.650297706466929e-05, "loss": 0.498477840423584, "step": 415740 }, { "epoch": 2.4713043374883346, "grad_norm": 1.0994998216629028, "learning_rate": 3.6499384574630304e-05, "loss": 0.4447612762451172, "step": 415750 }, { "epoch": 2.471363779565003, "grad_norm": 0.9866710901260376, "learning_rate": 3.649579243619423e-05, "loss": 0.4434189796447754, "step": 415760 }, { "epoch": 2.4714232216416714, "grad_norm": 0.9507150650024414, "learning_rate": 3.6492200649378245e-05, "loss": 0.4718486785888672, "step": 415770 }, { "epoch": 2.47148266371834, "grad_norm": 1.1484780311584473, "learning_rate": 3.6488609214199575e-05, "loss": 0.4953636169433594, "step": 415780 }, { "epoch": 2.471542105795008, "grad_norm": 1.2349766492843628, "learning_rate": 3.648501813067536e-05, "loss": 0.541651725769043, "step": 415790 }, { "epoch": 2.4716015478716766, "grad_norm": 1.3261538743972778, "learning_rate": 3.648142739882281e-05, "loss": 0.526242733001709, "step": 415800 }, { "epoch": 2.4716609899483446, "grad_norm": 1.5700711011886597, "learning_rate": 3.647783701865909e-05, "loss": 0.4526833534240723, "step": 415810 }, { "epoch": 2.4717204320250135, "grad_norm": 1.3600081205368042, "learning_rate": 3.6474246990201366e-05, "loss": 0.4762725353240967, "step": 415820 }, { "epoch": 2.4717798741016814, "grad_norm": 1.2911288738250732, "learning_rate": 3.647065731346681e-05, "loss": 0.48751144409179686, "step": 415830 }, { "epoch": 2.47183931617835, "grad_norm": 1.0485714673995972, "learning_rate": 3.646706798847258e-05, "loss": 0.45213022232055666, "step": 415840 }, { "epoch": 2.4718987582550183, "grad_norm": 1.644067406654358, "learning_rate": 3.6463479015235876e-05, "loss": 0.5300577640533447, "step": 415850 }, { "epoch": 2.4719582003316867, "grad_norm": 1.2510751485824585, "learning_rate": 3.645989039377388e-05, "loss": 0.47102947235107423, "step": 415860 }, { "epoch": 2.472017642408355, "grad_norm": 1.2834196090698242, "learning_rate": 3.645630212410373e-05, "loss": 0.5303736209869385, "step": 415870 }, { "epoch": 2.4720770844850235, "grad_norm": 1.2622640132904053, "learning_rate": 3.645271420624258e-05, "loss": 0.487933874130249, "step": 415880 }, { "epoch": 2.472136526561692, "grad_norm": 1.5498169660568237, "learning_rate": 3.644912664020762e-05, "loss": 0.5049882888793945, "step": 415890 }, { "epoch": 2.4721959686383603, "grad_norm": 1.4319041967391968, "learning_rate": 3.6445539426015975e-05, "loss": 0.4853797912597656, "step": 415900 }, { "epoch": 2.4722554107150287, "grad_norm": 1.0667355060577393, "learning_rate": 3.644195256368486e-05, "loss": 0.4205960750579834, "step": 415910 }, { "epoch": 2.472314852791697, "grad_norm": 1.3037971258163452, "learning_rate": 3.64383660532314e-05, "loss": 0.4545904159545898, "step": 415920 }, { "epoch": 2.4723742948683656, "grad_norm": 1.2782210111618042, "learning_rate": 3.643477989467275e-05, "loss": 0.46788482666015624, "step": 415930 }, { "epoch": 2.472433736945034, "grad_norm": 1.2400468587875366, "learning_rate": 3.6431194088026084e-05, "loss": 0.5180144309997559, "step": 415940 }, { "epoch": 2.4724931790217024, "grad_norm": 1.312227487564087, "learning_rate": 3.642760863330854e-05, "loss": 0.448073673248291, "step": 415950 }, { "epoch": 2.472552621098371, "grad_norm": 1.543946385383606, "learning_rate": 3.6424023530537276e-05, "loss": 0.44525957107543945, "step": 415960 }, { "epoch": 2.4726120631750392, "grad_norm": 1.178485631942749, "learning_rate": 3.642043877972941e-05, "loss": 0.4503444194793701, "step": 415970 }, { "epoch": 2.4726715052517076, "grad_norm": 1.1172443628311157, "learning_rate": 3.6416854380902146e-05, "loss": 0.5060823440551758, "step": 415980 }, { "epoch": 2.472730947328376, "grad_norm": 1.0240657329559326, "learning_rate": 3.641327033407259e-05, "loss": 0.47475423812866213, "step": 415990 }, { "epoch": 2.472790389405044, "grad_norm": 1.2641767263412476, "learning_rate": 3.640968663925792e-05, "loss": 0.436140251159668, "step": 416000 }, { "epoch": 2.472849831481713, "grad_norm": 1.2512147426605225, "learning_rate": 3.640610329647524e-05, "loss": 0.4341644287109375, "step": 416010 }, { "epoch": 2.472909273558381, "grad_norm": 1.316100835800171, "learning_rate": 3.640252030574173e-05, "loss": 0.47592916488647463, "step": 416020 }, { "epoch": 2.4729687156350493, "grad_norm": 0.9599211812019348, "learning_rate": 3.6398937667074485e-05, "loss": 0.43886432647705076, "step": 416030 }, { "epoch": 2.4730281577117177, "grad_norm": 1.496556043624878, "learning_rate": 3.639535538049068e-05, "loss": 0.4635947227478027, "step": 416040 }, { "epoch": 2.473087599788386, "grad_norm": 1.0101683139801025, "learning_rate": 3.639177344600744e-05, "loss": 0.41120662689208987, "step": 416050 }, { "epoch": 2.4731470418650545, "grad_norm": 1.6630793809890747, "learning_rate": 3.6388191863641915e-05, "loss": 0.4958819389343262, "step": 416060 }, { "epoch": 2.473206483941723, "grad_norm": 1.7045856714248657, "learning_rate": 3.638461063341121e-05, "loss": 0.5745396614074707, "step": 416070 }, { "epoch": 2.4732659260183913, "grad_norm": 0.953416109085083, "learning_rate": 3.6381029755332485e-05, "loss": 0.46949138641357424, "step": 416080 }, { "epoch": 2.4733253680950598, "grad_norm": 1.168946385383606, "learning_rate": 3.637744922942284e-05, "loss": 0.4300717353820801, "step": 416090 }, { "epoch": 2.473384810171728, "grad_norm": 1.297991394996643, "learning_rate": 3.637386905569939e-05, "loss": 0.46434879302978516, "step": 416100 }, { "epoch": 2.4734442522483966, "grad_norm": 1.3926723003387451, "learning_rate": 3.637028923417933e-05, "loss": 0.48953933715820314, "step": 416110 }, { "epoch": 2.473503694325065, "grad_norm": 1.3962271213531494, "learning_rate": 3.636670976487977e-05, "loss": 0.48064794540405276, "step": 416120 }, { "epoch": 2.4735631364017334, "grad_norm": 0.9373033046722412, "learning_rate": 3.636313064781774e-05, "loss": 0.4865856170654297, "step": 416130 }, { "epoch": 2.473622578478402, "grad_norm": 1.5514271259307861, "learning_rate": 3.6359551883010464e-05, "loss": 0.529080867767334, "step": 416140 }, { "epoch": 2.4736820205550702, "grad_norm": 1.3839497566223145, "learning_rate": 3.6355973470475026e-05, "loss": 0.47114973068237304, "step": 416150 }, { "epoch": 2.4737414626317387, "grad_norm": 1.3783053159713745, "learning_rate": 3.635239541022851e-05, "loss": 0.4521608352661133, "step": 416160 }, { "epoch": 2.473800904708407, "grad_norm": 1.722577452659607, "learning_rate": 3.634881770228813e-05, "loss": 0.5123902320861816, "step": 416170 }, { "epoch": 2.4738603467850755, "grad_norm": 2.5418200492858887, "learning_rate": 3.6345240346670895e-05, "loss": 0.4908797264099121, "step": 416180 }, { "epoch": 2.4739197888617435, "grad_norm": 1.4511027336120605, "learning_rate": 3.634166334339395e-05, "loss": 0.48719310760498047, "step": 416190 }, { "epoch": 2.473979230938412, "grad_norm": 1.4846593141555786, "learning_rate": 3.633808669247443e-05, "loss": 0.5057687759399414, "step": 416200 }, { "epoch": 2.4740386730150803, "grad_norm": 1.1333588361740112, "learning_rate": 3.633451039392943e-05, "loss": 0.4860945701599121, "step": 416210 }, { "epoch": 2.4740981150917487, "grad_norm": 1.1932554244995117, "learning_rate": 3.633093444777607e-05, "loss": 0.4608254909515381, "step": 416220 }, { "epoch": 2.474157557168417, "grad_norm": 1.3690721988677979, "learning_rate": 3.632735885403144e-05, "loss": 0.4965662479400635, "step": 416230 }, { "epoch": 2.4742169992450855, "grad_norm": 1.4641151428222656, "learning_rate": 3.632378361271264e-05, "loss": 0.5296867370605469, "step": 416240 }, { "epoch": 2.474276441321754, "grad_norm": 1.6341514587402344, "learning_rate": 3.632020872383679e-05, "loss": 0.4666457176208496, "step": 416250 }, { "epoch": 2.4743358833984224, "grad_norm": 1.5777344703674316, "learning_rate": 3.631663418742096e-05, "loss": 0.45613775253295896, "step": 416260 }, { "epoch": 2.474395325475091, "grad_norm": 1.5444594621658325, "learning_rate": 3.631306000348228e-05, "loss": 0.48592205047607423, "step": 416270 }, { "epoch": 2.474454767551759, "grad_norm": 1.433890461921692, "learning_rate": 3.630948617203786e-05, "loss": 0.47387018203735354, "step": 416280 }, { "epoch": 2.4745142096284276, "grad_norm": 1.5432336330413818, "learning_rate": 3.6305912693104774e-05, "loss": 0.5392865180969239, "step": 416290 }, { "epoch": 2.474573651705096, "grad_norm": 1.3473827838897705, "learning_rate": 3.630233956670011e-05, "loss": 0.4792133331298828, "step": 416300 }, { "epoch": 2.4746330937817644, "grad_norm": 1.2611747980117798, "learning_rate": 3.6298766792840964e-05, "loss": 0.4528352737426758, "step": 416310 }, { "epoch": 2.474692535858433, "grad_norm": 1.563607096672058, "learning_rate": 3.629519437154444e-05, "loss": 0.46211538314819334, "step": 416320 }, { "epoch": 2.4747519779351013, "grad_norm": 1.2311245203018188, "learning_rate": 3.629162230282759e-05, "loss": 0.49370622634887695, "step": 416330 }, { "epoch": 2.4748114200117697, "grad_norm": 1.4444926977157593, "learning_rate": 3.6288050586707555e-05, "loss": 0.5190738201141357, "step": 416340 }, { "epoch": 2.474870862088438, "grad_norm": 1.2704354524612427, "learning_rate": 3.62844792232014e-05, "loss": 0.5093713760375976, "step": 416350 }, { "epoch": 2.474930304165106, "grad_norm": 1.1781437397003174, "learning_rate": 3.6280908212326205e-05, "loss": 0.5063173770904541, "step": 416360 }, { "epoch": 2.474989746241775, "grad_norm": 0.958143949508667, "learning_rate": 3.627733755409906e-05, "loss": 0.4694622039794922, "step": 416370 }, { "epoch": 2.475049188318443, "grad_norm": 1.502887487411499, "learning_rate": 3.6273767248537025e-05, "loss": 0.5127586364746094, "step": 416380 }, { "epoch": 2.4751086303951113, "grad_norm": 1.198380470275879, "learning_rate": 3.6270197295657185e-05, "loss": 0.411126708984375, "step": 416390 }, { "epoch": 2.4751680724717797, "grad_norm": 1.1949923038482666, "learning_rate": 3.6266627695476645e-05, "loss": 0.4899017333984375, "step": 416400 }, { "epoch": 2.475227514548448, "grad_norm": 1.6593106985092163, "learning_rate": 3.6263058448012463e-05, "loss": 0.42984447479248045, "step": 416410 }, { "epoch": 2.4752869566251166, "grad_norm": 1.311715006828308, "learning_rate": 3.625948955328171e-05, "loss": 0.4782724380493164, "step": 416420 }, { "epoch": 2.475346398701785, "grad_norm": 1.0937930345535278, "learning_rate": 3.625592101130145e-05, "loss": 0.44672360420227053, "step": 416430 }, { "epoch": 2.4754058407784534, "grad_norm": 1.392045497894287, "learning_rate": 3.6252352822088776e-05, "loss": 0.5056771278381348, "step": 416440 }, { "epoch": 2.475465282855122, "grad_norm": 1.3193961381912231, "learning_rate": 3.624878498566073e-05, "loss": 0.4886295318603516, "step": 416450 }, { "epoch": 2.47552472493179, "grad_norm": 1.4466475248336792, "learning_rate": 3.62452175020344e-05, "loss": 0.5355699539184571, "step": 416460 }, { "epoch": 2.4755841670084586, "grad_norm": 1.4978266954421997, "learning_rate": 3.624165037122685e-05, "loss": 0.5062498569488525, "step": 416470 }, { "epoch": 2.475643609085127, "grad_norm": 1.116193413734436, "learning_rate": 3.6238083593255135e-05, "loss": 0.5043905258178711, "step": 416480 }, { "epoch": 2.4757030511617955, "grad_norm": 1.1775909662246704, "learning_rate": 3.623451716813634e-05, "loss": 0.45018649101257324, "step": 416490 }, { "epoch": 2.475762493238464, "grad_norm": 1.1897523403167725, "learning_rate": 3.623095109588749e-05, "loss": 0.4538862228393555, "step": 416500 }, { "epoch": 2.4758219353151323, "grad_norm": 1.3654111623764038, "learning_rate": 3.622738537652568e-05, "loss": 0.4426534652709961, "step": 416510 }, { "epoch": 2.4758813773918007, "grad_norm": 1.3548049926757812, "learning_rate": 3.622382001006791e-05, "loss": 0.4813357353210449, "step": 416520 }, { "epoch": 2.475940819468469, "grad_norm": 1.2537682056427002, "learning_rate": 3.62202549965313e-05, "loss": 0.4656523704528809, "step": 416530 }, { "epoch": 2.4760002615451375, "grad_norm": 1.2499089241027832, "learning_rate": 3.621669033593288e-05, "loss": 0.417203426361084, "step": 416540 }, { "epoch": 2.4760597036218055, "grad_norm": 1.245906114578247, "learning_rate": 3.6213126028289706e-05, "loss": 0.46454410552978515, "step": 416550 }, { "epoch": 2.4761191456984744, "grad_norm": 1.572069764137268, "learning_rate": 3.620956207361883e-05, "loss": 0.4469193458557129, "step": 416560 }, { "epoch": 2.4761785877751423, "grad_norm": 1.0411309003829956, "learning_rate": 3.620599847193728e-05, "loss": 0.5253055572509766, "step": 416570 }, { "epoch": 2.4762380298518107, "grad_norm": 1.3159587383270264, "learning_rate": 3.620243522326212e-05, "loss": 0.47202792167663576, "step": 416580 }, { "epoch": 2.476297471928479, "grad_norm": 1.510930061340332, "learning_rate": 3.619887232761037e-05, "loss": 0.5212198257446289, "step": 416590 }, { "epoch": 2.4763569140051476, "grad_norm": 1.612044095993042, "learning_rate": 3.619530978499912e-05, "loss": 0.468648099899292, "step": 416600 }, { "epoch": 2.476416356081816, "grad_norm": 1.586687684059143, "learning_rate": 3.619174759544541e-05, "loss": 0.46623806953430175, "step": 416610 }, { "epoch": 2.4764757981584844, "grad_norm": 1.3852299451828003, "learning_rate": 3.618818575896622e-05, "loss": 0.5264077186584473, "step": 416620 }, { "epoch": 2.476535240235153, "grad_norm": 1.4552505016326904, "learning_rate": 3.6184624275578644e-05, "loss": 0.5101948738098144, "step": 416630 }, { "epoch": 2.4765946823118212, "grad_norm": 1.5002305507659912, "learning_rate": 3.61810631452997e-05, "loss": 0.47906246185302737, "step": 416640 }, { "epoch": 2.4766541243884896, "grad_norm": 1.1669273376464844, "learning_rate": 3.617750236814641e-05, "loss": 0.4283742904663086, "step": 416650 }, { "epoch": 2.476713566465158, "grad_norm": 1.1442818641662598, "learning_rate": 3.6173941944135844e-05, "loss": 0.4920208930969238, "step": 416660 }, { "epoch": 2.4767730085418265, "grad_norm": 1.525463342666626, "learning_rate": 3.617038187328503e-05, "loss": 0.4627671718597412, "step": 416670 }, { "epoch": 2.476832450618495, "grad_norm": 1.5096012353897095, "learning_rate": 3.616682215561097e-05, "loss": 0.48642377853393554, "step": 416680 }, { "epoch": 2.4768918926951633, "grad_norm": 1.3591614961624146, "learning_rate": 3.616326279113067e-05, "loss": 0.44005374908447265, "step": 416690 }, { "epoch": 2.4769513347718317, "grad_norm": 1.3636053800582886, "learning_rate": 3.615970377986122e-05, "loss": 0.48935623168945314, "step": 416700 }, { "epoch": 2.4770107768485, "grad_norm": 1.5336130857467651, "learning_rate": 3.615614512181961e-05, "loss": 0.522107744216919, "step": 416710 }, { "epoch": 2.4770702189251685, "grad_norm": 1.618849754333496, "learning_rate": 3.6152586817022846e-05, "loss": 0.507457971572876, "step": 416720 }, { "epoch": 2.477129661001837, "grad_norm": 1.480807900428772, "learning_rate": 3.614902886548802e-05, "loss": 0.4231739044189453, "step": 416730 }, { "epoch": 2.477189103078505, "grad_norm": 1.1143436431884766, "learning_rate": 3.614547126723209e-05, "loss": 0.47880353927612307, "step": 416740 }, { "epoch": 2.477248545155174, "grad_norm": 1.4143346548080444, "learning_rate": 3.614191402227206e-05, "loss": 0.49384570121765137, "step": 416750 }, { "epoch": 2.4773079872318418, "grad_norm": 1.203025460243225, "learning_rate": 3.6138357130625e-05, "loss": 0.4796640396118164, "step": 416760 }, { "epoch": 2.47736742930851, "grad_norm": 1.7679184675216675, "learning_rate": 3.6134800592307905e-05, "loss": 0.462208890914917, "step": 416770 }, { "epoch": 2.4774268713851786, "grad_norm": 1.4278273582458496, "learning_rate": 3.613124440733777e-05, "loss": 0.4767141342163086, "step": 416780 }, { "epoch": 2.477486313461847, "grad_norm": 1.4034713506698608, "learning_rate": 3.6127688575731645e-05, "loss": 0.48264322280883787, "step": 416790 }, { "epoch": 2.4775457555385154, "grad_norm": 1.2708035707473755, "learning_rate": 3.6124133097506495e-05, "loss": 0.5003280639648438, "step": 416800 }, { "epoch": 2.477605197615184, "grad_norm": 1.0705195665359497, "learning_rate": 3.612057797267936e-05, "loss": 0.42981977462768556, "step": 416810 }, { "epoch": 2.4776646396918522, "grad_norm": 1.482830286026001, "learning_rate": 3.611702320126721e-05, "loss": 0.511410903930664, "step": 416820 }, { "epoch": 2.4777240817685207, "grad_norm": 1.0802934169769287, "learning_rate": 3.611346878328711e-05, "loss": 0.4344941139221191, "step": 416830 }, { "epoch": 2.477783523845189, "grad_norm": 1.530224084854126, "learning_rate": 3.610991471875601e-05, "loss": 0.5250811576843262, "step": 416840 }, { "epoch": 2.4778429659218575, "grad_norm": 1.22756826877594, "learning_rate": 3.610636100769094e-05, "loss": 0.49344959259033205, "step": 416850 }, { "epoch": 2.477902407998526, "grad_norm": 1.1468381881713867, "learning_rate": 3.610280765010888e-05, "loss": 0.4548661231994629, "step": 416860 }, { "epoch": 2.4779618500751943, "grad_norm": 1.8846871852874756, "learning_rate": 3.609925464602686e-05, "loss": 0.4462394714355469, "step": 416870 }, { "epoch": 2.4780212921518627, "grad_norm": 1.3176027536392212, "learning_rate": 3.6095701995461814e-05, "loss": 0.4700337886810303, "step": 416880 }, { "epoch": 2.478080734228531, "grad_norm": 1.3564177751541138, "learning_rate": 3.609214969843081e-05, "loss": 0.44803643226623535, "step": 416890 }, { "epoch": 2.4781401763051996, "grad_norm": 2.2584798336029053, "learning_rate": 3.608859775495081e-05, "loss": 0.491686487197876, "step": 416900 }, { "epoch": 2.478199618381868, "grad_norm": 1.5525267124176025, "learning_rate": 3.608504616503878e-05, "loss": 0.49834270477294923, "step": 416910 }, { "epoch": 2.4782590604585364, "grad_norm": 1.1750726699829102, "learning_rate": 3.608149492871176e-05, "loss": 0.436436128616333, "step": 416920 }, { "epoch": 2.4783185025352044, "grad_norm": 1.458729863166809, "learning_rate": 3.607794404598671e-05, "loss": 0.48326687812805175, "step": 416930 }, { "epoch": 2.4783779446118728, "grad_norm": 1.4634231328964233, "learning_rate": 3.60743935168806e-05, "loss": 0.4795886993408203, "step": 416940 }, { "epoch": 2.478437386688541, "grad_norm": 1.3002769947052002, "learning_rate": 3.6070843341410424e-05, "loss": 0.49035181999206545, "step": 416950 }, { "epoch": 2.4784968287652096, "grad_norm": 1.3559446334838867, "learning_rate": 3.606729351959319e-05, "loss": 0.48526725769042967, "step": 416960 }, { "epoch": 2.478556270841878, "grad_norm": 1.3923474550247192, "learning_rate": 3.6063744051445866e-05, "loss": 0.4358083724975586, "step": 416970 }, { "epoch": 2.4786157129185464, "grad_norm": 1.5125406980514526, "learning_rate": 3.606019493698543e-05, "loss": 0.47864952087402346, "step": 416980 }, { "epoch": 2.478675154995215, "grad_norm": 1.5322425365447998, "learning_rate": 3.6056646176228846e-05, "loss": 0.45527281761169436, "step": 416990 }, { "epoch": 2.4787345970718833, "grad_norm": 1.1524344682693481, "learning_rate": 3.6053097769193114e-05, "loss": 0.47794113159179685, "step": 417000 }, { "epoch": 2.4787940391485517, "grad_norm": 1.3963996171951294, "learning_rate": 3.604954971589517e-05, "loss": 0.5345767974853516, "step": 417010 }, { "epoch": 2.47885348122522, "grad_norm": 1.4340729713439941, "learning_rate": 3.604600201635203e-05, "loss": 0.45410356521606443, "step": 417020 }, { "epoch": 2.4789129233018885, "grad_norm": 1.0238544940948486, "learning_rate": 3.604245467058066e-05, "loss": 0.44164433479309084, "step": 417030 }, { "epoch": 2.478972365378557, "grad_norm": 1.5502912998199463, "learning_rate": 3.603890767859801e-05, "loss": 0.4933762550354004, "step": 417040 }, { "epoch": 2.4790318074552253, "grad_norm": 1.5887782573699951, "learning_rate": 3.6035361040421046e-05, "loss": 0.4912267684936523, "step": 417050 }, { "epoch": 2.4790912495318937, "grad_norm": 1.089314579963684, "learning_rate": 3.603181475606675e-05, "loss": 0.44153928756713867, "step": 417060 }, { "epoch": 2.479150691608562, "grad_norm": 1.3472806215286255, "learning_rate": 3.602826882555209e-05, "loss": 0.5031497001647949, "step": 417070 }, { "epoch": 2.4792101336852306, "grad_norm": 1.5059841871261597, "learning_rate": 3.6024723248893974e-05, "loss": 0.49564085006713865, "step": 417080 }, { "epoch": 2.479269575761899, "grad_norm": 1.3132344484329224, "learning_rate": 3.6021178026109445e-05, "loss": 0.5004712104797363, "step": 417090 }, { "epoch": 2.479329017838567, "grad_norm": 1.1216720342636108, "learning_rate": 3.601763315721545e-05, "loss": 0.45982513427734373, "step": 417100 }, { "epoch": 2.479388459915236, "grad_norm": 1.4314591884613037, "learning_rate": 3.601408864222886e-05, "loss": 0.5951931476593018, "step": 417110 }, { "epoch": 2.479447901991904, "grad_norm": 1.4311399459838867, "learning_rate": 3.6010544481166726e-05, "loss": 0.5275705337524415, "step": 417120 }, { "epoch": 2.479507344068572, "grad_norm": 1.0732288360595703, "learning_rate": 3.6007000674045966e-05, "loss": 0.45623092651367186, "step": 417130 }, { "epoch": 2.4795667861452406, "grad_norm": 1.3341929912567139, "learning_rate": 3.6003457220883496e-05, "loss": 0.48631906509399414, "step": 417140 }, { "epoch": 2.479626228221909, "grad_norm": 1.446655035018921, "learning_rate": 3.5999914121696346e-05, "loss": 0.48239455223083494, "step": 417150 }, { "epoch": 2.4796856702985774, "grad_norm": 1.3075001239776611, "learning_rate": 3.599637137650143e-05, "loss": 0.5149197578430176, "step": 417160 }, { "epoch": 2.479745112375246, "grad_norm": 1.1208164691925049, "learning_rate": 3.599282898531567e-05, "loss": 0.4823761463165283, "step": 417170 }, { "epoch": 2.4798045544519143, "grad_norm": 1.5362027883529663, "learning_rate": 3.598928694815602e-05, "loss": 0.4951956272125244, "step": 417180 }, { "epoch": 2.4798639965285827, "grad_norm": 1.5198924541473389, "learning_rate": 3.598574526503945e-05, "loss": 0.4514636039733887, "step": 417190 }, { "epoch": 2.479923438605251, "grad_norm": 1.0082141160964966, "learning_rate": 3.598220393598289e-05, "loss": 0.4568662643432617, "step": 417200 }, { "epoch": 2.4799828806819195, "grad_norm": 1.7168700695037842, "learning_rate": 3.5978662961003254e-05, "loss": 0.4816617965698242, "step": 417210 }, { "epoch": 2.480042322758588, "grad_norm": 1.1453365087509155, "learning_rate": 3.597512234011754e-05, "loss": 0.4360018253326416, "step": 417220 }, { "epoch": 2.4801017648352564, "grad_norm": 1.0179702043533325, "learning_rate": 3.5971582073342635e-05, "loss": 0.43955507278442385, "step": 417230 }, { "epoch": 2.4801612069119248, "grad_norm": 1.3561944961547852, "learning_rate": 3.5968042160695445e-05, "loss": 0.4518852710723877, "step": 417240 }, { "epoch": 2.480220648988593, "grad_norm": 1.4803749322891235, "learning_rate": 3.5964502602192995e-05, "loss": 0.43083791732788085, "step": 417250 }, { "epoch": 2.4802800910652616, "grad_norm": 1.3046115636825562, "learning_rate": 3.5960963397852164e-05, "loss": 0.46985397338867185, "step": 417260 }, { "epoch": 2.48033953314193, "grad_norm": 1.4440139532089233, "learning_rate": 3.5957424547689865e-05, "loss": 0.47437620162963867, "step": 417270 }, { "epoch": 2.4803989752185984, "grad_norm": 1.7006168365478516, "learning_rate": 3.595388605172309e-05, "loss": 0.5210313320159912, "step": 417280 }, { "epoch": 2.4804584172952664, "grad_norm": 1.580712080001831, "learning_rate": 3.5950347909968704e-05, "loss": 0.4453757286071777, "step": 417290 }, { "epoch": 2.4805178593719353, "grad_norm": 1.4085856676101685, "learning_rate": 3.594681012244366e-05, "loss": 0.45732269287109373, "step": 417300 }, { "epoch": 2.4805773014486032, "grad_norm": 1.4008417129516602, "learning_rate": 3.594327268916485e-05, "loss": 0.5236529350280762, "step": 417310 }, { "epoch": 2.4806367435252716, "grad_norm": 1.438249945640564, "learning_rate": 3.593973561014924e-05, "loss": 0.5009400844573975, "step": 417320 }, { "epoch": 2.48069618560194, "grad_norm": 1.2072503566741943, "learning_rate": 3.5936198885413736e-05, "loss": 0.47394647598266604, "step": 417330 }, { "epoch": 2.4807556276786085, "grad_norm": 1.1930415630340576, "learning_rate": 3.5932662514975254e-05, "loss": 0.4606220245361328, "step": 417340 }, { "epoch": 2.480815069755277, "grad_norm": 1.3961769342422485, "learning_rate": 3.592912649885071e-05, "loss": 0.4722102165222168, "step": 417350 }, { "epoch": 2.4808745118319453, "grad_norm": 1.3597558736801147, "learning_rate": 3.5925590837057006e-05, "loss": 0.5087604999542237, "step": 417360 }, { "epoch": 2.4809339539086137, "grad_norm": 1.1624701023101807, "learning_rate": 3.592205552961105e-05, "loss": 0.4405508995056152, "step": 417370 }, { "epoch": 2.480993395985282, "grad_norm": 1.5241172313690186, "learning_rate": 3.5918520576529804e-05, "loss": 0.5103432655334472, "step": 417380 }, { "epoch": 2.4810528380619505, "grad_norm": 1.9721794128417969, "learning_rate": 3.591498597783013e-05, "loss": 0.5283164024353028, "step": 417390 }, { "epoch": 2.481112280138619, "grad_norm": 1.2329100370407104, "learning_rate": 3.591145173352897e-05, "loss": 0.4911346435546875, "step": 417400 }, { "epoch": 2.4811717222152874, "grad_norm": 1.1942304372787476, "learning_rate": 3.59079178436432e-05, "loss": 0.48848614692687986, "step": 417410 }, { "epoch": 2.481231164291956, "grad_norm": 1.4075678586959839, "learning_rate": 3.5904384308189744e-05, "loss": 0.43213319778442383, "step": 417420 }, { "epoch": 2.481290606368624, "grad_norm": 1.5063871145248413, "learning_rate": 3.590085112718549e-05, "loss": 0.4843489646911621, "step": 417430 }, { "epoch": 2.4813500484452926, "grad_norm": 1.2248300313949585, "learning_rate": 3.589731830064733e-05, "loss": 0.4582469940185547, "step": 417440 }, { "epoch": 2.481409490521961, "grad_norm": 1.384726881980896, "learning_rate": 3.5893785828592204e-05, "loss": 0.4501943588256836, "step": 417450 }, { "epoch": 2.4814689325986294, "grad_norm": 1.2950719594955444, "learning_rate": 3.589025371103699e-05, "loss": 0.442462158203125, "step": 417460 }, { "epoch": 2.481528374675298, "grad_norm": 1.2349867820739746, "learning_rate": 3.588672194799858e-05, "loss": 0.5142463207244873, "step": 417470 }, { "epoch": 2.481587816751966, "grad_norm": 1.5408494472503662, "learning_rate": 3.588319053949388e-05, "loss": 0.4941108703613281, "step": 417480 }, { "epoch": 2.4816472588286347, "grad_norm": 1.2867658138275146, "learning_rate": 3.587965948553977e-05, "loss": 0.47995891571044924, "step": 417490 }, { "epoch": 2.4817067009053027, "grad_norm": 1.234681248664856, "learning_rate": 3.587612878615313e-05, "loss": 0.4477090835571289, "step": 417500 }, { "epoch": 2.481766142981971, "grad_norm": 1.3006359338760376, "learning_rate": 3.587259844135087e-05, "loss": 0.42757267951965333, "step": 417510 }, { "epoch": 2.4818255850586395, "grad_norm": 1.4501177072525024, "learning_rate": 3.586906845114989e-05, "loss": 0.5057324409484864, "step": 417520 }, { "epoch": 2.481885027135308, "grad_norm": 1.0815749168395996, "learning_rate": 3.586553881556708e-05, "loss": 0.473805570602417, "step": 417530 }, { "epoch": 2.4819444692119763, "grad_norm": 1.4096697568893433, "learning_rate": 3.586200953461926e-05, "loss": 0.5025556564331055, "step": 417540 }, { "epoch": 2.4820039112886447, "grad_norm": 1.6241306066513062, "learning_rate": 3.585848060832338e-05, "loss": 0.522403621673584, "step": 417550 }, { "epoch": 2.482063353365313, "grad_norm": 1.5320783853530884, "learning_rate": 3.5854952036696296e-05, "loss": 0.48641033172607423, "step": 417560 }, { "epoch": 2.4821227954419816, "grad_norm": 1.5710875988006592, "learning_rate": 3.585142381975487e-05, "loss": 0.5345028877258301, "step": 417570 }, { "epoch": 2.48218223751865, "grad_norm": 1.1971875429153442, "learning_rate": 3.584789595751602e-05, "loss": 0.4449488639831543, "step": 417580 }, { "epoch": 2.4822416795953184, "grad_norm": 1.1811374425888062, "learning_rate": 3.5844368449996625e-05, "loss": 0.45437397956848147, "step": 417590 }, { "epoch": 2.482301121671987, "grad_norm": 1.407607913017273, "learning_rate": 3.584084129721349e-05, "loss": 0.48058242797851564, "step": 417600 }, { "epoch": 2.482360563748655, "grad_norm": 1.2488367557525635, "learning_rate": 3.583731449918356e-05, "loss": 0.4567561149597168, "step": 417610 }, { "epoch": 2.4824200058253236, "grad_norm": 1.3764275312423706, "learning_rate": 3.5833788055923686e-05, "loss": 0.49873104095458987, "step": 417620 }, { "epoch": 2.482479447901992, "grad_norm": 1.110129475593567, "learning_rate": 3.583026196745072e-05, "loss": 0.4770336151123047, "step": 417630 }, { "epoch": 2.4825388899786605, "grad_norm": 1.3605462312698364, "learning_rate": 3.5826736233781546e-05, "loss": 0.5036537170410156, "step": 417640 }, { "epoch": 2.482598332055329, "grad_norm": 1.163820743560791, "learning_rate": 3.5823210854933054e-05, "loss": 0.5257250785827636, "step": 417650 }, { "epoch": 2.4826577741319973, "grad_norm": 1.257908821105957, "learning_rate": 3.581968583092205e-05, "loss": 0.4382458686828613, "step": 417660 }, { "epoch": 2.4827172162086653, "grad_norm": 1.135302186012268, "learning_rate": 3.5816161161765415e-05, "loss": 0.5015801429748535, "step": 417670 }, { "epoch": 2.4827766582853337, "grad_norm": 1.2455341815948486, "learning_rate": 3.581263684748003e-05, "loss": 0.4896082878112793, "step": 417680 }, { "epoch": 2.482836100362002, "grad_norm": 0.9945135712623596, "learning_rate": 3.580911288808276e-05, "loss": 0.43168368339538576, "step": 417690 }, { "epoch": 2.4828955424386705, "grad_norm": 1.715199589729309, "learning_rate": 3.5805589283590424e-05, "loss": 0.5098835945129394, "step": 417700 }, { "epoch": 2.482954984515339, "grad_norm": 0.986103892326355, "learning_rate": 3.580206603401994e-05, "loss": 0.47403631210327146, "step": 417710 }, { "epoch": 2.4830144265920073, "grad_norm": 1.1914244890213013, "learning_rate": 3.5798543139388105e-05, "loss": 0.4966000556945801, "step": 417720 }, { "epoch": 2.4830738686686757, "grad_norm": 1.714455246925354, "learning_rate": 3.579502059971177e-05, "loss": 0.48937177658081055, "step": 417730 }, { "epoch": 2.483133310745344, "grad_norm": 1.4014970064163208, "learning_rate": 3.5791498415007817e-05, "loss": 0.5380528450012207, "step": 417740 }, { "epoch": 2.4831927528220126, "grad_norm": 1.3411270380020142, "learning_rate": 3.57879765852931e-05, "loss": 0.4719701290130615, "step": 417750 }, { "epoch": 2.483252194898681, "grad_norm": 1.5120668411254883, "learning_rate": 3.578445511058442e-05, "loss": 0.5215671539306641, "step": 417760 }, { "epoch": 2.4833116369753494, "grad_norm": 1.743788719177246, "learning_rate": 3.57809339908987e-05, "loss": 0.476193904876709, "step": 417770 }, { "epoch": 2.483371079052018, "grad_norm": 1.321162462234497, "learning_rate": 3.577741322625272e-05, "loss": 0.4697396755218506, "step": 417780 }, { "epoch": 2.4834305211286862, "grad_norm": 1.3288586139678955, "learning_rate": 3.577389281666333e-05, "loss": 0.4570791721343994, "step": 417790 }, { "epoch": 2.4834899632053546, "grad_norm": 1.4803917407989502, "learning_rate": 3.577037276214736e-05, "loss": 0.47687621116638185, "step": 417800 }, { "epoch": 2.483549405282023, "grad_norm": 1.431663990020752, "learning_rate": 3.576685306272168e-05, "loss": 0.4777359962463379, "step": 417810 }, { "epoch": 2.4836088473586915, "grad_norm": 1.462288498878479, "learning_rate": 3.5763333718403134e-05, "loss": 0.47263059616088865, "step": 417820 }, { "epoch": 2.48366828943536, "grad_norm": 1.4351439476013184, "learning_rate": 3.5759814729208524e-05, "loss": 0.4561786651611328, "step": 417830 }, { "epoch": 2.483727731512028, "grad_norm": 1.3070926666259766, "learning_rate": 3.575629609515471e-05, "loss": 0.4902315139770508, "step": 417840 }, { "epoch": 2.4837871735886967, "grad_norm": 1.5510817766189575, "learning_rate": 3.57527778162585e-05, "loss": 0.5274378776550293, "step": 417850 }, { "epoch": 2.4838466156653647, "grad_norm": 1.2576344013214111, "learning_rate": 3.5749259892536724e-05, "loss": 0.493989086151123, "step": 417860 }, { "epoch": 2.483906057742033, "grad_norm": 1.2602059841156006, "learning_rate": 3.574574232400624e-05, "loss": 0.4948153495788574, "step": 417870 }, { "epoch": 2.4839654998187015, "grad_norm": 1.1757646799087524, "learning_rate": 3.574222511068387e-05, "loss": 0.48213443756103513, "step": 417880 }, { "epoch": 2.48402494189537, "grad_norm": 1.5074713230133057, "learning_rate": 3.57387082525864e-05, "loss": 0.47864904403686526, "step": 417890 }, { "epoch": 2.4840843839720383, "grad_norm": 1.3088587522506714, "learning_rate": 3.5735191749730713e-05, "loss": 0.5322598934173584, "step": 417900 }, { "epoch": 2.4841438260487068, "grad_norm": 1.354801893234253, "learning_rate": 3.573167560213358e-05, "loss": 0.4499246597290039, "step": 417910 }, { "epoch": 2.484203268125375, "grad_norm": 1.339443325996399, "learning_rate": 3.572815980981185e-05, "loss": 0.49105033874511717, "step": 417920 }, { "epoch": 2.4842627102020436, "grad_norm": 1.4320498704910278, "learning_rate": 3.5724644372782304e-05, "loss": 0.4737514019012451, "step": 417930 }, { "epoch": 2.484322152278712, "grad_norm": 1.3593518733978271, "learning_rate": 3.5721129291061803e-05, "loss": 0.5222227096557617, "step": 417940 }, { "epoch": 2.4843815943553804, "grad_norm": 1.4207135438919067, "learning_rate": 3.5717614564667145e-05, "loss": 0.44245157241821287, "step": 417950 }, { "epoch": 2.484441036432049, "grad_norm": 1.1373341083526611, "learning_rate": 3.571410019361515e-05, "loss": 0.4579660415649414, "step": 417960 }, { "epoch": 2.4845004785087172, "grad_norm": 1.2880017757415771, "learning_rate": 3.5710586177922616e-05, "loss": 0.5304555416107177, "step": 417970 }, { "epoch": 2.4845599205853857, "grad_norm": 1.328979730606079, "learning_rate": 3.570707251760636e-05, "loss": 0.4577168941497803, "step": 417980 }, { "epoch": 2.484619362662054, "grad_norm": 1.302543044090271, "learning_rate": 3.570355921268318e-05, "loss": 0.48497724533081055, "step": 417990 }, { "epoch": 2.4846788047387225, "grad_norm": 1.9246182441711426, "learning_rate": 3.5700046263169904e-05, "loss": 0.48364601135253904, "step": 418000 }, { "epoch": 2.484738246815391, "grad_norm": 1.3599333763122559, "learning_rate": 3.569653366908333e-05, "loss": 0.4600986480712891, "step": 418010 }, { "epoch": 2.4847976888920593, "grad_norm": 1.3629392385482788, "learning_rate": 3.569302143044025e-05, "loss": 0.5096950054168701, "step": 418020 }, { "epoch": 2.4848571309687273, "grad_norm": 1.3438574075698853, "learning_rate": 3.568950954725747e-05, "loss": 0.46998143196105957, "step": 418030 }, { "epoch": 2.484916573045396, "grad_norm": 1.1438260078430176, "learning_rate": 3.56859980195518e-05, "loss": 0.4618938446044922, "step": 418040 }, { "epoch": 2.484976015122064, "grad_norm": 1.119415283203125, "learning_rate": 3.5682486847340025e-05, "loss": 0.49801788330078123, "step": 418050 }, { "epoch": 2.4850354571987325, "grad_norm": 1.3535140752792358, "learning_rate": 3.567897603063892e-05, "loss": 0.5272300243377686, "step": 418060 }, { "epoch": 2.485094899275401, "grad_norm": 1.0303151607513428, "learning_rate": 3.567546556946534e-05, "loss": 0.5021524429321289, "step": 418070 }, { "epoch": 2.4851543413520694, "grad_norm": 1.2153149843215942, "learning_rate": 3.567195546383604e-05, "loss": 0.46945986747741697, "step": 418080 }, { "epoch": 2.4852137834287378, "grad_norm": 1.5536240339279175, "learning_rate": 3.5668445713767806e-05, "loss": 0.46818008422851565, "step": 418090 }, { "epoch": 2.485273225505406, "grad_norm": 1.615195870399475, "learning_rate": 3.566493631927743e-05, "loss": 0.4557816028594971, "step": 418100 }, { "epoch": 2.4853326675820746, "grad_norm": 1.1220875978469849, "learning_rate": 3.566142728038172e-05, "loss": 0.47290863990783694, "step": 418110 }, { "epoch": 2.485392109658743, "grad_norm": 1.3810417652130127, "learning_rate": 3.565791859709743e-05, "loss": 0.4851548194885254, "step": 418120 }, { "epoch": 2.4854515517354114, "grad_norm": 1.2671006917953491, "learning_rate": 3.5654410269441366e-05, "loss": 0.4445180416107178, "step": 418130 }, { "epoch": 2.48551099381208, "grad_norm": 1.2468137741088867, "learning_rate": 3.5650902297430314e-05, "loss": 0.44437379837036134, "step": 418140 }, { "epoch": 2.4855704358887483, "grad_norm": 1.3048561811447144, "learning_rate": 3.5647394681081084e-05, "loss": 0.41644039154052737, "step": 418150 }, { "epoch": 2.4856298779654167, "grad_norm": 0.9894250631332397, "learning_rate": 3.564388742041035e-05, "loss": 0.5100961685180664, "step": 418160 }, { "epoch": 2.485689320042085, "grad_norm": 1.2448161840438843, "learning_rate": 3.5640380515435e-05, "loss": 0.45401725769042967, "step": 418170 }, { "epoch": 2.4857487621187535, "grad_norm": 1.6191550493240356, "learning_rate": 3.563687396617176e-05, "loss": 0.5032124519348145, "step": 418180 }, { "epoch": 2.485808204195422, "grad_norm": 1.6822757720947266, "learning_rate": 3.563336777263739e-05, "loss": 0.49058008193969727, "step": 418190 }, { "epoch": 2.4858676462720903, "grad_norm": 1.1738572120666504, "learning_rate": 3.562986193484874e-05, "loss": 0.4694827556610107, "step": 418200 }, { "epoch": 2.4859270883487588, "grad_norm": 1.4398747682571411, "learning_rate": 3.5626356452822494e-05, "loss": 0.4568807601928711, "step": 418210 }, { "epoch": 2.4859865304254267, "grad_norm": 1.6257097721099854, "learning_rate": 3.562285132657544e-05, "loss": 0.49413909912109377, "step": 418220 }, { "epoch": 2.4860459725020956, "grad_norm": 1.3967065811157227, "learning_rate": 3.5619346556124366e-05, "loss": 0.4813694000244141, "step": 418230 }, { "epoch": 2.4861054145787636, "grad_norm": 1.5846107006072998, "learning_rate": 3.561584214148604e-05, "loss": 0.5884859085083007, "step": 418240 }, { "epoch": 2.486164856655432, "grad_norm": 1.1629714965820312, "learning_rate": 3.561233808267719e-05, "loss": 0.4790835380554199, "step": 418250 }, { "epoch": 2.4862242987321004, "grad_norm": 1.4342864751815796, "learning_rate": 3.560883437971465e-05, "loss": 0.47031145095825194, "step": 418260 }, { "epoch": 2.486283740808769, "grad_norm": 1.5340644121170044, "learning_rate": 3.560533103261512e-05, "loss": 0.46091785430908205, "step": 418270 }, { "epoch": 2.486343182885437, "grad_norm": 1.534698486328125, "learning_rate": 3.560182804139536e-05, "loss": 0.49451398849487305, "step": 418280 }, { "epoch": 2.4864026249621056, "grad_norm": 1.0389199256896973, "learning_rate": 3.559832540607213e-05, "loss": 0.43778510093688966, "step": 418290 }, { "epoch": 2.486462067038774, "grad_norm": 0.9448144435882568, "learning_rate": 3.559482312666221e-05, "loss": 0.5381097793579102, "step": 418300 }, { "epoch": 2.4865215091154425, "grad_norm": 1.3121925592422485, "learning_rate": 3.559132120318235e-05, "loss": 0.46103973388671876, "step": 418310 }, { "epoch": 2.486580951192111, "grad_norm": 1.5889812707901, "learning_rate": 3.5587819635649286e-05, "loss": 0.5012722015380859, "step": 418320 }, { "epoch": 2.4866403932687793, "grad_norm": 1.8625801801681519, "learning_rate": 3.558431842407978e-05, "loss": 0.49688968658447263, "step": 418330 }, { "epoch": 2.4866998353454477, "grad_norm": 1.5240503549575806, "learning_rate": 3.558081756849057e-05, "loss": 0.5159400939941406, "step": 418340 }, { "epoch": 2.486759277422116, "grad_norm": 1.0153231620788574, "learning_rate": 3.557731706889839e-05, "loss": 0.5212217330932617, "step": 418350 }, { "epoch": 2.4868187194987845, "grad_norm": 1.443311095237732, "learning_rate": 3.5573816925320013e-05, "loss": 0.4529090881347656, "step": 418360 }, { "epoch": 2.486878161575453, "grad_norm": 1.0472536087036133, "learning_rate": 3.557031713777219e-05, "loss": 0.40961613655090334, "step": 418370 }, { "epoch": 2.4869376036521214, "grad_norm": 1.3464841842651367, "learning_rate": 3.556681770627165e-05, "loss": 0.4760176181793213, "step": 418380 }, { "epoch": 2.4869970457287898, "grad_norm": 1.694064736366272, "learning_rate": 3.556331863083511e-05, "loss": 0.5222779750823975, "step": 418390 }, { "epoch": 2.487056487805458, "grad_norm": 1.6825727224349976, "learning_rate": 3.555981991147934e-05, "loss": 0.40872812271118164, "step": 418400 }, { "epoch": 2.487115929882126, "grad_norm": 1.157904028892517, "learning_rate": 3.5556321548221056e-05, "loss": 0.41677393913269045, "step": 418410 }, { "epoch": 2.4871753719587946, "grad_norm": 1.3901654481887817, "learning_rate": 3.555282354107698e-05, "loss": 0.47272043228149413, "step": 418420 }, { "epoch": 2.487234814035463, "grad_norm": 1.3156318664550781, "learning_rate": 3.554932589006389e-05, "loss": 0.519739294052124, "step": 418430 }, { "epoch": 2.4872942561121314, "grad_norm": 1.1083171367645264, "learning_rate": 3.55458285951985e-05, "loss": 0.5030243873596192, "step": 418440 }, { "epoch": 2.4873536981888, "grad_norm": 1.4440923929214478, "learning_rate": 3.554233165649754e-05, "loss": 0.4853976249694824, "step": 418450 }, { "epoch": 2.4874131402654682, "grad_norm": 1.0640472173690796, "learning_rate": 3.553883507397772e-05, "loss": 0.49289374351501464, "step": 418460 }, { "epoch": 2.4874725823421366, "grad_norm": 1.3614059686660767, "learning_rate": 3.553533884765578e-05, "loss": 0.4430248737335205, "step": 418470 }, { "epoch": 2.487532024418805, "grad_norm": 1.345468282699585, "learning_rate": 3.5531842977548425e-05, "loss": 0.4923499584197998, "step": 418480 }, { "epoch": 2.4875914664954735, "grad_norm": 1.2271023988723755, "learning_rate": 3.552834746367242e-05, "loss": 0.5011429786682129, "step": 418490 }, { "epoch": 2.487650908572142, "grad_norm": 1.4331274032592773, "learning_rate": 3.5524852306044454e-05, "loss": 0.5105064392089844, "step": 418500 }, { "epoch": 2.4877103506488103, "grad_norm": 1.5201590061187744, "learning_rate": 3.552135750468126e-05, "loss": 0.4822502613067627, "step": 418510 }, { "epoch": 2.4877697927254787, "grad_norm": 1.5462896823883057, "learning_rate": 3.5517863059599555e-05, "loss": 0.45052542686462405, "step": 418520 }, { "epoch": 2.487829234802147, "grad_norm": 1.6391470432281494, "learning_rate": 3.551436897081605e-05, "loss": 0.444162654876709, "step": 418530 }, { "epoch": 2.4878886768788155, "grad_norm": 1.549438714981079, "learning_rate": 3.5510875238347466e-05, "loss": 0.44400959014892577, "step": 418540 }, { "epoch": 2.487948118955484, "grad_norm": 1.23573899269104, "learning_rate": 3.550738186221049e-05, "loss": 0.4829390525817871, "step": 418550 }, { "epoch": 2.4880075610321524, "grad_norm": 1.466444730758667, "learning_rate": 3.5503888842421874e-05, "loss": 0.4854114532470703, "step": 418560 }, { "epoch": 2.488067003108821, "grad_norm": 1.3669449090957642, "learning_rate": 3.550039617899831e-05, "loss": 0.480205774307251, "step": 418570 }, { "epoch": 2.4881264451854888, "grad_norm": 1.2484760284423828, "learning_rate": 3.5496903871956496e-05, "loss": 0.4896484375, "step": 418580 }, { "epoch": 2.4881858872621576, "grad_norm": 1.1315616369247437, "learning_rate": 3.5493411921313154e-05, "loss": 0.47039089202880857, "step": 418590 }, { "epoch": 2.4882453293388256, "grad_norm": 1.5934820175170898, "learning_rate": 3.5489920327084966e-05, "loss": 0.49114294052124025, "step": 418600 }, { "epoch": 2.488304771415494, "grad_norm": 1.1837427616119385, "learning_rate": 3.548642908928865e-05, "loss": 0.4366436958312988, "step": 418610 }, { "epoch": 2.4883642134921624, "grad_norm": 1.455941081047058, "learning_rate": 3.5482938207940906e-05, "loss": 0.47344679832458497, "step": 418620 }, { "epoch": 2.488423655568831, "grad_norm": 1.3304260969161987, "learning_rate": 3.547944768305844e-05, "loss": 0.4389498710632324, "step": 418630 }, { "epoch": 2.4884830976454992, "grad_norm": 1.3845348358154297, "learning_rate": 3.547595751465798e-05, "loss": 0.48623952865600584, "step": 418640 }, { "epoch": 2.4885425397221677, "grad_norm": 1.8097071647644043, "learning_rate": 3.547246770275613e-05, "loss": 0.42229447364807127, "step": 418650 }, { "epoch": 2.488601981798836, "grad_norm": 1.2326867580413818, "learning_rate": 3.546897824736965e-05, "loss": 0.4871177673339844, "step": 418660 }, { "epoch": 2.4886614238755045, "grad_norm": 1.4027315378189087, "learning_rate": 3.546548914851523e-05, "loss": 0.47713618278503417, "step": 418670 }, { "epoch": 2.488720865952173, "grad_norm": 1.1261008977890015, "learning_rate": 3.546200040620954e-05, "loss": 0.4869693756103516, "step": 418680 }, { "epoch": 2.4887803080288413, "grad_norm": 1.2463994026184082, "learning_rate": 3.545851202046929e-05, "loss": 0.44531989097595215, "step": 418690 }, { "epoch": 2.4888397501055097, "grad_norm": 0.9544153809547424, "learning_rate": 3.545502399131118e-05, "loss": 0.44684133529663084, "step": 418700 }, { "epoch": 2.488899192182178, "grad_norm": 1.1588108539581299, "learning_rate": 3.545153631875183e-05, "loss": 0.4486522674560547, "step": 418710 }, { "epoch": 2.4889586342588466, "grad_norm": 2.2730231285095215, "learning_rate": 3.5448049002808e-05, "loss": 0.476821231842041, "step": 418720 }, { "epoch": 2.489018076335515, "grad_norm": 1.3279080390930176, "learning_rate": 3.544456204349632e-05, "loss": 0.4609574317932129, "step": 418730 }, { "epoch": 2.4890775184121834, "grad_norm": 0.9191768169403076, "learning_rate": 3.544107544083349e-05, "loss": 0.479628324508667, "step": 418740 }, { "epoch": 2.489136960488852, "grad_norm": 1.440014123916626, "learning_rate": 3.5437589194836197e-05, "loss": 0.5107236862182617, "step": 418750 }, { "epoch": 2.48919640256552, "grad_norm": 1.3858118057250977, "learning_rate": 3.543410330552115e-05, "loss": 0.5162472724914551, "step": 418760 }, { "epoch": 2.489255844642188, "grad_norm": 1.2991880178451538, "learning_rate": 3.543061777290494e-05, "loss": 0.46034946441650393, "step": 418770 }, { "epoch": 2.489315286718857, "grad_norm": 1.3674426078796387, "learning_rate": 3.5427132597004264e-05, "loss": 0.40568294525146487, "step": 418780 }, { "epoch": 2.489374728795525, "grad_norm": 1.1935174465179443, "learning_rate": 3.5423647777835844e-05, "loss": 0.5028439521789551, "step": 418790 }, { "epoch": 2.4894341708721934, "grad_norm": 1.965356469154358, "learning_rate": 3.542016331541632e-05, "loss": 0.5140158653259277, "step": 418800 }, { "epoch": 2.489493612948862, "grad_norm": 1.1833515167236328, "learning_rate": 3.541667920976237e-05, "loss": 0.45606365203857424, "step": 418810 }, { "epoch": 2.4895530550255303, "grad_norm": 1.490299940109253, "learning_rate": 3.5413195460890645e-05, "loss": 0.5277227401733399, "step": 418820 }, { "epoch": 2.4896124971021987, "grad_norm": 1.2247440814971924, "learning_rate": 3.540971206881782e-05, "loss": 0.43232436180114747, "step": 418830 }, { "epoch": 2.489671939178867, "grad_norm": 1.279701828956604, "learning_rate": 3.540622903356053e-05, "loss": 0.5057851791381835, "step": 418840 }, { "epoch": 2.4897313812555355, "grad_norm": 1.1207399368286133, "learning_rate": 3.540274635513549e-05, "loss": 0.4841048240661621, "step": 418850 }, { "epoch": 2.489790823332204, "grad_norm": 1.6340373754501343, "learning_rate": 3.539926403355933e-05, "loss": 0.5041079521179199, "step": 418860 }, { "epoch": 2.4898502654088723, "grad_norm": 1.0764315128326416, "learning_rate": 3.5395782068848717e-05, "loss": 0.4473728179931641, "step": 418870 }, { "epoch": 2.4899097074855407, "grad_norm": 1.4698996543884277, "learning_rate": 3.53923004610203e-05, "loss": 0.5353751182556152, "step": 418880 }, { "epoch": 2.489969149562209, "grad_norm": 1.1587895154953003, "learning_rate": 3.538881921009073e-05, "loss": 0.507481861114502, "step": 418890 }, { "epoch": 2.4900285916388776, "grad_norm": 1.3535643815994263, "learning_rate": 3.538533831607665e-05, "loss": 0.48096475601196287, "step": 418900 }, { "epoch": 2.490088033715546, "grad_norm": 1.1405495405197144, "learning_rate": 3.538185777899473e-05, "loss": 0.45052518844604494, "step": 418910 }, { "epoch": 2.4901474757922144, "grad_norm": 1.5279110670089722, "learning_rate": 3.5378377598861635e-05, "loss": 0.48755788803100586, "step": 418920 }, { "epoch": 2.490206917868883, "grad_norm": 1.2705711126327515, "learning_rate": 3.537489777569399e-05, "loss": 0.4693319320678711, "step": 418930 }, { "epoch": 2.4902663599455512, "grad_norm": 1.3913766145706177, "learning_rate": 3.537141830950844e-05, "loss": 0.4571803092956543, "step": 418940 }, { "epoch": 2.4903258020222196, "grad_norm": 1.6692748069763184, "learning_rate": 3.5367939200321656e-05, "loss": 0.4971779346466064, "step": 418950 }, { "epoch": 2.4903852440988876, "grad_norm": 1.4622281789779663, "learning_rate": 3.5364460448150245e-05, "loss": 0.4465012550354004, "step": 418960 }, { "epoch": 2.4904446861755565, "grad_norm": 1.77485191822052, "learning_rate": 3.536098205301084e-05, "loss": 0.5039389610290528, "step": 418970 }, { "epoch": 2.4905041282522244, "grad_norm": 1.2437132596969604, "learning_rate": 3.535750401492014e-05, "loss": 0.4854103088378906, "step": 418980 }, { "epoch": 2.490563570328893, "grad_norm": 1.5529841184616089, "learning_rate": 3.5354026333894735e-05, "loss": 0.46985759735107424, "step": 418990 }, { "epoch": 2.4906230124055613, "grad_norm": 1.1051437854766846, "learning_rate": 3.5350549009951276e-05, "loss": 0.41165771484375, "step": 419000 }, { "epoch": 2.4906824544822297, "grad_norm": 1.7014044523239136, "learning_rate": 3.53470720431064e-05, "loss": 0.4727779388427734, "step": 419010 }, { "epoch": 2.490741896558898, "grad_norm": 1.4945852756500244, "learning_rate": 3.534359543337673e-05, "loss": 0.4947681427001953, "step": 419020 }, { "epoch": 2.4908013386355665, "grad_norm": 1.3042587041854858, "learning_rate": 3.534011918077891e-05, "loss": 0.4576393127441406, "step": 419030 }, { "epoch": 2.490860780712235, "grad_norm": 1.3381491899490356, "learning_rate": 3.533664328532953e-05, "loss": 0.46559457778930663, "step": 419040 }, { "epoch": 2.4909202227889033, "grad_norm": 0.8634525537490845, "learning_rate": 3.533316774704527e-05, "loss": 0.42315120697021485, "step": 419050 }, { "epoch": 2.4909796648655718, "grad_norm": 1.215720772743225, "learning_rate": 3.532969256594273e-05, "loss": 0.4630753040313721, "step": 419060 }, { "epoch": 2.49103910694224, "grad_norm": 1.2990909814834595, "learning_rate": 3.5326217742038545e-05, "loss": 0.5353479862213135, "step": 419070 }, { "epoch": 2.4910985490189086, "grad_norm": 1.4113516807556152, "learning_rate": 3.532274327534933e-05, "loss": 0.5066648006439209, "step": 419080 }, { "epoch": 2.491157991095577, "grad_norm": 1.6419367790222168, "learning_rate": 3.531926916589171e-05, "loss": 0.4751280784606934, "step": 419090 }, { "epoch": 2.4912174331722454, "grad_norm": 1.3886748552322388, "learning_rate": 3.531579541368226e-05, "loss": 0.4455700397491455, "step": 419100 }, { "epoch": 2.491276875248914, "grad_norm": 1.4868743419647217, "learning_rate": 3.531232201873768e-05, "loss": 0.4605856895446777, "step": 419110 }, { "epoch": 2.4913363173255823, "grad_norm": 1.2571473121643066, "learning_rate": 3.530884898107454e-05, "loss": 0.4229687213897705, "step": 419120 }, { "epoch": 2.4913957594022507, "grad_norm": 1.3844112157821655, "learning_rate": 3.5305376300709466e-05, "loss": 0.47931718826293945, "step": 419130 }, { "epoch": 2.491455201478919, "grad_norm": 1.0456771850585938, "learning_rate": 3.5301903977659044e-05, "loss": 0.4950760841369629, "step": 419140 }, { "epoch": 2.491514643555587, "grad_norm": 1.3601438999176025, "learning_rate": 3.529843201193991e-05, "loss": 0.441127872467041, "step": 419150 }, { "epoch": 2.4915740856322555, "grad_norm": 1.0708136558532715, "learning_rate": 3.529496040356865e-05, "loss": 0.4489889144897461, "step": 419160 }, { "epoch": 2.491633527708924, "grad_norm": 1.6231210231781006, "learning_rate": 3.5291489152561885e-05, "loss": 0.4979203701019287, "step": 419170 }, { "epoch": 2.4916929697855923, "grad_norm": 1.1878055334091187, "learning_rate": 3.528801825893623e-05, "loss": 0.46376237869262693, "step": 419180 }, { "epoch": 2.4917524118622607, "grad_norm": 1.3112177848815918, "learning_rate": 3.5284547722708297e-05, "loss": 0.5209527969360351, "step": 419190 }, { "epoch": 2.491811853938929, "grad_norm": 1.4055900573730469, "learning_rate": 3.5281077543894635e-05, "loss": 0.4844532489776611, "step": 419200 }, { "epoch": 2.4918712960155975, "grad_norm": 1.570946216583252, "learning_rate": 3.527760772251191e-05, "loss": 0.5073318958282471, "step": 419210 }, { "epoch": 2.491930738092266, "grad_norm": 1.3377455472946167, "learning_rate": 3.5274138258576674e-05, "loss": 0.5010234832763671, "step": 419220 }, { "epoch": 2.4919901801689344, "grad_norm": 1.276781439781189, "learning_rate": 3.527066915210553e-05, "loss": 0.4586534023284912, "step": 419230 }, { "epoch": 2.492049622245603, "grad_norm": 1.296337604522705, "learning_rate": 3.5267200403115096e-05, "loss": 0.4643527030944824, "step": 419240 }, { "epoch": 2.492109064322271, "grad_norm": 1.1030120849609375, "learning_rate": 3.526373201162198e-05, "loss": 0.49442272186279296, "step": 419250 }, { "epoch": 2.4921685063989396, "grad_norm": 1.235920786857605, "learning_rate": 3.5260263977642714e-05, "loss": 0.4826198577880859, "step": 419260 }, { "epoch": 2.492227948475608, "grad_norm": 1.2269679307937622, "learning_rate": 3.525679630119391e-05, "loss": 0.4946319103240967, "step": 419270 }, { "epoch": 2.4922873905522764, "grad_norm": 1.1671898365020752, "learning_rate": 3.525332898229219e-05, "loss": 0.4622048377990723, "step": 419280 }, { "epoch": 2.492346832628945, "grad_norm": 1.356596827507019, "learning_rate": 3.524986202095411e-05, "loss": 0.47662744522094724, "step": 419290 }, { "epoch": 2.4924062747056133, "grad_norm": 1.3086683750152588, "learning_rate": 3.524639541719624e-05, "loss": 0.47056732177734373, "step": 419300 }, { "epoch": 2.4924657167822817, "grad_norm": 1.1284986734390259, "learning_rate": 3.524292917103523e-05, "loss": 0.5156115531921387, "step": 419310 }, { "epoch": 2.4925251588589497, "grad_norm": 1.3434584140777588, "learning_rate": 3.523946328248759e-05, "loss": 0.45000529289245605, "step": 419320 }, { "epoch": 2.4925846009356185, "grad_norm": 1.7009742259979248, "learning_rate": 3.5235997751569906e-05, "loss": 0.5079638481140136, "step": 419330 }, { "epoch": 2.4926440430122865, "grad_norm": 1.0604794025421143, "learning_rate": 3.52325325782988e-05, "loss": 0.45003976821899416, "step": 419340 }, { "epoch": 2.492703485088955, "grad_norm": 1.341781497001648, "learning_rate": 3.522906776269082e-05, "loss": 0.4891615867614746, "step": 419350 }, { "epoch": 2.4927629271656233, "grad_norm": 1.622789740562439, "learning_rate": 3.5225603304762555e-05, "loss": 0.5122621536254883, "step": 419360 }, { "epoch": 2.4928223692422917, "grad_norm": 1.5526546239852905, "learning_rate": 3.522213920453055e-05, "loss": 0.4106442451477051, "step": 419370 }, { "epoch": 2.49288181131896, "grad_norm": 1.2716156244277954, "learning_rate": 3.5218675462011404e-05, "loss": 0.46478900909423826, "step": 419380 }, { "epoch": 2.4929412533956286, "grad_norm": 1.0865964889526367, "learning_rate": 3.521521207722167e-05, "loss": 0.5151617050170898, "step": 419390 }, { "epoch": 2.493000695472297, "grad_norm": 1.4942594766616821, "learning_rate": 3.5211749050177914e-05, "loss": 0.5131931304931641, "step": 419400 }, { "epoch": 2.4930601375489654, "grad_norm": 0.9885582327842712, "learning_rate": 3.520828638089671e-05, "loss": 0.44936351776123046, "step": 419410 }, { "epoch": 2.493119579625634, "grad_norm": 1.5184566974639893, "learning_rate": 3.5204824069394636e-05, "loss": 0.48834905624389646, "step": 419420 }, { "epoch": 2.493179021702302, "grad_norm": 1.5173962116241455, "learning_rate": 3.520136211568823e-05, "loss": 0.48200440406799316, "step": 419430 }, { "epoch": 2.4932384637789706, "grad_norm": 1.6029092073440552, "learning_rate": 3.519790051979408e-05, "loss": 0.461041259765625, "step": 419440 }, { "epoch": 2.493297905855639, "grad_norm": 1.8231356143951416, "learning_rate": 3.519443928172871e-05, "loss": 0.45596680641174314, "step": 419450 }, { "epoch": 2.4933573479323075, "grad_norm": 1.4619485139846802, "learning_rate": 3.519097840150869e-05, "loss": 0.5373219013214111, "step": 419460 }, { "epoch": 2.493416790008976, "grad_norm": 1.4430490732192993, "learning_rate": 3.518751787915059e-05, "loss": 0.4569977283477783, "step": 419470 }, { "epoch": 2.4934762320856443, "grad_norm": 1.1210455894470215, "learning_rate": 3.518405771467097e-05, "loss": 0.45709524154663084, "step": 419480 }, { "epoch": 2.4935356741623127, "grad_norm": 1.1902703046798706, "learning_rate": 3.5180597908086355e-05, "loss": 0.5075389862060546, "step": 419490 }, { "epoch": 2.493595116238981, "grad_norm": 1.2353646755218506, "learning_rate": 3.517713845941332e-05, "loss": 0.49081878662109374, "step": 419500 }, { "epoch": 2.493654558315649, "grad_norm": 1.5528749227523804, "learning_rate": 3.517367936866839e-05, "loss": 0.507164478302002, "step": 419510 }, { "epoch": 2.493714000392318, "grad_norm": 1.4599709510803223, "learning_rate": 3.517022063586812e-05, "loss": 0.4663914680480957, "step": 419520 }, { "epoch": 2.493773442468986, "grad_norm": 1.4556713104248047, "learning_rate": 3.5166762261029045e-05, "loss": 0.5237922668457031, "step": 419530 }, { "epoch": 2.4938328845456543, "grad_norm": 1.2866089344024658, "learning_rate": 3.516330424416775e-05, "loss": 0.4595046043395996, "step": 419540 }, { "epoch": 2.4938923266223227, "grad_norm": 1.3047031164169312, "learning_rate": 3.515984658530076e-05, "loss": 0.44087772369384765, "step": 419550 }, { "epoch": 2.493951768698991, "grad_norm": 1.2839008569717407, "learning_rate": 3.515638928444458e-05, "loss": 0.5462697982788086, "step": 419560 }, { "epoch": 2.4940112107756596, "grad_norm": 1.7588937282562256, "learning_rate": 3.515293234161579e-05, "loss": 0.5125444412231446, "step": 419570 }, { "epoch": 2.494070652852328, "grad_norm": 1.2640432119369507, "learning_rate": 3.514947575683091e-05, "loss": 0.4777870178222656, "step": 419580 }, { "epoch": 2.4941300949289964, "grad_norm": 1.4405641555786133, "learning_rate": 3.514601953010645e-05, "loss": 0.49609174728393557, "step": 419590 }, { "epoch": 2.494189537005665, "grad_norm": 1.4804677963256836, "learning_rate": 3.5142563661458996e-05, "loss": 0.48886723518371583, "step": 419600 }, { "epoch": 2.4942489790823332, "grad_norm": 1.4882307052612305, "learning_rate": 3.5139108150905065e-05, "loss": 0.5099467754364013, "step": 419610 }, { "epoch": 2.4943084211590016, "grad_norm": 1.2977895736694336, "learning_rate": 3.513565299846118e-05, "loss": 0.5119848251342773, "step": 419620 }, { "epoch": 2.49436786323567, "grad_norm": 0.9672143459320068, "learning_rate": 3.513219820414383e-05, "loss": 0.4869713306427002, "step": 419630 }, { "epoch": 2.4944273053123385, "grad_norm": 0.9981365203857422, "learning_rate": 3.5128743767969597e-05, "loss": 0.4712660312652588, "step": 419640 }, { "epoch": 2.494486747389007, "grad_norm": 1.0362352132797241, "learning_rate": 3.512528968995499e-05, "loss": 0.4813056945800781, "step": 419650 }, { "epoch": 2.4945461894656753, "grad_norm": 1.3466062545776367, "learning_rate": 3.512183597011649e-05, "loss": 0.5080507755279541, "step": 419660 }, { "epoch": 2.4946056315423437, "grad_norm": 1.807064175605774, "learning_rate": 3.511838260847069e-05, "loss": 0.4894279479980469, "step": 419670 }, { "epoch": 2.494665073619012, "grad_norm": 1.0457156896591187, "learning_rate": 3.51149296050341e-05, "loss": 0.4663177490234375, "step": 419680 }, { "epoch": 2.4947245156956805, "grad_norm": 1.259476661682129, "learning_rate": 3.511147695982316e-05, "loss": 0.49048962593078616, "step": 419690 }, { "epoch": 2.4947839577723485, "grad_norm": 1.1560701131820679, "learning_rate": 3.510802467285448e-05, "loss": 0.5412340641021729, "step": 419700 }, { "epoch": 2.4948433998490174, "grad_norm": 1.1169650554656982, "learning_rate": 3.5104572744144525e-05, "loss": 0.49965572357177734, "step": 419710 }, { "epoch": 2.4949028419256853, "grad_norm": 1.2148357629776, "learning_rate": 3.5101121173709814e-05, "loss": 0.4902804851531982, "step": 419720 }, { "epoch": 2.4949622840023538, "grad_norm": 1.5047662258148193, "learning_rate": 3.509766996156685e-05, "loss": 0.47579612731933596, "step": 419730 }, { "epoch": 2.495021726079022, "grad_norm": 1.3967289924621582, "learning_rate": 3.509421910773218e-05, "loss": 0.4643536567687988, "step": 419740 }, { "epoch": 2.4950811681556906, "grad_norm": 1.0873970985412598, "learning_rate": 3.5090768612222294e-05, "loss": 0.4981743812561035, "step": 419750 }, { "epoch": 2.495140610232359, "grad_norm": 1.3471739292144775, "learning_rate": 3.5087318475053646e-05, "loss": 0.45042972564697265, "step": 419760 }, { "epoch": 2.4952000523090274, "grad_norm": 1.5303922891616821, "learning_rate": 3.5083868696242804e-05, "loss": 0.4676382541656494, "step": 419770 }, { "epoch": 2.495259494385696, "grad_norm": 0.9738335609436035, "learning_rate": 3.5080419275806256e-05, "loss": 0.4496640205383301, "step": 419780 }, { "epoch": 2.4953189364623642, "grad_norm": 1.2860572338104248, "learning_rate": 3.507697021376048e-05, "loss": 0.5152703762054444, "step": 419790 }, { "epoch": 2.4953783785390327, "grad_norm": 1.4513154029846191, "learning_rate": 3.507352151012204e-05, "loss": 0.44530496597290037, "step": 419800 }, { "epoch": 2.495437820615701, "grad_norm": 1.127590537071228, "learning_rate": 3.5070073164907355e-05, "loss": 0.45015482902526854, "step": 419810 }, { "epoch": 2.4954972626923695, "grad_norm": 1.1927870512008667, "learning_rate": 3.506662517813294e-05, "loss": 0.48090190887451173, "step": 419820 }, { "epoch": 2.495556704769038, "grad_norm": 1.2176978588104248, "learning_rate": 3.5063177549815324e-05, "loss": 0.4535695552825928, "step": 419830 }, { "epoch": 2.4956161468457063, "grad_norm": 1.2250076532363892, "learning_rate": 3.5059730279970974e-05, "loss": 0.4383707523345947, "step": 419840 }, { "epoch": 2.4956755889223747, "grad_norm": 1.8244869709014893, "learning_rate": 3.5056283368616384e-05, "loss": 0.5096628189086914, "step": 419850 }, { "epoch": 2.495735030999043, "grad_norm": 1.334238886833191, "learning_rate": 3.505283681576804e-05, "loss": 0.5019532203674316, "step": 419860 }, { "epoch": 2.4957944730757116, "grad_norm": 1.445503830909729, "learning_rate": 3.5049390621442435e-05, "loss": 0.4852851390838623, "step": 419870 }, { "epoch": 2.49585391515238, "grad_norm": 1.3588230609893799, "learning_rate": 3.504594478565605e-05, "loss": 0.5002202987670898, "step": 419880 }, { "epoch": 2.495913357229048, "grad_norm": 1.2098524570465088, "learning_rate": 3.504249930842534e-05, "loss": 0.49262571334838867, "step": 419890 }, { "epoch": 2.4959727993057164, "grad_norm": 1.3797725439071655, "learning_rate": 3.503905418976685e-05, "loss": 0.5292265892028809, "step": 419900 }, { "epoch": 2.4960322413823848, "grad_norm": 1.3188426494598389, "learning_rate": 3.503560942969703e-05, "loss": 0.5325429916381836, "step": 419910 }, { "epoch": 2.496091683459053, "grad_norm": 1.1312209367752075, "learning_rate": 3.503216502823235e-05, "loss": 0.4858139991760254, "step": 419920 }, { "epoch": 2.4961511255357216, "grad_norm": 1.3127106428146362, "learning_rate": 3.502872098538929e-05, "loss": 0.4842785358428955, "step": 419930 }, { "epoch": 2.49621056761239, "grad_norm": 1.138658046722412, "learning_rate": 3.5025277301184325e-05, "loss": 0.5192859649658204, "step": 419940 }, { "epoch": 2.4962700096890584, "grad_norm": 0.9396832585334778, "learning_rate": 3.502183397563392e-05, "loss": 0.4710831642150879, "step": 419950 }, { "epoch": 2.496329451765727, "grad_norm": 1.4173275232315063, "learning_rate": 3.501839100875457e-05, "loss": 0.48759946823120115, "step": 419960 }, { "epoch": 2.4963888938423953, "grad_norm": 1.118130087852478, "learning_rate": 3.5014948400562735e-05, "loss": 0.43793559074401855, "step": 419970 }, { "epoch": 2.4964483359190637, "grad_norm": 1.44499933719635, "learning_rate": 3.5011506151074884e-05, "loss": 0.48061676025390626, "step": 419980 }, { "epoch": 2.496507777995732, "grad_norm": 1.5659617185592651, "learning_rate": 3.500806426030749e-05, "loss": 0.49178781509399416, "step": 419990 }, { "epoch": 2.4965672200724005, "grad_norm": 1.023553490638733, "learning_rate": 3.500462272827699e-05, "loss": 0.4795074462890625, "step": 420000 }, { "epoch": 2.496626662149069, "grad_norm": 1.4338860511779785, "learning_rate": 3.500118155499989e-05, "loss": 0.4946559429168701, "step": 420010 }, { "epoch": 2.4966861042257373, "grad_norm": 1.4316378831863403, "learning_rate": 3.499774074049258e-05, "loss": 0.5057614803314209, "step": 420020 }, { "epoch": 2.4967455463024057, "grad_norm": 1.2122725248336792, "learning_rate": 3.4994300284771594e-05, "loss": 0.4716395378112793, "step": 420030 }, { "epoch": 2.496804988379074, "grad_norm": 1.3712629079818726, "learning_rate": 3.499086018785338e-05, "loss": 0.5078808784484863, "step": 420040 }, { "epoch": 2.4968644304557426, "grad_norm": 1.7389271259307861, "learning_rate": 3.4987420449754374e-05, "loss": 0.5019309043884277, "step": 420050 }, { "epoch": 2.4969238725324105, "grad_norm": 1.6524335145950317, "learning_rate": 3.498398107049102e-05, "loss": 0.488235330581665, "step": 420060 }, { "epoch": 2.4969833146090794, "grad_norm": 1.654145359992981, "learning_rate": 3.498054205007979e-05, "loss": 0.5081615924835206, "step": 420070 }, { "epoch": 2.4970427566857474, "grad_norm": 1.3675464391708374, "learning_rate": 3.4977103388537126e-05, "loss": 0.47649550437927246, "step": 420080 }, { "epoch": 2.497102198762416, "grad_norm": 1.1216826438903809, "learning_rate": 3.497366508587948e-05, "loss": 0.47411413192749025, "step": 420090 }, { "epoch": 2.497161640839084, "grad_norm": 1.2538641691207886, "learning_rate": 3.497022714212331e-05, "loss": 0.5144432067871094, "step": 420100 }, { "epoch": 2.4972210829157526, "grad_norm": 1.4089033603668213, "learning_rate": 3.496678955728505e-05, "loss": 0.46187400817871094, "step": 420110 }, { "epoch": 2.497280524992421, "grad_norm": 1.0283411741256714, "learning_rate": 3.496335233138116e-05, "loss": 0.444484806060791, "step": 420120 }, { "epoch": 2.4973399670690895, "grad_norm": 1.395401120185852, "learning_rate": 3.4959915464428055e-05, "loss": 0.4671199798583984, "step": 420130 }, { "epoch": 2.497399409145758, "grad_norm": 1.671396017074585, "learning_rate": 3.49564789564422e-05, "loss": 0.48270087242126464, "step": 420140 }, { "epoch": 2.4974588512224263, "grad_norm": 1.3456953763961792, "learning_rate": 3.4953042807439995e-05, "loss": 0.45334177017211913, "step": 420150 }, { "epoch": 2.4975182932990947, "grad_norm": 1.5693087577819824, "learning_rate": 3.494960701743794e-05, "loss": 0.4700198173522949, "step": 420160 }, { "epoch": 2.497577735375763, "grad_norm": 1.62204909324646, "learning_rate": 3.494617158645244e-05, "loss": 0.4628429889678955, "step": 420170 }, { "epoch": 2.4976371774524315, "grad_norm": 1.3683966398239136, "learning_rate": 3.494273651449992e-05, "loss": 0.47119979858398436, "step": 420180 }, { "epoch": 2.4976966195291, "grad_norm": 1.2215598821640015, "learning_rate": 3.4939301801596815e-05, "loss": 0.465625524520874, "step": 420190 }, { "epoch": 2.4977560616057684, "grad_norm": 1.4421887397766113, "learning_rate": 3.493586744775956e-05, "loss": 0.4942336082458496, "step": 420200 }, { "epoch": 2.4978155036824368, "grad_norm": 1.4824912548065186, "learning_rate": 3.493243345300459e-05, "loss": 0.46482172012329104, "step": 420210 }, { "epoch": 2.497874945759105, "grad_norm": 1.2963308095932007, "learning_rate": 3.4928999817348306e-05, "loss": 0.4908163070678711, "step": 420220 }, { "epoch": 2.4979343878357736, "grad_norm": 1.5908795595169067, "learning_rate": 3.4925566540807196e-05, "loss": 0.5024425506591796, "step": 420230 }, { "epoch": 2.497993829912442, "grad_norm": 1.3496733903884888, "learning_rate": 3.4922133623397614e-05, "loss": 0.5028090953826905, "step": 420240 }, { "epoch": 2.49805327198911, "grad_norm": 1.4241701364517212, "learning_rate": 3.4918701065136e-05, "loss": 0.47797231674194335, "step": 420250 }, { "epoch": 2.498112714065779, "grad_norm": 1.0664435625076294, "learning_rate": 3.4915268866038795e-05, "loss": 0.49691023826599123, "step": 420260 }, { "epoch": 2.498172156142447, "grad_norm": 1.4718552827835083, "learning_rate": 3.4911837026122396e-05, "loss": 0.449339771270752, "step": 420270 }, { "epoch": 2.4982315982191152, "grad_norm": 1.1123539209365845, "learning_rate": 3.490840554540322e-05, "loss": 0.4522256851196289, "step": 420280 }, { "epoch": 2.4982910402957836, "grad_norm": 1.3185280561447144, "learning_rate": 3.490497442389774e-05, "loss": 0.48457975387573243, "step": 420290 }, { "epoch": 2.498350482372452, "grad_norm": 1.7805622816085815, "learning_rate": 3.4901543661622296e-05, "loss": 0.44371747970581055, "step": 420300 }, { "epoch": 2.4984099244491205, "grad_norm": 1.3467378616333008, "learning_rate": 3.48981132585933e-05, "loss": 0.5329172134399414, "step": 420310 }, { "epoch": 2.498469366525789, "grad_norm": 1.1774404048919678, "learning_rate": 3.48946832148272e-05, "loss": 0.5080639839172363, "step": 420320 }, { "epoch": 2.4985288086024573, "grad_norm": 1.2455259561538696, "learning_rate": 3.489125353034041e-05, "loss": 0.4641718864440918, "step": 420330 }, { "epoch": 2.4985882506791257, "grad_norm": 1.7713543176651, "learning_rate": 3.48878242051493e-05, "loss": 0.5594041824340821, "step": 420340 }, { "epoch": 2.498647692755794, "grad_norm": 1.4971868991851807, "learning_rate": 3.48843952392703e-05, "loss": 0.4999566555023193, "step": 420350 }, { "epoch": 2.4987071348324625, "grad_norm": 1.3296539783477783, "learning_rate": 3.48809666327198e-05, "loss": 0.48061509132385255, "step": 420360 }, { "epoch": 2.498766576909131, "grad_norm": 1.3223366737365723, "learning_rate": 3.4877538385514215e-05, "loss": 0.49353847503662107, "step": 420370 }, { "epoch": 2.4988260189857994, "grad_norm": 1.3602644205093384, "learning_rate": 3.487411049766991e-05, "loss": 0.4475238800048828, "step": 420380 }, { "epoch": 2.498885461062468, "grad_norm": 1.8700131177902222, "learning_rate": 3.487068296920333e-05, "loss": 0.5444931983947754, "step": 420390 }, { "epoch": 2.498944903139136, "grad_norm": 1.2828620672225952, "learning_rate": 3.486725580013085e-05, "loss": 0.5077492713928222, "step": 420400 }, { "epoch": 2.4990043452158046, "grad_norm": 1.814785122871399, "learning_rate": 3.486382899046886e-05, "loss": 0.4979099273681641, "step": 420410 }, { "epoch": 2.499063787292473, "grad_norm": 1.1680138111114502, "learning_rate": 3.486040254023377e-05, "loss": 0.474698543548584, "step": 420420 }, { "epoch": 2.4991232293691414, "grad_norm": 1.5205788612365723, "learning_rate": 3.4856976449441946e-05, "loss": 0.44349517822265627, "step": 420430 }, { "epoch": 2.4991826714458094, "grad_norm": 1.1516789197921753, "learning_rate": 3.4853550718109773e-05, "loss": 0.49780750274658203, "step": 420440 }, { "epoch": 2.4992421135224783, "grad_norm": 1.2970826625823975, "learning_rate": 3.485012534625368e-05, "loss": 0.4512011051177979, "step": 420450 }, { "epoch": 2.4993015555991462, "grad_norm": 1.4265213012695312, "learning_rate": 3.484670033389002e-05, "loss": 0.4773214340209961, "step": 420460 }, { "epoch": 2.4993609976758147, "grad_norm": 1.1723825931549072, "learning_rate": 3.4843275681035195e-05, "loss": 0.4712832927703857, "step": 420470 }, { "epoch": 2.499420439752483, "grad_norm": 1.7278167009353638, "learning_rate": 3.483985138770557e-05, "loss": 0.49117450714111327, "step": 420480 }, { "epoch": 2.4994798818291515, "grad_norm": 1.3940385580062866, "learning_rate": 3.4836427453917534e-05, "loss": 0.48262653350830076, "step": 420490 }, { "epoch": 2.49953932390582, "grad_norm": 1.4038313627243042, "learning_rate": 3.483300387968746e-05, "loss": 0.4624584674835205, "step": 420500 }, { "epoch": 2.4995987659824883, "grad_norm": 1.176074743270874, "learning_rate": 3.4829580665031725e-05, "loss": 0.5159547328948975, "step": 420510 }, { "epoch": 2.4996582080591567, "grad_norm": 1.5387027263641357, "learning_rate": 3.482615780996672e-05, "loss": 0.5063264846801758, "step": 420520 }, { "epoch": 2.499717650135825, "grad_norm": 1.8080955743789673, "learning_rate": 3.482273531450881e-05, "loss": 0.43212547302246096, "step": 420530 }, { "epoch": 2.4997770922124936, "grad_norm": 1.3345531225204468, "learning_rate": 3.481931317867437e-05, "loss": 0.5020406723022461, "step": 420540 }, { "epoch": 2.499836534289162, "grad_norm": 1.7447822093963623, "learning_rate": 3.481589140247977e-05, "loss": 0.453082275390625, "step": 420550 }, { "epoch": 2.4998959763658304, "grad_norm": 1.4097046852111816, "learning_rate": 3.481246998594138e-05, "loss": 0.5159563541412353, "step": 420560 }, { "epoch": 2.499955418442499, "grad_norm": 1.7722374200820923, "learning_rate": 3.480904892907554e-05, "loss": 0.47216334342956545, "step": 420570 }, { "epoch": 2.500014860519167, "grad_norm": 1.4844472408294678, "learning_rate": 3.480562823189862e-05, "loss": 0.47518119812011717, "step": 420580 }, { "epoch": 2.5000743025958356, "grad_norm": 1.4458423852920532, "learning_rate": 3.480220789442704e-05, "loss": 0.44998598098754883, "step": 420590 }, { "epoch": 2.500133744672504, "grad_norm": 1.3439756631851196, "learning_rate": 3.479878791667711e-05, "loss": 0.48540468215942384, "step": 420600 }, { "epoch": 2.500193186749172, "grad_norm": 1.4521548748016357, "learning_rate": 3.47953682986652e-05, "loss": 0.5126850128173828, "step": 420610 }, { "epoch": 2.500252628825841, "grad_norm": 1.481529951095581, "learning_rate": 3.479194904040768e-05, "loss": 0.45821781158447267, "step": 420620 }, { "epoch": 2.500312070902509, "grad_norm": 1.1597347259521484, "learning_rate": 3.4788530141920895e-05, "loss": 0.4813797950744629, "step": 420630 }, { "epoch": 2.5003715129791777, "grad_norm": 1.1275848150253296, "learning_rate": 3.478511160322118e-05, "loss": 0.4632889270782471, "step": 420640 }, { "epoch": 2.5004309550558457, "grad_norm": 1.0857079029083252, "learning_rate": 3.478169342432492e-05, "loss": 0.4890793800354004, "step": 420650 }, { "epoch": 2.500490397132514, "grad_norm": 1.6871535778045654, "learning_rate": 3.477827560524848e-05, "loss": 0.49814376831054685, "step": 420660 }, { "epoch": 2.5005498392091825, "grad_norm": 1.0892682075500488, "learning_rate": 3.477485814600817e-05, "loss": 0.46401634216308596, "step": 420670 }, { "epoch": 2.500609281285851, "grad_norm": 1.3474688529968262, "learning_rate": 3.477144104662037e-05, "loss": 0.4938348770141602, "step": 420680 }, { "epoch": 2.5006687233625193, "grad_norm": 1.1578314304351807, "learning_rate": 3.4768024307101386e-05, "loss": 0.4905215263366699, "step": 420690 }, { "epoch": 2.5007281654391877, "grad_norm": 1.6515181064605713, "learning_rate": 3.4764607927467604e-05, "loss": 0.48636531829833984, "step": 420700 }, { "epoch": 2.500787607515856, "grad_norm": 1.3338541984558105, "learning_rate": 3.4761191907735323e-05, "loss": 0.48982925415039064, "step": 420710 }, { "epoch": 2.5008470495925246, "grad_norm": 1.2609367370605469, "learning_rate": 3.475777624792095e-05, "loss": 0.47034401893615724, "step": 420720 }, { "epoch": 2.500906491669193, "grad_norm": 1.5163965225219727, "learning_rate": 3.475436094804079e-05, "loss": 0.4871691703796387, "step": 420730 }, { "epoch": 2.5009659337458614, "grad_norm": 1.4476810693740845, "learning_rate": 3.475094600811114e-05, "loss": 0.4924659252166748, "step": 420740 }, { "epoch": 2.50102537582253, "grad_norm": 1.303215742111206, "learning_rate": 3.4747531428148386e-05, "loss": 0.4635773658752441, "step": 420750 }, { "epoch": 2.5010848178991982, "grad_norm": 1.198682427406311, "learning_rate": 3.4744117208168855e-05, "loss": 0.47205066680908203, "step": 420760 }, { "epoch": 2.5011442599758666, "grad_norm": 1.4662951231002808, "learning_rate": 3.474070334818885e-05, "loss": 0.4905573844909668, "step": 420770 }, { "epoch": 2.501203702052535, "grad_norm": 1.2891920804977417, "learning_rate": 3.473728984822476e-05, "loss": 0.4929699420928955, "step": 420780 }, { "epoch": 2.5012631441292035, "grad_norm": 1.1439825296401978, "learning_rate": 3.473387670829288e-05, "loss": 0.45446004867553713, "step": 420790 }, { "epoch": 2.5013225862058714, "grad_norm": 1.4763586521148682, "learning_rate": 3.4730463928409504e-05, "loss": 0.5101148128509522, "step": 420800 }, { "epoch": 2.5013820282825403, "grad_norm": 1.6347110271453857, "learning_rate": 3.4727051508591014e-05, "loss": 0.48106632232666013, "step": 420810 }, { "epoch": 2.5014414703592083, "grad_norm": 1.2407371997833252, "learning_rate": 3.472363944885371e-05, "loss": 0.4200741291046143, "step": 420820 }, { "epoch": 2.501500912435877, "grad_norm": 1.8252413272857666, "learning_rate": 3.472022774921391e-05, "loss": 0.4656697750091553, "step": 420830 }, { "epoch": 2.501560354512545, "grad_norm": 1.2443994283676147, "learning_rate": 3.471681640968794e-05, "loss": 0.43982553482055664, "step": 420840 }, { "epoch": 2.5016197965892135, "grad_norm": 1.4286079406738281, "learning_rate": 3.471340543029212e-05, "loss": 0.48612098693847655, "step": 420850 }, { "epoch": 2.501679238665882, "grad_norm": 1.1255261898040771, "learning_rate": 3.470999481104277e-05, "loss": 0.4461491584777832, "step": 420860 }, { "epoch": 2.5017386807425503, "grad_norm": 1.6078623533248901, "learning_rate": 3.470658455195616e-05, "loss": 0.47571582794189454, "step": 420870 }, { "epoch": 2.5017981228192188, "grad_norm": 1.6609585285186768, "learning_rate": 3.470317465304867e-05, "loss": 0.46973404884338377, "step": 420880 }, { "epoch": 2.501857564895887, "grad_norm": 1.0530058145523071, "learning_rate": 3.46997651143366e-05, "loss": 0.515619945526123, "step": 420890 }, { "epoch": 2.5019170069725556, "grad_norm": 1.3502304553985596, "learning_rate": 3.469635593583623e-05, "loss": 0.5099713325500488, "step": 420900 }, { "epoch": 2.501976449049224, "grad_norm": 1.3089627027511597, "learning_rate": 3.46929471175639e-05, "loss": 0.4868408203125, "step": 420910 }, { "epoch": 2.5020358911258924, "grad_norm": 1.4952670335769653, "learning_rate": 3.468953865953589e-05, "loss": 0.49048633575439454, "step": 420920 }, { "epoch": 2.502095333202561, "grad_norm": 0.9979127049446106, "learning_rate": 3.468613056176849e-05, "loss": 0.4447288513183594, "step": 420930 }, { "epoch": 2.5021547752792292, "grad_norm": 1.300805687904358, "learning_rate": 3.468272282427806e-05, "loss": 0.4662130355834961, "step": 420940 }, { "epoch": 2.5022142173558977, "grad_norm": 0.9731193780899048, "learning_rate": 3.467931544708085e-05, "loss": 0.4415430068969727, "step": 420950 }, { "epoch": 2.502273659432566, "grad_norm": 1.5099751949310303, "learning_rate": 3.46759084301932e-05, "loss": 0.48032679557800295, "step": 420960 }, { "epoch": 2.5023331015092345, "grad_norm": 1.5499120950698853, "learning_rate": 3.467250177363138e-05, "loss": 0.48459720611572266, "step": 420970 }, { "epoch": 2.502392543585903, "grad_norm": 1.2786704301834106, "learning_rate": 3.466909547741169e-05, "loss": 0.4963826656341553, "step": 420980 }, { "epoch": 2.502451985662571, "grad_norm": 1.503482460975647, "learning_rate": 3.466568954155044e-05, "loss": 0.45188040733337403, "step": 420990 }, { "epoch": 2.5025114277392397, "grad_norm": 1.056759238243103, "learning_rate": 3.4662283966063894e-05, "loss": 0.45722002983093263, "step": 421000 }, { "epoch": 2.5025708698159077, "grad_norm": 1.2772862911224365, "learning_rate": 3.4658878750968373e-05, "loss": 0.4713719367980957, "step": 421010 }, { "epoch": 2.502630311892576, "grad_norm": 1.3577779531478882, "learning_rate": 3.465547389628014e-05, "loss": 0.4285989761352539, "step": 421020 }, { "epoch": 2.5026897539692445, "grad_norm": 1.5081526041030884, "learning_rate": 3.465206940201552e-05, "loss": 0.46312880516052246, "step": 421030 }, { "epoch": 2.502749196045913, "grad_norm": 1.721341609954834, "learning_rate": 3.4648665268190774e-05, "loss": 0.4713785648345947, "step": 421040 }, { "epoch": 2.5028086381225814, "grad_norm": 1.2572259902954102, "learning_rate": 3.464526149482218e-05, "loss": 0.4961813449859619, "step": 421050 }, { "epoch": 2.50286808019925, "grad_norm": 1.7668792009353638, "learning_rate": 3.4641858081926026e-05, "loss": 0.4703801155090332, "step": 421060 }, { "epoch": 2.502927522275918, "grad_norm": 1.520647644996643, "learning_rate": 3.463845502951858e-05, "loss": 0.4785130500793457, "step": 421070 }, { "epoch": 2.5029869643525866, "grad_norm": 1.571812629699707, "learning_rate": 3.463505233761616e-05, "loss": 0.5154932498931885, "step": 421080 }, { "epoch": 2.503046406429255, "grad_norm": 1.1868386268615723, "learning_rate": 3.4631650006235015e-05, "loss": 0.44882049560546877, "step": 421090 }, { "epoch": 2.5031058485059234, "grad_norm": 1.287769079208374, "learning_rate": 3.462824803539143e-05, "loss": 0.4523739814758301, "step": 421100 }, { "epoch": 2.503165290582592, "grad_norm": 1.5961936712265015, "learning_rate": 3.4624846425101665e-05, "loss": 0.44552087783813477, "step": 421110 }, { "epoch": 2.5032247326592603, "grad_norm": 1.2614694833755493, "learning_rate": 3.462144517538202e-05, "loss": 0.4839455604553223, "step": 421120 }, { "epoch": 2.5032841747359287, "grad_norm": 1.644957184791565, "learning_rate": 3.4618044286248706e-05, "loss": 0.5300309181213378, "step": 421130 }, { "epoch": 2.503343616812597, "grad_norm": 1.5066356658935547, "learning_rate": 3.461464375771806e-05, "loss": 0.5279449939727783, "step": 421140 }, { "epoch": 2.5034030588892655, "grad_norm": 1.5593560934066772, "learning_rate": 3.461124358980634e-05, "loss": 0.48252267837524415, "step": 421150 }, { "epoch": 2.5034625009659335, "grad_norm": 1.3028522729873657, "learning_rate": 3.460784378252977e-05, "loss": 0.5504061698913574, "step": 421160 }, { "epoch": 2.5035219430426023, "grad_norm": 1.63302481174469, "learning_rate": 3.460444433590464e-05, "loss": 0.4861182689666748, "step": 421170 }, { "epoch": 2.5035813851192703, "grad_norm": 1.1584006547927856, "learning_rate": 3.4601045249947225e-05, "loss": 0.5452638626098633, "step": 421180 }, { "epoch": 2.503640827195939, "grad_norm": 1.2818851470947266, "learning_rate": 3.459764652467376e-05, "loss": 0.4956676006317139, "step": 421190 }, { "epoch": 2.503700269272607, "grad_norm": 0.9418551325798035, "learning_rate": 3.459424816010048e-05, "loss": 0.4528200149536133, "step": 421200 }, { "epoch": 2.5037597113492756, "grad_norm": 1.5549308061599731, "learning_rate": 3.45908501562437e-05, "loss": 0.43401269912719725, "step": 421210 }, { "epoch": 2.503819153425944, "grad_norm": 1.3358311653137207, "learning_rate": 3.458745251311969e-05, "loss": 0.4777512073516846, "step": 421220 }, { "epoch": 2.5038785955026124, "grad_norm": 1.0323238372802734, "learning_rate": 3.45840552307446e-05, "loss": 0.5046157836914062, "step": 421230 }, { "epoch": 2.503938037579281, "grad_norm": 1.158021092414856, "learning_rate": 3.4580658309134775e-05, "loss": 0.4789005756378174, "step": 421240 }, { "epoch": 2.503997479655949, "grad_norm": 1.0964696407318115, "learning_rate": 3.457726174830642e-05, "loss": 0.5041234493255615, "step": 421250 }, { "epoch": 2.5040569217326176, "grad_norm": 1.1350082159042358, "learning_rate": 3.457386554827578e-05, "loss": 0.47313776016235354, "step": 421260 }, { "epoch": 2.504116363809286, "grad_norm": 1.1624116897583008, "learning_rate": 3.457046970905914e-05, "loss": 0.4500739097595215, "step": 421270 }, { "epoch": 2.5041758058859545, "grad_norm": 1.257746934890747, "learning_rate": 3.4567074230672745e-05, "loss": 0.4872849464416504, "step": 421280 }, { "epoch": 2.504235247962623, "grad_norm": 1.4165290594100952, "learning_rate": 3.4563679113132775e-05, "loss": 0.5016303062438965, "step": 421290 }, { "epoch": 2.5042946900392913, "grad_norm": 1.5031459331512451, "learning_rate": 3.456028435645553e-05, "loss": 0.49454054832458494, "step": 421300 }, { "epoch": 2.5043541321159597, "grad_norm": 1.584623098373413, "learning_rate": 3.4556889960657224e-05, "loss": 0.5108700752258301, "step": 421310 }, { "epoch": 2.504413574192628, "grad_norm": 1.1905767917633057, "learning_rate": 3.455349592575411e-05, "loss": 0.4365110397338867, "step": 421320 }, { "epoch": 2.5044730162692965, "grad_norm": 1.491225004196167, "learning_rate": 3.4550102251762395e-05, "loss": 0.4977848052978516, "step": 421330 }, { "epoch": 2.504532458345965, "grad_norm": 1.4336400032043457, "learning_rate": 3.454670893869838e-05, "loss": 0.49619464874267577, "step": 421340 }, { "epoch": 2.504591900422633, "grad_norm": 1.1879620552062988, "learning_rate": 3.4543315986578216e-05, "loss": 0.42633786201477053, "step": 421350 }, { "epoch": 2.5046513424993018, "grad_norm": 1.0880426168441772, "learning_rate": 3.4539923395418155e-05, "loss": 0.4680215358734131, "step": 421360 }, { "epoch": 2.5047107845759697, "grad_norm": 1.591504454612732, "learning_rate": 3.4536531165234466e-05, "loss": 0.47198991775512694, "step": 421370 }, { "epoch": 2.5047702266526386, "grad_norm": 1.4390616416931152, "learning_rate": 3.453313929604335e-05, "loss": 0.4727326393127441, "step": 421380 }, { "epoch": 2.5048296687293066, "grad_norm": 1.0779900550842285, "learning_rate": 3.452974778786099e-05, "loss": 0.3995204925537109, "step": 421390 }, { "epoch": 2.504889110805975, "grad_norm": 1.662449836730957, "learning_rate": 3.452635664070372e-05, "loss": 0.47673678398132324, "step": 421400 }, { "epoch": 2.5049485528826434, "grad_norm": 1.1563570499420166, "learning_rate": 3.452296585458766e-05, "loss": 0.4626418113708496, "step": 421410 }, { "epoch": 2.505007994959312, "grad_norm": 1.145623803138733, "learning_rate": 3.451957542952907e-05, "loss": 0.47814264297485354, "step": 421420 }, { "epoch": 2.5050674370359802, "grad_norm": 1.4209827184677124, "learning_rate": 3.451618536554415e-05, "loss": 0.49362006187438967, "step": 421430 }, { "epoch": 2.5051268791126486, "grad_norm": 0.9860390424728394, "learning_rate": 3.451279566264915e-05, "loss": 0.4292536735534668, "step": 421440 }, { "epoch": 2.505186321189317, "grad_norm": 1.1262774467468262, "learning_rate": 3.450940632086026e-05, "loss": 0.4505678653717041, "step": 421450 }, { "epoch": 2.5052457632659855, "grad_norm": 1.3050830364227295, "learning_rate": 3.450601734019369e-05, "loss": 0.49776058197021483, "step": 421460 }, { "epoch": 2.505305205342654, "grad_norm": 1.1184966564178467, "learning_rate": 3.4502628720665675e-05, "loss": 0.4421264171600342, "step": 421470 }, { "epoch": 2.5053646474193223, "grad_norm": 1.166746973991394, "learning_rate": 3.4499240462292415e-05, "loss": 0.5160288333892822, "step": 421480 }, { "epoch": 2.5054240894959907, "grad_norm": 1.2027682065963745, "learning_rate": 3.449585256509008e-05, "loss": 0.47397842407226565, "step": 421490 }, { "epoch": 2.505483531572659, "grad_norm": 1.7148840427398682, "learning_rate": 3.449246502907495e-05, "loss": 0.4867249011993408, "step": 421500 }, { "epoch": 2.5055429736493275, "grad_norm": 1.0140804052352905, "learning_rate": 3.448907785426317e-05, "loss": 0.485296630859375, "step": 421510 }, { "epoch": 2.505602415725996, "grad_norm": 1.6062849760055542, "learning_rate": 3.4485691040670974e-05, "loss": 0.4899777889251709, "step": 421520 }, { "epoch": 2.5056618578026644, "grad_norm": 1.1577162742614746, "learning_rate": 3.448230458831455e-05, "loss": 0.4808956146240234, "step": 421530 }, { "epoch": 2.5057212998793323, "grad_norm": 0.9972883462905884, "learning_rate": 3.447891849721012e-05, "loss": 0.48284316062927246, "step": 421540 }, { "epoch": 2.505780741956001, "grad_norm": 1.2059438228607178, "learning_rate": 3.447553276737384e-05, "loss": 0.49286694526672364, "step": 421550 }, { "epoch": 2.505840184032669, "grad_norm": 1.5932841300964355, "learning_rate": 3.447214739882193e-05, "loss": 0.47450928688049315, "step": 421560 }, { "epoch": 2.505899626109338, "grad_norm": 1.6823210716247559, "learning_rate": 3.4468762391570586e-05, "loss": 0.47840261459350586, "step": 421570 }, { "epoch": 2.505959068186006, "grad_norm": 1.4150891304016113, "learning_rate": 3.446537774563601e-05, "loss": 0.5015505790710449, "step": 421580 }, { "epoch": 2.5060185102626744, "grad_norm": 1.231851577758789, "learning_rate": 3.446199346103437e-05, "loss": 0.47800326347351074, "step": 421590 }, { "epoch": 2.506077952339343, "grad_norm": 1.338006854057312, "learning_rate": 3.445860953778187e-05, "loss": 0.4889033317565918, "step": 421600 }, { "epoch": 2.5061373944160112, "grad_norm": 1.4555301666259766, "learning_rate": 3.44552259758947e-05, "loss": 0.47768173217773435, "step": 421610 }, { "epoch": 2.5061968364926797, "grad_norm": 1.2311235666275024, "learning_rate": 3.4451842775389026e-05, "loss": 0.45575551986694335, "step": 421620 }, { "epoch": 2.506256278569348, "grad_norm": 1.5229040384292603, "learning_rate": 3.4448459936281063e-05, "loss": 0.4937268257141113, "step": 421630 }, { "epoch": 2.5063157206460165, "grad_norm": 1.396449089050293, "learning_rate": 3.444507745858697e-05, "loss": 0.4550055503845215, "step": 421640 }, { "epoch": 2.506375162722685, "grad_norm": 1.3792943954467773, "learning_rate": 3.4441695342322944e-05, "loss": 0.4561589241027832, "step": 421650 }, { "epoch": 2.5064346047993533, "grad_norm": 1.3032227754592896, "learning_rate": 3.443831358750514e-05, "loss": 0.48801116943359374, "step": 421660 }, { "epoch": 2.5064940468760217, "grad_norm": 1.216788411140442, "learning_rate": 3.443493219414977e-05, "loss": 0.4329384326934814, "step": 421670 }, { "epoch": 2.50655348895269, "grad_norm": 1.566520094871521, "learning_rate": 3.4431551162272976e-05, "loss": 0.48531546592712405, "step": 421680 }, { "epoch": 2.5066129310293586, "grad_norm": 1.2036739587783813, "learning_rate": 3.442817049189093e-05, "loss": 0.46937131881713867, "step": 421690 }, { "epoch": 2.506672373106027, "grad_norm": 1.4662498235702515, "learning_rate": 3.442479018301984e-05, "loss": 0.46430196762084963, "step": 421700 }, { "epoch": 2.5067318151826954, "grad_norm": 1.24376380443573, "learning_rate": 3.4421410235675875e-05, "loss": 0.48189172744750974, "step": 421710 }, { "epoch": 2.506791257259364, "grad_norm": 1.3898643255233765, "learning_rate": 3.441803064987514e-05, "loss": 0.4483348846435547, "step": 421720 }, { "epoch": 2.5068506993360318, "grad_norm": 1.2413233518600464, "learning_rate": 3.441465142563387e-05, "loss": 0.470337438583374, "step": 421730 }, { "epoch": 2.5069101414127006, "grad_norm": 1.3115806579589844, "learning_rate": 3.44112725629682e-05, "loss": 0.4869863986968994, "step": 421740 }, { "epoch": 2.5069695834893686, "grad_norm": 1.3368475437164307, "learning_rate": 3.440789406189429e-05, "loss": 0.4577580451965332, "step": 421750 }, { "epoch": 2.507029025566037, "grad_norm": 1.187259316444397, "learning_rate": 3.440451592242832e-05, "loss": 0.4716036796569824, "step": 421760 }, { "epoch": 2.5070884676427054, "grad_norm": 1.4118895530700684, "learning_rate": 3.440113814458647e-05, "loss": 0.4245184898376465, "step": 421770 }, { "epoch": 2.507147909719374, "grad_norm": 1.2062125205993652, "learning_rate": 3.439776072838482e-05, "loss": 0.4772491455078125, "step": 421780 }, { "epoch": 2.5072073517960423, "grad_norm": 1.246856927871704, "learning_rate": 3.43943836738396e-05, "loss": 0.46144542694091795, "step": 421790 }, { "epoch": 2.5072667938727107, "grad_norm": 1.2887192964553833, "learning_rate": 3.4391006980966955e-05, "loss": 0.4505314826965332, "step": 421800 }, { "epoch": 2.507326235949379, "grad_norm": 1.078089714050293, "learning_rate": 3.438763064978301e-05, "loss": 0.4325474739074707, "step": 421810 }, { "epoch": 2.5073856780260475, "grad_norm": 1.4529532194137573, "learning_rate": 3.438425468030389e-05, "loss": 0.4717120170593262, "step": 421820 }, { "epoch": 2.507445120102716, "grad_norm": 1.2092182636260986, "learning_rate": 3.4380879072545855e-05, "loss": 0.44541568756103517, "step": 421830 }, { "epoch": 2.5075045621793843, "grad_norm": 1.1059942245483398, "learning_rate": 3.437750382652496e-05, "loss": 0.5207993507385253, "step": 421840 }, { "epoch": 2.5075640042560527, "grad_norm": 1.3300198316574097, "learning_rate": 3.4374128942257336e-05, "loss": 0.49984893798828123, "step": 421850 }, { "epoch": 2.507623446332721, "grad_norm": 1.3954925537109375, "learning_rate": 3.437075441975919e-05, "loss": 0.49504828453063965, "step": 421860 }, { "epoch": 2.5076828884093896, "grad_norm": 1.491201639175415, "learning_rate": 3.436738025904665e-05, "loss": 0.504249095916748, "step": 421870 }, { "epoch": 2.507742330486058, "grad_norm": 1.2629408836364746, "learning_rate": 3.43640064601358e-05, "loss": 0.4870450496673584, "step": 421880 }, { "epoch": 2.5078017725627264, "grad_norm": 0.7720575332641602, "learning_rate": 3.436063302304289e-05, "loss": 0.4856363296508789, "step": 421890 }, { "epoch": 2.5078612146393944, "grad_norm": 1.3246136903762817, "learning_rate": 3.435725994778396e-05, "loss": 0.4977110862731934, "step": 421900 }, { "epoch": 2.5079206567160632, "grad_norm": 1.2599247694015503, "learning_rate": 3.435388723437519e-05, "loss": 0.4686273574829102, "step": 421910 }, { "epoch": 2.507980098792731, "grad_norm": 1.3837711811065674, "learning_rate": 3.435051488283267e-05, "loss": 0.5055452346801758, "step": 421920 }, { "epoch": 2.5080395408694, "grad_norm": 1.0188770294189453, "learning_rate": 3.434714289317258e-05, "loss": 0.45308456420898435, "step": 421930 }, { "epoch": 2.508098982946068, "grad_norm": 1.076918601989746, "learning_rate": 3.4343771265411054e-05, "loss": 0.494201135635376, "step": 421940 }, { "epoch": 2.5081584250227364, "grad_norm": 1.344892978668213, "learning_rate": 3.4340399999564185e-05, "loss": 0.44745807647705077, "step": 421950 }, { "epoch": 2.508217867099405, "grad_norm": 1.3282119035720825, "learning_rate": 3.433702909564812e-05, "loss": 0.47012853622436523, "step": 421960 }, { "epoch": 2.5082773091760733, "grad_norm": 1.706201195716858, "learning_rate": 3.433365855367898e-05, "loss": 0.4736339569091797, "step": 421970 }, { "epoch": 2.5083367512527417, "grad_norm": 1.3459351062774658, "learning_rate": 3.433028837367288e-05, "loss": 0.5317189693450928, "step": 421980 }, { "epoch": 2.50839619332941, "grad_norm": 1.4781550168991089, "learning_rate": 3.432691855564596e-05, "loss": 0.4646303653717041, "step": 421990 }, { "epoch": 2.5084556354060785, "grad_norm": 1.0352462530136108, "learning_rate": 3.432354909961434e-05, "loss": 0.49576354026794434, "step": 422000 }, { "epoch": 2.508515077482747, "grad_norm": 1.3762965202331543, "learning_rate": 3.432018000559412e-05, "loss": 0.4926470756530762, "step": 422010 }, { "epoch": 2.5085745195594154, "grad_norm": 1.2468448877334595, "learning_rate": 3.4316811273601434e-05, "loss": 0.48793439865112304, "step": 422020 }, { "epoch": 2.5086339616360838, "grad_norm": 1.148485541343689, "learning_rate": 3.431344290365238e-05, "loss": 0.4373267650604248, "step": 422030 }, { "epoch": 2.508693403712752, "grad_norm": 1.271659255027771, "learning_rate": 3.431007489576309e-05, "loss": 0.48526906967163086, "step": 422040 }, { "epoch": 2.5087528457894206, "grad_norm": 0.8984134793281555, "learning_rate": 3.4306707249949645e-05, "loss": 0.48265933990478516, "step": 422050 }, { "epoch": 2.508812287866089, "grad_norm": 0.8879859447479248, "learning_rate": 3.430333996622819e-05, "loss": 0.4286796569824219, "step": 422060 }, { "epoch": 2.5088717299427574, "grad_norm": 1.0765389204025269, "learning_rate": 3.429997304461483e-05, "loss": 0.4499053478240967, "step": 422070 }, { "epoch": 2.508931172019426, "grad_norm": 1.221245527267456, "learning_rate": 3.429660648512565e-05, "loss": 0.48467063903808594, "step": 422080 }, { "epoch": 2.508990614096094, "grad_norm": 1.1466476917266846, "learning_rate": 3.429324028777676e-05, "loss": 0.46746277809143066, "step": 422090 }, { "epoch": 2.5090500561727627, "grad_norm": 0.9594401717185974, "learning_rate": 3.4289874452584267e-05, "loss": 0.4889923095703125, "step": 422100 }, { "epoch": 2.5091094982494306, "grad_norm": 1.539981722831726, "learning_rate": 3.428650897956426e-05, "loss": 0.4552910804748535, "step": 422110 }, { "epoch": 2.5091689403260995, "grad_norm": 1.5137351751327515, "learning_rate": 3.4283143868732876e-05, "loss": 0.47612819671630857, "step": 422120 }, { "epoch": 2.5092283824027675, "grad_norm": 1.1925697326660156, "learning_rate": 3.427977912010618e-05, "loss": 0.5299140453338623, "step": 422130 }, { "epoch": 2.509287824479436, "grad_norm": 1.300693392753601, "learning_rate": 3.427641473370028e-05, "loss": 0.4631173133850098, "step": 422140 }, { "epoch": 2.5093472665561043, "grad_norm": 1.2602436542510986, "learning_rate": 3.4273050709531255e-05, "loss": 0.48395791053771975, "step": 422150 }, { "epoch": 2.5094067086327727, "grad_norm": 1.2930630445480347, "learning_rate": 3.426968704761522e-05, "loss": 0.465455150604248, "step": 422160 }, { "epoch": 2.509466150709441, "grad_norm": 1.2812966108322144, "learning_rate": 3.426632374796824e-05, "loss": 0.4705062389373779, "step": 422170 }, { "epoch": 2.5095255927861095, "grad_norm": 1.4291197061538696, "learning_rate": 3.42629608106064e-05, "loss": 0.4784749984741211, "step": 422180 }, { "epoch": 2.509585034862778, "grad_norm": 1.4009554386138916, "learning_rate": 3.425959823554583e-05, "loss": 0.4953742504119873, "step": 422190 }, { "epoch": 2.5096444769394464, "grad_norm": 1.4414520263671875, "learning_rate": 3.425623602280259e-05, "loss": 0.4496433734893799, "step": 422200 }, { "epoch": 2.509703919016115, "grad_norm": 1.257220983505249, "learning_rate": 3.425287417239277e-05, "loss": 0.43893117904663087, "step": 422210 }, { "epoch": 2.509763361092783, "grad_norm": 1.495313048362732, "learning_rate": 3.424951268433243e-05, "loss": 0.45499401092529296, "step": 422220 }, { "epoch": 2.5098228031694516, "grad_norm": 1.2966911792755127, "learning_rate": 3.424615155863767e-05, "loss": 0.5104314804077148, "step": 422230 }, { "epoch": 2.50988224524612, "grad_norm": 1.157562017440796, "learning_rate": 3.424279079532455e-05, "loss": 0.5410082817077637, "step": 422240 }, { "epoch": 2.5099416873227884, "grad_norm": 1.5389426946640015, "learning_rate": 3.423943039440918e-05, "loss": 0.49071826934814455, "step": 422250 }, { "epoch": 2.510001129399457, "grad_norm": 1.4927926063537598, "learning_rate": 3.423607035590764e-05, "loss": 0.48035669326782227, "step": 422260 }, { "epoch": 2.5100605714761253, "grad_norm": 1.2739148139953613, "learning_rate": 3.423271067983593e-05, "loss": 0.42699122428894043, "step": 422270 }, { "epoch": 2.5101200135527932, "grad_norm": 1.4557394981384277, "learning_rate": 3.4229351366210196e-05, "loss": 0.482941198348999, "step": 422280 }, { "epoch": 2.510179455629462, "grad_norm": 1.3648159503936768, "learning_rate": 3.422599241504648e-05, "loss": 0.4716071128845215, "step": 422290 }, { "epoch": 2.51023889770613, "grad_norm": 1.2657387256622314, "learning_rate": 3.4222633826360854e-05, "loss": 0.49033141136169434, "step": 422300 }, { "epoch": 2.510298339782799, "grad_norm": 1.5614516735076904, "learning_rate": 3.421927560016937e-05, "loss": 0.5049961090087891, "step": 422310 }, { "epoch": 2.510357781859467, "grad_norm": 1.270740270614624, "learning_rate": 3.421591773648813e-05, "loss": 0.5257897853851319, "step": 422320 }, { "epoch": 2.5104172239361353, "grad_norm": 1.6038235425949097, "learning_rate": 3.421256023533318e-05, "loss": 0.5110016345977784, "step": 422330 }, { "epoch": 2.5104766660128037, "grad_norm": 1.3769447803497314, "learning_rate": 3.420920309672053e-05, "loss": 0.46370706558227537, "step": 422340 }, { "epoch": 2.510536108089472, "grad_norm": 1.2309825420379639, "learning_rate": 3.4205846320666314e-05, "loss": 0.4975566864013672, "step": 422350 }, { "epoch": 2.5105955501661406, "grad_norm": 1.4734632968902588, "learning_rate": 3.420248990718655e-05, "loss": 0.43843793869018555, "step": 422360 }, { "epoch": 2.510654992242809, "grad_norm": 1.0158740282058716, "learning_rate": 3.419913385629729e-05, "loss": 0.4968526840209961, "step": 422370 }, { "epoch": 2.5107144343194774, "grad_norm": 1.539223551750183, "learning_rate": 3.4195778168014645e-05, "loss": 0.4316368103027344, "step": 422380 }, { "epoch": 2.510773876396146, "grad_norm": 1.2461026906967163, "learning_rate": 3.4192422842354596e-05, "loss": 0.4305985927581787, "step": 422390 }, { "epoch": 2.510833318472814, "grad_norm": 1.155097484588623, "learning_rate": 3.418906787933324e-05, "loss": 0.4616060733795166, "step": 422400 }, { "epoch": 2.5108927605494826, "grad_norm": 1.3497402667999268, "learning_rate": 3.418571327896657e-05, "loss": 0.452439022064209, "step": 422410 }, { "epoch": 2.510952202626151, "grad_norm": 1.6175100803375244, "learning_rate": 3.41823590412707e-05, "loss": 0.46191725730895994, "step": 422420 }, { "epoch": 2.5110116447028195, "grad_norm": 0.9733077883720398, "learning_rate": 3.417900516626164e-05, "loss": 0.5074177742004394, "step": 422430 }, { "epoch": 2.511071086779488, "grad_norm": 1.307981252670288, "learning_rate": 3.417565165395545e-05, "loss": 0.474481201171875, "step": 422440 }, { "epoch": 2.511130528856156, "grad_norm": 1.4318511486053467, "learning_rate": 3.417229850436815e-05, "loss": 0.492874813079834, "step": 422450 }, { "epoch": 2.5111899709328247, "grad_norm": 1.1466494798660278, "learning_rate": 3.41689457175158e-05, "loss": 0.48147048950195315, "step": 422460 }, { "epoch": 2.5112494130094927, "grad_norm": 1.2130597829818726, "learning_rate": 3.416559329341441e-05, "loss": 0.5271313667297364, "step": 422470 }, { "epoch": 2.5113088550861615, "grad_norm": 1.5491803884506226, "learning_rate": 3.416224123208006e-05, "loss": 0.44393191337585447, "step": 422480 }, { "epoch": 2.5113682971628295, "grad_norm": 1.0691208839416504, "learning_rate": 3.4158889533528766e-05, "loss": 0.46320672035217286, "step": 422490 }, { "epoch": 2.511427739239498, "grad_norm": 1.3283140659332275, "learning_rate": 3.4155538197776554e-05, "loss": 0.4073344707489014, "step": 422500 }, { "epoch": 2.5114871813161663, "grad_norm": 1.5762230157852173, "learning_rate": 3.4152187224839474e-05, "loss": 0.5408401012420654, "step": 422510 }, { "epoch": 2.5115466233928347, "grad_norm": 1.4055184125900269, "learning_rate": 3.414883661473354e-05, "loss": 0.4782847881317139, "step": 422520 }, { "epoch": 2.511606065469503, "grad_norm": 1.470386028289795, "learning_rate": 3.414548636747476e-05, "loss": 0.5141444683074952, "step": 422530 }, { "epoch": 2.5116655075461716, "grad_norm": 1.0271812677383423, "learning_rate": 3.414213648307918e-05, "loss": 0.4778336524963379, "step": 422540 }, { "epoch": 2.51172494962284, "grad_norm": 1.6267019510269165, "learning_rate": 3.4138786961562855e-05, "loss": 0.45184803009033203, "step": 422550 }, { "epoch": 2.5117843916995084, "grad_norm": 1.1572821140289307, "learning_rate": 3.413543780294178e-05, "loss": 0.48589744567871096, "step": 422560 }, { "epoch": 2.511843833776177, "grad_norm": 1.4675142765045166, "learning_rate": 3.413208900723197e-05, "loss": 0.455812931060791, "step": 422570 }, { "epoch": 2.5119032758528452, "grad_norm": 1.5007253885269165, "learning_rate": 3.412874057444946e-05, "loss": 0.47342629432678224, "step": 422580 }, { "epoch": 2.5119627179295136, "grad_norm": 1.6104400157928467, "learning_rate": 3.412539250461025e-05, "loss": 0.46489520072937013, "step": 422590 }, { "epoch": 2.512022160006182, "grad_norm": 1.0586994886398315, "learning_rate": 3.412204479773035e-05, "loss": 0.4156294822692871, "step": 422600 }, { "epoch": 2.5120816020828505, "grad_norm": 0.8746955394744873, "learning_rate": 3.411869745382581e-05, "loss": 0.4378824234008789, "step": 422610 }, { "epoch": 2.512141044159519, "grad_norm": 1.4507051706314087, "learning_rate": 3.4115350472912635e-05, "loss": 0.44446678161621095, "step": 422620 }, { "epoch": 2.5122004862361873, "grad_norm": 1.40503990650177, "learning_rate": 3.411200385500681e-05, "loss": 0.46267213821411135, "step": 422630 }, { "epoch": 2.5122599283128553, "grad_norm": 1.3062925338745117, "learning_rate": 3.4108657600124364e-05, "loss": 0.48566360473632814, "step": 422640 }, { "epoch": 2.512319370389524, "grad_norm": 1.2651057243347168, "learning_rate": 3.41053117082813e-05, "loss": 0.47339954376220705, "step": 422650 }, { "epoch": 2.512378812466192, "grad_norm": 1.707724690437317, "learning_rate": 3.4101966179493614e-05, "loss": 0.5502265453338623, "step": 422660 }, { "epoch": 2.512438254542861, "grad_norm": 1.1833367347717285, "learning_rate": 3.409862101377731e-05, "loss": 0.513625192642212, "step": 422670 }, { "epoch": 2.512497696619529, "grad_norm": 1.265994668006897, "learning_rate": 3.409527621114841e-05, "loss": 0.5063034534454346, "step": 422680 }, { "epoch": 2.5125571386961973, "grad_norm": 1.0853009223937988, "learning_rate": 3.40919317716229e-05, "loss": 0.471828031539917, "step": 422690 }, { "epoch": 2.5126165807728658, "grad_norm": 1.0927050113677979, "learning_rate": 3.408858769521678e-05, "loss": 0.45667495727539065, "step": 422700 }, { "epoch": 2.512676022849534, "grad_norm": 1.094508409500122, "learning_rate": 3.408524398194606e-05, "loss": 0.44132609367370607, "step": 422710 }, { "epoch": 2.5127354649262026, "grad_norm": 0.9654054045677185, "learning_rate": 3.4081900631826713e-05, "loss": 0.4599503993988037, "step": 422720 }, { "epoch": 2.512794907002871, "grad_norm": 1.2347084283828735, "learning_rate": 3.407855764487473e-05, "loss": 0.47291059494018556, "step": 422730 }, { "epoch": 2.5128543490795394, "grad_norm": 1.2953269481658936, "learning_rate": 3.407521502110613e-05, "loss": 0.45348801612854006, "step": 422740 }, { "epoch": 2.512913791156208, "grad_norm": 1.192814826965332, "learning_rate": 3.4071872760536895e-05, "loss": 0.4702244758605957, "step": 422750 }, { "epoch": 2.5129732332328762, "grad_norm": 1.1477676630020142, "learning_rate": 3.406853086318302e-05, "loss": 0.45728302001953125, "step": 422760 }, { "epoch": 2.5130326753095447, "grad_norm": 1.0111544132232666, "learning_rate": 3.4065189329060445e-05, "loss": 0.45323781967163085, "step": 422770 }, { "epoch": 2.513092117386213, "grad_norm": 1.1994644403457642, "learning_rate": 3.40618481581852e-05, "loss": 0.5008129596710205, "step": 422780 }, { "epoch": 2.5131515594628815, "grad_norm": 1.4419887065887451, "learning_rate": 3.405850735057327e-05, "loss": 0.45668859481811525, "step": 422790 }, { "epoch": 2.51321100153955, "grad_norm": 1.060782551765442, "learning_rate": 3.405516690624059e-05, "loss": 0.46164522171020506, "step": 422800 }, { "epoch": 2.5132704436162183, "grad_norm": 1.5827041864395142, "learning_rate": 3.40518268252032e-05, "loss": 0.4674241065979004, "step": 422810 }, { "epoch": 2.5133298856928867, "grad_norm": 1.761512041091919, "learning_rate": 3.404848710747707e-05, "loss": 0.48836097717285154, "step": 422820 }, { "epoch": 2.5133893277695547, "grad_norm": 1.4508041143417358, "learning_rate": 3.404514775307812e-05, "loss": 0.48505325317382814, "step": 422830 }, { "epoch": 2.5134487698462236, "grad_norm": 1.35407292842865, "learning_rate": 3.4041808762022375e-05, "loss": 0.5211183071136475, "step": 422840 }, { "epoch": 2.5135082119228915, "grad_norm": 1.2311352491378784, "learning_rate": 3.403847013432579e-05, "loss": 0.5319769382476807, "step": 422850 }, { "epoch": 2.5135676539995604, "grad_norm": 1.4249109029769897, "learning_rate": 3.403513187000433e-05, "loss": 0.4974344253540039, "step": 422860 }, { "epoch": 2.5136270960762284, "grad_norm": 1.0891832113265991, "learning_rate": 3.4031793969073985e-05, "loss": 0.48968114852905276, "step": 422870 }, { "epoch": 2.5136865381528968, "grad_norm": 1.286039113998413, "learning_rate": 3.402845643155073e-05, "loss": 0.45232257843017576, "step": 422880 }, { "epoch": 2.513745980229565, "grad_norm": 1.2184066772460938, "learning_rate": 3.40251192574505e-05, "loss": 0.5088781356811524, "step": 422890 }, { "epoch": 2.5138054223062336, "grad_norm": 1.2882558107376099, "learning_rate": 3.4021782446789243e-05, "loss": 0.5045747756958008, "step": 422900 }, { "epoch": 2.513864864382902, "grad_norm": 1.2380425930023193, "learning_rate": 3.4018445999582974e-05, "loss": 0.48894128799438474, "step": 422910 }, { "epoch": 2.5139243064595704, "grad_norm": 1.3293832540512085, "learning_rate": 3.401510991584763e-05, "loss": 0.45217323303222656, "step": 422920 }, { "epoch": 2.513983748536239, "grad_norm": 1.3286279439926147, "learning_rate": 3.401177419559915e-05, "loss": 0.5098825454711914, "step": 422930 }, { "epoch": 2.5140431906129073, "grad_norm": 1.162756085395813, "learning_rate": 3.400843883885353e-05, "loss": 0.46866574287414553, "step": 422940 }, { "epoch": 2.5141026326895757, "grad_norm": 1.6957645416259766, "learning_rate": 3.4005103845626695e-05, "loss": 0.46786890029907224, "step": 422950 }, { "epoch": 2.514162074766244, "grad_norm": 1.1570547819137573, "learning_rate": 3.400176921593459e-05, "loss": 0.48757205009460447, "step": 422960 }, { "epoch": 2.5142215168429125, "grad_norm": 1.263752818107605, "learning_rate": 3.39984349497932e-05, "loss": 0.4401897430419922, "step": 422970 }, { "epoch": 2.514280958919581, "grad_norm": 1.3071789741516113, "learning_rate": 3.399510104721847e-05, "loss": 0.4924205780029297, "step": 422980 }, { "epoch": 2.5143404009962493, "grad_norm": 1.2827743291854858, "learning_rate": 3.3991767508226326e-05, "loss": 0.4899202823638916, "step": 422990 }, { "epoch": 2.5143998430729178, "grad_norm": 1.2684988975524902, "learning_rate": 3.398843433283273e-05, "loss": 0.46625576019287107, "step": 423000 }, { "epoch": 2.514459285149586, "grad_norm": 1.6210994720458984, "learning_rate": 3.398510152105363e-05, "loss": 0.47131686210632323, "step": 423010 }, { "epoch": 2.514518727226254, "grad_norm": 1.5954753160476685, "learning_rate": 3.3981769072904955e-05, "loss": 0.5066324234008789, "step": 423020 }, { "epoch": 2.514578169302923, "grad_norm": 1.1888173818588257, "learning_rate": 3.397843698840264e-05, "loss": 0.46956748962402345, "step": 423030 }, { "epoch": 2.514637611379591, "grad_norm": 1.6523795127868652, "learning_rate": 3.397510526756266e-05, "loss": 0.4717557907104492, "step": 423040 }, { "epoch": 2.51469705345626, "grad_norm": 1.4149380922317505, "learning_rate": 3.397177391040092e-05, "loss": 0.48267350196838377, "step": 423050 }, { "epoch": 2.514756495532928, "grad_norm": 1.2882946729660034, "learning_rate": 3.396844291693337e-05, "loss": 0.5114459991455078, "step": 423060 }, { "epoch": 2.514815937609596, "grad_norm": 0.8796682953834534, "learning_rate": 3.396511228717595e-05, "loss": 0.41130924224853516, "step": 423070 }, { "epoch": 2.5148753796862646, "grad_norm": 1.2878491878509521, "learning_rate": 3.396178202114458e-05, "loss": 0.4477278709411621, "step": 423080 }, { "epoch": 2.514934821762933, "grad_norm": 1.6478089094161987, "learning_rate": 3.3958452118855174e-05, "loss": 0.4384464740753174, "step": 423090 }, { "epoch": 2.5149942638396015, "grad_norm": 1.7020010948181152, "learning_rate": 3.39551225803237e-05, "loss": 0.4537515640258789, "step": 423100 }, { "epoch": 2.51505370591627, "grad_norm": 1.6056994199752808, "learning_rate": 3.395179340556608e-05, "loss": 0.4752355575561523, "step": 423110 }, { "epoch": 2.5151131479929383, "grad_norm": 1.4294583797454834, "learning_rate": 3.394846459459822e-05, "loss": 0.4967536926269531, "step": 423120 }, { "epoch": 2.5151725900696067, "grad_norm": 1.2542392015457153, "learning_rate": 3.394513614743605e-05, "loss": 0.5233736038208008, "step": 423130 }, { "epoch": 2.515232032146275, "grad_norm": 1.2022796869277954, "learning_rate": 3.394180806409548e-05, "loss": 0.42491464614868163, "step": 423140 }, { "epoch": 2.5152914742229435, "grad_norm": 1.6289207935333252, "learning_rate": 3.393848034459247e-05, "loss": 0.5129506111145019, "step": 423150 }, { "epoch": 2.515350916299612, "grad_norm": 1.740089774131775, "learning_rate": 3.393515298894288e-05, "loss": 0.5090172290802002, "step": 423160 }, { "epoch": 2.5154103583762804, "grad_norm": 1.1963706016540527, "learning_rate": 3.393182599716268e-05, "loss": 0.4684760093688965, "step": 423170 }, { "epoch": 2.5154698004529488, "grad_norm": 1.6610393524169922, "learning_rate": 3.392849936926776e-05, "loss": 0.4762281894683838, "step": 423180 }, { "epoch": 2.5155292425296167, "grad_norm": 1.0420691967010498, "learning_rate": 3.392517310527404e-05, "loss": 0.5135468482971192, "step": 423190 }, { "epoch": 2.5155886846062856, "grad_norm": 1.1961537599563599, "learning_rate": 3.3921847205197444e-05, "loss": 0.47989864349365235, "step": 423200 }, { "epoch": 2.5156481266829536, "grad_norm": 1.4631589651107788, "learning_rate": 3.391852166905385e-05, "loss": 0.47767333984375, "step": 423210 }, { "epoch": 2.5157075687596224, "grad_norm": 1.1881864070892334, "learning_rate": 3.391519649685918e-05, "loss": 0.40659608840942385, "step": 423220 }, { "epoch": 2.5157670108362904, "grad_norm": 1.560572624206543, "learning_rate": 3.391187168862936e-05, "loss": 0.4953104019165039, "step": 423230 }, { "epoch": 2.515826452912959, "grad_norm": 1.3767590522766113, "learning_rate": 3.390854724438027e-05, "loss": 0.4717063903808594, "step": 423240 }, { "epoch": 2.5158858949896272, "grad_norm": 1.6772255897521973, "learning_rate": 3.390522316412786e-05, "loss": 0.5159962177276611, "step": 423250 }, { "epoch": 2.5159453370662956, "grad_norm": 1.4280986785888672, "learning_rate": 3.390189944788794e-05, "loss": 0.5004002571105957, "step": 423260 }, { "epoch": 2.516004779142964, "grad_norm": 1.1844947338104248, "learning_rate": 3.389857609567649e-05, "loss": 0.48711328506469725, "step": 423270 }, { "epoch": 2.5160642212196325, "grad_norm": 1.6885918378829956, "learning_rate": 3.3895253107509384e-05, "loss": 0.5123612403869628, "step": 423280 }, { "epoch": 2.516123663296301, "grad_norm": 1.444718837738037, "learning_rate": 3.38919304834025e-05, "loss": 0.4842689037322998, "step": 423290 }, { "epoch": 2.5161831053729693, "grad_norm": 1.2548881769180298, "learning_rate": 3.388860822337175e-05, "loss": 0.44727230072021484, "step": 423300 }, { "epoch": 2.5162425474496377, "grad_norm": 1.1606152057647705, "learning_rate": 3.388528632743306e-05, "loss": 0.4535847187042236, "step": 423310 }, { "epoch": 2.516301989526306, "grad_norm": 1.196968913078308, "learning_rate": 3.388196479560224e-05, "loss": 0.5173675537109375, "step": 423320 }, { "epoch": 2.5163614316029745, "grad_norm": 1.4151440858840942, "learning_rate": 3.387864362789526e-05, "loss": 0.48152670860290525, "step": 423330 }, { "epoch": 2.516420873679643, "grad_norm": 1.1313649415969849, "learning_rate": 3.3875322824327956e-05, "loss": 0.472666072845459, "step": 423340 }, { "epoch": 2.5164803157563114, "grad_norm": 1.3888425827026367, "learning_rate": 3.3872002384916216e-05, "loss": 0.499729061126709, "step": 423350 }, { "epoch": 2.51653975783298, "grad_norm": 1.2501951456069946, "learning_rate": 3.386868230967595e-05, "loss": 0.45647706985473635, "step": 423360 }, { "epoch": 2.516599199909648, "grad_norm": 1.5485717058181763, "learning_rate": 3.3865362598623045e-05, "loss": 0.4394749641418457, "step": 423370 }, { "epoch": 2.516658641986316, "grad_norm": 1.2513669729232788, "learning_rate": 3.3862043251773354e-05, "loss": 0.5125076293945312, "step": 423380 }, { "epoch": 2.516718084062985, "grad_norm": 1.3834519386291504, "learning_rate": 3.385872426914274e-05, "loss": 0.48961467742919923, "step": 423390 }, { "epoch": 2.516777526139653, "grad_norm": 1.3220560550689697, "learning_rate": 3.385540565074714e-05, "loss": 0.4631350517272949, "step": 423400 }, { "epoch": 2.516836968216322, "grad_norm": 1.4691342115402222, "learning_rate": 3.385208739660238e-05, "loss": 0.46672658920288085, "step": 423410 }, { "epoch": 2.51689641029299, "grad_norm": 1.3237788677215576, "learning_rate": 3.384876950672433e-05, "loss": 0.4514770984649658, "step": 423420 }, { "epoch": 2.5169558523696582, "grad_norm": 1.316116213798523, "learning_rate": 3.3845451981128914e-05, "loss": 0.4576861381530762, "step": 423430 }, { "epoch": 2.5170152944463267, "grad_norm": 1.5437211990356445, "learning_rate": 3.384213481983197e-05, "loss": 0.4787684440612793, "step": 423440 }, { "epoch": 2.517074736522995, "grad_norm": 1.2650922536849976, "learning_rate": 3.3838818022849325e-05, "loss": 0.4621238708496094, "step": 423450 }, { "epoch": 2.5171341785996635, "grad_norm": 1.4210994243621826, "learning_rate": 3.3835501590196905e-05, "loss": 0.5035654067993164, "step": 423460 }, { "epoch": 2.517193620676332, "grad_norm": 1.4565123319625854, "learning_rate": 3.383218552189057e-05, "loss": 0.5147120952606201, "step": 423470 }, { "epoch": 2.5172530627530003, "grad_norm": 1.4946259260177612, "learning_rate": 3.382886981794613e-05, "loss": 0.4903535842895508, "step": 423480 }, { "epoch": 2.5173125048296687, "grad_norm": 1.0874948501586914, "learning_rate": 3.382555447837954e-05, "loss": 0.4719265937805176, "step": 423490 }, { "epoch": 2.517371946906337, "grad_norm": 1.1305347681045532, "learning_rate": 3.3822239503206576e-05, "loss": 0.49588832855224607, "step": 423500 }, { "epoch": 2.5174313889830056, "grad_norm": 1.4249799251556396, "learning_rate": 3.3818924892443124e-05, "loss": 0.4968131065368652, "step": 423510 }, { "epoch": 2.517490831059674, "grad_norm": 1.076351523399353, "learning_rate": 3.381561064610501e-05, "loss": 0.48759708404541013, "step": 423520 }, { "epoch": 2.5175502731363424, "grad_norm": 1.578597903251648, "learning_rate": 3.381229676420815e-05, "loss": 0.473370885848999, "step": 423530 }, { "epoch": 2.517609715213011, "grad_norm": 1.1787115335464478, "learning_rate": 3.380898324676835e-05, "loss": 0.4579643249511719, "step": 423540 }, { "epoch": 2.517669157289679, "grad_norm": 1.181978464126587, "learning_rate": 3.380567009380149e-05, "loss": 0.4566657066345215, "step": 423550 }, { "epoch": 2.5177285993663476, "grad_norm": 1.5212652683258057, "learning_rate": 3.3802357305323396e-05, "loss": 0.47522802352905275, "step": 423560 }, { "epoch": 2.5177880414430156, "grad_norm": 1.4367297887802124, "learning_rate": 3.3799044881349925e-05, "loss": 0.4981243133544922, "step": 423570 }, { "epoch": 2.5178474835196845, "grad_norm": 1.901535987854004, "learning_rate": 3.3795732821896906e-05, "loss": 0.49620814323425294, "step": 423580 }, { "epoch": 2.5179069255963524, "grad_norm": 1.148132085800171, "learning_rate": 3.379242112698021e-05, "loss": 0.4683968544006348, "step": 423590 }, { "epoch": 2.5179663676730213, "grad_norm": 1.3442546129226685, "learning_rate": 3.378910979661566e-05, "loss": 0.521071195602417, "step": 423600 }, { "epoch": 2.5180258097496893, "grad_norm": 1.3975830078125, "learning_rate": 3.3785798830819116e-05, "loss": 0.47263803482055666, "step": 423610 }, { "epoch": 2.5180852518263577, "grad_norm": 1.295050859451294, "learning_rate": 3.3782488229606405e-05, "loss": 0.4819904327392578, "step": 423620 }, { "epoch": 2.518144693903026, "grad_norm": 1.5100219249725342, "learning_rate": 3.377917799299335e-05, "loss": 0.4787074089050293, "step": 423630 }, { "epoch": 2.5182041359796945, "grad_norm": 1.050675868988037, "learning_rate": 3.37758681209958e-05, "loss": 0.4490382194519043, "step": 423640 }, { "epoch": 2.518263578056363, "grad_norm": 1.6018787622451782, "learning_rate": 3.3772558613629564e-05, "loss": 0.4567598819732666, "step": 423650 }, { "epoch": 2.5183230201330313, "grad_norm": 1.7982667684555054, "learning_rate": 3.3769249470910524e-05, "loss": 0.4219042301177979, "step": 423660 }, { "epoch": 2.5183824622096997, "grad_norm": 1.1959044933319092, "learning_rate": 3.3765940692854476e-05, "loss": 0.4347994327545166, "step": 423670 }, { "epoch": 2.518441904286368, "grad_norm": 1.3970497846603394, "learning_rate": 3.3762632279477256e-05, "loss": 0.511809253692627, "step": 423680 }, { "epoch": 2.5185013463630366, "grad_norm": 1.172240972518921, "learning_rate": 3.37593242307947e-05, "loss": 0.45955753326416016, "step": 423690 }, { "epoch": 2.518560788439705, "grad_norm": 1.4319931268692017, "learning_rate": 3.375601654682261e-05, "loss": 0.4875905513763428, "step": 423700 }, { "epoch": 2.5186202305163734, "grad_norm": 1.156632900238037, "learning_rate": 3.37527092275768e-05, "loss": 0.4767898082733154, "step": 423710 }, { "epoch": 2.518679672593042, "grad_norm": 1.279057264328003, "learning_rate": 3.374940227307313e-05, "loss": 0.5141970634460449, "step": 423720 }, { "epoch": 2.5187391146697102, "grad_norm": 1.3531690835952759, "learning_rate": 3.37460956833274e-05, "loss": 0.41858577728271484, "step": 423730 }, { "epoch": 2.5187985567463786, "grad_norm": 1.447299838066101, "learning_rate": 3.374278945835546e-05, "loss": 0.4830923080444336, "step": 423740 }, { "epoch": 2.518857998823047, "grad_norm": 1.5890021324157715, "learning_rate": 3.373948359817304e-05, "loss": 0.5317693710327148, "step": 423750 }, { "epoch": 2.518917440899715, "grad_norm": 1.2248903512954712, "learning_rate": 3.373617810279604e-05, "loss": 0.4927623748779297, "step": 423760 }, { "epoch": 2.518976882976384, "grad_norm": 0.9458379149436951, "learning_rate": 3.373287297224023e-05, "loss": 0.49625420570373535, "step": 423770 }, { "epoch": 2.519036325053052, "grad_norm": 1.643630027770996, "learning_rate": 3.3729568206521414e-05, "loss": 0.44461517333984374, "step": 423780 }, { "epoch": 2.5190957671297207, "grad_norm": 1.3345121145248413, "learning_rate": 3.372626380565544e-05, "loss": 0.47765140533447265, "step": 423790 }, { "epoch": 2.5191552092063887, "grad_norm": 1.3853564262390137, "learning_rate": 3.372295976965812e-05, "loss": 0.45520644187927245, "step": 423800 }, { "epoch": 2.519214651283057, "grad_norm": 1.350242257118225, "learning_rate": 3.371965609854518e-05, "loss": 0.4583188533782959, "step": 423810 }, { "epoch": 2.5192740933597255, "grad_norm": 1.0836536884307861, "learning_rate": 3.3716352792332505e-05, "loss": 0.44812283515930174, "step": 423820 }, { "epoch": 2.519333535436394, "grad_norm": 0.991350531578064, "learning_rate": 3.3713049851035864e-05, "loss": 0.5112533569335938, "step": 423830 }, { "epoch": 2.5193929775130623, "grad_norm": 1.685903549194336, "learning_rate": 3.370974727467104e-05, "loss": 0.45583419799804686, "step": 423840 }, { "epoch": 2.5194524195897308, "grad_norm": 1.581791639328003, "learning_rate": 3.3706445063253875e-05, "loss": 0.44537878036499023, "step": 423850 }, { "epoch": 2.519511861666399, "grad_norm": 1.7386366128921509, "learning_rate": 3.3703143216800174e-05, "loss": 0.5167184829711914, "step": 423860 }, { "epoch": 2.5195713037430676, "grad_norm": 1.1476542949676514, "learning_rate": 3.369984173532567e-05, "loss": 0.4399239540100098, "step": 423870 }, { "epoch": 2.519630745819736, "grad_norm": 1.4363609552383423, "learning_rate": 3.3696540618846176e-05, "loss": 0.4598592758178711, "step": 423880 }, { "epoch": 2.5196901878964044, "grad_norm": 1.214406132698059, "learning_rate": 3.369323986737751e-05, "loss": 0.5390603065490722, "step": 423890 }, { "epoch": 2.519749629973073, "grad_norm": 1.4891332387924194, "learning_rate": 3.368993948093545e-05, "loss": 0.5185004234313965, "step": 423900 }, { "epoch": 2.5198090720497412, "grad_norm": 1.4873985052108765, "learning_rate": 3.3686639459535754e-05, "loss": 0.5214068412780761, "step": 423910 }, { "epoch": 2.5198685141264097, "grad_norm": 1.1950172185897827, "learning_rate": 3.368333980319429e-05, "loss": 0.4965402603149414, "step": 423920 }, { "epoch": 2.5199279562030776, "grad_norm": 1.3211344480514526, "learning_rate": 3.368004051192675e-05, "loss": 0.4715869903564453, "step": 423930 }, { "epoch": 2.5199873982797465, "grad_norm": 1.1164658069610596, "learning_rate": 3.367674158574895e-05, "loss": 0.4243016242980957, "step": 423940 }, { "epoch": 2.5200468403564145, "grad_norm": 1.4982950687408447, "learning_rate": 3.3673443024676685e-05, "loss": 0.4653963565826416, "step": 423950 }, { "epoch": 2.5201062824330833, "grad_norm": 1.2247551679611206, "learning_rate": 3.367014482872573e-05, "loss": 0.4437709808349609, "step": 423960 }, { "epoch": 2.5201657245097513, "grad_norm": 1.2408143281936646, "learning_rate": 3.366684699791183e-05, "loss": 0.47821245193481443, "step": 423970 }, { "epoch": 2.5202251665864197, "grad_norm": 1.115024447441101, "learning_rate": 3.366354953225084e-05, "loss": 0.5177330493927002, "step": 423980 }, { "epoch": 2.520284608663088, "grad_norm": 1.1722605228424072, "learning_rate": 3.366025243175845e-05, "loss": 0.4843870162963867, "step": 423990 }, { "epoch": 2.5203440507397565, "grad_norm": 1.1236581802368164, "learning_rate": 3.3656955696450476e-05, "loss": 0.503969955444336, "step": 424000 }, { "epoch": 2.520403492816425, "grad_norm": 1.1843167543411255, "learning_rate": 3.365365932634265e-05, "loss": 0.49490156173706057, "step": 424010 }, { "epoch": 2.5204629348930934, "grad_norm": 1.0543266534805298, "learning_rate": 3.365036332145078e-05, "loss": 0.43597826957702634, "step": 424020 }, { "epoch": 2.520522376969762, "grad_norm": 1.481397032737732, "learning_rate": 3.364706768179063e-05, "loss": 0.48795356750488283, "step": 424030 }, { "epoch": 2.52058181904643, "grad_norm": 1.3118702173233032, "learning_rate": 3.364377240737796e-05, "loss": 0.44948816299438477, "step": 424040 }, { "epoch": 2.5206412611230986, "grad_norm": 1.1263983249664307, "learning_rate": 3.3640477498228515e-05, "loss": 0.48123464584350584, "step": 424050 }, { "epoch": 2.520700703199767, "grad_norm": 1.3702638149261475, "learning_rate": 3.363718295435809e-05, "loss": 0.4987939834594727, "step": 424060 }, { "epoch": 2.5207601452764354, "grad_norm": 1.51880943775177, "learning_rate": 3.363388877578238e-05, "loss": 0.5313574790954589, "step": 424070 }, { "epoch": 2.520819587353104, "grad_norm": 1.478509545326233, "learning_rate": 3.3630594962517236e-05, "loss": 0.4804689884185791, "step": 424080 }, { "epoch": 2.5208790294297723, "grad_norm": 1.3018734455108643, "learning_rate": 3.362730151457836e-05, "loss": 0.42774624824523927, "step": 424090 }, { "epoch": 2.5209384715064407, "grad_norm": 1.1929782629013062, "learning_rate": 3.3624008431981515e-05, "loss": 0.4858654022216797, "step": 424100 }, { "epoch": 2.520997913583109, "grad_norm": 1.3554742336273193, "learning_rate": 3.362071571474244e-05, "loss": 0.48810877799987795, "step": 424110 }, { "epoch": 2.521057355659777, "grad_norm": 0.97504723072052, "learning_rate": 3.361742336287692e-05, "loss": 0.44949588775634763, "step": 424120 }, { "epoch": 2.521116797736446, "grad_norm": 1.3076903820037842, "learning_rate": 3.361413137640067e-05, "loss": 0.4677897453308105, "step": 424130 }, { "epoch": 2.521176239813114, "grad_norm": 1.5366103649139404, "learning_rate": 3.361083975532944e-05, "loss": 0.5058079242706299, "step": 424140 }, { "epoch": 2.5212356818897828, "grad_norm": 0.9614367485046387, "learning_rate": 3.3607548499679004e-05, "loss": 0.44780821800231935, "step": 424150 }, { "epoch": 2.5212951239664507, "grad_norm": 1.2700828313827515, "learning_rate": 3.36042576094651e-05, "loss": 0.4544419288635254, "step": 424160 }, { "epoch": 2.521354566043119, "grad_norm": 1.2372835874557495, "learning_rate": 3.360096708470345e-05, "loss": 0.46474924087524416, "step": 424170 }, { "epoch": 2.5214140081197876, "grad_norm": 1.474246621131897, "learning_rate": 3.359767692540981e-05, "loss": 0.49855613708496094, "step": 424180 }, { "epoch": 2.521473450196456, "grad_norm": 1.322258710861206, "learning_rate": 3.359438713159991e-05, "loss": 0.493971586227417, "step": 424190 }, { "epoch": 2.5215328922731244, "grad_norm": 1.1038466691970825, "learning_rate": 3.359109770328948e-05, "loss": 0.4469186305999756, "step": 424200 }, { "epoch": 2.521592334349793, "grad_norm": 1.1514798402786255, "learning_rate": 3.3587808640494276e-05, "loss": 0.4841936111450195, "step": 424210 }, { "epoch": 2.521651776426461, "grad_norm": 1.233248233795166, "learning_rate": 3.3584519943230034e-05, "loss": 0.46015777587890627, "step": 424220 }, { "epoch": 2.5217112185031296, "grad_norm": 1.4526779651641846, "learning_rate": 3.358123161151249e-05, "loss": 0.49134073257446287, "step": 424230 }, { "epoch": 2.521770660579798, "grad_norm": 1.0912212133407593, "learning_rate": 3.357794364535734e-05, "loss": 0.4638932228088379, "step": 424240 }, { "epoch": 2.5218301026564665, "grad_norm": 1.1621307134628296, "learning_rate": 3.357465604478033e-05, "loss": 0.4888757705688477, "step": 424250 }, { "epoch": 2.521889544733135, "grad_norm": 1.13001549243927, "learning_rate": 3.35713688097972e-05, "loss": 0.4878434181213379, "step": 424260 }, { "epoch": 2.5219489868098033, "grad_norm": 1.2076764106750488, "learning_rate": 3.356808194042363e-05, "loss": 0.5069540977478028, "step": 424270 }, { "epoch": 2.5220084288864717, "grad_norm": 1.311587929725647, "learning_rate": 3.356479543667542e-05, "loss": 0.462736177444458, "step": 424280 }, { "epoch": 2.52206787096314, "grad_norm": 1.0740197896957397, "learning_rate": 3.356150929856825e-05, "loss": 0.4474388599395752, "step": 424290 }, { "epoch": 2.5221273130398085, "grad_norm": 1.2820290327072144, "learning_rate": 3.355822352611781e-05, "loss": 0.494290828704834, "step": 424300 }, { "epoch": 2.5221867551164765, "grad_norm": 1.2263877391815186, "learning_rate": 3.355493811933987e-05, "loss": 0.49323158264160155, "step": 424310 }, { "epoch": 2.5222461971931454, "grad_norm": 1.264310598373413, "learning_rate": 3.355165307825012e-05, "loss": 0.4575453758239746, "step": 424320 }, { "epoch": 2.5223056392698133, "grad_norm": 1.2280020713806152, "learning_rate": 3.3548368402864257e-05, "loss": 0.4921574592590332, "step": 424330 }, { "epoch": 2.522365081346482, "grad_norm": 1.2129032611846924, "learning_rate": 3.354508409319803e-05, "loss": 0.4429295539855957, "step": 424340 }, { "epoch": 2.52242452342315, "grad_norm": 1.4302504062652588, "learning_rate": 3.354180014926715e-05, "loss": 0.4829421043395996, "step": 424350 }, { "epoch": 2.5224839654998186, "grad_norm": 1.3213003873825073, "learning_rate": 3.353851657108731e-05, "loss": 0.5122313499450684, "step": 424360 }, { "epoch": 2.522543407576487, "grad_norm": 1.180661916732788, "learning_rate": 3.353523335867419e-05, "loss": 0.44749746322631834, "step": 424370 }, { "epoch": 2.5226028496531554, "grad_norm": 1.151841163635254, "learning_rate": 3.353195051204354e-05, "loss": 0.4753913402557373, "step": 424380 }, { "epoch": 2.522662291729824, "grad_norm": 1.3521714210510254, "learning_rate": 3.3528668031211045e-05, "loss": 0.46268696784973146, "step": 424390 }, { "epoch": 2.5227217338064922, "grad_norm": 1.6671786308288574, "learning_rate": 3.3525385916192396e-05, "loss": 0.5176507472991944, "step": 424400 }, { "epoch": 2.5227811758831606, "grad_norm": 1.310408353805542, "learning_rate": 3.352210416700337e-05, "loss": 0.46784043312072754, "step": 424410 }, { "epoch": 2.522840617959829, "grad_norm": 1.003021001815796, "learning_rate": 3.351882278365956e-05, "loss": 0.44861507415771484, "step": 424420 }, { "epoch": 2.5229000600364975, "grad_norm": 0.8810248970985413, "learning_rate": 3.3515541766176686e-05, "loss": 0.4668264389038086, "step": 424430 }, { "epoch": 2.522959502113166, "grad_norm": 1.7456856966018677, "learning_rate": 3.3512261114570484e-05, "loss": 0.455564022064209, "step": 424440 }, { "epoch": 2.5230189441898343, "grad_norm": 1.5831595659255981, "learning_rate": 3.350898082885664e-05, "loss": 0.5219922065734863, "step": 424450 }, { "epoch": 2.5230783862665027, "grad_norm": 1.139987826347351, "learning_rate": 3.350570090905084e-05, "loss": 0.44166107177734376, "step": 424460 }, { "epoch": 2.523137828343171, "grad_norm": 1.4871951341629028, "learning_rate": 3.350242135516876e-05, "loss": 0.4403530597686768, "step": 424470 }, { "epoch": 2.5231972704198395, "grad_norm": 1.3239033222198486, "learning_rate": 3.34991421672261e-05, "loss": 0.4698219299316406, "step": 424480 }, { "epoch": 2.523256712496508, "grad_norm": 1.4960299730300903, "learning_rate": 3.349586334523852e-05, "loss": 0.5095231056213378, "step": 424490 }, { "epoch": 2.523316154573176, "grad_norm": 1.6285951137542725, "learning_rate": 3.349258488922173e-05, "loss": 0.43713154792785647, "step": 424500 }, { "epoch": 2.523375596649845, "grad_norm": 1.3496370315551758, "learning_rate": 3.348930679919142e-05, "loss": 0.5002789497375488, "step": 424510 }, { "epoch": 2.5234350387265128, "grad_norm": 1.3421566486358643, "learning_rate": 3.348602907516328e-05, "loss": 0.4490135669708252, "step": 424520 }, { "epoch": 2.5234944808031816, "grad_norm": 1.4706943035125732, "learning_rate": 3.348275171715296e-05, "loss": 0.48893251419067385, "step": 424530 }, { "epoch": 2.5235539228798496, "grad_norm": 1.2665032148361206, "learning_rate": 3.3479474725176144e-05, "loss": 0.47267961502075195, "step": 424540 }, { "epoch": 2.523613364956518, "grad_norm": 1.331147313117981, "learning_rate": 3.347619809924852e-05, "loss": 0.4962337017059326, "step": 424550 }, { "epoch": 2.5236728070331864, "grad_norm": 0.9203386902809143, "learning_rate": 3.347292183938574e-05, "loss": 0.4344657897949219, "step": 424560 }, { "epoch": 2.523732249109855, "grad_norm": 1.2987195253372192, "learning_rate": 3.346964594560351e-05, "loss": 0.4908802032470703, "step": 424570 }, { "epoch": 2.5237916911865232, "grad_norm": 1.1928101778030396, "learning_rate": 3.3466370417917484e-05, "loss": 0.46871309280395507, "step": 424580 }, { "epoch": 2.5238511332631917, "grad_norm": 0.8633031845092773, "learning_rate": 3.346309525634332e-05, "loss": 0.4676973342895508, "step": 424590 }, { "epoch": 2.52391057533986, "grad_norm": 1.336534857749939, "learning_rate": 3.3459820460896704e-05, "loss": 0.4530631065368652, "step": 424600 }, { "epoch": 2.5239700174165285, "grad_norm": 1.1865192651748657, "learning_rate": 3.3456546031593305e-05, "loss": 0.4746112823486328, "step": 424610 }, { "epoch": 2.524029459493197, "grad_norm": 1.3033204078674316, "learning_rate": 3.3453271968448765e-05, "loss": 0.5110360145568847, "step": 424620 }, { "epoch": 2.5240889015698653, "grad_norm": 1.4558054208755493, "learning_rate": 3.3449998271478736e-05, "loss": 0.5289339065551758, "step": 424630 }, { "epoch": 2.5241483436465337, "grad_norm": 1.5367799997329712, "learning_rate": 3.344672494069891e-05, "loss": 0.46590251922607423, "step": 424640 }, { "epoch": 2.524207785723202, "grad_norm": 1.4613382816314697, "learning_rate": 3.344345197612495e-05, "loss": 0.4376387119293213, "step": 424650 }, { "epoch": 2.5242672277998706, "grad_norm": 1.086991548538208, "learning_rate": 3.344017937777249e-05, "loss": 0.48001580238342284, "step": 424660 }, { "epoch": 2.5243266698765385, "grad_norm": 1.1996381282806396, "learning_rate": 3.3436907145657186e-05, "loss": 0.46075801849365233, "step": 424670 }, { "epoch": 2.5243861119532074, "grad_norm": 1.450685739517212, "learning_rate": 3.3433635279794695e-05, "loss": 0.48432097434997556, "step": 424680 }, { "epoch": 2.5244455540298754, "grad_norm": 1.3982146978378296, "learning_rate": 3.3430363780200655e-05, "loss": 0.4375828742980957, "step": 424690 }, { "epoch": 2.524504996106544, "grad_norm": 1.5501224994659424, "learning_rate": 3.342709264689076e-05, "loss": 0.5049489974975586, "step": 424700 }, { "epoch": 2.524564438183212, "grad_norm": 1.245978593826294, "learning_rate": 3.342382187988062e-05, "loss": 0.5034934043884277, "step": 424710 }, { "epoch": 2.5246238802598806, "grad_norm": 1.1764440536499023, "learning_rate": 3.34205514791859e-05, "loss": 0.4604218006134033, "step": 424720 }, { "epoch": 2.524683322336549, "grad_norm": 1.2927964925765991, "learning_rate": 3.341728144482223e-05, "loss": 0.5032625198364258, "step": 424730 }, { "epoch": 2.5247427644132174, "grad_norm": 1.1233835220336914, "learning_rate": 3.3414011776805255e-05, "loss": 0.45592212677001953, "step": 424740 }, { "epoch": 2.524802206489886, "grad_norm": 1.5857356786727905, "learning_rate": 3.3410742475150616e-05, "loss": 0.4883152484893799, "step": 424750 }, { "epoch": 2.5248616485665543, "grad_norm": 1.3565595149993896, "learning_rate": 3.340747353987393e-05, "loss": 0.4721549987792969, "step": 424760 }, { "epoch": 2.5249210906432227, "grad_norm": 1.0076309442520142, "learning_rate": 3.3404204970990905e-05, "loss": 0.4666633605957031, "step": 424770 }, { "epoch": 2.524980532719891, "grad_norm": 1.280935525894165, "learning_rate": 3.340093676851712e-05, "loss": 0.452680778503418, "step": 424780 }, { "epoch": 2.5250399747965595, "grad_norm": 0.9767903089523315, "learning_rate": 3.339766893246821e-05, "loss": 0.4133000373840332, "step": 424790 }, { "epoch": 2.525099416873228, "grad_norm": 1.234071969985962, "learning_rate": 3.339440146285983e-05, "loss": 0.42853364944458006, "step": 424800 }, { "epoch": 2.5251588589498963, "grad_norm": 1.146453857421875, "learning_rate": 3.339113435970759e-05, "loss": 0.5125556945800781, "step": 424810 }, { "epoch": 2.5252183010265647, "grad_norm": 1.1427749395370483, "learning_rate": 3.338786762302711e-05, "loss": 0.4262566566467285, "step": 424820 }, { "epoch": 2.525277743103233, "grad_norm": 1.1938376426696777, "learning_rate": 3.338460125283406e-05, "loss": 0.46363301277160646, "step": 424830 }, { "epoch": 2.5253371851799016, "grad_norm": 1.0282458066940308, "learning_rate": 3.338133524914403e-05, "loss": 0.476195240020752, "step": 424840 }, { "epoch": 2.52539662725657, "grad_norm": 1.4260860681533813, "learning_rate": 3.3378069611972685e-05, "loss": 0.523629903793335, "step": 424850 }, { "epoch": 2.525456069333238, "grad_norm": 1.3171939849853516, "learning_rate": 3.3374804341335564e-05, "loss": 0.5222123146057129, "step": 424860 }, { "epoch": 2.525515511409907, "grad_norm": 1.2982709407806396, "learning_rate": 3.337153943724836e-05, "loss": 0.4429160594940186, "step": 424870 }, { "epoch": 2.525574953486575, "grad_norm": 1.5765184164047241, "learning_rate": 3.336827489972667e-05, "loss": 0.4965384483337402, "step": 424880 }, { "epoch": 2.5256343955632437, "grad_norm": 1.2507188320159912, "learning_rate": 3.336501072878609e-05, "loss": 0.426344108581543, "step": 424890 }, { "epoch": 2.5256938376399116, "grad_norm": 1.6806447505950928, "learning_rate": 3.3361746924442274e-05, "loss": 0.4530491828918457, "step": 424900 }, { "epoch": 2.52575327971658, "grad_norm": 1.123059630393982, "learning_rate": 3.335848348671083e-05, "loss": 0.4345227241516113, "step": 424910 }, { "epoch": 2.5258127217932484, "grad_norm": 1.2685942649841309, "learning_rate": 3.3355220415607324e-05, "loss": 0.4358982086181641, "step": 424920 }, { "epoch": 2.525872163869917, "grad_norm": 1.1688967943191528, "learning_rate": 3.3351957711147406e-05, "loss": 0.5305471897125245, "step": 424930 }, { "epoch": 2.5259316059465853, "grad_norm": 1.5186859369277954, "learning_rate": 3.3348695373346686e-05, "loss": 0.4764305591583252, "step": 424940 }, { "epoch": 2.5259910480232537, "grad_norm": 1.5596528053283691, "learning_rate": 3.3345433402220735e-05, "loss": 0.48988633155822753, "step": 424950 }, { "epoch": 2.526050490099922, "grad_norm": 1.2489970922470093, "learning_rate": 3.334217179778519e-05, "loss": 0.45639791488647463, "step": 424960 }, { "epoch": 2.5261099321765905, "grad_norm": 1.0485167503356934, "learning_rate": 3.333891056005566e-05, "loss": 0.45543689727783204, "step": 424970 }, { "epoch": 2.526169374253259, "grad_norm": 1.3048585653305054, "learning_rate": 3.333564968904771e-05, "loss": 0.4797943592071533, "step": 424980 }, { "epoch": 2.5262288163299274, "grad_norm": 1.4797635078430176, "learning_rate": 3.333238918477695e-05, "loss": 0.4487183094024658, "step": 424990 }, { "epoch": 2.5262882584065958, "grad_norm": 1.1119604110717773, "learning_rate": 3.332912904725899e-05, "loss": 0.46509370803833006, "step": 425000 }, { "epoch": 2.526347700483264, "grad_norm": 0.9668416380882263, "learning_rate": 3.3325869276509434e-05, "loss": 0.49946937561035154, "step": 425010 }, { "epoch": 2.5264071425599326, "grad_norm": 1.535390853881836, "learning_rate": 3.3322609872543855e-05, "loss": 0.5004009246826172, "step": 425020 }, { "epoch": 2.526466584636601, "grad_norm": 1.362214207649231, "learning_rate": 3.3319350835377863e-05, "loss": 0.5184818267822265, "step": 425030 }, { "epoch": 2.5265260267132694, "grad_norm": 1.3767248392105103, "learning_rate": 3.331609216502702e-05, "loss": 0.48450164794921874, "step": 425040 }, { "epoch": 2.5265854687899374, "grad_norm": 1.3350813388824463, "learning_rate": 3.331283386150692e-05, "loss": 0.44223670959472655, "step": 425050 }, { "epoch": 2.5266449108666063, "grad_norm": 1.216029405593872, "learning_rate": 3.330957592483318e-05, "loss": 0.47815542221069335, "step": 425060 }, { "epoch": 2.5267043529432742, "grad_norm": 1.5358778238296509, "learning_rate": 3.330631835502137e-05, "loss": 0.4416855812072754, "step": 425070 }, { "epoch": 2.526763795019943, "grad_norm": 1.3431206941604614, "learning_rate": 3.330306115208706e-05, "loss": 0.5045913696289063, "step": 425080 }, { "epoch": 2.526823237096611, "grad_norm": 1.329410195350647, "learning_rate": 3.329980431604585e-05, "loss": 0.5010349750518799, "step": 425090 }, { "epoch": 2.5268826791732795, "grad_norm": 1.3162593841552734, "learning_rate": 3.329654784691331e-05, "loss": 0.548038911819458, "step": 425100 }, { "epoch": 2.526942121249948, "grad_norm": 1.3062248229980469, "learning_rate": 3.3293291744705e-05, "loss": 0.46574816703796384, "step": 425110 }, { "epoch": 2.5270015633266163, "grad_norm": 1.2562339305877686, "learning_rate": 3.329003600943651e-05, "loss": 0.4779794692993164, "step": 425120 }, { "epoch": 2.5270610054032847, "grad_norm": 1.38671875, "learning_rate": 3.328678064112345e-05, "loss": 0.49009408950805666, "step": 425130 }, { "epoch": 2.527120447479953, "grad_norm": 1.2357343435287476, "learning_rate": 3.328352563978134e-05, "loss": 0.4577364921569824, "step": 425140 }, { "epoch": 2.5271798895566215, "grad_norm": 1.2753689289093018, "learning_rate": 3.328027100542578e-05, "loss": 0.45981802940368655, "step": 425150 }, { "epoch": 2.52723933163329, "grad_norm": 1.8066073656082153, "learning_rate": 3.3277016738072334e-05, "loss": 0.49593100547790525, "step": 425160 }, { "epoch": 2.5272987737099584, "grad_norm": 1.6377720832824707, "learning_rate": 3.327376283773657e-05, "loss": 0.4657007694244385, "step": 425170 }, { "epoch": 2.527358215786627, "grad_norm": 1.4399628639221191, "learning_rate": 3.327050930443402e-05, "loss": 0.4953589916229248, "step": 425180 }, { "epoch": 2.527417657863295, "grad_norm": 1.3296587467193604, "learning_rate": 3.3267256138180305e-05, "loss": 0.535439920425415, "step": 425190 }, { "epoch": 2.5274770999399636, "grad_norm": 1.284255027770996, "learning_rate": 3.3264003338990954e-05, "loss": 0.49522857666015624, "step": 425200 }, { "epoch": 2.527536542016632, "grad_norm": 1.4721873998641968, "learning_rate": 3.326075090688153e-05, "loss": 0.4922321796417236, "step": 425210 }, { "epoch": 2.5275959840933004, "grad_norm": 1.2066113948822021, "learning_rate": 3.3257498841867604e-05, "loss": 0.4438641548156738, "step": 425220 }, { "epoch": 2.527655426169969, "grad_norm": 1.654892086982727, "learning_rate": 3.325424714396472e-05, "loss": 0.4787919998168945, "step": 425230 }, { "epoch": 2.527714868246637, "grad_norm": 1.7057520151138306, "learning_rate": 3.325099581318845e-05, "loss": 0.4592252731323242, "step": 425240 }, { "epoch": 2.5277743103233057, "grad_norm": 1.3771508932113647, "learning_rate": 3.3247744849554304e-05, "loss": 0.509027624130249, "step": 425250 }, { "epoch": 2.5278337523999737, "grad_norm": 1.3839497566223145, "learning_rate": 3.3244494253077887e-05, "loss": 0.5074322700500489, "step": 425260 }, { "epoch": 2.5278931944766425, "grad_norm": 1.3094288110733032, "learning_rate": 3.3241244023774714e-05, "loss": 0.4541779041290283, "step": 425270 }, { "epoch": 2.5279526365533105, "grad_norm": 1.3669911623001099, "learning_rate": 3.323799416166036e-05, "loss": 0.46514172554016114, "step": 425280 }, { "epoch": 2.528012078629979, "grad_norm": 1.4972509145736694, "learning_rate": 3.3234744666750335e-05, "loss": 0.444075345993042, "step": 425290 }, { "epoch": 2.5280715207066473, "grad_norm": 1.3593157529830933, "learning_rate": 3.323149553906022e-05, "loss": 0.4542734622955322, "step": 425300 }, { "epoch": 2.5281309627833157, "grad_norm": 1.971031904220581, "learning_rate": 3.322824677860552e-05, "loss": 0.5295244693756104, "step": 425310 }, { "epoch": 2.528190404859984, "grad_norm": 1.4189735651016235, "learning_rate": 3.3224998385401816e-05, "loss": 0.4945277214050293, "step": 425320 }, { "epoch": 2.5282498469366526, "grad_norm": 1.489905834197998, "learning_rate": 3.322175035946463e-05, "loss": 0.4736498832702637, "step": 425330 }, { "epoch": 2.528309289013321, "grad_norm": 1.3534083366394043, "learning_rate": 3.321850270080953e-05, "loss": 0.49481992721557616, "step": 425340 }, { "epoch": 2.5283687310899894, "grad_norm": 1.2899084091186523, "learning_rate": 3.321525540945196e-05, "loss": 0.4777409076690674, "step": 425350 }, { "epoch": 2.528428173166658, "grad_norm": 1.0824003219604492, "learning_rate": 3.321200848540754e-05, "loss": 0.522767162322998, "step": 425360 }, { "epoch": 2.528487615243326, "grad_norm": 1.6056246757507324, "learning_rate": 3.320876192869179e-05, "loss": 0.520750904083252, "step": 425370 }, { "epoch": 2.5285470573199946, "grad_norm": 0.8371261954307556, "learning_rate": 3.3205515739320206e-05, "loss": 0.4579933643341064, "step": 425380 }, { "epoch": 2.528606499396663, "grad_norm": 1.428274154663086, "learning_rate": 3.320226991730835e-05, "loss": 0.4832883358001709, "step": 425390 }, { "epoch": 2.5286659414733315, "grad_norm": 1.6444754600524902, "learning_rate": 3.319902446267175e-05, "loss": 0.4568804740905762, "step": 425400 }, { "epoch": 2.5287253835499994, "grad_norm": 1.3209635019302368, "learning_rate": 3.319577937542588e-05, "loss": 0.45671896934509276, "step": 425410 }, { "epoch": 2.5287848256266683, "grad_norm": 1.070349097251892, "learning_rate": 3.319253465558633e-05, "loss": 0.4772913932800293, "step": 425420 }, { "epoch": 2.5288442677033363, "grad_norm": 1.3798856735229492, "learning_rate": 3.318929030316859e-05, "loss": 0.45955352783203124, "step": 425430 }, { "epoch": 2.528903709780005, "grad_norm": 1.0603299140930176, "learning_rate": 3.3186046318188194e-05, "loss": 0.4977848052978516, "step": 425440 }, { "epoch": 2.528963151856673, "grad_norm": 1.3106141090393066, "learning_rate": 3.318280270066061e-05, "loss": 0.41981215476989747, "step": 425450 }, { "epoch": 2.5290225939333415, "grad_norm": 1.3773248195648193, "learning_rate": 3.317955945060145e-05, "loss": 0.5298212051391602, "step": 425460 }, { "epoch": 2.52908203601001, "grad_norm": 1.3520268201828003, "learning_rate": 3.317631656802614e-05, "loss": 0.505734920501709, "step": 425470 }, { "epoch": 2.5291414780866783, "grad_norm": 1.6580641269683838, "learning_rate": 3.3173074052950216e-05, "loss": 0.43781180381774903, "step": 425480 }, { "epoch": 2.5292009201633467, "grad_norm": 1.3451495170593262, "learning_rate": 3.3169831905389215e-05, "loss": 0.4935136318206787, "step": 425490 }, { "epoch": 2.529260362240015, "grad_norm": 1.601317286491394, "learning_rate": 3.316659012535862e-05, "loss": 0.4804825782775879, "step": 425500 }, { "epoch": 2.5293198043166836, "grad_norm": 1.4228403568267822, "learning_rate": 3.3163348712873946e-05, "loss": 0.46196746826171875, "step": 425510 }, { "epoch": 2.529379246393352, "grad_norm": 1.371441125869751, "learning_rate": 3.316010766795072e-05, "loss": 0.4447275161743164, "step": 425520 }, { "epoch": 2.5294386884700204, "grad_norm": 1.5181481838226318, "learning_rate": 3.3156866990604416e-05, "loss": 0.49012451171875, "step": 425530 }, { "epoch": 2.529498130546689, "grad_norm": 1.6299914121627808, "learning_rate": 3.3153626680850536e-05, "loss": 0.4814610958099365, "step": 425540 }, { "epoch": 2.5295575726233572, "grad_norm": 1.4688540697097778, "learning_rate": 3.315038673870461e-05, "loss": 0.5121341705322265, "step": 425550 }, { "epoch": 2.5296170147000256, "grad_norm": 1.2586265802383423, "learning_rate": 3.314714716418211e-05, "loss": 0.5077304363250732, "step": 425560 }, { "epoch": 2.529676456776694, "grad_norm": 1.0187345743179321, "learning_rate": 3.314390795729855e-05, "loss": 0.47943954467773436, "step": 425570 }, { "epoch": 2.5297358988533625, "grad_norm": 1.1496959924697876, "learning_rate": 3.3140669118069415e-05, "loss": 0.47139248847961424, "step": 425580 }, { "epoch": 2.529795340930031, "grad_norm": 1.1567051410675049, "learning_rate": 3.3137430646510204e-05, "loss": 0.4434638977050781, "step": 425590 }, { "epoch": 2.529854783006699, "grad_norm": 1.1612917184829712, "learning_rate": 3.31341925426364e-05, "loss": 0.46983938217163085, "step": 425600 }, { "epoch": 2.5299142250833677, "grad_norm": 1.595947265625, "learning_rate": 3.3130954806463484e-05, "loss": 0.4756915092468262, "step": 425610 }, { "epoch": 2.5299736671600357, "grad_norm": 1.4295966625213623, "learning_rate": 3.312771743800698e-05, "loss": 0.4812169075012207, "step": 425620 }, { "epoch": 2.5300331092367045, "grad_norm": 1.0353596210479736, "learning_rate": 3.312448043728235e-05, "loss": 0.4477139949798584, "step": 425630 }, { "epoch": 2.5300925513133725, "grad_norm": 1.2415105104446411, "learning_rate": 3.312124380430508e-05, "loss": 0.4774333953857422, "step": 425640 }, { "epoch": 2.530151993390041, "grad_norm": 1.2955492734909058, "learning_rate": 3.311800753909066e-05, "loss": 0.5127702713012695, "step": 425650 }, { "epoch": 2.5302114354667093, "grad_norm": 1.4809818267822266, "learning_rate": 3.311477164165457e-05, "loss": 0.44632577896118164, "step": 425660 }, { "epoch": 2.5302708775433778, "grad_norm": 1.5881186723709106, "learning_rate": 3.311153611201226e-05, "loss": 0.5238077163696289, "step": 425670 }, { "epoch": 2.530330319620046, "grad_norm": 1.3251827955245972, "learning_rate": 3.310830095017925e-05, "loss": 0.44498538970947266, "step": 425680 }, { "epoch": 2.5303897616967146, "grad_norm": 1.4083303213119507, "learning_rate": 3.3105066156171005e-05, "loss": 0.4527588367462158, "step": 425690 }, { "epoch": 2.530449203773383, "grad_norm": 1.130508303642273, "learning_rate": 3.3101831730003e-05, "loss": 0.41736493110656736, "step": 425700 }, { "epoch": 2.5305086458500514, "grad_norm": 1.3592731952667236, "learning_rate": 3.3098597671690704e-05, "loss": 0.4627074718475342, "step": 425710 }, { "epoch": 2.53056808792672, "grad_norm": 1.4229274988174438, "learning_rate": 3.3095363981249574e-05, "loss": 0.48330936431884763, "step": 425720 }, { "epoch": 2.5306275300033882, "grad_norm": 1.2739464044570923, "learning_rate": 3.309213065869509e-05, "loss": 0.47534952163696287, "step": 425730 }, { "epoch": 2.5306869720800567, "grad_norm": 1.152764916419983, "learning_rate": 3.30888977040427e-05, "loss": 0.49425497055053713, "step": 425740 }, { "epoch": 2.530746414156725, "grad_norm": 1.4657130241394043, "learning_rate": 3.308566511730791e-05, "loss": 0.5527464866638183, "step": 425750 }, { "epoch": 2.5308058562333935, "grad_norm": 1.0707776546478271, "learning_rate": 3.308243289850616e-05, "loss": 0.43229923248291013, "step": 425760 }, { "epoch": 2.530865298310062, "grad_norm": 1.4052670001983643, "learning_rate": 3.307920104765292e-05, "loss": 0.4981518745422363, "step": 425770 }, { "epoch": 2.5309247403867303, "grad_norm": 1.5833505392074585, "learning_rate": 3.307596956476363e-05, "loss": 0.4632277488708496, "step": 425780 }, { "epoch": 2.5309841824633983, "grad_norm": 1.6821380853652954, "learning_rate": 3.307273844985379e-05, "loss": 0.5098184108734131, "step": 425790 }, { "epoch": 2.531043624540067, "grad_norm": 1.6143312454223633, "learning_rate": 3.3069507702938804e-05, "loss": 0.45886917114257814, "step": 425800 }, { "epoch": 2.531103066616735, "grad_norm": 1.355284571647644, "learning_rate": 3.306627732403414e-05, "loss": 0.4857296943664551, "step": 425810 }, { "epoch": 2.531162508693404, "grad_norm": 1.2484716176986694, "learning_rate": 3.3063047313155284e-05, "loss": 0.5026027679443359, "step": 425820 }, { "epoch": 2.531221950770072, "grad_norm": 1.4974786043167114, "learning_rate": 3.305981767031769e-05, "loss": 0.45180139541625974, "step": 425830 }, { "epoch": 2.5312813928467404, "grad_norm": 1.5565463304519653, "learning_rate": 3.305658839553674e-05, "loss": 0.5312578201293945, "step": 425840 }, { "epoch": 2.531340834923409, "grad_norm": 1.0584981441497803, "learning_rate": 3.305335948882794e-05, "loss": 0.4667510032653809, "step": 425850 }, { "epoch": 2.531400277000077, "grad_norm": 1.2190308570861816, "learning_rate": 3.3050130950206737e-05, "loss": 0.4909044742584229, "step": 425860 }, { "epoch": 2.5314597190767456, "grad_norm": 1.1070120334625244, "learning_rate": 3.3046902779688525e-05, "loss": 0.47490129470825193, "step": 425870 }, { "epoch": 2.531519161153414, "grad_norm": 1.180167555809021, "learning_rate": 3.30436749772888e-05, "loss": 0.49145355224609377, "step": 425880 }, { "epoch": 2.5315786032300824, "grad_norm": 1.6044903993606567, "learning_rate": 3.304044754302302e-05, "loss": 0.47319927215576174, "step": 425890 }, { "epoch": 2.531638045306751, "grad_norm": 1.067539095878601, "learning_rate": 3.303722047690653e-05, "loss": 0.47325935363769533, "step": 425900 }, { "epoch": 2.5316974873834193, "grad_norm": 1.5004127025604248, "learning_rate": 3.3033993778954866e-05, "loss": 0.48871822357177735, "step": 425910 }, { "epoch": 2.5317569294600877, "grad_norm": 1.7881213426589966, "learning_rate": 3.303076744918341e-05, "loss": 0.47201967239379883, "step": 425920 }, { "epoch": 2.531816371536756, "grad_norm": 1.3422422409057617, "learning_rate": 3.30275414876076e-05, "loss": 0.5047743320465088, "step": 425930 }, { "epoch": 2.5318758136134245, "grad_norm": 1.0760010480880737, "learning_rate": 3.302431589424287e-05, "loss": 0.4146824836730957, "step": 425940 }, { "epoch": 2.531935255690093, "grad_norm": 1.4549565315246582, "learning_rate": 3.30210906691047e-05, "loss": 0.5207852363586426, "step": 425950 }, { "epoch": 2.5319946977667613, "grad_norm": 1.0528877973556519, "learning_rate": 3.301786581220845e-05, "loss": 0.47503294944763186, "step": 425960 }, { "epoch": 2.5320541398434298, "grad_norm": 1.5384509563446045, "learning_rate": 3.301464132356955e-05, "loss": 0.4689064025878906, "step": 425970 }, { "epoch": 2.5321135819200977, "grad_norm": 1.6913578510284424, "learning_rate": 3.301141720320347e-05, "loss": 0.5052048683166503, "step": 425980 }, { "epoch": 2.5321730239967666, "grad_norm": 1.1063029766082764, "learning_rate": 3.300819345112561e-05, "loss": 0.47383651733398435, "step": 425990 }, { "epoch": 2.5322324660734346, "grad_norm": 1.6913472414016724, "learning_rate": 3.300497006735136e-05, "loss": 0.5268548011779786, "step": 426000 }, { "epoch": 2.532291908150103, "grad_norm": 1.1223735809326172, "learning_rate": 3.3001747051896226e-05, "loss": 0.4638523101806641, "step": 426010 }, { "epoch": 2.5323513502267714, "grad_norm": 1.1455633640289307, "learning_rate": 3.299852440477554e-05, "loss": 0.48737545013427735, "step": 426020 }, { "epoch": 2.53241079230344, "grad_norm": 1.6281157732009888, "learning_rate": 3.2995302126004734e-05, "loss": 0.5002066612243652, "step": 426030 }, { "epoch": 2.532470234380108, "grad_norm": 1.4922584295272827, "learning_rate": 3.299208021559926e-05, "loss": 0.4962170600891113, "step": 426040 }, { "epoch": 2.5325296764567766, "grad_norm": 1.4153062105178833, "learning_rate": 3.29888586735745e-05, "loss": 0.44986324310302733, "step": 426050 }, { "epoch": 2.532589118533445, "grad_norm": 1.0079665184020996, "learning_rate": 3.298563749994588e-05, "loss": 0.48496284484863283, "step": 426060 }, { "epoch": 2.5326485606101135, "grad_norm": 1.3007766008377075, "learning_rate": 3.29824166947288e-05, "loss": 0.5317225456237793, "step": 426070 }, { "epoch": 2.532708002686782, "grad_norm": 1.7045351266860962, "learning_rate": 3.297919625793867e-05, "loss": 0.5227356910705566, "step": 426080 }, { "epoch": 2.5327674447634503, "grad_norm": 1.1903854608535767, "learning_rate": 3.2975976189590895e-05, "loss": 0.4702142715454102, "step": 426090 }, { "epoch": 2.5328268868401187, "grad_norm": 1.2963539361953735, "learning_rate": 3.297275648970085e-05, "loss": 0.4797837734222412, "step": 426100 }, { "epoch": 2.532886328916787, "grad_norm": 1.4928832054138184, "learning_rate": 3.2969537158283994e-05, "loss": 0.4288607597351074, "step": 426110 }, { "epoch": 2.5329457709934555, "grad_norm": 1.380272388458252, "learning_rate": 3.2966318195355694e-05, "loss": 0.46040658950805663, "step": 426120 }, { "epoch": 2.533005213070124, "grad_norm": 1.1231220960617065, "learning_rate": 3.296309960093136e-05, "loss": 0.4535648822784424, "step": 426130 }, { "epoch": 2.5330646551467924, "grad_norm": 1.2181100845336914, "learning_rate": 3.295988137502637e-05, "loss": 0.529778528213501, "step": 426140 }, { "epoch": 2.5331240972234603, "grad_norm": 1.3648533821105957, "learning_rate": 3.295666351765614e-05, "loss": 0.4643234729766846, "step": 426150 }, { "epoch": 2.533183539300129, "grad_norm": 2.1005520820617676, "learning_rate": 3.295344602883603e-05, "loss": 0.46156158447265627, "step": 426160 }, { "epoch": 2.533242981376797, "grad_norm": 1.5532753467559814, "learning_rate": 3.295022890858148e-05, "loss": 0.5125890731811523, "step": 426170 }, { "epoch": 2.533302423453466, "grad_norm": 1.4739229679107666, "learning_rate": 3.2947012156907854e-05, "loss": 0.4673462390899658, "step": 426180 }, { "epoch": 2.533361865530134, "grad_norm": 1.4277769327163696, "learning_rate": 3.2943795773830525e-05, "loss": 0.4708517074584961, "step": 426190 }, { "epoch": 2.5334213076068024, "grad_norm": 1.2378000020980835, "learning_rate": 3.294057975936491e-05, "loss": 0.42868776321411134, "step": 426200 }, { "epoch": 2.533480749683471, "grad_norm": 1.0919902324676514, "learning_rate": 3.293736411352637e-05, "loss": 0.45990724563598634, "step": 426210 }, { "epoch": 2.5335401917601392, "grad_norm": 1.3331739902496338, "learning_rate": 3.2934148836330305e-05, "loss": 0.48746957778930666, "step": 426220 }, { "epoch": 2.5335996338368076, "grad_norm": 1.271321177482605, "learning_rate": 3.293093392779206e-05, "loss": 0.45528740882873536, "step": 426230 }, { "epoch": 2.533659075913476, "grad_norm": 1.2296552658081055, "learning_rate": 3.292771938792707e-05, "loss": 0.4443410873413086, "step": 426240 }, { "epoch": 2.5337185179901445, "grad_norm": 1.0554704666137695, "learning_rate": 3.2924505216750676e-05, "loss": 0.46486387252807615, "step": 426250 }, { "epoch": 2.533777960066813, "grad_norm": 1.1644874811172485, "learning_rate": 3.292129141427825e-05, "loss": 0.46868181228637695, "step": 426260 }, { "epoch": 2.5338374021434813, "grad_norm": 1.943489670753479, "learning_rate": 3.291807798052519e-05, "loss": 0.5342694759368897, "step": 426270 }, { "epoch": 2.5338968442201497, "grad_norm": 1.5219695568084717, "learning_rate": 3.291486491550685e-05, "loss": 0.4564981460571289, "step": 426280 }, { "epoch": 2.533956286296818, "grad_norm": 1.2329009771347046, "learning_rate": 3.2911652219238596e-05, "loss": 0.4641477108001709, "step": 426290 }, { "epoch": 2.5340157283734865, "grad_norm": 1.313315749168396, "learning_rate": 3.29084398917358e-05, "loss": 0.4449129581451416, "step": 426300 }, { "epoch": 2.534075170450155, "grad_norm": 1.374284267425537, "learning_rate": 3.290522793301385e-05, "loss": 0.4344050407409668, "step": 426310 }, { "epoch": 2.5341346125268234, "grad_norm": 1.590040683746338, "learning_rate": 3.2902016343088095e-05, "loss": 0.4678650856018066, "step": 426320 }, { "epoch": 2.534194054603492, "grad_norm": 1.1146305799484253, "learning_rate": 3.289880512197389e-05, "loss": 0.46233625411987306, "step": 426330 }, { "epoch": 2.5342534966801598, "grad_norm": 1.2491108179092407, "learning_rate": 3.289559426968661e-05, "loss": 0.4704317092895508, "step": 426340 }, { "epoch": 2.5343129387568286, "grad_norm": 1.2169069051742554, "learning_rate": 3.2892383786241613e-05, "loss": 0.46377315521240237, "step": 426350 }, { "epoch": 2.5343723808334966, "grad_norm": 1.353050947189331, "learning_rate": 3.288917367165423e-05, "loss": 0.4989001274108887, "step": 426360 }, { "epoch": 2.5344318229101654, "grad_norm": 1.307943344116211, "learning_rate": 3.288596392593985e-05, "loss": 0.4663553237915039, "step": 426370 }, { "epoch": 2.5344912649868334, "grad_norm": 1.5698703527450562, "learning_rate": 3.288275454911385e-05, "loss": 0.5187949180603028, "step": 426380 }, { "epoch": 2.534550707063502, "grad_norm": 1.3684937953948975, "learning_rate": 3.28795455411915e-05, "loss": 0.485123348236084, "step": 426390 }, { "epoch": 2.5346101491401702, "grad_norm": 1.5233933925628662, "learning_rate": 3.287633690218823e-05, "loss": 0.4872729301452637, "step": 426400 }, { "epoch": 2.5346695912168387, "grad_norm": 1.2107547521591187, "learning_rate": 3.287312863211936e-05, "loss": 0.4824066162109375, "step": 426410 }, { "epoch": 2.534729033293507, "grad_norm": 1.7142456769943237, "learning_rate": 3.286992073100024e-05, "loss": 0.433908748626709, "step": 426420 }, { "epoch": 2.5347884753701755, "grad_norm": 1.5550856590270996, "learning_rate": 3.286671319884618e-05, "loss": 0.447313117980957, "step": 426430 }, { "epoch": 2.534847917446844, "grad_norm": 1.3065773248672485, "learning_rate": 3.28635060356726e-05, "loss": 0.4827850818634033, "step": 426440 }, { "epoch": 2.5349073595235123, "grad_norm": 1.0956366062164307, "learning_rate": 3.28602992414948e-05, "loss": 0.44164528846740725, "step": 426450 }, { "epoch": 2.5349668016001807, "grad_norm": 1.2440563440322876, "learning_rate": 3.285709281632807e-05, "loss": 0.42355637550354003, "step": 426460 }, { "epoch": 2.535026243676849, "grad_norm": 1.2076867818832397, "learning_rate": 3.2853886760187834e-05, "loss": 0.4113480091094971, "step": 426470 }, { "epoch": 2.5350856857535176, "grad_norm": 1.318739652633667, "learning_rate": 3.285068107308938e-05, "loss": 0.5223330497741699, "step": 426480 }, { "epoch": 2.535145127830186, "grad_norm": 1.3700506687164307, "learning_rate": 3.284747575504804e-05, "loss": 0.4358646392822266, "step": 426490 }, { "epoch": 2.5352045699068544, "grad_norm": 1.2271366119384766, "learning_rate": 3.28442708060792e-05, "loss": 0.4477898597717285, "step": 426500 }, { "epoch": 2.535264011983523, "grad_norm": 1.0219311714172363, "learning_rate": 3.284106622619815e-05, "loss": 0.42861356735229494, "step": 426510 }, { "epoch": 2.535323454060191, "grad_norm": 1.2779139280319214, "learning_rate": 3.283786201542018e-05, "loss": 0.42725186347961425, "step": 426520 }, { "epoch": 2.535382896136859, "grad_norm": 1.035854697227478, "learning_rate": 3.28346581737607e-05, "loss": 0.457842493057251, "step": 426530 }, { "epoch": 2.535442338213528, "grad_norm": 1.3321170806884766, "learning_rate": 3.2831454701234995e-05, "loss": 0.49068102836608884, "step": 426540 }, { "epoch": 2.535501780290196, "grad_norm": 1.2995059490203857, "learning_rate": 3.282825159785837e-05, "loss": 0.4456171035766602, "step": 426550 }, { "epoch": 2.535561222366865, "grad_norm": 1.209099292755127, "learning_rate": 3.28250488636462e-05, "loss": 0.456365966796875, "step": 426560 }, { "epoch": 2.535620664443533, "grad_norm": 1.4179903268814087, "learning_rate": 3.282184649861376e-05, "loss": 0.463715934753418, "step": 426570 }, { "epoch": 2.5356801065202013, "grad_norm": 1.3285959959030151, "learning_rate": 3.281864450277639e-05, "loss": 0.5140287399291992, "step": 426580 }, { "epoch": 2.5357395485968697, "grad_norm": 1.3875210285186768, "learning_rate": 3.281544287614937e-05, "loss": 0.4663740634918213, "step": 426590 }, { "epoch": 2.535798990673538, "grad_norm": 1.4722787141799927, "learning_rate": 3.281224161874808e-05, "loss": 0.5079155445098877, "step": 426600 }, { "epoch": 2.5358584327502065, "grad_norm": 1.5644086599349976, "learning_rate": 3.2809040730587784e-05, "loss": 0.4778099060058594, "step": 426610 }, { "epoch": 2.535917874826875, "grad_norm": 1.5789836645126343, "learning_rate": 3.2805840211683826e-05, "loss": 0.45444021224975584, "step": 426620 }, { "epoch": 2.5359773169035433, "grad_norm": 1.6093196868896484, "learning_rate": 3.28026400620515e-05, "loss": 0.5408049583435058, "step": 426630 }, { "epoch": 2.5360367589802117, "grad_norm": 0.9054425954818726, "learning_rate": 3.2799440281706115e-05, "loss": 0.484559154510498, "step": 426640 }, { "epoch": 2.53609620105688, "grad_norm": 1.456964135169983, "learning_rate": 3.279624087066298e-05, "loss": 0.567811393737793, "step": 426650 }, { "epoch": 2.5361556431335486, "grad_norm": 1.3739145994186401, "learning_rate": 3.2793041828937364e-05, "loss": 0.4611471176147461, "step": 426660 }, { "epoch": 2.536215085210217, "grad_norm": 1.4283908605575562, "learning_rate": 3.278984315654464e-05, "loss": 0.51378493309021, "step": 426670 }, { "epoch": 2.5362745272868854, "grad_norm": 0.9814083576202393, "learning_rate": 3.278664485350006e-05, "loss": 0.4559167385101318, "step": 426680 }, { "epoch": 2.536333969363554, "grad_norm": 1.4092926979064941, "learning_rate": 3.278344691981895e-05, "loss": 0.44849519729614257, "step": 426690 }, { "epoch": 2.5363934114402222, "grad_norm": 1.4418137073516846, "learning_rate": 3.278024935551659e-05, "loss": 0.4970046043395996, "step": 426700 }, { "epoch": 2.5364528535168906, "grad_norm": 1.1351004838943481, "learning_rate": 3.277705216060828e-05, "loss": 0.4397110939025879, "step": 426710 }, { "epoch": 2.5365122955935586, "grad_norm": 1.7952300310134888, "learning_rate": 3.27738553351093e-05, "loss": 0.46962294578552244, "step": 426720 }, { "epoch": 2.5365717376702275, "grad_norm": 1.0600793361663818, "learning_rate": 3.277065887903497e-05, "loss": 0.45922260284423827, "step": 426730 }, { "epoch": 2.5366311797468954, "grad_norm": 1.0167121887207031, "learning_rate": 3.276746279240058e-05, "loss": 0.46568613052368163, "step": 426740 }, { "epoch": 2.536690621823564, "grad_norm": 0.8958787322044373, "learning_rate": 3.276426707522141e-05, "loss": 0.43709602355957033, "step": 426750 }, { "epoch": 2.5367500639002323, "grad_norm": 1.0329201221466064, "learning_rate": 3.2761071727512724e-05, "loss": 0.4701563358306885, "step": 426760 }, { "epoch": 2.5368095059769007, "grad_norm": 1.515282392501831, "learning_rate": 3.275787674928985e-05, "loss": 0.508494758605957, "step": 426770 }, { "epoch": 2.536868948053569, "grad_norm": 1.2447161674499512, "learning_rate": 3.275468214056805e-05, "loss": 0.46371002197265626, "step": 426780 }, { "epoch": 2.5369283901302375, "grad_norm": 1.367301344871521, "learning_rate": 3.275148790136257e-05, "loss": 0.46280632019042967, "step": 426790 }, { "epoch": 2.536987832206906, "grad_norm": 1.259579062461853, "learning_rate": 3.2748294031688766e-05, "loss": 0.4844329833984375, "step": 426800 }, { "epoch": 2.5370472742835743, "grad_norm": 0.9539769291877747, "learning_rate": 3.274510053156187e-05, "loss": 0.49384765625, "step": 426810 }, { "epoch": 2.5371067163602428, "grad_norm": 1.3437155485153198, "learning_rate": 3.2741907400997166e-05, "loss": 0.4874138832092285, "step": 426820 }, { "epoch": 2.537166158436911, "grad_norm": 1.310894250869751, "learning_rate": 3.2738714640009927e-05, "loss": 0.47698607444763186, "step": 426830 }, { "epoch": 2.5372256005135796, "grad_norm": 1.5383780002593994, "learning_rate": 3.2735522248615424e-05, "loss": 0.5979100227355957, "step": 426840 }, { "epoch": 2.537285042590248, "grad_norm": 1.4563143253326416, "learning_rate": 3.2732330226828925e-05, "loss": 0.43538694381713866, "step": 426850 }, { "epoch": 2.5373444846669164, "grad_norm": 1.50169837474823, "learning_rate": 3.272913857466571e-05, "loss": 0.5278400421142578, "step": 426860 }, { "epoch": 2.537403926743585, "grad_norm": 1.3963967561721802, "learning_rate": 3.272594729214106e-05, "loss": 0.49668397903442385, "step": 426870 }, { "epoch": 2.5374633688202533, "grad_norm": 1.6835137605667114, "learning_rate": 3.2722756379270214e-05, "loss": 0.45693235397338866, "step": 426880 }, { "epoch": 2.537522810896921, "grad_norm": 1.2960649728775024, "learning_rate": 3.2719565836068446e-05, "loss": 0.4796875, "step": 426890 }, { "epoch": 2.53758225297359, "grad_norm": 1.2627134323120117, "learning_rate": 3.2716375662551024e-05, "loss": 0.44481348991394043, "step": 426900 }, { "epoch": 2.537641695050258, "grad_norm": 1.1411913633346558, "learning_rate": 3.27131858587332e-05, "loss": 0.47669525146484376, "step": 426910 }, { "epoch": 2.537701137126927, "grad_norm": 1.247207760810852, "learning_rate": 3.2709996424630226e-05, "loss": 0.43166117668151854, "step": 426920 }, { "epoch": 2.537760579203595, "grad_norm": 1.1272823810577393, "learning_rate": 3.270680736025737e-05, "loss": 0.4502420902252197, "step": 426930 }, { "epoch": 2.5378200212802633, "grad_norm": 1.2002301216125488, "learning_rate": 3.270361866562993e-05, "loss": 0.45414342880249026, "step": 426940 }, { "epoch": 2.5378794633569317, "grad_norm": 1.6594728231430054, "learning_rate": 3.2700430340763074e-05, "loss": 0.5378501892089844, "step": 426950 }, { "epoch": 2.5379389054336, "grad_norm": 1.5250041484832764, "learning_rate": 3.269724238567211e-05, "loss": 0.5017879962921142, "step": 426960 }, { "epoch": 2.5379983475102685, "grad_norm": 1.3671704530715942, "learning_rate": 3.2694054800372284e-05, "loss": 0.4919741630554199, "step": 426970 }, { "epoch": 2.538057789586937, "grad_norm": 1.2368676662445068, "learning_rate": 3.269086758487882e-05, "loss": 0.4892565250396729, "step": 426980 }, { "epoch": 2.5381172316636054, "grad_norm": 1.3375720977783203, "learning_rate": 3.2687680739207e-05, "loss": 0.47133865356445315, "step": 426990 }, { "epoch": 2.538176673740274, "grad_norm": 1.2836575508117676, "learning_rate": 3.2684494263372046e-05, "loss": 0.557978630065918, "step": 427000 }, { "epoch": 2.538236115816942, "grad_norm": 1.5219874382019043, "learning_rate": 3.268130815738918e-05, "loss": 0.5756298065185547, "step": 427010 }, { "epoch": 2.5382955578936106, "grad_norm": 1.2849481105804443, "learning_rate": 3.2678122421273695e-05, "loss": 0.4908768653869629, "step": 427020 }, { "epoch": 2.538354999970279, "grad_norm": 1.0371326208114624, "learning_rate": 3.2674937055040786e-05, "loss": 0.48052706718444826, "step": 427030 }, { "epoch": 2.5384144420469474, "grad_norm": 1.330930233001709, "learning_rate": 3.2671752058705716e-05, "loss": 0.4881392478942871, "step": 427040 }, { "epoch": 2.538473884123616, "grad_norm": 1.4252387285232544, "learning_rate": 3.266856743228372e-05, "loss": 0.529726219177246, "step": 427050 }, { "epoch": 2.5385333262002843, "grad_norm": 1.3283637762069702, "learning_rate": 3.2665383175790034e-05, "loss": 0.4893671989440918, "step": 427060 }, { "epoch": 2.5385927682769527, "grad_norm": 1.0304368734359741, "learning_rate": 3.266219928923986e-05, "loss": 0.4643721580505371, "step": 427070 }, { "epoch": 2.5386522103536207, "grad_norm": 1.2879513502120972, "learning_rate": 3.265901577264844e-05, "loss": 0.4828857421875, "step": 427080 }, { "epoch": 2.5387116524302895, "grad_norm": 1.168656349182129, "learning_rate": 3.265583262603103e-05, "loss": 0.4599442481994629, "step": 427090 }, { "epoch": 2.5387710945069575, "grad_norm": 1.18610680103302, "learning_rate": 3.2652649849402844e-05, "loss": 0.5022113800048829, "step": 427100 }, { "epoch": 2.5388305365836263, "grad_norm": 1.1659713983535767, "learning_rate": 3.2649467442779103e-05, "loss": 0.4544057369232178, "step": 427110 }, { "epoch": 2.5388899786602943, "grad_norm": 1.1984333992004395, "learning_rate": 3.2646285406175024e-05, "loss": 0.4127218246459961, "step": 427120 }, { "epoch": 2.5389494207369627, "grad_norm": 1.734929084777832, "learning_rate": 3.264310373960584e-05, "loss": 0.47592926025390625, "step": 427130 }, { "epoch": 2.539008862813631, "grad_norm": 1.427345871925354, "learning_rate": 3.2639922443086776e-05, "loss": 0.5168396472930908, "step": 427140 }, { "epoch": 2.5390683048902996, "grad_norm": 0.9356791973114014, "learning_rate": 3.263674151663302e-05, "loss": 0.4673168182373047, "step": 427150 }, { "epoch": 2.539127746966968, "grad_norm": 1.20917546749115, "learning_rate": 3.2633560960259815e-05, "loss": 0.47514801025390624, "step": 427160 }, { "epoch": 2.5391871890436364, "grad_norm": 1.3540713787078857, "learning_rate": 3.2630380773982384e-05, "loss": 0.5152963638305664, "step": 427170 }, { "epoch": 2.539246631120305, "grad_norm": 1.31299889087677, "learning_rate": 3.262720095781592e-05, "loss": 0.49303760528564455, "step": 427180 }, { "epoch": 2.539306073196973, "grad_norm": 1.4487411975860596, "learning_rate": 3.262402151177564e-05, "loss": 0.523833179473877, "step": 427190 }, { "epoch": 2.5393655152736416, "grad_norm": 1.5933847427368164, "learning_rate": 3.2620842435876764e-05, "loss": 0.4953619003295898, "step": 427200 }, { "epoch": 2.53942495735031, "grad_norm": 1.5031591653823853, "learning_rate": 3.2617663730134476e-05, "loss": 0.49977893829345704, "step": 427210 }, { "epoch": 2.5394843994269785, "grad_norm": 1.3621766567230225, "learning_rate": 3.261448539456399e-05, "loss": 0.47835140228271483, "step": 427220 }, { "epoch": 2.539543841503647, "grad_norm": 1.5293891429901123, "learning_rate": 3.261130742918054e-05, "loss": 0.4913175582885742, "step": 427230 }, { "epoch": 2.5396032835803153, "grad_norm": 1.7732561826705933, "learning_rate": 3.260812983399929e-05, "loss": 0.5049795627593994, "step": 427240 }, { "epoch": 2.5396627256569837, "grad_norm": 1.0905239582061768, "learning_rate": 3.260495260903546e-05, "loss": 0.5190894126892089, "step": 427250 }, { "epoch": 2.539722167733652, "grad_norm": 1.1256654262542725, "learning_rate": 3.260177575430424e-05, "loss": 0.4724290370941162, "step": 427260 }, { "epoch": 2.53978160981032, "grad_norm": 1.5196889638900757, "learning_rate": 3.259859926982084e-05, "loss": 0.4673287391662598, "step": 427270 }, { "epoch": 2.539841051886989, "grad_norm": 1.1148838996887207, "learning_rate": 3.2595423155600426e-05, "loss": 0.4950078010559082, "step": 427280 }, { "epoch": 2.539900493963657, "grad_norm": 1.038246750831604, "learning_rate": 3.2592247411658214e-05, "loss": 0.5110104560852051, "step": 427290 }, { "epoch": 2.5399599360403258, "grad_norm": 1.5440473556518555, "learning_rate": 3.258907203800941e-05, "loss": 0.45655531883239747, "step": 427300 }, { "epoch": 2.5400193781169937, "grad_norm": 1.467339277267456, "learning_rate": 3.2585897034669175e-05, "loss": 0.5097290992736816, "step": 427310 }, { "epoch": 2.540078820193662, "grad_norm": 1.4926631450653076, "learning_rate": 3.258272240165272e-05, "loss": 0.5280928611755371, "step": 427320 }, { "epoch": 2.5401382622703306, "grad_norm": 1.4700658321380615, "learning_rate": 3.2579548138975216e-05, "loss": 0.4445025444030762, "step": 427330 }, { "epoch": 2.540197704346999, "grad_norm": 1.2350738048553467, "learning_rate": 3.257637424665184e-05, "loss": 0.44846858978271487, "step": 427340 }, { "epoch": 2.5402571464236674, "grad_norm": 1.1791229248046875, "learning_rate": 3.25732007246978e-05, "loss": 0.47464442253112793, "step": 427350 }, { "epoch": 2.540316588500336, "grad_norm": 1.593060851097107, "learning_rate": 3.257002757312827e-05, "loss": 0.43287363052368166, "step": 427360 }, { "epoch": 2.5403760305770042, "grad_norm": 1.4384746551513672, "learning_rate": 3.256685479195842e-05, "loss": 0.4060720443725586, "step": 427370 }, { "epoch": 2.5404354726536726, "grad_norm": 1.0186296701431274, "learning_rate": 3.256368238120342e-05, "loss": 0.40387396812438964, "step": 427380 }, { "epoch": 2.540494914730341, "grad_norm": 1.3619190454483032, "learning_rate": 3.256051034087847e-05, "loss": 0.44472684860229494, "step": 427390 }, { "epoch": 2.5405543568070095, "grad_norm": 1.4764028787612915, "learning_rate": 3.255733867099873e-05, "loss": 0.4391763210296631, "step": 427400 }, { "epoch": 2.540613798883678, "grad_norm": 1.373335361480713, "learning_rate": 3.2554167371579345e-05, "loss": 0.4332877635955811, "step": 427410 }, { "epoch": 2.5406732409603463, "grad_norm": 1.4036669731140137, "learning_rate": 3.255099644263555e-05, "loss": 0.3895565986633301, "step": 427420 }, { "epoch": 2.5407326830370147, "grad_norm": 1.650023102760315, "learning_rate": 3.254782588418249e-05, "loss": 0.47283191680908204, "step": 427430 }, { "epoch": 2.540792125113683, "grad_norm": 1.2835211753845215, "learning_rate": 3.254465569623527e-05, "loss": 0.46010770797729494, "step": 427440 }, { "epoch": 2.5408515671903515, "grad_norm": 1.041277289390564, "learning_rate": 3.254148587880913e-05, "loss": 0.47477078437805176, "step": 427450 }, { "epoch": 2.5409110092670195, "grad_norm": 1.2197576761245728, "learning_rate": 3.2538316431919214e-05, "loss": 0.4911952972412109, "step": 427460 }, { "epoch": 2.5409704513436884, "grad_norm": 1.384645700454712, "learning_rate": 3.253514735558065e-05, "loss": 0.48686704635620115, "step": 427470 }, { "epoch": 2.5410298934203563, "grad_norm": 1.239037036895752, "learning_rate": 3.253197864980865e-05, "loss": 0.5087519645690918, "step": 427480 }, { "epoch": 2.5410893354970248, "grad_norm": 1.059718132019043, "learning_rate": 3.252881031461836e-05, "loss": 0.5076605319976807, "step": 427490 }, { "epoch": 2.541148777573693, "grad_norm": 1.106736660003662, "learning_rate": 3.252564235002491e-05, "loss": 0.5159024238586426, "step": 427500 }, { "epoch": 2.5412082196503616, "grad_norm": 1.4644649028778076, "learning_rate": 3.252247475604345e-05, "loss": 0.5012889385223389, "step": 427510 }, { "epoch": 2.54126766172703, "grad_norm": 1.2977803945541382, "learning_rate": 3.251930753268917e-05, "loss": 0.5126772880554199, "step": 427520 }, { "epoch": 2.5413271038036984, "grad_norm": 1.3088936805725098, "learning_rate": 3.25161406799772e-05, "loss": 0.4817024230957031, "step": 427530 }, { "epoch": 2.541386545880367, "grad_norm": 1.0305243730545044, "learning_rate": 3.2512974197922666e-05, "loss": 0.5197466850280762, "step": 427540 }, { "epoch": 2.5414459879570352, "grad_norm": 1.310582160949707, "learning_rate": 3.2509808086540794e-05, "loss": 0.4620218753814697, "step": 427550 }, { "epoch": 2.5415054300337037, "grad_norm": 1.4379152059555054, "learning_rate": 3.2506642345846635e-05, "loss": 0.5097097873687744, "step": 427560 }, { "epoch": 2.541564872110372, "grad_norm": 1.4408904314041138, "learning_rate": 3.2503476975855375e-05, "loss": 0.42919187545776366, "step": 427570 }, { "epoch": 2.5416243141870405, "grad_norm": 1.2034462690353394, "learning_rate": 3.2500311976582165e-05, "loss": 0.44864044189453123, "step": 427580 }, { "epoch": 2.541683756263709, "grad_norm": 1.5623589754104614, "learning_rate": 3.249714734804213e-05, "loss": 0.5198549747467041, "step": 427590 }, { "epoch": 2.5417431983403773, "grad_norm": 1.303728699684143, "learning_rate": 3.249398309025041e-05, "loss": 0.44013442993164065, "step": 427600 }, { "epoch": 2.5418026404170457, "grad_norm": 1.2704800367355347, "learning_rate": 3.2490819203222174e-05, "loss": 0.5231957912445069, "step": 427610 }, { "epoch": 2.541862082493714, "grad_norm": 1.212382435798645, "learning_rate": 3.2487655686972513e-05, "loss": 0.4817957401275635, "step": 427620 }, { "epoch": 2.541921524570382, "grad_norm": 1.5018113851547241, "learning_rate": 3.248449254151657e-05, "loss": 0.5278451919555665, "step": 427630 }, { "epoch": 2.541980966647051, "grad_norm": 1.452885389328003, "learning_rate": 3.248132976686947e-05, "loss": 0.5090244770050049, "step": 427640 }, { "epoch": 2.542040408723719, "grad_norm": 1.1567257642745972, "learning_rate": 3.2478167363046365e-05, "loss": 0.430327033996582, "step": 427650 }, { "epoch": 2.542099850800388, "grad_norm": 1.7421132326126099, "learning_rate": 3.247500533006238e-05, "loss": 0.5592202186584473, "step": 427660 }, { "epoch": 2.5421592928770558, "grad_norm": 1.247565507888794, "learning_rate": 3.2471843667932636e-05, "loss": 0.4435729026794434, "step": 427670 }, { "epoch": 2.542218734953724, "grad_norm": 1.0234723091125488, "learning_rate": 3.2468682376672245e-05, "loss": 0.4684091567993164, "step": 427680 }, { "epoch": 2.5422781770303926, "grad_norm": 0.9900766015052795, "learning_rate": 3.246552145629636e-05, "loss": 0.4778292655944824, "step": 427690 }, { "epoch": 2.542337619107061, "grad_norm": 1.3322330713272095, "learning_rate": 3.2462360906820036e-05, "loss": 0.5207455635070801, "step": 427700 }, { "epoch": 2.5423970611837294, "grad_norm": 1.3329579830169678, "learning_rate": 3.245920072825848e-05, "loss": 0.4702929496765137, "step": 427710 }, { "epoch": 2.542456503260398, "grad_norm": 1.3276530504226685, "learning_rate": 3.245604092062676e-05, "loss": 0.44635543823242185, "step": 427720 }, { "epoch": 2.5425159453370663, "grad_norm": 1.415788173675537, "learning_rate": 3.245288148393999e-05, "loss": 0.45295066833496095, "step": 427730 }, { "epoch": 2.5425753874137347, "grad_norm": 0.9488295912742615, "learning_rate": 3.24497224182133e-05, "loss": 0.5203893184661865, "step": 427740 }, { "epoch": 2.542634829490403, "grad_norm": 1.5528019666671753, "learning_rate": 3.24465637234618e-05, "loss": 0.4850550651550293, "step": 427750 }, { "epoch": 2.5426942715670715, "grad_norm": 0.9612798690795898, "learning_rate": 3.2443405399700586e-05, "loss": 0.5157844543457031, "step": 427760 }, { "epoch": 2.54275371364374, "grad_norm": 1.1100455522537231, "learning_rate": 3.244024744694475e-05, "loss": 0.43989028930664065, "step": 427770 }, { "epoch": 2.5428131557204083, "grad_norm": 1.5262506008148193, "learning_rate": 3.2437089865209446e-05, "loss": 0.5078627109527588, "step": 427780 }, { "epoch": 2.5428725977970768, "grad_norm": 1.2622350454330444, "learning_rate": 3.243393265450976e-05, "loss": 0.4120069980621338, "step": 427790 }, { "epoch": 2.542932039873745, "grad_norm": 1.442678689956665, "learning_rate": 3.243077581486079e-05, "loss": 0.456010627746582, "step": 427800 }, { "epoch": 2.5429914819504136, "grad_norm": 1.0478253364562988, "learning_rate": 3.2427619346277646e-05, "loss": 0.4643994331359863, "step": 427810 }, { "epoch": 2.5430509240270815, "grad_norm": 1.5112793445587158, "learning_rate": 3.242446324877541e-05, "loss": 0.4603863716125488, "step": 427820 }, { "epoch": 2.5431103661037504, "grad_norm": 1.2046165466308594, "learning_rate": 3.242130752236918e-05, "loss": 0.4306267261505127, "step": 427830 }, { "epoch": 2.5431698081804184, "grad_norm": 1.1248645782470703, "learning_rate": 3.2418152167074074e-05, "loss": 0.4592794418334961, "step": 427840 }, { "epoch": 2.5432292502570872, "grad_norm": 1.029174566268921, "learning_rate": 3.241499718290517e-05, "loss": 0.44452600479125975, "step": 427850 }, { "epoch": 2.543288692333755, "grad_norm": 1.1941255331039429, "learning_rate": 3.241184256987757e-05, "loss": 0.48925132751464845, "step": 427860 }, { "epoch": 2.5433481344104236, "grad_norm": 1.1705867052078247, "learning_rate": 3.240868832800636e-05, "loss": 0.5034501075744628, "step": 427870 }, { "epoch": 2.543407576487092, "grad_norm": 1.374881386756897, "learning_rate": 3.240553445730663e-05, "loss": 0.5086184978485108, "step": 427880 }, { "epoch": 2.5434670185637605, "grad_norm": 1.1871943473815918, "learning_rate": 3.2402380957793454e-05, "loss": 0.5117173194885254, "step": 427890 }, { "epoch": 2.543526460640429, "grad_norm": 1.5250530242919922, "learning_rate": 3.2399227829481923e-05, "loss": 0.4514963150024414, "step": 427900 }, { "epoch": 2.5435859027170973, "grad_norm": 1.021496295928955, "learning_rate": 3.239607507238714e-05, "loss": 0.5315840721130372, "step": 427910 }, { "epoch": 2.5436453447937657, "grad_norm": 1.3539342880249023, "learning_rate": 3.2392922686524195e-05, "loss": 0.5054284572601319, "step": 427920 }, { "epoch": 2.543704786870434, "grad_norm": 2.3252222537994385, "learning_rate": 3.2389770671908104e-05, "loss": 0.5038717269897461, "step": 427930 }, { "epoch": 2.5437642289471025, "grad_norm": 1.782546877861023, "learning_rate": 3.2386619028554e-05, "loss": 0.462076473236084, "step": 427940 }, { "epoch": 2.543823671023771, "grad_norm": 1.2349001169204712, "learning_rate": 3.2383467756476955e-05, "loss": 0.4972556114196777, "step": 427950 }, { "epoch": 2.5438831131004394, "grad_norm": 1.047408103942871, "learning_rate": 3.2380316855692005e-05, "loss": 0.4444598197937012, "step": 427960 }, { "epoch": 2.5439425551771078, "grad_norm": 1.2558252811431885, "learning_rate": 3.237716632621428e-05, "loss": 0.4380940437316895, "step": 427970 }, { "epoch": 2.544001997253776, "grad_norm": 1.314725637435913, "learning_rate": 3.237401616805885e-05, "loss": 0.46868209838867186, "step": 427980 }, { "epoch": 2.5440614393304446, "grad_norm": 1.3152351379394531, "learning_rate": 3.2370866381240726e-05, "loss": 0.4673140525817871, "step": 427990 }, { "epoch": 2.544120881407113, "grad_norm": 1.3539339303970337, "learning_rate": 3.2367716965774995e-05, "loss": 0.4603559494018555, "step": 428000 }, { "epoch": 2.544180323483781, "grad_norm": 1.4708009958267212, "learning_rate": 3.236456792167675e-05, "loss": 0.4980438232421875, "step": 428010 }, { "epoch": 2.54423976556045, "grad_norm": 1.4710044860839844, "learning_rate": 3.2361419248961046e-05, "loss": 0.4659248352050781, "step": 428020 }, { "epoch": 2.544299207637118, "grad_norm": 1.244439959526062, "learning_rate": 3.235827094764292e-05, "loss": 0.5006177425384521, "step": 428030 }, { "epoch": 2.5443586497137867, "grad_norm": 1.5333588123321533, "learning_rate": 3.235512301773749e-05, "loss": 0.4852002143859863, "step": 428040 }, { "epoch": 2.5444180917904546, "grad_norm": 1.2241333723068237, "learning_rate": 3.2351975459259756e-05, "loss": 0.51923508644104, "step": 428050 }, { "epoch": 2.544477533867123, "grad_norm": 1.2241432666778564, "learning_rate": 3.234882827222478e-05, "loss": 0.47428140640258787, "step": 428060 }, { "epoch": 2.5445369759437915, "grad_norm": 1.1112033128738403, "learning_rate": 3.2345681456647645e-05, "loss": 0.5120549201965332, "step": 428070 }, { "epoch": 2.54459641802046, "grad_norm": 0.7993348240852356, "learning_rate": 3.23425350125434e-05, "loss": 0.44813003540039065, "step": 428080 }, { "epoch": 2.5446558600971283, "grad_norm": 1.2159864902496338, "learning_rate": 3.2339388939927055e-05, "loss": 0.4619622707366943, "step": 428090 }, { "epoch": 2.5447153021737967, "grad_norm": 1.4187878370285034, "learning_rate": 3.233624323881376e-05, "loss": 0.4937747955322266, "step": 428100 }, { "epoch": 2.544774744250465, "grad_norm": 1.4684369564056396, "learning_rate": 3.233309790921845e-05, "loss": 0.47838554382324217, "step": 428110 }, { "epoch": 2.5448341863271335, "grad_norm": 1.442386507987976, "learning_rate": 3.232995295115623e-05, "loss": 0.46834897994995117, "step": 428120 }, { "epoch": 2.544893628403802, "grad_norm": 1.5350099802017212, "learning_rate": 3.232680836464211e-05, "loss": 0.4608012199401855, "step": 428130 }, { "epoch": 2.5449530704804704, "grad_norm": 1.5525881052017212, "learning_rate": 3.232366414969117e-05, "loss": 0.4969936370849609, "step": 428140 }, { "epoch": 2.545012512557139, "grad_norm": 1.4075928926467896, "learning_rate": 3.2320520306318445e-05, "loss": 0.44657087326049805, "step": 428150 }, { "epoch": 2.545071954633807, "grad_norm": 1.0201140642166138, "learning_rate": 3.231737683453896e-05, "loss": 0.448819637298584, "step": 428160 }, { "epoch": 2.5451313967104756, "grad_norm": 1.5461194515228271, "learning_rate": 3.231423373436776e-05, "loss": 0.5118044376373291, "step": 428170 }, { "epoch": 2.545190838787144, "grad_norm": 1.1941490173339844, "learning_rate": 3.231109100581988e-05, "loss": 0.457952880859375, "step": 428180 }, { "epoch": 2.5452502808638124, "grad_norm": 1.2616912126541138, "learning_rate": 3.230794864891032e-05, "loss": 0.489786434173584, "step": 428190 }, { "epoch": 2.5453097229404804, "grad_norm": 1.4211485385894775, "learning_rate": 3.2304806663654176e-05, "loss": 0.4732700824737549, "step": 428200 }, { "epoch": 2.5453691650171493, "grad_norm": 1.184598684310913, "learning_rate": 3.2301665050066444e-05, "loss": 0.4730205535888672, "step": 428210 }, { "epoch": 2.5454286070938172, "grad_norm": 1.173354148864746, "learning_rate": 3.229852380816215e-05, "loss": 0.5019425392150879, "step": 428220 }, { "epoch": 2.5454880491704857, "grad_norm": 1.1337218284606934, "learning_rate": 3.229538293795633e-05, "loss": 0.4302389144897461, "step": 428230 }, { "epoch": 2.545547491247154, "grad_norm": 1.0938467979431152, "learning_rate": 3.2292242439464e-05, "loss": 0.4651623725891113, "step": 428240 }, { "epoch": 2.5456069333238225, "grad_norm": 1.3934855461120605, "learning_rate": 3.228910231270018e-05, "loss": 0.5298234939575195, "step": 428250 }, { "epoch": 2.545666375400491, "grad_norm": 1.21498441696167, "learning_rate": 3.22859625576799e-05, "loss": 0.4713568687438965, "step": 428260 }, { "epoch": 2.5457258174771593, "grad_norm": 1.5465553998947144, "learning_rate": 3.228282317441817e-05, "loss": 0.49604225158691406, "step": 428270 }, { "epoch": 2.5457852595538277, "grad_norm": 0.925119161605835, "learning_rate": 3.227968416293003e-05, "loss": 0.4225619316101074, "step": 428280 }, { "epoch": 2.545844701630496, "grad_norm": 1.1827503442764282, "learning_rate": 3.227654552323048e-05, "loss": 0.45622892379760743, "step": 428290 }, { "epoch": 2.5459041437071646, "grad_norm": 1.607979655265808, "learning_rate": 3.227340725533454e-05, "loss": 0.49702229499816897, "step": 428300 }, { "epoch": 2.545963585783833, "grad_norm": 1.4149824380874634, "learning_rate": 3.227026935925721e-05, "loss": 0.4670660972595215, "step": 428310 }, { "epoch": 2.5460230278605014, "grad_norm": 1.3612133264541626, "learning_rate": 3.2267131835013495e-05, "loss": 0.4572451114654541, "step": 428320 }, { "epoch": 2.54608246993717, "grad_norm": 1.2106802463531494, "learning_rate": 3.2263994682618436e-05, "loss": 0.4474684715270996, "step": 428330 }, { "epoch": 2.546141912013838, "grad_norm": 1.2820664644241333, "learning_rate": 3.226085790208703e-05, "loss": 0.4841141700744629, "step": 428340 }, { "epoch": 2.5462013540905066, "grad_norm": 1.3640326261520386, "learning_rate": 3.2257721493434265e-05, "loss": 0.47351574897766113, "step": 428350 }, { "epoch": 2.546260796167175, "grad_norm": 1.342864751815796, "learning_rate": 3.225458545667516e-05, "loss": 0.48840961456298826, "step": 428360 }, { "epoch": 2.546320238243843, "grad_norm": 1.2521013021469116, "learning_rate": 3.2251449791824703e-05, "loss": 0.5126412868499756, "step": 428370 }, { "epoch": 2.546379680320512, "grad_norm": 1.4313408136367798, "learning_rate": 3.224831449889791e-05, "loss": 0.5004911899566651, "step": 428380 }, { "epoch": 2.54643912239718, "grad_norm": 1.3624927997589111, "learning_rate": 3.224517957790974e-05, "loss": 0.4937132835388184, "step": 428390 }, { "epoch": 2.5464985644738487, "grad_norm": 1.1767483949661255, "learning_rate": 3.224204502887524e-05, "loss": 0.48379316329956057, "step": 428400 }, { "epoch": 2.5465580065505167, "grad_norm": 1.2980759143829346, "learning_rate": 3.2238910851809415e-05, "loss": 0.45553979873657224, "step": 428410 }, { "epoch": 2.546617448627185, "grad_norm": 1.291517972946167, "learning_rate": 3.2235777046727194e-05, "loss": 0.422586727142334, "step": 428420 }, { "epoch": 2.5466768907038535, "grad_norm": 1.3419853448867798, "learning_rate": 3.223264361364361e-05, "loss": 0.45041837692260744, "step": 428430 }, { "epoch": 2.546736332780522, "grad_norm": 1.5228339433670044, "learning_rate": 3.222951055257365e-05, "loss": 0.45919175148010255, "step": 428440 }, { "epoch": 2.5467957748571903, "grad_norm": 1.2673323154449463, "learning_rate": 3.222637786353227e-05, "loss": 0.4722709655761719, "step": 428450 }, { "epoch": 2.5468552169338587, "grad_norm": 1.4647161960601807, "learning_rate": 3.222324554653451e-05, "loss": 0.556551742553711, "step": 428460 }, { "epoch": 2.546914659010527, "grad_norm": 1.3769690990447998, "learning_rate": 3.2220113601595334e-05, "loss": 0.47612814903259276, "step": 428470 }, { "epoch": 2.5469741010871956, "grad_norm": 1.188863754272461, "learning_rate": 3.22169820287297e-05, "loss": 0.4394925594329834, "step": 428480 }, { "epoch": 2.547033543163864, "grad_norm": 1.627829670906067, "learning_rate": 3.221385082795259e-05, "loss": 0.4935744285583496, "step": 428490 }, { "epoch": 2.5470929852405324, "grad_norm": 1.1166194677352905, "learning_rate": 3.2210719999279014e-05, "loss": 0.4427161693572998, "step": 428500 }, { "epoch": 2.547152427317201, "grad_norm": 1.8694424629211426, "learning_rate": 3.220758954272392e-05, "loss": 0.4720162391662598, "step": 428510 }, { "epoch": 2.5472118693938692, "grad_norm": 1.0294855833053589, "learning_rate": 3.2204459458302295e-05, "loss": 0.4781189441680908, "step": 428520 }, { "epoch": 2.5472713114705376, "grad_norm": 1.2983952760696411, "learning_rate": 3.220132974602914e-05, "loss": 0.444873046875, "step": 428530 }, { "epoch": 2.547330753547206, "grad_norm": 1.477832317352295, "learning_rate": 3.219820040591939e-05, "loss": 0.4993032455444336, "step": 428540 }, { "epoch": 2.5473901956238745, "grad_norm": 1.5435869693756104, "learning_rate": 3.2195071437988e-05, "loss": 0.47350506782531737, "step": 428550 }, { "epoch": 2.5474496377005424, "grad_norm": 1.4830381870269775, "learning_rate": 3.219194284224997e-05, "loss": 0.4583630084991455, "step": 428560 }, { "epoch": 2.5475090797772113, "grad_norm": 1.4218151569366455, "learning_rate": 3.218881461872026e-05, "loss": 0.4688089847564697, "step": 428570 }, { "epoch": 2.5475685218538793, "grad_norm": 1.3901232481002808, "learning_rate": 3.2185686767413816e-05, "loss": 0.4977121353149414, "step": 428580 }, { "epoch": 2.547627963930548, "grad_norm": 1.07790207862854, "learning_rate": 3.218255928834565e-05, "loss": 0.45300588607788084, "step": 428590 }, { "epoch": 2.547687406007216, "grad_norm": 1.5470061302185059, "learning_rate": 3.217943218153068e-05, "loss": 0.5059110641479492, "step": 428600 }, { "epoch": 2.5477468480838845, "grad_norm": 1.2583192586898804, "learning_rate": 3.2176305446983866e-05, "loss": 0.4376839637756348, "step": 428610 }, { "epoch": 2.547806290160553, "grad_norm": 1.4260778427124023, "learning_rate": 3.2173179084720156e-05, "loss": 0.5247600555419922, "step": 428620 }, { "epoch": 2.5478657322372213, "grad_norm": 1.4814105033874512, "learning_rate": 3.217005309475455e-05, "loss": 0.48305883407592776, "step": 428630 }, { "epoch": 2.5479251743138898, "grad_norm": 1.419779658317566, "learning_rate": 3.216692747710197e-05, "loss": 0.4933434009552002, "step": 428640 }, { "epoch": 2.547984616390558, "grad_norm": 0.9952384829521179, "learning_rate": 3.216380223177737e-05, "loss": 0.46913971900939944, "step": 428650 }, { "epoch": 2.5480440584672266, "grad_norm": 1.294281244277954, "learning_rate": 3.2160677358795705e-05, "loss": 0.45008172988891604, "step": 428660 }, { "epoch": 2.548103500543895, "grad_norm": 1.2837938070297241, "learning_rate": 3.2157552858171926e-05, "loss": 0.43996152877807615, "step": 428670 }, { "epoch": 2.5481629426205634, "grad_norm": 1.3911089897155762, "learning_rate": 3.215442872992094e-05, "loss": 0.4885712623596191, "step": 428680 }, { "epoch": 2.548222384697232, "grad_norm": 0.959861159324646, "learning_rate": 3.2151304974057765e-05, "loss": 0.40903520584106445, "step": 428690 }, { "epoch": 2.5482818267739002, "grad_norm": 1.4521172046661377, "learning_rate": 3.21481815905973e-05, "loss": 0.4405373096466064, "step": 428700 }, { "epoch": 2.5483412688505687, "grad_norm": 1.7404170036315918, "learning_rate": 3.214505857955449e-05, "loss": 0.5187763214111328, "step": 428710 }, { "epoch": 2.548400710927237, "grad_norm": 1.7591557502746582, "learning_rate": 3.2141935940944277e-05, "loss": 0.5021714210510254, "step": 428720 }, { "epoch": 2.5484601530039055, "grad_norm": 1.3959619998931885, "learning_rate": 3.21388136747816e-05, "loss": 0.4935013294219971, "step": 428730 }, { "epoch": 2.548519595080574, "grad_norm": 1.4132559299468994, "learning_rate": 3.213569178108138e-05, "loss": 0.47397737503051757, "step": 428740 }, { "epoch": 2.548579037157242, "grad_norm": 1.4894073009490967, "learning_rate": 3.2132570259858564e-05, "loss": 0.4057806968688965, "step": 428750 }, { "epoch": 2.5486384792339107, "grad_norm": 1.2983105182647705, "learning_rate": 3.21294491111281e-05, "loss": 0.49002923965454104, "step": 428760 }, { "epoch": 2.5486979213105787, "grad_norm": 1.2068159580230713, "learning_rate": 3.2126328334904895e-05, "loss": 0.45277833938598633, "step": 428770 }, { "epoch": 2.5487573633872476, "grad_norm": 1.118104338645935, "learning_rate": 3.212320793120388e-05, "loss": 0.43940463066101076, "step": 428780 }, { "epoch": 2.5488168054639155, "grad_norm": 1.3750312328338623, "learning_rate": 3.212008790004e-05, "loss": 0.4888099193572998, "step": 428790 }, { "epoch": 2.548876247540584, "grad_norm": 1.1312105655670166, "learning_rate": 3.2116968241428165e-05, "loss": 0.46420745849609374, "step": 428800 }, { "epoch": 2.5489356896172524, "grad_norm": 0.9301615953445435, "learning_rate": 3.211384895538328e-05, "loss": 0.43374171257019045, "step": 428810 }, { "epoch": 2.548995131693921, "grad_norm": 1.2870060205459595, "learning_rate": 3.2110730041920304e-05, "loss": 0.44607954025268554, "step": 428820 }, { "epoch": 2.549054573770589, "grad_norm": 1.314382553100586, "learning_rate": 3.2107611501054155e-05, "loss": 0.500898027420044, "step": 428830 }, { "epoch": 2.5491140158472576, "grad_norm": 1.4502812623977661, "learning_rate": 3.2104493332799724e-05, "loss": 0.49649648666381835, "step": 428840 }, { "epoch": 2.549173457923926, "grad_norm": 1.2658177614212036, "learning_rate": 3.210137553717195e-05, "loss": 0.4576115131378174, "step": 428850 }, { "epoch": 2.5492329000005944, "grad_norm": 1.3179594278335571, "learning_rate": 3.209825811418573e-05, "loss": 0.46402502059936523, "step": 428860 }, { "epoch": 2.549292342077263, "grad_norm": 1.1642662286758423, "learning_rate": 3.209514106385599e-05, "loss": 0.4220695495605469, "step": 428870 }, { "epoch": 2.5493517841539313, "grad_norm": 1.1231372356414795, "learning_rate": 3.2092024386197614e-05, "loss": 0.5122511863708497, "step": 428880 }, { "epoch": 2.5494112262305997, "grad_norm": 1.042959213256836, "learning_rate": 3.208890808122555e-05, "loss": 0.44673910140991213, "step": 428890 }, { "epoch": 2.549470668307268, "grad_norm": 1.4504306316375732, "learning_rate": 3.208579214895469e-05, "loss": 0.4732086658477783, "step": 428900 }, { "epoch": 2.5495301103839365, "grad_norm": 1.3531968593597412, "learning_rate": 3.208267658939993e-05, "loss": 0.48888421058654785, "step": 428910 }, { "epoch": 2.549589552460605, "grad_norm": 1.5305644273757935, "learning_rate": 3.2079561402576197e-05, "loss": 0.47390179634094237, "step": 428920 }, { "epoch": 2.5496489945372733, "grad_norm": 1.7287700176239014, "learning_rate": 3.207644658849837e-05, "loss": 0.46504716873168944, "step": 428930 }, { "epoch": 2.5497084366139413, "grad_norm": 0.8748062252998352, "learning_rate": 3.207333214718134e-05, "loss": 0.4782198429107666, "step": 428940 }, { "epoch": 2.54976787869061, "grad_norm": 1.3492178916931152, "learning_rate": 3.2070218078640036e-05, "loss": 0.4632279396057129, "step": 428950 }, { "epoch": 2.549827320767278, "grad_norm": 1.3679190874099731, "learning_rate": 3.206710438288934e-05, "loss": 0.4695016860961914, "step": 428960 }, { "epoch": 2.5498867628439466, "grad_norm": 1.2989612817764282, "learning_rate": 3.2063991059944175e-05, "loss": 0.44272446632385254, "step": 428970 }, { "epoch": 2.549946204920615, "grad_norm": 1.285439133644104, "learning_rate": 3.2060878109819356e-05, "loss": 0.499085807800293, "step": 428980 }, { "epoch": 2.5500056469972834, "grad_norm": 1.3640456199645996, "learning_rate": 3.205776553252986e-05, "loss": 0.4802842617034912, "step": 428990 }, { "epoch": 2.550065089073952, "grad_norm": 1.4827488660812378, "learning_rate": 3.2054653328090536e-05, "loss": 0.503978157043457, "step": 429000 }, { "epoch": 2.55012453115062, "grad_norm": 1.2699934244155884, "learning_rate": 3.205154149651626e-05, "loss": 0.4994976043701172, "step": 429010 }, { "epoch": 2.5501839732272886, "grad_norm": 1.013946771621704, "learning_rate": 3.204843003782197e-05, "loss": 0.4298288345336914, "step": 429020 }, { "epoch": 2.550243415303957, "grad_norm": 0.9408595561981201, "learning_rate": 3.20453189520225e-05, "loss": 0.4838827133178711, "step": 429030 }, { "epoch": 2.5503028573806255, "grad_norm": 1.3411719799041748, "learning_rate": 3.204220823913272e-05, "loss": 0.42650794982910156, "step": 429040 }, { "epoch": 2.550362299457294, "grad_norm": 1.0766345262527466, "learning_rate": 3.203909789916757e-05, "loss": 0.46143131256103515, "step": 429050 }, { "epoch": 2.5504217415339623, "grad_norm": 1.5079818964004517, "learning_rate": 3.203598793214189e-05, "loss": 0.44817094802856444, "step": 429060 }, { "epoch": 2.5504811836106307, "grad_norm": 1.460189700126648, "learning_rate": 3.203287833807055e-05, "loss": 0.5094717025756836, "step": 429070 }, { "epoch": 2.550540625687299, "grad_norm": 1.4093308448791504, "learning_rate": 3.202976911696847e-05, "loss": 0.48563032150268554, "step": 429080 }, { "epoch": 2.5506000677639675, "grad_norm": 1.2934069633483887, "learning_rate": 3.202666026885048e-05, "loss": 0.5025941848754882, "step": 429090 }, { "epoch": 2.550659509840636, "grad_norm": 1.1679472923278809, "learning_rate": 3.202355179373148e-05, "loss": 0.46834840774536135, "step": 429100 }, { "epoch": 2.550718951917304, "grad_norm": 1.4986714124679565, "learning_rate": 3.202044369162629e-05, "loss": 0.48357281684875486, "step": 429110 }, { "epoch": 2.5507783939939728, "grad_norm": 1.371462345123291, "learning_rate": 3.2017335962549835e-05, "loss": 0.5315729141235351, "step": 429120 }, { "epoch": 2.5508378360706407, "grad_norm": 1.4587041139602661, "learning_rate": 3.201422860651696e-05, "loss": 0.5247716903686523, "step": 429130 }, { "epoch": 2.5508972781473096, "grad_norm": 1.6620763540267944, "learning_rate": 3.2011121623542525e-05, "loss": 0.49153909683227537, "step": 429140 }, { "epoch": 2.5509567202239776, "grad_norm": 1.1950656175613403, "learning_rate": 3.20080150136414e-05, "loss": 0.4937421798706055, "step": 429150 }, { "epoch": 2.551016162300646, "grad_norm": 1.2912514209747314, "learning_rate": 3.200490877682845e-05, "loss": 0.5055877685546875, "step": 429160 }, { "epoch": 2.5510756043773144, "grad_norm": 1.2002308368682861, "learning_rate": 3.20018029131185e-05, "loss": 0.523042869567871, "step": 429170 }, { "epoch": 2.551135046453983, "grad_norm": 1.0179853439331055, "learning_rate": 3.1998697422526456e-05, "loss": 0.47656688690185545, "step": 429180 }, { "epoch": 2.5511944885306512, "grad_norm": 1.0762643814086914, "learning_rate": 3.199559230506716e-05, "loss": 0.49166145324707033, "step": 429190 }, { "epoch": 2.5512539306073196, "grad_norm": 1.5583677291870117, "learning_rate": 3.199248756075545e-05, "loss": 0.49790587425231936, "step": 429200 }, { "epoch": 2.551313372683988, "grad_norm": 1.1542305946350098, "learning_rate": 3.198938318960618e-05, "loss": 0.5026625633239746, "step": 429210 }, { "epoch": 2.5513728147606565, "grad_norm": 0.9650657176971436, "learning_rate": 3.198627919163422e-05, "loss": 0.4674464225769043, "step": 429220 }, { "epoch": 2.551432256837325, "grad_norm": 1.4108952283859253, "learning_rate": 3.1983175566854405e-05, "loss": 0.44545860290527345, "step": 429230 }, { "epoch": 2.5514916989139933, "grad_norm": 1.4449571371078491, "learning_rate": 3.198007231528155e-05, "loss": 0.43898601531982423, "step": 429240 }, { "epoch": 2.5515511409906617, "grad_norm": 1.4805628061294556, "learning_rate": 3.1976969436930566e-05, "loss": 0.4700311660766602, "step": 429250 }, { "epoch": 2.55161058306733, "grad_norm": 1.3107531070709229, "learning_rate": 3.197386693181625e-05, "loss": 0.49949893951416013, "step": 429260 }, { "epoch": 2.5516700251439985, "grad_norm": 1.2925825119018555, "learning_rate": 3.1970764799953464e-05, "loss": 0.4884765625, "step": 429270 }, { "epoch": 2.551729467220667, "grad_norm": 1.6371815204620361, "learning_rate": 3.1967663041357035e-05, "loss": 0.4781682014465332, "step": 429280 }, { "epoch": 2.5517889092973354, "grad_norm": 1.273630142211914, "learning_rate": 3.1964561656041806e-05, "loss": 0.4642480850219727, "step": 429290 }, { "epoch": 2.5518483513740033, "grad_norm": 1.4258984327316284, "learning_rate": 3.196146064402258e-05, "loss": 0.5161357402801514, "step": 429300 }, { "epoch": 2.551907793450672, "grad_norm": 1.2945467233657837, "learning_rate": 3.195836000531425e-05, "loss": 0.5064562797546387, "step": 429310 }, { "epoch": 2.55196723552734, "grad_norm": 1.3874626159667969, "learning_rate": 3.195525973993163e-05, "loss": 0.46281042098999026, "step": 429320 }, { "epoch": 2.552026677604009, "grad_norm": 1.0182440280914307, "learning_rate": 3.195215984788954e-05, "loss": 0.4913190841674805, "step": 429330 }, { "epoch": 2.552086119680677, "grad_norm": 1.5496588945388794, "learning_rate": 3.1949060329202803e-05, "loss": 0.48360562324523926, "step": 429340 }, { "epoch": 2.5521455617573454, "grad_norm": 1.3988476991653442, "learning_rate": 3.194596118388626e-05, "loss": 0.4685800552368164, "step": 429350 }, { "epoch": 2.552205003834014, "grad_norm": 1.400171160697937, "learning_rate": 3.194286241195473e-05, "loss": 0.5170373916625977, "step": 429360 }, { "epoch": 2.5522644459106822, "grad_norm": 1.4202746152877808, "learning_rate": 3.1939764013423016e-05, "loss": 0.46056418418884276, "step": 429370 }, { "epoch": 2.5523238879873507, "grad_norm": 1.5458507537841797, "learning_rate": 3.193666598830599e-05, "loss": 0.4606143951416016, "step": 429380 }, { "epoch": 2.552383330064019, "grad_norm": 1.3188135623931885, "learning_rate": 3.193356833661843e-05, "loss": 0.4790655136108398, "step": 429390 }, { "epoch": 2.5524427721406875, "grad_norm": 1.61249840259552, "learning_rate": 3.193047105837517e-05, "loss": 0.42514910697937014, "step": 429400 }, { "epoch": 2.552502214217356, "grad_norm": 1.5065422058105469, "learning_rate": 3.1927374153591025e-05, "loss": 0.509097957611084, "step": 429410 }, { "epoch": 2.5525616562940243, "grad_norm": 1.5249531269073486, "learning_rate": 3.19242776222808e-05, "loss": 0.46941027641296384, "step": 429420 }, { "epoch": 2.5526210983706927, "grad_norm": 1.0477632284164429, "learning_rate": 3.1921181464459305e-05, "loss": 0.4720419406890869, "step": 429430 }, { "epoch": 2.552680540447361, "grad_norm": 1.5818145275115967, "learning_rate": 3.1918085680141376e-05, "loss": 0.4915908336639404, "step": 429440 }, { "epoch": 2.5527399825240296, "grad_norm": 1.35629141330719, "learning_rate": 3.191499026934181e-05, "loss": 0.4854565620422363, "step": 429450 }, { "epoch": 2.552799424600698, "grad_norm": 1.285007357597351, "learning_rate": 3.191189523207543e-05, "loss": 0.4420017242431641, "step": 429460 }, { "epoch": 2.5528588666773664, "grad_norm": 1.5811891555786133, "learning_rate": 3.190880056835698e-05, "loss": 0.5130230903625488, "step": 429470 }, { "epoch": 2.552918308754035, "grad_norm": 0.9225817322731018, "learning_rate": 3.190570627820133e-05, "loss": 0.4357147693634033, "step": 429480 }, { "epoch": 2.5529777508307028, "grad_norm": 1.2634234428405762, "learning_rate": 3.190261236162327e-05, "loss": 0.500572395324707, "step": 429490 }, { "epoch": 2.5530371929073716, "grad_norm": 1.118422269821167, "learning_rate": 3.189951881863756e-05, "loss": 0.4488212108612061, "step": 429500 }, { "epoch": 2.5530966349840396, "grad_norm": 1.3176910877227783, "learning_rate": 3.189642564925905e-05, "loss": 0.4947150230407715, "step": 429510 }, { "epoch": 2.5531560770607085, "grad_norm": 1.209840178489685, "learning_rate": 3.189333285350254e-05, "loss": 0.39532814025878904, "step": 429520 }, { "epoch": 2.5532155191373764, "grad_norm": 1.5048683881759644, "learning_rate": 3.189024043138275e-05, "loss": 0.47305889129638673, "step": 429530 }, { "epoch": 2.553274961214045, "grad_norm": 1.4227015972137451, "learning_rate": 3.188714838291456e-05, "loss": 0.5333686351776123, "step": 429540 }, { "epoch": 2.5533344032907133, "grad_norm": 1.2405484914779663, "learning_rate": 3.188405670811271e-05, "loss": 0.454357385635376, "step": 429550 }, { "epoch": 2.5533938453673817, "grad_norm": 1.2985875606536865, "learning_rate": 3.188096540699198e-05, "loss": 0.45279521942138673, "step": 429560 }, { "epoch": 2.55345328744405, "grad_norm": 1.1696579456329346, "learning_rate": 3.1877874479567216e-05, "loss": 0.4014756202697754, "step": 429570 }, { "epoch": 2.5535127295207185, "grad_norm": 1.0084205865859985, "learning_rate": 3.187478392585317e-05, "loss": 0.44510297775268554, "step": 429580 }, { "epoch": 2.553572171597387, "grad_norm": 1.0151218175888062, "learning_rate": 3.187169374586463e-05, "loss": 0.4784419059753418, "step": 429590 }, { "epoch": 2.5536316136740553, "grad_norm": 1.386886715888977, "learning_rate": 3.186860393961634e-05, "loss": 0.5025679111480713, "step": 429600 }, { "epoch": 2.5536910557507237, "grad_norm": 1.2296655178070068, "learning_rate": 3.186551450712314e-05, "loss": 0.4323071002960205, "step": 429610 }, { "epoch": 2.553750497827392, "grad_norm": 1.0298621654510498, "learning_rate": 3.1862425448399784e-05, "loss": 0.48799705505371094, "step": 429620 }, { "epoch": 2.5538099399040606, "grad_norm": 0.920037567615509, "learning_rate": 3.185933676346103e-05, "loss": 0.48763227462768555, "step": 429630 }, { "epoch": 2.553869381980729, "grad_norm": 1.5588297843933105, "learning_rate": 3.185624845232171e-05, "loss": 0.41532144546508787, "step": 429640 }, { "epoch": 2.5539288240573974, "grad_norm": 1.382796049118042, "learning_rate": 3.185316051499654e-05, "loss": 0.4499801158905029, "step": 429650 }, { "epoch": 2.553988266134066, "grad_norm": 1.4271397590637207, "learning_rate": 3.18500729515003e-05, "loss": 0.45339012145996094, "step": 429660 }, { "epoch": 2.5540477082107342, "grad_norm": 1.286558985710144, "learning_rate": 3.184698576184778e-05, "loss": 0.48791818618774413, "step": 429670 }, { "epoch": 2.554107150287402, "grad_norm": 1.2353193759918213, "learning_rate": 3.184389894605374e-05, "loss": 0.4500590324401855, "step": 429680 }, { "epoch": 2.554166592364071, "grad_norm": 0.9773488640785217, "learning_rate": 3.1840812504132944e-05, "loss": 0.45570054054260256, "step": 429690 }, { "epoch": 2.554226034440739, "grad_norm": 1.3059637546539307, "learning_rate": 3.183772643610017e-05, "loss": 0.4550124168395996, "step": 429700 }, { "epoch": 2.5542854765174074, "grad_norm": 1.0687255859375, "learning_rate": 3.183464074197016e-05, "loss": 0.44409904479980467, "step": 429710 }, { "epoch": 2.554344918594076, "grad_norm": 1.2061272859573364, "learning_rate": 3.1831555421757686e-05, "loss": 0.4547133922576904, "step": 429720 }, { "epoch": 2.5544043606707443, "grad_norm": 1.3986384868621826, "learning_rate": 3.182847047547748e-05, "loss": 0.5543889999389648, "step": 429730 }, { "epoch": 2.5544638027474127, "grad_norm": 1.3382251262664795, "learning_rate": 3.1825385903144354e-05, "loss": 0.5171631813049317, "step": 429740 }, { "epoch": 2.554523244824081, "grad_norm": 1.2946743965148926, "learning_rate": 3.182230170477303e-05, "loss": 0.498134708404541, "step": 429750 }, { "epoch": 2.5545826869007495, "grad_norm": 1.3163002729415894, "learning_rate": 3.181921788037826e-05, "loss": 0.45616817474365234, "step": 429760 }, { "epoch": 2.554642128977418, "grad_norm": 1.3819068670272827, "learning_rate": 3.181613442997481e-05, "loss": 0.4644184112548828, "step": 429770 }, { "epoch": 2.5547015710540864, "grad_norm": 1.1974064111709595, "learning_rate": 3.181305135357742e-05, "loss": 0.45997018814086915, "step": 429780 }, { "epoch": 2.5547610131307548, "grad_norm": 1.551730751991272, "learning_rate": 3.1809968651200815e-05, "loss": 0.4684597969055176, "step": 429790 }, { "epoch": 2.554820455207423, "grad_norm": 1.2690296173095703, "learning_rate": 3.18068863228598e-05, "loss": 0.4613498687744141, "step": 429800 }, { "epoch": 2.5548798972840916, "grad_norm": 1.3689696788787842, "learning_rate": 3.1803804368569066e-05, "loss": 0.4689043045043945, "step": 429810 }, { "epoch": 2.55493933936076, "grad_norm": 1.5226526260375977, "learning_rate": 3.18007227883434e-05, "loss": 0.48906698226928713, "step": 429820 }, { "epoch": 2.5549987814374284, "grad_norm": 1.298795223236084, "learning_rate": 3.1797641582197506e-05, "loss": 0.4472637176513672, "step": 429830 }, { "epoch": 2.555058223514097, "grad_norm": 1.603617787361145, "learning_rate": 3.179456075014615e-05, "loss": 0.4362298011779785, "step": 429840 }, { "epoch": 2.555117665590765, "grad_norm": 1.4660919904708862, "learning_rate": 3.1791480292204047e-05, "loss": 0.4670267105102539, "step": 429850 }, { "epoch": 2.5551771076674337, "grad_norm": 1.7410924434661865, "learning_rate": 3.178840020838592e-05, "loss": 0.4842674255371094, "step": 429860 }, { "epoch": 2.5552365497441016, "grad_norm": 1.0803724527359009, "learning_rate": 3.1785320498706555e-05, "loss": 0.4498126029968262, "step": 429870 }, { "epoch": 2.5552959918207705, "grad_norm": 1.442421317100525, "learning_rate": 3.178224116318066e-05, "loss": 0.47179355621337893, "step": 429880 }, { "epoch": 2.5553554338974385, "grad_norm": 0.7305040955543518, "learning_rate": 3.177916220182295e-05, "loss": 0.4443520069122314, "step": 429890 }, { "epoch": 2.555414875974107, "grad_norm": 1.105590581893921, "learning_rate": 3.177608361464818e-05, "loss": 0.4793370246887207, "step": 429900 }, { "epoch": 2.5554743180507753, "grad_norm": 1.4410741329193115, "learning_rate": 3.177300540167104e-05, "loss": 0.5338728904724122, "step": 429910 }, { "epoch": 2.5555337601274437, "grad_norm": 1.1149343252182007, "learning_rate": 3.176992756290628e-05, "loss": 0.4763925075531006, "step": 429920 }, { "epoch": 2.555593202204112, "grad_norm": 1.311293363571167, "learning_rate": 3.1766850098368625e-05, "loss": 0.4828179359436035, "step": 429930 }, { "epoch": 2.5556526442807805, "grad_norm": 1.2752801179885864, "learning_rate": 3.17637730080728e-05, "loss": 0.44476165771484377, "step": 429940 }, { "epoch": 2.555712086357449, "grad_norm": 1.403782606124878, "learning_rate": 3.1760696292033526e-05, "loss": 0.5390568733215332, "step": 429950 }, { "epoch": 2.5557715284341174, "grad_norm": 1.5997819900512695, "learning_rate": 3.1757619950265495e-05, "loss": 0.46938066482543944, "step": 429960 }, { "epoch": 2.555830970510786, "grad_norm": 1.2989391088485718, "learning_rate": 3.1754543982783435e-05, "loss": 0.44636974334716795, "step": 429970 }, { "epoch": 2.555890412587454, "grad_norm": 1.2728644609451294, "learning_rate": 3.175146838960208e-05, "loss": 0.45316662788391116, "step": 429980 }, { "epoch": 2.5559498546641226, "grad_norm": 1.2647120952606201, "learning_rate": 3.174839317073611e-05, "loss": 0.468316650390625, "step": 429990 }, { "epoch": 2.556009296740791, "grad_norm": 1.1569149494171143, "learning_rate": 3.174531832620027e-05, "loss": 0.47429628372192384, "step": 430000 }, { "epoch": 2.5560687388174594, "grad_norm": 1.291316032409668, "learning_rate": 3.174224385600926e-05, "loss": 0.4981094837188721, "step": 430010 }, { "epoch": 2.556128180894128, "grad_norm": 1.2773432731628418, "learning_rate": 3.1739169760177767e-05, "loss": 0.47978601455688474, "step": 430020 }, { "epoch": 2.5561876229707963, "grad_norm": 1.2791379690170288, "learning_rate": 3.173609603872051e-05, "loss": 0.4711313724517822, "step": 430030 }, { "epoch": 2.5562470650474642, "grad_norm": 1.1953213214874268, "learning_rate": 3.1733022691652196e-05, "loss": 0.4750516891479492, "step": 430040 }, { "epoch": 2.556306507124133, "grad_norm": 1.2083295583724976, "learning_rate": 3.172994971898751e-05, "loss": 0.43425760269165037, "step": 430050 }, { "epoch": 2.556365949200801, "grad_norm": 1.3198933601379395, "learning_rate": 3.1726877120741185e-05, "loss": 0.46336655616760253, "step": 430060 }, { "epoch": 2.55642539127747, "grad_norm": 1.3754414319992065, "learning_rate": 3.172380489692791e-05, "loss": 0.47218098640441897, "step": 430070 }, { "epoch": 2.556484833354138, "grad_norm": 1.6771503686904907, "learning_rate": 3.1720733047562357e-05, "loss": 0.48471722602844236, "step": 430080 }, { "epoch": 2.5565442754308063, "grad_norm": 1.1333321332931519, "learning_rate": 3.171766157265922e-05, "loss": 0.4054719924926758, "step": 430090 }, { "epoch": 2.5566037175074747, "grad_norm": 1.4782458543777466, "learning_rate": 3.1714590472233223e-05, "loss": 0.4697437286376953, "step": 430100 }, { "epoch": 2.556663159584143, "grad_norm": 1.4769898653030396, "learning_rate": 3.1711519746299034e-05, "loss": 0.5058390617370605, "step": 430110 }, { "epoch": 2.5567226016608116, "grad_norm": 1.4480854272842407, "learning_rate": 3.170844939487134e-05, "loss": 0.5231927871704102, "step": 430120 }, { "epoch": 2.55678204373748, "grad_norm": 1.3455336093902588, "learning_rate": 3.1705379417964876e-05, "loss": 0.469207763671875, "step": 430130 }, { "epoch": 2.5568414858141484, "grad_norm": 1.6773701906204224, "learning_rate": 3.170230981559426e-05, "loss": 0.4897933006286621, "step": 430140 }, { "epoch": 2.556900927890817, "grad_norm": 1.550220251083374, "learning_rate": 3.1699240587774206e-05, "loss": 0.482285213470459, "step": 430150 }, { "epoch": 2.556960369967485, "grad_norm": 1.1029672622680664, "learning_rate": 3.16961717345194e-05, "loss": 0.44434189796447754, "step": 430160 }, { "epoch": 2.5570198120441536, "grad_norm": 1.2483571767807007, "learning_rate": 3.169310325584453e-05, "loss": 0.47449793815612795, "step": 430170 }, { "epoch": 2.557079254120822, "grad_norm": 1.3520593643188477, "learning_rate": 3.169003515176426e-05, "loss": 0.48354668617248536, "step": 430180 }, { "epoch": 2.5571386961974905, "grad_norm": 1.0630195140838623, "learning_rate": 3.1686967422293256e-05, "loss": 0.46107964515686034, "step": 430190 }, { "epoch": 2.557198138274159, "grad_norm": 1.225982427597046, "learning_rate": 3.168390006744623e-05, "loss": 0.5103315830230712, "step": 430200 }, { "epoch": 2.5572575803508273, "grad_norm": 1.2690569162368774, "learning_rate": 3.168083308723781e-05, "loss": 0.5028681278228759, "step": 430210 }, { "epoch": 2.5573170224274957, "grad_norm": 1.3570786714553833, "learning_rate": 3.167776648168268e-05, "loss": 0.4491405010223389, "step": 430220 }, { "epoch": 2.5573764645041637, "grad_norm": 1.416239857673645, "learning_rate": 3.167470025079554e-05, "loss": 0.4746559143066406, "step": 430230 }, { "epoch": 2.5574359065808325, "grad_norm": 1.0262106657028198, "learning_rate": 3.1671634394591034e-05, "loss": 0.4279471397399902, "step": 430240 }, { "epoch": 2.5574953486575005, "grad_norm": 1.4435501098632812, "learning_rate": 3.166856891308383e-05, "loss": 0.512858772277832, "step": 430250 }, { "epoch": 2.5575547907341694, "grad_norm": 1.4409443140029907, "learning_rate": 3.1665503806288594e-05, "loss": 0.47348642349243164, "step": 430260 }, { "epoch": 2.5576142328108373, "grad_norm": 1.162696123123169, "learning_rate": 3.1662439074219985e-05, "loss": 0.4708414077758789, "step": 430270 }, { "epoch": 2.5576736748875057, "grad_norm": 1.140974521636963, "learning_rate": 3.1659374716892657e-05, "loss": 0.4893194675445557, "step": 430280 }, { "epoch": 2.557733116964174, "grad_norm": 1.1535615921020508, "learning_rate": 3.1656310734321286e-05, "loss": 0.49402170181274413, "step": 430290 }, { "epoch": 2.5577925590408426, "grad_norm": 1.4761574268341064, "learning_rate": 3.165324712652054e-05, "loss": 0.48142232894897463, "step": 430300 }, { "epoch": 2.557852001117511, "grad_norm": 1.3437641859054565, "learning_rate": 3.1650183893505035e-05, "loss": 0.45620336532592776, "step": 430310 }, { "epoch": 2.5579114431941794, "grad_norm": 1.166114091873169, "learning_rate": 3.1647121035289454e-05, "loss": 0.46270084381103516, "step": 430320 }, { "epoch": 2.557970885270848, "grad_norm": 0.9072625637054443, "learning_rate": 3.1644058551888446e-05, "loss": 0.4680363178253174, "step": 430330 }, { "epoch": 2.5580303273475162, "grad_norm": 1.315666675567627, "learning_rate": 3.164099644331664e-05, "loss": 0.5367875099182129, "step": 430340 }, { "epoch": 2.5580897694241846, "grad_norm": 1.5606948137283325, "learning_rate": 3.163793470958869e-05, "loss": 0.4684861660003662, "step": 430350 }, { "epoch": 2.558149211500853, "grad_norm": 0.9751740097999573, "learning_rate": 3.163487335071926e-05, "loss": 0.4978517532348633, "step": 430360 }, { "epoch": 2.5582086535775215, "grad_norm": 1.363690733909607, "learning_rate": 3.1631812366723e-05, "loss": 0.44038801193237304, "step": 430370 }, { "epoch": 2.55826809565419, "grad_norm": 1.2010754346847534, "learning_rate": 3.1628751757614536e-05, "loss": 0.43969550132751467, "step": 430380 }, { "epoch": 2.5583275377308583, "grad_norm": 1.1320257186889648, "learning_rate": 3.1625691523408505e-05, "loss": 0.48555965423583985, "step": 430390 }, { "epoch": 2.5583869798075267, "grad_norm": 1.4373003244400024, "learning_rate": 3.162263166411956e-05, "loss": 0.501048231124878, "step": 430400 }, { "epoch": 2.558446421884195, "grad_norm": 1.459472417831421, "learning_rate": 3.1619572179762314e-05, "loss": 0.4675424575805664, "step": 430410 }, { "epoch": 2.558505863960863, "grad_norm": 1.469446063041687, "learning_rate": 3.1616513070351426e-05, "loss": 0.4790602207183838, "step": 430420 }, { "epoch": 2.558565306037532, "grad_norm": 1.150619387626648, "learning_rate": 3.161345433590153e-05, "loss": 0.44717931747436523, "step": 430430 }, { "epoch": 2.5586247481142, "grad_norm": 1.5915160179138184, "learning_rate": 3.161039597642727e-05, "loss": 0.5401496410369873, "step": 430440 }, { "epoch": 2.5586841901908683, "grad_norm": 1.33292818069458, "learning_rate": 3.160733799194323e-05, "loss": 0.45966687202453616, "step": 430450 }, { "epoch": 2.5587436322675368, "grad_norm": 1.346771478652954, "learning_rate": 3.160428038246407e-05, "loss": 0.5249335289001464, "step": 430460 }, { "epoch": 2.558803074344205, "grad_norm": 1.1749600172042847, "learning_rate": 3.160122314800442e-05, "loss": 0.44927272796630857, "step": 430470 }, { "epoch": 2.5588625164208736, "grad_norm": 0.9913882613182068, "learning_rate": 3.159816628857887e-05, "loss": 0.39737858772277834, "step": 430480 }, { "epoch": 2.558921958497542, "grad_norm": 1.1130313873291016, "learning_rate": 3.1595109804202106e-05, "loss": 0.5044326305389404, "step": 430490 }, { "epoch": 2.5589814005742104, "grad_norm": 1.4409059286117554, "learning_rate": 3.159205369488872e-05, "loss": 0.4853670597076416, "step": 430500 }, { "epoch": 2.559040842650879, "grad_norm": 1.289499044418335, "learning_rate": 3.158899796065328e-05, "loss": 0.47618684768676756, "step": 430510 }, { "epoch": 2.5591002847275472, "grad_norm": 1.346476435661316, "learning_rate": 3.1585942601510487e-05, "loss": 0.4672565460205078, "step": 430520 }, { "epoch": 2.5591597268042157, "grad_norm": 1.5427895784378052, "learning_rate": 3.158288761747491e-05, "loss": 0.47310810089111327, "step": 430530 }, { "epoch": 2.559219168880884, "grad_norm": 1.3938406705856323, "learning_rate": 3.1579833008561174e-05, "loss": 0.4843482494354248, "step": 430540 }, { "epoch": 2.5592786109575525, "grad_norm": 1.4433791637420654, "learning_rate": 3.157677877478386e-05, "loss": 0.48659377098083495, "step": 430550 }, { "epoch": 2.559338053034221, "grad_norm": 1.2162922620773315, "learning_rate": 3.157372491615766e-05, "loss": 0.4556856632232666, "step": 430560 }, { "epoch": 2.5593974951108893, "grad_norm": 1.5099447965621948, "learning_rate": 3.1570671432697104e-05, "loss": 0.46573696136474607, "step": 430570 }, { "epoch": 2.5594569371875577, "grad_norm": 1.3069602251052856, "learning_rate": 3.15676183244168e-05, "loss": 0.5040135383605957, "step": 430580 }, { "epoch": 2.5595163792642257, "grad_norm": 1.206151008605957, "learning_rate": 3.1564565591331404e-05, "loss": 0.48095879554748533, "step": 430590 }, { "epoch": 2.5595758213408946, "grad_norm": 1.571681261062622, "learning_rate": 3.156151323345549e-05, "loss": 0.45682268142700194, "step": 430600 }, { "epoch": 2.5596352634175625, "grad_norm": 1.4285564422607422, "learning_rate": 3.155846125080364e-05, "loss": 0.4652984619140625, "step": 430610 }, { "epoch": 2.5596947054942314, "grad_norm": 1.2109911441802979, "learning_rate": 3.1555409643390524e-05, "loss": 0.4918825149536133, "step": 430620 }, { "epoch": 2.5597541475708994, "grad_norm": 1.097580909729004, "learning_rate": 3.1552358411230665e-05, "loss": 0.459493350982666, "step": 430630 }, { "epoch": 2.5598135896475678, "grad_norm": 1.5730767250061035, "learning_rate": 3.154930755433867e-05, "loss": 0.5088225364685058, "step": 430640 }, { "epoch": 2.559873031724236, "grad_norm": 1.3004697561264038, "learning_rate": 3.154625707272918e-05, "loss": 0.4665001392364502, "step": 430650 }, { "epoch": 2.5599324738009046, "grad_norm": 1.3463184833526611, "learning_rate": 3.154320696641674e-05, "loss": 0.4665006160736084, "step": 430660 }, { "epoch": 2.559991915877573, "grad_norm": 1.3075416088104248, "learning_rate": 3.154015723541597e-05, "loss": 0.48420076370239257, "step": 430670 }, { "epoch": 2.5600513579542414, "grad_norm": 1.122532606124878, "learning_rate": 3.1537107879741435e-05, "loss": 0.46071605682373046, "step": 430680 }, { "epoch": 2.56011080003091, "grad_norm": 1.030647873878479, "learning_rate": 3.153405889940775e-05, "loss": 0.5272191524505615, "step": 430690 }, { "epoch": 2.5601702421075783, "grad_norm": 1.1072065830230713, "learning_rate": 3.153101029442947e-05, "loss": 0.46420974731445314, "step": 430700 }, { "epoch": 2.5602296841842467, "grad_norm": 1.6359361410140991, "learning_rate": 3.152796206482118e-05, "loss": 0.4777512550354004, "step": 430710 }, { "epoch": 2.560289126260915, "grad_norm": 1.5755834579467773, "learning_rate": 3.1524914210597495e-05, "loss": 0.48926486968994143, "step": 430720 }, { "epoch": 2.5603485683375835, "grad_norm": 1.4995006322860718, "learning_rate": 3.1521866731772974e-05, "loss": 0.48962602615356443, "step": 430730 }, { "epoch": 2.560408010414252, "grad_norm": 1.1973178386688232, "learning_rate": 3.151881962836219e-05, "loss": 0.47432470321655273, "step": 430740 }, { "epoch": 2.5604674524909203, "grad_norm": 1.2757312059402466, "learning_rate": 3.1515772900379723e-05, "loss": 0.4649345874786377, "step": 430750 }, { "epoch": 2.5605268945675888, "grad_norm": 1.1382259130477905, "learning_rate": 3.151272654784016e-05, "loss": 0.5087654113769531, "step": 430760 }, { "epoch": 2.560586336644257, "grad_norm": 1.6488118171691895, "learning_rate": 3.150968057075804e-05, "loss": 0.520684814453125, "step": 430770 }, { "epoch": 2.560645778720925, "grad_norm": 1.0623035430908203, "learning_rate": 3.1506634969147973e-05, "loss": 0.43635969161987304, "step": 430780 }, { "epoch": 2.560705220797594, "grad_norm": 1.3614696264266968, "learning_rate": 3.150358974302452e-05, "loss": 0.4056978702545166, "step": 430790 }, { "epoch": 2.560764662874262, "grad_norm": 1.6488076448440552, "learning_rate": 3.150054489240223e-05, "loss": 0.48413453102111814, "step": 430800 }, { "epoch": 2.560824104950931, "grad_norm": 1.1429286003112793, "learning_rate": 3.149750041729568e-05, "loss": 0.4413407325744629, "step": 430810 }, { "epoch": 2.560883547027599, "grad_norm": 1.365986943244934, "learning_rate": 3.1494456317719444e-05, "loss": 0.46378498077392577, "step": 430820 }, { "epoch": 2.560942989104267, "grad_norm": 1.4030585289001465, "learning_rate": 3.149141259368807e-05, "loss": 0.451859188079834, "step": 430830 }, { "epoch": 2.5610024311809356, "grad_norm": 1.2260611057281494, "learning_rate": 3.1488369245216096e-05, "loss": 0.4699580192565918, "step": 430840 }, { "epoch": 2.561061873257604, "grad_norm": 1.1768852472305298, "learning_rate": 3.148532627231813e-05, "loss": 0.49404659271240237, "step": 430850 }, { "epoch": 2.5611213153342725, "grad_norm": 1.6580995321273804, "learning_rate": 3.1482283675008696e-05, "loss": 0.5301451683044434, "step": 430860 }, { "epoch": 2.561180757410941, "grad_norm": 1.2543938159942627, "learning_rate": 3.147924145330237e-05, "loss": 0.4394083499908447, "step": 430870 }, { "epoch": 2.5612401994876093, "grad_norm": 1.1975256204605103, "learning_rate": 3.147619960721369e-05, "loss": 0.517022705078125, "step": 430880 }, { "epoch": 2.5612996415642777, "grad_norm": 1.257460117340088, "learning_rate": 3.14731581367572e-05, "loss": 0.5319242477416992, "step": 430890 }, { "epoch": 2.561359083640946, "grad_norm": 1.5118831396102905, "learning_rate": 3.147011704194744e-05, "loss": 0.5018503665924072, "step": 430900 }, { "epoch": 2.5614185257176145, "grad_norm": 1.2321059703826904, "learning_rate": 3.1467076322798994e-05, "loss": 0.4797567367553711, "step": 430910 }, { "epoch": 2.561477967794283, "grad_norm": 1.489546298980713, "learning_rate": 3.146403597932641e-05, "loss": 0.5259503841400146, "step": 430920 }, { "epoch": 2.5615374098709514, "grad_norm": 1.340774416923523, "learning_rate": 3.146099601154419e-05, "loss": 0.45733017921447755, "step": 430930 }, { "epoch": 2.5615968519476198, "grad_norm": 1.079408049583435, "learning_rate": 3.1457956419466906e-05, "loss": 0.4737064361572266, "step": 430940 }, { "epoch": 2.561656294024288, "grad_norm": 1.0802521705627441, "learning_rate": 3.1454917203109084e-05, "loss": 0.48438348770141604, "step": 430950 }, { "epoch": 2.5617157361009566, "grad_norm": 1.7177574634552002, "learning_rate": 3.145187836248528e-05, "loss": 0.5212721824645996, "step": 430960 }, { "epoch": 2.5617751781776246, "grad_norm": 1.4039157629013062, "learning_rate": 3.144883989760999e-05, "loss": 0.5286765098571777, "step": 430970 }, { "epoch": 2.5618346202542934, "grad_norm": 1.4416999816894531, "learning_rate": 3.144580180849781e-05, "loss": 0.46657705307006836, "step": 430980 }, { "epoch": 2.5618940623309614, "grad_norm": 1.2644572257995605, "learning_rate": 3.1442764095163235e-05, "loss": 0.42622575759887693, "step": 430990 }, { "epoch": 2.5619535044076303, "grad_norm": 1.5969706773757935, "learning_rate": 3.143972675762081e-05, "loss": 0.44030394554138186, "step": 431000 }, { "epoch": 2.5620129464842982, "grad_norm": 1.502847671508789, "learning_rate": 3.143668979588505e-05, "loss": 0.48936781883239744, "step": 431010 }, { "epoch": 2.5620723885609666, "grad_norm": 1.2649469375610352, "learning_rate": 3.14336532099705e-05, "loss": 0.46905155181884767, "step": 431020 }, { "epoch": 2.562131830637635, "grad_norm": 1.3149458169937134, "learning_rate": 3.143061699989167e-05, "loss": 0.5063799858093262, "step": 431030 }, { "epoch": 2.5621912727143035, "grad_norm": 1.1663610935211182, "learning_rate": 3.1427581165663075e-05, "loss": 0.43270397186279297, "step": 431040 }, { "epoch": 2.562250714790972, "grad_norm": 1.177111029624939, "learning_rate": 3.142454570729929e-05, "loss": 0.4974383354187012, "step": 431050 }, { "epoch": 2.5623101568676403, "grad_norm": 1.197885513305664, "learning_rate": 3.1421510624814787e-05, "loss": 0.4332440376281738, "step": 431060 }, { "epoch": 2.5623695989443087, "grad_norm": 1.4604769945144653, "learning_rate": 3.141847591822408e-05, "loss": 0.5091043472290039, "step": 431070 }, { "epoch": 2.562429041020977, "grad_norm": 1.805477261543274, "learning_rate": 3.14154415875417e-05, "loss": 0.4781647682189941, "step": 431080 }, { "epoch": 2.5624884830976455, "grad_norm": 1.3122483491897583, "learning_rate": 3.1412407632782194e-05, "loss": 0.5005204200744628, "step": 431090 }, { "epoch": 2.562547925174314, "grad_norm": 1.1257894039154053, "learning_rate": 3.1409374053960024e-05, "loss": 0.46533451080322263, "step": 431100 }, { "epoch": 2.5626073672509824, "grad_norm": 1.4086856842041016, "learning_rate": 3.140634085108975e-05, "loss": 0.4527122020721436, "step": 431110 }, { "epoch": 2.562666809327651, "grad_norm": 1.1316101551055908, "learning_rate": 3.140330802418585e-05, "loss": 0.4807162284851074, "step": 431120 }, { "epoch": 2.562726251404319, "grad_norm": 1.3259782791137695, "learning_rate": 3.140027557326281e-05, "loss": 0.4710994243621826, "step": 431130 }, { "epoch": 2.5627856934809876, "grad_norm": 1.3262684345245361, "learning_rate": 3.139724349833518e-05, "loss": 0.4823695182800293, "step": 431140 }, { "epoch": 2.562845135557656, "grad_norm": 1.2816985845565796, "learning_rate": 3.139421179941746e-05, "loss": 0.45257930755615233, "step": 431150 }, { "epoch": 2.562904577634324, "grad_norm": 1.5334367752075195, "learning_rate": 3.139118047652413e-05, "loss": 0.4812502861022949, "step": 431160 }, { "epoch": 2.562964019710993, "grad_norm": 1.3881040811538696, "learning_rate": 3.138814952966971e-05, "loss": 0.5229606628417969, "step": 431170 }, { "epoch": 2.563023461787661, "grad_norm": 1.3188374042510986, "learning_rate": 3.13851189588687e-05, "loss": 0.4570788383483887, "step": 431180 }, { "epoch": 2.5630829038643292, "grad_norm": 1.4350173473358154, "learning_rate": 3.138208876413558e-05, "loss": 0.4743248462677002, "step": 431190 }, { "epoch": 2.5631423459409977, "grad_norm": 1.3421130180358887, "learning_rate": 3.137905894548484e-05, "loss": 0.4414675712585449, "step": 431200 }, { "epoch": 2.563201788017666, "grad_norm": 1.2640008926391602, "learning_rate": 3.137602950293101e-05, "loss": 0.4730551719665527, "step": 431210 }, { "epoch": 2.5632612300943345, "grad_norm": 1.417553186416626, "learning_rate": 3.137300043648855e-05, "loss": 0.5057518959045411, "step": 431220 }, { "epoch": 2.563320672171003, "grad_norm": 1.2726631164550781, "learning_rate": 3.136997174617197e-05, "loss": 0.44763479232788084, "step": 431230 }, { "epoch": 2.5633801142476713, "grad_norm": 1.447507619857788, "learning_rate": 3.136694343199575e-05, "loss": 0.4699852466583252, "step": 431240 }, { "epoch": 2.5634395563243397, "grad_norm": 1.2531447410583496, "learning_rate": 3.136391549397436e-05, "loss": 0.4464230537414551, "step": 431250 }, { "epoch": 2.563498998401008, "grad_norm": 1.2493475675582886, "learning_rate": 3.13608879321223e-05, "loss": 0.4706521511077881, "step": 431260 }, { "epoch": 2.5635584404776766, "grad_norm": 1.4248310327529907, "learning_rate": 3.135786074645406e-05, "loss": 0.4563741683959961, "step": 431270 }, { "epoch": 2.563617882554345, "grad_norm": 1.1018407344818115, "learning_rate": 3.135483393698411e-05, "loss": 0.4264535427093506, "step": 431280 }, { "epoch": 2.5636773246310134, "grad_norm": 1.5612441301345825, "learning_rate": 3.135180750372695e-05, "loss": 0.4469642639160156, "step": 431290 }, { "epoch": 2.563736766707682, "grad_norm": 1.4228371381759644, "learning_rate": 3.134878144669703e-05, "loss": 0.449248743057251, "step": 431300 }, { "epoch": 2.56379620878435, "grad_norm": 1.8024821281433105, "learning_rate": 3.134575576590883e-05, "loss": 0.5350727081298828, "step": 431310 }, { "epoch": 2.5638556508610186, "grad_norm": 1.288330078125, "learning_rate": 3.1342730461376837e-05, "loss": 0.510645866394043, "step": 431320 }, { "epoch": 2.5639150929376866, "grad_norm": 1.3669068813323975, "learning_rate": 3.13397055331155e-05, "loss": 0.5344851016998291, "step": 431330 }, { "epoch": 2.5639745350143555, "grad_norm": 1.3141180276870728, "learning_rate": 3.1336680981139316e-05, "loss": 0.4742793083190918, "step": 431340 }, { "epoch": 2.5640339770910234, "grad_norm": 1.635352373123169, "learning_rate": 3.1333656805462746e-05, "loss": 0.48451995849609375, "step": 431350 }, { "epoch": 2.5640934191676923, "grad_norm": 1.2640734910964966, "learning_rate": 3.1330633006100255e-05, "loss": 0.460053539276123, "step": 431360 }, { "epoch": 2.5641528612443603, "grad_norm": 1.3987369537353516, "learning_rate": 3.13276095830663e-05, "loss": 0.47271194458007815, "step": 431370 }, { "epoch": 2.5642123033210287, "grad_norm": 1.5406073331832886, "learning_rate": 3.132458653637536e-05, "loss": 0.4449592590332031, "step": 431380 }, { "epoch": 2.564271745397697, "grad_norm": 1.2106629610061646, "learning_rate": 3.132156386604188e-05, "loss": 0.5096634864807129, "step": 431390 }, { "epoch": 2.5643311874743655, "grad_norm": 1.369643211364746, "learning_rate": 3.1318541572080314e-05, "loss": 0.49284019470214846, "step": 431400 }, { "epoch": 2.564390629551034, "grad_norm": 1.0155562162399292, "learning_rate": 3.131551965450514e-05, "loss": 0.4748826026916504, "step": 431410 }, { "epoch": 2.5644500716277023, "grad_norm": 1.2265071868896484, "learning_rate": 3.131249811333081e-05, "loss": 0.5164544105529785, "step": 431420 }, { "epoch": 2.5645095137043707, "grad_norm": 1.3335587978363037, "learning_rate": 3.130947694857178e-05, "loss": 0.495928955078125, "step": 431430 }, { "epoch": 2.564568955781039, "grad_norm": 1.1916438341140747, "learning_rate": 3.1306456160242495e-05, "loss": 0.5428194999694824, "step": 431440 }, { "epoch": 2.5646283978577076, "grad_norm": 1.0337063074111938, "learning_rate": 3.1303435748357395e-05, "loss": 0.49094367027282715, "step": 431450 }, { "epoch": 2.564687839934376, "grad_norm": 1.9609181880950928, "learning_rate": 3.130041571293093e-05, "loss": 0.47762374877929686, "step": 431460 }, { "epoch": 2.5647472820110444, "grad_norm": 1.5277817249298096, "learning_rate": 3.129739605397757e-05, "loss": 0.5032001495361328, "step": 431470 }, { "epoch": 2.564806724087713, "grad_norm": 1.0213491916656494, "learning_rate": 3.129437677151175e-05, "loss": 0.49930710792541505, "step": 431480 }, { "epoch": 2.5648661661643812, "grad_norm": 1.2956693172454834, "learning_rate": 3.1291357865547914e-05, "loss": 0.5080275058746337, "step": 431490 }, { "epoch": 2.5649256082410496, "grad_norm": 1.60598623752594, "learning_rate": 3.12883393361005e-05, "loss": 0.46102199554443357, "step": 431500 }, { "epoch": 2.564985050317718, "grad_norm": 1.8020812273025513, "learning_rate": 3.128532118318394e-05, "loss": 0.5177384376525879, "step": 431510 }, { "epoch": 2.565044492394386, "grad_norm": 1.0895371437072754, "learning_rate": 3.1282303406812684e-05, "loss": 0.46031756401062013, "step": 431520 }, { "epoch": 2.565103934471055, "grad_norm": 1.250707745552063, "learning_rate": 3.1279286007001146e-05, "loss": 0.4525784969329834, "step": 431530 }, { "epoch": 2.565163376547723, "grad_norm": 1.0964314937591553, "learning_rate": 3.1276268983763794e-05, "loss": 0.41151719093322753, "step": 431540 }, { "epoch": 2.5652228186243917, "grad_norm": 1.6334478855133057, "learning_rate": 3.127325233711507e-05, "loss": 0.49135513305664064, "step": 431550 }, { "epoch": 2.5652822607010597, "grad_norm": 1.345191478729248, "learning_rate": 3.1270236067069325e-05, "loss": 0.47061777114868164, "step": 431560 }, { "epoch": 2.565341702777728, "grad_norm": 1.1756261587142944, "learning_rate": 3.1267220173641076e-05, "loss": 0.4988362789154053, "step": 431570 }, { "epoch": 2.5654011448543965, "grad_norm": 1.0781927108764648, "learning_rate": 3.126420465684471e-05, "loss": 0.49997758865356445, "step": 431580 }, { "epoch": 2.565460586931065, "grad_norm": 1.147801160812378, "learning_rate": 3.126118951669463e-05, "loss": 0.490936279296875, "step": 431590 }, { "epoch": 2.5655200290077333, "grad_norm": 1.4898279905319214, "learning_rate": 3.125817475320532e-05, "loss": 0.49901862144470216, "step": 431600 }, { "epoch": 2.5655794710844018, "grad_norm": 1.368046760559082, "learning_rate": 3.1255160366391185e-05, "loss": 0.45710101127624514, "step": 431610 }, { "epoch": 2.56563891316107, "grad_norm": 1.3174779415130615, "learning_rate": 3.125214635626658e-05, "loss": 0.5578034877777099, "step": 431620 }, { "epoch": 2.5656983552377386, "grad_norm": 1.0676180124282837, "learning_rate": 3.1249132722846e-05, "loss": 0.44633045196533205, "step": 431630 }, { "epoch": 2.565757797314407, "grad_norm": 1.1800538301467896, "learning_rate": 3.124611946614384e-05, "loss": 0.5067717552185058, "step": 431640 }, { "epoch": 2.5658172393910754, "grad_norm": 1.4047157764434814, "learning_rate": 3.124310658617449e-05, "loss": 0.4495397567749023, "step": 431650 }, { "epoch": 2.565876681467744, "grad_norm": 1.0903278589248657, "learning_rate": 3.124009408295238e-05, "loss": 0.4941405296325684, "step": 431660 }, { "epoch": 2.5659361235444123, "grad_norm": 1.2844759225845337, "learning_rate": 3.123708195649194e-05, "loss": 0.45210628509521483, "step": 431670 }, { "epoch": 2.5659955656210807, "grad_norm": 1.1180496215820312, "learning_rate": 3.123407020680755e-05, "loss": 0.4402350425720215, "step": 431680 }, { "epoch": 2.566055007697749, "grad_norm": 1.2945783138275146, "learning_rate": 3.1231058833913605e-05, "loss": 0.4801011085510254, "step": 431690 }, { "epoch": 2.5661144497744175, "grad_norm": 1.0031836032867432, "learning_rate": 3.1228047837824556e-05, "loss": 0.44646458625793456, "step": 431700 }, { "epoch": 2.5661738918510855, "grad_norm": 1.366309404373169, "learning_rate": 3.122503721855479e-05, "loss": 0.5001355171203613, "step": 431710 }, { "epoch": 2.5662333339277543, "grad_norm": 1.4914895296096802, "learning_rate": 3.122202697611869e-05, "loss": 0.4996326446533203, "step": 431720 }, { "epoch": 2.5662927760044223, "grad_norm": 1.3727810382843018, "learning_rate": 3.121901711053067e-05, "loss": 0.4824127197265625, "step": 431730 }, { "epoch": 2.566352218081091, "grad_norm": 0.9640752077102661, "learning_rate": 3.1216007621805125e-05, "loss": 0.5046931743621826, "step": 431740 }, { "epoch": 2.566411660157759, "grad_norm": 1.4070919752120972, "learning_rate": 3.1212998509956445e-05, "loss": 0.5310305118560791, "step": 431750 }, { "epoch": 2.5664711022344275, "grad_norm": 1.6839674711227417, "learning_rate": 3.120998977499904e-05, "loss": 0.49805850982666017, "step": 431760 }, { "epoch": 2.566530544311096, "grad_norm": 1.4461398124694824, "learning_rate": 3.1206981416947295e-05, "loss": 0.484101390838623, "step": 431770 }, { "epoch": 2.5665899863877644, "grad_norm": 1.166116714477539, "learning_rate": 3.1203973435815596e-05, "loss": 0.41974363327026365, "step": 431780 }, { "epoch": 2.566649428464433, "grad_norm": 1.0808571577072144, "learning_rate": 3.1200965831618356e-05, "loss": 0.48068528175354003, "step": 431790 }, { "epoch": 2.566708870541101, "grad_norm": 1.3016817569732666, "learning_rate": 3.119795860436993e-05, "loss": 0.4633518695831299, "step": 431800 }, { "epoch": 2.5667683126177696, "grad_norm": 1.1914173364639282, "learning_rate": 3.119495175408472e-05, "loss": 0.431368350982666, "step": 431810 }, { "epoch": 2.566827754694438, "grad_norm": 1.2014033794403076, "learning_rate": 3.119194528077709e-05, "loss": 0.47357959747314454, "step": 431820 }, { "epoch": 2.5668871967711064, "grad_norm": 1.2223012447357178, "learning_rate": 3.118893918446146e-05, "loss": 0.4889038562774658, "step": 431830 }, { "epoch": 2.566946638847775, "grad_norm": 1.3787615299224854, "learning_rate": 3.118593346515218e-05, "loss": 0.4855769634246826, "step": 431840 }, { "epoch": 2.5670060809244433, "grad_norm": 1.4423843622207642, "learning_rate": 3.118292812286364e-05, "loss": 0.48331351280212403, "step": 431850 }, { "epoch": 2.5670655230011117, "grad_norm": 1.184783935546875, "learning_rate": 3.1179923157610225e-05, "loss": 0.4971463203430176, "step": 431860 }, { "epoch": 2.56712496507778, "grad_norm": 1.5350730419158936, "learning_rate": 3.117691856940629e-05, "loss": 0.46497440338134766, "step": 431870 }, { "epoch": 2.5671844071544485, "grad_norm": 1.2537957429885864, "learning_rate": 3.117391435826621e-05, "loss": 0.4810323715209961, "step": 431880 }, { "epoch": 2.567243849231117, "grad_norm": 1.5131062269210815, "learning_rate": 3.1170910524204355e-05, "loss": 0.4489095211029053, "step": 431890 }, { "epoch": 2.567303291307785, "grad_norm": 1.35758638381958, "learning_rate": 3.116790706723513e-05, "loss": 0.5161635398864746, "step": 431900 }, { "epoch": 2.5673627333844538, "grad_norm": 1.3824955224990845, "learning_rate": 3.1164903987372854e-05, "loss": 0.44222068786621094, "step": 431910 }, { "epoch": 2.5674221754611217, "grad_norm": 1.357966661453247, "learning_rate": 3.116190128463193e-05, "loss": 0.43457651138305664, "step": 431920 }, { "epoch": 2.56748161753779, "grad_norm": 1.3496220111846924, "learning_rate": 3.115889895902669e-05, "loss": 0.46418046951293945, "step": 431930 }, { "epoch": 2.5675410596144586, "grad_norm": 1.300734043121338, "learning_rate": 3.115589701057152e-05, "loss": 0.4274118423461914, "step": 431940 }, { "epoch": 2.567600501691127, "grad_norm": 1.3996609449386597, "learning_rate": 3.115289543928076e-05, "loss": 0.5342197418212891, "step": 431950 }, { "epoch": 2.5676599437677954, "grad_norm": 0.975525438785553, "learning_rate": 3.114989424516879e-05, "loss": 0.4163971900939941, "step": 431960 }, { "epoch": 2.567719385844464, "grad_norm": 1.2112582921981812, "learning_rate": 3.1146893428249964e-05, "loss": 0.44900102615356446, "step": 431970 }, { "epoch": 2.567778827921132, "grad_norm": 1.3958266973495483, "learning_rate": 3.114389298853863e-05, "loss": 0.44577751159667967, "step": 431980 }, { "epoch": 2.5678382699978006, "grad_norm": 1.3271968364715576, "learning_rate": 3.114089292604913e-05, "loss": 0.46423492431640623, "step": 431990 }, { "epoch": 2.567897712074469, "grad_norm": 1.5732686519622803, "learning_rate": 3.113789324079584e-05, "loss": 0.4703102111816406, "step": 432000 }, { "epoch": 2.5679571541511375, "grad_norm": 1.4899319410324097, "learning_rate": 3.113489393279309e-05, "loss": 0.5167441368103027, "step": 432010 }, { "epoch": 2.568016596227806, "grad_norm": 1.4527615308761597, "learning_rate": 3.113189500205522e-05, "loss": 0.48691768646240235, "step": 432020 }, { "epoch": 2.5680760383044743, "grad_norm": 1.1916921138763428, "learning_rate": 3.11288964485966e-05, "loss": 0.4645721435546875, "step": 432030 }, { "epoch": 2.5681354803811427, "grad_norm": 1.2352858781814575, "learning_rate": 3.1125898272431594e-05, "loss": 0.4668882369995117, "step": 432040 }, { "epoch": 2.568194922457811, "grad_norm": 1.2362723350524902, "learning_rate": 3.112290047357447e-05, "loss": 0.4637276649475098, "step": 432050 }, { "epoch": 2.5682543645344795, "grad_norm": 1.1503485441207886, "learning_rate": 3.111990305203963e-05, "loss": 0.43117809295654297, "step": 432060 }, { "epoch": 2.5683138066111475, "grad_norm": 1.1112947463989258, "learning_rate": 3.1116906007841394e-05, "loss": 0.4341446876525879, "step": 432070 }, { "epoch": 2.5683732486878164, "grad_norm": 1.472114086151123, "learning_rate": 3.111390934099409e-05, "loss": 0.504870080947876, "step": 432080 }, { "epoch": 2.5684326907644843, "grad_norm": 1.3251558542251587, "learning_rate": 3.111091305151208e-05, "loss": 0.48836679458618165, "step": 432090 }, { "epoch": 2.568492132841153, "grad_norm": 1.1609432697296143, "learning_rate": 3.110791713940969e-05, "loss": 0.4828887939453125, "step": 432100 }, { "epoch": 2.568551574917821, "grad_norm": 1.3920843601226807, "learning_rate": 3.110492160470122e-05, "loss": 0.502322769165039, "step": 432110 }, { "epoch": 2.5686110169944896, "grad_norm": 1.2190790176391602, "learning_rate": 3.110192644740103e-05, "loss": 0.5044840812683106, "step": 432120 }, { "epoch": 2.568670459071158, "grad_norm": 1.3559508323669434, "learning_rate": 3.109893166752344e-05, "loss": 0.48477926254272463, "step": 432130 }, { "epoch": 2.5687299011478264, "grad_norm": 1.3598421812057495, "learning_rate": 3.109593726508278e-05, "loss": 0.45218381881713865, "step": 432140 }, { "epoch": 2.568789343224495, "grad_norm": 1.4730579853057861, "learning_rate": 3.1092943240093345e-05, "loss": 0.4427022933959961, "step": 432150 }, { "epoch": 2.5688487853011632, "grad_norm": 1.9303663969039917, "learning_rate": 3.1089949592569535e-05, "loss": 0.4750337600708008, "step": 432160 }, { "epoch": 2.5689082273778316, "grad_norm": 1.720218300819397, "learning_rate": 3.1086956322525584e-05, "loss": 0.5145634651184082, "step": 432170 }, { "epoch": 2.5689676694545, "grad_norm": 1.2067019939422607, "learning_rate": 3.108396342997584e-05, "loss": 0.5042967319488525, "step": 432180 }, { "epoch": 2.5690271115311685, "grad_norm": 1.1366143226623535, "learning_rate": 3.1080970914934626e-05, "loss": 0.40901908874511717, "step": 432190 }, { "epoch": 2.569086553607837, "grad_norm": 1.3947715759277344, "learning_rate": 3.107797877741627e-05, "loss": 0.4790228843688965, "step": 432200 }, { "epoch": 2.5691459956845053, "grad_norm": 1.5456204414367676, "learning_rate": 3.107498701743504e-05, "loss": 0.5250434398651123, "step": 432210 }, { "epoch": 2.5692054377611737, "grad_norm": 1.3228168487548828, "learning_rate": 3.107199563500533e-05, "loss": 0.4604204177856445, "step": 432220 }, { "epoch": 2.569264879837842, "grad_norm": 1.3794748783111572, "learning_rate": 3.1069004630141373e-05, "loss": 0.44898533821105957, "step": 432230 }, { "epoch": 2.5693243219145105, "grad_norm": 1.0010738372802734, "learning_rate": 3.106601400285749e-05, "loss": 0.49843902587890626, "step": 432240 }, { "epoch": 2.569383763991179, "grad_norm": 1.1945226192474365, "learning_rate": 3.106302375316801e-05, "loss": 0.4983349323272705, "step": 432250 }, { "epoch": 2.569443206067847, "grad_norm": 0.9489063620567322, "learning_rate": 3.106003388108724e-05, "loss": 0.46936330795288084, "step": 432260 }, { "epoch": 2.569502648144516, "grad_norm": 1.2763251066207886, "learning_rate": 3.105704438662946e-05, "loss": 0.48372421264648435, "step": 432270 }, { "epoch": 2.5695620902211838, "grad_norm": 1.034642219543457, "learning_rate": 3.105405526980898e-05, "loss": 0.4647844314575195, "step": 432280 }, { "epoch": 2.5696215322978526, "grad_norm": 1.1808583736419678, "learning_rate": 3.1051066530640106e-05, "loss": 0.46349153518676756, "step": 432290 }, { "epoch": 2.5696809743745206, "grad_norm": 1.4448304176330566, "learning_rate": 3.104807816913712e-05, "loss": 0.4893601417541504, "step": 432300 }, { "epoch": 2.569740416451189, "grad_norm": 1.3128496408462524, "learning_rate": 3.104509018531432e-05, "loss": 0.518300724029541, "step": 432310 }, { "epoch": 2.5697998585278574, "grad_norm": 1.3149961233139038, "learning_rate": 3.1042102579186016e-05, "loss": 0.5416717529296875, "step": 432320 }, { "epoch": 2.569859300604526, "grad_norm": 1.4680964946746826, "learning_rate": 3.103911535076649e-05, "loss": 0.4931805610656738, "step": 432330 }, { "epoch": 2.5699187426811942, "grad_norm": 1.1903964281082153, "learning_rate": 3.1036128500070026e-05, "loss": 0.4598383903503418, "step": 432340 }, { "epoch": 2.5699781847578627, "grad_norm": 0.9483336210250854, "learning_rate": 3.1033142027110924e-05, "loss": 0.4704704284667969, "step": 432350 }, { "epoch": 2.570037626834531, "grad_norm": 1.2929185628890991, "learning_rate": 3.103015593190347e-05, "loss": 0.442429780960083, "step": 432360 }, { "epoch": 2.5700970689111995, "grad_norm": 1.582894206047058, "learning_rate": 3.102717021446194e-05, "loss": 0.5180397987365722, "step": 432370 }, { "epoch": 2.570156510987868, "grad_norm": 1.427302598953247, "learning_rate": 3.102418487480059e-05, "loss": 0.47199597358703616, "step": 432380 }, { "epoch": 2.5702159530645363, "grad_norm": 1.1493699550628662, "learning_rate": 3.1021199912933755e-05, "loss": 0.43785982131958007, "step": 432390 }, { "epoch": 2.5702753951412047, "grad_norm": 1.346291422843933, "learning_rate": 3.1018215328875695e-05, "loss": 0.4904189109802246, "step": 432400 }, { "epoch": 2.570334837217873, "grad_norm": 1.2842317819595337, "learning_rate": 3.101523112264067e-05, "loss": 0.44491939544677733, "step": 432410 }, { "epoch": 2.5703942792945416, "grad_norm": 1.0772075653076172, "learning_rate": 3.101224729424297e-05, "loss": 0.47277493476867677, "step": 432420 }, { "epoch": 2.57045372137121, "grad_norm": 1.0506577491760254, "learning_rate": 3.100926384369687e-05, "loss": 0.4513416767120361, "step": 432430 }, { "epoch": 2.5705131634478784, "grad_norm": 1.2172778844833374, "learning_rate": 3.100628077101662e-05, "loss": 0.4965828895568848, "step": 432440 }, { "epoch": 2.5705726055245464, "grad_norm": 1.0195701122283936, "learning_rate": 3.100329807621652e-05, "loss": 0.4148555755615234, "step": 432450 }, { "epoch": 2.570632047601215, "grad_norm": 1.1449384689331055, "learning_rate": 3.100031575931083e-05, "loss": 0.5083215713500977, "step": 432460 }, { "epoch": 2.570691489677883, "grad_norm": 1.2007092237472534, "learning_rate": 3.099733382031381e-05, "loss": 0.46378021240234374, "step": 432470 }, { "epoch": 2.570750931754552, "grad_norm": 1.4280402660369873, "learning_rate": 3.0994352259239724e-05, "loss": 0.46198110580444335, "step": 432480 }, { "epoch": 2.57081037383122, "grad_norm": 1.3302913904190063, "learning_rate": 3.099137107610284e-05, "loss": 0.44678845405578616, "step": 432490 }, { "epoch": 2.5708698159078884, "grad_norm": 1.6488094329833984, "learning_rate": 3.098839027091742e-05, "loss": 0.47956094741821287, "step": 432500 }, { "epoch": 2.570929257984557, "grad_norm": 1.542781114578247, "learning_rate": 3.098540984369769e-05, "loss": 0.534184741973877, "step": 432510 }, { "epoch": 2.5709887000612253, "grad_norm": 0.9560126662254333, "learning_rate": 3.098242979445797e-05, "loss": 0.42113409042358396, "step": 432520 }, { "epoch": 2.5710481421378937, "grad_norm": 1.1138699054718018, "learning_rate": 3.09794501232125e-05, "loss": 0.429914665222168, "step": 432530 }, { "epoch": 2.571107584214562, "grad_norm": 1.1375095844268799, "learning_rate": 3.0976470829975474e-05, "loss": 0.43882203102111816, "step": 432540 }, { "epoch": 2.5711670262912305, "grad_norm": 1.194130778312683, "learning_rate": 3.09734919147612e-05, "loss": 0.4458927631378174, "step": 432550 }, { "epoch": 2.571226468367899, "grad_norm": 1.412746787071228, "learning_rate": 3.097051337758392e-05, "loss": 0.47580819129943847, "step": 432560 }, { "epoch": 2.5712859104445673, "grad_norm": 1.3467227220535278, "learning_rate": 3.096753521845786e-05, "loss": 0.45607690811157225, "step": 432570 }, { "epoch": 2.5713453525212357, "grad_norm": 1.0098446607589722, "learning_rate": 3.0964557437397305e-05, "loss": 0.4842985153198242, "step": 432580 }, { "epoch": 2.571404794597904, "grad_norm": 1.6914451122283936, "learning_rate": 3.096158003441649e-05, "loss": 0.468660831451416, "step": 432590 }, { "epoch": 2.5714642366745726, "grad_norm": 1.332028865814209, "learning_rate": 3.095860300952961e-05, "loss": 0.46746101379394533, "step": 432600 }, { "epoch": 2.571523678751241, "grad_norm": 1.5358275175094604, "learning_rate": 3.095562636275096e-05, "loss": 0.4542635440826416, "step": 432610 }, { "epoch": 2.5715831208279094, "grad_norm": 1.5640488862991333, "learning_rate": 3.095265009409475e-05, "loss": 0.46956443786621094, "step": 432620 }, { "epoch": 2.571642562904578, "grad_norm": 1.366058111190796, "learning_rate": 3.094967420357524e-05, "loss": 0.4195197582244873, "step": 432630 }, { "epoch": 2.571702004981246, "grad_norm": 1.1879867315292358, "learning_rate": 3.094669869120665e-05, "loss": 0.4608620643615723, "step": 432640 }, { "epoch": 2.5717614470579147, "grad_norm": 1.2182023525238037, "learning_rate": 3.0943723557003245e-05, "loss": 0.46738557815551757, "step": 432650 }, { "epoch": 2.5718208891345826, "grad_norm": 1.211509346961975, "learning_rate": 3.0940748800979215e-05, "loss": 0.4657078742980957, "step": 432660 }, { "epoch": 2.571880331211251, "grad_norm": 1.2955912351608276, "learning_rate": 3.093777442314878e-05, "loss": 0.49136981964111326, "step": 432670 }, { "epoch": 2.5719397732879195, "grad_norm": 1.3183863162994385, "learning_rate": 3.093480042352621e-05, "loss": 0.5358704090118408, "step": 432680 }, { "epoch": 2.571999215364588, "grad_norm": 1.1782861948013306, "learning_rate": 3.0931826802125726e-05, "loss": 0.5034660816192627, "step": 432690 }, { "epoch": 2.5720586574412563, "grad_norm": 1.535491704940796, "learning_rate": 3.0928853558961514e-05, "loss": 0.4024936676025391, "step": 432700 }, { "epoch": 2.5721180995179247, "grad_norm": 1.4416002035140991, "learning_rate": 3.0925880694047874e-05, "loss": 0.4562635898590088, "step": 432710 }, { "epoch": 2.572177541594593, "grad_norm": 1.2470121383666992, "learning_rate": 3.092290820739896e-05, "loss": 0.4596571922302246, "step": 432720 }, { "epoch": 2.5722369836712615, "grad_norm": 1.4213528633117676, "learning_rate": 3.091993609902901e-05, "loss": 0.48249568939208987, "step": 432730 }, { "epoch": 2.57229642574793, "grad_norm": 1.3760590553283691, "learning_rate": 3.091696436895221e-05, "loss": 0.44100055694580076, "step": 432740 }, { "epoch": 2.5723558678245984, "grad_norm": 1.6115719079971313, "learning_rate": 3.091399301718283e-05, "loss": 0.44263129234313964, "step": 432750 }, { "epoch": 2.5724153099012668, "grad_norm": 1.3778705596923828, "learning_rate": 3.091102204373508e-05, "loss": 0.509044885635376, "step": 432760 }, { "epoch": 2.572474751977935, "grad_norm": 1.383416771888733, "learning_rate": 3.090805144862313e-05, "loss": 0.4636493682861328, "step": 432770 }, { "epoch": 2.5725341940546036, "grad_norm": 1.0650945901870728, "learning_rate": 3.090508123186123e-05, "loss": 0.4738018989562988, "step": 432780 }, { "epoch": 2.572593636131272, "grad_norm": 1.0549464225769043, "learning_rate": 3.0902111393463575e-05, "loss": 0.4088605403900146, "step": 432790 }, { "epoch": 2.5726530782079404, "grad_norm": 1.3975515365600586, "learning_rate": 3.0899141933444344e-05, "loss": 0.44855308532714844, "step": 432800 }, { "epoch": 2.5727125202846084, "grad_norm": 1.4905686378479004, "learning_rate": 3.089617285181778e-05, "loss": 0.4457892417907715, "step": 432810 }, { "epoch": 2.5727719623612773, "grad_norm": 1.184849500656128, "learning_rate": 3.089320414859809e-05, "loss": 0.43293123245239257, "step": 432820 }, { "epoch": 2.5728314044379452, "grad_norm": 1.6557023525238037, "learning_rate": 3.0890235823799444e-05, "loss": 0.47644920349121095, "step": 432830 }, { "epoch": 2.572890846514614, "grad_norm": 0.9637899398803711, "learning_rate": 3.0887267877436065e-05, "loss": 0.48479633331298827, "step": 432840 }, { "epoch": 2.572950288591282, "grad_norm": 1.0972633361816406, "learning_rate": 3.0884300309522134e-05, "loss": 0.48642640113830565, "step": 432850 }, { "epoch": 2.5730097306679505, "grad_norm": 1.1879483461380005, "learning_rate": 3.088133312007186e-05, "loss": 0.4557713508605957, "step": 432860 }, { "epoch": 2.573069172744619, "grad_norm": 0.8951246738433838, "learning_rate": 3.087836630909942e-05, "loss": 0.43991656303405763, "step": 432870 }, { "epoch": 2.5731286148212873, "grad_norm": 1.4837055206298828, "learning_rate": 3.087539987661903e-05, "loss": 0.47809429168701173, "step": 432880 }, { "epoch": 2.5731880568979557, "grad_norm": 1.5315264463424683, "learning_rate": 3.0872433822644866e-05, "loss": 0.48616418838500974, "step": 432890 }, { "epoch": 2.573247498974624, "grad_norm": 1.7794855833053589, "learning_rate": 3.086946814719113e-05, "loss": 0.4529251575469971, "step": 432900 }, { "epoch": 2.5733069410512925, "grad_norm": 1.1419181823730469, "learning_rate": 3.0866502850271986e-05, "loss": 0.4359130859375, "step": 432910 }, { "epoch": 2.573366383127961, "grad_norm": 1.449462890625, "learning_rate": 3.086353793190164e-05, "loss": 0.49144630432128905, "step": 432920 }, { "epoch": 2.5734258252046294, "grad_norm": 1.2790095806121826, "learning_rate": 3.086057339209424e-05, "loss": 0.47882542610168455, "step": 432930 }, { "epoch": 2.573485267281298, "grad_norm": 0.8350799679756165, "learning_rate": 3.085760923086401e-05, "loss": 0.45125579833984375, "step": 432940 }, { "epoch": 2.573544709357966, "grad_norm": 1.4683477878570557, "learning_rate": 3.085464544822512e-05, "loss": 0.48042144775390627, "step": 432950 }, { "epoch": 2.5736041514346346, "grad_norm": 1.306850790977478, "learning_rate": 3.0851682044191754e-05, "loss": 0.48957242965698244, "step": 432960 }, { "epoch": 2.573663593511303, "grad_norm": 1.2186278104782104, "learning_rate": 3.084871901877806e-05, "loss": 0.4630765914916992, "step": 432970 }, { "epoch": 2.5737230355879714, "grad_norm": 1.1614015102386475, "learning_rate": 3.0845756371998224e-05, "loss": 0.4497097969055176, "step": 432980 }, { "epoch": 2.57378247766464, "grad_norm": 2.4383726119995117, "learning_rate": 3.084279410386643e-05, "loss": 0.5108757019042969, "step": 432990 }, { "epoch": 2.573841919741308, "grad_norm": 1.4955618381500244, "learning_rate": 3.0839832214396816e-05, "loss": 0.46460161209106443, "step": 433000 }, { "epoch": 2.5739013618179767, "grad_norm": 1.375722050666809, "learning_rate": 3.083687070360359e-05, "loss": 0.49454336166381835, "step": 433010 }, { "epoch": 2.5739608038946447, "grad_norm": 1.3501358032226562, "learning_rate": 3.0833909571500916e-05, "loss": 0.4541541576385498, "step": 433020 }, { "epoch": 2.5740202459713135, "grad_norm": 1.7836545705795288, "learning_rate": 3.0830948818102945e-05, "loss": 0.44868130683898927, "step": 433030 }, { "epoch": 2.5740796880479815, "grad_norm": 1.5065103769302368, "learning_rate": 3.082798844342384e-05, "loss": 0.4772099494934082, "step": 433040 }, { "epoch": 2.57413913012465, "grad_norm": 1.130957841873169, "learning_rate": 3.082502844747776e-05, "loss": 0.4913550853729248, "step": 433050 }, { "epoch": 2.5741985722013183, "grad_norm": 1.3795748949050903, "learning_rate": 3.0822068830278856e-05, "loss": 0.4955721855163574, "step": 433060 }, { "epoch": 2.5742580142779867, "grad_norm": 1.8070429563522339, "learning_rate": 3.081910959184131e-05, "loss": 0.4850583553314209, "step": 433070 }, { "epoch": 2.574317456354655, "grad_norm": 1.3288133144378662, "learning_rate": 3.081615073217928e-05, "loss": 0.459717845916748, "step": 433080 }, { "epoch": 2.5743768984313236, "grad_norm": 1.4325710535049438, "learning_rate": 3.081319225130689e-05, "loss": 0.442132568359375, "step": 433090 }, { "epoch": 2.574436340507992, "grad_norm": 1.2476191520690918, "learning_rate": 3.0810234149238327e-05, "loss": 0.43386340141296387, "step": 433100 }, { "epoch": 2.5744957825846604, "grad_norm": 1.232568621635437, "learning_rate": 3.080727642598771e-05, "loss": 0.5259856700897216, "step": 433110 }, { "epoch": 2.574555224661329, "grad_norm": 1.2051595449447632, "learning_rate": 3.0804319081569216e-05, "loss": 0.4683671951293945, "step": 433120 }, { "epoch": 2.574614666737997, "grad_norm": 1.1159982681274414, "learning_rate": 3.080136211599694e-05, "loss": 0.4416967391967773, "step": 433130 }, { "epoch": 2.5746741088146656, "grad_norm": 1.2887483835220337, "learning_rate": 3.0798405529285125e-05, "loss": 0.4723085403442383, "step": 433140 }, { "epoch": 2.574733550891334, "grad_norm": 1.3314560651779175, "learning_rate": 3.079544932144782e-05, "loss": 0.48842535018920896, "step": 433150 }, { "epoch": 2.5747929929680025, "grad_norm": 1.2178255319595337, "learning_rate": 3.07924934924992e-05, "loss": 0.45850210189819335, "step": 433160 }, { "epoch": 2.574852435044671, "grad_norm": 1.509570837020874, "learning_rate": 3.0789538042453404e-05, "loss": 0.5181695461273194, "step": 433170 }, { "epoch": 2.5749118771213393, "grad_norm": 1.3275952339172363, "learning_rate": 3.0786582971324575e-05, "loss": 0.437069034576416, "step": 433180 }, { "epoch": 2.5749713191980073, "grad_norm": 1.3862043619155884, "learning_rate": 3.078362827912684e-05, "loss": 0.49536714553833006, "step": 433190 }, { "epoch": 2.575030761274676, "grad_norm": 1.3329039812088013, "learning_rate": 3.0780673965874375e-05, "loss": 0.49875826835632325, "step": 433200 }, { "epoch": 2.575090203351344, "grad_norm": 1.2888646125793457, "learning_rate": 3.077772003158124e-05, "loss": 0.5229434967041016, "step": 433210 }, { "epoch": 2.575149645428013, "grad_norm": 1.2232091426849365, "learning_rate": 3.077476647626161e-05, "loss": 0.4525611400604248, "step": 433220 }, { "epoch": 2.575209087504681, "grad_norm": 1.424414873123169, "learning_rate": 3.0771813299929594e-05, "loss": 0.46997838020324706, "step": 433230 }, { "epoch": 2.5752685295813493, "grad_norm": 1.3163028955459595, "learning_rate": 3.076886050259935e-05, "loss": 0.44723854064941404, "step": 433240 }, { "epoch": 2.5753279716580177, "grad_norm": 1.2768117189407349, "learning_rate": 3.076590808428498e-05, "loss": 0.4813788414001465, "step": 433250 }, { "epoch": 2.575387413734686, "grad_norm": 1.5824029445648193, "learning_rate": 3.076295604500062e-05, "loss": 0.45250229835510253, "step": 433260 }, { "epoch": 2.5754468558113546, "grad_norm": 1.0606871843338013, "learning_rate": 3.0760004384760374e-05, "loss": 0.4342008113861084, "step": 433270 }, { "epoch": 2.575506297888023, "grad_norm": 1.4524827003479004, "learning_rate": 3.0757053103578376e-05, "loss": 0.4486096858978271, "step": 433280 }, { "epoch": 2.5755657399646914, "grad_norm": 1.4141178131103516, "learning_rate": 3.075410220146872e-05, "loss": 0.516396951675415, "step": 433290 }, { "epoch": 2.57562518204136, "grad_norm": 1.3420759439468384, "learning_rate": 3.075115167844556e-05, "loss": 0.4306159973144531, "step": 433300 }, { "epoch": 2.5756846241180282, "grad_norm": 0.9856551885604858, "learning_rate": 3.074820153452298e-05, "loss": 0.48860559463500974, "step": 433310 }, { "epoch": 2.5757440661946966, "grad_norm": 1.2887163162231445, "learning_rate": 3.0745251769715114e-05, "loss": 0.45420546531677247, "step": 433320 }, { "epoch": 2.575803508271365, "grad_norm": 1.1957775354385376, "learning_rate": 3.074230238403606e-05, "loss": 0.5138968467712403, "step": 433330 }, { "epoch": 2.5758629503480335, "grad_norm": 1.4774342775344849, "learning_rate": 3.0739353377499936e-05, "loss": 0.4385956287384033, "step": 433340 }, { "epoch": 2.575922392424702, "grad_norm": 1.5138312578201294, "learning_rate": 3.073640475012084e-05, "loss": 0.479995584487915, "step": 433350 }, { "epoch": 2.5759818345013703, "grad_norm": 1.0267497301101685, "learning_rate": 3.0733456501912855e-05, "loss": 0.46276402473449707, "step": 433360 }, { "epoch": 2.5760412765780387, "grad_norm": 1.537410855293274, "learning_rate": 3.0730508632890145e-05, "loss": 0.48652172088623047, "step": 433370 }, { "epoch": 2.5761007186547067, "grad_norm": 1.0329116582870483, "learning_rate": 3.072756114306676e-05, "loss": 0.4761174201965332, "step": 433380 }, { "epoch": 2.5761601607313755, "grad_norm": 1.6074869632720947, "learning_rate": 3.072461403245682e-05, "loss": 0.4737374305725098, "step": 433390 }, { "epoch": 2.5762196028080435, "grad_norm": 1.1841810941696167, "learning_rate": 3.0721667301074416e-05, "loss": 0.5120886325836181, "step": 433400 }, { "epoch": 2.576279044884712, "grad_norm": 1.2188396453857422, "learning_rate": 3.071872094893365e-05, "loss": 0.44894704818725584, "step": 433410 }, { "epoch": 2.5763384869613803, "grad_norm": 1.30366051197052, "learning_rate": 3.07157749760486e-05, "loss": 0.45215229988098143, "step": 433420 }, { "epoch": 2.5763979290380488, "grad_norm": 1.3237167596817017, "learning_rate": 3.071282938243339e-05, "loss": 0.4828327655792236, "step": 433430 }, { "epoch": 2.576457371114717, "grad_norm": 1.0051859617233276, "learning_rate": 3.0709884168102076e-05, "loss": 0.46121959686279296, "step": 433440 }, { "epoch": 2.5765168131913856, "grad_norm": 1.1717547178268433, "learning_rate": 3.070693933306879e-05, "loss": 0.4983526229858398, "step": 433450 }, { "epoch": 2.576576255268054, "grad_norm": 1.2988981008529663, "learning_rate": 3.070399487734757e-05, "loss": 0.47575016021728517, "step": 433460 }, { "epoch": 2.5766356973447224, "grad_norm": 1.2298249006271362, "learning_rate": 3.070105080095254e-05, "loss": 0.48306965827941895, "step": 433470 }, { "epoch": 2.576695139421391, "grad_norm": 1.282669186592102, "learning_rate": 3.069810710389777e-05, "loss": 0.4586376190185547, "step": 433480 }, { "epoch": 2.5767545814980592, "grad_norm": 1.2286454439163208, "learning_rate": 3.069516378619731e-05, "loss": 0.45114593505859374, "step": 433490 }, { "epoch": 2.5768140235747277, "grad_norm": 1.5934382677078247, "learning_rate": 3.069222084786529e-05, "loss": 0.5221089363098145, "step": 433500 }, { "epoch": 2.576873465651396, "grad_norm": 2.1125078201293945, "learning_rate": 3.0689278288915767e-05, "loss": 0.4783298492431641, "step": 433510 }, { "epoch": 2.5769329077280645, "grad_norm": 1.2272130250930786, "learning_rate": 3.068633610936282e-05, "loss": 0.4483355522155762, "step": 433520 }, { "epoch": 2.576992349804733, "grad_norm": 1.304644227027893, "learning_rate": 3.068339430922052e-05, "loss": 0.47277183532714845, "step": 433530 }, { "epoch": 2.5770517918814013, "grad_norm": 1.0300618410110474, "learning_rate": 3.0680452888502936e-05, "loss": 0.46100282669067383, "step": 433540 }, { "epoch": 2.5771112339580693, "grad_norm": 1.348515272140503, "learning_rate": 3.0677511847224135e-05, "loss": 0.4760167121887207, "step": 433550 }, { "epoch": 2.577170676034738, "grad_norm": 1.3467609882354736, "learning_rate": 3.0674571185398206e-05, "loss": 0.42772707939147947, "step": 433560 }, { "epoch": 2.577230118111406, "grad_norm": 1.2195756435394287, "learning_rate": 3.067163090303921e-05, "loss": 0.44299607276916503, "step": 433570 }, { "epoch": 2.577289560188075, "grad_norm": 1.3925855159759521, "learning_rate": 3.066869100016122e-05, "loss": 0.5062532424926758, "step": 433580 }, { "epoch": 2.577349002264743, "grad_norm": 1.3855684995651245, "learning_rate": 3.0665751476778244e-05, "loss": 0.4780995845794678, "step": 433590 }, { "epoch": 2.5774084443414114, "grad_norm": 1.2964437007904053, "learning_rate": 3.066281233290441e-05, "loss": 0.5215299606323243, "step": 433600 }, { "epoch": 2.57746788641808, "grad_norm": 1.2997281551361084, "learning_rate": 3.065987356855376e-05, "loss": 0.41527976989746096, "step": 433610 }, { "epoch": 2.577527328494748, "grad_norm": 1.4363733530044556, "learning_rate": 3.065693518374033e-05, "loss": 0.5211551666259766, "step": 433620 }, { "epoch": 2.5775867705714166, "grad_norm": 1.3176828622817993, "learning_rate": 3.06539971784782e-05, "loss": 0.47981977462768555, "step": 433630 }, { "epoch": 2.577646212648085, "grad_norm": 1.3598276376724243, "learning_rate": 3.065105955278144e-05, "loss": 0.46063814163208006, "step": 433640 }, { "epoch": 2.5777056547247534, "grad_norm": 1.2326881885528564, "learning_rate": 3.064812230666404e-05, "loss": 0.44434032440185545, "step": 433650 }, { "epoch": 2.577765096801422, "grad_norm": 1.3056801557540894, "learning_rate": 3.0645185440140113e-05, "loss": 0.4649784564971924, "step": 433660 }, { "epoch": 2.5778245388780903, "grad_norm": 1.0098458528518677, "learning_rate": 3.0642248953223686e-05, "loss": 0.5644610404968262, "step": 433670 }, { "epoch": 2.5778839809547587, "grad_norm": 1.073289394378662, "learning_rate": 3.063931284592878e-05, "loss": 0.4593712329864502, "step": 433680 }, { "epoch": 2.577943423031427, "grad_norm": 1.646636724472046, "learning_rate": 3.063637711826949e-05, "loss": 0.46936635971069335, "step": 433690 }, { "epoch": 2.5780028651080955, "grad_norm": 1.3844832181930542, "learning_rate": 3.063344177025986e-05, "loss": 0.4445648193359375, "step": 433700 }, { "epoch": 2.578062307184764, "grad_norm": 1.3796733617782593, "learning_rate": 3.063050680191388e-05, "loss": 0.43689470291137694, "step": 433710 }, { "epoch": 2.5781217492614323, "grad_norm": 1.536289930343628, "learning_rate": 3.06275722132456e-05, "loss": 0.5114924907684326, "step": 433720 }, { "epoch": 2.5781811913381008, "grad_norm": 1.1855392456054688, "learning_rate": 3.0624638004269096e-05, "loss": 0.4777024269104004, "step": 433730 }, { "epoch": 2.5782406334147687, "grad_norm": 1.3356362581253052, "learning_rate": 3.062170417499838e-05, "loss": 0.4464274406433105, "step": 433740 }, { "epoch": 2.5783000754914376, "grad_norm": 1.105067491531372, "learning_rate": 3.061877072544749e-05, "loss": 0.4180283546447754, "step": 433750 }, { "epoch": 2.5783595175681056, "grad_norm": 1.332482099533081, "learning_rate": 3.061583765563047e-05, "loss": 0.4763139247894287, "step": 433760 }, { "epoch": 2.5784189596447744, "grad_norm": 1.003258466720581, "learning_rate": 3.061290496556133e-05, "loss": 0.42117810249328613, "step": 433770 }, { "epoch": 2.5784784017214424, "grad_norm": 1.119047999382019, "learning_rate": 3.0609972655254087e-05, "loss": 0.4502433776855469, "step": 433780 }, { "epoch": 2.578537843798111, "grad_norm": 1.1459717750549316, "learning_rate": 3.060704072472282e-05, "loss": 0.44013471603393556, "step": 433790 }, { "epoch": 2.578597285874779, "grad_norm": 1.182370662689209, "learning_rate": 3.060410917398151e-05, "loss": 0.4567995071411133, "step": 433800 }, { "epoch": 2.5786567279514476, "grad_norm": 1.3087553977966309, "learning_rate": 3.06011780030442e-05, "loss": 0.5088974952697753, "step": 433810 }, { "epoch": 2.578716170028116, "grad_norm": 1.2707722187042236, "learning_rate": 3.0598247211924916e-05, "loss": 0.46130571365356443, "step": 433820 }, { "epoch": 2.5787756121047845, "grad_norm": 1.3453398942947388, "learning_rate": 3.0595316800637665e-05, "loss": 0.4953049659729004, "step": 433830 }, { "epoch": 2.578835054181453, "grad_norm": 1.382075309753418, "learning_rate": 3.059238676919646e-05, "loss": 0.4722099304199219, "step": 433840 }, { "epoch": 2.5788944962581213, "grad_norm": 0.875933825969696, "learning_rate": 3.0589457117615314e-05, "loss": 0.471065092086792, "step": 433850 }, { "epoch": 2.5789539383347897, "grad_norm": 1.1930396556854248, "learning_rate": 3.0586527845908274e-05, "loss": 0.4687436580657959, "step": 433860 }, { "epoch": 2.579013380411458, "grad_norm": 1.5049487352371216, "learning_rate": 3.0583598954089324e-05, "loss": 0.49502100944519045, "step": 433870 }, { "epoch": 2.5790728224881265, "grad_norm": 1.0956025123596191, "learning_rate": 3.058067044217249e-05, "loss": 0.4687830924987793, "step": 433880 }, { "epoch": 2.579132264564795, "grad_norm": 1.1561717987060547, "learning_rate": 3.057774231017177e-05, "loss": 0.4985663890838623, "step": 433890 }, { "epoch": 2.5791917066414634, "grad_norm": 1.5780506134033203, "learning_rate": 3.0574814558101175e-05, "loss": 0.4631326675415039, "step": 433900 }, { "epoch": 2.5792511487181318, "grad_norm": 1.317147135734558, "learning_rate": 3.05718871859747e-05, "loss": 0.461734676361084, "step": 433910 }, { "epoch": 2.5793105907948, "grad_norm": 1.4349397420883179, "learning_rate": 3.0568960193806365e-05, "loss": 0.4707046031951904, "step": 433920 }, { "epoch": 2.579370032871468, "grad_norm": 1.227009892463684, "learning_rate": 3.056603358161017e-05, "loss": 0.5100593566894531, "step": 433930 }, { "epoch": 2.579429474948137, "grad_norm": 1.0307374000549316, "learning_rate": 3.056310734940012e-05, "loss": 0.4885700225830078, "step": 433940 }, { "epoch": 2.579488917024805, "grad_norm": 1.5223027467727661, "learning_rate": 3.05601814971902e-05, "loss": 0.4432809829711914, "step": 433950 }, { "epoch": 2.579548359101474, "grad_norm": 1.4966901540756226, "learning_rate": 3.055725602499441e-05, "loss": 0.463850212097168, "step": 433960 }, { "epoch": 2.579607801178142, "grad_norm": 1.096858263015747, "learning_rate": 3.055433093282674e-05, "loss": 0.5128078460693359, "step": 433970 }, { "epoch": 2.5796672432548102, "grad_norm": 1.266845941543579, "learning_rate": 3.055140622070117e-05, "loss": 0.46863470077514646, "step": 433980 }, { "epoch": 2.5797266853314786, "grad_norm": 1.3919140100479126, "learning_rate": 3.0548481888631733e-05, "loss": 0.5072394371032715, "step": 433990 }, { "epoch": 2.579786127408147, "grad_norm": 1.4223543405532837, "learning_rate": 3.054555793663239e-05, "loss": 0.50472993850708, "step": 434000 }, { "epoch": 2.5798455694848155, "grad_norm": 1.477514624595642, "learning_rate": 3.054263436471713e-05, "loss": 0.5063773155212402, "step": 434010 }, { "epoch": 2.579905011561484, "grad_norm": 1.2753901481628418, "learning_rate": 3.053971117289994e-05, "loss": 0.49022707939147947, "step": 434020 }, { "epoch": 2.5799644536381523, "grad_norm": 1.5608066320419312, "learning_rate": 3.053678836119481e-05, "loss": 0.4817401885986328, "step": 434030 }, { "epoch": 2.5800238957148207, "grad_norm": 1.305052638053894, "learning_rate": 3.05338659296157e-05, "loss": 0.49819307327270507, "step": 434040 }, { "epoch": 2.580083337791489, "grad_norm": 1.1388282775878906, "learning_rate": 3.053094387817661e-05, "loss": 0.44901418685913086, "step": 434050 }, { "epoch": 2.5801427798681575, "grad_norm": 1.2948875427246094, "learning_rate": 3.052802220689153e-05, "loss": 0.4891351699829102, "step": 434060 }, { "epoch": 2.580202221944826, "grad_norm": 1.5353425741195679, "learning_rate": 3.052510091577442e-05, "loss": 0.4671633243560791, "step": 434070 }, { "epoch": 2.5802616640214944, "grad_norm": 1.4518771171569824, "learning_rate": 3.0522180004839224e-05, "loss": 0.4355055809020996, "step": 434080 }, { "epoch": 2.580321106098163, "grad_norm": 1.3354016542434692, "learning_rate": 3.0519259474099965e-05, "loss": 0.43674631118774415, "step": 434090 }, { "epoch": 2.580380548174831, "grad_norm": 1.543360948562622, "learning_rate": 3.0516339323570602e-05, "loss": 0.4465043067932129, "step": 434100 }, { "epoch": 2.5804399902514996, "grad_norm": 1.3017067909240723, "learning_rate": 3.0513419553265072e-05, "loss": 0.44484100341796873, "step": 434110 }, { "epoch": 2.5804994323281676, "grad_norm": 1.5228410959243774, "learning_rate": 3.051050016319738e-05, "loss": 0.396061635017395, "step": 434120 }, { "epoch": 2.5805588744048364, "grad_norm": 1.3344230651855469, "learning_rate": 3.050758115338151e-05, "loss": 0.5418438911437988, "step": 434130 }, { "epoch": 2.5806183164815044, "grad_norm": 1.5086528062820435, "learning_rate": 3.050466252383134e-05, "loss": 0.5327854633331299, "step": 434140 }, { "epoch": 2.580677758558173, "grad_norm": 1.5545904636383057, "learning_rate": 3.050174427456092e-05, "loss": 0.4806983947753906, "step": 434150 }, { "epoch": 2.5807372006348412, "grad_norm": 1.3897128105163574, "learning_rate": 3.0498826405584157e-05, "loss": 0.4875004768371582, "step": 434160 }, { "epoch": 2.5807966427115097, "grad_norm": 1.0355675220489502, "learning_rate": 3.0495908916915028e-05, "loss": 0.4832599639892578, "step": 434170 }, { "epoch": 2.580856084788178, "grad_norm": 1.356796383857727, "learning_rate": 3.049299180856749e-05, "loss": 0.5058579444885254, "step": 434180 }, { "epoch": 2.5809155268648465, "grad_norm": 1.1291056871414185, "learning_rate": 3.0490075080555523e-05, "loss": 0.4657607078552246, "step": 434190 }, { "epoch": 2.580974968941515, "grad_norm": 1.4050040245056152, "learning_rate": 3.048715873289303e-05, "loss": 0.4943540573120117, "step": 434200 }, { "epoch": 2.5810344110181833, "grad_norm": 1.4374083280563354, "learning_rate": 3.048424276559397e-05, "loss": 0.4385210037231445, "step": 434210 }, { "epoch": 2.5810938530948517, "grad_norm": 1.3015358448028564, "learning_rate": 3.0481327178672326e-05, "loss": 0.4250166893005371, "step": 434220 }, { "epoch": 2.58115329517152, "grad_norm": 1.276336431503296, "learning_rate": 3.0478411972142024e-05, "loss": 0.4677388668060303, "step": 434230 }, { "epoch": 2.5812127372481886, "grad_norm": 1.1942148208618164, "learning_rate": 3.0475497146016986e-05, "loss": 0.48552737236022947, "step": 434240 }, { "epoch": 2.581272179324857, "grad_norm": 1.1324552297592163, "learning_rate": 3.0472582700311226e-05, "loss": 0.49003114700317385, "step": 434250 }, { "epoch": 2.5813316214015254, "grad_norm": 0.9979408979415894, "learning_rate": 3.046966863503862e-05, "loss": 0.42673501968383787, "step": 434260 }, { "epoch": 2.581391063478194, "grad_norm": 1.1867400407791138, "learning_rate": 3.0466754950213106e-05, "loss": 0.39705348014831543, "step": 434270 }, { "epoch": 2.581450505554862, "grad_norm": 1.2547938823699951, "learning_rate": 3.0463841645848667e-05, "loss": 0.4784850120544434, "step": 434280 }, { "epoch": 2.58150994763153, "grad_norm": 1.248633861541748, "learning_rate": 3.046092872195922e-05, "loss": 0.42041358947753904, "step": 434290 }, { "epoch": 2.581569389708199, "grad_norm": 1.9165860414505005, "learning_rate": 3.0458016178558675e-05, "loss": 0.5250987052917481, "step": 434300 }, { "epoch": 2.581628831784867, "grad_norm": 1.0865566730499268, "learning_rate": 3.0455104015661023e-05, "loss": 0.44884719848632815, "step": 434310 }, { "epoch": 2.581688273861536, "grad_norm": 1.1100021600723267, "learning_rate": 3.0452192233280135e-05, "loss": 0.4567726612091064, "step": 434320 }, { "epoch": 2.581747715938204, "grad_norm": 1.1878641843795776, "learning_rate": 3.0449280831429972e-05, "loss": 0.4472055435180664, "step": 434330 }, { "epoch": 2.5818071580148723, "grad_norm": 1.3105871677398682, "learning_rate": 3.0446369810124424e-05, "loss": 0.4939835548400879, "step": 434340 }, { "epoch": 2.5818666000915407, "grad_norm": 1.289152979850769, "learning_rate": 3.0443459169377464e-05, "loss": 0.4534191131591797, "step": 434350 }, { "epoch": 2.581926042168209, "grad_norm": 1.3933312892913818, "learning_rate": 3.0440548909203003e-05, "loss": 0.492716121673584, "step": 434360 }, { "epoch": 2.5819854842448775, "grad_norm": 1.3218201398849487, "learning_rate": 3.0437639029614947e-05, "loss": 0.44285993576049804, "step": 434370 }, { "epoch": 2.582044926321546, "grad_norm": 1.1699286699295044, "learning_rate": 3.0434729530627233e-05, "loss": 0.5063750267028808, "step": 434380 }, { "epoch": 2.5821043683982143, "grad_norm": 1.3163529634475708, "learning_rate": 3.0431820412253765e-05, "loss": 0.484014892578125, "step": 434390 }, { "epoch": 2.5821638104748827, "grad_norm": 1.1818691492080688, "learning_rate": 3.042891167450845e-05, "loss": 0.4578144073486328, "step": 434400 }, { "epoch": 2.582223252551551, "grad_norm": 1.5601052045822144, "learning_rate": 3.0426003317405232e-05, "loss": 0.4843189239501953, "step": 434410 }, { "epoch": 2.5822826946282196, "grad_norm": 1.1311765909194946, "learning_rate": 3.042309534095802e-05, "loss": 0.45450439453125, "step": 434420 }, { "epoch": 2.582342136704888, "grad_norm": 1.027315378189087, "learning_rate": 3.0420187745180706e-05, "loss": 0.4730399131774902, "step": 434430 }, { "epoch": 2.5824015787815564, "grad_norm": 1.2805801630020142, "learning_rate": 3.04172805300872e-05, "loss": 0.450761604309082, "step": 434440 }, { "epoch": 2.582461020858225, "grad_norm": 1.4915413856506348, "learning_rate": 3.0414373695691423e-05, "loss": 0.4643272876739502, "step": 434450 }, { "epoch": 2.5825204629348932, "grad_norm": 1.5186203718185425, "learning_rate": 3.041146724200727e-05, "loss": 0.4597999095916748, "step": 434460 }, { "epoch": 2.5825799050115616, "grad_norm": 0.9447268843650818, "learning_rate": 3.0408561169048632e-05, "loss": 0.4470673084259033, "step": 434470 }, { "epoch": 2.5826393470882296, "grad_norm": 1.2874369621276855, "learning_rate": 3.040565547682945e-05, "loss": 0.4724308967590332, "step": 434480 }, { "epoch": 2.5826987891648985, "grad_norm": 1.569098711013794, "learning_rate": 3.0402750165363592e-05, "loss": 0.446605920791626, "step": 434490 }, { "epoch": 2.5827582312415664, "grad_norm": 1.3244317770004272, "learning_rate": 3.039984523466497e-05, "loss": 0.4467041015625, "step": 434500 }, { "epoch": 2.5828176733182353, "grad_norm": 1.6310298442840576, "learning_rate": 3.0396940684747472e-05, "loss": 0.48121047019958496, "step": 434510 }, { "epoch": 2.5828771153949033, "grad_norm": 1.2869980335235596, "learning_rate": 3.0394036515624997e-05, "loss": 0.4421964645385742, "step": 434520 }, { "epoch": 2.5829365574715717, "grad_norm": 1.6178125143051147, "learning_rate": 3.0391132727311412e-05, "loss": 0.5446489334106446, "step": 434530 }, { "epoch": 2.58299599954824, "grad_norm": 1.1229714155197144, "learning_rate": 3.0388229319820655e-05, "loss": 0.5319319248199463, "step": 434540 }, { "epoch": 2.5830554416249085, "grad_norm": 1.3168721199035645, "learning_rate": 3.03853262931666e-05, "loss": 0.48464508056640626, "step": 434550 }, { "epoch": 2.583114883701577, "grad_norm": 1.0493638515472412, "learning_rate": 3.0382423647363133e-05, "loss": 0.48621692657470705, "step": 434560 }, { "epoch": 2.5831743257782454, "grad_norm": 1.4517542123794556, "learning_rate": 3.0379521382424097e-05, "loss": 0.41788806915283205, "step": 434570 }, { "epoch": 2.5832337678549138, "grad_norm": 1.3179333209991455, "learning_rate": 3.0376619498363424e-05, "loss": 0.49809989929199217, "step": 434580 }, { "epoch": 2.583293209931582, "grad_norm": 1.3743107318878174, "learning_rate": 3.0373717995194995e-05, "loss": 0.5023240089416504, "step": 434590 }, { "epoch": 2.5833526520082506, "grad_norm": 1.147547721862793, "learning_rate": 3.037081687293264e-05, "loss": 0.5209495544433593, "step": 434600 }, { "epoch": 2.583412094084919, "grad_norm": 1.072221040725708, "learning_rate": 3.03679161315903e-05, "loss": 0.43468918800354006, "step": 434610 }, { "epoch": 2.5834715361615874, "grad_norm": 1.1045597791671753, "learning_rate": 3.0365015771181847e-05, "loss": 0.5066336631774903, "step": 434620 }, { "epoch": 2.583530978238256, "grad_norm": 1.77081298828125, "learning_rate": 3.0362115791721102e-05, "loss": 0.4923288822174072, "step": 434630 }, { "epoch": 2.5835904203149243, "grad_norm": 1.232246994972229, "learning_rate": 3.0359216193221984e-05, "loss": 0.49966702461242674, "step": 434640 }, { "epoch": 2.5836498623915927, "grad_norm": 1.8345431089401245, "learning_rate": 3.0356316975698353e-05, "loss": 0.48810338973999023, "step": 434650 }, { "epoch": 2.583709304468261, "grad_norm": 1.1265660524368286, "learning_rate": 3.0353418139164046e-05, "loss": 0.4493208408355713, "step": 434660 }, { "epoch": 2.583768746544929, "grad_norm": 1.394172191619873, "learning_rate": 3.035051968363298e-05, "loss": 0.416319751739502, "step": 434670 }, { "epoch": 2.583828188621598, "grad_norm": 1.1260535717010498, "learning_rate": 3.034762160911901e-05, "loss": 0.4803438186645508, "step": 434680 }, { "epoch": 2.583887630698266, "grad_norm": 1.0843340158462524, "learning_rate": 3.034472391563598e-05, "loss": 0.4991926193237305, "step": 434690 }, { "epoch": 2.5839470727749347, "grad_norm": 1.085939884185791, "learning_rate": 3.034182660319773e-05, "loss": 0.4698681354522705, "step": 434700 }, { "epoch": 2.5840065148516027, "grad_norm": 1.204302191734314, "learning_rate": 3.0338929671818173e-05, "loss": 0.45485639572143555, "step": 434710 }, { "epoch": 2.584065956928271, "grad_norm": 1.4310839176177979, "learning_rate": 3.033603312151114e-05, "loss": 0.4325230121612549, "step": 434720 }, { "epoch": 2.5841253990049395, "grad_norm": 1.5407781600952148, "learning_rate": 3.033313695229048e-05, "loss": 0.4603160858154297, "step": 434730 }, { "epoch": 2.584184841081608, "grad_norm": 1.1579070091247559, "learning_rate": 3.0330241164170088e-05, "loss": 0.46088876724243166, "step": 434740 }, { "epoch": 2.5842442831582764, "grad_norm": 1.2609467506408691, "learning_rate": 3.032734575716377e-05, "loss": 0.48035669326782227, "step": 434750 }, { "epoch": 2.584303725234945, "grad_norm": 1.1913079023361206, "learning_rate": 3.032445073128537e-05, "loss": 0.4561006546020508, "step": 434760 }, { "epoch": 2.584363167311613, "grad_norm": 1.3079924583435059, "learning_rate": 3.032155608654878e-05, "loss": 0.43955564498901367, "step": 434770 }, { "epoch": 2.5844226093882816, "grad_norm": 1.0503225326538086, "learning_rate": 3.031866182296783e-05, "loss": 0.4369847297668457, "step": 434780 }, { "epoch": 2.58448205146495, "grad_norm": 1.6041337251663208, "learning_rate": 3.031576794055634e-05, "loss": 0.5445239067077636, "step": 434790 }, { "epoch": 2.5845414935416184, "grad_norm": 1.4679090976715088, "learning_rate": 3.031287443932821e-05, "loss": 0.4363844871520996, "step": 434800 }, { "epoch": 2.584600935618287, "grad_norm": 1.4646013975143433, "learning_rate": 3.0309981319297236e-05, "loss": 0.46431121826171873, "step": 434810 }, { "epoch": 2.5846603776949553, "grad_norm": 1.0058900117874146, "learning_rate": 3.0307088580477256e-05, "loss": 0.4762709617614746, "step": 434820 }, { "epoch": 2.5847198197716237, "grad_norm": 1.4659922122955322, "learning_rate": 3.0304196222882113e-05, "loss": 0.4354663848876953, "step": 434830 }, { "epoch": 2.584779261848292, "grad_norm": 1.232479453086853, "learning_rate": 3.0301304246525665e-05, "loss": 0.4455986499786377, "step": 434840 }, { "epoch": 2.5848387039249605, "grad_norm": 1.5022350549697876, "learning_rate": 3.0298412651421727e-05, "loss": 0.3987236738204956, "step": 434850 }, { "epoch": 2.5848981460016285, "grad_norm": 1.2896491289138794, "learning_rate": 3.029552143758414e-05, "loss": 0.4572646141052246, "step": 434860 }, { "epoch": 2.5849575880782973, "grad_norm": 0.8247217535972595, "learning_rate": 3.0292630605026728e-05, "loss": 0.4652442932128906, "step": 434870 }, { "epoch": 2.5850170301549653, "grad_norm": 1.288954257965088, "learning_rate": 3.028974015376333e-05, "loss": 0.4974532604217529, "step": 434880 }, { "epoch": 2.5850764722316337, "grad_norm": 1.511631727218628, "learning_rate": 3.028685008380774e-05, "loss": 0.49615478515625, "step": 434890 }, { "epoch": 2.585135914308302, "grad_norm": 1.3728923797607422, "learning_rate": 3.0283960395173834e-05, "loss": 0.48870000839233396, "step": 434900 }, { "epoch": 2.5851953563849706, "grad_norm": 1.1331523656845093, "learning_rate": 3.0281071087875407e-05, "loss": 0.5045660972595215, "step": 434910 }, { "epoch": 2.585254798461639, "grad_norm": 0.9917845726013184, "learning_rate": 3.027818216192627e-05, "loss": 0.4778782844543457, "step": 434920 }, { "epoch": 2.5853142405383074, "grad_norm": 1.1412345170974731, "learning_rate": 3.0275293617340274e-05, "loss": 0.4859869956970215, "step": 434930 }, { "epoch": 2.585373682614976, "grad_norm": 1.4167689085006714, "learning_rate": 3.0272405454131208e-05, "loss": 0.5209979057312012, "step": 434940 }, { "epoch": 2.585433124691644, "grad_norm": 1.4460457563400269, "learning_rate": 3.026951767231291e-05, "loss": 0.459900426864624, "step": 434950 }, { "epoch": 2.5854925667683126, "grad_norm": 1.3781858682632446, "learning_rate": 3.0266630271899166e-05, "loss": 0.47248196601867676, "step": 434960 }, { "epoch": 2.585552008844981, "grad_norm": 1.1844463348388672, "learning_rate": 3.0263743252903815e-05, "loss": 0.45680828094482423, "step": 434970 }, { "epoch": 2.5856114509216495, "grad_norm": 1.3493132591247559, "learning_rate": 3.0260856615340654e-05, "loss": 0.4542597770690918, "step": 434980 }, { "epoch": 2.585670892998318, "grad_norm": 1.3821380138397217, "learning_rate": 3.0257970359223507e-05, "loss": 0.48781442642211914, "step": 434990 }, { "epoch": 2.5857303350749863, "grad_norm": 1.1991299390792847, "learning_rate": 3.0255084484566164e-05, "loss": 0.4893460273742676, "step": 435000 }, { "epoch": 2.5857897771516547, "grad_norm": 1.6350306272506714, "learning_rate": 3.025219899138243e-05, "loss": 0.4706240177154541, "step": 435010 }, { "epoch": 2.585849219228323, "grad_norm": 1.4476374387741089, "learning_rate": 3.0249313879686102e-05, "loss": 0.4786128044128418, "step": 435020 }, { "epoch": 2.585908661304991, "grad_norm": 1.7553973197937012, "learning_rate": 3.0246429149491014e-05, "loss": 0.48108773231506347, "step": 435030 }, { "epoch": 2.58596810338166, "grad_norm": 1.3391586542129517, "learning_rate": 3.0243544800810945e-05, "loss": 0.5011552810668946, "step": 435040 }, { "epoch": 2.586027545458328, "grad_norm": 1.0573022365570068, "learning_rate": 3.0240660833659697e-05, "loss": 0.47579450607299806, "step": 435050 }, { "epoch": 2.5860869875349968, "grad_norm": 1.5890581607818604, "learning_rate": 3.023777724805105e-05, "loss": 0.46576104164123533, "step": 435060 }, { "epoch": 2.5861464296116647, "grad_norm": 1.4858007431030273, "learning_rate": 3.0234894043998823e-05, "loss": 0.4233828544616699, "step": 435070 }, { "epoch": 2.586205871688333, "grad_norm": 1.539358139038086, "learning_rate": 3.0232011221516786e-05, "loss": 0.4884955883026123, "step": 435080 }, { "epoch": 2.5862653137650016, "grad_norm": 1.703498125076294, "learning_rate": 3.0229128780618725e-05, "loss": 0.477081298828125, "step": 435090 }, { "epoch": 2.58632475584167, "grad_norm": 1.7567975521087646, "learning_rate": 3.0226246721318453e-05, "loss": 0.4869713306427002, "step": 435100 }, { "epoch": 2.5863841979183384, "grad_norm": 1.1131168603897095, "learning_rate": 3.0223365043629763e-05, "loss": 0.48406038284301756, "step": 435110 }, { "epoch": 2.586443639995007, "grad_norm": 1.1278434991836548, "learning_rate": 3.0220483747566403e-05, "loss": 0.45769057273864744, "step": 435120 }, { "epoch": 2.5865030820716752, "grad_norm": 1.1449178457260132, "learning_rate": 3.0217602833142195e-05, "loss": 0.44872560501098635, "step": 435130 }, { "epoch": 2.5865625241483436, "grad_norm": 1.080538272857666, "learning_rate": 3.0214722300370894e-05, "loss": 0.4554173946380615, "step": 435140 }, { "epoch": 2.586621966225012, "grad_norm": 1.665971279144287, "learning_rate": 3.0211842149266263e-05, "loss": 0.4854267597198486, "step": 435150 }, { "epoch": 2.5866814083016805, "grad_norm": 1.166068434715271, "learning_rate": 3.020896237984213e-05, "loss": 0.4928130149841309, "step": 435160 }, { "epoch": 2.586740850378349, "grad_norm": 1.096726655960083, "learning_rate": 3.0206082992112262e-05, "loss": 0.49558143615722655, "step": 435170 }, { "epoch": 2.5868002924550173, "grad_norm": 1.6397223472595215, "learning_rate": 3.02032039860904e-05, "loss": 0.5019907474517822, "step": 435180 }, { "epoch": 2.5868597345316857, "grad_norm": 1.2218732833862305, "learning_rate": 3.020032536179031e-05, "loss": 0.4797316074371338, "step": 435190 }, { "epoch": 2.586919176608354, "grad_norm": 1.4770487546920776, "learning_rate": 3.01974471192258e-05, "loss": 0.5255777835845947, "step": 435200 }, { "epoch": 2.5869786186850225, "grad_norm": 1.429176926612854, "learning_rate": 3.0194569258410632e-05, "loss": 0.4661142826080322, "step": 435210 }, { "epoch": 2.5870380607616905, "grad_norm": 1.507749080657959, "learning_rate": 3.0191691779358538e-05, "loss": 0.4989777565002441, "step": 435220 }, { "epoch": 2.5870975028383594, "grad_norm": 1.5694115161895752, "learning_rate": 3.0188814682083343e-05, "loss": 0.4378143310546875, "step": 435230 }, { "epoch": 2.5871569449150273, "grad_norm": 1.0261653661727905, "learning_rate": 3.018593796659877e-05, "loss": 0.47191672325134276, "step": 435240 }, { "epoch": 2.587216386991696, "grad_norm": 1.1786389350891113, "learning_rate": 3.018306163291856e-05, "loss": 0.46249680519104003, "step": 435250 }, { "epoch": 2.587275829068364, "grad_norm": 1.119533896446228, "learning_rate": 3.0180185681056518e-05, "loss": 0.4496743202209473, "step": 435260 }, { "epoch": 2.5873352711450326, "grad_norm": 1.091765284538269, "learning_rate": 3.0177310111026386e-05, "loss": 0.5123343467712402, "step": 435270 }, { "epoch": 2.587394713221701, "grad_norm": 1.401754379272461, "learning_rate": 3.0174434922841888e-05, "loss": 0.47951173782348633, "step": 435280 }, { "epoch": 2.5874541552983694, "grad_norm": 1.574955940246582, "learning_rate": 3.0171560116516844e-05, "loss": 0.4793508529663086, "step": 435290 }, { "epoch": 2.587513597375038, "grad_norm": 1.3994712829589844, "learning_rate": 3.0168685692064956e-05, "loss": 0.4733980655670166, "step": 435300 }, { "epoch": 2.5875730394517062, "grad_norm": 1.4901340007781982, "learning_rate": 3.0165811649499987e-05, "loss": 0.5171490669250488, "step": 435310 }, { "epoch": 2.5876324815283747, "grad_norm": 1.2792952060699463, "learning_rate": 3.016293798883566e-05, "loss": 0.4621140956878662, "step": 435320 }, { "epoch": 2.587691923605043, "grad_norm": 1.5263967514038086, "learning_rate": 3.016006471008578e-05, "loss": 0.4683663368225098, "step": 435330 }, { "epoch": 2.5877513656817115, "grad_norm": 1.3874117136001587, "learning_rate": 3.0157191813264053e-05, "loss": 0.5125173568725586, "step": 435340 }, { "epoch": 2.58781080775838, "grad_norm": 1.6554279327392578, "learning_rate": 3.015431929838421e-05, "loss": 0.46862316131591797, "step": 435350 }, { "epoch": 2.5878702498350483, "grad_norm": 1.0885950326919556, "learning_rate": 3.015144716546003e-05, "loss": 0.409652042388916, "step": 435360 }, { "epoch": 2.5879296919117167, "grad_norm": 1.4395731687545776, "learning_rate": 3.0148575414505222e-05, "loss": 0.46243796348571775, "step": 435370 }, { "epoch": 2.587989133988385, "grad_norm": 1.1317620277404785, "learning_rate": 3.0145704045533512e-05, "loss": 0.5135056495666503, "step": 435380 }, { "epoch": 2.5880485760650536, "grad_norm": 1.6358089447021484, "learning_rate": 3.0142833058558683e-05, "loss": 0.5208487510681152, "step": 435390 }, { "epoch": 2.588108018141722, "grad_norm": 1.3340531587600708, "learning_rate": 3.013996245359444e-05, "loss": 0.4948259353637695, "step": 435400 }, { "epoch": 2.58816746021839, "grad_norm": 1.6314204931259155, "learning_rate": 3.0137092230654517e-05, "loss": 0.4938360691070557, "step": 435410 }, { "epoch": 2.588226902295059, "grad_norm": 1.4730923175811768, "learning_rate": 3.0134222389752646e-05, "loss": 0.48781399726867675, "step": 435420 }, { "epoch": 2.5882863443717268, "grad_norm": 1.4739015102386475, "learning_rate": 3.0131352930902558e-05, "loss": 0.48689908981323243, "step": 435430 }, { "epoch": 2.5883457864483956, "grad_norm": 1.2532374858856201, "learning_rate": 3.012848385411798e-05, "loss": 0.48436508178710935, "step": 435440 }, { "epoch": 2.5884052285250636, "grad_norm": 1.3264209032058716, "learning_rate": 3.0125615159412606e-05, "loss": 0.4485942840576172, "step": 435450 }, { "epoch": 2.588464670601732, "grad_norm": 1.4345251321792603, "learning_rate": 3.012274684680021e-05, "loss": 0.484420108795166, "step": 435460 }, { "epoch": 2.5885241126784004, "grad_norm": 1.232805609703064, "learning_rate": 3.011987891629448e-05, "loss": 0.4697774887084961, "step": 435470 }, { "epoch": 2.588583554755069, "grad_norm": 1.2390313148498535, "learning_rate": 3.0117011367909147e-05, "loss": 0.4795232772827148, "step": 435480 }, { "epoch": 2.5886429968317373, "grad_norm": 1.0796278715133667, "learning_rate": 3.011414420165793e-05, "loss": 0.4412410736083984, "step": 435490 }, { "epoch": 2.5887024389084057, "grad_norm": 1.5439437627792358, "learning_rate": 3.0111277417554545e-05, "loss": 0.4715282440185547, "step": 435500 }, { "epoch": 2.588761880985074, "grad_norm": 1.4541504383087158, "learning_rate": 3.010841101561267e-05, "loss": 0.488525390625, "step": 435510 }, { "epoch": 2.5888213230617425, "grad_norm": 1.2731921672821045, "learning_rate": 3.010554499584608e-05, "loss": 0.45743646621704104, "step": 435520 }, { "epoch": 2.588880765138411, "grad_norm": 1.199771523475647, "learning_rate": 3.0102679358268436e-05, "loss": 0.49770231246948243, "step": 435530 }, { "epoch": 2.5889402072150793, "grad_norm": 1.4113845825195312, "learning_rate": 3.0099814102893474e-05, "loss": 0.4598269462585449, "step": 435540 }, { "epoch": 2.5889996492917478, "grad_norm": 1.29280424118042, "learning_rate": 3.0096949229734895e-05, "loss": 0.473726224899292, "step": 435550 }, { "epoch": 2.589059091368416, "grad_norm": 1.2308752536773682, "learning_rate": 3.0094084738806382e-05, "loss": 0.4660961151123047, "step": 435560 }, { "epoch": 2.5891185334450846, "grad_norm": 1.2274233102798462, "learning_rate": 3.0091220630121662e-05, "loss": 0.49763851165771483, "step": 435570 }, { "epoch": 2.5891779755217526, "grad_norm": 1.380009412765503, "learning_rate": 3.0088356903694425e-05, "loss": 0.46001758575439455, "step": 435580 }, { "epoch": 2.5892374175984214, "grad_norm": 1.668314814567566, "learning_rate": 3.0085493559538374e-05, "loss": 0.5182194709777832, "step": 435590 }, { "epoch": 2.5892968596750894, "grad_norm": 1.0861750841140747, "learning_rate": 3.008263059766721e-05, "loss": 0.44888105392456057, "step": 435600 }, { "epoch": 2.5893563017517582, "grad_norm": 1.2881271839141846, "learning_rate": 3.0079768018094618e-05, "loss": 0.47794389724731445, "step": 435610 }, { "epoch": 2.589415743828426, "grad_norm": 1.6115813255310059, "learning_rate": 3.0076905820834307e-05, "loss": 0.5439690589904785, "step": 435620 }, { "epoch": 2.5894751859050946, "grad_norm": 1.0210951566696167, "learning_rate": 3.0074044005899948e-05, "loss": 0.45183238983154295, "step": 435630 }, { "epoch": 2.589534627981763, "grad_norm": 1.6126091480255127, "learning_rate": 3.0071182573305233e-05, "loss": 0.4509122848510742, "step": 435640 }, { "epoch": 2.5895940700584315, "grad_norm": 0.7416706681251526, "learning_rate": 3.0068321523063874e-05, "loss": 0.42850942611694337, "step": 435650 }, { "epoch": 2.5896535121351, "grad_norm": 1.0019272565841675, "learning_rate": 3.0065460855189542e-05, "loss": 0.4141866207122803, "step": 435660 }, { "epoch": 2.5897129542117683, "grad_norm": 1.8074917793273926, "learning_rate": 3.006260056969595e-05, "loss": 0.4981893539428711, "step": 435670 }, { "epoch": 2.5897723962884367, "grad_norm": 1.3732856512069702, "learning_rate": 3.0059740666596707e-05, "loss": 0.48351569175720216, "step": 435680 }, { "epoch": 2.589831838365105, "grad_norm": 1.4417363405227661, "learning_rate": 3.0056881145905564e-05, "loss": 0.48211517333984377, "step": 435690 }, { "epoch": 2.5898912804417735, "grad_norm": 1.7291983366012573, "learning_rate": 3.0054022007636172e-05, "loss": 0.445302152633667, "step": 435700 }, { "epoch": 2.589950722518442, "grad_norm": 1.356876015663147, "learning_rate": 3.00511632518022e-05, "loss": 0.44167041778564453, "step": 435710 }, { "epoch": 2.5900101645951104, "grad_norm": 1.1021099090576172, "learning_rate": 3.0048304878417343e-05, "loss": 0.456788969039917, "step": 435720 }, { "epoch": 2.5900696066717788, "grad_norm": 1.397583246231079, "learning_rate": 3.0045446887495292e-05, "loss": 0.5113719940185547, "step": 435730 }, { "epoch": 2.590129048748447, "grad_norm": 1.3237088918685913, "learning_rate": 3.004258927904966e-05, "loss": 0.44408330917358396, "step": 435740 }, { "epoch": 2.5901884908251156, "grad_norm": 1.4196901321411133, "learning_rate": 3.0039732053094153e-05, "loss": 0.47051205635070803, "step": 435750 }, { "epoch": 2.590247932901784, "grad_norm": 1.2781449556350708, "learning_rate": 3.0036875209642452e-05, "loss": 0.44544053077697754, "step": 435760 }, { "epoch": 2.590307374978452, "grad_norm": 1.3886908292770386, "learning_rate": 3.0034018748708204e-05, "loss": 0.5155871391296387, "step": 435770 }, { "epoch": 2.590366817055121, "grad_norm": 1.3584263324737549, "learning_rate": 3.003116267030508e-05, "loss": 0.470002269744873, "step": 435780 }, { "epoch": 2.590426259131789, "grad_norm": 1.3221023082733154, "learning_rate": 3.0028306974446735e-05, "loss": 0.43732428550720215, "step": 435790 }, { "epoch": 2.5904857012084577, "grad_norm": 1.3777087926864624, "learning_rate": 3.0025451661146836e-05, "loss": 0.4750096321105957, "step": 435800 }, { "epoch": 2.5905451432851256, "grad_norm": 1.1706124544143677, "learning_rate": 3.0022596730419016e-05, "loss": 0.466551399230957, "step": 435810 }, { "epoch": 2.590604585361794, "grad_norm": 1.3590253591537476, "learning_rate": 3.001974218227699e-05, "loss": 0.4778548240661621, "step": 435820 }, { "epoch": 2.5906640274384625, "grad_norm": 1.0110167264938354, "learning_rate": 3.0016888016734367e-05, "loss": 0.4708230018615723, "step": 435830 }, { "epoch": 2.590723469515131, "grad_norm": 1.1953474283218384, "learning_rate": 3.001403423380482e-05, "loss": 0.4454380512237549, "step": 435840 }, { "epoch": 2.5907829115917993, "grad_norm": 1.472464680671692, "learning_rate": 3.0011180833501996e-05, "loss": 0.47964868545532224, "step": 435850 }, { "epoch": 2.5908423536684677, "grad_norm": 1.5553126335144043, "learning_rate": 3.0008327815839532e-05, "loss": 0.45264415740966796, "step": 435860 }, { "epoch": 2.590901795745136, "grad_norm": 1.2208633422851562, "learning_rate": 3.0005475180831073e-05, "loss": 0.45751223564147947, "step": 435870 }, { "epoch": 2.5909612378218045, "grad_norm": 1.0379151105880737, "learning_rate": 3.0002622928490293e-05, "loss": 0.4352272033691406, "step": 435880 }, { "epoch": 2.591020679898473, "grad_norm": 1.3563511371612549, "learning_rate": 2.9999771058830827e-05, "loss": 0.4671353340148926, "step": 435890 }, { "epoch": 2.5910801219751414, "grad_norm": 1.448288083076477, "learning_rate": 2.9996919571866304e-05, "loss": 0.4585125923156738, "step": 435900 }, { "epoch": 2.59113956405181, "grad_norm": 1.1945700645446777, "learning_rate": 2.999406846761038e-05, "loss": 0.45679521560668945, "step": 435910 }, { "epoch": 2.591199006128478, "grad_norm": 1.3050204515457153, "learning_rate": 2.9991217746076678e-05, "loss": 0.4478456497192383, "step": 435920 }, { "epoch": 2.5912584482051466, "grad_norm": 1.4970252513885498, "learning_rate": 2.998836740727885e-05, "loss": 0.48958802223205566, "step": 435930 }, { "epoch": 2.591317890281815, "grad_norm": 1.3681825399398804, "learning_rate": 2.9985517451230503e-05, "loss": 0.46913576126098633, "step": 435940 }, { "epoch": 2.5913773323584834, "grad_norm": 1.154960036277771, "learning_rate": 2.998266787794532e-05, "loss": 0.4432734489440918, "step": 435950 }, { "epoch": 2.5914367744351514, "grad_norm": 1.2902231216430664, "learning_rate": 2.9979818687436893e-05, "loss": 0.45245943069458006, "step": 435960 }, { "epoch": 2.5914962165118203, "grad_norm": 1.4442750215530396, "learning_rate": 2.9976969879718857e-05, "loss": 0.47500028610229494, "step": 435970 }, { "epoch": 2.5915556585884882, "grad_norm": 1.3265684843063354, "learning_rate": 2.997412145480486e-05, "loss": 0.44811439514160156, "step": 435980 }, { "epoch": 2.591615100665157, "grad_norm": 1.6112734079360962, "learning_rate": 2.99712734127085e-05, "loss": 0.4706223964691162, "step": 435990 }, { "epoch": 2.591674542741825, "grad_norm": 1.436468482017517, "learning_rate": 2.9968425753443407e-05, "loss": 0.48881778717041013, "step": 436000 }, { "epoch": 2.5917339848184935, "grad_norm": 1.3208309412002563, "learning_rate": 2.996557847702322e-05, "loss": 0.4876873970031738, "step": 436010 }, { "epoch": 2.591793426895162, "grad_norm": 1.105738639831543, "learning_rate": 2.9962731583461558e-05, "loss": 0.5325555801391602, "step": 436020 }, { "epoch": 2.5918528689718303, "grad_norm": 0.9879587888717651, "learning_rate": 2.9959885072772033e-05, "loss": 0.47959651947021487, "step": 436030 }, { "epoch": 2.5919123110484987, "grad_norm": 1.2960575819015503, "learning_rate": 2.9957038944968247e-05, "loss": 0.4834000587463379, "step": 436040 }, { "epoch": 2.591971753125167, "grad_norm": 1.7055554389953613, "learning_rate": 2.9954193200063842e-05, "loss": 0.46770520210266114, "step": 436050 }, { "epoch": 2.5920311952018356, "grad_norm": 0.7908540368080139, "learning_rate": 2.9951347838072414e-05, "loss": 0.5087698936462403, "step": 436060 }, { "epoch": 2.592090637278504, "grad_norm": 1.37442147731781, "learning_rate": 2.994850285900755e-05, "loss": 0.4573657035827637, "step": 436070 }, { "epoch": 2.5921500793551724, "grad_norm": 1.3079336881637573, "learning_rate": 2.9945658262882918e-05, "loss": 0.44082093238830566, "step": 436080 }, { "epoch": 2.592209521431841, "grad_norm": 1.1048990488052368, "learning_rate": 2.9942814049712088e-05, "loss": 0.4424703121185303, "step": 436090 }, { "epoch": 2.592268963508509, "grad_norm": 1.5318856239318848, "learning_rate": 2.9939970219508672e-05, "loss": 0.4774644374847412, "step": 436100 }, { "epoch": 2.5923284055851776, "grad_norm": 1.1801118850708008, "learning_rate": 2.9937126772286284e-05, "loss": 0.5018866539001465, "step": 436110 }, { "epoch": 2.592387847661846, "grad_norm": 1.4166420698165894, "learning_rate": 2.993428370805851e-05, "loss": 0.4821911811828613, "step": 436120 }, { "epoch": 2.5924472897385145, "grad_norm": 0.9321455359458923, "learning_rate": 2.9931441026838935e-05, "loss": 0.43429079055786135, "step": 436130 }, { "epoch": 2.592506731815183, "grad_norm": 1.531652808189392, "learning_rate": 2.99285987286412e-05, "loss": 0.47641630172729493, "step": 436140 }, { "epoch": 2.592566173891851, "grad_norm": 1.3513267040252686, "learning_rate": 2.9925756813478883e-05, "loss": 0.46828041076660154, "step": 436150 }, { "epoch": 2.5926256159685197, "grad_norm": 1.3547461032867432, "learning_rate": 2.9922915281365594e-05, "loss": 0.5127115249633789, "step": 436160 }, { "epoch": 2.5926850580451877, "grad_norm": 1.3709402084350586, "learning_rate": 2.9920074132314868e-05, "loss": 0.477308988571167, "step": 436170 }, { "epoch": 2.5927445001218565, "grad_norm": 1.4501575231552124, "learning_rate": 2.9917233366340363e-05, "loss": 0.48236374855041503, "step": 436180 }, { "epoch": 2.5928039421985245, "grad_norm": 1.6750801801681519, "learning_rate": 2.991439298345564e-05, "loss": 0.5082601547241211, "step": 436190 }, { "epoch": 2.592863384275193, "grad_norm": 1.372564435005188, "learning_rate": 2.9911552983674275e-05, "loss": 0.49358558654785156, "step": 436200 }, { "epoch": 2.5929228263518613, "grad_norm": 1.0177204608917236, "learning_rate": 2.990871336700988e-05, "loss": 0.46277942657470705, "step": 436210 }, { "epoch": 2.5929822684285297, "grad_norm": 1.4835550785064697, "learning_rate": 2.9905874133476035e-05, "loss": 0.48723154067993163, "step": 436220 }, { "epoch": 2.593041710505198, "grad_norm": 1.2392363548278809, "learning_rate": 2.9903035283086296e-05, "loss": 0.45835485458374026, "step": 436230 }, { "epoch": 2.5931011525818666, "grad_norm": 1.5197956562042236, "learning_rate": 2.9900196815854265e-05, "loss": 0.5084150314331055, "step": 436240 }, { "epoch": 2.593160594658535, "grad_norm": 1.2493326663970947, "learning_rate": 2.9897358731793523e-05, "loss": 0.47040691375732424, "step": 436250 }, { "epoch": 2.5932200367352034, "grad_norm": 1.3525781631469727, "learning_rate": 2.989452103091763e-05, "loss": 0.5352000236511231, "step": 436260 }, { "epoch": 2.593279478811872, "grad_norm": 1.1254674196243286, "learning_rate": 2.989168371324016e-05, "loss": 0.45611915588378904, "step": 436270 }, { "epoch": 2.5933389208885402, "grad_norm": 0.9705508947372437, "learning_rate": 2.988884677877472e-05, "loss": 0.468003511428833, "step": 436280 }, { "epoch": 2.5933983629652086, "grad_norm": 1.3337732553482056, "learning_rate": 2.988601022753485e-05, "loss": 0.43030033111572263, "step": 436290 }, { "epoch": 2.593457805041877, "grad_norm": 1.1861276626586914, "learning_rate": 2.9883174059534108e-05, "loss": 0.45421929359436036, "step": 436300 }, { "epoch": 2.5935172471185455, "grad_norm": 1.292250394821167, "learning_rate": 2.988033827478609e-05, "loss": 0.3697976112365723, "step": 436310 }, { "epoch": 2.5935766891952134, "grad_norm": 1.3866193294525146, "learning_rate": 2.9877502873304347e-05, "loss": 0.47625370025634767, "step": 436320 }, { "epoch": 2.5936361312718823, "grad_norm": 1.2346179485321045, "learning_rate": 2.9874667855102444e-05, "loss": 0.4924921035766602, "step": 436330 }, { "epoch": 2.5936955733485503, "grad_norm": 1.3312947750091553, "learning_rate": 2.987183322019396e-05, "loss": 0.47978715896606444, "step": 436340 }, { "epoch": 2.593755015425219, "grad_norm": 1.5732018947601318, "learning_rate": 2.9868998968592437e-05, "loss": 0.42819061279296877, "step": 436350 }, { "epoch": 2.593814457501887, "grad_norm": 1.3315478563308716, "learning_rate": 2.986616510031141e-05, "loss": 0.4775251865386963, "step": 436360 }, { "epoch": 2.5938738995785555, "grad_norm": 1.4382702112197876, "learning_rate": 2.9863331615364487e-05, "loss": 0.43770465850830076, "step": 436370 }, { "epoch": 2.593933341655224, "grad_norm": 1.2750824689865112, "learning_rate": 2.98604985137652e-05, "loss": 0.5013426303863525, "step": 436380 }, { "epoch": 2.5939927837318923, "grad_norm": 1.2577542066574097, "learning_rate": 2.9857665795527077e-05, "loss": 0.46985588073730467, "step": 436390 }, { "epoch": 2.5940522258085608, "grad_norm": 1.4815434217453003, "learning_rate": 2.9854833460663704e-05, "loss": 0.44888153076171877, "step": 436400 }, { "epoch": 2.594111667885229, "grad_norm": 1.586870789527893, "learning_rate": 2.985200150918862e-05, "loss": 0.5054598808288574, "step": 436410 }, { "epoch": 2.5941711099618976, "grad_norm": 1.2658140659332275, "learning_rate": 2.9849169941115367e-05, "loss": 0.44913406372070314, "step": 436420 }, { "epoch": 2.594230552038566, "grad_norm": 1.2766103744506836, "learning_rate": 2.9846338756457464e-05, "loss": 0.43079490661621095, "step": 436430 }, { "epoch": 2.5942899941152344, "grad_norm": 1.4152804613113403, "learning_rate": 2.9843507955228507e-05, "loss": 0.5370774269104004, "step": 436440 }, { "epoch": 2.594349436191903, "grad_norm": 1.5116177797317505, "learning_rate": 2.9840677537442006e-05, "loss": 0.4127779006958008, "step": 436450 }, { "epoch": 2.5944088782685713, "grad_norm": 1.2796095609664917, "learning_rate": 2.9837847503111515e-05, "loss": 0.4788182735443115, "step": 436460 }, { "epoch": 2.5944683203452397, "grad_norm": 1.8580701351165771, "learning_rate": 2.9835017852250563e-05, "loss": 0.4730245590209961, "step": 436470 }, { "epoch": 2.594527762421908, "grad_norm": 1.3698232173919678, "learning_rate": 2.9832188584872695e-05, "loss": 0.45566720962524415, "step": 436480 }, { "epoch": 2.5945872044985765, "grad_norm": 1.4176864624023438, "learning_rate": 2.982935970099141e-05, "loss": 0.5523711204528808, "step": 436490 }, { "epoch": 2.594646646575245, "grad_norm": 1.263879656791687, "learning_rate": 2.982653120062029e-05, "loss": 0.49544668197631836, "step": 436500 }, { "epoch": 2.594706088651913, "grad_norm": 1.1191335916519165, "learning_rate": 2.9823703083772834e-05, "loss": 0.5045359134674072, "step": 436510 }, { "epoch": 2.5947655307285817, "grad_norm": 1.3487364053726196, "learning_rate": 2.9820875350462592e-05, "loss": 0.47134647369384763, "step": 436520 }, { "epoch": 2.5948249728052497, "grad_norm": 2.495213747024536, "learning_rate": 2.981804800070307e-05, "loss": 0.44888920783996583, "step": 436530 }, { "epoch": 2.5948844148819186, "grad_norm": 1.3945542573928833, "learning_rate": 2.9815221034507813e-05, "loss": 0.4852456569671631, "step": 436540 }, { "epoch": 2.5949438569585865, "grad_norm": 1.5702641010284424, "learning_rate": 2.9812394451890325e-05, "loss": 0.4690084457397461, "step": 436550 }, { "epoch": 2.595003299035255, "grad_norm": 1.39802086353302, "learning_rate": 2.9809568252864118e-05, "loss": 0.5359033584594727, "step": 436560 }, { "epoch": 2.5950627411119234, "grad_norm": 1.135716438293457, "learning_rate": 2.9806742437442748e-05, "loss": 0.45778613090515136, "step": 436570 }, { "epoch": 2.595122183188592, "grad_norm": 1.542775273323059, "learning_rate": 2.9803917005639726e-05, "loss": 0.4792035102844238, "step": 436580 }, { "epoch": 2.59518162526526, "grad_norm": 0.8843997716903687, "learning_rate": 2.980109195746854e-05, "loss": 0.45744986534118653, "step": 436590 }, { "epoch": 2.5952410673419286, "grad_norm": 1.1704578399658203, "learning_rate": 2.9798267292942732e-05, "loss": 0.4789694309234619, "step": 436600 }, { "epoch": 2.595300509418597, "grad_norm": 1.4837679862976074, "learning_rate": 2.9795443012075807e-05, "loss": 0.4962453842163086, "step": 436610 }, { "epoch": 2.5953599514952654, "grad_norm": 1.5539538860321045, "learning_rate": 2.9792619114881265e-05, "loss": 0.48278298377990725, "step": 436620 }, { "epoch": 2.595419393571934, "grad_norm": 1.4524669647216797, "learning_rate": 2.9789795601372607e-05, "loss": 0.4969494819641113, "step": 436630 }, { "epoch": 2.5954788356486023, "grad_norm": 1.4811018705368042, "learning_rate": 2.9786972471563362e-05, "loss": 0.4822948455810547, "step": 436640 }, { "epoch": 2.5955382777252707, "grad_norm": 1.3914744853973389, "learning_rate": 2.978414972546706e-05, "loss": 0.4512007236480713, "step": 436650 }, { "epoch": 2.595597719801939, "grad_norm": 1.077454924583435, "learning_rate": 2.9781327363097122e-05, "loss": 0.4619271278381348, "step": 436660 }, { "epoch": 2.5956571618786075, "grad_norm": 1.14622163772583, "learning_rate": 2.9778505384467116e-05, "loss": 0.47581963539123534, "step": 436670 }, { "epoch": 2.595716603955276, "grad_norm": 1.2606472969055176, "learning_rate": 2.977568378959053e-05, "loss": 0.5428353309631347, "step": 436680 }, { "epoch": 2.5957760460319443, "grad_norm": 1.2052634954452515, "learning_rate": 2.9772862578480836e-05, "loss": 0.45224504470825194, "step": 436690 }, { "epoch": 2.5958354881086123, "grad_norm": 1.4871832132339478, "learning_rate": 2.977004175115157e-05, "loss": 0.49017333984375, "step": 436700 }, { "epoch": 2.595894930185281, "grad_norm": 1.4660913944244385, "learning_rate": 2.976722130761621e-05, "loss": 0.4565694332122803, "step": 436710 }, { "epoch": 2.595954372261949, "grad_norm": 1.1571398973464966, "learning_rate": 2.976440124788822e-05, "loss": 0.5059704780578613, "step": 436720 }, { "epoch": 2.596013814338618, "grad_norm": 1.2994017601013184, "learning_rate": 2.9761581571981123e-05, "loss": 0.4281594276428223, "step": 436730 }, { "epoch": 2.596073256415286, "grad_norm": 1.2510730028152466, "learning_rate": 2.9758762279908404e-05, "loss": 0.4771017551422119, "step": 436740 }, { "epoch": 2.5961326984919544, "grad_norm": 1.5258755683898926, "learning_rate": 2.975594337168354e-05, "loss": 0.4949833869934082, "step": 436750 }, { "epoch": 2.596192140568623, "grad_norm": 1.2039061784744263, "learning_rate": 2.975312484732e-05, "loss": 0.46148881912231443, "step": 436760 }, { "epoch": 2.596251582645291, "grad_norm": 1.490534782409668, "learning_rate": 2.975030670683132e-05, "loss": 0.46912713050842286, "step": 436770 }, { "epoch": 2.5963110247219596, "grad_norm": 1.340465784072876, "learning_rate": 2.9747488950230935e-05, "loss": 0.43214712142944334, "step": 436780 }, { "epoch": 2.596370466798628, "grad_norm": 0.9892542362213135, "learning_rate": 2.9744671577532312e-05, "loss": 0.4619649887084961, "step": 436790 }, { "epoch": 2.5964299088752965, "grad_norm": 1.3157728910446167, "learning_rate": 2.9741854588748974e-05, "loss": 0.49428548812866213, "step": 436800 }, { "epoch": 2.596489350951965, "grad_norm": 1.220969557762146, "learning_rate": 2.9739037983894375e-05, "loss": 0.5015625, "step": 436810 }, { "epoch": 2.5965487930286333, "grad_norm": 1.8117361068725586, "learning_rate": 2.9736221762981975e-05, "loss": 0.48935484886169434, "step": 436820 }, { "epoch": 2.5966082351053017, "grad_norm": 1.332431674003601, "learning_rate": 2.9733405926025294e-05, "loss": 0.49610214233398436, "step": 436830 }, { "epoch": 2.59666767718197, "grad_norm": 1.2331500053405762, "learning_rate": 2.9730590473037746e-05, "loss": 0.4436192512512207, "step": 436840 }, { "epoch": 2.5967271192586385, "grad_norm": 1.2634421586990356, "learning_rate": 2.9727775404032797e-05, "loss": 0.45946359634399414, "step": 436850 }, { "epoch": 2.596786561335307, "grad_norm": 1.4541281461715698, "learning_rate": 2.9724960719023963e-05, "loss": 0.471262264251709, "step": 436860 }, { "epoch": 2.5968460034119754, "grad_norm": 1.0932838916778564, "learning_rate": 2.972214641802468e-05, "loss": 0.4748110294342041, "step": 436870 }, { "epoch": 2.5969054454886438, "grad_norm": 1.4879728555679321, "learning_rate": 2.9719332501048407e-05, "loss": 0.4292654037475586, "step": 436880 }, { "epoch": 2.5969648875653117, "grad_norm": 1.0387318134307861, "learning_rate": 2.971651896810862e-05, "loss": 0.5256599903106689, "step": 436890 }, { "epoch": 2.5970243296419806, "grad_norm": 1.068619728088379, "learning_rate": 2.9713705819218767e-05, "loss": 0.4625056266784668, "step": 436900 }, { "epoch": 2.5970837717186486, "grad_norm": 1.3614747524261475, "learning_rate": 2.9710893054392313e-05, "loss": 0.49270038604736327, "step": 436910 }, { "epoch": 2.5971432137953174, "grad_norm": 1.3010510206222534, "learning_rate": 2.970808067364269e-05, "loss": 0.5070087432861328, "step": 436920 }, { "epoch": 2.5972026558719854, "grad_norm": 1.7501343488693237, "learning_rate": 2.970526867698338e-05, "loss": 0.4946925163269043, "step": 436930 }, { "epoch": 2.597262097948654, "grad_norm": 1.2317328453063965, "learning_rate": 2.970245706442783e-05, "loss": 0.46918668746948244, "step": 436940 }, { "epoch": 2.5973215400253222, "grad_norm": 1.3475643396377563, "learning_rate": 2.969964583598947e-05, "loss": 0.5196820259094238, "step": 436950 }, { "epoch": 2.5973809821019906, "grad_norm": 1.041357159614563, "learning_rate": 2.9696834991681783e-05, "loss": 0.43120226860046384, "step": 436960 }, { "epoch": 2.597440424178659, "grad_norm": 0.9916747808456421, "learning_rate": 2.9694024531518178e-05, "loss": 0.4936168670654297, "step": 436970 }, { "epoch": 2.5974998662553275, "grad_norm": 1.2152431011199951, "learning_rate": 2.96912144555121e-05, "loss": 0.4851022720336914, "step": 436980 }, { "epoch": 2.597559308331996, "grad_norm": 1.206827163696289, "learning_rate": 2.9688404763677024e-05, "loss": 0.4345219135284424, "step": 436990 }, { "epoch": 2.5976187504086643, "grad_norm": 1.2283319234848022, "learning_rate": 2.968559545602639e-05, "loss": 0.4625070571899414, "step": 437000 }, { "epoch": 2.5976781924853327, "grad_norm": 1.2332371473312378, "learning_rate": 2.9682786532573604e-05, "loss": 0.4381752014160156, "step": 437010 }, { "epoch": 2.597737634562001, "grad_norm": 1.384720802307129, "learning_rate": 2.967997799333212e-05, "loss": 0.4789984703063965, "step": 437020 }, { "epoch": 2.5977970766386695, "grad_norm": 1.4483200311660767, "learning_rate": 2.9677169838315382e-05, "loss": 0.4945796012878418, "step": 437030 }, { "epoch": 2.597856518715338, "grad_norm": 1.214943289756775, "learning_rate": 2.9674362067536804e-05, "loss": 0.5452865600585938, "step": 437040 }, { "epoch": 2.5979159607920064, "grad_norm": 1.7550320625305176, "learning_rate": 2.9671554681009817e-05, "loss": 0.4762087821960449, "step": 437050 }, { "epoch": 2.5979754028686743, "grad_norm": 1.2538186311721802, "learning_rate": 2.9668747678747865e-05, "loss": 0.48708581924438477, "step": 437060 }, { "epoch": 2.598034844945343, "grad_norm": 1.3793474435806274, "learning_rate": 2.9665941060764384e-05, "loss": 0.551131010055542, "step": 437070 }, { "epoch": 2.598094287022011, "grad_norm": 1.4840070009231567, "learning_rate": 2.9663134827072786e-05, "loss": 0.5131167411804199, "step": 437080 }, { "epoch": 2.59815372909868, "grad_norm": 1.4033970832824707, "learning_rate": 2.966032897768649e-05, "loss": 0.46140079498291015, "step": 437090 }, { "epoch": 2.598213171175348, "grad_norm": 1.4444659948349, "learning_rate": 2.9657523512618934e-05, "loss": 0.49090824127197263, "step": 437100 }, { "epoch": 2.5982726132520164, "grad_norm": 1.50975501537323, "learning_rate": 2.965471843188352e-05, "loss": 0.49541397094726564, "step": 437110 }, { "epoch": 2.598332055328685, "grad_norm": 1.4515719413757324, "learning_rate": 2.965191373549367e-05, "loss": 0.44713191986083983, "step": 437120 }, { "epoch": 2.5983914974053532, "grad_norm": 1.5478261709213257, "learning_rate": 2.9649109423462807e-05, "loss": 0.4492827892303467, "step": 437130 }, { "epoch": 2.5984509394820217, "grad_norm": 1.366934895515442, "learning_rate": 2.964630549580436e-05, "loss": 0.47731542587280273, "step": 437140 }, { "epoch": 2.59851038155869, "grad_norm": 1.473021388053894, "learning_rate": 2.964350195253173e-05, "loss": 0.49085297584533694, "step": 437150 }, { "epoch": 2.5985698236353585, "grad_norm": 1.3955053091049194, "learning_rate": 2.9640698793658318e-05, "loss": 0.5213361740112304, "step": 437160 }, { "epoch": 2.598629265712027, "grad_norm": 1.1641861200332642, "learning_rate": 2.9637896019197536e-05, "loss": 0.5331938743591309, "step": 437170 }, { "epoch": 2.5986887077886953, "grad_norm": 1.248010277748108, "learning_rate": 2.9635093629162786e-05, "loss": 0.4644174575805664, "step": 437180 }, { "epoch": 2.5987481498653637, "grad_norm": 1.699049949645996, "learning_rate": 2.96322916235675e-05, "loss": 0.5135733604431152, "step": 437190 }, { "epoch": 2.598807591942032, "grad_norm": 1.6893864870071411, "learning_rate": 2.9629490002425093e-05, "loss": 0.4876591682434082, "step": 437200 }, { "epoch": 2.5988670340187006, "grad_norm": 1.3788617849349976, "learning_rate": 2.962668876574889e-05, "loss": 0.44507884979248047, "step": 437210 }, { "epoch": 2.598926476095369, "grad_norm": 1.2224712371826172, "learning_rate": 2.9623887913552366e-05, "loss": 0.4538443088531494, "step": 437220 }, { "epoch": 2.5989859181720374, "grad_norm": 1.4033551216125488, "learning_rate": 2.9621087445848905e-05, "loss": 0.5224272727966308, "step": 437230 }, { "epoch": 2.599045360248706, "grad_norm": 1.3945156335830688, "learning_rate": 2.9618287362651886e-05, "loss": 0.5191000938415528, "step": 437240 }, { "epoch": 2.5991048023253738, "grad_norm": 0.9134014248847961, "learning_rate": 2.9615487663974683e-05, "loss": 0.43288002014160154, "step": 437250 }, { "epoch": 2.5991642444020426, "grad_norm": 1.271012544631958, "learning_rate": 2.961268834983077e-05, "loss": 0.5281745910644531, "step": 437260 }, { "epoch": 2.5992236864787106, "grad_norm": 1.6224042177200317, "learning_rate": 2.9609889420233454e-05, "loss": 0.46995019912719727, "step": 437270 }, { "epoch": 2.5992831285553795, "grad_norm": 1.487381100654602, "learning_rate": 2.9607090875196148e-05, "loss": 0.47650856971740724, "step": 437280 }, { "epoch": 2.5993425706320474, "grad_norm": 1.2369654178619385, "learning_rate": 2.960429271473225e-05, "loss": 0.502876615524292, "step": 437290 }, { "epoch": 2.599402012708716, "grad_norm": 1.3480325937271118, "learning_rate": 2.9601494938855162e-05, "loss": 0.4367283821105957, "step": 437300 }, { "epoch": 2.5994614547853843, "grad_norm": 0.9848626852035522, "learning_rate": 2.9598697547578218e-05, "loss": 0.4803497791290283, "step": 437310 }, { "epoch": 2.5995208968620527, "grad_norm": 1.475306510925293, "learning_rate": 2.9595900540914863e-05, "loss": 0.48998146057128905, "step": 437320 }, { "epoch": 2.599580338938721, "grad_norm": 1.3809446096420288, "learning_rate": 2.959310391887843e-05, "loss": 0.4655097007751465, "step": 437330 }, { "epoch": 2.5996397810153895, "grad_norm": 1.440457820892334, "learning_rate": 2.9590307681482292e-05, "loss": 0.5212986946105957, "step": 437340 }, { "epoch": 2.599699223092058, "grad_norm": 1.273307204246521, "learning_rate": 2.9587511828739862e-05, "loss": 0.4607112884521484, "step": 437350 }, { "epoch": 2.5997586651687263, "grad_norm": 1.7047457695007324, "learning_rate": 2.95847163606645e-05, "loss": 0.4422429084777832, "step": 437360 }, { "epoch": 2.5998181072453947, "grad_norm": 1.425333023071289, "learning_rate": 2.9581921277269564e-05, "loss": 0.46609935760498045, "step": 437370 }, { "epoch": 2.599877549322063, "grad_norm": 1.6928539276123047, "learning_rate": 2.9579126578568444e-05, "loss": 0.4485729694366455, "step": 437380 }, { "epoch": 2.5999369913987316, "grad_norm": 1.2824416160583496, "learning_rate": 2.9576332264574503e-05, "loss": 0.5032585620880127, "step": 437390 }, { "epoch": 2.5999964334754, "grad_norm": 1.2744817733764648, "learning_rate": 2.9573538335301094e-05, "loss": 0.49471383094787597, "step": 437400 }, { "epoch": 2.6000558755520684, "grad_norm": 1.103271484375, "learning_rate": 2.9570744790761586e-05, "loss": 0.4380764961242676, "step": 437410 }, { "epoch": 2.600115317628737, "grad_norm": 1.277854084968567, "learning_rate": 2.9567951630969365e-05, "loss": 0.4871542930603027, "step": 437420 }, { "epoch": 2.6001747597054052, "grad_norm": 1.5139187574386597, "learning_rate": 2.956515885593778e-05, "loss": 0.4756319999694824, "step": 437430 }, { "epoch": 2.600234201782073, "grad_norm": 1.0584776401519775, "learning_rate": 2.9562366465680185e-05, "loss": 0.41672916412353517, "step": 437440 }, { "epoch": 2.600293643858742, "grad_norm": 1.3462297916412354, "learning_rate": 2.9559574460209947e-05, "loss": 0.4653656005859375, "step": 437450 }, { "epoch": 2.60035308593541, "grad_norm": 1.0883480310440063, "learning_rate": 2.9556782839540408e-05, "loss": 0.43216376304626464, "step": 437460 }, { "epoch": 2.600412528012079, "grad_norm": 1.3554136753082275, "learning_rate": 2.955399160368494e-05, "loss": 0.46341571807861326, "step": 437470 }, { "epoch": 2.600471970088747, "grad_norm": 1.5532227754592896, "learning_rate": 2.955120075265686e-05, "loss": 0.46651515960693357, "step": 437480 }, { "epoch": 2.6005314121654153, "grad_norm": 1.4112858772277832, "learning_rate": 2.9548410286469576e-05, "loss": 0.4741657257080078, "step": 437490 }, { "epoch": 2.6005908542420837, "grad_norm": 1.3895248174667358, "learning_rate": 2.9545620205136393e-05, "loss": 0.4951790332794189, "step": 437500 }, { "epoch": 2.600650296318752, "grad_norm": 1.3006089925765991, "learning_rate": 2.954283050867067e-05, "loss": 0.4894833564758301, "step": 437510 }, { "epoch": 2.6007097383954205, "grad_norm": 1.5648287534713745, "learning_rate": 2.9540041197085767e-05, "loss": 0.45765256881713867, "step": 437520 }, { "epoch": 2.600769180472089, "grad_norm": 1.600061058998108, "learning_rate": 2.9537252270394995e-05, "loss": 0.4531713008880615, "step": 437530 }, { "epoch": 2.6008286225487574, "grad_norm": 1.1892485618591309, "learning_rate": 2.9534463728611706e-05, "loss": 0.42068119049072267, "step": 437540 }, { "epoch": 2.6008880646254258, "grad_norm": 1.2570264339447021, "learning_rate": 2.9531675571749257e-05, "loss": 0.48065738677978515, "step": 437550 }, { "epoch": 2.600947506702094, "grad_norm": 1.4156017303466797, "learning_rate": 2.952888779982097e-05, "loss": 0.4259063720703125, "step": 437560 }, { "epoch": 2.6010069487787626, "grad_norm": 1.3448505401611328, "learning_rate": 2.952610041284019e-05, "loss": 0.48919992446899413, "step": 437570 }, { "epoch": 2.601066390855431, "grad_norm": 1.4877525568008423, "learning_rate": 2.9523313410820257e-05, "loss": 0.479339599609375, "step": 437580 }, { "epoch": 2.6011258329320994, "grad_norm": 1.2927484512329102, "learning_rate": 2.9520526793774484e-05, "loss": 0.43141779899597166, "step": 437590 }, { "epoch": 2.601185275008768, "grad_norm": 1.538375735282898, "learning_rate": 2.95177405617162e-05, "loss": 0.43827500343322756, "step": 437600 }, { "epoch": 2.6012447170854363, "grad_norm": 1.4800580739974976, "learning_rate": 2.951495471465874e-05, "loss": 0.5160105705261231, "step": 437610 }, { "epoch": 2.6013041591621047, "grad_norm": 1.5286860466003418, "learning_rate": 2.951216925261545e-05, "loss": 0.4530004024505615, "step": 437620 }, { "epoch": 2.6013636012387726, "grad_norm": 1.0530682802200317, "learning_rate": 2.950938417559963e-05, "loss": 0.4506664752960205, "step": 437630 }, { "epoch": 2.6014230433154415, "grad_norm": 1.6706165075302124, "learning_rate": 2.950659948362462e-05, "loss": 0.49300203323364256, "step": 437640 }, { "epoch": 2.6014824853921095, "grad_norm": 1.5045794248580933, "learning_rate": 2.9503815176703732e-05, "loss": 0.48172593116760254, "step": 437650 }, { "epoch": 2.6015419274687783, "grad_norm": 1.0324395895004272, "learning_rate": 2.9501031254850285e-05, "loss": 0.4551746368408203, "step": 437660 }, { "epoch": 2.6016013695454463, "grad_norm": 1.2959245443344116, "learning_rate": 2.9498247718077575e-05, "loss": 0.46899123191833497, "step": 437670 }, { "epoch": 2.6016608116221147, "grad_norm": 1.119836449623108, "learning_rate": 2.9495464566398955e-05, "loss": 0.4552785873413086, "step": 437680 }, { "epoch": 2.601720253698783, "grad_norm": 1.3296599388122559, "learning_rate": 2.949268179982773e-05, "loss": 0.44073915481567383, "step": 437690 }, { "epoch": 2.6017796957754515, "grad_norm": 1.4243073463439941, "learning_rate": 2.9489899418377204e-05, "loss": 0.4912972927093506, "step": 437700 }, { "epoch": 2.60183913785212, "grad_norm": 1.909040927886963, "learning_rate": 2.948711742206069e-05, "loss": 0.5224254608154297, "step": 437710 }, { "epoch": 2.6018985799287884, "grad_norm": 1.2564674615859985, "learning_rate": 2.948433581089149e-05, "loss": 0.3912216663360596, "step": 437720 }, { "epoch": 2.601958022005457, "grad_norm": 1.3659626245498657, "learning_rate": 2.9481554584882908e-05, "loss": 0.45543537139892576, "step": 437730 }, { "epoch": 2.602017464082125, "grad_norm": 1.2040263414382935, "learning_rate": 2.947877374404826e-05, "loss": 0.472244119644165, "step": 437740 }, { "epoch": 2.6020769061587936, "grad_norm": 1.3092085123062134, "learning_rate": 2.9475993288400845e-05, "loss": 0.5054239273071289, "step": 437750 }, { "epoch": 2.602136348235462, "grad_norm": 1.052760362625122, "learning_rate": 2.9473213217953988e-05, "loss": 0.44003982543945314, "step": 437760 }, { "epoch": 2.6021957903121304, "grad_norm": 1.458491563796997, "learning_rate": 2.9470433532720913e-05, "loss": 0.5037748336791992, "step": 437770 }, { "epoch": 2.602255232388799, "grad_norm": 1.5644383430480957, "learning_rate": 2.9467654232714997e-05, "loss": 0.5219117164611816, "step": 437780 }, { "epoch": 2.6023146744654673, "grad_norm": 1.401610255241394, "learning_rate": 2.94648753179495e-05, "loss": 0.5164723873138428, "step": 437790 }, { "epoch": 2.6023741165421352, "grad_norm": 1.4316203594207764, "learning_rate": 2.9462096788437704e-05, "loss": 0.4496469020843506, "step": 437800 }, { "epoch": 2.602433558618804, "grad_norm": 1.1896674633026123, "learning_rate": 2.945931864419295e-05, "loss": 0.4495231628417969, "step": 437810 }, { "epoch": 2.602493000695472, "grad_norm": 1.2336007356643677, "learning_rate": 2.945654088522848e-05, "loss": 0.44160752296447753, "step": 437820 }, { "epoch": 2.602552442772141, "grad_norm": 1.340959906578064, "learning_rate": 2.945376351155758e-05, "loss": 0.4424558639526367, "step": 437830 }, { "epoch": 2.602611884848809, "grad_norm": 1.0118286609649658, "learning_rate": 2.9450986523193567e-05, "loss": 0.44519681930541993, "step": 437840 }, { "epoch": 2.6026713269254773, "grad_norm": 1.4773982763290405, "learning_rate": 2.944820992014971e-05, "loss": 0.45752291679382323, "step": 437850 }, { "epoch": 2.6027307690021457, "grad_norm": 1.1252936124801636, "learning_rate": 2.944543370243929e-05, "loss": 0.4713140487670898, "step": 437860 }, { "epoch": 2.602790211078814, "grad_norm": 1.0957859754562378, "learning_rate": 2.9442657870075595e-05, "loss": 0.4386754989624023, "step": 437870 }, { "epoch": 2.6028496531554826, "grad_norm": 1.3911693096160889, "learning_rate": 2.9439882423071903e-05, "loss": 0.48129096031188967, "step": 437880 }, { "epoch": 2.602909095232151, "grad_norm": 1.3551944494247437, "learning_rate": 2.9437107361441473e-05, "loss": 0.4933636665344238, "step": 437890 }, { "epoch": 2.6029685373088194, "grad_norm": 1.2722033262252808, "learning_rate": 2.9434332685197587e-05, "loss": 0.47867794036865235, "step": 437900 }, { "epoch": 2.603027979385488, "grad_norm": 1.3143891096115112, "learning_rate": 2.9431558394353542e-05, "loss": 0.42703046798706057, "step": 437910 }, { "epoch": 2.603087421462156, "grad_norm": 1.3238455057144165, "learning_rate": 2.9428784488922577e-05, "loss": 0.5073864936828614, "step": 437920 }, { "epoch": 2.6031468635388246, "grad_norm": 1.598569393157959, "learning_rate": 2.942601096891799e-05, "loss": 0.46670985221862793, "step": 437930 }, { "epoch": 2.603206305615493, "grad_norm": 1.397695779800415, "learning_rate": 2.9423237834353034e-05, "loss": 0.45771169662475586, "step": 437940 }, { "epoch": 2.6032657476921615, "grad_norm": 1.5495671033859253, "learning_rate": 2.9420465085240972e-05, "loss": 0.4873665809631348, "step": 437950 }, { "epoch": 2.60332518976883, "grad_norm": 1.1233339309692383, "learning_rate": 2.941769272159507e-05, "loss": 0.40704941749572754, "step": 437960 }, { "epoch": 2.6033846318454983, "grad_norm": 1.4466098546981812, "learning_rate": 2.9414920743428576e-05, "loss": 0.47543039321899416, "step": 437970 }, { "epoch": 2.6034440739221667, "grad_norm": 1.1489927768707275, "learning_rate": 2.941214915075478e-05, "loss": 0.4639195442199707, "step": 437980 }, { "epoch": 2.6035035159988347, "grad_norm": 1.2669512033462524, "learning_rate": 2.940937794358693e-05, "loss": 0.46957931518554685, "step": 437990 }, { "epoch": 2.6035629580755035, "grad_norm": 1.0885934829711914, "learning_rate": 2.940660712193828e-05, "loss": 0.4415442943572998, "step": 438000 }, { "epoch": 2.6036224001521715, "grad_norm": 1.1946380138397217, "learning_rate": 2.940383668582208e-05, "loss": 0.4792900085449219, "step": 438010 }, { "epoch": 2.6036818422288404, "grad_norm": 1.4574475288391113, "learning_rate": 2.9401066635251586e-05, "loss": 0.45159015655517576, "step": 438020 }, { "epoch": 2.6037412843055083, "grad_norm": 1.0894492864608765, "learning_rate": 2.939829697024003e-05, "loss": 0.510146188735962, "step": 438030 }, { "epoch": 2.6038007263821767, "grad_norm": 1.0157992839813232, "learning_rate": 2.9395527690800706e-05, "loss": 0.43017868995666503, "step": 438040 }, { "epoch": 2.603860168458845, "grad_norm": 1.1024419069290161, "learning_rate": 2.9392758796946828e-05, "loss": 0.42527995109558103, "step": 438050 }, { "epoch": 2.6039196105355136, "grad_norm": 1.1671735048294067, "learning_rate": 2.938999028869165e-05, "loss": 0.48899641036987307, "step": 438060 }, { "epoch": 2.603979052612182, "grad_norm": 1.3121412992477417, "learning_rate": 2.9387222166048418e-05, "loss": 0.4924163341522217, "step": 438070 }, { "epoch": 2.6040384946888504, "grad_norm": 1.1612532138824463, "learning_rate": 2.938445442903036e-05, "loss": 0.4623861312866211, "step": 438080 }, { "epoch": 2.604097936765519, "grad_norm": 1.0232512950897217, "learning_rate": 2.9381687077650744e-05, "loss": 0.4476794242858887, "step": 438090 }, { "epoch": 2.6041573788421872, "grad_norm": 1.2994415760040283, "learning_rate": 2.9378920111922765e-05, "loss": 0.5040885925292968, "step": 438100 }, { "epoch": 2.6042168209188556, "grad_norm": 1.436566948890686, "learning_rate": 2.9376153531859702e-05, "loss": 0.4719128131866455, "step": 438110 }, { "epoch": 2.604276262995524, "grad_norm": 1.410441279411316, "learning_rate": 2.9373387337474772e-05, "loss": 0.4429923057556152, "step": 438120 }, { "epoch": 2.6043357050721925, "grad_norm": 1.0921976566314697, "learning_rate": 2.9370621528781206e-05, "loss": 0.47540721893310545, "step": 438130 }, { "epoch": 2.604395147148861, "grad_norm": 1.242620587348938, "learning_rate": 2.9367856105792237e-05, "loss": 0.4765620231628418, "step": 438140 }, { "epoch": 2.6044545892255293, "grad_norm": 1.1170283555984497, "learning_rate": 2.93650910685211e-05, "loss": 0.4726208209991455, "step": 438150 }, { "epoch": 2.6045140313021977, "grad_norm": 1.158471941947937, "learning_rate": 2.936232641698099e-05, "loss": 0.46852564811706543, "step": 438160 }, { "epoch": 2.604573473378866, "grad_norm": 1.456661343574524, "learning_rate": 2.9359562151185178e-05, "loss": 0.45251760482788084, "step": 438170 }, { "epoch": 2.604632915455534, "grad_norm": 1.0278204679489136, "learning_rate": 2.935679827114687e-05, "loss": 0.44406375885009763, "step": 438180 }, { "epoch": 2.604692357532203, "grad_norm": 1.4267135858535767, "learning_rate": 2.935403477687928e-05, "loss": 0.44469776153564455, "step": 438190 }, { "epoch": 2.604751799608871, "grad_norm": 1.4195466041564941, "learning_rate": 2.935127166839563e-05, "loss": 0.49045472145080565, "step": 438200 }, { "epoch": 2.60481124168554, "grad_norm": 1.5825693607330322, "learning_rate": 2.9348508945709152e-05, "loss": 0.45171413421630857, "step": 438210 }, { "epoch": 2.6048706837622078, "grad_norm": 1.3015811443328857, "learning_rate": 2.934574660883304e-05, "loss": 0.47698087692260743, "step": 438220 }, { "epoch": 2.604930125838876, "grad_norm": 1.5563839673995972, "learning_rate": 2.9342984657780504e-05, "loss": 0.519964075088501, "step": 438230 }, { "epoch": 2.6049895679155446, "grad_norm": 1.1651400327682495, "learning_rate": 2.9340223092564784e-05, "loss": 0.5082301139831543, "step": 438240 }, { "epoch": 2.605049009992213, "grad_norm": 1.2496029138565063, "learning_rate": 2.93374619131991e-05, "loss": 0.47095823287963867, "step": 438250 }, { "epoch": 2.6051084520688814, "grad_norm": 1.5747473239898682, "learning_rate": 2.93347011196966e-05, "loss": 0.4664926528930664, "step": 438260 }, { "epoch": 2.60516789414555, "grad_norm": 1.182400107383728, "learning_rate": 2.9331940712070545e-05, "loss": 0.4698482036590576, "step": 438270 }, { "epoch": 2.6052273362222182, "grad_norm": 1.2061960697174072, "learning_rate": 2.9329180690334124e-05, "loss": 0.44024100303649905, "step": 438280 }, { "epoch": 2.6052867782988867, "grad_norm": 1.1604775190353394, "learning_rate": 2.9326421054500524e-05, "loss": 0.47259044647216797, "step": 438290 }, { "epoch": 2.605346220375555, "grad_norm": 1.079736351966858, "learning_rate": 2.9323661804582975e-05, "loss": 0.45407934188842775, "step": 438300 }, { "epoch": 2.6054056624522235, "grad_norm": 1.1079626083374023, "learning_rate": 2.9320902940594673e-05, "loss": 0.48224611282348634, "step": 438310 }, { "epoch": 2.605465104528892, "grad_norm": 1.3568087816238403, "learning_rate": 2.9318144462548802e-05, "loss": 0.46475930213928224, "step": 438320 }, { "epoch": 2.6055245466055603, "grad_norm": 1.424757719039917, "learning_rate": 2.9315386370458532e-05, "loss": 0.4862339496612549, "step": 438330 }, { "epoch": 2.6055839886822287, "grad_norm": 1.4178190231323242, "learning_rate": 2.9312628664337117e-05, "loss": 0.4981855869293213, "step": 438340 }, { "epoch": 2.605643430758897, "grad_norm": 1.3790955543518066, "learning_rate": 2.9309871344197702e-05, "loss": 0.4423821449279785, "step": 438350 }, { "epoch": 2.6057028728355656, "grad_norm": 1.3797203302383423, "learning_rate": 2.9307114410053482e-05, "loss": 0.46216135025024413, "step": 438360 }, { "epoch": 2.6057623149122335, "grad_norm": 1.4357348680496216, "learning_rate": 2.930435786191769e-05, "loss": 0.4560856819152832, "step": 438370 }, { "epoch": 2.6058217569889024, "grad_norm": 0.9975212216377258, "learning_rate": 2.9301601699803456e-05, "loss": 0.4340629577636719, "step": 438380 }, { "epoch": 2.6058811990655704, "grad_norm": 1.6026313304901123, "learning_rate": 2.9298845923723982e-05, "loss": 0.4953179359436035, "step": 438390 }, { "epoch": 2.6059406411422392, "grad_norm": 1.2064260244369507, "learning_rate": 2.9296090533692466e-05, "loss": 0.4719125270843506, "step": 438400 }, { "epoch": 2.606000083218907, "grad_norm": 1.0909940004348755, "learning_rate": 2.9293335529722078e-05, "loss": 0.41759281158447265, "step": 438410 }, { "epoch": 2.6060595252955756, "grad_norm": 1.495524287223816, "learning_rate": 2.9290580911825976e-05, "loss": 0.4622365951538086, "step": 438420 }, { "epoch": 2.606118967372244, "grad_norm": 1.5253022909164429, "learning_rate": 2.9287826680017405e-05, "loss": 0.46812424659729, "step": 438430 }, { "epoch": 2.6061784094489124, "grad_norm": 1.1921778917312622, "learning_rate": 2.9285072834309464e-05, "loss": 0.47931385040283203, "step": 438440 }, { "epoch": 2.606237851525581, "grad_norm": 1.1616696119308472, "learning_rate": 2.9282319374715363e-05, "loss": 0.5053833961486817, "step": 438450 }, { "epoch": 2.6062972936022493, "grad_norm": 1.2463619709014893, "learning_rate": 2.9279566301248247e-05, "loss": 0.44074182510375975, "step": 438460 }, { "epoch": 2.6063567356789177, "grad_norm": 1.5156513452529907, "learning_rate": 2.9276813613921328e-05, "loss": 0.47876763343811035, "step": 438470 }, { "epoch": 2.606416177755586, "grad_norm": 1.263288974761963, "learning_rate": 2.9274061312747747e-05, "loss": 0.4624342918395996, "step": 438480 }, { "epoch": 2.6064756198322545, "grad_norm": 1.4042924642562866, "learning_rate": 2.927130939774069e-05, "loss": 0.4351625442504883, "step": 438490 }, { "epoch": 2.606535061908923, "grad_norm": 1.3803331851959229, "learning_rate": 2.926855786891328e-05, "loss": 0.48413381576538084, "step": 438500 }, { "epoch": 2.6065945039855913, "grad_norm": 1.3473564386367798, "learning_rate": 2.9265806726278727e-05, "loss": 0.49239678382873536, "step": 438510 }, { "epoch": 2.6066539460622598, "grad_norm": 1.0375304222106934, "learning_rate": 2.926305596985015e-05, "loss": 0.45926904678344727, "step": 438520 }, { "epoch": 2.606713388138928, "grad_norm": 1.7148220539093018, "learning_rate": 2.9260305599640734e-05, "loss": 0.5105978012084961, "step": 438530 }, { "epoch": 2.606772830215596, "grad_norm": 1.066184163093567, "learning_rate": 2.9257555615663644e-05, "loss": 0.5160431861877441, "step": 438540 }, { "epoch": 2.606832272292265, "grad_norm": 1.1364929676055908, "learning_rate": 2.9254806017932012e-05, "loss": 0.4620554447174072, "step": 438550 }, { "epoch": 2.606891714368933, "grad_norm": 1.4439318180084229, "learning_rate": 2.9252056806459e-05, "loss": 0.4951495170593262, "step": 438560 }, { "epoch": 2.606951156445602, "grad_norm": 1.0201573371887207, "learning_rate": 2.9249307981257766e-05, "loss": 0.5143512725830078, "step": 438570 }, { "epoch": 2.60701059852227, "grad_norm": 0.9265467524528503, "learning_rate": 2.9246559542341457e-05, "loss": 0.41459856033325193, "step": 438580 }, { "epoch": 2.607070040598938, "grad_norm": 1.1943368911743164, "learning_rate": 2.9243811489723184e-05, "loss": 0.4269280910491943, "step": 438590 }, { "epoch": 2.6071294826756066, "grad_norm": 1.6759958267211914, "learning_rate": 2.9241063823416153e-05, "loss": 0.4573927879333496, "step": 438600 }, { "epoch": 2.607188924752275, "grad_norm": 1.2615973949432373, "learning_rate": 2.9238316543433474e-05, "loss": 0.4571545600891113, "step": 438610 }, { "epoch": 2.6072483668289435, "grad_norm": 1.2315597534179688, "learning_rate": 2.9235569649788302e-05, "loss": 0.5143105506896972, "step": 438620 }, { "epoch": 2.607307808905612, "grad_norm": 1.2512456178665161, "learning_rate": 2.923282314249377e-05, "loss": 0.5179617881774903, "step": 438630 }, { "epoch": 2.6073672509822803, "grad_norm": 1.2060438394546509, "learning_rate": 2.923007702156302e-05, "loss": 0.4474571704864502, "step": 438640 }, { "epoch": 2.6074266930589487, "grad_norm": 1.2382551431655884, "learning_rate": 2.922733128700915e-05, "loss": 0.4648292541503906, "step": 438650 }, { "epoch": 2.607486135135617, "grad_norm": 1.170892357826233, "learning_rate": 2.9224585938845363e-05, "loss": 0.4812502861022949, "step": 438660 }, { "epoch": 2.6075455772122855, "grad_norm": 1.1891390085220337, "learning_rate": 2.9221840977084758e-05, "loss": 0.46685237884521485, "step": 438670 }, { "epoch": 2.607605019288954, "grad_norm": 1.6567047834396362, "learning_rate": 2.9219096401740465e-05, "loss": 0.43784666061401367, "step": 438680 }, { "epoch": 2.6076644613656224, "grad_norm": 1.7260191440582275, "learning_rate": 2.921635221282562e-05, "loss": 0.4623756408691406, "step": 438690 }, { "epoch": 2.6077239034422908, "grad_norm": 1.4489984512329102, "learning_rate": 2.9213608410353344e-05, "loss": 0.45248026847839357, "step": 438700 }, { "epoch": 2.607783345518959, "grad_norm": 1.215531826019287, "learning_rate": 2.9210864994336768e-05, "loss": 0.4636383056640625, "step": 438710 }, { "epoch": 2.6078427875956276, "grad_norm": 1.1709163188934326, "learning_rate": 2.9208121964788982e-05, "loss": 0.5021034717559815, "step": 438720 }, { "epoch": 2.6079022296722956, "grad_norm": 1.527107834815979, "learning_rate": 2.920537932172317e-05, "loss": 0.4785409927368164, "step": 438730 }, { "epoch": 2.6079616717489644, "grad_norm": 1.422366738319397, "learning_rate": 2.9202637065152417e-05, "loss": 0.4735115051269531, "step": 438740 }, { "epoch": 2.6080211138256324, "grad_norm": 1.1323741674423218, "learning_rate": 2.9199895195089822e-05, "loss": 0.4807234287261963, "step": 438750 }, { "epoch": 2.6080805559023013, "grad_norm": 1.2281404733657837, "learning_rate": 2.919715371154854e-05, "loss": 0.39682257175445557, "step": 438760 }, { "epoch": 2.6081399979789692, "grad_norm": 1.474297285079956, "learning_rate": 2.9194412614541667e-05, "loss": 0.4354358673095703, "step": 438770 }, { "epoch": 2.6081994400556376, "grad_norm": 1.029740571975708, "learning_rate": 2.9191671904082294e-05, "loss": 0.4788508892059326, "step": 438780 }, { "epoch": 2.608258882132306, "grad_norm": 1.3403549194335938, "learning_rate": 2.9188931580183575e-05, "loss": 0.45424399375915525, "step": 438790 }, { "epoch": 2.6083183242089745, "grad_norm": 1.2844910621643066, "learning_rate": 2.9186191642858624e-05, "loss": 0.4834726810455322, "step": 438800 }, { "epoch": 2.608377766285643, "grad_norm": 1.1146481037139893, "learning_rate": 2.918345209212049e-05, "loss": 0.4825160980224609, "step": 438810 }, { "epoch": 2.6084372083623113, "grad_norm": 1.3191990852355957, "learning_rate": 2.91807129279823e-05, "loss": 0.5100072860717774, "step": 438820 }, { "epoch": 2.6084966504389797, "grad_norm": 1.3717058897018433, "learning_rate": 2.917797415045718e-05, "loss": 0.4982191562652588, "step": 438830 }, { "epoch": 2.608556092515648, "grad_norm": 1.4930009841918945, "learning_rate": 2.9175235759558222e-05, "loss": 0.4808629512786865, "step": 438840 }, { "epoch": 2.6086155345923165, "grad_norm": 1.4941256046295166, "learning_rate": 2.9172497755298507e-05, "loss": 0.4483795166015625, "step": 438850 }, { "epoch": 2.608674976668985, "grad_norm": 1.3922878503799438, "learning_rate": 2.9169760137691193e-05, "loss": 0.43991785049438475, "step": 438860 }, { "epoch": 2.6087344187456534, "grad_norm": 1.0501255989074707, "learning_rate": 2.9167022906749292e-05, "loss": 0.46037921905517576, "step": 438870 }, { "epoch": 2.608793860822322, "grad_norm": 1.3902430534362793, "learning_rate": 2.9164286062485935e-05, "loss": 0.487946605682373, "step": 438880 }, { "epoch": 2.60885330289899, "grad_norm": 1.6360349655151367, "learning_rate": 2.916154960491423e-05, "loss": 0.514169979095459, "step": 438890 }, { "epoch": 2.6089127449756586, "grad_norm": 1.3737354278564453, "learning_rate": 2.9158813534047248e-05, "loss": 0.530029010772705, "step": 438900 }, { "epoch": 2.608972187052327, "grad_norm": 1.4119722843170166, "learning_rate": 2.915607784989806e-05, "loss": 0.4523118019104004, "step": 438910 }, { "epoch": 2.609031629128995, "grad_norm": 1.1436949968338013, "learning_rate": 2.9153342552479824e-05, "loss": 0.4675473213195801, "step": 438920 }, { "epoch": 2.609091071205664, "grad_norm": 1.2398267984390259, "learning_rate": 2.9150607641805556e-05, "loss": 0.496944522857666, "step": 438930 }, { "epoch": 2.609150513282332, "grad_norm": 1.6196116209030151, "learning_rate": 2.9147873117888354e-05, "loss": 0.48502683639526367, "step": 438940 }, { "epoch": 2.6092099553590007, "grad_norm": 1.4606263637542725, "learning_rate": 2.9145138980741286e-05, "loss": 0.4895297050476074, "step": 438950 }, { "epoch": 2.6092693974356687, "grad_norm": 1.1607310771942139, "learning_rate": 2.914240523037748e-05, "loss": 0.44470906257629395, "step": 438960 }, { "epoch": 2.609328839512337, "grad_norm": 1.426868200302124, "learning_rate": 2.913967186680997e-05, "loss": 0.44080753326416017, "step": 438970 }, { "epoch": 2.6093882815890055, "grad_norm": 1.405390739440918, "learning_rate": 2.9136938890051846e-05, "loss": 0.48625593185424804, "step": 438980 }, { "epoch": 2.609447723665674, "grad_norm": 1.2336899042129517, "learning_rate": 2.913420630011618e-05, "loss": 0.45586767196655276, "step": 438990 }, { "epoch": 2.6095071657423423, "grad_norm": 1.222273349761963, "learning_rate": 2.9131474097016043e-05, "loss": 0.46709470748901366, "step": 439000 }, { "epoch": 2.6095666078190107, "grad_norm": 1.193281650543213, "learning_rate": 2.9128742280764492e-05, "loss": 0.42604541778564453, "step": 439010 }, { "epoch": 2.609626049895679, "grad_norm": 1.5546680688858032, "learning_rate": 2.9126010851374624e-05, "loss": 0.4694479465484619, "step": 439020 }, { "epoch": 2.6096854919723476, "grad_norm": 1.784255027770996, "learning_rate": 2.91232798088595e-05, "loss": 0.43728461265563967, "step": 439030 }, { "epoch": 2.609744934049016, "grad_norm": 0.9778356552124023, "learning_rate": 2.9120549153232168e-05, "loss": 0.4349223136901855, "step": 439040 }, { "epoch": 2.6098043761256844, "grad_norm": 1.6598602533340454, "learning_rate": 2.9117818884505692e-05, "loss": 0.4863945960998535, "step": 439050 }, { "epoch": 2.609863818202353, "grad_norm": 1.5255720615386963, "learning_rate": 2.911508900269314e-05, "loss": 0.45777220726013185, "step": 439060 }, { "epoch": 2.609923260279021, "grad_norm": 1.3830890655517578, "learning_rate": 2.911235950780757e-05, "loss": 0.4300535202026367, "step": 439070 }, { "epoch": 2.6099827023556896, "grad_norm": 1.2819457054138184, "learning_rate": 2.910963039986202e-05, "loss": 0.5158337116241455, "step": 439080 }, { "epoch": 2.610042144432358, "grad_norm": 1.0155571699142456, "learning_rate": 2.9106901678869586e-05, "loss": 0.45450739860534667, "step": 439090 }, { "epoch": 2.6101015865090265, "grad_norm": 1.397281527519226, "learning_rate": 2.9104173344843296e-05, "loss": 0.46441307067871096, "step": 439100 }, { "epoch": 2.6101610285856944, "grad_norm": 1.0903958082199097, "learning_rate": 2.910144539779619e-05, "loss": 0.46698408126831054, "step": 439110 }, { "epoch": 2.6102204706623633, "grad_norm": 1.4633543491363525, "learning_rate": 2.909871783774134e-05, "loss": 0.44372220039367677, "step": 439120 }, { "epoch": 2.6102799127390313, "grad_norm": 1.0488028526306152, "learning_rate": 2.9095990664691795e-05, "loss": 0.47812743186950685, "step": 439130 }, { "epoch": 2.6103393548156997, "grad_norm": 1.1263844966888428, "learning_rate": 2.9093263878660565e-05, "loss": 0.48601508140563965, "step": 439140 }, { "epoch": 2.610398796892368, "grad_norm": 1.231469988822937, "learning_rate": 2.9090537479660728e-05, "loss": 0.4591682910919189, "step": 439150 }, { "epoch": 2.6104582389690365, "grad_norm": 1.4725247621536255, "learning_rate": 2.9087811467705335e-05, "loss": 0.4221476078033447, "step": 439160 }, { "epoch": 2.610517681045705, "grad_norm": 1.2435628175735474, "learning_rate": 2.90850858428074e-05, "loss": 0.4598628044128418, "step": 439170 }, { "epoch": 2.6105771231223733, "grad_norm": 1.4701460599899292, "learning_rate": 2.9082360604979976e-05, "loss": 0.5337472915649414, "step": 439180 }, { "epoch": 2.6106365651990417, "grad_norm": 1.148581862449646, "learning_rate": 2.9079635754236094e-05, "loss": 0.4948580741882324, "step": 439190 }, { "epoch": 2.61069600727571, "grad_norm": 1.203667163848877, "learning_rate": 2.907691129058878e-05, "loss": 0.46320295333862305, "step": 439200 }, { "epoch": 2.6107554493523786, "grad_norm": 1.0722167491912842, "learning_rate": 2.9074187214051068e-05, "loss": 0.47150936126708987, "step": 439210 }, { "epoch": 2.610814891429047, "grad_norm": 1.2481969594955444, "learning_rate": 2.9071463524636022e-05, "loss": 0.47336392402648925, "step": 439220 }, { "epoch": 2.6108743335057154, "grad_norm": 1.5545586347579956, "learning_rate": 2.906874022235665e-05, "loss": 0.5323779106140136, "step": 439230 }, { "epoch": 2.610933775582384, "grad_norm": 1.2356566190719604, "learning_rate": 2.9066017307225947e-05, "loss": 0.4432474136352539, "step": 439240 }, { "epoch": 2.6109932176590522, "grad_norm": 1.5897159576416016, "learning_rate": 2.906329477925699e-05, "loss": 0.45424304008483884, "step": 439250 }, { "epoch": 2.6110526597357206, "grad_norm": 1.3340396881103516, "learning_rate": 2.9060572638462774e-05, "loss": 0.47172117233276367, "step": 439260 }, { "epoch": 2.611112101812389, "grad_norm": 1.6137359142303467, "learning_rate": 2.9057850884856307e-05, "loss": 0.4650420665740967, "step": 439270 }, { "epoch": 2.611171543889057, "grad_norm": 1.3066668510437012, "learning_rate": 2.9055129518450658e-05, "loss": 0.5046555042266846, "step": 439280 }, { "epoch": 2.611230985965726, "grad_norm": 1.189024567604065, "learning_rate": 2.9052408539258825e-05, "loss": 0.43887624740600584, "step": 439290 }, { "epoch": 2.611290428042394, "grad_norm": 1.564265251159668, "learning_rate": 2.904968794729379e-05, "loss": 0.4668262958526611, "step": 439300 }, { "epoch": 2.6113498701190627, "grad_norm": 1.0321826934814453, "learning_rate": 2.9046967742568592e-05, "loss": 0.4778564453125, "step": 439310 }, { "epoch": 2.6114093121957307, "grad_norm": 1.2415531873703003, "learning_rate": 2.9044247925096253e-05, "loss": 0.4768930435180664, "step": 439320 }, { "epoch": 2.611468754272399, "grad_norm": 1.0710241794586182, "learning_rate": 2.904152849488978e-05, "loss": 0.46049041748046876, "step": 439330 }, { "epoch": 2.6115281963490675, "grad_norm": 1.0542072057724, "learning_rate": 2.9038809451962156e-05, "loss": 0.48207716941833495, "step": 439340 }, { "epoch": 2.611587638425736, "grad_norm": 1.2510955333709717, "learning_rate": 2.9036090796326442e-05, "loss": 0.48818221092224123, "step": 439350 }, { "epoch": 2.6116470805024043, "grad_norm": 0.9636127352714539, "learning_rate": 2.90333725279956e-05, "loss": 0.44388408660888673, "step": 439360 }, { "epoch": 2.6117065225790728, "grad_norm": 1.2542059421539307, "learning_rate": 2.903065464698262e-05, "loss": 0.47109155654907225, "step": 439370 }, { "epoch": 2.611765964655741, "grad_norm": 1.6411734819412231, "learning_rate": 2.902793715330055e-05, "loss": 0.43274354934692383, "step": 439380 }, { "epoch": 2.6118254067324096, "grad_norm": 1.3099068403244019, "learning_rate": 2.9025220046962365e-05, "loss": 0.44338650703430177, "step": 439390 }, { "epoch": 2.611884848809078, "grad_norm": 1.2379070520401, "learning_rate": 2.9022503327981037e-05, "loss": 0.4902836799621582, "step": 439400 }, { "epoch": 2.6119442908857464, "grad_norm": 1.22921621799469, "learning_rate": 2.9019786996369634e-05, "loss": 0.4553865432739258, "step": 439410 }, { "epoch": 2.612003732962415, "grad_norm": 1.5965473651885986, "learning_rate": 2.9017071052141093e-05, "loss": 0.5075443267822266, "step": 439420 }, { "epoch": 2.6120631750390833, "grad_norm": 1.1455531120300293, "learning_rate": 2.9014355495308416e-05, "loss": 0.48149285316467283, "step": 439430 }, { "epoch": 2.6121226171157517, "grad_norm": 1.1734954118728638, "learning_rate": 2.901164032588457e-05, "loss": 0.4653903961181641, "step": 439440 }, { "epoch": 2.61218205919242, "grad_norm": 1.3153141736984253, "learning_rate": 2.9008925543882587e-05, "loss": 0.46056246757507324, "step": 439450 }, { "epoch": 2.6122415012690885, "grad_norm": 1.5821857452392578, "learning_rate": 2.9006211149315443e-05, "loss": 0.4799956798553467, "step": 439460 }, { "epoch": 2.6123009433457565, "grad_norm": 1.1588197946548462, "learning_rate": 2.9003497142196123e-05, "loss": 0.4992579460144043, "step": 439470 }, { "epoch": 2.6123603854224253, "grad_norm": 1.3664436340332031, "learning_rate": 2.9000783522537585e-05, "loss": 0.46932287216186525, "step": 439480 }, { "epoch": 2.6124198274990933, "grad_norm": 1.2464889287948608, "learning_rate": 2.8998070290352836e-05, "loss": 0.5047496795654297, "step": 439490 }, { "epoch": 2.612479269575762, "grad_norm": 1.2320830821990967, "learning_rate": 2.8995357445654838e-05, "loss": 0.43404192924499513, "step": 439500 }, { "epoch": 2.61253871165243, "grad_norm": 1.4893144369125366, "learning_rate": 2.8992644988456585e-05, "loss": 0.47829856872558596, "step": 439510 }, { "epoch": 2.6125981537290985, "grad_norm": 1.5328843593597412, "learning_rate": 2.8989932918771047e-05, "loss": 0.4307874202728271, "step": 439520 }, { "epoch": 2.612657595805767, "grad_norm": 1.0296658277511597, "learning_rate": 2.8987221236611183e-05, "loss": 0.4036903381347656, "step": 439530 }, { "epoch": 2.6127170378824354, "grad_norm": 1.2820912599563599, "learning_rate": 2.898450994198999e-05, "loss": 0.48707242012023927, "step": 439540 }, { "epoch": 2.612776479959104, "grad_norm": 1.6102508306503296, "learning_rate": 2.8981799034920426e-05, "loss": 0.4930201530456543, "step": 439550 }, { "epoch": 2.612835922035772, "grad_norm": 1.8495829105377197, "learning_rate": 2.8979088515415458e-05, "loss": 0.505584716796875, "step": 439560 }, { "epoch": 2.6128953641124406, "grad_norm": 1.2287895679473877, "learning_rate": 2.8976378383488033e-05, "loss": 0.4940494537353516, "step": 439570 }, { "epoch": 2.612954806189109, "grad_norm": 1.370539665222168, "learning_rate": 2.8973668639151163e-05, "loss": 0.4908900737762451, "step": 439580 }, { "epoch": 2.6130142482657774, "grad_norm": 1.3008743524551392, "learning_rate": 2.8970959282417765e-05, "loss": 0.4885824680328369, "step": 439590 }, { "epoch": 2.613073690342446, "grad_norm": 1.7730460166931152, "learning_rate": 2.8968250313300826e-05, "loss": 0.4807849884033203, "step": 439600 }, { "epoch": 2.6131331324191143, "grad_norm": 0.9870175719261169, "learning_rate": 2.89655417318133e-05, "loss": 0.47980237007141113, "step": 439610 }, { "epoch": 2.6131925744957827, "grad_norm": 1.0025392770767212, "learning_rate": 2.896283353796813e-05, "loss": 0.4383504867553711, "step": 439620 }, { "epoch": 2.613252016572451, "grad_norm": 1.1005187034606934, "learning_rate": 2.8960125731778264e-05, "loss": 0.4619361400604248, "step": 439630 }, { "epoch": 2.6133114586491195, "grad_norm": 1.0845181941986084, "learning_rate": 2.89574183132567e-05, "loss": 0.4353893756866455, "step": 439640 }, { "epoch": 2.613370900725788, "grad_norm": 1.3886754512786865, "learning_rate": 2.895471128241636e-05, "loss": 0.4534608840942383, "step": 439650 }, { "epoch": 2.613430342802456, "grad_norm": 1.2674016952514648, "learning_rate": 2.8952004639270193e-05, "loss": 0.49236021041870115, "step": 439660 }, { "epoch": 2.6134897848791248, "grad_norm": 1.3397544622421265, "learning_rate": 2.8949298383831142e-05, "loss": 0.441726016998291, "step": 439670 }, { "epoch": 2.6135492269557927, "grad_norm": 1.5049636363983154, "learning_rate": 2.894659251611217e-05, "loss": 0.46560077667236327, "step": 439680 }, { "epoch": 2.6136086690324616, "grad_norm": 1.159022569656372, "learning_rate": 2.894388703612621e-05, "loss": 0.46871399879455566, "step": 439690 }, { "epoch": 2.6136681111091296, "grad_norm": 1.3711189031600952, "learning_rate": 2.8941181943886182e-05, "loss": 0.4716172695159912, "step": 439700 }, { "epoch": 2.613727553185798, "grad_norm": 1.1679342985153198, "learning_rate": 2.893847723940507e-05, "loss": 0.49706459045410156, "step": 439710 }, { "epoch": 2.6137869952624664, "grad_norm": 1.6088614463806152, "learning_rate": 2.8935772922695793e-05, "loss": 0.5072585582733155, "step": 439720 }, { "epoch": 2.613846437339135, "grad_norm": 1.29789400100708, "learning_rate": 2.893306899377128e-05, "loss": 0.46982383728027344, "step": 439730 }, { "epoch": 2.613905879415803, "grad_norm": 1.3277297019958496, "learning_rate": 2.893036545264447e-05, "loss": 0.46970839500427247, "step": 439740 }, { "epoch": 2.6139653214924716, "grad_norm": 1.6463353633880615, "learning_rate": 2.89276622993283e-05, "loss": 0.4669680595397949, "step": 439750 }, { "epoch": 2.61402476356914, "grad_norm": 1.255508542060852, "learning_rate": 2.8924959533835687e-05, "loss": 0.5208792686462402, "step": 439760 }, { "epoch": 2.6140842056458085, "grad_norm": 1.464911937713623, "learning_rate": 2.892225715617959e-05, "loss": 0.41446762084960936, "step": 439770 }, { "epoch": 2.614143647722477, "grad_norm": 1.1363307237625122, "learning_rate": 2.8919555166372914e-05, "loss": 0.45105686187744143, "step": 439780 }, { "epoch": 2.6142030897991453, "grad_norm": 1.3206144571304321, "learning_rate": 2.891685356442861e-05, "loss": 0.46613469123840334, "step": 439790 }, { "epoch": 2.6142625318758137, "grad_norm": 0.9533683061599731, "learning_rate": 2.8914152350359546e-05, "loss": 0.4670268058776855, "step": 439800 }, { "epoch": 2.614321973952482, "grad_norm": 1.0800962448120117, "learning_rate": 2.8911451524178694e-05, "loss": 0.4868650436401367, "step": 439810 }, { "epoch": 2.6143814160291505, "grad_norm": 1.3655507564544678, "learning_rate": 2.8908751085898956e-05, "loss": 0.47989277839660643, "step": 439820 }, { "epoch": 2.614440858105819, "grad_norm": 1.1082178354263306, "learning_rate": 2.8906051035533232e-05, "loss": 0.4902795791625977, "step": 439830 }, { "epoch": 2.6145003001824874, "grad_norm": 1.5321966409683228, "learning_rate": 2.8903351373094477e-05, "loss": 0.5119885921478271, "step": 439840 }, { "epoch": 2.6145597422591553, "grad_norm": 1.1339949369430542, "learning_rate": 2.8900652098595605e-05, "loss": 0.45169410705566404, "step": 439850 }, { "epoch": 2.614619184335824, "grad_norm": 1.300537347793579, "learning_rate": 2.889795321204948e-05, "loss": 0.45653958320617677, "step": 439860 }, { "epoch": 2.614678626412492, "grad_norm": 1.209210991859436, "learning_rate": 2.889525471346905e-05, "loss": 0.4916951656341553, "step": 439870 }, { "epoch": 2.6147380684891606, "grad_norm": 1.1136391162872314, "learning_rate": 2.889255660286722e-05, "loss": 0.4301417827606201, "step": 439880 }, { "epoch": 2.614797510565829, "grad_norm": 1.3564443588256836, "learning_rate": 2.888985888025688e-05, "loss": 0.49544658660888674, "step": 439890 }, { "epoch": 2.6148569526424974, "grad_norm": 1.353477120399475, "learning_rate": 2.8887161545650974e-05, "loss": 0.49962821006774905, "step": 439900 }, { "epoch": 2.614916394719166, "grad_norm": 1.3952269554138184, "learning_rate": 2.888446459906237e-05, "loss": 0.504854393005371, "step": 439910 }, { "epoch": 2.6149758367958342, "grad_norm": 1.4494693279266357, "learning_rate": 2.8881768040503975e-05, "loss": 0.44199414253234864, "step": 439920 }, { "epoch": 2.6150352788725026, "grad_norm": 0.9148450493812561, "learning_rate": 2.887907186998868e-05, "loss": 0.4646599769592285, "step": 439930 }, { "epoch": 2.615094720949171, "grad_norm": 1.0562995672225952, "learning_rate": 2.8876376087529404e-05, "loss": 0.4333852767944336, "step": 439940 }, { "epoch": 2.6151541630258395, "grad_norm": 1.3025157451629639, "learning_rate": 2.8873680693139044e-05, "loss": 0.5000190734863281, "step": 439950 }, { "epoch": 2.615213605102508, "grad_norm": 1.4641687870025635, "learning_rate": 2.8870985686830476e-05, "loss": 0.4863760471343994, "step": 439960 }, { "epoch": 2.6152730471791763, "grad_norm": 1.2726225852966309, "learning_rate": 2.8868291068616592e-05, "loss": 0.5191779613494873, "step": 439970 }, { "epoch": 2.6153324892558447, "grad_norm": 1.2055939435958862, "learning_rate": 2.88655968385103e-05, "loss": 0.4805617332458496, "step": 439980 }, { "epoch": 2.615391931332513, "grad_norm": 1.1862714290618896, "learning_rate": 2.886290299652446e-05, "loss": 0.5008602142333984, "step": 439990 }, { "epoch": 2.6154513734091815, "grad_norm": 1.4621278047561646, "learning_rate": 2.886020954267199e-05, "loss": 0.47464561462402344, "step": 440000 }, { "epoch": 2.61551081548585, "grad_norm": 0.8271809816360474, "learning_rate": 2.8857516476965757e-05, "loss": 0.4984795093536377, "step": 440010 }, { "epoch": 2.615570257562518, "grad_norm": 1.2732211351394653, "learning_rate": 2.8854823799418657e-05, "loss": 0.4644596099853516, "step": 440020 }, { "epoch": 2.615629699639187, "grad_norm": 1.0697888135910034, "learning_rate": 2.8852131510043555e-05, "loss": 0.45690135955810546, "step": 440030 }, { "epoch": 2.6156891417158548, "grad_norm": 1.457219123840332, "learning_rate": 2.884943960885333e-05, "loss": 0.42081174850463865, "step": 440040 }, { "epoch": 2.6157485837925236, "grad_norm": 1.4400547742843628, "learning_rate": 2.884674809586088e-05, "loss": 0.45619025230407717, "step": 440050 }, { "epoch": 2.6158080258691916, "grad_norm": 1.4190106391906738, "learning_rate": 2.8844056971079042e-05, "loss": 0.4885593891143799, "step": 440060 }, { "epoch": 2.61586746794586, "grad_norm": 1.2695869207382202, "learning_rate": 2.8841366234520728e-05, "loss": 0.4594892024993896, "step": 440070 }, { "epoch": 2.6159269100225284, "grad_norm": 1.2280914783477783, "learning_rate": 2.8838675886198796e-05, "loss": 0.5527978897094726, "step": 440080 }, { "epoch": 2.615986352099197, "grad_norm": 1.1971290111541748, "learning_rate": 2.8835985926126118e-05, "loss": 0.49361386299133303, "step": 440090 }, { "epoch": 2.6160457941758652, "grad_norm": 1.0964348316192627, "learning_rate": 2.8833296354315552e-05, "loss": 0.5026217937469483, "step": 440100 }, { "epoch": 2.6161052362525337, "grad_norm": 1.573649287223816, "learning_rate": 2.8830607170779976e-05, "loss": 0.5068569183349609, "step": 440110 }, { "epoch": 2.616164678329202, "grad_norm": 1.1105194091796875, "learning_rate": 2.8827918375532238e-05, "loss": 0.47521557807922366, "step": 440120 }, { "epoch": 2.6162241204058705, "grad_norm": 1.473625659942627, "learning_rate": 2.882522996858522e-05, "loss": 0.5073145866394043, "step": 440130 }, { "epoch": 2.616283562482539, "grad_norm": 1.1081207990646362, "learning_rate": 2.882254194995177e-05, "loss": 0.45907025337219237, "step": 440140 }, { "epoch": 2.6163430045592073, "grad_norm": 1.0210411548614502, "learning_rate": 2.881985431964476e-05, "loss": 0.4036243438720703, "step": 440150 }, { "epoch": 2.6164024466358757, "grad_norm": 1.0095454454421997, "learning_rate": 2.8817167077677033e-05, "loss": 0.43857173919677733, "step": 440160 }, { "epoch": 2.616461888712544, "grad_norm": 1.5432173013687134, "learning_rate": 2.8814480224061447e-05, "loss": 0.5389454364776611, "step": 440170 }, { "epoch": 2.6165213307892126, "grad_norm": 1.4498887062072754, "learning_rate": 2.8811793758810852e-05, "loss": 0.4660489082336426, "step": 440180 }, { "epoch": 2.616580772865881, "grad_norm": 1.1322731971740723, "learning_rate": 2.8809107681938095e-05, "loss": 0.5511372566223145, "step": 440190 }, { "epoch": 2.6166402149425494, "grad_norm": 1.1390714645385742, "learning_rate": 2.880642199345604e-05, "loss": 0.4879158020019531, "step": 440200 }, { "epoch": 2.6166996570192174, "grad_norm": 1.4656813144683838, "learning_rate": 2.880373669337753e-05, "loss": 0.5236471652984619, "step": 440210 }, { "epoch": 2.616759099095886, "grad_norm": 1.2225284576416016, "learning_rate": 2.880105178171541e-05, "loss": 0.447203254699707, "step": 440220 }, { "epoch": 2.616818541172554, "grad_norm": 1.3985570669174194, "learning_rate": 2.8798367258482534e-05, "loss": 0.4735832214355469, "step": 440230 }, { "epoch": 2.616877983249223, "grad_norm": 1.0517082214355469, "learning_rate": 2.879568312369172e-05, "loss": 0.44534716606140134, "step": 440240 }, { "epoch": 2.616937425325891, "grad_norm": 1.1732239723205566, "learning_rate": 2.8792999377355805e-05, "loss": 0.44957895278930665, "step": 440250 }, { "epoch": 2.6169968674025594, "grad_norm": 1.3262457847595215, "learning_rate": 2.879031601948765e-05, "loss": 0.4588120460510254, "step": 440260 }, { "epoch": 2.617056309479228, "grad_norm": 1.8586008548736572, "learning_rate": 2.8787633050100094e-05, "loss": 0.48915805816650393, "step": 440270 }, { "epoch": 2.6171157515558963, "grad_norm": 1.3191792964935303, "learning_rate": 2.8784950469205986e-05, "loss": 0.4228832721710205, "step": 440280 }, { "epoch": 2.6171751936325647, "grad_norm": 1.1411871910095215, "learning_rate": 2.878226827681808e-05, "loss": 0.4372696876525879, "step": 440290 }, { "epoch": 2.617234635709233, "grad_norm": 1.4140950441360474, "learning_rate": 2.8779586472949292e-05, "loss": 0.48275089263916016, "step": 440300 }, { "epoch": 2.6172940777859015, "grad_norm": 1.325706124305725, "learning_rate": 2.877690505761242e-05, "loss": 0.5099064826965332, "step": 440310 }, { "epoch": 2.61735351986257, "grad_norm": 1.1971807479858398, "learning_rate": 2.877422403082026e-05, "loss": 0.47967052459716797, "step": 440320 }, { "epoch": 2.6174129619392383, "grad_norm": 1.3194918632507324, "learning_rate": 2.87715433925857e-05, "loss": 0.47558369636535647, "step": 440330 }, { "epoch": 2.6174724040159068, "grad_norm": 1.0471980571746826, "learning_rate": 2.8768863142921537e-05, "loss": 0.48107500076293946, "step": 440340 }, { "epoch": 2.617531846092575, "grad_norm": 1.35921311378479, "learning_rate": 2.8766183281840553e-05, "loss": 0.4370105743408203, "step": 440350 }, { "epoch": 2.6175912881692436, "grad_norm": 1.033894419670105, "learning_rate": 2.876350380935562e-05, "loss": 0.4548606872558594, "step": 440360 }, { "epoch": 2.617650730245912, "grad_norm": 0.9946701526641846, "learning_rate": 2.8760824725479535e-05, "loss": 0.43375496864318847, "step": 440370 }, { "epoch": 2.6177101723225804, "grad_norm": 1.0525829792022705, "learning_rate": 2.8758146030225108e-05, "loss": 0.46825308799743653, "step": 440380 }, { "epoch": 2.617769614399249, "grad_norm": 1.3682446479797363, "learning_rate": 2.8755467723605162e-05, "loss": 0.453215503692627, "step": 440390 }, { "epoch": 2.617829056475917, "grad_norm": 1.3092694282531738, "learning_rate": 2.8752789805632528e-05, "loss": 0.44516839981079104, "step": 440400 }, { "epoch": 2.6178884985525857, "grad_norm": 1.0686472654342651, "learning_rate": 2.8750112276319986e-05, "loss": 0.4580549240112305, "step": 440410 }, { "epoch": 2.6179479406292536, "grad_norm": 1.0930012464523315, "learning_rate": 2.8747435135680327e-05, "loss": 0.5052478790283204, "step": 440420 }, { "epoch": 2.6180073827059225, "grad_norm": 1.466689109802246, "learning_rate": 2.874475838372641e-05, "loss": 0.5015022277832031, "step": 440430 }, { "epoch": 2.6180668247825905, "grad_norm": 1.2296085357666016, "learning_rate": 2.8742082020471016e-05, "loss": 0.4292470455169678, "step": 440440 }, { "epoch": 2.618126266859259, "grad_norm": 1.1742023229599, "learning_rate": 2.873940604592692e-05, "loss": 0.5198391914367676, "step": 440450 }, { "epoch": 2.6181857089359273, "grad_norm": 1.4347161054611206, "learning_rate": 2.8736730460106993e-05, "loss": 0.4425778388977051, "step": 440460 }, { "epoch": 2.6182451510125957, "grad_norm": 1.2647823095321655, "learning_rate": 2.8734055263023974e-05, "loss": 0.43084025382995605, "step": 440470 }, { "epoch": 2.618304593089264, "grad_norm": 1.286781668663025, "learning_rate": 2.873138045469065e-05, "loss": 0.4411035060882568, "step": 440480 }, { "epoch": 2.6183640351659325, "grad_norm": 1.4446985721588135, "learning_rate": 2.8728706035119868e-05, "loss": 0.4960744857788086, "step": 440490 }, { "epoch": 2.618423477242601, "grad_norm": 1.3518933057785034, "learning_rate": 2.8726032004324388e-05, "loss": 0.48450403213500975, "step": 440500 }, { "epoch": 2.6184829193192694, "grad_norm": 1.212924838066101, "learning_rate": 2.8723358362317017e-05, "loss": 0.48087048530578613, "step": 440510 }, { "epoch": 2.6185423613959378, "grad_norm": 1.205666422843933, "learning_rate": 2.872068510911054e-05, "loss": 0.49054651260375975, "step": 440520 }, { "epoch": 2.618601803472606, "grad_norm": 1.3055827617645264, "learning_rate": 2.871801224471773e-05, "loss": 0.450684642791748, "step": 440530 }, { "epoch": 2.6186612455492746, "grad_norm": 1.4761208295822144, "learning_rate": 2.8715339769151394e-05, "loss": 0.4510629177093506, "step": 440540 }, { "epoch": 2.618720687625943, "grad_norm": 0.9345632791519165, "learning_rate": 2.8712667682424298e-05, "loss": 0.44223432540893554, "step": 440550 }, { "epoch": 2.6187801297026114, "grad_norm": 0.899573028087616, "learning_rate": 2.870999598454925e-05, "loss": 0.46093339920043946, "step": 440560 }, { "epoch": 2.61883957177928, "grad_norm": 0.9870707988739014, "learning_rate": 2.8707324675539016e-05, "loss": 0.45740489959716796, "step": 440570 }, { "epoch": 2.6188990138559483, "grad_norm": 1.1848798990249634, "learning_rate": 2.8704653755406362e-05, "loss": 0.4445010185241699, "step": 440580 }, { "epoch": 2.6189584559326162, "grad_norm": 1.4927992820739746, "learning_rate": 2.8701983224164085e-05, "loss": 0.47321739196777346, "step": 440590 }, { "epoch": 2.619017898009285, "grad_norm": 1.2095249891281128, "learning_rate": 2.8699313081824952e-05, "loss": 0.4678484916687012, "step": 440600 }, { "epoch": 2.619077340085953, "grad_norm": 1.5658416748046875, "learning_rate": 2.8696643328401718e-05, "loss": 0.47695560455322267, "step": 440610 }, { "epoch": 2.6191367821626215, "grad_norm": 1.2571817636489868, "learning_rate": 2.8693973963907193e-05, "loss": 0.4658954620361328, "step": 440620 }, { "epoch": 2.61919622423929, "grad_norm": 1.3790576457977295, "learning_rate": 2.869130498835413e-05, "loss": 0.42442855834960935, "step": 440630 }, { "epoch": 2.6192556663159583, "grad_norm": 1.2153435945510864, "learning_rate": 2.8688636401755283e-05, "loss": 0.4347752571105957, "step": 440640 }, { "epoch": 2.6193151083926267, "grad_norm": 1.3004904985427856, "learning_rate": 2.868596820412342e-05, "loss": 0.4549426555633545, "step": 440650 }, { "epoch": 2.619374550469295, "grad_norm": 0.9792636036872864, "learning_rate": 2.8683300395471318e-05, "loss": 0.437923526763916, "step": 440660 }, { "epoch": 2.6194339925459635, "grad_norm": 1.1589702367782593, "learning_rate": 2.868063297581174e-05, "loss": 0.42163839340209963, "step": 440670 }, { "epoch": 2.619493434622632, "grad_norm": 1.5105559825897217, "learning_rate": 2.8677965945157414e-05, "loss": 0.491118335723877, "step": 440680 }, { "epoch": 2.6195528766993004, "grad_norm": 1.3530975580215454, "learning_rate": 2.8675299303521135e-05, "loss": 0.4755107402801514, "step": 440690 }, { "epoch": 2.619612318775969, "grad_norm": 1.3522007465362549, "learning_rate": 2.867263305091566e-05, "loss": 0.4654660701751709, "step": 440700 }, { "epoch": 2.619671760852637, "grad_norm": 1.2846624851226807, "learning_rate": 2.8669967187353718e-05, "loss": 0.5050979614257812, "step": 440710 }, { "epoch": 2.6197312029293056, "grad_norm": 1.429690957069397, "learning_rate": 2.8667301712848083e-05, "loss": 0.4687538146972656, "step": 440720 }, { "epoch": 2.619790645005974, "grad_norm": 1.0426472425460815, "learning_rate": 2.8664636627411485e-05, "loss": 0.49543232917785646, "step": 440730 }, { "epoch": 2.6198500870826424, "grad_norm": 1.4074701070785522, "learning_rate": 2.8661971931056676e-05, "loss": 0.4608067512512207, "step": 440740 }, { "epoch": 2.619909529159311, "grad_norm": 1.5324327945709229, "learning_rate": 2.8659307623796432e-05, "loss": 0.42514514923095703, "step": 440750 }, { "epoch": 2.619968971235979, "grad_norm": 1.4073315858840942, "learning_rate": 2.865664370564347e-05, "loss": 0.509387731552124, "step": 440760 }, { "epoch": 2.6200284133126477, "grad_norm": 1.2729783058166504, "learning_rate": 2.8653980176610563e-05, "loss": 0.4614872455596924, "step": 440770 }, { "epoch": 2.6200878553893157, "grad_norm": 1.194004774093628, "learning_rate": 2.8651317036710396e-05, "loss": 0.48883767127990724, "step": 440780 }, { "epoch": 2.6201472974659845, "grad_norm": 1.348505973815918, "learning_rate": 2.8648654285955755e-05, "loss": 0.471774959564209, "step": 440790 }, { "epoch": 2.6202067395426525, "grad_norm": 1.0051255226135254, "learning_rate": 2.8645991924359373e-05, "loss": 0.4565258502960205, "step": 440800 }, { "epoch": 2.620266181619321, "grad_norm": 1.501490592956543, "learning_rate": 2.8643329951933966e-05, "loss": 0.48375759124755857, "step": 440810 }, { "epoch": 2.6203256236959893, "grad_norm": 1.5110901594161987, "learning_rate": 2.864066836869229e-05, "loss": 0.42901997566223143, "step": 440820 }, { "epoch": 2.6203850657726577, "grad_norm": 1.3049097061157227, "learning_rate": 2.8638007174647086e-05, "loss": 0.47983474731445314, "step": 440830 }, { "epoch": 2.620444507849326, "grad_norm": 1.1999669075012207, "learning_rate": 2.8635346369811033e-05, "loss": 0.4306346893310547, "step": 440840 }, { "epoch": 2.6205039499259946, "grad_norm": 1.0835061073303223, "learning_rate": 2.8632685954196913e-05, "loss": 0.47305946350097655, "step": 440850 }, { "epoch": 2.620563392002663, "grad_norm": 1.1308457851409912, "learning_rate": 2.8630025927817427e-05, "loss": 0.4883664608001709, "step": 440860 }, { "epoch": 2.6206228340793314, "grad_norm": 1.4395924806594849, "learning_rate": 2.8627366290685285e-05, "loss": 0.4709585189819336, "step": 440870 }, { "epoch": 2.620682276156, "grad_norm": 1.3491840362548828, "learning_rate": 2.8624707042813253e-05, "loss": 0.44627857208251953, "step": 440880 }, { "epoch": 2.620741718232668, "grad_norm": 1.1876283884048462, "learning_rate": 2.862204818421404e-05, "loss": 0.4150993824005127, "step": 440890 }, { "epoch": 2.6208011603093366, "grad_norm": 1.3598965406417847, "learning_rate": 2.8619389714900347e-05, "loss": 0.4480766296386719, "step": 440900 }, { "epoch": 2.620860602386005, "grad_norm": 1.6036332845687866, "learning_rate": 2.861673163488488e-05, "loss": 0.4665935516357422, "step": 440910 }, { "epoch": 2.6209200444626735, "grad_norm": 1.194410800933838, "learning_rate": 2.861407394418038e-05, "loss": 0.5032153606414795, "step": 440920 }, { "epoch": 2.620979486539342, "grad_norm": 1.2346183061599731, "learning_rate": 2.861141664279956e-05, "loss": 0.4663290023803711, "step": 440930 }, { "epoch": 2.6210389286160103, "grad_norm": 1.5184470415115356, "learning_rate": 2.8608759730755108e-05, "loss": 0.4848764419555664, "step": 440940 }, { "epoch": 2.6210983706926783, "grad_norm": 1.114418864250183, "learning_rate": 2.8606103208059774e-05, "loss": 0.4852272033691406, "step": 440950 }, { "epoch": 2.621157812769347, "grad_norm": 1.4748783111572266, "learning_rate": 2.8603447074726236e-05, "loss": 0.5018452644348145, "step": 440960 }, { "epoch": 2.621217254846015, "grad_norm": 1.2312766313552856, "learning_rate": 2.860079133076719e-05, "loss": 0.4731014251708984, "step": 440970 }, { "epoch": 2.621276696922684, "grad_norm": 1.2878859043121338, "learning_rate": 2.8598135976195367e-05, "loss": 0.43044538497924806, "step": 440980 }, { "epoch": 2.621336138999352, "grad_norm": 1.3698176145553589, "learning_rate": 2.859548101102347e-05, "loss": 0.49529366493225097, "step": 440990 }, { "epoch": 2.6213955810760203, "grad_norm": 1.128410816192627, "learning_rate": 2.859282643526418e-05, "loss": 0.48721656799316404, "step": 441000 }, { "epoch": 2.6214550231526887, "grad_norm": 0.9499284625053406, "learning_rate": 2.8590172248930203e-05, "loss": 0.44769773483276365, "step": 441010 }, { "epoch": 2.621514465229357, "grad_norm": 1.175713300704956, "learning_rate": 2.8587518452034233e-05, "loss": 0.49934611320495603, "step": 441020 }, { "epoch": 2.6215739073060256, "grad_norm": 1.3792449235916138, "learning_rate": 2.8584865044588982e-05, "loss": 0.4954212188720703, "step": 441030 }, { "epoch": 2.621633349382694, "grad_norm": 1.1271147727966309, "learning_rate": 2.8582212026607102e-05, "loss": 0.4889410972595215, "step": 441040 }, { "epoch": 2.6216927914593624, "grad_norm": 1.5030802488327026, "learning_rate": 2.8579559398101343e-05, "loss": 0.46227397918701174, "step": 441050 }, { "epoch": 2.621752233536031, "grad_norm": 1.645261287689209, "learning_rate": 2.8576907159084354e-05, "loss": 0.48571386337280276, "step": 441060 }, { "epoch": 2.6218116756126992, "grad_norm": 1.0116938352584839, "learning_rate": 2.8574255309568826e-05, "loss": 0.4790217876434326, "step": 441070 }, { "epoch": 2.6218711176893676, "grad_norm": 1.3790181875228882, "learning_rate": 2.8571603849567457e-05, "loss": 0.4428138732910156, "step": 441080 }, { "epoch": 2.621930559766036, "grad_norm": 1.277658224105835, "learning_rate": 2.856895277909292e-05, "loss": 0.4247076988220215, "step": 441090 }, { "epoch": 2.6219900018427045, "grad_norm": 1.229178786277771, "learning_rate": 2.856630209815788e-05, "loss": 0.45697917938232424, "step": 441100 }, { "epoch": 2.622049443919373, "grad_norm": 1.6659789085388184, "learning_rate": 2.8563651806775072e-05, "loss": 0.5302914619445801, "step": 441110 }, { "epoch": 2.6221088859960413, "grad_norm": 1.4423396587371826, "learning_rate": 2.8561001904957125e-05, "loss": 0.4683736801147461, "step": 441120 }, { "epoch": 2.6221683280727097, "grad_norm": 1.480410099029541, "learning_rate": 2.8558352392716742e-05, "loss": 0.5276861190795898, "step": 441130 }, { "epoch": 2.6222277701493777, "grad_norm": 1.402117371559143, "learning_rate": 2.8555703270066575e-05, "loss": 0.46511430740356446, "step": 441140 }, { "epoch": 2.6222872122260465, "grad_norm": 1.1976606845855713, "learning_rate": 2.855305453701931e-05, "loss": 0.49024477005004885, "step": 441150 }, { "epoch": 2.6223466543027145, "grad_norm": 1.4692836999893188, "learning_rate": 2.8550406193587615e-05, "loss": 0.4835217475891113, "step": 441160 }, { "epoch": 2.6224060963793834, "grad_norm": 1.1444058418273926, "learning_rate": 2.8547758239784138e-05, "loss": 0.4729337215423584, "step": 441170 }, { "epoch": 2.6224655384560513, "grad_norm": 1.35470449924469, "learning_rate": 2.8545110675621596e-05, "loss": 0.47310304641723633, "step": 441180 }, { "epoch": 2.6225249805327198, "grad_norm": 1.3938716650009155, "learning_rate": 2.8542463501112622e-05, "loss": 0.47603797912597656, "step": 441190 }, { "epoch": 2.622584422609388, "grad_norm": 1.1077227592468262, "learning_rate": 2.8539816716269872e-05, "loss": 0.4672551155090332, "step": 441200 }, { "epoch": 2.6226438646860566, "grad_norm": 1.5598303079605103, "learning_rate": 2.8537170321106023e-05, "loss": 0.4981093406677246, "step": 441210 }, { "epoch": 2.622703306762725, "grad_norm": 1.446053385734558, "learning_rate": 2.8534524315633728e-05, "loss": 0.4632774829864502, "step": 441220 }, { "epoch": 2.6227627488393934, "grad_norm": 1.9603314399719238, "learning_rate": 2.8531878699865628e-05, "loss": 0.505117130279541, "step": 441230 }, { "epoch": 2.622822190916062, "grad_norm": 1.1452672481536865, "learning_rate": 2.8529233473814416e-05, "loss": 0.44196529388427735, "step": 441240 }, { "epoch": 2.6228816329927302, "grad_norm": 0.9773613214492798, "learning_rate": 2.8526588637492723e-05, "loss": 0.4209749698638916, "step": 441250 }, { "epoch": 2.6229410750693987, "grad_norm": 1.487199068069458, "learning_rate": 2.852394419091322e-05, "loss": 0.5009798526763916, "step": 441260 }, { "epoch": 2.623000517146067, "grad_norm": 1.3507702350616455, "learning_rate": 2.8521300134088515e-05, "loss": 0.44862847328186034, "step": 441270 }, { "epoch": 2.6230599592227355, "grad_norm": 1.4022722244262695, "learning_rate": 2.8518656467031295e-05, "loss": 0.4871060371398926, "step": 441280 }, { "epoch": 2.623119401299404, "grad_norm": 1.4775025844573975, "learning_rate": 2.8516013189754186e-05, "loss": 0.4712306022644043, "step": 441290 }, { "epoch": 2.6231788433760723, "grad_norm": 1.3968286514282227, "learning_rate": 2.8513370302269838e-05, "loss": 0.5224735260009765, "step": 441300 }, { "epoch": 2.6232382854527407, "grad_norm": 1.4557112455368042, "learning_rate": 2.8510727804590903e-05, "loss": 0.4447155475616455, "step": 441310 }, { "epoch": 2.623297727529409, "grad_norm": 1.3553880453109741, "learning_rate": 2.8508085696730035e-05, "loss": 0.5050070762634278, "step": 441320 }, { "epoch": 2.623357169606077, "grad_norm": 1.4862186908721924, "learning_rate": 2.850544397869982e-05, "loss": 0.45963335037231445, "step": 441330 }, { "epoch": 2.623416611682746, "grad_norm": 1.110863447189331, "learning_rate": 2.8502802650512948e-05, "loss": 0.5024051189422607, "step": 441340 }, { "epoch": 2.623476053759414, "grad_norm": 1.4226382970809937, "learning_rate": 2.8500161712182028e-05, "loss": 0.49068527221679686, "step": 441350 }, { "epoch": 2.6235354958360824, "grad_norm": 1.7456752061843872, "learning_rate": 2.8497521163719705e-05, "loss": 0.5058807373046875, "step": 441360 }, { "epoch": 2.623594937912751, "grad_norm": 1.2925629615783691, "learning_rate": 2.8494881005138585e-05, "loss": 0.4378800868988037, "step": 441370 }, { "epoch": 2.623654379989419, "grad_norm": 1.597128987312317, "learning_rate": 2.8492241236451355e-05, "loss": 0.46944437026977537, "step": 441380 }, { "epoch": 2.6237138220660876, "grad_norm": 1.2368053197860718, "learning_rate": 2.848960185767059e-05, "loss": 0.4710444450378418, "step": 441390 }, { "epoch": 2.623773264142756, "grad_norm": 1.4633814096450806, "learning_rate": 2.8486962868808914e-05, "loss": 0.47589707374572754, "step": 441400 }, { "epoch": 2.6238327062194244, "grad_norm": 1.3900527954101562, "learning_rate": 2.8484324269878988e-05, "loss": 0.410898494720459, "step": 441410 }, { "epoch": 2.623892148296093, "grad_norm": 1.3740642070770264, "learning_rate": 2.8481686060893402e-05, "loss": 0.5163021564483643, "step": 441420 }, { "epoch": 2.6239515903727613, "grad_norm": 1.3390703201293945, "learning_rate": 2.8479048241864787e-05, "loss": 0.4847861289978027, "step": 441430 }, { "epoch": 2.6240110324494297, "grad_norm": 1.5259617567062378, "learning_rate": 2.8476410812805787e-05, "loss": 0.5003029823303222, "step": 441440 }, { "epoch": 2.624070474526098, "grad_norm": 1.166172742843628, "learning_rate": 2.8473773773728986e-05, "loss": 0.487259578704834, "step": 441450 }, { "epoch": 2.6241299166027665, "grad_norm": 1.3549777269363403, "learning_rate": 2.847113712464699e-05, "loss": 0.49486989974975587, "step": 441460 }, { "epoch": 2.624189358679435, "grad_norm": 1.613731861114502, "learning_rate": 2.846850086557245e-05, "loss": 0.48511805534362795, "step": 441470 }, { "epoch": 2.6242488007561033, "grad_norm": 1.6009303331375122, "learning_rate": 2.8465864996517955e-05, "loss": 0.47977328300476074, "step": 441480 }, { "epoch": 2.6243082428327718, "grad_norm": 1.2023693323135376, "learning_rate": 2.846322951749612e-05, "loss": 0.4660656929016113, "step": 441490 }, { "epoch": 2.6243676849094397, "grad_norm": 1.4069451093673706, "learning_rate": 2.8460594428519538e-05, "loss": 0.45863871574401854, "step": 441500 }, { "epoch": 2.6244271269861086, "grad_norm": 1.4920146465301514, "learning_rate": 2.845795972960083e-05, "loss": 0.4819589614868164, "step": 441510 }, { "epoch": 2.6244865690627766, "grad_norm": 1.1457372903823853, "learning_rate": 2.8455325420752592e-05, "loss": 0.4347971439361572, "step": 441520 }, { "epoch": 2.6245460111394454, "grad_norm": 0.9405003786087036, "learning_rate": 2.8452691501987417e-05, "loss": 0.4650308609008789, "step": 441530 }, { "epoch": 2.6246054532161134, "grad_norm": 1.3834571838378906, "learning_rate": 2.8450057973317933e-05, "loss": 0.4005866527557373, "step": 441540 }, { "epoch": 2.624664895292782, "grad_norm": 1.0715653896331787, "learning_rate": 2.844742483475672e-05, "loss": 0.4040034770965576, "step": 441550 }, { "epoch": 2.62472433736945, "grad_norm": 1.241021990776062, "learning_rate": 2.8444792086316365e-05, "loss": 0.45902581214904786, "step": 441560 }, { "epoch": 2.6247837794461186, "grad_norm": 1.5728312730789185, "learning_rate": 2.844215972800948e-05, "loss": 0.5446294784545899, "step": 441570 }, { "epoch": 2.624843221522787, "grad_norm": 1.5145206451416016, "learning_rate": 2.8439527759848644e-05, "loss": 0.4644672393798828, "step": 441580 }, { "epoch": 2.6249026635994555, "grad_norm": 1.3471168279647827, "learning_rate": 2.8436896181846445e-05, "loss": 0.4794435977935791, "step": 441590 }, { "epoch": 2.624962105676124, "grad_norm": 1.3264151811599731, "learning_rate": 2.8434264994015493e-05, "loss": 0.4256855010986328, "step": 441600 }, { "epoch": 2.6250215477527923, "grad_norm": 1.4718081951141357, "learning_rate": 2.8431634196368363e-05, "loss": 0.49152331352233886, "step": 441610 }, { "epoch": 2.6250809898294607, "grad_norm": 1.1271361112594604, "learning_rate": 2.8429003788917634e-05, "loss": 0.47078766822814944, "step": 441620 }, { "epoch": 2.625140431906129, "grad_norm": 1.8808741569519043, "learning_rate": 2.8426373771675898e-05, "loss": 0.48167853355407714, "step": 441630 }, { "epoch": 2.6251998739827975, "grad_norm": 1.426209807395935, "learning_rate": 2.842374414465572e-05, "loss": 0.49698405265808104, "step": 441640 }, { "epoch": 2.625259316059466, "grad_norm": 1.5684064626693726, "learning_rate": 2.8421114907869706e-05, "loss": 0.45708365440368653, "step": 441650 }, { "epoch": 2.6253187581361344, "grad_norm": 1.297672986984253, "learning_rate": 2.84184860613304e-05, "loss": 0.4693293571472168, "step": 441660 }, { "epoch": 2.6253782002128028, "grad_norm": 1.411601185798645, "learning_rate": 2.84158576050504e-05, "loss": 0.5120939254760742, "step": 441670 }, { "epoch": 2.625437642289471, "grad_norm": 1.5827410221099854, "learning_rate": 2.8413229539042285e-05, "loss": 0.4657444953918457, "step": 441680 }, { "epoch": 2.625497084366139, "grad_norm": 1.7802674770355225, "learning_rate": 2.8410601863318614e-05, "loss": 0.4579660415649414, "step": 441690 }, { "epoch": 2.625556526442808, "grad_norm": 1.330285906791687, "learning_rate": 2.840797457789196e-05, "loss": 0.5021382808685303, "step": 441700 }, { "epoch": 2.625615968519476, "grad_norm": 1.183109164237976, "learning_rate": 2.840534768277489e-05, "loss": 0.49538450241088866, "step": 441710 }, { "epoch": 2.625675410596145, "grad_norm": 1.1570618152618408, "learning_rate": 2.840272117797995e-05, "loss": 0.4491624355316162, "step": 441720 }, { "epoch": 2.625734852672813, "grad_norm": 1.4252545833587646, "learning_rate": 2.8400095063519755e-05, "loss": 0.477704381942749, "step": 441730 }, { "epoch": 2.6257942947494812, "grad_norm": 2.2077581882476807, "learning_rate": 2.8397469339406823e-05, "loss": 0.4482569217681885, "step": 441740 }, { "epoch": 2.6258537368261496, "grad_norm": 1.6362708806991577, "learning_rate": 2.8394844005653743e-05, "loss": 0.4370288848876953, "step": 441750 }, { "epoch": 2.625913178902818, "grad_norm": 1.2886946201324463, "learning_rate": 2.8392219062273057e-05, "loss": 0.4538547515869141, "step": 441760 }, { "epoch": 2.6259726209794865, "grad_norm": 1.0970419645309448, "learning_rate": 2.8389594509277323e-05, "loss": 0.5134763717651367, "step": 441770 }, { "epoch": 2.626032063056155, "grad_norm": 1.6290314197540283, "learning_rate": 2.8386970346679092e-05, "loss": 0.4824080467224121, "step": 441780 }, { "epoch": 2.6260915051328233, "grad_norm": 1.3314656019210815, "learning_rate": 2.8384346574490916e-05, "loss": 0.4940680503845215, "step": 441790 }, { "epoch": 2.6261509472094917, "grad_norm": 1.2416881322860718, "learning_rate": 2.838172319272537e-05, "loss": 0.4397091865539551, "step": 441800 }, { "epoch": 2.62621038928616, "grad_norm": 1.2710167169570923, "learning_rate": 2.8379100201394983e-05, "loss": 0.5096785545349121, "step": 441810 }, { "epoch": 2.6262698313628285, "grad_norm": 1.432065725326538, "learning_rate": 2.8376477600512308e-05, "loss": 0.4341555595397949, "step": 441820 }, { "epoch": 2.626329273439497, "grad_norm": 1.410395622253418, "learning_rate": 2.8373855390089887e-05, "loss": 0.4883903980255127, "step": 441830 }, { "epoch": 2.6263887155161654, "grad_norm": 1.511198878288269, "learning_rate": 2.8371233570140276e-05, "loss": 0.48789167404174805, "step": 441840 }, { "epoch": 2.626448157592834, "grad_norm": 0.9925985932350159, "learning_rate": 2.8368612140676e-05, "loss": 0.46078667640686033, "step": 441850 }, { "epoch": 2.626507599669502, "grad_norm": 1.345757246017456, "learning_rate": 2.8365991101709586e-05, "loss": 0.4337013244628906, "step": 441860 }, { "epoch": 2.6265670417461706, "grad_norm": 1.368543267250061, "learning_rate": 2.8363370453253617e-05, "loss": 0.4744386672973633, "step": 441870 }, { "epoch": 2.6266264838228386, "grad_norm": 1.4003381729125977, "learning_rate": 2.8360750195320608e-05, "loss": 0.44622278213500977, "step": 441880 }, { "epoch": 2.6266859258995074, "grad_norm": 1.0830622911453247, "learning_rate": 2.8358130327923077e-05, "loss": 0.49181413650512695, "step": 441890 }, { "epoch": 2.6267453679761754, "grad_norm": 1.302594542503357, "learning_rate": 2.8355510851073563e-05, "loss": 0.5060966491699219, "step": 441900 }, { "epoch": 2.6268048100528443, "grad_norm": 1.3029905557632446, "learning_rate": 2.8352891764784618e-05, "loss": 0.4522997379302979, "step": 441910 }, { "epoch": 2.6268642521295122, "grad_norm": 1.5787827968597412, "learning_rate": 2.8350273069068735e-05, "loss": 0.48620095252990725, "step": 441920 }, { "epoch": 2.6269236942061807, "grad_norm": 1.249428153038025, "learning_rate": 2.8347654763938497e-05, "loss": 0.44000873565673826, "step": 441930 }, { "epoch": 2.626983136282849, "grad_norm": 1.419425129890442, "learning_rate": 2.834503684940638e-05, "loss": 0.45399723052978513, "step": 441940 }, { "epoch": 2.6270425783595175, "grad_norm": 1.2678077220916748, "learning_rate": 2.8342419325484902e-05, "loss": 0.4531074523925781, "step": 441950 }, { "epoch": 2.627102020436186, "grad_norm": 1.2937990427017212, "learning_rate": 2.8339802192186627e-05, "loss": 0.47298474311828614, "step": 441960 }, { "epoch": 2.6271614625128543, "grad_norm": 1.2602964639663696, "learning_rate": 2.833718544952404e-05, "loss": 0.48140363693237304, "step": 441970 }, { "epoch": 2.6272209045895227, "grad_norm": 1.3726540803909302, "learning_rate": 2.8334569097509684e-05, "loss": 0.4266031265258789, "step": 441980 }, { "epoch": 2.627280346666191, "grad_norm": 1.3512179851531982, "learning_rate": 2.8331953136156047e-05, "loss": 0.47069616317749025, "step": 441990 }, { "epoch": 2.6273397887428596, "grad_norm": 1.2252970933914185, "learning_rate": 2.8329337565475666e-05, "loss": 0.4188471794128418, "step": 442000 }, { "epoch": 2.627399230819528, "grad_norm": 0.9878740906715393, "learning_rate": 2.8326722385481036e-05, "loss": 0.4798792839050293, "step": 442010 }, { "epoch": 2.6274586728961964, "grad_norm": 1.6794838905334473, "learning_rate": 2.8324107596184663e-05, "loss": 0.4432101249694824, "step": 442020 }, { "epoch": 2.627518114972865, "grad_norm": 1.155341386795044, "learning_rate": 2.832149319759908e-05, "loss": 0.4739223480224609, "step": 442030 }, { "epoch": 2.627577557049533, "grad_norm": 1.3551722764968872, "learning_rate": 2.831887918973678e-05, "loss": 0.4066516876220703, "step": 442040 }, { "epoch": 2.6276369991262016, "grad_norm": 1.0121853351593018, "learning_rate": 2.8316265572610277e-05, "loss": 0.4774509906768799, "step": 442050 }, { "epoch": 2.62769644120287, "grad_norm": 1.4546020030975342, "learning_rate": 2.831365234623206e-05, "loss": 0.4758913516998291, "step": 442060 }, { "epoch": 2.627755883279538, "grad_norm": 1.229948878288269, "learning_rate": 2.8311039510614633e-05, "loss": 0.4659858703613281, "step": 442070 }, { "epoch": 2.627815325356207, "grad_norm": 1.3782713413238525, "learning_rate": 2.8308427065770494e-05, "loss": 0.46090235710144045, "step": 442080 }, { "epoch": 2.627874767432875, "grad_norm": 1.1773475408554077, "learning_rate": 2.8305815011712145e-05, "loss": 0.4387028217315674, "step": 442090 }, { "epoch": 2.6279342095095433, "grad_norm": 1.2692253589630127, "learning_rate": 2.830320334845208e-05, "loss": 0.441816520690918, "step": 442100 }, { "epoch": 2.6279936515862117, "grad_norm": 1.2567979097366333, "learning_rate": 2.8300592076002785e-05, "loss": 0.4738886833190918, "step": 442110 }, { "epoch": 2.62805309366288, "grad_norm": 1.210538387298584, "learning_rate": 2.8297981194376772e-05, "loss": 0.5003964900970459, "step": 442120 }, { "epoch": 2.6281125357395485, "grad_norm": 1.2876397371292114, "learning_rate": 2.8295370703586503e-05, "loss": 0.5229936122894288, "step": 442130 }, { "epoch": 2.628171977816217, "grad_norm": 1.4571235179901123, "learning_rate": 2.8292760603644496e-05, "loss": 0.43747291564941404, "step": 442140 }, { "epoch": 2.6282314198928853, "grad_norm": 1.4019817113876343, "learning_rate": 2.829015089456319e-05, "loss": 0.45308475494384765, "step": 442150 }, { "epoch": 2.6282908619695537, "grad_norm": 1.4346082210540771, "learning_rate": 2.828754157635512e-05, "loss": 0.4561800003051758, "step": 442160 }, { "epoch": 2.628350304046222, "grad_norm": 1.1520353555679321, "learning_rate": 2.8284932649032746e-05, "loss": 0.4707948207855225, "step": 442170 }, { "epoch": 2.6284097461228906, "grad_norm": 1.3387424945831299, "learning_rate": 2.8282324112608556e-05, "loss": 0.4889514446258545, "step": 442180 }, { "epoch": 2.628469188199559, "grad_norm": 1.2011010646820068, "learning_rate": 2.8279715967095016e-05, "loss": 0.5002695083618164, "step": 442190 }, { "epoch": 2.6285286302762274, "grad_norm": 1.5513209104537964, "learning_rate": 2.827710821250461e-05, "loss": 0.49515953063964846, "step": 442200 }, { "epoch": 2.628588072352896, "grad_norm": 1.07424795627594, "learning_rate": 2.8274500848849784e-05, "loss": 0.47702274322509763, "step": 442210 }, { "epoch": 2.6286475144295642, "grad_norm": 1.6375261545181274, "learning_rate": 2.8271893876143064e-05, "loss": 0.45785136222839357, "step": 442220 }, { "epoch": 2.6287069565062327, "grad_norm": 1.0858209133148193, "learning_rate": 2.82692872943969e-05, "loss": 0.5236046791076661, "step": 442230 }, { "epoch": 2.6287663985829006, "grad_norm": 1.2914282083511353, "learning_rate": 2.826668110362375e-05, "loss": 0.4425177574157715, "step": 442240 }, { "epoch": 2.6288258406595695, "grad_norm": 2.1221976280212402, "learning_rate": 2.826407530383608e-05, "loss": 0.5198031425476074, "step": 442250 }, { "epoch": 2.6288852827362374, "grad_norm": 1.2283450365066528, "learning_rate": 2.8261469895046365e-05, "loss": 0.4261444091796875, "step": 442260 }, { "epoch": 2.6289447248129063, "grad_norm": 1.2438722848892212, "learning_rate": 2.8258864877267076e-05, "loss": 0.45695981979370115, "step": 442270 }, { "epoch": 2.6290041668895743, "grad_norm": 1.1771622896194458, "learning_rate": 2.8256260250510648e-05, "loss": 0.48844289779663086, "step": 442280 }, { "epoch": 2.6290636089662427, "grad_norm": 1.3020004034042358, "learning_rate": 2.8253656014789564e-05, "loss": 0.4553974151611328, "step": 442290 }, { "epoch": 2.629123051042911, "grad_norm": 1.3946832418441772, "learning_rate": 2.8251052170116278e-05, "loss": 0.47350549697875977, "step": 442300 }, { "epoch": 2.6291824931195795, "grad_norm": 1.1437034606933594, "learning_rate": 2.8248448716503236e-05, "loss": 0.446857213973999, "step": 442310 }, { "epoch": 2.629241935196248, "grad_norm": 1.0793505907058716, "learning_rate": 2.8245845653962903e-05, "loss": 0.46138935089111327, "step": 442320 }, { "epoch": 2.6293013772729164, "grad_norm": 1.351100206375122, "learning_rate": 2.8243242982507735e-05, "loss": 0.5078234672546387, "step": 442330 }, { "epoch": 2.6293608193495848, "grad_norm": 1.5028891563415527, "learning_rate": 2.8240640702150162e-05, "loss": 0.49527435302734374, "step": 442340 }, { "epoch": 2.629420261426253, "grad_norm": 1.0832197666168213, "learning_rate": 2.823803881290263e-05, "loss": 0.4318744659423828, "step": 442350 }, { "epoch": 2.6294797035029216, "grad_norm": 1.0273191928863525, "learning_rate": 2.8235437314777625e-05, "loss": 0.4366426467895508, "step": 442360 }, { "epoch": 2.62953914557959, "grad_norm": 1.1298478841781616, "learning_rate": 2.8232836207787577e-05, "loss": 0.43666563034057615, "step": 442370 }, { "epoch": 2.6295985876562584, "grad_norm": 1.2815289497375488, "learning_rate": 2.823023549194489e-05, "loss": 0.4816624641418457, "step": 442380 }, { "epoch": 2.629658029732927, "grad_norm": 0.937355101108551, "learning_rate": 2.822763516726204e-05, "loss": 0.4467477798461914, "step": 442390 }, { "epoch": 2.6297174718095953, "grad_norm": 1.352386474609375, "learning_rate": 2.822503523375147e-05, "loss": 0.4580399513244629, "step": 442400 }, { "epoch": 2.6297769138862637, "grad_norm": 1.2635841369628906, "learning_rate": 2.8222435691425587e-05, "loss": 0.4670427322387695, "step": 442410 }, { "epoch": 2.629836355962932, "grad_norm": 1.0405069589614868, "learning_rate": 2.821983654029686e-05, "loss": 0.4943974494934082, "step": 442420 }, { "epoch": 2.6298957980396, "grad_norm": 1.4864171743392944, "learning_rate": 2.8217237780377735e-05, "loss": 0.5213659286499024, "step": 442430 }, { "epoch": 2.629955240116269, "grad_norm": 1.5609068870544434, "learning_rate": 2.821463941168057e-05, "loss": 0.46233410835266114, "step": 442440 }, { "epoch": 2.630014682192937, "grad_norm": 1.5520398616790771, "learning_rate": 2.8212041434217873e-05, "loss": 0.46413488388061525, "step": 442450 }, { "epoch": 2.6300741242696057, "grad_norm": 1.4503777027130127, "learning_rate": 2.8209443848002037e-05, "loss": 0.48569765090942385, "step": 442460 }, { "epoch": 2.6301335663462737, "grad_norm": 1.5578256845474243, "learning_rate": 2.8206846653045487e-05, "loss": 0.43721923828125, "step": 442470 }, { "epoch": 2.630193008422942, "grad_norm": 1.238966941833496, "learning_rate": 2.8204249849360642e-05, "loss": 0.5025968074798584, "step": 442480 }, { "epoch": 2.6302524504996105, "grad_norm": 1.2362905740737915, "learning_rate": 2.8201653436959963e-05, "loss": 0.43738641738891604, "step": 442490 }, { "epoch": 2.630311892576279, "grad_norm": 1.0995742082595825, "learning_rate": 2.8199057415855828e-05, "loss": 0.4672494888305664, "step": 442500 }, { "epoch": 2.6303713346529474, "grad_norm": 1.4098881483078003, "learning_rate": 2.8196461786060653e-05, "loss": 0.46607203483581544, "step": 442510 }, { "epoch": 2.630430776729616, "grad_norm": 1.273480772972107, "learning_rate": 2.819386654758689e-05, "loss": 0.49338717460632325, "step": 442520 }, { "epoch": 2.630490218806284, "grad_norm": 1.3128185272216797, "learning_rate": 2.819127170044693e-05, "loss": 0.4269547462463379, "step": 442530 }, { "epoch": 2.6305496608829526, "grad_norm": 1.3982195854187012, "learning_rate": 2.8188677244653195e-05, "loss": 0.4776193618774414, "step": 442540 }, { "epoch": 2.630609102959621, "grad_norm": 1.5646237134933472, "learning_rate": 2.8186083180218085e-05, "loss": 0.4584689140319824, "step": 442550 }, { "epoch": 2.6306685450362894, "grad_norm": 1.630715250968933, "learning_rate": 2.8183489507154027e-05, "loss": 0.5344974517822265, "step": 442560 }, { "epoch": 2.630727987112958, "grad_norm": 1.2676304578781128, "learning_rate": 2.818089622547339e-05, "loss": 0.5435374259948731, "step": 442570 }, { "epoch": 2.6307874291896263, "grad_norm": 1.264165997505188, "learning_rate": 2.8178303335188626e-05, "loss": 0.41968188285827634, "step": 442580 }, { "epoch": 2.6308468712662947, "grad_norm": 1.7126070261001587, "learning_rate": 2.8175710836312125e-05, "loss": 0.45519680976867677, "step": 442590 }, { "epoch": 2.630906313342963, "grad_norm": 1.5239295959472656, "learning_rate": 2.8173118728856275e-05, "loss": 0.4969011306762695, "step": 442600 }, { "epoch": 2.6309657554196315, "grad_norm": 1.3367373943328857, "learning_rate": 2.8170527012833492e-05, "loss": 0.4588154315948486, "step": 442610 }, { "epoch": 2.6310251974962995, "grad_norm": 1.267227292060852, "learning_rate": 2.8167935688256155e-05, "loss": 0.46920137405395507, "step": 442620 }, { "epoch": 2.6310846395729683, "grad_norm": 1.3458372354507446, "learning_rate": 2.8165344755136686e-05, "loss": 0.41467647552490233, "step": 442630 }, { "epoch": 2.6311440816496363, "grad_norm": 1.1884195804595947, "learning_rate": 2.816275421348743e-05, "loss": 0.4526791572570801, "step": 442640 }, { "epoch": 2.631203523726305, "grad_norm": 1.1248323917388916, "learning_rate": 2.8160164063320842e-05, "loss": 0.43013272285461424, "step": 442650 }, { "epoch": 2.631262965802973, "grad_norm": 1.5944997072219849, "learning_rate": 2.8157574304649282e-05, "loss": 0.4676517486572266, "step": 442660 }, { "epoch": 2.6313224078796416, "grad_norm": 1.1807130575180054, "learning_rate": 2.8154984937485136e-05, "loss": 0.47903032302856446, "step": 442670 }, { "epoch": 2.63138184995631, "grad_norm": 1.3708021640777588, "learning_rate": 2.8152395961840794e-05, "loss": 0.4528837203979492, "step": 442680 }, { "epoch": 2.6314412920329784, "grad_norm": 1.0659632682800293, "learning_rate": 2.8149807377728643e-05, "loss": 0.46565828323364256, "step": 442690 }, { "epoch": 2.631500734109647, "grad_norm": 1.610795021057129, "learning_rate": 2.8147219185161066e-05, "loss": 0.5162763595581055, "step": 442700 }, { "epoch": 2.631560176186315, "grad_norm": 1.6118429899215698, "learning_rate": 2.814463138415042e-05, "loss": 0.49968743324279785, "step": 442710 }, { "epoch": 2.6316196182629836, "grad_norm": 1.2084640264511108, "learning_rate": 2.814204397470913e-05, "loss": 0.4607353210449219, "step": 442720 }, { "epoch": 2.631679060339652, "grad_norm": 1.1295206546783447, "learning_rate": 2.8139456956849553e-05, "loss": 0.4041736602783203, "step": 442730 }, { "epoch": 2.6317385024163205, "grad_norm": 1.1714962720870972, "learning_rate": 2.813687033058406e-05, "loss": 0.5002506732940674, "step": 442740 }, { "epoch": 2.631797944492989, "grad_norm": 0.885443389415741, "learning_rate": 2.8134284095925016e-05, "loss": 0.4908872127532959, "step": 442750 }, { "epoch": 2.6318573865696573, "grad_norm": 1.6411844491958618, "learning_rate": 2.8131698252884815e-05, "loss": 0.4582479000091553, "step": 442760 }, { "epoch": 2.6319168286463257, "grad_norm": 1.5434058904647827, "learning_rate": 2.812911280147579e-05, "loss": 0.5255121231079102, "step": 442770 }, { "epoch": 2.631976270722994, "grad_norm": 1.290947675704956, "learning_rate": 2.8126527741710353e-05, "loss": 0.5223296165466309, "step": 442780 }, { "epoch": 2.6320357127996625, "grad_norm": 1.2531217336654663, "learning_rate": 2.8123943073600856e-05, "loss": 0.49266648292541504, "step": 442790 }, { "epoch": 2.632095154876331, "grad_norm": 1.1265631914138794, "learning_rate": 2.8121358797159654e-05, "loss": 0.46198306083679197, "step": 442800 }, { "epoch": 2.632154596952999, "grad_norm": 1.6810263395309448, "learning_rate": 2.8118774912399115e-05, "loss": 0.4210407257080078, "step": 442810 }, { "epoch": 2.6322140390296678, "grad_norm": 1.1648468971252441, "learning_rate": 2.8116191419331588e-05, "loss": 0.5140804290771485, "step": 442820 }, { "epoch": 2.6322734811063357, "grad_norm": 1.2562885284423828, "learning_rate": 2.8113608317969453e-05, "loss": 0.4746088027954102, "step": 442830 }, { "epoch": 2.632332923183004, "grad_norm": 1.248366117477417, "learning_rate": 2.811102560832503e-05, "loss": 0.4421885013580322, "step": 442840 }, { "epoch": 2.6323923652596726, "grad_norm": 1.276085376739502, "learning_rate": 2.8108443290410726e-05, "loss": 0.4396542549133301, "step": 442850 }, { "epoch": 2.632451807336341, "grad_norm": 1.4322428703308105, "learning_rate": 2.8105861364238877e-05, "loss": 0.5682510375976563, "step": 442860 }, { "epoch": 2.6325112494130094, "grad_norm": 1.0853006839752197, "learning_rate": 2.8103279829821795e-05, "loss": 0.4779543876647949, "step": 442870 }, { "epoch": 2.632570691489678, "grad_norm": 1.2060528993606567, "learning_rate": 2.8100698687171868e-05, "loss": 0.42046527862548827, "step": 442880 }, { "epoch": 2.6326301335663462, "grad_norm": 1.2768681049346924, "learning_rate": 2.8098117936301432e-05, "loss": 0.47731924057006836, "step": 442890 }, { "epoch": 2.6326895756430146, "grad_norm": 1.3234163522720337, "learning_rate": 2.8095537577222823e-05, "loss": 0.4950246810913086, "step": 442900 }, { "epoch": 2.632749017719683, "grad_norm": 1.504320502281189, "learning_rate": 2.8092957609948418e-05, "loss": 0.4933826446533203, "step": 442910 }, { "epoch": 2.6328084597963515, "grad_norm": 1.1404564380645752, "learning_rate": 2.809037803449054e-05, "loss": 0.43941521644592285, "step": 442920 }, { "epoch": 2.63286790187302, "grad_norm": 1.333510398864746, "learning_rate": 2.8087798850861496e-05, "loss": 0.48106813430786133, "step": 442930 }, { "epoch": 2.6329273439496883, "grad_norm": 1.0303913354873657, "learning_rate": 2.8085220059073675e-05, "loss": 0.42331690788269044, "step": 442940 }, { "epoch": 2.6329867860263567, "grad_norm": 1.2707493305206299, "learning_rate": 2.8082641659139386e-05, "loss": 0.48960514068603517, "step": 442950 }, { "epoch": 2.633046228103025, "grad_norm": 1.3006081581115723, "learning_rate": 2.8080063651070975e-05, "loss": 0.4325739860534668, "step": 442960 }, { "epoch": 2.6331056701796935, "grad_norm": 1.5084989070892334, "learning_rate": 2.807748603488074e-05, "loss": 0.48184828758239745, "step": 442970 }, { "epoch": 2.6331651122563615, "grad_norm": 0.9650675058364868, "learning_rate": 2.807490881058108e-05, "loss": 0.4553380489349365, "step": 442980 }, { "epoch": 2.6332245543330304, "grad_norm": 1.4990330934524536, "learning_rate": 2.807233197818427e-05, "loss": 0.5051019668579102, "step": 442990 }, { "epoch": 2.6332839964096983, "grad_norm": 1.1619478464126587, "learning_rate": 2.8069755537702617e-05, "loss": 0.47751617431640625, "step": 443000 }, { "epoch": 2.633343438486367, "grad_norm": 1.370875597000122, "learning_rate": 2.806717948914851e-05, "loss": 0.48729476928710935, "step": 443010 }, { "epoch": 2.633402880563035, "grad_norm": 1.292359471321106, "learning_rate": 2.8064603832534237e-05, "loss": 0.4647542953491211, "step": 443020 }, { "epoch": 2.6334623226397036, "grad_norm": 1.1091079711914062, "learning_rate": 2.806202856787211e-05, "loss": 0.48210897445678713, "step": 443030 }, { "epoch": 2.633521764716372, "grad_norm": 1.2502219676971436, "learning_rate": 2.805945369517448e-05, "loss": 0.48387703895568845, "step": 443040 }, { "epoch": 2.6335812067930404, "grad_norm": 1.4050352573394775, "learning_rate": 2.8056879214453646e-05, "loss": 0.5135936260223388, "step": 443050 }, { "epoch": 2.633640648869709, "grad_norm": 1.3401397466659546, "learning_rate": 2.8054305125721885e-05, "loss": 0.4630584239959717, "step": 443060 }, { "epoch": 2.6337000909463772, "grad_norm": 1.469306468963623, "learning_rate": 2.8051731428991585e-05, "loss": 0.4673458099365234, "step": 443070 }, { "epoch": 2.6337595330230457, "grad_norm": 1.3607765436172485, "learning_rate": 2.804915812427501e-05, "loss": 0.4804501533508301, "step": 443080 }, { "epoch": 2.633818975099714, "grad_norm": 1.5480180978775024, "learning_rate": 2.8046585211584486e-05, "loss": 0.5104880332946777, "step": 443090 }, { "epoch": 2.6338784171763825, "grad_norm": 1.1925373077392578, "learning_rate": 2.8044012690932308e-05, "loss": 0.44310760498046875, "step": 443100 }, { "epoch": 2.633937859253051, "grad_norm": 1.5050315856933594, "learning_rate": 2.80414405623308e-05, "loss": 0.5103375911712646, "step": 443110 }, { "epoch": 2.6339973013297193, "grad_norm": 1.2925231456756592, "learning_rate": 2.8038868825792254e-05, "loss": 0.4681065559387207, "step": 443120 }, { "epoch": 2.6340567434063877, "grad_norm": 1.0411900281906128, "learning_rate": 2.803629748132895e-05, "loss": 0.37853312492370605, "step": 443130 }, { "epoch": 2.634116185483056, "grad_norm": 1.4702540636062622, "learning_rate": 2.803372652895324e-05, "loss": 0.47509613037109377, "step": 443140 }, { "epoch": 2.6341756275597246, "grad_norm": 1.465708613395691, "learning_rate": 2.8031155968677382e-05, "loss": 0.4771301746368408, "step": 443150 }, { "epoch": 2.634235069636393, "grad_norm": 1.0609945058822632, "learning_rate": 2.8028585800513695e-05, "loss": 0.46594438552856443, "step": 443160 }, { "epoch": 2.634294511713061, "grad_norm": 1.144282579421997, "learning_rate": 2.802601602447446e-05, "loss": 0.44155254364013674, "step": 443170 }, { "epoch": 2.63435395378973, "grad_norm": 1.3576117753982544, "learning_rate": 2.8023446640571983e-05, "loss": 0.4978611469268799, "step": 443180 }, { "epoch": 2.6344133958663978, "grad_norm": 1.2142527103424072, "learning_rate": 2.8020877648818545e-05, "loss": 0.45236663818359374, "step": 443190 }, { "epoch": 2.6344728379430666, "grad_norm": 1.0749030113220215, "learning_rate": 2.801830904922641e-05, "loss": 0.49570350646972655, "step": 443200 }, { "epoch": 2.6345322800197346, "grad_norm": 1.0269296169281006, "learning_rate": 2.8015740841807926e-05, "loss": 0.41872668266296387, "step": 443210 }, { "epoch": 2.634591722096403, "grad_norm": 1.280810832977295, "learning_rate": 2.8013173026575334e-05, "loss": 0.47273502349853513, "step": 443220 }, { "epoch": 2.6346511641730714, "grad_norm": 1.3207076787948608, "learning_rate": 2.8010605603540936e-05, "loss": 0.43081417083740237, "step": 443230 }, { "epoch": 2.63471060624974, "grad_norm": 1.3524019718170166, "learning_rate": 2.8008038572716998e-05, "loss": 0.5279928207397461, "step": 443240 }, { "epoch": 2.6347700483264083, "grad_norm": 1.4200608730316162, "learning_rate": 2.8005471934115814e-05, "loss": 0.5130743980407715, "step": 443250 }, { "epoch": 2.6348294904030767, "grad_norm": 1.3104932308197021, "learning_rate": 2.8002905687749638e-05, "loss": 0.4428821563720703, "step": 443260 }, { "epoch": 2.634888932479745, "grad_norm": 1.1946991682052612, "learning_rate": 2.800033983363078e-05, "loss": 0.4340709686279297, "step": 443270 }, { "epoch": 2.6349483745564135, "grad_norm": 0.9645527005195618, "learning_rate": 2.7997774371771502e-05, "loss": 0.47696704864501954, "step": 443280 }, { "epoch": 2.635007816633082, "grad_norm": 1.137711763381958, "learning_rate": 2.7995209302184066e-05, "loss": 0.45554018020629883, "step": 443290 }, { "epoch": 2.6350672587097503, "grad_norm": 1.196755290031433, "learning_rate": 2.799264462488075e-05, "loss": 0.501432228088379, "step": 443300 }, { "epoch": 2.6351267007864188, "grad_norm": 1.2192063331604004, "learning_rate": 2.7990080339873827e-05, "loss": 0.4728226661682129, "step": 443310 }, { "epoch": 2.635186142863087, "grad_norm": 1.2783632278442383, "learning_rate": 2.7987516447175554e-05, "loss": 0.4211104869842529, "step": 443320 }, { "epoch": 2.6352455849397556, "grad_norm": 1.1474157571792603, "learning_rate": 2.798495294679818e-05, "loss": 0.45983114242553713, "step": 443330 }, { "epoch": 2.635305027016424, "grad_norm": 1.255810022354126, "learning_rate": 2.7982389838754015e-05, "loss": 0.5191502094268798, "step": 443340 }, { "epoch": 2.6353644690930924, "grad_norm": 1.3603525161743164, "learning_rate": 2.7979827123055303e-05, "loss": 0.4477283000946045, "step": 443350 }, { "epoch": 2.6354239111697604, "grad_norm": 1.4864909648895264, "learning_rate": 2.797726479971427e-05, "loss": 0.5048898696899414, "step": 443360 }, { "epoch": 2.6354833532464292, "grad_norm": 1.3332637548446655, "learning_rate": 2.7974702868743202e-05, "loss": 0.4547703742980957, "step": 443370 }, { "epoch": 2.635542795323097, "grad_norm": 1.4073957204818726, "learning_rate": 2.797214133015435e-05, "loss": 0.4752394676208496, "step": 443380 }, { "epoch": 2.635602237399766, "grad_norm": 1.4715168476104736, "learning_rate": 2.7969580183959953e-05, "loss": 0.4662971019744873, "step": 443390 }, { "epoch": 2.635661679476434, "grad_norm": 1.3029264211654663, "learning_rate": 2.7967019430172296e-05, "loss": 0.4495685577392578, "step": 443400 }, { "epoch": 2.6357211215531025, "grad_norm": 0.8826066255569458, "learning_rate": 2.7964459068803627e-05, "loss": 0.45498409271240237, "step": 443410 }, { "epoch": 2.635780563629771, "grad_norm": 1.4381440877914429, "learning_rate": 2.796189909986614e-05, "loss": 0.46111345291137695, "step": 443420 }, { "epoch": 2.6358400057064393, "grad_norm": 1.2959167957305908, "learning_rate": 2.795933952337213e-05, "loss": 0.4402184963226318, "step": 443430 }, { "epoch": 2.6358994477831077, "grad_norm": 1.2388763427734375, "learning_rate": 2.7956780339333838e-05, "loss": 0.44356374740600585, "step": 443440 }, { "epoch": 2.635958889859776, "grad_norm": 1.3891409635543823, "learning_rate": 2.7954221547763486e-05, "loss": 0.45478367805480957, "step": 443450 }, { "epoch": 2.6360183319364445, "grad_norm": 1.0722862482070923, "learning_rate": 2.7951663148673318e-05, "loss": 0.48206539154052735, "step": 443460 }, { "epoch": 2.636077774013113, "grad_norm": 1.2258613109588623, "learning_rate": 2.7949105142075604e-05, "loss": 0.44654216766357424, "step": 443470 }, { "epoch": 2.6361372160897814, "grad_norm": 1.56388258934021, "learning_rate": 2.7946547527982554e-05, "loss": 0.518186378479004, "step": 443480 }, { "epoch": 2.6361966581664498, "grad_norm": 1.1850733757019043, "learning_rate": 2.794399030640638e-05, "loss": 0.4024150848388672, "step": 443490 }, { "epoch": 2.636256100243118, "grad_norm": 0.9487664699554443, "learning_rate": 2.7941433477359356e-05, "loss": 0.4656955718994141, "step": 443500 }, { "epoch": 2.6363155423197866, "grad_norm": 1.2555724382400513, "learning_rate": 2.79388770408537e-05, "loss": 0.47624969482421875, "step": 443510 }, { "epoch": 2.636374984396455, "grad_norm": 1.9964625835418701, "learning_rate": 2.7936320996901617e-05, "loss": 0.46613545417785646, "step": 443520 }, { "epoch": 2.6364344264731234, "grad_norm": 1.3392353057861328, "learning_rate": 2.793376534551539e-05, "loss": 0.4960965156555176, "step": 443530 }, { "epoch": 2.636493868549792, "grad_norm": 1.4285989999771118, "learning_rate": 2.7931210086707194e-05, "loss": 0.49538373947143555, "step": 443540 }, { "epoch": 2.63655331062646, "grad_norm": 1.3925600051879883, "learning_rate": 2.792865522048927e-05, "loss": 0.4878748893737793, "step": 443550 }, { "epoch": 2.6366127527031287, "grad_norm": 1.492946743965149, "learning_rate": 2.7926100746873822e-05, "loss": 0.5180578231811523, "step": 443560 }, { "epoch": 2.6366721947797966, "grad_norm": 0.9335430264472961, "learning_rate": 2.7923546665873102e-05, "loss": 0.4358969688415527, "step": 443570 }, { "epoch": 2.636731636856465, "grad_norm": 1.389122486114502, "learning_rate": 2.7920992977499305e-05, "loss": 0.45314846038818357, "step": 443580 }, { "epoch": 2.6367910789331335, "grad_norm": 1.3747538328170776, "learning_rate": 2.7918439681764663e-05, "loss": 0.4659606456756592, "step": 443590 }, { "epoch": 2.636850521009802, "grad_norm": 1.13884437084198, "learning_rate": 2.7915886778681383e-05, "loss": 0.4519219398498535, "step": 443600 }, { "epoch": 2.6369099630864703, "grad_norm": 1.2958775758743286, "learning_rate": 2.7913334268261666e-05, "loss": 0.42723855972290037, "step": 443610 }, { "epoch": 2.6369694051631387, "grad_norm": 1.2857035398483276, "learning_rate": 2.7910782150517715e-05, "loss": 0.48075113296508787, "step": 443620 }, { "epoch": 2.637028847239807, "grad_norm": 1.2787752151489258, "learning_rate": 2.7908230425461783e-05, "loss": 0.4719973564147949, "step": 443630 }, { "epoch": 2.6370882893164755, "grad_norm": 1.497248888015747, "learning_rate": 2.790567909310604e-05, "loss": 0.43134298324584963, "step": 443640 }, { "epoch": 2.637147731393144, "grad_norm": 1.373368740081787, "learning_rate": 2.79031281534627e-05, "loss": 0.5286042213439941, "step": 443650 }, { "epoch": 2.6372071734698124, "grad_norm": 1.3555121421813965, "learning_rate": 2.7900577606543975e-05, "loss": 0.44754948616027834, "step": 443660 }, { "epoch": 2.637266615546481, "grad_norm": 1.5022093057632446, "learning_rate": 2.7898027452362042e-05, "loss": 0.5188441276550293, "step": 443670 }, { "epoch": 2.637326057623149, "grad_norm": 1.3687574863433838, "learning_rate": 2.7895477690929117e-05, "loss": 0.4969182014465332, "step": 443680 }, { "epoch": 2.6373854996998176, "grad_norm": 1.3136337995529175, "learning_rate": 2.7892928322257383e-05, "loss": 0.4870578765869141, "step": 443690 }, { "epoch": 2.637444941776486, "grad_norm": 1.4266011714935303, "learning_rate": 2.789037934635907e-05, "loss": 0.47849411964416505, "step": 443700 }, { "epoch": 2.6375043838531544, "grad_norm": 1.3064903020858765, "learning_rate": 2.7887830763246335e-05, "loss": 0.5018668174743652, "step": 443710 }, { "epoch": 2.6375638259298224, "grad_norm": 1.4284225702285767, "learning_rate": 2.788528257293139e-05, "loss": 0.43345346450805666, "step": 443720 }, { "epoch": 2.6376232680064913, "grad_norm": 1.9050331115722656, "learning_rate": 2.788273477542641e-05, "loss": 0.4736458778381348, "step": 443730 }, { "epoch": 2.6376827100831592, "grad_norm": 1.0815813541412354, "learning_rate": 2.788018737074361e-05, "loss": 0.4551693916320801, "step": 443740 }, { "epoch": 2.637742152159828, "grad_norm": 1.215766429901123, "learning_rate": 2.787764035889512e-05, "loss": 0.46832857131958006, "step": 443750 }, { "epoch": 2.637801594236496, "grad_norm": 1.702092170715332, "learning_rate": 2.787509373989318e-05, "loss": 0.5039790630340576, "step": 443760 }, { "epoch": 2.6378610363131645, "grad_norm": 1.2314997911453247, "learning_rate": 2.7872547513749965e-05, "loss": 0.5226411342620849, "step": 443770 }, { "epoch": 2.637920478389833, "grad_norm": 1.4694126844406128, "learning_rate": 2.7870001680477632e-05, "loss": 0.4914276599884033, "step": 443780 }, { "epoch": 2.6379799204665013, "grad_norm": 1.6464595794677734, "learning_rate": 2.7867456240088375e-05, "loss": 0.47363958358764646, "step": 443790 }, { "epoch": 2.6380393625431697, "grad_norm": 1.364680528640747, "learning_rate": 2.786491119259437e-05, "loss": 0.4782416820526123, "step": 443800 }, { "epoch": 2.638098804619838, "grad_norm": 1.3756763935089111, "learning_rate": 2.786236653800778e-05, "loss": 0.4539663791656494, "step": 443810 }, { "epoch": 2.6381582466965066, "grad_norm": 1.5917707681655884, "learning_rate": 2.785982227634077e-05, "loss": 0.48459625244140625, "step": 443820 }, { "epoch": 2.638217688773175, "grad_norm": 1.2925258874893188, "learning_rate": 2.7857278407605547e-05, "loss": 0.45610485076904295, "step": 443830 }, { "epoch": 2.6382771308498434, "grad_norm": 1.0846205949783325, "learning_rate": 2.7854734931814253e-05, "loss": 0.4701242446899414, "step": 443840 }, { "epoch": 2.638336572926512, "grad_norm": 1.3026434183120728, "learning_rate": 2.785219184897907e-05, "loss": 0.5013586997985839, "step": 443850 }, { "epoch": 2.63839601500318, "grad_norm": 1.1625272035598755, "learning_rate": 2.784964915911215e-05, "loss": 0.47248592376708987, "step": 443860 }, { "epoch": 2.6384554570798486, "grad_norm": 1.219061017036438, "learning_rate": 2.784710686222567e-05, "loss": 0.4510049343109131, "step": 443870 }, { "epoch": 2.638514899156517, "grad_norm": 1.4290398359298706, "learning_rate": 2.7844564958331758e-05, "loss": 0.47283029556274414, "step": 443880 }, { "epoch": 2.6385743412331855, "grad_norm": 1.2492517232894897, "learning_rate": 2.784202344744262e-05, "loss": 0.38074891567230223, "step": 443890 }, { "epoch": 2.638633783309854, "grad_norm": 1.373744249343872, "learning_rate": 2.7839482329570383e-05, "loss": 0.5056497573852539, "step": 443900 }, { "epoch": 2.638693225386522, "grad_norm": 1.1022387742996216, "learning_rate": 2.783694160472722e-05, "loss": 0.4570937633514404, "step": 443910 }, { "epoch": 2.6387526674631907, "grad_norm": 1.3461028337478638, "learning_rate": 2.7834401272925276e-05, "loss": 0.4271514415740967, "step": 443920 }, { "epoch": 2.6388121095398587, "grad_norm": 1.5834163427352905, "learning_rate": 2.78318613341767e-05, "loss": 0.47813730239868163, "step": 443930 }, { "epoch": 2.6388715516165275, "grad_norm": 1.5217251777648926, "learning_rate": 2.7829321788493645e-05, "loss": 0.49171934127807615, "step": 443940 }, { "epoch": 2.6389309936931955, "grad_norm": 1.3843395709991455, "learning_rate": 2.782678263588825e-05, "loss": 0.4645557403564453, "step": 443950 }, { "epoch": 2.638990435769864, "grad_norm": 1.3353694677352905, "learning_rate": 2.7824243876372706e-05, "loss": 0.4823476314544678, "step": 443960 }, { "epoch": 2.6390498778465323, "grad_norm": 1.2878133058547974, "learning_rate": 2.7821705509959105e-05, "loss": 0.4715733528137207, "step": 443970 }, { "epoch": 2.6391093199232007, "grad_norm": 1.255039930343628, "learning_rate": 2.7819167536659597e-05, "loss": 0.4984927177429199, "step": 443980 }, { "epoch": 2.639168761999869, "grad_norm": 1.1909170150756836, "learning_rate": 2.7816629956486345e-05, "loss": 0.5042158603668213, "step": 443990 }, { "epoch": 2.6392282040765376, "grad_norm": 1.58523690700531, "learning_rate": 2.781409276945148e-05, "loss": 0.45774002075195314, "step": 444000 }, { "epoch": 2.639287646153206, "grad_norm": 1.2494213581085205, "learning_rate": 2.781155597556712e-05, "loss": 0.5133839130401612, "step": 444010 }, { "epoch": 2.6393470882298744, "grad_norm": 1.2194947004318237, "learning_rate": 2.7809019574845445e-05, "loss": 0.42369809150695803, "step": 444020 }, { "epoch": 2.639406530306543, "grad_norm": 1.4802881479263306, "learning_rate": 2.7806483567298557e-05, "loss": 0.5246414184570313, "step": 444030 }, { "epoch": 2.6394659723832112, "grad_norm": 1.3671928644180298, "learning_rate": 2.780394795293858e-05, "loss": 0.4697597503662109, "step": 444040 }, { "epoch": 2.6395254144598796, "grad_norm": 1.3655952215194702, "learning_rate": 2.7801412731777632e-05, "loss": 0.45333185195922854, "step": 444050 }, { "epoch": 2.639584856536548, "grad_norm": 1.3610624074935913, "learning_rate": 2.779887790382789e-05, "loss": 0.4485684871673584, "step": 444060 }, { "epoch": 2.6396442986132165, "grad_norm": 1.2285408973693848, "learning_rate": 2.779634346910145e-05, "loss": 0.469389533996582, "step": 444070 }, { "epoch": 2.639703740689885, "grad_norm": 1.3338913917541504, "learning_rate": 2.7793809427610434e-05, "loss": 0.45500974655151366, "step": 444080 }, { "epoch": 2.6397631827665533, "grad_norm": 1.2020844221115112, "learning_rate": 2.7791275779366976e-05, "loss": 0.45737361907958984, "step": 444090 }, { "epoch": 2.6398226248432213, "grad_norm": 1.7317488193511963, "learning_rate": 2.7788742524383182e-05, "loss": 0.48037357330322267, "step": 444100 }, { "epoch": 2.63988206691989, "grad_norm": 1.2798207998275757, "learning_rate": 2.7786209662671164e-05, "loss": 0.44505157470703127, "step": 444110 }, { "epoch": 2.639941508996558, "grad_norm": 0.9676569104194641, "learning_rate": 2.7783677194243063e-05, "loss": 0.4374549388885498, "step": 444120 }, { "epoch": 2.640000951073227, "grad_norm": 1.5601541996002197, "learning_rate": 2.7781145119110986e-05, "loss": 0.4532002449035645, "step": 444130 }, { "epoch": 2.640060393149895, "grad_norm": 1.2558610439300537, "learning_rate": 2.7778613437287038e-05, "loss": 0.5186617374420166, "step": 444140 }, { "epoch": 2.6401198352265633, "grad_norm": 1.544970989227295, "learning_rate": 2.7776082148783333e-05, "loss": 0.5063933372497559, "step": 444150 }, { "epoch": 2.6401792773032318, "grad_norm": 1.2379151582717896, "learning_rate": 2.7773551253611985e-05, "loss": 0.5137473583221436, "step": 444160 }, { "epoch": 2.6402387193799, "grad_norm": 1.637893557548523, "learning_rate": 2.7771020751785092e-05, "loss": 0.4618563652038574, "step": 444170 }, { "epoch": 2.6402981614565686, "grad_norm": 1.2844271659851074, "learning_rate": 2.776849064331475e-05, "loss": 0.46038131713867186, "step": 444180 }, { "epoch": 2.640357603533237, "grad_norm": 1.3653137683868408, "learning_rate": 2.7765960928213085e-05, "loss": 0.44948744773864746, "step": 444190 }, { "epoch": 2.6404170456099054, "grad_norm": 1.325864315032959, "learning_rate": 2.7763431606492196e-05, "loss": 0.4527937412261963, "step": 444200 }, { "epoch": 2.640476487686574, "grad_norm": 1.8195011615753174, "learning_rate": 2.776090267816417e-05, "loss": 0.4779684066772461, "step": 444210 }, { "epoch": 2.6405359297632423, "grad_norm": 1.5466434955596924, "learning_rate": 2.7758374143241116e-05, "loss": 0.4766982078552246, "step": 444220 }, { "epoch": 2.6405953718399107, "grad_norm": 1.266424536705017, "learning_rate": 2.7755846001735115e-05, "loss": 0.44869608879089357, "step": 444230 }, { "epoch": 2.640654813916579, "grad_norm": 1.38738214969635, "learning_rate": 2.775331825365825e-05, "loss": 0.5024127006530762, "step": 444240 }, { "epoch": 2.6407142559932475, "grad_norm": 1.5402027368545532, "learning_rate": 2.7750790899022662e-05, "loss": 0.4604046821594238, "step": 444250 }, { "epoch": 2.640773698069916, "grad_norm": 1.0592377185821533, "learning_rate": 2.7748263937840407e-05, "loss": 0.4682034492492676, "step": 444260 }, { "epoch": 2.6408331401465843, "grad_norm": 1.493894100189209, "learning_rate": 2.774573737012357e-05, "loss": 0.4995582580566406, "step": 444270 }, { "epoch": 2.6408925822232527, "grad_norm": 1.272767186164856, "learning_rate": 2.774321119588425e-05, "loss": 0.4802975654602051, "step": 444280 }, { "epoch": 2.6409520242999207, "grad_norm": 1.2601617574691772, "learning_rate": 2.774068541513452e-05, "loss": 0.4436787605285645, "step": 444290 }, { "epoch": 2.6410114663765896, "grad_norm": 1.5605800151824951, "learning_rate": 2.7738160027886468e-05, "loss": 0.47445106506347656, "step": 444300 }, { "epoch": 2.6410709084532575, "grad_norm": 1.516371250152588, "learning_rate": 2.773563503415217e-05, "loss": 0.4539158821105957, "step": 444310 }, { "epoch": 2.641130350529926, "grad_norm": 1.3348848819732666, "learning_rate": 2.7733110433943715e-05, "loss": 0.43845653533935547, "step": 444320 }, { "epoch": 2.6411897926065944, "grad_norm": 1.1905430555343628, "learning_rate": 2.773058622727318e-05, "loss": 0.4811290740966797, "step": 444330 }, { "epoch": 2.641249234683263, "grad_norm": 1.5617979764938354, "learning_rate": 2.772806241415264e-05, "loss": 0.4731287002563477, "step": 444340 }, { "epoch": 2.641308676759931, "grad_norm": 1.4347909688949585, "learning_rate": 2.772553899459415e-05, "loss": 0.4755387306213379, "step": 444350 }, { "epoch": 2.6413681188365996, "grad_norm": 1.2907272577285767, "learning_rate": 2.7723015968609802e-05, "loss": 0.47220449447631835, "step": 444360 }, { "epoch": 2.641427560913268, "grad_norm": 1.1413148641586304, "learning_rate": 2.7720493336211626e-05, "loss": 0.42021784782409666, "step": 444370 }, { "epoch": 2.6414870029899364, "grad_norm": 1.2772923707962036, "learning_rate": 2.7717971097411766e-05, "loss": 0.4731614589691162, "step": 444380 }, { "epoch": 2.641546445066605, "grad_norm": 1.4412654638290405, "learning_rate": 2.771544925222222e-05, "loss": 0.48286848068237304, "step": 444390 }, { "epoch": 2.6416058871432733, "grad_norm": 1.208891749382019, "learning_rate": 2.7712927800655092e-05, "loss": 0.4332082748413086, "step": 444400 }, { "epoch": 2.6416653292199417, "grad_norm": 1.6478129625320435, "learning_rate": 2.7710406742722396e-05, "loss": 0.4087693214416504, "step": 444410 }, { "epoch": 2.64172477129661, "grad_norm": 1.0357482433319092, "learning_rate": 2.770788607843624e-05, "loss": 0.4507893562316895, "step": 444420 }, { "epoch": 2.6417842133732785, "grad_norm": 1.1993038654327393, "learning_rate": 2.7705365807808666e-05, "loss": 0.42079529762268064, "step": 444430 }, { "epoch": 2.641843655449947, "grad_norm": 1.2533786296844482, "learning_rate": 2.7702845930851707e-05, "loss": 0.4739344596862793, "step": 444440 }, { "epoch": 2.6419030975266153, "grad_norm": 1.3883627653121948, "learning_rate": 2.770032644757746e-05, "loss": 0.47053542137146, "step": 444450 }, { "epoch": 2.6419625396032833, "grad_norm": 1.5566717386245728, "learning_rate": 2.7697807357997964e-05, "loss": 0.4858372688293457, "step": 444460 }, { "epoch": 2.642021981679952, "grad_norm": 1.3220303058624268, "learning_rate": 2.769528866212523e-05, "loss": 0.4312585353851318, "step": 444470 }, { "epoch": 2.64208142375662, "grad_norm": 1.6817688941955566, "learning_rate": 2.769277035997135e-05, "loss": 0.4938526153564453, "step": 444480 }, { "epoch": 2.642140865833289, "grad_norm": 1.3324503898620605, "learning_rate": 2.7690252451548372e-05, "loss": 0.4226051330566406, "step": 444490 }, { "epoch": 2.642200307909957, "grad_norm": 1.9394018650054932, "learning_rate": 2.768773493686829e-05, "loss": 0.4902090072631836, "step": 444500 }, { "epoch": 2.6422597499866254, "grad_norm": 1.2985150814056396, "learning_rate": 2.768521781594322e-05, "loss": 0.44321355819702146, "step": 444510 }, { "epoch": 2.642319192063294, "grad_norm": 1.249372124671936, "learning_rate": 2.7682701088785178e-05, "loss": 0.4688886642456055, "step": 444520 }, { "epoch": 2.642378634139962, "grad_norm": 1.3544573783874512, "learning_rate": 2.768018475540617e-05, "loss": 0.5218288421630859, "step": 444530 }, { "epoch": 2.6424380762166306, "grad_norm": 1.564079761505127, "learning_rate": 2.767766881581825e-05, "loss": 0.4843772888183594, "step": 444540 }, { "epoch": 2.642497518293299, "grad_norm": 1.1203672885894775, "learning_rate": 2.767515327003347e-05, "loss": 0.49856133460998536, "step": 444550 }, { "epoch": 2.6425569603699675, "grad_norm": 1.280137062072754, "learning_rate": 2.7672638118063844e-05, "loss": 0.4738163948059082, "step": 444560 }, { "epoch": 2.642616402446636, "grad_norm": 1.2113291025161743, "learning_rate": 2.7670123359921407e-05, "loss": 0.4523445129394531, "step": 444570 }, { "epoch": 2.6426758445233043, "grad_norm": 1.1556859016418457, "learning_rate": 2.7667608995618228e-05, "loss": 0.5125597000122071, "step": 444580 }, { "epoch": 2.6427352865999727, "grad_norm": 1.400726318359375, "learning_rate": 2.7665095025166277e-05, "loss": 0.4421865940093994, "step": 444590 }, { "epoch": 2.642794728676641, "grad_norm": 1.189113974571228, "learning_rate": 2.7662581448577597e-05, "loss": 0.47722539901733396, "step": 444600 }, { "epoch": 2.6428541707533095, "grad_norm": 1.115485429763794, "learning_rate": 2.7660068265864224e-05, "loss": 0.48569631576538086, "step": 444610 }, { "epoch": 2.642913612829978, "grad_norm": 1.1610699892044067, "learning_rate": 2.7657555477038183e-05, "loss": 0.49074087142944334, "step": 444620 }, { "epoch": 2.6429730549066464, "grad_norm": 1.161393404006958, "learning_rate": 2.7655043082111482e-05, "loss": 0.4902032852172852, "step": 444630 }, { "epoch": 2.6430324969833148, "grad_norm": 1.5718157291412354, "learning_rate": 2.7652531081096145e-05, "loss": 0.4442646026611328, "step": 444640 }, { "epoch": 2.6430919390599827, "grad_norm": 1.2350233793258667, "learning_rate": 2.765001947400419e-05, "loss": 0.509532880783081, "step": 444650 }, { "epoch": 2.6431513811366516, "grad_norm": 1.1583300828933716, "learning_rate": 2.7647508260847633e-05, "loss": 0.48317618370056153, "step": 444660 }, { "epoch": 2.6432108232133196, "grad_norm": 1.6424423456192017, "learning_rate": 2.7644997441638465e-05, "loss": 0.46935558319091797, "step": 444670 }, { "epoch": 2.6432702652899884, "grad_norm": 1.5103092193603516, "learning_rate": 2.7642487016388725e-05, "loss": 0.4274557113647461, "step": 444680 }, { "epoch": 2.6433297073666564, "grad_norm": 1.2211931943893433, "learning_rate": 2.763997698511042e-05, "loss": 0.49488143920898436, "step": 444690 }, { "epoch": 2.643389149443325, "grad_norm": 1.4078253507614136, "learning_rate": 2.7637467347815547e-05, "loss": 0.47440142631530763, "step": 444700 }, { "epoch": 2.6434485915199932, "grad_norm": 0.9196376204490662, "learning_rate": 2.7634958104516108e-05, "loss": 0.4053510665893555, "step": 444710 }, { "epoch": 2.6435080335966616, "grad_norm": 1.248226284980774, "learning_rate": 2.7632449255224123e-05, "loss": 0.4394514083862305, "step": 444720 }, { "epoch": 2.64356747567333, "grad_norm": 1.3993842601776123, "learning_rate": 2.7629940799951563e-05, "loss": 0.48113536834716797, "step": 444730 }, { "epoch": 2.6436269177499985, "grad_norm": 1.3470911979675293, "learning_rate": 2.7627432738710464e-05, "loss": 0.45686635971069334, "step": 444740 }, { "epoch": 2.643686359826667, "grad_norm": 1.2035564184188843, "learning_rate": 2.7624925071512802e-05, "loss": 0.47119340896606443, "step": 444750 }, { "epoch": 2.6437458019033353, "grad_norm": 1.6790969371795654, "learning_rate": 2.7622417798370587e-05, "loss": 0.4765647888183594, "step": 444760 }, { "epoch": 2.6438052439800037, "grad_norm": 1.1654905080795288, "learning_rate": 2.7619910919295788e-05, "loss": 0.4768275260925293, "step": 444770 }, { "epoch": 2.643864686056672, "grad_norm": 1.4760451316833496, "learning_rate": 2.761740443430043e-05, "loss": 0.4654549598693848, "step": 444780 }, { "epoch": 2.6439241281333405, "grad_norm": 1.521193027496338, "learning_rate": 2.7614898343396478e-05, "loss": 0.48625802993774414, "step": 444790 }, { "epoch": 2.643983570210009, "grad_norm": 1.01408052444458, "learning_rate": 2.761239264659592e-05, "loss": 0.3991349458694458, "step": 444800 }, { "epoch": 2.6440430122866774, "grad_norm": 1.507022500038147, "learning_rate": 2.760988734391076e-05, "loss": 0.49547734260559084, "step": 444810 }, { "epoch": 2.644102454363346, "grad_norm": 1.11435067653656, "learning_rate": 2.7607382435352973e-05, "loss": 0.4635931491851807, "step": 444820 }, { "epoch": 2.644161896440014, "grad_norm": 1.259868860244751, "learning_rate": 2.7604877920934547e-05, "loss": 0.4740077018737793, "step": 444830 }, { "epoch": 2.644221338516682, "grad_norm": 1.5486111640930176, "learning_rate": 2.7602373800667453e-05, "loss": 0.46078171730041506, "step": 444840 }, { "epoch": 2.644280780593351, "grad_norm": 1.0623759031295776, "learning_rate": 2.759987007456367e-05, "loss": 0.43689870834350586, "step": 444850 }, { "epoch": 2.644340222670019, "grad_norm": 1.5975570678710938, "learning_rate": 2.7597366742635172e-05, "loss": 0.4559304714202881, "step": 444860 }, { "epoch": 2.644399664746688, "grad_norm": 1.0612374544143677, "learning_rate": 2.7594863804893967e-05, "loss": 0.4608501434326172, "step": 444870 }, { "epoch": 2.644459106823356, "grad_norm": 0.8986226916313171, "learning_rate": 2.7592361261351996e-05, "loss": 0.4472914695739746, "step": 444880 }, { "epoch": 2.6445185489000242, "grad_norm": 1.1764775514602661, "learning_rate": 2.7589859112021245e-05, "loss": 0.4925994873046875, "step": 444890 }, { "epoch": 2.6445779909766927, "grad_norm": 1.2645968198776245, "learning_rate": 2.7587357356913645e-05, "loss": 0.46341257095336913, "step": 444900 }, { "epoch": 2.644637433053361, "grad_norm": 1.2418252229690552, "learning_rate": 2.7584855996041216e-05, "loss": 0.46019325256347654, "step": 444910 }, { "epoch": 2.6446968751300295, "grad_norm": 1.3360031843185425, "learning_rate": 2.75823550294159e-05, "loss": 0.4384740352630615, "step": 444920 }, { "epoch": 2.644756317206698, "grad_norm": 1.5417677164077759, "learning_rate": 2.7579854457049648e-05, "loss": 0.5189389228820801, "step": 444930 }, { "epoch": 2.6448157592833663, "grad_norm": 1.414546012878418, "learning_rate": 2.7577354278954454e-05, "loss": 0.49956378936767576, "step": 444940 }, { "epoch": 2.6448752013600347, "grad_norm": 1.2415672540664673, "learning_rate": 2.7574854495142288e-05, "loss": 0.463225793838501, "step": 444950 }, { "epoch": 2.644934643436703, "grad_norm": 1.3041276931762695, "learning_rate": 2.7572355105625036e-05, "loss": 0.49915399551391604, "step": 444960 }, { "epoch": 2.6449940855133716, "grad_norm": 1.160184621810913, "learning_rate": 2.7569856110414717e-05, "loss": 0.45922513008117677, "step": 444970 }, { "epoch": 2.64505352759004, "grad_norm": 1.4627162218093872, "learning_rate": 2.7567357509523273e-05, "loss": 0.5150677680969238, "step": 444980 }, { "epoch": 2.6451129696667084, "grad_norm": 1.6353325843811035, "learning_rate": 2.756485930296262e-05, "loss": 0.49586052894592286, "step": 444990 }, { "epoch": 2.645172411743377, "grad_norm": 1.359395980834961, "learning_rate": 2.756236149074477e-05, "loss": 0.4841207981109619, "step": 445000 }, { "epoch": 2.645231853820045, "grad_norm": 1.0898479223251343, "learning_rate": 2.7559864072881657e-05, "loss": 0.4717380523681641, "step": 445010 }, { "epoch": 2.6452912958967136, "grad_norm": 1.3903852701187134, "learning_rate": 2.7557367049385197e-05, "loss": 0.4861132621765137, "step": 445020 }, { "epoch": 2.6453507379733816, "grad_norm": 0.9778438210487366, "learning_rate": 2.755487042026733e-05, "loss": 0.470005464553833, "step": 445030 }, { "epoch": 2.6454101800500505, "grad_norm": 1.2552744150161743, "learning_rate": 2.7552374185540042e-05, "loss": 0.5076534271240234, "step": 445040 }, { "epoch": 2.6454696221267184, "grad_norm": 1.2481889724731445, "learning_rate": 2.7549878345215242e-05, "loss": 0.4878016471862793, "step": 445050 }, { "epoch": 2.645529064203387, "grad_norm": 1.4029138088226318, "learning_rate": 2.754738289930487e-05, "loss": 0.4923841953277588, "step": 445060 }, { "epoch": 2.6455885062800553, "grad_norm": 1.2061238288879395, "learning_rate": 2.75448878478209e-05, "loss": 0.4755277633666992, "step": 445070 }, { "epoch": 2.6456479483567237, "grad_norm": 1.3324668407440186, "learning_rate": 2.7542393190775228e-05, "loss": 0.47611637115478517, "step": 445080 }, { "epoch": 2.645707390433392, "grad_norm": 1.4000102281570435, "learning_rate": 2.7539898928179786e-05, "loss": 0.44603757858276366, "step": 445090 }, { "epoch": 2.6457668325100605, "grad_norm": 1.043257236480713, "learning_rate": 2.7537405060046523e-05, "loss": 0.4771871089935303, "step": 445100 }, { "epoch": 2.645826274586729, "grad_norm": 1.4200981855392456, "learning_rate": 2.7534911586387373e-05, "loss": 0.5035301208496094, "step": 445110 }, { "epoch": 2.6458857166633973, "grad_norm": 1.2670161724090576, "learning_rate": 2.7532418507214252e-05, "loss": 0.45467557907104494, "step": 445120 }, { "epoch": 2.6459451587400658, "grad_norm": 1.8353508710861206, "learning_rate": 2.75299258225391e-05, "loss": 0.49285736083984377, "step": 445130 }, { "epoch": 2.646004600816734, "grad_norm": 1.1280683279037476, "learning_rate": 2.7527433532373835e-05, "loss": 0.4944495677947998, "step": 445140 }, { "epoch": 2.6460640428934026, "grad_norm": 1.2255648374557495, "learning_rate": 2.752494163673036e-05, "loss": 0.4827127456665039, "step": 445150 }, { "epoch": 2.646123484970071, "grad_norm": 1.4702341556549072, "learning_rate": 2.752245013562061e-05, "loss": 0.5299568176269531, "step": 445160 }, { "epoch": 2.6461829270467394, "grad_norm": 1.460099458694458, "learning_rate": 2.751995902905651e-05, "loss": 0.45690717697143557, "step": 445170 }, { "epoch": 2.646242369123408, "grad_norm": 1.3751990795135498, "learning_rate": 2.7517468317049966e-05, "loss": 0.46654090881347654, "step": 445180 }, { "epoch": 2.6463018112000762, "grad_norm": 1.293786883354187, "learning_rate": 2.7514977999612913e-05, "loss": 0.5282925128936767, "step": 445190 }, { "epoch": 2.646361253276744, "grad_norm": 1.1921989917755127, "learning_rate": 2.7512488076757236e-05, "loss": 0.46742734909057615, "step": 445200 }, { "epoch": 2.646420695353413, "grad_norm": 1.2833271026611328, "learning_rate": 2.7509998548494864e-05, "loss": 0.45604443550109863, "step": 445210 }, { "epoch": 2.646480137430081, "grad_norm": 1.3434176445007324, "learning_rate": 2.7507509414837684e-05, "loss": 0.47652549743652345, "step": 445220 }, { "epoch": 2.64653957950675, "grad_norm": 1.3784691095352173, "learning_rate": 2.7505020675797644e-05, "loss": 0.45876197814941405, "step": 445230 }, { "epoch": 2.646599021583418, "grad_norm": 0.9341955184936523, "learning_rate": 2.750253233138661e-05, "loss": 0.43858089447021487, "step": 445240 }, { "epoch": 2.6466584636600863, "grad_norm": 1.531597375869751, "learning_rate": 2.750004438161652e-05, "loss": 0.5112985134124756, "step": 445250 }, { "epoch": 2.6467179057367547, "grad_norm": 1.20660400390625, "learning_rate": 2.7497556826499238e-05, "loss": 0.5130191802978515, "step": 445260 }, { "epoch": 2.646777347813423, "grad_norm": 1.1772876977920532, "learning_rate": 2.7495069666046698e-05, "loss": 0.4713120460510254, "step": 445270 }, { "epoch": 2.6468367898900915, "grad_norm": 1.5551726818084717, "learning_rate": 2.7492582900270763e-05, "loss": 0.5135869026184082, "step": 445280 }, { "epoch": 2.64689623196676, "grad_norm": 1.7928653955459595, "learning_rate": 2.7490096529183345e-05, "loss": 0.5098803997039795, "step": 445290 }, { "epoch": 2.6469556740434284, "grad_norm": 1.2651026248931885, "learning_rate": 2.7487610552796363e-05, "loss": 0.48023300170898436, "step": 445300 }, { "epoch": 2.6470151161200968, "grad_norm": 1.7966690063476562, "learning_rate": 2.7485124971121666e-05, "loss": 0.4743672847747803, "step": 445310 }, { "epoch": 2.647074558196765, "grad_norm": 1.2296901941299438, "learning_rate": 2.7482639784171183e-05, "loss": 0.4281744956970215, "step": 445320 }, { "epoch": 2.6471340002734336, "grad_norm": 1.5811487436294556, "learning_rate": 2.7480154991956773e-05, "loss": 0.4889772891998291, "step": 445330 }, { "epoch": 2.647193442350102, "grad_norm": 1.2469899654388428, "learning_rate": 2.7477670594490346e-05, "loss": 0.4873775005340576, "step": 445340 }, { "epoch": 2.6472528844267704, "grad_norm": 1.9031182527542114, "learning_rate": 2.7475186591783745e-05, "loss": 0.49280595779418945, "step": 445350 }, { "epoch": 2.647312326503439, "grad_norm": 1.3952529430389404, "learning_rate": 2.7472702983848908e-05, "loss": 0.4620168209075928, "step": 445360 }, { "epoch": 2.6473717685801073, "grad_norm": 1.3751012086868286, "learning_rate": 2.7470219770697693e-05, "loss": 0.45089035034179686, "step": 445370 }, { "epoch": 2.6474312106567757, "grad_norm": 0.975152313709259, "learning_rate": 2.7467736952341982e-05, "loss": 0.44767112731933595, "step": 445380 }, { "epoch": 2.6474906527334436, "grad_norm": 1.8556514978408813, "learning_rate": 2.746525452879361e-05, "loss": 0.4918949127197266, "step": 445390 }, { "epoch": 2.6475500948101125, "grad_norm": 1.102333426475525, "learning_rate": 2.7462772500064516e-05, "loss": 0.4725356101989746, "step": 445400 }, { "epoch": 2.6476095368867805, "grad_norm": 1.107372760772705, "learning_rate": 2.746029086616654e-05, "loss": 0.45021514892578124, "step": 445410 }, { "epoch": 2.6476689789634493, "grad_norm": 1.252256155014038, "learning_rate": 2.7457809627111537e-05, "loss": 0.5003041744232177, "step": 445420 }, { "epoch": 2.6477284210401173, "grad_norm": 1.4188508987426758, "learning_rate": 2.7455328782911416e-05, "loss": 0.45231022834777834, "step": 445430 }, { "epoch": 2.6477878631167857, "grad_norm": 0.9304468035697937, "learning_rate": 2.7452848333578045e-05, "loss": 0.512185525894165, "step": 445440 }, { "epoch": 2.647847305193454, "grad_norm": 1.3222395181655884, "learning_rate": 2.7450368279123234e-05, "loss": 0.48035902976989747, "step": 445450 }, { "epoch": 2.6479067472701225, "grad_norm": 1.0771706104278564, "learning_rate": 2.7447888619558904e-05, "loss": 0.4479986190795898, "step": 445460 }, { "epoch": 2.647966189346791, "grad_norm": 1.4830348491668701, "learning_rate": 2.7445409354896896e-05, "loss": 0.5429579734802246, "step": 445470 }, { "epoch": 2.6480256314234594, "grad_norm": 1.3254741430282593, "learning_rate": 2.7442930485149054e-05, "loss": 0.4569918155670166, "step": 445480 }, { "epoch": 2.648085073500128, "grad_norm": 1.2566806077957153, "learning_rate": 2.744045201032727e-05, "loss": 0.4839885711669922, "step": 445490 }, { "epoch": 2.648144515576796, "grad_norm": 1.3010019063949585, "learning_rate": 2.7437973930443395e-05, "loss": 0.5144955158233643, "step": 445500 }, { "epoch": 2.6482039576534646, "grad_norm": 1.3838833570480347, "learning_rate": 2.7435496245509258e-05, "loss": 0.4777059555053711, "step": 445510 }, { "epoch": 2.648263399730133, "grad_norm": 1.4709903001785278, "learning_rate": 2.7433018955536705e-05, "loss": 0.44324679374694825, "step": 445520 }, { "epoch": 2.6483228418068014, "grad_norm": 1.4676820039749146, "learning_rate": 2.7430542060537634e-05, "loss": 0.43900527954101565, "step": 445530 }, { "epoch": 2.64838228388347, "grad_norm": 1.1817256212234497, "learning_rate": 2.7428065560523853e-05, "loss": 0.4396495819091797, "step": 445540 }, { "epoch": 2.6484417259601383, "grad_norm": 1.3138659000396729, "learning_rate": 2.742558945550721e-05, "loss": 0.40990533828735354, "step": 445550 }, { "epoch": 2.6485011680368067, "grad_norm": 1.2755056619644165, "learning_rate": 2.742311374549959e-05, "loss": 0.4384720802307129, "step": 445560 }, { "epoch": 2.648560610113475, "grad_norm": 1.4250835180282593, "learning_rate": 2.7420638430512797e-05, "loss": 0.453290319442749, "step": 445570 }, { "epoch": 2.648620052190143, "grad_norm": 1.2182896137237549, "learning_rate": 2.741816351055866e-05, "loss": 0.4443901538848877, "step": 445580 }, { "epoch": 2.648679494266812, "grad_norm": 1.4997572898864746, "learning_rate": 2.7415688985649062e-05, "loss": 0.47832727432250977, "step": 445590 }, { "epoch": 2.64873893634348, "grad_norm": 1.0504075288772583, "learning_rate": 2.741321485579582e-05, "loss": 0.44917688369750974, "step": 445600 }, { "epoch": 2.6487983784201488, "grad_norm": 1.4548218250274658, "learning_rate": 2.741074112101076e-05, "loss": 0.5288764476776123, "step": 445610 }, { "epoch": 2.6488578204968167, "grad_norm": 1.2555795907974243, "learning_rate": 2.740826778130574e-05, "loss": 0.4131604194641113, "step": 445620 }, { "epoch": 2.648917262573485, "grad_norm": 1.0173025131225586, "learning_rate": 2.7405794836692567e-05, "loss": 0.49333715438842773, "step": 445630 }, { "epoch": 2.6489767046501536, "grad_norm": 1.5584888458251953, "learning_rate": 2.740332228718308e-05, "loss": 0.4476634502410889, "step": 445640 }, { "epoch": 2.649036146726822, "grad_norm": 1.3799848556518555, "learning_rate": 2.7400850132789085e-05, "loss": 0.43098020553588867, "step": 445650 }, { "epoch": 2.6490955888034904, "grad_norm": 1.3409442901611328, "learning_rate": 2.739837837352245e-05, "loss": 0.46026086807250977, "step": 445660 }, { "epoch": 2.649155030880159, "grad_norm": 1.4088014364242554, "learning_rate": 2.7395907009394977e-05, "loss": 0.45918288230896, "step": 445670 }, { "epoch": 2.649214472956827, "grad_norm": 1.4690264463424683, "learning_rate": 2.7393436040418484e-05, "loss": 0.544001579284668, "step": 445680 }, { "epoch": 2.6492739150334956, "grad_norm": 1.2320231199264526, "learning_rate": 2.7390965466604806e-05, "loss": 0.4621101379394531, "step": 445690 }, { "epoch": 2.649333357110164, "grad_norm": 1.279659628868103, "learning_rate": 2.7388495287965754e-05, "loss": 0.5201394081115722, "step": 445700 }, { "epoch": 2.6493927991868325, "grad_norm": 1.3191205263137817, "learning_rate": 2.738602550451312e-05, "loss": 0.4715247631072998, "step": 445710 }, { "epoch": 2.649452241263501, "grad_norm": 1.1526364088058472, "learning_rate": 2.738355611625876e-05, "loss": 0.4602039813995361, "step": 445720 }, { "epoch": 2.6495116833401693, "grad_norm": 1.385754942893982, "learning_rate": 2.7381087123214466e-05, "loss": 0.4783730983734131, "step": 445730 }, { "epoch": 2.6495711254168377, "grad_norm": 1.150783658027649, "learning_rate": 2.7378618525392052e-05, "loss": 0.4503354072570801, "step": 445740 }, { "epoch": 2.649630567493506, "grad_norm": 1.609841227531433, "learning_rate": 2.737615032280333e-05, "loss": 0.4875929355621338, "step": 445750 }, { "epoch": 2.6496900095701745, "grad_norm": 1.3633111715316772, "learning_rate": 2.7373682515460104e-05, "loss": 0.5055026531219482, "step": 445760 }, { "epoch": 2.6497494516468425, "grad_norm": 1.7798055410385132, "learning_rate": 2.7371215103374165e-05, "loss": 0.47904300689697266, "step": 445770 }, { "epoch": 2.6498088937235114, "grad_norm": 1.3319416046142578, "learning_rate": 2.7368748086557323e-05, "loss": 0.46725263595581057, "step": 445780 }, { "epoch": 2.6498683358001793, "grad_norm": 0.9747362732887268, "learning_rate": 2.736628146502141e-05, "loss": 0.5089505672454834, "step": 445790 }, { "epoch": 2.6499277778768477, "grad_norm": 1.601441502571106, "learning_rate": 2.7363815238778183e-05, "loss": 0.4919602394104004, "step": 445800 }, { "epoch": 2.649987219953516, "grad_norm": 1.319688320159912, "learning_rate": 2.7361349407839475e-05, "loss": 0.47227916717529295, "step": 445810 }, { "epoch": 2.6500466620301846, "grad_norm": 1.6013096570968628, "learning_rate": 2.7358883972217055e-05, "loss": 0.4582187652587891, "step": 445820 }, { "epoch": 2.650106104106853, "grad_norm": 1.2331074476242065, "learning_rate": 2.7356418931922722e-05, "loss": 0.47475481033325195, "step": 445830 }, { "epoch": 2.6501655461835214, "grad_norm": 1.2304232120513916, "learning_rate": 2.735395428696827e-05, "loss": 0.47977700233459475, "step": 445840 }, { "epoch": 2.65022498826019, "grad_norm": 1.2310526371002197, "learning_rate": 2.7351490037365507e-05, "loss": 0.4863326072692871, "step": 445850 }, { "epoch": 2.6502844303368582, "grad_norm": 1.249187707901001, "learning_rate": 2.7349026183126192e-05, "loss": 0.465181827545166, "step": 445860 }, { "epoch": 2.6503438724135266, "grad_norm": 1.3834213018417358, "learning_rate": 2.7346562724262138e-05, "loss": 0.4434206485748291, "step": 445870 }, { "epoch": 2.650403314490195, "grad_norm": 1.0920361280441284, "learning_rate": 2.7344099660785105e-05, "loss": 0.4439888000488281, "step": 445880 }, { "epoch": 2.6504627565668635, "grad_norm": 1.6241616010665894, "learning_rate": 2.7341636992706904e-05, "loss": 0.5249818801879883, "step": 445890 }, { "epoch": 2.650522198643532, "grad_norm": 1.2145475149154663, "learning_rate": 2.7339174720039286e-05, "loss": 0.4964290618896484, "step": 445900 }, { "epoch": 2.6505816407202003, "grad_norm": 0.9442539811134338, "learning_rate": 2.7336712842794033e-05, "loss": 0.4488997459411621, "step": 445910 }, { "epoch": 2.6506410827968687, "grad_norm": 1.5152033567428589, "learning_rate": 2.7334251360982938e-05, "loss": 0.4649786472320557, "step": 445920 }, { "epoch": 2.650700524873537, "grad_norm": 1.2524075508117676, "learning_rate": 2.7331790274617776e-05, "loss": 0.44994916915893557, "step": 445930 }, { "epoch": 2.650759966950205, "grad_norm": 1.3008067607879639, "learning_rate": 2.7329329583710305e-05, "loss": 0.4760109901428223, "step": 445940 }, { "epoch": 2.650819409026874, "grad_norm": 1.3434799909591675, "learning_rate": 2.732686928827232e-05, "loss": 0.4379734039306641, "step": 445950 }, { "epoch": 2.650878851103542, "grad_norm": 1.2943254709243774, "learning_rate": 2.732440938831556e-05, "loss": 0.4841142654418945, "step": 445960 }, { "epoch": 2.650938293180211, "grad_norm": 1.3983986377716064, "learning_rate": 2.73219498838518e-05, "loss": 0.449644660949707, "step": 445970 }, { "epoch": 2.6509977352568788, "grad_norm": 1.2594819068908691, "learning_rate": 2.7319490774892826e-05, "loss": 0.43539953231811523, "step": 445980 }, { "epoch": 2.651057177333547, "grad_norm": 1.1946673393249512, "learning_rate": 2.7317032061450398e-05, "loss": 0.5018659591674804, "step": 445990 }, { "epoch": 2.6511166194102156, "grad_norm": 1.4580981731414795, "learning_rate": 2.731457374353626e-05, "loss": 0.44037961959838867, "step": 446000 }, { "epoch": 2.651176061486884, "grad_norm": 1.3345533609390259, "learning_rate": 2.7312115821162155e-05, "loss": 0.4287226676940918, "step": 446010 }, { "epoch": 2.6512355035635524, "grad_norm": 1.2136439085006714, "learning_rate": 2.7309658294339886e-05, "loss": 0.4807321548461914, "step": 446020 }, { "epoch": 2.651294945640221, "grad_norm": 1.339085578918457, "learning_rate": 2.7307201163081186e-05, "loss": 0.45366244316101073, "step": 446030 }, { "epoch": 2.6513543877168892, "grad_norm": 1.2086716890335083, "learning_rate": 2.73047444273978e-05, "loss": 0.4452423095703125, "step": 446040 }, { "epoch": 2.6514138297935577, "grad_norm": 1.3103723526000977, "learning_rate": 2.7302288087301516e-05, "loss": 0.4264718532562256, "step": 446050 }, { "epoch": 2.651473271870226, "grad_norm": 1.0687613487243652, "learning_rate": 2.7299832142804042e-05, "loss": 0.5030031204223633, "step": 446060 }, { "epoch": 2.6515327139468945, "grad_norm": 1.0480445623397827, "learning_rate": 2.7297376593917136e-05, "loss": 0.4711085319519043, "step": 446070 }, { "epoch": 2.651592156023563, "grad_norm": 1.3308978080749512, "learning_rate": 2.7294921440652566e-05, "loss": 0.44499635696411133, "step": 446080 }, { "epoch": 2.6516515981002313, "grad_norm": 1.401336431503296, "learning_rate": 2.7292466683022066e-05, "loss": 0.460620641708374, "step": 446090 }, { "epoch": 2.6517110401768997, "grad_norm": 1.3347511291503906, "learning_rate": 2.729001232103736e-05, "loss": 0.4605120658874512, "step": 446100 }, { "epoch": 2.651770482253568, "grad_norm": 1.5227922201156616, "learning_rate": 2.7287558354710237e-05, "loss": 0.46898317337036133, "step": 446110 }, { "epoch": 2.6518299243302366, "grad_norm": 1.2375915050506592, "learning_rate": 2.7285104784052383e-05, "loss": 0.4567394733428955, "step": 446120 }, { "epoch": 2.6518893664069045, "grad_norm": 1.185359239578247, "learning_rate": 2.7282651609075566e-05, "loss": 0.4570470809936523, "step": 446130 }, { "epoch": 2.6519488084835734, "grad_norm": 1.2279253005981445, "learning_rate": 2.7280198829791488e-05, "loss": 0.514040756225586, "step": 446140 }, { "epoch": 2.6520082505602414, "grad_norm": 1.078220009803772, "learning_rate": 2.7277746446211926e-05, "loss": 0.4788173198699951, "step": 446150 }, { "epoch": 2.6520676926369102, "grad_norm": 1.093793272972107, "learning_rate": 2.727529445834859e-05, "loss": 0.45223321914672854, "step": 446160 }, { "epoch": 2.652127134713578, "grad_norm": 1.3209556341171265, "learning_rate": 2.7272842866213204e-05, "loss": 0.46836533546447756, "step": 446170 }, { "epoch": 2.6521865767902466, "grad_norm": 1.5048576593399048, "learning_rate": 2.7270391669817508e-05, "loss": 0.4709531307220459, "step": 446180 }, { "epoch": 2.652246018866915, "grad_norm": 1.6857107877731323, "learning_rate": 2.726794086917322e-05, "loss": 0.4782895565032959, "step": 446190 }, { "epoch": 2.6523054609435834, "grad_norm": 1.3500088453292847, "learning_rate": 2.7265490464292044e-05, "loss": 0.497283935546875, "step": 446200 }, { "epoch": 2.652364903020252, "grad_norm": 0.9642572999000549, "learning_rate": 2.726304045518575e-05, "loss": 0.4942117214202881, "step": 446210 }, { "epoch": 2.6524243450969203, "grad_norm": 1.3211745023727417, "learning_rate": 2.7260590841866023e-05, "loss": 0.5234676361083984, "step": 446220 }, { "epoch": 2.6524837871735887, "grad_norm": 1.291259527206421, "learning_rate": 2.7258141624344602e-05, "loss": 0.47446236610412595, "step": 446230 }, { "epoch": 2.652543229250257, "grad_norm": 1.1735552549362183, "learning_rate": 2.7255692802633183e-05, "loss": 0.43510961532592773, "step": 446240 }, { "epoch": 2.6526026713269255, "grad_norm": 1.2151516675949097, "learning_rate": 2.7253244376743486e-05, "loss": 0.5088780403137207, "step": 446250 }, { "epoch": 2.652662113403594, "grad_norm": 1.2600791454315186, "learning_rate": 2.725079634668723e-05, "loss": 0.4327705383300781, "step": 446260 }, { "epoch": 2.6527215554802623, "grad_norm": 1.4320274591445923, "learning_rate": 2.7248348712476108e-05, "loss": 0.4872748374938965, "step": 446270 }, { "epoch": 2.6527809975569308, "grad_norm": 1.3999345302581787, "learning_rate": 2.7245901474121853e-05, "loss": 0.4961673736572266, "step": 446280 }, { "epoch": 2.652840439633599, "grad_norm": 1.5451242923736572, "learning_rate": 2.7243454631636167e-05, "loss": 0.5018889427185058, "step": 446290 }, { "epoch": 2.6528998817102676, "grad_norm": 1.0765694379806519, "learning_rate": 2.7241008185030743e-05, "loss": 0.48549184799194334, "step": 446300 }, { "epoch": 2.652959323786936, "grad_norm": 1.2274982929229736, "learning_rate": 2.723856213431729e-05, "loss": 0.48458061218261717, "step": 446310 }, { "epoch": 2.653018765863604, "grad_norm": 1.5408518314361572, "learning_rate": 2.7236116479507512e-05, "loss": 0.4820911407470703, "step": 446320 }, { "epoch": 2.653078207940273, "grad_norm": 1.0413872003555298, "learning_rate": 2.723367122061309e-05, "loss": 0.45847301483154296, "step": 446330 }, { "epoch": 2.653137650016941, "grad_norm": 1.1926698684692383, "learning_rate": 2.723122635764575e-05, "loss": 0.4521454334259033, "step": 446340 }, { "epoch": 2.6531970920936097, "grad_norm": 1.4359891414642334, "learning_rate": 2.722878189061717e-05, "loss": 0.43967952728271487, "step": 446350 }, { "epoch": 2.6532565341702776, "grad_norm": 1.048589825630188, "learning_rate": 2.722633781953906e-05, "loss": 0.45453786849975586, "step": 446360 }, { "epoch": 2.653315976246946, "grad_norm": 0.9208503365516663, "learning_rate": 2.722389414442309e-05, "loss": 0.47546844482421874, "step": 446370 }, { "epoch": 2.6533754183236145, "grad_norm": 1.1028351783752441, "learning_rate": 2.7221450865280958e-05, "loss": 0.44574499130249023, "step": 446380 }, { "epoch": 2.653434860400283, "grad_norm": 0.9290133714675903, "learning_rate": 2.7219007982124356e-05, "loss": 0.4488933563232422, "step": 446390 }, { "epoch": 2.6534943024769513, "grad_norm": 1.7386753559112549, "learning_rate": 2.721656549496495e-05, "loss": 0.4463987350463867, "step": 446400 }, { "epoch": 2.6535537445536197, "grad_norm": 1.4719576835632324, "learning_rate": 2.7214123403814457e-05, "loss": 0.4518146514892578, "step": 446410 }, { "epoch": 2.653613186630288, "grad_norm": 1.3405473232269287, "learning_rate": 2.7211681708684546e-05, "loss": 0.43486843109130857, "step": 446420 }, { "epoch": 2.6536726287069565, "grad_norm": 1.4006528854370117, "learning_rate": 2.7209240409586888e-05, "loss": 0.46542773246765134, "step": 446430 }, { "epoch": 2.653732070783625, "grad_norm": 0.9778284430503845, "learning_rate": 2.7206799506533166e-05, "loss": 0.5172004222869873, "step": 446440 }, { "epoch": 2.6537915128602934, "grad_norm": 1.2144874334335327, "learning_rate": 2.720435899953506e-05, "loss": 0.4786497116088867, "step": 446450 }, { "epoch": 2.6538509549369618, "grad_norm": 1.070967674255371, "learning_rate": 2.7201918888604234e-05, "loss": 0.4551412105560303, "step": 446460 }, { "epoch": 2.65391039701363, "grad_norm": 1.6164140701293945, "learning_rate": 2.719947917375238e-05, "loss": 0.4767737865447998, "step": 446470 }, { "epoch": 2.6539698390902986, "grad_norm": 1.195968747138977, "learning_rate": 2.7197039854991158e-05, "loss": 0.4658846855163574, "step": 446480 }, { "epoch": 2.654029281166967, "grad_norm": 1.3741077184677124, "learning_rate": 2.7194600932332254e-05, "loss": 0.46587285995483396, "step": 446490 }, { "epoch": 2.6540887232436354, "grad_norm": 1.023604393005371, "learning_rate": 2.7192162405787284e-05, "loss": 0.4738905429840088, "step": 446500 }, { "epoch": 2.6541481653203034, "grad_norm": 1.3243107795715332, "learning_rate": 2.7189724275367965e-05, "loss": 0.49377803802490233, "step": 446510 }, { "epoch": 2.6542076073969723, "grad_norm": 1.3253177404403687, "learning_rate": 2.7187286541085942e-05, "loss": 0.49877300262451174, "step": 446520 }, { "epoch": 2.6542670494736402, "grad_norm": 0.9489759206771851, "learning_rate": 2.718484920295286e-05, "loss": 0.4381235122680664, "step": 446530 }, { "epoch": 2.6543264915503086, "grad_norm": 1.4500889778137207, "learning_rate": 2.7182412260980418e-05, "loss": 0.5042736530303955, "step": 446540 }, { "epoch": 2.654385933626977, "grad_norm": 1.2896592617034912, "learning_rate": 2.717997571518025e-05, "loss": 0.5166253089904785, "step": 446550 }, { "epoch": 2.6544453757036455, "grad_norm": 1.3053083419799805, "learning_rate": 2.7177539565564e-05, "loss": 0.46973867416381837, "step": 446560 }, { "epoch": 2.654504817780314, "grad_norm": 1.6041064262390137, "learning_rate": 2.7175103812143337e-05, "loss": 0.4904036521911621, "step": 446570 }, { "epoch": 2.6545642598569823, "grad_norm": 1.5930169820785522, "learning_rate": 2.7172668454929918e-05, "loss": 0.513811731338501, "step": 446580 }, { "epoch": 2.6546237019336507, "grad_norm": 1.2895150184631348, "learning_rate": 2.717023349393538e-05, "loss": 0.4653822898864746, "step": 446590 }, { "epoch": 2.654683144010319, "grad_norm": 1.2980014085769653, "learning_rate": 2.716779892917136e-05, "loss": 0.4815344333648682, "step": 446600 }, { "epoch": 2.6547425860869875, "grad_norm": 1.3166918754577637, "learning_rate": 2.7165364760649553e-05, "loss": 0.44899768829345704, "step": 446610 }, { "epoch": 2.654802028163656, "grad_norm": 1.1721014976501465, "learning_rate": 2.7162930988381546e-05, "loss": 0.4920628547668457, "step": 446620 }, { "epoch": 2.6548614702403244, "grad_norm": 1.2366056442260742, "learning_rate": 2.7160497612379e-05, "loss": 0.45706543922424314, "step": 446630 }, { "epoch": 2.654920912316993, "grad_norm": 0.9567927122116089, "learning_rate": 2.7158064632653575e-05, "loss": 0.41977791786193847, "step": 446640 }, { "epoch": 2.654980354393661, "grad_norm": 1.0916798114776611, "learning_rate": 2.71556320492169e-05, "loss": 0.4446418285369873, "step": 446650 }, { "epoch": 2.6550397964703296, "grad_norm": 1.1925384998321533, "learning_rate": 2.7153199862080596e-05, "loss": 0.47803192138671874, "step": 446660 }, { "epoch": 2.655099238546998, "grad_norm": 1.4808698892593384, "learning_rate": 2.7150768071256315e-05, "loss": 0.5097703456878662, "step": 446670 }, { "epoch": 2.655158680623666, "grad_norm": 1.295339584350586, "learning_rate": 2.7148336676755693e-05, "loss": 0.4752965450286865, "step": 446680 }, { "epoch": 2.655218122700335, "grad_norm": 1.1412442922592163, "learning_rate": 2.7145905678590323e-05, "loss": 0.44405307769775393, "step": 446690 }, { "epoch": 2.655277564777003, "grad_norm": 1.6204674243927002, "learning_rate": 2.7143475076771885e-05, "loss": 0.4848334312438965, "step": 446700 }, { "epoch": 2.6553370068536717, "grad_norm": 1.1608197689056396, "learning_rate": 2.7141044871311988e-05, "loss": 0.443454647064209, "step": 446710 }, { "epoch": 2.6553964489303397, "grad_norm": 1.2231124639511108, "learning_rate": 2.7138615062222243e-05, "loss": 0.4510956764221191, "step": 446720 }, { "epoch": 2.655455891007008, "grad_norm": 1.3602666854858398, "learning_rate": 2.7136185649514288e-05, "loss": 0.4558847427368164, "step": 446730 }, { "epoch": 2.6555153330836765, "grad_norm": 1.2333908081054688, "learning_rate": 2.713375663319975e-05, "loss": 0.4744594573974609, "step": 446740 }, { "epoch": 2.655574775160345, "grad_norm": 1.193860650062561, "learning_rate": 2.7131328013290237e-05, "loss": 0.41924080848693845, "step": 446750 }, { "epoch": 2.6556342172370133, "grad_norm": 1.476773738861084, "learning_rate": 2.7128899789797346e-05, "loss": 0.4340648174285889, "step": 446760 }, { "epoch": 2.6556936593136817, "grad_norm": 1.0098994970321655, "learning_rate": 2.712647196273273e-05, "loss": 0.4481518745422363, "step": 446770 }, { "epoch": 2.65575310139035, "grad_norm": 1.187734842300415, "learning_rate": 2.7124044532108002e-05, "loss": 0.5120517253875733, "step": 446780 }, { "epoch": 2.6558125434670186, "grad_norm": 0.9904990196228027, "learning_rate": 2.7121617497934747e-05, "loss": 0.46547813415527345, "step": 446790 }, { "epoch": 2.655871985543687, "grad_norm": 1.8600021600723267, "learning_rate": 2.7119190860224593e-05, "loss": 0.5222907543182373, "step": 446800 }, { "epoch": 2.6559314276203554, "grad_norm": 1.1356698274612427, "learning_rate": 2.7116764618989143e-05, "loss": 0.4843717575073242, "step": 446810 }, { "epoch": 2.655990869697024, "grad_norm": 1.3198601007461548, "learning_rate": 2.7114338774239996e-05, "loss": 0.45548439025878906, "step": 446820 }, { "epoch": 2.656050311773692, "grad_norm": 1.788072109222412, "learning_rate": 2.7111913325988774e-05, "loss": 0.449859619140625, "step": 446830 }, { "epoch": 2.6561097538503606, "grad_norm": 1.7895348072052002, "learning_rate": 2.7109488274247075e-05, "loss": 0.45006437301635743, "step": 446840 }, { "epoch": 2.656169195927029, "grad_norm": 1.1321954727172852, "learning_rate": 2.7107063619026486e-05, "loss": 0.44997539520263674, "step": 446850 }, { "epoch": 2.6562286380036975, "grad_norm": 1.3493518829345703, "learning_rate": 2.7104639360338625e-05, "loss": 0.47672467231750487, "step": 446860 }, { "epoch": 2.6562880800803654, "grad_norm": 1.6050550937652588, "learning_rate": 2.7102215498195076e-05, "loss": 0.4741669178009033, "step": 446870 }, { "epoch": 2.6563475221570343, "grad_norm": 1.2463047504425049, "learning_rate": 2.7099792032607434e-05, "loss": 0.46993470191955566, "step": 446880 }, { "epoch": 2.6564069642337023, "grad_norm": 1.6661009788513184, "learning_rate": 2.7097368963587288e-05, "loss": 0.48974218368530276, "step": 446890 }, { "epoch": 2.656466406310371, "grad_norm": 1.0831398963928223, "learning_rate": 2.709494629114624e-05, "loss": 0.4185978412628174, "step": 446900 }, { "epoch": 2.656525848387039, "grad_norm": 1.5607575178146362, "learning_rate": 2.7092524015295878e-05, "loss": 0.47272696495056155, "step": 446910 }, { "epoch": 2.6565852904637075, "grad_norm": 1.5333118438720703, "learning_rate": 2.709010213604779e-05, "loss": 0.4586794853210449, "step": 446920 }, { "epoch": 2.656644732540376, "grad_norm": 1.2270939350128174, "learning_rate": 2.7087680653413562e-05, "loss": 0.472230863571167, "step": 446930 }, { "epoch": 2.6567041746170443, "grad_norm": 1.462597370147705, "learning_rate": 2.7085259567404763e-05, "loss": 0.4859361171722412, "step": 446940 }, { "epoch": 2.6567636166937127, "grad_norm": 1.0902663469314575, "learning_rate": 2.7082838878032972e-05, "loss": 0.4637777328491211, "step": 446950 }, { "epoch": 2.656823058770381, "grad_norm": 1.1080087423324585, "learning_rate": 2.7080418585309807e-05, "loss": 0.45226240158081055, "step": 446960 }, { "epoch": 2.6568825008470496, "grad_norm": 1.1760600805282593, "learning_rate": 2.7077998689246815e-05, "loss": 0.47513422966003416, "step": 446970 }, { "epoch": 2.656941942923718, "grad_norm": 0.9450474977493286, "learning_rate": 2.707557918985559e-05, "loss": 0.49109387397766113, "step": 446980 }, { "epoch": 2.6570013850003864, "grad_norm": 1.4267349243164062, "learning_rate": 2.7073160087147663e-05, "loss": 0.4380949974060059, "step": 446990 }, { "epoch": 2.657060827077055, "grad_norm": 1.4516676664352417, "learning_rate": 2.7070741381134662e-05, "loss": 0.4837066173553467, "step": 447000 }, { "epoch": 2.6571202691537232, "grad_norm": 1.4424657821655273, "learning_rate": 2.7068323071828122e-05, "loss": 0.4291065216064453, "step": 447010 }, { "epoch": 2.6571797112303916, "grad_norm": 1.391885757446289, "learning_rate": 2.7065905159239614e-05, "loss": 0.5034297943115235, "step": 447020 }, { "epoch": 2.65723915330706, "grad_norm": 1.0662569999694824, "learning_rate": 2.7063487643380725e-05, "loss": 0.43940372467041017, "step": 447030 }, { "epoch": 2.6572985953837285, "grad_norm": 1.3235942125320435, "learning_rate": 2.706107052426303e-05, "loss": 0.46831960678100587, "step": 447040 }, { "epoch": 2.657358037460397, "grad_norm": 1.5081154108047485, "learning_rate": 2.7058653801898025e-05, "loss": 0.443102502822876, "step": 447050 }, { "epoch": 2.657417479537065, "grad_norm": 1.5919456481933594, "learning_rate": 2.705623747629734e-05, "loss": 0.4938803195953369, "step": 447060 }, { "epoch": 2.6574769216137337, "grad_norm": 1.4775997400283813, "learning_rate": 2.7053821547472508e-05, "loss": 0.4717421531677246, "step": 447070 }, { "epoch": 2.6575363636904017, "grad_norm": 1.379888892173767, "learning_rate": 2.7051406015435078e-05, "loss": 0.4754990577697754, "step": 447080 }, { "epoch": 2.6575958057670706, "grad_norm": 1.7619290351867676, "learning_rate": 2.7048990880196605e-05, "loss": 0.5084015846252441, "step": 447090 }, { "epoch": 2.6576552478437385, "grad_norm": 1.3434724807739258, "learning_rate": 2.704657614176868e-05, "loss": 0.4623809814453125, "step": 447100 }, { "epoch": 2.657714689920407, "grad_norm": 1.14097261428833, "learning_rate": 2.7044161800162814e-05, "loss": 0.46137447357177735, "step": 447110 }, { "epoch": 2.6577741319970754, "grad_norm": 1.3093377351760864, "learning_rate": 2.7041747855390554e-05, "loss": 0.49811630249023436, "step": 447120 }, { "epoch": 2.6578335740737438, "grad_norm": 1.4245104789733887, "learning_rate": 2.7039334307463466e-05, "loss": 0.44976491928100587, "step": 447130 }, { "epoch": 2.657893016150412, "grad_norm": 1.200751781463623, "learning_rate": 2.7036921156393096e-05, "loss": 0.4469740867614746, "step": 447140 }, { "epoch": 2.6579524582270806, "grad_norm": 1.1006271839141846, "learning_rate": 2.7034508402190968e-05, "loss": 0.46607723236083987, "step": 447150 }, { "epoch": 2.658011900303749, "grad_norm": 1.2996749877929688, "learning_rate": 2.7032096044868664e-05, "loss": 0.4572285175323486, "step": 447160 }, { "epoch": 2.6580713423804174, "grad_norm": 1.1905438899993896, "learning_rate": 2.7029684084437695e-05, "loss": 0.4455108165740967, "step": 447170 }, { "epoch": 2.658130784457086, "grad_norm": 1.1970397233963013, "learning_rate": 2.7027272520909573e-05, "loss": 0.4740128517150879, "step": 447180 }, { "epoch": 2.6581902265337543, "grad_norm": 1.0081723928451538, "learning_rate": 2.7024861354295883e-05, "loss": 0.4284801006317139, "step": 447190 }, { "epoch": 2.6582496686104227, "grad_norm": 1.4853570461273193, "learning_rate": 2.702245058460815e-05, "loss": 0.49205656051635743, "step": 447200 }, { "epoch": 2.658309110687091, "grad_norm": 1.216700553894043, "learning_rate": 2.7020040211857883e-05, "loss": 0.48491725921630857, "step": 447210 }, { "epoch": 2.6583685527637595, "grad_norm": 1.2115731239318848, "learning_rate": 2.7017630236056636e-05, "loss": 0.48692007064819337, "step": 447220 }, { "epoch": 2.658427994840428, "grad_norm": 1.5193226337432861, "learning_rate": 2.7015220657215916e-05, "loss": 0.4719098091125488, "step": 447230 }, { "epoch": 2.6584874369170963, "grad_norm": 1.3014764785766602, "learning_rate": 2.7012811475347267e-05, "loss": 0.4957399845123291, "step": 447240 }, { "epoch": 2.6585468789937643, "grad_norm": 1.5499844551086426, "learning_rate": 2.701040269046219e-05, "loss": 0.49028468132019043, "step": 447250 }, { "epoch": 2.658606321070433, "grad_norm": 1.7145808935165405, "learning_rate": 2.7007994302572244e-05, "loss": 0.4586338996887207, "step": 447260 }, { "epoch": 2.658665763147101, "grad_norm": 1.3796908855438232, "learning_rate": 2.700558631168893e-05, "loss": 0.4777373313903809, "step": 447270 }, { "epoch": 2.6587252052237695, "grad_norm": 1.8011764287948608, "learning_rate": 2.700317871782377e-05, "loss": 0.495235538482666, "step": 447280 }, { "epoch": 2.658784647300438, "grad_norm": 1.2806262969970703, "learning_rate": 2.7000771520988276e-05, "loss": 0.4621835708618164, "step": 447290 }, { "epoch": 2.6588440893771064, "grad_norm": 1.1919909715652466, "learning_rate": 2.699836472119396e-05, "loss": 0.4215574264526367, "step": 447300 }, { "epoch": 2.658903531453775, "grad_norm": 1.7668132781982422, "learning_rate": 2.6995958318452342e-05, "loss": 0.516016674041748, "step": 447310 }, { "epoch": 2.658962973530443, "grad_norm": 0.9258456230163574, "learning_rate": 2.699355231277494e-05, "loss": 0.48404226303100584, "step": 447320 }, { "epoch": 2.6590224156071116, "grad_norm": 1.754401683807373, "learning_rate": 2.699114670417326e-05, "loss": 0.5470192432403564, "step": 447330 }, { "epoch": 2.65908185768378, "grad_norm": 1.6807008981704712, "learning_rate": 2.6988741492658804e-05, "loss": 0.469040584564209, "step": 447340 }, { "epoch": 2.6591412997604484, "grad_norm": 1.0982978343963623, "learning_rate": 2.6986336678243074e-05, "loss": 0.4653679847717285, "step": 447350 }, { "epoch": 2.659200741837117, "grad_norm": 1.495972752571106, "learning_rate": 2.6983932260937585e-05, "loss": 0.49677152633666993, "step": 447360 }, { "epoch": 2.6592601839137853, "grad_norm": 1.203878402709961, "learning_rate": 2.698152824075384e-05, "loss": 0.4954205513000488, "step": 447370 }, { "epoch": 2.6593196259904537, "grad_norm": 1.1670918464660645, "learning_rate": 2.6979124617703306e-05, "loss": 0.44307889938354494, "step": 447380 }, { "epoch": 2.659379068067122, "grad_norm": 1.5611467361450195, "learning_rate": 2.697672139179754e-05, "loss": 0.5061019420623779, "step": 447390 }, { "epoch": 2.6594385101437905, "grad_norm": 1.1273614168167114, "learning_rate": 2.6974318563047997e-05, "loss": 0.4729745864868164, "step": 447400 }, { "epoch": 2.659497952220459, "grad_norm": 1.3391308784484863, "learning_rate": 2.697191613146618e-05, "loss": 0.49348602294921873, "step": 447410 }, { "epoch": 2.659557394297127, "grad_norm": 1.7223875522613525, "learning_rate": 2.6969514097063587e-05, "loss": 0.47740764617919923, "step": 447420 }, { "epoch": 2.6596168363737958, "grad_norm": 1.469325065612793, "learning_rate": 2.6967112459851694e-05, "loss": 0.49884710311889646, "step": 447430 }, { "epoch": 2.6596762784504637, "grad_norm": 1.6310844421386719, "learning_rate": 2.696471121984201e-05, "loss": 0.5137938499450684, "step": 447440 }, { "epoch": 2.6597357205271326, "grad_norm": 1.5202854871749878, "learning_rate": 2.6962310377045995e-05, "loss": 0.5174731254577637, "step": 447450 }, { "epoch": 2.6597951626038006, "grad_norm": 1.1723034381866455, "learning_rate": 2.6959909931475156e-05, "loss": 0.47617378234863283, "step": 447460 }, { "epoch": 2.659854604680469, "grad_norm": 1.1121138334274292, "learning_rate": 2.6957509883140998e-05, "loss": 0.4783957004547119, "step": 447470 }, { "epoch": 2.6599140467571374, "grad_norm": 1.1091983318328857, "learning_rate": 2.6955110232054938e-05, "loss": 0.5099923133850097, "step": 447480 }, { "epoch": 2.659973488833806, "grad_norm": 1.5045603513717651, "learning_rate": 2.6952710978228502e-05, "loss": 0.5103943347930908, "step": 447490 }, { "epoch": 2.660032930910474, "grad_norm": 1.320249080657959, "learning_rate": 2.6950312121673167e-05, "loss": 0.43675918579101564, "step": 447500 }, { "epoch": 2.6600923729871426, "grad_norm": 1.309077262878418, "learning_rate": 2.694791366240037e-05, "loss": 0.4797627925872803, "step": 447510 }, { "epoch": 2.660151815063811, "grad_norm": 1.4270751476287842, "learning_rate": 2.6945515600421635e-05, "loss": 0.49991703033447266, "step": 447520 }, { "epoch": 2.6602112571404795, "grad_norm": 1.4038506746292114, "learning_rate": 2.694311793574842e-05, "loss": 0.46680216789245604, "step": 447530 }, { "epoch": 2.660270699217148, "grad_norm": 1.3426299095153809, "learning_rate": 2.6940720668392166e-05, "loss": 0.4887995719909668, "step": 447540 }, { "epoch": 2.6603301412938163, "grad_norm": 1.5440232753753662, "learning_rate": 2.6938323798364374e-05, "loss": 0.47988343238830566, "step": 447550 }, { "epoch": 2.6603895833704847, "grad_norm": 1.330944538116455, "learning_rate": 2.6935927325676492e-05, "loss": 0.4540290832519531, "step": 447560 }, { "epoch": 2.660449025447153, "grad_norm": 0.9577133655548096, "learning_rate": 2.6933531250339988e-05, "loss": 0.4429461479187012, "step": 447570 }, { "epoch": 2.6605084675238215, "grad_norm": 1.342463731765747, "learning_rate": 2.69311355723663e-05, "loss": 0.4634204387664795, "step": 447580 }, { "epoch": 2.66056790960049, "grad_norm": 1.150960922241211, "learning_rate": 2.692874029176695e-05, "loss": 0.42799086570739747, "step": 447590 }, { "epoch": 2.6606273516771584, "grad_norm": 1.2943376302719116, "learning_rate": 2.6926345408553355e-05, "loss": 0.4272374153137207, "step": 447600 }, { "epoch": 2.6606867937538263, "grad_norm": 1.2596770524978638, "learning_rate": 2.6923950922736945e-05, "loss": 0.5272788047790528, "step": 447610 }, { "epoch": 2.660746235830495, "grad_norm": 1.3191934823989868, "learning_rate": 2.6921556834329225e-05, "loss": 0.4700681209564209, "step": 447620 }, { "epoch": 2.660805677907163, "grad_norm": 1.5235646963119507, "learning_rate": 2.6919163143341624e-05, "loss": 0.4311258792877197, "step": 447630 }, { "epoch": 2.660865119983832, "grad_norm": 1.4774599075317383, "learning_rate": 2.691676984978558e-05, "loss": 0.43377208709716797, "step": 447640 }, { "epoch": 2.6609245620605, "grad_norm": 1.3606626987457275, "learning_rate": 2.691437695367259e-05, "loss": 0.4376725196838379, "step": 447650 }, { "epoch": 2.6609840041371684, "grad_norm": 1.3283371925354004, "learning_rate": 2.691198445501405e-05, "loss": 0.44629220962524413, "step": 447660 }, { "epoch": 2.661043446213837, "grad_norm": 2.214521884918213, "learning_rate": 2.6909592353821405e-05, "loss": 0.45940423011779785, "step": 447670 }, { "epoch": 2.6611028882905052, "grad_norm": 0.965570867061615, "learning_rate": 2.690720065010614e-05, "loss": 0.4537862777709961, "step": 447680 }, { "epoch": 2.6611623303671736, "grad_norm": 1.2763184309005737, "learning_rate": 2.6904809343879667e-05, "loss": 0.4821408748626709, "step": 447690 }, { "epoch": 2.661221772443842, "grad_norm": 1.4086289405822754, "learning_rate": 2.690241843515343e-05, "loss": 0.51492280960083, "step": 447700 }, { "epoch": 2.6612812145205105, "grad_norm": 1.2630821466445923, "learning_rate": 2.6900027923938874e-05, "loss": 0.47277097702026366, "step": 447710 }, { "epoch": 2.661340656597179, "grad_norm": 1.629839539527893, "learning_rate": 2.6897637810247424e-05, "loss": 0.510347843170166, "step": 447720 }, { "epoch": 2.6614000986738473, "grad_norm": 1.4820865392684937, "learning_rate": 2.6895248094090504e-05, "loss": 0.5022281646728516, "step": 447730 }, { "epoch": 2.6614595407505157, "grad_norm": 1.4773881435394287, "learning_rate": 2.6892858775479558e-05, "loss": 0.47875285148620605, "step": 447740 }, { "epoch": 2.661518982827184, "grad_norm": 1.3850911855697632, "learning_rate": 2.6890469854426025e-05, "loss": 0.4047555446624756, "step": 447750 }, { "epoch": 2.6615784249038525, "grad_norm": 1.2251368761062622, "learning_rate": 2.6888081330941318e-05, "loss": 0.4563863754272461, "step": 447760 }, { "epoch": 2.661637866980521, "grad_norm": 1.1826739311218262, "learning_rate": 2.6885693205036878e-05, "loss": 0.4524568557739258, "step": 447770 }, { "epoch": 2.6616973090571894, "grad_norm": 1.3587242364883423, "learning_rate": 2.688330547672412e-05, "loss": 0.47429418563842773, "step": 447780 }, { "epoch": 2.661756751133858, "grad_norm": 1.4492526054382324, "learning_rate": 2.6880918146014455e-05, "loss": 0.47748661041259766, "step": 447790 }, { "epoch": 2.6618161932105258, "grad_norm": 1.3526440858840942, "learning_rate": 2.687853121291931e-05, "loss": 0.4884799003601074, "step": 447800 }, { "epoch": 2.6618756352871946, "grad_norm": 1.3891973495483398, "learning_rate": 2.6876144677450116e-05, "loss": 0.48267059326171874, "step": 447810 }, { "epoch": 2.6619350773638626, "grad_norm": 1.1350208520889282, "learning_rate": 2.6873758539618282e-05, "loss": 0.428941535949707, "step": 447820 }, { "epoch": 2.6619945194405314, "grad_norm": 2.745077610015869, "learning_rate": 2.6871372799435223e-05, "loss": 0.4136784076690674, "step": 447830 }, { "epoch": 2.6620539615171994, "grad_norm": 1.3554770946502686, "learning_rate": 2.6868987456912354e-05, "loss": 0.41757998466491697, "step": 447840 }, { "epoch": 2.662113403593868, "grad_norm": 1.3375040292739868, "learning_rate": 2.6866602512061073e-05, "loss": 0.44245500564575196, "step": 447850 }, { "epoch": 2.6621728456705362, "grad_norm": 1.0011346340179443, "learning_rate": 2.68642179648928e-05, "loss": 0.4751554489135742, "step": 447860 }, { "epoch": 2.6622322877472047, "grad_norm": 1.1234468221664429, "learning_rate": 2.6861833815418924e-05, "loss": 0.4743603229522705, "step": 447870 }, { "epoch": 2.662291729823873, "grad_norm": 1.2030980587005615, "learning_rate": 2.6859450063650883e-05, "loss": 0.4355135917663574, "step": 447880 }, { "epoch": 2.6623511719005415, "grad_norm": 1.0586553812026978, "learning_rate": 2.6857066709600054e-05, "loss": 0.47249817848205566, "step": 447890 }, { "epoch": 2.66241061397721, "grad_norm": 1.2145804166793823, "learning_rate": 2.685468375327786e-05, "loss": 0.4945826530456543, "step": 447900 }, { "epoch": 2.6624700560538783, "grad_norm": 1.2564743757247925, "learning_rate": 2.6852301194695673e-05, "loss": 0.4765829563140869, "step": 447910 }, { "epoch": 2.6625294981305467, "grad_norm": 1.2150434255599976, "learning_rate": 2.6849919033864916e-05, "loss": 0.42304677963256837, "step": 447920 }, { "epoch": 2.662588940207215, "grad_norm": 1.3118364810943604, "learning_rate": 2.684753727079697e-05, "loss": 0.5156361579895019, "step": 447930 }, { "epoch": 2.6626483822838836, "grad_norm": 0.9136483073234558, "learning_rate": 2.684515590550321e-05, "loss": 0.44863452911376955, "step": 447940 }, { "epoch": 2.662707824360552, "grad_norm": 1.2015469074249268, "learning_rate": 2.6842774937995062e-05, "loss": 0.45008325576782227, "step": 447950 }, { "epoch": 2.6627672664372204, "grad_norm": 1.300445795059204, "learning_rate": 2.6840394368283906e-05, "loss": 0.44013137817382814, "step": 447960 }, { "epoch": 2.662826708513889, "grad_norm": 1.2232483625411987, "learning_rate": 2.6838014196381134e-05, "loss": 0.4631836414337158, "step": 447970 }, { "epoch": 2.662886150590557, "grad_norm": 1.4385625123977661, "learning_rate": 2.6835634422298122e-05, "loss": 0.4442768096923828, "step": 447980 }, { "epoch": 2.662945592667225, "grad_norm": 1.595385193824768, "learning_rate": 2.6833255046046256e-05, "loss": 0.5011143684387207, "step": 447990 }, { "epoch": 2.663005034743894, "grad_norm": 1.4072622060775757, "learning_rate": 2.68308760676369e-05, "loss": 0.4292750358581543, "step": 448000 }, { "epoch": 2.663064476820562, "grad_norm": 1.6269402503967285, "learning_rate": 2.6828497487081462e-05, "loss": 0.48234262466430666, "step": 448010 }, { "epoch": 2.6631239188972304, "grad_norm": 1.071265459060669, "learning_rate": 2.6826119304391335e-05, "loss": 0.42003598213195803, "step": 448020 }, { "epoch": 2.663183360973899, "grad_norm": 1.1543289422988892, "learning_rate": 2.6823741519577837e-05, "loss": 0.46602516174316405, "step": 448030 }, { "epoch": 2.6632428030505673, "grad_norm": 1.0573843717575073, "learning_rate": 2.6821364132652392e-05, "loss": 0.4116543769836426, "step": 448040 }, { "epoch": 2.6633022451272357, "grad_norm": 1.1849111318588257, "learning_rate": 2.681898714362637e-05, "loss": 0.4416957855224609, "step": 448050 }, { "epoch": 2.663361687203904, "grad_norm": 1.3035821914672852, "learning_rate": 2.6816610552511122e-05, "loss": 0.44302072525024416, "step": 448060 }, { "epoch": 2.6634211292805725, "grad_norm": 1.1862454414367676, "learning_rate": 2.6814234359318e-05, "loss": 0.4301650047302246, "step": 448070 }, { "epoch": 2.663480571357241, "grad_norm": 1.3927597999572754, "learning_rate": 2.6811858564058435e-05, "loss": 0.4866133689880371, "step": 448080 }, { "epoch": 2.6635400134339093, "grad_norm": 1.3925502300262451, "learning_rate": 2.6809483166743743e-05, "loss": 0.4549713611602783, "step": 448090 }, { "epoch": 2.6635994555105778, "grad_norm": 1.4192347526550293, "learning_rate": 2.680710816738527e-05, "loss": 0.46660609245300294, "step": 448100 }, { "epoch": 2.663658897587246, "grad_norm": 1.288895606994629, "learning_rate": 2.6804733565994423e-05, "loss": 0.43993358612060546, "step": 448110 }, { "epoch": 2.6637183396639146, "grad_norm": 1.2989670038223267, "learning_rate": 2.680235936258254e-05, "loss": 0.46015291213989257, "step": 448120 }, { "epoch": 2.663777781740583, "grad_norm": 1.2997101545333862, "learning_rate": 2.6799985557160973e-05, "loss": 0.4696225643157959, "step": 448130 }, { "epoch": 2.6638372238172514, "grad_norm": 1.3568278551101685, "learning_rate": 2.6797612149741102e-05, "loss": 0.4977713584899902, "step": 448140 }, { "epoch": 2.66389666589392, "grad_norm": 1.512314796447754, "learning_rate": 2.679523914033426e-05, "loss": 0.4653918743133545, "step": 448150 }, { "epoch": 2.663956107970588, "grad_norm": 1.5301860570907593, "learning_rate": 2.6792866528951787e-05, "loss": 0.41398191452026367, "step": 448160 }, { "epoch": 2.6640155500472567, "grad_norm": 1.1721481084823608, "learning_rate": 2.679049431560506e-05, "loss": 0.48046121597290037, "step": 448170 }, { "epoch": 2.6640749921239246, "grad_norm": 0.9692080616950989, "learning_rate": 2.6788122500305416e-05, "loss": 0.4821430206298828, "step": 448180 }, { "epoch": 2.6641344342005935, "grad_norm": 1.0610358715057373, "learning_rate": 2.6785751083064204e-05, "loss": 0.4861610412597656, "step": 448190 }, { "epoch": 2.6641938762772615, "grad_norm": 1.9441041946411133, "learning_rate": 2.6783380063892756e-05, "loss": 0.44310722351074217, "step": 448200 }, { "epoch": 2.66425331835393, "grad_norm": 1.1094557046890259, "learning_rate": 2.6781009442802422e-05, "loss": 0.4365256309509277, "step": 448210 }, { "epoch": 2.6643127604305983, "grad_norm": 1.166380524635315, "learning_rate": 2.6778639219804553e-05, "loss": 0.4873960494995117, "step": 448220 }, { "epoch": 2.6643722025072667, "grad_norm": 2.711082696914673, "learning_rate": 2.6776269394910448e-05, "loss": 0.5303617477416992, "step": 448230 }, { "epoch": 2.664431644583935, "grad_norm": 1.6292648315429688, "learning_rate": 2.6773899968131498e-05, "loss": 0.4381575584411621, "step": 448240 }, { "epoch": 2.6644910866606035, "grad_norm": 1.2848626375198364, "learning_rate": 2.6771530939479006e-05, "loss": 0.4400129795074463, "step": 448250 }, { "epoch": 2.664550528737272, "grad_norm": 1.4208844900131226, "learning_rate": 2.6769162308964314e-05, "loss": 0.47935166358947756, "step": 448260 }, { "epoch": 2.6646099708139404, "grad_norm": 1.3850857019424438, "learning_rate": 2.676679407659875e-05, "loss": 0.4654546737670898, "step": 448270 }, { "epoch": 2.6646694128906088, "grad_norm": 0.7914695143699646, "learning_rate": 2.676442624239364e-05, "loss": 0.4748393058776855, "step": 448280 }, { "epoch": 2.664728854967277, "grad_norm": 1.1553109884262085, "learning_rate": 2.6762058806360303e-05, "loss": 0.4958796501159668, "step": 448290 }, { "epoch": 2.6647882970439456, "grad_norm": 1.5713268518447876, "learning_rate": 2.6759691768510082e-05, "loss": 0.4773235321044922, "step": 448300 }, { "epoch": 2.664847739120614, "grad_norm": 1.49111008644104, "learning_rate": 2.6757325128854295e-05, "loss": 0.4880545139312744, "step": 448310 }, { "epoch": 2.6649071811972824, "grad_norm": 1.2959481477737427, "learning_rate": 2.6754958887404264e-05, "loss": 0.46875362396240233, "step": 448320 }, { "epoch": 2.664966623273951, "grad_norm": 1.0304263830184937, "learning_rate": 2.6752593044171294e-05, "loss": 0.4251973628997803, "step": 448330 }, { "epoch": 2.6650260653506193, "grad_norm": 1.1612359285354614, "learning_rate": 2.6750227599166723e-05, "loss": 0.4504573345184326, "step": 448340 }, { "epoch": 2.6650855074272872, "grad_norm": 1.4969779253005981, "learning_rate": 2.6747862552401852e-05, "loss": 0.5042692184448242, "step": 448350 }, { "epoch": 2.665144949503956, "grad_norm": 1.007511854171753, "learning_rate": 2.6745497903887996e-05, "loss": 0.4565099239349365, "step": 448360 }, { "epoch": 2.665204391580624, "grad_norm": 1.2146397829055786, "learning_rate": 2.6743133653636472e-05, "loss": 0.4643854141235352, "step": 448370 }, { "epoch": 2.665263833657293, "grad_norm": 1.378841519355774, "learning_rate": 2.6740769801658593e-05, "loss": 0.47699713706970215, "step": 448380 }, { "epoch": 2.665323275733961, "grad_norm": 1.088232159614563, "learning_rate": 2.6738406347965666e-05, "loss": 0.43020901679992674, "step": 448390 }, { "epoch": 2.6653827178106293, "grad_norm": 1.5023759603500366, "learning_rate": 2.6736043292568985e-05, "loss": 0.461352014541626, "step": 448400 }, { "epoch": 2.6654421598872977, "grad_norm": 1.484113335609436, "learning_rate": 2.673368063547986e-05, "loss": 0.46910796165466306, "step": 448410 }, { "epoch": 2.665501601963966, "grad_norm": 1.6739020347595215, "learning_rate": 2.67313183767096e-05, "loss": 0.47866134643554686, "step": 448420 }, { "epoch": 2.6655610440406345, "grad_norm": 1.549831748008728, "learning_rate": 2.672895651626949e-05, "loss": 0.464447021484375, "step": 448430 }, { "epoch": 2.665620486117303, "grad_norm": 1.097394585609436, "learning_rate": 2.672659505417085e-05, "loss": 0.4696056365966797, "step": 448440 }, { "epoch": 2.6656799281939714, "grad_norm": 1.1202811002731323, "learning_rate": 2.6724233990424964e-05, "loss": 0.4506685256958008, "step": 448450 }, { "epoch": 2.66573937027064, "grad_norm": 1.708833932876587, "learning_rate": 2.6721873325043136e-05, "loss": 0.45879125595092773, "step": 448460 }, { "epoch": 2.665798812347308, "grad_norm": 0.9615776538848877, "learning_rate": 2.6719513058036634e-05, "loss": 0.43315110206604, "step": 448470 }, { "epoch": 2.6658582544239766, "grad_norm": 1.4756935834884644, "learning_rate": 2.6717153189416778e-05, "loss": 0.4355937957763672, "step": 448480 }, { "epoch": 2.665917696500645, "grad_norm": 1.3747193813323975, "learning_rate": 2.671479371919482e-05, "loss": 0.49546012878417967, "step": 448490 }, { "epoch": 2.6659771385773134, "grad_norm": 1.1881103515625, "learning_rate": 2.6712434647382096e-05, "loss": 0.4657926559448242, "step": 448500 }, { "epoch": 2.666036580653982, "grad_norm": 1.621309518814087, "learning_rate": 2.6710075973989856e-05, "loss": 0.4929800987243652, "step": 448510 }, { "epoch": 2.6660960227306503, "grad_norm": 1.4357964992523193, "learning_rate": 2.6707717699029405e-05, "loss": 0.4889267921447754, "step": 448520 }, { "epoch": 2.6661554648073187, "grad_norm": 1.6525949239730835, "learning_rate": 2.6705359822512e-05, "loss": 0.46533832550048826, "step": 448530 }, { "epoch": 2.6662149068839867, "grad_norm": 1.1610474586486816, "learning_rate": 2.6703002344448937e-05, "loss": 0.4308527946472168, "step": 448540 }, { "epoch": 2.6662743489606555, "grad_norm": 1.2023239135742188, "learning_rate": 2.670064526485149e-05, "loss": 0.4490882396697998, "step": 448550 }, { "epoch": 2.6663337910373235, "grad_norm": 1.4623032808303833, "learning_rate": 2.6698288583730918e-05, "loss": 0.4874156951904297, "step": 448560 }, { "epoch": 2.6663932331139923, "grad_norm": 1.2275168895721436, "learning_rate": 2.669593230109853e-05, "loss": 0.475797176361084, "step": 448570 }, { "epoch": 2.6664526751906603, "grad_norm": 1.353606104850769, "learning_rate": 2.669357641696558e-05, "loss": 0.48791990280151365, "step": 448580 }, { "epoch": 2.6665121172673287, "grad_norm": 1.0493767261505127, "learning_rate": 2.6691220931343318e-05, "loss": 0.44019575119018556, "step": 448590 }, { "epoch": 2.666571559343997, "grad_norm": 1.328933835029602, "learning_rate": 2.6688865844243043e-05, "loss": 0.4395738124847412, "step": 448600 }, { "epoch": 2.6666310014206656, "grad_norm": 1.2448111772537231, "learning_rate": 2.668651115567601e-05, "loss": 0.4823139667510986, "step": 448610 }, { "epoch": 2.666690443497334, "grad_norm": 1.3267372846603394, "learning_rate": 2.6684156865653453e-05, "loss": 0.44568662643432616, "step": 448620 }, { "epoch": 2.6667498855740024, "grad_norm": 1.330590009689331, "learning_rate": 2.668180297418669e-05, "loss": 0.4750336170196533, "step": 448630 }, { "epoch": 2.666809327650671, "grad_norm": 1.222080111503601, "learning_rate": 2.6679449481286955e-05, "loss": 0.4658548831939697, "step": 448640 }, { "epoch": 2.666868769727339, "grad_norm": 1.3263821601867676, "learning_rate": 2.667709638696548e-05, "loss": 0.45372629165649414, "step": 448650 }, { "epoch": 2.6669282118040076, "grad_norm": 1.6752922534942627, "learning_rate": 2.6674743691233568e-05, "loss": 0.5005502223968505, "step": 448660 }, { "epoch": 2.666987653880676, "grad_norm": 1.3269524574279785, "learning_rate": 2.6672391394102446e-05, "loss": 0.4728275775909424, "step": 448670 }, { "epoch": 2.6670470959573445, "grad_norm": 1.4667277336120605, "learning_rate": 2.6670039495583365e-05, "loss": 0.5084903240203857, "step": 448680 }, { "epoch": 2.667106538034013, "grad_norm": 0.9307130575180054, "learning_rate": 2.6667687995687585e-05, "loss": 0.4297783851623535, "step": 448690 }, { "epoch": 2.6671659801106813, "grad_norm": 1.5711320638656616, "learning_rate": 2.6665336894426357e-05, "loss": 0.46350827217102053, "step": 448700 }, { "epoch": 2.6672254221873497, "grad_norm": 1.1929785013198853, "learning_rate": 2.6662986191810923e-05, "loss": 0.5197389602661133, "step": 448710 }, { "epoch": 2.667284864264018, "grad_norm": 1.240761637687683, "learning_rate": 2.6660635887852515e-05, "loss": 0.4800633430480957, "step": 448720 }, { "epoch": 2.667344306340686, "grad_norm": 1.1698460578918457, "learning_rate": 2.6658285982562397e-05, "loss": 0.45511646270751954, "step": 448730 }, { "epoch": 2.667403748417355, "grad_norm": 1.5410420894622803, "learning_rate": 2.665593647595181e-05, "loss": 0.44843482971191406, "step": 448740 }, { "epoch": 2.667463190494023, "grad_norm": 1.4844914674758911, "learning_rate": 2.6653587368031983e-05, "loss": 0.5059036254882813, "step": 448750 }, { "epoch": 2.6675226325706913, "grad_norm": 1.2655885219573975, "learning_rate": 2.665123865881415e-05, "loss": 0.4351457118988037, "step": 448760 }, { "epoch": 2.6675820746473597, "grad_norm": 1.2579227685928345, "learning_rate": 2.6648890348309558e-05, "loss": 0.5442719459533691, "step": 448770 }, { "epoch": 2.667641516724028, "grad_norm": 1.0975228548049927, "learning_rate": 2.6646542436529442e-05, "loss": 0.4346888542175293, "step": 448780 }, { "epoch": 2.6677009588006966, "grad_norm": 1.6894164085388184, "learning_rate": 2.6644194923485004e-05, "loss": 0.477945613861084, "step": 448790 }, { "epoch": 2.667760400877365, "grad_norm": 1.2056487798690796, "learning_rate": 2.664184780918751e-05, "loss": 0.47013163566589355, "step": 448800 }, { "epoch": 2.6678198429540334, "grad_norm": 1.2197872400283813, "learning_rate": 2.6639501093648177e-05, "loss": 0.5081757545471192, "step": 448810 }, { "epoch": 2.667879285030702, "grad_norm": 1.1759861707687378, "learning_rate": 2.663715477687823e-05, "loss": 0.45632166862487794, "step": 448820 }, { "epoch": 2.6679387271073702, "grad_norm": 1.5990886688232422, "learning_rate": 2.6634808858888887e-05, "loss": 0.4707175254821777, "step": 448830 }, { "epoch": 2.6679981691840386, "grad_norm": 1.44709312915802, "learning_rate": 2.663246333969138e-05, "loss": 0.4812604904174805, "step": 448840 }, { "epoch": 2.668057611260707, "grad_norm": 1.4163789749145508, "learning_rate": 2.6630118219296908e-05, "loss": 0.47785224914550783, "step": 448850 }, { "epoch": 2.6681170533373755, "grad_norm": 1.418492078781128, "learning_rate": 2.6627773497716718e-05, "loss": 0.45954408645629885, "step": 448860 }, { "epoch": 2.668176495414044, "grad_norm": 1.4560019969940186, "learning_rate": 2.6625429174962008e-05, "loss": 0.4338377952575684, "step": 448870 }, { "epoch": 2.6682359374907123, "grad_norm": 1.3803247213363647, "learning_rate": 2.6623085251044e-05, "loss": 0.4478907585144043, "step": 448880 }, { "epoch": 2.6682953795673807, "grad_norm": 1.28569495677948, "learning_rate": 2.6620741725973907e-05, "loss": 0.5173060417175293, "step": 448890 }, { "epoch": 2.6683548216440487, "grad_norm": 1.31218421459198, "learning_rate": 2.661839859976294e-05, "loss": 0.46230125427246094, "step": 448900 }, { "epoch": 2.6684142637207175, "grad_norm": 1.203652024269104, "learning_rate": 2.6616055872422297e-05, "loss": 0.46020755767822263, "step": 448910 }, { "epoch": 2.6684737057973855, "grad_norm": 1.3008848428726196, "learning_rate": 2.6613713543963188e-05, "loss": 0.46297173500061034, "step": 448920 }, { "epoch": 2.6685331478740544, "grad_norm": 0.8807013034820557, "learning_rate": 2.661137161439683e-05, "loss": 0.4614384174346924, "step": 448930 }, { "epoch": 2.6685925899507223, "grad_norm": 1.0907624959945679, "learning_rate": 2.6609030083734422e-05, "loss": 0.44345245361328123, "step": 448940 }, { "epoch": 2.6686520320273908, "grad_norm": 1.3552519083023071, "learning_rate": 2.6606688951987158e-05, "loss": 0.5339059829711914, "step": 448950 }, { "epoch": 2.668711474104059, "grad_norm": 1.5740336179733276, "learning_rate": 2.660434821916624e-05, "loss": 0.4532803535461426, "step": 448960 }, { "epoch": 2.6687709161807276, "grad_norm": 0.9804577231407166, "learning_rate": 2.6602007885282864e-05, "loss": 0.44391417503356934, "step": 448970 }, { "epoch": 2.668830358257396, "grad_norm": 1.4440969228744507, "learning_rate": 2.6599667950348224e-05, "loss": 0.4656373977661133, "step": 448980 }, { "epoch": 2.6688898003340644, "grad_norm": 1.1849093437194824, "learning_rate": 2.6597328414373522e-05, "loss": 0.4937553882598877, "step": 448990 }, { "epoch": 2.668949242410733, "grad_norm": 1.1486430168151855, "learning_rate": 2.6594989277369946e-05, "loss": 0.5022920608520508, "step": 449000 }, { "epoch": 2.6690086844874013, "grad_norm": 1.3680719137191772, "learning_rate": 2.6592650539348683e-05, "loss": 0.50606369972229, "step": 449010 }, { "epoch": 2.6690681265640697, "grad_norm": 1.6449028253555298, "learning_rate": 2.659031220032093e-05, "loss": 0.4752251148223877, "step": 449020 }, { "epoch": 2.669127568640738, "grad_norm": 1.3771584033966064, "learning_rate": 2.6587974260297855e-05, "loss": 0.41917076110839846, "step": 449030 }, { "epoch": 2.6691870107174065, "grad_norm": 1.4688001871109009, "learning_rate": 2.658563671929066e-05, "loss": 0.44791035652160643, "step": 449040 }, { "epoch": 2.669246452794075, "grad_norm": 1.1778115034103394, "learning_rate": 2.6583299577310505e-05, "loss": 0.5080367088317871, "step": 449050 }, { "epoch": 2.6693058948707433, "grad_norm": 1.2932839393615723, "learning_rate": 2.658096283436859e-05, "loss": 0.46305532455444337, "step": 449060 }, { "epoch": 2.6693653369474117, "grad_norm": 1.2476718425750732, "learning_rate": 2.657862649047611e-05, "loss": 0.47822933197021483, "step": 449070 }, { "epoch": 2.66942477902408, "grad_norm": 1.1944221258163452, "learning_rate": 2.6576290545644182e-05, "loss": 0.4569429397583008, "step": 449080 }, { "epoch": 2.669484221100748, "grad_norm": 1.5896090269088745, "learning_rate": 2.657395499988403e-05, "loss": 0.5331120491027832, "step": 449090 }, { "epoch": 2.669543663177417, "grad_norm": 1.2620635032653809, "learning_rate": 2.6571619853206818e-05, "loss": 0.47983312606811523, "step": 449100 }, { "epoch": 2.669603105254085, "grad_norm": 1.149774432182312, "learning_rate": 2.6569285105623703e-05, "loss": 0.4500751495361328, "step": 449110 }, { "epoch": 2.669662547330754, "grad_norm": 1.3646422624588013, "learning_rate": 2.6566950757145863e-05, "loss": 0.4699357509613037, "step": 449120 }, { "epoch": 2.669721989407422, "grad_norm": 1.5147099494934082, "learning_rate": 2.6564616807784487e-05, "loss": 0.43816437721252444, "step": 449130 }, { "epoch": 2.66978143148409, "grad_norm": 1.3182414770126343, "learning_rate": 2.656228325755069e-05, "loss": 0.4443822860717773, "step": 449140 }, { "epoch": 2.6698408735607586, "grad_norm": 1.2952548265457153, "learning_rate": 2.6559950106455676e-05, "loss": 0.42995729446411135, "step": 449150 }, { "epoch": 2.669900315637427, "grad_norm": 1.2088360786437988, "learning_rate": 2.6557617354510588e-05, "loss": 0.4348459243774414, "step": 449160 }, { "epoch": 2.6699597577140954, "grad_norm": 1.316422939300537, "learning_rate": 2.6555285001726597e-05, "loss": 0.47453131675720217, "step": 449170 }, { "epoch": 2.670019199790764, "grad_norm": 1.32737135887146, "learning_rate": 2.6552953048114825e-05, "loss": 0.4677027702331543, "step": 449180 }, { "epoch": 2.6700786418674323, "grad_norm": 1.121505618095398, "learning_rate": 2.65506214936865e-05, "loss": 0.43730459213256834, "step": 449190 }, { "epoch": 2.6701380839441007, "grad_norm": 1.4753254652023315, "learning_rate": 2.6548290338452703e-05, "loss": 0.5130405426025391, "step": 449200 }, { "epoch": 2.670197526020769, "grad_norm": 1.1949288845062256, "learning_rate": 2.6545959582424606e-05, "loss": 0.48793854713439944, "step": 449210 }, { "epoch": 2.6702569680974375, "grad_norm": 1.215207815170288, "learning_rate": 2.6543629225613375e-05, "loss": 0.4208060264587402, "step": 449220 }, { "epoch": 2.670316410174106, "grad_norm": 1.8666877746582031, "learning_rate": 2.6541299268030156e-05, "loss": 0.47193126678466796, "step": 449230 }, { "epoch": 2.6703758522507743, "grad_norm": 1.2305105924606323, "learning_rate": 2.6538969709686057e-05, "loss": 0.4584976673126221, "step": 449240 }, { "epoch": 2.6704352943274428, "grad_norm": 1.3275961875915527, "learning_rate": 2.6536640550592296e-05, "loss": 0.48615427017211915, "step": 449250 }, { "epoch": 2.670494736404111, "grad_norm": 1.2009046077728271, "learning_rate": 2.6534311790759952e-05, "loss": 0.5058279991149902, "step": 449260 }, { "epoch": 2.6705541784807796, "grad_norm": 1.3216302394866943, "learning_rate": 2.653198343020018e-05, "loss": 0.43816394805908204, "step": 449270 }, { "epoch": 2.6706136205574476, "grad_norm": 1.5439867973327637, "learning_rate": 2.652965546892411e-05, "loss": 0.48447465896606445, "step": 449280 }, { "epoch": 2.6706730626341164, "grad_norm": 1.3144745826721191, "learning_rate": 2.6527327906942896e-05, "loss": 0.47519874572753906, "step": 449290 }, { "epoch": 2.6707325047107844, "grad_norm": 1.029133677482605, "learning_rate": 2.652500074426767e-05, "loss": 0.48720664978027345, "step": 449300 }, { "epoch": 2.6707919467874532, "grad_norm": 1.2693952322006226, "learning_rate": 2.652267398090957e-05, "loss": 0.4808152675628662, "step": 449310 }, { "epoch": 2.670851388864121, "grad_norm": 1.4467313289642334, "learning_rate": 2.6520347616879716e-05, "loss": 0.45331878662109376, "step": 449320 }, { "epoch": 2.6709108309407896, "grad_norm": 1.3486278057098389, "learning_rate": 2.651802165218923e-05, "loss": 0.428737211227417, "step": 449330 }, { "epoch": 2.670970273017458, "grad_norm": 1.4767578840255737, "learning_rate": 2.651569608684923e-05, "loss": 0.4852949619293213, "step": 449340 }, { "epoch": 2.6710297150941265, "grad_norm": 0.9883160591125488, "learning_rate": 2.6513370920870873e-05, "loss": 0.4366902828216553, "step": 449350 }, { "epoch": 2.671089157170795, "grad_norm": 1.3154453039169312, "learning_rate": 2.6511046154265272e-05, "loss": 0.4446554183959961, "step": 449360 }, { "epoch": 2.6711485992474633, "grad_norm": 1.4432495832443237, "learning_rate": 2.6508721787043533e-05, "loss": 0.5029655456542969, "step": 449370 }, { "epoch": 2.6712080413241317, "grad_norm": 1.1521161794662476, "learning_rate": 2.6506397819216788e-05, "loss": 0.4702578067779541, "step": 449380 }, { "epoch": 2.6712674834008, "grad_norm": 1.5428977012634277, "learning_rate": 2.6504074250796147e-05, "loss": 0.4901253700256348, "step": 449390 }, { "epoch": 2.6713269254774685, "grad_norm": 1.0450695753097534, "learning_rate": 2.6501751081792737e-05, "loss": 0.4414381504058838, "step": 449400 }, { "epoch": 2.671386367554137, "grad_norm": 1.4121041297912598, "learning_rate": 2.6499428312217634e-05, "loss": 0.48887152671813966, "step": 449410 }, { "epoch": 2.6714458096308054, "grad_norm": 1.3462469577789307, "learning_rate": 2.6497105942082005e-05, "loss": 0.5099604606628418, "step": 449420 }, { "epoch": 2.6715052517074738, "grad_norm": 1.2805529832839966, "learning_rate": 2.649478397139692e-05, "loss": 0.4425034523010254, "step": 449430 }, { "epoch": 2.671564693784142, "grad_norm": 1.2586010694503784, "learning_rate": 2.6492462400173506e-05, "loss": 0.49941225051879884, "step": 449440 }, { "epoch": 2.67162413586081, "grad_norm": 1.2570465803146362, "learning_rate": 2.6490141228422873e-05, "loss": 0.4577950954437256, "step": 449450 }, { "epoch": 2.671683577937479, "grad_norm": 1.3344084024429321, "learning_rate": 2.6487820456156098e-05, "loss": 0.4582206249237061, "step": 449460 }, { "epoch": 2.671743020014147, "grad_norm": 1.460724949836731, "learning_rate": 2.6485500083384284e-05, "loss": 0.4595343589782715, "step": 449470 }, { "epoch": 2.671802462090816, "grad_norm": 1.3208197355270386, "learning_rate": 2.6483180110118555e-05, "loss": 0.488127326965332, "step": 449480 }, { "epoch": 2.671861904167484, "grad_norm": 1.5683634281158447, "learning_rate": 2.648086053637001e-05, "loss": 0.4785195827484131, "step": 449490 }, { "epoch": 2.6719213462441522, "grad_norm": 1.3630309104919434, "learning_rate": 2.6478541362149732e-05, "loss": 0.477093505859375, "step": 449500 }, { "epoch": 2.6719807883208206, "grad_norm": 1.5186717510223389, "learning_rate": 2.6476222587468807e-05, "loss": 0.44684691429138185, "step": 449510 }, { "epoch": 2.672040230397489, "grad_norm": 1.3924803733825684, "learning_rate": 2.6473904212338348e-05, "loss": 0.5040952682495117, "step": 449520 }, { "epoch": 2.6720996724741575, "grad_norm": 1.526244878768921, "learning_rate": 2.647158623676943e-05, "loss": 0.4471393585205078, "step": 449530 }, { "epoch": 2.672159114550826, "grad_norm": 1.157741904258728, "learning_rate": 2.6469268660773133e-05, "loss": 0.4647703170776367, "step": 449540 }, { "epoch": 2.6722185566274943, "grad_norm": 1.244886875152588, "learning_rate": 2.646695148436058e-05, "loss": 0.4666585922241211, "step": 449550 }, { "epoch": 2.6722779987041627, "grad_norm": 1.5461583137512207, "learning_rate": 2.646463470754283e-05, "loss": 0.500088119506836, "step": 449560 }, { "epoch": 2.672337440780831, "grad_norm": 1.2516160011291504, "learning_rate": 2.646231833033095e-05, "loss": 0.4452828884124756, "step": 449570 }, { "epoch": 2.6723968828574995, "grad_norm": 1.1961466073989868, "learning_rate": 2.6460002352736045e-05, "loss": 0.4420772552490234, "step": 449580 }, { "epoch": 2.672456324934168, "grad_norm": 1.2268258333206177, "learning_rate": 2.6457686774769193e-05, "loss": 0.5094314575195312, "step": 449590 }, { "epoch": 2.6725157670108364, "grad_norm": 1.1519620418548584, "learning_rate": 2.6455371596441453e-05, "loss": 0.4535529613494873, "step": 449600 }, { "epoch": 2.672575209087505, "grad_norm": 1.1548198461532593, "learning_rate": 2.6453056817763926e-05, "loss": 0.46261372566223147, "step": 449610 }, { "epoch": 2.672634651164173, "grad_norm": 1.1741259098052979, "learning_rate": 2.6450742438747683e-05, "loss": 0.46620941162109375, "step": 449620 }, { "epoch": 2.6726940932408416, "grad_norm": 1.2706520557403564, "learning_rate": 2.644842845940376e-05, "loss": 0.49468240737915037, "step": 449630 }, { "epoch": 2.6727535353175096, "grad_norm": 1.355710506439209, "learning_rate": 2.6446114879743255e-05, "loss": 0.47542634010314944, "step": 449640 }, { "epoch": 2.6728129773941784, "grad_norm": 1.2904796600341797, "learning_rate": 2.6443801699777237e-05, "loss": 0.4558436393737793, "step": 449650 }, { "epoch": 2.6728724194708464, "grad_norm": 1.3199869394302368, "learning_rate": 2.6441488919516766e-05, "loss": 0.5134161949157715, "step": 449660 }, { "epoch": 2.6729318615475153, "grad_norm": 1.501681923866272, "learning_rate": 2.643917653897289e-05, "loss": 0.452210807800293, "step": 449670 }, { "epoch": 2.6729913036241832, "grad_norm": 1.8695839643478394, "learning_rate": 2.6436864558156717e-05, "loss": 0.45418462753295896, "step": 449680 }, { "epoch": 2.6730507457008517, "grad_norm": 1.234769582748413, "learning_rate": 2.6434552977079252e-05, "loss": 0.42104082107543944, "step": 449690 }, { "epoch": 2.67311018777752, "grad_norm": 1.4279555082321167, "learning_rate": 2.6432241795751566e-05, "loss": 0.4932159423828125, "step": 449700 }, { "epoch": 2.6731696298541885, "grad_norm": 1.3120166063308716, "learning_rate": 2.642993101418474e-05, "loss": 0.483946418762207, "step": 449710 }, { "epoch": 2.673229071930857, "grad_norm": 1.023821473121643, "learning_rate": 2.642762063238981e-05, "loss": 0.4861504554748535, "step": 449720 }, { "epoch": 2.6732885140075253, "grad_norm": 1.8090219497680664, "learning_rate": 2.6425310650377833e-05, "loss": 0.45056838989257814, "step": 449730 }, { "epoch": 2.6733479560841937, "grad_norm": 1.4994394779205322, "learning_rate": 2.6423001068159864e-05, "loss": 0.47205066680908203, "step": 449740 }, { "epoch": 2.673407398160862, "grad_norm": 1.3520911931991577, "learning_rate": 2.642069188574694e-05, "loss": 0.46399688720703125, "step": 449750 }, { "epoch": 2.6734668402375306, "grad_norm": 1.6051441431045532, "learning_rate": 2.641838310315011e-05, "loss": 0.47213220596313477, "step": 449760 }, { "epoch": 2.673526282314199, "grad_norm": 1.2179056406021118, "learning_rate": 2.6416074720380412e-05, "loss": 0.45782980918884275, "step": 449770 }, { "epoch": 2.6735857243908674, "grad_norm": 1.0697699785232544, "learning_rate": 2.6413766737448908e-05, "loss": 0.45438356399536134, "step": 449780 }, { "epoch": 2.673645166467536, "grad_norm": 1.3973746299743652, "learning_rate": 2.6411459154366626e-05, "loss": 0.4436949729919434, "step": 449790 }, { "epoch": 2.673704608544204, "grad_norm": 1.055248737335205, "learning_rate": 2.6409151971144613e-05, "loss": 0.5207149028778076, "step": 449800 }, { "epoch": 2.6737640506208726, "grad_norm": 1.5087746381759644, "learning_rate": 2.640684518779388e-05, "loss": 0.42985119819641116, "step": 449810 }, { "epoch": 2.673823492697541, "grad_norm": 1.3460606336593628, "learning_rate": 2.6404538804325507e-05, "loss": 0.47227182388305666, "step": 449820 }, { "epoch": 2.673882934774209, "grad_norm": 1.1160238981246948, "learning_rate": 2.6402232820750467e-05, "loss": 0.4454166889190674, "step": 449830 }, { "epoch": 2.673942376850878, "grad_norm": 1.2725133895874023, "learning_rate": 2.6399927237079848e-05, "loss": 0.4860407829284668, "step": 449840 }, { "epoch": 2.674001818927546, "grad_norm": 1.198041558265686, "learning_rate": 2.6397622053324654e-05, "loss": 0.48182172775268556, "step": 449850 }, { "epoch": 2.6740612610042147, "grad_norm": 1.3108510971069336, "learning_rate": 2.6395317269495917e-05, "loss": 0.510951566696167, "step": 449860 }, { "epoch": 2.6741207030808827, "grad_norm": 1.2838928699493408, "learning_rate": 2.639301288560466e-05, "loss": 0.48726634979248046, "step": 449870 }, { "epoch": 2.674180145157551, "grad_norm": 1.9563475847244263, "learning_rate": 2.6390708901661897e-05, "loss": 0.5145861625671386, "step": 449880 }, { "epoch": 2.6742395872342195, "grad_norm": 1.373904824256897, "learning_rate": 2.6388405317678677e-05, "loss": 0.4623462677001953, "step": 449890 }, { "epoch": 2.674299029310888, "grad_norm": 1.2683887481689453, "learning_rate": 2.638610213366598e-05, "loss": 0.5149811744689942, "step": 449900 }, { "epoch": 2.6743584713875563, "grad_norm": 1.0979080200195312, "learning_rate": 2.638379934963485e-05, "loss": 0.46470165252685547, "step": 449910 }, { "epoch": 2.6744179134642247, "grad_norm": 1.4663163423538208, "learning_rate": 2.6381496965596303e-05, "loss": 0.5113601207733154, "step": 449920 }, { "epoch": 2.674477355540893, "grad_norm": 1.3685106039047241, "learning_rate": 2.6379194981561346e-05, "loss": 0.47519474029541015, "step": 449930 }, { "epoch": 2.6745367976175616, "grad_norm": 1.1173455715179443, "learning_rate": 2.637689339754099e-05, "loss": 0.4710592269897461, "step": 449940 }, { "epoch": 2.67459623969423, "grad_norm": 1.4920473098754883, "learning_rate": 2.6374592213546257e-05, "loss": 0.4031821727752686, "step": 449950 }, { "epoch": 2.6746556817708984, "grad_norm": 1.4490333795547485, "learning_rate": 2.637229142958813e-05, "loss": 0.5429089546203614, "step": 449960 }, { "epoch": 2.674715123847567, "grad_norm": 1.264158844947815, "learning_rate": 2.6369991045677643e-05, "loss": 0.4916396141052246, "step": 449970 }, { "epoch": 2.6747745659242352, "grad_norm": 1.4127259254455566, "learning_rate": 2.6367691061825796e-05, "loss": 0.517693042755127, "step": 449980 }, { "epoch": 2.6748340080009037, "grad_norm": 1.2562906742095947, "learning_rate": 2.6365391478043568e-05, "loss": 0.4493725299835205, "step": 449990 }, { "epoch": 2.674893450077572, "grad_norm": 1.2160722017288208, "learning_rate": 2.636309229434198e-05, "loss": 0.4699307918548584, "step": 450000 }, { "epoch": 2.6749528921542405, "grad_norm": 1.7176331281661987, "learning_rate": 2.6360793510732025e-05, "loss": 0.4118810653686523, "step": 450010 }, { "epoch": 2.6750123342309085, "grad_norm": 1.6151601076126099, "learning_rate": 2.635849512722471e-05, "loss": 0.46054730415344236, "step": 450020 }, { "epoch": 2.6750717763075773, "grad_norm": 1.2715165615081787, "learning_rate": 2.6356197143830997e-05, "loss": 0.4265433788299561, "step": 450030 }, { "epoch": 2.6751312183842453, "grad_norm": 1.5513256788253784, "learning_rate": 2.6353899560561918e-05, "loss": 0.4486834049224854, "step": 450040 }, { "epoch": 2.675190660460914, "grad_norm": 1.4796648025512695, "learning_rate": 2.635160237742845e-05, "loss": 0.3880211353302002, "step": 450050 }, { "epoch": 2.675250102537582, "grad_norm": 1.5200397968292236, "learning_rate": 2.634930559444157e-05, "loss": 0.4794787406921387, "step": 450060 }, { "epoch": 2.6753095446142505, "grad_norm": 1.1679943799972534, "learning_rate": 2.6347009211612288e-05, "loss": 0.4553277015686035, "step": 450070 }, { "epoch": 2.675368986690919, "grad_norm": 0.951858639717102, "learning_rate": 2.6344713228951567e-05, "loss": 0.4772182464599609, "step": 450080 }, { "epoch": 2.6754284287675874, "grad_norm": 1.4900790452957153, "learning_rate": 2.6342417646470392e-05, "loss": 0.44537057876586916, "step": 450090 }, { "epoch": 2.6754878708442558, "grad_norm": 1.329606533050537, "learning_rate": 2.6340122464179756e-05, "loss": 0.4803884506225586, "step": 450100 }, { "epoch": 2.675547312920924, "grad_norm": 1.2104846239089966, "learning_rate": 2.6337827682090653e-05, "loss": 0.48501272201538087, "step": 450110 }, { "epoch": 2.6756067549975926, "grad_norm": 1.0618369579315186, "learning_rate": 2.6335533300214026e-05, "loss": 0.43080663681030273, "step": 450120 }, { "epoch": 2.675666197074261, "grad_norm": 1.0484555959701538, "learning_rate": 2.6333239318560855e-05, "loss": 0.3970909357070923, "step": 450130 }, { "epoch": 2.6757256391509294, "grad_norm": 1.2419781684875488, "learning_rate": 2.633094573714213e-05, "loss": 0.4627964019775391, "step": 450140 }, { "epoch": 2.675785081227598, "grad_norm": 1.333180546760559, "learning_rate": 2.6328652555968835e-05, "loss": 0.5115904808044434, "step": 450150 }, { "epoch": 2.6758445233042663, "grad_norm": 1.4646027088165283, "learning_rate": 2.632635977505189e-05, "loss": 0.4607515811920166, "step": 450160 }, { "epoch": 2.6759039653809347, "grad_norm": 1.245064616203308, "learning_rate": 2.6324067394402336e-05, "loss": 0.48416662216186523, "step": 450170 }, { "epoch": 2.675963407457603, "grad_norm": 1.1551172733306885, "learning_rate": 2.6321775414031068e-05, "loss": 0.44850687980651854, "step": 450180 }, { "epoch": 2.676022849534271, "grad_norm": 1.324009895324707, "learning_rate": 2.6319483833949078e-05, "loss": 0.5008359432220459, "step": 450190 }, { "epoch": 2.67608229161094, "grad_norm": 1.2500615119934082, "learning_rate": 2.631719265416735e-05, "loss": 0.4279369831085205, "step": 450200 }, { "epoch": 2.676141733687608, "grad_norm": 1.9107881784439087, "learning_rate": 2.6314901874696813e-05, "loss": 0.4921173095703125, "step": 450210 }, { "epoch": 2.6762011757642767, "grad_norm": 1.3866757154464722, "learning_rate": 2.6312611495548423e-05, "loss": 0.49584574699401857, "step": 450220 }, { "epoch": 2.6762606178409447, "grad_norm": 0.9952343106269836, "learning_rate": 2.6310321516733183e-05, "loss": 0.41859970092773435, "step": 450230 }, { "epoch": 2.676320059917613, "grad_norm": 1.4614713191986084, "learning_rate": 2.6308031938262005e-05, "loss": 0.45441880226135256, "step": 450240 }, { "epoch": 2.6763795019942815, "grad_norm": 1.566328525543213, "learning_rate": 2.6305742760145842e-05, "loss": 0.469069242477417, "step": 450250 }, { "epoch": 2.67643894407095, "grad_norm": 1.48763906955719, "learning_rate": 2.6303453982395644e-05, "loss": 0.5002088069915771, "step": 450260 }, { "epoch": 2.6764983861476184, "grad_norm": 1.3324934244155884, "learning_rate": 2.6301165605022382e-05, "loss": 0.46422643661499025, "step": 450270 }, { "epoch": 2.676557828224287, "grad_norm": 1.459618091583252, "learning_rate": 2.6298877628037e-05, "loss": 0.476420259475708, "step": 450280 }, { "epoch": 2.676617270300955, "grad_norm": 1.300021767616272, "learning_rate": 2.6296590051450422e-05, "loss": 0.43693203926086427, "step": 450290 }, { "epoch": 2.6766767123776236, "grad_norm": 1.3668323755264282, "learning_rate": 2.6294302875273614e-05, "loss": 0.46082444190979005, "step": 450300 }, { "epoch": 2.676736154454292, "grad_norm": 1.50443696975708, "learning_rate": 2.6292016099517497e-05, "loss": 0.4503063201904297, "step": 450310 }, { "epoch": 2.6767955965309604, "grad_norm": 1.133475422859192, "learning_rate": 2.6289729724192996e-05, "loss": 0.4833414554595947, "step": 450320 }, { "epoch": 2.676855038607629, "grad_norm": 1.1154462099075317, "learning_rate": 2.62874437493111e-05, "loss": 0.4654579162597656, "step": 450330 }, { "epoch": 2.6769144806842973, "grad_norm": 1.1177319288253784, "learning_rate": 2.6285158174882714e-05, "loss": 0.47541656494140627, "step": 450340 }, { "epoch": 2.6769739227609657, "grad_norm": 1.5331661701202393, "learning_rate": 2.6282873000918768e-05, "loss": 0.4575178146362305, "step": 450350 }, { "epoch": 2.677033364837634, "grad_norm": 1.3379640579223633, "learning_rate": 2.6280588227430204e-05, "loss": 0.5009753227233886, "step": 450360 }, { "epoch": 2.6770928069143025, "grad_norm": 1.9838371276855469, "learning_rate": 2.627830385442793e-05, "loss": 0.46010513305664064, "step": 450370 }, { "epoch": 2.6771522489909705, "grad_norm": 1.1550250053405762, "learning_rate": 2.6276019881922908e-05, "loss": 0.5030652999877929, "step": 450380 }, { "epoch": 2.6772116910676393, "grad_norm": 0.9472278356552124, "learning_rate": 2.6273736309926032e-05, "loss": 0.4429325103759766, "step": 450390 }, { "epoch": 2.6772711331443073, "grad_norm": 0.8974627256393433, "learning_rate": 2.6271453138448242e-05, "loss": 0.4734637260437012, "step": 450400 }, { "epoch": 2.677330575220976, "grad_norm": 1.5819441080093384, "learning_rate": 2.626917036750046e-05, "loss": 0.472308349609375, "step": 450410 }, { "epoch": 2.677390017297644, "grad_norm": 0.9902681708335876, "learning_rate": 2.6266887997093615e-05, "loss": 0.4661208152770996, "step": 450420 }, { "epoch": 2.6774494593743126, "grad_norm": 1.4295713901519775, "learning_rate": 2.6264606027238603e-05, "loss": 0.44483437538146975, "step": 450430 }, { "epoch": 2.677508901450981, "grad_norm": 1.2796525955200195, "learning_rate": 2.6262324457946354e-05, "loss": 0.4391016960144043, "step": 450440 }, { "epoch": 2.6775683435276494, "grad_norm": 1.190547227859497, "learning_rate": 2.626004328922776e-05, "loss": 0.4261597156524658, "step": 450450 }, { "epoch": 2.677627785604318, "grad_norm": 1.2521575689315796, "learning_rate": 2.6257762521093775e-05, "loss": 0.46618924140930174, "step": 450460 }, { "epoch": 2.677687227680986, "grad_norm": 1.4769023656845093, "learning_rate": 2.6255482153555276e-05, "loss": 0.5597071647644043, "step": 450470 }, { "epoch": 2.6777466697576546, "grad_norm": 1.2959517240524292, "learning_rate": 2.625320218662318e-05, "loss": 0.43317861557006837, "step": 450480 }, { "epoch": 2.677806111834323, "grad_norm": 1.3674851655960083, "learning_rate": 2.6250922620308417e-05, "loss": 0.4609688758850098, "step": 450490 }, { "epoch": 2.6778655539109915, "grad_norm": 1.2502472400665283, "learning_rate": 2.6248643454621853e-05, "loss": 0.46001858711242677, "step": 450500 }, { "epoch": 2.67792499598766, "grad_norm": 1.0191478729248047, "learning_rate": 2.6246364689574416e-05, "loss": 0.40483717918395995, "step": 450510 }, { "epoch": 2.6779844380643283, "grad_norm": 1.1020153760910034, "learning_rate": 2.6244086325176975e-05, "loss": 0.48638210296630857, "step": 450520 }, { "epoch": 2.6780438801409967, "grad_norm": 1.3138443231582642, "learning_rate": 2.624180836144048e-05, "loss": 0.4655455589294434, "step": 450530 }, { "epoch": 2.678103322217665, "grad_norm": 1.2593697309494019, "learning_rate": 2.6239530798375787e-05, "loss": 0.4486688613891602, "step": 450540 }, { "epoch": 2.6781627642943335, "grad_norm": 1.161696434020996, "learning_rate": 2.6237253635993826e-05, "loss": 0.5152286529541016, "step": 450550 }, { "epoch": 2.678222206371002, "grad_norm": 1.1252511739730835, "learning_rate": 2.623497687430545e-05, "loss": 0.4777359962463379, "step": 450560 }, { "epoch": 2.67828164844767, "grad_norm": 1.103118896484375, "learning_rate": 2.6232700513321584e-05, "loss": 0.41826181411743163, "step": 450570 }, { "epoch": 2.6783410905243388, "grad_norm": 1.5651803016662598, "learning_rate": 2.6230424553053084e-05, "loss": 0.46314263343811035, "step": 450580 }, { "epoch": 2.6784005326010067, "grad_norm": 1.2161508798599243, "learning_rate": 2.6228148993510865e-05, "loss": 0.4692383766174316, "step": 450590 }, { "epoch": 2.6784599746776756, "grad_norm": 1.1496775150299072, "learning_rate": 2.622587383470581e-05, "loss": 0.4820101737976074, "step": 450600 }, { "epoch": 2.6785194167543436, "grad_norm": 1.2421549558639526, "learning_rate": 2.6223599076648812e-05, "loss": 0.4323331356048584, "step": 450610 }, { "epoch": 2.678578858831012, "grad_norm": 1.5497057437896729, "learning_rate": 2.622132471935071e-05, "loss": 0.44744267463684084, "step": 450620 }, { "epoch": 2.6786383009076804, "grad_norm": 1.3405791521072388, "learning_rate": 2.6219050762822423e-05, "loss": 0.4715450286865234, "step": 450630 }, { "epoch": 2.678697742984349, "grad_norm": 1.251204013824463, "learning_rate": 2.6216777207074815e-05, "loss": 0.43187336921691893, "step": 450640 }, { "epoch": 2.6787571850610172, "grad_norm": 1.2234094142913818, "learning_rate": 2.621450405211876e-05, "loss": 0.519828987121582, "step": 450650 }, { "epoch": 2.6788166271376856, "grad_norm": 2.283738851547241, "learning_rate": 2.6212231297965138e-05, "loss": 0.538581371307373, "step": 450660 }, { "epoch": 2.678876069214354, "grad_norm": 1.598924994468689, "learning_rate": 2.620995894462484e-05, "loss": 0.44627084732055666, "step": 450670 }, { "epoch": 2.6789355112910225, "grad_norm": 1.338064193725586, "learning_rate": 2.6207686992108686e-05, "loss": 0.5008336067199707, "step": 450680 }, { "epoch": 2.678994953367691, "grad_norm": 1.0601590871810913, "learning_rate": 2.6205415440427584e-05, "loss": 0.4640775203704834, "step": 450690 }, { "epoch": 2.6790543954443593, "grad_norm": 1.0926259756088257, "learning_rate": 2.6203144289592396e-05, "loss": 0.4616240978240967, "step": 450700 }, { "epoch": 2.6791138375210277, "grad_norm": 0.7968437671661377, "learning_rate": 2.620087353961397e-05, "loss": 0.42502174377441404, "step": 450710 }, { "epoch": 2.679173279597696, "grad_norm": 1.5353997945785522, "learning_rate": 2.6198603190503197e-05, "loss": 0.44502983093261717, "step": 450720 }, { "epoch": 2.6792327216743645, "grad_norm": 1.4759560823440552, "learning_rate": 2.6196333242270903e-05, "loss": 0.4529277801513672, "step": 450730 }, { "epoch": 2.679292163751033, "grad_norm": 1.3085638284683228, "learning_rate": 2.6194063694927974e-05, "loss": 0.45638346672058105, "step": 450740 }, { "epoch": 2.6793516058277014, "grad_norm": 1.3118423223495483, "learning_rate": 2.6191794548485237e-05, "loss": 0.46944313049316405, "step": 450750 }, { "epoch": 2.6794110479043693, "grad_norm": 0.9508360624313354, "learning_rate": 2.6189525802953585e-05, "loss": 0.4526327610015869, "step": 450760 }, { "epoch": 2.679470489981038, "grad_norm": 1.2893105745315552, "learning_rate": 2.618725745834385e-05, "loss": 0.4432413101196289, "step": 450770 }, { "epoch": 2.679529932057706, "grad_norm": 1.0781441926956177, "learning_rate": 2.618498951466688e-05, "loss": 0.46375551223754885, "step": 450780 }, { "epoch": 2.679589374134375, "grad_norm": 1.1395255327224731, "learning_rate": 2.6182721971933542e-05, "loss": 0.4749462127685547, "step": 450790 }, { "epoch": 2.679648816211043, "grad_norm": 1.4438538551330566, "learning_rate": 2.618045483015466e-05, "loss": 0.44206790924072265, "step": 450800 }, { "epoch": 2.6797082582877114, "grad_norm": 1.345706582069397, "learning_rate": 2.617818808934107e-05, "loss": 0.5066961288452149, "step": 450810 }, { "epoch": 2.67976770036438, "grad_norm": 1.5867984294891357, "learning_rate": 2.617592174950366e-05, "loss": 0.4824483871459961, "step": 450820 }, { "epoch": 2.6798271424410482, "grad_norm": 1.3832446336746216, "learning_rate": 2.6173655810653235e-05, "loss": 0.47106504440307617, "step": 450830 }, { "epoch": 2.6798865845177167, "grad_norm": 1.3669054508209229, "learning_rate": 2.617139027280066e-05, "loss": 0.4385099411010742, "step": 450840 }, { "epoch": 2.679946026594385, "grad_norm": 1.0289583206176758, "learning_rate": 2.6169125135956745e-05, "loss": 0.4440159797668457, "step": 450850 }, { "epoch": 2.6800054686710535, "grad_norm": 1.2864954471588135, "learning_rate": 2.616686040013235e-05, "loss": 0.4673469543457031, "step": 450860 }, { "epoch": 2.680064910747722, "grad_norm": 1.3193951845169067, "learning_rate": 2.616459606533829e-05, "loss": 0.4654338836669922, "step": 450870 }, { "epoch": 2.6801243528243903, "grad_norm": 1.081447958946228, "learning_rate": 2.61623321315854e-05, "loss": 0.40473384857177735, "step": 450880 }, { "epoch": 2.6801837949010587, "grad_norm": 1.501319169998169, "learning_rate": 2.6160068598884525e-05, "loss": 0.46231517791748045, "step": 450890 }, { "epoch": 2.680243236977727, "grad_norm": 1.4660465717315674, "learning_rate": 2.615780546724647e-05, "loss": 0.4553080558776855, "step": 450900 }, { "epoch": 2.6803026790543956, "grad_norm": 0.8903521299362183, "learning_rate": 2.6155542736682093e-05, "loss": 0.4311796188354492, "step": 450910 }, { "epoch": 2.680362121131064, "grad_norm": 1.145286202430725, "learning_rate": 2.615328040720219e-05, "loss": 0.4659876823425293, "step": 450920 }, { "epoch": 2.680421563207732, "grad_norm": 1.3644882440567017, "learning_rate": 2.6151018478817584e-05, "loss": 0.49633336067199707, "step": 450930 }, { "epoch": 2.680481005284401, "grad_norm": 1.0932648181915283, "learning_rate": 2.61487569515391e-05, "loss": 0.463408374786377, "step": 450940 }, { "epoch": 2.680540447361069, "grad_norm": 1.3078519105911255, "learning_rate": 2.6146495825377575e-05, "loss": 0.46403136253356936, "step": 450950 }, { "epoch": 2.6805998894377376, "grad_norm": 1.1793715953826904, "learning_rate": 2.6144235100343804e-05, "loss": 0.4947651863098145, "step": 450960 }, { "epoch": 2.6806593315144056, "grad_norm": 1.13643479347229, "learning_rate": 2.6141974776448615e-05, "loss": 0.4867081165313721, "step": 450970 }, { "epoch": 2.680718773591074, "grad_norm": 1.1352580785751343, "learning_rate": 2.6139714853702808e-05, "loss": 0.4301887512207031, "step": 450980 }, { "epoch": 2.6807782156677424, "grad_norm": 1.4529415369033813, "learning_rate": 2.61374553321172e-05, "loss": 0.44336953163146975, "step": 450990 }, { "epoch": 2.680837657744411, "grad_norm": 1.2607028484344482, "learning_rate": 2.61351962117026e-05, "loss": 0.4476937294006348, "step": 451000 }, { "epoch": 2.6808970998210793, "grad_norm": 1.5305722951889038, "learning_rate": 2.61329374924698e-05, "loss": 0.4830368995666504, "step": 451010 }, { "epoch": 2.6809565418977477, "grad_norm": 1.31353759765625, "learning_rate": 2.613067917442963e-05, "loss": 0.46291460990905764, "step": 451020 }, { "epoch": 2.681015983974416, "grad_norm": 1.3983652591705322, "learning_rate": 2.612842125759289e-05, "loss": 0.45414299964904786, "step": 451030 }, { "epoch": 2.6810754260510845, "grad_norm": 1.39352285861969, "learning_rate": 2.612616374197036e-05, "loss": 0.47122716903686523, "step": 451040 }, { "epoch": 2.681134868127753, "grad_norm": 1.1619563102722168, "learning_rate": 2.6123906627572862e-05, "loss": 0.4799817562103271, "step": 451050 }, { "epoch": 2.6811943102044213, "grad_norm": 1.2925145626068115, "learning_rate": 2.6121649914411184e-05, "loss": 0.4825868606567383, "step": 451060 }, { "epoch": 2.6812537522810898, "grad_norm": 1.5344170331954956, "learning_rate": 2.6119393602496108e-05, "loss": 0.47344627380371096, "step": 451070 }, { "epoch": 2.681313194357758, "grad_norm": 1.329796314239502, "learning_rate": 2.611713769183845e-05, "loss": 0.4726106643676758, "step": 451080 }, { "epoch": 2.6813726364344266, "grad_norm": 1.1156587600708008, "learning_rate": 2.611488218244899e-05, "loss": 0.4844038009643555, "step": 451090 }, { "epoch": 2.681432078511095, "grad_norm": 1.0286818742752075, "learning_rate": 2.611262707433854e-05, "loss": 0.5041657447814941, "step": 451100 }, { "epoch": 2.6814915205877634, "grad_norm": 0.9792787432670593, "learning_rate": 2.611037236751783e-05, "loss": 0.42868738174438475, "step": 451110 }, { "epoch": 2.6815509626644314, "grad_norm": 1.3536404371261597, "learning_rate": 2.6108118061997707e-05, "loss": 0.48074021339416506, "step": 451120 }, { "epoch": 2.6816104047411002, "grad_norm": 1.440329670906067, "learning_rate": 2.6105864157788928e-05, "loss": 0.4798147201538086, "step": 451130 }, { "epoch": 2.681669846817768, "grad_norm": 1.4199330806732178, "learning_rate": 2.6103610654902262e-05, "loss": 0.5009048461914063, "step": 451140 }, { "epoch": 2.681729288894437, "grad_norm": 1.23127281665802, "learning_rate": 2.610135755334852e-05, "loss": 0.47999186515808107, "step": 451150 }, { "epoch": 2.681788730971105, "grad_norm": 1.3608952760696411, "learning_rate": 2.6099104853138483e-05, "loss": 0.4405332565307617, "step": 451160 }, { "epoch": 2.6818481730477735, "grad_norm": 1.1497150659561157, "learning_rate": 2.609685255428288e-05, "loss": 0.4660470962524414, "step": 451170 }, { "epoch": 2.681907615124442, "grad_norm": 1.2608617544174194, "learning_rate": 2.609460065679252e-05, "loss": 0.4705066680908203, "step": 451180 }, { "epoch": 2.6819670572011103, "grad_norm": 1.2364097833633423, "learning_rate": 2.6092349160678188e-05, "loss": 0.46880474090576174, "step": 451190 }, { "epoch": 2.6820264992777787, "grad_norm": 1.190737247467041, "learning_rate": 2.6090098065950603e-05, "loss": 0.4786280632019043, "step": 451200 }, { "epoch": 2.682085941354447, "grad_norm": 1.1911230087280273, "learning_rate": 2.6087847372620595e-05, "loss": 0.4359130859375, "step": 451210 }, { "epoch": 2.6821453834311155, "grad_norm": 1.2488670349121094, "learning_rate": 2.6085597080698904e-05, "loss": 0.4317265510559082, "step": 451220 }, { "epoch": 2.682204825507784, "grad_norm": 1.3081644773483276, "learning_rate": 2.6083347190196288e-05, "loss": 0.4487712860107422, "step": 451230 }, { "epoch": 2.6822642675844524, "grad_norm": 1.346808671951294, "learning_rate": 2.608109770112349e-05, "loss": 0.45118937492370603, "step": 451240 }, { "epoch": 2.6823237096611208, "grad_norm": 1.0513008832931519, "learning_rate": 2.607884861349132e-05, "loss": 0.48096046447753904, "step": 451250 }, { "epoch": 2.682383151737789, "grad_norm": 1.5214186906814575, "learning_rate": 2.607659992731051e-05, "loss": 0.4947634220123291, "step": 451260 }, { "epoch": 2.6824425938144576, "grad_norm": 1.1452287435531616, "learning_rate": 2.607435164259181e-05, "loss": 0.44526185989379885, "step": 451270 }, { "epoch": 2.682502035891126, "grad_norm": 0.9604442119598389, "learning_rate": 2.6072103759346005e-05, "loss": 0.42505674362182616, "step": 451280 }, { "epoch": 2.6825614779677944, "grad_norm": 1.330807089805603, "learning_rate": 2.606985627758381e-05, "loss": 0.46872849464416505, "step": 451290 }, { "epoch": 2.682620920044463, "grad_norm": 1.3329787254333496, "learning_rate": 2.6067609197315995e-05, "loss": 0.4535043716430664, "step": 451300 }, { "epoch": 2.682680362121131, "grad_norm": 1.2152676582336426, "learning_rate": 2.6065362518553315e-05, "loss": 0.4856427192687988, "step": 451310 }, { "epoch": 2.6827398041977997, "grad_norm": 1.3989431858062744, "learning_rate": 2.6063116241306505e-05, "loss": 0.48503313064575193, "step": 451320 }, { "epoch": 2.6827992462744676, "grad_norm": 1.4150179624557495, "learning_rate": 2.6060870365586316e-05, "loss": 0.5113207817077636, "step": 451330 }, { "epoch": 2.6828586883511365, "grad_norm": 1.3732510805130005, "learning_rate": 2.6058624891403505e-05, "loss": 0.44922504425048826, "step": 451340 }, { "epoch": 2.6829181304278045, "grad_norm": 1.4886635541915894, "learning_rate": 2.6056379818768782e-05, "loss": 0.48084716796875, "step": 451350 }, { "epoch": 2.682977572504473, "grad_norm": 1.4027196168899536, "learning_rate": 2.605413514769292e-05, "loss": 0.45438084602355955, "step": 451360 }, { "epoch": 2.6830370145811413, "grad_norm": 1.5340907573699951, "learning_rate": 2.605189087818662e-05, "loss": 0.46608891487121584, "step": 451370 }, { "epoch": 2.6830964566578097, "grad_norm": 1.5560318231582642, "learning_rate": 2.6049647010260653e-05, "loss": 0.4730510711669922, "step": 451380 }, { "epoch": 2.683155898734478, "grad_norm": 1.3733227252960205, "learning_rate": 2.6047403543925747e-05, "loss": 0.46656179428100586, "step": 451390 }, { "epoch": 2.6832153408111465, "grad_norm": 1.440019130706787, "learning_rate": 2.604516047919262e-05, "loss": 0.550218915939331, "step": 451400 }, { "epoch": 2.683274782887815, "grad_norm": 1.27674400806427, "learning_rate": 2.604291781607201e-05, "loss": 0.4554577827453613, "step": 451410 }, { "epoch": 2.6833342249644834, "grad_norm": 1.4380863904953003, "learning_rate": 2.6040675554574634e-05, "loss": 0.51903395652771, "step": 451420 }, { "epoch": 2.683393667041152, "grad_norm": 1.4291476011276245, "learning_rate": 2.6038433694711224e-05, "loss": 0.44591007232666013, "step": 451430 }, { "epoch": 2.68345310911782, "grad_norm": 1.3576728105545044, "learning_rate": 2.6036192236492525e-05, "loss": 0.42993721961975095, "step": 451440 }, { "epoch": 2.6835125511944886, "grad_norm": 1.2827460765838623, "learning_rate": 2.603395117992924e-05, "loss": 0.46939549446105955, "step": 451450 }, { "epoch": 2.683571993271157, "grad_norm": 0.9474166631698608, "learning_rate": 2.6031710525032082e-05, "loss": 0.4473560333251953, "step": 451460 }, { "epoch": 2.6836314353478254, "grad_norm": 1.4793508052825928, "learning_rate": 2.6029470271811795e-05, "loss": 0.4687464714050293, "step": 451470 }, { "epoch": 2.683690877424494, "grad_norm": 0.9842312932014465, "learning_rate": 2.6027230420279076e-05, "loss": 0.5198240280151367, "step": 451480 }, { "epoch": 2.6837503195011623, "grad_norm": 1.7166229486465454, "learning_rate": 2.602499097044464e-05, "loss": 0.519596529006958, "step": 451490 }, { "epoch": 2.6838097615778302, "grad_norm": 1.077549934387207, "learning_rate": 2.6022751922319194e-05, "loss": 0.439207124710083, "step": 451500 }, { "epoch": 2.683869203654499, "grad_norm": 2.0720889568328857, "learning_rate": 2.6020513275913473e-05, "loss": 0.48321046829223635, "step": 451510 }, { "epoch": 2.683928645731167, "grad_norm": 1.4033269882202148, "learning_rate": 2.6018275031238165e-05, "loss": 0.4781040191650391, "step": 451520 }, { "epoch": 2.683988087807836, "grad_norm": 1.435052514076233, "learning_rate": 2.6016037188303994e-05, "loss": 0.4817760944366455, "step": 451530 }, { "epoch": 2.684047529884504, "grad_norm": 1.4239540100097656, "learning_rate": 2.6013799747121642e-05, "loss": 0.4827871322631836, "step": 451540 }, { "epoch": 2.6841069719611723, "grad_norm": 1.1429647207260132, "learning_rate": 2.6011562707701838e-05, "loss": 0.456726598739624, "step": 451550 }, { "epoch": 2.6841664140378407, "grad_norm": 1.1625484228134155, "learning_rate": 2.6009326070055245e-05, "loss": 0.4684173583984375, "step": 451560 }, { "epoch": 2.684225856114509, "grad_norm": 1.2821323871612549, "learning_rate": 2.600708983419261e-05, "loss": 0.47220191955566404, "step": 451570 }, { "epoch": 2.6842852981911776, "grad_norm": 1.4733343124389648, "learning_rate": 2.6004854000124605e-05, "loss": 0.5050004482269287, "step": 451580 }, { "epoch": 2.684344740267846, "grad_norm": 1.1425845623016357, "learning_rate": 2.6002618567861936e-05, "loss": 0.49216156005859374, "step": 451590 }, { "epoch": 2.6844041823445144, "grad_norm": 1.2259982824325562, "learning_rate": 2.600038353741527e-05, "loss": 0.47704548835754396, "step": 451600 }, { "epoch": 2.684463624421183, "grad_norm": 1.6452648639678955, "learning_rate": 2.5998148908795333e-05, "loss": 0.4858257293701172, "step": 451610 }, { "epoch": 2.684523066497851, "grad_norm": 1.0835281610488892, "learning_rate": 2.599591468201279e-05, "loss": 0.45906887054443357, "step": 451620 }, { "epoch": 2.6845825085745196, "grad_norm": 1.139237642288208, "learning_rate": 2.5993680857078335e-05, "loss": 0.43657584190368653, "step": 451630 }, { "epoch": 2.684641950651188, "grad_norm": 1.3275785446166992, "learning_rate": 2.599144743400266e-05, "loss": 0.5272433280944824, "step": 451640 }, { "epoch": 2.6847013927278565, "grad_norm": 1.3950711488723755, "learning_rate": 2.5989214412796476e-05, "loss": 0.4938446044921875, "step": 451650 }, { "epoch": 2.684760834804525, "grad_norm": 1.1953736543655396, "learning_rate": 2.5986981793470394e-05, "loss": 0.4313354015350342, "step": 451660 }, { "epoch": 2.684820276881193, "grad_norm": 1.5047931671142578, "learning_rate": 2.598474957603515e-05, "loss": 0.48684191703796387, "step": 451670 }, { "epoch": 2.6848797189578617, "grad_norm": 1.5730735063552856, "learning_rate": 2.5982517760501417e-05, "loss": 0.508869981765747, "step": 451680 }, { "epoch": 2.6849391610345297, "grad_norm": 1.1698211431503296, "learning_rate": 2.598028634687984e-05, "loss": 0.4609023094177246, "step": 451690 }, { "epoch": 2.6849986031111985, "grad_norm": 1.2038847208023071, "learning_rate": 2.5978055335181123e-05, "loss": 0.4100489616394043, "step": 451700 }, { "epoch": 2.6850580451878665, "grad_norm": 1.5235612392425537, "learning_rate": 2.597582472541596e-05, "loss": 0.48801383972167967, "step": 451710 }, { "epoch": 2.685117487264535, "grad_norm": 1.2195957899093628, "learning_rate": 2.5973594517594968e-05, "loss": 0.4582679748535156, "step": 451720 }, { "epoch": 2.6851769293412033, "grad_norm": 1.135144829750061, "learning_rate": 2.597136471172883e-05, "loss": 0.4534721374511719, "step": 451730 }, { "epoch": 2.6852363714178717, "grad_norm": 1.3022816181182861, "learning_rate": 2.596913530782823e-05, "loss": 0.49576468467712403, "step": 451740 }, { "epoch": 2.68529581349454, "grad_norm": 1.3713161945343018, "learning_rate": 2.596690630590383e-05, "loss": 0.4840208053588867, "step": 451750 }, { "epoch": 2.6853552555712086, "grad_norm": 1.158323049545288, "learning_rate": 2.5964677705966274e-05, "loss": 0.4633770942687988, "step": 451760 }, { "epoch": 2.685414697647877, "grad_norm": 1.4761409759521484, "learning_rate": 2.5962449508026267e-05, "loss": 0.4841853141784668, "step": 451770 }, { "epoch": 2.6854741397245454, "grad_norm": 1.4756240844726562, "learning_rate": 2.5960221712094422e-05, "loss": 0.4501218795776367, "step": 451780 }, { "epoch": 2.685533581801214, "grad_norm": 1.1990970373153687, "learning_rate": 2.595799431818139e-05, "loss": 0.4552361011505127, "step": 451790 }, { "epoch": 2.6855930238778822, "grad_norm": 1.4898182153701782, "learning_rate": 2.5955767326297874e-05, "loss": 0.46866416931152344, "step": 451800 }, { "epoch": 2.6856524659545506, "grad_norm": 1.2803082466125488, "learning_rate": 2.5953540736454494e-05, "loss": 0.45674972534179686, "step": 451810 }, { "epoch": 2.685711908031219, "grad_norm": 1.3781814575195312, "learning_rate": 2.595131454866191e-05, "loss": 0.49807229042053225, "step": 451820 }, { "epoch": 2.6857713501078875, "grad_norm": 1.3409390449523926, "learning_rate": 2.5949088762930774e-05, "loss": 0.4463957786560059, "step": 451830 }, { "epoch": 2.685830792184556, "grad_norm": 1.2122095823287964, "learning_rate": 2.5946863379271724e-05, "loss": 0.4446282386779785, "step": 451840 }, { "epoch": 2.6858902342612243, "grad_norm": 1.0444486141204834, "learning_rate": 2.594463839769541e-05, "loss": 0.47806410789489745, "step": 451850 }, { "epoch": 2.6859496763378923, "grad_norm": 1.2504242658615112, "learning_rate": 2.5942413818212468e-05, "loss": 0.4606772899627686, "step": 451860 }, { "epoch": 2.686009118414561, "grad_norm": 1.5136139392852783, "learning_rate": 2.5940189640833557e-05, "loss": 0.46347522735595703, "step": 451870 }, { "epoch": 2.686068560491229, "grad_norm": 1.4233300685882568, "learning_rate": 2.5937965865569303e-05, "loss": 0.5018983364105225, "step": 451880 }, { "epoch": 2.686128002567898, "grad_norm": 1.2323397397994995, "learning_rate": 2.5935742492430354e-05, "loss": 0.4840245246887207, "step": 451890 }, { "epoch": 2.686187444644566, "grad_norm": 1.3487110137939453, "learning_rate": 2.5933519521427353e-05, "loss": 0.4633461952209473, "step": 451900 }, { "epoch": 2.6862468867212344, "grad_norm": 1.412719964981079, "learning_rate": 2.59312969525709e-05, "loss": 0.44760851860046386, "step": 451910 }, { "epoch": 2.6863063287979028, "grad_norm": 1.5716743469238281, "learning_rate": 2.5929074785871643e-05, "loss": 0.4696837902069092, "step": 451920 }, { "epoch": 2.686365770874571, "grad_norm": 1.4669843912124634, "learning_rate": 2.5926853021340242e-05, "loss": 0.48223514556884767, "step": 451930 }, { "epoch": 2.6864252129512396, "grad_norm": 1.5960159301757812, "learning_rate": 2.5924631658987287e-05, "loss": 0.49150733947753905, "step": 451940 }, { "epoch": 2.686484655027908, "grad_norm": 1.4889967441558838, "learning_rate": 2.5922410698823417e-05, "loss": 0.4513411521911621, "step": 451950 }, { "epoch": 2.6865440971045764, "grad_norm": 1.53275728225708, "learning_rate": 2.5920190140859264e-05, "loss": 0.4434720516204834, "step": 451960 }, { "epoch": 2.686603539181245, "grad_norm": 1.2252228260040283, "learning_rate": 2.5917969985105443e-05, "loss": 0.5193184852600098, "step": 451970 }, { "epoch": 2.6866629812579133, "grad_norm": 1.5434401035308838, "learning_rate": 2.5915750231572574e-05, "loss": 0.5156856536865234, "step": 451980 }, { "epoch": 2.6867224233345817, "grad_norm": 1.1340980529785156, "learning_rate": 2.5913530880271263e-05, "loss": 0.5035488128662109, "step": 451990 }, { "epoch": 2.68678186541125, "grad_norm": 1.1965715885162354, "learning_rate": 2.5911311931212156e-05, "loss": 0.44350624084472656, "step": 452000 }, { "epoch": 2.6868413074879185, "grad_norm": 1.2475277185440063, "learning_rate": 2.5909093384405852e-05, "loss": 0.45966453552246095, "step": 452010 }, { "epoch": 2.686900749564587, "grad_norm": 1.5855685472488403, "learning_rate": 2.590687523986296e-05, "loss": 0.4166085243225098, "step": 452020 }, { "epoch": 2.6869601916412553, "grad_norm": 1.379317045211792, "learning_rate": 2.5904657497594104e-05, "loss": 0.44341120719909666, "step": 452030 }, { "epoch": 2.6870196337179237, "grad_norm": 1.3265541791915894, "learning_rate": 2.590244015760987e-05, "loss": 0.5347114562988281, "step": 452040 }, { "epoch": 2.6870790757945917, "grad_norm": 1.3811051845550537, "learning_rate": 2.5900223219920872e-05, "loss": 0.42690486907958985, "step": 452050 }, { "epoch": 2.6871385178712606, "grad_norm": 1.450747013092041, "learning_rate": 2.5898006684537745e-05, "loss": 0.4463838577270508, "step": 452060 }, { "epoch": 2.6871979599479285, "grad_norm": 1.4379644393920898, "learning_rate": 2.589579055147106e-05, "loss": 0.4577309608459473, "step": 452070 }, { "epoch": 2.6872574020245974, "grad_norm": 1.2747365236282349, "learning_rate": 2.5893574820731427e-05, "loss": 0.4515800952911377, "step": 452080 }, { "epoch": 2.6873168441012654, "grad_norm": 1.202620267868042, "learning_rate": 2.5891359492329442e-05, "loss": 0.4416921615600586, "step": 452090 }, { "epoch": 2.687376286177934, "grad_norm": 1.4856065511703491, "learning_rate": 2.5889144566275714e-05, "loss": 0.49182605743408203, "step": 452100 }, { "epoch": 2.687435728254602, "grad_norm": 1.4525583982467651, "learning_rate": 2.588693004258083e-05, "loss": 0.49844942092895506, "step": 452110 }, { "epoch": 2.6874951703312706, "grad_norm": 1.3128221035003662, "learning_rate": 2.588471592125537e-05, "loss": 0.4441819190979004, "step": 452120 }, { "epoch": 2.687554612407939, "grad_norm": 1.3635671138763428, "learning_rate": 2.5882502202309944e-05, "loss": 0.4895779609680176, "step": 452130 }, { "epoch": 2.6876140544846074, "grad_norm": 1.4183648824691772, "learning_rate": 2.588028888575516e-05, "loss": 0.5077995300292969, "step": 452140 }, { "epoch": 2.687673496561276, "grad_norm": 1.2551543712615967, "learning_rate": 2.5878075971601563e-05, "loss": 0.4274930953979492, "step": 452150 }, { "epoch": 2.6877329386379443, "grad_norm": 1.1706222295761108, "learning_rate": 2.587586345985976e-05, "loss": 0.4234048366546631, "step": 452160 }, { "epoch": 2.6877923807146127, "grad_norm": 1.3879690170288086, "learning_rate": 2.587365135054034e-05, "loss": 0.4758278846740723, "step": 452170 }, { "epoch": 2.687851822791281, "grad_norm": 1.0165075063705444, "learning_rate": 2.5871439643653866e-05, "loss": 0.44251203536987305, "step": 452180 }, { "epoch": 2.6879112648679495, "grad_norm": 1.1912943124771118, "learning_rate": 2.5869228339210945e-05, "loss": 0.45027809143066405, "step": 452190 }, { "epoch": 2.687970706944618, "grad_norm": 1.3378291130065918, "learning_rate": 2.5867017437222156e-05, "loss": 0.46024017333984374, "step": 452200 }, { "epoch": 2.6880301490212863, "grad_norm": 1.2504302263259888, "learning_rate": 2.586480693769804e-05, "loss": 0.4674367904663086, "step": 452210 }, { "epoch": 2.6880895910979548, "grad_norm": 1.114378571510315, "learning_rate": 2.586259684064919e-05, "loss": 0.42681541442871096, "step": 452220 }, { "epoch": 2.688149033174623, "grad_norm": 1.5820980072021484, "learning_rate": 2.5860387146086185e-05, "loss": 0.5058423519134522, "step": 452230 }, { "epoch": 2.688208475251291, "grad_norm": 1.2784926891326904, "learning_rate": 2.5858177854019593e-05, "loss": 0.45436553955078124, "step": 452240 }, { "epoch": 2.68826791732796, "grad_norm": 1.1771478652954102, "learning_rate": 2.5855968964459957e-05, "loss": 0.5134278297424316, "step": 452250 }, { "epoch": 2.688327359404628, "grad_norm": 1.3965743780136108, "learning_rate": 2.5853760477417903e-05, "loss": 0.4504913330078125, "step": 452260 }, { "epoch": 2.6883868014812964, "grad_norm": 1.125372290611267, "learning_rate": 2.5851552392903954e-05, "loss": 0.44384050369262695, "step": 452270 }, { "epoch": 2.688446243557965, "grad_norm": 1.357954740524292, "learning_rate": 2.584934471092865e-05, "loss": 0.4669018268585205, "step": 452280 }, { "epoch": 2.688505685634633, "grad_norm": 1.5069575309753418, "learning_rate": 2.5847137431502605e-05, "loss": 0.4858833312988281, "step": 452290 }, { "epoch": 2.6885651277113016, "grad_norm": 1.5847609043121338, "learning_rate": 2.5844930554636353e-05, "loss": 0.432247257232666, "step": 452300 }, { "epoch": 2.68862456978797, "grad_norm": 1.4705485105514526, "learning_rate": 2.5842724080340443e-05, "loss": 0.5110576152801514, "step": 452310 }, { "epoch": 2.6886840118646385, "grad_norm": 1.6405683755874634, "learning_rate": 2.584051800862545e-05, "loss": 0.5091698646545411, "step": 452320 }, { "epoch": 2.688743453941307, "grad_norm": 1.7121772766113281, "learning_rate": 2.5838312339501904e-05, "loss": 0.4294304847717285, "step": 452330 }, { "epoch": 2.6888028960179753, "grad_norm": 1.4185844659805298, "learning_rate": 2.583610707298037e-05, "loss": 0.4969164848327637, "step": 452340 }, { "epoch": 2.6888623380946437, "grad_norm": 1.69602370262146, "learning_rate": 2.5833902209071376e-05, "loss": 0.486415958404541, "step": 452350 }, { "epoch": 2.688921780171312, "grad_norm": 1.3905417919158936, "learning_rate": 2.583169774778551e-05, "loss": 0.4570174694061279, "step": 452360 }, { "epoch": 2.6889812222479805, "grad_norm": 1.2943305969238281, "learning_rate": 2.5829493689133295e-05, "loss": 0.47921075820922854, "step": 452370 }, { "epoch": 2.689040664324649, "grad_norm": 1.1375693082809448, "learning_rate": 2.5827290033125272e-05, "loss": 0.45418362617492675, "step": 452380 }, { "epoch": 2.6891001064013174, "grad_norm": 1.1415886878967285, "learning_rate": 2.5825086779771985e-05, "loss": 0.4711954593658447, "step": 452390 }, { "epoch": 2.6891595484779858, "grad_norm": 1.365817904472351, "learning_rate": 2.582288392908398e-05, "loss": 0.4775360107421875, "step": 452400 }, { "epoch": 2.6892189905546537, "grad_norm": 1.3502627611160278, "learning_rate": 2.5820681481071762e-05, "loss": 0.45771484375, "step": 452410 }, { "epoch": 2.6892784326313226, "grad_norm": 1.3857017755508423, "learning_rate": 2.5818479435745925e-05, "loss": 0.4433861255645752, "step": 452420 }, { "epoch": 2.6893378747079906, "grad_norm": 1.198142647743225, "learning_rate": 2.5816277793116965e-05, "loss": 0.457032585144043, "step": 452430 }, { "epoch": 2.6893973167846594, "grad_norm": 1.4068329334259033, "learning_rate": 2.5814076553195414e-05, "loss": 0.46089019775390627, "step": 452440 }, { "epoch": 2.6894567588613274, "grad_norm": 1.1460299491882324, "learning_rate": 2.581187571599181e-05, "loss": 0.47515525817871096, "step": 452450 }, { "epoch": 2.689516200937996, "grad_norm": 1.7099900245666504, "learning_rate": 2.580967528151668e-05, "loss": 0.45838279724121095, "step": 452460 }, { "epoch": 2.6895756430146642, "grad_norm": 1.1198734045028687, "learning_rate": 2.5807475249780555e-05, "loss": 0.48917350769042967, "step": 452470 }, { "epoch": 2.6896350850913326, "grad_norm": 1.1556514501571655, "learning_rate": 2.580527562079394e-05, "loss": 0.4776289463043213, "step": 452480 }, { "epoch": 2.689694527168001, "grad_norm": 1.1075390577316284, "learning_rate": 2.5803076394567383e-05, "loss": 0.43429765701293943, "step": 452490 }, { "epoch": 2.6897539692446695, "grad_norm": 1.272009253501892, "learning_rate": 2.5800877571111388e-05, "loss": 0.44219651222229006, "step": 452500 }, { "epoch": 2.689813411321338, "grad_norm": 1.2151974439620972, "learning_rate": 2.5798679150436484e-05, "loss": 0.4612231731414795, "step": 452510 }, { "epoch": 2.6898728533980063, "grad_norm": 1.7354744672775269, "learning_rate": 2.579648113255318e-05, "loss": 0.515207576751709, "step": 452520 }, { "epoch": 2.6899322954746747, "grad_norm": 0.7556231617927551, "learning_rate": 2.579428351747199e-05, "loss": 0.45005478858947756, "step": 452530 }, { "epoch": 2.689991737551343, "grad_norm": 1.2218472957611084, "learning_rate": 2.579208630520342e-05, "loss": 0.4880682945251465, "step": 452540 }, { "epoch": 2.6900511796280115, "grad_norm": 1.3896923065185547, "learning_rate": 2.5789889495757998e-05, "loss": 0.43718819618225097, "step": 452550 }, { "epoch": 2.69011062170468, "grad_norm": 1.3335214853286743, "learning_rate": 2.578769308914623e-05, "loss": 0.435986328125, "step": 452560 }, { "epoch": 2.6901700637813484, "grad_norm": 1.4913092851638794, "learning_rate": 2.578549708537861e-05, "loss": 0.5160750389099121, "step": 452570 }, { "epoch": 2.690229505858017, "grad_norm": 1.3401529788970947, "learning_rate": 2.578330148446566e-05, "loss": 0.4295044422149658, "step": 452580 }, { "epoch": 2.690288947934685, "grad_norm": 1.4820877313613892, "learning_rate": 2.578110628641787e-05, "loss": 0.4325456142425537, "step": 452590 }, { "epoch": 2.690348390011353, "grad_norm": 1.3364869356155396, "learning_rate": 2.5778911491245738e-05, "loss": 0.46303930282592776, "step": 452600 }, { "epoch": 2.690407832088022, "grad_norm": 1.552706241607666, "learning_rate": 2.5776717098959764e-05, "loss": 0.5285577297210693, "step": 452610 }, { "epoch": 2.69046727416469, "grad_norm": 1.4509789943695068, "learning_rate": 2.577452310957046e-05, "loss": 0.5228986263275146, "step": 452620 }, { "epoch": 2.690526716241359, "grad_norm": 1.111039161682129, "learning_rate": 2.5772329523088314e-05, "loss": 0.4819628715515137, "step": 452630 }, { "epoch": 2.690586158318027, "grad_norm": 1.5741629600524902, "learning_rate": 2.5770136339523813e-05, "loss": 0.5281274318695068, "step": 452640 }, { "epoch": 2.6906456003946952, "grad_norm": 1.3739821910858154, "learning_rate": 2.5767943558887465e-05, "loss": 0.4986612319946289, "step": 452650 }, { "epoch": 2.6907050424713637, "grad_norm": 1.5424909591674805, "learning_rate": 2.576575118118974e-05, "loss": 0.5005172252655029, "step": 452660 }, { "epoch": 2.690764484548032, "grad_norm": 1.7428616285324097, "learning_rate": 2.576355920644113e-05, "loss": 0.4771729946136475, "step": 452670 }, { "epoch": 2.6908239266247005, "grad_norm": 1.4093295335769653, "learning_rate": 2.5761367634652118e-05, "loss": 0.49047174453735354, "step": 452680 }, { "epoch": 2.690883368701369, "grad_norm": 1.6370209455490112, "learning_rate": 2.5759176465833196e-05, "loss": 0.5204571723937989, "step": 452690 }, { "epoch": 2.6909428107780373, "grad_norm": 1.3480796813964844, "learning_rate": 2.5756985699994868e-05, "loss": 0.4688433647155762, "step": 452700 }, { "epoch": 2.6910022528547057, "grad_norm": 1.163195013999939, "learning_rate": 2.575479533714756e-05, "loss": 0.46458001136779786, "step": 452710 }, { "epoch": 2.691061694931374, "grad_norm": 1.438586950302124, "learning_rate": 2.5752605377301792e-05, "loss": 0.4522427558898926, "step": 452720 }, { "epoch": 2.6911211370080426, "grad_norm": 1.0535081624984741, "learning_rate": 2.5750415820468033e-05, "loss": 0.49631175994873045, "step": 452730 }, { "epoch": 2.691180579084711, "grad_norm": 1.4249703884124756, "learning_rate": 2.5748226666656722e-05, "loss": 0.4742129325866699, "step": 452740 }, { "epoch": 2.6912400211613794, "grad_norm": 1.129225492477417, "learning_rate": 2.57460379158784e-05, "loss": 0.48161773681640624, "step": 452750 }, { "epoch": 2.691299463238048, "grad_norm": 1.0358948707580566, "learning_rate": 2.574384956814348e-05, "loss": 0.48651537895202634, "step": 452760 }, { "epoch": 2.691358905314716, "grad_norm": 1.1758780479431152, "learning_rate": 2.5741661623462437e-05, "loss": 0.42995643615722656, "step": 452770 }, { "epoch": 2.6914183473913846, "grad_norm": 1.7056621313095093, "learning_rate": 2.573947408184577e-05, "loss": 0.5255972385406494, "step": 452780 }, { "epoch": 2.6914777894680526, "grad_norm": 1.4875001907348633, "learning_rate": 2.5737286943303914e-05, "loss": 0.46140470504760744, "step": 452790 }, { "epoch": 2.6915372315447215, "grad_norm": 1.9852138757705688, "learning_rate": 2.5735100207847347e-05, "loss": 0.4794334411621094, "step": 452800 }, { "epoch": 2.6915966736213894, "grad_norm": 1.4446086883544922, "learning_rate": 2.573291387548651e-05, "loss": 0.46802444458007814, "step": 452810 }, { "epoch": 2.6916561156980583, "grad_norm": 1.2908892631530762, "learning_rate": 2.5730727946231887e-05, "loss": 0.45261049270629883, "step": 452820 }, { "epoch": 2.6917155577747263, "grad_norm": 1.262316107749939, "learning_rate": 2.572854242009391e-05, "loss": 0.5255807876586914, "step": 452830 }, { "epoch": 2.6917749998513947, "grad_norm": 1.1885883808135986, "learning_rate": 2.5726357297083037e-05, "loss": 0.4613502979278564, "step": 452840 }, { "epoch": 2.691834441928063, "grad_norm": 1.135878562927246, "learning_rate": 2.572417257720974e-05, "loss": 0.4332341194152832, "step": 452850 }, { "epoch": 2.6918938840047315, "grad_norm": 0.9472153782844543, "learning_rate": 2.572198826048447e-05, "loss": 0.4010158538818359, "step": 452860 }, { "epoch": 2.6919533260814, "grad_norm": 1.4172487258911133, "learning_rate": 2.571980434691766e-05, "loss": 0.47870492935180664, "step": 452870 }, { "epoch": 2.6920127681580683, "grad_norm": 1.597595453262329, "learning_rate": 2.5717620836519758e-05, "loss": 0.4718008041381836, "step": 452880 }, { "epoch": 2.6920722102347368, "grad_norm": 1.5275174379348755, "learning_rate": 2.5715437729301228e-05, "loss": 0.502403736114502, "step": 452890 }, { "epoch": 2.692131652311405, "grad_norm": 1.5141761302947998, "learning_rate": 2.571325502527247e-05, "loss": 0.46470155715942385, "step": 452900 }, { "epoch": 2.6921910943880736, "grad_norm": 1.4330960512161255, "learning_rate": 2.5711072724443985e-05, "loss": 0.48241658210754396, "step": 452910 }, { "epoch": 2.692250536464742, "grad_norm": 1.4547200202941895, "learning_rate": 2.570889082682616e-05, "loss": 0.4736884117126465, "step": 452920 }, { "epoch": 2.6923099785414104, "grad_norm": 1.1193634271621704, "learning_rate": 2.5706709332429478e-05, "loss": 0.4412380218505859, "step": 452930 }, { "epoch": 2.692369420618079, "grad_norm": 1.2198158502578735, "learning_rate": 2.5704528241264342e-05, "loss": 0.41799263954162597, "step": 452940 }, { "epoch": 2.6924288626947472, "grad_norm": 1.2376755475997925, "learning_rate": 2.5702347553341184e-05, "loss": 0.47571096420288084, "step": 452950 }, { "epoch": 2.6924883047714157, "grad_norm": 1.681565523147583, "learning_rate": 2.570016726867046e-05, "loss": 0.49970269203186035, "step": 452960 }, { "epoch": 2.692547746848084, "grad_norm": 1.1414796113967896, "learning_rate": 2.5697987387262567e-05, "loss": 0.44399056434631345, "step": 452970 }, { "epoch": 2.692607188924752, "grad_norm": 1.2332308292388916, "learning_rate": 2.569580790912797e-05, "loss": 0.436186408996582, "step": 452980 }, { "epoch": 2.692666631001421, "grad_norm": 1.0243350267410278, "learning_rate": 2.5693628834277065e-05, "loss": 0.4355198860168457, "step": 452990 }, { "epoch": 2.692726073078089, "grad_norm": 1.5259771347045898, "learning_rate": 2.5691450162720304e-05, "loss": 0.4505523681640625, "step": 453000 }, { "epoch": 2.6927855151547573, "grad_norm": 1.3822776079177856, "learning_rate": 2.5689271894468092e-05, "loss": 0.48906764984130857, "step": 453010 }, { "epoch": 2.6928449572314257, "grad_norm": 1.4338926076889038, "learning_rate": 2.568709402953084e-05, "loss": 0.5367963790893555, "step": 453020 }, { "epoch": 2.692904399308094, "grad_norm": 1.0587060451507568, "learning_rate": 2.568491656791897e-05, "loss": 0.4608654022216797, "step": 453030 }, { "epoch": 2.6929638413847625, "grad_norm": 1.263969898223877, "learning_rate": 2.5682739509642906e-05, "loss": 0.44887890815734866, "step": 453040 }, { "epoch": 2.693023283461431, "grad_norm": 1.2059500217437744, "learning_rate": 2.5680562854713082e-05, "loss": 0.4691037654876709, "step": 453050 }, { "epoch": 2.6930827255380994, "grad_norm": 1.5149683952331543, "learning_rate": 2.567838660313987e-05, "loss": 0.4767002105712891, "step": 453060 }, { "epoch": 2.6931421676147678, "grad_norm": 1.395613670349121, "learning_rate": 2.567621075493371e-05, "loss": 0.5385708808898926, "step": 453070 }, { "epoch": 2.693201609691436, "grad_norm": 1.2334431409835815, "learning_rate": 2.5674035310105004e-05, "loss": 0.46383137702941896, "step": 453080 }, { "epoch": 2.6932610517681046, "grad_norm": 1.381871223449707, "learning_rate": 2.567186026866415e-05, "loss": 0.48774032592773436, "step": 453090 }, { "epoch": 2.693320493844773, "grad_norm": 1.1978332996368408, "learning_rate": 2.5669685630621536e-05, "loss": 0.4666298389434814, "step": 453100 }, { "epoch": 2.6933799359214414, "grad_norm": 1.406975507736206, "learning_rate": 2.5667511395987616e-05, "loss": 0.4253091335296631, "step": 453110 }, { "epoch": 2.69343937799811, "grad_norm": 1.4815294742584229, "learning_rate": 2.566533756477275e-05, "loss": 0.43399677276611326, "step": 453120 }, { "epoch": 2.6934988200747783, "grad_norm": 1.4988123178482056, "learning_rate": 2.5663164136987356e-05, "loss": 0.5080081939697265, "step": 453130 }, { "epoch": 2.6935582621514467, "grad_norm": 1.2987197637557983, "learning_rate": 2.5660991112641808e-05, "loss": 0.45794429779052737, "step": 453140 }, { "epoch": 2.6936177042281146, "grad_norm": 1.2756770849227905, "learning_rate": 2.5658818491746528e-05, "loss": 0.4958634376525879, "step": 453150 }, { "epoch": 2.6936771463047835, "grad_norm": 1.5281071662902832, "learning_rate": 2.56566462743119e-05, "loss": 0.46690354347229, "step": 453160 }, { "epoch": 2.6937365883814515, "grad_norm": 1.3884731531143188, "learning_rate": 2.5654474460348294e-05, "loss": 0.5036163806915284, "step": 453170 }, { "epoch": 2.6937960304581203, "grad_norm": 1.636502981185913, "learning_rate": 2.5652303049866134e-05, "loss": 0.5184602260589599, "step": 453180 }, { "epoch": 2.6938554725347883, "grad_norm": 1.1951723098754883, "learning_rate": 2.5650132042875803e-05, "loss": 0.4795217990875244, "step": 453190 }, { "epoch": 2.6939149146114567, "grad_norm": 0.937197208404541, "learning_rate": 2.564796143938764e-05, "loss": 0.42716202735900877, "step": 453200 }, { "epoch": 2.693974356688125, "grad_norm": 1.6739274263381958, "learning_rate": 2.564579123941208e-05, "loss": 0.503090238571167, "step": 453210 }, { "epoch": 2.6940337987647935, "grad_norm": 1.4043757915496826, "learning_rate": 2.5643621442959502e-05, "loss": 0.4998318195343018, "step": 453220 }, { "epoch": 2.694093240841462, "grad_norm": 1.141072392463684, "learning_rate": 2.5641452050040237e-05, "loss": 0.46605396270751953, "step": 453230 }, { "epoch": 2.6941526829181304, "grad_norm": 1.2822641134262085, "learning_rate": 2.563928306066472e-05, "loss": 0.4509174346923828, "step": 453240 }, { "epoch": 2.694212124994799, "grad_norm": 0.9754449725151062, "learning_rate": 2.5637114474843327e-05, "loss": 0.43621411323547366, "step": 453250 }, { "epoch": 2.694271567071467, "grad_norm": 1.7346605062484741, "learning_rate": 2.563494629258636e-05, "loss": 0.4480288505554199, "step": 453260 }, { "epoch": 2.6943310091481356, "grad_norm": 1.4379777908325195, "learning_rate": 2.563277851390427e-05, "loss": 0.4600252151489258, "step": 453270 }, { "epoch": 2.694390451224804, "grad_norm": 1.3028385639190674, "learning_rate": 2.5630611138807387e-05, "loss": 0.482465934753418, "step": 453280 }, { "epoch": 2.6944498933014724, "grad_norm": 1.3937106132507324, "learning_rate": 2.5628444167306097e-05, "loss": 0.39998860359191896, "step": 453290 }, { "epoch": 2.694509335378141, "grad_norm": 1.2821483612060547, "learning_rate": 2.5626277599410735e-05, "loss": 0.49530420303344724, "step": 453300 }, { "epoch": 2.6945687774548093, "grad_norm": 1.3165122270584106, "learning_rate": 2.562411143513172e-05, "loss": 0.47469234466552734, "step": 453310 }, { "epoch": 2.6946282195314777, "grad_norm": 1.5486761331558228, "learning_rate": 2.562194567447936e-05, "loss": 0.47187061309814454, "step": 453320 }, { "epoch": 2.694687661608146, "grad_norm": 1.067987322807312, "learning_rate": 2.5619780317464025e-05, "loss": 0.46233301162719725, "step": 453330 }, { "epoch": 2.694747103684814, "grad_norm": 1.1491023302078247, "learning_rate": 2.561761536409611e-05, "loss": 0.4882218360900879, "step": 453340 }, { "epoch": 2.694806545761483, "grad_norm": 1.5346657037734985, "learning_rate": 2.5615450814385938e-05, "loss": 0.48372712135314944, "step": 453350 }, { "epoch": 2.694865987838151, "grad_norm": 2.0707669258117676, "learning_rate": 2.5613286668343855e-05, "loss": 0.4540562152862549, "step": 453360 }, { "epoch": 2.6949254299148198, "grad_norm": 1.452622413635254, "learning_rate": 2.5611122925980263e-05, "loss": 0.45199146270751955, "step": 453370 }, { "epoch": 2.6949848719914877, "grad_norm": 1.3548998832702637, "learning_rate": 2.5608959587305465e-05, "loss": 0.43975052833557127, "step": 453380 }, { "epoch": 2.695044314068156, "grad_norm": 1.6879167556762695, "learning_rate": 2.5606796652329813e-05, "loss": 0.4462411403656006, "step": 453390 }, { "epoch": 2.6951037561448246, "grad_norm": 1.3261204957962036, "learning_rate": 2.5604634121063677e-05, "loss": 0.48996968269348146, "step": 453400 }, { "epoch": 2.695163198221493, "grad_norm": 1.5256595611572266, "learning_rate": 2.560247199351739e-05, "loss": 0.4502309799194336, "step": 453410 }, { "epoch": 2.6952226402981614, "grad_norm": 1.3947666883468628, "learning_rate": 2.56003102697013e-05, "loss": 0.4004658699035645, "step": 453420 }, { "epoch": 2.69528208237483, "grad_norm": 0.9149662256240845, "learning_rate": 2.559814894962574e-05, "loss": 0.43482308387756347, "step": 453430 }, { "epoch": 2.695341524451498, "grad_norm": 1.3596148490905762, "learning_rate": 2.559598803330106e-05, "loss": 0.47923994064331055, "step": 453440 }, { "epoch": 2.6954009665281666, "grad_norm": 1.1147277355194092, "learning_rate": 2.559382752073758e-05, "loss": 0.3933910608291626, "step": 453450 }, { "epoch": 2.695460408604835, "grad_norm": 1.1998752355575562, "learning_rate": 2.5591667411945642e-05, "loss": 0.4558241367340088, "step": 453460 }, { "epoch": 2.6955198506815035, "grad_norm": 1.2082988023757935, "learning_rate": 2.5589507706935577e-05, "loss": 0.5237302780151367, "step": 453470 }, { "epoch": 2.695579292758172, "grad_norm": 1.5227851867675781, "learning_rate": 2.5587348405717736e-05, "loss": 0.4462860107421875, "step": 453480 }, { "epoch": 2.6956387348348403, "grad_norm": 1.4219505786895752, "learning_rate": 2.5585189508302432e-05, "loss": 0.4522359848022461, "step": 453490 }, { "epoch": 2.6956981769115087, "grad_norm": 1.5872329473495483, "learning_rate": 2.5583031014699993e-05, "loss": 0.5081031799316407, "step": 453500 }, { "epoch": 2.695757618988177, "grad_norm": 1.1959360837936401, "learning_rate": 2.5580872924920745e-05, "loss": 0.46030755043029786, "step": 453510 }, { "epoch": 2.6958170610648455, "grad_norm": 1.4447563886642456, "learning_rate": 2.5578715238975022e-05, "loss": 0.4565749168395996, "step": 453520 }, { "epoch": 2.6958765031415135, "grad_norm": 1.4823476076126099, "learning_rate": 2.5576557956873104e-05, "loss": 0.49063425064086913, "step": 453530 }, { "epoch": 2.6959359452181824, "grad_norm": 1.2186568975448608, "learning_rate": 2.5574401078625372e-05, "loss": 0.4360772132873535, "step": 453540 }, { "epoch": 2.6959953872948503, "grad_norm": 1.3839097023010254, "learning_rate": 2.5572244604242106e-05, "loss": 0.5262199878692627, "step": 453550 }, { "epoch": 2.696054829371519, "grad_norm": 1.1052459478378296, "learning_rate": 2.557008853373364e-05, "loss": 0.4510325908660889, "step": 453560 }, { "epoch": 2.696114271448187, "grad_norm": 1.7822009325027466, "learning_rate": 2.556793286711027e-05, "loss": 0.4703086853027344, "step": 453570 }, { "epoch": 2.6961737135248556, "grad_norm": 1.1331896781921387, "learning_rate": 2.5565777604382313e-05, "loss": 0.4428098201751709, "step": 453580 }, { "epoch": 2.696233155601524, "grad_norm": 1.4090819358825684, "learning_rate": 2.5563622745560074e-05, "loss": 0.43221292495727537, "step": 453590 }, { "epoch": 2.6962925976781924, "grad_norm": 1.2704534530639648, "learning_rate": 2.556146829065389e-05, "loss": 0.44989452362060545, "step": 453600 }, { "epoch": 2.696352039754861, "grad_norm": 1.1823108196258545, "learning_rate": 2.5559314239674043e-05, "loss": 0.46262302398681643, "step": 453610 }, { "epoch": 2.6964114818315292, "grad_norm": 1.7015351057052612, "learning_rate": 2.555716059263084e-05, "loss": 0.47104954719543457, "step": 453620 }, { "epoch": 2.6964709239081976, "grad_norm": 1.4100123643875122, "learning_rate": 2.5555007349534577e-05, "loss": 0.4666471481323242, "step": 453630 }, { "epoch": 2.696530365984866, "grad_norm": 1.0322728157043457, "learning_rate": 2.5552854510395567e-05, "loss": 0.4778574466705322, "step": 453640 }, { "epoch": 2.6965898080615345, "grad_norm": 1.1389833688735962, "learning_rate": 2.555070207522411e-05, "loss": 0.520412540435791, "step": 453650 }, { "epoch": 2.696649250138203, "grad_norm": 1.076034665107727, "learning_rate": 2.554855004403047e-05, "loss": 0.4068297386169434, "step": 453660 }, { "epoch": 2.6967086922148713, "grad_norm": 1.30893874168396, "learning_rate": 2.5546398416824996e-05, "loss": 0.4126443862915039, "step": 453670 }, { "epoch": 2.6967681342915397, "grad_norm": 1.34934401512146, "learning_rate": 2.5544247193617953e-05, "loss": 0.4971151351928711, "step": 453680 }, { "epoch": 2.696827576368208, "grad_norm": 1.2966169118881226, "learning_rate": 2.554209637441961e-05, "loss": 0.46251306533813474, "step": 453690 }, { "epoch": 2.6968870184448765, "grad_norm": 1.2226629257202148, "learning_rate": 2.5539945959240285e-05, "loss": 0.46166319847106935, "step": 453700 }, { "epoch": 2.696946460521545, "grad_norm": 1.4787684679031372, "learning_rate": 2.5537795948090264e-05, "loss": 0.4712241172790527, "step": 453710 }, { "epoch": 2.697005902598213, "grad_norm": 1.2262310981750488, "learning_rate": 2.5535646340979807e-05, "loss": 0.4441379547119141, "step": 453720 }, { "epoch": 2.697065344674882, "grad_norm": 1.3112183809280396, "learning_rate": 2.553349713791923e-05, "loss": 0.5066797256469726, "step": 453730 }, { "epoch": 2.6971247867515498, "grad_norm": 1.126517653465271, "learning_rate": 2.5531348338918816e-05, "loss": 0.42155141830444337, "step": 453740 }, { "epoch": 2.697184228828218, "grad_norm": 0.9793071150779724, "learning_rate": 2.552919994398879e-05, "loss": 0.43999538421630857, "step": 453750 }, { "epoch": 2.6972436709048866, "grad_norm": 1.2034350633621216, "learning_rate": 2.552705195313949e-05, "loss": 0.4325507164001465, "step": 453760 }, { "epoch": 2.697303112981555, "grad_norm": 1.4194265604019165, "learning_rate": 2.5524904366381165e-05, "loss": 0.4593629837036133, "step": 453770 }, { "epoch": 2.6973625550582234, "grad_norm": 1.5919921398162842, "learning_rate": 2.5522757183724087e-05, "loss": 0.4808525562286377, "step": 453780 }, { "epoch": 2.697421997134892, "grad_norm": 0.9705725908279419, "learning_rate": 2.552061040517852e-05, "loss": 0.47303285598754885, "step": 453790 }, { "epoch": 2.6974814392115603, "grad_norm": 1.5471702814102173, "learning_rate": 2.551846403075476e-05, "loss": 0.4771396636962891, "step": 453800 }, { "epoch": 2.6975408812882287, "grad_norm": 1.4767861366271973, "learning_rate": 2.5516318060463063e-05, "loss": 0.45503878593444824, "step": 453810 }, { "epoch": 2.697600323364897, "grad_norm": 1.3937556743621826, "learning_rate": 2.5514172494313666e-05, "loss": 0.5161317825317383, "step": 453820 }, { "epoch": 2.6976597654415655, "grad_norm": 1.1637969017028809, "learning_rate": 2.551202733231688e-05, "loss": 0.4777318000793457, "step": 453830 }, { "epoch": 2.697719207518234, "grad_norm": 1.5325853824615479, "learning_rate": 2.550988257448294e-05, "loss": 0.5017904758453369, "step": 453840 }, { "epoch": 2.6977786495949023, "grad_norm": 1.4821985960006714, "learning_rate": 2.5507738220822093e-05, "loss": 0.5012511253356934, "step": 453850 }, { "epoch": 2.6978380916715707, "grad_norm": 1.1556062698364258, "learning_rate": 2.5505594271344652e-05, "loss": 0.46692562103271484, "step": 453860 }, { "epoch": 2.697897533748239, "grad_norm": 1.1212835311889648, "learning_rate": 2.5503450726060807e-05, "loss": 0.4792177200317383, "step": 453870 }, { "epoch": 2.6979569758249076, "grad_norm": 1.9032031297683716, "learning_rate": 2.5501307584980833e-05, "loss": 0.4678346633911133, "step": 453880 }, { "epoch": 2.6980164179015755, "grad_norm": 1.6597169637680054, "learning_rate": 2.5499164848115004e-05, "loss": 0.5060087203979492, "step": 453890 }, { "epoch": 2.6980758599782444, "grad_norm": 1.0100748538970947, "learning_rate": 2.5497022515473552e-05, "loss": 0.45585079193115235, "step": 453900 }, { "epoch": 2.6981353020549124, "grad_norm": 1.741696834564209, "learning_rate": 2.549488058706673e-05, "loss": 0.48173093795776367, "step": 453910 }, { "epoch": 2.6981947441315812, "grad_norm": 1.0596376657485962, "learning_rate": 2.5492739062904787e-05, "loss": 0.44168734550476074, "step": 453920 }, { "epoch": 2.698254186208249, "grad_norm": 1.2457926273345947, "learning_rate": 2.5490597942997953e-05, "loss": 0.47851200103759767, "step": 453930 }, { "epoch": 2.6983136282849176, "grad_norm": 1.0610846281051636, "learning_rate": 2.5488457227356488e-05, "loss": 0.46454615592956544, "step": 453940 }, { "epoch": 2.698373070361586, "grad_norm": 1.3961031436920166, "learning_rate": 2.548631691599061e-05, "loss": 0.43764452934265136, "step": 453950 }, { "epoch": 2.6984325124382544, "grad_norm": 1.132644534111023, "learning_rate": 2.5484177008910586e-05, "loss": 0.4962954521179199, "step": 453960 }, { "epoch": 2.698491954514923, "grad_norm": 1.1886096000671387, "learning_rate": 2.5482037506126637e-05, "loss": 0.4158487319946289, "step": 453970 }, { "epoch": 2.6985513965915913, "grad_norm": 0.9731665849685669, "learning_rate": 2.5479898407649e-05, "loss": 0.4511092662811279, "step": 453980 }, { "epoch": 2.6986108386682597, "grad_norm": 1.3301750421524048, "learning_rate": 2.547775971348791e-05, "loss": 0.47359094619750974, "step": 453990 }, { "epoch": 2.698670280744928, "grad_norm": 1.3903623819351196, "learning_rate": 2.5475621423653596e-05, "loss": 0.47011523246765136, "step": 454000 }, { "epoch": 2.6987297228215965, "grad_norm": 1.096771240234375, "learning_rate": 2.547348353815629e-05, "loss": 0.46111173629760743, "step": 454010 }, { "epoch": 2.698789164898265, "grad_norm": 1.1544936895370483, "learning_rate": 2.5471346057006195e-05, "loss": 0.46473264694213867, "step": 454020 }, { "epoch": 2.6988486069749333, "grad_norm": 1.501773715019226, "learning_rate": 2.5469208980213573e-05, "loss": 0.49695191383361814, "step": 454030 }, { "epoch": 2.6989080490516018, "grad_norm": 1.1162480115890503, "learning_rate": 2.5467072307788624e-05, "loss": 0.4837085723876953, "step": 454040 }, { "epoch": 2.69896749112827, "grad_norm": 1.7308863401412964, "learning_rate": 2.5464936039741582e-05, "loss": 0.48645524978637694, "step": 454050 }, { "epoch": 2.6990269332049386, "grad_norm": 1.3713219165802002, "learning_rate": 2.546280017608266e-05, "loss": 0.44795875549316405, "step": 454060 }, { "epoch": 2.699086375281607, "grad_norm": 1.1868990659713745, "learning_rate": 2.5460664716822062e-05, "loss": 0.5103282451629638, "step": 454070 }, { "epoch": 2.699145817358275, "grad_norm": 1.1383614540100098, "learning_rate": 2.545852966197002e-05, "loss": 0.4685474395751953, "step": 454080 }, { "epoch": 2.699205259434944, "grad_norm": 1.398742914199829, "learning_rate": 2.5456395011536753e-05, "loss": 0.4654716491699219, "step": 454090 }, { "epoch": 2.699264701511612, "grad_norm": 1.3264272212982178, "learning_rate": 2.5454260765532455e-05, "loss": 0.46057701110839844, "step": 454100 }, { "epoch": 2.6993241435882807, "grad_norm": 1.1991748809814453, "learning_rate": 2.5452126923967355e-05, "loss": 0.49385976791381836, "step": 454110 }, { "epoch": 2.6993835856649486, "grad_norm": 1.3621766567230225, "learning_rate": 2.544999348685164e-05, "loss": 0.45145859718322756, "step": 454120 }, { "epoch": 2.699443027741617, "grad_norm": 1.3451141119003296, "learning_rate": 2.5447860454195534e-05, "loss": 0.4334604263305664, "step": 454130 }, { "epoch": 2.6995024698182855, "grad_norm": 1.961912989616394, "learning_rate": 2.5445727826009223e-05, "loss": 0.5491378307342529, "step": 454140 }, { "epoch": 2.699561911894954, "grad_norm": 1.6117979288101196, "learning_rate": 2.5443595602302904e-05, "loss": 0.4998380184173584, "step": 454150 }, { "epoch": 2.6996213539716223, "grad_norm": 1.405375599861145, "learning_rate": 2.544146378308681e-05, "loss": 0.5047659873962402, "step": 454160 }, { "epoch": 2.6996807960482907, "grad_norm": 0.9779385924339294, "learning_rate": 2.543933236837113e-05, "loss": 0.4607206344604492, "step": 454170 }, { "epoch": 2.699740238124959, "grad_norm": 1.2536060810089111, "learning_rate": 2.543720135816602e-05, "loss": 0.4535353660583496, "step": 454180 }, { "epoch": 2.6997996802016275, "grad_norm": 1.302851676940918, "learning_rate": 2.543507075248172e-05, "loss": 0.46100077629089353, "step": 454190 }, { "epoch": 2.699859122278296, "grad_norm": 1.5259934663772583, "learning_rate": 2.54329405513284e-05, "loss": 0.5065969467163086, "step": 454200 }, { "epoch": 2.6999185643549644, "grad_norm": 1.3331378698349, "learning_rate": 2.5430810754716244e-05, "loss": 0.4166593074798584, "step": 454210 }, { "epoch": 2.6999780064316328, "grad_norm": 1.2049040794372559, "learning_rate": 2.5428681362655466e-05, "loss": 0.5347416400909424, "step": 454220 }, { "epoch": 2.700037448508301, "grad_norm": 1.216787576675415, "learning_rate": 2.5426552375156253e-05, "loss": 0.460211181640625, "step": 454230 }, { "epoch": 2.7000968905849696, "grad_norm": 1.6024669408798218, "learning_rate": 2.5424423792228753e-05, "loss": 0.5057530879974366, "step": 454240 }, { "epoch": 2.700156332661638, "grad_norm": 1.1952787637710571, "learning_rate": 2.5422295613883173e-05, "loss": 0.45219926834106444, "step": 454250 }, { "epoch": 2.7002157747383064, "grad_norm": 1.2357583045959473, "learning_rate": 2.5420167840129704e-05, "loss": 0.4775118827819824, "step": 454260 }, { "epoch": 2.7002752168149744, "grad_norm": 1.112252116203308, "learning_rate": 2.5418040470978493e-05, "loss": 0.49308080673217775, "step": 454270 }, { "epoch": 2.7003346588916433, "grad_norm": 1.3274112939834595, "learning_rate": 2.5415913506439736e-05, "loss": 0.44051733016967776, "step": 454280 }, { "epoch": 2.7003941009683112, "grad_norm": 1.302551507949829, "learning_rate": 2.5413786946523627e-05, "loss": 0.46901798248291016, "step": 454290 }, { "epoch": 2.70045354304498, "grad_norm": 1.0575097799301147, "learning_rate": 2.5411660791240307e-05, "loss": 0.48462677001953125, "step": 454300 }, { "epoch": 2.700512985121648, "grad_norm": 1.39985191822052, "learning_rate": 2.540953504059994e-05, "loss": 0.42916526794433596, "step": 454310 }, { "epoch": 2.7005724271983165, "grad_norm": 1.174233317375183, "learning_rate": 2.5407409694612727e-05, "loss": 0.44893784523010255, "step": 454320 }, { "epoch": 2.700631869274985, "grad_norm": 1.3837864398956299, "learning_rate": 2.5405284753288828e-05, "loss": 0.45913333892822267, "step": 454330 }, { "epoch": 2.7006913113516533, "grad_norm": 0.9305291175842285, "learning_rate": 2.540316021663838e-05, "loss": 0.47332096099853516, "step": 454340 }, { "epoch": 2.7007507534283217, "grad_norm": 1.357109785079956, "learning_rate": 2.5401036084671593e-05, "loss": 0.48744707107543944, "step": 454350 }, { "epoch": 2.70081019550499, "grad_norm": 1.0526692867279053, "learning_rate": 2.5398912357398597e-05, "loss": 0.45883779525756835, "step": 454360 }, { "epoch": 2.7008696375816585, "grad_norm": 1.3566977977752686, "learning_rate": 2.5396789034829555e-05, "loss": 0.4695446968078613, "step": 454370 }, { "epoch": 2.700929079658327, "grad_norm": 1.5121433734893799, "learning_rate": 2.539466611697461e-05, "loss": 0.4658252716064453, "step": 454380 }, { "epoch": 2.7009885217349954, "grad_norm": 1.5737661123275757, "learning_rate": 2.5392543603843942e-05, "loss": 0.45372323989868163, "step": 454390 }, { "epoch": 2.701047963811664, "grad_norm": 1.5009831190109253, "learning_rate": 2.5390421495447698e-05, "loss": 0.4542387962341309, "step": 454400 }, { "epoch": 2.701107405888332, "grad_norm": 1.474485993385315, "learning_rate": 2.5388299791796027e-05, "loss": 0.44289321899414064, "step": 454410 }, { "epoch": 2.7011668479650006, "grad_norm": 1.5497452020645142, "learning_rate": 2.5386178492899078e-05, "loss": 0.485777473449707, "step": 454420 }, { "epoch": 2.701226290041669, "grad_norm": 1.2171082496643066, "learning_rate": 2.5384057598766996e-05, "loss": 0.5103313446044921, "step": 454430 }, { "epoch": 2.7012857321183374, "grad_norm": 1.475466251373291, "learning_rate": 2.5381937109409924e-05, "loss": 0.4701648712158203, "step": 454440 }, { "epoch": 2.701345174195006, "grad_norm": 1.161811113357544, "learning_rate": 2.5379817024838025e-05, "loss": 0.5282992362976074, "step": 454450 }, { "epoch": 2.701404616271674, "grad_norm": 1.6420739889144897, "learning_rate": 2.5377697345061424e-05, "loss": 0.47331390380859373, "step": 454460 }, { "epoch": 2.7014640583483427, "grad_norm": 1.6773642301559448, "learning_rate": 2.537557807009026e-05, "loss": 0.4910940170288086, "step": 454470 }, { "epoch": 2.7015235004250107, "grad_norm": 1.4022754430770874, "learning_rate": 2.5373459199934678e-05, "loss": 0.46661806106567383, "step": 454480 }, { "epoch": 2.701582942501679, "grad_norm": 1.298248291015625, "learning_rate": 2.537134073460481e-05, "loss": 0.4979248046875, "step": 454490 }, { "epoch": 2.7016423845783475, "grad_norm": 1.3594411611557007, "learning_rate": 2.5369222674110793e-05, "loss": 0.455829381942749, "step": 454500 }, { "epoch": 2.701701826655016, "grad_norm": 1.4234765768051147, "learning_rate": 2.5367105018462743e-05, "loss": 0.4801913261413574, "step": 454510 }, { "epoch": 2.7017612687316843, "grad_norm": 1.5000399351119995, "learning_rate": 2.536498776767082e-05, "loss": 0.4844944000244141, "step": 454520 }, { "epoch": 2.7018207108083527, "grad_norm": 1.6337451934814453, "learning_rate": 2.536287092174513e-05, "loss": 0.4650881767272949, "step": 454530 }, { "epoch": 2.701880152885021, "grad_norm": 1.090617299079895, "learning_rate": 2.5360754480695813e-05, "loss": 0.49799022674560545, "step": 454540 }, { "epoch": 2.7019395949616896, "grad_norm": 1.3127433061599731, "learning_rate": 2.5358638444532983e-05, "loss": 0.45790414810180663, "step": 454550 }, { "epoch": 2.701999037038358, "grad_norm": 1.6278475522994995, "learning_rate": 2.535652281326676e-05, "loss": 0.44248027801513673, "step": 454560 }, { "epoch": 2.7020584791150264, "grad_norm": 1.3891922235488892, "learning_rate": 2.5354407586907257e-05, "loss": 0.46994719505310056, "step": 454570 }, { "epoch": 2.702117921191695, "grad_norm": 0.9987216591835022, "learning_rate": 2.5352292765464636e-05, "loss": 0.40764331817626953, "step": 454580 }, { "epoch": 2.702177363268363, "grad_norm": 1.3406928777694702, "learning_rate": 2.5350178348948965e-05, "loss": 0.5113311767578125, "step": 454590 }, { "epoch": 2.7022368053450316, "grad_norm": 1.2275629043579102, "learning_rate": 2.5348064337370387e-05, "loss": 0.5089816093444824, "step": 454600 }, { "epoch": 2.7022962474217, "grad_norm": 1.1980639696121216, "learning_rate": 2.5345950730739004e-05, "loss": 0.43984193801879884, "step": 454610 }, { "epoch": 2.7023556894983685, "grad_norm": 1.2659488916397095, "learning_rate": 2.534383752906491e-05, "loss": 0.503972339630127, "step": 454620 }, { "epoch": 2.7024151315750364, "grad_norm": 1.3367321491241455, "learning_rate": 2.5341724732358256e-05, "loss": 0.4562700271606445, "step": 454630 }, { "epoch": 2.7024745736517053, "grad_norm": 1.255609154701233, "learning_rate": 2.53396123406291e-05, "loss": 0.49700727462768557, "step": 454640 }, { "epoch": 2.7025340157283733, "grad_norm": 1.1851749420166016, "learning_rate": 2.533750035388759e-05, "loss": 0.4980799674987793, "step": 454650 }, { "epoch": 2.702593457805042, "grad_norm": 1.3508461713790894, "learning_rate": 2.53353887721438e-05, "loss": 0.5383199691772461, "step": 454660 }, { "epoch": 2.70265289988171, "grad_norm": 1.0000758171081543, "learning_rate": 2.5333277595407852e-05, "loss": 0.43866429328918455, "step": 454670 }, { "epoch": 2.7027123419583785, "grad_norm": 1.5280686616897583, "learning_rate": 2.5331166823689826e-05, "loss": 0.4973060131072998, "step": 454680 }, { "epoch": 2.702771784035047, "grad_norm": 1.0766876935958862, "learning_rate": 2.532905645699983e-05, "loss": 0.5461750030517578, "step": 454690 }, { "epoch": 2.7028312261117153, "grad_norm": 1.6040064096450806, "learning_rate": 2.5326946495347943e-05, "loss": 0.4522112846374512, "step": 454700 }, { "epoch": 2.7028906681883837, "grad_norm": 1.3126300573349, "learning_rate": 2.5324836938744288e-05, "loss": 0.45027999877929686, "step": 454710 }, { "epoch": 2.702950110265052, "grad_norm": 1.4314547777175903, "learning_rate": 2.532272778719894e-05, "loss": 0.49007701873779297, "step": 454720 }, { "epoch": 2.7030095523417206, "grad_norm": 1.2582008838653564, "learning_rate": 2.5320619040721988e-05, "loss": 0.44440183639526365, "step": 454730 }, { "epoch": 2.703068994418389, "grad_norm": 1.6195440292358398, "learning_rate": 2.531851069932353e-05, "loss": 0.5257428169250489, "step": 454740 }, { "epoch": 2.7031284364950574, "grad_norm": 1.5827528238296509, "learning_rate": 2.5316402763013624e-05, "loss": 0.4776108741760254, "step": 454750 }, { "epoch": 2.703187878571726, "grad_norm": 1.6770789623260498, "learning_rate": 2.5314295231802386e-05, "loss": 0.4705680847167969, "step": 454760 }, { "epoch": 2.7032473206483942, "grad_norm": 1.3752691745758057, "learning_rate": 2.5312188105699875e-05, "loss": 0.5321964740753173, "step": 454770 }, { "epoch": 2.7033067627250627, "grad_norm": 1.2841001749038696, "learning_rate": 2.5310081384716207e-05, "loss": 0.43848862648010256, "step": 454780 }, { "epoch": 2.703366204801731, "grad_norm": 1.3642739057540894, "learning_rate": 2.53079750688614e-05, "loss": 0.477996301651001, "step": 454790 }, { "epoch": 2.7034256468783995, "grad_norm": 1.2403804063796997, "learning_rate": 2.5305869158145567e-05, "loss": 0.4248806953430176, "step": 454800 }, { "epoch": 2.703485088955068, "grad_norm": 1.1431881189346313, "learning_rate": 2.5303763652578782e-05, "loss": 0.49768657684326173, "step": 454810 }, { "epoch": 2.703544531031736, "grad_norm": 1.2727127075195312, "learning_rate": 2.5301658552171126e-05, "loss": 0.504376220703125, "step": 454820 }, { "epoch": 2.7036039731084047, "grad_norm": 1.3896803855895996, "learning_rate": 2.5299553856932623e-05, "loss": 0.46863517761230467, "step": 454830 }, { "epoch": 2.7036634151850727, "grad_norm": 1.300338864326477, "learning_rate": 2.529744956687341e-05, "loss": 0.49603900909423826, "step": 454840 }, { "epoch": 2.7037228572617416, "grad_norm": 1.2845773696899414, "learning_rate": 2.5295345682003514e-05, "loss": 0.4371026039123535, "step": 454850 }, { "epoch": 2.7037822993384095, "grad_norm": 1.3340777158737183, "learning_rate": 2.5293242202332985e-05, "loss": 0.5306046485900879, "step": 454860 }, { "epoch": 2.703841741415078, "grad_norm": 1.6019917726516724, "learning_rate": 2.5291139127871894e-05, "loss": 0.4339000701904297, "step": 454870 }, { "epoch": 2.7039011834917464, "grad_norm": 1.275274395942688, "learning_rate": 2.5289036458630333e-05, "loss": 0.46512670516967775, "step": 454880 }, { "epoch": 2.7039606255684148, "grad_norm": 1.4912974834442139, "learning_rate": 2.5286934194618335e-05, "loss": 0.49354329109191897, "step": 454890 }, { "epoch": 2.704020067645083, "grad_norm": 1.1715470552444458, "learning_rate": 2.5284832335845954e-05, "loss": 0.49708075523376466, "step": 454900 }, { "epoch": 2.7040795097217516, "grad_norm": 1.2911278009414673, "learning_rate": 2.5282730882323247e-05, "loss": 0.4232292175292969, "step": 454910 }, { "epoch": 2.70413895179842, "grad_norm": 1.5738623142242432, "learning_rate": 2.5280629834060278e-05, "loss": 0.48655195236206056, "step": 454920 }, { "epoch": 2.7041983938750884, "grad_norm": 1.140236735343933, "learning_rate": 2.5278529191067073e-05, "loss": 0.4602983474731445, "step": 454930 }, { "epoch": 2.704257835951757, "grad_norm": 1.1032078266143799, "learning_rate": 2.527642895335371e-05, "loss": 0.44924287796020507, "step": 454940 }, { "epoch": 2.7043172780284253, "grad_norm": 1.2905538082122803, "learning_rate": 2.527432912093022e-05, "loss": 0.456661319732666, "step": 454950 }, { "epoch": 2.7043767201050937, "grad_norm": 1.4492483139038086, "learning_rate": 2.5272229693806653e-05, "loss": 0.49728846549987793, "step": 454960 }, { "epoch": 2.704436162181762, "grad_norm": 1.424503207206726, "learning_rate": 2.5270130671993053e-05, "loss": 0.47595829963684083, "step": 454970 }, { "epoch": 2.7044956042584305, "grad_norm": 1.1618707180023193, "learning_rate": 2.526803205549946e-05, "loss": 0.4371642589569092, "step": 454980 }, { "epoch": 2.704555046335099, "grad_norm": 1.1963107585906982, "learning_rate": 2.5265933844335905e-05, "loss": 0.47481479644775393, "step": 454990 }, { "epoch": 2.7046144884117673, "grad_norm": 1.2149815559387207, "learning_rate": 2.5263836038512405e-05, "loss": 0.4802228927612305, "step": 455000 }, { "epoch": 2.7046739304884353, "grad_norm": 1.2301536798477173, "learning_rate": 2.5261738638039056e-05, "loss": 0.4525724411010742, "step": 455010 }, { "epoch": 2.704733372565104, "grad_norm": 1.2007399797439575, "learning_rate": 2.5259641642925847e-05, "loss": 0.44362821578979494, "step": 455020 }, { "epoch": 2.704792814641772, "grad_norm": 1.2521679401397705, "learning_rate": 2.525754505318282e-05, "loss": 0.46773109436035154, "step": 455030 }, { "epoch": 2.704852256718441, "grad_norm": 1.2153738737106323, "learning_rate": 2.5255448868820007e-05, "loss": 0.5002094268798828, "step": 455040 }, { "epoch": 2.704911698795109, "grad_norm": 1.6641168594360352, "learning_rate": 2.5253353089847427e-05, "loss": 0.5408387184143066, "step": 455050 }, { "epoch": 2.7049711408717774, "grad_norm": 1.2353675365447998, "learning_rate": 2.52512577162751e-05, "loss": 0.475358772277832, "step": 455060 }, { "epoch": 2.705030582948446, "grad_norm": 1.532584547996521, "learning_rate": 2.5249162748113077e-05, "loss": 0.44449853897094727, "step": 455070 }, { "epoch": 2.705090025025114, "grad_norm": 1.2457047700881958, "learning_rate": 2.5247068185371355e-05, "loss": 0.4554008483886719, "step": 455080 }, { "epoch": 2.7051494671017826, "grad_norm": 1.5608717203140259, "learning_rate": 2.5244974028059964e-05, "loss": 0.48480930328369143, "step": 455090 }, { "epoch": 2.705208909178451, "grad_norm": 1.3631268739700317, "learning_rate": 2.5242880276188913e-05, "loss": 0.45453453063964844, "step": 455100 }, { "epoch": 2.7052683512551194, "grad_norm": 1.157600998878479, "learning_rate": 2.5240786929768234e-05, "loss": 0.47832536697387695, "step": 455110 }, { "epoch": 2.705327793331788, "grad_norm": 1.094179391860962, "learning_rate": 2.5238693988807926e-05, "loss": 0.4845088005065918, "step": 455120 }, { "epoch": 2.7053872354084563, "grad_norm": 1.5659258365631104, "learning_rate": 2.5236601453317994e-05, "loss": 0.47350468635559084, "step": 455130 }, { "epoch": 2.7054466774851247, "grad_norm": 1.339735507965088, "learning_rate": 2.523450932330847e-05, "loss": 0.4664658546447754, "step": 455140 }, { "epoch": 2.705506119561793, "grad_norm": 1.0705080032348633, "learning_rate": 2.5232417598789355e-05, "loss": 0.42550153732299806, "step": 455150 }, { "epoch": 2.7055655616384615, "grad_norm": 1.5578672885894775, "learning_rate": 2.5230326279770645e-05, "loss": 0.49701452255249023, "step": 455160 }, { "epoch": 2.70562500371513, "grad_norm": 1.2489013671875, "learning_rate": 2.5228235366262358e-05, "loss": 0.4571883201599121, "step": 455170 }, { "epoch": 2.7056844457917983, "grad_norm": 1.3832186460494995, "learning_rate": 2.5226144858274493e-05, "loss": 0.4969333648681641, "step": 455180 }, { "epoch": 2.7057438878684668, "grad_norm": 1.5917599201202393, "learning_rate": 2.522405475581702e-05, "loss": 0.4751420021057129, "step": 455190 }, { "epoch": 2.7058033299451347, "grad_norm": 1.488028645515442, "learning_rate": 2.522196505889999e-05, "loss": 0.5163991928100586, "step": 455200 }, { "epoch": 2.7058627720218036, "grad_norm": 1.3234766721725464, "learning_rate": 2.5219875767533373e-05, "loss": 0.5097951412200927, "step": 455210 }, { "epoch": 2.7059222140984716, "grad_norm": 1.4754998683929443, "learning_rate": 2.5217786881727155e-05, "loss": 0.4479671001434326, "step": 455220 }, { "epoch": 2.70598165617514, "grad_norm": 1.3392993211746216, "learning_rate": 2.5215698401491345e-05, "loss": 0.4607978820800781, "step": 455230 }, { "epoch": 2.7060410982518084, "grad_norm": 1.193497896194458, "learning_rate": 2.5213610326835922e-05, "loss": 0.4311827659606934, "step": 455240 }, { "epoch": 2.706100540328477, "grad_norm": 1.2435939311981201, "learning_rate": 2.521152265777088e-05, "loss": 0.48458213806152345, "step": 455250 }, { "epoch": 2.706159982405145, "grad_norm": 1.1766798496246338, "learning_rate": 2.5209435394306185e-05, "loss": 0.43074979782104494, "step": 455260 }, { "epoch": 2.7062194244818136, "grad_norm": 1.2187554836273193, "learning_rate": 2.5207348536451864e-05, "loss": 0.48297319412231443, "step": 455270 }, { "epoch": 2.706278866558482, "grad_norm": 1.3129661083221436, "learning_rate": 2.5205262084217884e-05, "loss": 0.4349839687347412, "step": 455280 }, { "epoch": 2.7063383086351505, "grad_norm": 1.4626169204711914, "learning_rate": 2.5203176037614203e-05, "loss": 0.506783390045166, "step": 455290 }, { "epoch": 2.706397750711819, "grad_norm": 1.0707401037216187, "learning_rate": 2.5201090396650816e-05, "loss": 0.46648073196411133, "step": 455300 }, { "epoch": 2.7064571927884873, "grad_norm": 1.4943338632583618, "learning_rate": 2.5199005161337707e-05, "loss": 0.48835139274597167, "step": 455310 }, { "epoch": 2.7065166348651557, "grad_norm": 1.2431268692016602, "learning_rate": 2.519692033168482e-05, "loss": 0.48118934631347654, "step": 455320 }, { "epoch": 2.706576076941824, "grad_norm": 1.322952389717102, "learning_rate": 2.5194835907702184e-05, "loss": 0.47905645370483396, "step": 455330 }, { "epoch": 2.7066355190184925, "grad_norm": 1.1487923860549927, "learning_rate": 2.5192751889399736e-05, "loss": 0.40024471282958984, "step": 455340 }, { "epoch": 2.706694961095161, "grad_norm": 1.1769767999649048, "learning_rate": 2.5190668276787438e-05, "loss": 0.46107916831970214, "step": 455350 }, { "epoch": 2.7067544031718294, "grad_norm": 1.0684101581573486, "learning_rate": 2.5188585069875265e-05, "loss": 0.45325355529785155, "step": 455360 }, { "epoch": 2.7068138452484973, "grad_norm": 1.2616642713546753, "learning_rate": 2.5186502268673185e-05, "loss": 0.4651050090789795, "step": 455370 }, { "epoch": 2.706873287325166, "grad_norm": 1.2685054540634155, "learning_rate": 2.518441987319117e-05, "loss": 0.4600841522216797, "step": 455380 }, { "epoch": 2.706932729401834, "grad_norm": 1.3249177932739258, "learning_rate": 2.5182337883439144e-05, "loss": 0.46295928955078125, "step": 455390 }, { "epoch": 2.706992171478503, "grad_norm": 1.2549360990524292, "learning_rate": 2.5180256299427136e-05, "loss": 0.5202025413513184, "step": 455400 }, { "epoch": 2.707051613555171, "grad_norm": 1.1863701343536377, "learning_rate": 2.517817512116504e-05, "loss": 0.47813997268676756, "step": 455410 }, { "epoch": 2.7071110556318394, "grad_norm": 1.151169776916504, "learning_rate": 2.5176094348662832e-05, "loss": 0.43976573944091796, "step": 455420 }, { "epoch": 2.707170497708508, "grad_norm": 1.4258068799972534, "learning_rate": 2.5174013981930468e-05, "loss": 0.4783431053161621, "step": 455430 }, { "epoch": 2.7072299397851762, "grad_norm": 1.1997183561325073, "learning_rate": 2.5171934020977904e-05, "loss": 0.46488304138183595, "step": 455440 }, { "epoch": 2.7072893818618446, "grad_norm": 1.297927975654602, "learning_rate": 2.5169854465815085e-05, "loss": 0.45824122428894043, "step": 455450 }, { "epoch": 2.707348823938513, "grad_norm": 1.1696559190750122, "learning_rate": 2.5167775316451968e-05, "loss": 0.4438031196594238, "step": 455460 }, { "epoch": 2.7074082660151815, "grad_norm": 1.28349769115448, "learning_rate": 2.516569657289849e-05, "loss": 0.5080632209777832, "step": 455470 }, { "epoch": 2.70746770809185, "grad_norm": 1.410603642463684, "learning_rate": 2.5163618235164586e-05, "loss": 0.48204569816589354, "step": 455480 }, { "epoch": 2.7075271501685183, "grad_norm": 1.3946763277053833, "learning_rate": 2.5161540303260196e-05, "loss": 0.4453849792480469, "step": 455490 }, { "epoch": 2.7075865922451867, "grad_norm": 1.258186936378479, "learning_rate": 2.5159462777195282e-05, "loss": 0.4523052215576172, "step": 455500 }, { "epoch": 2.707646034321855, "grad_norm": 1.282125473022461, "learning_rate": 2.5157385656979787e-05, "loss": 0.495828914642334, "step": 455510 }, { "epoch": 2.7077054763985235, "grad_norm": 0.8519319295883179, "learning_rate": 2.5155308942623612e-05, "loss": 0.44069881439208985, "step": 455520 }, { "epoch": 2.707764918475192, "grad_norm": 1.3747230768203735, "learning_rate": 2.515323263413672e-05, "loss": 0.4688134670257568, "step": 455530 }, { "epoch": 2.7078243605518604, "grad_norm": 1.3370214700698853, "learning_rate": 2.515115673152904e-05, "loss": 0.5128016471862793, "step": 455540 }, { "epoch": 2.707883802628529, "grad_norm": 1.0717843770980835, "learning_rate": 2.514908123481048e-05, "loss": 0.48831605911254883, "step": 455550 }, { "epoch": 2.7079432447051968, "grad_norm": 1.8093191385269165, "learning_rate": 2.5147006143991005e-05, "loss": 0.4803805351257324, "step": 455560 }, { "epoch": 2.7080026867818656, "grad_norm": 1.4767495393753052, "learning_rate": 2.5144931459080516e-05, "loss": 0.4478741645812988, "step": 455570 }, { "epoch": 2.7080621288585336, "grad_norm": 1.3046842813491821, "learning_rate": 2.5142857180088947e-05, "loss": 0.4308154582977295, "step": 455580 }, { "epoch": 2.7081215709352024, "grad_norm": 1.0217772722244263, "learning_rate": 2.5140783307026206e-05, "loss": 0.4716458320617676, "step": 455590 }, { "epoch": 2.7081810130118704, "grad_norm": 1.4019551277160645, "learning_rate": 2.5138709839902236e-05, "loss": 0.4800429344177246, "step": 455600 }, { "epoch": 2.708240455088539, "grad_norm": 1.1267633438110352, "learning_rate": 2.5136636778726948e-05, "loss": 0.4258148670196533, "step": 455610 }, { "epoch": 2.7082998971652072, "grad_norm": 1.126585602760315, "learning_rate": 2.513456412351024e-05, "loss": 0.4482589244842529, "step": 455620 }, { "epoch": 2.7083593392418757, "grad_norm": 1.1337809562683105, "learning_rate": 2.5132491874262047e-05, "loss": 0.5064770221710205, "step": 455630 }, { "epoch": 2.708418781318544, "grad_norm": 1.401968002319336, "learning_rate": 2.5130420030992286e-05, "loss": 0.4725502967834473, "step": 455640 }, { "epoch": 2.7084782233952125, "grad_norm": 1.087279200553894, "learning_rate": 2.512834859371086e-05, "loss": 0.46297760009765626, "step": 455650 }, { "epoch": 2.708537665471881, "grad_norm": 1.1890608072280884, "learning_rate": 2.512627756242768e-05, "loss": 0.44138355255126954, "step": 455660 }, { "epoch": 2.7085971075485493, "grad_norm": 0.8687891960144043, "learning_rate": 2.512420693715265e-05, "loss": 0.482546329498291, "step": 455670 }, { "epoch": 2.7086565496252177, "grad_norm": 1.5281177759170532, "learning_rate": 2.5122136717895662e-05, "loss": 0.4512306213378906, "step": 455680 }, { "epoch": 2.708715991701886, "grad_norm": 1.8516885042190552, "learning_rate": 2.5120066904666638e-05, "loss": 0.4666050910949707, "step": 455690 }, { "epoch": 2.7087754337785546, "grad_norm": 1.38937509059906, "learning_rate": 2.5117997497475492e-05, "loss": 0.4663265228271484, "step": 455700 }, { "epoch": 2.708834875855223, "grad_norm": 0.9548129439353943, "learning_rate": 2.511592849633211e-05, "loss": 0.44579596519470216, "step": 455710 }, { "epoch": 2.7088943179318914, "grad_norm": 1.231672763824463, "learning_rate": 2.5113859901246357e-05, "loss": 0.508547592163086, "step": 455720 }, { "epoch": 2.70895376000856, "grad_norm": 1.3387115001678467, "learning_rate": 2.5111791712228166e-05, "loss": 0.42534923553466797, "step": 455730 }, { "epoch": 2.7090132020852282, "grad_norm": 1.1757673025131226, "learning_rate": 2.5109723929287437e-05, "loss": 0.4593350887298584, "step": 455740 }, { "epoch": 2.709072644161896, "grad_norm": 1.144007682800293, "learning_rate": 2.5107656552434027e-05, "loss": 0.47774791717529297, "step": 455750 }, { "epoch": 2.709132086238565, "grad_norm": 1.2850439548492432, "learning_rate": 2.5105589581677853e-05, "loss": 0.43114681243896485, "step": 455760 }, { "epoch": 2.709191528315233, "grad_norm": 1.4313287734985352, "learning_rate": 2.510352301702881e-05, "loss": 0.45025343894958497, "step": 455770 }, { "epoch": 2.709250970391902, "grad_norm": 1.1710762977600098, "learning_rate": 2.5101456858496742e-05, "loss": 0.4682788848876953, "step": 455780 }, { "epoch": 2.70931041246857, "grad_norm": 1.146789312362671, "learning_rate": 2.5099391106091576e-05, "loss": 0.4570319175720215, "step": 455790 }, { "epoch": 2.7093698545452383, "grad_norm": 1.0330448150634766, "learning_rate": 2.5097325759823166e-05, "loss": 0.41630067825317385, "step": 455800 }, { "epoch": 2.7094292966219067, "grad_norm": 1.2565338611602783, "learning_rate": 2.5095260819701404e-05, "loss": 0.4776435852050781, "step": 455810 }, { "epoch": 2.709488738698575, "grad_norm": 1.5137176513671875, "learning_rate": 2.509319628573617e-05, "loss": 0.48416452407836913, "step": 455820 }, { "epoch": 2.7095481807752435, "grad_norm": 1.379273533821106, "learning_rate": 2.5091132157937352e-05, "loss": 0.46196622848510743, "step": 455830 }, { "epoch": 2.709607622851912, "grad_norm": 1.1783366203308105, "learning_rate": 2.5089068436314805e-05, "loss": 0.4738274574279785, "step": 455840 }, { "epoch": 2.7096670649285803, "grad_norm": 1.2006280422210693, "learning_rate": 2.5087005120878387e-05, "loss": 0.4988706111907959, "step": 455850 }, { "epoch": 2.7097265070052488, "grad_norm": 1.392013430595398, "learning_rate": 2.5084942211637995e-05, "loss": 0.4637173652648926, "step": 455860 }, { "epoch": 2.709785949081917, "grad_norm": 1.3931453227996826, "learning_rate": 2.5082879708603497e-05, "loss": 0.4922351837158203, "step": 455870 }, { "epoch": 2.7098453911585856, "grad_norm": 1.230865240097046, "learning_rate": 2.5080817611784734e-05, "loss": 0.42490234375, "step": 455880 }, { "epoch": 2.709904833235254, "grad_norm": 1.2002562284469604, "learning_rate": 2.507875592119161e-05, "loss": 0.4397274017333984, "step": 455890 }, { "epoch": 2.7099642753119224, "grad_norm": 1.4994263648986816, "learning_rate": 2.507669463683396e-05, "loss": 0.45108709335327146, "step": 455900 }, { "epoch": 2.710023717388591, "grad_norm": 1.373471736907959, "learning_rate": 2.5074633758721633e-05, "loss": 0.44908676147460935, "step": 455910 }, { "epoch": 2.7100831594652592, "grad_norm": 1.456100344657898, "learning_rate": 2.5072573286864513e-05, "loss": 0.4751856803894043, "step": 455920 }, { "epoch": 2.7101426015419277, "grad_norm": 1.1623198986053467, "learning_rate": 2.5070513221272452e-05, "loss": 0.43662004470825194, "step": 455930 }, { "epoch": 2.7102020436185956, "grad_norm": 1.4796875715255737, "learning_rate": 2.5068453561955285e-05, "loss": 0.4378203392028809, "step": 455940 }, { "epoch": 2.7102614856952645, "grad_norm": 1.4128046035766602, "learning_rate": 2.506639430892291e-05, "loss": 0.4736202239990234, "step": 455950 }, { "epoch": 2.7103209277719325, "grad_norm": 1.0421234369277954, "learning_rate": 2.5064335462185136e-05, "loss": 0.504265022277832, "step": 455960 }, { "epoch": 2.710380369848601, "grad_norm": 1.3899987936019897, "learning_rate": 2.506227702175182e-05, "loss": 0.4973912239074707, "step": 455970 }, { "epoch": 2.7104398119252693, "grad_norm": 1.3588390350341797, "learning_rate": 2.5060218987632793e-05, "loss": 0.42765064239501954, "step": 455980 }, { "epoch": 2.7104992540019377, "grad_norm": 1.212092638015747, "learning_rate": 2.5058161359837946e-05, "loss": 0.4853058815002441, "step": 455990 }, { "epoch": 2.710558696078606, "grad_norm": 1.1027092933654785, "learning_rate": 2.5056104138377096e-05, "loss": 0.4483607292175293, "step": 456000 }, { "epoch": 2.7106181381552745, "grad_norm": 1.3627279996871948, "learning_rate": 2.505404732326007e-05, "loss": 0.4544090270996094, "step": 456010 }, { "epoch": 2.710677580231943, "grad_norm": 1.3157334327697754, "learning_rate": 2.5051990914496736e-05, "loss": 0.4328951358795166, "step": 456020 }, { "epoch": 2.7107370223086114, "grad_norm": 1.2386970520019531, "learning_rate": 2.5049934912096907e-05, "loss": 0.48276681900024415, "step": 456030 }, { "epoch": 2.7107964643852798, "grad_norm": 1.219810128211975, "learning_rate": 2.504787931607041e-05, "loss": 0.48996825218200685, "step": 456040 }, { "epoch": 2.710855906461948, "grad_norm": 1.5706655979156494, "learning_rate": 2.504582412642712e-05, "loss": 0.4469286441802979, "step": 456050 }, { "epoch": 2.7109153485386166, "grad_norm": 1.5271368026733398, "learning_rate": 2.5043769343176843e-05, "loss": 0.46500210762023925, "step": 456060 }, { "epoch": 2.710974790615285, "grad_norm": 1.2381035089492798, "learning_rate": 2.5041714966329406e-05, "loss": 0.4510688781738281, "step": 456070 }, { "epoch": 2.7110342326919534, "grad_norm": 1.4147001504898071, "learning_rate": 2.5039660995894638e-05, "loss": 0.503285264968872, "step": 456080 }, { "epoch": 2.711093674768622, "grad_norm": 1.4545364379882812, "learning_rate": 2.503760743188236e-05, "loss": 0.41933112144470214, "step": 456090 }, { "epoch": 2.7111531168452903, "grad_norm": 0.8256971836090088, "learning_rate": 2.503555427430242e-05, "loss": 0.4460734844207764, "step": 456100 }, { "epoch": 2.7112125589219582, "grad_norm": 1.254830002784729, "learning_rate": 2.5033501523164587e-05, "loss": 0.4438791751861572, "step": 456110 }, { "epoch": 2.711272000998627, "grad_norm": 1.2067334651947021, "learning_rate": 2.503144917847875e-05, "loss": 0.4550891876220703, "step": 456120 }, { "epoch": 2.711331443075295, "grad_norm": 1.5713380575180054, "learning_rate": 2.5029397240254675e-05, "loss": 0.47954397201538085, "step": 456130 }, { "epoch": 2.711390885151964, "grad_norm": 1.309274673461914, "learning_rate": 2.502734570850221e-05, "loss": 0.46481800079345703, "step": 456140 }, { "epoch": 2.711450327228632, "grad_norm": 1.1047760248184204, "learning_rate": 2.5025294583231135e-05, "loss": 0.4618964195251465, "step": 456150 }, { "epoch": 2.7115097693053003, "grad_norm": 1.2749682664871216, "learning_rate": 2.5023243864451294e-05, "loss": 0.4395002365112305, "step": 456160 }, { "epoch": 2.7115692113819687, "grad_norm": 1.2958509922027588, "learning_rate": 2.5021193552172472e-05, "loss": 0.42775917053222656, "step": 456170 }, { "epoch": 2.711628653458637, "grad_norm": 1.374293327331543, "learning_rate": 2.5019143646404503e-05, "loss": 0.45844449996948244, "step": 456180 }, { "epoch": 2.7116880955353055, "grad_norm": 1.0026119947433472, "learning_rate": 2.5017094147157167e-05, "loss": 0.44754838943481445, "step": 456190 }, { "epoch": 2.711747537611974, "grad_norm": 1.1151624917984009, "learning_rate": 2.50150450544403e-05, "loss": 0.43857583999633787, "step": 456200 }, { "epoch": 2.7118069796886424, "grad_norm": 1.230206847190857, "learning_rate": 2.501299636826366e-05, "loss": 0.4302228927612305, "step": 456210 }, { "epoch": 2.711866421765311, "grad_norm": 1.2466661930084229, "learning_rate": 2.5010948088637078e-05, "loss": 0.508792781829834, "step": 456220 }, { "epoch": 2.711925863841979, "grad_norm": 1.2492762804031372, "learning_rate": 2.5008900215570353e-05, "loss": 0.43227572441101075, "step": 456230 }, { "epoch": 2.7119853059186476, "grad_norm": 1.2301503419876099, "learning_rate": 2.5006852749073256e-05, "loss": 0.4137840747833252, "step": 456240 }, { "epoch": 2.712044747995316, "grad_norm": 1.4243875741958618, "learning_rate": 2.5004805689155613e-05, "loss": 0.42604336738586424, "step": 456250 }, { "epoch": 2.7121041900719844, "grad_norm": 1.5478163957595825, "learning_rate": 2.5002759035827215e-05, "loss": 0.5025734901428223, "step": 456260 }, { "epoch": 2.712163632148653, "grad_norm": 1.216877818107605, "learning_rate": 2.500071278909782e-05, "loss": 0.45845603942871094, "step": 456270 }, { "epoch": 2.7122230742253213, "grad_norm": 1.1732587814331055, "learning_rate": 2.4998666948977247e-05, "loss": 0.3967881202697754, "step": 456280 }, { "epoch": 2.7122825163019897, "grad_norm": 1.166769027709961, "learning_rate": 2.4996621515475274e-05, "loss": 0.4551053047180176, "step": 456290 }, { "epoch": 2.7123419583786577, "grad_norm": 1.2746752500534058, "learning_rate": 2.4994576488601663e-05, "loss": 0.5004258155822754, "step": 456300 }, { "epoch": 2.7124014004553265, "grad_norm": 1.4065372943878174, "learning_rate": 2.499253186836624e-05, "loss": 0.5135483264923095, "step": 456310 }, { "epoch": 2.7124608425319945, "grad_norm": 0.9029760956764221, "learning_rate": 2.4990487654778778e-05, "loss": 0.4101142883300781, "step": 456320 }, { "epoch": 2.7125202846086633, "grad_norm": 1.0314918756484985, "learning_rate": 2.498844384784902e-05, "loss": 0.4761201858520508, "step": 456330 }, { "epoch": 2.7125797266853313, "grad_norm": 1.4372069835662842, "learning_rate": 2.4986400447586753e-05, "loss": 0.5120153427124023, "step": 456340 }, { "epoch": 2.7126391687619997, "grad_norm": 1.1724330186843872, "learning_rate": 2.498435745400178e-05, "loss": 0.4816458702087402, "step": 456350 }, { "epoch": 2.712698610838668, "grad_norm": 1.0093482732772827, "learning_rate": 2.4982314867103855e-05, "loss": 0.43962464332580564, "step": 456360 }, { "epoch": 2.7127580529153366, "grad_norm": 1.6244409084320068, "learning_rate": 2.4980272686902743e-05, "loss": 0.43778262138366697, "step": 456370 }, { "epoch": 2.712817494992005, "grad_norm": 1.270991325378418, "learning_rate": 2.4978230913408248e-05, "loss": 0.48735804557800294, "step": 456380 }, { "epoch": 2.7128769370686734, "grad_norm": 1.2422757148742676, "learning_rate": 2.497618954663009e-05, "loss": 0.4496006011962891, "step": 456390 }, { "epoch": 2.712936379145342, "grad_norm": 1.5071333646774292, "learning_rate": 2.4974148586578044e-05, "loss": 0.5091372489929199, "step": 456400 }, { "epoch": 2.71299582122201, "grad_norm": 1.528333067893982, "learning_rate": 2.4972108033261906e-05, "loss": 0.4548137664794922, "step": 456410 }, { "epoch": 2.7130552632986786, "grad_norm": 1.336020588874817, "learning_rate": 2.4970067886691406e-05, "loss": 0.44946880340576173, "step": 456420 }, { "epoch": 2.713114705375347, "grad_norm": 1.4345693588256836, "learning_rate": 2.4968028146876305e-05, "loss": 0.48022685050964353, "step": 456430 }, { "epoch": 2.7131741474520155, "grad_norm": 1.6728236675262451, "learning_rate": 2.4965988813826394e-05, "loss": 0.46322293281555177, "step": 456440 }, { "epoch": 2.713233589528684, "grad_norm": 1.7382463216781616, "learning_rate": 2.4963949887551396e-05, "loss": 0.47887563705444336, "step": 456450 }, { "epoch": 2.7132930316053523, "grad_norm": 1.4291763305664062, "learning_rate": 2.4961911368061066e-05, "loss": 0.4155746936798096, "step": 456460 }, { "epoch": 2.7133524736820207, "grad_norm": 1.2170593738555908, "learning_rate": 2.4959873255365147e-05, "loss": 0.511082935333252, "step": 456470 }, { "epoch": 2.713411915758689, "grad_norm": 1.2904762029647827, "learning_rate": 2.4957835549473413e-05, "loss": 0.4964450836181641, "step": 456480 }, { "epoch": 2.713471357835357, "grad_norm": 1.3927491903305054, "learning_rate": 2.4955798250395604e-05, "loss": 0.47704243659973145, "step": 456490 }, { "epoch": 2.713530799912026, "grad_norm": 1.228035807609558, "learning_rate": 2.495376135814147e-05, "loss": 0.4948420524597168, "step": 456500 }, { "epoch": 2.713590241988694, "grad_norm": 1.379377841949463, "learning_rate": 2.4951724872720742e-05, "loss": 0.4475533485412598, "step": 456510 }, { "epoch": 2.7136496840653628, "grad_norm": 1.7677278518676758, "learning_rate": 2.4949688794143173e-05, "loss": 0.42231340408325196, "step": 456520 }, { "epoch": 2.7137091261420307, "grad_norm": 1.6165697574615479, "learning_rate": 2.4947653122418473e-05, "loss": 0.4959092140197754, "step": 456530 }, { "epoch": 2.713768568218699, "grad_norm": 1.1964551210403442, "learning_rate": 2.494561785755643e-05, "loss": 0.41766815185546874, "step": 456540 }, { "epoch": 2.7138280102953676, "grad_norm": 1.4243783950805664, "learning_rate": 2.4943582999566752e-05, "loss": 0.4773740768432617, "step": 456550 }, { "epoch": 2.713887452372036, "grad_norm": 1.0825576782226562, "learning_rate": 2.4941548548459173e-05, "loss": 0.46392135620117186, "step": 456560 }, { "epoch": 2.7139468944487044, "grad_norm": 1.0719356536865234, "learning_rate": 2.4939514504243432e-05, "loss": 0.4026063919067383, "step": 456570 }, { "epoch": 2.714006336525373, "grad_norm": 1.5561425685882568, "learning_rate": 2.4937480866929258e-05, "loss": 0.5056205749511719, "step": 456580 }, { "epoch": 2.7140657786020412, "grad_norm": 1.3549621105194092, "learning_rate": 2.4935447636526375e-05, "loss": 0.48282461166381835, "step": 456590 }, { "epoch": 2.7141252206787096, "grad_norm": 1.599455714225769, "learning_rate": 2.49334148130445e-05, "loss": 0.4741819381713867, "step": 456600 }, { "epoch": 2.714184662755378, "grad_norm": 1.1947522163391113, "learning_rate": 2.4931382396493372e-05, "loss": 0.49383935928344724, "step": 456610 }, { "epoch": 2.7142441048320465, "grad_norm": 1.3351986408233643, "learning_rate": 2.4929350386882718e-05, "loss": 0.4621823787689209, "step": 456620 }, { "epoch": 2.714303546908715, "grad_norm": 1.083815097808838, "learning_rate": 2.4927318784222246e-05, "loss": 0.46733078956604, "step": 456630 }, { "epoch": 2.7143629889853833, "grad_norm": 1.4270185232162476, "learning_rate": 2.4925287588521678e-05, "loss": 0.4741514682769775, "step": 456640 }, { "epoch": 2.7144224310620517, "grad_norm": 1.3939316272735596, "learning_rate": 2.4923256799790744e-05, "loss": 0.4720447540283203, "step": 456650 }, { "epoch": 2.71448187313872, "grad_norm": 1.4548406600952148, "learning_rate": 2.4921226418039114e-05, "loss": 0.47822179794311526, "step": 456660 }, { "epoch": 2.7145413152153886, "grad_norm": 1.3205420970916748, "learning_rate": 2.491919644327656e-05, "loss": 0.4539348602294922, "step": 456670 }, { "epoch": 2.7146007572920565, "grad_norm": 1.093540906906128, "learning_rate": 2.491716687551276e-05, "loss": 0.46549186706542967, "step": 456680 }, { "epoch": 2.7146601993687254, "grad_norm": 1.438019871711731, "learning_rate": 2.4915137714757425e-05, "loss": 0.4935100555419922, "step": 456690 }, { "epoch": 2.7147196414453933, "grad_norm": 1.249147653579712, "learning_rate": 2.491310896102027e-05, "loss": 0.48413429260253904, "step": 456700 }, { "epoch": 2.7147790835220618, "grad_norm": 1.2290526628494263, "learning_rate": 2.4911080614310995e-05, "loss": 0.47402048110961914, "step": 456710 }, { "epoch": 2.71483852559873, "grad_norm": 1.1558462381362915, "learning_rate": 2.4909052674639307e-05, "loss": 0.48023052215576173, "step": 456720 }, { "epoch": 2.7148979676753986, "grad_norm": 1.3761184215545654, "learning_rate": 2.4907025142014885e-05, "loss": 0.4711129188537598, "step": 456730 }, { "epoch": 2.714957409752067, "grad_norm": 1.1637396812438965, "learning_rate": 2.490499801644746e-05, "loss": 0.43975324630737306, "step": 456740 }, { "epoch": 2.7150168518287354, "grad_norm": 1.3266621828079224, "learning_rate": 2.4902971297946715e-05, "loss": 0.4651618003845215, "step": 456750 }, { "epoch": 2.715076293905404, "grad_norm": 1.1542885303497314, "learning_rate": 2.4900944986522344e-05, "loss": 0.4340044498443604, "step": 456760 }, { "epoch": 2.7151357359820723, "grad_norm": 1.2438149452209473, "learning_rate": 2.4898919082184044e-05, "loss": 0.4505751609802246, "step": 456770 }, { "epoch": 2.7151951780587407, "grad_norm": 1.3202866315841675, "learning_rate": 2.4896893584941495e-05, "loss": 0.4813080787658691, "step": 456780 }, { "epoch": 2.715254620135409, "grad_norm": 1.2266263961791992, "learning_rate": 2.4894868494804393e-05, "loss": 0.4538126945495605, "step": 456790 }, { "epoch": 2.7153140622120775, "grad_norm": 1.2361382246017456, "learning_rate": 2.4892843811782435e-05, "loss": 0.5022932529449463, "step": 456800 }, { "epoch": 2.715373504288746, "grad_norm": 1.427374243736267, "learning_rate": 2.48908195358853e-05, "loss": 0.46528139114379885, "step": 456810 }, { "epoch": 2.7154329463654143, "grad_norm": 1.1600464582443237, "learning_rate": 2.488879566712269e-05, "loss": 0.46381616592407227, "step": 456820 }, { "epoch": 2.7154923884420827, "grad_norm": 1.1860787868499756, "learning_rate": 2.4886772205504227e-05, "loss": 0.4108267784118652, "step": 456830 }, { "epoch": 2.715551830518751, "grad_norm": 1.4562573432922363, "learning_rate": 2.488474915103966e-05, "loss": 0.4929501533508301, "step": 456840 }, { "epoch": 2.715611272595419, "grad_norm": 1.0039098262786865, "learning_rate": 2.4882726503738618e-05, "loss": 0.4771367073059082, "step": 456850 }, { "epoch": 2.715670714672088, "grad_norm": 1.362221121788025, "learning_rate": 2.4880704263610797e-05, "loss": 0.48178510665893554, "step": 456860 }, { "epoch": 2.715730156748756, "grad_norm": 1.3403472900390625, "learning_rate": 2.4878682430665893e-05, "loss": 0.4741518497467041, "step": 456870 }, { "epoch": 2.715789598825425, "grad_norm": 1.5759227275848389, "learning_rate": 2.487666100491354e-05, "loss": 0.4465932846069336, "step": 456880 }, { "epoch": 2.715849040902093, "grad_norm": 1.2396700382232666, "learning_rate": 2.4874639986363403e-05, "loss": 0.46730947494506836, "step": 456890 }, { "epoch": 2.715908482978761, "grad_norm": 1.5561009645462036, "learning_rate": 2.4872619375025194e-05, "loss": 0.544864273071289, "step": 456900 }, { "epoch": 2.7159679250554296, "grad_norm": 1.2814768552780151, "learning_rate": 2.487059917090855e-05, "loss": 0.46120848655700686, "step": 456910 }, { "epoch": 2.716027367132098, "grad_norm": 1.3141666650772095, "learning_rate": 2.4868579374023116e-05, "loss": 0.4813241004943848, "step": 456920 }, { "epoch": 2.7160868092087664, "grad_norm": 1.195382833480835, "learning_rate": 2.4866559984378612e-05, "loss": 0.4579144477844238, "step": 456930 }, { "epoch": 2.716146251285435, "grad_norm": 1.0850507020950317, "learning_rate": 2.4864541001984653e-05, "loss": 0.5037612438201904, "step": 456940 }, { "epoch": 2.7162056933621033, "grad_norm": 1.1427444219589233, "learning_rate": 2.4862522426850898e-05, "loss": 0.48009319305419923, "step": 456950 }, { "epoch": 2.7162651354387717, "grad_norm": 1.3726418018341064, "learning_rate": 2.4860504258987013e-05, "loss": 0.46238293647766116, "step": 456960 }, { "epoch": 2.71632457751544, "grad_norm": 1.04379141330719, "learning_rate": 2.4858486498402654e-05, "loss": 0.4343231201171875, "step": 456970 }, { "epoch": 2.7163840195921085, "grad_norm": 1.2783730030059814, "learning_rate": 2.485646914510747e-05, "loss": 0.44427337646484377, "step": 456980 }, { "epoch": 2.716443461668777, "grad_norm": 1.3462276458740234, "learning_rate": 2.4854452199111113e-05, "loss": 0.4204546451568604, "step": 456990 }, { "epoch": 2.7165029037454453, "grad_norm": 1.498054027557373, "learning_rate": 2.485243566042324e-05, "loss": 0.4640620231628418, "step": 457000 }, { "epoch": 2.7165623458221138, "grad_norm": 1.1402467489242554, "learning_rate": 2.485041952905348e-05, "loss": 0.4647512435913086, "step": 457010 }, { "epoch": 2.716621787898782, "grad_norm": 1.4195585250854492, "learning_rate": 2.484840380501148e-05, "loss": 0.5011850357055664, "step": 457020 }, { "epoch": 2.7166812299754506, "grad_norm": 1.0665510892868042, "learning_rate": 2.4846388488306888e-05, "loss": 0.4944018840789795, "step": 457030 }, { "epoch": 2.7167406720521186, "grad_norm": 1.2748808860778809, "learning_rate": 2.4844373578949356e-05, "loss": 0.46170692443847655, "step": 457040 }, { "epoch": 2.7168001141287874, "grad_norm": 1.2096047401428223, "learning_rate": 2.4842359076948514e-05, "loss": 0.5159582614898681, "step": 457050 }, { "epoch": 2.7168595562054554, "grad_norm": 1.1890326738357544, "learning_rate": 2.484034498231399e-05, "loss": 0.4474614143371582, "step": 457060 }, { "epoch": 2.7169189982821242, "grad_norm": 1.5040754079818726, "learning_rate": 2.4838331295055423e-05, "loss": 0.49629802703857423, "step": 457070 }, { "epoch": 2.716978440358792, "grad_norm": 1.5758475065231323, "learning_rate": 2.4836318015182446e-05, "loss": 0.476209831237793, "step": 457080 }, { "epoch": 2.7170378824354606, "grad_norm": 1.0945343971252441, "learning_rate": 2.483430514270469e-05, "loss": 0.4829439163208008, "step": 457090 }, { "epoch": 2.717097324512129, "grad_norm": 1.3212789297103882, "learning_rate": 2.4832292677631793e-05, "loss": 0.40294189453125, "step": 457100 }, { "epoch": 2.7171567665887975, "grad_norm": 1.5122618675231934, "learning_rate": 2.483028061997337e-05, "loss": 0.4603236675262451, "step": 457110 }, { "epoch": 2.717216208665466, "grad_norm": 1.1812798976898193, "learning_rate": 2.4828268969739056e-05, "loss": 0.4962640285491943, "step": 457120 }, { "epoch": 2.7172756507421343, "grad_norm": 1.0374464988708496, "learning_rate": 2.4826257726938474e-05, "loss": 0.5089069366455078, "step": 457130 }, { "epoch": 2.7173350928188027, "grad_norm": 1.4311851263046265, "learning_rate": 2.482424689158123e-05, "loss": 0.4410258293151855, "step": 457140 }, { "epoch": 2.717394534895471, "grad_norm": 1.2281180620193481, "learning_rate": 2.4822236463676944e-05, "loss": 0.42960543632507325, "step": 457150 }, { "epoch": 2.7174539769721395, "grad_norm": 1.5249760150909424, "learning_rate": 2.4820226443235256e-05, "loss": 0.5011772155761719, "step": 457160 }, { "epoch": 2.717513419048808, "grad_norm": 1.4174212217330933, "learning_rate": 2.4818216830265763e-05, "loss": 0.44436187744140626, "step": 457170 }, { "epoch": 2.7175728611254764, "grad_norm": 1.2888535261154175, "learning_rate": 2.481620762477809e-05, "loss": 0.45636730194091796, "step": 457180 }, { "epoch": 2.7176323032021448, "grad_norm": 1.2685128450393677, "learning_rate": 2.481419882678184e-05, "loss": 0.47881283760070803, "step": 457190 }, { "epoch": 2.717691745278813, "grad_norm": 1.441306233406067, "learning_rate": 2.4812190436286622e-05, "loss": 0.5385796546936035, "step": 457200 }, { "epoch": 2.7177511873554816, "grad_norm": 1.3920220136642456, "learning_rate": 2.4810182453302044e-05, "loss": 0.47706780433654783, "step": 457210 }, { "epoch": 2.71781062943215, "grad_norm": 0.9642775654792786, "learning_rate": 2.4808174877837706e-05, "loss": 0.4451125144958496, "step": 457220 }, { "epoch": 2.717870071508818, "grad_norm": 1.3705332279205322, "learning_rate": 2.480616770990323e-05, "loss": 0.4622983932495117, "step": 457230 }, { "epoch": 2.717929513585487, "grad_norm": 1.2969406843185425, "learning_rate": 2.480416094950819e-05, "loss": 0.4767141342163086, "step": 457240 }, { "epoch": 2.717988955662155, "grad_norm": 1.3408763408660889, "learning_rate": 2.480215459666222e-05, "loss": 0.4759043216705322, "step": 457250 }, { "epoch": 2.7180483977388237, "grad_norm": 1.4452245235443115, "learning_rate": 2.4800148651374894e-05, "loss": 0.45989513397216797, "step": 457260 }, { "epoch": 2.7181078398154916, "grad_norm": 1.3417727947235107, "learning_rate": 2.4798143113655816e-05, "loss": 0.45564994812011717, "step": 457270 }, { "epoch": 2.71816728189216, "grad_norm": 1.1899584531784058, "learning_rate": 2.4796137983514562e-05, "loss": 0.4760701656341553, "step": 457280 }, { "epoch": 2.7182267239688285, "grad_norm": 1.3577237129211426, "learning_rate": 2.479413326096075e-05, "loss": 0.4695271015167236, "step": 457290 }, { "epoch": 2.718286166045497, "grad_norm": 1.2490277290344238, "learning_rate": 2.4792128946003956e-05, "loss": 0.4989804267883301, "step": 457300 }, { "epoch": 2.7183456081221653, "grad_norm": 1.622388243675232, "learning_rate": 2.479012503865379e-05, "loss": 0.5146303653717041, "step": 457310 }, { "epoch": 2.7184050501988337, "grad_norm": 1.0243945121765137, "learning_rate": 2.478812153891979e-05, "loss": 0.45331697463989257, "step": 457320 }, { "epoch": 2.718464492275502, "grad_norm": 1.3176090717315674, "learning_rate": 2.478611844681158e-05, "loss": 0.43086719512939453, "step": 457330 }, { "epoch": 2.7185239343521705, "grad_norm": 1.3680843114852905, "learning_rate": 2.4784115762338733e-05, "loss": 0.43730573654174804, "step": 457340 }, { "epoch": 2.718583376428839, "grad_norm": 1.2632193565368652, "learning_rate": 2.4782113485510815e-05, "loss": 0.43796367645263673, "step": 457350 }, { "epoch": 2.7186428185055074, "grad_norm": 1.2604215145111084, "learning_rate": 2.4780111616337436e-05, "loss": 0.4993983268737793, "step": 457360 }, { "epoch": 2.718702260582176, "grad_norm": 1.5810781717300415, "learning_rate": 2.4778110154828156e-05, "loss": 0.5565012454986572, "step": 457370 }, { "epoch": 2.718761702658844, "grad_norm": 1.1789770126342773, "learning_rate": 2.4776109100992527e-05, "loss": 0.4866324424743652, "step": 457380 }, { "epoch": 2.7188211447355126, "grad_norm": 1.8497021198272705, "learning_rate": 2.477410845484015e-05, "loss": 0.4850903511047363, "step": 457390 }, { "epoch": 2.718880586812181, "grad_norm": 1.4147769212722778, "learning_rate": 2.4772108216380585e-05, "loss": 0.42760910987854006, "step": 457400 }, { "epoch": 2.7189400288888494, "grad_norm": 1.5532947778701782, "learning_rate": 2.47701083856234e-05, "loss": 0.47023839950561525, "step": 457410 }, { "epoch": 2.7189994709655174, "grad_norm": 1.110615849494934, "learning_rate": 2.4768108962578154e-05, "loss": 0.4525450706481934, "step": 457420 }, { "epoch": 2.7190589130421863, "grad_norm": 1.602794885635376, "learning_rate": 2.4766109947254453e-05, "loss": 0.4338498115539551, "step": 457430 }, { "epoch": 2.7191183551188542, "grad_norm": 1.3154622316360474, "learning_rate": 2.4764111339661797e-05, "loss": 0.4461775779724121, "step": 457440 }, { "epoch": 2.7191777971955227, "grad_norm": 0.9660192728042603, "learning_rate": 2.4762113139809774e-05, "loss": 0.4657279014587402, "step": 457450 }, { "epoch": 2.719237239272191, "grad_norm": 1.2492783069610596, "learning_rate": 2.4760115347707965e-05, "loss": 0.44750261306762695, "step": 457460 }, { "epoch": 2.7192966813488595, "grad_norm": 1.2738146781921387, "learning_rate": 2.475811796336589e-05, "loss": 0.49284114837646487, "step": 457470 }, { "epoch": 2.719356123425528, "grad_norm": 1.3018931150436401, "learning_rate": 2.475612098679314e-05, "loss": 0.47618827819824217, "step": 457480 }, { "epoch": 2.7194155655021963, "grad_norm": 1.42264986038208, "learning_rate": 2.4754124417999243e-05, "loss": 0.47930517196655276, "step": 457490 }, { "epoch": 2.7194750075788647, "grad_norm": 1.3422514200210571, "learning_rate": 2.4752128256993753e-05, "loss": 0.4605849742889404, "step": 457500 }, { "epoch": 2.719534449655533, "grad_norm": 1.267532229423523, "learning_rate": 2.4750132503786208e-05, "loss": 0.5314016342163086, "step": 457510 }, { "epoch": 2.7195938917322016, "grad_norm": 0.9359573721885681, "learning_rate": 2.4748137158386192e-05, "loss": 0.4020369529724121, "step": 457520 }, { "epoch": 2.71965333380887, "grad_norm": 3.1617989540100098, "learning_rate": 2.4746142220803215e-05, "loss": 0.5047857284545898, "step": 457530 }, { "epoch": 2.7197127758855384, "grad_norm": 1.521674633026123, "learning_rate": 2.4744147691046837e-05, "loss": 0.45915751457214354, "step": 457540 }, { "epoch": 2.719772217962207, "grad_norm": 0.9259201288223267, "learning_rate": 2.4742153569126597e-05, "loss": 0.49018154144287107, "step": 457550 }, { "epoch": 2.719831660038875, "grad_norm": 1.146855354309082, "learning_rate": 2.4740159855052027e-05, "loss": 0.45734310150146484, "step": 457560 }, { "epoch": 2.7198911021155436, "grad_norm": 1.5647445917129517, "learning_rate": 2.4738166548832674e-05, "loss": 0.45357422828674315, "step": 457570 }, { "epoch": 2.719950544192212, "grad_norm": 1.3588453531265259, "learning_rate": 2.4736173650478052e-05, "loss": 0.46149072647094724, "step": 457580 }, { "epoch": 2.72000998626888, "grad_norm": 1.385101556777954, "learning_rate": 2.4734181159997723e-05, "loss": 0.4520595550537109, "step": 457590 }, { "epoch": 2.720069428345549, "grad_norm": 1.3415968418121338, "learning_rate": 2.4732189077401213e-05, "loss": 0.44910502433776855, "step": 457600 }, { "epoch": 2.720128870422217, "grad_norm": 1.3619271516799927, "learning_rate": 2.473019740269804e-05, "loss": 0.4852282524108887, "step": 457610 }, { "epoch": 2.7201883124988857, "grad_norm": 1.1388039588928223, "learning_rate": 2.4728206135897734e-05, "loss": 0.4672956943511963, "step": 457620 }, { "epoch": 2.7202477545755537, "grad_norm": 1.2335171699523926, "learning_rate": 2.4726215277009825e-05, "loss": 0.38771097660064696, "step": 457630 }, { "epoch": 2.720307196652222, "grad_norm": 1.2513985633850098, "learning_rate": 2.4724224826043818e-05, "loss": 0.45189828872680665, "step": 457640 }, { "epoch": 2.7203666387288905, "grad_norm": 1.0091347694396973, "learning_rate": 2.4722234783009266e-05, "loss": 0.4296566963195801, "step": 457650 }, { "epoch": 2.720426080805559, "grad_norm": 1.2522953748703003, "learning_rate": 2.4720245147915677e-05, "loss": 0.4635161399841309, "step": 457660 }, { "epoch": 2.7204855228822273, "grad_norm": 1.3806438446044922, "learning_rate": 2.471825592077256e-05, "loss": 0.43689785003662107, "step": 457670 }, { "epoch": 2.7205449649588958, "grad_norm": 1.1854933500289917, "learning_rate": 2.4716267101589438e-05, "loss": 0.4881425857543945, "step": 457680 }, { "epoch": 2.720604407035564, "grad_norm": 1.397209882736206, "learning_rate": 2.4714278690375825e-05, "loss": 0.42352995872497556, "step": 457690 }, { "epoch": 2.7206638491122326, "grad_norm": 1.421047568321228, "learning_rate": 2.4712290687141235e-05, "loss": 0.4862551212310791, "step": 457700 }, { "epoch": 2.720723291188901, "grad_norm": 1.3349299430847168, "learning_rate": 2.4710303091895154e-05, "loss": 0.47647671699523925, "step": 457710 }, { "epoch": 2.7207827332655694, "grad_norm": 1.4897534847259521, "learning_rate": 2.4708315904647132e-05, "loss": 0.47461776733398436, "step": 457720 }, { "epoch": 2.720842175342238, "grad_norm": 1.1064451932907104, "learning_rate": 2.4706329125406647e-05, "loss": 0.42804250717163084, "step": 457730 }, { "epoch": 2.7209016174189062, "grad_norm": 1.499634861946106, "learning_rate": 2.47043427541832e-05, "loss": 0.4968207836151123, "step": 457740 }, { "epoch": 2.7209610594955747, "grad_norm": 1.3030545711517334, "learning_rate": 2.4702356790986318e-05, "loss": 0.44553661346435547, "step": 457750 }, { "epoch": 2.721020501572243, "grad_norm": 1.417580246925354, "learning_rate": 2.4700371235825477e-05, "loss": 0.5123003005981446, "step": 457760 }, { "epoch": 2.7210799436489115, "grad_norm": 1.8833539485931396, "learning_rate": 2.469838608871017e-05, "loss": 0.48955502510070803, "step": 457770 }, { "epoch": 2.7211393857255795, "grad_norm": 1.6656519174575806, "learning_rate": 2.4696401349649924e-05, "loss": 0.5028654098510742, "step": 457780 }, { "epoch": 2.7211988278022483, "grad_norm": 1.5154300928115845, "learning_rate": 2.469441701865422e-05, "loss": 0.46556825637817384, "step": 457790 }, { "epoch": 2.7212582698789163, "grad_norm": 1.0843214988708496, "learning_rate": 2.4692433095732553e-05, "loss": 0.45427684783935546, "step": 457800 }, { "epoch": 2.721317711955585, "grad_norm": 1.1657617092132568, "learning_rate": 2.4690449580894383e-05, "loss": 0.43911209106445315, "step": 457810 }, { "epoch": 2.721377154032253, "grad_norm": 1.42194664478302, "learning_rate": 2.4688466474149236e-05, "loss": 0.49967503547668457, "step": 457820 }, { "epoch": 2.7214365961089215, "grad_norm": 1.4169446229934692, "learning_rate": 2.468648377550658e-05, "loss": 0.47139177322387693, "step": 457830 }, { "epoch": 2.72149603818559, "grad_norm": 1.2802423238754272, "learning_rate": 2.4684501484975897e-05, "loss": 0.46581034660339354, "step": 457840 }, { "epoch": 2.7215554802622584, "grad_norm": 1.1817030906677246, "learning_rate": 2.468251960256669e-05, "loss": 0.4540518283843994, "step": 457850 }, { "epoch": 2.7216149223389268, "grad_norm": 1.3954075574874878, "learning_rate": 2.4680538128288448e-05, "loss": 0.4574589729309082, "step": 457860 }, { "epoch": 2.721674364415595, "grad_norm": 0.9349886178970337, "learning_rate": 2.4678557062150592e-05, "loss": 0.4101205825805664, "step": 457870 }, { "epoch": 2.7217338064922636, "grad_norm": 1.3401291370391846, "learning_rate": 2.467657640416265e-05, "loss": 0.49120726585388186, "step": 457880 }, { "epoch": 2.721793248568932, "grad_norm": 1.585753321647644, "learning_rate": 2.4674596154334084e-05, "loss": 0.49366455078125, "step": 457890 }, { "epoch": 2.7218526906456004, "grad_norm": 1.2279633283615112, "learning_rate": 2.4672616312674368e-05, "loss": 0.4405537128448486, "step": 457900 }, { "epoch": 2.721912132722269, "grad_norm": 1.4534647464752197, "learning_rate": 2.4670636879192954e-05, "loss": 0.4848228931427002, "step": 457910 }, { "epoch": 2.7219715747989373, "grad_norm": 1.8703491687774658, "learning_rate": 2.466865785389935e-05, "loss": 0.46761465072631836, "step": 457920 }, { "epoch": 2.7220310168756057, "grad_norm": 1.4565378427505493, "learning_rate": 2.4666679236802997e-05, "loss": 0.4635223388671875, "step": 457930 }, { "epoch": 2.722090458952274, "grad_norm": 1.2737551927566528, "learning_rate": 2.4664701027913338e-05, "loss": 0.5054173469543457, "step": 457940 }, { "epoch": 2.7221499010289425, "grad_norm": 1.6761116981506348, "learning_rate": 2.4662723227239885e-05, "loss": 0.47320094108581545, "step": 457950 }, { "epoch": 2.722209343105611, "grad_norm": 1.2445303201675415, "learning_rate": 2.466074583479207e-05, "loss": 0.4920534133911133, "step": 457960 }, { "epoch": 2.722268785182279, "grad_norm": 1.481799840927124, "learning_rate": 2.4658768850579357e-05, "loss": 0.4735074996948242, "step": 457970 }, { "epoch": 2.7223282272589477, "grad_norm": 1.2338947057724, "learning_rate": 2.4656792274611214e-05, "loss": 0.45594167709350586, "step": 457980 }, { "epoch": 2.7223876693356157, "grad_norm": 1.668463945388794, "learning_rate": 2.4654816106897076e-05, "loss": 0.42482647895812986, "step": 457990 }, { "epoch": 2.7224471114122846, "grad_norm": 1.289829134941101, "learning_rate": 2.46528403474464e-05, "loss": 0.400407600402832, "step": 458000 }, { "epoch": 2.7225065534889525, "grad_norm": 1.6650066375732422, "learning_rate": 2.4650864996268653e-05, "loss": 0.43340067863464354, "step": 458010 }, { "epoch": 2.722565995565621, "grad_norm": 1.0961421728134155, "learning_rate": 2.464889005337327e-05, "loss": 0.46615238189697267, "step": 458020 }, { "epoch": 2.7226254376422894, "grad_norm": 1.4540683031082153, "learning_rate": 2.464691551876972e-05, "loss": 0.5100172519683838, "step": 458030 }, { "epoch": 2.722684879718958, "grad_norm": 1.4513477087020874, "learning_rate": 2.4644941392467418e-05, "loss": 0.4730682373046875, "step": 458040 }, { "epoch": 2.722744321795626, "grad_norm": 1.185245156288147, "learning_rate": 2.4642967674475826e-05, "loss": 0.4170795440673828, "step": 458050 }, { "epoch": 2.7228037638722946, "grad_norm": 1.6058509349822998, "learning_rate": 2.4640994364804382e-05, "loss": 0.43463926315307616, "step": 458060 }, { "epoch": 2.722863205948963, "grad_norm": 1.6504143476486206, "learning_rate": 2.4639021463462513e-05, "loss": 0.43639626502990725, "step": 458070 }, { "epoch": 2.7229226480256314, "grad_norm": 1.28166925907135, "learning_rate": 2.463704897045968e-05, "loss": 0.5060721874237061, "step": 458080 }, { "epoch": 2.7229820901023, "grad_norm": 1.2482991218566895, "learning_rate": 2.4635076885805313e-05, "loss": 0.46273012161254884, "step": 458090 }, { "epoch": 2.7230415321789683, "grad_norm": 1.1214503049850464, "learning_rate": 2.4633105209508832e-05, "loss": 0.44032907485961914, "step": 458100 }, { "epoch": 2.7231009742556367, "grad_norm": 1.2508740425109863, "learning_rate": 2.4631133941579682e-05, "loss": 0.43877077102661133, "step": 458110 }, { "epoch": 2.723160416332305, "grad_norm": 1.1832036972045898, "learning_rate": 2.4629163082027294e-05, "loss": 0.46973505020141604, "step": 458120 }, { "epoch": 2.7232198584089735, "grad_norm": 1.45939302444458, "learning_rate": 2.462719263086107e-05, "loss": 0.48216729164123534, "step": 458130 }, { "epoch": 2.723279300485642, "grad_norm": 1.4892513751983643, "learning_rate": 2.4625222588090475e-05, "loss": 0.4851698398590088, "step": 458140 }, { "epoch": 2.7233387425623103, "grad_norm": 1.2449743747711182, "learning_rate": 2.462325295372491e-05, "loss": 0.4498137474060059, "step": 458150 }, { "epoch": 2.7233981846389783, "grad_norm": 1.227196216583252, "learning_rate": 2.4621283727773796e-05, "loss": 0.474039363861084, "step": 458160 }, { "epoch": 2.723457626715647, "grad_norm": 1.0907078981399536, "learning_rate": 2.4619314910246567e-05, "loss": 0.462418794631958, "step": 458170 }, { "epoch": 2.723517068792315, "grad_norm": 1.0149831771850586, "learning_rate": 2.4617346501152632e-05, "loss": 0.41249237060546873, "step": 458180 }, { "epoch": 2.7235765108689836, "grad_norm": 1.0175259113311768, "learning_rate": 2.4615378500501402e-05, "loss": 0.4882184028625488, "step": 458190 }, { "epoch": 2.723635952945652, "grad_norm": 1.835403323173523, "learning_rate": 2.461341090830229e-05, "loss": 0.4777682304382324, "step": 458200 }, { "epoch": 2.7236953950223204, "grad_norm": 1.3075450658798218, "learning_rate": 2.4611443724564726e-05, "loss": 0.45977396965026857, "step": 458210 }, { "epoch": 2.723754837098989, "grad_norm": 1.7515853643417358, "learning_rate": 2.4609476949298115e-05, "loss": 0.4670823574066162, "step": 458220 }, { "epoch": 2.723814279175657, "grad_norm": 1.3819739818572998, "learning_rate": 2.4607510582511858e-05, "loss": 0.4484687805175781, "step": 458230 }, { "epoch": 2.7238737212523256, "grad_norm": 1.3276938199996948, "learning_rate": 2.460554462421536e-05, "loss": 0.515411376953125, "step": 458240 }, { "epoch": 2.723933163328994, "grad_norm": 1.70803701877594, "learning_rate": 2.460357907441803e-05, "loss": 0.5072877883911133, "step": 458250 }, { "epoch": 2.7239926054056625, "grad_norm": 1.3280787467956543, "learning_rate": 2.4601613933129263e-05, "loss": 0.4825026512145996, "step": 458260 }, { "epoch": 2.724052047482331, "grad_norm": 1.1025959253311157, "learning_rate": 2.4599649200358476e-05, "loss": 0.4768951416015625, "step": 458270 }, { "epoch": 2.7241114895589993, "grad_norm": 1.5842711925506592, "learning_rate": 2.459768487611505e-05, "loss": 0.4525822639465332, "step": 458280 }, { "epoch": 2.7241709316356677, "grad_norm": 1.1530215740203857, "learning_rate": 2.4595720960408413e-05, "loss": 0.476500129699707, "step": 458290 }, { "epoch": 2.724230373712336, "grad_norm": 0.941089928150177, "learning_rate": 2.459375745324791e-05, "loss": 0.4163393497467041, "step": 458300 }, { "epoch": 2.7242898157890045, "grad_norm": 1.1304199695587158, "learning_rate": 2.4591794354642965e-05, "loss": 0.4642526626586914, "step": 458310 }, { "epoch": 2.724349257865673, "grad_norm": 1.394338607788086, "learning_rate": 2.4589831664602973e-05, "loss": 0.4649655818939209, "step": 458320 }, { "epoch": 2.724408699942341, "grad_norm": 1.3900591135025024, "learning_rate": 2.4587869383137296e-05, "loss": 0.4634615421295166, "step": 458330 }, { "epoch": 2.7244681420190098, "grad_norm": 1.1996289491653442, "learning_rate": 2.4585907510255358e-05, "loss": 0.4423513889312744, "step": 458340 }, { "epoch": 2.7245275840956777, "grad_norm": 1.0579313039779663, "learning_rate": 2.4583946045966526e-05, "loss": 0.476914119720459, "step": 458350 }, { "epoch": 2.7245870261723466, "grad_norm": 1.3971660137176514, "learning_rate": 2.4581984990280167e-05, "loss": 0.44169840812683103, "step": 458360 }, { "epoch": 2.7246464682490146, "grad_norm": 1.5484734773635864, "learning_rate": 2.4580024343205683e-05, "loss": 0.5200137138366699, "step": 458370 }, { "epoch": 2.724705910325683, "grad_norm": 1.1608678102493286, "learning_rate": 2.4578064104752455e-05, "loss": 0.4770774841308594, "step": 458380 }, { "epoch": 2.7247653524023514, "grad_norm": 1.4468364715576172, "learning_rate": 2.4576104274929847e-05, "loss": 0.4548340797424316, "step": 458390 }, { "epoch": 2.72482479447902, "grad_norm": 1.5375936031341553, "learning_rate": 2.4574144853747228e-05, "loss": 0.4685699462890625, "step": 458400 }, { "epoch": 2.7248842365556882, "grad_norm": 1.3284744024276733, "learning_rate": 2.4572185841214008e-05, "loss": 0.48839626312255857, "step": 458410 }, { "epoch": 2.7249436786323566, "grad_norm": 1.1774413585662842, "learning_rate": 2.457022723733951e-05, "loss": 0.4986530303955078, "step": 458420 }, { "epoch": 2.725003120709025, "grad_norm": 1.3392424583435059, "learning_rate": 2.4568269042133125e-05, "loss": 0.47060585021972656, "step": 458430 }, { "epoch": 2.7250625627856935, "grad_norm": 1.1809667348861694, "learning_rate": 2.456631125560423e-05, "loss": 0.4435290336608887, "step": 458440 }, { "epoch": 2.725122004862362, "grad_norm": 1.3341398239135742, "learning_rate": 2.4564353877762187e-05, "loss": 0.4488996505737305, "step": 458450 }, { "epoch": 2.7251814469390303, "grad_norm": 1.2176403999328613, "learning_rate": 2.4562396908616335e-05, "loss": 0.4766658306121826, "step": 458460 }, { "epoch": 2.7252408890156987, "grad_norm": 1.2163664102554321, "learning_rate": 2.4560440348176084e-05, "loss": 0.4245079517364502, "step": 458470 }, { "epoch": 2.725300331092367, "grad_norm": 1.159691572189331, "learning_rate": 2.455848419645075e-05, "loss": 0.46001629829406737, "step": 458480 }, { "epoch": 2.7253597731690355, "grad_norm": 1.415212631225586, "learning_rate": 2.4556528453449694e-05, "loss": 0.4729013442993164, "step": 458490 }, { "epoch": 2.725419215245704, "grad_norm": 1.2041809558868408, "learning_rate": 2.4554573119182292e-05, "loss": 0.4539349555969238, "step": 458500 }, { "epoch": 2.7254786573223724, "grad_norm": 1.2118943929672241, "learning_rate": 2.4552618193657893e-05, "loss": 0.4474700927734375, "step": 458510 }, { "epoch": 2.7255380993990403, "grad_norm": 1.451059341430664, "learning_rate": 2.455066367688584e-05, "loss": 0.4809356689453125, "step": 458520 }, { "epoch": 2.725597541475709, "grad_norm": 1.155317783355713, "learning_rate": 2.4548709568875488e-05, "loss": 0.4347435474395752, "step": 458530 }, { "epoch": 2.725656983552377, "grad_norm": 1.2198617458343506, "learning_rate": 2.454675586963619e-05, "loss": 0.45789146423339844, "step": 458540 }, { "epoch": 2.725716425629046, "grad_norm": 1.3006855249404907, "learning_rate": 2.454480257917728e-05, "loss": 0.4762128353118896, "step": 458550 }, { "epoch": 2.725775867705714, "grad_norm": 1.0675206184387207, "learning_rate": 2.4542849697508097e-05, "loss": 0.45021567344665525, "step": 458560 }, { "epoch": 2.7258353097823824, "grad_norm": 1.1393300294876099, "learning_rate": 2.4540897224638006e-05, "loss": 0.4216376781463623, "step": 458570 }, { "epoch": 2.725894751859051, "grad_norm": 1.1733250617980957, "learning_rate": 2.4538945160576328e-05, "loss": 0.4782694339752197, "step": 458580 }, { "epoch": 2.7259541939357192, "grad_norm": 1.306321382522583, "learning_rate": 2.4536993505332406e-05, "loss": 0.44510908126831056, "step": 458590 }, { "epoch": 2.7260136360123877, "grad_norm": 1.4108631610870361, "learning_rate": 2.4535042258915583e-05, "loss": 0.44290690422058104, "step": 458600 }, { "epoch": 2.726073078089056, "grad_norm": 1.2710627317428589, "learning_rate": 2.4533091421335194e-05, "loss": 0.4804829597473145, "step": 458610 }, { "epoch": 2.7261325201657245, "grad_norm": 1.5115704536437988, "learning_rate": 2.4531140992600542e-05, "loss": 0.38538758754730223, "step": 458620 }, { "epoch": 2.726191962242393, "grad_norm": 1.3899800777435303, "learning_rate": 2.4529190972720993e-05, "loss": 0.49626383781433103, "step": 458630 }, { "epoch": 2.7262514043190613, "grad_norm": 1.1370108127593994, "learning_rate": 2.4527241361705867e-05, "loss": 0.44784998893737793, "step": 458640 }, { "epoch": 2.7263108463957297, "grad_norm": 1.2822802066802979, "learning_rate": 2.4525292159564482e-05, "loss": 0.4700337886810303, "step": 458650 }, { "epoch": 2.726370288472398, "grad_norm": 1.2994446754455566, "learning_rate": 2.4523343366306175e-05, "loss": 0.4465609550476074, "step": 458660 }, { "epoch": 2.7264297305490666, "grad_norm": 1.3730289936065674, "learning_rate": 2.452139498194025e-05, "loss": 0.4331790924072266, "step": 458670 }, { "epoch": 2.726489172625735, "grad_norm": 1.3821167945861816, "learning_rate": 2.4519447006476034e-05, "loss": 0.4633510589599609, "step": 458680 }, { "epoch": 2.7265486147024034, "grad_norm": 1.421891450881958, "learning_rate": 2.451749943992285e-05, "loss": 0.46858930587768555, "step": 458690 }, { "epoch": 2.726608056779072, "grad_norm": 1.338020920753479, "learning_rate": 2.4515552282290004e-05, "loss": 0.48650054931640624, "step": 458700 }, { "epoch": 2.72666749885574, "grad_norm": 1.4654490947723389, "learning_rate": 2.4513605533586835e-05, "loss": 0.48914575576782227, "step": 458710 }, { "epoch": 2.7267269409324086, "grad_norm": 1.2829092741012573, "learning_rate": 2.4511659193822635e-05, "loss": 0.46884708404541015, "step": 458720 }, { "epoch": 2.7267863830090766, "grad_norm": 1.5772199630737305, "learning_rate": 2.4509713263006724e-05, "loss": 0.47236127853393556, "step": 458730 }, { "epoch": 2.7268458250857455, "grad_norm": 1.3917981386184692, "learning_rate": 2.4507767741148397e-05, "loss": 0.4900857925415039, "step": 458740 }, { "epoch": 2.7269052671624134, "grad_norm": 1.7043861150741577, "learning_rate": 2.4505822628256983e-05, "loss": 0.4702890396118164, "step": 458750 }, { "epoch": 2.726964709239082, "grad_norm": 1.2697532176971436, "learning_rate": 2.450387792434175e-05, "loss": 0.4486098766326904, "step": 458760 }, { "epoch": 2.7270241513157503, "grad_norm": 1.6265981197357178, "learning_rate": 2.4501933629412033e-05, "loss": 0.47393479347229006, "step": 458770 }, { "epoch": 2.7270835933924187, "grad_norm": 1.1023920774459839, "learning_rate": 2.4499989743477138e-05, "loss": 0.4577054500579834, "step": 458780 }, { "epoch": 2.727143035469087, "grad_norm": 1.5297404527664185, "learning_rate": 2.4498046266546348e-05, "loss": 0.4788217544555664, "step": 458790 }, { "epoch": 2.7272024775457555, "grad_norm": 0.9982123374938965, "learning_rate": 2.4496103198628954e-05, "loss": 0.4910456657409668, "step": 458800 }, { "epoch": 2.727261919622424, "grad_norm": 1.6208678483963013, "learning_rate": 2.4494160539734263e-05, "loss": 0.42099151611328123, "step": 458810 }, { "epoch": 2.7273213616990923, "grad_norm": 1.2814359664916992, "learning_rate": 2.4492218289871552e-05, "loss": 0.4132343292236328, "step": 458820 }, { "epoch": 2.7273808037757608, "grad_norm": 1.260769009590149, "learning_rate": 2.4490276449050142e-05, "loss": 0.4362586498260498, "step": 458830 }, { "epoch": 2.727440245852429, "grad_norm": 0.9837900400161743, "learning_rate": 2.4488335017279296e-05, "loss": 0.41995654106140134, "step": 458840 }, { "epoch": 2.7274996879290976, "grad_norm": 1.142653465270996, "learning_rate": 2.4486393994568317e-05, "loss": 0.4685523986816406, "step": 458850 }, { "epoch": 2.727559130005766, "grad_norm": 1.3521313667297363, "learning_rate": 2.4484453380926485e-05, "loss": 0.4683993339538574, "step": 458860 }, { "epoch": 2.7276185720824344, "grad_norm": 1.407205581665039, "learning_rate": 2.448251317636307e-05, "loss": 0.4781466484069824, "step": 458870 }, { "epoch": 2.727678014159103, "grad_norm": 1.1168456077575684, "learning_rate": 2.4480573380887376e-05, "loss": 0.4781645774841309, "step": 458880 }, { "epoch": 2.7277374562357712, "grad_norm": 1.3164979219436646, "learning_rate": 2.4478633994508654e-05, "loss": 0.4012468338012695, "step": 458890 }, { "epoch": 2.727796898312439, "grad_norm": 1.5551445484161377, "learning_rate": 2.4476695017236225e-05, "loss": 0.4690260887145996, "step": 458900 }, { "epoch": 2.727856340389108, "grad_norm": 1.2184791564941406, "learning_rate": 2.4474756449079313e-05, "loss": 0.4875322341918945, "step": 458910 }, { "epoch": 2.727915782465776, "grad_norm": 1.3494259119033813, "learning_rate": 2.4472818290047215e-05, "loss": 0.4183390140533447, "step": 458920 }, { "epoch": 2.7279752245424445, "grad_norm": 1.3677541017532349, "learning_rate": 2.4470880540149216e-05, "loss": 0.43994550704956054, "step": 458930 }, { "epoch": 2.728034666619113, "grad_norm": 1.3431893587112427, "learning_rate": 2.4468943199394574e-05, "loss": 0.469149112701416, "step": 458940 }, { "epoch": 2.7280941086957813, "grad_norm": 1.0534873008728027, "learning_rate": 2.4467006267792537e-05, "loss": 0.46041288375854494, "step": 458950 }, { "epoch": 2.7281535507724497, "grad_norm": 1.5377320051193237, "learning_rate": 2.446506974535242e-05, "loss": 0.4600041389465332, "step": 458960 }, { "epoch": 2.728212992849118, "grad_norm": 1.1470316648483276, "learning_rate": 2.4463133632083443e-05, "loss": 0.49624929428100584, "step": 458970 }, { "epoch": 2.7282724349257865, "grad_norm": 1.3925780057907104, "learning_rate": 2.4461197927994864e-05, "loss": 0.4507299423217773, "step": 458980 }, { "epoch": 2.728331877002455, "grad_norm": 1.1956652402877808, "learning_rate": 2.4459262633095977e-05, "loss": 0.430257511138916, "step": 458990 }, { "epoch": 2.7283913190791234, "grad_norm": 1.141480803489685, "learning_rate": 2.445732774739603e-05, "loss": 0.45104293823242186, "step": 459000 }, { "epoch": 2.7284507611557918, "grad_norm": 1.2312296628952026, "learning_rate": 2.4455393270904264e-05, "loss": 0.4588029384613037, "step": 459010 }, { "epoch": 2.72851020323246, "grad_norm": 1.5139882564544678, "learning_rate": 2.445345920362994e-05, "loss": 0.47012887001037595, "step": 459020 }, { "epoch": 2.7285696453091286, "grad_norm": 1.3249318599700928, "learning_rate": 2.4451525545582307e-05, "loss": 0.4274052619934082, "step": 459030 }, { "epoch": 2.728629087385797, "grad_norm": 1.266578197479248, "learning_rate": 2.444959229677062e-05, "loss": 0.44634256362915037, "step": 459040 }, { "epoch": 2.7286885294624654, "grad_norm": 1.6246649026870728, "learning_rate": 2.4447659457204113e-05, "loss": 0.4525320053100586, "step": 459050 }, { "epoch": 2.728747971539134, "grad_norm": 1.3846707344055176, "learning_rate": 2.4445727026892055e-05, "loss": 0.500947380065918, "step": 459060 }, { "epoch": 2.728807413615802, "grad_norm": 1.327485203742981, "learning_rate": 2.4443795005843678e-05, "loss": 0.4543596267700195, "step": 459070 }, { "epoch": 2.7288668556924707, "grad_norm": 1.03647780418396, "learning_rate": 2.444186339406824e-05, "loss": 0.4331770896911621, "step": 459080 }, { "epoch": 2.7289262977691386, "grad_norm": 1.446710228919983, "learning_rate": 2.443993219157495e-05, "loss": 0.4499842166900635, "step": 459090 }, { "epoch": 2.7289857398458075, "grad_norm": 1.3371407985687256, "learning_rate": 2.4438001398373068e-05, "loss": 0.47048563957214357, "step": 459100 }, { "epoch": 2.7290451819224755, "grad_norm": 1.257157325744629, "learning_rate": 2.443607101447182e-05, "loss": 0.49999423027038575, "step": 459110 }, { "epoch": 2.729104623999144, "grad_norm": 1.4046337604522705, "learning_rate": 2.4434141039880448e-05, "loss": 0.4295696258544922, "step": 459120 }, { "epoch": 2.7291640660758123, "grad_norm": 1.147045612335205, "learning_rate": 2.4432211474608186e-05, "loss": 0.4411632537841797, "step": 459130 }, { "epoch": 2.7292235081524807, "grad_norm": 1.4510952234268188, "learning_rate": 2.4430282318664264e-05, "loss": 0.4666592597961426, "step": 459140 }, { "epoch": 2.729282950229149, "grad_norm": 1.1649808883666992, "learning_rate": 2.4428353572057903e-05, "loss": 0.4632145881652832, "step": 459150 }, { "epoch": 2.7293423923058175, "grad_norm": 1.2860188484191895, "learning_rate": 2.4426425234798335e-05, "loss": 0.46305112838745116, "step": 459160 }, { "epoch": 2.729401834382486, "grad_norm": 1.033474087715149, "learning_rate": 2.4424497306894783e-05, "loss": 0.45261363983154296, "step": 459170 }, { "epoch": 2.7294612764591544, "grad_norm": 1.0633678436279297, "learning_rate": 2.442256978835645e-05, "loss": 0.43834481239318845, "step": 459180 }, { "epoch": 2.729520718535823, "grad_norm": 1.5021915435791016, "learning_rate": 2.4420642679192596e-05, "loss": 0.48594188690185547, "step": 459190 }, { "epoch": 2.729580160612491, "grad_norm": 1.034077763557434, "learning_rate": 2.4418715979412428e-05, "loss": 0.42484140396118164, "step": 459200 }, { "epoch": 2.7296396026891596, "grad_norm": 1.594929575920105, "learning_rate": 2.4416789689025137e-05, "loss": 0.46288189888000486, "step": 459210 }, { "epoch": 2.729699044765828, "grad_norm": 1.2684173583984375, "learning_rate": 2.441486380803997e-05, "loss": 0.4703624725341797, "step": 459220 }, { "epoch": 2.7297584868424964, "grad_norm": 1.2262519598007202, "learning_rate": 2.4412938336466117e-05, "loss": 0.48354573249816896, "step": 459230 }, { "epoch": 2.729817928919165, "grad_norm": 1.265282154083252, "learning_rate": 2.4411013274312792e-05, "loss": 0.5043788909912109, "step": 459240 }, { "epoch": 2.7298773709958333, "grad_norm": 1.4307490587234497, "learning_rate": 2.4409088621589206e-05, "loss": 0.5013976097106934, "step": 459250 }, { "epoch": 2.7299368130725012, "grad_norm": 1.142748236656189, "learning_rate": 2.4407164378304576e-05, "loss": 0.47417221069335935, "step": 459260 }, { "epoch": 2.72999625514917, "grad_norm": 1.2961751222610474, "learning_rate": 2.4405240544468097e-05, "loss": 0.44681568145751954, "step": 459270 }, { "epoch": 2.730055697225838, "grad_norm": 1.2090985774993896, "learning_rate": 2.4403317120088988e-05, "loss": 0.4618813514709473, "step": 459280 }, { "epoch": 2.730115139302507, "grad_norm": 1.1369892358779907, "learning_rate": 2.440139410517642e-05, "loss": 0.4097733497619629, "step": 459290 }, { "epoch": 2.730174581379175, "grad_norm": 1.5065996646881104, "learning_rate": 2.4399471499739616e-05, "loss": 0.4513679027557373, "step": 459300 }, { "epoch": 2.7302340234558433, "grad_norm": 1.241217851638794, "learning_rate": 2.4397549303787755e-05, "loss": 0.4473737716674805, "step": 459310 }, { "epoch": 2.7302934655325117, "grad_norm": 1.6147093772888184, "learning_rate": 2.4395627517330056e-05, "loss": 0.4686318874359131, "step": 459320 }, { "epoch": 2.73035290760918, "grad_norm": 1.3880881071090698, "learning_rate": 2.4393706140375697e-05, "loss": 0.45972185134887694, "step": 459330 }, { "epoch": 2.7304123496858486, "grad_norm": 1.6094244718551636, "learning_rate": 2.4391785172933873e-05, "loss": 0.48675222396850587, "step": 459340 }, { "epoch": 2.730471791762517, "grad_norm": 1.4671053886413574, "learning_rate": 2.4389864615013764e-05, "loss": 0.45847325325012206, "step": 459350 }, { "epoch": 2.7305312338391854, "grad_norm": 1.237641453742981, "learning_rate": 2.4387944466624573e-05, "loss": 0.48101511001586916, "step": 459360 }, { "epoch": 2.730590675915854, "grad_norm": 1.4103715419769287, "learning_rate": 2.4386024727775474e-05, "loss": 0.4890655517578125, "step": 459370 }, { "epoch": 2.730650117992522, "grad_norm": 1.4746673107147217, "learning_rate": 2.438410539847564e-05, "loss": 0.49699959754943845, "step": 459380 }, { "epoch": 2.7307095600691906, "grad_norm": 1.346657395362854, "learning_rate": 2.4382186478734287e-05, "loss": 0.5057417869567871, "step": 459390 }, { "epoch": 2.730769002145859, "grad_norm": 1.2734962701797485, "learning_rate": 2.438026796856058e-05, "loss": 0.4707305431365967, "step": 459400 }, { "epoch": 2.7308284442225275, "grad_norm": 1.5728343725204468, "learning_rate": 2.4378349867963667e-05, "loss": 0.47750082015991213, "step": 459410 }, { "epoch": 2.730887886299196, "grad_norm": 1.198578953742981, "learning_rate": 2.437643217695276e-05, "loss": 0.5031237602233887, "step": 459420 }, { "epoch": 2.7309473283758643, "grad_norm": 1.331200122833252, "learning_rate": 2.437451489553701e-05, "loss": 0.49892396926879884, "step": 459430 }, { "epoch": 2.7310067704525327, "grad_norm": 1.565598726272583, "learning_rate": 2.4372598023725595e-05, "loss": 0.4289820671081543, "step": 459440 }, { "epoch": 2.7310662125292007, "grad_norm": 1.4475620985031128, "learning_rate": 2.43706815615277e-05, "loss": 0.45001978874206544, "step": 459450 }, { "epoch": 2.7311256546058695, "grad_norm": 1.1243882179260254, "learning_rate": 2.4368765508952486e-05, "loss": 0.46613569259643556, "step": 459460 }, { "epoch": 2.7311850966825375, "grad_norm": 1.821655035018921, "learning_rate": 2.4366849866009093e-05, "loss": 0.49770503044128417, "step": 459470 }, { "epoch": 2.7312445387592064, "grad_norm": 1.000572919845581, "learning_rate": 2.4364934632706714e-05, "loss": 0.4581345558166504, "step": 459480 }, { "epoch": 2.7313039808358743, "grad_norm": 1.2519619464874268, "learning_rate": 2.4363019809054506e-05, "loss": 0.4653456687927246, "step": 459490 }, { "epoch": 2.7313634229125427, "grad_norm": 1.410176396369934, "learning_rate": 2.436110539506162e-05, "loss": 0.47298660278320315, "step": 459500 }, { "epoch": 2.731422864989211, "grad_norm": 1.5299465656280518, "learning_rate": 2.4359191390737228e-05, "loss": 0.4331809997558594, "step": 459510 }, { "epoch": 2.7314823070658796, "grad_norm": 1.45872962474823, "learning_rate": 2.435727779609047e-05, "loss": 0.4973758697509766, "step": 459520 }, { "epoch": 2.731541749142548, "grad_norm": 1.1678088903427124, "learning_rate": 2.4355364611130513e-05, "loss": 0.4531722068786621, "step": 459530 }, { "epoch": 2.7316011912192164, "grad_norm": 1.3083624839782715, "learning_rate": 2.4353451835866484e-05, "loss": 0.4423371315002441, "step": 459540 }, { "epoch": 2.731660633295885, "grad_norm": 1.3171231746673584, "learning_rate": 2.4351539470307565e-05, "loss": 0.47496557235717773, "step": 459550 }, { "epoch": 2.7317200753725532, "grad_norm": 1.2612457275390625, "learning_rate": 2.4349627514462888e-05, "loss": 0.48039979934692384, "step": 459560 }, { "epoch": 2.7317795174492217, "grad_norm": 1.9154402017593384, "learning_rate": 2.4347715968341606e-05, "loss": 0.47892112731933595, "step": 459570 }, { "epoch": 2.73183895952589, "grad_norm": 1.2583836317062378, "learning_rate": 2.434580483195286e-05, "loss": 0.44611444473266604, "step": 459580 }, { "epoch": 2.7318984016025585, "grad_norm": 1.0410821437835693, "learning_rate": 2.4343894105305788e-05, "loss": 0.3799435138702393, "step": 459590 }, { "epoch": 2.731957843679227, "grad_norm": 1.7879620790481567, "learning_rate": 2.4341983788409538e-05, "loss": 0.43137493133544924, "step": 459600 }, { "epoch": 2.7320172857558953, "grad_norm": 1.2446197271347046, "learning_rate": 2.4340073881273238e-05, "loss": 0.43355674743652345, "step": 459610 }, { "epoch": 2.7320767278325637, "grad_norm": 1.3464679718017578, "learning_rate": 2.433816438390603e-05, "loss": 0.4114059925079346, "step": 459620 }, { "epoch": 2.732136169909232, "grad_norm": 0.9640126824378967, "learning_rate": 2.4336255296317058e-05, "loss": 0.4449207305908203, "step": 459630 }, { "epoch": 2.7321956119859, "grad_norm": 1.2327699661254883, "learning_rate": 2.433434661851544e-05, "loss": 0.5007390022277832, "step": 459640 }, { "epoch": 2.732255054062569, "grad_norm": 1.4384524822235107, "learning_rate": 2.4332438350510316e-05, "loss": 0.46593260765075684, "step": 459650 }, { "epoch": 2.732314496139237, "grad_norm": 1.3740615844726562, "learning_rate": 2.43305304923108e-05, "loss": 0.47704758644104006, "step": 459660 }, { "epoch": 2.7323739382159054, "grad_norm": 1.0884884595870972, "learning_rate": 2.432862304392603e-05, "loss": 0.46431851387023926, "step": 459670 }, { "epoch": 2.7324333802925738, "grad_norm": 1.355981707572937, "learning_rate": 2.4326716005365133e-05, "loss": 0.4514430046081543, "step": 459680 }, { "epoch": 2.732492822369242, "grad_norm": 1.3053754568099976, "learning_rate": 2.4324809376637234e-05, "loss": 0.46808929443359376, "step": 459690 }, { "epoch": 2.7325522644459106, "grad_norm": 1.3075685501098633, "learning_rate": 2.4322903157751445e-05, "loss": 0.4967888355255127, "step": 459700 }, { "epoch": 2.732611706522579, "grad_norm": 1.705493688583374, "learning_rate": 2.432099734871689e-05, "loss": 0.5348520278930664, "step": 459710 }, { "epoch": 2.7326711485992474, "grad_norm": 1.3628007173538208, "learning_rate": 2.431909194954268e-05, "loss": 0.4354249477386475, "step": 459720 }, { "epoch": 2.732730590675916, "grad_norm": 1.5697218179702759, "learning_rate": 2.4317186960237935e-05, "loss": 0.44357900619506835, "step": 459730 }, { "epoch": 2.7327900327525843, "grad_norm": 1.2615340948104858, "learning_rate": 2.4315282380811757e-05, "loss": 0.46768674850463865, "step": 459740 }, { "epoch": 2.7328494748292527, "grad_norm": 1.5156155824661255, "learning_rate": 2.431337821127328e-05, "loss": 0.4865670680999756, "step": 459750 }, { "epoch": 2.732908916905921, "grad_norm": 1.5096633434295654, "learning_rate": 2.431147445163159e-05, "loss": 0.49691972732543943, "step": 459760 }, { "epoch": 2.7329683589825895, "grad_norm": 1.4362965822219849, "learning_rate": 2.430957110189581e-05, "loss": 0.5496227264404296, "step": 459770 }, { "epoch": 2.733027801059258, "grad_norm": 1.1003365516662598, "learning_rate": 2.4307668162075028e-05, "loss": 0.4650681495666504, "step": 459780 }, { "epoch": 2.7330872431359263, "grad_norm": 1.3268030881881714, "learning_rate": 2.4305765632178366e-05, "loss": 0.480607271194458, "step": 459790 }, { "epoch": 2.7331466852125947, "grad_norm": 1.414232850074768, "learning_rate": 2.430386351221491e-05, "loss": 0.4892172336578369, "step": 459800 }, { "epoch": 2.7332061272892627, "grad_norm": 1.0044313669204712, "learning_rate": 2.430196180219376e-05, "loss": 0.46850314140319826, "step": 459810 }, { "epoch": 2.7332655693659316, "grad_norm": 1.6530468463897705, "learning_rate": 2.4300060502124037e-05, "loss": 0.47818660736083984, "step": 459820 }, { "epoch": 2.7333250114425995, "grad_norm": 1.0852910280227661, "learning_rate": 2.4298159612014808e-05, "loss": 0.48213539123535154, "step": 459830 }, { "epoch": 2.7333844535192684, "grad_norm": 1.0358282327651978, "learning_rate": 2.4296259131875167e-05, "loss": 0.4536724090576172, "step": 459840 }, { "epoch": 2.7334438955959364, "grad_norm": 1.085822343826294, "learning_rate": 2.4294359061714228e-05, "loss": 0.4598024845123291, "step": 459850 }, { "epoch": 2.733503337672605, "grad_norm": 1.296007752418518, "learning_rate": 2.4292459401541064e-05, "loss": 0.4707964897155762, "step": 459860 }, { "epoch": 2.733562779749273, "grad_norm": 1.5582832098007202, "learning_rate": 2.429056015136474e-05, "loss": 0.4326640605926514, "step": 459870 }, { "epoch": 2.7336222218259416, "grad_norm": 1.1813751459121704, "learning_rate": 2.4288661311194392e-05, "loss": 0.45936336517333987, "step": 459880 }, { "epoch": 2.73368166390261, "grad_norm": 1.103362798690796, "learning_rate": 2.4286762881039093e-05, "loss": 0.5002969741821289, "step": 459890 }, { "epoch": 2.7337411059792784, "grad_norm": 1.3813170194625854, "learning_rate": 2.428486486090787e-05, "loss": 0.4077995777130127, "step": 459900 }, { "epoch": 2.733800548055947, "grad_norm": 1.2482457160949707, "learning_rate": 2.428296725080986e-05, "loss": 0.4191451072692871, "step": 459910 }, { "epoch": 2.7338599901326153, "grad_norm": 1.216926097869873, "learning_rate": 2.4281070050754128e-05, "loss": 0.45694637298583984, "step": 459920 }, { "epoch": 2.7339194322092837, "grad_norm": 1.5948489904403687, "learning_rate": 2.4279173260749724e-05, "loss": 0.4878753662109375, "step": 459930 }, { "epoch": 2.733978874285952, "grad_norm": 1.5255643129348755, "learning_rate": 2.4277276880805757e-05, "loss": 0.467911958694458, "step": 459940 }, { "epoch": 2.7340383163626205, "grad_norm": 1.4180043935775757, "learning_rate": 2.4275380910931297e-05, "loss": 0.4315218448638916, "step": 459950 }, { "epoch": 2.734097758439289, "grad_norm": 1.628676414489746, "learning_rate": 2.427348535113537e-05, "loss": 0.4737688064575195, "step": 459960 }, { "epoch": 2.7341572005159573, "grad_norm": 1.5029720067977905, "learning_rate": 2.4271590201427087e-05, "loss": 0.42754621505737306, "step": 459970 }, { "epoch": 2.7342166425926258, "grad_norm": 1.1458137035369873, "learning_rate": 2.4269695461815497e-05, "loss": 0.435865592956543, "step": 459980 }, { "epoch": 2.734276084669294, "grad_norm": 1.14090096950531, "learning_rate": 2.426780113230968e-05, "loss": 0.4483769416809082, "step": 459990 }, { "epoch": 2.734335526745962, "grad_norm": 1.3124816417694092, "learning_rate": 2.4265907212918665e-05, "loss": 0.4398172855377197, "step": 460000 }, { "epoch": 2.734394968822631, "grad_norm": 1.5029003620147705, "learning_rate": 2.4264013703651553e-05, "loss": 0.48479671478271485, "step": 460010 }, { "epoch": 2.734454410899299, "grad_norm": 1.2422008514404297, "learning_rate": 2.426212060451737e-05, "loss": 0.4503934383392334, "step": 460020 }, { "epoch": 2.734513852975968, "grad_norm": 1.3045694828033447, "learning_rate": 2.4260227915525165e-05, "loss": 0.44641695022583006, "step": 460030 }, { "epoch": 2.734573295052636, "grad_norm": 1.461262583732605, "learning_rate": 2.4258335636684028e-05, "loss": 0.4870245933532715, "step": 460040 }, { "epoch": 2.734632737129304, "grad_norm": 1.8093631267547607, "learning_rate": 2.425644376800299e-05, "loss": 0.44721155166625975, "step": 460050 }, { "epoch": 2.7346921792059726, "grad_norm": 1.3407593965530396, "learning_rate": 2.4254552309491096e-05, "loss": 0.48852195739746096, "step": 460060 }, { "epoch": 2.734751621282641, "grad_norm": 1.2535004615783691, "learning_rate": 2.425266126115742e-05, "loss": 0.4401102066040039, "step": 460070 }, { "epoch": 2.7348110633593095, "grad_norm": 1.1859921216964722, "learning_rate": 2.425077062301098e-05, "loss": 0.445980167388916, "step": 460080 }, { "epoch": 2.734870505435978, "grad_norm": 1.4888112545013428, "learning_rate": 2.424888039506084e-05, "loss": 0.4841987133026123, "step": 460090 }, { "epoch": 2.7349299475126463, "grad_norm": 1.033742904663086, "learning_rate": 2.4246990577316003e-05, "loss": 0.4612607002258301, "step": 460100 }, { "epoch": 2.7349893895893147, "grad_norm": 1.2523777484893799, "learning_rate": 2.4245101169785564e-05, "loss": 0.4393780708312988, "step": 460110 }, { "epoch": 2.735048831665983, "grad_norm": 1.2490705251693726, "learning_rate": 2.424321217247853e-05, "loss": 0.4561725616455078, "step": 460120 }, { "epoch": 2.7351082737426515, "grad_norm": 1.4109852313995361, "learning_rate": 2.424132358540395e-05, "loss": 0.4635335445404053, "step": 460130 }, { "epoch": 2.73516771581932, "grad_norm": 1.594897985458374, "learning_rate": 2.4239435408570844e-05, "loss": 0.46333937644958495, "step": 460140 }, { "epoch": 2.7352271578959884, "grad_norm": 1.4054323434829712, "learning_rate": 2.423754764198825e-05, "loss": 0.4538857460021973, "step": 460150 }, { "epoch": 2.7352865999726568, "grad_norm": 1.4518296718597412, "learning_rate": 2.423566028566519e-05, "loss": 0.47644972801208496, "step": 460160 }, { "epoch": 2.735346042049325, "grad_norm": 1.409501552581787, "learning_rate": 2.4233773339610723e-05, "loss": 0.4462709426879883, "step": 460170 }, { "epoch": 2.7354054841259936, "grad_norm": 1.67665696144104, "learning_rate": 2.423188680383386e-05, "loss": 0.4822948455810547, "step": 460180 }, { "epoch": 2.7354649262026616, "grad_norm": 1.6338939666748047, "learning_rate": 2.4230000678343605e-05, "loss": 0.4852703094482422, "step": 460190 }, { "epoch": 2.7355243682793304, "grad_norm": 1.2621337175369263, "learning_rate": 2.4228114963149005e-05, "loss": 0.4563114166259766, "step": 460200 }, { "epoch": 2.7355838103559984, "grad_norm": 1.1498163938522339, "learning_rate": 2.422622965825907e-05, "loss": 0.47204113006591797, "step": 460210 }, { "epoch": 2.7356432524326673, "grad_norm": 1.496415615081787, "learning_rate": 2.422434476368283e-05, "loss": 0.4716094970703125, "step": 460220 }, { "epoch": 2.7357026945093352, "grad_norm": 1.0216981172561646, "learning_rate": 2.4222460279429265e-05, "loss": 0.47075629234313965, "step": 460230 }, { "epoch": 2.7357621365860036, "grad_norm": 1.0375076532363892, "learning_rate": 2.422057620550744e-05, "loss": 0.45581674575805664, "step": 460240 }, { "epoch": 2.735821578662672, "grad_norm": 1.3090370893478394, "learning_rate": 2.4218692541926344e-05, "loss": 0.4423306941986084, "step": 460250 }, { "epoch": 2.7358810207393405, "grad_norm": 1.1152582168579102, "learning_rate": 2.421680928869499e-05, "loss": 0.519552755355835, "step": 460260 }, { "epoch": 2.735940462816009, "grad_norm": 1.0652852058410645, "learning_rate": 2.421492644582239e-05, "loss": 0.4242897033691406, "step": 460270 }, { "epoch": 2.7359999048926773, "grad_norm": 1.2520313262939453, "learning_rate": 2.4213044013317534e-05, "loss": 0.4681718826293945, "step": 460280 }, { "epoch": 2.7360593469693457, "grad_norm": 1.622818946838379, "learning_rate": 2.4211161991189437e-05, "loss": 0.4874239921569824, "step": 460290 }, { "epoch": 2.736118789046014, "grad_norm": 1.072232961654663, "learning_rate": 2.420928037944712e-05, "loss": 0.4693000793457031, "step": 460300 }, { "epoch": 2.7361782311226825, "grad_norm": 1.3250625133514404, "learning_rate": 2.4207399178099562e-05, "loss": 0.45331315994262694, "step": 460310 }, { "epoch": 2.736237673199351, "grad_norm": 1.4393996000289917, "learning_rate": 2.4205518387155775e-05, "loss": 0.5088733196258545, "step": 460320 }, { "epoch": 2.7362971152760194, "grad_norm": 1.1808440685272217, "learning_rate": 2.420363800662474e-05, "loss": 0.5141455650329589, "step": 460330 }, { "epoch": 2.736356557352688, "grad_norm": 1.2359583377838135, "learning_rate": 2.4201758036515473e-05, "loss": 0.4627490520477295, "step": 460340 }, { "epoch": 2.736415999429356, "grad_norm": 1.4453020095825195, "learning_rate": 2.4199878476836955e-05, "loss": 0.493239164352417, "step": 460350 }, { "epoch": 2.7364754415060246, "grad_norm": 1.300514578819275, "learning_rate": 2.4197999327598163e-05, "loss": 0.4530898094177246, "step": 460360 }, { "epoch": 2.736534883582693, "grad_norm": 1.288076639175415, "learning_rate": 2.4196120588808114e-05, "loss": 0.4365659236907959, "step": 460370 }, { "epoch": 2.736594325659361, "grad_norm": 1.0564860105514526, "learning_rate": 2.4194242260475792e-05, "loss": 0.45651960372924805, "step": 460380 }, { "epoch": 2.73665376773603, "grad_norm": 0.8795798420906067, "learning_rate": 2.4192364342610157e-05, "loss": 0.46897478103637696, "step": 460390 }, { "epoch": 2.736713209812698, "grad_norm": 1.3965942859649658, "learning_rate": 2.4190486835220222e-05, "loss": 0.44368252754211424, "step": 460400 }, { "epoch": 2.7367726518893662, "grad_norm": 0.7890456318855286, "learning_rate": 2.418860973831495e-05, "loss": 0.4265417575836182, "step": 460410 }, { "epoch": 2.7368320939660347, "grad_norm": 1.6309280395507812, "learning_rate": 2.4186733051903306e-05, "loss": 0.4271207809448242, "step": 460420 }, { "epoch": 2.736891536042703, "grad_norm": 1.1153514385223389, "learning_rate": 2.4184856775994306e-05, "loss": 0.46949357986450196, "step": 460430 }, { "epoch": 2.7369509781193715, "grad_norm": 1.2209986448287964, "learning_rate": 2.418298091059692e-05, "loss": 0.43656387329101565, "step": 460440 }, { "epoch": 2.73701042019604, "grad_norm": 1.0679444074630737, "learning_rate": 2.4181105455720102e-05, "loss": 0.48551359176635744, "step": 460450 }, { "epoch": 2.7370698622727083, "grad_norm": 1.3546175956726074, "learning_rate": 2.4179230411372802e-05, "loss": 0.4106718063354492, "step": 460460 }, { "epoch": 2.7371293043493767, "grad_norm": 1.1332780122756958, "learning_rate": 2.417735577756404e-05, "loss": 0.46333799362182615, "step": 460470 }, { "epoch": 2.737188746426045, "grad_norm": 1.272080898284912, "learning_rate": 2.417548155430276e-05, "loss": 0.43924670219421386, "step": 460480 }, { "epoch": 2.7372481885027136, "grad_norm": 1.2978465557098389, "learning_rate": 2.417360774159792e-05, "loss": 0.4656390190124512, "step": 460490 }, { "epoch": 2.737307630579382, "grad_norm": 1.506937026977539, "learning_rate": 2.417173433945851e-05, "loss": 0.48572635650634766, "step": 460500 }, { "epoch": 2.7373670726560504, "grad_norm": 1.023193359375, "learning_rate": 2.4169861347893457e-05, "loss": 0.43607273101806643, "step": 460510 }, { "epoch": 2.737426514732719, "grad_norm": 1.2478829622268677, "learning_rate": 2.416798876691174e-05, "loss": 0.4753105163574219, "step": 460520 }, { "epoch": 2.737485956809387, "grad_norm": 0.9355472922325134, "learning_rate": 2.4166116596522315e-05, "loss": 0.47766432762145994, "step": 460530 }, { "epoch": 2.7375453988860556, "grad_norm": 1.2545477151870728, "learning_rate": 2.416424483673414e-05, "loss": 0.4443018913269043, "step": 460540 }, { "epoch": 2.7376048409627236, "grad_norm": 1.4313379526138306, "learning_rate": 2.4162373487556153e-05, "loss": 0.5077905654907227, "step": 460550 }, { "epoch": 2.7376642830393925, "grad_norm": 1.2830836772918701, "learning_rate": 2.4160502548997343e-05, "loss": 0.48274688720703124, "step": 460560 }, { "epoch": 2.7377237251160604, "grad_norm": 1.4574847221374512, "learning_rate": 2.4158632021066628e-05, "loss": 0.43170642852783203, "step": 460570 }, { "epoch": 2.7377831671927293, "grad_norm": 1.4462273120880127, "learning_rate": 2.4156761903772963e-05, "loss": 0.46332449913024903, "step": 460580 }, { "epoch": 2.7378426092693973, "grad_norm": 1.353579044342041, "learning_rate": 2.4154892197125288e-05, "loss": 0.5093845367431641, "step": 460590 }, { "epoch": 2.7379020513460657, "grad_norm": 1.0650293827056885, "learning_rate": 2.415302290113256e-05, "loss": 0.49209442138671877, "step": 460600 }, { "epoch": 2.737961493422734, "grad_norm": 1.1705842018127441, "learning_rate": 2.4151154015803718e-05, "loss": 0.4938713550567627, "step": 460610 }, { "epoch": 2.7380209354994025, "grad_norm": 1.6535015106201172, "learning_rate": 2.414928554114769e-05, "loss": 0.4756063461303711, "step": 460620 }, { "epoch": 2.738080377576071, "grad_norm": 1.1305696964263916, "learning_rate": 2.4147417477173434e-05, "loss": 0.47824974060058595, "step": 460630 }, { "epoch": 2.7381398196527393, "grad_norm": 1.4499632120132446, "learning_rate": 2.4145549823889878e-05, "loss": 0.5500441551208496, "step": 460640 }, { "epoch": 2.7381992617294078, "grad_norm": 1.2630705833435059, "learning_rate": 2.4143682581305933e-05, "loss": 0.45627427101135254, "step": 460650 }, { "epoch": 2.738258703806076, "grad_norm": 1.4649933576583862, "learning_rate": 2.4141815749430568e-05, "loss": 0.49939746856689454, "step": 460660 }, { "epoch": 2.7383181458827446, "grad_norm": 1.5158675909042358, "learning_rate": 2.41399493282727e-05, "loss": 0.4779537200927734, "step": 460670 }, { "epoch": 2.738377587959413, "grad_norm": 1.3018608093261719, "learning_rate": 2.413808331784126e-05, "loss": 0.45140867233276366, "step": 460680 }, { "epoch": 2.7384370300360814, "grad_norm": 1.344723105430603, "learning_rate": 2.4136217718145162e-05, "loss": 0.42303953170776365, "step": 460690 }, { "epoch": 2.73849647211275, "grad_norm": 1.0669441223144531, "learning_rate": 2.4134352529193333e-05, "loss": 0.4457250595092773, "step": 460700 }, { "epoch": 2.7385559141894182, "grad_norm": 1.8687386512756348, "learning_rate": 2.4132487750994706e-05, "loss": 0.47481207847595214, "step": 460710 }, { "epoch": 2.7386153562660867, "grad_norm": 1.375035047531128, "learning_rate": 2.4130623383558184e-05, "loss": 0.4754389762878418, "step": 460720 }, { "epoch": 2.738674798342755, "grad_norm": 1.0257290601730347, "learning_rate": 2.412875942689271e-05, "loss": 0.4420336723327637, "step": 460730 }, { "epoch": 2.738734240419423, "grad_norm": 1.2451362609863281, "learning_rate": 2.4126895881007196e-05, "loss": 0.4738022804260254, "step": 460740 }, { "epoch": 2.738793682496092, "grad_norm": 1.4525978565216064, "learning_rate": 2.412503274591053e-05, "loss": 0.4573091983795166, "step": 460750 }, { "epoch": 2.73885312457276, "grad_norm": 1.4761687517166138, "learning_rate": 2.4123170021611654e-05, "loss": 0.4578880310058594, "step": 460760 }, { "epoch": 2.7389125666494287, "grad_norm": 1.12975013256073, "learning_rate": 2.4121307708119467e-05, "loss": 0.39549641609191893, "step": 460770 }, { "epoch": 2.7389720087260967, "grad_norm": 1.344818353652954, "learning_rate": 2.411944580544287e-05, "loss": 0.45474882125854493, "step": 460780 }, { "epoch": 2.739031450802765, "grad_norm": 1.6378767490386963, "learning_rate": 2.4117584313590788e-05, "loss": 0.5154641151428223, "step": 460790 }, { "epoch": 2.7390908928794335, "grad_norm": 1.7269951105117798, "learning_rate": 2.4115723232572113e-05, "loss": 0.4553388118743896, "step": 460800 }, { "epoch": 2.739150334956102, "grad_norm": 1.606722116470337, "learning_rate": 2.4113862562395747e-05, "loss": 0.49622354507446287, "step": 460810 }, { "epoch": 2.7392097770327704, "grad_norm": 1.309505820274353, "learning_rate": 2.4112002303070595e-05, "loss": 0.45544090270996096, "step": 460820 }, { "epoch": 2.7392692191094388, "grad_norm": 1.2773317098617554, "learning_rate": 2.411014245460556e-05, "loss": 0.5030194282531738, "step": 460830 }, { "epoch": 2.739328661186107, "grad_norm": 1.9550671577453613, "learning_rate": 2.4108283017009534e-05, "loss": 0.5099889755249023, "step": 460840 }, { "epoch": 2.7393881032627756, "grad_norm": 0.9740496277809143, "learning_rate": 2.410642399029141e-05, "loss": 0.45702447891235354, "step": 460850 }, { "epoch": 2.739447545339444, "grad_norm": 1.5266810655593872, "learning_rate": 2.4104565374460076e-05, "loss": 0.4335519790649414, "step": 460860 }, { "epoch": 2.7395069874161124, "grad_norm": 1.3037419319152832, "learning_rate": 2.4102707169524447e-05, "loss": 0.4456472873687744, "step": 460870 }, { "epoch": 2.739566429492781, "grad_norm": 1.2845596075057983, "learning_rate": 2.4100849375493384e-05, "loss": 0.46358699798583985, "step": 460880 }, { "epoch": 2.7396258715694493, "grad_norm": 1.4541510343551636, "learning_rate": 2.4098991992375794e-05, "loss": 0.48906121253967283, "step": 460890 }, { "epoch": 2.7396853136461177, "grad_norm": 1.184037208557129, "learning_rate": 2.409713502018055e-05, "loss": 0.5033370018005371, "step": 460900 }, { "epoch": 2.739744755722786, "grad_norm": 1.2682734727859497, "learning_rate": 2.4095278458916524e-05, "loss": 0.44418678283691404, "step": 460910 }, { "epoch": 2.7398041977994545, "grad_norm": 1.2861794233322144, "learning_rate": 2.409342230859262e-05, "loss": 0.43987016677856444, "step": 460920 }, { "epoch": 2.7398636398761225, "grad_norm": 1.6750414371490479, "learning_rate": 2.4091566569217737e-05, "loss": 0.4723785400390625, "step": 460930 }, { "epoch": 2.7399230819527913, "grad_norm": 1.2668397426605225, "learning_rate": 2.4089711240800697e-05, "loss": 0.47243824005126955, "step": 460940 }, { "epoch": 2.7399825240294593, "grad_norm": 1.5940542221069336, "learning_rate": 2.4087856323350396e-05, "loss": 0.46700210571289064, "step": 460950 }, { "epoch": 2.740041966106128, "grad_norm": 1.0035228729248047, "learning_rate": 2.408600181687573e-05, "loss": 0.4560483455657959, "step": 460960 }, { "epoch": 2.740101408182796, "grad_norm": 1.1964720487594604, "learning_rate": 2.4084147721385554e-05, "loss": 0.448720645904541, "step": 460970 }, { "epoch": 2.7401608502594645, "grad_norm": 1.2957428693771362, "learning_rate": 2.4082294036888724e-05, "loss": 0.5080722808837891, "step": 460980 }, { "epoch": 2.740220292336133, "grad_norm": 1.1350992918014526, "learning_rate": 2.4080440763394136e-05, "loss": 0.5094221115112305, "step": 460990 }, { "epoch": 2.7402797344128014, "grad_norm": 1.132961630821228, "learning_rate": 2.407858790091063e-05, "loss": 0.48107166290283204, "step": 461000 }, { "epoch": 2.74033917648947, "grad_norm": 1.105831265449524, "learning_rate": 2.407673544944708e-05, "loss": 0.4495786190032959, "step": 461010 }, { "epoch": 2.740398618566138, "grad_norm": 1.3254296779632568, "learning_rate": 2.4074883409012355e-05, "loss": 0.4751983642578125, "step": 461020 }, { "epoch": 2.7404580606428066, "grad_norm": 1.4630708694458008, "learning_rate": 2.4073031779615308e-05, "loss": 0.4657705307006836, "step": 461030 }, { "epoch": 2.740517502719475, "grad_norm": 1.2051945924758911, "learning_rate": 2.4071180561264772e-05, "loss": 0.47434349060058595, "step": 461040 }, { "epoch": 2.7405769447961434, "grad_norm": 1.3559610843658447, "learning_rate": 2.406932975396967e-05, "loss": 0.41297092437744143, "step": 461050 }, { "epoch": 2.740636386872812, "grad_norm": 1.4555124044418335, "learning_rate": 2.406747935773878e-05, "loss": 0.4758049488067627, "step": 461060 }, { "epoch": 2.7406958289494803, "grad_norm": 1.0950473546981812, "learning_rate": 2.4065629372580996e-05, "loss": 0.4190824508666992, "step": 461070 }, { "epoch": 2.7407552710261487, "grad_norm": 1.1355544328689575, "learning_rate": 2.406377979850515e-05, "loss": 0.4304372787475586, "step": 461080 }, { "epoch": 2.740814713102817, "grad_norm": 1.0787121057510376, "learning_rate": 2.4061930635520106e-05, "loss": 0.45270519256591796, "step": 461090 }, { "epoch": 2.7408741551794855, "grad_norm": 1.5630942583084106, "learning_rate": 2.4060081883634693e-05, "loss": 0.4619241714477539, "step": 461100 }, { "epoch": 2.740933597256154, "grad_norm": 1.0919735431671143, "learning_rate": 2.405823354285777e-05, "loss": 0.4349708080291748, "step": 461110 }, { "epoch": 2.740993039332822, "grad_norm": 1.3407765626907349, "learning_rate": 2.4056385613198167e-05, "loss": 0.4653541088104248, "step": 461120 }, { "epoch": 2.7410524814094908, "grad_norm": 0.9696437120437622, "learning_rate": 2.405453809466474e-05, "loss": 0.49069485664367674, "step": 461130 }, { "epoch": 2.7411119234861587, "grad_norm": 1.3354923725128174, "learning_rate": 2.4052690987266292e-05, "loss": 0.5235899925231934, "step": 461140 }, { "epoch": 2.741171365562827, "grad_norm": 1.3220809698104858, "learning_rate": 2.40508442910117e-05, "loss": 0.4297954082489014, "step": 461150 }, { "epoch": 2.7412308076394956, "grad_norm": 1.679572582244873, "learning_rate": 2.4048998005909777e-05, "loss": 0.4643204689025879, "step": 461160 }, { "epoch": 2.741290249716164, "grad_norm": 1.4015804529190063, "learning_rate": 2.4047152131969357e-05, "loss": 0.4730068683624268, "step": 461170 }, { "epoch": 2.7413496917928324, "grad_norm": 1.5034096240997314, "learning_rate": 2.4045306669199276e-05, "loss": 0.5263311862945557, "step": 461180 }, { "epoch": 2.741409133869501, "grad_norm": 1.5349966287612915, "learning_rate": 2.404346161760836e-05, "loss": 0.5019052505493165, "step": 461190 }, { "epoch": 2.741468575946169, "grad_norm": 1.6471275091171265, "learning_rate": 2.4041616977205422e-05, "loss": 0.4979051113128662, "step": 461200 }, { "epoch": 2.7415280180228376, "grad_norm": 1.269097924232483, "learning_rate": 2.403977274799929e-05, "loss": 0.5100103378295898, "step": 461210 }, { "epoch": 2.741587460099506, "grad_norm": 1.6350096464157104, "learning_rate": 2.4037928929998814e-05, "loss": 0.4503779411315918, "step": 461220 }, { "epoch": 2.7416469021761745, "grad_norm": 1.2459758520126343, "learning_rate": 2.4036085523212788e-05, "loss": 0.49178338050842285, "step": 461230 }, { "epoch": 2.741706344252843, "grad_norm": 1.5006937980651855, "learning_rate": 2.4034242527650026e-05, "loss": 0.45377635955810547, "step": 461240 }, { "epoch": 2.7417657863295113, "grad_norm": 1.0846763849258423, "learning_rate": 2.403239994331936e-05, "loss": 0.43933629989624023, "step": 461250 }, { "epoch": 2.7418252284061797, "grad_norm": 1.3370585441589355, "learning_rate": 2.40305577702296e-05, "loss": 0.49790172576904296, "step": 461260 }, { "epoch": 2.741884670482848, "grad_norm": 1.1434346437454224, "learning_rate": 2.402871600838954e-05, "loss": 0.4402811050415039, "step": 461270 }, { "epoch": 2.7419441125595165, "grad_norm": 1.3439611196517944, "learning_rate": 2.402687465780803e-05, "loss": 0.43065338134765624, "step": 461280 }, { "epoch": 2.7420035546361845, "grad_norm": 1.4825365543365479, "learning_rate": 2.402503371849385e-05, "loss": 0.4091294765472412, "step": 461290 }, { "epoch": 2.7420629967128534, "grad_norm": 1.264784336090088, "learning_rate": 2.40231931904558e-05, "loss": 0.4854735374450684, "step": 461300 }, { "epoch": 2.7421224387895213, "grad_norm": 1.0008407831192017, "learning_rate": 2.402135307370271e-05, "loss": 0.4856691360473633, "step": 461310 }, { "epoch": 2.74218188086619, "grad_norm": 1.2804741859436035, "learning_rate": 2.4019513368243367e-05, "loss": 0.4333346366882324, "step": 461320 }, { "epoch": 2.742241322942858, "grad_norm": 1.1603472232818604, "learning_rate": 2.4017674074086568e-05, "loss": 0.4441686630249023, "step": 461330 }, { "epoch": 2.7423007650195266, "grad_norm": 1.439610242843628, "learning_rate": 2.4015835191241114e-05, "loss": 0.45578441619873045, "step": 461340 }, { "epoch": 2.742360207096195, "grad_norm": 1.0408201217651367, "learning_rate": 2.4013996719715808e-05, "loss": 0.4230502128601074, "step": 461350 }, { "epoch": 2.7424196491728634, "grad_norm": 1.256701111793518, "learning_rate": 2.401215865951944e-05, "loss": 0.4587067127227783, "step": 461360 }, { "epoch": 2.742479091249532, "grad_norm": 1.7073743343353271, "learning_rate": 2.4010321010660808e-05, "loss": 0.47077102661132814, "step": 461370 }, { "epoch": 2.7425385333262002, "grad_norm": 1.0890836715698242, "learning_rate": 2.4008483773148702e-05, "loss": 0.4906484603881836, "step": 461380 }, { "epoch": 2.7425979754028686, "grad_norm": 1.029038906097412, "learning_rate": 2.4006646946991896e-05, "loss": 0.4534811019897461, "step": 461390 }, { "epoch": 2.742657417479537, "grad_norm": 1.5575265884399414, "learning_rate": 2.400481053219918e-05, "loss": 0.4799331188201904, "step": 461400 }, { "epoch": 2.7427168595562055, "grad_norm": 1.4393876791000366, "learning_rate": 2.4002974528779365e-05, "loss": 0.47336225509643554, "step": 461410 }, { "epoch": 2.742776301632874, "grad_norm": 0.8317350745201111, "learning_rate": 2.4001138936741218e-05, "loss": 0.42311849594116213, "step": 461420 }, { "epoch": 2.7428357437095423, "grad_norm": 1.6478523015975952, "learning_rate": 2.399930375609352e-05, "loss": 0.5362708091735839, "step": 461430 }, { "epoch": 2.7428951857862107, "grad_norm": 1.5230778455734253, "learning_rate": 2.399746898684503e-05, "loss": 0.4202634334564209, "step": 461440 }, { "epoch": 2.742954627862879, "grad_norm": 1.3401490449905396, "learning_rate": 2.3995634629004553e-05, "loss": 0.4315162181854248, "step": 461450 }, { "epoch": 2.7430140699395476, "grad_norm": 1.3332949876785278, "learning_rate": 2.399380068258085e-05, "loss": 0.3974665641784668, "step": 461460 }, { "epoch": 2.743073512016216, "grad_norm": 0.8539186120033264, "learning_rate": 2.399196714758269e-05, "loss": 0.47338285446166994, "step": 461470 }, { "epoch": 2.743132954092884, "grad_norm": 1.2658933401107788, "learning_rate": 2.3990134024018865e-05, "loss": 0.5210975646972656, "step": 461480 }, { "epoch": 2.743192396169553, "grad_norm": 1.253111481666565, "learning_rate": 2.3988301311898132e-05, "loss": 0.45446271896362306, "step": 461490 }, { "epoch": 2.7432518382462208, "grad_norm": 1.386641025543213, "learning_rate": 2.398646901122924e-05, "loss": 0.4477346420288086, "step": 461500 }, { "epoch": 2.7433112803228896, "grad_norm": 1.0321365594863892, "learning_rate": 2.3984637122020983e-05, "loss": 0.4405195236206055, "step": 461510 }, { "epoch": 2.7433707223995576, "grad_norm": 1.3333609104156494, "learning_rate": 2.3982805644282117e-05, "loss": 0.44707484245300294, "step": 461520 }, { "epoch": 2.743430164476226, "grad_norm": 1.3631396293640137, "learning_rate": 2.398097457802138e-05, "loss": 0.4640204429626465, "step": 461530 }, { "epoch": 2.7434896065528944, "grad_norm": 1.3836005926132202, "learning_rate": 2.397914392324756e-05, "loss": 0.4360373497009277, "step": 461540 }, { "epoch": 2.743549048629563, "grad_norm": 1.1894168853759766, "learning_rate": 2.3977313679969414e-05, "loss": 0.43769354820251466, "step": 461550 }, { "epoch": 2.7436084907062313, "grad_norm": 1.341163158416748, "learning_rate": 2.3975483848195684e-05, "loss": 0.43255157470703126, "step": 461560 }, { "epoch": 2.7436679327828997, "grad_norm": 2.077537775039673, "learning_rate": 2.3973654427935104e-05, "loss": 0.49840030670166013, "step": 461570 }, { "epoch": 2.743727374859568, "grad_norm": 1.1947026252746582, "learning_rate": 2.397182541919646e-05, "loss": 0.46449432373046873, "step": 461580 }, { "epoch": 2.7437868169362365, "grad_norm": 1.1251791715621948, "learning_rate": 2.3969996821988495e-05, "loss": 0.4248355388641357, "step": 461590 }, { "epoch": 2.743846259012905, "grad_norm": 1.2917909622192383, "learning_rate": 2.3968168636319947e-05, "loss": 0.48814949989318845, "step": 461600 }, { "epoch": 2.7439057010895733, "grad_norm": 1.1699507236480713, "learning_rate": 2.396634086219957e-05, "loss": 0.4413431167602539, "step": 461610 }, { "epoch": 2.7439651431662417, "grad_norm": 1.450553059577942, "learning_rate": 2.3964513499636092e-05, "loss": 0.43877344131469725, "step": 461620 }, { "epoch": 2.74402458524291, "grad_norm": 1.2917293310165405, "learning_rate": 2.3962686548638258e-05, "loss": 0.5036271095275879, "step": 461630 }, { "epoch": 2.7440840273195786, "grad_norm": 1.3122402429580688, "learning_rate": 2.3960860009214828e-05, "loss": 0.47658562660217285, "step": 461640 }, { "epoch": 2.744143469396247, "grad_norm": 1.390987515449524, "learning_rate": 2.3959033881374525e-05, "loss": 0.5200090408325195, "step": 461650 }, { "epoch": 2.7442029114729154, "grad_norm": 1.4078168869018555, "learning_rate": 2.395720816512608e-05, "loss": 0.4672278881072998, "step": 461660 }, { "epoch": 2.7442623535495834, "grad_norm": 1.3381643295288086, "learning_rate": 2.3955382860478242e-05, "loss": 0.46597490310668943, "step": 461670 }, { "epoch": 2.7443217956262522, "grad_norm": 1.159287929534912, "learning_rate": 2.3953557967439734e-05, "loss": 0.49308290481567385, "step": 461680 }, { "epoch": 2.74438123770292, "grad_norm": 0.9200329184532166, "learning_rate": 2.395173348601927e-05, "loss": 0.45273637771606445, "step": 461690 }, { "epoch": 2.744440679779589, "grad_norm": 1.3190971612930298, "learning_rate": 2.3949909416225587e-05, "loss": 0.49500532150268556, "step": 461700 }, { "epoch": 2.744500121856257, "grad_norm": 1.0823984146118164, "learning_rate": 2.3948085758067435e-05, "loss": 0.4109483242034912, "step": 461710 }, { "epoch": 2.7445595639329254, "grad_norm": 1.2501757144927979, "learning_rate": 2.3946262511553508e-05, "loss": 0.4501375198364258, "step": 461720 }, { "epoch": 2.744619006009594, "grad_norm": 1.1655230522155762, "learning_rate": 2.3944439676692545e-05, "loss": 0.4895695686340332, "step": 461730 }, { "epoch": 2.7446784480862623, "grad_norm": 1.2933976650238037, "learning_rate": 2.3942617253493254e-05, "loss": 0.44040837287902834, "step": 461740 }, { "epoch": 2.7447378901629307, "grad_norm": 0.9100303649902344, "learning_rate": 2.3940795241964366e-05, "loss": 0.4596431732177734, "step": 461750 }, { "epoch": 2.744797332239599, "grad_norm": 1.379448413848877, "learning_rate": 2.3938973642114574e-05, "loss": 0.48894639015197755, "step": 461760 }, { "epoch": 2.7448567743162675, "grad_norm": 1.400161623954773, "learning_rate": 2.3937152453952618e-05, "loss": 0.4508199214935303, "step": 461770 }, { "epoch": 2.744916216392936, "grad_norm": 1.2778558731079102, "learning_rate": 2.3935331677487196e-05, "loss": 0.49597673416137694, "step": 461780 }, { "epoch": 2.7449756584696043, "grad_norm": 1.2766321897506714, "learning_rate": 2.3933511312727028e-05, "loss": 0.48293190002441405, "step": 461790 }, { "epoch": 2.7450351005462728, "grad_norm": 1.3270124197006226, "learning_rate": 2.393169135968081e-05, "loss": 0.4797189712524414, "step": 461800 }, { "epoch": 2.745094542622941, "grad_norm": 1.5392755270004272, "learning_rate": 2.392987181835725e-05, "loss": 0.4895769119262695, "step": 461810 }, { "epoch": 2.7451539846996096, "grad_norm": 1.5068974494934082, "learning_rate": 2.3928052688765055e-05, "loss": 0.48763837814331057, "step": 461820 }, { "epoch": 2.745213426776278, "grad_norm": 1.8552662134170532, "learning_rate": 2.3926233970912927e-05, "loss": 0.4788325309753418, "step": 461830 }, { "epoch": 2.7452728688529464, "grad_norm": 1.3502734899520874, "learning_rate": 2.3924415664809572e-05, "loss": 0.43375244140625, "step": 461840 }, { "epoch": 2.745332310929615, "grad_norm": 1.2243825197219849, "learning_rate": 2.3922597770463675e-05, "loss": 0.4493064880371094, "step": 461850 }, { "epoch": 2.745391753006283, "grad_norm": 1.3344495296478271, "learning_rate": 2.392078028788395e-05, "loss": 0.4668013095855713, "step": 461860 }, { "epoch": 2.7454511950829517, "grad_norm": 1.3323076963424683, "learning_rate": 2.3918963217079076e-05, "loss": 0.5044454574584961, "step": 461870 }, { "epoch": 2.7455106371596196, "grad_norm": 1.1268751621246338, "learning_rate": 2.3917146558057755e-05, "loss": 0.434252405166626, "step": 461880 }, { "epoch": 2.745570079236288, "grad_norm": 1.2777425050735474, "learning_rate": 2.391533031082866e-05, "loss": 0.4623429298400879, "step": 461890 }, { "epoch": 2.7456295213129565, "grad_norm": 1.3814762830734253, "learning_rate": 2.39135144754005e-05, "loss": 0.4958508491516113, "step": 461900 }, { "epoch": 2.745688963389625, "grad_norm": 1.2932931184768677, "learning_rate": 2.3911699051781954e-05, "loss": 0.48201684951782225, "step": 461910 }, { "epoch": 2.7457484054662933, "grad_norm": 1.3588389158248901, "learning_rate": 2.390988403998172e-05, "loss": 0.5008209705352783, "step": 461920 }, { "epoch": 2.7458078475429617, "grad_norm": 1.3313524723052979, "learning_rate": 2.3908069440008436e-05, "loss": 0.43375530242919924, "step": 461930 }, { "epoch": 2.74586728961963, "grad_norm": 1.1219223737716675, "learning_rate": 2.3906255251870833e-05, "loss": 0.44768199920654295, "step": 461940 }, { "epoch": 2.7459267316962985, "grad_norm": 1.4868311882019043, "learning_rate": 2.3904441475577565e-05, "loss": 0.4441274642944336, "step": 461950 }, { "epoch": 2.745986173772967, "grad_norm": 1.309919834136963, "learning_rate": 2.39026281111373e-05, "loss": 0.5014663219451905, "step": 461960 }, { "epoch": 2.7460456158496354, "grad_norm": 1.4412589073181152, "learning_rate": 2.3900815158558738e-05, "loss": 0.4223922252655029, "step": 461970 }, { "epoch": 2.7461050579263038, "grad_norm": 1.4528238773345947, "learning_rate": 2.3899002617850553e-05, "loss": 0.42153215408325195, "step": 461980 }, { "epoch": 2.746164500002972, "grad_norm": 1.2364352941513062, "learning_rate": 2.389719048902138e-05, "loss": 0.44652042388916013, "step": 461990 }, { "epoch": 2.7462239420796406, "grad_norm": 1.4369136095046997, "learning_rate": 2.389537877207991e-05, "loss": 0.4153904914855957, "step": 462000 }, { "epoch": 2.746283384156309, "grad_norm": 1.4860870838165283, "learning_rate": 2.3893567467034818e-05, "loss": 0.4993902683258057, "step": 462010 }, { "epoch": 2.7463428262329774, "grad_norm": 1.2223050594329834, "learning_rate": 2.3891756573894746e-05, "loss": 0.4540563583374023, "step": 462020 }, { "epoch": 2.7464022683096454, "grad_norm": 1.626362681388855, "learning_rate": 2.3889946092668378e-05, "loss": 0.467488431930542, "step": 462030 }, { "epoch": 2.7464617103863143, "grad_norm": 1.0748380422592163, "learning_rate": 2.3888136023364385e-05, "loss": 0.42647671699523926, "step": 462040 }, { "epoch": 2.7465211524629822, "grad_norm": 1.149529218673706, "learning_rate": 2.3886326365991393e-05, "loss": 0.5023781776428222, "step": 462050 }, { "epoch": 2.746580594539651, "grad_norm": 1.1804407835006714, "learning_rate": 2.3884517120558062e-05, "loss": 0.47740812301635743, "step": 462060 }, { "epoch": 2.746640036616319, "grad_norm": 1.0556724071502686, "learning_rate": 2.3882708287073065e-05, "loss": 0.4343446731567383, "step": 462070 }, { "epoch": 2.7466994786929875, "grad_norm": 1.4420579671859741, "learning_rate": 2.388089986554505e-05, "loss": 0.4504185676574707, "step": 462080 }, { "epoch": 2.746758920769656, "grad_norm": 0.9937002658843994, "learning_rate": 2.3879091855982655e-05, "loss": 0.46594867706298826, "step": 462090 }, { "epoch": 2.7468183628463243, "grad_norm": 1.2251018285751343, "learning_rate": 2.3877284258394565e-05, "loss": 0.5011266231536865, "step": 462100 }, { "epoch": 2.7468778049229927, "grad_norm": 1.2801764011383057, "learning_rate": 2.3875477072789393e-05, "loss": 0.47432765960693357, "step": 462110 }, { "epoch": 2.746937246999661, "grad_norm": 1.415253758430481, "learning_rate": 2.387367029917578e-05, "loss": 0.45786352157592775, "step": 462120 }, { "epoch": 2.7469966890763295, "grad_norm": 1.4135572910308838, "learning_rate": 2.3871863937562392e-05, "loss": 0.453904914855957, "step": 462130 }, { "epoch": 2.747056131152998, "grad_norm": 1.548579454421997, "learning_rate": 2.387005798795785e-05, "loss": 0.4966866493225098, "step": 462140 }, { "epoch": 2.7471155732296664, "grad_norm": 1.1368168592453003, "learning_rate": 2.38682524503708e-05, "loss": 0.434660530090332, "step": 462150 }, { "epoch": 2.747175015306335, "grad_norm": 1.2360085248947144, "learning_rate": 2.3866447324809913e-05, "loss": 0.512089204788208, "step": 462160 }, { "epoch": 2.747234457383003, "grad_norm": 1.939744234085083, "learning_rate": 2.3864642611283773e-05, "loss": 0.49672698974609375, "step": 462170 }, { "epoch": 2.7472938994596716, "grad_norm": 1.5997265577316284, "learning_rate": 2.386283830980104e-05, "loss": 0.4608463764190674, "step": 462180 }, { "epoch": 2.74735334153634, "grad_norm": 1.1154685020446777, "learning_rate": 2.386103442037032e-05, "loss": 0.4245628833770752, "step": 462190 }, { "epoch": 2.7474127836130084, "grad_norm": 1.4569498300552368, "learning_rate": 2.3859230943000265e-05, "loss": 0.4914088726043701, "step": 462200 }, { "epoch": 2.747472225689677, "grad_norm": 1.2920265197753906, "learning_rate": 2.385742787769951e-05, "loss": 0.5036449432373047, "step": 462210 }, { "epoch": 2.747531667766345, "grad_norm": 1.1417875289916992, "learning_rate": 2.3855625224476668e-05, "loss": 0.44441757202148435, "step": 462220 }, { "epoch": 2.7475911098430137, "grad_norm": 1.3232882022857666, "learning_rate": 2.385382298334036e-05, "loss": 0.4822687149047852, "step": 462230 }, { "epoch": 2.7476505519196817, "grad_norm": 1.2953801155090332, "learning_rate": 2.385202115429921e-05, "loss": 0.4761686325073242, "step": 462240 }, { "epoch": 2.7477099939963505, "grad_norm": 1.203243374824524, "learning_rate": 2.385021973736183e-05, "loss": 0.4271261215209961, "step": 462250 }, { "epoch": 2.7477694360730185, "grad_norm": 1.1823792457580566, "learning_rate": 2.3848418732536857e-05, "loss": 0.4792987823486328, "step": 462260 }, { "epoch": 2.747828878149687, "grad_norm": 1.4728343486785889, "learning_rate": 2.3846618139832887e-05, "loss": 0.48074755668640134, "step": 462270 }, { "epoch": 2.7478883202263553, "grad_norm": 1.5905499458312988, "learning_rate": 2.384481795925854e-05, "loss": 0.48978185653686523, "step": 462280 }, { "epoch": 2.7479477623030237, "grad_norm": 1.049707055091858, "learning_rate": 2.3843018190822426e-05, "loss": 0.44793119430541994, "step": 462290 }, { "epoch": 2.748007204379692, "grad_norm": 1.2048650979995728, "learning_rate": 2.3841218834533167e-05, "loss": 0.43923177719116213, "step": 462300 }, { "epoch": 2.7480666464563606, "grad_norm": 1.172433853149414, "learning_rate": 2.3839419890399353e-05, "loss": 0.47392873764038085, "step": 462310 }, { "epoch": 2.748126088533029, "grad_norm": 1.3022743463516235, "learning_rate": 2.383762135842959e-05, "loss": 0.4885589599609375, "step": 462320 }, { "epoch": 2.7481855306096974, "grad_norm": 1.5387938022613525, "learning_rate": 2.3835823238632498e-05, "loss": 0.46489763259887695, "step": 462330 }, { "epoch": 2.748244972686366, "grad_norm": 1.2557123899459839, "learning_rate": 2.383402553101667e-05, "loss": 0.4437582015991211, "step": 462340 }, { "epoch": 2.748304414763034, "grad_norm": 1.1726984977722168, "learning_rate": 2.3832228235590703e-05, "loss": 0.4830655097961426, "step": 462350 }, { "epoch": 2.7483638568397026, "grad_norm": 1.2525322437286377, "learning_rate": 2.383043135236319e-05, "loss": 0.4490200042724609, "step": 462360 }, { "epoch": 2.748423298916371, "grad_norm": 1.795072317123413, "learning_rate": 2.382863488134274e-05, "loss": 0.4993340492248535, "step": 462370 }, { "epoch": 2.7484827409930395, "grad_norm": 1.4018291234970093, "learning_rate": 2.3826838822537928e-05, "loss": 0.4544841289520264, "step": 462380 }, { "epoch": 2.748542183069708, "grad_norm": 1.7001979351043701, "learning_rate": 2.382504317595736e-05, "loss": 0.4865566253662109, "step": 462390 }, { "epoch": 2.7486016251463763, "grad_norm": 1.1511859893798828, "learning_rate": 2.3823247941609632e-05, "loss": 0.4394833564758301, "step": 462400 }, { "epoch": 2.7486610672230443, "grad_norm": 1.2015912532806396, "learning_rate": 2.3821453119503335e-05, "loss": 0.4388298034667969, "step": 462410 }, { "epoch": 2.748720509299713, "grad_norm": 1.1571862697601318, "learning_rate": 2.381965870964702e-05, "loss": 0.449587345123291, "step": 462420 }, { "epoch": 2.748779951376381, "grad_norm": 1.1594452857971191, "learning_rate": 2.3817864712049305e-05, "loss": 0.4732980728149414, "step": 462430 }, { "epoch": 2.74883939345305, "grad_norm": 0.9099866151809692, "learning_rate": 2.3816071126718756e-05, "loss": 0.409542179107666, "step": 462440 }, { "epoch": 2.748898835529718, "grad_norm": 1.3031363487243652, "learning_rate": 2.3814277953663943e-05, "loss": 0.45554242134094236, "step": 462450 }, { "epoch": 2.7489582776063863, "grad_norm": 1.4984891414642334, "learning_rate": 2.3812485192893477e-05, "loss": 0.4438033580780029, "step": 462460 }, { "epoch": 2.7490177196830548, "grad_norm": 1.1564289331436157, "learning_rate": 2.3810692844415934e-05, "loss": 0.4694709300994873, "step": 462470 }, { "epoch": 2.749077161759723, "grad_norm": 1.514832615852356, "learning_rate": 2.3808900908239828e-05, "loss": 0.4524549007415771, "step": 462480 }, { "epoch": 2.7491366038363916, "grad_norm": 1.3973355293273926, "learning_rate": 2.3807109384373803e-05, "loss": 0.5093708515167237, "step": 462490 }, { "epoch": 2.74919604591306, "grad_norm": 1.1887500286102295, "learning_rate": 2.380531827282638e-05, "loss": 0.46320180892944335, "step": 462500 }, { "epoch": 2.7492554879897284, "grad_norm": 1.2381235361099243, "learning_rate": 2.380352757360615e-05, "loss": 0.4689492702484131, "step": 462510 }, { "epoch": 2.749314930066397, "grad_norm": 1.160320520401001, "learning_rate": 2.380173728672168e-05, "loss": 0.4478268623352051, "step": 462520 }, { "epoch": 2.7493743721430652, "grad_norm": 1.203627347946167, "learning_rate": 2.3799947412181537e-05, "loss": 0.43241162300109864, "step": 462530 }, { "epoch": 2.7494338142197337, "grad_norm": 1.376537561416626, "learning_rate": 2.379815794999427e-05, "loss": 0.3971822261810303, "step": 462540 }, { "epoch": 2.749493256296402, "grad_norm": 1.3583080768585205, "learning_rate": 2.3796368900168422e-05, "loss": 0.4518287658691406, "step": 462550 }, { "epoch": 2.7495526983730705, "grad_norm": 1.1284781694412231, "learning_rate": 2.3794580262712594e-05, "loss": 0.4641414165496826, "step": 462560 }, { "epoch": 2.749612140449739, "grad_norm": 1.4509711265563965, "learning_rate": 2.3792792037635322e-05, "loss": 0.4611762046813965, "step": 462570 }, { "epoch": 2.749671582526407, "grad_norm": 1.3749256134033203, "learning_rate": 2.379100422494515e-05, "loss": 0.4814589500427246, "step": 462580 }, { "epoch": 2.7497310246030757, "grad_norm": 1.1599540710449219, "learning_rate": 2.378921682465066e-05, "loss": 0.4583831787109375, "step": 462590 }, { "epoch": 2.7497904666797437, "grad_norm": 1.3853269815444946, "learning_rate": 2.3787429836760367e-05, "loss": 0.46215190887451174, "step": 462600 }, { "epoch": 2.7498499087564126, "grad_norm": 1.4229942560195923, "learning_rate": 2.378564326128283e-05, "loss": 0.44669694900512696, "step": 462610 }, { "epoch": 2.7499093508330805, "grad_norm": 1.095631718635559, "learning_rate": 2.3783857098226616e-05, "loss": 0.42734594345092775, "step": 462620 }, { "epoch": 2.749968792909749, "grad_norm": 1.565172791481018, "learning_rate": 2.3782071347600246e-05, "loss": 0.5306827068328858, "step": 462630 }, { "epoch": 2.7500282349864174, "grad_norm": 1.2868520021438599, "learning_rate": 2.378028600941227e-05, "loss": 0.4209590911865234, "step": 462640 }, { "epoch": 2.7500876770630858, "grad_norm": 1.2700990438461304, "learning_rate": 2.3778501083671228e-05, "loss": 0.46151161193847656, "step": 462650 }, { "epoch": 2.750147119139754, "grad_norm": 1.0597666501998901, "learning_rate": 2.3776716570385667e-05, "loss": 0.48290605545043946, "step": 462660 }, { "epoch": 2.7502065612164226, "grad_norm": 1.513219952583313, "learning_rate": 2.377493246956411e-05, "loss": 0.4887065887451172, "step": 462670 }, { "epoch": 2.750266003293091, "grad_norm": 1.2954349517822266, "learning_rate": 2.3773148781215088e-05, "loss": 0.5249560356140137, "step": 462680 }, { "epoch": 2.7503254453697594, "grad_norm": 1.0161378383636475, "learning_rate": 2.3771365505347153e-05, "loss": 0.4894989490509033, "step": 462690 }, { "epoch": 2.750384887446428, "grad_norm": 1.1419618129730225, "learning_rate": 2.3769582641968823e-05, "loss": 0.4500019073486328, "step": 462700 }, { "epoch": 2.7504443295230963, "grad_norm": 1.100710153579712, "learning_rate": 2.376780019108864e-05, "loss": 0.4429986000061035, "step": 462710 }, { "epoch": 2.7505037715997647, "grad_norm": 1.7502797842025757, "learning_rate": 2.3766018152715106e-05, "loss": 0.46532611846923827, "step": 462720 }, { "epoch": 2.750563213676433, "grad_norm": 1.5158742666244507, "learning_rate": 2.376423652685677e-05, "loss": 0.5135293960571289, "step": 462730 }, { "epoch": 2.7506226557531015, "grad_norm": 1.0494332313537598, "learning_rate": 2.3762455313522132e-05, "loss": 0.4675633907318115, "step": 462740 }, { "epoch": 2.75068209782977, "grad_norm": 1.4715920686721802, "learning_rate": 2.3760674512719732e-05, "loss": 0.4302023410797119, "step": 462750 }, { "epoch": 2.7507415399064383, "grad_norm": 1.1372621059417725, "learning_rate": 2.3758894124458082e-05, "loss": 0.492120361328125, "step": 462760 }, { "epoch": 2.7508009819831063, "grad_norm": 1.3599636554718018, "learning_rate": 2.3757114148745702e-05, "loss": 0.4616800308227539, "step": 462770 }, { "epoch": 2.750860424059775, "grad_norm": 1.3619811534881592, "learning_rate": 2.3755334585591094e-05, "loss": 0.46298489570617674, "step": 462780 }, { "epoch": 2.750919866136443, "grad_norm": 1.3892216682434082, "learning_rate": 2.375355543500279e-05, "loss": 0.48417110443115235, "step": 462790 }, { "epoch": 2.750979308213112, "grad_norm": 1.5396134853363037, "learning_rate": 2.375177669698929e-05, "loss": 0.4251537322998047, "step": 462800 }, { "epoch": 2.75103875028978, "grad_norm": 1.5159003734588623, "learning_rate": 2.374999837155909e-05, "loss": 0.4857828140258789, "step": 462810 }, { "epoch": 2.7510981923664484, "grad_norm": 1.0420770645141602, "learning_rate": 2.3748220458720724e-05, "loss": 0.4796929836273193, "step": 462820 }, { "epoch": 2.751157634443117, "grad_norm": 1.0243765115737915, "learning_rate": 2.3746442958482688e-05, "loss": 0.44226560592651365, "step": 462830 }, { "epoch": 2.751217076519785, "grad_norm": 2.0784425735473633, "learning_rate": 2.3744665870853476e-05, "loss": 0.4682943820953369, "step": 462840 }, { "epoch": 2.7512765185964536, "grad_norm": 1.244803547859192, "learning_rate": 2.3742889195841596e-05, "loss": 0.44266324043273925, "step": 462850 }, { "epoch": 2.751335960673122, "grad_norm": 1.5626124143600464, "learning_rate": 2.3741112933455538e-05, "loss": 0.4960758209228516, "step": 462860 }, { "epoch": 2.7513954027497904, "grad_norm": 1.3658050298690796, "learning_rate": 2.37393370837038e-05, "loss": 0.4633944988250732, "step": 462870 }, { "epoch": 2.751454844826459, "grad_norm": 1.0112544298171997, "learning_rate": 2.3737561646594897e-05, "loss": 0.4920199394226074, "step": 462880 }, { "epoch": 2.7515142869031273, "grad_norm": 2.2269411087036133, "learning_rate": 2.37357866221373e-05, "loss": 0.4923027515411377, "step": 462890 }, { "epoch": 2.7515737289797957, "grad_norm": 1.204013466835022, "learning_rate": 2.3734012010339517e-05, "loss": 0.479793119430542, "step": 462900 }, { "epoch": 2.751633171056464, "grad_norm": 1.3445029258728027, "learning_rate": 2.3732237811210027e-05, "loss": 0.45911741256713867, "step": 462910 }, { "epoch": 2.7516926131331325, "grad_norm": 1.2651972770690918, "learning_rate": 2.3730464024757314e-05, "loss": 0.5041205406188964, "step": 462920 }, { "epoch": 2.751752055209801, "grad_norm": 1.0847762823104858, "learning_rate": 2.3728690650989873e-05, "loss": 0.4618827819824219, "step": 462930 }, { "epoch": 2.7518114972864693, "grad_norm": 1.1803275346755981, "learning_rate": 2.372691768991617e-05, "loss": 0.4173421859741211, "step": 462940 }, { "epoch": 2.7518709393631378, "grad_norm": 1.6662085056304932, "learning_rate": 2.372514514154471e-05, "loss": 0.4540445327758789, "step": 462950 }, { "epoch": 2.7519303814398057, "grad_norm": 1.1101288795471191, "learning_rate": 2.3723373005883972e-05, "loss": 0.4572138786315918, "step": 462960 }, { "epoch": 2.7519898235164746, "grad_norm": 1.5339579582214355, "learning_rate": 2.3721601282942397e-05, "loss": 0.43965463638305663, "step": 462970 }, { "epoch": 2.7520492655931426, "grad_norm": 1.3294804096221924, "learning_rate": 2.3719829972728492e-05, "loss": 0.4576591491699219, "step": 462980 }, { "epoch": 2.7521087076698114, "grad_norm": 1.2370998859405518, "learning_rate": 2.3718059075250733e-05, "loss": 0.4714644432067871, "step": 462990 }, { "epoch": 2.7521681497464794, "grad_norm": 0.9313926696777344, "learning_rate": 2.371628859051757e-05, "loss": 0.5024327278137207, "step": 463000 }, { "epoch": 2.752227591823148, "grad_norm": 1.247008204460144, "learning_rate": 2.371451851853749e-05, "loss": 0.46754302978515627, "step": 463010 }, { "epoch": 2.752287033899816, "grad_norm": 1.2602407932281494, "learning_rate": 2.3712748859318966e-05, "loss": 0.4668130397796631, "step": 463020 }, { "epoch": 2.7523464759764846, "grad_norm": 1.0512925386428833, "learning_rate": 2.3710979612870448e-05, "loss": 0.5008425235748291, "step": 463030 }, { "epoch": 2.752405918053153, "grad_norm": 1.1877495050430298, "learning_rate": 2.3709210779200395e-05, "loss": 0.49225521087646484, "step": 463040 }, { "epoch": 2.7524653601298215, "grad_norm": 1.9148691892623901, "learning_rate": 2.3707442358317272e-05, "loss": 0.432122802734375, "step": 463050 }, { "epoch": 2.75252480220649, "grad_norm": 1.3108484745025635, "learning_rate": 2.370567435022956e-05, "loss": 0.46596479415893555, "step": 463060 }, { "epoch": 2.7525842442831583, "grad_norm": 1.1754584312438965, "learning_rate": 2.3703906754945678e-05, "loss": 0.44677166938781737, "step": 463070 }, { "epoch": 2.7526436863598267, "grad_norm": 0.9976134300231934, "learning_rate": 2.370213957247414e-05, "loss": 0.40377082824707033, "step": 463080 }, { "epoch": 2.752703128436495, "grad_norm": 1.532257080078125, "learning_rate": 2.370037280282334e-05, "loss": 0.4640533924102783, "step": 463090 }, { "epoch": 2.7527625705131635, "grad_norm": 1.2643080949783325, "learning_rate": 2.3698606446001753e-05, "loss": 0.47057347297668456, "step": 463100 }, { "epoch": 2.752822012589832, "grad_norm": 1.2951117753982544, "learning_rate": 2.369684050201784e-05, "loss": 0.4628255367279053, "step": 463110 }, { "epoch": 2.7528814546665004, "grad_norm": 1.5029371976852417, "learning_rate": 2.369507497088003e-05, "loss": 0.4344027996063232, "step": 463120 }, { "epoch": 2.7529408967431688, "grad_norm": 1.36964750289917, "learning_rate": 2.3693309852596775e-05, "loss": 0.4416624069213867, "step": 463130 }, { "epoch": 2.753000338819837, "grad_norm": 1.7450402975082397, "learning_rate": 2.3691545147176533e-05, "loss": 0.4519349575042725, "step": 463140 }, { "epoch": 2.753059780896505, "grad_norm": 1.2563977241516113, "learning_rate": 2.3689780854627716e-05, "loss": 0.47742519378662107, "step": 463150 }, { "epoch": 2.753119222973174, "grad_norm": 1.537131667137146, "learning_rate": 2.368801697495879e-05, "loss": 0.47645864486694334, "step": 463160 }, { "epoch": 2.753178665049842, "grad_norm": 0.9825645685195923, "learning_rate": 2.368625350817818e-05, "loss": 0.48009319305419923, "step": 463170 }, { "epoch": 2.753238107126511, "grad_norm": 1.8135180473327637, "learning_rate": 2.3684490454294323e-05, "loss": 0.5314949512481689, "step": 463180 }, { "epoch": 2.753297549203179, "grad_norm": 1.2057839632034302, "learning_rate": 2.368272781331567e-05, "loss": 0.4781654357910156, "step": 463190 }, { "epoch": 2.7533569912798472, "grad_norm": 1.059458613395691, "learning_rate": 2.3680965585250625e-05, "loss": 0.4263925552368164, "step": 463200 }, { "epoch": 2.7534164333565156, "grad_norm": 1.3364521265029907, "learning_rate": 2.367920377010764e-05, "loss": 0.4346658229827881, "step": 463210 }, { "epoch": 2.753475875433184, "grad_norm": 1.228226900100708, "learning_rate": 2.3677442367895126e-05, "loss": 0.44523029327392577, "step": 463220 }, { "epoch": 2.7535353175098525, "grad_norm": 1.3644336462020874, "learning_rate": 2.367568137862151e-05, "loss": 0.45752506256103515, "step": 463230 }, { "epoch": 2.753594759586521, "grad_norm": 1.3683172464370728, "learning_rate": 2.3673920802295234e-05, "loss": 0.4700460433959961, "step": 463240 }, { "epoch": 2.7536542016631893, "grad_norm": 1.4031407833099365, "learning_rate": 2.3672160638924722e-05, "loss": 0.518522834777832, "step": 463250 }, { "epoch": 2.7537136437398577, "grad_norm": 1.45071280002594, "learning_rate": 2.3670400888518364e-05, "loss": 0.49912238121032715, "step": 463260 }, { "epoch": 2.753773085816526, "grad_norm": 1.2654074430465698, "learning_rate": 2.3668641551084597e-05, "loss": 0.4910739421844482, "step": 463270 }, { "epoch": 2.7538325278931945, "grad_norm": 1.3315811157226562, "learning_rate": 2.366688262663184e-05, "loss": 0.5254980087280273, "step": 463280 }, { "epoch": 2.753891969969863, "grad_norm": 1.3784269094467163, "learning_rate": 2.3665124115168505e-05, "loss": 0.48698816299438474, "step": 463290 }, { "epoch": 2.7539514120465314, "grad_norm": 1.3315706253051758, "learning_rate": 2.3663366016702983e-05, "loss": 0.4881416320800781, "step": 463300 }, { "epoch": 2.7540108541232, "grad_norm": 1.3739466667175293, "learning_rate": 2.3661608331243722e-05, "loss": 0.5358911514282226, "step": 463310 }, { "epoch": 2.7540702961998678, "grad_norm": 1.28866446018219, "learning_rate": 2.3659851058799106e-05, "loss": 0.46248464584350585, "step": 463320 }, { "epoch": 2.7541297382765366, "grad_norm": 1.6148535013198853, "learning_rate": 2.3658094199377546e-05, "loss": 0.4995163917541504, "step": 463330 }, { "epoch": 2.7541891803532046, "grad_norm": 1.2056167125701904, "learning_rate": 2.3656337752987452e-05, "loss": 0.4916676998138428, "step": 463340 }, { "epoch": 2.7542486224298734, "grad_norm": 0.9850741028785706, "learning_rate": 2.365458171963722e-05, "loss": 0.49016599655151366, "step": 463350 }, { "epoch": 2.7543080645065414, "grad_norm": 1.4666320085525513, "learning_rate": 2.3652826099335236e-05, "loss": 0.46294126510620115, "step": 463360 }, { "epoch": 2.75436750658321, "grad_norm": 1.4345332384109497, "learning_rate": 2.365107089208992e-05, "loss": 0.4606348991394043, "step": 463370 }, { "epoch": 2.7544269486598782, "grad_norm": 1.4238382577896118, "learning_rate": 2.3649316097909664e-05, "loss": 0.4331688404083252, "step": 463380 }, { "epoch": 2.7544863907365467, "grad_norm": 1.273260474205017, "learning_rate": 2.3647561716802865e-05, "loss": 0.5058576107025147, "step": 463390 }, { "epoch": 2.754545832813215, "grad_norm": 1.405410647392273, "learning_rate": 2.3645807748777914e-05, "loss": 0.4015493392944336, "step": 463400 }, { "epoch": 2.7546052748898835, "grad_norm": 1.4381496906280518, "learning_rate": 2.364405419384319e-05, "loss": 0.4820569038391113, "step": 463410 }, { "epoch": 2.754664716966552, "grad_norm": 1.4730924367904663, "learning_rate": 2.3642301052007093e-05, "loss": 0.45236892700195314, "step": 463420 }, { "epoch": 2.7547241590432203, "grad_norm": 1.7602275609970093, "learning_rate": 2.3640548323277988e-05, "loss": 0.4761622428894043, "step": 463430 }, { "epoch": 2.7547836011198887, "grad_norm": 1.278394103050232, "learning_rate": 2.36387960076643e-05, "loss": 0.46341733932495116, "step": 463440 }, { "epoch": 2.754843043196557, "grad_norm": 1.100198745727539, "learning_rate": 2.363704410517438e-05, "loss": 0.48710927963256834, "step": 463450 }, { "epoch": 2.7549024852732256, "grad_norm": 1.4325203895568848, "learning_rate": 2.3635292615816624e-05, "loss": 0.5377940654754638, "step": 463460 }, { "epoch": 2.754961927349894, "grad_norm": 1.6073030233383179, "learning_rate": 2.3633541539599397e-05, "loss": 0.49623122215271, "step": 463470 }, { "epoch": 2.7550213694265624, "grad_norm": 1.5981347560882568, "learning_rate": 2.3631790876531085e-05, "loss": 0.5233852386474609, "step": 463480 }, { "epoch": 2.755080811503231, "grad_norm": 1.3123672008514404, "learning_rate": 2.3630040626620058e-05, "loss": 0.4853996276855469, "step": 463490 }, { "epoch": 2.7551402535798992, "grad_norm": 1.223878026008606, "learning_rate": 2.362829078987468e-05, "loss": 0.483499813079834, "step": 463500 }, { "epoch": 2.755199695656567, "grad_norm": 1.226717472076416, "learning_rate": 2.3626541366303352e-05, "loss": 0.46741132736206054, "step": 463510 }, { "epoch": 2.755259137733236, "grad_norm": 1.255825161933899, "learning_rate": 2.3624792355914424e-05, "loss": 0.49785714149475097, "step": 463520 }, { "epoch": 2.755318579809904, "grad_norm": 1.4985421895980835, "learning_rate": 2.362304375871624e-05, "loss": 0.458116340637207, "step": 463530 }, { "epoch": 2.755378021886573, "grad_norm": 1.2599186897277832, "learning_rate": 2.3621295574717205e-05, "loss": 0.45473709106445315, "step": 463540 }, { "epoch": 2.755437463963241, "grad_norm": 1.4726074934005737, "learning_rate": 2.361954780392565e-05, "loss": 0.49300203323364256, "step": 463550 }, { "epoch": 2.7554969060399093, "grad_norm": 1.4503535032272339, "learning_rate": 2.361780044634995e-05, "loss": 0.5224484443664551, "step": 463560 }, { "epoch": 2.7555563481165777, "grad_norm": 1.6713858842849731, "learning_rate": 2.361605350199847e-05, "loss": 0.49228386878967284, "step": 463570 }, { "epoch": 2.755615790193246, "grad_norm": 1.1664434671401978, "learning_rate": 2.3614306970879574e-05, "loss": 0.4788514614105225, "step": 463580 }, { "epoch": 2.7556752322699145, "grad_norm": 1.2346749305725098, "learning_rate": 2.3612560853001574e-05, "loss": 0.46598072052001954, "step": 463590 }, { "epoch": 2.755734674346583, "grad_norm": 1.0798614025115967, "learning_rate": 2.3610815148372863e-05, "loss": 0.4310292720794678, "step": 463600 }, { "epoch": 2.7557941164232513, "grad_norm": 1.3874796628952026, "learning_rate": 2.360906985700178e-05, "loss": 0.46590709686279297, "step": 463610 }, { "epoch": 2.7558535584999198, "grad_norm": 1.5213501453399658, "learning_rate": 2.3607324978896674e-05, "loss": 0.46204161643981934, "step": 463620 }, { "epoch": 2.755913000576588, "grad_norm": 0.9528678059577942, "learning_rate": 2.3605580514065893e-05, "loss": 0.4287015438079834, "step": 463630 }, { "epoch": 2.7559724426532566, "grad_norm": 1.3603262901306152, "learning_rate": 2.3603836462517788e-05, "loss": 0.4622683525085449, "step": 463640 }, { "epoch": 2.756031884729925, "grad_norm": 1.6305001974105835, "learning_rate": 2.3602092824260687e-05, "loss": 0.4439499855041504, "step": 463650 }, { "epoch": 2.7560913268065934, "grad_norm": 0.9360575079917908, "learning_rate": 2.3600349599302924e-05, "loss": 0.4296267509460449, "step": 463660 }, { "epoch": 2.756150768883262, "grad_norm": 1.3117507696151733, "learning_rate": 2.3598606787652866e-05, "loss": 0.4901418209075928, "step": 463670 }, { "epoch": 2.7562102109599302, "grad_norm": 1.3918896913528442, "learning_rate": 2.359686438931884e-05, "loss": 0.44768171310424804, "step": 463680 }, { "epoch": 2.7562696530365987, "grad_norm": 1.289149284362793, "learning_rate": 2.3595122404309182e-05, "loss": 0.445966100692749, "step": 463690 }, { "epoch": 2.7563290951132666, "grad_norm": 1.2963478565216064, "learning_rate": 2.359338083263221e-05, "loss": 0.4987985134124756, "step": 463700 }, { "epoch": 2.7563885371899355, "grad_norm": 1.3939090967178345, "learning_rate": 2.3591639674296278e-05, "loss": 0.4204303741455078, "step": 463710 }, { "epoch": 2.7564479792666035, "grad_norm": 0.9999634027481079, "learning_rate": 2.3589898929309683e-05, "loss": 0.4321547508239746, "step": 463720 }, { "epoch": 2.7565074213432723, "grad_norm": 1.6887996196746826, "learning_rate": 2.3588158597680783e-05, "loss": 0.45578851699829104, "step": 463730 }, { "epoch": 2.7565668634199403, "grad_norm": 1.2585546970367432, "learning_rate": 2.3586418679417898e-05, "loss": 0.4651516914367676, "step": 463740 }, { "epoch": 2.7566263054966087, "grad_norm": 1.3554967641830444, "learning_rate": 2.3584679174529347e-05, "loss": 0.46494665145874026, "step": 463750 }, { "epoch": 2.756685747573277, "grad_norm": 1.430336594581604, "learning_rate": 2.3582940083023446e-05, "loss": 0.46583900451660154, "step": 463760 }, { "epoch": 2.7567451896499455, "grad_norm": 1.2807793617248535, "learning_rate": 2.358120140490852e-05, "loss": 0.46920342445373536, "step": 463770 }, { "epoch": 2.756804631726614, "grad_norm": 1.44918954372406, "learning_rate": 2.3579463140192883e-05, "loss": 0.45654025077819826, "step": 463780 }, { "epoch": 2.7568640738032824, "grad_norm": 1.2954281568527222, "learning_rate": 2.3577725288884843e-05, "loss": 0.450407600402832, "step": 463790 }, { "epoch": 2.7569235158799508, "grad_norm": 1.283278226852417, "learning_rate": 2.357598785099273e-05, "loss": 0.4812960147857666, "step": 463800 }, { "epoch": 2.756982957956619, "grad_norm": 1.6552705764770508, "learning_rate": 2.3574250826524845e-05, "loss": 0.4391517162322998, "step": 463810 }, { "epoch": 2.7570424000332876, "grad_norm": 1.3718680143356323, "learning_rate": 2.3572514215489512e-05, "loss": 0.486007022857666, "step": 463820 }, { "epoch": 2.757101842109956, "grad_norm": 1.4618767499923706, "learning_rate": 2.357077801789502e-05, "loss": 0.5154065132141114, "step": 463830 }, { "epoch": 2.7571612841866244, "grad_norm": 1.036865234375, "learning_rate": 2.3569042233749668e-05, "loss": 0.43406243324279786, "step": 463840 }, { "epoch": 2.757220726263293, "grad_norm": 1.5432971715927124, "learning_rate": 2.356730686306178e-05, "loss": 0.48798704147338867, "step": 463850 }, { "epoch": 2.7572801683399613, "grad_norm": 1.178782343864441, "learning_rate": 2.356557190583965e-05, "loss": 0.4223648548126221, "step": 463860 }, { "epoch": 2.7573396104166297, "grad_norm": 1.1509413719177246, "learning_rate": 2.356383736209158e-05, "loss": 0.44791698455810547, "step": 463870 }, { "epoch": 2.757399052493298, "grad_norm": 1.4633351564407349, "learning_rate": 2.3562103231825864e-05, "loss": 0.4924044609069824, "step": 463880 }, { "epoch": 2.757458494569966, "grad_norm": 0.9080279469490051, "learning_rate": 2.3560369515050802e-05, "loss": 0.4670600891113281, "step": 463890 }, { "epoch": 2.757517936646635, "grad_norm": 1.3307170867919922, "learning_rate": 2.3558636211774673e-05, "loss": 0.4927989959716797, "step": 463900 }, { "epoch": 2.757577378723303, "grad_norm": 1.2184767723083496, "learning_rate": 2.355690332200578e-05, "loss": 0.4533475399017334, "step": 463910 }, { "epoch": 2.7576368207999717, "grad_norm": 1.3003064393997192, "learning_rate": 2.3555170845752405e-05, "loss": 0.4352766990661621, "step": 463920 }, { "epoch": 2.7576962628766397, "grad_norm": 1.259673833847046, "learning_rate": 2.355343878302286e-05, "loss": 0.43889951705932617, "step": 463930 }, { "epoch": 2.757755704953308, "grad_norm": 1.1855708360671997, "learning_rate": 2.355170713382541e-05, "loss": 0.413370418548584, "step": 463940 }, { "epoch": 2.7578151470299765, "grad_norm": 1.2942407131195068, "learning_rate": 2.3549975898168335e-05, "loss": 0.53494873046875, "step": 463950 }, { "epoch": 2.757874589106645, "grad_norm": 1.3445689678192139, "learning_rate": 2.3548245076059922e-05, "loss": 0.4535226821899414, "step": 463960 }, { "epoch": 2.7579340311833134, "grad_norm": 1.2495160102844238, "learning_rate": 2.3546514667508462e-05, "loss": 0.512018871307373, "step": 463970 }, { "epoch": 2.757993473259982, "grad_norm": 1.4805951118469238, "learning_rate": 2.3544784672522217e-05, "loss": 0.46913371086120603, "step": 463980 }, { "epoch": 2.75805291533665, "grad_norm": 1.283532977104187, "learning_rate": 2.3543055091109458e-05, "loss": 0.47712268829345705, "step": 463990 }, { "epoch": 2.7581123574133186, "grad_norm": 0.9284404516220093, "learning_rate": 2.3541325923278472e-05, "loss": 0.42796735763549804, "step": 464000 }, { "epoch": 2.758171799489987, "grad_norm": 1.281217336654663, "learning_rate": 2.3539597169037543e-05, "loss": 0.429230785369873, "step": 464010 }, { "epoch": 2.7582312415666554, "grad_norm": 1.3511850833892822, "learning_rate": 2.353786882839491e-05, "loss": 0.5011840343475342, "step": 464020 }, { "epoch": 2.758290683643324, "grad_norm": 1.1496332883834839, "learning_rate": 2.3536140901358865e-05, "loss": 0.4786224365234375, "step": 464030 }, { "epoch": 2.7583501257199923, "grad_norm": 1.3395644426345825, "learning_rate": 2.3534413387937666e-05, "loss": 0.46587247848510743, "step": 464040 }, { "epoch": 2.7584095677966607, "grad_norm": 1.7097465991973877, "learning_rate": 2.353268628813956e-05, "loss": 0.47144031524658203, "step": 464050 }, { "epoch": 2.7584690098733287, "grad_norm": 1.449317455291748, "learning_rate": 2.353095960197284e-05, "loss": 0.485736083984375, "step": 464060 }, { "epoch": 2.7585284519499975, "grad_norm": 1.2791863679885864, "learning_rate": 2.3529233329445755e-05, "loss": 0.44753503799438477, "step": 464070 }, { "epoch": 2.7585878940266655, "grad_norm": 1.351093053817749, "learning_rate": 2.3527507470566545e-05, "loss": 0.4834277629852295, "step": 464080 }, { "epoch": 2.7586473361033343, "grad_norm": 1.3734596967697144, "learning_rate": 2.3525782025343485e-05, "loss": 0.481122350692749, "step": 464090 }, { "epoch": 2.7587067781800023, "grad_norm": 1.3109444379806519, "learning_rate": 2.3524056993784828e-05, "loss": 0.46665706634521487, "step": 464100 }, { "epoch": 2.7587662202566707, "grad_norm": 1.156463384628296, "learning_rate": 2.3522332375898827e-05, "loss": 0.5019762992858887, "step": 464110 }, { "epoch": 2.758825662333339, "grad_norm": 1.0561960935592651, "learning_rate": 2.3520608171693705e-05, "loss": 0.45497732162475585, "step": 464120 }, { "epoch": 2.7588851044100076, "grad_norm": 1.1152825355529785, "learning_rate": 2.3518884381177758e-05, "loss": 0.43529052734375, "step": 464130 }, { "epoch": 2.758944546486676, "grad_norm": 1.174700379371643, "learning_rate": 2.3517161004359197e-05, "loss": 0.4641884326934814, "step": 464140 }, { "epoch": 2.7590039885633444, "grad_norm": 1.733622670173645, "learning_rate": 2.3515438041246262e-05, "loss": 0.47124643325805665, "step": 464150 }, { "epoch": 2.759063430640013, "grad_norm": 1.3049280643463135, "learning_rate": 2.3513715491847217e-05, "loss": 0.5223731994628906, "step": 464160 }, { "epoch": 2.759122872716681, "grad_norm": 1.160548448562622, "learning_rate": 2.3511993356170292e-05, "loss": 0.48144078254699707, "step": 464170 }, { "epoch": 2.7591823147933496, "grad_norm": 1.2490754127502441, "learning_rate": 2.3510271634223717e-05, "loss": 0.5081986427307129, "step": 464180 }, { "epoch": 2.759241756870018, "grad_norm": 1.498178243637085, "learning_rate": 2.3508550326015762e-05, "loss": 0.4555517196655273, "step": 464190 }, { "epoch": 2.7593011989466865, "grad_norm": 1.4247454404830933, "learning_rate": 2.350682943155463e-05, "loss": 0.4745491981506348, "step": 464200 }, { "epoch": 2.759360641023355, "grad_norm": 1.0489487648010254, "learning_rate": 2.3505108950848536e-05, "loss": 0.4694718360900879, "step": 464210 }, { "epoch": 2.7594200831000233, "grad_norm": 1.587598204612732, "learning_rate": 2.3503388883905748e-05, "loss": 0.4760545253753662, "step": 464220 }, { "epoch": 2.7594795251766917, "grad_norm": 1.0461915731430054, "learning_rate": 2.3501669230734486e-05, "loss": 0.43930416107177733, "step": 464230 }, { "epoch": 2.75953896725336, "grad_norm": 1.3513461351394653, "learning_rate": 2.3499949991342966e-05, "loss": 0.4880661964416504, "step": 464240 }, { "epoch": 2.759598409330028, "grad_norm": 1.2587889432907104, "learning_rate": 2.3498231165739417e-05, "loss": 0.46077470779418944, "step": 464250 }, { "epoch": 2.759657851406697, "grad_norm": 1.5864464044570923, "learning_rate": 2.3496512753932067e-05, "loss": 0.4784384727478027, "step": 464260 }, { "epoch": 2.759717293483365, "grad_norm": 1.2804620265960693, "learning_rate": 2.3494794755929127e-05, "loss": 0.44979195594787597, "step": 464270 }, { "epoch": 2.759776735560034, "grad_norm": 1.3557387590408325, "learning_rate": 2.3493077171738804e-05, "loss": 0.4391439437866211, "step": 464280 }, { "epoch": 2.7598361776367017, "grad_norm": 1.7839189767837524, "learning_rate": 2.3491360001369345e-05, "loss": 0.5286679267883301, "step": 464290 }, { "epoch": 2.75989561971337, "grad_norm": 1.4582446813583374, "learning_rate": 2.3489643244828948e-05, "loss": 0.4467642307281494, "step": 464300 }, { "epoch": 2.7599550617900386, "grad_norm": 1.3863551616668701, "learning_rate": 2.3487926902125817e-05, "loss": 0.4614140033721924, "step": 464310 }, { "epoch": 2.760014503866707, "grad_norm": 1.5109962224960327, "learning_rate": 2.348621097326818e-05, "loss": 0.4796009063720703, "step": 464320 }, { "epoch": 2.7600739459433754, "grad_norm": 1.082795262336731, "learning_rate": 2.348449545826424e-05, "loss": 0.4593782901763916, "step": 464330 }, { "epoch": 2.760133388020044, "grad_norm": 1.0080840587615967, "learning_rate": 2.3482780357122193e-05, "loss": 0.45833873748779297, "step": 464340 }, { "epoch": 2.7601928300967122, "grad_norm": 1.298530101776123, "learning_rate": 2.3481065669850245e-05, "loss": 0.462342643737793, "step": 464350 }, { "epoch": 2.7602522721733806, "grad_norm": 1.1850231885910034, "learning_rate": 2.3479351396456607e-05, "loss": 0.48978257179260254, "step": 464360 }, { "epoch": 2.760311714250049, "grad_norm": 1.4196370840072632, "learning_rate": 2.347763753694948e-05, "loss": 0.5042170524597168, "step": 464370 }, { "epoch": 2.7603711563267175, "grad_norm": 1.0779168605804443, "learning_rate": 2.3475924091337056e-05, "loss": 0.4445620059967041, "step": 464380 }, { "epoch": 2.760430598403386, "grad_norm": 1.2130670547485352, "learning_rate": 2.3474211059627545e-05, "loss": 0.38723602294921877, "step": 464390 }, { "epoch": 2.7604900404800543, "grad_norm": 1.5405380725860596, "learning_rate": 2.3472498441829127e-05, "loss": 0.4537988185882568, "step": 464400 }, { "epoch": 2.7605494825567227, "grad_norm": 1.6323187351226807, "learning_rate": 2.3470786237949987e-05, "loss": 0.45699033737182615, "step": 464410 }, { "epoch": 2.760608924633391, "grad_norm": 1.4828883409500122, "learning_rate": 2.3469074447998332e-05, "loss": 0.5005959033966064, "step": 464420 }, { "epoch": 2.7606683667100596, "grad_norm": 1.4588617086410522, "learning_rate": 2.346736307198235e-05, "loss": 0.4743319511413574, "step": 464430 }, { "epoch": 2.7607278087867275, "grad_norm": 0.9253790378570557, "learning_rate": 2.346565210991023e-05, "loss": 0.4755224704742432, "step": 464440 }, { "epoch": 2.7607872508633964, "grad_norm": 1.554324984550476, "learning_rate": 2.3463941561790153e-05, "loss": 0.41755075454711915, "step": 464450 }, { "epoch": 2.7608466929400644, "grad_norm": 1.4304925203323364, "learning_rate": 2.346223142763029e-05, "loss": 0.4709151744842529, "step": 464460 }, { "epoch": 2.760906135016733, "grad_norm": 1.1886975765228271, "learning_rate": 2.346052170743884e-05, "loss": 0.43479409217834475, "step": 464470 }, { "epoch": 2.760965577093401, "grad_norm": 1.4887025356292725, "learning_rate": 2.3458812401223948e-05, "loss": 0.506546926498413, "step": 464480 }, { "epoch": 2.7610250191700696, "grad_norm": 1.261594533920288, "learning_rate": 2.3457103508993832e-05, "loss": 0.44721331596374514, "step": 464490 }, { "epoch": 2.761084461246738, "grad_norm": 1.1506640911102295, "learning_rate": 2.3455395030756673e-05, "loss": 0.45790853500366213, "step": 464500 }, { "epoch": 2.7611439033234064, "grad_norm": 1.2893568277359009, "learning_rate": 2.345368696652058e-05, "loss": 0.4597298622131348, "step": 464510 }, { "epoch": 2.761203345400075, "grad_norm": 1.429642915725708, "learning_rate": 2.3451979316293786e-05, "loss": 0.47633700370788573, "step": 464520 }, { "epoch": 2.7612627874767433, "grad_norm": 1.1362863779067993, "learning_rate": 2.3450272080084446e-05, "loss": 0.41258935928344725, "step": 464530 }, { "epoch": 2.7613222295534117, "grad_norm": 1.2079819440841675, "learning_rate": 2.3448565257900694e-05, "loss": 0.5073113918304444, "step": 464540 }, { "epoch": 2.76138167163008, "grad_norm": 1.2729071378707886, "learning_rate": 2.3446858849750743e-05, "loss": 0.4701117515563965, "step": 464550 }, { "epoch": 2.7614411137067485, "grad_norm": 1.3426014184951782, "learning_rate": 2.3445152855642745e-05, "loss": 0.4954536437988281, "step": 464560 }, { "epoch": 2.761500555783417, "grad_norm": 1.3693772554397583, "learning_rate": 2.3443447275584814e-05, "loss": 0.4542084693908691, "step": 464570 }, { "epoch": 2.7615599978600853, "grad_norm": 1.3909075260162354, "learning_rate": 2.3441742109585166e-05, "loss": 0.4329995155334473, "step": 464580 }, { "epoch": 2.7616194399367537, "grad_norm": 1.6328153610229492, "learning_rate": 2.344003735765194e-05, "loss": 0.5118276596069335, "step": 464590 }, { "epoch": 2.761678882013422, "grad_norm": 1.3653353452682495, "learning_rate": 2.3438333019793275e-05, "loss": 0.5074105262756348, "step": 464600 }, { "epoch": 2.7617383240900906, "grad_norm": 1.0243737697601318, "learning_rate": 2.343662909601733e-05, "loss": 0.47758140563964846, "step": 464610 }, { "epoch": 2.761797766166759, "grad_norm": 1.136755347251892, "learning_rate": 2.3434925586332286e-05, "loss": 0.45097923278808594, "step": 464620 }, { "epoch": 2.761857208243427, "grad_norm": 1.0388641357421875, "learning_rate": 2.3433222490746256e-05, "loss": 0.43408689498901365, "step": 464630 }, { "epoch": 2.761916650320096, "grad_norm": 1.4633126258850098, "learning_rate": 2.343151980926739e-05, "loss": 0.4422738552093506, "step": 464640 }, { "epoch": 2.761976092396764, "grad_norm": 1.079163670539856, "learning_rate": 2.3429817541903847e-05, "loss": 0.4597633361816406, "step": 464650 }, { "epoch": 2.7620355344734326, "grad_norm": 1.2017439603805542, "learning_rate": 2.3428115688663778e-05, "loss": 0.41308002471923827, "step": 464660 }, { "epoch": 2.7620949765501006, "grad_norm": 1.3748936653137207, "learning_rate": 2.342641424955529e-05, "loss": 0.4319146156311035, "step": 464670 }, { "epoch": 2.762154418626769, "grad_norm": 1.4255037307739258, "learning_rate": 2.3424713224586573e-05, "loss": 0.4321286678314209, "step": 464680 }, { "epoch": 2.7622138607034374, "grad_norm": 1.3831080198287964, "learning_rate": 2.3423012613765717e-05, "loss": 0.4318809509277344, "step": 464690 }, { "epoch": 2.762273302780106, "grad_norm": 1.3470438718795776, "learning_rate": 2.342131241710086e-05, "loss": 0.44034633636474607, "step": 464700 }, { "epoch": 2.7623327448567743, "grad_norm": 1.5581672191619873, "learning_rate": 2.341961263460017e-05, "loss": 0.4599305152893066, "step": 464710 }, { "epoch": 2.7623921869334427, "grad_norm": 1.380133867263794, "learning_rate": 2.3417913266271753e-05, "loss": 0.520303201675415, "step": 464720 }, { "epoch": 2.762451629010111, "grad_norm": 1.2982498407363892, "learning_rate": 2.3416214312123746e-05, "loss": 0.49595069885253906, "step": 464730 }, { "epoch": 2.7625110710867795, "grad_norm": 1.721308708190918, "learning_rate": 2.3414515772164276e-05, "loss": 0.47112550735473635, "step": 464740 }, { "epoch": 2.762570513163448, "grad_norm": 1.4223272800445557, "learning_rate": 2.3412817646401468e-05, "loss": 0.5155326843261718, "step": 464750 }, { "epoch": 2.7626299552401163, "grad_norm": 1.5294816493988037, "learning_rate": 2.3411119934843442e-05, "loss": 0.4647963047027588, "step": 464760 }, { "epoch": 2.7626893973167848, "grad_norm": 1.5276362895965576, "learning_rate": 2.34094226374983e-05, "loss": 0.46957149505615237, "step": 464770 }, { "epoch": 2.762748839393453, "grad_norm": 1.7825725078582764, "learning_rate": 2.340772575437421e-05, "loss": 0.4796872138977051, "step": 464780 }, { "epoch": 2.7628082814701216, "grad_norm": 1.4895193576812744, "learning_rate": 2.3406029285479243e-05, "loss": 0.446000862121582, "step": 464790 }, { "epoch": 2.7628677235467896, "grad_norm": 1.1181763410568237, "learning_rate": 2.3404333230821546e-05, "loss": 0.4670561790466309, "step": 464800 }, { "epoch": 2.7629271656234584, "grad_norm": 1.3045024871826172, "learning_rate": 2.3402637590409215e-05, "loss": 0.47371225357055663, "step": 464810 }, { "epoch": 2.7629866077001264, "grad_norm": 1.7603487968444824, "learning_rate": 2.3400942364250367e-05, "loss": 0.475861930847168, "step": 464820 }, { "epoch": 2.7630460497767952, "grad_norm": 1.246812343597412, "learning_rate": 2.3399247552353105e-05, "loss": 0.4671477317810059, "step": 464830 }, { "epoch": 2.763105491853463, "grad_norm": 1.9986567497253418, "learning_rate": 2.339755315472553e-05, "loss": 0.44013776779174807, "step": 464840 }, { "epoch": 2.7631649339301316, "grad_norm": 1.3510992527008057, "learning_rate": 2.3395859171375774e-05, "loss": 0.4052595138549805, "step": 464850 }, { "epoch": 2.7632243760068, "grad_norm": 1.393653392791748, "learning_rate": 2.339416560231193e-05, "loss": 0.44904441833496095, "step": 464860 }, { "epoch": 2.7632838180834685, "grad_norm": 1.4134377241134644, "learning_rate": 2.339247244754208e-05, "loss": 0.48314752578735354, "step": 464870 }, { "epoch": 2.763343260160137, "grad_norm": 1.333483338356018, "learning_rate": 2.3390779707074355e-05, "loss": 0.44170303344726564, "step": 464880 }, { "epoch": 2.7634027022368053, "grad_norm": 1.4084950685501099, "learning_rate": 2.3389087380916826e-05, "loss": 0.42447381019592284, "step": 464890 }, { "epoch": 2.7634621443134737, "grad_norm": 0.9941654205322266, "learning_rate": 2.3387395469077582e-05, "loss": 0.4605693817138672, "step": 464900 }, { "epoch": 2.763521586390142, "grad_norm": 1.5631128549575806, "learning_rate": 2.3385703971564758e-05, "loss": 0.44378113746643066, "step": 464910 }, { "epoch": 2.7635810284668105, "grad_norm": 1.1718803644180298, "learning_rate": 2.3384012888386408e-05, "loss": 0.4736766815185547, "step": 464920 }, { "epoch": 2.763640470543479, "grad_norm": 0.9702281951904297, "learning_rate": 2.3382322219550637e-05, "loss": 0.4182835578918457, "step": 464930 }, { "epoch": 2.7636999126201474, "grad_norm": 1.4379762411117554, "learning_rate": 2.338063196506553e-05, "loss": 0.45827341079711914, "step": 464940 }, { "epoch": 2.7637593546968158, "grad_norm": 1.2617735862731934, "learning_rate": 2.3378942124939175e-05, "loss": 0.4672743797302246, "step": 464950 }, { "epoch": 2.763818796773484, "grad_norm": 1.3395439386367798, "learning_rate": 2.3377252699179656e-05, "loss": 0.43528523445129397, "step": 464960 }, { "epoch": 2.7638782388501526, "grad_norm": 1.5078818798065186, "learning_rate": 2.337556368779503e-05, "loss": 0.44956164360046386, "step": 464970 }, { "epoch": 2.763937680926821, "grad_norm": 1.2305161952972412, "learning_rate": 2.3373875090793416e-05, "loss": 0.44497504234313967, "step": 464980 }, { "epoch": 2.763997123003489, "grad_norm": 1.5954514741897583, "learning_rate": 2.337218690818288e-05, "loss": 0.43068809509277345, "step": 464990 }, { "epoch": 2.764056565080158, "grad_norm": 1.660739541053772, "learning_rate": 2.3370499139971483e-05, "loss": 0.5296920776367188, "step": 465000 }, { "epoch": 2.764116007156826, "grad_norm": 1.5302282571792603, "learning_rate": 2.3368811786167303e-05, "loss": 0.46910924911499025, "step": 465010 }, { "epoch": 2.7641754492334947, "grad_norm": 1.085437536239624, "learning_rate": 2.3367124846778425e-05, "loss": 0.4965775966644287, "step": 465020 }, { "epoch": 2.7642348913101626, "grad_norm": 1.124779462814331, "learning_rate": 2.336543832181289e-05, "loss": 0.4877882957458496, "step": 465030 }, { "epoch": 2.764294333386831, "grad_norm": 1.1482354402542114, "learning_rate": 2.3363752211278806e-05, "loss": 0.43253097534179685, "step": 465040 }, { "epoch": 2.7643537754634995, "grad_norm": 1.0445048809051514, "learning_rate": 2.3362066515184224e-05, "loss": 0.42759151458740235, "step": 465050 }, { "epoch": 2.764413217540168, "grad_norm": 1.1203370094299316, "learning_rate": 2.336038123353718e-05, "loss": 0.4839171409606934, "step": 465060 }, { "epoch": 2.7644726596168363, "grad_norm": 1.5340476036071777, "learning_rate": 2.3358696366345774e-05, "loss": 0.4573190689086914, "step": 465070 }, { "epoch": 2.7645321016935047, "grad_norm": 1.6041756868362427, "learning_rate": 2.3357011913618045e-05, "loss": 0.4518528938293457, "step": 465080 }, { "epoch": 2.764591543770173, "grad_norm": 1.5433783531188965, "learning_rate": 2.335532787536206e-05, "loss": 0.4619175910949707, "step": 465090 }, { "epoch": 2.7646509858468415, "grad_norm": 0.8347463011741638, "learning_rate": 2.3353644251585855e-05, "loss": 0.4376032829284668, "step": 465100 }, { "epoch": 2.76471042792351, "grad_norm": 1.3589297533035278, "learning_rate": 2.3351961042297528e-05, "loss": 0.46556987762451174, "step": 465110 }, { "epoch": 2.7647698700001784, "grad_norm": 1.2961968183517456, "learning_rate": 2.3350278247505083e-05, "loss": 0.47956123352050783, "step": 465120 }, { "epoch": 2.764829312076847, "grad_norm": 1.1435028314590454, "learning_rate": 2.3348595867216582e-05, "loss": 0.4620955467224121, "step": 465130 }, { "epoch": 2.764888754153515, "grad_norm": 1.469230055809021, "learning_rate": 2.3346913901440083e-05, "loss": 0.45409793853759767, "step": 465140 }, { "epoch": 2.7649481962301836, "grad_norm": 1.4432942867279053, "learning_rate": 2.3345232350183646e-05, "loss": 0.43389291763305665, "step": 465150 }, { "epoch": 2.765007638306852, "grad_norm": 1.4076231718063354, "learning_rate": 2.334355121345528e-05, "loss": 0.5008442878723145, "step": 465160 }, { "epoch": 2.7650670803835204, "grad_norm": 1.4458084106445312, "learning_rate": 2.334187049126306e-05, "loss": 0.49354047775268556, "step": 465170 }, { "epoch": 2.7651265224601884, "grad_norm": 1.371233344078064, "learning_rate": 2.3340190183615008e-05, "loss": 0.45645790100097655, "step": 465180 }, { "epoch": 2.7651859645368573, "grad_norm": 1.5334160327911377, "learning_rate": 2.333851029051916e-05, "loss": 0.49111413955688477, "step": 465190 }, { "epoch": 2.7652454066135252, "grad_norm": 1.3155564069747925, "learning_rate": 2.3336830811983553e-05, "loss": 0.43526997566223147, "step": 465200 }, { "epoch": 2.765304848690194, "grad_norm": 1.2984638214111328, "learning_rate": 2.333515174801624e-05, "loss": 0.46504764556884765, "step": 465210 }, { "epoch": 2.765364290766862, "grad_norm": 1.335939645767212, "learning_rate": 2.333347309862523e-05, "loss": 0.47709269523620607, "step": 465220 }, { "epoch": 2.7654237328435305, "grad_norm": 1.3232589960098267, "learning_rate": 2.3331794863818568e-05, "loss": 0.45725092887878416, "step": 465230 }, { "epoch": 2.765483174920199, "grad_norm": 1.3682554960250854, "learning_rate": 2.3330117043604276e-05, "loss": 0.46982564926147463, "step": 465240 }, { "epoch": 2.7655426169968673, "grad_norm": 1.3457671403884888, "learning_rate": 2.3328439637990374e-05, "loss": 0.4796492099761963, "step": 465250 }, { "epoch": 2.7656020590735357, "grad_norm": 1.294580340385437, "learning_rate": 2.3326762646984884e-05, "loss": 0.46930737495422364, "step": 465260 }, { "epoch": 2.765661501150204, "grad_norm": 1.1366117000579834, "learning_rate": 2.3325086070595842e-05, "loss": 0.4695998191833496, "step": 465270 }, { "epoch": 2.7657209432268726, "grad_norm": 0.9202807545661926, "learning_rate": 2.3323409908831267e-05, "loss": 0.47246241569519043, "step": 465280 }, { "epoch": 2.765780385303541, "grad_norm": 0.9840338230133057, "learning_rate": 2.332173416169918e-05, "loss": 0.4470663070678711, "step": 465290 }, { "epoch": 2.7658398273802094, "grad_norm": 1.5516060590744019, "learning_rate": 2.3320058829207585e-05, "loss": 0.4237785816192627, "step": 465300 }, { "epoch": 2.765899269456878, "grad_norm": 1.1162062883377075, "learning_rate": 2.3318383911364494e-05, "loss": 0.4651606559753418, "step": 465310 }, { "epoch": 2.765958711533546, "grad_norm": 1.30562162399292, "learning_rate": 2.3316709408177935e-05, "loss": 0.46961822509765627, "step": 465320 }, { "epoch": 2.7660181536102146, "grad_norm": 1.6438606977462769, "learning_rate": 2.3315035319655898e-05, "loss": 0.4523585319519043, "step": 465330 }, { "epoch": 2.766077595686883, "grad_norm": 0.9343354105949402, "learning_rate": 2.3313361645806413e-05, "loss": 0.4563289642333984, "step": 465340 }, { "epoch": 2.7661370377635515, "grad_norm": 1.0442087650299072, "learning_rate": 2.3311688386637472e-05, "loss": 0.45247325897216795, "step": 465350 }, { "epoch": 2.76619647984022, "grad_norm": 1.7014096975326538, "learning_rate": 2.3310015542157085e-05, "loss": 0.4798921585083008, "step": 465360 }, { "epoch": 2.766255921916888, "grad_norm": 1.3225266933441162, "learning_rate": 2.3308343112373265e-05, "loss": 0.4931172847747803, "step": 465370 }, { "epoch": 2.7663153639935567, "grad_norm": 1.383589267730713, "learning_rate": 2.3306671097293984e-05, "loss": 0.4757756233215332, "step": 465380 }, { "epoch": 2.7663748060702247, "grad_norm": 1.290177822113037, "learning_rate": 2.3304999496927256e-05, "loss": 0.4700343132019043, "step": 465390 }, { "epoch": 2.766434248146893, "grad_norm": 1.2231563329696655, "learning_rate": 2.3303328311281082e-05, "loss": 0.451994800567627, "step": 465400 }, { "epoch": 2.7664936902235615, "grad_norm": 1.1143451929092407, "learning_rate": 2.3301657540363462e-05, "loss": 0.49245753288269045, "step": 465410 }, { "epoch": 2.76655313230023, "grad_norm": 1.01459538936615, "learning_rate": 2.329998718418237e-05, "loss": 0.43433361053466796, "step": 465420 }, { "epoch": 2.7666125743768983, "grad_norm": 1.377512812614441, "learning_rate": 2.329831724274581e-05, "loss": 0.46561341285705565, "step": 465430 }, { "epoch": 2.7666720164535668, "grad_norm": 1.3477442264556885, "learning_rate": 2.3296647716061767e-05, "loss": 0.4486638069152832, "step": 465440 }, { "epoch": 2.766731458530235, "grad_norm": 1.2034040689468384, "learning_rate": 2.3294978604138223e-05, "loss": 0.4425335884094238, "step": 465450 }, { "epoch": 2.7667909006069036, "grad_norm": 1.689879059791565, "learning_rate": 2.3293309906983148e-05, "loss": 0.45681037902832033, "step": 465460 }, { "epoch": 2.766850342683572, "grad_norm": 0.9245290756225586, "learning_rate": 2.3291641624604566e-05, "loss": 0.44846010208129883, "step": 465470 }, { "epoch": 2.7669097847602404, "grad_norm": 1.3294305801391602, "learning_rate": 2.328997375701043e-05, "loss": 0.5233974933624268, "step": 465480 }, { "epoch": 2.766969226836909, "grad_norm": 1.3196157217025757, "learning_rate": 2.3288306304208717e-05, "loss": 0.45829038619995116, "step": 465490 }, { "epoch": 2.7670286689135772, "grad_norm": 1.1810507774353027, "learning_rate": 2.3286639266207417e-05, "loss": 0.45968198776245117, "step": 465500 }, { "epoch": 2.7670881109902457, "grad_norm": 1.3250062465667725, "learning_rate": 2.3284972643014493e-05, "loss": 0.5222455024719238, "step": 465510 }, { "epoch": 2.767147553066914, "grad_norm": 1.1833711862564087, "learning_rate": 2.3283306434637912e-05, "loss": 0.5157053947448731, "step": 465520 }, { "epoch": 2.7672069951435825, "grad_norm": 1.021078109741211, "learning_rate": 2.3281640641085665e-05, "loss": 0.4884010314941406, "step": 465530 }, { "epoch": 2.7672664372202505, "grad_norm": 1.2755120992660522, "learning_rate": 2.3279975262365707e-05, "loss": 0.48147430419921877, "step": 465540 }, { "epoch": 2.7673258792969193, "grad_norm": 1.019587516784668, "learning_rate": 2.3278310298486e-05, "loss": 0.4515716552734375, "step": 465550 }, { "epoch": 2.7673853213735873, "grad_norm": 1.7445005178451538, "learning_rate": 2.3276645749454528e-05, "loss": 0.49515647888183595, "step": 465560 }, { "epoch": 2.767444763450256, "grad_norm": 1.1163544654846191, "learning_rate": 2.327498161527923e-05, "loss": 0.46178641319274905, "step": 465570 }, { "epoch": 2.767504205526924, "grad_norm": 1.1341593265533447, "learning_rate": 2.327331789596809e-05, "loss": 0.4394798755645752, "step": 465580 }, { "epoch": 2.7675636476035925, "grad_norm": 1.121942162513733, "learning_rate": 2.327165459152903e-05, "loss": 0.42426042556762694, "step": 465590 }, { "epoch": 2.767623089680261, "grad_norm": 1.15802800655365, "learning_rate": 2.326999170197006e-05, "loss": 0.48749370574951173, "step": 465600 }, { "epoch": 2.7676825317569294, "grad_norm": 1.2756249904632568, "learning_rate": 2.32683292272991e-05, "loss": 0.42211389541625977, "step": 465610 }, { "epoch": 2.7677419738335978, "grad_norm": 1.5395174026489258, "learning_rate": 2.326666716752409e-05, "loss": 0.4881711006164551, "step": 465620 }, { "epoch": 2.767801415910266, "grad_norm": 1.3899149894714355, "learning_rate": 2.3265005522653012e-05, "loss": 0.47038707733154295, "step": 465630 }, { "epoch": 2.7678608579869346, "grad_norm": 1.308658242225647, "learning_rate": 2.3263344292693812e-05, "loss": 0.48202691078186033, "step": 465640 }, { "epoch": 2.767920300063603, "grad_norm": 1.1057090759277344, "learning_rate": 2.3261683477654406e-05, "loss": 0.4421882629394531, "step": 465650 }, { "epoch": 2.7679797421402714, "grad_norm": 1.2609087228775024, "learning_rate": 2.3260023077542784e-05, "loss": 0.43672494888305663, "step": 465660 }, { "epoch": 2.76803918421694, "grad_norm": 1.275708556175232, "learning_rate": 2.3258363092366855e-05, "loss": 0.4345996856689453, "step": 465670 }, { "epoch": 2.7680986262936083, "grad_norm": 1.229034662246704, "learning_rate": 2.3256703522134567e-05, "loss": 0.41060194969177244, "step": 465680 }, { "epoch": 2.7681580683702767, "grad_norm": 1.4928747415542603, "learning_rate": 2.3255044366853853e-05, "loss": 0.44423618316650393, "step": 465690 }, { "epoch": 2.768217510446945, "grad_norm": 1.3140919208526611, "learning_rate": 2.325338562653267e-05, "loss": 0.4528437614440918, "step": 465700 }, { "epoch": 2.7682769525236135, "grad_norm": 1.0508182048797607, "learning_rate": 2.325172730117893e-05, "loss": 0.4584920883178711, "step": 465710 }, { "epoch": 2.768336394600282, "grad_norm": 1.1555445194244385, "learning_rate": 2.3250069390800586e-05, "loss": 0.4276263236999512, "step": 465720 }, { "epoch": 2.76839583667695, "grad_norm": 1.5823392868041992, "learning_rate": 2.324841189540556e-05, "loss": 0.4887550354003906, "step": 465730 }, { "epoch": 2.7684552787536187, "grad_norm": 0.9938728213310242, "learning_rate": 2.3246754815001786e-05, "loss": 0.4336079597473145, "step": 465740 }, { "epoch": 2.7685147208302867, "grad_norm": 1.4106411933898926, "learning_rate": 2.3245098149597165e-05, "loss": 0.4898396015167236, "step": 465750 }, { "epoch": 2.7685741629069556, "grad_norm": 1.2612258195877075, "learning_rate": 2.3243441899199657e-05, "loss": 0.4761049747467041, "step": 465760 }, { "epoch": 2.7686336049836235, "grad_norm": 1.8288668394088745, "learning_rate": 2.324178606381717e-05, "loss": 0.4799952507019043, "step": 465770 }, { "epoch": 2.768693047060292, "grad_norm": 1.4175490140914917, "learning_rate": 2.3240130643457628e-05, "loss": 0.47524094581604004, "step": 465780 }, { "epoch": 2.7687524891369604, "grad_norm": 1.2377703189849854, "learning_rate": 2.3238475638128947e-05, "loss": 0.47289628982543946, "step": 465790 }, { "epoch": 2.768811931213629, "grad_norm": 1.1043789386749268, "learning_rate": 2.3236821047839047e-05, "loss": 0.46262412071228026, "step": 465800 }, { "epoch": 2.768871373290297, "grad_norm": 1.3597158193588257, "learning_rate": 2.3235166872595833e-05, "loss": 0.457393741607666, "step": 465810 }, { "epoch": 2.7689308153669656, "grad_norm": 1.8622068166732788, "learning_rate": 2.3233513112407224e-05, "loss": 0.5506515502929688, "step": 465820 }, { "epoch": 2.768990257443634, "grad_norm": 1.3266559839248657, "learning_rate": 2.3231859767281138e-05, "loss": 0.5003067016601562, "step": 465830 }, { "epoch": 2.7690496995203024, "grad_norm": 1.2680277824401855, "learning_rate": 2.3230206837225478e-05, "loss": 0.46598014831542967, "step": 465840 }, { "epoch": 2.769109141596971, "grad_norm": 1.2414857149124146, "learning_rate": 2.322855432224815e-05, "loss": 0.4227334499359131, "step": 465850 }, { "epoch": 2.7691685836736393, "grad_norm": 1.1831517219543457, "learning_rate": 2.3226902222357067e-05, "loss": 0.4643595218658447, "step": 465860 }, { "epoch": 2.7692280257503077, "grad_norm": 1.3452565670013428, "learning_rate": 2.3225250537560125e-05, "loss": 0.4866787433624268, "step": 465870 }, { "epoch": 2.769287467826976, "grad_norm": 1.1396554708480835, "learning_rate": 2.3223599267865214e-05, "loss": 0.4527390956878662, "step": 465880 }, { "epoch": 2.7693469099036445, "grad_norm": 1.5371109247207642, "learning_rate": 2.322194841328025e-05, "loss": 0.45077667236328123, "step": 465890 }, { "epoch": 2.769406351980313, "grad_norm": 1.1946847438812256, "learning_rate": 2.3220297973813136e-05, "loss": 0.478619909286499, "step": 465900 }, { "epoch": 2.7694657940569813, "grad_norm": 1.2910640239715576, "learning_rate": 2.3218647949471747e-05, "loss": 0.5613750457763672, "step": 465910 }, { "epoch": 2.7695252361336493, "grad_norm": 1.3920557498931885, "learning_rate": 2.3216998340263997e-05, "loss": 0.46672582626342773, "step": 465920 }, { "epoch": 2.769584678210318, "grad_norm": 1.597955346107483, "learning_rate": 2.3215349146197753e-05, "loss": 0.4664448261260986, "step": 465930 }, { "epoch": 2.769644120286986, "grad_norm": 1.2271989583969116, "learning_rate": 2.3213700367280927e-05, "loss": 0.468688440322876, "step": 465940 }, { "epoch": 2.769703562363655, "grad_norm": 1.060470461845398, "learning_rate": 2.321205200352138e-05, "loss": 0.44217720031738283, "step": 465950 }, { "epoch": 2.769763004440323, "grad_norm": 1.1307573318481445, "learning_rate": 2.3210404054927025e-05, "loss": 0.4719380378723145, "step": 465960 }, { "epoch": 2.7698224465169914, "grad_norm": 1.2932223081588745, "learning_rate": 2.3208756521505738e-05, "loss": 0.4190350532531738, "step": 465970 }, { "epoch": 2.76988188859366, "grad_norm": 1.2060096263885498, "learning_rate": 2.3207109403265395e-05, "loss": 0.45300860404968263, "step": 465980 }, { "epoch": 2.769941330670328, "grad_norm": 1.2543528079986572, "learning_rate": 2.320546270021387e-05, "loss": 0.42075386047363283, "step": 465990 }, { "epoch": 2.7700007727469966, "grad_norm": 1.299888253211975, "learning_rate": 2.320381641235905e-05, "loss": 0.4558867454528809, "step": 466000 }, { "epoch": 2.770060214823665, "grad_norm": 1.013924241065979, "learning_rate": 2.3202170539708802e-05, "loss": 0.42232341766357423, "step": 466010 }, { "epoch": 2.7701196569003335, "grad_norm": 1.4175351858139038, "learning_rate": 2.3200525082271007e-05, "loss": 0.4800702095031738, "step": 466020 }, { "epoch": 2.770179098977002, "grad_norm": 1.5113471746444702, "learning_rate": 2.319888004005354e-05, "loss": 0.4673591136932373, "step": 466030 }, { "epoch": 2.7702385410536703, "grad_norm": 1.6447045803070068, "learning_rate": 2.3197235413064254e-05, "loss": 0.4693424224853516, "step": 466040 }, { "epoch": 2.7702979831303387, "grad_norm": 1.3067760467529297, "learning_rate": 2.3195591201311038e-05, "loss": 0.4432559013366699, "step": 466050 }, { "epoch": 2.770357425207007, "grad_norm": 1.5731945037841797, "learning_rate": 2.319394740480175e-05, "loss": 0.4707003593444824, "step": 466060 }, { "epoch": 2.7704168672836755, "grad_norm": 1.345435380935669, "learning_rate": 2.3192304023544232e-05, "loss": 0.4633317947387695, "step": 466070 }, { "epoch": 2.770476309360344, "grad_norm": 1.0812746286392212, "learning_rate": 2.319066105754636e-05, "loss": 0.5148158550262452, "step": 466080 }, { "epoch": 2.7705357514370124, "grad_norm": 1.4966498613357544, "learning_rate": 2.318901850681601e-05, "loss": 0.4805144786834717, "step": 466090 }, { "epoch": 2.7705951935136808, "grad_norm": 1.3160322904586792, "learning_rate": 2.3187376371361035e-05, "loss": 0.48876099586486815, "step": 466100 }, { "epoch": 2.7706546355903487, "grad_norm": 1.212524175643921, "learning_rate": 2.3185734651189257e-05, "loss": 0.4670101642608643, "step": 466110 }, { "epoch": 2.7707140776670176, "grad_norm": 1.2366760969161987, "learning_rate": 2.318409334630856e-05, "loss": 0.4769484519958496, "step": 466120 }, { "epoch": 2.7707735197436856, "grad_norm": 0.9761563539505005, "learning_rate": 2.3182452456726788e-05, "loss": 0.4098848342895508, "step": 466130 }, { "epoch": 2.770832961820354, "grad_norm": 1.2190675735473633, "learning_rate": 2.3180811982451788e-05, "loss": 0.4640693187713623, "step": 466140 }, { "epoch": 2.7708924038970224, "grad_norm": 1.399045467376709, "learning_rate": 2.317917192349142e-05, "loss": 0.45826125144958496, "step": 466150 }, { "epoch": 2.770951845973691, "grad_norm": 1.2925328016281128, "learning_rate": 2.3177532279853527e-05, "loss": 0.43678483963012693, "step": 466160 }, { "epoch": 2.7710112880503592, "grad_norm": 1.5158984661102295, "learning_rate": 2.3175893051545943e-05, "loss": 0.5041868209838867, "step": 466170 }, { "epoch": 2.7710707301270276, "grad_norm": 1.6347777843475342, "learning_rate": 2.3174254238576493e-05, "loss": 0.49261884689331054, "step": 466180 }, { "epoch": 2.771130172203696, "grad_norm": 1.8891966342926025, "learning_rate": 2.3172615840953053e-05, "loss": 0.5094308376312255, "step": 466190 }, { "epoch": 2.7711896142803645, "grad_norm": 1.1647181510925293, "learning_rate": 2.317097785868343e-05, "loss": 0.4397730827331543, "step": 466200 }, { "epoch": 2.771249056357033, "grad_norm": 1.6373251676559448, "learning_rate": 2.3169340291775476e-05, "loss": 0.47128868103027344, "step": 466210 }, { "epoch": 2.7713084984337013, "grad_norm": 1.2005032300949097, "learning_rate": 2.316770314023704e-05, "loss": 0.4147964000701904, "step": 466220 }, { "epoch": 2.7713679405103697, "grad_norm": 1.2147597074508667, "learning_rate": 2.3166066404075918e-05, "loss": 0.4457228660583496, "step": 466230 }, { "epoch": 2.771427382587038, "grad_norm": 1.6722991466522217, "learning_rate": 2.316443008329995e-05, "loss": 0.509262990951538, "step": 466240 }, { "epoch": 2.7714868246637065, "grad_norm": 1.3974714279174805, "learning_rate": 2.316279417791698e-05, "loss": 0.42980012893676756, "step": 466250 }, { "epoch": 2.771546266740375, "grad_norm": 1.2855764627456665, "learning_rate": 2.316115868793483e-05, "loss": 0.43051671981811523, "step": 466260 }, { "epoch": 2.7716057088170434, "grad_norm": 1.3493622541427612, "learning_rate": 2.3159523613361315e-05, "loss": 0.4562380790710449, "step": 466270 }, { "epoch": 2.7716651508937113, "grad_norm": 1.0481476783752441, "learning_rate": 2.315788895420426e-05, "loss": 0.4265098571777344, "step": 466280 }, { "epoch": 2.77172459297038, "grad_norm": 1.3065505027770996, "learning_rate": 2.3156254710471478e-05, "loss": 0.4932283401489258, "step": 466290 }, { "epoch": 2.771784035047048, "grad_norm": 1.4608978033065796, "learning_rate": 2.3154620882170796e-05, "loss": 0.45407824516296386, "step": 466300 }, { "epoch": 2.771843477123717, "grad_norm": 1.2863452434539795, "learning_rate": 2.315298746931002e-05, "loss": 0.45511584281921386, "step": 466310 }, { "epoch": 2.771902919200385, "grad_norm": 1.418339729309082, "learning_rate": 2.3151354471896977e-05, "loss": 0.45784754753112794, "step": 466320 }, { "epoch": 2.7719623612770534, "grad_norm": 1.3896138668060303, "learning_rate": 2.3149721889939463e-05, "loss": 0.4384756565093994, "step": 466330 }, { "epoch": 2.772021803353722, "grad_norm": 0.9297456741333008, "learning_rate": 2.3148089723445317e-05, "loss": 0.47336111068725584, "step": 466340 }, { "epoch": 2.7720812454303903, "grad_norm": 1.4698408842086792, "learning_rate": 2.3146457972422302e-05, "loss": 0.49568376541137693, "step": 466350 }, { "epoch": 2.7721406875070587, "grad_norm": 1.4263873100280762, "learning_rate": 2.3144826636878263e-05, "loss": 0.46930761337280275, "step": 466360 }, { "epoch": 2.772200129583727, "grad_norm": 1.3319847583770752, "learning_rate": 2.314319571682098e-05, "loss": 0.4910407066345215, "step": 466370 }, { "epoch": 2.7722595716603955, "grad_norm": 1.4075924158096313, "learning_rate": 2.3141565212258274e-05, "loss": 0.4743794918060303, "step": 466380 }, { "epoch": 2.772319013737064, "grad_norm": 1.3733320236206055, "learning_rate": 2.313993512319792e-05, "loss": 0.4621603488922119, "step": 466390 }, { "epoch": 2.7723784558137323, "grad_norm": 1.641068458557129, "learning_rate": 2.313830544964774e-05, "loss": 0.4776630401611328, "step": 466400 }, { "epoch": 2.7724378978904007, "grad_norm": 1.2377136945724487, "learning_rate": 2.3136676191615525e-05, "loss": 0.4953620433807373, "step": 466410 }, { "epoch": 2.772497339967069, "grad_norm": 1.643528699874878, "learning_rate": 2.313504734910906e-05, "loss": 0.4822338581085205, "step": 466420 }, { "epoch": 2.7725567820437376, "grad_norm": 1.444415807723999, "learning_rate": 2.3133418922136137e-05, "loss": 0.4682157516479492, "step": 466430 }, { "epoch": 2.772616224120406, "grad_norm": 1.0664927959442139, "learning_rate": 2.313179091070454e-05, "loss": 0.46314711570739747, "step": 466440 }, { "epoch": 2.7726756661970744, "grad_norm": 1.4991858005523682, "learning_rate": 2.3130163314822078e-05, "loss": 0.4638726234436035, "step": 466450 }, { "epoch": 2.772735108273743, "grad_norm": 1.1067349910736084, "learning_rate": 2.312853613449653e-05, "loss": 0.44300260543823244, "step": 466460 }, { "epoch": 2.772794550350411, "grad_norm": 1.5182243585586548, "learning_rate": 2.3126909369735674e-05, "loss": 0.4435280799865723, "step": 466470 }, { "epoch": 2.7728539924270796, "grad_norm": 1.184971809387207, "learning_rate": 2.312528302054729e-05, "loss": 0.4202445983886719, "step": 466480 }, { "epoch": 2.7729134345037476, "grad_norm": 1.2437366247177124, "learning_rate": 2.3123657086939156e-05, "loss": 0.48388051986694336, "step": 466490 }, { "epoch": 2.7729728765804165, "grad_norm": 1.502777099609375, "learning_rate": 2.3122031568919052e-05, "loss": 0.4610546588897705, "step": 466500 }, { "epoch": 2.7730323186570844, "grad_norm": 1.1408491134643555, "learning_rate": 2.312040646649476e-05, "loss": 0.46282210350036623, "step": 466510 }, { "epoch": 2.773091760733753, "grad_norm": 1.1236778497695923, "learning_rate": 2.3118781779674063e-05, "loss": 0.4749117851257324, "step": 466520 }, { "epoch": 2.7731512028104213, "grad_norm": 0.7817328572273254, "learning_rate": 2.3117157508464722e-05, "loss": 0.40212674140930177, "step": 466530 }, { "epoch": 2.7732106448870897, "grad_norm": 1.3242192268371582, "learning_rate": 2.3115533652874486e-05, "loss": 0.45538668632507323, "step": 466540 }, { "epoch": 2.773270086963758, "grad_norm": 1.276003122329712, "learning_rate": 2.3113910212911153e-05, "loss": 0.44927215576171875, "step": 466550 }, { "epoch": 2.7733295290404265, "grad_norm": 1.3346648216247559, "learning_rate": 2.3112287188582484e-05, "loss": 0.447360897064209, "step": 466560 }, { "epoch": 2.773388971117095, "grad_norm": 1.463349461555481, "learning_rate": 2.3110664579896225e-05, "loss": 0.4691593170166016, "step": 466570 }, { "epoch": 2.7734484131937633, "grad_norm": 1.0708684921264648, "learning_rate": 2.3109042386860157e-05, "loss": 0.49846200942993163, "step": 466580 }, { "epoch": 2.7735078552704318, "grad_norm": 1.4423247575759888, "learning_rate": 2.310742060948205e-05, "loss": 0.4441875457763672, "step": 466590 }, { "epoch": 2.7735672973471, "grad_norm": 1.3813494443893433, "learning_rate": 2.3105799247769618e-05, "loss": 0.5072325706481934, "step": 466600 }, { "epoch": 2.7736267394237686, "grad_norm": 1.4403146505355835, "learning_rate": 2.3104178301730664e-05, "loss": 0.4530076503753662, "step": 466610 }, { "epoch": 2.773686181500437, "grad_norm": 1.2752610445022583, "learning_rate": 2.310255777137292e-05, "loss": 0.44802517890930177, "step": 466620 }, { "epoch": 2.7737456235771054, "grad_norm": 1.295888066291809, "learning_rate": 2.3100937656704128e-05, "loss": 0.4293178081512451, "step": 466630 }, { "epoch": 2.773805065653774, "grad_norm": 1.6865793466567993, "learning_rate": 2.3099317957732063e-05, "loss": 0.5136574268341064, "step": 466640 }, { "epoch": 2.7738645077304422, "grad_norm": 1.4244264364242554, "learning_rate": 2.309769867446447e-05, "loss": 0.5172126770019532, "step": 466650 }, { "epoch": 2.77392394980711, "grad_norm": 1.3639235496520996, "learning_rate": 2.309607980690908e-05, "loss": 0.4537497520446777, "step": 466660 }, { "epoch": 2.773983391883779, "grad_norm": 1.5422358512878418, "learning_rate": 2.3094461355073634e-05, "loss": 0.4793100357055664, "step": 466670 }, { "epoch": 2.774042833960447, "grad_norm": 1.4007104635238647, "learning_rate": 2.3092843318965897e-05, "loss": 0.4577023029327393, "step": 466680 }, { "epoch": 2.774102276037116, "grad_norm": 1.5602692365646362, "learning_rate": 2.3091225698593593e-05, "loss": 0.43227829933166506, "step": 466690 }, { "epoch": 2.774161718113784, "grad_norm": 1.4528452157974243, "learning_rate": 2.308960849396445e-05, "loss": 0.475220251083374, "step": 466700 }, { "epoch": 2.7742211601904523, "grad_norm": 1.2980109453201294, "learning_rate": 2.3087991705086233e-05, "loss": 0.41623592376708984, "step": 466710 }, { "epoch": 2.7742806022671207, "grad_norm": 0.991885781288147, "learning_rate": 2.308637533196666e-05, "loss": 0.47597737312316896, "step": 466720 }, { "epoch": 2.774340044343789, "grad_norm": 1.0483119487762451, "learning_rate": 2.308475937461345e-05, "loss": 0.47225341796875, "step": 466730 }, { "epoch": 2.7743994864204575, "grad_norm": 1.2749308347702026, "learning_rate": 2.308314383303436e-05, "loss": 0.4236783027648926, "step": 466740 }, { "epoch": 2.774458928497126, "grad_norm": 1.387308955192566, "learning_rate": 2.3081528707237104e-05, "loss": 0.437513542175293, "step": 466750 }, { "epoch": 2.7745183705737944, "grad_norm": 1.1844545602798462, "learning_rate": 2.307991399722939e-05, "loss": 0.4639273643493652, "step": 466760 }, { "epoch": 2.7745778126504628, "grad_norm": 1.1983869075775146, "learning_rate": 2.3078299703018996e-05, "loss": 0.4305964469909668, "step": 466770 }, { "epoch": 2.774637254727131, "grad_norm": 1.2818944454193115, "learning_rate": 2.307668582461359e-05, "loss": 0.45683813095092773, "step": 466780 }, { "epoch": 2.7746966968037996, "grad_norm": 1.3664807081222534, "learning_rate": 2.3075072362020918e-05, "loss": 0.46286373138427733, "step": 466790 }, { "epoch": 2.774756138880468, "grad_norm": 1.4413423538208008, "learning_rate": 2.3073459315248675e-05, "loss": 0.46683626174926757, "step": 466800 }, { "epoch": 2.7748155809571364, "grad_norm": 1.074798345565796, "learning_rate": 2.3071846684304617e-05, "loss": 0.4826936721801758, "step": 466810 }, { "epoch": 2.774875023033805, "grad_norm": 1.0624066591262817, "learning_rate": 2.307023446919642e-05, "loss": 0.46625847816467286, "step": 466820 }, { "epoch": 2.7749344651104733, "grad_norm": 1.0369207859039307, "learning_rate": 2.306862266993182e-05, "loss": 0.42043156623840333, "step": 466830 }, { "epoch": 2.7749939071871417, "grad_norm": 1.4197454452514648, "learning_rate": 2.3067011286518518e-05, "loss": 0.5014040470123291, "step": 466840 }, { "epoch": 2.7750533492638096, "grad_norm": 1.1096256971359253, "learning_rate": 2.3065400318964237e-05, "loss": 0.4841891288757324, "step": 466850 }, { "epoch": 2.7751127913404785, "grad_norm": 1.3505841493606567, "learning_rate": 2.306378976727664e-05, "loss": 0.47710933685302737, "step": 466860 }, { "epoch": 2.7751722334171465, "grad_norm": 1.1541136503219604, "learning_rate": 2.3062179631463493e-05, "loss": 0.5106914520263672, "step": 466870 }, { "epoch": 2.775231675493815, "grad_norm": 1.2370893955230713, "learning_rate": 2.3060569911532452e-05, "loss": 0.4883267402648926, "step": 466880 }, { "epoch": 2.7752911175704833, "grad_norm": 1.5599929094314575, "learning_rate": 2.3058960607491235e-05, "loss": 0.44349069595336915, "step": 466890 }, { "epoch": 2.7753505596471517, "grad_norm": 1.6610552072525024, "learning_rate": 2.305735171934754e-05, "loss": 0.5191091537475586, "step": 466900 }, { "epoch": 2.77541000172382, "grad_norm": 1.162412166595459, "learning_rate": 2.305574324710906e-05, "loss": 0.43790855407714846, "step": 466910 }, { "epoch": 2.7754694438004885, "grad_norm": 1.1074824333190918, "learning_rate": 2.305413519078348e-05, "loss": 0.4337824821472168, "step": 466920 }, { "epoch": 2.775528885877157, "grad_norm": 1.3279253244400024, "learning_rate": 2.3052527550378513e-05, "loss": 0.5235320091247558, "step": 466930 }, { "epoch": 2.7755883279538254, "grad_norm": 1.4518487453460693, "learning_rate": 2.3050920325901837e-05, "loss": 0.4734479904174805, "step": 466940 }, { "epoch": 2.775647770030494, "grad_norm": 1.3280746936798096, "learning_rate": 2.3049313517361146e-05, "loss": 0.4306465148925781, "step": 466950 }, { "epoch": 2.775707212107162, "grad_norm": 1.1795004606246948, "learning_rate": 2.3047707124764123e-05, "loss": 0.49033370018005373, "step": 466960 }, { "epoch": 2.7757666541838306, "grad_norm": 1.2373764514923096, "learning_rate": 2.3046101148118455e-05, "loss": 0.44287548065185545, "step": 466970 }, { "epoch": 2.775826096260499, "grad_norm": 1.3186262845993042, "learning_rate": 2.3044495587431822e-05, "loss": 0.45360116958618163, "step": 466980 }, { "epoch": 2.7758855383371674, "grad_norm": 1.5893751382827759, "learning_rate": 2.3042890442711892e-05, "loss": 0.4110149383544922, "step": 466990 }, { "epoch": 2.775944980413836, "grad_norm": 1.0742053985595703, "learning_rate": 2.3041285713966366e-05, "loss": 0.4153267860412598, "step": 467000 }, { "epoch": 2.7760044224905043, "grad_norm": 1.4969459772109985, "learning_rate": 2.303968140120291e-05, "loss": 0.47454276084899905, "step": 467010 }, { "epoch": 2.7760638645671722, "grad_norm": 1.5001468658447266, "learning_rate": 2.3038077504429207e-05, "loss": 0.4652246952056885, "step": 467020 }, { "epoch": 2.776123306643841, "grad_norm": 1.1904661655426025, "learning_rate": 2.303647402365292e-05, "loss": 0.4594699859619141, "step": 467030 }, { "epoch": 2.776182748720509, "grad_norm": 1.2962080240249634, "learning_rate": 2.303487095888171e-05, "loss": 0.5051055908203125, "step": 467040 }, { "epoch": 2.776242190797178, "grad_norm": 1.3233191967010498, "learning_rate": 2.303326831012327e-05, "loss": 0.4310978889465332, "step": 467050 }, { "epoch": 2.776301632873846, "grad_norm": 1.1167917251586914, "learning_rate": 2.3031666077385234e-05, "loss": 0.4885064125061035, "step": 467060 }, { "epoch": 2.7763610749505143, "grad_norm": 1.4905784130096436, "learning_rate": 2.30300642606753e-05, "loss": 0.43990330696105956, "step": 467070 }, { "epoch": 2.7764205170271827, "grad_norm": 1.2568403482437134, "learning_rate": 2.302846286000112e-05, "loss": 0.4695276260375977, "step": 467080 }, { "epoch": 2.776479959103851, "grad_norm": 1.4747097492218018, "learning_rate": 2.3026861875370344e-05, "loss": 0.4648991584777832, "step": 467090 }, { "epoch": 2.7765394011805196, "grad_norm": 1.211214542388916, "learning_rate": 2.3025261306790642e-05, "loss": 0.4161544322967529, "step": 467100 }, { "epoch": 2.776598843257188, "grad_norm": 1.1148134469985962, "learning_rate": 2.3023661154269665e-05, "loss": 0.46234931945800783, "step": 467110 }, { "epoch": 2.7766582853338564, "grad_norm": 1.2453925609588623, "learning_rate": 2.302206141781505e-05, "loss": 0.4711305141448975, "step": 467120 }, { "epoch": 2.776717727410525, "grad_norm": 1.1273932456970215, "learning_rate": 2.3020462097434488e-05, "loss": 0.4715599060058594, "step": 467130 }, { "epoch": 2.776777169487193, "grad_norm": 1.3329648971557617, "learning_rate": 2.301886319313562e-05, "loss": 0.48274989128112794, "step": 467140 }, { "epoch": 2.7768366115638616, "grad_norm": 1.6400947570800781, "learning_rate": 2.3017264704926073e-05, "loss": 0.42098293304443357, "step": 467150 }, { "epoch": 2.77689605364053, "grad_norm": 1.1130235195159912, "learning_rate": 2.30156666328135e-05, "loss": 0.4855531692504883, "step": 467160 }, { "epoch": 2.7769554957171985, "grad_norm": 1.2665666341781616, "learning_rate": 2.301406897680556e-05, "loss": 0.5385664939880371, "step": 467170 }, { "epoch": 2.777014937793867, "grad_norm": 1.0545541048049927, "learning_rate": 2.3012471736909886e-05, "loss": 0.4844522476196289, "step": 467180 }, { "epoch": 2.7770743798705353, "grad_norm": 1.0172518491744995, "learning_rate": 2.3010874913134096e-05, "loss": 0.4521444797515869, "step": 467190 }, { "epoch": 2.7771338219472037, "grad_norm": 1.3432166576385498, "learning_rate": 2.300927850548589e-05, "loss": 0.4949361801147461, "step": 467200 }, { "epoch": 2.7771932640238717, "grad_norm": 1.613502860069275, "learning_rate": 2.3007682513972844e-05, "loss": 0.43291749954223635, "step": 467210 }, { "epoch": 2.7772527061005405, "grad_norm": 1.238710880279541, "learning_rate": 2.3006086938602618e-05, "loss": 0.4289595603942871, "step": 467220 }, { "epoch": 2.7773121481772085, "grad_norm": 1.4914557933807373, "learning_rate": 2.3004491779382843e-05, "loss": 0.45195894241333007, "step": 467230 }, { "epoch": 2.7773715902538774, "grad_norm": 1.224623203277588, "learning_rate": 2.3002897036321157e-05, "loss": 0.4755399703979492, "step": 467240 }, { "epoch": 2.7774310323305453, "grad_norm": 1.5147614479064941, "learning_rate": 2.3001302709425166e-05, "loss": 0.47498278617858886, "step": 467250 }, { "epoch": 2.7774904744072137, "grad_norm": 1.5178024768829346, "learning_rate": 2.2999708798702526e-05, "loss": 0.4932860851287842, "step": 467260 }, { "epoch": 2.777549916483882, "grad_norm": 1.6099553108215332, "learning_rate": 2.2998115304160848e-05, "loss": 0.44633030891418457, "step": 467270 }, { "epoch": 2.7776093585605506, "grad_norm": 1.230603575706482, "learning_rate": 2.299652222580774e-05, "loss": 0.4585928440093994, "step": 467280 }, { "epoch": 2.777668800637219, "grad_norm": 1.4577009677886963, "learning_rate": 2.2994929563650836e-05, "loss": 0.5448426246643067, "step": 467290 }, { "epoch": 2.7777282427138874, "grad_norm": 1.1223480701446533, "learning_rate": 2.299333731769777e-05, "loss": 0.4244253158569336, "step": 467300 }, { "epoch": 2.777787684790556, "grad_norm": 1.1564841270446777, "learning_rate": 2.299174548795613e-05, "loss": 0.45014324188232424, "step": 467310 }, { "epoch": 2.7778471268672242, "grad_norm": 1.1837204694747925, "learning_rate": 2.2990154074433555e-05, "loss": 0.48384952545166016, "step": 467320 }, { "epoch": 2.7779065689438927, "grad_norm": 1.224657654762268, "learning_rate": 2.2988563077137648e-05, "loss": 0.4472515106201172, "step": 467330 }, { "epoch": 2.777966011020561, "grad_norm": 1.506896734237671, "learning_rate": 2.298697249607602e-05, "loss": 0.4414863109588623, "step": 467340 }, { "epoch": 2.7780254530972295, "grad_norm": 1.4504910707473755, "learning_rate": 2.298538233125626e-05, "loss": 0.4172344207763672, "step": 467350 }, { "epoch": 2.778084895173898, "grad_norm": 1.367860198020935, "learning_rate": 2.2983792582686012e-05, "loss": 0.4702901363372803, "step": 467360 }, { "epoch": 2.7781443372505663, "grad_norm": 1.9723373651504517, "learning_rate": 2.2982203250372866e-05, "loss": 0.49677042961120604, "step": 467370 }, { "epoch": 2.7782037793272347, "grad_norm": 1.1911778450012207, "learning_rate": 2.2980614334324412e-05, "loss": 0.4411191463470459, "step": 467380 }, { "epoch": 2.778263221403903, "grad_norm": 1.0068303346633911, "learning_rate": 2.2979025834548274e-05, "loss": 0.44939241409301756, "step": 467390 }, { "epoch": 2.778322663480571, "grad_norm": 1.1379367113113403, "learning_rate": 2.2977437751052028e-05, "loss": 0.5050423622131348, "step": 467400 }, { "epoch": 2.77838210555724, "grad_norm": 1.3388949632644653, "learning_rate": 2.2975850083843287e-05, "loss": 0.4745673656463623, "step": 467410 }, { "epoch": 2.778441547633908, "grad_norm": 1.6095644235610962, "learning_rate": 2.2974262832929622e-05, "loss": 0.5107409000396729, "step": 467420 }, { "epoch": 2.778500989710577, "grad_norm": 1.3588049411773682, "learning_rate": 2.297267599831865e-05, "loss": 0.4508977890014648, "step": 467430 }, { "epoch": 2.7785604317872448, "grad_norm": 1.1979360580444336, "learning_rate": 2.2971089580017965e-05, "loss": 0.44835147857666013, "step": 467440 }, { "epoch": 2.778619873863913, "grad_norm": 1.217360496520996, "learning_rate": 2.296950357803514e-05, "loss": 0.4438906669616699, "step": 467450 }, { "epoch": 2.7786793159405816, "grad_norm": 1.3629262447357178, "learning_rate": 2.2967917992377767e-05, "loss": 0.4605884552001953, "step": 467460 }, { "epoch": 2.77873875801725, "grad_norm": 1.1546860933303833, "learning_rate": 2.2966332823053446e-05, "loss": 0.452864933013916, "step": 467470 }, { "epoch": 2.7787982000939184, "grad_norm": 1.095361351966858, "learning_rate": 2.2964748070069725e-05, "loss": 0.45440187454223635, "step": 467480 }, { "epoch": 2.778857642170587, "grad_norm": 1.0727357864379883, "learning_rate": 2.296316373343421e-05, "loss": 0.47151899337768555, "step": 467490 }, { "epoch": 2.7789170842472553, "grad_norm": 1.4156863689422607, "learning_rate": 2.2961579813154485e-05, "loss": 0.4528497219085693, "step": 467500 }, { "epoch": 2.7789765263239237, "grad_norm": 1.639878749847412, "learning_rate": 2.295999630923811e-05, "loss": 0.4706560134887695, "step": 467510 }, { "epoch": 2.779035968400592, "grad_norm": 1.3318077325820923, "learning_rate": 2.295841322169268e-05, "loss": 0.4521904945373535, "step": 467520 }, { "epoch": 2.7790954104772605, "grad_norm": 1.3465873003005981, "learning_rate": 2.295683055052575e-05, "loss": 0.3952200889587402, "step": 467530 }, { "epoch": 2.779154852553929, "grad_norm": 1.2956700325012207, "learning_rate": 2.2955248295744892e-05, "loss": 0.43132729530334474, "step": 467540 }, { "epoch": 2.7792142946305973, "grad_norm": 1.3357988595962524, "learning_rate": 2.2953666457357677e-05, "loss": 0.4570530891418457, "step": 467550 }, { "epoch": 2.7792737367072657, "grad_norm": 1.566660761833191, "learning_rate": 2.295208503537167e-05, "loss": 0.4509413242340088, "step": 467560 }, { "epoch": 2.779333178783934, "grad_norm": 1.5554935932159424, "learning_rate": 2.2950504029794456e-05, "loss": 0.48100080490112307, "step": 467570 }, { "epoch": 2.7793926208606026, "grad_norm": 1.336412787437439, "learning_rate": 2.2948923440633572e-05, "loss": 0.5021210670471191, "step": 467580 }, { "epoch": 2.7794520629372705, "grad_norm": 1.1815869808197021, "learning_rate": 2.29473432678966e-05, "loss": 0.4497241497039795, "step": 467590 }, { "epoch": 2.7795115050139394, "grad_norm": 1.481137990951538, "learning_rate": 2.294576351159108e-05, "loss": 0.5123844146728516, "step": 467600 }, { "epoch": 2.7795709470906074, "grad_norm": 1.4869921207427979, "learning_rate": 2.2944184171724576e-05, "loss": 0.4494189739227295, "step": 467610 }, { "epoch": 2.779630389167276, "grad_norm": 1.17890465259552, "learning_rate": 2.2942605248304645e-05, "loss": 0.4945223808288574, "step": 467620 }, { "epoch": 2.779689831243944, "grad_norm": 1.3907172679901123, "learning_rate": 2.294102674133885e-05, "loss": 0.5322988033294678, "step": 467630 }, { "epoch": 2.7797492733206126, "grad_norm": 1.276841402053833, "learning_rate": 2.2939448650834737e-05, "loss": 0.47967052459716797, "step": 467640 }, { "epoch": 2.779808715397281, "grad_norm": 1.1494418382644653, "learning_rate": 2.2937870976799822e-05, "loss": 0.4675632953643799, "step": 467650 }, { "epoch": 2.7798681574739494, "grad_norm": 1.151811122894287, "learning_rate": 2.29362937192417e-05, "loss": 0.4481705665588379, "step": 467660 }, { "epoch": 2.779927599550618, "grad_norm": 1.205428123474121, "learning_rate": 2.2934716878167896e-05, "loss": 0.4649368762969971, "step": 467670 }, { "epoch": 2.7799870416272863, "grad_norm": 1.3092752695083618, "learning_rate": 2.2933140453585945e-05, "loss": 0.48173131942749026, "step": 467680 }, { "epoch": 2.7800464837039547, "grad_norm": 1.2515716552734375, "learning_rate": 2.2931564445503407e-05, "loss": 0.4688671112060547, "step": 467690 }, { "epoch": 2.780105925780623, "grad_norm": 0.9745833873748779, "learning_rate": 2.292998885392781e-05, "loss": 0.49127950668334963, "step": 467700 }, { "epoch": 2.7801653678572915, "grad_norm": 1.3107123374938965, "learning_rate": 2.2928413678866673e-05, "loss": 0.4482755661010742, "step": 467710 }, { "epoch": 2.78022480993396, "grad_norm": 1.3331371545791626, "learning_rate": 2.292683892032756e-05, "loss": 0.4803889274597168, "step": 467720 }, { "epoch": 2.7802842520106283, "grad_norm": 1.5120688676834106, "learning_rate": 2.2925264578318003e-05, "loss": 0.45298080444335936, "step": 467730 }, { "epoch": 2.7803436940872968, "grad_norm": 1.541034460067749, "learning_rate": 2.2923690652845512e-05, "loss": 0.49764289855957033, "step": 467740 }, { "epoch": 2.780403136163965, "grad_norm": 0.844470202922821, "learning_rate": 2.292211714391764e-05, "loss": 0.41689419746398926, "step": 467750 }, { "epoch": 2.780462578240633, "grad_norm": 1.5026066303253174, "learning_rate": 2.2920544051541896e-05, "loss": 0.4527534008026123, "step": 467760 }, { "epoch": 2.780522020317302, "grad_norm": 1.5938340425491333, "learning_rate": 2.291897137572581e-05, "loss": 0.49542970657348634, "step": 467770 }, { "epoch": 2.78058146239397, "grad_norm": 1.4663112163543701, "learning_rate": 2.2917399116476906e-05, "loss": 0.46120223999023435, "step": 467780 }, { "epoch": 2.780640904470639, "grad_norm": 1.2519793510437012, "learning_rate": 2.2915827273802708e-05, "loss": 0.5242507457733154, "step": 467790 }, { "epoch": 2.780700346547307, "grad_norm": 1.4951786994934082, "learning_rate": 2.2914255847710725e-05, "loss": 0.5165732860565185, "step": 467800 }, { "epoch": 2.780759788623975, "grad_norm": 1.206909418106079, "learning_rate": 2.2912684838208498e-05, "loss": 0.4666759490966797, "step": 467810 }, { "epoch": 2.7808192307006436, "grad_norm": 1.4025806188583374, "learning_rate": 2.2911114245303516e-05, "loss": 0.4346480846405029, "step": 467820 }, { "epoch": 2.780878672777312, "grad_norm": 1.0955350399017334, "learning_rate": 2.2909544069003304e-05, "loss": 0.43668618202209475, "step": 467830 }, { "epoch": 2.7809381148539805, "grad_norm": 1.3512561321258545, "learning_rate": 2.290797430931536e-05, "loss": 0.46808013916015623, "step": 467840 }, { "epoch": 2.780997556930649, "grad_norm": 1.093459129333496, "learning_rate": 2.2906404966247223e-05, "loss": 0.4479098320007324, "step": 467850 }, { "epoch": 2.7810569990073173, "grad_norm": 1.570539116859436, "learning_rate": 2.2904836039806378e-05, "loss": 0.49445219039916993, "step": 467860 }, { "epoch": 2.7811164410839857, "grad_norm": 1.487898826599121, "learning_rate": 2.2903267530000327e-05, "loss": 0.4715277671813965, "step": 467870 }, { "epoch": 2.781175883160654, "grad_norm": 1.1981192827224731, "learning_rate": 2.290169943683659e-05, "loss": 0.4588634014129639, "step": 467880 }, { "epoch": 2.7812353252373225, "grad_norm": 1.4363322257995605, "learning_rate": 2.2900131760322658e-05, "loss": 0.46459369659423827, "step": 467890 }, { "epoch": 2.781294767313991, "grad_norm": 1.1950305700302124, "learning_rate": 2.2898564500466025e-05, "loss": 0.4917466163635254, "step": 467900 }, { "epoch": 2.7813542093906594, "grad_norm": 1.26041579246521, "learning_rate": 2.2896997657274195e-05, "loss": 0.47506208419799806, "step": 467910 }, { "epoch": 2.7814136514673278, "grad_norm": 1.1906322240829468, "learning_rate": 2.2895431230754657e-05, "loss": 0.4881446361541748, "step": 467920 }, { "epoch": 2.781473093543996, "grad_norm": 1.214900016784668, "learning_rate": 2.2893865220914923e-05, "loss": 0.4648433685302734, "step": 467930 }, { "epoch": 2.7815325356206646, "grad_norm": 0.8276613354682922, "learning_rate": 2.2892299627762465e-05, "loss": 0.4898090362548828, "step": 467940 }, { "epoch": 2.7815919776973326, "grad_norm": 1.2953846454620361, "learning_rate": 2.2890734451304786e-05, "loss": 0.4347127914428711, "step": 467950 }, { "epoch": 2.7816514197740014, "grad_norm": 1.5284281969070435, "learning_rate": 2.2889169691549356e-05, "loss": 0.431146240234375, "step": 467960 }, { "epoch": 2.7817108618506694, "grad_norm": 1.3564702272415161, "learning_rate": 2.2887605348503667e-05, "loss": 0.4355149269104004, "step": 467970 }, { "epoch": 2.7817703039273383, "grad_norm": 1.030092477798462, "learning_rate": 2.2886041422175213e-05, "loss": 0.4835525035858154, "step": 467980 }, { "epoch": 2.7818297460040062, "grad_norm": 1.1237592697143555, "learning_rate": 2.2884477912571466e-05, "loss": 0.4462471008300781, "step": 467990 }, { "epoch": 2.7818891880806746, "grad_norm": 1.2403247356414795, "learning_rate": 2.288291481969991e-05, "loss": 0.46866836547851565, "step": 468000 }, { "epoch": 2.781948630157343, "grad_norm": 1.6216704845428467, "learning_rate": 2.2881352143568015e-05, "loss": 0.4666454315185547, "step": 468010 }, { "epoch": 2.7820080722340115, "grad_norm": 1.066167950630188, "learning_rate": 2.2879789884183257e-05, "loss": 0.42630863189697266, "step": 468020 }, { "epoch": 2.78206751431068, "grad_norm": 1.2280759811401367, "learning_rate": 2.2878228041553123e-05, "loss": 0.41535229682922364, "step": 468030 }, { "epoch": 2.7821269563873483, "grad_norm": 1.5361535549163818, "learning_rate": 2.2876666615685062e-05, "loss": 0.42900772094726564, "step": 468040 }, { "epoch": 2.7821863984640167, "grad_norm": 1.4197993278503418, "learning_rate": 2.2875105606586566e-05, "loss": 0.4952428340911865, "step": 468050 }, { "epoch": 2.782245840540685, "grad_norm": 1.0542490482330322, "learning_rate": 2.287354501426509e-05, "loss": 0.5093746185302734, "step": 468060 }, { "epoch": 2.7823052826173535, "grad_norm": 1.2312054634094238, "learning_rate": 2.2871984838728104e-05, "loss": 0.4596080780029297, "step": 468070 }, { "epoch": 2.782364724694022, "grad_norm": 1.1473711729049683, "learning_rate": 2.2870425079983064e-05, "loss": 0.4889334201812744, "step": 468080 }, { "epoch": 2.7824241667706904, "grad_norm": 1.4170466661453247, "learning_rate": 2.2868865738037433e-05, "loss": 0.44420900344848635, "step": 468090 }, { "epoch": 2.782483608847359, "grad_norm": 1.5356544256210327, "learning_rate": 2.2867306812898675e-05, "loss": 0.46021299362182616, "step": 468100 }, { "epoch": 2.782543050924027, "grad_norm": 1.5516618490219116, "learning_rate": 2.2865748304574252e-05, "loss": 0.4645951747894287, "step": 468110 }, { "epoch": 2.7826024930006956, "grad_norm": 1.1693613529205322, "learning_rate": 2.2864190213071612e-05, "loss": 0.5099213123321533, "step": 468120 }, { "epoch": 2.782661935077364, "grad_norm": 1.302862524986267, "learning_rate": 2.2862632538398215e-05, "loss": 0.48394002914428713, "step": 468130 }, { "epoch": 2.782721377154032, "grad_norm": 0.9062688946723938, "learning_rate": 2.2861075280561495e-05, "loss": 0.4414798736572266, "step": 468140 }, { "epoch": 2.782780819230701, "grad_norm": 1.0366114377975464, "learning_rate": 2.2859518439568923e-05, "loss": 0.4591540336608887, "step": 468150 }, { "epoch": 2.782840261307369, "grad_norm": 1.05605947971344, "learning_rate": 2.2857962015427932e-05, "loss": 0.4698348045349121, "step": 468160 }, { "epoch": 2.7828997033840377, "grad_norm": 1.2730129957199097, "learning_rate": 2.285640600814596e-05, "loss": 0.4065608024597168, "step": 468170 }, { "epoch": 2.7829591454607057, "grad_norm": 1.3937487602233887, "learning_rate": 2.285485041773048e-05, "loss": 0.4772947311401367, "step": 468180 }, { "epoch": 2.783018587537374, "grad_norm": 0.9013304710388184, "learning_rate": 2.2853295244188923e-05, "loss": 0.47287187576293943, "step": 468190 }, { "epoch": 2.7830780296140425, "grad_norm": 1.1598066091537476, "learning_rate": 2.28517404875287e-05, "loss": 0.5008206367492676, "step": 468200 }, { "epoch": 2.783137471690711, "grad_norm": 1.543523907661438, "learning_rate": 2.2850186147757286e-05, "loss": 0.4765620231628418, "step": 468210 }, { "epoch": 2.7831969137673793, "grad_norm": 1.3110272884368896, "learning_rate": 2.2848632224882092e-05, "loss": 0.4591847896575928, "step": 468220 }, { "epoch": 2.7832563558440477, "grad_norm": 1.2811870574951172, "learning_rate": 2.2847078718910557e-05, "loss": 0.4492639541625977, "step": 468230 }, { "epoch": 2.783315797920716, "grad_norm": 1.1911901235580444, "learning_rate": 2.284552562985012e-05, "loss": 0.4360679626464844, "step": 468240 }, { "epoch": 2.7833752399973846, "grad_norm": 1.3283097743988037, "learning_rate": 2.2843972957708224e-05, "loss": 0.5073400497436523, "step": 468250 }, { "epoch": 2.783434682074053, "grad_norm": 1.3525609970092773, "learning_rate": 2.2842420702492258e-05, "loss": 0.5018040180206299, "step": 468260 }, { "epoch": 2.7834941241507214, "grad_norm": 1.2801302671432495, "learning_rate": 2.2840868864209674e-05, "loss": 0.46044721603393557, "step": 468270 }, { "epoch": 2.78355356622739, "grad_norm": 1.0416522026062012, "learning_rate": 2.283931744286789e-05, "loss": 0.4754059314727783, "step": 468280 }, { "epoch": 2.7836130083040582, "grad_norm": 2.0772297382354736, "learning_rate": 2.283776643847432e-05, "loss": 0.46934165954589846, "step": 468290 }, { "epoch": 2.7836724503807266, "grad_norm": 1.568389654159546, "learning_rate": 2.283621585103638e-05, "loss": 0.49114298820495605, "step": 468300 }, { "epoch": 2.783731892457395, "grad_norm": 1.2251675128936768, "learning_rate": 2.2834665680561525e-05, "loss": 0.403049373626709, "step": 468310 }, { "epoch": 2.7837913345340635, "grad_norm": 1.3070801496505737, "learning_rate": 2.283311592705714e-05, "loss": 0.4569406986236572, "step": 468320 }, { "epoch": 2.7838507766107314, "grad_norm": 1.2209762334823608, "learning_rate": 2.2831566590530626e-05, "loss": 0.473267936706543, "step": 468330 }, { "epoch": 2.7839102186874003, "grad_norm": 1.4872095584869385, "learning_rate": 2.2830017670989417e-05, "loss": 0.4398983001708984, "step": 468340 }, { "epoch": 2.7839696607640683, "grad_norm": 1.335059642791748, "learning_rate": 2.2828469168440923e-05, "loss": 0.4817051887512207, "step": 468350 }, { "epoch": 2.7840291028407367, "grad_norm": 1.4770033359527588, "learning_rate": 2.282692108289254e-05, "loss": 0.492657470703125, "step": 468360 }, { "epoch": 2.784088544917405, "grad_norm": 1.5697723627090454, "learning_rate": 2.2825373414351675e-05, "loss": 0.4209261417388916, "step": 468370 }, { "epoch": 2.7841479869940735, "grad_norm": 1.4820317029953003, "learning_rate": 2.282382616282573e-05, "loss": 0.46820387840270994, "step": 468380 }, { "epoch": 2.784207429070742, "grad_norm": 1.2949965000152588, "learning_rate": 2.2822279328322126e-05, "loss": 0.5159695625305176, "step": 468390 }, { "epoch": 2.7842668711474103, "grad_norm": 1.5704573392868042, "learning_rate": 2.2820732910848234e-05, "loss": 0.4018956184387207, "step": 468400 }, { "epoch": 2.7843263132240788, "grad_norm": 1.5065178871154785, "learning_rate": 2.2819186910411464e-05, "loss": 0.45426530838012696, "step": 468410 }, { "epoch": 2.784385755300747, "grad_norm": 1.4107012748718262, "learning_rate": 2.2817641327019223e-05, "loss": 0.4518634796142578, "step": 468420 }, { "epoch": 2.7844451973774156, "grad_norm": 1.564071536064148, "learning_rate": 2.2816096160678896e-05, "loss": 0.4909360408782959, "step": 468430 }, { "epoch": 2.784504639454084, "grad_norm": 1.3366436958312988, "learning_rate": 2.2814551411397864e-05, "loss": 0.45102863311767577, "step": 468440 }, { "epoch": 2.7845640815307524, "grad_norm": 1.0745080709457397, "learning_rate": 2.2813007079183522e-05, "loss": 0.4523651599884033, "step": 468450 }, { "epoch": 2.784623523607421, "grad_norm": 1.139074444770813, "learning_rate": 2.281146316404327e-05, "loss": 0.513827896118164, "step": 468460 }, { "epoch": 2.7846829656840892, "grad_norm": 1.1387003660202026, "learning_rate": 2.2809919665984485e-05, "loss": 0.4747437000274658, "step": 468470 }, { "epoch": 2.7847424077607577, "grad_norm": 1.2535372972488403, "learning_rate": 2.2808376585014545e-05, "loss": 0.44002480506896974, "step": 468480 }, { "epoch": 2.784801849837426, "grad_norm": 1.3662551641464233, "learning_rate": 2.2806833921140843e-05, "loss": 0.5050529956817627, "step": 468490 }, { "epoch": 2.784861291914094, "grad_norm": 1.4044969081878662, "learning_rate": 2.2805291674370748e-05, "loss": 0.483333683013916, "step": 468500 }, { "epoch": 2.784920733990763, "grad_norm": 1.2782435417175293, "learning_rate": 2.280374984471164e-05, "loss": 0.46136045455932617, "step": 468510 }, { "epoch": 2.784980176067431, "grad_norm": 1.2490447759628296, "learning_rate": 2.2802208432170906e-05, "loss": 0.46421194076538086, "step": 468520 }, { "epoch": 2.7850396181440997, "grad_norm": 1.351155161857605, "learning_rate": 2.2800667436755893e-05, "loss": 0.45183191299438474, "step": 468530 }, { "epoch": 2.7850990602207677, "grad_norm": 1.4459648132324219, "learning_rate": 2.279912685847401e-05, "loss": 0.48402109146118166, "step": 468540 }, { "epoch": 2.785158502297436, "grad_norm": 1.4338299036026, "learning_rate": 2.2797586697332595e-05, "loss": 0.49349727630615237, "step": 468550 }, { "epoch": 2.7852179443741045, "grad_norm": 1.3643321990966797, "learning_rate": 2.279604695333903e-05, "loss": 0.4838465690612793, "step": 468560 }, { "epoch": 2.785277386450773, "grad_norm": 1.58571457862854, "learning_rate": 2.2794507626500685e-05, "loss": 0.480745267868042, "step": 468570 }, { "epoch": 2.7853368285274414, "grad_norm": 1.3291823863983154, "learning_rate": 2.2792968716824904e-05, "loss": 0.41173372268676756, "step": 468580 }, { "epoch": 2.7853962706041098, "grad_norm": 1.440806269645691, "learning_rate": 2.279143022431906e-05, "loss": 0.48116397857666016, "step": 468590 }, { "epoch": 2.785455712680778, "grad_norm": 1.074765920639038, "learning_rate": 2.2789892148990522e-05, "loss": 0.42550153732299806, "step": 468600 }, { "epoch": 2.7855151547574466, "grad_norm": 1.4951250553131104, "learning_rate": 2.278835449084664e-05, "loss": 0.4842694282531738, "step": 468610 }, { "epoch": 2.785574596834115, "grad_norm": 1.2802096605300903, "learning_rate": 2.2786817249894777e-05, "loss": 0.44510226249694823, "step": 468620 }, { "epoch": 2.7856340389107834, "grad_norm": 1.2931201457977295, "learning_rate": 2.2785280426142258e-05, "loss": 0.5077522277832032, "step": 468630 }, { "epoch": 2.785693480987452, "grad_norm": 1.2327899932861328, "learning_rate": 2.278374401959647e-05, "loss": 0.40476016998291015, "step": 468640 }, { "epoch": 2.7857529230641203, "grad_norm": 1.6851515769958496, "learning_rate": 2.2782208030264747e-05, "loss": 0.4757255554199219, "step": 468650 }, { "epoch": 2.7858123651407887, "grad_norm": 1.1726641654968262, "learning_rate": 2.278067245815442e-05, "loss": 0.45564918518066405, "step": 468660 }, { "epoch": 2.785871807217457, "grad_norm": 1.458122968673706, "learning_rate": 2.2779137303272874e-05, "loss": 0.46824159622192385, "step": 468670 }, { "epoch": 2.7859312492941255, "grad_norm": 1.4963011741638184, "learning_rate": 2.2777602565627436e-05, "loss": 0.42608299255371096, "step": 468680 }, { "epoch": 2.7859906913707935, "grad_norm": 1.1107308864593506, "learning_rate": 2.2776068245225413e-05, "loss": 0.45060291290283205, "step": 468690 }, { "epoch": 2.7860501334474623, "grad_norm": 1.1043320894241333, "learning_rate": 2.2774534342074198e-05, "loss": 0.4490349769592285, "step": 468700 }, { "epoch": 2.7861095755241303, "grad_norm": 0.9269363284111023, "learning_rate": 2.2773000856181097e-05, "loss": 0.4444594383239746, "step": 468710 }, { "epoch": 2.786169017600799, "grad_norm": 1.1025561094284058, "learning_rate": 2.2771467787553464e-05, "loss": 0.4406906604766846, "step": 468720 }, { "epoch": 2.786228459677467, "grad_norm": 1.199987769126892, "learning_rate": 2.2769935136198605e-05, "loss": 0.43581371307373046, "step": 468730 }, { "epoch": 2.7862879017541355, "grad_norm": 1.3216406106948853, "learning_rate": 2.2768402902123885e-05, "loss": 0.450726318359375, "step": 468740 }, { "epoch": 2.786347343830804, "grad_norm": 1.5169165134429932, "learning_rate": 2.276687108533662e-05, "loss": 0.45101299285888674, "step": 468750 }, { "epoch": 2.7864067859074724, "grad_norm": 1.3288532495498657, "learning_rate": 2.2765339685844113e-05, "loss": 0.4540560722351074, "step": 468760 }, { "epoch": 2.786466227984141, "grad_norm": 1.2426618337631226, "learning_rate": 2.276380870365373e-05, "loss": 0.4412686824798584, "step": 468770 }, { "epoch": 2.786525670060809, "grad_norm": 1.554875135421753, "learning_rate": 2.2762278138772776e-05, "loss": 0.46522960662841795, "step": 468780 }, { "epoch": 2.7865851121374776, "grad_norm": 1.4154109954833984, "learning_rate": 2.276074799120856e-05, "loss": 0.49750165939331054, "step": 468790 }, { "epoch": 2.786644554214146, "grad_norm": 1.334373950958252, "learning_rate": 2.275921826096844e-05, "loss": 0.440310001373291, "step": 468800 }, { "epoch": 2.7867039962908144, "grad_norm": 1.2498371601104736, "learning_rate": 2.27576889480597e-05, "loss": 0.5365428447723388, "step": 468810 }, { "epoch": 2.786763438367483, "grad_norm": 1.1278403997421265, "learning_rate": 2.2756160052489644e-05, "loss": 0.46308460235595705, "step": 468820 }, { "epoch": 2.7868228804441513, "grad_norm": 1.3797063827514648, "learning_rate": 2.2754631574265626e-05, "loss": 0.4792156219482422, "step": 468830 }, { "epoch": 2.7868823225208197, "grad_norm": 0.9534748196601868, "learning_rate": 2.275310351339494e-05, "loss": 0.4486653804779053, "step": 468840 }, { "epoch": 2.786941764597488, "grad_norm": 1.4523895978927612, "learning_rate": 2.2751575869884886e-05, "loss": 0.4404136657714844, "step": 468850 }, { "epoch": 2.7870012066741565, "grad_norm": 1.5853296518325806, "learning_rate": 2.2750048643742785e-05, "loss": 0.4699705600738525, "step": 468860 }, { "epoch": 2.787060648750825, "grad_norm": 1.2539570331573486, "learning_rate": 2.274852183497594e-05, "loss": 0.489957332611084, "step": 468870 }, { "epoch": 2.787120090827493, "grad_norm": 1.2842888832092285, "learning_rate": 2.274699544359165e-05, "loss": 0.45142831802368166, "step": 468880 }, { "epoch": 2.7871795329041618, "grad_norm": 1.381197214126587, "learning_rate": 2.2745469469597217e-05, "loss": 0.45948266983032227, "step": 468890 }, { "epoch": 2.7872389749808297, "grad_norm": 1.20149564743042, "learning_rate": 2.274394391299995e-05, "loss": 0.4938357353210449, "step": 468900 }, { "epoch": 2.7872984170574986, "grad_norm": 1.195094108581543, "learning_rate": 2.2742418773807132e-05, "loss": 0.4562946319580078, "step": 468910 }, { "epoch": 2.7873578591341666, "grad_norm": 1.624281644821167, "learning_rate": 2.274089405202607e-05, "loss": 0.4260274887084961, "step": 468920 }, { "epoch": 2.787417301210835, "grad_norm": 1.1375982761383057, "learning_rate": 2.2739369747664056e-05, "loss": 0.508090591430664, "step": 468930 }, { "epoch": 2.7874767432875034, "grad_norm": 1.050912618637085, "learning_rate": 2.2737845860728376e-05, "loss": 0.4882938861846924, "step": 468940 }, { "epoch": 2.787536185364172, "grad_norm": 1.5273746252059937, "learning_rate": 2.2736322391226315e-05, "loss": 0.4857653617858887, "step": 468950 }, { "epoch": 2.78759562744084, "grad_norm": 1.0381197929382324, "learning_rate": 2.2734799339165174e-05, "loss": 0.4642824649810791, "step": 468960 }, { "epoch": 2.7876550695175086, "grad_norm": 1.2982929944992065, "learning_rate": 2.2733276704552253e-05, "loss": 0.43296356201171876, "step": 468970 }, { "epoch": 2.787714511594177, "grad_norm": 1.5412001609802246, "learning_rate": 2.2731754487394798e-05, "loss": 0.47825055122375487, "step": 468980 }, { "epoch": 2.7877739536708455, "grad_norm": 1.1400569677352905, "learning_rate": 2.273023268770012e-05, "loss": 0.4602514266967773, "step": 468990 }, { "epoch": 2.787833395747514, "grad_norm": 1.4878134727478027, "learning_rate": 2.2728711305475488e-05, "loss": 0.48566336631774903, "step": 469000 }, { "epoch": 2.7878928378241823, "grad_norm": 1.1366374492645264, "learning_rate": 2.272719034072818e-05, "loss": 0.4233543872833252, "step": 469010 }, { "epoch": 2.7879522799008507, "grad_norm": 1.1650607585906982, "learning_rate": 2.272566979346546e-05, "loss": 0.45847654342651367, "step": 469020 }, { "epoch": 2.788011721977519, "grad_norm": 1.219273567199707, "learning_rate": 2.272414966369462e-05, "loss": 0.46013317108154295, "step": 469030 }, { "epoch": 2.7880711640541875, "grad_norm": 1.1586318016052246, "learning_rate": 2.2722629951422935e-05, "loss": 0.43471035957336424, "step": 469040 }, { "epoch": 2.788130606130856, "grad_norm": 1.2210708856582642, "learning_rate": 2.272111065665766e-05, "loss": 0.513121223449707, "step": 469050 }, { "epoch": 2.7881900482075244, "grad_norm": 1.0002535581588745, "learning_rate": 2.2719591779406068e-05, "loss": 0.45038766860961915, "step": 469060 }, { "epoch": 2.7882494902841923, "grad_norm": 1.140659213066101, "learning_rate": 2.2718073319675433e-05, "loss": 0.46674599647521975, "step": 469070 }, { "epoch": 2.788308932360861, "grad_norm": 1.3103846311569214, "learning_rate": 2.2716555277472993e-05, "loss": 0.4245567798614502, "step": 469080 }, { "epoch": 2.788368374437529, "grad_norm": 1.5272270441055298, "learning_rate": 2.2715037652806036e-05, "loss": 0.47634615898132326, "step": 469090 }, { "epoch": 2.7884278165141976, "grad_norm": 1.4111868143081665, "learning_rate": 2.271352044568182e-05, "loss": 0.4375709056854248, "step": 469100 }, { "epoch": 2.788487258590866, "grad_norm": 1.3892382383346558, "learning_rate": 2.271200365610761e-05, "loss": 0.4785611152648926, "step": 469110 }, { "epoch": 2.7885467006675344, "grad_norm": 1.7788832187652588, "learning_rate": 2.271048728409062e-05, "loss": 0.4694960117340088, "step": 469120 }, { "epoch": 2.788606142744203, "grad_norm": 1.2355406284332275, "learning_rate": 2.2708971329638148e-05, "loss": 0.4573334217071533, "step": 469130 }, { "epoch": 2.7886655848208712, "grad_norm": 1.5855259895324707, "learning_rate": 2.2707455792757427e-05, "loss": 0.47412815093994143, "step": 469140 }, { "epoch": 2.7887250268975396, "grad_norm": 1.552319884300232, "learning_rate": 2.2705940673455705e-05, "loss": 0.43243932723999023, "step": 469150 }, { "epoch": 2.788784468974208, "grad_norm": 1.2353702783584595, "learning_rate": 2.2704425971740243e-05, "loss": 0.5148489475250244, "step": 469160 }, { "epoch": 2.7888439110508765, "grad_norm": 1.6799743175506592, "learning_rate": 2.2702911687618286e-05, "loss": 0.4708854198455811, "step": 469170 }, { "epoch": 2.788903353127545, "grad_norm": 1.407167911529541, "learning_rate": 2.2701397821097047e-05, "loss": 0.46741509437561035, "step": 469180 }, { "epoch": 2.7889627952042133, "grad_norm": 1.5291680097579956, "learning_rate": 2.2699884372183803e-05, "loss": 0.44545822143554686, "step": 469190 }, { "epoch": 2.7890222372808817, "grad_norm": 1.3888773918151855, "learning_rate": 2.2698371340885794e-05, "loss": 0.5184304237365722, "step": 469200 }, { "epoch": 2.78908167935755, "grad_norm": 1.2714072465896606, "learning_rate": 2.2696858727210228e-05, "loss": 0.5238643646240234, "step": 469210 }, { "epoch": 2.7891411214342186, "grad_norm": 1.203622817993164, "learning_rate": 2.2695346531164365e-05, "loss": 0.4563440322875977, "step": 469220 }, { "epoch": 2.789200563510887, "grad_norm": 1.221752643585205, "learning_rate": 2.269383475275544e-05, "loss": 0.5023320198059082, "step": 469230 }, { "epoch": 2.789260005587555, "grad_norm": 1.213441252708435, "learning_rate": 2.269232339199067e-05, "loss": 0.4235528945922852, "step": 469240 }, { "epoch": 2.789319447664224, "grad_norm": 1.0374290943145752, "learning_rate": 2.2690812448877293e-05, "loss": 0.4432226181030273, "step": 469250 }, { "epoch": 2.7893788897408918, "grad_norm": 1.0149108171463013, "learning_rate": 2.2689301923422535e-05, "loss": 0.47726807594299314, "step": 469260 }, { "epoch": 2.7894383318175606, "grad_norm": 1.109818458557129, "learning_rate": 2.268779181563363e-05, "loss": 0.4142632484436035, "step": 469270 }, { "epoch": 2.7894977738942286, "grad_norm": 1.1626166105270386, "learning_rate": 2.268628212551778e-05, "loss": 0.48995490074157716, "step": 469280 }, { "epoch": 2.789557215970897, "grad_norm": 1.256581425666809, "learning_rate": 2.2684772853082243e-05, "loss": 0.4603839874267578, "step": 469290 }, { "epoch": 2.7896166580475654, "grad_norm": 1.4153664112091064, "learning_rate": 2.2683263998334206e-05, "loss": 0.45031185150146485, "step": 469300 }, { "epoch": 2.789676100124234, "grad_norm": 0.7241479158401489, "learning_rate": 2.268175556128089e-05, "loss": 0.43338909149169924, "step": 469310 }, { "epoch": 2.7897355422009023, "grad_norm": 1.366621732711792, "learning_rate": 2.2680247541929527e-05, "loss": 0.47750425338745117, "step": 469320 }, { "epoch": 2.7897949842775707, "grad_norm": 1.3040945529937744, "learning_rate": 2.2678739940287335e-05, "loss": 0.5126095771789551, "step": 469330 }, { "epoch": 2.789854426354239, "grad_norm": 1.2923961877822876, "learning_rate": 2.26772327563615e-05, "loss": 0.47656707763671874, "step": 469340 }, { "epoch": 2.7899138684309075, "grad_norm": 1.3359556198120117, "learning_rate": 2.267572599015925e-05, "loss": 0.4701682567596436, "step": 469350 }, { "epoch": 2.789973310507576, "grad_norm": 1.451683521270752, "learning_rate": 2.2674219641687793e-05, "loss": 0.4640962600708008, "step": 469360 }, { "epoch": 2.7900327525842443, "grad_norm": 1.811672329902649, "learning_rate": 2.2672713710954326e-05, "loss": 0.4459886074066162, "step": 469370 }, { "epoch": 2.7900921946609127, "grad_norm": 1.1485031843185425, "learning_rate": 2.2671208197966053e-05, "loss": 0.45312976837158203, "step": 469380 }, { "epoch": 2.790151636737581, "grad_norm": 1.4589884281158447, "learning_rate": 2.2669703102730188e-05, "loss": 0.4855314254760742, "step": 469390 }, { "epoch": 2.7902110788142496, "grad_norm": 1.3575116395950317, "learning_rate": 2.2668198425253923e-05, "loss": 0.4715970516204834, "step": 469400 }, { "epoch": 2.790270520890918, "grad_norm": 1.309068202972412, "learning_rate": 2.266669416554446e-05, "loss": 0.44255900382995605, "step": 469410 }, { "epoch": 2.7903299629675864, "grad_norm": 1.293533205986023, "learning_rate": 2.2665190323608985e-05, "loss": 0.48566231727600095, "step": 469420 }, { "epoch": 2.7903894050442544, "grad_norm": 1.2691221237182617, "learning_rate": 2.2663686899454708e-05, "loss": 0.4801929473876953, "step": 469430 }, { "epoch": 2.7904488471209232, "grad_norm": 1.1552214622497559, "learning_rate": 2.2662183893088793e-05, "loss": 0.4624637603759766, "step": 469440 }, { "epoch": 2.790508289197591, "grad_norm": 1.248105525970459, "learning_rate": 2.2660681304518464e-05, "loss": 0.4903434753417969, "step": 469450 }, { "epoch": 2.79056773127426, "grad_norm": 1.221110463142395, "learning_rate": 2.2659179133750887e-05, "loss": 0.4638339996337891, "step": 469460 }, { "epoch": 2.790627173350928, "grad_norm": 1.510461449623108, "learning_rate": 2.265767738079325e-05, "loss": 0.507692813873291, "step": 469470 }, { "epoch": 2.7906866154275964, "grad_norm": 1.4455476999282837, "learning_rate": 2.265617604565275e-05, "loss": 0.45093860626220705, "step": 469480 }, { "epoch": 2.790746057504265, "grad_norm": 1.1788065433502197, "learning_rate": 2.265467512833655e-05, "loss": 0.437143611907959, "step": 469490 }, { "epoch": 2.7908054995809333, "grad_norm": 1.0755205154418945, "learning_rate": 2.2653174628851843e-05, "loss": 0.4581000328063965, "step": 469500 }, { "epoch": 2.7908649416576017, "grad_norm": 1.1192978620529175, "learning_rate": 2.2651674547205796e-05, "loss": 0.45518102645874026, "step": 469510 }, { "epoch": 2.79092438373427, "grad_norm": 1.4620039463043213, "learning_rate": 2.2650174883405603e-05, "loss": 0.44283246994018555, "step": 469520 }, { "epoch": 2.7909838258109385, "grad_norm": 1.1774210929870605, "learning_rate": 2.2648675637458426e-05, "loss": 0.44859957695007324, "step": 469530 }, { "epoch": 2.791043267887607, "grad_norm": 1.7102394104003906, "learning_rate": 2.264717680937144e-05, "loss": 0.4460179328918457, "step": 469540 }, { "epoch": 2.7911027099642753, "grad_norm": 1.5571483373641968, "learning_rate": 2.264567839915181e-05, "loss": 0.45981321334838865, "step": 469550 }, { "epoch": 2.7911621520409438, "grad_norm": 1.379969835281372, "learning_rate": 2.26441804068067e-05, "loss": 0.44117107391357424, "step": 469560 }, { "epoch": 2.791221594117612, "grad_norm": 1.2592859268188477, "learning_rate": 2.2642682832343292e-05, "loss": 0.4584153175354004, "step": 469570 }, { "epoch": 2.7912810361942806, "grad_norm": 1.4180822372436523, "learning_rate": 2.2641185675768728e-05, "loss": 0.4732943058013916, "step": 469580 }, { "epoch": 2.791340478270949, "grad_norm": 0.9492257833480835, "learning_rate": 2.26396889370902e-05, "loss": 0.44045066833496094, "step": 469590 }, { "epoch": 2.7913999203476174, "grad_norm": 1.2056041955947876, "learning_rate": 2.2638192616314834e-05, "loss": 0.47418913841247556, "step": 469600 }, { "epoch": 2.791459362424286, "grad_norm": 1.300961971282959, "learning_rate": 2.263669671344982e-05, "loss": 0.42996931076049805, "step": 469610 }, { "epoch": 2.791518804500954, "grad_norm": 1.2093696594238281, "learning_rate": 2.263520122850229e-05, "loss": 0.4423066139221191, "step": 469620 }, { "epoch": 2.7915782465776227, "grad_norm": 1.2504125833511353, "learning_rate": 2.2633706161479408e-05, "loss": 0.46819429397583007, "step": 469630 }, { "epoch": 2.7916376886542906, "grad_norm": 1.5318365097045898, "learning_rate": 2.2632211512388322e-05, "loss": 0.4409781455993652, "step": 469640 }, { "epoch": 2.7916971307309595, "grad_norm": 1.3859243392944336, "learning_rate": 2.2630717281236182e-05, "loss": 0.46764307022094725, "step": 469650 }, { "epoch": 2.7917565728076275, "grad_norm": 1.3128379583358765, "learning_rate": 2.262922346803014e-05, "loss": 0.45993900299072266, "step": 469660 }, { "epoch": 2.791816014884296, "grad_norm": 1.4587454795837402, "learning_rate": 2.2627730072777348e-05, "loss": 0.4537955284118652, "step": 469670 }, { "epoch": 2.7918754569609643, "grad_norm": 1.1547917127609253, "learning_rate": 2.2626237095484935e-05, "loss": 0.5296941757202148, "step": 469680 }, { "epoch": 2.7919348990376327, "grad_norm": 1.190804123878479, "learning_rate": 2.262474453616005e-05, "loss": 0.4744900703430176, "step": 469690 }, { "epoch": 2.791994341114301, "grad_norm": 1.105970025062561, "learning_rate": 2.2623252394809832e-05, "loss": 0.444179630279541, "step": 469700 }, { "epoch": 2.7920537831909695, "grad_norm": 1.7158328294754028, "learning_rate": 2.262176067144141e-05, "loss": 0.47236342430114747, "step": 469710 }, { "epoch": 2.792113225267638, "grad_norm": 1.443061351776123, "learning_rate": 2.2620269366061947e-05, "loss": 0.44617090225219724, "step": 469720 }, { "epoch": 2.7921726673443064, "grad_norm": 1.1226214170455933, "learning_rate": 2.2618778478678557e-05, "loss": 0.4473566055297852, "step": 469730 }, { "epoch": 2.7922321094209748, "grad_norm": 1.5719419717788696, "learning_rate": 2.261728800929836e-05, "loss": 0.4860665798187256, "step": 469740 }, { "epoch": 2.792291551497643, "grad_norm": 1.1951640844345093, "learning_rate": 2.261579795792851e-05, "loss": 0.45376005172729494, "step": 469750 }, { "epoch": 2.7923509935743116, "grad_norm": 1.268136739730835, "learning_rate": 2.2614308324576124e-05, "loss": 0.44396533966064455, "step": 469760 }, { "epoch": 2.79241043565098, "grad_norm": 1.3216418027877808, "learning_rate": 2.2612819109248317e-05, "loss": 0.4921051025390625, "step": 469770 }, { "epoch": 2.7924698777276484, "grad_norm": 0.8230710029602051, "learning_rate": 2.261133031195225e-05, "loss": 0.45168094635009765, "step": 469780 }, { "epoch": 2.792529319804317, "grad_norm": 1.3705487251281738, "learning_rate": 2.260984193269501e-05, "loss": 0.40036735534667967, "step": 469790 }, { "epoch": 2.7925887618809853, "grad_norm": 1.6325562000274658, "learning_rate": 2.2608353971483714e-05, "loss": 0.48200273513793945, "step": 469800 }, { "epoch": 2.7926482039576532, "grad_norm": 1.5070325136184692, "learning_rate": 2.2606866428325506e-05, "loss": 0.43541641235351564, "step": 469810 }, { "epoch": 2.792707646034322, "grad_norm": 1.5515567064285278, "learning_rate": 2.260537930322748e-05, "loss": 0.48245925903320314, "step": 469820 }, { "epoch": 2.79276708811099, "grad_norm": 1.4378492832183838, "learning_rate": 2.2603892596196764e-05, "loss": 0.4190701484680176, "step": 469830 }, { "epoch": 2.7928265301876585, "grad_norm": 1.0197334289550781, "learning_rate": 2.2602406307240465e-05, "loss": 0.4358680725097656, "step": 469840 }, { "epoch": 2.792885972264327, "grad_norm": 0.9836238622665405, "learning_rate": 2.2600920436365693e-05, "loss": 0.47699794769287107, "step": 469850 }, { "epoch": 2.7929454143409953, "grad_norm": 1.409532904624939, "learning_rate": 2.259943498357956e-05, "loss": 0.4547887325286865, "step": 469860 }, { "epoch": 2.7930048564176637, "grad_norm": 1.2767024040222168, "learning_rate": 2.259794994888915e-05, "loss": 0.47188353538513184, "step": 469870 }, { "epoch": 2.793064298494332, "grad_norm": 1.2572479248046875, "learning_rate": 2.2596465332301593e-05, "loss": 0.4847048282623291, "step": 469880 }, { "epoch": 2.7931237405710005, "grad_norm": 1.2891079187393188, "learning_rate": 2.2594981133823983e-05, "loss": 0.43497161865234374, "step": 469890 }, { "epoch": 2.793183182647669, "grad_norm": 1.3536972999572754, "learning_rate": 2.259349735346343e-05, "loss": 0.4258999824523926, "step": 469900 }, { "epoch": 2.7932426247243374, "grad_norm": 0.9518484473228455, "learning_rate": 2.2592013991227003e-05, "loss": 0.40977892875671384, "step": 469910 }, { "epoch": 2.793302066801006, "grad_norm": 1.2252815961837769, "learning_rate": 2.259053104712183e-05, "loss": 0.455152702331543, "step": 469920 }, { "epoch": 2.793361508877674, "grad_norm": 1.422079086303711, "learning_rate": 2.258904852115497e-05, "loss": 0.49742584228515624, "step": 469930 }, { "epoch": 2.7934209509543426, "grad_norm": 1.2965024709701538, "learning_rate": 2.258756641333355e-05, "loss": 0.46422595977783204, "step": 469940 }, { "epoch": 2.793480393031011, "grad_norm": 1.5769668817520142, "learning_rate": 2.2586084723664652e-05, "loss": 0.4338072776794434, "step": 469950 }, { "epoch": 2.7935398351076794, "grad_norm": 1.5495685338974, "learning_rate": 2.258460345215535e-05, "loss": 0.47348957061767577, "step": 469960 }, { "epoch": 2.793599277184348, "grad_norm": 1.4421039819717407, "learning_rate": 2.2583122598812738e-05, "loss": 0.4398475170135498, "step": 469970 }, { "epoch": 2.793658719261016, "grad_norm": 1.771206021308899, "learning_rate": 2.2581642163643905e-05, "loss": 0.49247016906738283, "step": 469980 }, { "epoch": 2.7937181613376847, "grad_norm": 1.1834304332733154, "learning_rate": 2.258016214665592e-05, "loss": 0.4692661285400391, "step": 469990 }, { "epoch": 2.7937776034143527, "grad_norm": 1.296372413635254, "learning_rate": 2.257868254785587e-05, "loss": 0.4670903205871582, "step": 470000 }, { "epoch": 2.7938370454910215, "grad_norm": 1.184924602508545, "learning_rate": 2.2577203367250826e-05, "loss": 0.4470804214477539, "step": 470010 }, { "epoch": 2.7938964875676895, "grad_norm": 1.2446775436401367, "learning_rate": 2.2575724604847888e-05, "loss": 0.48187956809997556, "step": 470020 }, { "epoch": 2.793955929644358, "grad_norm": 1.0576086044311523, "learning_rate": 2.257424626065411e-05, "loss": 0.42642598152160643, "step": 470030 }, { "epoch": 2.7940153717210263, "grad_norm": 1.3092472553253174, "learning_rate": 2.257276833467656e-05, "loss": 0.44565258026123045, "step": 470040 }, { "epoch": 2.7940748137976947, "grad_norm": 1.2981126308441162, "learning_rate": 2.2571290826922316e-05, "loss": 0.4567840099334717, "step": 470050 }, { "epoch": 2.794134255874363, "grad_norm": 1.1574121713638306, "learning_rate": 2.2569813737398448e-05, "loss": 0.41759839057922366, "step": 470060 }, { "epoch": 2.7941936979510316, "grad_norm": 1.2553026676177979, "learning_rate": 2.2568337066112012e-05, "loss": 0.45876436233520507, "step": 470070 }, { "epoch": 2.7942531400277, "grad_norm": 1.3421428203582764, "learning_rate": 2.256686081307008e-05, "loss": 0.477158260345459, "step": 470080 }, { "epoch": 2.7943125821043684, "grad_norm": 1.297888159751892, "learning_rate": 2.2565384978279712e-05, "loss": 0.4877768516540527, "step": 470090 }, { "epoch": 2.794372024181037, "grad_norm": 1.1785389184951782, "learning_rate": 2.2563909561747975e-05, "loss": 0.4228175163269043, "step": 470100 }, { "epoch": 2.794431466257705, "grad_norm": 1.172061800956726, "learning_rate": 2.2562434563481918e-05, "loss": 0.44449796676635744, "step": 470110 }, { "epoch": 2.7944909083343736, "grad_norm": 1.4200589656829834, "learning_rate": 2.25609599834886e-05, "loss": 0.4487953186035156, "step": 470120 }, { "epoch": 2.794550350411042, "grad_norm": 1.4268797636032104, "learning_rate": 2.255948582177506e-05, "loss": 0.4875300407409668, "step": 470130 }, { "epoch": 2.7946097924877105, "grad_norm": 1.3242496252059937, "learning_rate": 2.2558012078348375e-05, "loss": 0.45855140686035156, "step": 470140 }, { "epoch": 2.794669234564379, "grad_norm": 1.1748387813568115, "learning_rate": 2.255653875321559e-05, "loss": 0.4504812717437744, "step": 470150 }, { "epoch": 2.7947286766410473, "grad_norm": 1.3627914190292358, "learning_rate": 2.255506584638374e-05, "loss": 0.4265892028808594, "step": 470160 }, { "epoch": 2.7947881187177153, "grad_norm": 1.4961624145507812, "learning_rate": 2.2553593357859875e-05, "loss": 0.47043538093566895, "step": 470170 }, { "epoch": 2.794847560794384, "grad_norm": 1.2583898305892944, "learning_rate": 2.2552121287651055e-05, "loss": 0.45488543510437013, "step": 470180 }, { "epoch": 2.794907002871052, "grad_norm": 0.9529891610145569, "learning_rate": 2.2550649635764293e-05, "loss": 0.5007597923278808, "step": 470190 }, { "epoch": 2.794966444947721, "grad_norm": 1.2707587480545044, "learning_rate": 2.2549178402206643e-05, "loss": 0.4187575340270996, "step": 470200 }, { "epoch": 2.795025887024389, "grad_norm": 1.1791805028915405, "learning_rate": 2.2547707586985156e-05, "loss": 0.44901156425476074, "step": 470210 }, { "epoch": 2.7950853291010573, "grad_norm": 1.4470270872116089, "learning_rate": 2.254623719010686e-05, "loss": 0.4475123405456543, "step": 470220 }, { "epoch": 2.7951447711777258, "grad_norm": 1.1533472537994385, "learning_rate": 2.254476721157877e-05, "loss": 0.4883861541748047, "step": 470230 }, { "epoch": 2.795204213254394, "grad_norm": 1.2322938442230225, "learning_rate": 2.2543297651407947e-05, "loss": 0.46121888160705565, "step": 470240 }, { "epoch": 2.7952636553310626, "grad_norm": 1.5725293159484863, "learning_rate": 2.25418285096014e-05, "loss": 0.4539363384246826, "step": 470250 }, { "epoch": 2.795323097407731, "grad_norm": 1.5096497535705566, "learning_rate": 2.2540359786166155e-05, "loss": 0.41395182609558107, "step": 470260 }, { "epoch": 2.7953825394843994, "grad_norm": 1.2727042436599731, "learning_rate": 2.2538891481109256e-05, "loss": 0.4804062843322754, "step": 470270 }, { "epoch": 2.795441981561068, "grad_norm": 1.496923804283142, "learning_rate": 2.2537423594437722e-05, "loss": 0.5040114402770997, "step": 470280 }, { "epoch": 2.7955014236377362, "grad_norm": 1.2555845975875854, "learning_rate": 2.253595612615856e-05, "loss": 0.44716219902038573, "step": 470290 }, { "epoch": 2.7955608657144047, "grad_norm": 1.412099003791809, "learning_rate": 2.2534489076278802e-05, "loss": 0.49144906997680665, "step": 470300 }, { "epoch": 2.795620307791073, "grad_norm": 1.4281306266784668, "learning_rate": 2.2533022444805474e-05, "loss": 0.46419944763183596, "step": 470310 }, { "epoch": 2.7956797498677415, "grad_norm": 1.181325912475586, "learning_rate": 2.253155623174557e-05, "loss": 0.4640503406524658, "step": 470320 }, { "epoch": 2.79573919194441, "grad_norm": 1.4098761081695557, "learning_rate": 2.2530090437106113e-05, "loss": 0.46201515197753906, "step": 470330 }, { "epoch": 2.7957986340210783, "grad_norm": 1.1989606618881226, "learning_rate": 2.252862506089414e-05, "loss": 0.4400771141052246, "step": 470340 }, { "epoch": 2.7958580760977467, "grad_norm": 1.0822418928146362, "learning_rate": 2.2527160103116623e-05, "loss": 0.4450522899627686, "step": 470350 }, { "epoch": 2.7959175181744147, "grad_norm": 1.3267731666564941, "learning_rate": 2.252569556378058e-05, "loss": 0.43593416213989256, "step": 470360 }, { "epoch": 2.7959769602510836, "grad_norm": 1.3313202857971191, "learning_rate": 2.252423144289303e-05, "loss": 0.42994046211242676, "step": 470370 }, { "epoch": 2.7960364023277515, "grad_norm": 1.604983925819397, "learning_rate": 2.2522767740460973e-05, "loss": 0.47304821014404297, "step": 470380 }, { "epoch": 2.7960958444044204, "grad_norm": 1.0484164953231812, "learning_rate": 2.252130445649141e-05, "loss": 0.47513160705566404, "step": 470390 }, { "epoch": 2.7961552864810884, "grad_norm": 1.378669023513794, "learning_rate": 2.2519841590991333e-05, "loss": 0.4827249050140381, "step": 470400 }, { "epoch": 2.7962147285577568, "grad_norm": 1.3855727910995483, "learning_rate": 2.2518379143967744e-05, "loss": 0.4793240070343018, "step": 470410 }, { "epoch": 2.796274170634425, "grad_norm": 1.5881773233413696, "learning_rate": 2.2516917115427637e-05, "loss": 0.4828636169433594, "step": 470420 }, { "epoch": 2.7963336127110936, "grad_norm": 1.263903260231018, "learning_rate": 2.251545550537801e-05, "loss": 0.4786330223083496, "step": 470430 }, { "epoch": 2.796393054787762, "grad_norm": 0.9800993800163269, "learning_rate": 2.2513994313825855e-05, "loss": 0.46555776596069337, "step": 470440 }, { "epoch": 2.7964524968644304, "grad_norm": 1.326620101928711, "learning_rate": 2.251253354077816e-05, "loss": 0.4660040855407715, "step": 470450 }, { "epoch": 2.796511938941099, "grad_norm": 1.3356797695159912, "learning_rate": 2.2511073186241913e-05, "loss": 0.46898555755615234, "step": 470460 }, { "epoch": 2.7965713810177673, "grad_norm": 1.3394179344177246, "learning_rate": 2.2509613250224105e-05, "loss": 0.43450679779052737, "step": 470470 }, { "epoch": 2.7966308230944357, "grad_norm": 1.3475136756896973, "learning_rate": 2.250815373273171e-05, "loss": 0.4691723346710205, "step": 470480 }, { "epoch": 2.796690265171104, "grad_norm": 1.1659691333770752, "learning_rate": 2.2506694633771718e-05, "loss": 0.43680534362792967, "step": 470490 }, { "epoch": 2.7967497072477725, "grad_norm": 1.5325992107391357, "learning_rate": 2.2505235953351095e-05, "loss": 0.47222251892089845, "step": 470500 }, { "epoch": 2.796809149324441, "grad_norm": 1.2661035060882568, "learning_rate": 2.250377769147684e-05, "loss": 0.49373693466186525, "step": 470510 }, { "epoch": 2.7968685914011093, "grad_norm": 1.0517688989639282, "learning_rate": 2.2502319848155918e-05, "loss": 0.4139974594116211, "step": 470520 }, { "epoch": 2.7969280334777777, "grad_norm": 1.1095041036605835, "learning_rate": 2.250086242339531e-05, "loss": 0.4542823791503906, "step": 470530 }, { "epoch": 2.796987475554446, "grad_norm": 1.0654581785202026, "learning_rate": 2.2499405417201965e-05, "loss": 0.41958045959472656, "step": 470540 }, { "epoch": 2.797046917631114, "grad_norm": 1.2570816278457642, "learning_rate": 2.2497948829582888e-05, "loss": 0.4654015064239502, "step": 470550 }, { "epoch": 2.797106359707783, "grad_norm": 1.1287091970443726, "learning_rate": 2.249649266054501e-05, "loss": 0.43613805770874026, "step": 470560 }, { "epoch": 2.797165801784451, "grad_norm": 1.2258206605911255, "learning_rate": 2.2495036910095322e-05, "loss": 0.47782435417175295, "step": 470570 }, { "epoch": 2.7972252438611194, "grad_norm": 1.578074336051941, "learning_rate": 2.2493581578240783e-05, "loss": 0.4336691856384277, "step": 470580 }, { "epoch": 2.797284685937788, "grad_norm": 1.1139048337936401, "learning_rate": 2.249212666498835e-05, "loss": 0.45148067474365233, "step": 470590 }, { "epoch": 2.797344128014456, "grad_norm": 1.3370968103408813, "learning_rate": 2.249067217034498e-05, "loss": 0.44711666107177733, "step": 470600 }, { "epoch": 2.7974035700911246, "grad_norm": 1.2611560821533203, "learning_rate": 2.2489218094317645e-05, "loss": 0.4381659507751465, "step": 470610 }, { "epoch": 2.797463012167793, "grad_norm": 1.3862191438674927, "learning_rate": 2.248776443691328e-05, "loss": 0.43663315773010253, "step": 470620 }, { "epoch": 2.7975224542444614, "grad_norm": 1.2419066429138184, "learning_rate": 2.248631119813886e-05, "loss": 0.43959388732910154, "step": 470630 }, { "epoch": 2.79758189632113, "grad_norm": 1.355322241783142, "learning_rate": 2.2484858378001328e-05, "loss": 0.4742382049560547, "step": 470640 }, { "epoch": 2.7976413383977983, "grad_norm": 1.474730372428894, "learning_rate": 2.248340597650763e-05, "loss": 0.5017476558685303, "step": 470650 }, { "epoch": 2.7977007804744667, "grad_norm": 1.4648374319076538, "learning_rate": 2.2481953993664715e-05, "loss": 0.47295341491699217, "step": 470660 }, { "epoch": 2.797760222551135, "grad_norm": 1.442266821861267, "learning_rate": 2.2480502429479533e-05, "loss": 0.4549900531768799, "step": 470670 }, { "epoch": 2.7978196646278035, "grad_norm": 1.23094642162323, "learning_rate": 2.2479051283959036e-05, "loss": 0.44239959716796873, "step": 470680 }, { "epoch": 2.797879106704472, "grad_norm": 1.074588656425476, "learning_rate": 2.2477600557110134e-05, "loss": 0.4544830322265625, "step": 470690 }, { "epoch": 2.7979385487811403, "grad_norm": 1.2229984998703003, "learning_rate": 2.2476150248939805e-05, "loss": 0.4222546577453613, "step": 470700 }, { "epoch": 2.7979979908578088, "grad_norm": 1.3782906532287598, "learning_rate": 2.2474700359454972e-05, "loss": 0.4688267230987549, "step": 470710 }, { "epoch": 2.7980574329344767, "grad_norm": 1.2547557353973389, "learning_rate": 2.247325088866255e-05, "loss": 0.4415476322174072, "step": 470720 }, { "epoch": 2.7981168750111456, "grad_norm": 1.6971254348754883, "learning_rate": 2.2471801836569505e-05, "loss": 0.45621557235717775, "step": 470730 }, { "epoch": 2.7981763170878136, "grad_norm": 1.05902099609375, "learning_rate": 2.247035320318276e-05, "loss": 0.45431013107299806, "step": 470740 }, { "epoch": 2.7982357591644824, "grad_norm": 0.7221221327781677, "learning_rate": 2.2468904988509227e-05, "loss": 0.43624305725097656, "step": 470750 }, { "epoch": 2.7982952012411504, "grad_norm": 1.4659587144851685, "learning_rate": 2.246745719255585e-05, "loss": 0.47673635482788085, "step": 470760 }, { "epoch": 2.798354643317819, "grad_norm": 1.284135103225708, "learning_rate": 2.246600981532957e-05, "loss": 0.48166751861572266, "step": 470770 }, { "epoch": 2.798414085394487, "grad_norm": 1.4381160736083984, "learning_rate": 2.2464562856837277e-05, "loss": 0.463514518737793, "step": 470780 }, { "epoch": 2.7984735274711556, "grad_norm": 1.308848261833191, "learning_rate": 2.2463116317085902e-05, "loss": 0.4889217376708984, "step": 470790 }, { "epoch": 2.798532969547824, "grad_norm": 1.0786159038543701, "learning_rate": 2.2461670196082388e-05, "loss": 0.42588138580322266, "step": 470800 }, { "epoch": 2.7985924116244925, "grad_norm": 1.7761156558990479, "learning_rate": 2.2460224493833623e-05, "loss": 0.4508814334869385, "step": 470810 }, { "epoch": 2.798651853701161, "grad_norm": 1.2732418775558472, "learning_rate": 2.2458779210346533e-05, "loss": 0.45102882385253906, "step": 470820 }, { "epoch": 2.7987112957778293, "grad_norm": 1.6233997344970703, "learning_rate": 2.2457334345628056e-05, "loss": 0.5274233818054199, "step": 470830 }, { "epoch": 2.7987707378544977, "grad_norm": 1.1108016967773438, "learning_rate": 2.245588989968507e-05, "loss": 0.4263725280761719, "step": 470840 }, { "epoch": 2.798830179931166, "grad_norm": 1.564813494682312, "learning_rate": 2.245444587252448e-05, "loss": 0.45392637252807616, "step": 470850 }, { "epoch": 2.7988896220078345, "grad_norm": 1.4052304029464722, "learning_rate": 2.245300226415323e-05, "loss": 0.4339917659759521, "step": 470860 }, { "epoch": 2.798949064084503, "grad_norm": 1.2620089054107666, "learning_rate": 2.2451559074578203e-05, "loss": 0.491484546661377, "step": 470870 }, { "epoch": 2.7990085061611714, "grad_norm": 1.3618491888046265, "learning_rate": 2.24501163038063e-05, "loss": 0.39789087772369386, "step": 470880 }, { "epoch": 2.7990679482378398, "grad_norm": 1.3865439891815186, "learning_rate": 2.2448673951844445e-05, "loss": 0.48455357551574707, "step": 470890 }, { "epoch": 2.799127390314508, "grad_norm": 1.3052736520767212, "learning_rate": 2.2447232018699518e-05, "loss": 0.482133674621582, "step": 470900 }, { "epoch": 2.799186832391176, "grad_norm": 1.639840841293335, "learning_rate": 2.244579050437841e-05, "loss": 0.45838313102722167, "step": 470910 }, { "epoch": 2.799246274467845, "grad_norm": 1.7712305784225464, "learning_rate": 2.244434940888803e-05, "loss": 0.492763614654541, "step": 470920 }, { "epoch": 2.799305716544513, "grad_norm": 1.453423023223877, "learning_rate": 2.2442908732235263e-05, "loss": 0.4989602088928223, "step": 470930 }, { "epoch": 2.799365158621182, "grad_norm": 1.3427187204360962, "learning_rate": 2.2441468474427017e-05, "loss": 0.4255516529083252, "step": 470940 }, { "epoch": 2.79942460069785, "grad_norm": 1.25435209274292, "learning_rate": 2.2440028635470164e-05, "loss": 0.45432543754577637, "step": 470950 }, { "epoch": 2.7994840427745182, "grad_norm": 1.8527376651763916, "learning_rate": 2.243858921537161e-05, "loss": 0.5209915161132812, "step": 470960 }, { "epoch": 2.7995434848511866, "grad_norm": 1.1899890899658203, "learning_rate": 2.243715021413822e-05, "loss": 0.4261810302734375, "step": 470970 }, { "epoch": 2.799602926927855, "grad_norm": 1.4872034788131714, "learning_rate": 2.2435711631776884e-05, "loss": 0.4381218433380127, "step": 470980 }, { "epoch": 2.7996623690045235, "grad_norm": 1.4284639358520508, "learning_rate": 2.24342734682945e-05, "loss": 0.441161584854126, "step": 470990 }, { "epoch": 2.799721811081192, "grad_norm": 1.512221336364746, "learning_rate": 2.2432835723697922e-05, "loss": 0.4082615375518799, "step": 471000 }, { "epoch": 2.7997812531578603, "grad_norm": 1.140994906425476, "learning_rate": 2.2431398397994054e-05, "loss": 0.45914506912231445, "step": 471010 }, { "epoch": 2.7998406952345287, "grad_norm": 1.306776523590088, "learning_rate": 2.2429961491189755e-05, "loss": 0.48295116424560547, "step": 471020 }, { "epoch": 2.799900137311197, "grad_norm": 1.4314875602722168, "learning_rate": 2.242852500329189e-05, "loss": 0.4968844413757324, "step": 471030 }, { "epoch": 2.7999595793878655, "grad_norm": 1.6000431776046753, "learning_rate": 2.2427088934307354e-05, "loss": 0.4571988582611084, "step": 471040 }, { "epoch": 2.800019021464534, "grad_norm": 1.4461255073547363, "learning_rate": 2.2425653284242992e-05, "loss": 0.4591175079345703, "step": 471050 }, { "epoch": 2.8000784635412024, "grad_norm": 1.2093623876571655, "learning_rate": 2.2424218053105707e-05, "loss": 0.4448277473449707, "step": 471060 }, { "epoch": 2.800137905617871, "grad_norm": 1.0549529790878296, "learning_rate": 2.2422783240902328e-05, "loss": 0.4182907581329346, "step": 471070 }, { "epoch": 2.800197347694539, "grad_norm": 1.2126405239105225, "learning_rate": 2.242134884763974e-05, "loss": 0.4659290313720703, "step": 471080 }, { "epoch": 2.8002567897712076, "grad_norm": 1.040053129196167, "learning_rate": 2.241991487332479e-05, "loss": 0.464578914642334, "step": 471090 }, { "epoch": 2.8003162318478756, "grad_norm": 1.3162363767623901, "learning_rate": 2.241848131796436e-05, "loss": 0.478516960144043, "step": 471100 }, { "epoch": 2.8003756739245445, "grad_norm": 1.431723713874817, "learning_rate": 2.2417048181565277e-05, "loss": 0.42921009063720705, "step": 471110 }, { "epoch": 2.8004351160012124, "grad_norm": 1.5253665447235107, "learning_rate": 2.241561546413441e-05, "loss": 0.43436613082885744, "step": 471120 }, { "epoch": 2.8004945580778813, "grad_norm": 1.4214955568313599, "learning_rate": 2.2414183165678635e-05, "loss": 0.5128917217254638, "step": 471130 }, { "epoch": 2.8005540001545493, "grad_norm": 1.0713918209075928, "learning_rate": 2.2412751286204775e-05, "loss": 0.44083585739135744, "step": 471140 }, { "epoch": 2.8006134422312177, "grad_norm": 1.1497339010238647, "learning_rate": 2.2411319825719686e-05, "loss": 0.4707972526550293, "step": 471150 }, { "epoch": 2.800672884307886, "grad_norm": 1.2576946020126343, "learning_rate": 2.240988878423023e-05, "loss": 0.43666276931762693, "step": 471160 }, { "epoch": 2.8007323263845545, "grad_norm": 1.4334676265716553, "learning_rate": 2.2408458161743234e-05, "loss": 0.4333950519561768, "step": 471170 }, { "epoch": 2.800791768461223, "grad_norm": 1.3803730010986328, "learning_rate": 2.2407027958265535e-05, "loss": 0.4665987014770508, "step": 471180 }, { "epoch": 2.8008512105378913, "grad_norm": 1.5880545377731323, "learning_rate": 2.240559817380401e-05, "loss": 0.46860756874084475, "step": 471190 }, { "epoch": 2.8009106526145597, "grad_norm": 1.5588021278381348, "learning_rate": 2.240416880836547e-05, "loss": 0.475941801071167, "step": 471200 }, { "epoch": 2.800970094691228, "grad_norm": 1.4315366744995117, "learning_rate": 2.240273986195675e-05, "loss": 0.4193584442138672, "step": 471210 }, { "epoch": 2.8010295367678966, "grad_norm": 1.028608798980713, "learning_rate": 2.2401311334584708e-05, "loss": 0.4231398582458496, "step": 471220 }, { "epoch": 2.801088978844565, "grad_norm": 1.194049596786499, "learning_rate": 2.2399883226256163e-05, "loss": 0.4296416759490967, "step": 471230 }, { "epoch": 2.8011484209212334, "grad_norm": 1.5359234809875488, "learning_rate": 2.2398455536977946e-05, "loss": 0.5122269630432129, "step": 471240 }, { "epoch": 2.801207862997902, "grad_norm": 1.1966546773910522, "learning_rate": 2.2397028266756885e-05, "loss": 0.45803060531616213, "step": 471250 }, { "epoch": 2.8012673050745702, "grad_norm": 1.843504786491394, "learning_rate": 2.2395601415599825e-05, "loss": 0.4726411819458008, "step": 471260 }, { "epoch": 2.8013267471512386, "grad_norm": 1.2675195932388306, "learning_rate": 2.2394174983513576e-05, "loss": 0.4849421501159668, "step": 471270 }, { "epoch": 2.801386189227907, "grad_norm": 1.1899362802505493, "learning_rate": 2.239274897050495e-05, "loss": 0.4519341945648193, "step": 471280 }, { "epoch": 2.801445631304575, "grad_norm": 1.315273404121399, "learning_rate": 2.2391323376580792e-05, "loss": 0.44084782600402833, "step": 471290 }, { "epoch": 2.801505073381244, "grad_norm": 1.3216869831085205, "learning_rate": 2.2389898201747915e-05, "loss": 0.45964345932006834, "step": 471300 }, { "epoch": 2.801564515457912, "grad_norm": 1.6357163190841675, "learning_rate": 2.2388473446013113e-05, "loss": 0.4900506019592285, "step": 471310 }, { "epoch": 2.8016239575345803, "grad_norm": 1.5202465057373047, "learning_rate": 2.238704910938325e-05, "loss": 0.45611772537231443, "step": 471320 }, { "epoch": 2.8016833996112487, "grad_norm": 1.1789045333862305, "learning_rate": 2.2385625191865105e-05, "loss": 0.4582625389099121, "step": 471330 }, { "epoch": 2.801742841687917, "grad_norm": 1.2205053567886353, "learning_rate": 2.2384201693465482e-05, "loss": 0.47457475662231446, "step": 471340 }, { "epoch": 2.8018022837645855, "grad_norm": 1.319712519645691, "learning_rate": 2.2382778614191222e-05, "loss": 0.5187761306762695, "step": 471350 }, { "epoch": 2.801861725841254, "grad_norm": 1.1457300186157227, "learning_rate": 2.2381355954049098e-05, "loss": 0.43840560913085935, "step": 471360 }, { "epoch": 2.8019211679179223, "grad_norm": 1.6292192935943604, "learning_rate": 2.237993371304594e-05, "loss": 0.467623233795166, "step": 471370 }, { "epoch": 2.8019806099945908, "grad_norm": 1.223162293434143, "learning_rate": 2.237851189118856e-05, "loss": 0.46376981735229494, "step": 471380 }, { "epoch": 2.802040052071259, "grad_norm": 1.505598545074463, "learning_rate": 2.237709048848373e-05, "loss": 0.5075032234191894, "step": 471390 }, { "epoch": 2.8020994941479276, "grad_norm": 1.3888839483261108, "learning_rate": 2.2375669504938273e-05, "loss": 0.42008113861083984, "step": 471400 }, { "epoch": 2.802158936224596, "grad_norm": 1.1853233575820923, "learning_rate": 2.2374248940558952e-05, "loss": 0.43923773765563967, "step": 471410 }, { "epoch": 2.8022183783012644, "grad_norm": 1.4403470754623413, "learning_rate": 2.237282879535261e-05, "loss": 0.5545259475708008, "step": 471420 }, { "epoch": 2.802277820377933, "grad_norm": 1.4507529735565186, "learning_rate": 2.237140906932602e-05, "loss": 0.45713157653808595, "step": 471430 }, { "epoch": 2.8023372624546012, "grad_norm": 1.1507824659347534, "learning_rate": 2.2369989762485965e-05, "loss": 0.4691028118133545, "step": 471440 }, { "epoch": 2.8023967045312697, "grad_norm": 1.1742713451385498, "learning_rate": 2.236857087483924e-05, "loss": 0.4443188190460205, "step": 471450 }, { "epoch": 2.8024561466079376, "grad_norm": 1.3248449563980103, "learning_rate": 2.236715240639264e-05, "loss": 0.47010002136230467, "step": 471460 }, { "epoch": 2.8025155886846065, "grad_norm": 1.5651718378067017, "learning_rate": 2.2365734357152928e-05, "loss": 0.4642343521118164, "step": 471470 }, { "epoch": 2.8025750307612745, "grad_norm": 1.1900392770767212, "learning_rate": 2.2364316727126915e-05, "loss": 0.4286206245422363, "step": 471480 }, { "epoch": 2.8026344728379433, "grad_norm": 1.423234224319458, "learning_rate": 2.2362899516321377e-05, "loss": 0.4384283542633057, "step": 471490 }, { "epoch": 2.8026939149146113, "grad_norm": 1.1830384731292725, "learning_rate": 2.236148272474308e-05, "loss": 0.5251243591308594, "step": 471500 }, { "epoch": 2.8027533569912797, "grad_norm": 1.531887173652649, "learning_rate": 2.236006635239881e-05, "loss": 0.49303011894226073, "step": 471510 }, { "epoch": 2.802812799067948, "grad_norm": 1.5809361934661865, "learning_rate": 2.2358650399295346e-05, "loss": 0.4892261028289795, "step": 471520 }, { "epoch": 2.8028722411446165, "grad_norm": 1.0191136598587036, "learning_rate": 2.2357234865439454e-05, "loss": 0.44564237594604494, "step": 471530 }, { "epoch": 2.802931683221285, "grad_norm": 1.3005576133728027, "learning_rate": 2.2355819750837905e-05, "loss": 0.45396761894226073, "step": 471540 }, { "epoch": 2.8029911252979534, "grad_norm": 1.1976284980773926, "learning_rate": 2.2354405055497468e-05, "loss": 0.4292795181274414, "step": 471550 }, { "epoch": 2.8030505673746218, "grad_norm": 1.3513356447219849, "learning_rate": 2.2352990779424926e-05, "loss": 0.4960108757019043, "step": 471560 }, { "epoch": 2.80311000945129, "grad_norm": 1.5337694883346558, "learning_rate": 2.2351576922627025e-05, "loss": 0.4555633544921875, "step": 471570 }, { "epoch": 2.8031694515279586, "grad_norm": 1.269897699356079, "learning_rate": 2.2350163485110538e-05, "loss": 0.41411590576171875, "step": 471580 }, { "epoch": 2.803228893604627, "grad_norm": 1.424970030784607, "learning_rate": 2.2348750466882225e-05, "loss": 0.46176986694335936, "step": 471590 }, { "epoch": 2.8032883356812954, "grad_norm": 1.288147211074829, "learning_rate": 2.234733786794884e-05, "loss": 0.44301886558532716, "step": 471600 }, { "epoch": 2.803347777757964, "grad_norm": 1.2486255168914795, "learning_rate": 2.2345925688317158e-05, "loss": 0.4778045654296875, "step": 471610 }, { "epoch": 2.8034072198346323, "grad_norm": 1.2666668891906738, "learning_rate": 2.2344513927993913e-05, "loss": 0.48889894485473634, "step": 471620 }, { "epoch": 2.8034666619113007, "grad_norm": 1.0682176351547241, "learning_rate": 2.234310258698587e-05, "loss": 0.512139368057251, "step": 471630 }, { "epoch": 2.803526103987969, "grad_norm": 1.463890790939331, "learning_rate": 2.2341691665299774e-05, "loss": 0.5017507553100586, "step": 471640 }, { "epoch": 2.803585546064637, "grad_norm": 1.2428869009017944, "learning_rate": 2.2340281162942385e-05, "loss": 0.4355755805969238, "step": 471650 }, { "epoch": 2.803644988141306, "grad_norm": 1.3368815183639526, "learning_rate": 2.2338871079920436e-05, "loss": 0.46080217361450193, "step": 471660 }, { "epoch": 2.803704430217974, "grad_norm": 1.7472769021987915, "learning_rate": 2.2337461416240678e-05, "loss": 0.42298574447631837, "step": 471670 }, { "epoch": 2.8037638722946427, "grad_norm": 1.234466552734375, "learning_rate": 2.233605217190986e-05, "loss": 0.442076587677002, "step": 471680 }, { "epoch": 2.8038233143713107, "grad_norm": 1.510370135307312, "learning_rate": 2.233464334693472e-05, "loss": 0.51230788230896, "step": 471690 }, { "epoch": 2.803882756447979, "grad_norm": 1.3663803339004517, "learning_rate": 2.2333234941322007e-05, "loss": 0.4660176753997803, "step": 471700 }, { "epoch": 2.8039421985246475, "grad_norm": 1.326960563659668, "learning_rate": 2.233182695507843e-05, "loss": 0.4987764358520508, "step": 471710 }, { "epoch": 2.804001640601316, "grad_norm": 1.3830434083938599, "learning_rate": 2.233041938821076e-05, "loss": 0.4722696304321289, "step": 471720 }, { "epoch": 2.8040610826779844, "grad_norm": 1.5642777681350708, "learning_rate": 2.2329012240725695e-05, "loss": 0.5233494281768799, "step": 471730 }, { "epoch": 2.804120524754653, "grad_norm": 1.2994495630264282, "learning_rate": 2.2327605512629994e-05, "loss": 0.4665335178375244, "step": 471740 }, { "epoch": 2.804179966831321, "grad_norm": 1.3519173860549927, "learning_rate": 2.2326199203930386e-05, "loss": 0.49025907516479494, "step": 471750 }, { "epoch": 2.8042394089079896, "grad_norm": 1.4154434204101562, "learning_rate": 2.2324793314633574e-05, "loss": 0.5016526699066162, "step": 471760 }, { "epoch": 2.804298850984658, "grad_norm": 1.1823333501815796, "learning_rate": 2.2323387844746302e-05, "loss": 0.46529221534729004, "step": 471770 }, { "epoch": 2.8043582930613264, "grad_norm": 1.2229039669036865, "learning_rate": 2.232198279427529e-05, "loss": 0.4301889419555664, "step": 471780 }, { "epoch": 2.804417735137995, "grad_norm": 1.531212568283081, "learning_rate": 2.2320578163227258e-05, "loss": 0.4995570182800293, "step": 471790 }, { "epoch": 2.8044771772146633, "grad_norm": 1.0230274200439453, "learning_rate": 2.2319173951608923e-05, "loss": 0.43972291946411135, "step": 471800 }, { "epoch": 2.8045366192913317, "grad_norm": 1.1624090671539307, "learning_rate": 2.2317770159427016e-05, "loss": 0.4954981803894043, "step": 471810 }, { "epoch": 2.804596061368, "grad_norm": 1.4221844673156738, "learning_rate": 2.231636678668824e-05, "loss": 0.4559628486633301, "step": 471820 }, { "epoch": 2.8046555034446685, "grad_norm": 1.4817692041397095, "learning_rate": 2.2314963833399296e-05, "loss": 0.48011074066162107, "step": 471830 }, { "epoch": 2.8047149455213365, "grad_norm": 1.6025390625, "learning_rate": 2.2313561299566913e-05, "loss": 0.46345205307006837, "step": 471840 }, { "epoch": 2.8047743875980053, "grad_norm": 1.2121572494506836, "learning_rate": 2.2312159185197805e-05, "loss": 0.41785593032836915, "step": 471850 }, { "epoch": 2.8048338296746733, "grad_norm": 1.2418984174728394, "learning_rate": 2.2310757490298664e-05, "loss": 0.5095203399658204, "step": 471860 }, { "epoch": 2.804893271751342, "grad_norm": 1.221982479095459, "learning_rate": 2.230935621487622e-05, "loss": 0.4847381591796875, "step": 471870 }, { "epoch": 2.80495271382801, "grad_norm": 1.2233974933624268, "learning_rate": 2.2307955358937138e-05, "loss": 0.4348575592041016, "step": 471880 }, { "epoch": 2.8050121559046786, "grad_norm": 1.3784719705581665, "learning_rate": 2.230655492248815e-05, "loss": 0.46915268898010254, "step": 471890 }, { "epoch": 2.805071597981347, "grad_norm": 1.379271149635315, "learning_rate": 2.2305154905535933e-05, "loss": 0.44193272590637206, "step": 471900 }, { "epoch": 2.8051310400580154, "grad_norm": 1.3077960014343262, "learning_rate": 2.2303755308087206e-05, "loss": 0.5024869918823243, "step": 471910 }, { "epoch": 2.805190482134684, "grad_norm": 1.62344229221344, "learning_rate": 2.2302356130148647e-05, "loss": 0.5044511318206787, "step": 471920 }, { "epoch": 2.805249924211352, "grad_norm": 1.3777390718460083, "learning_rate": 2.2300957371726966e-05, "loss": 0.4817205429077148, "step": 471930 }, { "epoch": 2.8053093662880206, "grad_norm": 1.404577374458313, "learning_rate": 2.2299559032828836e-05, "loss": 0.4767942428588867, "step": 471940 }, { "epoch": 2.805368808364689, "grad_norm": 1.1136006116867065, "learning_rate": 2.229816111346096e-05, "loss": 0.4794939994812012, "step": 471950 }, { "epoch": 2.8054282504413575, "grad_norm": 1.2319538593292236, "learning_rate": 2.2296763613630015e-05, "loss": 0.4914987087249756, "step": 471960 }, { "epoch": 2.805487692518026, "grad_norm": 1.4706364870071411, "learning_rate": 2.2295366533342695e-05, "loss": 0.4185230255126953, "step": 471970 }, { "epoch": 2.8055471345946943, "grad_norm": 1.2320542335510254, "learning_rate": 2.2293969872605674e-05, "loss": 0.47289175987243653, "step": 471980 }, { "epoch": 2.8056065766713627, "grad_norm": 1.2563385963439941, "learning_rate": 2.229257363142565e-05, "loss": 0.4699345588684082, "step": 471990 }, { "epoch": 2.805666018748031, "grad_norm": 0.9758999943733215, "learning_rate": 2.229117780980928e-05, "loss": 0.4260589122772217, "step": 472000 }, { "epoch": 2.8057254608246995, "grad_norm": 1.1288363933563232, "learning_rate": 2.228978240776326e-05, "loss": 0.4589405059814453, "step": 472010 }, { "epoch": 2.805784902901368, "grad_norm": 1.4588474035263062, "learning_rate": 2.228838742529425e-05, "loss": 0.42476234436035154, "step": 472020 }, { "epoch": 2.805844344978036, "grad_norm": 1.1106220483779907, "learning_rate": 2.228699286240893e-05, "loss": 0.43547840118408204, "step": 472030 }, { "epoch": 2.805903787054705, "grad_norm": 1.5120885372161865, "learning_rate": 2.228559871911397e-05, "loss": 0.5277227878570556, "step": 472040 }, { "epoch": 2.8059632291313727, "grad_norm": 1.912615418434143, "learning_rate": 2.228420499541605e-05, "loss": 0.515934944152832, "step": 472050 }, { "epoch": 2.806022671208041, "grad_norm": 1.2706634998321533, "learning_rate": 2.228281169132182e-05, "loss": 0.46550979614257815, "step": 472060 }, { "epoch": 2.8060821132847096, "grad_norm": 1.4967767000198364, "learning_rate": 2.2281418806837957e-05, "loss": 0.4604331016540527, "step": 472070 }, { "epoch": 2.806141555361378, "grad_norm": 1.3245798349380493, "learning_rate": 2.2280026341971116e-05, "loss": 0.4462278842926025, "step": 472080 }, { "epoch": 2.8062009974380464, "grad_norm": 1.2118477821350098, "learning_rate": 2.2278634296727947e-05, "loss": 0.4452934741973877, "step": 472090 }, { "epoch": 2.806260439514715, "grad_norm": 1.3282699584960938, "learning_rate": 2.2277242671115143e-05, "loss": 0.47875776290893557, "step": 472100 }, { "epoch": 2.8063198815913832, "grad_norm": 1.5927298069000244, "learning_rate": 2.2275851465139345e-05, "loss": 0.5007708549499512, "step": 472110 }, { "epoch": 2.8063793236680517, "grad_norm": 1.3332233428955078, "learning_rate": 2.2274460678807195e-05, "loss": 0.4648092746734619, "step": 472120 }, { "epoch": 2.80643876574472, "grad_norm": 1.6101933717727661, "learning_rate": 2.2273070312125366e-05, "loss": 0.4230513572692871, "step": 472130 }, { "epoch": 2.8064982078213885, "grad_norm": 1.3396660089492798, "learning_rate": 2.2271680365100488e-05, "loss": 0.43094692230224607, "step": 472140 }, { "epoch": 2.806557649898057, "grad_norm": 0.9103192090988159, "learning_rate": 2.2270290837739226e-05, "loss": 0.4867689609527588, "step": 472150 }, { "epoch": 2.8066170919747253, "grad_norm": 1.185390830039978, "learning_rate": 2.2268901730048223e-05, "loss": 0.49335536956787107, "step": 472160 }, { "epoch": 2.8066765340513937, "grad_norm": 1.5977702140808105, "learning_rate": 2.226751304203412e-05, "loss": 0.4227640628814697, "step": 472170 }, { "epoch": 2.806735976128062, "grad_norm": 1.2631429433822632, "learning_rate": 2.2266124773703566e-05, "loss": 0.4542860984802246, "step": 472180 }, { "epoch": 2.8067954182047306, "grad_norm": 1.6443313360214233, "learning_rate": 2.2264736925063197e-05, "loss": 0.48465638160705565, "step": 472190 }, { "epoch": 2.8068548602813985, "grad_norm": 0.8752305507659912, "learning_rate": 2.2263349496119664e-05, "loss": 0.3995331287384033, "step": 472200 }, { "epoch": 2.8069143023580674, "grad_norm": 1.365945816040039, "learning_rate": 2.2261962486879584e-05, "loss": 0.489106273651123, "step": 472210 }, { "epoch": 2.8069737444347354, "grad_norm": 1.1759700775146484, "learning_rate": 2.2260575897349598e-05, "loss": 0.47344970703125, "step": 472220 }, { "epoch": 2.807033186511404, "grad_norm": 1.3682382106781006, "learning_rate": 2.2259189727536356e-05, "loss": 0.44620285034179685, "step": 472230 }, { "epoch": 2.807092628588072, "grad_norm": 1.343940019607544, "learning_rate": 2.2257803977446467e-05, "loss": 0.47971601486206056, "step": 472240 }, { "epoch": 2.8071520706647406, "grad_norm": 1.225555181503296, "learning_rate": 2.225641864708658e-05, "loss": 0.4412355422973633, "step": 472250 }, { "epoch": 2.807211512741409, "grad_norm": 1.4708194732666016, "learning_rate": 2.22550337364633e-05, "loss": 0.4266076564788818, "step": 472260 }, { "epoch": 2.8072709548180774, "grad_norm": 1.5252691507339478, "learning_rate": 2.2253649245583268e-05, "loss": 0.47914786338806153, "step": 472270 }, { "epoch": 2.807330396894746, "grad_norm": 1.3444114923477173, "learning_rate": 2.22522651744531e-05, "loss": 0.44322052001953127, "step": 472280 }, { "epoch": 2.8073898389714143, "grad_norm": 1.1873892545700073, "learning_rate": 2.225088152307942e-05, "loss": 0.45423126220703125, "step": 472290 }, { "epoch": 2.8074492810480827, "grad_norm": 1.305418610572815, "learning_rate": 2.2249498291468847e-05, "loss": 0.45843234062194826, "step": 472300 }, { "epoch": 2.807508723124751, "grad_norm": 1.564786434173584, "learning_rate": 2.2248115479628e-05, "loss": 0.45416765213012694, "step": 472310 }, { "epoch": 2.8075681652014195, "grad_norm": 1.2234933376312256, "learning_rate": 2.2246733087563483e-05, "loss": 0.48218188285827634, "step": 472320 }, { "epoch": 2.807627607278088, "grad_norm": 1.3339945077896118, "learning_rate": 2.224535111528192e-05, "loss": 0.4801762580871582, "step": 472330 }, { "epoch": 2.8076870493547563, "grad_norm": 1.1176562309265137, "learning_rate": 2.2243969562789925e-05, "loss": 0.4928534507751465, "step": 472340 }, { "epoch": 2.8077464914314247, "grad_norm": 1.2780524492263794, "learning_rate": 2.2242588430094084e-05, "loss": 0.48627219200134275, "step": 472350 }, { "epoch": 2.807805933508093, "grad_norm": 1.3271067142486572, "learning_rate": 2.2241207717201034e-05, "loss": 0.4164441108703613, "step": 472360 }, { "epoch": 2.8078653755847616, "grad_norm": 1.5116305351257324, "learning_rate": 2.2239827424117373e-05, "loss": 0.46232175827026367, "step": 472370 }, { "epoch": 2.80792481766143, "grad_norm": 1.4640464782714844, "learning_rate": 2.2238447550849695e-05, "loss": 0.43486576080322265, "step": 472380 }, { "epoch": 2.807984259738098, "grad_norm": 1.231554388999939, "learning_rate": 2.2237068097404584e-05, "loss": 0.4763349056243896, "step": 472390 }, { "epoch": 2.808043701814767, "grad_norm": 1.275113582611084, "learning_rate": 2.2235689063788673e-05, "loss": 0.5121289730072022, "step": 472400 }, { "epoch": 2.808103143891435, "grad_norm": 0.9538511633872986, "learning_rate": 2.223431045000855e-05, "loss": 0.41047396659851076, "step": 472410 }, { "epoch": 2.8081625859681036, "grad_norm": 1.7498914003372192, "learning_rate": 2.2232932256070795e-05, "loss": 0.46932244300842285, "step": 472420 }, { "epoch": 2.8082220280447716, "grad_norm": 1.6388012170791626, "learning_rate": 2.2231554481982008e-05, "loss": 0.4402772426605225, "step": 472430 }, { "epoch": 2.80828147012144, "grad_norm": 1.4683449268341064, "learning_rate": 2.223017712774879e-05, "loss": 0.408493709564209, "step": 472440 }, { "epoch": 2.8083409121981084, "grad_norm": 1.2643368244171143, "learning_rate": 2.22288001933777e-05, "loss": 0.463879919052124, "step": 472450 }, { "epoch": 2.808400354274777, "grad_norm": 1.209330677986145, "learning_rate": 2.222742367887537e-05, "loss": 0.48971214294433596, "step": 472460 }, { "epoch": 2.8084597963514453, "grad_norm": 1.3739821910858154, "learning_rate": 2.222604758424835e-05, "loss": 0.4669647693634033, "step": 472470 }, { "epoch": 2.8085192384281137, "grad_norm": 1.3234695196151733, "learning_rate": 2.222467190950323e-05, "loss": 0.4348598957061768, "step": 472480 }, { "epoch": 2.808578680504782, "grad_norm": 1.5060091018676758, "learning_rate": 2.2223296654646605e-05, "loss": 0.4986092567443848, "step": 472490 }, { "epoch": 2.8086381225814505, "grad_norm": 1.3271507024765015, "learning_rate": 2.2221921819685037e-05, "loss": 0.4389315605163574, "step": 472500 }, { "epoch": 2.808697564658119, "grad_norm": 1.331689476966858, "learning_rate": 2.2220547404625105e-05, "loss": 0.4790738582611084, "step": 472510 }, { "epoch": 2.8087570067347873, "grad_norm": 1.0393177270889282, "learning_rate": 2.2219173409473394e-05, "loss": 0.43734130859375, "step": 472520 }, { "epoch": 2.8088164488114558, "grad_norm": 1.0254814624786377, "learning_rate": 2.221779983423646e-05, "loss": 0.4816867828369141, "step": 472530 }, { "epoch": 2.808875890888124, "grad_norm": 1.1934744119644165, "learning_rate": 2.2216426678920896e-05, "loss": 0.470224666595459, "step": 472540 }, { "epoch": 2.8089353329647926, "grad_norm": 1.587592601776123, "learning_rate": 2.2215053943533254e-05, "loss": 0.48061313629150393, "step": 472550 }, { "epoch": 2.808994775041461, "grad_norm": 1.6891361474990845, "learning_rate": 2.221368162808011e-05, "loss": 0.5116312026977539, "step": 472560 }, { "epoch": 2.8090542171181294, "grad_norm": 1.2383949756622314, "learning_rate": 2.2212309732568017e-05, "loss": 0.4759495735168457, "step": 472570 }, { "epoch": 2.8091136591947974, "grad_norm": 1.6861708164215088, "learning_rate": 2.2210938257003544e-05, "loss": 0.4204148292541504, "step": 472580 }, { "epoch": 2.8091731012714662, "grad_norm": 1.3004658222198486, "learning_rate": 2.220956720139326e-05, "loss": 0.44638772010803224, "step": 472590 }, { "epoch": 2.809232543348134, "grad_norm": 1.0473071336746216, "learning_rate": 2.220819656574371e-05, "loss": 0.45492939949035643, "step": 472600 }, { "epoch": 2.809291985424803, "grad_norm": 1.658409833908081, "learning_rate": 2.2206826350061465e-05, "loss": 0.49204444885253906, "step": 472610 }, { "epoch": 2.809351427501471, "grad_norm": 1.154603123664856, "learning_rate": 2.2205456554353065e-05, "loss": 0.40590810775756836, "step": 472620 }, { "epoch": 2.8094108695781395, "grad_norm": 1.4856396913528442, "learning_rate": 2.220408717862507e-05, "loss": 0.46313915252685545, "step": 472630 }, { "epoch": 2.809470311654808, "grad_norm": 1.3602840900421143, "learning_rate": 2.2202718222884038e-05, "loss": 0.4523302555084229, "step": 472640 }, { "epoch": 2.8095297537314763, "grad_norm": 1.2517837285995483, "learning_rate": 2.2201349687136492e-05, "loss": 0.4655926704406738, "step": 472650 }, { "epoch": 2.8095891958081447, "grad_norm": 1.2179882526397705, "learning_rate": 2.2199981571389008e-05, "loss": 0.46355504989624025, "step": 472660 }, { "epoch": 2.809648637884813, "grad_norm": 1.2356008291244507, "learning_rate": 2.2198613875648116e-05, "loss": 0.4442293167114258, "step": 472670 }, { "epoch": 2.8097080799614815, "grad_norm": 1.3686368465423584, "learning_rate": 2.2197246599920372e-05, "loss": 0.5254690170288085, "step": 472680 }, { "epoch": 2.80976752203815, "grad_norm": 1.0018656253814697, "learning_rate": 2.2195879744212293e-05, "loss": 0.45371074676513673, "step": 472690 }, { "epoch": 2.8098269641148184, "grad_norm": 1.2925397157669067, "learning_rate": 2.2194513308530438e-05, "loss": 0.44939794540405276, "step": 472700 }, { "epoch": 2.8098864061914868, "grad_norm": 1.2682653665542603, "learning_rate": 2.219314729288132e-05, "loss": 0.4648845672607422, "step": 472710 }, { "epoch": 2.809945848268155, "grad_norm": 1.4054127931594849, "learning_rate": 2.219178169727151e-05, "loss": 0.48473167419433594, "step": 472720 }, { "epoch": 2.8100052903448236, "grad_norm": 1.0496751070022583, "learning_rate": 2.2190416521707505e-05, "loss": 0.4463754653930664, "step": 472730 }, { "epoch": 2.810064732421492, "grad_norm": 1.1108578443527222, "learning_rate": 2.2189051766195873e-05, "loss": 0.4461495399475098, "step": 472740 }, { "epoch": 2.8101241744981604, "grad_norm": 1.428466558456421, "learning_rate": 2.21876874307431e-05, "loss": 0.45676169395446775, "step": 472750 }, { "epoch": 2.810183616574829, "grad_norm": 1.7959786653518677, "learning_rate": 2.218632351535574e-05, "loss": 0.5010976314544677, "step": 472760 }, { "epoch": 2.810243058651497, "grad_norm": 0.9510363936424255, "learning_rate": 2.2184960020040304e-05, "loss": 0.42823076248168945, "step": 472770 }, { "epoch": 2.8103025007281657, "grad_norm": 1.3494760990142822, "learning_rate": 2.2183596944803322e-05, "loss": 0.40793304443359374, "step": 472780 }, { "epoch": 2.8103619428048336, "grad_norm": 1.2484750747680664, "learning_rate": 2.2182234289651318e-05, "loss": 0.4763522148132324, "step": 472790 }, { "epoch": 2.810421384881502, "grad_norm": 1.4305777549743652, "learning_rate": 2.2180872054590816e-05, "loss": 0.4522587299346924, "step": 472800 }, { "epoch": 2.8104808269581705, "grad_norm": 1.3853819370269775, "learning_rate": 2.2179510239628308e-05, "loss": 0.4620415687561035, "step": 472810 }, { "epoch": 2.810540269034839, "grad_norm": 1.383198857307434, "learning_rate": 2.217814884477033e-05, "loss": 0.5146098613739014, "step": 472820 }, { "epoch": 2.8105997111115073, "grad_norm": 1.170617938041687, "learning_rate": 2.217678787002338e-05, "loss": 0.43193769454956055, "step": 472830 }, { "epoch": 2.8106591531881757, "grad_norm": 1.1863279342651367, "learning_rate": 2.217542731539397e-05, "loss": 0.4536905288696289, "step": 472840 }, { "epoch": 2.810718595264844, "grad_norm": 1.7943936586380005, "learning_rate": 2.2174067180888627e-05, "loss": 0.4690235137939453, "step": 472850 }, { "epoch": 2.8107780373415125, "grad_norm": 1.4555599689483643, "learning_rate": 2.2172707466513853e-05, "loss": 0.471530818939209, "step": 472860 }, { "epoch": 2.810837479418181, "grad_norm": 0.8011294603347778, "learning_rate": 2.2171348172276134e-05, "loss": 0.4324751377105713, "step": 472870 }, { "epoch": 2.8108969214948494, "grad_norm": 1.1603851318359375, "learning_rate": 2.2169989298181977e-05, "loss": 0.4784630298614502, "step": 472880 }, { "epoch": 2.810956363571518, "grad_norm": 1.590506672859192, "learning_rate": 2.2168630844237896e-05, "loss": 0.4645075798034668, "step": 472890 }, { "epoch": 2.811015805648186, "grad_norm": 1.2805285453796387, "learning_rate": 2.216727281045038e-05, "loss": 0.4273801803588867, "step": 472900 }, { "epoch": 2.8110752477248546, "grad_norm": 1.4786417484283447, "learning_rate": 2.2165915196825922e-05, "loss": 0.48491582870483396, "step": 472910 }, { "epoch": 2.811134689801523, "grad_norm": 1.3838326930999756, "learning_rate": 2.216455800337103e-05, "loss": 0.41751918792724607, "step": 472920 }, { "epoch": 2.8111941318781914, "grad_norm": 1.3416472673416138, "learning_rate": 2.2163201230092185e-05, "loss": 0.4342978000640869, "step": 472930 }, { "epoch": 2.8112535739548594, "grad_norm": 1.31302011013031, "learning_rate": 2.2161844876995873e-05, "loss": 0.44260368347167967, "step": 472940 }, { "epoch": 2.8113130160315283, "grad_norm": 1.2551162242889404, "learning_rate": 2.216048894408859e-05, "loss": 0.4486283302307129, "step": 472950 }, { "epoch": 2.8113724581081962, "grad_norm": 1.399842619895935, "learning_rate": 2.2159133431376834e-05, "loss": 0.4223177909851074, "step": 472960 }, { "epoch": 2.811431900184865, "grad_norm": 1.4089970588684082, "learning_rate": 2.2157778338867063e-05, "loss": 0.4558969020843506, "step": 472970 }, { "epoch": 2.811491342261533, "grad_norm": 1.0976213216781616, "learning_rate": 2.2156423666565788e-05, "loss": 0.45134906768798827, "step": 472980 }, { "epoch": 2.8115507843382015, "grad_norm": 1.5469508171081543, "learning_rate": 2.2155069414479465e-05, "loss": 0.5048004150390625, "step": 472990 }, { "epoch": 2.81161022641487, "grad_norm": 1.041515827178955, "learning_rate": 2.2153715582614583e-05, "loss": 0.42150263786315917, "step": 473000 }, { "epoch": 2.8116696684915383, "grad_norm": 1.059730052947998, "learning_rate": 2.215236217097761e-05, "loss": 0.44727449417114257, "step": 473010 }, { "epoch": 2.8117291105682067, "grad_norm": 1.6921292543411255, "learning_rate": 2.2151009179575037e-05, "loss": 0.48312973976135254, "step": 473020 }, { "epoch": 2.811788552644875, "grad_norm": 1.3801664113998413, "learning_rate": 2.2149656608413322e-05, "loss": 0.46007518768310546, "step": 473030 }, { "epoch": 2.8118479947215436, "grad_norm": 1.5362054109573364, "learning_rate": 2.2148304457498938e-05, "loss": 0.5100572109222412, "step": 473040 }, { "epoch": 2.811907436798212, "grad_norm": 1.3229693174362183, "learning_rate": 2.2146952726838364e-05, "loss": 0.49710879325866697, "step": 473050 }, { "epoch": 2.8119668788748804, "grad_norm": 1.6394833326339722, "learning_rate": 2.2145601416438046e-05, "loss": 0.502195930480957, "step": 473060 }, { "epoch": 2.812026320951549, "grad_norm": 1.3966755867004395, "learning_rate": 2.214425052630446e-05, "loss": 0.4610757827758789, "step": 473070 }, { "epoch": 2.8120857630282172, "grad_norm": 1.3912205696105957, "learning_rate": 2.214290005644407e-05, "loss": 0.45262737274169923, "step": 473080 }, { "epoch": 2.8121452051048856, "grad_norm": 1.3636572360992432, "learning_rate": 2.2141550006863343e-05, "loss": 0.47341117858886717, "step": 473090 }, { "epoch": 2.812204647181554, "grad_norm": 1.3167892694473267, "learning_rate": 2.2140200377568733e-05, "loss": 0.4408547401428223, "step": 473100 }, { "epoch": 2.8122640892582225, "grad_norm": 1.5700856447219849, "learning_rate": 2.213885116856668e-05, "loss": 0.49826765060424805, "step": 473110 }, { "epoch": 2.812323531334891, "grad_norm": 1.5569484233856201, "learning_rate": 2.2137502379863653e-05, "loss": 0.45500965118408204, "step": 473120 }, { "epoch": 2.812382973411559, "grad_norm": 1.1627867221832275, "learning_rate": 2.21361540114661e-05, "loss": 0.4695915222167969, "step": 473130 }, { "epoch": 2.8124424154882277, "grad_norm": 1.1801687479019165, "learning_rate": 2.2134806063380457e-05, "loss": 0.4508823394775391, "step": 473140 }, { "epoch": 2.8125018575648957, "grad_norm": 1.4933710098266602, "learning_rate": 2.2133458535613206e-05, "loss": 0.49577016830444337, "step": 473150 }, { "epoch": 2.8125612996415645, "grad_norm": 1.2620110511779785, "learning_rate": 2.2132111428170772e-05, "loss": 0.47251310348510744, "step": 473160 }, { "epoch": 2.8126207417182325, "grad_norm": 1.0133607387542725, "learning_rate": 2.2130764741059595e-05, "loss": 0.4864818572998047, "step": 473170 }, { "epoch": 2.812680183794901, "grad_norm": 1.2548961639404297, "learning_rate": 2.2129418474286135e-05, "loss": 0.45223064422607423, "step": 473180 }, { "epoch": 2.8127396258715693, "grad_norm": 0.9195573925971985, "learning_rate": 2.2128072627856812e-05, "loss": 0.4512190341949463, "step": 473190 }, { "epoch": 2.8127990679482378, "grad_norm": 1.4926528930664062, "learning_rate": 2.2126727201778068e-05, "loss": 0.475274658203125, "step": 473200 }, { "epoch": 2.812858510024906, "grad_norm": 1.360945224761963, "learning_rate": 2.2125382196056347e-05, "loss": 0.4630439281463623, "step": 473210 }, { "epoch": 2.8129179521015746, "grad_norm": 1.5448782444000244, "learning_rate": 2.2124037610698085e-05, "loss": 0.4732001304626465, "step": 473220 }, { "epoch": 2.812977394178243, "grad_norm": 1.360776424407959, "learning_rate": 2.2122693445709708e-05, "loss": 0.45447750091552735, "step": 473230 }, { "epoch": 2.8130368362549114, "grad_norm": 1.2659344673156738, "learning_rate": 2.212134970109765e-05, "loss": 0.42866063117980957, "step": 473240 }, { "epoch": 2.81309627833158, "grad_norm": 1.1635092496871948, "learning_rate": 2.2120006376868324e-05, "loss": 0.4296386241912842, "step": 473250 }, { "epoch": 2.8131557204082482, "grad_norm": 1.4269495010375977, "learning_rate": 2.2118663473028176e-05, "loss": 0.4439517974853516, "step": 473260 }, { "epoch": 2.8132151624849167, "grad_norm": 1.194059133529663, "learning_rate": 2.2117320989583616e-05, "loss": 0.48886518478393554, "step": 473270 }, { "epoch": 2.813274604561585, "grad_norm": 1.1181360483169556, "learning_rate": 2.2115978926541077e-05, "loss": 0.4751845359802246, "step": 473280 }, { "epoch": 2.8133340466382535, "grad_norm": 1.2789171934127808, "learning_rate": 2.211463728390699e-05, "loss": 0.4821725845336914, "step": 473290 }, { "epoch": 2.813393488714922, "grad_norm": 1.5234136581420898, "learning_rate": 2.2113296061687732e-05, "loss": 0.4705810070037842, "step": 473300 }, { "epoch": 2.8134529307915903, "grad_norm": 1.5290461778640747, "learning_rate": 2.2111955259889754e-05, "loss": 0.4813732147216797, "step": 473310 }, { "epoch": 2.8135123728682583, "grad_norm": 1.5249204635620117, "learning_rate": 2.2110614878519455e-05, "loss": 0.5379953384399414, "step": 473320 }, { "epoch": 2.813571814944927, "grad_norm": 1.0384389162063599, "learning_rate": 2.2109274917583247e-05, "loss": 0.48244075775146483, "step": 473330 }, { "epoch": 2.813631257021595, "grad_norm": 1.2968053817749023, "learning_rate": 2.2107935377087553e-05, "loss": 0.48601546287536623, "step": 473340 }, { "epoch": 2.813690699098264, "grad_norm": 1.3287850618362427, "learning_rate": 2.2106596257038784e-05, "loss": 0.45828022956848147, "step": 473350 }, { "epoch": 2.813750141174932, "grad_norm": 1.586307406425476, "learning_rate": 2.2105257557443325e-05, "loss": 0.4613664627075195, "step": 473360 }, { "epoch": 2.8138095832516004, "grad_norm": 1.394633412361145, "learning_rate": 2.2103919278307585e-05, "loss": 0.44531497955322263, "step": 473370 }, { "epoch": 2.8138690253282688, "grad_norm": 1.2269573211669922, "learning_rate": 2.210258141963797e-05, "loss": 0.43050379753112794, "step": 473380 }, { "epoch": 2.813928467404937, "grad_norm": 1.6999253034591675, "learning_rate": 2.210124398144089e-05, "loss": 0.489093017578125, "step": 473390 }, { "epoch": 2.8139879094816056, "grad_norm": 1.1601696014404297, "learning_rate": 2.2099906963722718e-05, "loss": 0.46915082931518554, "step": 473400 }, { "epoch": 2.814047351558274, "grad_norm": 1.1087028980255127, "learning_rate": 2.2098570366489886e-05, "loss": 0.45966787338256837, "step": 473410 }, { "epoch": 2.8141067936349424, "grad_norm": 1.3313168287277222, "learning_rate": 2.2097234189748755e-05, "loss": 0.4763755798339844, "step": 473420 }, { "epoch": 2.814166235711611, "grad_norm": 0.9378176927566528, "learning_rate": 2.2095898433505717e-05, "loss": 0.4278397560119629, "step": 473430 }, { "epoch": 2.8142256777882793, "grad_norm": 1.5218493938446045, "learning_rate": 2.2094563097767184e-05, "loss": 0.47171750068664553, "step": 473440 }, { "epoch": 2.8142851198649477, "grad_norm": 1.400309681892395, "learning_rate": 2.2093228182539538e-05, "loss": 0.4608620643615723, "step": 473450 }, { "epoch": 2.814344561941616, "grad_norm": 1.0958855152130127, "learning_rate": 2.2091893687829163e-05, "loss": 0.4505767822265625, "step": 473460 }, { "epoch": 2.8144040040182845, "grad_norm": 1.603663444519043, "learning_rate": 2.209055961364243e-05, "loss": 0.4498444557189941, "step": 473470 }, { "epoch": 2.814463446094953, "grad_norm": 1.431408405303955, "learning_rate": 2.208922595998574e-05, "loss": 0.4100391387939453, "step": 473480 }, { "epoch": 2.8145228881716213, "grad_norm": 1.3603826761245728, "learning_rate": 2.2087892726865454e-05, "loss": 0.48795385360717775, "step": 473490 }, { "epoch": 2.8145823302482897, "grad_norm": 1.2461156845092773, "learning_rate": 2.2086559914287964e-05, "loss": 0.4641819953918457, "step": 473500 }, { "epoch": 2.8146417723249577, "grad_norm": 1.5646004676818848, "learning_rate": 2.2085227522259635e-05, "loss": 0.4851961135864258, "step": 473510 }, { "epoch": 2.8147012144016266, "grad_norm": 1.1362922191619873, "learning_rate": 2.2083895550786857e-05, "loss": 0.4883427619934082, "step": 473520 }, { "epoch": 2.8147606564782945, "grad_norm": 1.386133074760437, "learning_rate": 2.2082563999875987e-05, "loss": 0.4239667892456055, "step": 473530 }, { "epoch": 2.814820098554963, "grad_norm": 1.3004100322723389, "learning_rate": 2.208123286953339e-05, "loss": 0.44070072174072267, "step": 473540 }, { "epoch": 2.8148795406316314, "grad_norm": 1.0928064584732056, "learning_rate": 2.2079902159765454e-05, "loss": 0.4190218925476074, "step": 473550 }, { "epoch": 2.8149389827083, "grad_norm": 1.10052490234375, "learning_rate": 2.2078571870578528e-05, "loss": 0.5175399780273438, "step": 473560 }, { "epoch": 2.814998424784968, "grad_norm": 1.4252572059631348, "learning_rate": 2.207724200197899e-05, "loss": 0.4695389747619629, "step": 473570 }, { "epoch": 2.8150578668616366, "grad_norm": 1.2317514419555664, "learning_rate": 2.2075912553973184e-05, "loss": 0.4390594005584717, "step": 473580 }, { "epoch": 2.815117308938305, "grad_norm": 1.3051742315292358, "learning_rate": 2.207458352656748e-05, "loss": 0.48321971893310545, "step": 473590 }, { "epoch": 2.8151767510149734, "grad_norm": 1.3623992204666138, "learning_rate": 2.2073254919768237e-05, "loss": 0.43996496200561525, "step": 473600 }, { "epoch": 2.815236193091642, "grad_norm": 0.964317798614502, "learning_rate": 2.2071926733581804e-05, "loss": 0.45533599853515627, "step": 473610 }, { "epoch": 2.8152956351683103, "grad_norm": 1.2086997032165527, "learning_rate": 2.207059896801454e-05, "loss": 0.4333191871643066, "step": 473620 }, { "epoch": 2.8153550772449787, "grad_norm": 1.1921488046646118, "learning_rate": 2.206927162307279e-05, "loss": 0.47017612457275393, "step": 473630 }, { "epoch": 2.815414519321647, "grad_norm": 1.3376141786575317, "learning_rate": 2.206794469876291e-05, "loss": 0.4696492195129395, "step": 473640 }, { "epoch": 2.8154739613983155, "grad_norm": 1.3534581661224365, "learning_rate": 2.2066618195091253e-05, "loss": 0.4485255241394043, "step": 473650 }, { "epoch": 2.815533403474984, "grad_norm": 1.164605736732483, "learning_rate": 2.2065292112064158e-05, "loss": 0.4453145980834961, "step": 473660 }, { "epoch": 2.8155928455516523, "grad_norm": 1.2090198993682861, "learning_rate": 2.2063966449687957e-05, "loss": 0.46407289505004884, "step": 473670 }, { "epoch": 2.8156522876283203, "grad_norm": 1.5989561080932617, "learning_rate": 2.206264120796901e-05, "loss": 0.4881433010101318, "step": 473680 }, { "epoch": 2.815711729704989, "grad_norm": 1.2537875175476074, "learning_rate": 2.2061316386913644e-05, "loss": 0.43084301948547366, "step": 473690 }, { "epoch": 2.815771171781657, "grad_norm": 1.4635940790176392, "learning_rate": 2.2059991986528212e-05, "loss": 0.49222712516784667, "step": 473700 }, { "epoch": 2.815830613858326, "grad_norm": 1.267440676689148, "learning_rate": 2.2058668006819037e-05, "loss": 0.4525906562805176, "step": 473710 }, { "epoch": 2.815890055934994, "grad_norm": 1.1290820837020874, "learning_rate": 2.2057344447792448e-05, "loss": 0.42225112915039065, "step": 473720 }, { "epoch": 2.8159494980116624, "grad_norm": 1.3738598823547363, "learning_rate": 2.2056021309454784e-05, "loss": 0.502747917175293, "step": 473730 }, { "epoch": 2.816008940088331, "grad_norm": 1.0456058979034424, "learning_rate": 2.2054698591812378e-05, "loss": 0.4687491416931152, "step": 473740 }, { "epoch": 2.816068382164999, "grad_norm": 1.4715049266815186, "learning_rate": 2.2053376294871555e-05, "loss": 0.45906686782836914, "step": 473750 }, { "epoch": 2.8161278242416676, "grad_norm": 1.0798290967941284, "learning_rate": 2.205205441863863e-05, "loss": 0.4221890926361084, "step": 473760 }, { "epoch": 2.816187266318336, "grad_norm": 1.1041396856307983, "learning_rate": 2.205073296311994e-05, "loss": 0.44240407943725585, "step": 473770 }, { "epoch": 2.8162467083950045, "grad_norm": 1.2852040529251099, "learning_rate": 2.20494119283218e-05, "loss": 0.46901679039001465, "step": 473780 }, { "epoch": 2.816306150471673, "grad_norm": 1.5862725973129272, "learning_rate": 2.204809131425053e-05, "loss": 0.4839299201965332, "step": 473790 }, { "epoch": 2.8163655925483413, "grad_norm": 1.24568772315979, "learning_rate": 2.204677112091246e-05, "loss": 0.4555100917816162, "step": 473800 }, { "epoch": 2.8164250346250097, "grad_norm": 1.2386445999145508, "learning_rate": 2.2045451348313884e-05, "loss": 0.4888956069946289, "step": 473810 }, { "epoch": 2.816484476701678, "grad_norm": 1.4403820037841797, "learning_rate": 2.2044131996461115e-05, "loss": 0.48511333465576173, "step": 473820 }, { "epoch": 2.8165439187783465, "grad_norm": 1.5138188600540161, "learning_rate": 2.2042813065360478e-05, "loss": 0.42504167556762695, "step": 473830 }, { "epoch": 2.816603360855015, "grad_norm": 1.1149132251739502, "learning_rate": 2.20414945550183e-05, "loss": 0.44134840965270994, "step": 473840 }, { "epoch": 2.8166628029316834, "grad_norm": 1.1006205081939697, "learning_rate": 2.2040176465440848e-05, "loss": 0.4446101665496826, "step": 473850 }, { "epoch": 2.8167222450083518, "grad_norm": 1.5812232494354248, "learning_rate": 2.203885879663444e-05, "loss": 0.4462554454803467, "step": 473860 }, { "epoch": 2.8167816870850197, "grad_norm": 1.1922311782836914, "learning_rate": 2.2037541548605397e-05, "loss": 0.43087072372436525, "step": 473870 }, { "epoch": 2.8168411291616886, "grad_norm": 1.3462401628494263, "learning_rate": 2.203622472136001e-05, "loss": 0.4743989944458008, "step": 473880 }, { "epoch": 2.8169005712383566, "grad_norm": 1.2198073863983154, "learning_rate": 2.2034908314904566e-05, "loss": 0.42909908294677734, "step": 473890 }, { "epoch": 2.8169600133150254, "grad_norm": 1.508764386177063, "learning_rate": 2.2033592329245396e-05, "loss": 0.4620652675628662, "step": 473900 }, { "epoch": 2.8170194553916934, "grad_norm": 1.0103057622909546, "learning_rate": 2.2032276764388752e-05, "loss": 0.46213908195495607, "step": 473910 }, { "epoch": 2.817078897468362, "grad_norm": 1.074022650718689, "learning_rate": 2.2030961620340947e-05, "loss": 0.4163679122924805, "step": 473920 }, { "epoch": 2.8171383395450302, "grad_norm": 1.1639883518218994, "learning_rate": 2.2029646897108287e-05, "loss": 0.4699872493743896, "step": 473930 }, { "epoch": 2.8171977816216986, "grad_norm": 1.3714990615844727, "learning_rate": 2.2028332594697043e-05, "loss": 0.4661055564880371, "step": 473940 }, { "epoch": 2.817257223698367, "grad_norm": 1.2092127799987793, "learning_rate": 2.20270187131135e-05, "loss": 0.469052791595459, "step": 473950 }, { "epoch": 2.8173166657750355, "grad_norm": 1.5323699712753296, "learning_rate": 2.2025705252363958e-05, "loss": 0.40026230812072755, "step": 473960 }, { "epoch": 2.817376107851704, "grad_norm": 1.0831788778305054, "learning_rate": 2.2024392212454688e-05, "loss": 0.48641281127929686, "step": 473970 }, { "epoch": 2.8174355499283723, "grad_norm": 1.8519337177276611, "learning_rate": 2.2023079593391972e-05, "loss": 0.48977837562561033, "step": 473980 }, { "epoch": 2.8174949920050407, "grad_norm": 1.1527751684188843, "learning_rate": 2.2021767395182083e-05, "loss": 0.4220613479614258, "step": 473990 }, { "epoch": 2.817554434081709, "grad_norm": 1.0196269750595093, "learning_rate": 2.202045561783132e-05, "loss": 0.44928731918334963, "step": 474000 }, { "epoch": 2.8176138761583776, "grad_norm": 1.3428256511688232, "learning_rate": 2.201914426134594e-05, "loss": 0.5376611232757569, "step": 474010 }, { "epoch": 2.817673318235046, "grad_norm": 1.3825207948684692, "learning_rate": 2.2017833325732227e-05, "loss": 0.46385946273803713, "step": 474020 }, { "epoch": 2.8177327603117144, "grad_norm": 1.6758784055709839, "learning_rate": 2.2016522810996444e-05, "loss": 0.5040575981140136, "step": 474030 }, { "epoch": 2.817792202388383, "grad_norm": 1.34092378616333, "learning_rate": 2.201521271714486e-05, "loss": 0.49483156204223633, "step": 474040 }, { "epoch": 2.817851644465051, "grad_norm": 1.2614985704421997, "learning_rate": 2.2013903044183743e-05, "loss": 0.409153413772583, "step": 474050 }, { "epoch": 2.817911086541719, "grad_norm": 1.4338780641555786, "learning_rate": 2.201259379211937e-05, "loss": 0.4134706497192383, "step": 474060 }, { "epoch": 2.817970528618388, "grad_norm": 1.116943597793579, "learning_rate": 2.2011284960957988e-05, "loss": 0.4868013381958008, "step": 474070 }, { "epoch": 2.818029970695056, "grad_norm": 1.4728678464889526, "learning_rate": 2.2009976550705862e-05, "loss": 0.49520244598388674, "step": 474080 }, { "epoch": 2.818089412771725, "grad_norm": 1.2772388458251953, "learning_rate": 2.2008668561369253e-05, "loss": 0.47928056716918943, "step": 474090 }, { "epoch": 2.818148854848393, "grad_norm": 1.615170955657959, "learning_rate": 2.200736099295442e-05, "loss": 0.44613170623779297, "step": 474100 }, { "epoch": 2.8182082969250613, "grad_norm": 0.9993672966957092, "learning_rate": 2.2006053845467607e-05, "loss": 0.4506591796875, "step": 474110 }, { "epoch": 2.8182677390017297, "grad_norm": 1.1727638244628906, "learning_rate": 2.2004747118915086e-05, "loss": 0.4639445304870605, "step": 474120 }, { "epoch": 2.818327181078398, "grad_norm": 1.0900341272354126, "learning_rate": 2.2003440813303095e-05, "loss": 0.43471317291259765, "step": 474130 }, { "epoch": 2.8183866231550665, "grad_norm": 1.542799949645996, "learning_rate": 2.200213492863788e-05, "loss": 0.515887975692749, "step": 474140 }, { "epoch": 2.818446065231735, "grad_norm": 1.5176118612289429, "learning_rate": 2.20008294649257e-05, "loss": 0.4880975723266602, "step": 474150 }, { "epoch": 2.8185055073084033, "grad_norm": 1.1150095462799072, "learning_rate": 2.1999524422172795e-05, "loss": 0.474514102935791, "step": 474160 }, { "epoch": 2.8185649493850717, "grad_norm": 1.2865664958953857, "learning_rate": 2.1998219800385407e-05, "loss": 0.460459041595459, "step": 474170 }, { "epoch": 2.81862439146174, "grad_norm": 1.3655781745910645, "learning_rate": 2.199691559956976e-05, "loss": 0.5040057182312012, "step": 474180 }, { "epoch": 2.8186838335384086, "grad_norm": 1.7258061170578003, "learning_rate": 2.199561181973213e-05, "loss": 0.46828060150146483, "step": 474190 }, { "epoch": 2.818743275615077, "grad_norm": 1.7117921113967896, "learning_rate": 2.1994308460878716e-05, "loss": 0.4873525619506836, "step": 474200 }, { "epoch": 2.8188027176917454, "grad_norm": 1.5125887393951416, "learning_rate": 2.1993005523015782e-05, "loss": 0.4576836585998535, "step": 474210 }, { "epoch": 2.818862159768414, "grad_norm": 1.2595045566558838, "learning_rate": 2.199170300614955e-05, "loss": 0.43906455039978026, "step": 474220 }, { "epoch": 2.8189216018450822, "grad_norm": 1.3768157958984375, "learning_rate": 2.199040091028624e-05, "loss": 0.41907782554626466, "step": 474230 }, { "epoch": 2.8189810439217506, "grad_norm": 1.6760315895080566, "learning_rate": 2.1989099235432096e-05, "loss": 0.46666383743286133, "step": 474240 }, { "epoch": 2.8190404859984186, "grad_norm": 1.2517600059509277, "learning_rate": 2.1987797981593335e-05, "loss": 0.42203598022460936, "step": 474250 }, { "epoch": 2.8190999280750875, "grad_norm": 1.4456690549850464, "learning_rate": 2.198649714877618e-05, "loss": 0.43186097145080565, "step": 474260 }, { "epoch": 2.8191593701517554, "grad_norm": 1.3050916194915771, "learning_rate": 2.1985196736986867e-05, "loss": 0.4659027099609375, "step": 474270 }, { "epoch": 2.819218812228424, "grad_norm": 0.972456157207489, "learning_rate": 2.1983896746231612e-05, "loss": 0.44144258499145506, "step": 474280 }, { "epoch": 2.8192782543050923, "grad_norm": 1.5662810802459717, "learning_rate": 2.1982597176516635e-05, "loss": 0.4497654914855957, "step": 474290 }, { "epoch": 2.8193376963817607, "grad_norm": 1.2885342836380005, "learning_rate": 2.198129802784814e-05, "loss": 0.4898989677429199, "step": 474300 }, { "epoch": 2.819397138458429, "grad_norm": 1.009526252746582, "learning_rate": 2.197999930023236e-05, "loss": 0.4761359691619873, "step": 474310 }, { "epoch": 2.8194565805350975, "grad_norm": 1.5738469362258911, "learning_rate": 2.197870099367548e-05, "loss": 0.4788087844848633, "step": 474320 }, { "epoch": 2.819516022611766, "grad_norm": 1.4214807748794556, "learning_rate": 2.1977403108183735e-05, "loss": 0.47888822555541993, "step": 474330 }, { "epoch": 2.8195754646884343, "grad_norm": 1.1420780420303345, "learning_rate": 2.1976105643763344e-05, "loss": 0.47398223876953127, "step": 474340 }, { "epoch": 2.8196349067651028, "grad_norm": 1.1109594106674194, "learning_rate": 2.1974808600420477e-05, "loss": 0.48781213760375974, "step": 474350 }, { "epoch": 2.819694348841771, "grad_norm": 1.4611870050430298, "learning_rate": 2.1973511978161375e-05, "loss": 0.5370387077331543, "step": 474360 }, { "epoch": 2.8197537909184396, "grad_norm": 1.1504486799240112, "learning_rate": 2.1972215776992217e-05, "loss": 0.5238297462463379, "step": 474370 }, { "epoch": 2.819813232995108, "grad_norm": 1.1853779554367065, "learning_rate": 2.1970919996919197e-05, "loss": 0.4850324630737305, "step": 474380 }, { "epoch": 2.8198726750717764, "grad_norm": 1.2233226299285889, "learning_rate": 2.1969624637948546e-05, "loss": 0.4675127983093262, "step": 474390 }, { "epoch": 2.819932117148445, "grad_norm": 1.2117359638214111, "learning_rate": 2.196832970008645e-05, "loss": 0.475862455368042, "step": 474400 }, { "epoch": 2.8199915592251132, "grad_norm": 1.1519557237625122, "learning_rate": 2.1967035183339073e-05, "loss": 0.41563048362731936, "step": 474410 }, { "epoch": 2.820051001301781, "grad_norm": 1.3917869329452515, "learning_rate": 2.196574108771263e-05, "loss": 0.5184398174285889, "step": 474420 }, { "epoch": 2.82011044337845, "grad_norm": 1.322952389717102, "learning_rate": 2.1964447413213325e-05, "loss": 0.5060192584991455, "step": 474430 }, { "epoch": 2.820169885455118, "grad_norm": 1.352285623550415, "learning_rate": 2.196315415984733e-05, "loss": 0.47294049263000487, "step": 474440 }, { "epoch": 2.820229327531787, "grad_norm": 1.1942938566207886, "learning_rate": 2.1961861327620835e-05, "loss": 0.4389488220214844, "step": 474450 }, { "epoch": 2.820288769608455, "grad_norm": 1.0921517610549927, "learning_rate": 2.196056891654003e-05, "loss": 0.49396886825561526, "step": 474460 }, { "epoch": 2.8203482116851233, "grad_norm": 1.344718337059021, "learning_rate": 2.195927692661109e-05, "loss": 0.40568199157714846, "step": 474470 }, { "epoch": 2.8204076537617917, "grad_norm": 1.479321002960205, "learning_rate": 2.1957985357840176e-05, "loss": 0.4727086067199707, "step": 474480 }, { "epoch": 2.82046709583846, "grad_norm": 1.5108765363693237, "learning_rate": 2.1956694210233506e-05, "loss": 0.46312732696533204, "step": 474490 }, { "epoch": 2.8205265379151285, "grad_norm": 1.6094145774841309, "learning_rate": 2.1955403483797242e-05, "loss": 0.45044584274291993, "step": 474500 }, { "epoch": 2.820585979991797, "grad_norm": 1.43362295627594, "learning_rate": 2.1954113178537543e-05, "loss": 0.4367403030395508, "step": 474510 }, { "epoch": 2.8206454220684654, "grad_norm": 0.9464185833930969, "learning_rate": 2.1952823294460606e-05, "loss": 0.44145002365112307, "step": 474520 }, { "epoch": 2.8207048641451338, "grad_norm": 1.0913437604904175, "learning_rate": 2.195153383157258e-05, "loss": 0.4405377388000488, "step": 474530 }, { "epoch": 2.820764306221802, "grad_norm": 1.3569989204406738, "learning_rate": 2.1950244789879635e-05, "loss": 0.49915828704833987, "step": 474540 }, { "epoch": 2.8208237482984706, "grad_norm": 1.1197118759155273, "learning_rate": 2.194895616938795e-05, "loss": 0.46773719787597656, "step": 474550 }, { "epoch": 2.820883190375139, "grad_norm": 1.2650377750396729, "learning_rate": 2.1947667970103687e-05, "loss": 0.4338264465332031, "step": 474560 }, { "epoch": 2.8209426324518074, "grad_norm": 1.6336265802383423, "learning_rate": 2.1946380192032997e-05, "loss": 0.45776710510253904, "step": 474570 }, { "epoch": 2.821002074528476, "grad_norm": 1.554974913597107, "learning_rate": 2.1945092835182058e-05, "loss": 0.47684249877929685, "step": 474580 }, { "epoch": 2.8210615166051443, "grad_norm": 1.029906988143921, "learning_rate": 2.194380589955701e-05, "loss": 0.4537069320678711, "step": 474590 }, { "epoch": 2.8211209586818127, "grad_norm": 0.9552024006843567, "learning_rate": 2.1942519385164022e-05, "loss": 0.4844069004058838, "step": 474600 }, { "epoch": 2.8211804007584806, "grad_norm": 1.1234954595565796, "learning_rate": 2.1941233292009238e-05, "loss": 0.4441837310791016, "step": 474610 }, { "epoch": 2.8212398428351495, "grad_norm": 1.341807246208191, "learning_rate": 2.1939947620098816e-05, "loss": 0.4652510643005371, "step": 474620 }, { "epoch": 2.8212992849118175, "grad_norm": 1.1046298742294312, "learning_rate": 2.1938662369438915e-05, "loss": 0.4380343914031982, "step": 474630 }, { "epoch": 2.8213587269884863, "grad_norm": 1.2642163038253784, "learning_rate": 2.1937377540035676e-05, "loss": 0.5013992786407471, "step": 474640 }, { "epoch": 2.8214181690651543, "grad_norm": 1.134247064590454, "learning_rate": 2.193609313189523e-05, "loss": 0.5193116664886475, "step": 474650 }, { "epoch": 2.8214776111418227, "grad_norm": 1.4322874546051025, "learning_rate": 2.1934809145023747e-05, "loss": 0.4925670623779297, "step": 474660 }, { "epoch": 2.821537053218491, "grad_norm": 1.1537145376205444, "learning_rate": 2.1933525579427346e-05, "loss": 0.4388163089752197, "step": 474670 }, { "epoch": 2.8215964952951595, "grad_norm": 1.359190583229065, "learning_rate": 2.1932242435112187e-05, "loss": 0.48607187271118163, "step": 474680 }, { "epoch": 2.821655937371828, "grad_norm": 1.5894380807876587, "learning_rate": 2.19309597120844e-05, "loss": 0.49891085624694825, "step": 474690 }, { "epoch": 2.8217153794484964, "grad_norm": 0.9865167737007141, "learning_rate": 2.1929677410350114e-05, "loss": 0.45351715087890626, "step": 474700 }, { "epoch": 2.821774821525165, "grad_norm": 1.333440899848938, "learning_rate": 2.1928395529915475e-05, "loss": 0.4657417297363281, "step": 474710 }, { "epoch": 2.821834263601833, "grad_norm": 1.4437419176101685, "learning_rate": 2.1927114070786615e-05, "loss": 0.43949050903320314, "step": 474720 }, { "epoch": 2.8218937056785016, "grad_norm": 0.8913676738739014, "learning_rate": 2.192583303296965e-05, "loss": 0.44237823486328126, "step": 474730 }, { "epoch": 2.82195314775517, "grad_norm": 1.406732439994812, "learning_rate": 2.1924552416470703e-05, "loss": 0.44979124069213866, "step": 474740 }, { "epoch": 2.8220125898318384, "grad_norm": 0.9364941120147705, "learning_rate": 2.1923272221295934e-05, "loss": 0.4700336456298828, "step": 474750 }, { "epoch": 2.822072031908507, "grad_norm": 1.3202589750289917, "learning_rate": 2.192199244745145e-05, "loss": 0.453427791595459, "step": 474760 }, { "epoch": 2.8221314739851753, "grad_norm": 1.00914466381073, "learning_rate": 2.1920713094943354e-05, "loss": 0.47665696144104003, "step": 474770 }, { "epoch": 2.8221909160618437, "grad_norm": 1.1407139301300049, "learning_rate": 2.1919434163777793e-05, "loss": 0.45154271125793455, "step": 474780 }, { "epoch": 2.822250358138512, "grad_norm": 1.2273049354553223, "learning_rate": 2.1918155653960867e-05, "loss": 0.4532073974609375, "step": 474790 }, { "epoch": 2.82230980021518, "grad_norm": 1.1213253736495972, "learning_rate": 2.19168775654987e-05, "loss": 0.4683551788330078, "step": 474800 }, { "epoch": 2.822369242291849, "grad_norm": 1.3553388118743896, "learning_rate": 2.1915599898397403e-05, "loss": 0.5034655094146728, "step": 474810 }, { "epoch": 2.822428684368517, "grad_norm": 1.3025647401809692, "learning_rate": 2.19143226526631e-05, "loss": 0.4952096939086914, "step": 474820 }, { "epoch": 2.8224881264451858, "grad_norm": 1.4372906684875488, "learning_rate": 2.19130458283019e-05, "loss": 0.4372850894927979, "step": 474830 }, { "epoch": 2.8225475685218537, "grad_norm": 1.1541403532028198, "learning_rate": 2.191176942531987e-05, "loss": 0.41819448471069337, "step": 474840 }, { "epoch": 2.822607010598522, "grad_norm": 1.5193861722946167, "learning_rate": 2.1910493443723167e-05, "loss": 0.49904422760009765, "step": 474850 }, { "epoch": 2.8226664526751906, "grad_norm": 1.640039086341858, "learning_rate": 2.190921788351788e-05, "loss": 0.5083806037902832, "step": 474860 }, { "epoch": 2.822725894751859, "grad_norm": 1.6352602243423462, "learning_rate": 2.1907942744710082e-05, "loss": 0.5144097328186035, "step": 474870 }, { "epoch": 2.8227853368285274, "grad_norm": 1.2364401817321777, "learning_rate": 2.190666802730592e-05, "loss": 0.4764710903167725, "step": 474880 }, { "epoch": 2.822844778905196, "grad_norm": 1.3140531778335571, "learning_rate": 2.190539373131148e-05, "loss": 0.39846751689910886, "step": 474890 }, { "epoch": 2.822904220981864, "grad_norm": 1.0540950298309326, "learning_rate": 2.1904119856732814e-05, "loss": 0.42761030197143557, "step": 474900 }, { "epoch": 2.8229636630585326, "grad_norm": 1.6227123737335205, "learning_rate": 2.190284640357607e-05, "loss": 0.4951587677001953, "step": 474910 }, { "epoch": 2.823023105135201, "grad_norm": 1.1022627353668213, "learning_rate": 2.1901573371847305e-05, "loss": 0.447265625, "step": 474920 }, { "epoch": 2.8230825472118695, "grad_norm": 1.5140048265457153, "learning_rate": 2.1900300761552633e-05, "loss": 0.4526381015777588, "step": 474930 }, { "epoch": 2.823141989288538, "grad_norm": 1.5287506580352783, "learning_rate": 2.189902857269812e-05, "loss": 0.47007904052734373, "step": 474940 }, { "epoch": 2.8232014313652063, "grad_norm": 1.629930019378662, "learning_rate": 2.1897756805289875e-05, "loss": 0.5286134719848633, "step": 474950 }, { "epoch": 2.8232608734418747, "grad_norm": 1.3323392868041992, "learning_rate": 2.1896485459333975e-05, "loss": 0.4060249328613281, "step": 474960 }, { "epoch": 2.823320315518543, "grad_norm": 1.2804338932037354, "learning_rate": 2.1895214534836473e-05, "loss": 0.473158073425293, "step": 474970 }, { "epoch": 2.8233797575952115, "grad_norm": 1.068565011024475, "learning_rate": 2.1893944031803483e-05, "loss": 0.436183500289917, "step": 474980 }, { "epoch": 2.8234391996718795, "grad_norm": 1.3236925601959229, "learning_rate": 2.189267395024107e-05, "loss": 0.43115959167480467, "step": 474990 }, { "epoch": 2.8234986417485484, "grad_norm": 1.2023828029632568, "learning_rate": 2.1891404290155316e-05, "loss": 0.4135789394378662, "step": 475000 }, { "epoch": 2.8235580838252163, "grad_norm": 1.445924162864685, "learning_rate": 2.1890135051552297e-05, "loss": 0.4986870288848877, "step": 475010 }, { "epoch": 2.8236175259018848, "grad_norm": 1.434110164642334, "learning_rate": 2.188886623443806e-05, "loss": 0.4779056549072266, "step": 475020 }, { "epoch": 2.823676967978553, "grad_norm": 1.1462239027023315, "learning_rate": 2.1887597838818695e-05, "loss": 0.477449893951416, "step": 475030 }, { "epoch": 2.8237364100552216, "grad_norm": 1.625481128692627, "learning_rate": 2.1886329864700273e-05, "loss": 0.42867746353149416, "step": 475040 }, { "epoch": 2.82379585213189, "grad_norm": 1.4136979579925537, "learning_rate": 2.188506231208885e-05, "loss": 0.48593759536743164, "step": 475050 }, { "epoch": 2.8238552942085584, "grad_norm": 1.3517407178878784, "learning_rate": 2.1883795180990492e-05, "loss": 0.4599421977996826, "step": 475060 }, { "epoch": 2.823914736285227, "grad_norm": 1.3998284339904785, "learning_rate": 2.1882528471411263e-05, "loss": 0.44341220855712893, "step": 475070 }, { "epoch": 2.8239741783618952, "grad_norm": 1.6430128812789917, "learning_rate": 2.1881262183357228e-05, "loss": 0.5130838394165039, "step": 475080 }, { "epoch": 2.8240336204385637, "grad_norm": 1.0937879085540771, "learning_rate": 2.1879996316834425e-05, "loss": 0.45528268814086914, "step": 475090 }, { "epoch": 2.824093062515232, "grad_norm": 1.2987667322158813, "learning_rate": 2.1878730871848925e-05, "loss": 0.49460549354553224, "step": 475100 }, { "epoch": 2.8241525045919005, "grad_norm": 1.5698853731155396, "learning_rate": 2.1877465848406777e-05, "loss": 0.4836560249328613, "step": 475110 }, { "epoch": 2.824211946668569, "grad_norm": 1.4491019248962402, "learning_rate": 2.1876201246514037e-05, "loss": 0.5036316871643066, "step": 475120 }, { "epoch": 2.8242713887452373, "grad_norm": 1.3219642639160156, "learning_rate": 2.1874937066176754e-05, "loss": 0.43218340873718264, "step": 475130 }, { "epoch": 2.8243308308219057, "grad_norm": 1.6348254680633545, "learning_rate": 2.1873673307400965e-05, "loss": 0.4423419952392578, "step": 475140 }, { "epoch": 2.824390272898574, "grad_norm": 1.2399635314941406, "learning_rate": 2.1872409970192733e-05, "loss": 0.424759578704834, "step": 475150 }, { "epoch": 2.824449714975242, "grad_norm": 1.4617657661437988, "learning_rate": 2.187114705455807e-05, "loss": 0.5052237033843994, "step": 475160 }, { "epoch": 2.824509157051911, "grad_norm": 1.0084657669067383, "learning_rate": 2.186988456050306e-05, "loss": 0.45287575721740725, "step": 475170 }, { "epoch": 2.824568599128579, "grad_norm": 1.1412904262542725, "learning_rate": 2.186862248803371e-05, "loss": 0.4431140422821045, "step": 475180 }, { "epoch": 2.824628041205248, "grad_norm": 1.7458031177520752, "learning_rate": 2.186736083715608e-05, "loss": 0.47380685806274414, "step": 475190 }, { "epoch": 2.8246874832819158, "grad_norm": 1.4328068494796753, "learning_rate": 2.1866099607876184e-05, "loss": 0.518956184387207, "step": 475200 }, { "epoch": 2.824746925358584, "grad_norm": 1.105771780014038, "learning_rate": 2.186483880020007e-05, "loss": 0.42693843841552737, "step": 475210 }, { "epoch": 2.8248063674352526, "grad_norm": 1.3709352016448975, "learning_rate": 2.1863578414133766e-05, "loss": 0.45034399032592776, "step": 475220 }, { "epoch": 2.824865809511921, "grad_norm": 1.4983775615692139, "learning_rate": 2.1862318449683285e-05, "loss": 0.48874311447143554, "step": 475230 }, { "epoch": 2.8249252515885894, "grad_norm": 1.316227912902832, "learning_rate": 2.1861058906854678e-05, "loss": 0.4822572708129883, "step": 475240 }, { "epoch": 2.824984693665258, "grad_norm": 1.175195336341858, "learning_rate": 2.1859799785653963e-05, "loss": 0.44783697128295896, "step": 475250 }, { "epoch": 2.8250441357419263, "grad_norm": 1.2809505462646484, "learning_rate": 2.185854108608716e-05, "loss": 0.4809288024902344, "step": 475260 }, { "epoch": 2.8251035778185947, "grad_norm": 1.0907312631607056, "learning_rate": 2.1857282808160297e-05, "loss": 0.4172982215881348, "step": 475270 }, { "epoch": 2.825163019895263, "grad_norm": 1.4871996641159058, "learning_rate": 2.1856024951879385e-05, "loss": 0.5121803760528565, "step": 475280 }, { "epoch": 2.8252224619719315, "grad_norm": 1.303253412246704, "learning_rate": 2.1854767517250443e-05, "loss": 0.4660640716552734, "step": 475290 }, { "epoch": 2.8252819040486, "grad_norm": 0.9446916580200195, "learning_rate": 2.185351050427947e-05, "loss": 0.44567251205444336, "step": 475300 }, { "epoch": 2.8253413461252683, "grad_norm": 1.1671297550201416, "learning_rate": 2.1852253912972513e-05, "loss": 0.5226969242095947, "step": 475310 }, { "epoch": 2.8254007882019367, "grad_norm": 1.5215166807174683, "learning_rate": 2.1850997743335582e-05, "loss": 0.5020414352416992, "step": 475320 }, { "epoch": 2.825460230278605, "grad_norm": 1.4137630462646484, "learning_rate": 2.1849741995374648e-05, "loss": 0.45217022895812986, "step": 475330 }, { "epoch": 2.8255196723552736, "grad_norm": 1.1444326639175415, "learning_rate": 2.184848666909574e-05, "loss": 0.47628011703491213, "step": 475340 }, { "epoch": 2.8255791144319415, "grad_norm": 1.5070264339447021, "learning_rate": 2.184723176450487e-05, "loss": 0.4642195701599121, "step": 475350 }, { "epoch": 2.8256385565086104, "grad_norm": 1.3253352642059326, "learning_rate": 2.1845977281608027e-05, "loss": 0.4446387767791748, "step": 475360 }, { "epoch": 2.8256979985852784, "grad_norm": 1.0669718980789185, "learning_rate": 2.184472322041123e-05, "loss": 0.4111655235290527, "step": 475370 }, { "epoch": 2.8257574406619472, "grad_norm": 1.9687299728393555, "learning_rate": 2.184346958092047e-05, "loss": 0.4564582347869873, "step": 475380 }, { "epoch": 2.825816882738615, "grad_norm": 1.3084443807601929, "learning_rate": 2.1842216363141733e-05, "loss": 0.48770532608032224, "step": 475390 }, { "epoch": 2.8258763248152836, "grad_norm": 1.1261074542999268, "learning_rate": 2.184096356708102e-05, "loss": 0.46770753860473635, "step": 475400 }, { "epoch": 2.825935766891952, "grad_norm": 1.406175971031189, "learning_rate": 2.1839711192744336e-05, "loss": 0.4520857810974121, "step": 475410 }, { "epoch": 2.8259952089686204, "grad_norm": 1.2818799018859863, "learning_rate": 2.183845924013766e-05, "loss": 0.472813081741333, "step": 475420 }, { "epoch": 2.826054651045289, "grad_norm": 1.1365633010864258, "learning_rate": 2.1837207709266973e-05, "loss": 0.4590189456939697, "step": 475430 }, { "epoch": 2.8261140931219573, "grad_norm": 1.4372669458389282, "learning_rate": 2.1835956600138295e-05, "loss": 0.48587946891784667, "step": 475440 }, { "epoch": 2.8261735351986257, "grad_norm": 1.2987205982208252, "learning_rate": 2.1834705912757574e-05, "loss": 0.5027905464172363, "step": 475450 }, { "epoch": 2.826232977275294, "grad_norm": 1.49604070186615, "learning_rate": 2.1833455647130807e-05, "loss": 0.449677848815918, "step": 475460 }, { "epoch": 2.8262924193519625, "grad_norm": 1.1093101501464844, "learning_rate": 2.1832205803263974e-05, "loss": 0.4432381629943848, "step": 475470 }, { "epoch": 2.826351861428631, "grad_norm": 1.2598600387573242, "learning_rate": 2.1830956381163052e-05, "loss": 0.45990738868713377, "step": 475480 }, { "epoch": 2.8264113035052993, "grad_norm": 0.9912949204444885, "learning_rate": 2.182970738083402e-05, "loss": 0.44906139373779297, "step": 475490 }, { "epoch": 2.8264707455819678, "grad_norm": 1.497347354888916, "learning_rate": 2.1828458802282873e-05, "loss": 0.4680013179779053, "step": 475500 }, { "epoch": 2.826530187658636, "grad_norm": 1.2353770732879639, "learning_rate": 2.182721064551555e-05, "loss": 0.4605660915374756, "step": 475510 }, { "epoch": 2.8265896297353046, "grad_norm": 1.255548119544983, "learning_rate": 2.1825962910538033e-05, "loss": 0.41934638023376464, "step": 475520 }, { "epoch": 2.826649071811973, "grad_norm": 1.5672234296798706, "learning_rate": 2.1824715597356294e-05, "loss": 0.46913814544677734, "step": 475530 }, { "epoch": 2.826708513888641, "grad_norm": 1.467504858970642, "learning_rate": 2.1823468705976304e-05, "loss": 0.4265730857849121, "step": 475540 }, { "epoch": 2.82676795596531, "grad_norm": 1.2391557693481445, "learning_rate": 2.1822222236404015e-05, "loss": 0.4772193908691406, "step": 475550 }, { "epoch": 2.826827398041978, "grad_norm": 1.2559876441955566, "learning_rate": 2.1820976188645416e-05, "loss": 0.4551642417907715, "step": 475560 }, { "epoch": 2.8268868401186467, "grad_norm": 0.9471666812896729, "learning_rate": 2.181973056270644e-05, "loss": 0.44056024551391604, "step": 475570 }, { "epoch": 2.8269462821953146, "grad_norm": 1.3785885572433472, "learning_rate": 2.181848535859305e-05, "loss": 0.4714812278747559, "step": 475580 }, { "epoch": 2.827005724271983, "grad_norm": 1.4794760942459106, "learning_rate": 2.1817240576311207e-05, "loss": 0.46690025329589846, "step": 475590 }, { "epoch": 2.8270651663486515, "grad_norm": 1.0997620820999146, "learning_rate": 2.181599621586687e-05, "loss": 0.4222602844238281, "step": 475600 }, { "epoch": 2.82712460842532, "grad_norm": 1.1789214611053467, "learning_rate": 2.1814752277265995e-05, "loss": 0.4402010917663574, "step": 475610 }, { "epoch": 2.8271840505019883, "grad_norm": 1.202975869178772, "learning_rate": 2.1813508760514524e-05, "loss": 0.5043789386749268, "step": 475620 }, { "epoch": 2.8272434925786567, "grad_norm": 1.332096815109253, "learning_rate": 2.1812265665618408e-05, "loss": 0.457521390914917, "step": 475630 }, { "epoch": 2.827302934655325, "grad_norm": 1.0275381803512573, "learning_rate": 2.181102299258358e-05, "loss": 0.4763628005981445, "step": 475640 }, { "epoch": 2.8273623767319935, "grad_norm": 1.4444310665130615, "learning_rate": 2.180978074141601e-05, "loss": 0.5225846290588378, "step": 475650 }, { "epoch": 2.827421818808662, "grad_norm": 1.1433603763580322, "learning_rate": 2.1808538912121622e-05, "loss": 0.43601508140563966, "step": 475660 }, { "epoch": 2.8274812608853304, "grad_norm": 1.16416597366333, "learning_rate": 2.180729750470637e-05, "loss": 0.4215813636779785, "step": 475670 }, { "epoch": 2.8275407029619988, "grad_norm": 1.2275197505950928, "learning_rate": 2.180605651917618e-05, "loss": 0.4454911231994629, "step": 475680 }, { "epoch": 2.827600145038667, "grad_norm": 1.2354488372802734, "learning_rate": 2.1804815955536996e-05, "loss": 0.46839656829833987, "step": 475690 }, { "epoch": 2.8276595871153356, "grad_norm": 1.3108011484146118, "learning_rate": 2.180357581379475e-05, "loss": 0.466862154006958, "step": 475700 }, { "epoch": 2.8277190291920036, "grad_norm": 1.1596205234527588, "learning_rate": 2.1802336093955373e-05, "loss": 0.45943422317504884, "step": 475710 }, { "epoch": 2.8277784712686724, "grad_norm": 1.401084542274475, "learning_rate": 2.1801096796024785e-05, "loss": 0.5012609481811523, "step": 475720 }, { "epoch": 2.8278379133453404, "grad_norm": 1.3100762367248535, "learning_rate": 2.1799857920008942e-05, "loss": 0.47901010513305664, "step": 475730 }, { "epoch": 2.8278973554220093, "grad_norm": 1.1975566148757935, "learning_rate": 2.1798619465913746e-05, "loss": 0.46167831420898436, "step": 475740 }, { "epoch": 2.8279567974986772, "grad_norm": 1.3760132789611816, "learning_rate": 2.1797381433745135e-05, "loss": 0.4977286338806152, "step": 475750 }, { "epoch": 2.8280162395753456, "grad_norm": 1.1929359436035156, "learning_rate": 2.179614382350903e-05, "loss": 0.4720294952392578, "step": 475760 }, { "epoch": 2.828075681652014, "grad_norm": 1.254573941230774, "learning_rate": 2.179490663521134e-05, "loss": 0.45898046493530276, "step": 475770 }, { "epoch": 2.8281351237286825, "grad_norm": 1.417372226715088, "learning_rate": 2.1793669868858e-05, "loss": 0.48563547134399415, "step": 475780 }, { "epoch": 2.828194565805351, "grad_norm": 1.2855514287948608, "learning_rate": 2.1792433524454905e-05, "loss": 0.44428653717041017, "step": 475790 }, { "epoch": 2.8282540078820193, "grad_norm": 1.233254075050354, "learning_rate": 2.179119760200798e-05, "loss": 0.4437751770019531, "step": 475800 }, { "epoch": 2.8283134499586877, "grad_norm": 1.6298348903656006, "learning_rate": 2.1789962101523152e-05, "loss": 0.4321180820465088, "step": 475810 }, { "epoch": 2.828372892035356, "grad_norm": 1.3212703466415405, "learning_rate": 2.178872702300631e-05, "loss": 0.47028751373291017, "step": 475820 }, { "epoch": 2.8284323341120245, "grad_norm": 0.9552810788154602, "learning_rate": 2.178749236646338e-05, "loss": 0.4317337512969971, "step": 475830 }, { "epoch": 2.828491776188693, "grad_norm": 1.2628313302993774, "learning_rate": 2.178625813190025e-05, "loss": 0.47660274505615235, "step": 475840 }, { "epoch": 2.8285512182653614, "grad_norm": 1.0327632427215576, "learning_rate": 2.1785024319322823e-05, "loss": 0.5074857711791992, "step": 475850 }, { "epoch": 2.82861066034203, "grad_norm": 1.3498561382293701, "learning_rate": 2.1783790928737026e-05, "loss": 0.43910064697265627, "step": 475860 }, { "epoch": 2.828670102418698, "grad_norm": 1.5180455446243286, "learning_rate": 2.178255796014875e-05, "loss": 0.44568963050842286, "step": 475870 }, { "epoch": 2.8287295444953666, "grad_norm": 1.0291146039962769, "learning_rate": 2.1781325413563863e-05, "loss": 0.44327192306518554, "step": 475880 }, { "epoch": 2.828788986572035, "grad_norm": 1.2862436771392822, "learning_rate": 2.1780093288988295e-05, "loss": 0.4865865230560303, "step": 475890 }, { "epoch": 2.828848428648703, "grad_norm": 1.2313616275787354, "learning_rate": 2.1778861586427942e-05, "loss": 0.45066280364990235, "step": 475900 }, { "epoch": 2.828907870725372, "grad_norm": 1.5608975887298584, "learning_rate": 2.1777630305888675e-05, "loss": 0.4814507007598877, "step": 475910 }, { "epoch": 2.82896731280204, "grad_norm": 1.3999881744384766, "learning_rate": 2.1776399447376383e-05, "loss": 0.45768046379089355, "step": 475920 }, { "epoch": 2.8290267548787087, "grad_norm": 1.246240258216858, "learning_rate": 2.1775169010896987e-05, "loss": 0.45130329132080077, "step": 475930 }, { "epoch": 2.8290861969553767, "grad_norm": 1.4277615547180176, "learning_rate": 2.1773938996456338e-05, "loss": 0.48908233642578125, "step": 475940 }, { "epoch": 2.829145639032045, "grad_norm": 1.065504789352417, "learning_rate": 2.1772709404060327e-05, "loss": 0.416271448135376, "step": 475950 }, { "epoch": 2.8292050811087135, "grad_norm": 1.3244510889053345, "learning_rate": 2.177148023371484e-05, "loss": 0.46254377365112304, "step": 475960 }, { "epoch": 2.829264523185382, "grad_norm": 1.3756746053695679, "learning_rate": 2.1770251485425773e-05, "loss": 0.4916964530944824, "step": 475970 }, { "epoch": 2.8293239652620503, "grad_norm": 1.523713231086731, "learning_rate": 2.176902315919897e-05, "loss": 0.5065078258514404, "step": 475980 }, { "epoch": 2.8293834073387187, "grad_norm": 1.1330422163009644, "learning_rate": 2.1767795255040348e-05, "loss": 0.44342708587646484, "step": 475990 }, { "epoch": 2.829442849415387, "grad_norm": 1.0752232074737549, "learning_rate": 2.1766567772955744e-05, "loss": 0.46615076065063477, "step": 476000 }, { "epoch": 2.8295022914920556, "grad_norm": 1.2652887105941772, "learning_rate": 2.176534071295104e-05, "loss": 0.4842063426971436, "step": 476010 }, { "epoch": 2.829561733568724, "grad_norm": 1.5284478664398193, "learning_rate": 2.176411407503212e-05, "loss": 0.45932807922363283, "step": 476020 }, { "epoch": 2.8296211756453924, "grad_norm": 0.9345810413360596, "learning_rate": 2.176288785920484e-05, "loss": 0.472639799118042, "step": 476030 }, { "epoch": 2.829680617722061, "grad_norm": 1.1330757141113281, "learning_rate": 2.1761662065475072e-05, "loss": 0.48049182891845704, "step": 476040 }, { "epoch": 2.8297400597987292, "grad_norm": 1.4638375043869019, "learning_rate": 2.1760436693848673e-05, "loss": 0.44809961318969727, "step": 476050 }, { "epoch": 2.8297995018753976, "grad_norm": 1.117714524269104, "learning_rate": 2.1759211744331514e-05, "loss": 0.45345821380615237, "step": 476060 }, { "epoch": 2.829858943952066, "grad_norm": 1.3187754154205322, "learning_rate": 2.1757987216929446e-05, "loss": 0.3780842304229736, "step": 476070 }, { "epoch": 2.8299183860287345, "grad_norm": 1.1347837448120117, "learning_rate": 2.1756763111648318e-05, "loss": 0.43067612648010256, "step": 476080 }, { "epoch": 2.8299778281054024, "grad_norm": 1.232630729675293, "learning_rate": 2.1755539428494e-05, "loss": 0.4351816177368164, "step": 476090 }, { "epoch": 2.8300372701820713, "grad_norm": 1.813938856124878, "learning_rate": 2.1754316167472356e-05, "loss": 0.4620495796203613, "step": 476100 }, { "epoch": 2.8300967122587393, "grad_norm": 1.2513123750686646, "learning_rate": 2.1753093328589214e-05, "loss": 0.431395435333252, "step": 476110 }, { "epoch": 2.830156154335408, "grad_norm": 1.3364988565444946, "learning_rate": 2.1751870911850438e-05, "loss": 0.4864187240600586, "step": 476120 }, { "epoch": 2.830215596412076, "grad_norm": 1.1041182279586792, "learning_rate": 2.175064891726187e-05, "loss": 0.44718456268310547, "step": 476130 }, { "epoch": 2.8302750384887445, "grad_norm": 1.0570425987243652, "learning_rate": 2.1749427344829362e-05, "loss": 0.4233089923858643, "step": 476140 }, { "epoch": 2.830334480565413, "grad_norm": 1.2059906721115112, "learning_rate": 2.174820619455874e-05, "loss": 0.43264269828796387, "step": 476150 }, { "epoch": 2.8303939226420813, "grad_norm": 1.8108054399490356, "learning_rate": 2.174698546645587e-05, "loss": 0.5101733207702637, "step": 476160 }, { "epoch": 2.8304533647187498, "grad_norm": 1.3760602474212646, "learning_rate": 2.1745765160526572e-05, "loss": 0.4757406234741211, "step": 476170 }, { "epoch": 2.830512806795418, "grad_norm": 1.3836718797683716, "learning_rate": 2.1744545276776707e-05, "loss": 0.467362117767334, "step": 476180 }, { "epoch": 2.8305722488720866, "grad_norm": 1.0776453018188477, "learning_rate": 2.174332581521208e-05, "loss": 0.4687982082366943, "step": 476190 }, { "epoch": 2.830631690948755, "grad_norm": 1.2468693256378174, "learning_rate": 2.1742106775838543e-05, "loss": 0.4833033561706543, "step": 476200 }, { "epoch": 2.8306911330254234, "grad_norm": 1.3074264526367188, "learning_rate": 2.1740888158661927e-05, "loss": 0.4885965347290039, "step": 476210 }, { "epoch": 2.830750575102092, "grad_norm": 1.0968234539031982, "learning_rate": 2.1739669963688063e-05, "loss": 0.451122522354126, "step": 476220 }, { "epoch": 2.8308100171787602, "grad_norm": 1.0761322975158691, "learning_rate": 2.1738452190922765e-05, "loss": 0.49502248764038087, "step": 476230 }, { "epoch": 2.8308694592554287, "grad_norm": 1.6682201623916626, "learning_rate": 2.173723484037187e-05, "loss": 0.47215991020202636, "step": 476240 }, { "epoch": 2.830928901332097, "grad_norm": 0.8435778021812439, "learning_rate": 2.1736017912041204e-05, "loss": 0.4416947364807129, "step": 476250 }, { "epoch": 2.8309883434087655, "grad_norm": 1.3122563362121582, "learning_rate": 2.1734801405936583e-05, "loss": 0.45734119415283203, "step": 476260 }, { "epoch": 2.831047785485434, "grad_norm": 1.625362753868103, "learning_rate": 2.173358532206382e-05, "loss": 0.4506803035736084, "step": 476270 }, { "epoch": 2.831107227562102, "grad_norm": 1.2385090589523315, "learning_rate": 2.1732369660428737e-05, "loss": 0.4638941764831543, "step": 476280 }, { "epoch": 2.8311666696387707, "grad_norm": 1.3250560760498047, "learning_rate": 2.1731154421037158e-05, "loss": 0.4549161434173584, "step": 476290 }, { "epoch": 2.8312261117154387, "grad_norm": 1.584417462348938, "learning_rate": 2.1729939603894888e-05, "loss": 0.4554886817932129, "step": 476300 }, { "epoch": 2.8312855537921076, "grad_norm": 1.410483717918396, "learning_rate": 2.1728725209007737e-05, "loss": 0.4342014312744141, "step": 476310 }, { "epoch": 2.8313449958687755, "grad_norm": 1.6249340772628784, "learning_rate": 2.1727511236381524e-05, "loss": 0.48978252410888673, "step": 476320 }, { "epoch": 2.831404437945444, "grad_norm": 1.2932795286178589, "learning_rate": 2.172629768602205e-05, "loss": 0.40960845947265623, "step": 476330 }, { "epoch": 2.8314638800221124, "grad_norm": 1.531840205192566, "learning_rate": 2.1725084557935106e-05, "loss": 0.47824945449829104, "step": 476340 }, { "epoch": 2.8315233220987808, "grad_norm": 1.01600182056427, "learning_rate": 2.1723871852126523e-05, "loss": 0.41313953399658204, "step": 476350 }, { "epoch": 2.831582764175449, "grad_norm": 1.3004900217056274, "learning_rate": 2.172265956860209e-05, "loss": 0.45869836807250974, "step": 476360 }, { "epoch": 2.8316422062521176, "grad_norm": 1.5908195972442627, "learning_rate": 2.1721447707367596e-05, "loss": 0.4586617469787598, "step": 476370 }, { "epoch": 2.831701648328786, "grad_norm": 1.1403213739395142, "learning_rate": 2.1720236268428852e-05, "loss": 0.4470066070556641, "step": 476380 }, { "epoch": 2.8317610904054544, "grad_norm": 1.1182351112365723, "learning_rate": 2.171902525179164e-05, "loss": 0.45433712005615234, "step": 476390 }, { "epoch": 2.831820532482123, "grad_norm": 1.2213529348373413, "learning_rate": 2.171781465746177e-05, "loss": 0.49596405029296875, "step": 476400 }, { "epoch": 2.8318799745587913, "grad_norm": 1.3797142505645752, "learning_rate": 2.1716604485445013e-05, "loss": 0.4628045082092285, "step": 476410 }, { "epoch": 2.8319394166354597, "grad_norm": 1.1928939819335938, "learning_rate": 2.1715394735747166e-05, "loss": 0.4840856552124023, "step": 476420 }, { "epoch": 2.831998858712128, "grad_norm": 1.3016469478607178, "learning_rate": 2.1714185408374044e-05, "loss": 0.4630826473236084, "step": 476430 }, { "epoch": 2.8320583007887965, "grad_norm": 1.1828017234802246, "learning_rate": 2.1712976503331383e-05, "loss": 0.47420520782470704, "step": 476440 }, { "epoch": 2.8321177428654645, "grad_norm": 1.3816711902618408, "learning_rate": 2.1711768020625e-05, "loss": 0.4194484710693359, "step": 476450 }, { "epoch": 2.8321771849421333, "grad_norm": 1.0852296352386475, "learning_rate": 2.1710559960260655e-05, "loss": 0.4536449909210205, "step": 476460 }, { "epoch": 2.8322366270188013, "grad_norm": 1.5040886402130127, "learning_rate": 2.170935232224415e-05, "loss": 0.4274605274200439, "step": 476470 }, { "epoch": 2.83229606909547, "grad_norm": 1.3742878437042236, "learning_rate": 2.170814510658124e-05, "loss": 0.48958473205566405, "step": 476480 }, { "epoch": 2.832355511172138, "grad_norm": 1.5600533485412598, "learning_rate": 2.1706938313277725e-05, "loss": 0.4720651626586914, "step": 476490 }, { "epoch": 2.8324149532488065, "grad_norm": 0.9426327347755432, "learning_rate": 2.170573194233935e-05, "loss": 0.4432659149169922, "step": 476500 }, { "epoch": 2.832474395325475, "grad_norm": 1.649688959121704, "learning_rate": 2.1704525993771892e-05, "loss": 0.45471906661987305, "step": 476510 }, { "epoch": 2.8325338374021434, "grad_norm": 1.4320653676986694, "learning_rate": 2.170332046758114e-05, "loss": 0.4830023765563965, "step": 476520 }, { "epoch": 2.832593279478812, "grad_norm": 1.5114306211471558, "learning_rate": 2.1702115363772846e-05, "loss": 0.44503040313720704, "step": 476530 }, { "epoch": 2.83265272155548, "grad_norm": 1.1959640979766846, "learning_rate": 2.1700910682352776e-05, "loss": 0.44772796630859374, "step": 476540 }, { "epoch": 2.8327121636321486, "grad_norm": 1.6152732372283936, "learning_rate": 2.169970642332669e-05, "loss": 0.4951263427734375, "step": 476550 }, { "epoch": 2.832771605708817, "grad_norm": 1.1736990213394165, "learning_rate": 2.1698502586700354e-05, "loss": 0.4418140411376953, "step": 476560 }, { "epoch": 2.8328310477854854, "grad_norm": 1.5667545795440674, "learning_rate": 2.1697299172479507e-05, "loss": 0.4815112590789795, "step": 476570 }, { "epoch": 2.832890489862154, "grad_norm": 1.2990821599960327, "learning_rate": 2.169609618066994e-05, "loss": 0.47580876350402834, "step": 476580 }, { "epoch": 2.8329499319388223, "grad_norm": 1.2988758087158203, "learning_rate": 2.1694893611277395e-05, "loss": 0.4790159225463867, "step": 476590 }, { "epoch": 2.8330093740154907, "grad_norm": 1.519158124923706, "learning_rate": 2.1693691464307613e-05, "loss": 0.5014204978942871, "step": 476600 }, { "epoch": 2.833068816092159, "grad_norm": 1.3329331874847412, "learning_rate": 2.1692489739766354e-05, "loss": 0.4531232833862305, "step": 476610 }, { "epoch": 2.8331282581688275, "grad_norm": 1.6359246969223022, "learning_rate": 2.1691288437659366e-05, "loss": 0.43329501152038574, "step": 476620 }, { "epoch": 2.833187700245496, "grad_norm": 1.2551804780960083, "learning_rate": 2.169008755799239e-05, "loss": 0.4611567497253418, "step": 476630 }, { "epoch": 2.833247142322164, "grad_norm": 1.190454363822937, "learning_rate": 2.168888710077117e-05, "loss": 0.4495635986328125, "step": 476640 }, { "epoch": 2.8333065843988328, "grad_norm": 1.3183363676071167, "learning_rate": 2.1687687066001465e-05, "loss": 0.4899445533752441, "step": 476650 }, { "epoch": 2.8333660264755007, "grad_norm": 1.4198399782180786, "learning_rate": 2.1686487453689e-05, "loss": 0.5266031265258789, "step": 476660 }, { "epoch": 2.8334254685521696, "grad_norm": 1.367131233215332, "learning_rate": 2.168528826383952e-05, "loss": 0.4331235885620117, "step": 476670 }, { "epoch": 2.8334849106288376, "grad_norm": 1.3776748180389404, "learning_rate": 2.1684089496458758e-05, "loss": 0.4602532863616943, "step": 476680 }, { "epoch": 2.833544352705506, "grad_norm": 1.7187379598617554, "learning_rate": 2.168289115155245e-05, "loss": 0.4953147888183594, "step": 476690 }, { "epoch": 2.8336037947821744, "grad_norm": 1.2523409128189087, "learning_rate": 2.1681693229126326e-05, "loss": 0.44492640495300295, "step": 476700 }, { "epoch": 2.833663236858843, "grad_norm": 1.1929950714111328, "learning_rate": 2.1680495729186117e-05, "loss": 0.5180270195007324, "step": 476710 }, { "epoch": 2.833722678935511, "grad_norm": 1.6137572526931763, "learning_rate": 2.167929865173756e-05, "loss": 0.45115861892700193, "step": 476720 }, { "epoch": 2.8337821210121796, "grad_norm": 1.4524848461151123, "learning_rate": 2.167810199678638e-05, "loss": 0.45512142181396487, "step": 476730 }, { "epoch": 2.833841563088848, "grad_norm": 1.0585347414016724, "learning_rate": 2.1676905764338286e-05, "loss": 0.4042679786682129, "step": 476740 }, { "epoch": 2.8339010051655165, "grad_norm": 1.5005567073822021, "learning_rate": 2.1675709954399016e-05, "loss": 0.42373032569885255, "step": 476750 }, { "epoch": 2.833960447242185, "grad_norm": 1.4523844718933105, "learning_rate": 2.167451456697428e-05, "loss": 0.4746528625488281, "step": 476760 }, { "epoch": 2.8340198893188533, "grad_norm": 1.100338101387024, "learning_rate": 2.16733196020698e-05, "loss": 0.4099161148071289, "step": 476770 }, { "epoch": 2.8340793313955217, "grad_norm": 1.2330193519592285, "learning_rate": 2.1672125059691297e-05, "loss": 0.4393270969390869, "step": 476780 }, { "epoch": 2.83413877347219, "grad_norm": 1.4750920534133911, "learning_rate": 2.1670930939844483e-05, "loss": 0.4725243091583252, "step": 476790 }, { "epoch": 2.8341982155488585, "grad_norm": 1.3412755727767944, "learning_rate": 2.1669737242535065e-05, "loss": 0.4552490711212158, "step": 476800 }, { "epoch": 2.834257657625527, "grad_norm": 1.4951473474502563, "learning_rate": 2.1668543967768758e-05, "loss": 0.45208263397216797, "step": 476810 }, { "epoch": 2.8343170997021954, "grad_norm": 1.3321462869644165, "learning_rate": 2.1667351115551277e-05, "loss": 0.43080615997314453, "step": 476820 }, { "epoch": 2.8343765417788633, "grad_norm": 1.6749498844146729, "learning_rate": 2.1666158685888305e-05, "loss": 0.46411933898925783, "step": 476830 }, { "epoch": 2.834435983855532, "grad_norm": 1.5015006065368652, "learning_rate": 2.166496667878557e-05, "loss": 0.4644256591796875, "step": 476840 }, { "epoch": 2.8344954259322, "grad_norm": 1.737137794494629, "learning_rate": 2.166377509424878e-05, "loss": 0.47418813705444335, "step": 476850 }, { "epoch": 2.834554868008869, "grad_norm": 1.3975908756256104, "learning_rate": 2.1662583932283607e-05, "loss": 0.43790063858032224, "step": 476860 }, { "epoch": 2.834614310085537, "grad_norm": 1.1906665563583374, "learning_rate": 2.1661393192895765e-05, "loss": 0.47295846939086916, "step": 476870 }, { "epoch": 2.8346737521622054, "grad_norm": 1.3103395700454712, "learning_rate": 2.1660202876090953e-05, "loss": 0.46999235153198243, "step": 476880 }, { "epoch": 2.834733194238874, "grad_norm": 1.5386570692062378, "learning_rate": 2.1659012981874853e-05, "loss": 0.4582559585571289, "step": 476890 }, { "epoch": 2.8347926363155422, "grad_norm": 1.2644526958465576, "learning_rate": 2.1657823510253167e-05, "loss": 0.4341722011566162, "step": 476900 }, { "epoch": 2.8348520783922107, "grad_norm": 1.2757089138031006, "learning_rate": 2.1656634461231593e-05, "loss": 0.4344953536987305, "step": 476910 }, { "epoch": 2.834911520468879, "grad_norm": 0.9974319934844971, "learning_rate": 2.1655445834815807e-05, "loss": 0.4146108150482178, "step": 476920 }, { "epoch": 2.8349709625455475, "grad_norm": 1.1536412239074707, "learning_rate": 2.165425763101148e-05, "loss": 0.4709324836730957, "step": 476930 }, { "epoch": 2.835030404622216, "grad_norm": 1.9640001058578491, "learning_rate": 2.1653069849824327e-05, "loss": 0.4206681251525879, "step": 476940 }, { "epoch": 2.8350898466988843, "grad_norm": 0.9898751974105835, "learning_rate": 2.1651882491260013e-05, "loss": 0.449429988861084, "step": 476950 }, { "epoch": 2.8351492887755527, "grad_norm": 1.3323357105255127, "learning_rate": 2.1650695555324208e-05, "loss": 0.46619763374328616, "step": 476960 }, { "epoch": 2.835208730852221, "grad_norm": 1.3290363550186157, "learning_rate": 2.1649509042022617e-05, "loss": 0.477069091796875, "step": 476970 }, { "epoch": 2.8352681729288896, "grad_norm": 1.2752656936645508, "learning_rate": 2.1648322951360912e-05, "loss": 0.4349347114562988, "step": 476980 }, { "epoch": 2.835327615005558, "grad_norm": 1.3038640022277832, "learning_rate": 2.164713728334474e-05, "loss": 0.47052793502807616, "step": 476990 }, { "epoch": 2.8353870570822264, "grad_norm": 1.2952492237091064, "learning_rate": 2.164595203797979e-05, "loss": 0.4723992347717285, "step": 477000 }, { "epoch": 2.835446499158895, "grad_norm": 1.4500294923782349, "learning_rate": 2.1644767215271732e-05, "loss": 0.4724606513977051, "step": 477010 }, { "epoch": 2.8355059412355628, "grad_norm": 1.643454909324646, "learning_rate": 2.1643582815226235e-05, "loss": 0.49799089431762694, "step": 477020 }, { "epoch": 2.8355653833122316, "grad_norm": 1.2609937191009521, "learning_rate": 2.1642398837848954e-05, "loss": 0.47419562339782717, "step": 477030 }, { "epoch": 2.8356248253888996, "grad_norm": 1.0243669748306274, "learning_rate": 2.1641215283145584e-05, "loss": 0.43475914001464844, "step": 477040 }, { "epoch": 2.8356842674655685, "grad_norm": 0.9645618200302124, "learning_rate": 2.164003215112175e-05, "loss": 0.421647834777832, "step": 477050 }, { "epoch": 2.8357437095422364, "grad_norm": 1.2853484153747559, "learning_rate": 2.1638849441783116e-05, "loss": 0.3948704242706299, "step": 477060 }, { "epoch": 2.835803151618905, "grad_norm": 1.2911317348480225, "learning_rate": 2.163766715513536e-05, "loss": 0.4114240646362305, "step": 477070 }, { "epoch": 2.8358625936955733, "grad_norm": 1.7030696868896484, "learning_rate": 2.1636485291184128e-05, "loss": 0.47369070053100587, "step": 477080 }, { "epoch": 2.8359220357722417, "grad_norm": 1.1549077033996582, "learning_rate": 2.1635303849935066e-05, "loss": 0.5015475749969482, "step": 477090 }, { "epoch": 2.83598147784891, "grad_norm": 1.2769479751586914, "learning_rate": 2.163412283139384e-05, "loss": 0.4521651744842529, "step": 477100 }, { "epoch": 2.8360409199255785, "grad_norm": 1.1371179819107056, "learning_rate": 2.1632942235566092e-05, "loss": 0.4743986129760742, "step": 477110 }, { "epoch": 2.836100362002247, "grad_norm": 1.6235535144805908, "learning_rate": 2.1631762062457473e-05, "loss": 0.5199941158294678, "step": 477120 }, { "epoch": 2.8361598040789153, "grad_norm": 1.530829906463623, "learning_rate": 2.163058231207361e-05, "loss": 0.4496877670288086, "step": 477130 }, { "epoch": 2.8362192461555837, "grad_norm": 1.110033392906189, "learning_rate": 2.162940298442018e-05, "loss": 0.4711006164550781, "step": 477140 }, { "epoch": 2.836278688232252, "grad_norm": 1.4144577980041504, "learning_rate": 2.162822407950279e-05, "loss": 0.4879878044128418, "step": 477150 }, { "epoch": 2.8363381303089206, "grad_norm": 1.279625415802002, "learning_rate": 2.1627045597327104e-05, "loss": 0.4508537292480469, "step": 477160 }, { "epoch": 2.836397572385589, "grad_norm": 1.4972871541976929, "learning_rate": 2.1625867537898755e-05, "loss": 0.47417402267456055, "step": 477170 }, { "epoch": 2.8364570144622574, "grad_norm": 1.156540036201477, "learning_rate": 2.162468990122337e-05, "loss": 0.4458174705505371, "step": 477180 }, { "epoch": 2.8365164565389254, "grad_norm": 1.549889087677002, "learning_rate": 2.1623512687306582e-05, "loss": 0.515306043624878, "step": 477190 }, { "epoch": 2.8365758986155942, "grad_norm": 1.2243057489395142, "learning_rate": 2.1622335896154038e-05, "loss": 0.46404061317443845, "step": 477200 }, { "epoch": 2.836635340692262, "grad_norm": 1.2744053602218628, "learning_rate": 2.1621159527771342e-05, "loss": 0.48709869384765625, "step": 477210 }, { "epoch": 2.836694782768931, "grad_norm": 0.9538394212722778, "learning_rate": 2.1619983582164152e-05, "loss": 0.4118062973022461, "step": 477220 }, { "epoch": 2.836754224845599, "grad_norm": 1.3276878595352173, "learning_rate": 2.1618808059338072e-05, "loss": 0.4691641807556152, "step": 477230 }, { "epoch": 2.8368136669222674, "grad_norm": 1.5829787254333496, "learning_rate": 2.161763295929874e-05, "loss": 0.5024674892425537, "step": 477240 }, { "epoch": 2.836873108998936, "grad_norm": 1.5760328769683838, "learning_rate": 2.1616458282051753e-05, "loss": 0.5222353935241699, "step": 477250 }, { "epoch": 2.8369325510756043, "grad_norm": 1.5885357856750488, "learning_rate": 2.1615284027602746e-05, "loss": 0.43986940383911133, "step": 477260 }, { "epoch": 2.8369919931522727, "grad_norm": 1.1547152996063232, "learning_rate": 2.1614110195957343e-05, "loss": 0.4363719940185547, "step": 477270 }, { "epoch": 2.837051435228941, "grad_norm": 0.9130276441574097, "learning_rate": 2.1612936787121148e-05, "loss": 0.4258290767669678, "step": 477280 }, { "epoch": 2.8371108773056095, "grad_norm": 1.261832356452942, "learning_rate": 2.161176380109978e-05, "loss": 0.4252635955810547, "step": 477290 }, { "epoch": 2.837170319382278, "grad_norm": 1.159458041191101, "learning_rate": 2.1610591237898858e-05, "loss": 0.43213481903076173, "step": 477300 }, { "epoch": 2.8372297614589463, "grad_norm": 1.5728579759597778, "learning_rate": 2.1609419097523967e-05, "loss": 0.4548074722290039, "step": 477310 }, { "epoch": 2.8372892035356148, "grad_norm": 1.2185059785842896, "learning_rate": 2.1608247379980724e-05, "loss": 0.49686408042907715, "step": 477320 }, { "epoch": 2.837348645612283, "grad_norm": 1.4207903146743774, "learning_rate": 2.1607076085274757e-05, "loss": 0.42650618553161623, "step": 477330 }, { "epoch": 2.8374080876889516, "grad_norm": 1.1292496919631958, "learning_rate": 2.160590521341164e-05, "loss": 0.4720598697662354, "step": 477340 }, { "epoch": 2.83746752976562, "grad_norm": 1.4244027137756348, "learning_rate": 2.1604734764396995e-05, "loss": 0.4291866302490234, "step": 477350 }, { "epoch": 2.8375269718422884, "grad_norm": 1.414025902748108, "learning_rate": 2.16035647382364e-05, "loss": 0.4845569610595703, "step": 477360 }, { "epoch": 2.837586413918957, "grad_norm": 1.0843669176101685, "learning_rate": 2.1602395134935467e-05, "loss": 0.46558871269226076, "step": 477370 }, { "epoch": 2.837645855995625, "grad_norm": 1.5277167558670044, "learning_rate": 2.160122595449979e-05, "loss": 0.4710810661315918, "step": 477380 }, { "epoch": 2.8377052980722937, "grad_norm": 1.2256271839141846, "learning_rate": 2.160005719693495e-05, "loss": 0.4693032741546631, "step": 477390 }, { "epoch": 2.8377647401489616, "grad_norm": 1.0732566118240356, "learning_rate": 2.1598888862246555e-05, "loss": 0.3847970485687256, "step": 477400 }, { "epoch": 2.8378241822256305, "grad_norm": 1.4774187803268433, "learning_rate": 2.159772095044019e-05, "loss": 0.4383668899536133, "step": 477410 }, { "epoch": 2.8378836243022985, "grad_norm": 1.1826940774917603, "learning_rate": 2.159655346152142e-05, "loss": 0.4990066051483154, "step": 477420 }, { "epoch": 2.837943066378967, "grad_norm": 1.1153826713562012, "learning_rate": 2.159538639549586e-05, "loss": 0.3889544248580933, "step": 477430 }, { "epoch": 2.8380025084556353, "grad_norm": 1.3050497770309448, "learning_rate": 2.1594219752369086e-05, "loss": 0.4902451992034912, "step": 477440 }, { "epoch": 2.8380619505323037, "grad_norm": 1.050915002822876, "learning_rate": 2.1593053532146663e-05, "loss": 0.4867189884185791, "step": 477450 }, { "epoch": 2.838121392608972, "grad_norm": 1.40531325340271, "learning_rate": 2.1591887734834177e-05, "loss": 0.4512634754180908, "step": 477460 }, { "epoch": 2.8381808346856405, "grad_norm": 1.5413906574249268, "learning_rate": 2.1590722360437225e-05, "loss": 0.46452670097351073, "step": 477470 }, { "epoch": 2.838240276762309, "grad_norm": 1.500588059425354, "learning_rate": 2.1589557408961357e-05, "loss": 0.4443406105041504, "step": 477480 }, { "epoch": 2.8382997188389774, "grad_norm": 1.2922685146331787, "learning_rate": 2.1588392880412147e-05, "loss": 0.4126731872558594, "step": 477490 }, { "epoch": 2.8383591609156458, "grad_norm": 0.9075441360473633, "learning_rate": 2.1587228774795178e-05, "loss": 0.40255060195922854, "step": 477500 }, { "epoch": 2.838418602992314, "grad_norm": 1.2700568437576294, "learning_rate": 2.158606509211601e-05, "loss": 0.47613821029663084, "step": 477510 }, { "epoch": 2.8384780450689826, "grad_norm": 1.3012847900390625, "learning_rate": 2.1584901832380212e-05, "loss": 0.4136373043060303, "step": 477520 }, { "epoch": 2.838537487145651, "grad_norm": 1.2148922681808472, "learning_rate": 2.158373899559336e-05, "loss": 0.452454662322998, "step": 477530 }, { "epoch": 2.8385969292223194, "grad_norm": 1.2525323629379272, "learning_rate": 2.158257658176099e-05, "loss": 0.4351199150085449, "step": 477540 }, { "epoch": 2.838656371298988, "grad_norm": 1.1754192113876343, "learning_rate": 2.1581414590888688e-05, "loss": 0.4213930606842041, "step": 477550 }, { "epoch": 2.8387158133756563, "grad_norm": 1.1137757301330566, "learning_rate": 2.1580253022981998e-05, "loss": 0.4301823616027832, "step": 477560 }, { "epoch": 2.8387752554523242, "grad_norm": 1.4813663959503174, "learning_rate": 2.1579091878046486e-05, "loss": 0.46157402992248536, "step": 477570 }, { "epoch": 2.838834697528993, "grad_norm": 1.9086713790893555, "learning_rate": 2.1577931156087698e-05, "loss": 0.4214797019958496, "step": 477580 }, { "epoch": 2.838894139605661, "grad_norm": 1.5458979606628418, "learning_rate": 2.1576770857111197e-05, "loss": 0.48137874603271485, "step": 477590 }, { "epoch": 2.83895358168233, "grad_norm": 1.137879729270935, "learning_rate": 2.1575610981122523e-05, "loss": 0.4949549674987793, "step": 477600 }, { "epoch": 2.839013023758998, "grad_norm": 1.5068166255950928, "learning_rate": 2.157445152812723e-05, "loss": 0.4488378524780273, "step": 477610 }, { "epoch": 2.8390724658356663, "grad_norm": 1.8583837747573853, "learning_rate": 2.157329249813086e-05, "loss": 0.5415577411651611, "step": 477620 }, { "epoch": 2.8391319079123347, "grad_norm": 1.3623695373535156, "learning_rate": 2.1572133891138966e-05, "loss": 0.4461977481842041, "step": 477630 }, { "epoch": 2.839191349989003, "grad_norm": 1.095945119857788, "learning_rate": 2.1570975707157076e-05, "loss": 0.5148974895477295, "step": 477640 }, { "epoch": 2.8392507920656715, "grad_norm": 1.4133137464523315, "learning_rate": 2.156981794619075e-05, "loss": 0.4943901538848877, "step": 477650 }, { "epoch": 2.83931023414234, "grad_norm": 0.9002841711044312, "learning_rate": 2.156866060824551e-05, "loss": 0.4258707046508789, "step": 477660 }, { "epoch": 2.8393696762190084, "grad_norm": 1.1163254976272583, "learning_rate": 2.1567503693326904e-05, "loss": 0.45382161140441896, "step": 477670 }, { "epoch": 2.839429118295677, "grad_norm": 1.287711501121521, "learning_rate": 2.156634720144045e-05, "loss": 0.469939661026001, "step": 477680 }, { "epoch": 2.839488560372345, "grad_norm": 0.9774751663208008, "learning_rate": 2.1565191132591685e-05, "loss": 0.46680703163146975, "step": 477690 }, { "epoch": 2.8395480024490136, "grad_norm": 1.3613862991333008, "learning_rate": 2.1564035486786167e-05, "loss": 0.4239603042602539, "step": 477700 }, { "epoch": 2.839607444525682, "grad_norm": 0.9499058127403259, "learning_rate": 2.156288026402939e-05, "loss": 0.47053003311157227, "step": 477710 }, { "epoch": 2.8396668866023504, "grad_norm": 1.3630268573760986, "learning_rate": 2.1561725464326886e-05, "loss": 0.4845764636993408, "step": 477720 }, { "epoch": 2.839726328679019, "grad_norm": 1.0312440395355225, "learning_rate": 2.1560571087684192e-05, "loss": 0.4684617042541504, "step": 477730 }, { "epoch": 2.8397857707556873, "grad_norm": 1.2073984146118164, "learning_rate": 2.155941713410683e-05, "loss": 0.4517484188079834, "step": 477740 }, { "epoch": 2.8398452128323557, "grad_norm": 1.4459201097488403, "learning_rate": 2.1558263603600305e-05, "loss": 0.4616688251495361, "step": 477750 }, { "epoch": 2.8399046549090237, "grad_norm": 1.4685331583023071, "learning_rate": 2.1557110496170143e-05, "loss": 0.4608765602111816, "step": 477760 }, { "epoch": 2.8399640969856925, "grad_norm": 1.2997772693634033, "learning_rate": 2.1555957811821863e-05, "loss": 0.4896858692169189, "step": 477770 }, { "epoch": 2.8400235390623605, "grad_norm": 1.0322023630142212, "learning_rate": 2.1554805550560976e-05, "loss": 0.4777833461761475, "step": 477780 }, { "epoch": 2.8400829811390294, "grad_norm": 1.2705104351043701, "learning_rate": 2.1553653712393003e-05, "loss": 0.4315927505493164, "step": 477790 }, { "epoch": 2.8401424232156973, "grad_norm": 1.1945767402648926, "learning_rate": 2.1552502297323445e-05, "loss": 0.44310941696166994, "step": 477800 }, { "epoch": 2.8402018652923657, "grad_norm": 1.4069468975067139, "learning_rate": 2.1551351305357794e-05, "loss": 0.43827457427978517, "step": 477810 }, { "epoch": 2.840261307369034, "grad_norm": 1.2681021690368652, "learning_rate": 2.1550200736501584e-05, "loss": 0.4618045806884766, "step": 477820 }, { "epoch": 2.8403207494457026, "grad_norm": 1.6868034601211548, "learning_rate": 2.154905059076032e-05, "loss": 0.4659700870513916, "step": 477830 }, { "epoch": 2.840380191522371, "grad_norm": 1.6588778495788574, "learning_rate": 2.154790086813948e-05, "loss": 0.4452971458435059, "step": 477840 }, { "epoch": 2.8404396335990394, "grad_norm": 1.3046237230300903, "learning_rate": 2.1546751568644576e-05, "loss": 0.4675894737243652, "step": 477850 }, { "epoch": 2.840499075675708, "grad_norm": 1.2769242525100708, "learning_rate": 2.1545602692281103e-05, "loss": 0.4524860382080078, "step": 477860 }, { "epoch": 2.840558517752376, "grad_norm": 1.04584538936615, "learning_rate": 2.1544454239054566e-05, "loss": 0.519139575958252, "step": 477870 }, { "epoch": 2.8406179598290446, "grad_norm": 1.0101885795593262, "learning_rate": 2.154330620897045e-05, "loss": 0.4217654228210449, "step": 477880 }, { "epoch": 2.840677401905713, "grad_norm": 1.3957383632659912, "learning_rate": 2.1542158602034248e-05, "loss": 0.4758298397064209, "step": 477890 }, { "epoch": 2.8407368439823815, "grad_norm": 1.3309580087661743, "learning_rate": 2.1541011418251462e-05, "loss": 0.5110857963562012, "step": 477900 }, { "epoch": 2.84079628605905, "grad_norm": 1.503559947013855, "learning_rate": 2.1539864657627553e-05, "loss": 0.4719792366027832, "step": 477910 }, { "epoch": 2.8408557281357183, "grad_norm": 1.1956442594528198, "learning_rate": 2.1538718320168022e-05, "loss": 0.44052691459655763, "step": 477920 }, { "epoch": 2.8409151702123863, "grad_norm": 1.2985128164291382, "learning_rate": 2.1537572405878356e-05, "loss": 0.4978771686553955, "step": 477930 }, { "epoch": 2.840974612289055, "grad_norm": 1.3344920873641968, "learning_rate": 2.1536426914764033e-05, "loss": 0.4537909507751465, "step": 477940 }, { "epoch": 2.841034054365723, "grad_norm": 1.5979406833648682, "learning_rate": 2.1535281846830542e-05, "loss": 0.5121051788330078, "step": 477950 }, { "epoch": 2.841093496442392, "grad_norm": 1.2401260137557983, "learning_rate": 2.1534137202083354e-05, "loss": 0.45171117782592773, "step": 477960 }, { "epoch": 2.84115293851906, "grad_norm": 1.262139916419983, "learning_rate": 2.1532992980527932e-05, "loss": 0.4788257598876953, "step": 477970 }, { "epoch": 2.8412123805957283, "grad_norm": 1.6340266466140747, "learning_rate": 2.153184918216976e-05, "loss": 0.4398649215698242, "step": 477980 }, { "epoch": 2.8412718226723968, "grad_norm": 1.3282561302185059, "learning_rate": 2.1530705807014307e-05, "loss": 0.49144682884216306, "step": 477990 }, { "epoch": 2.841331264749065, "grad_norm": 1.3970518112182617, "learning_rate": 2.1529562855067062e-05, "loss": 0.45585098266601565, "step": 478000 }, { "epoch": 2.8413907068257336, "grad_norm": 1.3565047979354858, "learning_rate": 2.152842032633346e-05, "loss": 0.46641969680786133, "step": 478010 }, { "epoch": 2.841450148902402, "grad_norm": 1.1229140758514404, "learning_rate": 2.1527278220818985e-05, "loss": 0.4411163330078125, "step": 478020 }, { "epoch": 2.8415095909790704, "grad_norm": 1.1163955926895142, "learning_rate": 2.152613653852911e-05, "loss": 0.5003939628601074, "step": 478030 }, { "epoch": 2.841569033055739, "grad_norm": 1.605178952217102, "learning_rate": 2.1524995279469266e-05, "loss": 0.5012869358062744, "step": 478040 }, { "epoch": 2.8416284751324072, "grad_norm": 1.1439337730407715, "learning_rate": 2.1523854443644944e-05, "loss": 0.4276407241821289, "step": 478050 }, { "epoch": 2.8416879172090757, "grad_norm": 1.4960250854492188, "learning_rate": 2.1522714031061577e-05, "loss": 0.47998361587524413, "step": 478060 }, { "epoch": 2.841747359285744, "grad_norm": 1.4825055599212646, "learning_rate": 2.152157404172464e-05, "loss": 0.45996732711791993, "step": 478070 }, { "epoch": 2.8418068013624125, "grad_norm": 1.1098393201828003, "learning_rate": 2.1520434475639582e-05, "loss": 0.44189839363098143, "step": 478080 }, { "epoch": 2.841866243439081, "grad_norm": 1.083608627319336, "learning_rate": 2.1519295332811848e-05, "loss": 0.4199060916900635, "step": 478090 }, { "epoch": 2.8419256855157493, "grad_norm": 1.2536369562149048, "learning_rate": 2.1518156613246887e-05, "loss": 0.4281009674072266, "step": 478100 }, { "epoch": 2.8419851275924177, "grad_norm": 1.3976682424545288, "learning_rate": 2.1517018316950137e-05, "loss": 0.46820697784423826, "step": 478110 }, { "epoch": 2.8420445696690857, "grad_norm": 1.2772555351257324, "learning_rate": 2.151588044392706e-05, "loss": 0.4762128829956055, "step": 478120 }, { "epoch": 2.8421040117457546, "grad_norm": 1.5023075342178345, "learning_rate": 2.1514742994183106e-05, "loss": 0.49655590057373045, "step": 478130 }, { "epoch": 2.8421634538224225, "grad_norm": 1.0034418106079102, "learning_rate": 2.151360596772369e-05, "loss": 0.47023963928222656, "step": 478140 }, { "epoch": 2.8422228958990914, "grad_norm": 1.4419454336166382, "learning_rate": 2.1512469364554276e-05, "loss": 0.42206544876098634, "step": 478150 }, { "epoch": 2.8422823379757594, "grad_norm": 1.2577084302902222, "learning_rate": 2.1511333184680286e-05, "loss": 0.45449342727661135, "step": 478160 }, { "epoch": 2.8423417800524278, "grad_norm": 1.5637749433517456, "learning_rate": 2.1510197428107153e-05, "loss": 0.45960378646850586, "step": 478170 }, { "epoch": 2.842401222129096, "grad_norm": 1.2410533428192139, "learning_rate": 2.1509062094840327e-05, "loss": 0.44360666275024413, "step": 478180 }, { "epoch": 2.8424606642057646, "grad_norm": 1.0469555854797363, "learning_rate": 2.150792718488523e-05, "loss": 0.4294104099273682, "step": 478190 }, { "epoch": 2.842520106282433, "grad_norm": 1.0109894275665283, "learning_rate": 2.1506792698247287e-05, "loss": 0.4541622161865234, "step": 478200 }, { "epoch": 2.8425795483591014, "grad_norm": 1.418752908706665, "learning_rate": 2.1505658634931925e-05, "loss": 0.4837949752807617, "step": 478210 }, { "epoch": 2.84263899043577, "grad_norm": 1.2545398473739624, "learning_rate": 2.150452499494457e-05, "loss": 0.4530510902404785, "step": 478220 }, { "epoch": 2.8426984325124383, "grad_norm": 1.0792192220687866, "learning_rate": 2.1503391778290654e-05, "loss": 0.44829597473144533, "step": 478230 }, { "epoch": 2.8427578745891067, "grad_norm": 1.4783742427825928, "learning_rate": 2.1502258984975584e-05, "loss": 0.4540554046630859, "step": 478240 }, { "epoch": 2.842817316665775, "grad_norm": 1.3442927598953247, "learning_rate": 2.1501126615004786e-05, "loss": 0.523319149017334, "step": 478250 }, { "epoch": 2.8428767587424435, "grad_norm": 1.1830544471740723, "learning_rate": 2.1499994668383678e-05, "loss": 0.4509130954742432, "step": 478260 }, { "epoch": 2.842936200819112, "grad_norm": 1.6370071172714233, "learning_rate": 2.1498863145117673e-05, "loss": 0.5062602043151856, "step": 478270 }, { "epoch": 2.8429956428957803, "grad_norm": 1.149612307548523, "learning_rate": 2.1497732045212196e-05, "loss": 0.5128532409667969, "step": 478280 }, { "epoch": 2.8430550849724487, "grad_norm": 1.3517975807189941, "learning_rate": 2.149660136867263e-05, "loss": 0.458710765838623, "step": 478290 }, { "epoch": 2.843114527049117, "grad_norm": 1.321340560913086, "learning_rate": 2.14954711155044e-05, "loss": 0.4737208366394043, "step": 478300 }, { "epoch": 2.843173969125785, "grad_norm": 1.717641830444336, "learning_rate": 2.1494341285712918e-05, "loss": 0.4557461738586426, "step": 478310 }, { "epoch": 2.843233411202454, "grad_norm": 1.010210633277893, "learning_rate": 2.149321187930358e-05, "loss": 0.4622836112976074, "step": 478320 }, { "epoch": 2.843292853279122, "grad_norm": 1.1940476894378662, "learning_rate": 2.1492082896281802e-05, "loss": 0.4804119110107422, "step": 478330 }, { "epoch": 2.843352295355791, "grad_norm": 1.361668586730957, "learning_rate": 2.1490954336652963e-05, "loss": 0.4472835063934326, "step": 478340 }, { "epoch": 2.843411737432459, "grad_norm": 1.2981501817703247, "learning_rate": 2.148982620042248e-05, "loss": 0.4698976993560791, "step": 478350 }, { "epoch": 2.843471179509127, "grad_norm": 1.3371938467025757, "learning_rate": 2.148869848759575e-05, "loss": 0.44022860527038576, "step": 478360 }, { "epoch": 2.8435306215857956, "grad_norm": 1.3490880727767944, "learning_rate": 2.148757119817814e-05, "loss": 0.4756014823913574, "step": 478370 }, { "epoch": 2.843590063662464, "grad_norm": 1.499975323677063, "learning_rate": 2.148644433217508e-05, "loss": 0.47318143844604493, "step": 478380 }, { "epoch": 2.8436495057391324, "grad_norm": 1.2756370306015015, "learning_rate": 2.1485317889591937e-05, "loss": 0.4341566562652588, "step": 478390 }, { "epoch": 2.843708947815801, "grad_norm": 1.3677326440811157, "learning_rate": 2.148419187043411e-05, "loss": 0.46224613189697267, "step": 478400 }, { "epoch": 2.8437683898924693, "grad_norm": 1.4389424324035645, "learning_rate": 2.148306627470698e-05, "loss": 0.42749900817871095, "step": 478410 }, { "epoch": 2.8438278319691377, "grad_norm": 1.4977720975875854, "learning_rate": 2.148194110241594e-05, "loss": 0.462933874130249, "step": 478420 }, { "epoch": 2.843887274045806, "grad_norm": 1.1190474033355713, "learning_rate": 2.148081635356635e-05, "loss": 0.4524395942687988, "step": 478430 }, { "epoch": 2.8439467161224745, "grad_norm": 2.022409439086914, "learning_rate": 2.147969202816361e-05, "loss": 0.438963794708252, "step": 478440 }, { "epoch": 2.844006158199143, "grad_norm": 1.076246738433838, "learning_rate": 2.1478568126213107e-05, "loss": 0.422714900970459, "step": 478450 }, { "epoch": 2.8440656002758113, "grad_norm": 1.2787799835205078, "learning_rate": 2.14774446477202e-05, "loss": 0.4513684272766113, "step": 478460 }, { "epoch": 2.8441250423524798, "grad_norm": 1.2619973421096802, "learning_rate": 2.147632159269027e-05, "loss": 0.47613887786865233, "step": 478470 }, { "epoch": 2.844184484429148, "grad_norm": 1.1895288228988647, "learning_rate": 2.1475198961128677e-05, "loss": 0.5340133666992187, "step": 478480 }, { "epoch": 2.8442439265058166, "grad_norm": 1.3766696453094482, "learning_rate": 2.1474076753040807e-05, "loss": 0.4328105926513672, "step": 478490 }, { "epoch": 2.8443033685824846, "grad_norm": 1.1431127786636353, "learning_rate": 2.1472954968432023e-05, "loss": 0.5208207130432129, "step": 478500 }, { "epoch": 2.8443628106591534, "grad_norm": 1.0644826889038086, "learning_rate": 2.14718336073077e-05, "loss": 0.44710192680358884, "step": 478510 }, { "epoch": 2.8444222527358214, "grad_norm": 0.7799113988876343, "learning_rate": 2.1470712669673183e-05, "loss": 0.4567458152770996, "step": 478520 }, { "epoch": 2.8444816948124902, "grad_norm": 1.0576145648956299, "learning_rate": 2.1469592155533853e-05, "loss": 0.4570940971374512, "step": 478530 }, { "epoch": 2.844541136889158, "grad_norm": 1.784435510635376, "learning_rate": 2.146847206489505e-05, "loss": 0.4750316619873047, "step": 478540 }, { "epoch": 2.8446005789658266, "grad_norm": 1.4309312105178833, "learning_rate": 2.146735239776216e-05, "loss": 0.44915142059326174, "step": 478550 }, { "epoch": 2.844660021042495, "grad_norm": 1.0330122709274292, "learning_rate": 2.146623315414051e-05, "loss": 0.4665720462799072, "step": 478560 }, { "epoch": 2.8447194631191635, "grad_norm": 1.2995104789733887, "learning_rate": 2.1465114334035477e-05, "loss": 0.4685695171356201, "step": 478570 }, { "epoch": 2.844778905195832, "grad_norm": 0.7710204124450684, "learning_rate": 2.1463995937452403e-05, "loss": 0.44539427757263184, "step": 478580 }, { "epoch": 2.8448383472725003, "grad_norm": 1.3798118829727173, "learning_rate": 2.1462877964396634e-05, "loss": 0.4932121276855469, "step": 478590 }, { "epoch": 2.8448977893491687, "grad_norm": 1.299248218536377, "learning_rate": 2.1461760414873518e-05, "loss": 0.46880321502685546, "step": 478600 }, { "epoch": 2.844957231425837, "grad_norm": 1.2085736989974976, "learning_rate": 2.1460643288888413e-05, "loss": 0.4545127868652344, "step": 478610 }, { "epoch": 2.8450166735025055, "grad_norm": 1.587174892425537, "learning_rate": 2.1459526586446654e-05, "loss": 0.45267491340637206, "step": 478620 }, { "epoch": 2.845076115579174, "grad_norm": 1.649206519126892, "learning_rate": 2.1458410307553582e-05, "loss": 0.4688842296600342, "step": 478630 }, { "epoch": 2.8451355576558424, "grad_norm": 1.5126452445983887, "learning_rate": 2.1457294452214545e-05, "loss": 0.4718128204345703, "step": 478640 }, { "epoch": 2.8451949997325108, "grad_norm": 1.3549648523330688, "learning_rate": 2.1456179020434875e-05, "loss": 0.45905513763427735, "step": 478650 }, { "epoch": 2.845254441809179, "grad_norm": 1.0704491138458252, "learning_rate": 2.1455064012219896e-05, "loss": 0.47358026504516604, "step": 478660 }, { "epoch": 2.845313883885847, "grad_norm": 1.1011592149734497, "learning_rate": 2.145394942757497e-05, "loss": 0.45812044143676756, "step": 478670 }, { "epoch": 2.845373325962516, "grad_norm": 1.1775513887405396, "learning_rate": 2.1452835266505403e-05, "loss": 0.48496007919311523, "step": 478680 }, { "epoch": 2.845432768039184, "grad_norm": 1.256201148033142, "learning_rate": 2.145172152901654e-05, "loss": 0.3916717290878296, "step": 478690 }, { "epoch": 2.845492210115853, "grad_norm": 1.1866434812545776, "learning_rate": 2.1450608215113703e-05, "loss": 0.42684621810913087, "step": 478700 }, { "epoch": 2.845551652192521, "grad_norm": 1.7458631992340088, "learning_rate": 2.1449495324802215e-05, "loss": 0.48666934967041015, "step": 478710 }, { "epoch": 2.8456110942691892, "grad_norm": 1.2874486446380615, "learning_rate": 2.14483828580874e-05, "loss": 0.3883335113525391, "step": 478720 }, { "epoch": 2.8456705363458576, "grad_norm": 1.3348150253295898, "learning_rate": 2.1447270814974585e-05, "loss": 0.5287659645080567, "step": 478730 }, { "epoch": 2.845729978422526, "grad_norm": 1.5395920276641846, "learning_rate": 2.1446159195469078e-05, "loss": 0.4800938606262207, "step": 478740 }, { "epoch": 2.8457894204991945, "grad_norm": 1.5226855278015137, "learning_rate": 2.144504799957622e-05, "loss": 0.4815515518188477, "step": 478750 }, { "epoch": 2.845848862575863, "grad_norm": 1.3982001543045044, "learning_rate": 2.1443937227301313e-05, "loss": 0.4369896411895752, "step": 478760 }, { "epoch": 2.8459083046525313, "grad_norm": 0.9122715592384338, "learning_rate": 2.144282687864967e-05, "loss": 0.4818402290344238, "step": 478770 }, { "epoch": 2.8459677467291997, "grad_norm": 1.004178524017334, "learning_rate": 2.1441716953626598e-05, "loss": 0.44801950454711914, "step": 478780 }, { "epoch": 2.846027188805868, "grad_norm": 1.2621946334838867, "learning_rate": 2.1440607452237394e-05, "loss": 0.44998607635498045, "step": 478790 }, { "epoch": 2.8460866308825366, "grad_norm": 1.9344217777252197, "learning_rate": 2.1439498374487406e-05, "loss": 0.41575002670288086, "step": 478800 }, { "epoch": 2.846146072959205, "grad_norm": 1.3738857507705688, "learning_rate": 2.143838972038191e-05, "loss": 0.48401632308959963, "step": 478810 }, { "epoch": 2.8462055150358734, "grad_norm": 1.44490647315979, "learning_rate": 2.1437281489926212e-05, "loss": 0.49473843574523924, "step": 478820 }, { "epoch": 2.846264957112542, "grad_norm": 1.7717736959457397, "learning_rate": 2.1436173683125617e-05, "loss": 0.4564323425292969, "step": 478830 }, { "epoch": 2.84632439918921, "grad_norm": 1.4077670574188232, "learning_rate": 2.143506629998543e-05, "loss": 0.5153609275817871, "step": 478840 }, { "epoch": 2.8463838412658786, "grad_norm": 1.7864882946014404, "learning_rate": 2.143395934051094e-05, "loss": 0.4719722270965576, "step": 478850 }, { "epoch": 2.8464432833425466, "grad_norm": 1.374310851097107, "learning_rate": 2.143285280470743e-05, "loss": 0.46387405395507814, "step": 478860 }, { "epoch": 2.8465027254192155, "grad_norm": 1.282340168952942, "learning_rate": 2.1431746692580222e-05, "loss": 0.45808563232421873, "step": 478870 }, { "epoch": 2.8465621674958834, "grad_norm": 1.4065676927566528, "learning_rate": 2.1430641004134598e-05, "loss": 0.48685531616210936, "step": 478880 }, { "epoch": 2.8466216095725523, "grad_norm": 1.3400638103485107, "learning_rate": 2.1429535739375833e-05, "loss": 0.4520699501037598, "step": 478890 }, { "epoch": 2.8466810516492203, "grad_norm": 1.1238768100738525, "learning_rate": 2.142843089830923e-05, "loss": 0.464511775970459, "step": 478900 }, { "epoch": 2.8467404937258887, "grad_norm": 1.370736837387085, "learning_rate": 2.142732648094007e-05, "loss": 0.47672786712646487, "step": 478910 }, { "epoch": 2.846799935802557, "grad_norm": 1.1425235271453857, "learning_rate": 2.1426222487273625e-05, "loss": 0.4226856231689453, "step": 478920 }, { "epoch": 2.8468593778792255, "grad_norm": 1.108463168144226, "learning_rate": 2.142511891731519e-05, "loss": 0.47153921127319337, "step": 478930 }, { "epoch": 2.846918819955894, "grad_norm": 0.9822619557380676, "learning_rate": 2.1424015771070038e-05, "loss": 0.41091036796569824, "step": 478940 }, { "epoch": 2.8469782620325623, "grad_norm": 1.3263604640960693, "learning_rate": 2.1422913048543458e-05, "loss": 0.4319607734680176, "step": 478950 }, { "epoch": 2.8470377041092307, "grad_norm": 1.247260332107544, "learning_rate": 2.14218107497407e-05, "loss": 0.4163325309753418, "step": 478960 }, { "epoch": 2.847097146185899, "grad_norm": 1.2144566774368286, "learning_rate": 2.142070887466706e-05, "loss": 0.42652101516723634, "step": 478970 }, { "epoch": 2.8471565882625676, "grad_norm": 1.3525567054748535, "learning_rate": 2.1419607423327802e-05, "loss": 0.4399374485015869, "step": 478980 }, { "epoch": 2.847216030339236, "grad_norm": 1.1667640209197998, "learning_rate": 2.141850639572818e-05, "loss": 0.45437002182006836, "step": 478990 }, { "epoch": 2.8472754724159044, "grad_norm": 1.3541806936264038, "learning_rate": 2.1417405791873484e-05, "loss": 0.44771685600280764, "step": 479000 }, { "epoch": 2.847334914492573, "grad_norm": 1.279238224029541, "learning_rate": 2.1416305611768988e-05, "loss": 0.48511595726013185, "step": 479010 }, { "epoch": 2.8473943565692412, "grad_norm": 1.3818811178207397, "learning_rate": 2.141520585541991e-05, "loss": 0.47556447982788086, "step": 479020 }, { "epoch": 2.8474537986459096, "grad_norm": 1.343687653541565, "learning_rate": 2.141410652283155e-05, "loss": 0.4403555870056152, "step": 479030 }, { "epoch": 2.847513240722578, "grad_norm": 1.5274583101272583, "learning_rate": 2.141300761400915e-05, "loss": 0.45716304779052735, "step": 479040 }, { "epoch": 2.847572682799246, "grad_norm": 1.5437893867492676, "learning_rate": 2.1411909128957956e-05, "loss": 0.45825467109680174, "step": 479050 }, { "epoch": 2.847632124875915, "grad_norm": 1.2438756227493286, "learning_rate": 2.141081106768326e-05, "loss": 0.44292583465576174, "step": 479060 }, { "epoch": 2.847691566952583, "grad_norm": 1.4621458053588867, "learning_rate": 2.1409713430190295e-05, "loss": 0.4349239349365234, "step": 479070 }, { "epoch": 2.8477510090292517, "grad_norm": 1.3407524824142456, "learning_rate": 2.1408616216484302e-05, "loss": 0.46492748260498046, "step": 479080 }, { "epoch": 2.8478104511059197, "grad_norm": 1.3250465393066406, "learning_rate": 2.1407519426570532e-05, "loss": 0.4318229198455811, "step": 479090 }, { "epoch": 2.847869893182588, "grad_norm": 1.4842344522476196, "learning_rate": 2.140642306045424e-05, "loss": 0.4491755485534668, "step": 479100 }, { "epoch": 2.8479293352592565, "grad_norm": 1.1341487169265747, "learning_rate": 2.140532711814067e-05, "loss": 0.4558372497558594, "step": 479110 }, { "epoch": 2.847988777335925, "grad_norm": 0.9884824156761169, "learning_rate": 2.1404231599635046e-05, "loss": 0.44985170364379884, "step": 479120 }, { "epoch": 2.8480482194125933, "grad_norm": 1.3280808925628662, "learning_rate": 2.140313650494265e-05, "loss": 0.4751854419708252, "step": 479130 }, { "epoch": 2.8481076614892618, "grad_norm": 1.454011082649231, "learning_rate": 2.1402041834068683e-05, "loss": 0.4828470230102539, "step": 479140 }, { "epoch": 2.84816710356593, "grad_norm": 1.3705247640609741, "learning_rate": 2.1400947587018395e-05, "loss": 0.47883176803588867, "step": 479150 }, { "epoch": 2.8482265456425986, "grad_norm": 1.3240609169006348, "learning_rate": 2.1399853763797015e-05, "loss": 0.49687604904174804, "step": 479160 }, { "epoch": 2.848285987719267, "grad_norm": 1.4963937997817993, "learning_rate": 2.1398760364409782e-05, "loss": 0.421893310546875, "step": 479170 }, { "epoch": 2.8483454297959354, "grad_norm": 1.6752088069915771, "learning_rate": 2.1397667388861926e-05, "loss": 0.4570335388183594, "step": 479180 }, { "epoch": 2.848404871872604, "grad_norm": 1.1831891536712646, "learning_rate": 2.1396574837158678e-05, "loss": 0.4581741809844971, "step": 479190 }, { "epoch": 2.8484643139492722, "grad_norm": 1.1360533237457275, "learning_rate": 2.1395482709305257e-05, "loss": 0.454790735244751, "step": 479200 }, { "epoch": 2.8485237560259407, "grad_norm": 1.8067973852157593, "learning_rate": 2.1394391005306887e-05, "loss": 0.4777981758117676, "step": 479210 }, { "epoch": 2.848583198102609, "grad_norm": 1.2184669971466064, "learning_rate": 2.139329972516879e-05, "loss": 0.45109100341796876, "step": 479220 }, { "epoch": 2.8486426401792775, "grad_norm": 1.384554386138916, "learning_rate": 2.1392208868896196e-05, "loss": 0.4790009021759033, "step": 479230 }, { "epoch": 2.8487020822559455, "grad_norm": 1.394656777381897, "learning_rate": 2.1391118436494314e-05, "loss": 0.48882579803466797, "step": 479240 }, { "epoch": 2.8487615243326143, "grad_norm": 1.1836960315704346, "learning_rate": 2.1390028427968364e-05, "loss": 0.49895949363708497, "step": 479250 }, { "epoch": 2.8488209664092823, "grad_norm": 1.281413197517395, "learning_rate": 2.1388938843323568e-05, "loss": 0.473417854309082, "step": 479260 }, { "epoch": 2.8488804084859507, "grad_norm": 1.3951832056045532, "learning_rate": 2.1387849682565122e-05, "loss": 0.4437901020050049, "step": 479270 }, { "epoch": 2.848939850562619, "grad_norm": 1.272945761680603, "learning_rate": 2.1386760945698242e-05, "loss": 0.4222882747650146, "step": 479280 }, { "epoch": 2.8489992926392875, "grad_norm": 1.1773009300231934, "learning_rate": 2.1385672632728148e-05, "loss": 0.47205343246459963, "step": 479290 }, { "epoch": 2.849058734715956, "grad_norm": 1.218269944190979, "learning_rate": 2.138458474366003e-05, "loss": 0.49305143356323244, "step": 479300 }, { "epoch": 2.8491181767926244, "grad_norm": 1.324650526046753, "learning_rate": 2.1383497278499098e-05, "loss": 0.41950230598449706, "step": 479310 }, { "epoch": 2.8491776188692928, "grad_norm": 1.0091112852096558, "learning_rate": 2.1382410237250565e-05, "loss": 0.45375795364379884, "step": 479320 }, { "epoch": 2.849237060945961, "grad_norm": 1.4683783054351807, "learning_rate": 2.1381323619919607e-05, "loss": 0.4726703643798828, "step": 479330 }, { "epoch": 2.8492965030226296, "grad_norm": 1.5475342273712158, "learning_rate": 2.138023742651145e-05, "loss": 0.481982421875, "step": 479340 }, { "epoch": 2.849355945099298, "grad_norm": 1.1906651258468628, "learning_rate": 2.1379151657031256e-05, "loss": 0.4405496120452881, "step": 479350 }, { "epoch": 2.8494153871759664, "grad_norm": 1.2790693044662476, "learning_rate": 2.137806631148426e-05, "loss": 0.49480438232421875, "step": 479360 }, { "epoch": 2.849474829252635, "grad_norm": 1.3926455974578857, "learning_rate": 2.137698138987562e-05, "loss": 0.45809521675109866, "step": 479370 }, { "epoch": 2.8495342713293033, "grad_norm": 1.1571834087371826, "learning_rate": 2.137589689221055e-05, "loss": 0.4838083267211914, "step": 479380 }, { "epoch": 2.8495937134059717, "grad_norm": 1.4748661518096924, "learning_rate": 2.1374812818494212e-05, "loss": 0.4662941932678223, "step": 479390 }, { "epoch": 2.84965315548264, "grad_norm": 1.193058729171753, "learning_rate": 2.1373729168731817e-05, "loss": 0.42830986976623536, "step": 479400 }, { "epoch": 2.849712597559308, "grad_norm": 1.3344218730926514, "learning_rate": 2.137264594292853e-05, "loss": 0.4552180767059326, "step": 479410 }, { "epoch": 2.849772039635977, "grad_norm": 1.518381118774414, "learning_rate": 2.1371563141089552e-05, "loss": 0.5034737110137939, "step": 479420 }, { "epoch": 2.849831481712645, "grad_norm": 1.3672536611557007, "learning_rate": 2.1370480763220037e-05, "loss": 0.47213168144226075, "step": 479430 }, { "epoch": 2.8498909237893137, "grad_norm": 1.0981673002243042, "learning_rate": 2.1369398809325202e-05, "loss": 0.4764518737792969, "step": 479440 }, { "epoch": 2.8499503658659817, "grad_norm": 1.5917341709136963, "learning_rate": 2.136831727941018e-05, "loss": 0.4769893646240234, "step": 479450 }, { "epoch": 2.85000980794265, "grad_norm": 1.6998223066329956, "learning_rate": 2.1367236173480157e-05, "loss": 0.4654045104980469, "step": 479460 }, { "epoch": 2.8500692500193185, "grad_norm": 1.356512188911438, "learning_rate": 2.136615549154032e-05, "loss": 0.4240547180175781, "step": 479470 }, { "epoch": 2.850128692095987, "grad_norm": 0.8166711330413818, "learning_rate": 2.1365075233595825e-05, "loss": 0.46416349411010743, "step": 479480 }, { "epoch": 2.8501881341726554, "grad_norm": 1.1971057653427124, "learning_rate": 2.1363995399651853e-05, "loss": 0.43928165435791017, "step": 479490 }, { "epoch": 2.850247576249324, "grad_norm": 1.4134258031845093, "learning_rate": 2.136291598971356e-05, "loss": 0.47044076919555666, "step": 479500 }, { "epoch": 2.850307018325992, "grad_norm": 1.3027513027191162, "learning_rate": 2.1361837003786096e-05, "loss": 0.4740184783935547, "step": 479510 }, { "epoch": 2.8503664604026606, "grad_norm": 1.3319648504257202, "learning_rate": 2.1360758441874655e-05, "loss": 0.45323925018310546, "step": 479520 }, { "epoch": 2.850425902479329, "grad_norm": 1.2705377340316772, "learning_rate": 2.135968030398436e-05, "loss": 0.4783848762512207, "step": 479530 }, { "epoch": 2.8504853445559974, "grad_norm": 1.200109839439392, "learning_rate": 2.13586025901204e-05, "loss": 0.4894582271575928, "step": 479540 }, { "epoch": 2.850544786632666, "grad_norm": 1.26334810256958, "learning_rate": 2.1357525300287906e-05, "loss": 0.44653973579406736, "step": 479550 }, { "epoch": 2.8506042287093343, "grad_norm": 1.0696611404418945, "learning_rate": 2.135644843449205e-05, "loss": 0.477934455871582, "step": 479560 }, { "epoch": 2.8506636707860027, "grad_norm": 1.359702229499817, "learning_rate": 2.135537199273798e-05, "loss": 0.49282150268554686, "step": 479570 }, { "epoch": 2.850723112862671, "grad_norm": 1.4883968830108643, "learning_rate": 2.1354295975030826e-05, "loss": 0.43294801712036135, "step": 479580 }, { "epoch": 2.8507825549393395, "grad_norm": 1.4785972833633423, "learning_rate": 2.135322038137576e-05, "loss": 0.45702619552612306, "step": 479590 }, { "epoch": 2.8508419970160075, "grad_norm": 1.4003536701202393, "learning_rate": 2.135214521177792e-05, "loss": 0.4934150218963623, "step": 479600 }, { "epoch": 2.8509014390926763, "grad_norm": 1.2431150674819946, "learning_rate": 2.135107046624244e-05, "loss": 0.4373476982116699, "step": 479610 }, { "epoch": 2.8509608811693443, "grad_norm": 1.2660518884658813, "learning_rate": 2.1349996144774475e-05, "loss": 0.43861045837402346, "step": 479620 }, { "epoch": 2.851020323246013, "grad_norm": 1.5351589918136597, "learning_rate": 2.1348922247379155e-05, "loss": 0.4920666217803955, "step": 479630 }, { "epoch": 2.851079765322681, "grad_norm": 1.7448927164077759, "learning_rate": 2.1347848774061608e-05, "loss": 0.5082876205444335, "step": 479640 }, { "epoch": 2.8511392073993496, "grad_norm": 1.6115881204605103, "learning_rate": 2.1346775724827e-05, "loss": 0.5015023231506348, "step": 479650 }, { "epoch": 2.851198649476018, "grad_norm": 1.236918330192566, "learning_rate": 2.1345703099680436e-05, "loss": 0.47860307693481446, "step": 479660 }, { "epoch": 2.8512580915526864, "grad_norm": 0.9418741464614868, "learning_rate": 2.1344630898627053e-05, "loss": 0.43769397735595705, "step": 479670 }, { "epoch": 2.851317533629355, "grad_norm": 1.6345927715301514, "learning_rate": 2.1343559121671988e-05, "loss": 0.4550487041473389, "step": 479680 }, { "epoch": 2.851376975706023, "grad_norm": 1.4326517581939697, "learning_rate": 2.1342487768820367e-05, "loss": 0.44030609130859377, "step": 479690 }, { "epoch": 2.8514364177826916, "grad_norm": 1.2235336303710938, "learning_rate": 2.1341416840077298e-05, "loss": 0.4745497226715088, "step": 479700 }, { "epoch": 2.85149585985936, "grad_norm": 1.1355608701705933, "learning_rate": 2.134034633544792e-05, "loss": 0.4444724082946777, "step": 479710 }, { "epoch": 2.8515553019360285, "grad_norm": 1.0970792770385742, "learning_rate": 2.1339276254937356e-05, "loss": 0.42998442649841306, "step": 479720 }, { "epoch": 2.851614744012697, "grad_norm": 1.3379218578338623, "learning_rate": 2.133820659855071e-05, "loss": 0.468912410736084, "step": 479730 }, { "epoch": 2.8516741860893653, "grad_norm": 1.6539983749389648, "learning_rate": 2.133713736629312e-05, "loss": 0.4430237770080566, "step": 479740 }, { "epoch": 2.8517336281660337, "grad_norm": 1.3225836753845215, "learning_rate": 2.133606855816969e-05, "loss": 0.47073822021484374, "step": 479750 }, { "epoch": 2.851793070242702, "grad_norm": 1.5216552019119263, "learning_rate": 2.133500017418553e-05, "loss": 0.4831081390380859, "step": 479760 }, { "epoch": 2.8518525123193705, "grad_norm": 1.1517784595489502, "learning_rate": 2.133393221434574e-05, "loss": 0.44512009620666504, "step": 479770 }, { "epoch": 2.851911954396039, "grad_norm": 0.8373428583145142, "learning_rate": 2.133286467865546e-05, "loss": 0.4569223880767822, "step": 479780 }, { "epoch": 2.851971396472707, "grad_norm": 1.115786075592041, "learning_rate": 2.1331797567119766e-05, "loss": 0.4453089714050293, "step": 479790 }, { "epoch": 2.852030838549376, "grad_norm": 1.3545809984207153, "learning_rate": 2.133073087974379e-05, "loss": 0.4738636493682861, "step": 479800 }, { "epoch": 2.8520902806260438, "grad_norm": 1.2469499111175537, "learning_rate": 2.1329664616532604e-05, "loss": 0.42103281021118166, "step": 479810 }, { "epoch": 2.8521497227027126, "grad_norm": 1.0876877307891846, "learning_rate": 2.1328598777491338e-05, "loss": 0.4964413642883301, "step": 479820 }, { "epoch": 2.8522091647793806, "grad_norm": 1.11236572265625, "learning_rate": 2.132753336262507e-05, "loss": 0.49233760833740237, "step": 479830 }, { "epoch": 2.852268606856049, "grad_norm": 1.138205647468567, "learning_rate": 2.13264683719389e-05, "loss": 0.5409947872161865, "step": 479840 }, { "epoch": 2.8523280489327174, "grad_norm": 1.42599356174469, "learning_rate": 2.1325403805437936e-05, "loss": 0.49135942459106446, "step": 479850 }, { "epoch": 2.852387491009386, "grad_norm": 1.3972402811050415, "learning_rate": 2.1324339663127256e-05, "loss": 0.41768245697021483, "step": 479860 }, { "epoch": 2.8524469330860542, "grad_norm": 1.1951704025268555, "learning_rate": 2.1323275945011957e-05, "loss": 0.46254777908325195, "step": 479870 }, { "epoch": 2.8525063751627227, "grad_norm": 0.9708476662635803, "learning_rate": 2.132221265109712e-05, "loss": 0.4381869316101074, "step": 479880 }, { "epoch": 2.852565817239391, "grad_norm": 1.5167155265808105, "learning_rate": 2.1321149781387845e-05, "loss": 0.46048822402954104, "step": 479890 }, { "epoch": 2.8526252593160595, "grad_norm": 1.5637174844741821, "learning_rate": 2.1320087335889208e-05, "loss": 0.43155593872070314, "step": 479900 }, { "epoch": 2.852684701392728, "grad_norm": 1.3727095127105713, "learning_rate": 2.131902531460629e-05, "loss": 0.45104432106018066, "step": 479910 }, { "epoch": 2.8527441434693963, "grad_norm": 1.1380696296691895, "learning_rate": 2.1317963717544175e-05, "loss": 0.48113365173339845, "step": 479920 }, { "epoch": 2.8528035855460647, "grad_norm": 1.2735495567321777, "learning_rate": 2.131690254470794e-05, "loss": 0.5005213737487793, "step": 479930 }, { "epoch": 2.852863027622733, "grad_norm": 1.1677029132843018, "learning_rate": 2.1315841796102658e-05, "loss": 0.4660604000091553, "step": 479940 }, { "epoch": 2.8529224696994016, "grad_norm": 0.8926974534988403, "learning_rate": 2.131478147173341e-05, "loss": 0.4607714653015137, "step": 479950 }, { "epoch": 2.85298191177607, "grad_norm": 1.1852943897247314, "learning_rate": 2.1313721571605266e-05, "loss": 0.4735837936401367, "step": 479960 }, { "epoch": 2.8530413538527384, "grad_norm": 1.537180781364441, "learning_rate": 2.131266209572329e-05, "loss": 0.5024983882904053, "step": 479970 }, { "epoch": 2.8531007959294064, "grad_norm": 1.4147285223007202, "learning_rate": 2.131160304409256e-05, "loss": 0.4760565280914307, "step": 479980 }, { "epoch": 2.853160238006075, "grad_norm": 1.1222522258758545, "learning_rate": 2.1310544416718135e-05, "loss": 0.45518922805786133, "step": 479990 }, { "epoch": 2.853219680082743, "grad_norm": 1.357460379600525, "learning_rate": 2.1309486213605082e-05, "loss": 0.4797187805175781, "step": 480000 }, { "epoch": 2.8532791221594116, "grad_norm": 1.462883710861206, "learning_rate": 2.1308428434758458e-05, "loss": 0.48238544464111327, "step": 480010 }, { "epoch": 2.85333856423608, "grad_norm": 1.2022168636322021, "learning_rate": 2.1307371080183333e-05, "loss": 0.5041656017303466, "step": 480020 }, { "epoch": 2.8533980063127484, "grad_norm": 1.4814013242721558, "learning_rate": 2.1306314149884758e-05, "loss": 0.48914279937744143, "step": 480030 }, { "epoch": 2.853457448389417, "grad_norm": 1.0562466382980347, "learning_rate": 2.130525764386779e-05, "loss": 0.46152796745300295, "step": 480040 }, { "epoch": 2.8535168904660853, "grad_norm": 1.4472708702087402, "learning_rate": 2.1304201562137493e-05, "loss": 0.4836728572845459, "step": 480050 }, { "epoch": 2.8535763325427537, "grad_norm": 1.2129546403884888, "learning_rate": 2.1303145904698905e-05, "loss": 0.4348630428314209, "step": 480060 }, { "epoch": 2.853635774619422, "grad_norm": 1.1796245574951172, "learning_rate": 2.1302090671557072e-05, "loss": 0.45443124771118165, "step": 480070 }, { "epoch": 2.8536952166960905, "grad_norm": 1.3962641954421997, "learning_rate": 2.1301035862717057e-05, "loss": 0.41962270736694335, "step": 480080 }, { "epoch": 2.853754658772759, "grad_norm": 1.0341417789459229, "learning_rate": 2.1299981478183896e-05, "loss": 0.4490945339202881, "step": 480090 }, { "epoch": 2.8538141008494273, "grad_norm": 1.1912933588027954, "learning_rate": 2.1298927517962637e-05, "loss": 0.522992467880249, "step": 480100 }, { "epoch": 2.8538735429260957, "grad_norm": 1.3178503513336182, "learning_rate": 2.129787398205833e-05, "loss": 0.4828195571899414, "step": 480110 }, { "epoch": 2.853932985002764, "grad_norm": 1.548288345336914, "learning_rate": 2.129682087047599e-05, "loss": 0.4678053855895996, "step": 480120 }, { "epoch": 2.8539924270794326, "grad_norm": 1.445038914680481, "learning_rate": 2.1295768183220676e-05, "loss": 0.41214957237243655, "step": 480130 }, { "epoch": 2.854051869156101, "grad_norm": 1.3743360042572021, "learning_rate": 2.129471592029742e-05, "loss": 0.41598005294799806, "step": 480140 }, { "epoch": 2.854111311232769, "grad_norm": 1.3893036842346191, "learning_rate": 2.1293664081711263e-05, "loss": 0.494755220413208, "step": 480150 }, { "epoch": 2.854170753309438, "grad_norm": 1.4944241046905518, "learning_rate": 2.1292612667467214e-05, "loss": 0.45217232704162597, "step": 480160 }, { "epoch": 2.854230195386106, "grad_norm": 1.0382392406463623, "learning_rate": 2.129156167757032e-05, "loss": 0.3979356288909912, "step": 480170 }, { "epoch": 2.8542896374627746, "grad_norm": 1.4665447473526, "learning_rate": 2.1290511112025612e-05, "loss": 0.4248193264007568, "step": 480180 }, { "epoch": 2.8543490795394426, "grad_norm": 1.571807622909546, "learning_rate": 2.1289460970838092e-05, "loss": 0.46884880065917967, "step": 480190 }, { "epoch": 2.854408521616111, "grad_norm": 1.1759347915649414, "learning_rate": 2.1288411254012812e-05, "loss": 0.48479557037353516, "step": 480200 }, { "epoch": 2.8544679636927794, "grad_norm": 1.4945337772369385, "learning_rate": 2.128736196155478e-05, "loss": 0.5276124000549316, "step": 480210 }, { "epoch": 2.854527405769448, "grad_norm": 1.0197643041610718, "learning_rate": 2.1286313093469014e-05, "loss": 0.46723122596740724, "step": 480220 }, { "epoch": 2.8545868478461163, "grad_norm": 1.0880869626998901, "learning_rate": 2.1285264649760535e-05, "loss": 0.4655512809753418, "step": 480230 }, { "epoch": 2.8546462899227847, "grad_norm": 1.0953353643417358, "learning_rate": 2.128421663043436e-05, "loss": 0.46169424057006836, "step": 480240 }, { "epoch": 2.854705731999453, "grad_norm": 1.135103702545166, "learning_rate": 2.1283169035495503e-05, "loss": 0.41146297454833985, "step": 480250 }, { "epoch": 2.8547651740761215, "grad_norm": 1.3580896854400635, "learning_rate": 2.128212186494896e-05, "loss": 0.4492605209350586, "step": 480260 }, { "epoch": 2.85482461615279, "grad_norm": 1.131408452987671, "learning_rate": 2.1281075118799763e-05, "loss": 0.4074713230133057, "step": 480270 }, { "epoch": 2.8548840582294583, "grad_norm": 1.234926462173462, "learning_rate": 2.1280028797052907e-05, "loss": 0.45862884521484376, "step": 480280 }, { "epoch": 2.8549435003061268, "grad_norm": 1.0684814453125, "learning_rate": 2.12789828997134e-05, "loss": 0.48062286376953123, "step": 480290 }, { "epoch": 2.855002942382795, "grad_norm": 1.3376253843307495, "learning_rate": 2.127793742678624e-05, "loss": 0.4648745536804199, "step": 480300 }, { "epoch": 2.8550623844594636, "grad_norm": 1.6186217069625854, "learning_rate": 2.127689237827644e-05, "loss": 0.4581045627593994, "step": 480310 }, { "epoch": 2.855121826536132, "grad_norm": 1.2377710342407227, "learning_rate": 2.127584775418899e-05, "loss": 0.4832138538360596, "step": 480320 }, { "epoch": 2.8551812686128004, "grad_norm": 1.0282448530197144, "learning_rate": 2.1274803554528882e-05, "loss": 0.45024900436401366, "step": 480330 }, { "epoch": 2.8552407106894684, "grad_norm": 1.5404911041259766, "learning_rate": 2.1273759779301124e-05, "loss": 0.4104166984558105, "step": 480340 }, { "epoch": 2.8553001527661372, "grad_norm": 1.5156991481781006, "learning_rate": 2.1272716428510696e-05, "loss": 0.5027717113494873, "step": 480350 }, { "epoch": 2.855359594842805, "grad_norm": 1.145005702972412, "learning_rate": 2.1271673502162606e-05, "loss": 0.47033090591430665, "step": 480360 }, { "epoch": 2.855419036919474, "grad_norm": 1.4499099254608154, "learning_rate": 2.1270631000261832e-05, "loss": 0.48410558700561523, "step": 480370 }, { "epoch": 2.855478478996142, "grad_norm": 1.1542760133743286, "learning_rate": 2.1269588922813357e-05, "loss": 0.4390112400054932, "step": 480380 }, { "epoch": 2.8555379210728105, "grad_norm": 1.3593624830245972, "learning_rate": 2.1268547269822176e-05, "loss": 0.48246426582336427, "step": 480390 }, { "epoch": 2.855597363149479, "grad_norm": 1.6631135940551758, "learning_rate": 2.126750604129326e-05, "loss": 0.48256669044494627, "step": 480400 }, { "epoch": 2.8556568052261473, "grad_norm": 1.4278956651687622, "learning_rate": 2.1266465237231602e-05, "loss": 0.45760364532470704, "step": 480410 }, { "epoch": 2.8557162473028157, "grad_norm": 1.2080762386322021, "learning_rate": 2.1265424857642174e-05, "loss": 0.4177433967590332, "step": 480420 }, { "epoch": 2.855775689379484, "grad_norm": 1.4787920713424683, "learning_rate": 2.126438490252996e-05, "loss": 0.48137969970703126, "step": 480430 }, { "epoch": 2.8558351314561525, "grad_norm": 1.3705124855041504, "learning_rate": 2.1263345371899922e-05, "loss": 0.4371828079223633, "step": 480440 }, { "epoch": 2.855894573532821, "grad_norm": 1.353751540184021, "learning_rate": 2.1262306265757053e-05, "loss": 0.45649356842041017, "step": 480450 }, { "epoch": 2.8559540156094894, "grad_norm": 1.3319201469421387, "learning_rate": 2.1261267584106293e-05, "loss": 0.46572246551513674, "step": 480460 }, { "epoch": 2.8560134576861578, "grad_norm": 1.2355290651321411, "learning_rate": 2.126022932695264e-05, "loss": 0.5127393722534179, "step": 480470 }, { "epoch": 2.856072899762826, "grad_norm": 1.2060365676879883, "learning_rate": 2.1259191494301042e-05, "loss": 0.4682516098022461, "step": 480480 }, { "epoch": 2.8561323418394946, "grad_norm": 1.4297863245010376, "learning_rate": 2.1258154086156485e-05, "loss": 0.5217636585235595, "step": 480490 }, { "epoch": 2.856191783916163, "grad_norm": 1.4874403476715088, "learning_rate": 2.1257117102523902e-05, "loss": 0.4485630512237549, "step": 480500 }, { "epoch": 2.8562512259928314, "grad_norm": 1.091684341430664, "learning_rate": 2.1256080543408278e-05, "loss": 0.45131878852844237, "step": 480510 }, { "epoch": 2.8563106680695, "grad_norm": 1.4270029067993164, "learning_rate": 2.1255044408814566e-05, "loss": 0.46621074676513674, "step": 480520 }, { "epoch": 2.856370110146168, "grad_norm": 1.3547475337982178, "learning_rate": 2.1254008698747706e-05, "loss": 0.466047477722168, "step": 480530 }, { "epoch": 2.8564295522228367, "grad_norm": 1.1039904356002808, "learning_rate": 2.1252973413212678e-05, "loss": 0.43863162994384763, "step": 480540 }, { "epoch": 2.8564889942995046, "grad_norm": 1.3187251091003418, "learning_rate": 2.1251938552214422e-05, "loss": 0.43422603607177734, "step": 480550 }, { "epoch": 2.8565484363761735, "grad_norm": 1.3211466073989868, "learning_rate": 2.125090411575789e-05, "loss": 0.4846461296081543, "step": 480560 }, { "epoch": 2.8566078784528415, "grad_norm": 1.401162028312683, "learning_rate": 2.1249870103848024e-05, "loss": 0.48169965744018556, "step": 480570 }, { "epoch": 2.85666732052951, "grad_norm": 1.5717252492904663, "learning_rate": 2.1248836516489772e-05, "loss": 0.45454111099243166, "step": 480580 }, { "epoch": 2.8567267626061783, "grad_norm": 1.309041142463684, "learning_rate": 2.1247803353688082e-05, "loss": 0.4842092514038086, "step": 480590 }, { "epoch": 2.8567862046828467, "grad_norm": 1.4274272918701172, "learning_rate": 2.1246770615447904e-05, "loss": 0.46569089889526366, "step": 480600 }, { "epoch": 2.856845646759515, "grad_norm": 1.5977014303207397, "learning_rate": 2.124573830177417e-05, "loss": 0.4546320915222168, "step": 480610 }, { "epoch": 2.8569050888361835, "grad_norm": 1.2243239879608154, "learning_rate": 2.1244706412671806e-05, "loss": 0.4062387466430664, "step": 480620 }, { "epoch": 2.856964530912852, "grad_norm": 1.194393277168274, "learning_rate": 2.1243674948145774e-05, "loss": 0.46026058197021485, "step": 480630 }, { "epoch": 2.8570239729895204, "grad_norm": 1.2678180932998657, "learning_rate": 2.1242643908200994e-05, "loss": 0.46346654891967776, "step": 480640 }, { "epoch": 2.857083415066189, "grad_norm": 1.1494605541229248, "learning_rate": 2.12416132928424e-05, "loss": 0.43296189308166505, "step": 480650 }, { "epoch": 2.857142857142857, "grad_norm": 1.1861568689346313, "learning_rate": 2.124058310207492e-05, "loss": 0.4507004737854004, "step": 480660 }, { "epoch": 2.8572022992195256, "grad_norm": 1.2327972650527954, "learning_rate": 2.1239553335903482e-05, "loss": 0.47834253311157227, "step": 480670 }, { "epoch": 2.857261741296194, "grad_norm": 1.5660587549209595, "learning_rate": 2.1238523994333013e-05, "loss": 0.4837050437927246, "step": 480680 }, { "epoch": 2.8573211833728624, "grad_norm": 1.1525646448135376, "learning_rate": 2.1237495077368434e-05, "loss": 0.4626304626464844, "step": 480690 }, { "epoch": 2.857380625449531, "grad_norm": 1.2376713752746582, "learning_rate": 2.1236466585014668e-05, "loss": 0.4313954830169678, "step": 480700 }, { "epoch": 2.8574400675261993, "grad_norm": 1.2168713808059692, "learning_rate": 2.1235438517276652e-05, "loss": 0.4413772106170654, "step": 480710 }, { "epoch": 2.8574995096028672, "grad_norm": 1.4210727214813232, "learning_rate": 2.1234410874159278e-05, "loss": 0.45250897407531737, "step": 480720 }, { "epoch": 2.857558951679536, "grad_norm": 1.1968109607696533, "learning_rate": 2.1233383655667482e-05, "loss": 0.4742758750915527, "step": 480730 }, { "epoch": 2.857618393756204, "grad_norm": 1.4134341478347778, "learning_rate": 2.1232356861806167e-05, "loss": 0.46184568405151366, "step": 480740 }, { "epoch": 2.8576778358328725, "grad_norm": 1.3900896310806274, "learning_rate": 2.1231330492580237e-05, "loss": 0.494492244720459, "step": 480750 }, { "epoch": 2.857737277909541, "grad_norm": 1.6721724271774292, "learning_rate": 2.123030454799462e-05, "loss": 0.43118715286254883, "step": 480760 }, { "epoch": 2.8577967199862093, "grad_norm": 1.0093094110488892, "learning_rate": 2.1229279028054222e-05, "loss": 0.43163576126098635, "step": 480770 }, { "epoch": 2.8578561620628777, "grad_norm": 1.171957015991211, "learning_rate": 2.122825393276394e-05, "loss": 0.43446836471557615, "step": 480780 }, { "epoch": 2.857915604139546, "grad_norm": 1.4974982738494873, "learning_rate": 2.122722926212867e-05, "loss": 0.46177825927734373, "step": 480790 }, { "epoch": 2.8579750462162146, "grad_norm": 0.9892352819442749, "learning_rate": 2.1226205016153332e-05, "loss": 0.4371776103973389, "step": 480800 }, { "epoch": 2.858034488292883, "grad_norm": 1.114804744720459, "learning_rate": 2.1225181194842826e-05, "loss": 0.4215195655822754, "step": 480810 }, { "epoch": 2.8580939303695514, "grad_norm": 1.026015043258667, "learning_rate": 2.122415779820202e-05, "loss": 0.4305423259735107, "step": 480820 }, { "epoch": 2.85815337244622, "grad_norm": 1.1831934452056885, "learning_rate": 2.1223134826235845e-05, "loss": 0.4169149398803711, "step": 480830 }, { "epoch": 2.8582128145228882, "grad_norm": 1.3253470659255981, "learning_rate": 2.122211227894917e-05, "loss": 0.44475741386413575, "step": 480840 }, { "epoch": 2.8582722565995566, "grad_norm": 1.1280592679977417, "learning_rate": 2.1221090156346915e-05, "loss": 0.42081151008605955, "step": 480850 }, { "epoch": 2.858331698676225, "grad_norm": 1.3819178342819214, "learning_rate": 2.1220068458433943e-05, "loss": 0.44783506393432615, "step": 480860 }, { "epoch": 2.8583911407528935, "grad_norm": 1.0989832878112793, "learning_rate": 2.1219047185215148e-05, "loss": 0.435806941986084, "step": 480870 }, { "epoch": 2.858450582829562, "grad_norm": 1.535062313079834, "learning_rate": 2.1218026336695414e-05, "loss": 0.4849538803100586, "step": 480880 }, { "epoch": 2.85851002490623, "grad_norm": 1.3174201250076294, "learning_rate": 2.121700591287963e-05, "loss": 0.44785194396972655, "step": 480890 }, { "epoch": 2.8585694669828987, "grad_norm": 1.9159061908721924, "learning_rate": 2.121598591377267e-05, "loss": 0.47024078369140626, "step": 480900 }, { "epoch": 2.8586289090595667, "grad_norm": 1.4017589092254639, "learning_rate": 2.1214966339379427e-05, "loss": 0.44130764007568357, "step": 480910 }, { "epoch": 2.8586883511362355, "grad_norm": 1.3652797937393188, "learning_rate": 2.1213947189704774e-05, "loss": 0.47656497955322263, "step": 480920 }, { "epoch": 2.8587477932129035, "grad_norm": 1.2653254270553589, "learning_rate": 2.1212928464753566e-05, "loss": 0.4403067588806152, "step": 480930 }, { "epoch": 2.858807235289572, "grad_norm": 1.2173078060150146, "learning_rate": 2.1211910164530705e-05, "loss": 0.49570837020874026, "step": 480940 }, { "epoch": 2.8588666773662403, "grad_norm": 1.1848047971725464, "learning_rate": 2.121089228904104e-05, "loss": 0.4668576240539551, "step": 480950 }, { "epoch": 2.8589261194429088, "grad_norm": 1.1996597051620483, "learning_rate": 2.120987483828946e-05, "loss": 0.4733741283416748, "step": 480960 }, { "epoch": 2.858985561519577, "grad_norm": 1.1626590490341187, "learning_rate": 2.120885781228082e-05, "loss": 0.4067848682403564, "step": 480970 }, { "epoch": 2.8590450035962456, "grad_norm": 1.3159568309783936, "learning_rate": 2.120784121101999e-05, "loss": 0.45108942985534667, "step": 480980 }, { "epoch": 2.859104445672914, "grad_norm": 1.3509200811386108, "learning_rate": 2.120682503451182e-05, "loss": 0.4208892822265625, "step": 480990 }, { "epoch": 2.8591638877495824, "grad_norm": 1.4837902784347534, "learning_rate": 2.1205809282761188e-05, "loss": 0.47469215393066405, "step": 481000 }, { "epoch": 2.859223329826251, "grad_norm": 1.31108558177948, "learning_rate": 2.120479395577294e-05, "loss": 0.448182201385498, "step": 481010 }, { "epoch": 2.8592827719029192, "grad_norm": 1.5673140287399292, "learning_rate": 2.1203779053551938e-05, "loss": 0.47344136238098145, "step": 481020 }, { "epoch": 2.8593422139795877, "grad_norm": 1.2314852476119995, "learning_rate": 2.1202764576103043e-05, "loss": 0.4340752124786377, "step": 481030 }, { "epoch": 2.859401656056256, "grad_norm": 1.365075707435608, "learning_rate": 2.120175052343112e-05, "loss": 0.4507054328918457, "step": 481040 }, { "epoch": 2.8594610981329245, "grad_norm": 1.348728895187378, "learning_rate": 2.1200736895540976e-05, "loss": 0.48029336929321287, "step": 481050 }, { "epoch": 2.859520540209593, "grad_norm": 1.5477454662322998, "learning_rate": 2.11997236924375e-05, "loss": 0.5084110260009765, "step": 481060 }, { "epoch": 2.8595799822862613, "grad_norm": 1.1061246395111084, "learning_rate": 2.1198710914125524e-05, "loss": 0.41758131980895996, "step": 481070 }, { "epoch": 2.8596394243629293, "grad_norm": 1.4596651792526245, "learning_rate": 2.1197698560609888e-05, "loss": 0.4317949295043945, "step": 481080 }, { "epoch": 2.859698866439598, "grad_norm": 1.3416274785995483, "learning_rate": 2.1196686631895447e-05, "loss": 0.4780106544494629, "step": 481090 }, { "epoch": 2.859758308516266, "grad_norm": 2.0576159954071045, "learning_rate": 2.1195675127987033e-05, "loss": 0.47896862030029297, "step": 481100 }, { "epoch": 2.859817750592935, "grad_norm": 1.293399691581726, "learning_rate": 2.119466404888949e-05, "loss": 0.47022714614868166, "step": 481110 }, { "epoch": 2.859877192669603, "grad_norm": 1.249664068222046, "learning_rate": 2.1193653394607654e-05, "loss": 0.4288337707519531, "step": 481120 }, { "epoch": 2.8599366347462714, "grad_norm": 1.4814265966415405, "learning_rate": 2.1192643165146348e-05, "loss": 0.4679254055023193, "step": 481130 }, { "epoch": 2.8599960768229398, "grad_norm": 1.2199305295944214, "learning_rate": 2.119163336051043e-05, "loss": 0.48622832298278806, "step": 481140 }, { "epoch": 2.860055518899608, "grad_norm": 1.2236133813858032, "learning_rate": 2.11906239807047e-05, "loss": 0.45906405448913573, "step": 481150 }, { "epoch": 2.8601149609762766, "grad_norm": 1.3946932554244995, "learning_rate": 2.118961502573402e-05, "loss": 0.46399765014648436, "step": 481160 }, { "epoch": 2.860174403052945, "grad_norm": 1.5470284223556519, "learning_rate": 2.118860649560318e-05, "loss": 0.40545101165771485, "step": 481170 }, { "epoch": 2.8602338451296134, "grad_norm": 1.454750657081604, "learning_rate": 2.1187598390317032e-05, "loss": 0.42970123291015627, "step": 481180 }, { "epoch": 2.860293287206282, "grad_norm": 1.562639594078064, "learning_rate": 2.1186590709880387e-05, "loss": 0.48688721656799316, "step": 481190 }, { "epoch": 2.8603527292829503, "grad_norm": 1.1385010480880737, "learning_rate": 2.1185583454298067e-05, "loss": 0.46639313697814944, "step": 481200 }, { "epoch": 2.8604121713596187, "grad_norm": 1.3462122678756714, "learning_rate": 2.1184576623574893e-05, "loss": 0.4556105613708496, "step": 481210 }, { "epoch": 2.860471613436287, "grad_norm": 1.1653739213943481, "learning_rate": 2.1183570217715673e-05, "loss": 0.4621898174285889, "step": 481220 }, { "epoch": 2.8605310555129555, "grad_norm": 1.1138720512390137, "learning_rate": 2.1182564236725232e-05, "loss": 0.42417497634887696, "step": 481230 }, { "epoch": 2.860590497589624, "grad_norm": 1.1959929466247559, "learning_rate": 2.1181558680608384e-05, "loss": 0.4540433883666992, "step": 481240 }, { "epoch": 2.8606499396662923, "grad_norm": 0.9939051866531372, "learning_rate": 2.118055354936992e-05, "loss": 0.4629486083984375, "step": 481250 }, { "epoch": 2.8607093817429607, "grad_norm": 1.106491208076477, "learning_rate": 2.1179548843014668e-05, "loss": 0.4155993938446045, "step": 481260 }, { "epoch": 2.8607688238196287, "grad_norm": 1.3654929399490356, "learning_rate": 2.1178544561547432e-05, "loss": 0.431031608581543, "step": 481270 }, { "epoch": 2.8608282658962976, "grad_norm": 1.4195928573608398, "learning_rate": 2.1177540704973004e-05, "loss": 0.44282259941101076, "step": 481280 }, { "epoch": 2.8608877079729655, "grad_norm": 1.2642936706542969, "learning_rate": 2.1176537273296204e-05, "loss": 0.454840087890625, "step": 481290 }, { "epoch": 2.8609471500496344, "grad_norm": 1.1177070140838623, "learning_rate": 2.117553426652181e-05, "loss": 0.4733604431152344, "step": 481300 }, { "epoch": 2.8610065921263024, "grad_norm": 1.547547459602356, "learning_rate": 2.1174531684654634e-05, "loss": 0.46755194664001465, "step": 481310 }, { "epoch": 2.861066034202971, "grad_norm": 1.375379204750061, "learning_rate": 2.1173529527699472e-05, "loss": 0.4463654518127441, "step": 481320 }, { "epoch": 2.861125476279639, "grad_norm": 1.3724602460861206, "learning_rate": 2.1172527795661122e-05, "loss": 0.4620718002319336, "step": 481330 }, { "epoch": 2.8611849183563076, "grad_norm": 1.4281917810440063, "learning_rate": 2.1171526488544362e-05, "loss": 0.446051025390625, "step": 481340 }, { "epoch": 2.861244360432976, "grad_norm": 1.3675963878631592, "learning_rate": 2.1170525606353995e-05, "loss": 0.4762421607971191, "step": 481350 }, { "epoch": 2.8613038025096444, "grad_norm": 1.3772598505020142, "learning_rate": 2.1169525149094797e-05, "loss": 0.43300447463989256, "step": 481360 }, { "epoch": 2.861363244586313, "grad_norm": 1.234727144241333, "learning_rate": 2.1168525116771566e-05, "loss": 0.4819968223571777, "step": 481370 }, { "epoch": 2.8614226866629813, "grad_norm": 1.2556711435317993, "learning_rate": 2.116752550938908e-05, "loss": 0.4788812637329102, "step": 481380 }, { "epoch": 2.8614821287396497, "grad_norm": 1.1968810558319092, "learning_rate": 2.1166526326952118e-05, "loss": 0.43243207931518557, "step": 481390 }, { "epoch": 2.861541570816318, "grad_norm": 1.4946296215057373, "learning_rate": 2.1165527569465465e-05, "loss": 0.4873487949371338, "step": 481400 }, { "epoch": 2.8616010128929865, "grad_norm": 1.3071483373641968, "learning_rate": 2.11645292369339e-05, "loss": 0.4689011573791504, "step": 481410 }, { "epoch": 2.861660454969655, "grad_norm": 1.2280789613723755, "learning_rate": 2.1163531329362195e-05, "loss": 0.44167404174804686, "step": 481420 }, { "epoch": 2.8617198970463233, "grad_norm": 1.2525441646575928, "learning_rate": 2.1162533846755124e-05, "loss": 0.4346522331237793, "step": 481430 }, { "epoch": 2.8617793391229918, "grad_norm": 1.1165844202041626, "learning_rate": 2.116153678911745e-05, "loss": 0.4932133197784424, "step": 481440 }, { "epoch": 2.86183878119966, "grad_norm": 1.1258955001831055, "learning_rate": 2.1160540156453953e-05, "loss": 0.48630800247192385, "step": 481450 }, { "epoch": 2.861898223276328, "grad_norm": 1.5462470054626465, "learning_rate": 2.1159543948769408e-05, "loss": 0.47803535461425783, "step": 481460 }, { "epoch": 2.861957665352997, "grad_norm": 1.7428488731384277, "learning_rate": 2.1158548166068563e-05, "loss": 0.44194755554199217, "step": 481470 }, { "epoch": 2.862017107429665, "grad_norm": 1.3580034971237183, "learning_rate": 2.1157552808356197e-05, "loss": 0.4887848377227783, "step": 481480 }, { "epoch": 2.8620765495063334, "grad_norm": 1.3791831731796265, "learning_rate": 2.1156557875637056e-05, "loss": 0.48107757568359377, "step": 481490 }, { "epoch": 2.862135991583002, "grad_norm": 1.4917138814926147, "learning_rate": 2.1155563367915923e-05, "loss": 0.49947199821472166, "step": 481500 }, { "epoch": 2.86219543365967, "grad_norm": 1.8573142290115356, "learning_rate": 2.115456928519752e-05, "loss": 0.4558112621307373, "step": 481510 }, { "epoch": 2.8622548757363386, "grad_norm": 1.1615346670150757, "learning_rate": 2.1153575627486627e-05, "loss": 0.47060203552246094, "step": 481520 }, { "epoch": 2.862314317813007, "grad_norm": 1.3297497034072876, "learning_rate": 2.1152582394788012e-05, "loss": 0.46583943367004393, "step": 481530 }, { "epoch": 2.8623737598896755, "grad_norm": 1.2689225673675537, "learning_rate": 2.1151589587106385e-05, "loss": 0.40343146324157714, "step": 481540 }, { "epoch": 2.862433201966344, "grad_norm": 1.3555505275726318, "learning_rate": 2.1150597204446525e-05, "loss": 0.43711466789245607, "step": 481550 }, { "epoch": 2.8624926440430123, "grad_norm": 1.1383285522460938, "learning_rate": 2.114960524681317e-05, "loss": 0.45677833557128905, "step": 481560 }, { "epoch": 2.8625520861196807, "grad_norm": 1.32614004611969, "learning_rate": 2.1148613714211068e-05, "loss": 0.44912190437316896, "step": 481570 }, { "epoch": 2.862611528196349, "grad_norm": 1.211073398590088, "learning_rate": 2.1147622606644964e-05, "loss": 0.4407292366027832, "step": 481580 }, { "epoch": 2.8626709702730175, "grad_norm": 1.4849283695220947, "learning_rate": 2.114663192411961e-05, "loss": 0.46678009033203127, "step": 481590 }, { "epoch": 2.862730412349686, "grad_norm": 1.204128623008728, "learning_rate": 2.1145641666639702e-05, "loss": 0.4181061744689941, "step": 481600 }, { "epoch": 2.8627898544263544, "grad_norm": 1.4792953729629517, "learning_rate": 2.114465183421002e-05, "loss": 0.43691301345825195, "step": 481610 }, { "epoch": 2.8628492965030228, "grad_norm": 1.46369206905365, "learning_rate": 2.1143662426835293e-05, "loss": 0.5012914657592773, "step": 481620 }, { "epoch": 2.8629087385796907, "grad_norm": 1.401646614074707, "learning_rate": 2.114267344452024e-05, "loss": 0.40918636322021484, "step": 481630 }, { "epoch": 2.8629681806563596, "grad_norm": 0.9806662201881409, "learning_rate": 2.114168488726959e-05, "loss": 0.3872947931289673, "step": 481640 }, { "epoch": 2.8630276227330276, "grad_norm": 1.5435916185379028, "learning_rate": 2.114069675508809e-05, "loss": 0.47322778701782225, "step": 481650 }, { "epoch": 2.8630870648096964, "grad_norm": 1.4268043041229248, "learning_rate": 2.113970904798046e-05, "loss": 0.4187943935394287, "step": 481660 }, { "epoch": 2.8631465068863644, "grad_norm": 1.3921014070510864, "learning_rate": 2.113872176595141e-05, "loss": 0.4142664909362793, "step": 481670 }, { "epoch": 2.863205948963033, "grad_norm": 1.4646329879760742, "learning_rate": 2.1137734909005678e-05, "loss": 0.46789259910583497, "step": 481680 }, { "epoch": 2.8632653910397012, "grad_norm": 1.2311302423477173, "learning_rate": 2.1136748477147993e-05, "loss": 0.49808874130249026, "step": 481690 }, { "epoch": 2.8633248331163696, "grad_norm": 1.2495697736740112, "learning_rate": 2.1135762470383045e-05, "loss": 0.42857980728149414, "step": 481700 }, { "epoch": 2.863384275193038, "grad_norm": 1.3903865814208984, "learning_rate": 2.1134776888715585e-05, "loss": 0.47115178108215333, "step": 481710 }, { "epoch": 2.8634437172697065, "grad_norm": 0.8933892250061035, "learning_rate": 2.1133791732150302e-05, "loss": 0.44876537322998045, "step": 481720 }, { "epoch": 2.863503159346375, "grad_norm": 1.3855104446411133, "learning_rate": 2.1132807000691925e-05, "loss": 0.4681145668029785, "step": 481730 }, { "epoch": 2.8635626014230433, "grad_norm": 1.3378093242645264, "learning_rate": 2.1131822694345145e-05, "loss": 0.42706756591796874, "step": 481740 }, { "epoch": 2.8636220434997117, "grad_norm": 1.3236500024795532, "learning_rate": 2.113083881311469e-05, "loss": 0.49245615005493165, "step": 481750 }, { "epoch": 2.86368148557638, "grad_norm": 1.5294990539550781, "learning_rate": 2.112985535700526e-05, "loss": 0.48024563789367675, "step": 481760 }, { "epoch": 2.8637409276530486, "grad_norm": 1.2807992696762085, "learning_rate": 2.1128872326021555e-05, "loss": 0.49245338439941405, "step": 481770 }, { "epoch": 2.863800369729717, "grad_norm": 1.1934393644332886, "learning_rate": 2.112788972016828e-05, "loss": 0.4468390464782715, "step": 481780 }, { "epoch": 2.8638598118063854, "grad_norm": 1.2357046604156494, "learning_rate": 2.1126907539450143e-05, "loss": 0.4936957359313965, "step": 481790 }, { "epoch": 2.863919253883054, "grad_norm": 1.2949917316436768, "learning_rate": 2.112592578387183e-05, "loss": 0.4583435535430908, "step": 481800 }, { "epoch": 2.863978695959722, "grad_norm": 1.5560681819915771, "learning_rate": 2.1124944453438047e-05, "loss": 0.44420995712280276, "step": 481810 }, { "epoch": 2.86403813803639, "grad_norm": 1.162438154220581, "learning_rate": 2.112396354815349e-05, "loss": 0.4747478485107422, "step": 481820 }, { "epoch": 2.864097580113059, "grad_norm": 1.3078763484954834, "learning_rate": 2.1122983068022845e-05, "loss": 0.48772683143615725, "step": 481830 }, { "epoch": 2.864157022189727, "grad_norm": 1.0517103672027588, "learning_rate": 2.11220030130508e-05, "loss": 0.44324917793273927, "step": 481840 }, { "epoch": 2.864216464266396, "grad_norm": 1.353291630744934, "learning_rate": 2.1121023383242045e-05, "loss": 0.4655433654785156, "step": 481850 }, { "epoch": 2.864275906343064, "grad_norm": 1.598604440689087, "learning_rate": 2.1120044178601272e-05, "loss": 0.5010333061218262, "step": 481860 }, { "epoch": 2.8643353484197323, "grad_norm": 1.5453824996948242, "learning_rate": 2.111906539913316e-05, "loss": 0.48618574142456056, "step": 481870 }, { "epoch": 2.8643947904964007, "grad_norm": 1.5129774808883667, "learning_rate": 2.1118087044842397e-05, "loss": 0.5065732002258301, "step": 481880 }, { "epoch": 2.864454232573069, "grad_norm": 1.3183579444885254, "learning_rate": 2.1117109115733655e-05, "loss": 0.4596888542175293, "step": 481890 }, { "epoch": 2.8645136746497375, "grad_norm": 1.2079836130142212, "learning_rate": 2.1116131611811607e-05, "loss": 0.4190847396850586, "step": 481900 }, { "epoch": 2.864573116726406, "grad_norm": 0.9708548784255981, "learning_rate": 2.1115154533080956e-05, "loss": 0.4002429962158203, "step": 481910 }, { "epoch": 2.8646325588030743, "grad_norm": 1.2980451583862305, "learning_rate": 2.111417787954635e-05, "loss": 0.4541788101196289, "step": 481920 }, { "epoch": 2.8646920008797427, "grad_norm": 0.9629573225975037, "learning_rate": 2.1113201651212458e-05, "loss": 0.4266185760498047, "step": 481930 }, { "epoch": 2.864751442956411, "grad_norm": 1.289303183555603, "learning_rate": 2.1112225848083965e-05, "loss": 0.48229031562805175, "step": 481940 }, { "epoch": 2.8648108850330796, "grad_norm": 1.206529140472412, "learning_rate": 2.1111250470165545e-05, "loss": 0.4801003932952881, "step": 481950 }, { "epoch": 2.864870327109748, "grad_norm": 1.3847838640213013, "learning_rate": 2.1110275517461845e-05, "loss": 0.4525332450866699, "step": 481960 }, { "epoch": 2.8649297691864164, "grad_norm": 1.06817626953125, "learning_rate": 2.1109300989977544e-05, "loss": 0.4325073719024658, "step": 481970 }, { "epoch": 2.864989211263085, "grad_norm": 1.1551578044891357, "learning_rate": 2.1108326887717292e-05, "loss": 0.43758645057678225, "step": 481980 }, { "epoch": 2.8650486533397532, "grad_norm": 1.6478043794631958, "learning_rate": 2.110735321068576e-05, "loss": 0.4482594013214111, "step": 481990 }, { "epoch": 2.8651080954164216, "grad_norm": 1.3655015230178833, "learning_rate": 2.1106379958887586e-05, "loss": 0.46848373413085936, "step": 482000 }, { "epoch": 2.8651675374930896, "grad_norm": 1.3450591564178467, "learning_rate": 2.110540713232745e-05, "loss": 0.44511728286743163, "step": 482010 }, { "epoch": 2.8652269795697585, "grad_norm": 1.1151617765426636, "learning_rate": 2.110443473101e-05, "loss": 0.43048386573791503, "step": 482020 }, { "epoch": 2.8652864216464264, "grad_norm": 1.4364886283874512, "learning_rate": 2.110346275493987e-05, "loss": 0.4383901596069336, "step": 482030 }, { "epoch": 2.8653458637230953, "grad_norm": 1.3401226997375488, "learning_rate": 2.1102491204121735e-05, "loss": 0.43525171279907227, "step": 482040 }, { "epoch": 2.8654053057997633, "grad_norm": 1.4534084796905518, "learning_rate": 2.1101520078560218e-05, "loss": 0.527017879486084, "step": 482050 }, { "epoch": 2.8654647478764317, "grad_norm": 1.3525434732437134, "learning_rate": 2.1100549378259977e-05, "loss": 0.4931751251220703, "step": 482060 }, { "epoch": 2.8655241899531, "grad_norm": 1.8869739770889282, "learning_rate": 2.109957910322567e-05, "loss": 0.42923884391784667, "step": 482070 }, { "epoch": 2.8655836320297685, "grad_norm": 1.307650089263916, "learning_rate": 2.109860925346192e-05, "loss": 0.4660271167755127, "step": 482080 }, { "epoch": 2.865643074106437, "grad_norm": 1.481450080871582, "learning_rate": 2.109763982897336e-05, "loss": 0.44722700119018555, "step": 482090 }, { "epoch": 2.8657025161831053, "grad_norm": 1.0555423498153687, "learning_rate": 2.1096670829764638e-05, "loss": 0.4507737159729004, "step": 482100 }, { "epoch": 2.8657619582597738, "grad_norm": 1.2272604703903198, "learning_rate": 2.10957022558404e-05, "loss": 0.4205802917480469, "step": 482110 }, { "epoch": 2.865821400336442, "grad_norm": 1.0683209896087646, "learning_rate": 2.109473410720526e-05, "loss": 0.46804285049438477, "step": 482120 }, { "epoch": 2.8658808424131106, "grad_norm": 1.2055402994155884, "learning_rate": 2.109376638386385e-05, "loss": 0.42993874549865724, "step": 482130 }, { "epoch": 2.865940284489779, "grad_norm": 1.2337135076522827, "learning_rate": 2.1092799085820826e-05, "loss": 0.5384761810302734, "step": 482140 }, { "epoch": 2.8659997265664474, "grad_norm": 1.1066997051239014, "learning_rate": 2.1091832213080785e-05, "loss": 0.44910330772399903, "step": 482150 }, { "epoch": 2.866059168643116, "grad_norm": 1.0420321226119995, "learning_rate": 2.109086576564835e-05, "loss": 0.4509955883026123, "step": 482160 }, { "epoch": 2.8661186107197842, "grad_norm": 1.4401801824569702, "learning_rate": 2.1089899743528174e-05, "loss": 0.46918625831604005, "step": 482170 }, { "epoch": 2.8661780527964527, "grad_norm": 1.2311395406723022, "learning_rate": 2.108893414672486e-05, "loss": 0.45165104866027833, "step": 482180 }, { "epoch": 2.866237494873121, "grad_norm": 1.4812315702438354, "learning_rate": 2.1087968975243023e-05, "loss": 0.4765500545501709, "step": 482190 }, { "epoch": 2.866296936949789, "grad_norm": 1.5117393732070923, "learning_rate": 2.10870042290873e-05, "loss": 0.49843697547912597, "step": 482200 }, { "epoch": 2.866356379026458, "grad_norm": 1.356397032737732, "learning_rate": 2.1086039908262277e-05, "loss": 0.49193658828735354, "step": 482210 }, { "epoch": 2.866415821103126, "grad_norm": 1.7936145067214966, "learning_rate": 2.1085076012772593e-05, "loss": 0.469303035736084, "step": 482220 }, { "epoch": 2.8664752631797943, "grad_norm": 1.3026766777038574, "learning_rate": 2.108411254262283e-05, "loss": 0.44268050193786623, "step": 482230 }, { "epoch": 2.8665347052564627, "grad_norm": 1.2988680601119995, "learning_rate": 2.1083149497817627e-05, "loss": 0.4554800033569336, "step": 482240 }, { "epoch": 2.866594147333131, "grad_norm": 1.3873332738876343, "learning_rate": 2.108218687836158e-05, "loss": 0.41537628173828123, "step": 482250 }, { "epoch": 2.8666535894097995, "grad_norm": 1.3445309400558472, "learning_rate": 2.1081224684259286e-05, "loss": 0.4724698066711426, "step": 482260 }, { "epoch": 2.866713031486468, "grad_norm": 1.1517810821533203, "learning_rate": 2.1080262915515363e-05, "loss": 0.42362174987792967, "step": 482270 }, { "epoch": 2.8667724735631364, "grad_norm": 1.093843936920166, "learning_rate": 2.107930157213439e-05, "loss": 0.4727581024169922, "step": 482280 }, { "epoch": 2.8668319156398048, "grad_norm": 1.3063137531280518, "learning_rate": 2.107834065412098e-05, "loss": 0.47339687347412107, "step": 482290 }, { "epoch": 2.866891357716473, "grad_norm": 1.1543635129928589, "learning_rate": 2.107738016147974e-05, "loss": 0.5195776462554932, "step": 482300 }, { "epoch": 2.8669507997931416, "grad_norm": 0.9232298135757446, "learning_rate": 2.1076420094215253e-05, "loss": 0.4214217185974121, "step": 482310 }, { "epoch": 2.86701024186981, "grad_norm": 1.2787764072418213, "learning_rate": 2.1075460452332103e-05, "loss": 0.45488758087158204, "step": 482320 }, { "epoch": 2.8670696839464784, "grad_norm": 1.4106403589248657, "learning_rate": 2.1074501235834893e-05, "loss": 0.50619478225708, "step": 482330 }, { "epoch": 2.867129126023147, "grad_norm": 1.4783817529678345, "learning_rate": 2.1073542444728204e-05, "loss": 0.47769947052001954, "step": 482340 }, { "epoch": 2.8671885680998153, "grad_norm": 1.1324514150619507, "learning_rate": 2.1072584079016632e-05, "loss": 0.45197129249572754, "step": 482350 }, { "epoch": 2.8672480101764837, "grad_norm": 1.3970168828964233, "learning_rate": 2.1071626138704746e-05, "loss": 0.4545957088470459, "step": 482360 }, { "epoch": 2.8673074522531516, "grad_norm": 1.308215618133545, "learning_rate": 2.1070668623797147e-05, "loss": 0.45547213554382326, "step": 482370 }, { "epoch": 2.8673668943298205, "grad_norm": 1.2363847494125366, "learning_rate": 2.106971153429841e-05, "loss": 0.48562021255493165, "step": 482380 }, { "epoch": 2.8674263364064885, "grad_norm": 1.4122124910354614, "learning_rate": 2.1068754870213103e-05, "loss": 0.4542232513427734, "step": 482390 }, { "epoch": 2.8674857784831573, "grad_norm": 1.4612981081008911, "learning_rate": 2.1067798631545814e-05, "loss": 0.5102999687194825, "step": 482400 }, { "epoch": 2.8675452205598253, "grad_norm": 1.6020596027374268, "learning_rate": 2.106684281830111e-05, "loss": 0.5228355407714844, "step": 482410 }, { "epoch": 2.8676046626364937, "grad_norm": 1.3753540515899658, "learning_rate": 2.1065887430483562e-05, "loss": 0.4389208793640137, "step": 482420 }, { "epoch": 2.867664104713162, "grad_norm": 1.2992178201675415, "learning_rate": 2.1064932468097752e-05, "loss": 0.48260927200317383, "step": 482430 }, { "epoch": 2.8677235467898305, "grad_norm": 1.24051034450531, "learning_rate": 2.1063977931148243e-05, "loss": 0.4800116062164307, "step": 482440 }, { "epoch": 2.867782988866499, "grad_norm": 1.155163049697876, "learning_rate": 2.1063023819639594e-05, "loss": 0.4645376682281494, "step": 482450 }, { "epoch": 2.8678424309431674, "grad_norm": 1.2959625720977783, "learning_rate": 2.106207013357638e-05, "loss": 0.42583532333374025, "step": 482460 }, { "epoch": 2.867901873019836, "grad_norm": 1.1806684732437134, "learning_rate": 2.1061116872963154e-05, "loss": 0.4725343704223633, "step": 482470 }, { "epoch": 2.867961315096504, "grad_norm": 1.0874335765838623, "learning_rate": 2.1060164037804473e-05, "loss": 0.4251992225646973, "step": 482480 }, { "epoch": 2.8680207571731726, "grad_norm": 1.0043630599975586, "learning_rate": 2.1059211628104905e-05, "loss": 0.3943521499633789, "step": 482490 }, { "epoch": 2.868080199249841, "grad_norm": 1.3061137199401855, "learning_rate": 2.1058259643869004e-05, "loss": 0.4563162803649902, "step": 482500 }, { "epoch": 2.8681396413265094, "grad_norm": 1.1297253370285034, "learning_rate": 2.1057308085101323e-05, "loss": 0.47116799354553224, "step": 482510 }, { "epoch": 2.868199083403178, "grad_norm": 0.9036431312561035, "learning_rate": 2.1056356951806407e-05, "loss": 0.4259197235107422, "step": 482520 }, { "epoch": 2.8682585254798463, "grad_norm": 1.1990617513656616, "learning_rate": 2.1055406243988828e-05, "loss": 0.4164132595062256, "step": 482530 }, { "epoch": 2.8683179675565147, "grad_norm": 1.9125330448150635, "learning_rate": 2.1054455961653107e-05, "loss": 0.49872798919677735, "step": 482540 }, { "epoch": 2.868377409633183, "grad_norm": 1.020395040512085, "learning_rate": 2.105350610480379e-05, "loss": 0.42963376045227053, "step": 482550 }, { "epoch": 2.868436851709851, "grad_norm": 1.4022512435913086, "learning_rate": 2.105255667344545e-05, "loss": 0.4546222686767578, "step": 482560 }, { "epoch": 2.86849629378652, "grad_norm": 1.4291248321533203, "learning_rate": 2.1051607667582606e-05, "loss": 0.4805576324462891, "step": 482570 }, { "epoch": 2.868555735863188, "grad_norm": 1.3515580892562866, "learning_rate": 2.1050659087219805e-05, "loss": 0.5158074855804443, "step": 482580 }, { "epoch": 2.8686151779398568, "grad_norm": 1.3111441135406494, "learning_rate": 2.1049710932361573e-05, "loss": 0.5124408721923828, "step": 482590 }, { "epoch": 2.8686746200165247, "grad_norm": 1.4388275146484375, "learning_rate": 2.1048763203012462e-05, "loss": 0.44888720512390134, "step": 482600 }, { "epoch": 2.868734062093193, "grad_norm": 1.3203760385513306, "learning_rate": 2.1047815899176986e-05, "loss": 0.4782547473907471, "step": 482610 }, { "epoch": 2.8687935041698616, "grad_norm": 1.092948317527771, "learning_rate": 2.1046869020859693e-05, "loss": 0.4927011489868164, "step": 482620 }, { "epoch": 2.86885294624653, "grad_norm": 1.1156866550445557, "learning_rate": 2.1045922568065128e-05, "loss": 0.4210366725921631, "step": 482630 }, { "epoch": 2.8689123883231984, "grad_norm": 1.4826323986053467, "learning_rate": 2.1044976540797784e-05, "loss": 0.4939127922058105, "step": 482640 }, { "epoch": 2.868971830399867, "grad_norm": 1.3831746578216553, "learning_rate": 2.104403093906219e-05, "loss": 0.4476707935333252, "step": 482650 }, { "epoch": 2.869031272476535, "grad_norm": 0.923499345779419, "learning_rate": 2.10430857628629e-05, "loss": 0.4544278621673584, "step": 482660 }, { "epoch": 2.8690907145532036, "grad_norm": 1.3395525217056274, "learning_rate": 2.104214101220441e-05, "loss": 0.4353672504425049, "step": 482670 }, { "epoch": 2.869150156629872, "grad_norm": 1.1081409454345703, "learning_rate": 2.104119668709123e-05, "loss": 0.4708428382873535, "step": 482680 }, { "epoch": 2.8692095987065405, "grad_norm": 1.1558527946472168, "learning_rate": 2.1040252787527918e-05, "loss": 0.4739251136779785, "step": 482690 }, { "epoch": 2.869269040783209, "grad_norm": 1.306877851486206, "learning_rate": 2.103930931351895e-05, "loss": 0.4974216461181641, "step": 482700 }, { "epoch": 2.8693284828598773, "grad_norm": 1.0611234903335571, "learning_rate": 2.1038366265068863e-05, "loss": 0.392732572555542, "step": 482710 }, { "epoch": 2.8693879249365457, "grad_norm": 1.4793305397033691, "learning_rate": 2.1037423642182148e-05, "loss": 0.47930088043212893, "step": 482720 }, { "epoch": 2.869447367013214, "grad_norm": 1.2472251653671265, "learning_rate": 2.1036481444863333e-05, "loss": 0.4684313774108887, "step": 482730 }, { "epoch": 2.8695068090898825, "grad_norm": 1.5013049840927124, "learning_rate": 2.1035539673116912e-05, "loss": 0.4517106056213379, "step": 482740 }, { "epoch": 2.8695662511665505, "grad_norm": 1.4164303541183472, "learning_rate": 2.10345983269474e-05, "loss": 0.48657026290893557, "step": 482750 }, { "epoch": 2.8696256932432194, "grad_norm": 1.2444945573806763, "learning_rate": 2.1033657406359293e-05, "loss": 0.45310020446777344, "step": 482760 }, { "epoch": 2.8696851353198873, "grad_norm": 1.5886821746826172, "learning_rate": 2.1032716911357097e-05, "loss": 0.5310648918151856, "step": 482770 }, { "epoch": 2.869744577396556, "grad_norm": 1.494126319885254, "learning_rate": 2.1031776841945303e-05, "loss": 0.395028281211853, "step": 482780 }, { "epoch": 2.869804019473224, "grad_norm": 1.349297285079956, "learning_rate": 2.1030837198128416e-05, "loss": 0.49502034187316896, "step": 482790 }, { "epoch": 2.8698634615498926, "grad_norm": 1.3796173334121704, "learning_rate": 2.1029897979910928e-05, "loss": 0.5007164955139161, "step": 482800 }, { "epoch": 2.869922903626561, "grad_norm": 1.2932666540145874, "learning_rate": 2.102895918729733e-05, "loss": 0.42081441879272463, "step": 482810 }, { "epoch": 2.8699823457032294, "grad_norm": 1.2137863636016846, "learning_rate": 2.102802082029212e-05, "loss": 0.45833725929260255, "step": 482820 }, { "epoch": 2.870041787779898, "grad_norm": 1.521332025527954, "learning_rate": 2.1027082878899778e-05, "loss": 0.49614543914794923, "step": 482830 }, { "epoch": 2.8701012298565662, "grad_norm": 1.1638585329055786, "learning_rate": 2.1026145363124805e-05, "loss": 0.44408740997314455, "step": 482840 }, { "epoch": 2.8701606719332347, "grad_norm": 1.1994775533676147, "learning_rate": 2.102520827297166e-05, "loss": 0.4740854263305664, "step": 482850 }, { "epoch": 2.870220114009903, "grad_norm": 1.407778263092041, "learning_rate": 2.1024271608444852e-05, "loss": 0.4943240165710449, "step": 482860 }, { "epoch": 2.8702795560865715, "grad_norm": 1.5611680746078491, "learning_rate": 2.1023335369548852e-05, "loss": 0.5152060508728027, "step": 482870 }, { "epoch": 2.87033899816324, "grad_norm": 0.9959720373153687, "learning_rate": 2.1022399556288127e-05, "loss": 0.4795825004577637, "step": 482880 }, { "epoch": 2.8703984402399083, "grad_norm": 1.182515025138855, "learning_rate": 2.102146416866718e-05, "loss": 0.4322981834411621, "step": 482890 }, { "epoch": 2.8704578823165767, "grad_norm": 1.2956546545028687, "learning_rate": 2.1020529206690458e-05, "loss": 0.4739635467529297, "step": 482900 }, { "epoch": 2.870517324393245, "grad_norm": 1.2175778150558472, "learning_rate": 2.1019594670362445e-05, "loss": 0.45495095252990725, "step": 482910 }, { "epoch": 2.8705767664699136, "grad_norm": 1.4245439767837524, "learning_rate": 2.1018660559687614e-05, "loss": 0.46458778381347654, "step": 482920 }, { "epoch": 2.870636208546582, "grad_norm": 1.0338772535324097, "learning_rate": 2.1017726874670434e-05, "loss": 0.5147675514221192, "step": 482930 }, { "epoch": 2.87069565062325, "grad_norm": 1.2353249788284302, "learning_rate": 2.1016793615315368e-05, "loss": 0.5074009895324707, "step": 482940 }, { "epoch": 2.870755092699919, "grad_norm": 1.2438890933990479, "learning_rate": 2.1015860781626883e-05, "loss": 0.4674847602844238, "step": 482950 }, { "epoch": 2.8708145347765868, "grad_norm": 1.4618865251541138, "learning_rate": 2.101492837360944e-05, "loss": 0.45605010986328126, "step": 482960 }, { "epoch": 2.870873976853255, "grad_norm": 1.1946271657943726, "learning_rate": 2.1013996391267498e-05, "loss": 0.45529584884643554, "step": 482970 }, { "epoch": 2.8709334189299236, "grad_norm": 1.3533085584640503, "learning_rate": 2.101306483460551e-05, "loss": 0.4986722469329834, "step": 482980 }, { "epoch": 2.870992861006592, "grad_norm": 1.0741305351257324, "learning_rate": 2.1012133703627937e-05, "loss": 0.47301540374755857, "step": 482990 }, { "epoch": 2.8710523030832604, "grad_norm": 1.0954711437225342, "learning_rate": 2.101120299833925e-05, "loss": 0.42601814270019533, "step": 483000 }, { "epoch": 2.871111745159929, "grad_norm": 1.687595248222351, "learning_rate": 2.1010272718743873e-05, "loss": 0.5285763740539551, "step": 483010 }, { "epoch": 2.8711711872365973, "grad_norm": 1.0907232761383057, "learning_rate": 2.100934286484627e-05, "loss": 0.4536889553070068, "step": 483020 }, { "epoch": 2.8712306293132657, "grad_norm": 1.3248810768127441, "learning_rate": 2.1008413436650894e-05, "loss": 0.49314866065979, "step": 483030 }, { "epoch": 2.871290071389934, "grad_norm": 1.204986333847046, "learning_rate": 2.1007484434162178e-05, "loss": 0.489471435546875, "step": 483040 }, { "epoch": 2.8713495134666025, "grad_norm": 1.1993488073349, "learning_rate": 2.100655585738458e-05, "loss": 0.4068051815032959, "step": 483050 }, { "epoch": 2.871408955543271, "grad_norm": 1.1090599298477173, "learning_rate": 2.100562770632254e-05, "loss": 0.45967278480529783, "step": 483060 }, { "epoch": 2.8714683976199393, "grad_norm": 1.5196226835250854, "learning_rate": 2.1004699980980494e-05, "loss": 0.44916572570800783, "step": 483070 }, { "epoch": 2.8715278396966077, "grad_norm": 1.2824538946151733, "learning_rate": 2.100377268136286e-05, "loss": 0.43597936630249023, "step": 483080 }, { "epoch": 2.871587281773276, "grad_norm": 1.8706555366516113, "learning_rate": 2.100284580747411e-05, "loss": 0.47214670181274415, "step": 483090 }, { "epoch": 2.8716467238499446, "grad_norm": 1.290334939956665, "learning_rate": 2.100191935931866e-05, "loss": 0.46966238021850587, "step": 483100 }, { "epoch": 2.8717061659266125, "grad_norm": 1.1024256944656372, "learning_rate": 2.1000993336900933e-05, "loss": 0.4745213031768799, "step": 483110 }, { "epoch": 2.8717656080032814, "grad_norm": 1.3011153936386108, "learning_rate": 2.1000067740225378e-05, "loss": 0.40493249893188477, "step": 483120 }, { "epoch": 2.8718250500799494, "grad_norm": 1.4158833026885986, "learning_rate": 2.099914256929642e-05, "loss": 0.41871004104614257, "step": 483130 }, { "epoch": 2.8718844921566182, "grad_norm": 1.2776567935943604, "learning_rate": 2.0998217824118458e-05, "loss": 0.4837827682495117, "step": 483140 }, { "epoch": 2.871943934233286, "grad_norm": 1.71547269821167, "learning_rate": 2.0997293504695946e-05, "loss": 0.4526073455810547, "step": 483150 }, { "epoch": 2.8720033763099546, "grad_norm": 1.32724928855896, "learning_rate": 2.09963696110333e-05, "loss": 0.452147388458252, "step": 483160 }, { "epoch": 2.872062818386623, "grad_norm": 1.1227103471755981, "learning_rate": 2.0995446143134932e-05, "loss": 0.46336851119995115, "step": 483170 }, { "epoch": 2.8721222604632914, "grad_norm": 1.3341805934906006, "learning_rate": 2.099452310100526e-05, "loss": 0.46651010513305663, "step": 483180 }, { "epoch": 2.87218170253996, "grad_norm": 0.9447236657142639, "learning_rate": 2.0993600484648707e-05, "loss": 0.4827385902404785, "step": 483190 }, { "epoch": 2.8722411446166283, "grad_norm": 1.3548921346664429, "learning_rate": 2.099267829406968e-05, "loss": 0.46037139892578127, "step": 483200 }, { "epoch": 2.8723005866932967, "grad_norm": 1.3223795890808105, "learning_rate": 2.0991756529272587e-05, "loss": 0.46269636154174804, "step": 483210 }, { "epoch": 2.872360028769965, "grad_norm": 1.2571465969085693, "learning_rate": 2.0990835190261853e-05, "loss": 0.48044657707214355, "step": 483220 }, { "epoch": 2.8724194708466335, "grad_norm": 1.2631213665008545, "learning_rate": 2.098991427704186e-05, "loss": 0.44879817962646484, "step": 483230 }, { "epoch": 2.872478912923302, "grad_norm": 1.3345826864242554, "learning_rate": 2.098899378961704e-05, "loss": 0.4751396179199219, "step": 483240 }, { "epoch": 2.8725383549999703, "grad_norm": 1.2316677570343018, "learning_rate": 2.098807372799178e-05, "loss": 0.458405876159668, "step": 483250 }, { "epoch": 2.8725977970766388, "grad_norm": 1.3517009019851685, "learning_rate": 2.0987154092170495e-05, "loss": 0.4493247032165527, "step": 483260 }, { "epoch": 2.872657239153307, "grad_norm": 1.4984585046768188, "learning_rate": 2.098623488215756e-05, "loss": 0.48153066635131836, "step": 483270 }, { "epoch": 2.8727166812299756, "grad_norm": 1.6138980388641357, "learning_rate": 2.09853160979574e-05, "loss": 0.4650753974914551, "step": 483280 }, { "epoch": 2.872776123306644, "grad_norm": 1.2206711769104004, "learning_rate": 2.098439773957439e-05, "loss": 0.4791244983673096, "step": 483290 }, { "epoch": 2.872835565383312, "grad_norm": 1.2234537601470947, "learning_rate": 2.098347980701293e-05, "loss": 0.4712703704833984, "step": 483300 }, { "epoch": 2.872895007459981, "grad_norm": 0.8953691720962524, "learning_rate": 2.098256230027742e-05, "loss": 0.48511581420898436, "step": 483310 }, { "epoch": 2.872954449536649, "grad_norm": 1.4057608842849731, "learning_rate": 2.0981645219372235e-05, "loss": 0.5101223945617676, "step": 483320 }, { "epoch": 2.8730138916133177, "grad_norm": 1.1367117166519165, "learning_rate": 2.0980728564301766e-05, "loss": 0.48867454528808596, "step": 483330 }, { "epoch": 2.8730733336899856, "grad_norm": 1.825036883354187, "learning_rate": 2.09798123350704e-05, "loss": 0.4891334056854248, "step": 483340 }, { "epoch": 2.873132775766654, "grad_norm": 1.3719843626022339, "learning_rate": 2.097889653168252e-05, "loss": 0.46044397354125977, "step": 483350 }, { "epoch": 2.8731922178433225, "grad_norm": 1.479752779006958, "learning_rate": 2.097798115414251e-05, "loss": 0.47493600845336914, "step": 483360 }, { "epoch": 2.873251659919991, "grad_norm": 1.4130144119262695, "learning_rate": 2.0977066202454745e-05, "loss": 0.4851649284362793, "step": 483370 }, { "epoch": 2.8733111019966593, "grad_norm": 1.1713999509811401, "learning_rate": 2.09761516766236e-05, "loss": 0.4679225444793701, "step": 483380 }, { "epoch": 2.8733705440733277, "grad_norm": 1.2940987348556519, "learning_rate": 2.0975237576653457e-05, "loss": 0.5205949783325196, "step": 483390 }, { "epoch": 2.873429986149996, "grad_norm": 1.1287325620651245, "learning_rate": 2.097432390254867e-05, "loss": 0.45213680267333983, "step": 483400 }, { "epoch": 2.8734894282266645, "grad_norm": 1.0826702117919922, "learning_rate": 2.0973410654313635e-05, "loss": 0.4594226837158203, "step": 483410 }, { "epoch": 2.873548870303333, "grad_norm": 1.4003069400787354, "learning_rate": 2.0972497831952706e-05, "loss": 0.43591699600219724, "step": 483420 }, { "epoch": 2.8736083123800014, "grad_norm": 1.5476021766662598, "learning_rate": 2.097158543547025e-05, "loss": 0.5387405395507813, "step": 483430 }, { "epoch": 2.8736677544566698, "grad_norm": 1.5718896389007568, "learning_rate": 2.0970673464870643e-05, "loss": 0.466765308380127, "step": 483440 }, { "epoch": 2.873727196533338, "grad_norm": 1.1877011060714722, "learning_rate": 2.096976192015824e-05, "loss": 0.43374409675598147, "step": 483450 }, { "epoch": 2.8737866386100066, "grad_norm": 1.1436926126480103, "learning_rate": 2.096885080133739e-05, "loss": 0.46159887313842773, "step": 483460 }, { "epoch": 2.873846080686675, "grad_norm": 1.159240484237671, "learning_rate": 2.096794010841246e-05, "loss": 0.44998674392700194, "step": 483470 }, { "epoch": 2.8739055227633434, "grad_norm": 2.2478435039520264, "learning_rate": 2.0967029841387822e-05, "loss": 0.5115004539489746, "step": 483480 }, { "epoch": 2.8739649648400114, "grad_norm": 1.2788426876068115, "learning_rate": 2.096612000026781e-05, "loss": 0.46066880226135254, "step": 483490 }, { "epoch": 2.8740244069166803, "grad_norm": 1.5140221118927002, "learning_rate": 2.096521058505678e-05, "loss": 0.4478776931762695, "step": 483500 }, { "epoch": 2.8740838489933482, "grad_norm": 0.9916657209396362, "learning_rate": 2.09643015957591e-05, "loss": 0.4516643524169922, "step": 483510 }, { "epoch": 2.874143291070017, "grad_norm": 1.3000320196151733, "learning_rate": 2.096339303237909e-05, "loss": 0.499857234954834, "step": 483520 }, { "epoch": 2.874202733146685, "grad_norm": 1.2696189880371094, "learning_rate": 2.0962484894921104e-05, "loss": 0.428653621673584, "step": 483530 }, { "epoch": 2.8742621752233535, "grad_norm": 1.5136492252349854, "learning_rate": 2.0961577183389504e-05, "loss": 0.4188286781311035, "step": 483540 }, { "epoch": 2.874321617300022, "grad_norm": 1.1257145404815674, "learning_rate": 2.0960669897788628e-05, "loss": 0.4628868103027344, "step": 483550 }, { "epoch": 2.8743810593766903, "grad_norm": 1.2672232389450073, "learning_rate": 2.0959763038122806e-05, "loss": 0.46315650939941405, "step": 483560 }, { "epoch": 2.8744405014533587, "grad_norm": 1.2361315488815308, "learning_rate": 2.0958856604396368e-05, "loss": 0.46160311698913575, "step": 483570 }, { "epoch": 2.874499943530027, "grad_norm": 1.107877254486084, "learning_rate": 2.095795059661366e-05, "loss": 0.4453113079071045, "step": 483580 }, { "epoch": 2.8745593856066955, "grad_norm": 1.2110756635665894, "learning_rate": 2.095704501477903e-05, "loss": 0.43778505325317385, "step": 483590 }, { "epoch": 2.874618827683364, "grad_norm": 1.4094297885894775, "learning_rate": 2.0956139858896783e-05, "loss": 0.4518261432647705, "step": 483600 }, { "epoch": 2.8746782697600324, "grad_norm": 1.5960768461227417, "learning_rate": 2.0955235128971267e-05, "loss": 0.4635485649108887, "step": 483610 }, { "epoch": 2.874737711836701, "grad_norm": 1.2812265157699585, "learning_rate": 2.0954330825006817e-05, "loss": 0.4518288135528564, "step": 483620 }, { "epoch": 2.874797153913369, "grad_norm": 1.3067712783813477, "learning_rate": 2.0953426947007737e-05, "loss": 0.47077412605285646, "step": 483630 }, { "epoch": 2.8748565959900376, "grad_norm": 1.831728458404541, "learning_rate": 2.095252349497836e-05, "loss": 0.447340726852417, "step": 483640 }, { "epoch": 2.874916038066706, "grad_norm": 1.2564730644226074, "learning_rate": 2.0951620468923016e-05, "loss": 0.4482419013977051, "step": 483650 }, { "epoch": 2.8749754801433745, "grad_norm": 1.3930720090866089, "learning_rate": 2.0950717868846017e-05, "loss": 0.5020808696746826, "step": 483660 }, { "epoch": 2.875034922220043, "grad_norm": 1.3690823316574097, "learning_rate": 2.094981569475168e-05, "loss": 0.47185688018798827, "step": 483670 }, { "epoch": 2.875094364296711, "grad_norm": 1.142402172088623, "learning_rate": 2.0948913946644334e-05, "loss": 0.4656974792480469, "step": 483680 }, { "epoch": 2.8751538063733797, "grad_norm": 1.4803026914596558, "learning_rate": 2.094801262452827e-05, "loss": 0.47080116271972655, "step": 483690 }, { "epoch": 2.8752132484500477, "grad_norm": 1.3657788038253784, "learning_rate": 2.0947111728407807e-05, "loss": 0.45069150924682616, "step": 483700 }, { "epoch": 2.875272690526716, "grad_norm": 1.2404263019561768, "learning_rate": 2.0946211258287267e-05, "loss": 0.42624635696411134, "step": 483710 }, { "epoch": 2.8753321326033845, "grad_norm": 1.2538858652114868, "learning_rate": 2.094531121417095e-05, "loss": 0.46377038955688477, "step": 483720 }, { "epoch": 2.875391574680053, "grad_norm": 1.4117786884307861, "learning_rate": 2.0944411596063156e-05, "loss": 0.4895144462585449, "step": 483730 }, { "epoch": 2.8754510167567213, "grad_norm": 1.4545189142227173, "learning_rate": 2.094351240396819e-05, "loss": 0.47632179260253904, "step": 483740 }, { "epoch": 2.8755104588333897, "grad_norm": 1.2694326639175415, "learning_rate": 2.094261363789037e-05, "loss": 0.44444847106933594, "step": 483750 }, { "epoch": 2.875569900910058, "grad_norm": 1.2348878383636475, "learning_rate": 2.0941715297833966e-05, "loss": 0.466165828704834, "step": 483760 }, { "epoch": 2.8756293429867266, "grad_norm": 1.2359402179718018, "learning_rate": 2.0940817383803298e-05, "loss": 0.4672105312347412, "step": 483770 }, { "epoch": 2.875688785063395, "grad_norm": 1.3936973810195923, "learning_rate": 2.093991989580266e-05, "loss": 0.46479811668396, "step": 483780 }, { "epoch": 2.8757482271400634, "grad_norm": 1.0728729963302612, "learning_rate": 2.093902283383633e-05, "loss": 0.4331961154937744, "step": 483790 }, { "epoch": 2.875807669216732, "grad_norm": 1.175247073173523, "learning_rate": 2.0938126197908624e-05, "loss": 0.4559276580810547, "step": 483800 }, { "epoch": 2.8758671112934002, "grad_norm": 1.1258333921432495, "learning_rate": 2.093722998802381e-05, "loss": 0.403639554977417, "step": 483810 }, { "epoch": 2.8759265533700686, "grad_norm": 1.6010745763778687, "learning_rate": 2.0936334204186177e-05, "loss": 0.46308422088623047, "step": 483820 }, { "epoch": 2.875985995446737, "grad_norm": 1.2229948043823242, "learning_rate": 2.0935438846400014e-05, "loss": 0.5217488288879395, "step": 483830 }, { "epoch": 2.8760454375234055, "grad_norm": 1.2792202234268188, "learning_rate": 2.093454391466961e-05, "loss": 0.47457351684570315, "step": 483840 }, { "epoch": 2.8761048796000734, "grad_norm": 1.4542274475097656, "learning_rate": 2.0933649408999233e-05, "loss": 0.4947700500488281, "step": 483850 }, { "epoch": 2.8761643216767423, "grad_norm": 1.3973875045776367, "learning_rate": 2.0932755329393184e-05, "loss": 0.4628195285797119, "step": 483860 }, { "epoch": 2.8762237637534103, "grad_norm": 1.0849595069885254, "learning_rate": 2.0931861675855712e-05, "loss": 0.4136547088623047, "step": 483870 }, { "epoch": 2.876283205830079, "grad_norm": 1.2817518711090088, "learning_rate": 2.093096844839112e-05, "loss": 0.448892879486084, "step": 483880 }, { "epoch": 2.876342647906747, "grad_norm": 1.204980492591858, "learning_rate": 2.093007564700365e-05, "loss": 0.44693498611450194, "step": 483890 }, { "epoch": 2.8764020899834155, "grad_norm": 1.1259363889694214, "learning_rate": 2.09291832716976e-05, "loss": 0.4450986862182617, "step": 483900 }, { "epoch": 2.876461532060084, "grad_norm": 1.2629868984222412, "learning_rate": 2.0928291322477226e-05, "loss": 0.48227643966674805, "step": 483910 }, { "epoch": 2.8765209741367523, "grad_norm": 1.2710870504379272, "learning_rate": 2.0927399799346798e-05, "loss": 0.517028522491455, "step": 483920 }, { "epoch": 2.8765804162134208, "grad_norm": 1.611670732498169, "learning_rate": 2.0926508702310587e-05, "loss": 0.46748056411743166, "step": 483930 }, { "epoch": 2.876639858290089, "grad_norm": 1.2798659801483154, "learning_rate": 2.0925618031372844e-05, "loss": 0.4832207202911377, "step": 483940 }, { "epoch": 2.8766993003667576, "grad_norm": 1.1838940382003784, "learning_rate": 2.0924727786537834e-05, "loss": 0.48424439430236815, "step": 483950 }, { "epoch": 2.876758742443426, "grad_norm": 1.1884604692459106, "learning_rate": 2.0923837967809806e-05, "loss": 0.4363499641418457, "step": 483960 }, { "epoch": 2.8768181845200944, "grad_norm": 1.2150068283081055, "learning_rate": 2.092294857519304e-05, "loss": 0.4837947845458984, "step": 483970 }, { "epoch": 2.876877626596763, "grad_norm": 1.3941500186920166, "learning_rate": 2.092205960869178e-05, "loss": 0.46650333404541017, "step": 483980 }, { "epoch": 2.8769370686734312, "grad_norm": 1.5220043659210205, "learning_rate": 2.092117106831027e-05, "loss": 0.5148885250091553, "step": 483990 }, { "epoch": 2.8769965107500997, "grad_norm": 1.0309317111968994, "learning_rate": 2.0920282954052763e-05, "loss": 0.45099945068359376, "step": 484000 }, { "epoch": 2.877055952826768, "grad_norm": 1.2460135221481323, "learning_rate": 2.0919395265923508e-05, "loss": 0.40992279052734376, "step": 484010 }, { "epoch": 2.8771153949034365, "grad_norm": 1.6709389686584473, "learning_rate": 2.0918508003926758e-05, "loss": 0.48227834701538086, "step": 484020 }, { "epoch": 2.877174836980105, "grad_norm": 1.3520598411560059, "learning_rate": 2.0917621168066758e-05, "loss": 0.4669948577880859, "step": 484030 }, { "epoch": 2.877234279056773, "grad_norm": 1.0295970439910889, "learning_rate": 2.0916734758347743e-05, "loss": 0.4856388092041016, "step": 484040 }, { "epoch": 2.8772937211334417, "grad_norm": 1.3080644607543945, "learning_rate": 2.0915848774773968e-05, "loss": 0.4678958892822266, "step": 484050 }, { "epoch": 2.8773531632101097, "grad_norm": 1.9930496215820312, "learning_rate": 2.0914963217349638e-05, "loss": 0.46441078186035156, "step": 484060 }, { "epoch": 2.8774126052867786, "grad_norm": 1.329911708831787, "learning_rate": 2.091407808607902e-05, "loss": 0.4906172275543213, "step": 484070 }, { "epoch": 2.8774720473634465, "grad_norm": 1.4965983629226685, "learning_rate": 2.091319338096634e-05, "loss": 0.4664799690246582, "step": 484080 }, { "epoch": 2.877531489440115, "grad_norm": 1.7590662240982056, "learning_rate": 2.0912309102015826e-05, "loss": 0.4223779201507568, "step": 484090 }, { "epoch": 2.8775909315167834, "grad_norm": 1.2903274297714233, "learning_rate": 2.0911425249231716e-05, "loss": 0.43100910186767577, "step": 484100 }, { "epoch": 2.8776503735934518, "grad_norm": 1.1702313423156738, "learning_rate": 2.091054182261823e-05, "loss": 0.48579983711242675, "step": 484110 }, { "epoch": 2.87770981567012, "grad_norm": 1.627139687538147, "learning_rate": 2.0909658822179594e-05, "loss": 0.49290103912353517, "step": 484120 }, { "epoch": 2.8777692577467886, "grad_norm": 1.1484588384628296, "learning_rate": 2.0908776247920038e-05, "loss": 0.4475828170776367, "step": 484130 }, { "epoch": 2.877828699823457, "grad_norm": 1.1274155378341675, "learning_rate": 2.0907894099843782e-05, "loss": 0.466673755645752, "step": 484140 }, { "epoch": 2.8778881419001254, "grad_norm": 1.4065618515014648, "learning_rate": 2.090701237795504e-05, "loss": 0.5018116950988769, "step": 484150 }, { "epoch": 2.877947583976794, "grad_norm": 1.3230960369110107, "learning_rate": 2.090613108225804e-05, "loss": 0.44689302444458007, "step": 484160 }, { "epoch": 2.8780070260534623, "grad_norm": 1.2994236946105957, "learning_rate": 2.0905250212756998e-05, "loss": 0.501007080078125, "step": 484170 }, { "epoch": 2.8780664681301307, "grad_norm": 1.584593653678894, "learning_rate": 2.090436976945612e-05, "loss": 0.4458615779876709, "step": 484180 }, { "epoch": 2.878125910206799, "grad_norm": 0.9797763824462891, "learning_rate": 2.0903489752359608e-05, "loss": 0.46312317848205564, "step": 484190 }, { "epoch": 2.8781853522834675, "grad_norm": 0.9858788847923279, "learning_rate": 2.0902610161471703e-05, "loss": 0.4590930938720703, "step": 484200 }, { "epoch": 2.878244794360136, "grad_norm": 1.7873607873916626, "learning_rate": 2.0901730996796584e-05, "loss": 0.5139130592346192, "step": 484210 }, { "epoch": 2.8783042364368043, "grad_norm": 1.2415376901626587, "learning_rate": 2.0900852258338456e-05, "loss": 0.4263620376586914, "step": 484220 }, { "epoch": 2.8783636785134723, "grad_norm": 1.4269119501113892, "learning_rate": 2.0899973946101554e-05, "loss": 0.4742149353027344, "step": 484230 }, { "epoch": 2.878423120590141, "grad_norm": 1.1396833658218384, "learning_rate": 2.089909606009005e-05, "loss": 0.4339247703552246, "step": 484240 }, { "epoch": 2.878482562666809, "grad_norm": 1.1381993293762207, "learning_rate": 2.0898218600308135e-05, "loss": 0.37745115756988523, "step": 484250 }, { "epoch": 2.878542004743478, "grad_norm": 1.167706847190857, "learning_rate": 2.089734156676004e-05, "loss": 0.4080661296844482, "step": 484260 }, { "epoch": 2.878601446820146, "grad_norm": 1.3740123510360718, "learning_rate": 2.0896464959449948e-05, "loss": 0.45490169525146484, "step": 484270 }, { "epoch": 2.8786608888968144, "grad_norm": 1.29316246509552, "learning_rate": 2.089558877838204e-05, "loss": 0.4706092834472656, "step": 484280 }, { "epoch": 2.878720330973483, "grad_norm": 1.2452690601348877, "learning_rate": 2.089471302356052e-05, "loss": 0.44231863021850587, "step": 484290 }, { "epoch": 2.878779773050151, "grad_norm": 1.2644850015640259, "learning_rate": 2.0893837694989572e-05, "loss": 0.43615269660949707, "step": 484300 }, { "epoch": 2.8788392151268196, "grad_norm": 1.139141321182251, "learning_rate": 2.0892962792673375e-05, "loss": 0.445638370513916, "step": 484310 }, { "epoch": 2.878898657203488, "grad_norm": 1.1883436441421509, "learning_rate": 2.089208831661613e-05, "loss": 0.5215890407562256, "step": 484320 }, { "epoch": 2.8789580992801564, "grad_norm": 1.5607510805130005, "learning_rate": 2.0891214266822018e-05, "loss": 0.5182610511779785, "step": 484330 }, { "epoch": 2.879017541356825, "grad_norm": 1.2346594333648682, "learning_rate": 2.089034064329521e-05, "loss": 0.4397940158843994, "step": 484340 }, { "epoch": 2.8790769834334933, "grad_norm": 1.0511189699172974, "learning_rate": 2.0889467446039896e-05, "loss": 0.46697559356689455, "step": 484350 }, { "epoch": 2.8791364255101617, "grad_norm": 1.414651870727539, "learning_rate": 2.088859467506025e-05, "loss": 0.490736198425293, "step": 484360 }, { "epoch": 2.87919586758683, "grad_norm": 1.2567702531814575, "learning_rate": 2.0887722330360444e-05, "loss": 0.4532130718231201, "step": 484370 }, { "epoch": 2.8792553096634985, "grad_norm": 1.1733641624450684, "learning_rate": 2.0886850411944636e-05, "loss": 0.4229482650756836, "step": 484380 }, { "epoch": 2.879314751740167, "grad_norm": 1.3318500518798828, "learning_rate": 2.088597891981703e-05, "loss": 0.4392414093017578, "step": 484390 }, { "epoch": 2.8793741938168353, "grad_norm": 1.9299874305725098, "learning_rate": 2.088510785398177e-05, "loss": 0.4125836849212646, "step": 484400 }, { "epoch": 2.8794336358935038, "grad_norm": 0.9698330760002136, "learning_rate": 2.0884237214443037e-05, "loss": 0.3877002477645874, "step": 484410 }, { "epoch": 2.8794930779701717, "grad_norm": 1.547891616821289, "learning_rate": 2.0883367001205e-05, "loss": 0.46281018257141116, "step": 484420 }, { "epoch": 2.8795525200468406, "grad_norm": 1.2409260272979736, "learning_rate": 2.088249721427179e-05, "loss": 0.4564647674560547, "step": 484430 }, { "epoch": 2.8796119621235086, "grad_norm": 1.4698694944381714, "learning_rate": 2.08816278536476e-05, "loss": 0.48731269836425783, "step": 484440 }, { "epoch": 2.879671404200177, "grad_norm": 2.056262493133545, "learning_rate": 2.0880758919336578e-05, "loss": 0.47120156288146975, "step": 484450 }, { "epoch": 2.8797308462768454, "grad_norm": 1.5364290475845337, "learning_rate": 2.0879890411342885e-05, "loss": 0.36954340934753416, "step": 484460 }, { "epoch": 2.879790288353514, "grad_norm": 1.2422972917556763, "learning_rate": 2.087902232967066e-05, "loss": 0.4277974605560303, "step": 484470 }, { "epoch": 2.879849730430182, "grad_norm": 0.9840850234031677, "learning_rate": 2.0878154674324078e-05, "loss": 0.4350258827209473, "step": 484480 }, { "epoch": 2.8799091725068506, "grad_norm": 1.0873947143554688, "learning_rate": 2.087728744530727e-05, "loss": 0.44770302772521975, "step": 484490 }, { "epoch": 2.879968614583519, "grad_norm": 1.2199410200119019, "learning_rate": 2.08764206426244e-05, "loss": 0.44928932189941406, "step": 484500 }, { "epoch": 2.8800280566601875, "grad_norm": 1.218502402305603, "learning_rate": 2.08755542662796e-05, "loss": 0.48421487808227537, "step": 484510 }, { "epoch": 2.880087498736856, "grad_norm": 1.2548426389694214, "learning_rate": 2.0874688316277026e-05, "loss": 0.47192206382751467, "step": 484520 }, { "epoch": 2.8801469408135243, "grad_norm": 1.2482547760009766, "learning_rate": 2.087382279262082e-05, "loss": 0.43634328842163084, "step": 484530 }, { "epoch": 2.8802063828901927, "grad_norm": 1.3467097282409668, "learning_rate": 2.087295769531512e-05, "loss": 0.4589683532714844, "step": 484540 }, { "epoch": 2.880265824966861, "grad_norm": 1.408676266670227, "learning_rate": 2.0872093024364063e-05, "loss": 0.49915404319763185, "step": 484550 }, { "epoch": 2.8803252670435295, "grad_norm": 1.3929225206375122, "learning_rate": 2.087122877977178e-05, "loss": 0.48641672134399416, "step": 484560 }, { "epoch": 2.880384709120198, "grad_norm": 1.2105456590652466, "learning_rate": 2.0870364961542414e-05, "loss": 0.4061107635498047, "step": 484570 }, { "epoch": 2.8804441511968664, "grad_norm": 1.2397385835647583, "learning_rate": 2.086950156968009e-05, "loss": 0.45584979057312014, "step": 484580 }, { "epoch": 2.8805035932735343, "grad_norm": 1.7689400911331177, "learning_rate": 2.0868638604188953e-05, "loss": 0.46048402786254883, "step": 484590 }, { "epoch": 2.880563035350203, "grad_norm": 1.4462976455688477, "learning_rate": 2.086777606507311e-05, "loss": 0.5001550674438476, "step": 484600 }, { "epoch": 2.880622477426871, "grad_norm": 1.026291847229004, "learning_rate": 2.0866913952336704e-05, "loss": 0.4597773551940918, "step": 484610 }, { "epoch": 2.88068191950354, "grad_norm": 1.1313451528549194, "learning_rate": 2.086605226598385e-05, "loss": 0.45430517196655273, "step": 484620 }, { "epoch": 2.880741361580208, "grad_norm": 1.351453423500061, "learning_rate": 2.0865191006018674e-05, "loss": 0.5173141479492187, "step": 484630 }, { "epoch": 2.8808008036568764, "grad_norm": 1.3312132358551025, "learning_rate": 2.086433017244529e-05, "loss": 0.48368105888366697, "step": 484640 }, { "epoch": 2.880860245733545, "grad_norm": 1.21047043800354, "learning_rate": 2.0863469765267826e-05, "loss": 0.5179032802581787, "step": 484650 }, { "epoch": 2.8809196878102132, "grad_norm": 1.321131706237793, "learning_rate": 2.0862609784490393e-05, "loss": 0.45116734504699707, "step": 484660 }, { "epoch": 2.8809791298868817, "grad_norm": 1.4796812534332275, "learning_rate": 2.0861750230117107e-05, "loss": 0.465189266204834, "step": 484670 }, { "epoch": 2.88103857196355, "grad_norm": 1.152673602104187, "learning_rate": 2.086089110215207e-05, "loss": 0.46233034133911133, "step": 484680 }, { "epoch": 2.8810980140402185, "grad_norm": 1.386018991470337, "learning_rate": 2.0860032400599395e-05, "loss": 0.45296354293823243, "step": 484690 }, { "epoch": 2.881157456116887, "grad_norm": 1.5193185806274414, "learning_rate": 2.0859174125463202e-05, "loss": 0.4343098640441895, "step": 484700 }, { "epoch": 2.8812168981935553, "grad_norm": 1.1056439876556396, "learning_rate": 2.0858316276747582e-05, "loss": 0.5206300735473632, "step": 484710 }, { "epoch": 2.8812763402702237, "grad_norm": 1.3638997077941895, "learning_rate": 2.0857458854456652e-05, "loss": 0.4535490036010742, "step": 484720 }, { "epoch": 2.881335782346892, "grad_norm": 1.4211808443069458, "learning_rate": 2.085660185859451e-05, "loss": 0.43599472045898435, "step": 484730 }, { "epoch": 2.8813952244235606, "grad_norm": 1.2315452098846436, "learning_rate": 2.085574528916524e-05, "loss": 0.48828716278076173, "step": 484740 }, { "epoch": 2.881454666500229, "grad_norm": 1.1746408939361572, "learning_rate": 2.085488914617296e-05, "loss": 0.508747673034668, "step": 484750 }, { "epoch": 2.8815141085768974, "grad_norm": 1.4452937841415405, "learning_rate": 2.0854033429621752e-05, "loss": 0.47144079208374023, "step": 484760 }, { "epoch": 2.881573550653566, "grad_norm": 1.3898509740829468, "learning_rate": 2.0853178139515724e-05, "loss": 0.41379804611206056, "step": 484770 }, { "epoch": 2.8816329927302338, "grad_norm": 1.3091485500335693, "learning_rate": 2.0852323275858952e-05, "loss": 0.45340681076049805, "step": 484780 }, { "epoch": 2.8816924348069026, "grad_norm": 1.283271074295044, "learning_rate": 2.085146883865553e-05, "loss": 0.4375406265258789, "step": 484790 }, { "epoch": 2.8817518768835706, "grad_norm": 1.100597858428955, "learning_rate": 2.085061482790956e-05, "loss": 0.4282581329345703, "step": 484800 }, { "epoch": 2.8818113189602395, "grad_norm": 1.4323594570159912, "learning_rate": 2.084976124362509e-05, "loss": 0.41908903121948243, "step": 484810 }, { "epoch": 2.8818707610369074, "grad_norm": 1.4775676727294922, "learning_rate": 2.084890808580624e-05, "loss": 0.4602818489074707, "step": 484820 }, { "epoch": 2.881930203113576, "grad_norm": 1.499704122543335, "learning_rate": 2.084805535445709e-05, "loss": 0.464280891418457, "step": 484830 }, { "epoch": 2.8819896451902443, "grad_norm": 1.4643073081970215, "learning_rate": 2.0847203049581694e-05, "loss": 0.4428571701049805, "step": 484840 }, { "epoch": 2.8820490872669127, "grad_norm": 1.4040828943252563, "learning_rate": 2.084635117118415e-05, "loss": 0.4619739055633545, "step": 484850 }, { "epoch": 2.882108529343581, "grad_norm": 1.6389808654785156, "learning_rate": 2.0845499719268526e-05, "loss": 0.461897611618042, "step": 484860 }, { "epoch": 2.8821679714202495, "grad_norm": 1.5792592763900757, "learning_rate": 2.0844648693838892e-05, "loss": 0.4793687343597412, "step": 484870 }, { "epoch": 2.882227413496918, "grad_norm": 1.5844498872756958, "learning_rate": 2.0843798094899318e-05, "loss": 0.47078571319580076, "step": 484880 }, { "epoch": 2.8822868555735863, "grad_norm": 1.5014469623565674, "learning_rate": 2.0842947922453884e-05, "loss": 0.5004405975341797, "step": 484890 }, { "epoch": 2.8823462976502547, "grad_norm": 1.2383211851119995, "learning_rate": 2.0842098176506646e-05, "loss": 0.4971640586853027, "step": 484900 }, { "epoch": 2.882405739726923, "grad_norm": 1.5217888355255127, "learning_rate": 2.0841248857061686e-05, "loss": 0.45610618591308594, "step": 484910 }, { "epoch": 2.8824651818035916, "grad_norm": 1.490474820137024, "learning_rate": 2.0840399964123043e-05, "loss": 0.423033618927002, "step": 484920 }, { "epoch": 2.88252462388026, "grad_norm": 1.5724977254867554, "learning_rate": 2.0839551497694783e-05, "loss": 0.4010136604309082, "step": 484930 }, { "epoch": 2.8825840659569284, "grad_norm": 1.263999104499817, "learning_rate": 2.0838703457780985e-05, "loss": 0.4638568878173828, "step": 484940 }, { "epoch": 2.882643508033597, "grad_norm": 1.6380833387374878, "learning_rate": 2.083785584438568e-05, "loss": 0.47131919860839844, "step": 484950 }, { "epoch": 2.8827029501102652, "grad_norm": 1.0449410676956177, "learning_rate": 2.0837008657512936e-05, "loss": 0.3956732749938965, "step": 484960 }, { "epoch": 2.882762392186933, "grad_norm": 1.3043615818023682, "learning_rate": 2.0836161897166807e-05, "loss": 0.4804424285888672, "step": 484970 }, { "epoch": 2.882821834263602, "grad_norm": 1.4753594398498535, "learning_rate": 2.0835315563351345e-05, "loss": 0.5264042854309082, "step": 484980 }, { "epoch": 2.88288127634027, "grad_norm": 1.2742141485214233, "learning_rate": 2.0834469656070586e-05, "loss": 0.4870098114013672, "step": 484990 }, { "epoch": 2.882940718416939, "grad_norm": 1.0018888711929321, "learning_rate": 2.0833624175328585e-05, "loss": 0.39221968650817873, "step": 485000 }, { "epoch": 2.883000160493607, "grad_norm": 5.097621917724609, "learning_rate": 2.083277912112939e-05, "loss": 0.4410714626312256, "step": 485010 }, { "epoch": 2.8830596025702753, "grad_norm": 1.3446253538131714, "learning_rate": 2.083193449347703e-05, "loss": 0.45890026092529296, "step": 485020 }, { "epoch": 2.8831190446469437, "grad_norm": 1.5793362855911255, "learning_rate": 2.0831090292375567e-05, "loss": 0.5004080772399903, "step": 485030 }, { "epoch": 2.883178486723612, "grad_norm": 1.5347483158111572, "learning_rate": 2.0830246517829023e-05, "loss": 0.5044281005859375, "step": 485040 }, { "epoch": 2.8832379288002805, "grad_norm": 1.42825448513031, "learning_rate": 2.0829403169841438e-05, "loss": 0.4849863052368164, "step": 485050 }, { "epoch": 2.883297370876949, "grad_norm": 1.136414885520935, "learning_rate": 2.082856024841685e-05, "loss": 0.45573973655700684, "step": 485060 }, { "epoch": 2.8833568129536173, "grad_norm": 1.425987958908081, "learning_rate": 2.082771775355928e-05, "loss": 0.4369007110595703, "step": 485070 }, { "epoch": 2.8834162550302858, "grad_norm": 1.4246903657913208, "learning_rate": 2.0826875685272772e-05, "loss": 0.47037482261657715, "step": 485080 }, { "epoch": 2.883475697106954, "grad_norm": 0.958571195602417, "learning_rate": 2.0826034043561356e-05, "loss": 0.4767632484436035, "step": 485090 }, { "epoch": 2.8835351391836226, "grad_norm": 1.4039934873580933, "learning_rate": 2.0825192828429048e-05, "loss": 0.4652703285217285, "step": 485100 }, { "epoch": 2.883594581260291, "grad_norm": 1.3359873294830322, "learning_rate": 2.082435203987986e-05, "loss": 0.4956056118011475, "step": 485110 }, { "epoch": 2.8836540233369594, "grad_norm": 1.4356939792633057, "learning_rate": 2.0823511677917844e-05, "loss": 0.44124689102172854, "step": 485120 }, { "epoch": 2.883713465413628, "grad_norm": 1.4170621633529663, "learning_rate": 2.0822671742547e-05, "loss": 0.44628243446350097, "step": 485130 }, { "epoch": 2.8837729074902962, "grad_norm": 1.273028016090393, "learning_rate": 2.082183223377135e-05, "loss": 0.4506070613861084, "step": 485140 }, { "epoch": 2.8838323495669647, "grad_norm": 1.3260687589645386, "learning_rate": 2.082099315159491e-05, "loss": 0.49935126304626465, "step": 485150 }, { "epoch": 2.8838917916436326, "grad_norm": 1.2406775951385498, "learning_rate": 2.0820154496021703e-05, "loss": 0.448256778717041, "step": 485160 }, { "epoch": 2.8839512337203015, "grad_norm": 1.2573801279067993, "learning_rate": 2.081931626705573e-05, "loss": 0.4564670562744141, "step": 485170 }, { "epoch": 2.8840106757969695, "grad_norm": 1.143442153930664, "learning_rate": 2.0818478464700995e-05, "loss": 0.4754368305206299, "step": 485180 }, { "epoch": 2.884070117873638, "grad_norm": 1.5088964700698853, "learning_rate": 2.0817641088961513e-05, "loss": 0.4815785884857178, "step": 485190 }, { "epoch": 2.8841295599503063, "grad_norm": 1.1939804553985596, "learning_rate": 2.08168041398413e-05, "loss": 0.4540811538696289, "step": 485200 }, { "epoch": 2.8841890020269747, "grad_norm": 1.5190818309783936, "learning_rate": 2.0815967617344346e-05, "loss": 0.42502412796020506, "step": 485210 }, { "epoch": 2.884248444103643, "grad_norm": 0.9211401343345642, "learning_rate": 2.0815131521474667e-05, "loss": 0.43778200149536134, "step": 485220 }, { "epoch": 2.8843078861803115, "grad_norm": 1.6431013345718384, "learning_rate": 2.0814295852236238e-05, "loss": 0.44362807273864746, "step": 485230 }, { "epoch": 2.88436732825698, "grad_norm": 1.7116475105285645, "learning_rate": 2.081346060963308e-05, "loss": 0.48915977478027345, "step": 485240 }, { "epoch": 2.8844267703336484, "grad_norm": 1.3629449605941772, "learning_rate": 2.081262579366918e-05, "loss": 0.4552304267883301, "step": 485250 }, { "epoch": 2.8844862124103168, "grad_norm": 1.3027195930480957, "learning_rate": 2.0811791404348523e-05, "loss": 0.5252681732177734, "step": 485260 }, { "epoch": 2.884545654486985, "grad_norm": 1.240203619003296, "learning_rate": 2.0810957441675115e-05, "loss": 0.47968292236328125, "step": 485270 }, { "epoch": 2.8846050965636536, "grad_norm": 1.5053883790969849, "learning_rate": 2.0810123905652952e-05, "loss": 0.4528053283691406, "step": 485280 }, { "epoch": 2.884664538640322, "grad_norm": 1.0092363357543945, "learning_rate": 2.0809290796285987e-05, "loss": 0.44904489517211915, "step": 485290 }, { "epoch": 2.8847239807169904, "grad_norm": 1.0781198740005493, "learning_rate": 2.0808458113578232e-05, "loss": 0.46751818656921384, "step": 485300 }, { "epoch": 2.884783422793659, "grad_norm": 0.8888217806816101, "learning_rate": 2.080762585753367e-05, "loss": 0.47961902618408203, "step": 485310 }, { "epoch": 2.8848428648703273, "grad_norm": 1.2821435928344727, "learning_rate": 2.0806794028156282e-05, "loss": 0.4936084747314453, "step": 485320 }, { "epoch": 2.8849023069469952, "grad_norm": 1.4094773530960083, "learning_rate": 2.0805962625450043e-05, "loss": 0.4923098087310791, "step": 485330 }, { "epoch": 2.884961749023664, "grad_norm": 1.1039655208587646, "learning_rate": 2.0805131649418927e-05, "loss": 0.4615638732910156, "step": 485340 }, { "epoch": 2.885021191100332, "grad_norm": 1.1012258529663086, "learning_rate": 2.0804301100066903e-05, "loss": 0.469284725189209, "step": 485350 }, { "epoch": 2.885080633177001, "grad_norm": 1.3138494491577148, "learning_rate": 2.0803470977397958e-05, "loss": 0.49228968620300295, "step": 485360 }, { "epoch": 2.885140075253669, "grad_norm": 1.152444839477539, "learning_rate": 2.080264128141606e-05, "loss": 0.46228952407836915, "step": 485370 }, { "epoch": 2.8851995173303373, "grad_norm": 1.3615939617156982, "learning_rate": 2.0801812012125176e-05, "loss": 0.4497547149658203, "step": 485380 }, { "epoch": 2.8852589594070057, "grad_norm": 1.0892611742019653, "learning_rate": 2.0800983169529277e-05, "loss": 0.45646305084228517, "step": 485390 }, { "epoch": 2.885318401483674, "grad_norm": 1.3357832431793213, "learning_rate": 2.0800154753632317e-05, "loss": 0.4538093566894531, "step": 485400 }, { "epoch": 2.8853778435603425, "grad_norm": 1.2899030447006226, "learning_rate": 2.0799326764438267e-05, "loss": 0.47791080474853515, "step": 485410 }, { "epoch": 2.885437285637011, "grad_norm": 1.1794787645339966, "learning_rate": 2.079849920195109e-05, "loss": 0.41584253311157227, "step": 485420 }, { "epoch": 2.8854967277136794, "grad_norm": 1.5358959436416626, "learning_rate": 2.079767206617474e-05, "loss": 0.45732684135437013, "step": 485430 }, { "epoch": 2.885556169790348, "grad_norm": 1.0584783554077148, "learning_rate": 2.079684535711317e-05, "loss": 0.44728693962097166, "step": 485440 }, { "epoch": 2.885615611867016, "grad_norm": 1.266318440437317, "learning_rate": 2.0796019074770347e-05, "loss": 0.4545417785644531, "step": 485450 }, { "epoch": 2.8856750539436846, "grad_norm": 1.5772204399108887, "learning_rate": 2.0795193219150213e-05, "loss": 0.4886772155761719, "step": 485460 }, { "epoch": 2.885734496020353, "grad_norm": 1.282856822013855, "learning_rate": 2.0794367790256727e-05, "loss": 0.45963363647460936, "step": 485470 }, { "epoch": 2.8857939380970214, "grad_norm": 1.2695567607879639, "learning_rate": 2.0793542788093835e-05, "loss": 0.4450082778930664, "step": 485480 }, { "epoch": 2.88585338017369, "grad_norm": 1.195888876914978, "learning_rate": 2.0792718212665464e-05, "loss": 0.44307236671447753, "step": 485490 }, { "epoch": 2.8859128222503583, "grad_norm": 1.489283800125122, "learning_rate": 2.0791894063975592e-05, "loss": 0.4474371910095215, "step": 485500 }, { "epoch": 2.8859722643270267, "grad_norm": 1.242130160331726, "learning_rate": 2.079107034202814e-05, "loss": 0.410292387008667, "step": 485510 }, { "epoch": 2.8860317064036947, "grad_norm": 1.188158631324768, "learning_rate": 2.079024704682706e-05, "loss": 0.4697169303894043, "step": 485520 }, { "epoch": 2.8860911484803635, "grad_norm": 1.3033205270767212, "learning_rate": 2.078942417837628e-05, "loss": 0.4942929744720459, "step": 485530 }, { "epoch": 2.8861505905570315, "grad_norm": 1.4350018501281738, "learning_rate": 2.0788601736679732e-05, "loss": 0.40092968940734863, "step": 485540 }, { "epoch": 2.8862100326337004, "grad_norm": 1.1963590383529663, "learning_rate": 2.0787779721741372e-05, "loss": 0.4416388988494873, "step": 485550 }, { "epoch": 2.8862694747103683, "grad_norm": 1.0225454568862915, "learning_rate": 2.0786958133565103e-05, "loss": 0.46857056617736814, "step": 485560 }, { "epoch": 2.8863289167870367, "grad_norm": 1.7656673192977905, "learning_rate": 2.0786136972154885e-05, "loss": 0.5128606796264649, "step": 485570 }, { "epoch": 2.886388358863705, "grad_norm": 1.107867956161499, "learning_rate": 2.0785316237514624e-05, "loss": 0.4387096405029297, "step": 485580 }, { "epoch": 2.8864478009403736, "grad_norm": 1.3791776895523071, "learning_rate": 2.078449592964826e-05, "loss": 0.47376103401184083, "step": 485590 }, { "epoch": 2.886507243017042, "grad_norm": 1.4574555158615112, "learning_rate": 2.0783676048559718e-05, "loss": 0.4632093906402588, "step": 485600 }, { "epoch": 2.8865666850937104, "grad_norm": 1.2980924844741821, "learning_rate": 2.0782856594252898e-05, "loss": 0.45568180084228516, "step": 485610 }, { "epoch": 2.886626127170379, "grad_norm": 1.0395504236221313, "learning_rate": 2.0782037566731744e-05, "loss": 0.4282963752746582, "step": 485620 }, { "epoch": 2.8866855692470472, "grad_norm": 1.1697081327438354, "learning_rate": 2.0781218966000164e-05, "loss": 0.47368173599243163, "step": 485630 }, { "epoch": 2.8867450113237156, "grad_norm": 1.3676937818527222, "learning_rate": 2.0780400792062073e-05, "loss": 0.5001978874206543, "step": 485640 }, { "epoch": 2.886804453400384, "grad_norm": 1.3243448734283447, "learning_rate": 2.0779583044921403e-05, "loss": 0.447597599029541, "step": 485650 }, { "epoch": 2.8868638954770525, "grad_norm": 1.7973712682724, "learning_rate": 2.077876572458203e-05, "loss": 0.4828812599182129, "step": 485660 }, { "epoch": 2.886923337553721, "grad_norm": 1.0990376472473145, "learning_rate": 2.07779488310479e-05, "loss": 0.500041389465332, "step": 485670 }, { "epoch": 2.8869827796303893, "grad_norm": 1.2322046756744385, "learning_rate": 2.0777132364322886e-05, "loss": 0.4290029048919678, "step": 485680 }, { "epoch": 2.8870422217070577, "grad_norm": 1.4642997980117798, "learning_rate": 2.0776316324410925e-05, "loss": 0.4429046630859375, "step": 485690 }, { "epoch": 2.887101663783726, "grad_norm": 1.3090540170669556, "learning_rate": 2.0775500711315905e-05, "loss": 0.497259521484375, "step": 485700 }, { "epoch": 2.887161105860394, "grad_norm": 1.148949384689331, "learning_rate": 2.077468552504174e-05, "loss": 0.47402362823486327, "step": 485710 }, { "epoch": 2.887220547937063, "grad_norm": 1.402271032333374, "learning_rate": 2.07738707655923e-05, "loss": 0.47489261627197266, "step": 485720 }, { "epoch": 2.887279990013731, "grad_norm": 1.530503273010254, "learning_rate": 2.0773056432971515e-05, "loss": 0.46160154342651366, "step": 485730 }, { "epoch": 2.8873394320904, "grad_norm": 1.4825265407562256, "learning_rate": 2.077224252718327e-05, "loss": 0.4257394790649414, "step": 485740 }, { "epoch": 2.8873988741670678, "grad_norm": 1.5448720455169678, "learning_rate": 2.077142904823146e-05, "loss": 0.43991765975952146, "step": 485750 }, { "epoch": 2.887458316243736, "grad_norm": 1.410369634628296, "learning_rate": 2.0770615996119963e-05, "loss": 0.4897468566894531, "step": 485760 }, { "epoch": 2.8875177583204046, "grad_norm": 1.2998926639556885, "learning_rate": 2.0769803370852685e-05, "loss": 0.43627347946166994, "step": 485770 }, { "epoch": 2.887577200397073, "grad_norm": 1.3193341493606567, "learning_rate": 2.0768991172433505e-05, "loss": 0.49311008453369143, "step": 485780 }, { "epoch": 2.8876366424737414, "grad_norm": 1.1932284832000732, "learning_rate": 2.0768179400866313e-05, "loss": 0.44501447677612305, "step": 485790 }, { "epoch": 2.88769608455041, "grad_norm": 1.5756421089172363, "learning_rate": 2.0767368056154984e-05, "loss": 0.4678135871887207, "step": 485800 }, { "epoch": 2.8877555266270782, "grad_norm": 1.3282177448272705, "learning_rate": 2.0766557138303405e-05, "loss": 0.4716236114501953, "step": 485810 }, { "epoch": 2.8878149687037467, "grad_norm": 1.3608992099761963, "learning_rate": 2.0765746647315452e-05, "loss": 0.4247603893280029, "step": 485820 }, { "epoch": 2.887874410780415, "grad_norm": 1.1776690483093262, "learning_rate": 2.0764936583195022e-05, "loss": 0.4956092834472656, "step": 485830 }, { "epoch": 2.8879338528570835, "grad_norm": 1.486989140510559, "learning_rate": 2.0764126945945966e-05, "loss": 0.4665501594543457, "step": 485840 }, { "epoch": 2.887993294933752, "grad_norm": 0.9765626788139343, "learning_rate": 2.0763317735572147e-05, "loss": 0.47885541915893554, "step": 485850 }, { "epoch": 2.8880527370104203, "grad_norm": 1.6617701053619385, "learning_rate": 2.076250895207747e-05, "loss": 0.45560636520385744, "step": 485860 }, { "epoch": 2.8881121790870887, "grad_norm": 1.4282046556472778, "learning_rate": 2.0761700595465783e-05, "loss": 0.508139705657959, "step": 485870 }, { "epoch": 2.888171621163757, "grad_norm": 1.2791178226470947, "learning_rate": 2.0760892665740962e-05, "loss": 0.4707071781158447, "step": 485880 }, { "epoch": 2.8882310632404256, "grad_norm": 1.1993595361709595, "learning_rate": 2.0760085162906862e-05, "loss": 0.4207131385803223, "step": 485890 }, { "epoch": 2.8882905053170935, "grad_norm": 1.143237590789795, "learning_rate": 2.0759278086967352e-05, "loss": 0.47636823654174804, "step": 485900 }, { "epoch": 2.8883499473937624, "grad_norm": 1.308178186416626, "learning_rate": 2.0758471437926288e-05, "loss": 0.47756280899047854, "step": 485910 }, { "epoch": 2.8884093894704304, "grad_norm": 1.3969942331314087, "learning_rate": 2.0757665215787532e-05, "loss": 0.4681959629058838, "step": 485920 }, { "epoch": 2.8884688315470988, "grad_norm": 1.1525958776474, "learning_rate": 2.075685942055494e-05, "loss": 0.43814702033996583, "step": 485930 }, { "epoch": 2.888528273623767, "grad_norm": 1.054126262664795, "learning_rate": 2.0756054052232368e-05, "loss": 0.45681171417236327, "step": 485940 }, { "epoch": 2.8885877157004356, "grad_norm": 1.5152143239974976, "learning_rate": 2.075524911082367e-05, "loss": 0.5084044456481933, "step": 485950 }, { "epoch": 2.888647157777104, "grad_norm": 1.3949849605560303, "learning_rate": 2.0754444596332695e-05, "loss": 0.4916349411010742, "step": 485960 }, { "epoch": 2.8887065998537724, "grad_norm": 1.196609616279602, "learning_rate": 2.0753640508763296e-05, "loss": 0.42761955261230467, "step": 485970 }, { "epoch": 2.888766041930441, "grad_norm": 1.449802041053772, "learning_rate": 2.07528368481193e-05, "loss": 0.4572917938232422, "step": 485980 }, { "epoch": 2.8888254840071093, "grad_norm": 1.0345940589904785, "learning_rate": 2.0752033614404582e-05, "loss": 0.4620722770690918, "step": 485990 }, { "epoch": 2.8888849260837777, "grad_norm": 1.5198864936828613, "learning_rate": 2.075123080762297e-05, "loss": 0.4159239768981934, "step": 486000 }, { "epoch": 2.888944368160446, "grad_norm": 1.4694535732269287, "learning_rate": 2.0750428427778293e-05, "loss": 0.4739060878753662, "step": 486010 }, { "epoch": 2.8890038102371145, "grad_norm": 0.9862247109413147, "learning_rate": 2.0749626474874402e-05, "loss": 0.42783169746398925, "step": 486020 }, { "epoch": 2.889063252313783, "grad_norm": 1.6026555299758911, "learning_rate": 2.0748824948915137e-05, "loss": 0.45504207611083985, "step": 486030 }, { "epoch": 2.8891226943904513, "grad_norm": 1.3745123147964478, "learning_rate": 2.074802384990432e-05, "loss": 0.5122336387634278, "step": 486040 }, { "epoch": 2.8891821364671197, "grad_norm": 1.5885099172592163, "learning_rate": 2.0747223177845785e-05, "loss": 0.5398933410644531, "step": 486050 }, { "epoch": 2.889241578543788, "grad_norm": 1.2703819274902344, "learning_rate": 2.074642293274337e-05, "loss": 0.4535046577453613, "step": 486060 }, { "epoch": 2.889301020620456, "grad_norm": 1.6417316198349, "learning_rate": 2.0745623114600894e-05, "loss": 0.4805158615112305, "step": 486070 }, { "epoch": 2.889360462697125, "grad_norm": 1.0333770513534546, "learning_rate": 2.074482372342219e-05, "loss": 0.4384159088134766, "step": 486080 }, { "epoch": 2.889419904773793, "grad_norm": 1.3406946659088135, "learning_rate": 2.0744024759211093e-05, "loss": 0.42594280242919924, "step": 486090 }, { "epoch": 2.889479346850462, "grad_norm": 1.6262046098709106, "learning_rate": 2.0743226221971397e-05, "loss": 0.4956388473510742, "step": 486100 }, { "epoch": 2.88953878892713, "grad_norm": 1.1830904483795166, "learning_rate": 2.0742428111706952e-05, "loss": 0.45892982482910155, "step": 486110 }, { "epoch": 2.889598231003798, "grad_norm": 1.1837469339370728, "learning_rate": 2.0741630428421547e-05, "loss": 0.43355188369750974, "step": 486120 }, { "epoch": 2.8896576730804666, "grad_norm": 1.7568503618240356, "learning_rate": 2.074083317211902e-05, "loss": 0.46405644416809083, "step": 486130 }, { "epoch": 2.889717115157135, "grad_norm": 1.0752371549606323, "learning_rate": 2.074003634280318e-05, "loss": 0.4296594142913818, "step": 486140 }, { "epoch": 2.8897765572338034, "grad_norm": 1.0455372333526611, "learning_rate": 2.073923994047782e-05, "loss": 0.4049665451049805, "step": 486150 }, { "epoch": 2.889835999310472, "grad_norm": 1.8972657918930054, "learning_rate": 2.0738443965146788e-05, "loss": 0.45451717376708983, "step": 486160 }, { "epoch": 2.8898954413871403, "grad_norm": 1.4487481117248535, "learning_rate": 2.0737648416813855e-05, "loss": 0.45452537536621096, "step": 486170 }, { "epoch": 2.8899548834638087, "grad_norm": 1.6983928680419922, "learning_rate": 2.073685329548284e-05, "loss": 0.4579127311706543, "step": 486180 }, { "epoch": 2.890014325540477, "grad_norm": 1.1541844606399536, "learning_rate": 2.0736058601157543e-05, "loss": 0.5692607879638671, "step": 486190 }, { "epoch": 2.8900737676171455, "grad_norm": 1.1029173135757446, "learning_rate": 2.0735264333841786e-05, "loss": 0.4654454231262207, "step": 486200 }, { "epoch": 2.890133209693814, "grad_norm": 1.2704075574874878, "learning_rate": 2.0734470493539343e-05, "loss": 0.43699064254760744, "step": 486210 }, { "epoch": 2.8901926517704823, "grad_norm": 1.6262322664260864, "learning_rate": 2.0733677080254022e-05, "loss": 0.4777683258056641, "step": 486220 }, { "epoch": 2.8902520938471508, "grad_norm": 1.0694645643234253, "learning_rate": 2.0732884093989607e-05, "loss": 0.4685725212097168, "step": 486230 }, { "epoch": 2.890311535923819, "grad_norm": 1.2049622535705566, "learning_rate": 2.073209153474992e-05, "loss": 0.4828490257263184, "step": 486240 }, { "epoch": 2.8903709780004876, "grad_norm": 1.2724370956420898, "learning_rate": 2.0731299402538717e-05, "loss": 0.4712515830993652, "step": 486250 }, { "epoch": 2.8904304200771556, "grad_norm": 1.4104994535446167, "learning_rate": 2.0730507697359823e-05, "loss": 0.45287394523620605, "step": 486260 }, { "epoch": 2.8904898621538244, "grad_norm": 1.297752857208252, "learning_rate": 2.0729716419216995e-05, "loss": 0.4509106636047363, "step": 486270 }, { "epoch": 2.8905493042304924, "grad_norm": 1.527269959449768, "learning_rate": 2.0728925568114026e-05, "loss": 0.42214102745056153, "step": 486280 }, { "epoch": 2.8906087463071612, "grad_norm": 1.1424387693405151, "learning_rate": 2.0728135144054712e-05, "loss": 0.47702727317810056, "step": 486290 }, { "epoch": 2.890668188383829, "grad_norm": 0.9857640266418457, "learning_rate": 2.0727345147042816e-05, "loss": 0.44063501358032225, "step": 486300 }, { "epoch": 2.8907276304604976, "grad_norm": 1.7743459939956665, "learning_rate": 2.0726555577082133e-05, "loss": 0.4306760311126709, "step": 486310 }, { "epoch": 2.890787072537166, "grad_norm": 1.1024789810180664, "learning_rate": 2.0725766434176432e-05, "loss": 0.49497394561767577, "step": 486320 }, { "epoch": 2.8908465146138345, "grad_norm": 1.39509916305542, "learning_rate": 2.0724977718329485e-05, "loss": 0.4687823295593262, "step": 486330 }, { "epoch": 2.890905956690503, "grad_norm": 1.1046785116195679, "learning_rate": 2.072418942954508e-05, "loss": 0.4677712917327881, "step": 486340 }, { "epoch": 2.8909653987671713, "grad_norm": 0.968004047870636, "learning_rate": 2.0723401567826962e-05, "loss": 0.48319277763366697, "step": 486350 }, { "epoch": 2.8910248408438397, "grad_norm": 1.3715945482254028, "learning_rate": 2.0722614133178928e-05, "loss": 0.4441249847412109, "step": 486360 }, { "epoch": 2.891084282920508, "grad_norm": 1.3313246965408325, "learning_rate": 2.0721827125604726e-05, "loss": 0.47463741302490237, "step": 486370 }, { "epoch": 2.8911437249971765, "grad_norm": 1.2792857885360718, "learning_rate": 2.072104054510813e-05, "loss": 0.49946322441101076, "step": 486380 }, { "epoch": 2.891203167073845, "grad_norm": 1.3545888662338257, "learning_rate": 2.0720254391692893e-05, "loss": 0.41652798652648926, "step": 486390 }, { "epoch": 2.8912626091505134, "grad_norm": 1.6267602443695068, "learning_rate": 2.0719468665362794e-05, "loss": 0.4242091178894043, "step": 486400 }, { "epoch": 2.8913220512271818, "grad_norm": 1.3076744079589844, "learning_rate": 2.071868336612156e-05, "loss": 0.47199578285217286, "step": 486410 }, { "epoch": 2.89138149330385, "grad_norm": 1.399720311164856, "learning_rate": 2.0717898493972987e-05, "loss": 0.48677353858947753, "step": 486420 }, { "epoch": 2.8914409353805186, "grad_norm": 1.1316030025482178, "learning_rate": 2.0717114048920798e-05, "loss": 0.4466671943664551, "step": 486430 }, { "epoch": 2.891500377457187, "grad_norm": 1.048631191253662, "learning_rate": 2.071633003096876e-05, "loss": 0.4822256088256836, "step": 486440 }, { "epoch": 2.891559819533855, "grad_norm": 1.042659878730774, "learning_rate": 2.0715546440120624e-05, "loss": 0.4675448417663574, "step": 486450 }, { "epoch": 2.891619261610524, "grad_norm": 1.4467816352844238, "learning_rate": 2.0714763276380134e-05, "loss": 0.49053206443786623, "step": 486460 }, { "epoch": 2.891678703687192, "grad_norm": 1.381230354309082, "learning_rate": 2.071398053975104e-05, "loss": 0.49530625343322754, "step": 486470 }, { "epoch": 2.8917381457638607, "grad_norm": 1.2450720071792603, "learning_rate": 2.0713198230237072e-05, "loss": 0.41912236213684084, "step": 486480 }, { "epoch": 2.8917975878405286, "grad_norm": 1.1317899227142334, "learning_rate": 2.0712416347841993e-05, "loss": 0.4403717517852783, "step": 486490 }, { "epoch": 2.891857029917197, "grad_norm": 1.2958155870437622, "learning_rate": 2.0711634892569543e-05, "loss": 0.42845544815063474, "step": 486500 }, { "epoch": 2.8919164719938655, "grad_norm": 1.224929928779602, "learning_rate": 2.0710853864423445e-05, "loss": 0.4089180946350098, "step": 486510 }, { "epoch": 2.891975914070534, "grad_norm": 1.3978307247161865, "learning_rate": 2.0710073263407436e-05, "loss": 0.44577836990356445, "step": 486520 }, { "epoch": 2.8920353561472023, "grad_norm": 1.095126986503601, "learning_rate": 2.070929308952527e-05, "loss": 0.4693304538726807, "step": 486530 }, { "epoch": 2.8920947982238707, "grad_norm": 1.316148042678833, "learning_rate": 2.0708513342780646e-05, "loss": 0.472036075592041, "step": 486540 }, { "epoch": 2.892154240300539, "grad_norm": 1.4274377822875977, "learning_rate": 2.0707734023177327e-05, "loss": 0.42462930679321287, "step": 486550 }, { "epoch": 2.8922136823772076, "grad_norm": 1.2948380708694458, "learning_rate": 2.0706955130719027e-05, "loss": 0.46413211822509765, "step": 486560 }, { "epoch": 2.892273124453876, "grad_norm": 1.3141438961029053, "learning_rate": 2.0706176665409472e-05, "loss": 0.47731494903564453, "step": 486570 }, { "epoch": 2.8923325665305444, "grad_norm": 1.2251718044281006, "learning_rate": 2.070539862725238e-05, "loss": 0.4571199417114258, "step": 486580 }, { "epoch": 2.892392008607213, "grad_norm": 1.3069148063659668, "learning_rate": 2.070462101625149e-05, "loss": 0.4472538948059082, "step": 486590 }, { "epoch": 2.892451450683881, "grad_norm": 1.7573601007461548, "learning_rate": 2.0703843832410496e-05, "loss": 0.5016330718994141, "step": 486600 }, { "epoch": 2.8925108927605496, "grad_norm": 1.0412862300872803, "learning_rate": 2.070306707573314e-05, "loss": 0.45852861404418943, "step": 486610 }, { "epoch": 2.892570334837218, "grad_norm": 1.2051194906234741, "learning_rate": 2.0702290746223134e-05, "loss": 0.44567255973815917, "step": 486620 }, { "epoch": 2.8926297769138865, "grad_norm": 1.270249605178833, "learning_rate": 2.0701514843884173e-05, "loss": 0.4606305122375488, "step": 486630 }, { "epoch": 2.8926892189905544, "grad_norm": 1.356671929359436, "learning_rate": 2.070073936871999e-05, "loss": 0.43495845794677734, "step": 486640 }, { "epoch": 2.8927486610672233, "grad_norm": 1.1908003091812134, "learning_rate": 2.0699964320734287e-05, "loss": 0.45048208236694337, "step": 486650 }, { "epoch": 2.8928081031438913, "grad_norm": 1.3926464319229126, "learning_rate": 2.0699189699930768e-05, "loss": 0.44242067337036134, "step": 486660 }, { "epoch": 2.8928675452205597, "grad_norm": 1.4605215787887573, "learning_rate": 2.0698415506313147e-05, "loss": 0.5084085464477539, "step": 486670 }, { "epoch": 2.892926987297228, "grad_norm": 1.3905543088912964, "learning_rate": 2.0697641739885114e-05, "loss": 0.49078760147094724, "step": 486680 }, { "epoch": 2.8929864293738965, "grad_norm": 1.1833490133285522, "learning_rate": 2.0696868400650393e-05, "loss": 0.450379467010498, "step": 486690 }, { "epoch": 2.893045871450565, "grad_norm": 1.391481876373291, "learning_rate": 2.0696095488612653e-05, "loss": 0.4745031833648682, "step": 486700 }, { "epoch": 2.8931053135272333, "grad_norm": 1.8623740673065186, "learning_rate": 2.0695323003775617e-05, "loss": 0.4927236557006836, "step": 486710 }, { "epoch": 2.8931647556039017, "grad_norm": 1.4051481485366821, "learning_rate": 2.069455094614296e-05, "loss": 0.45692949295043944, "step": 486720 }, { "epoch": 2.89322419768057, "grad_norm": 1.315789818763733, "learning_rate": 2.0693779315718393e-05, "loss": 0.40569705963134767, "step": 486730 }, { "epoch": 2.8932836397572386, "grad_norm": 1.2478278875350952, "learning_rate": 2.06930081125056e-05, "loss": 0.46305274963378906, "step": 486740 }, { "epoch": 2.893343081833907, "grad_norm": 1.532358169555664, "learning_rate": 2.0692237336508273e-05, "loss": 0.4046076774597168, "step": 486750 }, { "epoch": 2.8934025239105754, "grad_norm": 1.304978370666504, "learning_rate": 2.0691466987730097e-05, "loss": 0.41744303703308105, "step": 486760 }, { "epoch": 2.893461965987244, "grad_norm": 1.022491693496704, "learning_rate": 2.0690697066174747e-05, "loss": 0.44924249649047854, "step": 486770 }, { "epoch": 2.8935214080639122, "grad_norm": 1.4031440019607544, "learning_rate": 2.0689927571845923e-05, "loss": 0.4376307487487793, "step": 486780 }, { "epoch": 2.8935808501405806, "grad_norm": 1.3543338775634766, "learning_rate": 2.068915850474731e-05, "loss": 0.4642171859741211, "step": 486790 }, { "epoch": 2.893640292217249, "grad_norm": 1.4082920551300049, "learning_rate": 2.068838986488255e-05, "loss": 0.431123161315918, "step": 486800 }, { "epoch": 2.893699734293917, "grad_norm": 1.1627249717712402, "learning_rate": 2.068762165225537e-05, "loss": 0.43862247467041016, "step": 486810 }, { "epoch": 2.893759176370586, "grad_norm": 1.9188631772994995, "learning_rate": 2.068685386686941e-05, "loss": 0.4461048126220703, "step": 486820 }, { "epoch": 2.893818618447254, "grad_norm": 1.0052728652954102, "learning_rate": 2.068608650872834e-05, "loss": 0.41957674026489256, "step": 486830 }, { "epoch": 2.8938780605239227, "grad_norm": 1.037370204925537, "learning_rate": 2.0685319577835857e-05, "loss": 0.4352383613586426, "step": 486840 }, { "epoch": 2.8939375026005907, "grad_norm": 1.6448783874511719, "learning_rate": 2.0684553074195617e-05, "loss": 0.4945096969604492, "step": 486850 }, { "epoch": 2.893996944677259, "grad_norm": 1.199512243270874, "learning_rate": 2.068378699781129e-05, "loss": 0.4649043083190918, "step": 486860 }, { "epoch": 2.8940563867539275, "grad_norm": 1.647655963897705, "learning_rate": 2.0683021348686536e-05, "loss": 0.4940537452697754, "step": 486870 }, { "epoch": 2.894115828830596, "grad_norm": 1.0338126420974731, "learning_rate": 2.0682256126825013e-05, "loss": 0.4349393844604492, "step": 486880 }, { "epoch": 2.8941752709072643, "grad_norm": 1.3897764682769775, "learning_rate": 2.068149133223039e-05, "loss": 0.4437414169311523, "step": 486890 }, { "epoch": 2.8942347129839328, "grad_norm": 1.2143027782440186, "learning_rate": 2.068072696490632e-05, "loss": 0.5082924842834473, "step": 486900 }, { "epoch": 2.894294155060601, "grad_norm": 1.0075353384017944, "learning_rate": 2.0679963024856464e-05, "loss": 0.4515162467956543, "step": 486910 }, { "epoch": 2.8943535971372696, "grad_norm": 1.0846879482269287, "learning_rate": 2.0679199512084476e-05, "loss": 0.46032133102416994, "step": 486920 }, { "epoch": 2.894413039213938, "grad_norm": 1.3678778409957886, "learning_rate": 2.0678436426594012e-05, "loss": 0.4435539245605469, "step": 486930 }, { "epoch": 2.8944724812906064, "grad_norm": 1.430540919303894, "learning_rate": 2.0677673768388713e-05, "loss": 0.46796574592590334, "step": 486940 }, { "epoch": 2.894531923367275, "grad_norm": 1.3811057806015015, "learning_rate": 2.0676911537472236e-05, "loss": 0.455857515335083, "step": 486950 }, { "epoch": 2.8945913654439432, "grad_norm": 1.0859451293945312, "learning_rate": 2.0676149733848215e-05, "loss": 0.43691096305847166, "step": 486960 }, { "epoch": 2.8946508075206117, "grad_norm": 0.9862753748893738, "learning_rate": 2.06753883575203e-05, "loss": 0.4567741394042969, "step": 486970 }, { "epoch": 2.89471024959728, "grad_norm": 1.5322620868682861, "learning_rate": 2.0674627408492143e-05, "loss": 0.45487384796142577, "step": 486980 }, { "epoch": 2.8947696916739485, "grad_norm": 1.296342134475708, "learning_rate": 2.0673866886767374e-05, "loss": 0.44042072296142576, "step": 486990 }, { "epoch": 2.8948291337506165, "grad_norm": 1.3065980672836304, "learning_rate": 2.067310679234964e-05, "loss": 0.46163668632507326, "step": 487000 }, { "epoch": 2.8948885758272853, "grad_norm": 1.4842473268508911, "learning_rate": 2.067234712524257e-05, "loss": 0.4429001808166504, "step": 487010 }, { "epoch": 2.8949480179039533, "grad_norm": 1.2147178649902344, "learning_rate": 2.0671587885449793e-05, "loss": 0.44226322174072263, "step": 487020 }, { "epoch": 2.895007459980622, "grad_norm": 1.3788725137710571, "learning_rate": 2.0670829072974936e-05, "loss": 0.4586039543151855, "step": 487030 }, { "epoch": 2.89506690205729, "grad_norm": 1.0522352457046509, "learning_rate": 2.067007068782166e-05, "loss": 0.43526496887207033, "step": 487040 }, { "epoch": 2.8951263441339585, "grad_norm": 1.491218090057373, "learning_rate": 2.0669312729993558e-05, "loss": 0.4448955535888672, "step": 487050 }, { "epoch": 2.895185786210627, "grad_norm": 1.6930476427078247, "learning_rate": 2.066855519949428e-05, "loss": 0.48757495880126955, "step": 487060 }, { "epoch": 2.8952452282872954, "grad_norm": 1.513065218925476, "learning_rate": 2.066779809632744e-05, "loss": 0.4599980354309082, "step": 487070 }, { "epoch": 2.8953046703639638, "grad_norm": 1.0062252283096313, "learning_rate": 2.0667041420496658e-05, "loss": 0.447878360748291, "step": 487080 }, { "epoch": 2.895364112440632, "grad_norm": 1.348933458328247, "learning_rate": 2.066628517200555e-05, "loss": 0.4477236747741699, "step": 487090 }, { "epoch": 2.8954235545173006, "grad_norm": 1.1880580186843872, "learning_rate": 2.066552935085774e-05, "loss": 0.4406414985656738, "step": 487100 }, { "epoch": 2.895482996593969, "grad_norm": 1.2121797800064087, "learning_rate": 2.066477395705685e-05, "loss": 0.47762632369995117, "step": 487110 }, { "epoch": 2.8955424386706374, "grad_norm": 1.7146213054656982, "learning_rate": 2.0664018990606482e-05, "loss": 0.47864208221435545, "step": 487120 }, { "epoch": 2.895601880747306, "grad_norm": 0.8839303255081177, "learning_rate": 2.066326445151025e-05, "loss": 0.40971221923828127, "step": 487130 }, { "epoch": 2.8956613228239743, "grad_norm": 1.4310084581375122, "learning_rate": 2.0662510339771774e-05, "loss": 0.4529751777648926, "step": 487140 }, { "epoch": 2.8957207649006427, "grad_norm": 1.0155192613601685, "learning_rate": 2.0661756655394645e-05, "loss": 0.43572444915771485, "step": 487150 }, { "epoch": 2.895780206977311, "grad_norm": 1.2501592636108398, "learning_rate": 2.066100339838247e-05, "loss": 0.4306177139282227, "step": 487160 }, { "epoch": 2.8958396490539795, "grad_norm": 1.6240713596343994, "learning_rate": 2.066025056873887e-05, "loss": 0.5229989051818847, "step": 487170 }, { "epoch": 2.895899091130648, "grad_norm": 1.0830894708633423, "learning_rate": 2.065949816646743e-05, "loss": 0.4411479949951172, "step": 487180 }, { "epoch": 2.895958533207316, "grad_norm": 1.3910986185073853, "learning_rate": 2.065874619157175e-05, "loss": 0.459886360168457, "step": 487190 }, { "epoch": 2.8960179752839847, "grad_norm": 1.3737413883209229, "learning_rate": 2.0657994644055438e-05, "loss": 0.4804116725921631, "step": 487200 }, { "epoch": 2.8960774173606527, "grad_norm": 1.4947350025177002, "learning_rate": 2.0657243523922076e-05, "loss": 0.46510915756225585, "step": 487210 }, { "epoch": 2.8961368594373216, "grad_norm": 1.303382396697998, "learning_rate": 2.0656492831175273e-05, "loss": 0.5021825790405273, "step": 487220 }, { "epoch": 2.8961963015139895, "grad_norm": 1.1056931018829346, "learning_rate": 2.06557425658186e-05, "loss": 0.45508289337158203, "step": 487230 }, { "epoch": 2.896255743590658, "grad_norm": 1.4311044216156006, "learning_rate": 2.0654992727855658e-05, "loss": 0.42991127967834475, "step": 487240 }, { "epoch": 2.8963151856673264, "grad_norm": 1.4178844690322876, "learning_rate": 2.0654243317290045e-05, "loss": 0.4638528347015381, "step": 487250 }, { "epoch": 2.896374627743995, "grad_norm": 1.3235933780670166, "learning_rate": 2.0653494334125317e-05, "loss": 0.5075840950012207, "step": 487260 }, { "epoch": 2.896434069820663, "grad_norm": 1.351161241531372, "learning_rate": 2.065274577836508e-05, "loss": 0.45803146362304686, "step": 487270 }, { "epoch": 2.8964935118973316, "grad_norm": 1.464296579360962, "learning_rate": 2.065199765001291e-05, "loss": 0.4484230041503906, "step": 487280 }, { "epoch": 2.896552953974, "grad_norm": 1.3092238903045654, "learning_rate": 2.0651249949072378e-05, "loss": 0.443571949005127, "step": 487290 }, { "epoch": 2.8966123960506684, "grad_norm": 1.2522602081298828, "learning_rate": 2.0650502675547082e-05, "loss": 0.4228250503540039, "step": 487300 }, { "epoch": 2.896671838127337, "grad_norm": 1.4052773714065552, "learning_rate": 2.064975582944057e-05, "loss": 0.5054591655731201, "step": 487310 }, { "epoch": 2.8967312802040053, "grad_norm": 0.9086586833000183, "learning_rate": 2.064900941075643e-05, "loss": 0.439588737487793, "step": 487320 }, { "epoch": 2.8967907222806737, "grad_norm": 1.5462899208068848, "learning_rate": 2.0648263419498216e-05, "loss": 0.47552990913391113, "step": 487330 }, { "epoch": 2.896850164357342, "grad_norm": 1.4427391290664673, "learning_rate": 2.064751785566952e-05, "loss": 0.4531558990478516, "step": 487340 }, { "epoch": 2.8969096064340105, "grad_norm": 1.203345775604248, "learning_rate": 2.0646772719273904e-05, "loss": 0.3930227279663086, "step": 487350 }, { "epoch": 2.896969048510679, "grad_norm": 1.2579306364059448, "learning_rate": 2.0646028010314915e-05, "loss": 0.43901824951171875, "step": 487360 }, { "epoch": 2.8970284905873473, "grad_norm": 1.0876023769378662, "learning_rate": 2.0645283728796137e-05, "loss": 0.5060172080993652, "step": 487370 }, { "epoch": 2.8970879326640153, "grad_norm": 1.3295263051986694, "learning_rate": 2.0644539874721115e-05, "loss": 0.4180456638336182, "step": 487380 }, { "epoch": 2.897147374740684, "grad_norm": 1.3110171556472778, "learning_rate": 2.0643796448093405e-05, "loss": 0.45542058944702146, "step": 487390 }, { "epoch": 2.897206816817352, "grad_norm": 1.153188705444336, "learning_rate": 2.064305344891658e-05, "loss": 0.4690400123596191, "step": 487400 }, { "epoch": 2.8972662588940206, "grad_norm": 1.3054834604263306, "learning_rate": 2.064231087719418e-05, "loss": 0.4390374183654785, "step": 487410 }, { "epoch": 2.897325700970689, "grad_norm": 1.1766619682312012, "learning_rate": 2.0641568732929767e-05, "loss": 0.4472965240478516, "step": 487420 }, { "epoch": 2.8973851430473574, "grad_norm": 1.0374112129211426, "learning_rate": 2.0640827016126892e-05, "loss": 0.4331180572509766, "step": 487430 }, { "epoch": 2.897444585124026, "grad_norm": 1.6344386339187622, "learning_rate": 2.0640085726789087e-05, "loss": 0.44696712493896484, "step": 487440 }, { "epoch": 2.897504027200694, "grad_norm": 1.2627781629562378, "learning_rate": 2.0639344864919913e-05, "loss": 0.4572101593017578, "step": 487450 }, { "epoch": 2.8975634692773626, "grad_norm": 1.3099393844604492, "learning_rate": 2.0638604430522897e-05, "loss": 0.4551185131072998, "step": 487460 }, { "epoch": 2.897622911354031, "grad_norm": 1.1380116939544678, "learning_rate": 2.0637864423601606e-05, "loss": 0.41481781005859375, "step": 487470 }, { "epoch": 2.8976823534306995, "grad_norm": 1.2279993295669556, "learning_rate": 2.063712484415957e-05, "loss": 0.46461195945739747, "step": 487480 }, { "epoch": 2.897741795507368, "grad_norm": 1.3768740892410278, "learning_rate": 2.063638569220033e-05, "loss": 0.4742616653442383, "step": 487490 }, { "epoch": 2.8978012375840363, "grad_norm": 1.1695584058761597, "learning_rate": 2.0635646967727406e-05, "loss": 0.4345064163208008, "step": 487500 }, { "epoch": 2.8978606796607047, "grad_norm": 1.3335306644439697, "learning_rate": 2.0634908670744347e-05, "loss": 0.4313045024871826, "step": 487510 }, { "epoch": 2.897920121737373, "grad_norm": 1.5471961498260498, "learning_rate": 2.0634170801254666e-05, "loss": 0.46744914054870607, "step": 487520 }, { "epoch": 2.8979795638140415, "grad_norm": 1.3106378316879272, "learning_rate": 2.0633433359261928e-05, "loss": 0.4548341751098633, "step": 487530 }, { "epoch": 2.89803900589071, "grad_norm": 1.4623204469680786, "learning_rate": 2.0632696344769632e-05, "loss": 0.43137421607971194, "step": 487540 }, { "epoch": 2.898098447967378, "grad_norm": 0.9315485954284668, "learning_rate": 2.063195975778131e-05, "loss": 0.4161405086517334, "step": 487550 }, { "epoch": 2.898157890044047, "grad_norm": 1.2232946157455444, "learning_rate": 2.0631223598300485e-05, "loss": 0.44729928970336913, "step": 487560 }, { "epoch": 2.8982173321207148, "grad_norm": 1.630670428276062, "learning_rate": 2.0630487866330678e-05, "loss": 0.501996374130249, "step": 487570 }, { "epoch": 2.8982767741973836, "grad_norm": 1.5767641067504883, "learning_rate": 2.062975256187541e-05, "loss": 0.5046411514282226, "step": 487580 }, { "epoch": 2.8983362162740516, "grad_norm": 1.1899139881134033, "learning_rate": 2.062901768493821e-05, "loss": 0.4491007328033447, "step": 487590 }, { "epoch": 2.89839565835072, "grad_norm": 1.2919484376907349, "learning_rate": 2.0628283235522573e-05, "loss": 0.46979751586914065, "step": 487600 }, { "epoch": 2.8984551004273884, "grad_norm": 1.2778217792510986, "learning_rate": 2.0627549213632025e-05, "loss": 0.4397444248199463, "step": 487610 }, { "epoch": 2.898514542504057, "grad_norm": 1.0631098747253418, "learning_rate": 2.062681561927008e-05, "loss": 0.4694009780883789, "step": 487620 }, { "epoch": 2.8985739845807252, "grad_norm": 1.3324579000473022, "learning_rate": 2.0626082452440233e-05, "loss": 0.46677513122558595, "step": 487630 }, { "epoch": 2.8986334266573937, "grad_norm": 1.704030990600586, "learning_rate": 2.0625349713146e-05, "loss": 0.4755691051483154, "step": 487640 }, { "epoch": 2.898692868734062, "grad_norm": 1.4132883548736572, "learning_rate": 2.0624617401390888e-05, "loss": 0.43935451507568357, "step": 487650 }, { "epoch": 2.8987523108107305, "grad_norm": 1.3215748071670532, "learning_rate": 2.0623885517178402e-05, "loss": 0.47339491844177245, "step": 487660 }, { "epoch": 2.898811752887399, "grad_norm": 1.4312258958816528, "learning_rate": 2.0623154060512034e-05, "loss": 0.4597465515136719, "step": 487670 }, { "epoch": 2.8988711949640673, "grad_norm": 1.1848244667053223, "learning_rate": 2.0622423031395294e-05, "loss": 0.47232255935668943, "step": 487680 }, { "epoch": 2.8989306370407357, "grad_norm": 1.2421525716781616, "learning_rate": 2.0621692429831664e-05, "loss": 0.45403461456298827, "step": 487690 }, { "epoch": 2.898990079117404, "grad_norm": 1.2304890155792236, "learning_rate": 2.062096225582466e-05, "loss": 0.43831558227539064, "step": 487700 }, { "epoch": 2.8990495211940726, "grad_norm": 1.0881246328353882, "learning_rate": 2.0620232509377758e-05, "loss": 0.4477675437927246, "step": 487710 }, { "epoch": 2.899108963270741, "grad_norm": 1.2855439186096191, "learning_rate": 2.0619503190494443e-05, "loss": 0.49344615936279296, "step": 487720 }, { "epoch": 2.8991684053474094, "grad_norm": 1.6875556707382202, "learning_rate": 2.061877429917823e-05, "loss": 0.45957536697387696, "step": 487730 }, { "epoch": 2.8992278474240774, "grad_norm": 1.4110438823699951, "learning_rate": 2.0618045835432592e-05, "loss": 0.49825682640075686, "step": 487740 }, { "epoch": 2.899287289500746, "grad_norm": 1.1145412921905518, "learning_rate": 2.0617317799261004e-05, "loss": 0.47608175277709963, "step": 487750 }, { "epoch": 2.899346731577414, "grad_norm": 1.330162525177002, "learning_rate": 2.0616590190666958e-05, "loss": 0.46030941009521487, "step": 487760 }, { "epoch": 2.899406173654083, "grad_norm": 1.313955307006836, "learning_rate": 2.0615863009653935e-05, "loss": 0.47437162399291993, "step": 487770 }, { "epoch": 2.899465615730751, "grad_norm": 1.1814106702804565, "learning_rate": 2.0615136256225407e-05, "loss": 0.4215374946594238, "step": 487780 }, { "epoch": 2.8995250578074194, "grad_norm": 1.3202834129333496, "learning_rate": 2.0614409930384864e-05, "loss": 0.4668626308441162, "step": 487790 }, { "epoch": 2.899584499884088, "grad_norm": 1.1001094579696655, "learning_rate": 2.0613684032135774e-05, "loss": 0.5168567180633545, "step": 487800 }, { "epoch": 2.8996439419607563, "grad_norm": 1.5587592124938965, "learning_rate": 2.0612958561481606e-05, "loss": 0.4477664947509766, "step": 487810 }, { "epoch": 2.8997033840374247, "grad_norm": 1.1498916149139404, "learning_rate": 2.0612233518425823e-05, "loss": 0.4837596893310547, "step": 487820 }, { "epoch": 2.899762826114093, "grad_norm": 1.414872169494629, "learning_rate": 2.061150890297191e-05, "loss": 0.4502157211303711, "step": 487830 }, { "epoch": 2.8998222681907615, "grad_norm": 1.615896224975586, "learning_rate": 2.0610784715123323e-05, "loss": 0.47125587463378904, "step": 487840 }, { "epoch": 2.89988171026743, "grad_norm": 1.277485966682434, "learning_rate": 2.061006095488353e-05, "loss": 0.46957950592041015, "step": 487850 }, { "epoch": 2.8999411523440983, "grad_norm": 1.6830101013183594, "learning_rate": 2.0609337622255998e-05, "loss": 0.4338953971862793, "step": 487860 }, { "epoch": 2.9000005944207667, "grad_norm": 1.0915437936782837, "learning_rate": 2.0608614717244175e-05, "loss": 0.4707427978515625, "step": 487870 }, { "epoch": 2.900060036497435, "grad_norm": 1.1274735927581787, "learning_rate": 2.0607892239851522e-05, "loss": 0.445432710647583, "step": 487880 }, { "epoch": 2.9001194785741036, "grad_norm": 1.0894347429275513, "learning_rate": 2.060717019008151e-05, "loss": 0.41038899421691893, "step": 487890 }, { "epoch": 2.900178920650772, "grad_norm": 1.0039101839065552, "learning_rate": 2.060644856793758e-05, "loss": 0.4956353187561035, "step": 487900 }, { "epoch": 2.9002383627274404, "grad_norm": 1.2597768306732178, "learning_rate": 2.0605727373423174e-05, "loss": 0.4611365795135498, "step": 487910 }, { "epoch": 2.900297804804109, "grad_norm": 1.2400566339492798, "learning_rate": 2.060500660654177e-05, "loss": 0.4600813865661621, "step": 487920 }, { "epoch": 2.900357246880777, "grad_norm": 1.3327873945236206, "learning_rate": 2.060428626729679e-05, "loss": 0.4283896446228027, "step": 487930 }, { "epoch": 2.9004166889574456, "grad_norm": 1.3112012147903442, "learning_rate": 2.060356635569169e-05, "loss": 0.48740034103393554, "step": 487940 }, { "epoch": 2.9004761310341136, "grad_norm": 1.1967594623565674, "learning_rate": 2.0602846871729912e-05, "loss": 0.4622349739074707, "step": 487950 }, { "epoch": 2.9005355731107825, "grad_norm": 1.3747925758361816, "learning_rate": 2.0602127815414913e-05, "loss": 0.49921588897705077, "step": 487960 }, { "epoch": 2.9005950151874504, "grad_norm": 1.1865910291671753, "learning_rate": 2.0601409186750108e-05, "loss": 0.4399977684020996, "step": 487970 }, { "epoch": 2.900654457264119, "grad_norm": 1.6778029203414917, "learning_rate": 2.0600690985738943e-05, "loss": 0.4751926898956299, "step": 487980 }, { "epoch": 2.9007138993407873, "grad_norm": 1.5372562408447266, "learning_rate": 2.059997321238486e-05, "loss": 0.4723937511444092, "step": 487990 }, { "epoch": 2.9007733414174557, "grad_norm": 1.2918040752410889, "learning_rate": 2.0599255866691282e-05, "loss": 0.473509693145752, "step": 488000 }, { "epoch": 2.900832783494124, "grad_norm": 1.2650601863861084, "learning_rate": 2.059853894866165e-05, "loss": 0.4227287769317627, "step": 488010 }, { "epoch": 2.9008922255707925, "grad_norm": 1.4708093404769897, "learning_rate": 2.0597822458299402e-05, "loss": 0.4597932815551758, "step": 488020 }, { "epoch": 2.900951667647461, "grad_norm": 1.1673498153686523, "learning_rate": 2.059710639560795e-05, "loss": 0.48377437591552735, "step": 488030 }, { "epoch": 2.9010111097241293, "grad_norm": 0.8968254923820496, "learning_rate": 2.0596390760590725e-05, "loss": 0.4859751224517822, "step": 488040 }, { "epoch": 2.9010705518007978, "grad_norm": 1.6897855997085571, "learning_rate": 2.059567555325114e-05, "loss": 0.46764564514160156, "step": 488050 }, { "epoch": 2.901129993877466, "grad_norm": 1.5168405771255493, "learning_rate": 2.0594960773592632e-05, "loss": 0.467741584777832, "step": 488060 }, { "epoch": 2.9011894359541346, "grad_norm": 1.2957637310028076, "learning_rate": 2.0594246421618618e-05, "loss": 0.47136220932006834, "step": 488070 }, { "epoch": 2.901248878030803, "grad_norm": 1.0146647691726685, "learning_rate": 2.0593532497332498e-05, "loss": 0.43776907920837405, "step": 488080 }, { "epoch": 2.9013083201074714, "grad_norm": 1.675868034362793, "learning_rate": 2.059281900073771e-05, "loss": 0.5014419555664062, "step": 488090 }, { "epoch": 2.90136776218414, "grad_norm": 1.9797145128250122, "learning_rate": 2.0592105931837655e-05, "loss": 0.509764575958252, "step": 488100 }, { "epoch": 2.9014272042608082, "grad_norm": 1.8868261575698853, "learning_rate": 2.0591393290635746e-05, "loss": 0.48507843017578123, "step": 488110 }, { "epoch": 2.901486646337476, "grad_norm": 1.1865686178207397, "learning_rate": 2.059068107713539e-05, "loss": 0.4516456604003906, "step": 488120 }, { "epoch": 2.901546088414145, "grad_norm": 1.353772759437561, "learning_rate": 2.0589969291340004e-05, "loss": 0.4354654312133789, "step": 488130 }, { "epoch": 2.901605530490813, "grad_norm": 1.5807973146438599, "learning_rate": 2.0589257933252982e-05, "loss": 0.4430813789367676, "step": 488140 }, { "epoch": 2.9016649725674815, "grad_norm": 1.4620248079299927, "learning_rate": 2.058854700287772e-05, "loss": 0.48230934143066406, "step": 488150 }, { "epoch": 2.90172441464415, "grad_norm": 1.3793752193450928, "learning_rate": 2.0587836500217643e-05, "loss": 0.4769547462463379, "step": 488160 }, { "epoch": 2.9017838567208183, "grad_norm": 1.3838649988174438, "learning_rate": 2.058712642527613e-05, "loss": 0.5101293087005615, "step": 488170 }, { "epoch": 2.9018432987974867, "grad_norm": 1.474845051765442, "learning_rate": 2.058641677805659e-05, "loss": 0.4679116725921631, "step": 488180 }, { "epoch": 2.901902740874155, "grad_norm": 1.5471328496932983, "learning_rate": 2.058570755856241e-05, "loss": 0.5018115043640137, "step": 488190 }, { "epoch": 2.9019621829508235, "grad_norm": 1.0352764129638672, "learning_rate": 2.0584998766796977e-05, "loss": 0.43837499618530273, "step": 488200 }, { "epoch": 2.902021625027492, "grad_norm": 1.4235179424285889, "learning_rate": 2.0584290402763687e-05, "loss": 0.4689463138580322, "step": 488210 }, { "epoch": 2.9020810671041604, "grad_norm": 1.1554019451141357, "learning_rate": 2.0583582466465934e-05, "loss": 0.4336398601531982, "step": 488220 }, { "epoch": 2.9021405091808288, "grad_norm": 1.2789733409881592, "learning_rate": 2.0582874957907105e-05, "loss": 0.42045025825500487, "step": 488230 }, { "epoch": 2.902199951257497, "grad_norm": 1.139088749885559, "learning_rate": 2.0582167877090576e-05, "loss": 0.46985516548156736, "step": 488240 }, { "epoch": 2.9022593933341656, "grad_norm": 1.3510873317718506, "learning_rate": 2.058146122401974e-05, "loss": 0.4427676200866699, "step": 488250 }, { "epoch": 2.902318835410834, "grad_norm": 1.5117448568344116, "learning_rate": 2.0580754998697966e-05, "loss": 0.4596225738525391, "step": 488260 }, { "epoch": 2.9023782774875024, "grad_norm": 0.9840713143348694, "learning_rate": 2.0580049201128638e-05, "loss": 0.43330860137939453, "step": 488270 }, { "epoch": 2.902437719564171, "grad_norm": 1.2462409734725952, "learning_rate": 2.057934383131513e-05, "loss": 0.42051239013671876, "step": 488280 }, { "epoch": 2.902497161640839, "grad_norm": 1.4242216348648071, "learning_rate": 2.0578638889260827e-05, "loss": 0.4632760524749756, "step": 488290 }, { "epoch": 2.9025566037175077, "grad_norm": 1.5161888599395752, "learning_rate": 2.0577934374969083e-05, "loss": 0.44357619285583494, "step": 488300 }, { "epoch": 2.9026160457941756, "grad_norm": 1.2368030548095703, "learning_rate": 2.057723028844328e-05, "loss": 0.4512141227722168, "step": 488310 }, { "epoch": 2.9026754878708445, "grad_norm": 1.3364109992980957, "learning_rate": 2.0576526629686776e-05, "loss": 0.4415395736694336, "step": 488320 }, { "epoch": 2.9027349299475125, "grad_norm": 1.5475683212280273, "learning_rate": 2.0575823398702962e-05, "loss": 0.47680320739746096, "step": 488330 }, { "epoch": 2.902794372024181, "grad_norm": 1.5452873706817627, "learning_rate": 2.0575120595495174e-05, "loss": 0.4914248466491699, "step": 488340 }, { "epoch": 2.9028538141008493, "grad_norm": 1.4333884716033936, "learning_rate": 2.0574418220066783e-05, "loss": 0.47065420150756837, "step": 488350 }, { "epoch": 2.9029132561775177, "grad_norm": 1.1095471382141113, "learning_rate": 2.0573716272421154e-05, "loss": 0.4560441017150879, "step": 488360 }, { "epoch": 2.902972698254186, "grad_norm": 1.034883737564087, "learning_rate": 2.057301475256164e-05, "loss": 0.416916561126709, "step": 488370 }, { "epoch": 2.9030321403308545, "grad_norm": 1.6813583374023438, "learning_rate": 2.05723136604916e-05, "loss": 0.4536764144897461, "step": 488380 }, { "epoch": 2.903091582407523, "grad_norm": 1.2748020887374878, "learning_rate": 2.0571612996214383e-05, "loss": 0.4858137607574463, "step": 488390 }, { "epoch": 2.9031510244841914, "grad_norm": 1.8116068840026855, "learning_rate": 2.0570912759733347e-05, "loss": 0.46540184020996095, "step": 488400 }, { "epoch": 2.90321046656086, "grad_norm": 1.3662021160125732, "learning_rate": 2.0570212951051844e-05, "loss": 0.4319246768951416, "step": 488410 }, { "epoch": 2.903269908637528, "grad_norm": 1.48636794090271, "learning_rate": 2.056951357017321e-05, "loss": 0.42236948013305664, "step": 488420 }, { "epoch": 2.9033293507141966, "grad_norm": 1.2736375331878662, "learning_rate": 2.056881461710079e-05, "loss": 0.43726773262023927, "step": 488430 }, { "epoch": 2.903388792790865, "grad_norm": 1.4796429872512817, "learning_rate": 2.056811609183794e-05, "loss": 0.46000032424926757, "step": 488440 }, { "epoch": 2.9034482348675335, "grad_norm": 1.5807867050170898, "learning_rate": 2.0567417994388002e-05, "loss": 0.464778470993042, "step": 488450 }, { "epoch": 2.903507676944202, "grad_norm": 1.3563737869262695, "learning_rate": 2.0566720324754308e-05, "loss": 0.45026235580444335, "step": 488460 }, { "epoch": 2.9035671190208703, "grad_norm": 1.5294538736343384, "learning_rate": 2.056602308294019e-05, "loss": 0.4096848964691162, "step": 488470 }, { "epoch": 2.9036265610975383, "grad_norm": 1.1703031063079834, "learning_rate": 2.0565326268948996e-05, "loss": 0.4092280864715576, "step": 488480 }, { "epoch": 2.903686003174207, "grad_norm": 1.5097557306289673, "learning_rate": 2.0564629882784052e-05, "loss": 0.4619462013244629, "step": 488490 }, { "epoch": 2.903745445250875, "grad_norm": 1.2505182027816772, "learning_rate": 2.0563933924448687e-05, "loss": 0.42043318748474123, "step": 488500 }, { "epoch": 2.903804887327544, "grad_norm": 1.1073527336120605, "learning_rate": 2.056323839394624e-05, "loss": 0.4408393859863281, "step": 488510 }, { "epoch": 2.903864329404212, "grad_norm": 1.1759189367294312, "learning_rate": 2.056254329128003e-05, "loss": 0.5005061149597168, "step": 488520 }, { "epoch": 2.9039237714808803, "grad_norm": 1.5267714262008667, "learning_rate": 2.056184861645339e-05, "loss": 0.452623176574707, "step": 488530 }, { "epoch": 2.9039832135575487, "grad_norm": 1.4987431764602661, "learning_rate": 2.0561154369469625e-05, "loss": 0.44574618339538574, "step": 488540 }, { "epoch": 2.904042655634217, "grad_norm": 1.527148723602295, "learning_rate": 2.0560460550332076e-05, "loss": 0.4766660690307617, "step": 488550 }, { "epoch": 2.9041020977108856, "grad_norm": 1.550220251083374, "learning_rate": 2.055976715904406e-05, "loss": 0.47292208671569824, "step": 488560 }, { "epoch": 2.904161539787554, "grad_norm": 1.2281060218811035, "learning_rate": 2.0559074195608873e-05, "loss": 0.4513257026672363, "step": 488570 }, { "epoch": 2.9042209818642224, "grad_norm": 1.1403679847717285, "learning_rate": 2.055838166002986e-05, "loss": 0.444028377532959, "step": 488580 }, { "epoch": 2.904280423940891, "grad_norm": 1.4182451963424683, "learning_rate": 2.0557689552310315e-05, "loss": 0.4434232711791992, "step": 488590 }, { "epoch": 2.9043398660175592, "grad_norm": 1.2649561166763306, "learning_rate": 2.0556997872453546e-05, "loss": 0.4259203910827637, "step": 488600 }, { "epoch": 2.9043993080942276, "grad_norm": 1.48015296459198, "learning_rate": 2.0556306620462877e-05, "loss": 0.47092633247375487, "step": 488610 }, { "epoch": 2.904458750170896, "grad_norm": 1.2500617504119873, "learning_rate": 2.055561579634161e-05, "loss": 0.4497506141662598, "step": 488620 }, { "epoch": 2.9045181922475645, "grad_norm": 1.3310861587524414, "learning_rate": 2.0554925400093038e-05, "loss": 0.4680182456970215, "step": 488630 }, { "epoch": 2.904577634324233, "grad_norm": 1.1991022825241089, "learning_rate": 2.0554235431720472e-05, "loss": 0.44289588928222656, "step": 488640 }, { "epoch": 2.9046370764009013, "grad_norm": 1.2919518947601318, "learning_rate": 2.055354589122722e-05, "loss": 0.4403702259063721, "step": 488650 }, { "epoch": 2.9046965184775697, "grad_norm": 1.248673915863037, "learning_rate": 2.0552856778616565e-05, "loss": 0.41291656494140627, "step": 488660 }, { "epoch": 2.9047559605542377, "grad_norm": 1.0286333560943604, "learning_rate": 2.0552168093891815e-05, "loss": 0.44093799591064453, "step": 488670 }, { "epoch": 2.9048154026309065, "grad_norm": 1.2968626022338867, "learning_rate": 2.0551479837056265e-05, "loss": 0.43894028663635254, "step": 488680 }, { "epoch": 2.9048748447075745, "grad_norm": 1.2925822734832764, "learning_rate": 2.05507920081132e-05, "loss": 0.47289581298828126, "step": 488690 }, { "epoch": 2.9049342867842434, "grad_norm": 1.4634840488433838, "learning_rate": 2.0550104607065907e-05, "loss": 0.43976497650146484, "step": 488700 }, { "epoch": 2.9049937288609113, "grad_norm": 1.235166311264038, "learning_rate": 2.054941763391769e-05, "loss": 0.488860559463501, "step": 488710 }, { "epoch": 2.9050531709375798, "grad_norm": 1.2155965566635132, "learning_rate": 2.0548731088671827e-05, "loss": 0.4571228981018066, "step": 488720 }, { "epoch": 2.905112613014248, "grad_norm": 1.525211215019226, "learning_rate": 2.0548044971331594e-05, "loss": 0.4501655578613281, "step": 488730 }, { "epoch": 2.9051720550909166, "grad_norm": 1.1443992853164673, "learning_rate": 2.054735928190028e-05, "loss": 0.4277339458465576, "step": 488740 }, { "epoch": 2.905231497167585, "grad_norm": 1.6694042682647705, "learning_rate": 2.054667402038117e-05, "loss": 0.49842610359191897, "step": 488750 }, { "epoch": 2.9052909392442534, "grad_norm": 1.342381477355957, "learning_rate": 2.0545989186777534e-05, "loss": 0.47191486358642576, "step": 488760 }, { "epoch": 2.905350381320922, "grad_norm": 0.9302663803100586, "learning_rate": 2.0545304781092658e-05, "loss": 0.44401350021362307, "step": 488770 }, { "epoch": 2.9054098233975902, "grad_norm": 1.4270286560058594, "learning_rate": 2.0544620803329813e-05, "loss": 0.48143630027770995, "step": 488780 }, { "epoch": 2.9054692654742587, "grad_norm": 1.3993395566940308, "learning_rate": 2.0543937253492268e-05, "loss": 0.4396510124206543, "step": 488790 }, { "epoch": 2.905528707550927, "grad_norm": 1.4941041469573975, "learning_rate": 2.054325413158328e-05, "loss": 0.48234167098999026, "step": 488800 }, { "epoch": 2.9055881496275955, "grad_norm": 1.2629646062850952, "learning_rate": 2.054257143760614e-05, "loss": 0.45830135345458983, "step": 488810 }, { "epoch": 2.905647591704264, "grad_norm": 1.224774718284607, "learning_rate": 2.0541889171564098e-05, "loss": 0.43619575500488283, "step": 488820 }, { "epoch": 2.9057070337809323, "grad_norm": 1.3621273040771484, "learning_rate": 2.054120733346042e-05, "loss": 0.40134763717651367, "step": 488830 }, { "epoch": 2.9057664758576003, "grad_norm": 1.4118382930755615, "learning_rate": 2.0540525923298384e-05, "loss": 0.43099145889282225, "step": 488840 }, { "epoch": 2.905825917934269, "grad_norm": 1.290145754814148, "learning_rate": 2.0539844941081228e-05, "loss": 0.4761674880981445, "step": 488850 }, { "epoch": 2.905885360010937, "grad_norm": 1.0979899168014526, "learning_rate": 2.0539164386812208e-05, "loss": 0.46404037475585935, "step": 488860 }, { "epoch": 2.905944802087606, "grad_norm": 1.0726138353347778, "learning_rate": 2.0538484260494605e-05, "loss": 0.44273786544799804, "step": 488870 }, { "epoch": 2.906004244164274, "grad_norm": 1.2417386770248413, "learning_rate": 2.0537804562131653e-05, "loss": 0.43816680908203126, "step": 488880 }, { "epoch": 2.9060636862409424, "grad_norm": 1.4640076160430908, "learning_rate": 2.0537125291726596e-05, "loss": 0.4559546947479248, "step": 488890 }, { "epoch": 2.9061231283176108, "grad_norm": 0.9711586833000183, "learning_rate": 2.053644644928271e-05, "loss": 0.4476437568664551, "step": 488900 }, { "epoch": 2.906182570394279, "grad_norm": 1.251113772392273, "learning_rate": 2.0535768034803215e-05, "loss": 0.4776106357574463, "step": 488910 }, { "epoch": 2.9062420124709476, "grad_norm": 1.2840220928192139, "learning_rate": 2.0535090048291383e-05, "loss": 0.4690413951873779, "step": 488920 }, { "epoch": 2.906301454547616, "grad_norm": 1.1504818201065063, "learning_rate": 2.053441248975043e-05, "loss": 0.4250269889831543, "step": 488930 }, { "epoch": 2.9063608966242844, "grad_norm": 1.3725779056549072, "learning_rate": 2.0533735359183612e-05, "loss": 0.43550834655761717, "step": 488940 }, { "epoch": 2.906420338700953, "grad_norm": 1.4780056476593018, "learning_rate": 2.0533058656594167e-05, "loss": 0.5207610130310059, "step": 488950 }, { "epoch": 2.9064797807776213, "grad_norm": 1.4178080558776855, "learning_rate": 2.0532382381985334e-05, "loss": 0.4997416496276855, "step": 488960 }, { "epoch": 2.9065392228542897, "grad_norm": 1.4830211400985718, "learning_rate": 2.0531706535360352e-05, "loss": 0.5063159942626954, "step": 488970 }, { "epoch": 2.906598664930958, "grad_norm": 1.3474795818328857, "learning_rate": 2.0531031116722433e-05, "loss": 0.49225425720214844, "step": 488980 }, { "epoch": 2.9066581070076265, "grad_norm": 1.321589469909668, "learning_rate": 2.0530356126074825e-05, "loss": 0.45787882804870605, "step": 488990 }, { "epoch": 2.906717549084295, "grad_norm": 1.191270351409912, "learning_rate": 2.0529681563420762e-05, "loss": 0.4950376510620117, "step": 489000 }, { "epoch": 2.9067769911609633, "grad_norm": 1.2431018352508545, "learning_rate": 2.0529007428763455e-05, "loss": 0.438466215133667, "step": 489010 }, { "epoch": 2.9068364332376317, "grad_norm": 1.3702242374420166, "learning_rate": 2.0528333722106143e-05, "loss": 0.460219669342041, "step": 489020 }, { "epoch": 2.9068958753142997, "grad_norm": 1.49833083152771, "learning_rate": 2.0527660443452045e-05, "loss": 0.4669219970703125, "step": 489030 }, { "epoch": 2.9069553173909686, "grad_norm": 1.4054137468338013, "learning_rate": 2.0526987592804376e-05, "loss": 0.4797757625579834, "step": 489040 }, { "epoch": 2.9070147594676365, "grad_norm": 1.1960619688034058, "learning_rate": 2.0526315170166356e-05, "loss": 0.4404598712921143, "step": 489050 }, { "epoch": 2.9070742015443054, "grad_norm": 0.9493871927261353, "learning_rate": 2.05256431755412e-05, "loss": 0.4456817626953125, "step": 489060 }, { "epoch": 2.9071336436209734, "grad_norm": 1.0987929105758667, "learning_rate": 2.0524971608932136e-05, "loss": 0.46956462860107423, "step": 489070 }, { "epoch": 2.907193085697642, "grad_norm": 1.1688976287841797, "learning_rate": 2.0524300470342365e-05, "loss": 0.49423832893371583, "step": 489080 }, { "epoch": 2.90725252777431, "grad_norm": 1.0764083862304688, "learning_rate": 2.0523629759775097e-05, "loss": 0.4234021186828613, "step": 489090 }, { "epoch": 2.9073119698509786, "grad_norm": 1.2731764316558838, "learning_rate": 2.052295947723355e-05, "loss": 0.47287492752075194, "step": 489100 }, { "epoch": 2.907371411927647, "grad_norm": 1.3747453689575195, "learning_rate": 2.0522289622720918e-05, "loss": 0.46296377182006837, "step": 489110 }, { "epoch": 2.9074308540043154, "grad_norm": 1.3030208349227905, "learning_rate": 2.05216201962404e-05, "loss": 0.4240715026855469, "step": 489120 }, { "epoch": 2.907490296080984, "grad_norm": 1.2639806270599365, "learning_rate": 2.0520951197795222e-05, "loss": 0.4126278400421143, "step": 489130 }, { "epoch": 2.9075497381576523, "grad_norm": 1.3266642093658447, "learning_rate": 2.0520282627388574e-05, "loss": 0.38028864860534667, "step": 489140 }, { "epoch": 2.9076091802343207, "grad_norm": 1.0659583806991577, "learning_rate": 2.051961448502365e-05, "loss": 0.4819830894470215, "step": 489150 }, { "epoch": 2.907668622310989, "grad_norm": 1.2688450813293457, "learning_rate": 2.0518946770703644e-05, "loss": 0.49720163345336915, "step": 489160 }, { "epoch": 2.9077280643876575, "grad_norm": 1.2538057565689087, "learning_rate": 2.0518279484431745e-05, "loss": 0.45131306648254393, "step": 489170 }, { "epoch": 2.907787506464326, "grad_norm": 1.26517915725708, "learning_rate": 2.051761262621117e-05, "loss": 0.48898963928222655, "step": 489180 }, { "epoch": 2.9078469485409943, "grad_norm": 1.6216202974319458, "learning_rate": 2.051694619604508e-05, "loss": 0.5156021118164062, "step": 489190 }, { "epoch": 2.9079063906176628, "grad_norm": 1.4069355726242065, "learning_rate": 2.0516280193936688e-05, "loss": 0.46663331985473633, "step": 489200 }, { "epoch": 2.907965832694331, "grad_norm": 1.3396496772766113, "learning_rate": 2.0515614619889162e-05, "loss": 0.4895742416381836, "step": 489210 }, { "epoch": 2.908025274770999, "grad_norm": 0.993915319442749, "learning_rate": 2.051494947390569e-05, "loss": 0.4675943374633789, "step": 489220 }, { "epoch": 2.908084716847668, "grad_norm": 1.299239158630371, "learning_rate": 2.051428475598946e-05, "loss": 0.4311948776245117, "step": 489230 }, { "epoch": 2.908144158924336, "grad_norm": 1.133689045906067, "learning_rate": 2.051362046614364e-05, "loss": 0.5019729614257813, "step": 489240 }, { "epoch": 2.908203601001005, "grad_norm": 1.3131359815597534, "learning_rate": 2.0512956604371413e-05, "loss": 0.43950419425964354, "step": 489250 }, { "epoch": 2.908263043077673, "grad_norm": 1.2585667371749878, "learning_rate": 2.0512293170675974e-05, "loss": 0.47246403694152833, "step": 489260 }, { "epoch": 2.908322485154341, "grad_norm": 1.6049851179122925, "learning_rate": 2.0511630165060467e-05, "loss": 0.4864204883575439, "step": 489270 }, { "epoch": 2.9083819272310096, "grad_norm": 1.1802486181259155, "learning_rate": 2.0510967587528084e-05, "loss": 0.44289569854736327, "step": 489280 }, { "epoch": 2.908441369307678, "grad_norm": 1.3208483457565308, "learning_rate": 2.0510305438081984e-05, "loss": 0.4804126739501953, "step": 489290 }, { "epoch": 2.9085008113843465, "grad_norm": 0.8586606383323669, "learning_rate": 2.0509643716725333e-05, "loss": 0.40723533630371095, "step": 489300 }, { "epoch": 2.908560253461015, "grad_norm": 1.1496214866638184, "learning_rate": 2.0508982423461305e-05, "loss": 0.4525304317474365, "step": 489310 }, { "epoch": 2.9086196955376833, "grad_norm": 1.0759252309799194, "learning_rate": 2.0508321558293045e-05, "loss": 0.41897430419921877, "step": 489320 }, { "epoch": 2.9086791376143517, "grad_norm": 1.8115582466125488, "learning_rate": 2.0507661121223744e-05, "loss": 0.4959084987640381, "step": 489330 }, { "epoch": 2.90873857969102, "grad_norm": 1.3635808229446411, "learning_rate": 2.0507001112256543e-05, "loss": 0.4966322898864746, "step": 489340 }, { "epoch": 2.9087980217676885, "grad_norm": 1.1803886890411377, "learning_rate": 2.0506341531394606e-05, "loss": 0.497760009765625, "step": 489350 }, { "epoch": 2.908857463844357, "grad_norm": 1.544288992881775, "learning_rate": 2.0505682378641075e-05, "loss": 0.482253360748291, "step": 489360 }, { "epoch": 2.9089169059210254, "grad_norm": 1.552781105041504, "learning_rate": 2.0505023653999113e-05, "loss": 0.46143207550048826, "step": 489370 }, { "epoch": 2.908976347997694, "grad_norm": 1.3476516008377075, "learning_rate": 2.0504365357471872e-05, "loss": 0.4379246711730957, "step": 489380 }, { "epoch": 2.909035790074362, "grad_norm": 1.5097466707229614, "learning_rate": 2.0503707489062503e-05, "loss": 0.45929555892944335, "step": 489390 }, { "epoch": 2.9090952321510306, "grad_norm": 1.3522975444793701, "learning_rate": 2.0503050048774156e-05, "loss": 0.46190996170043946, "step": 489400 }, { "epoch": 2.9091546742276986, "grad_norm": 1.5539790391921997, "learning_rate": 2.0502393036609963e-05, "loss": 0.4841917037963867, "step": 489410 }, { "epoch": 2.9092141163043674, "grad_norm": 1.1467193365097046, "learning_rate": 2.0501736452573074e-05, "loss": 0.49666900634765626, "step": 489420 }, { "epoch": 2.9092735583810354, "grad_norm": 1.2461223602294922, "learning_rate": 2.0501080296666623e-05, "loss": 0.5263925552368164, "step": 489430 }, { "epoch": 2.9093330004577043, "grad_norm": 1.5203794240951538, "learning_rate": 2.050042456889376e-05, "loss": 0.45817270278930666, "step": 489440 }, { "epoch": 2.9093924425343722, "grad_norm": 1.0992263555526733, "learning_rate": 2.0499769269257617e-05, "loss": 0.4643683433532715, "step": 489450 }, { "epoch": 2.9094518846110407, "grad_norm": 1.515763759613037, "learning_rate": 2.0499114397761325e-05, "loss": 0.47542705535888674, "step": 489460 }, { "epoch": 2.909511326687709, "grad_norm": 1.1979069709777832, "learning_rate": 2.049845995440803e-05, "loss": 0.48995418548583985, "step": 489470 }, { "epoch": 2.9095707687643775, "grad_norm": 1.0373395681381226, "learning_rate": 2.0497805939200848e-05, "loss": 0.4351823329925537, "step": 489480 }, { "epoch": 2.909630210841046, "grad_norm": 1.183355450630188, "learning_rate": 2.0497152352142912e-05, "loss": 0.48608856201171874, "step": 489490 }, { "epoch": 2.9096896529177143, "grad_norm": 1.1298366785049438, "learning_rate": 2.049649919323735e-05, "loss": 0.464373779296875, "step": 489500 }, { "epoch": 2.9097490949943827, "grad_norm": 1.1623280048370361, "learning_rate": 2.0495846462487288e-05, "loss": 0.4854111671447754, "step": 489510 }, { "epoch": 2.909808537071051, "grad_norm": 1.367982268333435, "learning_rate": 2.0495194159895846e-05, "loss": 0.45122556686401366, "step": 489520 }, { "epoch": 2.9098679791477196, "grad_norm": 0.8089070916175842, "learning_rate": 2.0494542285466143e-05, "loss": 0.4104194641113281, "step": 489530 }, { "epoch": 2.909927421224388, "grad_norm": 1.2896829843521118, "learning_rate": 2.04938908392013e-05, "loss": 0.44433889389038084, "step": 489540 }, { "epoch": 2.9099868633010564, "grad_norm": 1.5840388536453247, "learning_rate": 2.049323982110443e-05, "loss": 0.528929328918457, "step": 489550 }, { "epoch": 2.910046305377725, "grad_norm": 1.188389539718628, "learning_rate": 2.0492589231178647e-05, "loss": 0.4119504451751709, "step": 489560 }, { "epoch": 2.910105747454393, "grad_norm": 1.2723761796951294, "learning_rate": 2.0491939069427072e-05, "loss": 0.46827259063720705, "step": 489570 }, { "epoch": 2.910165189531061, "grad_norm": 1.6123968362808228, "learning_rate": 2.049128933585281e-05, "loss": 0.48163952827453616, "step": 489580 }, { "epoch": 2.91022463160773, "grad_norm": 1.4587624073028564, "learning_rate": 2.049064003045896e-05, "loss": 0.479203987121582, "step": 489590 }, { "epoch": 2.910284073684398, "grad_norm": 1.8194266557693481, "learning_rate": 2.0489991153248644e-05, "loss": 0.47085747718811033, "step": 489600 }, { "epoch": 2.910343515761067, "grad_norm": 1.8861130475997925, "learning_rate": 2.0489342704224946e-05, "loss": 0.4693428993225098, "step": 489610 }, { "epoch": 2.910402957837735, "grad_norm": 1.7445389032363892, "learning_rate": 2.0488694683390992e-05, "loss": 0.4945816993713379, "step": 489620 }, { "epoch": 2.9104623999144033, "grad_norm": 1.1559031009674072, "learning_rate": 2.0488047090749863e-05, "loss": 0.40796937942504885, "step": 489630 }, { "epoch": 2.9105218419910717, "grad_norm": 1.121306300163269, "learning_rate": 2.0487399926304667e-05, "loss": 0.46050519943237306, "step": 489640 }, { "epoch": 2.91058128406774, "grad_norm": 1.230371117591858, "learning_rate": 2.04867531900585e-05, "loss": 0.4405625820159912, "step": 489650 }, { "epoch": 2.9106407261444085, "grad_norm": 0.8854296803474426, "learning_rate": 2.0486106882014446e-05, "loss": 0.4287257194519043, "step": 489660 }, { "epoch": 2.910700168221077, "grad_norm": 1.6101868152618408, "learning_rate": 2.0485461002175617e-05, "loss": 0.43476047515869143, "step": 489670 }, { "epoch": 2.9107596102977453, "grad_norm": 1.1567306518554688, "learning_rate": 2.048481555054507e-05, "loss": 0.5107803821563721, "step": 489680 }, { "epoch": 2.9108190523744137, "grad_norm": 1.1770023107528687, "learning_rate": 2.0484170527125927e-05, "loss": 0.4507575035095215, "step": 489690 }, { "epoch": 2.910878494451082, "grad_norm": 2.0565972328186035, "learning_rate": 2.048352593192125e-05, "loss": 0.48212709426879885, "step": 489700 }, { "epoch": 2.9109379365277506, "grad_norm": 1.1707861423492432, "learning_rate": 2.048288176493413e-05, "loss": 0.5032203674316407, "step": 489710 }, { "epoch": 2.910997378604419, "grad_norm": 0.9576488733291626, "learning_rate": 2.048223802616765e-05, "loss": 0.44917755126953124, "step": 489720 }, { "epoch": 2.9110568206810874, "grad_norm": 1.1540967226028442, "learning_rate": 2.048159471562489e-05, "loss": 0.49649982452392577, "step": 489730 }, { "epoch": 2.911116262757756, "grad_norm": 1.655563473701477, "learning_rate": 2.0480951833308932e-05, "loss": 0.5021257400512695, "step": 489740 }, { "epoch": 2.9111757048344242, "grad_norm": 1.155940294265747, "learning_rate": 2.048030937922283e-05, "loss": 0.4341947078704834, "step": 489750 }, { "epoch": 2.9112351469110926, "grad_norm": 1.5629289150238037, "learning_rate": 2.047966735336969e-05, "loss": 0.46018333435058595, "step": 489760 }, { "epoch": 2.9112945889877606, "grad_norm": 1.3586440086364746, "learning_rate": 2.0479025755752553e-05, "loss": 0.45984630584716796, "step": 489770 }, { "epoch": 2.9113540310644295, "grad_norm": 1.052395224571228, "learning_rate": 2.0478384586374502e-05, "loss": 0.4703989028930664, "step": 489780 }, { "epoch": 2.9114134731410974, "grad_norm": 1.3672280311584473, "learning_rate": 2.0477743845238616e-05, "loss": 0.48282670974731445, "step": 489790 }, { "epoch": 2.9114729152177663, "grad_norm": 1.521505355834961, "learning_rate": 2.0477103532347935e-05, "loss": 0.45592308044433594, "step": 489800 }, { "epoch": 2.9115323572944343, "grad_norm": 1.5504634380340576, "learning_rate": 2.047646364770553e-05, "loss": 0.4372661590576172, "step": 489810 }, { "epoch": 2.9115917993711027, "grad_norm": 1.7808094024658203, "learning_rate": 2.0475824191314474e-05, "loss": 0.4937014579772949, "step": 489820 }, { "epoch": 2.911651241447771, "grad_norm": 1.36212956905365, "learning_rate": 2.0475185163177827e-05, "loss": 0.4373303413391113, "step": 489830 }, { "epoch": 2.9117106835244395, "grad_norm": 1.289202332496643, "learning_rate": 2.047454656329862e-05, "loss": 0.4466557025909424, "step": 489840 }, { "epoch": 2.911770125601108, "grad_norm": 1.0351520776748657, "learning_rate": 2.047390839167994e-05, "loss": 0.4316659450531006, "step": 489850 }, { "epoch": 2.9118295676777763, "grad_norm": 1.5208368301391602, "learning_rate": 2.0473270648324816e-05, "loss": 0.46734156608581545, "step": 489860 }, { "epoch": 2.9118890097544448, "grad_norm": 1.327276587486267, "learning_rate": 2.0472633333236302e-05, "loss": 0.5065608024597168, "step": 489870 }, { "epoch": 2.911948451831113, "grad_norm": 1.1333889961242676, "learning_rate": 2.047199644641746e-05, "loss": 0.4268013000488281, "step": 489880 }, { "epoch": 2.9120078939077816, "grad_norm": 0.9821795225143433, "learning_rate": 2.0471359987871334e-05, "loss": 0.45508460998535155, "step": 489890 }, { "epoch": 2.91206733598445, "grad_norm": 1.2697004079818726, "learning_rate": 2.0470723957600962e-05, "loss": 0.4640628814697266, "step": 489900 }, { "epoch": 2.9121267780611184, "grad_norm": 1.5711497068405151, "learning_rate": 2.0470088355609374e-05, "loss": 0.46133623123168943, "step": 489910 }, { "epoch": 2.912186220137787, "grad_norm": 1.8557407855987549, "learning_rate": 2.0469453181899633e-05, "loss": 0.49679880142211913, "step": 489920 }, { "epoch": 2.9122456622144552, "grad_norm": 1.3920687437057495, "learning_rate": 2.0468818436474772e-05, "loss": 0.4856518268585205, "step": 489930 }, { "epoch": 2.9123051042911237, "grad_norm": 1.231740951538086, "learning_rate": 2.0468184119337826e-05, "loss": 0.44298372268676756, "step": 489940 }, { "epoch": 2.912364546367792, "grad_norm": 1.3256018161773682, "learning_rate": 2.046755023049182e-05, "loss": 0.44672374725341796, "step": 489950 }, { "epoch": 2.91242398844446, "grad_norm": 1.2216957807540894, "learning_rate": 2.046691676993981e-05, "loss": 0.4835533618927002, "step": 489960 }, { "epoch": 2.912483430521129, "grad_norm": 1.3811843395233154, "learning_rate": 2.0466283737684793e-05, "loss": 0.4550673007965088, "step": 489970 }, { "epoch": 2.912542872597797, "grad_norm": 1.2906343936920166, "learning_rate": 2.0465651133729825e-05, "loss": 0.45376110076904297, "step": 489980 }, { "epoch": 2.9126023146744657, "grad_norm": 1.208052635192871, "learning_rate": 2.046501895807792e-05, "loss": 0.43253259658813475, "step": 489990 }, { "epoch": 2.9126617567511337, "grad_norm": 1.3494434356689453, "learning_rate": 2.04643872107321e-05, "loss": 0.4537287712097168, "step": 490000 }, { "epoch": 2.912721198827802, "grad_norm": 1.2578833103179932, "learning_rate": 2.0463755891695394e-05, "loss": 0.4790816307067871, "step": 490010 }, { "epoch": 2.9127806409044705, "grad_norm": 1.7662118673324585, "learning_rate": 2.046312500097081e-05, "loss": 0.4433741092681885, "step": 490020 }, { "epoch": 2.912840082981139, "grad_norm": 1.689496636390686, "learning_rate": 2.0462494538561393e-05, "loss": 0.5365796089172363, "step": 490030 }, { "epoch": 2.9128995250578074, "grad_norm": 1.8765662908554077, "learning_rate": 2.0461864504470122e-05, "loss": 0.4571223258972168, "step": 490040 }, { "epoch": 2.9129589671344758, "grad_norm": 1.188698172569275, "learning_rate": 2.0461234898700046e-05, "loss": 0.4305391788482666, "step": 490050 }, { "epoch": 2.913018409211144, "grad_norm": 1.492384433746338, "learning_rate": 2.0460605721254154e-05, "loss": 0.4797203540802002, "step": 490060 }, { "epoch": 2.9130778512878126, "grad_norm": 1.246043086051941, "learning_rate": 2.0459976972135463e-05, "loss": 0.445847749710083, "step": 490070 }, { "epoch": 2.913137293364481, "grad_norm": 1.700812578201294, "learning_rate": 2.0459348651346975e-05, "loss": 0.46385440826416013, "step": 490080 }, { "epoch": 2.9131967354411494, "grad_norm": 1.1608103513717651, "learning_rate": 2.0458720758891704e-05, "loss": 0.45688776969909667, "step": 490090 }, { "epoch": 2.913256177517818, "grad_norm": 1.0579848289489746, "learning_rate": 2.045809329477265e-05, "loss": 0.45060977935791013, "step": 490100 }, { "epoch": 2.9133156195944863, "grad_norm": 1.4730722904205322, "learning_rate": 2.0457466258992815e-05, "loss": 0.4495041847229004, "step": 490110 }, { "epoch": 2.9133750616711547, "grad_norm": 1.4968862533569336, "learning_rate": 2.0456839651555206e-05, "loss": 0.4788225173950195, "step": 490120 }, { "epoch": 2.913434503747823, "grad_norm": 1.1194368600845337, "learning_rate": 2.045621347246281e-05, "loss": 0.43875598907470703, "step": 490130 }, { "epoch": 2.9134939458244915, "grad_norm": 1.6344071626663208, "learning_rate": 2.0455587721718616e-05, "loss": 0.44101800918579104, "step": 490140 }, { "epoch": 2.9135533879011595, "grad_norm": 1.1338839530944824, "learning_rate": 2.0454962399325642e-05, "loss": 0.47427568435668943, "step": 490150 }, { "epoch": 2.9136128299778283, "grad_norm": 1.7503867149353027, "learning_rate": 2.045433750528685e-05, "loss": 0.42041430473327634, "step": 490160 }, { "epoch": 2.9136722720544963, "grad_norm": 1.3233745098114014, "learning_rate": 2.0453713039605244e-05, "loss": 0.4412407875061035, "step": 490170 }, { "epoch": 2.913731714131165, "grad_norm": 1.3393492698669434, "learning_rate": 2.0453089002283817e-05, "loss": 0.4080845832824707, "step": 490180 }, { "epoch": 2.913791156207833, "grad_norm": 1.1314746141433716, "learning_rate": 2.0452465393325555e-05, "loss": 0.4527899742126465, "step": 490190 }, { "epoch": 2.9138505982845015, "grad_norm": 1.658079981803894, "learning_rate": 2.0451842212733424e-05, "loss": 0.4642143249511719, "step": 490200 }, { "epoch": 2.91391004036117, "grad_norm": 0.9239795804023743, "learning_rate": 2.045121946051041e-05, "loss": 0.4424879550933838, "step": 490210 }, { "epoch": 2.9139694824378384, "grad_norm": 1.1098982095718384, "learning_rate": 2.0450597136659512e-05, "loss": 0.4359405517578125, "step": 490220 }, { "epoch": 2.914028924514507, "grad_norm": 1.3768013715744019, "learning_rate": 2.0449975241183674e-05, "loss": 0.4632126808166504, "step": 490230 }, { "epoch": 2.914088366591175, "grad_norm": 2.0089035034179688, "learning_rate": 2.0449353774085903e-05, "loss": 0.47616424560546877, "step": 490240 }, { "epoch": 2.9141478086678436, "grad_norm": 1.2874776124954224, "learning_rate": 2.0448732735369157e-05, "loss": 0.4853494167327881, "step": 490250 }, { "epoch": 2.914207250744512, "grad_norm": 1.373818278312683, "learning_rate": 2.0448112125036413e-05, "loss": 0.4603711128234863, "step": 490260 }, { "epoch": 2.9142666928211804, "grad_norm": 1.509315013885498, "learning_rate": 2.0447491943090626e-05, "loss": 0.49043979644775393, "step": 490270 }, { "epoch": 2.914326134897849, "grad_norm": 1.1663670539855957, "learning_rate": 2.044687218953477e-05, "loss": 0.4581474304199219, "step": 490280 }, { "epoch": 2.9143855769745173, "grad_norm": 1.7104346752166748, "learning_rate": 2.0446252864371816e-05, "loss": 0.4615306377410889, "step": 490290 }, { "epoch": 2.9144450190511857, "grad_norm": 1.2480255365371704, "learning_rate": 2.0445633967604713e-05, "loss": 0.4670598030090332, "step": 490300 }, { "epoch": 2.914504461127854, "grad_norm": 1.2461405992507935, "learning_rate": 2.0445015499236445e-05, "loss": 0.5073997497558593, "step": 490310 }, { "epoch": 2.914563903204522, "grad_norm": 1.258926510810852, "learning_rate": 2.044439745926995e-05, "loss": 0.449137544631958, "step": 490320 }, { "epoch": 2.914623345281191, "grad_norm": 1.485946774482727, "learning_rate": 2.0443779847708187e-05, "loss": 0.47728309631347654, "step": 490330 }, { "epoch": 2.914682787357859, "grad_norm": 1.0326054096221924, "learning_rate": 2.0443162664554112e-05, "loss": 0.46691198348999025, "step": 490340 }, { "epoch": 2.9147422294345278, "grad_norm": 1.544507384300232, "learning_rate": 2.044254590981069e-05, "loss": 0.45571365356445315, "step": 490350 }, { "epoch": 2.9148016715111957, "grad_norm": 1.153172254562378, "learning_rate": 2.0441929583480852e-05, "loss": 0.44647669792175293, "step": 490360 }, { "epoch": 2.914861113587864, "grad_norm": 1.5737308263778687, "learning_rate": 2.0441313685567555e-05, "loss": 0.42971124649047854, "step": 490370 }, { "epoch": 2.9149205556645326, "grad_norm": 1.4373787641525269, "learning_rate": 2.0440698216073744e-05, "loss": 0.47605457305908205, "step": 490380 }, { "epoch": 2.914979997741201, "grad_norm": 1.550374984741211, "learning_rate": 2.044008317500237e-05, "loss": 0.45371227264404296, "step": 490390 }, { "epoch": 2.9150394398178694, "grad_norm": 1.0694385766983032, "learning_rate": 2.0439468562356364e-05, "loss": 0.55477876663208, "step": 490400 }, { "epoch": 2.915098881894538, "grad_norm": 1.2256865501403809, "learning_rate": 2.0438854378138682e-05, "loss": 0.48955812454223635, "step": 490410 }, { "epoch": 2.9151583239712062, "grad_norm": 1.0316424369812012, "learning_rate": 2.0438240622352237e-05, "loss": 0.41864190101623533, "step": 490420 }, { "epoch": 2.9152177660478746, "grad_norm": 1.469123363494873, "learning_rate": 2.0437627294999993e-05, "loss": 0.46345996856689453, "step": 490430 }, { "epoch": 2.915277208124543, "grad_norm": 1.3738794326782227, "learning_rate": 2.043701439608486e-05, "loss": 0.48532328605651853, "step": 490440 }, { "epoch": 2.9153366502012115, "grad_norm": 1.4940133094787598, "learning_rate": 2.0436401925609794e-05, "loss": 0.4376777172088623, "step": 490450 }, { "epoch": 2.91539609227788, "grad_norm": 1.134670615196228, "learning_rate": 2.04357898835777e-05, "loss": 0.45591392517089846, "step": 490460 }, { "epoch": 2.9154555343545483, "grad_norm": 1.386799931526184, "learning_rate": 2.0435178269991522e-05, "loss": 0.4473999500274658, "step": 490470 }, { "epoch": 2.9155149764312167, "grad_norm": 1.378017544746399, "learning_rate": 2.0434567084854174e-05, "loss": 0.45813546180725095, "step": 490480 }, { "epoch": 2.915574418507885, "grad_norm": 1.295233130455017, "learning_rate": 2.0433956328168598e-05, "loss": 0.3817532300949097, "step": 490490 }, { "epoch": 2.9156338605845535, "grad_norm": 1.2817426919937134, "learning_rate": 2.043334599993769e-05, "loss": 0.44387617111206057, "step": 490500 }, { "epoch": 2.9156933026612215, "grad_norm": 1.5463968515396118, "learning_rate": 2.0432736100164397e-05, "loss": 0.44188632965087893, "step": 490510 }, { "epoch": 2.9157527447378904, "grad_norm": 1.0353789329528809, "learning_rate": 2.043212662885162e-05, "loss": 0.4997719764709473, "step": 490520 }, { "epoch": 2.9158121868145583, "grad_norm": 1.7259403467178345, "learning_rate": 2.0431517586002274e-05, "loss": 0.5102256298065185, "step": 490530 }, { "epoch": 2.915871628891227, "grad_norm": 1.2752258777618408, "learning_rate": 2.0430908971619283e-05, "loss": 0.4731456756591797, "step": 490540 }, { "epoch": 2.915931070967895, "grad_norm": 1.6207599639892578, "learning_rate": 2.0430300785705546e-05, "loss": 0.44667534828186034, "step": 490550 }, { "epoch": 2.9159905130445636, "grad_norm": 1.1496531963348389, "learning_rate": 2.042969302826398e-05, "loss": 0.4680930137634277, "step": 490560 }, { "epoch": 2.916049955121232, "grad_norm": 1.4344955682754517, "learning_rate": 2.0429085699297492e-05, "loss": 0.426665210723877, "step": 490570 }, { "epoch": 2.9161093971979004, "grad_norm": 1.2530183792114258, "learning_rate": 2.042847879880899e-05, "loss": 0.4335193157196045, "step": 490580 }, { "epoch": 2.916168839274569, "grad_norm": 1.0685627460479736, "learning_rate": 2.0427872326801365e-05, "loss": 0.49095873832702636, "step": 490590 }, { "epoch": 2.9162282813512372, "grad_norm": 1.3576217889785767, "learning_rate": 2.042726628327753e-05, "loss": 0.43991336822509763, "step": 490600 }, { "epoch": 2.9162877234279057, "grad_norm": 1.328049659729004, "learning_rate": 2.0426660668240378e-05, "loss": 0.43372130393981934, "step": 490610 }, { "epoch": 2.916347165504574, "grad_norm": 1.3290460109710693, "learning_rate": 2.0426055481692815e-05, "loss": 0.4921107292175293, "step": 490620 }, { "epoch": 2.9164066075812425, "grad_norm": 1.5376394987106323, "learning_rate": 2.0425450723637732e-05, "loss": 0.5056281089782715, "step": 490630 }, { "epoch": 2.916466049657911, "grad_norm": 1.2484796047210693, "learning_rate": 2.0424846394078007e-05, "loss": 0.4637942314147949, "step": 490640 }, { "epoch": 2.9165254917345793, "grad_norm": 1.674588918685913, "learning_rate": 2.042424249301655e-05, "loss": 0.508273696899414, "step": 490650 }, { "epoch": 2.9165849338112477, "grad_norm": 1.2759171724319458, "learning_rate": 2.0423639020456244e-05, "loss": 0.44624905586242675, "step": 490660 }, { "epoch": 2.916644375887916, "grad_norm": 1.649175763130188, "learning_rate": 2.0423035976399974e-05, "loss": 0.4744138240814209, "step": 490670 }, { "epoch": 2.9167038179645846, "grad_norm": 1.4059560298919678, "learning_rate": 2.0422433360850625e-05, "loss": 0.42636284828186033, "step": 490680 }, { "epoch": 2.916763260041253, "grad_norm": 1.7793939113616943, "learning_rate": 2.042183117381108e-05, "loss": 0.4782121658325195, "step": 490690 }, { "epoch": 2.916822702117921, "grad_norm": 1.4501557350158691, "learning_rate": 2.042122941528422e-05, "loss": 0.4800724506378174, "step": 490700 }, { "epoch": 2.91688214419459, "grad_norm": 1.0671908855438232, "learning_rate": 2.0420628085272927e-05, "loss": 0.45100693702697753, "step": 490710 }, { "epoch": 2.9169415862712578, "grad_norm": 1.3309141397476196, "learning_rate": 2.0420027183780073e-05, "loss": 0.42829318046569825, "step": 490720 }, { "epoch": 2.9170010283479266, "grad_norm": 1.458967924118042, "learning_rate": 2.0419426710808525e-05, "loss": 0.5114228248596191, "step": 490730 }, { "epoch": 2.9170604704245946, "grad_norm": 1.301716923713684, "learning_rate": 2.0418826666361178e-05, "loss": 0.501588249206543, "step": 490740 }, { "epoch": 2.917119912501263, "grad_norm": 1.4771528244018555, "learning_rate": 2.041822705044088e-05, "loss": 0.4845707893371582, "step": 490750 }, { "epoch": 2.9171793545779314, "grad_norm": 1.2969310283660889, "learning_rate": 2.0417627863050516e-05, "loss": 0.45129880905151365, "step": 490760 }, { "epoch": 2.9172387966546, "grad_norm": 1.379279613494873, "learning_rate": 2.041702910419294e-05, "loss": 0.46974806785583495, "step": 490770 }, { "epoch": 2.9172982387312683, "grad_norm": 1.434080958366394, "learning_rate": 2.0416430773871024e-05, "loss": 0.42457923889160154, "step": 490780 }, { "epoch": 2.9173576808079367, "grad_norm": 1.216068148612976, "learning_rate": 2.041583287208762e-05, "loss": 0.46063847541809083, "step": 490790 }, { "epoch": 2.917417122884605, "grad_norm": 1.6892131567001343, "learning_rate": 2.04152353988456e-05, "loss": 0.4600236892700195, "step": 490800 }, { "epoch": 2.9174765649612735, "grad_norm": 0.9592395424842834, "learning_rate": 2.041463835414782e-05, "loss": 0.4334709167480469, "step": 490810 }, { "epoch": 2.917536007037942, "grad_norm": 0.9505826830863953, "learning_rate": 2.0414041737997124e-05, "loss": 0.4292039394378662, "step": 490820 }, { "epoch": 2.9175954491146103, "grad_norm": 1.4454084634780884, "learning_rate": 2.0413445550396375e-05, "loss": 0.4923506736755371, "step": 490830 }, { "epoch": 2.9176548911912787, "grad_norm": 1.4786293506622314, "learning_rate": 2.0412849791348442e-05, "loss": 0.47910871505737307, "step": 490840 }, { "epoch": 2.917714333267947, "grad_norm": 1.2569068670272827, "learning_rate": 2.041225446085614e-05, "loss": 0.47046756744384766, "step": 490850 }, { "epoch": 2.9177737753446156, "grad_norm": 1.1093553304672241, "learning_rate": 2.0411659558922345e-05, "loss": 0.4563741683959961, "step": 490860 }, { "epoch": 2.917833217421284, "grad_norm": 1.2959043979644775, "learning_rate": 2.0411065085549897e-05, "loss": 0.46586856842041013, "step": 490870 }, { "epoch": 2.9178926594979524, "grad_norm": 1.7014578580856323, "learning_rate": 2.0410471040741622e-05, "loss": 0.40334205627441405, "step": 490880 }, { "epoch": 2.9179521015746204, "grad_norm": 1.4969199895858765, "learning_rate": 2.040987742450038e-05, "loss": 0.4397785186767578, "step": 490890 }, { "epoch": 2.9180115436512892, "grad_norm": 1.1944940090179443, "learning_rate": 2.0409284236829007e-05, "loss": 0.4758718490600586, "step": 490900 }, { "epoch": 2.918070985727957, "grad_norm": 0.962394118309021, "learning_rate": 2.0408691477730342e-05, "loss": 0.43361916542053225, "step": 490910 }, { "epoch": 2.918130427804626, "grad_norm": 1.4034411907196045, "learning_rate": 2.040809914720721e-05, "loss": 0.4736448287963867, "step": 490920 }, { "epoch": 2.918189869881294, "grad_norm": 1.3440560102462769, "learning_rate": 2.0407507245262476e-05, "loss": 0.4760921001434326, "step": 490930 }, { "epoch": 2.9182493119579624, "grad_norm": 1.1788806915283203, "learning_rate": 2.0406915771898926e-05, "loss": 0.5353315830230713, "step": 490940 }, { "epoch": 2.918308754034631, "grad_norm": 1.6699533462524414, "learning_rate": 2.0406324727119418e-05, "loss": 0.4164768695831299, "step": 490950 }, { "epoch": 2.9183681961112993, "grad_norm": 1.4179867506027222, "learning_rate": 2.0405734110926767e-05, "loss": 0.45021533966064453, "step": 490960 }, { "epoch": 2.9184276381879677, "grad_norm": 1.2354352474212646, "learning_rate": 2.0405143923323815e-05, "loss": 0.5098729133605957, "step": 490970 }, { "epoch": 2.918487080264636, "grad_norm": 1.314965844154358, "learning_rate": 2.040455416431337e-05, "loss": 0.42207860946655273, "step": 490980 }, { "epoch": 2.9185465223413045, "grad_norm": 1.3733018636703491, "learning_rate": 2.040396483389825e-05, "loss": 0.4449418067932129, "step": 490990 }, { "epoch": 2.918605964417973, "grad_norm": 1.477523922920227, "learning_rate": 2.040337593208129e-05, "loss": 0.43306694030761717, "step": 491000 }, { "epoch": 2.9186654064946413, "grad_norm": 1.1565711498260498, "learning_rate": 2.04027874588653e-05, "loss": 0.44429898262023926, "step": 491010 }, { "epoch": 2.9187248485713098, "grad_norm": 1.1113390922546387, "learning_rate": 2.0402199414253087e-05, "loss": 0.4827709674835205, "step": 491020 }, { "epoch": 2.918784290647978, "grad_norm": 0.9854902029037476, "learning_rate": 2.0401611798247483e-05, "loss": 0.47197914123535156, "step": 491030 }, { "epoch": 2.9188437327246466, "grad_norm": 1.187351107597351, "learning_rate": 2.0401024610851277e-05, "loss": 0.45134854316711426, "step": 491040 }, { "epoch": 2.918903174801315, "grad_norm": 1.245996356010437, "learning_rate": 2.0400437852067287e-05, "loss": 0.4423075675964355, "step": 491050 }, { "epoch": 2.918962616877983, "grad_norm": 1.3812841176986694, "learning_rate": 2.039985152189833e-05, "loss": 0.48130002021789553, "step": 491060 }, { "epoch": 2.919022058954652, "grad_norm": 1.5840232372283936, "learning_rate": 2.0399265620347195e-05, "loss": 0.47761688232421873, "step": 491070 }, { "epoch": 2.91908150103132, "grad_norm": 1.0094496011734009, "learning_rate": 2.0398680147416686e-05, "loss": 0.4402805805206299, "step": 491080 }, { "epoch": 2.9191409431079887, "grad_norm": 1.5497039556503296, "learning_rate": 2.039809510310963e-05, "loss": 0.45351428985595704, "step": 491090 }, { "epoch": 2.9192003851846566, "grad_norm": 1.369716763496399, "learning_rate": 2.0397510487428782e-05, "loss": 0.4315922260284424, "step": 491100 }, { "epoch": 2.919259827261325, "grad_norm": 1.1159722805023193, "learning_rate": 2.039692630037697e-05, "loss": 0.48387846946716306, "step": 491110 }, { "epoch": 2.9193192693379935, "grad_norm": 1.0052701234817505, "learning_rate": 2.0396342541956987e-05, "loss": 0.4524271011352539, "step": 491120 }, { "epoch": 2.919378711414662, "grad_norm": 1.241196870803833, "learning_rate": 2.0395759212171613e-05, "loss": 0.443544864654541, "step": 491130 }, { "epoch": 2.9194381534913303, "grad_norm": 1.2938274145126343, "learning_rate": 2.0395176311023643e-05, "loss": 0.4345715522766113, "step": 491140 }, { "epoch": 2.9194975955679987, "grad_norm": 1.6232478618621826, "learning_rate": 2.0394593838515865e-05, "loss": 0.49681801795959474, "step": 491150 }, { "epoch": 2.919557037644667, "grad_norm": 1.348454236984253, "learning_rate": 2.039401179465106e-05, "loss": 0.4348898887634277, "step": 491160 }, { "epoch": 2.9196164797213355, "grad_norm": 1.488693118095398, "learning_rate": 2.0393430179432037e-05, "loss": 0.4735809326171875, "step": 491170 }, { "epoch": 2.919675921798004, "grad_norm": 1.0437976121902466, "learning_rate": 2.0392848992861545e-05, "loss": 0.468396520614624, "step": 491180 }, { "epoch": 2.9197353638746724, "grad_norm": 1.5172853469848633, "learning_rate": 2.039226823494239e-05, "loss": 0.4945050239562988, "step": 491190 }, { "epoch": 2.9197948059513408, "grad_norm": 1.192525863647461, "learning_rate": 2.0391687905677325e-05, "loss": 0.46910624504089354, "step": 491200 }, { "epoch": 2.919854248028009, "grad_norm": 1.2648361921310425, "learning_rate": 2.0391108005069154e-05, "loss": 0.4402941703796387, "step": 491210 }, { "epoch": 2.9199136901046776, "grad_norm": 1.4782485961914062, "learning_rate": 2.039052853312064e-05, "loss": 0.44561014175415037, "step": 491220 }, { "epoch": 2.919973132181346, "grad_norm": 1.2524620294570923, "learning_rate": 2.038994948983454e-05, "loss": 0.4486401557922363, "step": 491230 }, { "epoch": 2.9200325742580144, "grad_norm": 1.5315120220184326, "learning_rate": 2.038937087521364e-05, "loss": 0.49453043937683105, "step": 491240 }, { "epoch": 2.9200920163346824, "grad_norm": 1.4797452688217163, "learning_rate": 2.0388792689260716e-05, "loss": 0.4659564018249512, "step": 491250 }, { "epoch": 2.9201514584113513, "grad_norm": 1.2043734788894653, "learning_rate": 2.038821493197851e-05, "loss": 0.4513543128967285, "step": 491260 }, { "epoch": 2.9202109004880192, "grad_norm": 0.9536694884300232, "learning_rate": 2.0387637603369804e-05, "loss": 0.46106853485107424, "step": 491270 }, { "epoch": 2.920270342564688, "grad_norm": 1.405523657798767, "learning_rate": 2.0387060703437356e-05, "loss": 0.45610995292663575, "step": 491280 }, { "epoch": 2.920329784641356, "grad_norm": 1.2649898529052734, "learning_rate": 2.0386484232183913e-05, "loss": 0.4360644817352295, "step": 491290 }, { "epoch": 2.9203892267180245, "grad_norm": 1.4144455194473267, "learning_rate": 2.038590818961226e-05, "loss": 0.47260313034057616, "step": 491300 }, { "epoch": 2.920448668794693, "grad_norm": 1.6959861516952515, "learning_rate": 2.0385332575725123e-05, "loss": 0.44179573059082033, "step": 491310 }, { "epoch": 2.9205081108713613, "grad_norm": 1.2934073209762573, "learning_rate": 2.0384757390525276e-05, "loss": 0.5146916389465332, "step": 491320 }, { "epoch": 2.9205675529480297, "grad_norm": 1.205008864402771, "learning_rate": 2.038418263401546e-05, "loss": 0.4396191120147705, "step": 491330 }, { "epoch": 2.920626995024698, "grad_norm": 1.6568334102630615, "learning_rate": 2.0383608306198427e-05, "loss": 0.526912784576416, "step": 491340 }, { "epoch": 2.9206864371013666, "grad_norm": 1.024053692817688, "learning_rate": 2.038303440707692e-05, "loss": 0.4599268913269043, "step": 491350 }, { "epoch": 2.920745879178035, "grad_norm": 1.214267611503601, "learning_rate": 2.0382460936653692e-05, "loss": 0.42224550247192383, "step": 491360 }, { "epoch": 2.9208053212547034, "grad_norm": 1.1262798309326172, "learning_rate": 2.0381887894931498e-05, "loss": 0.4290276527404785, "step": 491370 }, { "epoch": 2.920864763331372, "grad_norm": 1.450446367263794, "learning_rate": 2.0381315281913048e-05, "loss": 0.49317946434021, "step": 491380 }, { "epoch": 2.92092420540804, "grad_norm": 1.292650580406189, "learning_rate": 2.0380743097601096e-05, "loss": 0.42769393920898435, "step": 491390 }, { "epoch": 2.9209836474847086, "grad_norm": 1.2672042846679688, "learning_rate": 2.0380171341998395e-05, "loss": 0.4706812858581543, "step": 491400 }, { "epoch": 2.921043089561377, "grad_norm": 1.2700814008712769, "learning_rate": 2.0379600015107656e-05, "loss": 0.43394808769226073, "step": 491410 }, { "epoch": 2.9211025316380455, "grad_norm": 1.3091328144073486, "learning_rate": 2.0379029116931623e-05, "loss": 0.4823614120483398, "step": 491420 }, { "epoch": 2.921161973714714, "grad_norm": 1.124046802520752, "learning_rate": 2.0378458647473032e-05, "loss": 0.44676909446716306, "step": 491430 }, { "epoch": 2.921221415791382, "grad_norm": 1.2708691358566284, "learning_rate": 2.03778886067346e-05, "loss": 0.45510058403015136, "step": 491440 }, { "epoch": 2.9212808578680507, "grad_norm": 1.179891586303711, "learning_rate": 2.0377318994719062e-05, "loss": 0.46745977401733396, "step": 491450 }, { "epoch": 2.9213402999447187, "grad_norm": 1.5110468864440918, "learning_rate": 2.0376749811429145e-05, "loss": 0.4418825149536133, "step": 491460 }, { "epoch": 2.9213997420213875, "grad_norm": 1.4082856178283691, "learning_rate": 2.0376181056867567e-05, "loss": 0.45968427658081057, "step": 491470 }, { "epoch": 2.9214591840980555, "grad_norm": 1.4224692583084106, "learning_rate": 2.0375612731037048e-05, "loss": 0.4765993595123291, "step": 491480 }, { "epoch": 2.921518626174724, "grad_norm": 1.4442013502120972, "learning_rate": 2.0375044833940302e-05, "loss": 0.46375303268432616, "step": 491490 }, { "epoch": 2.9215780682513923, "grad_norm": 1.2667150497436523, "learning_rate": 2.0374477365580057e-05, "loss": 0.47596378326416017, "step": 491500 }, { "epoch": 2.9216375103280607, "grad_norm": 1.0722754001617432, "learning_rate": 2.0373910325959023e-05, "loss": 0.4399301052093506, "step": 491510 }, { "epoch": 2.921696952404729, "grad_norm": 1.2253899574279785, "learning_rate": 2.0373343715079906e-05, "loss": 0.4554760456085205, "step": 491520 }, { "epoch": 2.9217563944813976, "grad_norm": 1.3256316184997559, "learning_rate": 2.0372777532945432e-05, "loss": 0.44574289321899413, "step": 491530 }, { "epoch": 2.921815836558066, "grad_norm": 1.2730870246887207, "learning_rate": 2.0372211779558294e-05, "loss": 0.4635785102844238, "step": 491540 }, { "epoch": 2.9218752786347344, "grad_norm": 1.3268458843231201, "learning_rate": 2.037164645492121e-05, "loss": 0.4483620643615723, "step": 491550 }, { "epoch": 2.921934720711403, "grad_norm": 1.3581640720367432, "learning_rate": 2.037108155903687e-05, "loss": 0.49536991119384766, "step": 491560 }, { "epoch": 2.9219941627880712, "grad_norm": 1.033271074295044, "learning_rate": 2.0370517091907988e-05, "loss": 0.48363428115844725, "step": 491570 }, { "epoch": 2.9220536048647396, "grad_norm": 1.627808690071106, "learning_rate": 2.036995305353726e-05, "loss": 0.5018362998962402, "step": 491580 }, { "epoch": 2.922113046941408, "grad_norm": 1.3748666048049927, "learning_rate": 2.0369389443927388e-05, "loss": 0.4950603485107422, "step": 491590 }, { "epoch": 2.9221724890180765, "grad_norm": 1.3258579969406128, "learning_rate": 2.036882626308106e-05, "loss": 0.4442112922668457, "step": 491600 }, { "epoch": 2.922231931094745, "grad_norm": 1.3379285335540771, "learning_rate": 2.0368263511000986e-05, "loss": 0.4846828460693359, "step": 491610 }, { "epoch": 2.9222913731714133, "grad_norm": 1.332942247390747, "learning_rate": 2.0367701187689837e-05, "loss": 0.41672601699829104, "step": 491620 }, { "epoch": 2.9223508152480813, "grad_norm": 1.3530021905899048, "learning_rate": 2.0367139293150324e-05, "loss": 0.44328889846801756, "step": 491630 }, { "epoch": 2.92241025732475, "grad_norm": 1.184626817703247, "learning_rate": 2.036657782738511e-05, "loss": 0.45893087387084963, "step": 491640 }, { "epoch": 2.922469699401418, "grad_norm": 1.3695276975631714, "learning_rate": 2.0366016790396904e-05, "loss": 0.44777865409851075, "step": 491650 }, { "epoch": 2.922529141478087, "grad_norm": 1.2852541208267212, "learning_rate": 2.036545618218838e-05, "loss": 0.41152215003967285, "step": 491660 }, { "epoch": 2.922588583554755, "grad_norm": 0.9534182548522949, "learning_rate": 2.0364896002762223e-05, "loss": 0.46872496604919434, "step": 491670 }, { "epoch": 2.9226480256314233, "grad_norm": 1.4177110195159912, "learning_rate": 2.0364336252121104e-05, "loss": 0.42555952072143555, "step": 491680 }, { "epoch": 2.9227074677080918, "grad_norm": 1.2952468395233154, "learning_rate": 2.0363776930267715e-05, "loss": 0.4403423309326172, "step": 491690 }, { "epoch": 2.92276690978476, "grad_norm": 1.5691183805465698, "learning_rate": 2.0363218037204714e-05, "loss": 0.46283769607543945, "step": 491700 }, { "epoch": 2.9228263518614286, "grad_norm": 0.9818185567855835, "learning_rate": 2.0362659572934795e-05, "loss": 0.4778864860534668, "step": 491710 }, { "epoch": 2.922885793938097, "grad_norm": 0.9987988471984863, "learning_rate": 2.0362101537460605e-05, "loss": 0.4428256988525391, "step": 491720 }, { "epoch": 2.9229452360147654, "grad_norm": 1.672451376914978, "learning_rate": 2.0361543930784843e-05, "loss": 0.46036081314086913, "step": 491730 }, { "epoch": 2.923004678091434, "grad_norm": 1.608537197113037, "learning_rate": 2.0360986752910154e-05, "loss": 0.48641366958618165, "step": 491740 }, { "epoch": 2.9230641201681022, "grad_norm": 1.5039594173431396, "learning_rate": 2.036043000383921e-05, "loss": 0.5114906787872314, "step": 491750 }, { "epoch": 2.9231235622447707, "grad_norm": 1.3802541494369507, "learning_rate": 2.0359873683574675e-05, "loss": 0.4671813488006592, "step": 491760 }, { "epoch": 2.923183004321439, "grad_norm": 1.4067612886428833, "learning_rate": 2.0359317792119205e-05, "loss": 0.41936211585998534, "step": 491770 }, { "epoch": 2.9232424463981075, "grad_norm": 1.3358036279678345, "learning_rate": 2.0358762329475466e-05, "loss": 0.44452104568481443, "step": 491780 }, { "epoch": 2.923301888474776, "grad_norm": 1.2436089515686035, "learning_rate": 2.0358207295646117e-05, "loss": 0.4521660327911377, "step": 491790 }, { "epoch": 2.923361330551444, "grad_norm": 1.16422700881958, "learning_rate": 2.03576526906338e-05, "loss": 0.4633808135986328, "step": 491800 }, { "epoch": 2.9234207726281127, "grad_norm": 1.253339409828186, "learning_rate": 2.0357098514441188e-05, "loss": 0.5224802494049072, "step": 491810 }, { "epoch": 2.9234802147047807, "grad_norm": 1.4229387044906616, "learning_rate": 2.035654476707092e-05, "loss": 0.4726749897003174, "step": 491820 }, { "epoch": 2.9235396567814496, "grad_norm": 1.2441240549087524, "learning_rate": 2.0355991448525638e-05, "loss": 0.4422718048095703, "step": 491830 }, { "epoch": 2.9235990988581175, "grad_norm": 1.2804862260818481, "learning_rate": 2.0355438558808e-05, "loss": 0.4725028991699219, "step": 491840 }, { "epoch": 2.923658540934786, "grad_norm": 1.307446002960205, "learning_rate": 2.035488609792065e-05, "loss": 0.4319918632507324, "step": 491850 }, { "epoch": 2.9237179830114544, "grad_norm": 1.263992190361023, "learning_rate": 2.0354334065866233e-05, "loss": 0.4758795738220215, "step": 491860 }, { "epoch": 2.9237774250881228, "grad_norm": 1.7381738424301147, "learning_rate": 2.0353782462647372e-05, "loss": 0.47510466575622556, "step": 491870 }, { "epoch": 2.923836867164791, "grad_norm": 1.297004222869873, "learning_rate": 2.0353231288266723e-05, "loss": 0.44352054595947266, "step": 491880 }, { "epoch": 2.9238963092414596, "grad_norm": 1.2204352617263794, "learning_rate": 2.0352680542726933e-05, "loss": 0.4924469470977783, "step": 491890 }, { "epoch": 2.923955751318128, "grad_norm": 1.4096438884735107, "learning_rate": 2.0352130226030606e-05, "loss": 0.49374985694885254, "step": 491900 }, { "epoch": 2.9240151933947964, "grad_norm": 1.4981569051742554, "learning_rate": 2.0351580338180397e-05, "loss": 0.477370023727417, "step": 491910 }, { "epoch": 2.924074635471465, "grad_norm": 1.3778403997421265, "learning_rate": 2.035103087917893e-05, "loss": 0.4589062690734863, "step": 491920 }, { "epoch": 2.9241340775481333, "grad_norm": 1.2183105945587158, "learning_rate": 2.0350481849028834e-05, "loss": 0.4688395023345947, "step": 491930 }, { "epoch": 2.9241935196248017, "grad_norm": 1.365032434463501, "learning_rate": 2.0349933247732732e-05, "loss": 0.5131890296936035, "step": 491940 }, { "epoch": 2.92425296170147, "grad_norm": 1.4204728603363037, "learning_rate": 2.0349385075293254e-05, "loss": 0.49140229225158694, "step": 491950 }, { "epoch": 2.9243124037781385, "grad_norm": 1.50112783908844, "learning_rate": 2.034883733171302e-05, "loss": 0.5340929985046386, "step": 491960 }, { "epoch": 2.924371845854807, "grad_norm": 1.300869107246399, "learning_rate": 2.034829001699464e-05, "loss": 0.496885871887207, "step": 491970 }, { "epoch": 2.9244312879314753, "grad_norm": 1.3632736206054688, "learning_rate": 2.034774313114076e-05, "loss": 0.45343379974365233, "step": 491980 }, { "epoch": 2.9244907300081433, "grad_norm": 1.2633568048477173, "learning_rate": 2.034719667415397e-05, "loss": 0.42635011672973633, "step": 491990 }, { "epoch": 2.924550172084812, "grad_norm": 1.1772171258926392, "learning_rate": 2.0346650646036887e-05, "loss": 0.4653043746948242, "step": 492000 }, { "epoch": 2.92460961416148, "grad_norm": 1.4730312824249268, "learning_rate": 2.0346105046792135e-05, "loss": 0.45493159294128416, "step": 492010 }, { "epoch": 2.924669056238149, "grad_norm": 1.4755324125289917, "learning_rate": 2.034555987642232e-05, "loss": 0.505116081237793, "step": 492020 }, { "epoch": 2.924728498314817, "grad_norm": 1.4817441701889038, "learning_rate": 2.034501513493004e-05, "loss": 0.5044369697570801, "step": 492030 }, { "epoch": 2.9247879403914854, "grad_norm": 1.1273024082183838, "learning_rate": 2.034447082231791e-05, "loss": 0.46782984733581545, "step": 492040 }, { "epoch": 2.924847382468154, "grad_norm": 1.6916788816452026, "learning_rate": 2.0343926938588537e-05, "loss": 0.4391488552093506, "step": 492050 }, { "epoch": 2.924906824544822, "grad_norm": 1.1559147834777832, "learning_rate": 2.034338348374451e-05, "loss": 0.4699379920959473, "step": 492060 }, { "epoch": 2.9249662666214906, "grad_norm": 1.6149725914001465, "learning_rate": 2.034284045778844e-05, "loss": 0.4717113494873047, "step": 492070 }, { "epoch": 2.925025708698159, "grad_norm": 1.1572763919830322, "learning_rate": 2.034229786072292e-05, "loss": 0.42676963806152346, "step": 492080 }, { "epoch": 2.9250851507748274, "grad_norm": 1.587060570716858, "learning_rate": 2.0341755692550542e-05, "loss": 0.4688570976257324, "step": 492090 }, { "epoch": 2.925144592851496, "grad_norm": 1.4240224361419678, "learning_rate": 2.0341213953273915e-05, "loss": 0.5065670013427734, "step": 492100 }, { "epoch": 2.9252040349281643, "grad_norm": 1.2079811096191406, "learning_rate": 2.0340672642895615e-05, "loss": 0.4399570465087891, "step": 492110 }, { "epoch": 2.9252634770048327, "grad_norm": 1.2677361965179443, "learning_rate": 2.034013176141824e-05, "loss": 0.48166933059692385, "step": 492120 }, { "epoch": 2.925322919081501, "grad_norm": 1.456610083580017, "learning_rate": 2.0339591308844353e-05, "loss": 0.4825435638427734, "step": 492130 }, { "epoch": 2.9253823611581695, "grad_norm": 1.5861122608184814, "learning_rate": 2.0339051285176582e-05, "loss": 0.4407508850097656, "step": 492140 }, { "epoch": 2.925441803234838, "grad_norm": 1.2004847526550293, "learning_rate": 2.0338511690417475e-05, "loss": 0.4295808792114258, "step": 492150 }, { "epoch": 2.9255012453115063, "grad_norm": 1.4696627855300903, "learning_rate": 2.0337972524569636e-05, "loss": 0.4658210754394531, "step": 492160 }, { "epoch": 2.9255606873881748, "grad_norm": 1.253714680671692, "learning_rate": 2.0337433787635636e-05, "loss": 0.46094818115234376, "step": 492170 }, { "epoch": 2.9256201294648427, "grad_norm": 1.1631546020507812, "learning_rate": 2.0336895479618042e-05, "loss": 0.4603278636932373, "step": 492180 }, { "epoch": 2.9256795715415116, "grad_norm": 1.2896740436553955, "learning_rate": 2.033635760051944e-05, "loss": 0.4297312259674072, "step": 492190 }, { "epoch": 2.9257390136181796, "grad_norm": 1.096293330192566, "learning_rate": 2.03358201503424e-05, "loss": 0.44457073211669923, "step": 492200 }, { "epoch": 2.9257984556948484, "grad_norm": 1.4552804231643677, "learning_rate": 2.0335283129089503e-05, "loss": 0.4678036689758301, "step": 492210 }, { "epoch": 2.9258578977715164, "grad_norm": 1.0797935724258423, "learning_rate": 2.03347465367633e-05, "loss": 0.45937066078186034, "step": 492220 }, { "epoch": 2.925917339848185, "grad_norm": 1.1718695163726807, "learning_rate": 2.033421037336637e-05, "loss": 0.44010152816772463, "step": 492230 }, { "epoch": 2.925976781924853, "grad_norm": 1.155597448348999, "learning_rate": 2.033367463890127e-05, "loss": 0.45506772994995115, "step": 492240 }, { "epoch": 2.9260362240015216, "grad_norm": 1.3163869380950928, "learning_rate": 2.0333139333370576e-05, "loss": 0.5126855850219727, "step": 492250 }, { "epoch": 2.92609566607819, "grad_norm": 1.244572401046753, "learning_rate": 2.033260445677683e-05, "loss": 0.4595595359802246, "step": 492260 }, { "epoch": 2.9261551081548585, "grad_norm": 1.0607757568359375, "learning_rate": 2.033207000912261e-05, "loss": 0.44605288505554197, "step": 492270 }, { "epoch": 2.926214550231527, "grad_norm": 1.7216460704803467, "learning_rate": 2.0331535990410447e-05, "loss": 0.4769582271575928, "step": 492280 }, { "epoch": 2.9262739923081953, "grad_norm": 1.2023667097091675, "learning_rate": 2.0331002400642926e-05, "loss": 0.48311724662780764, "step": 492290 }, { "epoch": 2.9263334343848637, "grad_norm": 1.2377467155456543, "learning_rate": 2.0330469239822583e-05, "loss": 0.4544086456298828, "step": 492300 }, { "epoch": 2.926392876461532, "grad_norm": 1.3796319961547852, "learning_rate": 2.0329936507951976e-05, "loss": 0.4621117115020752, "step": 492310 }, { "epoch": 2.9264523185382005, "grad_norm": 1.4459490776062012, "learning_rate": 2.0329404205033642e-05, "loss": 0.4762387752532959, "step": 492320 }, { "epoch": 2.926511760614869, "grad_norm": 1.1561459302902222, "learning_rate": 2.032887233107013e-05, "loss": 0.4672114372253418, "step": 492330 }, { "epoch": 2.9265712026915374, "grad_norm": 1.28946852684021, "learning_rate": 2.032834088606399e-05, "loss": 0.4841634750366211, "step": 492340 }, { "epoch": 2.926630644768206, "grad_norm": 1.2326576709747314, "learning_rate": 2.0327809870017776e-05, "loss": 0.47727556228637696, "step": 492350 }, { "epoch": 2.926690086844874, "grad_norm": 0.9614645838737488, "learning_rate": 2.0327279282933995e-05, "loss": 0.40132851600646974, "step": 492360 }, { "epoch": 2.926749528921542, "grad_norm": 1.1766303777694702, "learning_rate": 2.0326749124815208e-05, "loss": 0.4791682243347168, "step": 492370 }, { "epoch": 2.926808970998211, "grad_norm": 1.453757882118225, "learning_rate": 2.0326219395663957e-05, "loss": 0.46092729568481444, "step": 492380 }, { "epoch": 2.926868413074879, "grad_norm": 1.3701727390289307, "learning_rate": 2.032569009548276e-05, "loss": 0.47550311088562014, "step": 492390 }, { "epoch": 2.9269278551515474, "grad_norm": 1.1759074926376343, "learning_rate": 2.032516122427415e-05, "loss": 0.45241289138793944, "step": 492400 }, { "epoch": 2.926987297228216, "grad_norm": 1.60234797000885, "learning_rate": 2.032463278204068e-05, "loss": 0.4786100387573242, "step": 492410 }, { "epoch": 2.9270467393048842, "grad_norm": 1.4867002964019775, "learning_rate": 2.0324104768784845e-05, "loss": 0.43218579292297366, "step": 492420 }, { "epoch": 2.9271061813815527, "grad_norm": 1.4001611471176147, "learning_rate": 2.0323577184509197e-05, "loss": 0.5008902549743652, "step": 492430 }, { "epoch": 2.927165623458221, "grad_norm": 1.5421189069747925, "learning_rate": 2.032305002921624e-05, "loss": 0.4737497329711914, "step": 492440 }, { "epoch": 2.9272250655348895, "grad_norm": 1.5076701641082764, "learning_rate": 2.032252330290851e-05, "loss": 0.424207067489624, "step": 492450 }, { "epoch": 2.927284507611558, "grad_norm": 0.8551988005638123, "learning_rate": 2.0321997005588515e-05, "loss": 0.43243980407714844, "step": 492460 }, { "epoch": 2.9273439496882263, "grad_norm": 1.3767746686935425, "learning_rate": 2.0321471137258795e-05, "loss": 0.4754611015319824, "step": 492470 }, { "epoch": 2.9274033917648947, "grad_norm": 1.3622809648513794, "learning_rate": 2.0320945697921833e-05, "loss": 0.4799202919006348, "step": 492480 }, { "epoch": 2.927462833841563, "grad_norm": 0.9880627989768982, "learning_rate": 2.032042068758016e-05, "loss": 0.4669055938720703, "step": 492490 }, { "epoch": 2.9275222759182316, "grad_norm": 1.155613899230957, "learning_rate": 2.0319896106236296e-05, "loss": 0.47611660957336427, "step": 492500 }, { "epoch": 2.9275817179949, "grad_norm": 1.1216819286346436, "learning_rate": 2.031937195389274e-05, "loss": 0.5138393878936768, "step": 492510 }, { "epoch": 2.9276411600715684, "grad_norm": 1.2448196411132812, "learning_rate": 2.0318848230551994e-05, "loss": 0.46111230850219725, "step": 492520 }, { "epoch": 2.927700602148237, "grad_norm": 1.4288438558578491, "learning_rate": 2.0318324936216583e-05, "loss": 0.449659538269043, "step": 492530 }, { "epoch": 2.9277600442249048, "grad_norm": 1.9311331510543823, "learning_rate": 2.0317802070888986e-05, "loss": 0.5071194648742676, "step": 492540 }, { "epoch": 2.9278194863015736, "grad_norm": 1.171170949935913, "learning_rate": 2.031727963457172e-05, "loss": 0.47338228225708007, "step": 492550 }, { "epoch": 2.9278789283782416, "grad_norm": 1.4973541498184204, "learning_rate": 2.031675762726728e-05, "loss": 0.47609786987304686, "step": 492560 }, { "epoch": 2.9279383704549105, "grad_norm": 1.223802924156189, "learning_rate": 2.0316236048978158e-05, "loss": 0.4206096172332764, "step": 492570 }, { "epoch": 2.9279978125315784, "grad_norm": 1.1958599090576172, "learning_rate": 2.031571489970685e-05, "loss": 0.414718770980835, "step": 492580 }, { "epoch": 2.928057254608247, "grad_norm": 1.3886886835098267, "learning_rate": 2.031519417945586e-05, "loss": 0.4940019607543945, "step": 492590 }, { "epoch": 2.9281166966849153, "grad_norm": 1.28033447265625, "learning_rate": 2.031467388822767e-05, "loss": 0.4441844463348389, "step": 492600 }, { "epoch": 2.9281761387615837, "grad_norm": 0.9307246208190918, "learning_rate": 2.0314154026024776e-05, "loss": 0.4579764842987061, "step": 492610 }, { "epoch": 2.928235580838252, "grad_norm": 1.6207634210586548, "learning_rate": 2.0313634592849654e-05, "loss": 0.47158288955688477, "step": 492620 }, { "epoch": 2.9282950229149205, "grad_norm": 1.8446216583251953, "learning_rate": 2.0313115588704793e-05, "loss": 0.473301362991333, "step": 492630 }, { "epoch": 2.928354464991589, "grad_norm": 1.5671101808547974, "learning_rate": 2.031259701359268e-05, "loss": 0.4412832736968994, "step": 492640 }, { "epoch": 2.9284139070682573, "grad_norm": 1.4803380966186523, "learning_rate": 2.0312078867515784e-05, "loss": 0.4632267475128174, "step": 492650 }, { "epoch": 2.9284733491449257, "grad_norm": 1.4509919881820679, "learning_rate": 2.0311561150476606e-05, "loss": 0.4734968662261963, "step": 492660 }, { "epoch": 2.928532791221594, "grad_norm": 1.6205819845199585, "learning_rate": 2.0311043862477604e-05, "loss": 0.4398850440979004, "step": 492670 }, { "epoch": 2.9285922332982626, "grad_norm": 1.309504747390747, "learning_rate": 2.0310527003521257e-05, "loss": 0.410733699798584, "step": 492680 }, { "epoch": 2.928651675374931, "grad_norm": 1.176875114440918, "learning_rate": 2.0310010573610032e-05, "loss": 0.4545408248901367, "step": 492690 }, { "epoch": 2.9287111174515994, "grad_norm": 1.449607253074646, "learning_rate": 2.0309494572746416e-05, "loss": 0.40560150146484375, "step": 492700 }, { "epoch": 2.928770559528268, "grad_norm": 1.8078851699829102, "learning_rate": 2.0308979000932862e-05, "loss": 0.5079804420471191, "step": 492710 }, { "epoch": 2.9288300016049362, "grad_norm": 1.3692045211791992, "learning_rate": 2.0308463858171833e-05, "loss": 0.38478403091430663, "step": 492720 }, { "epoch": 2.928889443681604, "grad_norm": 1.2687338590621948, "learning_rate": 2.030794914446582e-05, "loss": 0.4511255264282227, "step": 492730 }, { "epoch": 2.928948885758273, "grad_norm": 1.0750784873962402, "learning_rate": 2.030743485981725e-05, "loss": 0.4315805435180664, "step": 492740 }, { "epoch": 2.929008327834941, "grad_norm": 1.456936001777649, "learning_rate": 2.0306921004228603e-05, "loss": 0.44167070388793944, "step": 492750 }, { "epoch": 2.92906776991161, "grad_norm": 1.0729076862335205, "learning_rate": 2.0306407577702337e-05, "loss": 0.45803275108337405, "step": 492760 }, { "epoch": 2.929127211988278, "grad_norm": 1.045623540878296, "learning_rate": 2.0305894580240905e-05, "loss": 0.42920970916748047, "step": 492770 }, { "epoch": 2.9291866540649463, "grad_norm": 1.6419955492019653, "learning_rate": 2.0305382011846756e-05, "loss": 0.44872894287109377, "step": 492780 }, { "epoch": 2.9292460961416147, "grad_norm": 1.3342145681381226, "learning_rate": 2.030486987252236e-05, "loss": 0.4591535568237305, "step": 492790 }, { "epoch": 2.929305538218283, "grad_norm": 1.0607929229736328, "learning_rate": 2.0304358162270137e-05, "loss": 0.4781200408935547, "step": 492800 }, { "epoch": 2.9293649802949515, "grad_norm": 1.424119472503662, "learning_rate": 2.030384688109256e-05, "loss": 0.45668468475341795, "step": 492810 }, { "epoch": 2.92942442237162, "grad_norm": 1.1767172813415527, "learning_rate": 2.0303336028992072e-05, "loss": 0.4874879837036133, "step": 492820 }, { "epoch": 2.9294838644482883, "grad_norm": 1.0695877075195312, "learning_rate": 2.03028256059711e-05, "loss": 0.4411949634552002, "step": 492830 }, { "epoch": 2.9295433065249568, "grad_norm": 1.2000727653503418, "learning_rate": 2.030231561203211e-05, "loss": 0.4329672813415527, "step": 492840 }, { "epoch": 2.929602748601625, "grad_norm": 1.2910481691360474, "learning_rate": 2.030180604717752e-05, "loss": 0.46678552627563474, "step": 492850 }, { "epoch": 2.9296621906782936, "grad_norm": 1.4001692533493042, "learning_rate": 2.0301296911409773e-05, "loss": 0.4757205963134766, "step": 492860 }, { "epoch": 2.929721632754962, "grad_norm": 1.6396522521972656, "learning_rate": 2.0300788204731314e-05, "loss": 0.47292509078979494, "step": 492870 }, { "epoch": 2.9297810748316304, "grad_norm": 1.2165749073028564, "learning_rate": 2.0300279927144563e-05, "loss": 0.4737152099609375, "step": 492880 }, { "epoch": 2.929840516908299, "grad_norm": 1.1132729053497314, "learning_rate": 2.0299772078651964e-05, "loss": 0.43356857299804685, "step": 492890 }, { "epoch": 2.9298999589849672, "grad_norm": 1.3259552717208862, "learning_rate": 2.0299264659255943e-05, "loss": 0.48247499465942384, "step": 492900 }, { "epoch": 2.9299594010616357, "grad_norm": 1.4636907577514648, "learning_rate": 2.029875766895893e-05, "loss": 0.47755918502807615, "step": 492910 }, { "epoch": 2.9300188431383036, "grad_norm": 1.3320837020874023, "learning_rate": 2.0298251107763338e-05, "loss": 0.43892321586608884, "step": 492920 }, { "epoch": 2.9300782852149725, "grad_norm": 1.345436692237854, "learning_rate": 2.029774497567159e-05, "loss": 0.5230600357055664, "step": 492930 }, { "epoch": 2.9301377272916405, "grad_norm": 1.492469310760498, "learning_rate": 2.0297239272686133e-05, "loss": 0.5262363433837891, "step": 492940 }, { "epoch": 2.9301971693683093, "grad_norm": 1.3527703285217285, "learning_rate": 2.0296733998809354e-05, "loss": 0.459507417678833, "step": 492950 }, { "epoch": 2.9302566114449773, "grad_norm": 1.2707304954528809, "learning_rate": 2.0296229154043695e-05, "loss": 0.46291866302490237, "step": 492960 }, { "epoch": 2.9303160535216457, "grad_norm": 1.6658096313476562, "learning_rate": 2.0295724738391548e-05, "loss": 0.5104570388793945, "step": 492970 }, { "epoch": 2.930375495598314, "grad_norm": 1.39895498752594, "learning_rate": 2.029522075185534e-05, "loss": 0.48160572052001954, "step": 492980 }, { "epoch": 2.9304349376749825, "grad_norm": 1.309767484664917, "learning_rate": 2.0294717194437488e-05, "loss": 0.4627120018005371, "step": 492990 }, { "epoch": 2.930494379751651, "grad_norm": 1.3078893423080444, "learning_rate": 2.0294214066140393e-05, "loss": 0.47946815490722655, "step": 493000 }, { "epoch": 2.9305538218283194, "grad_norm": 1.2275645732879639, "learning_rate": 2.0293711366966455e-05, "loss": 0.4009710311889648, "step": 493010 }, { "epoch": 2.9306132639049878, "grad_norm": 1.602659821510315, "learning_rate": 2.029320909691809e-05, "loss": 0.4746638298034668, "step": 493020 }, { "epoch": 2.930672705981656, "grad_norm": 1.2397352457046509, "learning_rate": 2.0292707255997696e-05, "loss": 0.47469725608825686, "step": 493030 }, { "epoch": 2.9307321480583246, "grad_norm": 1.4828248023986816, "learning_rate": 2.0292205844207675e-05, "loss": 0.43936796188354493, "step": 493040 }, { "epoch": 2.930791590134993, "grad_norm": 1.5135011672973633, "learning_rate": 2.0291704861550416e-05, "loss": 0.5012887001037598, "step": 493050 }, { "epoch": 2.9308510322116614, "grad_norm": 1.086532711982727, "learning_rate": 2.0291204308028326e-05, "loss": 0.4685681343078613, "step": 493060 }, { "epoch": 2.93091047428833, "grad_norm": 1.309133529663086, "learning_rate": 2.029070418364381e-05, "loss": 0.4868345260620117, "step": 493070 }, { "epoch": 2.9309699163649983, "grad_norm": 1.44197416305542, "learning_rate": 2.0290204488399237e-05, "loss": 0.46567707061767577, "step": 493080 }, { "epoch": 2.9310293584416667, "grad_norm": 1.4564865827560425, "learning_rate": 2.0289705222297007e-05, "loss": 0.45454964637756345, "step": 493090 }, { "epoch": 2.931088800518335, "grad_norm": 1.5410692691802979, "learning_rate": 2.0289206385339515e-05, "loss": 0.4179252624511719, "step": 493100 }, { "epoch": 2.931148242595003, "grad_norm": 1.2125686407089233, "learning_rate": 2.0288707977529144e-05, "loss": 0.4701526641845703, "step": 493110 }, { "epoch": 2.931207684671672, "grad_norm": 1.479838490486145, "learning_rate": 2.0288209998868266e-05, "loss": 0.4050435543060303, "step": 493120 }, { "epoch": 2.93126712674834, "grad_norm": 1.315086007118225, "learning_rate": 2.028771244935928e-05, "loss": 0.42621631622314454, "step": 493130 }, { "epoch": 2.9313265688250083, "grad_norm": 0.9007627964019775, "learning_rate": 2.028721532900456e-05, "loss": 0.4474805355072021, "step": 493140 }, { "epoch": 2.9313860109016767, "grad_norm": 1.4090358018875122, "learning_rate": 2.0286718637806478e-05, "loss": 0.47640209197998046, "step": 493150 }, { "epoch": 2.931445452978345, "grad_norm": 1.3410096168518066, "learning_rate": 2.0286222375767426e-05, "loss": 0.47412567138671874, "step": 493160 }, { "epoch": 2.9315048950550135, "grad_norm": 1.2132031917572021, "learning_rate": 2.028572654288976e-05, "loss": 0.529348611831665, "step": 493170 }, { "epoch": 2.931564337131682, "grad_norm": 1.1031285524368286, "learning_rate": 2.028523113917586e-05, "loss": 0.44240684509277345, "step": 493180 }, { "epoch": 2.9316237792083504, "grad_norm": 1.3042515516281128, "learning_rate": 2.028473616462809e-05, "loss": 0.50656099319458, "step": 493190 }, { "epoch": 2.931683221285019, "grad_norm": 1.055456280708313, "learning_rate": 2.0284241619248834e-05, "loss": 0.44769535064697263, "step": 493200 }, { "epoch": 2.931742663361687, "grad_norm": 1.4831902980804443, "learning_rate": 2.0283747503040435e-05, "loss": 0.452932071685791, "step": 493210 }, { "epoch": 2.9318021054383556, "grad_norm": 1.7729276418685913, "learning_rate": 2.028325381600527e-05, "loss": 0.5130398750305176, "step": 493220 }, { "epoch": 2.931861547515024, "grad_norm": 1.3444063663482666, "learning_rate": 2.0282760558145712e-05, "loss": 0.44693427085876464, "step": 493230 }, { "epoch": 2.9319209895916925, "grad_norm": 1.5940858125686646, "learning_rate": 2.0282267729464087e-05, "loss": 0.4602458953857422, "step": 493240 }, { "epoch": 2.931980431668361, "grad_norm": 1.3450859785079956, "learning_rate": 2.0281775329962787e-05, "loss": 0.4451756000518799, "step": 493250 }, { "epoch": 2.9320398737450293, "grad_norm": 1.2778737545013428, "learning_rate": 2.0281283359644154e-05, "loss": 0.4687098503112793, "step": 493260 }, { "epoch": 2.9320993158216977, "grad_norm": 1.4155243635177612, "learning_rate": 2.0280791818510535e-05, "loss": 0.4101426124572754, "step": 493270 }, { "epoch": 2.9321587578983657, "grad_norm": 1.6576671600341797, "learning_rate": 2.02803007065643e-05, "loss": 0.4883717060089111, "step": 493280 }, { "epoch": 2.9322181999750345, "grad_norm": 1.4671064615249634, "learning_rate": 2.027981002380777e-05, "loss": 0.47522449493408203, "step": 493290 }, { "epoch": 2.9322776420517025, "grad_norm": 1.2441999912261963, "learning_rate": 2.0279319770243315e-05, "loss": 0.501870059967041, "step": 493300 }, { "epoch": 2.9323370841283714, "grad_norm": 1.284183382987976, "learning_rate": 2.0278829945873272e-05, "loss": 0.4613675117492676, "step": 493310 }, { "epoch": 2.9323965262050393, "grad_norm": 1.9017471075057983, "learning_rate": 2.0278340550699983e-05, "loss": 0.481229305267334, "step": 493320 }, { "epoch": 2.9324559682817077, "grad_norm": 1.2985577583312988, "learning_rate": 2.0277851584725794e-05, "loss": 0.5062343597412109, "step": 493330 }, { "epoch": 2.932515410358376, "grad_norm": 1.263096809387207, "learning_rate": 2.0277363047953048e-05, "loss": 0.44483642578125, "step": 493340 }, { "epoch": 2.9325748524350446, "grad_norm": 1.3150540590286255, "learning_rate": 2.0276874940384067e-05, "loss": 0.47024011611938477, "step": 493350 }, { "epoch": 2.932634294511713, "grad_norm": 1.3074432611465454, "learning_rate": 2.0276387262021195e-05, "loss": 0.44906110763549806, "step": 493360 }, { "epoch": 2.9326937365883814, "grad_norm": 1.3822180032730103, "learning_rate": 2.027590001286677e-05, "loss": 0.4283731937408447, "step": 493370 }, { "epoch": 2.93275317866505, "grad_norm": 1.2113786935806274, "learning_rate": 2.0275413192923112e-05, "loss": 0.46037731170654295, "step": 493380 }, { "epoch": 2.9328126207417182, "grad_norm": 1.2141700983047485, "learning_rate": 2.027492680219255e-05, "loss": 0.48807482719421386, "step": 493390 }, { "epoch": 2.9328720628183866, "grad_norm": 1.8280503749847412, "learning_rate": 2.027444084067743e-05, "loss": 0.4803775310516357, "step": 493400 }, { "epoch": 2.932931504895055, "grad_norm": 1.359462857246399, "learning_rate": 2.0273955308380054e-05, "loss": 0.4585736274719238, "step": 493410 }, { "epoch": 2.9329909469717235, "grad_norm": 1.5253254175186157, "learning_rate": 2.0273470205302748e-05, "loss": 0.47771511077880857, "step": 493420 }, { "epoch": 2.933050389048392, "grad_norm": 1.6123249530792236, "learning_rate": 2.0272985531447847e-05, "loss": 0.48305749893188477, "step": 493430 }, { "epoch": 2.9331098311250603, "grad_norm": 1.2802180051803589, "learning_rate": 2.0272501286817654e-05, "loss": 0.44611315727233886, "step": 493440 }, { "epoch": 2.9331692732017287, "grad_norm": 1.7539944648742676, "learning_rate": 2.027201747141449e-05, "loss": 0.5006324768066406, "step": 493450 }, { "epoch": 2.933228715278397, "grad_norm": 1.1457520723342896, "learning_rate": 2.027153408524068e-05, "loss": 0.4067215442657471, "step": 493460 }, { "epoch": 2.933288157355065, "grad_norm": 1.254422903060913, "learning_rate": 2.0271051128298514e-05, "loss": 0.4503643035888672, "step": 493470 }, { "epoch": 2.933347599431734, "grad_norm": 1.1354254484176636, "learning_rate": 2.0270568600590322e-05, "loss": 0.41628637313842776, "step": 493480 }, { "epoch": 2.933407041508402, "grad_norm": 1.2652984857559204, "learning_rate": 2.027008650211841e-05, "loss": 0.40638084411621095, "step": 493490 }, { "epoch": 2.933466483585071, "grad_norm": 1.44841468334198, "learning_rate": 2.0269604832885082e-05, "loss": 0.47237534523010255, "step": 493500 }, { "epoch": 2.9335259256617388, "grad_norm": 1.6285064220428467, "learning_rate": 2.0269123592892636e-05, "loss": 0.4886777877807617, "step": 493510 }, { "epoch": 2.933585367738407, "grad_norm": 1.0750935077667236, "learning_rate": 2.0268642782143382e-05, "loss": 0.45479207038879393, "step": 493520 }, { "epoch": 2.9336448098150756, "grad_norm": 1.8133410215377808, "learning_rate": 2.0268162400639607e-05, "loss": 0.4764035701751709, "step": 493530 }, { "epoch": 2.933704251891744, "grad_norm": 1.2374038696289062, "learning_rate": 2.0267682448383626e-05, "loss": 0.5083621978759766, "step": 493540 }, { "epoch": 2.9337636939684124, "grad_norm": 1.4298386573791504, "learning_rate": 2.0267202925377725e-05, "loss": 0.42974443435668946, "step": 493550 }, { "epoch": 2.933823136045081, "grad_norm": 1.1712076663970947, "learning_rate": 2.0266723831624195e-05, "loss": 0.4614219665527344, "step": 493560 }, { "epoch": 2.9338825781217492, "grad_norm": 1.3674795627593994, "learning_rate": 2.0266245167125346e-05, "loss": 0.4590760231018066, "step": 493570 }, { "epoch": 2.9339420201984177, "grad_norm": 1.310034990310669, "learning_rate": 2.026576693188344e-05, "loss": 0.45243172645568847, "step": 493580 }, { "epoch": 2.934001462275086, "grad_norm": 1.0043600797653198, "learning_rate": 2.0265289125900792e-05, "loss": 0.40662379264831544, "step": 493590 }, { "epoch": 2.9340609043517545, "grad_norm": 1.6928009986877441, "learning_rate": 2.026481174917967e-05, "loss": 0.4535694122314453, "step": 493600 }, { "epoch": 2.934120346428423, "grad_norm": 1.1982698440551758, "learning_rate": 2.0264334801722358e-05, "loss": 0.4619132995605469, "step": 493610 }, { "epoch": 2.9341797885050913, "grad_norm": 1.4457671642303467, "learning_rate": 2.0263858283531153e-05, "loss": 0.5108983516693115, "step": 493620 }, { "epoch": 2.9342392305817597, "grad_norm": 1.3640644550323486, "learning_rate": 2.0263382194608317e-05, "loss": 0.498201322555542, "step": 493630 }, { "epoch": 2.934298672658428, "grad_norm": 1.2547253370285034, "learning_rate": 2.0262906534956135e-05, "loss": 0.46723217964172364, "step": 493640 }, { "epoch": 2.9343581147350966, "grad_norm": 1.2356191873550415, "learning_rate": 2.0262431304576886e-05, "loss": 0.45452136993408204, "step": 493650 }, { "epoch": 2.9344175568117645, "grad_norm": 1.0038341283798218, "learning_rate": 2.026195650347283e-05, "loss": 0.475282096862793, "step": 493660 }, { "epoch": 2.9344769988884334, "grad_norm": 1.059164047241211, "learning_rate": 2.026148213164625e-05, "loss": 0.4533099174499512, "step": 493670 }, { "epoch": 2.9345364409651014, "grad_norm": 1.4804737567901611, "learning_rate": 2.026100818909941e-05, "loss": 0.4360026836395264, "step": 493680 }, { "epoch": 2.93459588304177, "grad_norm": 1.1024487018585205, "learning_rate": 2.0260534675834595e-05, "loss": 0.4334433555603027, "step": 493690 }, { "epoch": 2.934655325118438, "grad_norm": 1.3353158235549927, "learning_rate": 2.0260061591854042e-05, "loss": 0.4683931827545166, "step": 493700 }, { "epoch": 2.9347147671951066, "grad_norm": 1.3983224630355835, "learning_rate": 2.025958893716003e-05, "loss": 0.48143830299377444, "step": 493710 }, { "epoch": 2.934774209271775, "grad_norm": 1.1376957893371582, "learning_rate": 2.025911671175482e-05, "loss": 0.4079634189605713, "step": 493720 }, { "epoch": 2.9348336513484434, "grad_norm": 1.2419168949127197, "learning_rate": 2.0258644915640664e-05, "loss": 0.43459334373474123, "step": 493730 }, { "epoch": 2.934893093425112, "grad_norm": 1.361515998840332, "learning_rate": 2.025817354881982e-05, "loss": 0.44560894966125486, "step": 493740 }, { "epoch": 2.9349525355017803, "grad_norm": 1.5248908996582031, "learning_rate": 2.025770261129455e-05, "loss": 0.5476689338684082, "step": 493750 }, { "epoch": 2.9350119775784487, "grad_norm": 1.2298592329025269, "learning_rate": 2.0257232103067102e-05, "loss": 0.46321864128112794, "step": 493760 }, { "epoch": 2.935071419655117, "grad_norm": 1.3494172096252441, "learning_rate": 2.025676202413973e-05, "loss": 0.455902099609375, "step": 493770 }, { "epoch": 2.9351308617317855, "grad_norm": 1.6354436874389648, "learning_rate": 2.025629237451468e-05, "loss": 0.5195513248443604, "step": 493780 }, { "epoch": 2.935190303808454, "grad_norm": 1.3369807004928589, "learning_rate": 2.0255823154194192e-05, "loss": 0.4682448387145996, "step": 493790 }, { "epoch": 2.9352497458851223, "grad_norm": 1.3447353839874268, "learning_rate": 2.0255354363180525e-05, "loss": 0.4246467113494873, "step": 493800 }, { "epoch": 2.9353091879617907, "grad_norm": 1.2901793718338013, "learning_rate": 2.0254886001475904e-05, "loss": 0.44990854263305663, "step": 493810 }, { "epoch": 2.935368630038459, "grad_norm": 1.1118258237838745, "learning_rate": 2.025441806908259e-05, "loss": 0.45786395072937014, "step": 493820 }, { "epoch": 2.9354280721151276, "grad_norm": 1.504418969154358, "learning_rate": 2.0253950566002804e-05, "loss": 0.4603249549865723, "step": 493830 }, { "epoch": 2.935487514191796, "grad_norm": 1.3226391077041626, "learning_rate": 2.0253483492238796e-05, "loss": 0.4135955810546875, "step": 493840 }, { "epoch": 2.935546956268464, "grad_norm": 1.431768536567688, "learning_rate": 2.025301684779279e-05, "loss": 0.44717884063720703, "step": 493850 }, { "epoch": 2.935606398345133, "grad_norm": 1.5354382991790771, "learning_rate": 2.0252550632667018e-05, "loss": 0.4745664596557617, "step": 493860 }, { "epoch": 2.935665840421801, "grad_norm": 1.2036794424057007, "learning_rate": 2.025208484686372e-05, "loss": 0.4564703941345215, "step": 493870 }, { "epoch": 2.935725282498469, "grad_norm": 1.5281367301940918, "learning_rate": 2.0251619490385106e-05, "loss": 0.4796431541442871, "step": 493880 }, { "epoch": 2.9357847245751376, "grad_norm": 1.2877815961837769, "learning_rate": 2.0251154563233428e-05, "loss": 0.45766606330871584, "step": 493890 }, { "epoch": 2.935844166651806, "grad_norm": 1.3794504404067993, "learning_rate": 2.0250690065410895e-05, "loss": 0.4358414649963379, "step": 493900 }, { "epoch": 2.9359036087284744, "grad_norm": 1.1117342710494995, "learning_rate": 2.025022599691973e-05, "loss": 0.46208529472351073, "step": 493910 }, { "epoch": 2.935963050805143, "grad_norm": 1.1289818286895752, "learning_rate": 2.0249762357762143e-05, "loss": 0.4335916519165039, "step": 493920 }, { "epoch": 2.9360224928818113, "grad_norm": 1.5219519138336182, "learning_rate": 2.0249299147940372e-05, "loss": 0.4460597515106201, "step": 493930 }, { "epoch": 2.9360819349584797, "grad_norm": 0.9472233653068542, "learning_rate": 2.0248836367456618e-05, "loss": 0.4577980041503906, "step": 493940 }, { "epoch": 2.936141377035148, "grad_norm": 1.3603661060333252, "learning_rate": 2.024837401631311e-05, "loss": 0.4744541168212891, "step": 493950 }, { "epoch": 2.9362008191118165, "grad_norm": 1.4184144735336304, "learning_rate": 2.024791209451204e-05, "loss": 0.47937793731689454, "step": 493960 }, { "epoch": 2.936260261188485, "grad_norm": 1.2478697299957275, "learning_rate": 2.024745060205563e-05, "loss": 0.46848478317260744, "step": 493970 }, { "epoch": 2.9363197032651533, "grad_norm": 1.3339821100234985, "learning_rate": 2.024698953894608e-05, "loss": 0.42815494537353516, "step": 493980 }, { "epoch": 2.9363791453418218, "grad_norm": 1.1114827394485474, "learning_rate": 2.02465289051856e-05, "loss": 0.43575477600097656, "step": 493990 }, { "epoch": 2.93643858741849, "grad_norm": 1.3476324081420898, "learning_rate": 2.0246068700776403e-05, "loss": 0.4932117462158203, "step": 494000 }, { "epoch": 2.9364980294951586, "grad_norm": 1.2084729671478271, "learning_rate": 2.0245608925720675e-05, "loss": 0.4305578231811523, "step": 494010 }, { "epoch": 2.9365574715718266, "grad_norm": 1.2897447347640991, "learning_rate": 2.0245149580020628e-05, "loss": 0.47309303283691406, "step": 494020 }, { "epoch": 2.9366169136484954, "grad_norm": 1.2764803171157837, "learning_rate": 2.0244690663678438e-05, "loss": 0.42945151329040526, "step": 494030 }, { "epoch": 2.9366763557251634, "grad_norm": 1.117614507675171, "learning_rate": 2.024423217669633e-05, "loss": 0.47696566581726074, "step": 494040 }, { "epoch": 2.9367357978018322, "grad_norm": 1.6055501699447632, "learning_rate": 2.0243774119076488e-05, "loss": 0.44344115257263184, "step": 494050 }, { "epoch": 2.9367952398785, "grad_norm": 1.356004238128662, "learning_rate": 2.0243316490821085e-05, "loss": 0.4723213672637939, "step": 494060 }, { "epoch": 2.9368546819551686, "grad_norm": 0.9956935048103333, "learning_rate": 2.0242859291932328e-05, "loss": 0.437160587310791, "step": 494070 }, { "epoch": 2.936914124031837, "grad_norm": 1.0590779781341553, "learning_rate": 2.02424025224124e-05, "loss": 0.48642902374267577, "step": 494080 }, { "epoch": 2.9369735661085055, "grad_norm": 1.4156030416488647, "learning_rate": 2.024194618226348e-05, "loss": 0.5015380859375, "step": 494090 }, { "epoch": 2.937033008185174, "grad_norm": 1.1618168354034424, "learning_rate": 2.024149027148776e-05, "loss": 0.4085689067840576, "step": 494100 }, { "epoch": 2.9370924502618423, "grad_norm": 1.267900824546814, "learning_rate": 2.024103479008741e-05, "loss": 0.4709298133850098, "step": 494110 }, { "epoch": 2.9371518923385107, "grad_norm": 1.3029412031173706, "learning_rate": 2.024057973806463e-05, "loss": 0.44730939865112307, "step": 494120 }, { "epoch": 2.937211334415179, "grad_norm": 1.5934890508651733, "learning_rate": 2.024012511542158e-05, "loss": 0.4676965713500977, "step": 494130 }, { "epoch": 2.9372707764918475, "grad_norm": 1.578197956085205, "learning_rate": 2.023967092216043e-05, "loss": 0.4541065216064453, "step": 494140 }, { "epoch": 2.937330218568516, "grad_norm": 1.2010042667388916, "learning_rate": 2.0239217158283364e-05, "loss": 0.48839564323425294, "step": 494150 }, { "epoch": 2.9373896606451844, "grad_norm": 1.4876242876052856, "learning_rate": 2.0238763823792547e-05, "loss": 0.4393035411834717, "step": 494160 }, { "epoch": 2.937449102721853, "grad_norm": 1.1997781991958618, "learning_rate": 2.0238310918690145e-05, "loss": 0.46552734375, "step": 494170 }, { "epoch": 2.937508544798521, "grad_norm": 1.2319945096969604, "learning_rate": 2.023785844297834e-05, "loss": 0.433826208114624, "step": 494180 }, { "epoch": 2.9375679868751896, "grad_norm": 1.4702290296554565, "learning_rate": 2.023740639665928e-05, "loss": 0.47058725357055664, "step": 494190 }, { "epoch": 2.937627428951858, "grad_norm": 1.5697873830795288, "learning_rate": 2.0236954779735133e-05, "loss": 0.46730813980102537, "step": 494200 }, { "epoch": 2.937686871028526, "grad_norm": 1.591635823249817, "learning_rate": 2.0236503592208066e-05, "loss": 0.466074275970459, "step": 494210 }, { "epoch": 2.937746313105195, "grad_norm": 1.4390840530395508, "learning_rate": 2.023605283408022e-05, "loss": 0.40592069625854493, "step": 494220 }, { "epoch": 2.937805755181863, "grad_norm": 1.4194798469543457, "learning_rate": 2.023560250535377e-05, "loss": 0.4921867370605469, "step": 494230 }, { "epoch": 2.9378651972585317, "grad_norm": 1.7384463548660278, "learning_rate": 2.0235152606030855e-05, "loss": 0.49674224853515625, "step": 494240 }, { "epoch": 2.9379246393351997, "grad_norm": 1.3563987016677856, "learning_rate": 2.023470313611364e-05, "loss": 0.45149741172790525, "step": 494250 }, { "epoch": 2.937984081411868, "grad_norm": 1.4384859800338745, "learning_rate": 2.0234254095604275e-05, "loss": 0.44457225799560546, "step": 494260 }, { "epoch": 2.9380435234885365, "grad_norm": 1.4529292583465576, "learning_rate": 2.0233805484504895e-05, "loss": 0.4783929824829102, "step": 494270 }, { "epoch": 2.938102965565205, "grad_norm": 1.447422981262207, "learning_rate": 2.023335730281765e-05, "loss": 0.4650267124176025, "step": 494280 }, { "epoch": 2.9381624076418733, "grad_norm": 1.1899162530899048, "learning_rate": 2.0232909550544692e-05, "loss": 0.4253437042236328, "step": 494290 }, { "epoch": 2.9382218497185417, "grad_norm": 1.5517668724060059, "learning_rate": 2.0232462227688158e-05, "loss": 0.4776963710784912, "step": 494300 }, { "epoch": 2.93828129179521, "grad_norm": 1.4985054731369019, "learning_rate": 2.0232015334250192e-05, "loss": 0.4920366287231445, "step": 494310 }, { "epoch": 2.9383407338718786, "grad_norm": 1.9096688032150269, "learning_rate": 2.0231568870232926e-05, "loss": 0.4795267105102539, "step": 494320 }, { "epoch": 2.938400175948547, "grad_norm": 1.255550503730774, "learning_rate": 2.0231122835638498e-05, "loss": 0.4542410850524902, "step": 494330 }, { "epoch": 2.9384596180252154, "grad_norm": 1.2603882551193237, "learning_rate": 2.0230677230469045e-05, "loss": 0.4165828704833984, "step": 494340 }, { "epoch": 2.938519060101884, "grad_norm": 1.3516278266906738, "learning_rate": 2.0230232054726683e-05, "loss": 0.4047112464904785, "step": 494350 }, { "epoch": 2.938578502178552, "grad_norm": 1.3981659412384033, "learning_rate": 2.0229787308413568e-05, "loss": 0.4318850517272949, "step": 494360 }, { "epoch": 2.9386379442552206, "grad_norm": 1.3076037168502808, "learning_rate": 2.02293429915318e-05, "loss": 0.4808805465698242, "step": 494370 }, { "epoch": 2.938697386331889, "grad_norm": 1.124031662940979, "learning_rate": 2.0228899104083533e-05, "loss": 0.45540337562561034, "step": 494380 }, { "epoch": 2.9387568284085575, "grad_norm": 1.1825073957443237, "learning_rate": 2.022845564607086e-05, "loss": 0.4170376777648926, "step": 494390 }, { "epoch": 2.9388162704852254, "grad_norm": 1.7425493001937866, "learning_rate": 2.0228012617495926e-05, "loss": 0.42908172607421874, "step": 494400 }, { "epoch": 2.9388757125618943, "grad_norm": 1.8121176958084106, "learning_rate": 2.0227570018360842e-05, "loss": 0.4969926834106445, "step": 494410 }, { "epoch": 2.9389351546385623, "grad_norm": 1.2076029777526855, "learning_rate": 2.0227127848667723e-05, "loss": 0.49012055397033694, "step": 494420 }, { "epoch": 2.938994596715231, "grad_norm": 1.5017402172088623, "learning_rate": 2.022668610841868e-05, "loss": 0.5027891159057617, "step": 494430 }, { "epoch": 2.939054038791899, "grad_norm": 1.2372745275497437, "learning_rate": 2.0226244797615852e-05, "loss": 0.46048736572265625, "step": 494440 }, { "epoch": 2.9391134808685675, "grad_norm": 1.8071039915084839, "learning_rate": 2.0225803916261306e-05, "loss": 0.48780479431152346, "step": 494450 }, { "epoch": 2.939172922945236, "grad_norm": 1.028692364692688, "learning_rate": 2.02253634643572e-05, "loss": 0.45014204978942873, "step": 494460 }, { "epoch": 2.9392323650219043, "grad_norm": 1.1790502071380615, "learning_rate": 2.0224923441905592e-05, "loss": 0.48285207748413084, "step": 494470 }, { "epoch": 2.9392918070985727, "grad_norm": 1.1810098886489868, "learning_rate": 2.022448384890863e-05, "loss": 0.4330780029296875, "step": 494480 }, { "epoch": 2.939351249175241, "grad_norm": 1.2869056463241577, "learning_rate": 2.0224044685368387e-05, "loss": 0.4977402210235596, "step": 494490 }, { "epoch": 2.9394106912519096, "grad_norm": 1.2303426265716553, "learning_rate": 2.022360595128698e-05, "loss": 0.44505810737609863, "step": 494500 }, { "epoch": 2.939470133328578, "grad_norm": 1.1301031112670898, "learning_rate": 2.0223167646666503e-05, "loss": 0.4541661739349365, "step": 494510 }, { "epoch": 2.9395295754052464, "grad_norm": 1.0913556814193726, "learning_rate": 2.0222729771509048e-05, "loss": 0.4365664482116699, "step": 494520 }, { "epoch": 2.939589017481915, "grad_norm": 1.176398754119873, "learning_rate": 2.022229232581672e-05, "loss": 0.44651012420654296, "step": 494530 }, { "epoch": 2.9396484595585832, "grad_norm": 1.4423277378082275, "learning_rate": 2.0221855309591613e-05, "loss": 0.4535764217376709, "step": 494540 }, { "epoch": 2.9397079016352516, "grad_norm": 0.9492327570915222, "learning_rate": 2.0221418722835795e-05, "loss": 0.4221469879150391, "step": 494550 }, { "epoch": 2.93976734371192, "grad_norm": 1.4931702613830566, "learning_rate": 2.022098256555138e-05, "loss": 0.42750062942504885, "step": 494560 }, { "epoch": 2.9398267857885885, "grad_norm": 1.2454793453216553, "learning_rate": 2.0220546837740443e-05, "loss": 0.4515749454498291, "step": 494570 }, { "epoch": 2.939886227865257, "grad_norm": 1.287049412727356, "learning_rate": 2.0220111539405068e-05, "loss": 0.4602216720581055, "step": 494580 }, { "epoch": 2.939945669941925, "grad_norm": 1.7280863523483276, "learning_rate": 2.0219676670547334e-05, "loss": 0.481766939163208, "step": 494590 }, { "epoch": 2.9400051120185937, "grad_norm": 1.349622130393982, "learning_rate": 2.021924223116933e-05, "loss": 0.4476963520050049, "step": 494600 }, { "epoch": 2.9400645540952617, "grad_norm": 1.226236343383789, "learning_rate": 2.0218808221273126e-05, "loss": 0.42186574935913085, "step": 494610 }, { "epoch": 2.94012399617193, "grad_norm": 1.8877954483032227, "learning_rate": 2.0218374640860816e-05, "loss": 0.43511333465576174, "step": 494620 }, { "epoch": 2.9401834382485985, "grad_norm": 1.5160331726074219, "learning_rate": 2.021794148993445e-05, "loss": 0.492674732208252, "step": 494630 }, { "epoch": 2.940242880325267, "grad_norm": 1.230690836906433, "learning_rate": 2.021750876849612e-05, "loss": 0.47095494270324706, "step": 494640 }, { "epoch": 2.9403023224019353, "grad_norm": 1.0398707389831543, "learning_rate": 2.021707647654787e-05, "loss": 0.4380070686340332, "step": 494650 }, { "epoch": 2.9403617644786038, "grad_norm": 1.0586847066879272, "learning_rate": 2.021664461409179e-05, "loss": 0.49362621307373045, "step": 494660 }, { "epoch": 2.940421206555272, "grad_norm": 1.1859097480773926, "learning_rate": 2.0216213181129956e-05, "loss": 0.49878759384155275, "step": 494670 }, { "epoch": 2.9404806486319406, "grad_norm": 1.16153883934021, "learning_rate": 2.02157821776644e-05, "loss": 0.4596217155456543, "step": 494680 }, { "epoch": 2.940540090708609, "grad_norm": 1.2568060159683228, "learning_rate": 2.021535160369721e-05, "loss": 0.48913049697875977, "step": 494690 }, { "epoch": 2.9405995327852774, "grad_norm": 1.0649536848068237, "learning_rate": 2.0214921459230435e-05, "loss": 0.46709909439086916, "step": 494700 }, { "epoch": 2.940658974861946, "grad_norm": 1.5344346761703491, "learning_rate": 2.0214491744266122e-05, "loss": 0.4432100296020508, "step": 494710 }, { "epoch": 2.9407184169386142, "grad_norm": 1.1756680011749268, "learning_rate": 2.0214062458806353e-05, "loss": 0.4806997776031494, "step": 494720 }, { "epoch": 2.9407778590152827, "grad_norm": 1.330033779144287, "learning_rate": 2.021363360285316e-05, "loss": 0.5104292869567871, "step": 494730 }, { "epoch": 2.940837301091951, "grad_norm": 1.168778419494629, "learning_rate": 2.02132051764086e-05, "loss": 0.4380935192108154, "step": 494740 }, { "epoch": 2.9408967431686195, "grad_norm": 1.4429643154144287, "learning_rate": 2.021277717947473e-05, "loss": 0.5059496879577636, "step": 494750 }, { "epoch": 2.9409561852452875, "grad_norm": 1.3283888101577759, "learning_rate": 2.0212349612053587e-05, "loss": 0.44953417778015137, "step": 494760 }, { "epoch": 2.9410156273219563, "grad_norm": 1.3359988927841187, "learning_rate": 2.0211922474147223e-05, "loss": 0.49299206733703616, "step": 494770 }, { "epoch": 2.9410750693986243, "grad_norm": 1.3824924230575562, "learning_rate": 2.021149576575767e-05, "loss": 0.46695427894592284, "step": 494780 }, { "epoch": 2.941134511475293, "grad_norm": 1.0942782163619995, "learning_rate": 2.0211069486886992e-05, "loss": 0.45179996490478513, "step": 494790 }, { "epoch": 2.941193953551961, "grad_norm": 1.2513314485549927, "learning_rate": 2.0210643637537207e-05, "loss": 0.4660041809082031, "step": 494800 }, { "epoch": 2.9412533956286295, "grad_norm": 1.3727977275848389, "learning_rate": 2.021021821771035e-05, "loss": 0.42922191619873046, "step": 494810 }, { "epoch": 2.941312837705298, "grad_norm": 1.2264870405197144, "learning_rate": 2.020979322740848e-05, "loss": 0.4216853141784668, "step": 494820 }, { "epoch": 2.9413722797819664, "grad_norm": 1.4631614685058594, "learning_rate": 2.0209368666633614e-05, "loss": 0.448836088180542, "step": 494830 }, { "epoch": 2.9414317218586348, "grad_norm": 1.2308763265609741, "learning_rate": 2.020894453538777e-05, "loss": 0.4533113479614258, "step": 494840 }, { "epoch": 2.941491163935303, "grad_norm": 0.9396542310714722, "learning_rate": 2.0208520833673004e-05, "loss": 0.4421194076538086, "step": 494850 }, { "epoch": 2.9415506060119716, "grad_norm": 1.1964561939239502, "learning_rate": 2.0208097561491333e-05, "loss": 0.4752956390380859, "step": 494860 }, { "epoch": 2.94161004808864, "grad_norm": 0.9513022303581238, "learning_rate": 2.0207674718844775e-05, "loss": 0.4692839622497559, "step": 494870 }, { "epoch": 2.9416694901653084, "grad_norm": 1.2241543531417847, "learning_rate": 2.0207252305735354e-05, "loss": 0.48955731391906737, "step": 494880 }, { "epoch": 2.941728932241977, "grad_norm": 1.4588056802749634, "learning_rate": 2.0206830322165095e-05, "loss": 0.43879947662353513, "step": 494890 }, { "epoch": 2.9417883743186453, "grad_norm": 1.0953675508499146, "learning_rate": 2.020640876813601e-05, "loss": 0.4551088333129883, "step": 494900 }, { "epoch": 2.9418478163953137, "grad_norm": 1.3826904296875, "learning_rate": 2.020598764365013e-05, "loss": 0.40599822998046875, "step": 494910 }, { "epoch": 2.941907258471982, "grad_norm": 1.0319010019302368, "learning_rate": 2.0205566948709456e-05, "loss": 0.46309676170349123, "step": 494920 }, { "epoch": 2.9419667005486505, "grad_norm": 1.0709894895553589, "learning_rate": 2.0205146683316e-05, "loss": 0.5109455585479736, "step": 494930 }, { "epoch": 2.942026142625319, "grad_norm": 1.245721697807312, "learning_rate": 2.020472684747178e-05, "loss": 0.4684932231903076, "step": 494940 }, { "epoch": 2.942085584701987, "grad_norm": 1.2728056907653809, "learning_rate": 2.0204307441178806e-05, "loss": 0.49480361938476564, "step": 494950 }, { "epoch": 2.9421450267786557, "grad_norm": 1.461175799369812, "learning_rate": 2.0203888464439073e-05, "loss": 0.4439099788665771, "step": 494960 }, { "epoch": 2.9422044688553237, "grad_norm": 1.1938246488571167, "learning_rate": 2.020346991725459e-05, "loss": 0.46353950500488283, "step": 494970 }, { "epoch": 2.9422639109319926, "grad_norm": 1.0806845426559448, "learning_rate": 2.0203051799627372e-05, "loss": 0.42454843521118163, "step": 494980 }, { "epoch": 2.9423233530086605, "grad_norm": 1.394479513168335, "learning_rate": 2.0202634111559408e-05, "loss": 0.47913551330566406, "step": 494990 }, { "epoch": 2.942382795085329, "grad_norm": 1.6287505626678467, "learning_rate": 2.020221685305269e-05, "loss": 0.4773283004760742, "step": 495000 }, { "epoch": 2.9424422371619974, "grad_norm": 1.3898032903671265, "learning_rate": 2.0201800024109218e-05, "loss": 0.5375240325927735, "step": 495010 }, { "epoch": 2.942501679238666, "grad_norm": 1.3788293600082397, "learning_rate": 2.020138362473099e-05, "loss": 0.44269695281982424, "step": 495020 }, { "epoch": 2.942561121315334, "grad_norm": 1.8557544946670532, "learning_rate": 2.0200967654919995e-05, "loss": 0.4456939697265625, "step": 495030 }, { "epoch": 2.9426205633920026, "grad_norm": 1.2807962894439697, "learning_rate": 2.020055211467823e-05, "loss": 0.46820940971374514, "step": 495040 }, { "epoch": 2.942680005468671, "grad_norm": 1.4413150548934937, "learning_rate": 2.0200137004007673e-05, "loss": 0.460829496383667, "step": 495050 }, { "epoch": 2.9427394475453394, "grad_norm": 1.6220747232437134, "learning_rate": 2.019972232291032e-05, "loss": 0.45159201622009276, "step": 495060 }, { "epoch": 2.942798889622008, "grad_norm": 1.7986682653427124, "learning_rate": 2.0199308071388137e-05, "loss": 0.4569828987121582, "step": 495070 }, { "epoch": 2.9428583316986763, "grad_norm": 1.3935505151748657, "learning_rate": 2.0198894249443127e-05, "loss": 0.44097156524658204, "step": 495080 }, { "epoch": 2.9429177737753447, "grad_norm": 1.2629961967468262, "learning_rate": 2.0198480857077245e-05, "loss": 0.45376977920532224, "step": 495090 }, { "epoch": 2.942977215852013, "grad_norm": 1.3553801774978638, "learning_rate": 2.01980678942925e-05, "loss": 0.48037872314453123, "step": 495100 }, { "epoch": 2.9430366579286815, "grad_norm": 1.3600412607192993, "learning_rate": 2.0197655361090838e-05, "loss": 0.4583989143371582, "step": 495110 }, { "epoch": 2.94309610000535, "grad_norm": 1.349805235862732, "learning_rate": 2.0197243257474256e-05, "loss": 0.5166654109954834, "step": 495120 }, { "epoch": 2.9431555420820183, "grad_norm": 1.1114757061004639, "learning_rate": 2.019683158344471e-05, "loss": 0.4413337707519531, "step": 495130 }, { "epoch": 2.9432149841586863, "grad_norm": 1.0596574544906616, "learning_rate": 2.019642033900417e-05, "loss": 0.4352375030517578, "step": 495140 }, { "epoch": 2.943274426235355, "grad_norm": 1.519709825515747, "learning_rate": 2.0196009524154612e-05, "loss": 0.4809823989868164, "step": 495150 }, { "epoch": 2.943333868312023, "grad_norm": 1.0462491512298584, "learning_rate": 2.0195599138897995e-05, "loss": 0.4132349491119385, "step": 495160 }, { "epoch": 2.943393310388692, "grad_norm": 1.1571755409240723, "learning_rate": 2.0195189183236275e-05, "loss": 0.41481747627258303, "step": 495170 }, { "epoch": 2.94345275246536, "grad_norm": 1.5884826183319092, "learning_rate": 2.0194779657171438e-05, "loss": 0.4142301082611084, "step": 495180 }, { "epoch": 2.9435121945420284, "grad_norm": 1.410388708114624, "learning_rate": 2.0194370560705415e-05, "loss": 0.4596701622009277, "step": 495190 }, { "epoch": 2.943571636618697, "grad_norm": 1.5283045768737793, "learning_rate": 2.0193961893840178e-05, "loss": 0.4753390312194824, "step": 495200 }, { "epoch": 2.943631078695365, "grad_norm": 0.909611701965332, "learning_rate": 2.019355365657767e-05, "loss": 0.44301738739013674, "step": 495210 }, { "epoch": 2.9436905207720336, "grad_norm": 1.232547402381897, "learning_rate": 2.019314584891987e-05, "loss": 0.38785834312438966, "step": 495220 }, { "epoch": 2.943749962848702, "grad_norm": 1.4464924335479736, "learning_rate": 2.0192738470868696e-05, "loss": 0.4297694206237793, "step": 495230 }, { "epoch": 2.9438094049253705, "grad_norm": 1.2132099866867065, "learning_rate": 2.019233152242611e-05, "loss": 0.4376434326171875, "step": 495240 }, { "epoch": 2.943868847002039, "grad_norm": 1.5519167184829712, "learning_rate": 2.0191925003594077e-05, "loss": 0.5049435138702393, "step": 495250 }, { "epoch": 2.9439282890787073, "grad_norm": 1.159483790397644, "learning_rate": 2.0191518914374513e-05, "loss": 0.4786062717437744, "step": 495260 }, { "epoch": 2.9439877311553757, "grad_norm": 0.9742324352264404, "learning_rate": 2.0191113254769366e-05, "loss": 0.4315786361694336, "step": 495270 }, { "epoch": 2.944047173232044, "grad_norm": 1.7430756092071533, "learning_rate": 2.019070802478059e-05, "loss": 0.47442045211791994, "step": 495280 }, { "epoch": 2.9441066153087125, "grad_norm": 1.1690421104431152, "learning_rate": 2.0190303224410128e-05, "loss": 0.4156160354614258, "step": 495290 }, { "epoch": 2.944166057385381, "grad_norm": 1.3129264116287231, "learning_rate": 2.0189898853659895e-05, "loss": 0.46907787322998046, "step": 495300 }, { "epoch": 2.9442254994620494, "grad_norm": 1.2500810623168945, "learning_rate": 2.0189494912531837e-05, "loss": 0.46990246772766114, "step": 495310 }, { "epoch": 2.944284941538718, "grad_norm": 1.2050930261611938, "learning_rate": 2.0189091401027886e-05, "loss": 0.4694314479827881, "step": 495320 }, { "epoch": 2.9443443836153858, "grad_norm": 1.1573383808135986, "learning_rate": 2.0188688319149962e-05, "loss": 0.4712636947631836, "step": 495330 }, { "epoch": 2.9444038256920546, "grad_norm": 1.3043006658554077, "learning_rate": 2.0188285666900007e-05, "loss": 0.4308662414550781, "step": 495340 }, { "epoch": 2.9444632677687226, "grad_norm": 1.5182759761810303, "learning_rate": 2.018788344427995e-05, "loss": 0.4899850845336914, "step": 495350 }, { "epoch": 2.944522709845391, "grad_norm": 1.1608645915985107, "learning_rate": 2.0187481651291708e-05, "loss": 0.4387380599975586, "step": 495360 }, { "epoch": 2.9445821519220594, "grad_norm": 1.2818387746810913, "learning_rate": 2.0187080287937196e-05, "loss": 0.4481359958648682, "step": 495370 }, { "epoch": 2.944641593998728, "grad_norm": 1.0658892393112183, "learning_rate": 2.018667935421834e-05, "loss": 0.4620870590209961, "step": 495380 }, { "epoch": 2.9447010360753962, "grad_norm": 1.7750296592712402, "learning_rate": 2.0186278850137062e-05, "loss": 0.46764631271362306, "step": 495390 }, { "epoch": 2.9447604781520647, "grad_norm": 1.4118518829345703, "learning_rate": 2.0185878775695276e-05, "loss": 0.43221359252929686, "step": 495400 }, { "epoch": 2.944819920228733, "grad_norm": 1.3232142925262451, "learning_rate": 2.0185479130894892e-05, "loss": 0.45896139144897463, "step": 495410 }, { "epoch": 2.9448793623054015, "grad_norm": 1.4172800779342651, "learning_rate": 2.0185079915737823e-05, "loss": 0.4458639144897461, "step": 495420 }, { "epoch": 2.94493880438207, "grad_norm": 1.0662449598312378, "learning_rate": 2.018468113022598e-05, "loss": 0.4507343292236328, "step": 495430 }, { "epoch": 2.9449982464587383, "grad_norm": 1.3573298454284668, "learning_rate": 2.0184282774361274e-05, "loss": 0.4338430881500244, "step": 495440 }, { "epoch": 2.9450576885354067, "grad_norm": 1.3694911003112793, "learning_rate": 2.0183884848145608e-05, "loss": 0.45384950637817384, "step": 495450 }, { "epoch": 2.945117130612075, "grad_norm": 1.2476402521133423, "learning_rate": 2.018348735158088e-05, "loss": 0.4530359745025635, "step": 495460 }, { "epoch": 2.9451765726887436, "grad_norm": 1.5369465351104736, "learning_rate": 2.0183090284668992e-05, "loss": 0.4801139831542969, "step": 495470 }, { "epoch": 2.945236014765412, "grad_norm": 1.4358340501785278, "learning_rate": 2.0182693647411856e-05, "loss": 0.4601613998413086, "step": 495480 }, { "epoch": 2.9452954568420804, "grad_norm": 1.3960062265396118, "learning_rate": 2.0182297439811365e-05, "loss": 0.4385714054107666, "step": 495490 }, { "epoch": 2.9453548989187484, "grad_norm": 1.1771094799041748, "learning_rate": 2.0181901661869397e-05, "loss": 0.4485121250152588, "step": 495500 }, { "epoch": 2.945414340995417, "grad_norm": 1.2910492420196533, "learning_rate": 2.0181506313587863e-05, "loss": 0.4741845607757568, "step": 495510 }, { "epoch": 2.945473783072085, "grad_norm": 1.5748049020767212, "learning_rate": 2.0181111394968657e-05, "loss": 0.4964907169342041, "step": 495520 }, { "epoch": 2.945533225148754, "grad_norm": 1.0235812664031982, "learning_rate": 2.0180716906013656e-05, "loss": 0.39147946834564207, "step": 495530 }, { "epoch": 2.945592667225422, "grad_norm": 1.1491574048995972, "learning_rate": 2.0180322846724757e-05, "loss": 0.43517532348632815, "step": 495540 }, { "epoch": 2.9456521093020904, "grad_norm": 1.4362910985946655, "learning_rate": 2.0179929217103827e-05, "loss": 0.490206241607666, "step": 495550 }, { "epoch": 2.945711551378759, "grad_norm": 1.4648985862731934, "learning_rate": 2.017953601715277e-05, "loss": 0.4630625247955322, "step": 495560 }, { "epoch": 2.9457709934554273, "grad_norm": 1.3158626556396484, "learning_rate": 2.0179143246873457e-05, "loss": 0.454908561706543, "step": 495570 }, { "epoch": 2.9458304355320957, "grad_norm": 1.4559175968170166, "learning_rate": 2.0178750906267774e-05, "loss": 0.47396020889282225, "step": 495580 }, { "epoch": 2.945889877608764, "grad_norm": 1.2565306425094604, "learning_rate": 2.0178358995337596e-05, "loss": 0.4590141773223877, "step": 495590 }, { "epoch": 2.9459493196854325, "grad_norm": 1.3045789003372192, "learning_rate": 2.0177967514084793e-05, "loss": 0.450881290435791, "step": 495600 }, { "epoch": 2.946008761762101, "grad_norm": 1.2367126941680908, "learning_rate": 2.0177576462511227e-05, "loss": 0.4951505661010742, "step": 495610 }, { "epoch": 2.9460682038387693, "grad_norm": 1.058148741722107, "learning_rate": 2.0177185840618786e-05, "loss": 0.4461836814880371, "step": 495620 }, { "epoch": 2.9461276459154377, "grad_norm": 1.0790129899978638, "learning_rate": 2.0176795648409335e-05, "loss": 0.46105160713195803, "step": 495630 }, { "epoch": 2.946187087992106, "grad_norm": 1.1789811849594116, "learning_rate": 2.017640588588475e-05, "loss": 0.43503313064575194, "step": 495640 }, { "epoch": 2.9462465300687746, "grad_norm": 1.196977972984314, "learning_rate": 2.017601655304687e-05, "loss": 0.3828450679779053, "step": 495650 }, { "epoch": 2.946305972145443, "grad_norm": 1.530651330947876, "learning_rate": 2.0175627649897573e-05, "loss": 0.4768521308898926, "step": 495660 }, { "epoch": 2.9463654142221114, "grad_norm": 1.1945955753326416, "learning_rate": 2.0175239176438724e-05, "loss": 0.46721487045288085, "step": 495670 }, { "epoch": 2.94642485629878, "grad_norm": 1.125336766242981, "learning_rate": 2.0174851132672175e-05, "loss": 0.4514489650726318, "step": 495680 }, { "epoch": 2.946484298375448, "grad_norm": 1.8467432260513306, "learning_rate": 2.0174463518599785e-05, "loss": 0.4661494255065918, "step": 495690 }, { "epoch": 2.9465437404521166, "grad_norm": 1.2548696994781494, "learning_rate": 2.0174076334223397e-05, "loss": 0.5275328636169434, "step": 495700 }, { "epoch": 2.9466031825287846, "grad_norm": 1.235533595085144, "learning_rate": 2.0173689579544882e-05, "loss": 0.48258261680603026, "step": 495710 }, { "epoch": 2.9466626246054535, "grad_norm": 1.2360458374023438, "learning_rate": 2.0173303254566076e-05, "loss": 0.4553811550140381, "step": 495720 }, { "epoch": 2.9467220666821214, "grad_norm": 0.978776216506958, "learning_rate": 2.0172917359288833e-05, "loss": 0.4425232410430908, "step": 495730 }, { "epoch": 2.94678150875879, "grad_norm": 1.436192512512207, "learning_rate": 2.0172531893715e-05, "loss": 0.468862247467041, "step": 495740 }, { "epoch": 2.9468409508354583, "grad_norm": 1.5479462146759033, "learning_rate": 2.0172146857846412e-05, "loss": 0.49732465744018556, "step": 495750 }, { "epoch": 2.9469003929121267, "grad_norm": 1.0609437227249146, "learning_rate": 2.0171762251684925e-05, "loss": 0.47684535980224607, "step": 495760 }, { "epoch": 2.946959834988795, "grad_norm": 1.2214429378509521, "learning_rate": 2.0171378075232363e-05, "loss": 0.42520580291748045, "step": 495770 }, { "epoch": 2.9470192770654635, "grad_norm": 1.3923158645629883, "learning_rate": 2.0170994328490572e-05, "loss": 0.41759543418884276, "step": 495780 }, { "epoch": 2.947078719142132, "grad_norm": 1.2770593166351318, "learning_rate": 2.0170611011461392e-05, "loss": 0.45801534652709963, "step": 495790 }, { "epoch": 2.9471381612188003, "grad_norm": 1.6868945360183716, "learning_rate": 2.017022812414666e-05, "loss": 0.46656064987182616, "step": 495800 }, { "epoch": 2.9471976032954688, "grad_norm": 1.1637141704559326, "learning_rate": 2.0169845666548188e-05, "loss": 0.4397097587585449, "step": 495810 }, { "epoch": 2.947257045372137, "grad_norm": 1.4563480615615845, "learning_rate": 2.016946363866782e-05, "loss": 0.4802204132080078, "step": 495820 }, { "epoch": 2.9473164874488056, "grad_norm": 1.3509901762008667, "learning_rate": 2.0169082040507386e-05, "loss": 0.4619241714477539, "step": 495830 }, { "epoch": 2.947375929525474, "grad_norm": 1.4740991592407227, "learning_rate": 2.0168700872068696e-05, "loss": 0.4536159038543701, "step": 495840 }, { "epoch": 2.9474353716021424, "grad_norm": 1.2264119386672974, "learning_rate": 2.01683201333536e-05, "loss": 0.42824344635009765, "step": 495850 }, { "epoch": 2.947494813678811, "grad_norm": 1.6299771070480347, "learning_rate": 2.016793982436389e-05, "loss": 0.44080705642700196, "step": 495860 }, { "epoch": 2.9475542557554792, "grad_norm": 1.262037754058838, "learning_rate": 2.0167559945101403e-05, "loss": 0.42789511680603026, "step": 495870 }, { "epoch": 2.947613697832147, "grad_norm": 1.0770237445831299, "learning_rate": 2.016718049556795e-05, "loss": 0.4657174587249756, "step": 495880 }, { "epoch": 2.947673139908816, "grad_norm": 1.2254101037979126, "learning_rate": 2.0166801475765346e-05, "loss": 0.4551072597503662, "step": 495890 }, { "epoch": 2.947732581985484, "grad_norm": 1.0424588918685913, "learning_rate": 2.0166422885695415e-05, "loss": 0.4379530906677246, "step": 495900 }, { "epoch": 2.947792024062153, "grad_norm": 1.5580464601516724, "learning_rate": 2.0166044725359944e-05, "loss": 0.45140557289123534, "step": 495910 }, { "epoch": 2.947851466138821, "grad_norm": 1.4819886684417725, "learning_rate": 2.0165666994760768e-05, "loss": 0.4233922004699707, "step": 495920 }, { "epoch": 2.9479109082154893, "grad_norm": 1.3078213930130005, "learning_rate": 2.016528969389968e-05, "loss": 0.474320125579834, "step": 495930 }, { "epoch": 2.9479703502921577, "grad_norm": 1.3210636377334595, "learning_rate": 2.016491282277849e-05, "loss": 0.44846515655517577, "step": 495940 }, { "epoch": 2.948029792368826, "grad_norm": 1.2669074535369873, "learning_rate": 2.0164536381398992e-05, "loss": 0.4452777862548828, "step": 495950 }, { "epoch": 2.9480892344454945, "grad_norm": 1.3172093629837036, "learning_rate": 2.0164160369763007e-05, "loss": 0.42316446304321287, "step": 495960 }, { "epoch": 2.948148676522163, "grad_norm": 1.2462643384933472, "learning_rate": 2.016378478787231e-05, "loss": 0.4362480163574219, "step": 495970 }, { "epoch": 2.9482081185988314, "grad_norm": 1.1423802375793457, "learning_rate": 2.016340963572871e-05, "loss": 0.46300034523010253, "step": 495980 }, { "epoch": 2.9482675606754998, "grad_norm": 1.4146307706832886, "learning_rate": 2.0163034913333993e-05, "loss": 0.4653743267059326, "step": 495990 }, { "epoch": 2.948327002752168, "grad_norm": 3.025456428527832, "learning_rate": 2.0162660620689965e-05, "loss": 0.44820442199707033, "step": 496000 }, { "epoch": 2.9483864448288366, "grad_norm": 1.9883767366409302, "learning_rate": 2.016228675779841e-05, "loss": 0.5024559497833252, "step": 496010 }, { "epoch": 2.948445886905505, "grad_norm": 1.116413950920105, "learning_rate": 2.0161913324661118e-05, "loss": 0.4136397361755371, "step": 496020 }, { "epoch": 2.9485053289821734, "grad_norm": 1.459099292755127, "learning_rate": 2.0161540321279864e-05, "loss": 0.48018569946289064, "step": 496030 }, { "epoch": 2.948564771058842, "grad_norm": 1.3827353715896606, "learning_rate": 2.0161167747656452e-05, "loss": 0.44142489433288573, "step": 496040 }, { "epoch": 2.9486242131355103, "grad_norm": 1.2401670217514038, "learning_rate": 2.016079560379265e-05, "loss": 0.472275972366333, "step": 496050 }, { "epoch": 2.9486836552121787, "grad_norm": 1.0681205987930298, "learning_rate": 2.016042388969024e-05, "loss": 0.45111818313598634, "step": 496060 }, { "epoch": 2.9487430972888466, "grad_norm": 1.1102936267852783, "learning_rate": 2.0160052605350997e-05, "loss": 0.4257169723510742, "step": 496070 }, { "epoch": 2.9488025393655155, "grad_norm": 1.2155452966690063, "learning_rate": 2.0159681750776717e-05, "loss": 0.4606014251708984, "step": 496080 }, { "epoch": 2.9488619814421835, "grad_norm": 1.2926048040390015, "learning_rate": 2.015931132596915e-05, "loss": 0.43555750846862795, "step": 496090 }, { "epoch": 2.948921423518852, "grad_norm": 1.555891990661621, "learning_rate": 2.0158941330930074e-05, "loss": 0.5047957897186279, "step": 496100 }, { "epoch": 2.9489808655955203, "grad_norm": 1.4322988986968994, "learning_rate": 2.0158571765661265e-05, "loss": 0.43546667098999026, "step": 496110 }, { "epoch": 2.9490403076721887, "grad_norm": 1.4813159704208374, "learning_rate": 2.0158202630164484e-05, "loss": 0.4277483463287354, "step": 496120 }, { "epoch": 2.949099749748857, "grad_norm": 1.0564117431640625, "learning_rate": 2.0157833924441512e-05, "loss": 0.4255183219909668, "step": 496130 }, { "epoch": 2.9491591918255256, "grad_norm": 1.5920835733413696, "learning_rate": 2.0157465648494095e-05, "loss": 0.4415735721588135, "step": 496140 }, { "epoch": 2.949218633902194, "grad_norm": 1.3910266160964966, "learning_rate": 2.0157097802324003e-05, "loss": 0.525761890411377, "step": 496150 }, { "epoch": 2.9492780759788624, "grad_norm": 1.3612635135650635, "learning_rate": 2.0156730385932997e-05, "loss": 0.4593212127685547, "step": 496160 }, { "epoch": 2.949337518055531, "grad_norm": 1.606782078742981, "learning_rate": 2.015636339932283e-05, "loss": 0.466845178604126, "step": 496170 }, { "epoch": 2.949396960132199, "grad_norm": 1.4805418252944946, "learning_rate": 2.0155996842495257e-05, "loss": 0.4541177749633789, "step": 496180 }, { "epoch": 2.9494564022088676, "grad_norm": 1.4162789583206177, "learning_rate": 2.0155630715452033e-05, "loss": 0.45763702392578126, "step": 496190 }, { "epoch": 2.949515844285536, "grad_norm": 1.5156891345977783, "learning_rate": 2.015526501819491e-05, "loss": 0.4741551876068115, "step": 496200 }, { "epoch": 2.9495752863622045, "grad_norm": 0.8439022302627563, "learning_rate": 2.0154899750725636e-05, "loss": 0.4657160758972168, "step": 496210 }, { "epoch": 2.949634728438873, "grad_norm": 1.6069104671478271, "learning_rate": 2.015453491304597e-05, "loss": 0.44829425811767576, "step": 496220 }, { "epoch": 2.9496941705155413, "grad_norm": 1.5401099920272827, "learning_rate": 2.0154170505157635e-05, "loss": 0.4589974403381348, "step": 496230 }, { "epoch": 2.9497536125922093, "grad_norm": 0.9594605565071106, "learning_rate": 2.0153806527062392e-05, "loss": 0.4357417106628418, "step": 496240 }, { "epoch": 2.949813054668878, "grad_norm": 1.4376399517059326, "learning_rate": 2.0153442978761977e-05, "loss": 0.44456777572631834, "step": 496250 }, { "epoch": 2.949872496745546, "grad_norm": 1.503785252571106, "learning_rate": 2.015307986025813e-05, "loss": 0.500211238861084, "step": 496260 }, { "epoch": 2.949931938822215, "grad_norm": 1.185349702835083, "learning_rate": 2.0152717171552582e-05, "loss": 0.4794460296630859, "step": 496270 }, { "epoch": 2.949991380898883, "grad_norm": 1.048397183418274, "learning_rate": 2.0152354912647082e-05, "loss": 0.4705961227416992, "step": 496280 }, { "epoch": 2.9500508229755513, "grad_norm": 0.9819129705429077, "learning_rate": 2.015199308354334e-05, "loss": 0.4170095920562744, "step": 496290 }, { "epoch": 2.9501102650522197, "grad_norm": 0.8820973038673401, "learning_rate": 2.0151631684243105e-05, "loss": 0.38929760456085205, "step": 496300 }, { "epoch": 2.950169707128888, "grad_norm": 1.0458189249038696, "learning_rate": 2.01512707147481e-05, "loss": 0.49898691177368165, "step": 496310 }, { "epoch": 2.9502291492055566, "grad_norm": 1.1429802179336548, "learning_rate": 2.0150910175060068e-05, "loss": 0.44711732864379883, "step": 496320 }, { "epoch": 2.950288591282225, "grad_norm": 1.2918810844421387, "learning_rate": 2.01505500651807e-05, "loss": 0.49411535263061523, "step": 496330 }, { "epoch": 2.9503480333588934, "grad_norm": 1.3350692987442017, "learning_rate": 2.015019038511174e-05, "loss": 0.44847736358642576, "step": 496340 }, { "epoch": 2.950407475435562, "grad_norm": 1.2873573303222656, "learning_rate": 2.014983113485492e-05, "loss": 0.48847007751464844, "step": 496350 }, { "epoch": 2.9504669175122302, "grad_norm": 1.233022689819336, "learning_rate": 2.014947231441193e-05, "loss": 0.4557957649230957, "step": 496360 }, { "epoch": 2.9505263595888986, "grad_norm": 1.577680230140686, "learning_rate": 2.0149113923784506e-05, "loss": 0.4421206474304199, "step": 496370 }, { "epoch": 2.950585801665567, "grad_norm": 1.5482879877090454, "learning_rate": 2.0148755962974363e-05, "loss": 0.48387699127197265, "step": 496380 }, { "epoch": 2.9506452437422355, "grad_norm": 1.6221520900726318, "learning_rate": 2.0148398431983198e-05, "loss": 0.4292302131652832, "step": 496390 }, { "epoch": 2.950704685818904, "grad_norm": 1.0603153705596924, "learning_rate": 2.0148041330812732e-05, "loss": 0.4259174823760986, "step": 496400 }, { "epoch": 2.9507641278955723, "grad_norm": 1.3323562145233154, "learning_rate": 2.0147684659464677e-05, "loss": 0.4284073829650879, "step": 496410 }, { "epoch": 2.9508235699722407, "grad_norm": 1.3480255603790283, "learning_rate": 2.014732841794074e-05, "loss": 0.43076066970825194, "step": 496420 }, { "epoch": 2.9508830120489087, "grad_norm": 1.258788824081421, "learning_rate": 2.0146972606242604e-05, "loss": 0.4410861968994141, "step": 496430 }, { "epoch": 2.9509424541255775, "grad_norm": 1.3016687631607056, "learning_rate": 2.0146617224372002e-05, "loss": 0.42341251373291017, "step": 496440 }, { "epoch": 2.9510018962022455, "grad_norm": 1.790378212928772, "learning_rate": 2.0146262272330603e-05, "loss": 0.5306994438171386, "step": 496450 }, { "epoch": 2.9510613382789144, "grad_norm": 1.1202701330184937, "learning_rate": 2.0145907750120136e-05, "loss": 0.4604640483856201, "step": 496460 }, { "epoch": 2.9511207803555823, "grad_norm": 1.2415425777435303, "learning_rate": 2.0145553657742273e-05, "loss": 0.469282341003418, "step": 496470 }, { "epoch": 2.9511802224322508, "grad_norm": 0.9404443502426147, "learning_rate": 2.0145199995198724e-05, "loss": 0.46675763130187986, "step": 496480 }, { "epoch": 2.951239664508919, "grad_norm": 1.0865706205368042, "learning_rate": 2.014484676249116e-05, "loss": 0.4565431594848633, "step": 496490 }, { "epoch": 2.9512991065855876, "grad_norm": 0.7664284110069275, "learning_rate": 2.0144493959621303e-05, "loss": 0.4489724159240723, "step": 496500 }, { "epoch": 2.951358548662256, "grad_norm": 1.2625055313110352, "learning_rate": 2.014414158659081e-05, "loss": 0.4836165428161621, "step": 496510 }, { "epoch": 2.9514179907389244, "grad_norm": 1.2048945426940918, "learning_rate": 2.0143789643401377e-05, "loss": 0.47565498352050783, "step": 496520 }, { "epoch": 2.951477432815593, "grad_norm": 1.3943761587142944, "learning_rate": 2.0143438130054694e-05, "loss": 0.4435171127319336, "step": 496530 }, { "epoch": 2.9515368748922612, "grad_norm": 1.2183349132537842, "learning_rate": 2.0143087046552438e-05, "loss": 0.433242654800415, "step": 496540 }, { "epoch": 2.9515963169689297, "grad_norm": 1.292467474937439, "learning_rate": 2.0142736392896275e-05, "loss": 0.4916104316711426, "step": 496550 }, { "epoch": 2.951655759045598, "grad_norm": 1.2922682762145996, "learning_rate": 2.014238616908791e-05, "loss": 0.4028536319732666, "step": 496560 }, { "epoch": 2.9517152011222665, "grad_norm": 1.4406793117523193, "learning_rate": 2.0142036375129005e-05, "loss": 0.44898409843444825, "step": 496570 }, { "epoch": 2.951774643198935, "grad_norm": 1.4921334981918335, "learning_rate": 2.014168701102122e-05, "loss": 0.45513224601745605, "step": 496580 }, { "epoch": 2.9518340852756033, "grad_norm": 1.3969835042953491, "learning_rate": 2.0141338076766247e-05, "loss": 0.4069779872894287, "step": 496590 }, { "epoch": 2.9518935273522717, "grad_norm": 1.314936876296997, "learning_rate": 2.014098957236574e-05, "loss": 0.4537976264953613, "step": 496600 }, { "epoch": 2.95195296942894, "grad_norm": 1.1620744466781616, "learning_rate": 2.0140641497821382e-05, "loss": 0.43138918876647947, "step": 496610 }, { "epoch": 2.952012411505608, "grad_norm": 1.6629990339279175, "learning_rate": 2.0140293853134825e-05, "loss": 0.4488087177276611, "step": 496620 }, { "epoch": 2.952071853582277, "grad_norm": 1.5788954496383667, "learning_rate": 2.0139946638307735e-05, "loss": 0.49678730964660645, "step": 496630 }, { "epoch": 2.952131295658945, "grad_norm": 1.5714397430419922, "learning_rate": 2.0139599853341774e-05, "loss": 0.5159646034240722, "step": 496640 }, { "epoch": 2.952190737735614, "grad_norm": 1.0422335863113403, "learning_rate": 2.0139253498238593e-05, "loss": 0.4532637596130371, "step": 496650 }, { "epoch": 2.9522501798122818, "grad_norm": 1.5074559450149536, "learning_rate": 2.013890757299987e-05, "loss": 0.4832344055175781, "step": 496660 }, { "epoch": 2.95230962188895, "grad_norm": 1.440346121788025, "learning_rate": 2.013856207762724e-05, "loss": 0.4871466636657715, "step": 496670 }, { "epoch": 2.9523690639656186, "grad_norm": 1.4436640739440918, "learning_rate": 2.013821701212236e-05, "loss": 0.4306300163269043, "step": 496680 }, { "epoch": 2.952428506042287, "grad_norm": 1.197155237197876, "learning_rate": 2.013787237648688e-05, "loss": 0.4304825305938721, "step": 496690 }, { "epoch": 2.9524879481189554, "grad_norm": 0.9338637590408325, "learning_rate": 2.0137528170722457e-05, "loss": 0.4144893169403076, "step": 496700 }, { "epoch": 2.952547390195624, "grad_norm": 1.2303754091262817, "learning_rate": 2.0137184394830734e-05, "loss": 0.4483694553375244, "step": 496710 }, { "epoch": 2.9526068322722923, "grad_norm": 1.2514859437942505, "learning_rate": 2.013684104881335e-05, "loss": 0.494721508026123, "step": 496720 }, { "epoch": 2.9526662743489607, "grad_norm": 1.6395183801651, "learning_rate": 2.0136498132671943e-05, "loss": 0.4309211254119873, "step": 496730 }, { "epoch": 2.952725716425629, "grad_norm": 1.3230184316635132, "learning_rate": 2.0136155646408168e-05, "loss": 0.4459354400634766, "step": 496740 }, { "epoch": 2.9527851585022975, "grad_norm": 1.5367966890335083, "learning_rate": 2.013581359002366e-05, "loss": 0.4643287658691406, "step": 496750 }, { "epoch": 2.952844600578966, "grad_norm": 1.1364765167236328, "learning_rate": 2.0135471963520053e-05, "loss": 0.44098362922668455, "step": 496760 }, { "epoch": 2.9529040426556343, "grad_norm": 1.2881464958190918, "learning_rate": 2.0135130766898977e-05, "loss": 0.4957550048828125, "step": 496770 }, { "epoch": 2.9529634847323027, "grad_norm": 1.5172637701034546, "learning_rate": 2.0134790000162056e-05, "loss": 0.4626278877258301, "step": 496780 }, { "epoch": 2.953022926808971, "grad_norm": 1.5773221254348755, "learning_rate": 2.0134449663310948e-05, "loss": 0.44885997772216796, "step": 496790 }, { "epoch": 2.9530823688856396, "grad_norm": 1.281537652015686, "learning_rate": 2.013410975634726e-05, "loss": 0.45715789794921874, "step": 496800 }, { "epoch": 2.9531418109623075, "grad_norm": 1.2242745161056519, "learning_rate": 2.0133770279272622e-05, "loss": 0.4974861145019531, "step": 496810 }, { "epoch": 2.9532012530389764, "grad_norm": 1.355697751045227, "learning_rate": 2.013343123208865e-05, "loss": 0.4871085166931152, "step": 496820 }, { "epoch": 2.9532606951156444, "grad_norm": 1.3112963438034058, "learning_rate": 2.0133092614796988e-05, "loss": 0.47741031646728516, "step": 496830 }, { "epoch": 2.953320137192313, "grad_norm": 1.377502202987671, "learning_rate": 2.013275442739923e-05, "loss": 0.46345791816711424, "step": 496840 }, { "epoch": 2.953379579268981, "grad_norm": 1.4223192930221558, "learning_rate": 2.0132416669897014e-05, "loss": 0.42148284912109374, "step": 496850 }, { "epoch": 2.9534390213456496, "grad_norm": 1.2150237560272217, "learning_rate": 2.0132079342291942e-05, "loss": 0.4233292579650879, "step": 496860 }, { "epoch": 2.953498463422318, "grad_norm": 1.2633005380630493, "learning_rate": 2.0131742444585633e-05, "loss": 0.46323456764221194, "step": 496870 }, { "epoch": 2.9535579054989864, "grad_norm": 1.3438010215759277, "learning_rate": 2.0131405976779705e-05, "loss": 0.42517967224121095, "step": 496880 }, { "epoch": 2.953617347575655, "grad_norm": 1.7056958675384521, "learning_rate": 2.0131069938875764e-05, "loss": 0.4569713592529297, "step": 496890 }, { "epoch": 2.9536767896523233, "grad_norm": 1.4788763523101807, "learning_rate": 2.01307343308754e-05, "loss": 0.4927823066711426, "step": 496900 }, { "epoch": 2.9537362317289917, "grad_norm": 1.2461442947387695, "learning_rate": 2.013039915278025e-05, "loss": 0.4585394859313965, "step": 496910 }, { "epoch": 2.95379567380566, "grad_norm": 1.3121838569641113, "learning_rate": 2.0130064404591895e-05, "loss": 0.42183723449707033, "step": 496920 }, { "epoch": 2.9538551158823285, "grad_norm": 1.7894545793533325, "learning_rate": 2.0129730086311936e-05, "loss": 0.5034418106079102, "step": 496930 }, { "epoch": 2.953914557958997, "grad_norm": 1.4936738014221191, "learning_rate": 2.0129396197941984e-05, "loss": 0.47714643478393554, "step": 496940 }, { "epoch": 2.9539740000356653, "grad_norm": 1.026201605796814, "learning_rate": 2.0129062739483625e-05, "loss": 0.4430221080780029, "step": 496950 }, { "epoch": 2.9540334421123338, "grad_norm": 1.3322794437408447, "learning_rate": 2.0128729710938465e-05, "loss": 0.4808049201965332, "step": 496960 }, { "epoch": 2.954092884189002, "grad_norm": 1.3948416709899902, "learning_rate": 2.012839711230809e-05, "loss": 0.4781512260437012, "step": 496970 }, { "epoch": 2.95415232626567, "grad_norm": 1.0786508321762085, "learning_rate": 2.0128064943594093e-05, "loss": 0.43721590042114256, "step": 496980 }, { "epoch": 2.954211768342339, "grad_norm": 1.2622300386428833, "learning_rate": 2.0127733204798073e-05, "loss": 0.4471734523773193, "step": 496990 }, { "epoch": 2.954271210419007, "grad_norm": 1.075186014175415, "learning_rate": 2.0127401895921587e-05, "loss": 0.43418245315551757, "step": 497000 }, { "epoch": 2.954330652495676, "grad_norm": 1.3945595026016235, "learning_rate": 2.0127071016966253e-05, "loss": 0.46799526214599607, "step": 497010 }, { "epoch": 2.954390094572344, "grad_norm": 1.7771321535110474, "learning_rate": 2.0126740567933644e-05, "loss": 0.4661004066467285, "step": 497020 }, { "epoch": 2.954449536649012, "grad_norm": 1.1191481351852417, "learning_rate": 2.0126410548825327e-05, "loss": 0.4401089668273926, "step": 497030 }, { "epoch": 2.9545089787256806, "grad_norm": 1.241301417350769, "learning_rate": 2.01260809596429e-05, "loss": 0.46424245834350586, "step": 497040 }, { "epoch": 2.954568420802349, "grad_norm": 1.2917680740356445, "learning_rate": 2.0125751800387916e-05, "loss": 0.4649174213409424, "step": 497050 }, { "epoch": 2.9546278628790175, "grad_norm": 1.1225420236587524, "learning_rate": 2.0125423071061973e-05, "loss": 0.4450568199157715, "step": 497060 }, { "epoch": 2.954687304955686, "grad_norm": 1.3357902765274048, "learning_rate": 2.0125094771666637e-05, "loss": 0.5099440574645996, "step": 497070 }, { "epoch": 2.9547467470323543, "grad_norm": 1.4987640380859375, "learning_rate": 2.0124766902203477e-05, "loss": 0.4392538070678711, "step": 497080 }, { "epoch": 2.9548061891090227, "grad_norm": 0.8864993453025818, "learning_rate": 2.0124439462674055e-05, "loss": 0.45491814613342285, "step": 497090 }, { "epoch": 2.954865631185691, "grad_norm": 1.6420623064041138, "learning_rate": 2.0124112453079945e-05, "loss": 0.4704792022705078, "step": 497100 }, { "epoch": 2.9549250732623595, "grad_norm": 1.0322948694229126, "learning_rate": 2.0123785873422707e-05, "loss": 0.4588353157043457, "step": 497110 }, { "epoch": 2.954984515339028, "grad_norm": 1.4364147186279297, "learning_rate": 2.0123459723703913e-05, "loss": 0.4878234386444092, "step": 497120 }, { "epoch": 2.9550439574156964, "grad_norm": 1.1106523275375366, "learning_rate": 2.0123134003925103e-05, "loss": 0.4579314231872559, "step": 497130 }, { "epoch": 2.955103399492365, "grad_norm": 1.187617301940918, "learning_rate": 2.012280871408787e-05, "loss": 0.46916589736938474, "step": 497140 }, { "epoch": 2.955162841569033, "grad_norm": 1.3641576766967773, "learning_rate": 2.0122483854193726e-05, "loss": 0.531184196472168, "step": 497150 }, { "epoch": 2.9552222836457016, "grad_norm": 1.01898992061615, "learning_rate": 2.0122159424244258e-05, "loss": 0.44022531509399415, "step": 497160 }, { "epoch": 2.9552817257223696, "grad_norm": 1.66816246509552, "learning_rate": 2.0121835424241002e-05, "loss": 0.4939758777618408, "step": 497170 }, { "epoch": 2.9553411677990384, "grad_norm": 1.3484234809875488, "learning_rate": 2.012151185418551e-05, "loss": 0.48986148834228516, "step": 497180 }, { "epoch": 2.9554006098757064, "grad_norm": 1.4542101621627808, "learning_rate": 2.012118871407934e-05, "loss": 0.41121301651000974, "step": 497190 }, { "epoch": 2.9554600519523753, "grad_norm": 1.448328971862793, "learning_rate": 2.012086600392403e-05, "loss": 0.458217716217041, "step": 497200 }, { "epoch": 2.9555194940290432, "grad_norm": 1.7882099151611328, "learning_rate": 2.0120543723721124e-05, "loss": 0.4681382179260254, "step": 497210 }, { "epoch": 2.9555789361057117, "grad_norm": 1.3043218851089478, "learning_rate": 2.0120221873472164e-05, "loss": 0.4803603649139404, "step": 497220 }, { "epoch": 2.95563837818238, "grad_norm": 1.4620108604431152, "learning_rate": 2.0119900453178683e-05, "loss": 0.4275965690612793, "step": 497230 }, { "epoch": 2.9556978202590485, "grad_norm": 1.294623851776123, "learning_rate": 2.011957946284223e-05, "loss": 0.45620222091674806, "step": 497240 }, { "epoch": 2.955757262335717, "grad_norm": 1.402733564376831, "learning_rate": 2.011925890246433e-05, "loss": 0.49923105239868165, "step": 497250 }, { "epoch": 2.9558167044123853, "grad_norm": 1.7375569343566895, "learning_rate": 2.0118938772046535e-05, "loss": 0.46628484725952146, "step": 497260 }, { "epoch": 2.9558761464890537, "grad_norm": 1.3890044689178467, "learning_rate": 2.0118619071590347e-05, "loss": 0.5013693809509278, "step": 497270 }, { "epoch": 2.955935588565722, "grad_norm": 1.28465735912323, "learning_rate": 2.0118299801097325e-05, "loss": 0.43488430976867676, "step": 497280 }, { "epoch": 2.9559950306423906, "grad_norm": 1.1186102628707886, "learning_rate": 2.0117980960568974e-05, "loss": 0.44368505477905273, "step": 497290 }, { "epoch": 2.956054472719059, "grad_norm": 1.2217345237731934, "learning_rate": 2.011766255000684e-05, "loss": 0.428192138671875, "step": 497300 }, { "epoch": 2.9561139147957274, "grad_norm": 1.5623695850372314, "learning_rate": 2.0117344569412422e-05, "loss": 0.45269007682800294, "step": 497310 }, { "epoch": 2.956173356872396, "grad_norm": 1.325825572013855, "learning_rate": 2.0117027018787256e-05, "loss": 0.49743127822875977, "step": 497320 }, { "epoch": 2.956232798949064, "grad_norm": 0.9842247366905212, "learning_rate": 2.011670989813287e-05, "loss": 0.5021274566650391, "step": 497330 }, { "epoch": 2.9562922410257326, "grad_norm": 1.1778340339660645, "learning_rate": 2.0116393207450763e-05, "loss": 0.41054296493530273, "step": 497340 }, { "epoch": 2.956351683102401, "grad_norm": 1.4873155355453491, "learning_rate": 2.011607694674245e-05, "loss": 0.4556093215942383, "step": 497350 }, { "epoch": 2.956411125179069, "grad_norm": 1.229987621307373, "learning_rate": 2.0115761116009454e-05, "loss": 0.44902667999267576, "step": 497360 }, { "epoch": 2.956470567255738, "grad_norm": 1.2537827491760254, "learning_rate": 2.011544571525328e-05, "loss": 0.4342078685760498, "step": 497370 }, { "epoch": 2.956530009332406, "grad_norm": 0.9315333366394043, "learning_rate": 2.011513074447544e-05, "loss": 0.46393284797668455, "step": 497380 }, { "epoch": 2.9565894514090747, "grad_norm": 1.2749325037002563, "learning_rate": 2.0114816203677444e-05, "loss": 0.4462272644042969, "step": 497390 }, { "epoch": 2.9566488934857427, "grad_norm": 1.0257333517074585, "learning_rate": 2.01145020928608e-05, "loss": 0.4447686195373535, "step": 497400 }, { "epoch": 2.956708335562411, "grad_norm": 1.4138041734695435, "learning_rate": 2.0114188412026992e-05, "loss": 0.5138062477111817, "step": 497410 }, { "epoch": 2.9567677776390795, "grad_norm": 1.290496826171875, "learning_rate": 2.011387516117753e-05, "loss": 0.4486806869506836, "step": 497420 }, { "epoch": 2.956827219715748, "grad_norm": 1.3176630735397339, "learning_rate": 2.0113562340313917e-05, "loss": 0.44551858901977537, "step": 497430 }, { "epoch": 2.9568866617924163, "grad_norm": 1.2462775707244873, "learning_rate": 2.011324994943765e-05, "loss": 0.4694080352783203, "step": 497440 }, { "epoch": 2.9569461038690847, "grad_norm": 1.4786133766174316, "learning_rate": 2.0112937988550218e-05, "loss": 0.5018479347229003, "step": 497450 }, { "epoch": 2.957005545945753, "grad_norm": 1.4631202220916748, "learning_rate": 2.0112626457653107e-05, "loss": 0.4485506057739258, "step": 497460 }, { "epoch": 2.9570649880224216, "grad_norm": 1.4357426166534424, "learning_rate": 2.0112315356747833e-05, "loss": 0.4567802906036377, "step": 497470 }, { "epoch": 2.95712443009909, "grad_norm": 1.165777564048767, "learning_rate": 2.0112004685835856e-05, "loss": 0.45046253204345704, "step": 497480 }, { "epoch": 2.9571838721757584, "grad_norm": 1.230493187904358, "learning_rate": 2.0111694444918668e-05, "loss": 0.48366336822509765, "step": 497490 }, { "epoch": 2.957243314252427, "grad_norm": 1.245676040649414, "learning_rate": 2.0111384633997762e-05, "loss": 0.4520069122314453, "step": 497500 }, { "epoch": 2.9573027563290952, "grad_norm": 1.5764662027359009, "learning_rate": 2.011107525307462e-05, "loss": 0.5125460624694824, "step": 497510 }, { "epoch": 2.9573621984057636, "grad_norm": 1.5211079120635986, "learning_rate": 2.0110766302150717e-05, "loss": 0.45229349136352537, "step": 497520 }, { "epoch": 2.957421640482432, "grad_norm": 1.1564503908157349, "learning_rate": 2.011045778122753e-05, "loss": 0.4522099018096924, "step": 497530 }, { "epoch": 2.9574810825591005, "grad_norm": 1.3824965953826904, "learning_rate": 2.0110149690306536e-05, "loss": 0.4578256607055664, "step": 497540 }, { "epoch": 2.9575405246357684, "grad_norm": 1.3521910905838013, "learning_rate": 2.010984202938921e-05, "loss": 0.44431772232055666, "step": 497550 }, { "epoch": 2.9575999667124373, "grad_norm": 1.3490450382232666, "learning_rate": 2.0109534798477032e-05, "loss": 0.4121979236602783, "step": 497560 }, { "epoch": 2.9576594087891053, "grad_norm": 1.2544684410095215, "learning_rate": 2.0109227997571452e-05, "loss": 0.4132573127746582, "step": 497570 }, { "epoch": 2.9577188508657737, "grad_norm": 1.4354209899902344, "learning_rate": 2.010892162667395e-05, "loss": 0.4474945068359375, "step": 497580 }, { "epoch": 2.957778292942442, "grad_norm": 1.0232324600219727, "learning_rate": 2.0108615685785996e-05, "loss": 0.45049705505371096, "step": 497590 }, { "epoch": 2.9578377350191105, "grad_norm": 1.2772250175476074, "learning_rate": 2.0108310174909037e-05, "loss": 0.436810302734375, "step": 497600 }, { "epoch": 2.957897177095779, "grad_norm": 1.275093674659729, "learning_rate": 2.010800509404456e-05, "loss": 0.5131165504455566, "step": 497610 }, { "epoch": 2.9579566191724473, "grad_norm": 0.9853571653366089, "learning_rate": 2.0107700443193988e-05, "loss": 0.4084662437438965, "step": 497620 }, { "epoch": 2.9580160612491158, "grad_norm": 1.647124171257019, "learning_rate": 2.0107396222358816e-05, "loss": 0.4615302562713623, "step": 497630 }, { "epoch": 2.958075503325784, "grad_norm": 1.5576822757720947, "learning_rate": 2.0107092431540485e-05, "loss": 0.45198941230773926, "step": 497640 }, { "epoch": 2.9581349454024526, "grad_norm": 1.0343469381332397, "learning_rate": 2.0106789070740446e-05, "loss": 0.4609675407409668, "step": 497650 }, { "epoch": 2.958194387479121, "grad_norm": 1.6716275215148926, "learning_rate": 2.0106486139960146e-05, "loss": 0.49299964904785154, "step": 497660 }, { "epoch": 2.9582538295557894, "grad_norm": 1.2799736261367798, "learning_rate": 2.010618363920103e-05, "loss": 0.49682159423828126, "step": 497670 }, { "epoch": 2.958313271632458, "grad_norm": 1.648721694946289, "learning_rate": 2.0105881568464568e-05, "loss": 0.4031072616577148, "step": 497680 }, { "epoch": 2.9583727137091262, "grad_norm": 1.331180453300476, "learning_rate": 2.010557992775219e-05, "loss": 0.47104291915893554, "step": 497690 }, { "epoch": 2.9584321557857947, "grad_norm": 1.2042828798294067, "learning_rate": 2.010527871706534e-05, "loss": 0.4396331310272217, "step": 497700 }, { "epoch": 2.958491597862463, "grad_norm": 1.1693814992904663, "learning_rate": 2.010497793640545e-05, "loss": 0.43863964080810547, "step": 497710 }, { "epoch": 2.958551039939131, "grad_norm": 0.9456309676170349, "learning_rate": 2.0104677585773974e-05, "loss": 0.47909722328186033, "step": 497720 }, { "epoch": 2.9586104820158, "grad_norm": 1.136606216430664, "learning_rate": 2.0104377665172338e-05, "loss": 0.5014053821563721, "step": 497730 }, { "epoch": 2.958669924092468, "grad_norm": 1.035078763961792, "learning_rate": 2.0104078174601987e-05, "loss": 0.43688440322875977, "step": 497740 }, { "epoch": 2.9587293661691367, "grad_norm": 1.1776361465454102, "learning_rate": 2.010377911406434e-05, "loss": 0.4579480171203613, "step": 497750 }, { "epoch": 2.9587888082458047, "grad_norm": 1.5479099750518799, "learning_rate": 2.0103480483560837e-05, "loss": 0.43926048278808594, "step": 497760 }, { "epoch": 2.958848250322473, "grad_norm": 1.123709797859192, "learning_rate": 2.0103182283092907e-05, "loss": 0.4496432304382324, "step": 497770 }, { "epoch": 2.9589076923991415, "grad_norm": 1.3699603080749512, "learning_rate": 2.0102884512661975e-05, "loss": 0.4339767932891846, "step": 497780 }, { "epoch": 2.95896713447581, "grad_norm": 1.3473458290100098, "learning_rate": 2.0102587172269467e-05, "loss": 0.48711528778076174, "step": 497790 }, { "epoch": 2.9590265765524784, "grad_norm": 1.2402571439743042, "learning_rate": 2.0102290261916802e-05, "loss": 0.5119808673858642, "step": 497800 }, { "epoch": 2.9590860186291468, "grad_norm": 1.1030168533325195, "learning_rate": 2.01019937816054e-05, "loss": 0.4943653106689453, "step": 497810 }, { "epoch": 2.959145460705815, "grad_norm": 1.0674782991409302, "learning_rate": 2.0101697731336683e-05, "loss": 0.4090674877166748, "step": 497820 }, { "epoch": 2.9592049027824836, "grad_norm": 1.3202166557312012, "learning_rate": 2.010140211111206e-05, "loss": 0.48606128692626954, "step": 497830 }, { "epoch": 2.959264344859152, "grad_norm": 1.1254740953445435, "learning_rate": 2.0101106920932953e-05, "loss": 0.4330570220947266, "step": 497840 }, { "epoch": 2.9593237869358204, "grad_norm": 1.3935006856918335, "learning_rate": 2.010081216080077e-05, "loss": 0.4195373058319092, "step": 497850 }, { "epoch": 2.959383229012489, "grad_norm": 1.041748046875, "learning_rate": 2.0100517830716926e-05, "loss": 0.44571819305419924, "step": 497860 }, { "epoch": 2.9594426710891573, "grad_norm": 1.2965419292449951, "learning_rate": 2.0100223930682825e-05, "loss": 0.45638179779052734, "step": 497870 }, { "epoch": 2.9595021131658257, "grad_norm": 1.2583471536636353, "learning_rate": 2.009993046069987e-05, "loss": 0.4717097282409668, "step": 497880 }, { "epoch": 2.959561555242494, "grad_norm": 1.1831562519073486, "learning_rate": 2.009963742076947e-05, "loss": 0.42913193702697755, "step": 497890 }, { "epoch": 2.9596209973191625, "grad_norm": 1.4297980070114136, "learning_rate": 2.009934481089302e-05, "loss": 0.42958760261535645, "step": 497900 }, { "epoch": 2.9596804393958305, "grad_norm": 1.0479246377944946, "learning_rate": 2.0099052631071934e-05, "loss": 0.4963250160217285, "step": 497910 }, { "epoch": 2.9597398814724993, "grad_norm": 1.1816363334655762, "learning_rate": 2.0098760881307585e-05, "loss": 0.4308451175689697, "step": 497920 }, { "epoch": 2.9597993235491673, "grad_norm": 1.4858225584030151, "learning_rate": 2.0098469561601397e-05, "loss": 0.471617603302002, "step": 497930 }, { "epoch": 2.959858765625836, "grad_norm": 1.3526434898376465, "learning_rate": 2.0098178671954747e-05, "loss": 0.4536196231842041, "step": 497940 }, { "epoch": 2.959918207702504, "grad_norm": 1.2405173778533936, "learning_rate": 2.0097888212369032e-05, "loss": 0.41678757667541505, "step": 497950 }, { "epoch": 2.9599776497791725, "grad_norm": 0.928076446056366, "learning_rate": 2.0097598182845635e-05, "loss": 0.40954980850219724, "step": 497960 }, { "epoch": 2.960037091855841, "grad_norm": 1.3352690935134888, "learning_rate": 2.009730858338595e-05, "loss": 0.4614879608154297, "step": 497970 }, { "epoch": 2.9600965339325094, "grad_norm": 1.2562057971954346, "learning_rate": 2.0097019413991364e-05, "loss": 0.4343113899230957, "step": 497980 }, { "epoch": 2.960155976009178, "grad_norm": 1.5154098272323608, "learning_rate": 2.0096730674663246e-05, "loss": 0.48891315460205076, "step": 497990 }, { "epoch": 2.960215418085846, "grad_norm": 1.0211395025253296, "learning_rate": 2.0096442365403e-05, "loss": 0.44269485473632814, "step": 498000 }, { "epoch": 2.9602748601625146, "grad_norm": 1.312923789024353, "learning_rate": 2.0096154486211985e-05, "loss": 0.4578084945678711, "step": 498010 }, { "epoch": 2.960334302239183, "grad_norm": 1.1791563034057617, "learning_rate": 2.0095867037091588e-05, "loss": 0.5083919525146484, "step": 498020 }, { "epoch": 2.9603937443158514, "grad_norm": 1.4706718921661377, "learning_rate": 2.009558001804318e-05, "loss": 0.4640793800354004, "step": 498030 }, { "epoch": 2.96045318639252, "grad_norm": 0.9011083245277405, "learning_rate": 2.009529342906814e-05, "loss": 0.461683988571167, "step": 498040 }, { "epoch": 2.9605126284691883, "grad_norm": 1.5305120944976807, "learning_rate": 2.0095007270167832e-05, "loss": 0.5109901905059815, "step": 498050 }, { "epoch": 2.9605720705458567, "grad_norm": 1.2881308794021606, "learning_rate": 2.0094721541343632e-05, "loss": 0.4893303394317627, "step": 498060 }, { "epoch": 2.960631512622525, "grad_norm": 1.317518711090088, "learning_rate": 2.0094436242596904e-05, "loss": 0.462997579574585, "step": 498070 }, { "epoch": 2.9606909546991935, "grad_norm": 1.4847991466522217, "learning_rate": 2.009415137392901e-05, "loss": 0.4794208526611328, "step": 498080 }, { "epoch": 2.960750396775862, "grad_norm": 1.4397889375686646, "learning_rate": 2.0093866935341307e-05, "loss": 0.5027259826660156, "step": 498090 }, { "epoch": 2.96080983885253, "grad_norm": 1.211930751800537, "learning_rate": 2.0093582926835175e-05, "loss": 0.43319225311279297, "step": 498100 }, { "epoch": 2.9608692809291988, "grad_norm": 1.5057169198989868, "learning_rate": 2.009329934841195e-05, "loss": 0.48278169631958007, "step": 498110 }, { "epoch": 2.9609287230058667, "grad_norm": 1.0628522634506226, "learning_rate": 2.0093016200072997e-05, "loss": 0.48381919860839845, "step": 498120 }, { "epoch": 2.9609881650825356, "grad_norm": 1.546346664428711, "learning_rate": 2.0092733481819688e-05, "loss": 0.43946142196655275, "step": 498130 }, { "epoch": 2.9610476071592036, "grad_norm": 1.2158440351486206, "learning_rate": 2.0092451193653345e-05, "loss": 0.4713033676147461, "step": 498140 }, { "epoch": 2.961107049235872, "grad_norm": 1.4535006284713745, "learning_rate": 2.0092169335575337e-05, "loss": 0.48746752738952637, "step": 498150 }, { "epoch": 2.9611664913125404, "grad_norm": 1.430915355682373, "learning_rate": 2.0091887907587015e-05, "loss": 0.5082050323486328, "step": 498160 }, { "epoch": 2.961225933389209, "grad_norm": 1.193210244178772, "learning_rate": 2.0091606909689715e-05, "loss": 0.5113981246948243, "step": 498170 }, { "epoch": 2.9612853754658772, "grad_norm": 1.2729750871658325, "learning_rate": 2.0091326341884784e-05, "loss": 0.4597621917724609, "step": 498180 }, { "epoch": 2.9613448175425456, "grad_norm": 0.8749583959579468, "learning_rate": 2.0091046204173565e-05, "loss": 0.42968387603759767, "step": 498190 }, { "epoch": 2.961404259619214, "grad_norm": 1.3496416807174683, "learning_rate": 2.0090766496557396e-05, "loss": 0.43306608200073243, "step": 498200 }, { "epoch": 2.9614637016958825, "grad_norm": 1.0806468725204468, "learning_rate": 2.009048721903762e-05, "loss": 0.493012523651123, "step": 498210 }, { "epoch": 2.961523143772551, "grad_norm": 1.3542784452438354, "learning_rate": 2.0090208371615575e-05, "loss": 0.4427330017089844, "step": 498220 }, { "epoch": 2.9615825858492193, "grad_norm": 1.3619203567504883, "learning_rate": 2.008992995429259e-05, "loss": 0.43876161575317385, "step": 498230 }, { "epoch": 2.9616420279258877, "grad_norm": 0.9229750037193298, "learning_rate": 2.0089651967069985e-05, "loss": 0.4278708457946777, "step": 498240 }, { "epoch": 2.961701470002556, "grad_norm": 1.2392044067382812, "learning_rate": 2.008937440994911e-05, "loss": 0.45948114395141604, "step": 498250 }, { "epoch": 2.9617609120792245, "grad_norm": 1.077405571937561, "learning_rate": 2.0089097282931284e-05, "loss": 0.40836529731750487, "step": 498260 }, { "epoch": 2.961820354155893, "grad_norm": 1.099683403968811, "learning_rate": 2.0088820586017845e-05, "loss": 0.4418360233306885, "step": 498270 }, { "epoch": 2.9618797962325614, "grad_norm": 1.534371256828308, "learning_rate": 2.0088544319210095e-05, "loss": 0.4429590702056885, "step": 498280 }, { "epoch": 2.9619392383092293, "grad_norm": 1.295945644378662, "learning_rate": 2.0088268482509365e-05, "loss": 0.46004838943481446, "step": 498290 }, { "epoch": 2.961998680385898, "grad_norm": 1.6104044914245605, "learning_rate": 2.0087993075916973e-05, "loss": 0.47590065002441406, "step": 498300 }, { "epoch": 2.962058122462566, "grad_norm": 1.076309323310852, "learning_rate": 2.0087718099434238e-05, "loss": 0.4606324195861816, "step": 498310 }, { "epoch": 2.9621175645392346, "grad_norm": 1.3200047016143799, "learning_rate": 2.0087443553062483e-05, "loss": 0.5040481567382813, "step": 498320 }, { "epoch": 2.962177006615903, "grad_norm": 1.0071288347244263, "learning_rate": 2.008716943680301e-05, "loss": 0.4026328086853027, "step": 498330 }, { "epoch": 2.9622364486925714, "grad_norm": 1.5932905673980713, "learning_rate": 2.0086895750657134e-05, "loss": 0.4814620494842529, "step": 498340 }, { "epoch": 2.96229589076924, "grad_norm": 1.4987213611602783, "learning_rate": 2.0086622494626162e-05, "loss": 0.46757211685180666, "step": 498350 }, { "epoch": 2.9623553328459082, "grad_norm": 1.2148399353027344, "learning_rate": 2.0086349668711412e-05, "loss": 0.4324989318847656, "step": 498360 }, { "epoch": 2.9624147749225767, "grad_norm": 1.1001499891281128, "learning_rate": 2.0086077272914173e-05, "loss": 0.4695599555969238, "step": 498370 }, { "epoch": 2.962474216999245, "grad_norm": 1.1598834991455078, "learning_rate": 2.0085805307235757e-05, "loss": 0.45203423500061035, "step": 498380 }, { "epoch": 2.9625336590759135, "grad_norm": 1.442017912864685, "learning_rate": 2.0085533771677467e-05, "loss": 0.43850078582763674, "step": 498390 }, { "epoch": 2.962593101152582, "grad_norm": 1.5756397247314453, "learning_rate": 2.0085262666240607e-05, "loss": 0.4438209056854248, "step": 498400 }, { "epoch": 2.9626525432292503, "grad_norm": 2.112459659576416, "learning_rate": 2.0084991990926454e-05, "loss": 0.5111924648284912, "step": 498410 }, { "epoch": 2.9627119853059187, "grad_norm": 1.2017340660095215, "learning_rate": 2.008472174573632e-05, "loss": 0.4782089710235596, "step": 498420 }, { "epoch": 2.962771427382587, "grad_norm": 1.5053634643554688, "learning_rate": 2.0084451930671488e-05, "loss": 0.4425366401672363, "step": 498430 }, { "epoch": 2.9628308694592556, "grad_norm": 1.4537144899368286, "learning_rate": 2.0084182545733252e-05, "loss": 0.42584381103515623, "step": 498440 }, { "epoch": 2.962890311535924, "grad_norm": 1.5079975128173828, "learning_rate": 2.0083913590922908e-05, "loss": 0.4624776363372803, "step": 498450 }, { "epoch": 2.962949753612592, "grad_norm": 1.1182494163513184, "learning_rate": 2.008364506624174e-05, "loss": 0.43209190368652345, "step": 498460 }, { "epoch": 2.963009195689261, "grad_norm": 1.1495743989944458, "learning_rate": 2.008337697169102e-05, "loss": 0.46210470199584963, "step": 498470 }, { "epoch": 2.9630686377659288, "grad_norm": 1.3438318967819214, "learning_rate": 2.0083109307272042e-05, "loss": 0.4714613914489746, "step": 498480 }, { "epoch": 2.9631280798425976, "grad_norm": 1.4469244480133057, "learning_rate": 2.008284207298609e-05, "loss": 0.4066455841064453, "step": 498490 }, { "epoch": 2.9631875219192656, "grad_norm": 1.4594937562942505, "learning_rate": 2.008257526883443e-05, "loss": 0.43485398292541505, "step": 498500 }, { "epoch": 2.963246963995934, "grad_norm": 1.2952302694320679, "learning_rate": 2.0082308894818343e-05, "loss": 0.41272807121276855, "step": 498510 }, { "epoch": 2.9633064060726024, "grad_norm": 1.3263392448425293, "learning_rate": 2.0082042950939116e-05, "loss": 0.46919889450073243, "step": 498520 }, { "epoch": 2.963365848149271, "grad_norm": 1.1664708852767944, "learning_rate": 2.0081777437197992e-05, "loss": 0.439717960357666, "step": 498530 }, { "epoch": 2.9634252902259393, "grad_norm": 1.4864341020584106, "learning_rate": 2.0081512353596272e-05, "loss": 0.4804050445556641, "step": 498540 }, { "epoch": 2.9634847323026077, "grad_norm": 1.551940679550171, "learning_rate": 2.0081247700135207e-05, "loss": 0.4874431133270264, "step": 498550 }, { "epoch": 2.963544174379276, "grad_norm": 1.4323028326034546, "learning_rate": 2.0080983476816072e-05, "loss": 0.45772390365600585, "step": 498560 }, { "epoch": 2.9636036164559445, "grad_norm": 1.7933712005615234, "learning_rate": 2.008071968364012e-05, "loss": 0.40712652206420896, "step": 498570 }, { "epoch": 2.963663058532613, "grad_norm": 1.2294483184814453, "learning_rate": 2.0080456320608626e-05, "loss": 0.48576669692993163, "step": 498580 }, { "epoch": 2.9637225006092813, "grad_norm": 1.4039539098739624, "learning_rate": 2.0080193387722832e-05, "loss": 0.4144162178039551, "step": 498590 }, { "epoch": 2.9637819426859497, "grad_norm": 1.54669189453125, "learning_rate": 2.0079930884984017e-05, "loss": 0.49410381317138674, "step": 498600 }, { "epoch": 2.963841384762618, "grad_norm": 1.0161645412445068, "learning_rate": 2.007966881239342e-05, "loss": 0.4399594306945801, "step": 498610 }, { "epoch": 2.9639008268392866, "grad_norm": 1.3396811485290527, "learning_rate": 2.0079407169952304e-05, "loss": 0.47698631286621096, "step": 498620 }, { "epoch": 2.963960268915955, "grad_norm": 1.6848657131195068, "learning_rate": 2.0079145957661917e-05, "loss": 0.4779573917388916, "step": 498630 }, { "epoch": 2.9640197109926234, "grad_norm": 1.374363899230957, "learning_rate": 2.0078885175523513e-05, "loss": 0.4780400276184082, "step": 498640 }, { "epoch": 2.9640791530692914, "grad_norm": 1.3984653949737549, "learning_rate": 2.0078624823538334e-05, "loss": 0.49054765701293945, "step": 498650 }, { "epoch": 2.9641385951459602, "grad_norm": 1.2936062812805176, "learning_rate": 2.0078364901707625e-05, "loss": 0.4405363082885742, "step": 498660 }, { "epoch": 2.964198037222628, "grad_norm": 1.388384222984314, "learning_rate": 2.0078105410032635e-05, "loss": 0.4963070869445801, "step": 498670 }, { "epoch": 2.964257479299297, "grad_norm": 1.2817612886428833, "learning_rate": 2.0077846348514598e-05, "loss": 0.4308962345123291, "step": 498680 }, { "epoch": 2.964316921375965, "grad_norm": 1.3096624612808228, "learning_rate": 2.007758771715476e-05, "loss": 0.5130993843078613, "step": 498690 }, { "epoch": 2.9643763634526334, "grad_norm": 1.3940534591674805, "learning_rate": 2.007732951595435e-05, "loss": 0.48540425300598145, "step": 498700 }, { "epoch": 2.964435805529302, "grad_norm": 1.397039771080017, "learning_rate": 2.0077071744914616e-05, "loss": 0.5124770164489746, "step": 498710 }, { "epoch": 2.9644952476059703, "grad_norm": 1.4838138818740845, "learning_rate": 2.0076814404036778e-05, "loss": 0.5117694854736328, "step": 498720 }, { "epoch": 2.9645546896826387, "grad_norm": 1.461937427520752, "learning_rate": 2.0076557493322078e-05, "loss": 0.4036135673522949, "step": 498730 }, { "epoch": 2.964614131759307, "grad_norm": 1.2903748750686646, "learning_rate": 2.0076301012771728e-05, "loss": 0.44340028762817385, "step": 498740 }, { "epoch": 2.9646735738359755, "grad_norm": 1.1338772773742676, "learning_rate": 2.0076044962386982e-05, "loss": 0.4418063163757324, "step": 498750 }, { "epoch": 2.964733015912644, "grad_norm": 1.1613879203796387, "learning_rate": 2.007578934216904e-05, "loss": 0.43987016677856444, "step": 498760 }, { "epoch": 2.9647924579893123, "grad_norm": 1.0215767621994019, "learning_rate": 2.0075534152119142e-05, "loss": 0.46187400817871094, "step": 498770 }, { "epoch": 2.9648519000659808, "grad_norm": 1.4257621765136719, "learning_rate": 2.0075279392238488e-05, "loss": 0.46883597373962405, "step": 498780 }, { "epoch": 2.964911342142649, "grad_norm": 1.5620386600494385, "learning_rate": 2.0075025062528316e-05, "loss": 0.454893159866333, "step": 498790 }, { "epoch": 2.9649707842193176, "grad_norm": 1.211937427520752, "learning_rate": 2.007477116298984e-05, "loss": 0.4465169906616211, "step": 498800 }, { "epoch": 2.965030226295986, "grad_norm": 1.2936073541641235, "learning_rate": 2.0074517693624268e-05, "loss": 0.42523884773254395, "step": 498810 }, { "epoch": 2.9650896683726544, "grad_norm": 1.2652368545532227, "learning_rate": 2.0074264654432817e-05, "loss": 0.45722217559814454, "step": 498820 }, { "epoch": 2.965149110449323, "grad_norm": 1.3799517154693604, "learning_rate": 2.007401204541669e-05, "loss": 0.4509763240814209, "step": 498830 }, { "epoch": 2.965208552525991, "grad_norm": 1.725927472114563, "learning_rate": 2.007375986657711e-05, "loss": 0.4541301727294922, "step": 498840 }, { "epoch": 2.9652679946026597, "grad_norm": 1.0726009607315063, "learning_rate": 2.0073508117915272e-05, "loss": 0.41276063919067385, "step": 498850 }, { "epoch": 2.9653274366793276, "grad_norm": 1.0820963382720947, "learning_rate": 2.007325679943238e-05, "loss": 0.4560997486114502, "step": 498860 }, { "epoch": 2.9653868787559965, "grad_norm": 1.8413766622543335, "learning_rate": 2.0073005911129648e-05, "loss": 0.44780359268188474, "step": 498870 }, { "epoch": 2.9654463208326645, "grad_norm": 0.8143846392631531, "learning_rate": 2.0072755453008256e-05, "loss": 0.4518765449523926, "step": 498880 }, { "epoch": 2.965505762909333, "grad_norm": 1.337659239768982, "learning_rate": 2.007250542506941e-05, "loss": 0.4607836723327637, "step": 498890 }, { "epoch": 2.9655652049860013, "grad_norm": 1.2493623495101929, "learning_rate": 2.007225582731432e-05, "loss": 0.4503462791442871, "step": 498900 }, { "epoch": 2.9656246470626697, "grad_norm": 1.1762453317642212, "learning_rate": 2.0072006659744168e-05, "loss": 0.5042662620544434, "step": 498910 }, { "epoch": 2.965684089139338, "grad_norm": 1.2550172805786133, "learning_rate": 2.0071757922360142e-05, "loss": 0.47425079345703125, "step": 498920 }, { "epoch": 2.9657435312160065, "grad_norm": 1.3893096446990967, "learning_rate": 2.007150961516345e-05, "loss": 0.5012527942657471, "step": 498930 }, { "epoch": 2.965802973292675, "grad_norm": 1.0614278316497803, "learning_rate": 2.0071261738155246e-05, "loss": 0.4616873741149902, "step": 498940 }, { "epoch": 2.9658624153693434, "grad_norm": 1.2044508457183838, "learning_rate": 2.007101429133675e-05, "loss": 0.49072918891906736, "step": 498950 }, { "epoch": 2.9659218574460118, "grad_norm": 1.5204905271530151, "learning_rate": 2.007076727470913e-05, "loss": 0.520626449584961, "step": 498960 }, { "epoch": 2.96598129952268, "grad_norm": 1.5378657579421997, "learning_rate": 2.0070520688273577e-05, "loss": 0.44939327239990234, "step": 498970 }, { "epoch": 2.9660407415993486, "grad_norm": 1.1372684240341187, "learning_rate": 2.007027453203126e-05, "loss": 0.44461612701416015, "step": 498980 }, { "epoch": 2.966100183676017, "grad_norm": 1.4458742141723633, "learning_rate": 2.0070028805983348e-05, "loss": 0.45258541107177735, "step": 498990 }, { "epoch": 2.9661596257526854, "grad_norm": 1.6289242506027222, "learning_rate": 2.006978351013105e-05, "loss": 0.42261362075805664, "step": 499000 }, { "epoch": 2.966219067829354, "grad_norm": 1.1851140260696411, "learning_rate": 2.0069538644475496e-05, "loss": 0.43179779052734374, "step": 499010 }, { "epoch": 2.9662785099060223, "grad_norm": 1.1099302768707275, "learning_rate": 2.006929420901789e-05, "loss": 0.4726696968078613, "step": 499020 }, { "epoch": 2.9663379519826902, "grad_norm": 1.2196705341339111, "learning_rate": 2.0069050203759394e-05, "loss": 0.44792780876159666, "step": 499030 }, { "epoch": 2.966397394059359, "grad_norm": 1.4976004362106323, "learning_rate": 2.006880662870117e-05, "loss": 0.4556573867797852, "step": 499040 }, { "epoch": 2.966456836136027, "grad_norm": 1.508131742477417, "learning_rate": 2.0068563483844395e-05, "loss": 0.47108211517333987, "step": 499050 }, { "epoch": 2.9665162782126955, "grad_norm": 1.1914007663726807, "learning_rate": 2.0068320769190206e-05, "loss": 0.422960901260376, "step": 499060 }, { "epoch": 2.966575720289364, "grad_norm": 1.654591679573059, "learning_rate": 2.0068078484739786e-05, "loss": 0.4174160957336426, "step": 499070 }, { "epoch": 2.9666351623660323, "grad_norm": 1.5874385833740234, "learning_rate": 2.0067836630494287e-05, "loss": 0.46892366409301756, "step": 499080 }, { "epoch": 2.9666946044427007, "grad_norm": 1.9181362390518188, "learning_rate": 2.0067595206454866e-05, "loss": 0.4782229423522949, "step": 499090 }, { "epoch": 2.966754046519369, "grad_norm": 1.3226802349090576, "learning_rate": 2.0067354212622686e-05, "loss": 0.458071231842041, "step": 499100 }, { "epoch": 2.9668134885960376, "grad_norm": 1.665610909461975, "learning_rate": 2.0067113648998892e-05, "loss": 0.4972522735595703, "step": 499110 }, { "epoch": 2.966872930672706, "grad_norm": 1.3931838274002075, "learning_rate": 2.006687351558463e-05, "loss": 0.4786965847015381, "step": 499120 }, { "epoch": 2.9669323727493744, "grad_norm": 1.0789854526519775, "learning_rate": 2.0066633812381065e-05, "loss": 0.47157797813415525, "step": 499130 }, { "epoch": 2.966991814826043, "grad_norm": 1.4027944803237915, "learning_rate": 2.0066394539389326e-05, "loss": 0.4237251281738281, "step": 499140 }, { "epoch": 2.967051256902711, "grad_norm": 1.1109199523925781, "learning_rate": 2.006615569661056e-05, "loss": 0.5133090019226074, "step": 499150 }, { "epoch": 2.9671106989793796, "grad_norm": 1.4959746599197388, "learning_rate": 2.006591728404592e-05, "loss": 0.4638570785522461, "step": 499160 }, { "epoch": 2.967170141056048, "grad_norm": 1.3271280527114868, "learning_rate": 2.006567930169654e-05, "loss": 0.506063175201416, "step": 499170 }, { "epoch": 2.9672295831327165, "grad_norm": 1.388247013092041, "learning_rate": 2.006544174956357e-05, "loss": 0.47730331420898436, "step": 499180 }, { "epoch": 2.967289025209385, "grad_norm": 1.670056700706482, "learning_rate": 2.0065204627648114e-05, "loss": 0.48688716888427735, "step": 499190 }, { "epoch": 2.967348467286053, "grad_norm": 1.3845504522323608, "learning_rate": 2.0064967935951344e-05, "loss": 0.4590874671936035, "step": 499200 }, { "epoch": 2.9674079093627217, "grad_norm": 1.6871966123580933, "learning_rate": 2.0064731674474368e-05, "loss": 0.45214390754699707, "step": 499210 }, { "epoch": 2.9674673514393897, "grad_norm": 1.414196252822876, "learning_rate": 2.0064495843218338e-05, "loss": 0.4913652420043945, "step": 499220 }, { "epoch": 2.9675267935160585, "grad_norm": 1.123709797859192, "learning_rate": 2.0064260442184352e-05, "loss": 0.44234490394592285, "step": 499230 }, { "epoch": 2.9675862355927265, "grad_norm": 1.2494583129882812, "learning_rate": 2.0064025471373562e-05, "loss": 0.45727062225341797, "step": 499240 }, { "epoch": 2.967645677669395, "grad_norm": 1.6305692195892334, "learning_rate": 2.006379093078708e-05, "loss": 0.5117491722106934, "step": 499250 }, { "epoch": 2.9677051197460633, "grad_norm": 1.5709315538406372, "learning_rate": 2.006355682042603e-05, "loss": 0.45962204933166506, "step": 499260 }, { "epoch": 2.9677645618227317, "grad_norm": 1.4219328165054321, "learning_rate": 2.006332314029154e-05, "loss": 0.4955726623535156, "step": 499270 }, { "epoch": 2.9678240038994, "grad_norm": 1.2324856519699097, "learning_rate": 2.006308989038471e-05, "loss": 0.47786388397216795, "step": 499280 }, { "epoch": 2.9678834459760686, "grad_norm": 1.700500249862671, "learning_rate": 2.0062857070706675e-05, "loss": 0.47325658798217773, "step": 499290 }, { "epoch": 2.967942888052737, "grad_norm": 1.1281592845916748, "learning_rate": 2.006262468125853e-05, "loss": 0.4594434261322021, "step": 499300 }, { "epoch": 2.9680023301294054, "grad_norm": 1.4360365867614746, "learning_rate": 2.0062392722041406e-05, "loss": 0.48619871139526366, "step": 499310 }, { "epoch": 2.968061772206074, "grad_norm": 1.5841619968414307, "learning_rate": 2.00621611930564e-05, "loss": 0.48078055381774903, "step": 499320 }, { "epoch": 2.9681212142827422, "grad_norm": 1.2901546955108643, "learning_rate": 2.0061930094304627e-05, "loss": 0.47154712677001953, "step": 499330 }, { "epoch": 2.9681806563594106, "grad_norm": 1.2822495698928833, "learning_rate": 2.0061699425787178e-05, "loss": 0.5055878639221192, "step": 499340 }, { "epoch": 2.968240098436079, "grad_norm": 1.1884247064590454, "learning_rate": 2.006146918750517e-05, "loss": 0.4528516292572021, "step": 499350 }, { "epoch": 2.9682995405127475, "grad_norm": 1.6179254055023193, "learning_rate": 2.0061239379459705e-05, "loss": 0.4475541114807129, "step": 499360 }, { "epoch": 2.968358982589416, "grad_norm": 0.924823522567749, "learning_rate": 2.0061010001651877e-05, "loss": 0.4382600784301758, "step": 499370 }, { "epoch": 2.9684184246660843, "grad_norm": 1.5163249969482422, "learning_rate": 2.0060781054082787e-05, "loss": 0.4783614158630371, "step": 499380 }, { "epoch": 2.9684778667427523, "grad_norm": 1.182200312614441, "learning_rate": 2.0060552536753528e-05, "loss": 0.4874152183532715, "step": 499390 }, { "epoch": 2.968537308819421, "grad_norm": 1.7366979122161865, "learning_rate": 2.006032444966519e-05, "loss": 0.5187088489532471, "step": 499400 }, { "epoch": 2.968596750896089, "grad_norm": 1.360065221786499, "learning_rate": 2.0060096792818868e-05, "loss": 0.41270952224731444, "step": 499410 }, { "epoch": 2.968656192972758, "grad_norm": 1.2770463228225708, "learning_rate": 2.0059869566215653e-05, "loss": 0.3925445079803467, "step": 499420 }, { "epoch": 2.968715635049426, "grad_norm": 1.2169380187988281, "learning_rate": 2.005964276985663e-05, "loss": 0.4854437828063965, "step": 499430 }, { "epoch": 2.9687750771260943, "grad_norm": 1.18841552734375, "learning_rate": 2.0059416403742876e-05, "loss": 0.47645955085754393, "step": 499440 }, { "epoch": 2.9688345192027628, "grad_norm": 1.7064456939697266, "learning_rate": 2.005919046787548e-05, "loss": 0.4848925590515137, "step": 499450 }, { "epoch": 2.968893961279431, "grad_norm": 1.2843832969665527, "learning_rate": 2.0058964962255534e-05, "loss": 0.43121886253356934, "step": 499460 }, { "epoch": 2.9689534033560996, "grad_norm": 1.2850390672683716, "learning_rate": 2.0058739886884104e-05, "loss": 0.4374279022216797, "step": 499470 }, { "epoch": 2.969012845432768, "grad_norm": 1.1881769895553589, "learning_rate": 2.0058515241762267e-05, "loss": 0.45602617263793943, "step": 499480 }, { "epoch": 2.9690722875094364, "grad_norm": 1.6081459522247314, "learning_rate": 2.00582910268911e-05, "loss": 0.5313760757446289, "step": 499490 }, { "epoch": 2.969131729586105, "grad_norm": 1.32076895236969, "learning_rate": 2.005806724227167e-05, "loss": 0.49878926277160646, "step": 499500 }, { "epoch": 2.9691911716627732, "grad_norm": 1.2893279790878296, "learning_rate": 2.0057843887905062e-05, "loss": 0.44638309478759763, "step": 499510 }, { "epoch": 2.9692506137394417, "grad_norm": 1.6896086931228638, "learning_rate": 2.005762096379233e-05, "loss": 0.5028860092163085, "step": 499520 }, { "epoch": 2.96931005581611, "grad_norm": 1.224128246307373, "learning_rate": 2.0057398469934543e-05, "loss": 0.45766162872314453, "step": 499530 }, { "epoch": 2.9693694978927785, "grad_norm": 1.6589305400848389, "learning_rate": 2.005717640633278e-05, "loss": 0.450318717956543, "step": 499540 }, { "epoch": 2.969428939969447, "grad_norm": 0.995883047580719, "learning_rate": 2.005695477298808e-05, "loss": 0.4605973720550537, "step": 499550 }, { "epoch": 2.9694883820461153, "grad_norm": 1.3699591159820557, "learning_rate": 2.005673356990152e-05, "loss": 0.4572916030883789, "step": 499560 }, { "epoch": 2.9695478241227837, "grad_norm": 1.8662689924240112, "learning_rate": 2.0056512797074154e-05, "loss": 0.42803325653076174, "step": 499570 }, { "epoch": 2.9696072661994517, "grad_norm": 1.3397525548934937, "learning_rate": 2.0056292454507032e-05, "loss": 0.4440777778625488, "step": 499580 }, { "epoch": 2.9696667082761206, "grad_norm": 1.4633777141571045, "learning_rate": 2.0056072542201215e-05, "loss": 0.491929817199707, "step": 499590 }, { "epoch": 2.9697261503527885, "grad_norm": 1.2477902173995972, "learning_rate": 2.0055853060157757e-05, "loss": 0.45526580810546874, "step": 499600 }, { "epoch": 2.9697855924294574, "grad_norm": 1.3769139051437378, "learning_rate": 2.00556340083777e-05, "loss": 0.43665146827697754, "step": 499610 }, { "epoch": 2.9698450345061254, "grad_norm": 1.3351620435714722, "learning_rate": 2.005541538686209e-05, "loss": 0.5179888725280761, "step": 499620 }, { "epoch": 2.9699044765827938, "grad_norm": 1.3991798162460327, "learning_rate": 2.0055197195611982e-05, "loss": 0.4786829948425293, "step": 499630 }, { "epoch": 2.969963918659462, "grad_norm": 1.2050390243530273, "learning_rate": 2.0054979434628427e-05, "loss": 0.436222505569458, "step": 499640 }, { "epoch": 2.9700233607361306, "grad_norm": 1.6138756275177002, "learning_rate": 2.0054762103912446e-05, "loss": 0.467943000793457, "step": 499650 }, { "epoch": 2.970082802812799, "grad_norm": 1.2126606702804565, "learning_rate": 2.0054545203465092e-05, "loss": 0.47841243743896483, "step": 499660 }, { "epoch": 2.9701422448894674, "grad_norm": 1.2961863279342651, "learning_rate": 2.00543287332874e-05, "loss": 0.4733599662780762, "step": 499670 }, { "epoch": 2.970201686966136, "grad_norm": 1.9428424835205078, "learning_rate": 2.0054112693380396e-05, "loss": 0.48599958419799805, "step": 499680 }, { "epoch": 2.9702611290428043, "grad_norm": 1.4184859991073608, "learning_rate": 2.0053897083745127e-05, "loss": 0.43708219528198244, "step": 499690 }, { "epoch": 2.9703205711194727, "grad_norm": 1.236568570137024, "learning_rate": 2.005368190438262e-05, "loss": 0.4317753791809082, "step": 499700 }, { "epoch": 2.970380013196141, "grad_norm": 0.938812792301178, "learning_rate": 2.005346715529391e-05, "loss": 0.4571571350097656, "step": 499710 }, { "epoch": 2.9704394552728095, "grad_norm": 1.476055383682251, "learning_rate": 2.0053252836480013e-05, "loss": 0.4324537754058838, "step": 499720 }, { "epoch": 2.970498897349478, "grad_norm": 1.3594266176223755, "learning_rate": 2.005303894794196e-05, "loss": 0.42426352500915526, "step": 499730 }, { "epoch": 2.9705583394261463, "grad_norm": 1.4668841361999512, "learning_rate": 2.0052825489680772e-05, "loss": 0.4855016231536865, "step": 499740 }, { "epoch": 2.9706177815028147, "grad_norm": 1.3648488521575928, "learning_rate": 2.005261246169747e-05, "loss": 0.4685638427734375, "step": 499750 }, { "epoch": 2.970677223579483, "grad_norm": 1.1693649291992188, "learning_rate": 2.005239986399308e-05, "loss": 0.43216791152954104, "step": 499760 }, { "epoch": 2.970736665656151, "grad_norm": 1.1450966596603394, "learning_rate": 2.005218769656862e-05, "loss": 0.4789722442626953, "step": 499770 }, { "epoch": 2.97079610773282, "grad_norm": 1.3265272378921509, "learning_rate": 2.0051975959425094e-05, "loss": 0.43561973571777346, "step": 499780 }, { "epoch": 2.970855549809488, "grad_norm": 1.227872610092163, "learning_rate": 2.0051764652563515e-05, "loss": 0.4459963798522949, "step": 499790 }, { "epoch": 2.9709149918861564, "grad_norm": 1.2323020696640015, "learning_rate": 2.0051553775984895e-05, "loss": 0.4212906837463379, "step": 499800 }, { "epoch": 2.970974433962825, "grad_norm": 1.552979588508606, "learning_rate": 2.0051343329690254e-05, "loss": 0.41620516777038574, "step": 499810 }, { "epoch": 2.971033876039493, "grad_norm": 1.3626254796981812, "learning_rate": 2.0051133313680592e-05, "loss": 0.46675786972045896, "step": 499820 }, { "epoch": 2.9710933181161616, "grad_norm": 1.1868513822555542, "learning_rate": 2.0050923727956904e-05, "loss": 0.4791570663452148, "step": 499830 }, { "epoch": 2.97115276019283, "grad_norm": 1.3508580923080444, "learning_rate": 2.0050714572520204e-05, "loss": 0.5121808052062988, "step": 499840 }, { "epoch": 2.9712122022694984, "grad_norm": 1.0614627599716187, "learning_rate": 2.005050584737149e-05, "loss": 0.49956531524658204, "step": 499850 }, { "epoch": 2.971271644346167, "grad_norm": 1.740740180015564, "learning_rate": 2.005029755251177e-05, "loss": 0.4758141994476318, "step": 499860 }, { "epoch": 2.9713310864228353, "grad_norm": 1.446483850479126, "learning_rate": 2.0050089687942023e-05, "loss": 0.4977748394012451, "step": 499870 }, { "epoch": 2.9713905284995037, "grad_norm": 1.4538905620574951, "learning_rate": 2.004988225366325e-05, "loss": 0.49949188232421876, "step": 499880 }, { "epoch": 2.971449970576172, "grad_norm": 1.4781681299209595, "learning_rate": 2.0049675249676446e-05, "loss": 0.47405424118041994, "step": 499890 }, { "epoch": 2.9715094126528405, "grad_norm": 1.4313935041427612, "learning_rate": 2.0049468675982596e-05, "loss": 0.4173718452453613, "step": 499900 }, { "epoch": 2.971568854729509, "grad_norm": 1.2328115701675415, "learning_rate": 2.0049262532582696e-05, "loss": 0.5008800506591797, "step": 499910 }, { "epoch": 2.9716282968061773, "grad_norm": 1.5403255224227905, "learning_rate": 2.0049056819477726e-05, "loss": 0.45734596252441406, "step": 499920 }, { "epoch": 2.9716877388828458, "grad_norm": 1.562683343887329, "learning_rate": 2.0048851536668674e-05, "loss": 0.4494324207305908, "step": 499930 }, { "epoch": 2.9717471809595137, "grad_norm": 1.533393144607544, "learning_rate": 2.004864668415651e-05, "loss": 0.4732512950897217, "step": 499940 }, { "epoch": 2.9718066230361826, "grad_norm": 1.0133836269378662, "learning_rate": 2.0048442261942236e-05, "loss": 0.493145751953125, "step": 499950 }, { "epoch": 2.9718660651128506, "grad_norm": 1.3972328901290894, "learning_rate": 2.0048238270026815e-05, "loss": 0.49558558464050295, "step": 499960 }, { "epoch": 2.9719255071895194, "grad_norm": 1.3435354232788086, "learning_rate": 2.0048034708411223e-05, "loss": 0.47054481506347656, "step": 499970 }, { "epoch": 2.9719849492661874, "grad_norm": 1.1912498474121094, "learning_rate": 2.004783157709643e-05, "loss": 0.42804393768310545, "step": 499980 }, { "epoch": 2.972044391342856, "grad_norm": 1.2050076723098755, "learning_rate": 2.004762887608343e-05, "loss": 0.42063007354736326, "step": 499990 }, { "epoch": 2.972103833419524, "grad_norm": 0.9890337586402893, "learning_rate": 2.004742660537317e-05, "loss": 0.41370186805725095, "step": 500000 }, { "epoch": 2.9721632754961926, "grad_norm": 1.2857714891433716, "learning_rate": 2.0047224764966618e-05, "loss": 0.4610001564025879, "step": 500010 }, { "epoch": 2.972222717572861, "grad_norm": 1.6567798852920532, "learning_rate": 2.0047023354864754e-05, "loss": 0.45896329879760744, "step": 500020 }, { "epoch": 2.9722821596495295, "grad_norm": 1.3930248022079468, "learning_rate": 2.0046822375068526e-05, "loss": 0.4117025375366211, "step": 500030 }, { "epoch": 2.972341601726198, "grad_norm": 1.273227334022522, "learning_rate": 2.00466218255789e-05, "loss": 0.4768813610076904, "step": 500040 }, { "epoch": 2.9724010438028663, "grad_norm": 1.481876254081726, "learning_rate": 2.0046421706396844e-05, "loss": 0.4738468170166016, "step": 500050 }, { "epoch": 2.9724604858795347, "grad_norm": 1.446803092956543, "learning_rate": 2.004622201752332e-05, "loss": 0.4486647129058838, "step": 500060 }, { "epoch": 2.972519927956203, "grad_norm": 1.2454872131347656, "learning_rate": 2.004602275895926e-05, "loss": 0.472052001953125, "step": 500070 }, { "epoch": 2.9725793700328715, "grad_norm": 1.3326185941696167, "learning_rate": 2.004582393070563e-05, "loss": 0.4810306549072266, "step": 500080 }, { "epoch": 2.97263881210954, "grad_norm": 1.206051230430603, "learning_rate": 2.0045625532763383e-05, "loss": 0.4935971736907959, "step": 500090 }, { "epoch": 2.9726982541862084, "grad_norm": 1.3284826278686523, "learning_rate": 2.0045427565133464e-05, "loss": 0.4281277656555176, "step": 500100 }, { "epoch": 2.972757696262877, "grad_norm": 1.102304220199585, "learning_rate": 2.004523002781683e-05, "loss": 0.48186407089233396, "step": 500110 }, { "epoch": 2.972817138339545, "grad_norm": 1.394864559173584, "learning_rate": 2.004503292081441e-05, "loss": 0.4597827434539795, "step": 500120 }, { "epoch": 2.972876580416213, "grad_norm": 1.7900254726409912, "learning_rate": 2.0044836244127154e-05, "loss": 0.5089816093444824, "step": 500130 }, { "epoch": 2.972936022492882, "grad_norm": 0.9721648097038269, "learning_rate": 2.0044639997756014e-05, "loss": 0.4403367042541504, "step": 500140 }, { "epoch": 2.97299546456955, "grad_norm": 1.0119826793670654, "learning_rate": 2.004444418170191e-05, "loss": 0.4809131622314453, "step": 500150 }, { "epoch": 2.973054906646219, "grad_norm": 1.178226113319397, "learning_rate": 2.004424879596579e-05, "loss": 0.45386486053466796, "step": 500160 }, { "epoch": 2.973114348722887, "grad_norm": 1.409690499305725, "learning_rate": 2.004405384054858e-05, "loss": 0.4319149971008301, "step": 500170 }, { "epoch": 2.9731737907995552, "grad_norm": 1.7054545879364014, "learning_rate": 2.0043859315451218e-05, "loss": 0.4408857345581055, "step": 500180 }, { "epoch": 2.9732332328762237, "grad_norm": 1.7130873203277588, "learning_rate": 2.0043665220674648e-05, "loss": 0.509278678894043, "step": 500190 }, { "epoch": 2.973292674952892, "grad_norm": 1.2459429502487183, "learning_rate": 2.0043471556219776e-05, "loss": 0.43136110305786135, "step": 500200 }, { "epoch": 2.9733521170295605, "grad_norm": 1.0761332511901855, "learning_rate": 2.0043278322087542e-05, "loss": 0.4695671558380127, "step": 500210 }, { "epoch": 2.973411559106229, "grad_norm": 1.3225308656692505, "learning_rate": 2.004308551827886e-05, "loss": 0.47288904190063474, "step": 500220 }, { "epoch": 2.9734710011828973, "grad_norm": 1.2371138334274292, "learning_rate": 2.004289314479466e-05, "loss": 0.4656511306762695, "step": 500230 }, { "epoch": 2.9735304432595657, "grad_norm": 1.194252848625183, "learning_rate": 2.0042701201635864e-05, "loss": 0.408925724029541, "step": 500240 }, { "epoch": 2.973589885336234, "grad_norm": 1.1553752422332764, "learning_rate": 2.004250968880339e-05, "loss": 0.4913188457489014, "step": 500250 }, { "epoch": 2.9736493274129026, "grad_norm": 1.1598527431488037, "learning_rate": 2.0042318606298153e-05, "loss": 0.41191921234130857, "step": 500260 }, { "epoch": 2.973708769489571, "grad_norm": 1.1786290407180786, "learning_rate": 2.0042127954121056e-05, "loss": 0.4415763854980469, "step": 500270 }, { "epoch": 2.9737682115662394, "grad_norm": 1.3811285495758057, "learning_rate": 2.0041937732273024e-05, "loss": 0.4992661476135254, "step": 500280 }, { "epoch": 2.973827653642908, "grad_norm": 1.4060726165771484, "learning_rate": 2.004174794075496e-05, "loss": 0.47141332626342775, "step": 500290 }, { "epoch": 2.973887095719576, "grad_norm": 1.5812199115753174, "learning_rate": 2.0041558579567783e-05, "loss": 0.456358814239502, "step": 500300 }, { "epoch": 2.9739465377962446, "grad_norm": 1.6729708909988403, "learning_rate": 2.004136964871238e-05, "loss": 0.45098018646240234, "step": 500310 }, { "epoch": 2.9740059798729126, "grad_norm": 1.3852258920669556, "learning_rate": 2.004118114818968e-05, "loss": 0.5004890441894532, "step": 500320 }, { "epoch": 2.9740654219495815, "grad_norm": 1.1471120119094849, "learning_rate": 2.0040993078000558e-05, "loss": 0.4852792739868164, "step": 500330 }, { "epoch": 2.9741248640262494, "grad_norm": 1.4123941659927368, "learning_rate": 2.0040805438145932e-05, "loss": 0.4655506134033203, "step": 500340 }, { "epoch": 2.9741843061029183, "grad_norm": 1.2509210109710693, "learning_rate": 2.0040618228626696e-05, "loss": 0.4626439571380615, "step": 500350 }, { "epoch": 2.9742437481795863, "grad_norm": 1.2593213319778442, "learning_rate": 2.0040431449443736e-05, "loss": 0.440706205368042, "step": 500360 }, { "epoch": 2.9743031902562547, "grad_norm": 1.1545720100402832, "learning_rate": 2.004024510059796e-05, "loss": 0.42711672782897947, "step": 500370 }, { "epoch": 2.974362632332923, "grad_norm": 1.3523670434951782, "learning_rate": 2.0040059182090253e-05, "loss": 0.428879976272583, "step": 500380 }, { "epoch": 2.9744220744095915, "grad_norm": 1.2518749237060547, "learning_rate": 2.00398736939215e-05, "loss": 0.4101534843444824, "step": 500390 }, { "epoch": 2.97448151648626, "grad_norm": 1.285265564918518, "learning_rate": 2.0039688636092586e-05, "loss": 0.4838862419128418, "step": 500400 }, { "epoch": 2.9745409585629283, "grad_norm": 1.5657248497009277, "learning_rate": 2.003950400860441e-05, "loss": 0.5088154792785644, "step": 500410 }, { "epoch": 2.9746004006395967, "grad_norm": 1.251442551612854, "learning_rate": 2.0039319811457843e-05, "loss": 0.46576805114746095, "step": 500420 }, { "epoch": 2.974659842716265, "grad_norm": 1.2140616178512573, "learning_rate": 2.003913604465378e-05, "loss": 0.454421329498291, "step": 500430 }, { "epoch": 2.9747192847929336, "grad_norm": 1.5003602504730225, "learning_rate": 2.0038952708193078e-05, "loss": 0.44780645370483396, "step": 500440 }, { "epoch": 2.974778726869602, "grad_norm": 0.938338577747345, "learning_rate": 2.0038769802076633e-05, "loss": 0.42175898551940916, "step": 500450 }, { "epoch": 2.9748381689462704, "grad_norm": 1.3587156534194946, "learning_rate": 2.003858732630532e-05, "loss": 0.4502267837524414, "step": 500460 }, { "epoch": 2.974897611022939, "grad_norm": 1.1140730381011963, "learning_rate": 2.0038405280879996e-05, "loss": 0.39788496494293213, "step": 500470 }, { "epoch": 2.9749570530996072, "grad_norm": 1.6022926568984985, "learning_rate": 2.003822366580154e-05, "loss": 0.4512917518615723, "step": 500480 }, { "epoch": 2.9750164951762756, "grad_norm": 1.128912091255188, "learning_rate": 2.0038042481070833e-05, "loss": 0.46496381759643557, "step": 500490 }, { "epoch": 2.975075937252944, "grad_norm": 1.3501756191253662, "learning_rate": 2.003786172668872e-05, "loss": 0.47039308547973635, "step": 500500 }, { "epoch": 2.975135379329612, "grad_norm": 1.245749592781067, "learning_rate": 2.0037681402656083e-05, "loss": 0.46877636909484866, "step": 500510 }, { "epoch": 2.975194821406281, "grad_norm": 1.3259047269821167, "learning_rate": 2.0037501508973775e-05, "loss": 0.45850286483764646, "step": 500520 }, { "epoch": 2.975254263482949, "grad_norm": 1.2713849544525146, "learning_rate": 2.003732204564266e-05, "loss": 0.43507747650146483, "step": 500530 }, { "epoch": 2.9753137055596173, "grad_norm": 1.305405616760254, "learning_rate": 2.0037143012663596e-05, "loss": 0.5163442611694335, "step": 500540 }, { "epoch": 2.9753731476362857, "grad_norm": 1.3370712995529175, "learning_rate": 2.0036964410037438e-05, "loss": 0.47435245513916013, "step": 500550 }, { "epoch": 2.975432589712954, "grad_norm": 1.2459299564361572, "learning_rate": 2.0036786237765045e-05, "loss": 0.4548431396484375, "step": 500560 }, { "epoch": 2.9754920317896225, "grad_norm": 1.457520604133606, "learning_rate": 2.0036608495847266e-05, "loss": 0.4644339561462402, "step": 500570 }, { "epoch": 2.975551473866291, "grad_norm": 1.8336941003799438, "learning_rate": 2.0036431184284955e-05, "loss": 0.5072891235351562, "step": 500580 }, { "epoch": 2.9756109159429593, "grad_norm": 1.2949161529541016, "learning_rate": 2.0036254303078953e-05, "loss": 0.43401055335998534, "step": 500590 }, { "epoch": 2.9756703580196278, "grad_norm": 1.0873525142669678, "learning_rate": 2.003607785223011e-05, "loss": 0.4530916213989258, "step": 500600 }, { "epoch": 2.975729800096296, "grad_norm": 1.3144488334655762, "learning_rate": 2.0035901831739268e-05, "loss": 0.4443765163421631, "step": 500610 }, { "epoch": 2.9757892421729646, "grad_norm": 1.3131381273269653, "learning_rate": 2.003572624160727e-05, "loss": 0.4305558204650879, "step": 500620 }, { "epoch": 2.975848684249633, "grad_norm": 1.1207610368728638, "learning_rate": 2.0035551081834968e-05, "loss": 0.4309826850891113, "step": 500630 }, { "epoch": 2.9759081263263014, "grad_norm": 1.2430589199066162, "learning_rate": 2.0035376352423178e-05, "loss": 0.3929450273513794, "step": 500640 }, { "epoch": 2.97596756840297, "grad_norm": 1.1084333658218384, "learning_rate": 2.0035202053372745e-05, "loss": 0.48972034454345703, "step": 500650 }, { "epoch": 2.9760270104796382, "grad_norm": 1.3489291667938232, "learning_rate": 2.0035028184684506e-05, "loss": 0.49517064094543456, "step": 500660 }, { "epoch": 2.9760864525563067, "grad_norm": 1.3825126886367798, "learning_rate": 2.0034854746359298e-05, "loss": 0.47005767822265626, "step": 500670 }, { "epoch": 2.9761458946329746, "grad_norm": 1.240167498588562, "learning_rate": 2.003468173839794e-05, "loss": 0.48027725219726564, "step": 500680 }, { "epoch": 2.9762053367096435, "grad_norm": 1.7205809354782104, "learning_rate": 2.0034509160801264e-05, "loss": 0.4985527515411377, "step": 500690 }, { "epoch": 2.9762647787863115, "grad_norm": 1.475610613822937, "learning_rate": 2.0034337013570095e-05, "loss": 0.5011427402496338, "step": 500700 }, { "epoch": 2.9763242208629803, "grad_norm": 1.3147493600845337, "learning_rate": 2.003416529670526e-05, "loss": 0.4634113788604736, "step": 500710 }, { "epoch": 2.9763836629396483, "grad_norm": 1.2733532190322876, "learning_rate": 2.0033994010207576e-05, "loss": 0.3949750900268555, "step": 500720 }, { "epoch": 2.9764431050163167, "grad_norm": 1.0891015529632568, "learning_rate": 2.003382315407786e-05, "loss": 0.4417437553405762, "step": 500730 }, { "epoch": 2.976502547092985, "grad_norm": 1.1968145370483398, "learning_rate": 2.0033652728316936e-05, "loss": 0.4352889537811279, "step": 500740 }, { "epoch": 2.9765619891696535, "grad_norm": 1.326313853263855, "learning_rate": 2.0033482732925613e-05, "loss": 0.47013092041015625, "step": 500750 }, { "epoch": 2.976621431246322, "grad_norm": 1.3883835077285767, "learning_rate": 2.0033313167904708e-05, "loss": 0.4947669982910156, "step": 500760 }, { "epoch": 2.9766808733229904, "grad_norm": 1.2325202226638794, "learning_rate": 2.003314403325503e-05, "loss": 0.4626631736755371, "step": 500770 }, { "epoch": 2.9767403153996588, "grad_norm": 1.2254868745803833, "learning_rate": 2.0032975328977393e-05, "loss": 0.3846349000930786, "step": 500780 }, { "epoch": 2.976799757476327, "grad_norm": 1.0085097551345825, "learning_rate": 2.0032807055072593e-05, "loss": 0.43337531089782716, "step": 500790 }, { "epoch": 2.9768591995529956, "grad_norm": 1.5572713613510132, "learning_rate": 2.003263921154145e-05, "loss": 0.47214927673339846, "step": 500800 }, { "epoch": 2.976918641629664, "grad_norm": 1.2588087320327759, "learning_rate": 2.003247179838476e-05, "loss": 0.4423013687133789, "step": 500810 }, { "epoch": 2.9769780837063324, "grad_norm": 1.2621557712554932, "learning_rate": 2.003230481560332e-05, "loss": 0.410932731628418, "step": 500820 }, { "epoch": 2.977037525783001, "grad_norm": 1.4997665882110596, "learning_rate": 2.0032138263197933e-05, "loss": 0.4602869987487793, "step": 500830 }, { "epoch": 2.9770969678596693, "grad_norm": 1.0260157585144043, "learning_rate": 2.00319721411694e-05, "loss": 0.4330394744873047, "step": 500840 }, { "epoch": 2.9771564099363377, "grad_norm": 1.1685019731521606, "learning_rate": 2.00318064495185e-05, "loss": 0.4498033046722412, "step": 500850 }, { "epoch": 2.977215852013006, "grad_norm": 1.3513867855072021, "learning_rate": 2.003164118824604e-05, "loss": 0.5177412509918213, "step": 500860 }, { "epoch": 2.977275294089674, "grad_norm": 1.2634538412094116, "learning_rate": 2.0031476357352806e-05, "loss": 0.46571950912475585, "step": 500870 }, { "epoch": 2.977334736166343, "grad_norm": 1.0323702096939087, "learning_rate": 2.0031311956839597e-05, "loss": 0.44757466316223143, "step": 500880 }, { "epoch": 2.977394178243011, "grad_norm": 1.4949874877929688, "learning_rate": 2.0031147986707173e-05, "loss": 0.4934375286102295, "step": 500890 }, { "epoch": 2.9774536203196798, "grad_norm": 0.940326988697052, "learning_rate": 2.003098444695634e-05, "loss": 0.4031051158905029, "step": 500900 }, { "epoch": 2.9775130623963477, "grad_norm": 1.8317828178405762, "learning_rate": 2.003082133758788e-05, "loss": 0.49074435234069824, "step": 500910 }, { "epoch": 2.977572504473016, "grad_norm": 1.3408913612365723, "learning_rate": 2.003065865860257e-05, "loss": 0.43955769538879397, "step": 500920 }, { "epoch": 2.9776319465496845, "grad_norm": 1.1097266674041748, "learning_rate": 2.0030496410001185e-05, "loss": 0.44494428634643557, "step": 500930 }, { "epoch": 2.977691388626353, "grad_norm": 1.0583059787750244, "learning_rate": 2.00303345917845e-05, "loss": 0.42287378311157225, "step": 500940 }, { "epoch": 2.9777508307030214, "grad_norm": 1.3665311336517334, "learning_rate": 2.003017320395329e-05, "loss": 0.4568429946899414, "step": 500950 }, { "epoch": 2.97781027277969, "grad_norm": 1.3595702648162842, "learning_rate": 2.0030012246508335e-05, "loss": 0.4659119606018066, "step": 500960 }, { "epoch": 2.977869714856358, "grad_norm": 1.5026806592941284, "learning_rate": 2.002985171945039e-05, "loss": 0.4878350257873535, "step": 500970 }, { "epoch": 2.9779291569330266, "grad_norm": 1.3622946739196777, "learning_rate": 2.002969162278024e-05, "loss": 0.49033451080322266, "step": 500980 }, { "epoch": 2.977988599009695, "grad_norm": 1.504636287689209, "learning_rate": 2.0029531956498644e-05, "loss": 0.4644901275634766, "step": 500990 }, { "epoch": 2.9780480410863635, "grad_norm": 1.3535863161087036, "learning_rate": 2.002937272060636e-05, "loss": 0.4580532073974609, "step": 501000 }, { "epoch": 2.978107483163032, "grad_norm": 1.3520406484603882, "learning_rate": 2.0029213915104154e-05, "loss": 0.4544976711273193, "step": 501010 }, { "epoch": 2.9781669252397003, "grad_norm": 1.4318358898162842, "learning_rate": 2.0029055539992785e-05, "loss": 0.4364158630371094, "step": 501020 }, { "epoch": 2.9782263673163687, "grad_norm": 1.493929386138916, "learning_rate": 2.0028897595273013e-05, "loss": 0.4596559524536133, "step": 501030 }, { "epoch": 2.978285809393037, "grad_norm": 1.4730007648468018, "learning_rate": 2.0028740080945592e-05, "loss": 0.4268023490905762, "step": 501040 }, { "epoch": 2.9783452514697055, "grad_norm": 1.4007643461227417, "learning_rate": 2.002858299701127e-05, "loss": 0.4347386360168457, "step": 501050 }, { "epoch": 2.9784046935463735, "grad_norm": 1.544607162475586, "learning_rate": 2.0028426343470814e-05, "loss": 0.46947393417358396, "step": 501060 }, { "epoch": 2.9784641356230424, "grad_norm": 1.4612767696380615, "learning_rate": 2.0028270120324964e-05, "loss": 0.45170249938964846, "step": 501070 }, { "epoch": 2.9785235776997103, "grad_norm": 1.3709737062454224, "learning_rate": 2.002811432757446e-05, "loss": 0.4810147762298584, "step": 501080 }, { "epoch": 2.978583019776379, "grad_norm": 1.4668352603912354, "learning_rate": 2.002795896522005e-05, "loss": 0.4860832214355469, "step": 501090 }, { "epoch": 2.978642461853047, "grad_norm": 1.13826584815979, "learning_rate": 2.002780403326249e-05, "loss": 0.4395030975341797, "step": 501100 }, { "epoch": 2.9787019039297156, "grad_norm": 1.0541983842849731, "learning_rate": 2.0027649531702515e-05, "loss": 0.48497600555419923, "step": 501110 }, { "epoch": 2.978761346006384, "grad_norm": 1.5160516500473022, "learning_rate": 2.0027495460540854e-05, "loss": 0.4611045837402344, "step": 501120 }, { "epoch": 2.9788207880830524, "grad_norm": 1.1786434650421143, "learning_rate": 2.002734181977825e-05, "loss": 0.5012811660766602, "step": 501130 }, { "epoch": 2.978880230159721, "grad_norm": 1.1911275386810303, "learning_rate": 2.0027188609415446e-05, "loss": 0.4509236812591553, "step": 501140 }, { "epoch": 2.9789396722363892, "grad_norm": 1.4085773229599, "learning_rate": 2.0027035829453164e-05, "loss": 0.4649778366088867, "step": 501150 }, { "epoch": 2.9789991143130576, "grad_norm": 1.5961474180221558, "learning_rate": 2.0026883479892137e-05, "loss": 0.4414172649383545, "step": 501160 }, { "epoch": 2.979058556389726, "grad_norm": 1.4448785781860352, "learning_rate": 2.0026731560733094e-05, "loss": 0.4658055782318115, "step": 501170 }, { "epoch": 2.9791179984663945, "grad_norm": 1.213268518447876, "learning_rate": 2.0026580071976765e-05, "loss": 0.41480298042297364, "step": 501180 }, { "epoch": 2.979177440543063, "grad_norm": 1.0113238096237183, "learning_rate": 2.002642901362388e-05, "loss": 0.4495917797088623, "step": 501190 }, { "epoch": 2.9792368826197313, "grad_norm": 1.2524691820144653, "learning_rate": 2.0026278385675153e-05, "loss": 0.436860990524292, "step": 501200 }, { "epoch": 2.9792963246963997, "grad_norm": 1.3579541444778442, "learning_rate": 2.00261281881313e-05, "loss": 0.4922985553741455, "step": 501210 }, { "epoch": 2.979355766773068, "grad_norm": 1.3471333980560303, "learning_rate": 2.002597842099305e-05, "loss": 0.4374097347259521, "step": 501220 }, { "epoch": 2.9794152088497365, "grad_norm": 1.4653421640396118, "learning_rate": 2.0025829084261123e-05, "loss": 0.42832274436950685, "step": 501230 }, { "epoch": 2.979474650926405, "grad_norm": 1.3323272466659546, "learning_rate": 2.002568017793622e-05, "loss": 0.48305797576904297, "step": 501240 }, { "epoch": 2.979534093003073, "grad_norm": 0.9623265266418457, "learning_rate": 2.0025531702019048e-05, "loss": 0.4836000442504883, "step": 501250 }, { "epoch": 2.979593535079742, "grad_norm": 1.4543473720550537, "learning_rate": 2.0025383656510348e-05, "loss": 0.5068909168243408, "step": 501260 }, { "epoch": 2.9796529771564098, "grad_norm": 1.134550929069519, "learning_rate": 2.0025236041410795e-05, "loss": 0.46805486679077146, "step": 501270 }, { "epoch": 2.979712419233078, "grad_norm": 1.4572415351867676, "learning_rate": 2.002508885672111e-05, "loss": 0.4851022720336914, "step": 501280 }, { "epoch": 2.9797718613097466, "grad_norm": 1.4841275215148926, "learning_rate": 2.0024942102441998e-05, "loss": 0.49042534828186035, "step": 501290 }, { "epoch": 2.979831303386415, "grad_norm": 1.3725286722183228, "learning_rate": 2.0024795778574157e-05, "loss": 0.43050756454467776, "step": 501300 }, { "epoch": 2.9798907454630834, "grad_norm": 1.0448068380355835, "learning_rate": 2.002464988511829e-05, "loss": 0.4293302059173584, "step": 501310 }, { "epoch": 2.979950187539752, "grad_norm": 1.3930619955062866, "learning_rate": 2.00245044220751e-05, "loss": 0.4284313201904297, "step": 501320 }, { "epoch": 2.9800096296164202, "grad_norm": 1.2851338386535645, "learning_rate": 2.0024359389445273e-05, "loss": 0.44965109825134275, "step": 501330 }, { "epoch": 2.9800690716930887, "grad_norm": 1.0953989028930664, "learning_rate": 2.00242147872295e-05, "loss": 0.44121379852294923, "step": 501340 }, { "epoch": 2.980128513769757, "grad_norm": 1.1274981498718262, "learning_rate": 2.0024070615428483e-05, "loss": 0.4137399673461914, "step": 501350 }, { "epoch": 2.9801879558464255, "grad_norm": 1.1033190488815308, "learning_rate": 2.0023926874042908e-05, "loss": 0.4308375358581543, "step": 501360 }, { "epoch": 2.980247397923094, "grad_norm": 1.3461486101150513, "learning_rate": 2.002378356307346e-05, "loss": 0.47020206451416013, "step": 501370 }, { "epoch": 2.9803068399997623, "grad_norm": 1.537989854812622, "learning_rate": 2.0023640682520828e-05, "loss": 0.4579169273376465, "step": 501380 }, { "epoch": 2.9803662820764307, "grad_norm": 1.0624719858169556, "learning_rate": 2.0023498232385702e-05, "loss": 0.471269416809082, "step": 501390 }, { "epoch": 2.980425724153099, "grad_norm": 1.2230746746063232, "learning_rate": 2.0023356212668745e-05, "loss": 0.45932350158691404, "step": 501400 }, { "epoch": 2.9804851662297676, "grad_norm": 1.168553113937378, "learning_rate": 2.0023214623370648e-05, "loss": 0.42988386154174807, "step": 501410 }, { "epoch": 2.9805446083064355, "grad_norm": 1.0154551267623901, "learning_rate": 2.0023073464492093e-05, "loss": 0.42560462951660155, "step": 501420 }, { "epoch": 2.9806040503831044, "grad_norm": 1.1655974388122559, "learning_rate": 2.0022932736033757e-05, "loss": 0.4077742576599121, "step": 501430 }, { "epoch": 2.9806634924597724, "grad_norm": 1.429370641708374, "learning_rate": 2.0022792437996287e-05, "loss": 0.4668276786804199, "step": 501440 }, { "epoch": 2.980722934536441, "grad_norm": 1.0144364833831787, "learning_rate": 2.0022652570380392e-05, "loss": 0.4265900611877441, "step": 501450 }, { "epoch": 2.980782376613109, "grad_norm": 1.2692631483078003, "learning_rate": 2.0022513133186707e-05, "loss": 0.416219425201416, "step": 501460 }, { "epoch": 2.9808418186897776, "grad_norm": 1.285431981086731, "learning_rate": 2.0022374126415926e-05, "loss": 0.409246826171875, "step": 501470 }, { "epoch": 2.980901260766446, "grad_norm": 1.2931170463562012, "learning_rate": 2.0022235550068697e-05, "loss": 0.46622481346130373, "step": 501480 }, { "epoch": 2.9809607028431144, "grad_norm": 1.5652661323547363, "learning_rate": 2.0022097404145685e-05, "loss": 0.48340811729431155, "step": 501490 }, { "epoch": 2.981020144919783, "grad_norm": 1.1503815650939941, "learning_rate": 2.002195968864755e-05, "loss": 0.5006112575531005, "step": 501500 }, { "epoch": 2.9810795869964513, "grad_norm": 1.193544626235962, "learning_rate": 2.002182240357497e-05, "loss": 0.4299644470214844, "step": 501510 }, { "epoch": 2.9811390290731197, "grad_norm": 1.4135204553604126, "learning_rate": 2.0021685548928576e-05, "loss": 0.48417201042175295, "step": 501520 }, { "epoch": 2.981198471149788, "grad_norm": 1.4006890058517456, "learning_rate": 2.0021549124709032e-05, "loss": 0.47845921516418455, "step": 501530 }, { "epoch": 2.9812579132264565, "grad_norm": 1.4541884660720825, "learning_rate": 2.0021413130916996e-05, "loss": 0.4330099582672119, "step": 501540 }, { "epoch": 2.981317355303125, "grad_norm": 1.6576464176177979, "learning_rate": 2.0021277567553113e-05, "loss": 0.46389064788818357, "step": 501550 }, { "epoch": 2.9813767973797933, "grad_norm": 1.27049720287323, "learning_rate": 2.0021142434618028e-05, "loss": 0.41606950759887695, "step": 501560 }, { "epoch": 2.9814362394564617, "grad_norm": 1.0386772155761719, "learning_rate": 2.0021007732112402e-05, "loss": 0.43078861236572263, "step": 501570 }, { "epoch": 2.98149568153313, "grad_norm": 1.4976143836975098, "learning_rate": 2.002087346003686e-05, "loss": 0.49015045166015625, "step": 501580 }, { "epoch": 2.9815551236097986, "grad_norm": 1.2132461071014404, "learning_rate": 2.0020739618392053e-05, "loss": 0.48134584426879884, "step": 501590 }, { "epoch": 2.981614565686467, "grad_norm": 1.6521751880645752, "learning_rate": 2.0020606207178627e-05, "loss": 0.4688619613647461, "step": 501600 }, { "epoch": 2.981674007763135, "grad_norm": 1.3557015657424927, "learning_rate": 2.002047322639722e-05, "loss": 0.4647531509399414, "step": 501610 }, { "epoch": 2.981733449839804, "grad_norm": 1.4077955484390259, "learning_rate": 2.0020340676048456e-05, "loss": 0.460997200012207, "step": 501620 }, { "epoch": 2.981792891916472, "grad_norm": 1.4459782838821411, "learning_rate": 2.0020208556132987e-05, "loss": 0.4412792682647705, "step": 501630 }, { "epoch": 2.9818523339931406, "grad_norm": 1.037033200263977, "learning_rate": 2.0020076866651426e-05, "loss": 0.4125518321990967, "step": 501640 }, { "epoch": 2.9819117760698086, "grad_norm": 1.2110304832458496, "learning_rate": 2.001994560760441e-05, "loss": 0.48436784744262695, "step": 501650 }, { "epoch": 2.981971218146477, "grad_norm": 2.243767738342285, "learning_rate": 2.0019814778992572e-05, "loss": 0.5161520004272461, "step": 501660 }, { "epoch": 2.9820306602231454, "grad_norm": 1.2520171403884888, "learning_rate": 2.0019684380816533e-05, "loss": 0.37850868701934814, "step": 501670 }, { "epoch": 2.982090102299814, "grad_norm": 1.7077319622039795, "learning_rate": 2.0019554413076913e-05, "loss": 0.44958815574645994, "step": 501680 }, { "epoch": 2.9821495443764823, "grad_norm": 1.3062926530838013, "learning_rate": 2.001942487577435e-05, "loss": 0.46536993980407715, "step": 501690 }, { "epoch": 2.9822089864531507, "grad_norm": 1.3239691257476807, "learning_rate": 2.001929576890944e-05, "loss": 0.4442633628845215, "step": 501700 }, { "epoch": 2.982268428529819, "grad_norm": 1.1284902095794678, "learning_rate": 2.0019167092482828e-05, "loss": 0.5003068923950196, "step": 501710 }, { "epoch": 2.9823278706064875, "grad_norm": 1.1164708137512207, "learning_rate": 2.0019038846495098e-05, "loss": 0.4525632858276367, "step": 501720 }, { "epoch": 2.982387312683156, "grad_norm": 1.5733304023742676, "learning_rate": 2.001891103094689e-05, "loss": 0.4338594913482666, "step": 501730 }, { "epoch": 2.9824467547598243, "grad_norm": 1.3790251016616821, "learning_rate": 2.0018783645838803e-05, "loss": 0.45010952949523925, "step": 501740 }, { "epoch": 2.9825061968364928, "grad_norm": 1.238989233970642, "learning_rate": 2.001865669117145e-05, "loss": 0.45069074630737305, "step": 501750 }, { "epoch": 2.982565638913161, "grad_norm": 1.2263132333755493, "learning_rate": 2.0018530166945434e-05, "loss": 0.456303071975708, "step": 501760 }, { "epoch": 2.9826250809898296, "grad_norm": 1.335774540901184, "learning_rate": 2.0018404073161372e-05, "loss": 0.4945680141448975, "step": 501770 }, { "epoch": 2.982684523066498, "grad_norm": 1.3285835981369019, "learning_rate": 2.001827840981985e-05, "loss": 0.4513093948364258, "step": 501780 }, { "epoch": 2.9827439651431664, "grad_norm": 1.4150733947753906, "learning_rate": 2.0018153176921478e-05, "loss": 0.4088163375854492, "step": 501790 }, { "epoch": 2.9828034072198344, "grad_norm": 1.2942475080490112, "learning_rate": 2.0018028374466856e-05, "loss": 0.4217498779296875, "step": 501800 }, { "epoch": 2.9828628492965032, "grad_norm": 1.3895823955535889, "learning_rate": 2.0017904002456586e-05, "loss": 0.46782522201538085, "step": 501810 }, { "epoch": 2.982922291373171, "grad_norm": 1.5070586204528809, "learning_rate": 2.0017780060891246e-05, "loss": 0.49387669563293457, "step": 501820 }, { "epoch": 2.98298173344984, "grad_norm": 1.4925137758255005, "learning_rate": 2.0017656549771443e-05, "loss": 0.4127145767211914, "step": 501830 }, { "epoch": 2.983041175526508, "grad_norm": 1.462114930152893, "learning_rate": 2.0017533469097773e-05, "loss": 0.4573351860046387, "step": 501840 }, { "epoch": 2.9831006176031765, "grad_norm": 1.4442700147628784, "learning_rate": 2.0017410818870806e-05, "loss": 0.4990409851074219, "step": 501850 }, { "epoch": 2.983160059679845, "grad_norm": 1.5386126041412354, "learning_rate": 2.001728859909115e-05, "loss": 0.4811370849609375, "step": 501860 }, { "epoch": 2.9832195017565133, "grad_norm": 1.3562040328979492, "learning_rate": 2.001716680975937e-05, "loss": 0.46044673919677737, "step": 501870 }, { "epoch": 2.9832789438331817, "grad_norm": 1.8284467458724976, "learning_rate": 2.0017045450876056e-05, "loss": 0.4760449409484863, "step": 501880 }, { "epoch": 2.98333838590985, "grad_norm": 1.2687180042266846, "learning_rate": 2.001692452244179e-05, "loss": 0.4350987434387207, "step": 501890 }, { "epoch": 2.9833978279865185, "grad_norm": 1.6466784477233887, "learning_rate": 2.0016804024457157e-05, "loss": 0.4577822685241699, "step": 501900 }, { "epoch": 2.983457270063187, "grad_norm": 1.5931072235107422, "learning_rate": 2.0016683956922724e-05, "loss": 0.4963984966278076, "step": 501910 }, { "epoch": 2.9835167121398554, "grad_norm": 1.4663077592849731, "learning_rate": 2.0016564319839064e-05, "loss": 0.5155320167541504, "step": 501920 }, { "epoch": 2.983576154216524, "grad_norm": 1.0365673303604126, "learning_rate": 2.001644511320676e-05, "loss": 0.41761441230773927, "step": 501930 }, { "epoch": 2.983635596293192, "grad_norm": 1.1000640392303467, "learning_rate": 2.001632633702637e-05, "loss": 0.44395761489868163, "step": 501940 }, { "epoch": 2.9836950383698606, "grad_norm": 0.9412174820899963, "learning_rate": 2.0016207991298473e-05, "loss": 0.45541772842407224, "step": 501950 }, { "epoch": 2.983754480446529, "grad_norm": 1.3294860124588013, "learning_rate": 2.001609007602363e-05, "loss": 0.4741374015808105, "step": 501960 }, { "epoch": 2.983813922523197, "grad_norm": 1.2909126281738281, "learning_rate": 2.0015972591202396e-05, "loss": 0.48276281356811523, "step": 501970 }, { "epoch": 2.983873364599866, "grad_norm": 1.2029975652694702, "learning_rate": 2.0015855536835346e-05, "loss": 0.45230755805969236, "step": 501980 }, { "epoch": 2.983932806676534, "grad_norm": 1.3191131353378296, "learning_rate": 2.0015738912923037e-05, "loss": 0.4776113033294678, "step": 501990 }, { "epoch": 2.9839922487532027, "grad_norm": 1.1986165046691895, "learning_rate": 2.0015622719466023e-05, "loss": 0.46378240585327146, "step": 502000 }, { "epoch": 2.9840516908298707, "grad_norm": 1.1871562004089355, "learning_rate": 2.001550695646487e-05, "loss": 0.4258233070373535, "step": 502010 }, { "epoch": 2.984111132906539, "grad_norm": 1.5332157611846924, "learning_rate": 2.0015391623920126e-05, "loss": 0.4417888641357422, "step": 502020 }, { "epoch": 2.9841705749832075, "grad_norm": 0.9728146195411682, "learning_rate": 2.001527672183233e-05, "loss": 0.4318181037902832, "step": 502030 }, { "epoch": 2.984230017059876, "grad_norm": 1.5683107376098633, "learning_rate": 2.0015162250202044e-05, "loss": 0.4594841003417969, "step": 502040 }, { "epoch": 2.9842894591365443, "grad_norm": 1.6017931699752808, "learning_rate": 2.0015048209029817e-05, "loss": 0.4724163055419922, "step": 502050 }, { "epoch": 2.9843489012132127, "grad_norm": 1.2939717769622803, "learning_rate": 2.00149345983162e-05, "loss": 0.4740837574005127, "step": 502060 }, { "epoch": 2.984408343289881, "grad_norm": 1.3797242641448975, "learning_rate": 2.0014821418061725e-05, "loss": 0.46006269454956056, "step": 502070 }, { "epoch": 2.9844677853665496, "grad_norm": 1.2474710941314697, "learning_rate": 2.0014708668266934e-05, "loss": 0.41901612281799316, "step": 502080 }, { "epoch": 2.984527227443218, "grad_norm": 1.23933744430542, "learning_rate": 2.001459634893237e-05, "loss": 0.49101104736328127, "step": 502090 }, { "epoch": 2.9845866695198864, "grad_norm": 1.201775074005127, "learning_rate": 2.0014484460058565e-05, "loss": 0.46745877265930175, "step": 502100 }, { "epoch": 2.984646111596555, "grad_norm": 1.1021113395690918, "learning_rate": 2.0014373001646065e-05, "loss": 0.40632071495056155, "step": 502110 }, { "epoch": 2.984705553673223, "grad_norm": 1.3798623085021973, "learning_rate": 2.001426197369539e-05, "loss": 0.4254453659057617, "step": 502120 }, { "epoch": 2.9847649957498916, "grad_norm": 1.2845689058303833, "learning_rate": 2.0014151376207083e-05, "loss": 0.47306241989135744, "step": 502130 }, { "epoch": 2.98482443782656, "grad_norm": 1.8406641483306885, "learning_rate": 2.001404120918167e-05, "loss": 0.4442462921142578, "step": 502140 }, { "epoch": 2.9848838799032285, "grad_norm": 1.6558418273925781, "learning_rate": 2.0013931472619675e-05, "loss": 0.48081607818603517, "step": 502150 }, { "epoch": 2.9849433219798964, "grad_norm": 1.3321216106414795, "learning_rate": 2.001382216652162e-05, "loss": 0.4130067825317383, "step": 502160 }, { "epoch": 2.9850027640565653, "grad_norm": 1.19208562374115, "learning_rate": 2.001371329088804e-05, "loss": 0.4770184516906738, "step": 502170 }, { "epoch": 2.9850622061332333, "grad_norm": 1.2862350940704346, "learning_rate": 2.0013604845719435e-05, "loss": 0.416688060760498, "step": 502180 }, { "epoch": 2.985121648209902, "grad_norm": 1.263829231262207, "learning_rate": 2.0013496831016354e-05, "loss": 0.46834349632263184, "step": 502190 }, { "epoch": 2.98518109028657, "grad_norm": 1.1203449964523315, "learning_rate": 2.0013389246779285e-05, "loss": 0.4358473777770996, "step": 502200 }, { "epoch": 2.9852405323632385, "grad_norm": 1.2695766687393188, "learning_rate": 2.0013282093008752e-05, "loss": 0.4672269821166992, "step": 502210 }, { "epoch": 2.985299974439907, "grad_norm": 1.0513840913772583, "learning_rate": 2.0013175369705275e-05, "loss": 0.43401079177856444, "step": 502220 }, { "epoch": 2.9853594165165753, "grad_norm": 1.4754525423049927, "learning_rate": 2.001306907686935e-05, "loss": 0.4488847255706787, "step": 502230 }, { "epoch": 2.9854188585932437, "grad_norm": 0.8434231877326965, "learning_rate": 2.001296321450151e-05, "loss": 0.40797104835510256, "step": 502240 }, { "epoch": 2.985478300669912, "grad_norm": 1.0074632167816162, "learning_rate": 2.001285778260224e-05, "loss": 0.45699357986450195, "step": 502250 }, { "epoch": 2.9855377427465806, "grad_norm": 0.8989769220352173, "learning_rate": 2.001275278117204e-05, "loss": 0.4688591957092285, "step": 502260 }, { "epoch": 2.985597184823249, "grad_norm": 1.40984308719635, "learning_rate": 2.0012648210211436e-05, "loss": 0.44150638580322266, "step": 502270 }, { "epoch": 2.9856566268999174, "grad_norm": 1.1431117057800293, "learning_rate": 2.0012544069720907e-05, "loss": 0.39011831283569337, "step": 502280 }, { "epoch": 2.985716068976586, "grad_norm": 1.3203283548355103, "learning_rate": 2.0012440359700955e-05, "loss": 0.4560398578643799, "step": 502290 }, { "epoch": 2.9857755110532542, "grad_norm": 1.345577597618103, "learning_rate": 2.001233708015209e-05, "loss": 0.45954256057739257, "step": 502300 }, { "epoch": 2.9858349531299226, "grad_norm": 1.5868295431137085, "learning_rate": 2.0012234231074797e-05, "loss": 0.48746414184570314, "step": 502310 }, { "epoch": 2.985894395206591, "grad_norm": 1.8737605810165405, "learning_rate": 2.001213181246956e-05, "loss": 0.5001786231994629, "step": 502320 }, { "epoch": 2.9859538372832595, "grad_norm": 1.2335898876190186, "learning_rate": 2.001202982433687e-05, "loss": 0.4921300411224365, "step": 502330 }, { "epoch": 2.986013279359928, "grad_norm": 1.3864998817443848, "learning_rate": 2.0011928266677238e-05, "loss": 0.39845824241638184, "step": 502340 }, { "epoch": 2.986072721436596, "grad_norm": 1.410475254058838, "learning_rate": 2.0011827139491125e-05, "loss": 0.427518367767334, "step": 502350 }, { "epoch": 2.9861321635132647, "grad_norm": 1.397855281829834, "learning_rate": 2.0011726442779017e-05, "loss": 0.4787732124328613, "step": 502360 }, { "epoch": 2.9861916055899327, "grad_norm": 1.3032457828521729, "learning_rate": 2.0011626176541403e-05, "loss": 0.4058089256286621, "step": 502370 }, { "epoch": 2.9862510476666015, "grad_norm": 1.2705994844436646, "learning_rate": 2.0011526340778767e-05, "loss": 0.44970245361328126, "step": 502380 }, { "epoch": 2.9863104897432695, "grad_norm": 1.6925323009490967, "learning_rate": 2.0011426935491573e-05, "loss": 0.49136600494384763, "step": 502390 }, { "epoch": 2.986369931819938, "grad_norm": 0.846678614616394, "learning_rate": 2.0011327960680306e-05, "loss": 0.4268453598022461, "step": 502400 }, { "epoch": 2.9864293738966063, "grad_norm": 1.1518884897232056, "learning_rate": 2.0011229416345444e-05, "loss": 0.4698930740356445, "step": 502410 }, { "epoch": 2.9864888159732748, "grad_norm": 0.9787378907203674, "learning_rate": 2.0011131302487446e-05, "loss": 0.4569993495941162, "step": 502420 }, { "epoch": 2.986548258049943, "grad_norm": 1.5102176666259766, "learning_rate": 2.0011033619106792e-05, "loss": 0.45099821090698244, "step": 502430 }, { "epoch": 2.9866077001266116, "grad_norm": 1.4174535274505615, "learning_rate": 2.001093636620394e-05, "loss": 0.43070240020751954, "step": 502440 }, { "epoch": 2.98666714220328, "grad_norm": 1.1269071102142334, "learning_rate": 2.001083954377935e-05, "loss": 0.5000664234161377, "step": 502450 }, { "epoch": 2.9867265842799484, "grad_norm": 1.042536735534668, "learning_rate": 2.0010743151833508e-05, "loss": 0.45960121154785155, "step": 502460 }, { "epoch": 2.986786026356617, "grad_norm": 1.2322819232940674, "learning_rate": 2.0010647190366867e-05, "loss": 0.4503476142883301, "step": 502470 }, { "epoch": 2.9868454684332852, "grad_norm": 1.415971040725708, "learning_rate": 2.0010551659379866e-05, "loss": 0.45461397171020507, "step": 502480 }, { "epoch": 2.9869049105099537, "grad_norm": 1.3096833229064941, "learning_rate": 2.0010456558872986e-05, "loss": 0.5010645866394043, "step": 502490 }, { "epoch": 2.986964352586622, "grad_norm": 1.1133298873901367, "learning_rate": 2.0010361888846675e-05, "loss": 0.4408561229705811, "step": 502500 }, { "epoch": 2.9870237946632905, "grad_norm": 1.4884114265441895, "learning_rate": 2.001026764930138e-05, "loss": 0.513556957244873, "step": 502510 }, { "epoch": 2.987083236739959, "grad_norm": 1.3860877752304077, "learning_rate": 2.0010173840237554e-05, "loss": 0.437468957901001, "step": 502520 }, { "epoch": 2.9871426788166273, "grad_norm": 1.301477074623108, "learning_rate": 2.0010080461655645e-05, "loss": 0.49310455322265623, "step": 502530 }, { "epoch": 2.9872021208932953, "grad_norm": 1.7369191646575928, "learning_rate": 2.0009987513556107e-05, "loss": 0.48118042945861816, "step": 502540 }, { "epoch": 2.987261562969964, "grad_norm": 1.0970046520233154, "learning_rate": 2.000989499593938e-05, "loss": 0.4719382762908936, "step": 502550 }, { "epoch": 2.987321005046632, "grad_norm": 1.089809536933899, "learning_rate": 2.0009802908805903e-05, "loss": 0.4741035461425781, "step": 502560 }, { "epoch": 2.987380447123301, "grad_norm": 1.2401928901672363, "learning_rate": 2.000971125215612e-05, "loss": 0.4301036834716797, "step": 502570 }, { "epoch": 2.987439889199969, "grad_norm": 1.4957410097122192, "learning_rate": 2.000962002599047e-05, "loss": 0.4684952735900879, "step": 502580 }, { "epoch": 2.9874993312766374, "grad_norm": 1.1568747758865356, "learning_rate": 2.0009529230309388e-05, "loss": 0.46741399765014646, "step": 502590 }, { "epoch": 2.9875587733533058, "grad_norm": 1.5367904901504517, "learning_rate": 2.0009438865113312e-05, "loss": 0.45386953353881837, "step": 502600 }, { "epoch": 2.987618215429974, "grad_norm": 1.3258253335952759, "learning_rate": 2.0009348930402673e-05, "loss": 0.4273850440979004, "step": 502610 }, { "epoch": 2.9876776575066426, "grad_norm": 1.6048997640609741, "learning_rate": 2.000925942617789e-05, "loss": 0.42790651321411133, "step": 502620 }, { "epoch": 2.987737099583311, "grad_norm": 1.5817899703979492, "learning_rate": 2.0009170352439404e-05, "loss": 0.5112903594970704, "step": 502630 }, { "epoch": 2.9877965416599794, "grad_norm": 1.0611554384231567, "learning_rate": 2.0009081709187645e-05, "loss": 0.45037145614624025, "step": 502640 }, { "epoch": 2.987855983736648, "grad_norm": 1.3549468517303467, "learning_rate": 2.0008993496423024e-05, "loss": 0.44852261543273925, "step": 502650 }, { "epoch": 2.9879154258133163, "grad_norm": 1.2255750894546509, "learning_rate": 2.0008905714145968e-05, "loss": 0.4448084831237793, "step": 502660 }, { "epoch": 2.9879748678899847, "grad_norm": 1.2369505167007446, "learning_rate": 2.0008818362356903e-05, "loss": 0.4829586029052734, "step": 502670 }, { "epoch": 2.988034309966653, "grad_norm": 1.4396976232528687, "learning_rate": 2.0008731441056237e-05, "loss": 0.4699641227722168, "step": 502680 }, { "epoch": 2.9880937520433215, "grad_norm": 0.8744385242462158, "learning_rate": 2.0008644950244397e-05, "loss": 0.417984676361084, "step": 502690 }, { "epoch": 2.98815319411999, "grad_norm": 1.1340872049331665, "learning_rate": 2.0008558889921778e-05, "loss": 0.49218034744262695, "step": 502700 }, { "epoch": 2.988212636196658, "grad_norm": 1.2367396354675293, "learning_rate": 2.000847326008881e-05, "loss": 0.40490245819091797, "step": 502710 }, { "epoch": 2.9882720782733267, "grad_norm": 1.5669454336166382, "learning_rate": 2.0008388060745903e-05, "loss": 0.4437458038330078, "step": 502720 }, { "epoch": 2.9883315203499947, "grad_norm": 1.3100286722183228, "learning_rate": 2.0008303291893443e-05, "loss": 0.5037262916564942, "step": 502730 }, { "epoch": 2.9883909624266636, "grad_norm": 1.3533096313476562, "learning_rate": 2.000821895353186e-05, "loss": 0.4780268669128418, "step": 502740 }, { "epoch": 2.9884504045033315, "grad_norm": 1.2402548789978027, "learning_rate": 2.0008135045661545e-05, "loss": 0.4347654342651367, "step": 502750 }, { "epoch": 2.98850984658, "grad_norm": 1.1493971347808838, "learning_rate": 2.000805156828291e-05, "loss": 0.45517544746398925, "step": 502760 }, { "epoch": 2.9885692886566684, "grad_norm": 1.3578197956085205, "learning_rate": 2.0007968521396343e-05, "loss": 0.4564465045928955, "step": 502770 }, { "epoch": 2.988628730733337, "grad_norm": 1.5398701429367065, "learning_rate": 2.0007885905002237e-05, "loss": 0.4861896514892578, "step": 502780 }, { "epoch": 2.988688172810005, "grad_norm": 1.2283300161361694, "learning_rate": 2.0007803719101e-05, "loss": 0.3679476261138916, "step": 502790 }, { "epoch": 2.9887476148866736, "grad_norm": 1.0142196416854858, "learning_rate": 2.0007721963693015e-05, "loss": 0.4337261199951172, "step": 502800 }, { "epoch": 2.988807056963342, "grad_norm": 1.1987383365631104, "learning_rate": 2.0007640638778687e-05, "loss": 0.4072869300842285, "step": 502810 }, { "epoch": 2.9888664990400104, "grad_norm": 1.3526639938354492, "learning_rate": 2.000755974435839e-05, "loss": 0.4649964332580566, "step": 502820 }, { "epoch": 2.988925941116679, "grad_norm": 1.1830425262451172, "learning_rate": 2.0007479280432528e-05, "loss": 0.4400321006774902, "step": 502830 }, { "epoch": 2.9889853831933473, "grad_norm": 1.8166981935501099, "learning_rate": 2.0007399247001467e-05, "loss": 0.47656927108764646, "step": 502840 }, { "epoch": 2.9890448252700157, "grad_norm": 1.16569185256958, "learning_rate": 2.0007319644065594e-05, "loss": 0.4835536479949951, "step": 502850 }, { "epoch": 2.989104267346684, "grad_norm": 1.3076605796813965, "learning_rate": 2.00072404716253e-05, "loss": 0.4536435127258301, "step": 502860 }, { "epoch": 2.9891637094233525, "grad_norm": 1.1727511882781982, "learning_rate": 2.0007161729680958e-05, "loss": 0.4320681095123291, "step": 502870 }, { "epoch": 2.989223151500021, "grad_norm": 1.3011811971664429, "learning_rate": 2.000708341823294e-05, "loss": 0.44387173652648926, "step": 502880 }, { "epoch": 2.9892825935766894, "grad_norm": 1.2871328592300415, "learning_rate": 2.0007005537281632e-05, "loss": 0.48514084815979003, "step": 502890 }, { "epoch": 2.9893420356533573, "grad_norm": 1.1433254480361938, "learning_rate": 2.0006928086827392e-05, "loss": 0.4589847087860107, "step": 502900 }, { "epoch": 2.989401477730026, "grad_norm": 1.168121576309204, "learning_rate": 2.00068510668706e-05, "loss": 0.4533840656280518, "step": 502910 }, { "epoch": 2.989460919806694, "grad_norm": 1.3768783807754517, "learning_rate": 2.0006774477411623e-05, "loss": 0.443843412399292, "step": 502920 }, { "epoch": 2.989520361883363, "grad_norm": 1.3555701971054077, "learning_rate": 2.0006698318450826e-05, "loss": 0.4505475044250488, "step": 502930 }, { "epoch": 2.989579803960031, "grad_norm": 1.325581669807434, "learning_rate": 2.0006622589988585e-05, "loss": 0.48496103286743164, "step": 502940 }, { "epoch": 2.9896392460366994, "grad_norm": 1.5536832809448242, "learning_rate": 2.000654729202524e-05, "loss": 0.43807473182678225, "step": 502950 }, { "epoch": 2.989698688113368, "grad_norm": 1.6493771076202393, "learning_rate": 2.0006472424561162e-05, "loss": 0.47114057540893556, "step": 502960 }, { "epoch": 2.9897581301900362, "grad_norm": 1.3700087070465088, "learning_rate": 2.000639798759671e-05, "loss": 0.5058929443359375, "step": 502970 }, { "epoch": 2.9898175722667046, "grad_norm": 1.7280200719833374, "learning_rate": 2.0006323981132244e-05, "loss": 0.4543734073638916, "step": 502980 }, { "epoch": 2.989877014343373, "grad_norm": 1.0745904445648193, "learning_rate": 2.0006250405168112e-05, "loss": 0.4527024269104004, "step": 502990 }, { "epoch": 2.9899364564200415, "grad_norm": 1.4626442193984985, "learning_rate": 2.0006177259704668e-05, "loss": 0.5034044265747071, "step": 503000 }, { "epoch": 2.98999589849671, "grad_norm": 1.3647406101226807, "learning_rate": 2.0006104544742256e-05, "loss": 0.4582366943359375, "step": 503010 }, { "epoch": 2.9900553405733783, "grad_norm": 1.2518579959869385, "learning_rate": 2.0006032260281236e-05, "loss": 0.4159503936767578, "step": 503020 }, { "epoch": 2.9901147826500467, "grad_norm": 1.2328764200210571, "learning_rate": 2.0005960406321944e-05, "loss": 0.4565255165100098, "step": 503030 }, { "epoch": 2.990174224726715, "grad_norm": 1.6306766271591187, "learning_rate": 2.0005888982864738e-05, "loss": 0.43798007965087893, "step": 503040 }, { "epoch": 2.9902336668033835, "grad_norm": 1.2082206010818481, "learning_rate": 2.000581798990993e-05, "loss": 0.5097210884094239, "step": 503050 }, { "epoch": 2.990293108880052, "grad_norm": 1.1584646701812744, "learning_rate": 2.000574742745789e-05, "loss": 0.4735894203186035, "step": 503060 }, { "epoch": 2.9903525509567204, "grad_norm": 1.350511074066162, "learning_rate": 2.0005677295508942e-05, "loss": 0.4711940765380859, "step": 503070 }, { "epoch": 2.990411993033389, "grad_norm": 1.1581437587738037, "learning_rate": 2.0005607594063426e-05, "loss": 0.43552217483520506, "step": 503080 }, { "epoch": 2.9904714351100568, "grad_norm": 1.21089506149292, "learning_rate": 2.0005538323121674e-05, "loss": 0.42347893714904783, "step": 503090 }, { "epoch": 2.9905308771867256, "grad_norm": 1.41250479221344, "learning_rate": 2.0005469482684004e-05, "loss": 0.5079209327697753, "step": 503100 }, { "epoch": 2.9905903192633936, "grad_norm": 1.2379316091537476, "learning_rate": 2.0005401072750765e-05, "loss": 0.47641167640686033, "step": 503110 }, { "epoch": 2.9906497613400624, "grad_norm": 1.1597750186920166, "learning_rate": 2.000533309332228e-05, "loss": 0.44563732147216795, "step": 503120 }, { "epoch": 2.9907092034167304, "grad_norm": 1.5349658727645874, "learning_rate": 2.0005265544398874e-05, "loss": 0.42933011054992676, "step": 503130 }, { "epoch": 2.990768645493399, "grad_norm": 1.506790041923523, "learning_rate": 2.0005198425980862e-05, "loss": 0.42006449699401854, "step": 503140 }, { "epoch": 2.9908280875700672, "grad_norm": 1.355100154876709, "learning_rate": 2.000513173806857e-05, "loss": 0.42689218521118166, "step": 503150 }, { "epoch": 2.9908875296467357, "grad_norm": 1.4528872966766357, "learning_rate": 2.0005065480662307e-05, "loss": 0.4337014198303223, "step": 503160 }, { "epoch": 2.990946971723404, "grad_norm": 1.5620129108428955, "learning_rate": 2.0004999653762417e-05, "loss": 0.4629044532775879, "step": 503170 }, { "epoch": 2.9910064138000725, "grad_norm": 1.1792703866958618, "learning_rate": 2.0004934257369184e-05, "loss": 0.4178024768829346, "step": 503180 }, { "epoch": 2.991065855876741, "grad_norm": 1.3772722482681274, "learning_rate": 2.0004869291482944e-05, "loss": 0.4787330627441406, "step": 503190 }, { "epoch": 2.9911252979534093, "grad_norm": 1.4450668096542358, "learning_rate": 2.0004804756103994e-05, "loss": 0.4601594924926758, "step": 503200 }, { "epoch": 2.9911847400300777, "grad_norm": 1.3844473361968994, "learning_rate": 2.0004740651232653e-05, "loss": 0.43418493270874026, "step": 503210 }, { "epoch": 2.991244182106746, "grad_norm": 1.1586179733276367, "learning_rate": 2.000467697686921e-05, "loss": 0.4775370121002197, "step": 503220 }, { "epoch": 2.9913036241834146, "grad_norm": 1.35172700881958, "learning_rate": 2.0004613733014e-05, "loss": 0.4886017799377441, "step": 503230 }, { "epoch": 2.991363066260083, "grad_norm": 1.1630661487579346, "learning_rate": 2.0004550919667294e-05, "loss": 0.4245316982269287, "step": 503240 }, { "epoch": 2.9914225083367514, "grad_norm": 1.3143417835235596, "learning_rate": 2.000448853682941e-05, "loss": 0.432773494720459, "step": 503250 }, { "epoch": 2.99148195041342, "grad_norm": 0.7978429794311523, "learning_rate": 2.0004426584500634e-05, "loss": 0.44465045928955077, "step": 503260 }, { "epoch": 2.991541392490088, "grad_norm": 1.1865389347076416, "learning_rate": 2.0004365062681284e-05, "loss": 0.42392559051513673, "step": 503270 }, { "epoch": 2.991600834566756, "grad_norm": 1.3380321264266968, "learning_rate": 2.0004303971371633e-05, "loss": 0.45876073837280273, "step": 503280 }, { "epoch": 2.991660276643425, "grad_norm": 1.1502649784088135, "learning_rate": 2.000424331057198e-05, "loss": 0.4807705879211426, "step": 503290 }, { "epoch": 2.991719718720093, "grad_norm": 1.5272725820541382, "learning_rate": 2.0004183080282614e-05, "loss": 0.4756599426269531, "step": 503300 }, { "epoch": 2.991779160796762, "grad_norm": 1.3442083597183228, "learning_rate": 2.0004123280503824e-05, "loss": 0.48774189949035646, "step": 503310 }, { "epoch": 2.99183860287343, "grad_norm": 1.0874731540679932, "learning_rate": 2.0004063911235903e-05, "loss": 0.4748660087585449, "step": 503320 }, { "epoch": 2.9918980449500983, "grad_norm": 1.179129719734192, "learning_rate": 2.0004004972479128e-05, "loss": 0.47183523178100584, "step": 503330 }, { "epoch": 2.9919574870267667, "grad_norm": 1.4810547828674316, "learning_rate": 2.0003946464233787e-05, "loss": 0.4446870803833008, "step": 503340 }, { "epoch": 2.992016929103435, "grad_norm": 1.511324405670166, "learning_rate": 2.000388838650015e-05, "loss": 0.48288555145263673, "step": 503350 }, { "epoch": 2.9920763711801035, "grad_norm": 1.7259342670440674, "learning_rate": 2.00038307392785e-05, "loss": 0.43864879608154295, "step": 503360 }, { "epoch": 2.992135813256772, "grad_norm": 0.8954766392707825, "learning_rate": 2.000377352256911e-05, "loss": 0.4193511962890625, "step": 503370 }, { "epoch": 2.9921952553334403, "grad_norm": 1.2458969354629517, "learning_rate": 2.0003716736372264e-05, "loss": 0.41228508949279785, "step": 503380 }, { "epoch": 2.9922546974101087, "grad_norm": 1.3725237846374512, "learning_rate": 2.0003660380688215e-05, "loss": 0.46271419525146484, "step": 503390 }, { "epoch": 2.992314139486777, "grad_norm": 1.991814136505127, "learning_rate": 2.000360445551725e-05, "loss": 0.4552297592163086, "step": 503400 }, { "epoch": 2.9923735815634456, "grad_norm": 1.2307016849517822, "learning_rate": 2.000354896085963e-05, "loss": 0.44105215072631837, "step": 503410 }, { "epoch": 2.992433023640114, "grad_norm": 1.2557951211929321, "learning_rate": 2.0003493896715617e-05, "loss": 0.44630894660949705, "step": 503420 }, { "epoch": 2.9924924657167824, "grad_norm": 1.3073339462280273, "learning_rate": 2.0003439263085488e-05, "loss": 0.45116419792175294, "step": 503430 }, { "epoch": 2.992551907793451, "grad_norm": 1.1696677207946777, "learning_rate": 2.0003385059969483e-05, "loss": 0.469187068939209, "step": 503440 }, { "epoch": 2.992611349870119, "grad_norm": 1.3851001262664795, "learning_rate": 2.000333128736788e-05, "loss": 0.4699090003967285, "step": 503450 }, { "epoch": 2.9926707919467876, "grad_norm": 1.1283553838729858, "learning_rate": 2.0003277945280925e-05, "loss": 0.427918815612793, "step": 503460 }, { "epoch": 2.9927302340234556, "grad_norm": 1.1560087203979492, "learning_rate": 2.000322503370888e-05, "loss": 0.4157313346862793, "step": 503470 }, { "epoch": 2.9927896761001245, "grad_norm": 0.9560492038726807, "learning_rate": 2.0003172552651998e-05, "loss": 0.4565927505493164, "step": 503480 }, { "epoch": 2.9928491181767924, "grad_norm": 1.305816650390625, "learning_rate": 2.0003120502110523e-05, "loss": 0.47816882133483884, "step": 503490 }, { "epoch": 2.992908560253461, "grad_norm": 1.2416462898254395, "learning_rate": 2.0003068882084706e-05, "loss": 0.48419342041015623, "step": 503500 }, { "epoch": 2.9929680023301293, "grad_norm": 1.2697553634643555, "learning_rate": 2.0003017692574797e-05, "loss": 0.5004115581512452, "step": 503510 }, { "epoch": 2.9930274444067977, "grad_norm": 1.054495930671692, "learning_rate": 2.0002966933581037e-05, "loss": 0.47081298828125, "step": 503520 }, { "epoch": 2.993086886483466, "grad_norm": 1.2036817073822021, "learning_rate": 2.0002916605103683e-05, "loss": 0.47432584762573243, "step": 503530 }, { "epoch": 2.9931463285601345, "grad_norm": 1.1831293106079102, "learning_rate": 2.000286670714295e-05, "loss": 0.42610874176025393, "step": 503540 }, { "epoch": 2.993205770636803, "grad_norm": 1.2083107233047485, "learning_rate": 2.0002817239699097e-05, "loss": 0.4178898811340332, "step": 503550 }, { "epoch": 2.9932652127134713, "grad_norm": 1.197045087814331, "learning_rate": 2.000276820277236e-05, "loss": 0.4998015403747559, "step": 503560 }, { "epoch": 2.9933246547901398, "grad_norm": 0.8756071925163269, "learning_rate": 2.0002719596362972e-05, "loss": 0.4046992301940918, "step": 503570 }, { "epoch": 2.993384096866808, "grad_norm": 1.6039931774139404, "learning_rate": 2.0002671420471148e-05, "loss": 0.44313974380493165, "step": 503580 }, { "epoch": 2.9934435389434766, "grad_norm": 1.1859184503555298, "learning_rate": 2.000262367509714e-05, "loss": 0.47147159576416015, "step": 503590 }, { "epoch": 2.993502981020145, "grad_norm": 1.4430184364318848, "learning_rate": 2.000257636024117e-05, "loss": 0.41617717742919924, "step": 503600 }, { "epoch": 2.9935624230968134, "grad_norm": 1.378978967666626, "learning_rate": 2.0002529475903465e-05, "loss": 0.43391952514648435, "step": 503610 }, { "epoch": 2.993621865173482, "grad_norm": 1.1534498929977417, "learning_rate": 2.0002483022084247e-05, "loss": 0.424548864364624, "step": 503620 }, { "epoch": 2.9936813072501502, "grad_norm": 1.3996673822402954, "learning_rate": 2.0002436998783737e-05, "loss": 0.4977441310882568, "step": 503630 }, { "epoch": 2.993740749326818, "grad_norm": 1.2011750936508179, "learning_rate": 2.0002391406002155e-05, "loss": 0.4843925952911377, "step": 503640 }, { "epoch": 2.993800191403487, "grad_norm": 1.5295095443725586, "learning_rate": 2.0002346243739713e-05, "loss": 0.4212669372558594, "step": 503650 }, { "epoch": 2.993859633480155, "grad_norm": 1.3375093936920166, "learning_rate": 2.0002301511996647e-05, "loss": 0.46242570877075195, "step": 503660 }, { "epoch": 2.993919075556824, "grad_norm": 1.602129578590393, "learning_rate": 2.0002257210773157e-05, "loss": 0.4600494384765625, "step": 503670 }, { "epoch": 2.993978517633492, "grad_norm": 1.0353000164031982, "learning_rate": 2.0002213340069456e-05, "loss": 0.46918182373046874, "step": 503680 }, { "epoch": 2.9940379597101603, "grad_norm": 1.5512685775756836, "learning_rate": 2.0002169899885755e-05, "loss": 0.48428006172180177, "step": 503690 }, { "epoch": 2.9940974017868287, "grad_norm": 1.2833713293075562, "learning_rate": 2.0002126890222263e-05, "loss": 0.45202460289001467, "step": 503700 }, { "epoch": 2.994156843863497, "grad_norm": 0.8990858793258667, "learning_rate": 2.0002084311079185e-05, "loss": 0.42508764266967775, "step": 503710 }, { "epoch": 2.9942162859401655, "grad_norm": 1.1111109256744385, "learning_rate": 2.0002042162456722e-05, "loss": 0.4578214168548584, "step": 503720 }, { "epoch": 2.994275728016834, "grad_norm": 1.096908450126648, "learning_rate": 2.000200044435507e-05, "loss": 0.4462696075439453, "step": 503730 }, { "epoch": 2.9943351700935024, "grad_norm": 1.6623202562332153, "learning_rate": 2.0001959156774445e-05, "loss": 0.4740056037902832, "step": 503740 }, { "epoch": 2.9943946121701708, "grad_norm": 1.2635650634765625, "learning_rate": 2.0001918299715038e-05, "loss": 0.4748980522155762, "step": 503750 }, { "epoch": 2.994454054246839, "grad_norm": 1.4112954139709473, "learning_rate": 2.000187787317703e-05, "loss": 0.49930429458618164, "step": 503760 }, { "epoch": 2.9945134963235076, "grad_norm": 0.9150269031524658, "learning_rate": 2.0001837877160642e-05, "loss": 0.4452364444732666, "step": 503770 }, { "epoch": 2.994572938400176, "grad_norm": 1.5510905981063843, "learning_rate": 2.0001798311666044e-05, "loss": 0.4702486991882324, "step": 503780 }, { "epoch": 2.9946323804768444, "grad_norm": 1.4347336292266846, "learning_rate": 2.000175917669343e-05, "loss": 0.44279961585998534, "step": 503790 }, { "epoch": 2.994691822553513, "grad_norm": 1.328261375427246, "learning_rate": 2.0001720472242986e-05, "loss": 0.4605544090270996, "step": 503800 }, { "epoch": 2.9947512646301813, "grad_norm": 1.396345615386963, "learning_rate": 2.00016821983149e-05, "loss": 0.440902042388916, "step": 503810 }, { "epoch": 2.9948107067068497, "grad_norm": 1.1857631206512451, "learning_rate": 2.0001644354909358e-05, "loss": 0.45618319511413574, "step": 503820 }, { "epoch": 2.9948701487835176, "grad_norm": 1.6029971837997437, "learning_rate": 2.0001606942026535e-05, "loss": 0.47365608215332033, "step": 503830 }, { "epoch": 2.9949295908601865, "grad_norm": 1.3628543615341187, "learning_rate": 2.000156995966661e-05, "loss": 0.4320532321929932, "step": 503840 }, { "epoch": 2.9949890329368545, "grad_norm": 1.2839442491531372, "learning_rate": 2.0001533407829764e-05, "loss": 0.4213070869445801, "step": 503850 }, { "epoch": 2.9950484750135233, "grad_norm": 1.51363205909729, "learning_rate": 2.0001497286516175e-05, "loss": 0.5241832733154297, "step": 503860 }, { "epoch": 2.9951079170901913, "grad_norm": 1.2806204557418823, "learning_rate": 2.0001461595726012e-05, "loss": 0.4272905349731445, "step": 503870 }, { "epoch": 2.9951673591668597, "grad_norm": 1.4340850114822388, "learning_rate": 2.0001426335459432e-05, "loss": 0.40920228958129884, "step": 503880 }, { "epoch": 2.995226801243528, "grad_norm": 1.3054280281066895, "learning_rate": 2.0001391505716634e-05, "loss": 0.466217041015625, "step": 503890 }, { "epoch": 2.9952862433201966, "grad_norm": 1.2884299755096436, "learning_rate": 2.000135710649776e-05, "loss": 0.40684309005737307, "step": 503900 }, { "epoch": 2.995345685396865, "grad_norm": 1.1999775171279907, "learning_rate": 2.0001323137802974e-05, "loss": 0.45106935501098633, "step": 503910 }, { "epoch": 2.9954051274735334, "grad_norm": 1.3318467140197754, "learning_rate": 2.0001289599632453e-05, "loss": 0.44699621200561523, "step": 503920 }, { "epoch": 2.995464569550202, "grad_norm": 1.6232869625091553, "learning_rate": 2.000125649198636e-05, "loss": 0.48146328926086424, "step": 503930 }, { "epoch": 2.99552401162687, "grad_norm": 1.4946061372756958, "learning_rate": 2.0001223814864832e-05, "loss": 0.43500518798828125, "step": 503940 }, { "epoch": 2.9955834537035386, "grad_norm": 1.1470394134521484, "learning_rate": 2.0001191568268038e-05, "loss": 0.45398626327514646, "step": 503950 }, { "epoch": 2.995642895780207, "grad_norm": 1.4981852769851685, "learning_rate": 2.0001159752196132e-05, "loss": 0.4599772453308105, "step": 503960 }, { "epoch": 2.9957023378568755, "grad_norm": 1.5641727447509766, "learning_rate": 2.0001128366649267e-05, "loss": 0.46991939544677735, "step": 503970 }, { "epoch": 2.995761779933544, "grad_norm": 1.6404147148132324, "learning_rate": 2.0001097411627593e-05, "loss": 0.4554417610168457, "step": 503980 }, { "epoch": 2.9958212220102123, "grad_norm": 1.4201240539550781, "learning_rate": 2.0001066887131254e-05, "loss": 0.4608436584472656, "step": 503990 }, { "epoch": 2.9958806640868807, "grad_norm": 1.234191656112671, "learning_rate": 2.0001036793160407e-05, "loss": 0.4685208797454834, "step": 504000 }, { "epoch": 2.995940106163549, "grad_norm": 1.3750463724136353, "learning_rate": 2.0001007129715177e-05, "loss": 0.44806909561157227, "step": 504010 }, { "epoch": 2.995999548240217, "grad_norm": 1.1148611307144165, "learning_rate": 2.0000977896795724e-05, "loss": 0.4508343696594238, "step": 504020 }, { "epoch": 2.996058990316886, "grad_norm": 1.347612738609314, "learning_rate": 2.0000949094402182e-05, "loss": 0.4012903690338135, "step": 504030 }, { "epoch": 2.996118432393554, "grad_norm": 1.0242124795913696, "learning_rate": 2.0000920722534684e-05, "loss": 0.41398143768310547, "step": 504040 }, { "epoch": 2.9961778744702228, "grad_norm": 1.644431471824646, "learning_rate": 2.0000892781193366e-05, "loss": 0.4856376647949219, "step": 504050 }, { "epoch": 2.9962373165468907, "grad_norm": 1.5856481790542603, "learning_rate": 2.000086527037837e-05, "loss": 0.4325114250183105, "step": 504060 }, { "epoch": 2.996296758623559, "grad_norm": 1.3022645711898804, "learning_rate": 2.000083819008982e-05, "loss": 0.5111292839050293, "step": 504070 }, { "epoch": 2.9963562007002276, "grad_norm": 0.9225940108299255, "learning_rate": 2.0000811540327853e-05, "loss": 0.44110755920410155, "step": 504080 }, { "epoch": 2.996415642776896, "grad_norm": 1.5985947847366333, "learning_rate": 2.0000785321092588e-05, "loss": 0.5184551239013672, "step": 504090 }, { "epoch": 2.9964750848535644, "grad_norm": 1.2661759853363037, "learning_rate": 2.000075953238415e-05, "loss": 0.4087544918060303, "step": 504100 }, { "epoch": 2.996534526930233, "grad_norm": 1.0972405672073364, "learning_rate": 2.0000734174202672e-05, "loss": 0.47145566940307615, "step": 504110 }, { "epoch": 2.9965939690069012, "grad_norm": 1.3192304372787476, "learning_rate": 2.0000709246548263e-05, "loss": 0.44517054557800295, "step": 504120 }, { "epoch": 2.9966534110835696, "grad_norm": 1.0230367183685303, "learning_rate": 2.0000684749421056e-05, "loss": 0.43610467910766604, "step": 504130 }, { "epoch": 2.996712853160238, "grad_norm": 1.1820127964019775, "learning_rate": 2.0000660682821164e-05, "loss": 0.44820165634155273, "step": 504140 }, { "epoch": 2.9967722952369065, "grad_norm": 1.3144617080688477, "learning_rate": 2.0000637046748694e-05, "loss": 0.45500693321228025, "step": 504150 }, { "epoch": 2.996831737313575, "grad_norm": 1.7118818759918213, "learning_rate": 2.0000613841203756e-05, "loss": 0.4537461757659912, "step": 504160 }, { "epoch": 2.9968911793902433, "grad_norm": 1.4361310005187988, "learning_rate": 2.000059106618648e-05, "loss": 0.4614572525024414, "step": 504170 }, { "epoch": 2.9969506214669117, "grad_norm": 0.9600735902786255, "learning_rate": 2.000056872169696e-05, "loss": 0.4286990165710449, "step": 504180 }, { "epoch": 2.9970100635435797, "grad_norm": 1.3137131929397583, "learning_rate": 2.0000546807735313e-05, "loss": 0.4926793098449707, "step": 504190 }, { "epoch": 2.9970695056202485, "grad_norm": 1.172379493713379, "learning_rate": 2.0000525324301632e-05, "loss": 0.4330450534820557, "step": 504200 }, { "epoch": 2.9971289476969165, "grad_norm": 1.4413994550704956, "learning_rate": 2.0000504271396024e-05, "loss": 0.47876462936401365, "step": 504210 }, { "epoch": 2.9971883897735854, "grad_norm": 1.4157538414001465, "learning_rate": 2.00004836490186e-05, "loss": 0.4331291675567627, "step": 504220 }, { "epoch": 2.9972478318502533, "grad_norm": 1.1963443756103516, "learning_rate": 2.0000463457169443e-05, "loss": 0.4805091381072998, "step": 504230 }, { "epoch": 2.9973072739269218, "grad_norm": 1.5130112171173096, "learning_rate": 2.0000443695848652e-05, "loss": 0.45835065841674805, "step": 504240 }, { "epoch": 2.99736671600359, "grad_norm": 1.397985577583313, "learning_rate": 2.0000424365056335e-05, "loss": 0.5027919769287109, "step": 504250 }, { "epoch": 2.9974261580802586, "grad_norm": 1.129111409187317, "learning_rate": 2.0000405464792575e-05, "loss": 0.42371454238891604, "step": 504260 }, { "epoch": 2.997485600156927, "grad_norm": 1.884155035018921, "learning_rate": 2.000038699505746e-05, "loss": 0.4279582977294922, "step": 504270 }, { "epoch": 2.9975450422335954, "grad_norm": 1.3735419511795044, "learning_rate": 2.0000368955851085e-05, "loss": 0.5016373634338379, "step": 504280 }, { "epoch": 2.997604484310264, "grad_norm": 1.5894131660461426, "learning_rate": 2.0000351347173528e-05, "loss": 0.4510646820068359, "step": 504290 }, { "epoch": 2.9976639263869322, "grad_norm": 1.1773574352264404, "learning_rate": 2.0000334169024884e-05, "loss": 0.4398458003997803, "step": 504300 }, { "epoch": 2.9977233684636007, "grad_norm": 1.149342656135559, "learning_rate": 2.0000317421405222e-05, "loss": 0.4503413200378418, "step": 504310 }, { "epoch": 2.997782810540269, "grad_norm": 1.3456488847732544, "learning_rate": 2.0000301104314633e-05, "loss": 0.4351504325866699, "step": 504320 }, { "epoch": 2.9978422526169375, "grad_norm": 1.1319339275360107, "learning_rate": 2.0000285217753188e-05, "loss": 0.4455379009246826, "step": 504330 }, { "epoch": 2.997901694693606, "grad_norm": 1.0541998147964478, "learning_rate": 2.0000269761720975e-05, "loss": 0.4548606872558594, "step": 504340 }, { "epoch": 2.9979611367702743, "grad_norm": 0.9856186509132385, "learning_rate": 2.0000254736218052e-05, "loss": 0.435077428817749, "step": 504350 }, { "epoch": 2.9980205788469427, "grad_norm": 1.3607503175735474, "learning_rate": 2.0000240141244504e-05, "loss": 0.4700500965118408, "step": 504360 }, { "epoch": 2.998080020923611, "grad_norm": 1.4277805089950562, "learning_rate": 2.0000225976800384e-05, "loss": 0.4642969608306885, "step": 504370 }, { "epoch": 2.998139463000279, "grad_norm": 1.278019666671753, "learning_rate": 2.000021224288578e-05, "loss": 0.4496643543243408, "step": 504380 }, { "epoch": 2.998198905076948, "grad_norm": 1.2632778882980347, "learning_rate": 2.0000198939500746e-05, "loss": 0.45783495903015137, "step": 504390 }, { "epoch": 2.998258347153616, "grad_norm": 1.260581612586975, "learning_rate": 2.0000186066645342e-05, "loss": 0.43141927719116213, "step": 504400 }, { "epoch": 2.998317789230285, "grad_norm": 0.9964882135391235, "learning_rate": 2.0000173624319642e-05, "loss": 0.4491230010986328, "step": 504410 }, { "epoch": 2.9983772313069528, "grad_norm": 1.1348685026168823, "learning_rate": 2.0000161612523696e-05, "loss": 0.40114336013793944, "step": 504420 }, { "epoch": 2.998436673383621, "grad_norm": 1.1178969144821167, "learning_rate": 2.000015003125757e-05, "loss": 0.44685754776000974, "step": 504430 }, { "epoch": 2.9984961154602896, "grad_norm": 1.2195415496826172, "learning_rate": 2.0000138880521315e-05, "loss": 0.41132144927978515, "step": 504440 }, { "epoch": 2.998555557536958, "grad_norm": 1.260064959526062, "learning_rate": 2.0000128160314973e-05, "loss": 0.48091373443603513, "step": 504450 }, { "epoch": 2.9986149996136264, "grad_norm": 1.2178831100463867, "learning_rate": 2.0000117870638612e-05, "loss": 0.44896998405456545, "step": 504460 }, { "epoch": 2.998674441690295, "grad_norm": 1.322615385055542, "learning_rate": 2.0000108011492272e-05, "loss": 0.45820064544677735, "step": 504470 }, { "epoch": 2.9987338837669633, "grad_norm": 1.2070167064666748, "learning_rate": 2.0000098582876015e-05, "loss": 0.4302203178405762, "step": 504480 }, { "epoch": 2.9987933258436317, "grad_norm": 1.3835958242416382, "learning_rate": 2.0000089584789858e-05, "loss": 0.4133628845214844, "step": 504490 }, { "epoch": 2.9988527679203, "grad_norm": 1.4721324443817139, "learning_rate": 2.000008101723386e-05, "loss": 0.49434795379638674, "step": 504500 }, { "epoch": 2.9989122099969685, "grad_norm": 1.4135600328445435, "learning_rate": 2.0000072880208082e-05, "loss": 0.49072632789611814, "step": 504510 }, { "epoch": 2.998971652073637, "grad_norm": 1.4469993114471436, "learning_rate": 2.0000065173712528e-05, "loss": 0.4681534290313721, "step": 504520 }, { "epoch": 2.9990310941503053, "grad_norm": 1.11445951461792, "learning_rate": 2.000005789774725e-05, "loss": 0.4594071865081787, "step": 504530 }, { "epoch": 2.9990905362269737, "grad_norm": 1.0661057233810425, "learning_rate": 2.0000051052312278e-05, "loss": 0.4817944526672363, "step": 504540 }, { "epoch": 2.999149978303642, "grad_norm": 1.8802989721298218, "learning_rate": 2.000004463740766e-05, "loss": 0.4480271339416504, "step": 504550 }, { "epoch": 2.9992094203803106, "grad_norm": 0.9797672033309937, "learning_rate": 2.0000038653033416e-05, "loss": 0.42749910354614257, "step": 504560 }, { "epoch": 2.9992688624569785, "grad_norm": 1.3889026641845703, "learning_rate": 2.0000033099189573e-05, "loss": 0.4496657371520996, "step": 504570 }, { "epoch": 2.9993283045336474, "grad_norm": 1.2639446258544922, "learning_rate": 2.0000027975876147e-05, "loss": 0.42672052383422854, "step": 504580 }, { "epoch": 2.9993877466103154, "grad_norm": 1.2366135120391846, "learning_rate": 2.0000023283093184e-05, "loss": 0.4391790866851807, "step": 504590 }, { "epoch": 2.9994471886869842, "grad_norm": 1.2601205110549927, "learning_rate": 2.0000019020840704e-05, "loss": 0.43431844711303713, "step": 504600 }, { "epoch": 2.999506630763652, "grad_norm": 1.1931517124176025, "learning_rate": 2.0000015189118716e-05, "loss": 0.46694116592407225, "step": 504610 }, { "epoch": 2.9995660728403206, "grad_norm": 1.4504241943359375, "learning_rate": 2.0000011787927237e-05, "loss": 0.4290257453918457, "step": 504620 }, { "epoch": 2.999625514916989, "grad_norm": 1.3623840808868408, "learning_rate": 2.00000088172663e-05, "loss": 0.4783351421356201, "step": 504630 }, { "epoch": 2.9996849569936574, "grad_norm": 1.1794124841690063, "learning_rate": 2.0000006277135904e-05, "loss": 0.41489353179931643, "step": 504640 }, { "epoch": 2.999744399070326, "grad_norm": 1.345543622970581, "learning_rate": 2.000000416753606e-05, "loss": 0.4806215286254883, "step": 504650 }, { "epoch": 2.9998038411469943, "grad_norm": 1.4212751388549805, "learning_rate": 2.0000002488466784e-05, "loss": 0.41163482666015627, "step": 504660 }, { "epoch": 2.9998632832236627, "grad_norm": 1.1118172407150269, "learning_rate": 2.0000001239928094e-05, "loss": 0.4427067279815674, "step": 504670 }, { "epoch": 2.999922725300331, "grad_norm": 1.0321742296218872, "learning_rate": 2.000000042191998e-05, "loss": 0.45934104919433594, "step": 504680 }, { "epoch": 2.9999821673769995, "grad_norm": 1.584671974182129, "learning_rate": 2.0000000034442452e-05, "loss": 0.46037139892578127, "step": 504690 } ], "logging_steps": 10, "max_steps": 504693, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.291171762935064e+19, "train_batch_size": 4, "trial_name": null, "trial_params": null }